Le jeudi 23 septembre 2010 Ã 00:13 +0200, Jarek Poplawski a Ãcrit :
> Eric Dumazet wrote:
> > [PATCH] net: fix a lockdep splat
> >
> > We have for each socket :
> >
> > One spinlock (sk_slock.slock)
> > One rwlock (sk_callback_lock)
> >
> > Possible scenarios are :
> >
> > (A) (this is used in net/sunrpc/xprtsock.c)
> > read_lock(&sk->sk_callback_lock) (without blocking BH)
> > <BH>
> > spin_lock(&sk->sk_slock.slock);
> > ...
> > read_lock(&sk->sk_callback_lock);
> > ...
> >
> >
> > (B)
> > write_lock_bh(&sk->sk_callback_lock)
> > stuff
> > write_unlock_bh(&sk->sk_callback_lock)
> >
> >
> > (C)
> > spin_lock_bh(&sk->sk_slock)
> > ...
> > write_lock_bh(&sk->sk_callback_lock)
> > stuff
> > write_unlock_bh(&sk->sk_callback_lock)
> > spin_unlock_bh(&sk->sk_slock)
> >
> > This (C) case conflicts with (A) :
> >
> > CPU1 [A] CPU2 [C]
> > read_lock(callback_lock)
> > <BH> spin_lock_bh(slock)
> > <wait to spin_lock(slock)>
> > <wait to write_lock_bh(callback_lock)>
> >
> > We have one problematic (C) use case in inet_csk_listen_stop() :
> >
> > local_bh_disable();
> > bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock)
> > WARN_ON(sock_owned_by_user(child));
> > ...
> > sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock)
> >
> > lockdep is not happy with this, as reported by Tetsuo Handa
> >
> > This patch makes sure inet_csk_listen_stop() uses following lock order :
> >
> > write_lock_bh(&sk->sk_callback_lock)
> > spin_lock(&sk->sk_slock)
> > ...
> > spin_unlock(&sk->sk_slock)
> > write_unlock_bh(&sk->sk_callback_lock)
>
> IMHO this order conflicts with (A) too (but I'm not sure lockdep
> tracks that):
>
It should... thats strange I did not hit it in my tests
> CPU1 [A] CPU2 [C-reversed]
> ... write_lock_bh(callback_lock)
> <BH>
> spin_lock(slock)
> <wait to spin_lock(slock)>
> <wait to read_lock(callback_lock)>
>
Oh well, you're right. I tried to avoid the _bh everywhere but it seems
buggy too.
> My proposal is to BH protect read_lock(sk_callback_lock) everywhere (it's
> done by netfilter in a few places already).
>
Yes... its a bit strange we never hit this lockdep splat before...
I tried to track recent changes but really I am mystified ???
Thanks !
[PATCH v2] net: fix a lockdep splat
We have for each socket :
One spinlock (sk_slock.slock)
One rwlock (sk_callback_lock)
Possible scenarios are :
(A) (this is used in net/sunrpc/xprtsock.c)
read_lock(&sk->sk_callback_lock) (without blocking BH)
<BH>
spin_lock(&sk->sk_slock.slock);
...
read_lock(&sk->sk_callback_lock);
...
(B)
write_lock_bh(&sk->sk_callback_lock)
stuff
write_unlock_bh(&sk->sk_callback_lock)
(C)
spin_lock_bh(&sk->sk_slock)
...
write_lock_bh(&sk->sk_callback_lock)
stuff
write_unlock_bh(&sk->sk_callback_lock)
spin_unlock_bh(&sk->sk_slock)
This (C) case conflicts with (A) :
CPU1 [A] CPU2 [C]
read_lock(callback_lock)
<BH> spin_lock_bh(slock)
<wait to spin_lock(slock)>
<wait to write_lock_bh(callback_lock)>
We have one problematic (C) use case in inet_csk_listen_stop() :
local_bh_disable();
bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock)
WARN_ON(sock_owned_by_user(child));
...
sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock)
lockdep is not happy with this, as reported by Tetsuo Handa
It seems only way to deal with this is to use read_lock_bh(callbacklock)
everywhere.
Thanks to Jarek for pointing a bug in my first attempt and suggesting
this solution.
