net: unix: fix inflight counting bug in garbage collector

Previously I assumed that the receive queues of candidates don't
change during the GC.  This is only half true, nothing can be received
from the queues (see comment in unix_gc()), but buffers could be added
through the other half of the socket pair, which may still have file
descriptors referring to it.

This can result in inc_inflight_move_tail() erronously increasing the
"inflight" counter for a unix socket for which dec_inflight() wasn't
previously called.  This in turn can trigger the "BUG_ON(total_refs <
inflight_refs)" in a later garbage collection run.

Fix this by only manipulating the "inflight" counter for sockets which
are candidates themselves.  Duplicating the file references in
unix_attach_fds() is also needed to prevent a socket becoming a
candidate for GC while the skb that contains it is not yet queued.

Reported-by: Andrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
CC: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 24 insertions, 7 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4d3c6071b9a4..eb90f77bb0e2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1302,14 +1302,23 @@ static void unix_destruct_fds(struct sk_buff *skb)
         sock_wfree(skb);
 }
 
-static void unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
         int i;
+
+        /*
+         * Need to duplicate file references for the sake of garbage
+         * collection.  Otherwise a socket in the fps might become a
+         * candidate for GC while the skb is not yet queued.
+         */
+        UNIXCB(skb).fp = scm_fp_dup(scm->fp);
+        if (!UNIXCB(skb).fp)
+                return -ENOMEM;
+
         for (i=scm->fp->count-1; i>=0; i--)
                 unix_inflight(scm->fp->fp[i]);
-        UNIXCB(skb).fp = scm->fp;
         skb->destructor = unix_destruct_fds;
-        scm->fp = NULL;
+        return 0;
 }
 
 /*
@@ -1368,8 +1377,11 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
                 goto out;
 
         memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
-        if (siocb->scm->fp)
-                unix_attach_fds(siocb->scm, skb);
+        if (siocb->scm->fp) {
+                err = unix_attach_fds(siocb->scm, skb);
+                if (err)
+                        goto out_free;
+        }
         unix_get_secdata(siocb->scm, skb);
 
         skb_reset_transport_header(skb);
@@ -1538,8 +1550,13 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
                 size = min_t(int, size, skb_tailroom(skb));
 
                 memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
-                if (siocb->scm->fp)
-                        unix_attach_fds(siocb->scm, skb);
+                if (siocb->scm->fp) {
+                        err = unix_attach_fds(siocb->scm, skb);
+                        if (err) {
+                                kfree_skb(skb);
+                                goto out_err;
+                        }
+                }
 
                 if ((err = memcpy_fromiovec(skb_put(skb,size), msg->msg_iov, size)) != 0) {
                         kfree_skb(skb);