From a57de0b4336e48db2811a2030bb68dba8dd09d88 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 8 Jul 2009 12:09:13 +0000
Subject: net: adding memory barrier to the poll and receive callbacks
Adding memory barrier after the poll_wait function, paired with
receive callbacks. Adding fuctions sock_poll_wait and sk_has_sleeper
to wrap the memory barrier.
Without the memory barrier, following race can happen.
The race fires, when following code paths meet, and the tp->rcv_nxt
and __add_wait_queue updates stay in CPU caches.
CPU1 CPU2
sys_select receive packet
... ...
__add_wait_queue update tp->rcv_nxt
... ...
tp->rcv_nxt check sock_def_readable
... {
schedule ...
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
wake_up_interruptible(sk->sk_sleep)
...
}
If there was no cache the code would work ok, since the wait_queue and
rcv_nxt are opposit to each other.
Meaning that once tp->rcv_nxt is updated by CPU2, the CPU1 either already
passed the tp->rcv_nxt check and sleeps, or will get the new value for
tp->rcv_nxt and will return with new data mask.
In both cases the process (CPU1) is being added to the wait queue, so the
waitqueue_active (CPU2) call cannot miss and will wake up CPU1.
The bad case is when the __add_wait_queue changes done by CPU1 stay in its
cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 will then
endup calling schedule and sleep forever if there are no more data on the
socket.
Calls to poll_wait in following modules were ommited:
net/bluetooth/af_bluetooth.c
net/irda/af_irda.c
net/irda/irnet/irnet_ppp.c
net/mac80211/rc80211_pid_debugfs.c
net/phonet/socket.c
net/rds/af_rds.c
net/rfkill/core.c
net/sunrpc/cache.c
net/sunrpc/rpc_pipe.c
net/tipc/socket.c
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/datagram.c | 2 +-
net/core/sock.c | 8 ++++----
2 files changed, 5 insertions(+), 5 deletions(-)
(limited to 'net/core')
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 58abee1f1df1..b0fe69211eef 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -712,7 +712,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk;
unsigned int mask;
- poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk->sk_sleep, wait);
mask = 0;
/* exceptional events? */
diff --git a/net/core/sock.c b/net/core/sock.c
index b0ba569bc973..6354863b1c68 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1715,7 +1715,7 @@ EXPORT_SYMBOL(sock_no_sendpage);
static void sock_def_wakeup(struct sock *sk)
{
read_lock(&sk->sk_callback_lock);
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ if (sk_has_sleeper(sk))
wake_up_interruptible_all(sk->sk_sleep);
read_unlock(&sk->sk_callback_lock);
}
@@ -1723,7 +1723,7 @@ static void sock_def_wakeup(struct sock *sk)
static void sock_def_error_report(struct sock *sk)
{
read_lock(&sk->sk_callback_lock);
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ if (sk_has_sleeper(sk))
wake_up_interruptible_poll(sk->sk_sleep, POLLERR);
sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
read_unlock(&sk->sk_callback_lock);
@@ -1732,7 +1732,7 @@ static void sock_def_error_report(struct sock *sk)
static void sock_def_readable(struct sock *sk, int len)
{
read_lock(&sk->sk_callback_lock);
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ if (sk_has_sleeper(sk))
wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN |
POLLRDNORM | POLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
@@ -1747,7 +1747,7 @@ static void sock_def_write_space(struct sock *sk)
* progress. --DaveM
*/
if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ if (sk_has_sleeper(sk))
wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT |
POLLWRNORM | POLLWRBAND);
--
cgit v1.2.3