From 55432d2b543a4b6dfae54f5c432a566877a85d90 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Jun 2012 03:00:18 +0000 Subject: inetpeer: fix a race in inetpeer_gc_worker() commit 5faa5df1fa2024 (inetpeer: Invalidate the inetpeer tree along with the routing cache) added a race : Before freeing an inetpeer, we must respect a RCU grace period, and make sure no user will attempt to increase refcnt. inetpeer_invalidate_tree() waits for a RCU grace period before inserting inetpeer tree into gc_list and waking the worker. At that time, no concurrent lookup can find a inetpeer in this tree. Signed-off-by: Eric Dumazet Cc: Steffen Klassert Acked-by: Steffen Klassert Signed-off-by: David S. Miller --- net/ipv4/inetpeer.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d4d61b694fab..dfba343b2509 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -560,6 +560,17 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) } EXPORT_SYMBOL(inet_peer_xrlim_allow); +static void inetpeer_inval_rcu(struct rcu_head *head) +{ + struct inet_peer *p = container_of(head, struct inet_peer, gc_rcu); + + spin_lock_bh(&gc_lock); + list_add_tail(&p->gc_list, &gc_list); + spin_unlock_bh(&gc_lock); + + schedule_delayed_work(&gc_work, gc_delay); +} + void inetpeer_invalidate_tree(int family) { struct inet_peer *old, *new, *prev; @@ -576,10 +587,7 @@ void inetpeer_invalidate_tree(int family) prev = cmpxchg(&base->root, old, new); if (prev == old) { base->total = 0; - spin_lock(&gc_lock); - list_add_tail(&prev->gc_list, &gc_list); - spin_unlock(&gc_lock); - schedule_delayed_work(&gc_work, gc_delay); + call_rcu(&prev->gc_rcu, inetpeer_inval_rcu); } out: -- cgit v1.2.2 From 2d8dbb04c63e5369988f008bc4df3359c01d8812 Mon Sep 17 00:00:00 2001 From: Vincent Bernat Date: Tue, 5 Jun 2012 03:41:42 +0000 Subject: snmp: fix OutOctets counter to include forwarded datagrams RFC 4293 defines ipIfStatsOutOctets (similar definition for ipSystemStatsOutOctets): The total number of octets in IP datagrams delivered to the lower layers for transmission. Octets from datagrams counted in ipIfStatsOutTransmits MUST be counted here. And ipIfStatsOutTransmits: The total number of IP datagrams that this entity supplied to the lower layers for transmission. This includes datagrams generated locally and those forwarded by this entity. Therefore, IPSTATS_MIB_OUTOCTETS must be incremented when incrementing IPSTATS_MIB_OUTFORWDATAGRAMS. IP_UPD_PO_STATS is not used since ipIfStatsOutRequests must not include forwarded datagrams: The total number of IP datagrams that local IP user-protocols (including ICMP) supplied to IP in requests for transmission. Note that this counter does not include any datagrams counted in ipIfStatsOutForwDatagrams. Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller --- net/ipv4/ip_forward.c | 1 + net/ipv4/ipmr.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e5c44fc586ab..ab09b126423c 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -44,6 +44,7 @@ static int ip_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9e519ad6db5..c94bbc6f2ba3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1574,6 +1574,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); -- cgit v1.2.2 From 89d7ae34cdda4195809a5a987f697a517a2a3177 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 17 Jul 2012 11:07:47 +0000 Subject: cipso: don't follow a NULL pointer when setsockopt() is called As reported by Alan Cox, and verified by Lin Ming, when a user attempts to add a CIPSO option to a socket using the CIPSO_V4_TAG_LOCAL tag the kernel dies a terrible death when it attempts to follow a NULL pointer (the skb argument to cipso_v4_validate() is NULL when called via the setsockopt() syscall). This patch fixes this by first checking to ensure that the skb is non-NULL before using it to find the incoming network interface. In the unlikely case where the skb is NULL and the user attempts to add a CIPSO option with the _TAG_LOCAL tag we return an error as this is not something we want to allow. A simple reproducer, kindly supplied by Lin Ming, although you must have the CIPSO DOI #3 configure on the system first or you will be caught early in cipso_v4_validate(): #include #include #include #include #include struct local_tag { char type; char length; char info[4]; }; struct cipso { char type; char length; char doi[4]; struct local_tag local; }; int main(int argc, char **argv) { int sockfd; struct cipso cipso = { .type = IPOPT_CIPSO, .length = sizeof(struct cipso), .local = { .type = 128, .length = sizeof(struct local_tag), }, }; memset(cipso.doi, 0, 4); cipso.doi[3] = 3; sockfd = socket(AF_INET, SOCK_DGRAM, 0); #define SOL_IP 0 setsockopt(sockfd, SOL_IP, IP_OPTIONS, &cipso, sizeof(struct cipso)); return 0; } CC: Lin Ming Reported-by: Alan Cox Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- net/ipv4/cipso_ipv4.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c48adc565e92..667c1d4ca984 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1725,8 +1725,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) case CIPSO_V4_TAG_LOCAL: /* This is a non-standard tag that we only allow for * local connections, so if the incoming interface is - * not the loopback device drop the packet. */ - if (!(skb->dev->flags & IFF_LOOPBACK)) { + * not the loopback device drop the packet. Further, + * there is no legitimate reason for setting this from + * userspace so reject it if skb is NULL. */ + if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) { err_offset = opt_iter; goto validate_return_locked; } -- cgit v1.2.2