svcrdma: Fix race between svc_rdma_recvfrom thread and the dto_tasklet

RDMA_READ completions are kept on a separate queue from the general
I/O request queue. Since a separate lock is used to protect the RDMA_READ
completion queue, a race exists between the dto_tasklet and the
svc_rdma_recvfrom thread where the dto_tasklet sets the XPT_DATA
bit and adds I/O to the read-completion queue. Concurrently, the
recvfrom thread checks the generic queue, finds it empty and resets
the XPT_DATA bit. A subsequent svc_xprt_enqueue will fail to enqueue
the transport for I/O and cause the transport to "stall".

The fix is to protect both lists with the same lock and set the XPT_DATA
bit with this lock held.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
This commit is contained in:
Tom Tucker
2008-08-13 11:05:41 -05:00
committed by J. Bruce Fields
parent 30a2f3c60a
commit 24b8b44780
3 changed files with 6 additions and 8 deletions

View File

@@ -443,18 +443,18 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
dprintk("svcrdma: rqstp=%p\n", rqstp);
spin_lock_bh(&rdma_xprt->sc_read_complete_lock);
spin_lock_bh(&rdma_xprt->sc_rq_dto_lock);
if (!list_empty(&rdma_xprt->sc_read_complete_q)) {
ctxt = list_entry(rdma_xprt->sc_read_complete_q.next,
struct svc_rdma_op_ctxt,
dto_q);
list_del_init(&ctxt->dto_q);
}
spin_unlock_bh(&rdma_xprt->sc_read_complete_lock);
if (ctxt)
if (ctxt) {
spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
return rdma_read_complete(rqstp, ctxt);
}
spin_lock_bh(&rdma_xprt->sc_rq_dto_lock);
if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
ctxt = list_entry(rdma_xprt->sc_rq_dto_q.next,
struct svc_rdma_op_ctxt,