SUNRPC: Respond promptly to server TCP resets

If the server sends us an RST error while we're in the TCP_ESTABLISHED
state, then that will not result in a state change, and so the RPC client
ends up hanging forever (see
http://bugzilla.kernel.org/show_bug.cgi?id=11154)

We can intercept the reset by setting up an sk->sk_error_report callback,
which will then allow us to initiate a proper shutdown and retry...

We also make sure that if the send request receives an ECONNRESET, then we
shutdown too...

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
This commit is contained in:
Trond Myklebust 2008-10-28 15:21:39 -04:00
parent e946217e4f
commit 2a9e1cfa23
1 changed files with 48 additions and 10 deletions

View File

@ -249,6 +249,7 @@ struct sock_xprt {
void (*old_data_ready)(struct sock *, int);
void (*old_state_change)(struct sock *);
void (*old_write_space)(struct sock *);
void (*old_error_report)(struct sock *);
};
/*
@ -698,8 +699,9 @@ static int xs_tcp_send_request(struct rpc_task *task)
case -EAGAIN:
xs_nospace(task);
break;
case -ECONNREFUSED:
case -ECONNRESET:
xs_tcp_shutdown(xprt);
case -ECONNREFUSED:
case -ENOTCONN:
case -EPIPE:
status = -ENOTCONN;
@ -742,6 +744,22 @@ out_release:
xprt_release_xprt(xprt, task);
}
static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
{
transport->old_data_ready = sk->sk_data_ready;
transport->old_state_change = sk->sk_state_change;
transport->old_write_space = sk->sk_write_space;
transport->old_error_report = sk->sk_error_report;
}
static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
{
sk->sk_data_ready = transport->old_data_ready;
sk->sk_state_change = transport->old_state_change;
sk->sk_write_space = transport->old_write_space;
sk->sk_error_report = transport->old_error_report;
}
/**
* xs_close - close a socket
* @xprt: transport
@ -765,9 +783,8 @@ static void xs_close(struct rpc_xprt *xprt)
transport->sock = NULL;
sk->sk_user_data = NULL;
sk->sk_data_ready = transport->old_data_ready;
sk->sk_state_change = transport->old_state_change;
sk->sk_write_space = transport->old_write_space;
xs_restore_old_callbacks(transport, sk);
write_unlock_bh(&sk->sk_callback_lock);
sk->sk_no_check = 0;
@ -1179,6 +1196,28 @@ static void xs_tcp_state_change(struct sock *sk)
read_unlock(&sk->sk_callback_lock);
}
/**
* xs_tcp_error_report - callback mainly for catching RST events
* @sk: socket
*/
static void xs_tcp_error_report(struct sock *sk)
{
struct rpc_xprt *xprt;
read_lock(&sk->sk_callback_lock);
if (sk->sk_err != ECONNRESET || sk->sk_state != TCP_ESTABLISHED)
goto out;
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: %s client %p...\n"
"RPC: error %d\n",
__func__, xprt, sk->sk_err);
xprt_force_disconnect(xprt);
out:
read_unlock(&sk->sk_callback_lock);
}
/**
* xs_udp_write_space - callback invoked when socket buffer space
* becomes available
@ -1454,10 +1493,9 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
write_lock_bh(&sk->sk_callback_lock);
xs_save_old_callbacks(transport, sk);
sk->sk_user_data = xprt;
transport->old_data_ready = sk->sk_data_ready;
transport->old_state_change = sk->sk_state_change;
transport->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_udp_data_ready;
sk->sk_write_space = xs_udp_write_space;
sk->sk_no_check = UDP_CSUM_NORCV;
@ -1589,13 +1627,13 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
write_lock_bh(&sk->sk_callback_lock);
xs_save_old_callbacks(transport, sk);
sk->sk_user_data = xprt;
transport->old_data_ready = sk->sk_data_ready;
transport->old_state_change = sk->sk_state_change;
transport->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_tcp_data_ready;
sk->sk_state_change = xs_tcp_state_change;
sk->sk_write_space = xs_tcp_write_space;
sk->sk_error_report = xs_tcp_error_report;
sk->sk_allocation = GFP_ATOMIC;
/* socket options */