From 93209264203987cdd2c69d34df6eaa2cd184e283 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 19 Feb 2013 12:25:57 -0600 Subject: [PATCH] libceph: separate non-locked fault handling An error occurring on a ceph connection is treated as a fault, causing the connection to be reset. The initial part of this fault handling has to be done while holding the connection mutex, but it must then be dropped for the last part. Separate the part of this fault handling that executes without the lock into its own function, con_fault_finish(). Move the call to this new function, as well as call that drops the connection mutex, into ceph_fault(). Rename that function con_fault() to reflect that it's only handling the connection part of the fault handling. The motivation for this was a warning from sparse about the locking being done here. Rearranging things this way keeps all the mutex manipulation within ceph_fault(), and this stops sparse from complaining. This partially resolves: http://tracker.ceph.com/issues/4184 Reported-by: Fengguang Wu Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- net/ceph/messenger.c | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9a29d8a4bad7..c3b9060d4844 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -166,7 +166,7 @@ static struct lock_class_key socket_class; static void queue_con(struct ceph_connection *con); static void con_work(struct work_struct *); -static void ceph_fault(struct ceph_connection *con); +static void con_fault(struct ceph_connection *con); /* * Nicely render a sockaddr as a string. An array of formatted @@ -2363,6 +2363,23 @@ static bool con_backoff(struct ceph_connection *con) return true; } +/* Finish fault handling; con->mutex must *not* be held here */ + +static void con_fault_finish(struct ceph_connection *con) +{ + /* + * in case we faulted due to authentication, invalidate our + * current tickets so that we can get new ones. + */ + if (con->auth_retry && con->ops->invalidate_authorizer) { + dout("calling invalidate_authorizer()\n"); + con->ops->invalidate_authorizer(con); + } + + if (con->ops->fault) + con->ops->fault(con); +} + /* * Do some work on a connection. Drop a connection ref when we're done. */ @@ -2419,7 +2436,9 @@ done_unlocked: return; fault: - ceph_fault(con); /* error/fault path */ + con_fault(con); + mutex_unlock(&con->mutex); + con_fault_finish(con); goto done_unlocked; } @@ -2428,8 +2447,7 @@ fault: * Generic error/fault handler. A retry mechanism is used with * exponential backoff */ -static void ceph_fault(struct ceph_connection *con) - __releases(con->mutex) +static void con_fault(struct ceph_connection *con) { pr_warning("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); @@ -2445,7 +2463,7 @@ static void ceph_fault(struct ceph_connection *con) if (con_flag_test(con, CON_FLAG_LOSSYTX)) { dout("fault on LOSSYTX channel, marking CLOSED\n"); con->state = CON_STATE_CLOSED; - goto out_unlock; + return; } if (con->in_msg) { @@ -2476,20 +2494,6 @@ static void ceph_fault(struct ceph_connection *con) con_flag_set(con, CON_FLAG_BACKOFF); queue_con(con); } - -out_unlock: - mutex_unlock(&con->mutex); - /* - * in case we faulted due to authentication, invalidate our - * current tickets so that we can get new ones. - */ - if (con->auth_retry && con->ops->invalidate_authorizer) { - dout("calling invalidate_authorizer()\n"); - con->ops->invalidate_authorizer(con); - } - - if (con->ops->fault) - con->ops->fault(con); }