All of lore.kernel.org
 help / color / mirror / Atom feed
From: "D. Wythe" <alibuda@linux.alibaba.com>
To: kgraul@linux.ibm.com, wenjia@linux.ibm.com, jaka@linux.ibm.com
Cc: kuba@kernel.org, davem@davemloft.net, netdev@vger.kernel.org,
	linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org,
	"D. Wythe" <alibuda@linux.alibaba.com>
Subject: [net-next v7 3/4] net/smc: reduce unnecessary blocking in smcr_lgr_reg_rmbs()
Date: Thu,  2 Feb 2023 16:26:41 +0800	[thread overview]
Message-ID: <1675326402-109943-4-git-send-email-alibuda@linux.alibaba.com> (raw)
In-Reply-To: <1675326402-109943-1-git-send-email-alibuda@linux.alibaba.com>

From: "D. Wythe" <alibuda@linux.alibaba.com>

Unlike smc_buf_create() and smcr_buf_unuse(), smcr_lgr_reg_rmbs() is
exclusive when assigned rmb_desc was not registered, although it can be
executed in parallel when assigned rmb_desc was registered already
and only performs read semtamics on it. Hence, we can not simply replace
it with read semaphore.

The idea here is that if the assigned rmb_desc was registered already,
use read semaphore to protect the critical section, once the assigned
rmb_desc was not registered, keep using keep write semaphore still
to keep its exclusivity.

Thanks to the reusable features of rmb_desc, which allows us to execute
in parallel in most cases.

Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
 net/smc/af_smc.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 6e93ad6..b163266 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -519,11 +519,26 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
 			     struct smc_buf_desc *rmb_desc)
 {
 	struct smc_link_group *lgr = link->lgr;
+	bool do_slow = false;
 	int i, rc = 0;
 
 	rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
 	if (rc)
 		return rc;
+
+	down_read(&lgr->llc_conf_mutex);
+	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+		if (!smc_link_active(&lgr->lnk[i]))
+			continue;
+		if (!rmb_desc->is_reg_mr[link->link_idx]) {
+			up_read(&lgr->llc_conf_mutex);
+			goto slow_path;
+		}
+	}
+	/* mr register already */
+	goto fast_path;
+slow_path:
+	do_slow = true;
 	/* protect against parallel smc_llc_cli_rkey_exchange() and
 	 * parallel smcr_link_reg_buf()
 	 */
@@ -535,7 +550,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
 		if (rc)
 			goto out;
 	}
-
+fast_path:
 	/* exchange confirm_rkey msg with peer */
 	rc = smc_llc_do_confirm_rkey(link, rmb_desc);
 	if (rc) {
@@ -544,7 +559,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
 	}
 	rmb_desc->is_conf_rkey = true;
 out:
-	up_write(&lgr->llc_conf_mutex);
+	do_slow ? up_write(&lgr->llc_conf_mutex) : up_read(&lgr->llc_conf_mutex);
 	smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
 	return rc;
 }
-- 
1.8.3.1


  parent reply	other threads:[~2023-02-02  8:27 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-02  8:26 [net-next v7 0/4] net/smc: optimize the parallelism of SMC-R connections D. Wythe
2023-02-02  8:26 ` [net-next v7 1/4] net/smc: llc_conf_mutex refactor, replace it with rw_semaphore D. Wythe
2023-02-02  8:26 ` [net-next v7 2/4] net/smc: use read semaphores to reduce unnecessary blocking in smc_buf_create() & smcr_buf_unuse() D. Wythe
2023-02-02  8:26 ` D. Wythe [this message]
2023-02-02  8:26 ` [net-next v7 4/4] net/smc: replace mutex rmbs_lock and sndbufs_lock with rw_semaphore D. Wythe
2023-02-03 17:36 ` [net-next v7 0/4] net/smc: optimize the parallelism of SMC-R connections Wenjia Zhang
2023-02-06 11:06 ` Wenjia Zhang
2023-02-06 12:11   ` D. Wythe

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=1675326402-109943-4-git-send-email-alibuda@linux.alibaba.com \
    --to=alibuda@linux.alibaba.com \
    --cc=davem@davemloft.net \
    --cc=jaka@linux.ibm.com \
    --cc=kgraul@linux.ibm.com \
    --cc=kuba@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=wenjia@linux.ibm.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.