From 9cd3e072b0be17446e37d7414eac8a3499e0601e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Nov 2015 20:03:10 -0800
Subject: net: rename SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA
This patch is a cleanup to make following patch easier to
review.
Goal is to move SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA
from (struct socket)->flags to a (struct socket_wq)->flags
to benefit from RCU protection in sock_wake_async()
To ease backports, we rename both constants.
Two new helpers, sk_set_bit(int nr, struct sock *sk)
and sk_clear_bit(int net, struct sock *sk) are added so that
following patch can change their implementation.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/sock.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
(limited to 'net/core/sock.c')
diff --git a/net/core/sock.c b/net/core/sock.c
index 1e4dd54bfb5a..9d79569935a3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1815,7 +1815,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
{
DEFINE_WAIT(wait);
- clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
for (;;) {
if (!timeo)
break;
@@ -1861,7 +1861,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
break;
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
if (!timeo)
@@ -2048,9 +2048,9 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
DEFINE_WAIT(wait);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
- clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
finish_wait(sk_sleep(sk), &wait);
return rc;
}
--
cgit
From 6bd4f355df2eae80b8a5c7b097371cd1e05f20d5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Dec 2015 21:53:57 -0800
Subject: ipv6: kill sk_dst_lock
While testing the np->opt RCU conversion, I found that UDP/IPv6 was
using a mixture of xchg() and sk_dst_lock to protect concurrent changes
to sk->sk_dst_cache, leading to possible corruptions and crashes.
ip6_sk_dst_lookup_flow() uses sk_dst_check() anyway, so the simplest
way to fix the mess is to remove sk_dst_lock completely, as we did for
IPv4.
__ip6_dst_store() and ip6_dst_store() share same implementation.
sk_setup_caps() being called with socket lock being held or not,
we have to use sk_dst_set() instead of __sk_dst_set()
Note that I had to move the "np->dst_cookie = rt6_get_cookie(rt);"
in ip6_dst_store() before the sk_setup_caps(sk, dst) call.
This is because ip6_dst_store() can be called from process context,
without any lock held.
As soon as the dst is installed in sk->sk_dst_cache, dst can be freed
from another cpu doing a concurrent ip6_dst_store()
Doing the dst dereference before doing the install is needed to make
sure no use after free would trigger.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/sock.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
(limited to 'net/core/sock.c')
diff --git a/net/core/sock.c b/net/core/sock.c
index 9d79569935a3..e31dfcee1729 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1530,7 +1530,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
skb_queue_head_init(&newsk->sk_receive_queue);
skb_queue_head_init(&newsk->sk_write_queue);
- spin_lock_init(&newsk->sk_dst_lock);
rwlock_init(&newsk->sk_callback_lock);
lockdep_set_class_and_name(&newsk->sk_callback_lock,
af_callback_keys + newsk->sk_family,
@@ -1607,7 +1606,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
- __sk_dst_set(sk, dst);
+ sk_dst_set(sk, dst);
sk->sk_route_caps = dst->dev->features;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
@@ -2388,7 +2387,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
} else
sk->sk_wq = NULL;
- spin_lock_init(&sk->sk_dst_lock);
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_callback_lock,
af_callback_keys + sk->sk_family,
--
cgit
From 01ce63c90170283a9855d1db4fe81934dddce648 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:04 -0200
Subject: sctp: update the netstamp_needed counter when copying sockets
Dmitry Vyukov reported that SCTP was triggering a WARN on socket destroy
related to disabling sock timestamp.
When SCTP accepts an association or peel one off, it copies sock flags
but forgot to call net_enable_timestamp() if a packet timestamping flag
was copied, leading to extra calls to net_disable_timestamp() whenever
such clones were closed.
The fix is to call net_enable_timestamp() whenever we copy a sock with
that flag on, like tcp does.
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/sock.c | 2 --
1 file changed, 2 deletions(-)
(limited to 'net/core/sock.c')
diff --git a/net/core/sock.c b/net/core/sock.c
index e31dfcee1729..d01c8f42dbb2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -433,8 +433,6 @@ static bool sock_needs_netstamp(const struct sock *sk)
}
}
-#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
-
static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
if (sk->sk_flags & flags) {
--
cgit
From d188ba86dd07a72ebebfa22fe9cb0b0572e57740 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Dec 2015 07:22:02 -0800
Subject: xfrm: add rcu protection to sk->sk_policy[]
XFRM can deal with SYNACK messages, sent while listener socket
is not locked. We add proper rcu protection to __xfrm_sk_clone_policy()
and xfrm_sk_policy_lookup()
This might serve as the first step to remove xfrm.xfrm_policy_lock
use in fast path.
Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/sock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'net/core/sock.c')
diff --git a/net/core/sock.c b/net/core/sock.c
index d01c8f42dbb2..765be835b06c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1550,7 +1550,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
*/
is_charged = sk_filter_charge(newsk, filter);
- if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk))) {
+ if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
/* It is still raw copy of parent, so invalidate
* destructor and make plain sk_free() */
newsk->sk_destruct = NULL;
--
cgit
From ac5cc977991d2dce85fc734a6c71ddb33f6fe3c1 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 16 Dec 2015 23:39:04 -0800
Subject: net: check both type and procotol for tcp sockets
Dmitry reported the following out-of-bound access:
Call Trace:
[<ffffffff816cec2e>] __asan_report_load4_noabort+0x3e/0x40
mm/kasan/report.c:294
[<ffffffff84affb14>] sock_setsockopt+0x1284/0x13d0 net/core/sock.c:880
[< inline >] SYSC_setsockopt net/socket.c:1746
[<ffffffff84aed7ee>] SyS_setsockopt+0x1fe/0x240 net/socket.c:1729
[<ffffffff85c18c76>] entry_SYSCALL_64_fastpath+0x16/0x7a
arch/x86/entry/entry_64.S:185
This is because we mistake a raw socket as a tcp socket.
We should check both sk->sk_type and sk->sk_protocol to ensure
it is a tcp socket.
Willem points out __skb_complete_tx_timestamp() needs to fix as well.
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/sock.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
(limited to 'net/core/sock.c')
diff --git a/net/core/sock.c b/net/core/sock.c
index 765be835b06c..0d91f7dca751 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -872,7 +872,8 @@ set_rcvbuf:
if (val & SOF_TIMESTAMPING_OPT_ID &&
!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
- if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_protocol == IPPROTO_TCP &&
+ sk->sk_type == SOCK_STREAM) {
if (sk->sk_state != TCP_ESTABLISHED) {
ret = -EINVAL;
break;
--
cgit