summaryrefslogtreecommitdiff
path: root/net/smc
diff options
context:
space:
mode:
Diffstat (limited to 'net/smc')
-rw-r--r--net/smc/Kconfig4
-rw-r--r--net/smc/af_smc.c118
-rw-r--r--net/smc/smc.h3
-rw-r--r--net/smc/smc_cdc.c8
-rw-r--r--net/smc/smc_cdc.h4
-rw-r--r--net/smc/smc_clc.c23
-rw-r--r--net/smc/smc_clc.h4
-rw-r--r--net/smc/smc_close.c31
-rw-r--r--net/smc/smc_close.h1
-rw-r--r--net/smc/smc_core.c417
-rw-r--r--net/smc/smc_core.h32
-rw-r--r--net/smc/smc_ib.c154
-rw-r--r--net/smc/smc_ib.h20
-rw-r--r--net/smc/smc_llc.c1
-rw-r--r--net/smc/smc_llc.h1
-rw-r--r--net/smc/smc_pnet.c5
-rw-r--r--net/smc/smc_pnet.h1
-rw-r--r--net/smc/smc_rx.c6
-rw-r--r--net/smc/smc_rx.h1
-rw-r--r--net/smc/smc_tx.c28
-rw-r--r--net/smc/smc_tx.h1
-rw-r--r--net/smc/smc_wr.c66
-rw-r--r--net/smc/smc_wr.h2
23 files changed, 611 insertions, 320 deletions
diff --git a/net/smc/Kconfig b/net/smc/Kconfig
index 33954852f3f8..c717ef0896aa 100644
--- a/net/smc/Kconfig
+++ b/net/smc/Kconfig
@@ -8,10 +8,6 @@ config SMC
The Linux implementation of the SMC-R solution is designed as
a separate socket family SMC.
- Warning: SMC will expose all memory for remote reads and writes
- once a connection is established. Don't enable this option except
- for tightly controlled lab environment.
-
Select this option if you want to run SMC socket applications
config SMC_DIAG
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 6793d7348cc8..6451c5013e06 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -282,6 +282,7 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock,
__be32 *subnet, u8 *prefix_len)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
+ struct in_device *in_dev;
struct sockaddr_in addr;
int rc = -ENOENT;
int len;
@@ -298,14 +299,17 @@ int smc_netinfo_by_tcpsk(struct socket *clcsock,
/* get address to which the internal TCP socket is bound */
kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len);
/* analyze IPv4 specific data of net_device belonging to TCP socket */
- for_ifa(dst->dev->ip_ptr) {
- if (ifa->ifa_address != addr.sin_addr.s_addr)
+ rcu_read_lock();
+ in_dev = __in_dev_get_rcu(dst->dev);
+ for_ifa(in_dev) {
+ if (!inet_ifa_match(addr.sin_addr.s_addr, ifa))
continue;
*prefix_len = inet_mask_len(ifa->ifa_mask);
*subnet = ifa->ifa_address & ifa->ifa_mask;
rc = 0;
break;
- } endfor_ifa(dst->dev->ip_ptr);
+ } endfor_ifa(in_dev);
+ rcu_read_unlock();
out_rel:
dst_release(dst);
@@ -338,6 +342,12 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc, union ib_gid *gid)
return SMC_CLC_DECL_INTERR;
smc_wr_remember_qp_attr(link);
+
+ rc = smc_wr_reg_send(link,
+ smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
+ if (rc)
+ return SMC_CLC_DECL_INTERR;
+
/* send CONFIRM LINK response over RoCE fabric */
rc = smc_llc_send_confirm_link(link,
link->smcibdev->mac[link->ibport - 1],
@@ -380,6 +390,12 @@ static int smc_connect_rdma(struct smc_sock *smc)
int rc = 0;
u8 ibport;
+ if (!tcp_sk(smc->clcsock->sk)->syn_smc) {
+ /* peer has not signalled SMC-capability */
+ smc->use_fallback = true;
+ goto out_connected;
+ }
+
/* IPSec connections opt out of SMC-R optimizations */
if (using_ipsec(smc)) {
reason_code = SMC_CLC_DECL_IPSEC;
@@ -430,12 +446,8 @@ static int smc_connect_rdma(struct smc_sock *smc)
smc_conn_save_peer_info(smc, &aclc);
- rc = smc_sndbuf_create(smc);
- if (rc) {
- reason_code = SMC_CLC_DECL_MEM;
- goto decline_rdma_unlock;
- }
- rc = smc_rmb_create(smc);
+ /* create send buffer and rmb */
+ rc = smc_buf_create(smc);
if (rc) {
reason_code = SMC_CLC_DECL_MEM;
goto decline_rdma_unlock;
@@ -459,7 +471,20 @@ static int smc_connect_rdma(struct smc_sock *smc)
reason_code = SMC_CLC_DECL_INTERR;
goto decline_rdma_unlock;
}
+ } else {
+ struct smc_buf_desc *buf_desc = smc->conn.rmb_desc;
+
+ if (!buf_desc->reused) {
+ /* register memory region for new rmb */
+ rc = smc_wr_reg_send(link,
+ buf_desc->mr_rx[SMC_SINGLE_LINK]);
+ if (rc) {
+ reason_code = SMC_CLC_DECL_INTERR;
+ goto decline_rdma_unlock;
+ }
+ }
}
+ smc_rmb_sync_sg_for_device(&smc->conn);
rc = smc_clc_send_confirm(smc);
if (rc)
@@ -494,7 +519,7 @@ decline_rdma:
/* RDMA setup failed, switch back to TCP */
smc->use_fallback = true;
if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- rc = smc_clc_send_decline(smc, reason_code, 0);
+ rc = smc_clc_send_decline(smc, reason_code);
if (rc < sizeof(struct smc_clc_msg_decline))
goto out_err;
}
@@ -536,6 +561,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
}
smc_copy_sock_settings_to_clc(smc);
+ tcp_sk(smc->clcsock->sk)->syn_smc = 1;
rc = kernel_connect(smc->clcsock, addr, alen, flags);
if (rc)
goto out;
@@ -692,6 +718,12 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
int rc;
link = &lgr->lnk[SMC_SINGLE_LINK];
+
+ rc = smc_wr_reg_send(link,
+ smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
+ if (rc)
+ return SMC_CLC_DECL_INTERR;
+
/* send CONFIRM LINK request to client over the RoCE fabric */
rc = smc_llc_send_confirm_link(link,
link->smcibdev->mac[link->ibport - 1],
@@ -734,6 +766,12 @@ static void smc_listen_work(struct work_struct *work)
u8 prefix_len;
u8 ibport;
+ /* check if peer is smc capable */
+ if (!tcp_sk(newclcsock->sk)->syn_smc) {
+ new_smc->use_fallback = true;
+ goto out_connected;
+ }
+
/* do inband token exchange -
*wait for and receive SMC Proposal CLC message
*/
@@ -779,46 +817,50 @@ static void smc_listen_work(struct work_struct *work)
mutex_lock(&smc_create_lgr_pending);
local_contact = smc_conn_create(new_smc, peeraddr.sin_addr.s_addr,
smcibdev, ibport, &pclc.lcl, 0);
- if (local_contact == SMC_REUSE_CONTACT)
- /* lock no longer needed, free it due to following
- * smc_clc_wait_msg() call
- */
- mutex_unlock(&smc_create_lgr_pending);
if (local_contact < 0) {
rc = local_contact;
if (rc == -ENOMEM)
reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- else if (rc == -ENOLINK)
- reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
- goto decline_rdma;
+ goto decline_rdma_unlock;
}
link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
- rc = smc_sndbuf_create(new_smc);
+ /* create send buffer and rmb */
+ rc = smc_buf_create(new_smc);
if (rc) {
reason_code = SMC_CLC_DECL_MEM;
- goto decline_rdma;
- }
- rc = smc_rmb_create(new_smc);
- if (rc) {
- reason_code = SMC_CLC_DECL_MEM;
- goto decline_rdma;
+ goto decline_rdma_unlock;
}
smc_close_init(new_smc);
smc_rx_init(new_smc);
+ if (local_contact != SMC_FIRST_CONTACT) {
+ struct smc_buf_desc *buf_desc = new_smc->conn.rmb_desc;
+
+ if (!buf_desc->reused) {
+ /* register memory region for new rmb */
+ rc = smc_wr_reg_send(link,
+ buf_desc->mr_rx[SMC_SINGLE_LINK]);
+ if (rc) {
+ reason_code = SMC_CLC_DECL_INTERR;
+ goto decline_rdma_unlock;
+ }
+ }
+ }
+ smc_rmb_sync_sg_for_device(&new_smc->conn);
+
rc = smc_clc_send_accept(new_smc, local_contact);
if (rc)
- goto out_err;
+ goto out_err_unlock;
/* receive SMC Confirm CLC message */
reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
SMC_CLC_CONFIRM);
if (reason_code < 0)
- goto out_err;
+ goto out_err_unlock;
if (reason_code > 0)
- goto decline_rdma;
+ goto decline_rdma_unlock;
smc_conn_save_peer_info(new_smc, &cclc);
if (local_contact == SMC_FIRST_CONTACT)
smc_link_save_peer_info(link, &cclc);
@@ -826,35 +868,34 @@ static void smc_listen_work(struct work_struct *work)
rc = smc_rmb_rtoken_handling(&new_smc->conn, &cclc);
if (rc) {
reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma;
