linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Selvin Xavier <selvin.xavier@broadcom.com>
To: dledford@redhat.com, jgg@ziepe.ca
Cc: linux-rdma@vger.kernel.org, Selvin Xavier <selvin.xavier@broadcom.com>
Subject: [PATCH for-next 2/6] RDMA/bnxt_re: Fix Send Work Entry state check while polling completions
Date: Mon, 25 Nov 2019 00:39:30 -0800	[thread overview]
Message-ID: <1574671174-5064-3-git-send-email-selvin.xavier@broadcom.com> (raw)
In-Reply-To: <1574671174-5064-1-git-send-email-selvin.xavier@broadcom.com>

Some adapters need fence Work Entry to handle retransmission.
Currently the driver checks for this condition, only if the Send
queue entry is signalled. Implement the condition check, irrespective
of the signalled state of the Work queue entries

Fixes: 9152e0b722b2 ("RDMA/bnxt_re: HW workarounds for handling specific conditions")
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/infiniband/hw/bnxt_re/qplib_fp.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 958c1ff..4d07d22 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -2283,13 +2283,13 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq,
 			/* Add qp to flush list of the CQ */
 			bnxt_qplib_add_flush_qp(qp);
 		} else {
+			/* Before we complete, do WA 9060 */
+			if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
+				      cqe_sq_cons)) {
+				*lib_qp = qp;
+				goto out;
+			}
 			if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) {
-				/* Before we complete, do WA 9060 */
-				if (do_wa9060(qp, cq, cq_cons, sw_sq_cons,
-					      cqe_sq_cons)) {
-					*lib_qp = qp;
-					goto out;
-				}
 				cqe->status = CQ_REQ_STATUS_OK;
 				cqe++;
 				(*budget)--;
-- 
2.5.5


  parent reply	other threads:[~2019-11-25  8:40 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-25  8:39 [PATCH for-next 0/6] RDMA/bnxt_re driver update Selvin Xavier
2019-11-25  8:39 ` [PATCH for-next 1/6] RDMA/bnxt_re: Avoid freeing MR resources if dereg fails Selvin Xavier
2019-11-25  8:39 ` Selvin Xavier [this message]
2019-11-25  8:39 ` [PATCH for-next 3/6] RDMA/bnxt_re: Add more flags in device init and uninit path Selvin Xavier
2019-11-25  8:39 ` [PATCH for-next 4/6] RDMA/bnxt_re: Refactor device add/remove functionalities Selvin Xavier
2020-01-03 19:36   ` Jason Gunthorpe
2020-02-18  7:23     ` Selvin Xavier
2019-11-25  8:39 ` [PATCH for-next 5/6] RDMA/bnxt_re: Use driver_unregister and unregistration API Selvin Xavier
2020-01-03 19:44   ` Jason Gunthorpe
2020-02-18 11:49     ` Selvin Xavier
2020-02-19  0:15       ` Jason Gunthorpe
2020-02-19  9:27         ` Selvin Xavier
2020-02-19 13:15           ` Jason Gunthorpe
2019-11-25  8:39 ` [PATCH for-next 6/6] RDMA/bnxt_re: Report more number of completion vectors Selvin Xavier
2020-01-03 19:46   ` Jason Gunthorpe
2019-12-11 12:57 ` [PATCH for-next 0/6] RDMA/bnxt_re driver update Selvin Xavier
2019-12-11 16:20   ` Jason Gunthorpe
2020-01-03 19:29 ` Jason Gunthorpe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1574671174-5064-3-git-send-email-selvin.xavier@broadcom.com \
    --to=selvin.xavier@broadcom.com \
    --cc=dledford@redhat.com \
    --cc=jgg@ziepe.ca \
    --cc=linux-rdma@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).