From: Mike Maloney <maloney@google.com>
Date: Tue, 28 Nov 2017 10:44:29 -0500
Subject: packet: fix crash in fanout_demux_rollover()
Patch-mainline: v4.15-rc2
Git-commit: 57f015f5eccf25fd4a3336fe3cbbee920a8fba6f
References: bsc#1076830

syzkaller found a race condition fanout_demux_rollover() while removing
a packet socket from a fanout group.

po->rollover is read and operated on during packet_rcv_fanout(), via
fanout_demux_rollover(), but the pointer is currently cleared before the
synchronization in packet_release().   It is safer to delay the cleanup
until after synchronize_net() has been called, ensuring all calls to
packet_rcv_fanout() for this socket have finished.

To further simplify synchronization around the rollover structure, set
po->rollover in fanout_add() only if there are no errors.  This removes
the need for rcu in the struct and in the call to
packet_getsockopt(..., PACKET_ROLLOVER_STATS, ...).

Crashing stack trace:
 fanout_demux_rollover+0xb6/0x4d0 net/packet/af_packet.c:1392
 packet_rcv_fanout+0x649/0x7c8 net/packet/af_packet.c:1487
 dev_queue_xmit_nit+0x835/0xc10 net/core/dev.c:1953
 xmit_one net/core/dev.c:2975 [inline]
 dev_hard_start_xmit+0x16b/0xac0 net/core/dev.c:2995
 __dev_queue_xmit+0x17a4/0x2050 net/core/dev.c:3476
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3509
 neigh_connected_output+0x489/0x720 net/core/neighbour.c:1379
 neigh_output include/net/neighbour.h:482 [inline]
 ip6_finish_output2+0xad1/0x22a0 net/ipv6/ip6_output.c:120
 ip6_finish_output+0x2f9/0x920 net/ipv6/ip6_output.c:146
 NF_HOOK_COND include/linux/netfilter.h:239 [inline]
 ip6_output+0x1f4/0x850 net/ipv6/ip6_output.c:163
 dst_output include/net/dst.h:459 [inline]
 NF_HOOK.constprop.35+0xff/0x630 include/linux/netfilter.h:250
 mld_sendpack+0x6a8/0xcc0 net/ipv6/mcast.c:1660
 mld_send_initial_cr.part.24+0x103/0x150 net/ipv6/mcast.c:2072
 mld_send_initial_cr net/ipv6/mcast.c:2056 [inline]
 ipv6_mc_dad_complete+0x99/0x130 net/ipv6/mcast.c:2079
 addrconf_dad_completed+0x595/0x970 net/ipv6/addrconf.c:4039
 addrconf_dad_work+0xac9/0x1160 net/ipv6/addrconf.c:3971
 process_one_work+0xbf0/0x1bc0 kernel/workqueue.c:2113
 worker_thread+0x223/0x1990 kernel/workqueue.c:2247
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:432

Fixes: 0648ab70afe6 ("packet: rollover prepare: per-socket state")
Fixes: 509c7a1ecc860 ("packet: avoid panic in packet_getsockopt()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Mike Maloney <maloney@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Michal Kubecek <mkubecek@suse.cz>

---
 net/packet/af_packet.c | 32 ++++++++++----------------------
 net/packet/internal.h  |  1 -
 2 files changed, 10 insertions(+), 23 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c4bc46e112ac..7abb9180667f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1700,7 +1700,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		atomic_long_set(&rollover->num, 0);
 		atomic_long_set(&rollover->num_huge, 0);
 		atomic_long_set(&rollover->num_failed, 0);
-		po->rollover = rollover;
 	}
 
 	if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) {
@@ -1758,6 +1757,8 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		if (atomic_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
 			__dev_remove_pack(&po->prot_hook);
 			po->fanout = match;
+			po->rollover = rollover;
+			rollover = NULL;
 			atomic_inc(&match->sk_ref);
 			__fanout_link(sk, po);
 			err = 0;
@@ -1771,10 +1772,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	}
 
 out:
-	if (err && rollover) {
-		kfree_rcu(rollover, rcu);
-		po->rollover = NULL;
-	}
+	kfree(rollover);
 	mutex_unlock(&fanout_mutex);
 	return err;
 }
@@ -1798,11 +1796,6 @@ static struct packet_fanout *fanout_release(struct sock *sk)
 			list_del(&f->list);
 		else
 			f = NULL;
-
-		if (po->rollover) {
-			kfree_rcu(po->rollover, rcu);
-			po->rollover = NULL;
-		}
 	}
 	mutex_unlock(&fanout_mutex);
 
@@ -3044,6 +3037,7 @@ static int packet_release(struct socket *sock)
 	synchronize_net();
 
 	if (f) {
+		kfree(po->rollover);
 		fanout_release_data(f);
 		kfree(f);
 	}
@@ -3863,7 +3857,6 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	void *data = &val;
 	union tpacket_stats_u st;
 	struct tpacket_rollover_stats rstats;
-	struct packet_rollover *rollover;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3942,18 +3935,13 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		       0);
 		break;
 	case PACKET_ROLLOVER_STATS:
-		rcu_read_lock();
-		rollover = rcu_dereference(po->rollover);
-		if (rollover) {
-			rstats.tp_all = atomic_long_read(&rollover->num);
-			rstats.tp_huge = atomic_long_read(&rollover->num_huge);
-			rstats.tp_failed = atomic_long_read(&rollover->num_failed);
-			data = &rstats;
-			lv = sizeof(rstats);
-		}
-		rcu_read_unlock();
-		if (!rollover)
+		if (!po->rollover)
 			return -EINVAL;
+		rstats.tp_all = atomic_long_read(&po->rollover->num);
+		rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
+		rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
+		data = &rstats;
+		lv = sizeof(rstats);
 		break;
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 9ee46314b7d7..d55bfc34d6b3 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -92,7 +92,6 @@ struct packet_fanout {
 
 struct packet_rollover {
 	int			sock;
-	struct rcu_head		rcu;
 	atomic_long_t		num;
 	atomic_long_t		num_huge;
 	atomic_long_t		num_failed;
-- 
2.15.1