+ goto decline_rdma_unlock;
}
if (local_contact == SMC_FIRST_CONTACT) {
rc = smc_ib_ready_link(link);
if (rc) {
reason_code = SMC_CLC_DECL_INTERR;
- goto decline_rdma;
+ goto decline_rdma_unlock;
}
/* QP confirmation over RoCE fabric */
reason_code = smc_serv_conf_first_link(new_smc);
if (reason_code < 0) {
/* peer is not aware of a problem */
rc = reason_code;
- goto out_err;
+ goto out_err_unlock;
}
if (reason_code > 0)
- goto decline_rdma;
+ goto decline_rdma_unlock;
}
smc_tx_init(new_smc);
+ mutex_unlock(&smc_create_lgr_pending);
out_connected:
sk_refcnt_debug_inc(newsmcsk);
if (newsmcsk->sk_state == SMC_INIT)
newsmcsk->sk_state = SMC_ACTIVE;
enqueue:
- if (local_contact == SMC_FIRST_CONTACT)
- mutex_unlock(&smc_create_lgr_pending);
lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
smc_accept_enqueue(&lsmc->sk, newsmcsk);
@@ -868,17 +909,21 @@ enqueue:
sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */
return;
+decline_rdma_unlock:
+ mutex_unlock(&smc_create_lgr_pending);
decline_rdma:
/* RDMA setup failed, switch back to TCP */
smc_conn_free(&new_smc->conn);
new_smc->use_fallback = true;
if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- rc = smc_clc_send_decline(new_smc, reason_code, 0);
+ rc = smc_clc_send_decline(new_smc, reason_code);
if (rc < sizeof(struct smc_clc_msg_decline))
goto out_err;
}
goto out_connected;
+out_err_unlock:
+ mutex_unlock(&smc_create_lgr_pending);
out_err:
newsmcsk->sk_state = SMC_CLOSED;
smc_conn_free(&new_smc->conn);
@@ -935,6 +980,7 @@ static int smc_listen(struct socket *sock, int backlog)
* them to the clc socket -- copy smc socket options to clc socket
*/
smc_copy_sock_settings_to_clc(smc);
+ tcp_sk(smc->clcsock->sk)->syn_smc = 1;
rc = kernel_listen(smc->clcsock, backlog);
if (rc)
@@ -1377,6 +1423,7 @@ static int __init smc_init(void)
goto out_sock;
}
+ static_branch_enable(&tcp_have_smc);
return 0;
out_sock:
@@ -1401,6 +1448,7 @@ static void __exit smc_exit(void)
list_del_init(&lgr->list);
smc_lgr_free(lgr); /* free link group */
}
+ static_branch_disable(&tcp_have_smc);
smc_ib_unregister_client();
sock_unregister(PF_SMC);
proto_unregister(&smc_proto);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 6e44313e4467..0bee9d16cf29 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -149,7 +150,7 @@ struct smc_connection {
atomic_t sndbuf_space; /* remaining space in sndbuf */
u16 tx_cdc_seq; /* sequence # for CDC send */
spinlock_t send_lock; /* protect wr_sends */
- struct work_struct tx_work; /* retry of smc_cdc_msg_send */
+ struct delayed_work tx_work; /* retry of smc_cdc_msg_send */
struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl.
* .prod cf. TCP rcv_nxt
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index a7294edbc221..87f7bede6eab 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -62,10 +63,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
bh_unlock_sock(&smc->sk);
}
-int smc_cdc_get_free_slot(struct smc_link *link,
+int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
struct smc_cdc_tx_pend **pend)
{
+ struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+
return smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
(struct smc_wr_tx_pend_priv **)pend);
}
@@ -118,8 +121,7 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
struct smc_wr_buf *wr_buf;
int rc;
- rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf,
- &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
if (rc)
return rc;
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 8e1d76f26007..149ceda1b088 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -206,7 +207,8 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
struct smc_cdc_tx_pend;
-int smc_cdc_get_free_slot(struct smc_link *link, struct smc_wr_buf **wr_buf,
+int smc_cdc_get_free_slot(struct smc_connection *conn,
+ struct smc_wr_buf **wr_buf,
struct smc_cdc_tx_pend **pend);
void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 03ec058d18df..1800e16b2a02 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -95,9 +96,10 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
}
if (clcm->type == SMC_CLC_DECLINE) {
reason_code = SMC_CLC_DECL_REPLY;
- if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis)
- == SMC_CLC_DECL_SYNCERR)
+ if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
smc->conn.lgr->sync_err = true;
+ smc_lgr_terminate(smc->conn.lgr);
+ }
}
out:
@@ -105,8 +107,7 @@ out:
}
/* send CLC DECLINE message across internal TCP socket */
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
- u8 out_of_sync)
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
{
struct smc_clc_msg_decline dclc;
struct msghdr msg;
@@ -118,7 +119,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
dclc.hdr.type = SMC_CLC_DECLINE;
dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
dclc.hdr.version = SMC_CLC_V1;
- dclc.hdr.flag = out_of_sync ? 1 : 0;
+ dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
dclc.peer_diagnosis = htonl(peer_diag_info);
memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
@@ -204,13 +205,13 @@ int smc_clc_send_confirm(struct smc_sock *smc)
memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
hton24(cclc.qpn, link->roce_qp->qp_num);
cclc.rmb_rkey =
- htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
+ htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
cclc.rmbe_alert_token = htonl(conn->alert_token_local);
cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
cclc.rmbe_size = conn->rmbe_size_short;
- cclc.rmb_dma_addr =
- cpu_to_be64((u64)conn->rmb_desc->dma_addr[SMC_SINGLE_LINK]);
+ cclc.rmb_dma_addr = cpu_to_be64(
+ (u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
hton24(cclc.psn, link->psn_initial);
memcpy(cclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
@@ -256,13 +257,13 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
hton24(aclc.qpn, link->roce_qp->qp_num);
aclc.rmb_rkey =
- htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
+ htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
aclc.conn_idx = 1; /* as long as 1 RMB = 1 RMBE */
aclc.rmbe_alert_token = htonl(conn->alert_token_local);
aclc.qp_mtu = link->path_mtu;
aclc.rmbe_size = conn->rmbe_size_short,
- aclc.rmb_dma_addr =
- cpu_to_be64((u64)conn->rmb_desc->dma_addr[SMC_SINGLE_LINK]);
+ aclc.rmb_dma_addr = cpu_to_be64(
+ (u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
hton24(aclc.psn, link->psn_initial);
memcpy(aclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 13db8ce177c9..12a9af1539a2 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -106,8 +107,7 @@ struct smc_ib_device;
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
u8 expected_type);
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
- u8 out_of_sync);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
u8 ibport);
int smc_clc_send_confirm(struct smc_sock *smc);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 3c2e166b5d22..48615d2ac4aa 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -174,15 +175,15 @@ int smc_close_active(struct smc_sock *smc)
{
struct smc_cdc_conn_state_flags *txflags =
&smc->conn.local_tx_ctrl.conn_state_flags;
- long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
int old_state;
+ long timeout;
int rc = 0;
- if (sock_flag(sk, SOCK_LINGER) &&
- !(current->flags & PF_EXITING))
- timeout = sk->sk_lingertime;
+ timeout = current->flags & PF_EXITING ?
