Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Max Gurtovoy <mgurtovoy@nvidia.com>
To: <sagi@grimberg.me>, <jgg@nvidia.com>, <linux-rdma@vger.kernel.org>
Cc: <sergeygo@nvidia.com>, <leonro@nvidia.com>, <oren@nvidia.com>,
	<israelr@nvidia.com>, Max Gurtovoy <mgurtovoy@nvidia.com>
Subject: [PATCH 1/1] IB/iser: drain the entire QP during destruction flow
Date: Wed, 15 Jun 2022 11:28:39 +0300	[thread overview]
Message-ID: <20220615082839.26328-1-mgurtovoy@nvidia.com> (raw)

It's important to drain both the sq and the rq to make sure all WRs were
flushed before destroying the QP.

Reviewed-by: Sergey Gorenko <sergeygo@nvidia.com>
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
---
 drivers/infiniband/ulp/iser/iser_verbs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 5dbad68c7390..df3e7a1bf293 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -246,6 +246,7 @@ static int iser_create_ib_conn_res(struct ib_conn *ib_conn)
 	device = ib_conn->device;
 	ib_dev = device->ib_device;
 
+	/* +1 for drain */
 	if (ib_conn->pi_support)
 		max_send_wr = ISER_QP_SIG_MAX_REQ_DTOS + 1;
 	else
@@ -267,7 +268,8 @@ static int iser_create_ib_conn_res(struct ib_conn *ib_conn)
 	init_attr.qp_context = (void *)ib_conn;
 	init_attr.send_cq = ib_conn->cq;
 	init_attr.recv_cq = ib_conn->cq;
-	init_attr.cap.max_recv_wr = ISER_QP_MAX_RECV_DTOS;
+	/* +1 for drain */
+	init_attr.cap.max_recv_wr = ISER_QP_MAX_RECV_DTOS + 1;
 	init_attr.cap.max_send_sge = 2;
 	init_attr.cap.max_recv_sge = 1;
 	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
@@ -485,7 +487,7 @@ int iser_conn_terminate(struct iser_conn *iser_conn)
 				 iser_conn, err);
 
 		/* block until all flush errors are consumed */
-		ib_drain_sq(ib_conn->qp);
+		ib_drain_qp(ib_conn->qp);
 	}
 
 	return 1;
-- 
2.18.1


             reply	other threads:[~2022-06-15  8:29 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-15  8:28 Max Gurtovoy [this message]
2022-06-24 19:38 ` [PATCH 1/1] IB/iser: drain the entire QP during destruction flow 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=20220615082839.26328-1-mgurtovoy@nvidia.com \
    --to=mgurtovoy@nvidia.com \
    --cc=israelr@nvidia.com \
    --cc=jgg@nvidia.com \
    --cc=leonro@nvidia.com \
    --cc=linux-rdma@vger.kernel.org \
    --cc=oren@nvidia.com \
    --cc=sagi@grimberg.me \
    --cc=sergeygo@nvidia.com \
    /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