[SCTP]: Fix couple of races between sctp_peeloff() and sctp_rcv().

Validate and update the sk in sctp_rcv() to avoid the race where an
assoc/ep could move to a different socket after we get the sk, but before
the skb is added to the backlog.

Also migrate the skb's in backlog queue to new sk when doing a peeloff.

Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index a553f39..e673b2c 100644 (file)
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -175,6 +175,8 @@ void sctp_icmp_frag_needed(struct sock *, struct sctp_association *,
 void sctp_icmp_proto_unreachable(struct sock *sk,
                                 struct sctp_association *asoc,
                                 struct sctp_transport *t);
+void sctp_backlog_migrate(struct sctp_association *assoc,
+                         struct sock *oldsk, struct sock *newsk);
 
 /*
  *  Section:  Macros, externs, and inlines

diff --git a/net/sctp/input.c b/net/sctp/input.c
index c463e40..71fd563 100644 (file)
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -257,12 +257,21 @@ int sctp_rcv(struct sk_buff *skb)
         */
        sctp_bh_lock_sock(sk);
 
+       /* It is possible that the association could have moved to a different
+        * socket if it is peeled off. If so, update the sk.
+        */ 
+       if (sk != rcvr->sk) {
+               sctp_bh_lock_sock(rcvr->sk);
+               sctp_bh_unlock_sock(sk);
+               sk = rcvr->sk;
+       }
+
        if (sock_owned_by_user(sk))
                sk_add_backlog(sk, skb);
        else
                sctp_backlog_rcv(sk, skb);
 
-       /* Release the sock and the sock ref we took in the lookup calls. 
+       /* Release the sock and the sock ref we took in the lookup calls.
         * The asoc/ep ref will be released in sctp_backlog_rcv.
         */
        sctp_bh_unlock_sock(sk);
@@ -297,6 +306,9 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
        struct sctp_ep_common *rcvr = NULL;
 
        rcvr = chunk->rcvr;
+
+       BUG_TRAP(rcvr->sk == sk);
+
        if (rcvr->dead) {
                sctp_chunk_free(chunk);
        } else {
@@ -313,6 +325,27 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
         return 0;
 }
 
+void sctp_backlog_migrate(struct sctp_association *assoc, 
+                         struct sock *oldsk, struct sock *newsk)
+{
+       struct sk_buff *skb;
+       struct sctp_chunk *chunk;
+
+       skb = oldsk->sk_backlog.head;
+       oldsk->sk_backlog.head = oldsk->sk_backlog.tail = NULL;
+       while (skb != NULL) {
+               struct sk_buff *next = skb->next;
+
+               chunk = SCTP_INPUT_CB(skb)->chunk;
+               skb->next = NULL;
+               if (&assoc->base == chunk->rcvr)
+                       sk_add_backlog(newsk, skb);
+               else
+                       sk_add_backlog(oldsk, skb);
+               skb = next;
+       }
+}
+
 /* Handle icmp frag needed error. */
 void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
                           struct sctp_transport *t, __u32 pmtu)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6a0b1af..fb1821d 100644 (file)
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5602,8 +5602,12 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
         */
        newsp->type = type;
 
+       spin_lock_bh(&oldsk->sk_lock.slock);
+       /* Migrate the backlog from oldsk to newsk. */
+       sctp_backlog_migrate(assoc, oldsk, newsk);
        /* Migrate the association to the new socket. */
        sctp_assoc_migrate(assoc, newsk);
+       spin_unlock_bh(&oldsk->sk_lock.slock);
 
        /* If the association on the newsk is already closed before accept()
         * is called, set RCV_SHUTDOWN flag.