+ 0 : sock_flag(sk, SOCK_LINGER) ?
+ sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
again:
old_state = sk->sk_state;
@@ -208,7 +209,7 @@ again:
case SMC_ACTIVE:
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
if (sk->sk_state == SMC_ACTIVE) {
/* send close request */
@@ -234,7 +235,7 @@ again:
if (!smc_cdc_rxed_any_close(conn))
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
if (sk->sk_err != ECONNABORTED) {
/* confirm close from peer */
@@ -263,7 +264,9 @@ again:
/* peer sending PeerConnectionClosed will cause transition */
break;
case SMC_PROCESSABORT:
- cancel_work_sync(&conn->tx_work);
+ release_sock(sk);
+ cancel_delayed_work_sync(&conn->tx_work);
+ lock_sock(sk);
smc_close_abort(conn);
sk->sk_state = SMC_CLOSED;
smc_close_wait_tx_pends(smc);
@@ -358,7 +361,8 @@ static void smc_close_passive_work(struct work_struct *work)
case SMC_PEERCLOSEWAIT1:
if (rxflags->peer_done_writing)
sk->sk_state = SMC_PEERCLOSEWAIT2;
- /* fall through to check for closing */
+ /* fall through */
+ /* to check for closing */
case SMC_PEERCLOSEWAIT2:
case SMC_PEERFINCLOSEWAIT:
if (!smc_cdc_rxed_any_close(&smc->conn))
@@ -411,13 +415,14 @@ void smc_close_sock_put_work(struct work_struct *work)
int smc_close_shutdown_write(struct smc_sock *smc)
{
struct smc_connection *conn = &smc->conn;
- long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
struct sock *sk = &smc->sk;
int old_state;
+ long timeout;
int rc = 0;
- if (sock_flag(sk, SOCK_LINGER))
- timeout = sk->sk_lingertime;
+ timeout = current->flags & PF_EXITING ?
+ 0 : sock_flag(sk, SOCK_LINGER) ?
+ sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
again:
old_state = sk->sk_state;
@@ -425,7 +430,7 @@ again:
case SMC_ACTIVE:
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
/* send close wr request */
rc = smc_close_wr(conn);
@@ -439,7 +444,7 @@ again:
if (!smc_cdc_rxed_any_close(conn))
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
/* confirm close from peer */
rc = smc_close_wr(conn);
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index 4a3d99a8d7cb..ed82506b1b0a 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 3ac09a629ea1..94f21116dac5 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -25,8 +26,9 @@
#include "smc_cdc.h"
#include "smc_close.h"
-#define SMC_LGR_NUM_INCR 256
-#define SMC_LGR_FREE_DELAY (600 * HZ)
+#define SMC_LGR_NUM_INCR 256
+#define SMC_LGR_FREE_DELAY_SERV (600 * HZ)
+#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10)
static u32 smc_lgr_num; /* unique link group number */
@@ -107,8 +109,15 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
__smc_lgr_unregister_conn(conn);
}
write_unlock_bh(&lgr->conns_lock);
- if (reduced && !lgr->conns_num)
- schedule_delayed_work(&lgr->free_work, SMC_LGR_FREE_DELAY);
+ if (!reduced || lgr->conns_num)
+ return;
+ /* client link group creation always follows the server link group
+ * creation. For client use a somewhat higher removal delay time,
+ * otherwise there is a risk of out-of-sync link groups.
