lkml.org 
[lkml]   [2012]   [Jan]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[25/75] SUNRPC: Ensure we always bump the backlog queue in xprt_free_slot
3.1-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <Trond.Myklebust@netapp.com>

commit c25573b5134294c0be82bfaecc6d08136835b271 upstream.

Whenever we free a slot, we know that the resulting xprt->num_reqs will
be less than xprt->max_reqs, so we know that we can release at least one
backlogged rpc_task.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
net/sunrpc/xprt.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)

--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -995,13 +995,11 @@ out_init_req:

static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
{
- if (xprt_dynamic_free_slot(xprt, req))
- return;
-
- memset(req, 0, sizeof(*req)); /* mark unused */
-
spin_lock(&xprt->reserve_lock);
- list_add(&req->rq_list, &xprt->free);
+ if (!xprt_dynamic_free_slot(xprt, req)) {
+ memset(req, 0, sizeof(*req)); /* mark unused */
+ list_add(&req->rq_list, &xprt->free);
+ }
rpc_wake_up_next(&xprt->backlog);
spin_unlock(&xprt->reserve_lock);
}



\
 
 \ /
  Last update: 2012-01-03 23:53    [W:0.261 / U:0.364 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site