summaryrefslogtreecommitdiffstats
path: root/net/sunrpc
diff options
context:
space:
mode:
authorNeil Brown <neilb@suse.de>2015-06-15 15:55:30 +1000
committerTrond Myklebust <trond.myklebust@primarydata.com>2015-06-16 11:13:21 -0400
commit298073181112a6ab6c30fe7971b99de968daf81e (patch)
tree9e5475e6fa6b3816663d26e33d80ee1182c8f487 /net/sunrpc
parent6f02dc88be1d5ecfcc2b708250f4e5d49295326c (diff)
downloadlinux-298073181112a6ab6c30fe7971b99de968daf81e.tar.bz2
SUNRPC: never enqueue a ->rq_cong request on ->sending
If the sending queue has a task without ->rq_cong set at the front, and then a number of tasks with ->rq_cong set such that they use the entire congestion window, then the queue deadlocks. The first entry cannot be processed until later entries complete. This scenario has been seen with a client using UDP to access a server, and the network connection breaking for a period of time - it doesn't recover. It never really makes sense for an ->rq_cong request to be on the ->sending queue, but it can happen when a request is being retried, and finds the transport if locked (XPRT_LOCKED). In this case we simple call __xprt_put_cong() and the deadlock goes away. Signed-off-by: NeilBrown <neilb@suse.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Diffstat (limited to 'net/sunrpc')
-rw-r--r--net/sunrpc/xprt.c3
1 files changed, 3 insertions, 0 deletions
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index e1fb538e10e0..3ca31f20b97c 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -68,6 +68,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net);
static void xprt_request_init(struct rpc_task *, struct rpc_xprt *);
static void xprt_connect_status(struct rpc_task *task);
static int __xprt_get_cong(struct rpc_xprt *, struct rpc_task *);
+static void __xprt_put_cong(struct rpc_xprt *, struct rpc_rqst *);
static void xprt_destroy(struct rpc_xprt *xprt);
static DEFINE_SPINLOCK(xprt_list_lock);
@@ -250,6 +251,8 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task)
}
xprt_clear_locked(xprt);
out_sleep:
+ if (req)
+ __xprt_put_cong(xprt, req);
dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt);
task->tk_timeout = 0;
task->tk_status = -EAGAIN;