From: Bob Pearson <rpearsonhpe@gmail.com>
To: yanjun.zhu@linux.dev, jgg@ziepe.ca, leon@kernel.org,
linux-rdma@vger.kernel.org, jhack@hpe.com
Cc: Bob Pearson <rpearsonhpe@gmail.com>
Subject: [PATCH for-next 07/11] RDMA/rxe: Don't call rxe_requester from rxe_completer
Date: Tue, 26 Mar 2024 12:43:22 -0500 [thread overview]
Message-ID: <20240326174325.300849-9-rpearsonhpe@gmail.com> (raw)
In-Reply-To: <20240326174325.300849-2-rpearsonhpe@gmail.com>
Instead of rescheduling rxe_requester from rxe_completer() just extend
the duration of rxe_sender() by one pass. Setting run_requester_again
forces rxe_completer() to return 0 which will cause rxe_sender() to be
called at least one more time.
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index ea64a25fe876..c41743fbd5f1 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -82,6 +82,8 @@ static unsigned long rnrnak_usec[32] = {
[IB_RNR_TIMER_491_52] = 491520,
};
+static int run_requester_again;
+
static inline unsigned long rnrnak_jiffies(u8 timeout)
{
return max_t(unsigned long,
@@ -325,7 +327,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp,
qp->comp.psn = pkt->psn;
if (qp->req.wait_psn) {
qp->req.wait_psn = 0;
- rxe_sched_task(&qp->send_task);
+ run_requester_again = 1;
}
}
return COMPST_ERROR_RETRY;
@@ -476,7 +478,7 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
*/
if (qp->req.wait_fence) {
qp->req.wait_fence = 0;
- rxe_sched_task(&qp->send_task);
+ run_requester_again = 1;
}
}
@@ -515,7 +517,7 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp,
if (qp->req.need_rd_atomic) {
qp->comp.timeout_retry = 0;
qp->req.need_rd_atomic = 0;
- rxe_sched_task(&qp->send_task);
+ run_requester_again = 1;
}
}
@@ -541,7 +543,7 @@ static inline enum comp_state complete_wqe(struct rxe_qp *qp,
if (qp->req.wait_psn) {
qp->req.wait_psn = 0;
- rxe_sched_task(&qp->send_task);
+ run_requester_again = 1;
}
}
@@ -654,6 +656,8 @@ int rxe_completer(struct rxe_qp *qp)
int ret;
unsigned long flags;
+ run_requester_again = 0;
+
spin_lock_irqsave(&qp->state_lock, flags);
if (!qp->valid || qp_state(qp) == IB_QPS_ERR ||
qp_state(qp) == IB_QPS_RESET) {
@@ -737,7 +741,7 @@ int rxe_completer(struct rxe_qp *qp)
if (qp->req.wait_psn) {
qp->req.wait_psn = 0;
- rxe_sched_task(&qp->send_task);
+ run_requester_again = 1;
}
state = COMPST_DONE;
@@ -792,7 +796,7 @@ int rxe_completer(struct rxe_qp *qp)
RXE_CNT_COMP_RETRY);
qp->req.need_retry = 1;
qp->comp.started_retry = 1;
- rxe_sched_task(&qp->send_task);
+ run_requester_again = 1;
}
goto done;
@@ -843,8 +847,9 @@ int rxe_completer(struct rxe_qp *qp)
ret = 0;
goto out;
exit:
- ret = -EAGAIN;
+ ret = (run_requester_again) ? 0 : -EAGAIN;
out:
+ run_requester_again = 0;
if (pkt)
free_pkt(pkt);
return ret;
--
2.43.0
next prev parent reply other threads:[~2024-03-26 17:44 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-26 17:43 [PATCH for-next 00/11] RDMA/rxe: Various fixes and cleanups Bob Pearson
2024-03-26 17:43 ` [PATCH for-next 01/11] RDMA/rxe: Fix seg fault in rxe_comp_queue_pkt Bob Pearson
2024-04-02 12:31 ` Leon Romanovsky
2024-03-26 17:43 ` [PATCH for-next 02/11] RDMA/rxe: Allow good work requests to be executed Bob Pearson
2024-04-02 12:57 ` Zhu Yanjun
2024-03-26 17:43 ` [PATCH for-next 03/11] RDMA/rxe: Remove redundant scheduling of rxe_completer Bob Pearson
2024-03-26 17:43 ` [PATCH for-next 04/11] RDMA/rxe: Merge request and complete tasks Bob Pearson
2024-03-26 17:43 ` [PATCH for-next 05/11] RDMA/rxe: Remove save/rollback_state in rxe_requester Bob Pearson
2024-03-26 17:43 ` [PATCH for-next 06/11] RDMA/rxe: Don't schedule rxe_completer() in rxe_requester() Bob Pearson
2024-03-26 17:43 ` Bob Pearson [this message]
2024-04-02 12:29 ` [PATCH for-next 07/11] RDMA/rxe: Don't call rxe_requester from rxe_completer Leon Romanovsky
2024-03-26 17:43 ` [PATCH for-next 08/11] RDMA/rxe: Don't call direct between tasks Bob Pearson
2024-03-26 17:43 ` [PATCH for-next 09/11] RDMA/rxe: Fix incorrect rxe_put in error path Bob Pearson
2024-03-26 17:43 ` [PATCH for-next 10/11] RDMA/rxe: Make rxe_loopback match rxe_send behavior Bob Pearson
2024-03-26 17:43 ` [PATCH for-next 11/11] RDMA/rxe: Get rid of pkt resend on err Bob Pearson
2024-03-26 19:01 ` [PATCH for-next 00/11] RDMA/rxe: Various fixes and cleanups Zhu Yanjun
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=20240326174325.300849-9-rpearsonhpe@gmail.com \
--to=rpearsonhpe@gmail.com \
--cc=jgg@ziepe.ca \
--cc=jhack@hpe.com \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=yanjun.zhu@linux.dev \
/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