+ */
+ mod_delayed_work(system_wq, &lgr->free_work,
+ lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT :
+ SMC_LGR_FREE_DELAY_SERV);
}
static void smc_lgr_free_work(struct work_struct *work)
@@ -175,7 +184,6 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr,
rc = smc_wr_alloc_link_mem(lnk);
if (rc)
goto free_lgr;
- init_waitqueue_head(&lnk->wr_tx_wait);
rc = smc_ib_create_protection_domain(lnk);
if (rc)
goto free_link_mem;
@@ -207,17 +215,14 @@ out:
return rc;
}
-static void smc_sndbuf_unuse(struct smc_connection *conn)
+static void smc_buf_unuse(struct smc_connection *conn)
{
if (conn->sndbuf_desc) {
conn->sndbuf_desc->used = 0;
conn->sndbuf_size = 0;
}
-}
-
-static void smc_rmb_unuse(struct smc_connection *conn)
-{
if (conn->rmb_desc) {
+ conn->rmb_desc->reused = true;
conn->rmb_desc->used = 0;
conn->rmbe_size = 0;
}
@@ -232,8 +237,7 @@ void smc_conn_free(struct smc_connection *conn)
return;
smc_cdc_tx_dismiss_slots(conn);
smc_lgr_unregister_conn(conn);
- smc_rmb_unuse(conn);
- smc_sndbuf_unuse(conn);
+ smc_buf_unuse(conn);
}
static void smc_link_clear(struct smc_link *lnk)
@@ -246,48 +250,57 @@ static void smc_link_clear(struct smc_link *lnk)
smc_wr_free_link_mem(lnk);
}
-static void smc_lgr_free_sndbufs(struct smc_link_group *lgr)
+static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk,
+ bool is_rmb)
{
- struct smc_buf_desc *sndbuf_desc, *bf_desc;
- int i;
-
- for (i = 0; i < SMC_RMBE_SIZES; i++) {
- list_for_each_entry_safe(sndbuf_desc, bf_desc, &lgr->sndbufs[i],
- list) {
- list_del(&sndbuf_desc->list);
- smc_ib_buf_unmap(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
- smc_uncompress_bufsize(i),
- sndbuf_desc, DMA_TO_DEVICE);
- kfree(sndbuf_desc->cpu_addr);
- kfree(sndbuf_desc);
- }
+ if (is_rmb) {
+ if (buf_desc->mr_rx[SMC_SINGLE_LINK])
+ smc_ib_put_memory_region(
+ buf_desc->mr_rx[SMC_SINGLE_LINK]);
+ smc_ib_buf_unmap_sg(lnk->smcibdev, buf_desc,
+ DMA_FROM_DEVICE);
+ } else {
+ smc_ib_buf_unmap_sg(lnk->smcibdev, buf_desc,
+ DMA_TO_DEVICE);
}
+ sg_free_table(&buf_desc->sgt[SMC_SINGLE_LINK]);
+ if (buf_desc->cpu_addr)
+ free_pages((unsigned long)buf_desc->cpu_addr, buf_desc->order);
+ kfree(buf_desc);
}
-static void smc_lgr_free_rmbs(struct smc_link_group *lgr)
+static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb)
{
- struct smc_buf_desc *rmb_desc, *bf_desc;
struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+ struct smc_buf_desc *buf_desc, *bf_desc;
+ struct list_head *buf_list;
int i;
for (i = 0; i < SMC_RMBE_SIZES; i++) {
- list_for_each_entry_safe(rmb_desc, bf_desc, &lgr->rmbs[i],
+ if (is_rmb)
+ buf_list = &lgr->rmbs[i];
+ else
+ buf_list = &lgr->sndbufs[i];
+ list_for_each_entry_safe(buf_desc, bf_desc, buf_list,
list) {
- list_del(&rmb_desc->list);
- smc_ib_buf_unmap(lnk->smcibdev,
- smc_uncompress_bufsize(i),
- rmb_desc, DMA_FROM_DEVICE);
- kfree(rmb_desc->cpu_addr);
- kfree(rmb_desc);
+ list_del(&buf_desc->list);
+ smc_buf_free(buf_desc, lnk, is_rmb);
}
}
}
+static void smc_lgr_free_bufs(struct smc_link_group *lgr)
+{
+ /* free send buffers */
+ __smc_lgr_free_bufs(lgr, false);
+ /* free rmbs */
+ __smc_lgr_free_bufs(lgr, true);
+}
+
/* remove a link group */
void smc_lgr_free(struct smc_link_group *lgr)
{
- smc_lgr_free_rmbs(lgr);
- smc_lgr_free_sndbufs(lgr);
+ smc_lgr_free_bufs(lgr);
smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
kfree(lgr);
}
@@ -368,10 +381,14 @@ static int smc_link_determine_gid(struct smc_link_group *lgr)
if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid,
&gattr))
continue;
- if (gattr.ndev &&
- (vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id)) {
- lnk->gid = gid;
- return 0;
+ if (gattr.ndev) {
+ if (is_vlan_dev(gattr.ndev) &&
+ vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) {
+ lnk->gid = gid;
+ dev_put(gattr.ndev);
+ return 0;
+ }
+ dev_put(gattr.ndev);
}
}
return -ENODEV;
@@ -452,45 +469,25 @@ out:
return rc ? rc : local_contact;
}
-/* try to reuse a sndbuf description slot of the sndbufs list for a certain
- * buf_size; if not available, return NULL
+/* try to reuse a sndbuf or rmb description slot for a certain
+ * buffer size; if not available, return NULL
*/
static inline
-struct smc_buf_desc *smc_sndbuf_get_slot(struct smc_link_group *lgr,
- int compressed_bufsize)
+struct smc_buf_desc *smc_buf_get_slot(struct smc_link_group *lgr,
+ int compressed_bufsize,
+ rwlock_t *lock,
+ struct list_head *buf_list)
{
- struct smc_buf_desc *sndbuf_slot;
-
- read_lock_bh(&lgr->sndbufs_lock);
- list_for_each_entry(sndbuf_slot, &lgr->sndbufs[compressed_bufsize],
- list) {
- if (cmpxchg(&sndbuf_slot->used, 0, 1) == 0) {
- read_unlock_bh(&lgr->sndbufs_lock);
- return sndbuf_slot;
- }
- }
- read_unlock_bh(&lgr->sndbufs_lock);
- return NULL;
-}
+ struct smc_buf_desc *buf_slot;
-/* try to reuse an rmb description slot of the rmbs list for a certain
- * rmbe_size; if not available, return NULL
- */
-static inline
-struct smc_buf_desc *smc_rmb_get_slot(struct smc_link_group *lgr,
- int compressed_bufsize)
-{
- struct smc_buf_desc *rmb_slot;
-
- read_lock_bh(&lgr->rmbs_lock);
- list_for_each_entry(rmb_slot, &lgr->rmbs[compressed_bufsize],
- list) {
- if (cmpxchg(&rmb_slot->used, 0, 1) == 0) {
- read_unlock_bh(&lgr->rmbs_lock);
- return rmb_slot;
+ read_lock_bh(lock);
+ list_for_each_entry(buf_slot, buf_list, list) {
+ if (cmpxchg(&buf_slot->used, 0, 1) == 0) {
+ read_unlock_bh(lock);
+ return buf_slot;
}
}
- read_unlock_bh(&lgr->rmbs_lock);
+ read_unlock_bh(lock);
return NULL;
}
@@ -503,136 +500,186 @@ static inline int smc_rmb_wnd_update_limit(int rmbe_size)
return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
}
-/* create the tx buffer for an SMC socket */
-int smc_sndbuf_create(struct smc_sock *smc)
+static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr,
+ bool is_rmb, int bufsize)
{
- struct smc_connection *conn = &smc->conn;
- struct smc_link_group *lgr = conn->lgr;
- int tmp_bufsize, tmp_bufsize_short;
- struct smc_buf_desc *sndbuf_desc;
+ struct smc_buf_desc *buf_desc;
+ struct smc_link *lnk;
int rc;
- /* use socket send buffer size (w/o overhead) as start value */
- for (tmp_bufsize_short = smc_compress_bufsize(smc->sk.sk_sndbuf / 2);
- tmp_bufsize_short >= 0; tmp_bufsize_short--) {
- tmp_bufsize = smc_uncompress_bufsize(tmp_bufsize_short);
- /* check for reusable sndbuf_slot in the link group */
- sndbuf_desc = smc_sndbuf_get_slot(lgr, tmp_bufsize_short);
- if (sndbuf_desc) {
- memset(sndbuf_desc->cpu_addr, 0, tmp_bufsize);
- break; /* found reusable slot */
- }
- /* try to alloc a new send buffer */
- sndbuf_desc = kzalloc(sizeof(*sndbuf_desc), GFP_KERNEL);
- if (!sndbuf_desc)
