@@ -317,8 +317,15 @@ rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context)
static void
rpcrdma_flush_cqs(struct rpcrdma_ep *ep)
{
- rpcrdma_recvcq_upcall(ep->rep_attr.recv_cq, ep);
- rpcrdma_sendcq_upcall(ep->rep_attr.send_cq, ep);
+ struct ib_wc wc;
+ LIST_HEAD(sched_list);
+
+ while (ib_poll_cq(ep->rep_attr.recv_cq, 1, &wc) > 0)
+ rpcrdma_recvcq_process_wc(&wc, &sched_list);
+ if (!list_empty(&sched_list))
+ rpcrdma_schedule_tasklet(&sched_list);
+ while (ib_poll_cq(ep->rep_attr.send_cq, 1, &wc) > 0)
+ rpcrdma_sendcq_process_wc(&wc);
}
#ifdef RPC_DEBUG
Currently rpcrdma_flush_cqs() attempts to avoid code duplication, and simply invokes rpcrdma_recvcq_upcall and rpcrdma_sendcq_upcall. 1. rpcrdma_flush_cqs() can run concurrently with provider upcalls. Both flush_cqs() and the upcalls were invoking ib_poll_cq() in different threads using the same wc buffers (ep->rep_recv_wcs and ep->rep_send_wcs), added by commit 1c00dd077654 ("xprtrmda: Reduce calls to ib_poll_cq() in completion handlers"). During transport disconnect processing, this sometimes resulted in the same reply getting added to the rpcrdma_tasklets_g list more than once, which corrupted the list. 2. The upcall functions drain only a limited number of CQEs, thanks to the poll budget added by commit 8301a2c047cc ("xprtrdma: Limit work done by completion handler"). Fixes: a7bc211ac926 ("xprtrdma: On disconnect, don't ignore ... ") BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=276 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> --- net/sunrpc/xprtrdma/verbs.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html