From 6552df6df2fcfc281c64dea191fef144d5a188c5 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Thu, 6 May 2010 00:56:07 -0700 Subject: [PATCH] sctp: Fix a race between ICMP protocol unreachable and connect() commit 50b5d6ad63821cea324a5a7a19854d4de1a0a819 upstream. ICMP protocol unreachable handling completely disregarded the fact that the user may have locked the socket. It proceeded to destroy the association, even though the user may have held the lock and had a ref on the association. This resulted in the following: Attempt to release alive inet socket f6afcc00 ========================= [ BUG: held lock freed! ] ------------------------- somenu/2672 is freeing memory f6afcc00-f6afcfff, with a lock still held there! (sk_lock-AF_INET){+.+.+.}, at: [] sctp_connect+0x13/0x4c 1 lock held by somenu/2672: #0: (sk_lock-AF_INET){+.+.+.}, at: [] sctp_connect+0x13/0x4c stack backtrace: Pid: 2672, comm: somenu Not tainted 2.6.32-telco #55 Call Trace: [] ? printk+0xf/0x11 [] debug_check_no_locks_freed+0xce/0xff [] kmem_cache_free+0x21/0x66 [] __sk_free+0x9d/0xab [] sk_free+0x1c/0x1e [] sctp_association_put+0x32/0x89 [] __sctp_connect+0x36d/0x3f4 [] ? sctp_connect+0x13/0x4c [] ? autoremove_wake_function+0x0/0x33 [] sctp_connect+0x31/0x4c [] inet_dgram_connect+0x4b/0x55 [] sys_connect+0x54/0x71 [] ? lock_release_non_nested+0x88/0x239 [] ? might_fault+0x42/0x7c [] ? might_fault+0x42/0x7c [] sys_socketcall+0x6d/0x178 [] ? trace_hardirqs_on_thunk+0xc/0x10 [] syscall_call+0x7/0xb This was because the sctp_wait_for_connect() would aqcure the socket lock and then proceed to release the last reference count on the association, thus cause the fully destruction path to finish freeing the socket. The simplest solution is to start a very short timer in case the socket is owned by user. When the timer expires, we can do some verification and be able to do the release properly. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/sctp/sm.h | 1 + include/net/sctp/structs.h | 3 +++ net/sctp/input.c | 22 ++++++++++++++++++---- net/sctp/sm_sideeffect.c | 35 +++++++++++++++++++++++++++++++++++ net/sctp/transport.c | 2 ++ 5 files changed, 59 insertions(+), 4 deletions(-) diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index c1dd89365833..76abe6cb7e2f 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -278,6 +278,7 @@ int sctp_do_sm(sctp_event_t event_type, sctp_subtype_t subtype, /* 2nd level prototypes */ void sctp_generate_t3_rtx_event(unsigned long peer); void sctp_generate_heartbeat_event(unsigned long peer); +void sctp_generate_proto_unreach_event(unsigned long peer); void sctp_ootb_pkt_free(struct sctp_packet *); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 89e54e932368..88daa54eeef8 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1008,6 +1008,9 @@ struct sctp_transport { /* Heartbeat timer is per destination. */ struct timer_list hb_timer; + /* Timer to handle ICMP proto unreachable envets */ + struct timer_list proto_unreach_timer; + /* Since we're using per-destination retransmission timers * (see above), we're also using per-destination "transmitted" * queues. This probably ought to be a private struct diff --git a/net/sctp/input.c b/net/sctp/input.c index c0c973e67add..254afea4c1af 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -427,11 +427,25 @@ void sctp_icmp_proto_unreachable(struct sock *sk, { SCTP_DEBUG_PRINTK("%s\n", __func__); - sctp_do_sm(SCTP_EVENT_T_OTHER, - SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), - asoc->state, asoc->ep, asoc, t, - GFP_ATOMIC); + if (sock_owned_by_user(sk)) { + if (timer_pending(&t->proto_unreach_timer)) + return; + else { + if (!mod_timer(&t->proto_unreach_timer, + jiffies + (HZ/20))) + sctp_association_hold(asoc); + } + } else { + if (timer_pending(&t->proto_unreach_timer) && + del_timer(&t->proto_unreach_timer)) + sctp_association_put(asoc); + + sctp_do_sm(SCTP_EVENT_T_OTHER, + SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), + asoc->state, asoc->ep, asoc, t, + GFP_ATOMIC); + } } /* Common lookup code for icmp/icmpv6 error handler. */ diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index efa516b47e81..306bb8b07a51 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -397,6 +397,41 @@ out_unlock: sctp_transport_put(transport); } +/* Handle the timeout of the ICMP protocol unreachable timer. Trigger + * the correct state machine transition that will close the association. + */ +void sctp_generate_proto_unreach_event(unsigned long data) +{ + struct sctp_transport *transport = (struct sctp_transport *) data; + struct sctp_association *asoc = transport->asoc; + + sctp_bh_lock_sock(asoc->base.sk); + if (sock_owned_by_user(asoc->base.sk)) { + SCTP_DEBUG_PRINTK("%s:Sock is busy.\n", __func__); + + /* Try again later. */ + if (!mod_timer(&transport->proto_unreach_timer, + jiffies + (HZ/20))) + sctp_association_hold(asoc); + goto out_unlock; + } + + /* Is this structure just waiting around for us to actually + * get destroyed? + */ + if (asoc->base.dead) + goto out_unlock; + + sctp_do_sm(SCTP_EVENT_T_OTHER, + SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), + asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); + +out_unlock: + sctp_bh_unlock_sock(asoc->base.sk); + sctp_association_put(asoc); +} + + /* Inject a SACK Timeout event into the state machine. */ static void sctp_generate_sack_event(unsigned long data) { diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 37a1184d789f..e04c9f844abf 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -108,6 +108,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, (unsigned long)peer); setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event, (unsigned long)peer); + setup_timer(&peer->proto_unreach_timer, + sctp_generate_proto_unreach_event, (unsigned long)peer); /* Initialize the 64-bit random nonce sent with heartbeat. */ get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); -- 2.34.1