summaryrefslogtreecommitdiff
path: root/net/smc
diff options
context:
space:
mode:
Diffstat (limited to 'net/smc')
-rw-r--r--net/smc/af_smc.c134
-rw-r--r--net/smc/smc.h2
-rw-r--r--net/smc/smc_cdc.c38
-rw-r--r--net/smc/smc_cdc.h43
-rw-r--r--net/smc/smc_clc.c19
-rw-r--r--net/smc/smc_clc.h20
-rw-r--r--net/smc/smc_close.c2
-rw-r--r--net/smc/smc_core.c84
-rw-r--r--net/smc/smc_core.h17
-rw-r--r--net/smc/smc_diag.c15
-rw-r--r--net/smc/smc_ib.c44
-rw-r--r--net/smc/smc_ib.h3
-rw-r--r--net/smc/smc_llc.c80
-rw-r--r--net/smc/smc_llc.h7
-rw-r--r--net/smc/smc_pnet.c30
-rw-r--r--net/smc/smc_pnet.h3
-rw-r--r--net/smc/smc_rx.c19
-rw-r--r--net/smc/smc_tx.c46
-rw-r--r--net/smc/smc_tx.h4
-rw-r--r--net/smc/smc_wr.c32
20 files changed, 332 insertions, 310 deletions
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index f3fdf3714f8b..0fc94f296e54 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -149,7 +149,8 @@ static int smc_release(struct socket *sock)
smc->clcsock = NULL;
}
if (smc->use_fallback) {
- sock_put(sk); /* passive closing */
+ if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+ sock_put(sk); /* passive closing */
sk->sk_state = SMC_CLOSED;
sk->sk_state_change(sk);
}
@@ -343,20 +344,17 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
rc = smc_ib_modify_qp_rts(link);
if (rc)
- return SMC_CLC_DECL_INTERR;
+ return SMC_CLC_DECL_ERR_RDYLNK;
smc_wr_remember_qp_attr(link);
if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
- return SMC_CLC_DECL_INTERR;
+ return SMC_CLC_DECL_ERR_REGRMB;
/* send CONFIRM LINK response over RoCE fabric */
- rc = smc_llc_send_confirm_link(link,
- link->smcibdev->mac[link->ibport - 1],
- &link->smcibdev->gid[link->ibport - 1],
- SMC_LLC_RESP);
+ rc = smc_llc_send_confirm_link(link, SMC_LLC_RESP);
if (rc < 0)
- return SMC_CLC_DECL_TCL;
+ return SMC_CLC_DECL_TIMEOUT_CL;
/* receive ADD LINK request from server over RoCE fabric */
rest = wait_for_completion_interruptible_timeout(&link->llc_add,
@@ -372,10 +370,9 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
/* send add link reject message, only one link supported for now */
rc = smc_llc_send_add_link(link,
link->smcibdev->mac[link->ibport - 1],
- &link->smcibdev->gid[link->ibport - 1],
- SMC_LLC_RESP);
+ link->gid, SMC_LLC_RESP);
if (rc < 0)
- return SMC_CLC_DECL_TCL;
+ return SMC_CLC_DECL_TIMEOUT_AL;
smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
@@ -427,9 +424,10 @@ static void smc_link_save_peer_info(struct smc_link *link,
}
/* fall back during connect */
-static int smc_connect_fallback(struct smc_sock *smc)
+static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
{
smc->use_fallback = true;
+ smc->fallback_rsn = reason_code;
smc_copy_sock_settings_to_clc(smc);
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
@@ -441,14 +439,20 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
{
int rc;
- if (reason_code < 0) /* error, fallback is not possible */
+ if (reason_code < 0) { /* error, fallback is not possible */
+ if (smc->sk.sk_state == SMC_INIT)
+ sock_put(&smc->sk); /* passive closing */
return reason_code;
- if (reason_code != SMC_CLC_DECL_REPLY) {
+ }
+ if (reason_code != SMC_CLC_DECL_PEERDECL) {
rc = smc_clc_send_decline(smc, reason_code);
- if (rc < 0)
+ if (rc < 0) {
+ if (smc->sk.sk_state == SMC_INIT)
+ sock_put(&smc->sk); /* passive closing */
return rc;
+ }
}
- return smc_connect_fallback(smc);
+ return smc_connect_fallback(smc, reason_code);
}
/* abort connecting */
@@ -459,15 +463,13 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code,
smc_lgr_forget(smc->conn.lgr);
mutex_unlock(&smc_create_lgr_pending);
smc_conn_free(&smc->conn);
- if (reason_code < 0 && smc->sk.sk_state == SMC_INIT)
- sock_put(&smc->sk); /* passive closing */
return reason_code;
}
/* check if there is a rdma device available for this connection. */
/* called for connect and listen */
static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
- u8 *ibport)
+ u8 *ibport, unsigned short vlan_id, u8 gid[])
{
int reason_code = 0;
@@ -475,7 +477,8 @@ static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
* within same PNETID that also contains the ethernet device
* used for the internal TCP socket
*/
- smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport);
+ smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport, vlan_id,
+ gid);
if (!(*ibdev))
reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
@@ -521,12 +524,12 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
static int smc_connect_clc(struct smc_sock *smc, int smc_type,
struct smc_clc_msg_accept_confirm *aclc,
struct smc_ib_device *ibdev, u8 ibport,
- struct smcd_dev *ismdev)
+ u8 gid[], struct smcd_dev *ismdev)
{
int rc = 0;
/* do inband token exchange */
- rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, ismdev);
+ rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev);
if (rc)
return rc;
/* receive SMC Accept CLC message */
@@ -566,7 +569,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
smc_link_save_peer_info(link, aclc);
if (smc_rmb_rtoken_handling(&smc->conn, aclc))
- return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+ return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
local_contact);
smc_close_init(smc);
@@ -574,12 +577,12 @@ static int smc_connect_rdma(struct smc_sock *smc,
if (local_contact == SMC_FIRST_CONTACT) {
if (smc_ib_ready_link(link))
- return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+ return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
local_contact);
} else {
if (!smc->conn.rmb_desc->reused &&
smc_reg_rmb(link, smc->conn.rmb_desc, true))
- return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+ return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
local_contact);
}
smc_rmb_sync_sg_for_device(&smc->conn);
@@ -648,6 +651,7 @@ static int __smc_connect(struct smc_sock *smc)
struct smc_clc_msg_accept_confirm aclc;
struct smc_ib_device *ibdev;
struct smcd_dev *ismdev;
+ u8 gid[SMC_GID_SIZE];
unsigned short vlan;
int smc_type;
int rc = 0;
@@ -656,11 +660,11 @@ static int __smc_connect(struct smc_sock *smc)
sock_hold(&smc->sk); /* sock put in passive closing */
if (smc->use_fallback)
- return smc_connect_fallback(smc);
+ return smc_connect_fallback(smc, smc->fallback_rsn);
/* if peer has not signalled SMC-capability, fall back */
if (!tcp_sk(smc->clcsock->sk)->syn_smc)
- return smc_connect_fallback(smc);
+ return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC);
/* IPSec connections opt out of SMC-R optimizations */
if (using_ipsec(smc))
@@ -679,7 +683,7 @@ static int __smc_connect(struct smc_sock *smc)
}
/* check if there is a rdma device available */
- if (!smc_check_rdma(smc, &ibdev, &ibport)) {
+ if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) {
/* RDMA is supported for this connection */
rdma_supported = true;
if (ism_supported)
@@ -690,10 +694,10 @@ static int __smc_connect(struct smc_sock *smc)
/* if neither ISM nor RDMA are supported, fallback */
if (!rdma_supported && !ism_supported)
- return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+ return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
/* perform CLC handshake */
- rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, ismdev);
+ rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
if (rc) {
smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
return smc_connect_decline_fallback(smc, rc);
@@ -705,7 +709,7 @@ static int __smc_connect(struct smc_sock *smc)
else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
rc = smc_connect_ism(smc, &aclc, ismdev);
else
- rc = SMC_CLC_DECL_CNFERR;
+ rc = SMC_CLC_DECL_MODEUNSUPP;
if (rc) {
smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
return smc_connect_decline_fallback(smc, rc);
@@ -943,15 +947,12 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
link = &lgr->lnk[SMC_SINGLE_LINK];
if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
- return SMC_CLC_DECL_INTERR;
+ return SMC_CLC_DECL_ERR_REGRMB;
/* send CONFIRM LINK request to client over the RoCE fabric */
- rc = smc_llc_send_confirm_link(link,
- link->smcibdev->mac[link->ibport - 1],
- &link->smcibdev->gid[link->ibport - 1],
- SMC_LLC_REQ);
+ rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ);
if (rc < 0)
- return SMC_CLC_DECL_TCL;
+ return SMC_CLC_DECL_TIMEOUT_CL;
/* receive CONFIRM LINK response from client over the RoCE fabric */
rest = wait_for_completion_interruptible_timeout(
@@ -971,10 +972,9 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
/* send ADD LINK request to client over the RoCE fabric */
rc = smc_llc_send_add_link(link,
link->smcibdev->mac[link->ibport - 1],
- &link->smcibdev->gid[link->ibport - 1],
- SMC_LLC_REQ);
+ link->gid, SMC_LLC_REQ);
if (rc < 0)
- return SMC_CLC_DECL_TCL;
+ return SMC_CLC_DECL_TIMEOUT_AL;
/* receive ADD LINK response from client over the RoCE fabric */
rest = wait_for_completion_interruptible_timeout(&link->llc_add_resp,
@@ -1049,7 +1049,8 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
}
smc_conn_free(&new_smc->conn);
new_smc->use_fallback = true;
- if (reason_code && reason_code != SMC_CLC_DECL_REPLY) {
+ new_smc->fallback_rsn = reason_code;
+ if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
if (smc_clc_send_decline(new_smc, reason_code) < 0) {
smc_listen_out_err(new_smc);
return;
@@ -1140,7 +1141,7 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
if (local_contact != SMC_FIRST_CONTACT) {
if (!new_smc->conn.rmb_desc->reused) {
if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
- return SMC_CLC_DECL_INTERR;
+ return SMC_CLC_DECL_ERR_REGRMB;
}
}
smc_rmb_sync_sg_for_device(&new_smc->conn);
@@ -1160,13 +1161,13 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc,
smc_link_save_peer_info(link, cclc);
if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) {
- reason_code = SMC_CLC_DECL_INTERR;
+ reason_code = SMC_CLC_DECL_ERR_RTOK;
goto decline;
}
if (local_contact == SMC_FIRST_CONTACT) {
if (smc_ib_ready_link(link)) {
- reason_code = SMC_CLC_DECL_INTERR;
+ reason_code = SMC_CLC_DECL_ERR_RDYLNK;
goto decline;
}
/* QP confirmation over RoCE fabric */
@@ -1194,6 +1195,7 @@ static void smc_listen_work(struct work_struct *work)
struct smcd_dev *ismdev;
u8 buf[SMC_CLC_MAX_LEN];
int local_contact = 0;
+ unsigned short vlan;
int reason_code = 0;
int rc = 0;
u8 ibport;
@@ -1206,6 +1208,7 @@ static void smc_listen_work(struct work_struct *work)
/* check if peer is smc capable */
if (!tcp_sk(newclcsock->sk)->syn_smc) {
new_smc->use_fallback = true;
+ new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
smc_listen_out_connected(new_smc);
return;
}
@@ -1242,14 +1245,16 @@ static void smc_listen_work(struct work_struct *work)
/* check if RDMA is available */
if (!ism_supported &&
((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
- smc_check_rdma(new_smc, &ibdev, &ibport) ||
+ smc_vlan_by_tcpsk(new_smc->clcsock, &vlan) ||
+ smc_check_rdma(new_smc, &ibdev, &ibport, vlan, NULL) ||
smc_listen_rdma_check(new_smc, pclc) ||
smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
&local_contact) ||
smc_listen_rdma_reg(new_smc, local_contact))) {
/* SMC not supported, decline */
mutex_unlock(&smc_create_lgr_pending);
- smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact);
+ smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP,
+ local_contact);
return;
}
@@ -1296,6 +1301,7 @@ static void smc_tcp_listen_work(struct work_struct *work)
new_smc->listen_smc = lsmc;
new_smc->use_fallback = lsmc->use_fallback;
+ new_smc->fallback_rsn = lsmc->fallback_rsn;
sock_hold(lsk); /* sock_put in smc_listen_work */
INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
smc_copy_sock_settings_to_smc(new_smc);
@@ -1450,6 +1456,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (msg->msg_flags & MSG_FASTOPEN) {
if (sk->sk_state == SMC_INIT) {
smc->use_fallback = true;
+ smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
rc = -EINVAL;
goto out;
@@ -1527,6 +1534,8 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
if (sk->sk_err)
mask |= EPOLLERR;
} else {
+ if (sk->sk_state != SMC_CLOSED)
+ sock_poll_wait(file, wait);
if (sk->sk_err)
mask |= EPOLLERR;
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
@@ -1552,7 +1561,6 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
}
if (smc->conn.urg_state == SMC_URG_VALID)
mask |= EPOLLPRI;
-
}
return mask;
@@ -1633,7 +1641,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
if (optlen < sizeof(int))
return -EINVAL;
- get_user(val, (int __user *)optval);
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
lock_sock(sk);
switch (optname) {
@@ -1645,6 +1654,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
/* option not supported by SMC */
if (sk->sk_state == SMC_INIT) {
smc->use_fallback = true;
+ smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
if (!smc->use_fallback)
rc = -EINVAL;
@@ -1701,10 +1711,13 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
return -EBADF;
return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
}
+ lock_sock(&smc->sk);
switch (cmd) {
case SIOCINQ: /* same as FIONREAD */
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED)
answ = 0;
@@ -1713,8 +1726,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
break;
case SIOCOUTQ:
/* output queue size (not send + not acked) */
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED)
answ = 0;
@@ -1724,8 +1739,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
break;
case SIOCOUTQNSD:
/* output queue size (not send only) */
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED)
answ = 0;
@@ -1733,25 +1750,25 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
answ = smc_tx_prepared_sends(&smc->conn);
break;
case SIOCATMARK:
- if (smc->sk.sk_state == SMC_LISTEN)
+ if (smc->sk.sk_state == SMC_LISTEN) {
+ release_sock(&smc->sk);
return -EINVAL;
+ }
if (smc->sk.sk_state == SMC_INIT ||
smc->sk.sk_state == SMC_CLOSED) {
answ = 0;
} else {
- smc_curs_write(&cons,
- smc_curs_read(&conn->local_tx_ctrl.cons, conn),
- conn);
- smc_curs_write(&urg,
- smc_curs_read(&conn->urg_curs, conn),
- conn);
+ smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+ smc_curs_copy(&urg, &conn->urg_curs, conn);
answ = smc_curs_diff(conn->rmb_desc->len,
&cons, &urg) == 1;
}
break;
default:
+ release_sock(&smc->sk);
return -ENOIOCTLCMD;
}
+ release_sock(&smc->sk);
return put_user(answ, (int __user *)arg);
}
@@ -1875,6 +1892,7 @@ static int smc_create(struct net *net, struct socket *sock, int protocol,
/* create internal TCP socket for CLC handshake and fallback */
smc = smc_sk(sk);
smc->use_fallback = false; /* assume rdma capability first */
+ smc->fallback_rsn = 0;
rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
&smc->clcsock);
if (rc) {
diff --git a/net/smc/smc.h b/net/smc/smc.h
index be20acd7b5ab..08786ace6010 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -208,6 +208,8 @@ struct smc_sock { /* smc sock container */
struct list_head accept_q; /* sockets to be accepted */
spinlock_t accept_q_lock; /* protects accept_q */
bool use_fallback; /* fallback to tcp */
+ int fallback_rsn; /* reason for fallback */
+ u32 peer_diagnosis; /* decline reason from peer */
int sockopt_defer_accept;
/* sockopt TCP_DEFER_ACCEPT
* value
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 621d8cca570b..ed5dcf03fe0b 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -34,14 +34,15 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
enum ib_wc_status wc_status)
{
struct smc_cdc_tx_pend *cdcpend = (struct smc_cdc_tx_pend *)pnd_snd;
+ struct smc_connection *conn = cdcpend->conn;
struct smc_sock *smc;
int diff;
- if (!cdcpend->conn)
+ if (!conn)
/* already dismissed */
return;
- smc = container_of(cdcpend->conn, struct smc_sock, conn);
+ smc = container_of(conn, struct smc_sock, conn);
bh_lock_sock(&smc->sk);
if (!wc_status) {
diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len,
@@ -52,9 +53,7 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
atomic_add(diff, &cdcpend->conn->sndbuf_space);
/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
smp_mb__after_atomic();
- smc_curs_write(&cdcpend->conn->tx_curs_fin,
- smc_curs_read(&cdcpend->cursor, cdcpend->conn),
- cdcpend->conn);
+ smc_curs_copy(&conn->tx_curs_fin, &cdcpend->cursor, conn);
}
smc_tx_sndbuf_nonfull(smc);
bh_unlock_sock(&smc->sk);
@@ -110,9 +109,8 @@ int smc_cdc_msg_send(struct smc_connection *conn,
&conn->local_tx_ctrl, conn);
rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
if (!rc)
- smc_curs_write(&conn->rx_curs_confirmed,
- smc_curs_read(&conn->local_tx_ctrl.cons, conn),
- conn);
+ smc_curs_copy(&conn->rx_curs_confirmed,
+ &conn->local_tx_ctrl.cons, conn);
return rc;
}
@@ -194,8 +192,8 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1);
if (rc)
return rc;
- smc_curs_write(&conn->rx_curs_confirmed,
- smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn);
+ smc_curs_copy(&conn->rx_curs_confirmed, &conn->local_tx_ctrl.cons,
+ conn);
/* 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);
@@ -204,8 +202,7 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
atomic_add(diff, &conn->sndbuf_space);
/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
smp_mb__after_atomic();
- smc_curs_write(&conn->tx_curs_fin,
- smc_curs_read(&conn->tx_curs_sent, conn), conn);
+ smc_curs_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn);
smc_tx_sndbuf_nonfull(smc);
return rc;
@@ -225,9 +222,7 @@ static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc,
char *base;
/* new data included urgent business */
- smc_curs_write(&conn->urg_curs,
- smc_curs_read(&conn->local_rx_ctrl.prod, conn),
- conn);
+ smc_curs_copy(&conn->urg_curs, &conn->local_rx_ctrl.prod, conn);
conn->urg_state = SMC_URG_VALID;
if (!sock_flag(&smc->sk, SOCK_URGINLINE))
/* we'll skip the urgent byte, so don't account for it */
@@ -247,12 +242,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
struct smc_connection *conn = &smc->conn;
int diff_cons, diff_prod;
- smc_curs_write(&prod_old,
- smc_curs_read(&conn->local_rx_ctrl.prod, conn),
- conn);
- smc_curs_write(&cons_old,
- smc_curs_read(&conn->local_rx_ctrl.cons, conn),
- conn);
+ smc_curs_copy(&prod_old, &conn->local_rx_ctrl.prod, conn);
+ smc_curs_copy(&cons_old, &conn->local_rx_ctrl.cons, conn);
smc_cdc_msg_to_host(&conn->local_rx_ctrl, cdc, conn);
diff_cons = smc_curs_diff(conn->peer_rmbe_size, &cons_old,
@@ -287,7 +278,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
/* force immediate tx of current consumer cursor, but
* under send_lock to guarantee arrival in seqno-order
*/
- smc_tx_sndbuf_nonempty(conn);
+ if (smc->sk.sk_state != SMC_INIT)
+ smc_tx_sndbuf_nonempty(conn);
}
}
@@ -374,7 +366,7 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
return; /* invalid message */
/* lookup connection */
- lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+ lgr = smc_get_lgr(link);
read_lock_bh(&lgr->conns_lock);
conn = smc_lgr_find_conn(ntohl(cdc->token), lgr);
read_unlock_bh(&lgr->conns_lock);
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 8fbce4fee3e4..934df4473a7c 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -104,47 +104,34 @@ static inline u64 smc_curs_read(union smc_host_cursor *curs,
#endif
}
-static inline u64 smc_curs_read_net(union smc_cdc_cursor *curs,
- struct smc_connection *conn)
-{
-#ifndef KERNEL_HAS_ATOMIC64
- unsigned long flags;
- u64 ret;
-
- spin_lock_irqsave(&conn->acurs_lock, flags);
- ret = curs->acurs;
- spin_unlock_irqrestore(&conn->acurs_lock, flags);
- return ret;
-#else
- return atomic64_read(&curs->acurs);
-#endif
-}
-
-static inline void smc_curs_write(union smc_host_cursor *curs, u64 val,
- struct smc_connection *conn)
+/* Copy cursor src into tgt */
+static inline void smc_curs_copy(union smc_host_cursor *tgt,
+ union smc_host_cursor *src,
+ struct smc_connection *conn)
{
#ifndef KERNEL_HAS_ATOMIC64
unsigned long flags;
spin_lock_irqsave(&conn->acurs_lock, flags);
- curs->acurs = val;
+ tgt->acurs = src->acurs;
spin_unlock_irqrestore(&conn->acurs_lock, flags);
#else
- atomic64_set(&curs->acurs, val);
+ atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
#endif
}
-static inline void smc_curs_write_net(union smc_cdc_cursor *curs, u64 val,
- struct smc_connection *conn)
+static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt,
+ union smc_cdc_cursor *src,
+ struct smc_connection *conn)
{
#ifndef KERNEL_HAS_ATOMIC64
unsigned long flags;
spin_lock_irqsave(&conn->acurs_lock, flags);
- curs->acurs = val;
+ tgt->acurs = src->acurs;
spin_unlock_irqrestore(&conn->acurs_lock, flags);
#else
- atomic64_set(&curs->acurs, val);
+ atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
#endif
}
@@ -179,7 +166,7 @@ static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
{
union smc_host_cursor temp;
- smc_curs_write(&temp, smc_curs_read(local, conn), conn);
+ smc_curs_copy(&temp, local, conn);
peer->count = htonl(temp.count);
peer->wrap = htons(temp.wrap);
/* peer->reserved = htons(0); must be ensured by caller */
@@ -206,8 +193,8 @@ static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local,
union smc_host_cursor temp, old;
union smc_cdc_cursor net;
- smc_curs_write(&old, smc_curs_read(local, conn), conn);
- smc_curs_write_net(&net, smc_curs_read_net(peer, conn), conn);
+ smc_curs_copy(&old, local, conn);
+ smc_curs_copy_net(&net, peer, conn);
temp.count = ntohl(net.count);
temp.wrap = ntohs(net.wrap);
if ((old.wrap > temp.wrap) && temp.wrap)
@@ -215,7 +202,7 @@ static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local,
if ((old.wrap == temp.wrap) &&
(old.count > temp.count))
return;
- smc_curs_write(local, smc_curs_read(&temp, conn), conn);
+ smc_curs_copy(local, &temp, conn);
}
static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 038d70ef7892..83aba9ade060 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -267,6 +267,7 @@ out:
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
u8 expected_type)
{
+ long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
struct sock *clc_sk = smc->clcsock->sk;
struct smc_clc_msg_hdr *clcm = buf;
struct msghdr msg = {NULL, 0};
@@ -326,7 +327,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
memset(&msg, 0, sizeof(struct msghdr));
iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
krflags = MSG_WAITALL;
- smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
len = sock_recvmsg(smc->clcsock, &msg, krflags);
if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
smc->sk.sk_err = EPROTO;
@@ -334,7 +334,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
goto out;
}
if (clcm->type == SMC_CLC_DECLINE) {
- reason_code = SMC_CLC_DECL_REPLY;
+ struct smc_clc_msg_decline *dclc;
+
+ dclc = (struct smc_clc_msg_decline *)clcm;
+ reason_code = SMC_CLC_DECL_PEERDECL;
+ smc->peer_diagnosis = ntohl(dclc->peer_diagnosis);
if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
smc->conn.lgr->sync_err = 1;
smc_lgr_terminate(smc->conn.lgr);
@@ -342,6 +346,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
}
out:
+ smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
return reason_code;
}
@@ -377,7 +382,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
/* send CLC PROPOSAL message across internal TCP socket */
int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
- struct smc_ib_device *ibdev, u8 ibport,
+ struct smc_ib_device *ibdev, u8 ibport, u8 gid[],
struct smcd_dev *ismdev)
{
struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
@@ -408,7 +413,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
/* add SMC-R specifics */
memcpy(pclc.lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
- memcpy(&pclc.lcl.gid, &ibdev->gid[ibport - 1], SMC_GID_SIZE);
+ memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE);
memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
pclc.iparea_offset = htons(0);
}
@@ -491,8 +496,7 @@ int smc_clc_send_confirm(struct smc_sock *smc)
cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
memcpy(cclc.lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
- memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
- SMC_GID_SIZE);
+ memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE);
memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
ETH_ALEN);
hton24(cclc.qpn, link->roce_qp->qp_num);
@@ -565,8 +569,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
link = &conn->lgr->lnk[SMC_SINGLE_LINK];
memcpy(aclc.lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
- memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
- SMC_GID_SIZE);
+ memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE);
memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
ETH_ALEN);
hton24(aclc.qpn, link->roce_qp->qp_num);
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 100e988ad1a8..18da89b681c2 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -28,15 +28,21 @@
#define SMC_TYPE_B 3 /* SMC-R and SMC-D */
#define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */
#define SMC_CLC_DECL_MEM 0x01010000 /* insufficient memory resources */
-#define SMC_CLC_DECL_TIMEOUT 0x02000000 /* timeout */
+#define SMC_CLC_DECL_TIMEOUT_CL 0x02010000 /* timeout w4 QP confirm link */
+#define SMC_CLC_DECL_TIMEOUT_AL 0x02020000 /* timeout w4 QP add link */
#define SMC_CLC_DECL_CNFERR 0x03000000 /* configuration error */
-#define SMC_CLC_DECL_IPSEC 0x03030000 /* IPsec usage */
+#define SMC_CLC_DECL_PEERNOSMC 0x03010000 /* peer did not indicate SMC */
+#define SMC_CLC_DECL_IPSEC 0x03020000 /* IPsec usage */
+#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found */
+#define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/
+#define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */
+#define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */
#define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */
-#define SMC_CLC_DECL_REPLY 0x06000000 /* reply to a received decline */
+#define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */
#define SMC_CLC_DECL_INTERR 0x99990000 /* internal error */
-#define SMC_CLC_DECL_TCL 0x02040000 /* timeout w4 QP confirm */
-#define SMC_CLC_DECL_SEND 0x07000000 /* sending problem */
-#define SMC_CLC_DECL_RMBE_EC 0x08000000 /* peer has eyecatcher in RMBE */
+#define SMC_CLC_DECL_ERR_RTOK 0x99990001 /* rtoken handling failed */
+#define SMC_CLC_DECL_ERR_RDYLNK 0x99990002 /* ib ready link failed */
+#define SMC_CLC_DECL_ERR_REGRMB 0x99990003 /* reg rmb failed */
struct smc_clc_msg_hdr { /* header1 of clc messages */
u8 eyecatcher[4]; /* eye catcher */
@@ -179,7 +185,7 @@ 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);
int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
- struct smc_ib_device *smcibdev, u8 ibport,
+ struct smc_ib_device *smcibdev, u8 ibport, u8 gid[],
struct smcd_dev *ismdev);
int smc_clc_send_confirm(struct smc_sock *smc);
int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index fa41d9881741..ac961dfb1ea1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -107,6 +107,8 @@ static void smc_close_active_abort(struct smc_sock *smc)
}
switch (sk->sk_state) {
case SMC_INIT:
+ sk->sk_state = SMC_PEERABORTWAIT;
+ break;
case SMC_ACTIVE:
sk->sk_state = SMC_PEERABORTWAIT;
release_sock(sk);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 66741e61a3b0..a46418f45ecd 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -30,6 +30,7 @@
#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 * HZ)
+#define SMC_LGR_FREE_DELAY_FAST (8 * HZ)
static struct smc_lgr_list smc_lgr_list = { /* established link groups */
.lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
@@ -51,6 +52,11 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV);
}
+void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr)
+{
+ mod_delayed_work(system_wq, &lgr->free_work, SMC_LGR_FREE_DELAY_FAST);
+}
+
/* Register connection's alert token in our lookup structure.
* To use rbtrees we have to implement our own insert core.
* Requires @conns_lock
@@ -133,6 +139,20 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
smc_lgr_schedule_free_work(lgr);
}
+/* Send delete link, either as client to request the initiation
+ * of the DELETE LINK sequence from server; or as server to
+ * initiate the delete processing. See smc_llc_rx_delete_link().
+ */
+static int smc_link_send_delete(struct smc_link *lnk)
+{
+ if (lnk->state == SMC_LNK_ACTIVE &&
+ !smc_llc_send_delete_link(lnk, SMC_LLC_REQ, true)) {
+ smc_llc_link_deleting(lnk);
+ return 0;
+ }
+ return -ENOTCONN;
+}
+
static void smc_lgr_free_work(struct work_struct *work)
{
struct smc_link_group *lgr = container_of(to_delayed_work(work),
@@ -153,10 +173,21 @@ static void smc_lgr_free_work(struct work_struct *work)
list_del_init(&lgr->list); /* remove from smc_lgr_list */
free:
spin_unlock_bh(&smc_lgr_list.lock);
+
+ if (!lgr->is_smcd && !lgr->terminating) {
+ /* try to send del link msg, on error free lgr immediately */
+ if (!smc_link_send_delete(&lgr->lnk[SMC_SINGLE_LINK])) {
+ /* reschedule in case we never receive a response */
+ smc_lgr_schedule_free_work(lgr);
+ return;
+ }
+ }
+
if (!delayed_work_pending(&lgr->free_work)) {
- if (!lgr->is_smcd &&
- lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE)
- smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+ struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
+ if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE)
+ smc_llc_link_inactive(lnk);
smc_lgr_free(lgr);
}
}
@@ -219,6 +250,10 @@ static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
get_random_bytes(rndvec, sizeof(rndvec));
lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
(rndvec[2] << 16);
+ rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport,
+ vlan_id, lnk->gid, &lnk->sgid_index);
+ if (rc)
+ goto free_lgr;
rc = smc_llc_link_init(lnk);
if (rc)
goto free_lgr;
@@ -522,37 +557,6 @@ out:
return rc;
}
-/* determine the link gid matching the vlan id of the link group */
-static int smc_link_determine_gid(struct smc_link_group *lgr)
-{
- struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
- struct ib_gid_attr gattr;
- union ib_gid gid;
- int i;
-
- if (!lgr->vlan_id) {
- lnk->gid = lnk->smcibdev->gid[lnk->ibport - 1];
- return 0;
- }
-
- for (i = 0; i < lnk->smcibdev->pattr[lnk->ibport - 1].gid_tbl_len;
- i++) {
- if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid,
- &gattr))
- continue;
- 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;
-}
-
static bool smcr_lgr_match(struct smc_link_group *lgr,
struct smc_clc_msg_local *lcl,
enum smc_lgr_role role)
@@ -631,8 +635,6 @@ create:
if (rc)
goto out;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
- if (!is_smcd)
- rc = smc_link_determine_gid(conn->lgr);
}
conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
@@ -1013,8 +1015,14 @@ void smc_core_exit(void)
spin_unlock_bh(&smc_lgr_list.lock);
list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) {
list_del_init(&lgr->list);
- if (!lgr->is_smcd)
- smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+ if (!lgr->is_smcd) {
+ struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
+ if (lnk->state == SMC_LNK_ACTIVE)
+ smc_llc_send_delete_link(lnk, SMC_LLC_REQ,
+ false);
+ smc_llc_link_inactive(lnk);
+ }
cancel_delayed_work_sync(&lgr->free_work);
smc_lgr_free(lgr); /* free link group */
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 8b47e0168fc3..c156674733c9 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -34,7 +34,8 @@ enum smc_lgr_role { /* possible roles of a link group */
enum smc_link_state { /* possible states of a link */
SMC_LNK_INACTIVE, /* link is inactive */
SMC_LNK_ACTIVATING, /* link is being activated */
- SMC_LNK_ACTIVE /* link is active */
+ SMC_LNK_ACTIVE, /* link is active */
+ SMC_LNK_DELETING, /* link is being deleted */
};
#define SMC_WR_BUF_SIZE 48 /* size of work request buffer */
@@ -84,14 +85,15 @@ struct smc_link {
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 */
+ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/
+ u8 sgid_index; /* gid index for vlan id */
u32 peer_qpn; /* QP number of peer */
enum ib_mtu path_mtu; /* used mtu */
enum ib_mtu peer_mtu; /* mtu size of peer */
u32 psn_initial; /* QP tx initial packet seqno */
u32 peer_psn; /* QP rx initial packet seqno */
u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */
- u8 peer_gid[sizeof(union ib_gid)]; /* gid of peer*/
+ u8 peer_gid[SMC_GID_SIZE]; /* gid of peer*/
u8 link_id; /* unique # within link group */
enum smc_link_state state; /* state of link */
@@ -192,8 +194,7 @@ struct smc_link_group {
struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX]
[SMC_LINKS_PER_LGR_MAX];
/* remote addr/key pairs */
- unsigned long rtokens_used_mask[BITS_TO_LONGS
- (SMC_RMBS_PER_LGR_MAX)];
+ DECLARE_BITMAP(rtokens_used_mask, SMC_RMBS_PER_LGR_MAX);
/* used rtoken elements */
};
struct { /* SMC-D */
@@ -265,5 +266,11 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
u64 peer_gid);
void smcd_conn_free(struct smc_connection *conn);
+void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
void smc_core_exit(void);
+
+static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
+{
+ return container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+}
#endif
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 6d83eef1b743..dbf64a93d68a 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -79,6 +79,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
struct nlattr *bc)
{
struct smc_sock *smc = smc_sk(sk);
+ struct smc_diag_fallback fallback;
struct user_namespace *user_ns;
struct smc_diag_msg *r;
struct nlmsghdr *nlh;
@@ -91,11 +92,21 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
r = nlmsg_data(nlh);
smc_diag_msg_common_fill(r, sk);
r->diag_state = sk->sk_state;
- r->diag_fallback = smc->use_fallback;
+ if (smc->use_fallback)
+ r->diag_mode = SMC_DIAG_MODE_FALLBACK_TCP;
+ else if (smc->conn.lgr && smc->conn.lgr->is_smcd)
+ r->diag_mode = SMC_DIAG_MODE_SMCD;
+ else
+ r->diag_mode = SMC_DIAG_MODE_SMCR;
user_ns = sk_user_ns(NETLINK_CB(cb->skb).sk);
if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns))
goto errout;
+ fallback.reason = smc->fallback_rsn;
+ fallback.peer_diagnosis = smc->peer_diagnosis;
+ if (nla_put(skb, SMC_DIAG_FALLBACK, sizeof(fallback), &fallback) < 0)
+ goto errout;
+
if ((req->diag_ext & (1 << (SMC_DIAG_CONNINFO - 1))) &&
smc->conn.alert_token_local) {
struct smc_connection *conn = &smc->conn;
@@ -149,7 +160,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name));
smc_gid_be16_convert(linfo.lnk[0].gid,
- smc->conn.lgr->lnk[0].gid.raw);
+ smc->conn.lgr->lnk[0].gid);
smc_gid_be16_convert(linfo.lnk[0].peer_gid,
smc->conn.lgr->lnk[0].peer_gid);
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 36de2fd76170..2cc64bc8ae20 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -68,7 +68,7 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu);
qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport);
- rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, 0, 1, 0);
+ rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
sizeof(lnk->peer_mac));
@@ -112,8 +112,7 @@ int smc_ib_modify_qp_reset(struct smc_link *lnk)
int smc_ib_ready_link(struct smc_link *lnk)
{
- struct smc_link_group *lgr =
- container_of(lnk, struct smc_link_group, lnk[0]);
+ struct smc_link_group *lgr = smc_get_lgr(lnk);
int rc = 0;
rc = smc_ib_modify_qp_init(lnk);
@@ -143,13 +142,13 @@ out:
return rc;
}
-static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
+static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
{
struct ib_gid_attr gattr;
+ union ib_gid gid;
int rc;
- rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
- &smcibdev->gid[ibport - 1], &gattr);
+ rc = ib_query_gid(smcibdev->ibdev, ibport, 0, &gid, &gattr);
if (rc || !gattr.ndev)
return -ENODEV;
@@ -176,6 +175,37 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
}
+/* determine the gid for an ib-device port and vlan id */
+int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
+ unsigned short vlan_id, u8 gid[], u8 *sgid_index)
+{
+ struct ib_gid_attr gattr;
+ union ib_gid _gid;
+ int i;
+
+ for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
+ memset(&_gid, 0, SMC_GID_SIZE);
+ memset(&gattr, 0, sizeof(gattr));
+ if (ib_query_gid(smcibdev->ibdev, ibport, i, &_gid, &gattr))
+ continue;
+ if (!gattr.ndev)
+ continue;
+ if (((!vlan_id && !is_vlan_dev(gattr.ndev)) ||
+ (vlan_id && is_vlan_dev(gattr.ndev) &&
+ vlan_dev_vlan_id(gattr.ndev) == vlan_id)) &&
+ gattr.gid_type == IB_GID_TYPE_IB) {
+ if (gid)
+ memcpy(gid, &_gid, SMC_GID_SIZE);
+ if (sgid_index)
+ *sgid_index = i;
+ dev_put(gattr.ndev);
+ return 0;
+ }
+ dev_put(gattr.ndev);
+ }
+ return -ENODEV;
+}
+
static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
{
int rc;
@@ -187,7 +217,7 @@ static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
if (rc)
goto out;
/* the SMC protocol requires specification of the RoCE MAC address */
- rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
+ rc = smc_ib_fill_mac(smcibdev, ibport);
if (rc)
goto out;
if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 7c1223c91229..bac7fd65a4c0 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -40,7 +40,6 @@ struct smc_ib_device { /* ib-device infos for smc */
struct tasklet_struct recv_tasklet; /* called by recv cq handler */
char mac[SMC_MAX_PORTS][ETH_ALEN];
/* mac address per port*/
- union ib_gid gid[SMC_MAX_PORTS]; /* gid per port */
u8 pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
/* pnetid per port */
u8 initialized : 1; /* ib dev CQ, evthdl done */
@@ -77,4 +76,6 @@ void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
struct smc_buf_desc *buf_slot,
enum dma_data_direction data_direction);
+int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
+ unsigned short vlan_id, u8 gid[], u8 *sgid_index);
#endif
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 5800a6b43d83..9c916c709ca7 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -182,12 +182,10 @@ static int smc_llc_add_pending_send(struct smc_link *link,
}
/* high-level API to send LLC confirm link */
-int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[],
- union ib_gid *gid,
+int smc_llc_send_confirm_link(struct smc_link *link,
enum smc_llc_reqresp reqresp)
{
- struct smc_link_group *lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
+ struct smc_link_group *lgr = smc_get_lgr(link);
struct smc_llc_msg_confirm_link *confllc;
struct smc_wr_tx_pend_priv *pend;
struct smc_wr_buf *wr_buf;
@@ -203,8 +201,9 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[],
confllc->hd.flags |= SMC_LLC_FLAG_NO_RMBE_EYEC;
if (reqresp == SMC_LLC_RESP)
confllc->hd.flags |= SMC_LLC_FLAG_RESP;
- memcpy(confllc->sender_mac, mac, ETH_ALEN);
- memcpy(confllc->sender_gid, gid, SMC_GID_SIZE);
+ memcpy(confllc->sender_mac, link->smcibdev->mac[link->ibport - 1],
+ ETH_ALEN);
+ memcpy(confllc->sender_gid, link->gid, SMC_GID_SIZE);
hton24(confllc->sender_qp_num, link->roce_qp->qp_num);
confllc->link_num = link->link_id;
memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE);
@@ -241,8 +240,7 @@ static int smc_llc_send_confirm_rkey(struct smc_link *link,
/* prepare an add link message */
static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
- struct smc_link *link, u8 mac[],
- union ib_gid *gid,
+ struct smc_link *link, u8 mac[], u8 gid[],
enum smc_llc_reqresp reqresp)
{
memset(addllc, 0, sizeof(*addllc));
@@ -259,8 +257,7 @@ static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
}
/* send ADD LINK request or response */
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
- union ib_gid *gid,
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
enum smc_llc_reqresp reqresp)
{
struct smc_llc_msg_add_link *addllc;
@@ -281,7 +278,7 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
/* prepare a delete link message */
static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc,
struct smc_link *link,
- enum smc_llc_reqresp reqresp)
+ enum smc_llc_reqresp reqresp, bool orderly)
{
memset(delllc, 0, sizeof(*delllc));
delllc->hd.common.type = SMC_LLC_DELETE_LINK;
@@ -290,13 +287,14 @@ static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc,
delllc->hd.flags |= SMC_LLC_FLAG_RESP;
/* DEL_LINK_ALL because only 1 link supported */
delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL;
- delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
+ if (orderly)
+ delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
delllc->link_num = link->link_id;
}
/* send DELETE LINK request or response */
int smc_llc_send_delete_link(struct smc_link *link,
- enum smc_llc_reqresp reqresp)
+ enum smc_llc_reqresp reqresp, bool orderly)
{
struct smc_llc_msg_del_link *delllc;
struct smc_wr_tx_pend_priv *pend;
@@ -307,7 +305,7 @@ int smc_llc_send_delete_link(struct smc_link *link,
if (rc)
return rc;
delllc = (struct smc_llc_msg_del_link *)wr_buf;
- smc_llc_prep_delete_link(delllc, link, reqresp);
+ smc_llc_prep_delete_link(delllc, link, reqresp, orderly);
/* send llc message */
rc = smc_wr_tx_send(link, pend);
return rc;
@@ -381,11 +379,9 @@ static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen)
static void smc_llc_rx_confirm_link(struct smc_link *link,
struct smc_llc_msg_confirm_link *llc)
{
- struct smc_link_group *lgr;
+ struct smc_link_group *lgr = smc_get_lgr(link);
int conf_rc;
- lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
-
/* RMBE eyecatchers are not supported */
if (llc->hd.flags & SMC_LLC_FLAG_NO_RMBE_EYEC)
conf_rc = 0;
@@ -411,8 +407,7 @@ static void smc_llc_rx_confirm_link(struct smc_link *link,
static void smc_llc_rx_add_link(struct smc_link *link,
struct smc_llc_msg_add_link *llc)
{
- struct smc_link_group *lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
+ struct smc_link_group *lgr = smc_get_lgr(link);
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
if (link->state == SMC_LNK_ACTIVATING)
@@ -426,14 +421,12 @@ static void smc_llc_rx_add_link(struct smc_link *link,
if (lgr->role == SMC_SERV) {
smc_llc_prep_add_link(llc, link,
link->smcibdev->mac[link->ibport - 1],
- &link->smcibdev->gid[link->ibport - 1],
- SMC_LLC_REQ);
+ link->gid, SMC_LLC_REQ);
} else {
smc_llc_prep_add_link(llc, link,
link->smcibdev->mac[link->ibport - 1],
- &link->smcibdev->gid[link->ibport - 1],
- SMC_LLC_RESP);
+ link->gid, SMC_LLC_RESP);
}
smc_llc_send_message(link, llc, sizeof(*llc));
}
@@ -442,22 +435,23 @@ static void smc_llc_rx_add_link(struct smc_link *link,
static void smc_llc_rx_delete_link(struct smc_link *link,
struct smc_llc_msg_del_link *llc)
{
- struct smc_link_group *lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
+ struct smc_link_group *lgr = smc_get_lgr(link);
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
if (lgr->role == SMC_SERV)
- smc_lgr_terminate(lgr);
+ smc_lgr_schedule_free_work_fast(lgr);
} else {
+ smc_lgr_forget(lgr);
+ smc_llc_link_deleting(link);
if (lgr->role == SMC_SERV) {
- smc_lgr_forget(lgr);
- smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ);
- smc_llc_send_message(link, llc, sizeof(*llc));
+ /* client asks to delete this link, send request */
+ smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ, true);
} else {
- smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP);
- smc_llc_send_message(link, llc, sizeof(*llc));
- smc_lgr_terminate(lgr);
+ /* server requests to delete this link, send response */
+ smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP, true);
}
+ smc_llc_send_message(link, llc, sizeof(*llc));
+ smc_lgr_schedule_free_work_fast(lgr);
}
}
@@ -476,17 +470,14 @@ static void smc_llc_rx_test_link(struct smc_link *link,
static void smc_llc_rx_confirm_rkey(struct smc_link *link,
struct smc_llc_msg_confirm_rkey *llc)
{
- struct smc_link_group *lgr;
int rc;
- lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
-
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
link->llc_confirm_rkey_rc = llc->hd.flags &
SMC_LLC_FLAG_RKEY_NEG;
complete(&link->llc_confirm_rkey);
} else {
- rc = smc_rtoken_add(lgr,
+ rc = smc_rtoken_add(smc_get_lgr(link),
llc->rtoken[0].rmb_vaddr,
llc->rtoken[0].rmb_key);
@@ -514,18 +505,15 @@ static void smc_llc_rx_confirm_rkey_cont(struct smc_link *link,
static void smc_llc_rx_delete_rkey(struct smc_link *link,
struct smc_llc_msg_delete_rkey *llc)
{
- struct smc_link_group *lgr;
u8 err_mask = 0;
int i, max;
- lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
-
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
/* unused as long as we don't send this type of msg */
} else {
max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX);
for (i = 0; i < max; i++) {
- if (smc_rtoken_delete(lgr, llc->rkey[i]))
+ if (smc_rtoken_delete(smc_get_lgr(link), llc->rkey[i]))
err_mask |= 1 << (SMC_LLC_DEL_RKEY_MAX - 1 - i);
}
@@ -583,12 +571,10 @@ static void smc_llc_testlink_work(struct work_struct *work)
struct smc_link *link = container_of(to_delayed_work(work),
struct smc_link, llc_testlink_wrk);
unsigned long next_interval;
- struct smc_link_group *lgr;
unsigned long expire_time;
u8 user_data[16] = { 0 };
int rc;
- lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
if (link->state != SMC_LNK_ACTIVE)
return; /* don't reschedule worker */
expire_time = link->wr_rx_tstamp + link->llc_testlink_time;
@@ -602,7 +588,7 @@ static void smc_llc_testlink_work(struct work_struct *work)
rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp,
SMC_LLC_WAIT_TIME);
if (rc <= 0) {
- smc_lgr_terminate(lgr);
+ smc_lgr_terminate(smc_get_lgr(link));
return;
}
next_interval = link->llc_testlink_time;
@@ -613,8 +599,7 @@ out:
int smc_llc_link_init(struct smc_link *link)
{
- struct smc_link_group *lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
+ struct smc_link_group *lgr = smc_get_lgr(link);
link->llc_wq = alloc_ordered_workqueue("llc_wq-%x:%x)", WQ_MEM_RECLAIM,
*((u32 *)lgr->id),
link->link_id);
@@ -640,6 +625,11 @@ void smc_llc_link_active(struct smc_link *link, int testlink_time)
}
}
+void smc_llc_link_deleting(struct smc_link *link)
+{
+ link->state = SMC_LNK_DELETING;
+}
+
/* called in tasklet context */
void smc_llc_link_inactive(struct smc_link *link)
{
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 65c8645e96a1..9e2ff088e301 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -36,14 +36,15 @@ enum smc_llc_msg_type {
};
/* transmit */
-int smc_llc_send_confirm_link(struct smc_link *lnk, u8 mac[], union ib_gid *gid,
+int smc_llc_send_confirm_link(struct smc_link *lnk,
enum smc_llc_reqresp reqresp);
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[], union ib_gid *gid,
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
enum smc_llc_reqresp reqresp);
int smc_llc_send_delete_link(struct smc_link *link,
- enum smc_llc_reqresp reqresp);
+ enum smc_llc_reqresp reqresp, bool orderly);
int smc_llc_link_init(struct smc_link *link);
void smc_llc_link_active(struct smc_link *link, int testlink_time);
+void smc_llc_link_deleting(struct smc_link *link);
void smc_llc_link_inactive(struct smc_link *link);
void smc_llc_link_clear(struct smc_link *link);
int smc_llc_do_confirm_rkey(struct smc_link *link,
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 1b6c066d3495..01c6ce042a1c 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -535,11 +535,13 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
}
/* Determine the corresponding IB device port based on the hardware PNETID.
- * Searching stops at the first matching active IB device port.
+ * Searching stops at the first matching active IB device port with vlan_id
+ * configured.
*/
static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
struct smc_ib_device **smcibdev,
- u8 *ibport)
+ u8 *ibport, unsigned short vlan_id,
+ u8 gid[])
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct smc_ib_device *ibdev;
@@ -553,15 +555,20 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
spin_lock(&smc_ib_devices.lock);
list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
for (i = 1; i <= SMC_MAX_PORTS; i++) {
+ if (!rdma_is_port_valid(ibdev->ibdev, i))
+ continue;
if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid,
SMC_MAX_PNETID_LEN) &&
- smc_ib_port_active(ibdev, i)) {
+ smc_ib_port_active(ibdev, i) &&
+ !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
+ NULL)) {
*smcibdev = ibdev;
*ibport = i;
- break;
+ goto out;
}
}
}
+out:
spin_unlock(&smc_ib_devices.lock);
}
@@ -589,7 +596,8 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
/* Lookup of coupled ib_device via SMC pnet table */
static void smc_pnet_find_roce_by_table(struct net_device *netdev,
struct smc_ib_device **smcibdev,
- u8 *ibport)
+ u8 *ibport, unsigned short vlan_id,
+ u8 gid[])
{
struct smc_pnetentry *pnetelem;
@@ -597,7 +605,10 @@ static void smc_pnet_find_roce_by_table(struct net_device *netdev,
list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
if (netdev == pnetelem->ndev) {
if (smc_ib_port_active(pnetelem->smcibdev,
- pnetelem->ib_port)) {
+ pnetelem->ib_port) &&
+ !smc_ib_determine_gid(pnetelem->smcibdev,
+ pnetelem->ib_port, vlan_id,
+ gid, NULL)) {
*smcibdev = pnetelem->smcibdev;
*ibport = pnetelem->ib_port;
}
@@ -612,7 +623,8 @@ static void smc_pnet_find_roce_by_table(struct net_device *netdev,
* ethernet interface.
*/
void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport)
+ struct smc_ib_device **smcibdev, u8 *ibport,
+ unsigned short vlan_id, u8 gid[])
{
struct dst_entry *dst = sk_dst_get(sk);
@@ -625,12 +637,12 @@ void smc_pnet_find_roce_resource(struct sock *sk,
goto out_rel;
/* if possible, lookup via hardware-defined pnetid */
- smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport);
+ smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport, vlan_id, gid);
if (*smcibdev)
goto out_rel;
/* lookup via SMC PNET table */
- smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport);
+ smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport, vlan_id, gid);
out_rel:
dst_release(dst);
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 1e94fd4df7bc..8ff777636e32 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -33,7 +33,8 @@ int smc_pnet_init(void) __init;
void smc_pnet_exit(void);
int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport);
+ struct smc_ib_device **smcibdev, u8 *ibport,
+ unsigned short vlan_id, u8 gid[]);
void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
#endif
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index b329803c8339..bbcf0fe4ae10 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -82,8 +82,7 @@ static int smc_rx_update_consumer(struct smc_sock *smc,
}
}
- smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn),
- conn);
+ smc_curs_copy(&conn->local_tx_ctrl.cons, &cons, conn);
/* send consumer cursor update if required */
/* similar to advertising new TCP rcv_wnd if required */
@@ -97,8 +96,7 @@ static void smc_rx_update_cons(struct smc_sock *smc, size_t len)
struct smc_connection *conn = &smc->conn;
union smc_host_cursor cons;
- smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn),
- conn);
+ smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
smc_rx_update_consumer(smc, cons, len);
}
@@ -157,10 +155,8 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
struct splice_pipe_desc spd;
struct partial_page partial;
struct smc_spd_priv *priv;
- struct page *page;
int bytes;
- page = virt_to_page(smc->conn.rmb_desc->cpu_addr);
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
@@ -172,7 +168,7 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
spd.nr_pages_max = 1;
spd.nr_pages = 1;
- spd.pages = &page;
+ spd.pages = &smc->conn.rmb_desc->pages;
spd.partial = &partial;
spd.ops = &smc_pipe_ops;
spd.spd_release = smc_rx_spd_release;
@@ -245,10 +241,7 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len,
if (!(flags & MSG_TRUNC))
rc = memcpy_to_msg(msg, &conn->urg_rx_byte, 1);
len = 1;
- smc_curs_write(&cons,
- smc_curs_read(&conn->local_tx_ctrl.cons,
- conn),
- conn);
+ smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
if (smc_curs_diff(conn->rmb_desc->len, &cons,
&conn->urg_curs) > 1)
conn->urg_rx_skip_pend = true;
@@ -370,9 +363,7 @@ copy:
continue;
}
- smc_curs_write(&cons,
- smc_curs_read(&conn->local_tx_ctrl.cons, conn),
- conn);
+ smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
/* subsequent splice() calls pick up where previous left */
if (splbytes)
smc_curs_add(conn->rmb_desc->len, &cons, splbytes);
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 142bcb134dd6..2f5e324e54b9 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -181,9 +181,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
copylen = min_t(size_t, send_remaining, writespace);
/* determine start of sndbuf */
sndbuf_base = conn->sndbuf_desc->cpu_addr;
- smc_curs_write(&prep,
- smc_curs_read(&conn->tx_curs_prep, conn),
- conn);
+ smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
tx_cnt_prep = prep.count;
/* determine chunks where to write into sndbuf */
/* either unwrapped case, or 1st chunk of wrapped case */
@@ -214,9 +212,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
smc_sndbuf_sync_sg_for_device(conn);
/* update cursors */
smc_curs_add(conn->sndbuf_desc->len, &prep, copylen);
- smc_curs_write(&conn->tx_curs_prep,
- smc_curs_read(&prep, conn),
- conn);
+ smc_curs_copy(&conn->tx_curs_prep, &prep, conn);
/* increased in send tasklet smc_cdc_tx_handler() */
smp_mb__before_atomic();
atomic_sub(copylen, &conn->sndbuf_space);
@@ -417,8 +413,8 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
int rc;
/* source: sndbuf */
- smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
- smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
+ smc_curs_copy(&sent, &conn->tx_curs_sent, conn);
+ smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
/* cf. wmem_alloc - (snd_max - snd_una) */
to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
if (to_send <= 0)
@@ -429,12 +425,8 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
rmbespace = atomic_read(&conn->peer_rmbe_space);
if (rmbespace <= 0)
return 0;
- smc_curs_write(&prod,
- smc_curs_read(&conn->local_tx_ctrl.prod, conn),
- conn);
- smc_curs_write(&cons,
- smc_curs_read(&conn->local_rx_ctrl.cons, conn),
- conn);
+ smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn);
+ smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn);
/* if usable snd_wnd closes ask peer to advertise once it opens again */
pflags = &conn->local_tx_ctrl.prod_flags;
@@ -481,14 +473,9 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
pflags->urg_data_present = 1;
smc_tx_advance_cursors(conn, &prod, &sent, len);
/* update connection's cursors with advanced local cursors */
- smc_curs_write(&conn->local_tx_ctrl.prod,
- smc_curs_read(&prod, conn),
- conn);
+ smc_curs_copy(&conn->local_tx_ctrl.prod, &prod, conn);
/* dst: peer RMBE */
- smc_curs_write(&conn->tx_curs_sent,
- smc_curs_read(&sent, conn),
- conn);
- /* src: local sndbuf */
+ smc_curs_copy(&conn->tx_curs_sent, &sent, conn);/* src: local sndbuf */
return 0;
}
@@ -606,17 +593,11 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
int sender_free = conn->rmb_desc->len;
int to_confirm;
- smc_curs_write(&cons,
- smc_curs_read(&conn->local_tx_ctrl.cons, conn),
- conn);
- smc_curs_write(&cfed,
- smc_curs_read(&conn->rx_curs_confirmed, conn),
- conn);
+ smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+ smc_curs_copy(&cfed, &conn->rx_curs_confirmed, conn);
to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
if (to_confirm > conn->rmbe_update_limit) {
- smc_curs_write(&prod,
- smc_curs_read(&conn->local_rx_ctrl.prod, conn),
- conn);
+ smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn);
sender_free = conn->rmb_desc->len -
smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
}
@@ -632,9 +613,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
SMC_TX_WORK_DELAY);
return;
}
- smc_curs_write(&conn->rx_curs_confirmed,
- smc_curs_read(&conn->local_tx_ctrl.cons, conn),
- conn);
+ smc_curs_copy(&conn->rx_curs_confirmed,
+ &conn->local_tx_ctrl.cons, conn);
conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
}
if (conn->local_rx_ctrl.prod_flags.write_blocked &&
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index b22bdc5694c4..07e6ad76224a 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -22,8 +22,8 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn)
{
union smc_host_cursor sent, prep;
- smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
- smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
+ smc_curs_copy(&sent, &conn->tx_curs_sent, conn);
+ smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
}
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index dbd2605d1962..f856b8402b3f 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -92,8 +92,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask))
return;
if (wc->status) {
- struct smc_link_group *lgr;
-
for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
/* clear full struct smc_wr_tx_pend including .priv */
memset(&link->wr_tx_pends[i], 0,
@@ -103,9 +101,7 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
clear_bit(i, link->wr_tx_mask);
}
/* terminate connections of this link group abnormally */
- lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
- smc_lgr_terminate(lgr);
+ smc_lgr_terminate(smc_get_lgr(link));
}
if (pnd_snd.handler)
pnd_snd.handler(&pnd_snd.priv, link, wc->status);
@@ -186,18 +182,14 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
if (rc)
return rc;
} else {
- struct smc_link_group *lgr;
-
- lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
rc = wait_event_timeout(
link->wr_tx_wait,
- list_empty(&lgr->list) || /* lgr terminated */
+ link->state == SMC_LNK_INACTIVE ||
(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
SMC_WR_TX_WAIT_FREE_SLOT_TIME);
if (!rc) {
/* timeout - terminate connections */
- smc_lgr_terminate(lgr);
+ smc_lgr_terminate(smc_get_lgr(link));
return -EPIPE;
}
if (idx == link->wr_tx_cnt)
@@ -250,12 +242,8 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx],
&failed_wr);
if (rc) {
- struct smc_link_group *lgr =
- container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
-
smc_wr_tx_put_slot(link, priv);
- smc_lgr_terminate(lgr);
+ smc_lgr_terminate(smc_get_lgr(link));
}
return rc;
}
@@ -283,11 +271,7 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
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);
+ smc_lgr_terminate(smc_get_lgr(link));
return -EPIPE;
}
if (rc == -ERESTARTSYS)
@@ -380,8 +364,6 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
smc_wr_rx_demultiplex(&wc[i]);
smc_wr_rx_post(link); /* refill WR RX */
} else {
- struct smc_link_group *lgr;
-
/* handle status errors */
switch (wc[i].status) {
case IB_WC_RETRY_EXC_ERR:
@@ -390,9 +372,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
/* terminate connections of this link group
* abnormally
*/
- lgr = container_of(link, struct smc_link_group,
- lnk[SMC_SINGLE_LINK]);
- smc_lgr_terminate(lgr);
+ smc_lgr_terminate(smc_get_lgr(link));
break;
default:
smc_wr_rx_post(link); /* refill WR RX */
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-05 05:18:32 +0300