From 85fbaa75037d0b6b786ff18658ddf0b4014ce2a4 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sat, 23 Nov 2013 00:46:12 +0100 Subject: inet: fix addr_len/msg->msg_namelen assignment in recv_error and rxpmtu functions Commit bceaa90240b6019ed73b49965eac7d167610be69 ("inet: prevent leakage of uninitialized memory to user in recv syscalls") conditionally updated addr_len if the msg_name is written to. The recv_error and rxpmtu functions relied on the recvmsg functions to set up addr_len before. As this does not happen any more we have to pass addr_len to those functions as well and set it to the size of the corresponding sockaddr length. This broke traceroute and such. Fixes: bceaa90240b6 ("inet: prevent leakage of uninitialized memory to user in recv syscalls") Reported-by: Brad Spengler Reported-by: Tom Labanowski Cc: mpb Cc: David S. Miller Cc: Eric Dumazet Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/udp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5944d7d668d..44dfaa09b58 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1236,7 +1236,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, bool slow; if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), -- cgit v1.2.3-70-g09d2 From d3f7d56a7a4671d395e8af87071068a195257bf6 Mon Sep 17 00:00:00 2001 From: Shawn Landden Date: Sun, 24 Nov 2013 22:36:28 -0800 Subject: net: update consumers of MSG_MORE to recognize MSG_SENDPAGE_NOTLAST Commit 35f9c09fe (tcp: tcp_sendpages() should call tcp_push() once) added an internal flag MSG_SENDPAGE_NOTLAST, similar to MSG_MORE. algif_hash, algif_skcipher, and udp used MSG_MORE from tcp_sendpages() and need to see the new flag as identical to MSG_MORE. This fixes sendfile() on AF_ALG. v3: also fix udp Cc: Tom Herbert Cc: Eric Dumazet Cc: David S. Miller Cc: # 3.4.x + 3.2.x Reported-and-tested-by: Shawn Landden Original-patch: Richard Weinberger Signed-off-by: Shawn Landden Signed-off-by: David S. Miller --- crypto/algif_hash.c | 3 +++ crypto/algif_skcipher.c | 3 +++ net/ipv4/udp.c | 3 +++ 3 files changed, 9 insertions(+) (limited to 'net/ipv4/udp.c') diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index ef5356cd280..850246206b1 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -114,6 +114,9 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, struct hash_ctx *ctx = ask->private; int err; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + lock_sock(sk); sg_init_table(ctx->sgl.sg, 1); sg_set_page(ctx->sgl.sg, page, size, offset); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 6a6dfc062d2..a19c027b29b 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -378,6 +378,9 @@ static ssize_t skcipher_sendpage(struct socket *sock, struct page *page, struct skcipher_sg_list *sgl; int err = -EINVAL; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + lock_sock(sk); if (!ctx->more && ctx->used) goto unlock; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 44dfaa09b58..bf2b85b2549 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1098,6 +1098,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, struct udp_sock *up = udp_sk(sk); int ret; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + if (!up->pending) { struct msghdr msg = { .msg_flags = flags|MSG_MORE }; -- cgit v1.2.3-70-g09d2 From f1d8cba61c3c4b1eb88e507249c4cb8d635d9a76 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 28 Nov 2013 09:51:22 -0800 Subject: inet: fix possible seqlock deadlocks In commit c9e9042994d3 ("ipv4: fix possible seqlock deadlock") I left another places where IP_INC_STATS_BH() were improperly used. udp_sendmsg(), ping_v4_sendmsg() and tcp_v4_connect() are called from process context, not from softirq context. This was detected by lockdep seqlock support. Reported-by: jongman heo Fixes: 584bdf8cbdf6 ("[IPV4]: Fix "ipOutNoRoutes" counter error for TCP and UDP") Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Signed-off-by: Eric Dumazet Cc: Hannes Frederic Sowa Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/ping.