- break; /* give up with -ENOMEM */
- sndbuf_desc->cpu_addr = kzalloc(tmp_bufsize,
- GFP_KERNEL | __GFP_NOWARN |
- __GFP_NOMEMALLOC |
- __GFP_NORETRY);
- if (!sndbuf_desc->cpu_addr) {
- kfree(sndbuf_desc);
- sndbuf_desc = NULL;
- /* if send buffer allocation has failed,
- * try a smaller one
- */
- continue;
- }
- rc = smc_ib_buf_map(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
- tmp_bufsize, sndbuf_desc,
- DMA_TO_DEVICE);
+ /* try to alloc a new buffer */
+ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL);
+ if (!buf_desc)
+ return ERR_PTR(-ENOMEM);
+
+ buf_desc->cpu_addr =
+ (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN |
+ __GFP_NOMEMALLOC |
+ __GFP_NORETRY | __GFP_ZERO,
+ get_order(bufsize));
+ if (!buf_desc->cpu_addr) {
+ kfree(buf_desc);
+ return ERR_PTR(-EAGAIN);
+ }
+ buf_desc->order = get_order(bufsize);
+
+ /* build the sg table from the pages */
+ lnk = &lgr->lnk[SMC_SINGLE_LINK];
+ rc = sg_alloc_table(&buf_desc->sgt[SMC_SINGLE_LINK], 1,
+ GFP_KERNEL);
+ if (rc) {
+ smc_buf_free(buf_desc, lnk, is_rmb);
+ return ERR_PTR(rc);
+ }
+ sg_set_buf(buf_desc->sgt[SMC_SINGLE_LINK].sgl,
+ buf_desc->cpu_addr, bufsize);
+
+ /* map sg table to DMA address */
+ rc = smc_ib_buf_map_sg(lnk->smcibdev, buf_desc,
+ is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ /* SMC protocol depends on mapping to one DMA address only */
+ if (rc != 1) {
+ smc_buf_free(buf_desc, lnk, is_rmb);
+ return ERR_PTR(-EAGAIN);
+ }
+
+ /* create a new memory region for the RMB */
+ if (is_rmb) {
+ rc = smc_ib_get_memory_region(lnk->roce_pd,
+ IB_ACCESS_REMOTE_WRITE |
+ IB_ACCESS_LOCAL_WRITE,
+ buf_desc);
if (rc) {
- kfree(sndbuf_desc->cpu_addr);
- kfree(sndbuf_desc);
- sndbuf_desc = NULL;
- continue; /* if mapping failed, try smaller one */
+ smc_buf_free(buf_desc, lnk, is_rmb);
+ return ERR_PTR(rc);
}
- sndbuf_desc->used = 1;
- write_lock_bh(&lgr->sndbufs_lock);
- list_add(&sndbuf_desc->list,
- &lgr->sndbufs[tmp_bufsize_short]);
- write_unlock_bh(&lgr->sndbufs_lock);
- break;
- }
- if (sndbuf_desc && sndbuf_desc->cpu_addr) {
- conn->sndbuf_desc = sndbuf_desc;
- conn->sndbuf_size = tmp_bufsize;
- smc->sk.sk_sndbuf = tmp_bufsize * 2;
- atomic_set(&conn->sndbuf_space, tmp_bufsize);
- return 0;
- } else {
- return -ENOMEM;
}
+
+ return buf_desc;
}
-/* create the RMB for an SMC socket (even though the SMC protocol
- * allows more than one RMB-element per RMB, the Linux implementation
- * uses just one RMB-element per RMB, i.e. uses an extra RMB for every
- * connection in a link group
- */
-int smc_rmb_create(struct smc_sock *smc)
+static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
{
struct smc_connection *conn = &smc->conn;
struct smc_link_group *lgr = conn->lgr;
- int tmp_bufsize, tmp_bufsize_short;
- struct smc_buf_desc *rmb_desc;
- int rc;
+ struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM);
+ struct list_head *buf_list;
+ int bufsize, bufsize_short;
+ int sk_buf_size;
+ rwlock_t *lock;
+
+ if (is_rmb)
+ /* use socket recv buffer size (w/o overhead) as start value */
+ sk_buf_size = smc->sk.sk_rcvbuf / 2;
+ else
+ /* use socket send buffer size (w/o overhead) as start value */
+ sk_buf_size = smc->sk.sk_sndbuf / 2;
+
+ for (bufsize_short = smc_compress_bufsize(sk_buf_size);
+ bufsize_short >= 0; bufsize_short--) {
+
+ if (is_rmb) {
+ lock = &lgr->rmbs_lock;
+ buf_list = &lgr->rmbs[bufsize_short];
+ } else {
+ lock = &lgr->sndbufs_lock;
+ buf_list = &lgr->sndbufs[bufsize_short];
+ }
+ bufsize = smc_uncompress_bufsize(bufsize_short);
+ if ((1 << get_order(bufsize)) > SG_MAX_SINGLE_ALLOC)
+ continue;
- /* use socket recv buffer size (w/o overhead) as start value */
- for (tmp_bufsize_short = smc_compress_bufsize(smc->sk.sk_rcvbuf / 2);
- tmp_bufsize_short >= 0; tmp_bufsize_short--) {
- tmp_bufsize = smc_uncompress_bufsize(tmp_bufsize_short);
- /* check for reusable rmb_slot in the link group */
- rmb_desc = smc_rmb_get_slot(lgr, tmp_bufsize_short);
- if (rmb_desc) {
- memset(rmb_desc->cpu_addr, 0, tmp_bufsize);
+ /* check for reusable slot in the link group */
+ buf_desc = smc_buf_get_slot(lgr, bufsize_short, lock, buf_list);
+ if (buf_desc) {
+ memset(buf_desc->cpu_addr, 0, bufsize);
break; /* found reusable slot */
}
- /* try to alloc a new RMB */
- rmb_desc = kzalloc(sizeof(*rmb_desc), GFP_KERNEL);
- if (!rmb_desc)
- break; /* give up with -ENOMEM */
- rmb_desc->cpu_addr = kzalloc(tmp_bufsize,
- GFP_KERNEL | __GFP_NOWARN |
- __GFP_NOMEMALLOC |
- __GFP_NORETRY);
- if (!rmb_desc->cpu_addr) {
- kfree(rmb_desc);
- rmb_desc = NULL;
- /* if RMB allocation has failed,
- * try a smaller one
- */
+
+ buf_desc = smc_new_buf_create(lgr, is_rmb, bufsize);
+ if (PTR_ERR(buf_desc) == -ENOMEM)
+ break;
+ if (IS_ERR(buf_desc))
continue;
- }
- rc = smc_ib_buf_map(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
- tmp_bufsize, rmb_desc,
- DMA_FROM_DEVICE);
- if (rc) {
- kfree(rmb_desc->cpu_addr);
- kfree(rmb_desc);
- rmb_desc = NULL;
- continue; /* if mapping failed, try smaller one */
- }
- rmb_desc->rkey[SMC_SINGLE_LINK] =
- lgr->lnk[SMC_SINGLE_LINK].roce_pd->unsafe_global_rkey;
- rmb_desc->used = 1;
- write_lock_bh(&lgr->rmbs_lock);
- list_add(&rmb_desc->list,
- &lgr->rmbs[tmp_bufsize_short]);
- write_unlock_bh(&lgr->rmbs_lock);
- break;
+
+ buf_desc->used = 1;
+ write_lock_bh(lock);
+ list_add(&buf_desc->list, buf_list);
+ write_unlock_bh(lock);
+ break; /* found */
}
- if (rmb_desc && rmb_desc->cpu_addr) {
- conn->rmb_desc = rmb_desc;
- conn->rmbe_size = tmp_bufsize;
- conn->rmbe_size_short = tmp_bufsize_short;
- smc->sk.sk_rcvbuf = tmp_bufsize * 2;
+
+ if (IS_ERR(buf_desc))
+ return -ENOMEM;
+
+ if (is_rmb) {
+ conn->rmb_desc = buf_desc;
+ conn->rmbe_size = bufsize;
+ conn->rmbe_size_short = bufsize_short;
+ smc->sk.sk_rcvbuf = bufsize * 2;
atomic_set(&conn->bytes_to_rcv, 0);
- conn->rmbe_update_limit = smc_rmb_wnd_update_limit(tmp_bufsize);
- return 0;
+ conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
} else {
- return -ENOMEM;
+ conn->sndbuf_desc = buf_desc;
+ conn->sndbuf_size = bufsize;
+ smc->sk.sk_sndbuf = bufsize * 2;
+ atomic_set(&conn->sndbuf_space, bufsize);
}
+ return 0;
+}
+
+void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn)
+{
+ struct smc_link_group *lgr = conn->lgr;
+
+ smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+ conn->sndbuf_desc, DMA_TO_DEVICE);
+}
+
+void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn)
+{
+ struct smc_link_group *lgr = conn->lgr;
+
+ smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+ conn->sndbuf_desc, DMA_TO_DEVICE);
+}
+
+void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
+{
+ struct smc_link_group *lgr = conn->lgr;
