Currently the completer tasklet when retransmit timer or the rnr timer fires the same flag (qp->req.need_retry) is set so that if either timer fires it will attempt to perform a retry flow on the send queue. This has the effect of responding to an RNR NAK at the first retransmit timer event which might not allow the requested rnr timeout. This patch adds a new flag (qp->req.wait_for_rnr_timer) which, if set, prevents a retry flow until the rnr nak timer fires. This patch fixes rnr retry errors which can be observed by running the pyverbs test_rdmacm_async_traffic_external_qp multiple times. With this patch applied they do not occur. Link: https://lore.kernel.org/linux-rdma/a8287823-1408-4273-bc22-99a0678db640@xxxxxxxxx/ Link: https://lore.kernel.org/linux-rdma/2bafda9e-2bb6-186d-12a1-179e8f6a2678@xxxxxxxxxx/ Fixes: 8700e3e7c485 ("Soft RoCE (RXE) - The software RoCE driver") Signed-off-by: Bob Pearson <rpearsonhpe@xxxxxxxxx> --- drivers/infiniband/sw/rxe/rxe_comp.c | 8 +++++++- drivers/infiniband/sw/rxe/rxe_qp.c | 1 + drivers/infiniband/sw/rxe/rxe_req.c | 15 +++++++++++++-- drivers/infiniband/sw/rxe/rxe_verbs.h | 1 + 4 files changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index da3a398053b8..4fc31bb7eee6 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -114,6 +114,8 @@ void retransmit_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, retrans_timer); + pr_debug("%s: fired for qp#%d\n", __func__, qp->elem.index); + if (qp->valid) { qp->comp.timeout = 1; rxe_run_task(&qp->comp.task, 1); @@ -730,11 +732,15 @@ int rxe_completer(void *arg) break; case COMPST_RNR_RETRY: + /* we come here if we received an RNR NAK */ if (qp->comp.rnr_retry > 0) { if (qp->comp.rnr_retry != 7) qp->comp.rnr_retry--; - qp->req.need_retry = 1; + /* don't start a retry flow until the + * rnr timer has fired + */ + qp->req.wait_for_rnr_timer = 1; pr_debug("qp#%d set rnr nak timer\n", qp_num(qp)); mod_timer(&qp->rnr_nak_timer, diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 22e9b85344c3..edc0c34feb05 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -507,6 +507,7 @@ static void rxe_qp_reset(struct rxe_qp *qp) atomic_set(&qp->ssn, 0); qp->req.opcode = -1; qp->req.need_retry = 0; + qp->req.wait_for_rnr_timer = 0; qp->req.noack_pkts = 0; qp->resp.msn = 0; qp->resp.opcode = -1; diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index e8a1664a40eb..4d92f929d269 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -101,7 +101,11 @@ void rnr_nak_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, rnr_nak_timer); - pr_debug("qp#%d rnr nak timer fired\n", qp_num(qp)); + pr_debug("%s: fired for qp#%d\n", __func__, qp_num(qp)); + + /* request a send queue retry */ + qp->req.need_retry = 1; + qp->req.wait_for_rnr_timer = 0; rxe_run_task(&qp->req.task, 1); } @@ -640,10 +644,17 @@ int rxe_requester(void *arg) qp->req.need_rd_atomic = 0; qp->req.wait_psn = 0; qp->req.need_retry = 0; + qp->req.wait_for_rnr_timer = 0; goto exit; } - if (unlikely(qp->req.need_retry)) { + /* we come here if the retransmot timer has fired + * or if the rnr timer has fired. If the retransmit + * timer fires while we are processing an RNR NAK wait + * until the rnr timer has fired before starting the + * retry flow + */ + if (unlikely(qp->req.need_retry && !qp->req.wait_for_rnr_timer)) { req_retry(qp); qp->req.need_retry = 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index ec9a70aecc1e..d9f01af4050d 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -123,6 +123,7 @@ struct rxe_req_info { int need_rd_atomic; int wait_psn; int need_retry; + int wait_for_rnr_timer; int noack_pkts; struct rxe_task task; }; -- 2.34.1