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 840cf1b9e6e..242e7f4ed6f 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -772,7 +772,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 59a6f8b90cd..06721392475 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -177,7 +177,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); return err; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index bf2b85b2549..44f6a20fa29 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -999,7 +999,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } -- cgit v1.2.3-70-g09d2 From 8afdd99a1315e759de04ad6e2344f0c5f17ecb1b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Dec 2013 18:07:23 -0800 Subject: udp: ipv4: fix an use after free in __udp4_lib_rcv() Dave Jones reported a use after free in UDP stack : [ 5059.434216] ========================= [ 5059.434314] [ BUG: held lock freed! ] [ 5059.434420] 3.13.0-rc3+ #9 Not tainted [ 5059.434520] ------------------------- [ 5059.434620] named/863 is freeing memory ffff88005e960000-ffff88005e96061f, with a lock still held there! [ 5059.434815] (slock-AF_INET){+.-...}, at: [] udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.435012] 3 locks held by named/863: [ 5059.435086] #0: (rcu_read_lock){.+.+..}, at: [] __netif_receive_skb_core+0x11d/0x940 [ 5059.435295] #1: (rcu_read_lock){.+.+..}, at: [] ip_local_deliver_finish+0x3e/0x410 [ 5059.435500] #2: (slock-AF_INET){+.-...}, at: [] udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.435734] stack backtrace: [ 5059.435858] CPU: 0 PID: 863 Comm: named Not tainted 3.13.0-rc3+ #9 [loadavg: 0.21 0.06 0.06 1/115 1365] [ 5059.436052] Hardware name: /D510MO, BIOS MOPNV10J.86A.0175.2010.0308.0620 03/08/2010 [ 5059.436223] 0000000000000002 ffff88007e203ad8 ffffffff8153a372 ffff8800677130e0 [ 5059.436390] ffff88007e203b10 ffffffff8108cafa ffff88005e960000 ffff88007b00cfc0 [ 5059.436554] ffffea00017a5800 ffffffff8141c490 0000000000000246 ffff88007e203b48 [ 5059.436718] Call Trace: [ 5059.436769] [] dump_stack+0x4d/0x66 [ 5059.436904] [] debug_check_no_locks_freed+0x15a/0x160 [ 5059.437037] [] ? __sk_free+0x110/0x230 [ 5059.437147] [] kmem_cache_free+0x6a/0x150 [ 5059.437260] [] __sk_free+0x110/0x230 [ 5059.437364] [] sk_free+0x19/0x20 [ 5059.437463] [] sock_edemux+0x25/0x40 [ 5059.437567] [] sock_queue_rcv_skb+0x81/0x280 [ 5059.437685] [] ? udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.437805] [] __udp_queue_rcv_skb+0x42/0x240 [ 5059.437925] [] ? _raw_spin_lock+0x65/0x70 [ 5059.438038] [] udp_queue_rcv_skb+0x26b/0x4b0 [ 5059.438155] [] __udp4_lib_rcv+0x152/0xb00 [ 5059.438269] [] udp_rcv+0x15/0x20 [ 5059.438367] [] ip_local_deliver_finish+0x10f/0x410 [ 5059.438492] [] ? ip_local_deliver_finish+0x3e/0x410 [ 5059.438621] [] ip_local_deliver+0x43/0x80 [ 5059.438733] [] ip_rcv_finish+0x140/0x5a0 [ 5059.438843] [] ip_rcv+0x296/0x3f0 [ 5059.438945] [] __netif_receive_skb_core+0x742/0x940 [ 5059.439074] [] ? __netif_receive_skb_core+0x11d/0x940 [ 5059.442231] [] ? trace_hardirqs_on+0xd/0x10 [ 5059.442231] [] __netif_receive_skb+0x13/0x60 [ 5059.442231] [] netif_receive_skb+0x1e/0x1f0 [ 5059.442231] [] napi_gro_receive+0x70/0xa0 [ 5059.442231] [] rtl8169_poll+0x166/0x700 [r8169] [ 5059.442231] [] net_rx_action+0x129/0x1e0 [ 5059.442231] [] __do_softirq+0xed/0x240 [ 5059.442231] [] irq_exit+0x125/0x140 [ 5059.442231] [] do_IRQ+0x51/0xc0 [ 5059.442231] [] common_interrupt+0x6f/0x6f We need to keep a reference on the socket, by using skb_steal_sock() at the right place. Note that another patch is needed to fix a race in udp_sk_rx_dst_set(), as we hold no lock protecting the dst. Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux") Reported-by: Dave Jones Signed-off-by: Eric Dumazet Cc: Shawn Bohrer Signed-off-by: David S. Miller --- net/ipv4/udp.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 44f6a20fa29..2e2aecbe22c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -560,15 +560,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { - struct sock *sk; const struct iphdr *iph = ip_hdr(skb); - if (unlikely(sk = skb_steal_sock(skb))) - return sk; - else - return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), - udptable); + return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + udptable); } struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, @@ -1739,15 +1735,15 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - if (skb->sk) { + sk = skb_steal_sock(skb); + if (sk) { int ret; - sk = skb->sk; if (unlikely(sk->sk_rx_dst == NULL)) udp_sk_rx_dst_set(sk, skb); ret = udp_queue_rcv_skb(sk, skb); - + sock_put(sk); /* a return value > 0 means to resubmit the input, but * it wants the return to be -protocol, or 0 */ -- cgit v1.2.3-70-g09d2 From 610438b74496b2986a9025f8e23c134cb638e338 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Dec 2013 08:10:05 -0800 Subject: udp: ipv4: fix potential use after free in udp_v4_early_demux() pskb_may_pull() can reallocate skb->head, we need to move the initialization of iph and uh pointers after its call. Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux") Signed-off-by: Eric Dumazet Cc: Shawn Bohrer Signed-off-by: David S. Miller --- net/ipv4/udp.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2e2aecbe22c..16d246a51a0 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1909,17 +1909,20 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, void udp_v4_early_demux(struct sk_buff *skb) { - const struct iphdr *iph = ip_hdr(skb); - const struct udphdr *uh = udp_hdr(skb); + struct net *net = dev_net(skb->dev); + const struct iphdr *iph; + const struct udphdr *uh; struct sock *sk; struct dst_entry *dst; - struct net *net = dev_net(skb->dev); int dif = skb->dev->ifindex; /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) return; + iph = ip_hdr(skb); + uh = udp_hdr(skb); + if (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, -- cgit v1.2.3-70-g09d2 From 975022310233fb0f0193873d79a7b8438070fa82 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Dec 2013 14:46:51 -0800 Subject: udp: ipv4: must add synchronization in udp_sk_rx_dst_set() Unlike TCP, UDP input path does not hold the socket lock. Before messing with sk->sk_rx_dst, we must use a spinlock, otherwise multiple cpus could leak a refcount. This patch also takes care of renewing a stale dst entry. (When the sk->sk_rx_dst would not be used by IP early demux) Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux") Signed-off-by: Eric Dumazet Cc: Shawn Bohrer Signed-off-by: David S. Miller --- net/ipv4/udp.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 16d246a51a0..62c19fdd102 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1599,12 +1599,21 @@ static void flush_stack(struct sock **stack, unsigned int count, kfree_skb(skb1); } -static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) +/* For TCP sockets, sk_rx_dst is protected by socket lock + * For UDP, we use sk_dst_lock to guard against concurrent changes. + */ +static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { - struct dst_entry *dst = skb_dst(skb); + struct dst_entry *old; - dst_hold(dst); - sk->sk_rx_dst = dst; + spin_lock(&sk->sk_dst_lock); + old = sk->sk_rx_dst; + if (likely(old != dst)) { + dst_hold(dst); + sk->sk_rx_dst = dst; + dst_release(old); + } + spin_unlock(&sk->sk_dst_lock); } /* @@ -1737,10 +1746,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, sk = skb_steal_sock(skb); if (sk) { + struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst == NULL)) - udp_sk_rx_dst_set(sk, skb); + if (unlikely(sk->sk_rx_dst != dst)) + udp_sk_rx_dst_set(sk, dst); ret = udp_queue_rcv_skb(sk, skb); sock_put(sk); -- cgit v1.2.3-70-g09d2 From e47eb5dfb296bf217e9ebee7b2f07486670b9c1b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 15 Dec 2013 10:53:46 -0800 Subject: udp: ipv4: do not use sk_dst_lock from softirq context Using sk_dst_lock from softirq context is not supported right now. Instead of adding BH protection everywhere, udp_sk_rx_dst_set() can instead use xchg(), as suggested by David. Reported-by: Fengguang Wu Fixes: 975022310233 ("udp: ipv4: must add synchronization in udp_sk_rx_dst_set()") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/udp.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 62c19fdd102..f140048334c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1600,20 +1600,15 @@ static void flush_stack(struct sock **stack, unsigned int count, } /* For TCP sockets, sk_rx_dst is protected by socket lock - * For UDP, we use sk_dst_lock to guard against concurrent changes. + * For UDP, we use xchg() to guard against concurrent changes. */ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; - spin_lock(&sk->sk_dst_lock); - old = sk->sk_rx_dst; - if (likely(old != dst)) { - dst_hold(dst); - sk->sk_rx_dst = dst; - dst_release(old); - } - spin_unlock(&sk->sk_dst_lock); + dst_hold(dst); + old = xchg(&sk->sk_rx_dst, dst); + dst_release(old); } /* -- cgit v1.2.3-70-g09d2