linux-toradex.git/net/sunrpc, branch v3.2.48

SUNRPC: Prevent an rpc_task wakeup race

2013-05-30T13:35:04+00:00

commit a3c3cac5d31879cd9ae2de7874dc6544ca704aec upstream.

The lockless RPC_IS_QUEUED() test in __rpc_execute means that we need to
be careful about ordering the calls to rpc_test_and_set_running(task) and
rpc_clear_queued(task). If we get the order wrong, then we may end up
testing the RPC_TASK_RUNNING flag after __rpc_execute() has looped
and changed the state of the rpc_task.

Signed-off-by: Trond Myklebust 
Signed-off-by: Ben Hutchings

sunrpc: clarify comments on rpc_make_runnable

2013-05-30T13:35:04+00:00

commit 506026c3ec270e18402f0c9d33fee37482c23861 upstream.

rpc_make_runnable is not generally called with the queue lock held, unless
it's waking up a task that has been sitting on a waitqueue. This is safe
when the task has not entered the FSM yet, but the comments don't really
spell this out.

Signed-off-by: Jeff Layton 
Signed-off-by: Trond Myklebust 
Signed-off-by: Ben Hutchings

SUNRPC: Add barriers to ensure read ordering in rpc_wake_up_task_queue_locked

2013-04-10T02:20:02+00:00

commit 1166fde6a923c30f4351515b6a9a1efc513e7d00 upstream.

We need to be careful when testing task->tk_waitqueue in
rpc_wake_up_task_queue_locked, because it can be changed while we
are holding the queue->lock.
By adding appropriate memory barriers, we can ensure that it is safe to
test task->tk_waitqueue for equality if the RPC_TASK_QUEUED bit is set.

Signed-off-by: Trond Myklebust 
Signed-off-by: Ben Hutchings

SUNRPC: Don't start the retransmission timer when out of socket space

2013-03-20T15:03:16+00:00

commit a9a6b52ee1baa865283a91eb8d443ee91adfca56 upstream.

If the socket is full, we're better off just waiting until it empties,
or until the connection is broken. The reason why we generally don't
want to time out is that the call to xprt->ops->release_xprt() will
trigger a connection reset, which isn't helpful...

Let's make an exception for soft RPC calls, since they have to provide
timeout guarantees.

Signed-off-by: Trond Myklebust 
Signed-off-by: Ben Hutchings

svcrpc: make svc_age_temp_xprts enqueue under sv_lock

2013-03-06T03:24:01+00:00

commit e75bafbff2270993926abcc31358361db74a9bc2 upstream.

svc_age_temp_xprts expires xprts in a two-step process: first it takes
the sv_lock and moves the xprts to expire off their server-wide list
(sv_tempsocks or sv_permsocks) to a local list.  Then it drops the
sv_lock and enqueues and puts each one.

I see no reason for this: svc_xprt_enqueue() will take sp_lock, but the
sv_lock and sp_lock are not otherwise nested anywhere (and documentation
at the top of this file claims it's correct to nest these with sp_lock
inside.)

Tested-by: Jason Tibbitts 
Tested-by: Paweł Sikora 
Signed-off-by: J. Bruce Fields 
Signed-off-by: Ben Hutchings

SUNRPC: Ensure we release the socket write lock if the rpc_task exits early

2013-02-06T04:33:27+00:00

commit 87ed50036b866db2ec2ba16b2a7aec4a2b0b7c39 upstream.

If the rpc_task exits while holding the socket write lock before it has
allocated an rpc slot, then the usual mechanism for releasing the write
lock in xprt_release() is defeated.

The problem occurs if the call to xprt_lock_write() initially fails, so
that the rpc_task is put on the xprt->sending wait queue. If the task
exits after being assigned the lock by __xprt_lock_write_func, but
before it has retried the call to xprt_lock_and_alloc_slot(), then
it calls xprt_release() while holding the write lock, but will
immediately exit due to the test for task->tk_rqstp != NULL.

Reported-by: Chris Perl 
Signed-off-by: Trond Myklebust 
Signed-off-by: Ben Hutchings

SUNRPC: Ensure that we free the rpc_task after cleanups are done

2013-01-16T01:13:19+00:00

commit c6567ed1402c55e19b012e66a8398baec2a726f3 upstream.

This patch ensures that we free the rpc_task after the cleanup callbacks
are done in order to avoid a deadlock problem that can be triggered if
the callback needs to wait for another workqueue item to complete.

Signed-off-by: Trond Myklebust 
Cc: Weston Andros Adamson 
Cc: Tejun Heo 
Cc: Bruce Fields 
Signed-off-by: Ben Hutchings

SUNRPC: Get rid of the xs_error_report socket callback

2012-10-30T23:26:57+00:00

commit f878b657ce8e7d3673afe48110ec208a29e38c4a upstream.

Chris Perl reports that we're seeing races between the wakeup call in
xs_error_report and the connect attempts. Basically, Chris has shown
that in certain circumstances, the call to xs_error_report causes the
rpc_task that is responsible for reconnecting to wake up early, thus
triggering a disconnect and retry.

Since the sk->sk_error_report() calls in the socket layer are always
followed by a tcp_done() in the cases where we care about waking up
the rpc_tasks, just let the state_change callbacks take responsibility
for those wake ups.

Reported-by: Chris Perl 
Signed-off-by: Trond Myklebust 
Tested-by: Chris Perl 
Signed-off-by: Ben Hutchings

SUNRPC: Prevent races in xs_abort_connection()

2012-10-30T23:26:57+00:00

commit 4bc1e68ed6a8b59be8a79eb719be515a55c7bc68 upstream.

The call to xprt_disconnect_done() that is triggered by a successful
connection reset will trigger another automatic wakeup of all tasks
on the xprt->pending rpc_wait_queue. In particular it will cause an
early wake up of the task that called xprt_connect().

All we really want to do here is clear all the socket-specific state
flags, so we split that functionality out of xs_sock_mark_closed()
into a helper that can be called by xs_abort_connection()

Reported-by: Chris Perl 
Signed-off-by: Trond Myklebust 
Tested-by: Chris Perl 
Signed-off-by: Ben Hutchings

Revert "SUNRPC: Ensure we close the socket on EPIPE errors too..."

2012-10-30T23:26:56+00:00

commit b9d2bb2ee537424a7f855e1f93eed44eb9ee0854 upstream.

This reverts commit 55420c24a0d4d1fce70ca713f84aa00b6b74a70e.
Now that we clear the connected flag when entering TCP_CLOSE_WAIT,
the deadlock described in this commit is no longer possible.
Instead, the resulting call to xs_tcp_shutdown() can interfere
with pending reconnection attempts.

Reported-by: Chris Perl 
Signed-off-by: Trond Myklebust 
Tested-by: Chris Perl 
Signed-off-by: Ben Hutchings