Hi Linus,

Please pull from the "bugfixes" branch of the repository at

git pull git://git.linux-nfs.org/projects/trondmy/nfs-2.6.git bugfixes

This will update the following files through the appended changesets.

Cheers,
Trond

----
fs/nfs/inode.c | 11 ++------
net/sunrpc/auth.c | 18 ++++++++------
net/sunrpc/xprtsock.c | 58 ++++++++++++++++++++++++++++++++++++++++--------
3 files changed, 61 insertions(+), 26 deletions(-)

commit 5f707eb429e2c98dfd564ffbbd9f536bf493d869
Author: Trond Myklebust
Date: Tue Oct 28 15:21:42 2008 -0400

SUNRPC: Fix potential race in put_rpccred()

We have to be careful when we try to unhash the credential in
put_rpccred(), because we're not holding the credcache lock, so the call to
rpcauth_unhash_cred() may fail if someone else has looked the cred up, and
obtained a reference to it.

Signed-off-by: Trond Myklebust

commit eac0d18d44705f8a1b72cccec3a453e1a43eb20a
Author: Trond Myklebust
Date: Tue Oct 28 15:21:41 2008 -0400

SUNRPC: Fix rpcauth_prune_expired

We need to make sure that we don't remove creds from the cred_unused list
if they are still under the moratorium, or else they will never get
garbage collected.

Signed-off-by: Trond Myklebust

commit ae05f269400533cbb32bfba131ab528d78dffd16
Author: Trond Myklebust
Date: Tue Oct 28 15:21:40 2008 -0400

NFS: Convert nfs_attr_generation_counter into an atomic_long

The most important property we need from nfs_attr_generation_counter is
monotonicity, which is not guaranteed by the current system of smp memory
barriers. We should convert it to an atomic_long_t, and drop the memory
barriers.

Signed-off-by: Trond Myklebust

commit 2a9e1cfa23fb62da37739af81127dab5af095d99
Author: Trond Myklebust
Date: Tue Oct 28 15:21:39 2008 -0400

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

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index dc52793..d22eb38 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -908,21 +908,16 @@ static int nfs_size_need_update(const struct inode *inode, const struct nfs_fatt
return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
}

-static unsigned long nfs_attr_generation_counter;
+static atomic_long_t nfs_attr_generation_counter;

static unsigned long nfs_read_attr_generation_counter(void)
{
- smp_rmb();
- return nfs_attr_generation_counter;
+ return atomic_long_read(&nfs_attr_generation_counter);
}

unsigned long nfs_inc_attr_generation_counter(void)
{
- unsigned long ret;
- smp_rmb();
- ret = ++nfs_attr_generation_counter;
- smp_wmb();
- return ret;
+ return atomic_long_inc_return(&nfs_attr_generation_counter);
}

void nfs_fattr_init(struct nfs_fattr *fattr)
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 436bf1b..cb216b2 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -228,19 +228,21 @@ static int
rpcauth_prune_expired(struct list_head *free, int nr_to_scan)
{
spinlock_t *cache_lock;
- struct rpc_cred *cred;
+ struct rpc_cred *cred, *next;
unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM;

- while (!list_empty(&cred_unused)) {
- cred = list_entry(cred_unused.next, struct rpc_cred, cr_lru);
+ list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) {
+
+ /* Enforce a 60 second garbage collection moratorium */
+ if (time_in_range(cred->cr_expire, expired, jiffies) &&
+ test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0)
+ continue;
+
list_del_init(&cred->cr_lru);
number_cred_unused--;
if (atomic_read(&cred->cr_count) != 0)
continue;
- /* Enforce a 5 second garbage collection moratorium */
- if (time_in_range(cred->cr_expire, expired, jiffies) &&
- test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0)
- continue;
+
cache_lock = &cred->cr_auth->au_credcache->lock;
spin_lock(cache_lock);
if (atomic_read(&cred->cr_count) == 0) {
@@ -453,7 +455,7 @@ need_lock:
}
if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0)
rpcauth_unhash_cred(cred);
- else if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) {
+ if (test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags) != 0) {
cred->cr_expire = jiffies;
list_add_tail(&cred->cr_lru, &cred_unused);
number_cred_unused++;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9a288d5..0a50361 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -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;
@@ -1180,6 +1197,28 @@ static void xs_tcp_state_change(struct sock *sk)
}

/**
+ * 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
* @sk: socket whose state has changed
@@ -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 */

--
Trond Myklebust
Linux NFS client maintainer

NetApp
Trond.Myklebust@netapp.com
www.netapp.com
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/