From c6567ed1402c55e19b012e66a8398baec2a726f3 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Fri, 4 Jan 2013 12:23:21 -0500
Subject: SUNRPC: Ensure that we free the rpc_task after cleanups are done
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 <Trond.Myklebust@netapp.com>
Cc: Weston Andros Adamson <dros@netapp.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Bruce Fields <bfields@fieldses.org>
Cc: stable@vger.kernel.org
---
net/sunrpc/sched.c | 27 +++++++++++++++++++++++----
1 file changed, 23 insertions(+), 4 deletions(-)
(limited to 'net/sunrpc/sched.c')
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index d17a704aaf5..b4133bd1391 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -934,16 +934,35 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data)
return task;
}
+/*
+ * rpc_free_task - release rpc task and perform cleanups
+ *
+ * Note that we free up the rpc_task _after_ rpc_release_calldata()
+ * in order to work around a workqueue dependency issue.
+ *
+ * Tejun Heo states:
+ * "Workqueue currently considers two work items to be the same if they're
+ * on the same address and won't execute them concurrently - ie. it
+ * makes a work item which is queued again while being executed wait
+ * for the previous execution to complete.
+ *
+ * If a work function frees the work item, and then waits for an event
+ * which should be performed by another work item and *that* work item
+ * recycles the freed work item, it can create a false dependency loop.
+ * There really is no reliable way to detect this short of verifying
+ * every memory free."
+ *
+ */
static void rpc_free_task(struct rpc_task *task)
{
- const struct rpc_call_ops *tk_ops = task->tk_ops;
- void *calldata = task->tk_calldata;
+ unsigned short tk_flags = task->tk_flags;
+
+ rpc_release_calldata(task->tk_ops, task->tk_calldata);
- if (task->tk_flags & RPC_TASK_DYNAMIC) {
+ if (tk_flags & RPC_TASK_DYNAMIC) {
dprintk("RPC: %5u freeing task\n", task->tk_pid);
mempool_free(task, rpc_task_mempool);
}
- rpc_release_calldata(tk_ops, calldata);
}
static void rpc_async_release(struct work_struct *work)
--
cgit v1.2.3-70-g09d2
From 87ed50036b866db2ec2ba16b2a7aec4a2b0b7c39 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Mon, 7 Jan 2013 14:30:46 -0500
Subject: SUNRPC: Ensure we release the socket write lock if the rpc_task exits
early
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 <chris.perl@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@vger.kernel.org [>= 3.1]
---
net/sunrpc/sched.c | 3 +--
net/sunrpc/xprt.c | 12 ++++++++++--
2 files changed, 11 insertions(+), 4 deletions(-)
(limited to 'net/sunrpc/sched.c')
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index b4133bd1391..bfa31714581 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -972,8 +972,7 @@ static void rpc_async_release(struct work_struct *work)
static void rpc_release_resources_task(struct rpc_task *task)
{
- if (task->tk_rqstp)
- xprt_release(task);
+ xprt_release(task);
if (task->tk_msg.rpc_cred) {
put_rpccred(task->tk_msg.rpc_cred);
task->tk_msg.rpc_cred = NULL;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index bd462a532ac..33811db8788 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1136,10 +1136,18 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt)
void xprt_release(struct rpc_task *task)
{
struct rpc_xprt *xprt;
- struct rpc_rqst *req;
+ struct rpc_rqst *req = task->tk_rqstp;
- if (!(req = task->tk_rqstp))
+ if (req == NULL) {
+ if (task->tk_client) {
+ rcu_read_lock();
+ xprt = rcu_dereference(task->tk_client->cl_xprt);
+ if (xprt->snd_task == task)
+ xprt_release_write(xprt, task);
+ rcu_read_unlock();
+ }
return;
+ }
xprt = req->rq_xprt;
if (task->tk_ops->rpc_count_stats != NULL)
--
cgit v1.2.3-70-g09d2