+
+ smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+ conn->rmb_desc, DMA_FROM_DEVICE);
+}
+
+void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
+{
+ struct smc_link_group *lgr = conn->lgr;
+
+ smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+ conn->rmb_desc, DMA_FROM_DEVICE);
+}
+
+/* create the send and receive buffer for an SMC socket;
+ * receive buffers are called RMBs;
+ * (even though the SMC protocol allows more than one RMB-element per RMB,
+ * the Linux implementation uses just one RMB-element per RMB, i.e. uses an
+ * extra RMB for every connection in a link group
+ */
+int smc_buf_create(struct smc_sock *smc)
+{
+ int rc;
+
+ /* create send buffer */
+ rc = __smc_buf_create(smc, false);
+ if (rc)
+ return rc;
+ /* create rmb */
+ rc = __smc_buf_create(smc, true);
+ if (rc)
+ smc_buf_free(smc->conn.sndbuf_desc,
+ &smc->conn.lgr->lnk[SMC_SINGLE_LINK], false);
+ return rc;
}
static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr)
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index b013cb43a327..fe691bf9af91 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -37,6 +38,14 @@ struct smc_wr_buf {
u8 raw[SMC_WR_BUF_SIZE];
};
+#define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */
+
+enum smc_wr_reg_state {
+ POSTED, /* ib_wr_reg_mr request posted */
+ CONFIRMED, /* ib_wr_reg_mr response: successful */
+ FAILED /* ib_wr_reg_mr response: failure */
+};
+
struct smc_link {
struct smc_ib_device *smcibdev; /* ib-device */
u8 ibport; /* port - values 1 | 2 */
@@ -65,6 +74,10 @@ struct smc_link {
u64 wr_rx_id; /* seq # of last recv WR */
u32 wr_rx_cnt; /* number of WR recv buffers */
+ struct ib_reg_wr wr_reg; /* WR register memory region */
+ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */
+ enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */
+
union ib_gid gid; /* gid matching used vlan id */
u32 peer_qpn; /* QP number of peer */
enum ib_mtu path_mtu; /* used mtu */
@@ -90,14 +103,15 @@ struct smc_link {
/* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */
struct smc_buf_desc {
struct list_head list;
- u64 dma_addr[SMC_LINKS_PER_LGR_MAX];
- /* mapped address of buffer */
void *cpu_addr; /* virtual address of buffer */
- u32 rkey[SMC_LINKS_PER_LGR_MAX];
- /* for rmb only:
- * rkey provided to peer
+ struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */
+ struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX];
+ /* for rmb only: memory region
+ * incl. rkey provided to peer
*/
+ u32 order; /* allocation order */
u32 used; /* currently used / unused */
+ bool reused; /* new created / reused */
};
struct smc_rtoken { /* address/key of remote RMB */
@@ -173,9 +187,11 @@ struct smc_clc_msg_accept_confirm;
void smc_lgr_free(struct smc_link_group *lgr);
void smc_lgr_terminate(struct smc_link_group *lgr);
-int smc_sndbuf_create(struct smc_sock *smc);
-int smc_rmb_create(struct smc_sock *smc);
+int smc_buf_create(struct smc_sock *smc);
int smc_rmb_rtoken_handling(struct smc_connection *conn,
struct smc_clc_msg_accept_confirm *clc);
-
+void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
+void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
+void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
+void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
#endif
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index b31715505a35..90f1a7f9085c 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -13,6 +14,7 @@
#include <linux/random.h>
#include <linux/workqueue.h>
+#include <linux/scatterlist.h>
#include <rdma/ib_verbs.h>
#include "smc_pnet.h"
@@ -192,8 +194,7 @@ int smc_ib_create_protection_domain(struct smc_link *lnk)
{
int rc;
- lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev,
- IB_PD_UNSAFE_GLOBAL_RKEY);
+ lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0);
rc = PTR_ERR_OR_ZERO(lnk->roce_pd);
if (IS_ERR(lnk->roce_pd))
lnk->roce_pd = NULL;
@@ -232,10 +233,10 @@ int smc_ib_create_queue_pair(struct smc_link *lnk)
.recv_cq = lnk->smcibdev->roce_cq_recv,
.srq = NULL,
.cap = {
- .max_send_wr = SMC_WR_BUF_CNT,
/* include unsolicited rdma_writes as well,
* there are max. 2 RDMA_WRITE per 1 WR_SEND
*/
+ .max_send_wr = SMC_WR_BUF_CNT * 3,
.max_recv_wr = SMC_WR_BUF_CNT * 3,
.max_send_sge = SMC_IB_MAX_SEND_SGE,
.max_recv_sge = 1,
@@ -254,56 +255,132 @@ int smc_ib_create_queue_pair(struct smc_link *lnk)
return rc;
}
-/* map a new TX or RX buffer to DMA */
-int smc_ib_buf_map(struct smc_ib_device *smcibdev, int buf_size,
- struct smc_buf_desc *buf_slot,
- enum dma_data_direction data_direction)
+void smc_ib_put_memory_region(struct ib_mr *mr)
{
- int rc = 0;
+ ib_dereg_mr(mr);
+}
- if (buf_slot->dma_addr[SMC_SINGLE_LINK])
- return rc; /* already mapped */
- buf_slot->dma_addr[SMC_SINGLE_LINK] =
- ib_dma_map_single(smcibdev->ibdev, buf_slot->cpu_addr,
- buf_size, data_direction);
- if (ib_dma_mapping_error(smcibdev->ibdev,
- buf_slot->dma_addr[SMC_SINGLE_LINK]))
- rc = -EIO;
- return rc;
+static int smc_ib_map_mr_sg(struct smc_buf_desc *buf_slot)
+{
+ unsigned int offset = 0;
+ int sg_num;
+
+ /* map the largest prefix of a dma mapped SG list */
+ sg_num = ib_map_mr_sg(buf_slot->mr_rx[SMC_SINGLE_LINK],
+ buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+ buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+ &offset, PAGE_SIZE);
+
+ return sg_num;
+}
+
+/* Allocate a memory region and map the dma mapped SG list of buf_slot */
+int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
+ struct smc_buf_desc *buf_slot)
+{
+ if (buf_slot->mr_rx[SMC_SINGLE_LINK])
+ return 0; /* already done */
+
+ buf_slot->mr_rx[SMC_SINGLE_LINK] =
+ ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, 1 << buf_slot->order);
+ if (IS_ERR(buf_slot->mr_rx[SMC_SINGLE_LINK])) {
+ int rc;
+
+ rc = PTR_ERR(buf_slot->mr_rx[SMC_SINGLE_LINK]);
+ buf_slot->mr_rx[SMC_SINGLE_LINK] = NULL;
+ return rc;
+ }
+
+ if (smc_ib_map_mr_sg(buf_slot) != 1)
+ return -EINVAL;
+
+ return 0;
+}
+
+/* synchronize buffer usage for cpu access */
+void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
+ struct smc_buf_desc *buf_slot,
+ enum dma_data_direction data_direction)
+{
+ struct scatterlist *sg;
+ unsigned int i;
+
+ /* for now there is just one DMA address */
+ for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
+ buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
+ if (!sg_dma_len(sg))
+ break;
+ ib_dma_sync_single_for_cpu(smcibdev->ibdev,
+ sg_dma_address(sg),
+ sg_dma_len(sg),
+ data_direction);
+ }
+}
+
+/* synchronize buffer usage for device access */
+void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
+ struct smc_buf_desc *buf_slot,
