lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1676477905-88043-8-git-send-email-guwen@linux.alibaba.com>
Date:   Thu, 16 Feb 2023 00:18:23 +0800
From:   Wen Gu <guwen@...ux.alibaba.com>
To:     kgraul@...ux.ibm.com, wenjia@...ux.ibm.com, jaka@...ux.ibm.com,
        davem@...emloft.net, edumazet@...gle.com, kuba@...nel.org,
        pabeni@...hat.com
Cc:     linux-s390@...r.kernel.org, netdev@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: [RFC PATCH net-next v3 7/9] net/smc: Avoid data copy from sndbuf to peer RMB in SMC-D

This patch aims to avoid data copy from local sndbuf to peer RMB by
attaching local sndbuf to peer RMB when DMBs have ISM_DMB_MAPPABLE
attribute.

After this, local sndbuf and peer RMB share the same physical memory.

 +----------+                     +----------+
 | socket A |                     | socket B |
 +----------+                     +----------+
       |                               ^
       |         +---------+           |
  regard as      |         | ----------|
  local sndbuf   |  B's    |     regard as
       |         |  RMB    |     local RMB
       |-------> |         |
                 +---------+

1. Actions on local RMB.

     a. Create or reuse RMB when connection is created;
     b. Unuse RMB when connection is freed;
     c. Free RMB when link group is freed;

2. Actions on local sndbuf.Attach local sndbuf to peer RMB.

     a. Attach local sndbuf to peer RMB by the rtoken exchanged through
        CLC message. Since then, accessing local sndbuf is equivalent to
        accessing peer RMB
     b. sndbuf_desc is exclusive to specific connection and won't be
        added to lgr buffer pool for reuse.
     c. Local sndbuf is detached from peer RMB when connection is freed,
        and sndbuf_desc will be freed.

Therefore, the data written to local sndbuf will directly reach peer RMB.

Signed-off-by: Wen Gu <guwen@...ux.alibaba.com>
---
 net/smc/af_smc.c   | 14 +++++++++++
 net/smc/smc_core.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 net/smc/smc_core.h |  1 +
 3 files changed, 84 insertions(+), 1 deletion(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index dcbd7e3..079a9f1 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1366,6 +1366,12 @@ static int smc_connect_ism(struct smc_sock *smc,
 	}
 
 	smc_conn_save_peer_info(smc, aclc);
+
+	if (smc_ism_dmb_mappable(smc->conn.lgr->smcd)) {
+		rc = smcd_buf_attach(smc);
+		if (rc)
+			goto connect_abort;
+	}
 	smc_close_init(smc);
 	smc_rx_init(smc);
 	smc_tx_init(smc);
@@ -2422,6 +2428,14 @@ static void smc_listen_work(struct work_struct *work)
 		mutex_unlock(&smc_server_lgr_pending);
 	}
 	smc_conn_save_peer_info(new_smc, cclc);
+
+	if (ini->is_smcd &&
+	    smc_ism_dmb_mappable(new_smc->conn.lgr->smcd)) {
+		rc = smcd_buf_attach(new_smc);
+		if (rc)
+			goto out_decl;
+	}
+
 	smc_listen_out_connected(new_smc);
 	SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini);
 	goto out_free;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 7642b16..5ed018b 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1129,6 +1129,20 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
 	}
 }
 
+static void smcd_buf_detach(struct smc_connection *conn)
+{
+	struct smcd_dev *smcd = conn->lgr->smcd;
+	u64 peer_token = conn->peer_token;
+
+	if (!conn->sndbuf_desc)
+		return;
+
+	smc_ism_detach_dmb(smcd, peer_token);
+
+	kfree(conn->sndbuf_desc);
+	conn->sndbuf_desc = NULL;
+}
+
 static void smc_buf_unuse(struct smc_connection *conn,
 			  struct smc_link_group *lgr)
 {
@@ -1175,6 +1189,10 @@ void smc_conn_free(struct smc_connection *conn)
 		if (!list_empty(&lgr->list))
 			smc_ism_unset_conn(conn);
 		tasklet_kill(&conn->rx_tsklet);
+
+		/* detach sndbuf from peer RMB */
+		if (smc_ism_dmb_mappable(lgr->smcd))
+			smcd_buf_detach(conn);
 	} else {
 		smc_cdc_wait_pend_tx_wr(conn);
 		if (current_work() != &conn->abort_work)
@@ -2425,15 +2443,23 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
  */
 int smc_buf_create(struct smc_sock *smc, bool is_smcd)
 {
+	bool sndbuf_created = false;
 	int rc;
 
+	if (is_smcd &&
+	    smc_ism_dmb_mappable(smc->conn.lgr->smcd))
+		goto create_rmb;
+
 	/* create send buffer */
 	rc = __smc_buf_create(smc, is_smcd, false);
 	if (rc)
 		return rc;
+	sndbuf_created = true;
+
+create_rmb:
 	/* create rmb */
 	rc = __smc_buf_create(smc, is_smcd, true);
-	if (rc) {
+	if (rc && sndbuf_created) {
 		mutex_lock(&smc->conn.lgr->sndbufs_lock);
 		list_del(&smc->conn.sndbuf_desc->list);
 		mutex_unlock(&smc->conn.lgr->sndbufs_lock);
@@ -2443,6 +2469,48 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd)
 	return rc;
 }
 
+int smcd_buf_attach(struct smc_sock *smc)
+{
+	struct smc_connection *conn = &smc->conn;
+	struct smcd_dev *smcd = conn->lgr->smcd;
+	u64 peer_token = conn->peer_token;
+	struct smc_buf_desc *buf_desc;
+	int rc;
+
+	buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL);
+	if (!buf_desc)
+		return -ENOMEM;
+
+	/* map local sndbuf desc to peer RMB, so operations on local
+	 * sndbuf are equivalent to operations on peer RMB.
+	 */
+	rc = smc_ism_attach_dmb(smcd, peer_token, buf_desc);
+	if (rc) {
+		rc = SMC_CLC_DECL_MEM;
+		goto free;
+	}
+
+	smc->sk.sk_sndbuf = buf_desc->len;
+	buf_desc->cpu_addr = (u8 *)buf_desc->cpu_addr + sizeof(struct smcd_cdc_msg);
+	buf_desc->len -=  sizeof(struct smcd_cdc_msg);
+	conn->sndbuf_desc = buf_desc;
+	conn->sndbuf_desc->used = 1;
+	atomic_set(&conn->sndbuf_space, conn->sndbuf_desc->len);
+	return 0;
+
+free:
+	if (conn->rmb_desc) {
+		/* free local RMB as well */
+		mutex_lock(&conn->lgr->rmbs_lock);
+		list_del(&conn->rmb_desc->list);
+		mutex_unlock(&conn->lgr->rmbs_lock);
+		smc_buf_free(conn->lgr, true, conn->rmb_desc);
+		conn->rmb_desc = NULL;
+	}
+	kfree(buf_desc);
+	return rc;
+}
+
 static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr)
 {
 	int i;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 285f9bd..080c810 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -518,6 +518,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
 void smc_smcd_terminate_all(struct smcd_dev *dev);
 void smc_smcr_terminate_all(struct smc_ib_device *smcibdev);
 int smc_buf_create(struct smc_sock *smc, bool is_smcd);
+int smcd_buf_attach(struct smc_sock *smc);
 int smc_uncompress_bufsize(u8 compressed);
 int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *link,
 			    struct smc_clc_msg_accept_confirm *clc);
-- 
1.8.3.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