From 5d299f3d3c8a2fbc732b1bf03af36333ccec3130 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Aug 2012 05:09:33 +0000
Subject: net: ipv6: fix TCP early demux
IPv6 needs a cookie in dst_check() call.
We need to add rx_dst_cookie and provide a family independent
sk_rx_dst_set(sk, skb) method to properly support IPv6 TCP early demux.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/tcp_ipv6.c | 27 +++++++++++++++++++++++++--
1 file changed, 25 insertions(+), 2 deletions(-)
(limited to 'net/ipv6/tcp_ipv6.c')
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c66b90f71c9..5a439e9a4c0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1447,7 +1447,17 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC));
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+ struct dst_entry *dst = sk->sk_rx_dst;
+
sock_rps_save_rxhash(sk, skb);
+ if (dst) {
+ if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
+ dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
+ dst_release(dst);
+ sk->sk_rx_dst = NULL;
+ }
+ }
+
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
goto reset;
if (opt_skb)
@@ -1705,9 +1715,9 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
struct dst_entry *dst = sk->sk_rx_dst;
struct inet_sock *icsk = inet_sk(sk);
if (dst)
- dst = dst_check(dst, 0);
+ dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
if (dst &&
- icsk->rx_dst_ifindex == inet6_iif(skb))
+ icsk->rx_dst_ifindex == skb->skb_iif)
skb_dst_set_noref(skb, dst);
}
}
@@ -1719,10 +1729,23 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_destructor= tcp_twsk_destructor,
};
+static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+ if (rt->rt6i_node)
+ inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+}
+
static const struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
+ .sk_rx_dst_set = inet6_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct ipv6hdr),
--
cgit v1.2.3-70-g09d2
From 63d02d157ec4124990258d66517b6c11fd6df0cf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 9 Aug 2012 14:11:00 +0000
Subject: net: tcp: ipv6_mapped needs sk_rx_dst_set method
commit 5d299f3d3c8a2fb (net: ipv6: fix TCP early demux) added a
regression for ipv6_mapped case.
[ 67.422369] SELinux: initialized (dev autofs, type autofs), uses
genfs_contexts
[ 67.449678] SELinux: initialized (dev autofs, type autofs), uses
genfs_contexts
[ 92.631060] BUG: unable to handle kernel NULL pointer dereference at
(null)
[ 92.631435] IP: [< (null)>] (null)
[ 92.631645] PGD 0
[ 92.631846] Oops: 0010 [#1] SMP
[ 92.632095] Modules linked in: autofs4 sunrpc ipv6 dm_mirror
dm_region_hash dm_log dm_multipath dm_mod video sbs sbshc battery ac lp
parport sg snd_hda_intel snd_hda_codec snd_seq_oss snd_seq_midi_event
snd_seq snd_seq_device pcspkr snd_pcm_oss snd_mixer_oss snd_pcm
snd_timer serio_raw button floppy snd i2c_i801 i2c_core soundcore
snd_page_alloc shpchp ide_cd_mod cdrom microcode ehci_hcd ohci_hcd
uhci_hcd
[ 92.634294] CPU 0
[ 92.634294] Pid: 4469, comm: sendmail Not tainted 3.6.0-rc1 #3
[ 92.634294] RIP: 0010:[<0000000000000000>] [< (null)>]
(null)
[ 92.634294] RSP: 0018:ffff880245fc7cb0 EFLAGS: 00010282
[ 92.634294] RAX: ffffffffa01985f0 RBX: ffff88024827ad00 RCX:
0000000000000000
[ 92.634294] RDX: 0000000000000218 RSI: ffff880254735380 RDI:
ffff88024827ad00
[ 92.634294] RBP: ffff880245fc7cc8 R08: 0000000000000001 R09:
0000000000000000
[ 92.634294] R10: 0000000000000000 R11: ffff880245fc7bf8 R12:
ffff880254735380
[ 92.634294] R13: ffff880254735380 R14: 0000000000000000 R15:
7fffffffffff0218
[ 92.634294] FS: 00007f4516ccd6f0(0000) GS:ffff880256600000(0000)
knlGS:0000000000000000
[ 92.634294] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 92.634294] CR2: 0000000000000000 CR3: 0000000245ed1000 CR4:
00000000000007f0
[ 92.634294] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[ 92.634294] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7:
0000000000000400
[ 92.634294] Process sendmail (pid: 4469, threadinfo ffff880245fc6000,
task ffff880254b8cac0)
[ 92.634294] Stack:
[ 92.634294] ffffffff813837a7 ffff88024827ad00 ffff880254b6b0e8
ffff880245fc7d68
[ 92.634294] ffffffff81385083 00000000001d2680 ffff8802547353a8
ffff880245fc7d18
[ 92.634294] ffffffff8105903a ffff88024827ad60 0000000000000002
00000000000000ff
[ 92.634294] Call Trace:
[ 92.634294] [<ffffffff813837a7>] ? tcp_finish_connect+0x2c/0xfa
[ 92.634294] [<ffffffff81385083>] tcp_rcv_state_process+0x2b6/0x9c6
[ 92.634294] [<ffffffff8105903a>] ? sched_clock_cpu+0xc3/0xd1
[ 92.634294] [<ffffffff81059073>] ? local_clock+0x2b/0x3c
[ 92.634294] [<ffffffff8138caf3>] tcp_v4_do_rcv+0x63a/0x670
[ 92.634294] [<ffffffff8133278e>] release_sock+0x128/0x1bd
[ 92.634294] [<ffffffff8139f060>] __inet_stream_connect+0x1b1/0x352
[ 92.634294] [<ffffffff813325f5>] ? lock_sock_nested+0x74/0x7f
[ 92.634294] [<ffffffff8104b333>] ? wake_up_bit+0x25/0x25
[ 92.634294] [<ffffffff813325f5>] ? lock_sock_nested+0x74/0x7f
[ 92.634294] [<ffffffff8139f223>] ? inet_stream_connect+0x22/0x4b
[ 92.634294] [<ffffffff8139f234>] inet_stream_connect+0x33/0x4b
[ 92.634294] [<ffffffff8132e8cf>] sys_connect+0x78/0x9e
[ 92.634294] [<ffffffff813fd407>] ? sysret_check+0x1b/0x56
[ 92.634294] [<ffffffff81088503>] ? __audit_syscall_entry+0x195/0x1c8
[ 92.634294] [<ffffffff811cc26e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
[ 92.634294] [<ffffffff813fd3e2>] system_call_fastpath+0x16/0x1b
[ 92.634294] Code: Bad RIP value.
[ 92.634294] RIP [< (null)>] (null)
[ 92.634294] RSP <ffff880245fc7cb0>
[ 92.634294] CR2: 0000000000000000
[ 92.648982] ---[ end trace 24e2bed94314c8d9 ]---
[ 92.649146] Kernel panic - not syncing: Fatal exception in interrupt
Fix this using inet_sk_rx_dst_set(), and export this function in case
IPv6 is modular.
Reported-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/tcp.h | 1 +
net/ipv4/tcp_ipv4.c | 3 ++-
net/ipv6/tcp_ipv6.c | 1 +
3 files changed, 4 insertions(+), 1 deletion(-)
(limited to 'net/ipv6/tcp_ipv6.c')
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e19124b84cd..1f000ffe707 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -464,6 +464,7 @@ extern int tcp_disconnect(struct sock *sk, int flags);
void tcp_connect_init(struct sock *sk);
void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size);
+void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
/* From syncookies.c */
extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 272241f16fc..76782376401 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1869,7 +1869,7 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
.twsk_destructor= tcp_twsk_destructor,
};
-static void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -1877,6 +1877,7 @@ static void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
}
+EXPORT_SYMBOL(inet_sk_rx_dst_set);
const struct inet_connection_sock_af_ops ipv4_specific = {
.queue_xmit = ip_queue_xmit,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5a439e9a4c0..bb9ce2b2f37 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1777,6 +1777,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
+ .sk_rx_dst_set = inet_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct iphdr),
--
cgit v1.2.3-70-g09d2
From fae6ef87faeb8853896920c68ee703d715799d28 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Sun, 19 Aug 2012 03:30:38 +0000
Subject: net: tcp: move sk_rx_dst_set call after tcp_create_openreq_child()
This commit removes the sk_rx_dst_set calls from
tcp_create_openreq_child(), because at that point the icsk_af_ops
field of ipv6_mapped TCP sockets has not been set to its proper final
value.
Instead, to make sure we get the right sk_rx_dst_set variant
appropriate for the address family of the new connection, we have
tcp_v{4,6}_syn_recv_sock() directly call the appropriate function
shortly after the call to tcp_create_openreq_child() returns.
This also moves inet6_sk_rx_dst_set() to avoid a forward declaration
with the new approach.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reported-by: Artem Savkov <artem.savkov@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_minisocks.c | 2 --
net/ipv6/tcp_ipv6.c | 25 +++++++++++++------------
3 files changed, 14 insertions(+), 14 deletions(-)
(limited to 'net/ipv6/tcp_ipv6.c')
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 76782376401..5bf2040b25b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1462,6 +1462,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
goto exit_nonewsk;
newsk->sk_gso_type = SKB_GSO_TCPV4;
+ inet_sk_rx_dst_set(newsk, skb);
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index d9c9dcef2de..6ff7f10dce9 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -387,8 +387,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_sock *oldtp = tcp_sk(sk);
struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
- newicsk->icsk_af_ops->sk_rx_dst_set(newsk, skb);
-
/* TCP Cookie Transactions require space for the cookie pair,
* as it differs for each connection. There is no need to
* copy any s_data_payload stored at the original socket.
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index bb9ce2b2f37..a3e60cc04a8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -94,6 +94,18 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
}
#endif
+static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+ if (rt->rt6i_node)
+ inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+}
+
static void tcp_v6_hash(struct sock *sk)
{
if (sk->sk_state != TCP_CLOSE) {
@@ -1270,6 +1282,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newsk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(newsk, dst, NULL, NULL);
+ inet6_sk_rx_dst_set(newsk, skb);
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
@@ -1729,18 +1742,6 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_destructor= tcp_twsk_destructor,
};
-static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
-{
- struct dst_entry *dst = skb_dst(skb);
- const struct rt6_info *rt = (const struct rt6_info *)dst;
-
- dst_hold(dst);
- sk->sk_rx_dst = dst;
- inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
- if (rt->rt6i_node)
- inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
-}
-
static const struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
--
cgit v1.2.3-70-g09d2