+ enum dma_data_direction data_direction)
+{
+ struct scatterlist *sg;
+ unsigned int i;
+
+ /* for now there is just one DMA address */
+ for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
+ buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
+ if (!sg_dma_len(sg))
+ break;
+ ib_dma_sync_single_for_device(smcibdev->ibdev,
+ sg_dma_address(sg),
+ sg_dma_len(sg),
+ data_direction);
+ }
}
-void smc_ib_buf_unmap(struct smc_ib_device *smcibdev, int buf_size,
+/* Map a new TX or RX buffer SG-table to DMA */
+int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
struct smc_buf_desc *buf_slot,
enum dma_data_direction data_direction)
{
- if (!buf_slot->dma_addr[SMC_SINGLE_LINK])
+ int mapped_nents;
+
+ mapped_nents = ib_dma_map_sg(smcibdev->ibdev,
+ buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+ buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+ data_direction);
+ if (!mapped_nents)
+ return -ENOMEM;
+
+ return mapped_nents;
+}
+
+void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
+ struct smc_buf_desc *buf_slot,
+ enum dma_data_direction data_direction)
+{
+ if (!buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address)
return; /* already unmapped */
- ib_dma_unmap_single(smcibdev->ibdev, *buf_slot->dma_addr, buf_size,
- data_direction);
- buf_slot->dma_addr[SMC_SINGLE_LINK] = 0;
+
+ ib_dma_unmap_sg(smcibdev->ibdev,
+ buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+ buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+ data_direction);
+ buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address = 0;
}
static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
{
- struct net_device *ndev;
+ struct ib_gid_attr gattr;
int rc;
rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
- &smcibdev->gid[ibport - 1], NULL);
- /* the SMC protocol requires specification of the roce MAC address;
- * if net_device cannot be determined, it can be derived from gid 0
- */
- ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
- if (ndev) {
- memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
- } else if (!rc) {
- memcpy(&smcibdev->mac[ibport - 1][0],
- &smcibdev->gid[ibport - 1].raw[8], 3);
- memcpy(&smcibdev->mac[ibport - 1][3],
- &smcibdev->gid[ibport - 1].raw[13], 3);
- smcibdev->mac[ibport - 1][0] &= ~0x02;
- }
- return rc;
+ &smcibdev->gid[ibport - 1], &gattr);
+ if (rc || !gattr.ndev)
+ return -ENODEV;
+
+ memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
+ dev_put(gattr.ndev);
+ return 0;
}
/* Create an identifier unique for this instance of SMC-R.
@@ -334,6 +411,7 @@ int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
&smcibdev->pattr[ibport - 1]);
if (rc)
goto out;
+ /* the SMC protocol requires specification of the RoCE MAC address */
rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
if (rc)
goto out;
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index b567152a526d..e90630dadf8e 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -51,12 +52,12 @@ int smc_ib_register_client(void) __init;
void smc_ib_unregister_client(void);
bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport);
int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport);
-int smc_ib_buf_map(struct smc_ib_device *smcibdev, int buf_size,
- struct smc_buf_desc *buf_slot,
- enum dma_data_direction data_direction);
-void smc_ib_buf_unmap(struct smc_ib_device *smcibdev, int bufsize,
+int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
struct smc_buf_desc *buf_slot,
enum dma_data_direction data_direction);
+void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
+ struct smc_buf_desc *buf_slot,
+ enum dma_data_direction data_direction);
void smc_ib_dealloc_protection_domain(struct smc_link *lnk);
int smc_ib_create_protection_domain(struct smc_link *lnk);
void smc_ib_destroy_queue_pair(struct smc_link *lnk);
@@ -65,6 +66,13 @@ int smc_ib_ready_link(struct smc_link *lnk);
int smc_ib_modify_qp_rts(struct smc_link *lnk);
int smc_ib_modify_qp_reset(struct smc_link *lnk);
long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
-
-
+int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
+ struct smc_buf_desc *buf_slot);
+void smc_ib_put_memory_region(struct ib_mr *mr);
+void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
+ struct smc_buf_desc *buf_slot,
+ enum dma_data_direction data_direction);
+void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
+ struct smc_buf_desc *buf_slot,
+ enum dma_data_direction data_direction);
#endif
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index c2f9165d13ef..92fe4cc8c82c 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index b472f853953a..51b27ce90dbd 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 78f7af28ae4f..74568cdbca70 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -181,8 +182,10 @@ static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem)
sizeof(new_pnetelem->ndev->name)) ||
smc_pnet_same_ibname(pnetelem,
new_pnetelem->smcibdev->ibdev->name,
- new_pnetelem->ib_port))
+ new_pnetelem->ib_port)) {
+ dev_put(pnetelem->ndev);
goto found;
+ }
}
list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
rc = 0;
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index c4f1bccd4358..5a29519db976 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index f0c8b089f770..cbf58637ee14 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -148,6 +149,8 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
read_done = sock_intr_errno(timeo);
break;
}
+ if (!timeo)
+ return -EAGAIN;
}
if (!atomic_read(&conn->bytes_to_rcv)) {
@@ -170,6 +173,7 @@ copy:
copylen, conn->rmbe_size - cons.count);
chunk_len_sum = chunk_len;
chunk_off = cons.count;
+ smc_rmb_sync_sg_for_cpu(conn);
for (chunk = 0; chunk < 2; chunk++) {
if (!(flags & MSG_TRUNC)) {
rc = memcpy_to_msg(msg, rcvbuf_base + chunk_off,
@@ -177,6 +181,7 @@ copy:
if (rc) {
if (!read_done)
read_done = -EFAULT;
+ smc_rmb_sync_sg_for_device(conn);
goto out;
}
}
@@ -190,6 +195,7 @@ copy:
chunk_len_sum += chunk_len;
chunk_off = 0; /* modulo offset in recv ring buffer */
}
+ smc_rmb_sync_sg_for_device(conn);
/* update cursors */
if (!(flags & MSG_PEEK)) {
diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h
index b5b80e1f8b0f..3a32b59bf06c 100644
--- a/net/smc/smc_rx.h
+++ b/net/smc/smc_rx.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 21ec1832ab51..c48dc2d5fd3a 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -24,6 +25,8 @@
#include "smc_cdc.h"
#include "smc_tx.h"
+#define SMC_TX_WORK_DELAY HZ
+
/***************************** sndbuf producer *******************************/
/* callback implementation for sk.sk_write_space()
