Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Bob Pearson <rpearsonhpe@gmail.com>
To: jgg@nvidia.com, zyjzyj2000@gmail.com, linux-rdma@vger.kernel.org,
	frank.zago@hpe.com, jhack@hpe.com
Cc: Bob Pearson <rpearsonhpe@gmail.com>
Subject: [PATCH 3/5] RDMA/rxe: Move atomic responder res to atomic_reply
Date: Mon,  6 Jun 2022 09:38:35 -0500	[thread overview]
Message-ID: <20220606143836.3323-4-rpearsonhpe@gmail.com> (raw)
In-Reply-To: <20220606143836.3323-1-rpearsonhpe@gmail.com>

Move the allocation of the atomic responder resource up into
rxe_atomic_reply() from send_atomic_ack(). In preparation for
merging the normal and retry atomic responder flows.

Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
---
 drivers/infiniband/sw/rxe/rxe_resp.c | 49 +++++++++++++++++-----------
 1 file changed, 30 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 4babd6fbfefe..4908b9fc0204 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -554,12 +554,36 @@ static enum resp_states write_data_in(struct rxe_qp *qp,
 /* Guarantee atomicity of atomic operations at the machine level. */
 static DEFINE_SPINLOCK(atomic_ops_lock);
 
+static struct resp_res *rxe_prepare_atomic_res(struct rxe_qp *qp,
+					       struct rxe_pkt_info *pkt)
+{
+	struct resp_res *res;
+
+	res = &qp->resp.resources[qp->resp.res_head];
+	rxe_advance_resp_resource(qp);
+	free_rd_atomic_resource(qp, res);
+
+	res->type = RXE_ATOMIC_MASK;
+	res->first_psn = pkt->psn;
+	res->last_psn = pkt->psn;
+	res->cur_psn = pkt->psn;
+	res->replay = 0;
+
+	return res;
+}
+
 static enum resp_states rxe_atomic_reply(struct rxe_qp *qp,
 					 struct rxe_pkt_info *pkt)
 {
 	u64 *vaddr;
 	enum resp_states ret;
 	struct rxe_mr *mr = qp->resp.mr;
+	struct resp_res *res = qp->resp.res;
+
+	if (!res) {
+		res = rxe_prepare_atomic_res(qp, pkt);
+		qp->resp.res = res;
+	}
 
 	if (mr->state != RXE_MR_STATE_VALID) {
 		ret = RESPST_ERR_RKEY_VIOLATION;
@@ -1028,30 +1052,13 @@ static int send_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 	return err;
 }
 
-static struct resp_res *rxe_prepare_atomic_res(struct rxe_qp *qp,
-					       struct rxe_pkt_info *pkt)
-{
-	struct resp_res *res;
-
-	res = &qp->resp.resources[qp->resp.res_head];
-	rxe_advance_resp_resource(qp);
-	free_rd_atomic_resource(qp, res);
-
-	res->type = RXE_ATOMIC_MASK;
-	res->first_psn = pkt->psn;
-	res->last_psn = pkt->psn;
-	res->cur_psn = pkt->psn;
-
-	return res;
-}
-
 static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 			   u8 syndrome)
 {
 	int err = 0;
 	struct rxe_pkt_info ack_pkt;
 	struct sk_buff *skb;
-	struct resp_res *res;
+	struct resp_res *res = qp->resp.res;
 
 	skb = prepare_ack_packet(qp, pkt, &ack_pkt,
 				 IB_OPCODE_RC_ATOMIC_ACKNOWLEDGE, 0, pkt->psn,
@@ -1063,7 +1070,6 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 
 	skb_get(skb);
 
-	res = rxe_prepare_atomic_res(qp, pkt);
 	res->atomic.skb = skb;
 
 	err = rxe_xmit_packet(qp, &ack_pkt, skb);
@@ -1071,6 +1077,11 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 		pr_err_ratelimited("Failed sending ack\n");
 		rxe_put(qp);
 	}
+
+	/* have to clear this since it is used to trigger
+	 * long read replies
+	 */
+	qp->resp.res = NULL;
 out:
 	return err;
 }
-- 
2.34.1


  parent reply	other threads:[~2022-06-06 14:39 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-06 14:38 [PATCH for-next 0/5] Fix incorrect atomic retry behavior Bob Pearson
2022-06-06 14:38 ` [PATCH 1/5] RDMA/rxe: Move code to rxe_prepare_atomic_res() Bob Pearson
2022-06-06 14:38 ` [PATCH 2/5] RDMA/rxe: Add a responder state for atomic reply Bob Pearson
2022-06-06 14:38 ` Bob Pearson [this message]
2022-06-06 14:38 ` [PATCH 4/5] RDMA/rxe: Move atomic original value to res Bob Pearson
2022-06-06 14:38 ` [PATCH 5/5] RDMA/rxe: Merge normal and retry atomic flows Bob Pearson
2022-06-30 18:52 ` [PATCH for-next 0/5] Fix incorrect atomic retry behavior Jason Gunthorpe
2022-06-30 19:28   ` Bob Pearson

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=20220606143836.3323-4-rpearsonhpe@gmail.com \
    --to=rpearsonhpe@gmail.com \
    --cc=frank.zago@hpe.com \
    --cc=jgg@nvidia.com \
    --cc=jhack@hpe.com \
    --cc=linux-rdma@vger.kernel.org \
    --cc=zyjzyj2000@gmail.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