Reported-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Eric Dumazet <eric.dumazet@xxxxxxxxx>
CC: Jarek Poplawski <jarkao2@xxxxxxxxx>
---
net/core/sock.c | 8 ++++----
net/rds/tcp_connect.c | 4 ++--
net/rds/tcp_listen.c | 4 ++--
net/rds/tcp_recv.c | 4 ++--
net/rds/tcp_send.c | 4 ++--
net/sunrpc/xprtsock.c | 28 ++++++++++++++--------------
6 files changed, 26 insertions(+), 26 deletions(-)
diff --git a/net/core/sock.c b/net/core/sock.c
index b05b9b6..ef30e9d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1351,9 +1351,9 @@ int sock_i_uid(struct sock *sk)
{
int uid;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0;
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
return uid;
}
EXPORT_SYMBOL(sock_i_uid);
@@ -1362,9 +1362,9 @@ unsigned long sock_i_ino(struct sock *sk)
{
unsigned long ino;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index c397524..c519939 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -43,7 +43,7 @@ void rds_tcp_state_change(struct sock *sk)
struct rds_connection *conn;
struct rds_tcp_connection *tc;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
conn = sk->sk_user_data;
if (conn == NULL) {
state_change = sk->sk_state_change;
@@ -68,7 +68,7 @@ void rds_tcp_state_change(struct sock *sk)
break;
}
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
state_change(sk);
}
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 975183f..27844f2 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -114,7 +114,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
rdsdebug("listen data ready sk %p\n", sk);
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
ready = sk->sk_user_data;
if (ready == NULL) { /* check for teardown race */
ready = sk->sk_data_ready;
@@ -131,7 +131,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
queue_work(rds_wq, &rds_tcp_listen_work);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
ready(sk, bytes);
}
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 1aba687..e437974 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -324,7 +324,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
rdsdebug("data ready sk %p bytes %d\n", sk, bytes);
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
conn = sk->sk_user_data;
if (conn == NULL) { /* check for teardown race */
ready = sk->sk_data_ready;
@@ -338,7 +338,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM)
queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
ready(sk, bytes);
}
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index a28b895..2f012a0 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -224,7 +224,7 @@ void rds_tcp_write_space(struct sock *sk)
struct rds_connection *conn;
struct rds_tcp_connection *tc;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
conn = sk->sk_user_data;
if (conn == NULL) {
write_space = sk->sk_write_space;
@@ -244,7 +244,7 @@ void rds_tcp_write_space(struct sock *sk)
queue_delayed_work(rds_wq, &conn->c_send_w, 0);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
/*
* write_space is only called when data leaves tcp's send queue if
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index b6309db..fe9306b 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -800,7 +800,7 @@ static void xs_udp_data_ready(struct sock *sk, int len)
u32 _xid;
__be32 *xp;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
dprintk("RPC: xs_udp_data_ready...\n");
if (!(xprt = xprt_from_sock(sk)))
goto out;
@@ -852,7 +852,7 @@ static void xs_udp_data_ready(struct sock *sk, int len)
dropit:
skb_free_datagram(sk, skb);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
@@ -1229,7 +1229,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes)
dprintk("RPC: xs_tcp_data_ready...\n");
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
if (xprt->shutdown)
@@ -1248,7 +1248,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes)
read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
} while (read > 0);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/*
@@ -1301,7 +1301,7 @@ static void xs_tcp_state_change(struct sock *sk)
{
struct rpc_xprt *xprt;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
@@ -1313,7 +1313,7 @@ static void xs_tcp_state_change(struct sock *sk)
switch (sk->sk_state) {
case TCP_ESTABLISHED:
- spin_lock_bh(&xprt->transport_lock);
+ spin_lock(&xprt->transport_lock);
if (!xprt_test_and_set_connected(xprt)) {
struct sock_xprt *transport = container_of(xprt,
struct sock_xprt, xprt);
@@ -1327,7 +1327,7 @@ static void xs_tcp_state_change(struct sock *sk)
xprt_wake_pending_tasks(xprt, -EAGAIN);
}
- spin_unlock_bh(&xprt->transport_lock);
+ spin_unlock(&xprt->transport_lock);
break;
case TCP_FIN_WAIT1:
/* The client initiated a shutdown of the socket */
@@ -1365,7 +1365,7 @@ static void xs_tcp_state_change(struct sock *sk)
xs_sock_mark_closed(xprt);
}
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/**
@@ -1376,7 +1376,7 @@ static void xs_error_report(struct sock *sk)
{
struct rpc_xprt *xprt;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: %s client %p...\n"
@@ -1384,7 +1384,7 @@ static void xs_error_report(struct sock *sk)
__func__, xprt, sk->sk_err);
xprt_wake_pending_tasks(xprt, -EAGAIN);
out:
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void xs_write_space(struct sock *sk)
@@ -1416,13 +1416,13 @@ static void xs_write_space(struct sock *sk)
*/
static void xs_udp_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
/* from net/core/sock.c:sock_def_write_space */
if (sock_writeable(sk))
xs_write_space(sk);
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
/**
@@ -1437,13 +1437,13 @@ static void xs_udp_write_space(struct sock *sk)
*/
static void xs_tcp_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
/* from net/core/stream.c:sk_stream_write_space */
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
xs_write_space(sk);
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