@@ -174,10 +177,12 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
copylen, conn->sndbuf_size - tx_cnt_prep);
chunk_len_sum = chunk_len;
chunk_off = tx_cnt_prep;
+ smc_sndbuf_sync_sg_for_cpu(conn);
for (chunk = 0; chunk < 2; chunk++) {
rc = memcpy_from_msg(sndbuf_base + chunk_off,
msg, chunk_len);
if (rc) {
+ smc_sndbuf_sync_sg_for_device(conn);
if (send_done)
return send_done;
goto out_err;
@@ -192,6 +197,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
chunk_len_sum += chunk_len;
chunk_off = 0; /* modulo offset in send ring buffer */
}
+ smc_sndbuf_sync_sg_for_device(conn);
/* update cursors */
smc_curs_add(conn->sndbuf_size, &prep, copylen);
smc_curs_write(&conn->tx_curs_prep,
@@ -277,6 +283,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
struct smc_link_group *lgr = conn->lgr;
int to_send, rmbespace;
struct smc_link *link;
+ dma_addr_t dma_addr;
int num_sges;
int rc;
@@ -334,12 +341,11 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
src_len = conn->sndbuf_size - sent.count;
}
src_len_sum = src_len;
+ dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
for (dstchunk = 0; dstchunk < 2; dstchunk++) {
num_sges = 0;
for (srcchunk = 0; srcchunk < 2; srcchunk++) {
- sges[srcchunk].addr =
- conn->sndbuf_desc->dma_addr[SMC_SINGLE_LINK] +
- src_off;
+ sges[srcchunk].addr = dma_addr + src_off;
sges[srcchunk].length = src_len;
sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
num_sges++;
@@ -391,8 +397,7 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
int rc;
spin_lock_bh(&conn->send_lock);
- rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf,
- &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
if (rc < 0) {
if (rc == -EBUSY) {
struct smc_sock *smc =
@@ -403,7 +408,8 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
goto out_unlock;
}
rc = 0;
- schedule_work(&conn->tx_work);
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_WORK_DELAY);
}
goto out_unlock;
}
@@ -427,7 +433,7 @@ out_unlock:
*/
static void smc_tx_work(struct work_struct *work)
{
- struct smc_connection *conn = container_of(work,
+ struct smc_connection *conn = container_of(to_delayed_work(work),
struct smc_connection,
tx_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
@@ -460,12 +466,12 @@ void smc_tx_consumer_update(struct smc_connection *conn)
((to_confirm > conn->rmbe_update_limit) &&
((to_confirm > (conn->rmbe_size / 2)) ||
conn->local_rx_ctrl.prod_flags.write_blocked))) {
- rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
- &wr_buf, &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
if (!rc)
rc = smc_cdc_msg_send(conn, wr_buf, pend);
if (rc < 0) {
- schedule_work(&conn->tx_work);
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_WORK_DELAY);
return;
}
smc_curs_write(&conn->rx_curs_confirmed,
@@ -484,6 +490,6 @@ void smc_tx_consumer_update(struct smc_connection *conn)
void smc_tx_init(struct smc_sock *smc)
{
smc->sk.sk_write_space = smc_tx_write_space;
- INIT_WORK(&smc->conn.tx_work, smc_tx_work);
+ INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
spin_lock_init(&smc->conn.send_lock);
}
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index 1d6a0dcdcfe6..78255964fa4d 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 874ee9f9d796..de4537f66832 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -68,6 +69,16 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
int i;
link = wc->qp->qp_context;
+
+ if (wc->opcode == IB_WC_REG_MR) {
+ if (wc->status)
+ link->wr_reg_state = FAILED;
+ else
+ link->wr_reg_state = CONFIRMED;
+ wake_up(&link->wr_reg_wait);
+ return;
+ }
+
pnd_snd_idx = smc_wr_tx_find_pending_index(link, wc->wr_id);
if (pnd_snd_idx == link->wr_tx_cnt)
return;
@@ -234,7 +245,7 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
int rc;
ib_req_notify_cq(link->smcibdev->roce_cq_send,
- IB_CQ_SOLICITED_MASK | IB_CQ_REPORT_MISSED_EVENTS);
+ IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
pend = container_of(priv, struct smc_wr_tx_pend, priv);
rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx],
&failed_wr);
@@ -243,6 +254,52 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
return rc;
}
+/* Register a memory region and wait for result. */
+int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
+{
+ struct ib_send_wr *failed_wr = NULL;
+ int rc;
+
+ ib_req_notify_cq(link->smcibdev->roce_cq_send,
+ IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+ link->wr_reg_state = POSTED;
+ link->wr_reg.wr.wr_id = (u64)(uintptr_t)mr;
+ link->wr_reg.mr = mr;
+ link->wr_reg.key = mr->rkey;
+ failed_wr = &link->wr_reg.wr;
+ rc = ib_post_send(link->roce_qp, &link->wr_reg.wr, &failed_wr);
+ WARN_ON(failed_wr != &link->wr_reg.wr);
+ if (rc)
+ return rc;
+
+ rc = wait_event_interruptible_timeout(link->wr_reg_wait,
+ (link->wr_reg_state != POSTED),
+ SMC_WR_REG_MR_WAIT_TIME);
+ if (!rc) {
+ /* timeout - terminate connections */
+ struct smc_link_group *lgr;
+
+ lgr = container_of(link, struct smc_link_group,
+ lnk[SMC_SINGLE_LINK]);
+ smc_lgr_terminate(lgr);
+ return -EPIPE;
+ }
+ if (rc == -ERESTARTSYS)
+ return -EINTR;
+ switch (link->wr_reg_state) {
+ case CONFIRMED:
+ rc = 0;
+ break;
+ case FAILED:
+ rc = -EIO;
+ break;
+ case POSTED:
+ rc = -EPIPE;
+ break;
+ }
+ return rc;
+}
+
void smc_wr_tx_dismiss_slots(struct smc_link *link, u8 wr_rx_hdr_type,
smc_wr_tx_filter filter,
smc_wr_tx_dismisser dismisser,
@@ -458,6 +515,11 @@ static void smc_wr_init_sge(struct smc_link *lnk)
lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[i];
lnk->wr_rx_ibs[i].num_sge = 1;
}
+ lnk->wr_reg.wr.next = NULL;
+ lnk->wr_reg.wr.num_sge = 0;
+ lnk->wr_reg.wr.send_flags = IB_SEND_SIGNALED;
+ lnk->wr_reg.wr.opcode = IB_WR_REG_MR;
+ lnk->wr_reg.access = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE;
}
void smc_wr_free_link(struct smc_link *lnk)
@@ -602,6 +664,8 @@ int smc_wr_create_link(struct smc_link *lnk)
smc_wr_init_sge(lnk);
memset(lnk->wr_tx_mask, 0,
BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask));
+ init_waitqueue_head(&lnk->wr_tx_wait);
+ init_waitqueue_head(&lnk->wr_reg_wait);
return rc;
dma_unmap:
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 0b9beeda6053..2acf12b06063 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -102,5 +103,6 @@ void smc_wr_tx_dismiss_slots(struct smc_link *lnk, u8 wr_rx_hdr_type,
int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler);
int smc_wr_rx_post_init(struct smc_link *link);
void smc_wr_rx_cq_handler(struct ib_cq *ib_cq, void *cq_context);
+int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr);
#endif /* SMC_WR_H */
generated by cgit v1.2.3 (git 2.46.0) at 2025-10-31 09:04:16 +0000