From: Wen Gu <guwen@linux.alibaba.com>
To: wintera@linux.ibm.com, wenjia@linux.ibm.com, hca@linux.ibm.com,
gor@linux.ibm.com, agordeev@linux.ibm.com, davem@davemloft.net,
edumazet@google.com, kuba@kernel.org, pabeni@redhat.com,
kgraul@linux.ibm.com, jaka@linux.ibm.com
Cc: borntraeger@linux.ibm.com, svens@linux.ibm.com,
alibuda@linux.alibaba.com, tonylu@linux.alibaba.com,
guwen@linux.alibaba.com, linux-s390@vger.kernel.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [RFC PATCH net-next 12/13] net/smc: adapt cursor update when sndbuf is mapped to peer DMB
Date: Sun, 10 Dec 2023 21:24:13 +0800 [thread overview]
Message-ID: <1702214654-32069-13-git-send-email-guwen@linux.alibaba.com> (raw)
In-Reply-To: <1702214654-32069-1-git-send-email-guwen@linux.alibaba.com>
Since ghost sndbuf shares the same physical memory with peer DMB,
the cursor update processing needs to be adapted to ensure that the
data to be consumed won't be overwritten.
So in this case, the fin_curs and sndbuf_space that were originally
updated after sending the CDC message should be modified to not be
update until the peer updates cons_curs.
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
---
net/smc/smc_cdc.c | 52 +++++++++++++++++++++++++++++++++++++++++-----------
1 file changed, 41 insertions(+), 11 deletions(-)
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index c820ef1..f2b0bcc 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -18,6 +18,7 @@
#include "smc_tx.h"
#include "smc_rx.h"
#include "smc_close.h"
+#include "smc_ism.h"
/********************************** send *************************************/
@@ -255,17 +256,25 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
return rc;
smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn);
conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
- /* Calculate transmitted data and increment free send buffer space */
- diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
- &conn->tx_curs_sent);
- /* increased by confirmed number of bytes */
- smp_mb__before_atomic();
- atomic_add(diff, &conn->sndbuf_space);
- /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
- smp_mb__after_atomic();
- smc_curs_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn);
+ if (!smc_ism_dmb_mappable(conn->lgr->smcd)) {
+ /* Ghost sndbuf shares the same memory region with
+ * peer DMB, so don't update the tx_curs_fin and
+ * sndbuf_space until peer has consumed the data.
+ */
+ /* Calculate transmitted data and increment free
+ * send buffer space
+ */
+ diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
+ &conn->tx_curs_sent);
+ /* increased by confirmed number of bytes */
+ smp_mb__before_atomic();
+ atomic_add(diff, &conn->sndbuf_space);
+ /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+ smp_mb__after_atomic();
+ smc_curs_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn);
- smc_tx_sndbuf_nonfull(smc);
+ smc_tx_sndbuf_nonfull(smc);
+ }
return rc;
}
@@ -323,7 +332,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
{
union smc_host_cursor cons_old, prod_old;
struct smc_connection *conn = &smc->conn;
- int diff_cons, diff_prod;
+ int diff_cons, diff_prod, diff_tx;
smc_curs_copy(&prod_old, &conn->local_rx_ctrl.prod, conn);
smc_curs_copy(&cons_old, &conn->local_rx_ctrl.cons, conn);
@@ -339,6 +348,27 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
atomic_add(diff_cons, &conn->peer_rmbe_space);
/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
smp_mb__after_atomic();
+
+ if (conn->lgr->is_smcd &&
+ smc_ism_dmb_mappable(conn->lgr->smcd)) {
+ /* Ghost sndbuf shares the same memory region with
+ * peer RMB, so update tx_curs_fin and sndbuf_space
+ * when peer has consumed the data.
+ */
+ /* calculate peer rmb consumed data */
+ diff_tx = smc_curs_diff(conn->sndbuf_desc->len,
+ &conn->tx_curs_fin,
+ &conn->local_rx_ctrl.cons);
+ /* increase local sndbuf space and fin_curs */
+ smp_mb__before_atomic();
+ atomic_add(diff_tx, &conn->sndbuf_space);
+ /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+ smp_mb__after_atomic();
+ smc_curs_copy(&conn->tx_curs_fin,
+ &conn->local_rx_ctrl.cons, conn);
+
+ smc_tx_sndbuf_nonfull(smc);
+ }
}
diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old,
--
1.8.3.1
next prev parent reply other threads:[~2023-12-10 13:25 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-10 13:24 [RFC PATCH net-next 00/13] net/smc: implement loopback-ism used by SMC-D Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 01/13] net/smc: improve SMC-D device dump for virtual ISM Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 02/13] net/smc: decouple specialized struct from SMC-D DMB registration Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 03/13] net/smc: introduce virtual ISM device loopback-ism Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 04/13] net/smc: implement ID-related operations of loopback-ism Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 05/13] net/smc: implement some unsupported " Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 06/13] net/smc: implement DMB-related " Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 07/13] net/smc: register loopback-ism into SMC-D device list Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 08/13] net/smc: introduce loopback-ism runtime switch Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 09/13] net/smc: introduce loopback-ism statistics attributes Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 10/13] net/smc: introduce operations to {at|de}tach ghost sndbuf to peer DMB Wen Gu
2023-12-10 13:24 ` [RFC PATCH net-next 11/13] net/smc: attach or detach " Wen Gu
2023-12-10 13:24 ` Wen Gu [this message]
2023-12-10 13:24 ` [RFC PATCH net-next 13/13] net/smc: implement {at|de}tach_dmb interfaces of loopback-ism Wen Gu
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=1702214654-32069-13-git-send-email-guwen@linux.alibaba.com \
--to=guwen@linux.alibaba.com \
--cc=agordeev@linux.ibm.com \
--cc=alibuda@linux.alibaba.com \
--cc=borntraeger@linux.ibm.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=jaka@linux.ibm.com \
--cc=kgraul@linux.ibm.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=svens@linux.ibm.com \
--cc=tonylu@linux.alibaba.com \
--cc=wenjia@linux.ibm.com \
--cc=wintera@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox