Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/net/smc/Kconfig b/net/smc/Kconfig
index c717ef0..f54a70b 100644
--- a/net/smc/Kconfig
+++ b/net/smc/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config SMC
tristate "SMC socket protocol family"
depends on INET && INFINIBAND
diff --git a/net/smc/Makefile b/net/smc/Makefile
index 4df96b4..cb12545 100644
--- a/net/smc/Makefile
+++ b/net/smc/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_SMC) += smc.o
obj-$(CONFIG_SMC_DIAG) += smc_diag.o
smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 80e2119..737b499 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -30,6 +31,10 @@
#include <net/smc.h>
#include <asm/ioctls.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include "smc_netns.h"
+
#include "smc.h"
#include "smc_clc.h"
#include "smc_llc.h"
@@ -42,8 +47,11 @@
#include "smc_rx.h"
#include "smc_close.h"
-static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group
- * creation
+static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group
+ * creation on server
+ */
+static DEFINE_MUTEX(smc_client_lgr_pending); /* serialize link group
+ * creation on client
*/
static void smc_tcp_listen_work(struct work_struct *);
@@ -115,6 +123,48 @@
};
EXPORT_SYMBOL_GPL(smc_proto6);
+static void smc_restore_fallback_changes(struct smc_sock *smc)
+{
+ smc->clcsock->file->private_data = smc->sk.sk_socket;
+ smc->clcsock->file = NULL;
+}
+
+static int __smc_release(struct smc_sock *smc)
+{
+ struct sock *sk = &smc->sk;
+ int rc = 0;
+
+ if (!smc->use_fallback) {
+ rc = smc_close_active(smc);
+ sock_set_flag(sk, SOCK_DEAD);
+ sk->sk_shutdown |= SHUTDOWN_MASK;
+ } else {
+ if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+ sock_put(sk); /* passive closing */
+ if (sk->sk_state == SMC_LISTEN) {
+ /* wake up clcsock accept */
+ rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
+ }
+ sk->sk_state = SMC_CLOSED;
+ sk->sk_state_change(sk);
+ smc_restore_fallback_changes(smc);
+ }
+
+ sk->sk_prot->unhash(sk);
+
+ if (sk->sk_state == SMC_CLOSED) {
+ if (smc->clcsock) {
+ release_sock(sk);
+ smc_clcsock_release(smc);
+ lock_sock(sk);
+ }
+ if (!smc->use_fallback)
+ smc_conn_free(&smc->conn);
+ }
+
+ return rc;
+}
+
static int smc_release(struct socket *sock)
{
struct sock *sk = sock->sk;
@@ -127,9 +177,9 @@
smc = smc_sk(sk);
/* cleanup for a dangling non-blocking connect */
+ if (smc->connect_nonblock && sk->sk_state == SMC_INIT)
+ tcp_abort(smc->clcsock->sk, ECONNABORTED);
flush_work(&smc->connect_work);
- kfree(smc->connect_info);
- smc->connect_info = NULL;
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
@@ -139,30 +189,13 @@
else
lock_sock(sk);
- if (!smc->use_fallback) {
- rc = smc_close_active(smc);
- sock_set_flag(sk, SOCK_DEAD);
- sk->sk_shutdown |= SHUTDOWN_MASK;
- }
- if (smc->clcsock) {
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- }
- if (smc->use_fallback) {
- 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);
- }
+ rc = __smc_release(smc);
/* detach socket */
sock_orphan(sk);
sock->sk = NULL;
- if (!smc->use_fallback && sk->sk_state == SMC_CLOSED)
- smc_conn_free(&smc->conn);
release_sock(sk);
- sk->sk_prot->unhash(sk);
sock_put(sk); /* final sock_put */
out:
return rc;
@@ -203,6 +236,7 @@
spin_lock_init(&smc->conn.send_lock);
sk->sk_prot->hash(sk);
sk_refcnt_debug_inc(sk);
+ mutex_init(&smc->clcsock_release_lock);
return sk;
}
@@ -236,7 +270,7 @@
/* Check if socket is already active */
rc = -EINVAL;
- if (sk->sk_state != SMC_INIT)
+ if (sk->sk_state != SMC_INIT || smc->connect_nonblock)
goto out_rel;
smc->clcsock->sk->sk_reuse = sk->sk_reuse;
@@ -280,7 +314,8 @@
(1UL << SOCK_RXQ_OVFL) | \
(1UL << SOCK_WIFI_STATUS) | \
(1UL << SOCK_NOFCS) | \
- (1UL << SOCK_FILTER_LOCKED))
+ (1UL << SOCK_FILTER_LOCKED) | \
+ (1UL << SOCK_TSTAMP_NEW))
/* copy only relevant settings and flags of SOL_SOCKET level from smc to
* clc socket (since smc is not called for these options from net/core)
*/
@@ -299,14 +334,17 @@
smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
}
-/* register a new rmb, optionally send confirm_rkey msg to register with peer */
+/* register a new rmb, send confirm_rkey msg to register with peer */
static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc,
bool conf_rkey)
{
- /* register memory region for new rmb */
- if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
- rmb_desc->regerr = 1;
- return -EFAULT;
+ if (!rmb_desc->wr_reg) {
+ /* register memory region for new rmb */
+ if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
+ rmb_desc->regerr = 1;
+ return -EFAULT;
+ }
+ rmb_desc->wr_reg = 1;
}
if (!conf_rkey)
return 0;
@@ -335,8 +373,8 @@
struct smc_clc_msg_decline dclc;
rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
- SMC_CLC_DECLINE);
- return rc;
+ SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
+ return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
}
if (link->llc_confirm_rc)
@@ -363,8 +401,8 @@
struct smc_clc_msg_decline dclc;
rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
- SMC_CLC_DECLINE);
- return rc;
+ SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
+ return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
}
/* send add link reject message, only one link supported for now */
@@ -423,12 +461,22 @@
link->peer_mtu = clc->qp_mtu;
}
+static void smc_switch_to_fallback(struct smc_sock *smc)
+{
+ smc->use_fallback = true;
+ if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
+ smc->clcsock->file = smc->sk.sk_socket->file;
+ smc->clcsock->file->private_data = smc->clcsock;
+ }
+}
+
/* fall back during connect */
static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
{
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = reason_code;
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
return 0;
@@ -461,48 +509,48 @@
{
if (local_contact == SMC_FIRST_CONTACT)
smc_lgr_forget(smc->conn.lgr);
- mutex_unlock(&smc_create_lgr_pending);
+ if (smc->conn.lgr->is_smcd)
+ /* there is only one lgr role for SMC-D; use server lock */
+ mutex_unlock(&smc_server_lgr_pending);
+ else
+ mutex_unlock(&smc_client_lgr_pending);
+
smc_conn_free(&smc->conn);
+ smc->connect_nonblock = 0;
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, unsigned short vlan_id, u8 gid[])
+static int smc_find_rdma_device(struct smc_sock *smc, struct smc_init_info *ini)
{
- int reason_code = 0;
-
/* PNET table look up: search active ib_device and port
* 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, vlan_id,
- gid);
- if (!(*ibdev))
- reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
-
- return reason_code;
+ smc_pnet_find_roce_resource(smc->clcsock->sk, ini);
+ if (!ini->ib_dev)
+ return SMC_CLC_DECL_NOSMCRDEV;
+ return 0;
}
/* check if there is an ISM device available for this connection. */
/* called for connect and listen */
-static int smc_check_ism(struct smc_sock *smc, struct smcd_dev **ismdev)
+static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini)
{
/* Find ISM device with same PNETID as connecting interface */
- smc_pnet_find_ism_resource(smc->clcsock->sk, ismdev);
- if (!(*ismdev))
- return SMC_CLC_DECL_CNFERR; /* configuration error */
+ smc_pnet_find_ism_resource(smc->clcsock->sk, ini);
+ if (!ini->ism_dev)
+ return SMC_CLC_DECL_NOSMCDDEV;
return 0;
}
/* Check for VLAN ID and register it on ISM device just for CLC handshake */
static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
- struct smcd_dev *ismdev,
- unsigned short vlan_id)
+ struct smc_init_info *ini)
{
- if (vlan_id && smc_ism_get_vlan(ismdev, vlan_id))
- return SMC_CLC_DECL_CNFERR;
+ if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev, ini->vlan_id))
+ return SMC_CLC_DECL_ISMVLANERR;
return 0;
}
@@ -510,12 +558,11 @@
* used, the VLAN ID will be registered again during the connection setup.
*/
static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
- struct smcd_dev *ismdev,
- unsigned short vlan_id)
+ struct smc_init_info *ini)
{
if (!is_smcd)
return 0;
- if (vlan_id && smc_ism_put_vlan(ismdev, vlan_id))
+ if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev, ini->vlan_id))
return SMC_CLC_DECL_CNFERR;
return 0;
}
@@ -523,39 +570,37 @@
/* CLC handshake during connect */
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,
- u8 gid[], struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
int rc = 0;
/* do inband token exchange */
- rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev);
+ rc = smc_clc_send_proposal(smc, smc_type, ini);
if (rc)
return rc;
/* receive SMC Accept CLC message */
- return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT);
+ return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT,
+ CLC_WAIT_TIME);
}
/* setup for RDMA connection of client */
static int smc_connect_rdma(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *aclc,
- struct smc_ib_device *ibdev, u8 ibport)
+ struct smc_init_info *ini)
{
- int local_contact = SMC_FIRST_CONTACT;
struct smc_link *link;
int reason_code = 0;
- mutex_lock(&smc_create_lgr_pending);
- local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
- ibport, &aclc->lcl, NULL, 0);
- if (local_contact < 0) {
- if (local_contact == -ENOMEM)
- reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- else if (local_contact == -ENOLINK)
- reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
- else
- reason_code = SMC_CLC_DECL_INTERR; /* other error */
- return smc_connect_abort(smc, reason_code, 0);
+ ini->is_smcd = false;
+ ini->ib_lcl = &aclc->lcl;
+ ini->ib_clcqpn = ntoh24(aclc->qpn);
+ ini->srv_first_contact = aclc->hdr.flag;
+
+ mutex_lock(&smc_client_lgr_pending);
+ reason_code = smc_conn_create(smc, ini);
+ if (reason_code) {
+ mutex_unlock(&smc_client_lgr_pending);
+ return reason_code;
}
link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK];
@@ -563,46 +608,48 @@
/* create send buffer and rmb */
if (smc_buf_create(smc, false))
- return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
+ ini->cln_first_contact);
- if (local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_link_save_peer_info(link, aclc);
if (smc_rmb_rtoken_handling(&smc->conn, aclc))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
- local_contact);
+ ini->cln_first_contact);
smc_close_init(smc);
smc_rx_init(smc);
- if (local_contact == SMC_FIRST_CONTACT) {
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
if (smc_ib_ready_link(link))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
- local_contact);
+ ini->cln_first_contact);
} else {
- if (!smc->conn.rmb_desc->reused &&
- smc_reg_rmb(link, smc->conn.rmb_desc, true))
+ if (smc_reg_rmb(link, smc->conn.rmb_desc, true))
return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
- local_contact);
+ ini->cln_first_contact);
}
smc_rmb_sync_sg_for_device(&smc->conn);
reason_code = smc_clc_send_confirm(smc);
if (reason_code)
- return smc_connect_abort(smc, reason_code, local_contact);
+ return smc_connect_abort(smc, reason_code,
+ ini->cln_first_contact);
smc_tx_init(smc);
- if (local_contact == SMC_FIRST_CONTACT) {
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
/* QP confirmation over RoCE fabric */
reason_code = smc_clnt_conf_first_link(smc);
if (reason_code)
return smc_connect_abort(smc, reason_code,
- local_contact);
+ ini->cln_first_contact);
}
- mutex_unlock(&smc_create_lgr_pending);
+ mutex_unlock(&smc_client_lgr_pending);
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
@@ -612,20 +659,26 @@
/* setup for ISM connection of client */
static int smc_connect_ism(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *aclc,
- struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
- int local_contact = SMC_FIRST_CONTACT;
int rc = 0;
- mutex_lock(&smc_create_lgr_pending);
- local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0,
- NULL, ismdev, aclc->gid);
- if (local_contact < 0)
- return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0);
+ ini->is_smcd = true;
+ ini->ism_gid = aclc->gid;
+ ini->srv_first_contact = aclc->hdr.flag;
+
+ /* there is only one lgr role for SMC-D; use server lock */
+ mutex_lock(&smc_server_lgr_pending);
+ rc = smc_conn_create(smc, ini);
+ if (rc) {
+ mutex_unlock(&smc_server_lgr_pending);
+ return rc;
+ }
/* Create send and receive buffers */
if (smc_buf_create(smc, true))
- return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+ return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
+ ini->cln_first_contact);
smc_conn_save_peer_info(smc, aclc);
smc_close_init(smc);
@@ -634,10 +687,11 @@
rc = smc_clc_send_confirm(smc);
if (rc)
- return smc_connect_abort(smc, rc, local_contact);
- mutex_unlock(&smc_create_lgr_pending);
+ return smc_connect_abort(smc, rc, ini->cln_first_contact);
+ mutex_unlock(&smc_server_lgr_pending);
smc_copy_sock_settings_to_clc(smc);
+ smc->connect_nonblock = 0;
if (smc->sk.sk_state == SMC_INIT)
smc->sk.sk_state = SMC_ACTIVE;
@@ -649,15 +703,9 @@
{
bool ism_supported = false, rdma_supported = false;
struct smc_clc_msg_accept_confirm aclc;
- struct smc_ib_device *ibdev;
- struct smcd_dev *ismdev;
- u8 gid[SMC_GID_SIZE];
- unsigned short vlan;
+ struct smc_init_info ini = {0};
int smc_type;
int rc = 0;
- u8 ibport;
-
- sock_hold(&smc->sk); /* sock put in passive closing */
if (smc->use_fallback)
return smc_connect_fallback(smc, smc->fallback_rsn);
@@ -670,20 +718,21 @@
if (using_ipsec(smc))
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
- /* check for VLAN ID */
- if (smc_vlan_by_tcpsk(smc->clcsock, &vlan))
- return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+ /* get vlan id from IP device */
+ if (smc_vlan_by_tcpsk(smc->clcsock, &ini))
+ return smc_connect_decline_fallback(smc,
+ SMC_CLC_DECL_GETVLANERR);
/* check if there is an ism device available */
- if (!smc_check_ism(smc, &ismdev) &&
- !smc_connect_ism_vlan_setup(smc, ismdev, vlan)) {
+ if (!smc_find_ism_device(smc, &ini) &&
+ !smc_connect_ism_vlan_setup(smc, &ini)) {
/* ISM is supported for this connection */
ism_supported = true;
smc_type = SMC_TYPE_D;
}
/* check if there is a rdma device available */
- if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) {
+ if (!smc_find_rdma_device(smc, &ini)) {
/* RDMA is supported for this connection */
rdma_supported = true;
if (ism_supported)
@@ -697,25 +746,25 @@
return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
/* perform CLC handshake */
- rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
+ rc = smc_connect_clc(smc, smc_type, &aclc, &ini);
if (rc) {
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return smc_connect_decline_fallback(smc, rc);
}
/* depending on previous steps, connect using rdma or ism */
if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
- rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
+ rc = smc_connect_rdma(smc, &aclc, &ini);
else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
- rc = smc_connect_ism(smc, &aclc, ismdev);
+ rc = smc_connect_ism(smc, &aclc, &ini);
else
rc = SMC_CLC_DECL_MODEUNSUPP;
if (rc) {
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return smc_connect_decline_fallback(smc, rc);
}
- smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
+ smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
return 0;
}
@@ -723,17 +772,31 @@
{
struct smc_sock *smc = container_of(work, struct smc_sock,
connect_work);
- int rc;
+ long timeo = smc->sk.sk_sndtimeo;
+ int rc = 0;
- lock_sock(&smc->sk);
- rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
- smc->connect_info->alen, smc->connect_info->flags);
+ if (!timeo)
+ timeo = MAX_SCHEDULE_TIMEOUT;
+ lock_sock(smc->clcsock->sk);
if (smc->clcsock->sk->sk_err) {
smc->sk.sk_err = smc->clcsock->sk->sk_err;
- goto out;
+ } else if ((1 << smc->clcsock->sk->sk_state) &
+ (TCPF_SYN_SENT | TCP_SYN_RECV)) {
+ rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo);
+ if ((rc == -EPIPE) &&
+ ((1 << smc->clcsock->sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)))
+ rc = 0;
}
- if (rc < 0) {
- smc->sk.sk_err = -rc;
+ release_sock(smc->clcsock->sk);
+ lock_sock(&smc->sk);
+ if (rc != 0 || smc->sk.sk_err) {
+ smc->sk.sk_state = SMC_CLOSED;
+ if (rc == -EPIPE || rc == -EAGAIN)
+ smc->sk.sk_err = EPIPE;
+ else if (signal_pending(current))
+ smc->sk.sk_err = -sock_intr_errno(timeo);
+ sock_put(&smc->sk); /* passive closing */
goto out;
}
@@ -742,12 +805,14 @@
smc->sk.sk_err = -rc;
out:
- if (smc->sk.sk_err)
- smc->sk.sk_state_change(&smc->sk);
- else
- smc->sk.sk_write_space(&smc->sk);
- kfree(smc->connect_info);
- smc->connect_info = NULL;
+ if (!sock_flag(&smc->sk, SOCK_DEAD)) {
+ if (smc->sk.sk_err) {
+ smc->sk.sk_state_change(&smc->sk);
+ } else { /* allow polling before and after fallback decision */
+ smc->clcsock->sk->sk_write_space(smc->clcsock->sk);
+ smc->sk.sk_write_space(&smc->sk);
+ }
+ }
release_sock(&smc->sk);
}
@@ -780,26 +845,20 @@
smc_copy_sock_settings_to_clc(smc);
tcp_sk(smc->clcsock->sk)->syn_smc = 1;
+ if (smc->connect_nonblock) {
+ rc = -EALREADY;
+ goto out;
+ }
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc && rc != -EINPROGRESS)
+ goto out;
+
+ sock_hold(&smc->sk); /* sock put in passive closing */
if (flags & O_NONBLOCK) {
- if (smc->connect_info) {
- rc = -EALREADY;
- goto out;
- }
- smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
- if (!smc->connect_info) {
- rc = -ENOMEM;
- goto out;
- }
- smc->connect_info->alen = alen;
- smc->connect_info->flags = flags ^ O_NONBLOCK;
- memcpy(&smc->connect_info->addr, addr, alen);
- schedule_work(&smc->connect_work);
+ if (schedule_work(&smc->connect_work))
+ smc->connect_nonblock = 1;
rc = -EINPROGRESS;
} else {
- rc = kernel_connect(smc->clcsock, addr, alen, flags);
- if (rc)
- goto out;
-
rc = __smc_connect(smc);
if (rc < 0)
goto out;
@@ -818,7 +877,7 @@
struct socket *new_clcsock = NULL;
struct sock *lsk = &lsmc->sk;
struct sock *new_sk;
- int rc;
+ int rc = -EINVAL;
release_sock(lsk);
new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol);
@@ -831,16 +890,19 @@
}
*new_smc = smc_sk(new_sk);
- rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0);
+ mutex_lock(&lsmc->clcsock_release_lock);
+ if (lsmc->clcsock)
+ rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0);
+ mutex_unlock(&lsmc->clcsock_release_lock);
lock_sock(lsk);
if (rc < 0)
lsk->sk_err = -rc;
if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (new_clcsock)
sock_release(new_clcsock);
new_sk->sk_state = SMC_CLOSED;
sock_set_flag(new_sk, SOCK_DEAD);
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
*new_smc = NULL;
goto out;
@@ -891,16 +953,21 @@
smc_accept_unlink(new_sk);
if (new_sk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (isk->clcsock) {
sock_release(isk->clcsock);
isk->clcsock = NULL;
}
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
continue;
}
- if (new_sock)
+ if (new_sock) {
sock_graft(new_sk, new_sock);
+ if (isk->use_fallback) {
+ smc_sk(new_sk)->clcsock->file = new_sock->file;
+ isk->clcsock->file->private_data = isk->clcsock;
+ }
+ }
return new_sk;
}
return NULL;
@@ -915,27 +982,8 @@
if (!sk->sk_lingertime)
/* wait for peer closing */
sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT;
- if (!smc->use_fallback) {
- smc_close_active(smc);
- sock_set_flag(sk, SOCK_DEAD);
- sk->sk_shutdown |= SHUTDOWN_MASK;
- }
- if (smc->clcsock) {
- struct socket *tcp;
-
- tcp = smc->clcsock;
- smc->clcsock = NULL;
- sock_release(tcp);
- }
- if (smc->use_fallback) {
- sock_put(sk); /* passive closing */
- sk->sk_state = SMC_CLOSED;
- } else {
- if (sk->sk_state == SMC_CLOSED)
- smc_conn_free(&smc->conn);
- }
+ __smc_release(smc);
release_sock(sk);
- sk->sk_prot->unhash(sk);
sock_put(sk); /* final sock_put */
}
@@ -965,8 +1013,8 @@
struct smc_clc_msg_decline dclc;
rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
- SMC_CLC_DECLINE);
- return rc;
+ SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
+ return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
}
if (link->llc_confirm_resp_rc)
@@ -986,8 +1034,8 @@
struct smc_clc_msg_decline dclc;
rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc),
- SMC_CLC_DECLINE);
- return rc;
+ SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
+ return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_AL : rc;
}
smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
@@ -1001,13 +1049,13 @@
struct smc_sock *lsmc = new_smc->listen_smc;
struct sock *newsmcsk = &new_smc->sk;
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
smc_accept_enqueue(&lsmc->sk, newsmcsk);
+ release_sock(&lsmc->sk);
} else { /* no longer listening */
smc_close_non_accepted(newsmcsk);
}
- release_sock(&lsmc->sk);
/* Wake up accept */
lsmc->sk.sk_data_ready(&lsmc->sk);
@@ -1051,7 +1099,7 @@
return;
}
smc_conn_free(&new_smc->conn);
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
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) {
@@ -1063,7 +1111,7 @@
}
/* listen worker: check prefixes */
-static int smc_listen_rdma_check(struct smc_sock *new_smc,
+static int smc_listen_prfx_check(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc)
{
struct smc_clc_msg_proposal_prefix *pclc_prfx;
@@ -1071,25 +1119,21 @@
pclc_prfx = smc_clc_proposal_get_prefix(pclc);
if (smc_clc_prfx_match(newclcsock, pclc_prfx))
- return SMC_CLC_DECL_CNFERR;
+ return SMC_CLC_DECL_DIFFPREFIX;
return 0;
}
/* listen worker: initialize connection and buffers */
static int smc_listen_rdma_init(struct smc_sock *new_smc,
- struct smc_clc_msg_proposal *pclc,
- struct smc_ib_device *ibdev, u8 ibport,
- int *local_contact)
+ struct smc_init_info *ini)
{
+ int rc;
+
/* allocate connection / link group */
- *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport,
- &pclc->lcl, NULL, 0);
- if (*local_contact < 0) {
- if (*local_contact == -ENOMEM)
- return SMC_CLC_DECL_MEM;/* insufficient memory*/
- return SMC_CLC_DECL_INTERR; /* other error */
- }
+ rc = smc_conn_create(new_smc, ini);
+ if (rc)
+ return rc;
/* create send buffer and rmb */
if (smc_buf_create(new_smc, false))
@@ -1101,33 +1145,30 @@
/* listen worker: initialize connection and buffers for SMC-D */
static int smc_listen_ism_init(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc,
- struct smcd_dev *ismdev,
- int *local_contact)
+ struct smc_init_info *ini)
{
struct smc_clc_msg_smcd *pclc_smcd;
+ int rc;
pclc_smcd = smc_get_clc_msg_smcd(pclc);
- *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL,
- ismdev, pclc_smcd->gid);
- if (*local_contact < 0) {
- if (*local_contact == -ENOMEM)
- return SMC_CLC_DECL_MEM;/* insufficient memory*/
- return SMC_CLC_DECL_INTERR; /* other error */
- }
+ ini->ism_gid = pclc_smcd->gid;
+ rc = smc_conn_create(new_smc, ini);
+ if (rc)
+ return rc;
/* Check if peer can be reached via ISM device */
if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid,
new_smc->conn.lgr->vlan_id,
new_smc->conn.lgr->smcd)) {
- if (*local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_lgr_forget(new_smc->conn.lgr);
smc_conn_free(&new_smc->conn);
- return SMC_CLC_DECL_CNFERR;
+ return SMC_CLC_DECL_SMCDNOTALK;
}
/* Create send and receive buffers */
if (smc_buf_create(new_smc, true)) {
- if (*local_contact == SMC_FIRST_CONTACT)
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT)
smc_lgr_forget(new_smc->conn.lgr);
smc_conn_free(&new_smc->conn);
return SMC_CLC_DECL_MEM;
@@ -1142,10 +1183,8 @@
struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
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_ERR_REGRMB;
- }
+ if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
+ return SMC_CLC_DECL_ERR_REGRMB;
}
smc_rmb_sync_sg_for_device(&new_smc->conn);
@@ -1181,7 +1220,6 @@
return 0;
decline:
- mutex_unlock(&smc_create_lgr_pending);
smc_listen_decline(new_smc, reason_code, local_contact);
return reason_code;
}
@@ -1194,15 +1232,13 @@
struct socket *newclcsock = new_smc->clcsock;
struct smc_clc_msg_accept_confirm cclc;
struct smc_clc_msg_proposal *pclc;
- struct smc_ib_device *ibdev;
+ struct smc_init_info ini = {0};
bool ism_supported = false;
- 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;
+
+ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+ return smc_listen_out_err(new_smc);
if (new_smc->use_fallback) {
smc_listen_out_connected(new_smc);
@@ -1211,7 +1247,7 @@
/* check if peer is smc capable */
if (!tcp_sk(newclcsock->sk)->syn_smc) {
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
smc_listen_out_connected(new_smc);
return;
@@ -1221,72 +1257,101 @@
* wait for and receive SMC Proposal CLC message
*/
pclc = (struct smc_clc_msg_proposal *)&buf;
- reason_code = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
- SMC_CLC_PROPOSAL);
- if (reason_code) {
- smc_listen_decline(new_smc, reason_code, 0);
- return;
- }
+ rc = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
+ SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
+ if (rc)
+ goto out_decl;
/* IPSec connections opt out of SMC-R optimizations */
if (using_ipsec(new_smc)) {
- smc_listen_decline(new_smc, SMC_CLC_DECL_IPSEC, 0);
- return;
+ rc = SMC_CLC_DECL_IPSEC;
+ goto out_decl;
}
- mutex_lock(&smc_create_lgr_pending);
+ /* check for matching IP prefix and subnet length */
+ rc = smc_listen_prfx_check(new_smc, pclc);
+ if (rc)
+ goto out_decl;
+
+ /* get vlan id from IP device */
+ if (smc_vlan_by_tcpsk(new_smc->clcsock, &ini)) {
+ rc = SMC_CLC_DECL_GETVLANERR;
+ goto out_decl;
+ }
+
+ mutex_lock(&smc_server_lgr_pending);
smc_close_init(new_smc);
smc_rx_init(new_smc);
smc_tx_init(new_smc);
/* check if ISM is available */
- if ((pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) &&
- !smc_check_ism(new_smc, &ismdev) &&
- !smc_listen_ism_init(new_smc, pclc, ismdev, &local_contact)) {
- ism_supported = true;
+ if (pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) {
+ ini.is_smcd = true; /* prepare ISM check */
+ rc = smc_find_ism_device(new_smc, &ini);
+ if (!rc)
+ rc = smc_listen_ism_init(new_smc, pclc, &ini);
+ if (!rc)
+ ism_supported = true;
+ else if (pclc->hdr.path == SMC_TYPE_D)
+ goto out_unlock; /* skip RDMA and decline */
}
/* check if RDMA is available */
- if (!ism_supported &&
- ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
- 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_MODEUNSUPP,
- local_contact);
- return;
+ if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */
+ /* prepare RDMA check */
+ ini.is_smcd = false;
+ ini.ism_dev = NULL;
+ ini.ib_lcl = &pclc->lcl;
+ rc = smc_find_rdma_device(new_smc, &ini);
+ if (rc) {
+ /* no RDMA device found */
+ if (pclc->hdr.path == SMC_TYPE_B)
+ /* neither ISM nor RDMA device found */
+ rc = SMC_CLC_DECL_NOSMCDEV;
+ goto out_unlock;
+ }
+ rc = smc_listen_rdma_init(new_smc, &ini);
+ if (rc)
+ goto out_unlock;
+ rc = smc_listen_rdma_reg(new_smc, ini.cln_first_contact);
+ if (rc)
+ goto out_unlock;
}
/* send SMC Accept CLC message */
- rc = smc_clc_send_accept(new_smc, local_contact);
- if (rc) {
- mutex_unlock(&smc_create_lgr_pending);
- smc_listen_decline(new_smc, rc, local_contact);
- return;
- }
+ rc = smc_clc_send_accept(new_smc, ini.cln_first_contact);
+ if (rc)
+ goto out_unlock;
+
+ /* SMC-D does not need this lock any more */
+ if (ism_supported)
+ mutex_unlock(&smc_server_lgr_pending);
/* receive SMC Confirm CLC message */
- reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
- SMC_CLC_CONFIRM);
- if (reason_code) {
- mutex_unlock(&smc_create_lgr_pending);
- smc_listen_decline(new_smc, reason_code, local_contact);
- return;
+ rc = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
+ SMC_CLC_CONFIRM, CLC_WAIT_TIME);
+ if (rc) {
+ if (!ism_supported)
+ goto out_unlock;
+ goto out_decl;
}
/* finish worker */
if (!ism_supported) {
- if (smc_listen_rdma_finish(new_smc, &cclc, local_contact))
+ rc = smc_listen_rdma_finish(new_smc, &cclc,
+ ini.cln_first_contact);
+ mutex_unlock(&smc_server_lgr_pending);
+ if (rc)
return;
}
smc_conn_save_peer_info(new_smc, &cclc);
- mutex_unlock(&smc_create_lgr_pending);
smc_listen_out_connected(new_smc);
+ return;
+
+out_unlock:
+ mutex_unlock(&smc_server_lgr_pending);
+out_decl:
+ smc_listen_decline(new_smc, rc, ini.cln_first_contact);
}
static void smc_tcp_listen_work(struct work_struct *work)
@@ -1333,7 +1398,8 @@
lock_sock(sk);
rc = -EINVAL;
- if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN))
+ if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) ||
+ smc->connect_nonblock)
goto out;
rc = 0;
@@ -1354,7 +1420,6 @@
sk->sk_max_ack_backlog = backlog;
sk->sk_ack_backlog = 0;
sk->sk_state = SMC_LISTEN;
- INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
sock_hold(sk); /* sock_hold in tcp_listen_worker */
if (!schedule_work(&smc->tcp_listen_work))
sock_put(sk);
@@ -1462,8 +1527,8 @@
goto out;
if (msg->msg_flags & MSG_FASTOPEN) {
- if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
rc = -EINVAL;
@@ -1489,6 +1554,11 @@
smc = smc_sk(sk);
lock_sock(sk);
+ if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) {
+ /* socket was connected before, no more data to read */
+ rc = 0;
+ goto out;
+ }
if ((sk->sk_state == SMC_INIT) ||
(sk->sk_state == SMC_LISTEN) ||
(sk->sk_state == SMC_CLOSED))
@@ -1528,8 +1598,8 @@
poll_table *wait)
{
struct sock *sk = sock->sk;
- __poll_t mask = 0;
struct smc_sock *smc;
+ __poll_t mask = 0;
if (!sk)
return EPOLLNVAL;
@@ -1539,8 +1609,6 @@
/* delegate to CLC child sock */
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err)
- mask |= EPOLLERR;
} else {
if (sk->sk_state != SMC_CLOSED)
sock_poll_wait(file, sock, wait);
@@ -1551,9 +1619,14 @@
mask |= EPOLLHUP;
if (sk->sk_state == SMC_LISTEN) {
/* woken up by sk_data_ready in smc_listen_work() */
- mask = smc_accept_poll(sk);
+ mask |= smc_accept_poll(sk);
+ } else if (smc->use_fallback) { /* as result of connect_work()*/
+ mask |= smc->clcsock->ops->poll(file, smc->clcsock,
+ wait);
+ sk->sk_err = smc->clcsock->sk->sk_err;
} else {
- if (atomic_read(&smc->conn.sndbuf_space) ||
+ if ((sk->sk_state != SMC_INIT &&
+ atomic_read(&smc->conn.sndbuf_space)) ||
sk->sk_shutdown & SEND_SHUTDOWN) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else {
@@ -1659,8 +1732,8 @@
case TCP_FASTOPEN_KEY:
case TCP_FASTOPEN_NO_COOKIE:
/* option not supported by SMC */
- if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
if (!smc->use_fallback)
@@ -1668,14 +1741,18 @@
}
break;
case TCP_NODELAY:
- if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+ if (sk->sk_state != SMC_INIT &&
+ sk->sk_state != SMC_LISTEN &&
+ sk->sk_state != SMC_CLOSED) {
if (val && !smc->use_fallback)
mod_delayed_work(system_wq, &smc->conn.tx_work,
0);
}
break;
case TCP_CORK:
- if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+ if (sk->sk_state != SMC_INIT &&
+ sk->sk_state != SMC_LISTEN &&
+ sk->sk_state != SMC_CLOSED) {
if (!val && !smc->use_fallback)
mod_delayed_work(system_wq, &smc->conn.tx_work,
0);
@@ -1824,7 +1901,11 @@
smc = smc_sk(sk);
lock_sock(sk);
-
+ if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) {
+ /* socket was connected before, no more data to read */
+ rc = 0;
+ goto out;
+ }
if (sk->sk_state == SMC_INIT ||
sk->sk_state == SMC_LISTEN ||
sk->sk_state == SMC_CLOSED)
@@ -1923,14 +2004,37 @@
.create = smc_create,
};
+unsigned int smc_net_id;
+
+static __net_init int smc_net_init(struct net *net)
+{
+ return smc_pnet_net_init(net);
+}
+
+static void __net_exit smc_net_exit(struct net *net)
+{
+ smc_pnet_net_exit(net);
+}
+
+static struct pernet_operations smc_net_ops = {
+ .init = smc_net_init,
+ .exit = smc_net_exit,
+ .id = &smc_net_id,
+ .size = sizeof(struct smc_net),
+};
+
static int __init smc_init(void)
{
int rc;
- rc = smc_pnet_init();
+ rc = register_pernet_subsys(&smc_net_ops);
if (rc)
return rc;
+ rc = smc_pnet_init();
+ if (rc)
+ goto out_pernet_subsys;
+
rc = smc_llc_init();
if (rc) {
pr_err("%s: smc_llc_init fails with %d\n", __func__, rc);
@@ -1980,6 +2084,9 @@
proto_unregister(&smc_proto);
out_pnet:
smc_pnet_exit();
+out_pernet_subsys:
+ unregister_pernet_subsys(&smc_net_ops);
+
return rc;
}
@@ -1992,6 +2099,7 @@
proto_unregister(&smc_proto6);
proto_unregister(&smc_proto);
smc_pnet_exit();
+ unregister_pernet_subsys(&smc_net_ops);
}
module_init(smc_init);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 08786ac..878313f 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -113,9 +113,9 @@
} __aligned(8);
enum smc_urg_state {
- SMC_URG_VALID, /* data present */
- SMC_URG_NOTYET, /* data pending */
- SMC_URG_READ /* data was already read */
+ SMC_URG_VALID = 1, /* data present */
+ SMC_URG_NOTYET = 2, /* data pending */
+ SMC_URG_READ = 3, /* data was already read */
};
struct smc_connection {
@@ -190,18 +190,11 @@
u64 peer_token; /* SMC-D token of peer */
};
-struct smc_connect_info {
- int flags;
- int alen;
- struct sockaddr addr;
-};
-
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
- struct smc_connect_info *connect_info; /* connect address & flags */
struct work_struct connect_work; /* handle non-blocking connect*/
struct work_struct tcp_listen_work;/* handle tcp socket accepts */
struct work_struct smc_listen_work;/* prepare new accept socket */
@@ -219,6 +212,14 @@
* started, waiting for unsent
* data to be sent
*/
+ u8 connect_nonblock : 1;
+ /* non-blocking connect in
+ * flight
+ */
+ struct mutex clcsock_release_lock;
+ /* protects clcsock of a listen
+ * socket
+ * */
};
static inline struct smc_sock *smc_sk(const struct sock *sk)
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index ed5dcf0..d0b0f4c 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -21,13 +21,6 @@
/********************************** send *************************************/
-struct smc_cdc_tx_pend {
- struct smc_connection *conn; /* socket connection */
- union smc_host_cursor cursor; /* tx sndbuf cursor sent */
- union smc_host_cursor p_cursor; /* rx RMBE cursor produced */
- u16 ctrl_seq; /* conn. tx sequence # */
-};
-
/* handler for send/transmission completion of a CDC msg */
static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
struct smc_link *link,
@@ -61,12 +54,14 @@
int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_cdc_tx_pend **pend)
{
struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
int rc;
rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
+ wr_rdma_buf,
(struct smc_wr_tx_pend_priv **)pend);
if (!conn->alert_token_local)
/* abnormal termination */
@@ -81,7 +76,7 @@
sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE,
"must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)");
BUILD_BUG_ON_MSG(
- sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE,
+ offsetofend(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE,
"must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()");
BUILD_BUG_ON_MSG(
sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE,
@@ -96,6 +91,7 @@
struct smc_wr_buf *wr_buf,
struct smc_cdc_tx_pend *pend)
{
+ union smc_host_cursor cfed;
struct smc_link *link;
int rc;
@@ -105,12 +101,12 @@
conn->tx_cdc_seq++;
conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
- smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf,
- &conn->local_tx_ctrl, conn);
+ smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed);
rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
- if (!rc)
- smc_curs_copy(&conn->rx_curs_confirmed,
- &conn->local_tx_ctrl.cons, conn);
+ if (!rc) {
+ smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
+ conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
+ }
return rc;
}
@@ -121,11 +117,14 @@
struct smc_wr_buf *wr_buf;
int rc;
- rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend);
if (rc)
return rc;
- return smc_cdc_msg_send(conn, wr_buf, pend);
+ spin_lock_bh(&conn->send_lock);
+ rc = smc_cdc_msg_send(conn, wr_buf, pend);
+ spin_unlock_bh(&conn->send_lock);
+ return rc;
}
int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
@@ -177,23 +176,25 @@
int smcd_cdc_msg_send(struct smc_connection *conn)
{
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+ union smc_host_cursor curs;
struct smcd_cdc_msg cdc;
int rc, diff;
memset(&cdc, 0, sizeof(cdc));
cdc.common.type = SMC_CDC_MSG_TYPE;
- cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap;
- cdc.prod_count = conn->local_tx_ctrl.prod.count;
-
- cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap;
- cdc.cons_count = conn->local_tx_ctrl.cons.count;
- cdc.prod_flags = conn->local_tx_ctrl.prod_flags;
- cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags;
+ curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.prod.acurs);
+ cdc.prod.wrap = curs.wrap;
+ cdc.prod.count = curs.count;
+ curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.cons.acurs);
+ cdc.cons.wrap = curs.wrap;
+ cdc.cons.count = curs.count;
+ cdc.cons.prod_flags = conn->local_tx_ctrl.prod_flags;
+ cdc.cons.conn_state_flags = conn->local_tx_ctrl.conn_state_flags;
rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1);
if (rc)
return rc;
- smc_curs_copy(&conn->rx_curs_confirmed, &conn->local_tx_ctrl.cons,
- conn);
+ smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn);
+ conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
/* Calculate transmitted data and increment free send buffer space */
diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
&conn->tx_curs_sent);
@@ -270,26 +271,18 @@
smp_mb__after_atomic();
smc->sk.sk_data_ready(&smc->sk);
} else {
- if (conn->local_rx_ctrl.prod_flags.write_blocked ||
- conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
- conn->local_rx_ctrl.prod_flags.urg_data_pending) {
- if (conn->local_rx_ctrl.prod_flags.urg_data_pending)
- conn->urg_state = SMC_URG_NOTYET;
- /* force immediate tx of current consumer cursor, but
- * under send_lock to guarantee arrival in seqno-order
- */
- if (smc->sk.sk_state != SMC_INIT)
- smc_tx_sndbuf_nonempty(conn);
- }
+ if (conn->local_rx_ctrl.prod_flags.write_blocked)
+ smc->sk.sk_data_ready(&smc->sk);
+ if (conn->local_rx_ctrl.prod_flags.urg_data_pending)
+ conn->urg_state = SMC_URG_NOTYET;
}
- /* piggy backed tx info */
/* trigger sndbuf consumer: RDMA write into peer RMBE and CDC */
- if (diff_cons && smc_tx_prepared_sends(conn)) {
+ if ((diff_cons && smc_tx_prepared_sends(conn)) ||
+ conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
+ conn->local_rx_ctrl.prod_flags.urg_data_pending)
smc_tx_sndbuf_nonempty(conn);
- /* trigger socket release if connection closed */
- smc_close_wake_tx_prepared(smc);
- }
+
if (diff_cons && conn->urg_tx_pend &&
atomic_read(&conn->peer_rmbe_space) == conn->peer_rmbe_size) {
/* urg data confirmed by peer, indicate we're ready for more */
@@ -331,13 +324,16 @@
static void smcd_cdc_rx_tsklet(unsigned long data)
{
struct smc_connection *conn = (struct smc_connection *)data;
+ struct smcd_cdc_msg *data_cdc;
struct smcd_cdc_msg cdc;
struct smc_sock *smc;
if (!conn)
return;
- memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc));
+ data_cdc = (struct smcd_cdc_msg *)conn->rmb_desc->cpu_addr;
+ smcd_curs_copy(&cdc.prod, &data_cdc->prod, conn);
+ smcd_curs_copy(&cdc.cons, &data_cdc->cons, conn);
smc = container_of(conn, struct smc_sock, conn);
smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc);
}
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 934df44..861dc24 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -48,21 +48,31 @@
struct smc_cdc_producer_flags prod_flags;
struct smc_cdc_conn_state_flags conn_state_flags;
u8 reserved[18];
-} __packed; /* format defined in RFC7609 */
+};
+
+/* SMC-D cursor format */
+union smcd_cdc_cursor {
+ struct {
+ u16 wrap;
+ u32 count;
+ struct smc_cdc_producer_flags prod_flags;
+ struct smc_cdc_conn_state_flags conn_state_flags;
+ } __packed;
+#ifdef KERNEL_HAS_ATOMIC64
+ atomic64_t acurs; /* for atomic processing */
+#else
+ u64 acurs; /* for atomic processing */
+#endif
+} __aligned(8);
/* CDC message for SMC-D */
struct smcd_cdc_msg {
struct smc_wr_rx_hdr common; /* Type = 0xFE */
u8 res1[7];
- u16 prod_wrap;
- u32 prod_count;
- u8 res2[2];
- u16 cons_wrap;
- u32 cons_count;
- struct smc_cdc_producer_flags prod_flags;
- struct smc_cdc_conn_state_flags conn_state_flags;
+ union smcd_cdc_cursor prod;
+ union smcd_cdc_cursor cons;
u8 res3[8];
-} __packed;
+} __aligned(8);
static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn)
{
@@ -135,7 +145,24 @@
#endif
}
-/* calculate cursor difference between old and new, where old <= new */
+static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt,
+ union smcd_cdc_cursor *src,
+ struct smc_connection *conn)
+{
+#ifndef KERNEL_HAS_ATOMIC64
+ unsigned long flags;
+
+ spin_lock_irqsave(&conn->acurs_lock, flags);
+ tgt->acurs = src->acurs;
+ spin_unlock_irqrestore(&conn->acurs_lock, flags);
+#else
+ atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
+#endif
+}
+
+/* calculate cursor difference between old and new, where old <= new and
+ * difference cannot exceed size
+ */
static inline int smc_curs_diff(unsigned int size,
union smc_host_cursor *old,
union smc_host_cursor *new)
@@ -160,28 +187,51 @@
return smc_curs_diff(size, old, new);
}
+/* calculate cursor difference between old and new, where old <= new and
+ * difference may exceed size
+ */
+static inline int smc_curs_diff_large(unsigned int size,
+ union smc_host_cursor *old,
+ union smc_host_cursor *new)
+{
+ if (old->wrap < new->wrap)
+ return min_t(int,
+ (size - old->count) + new->count +
+ (new->wrap - old->wrap - 1) * size,
+ size);
+
+ if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */
+ return min_t(int,
+ (size - old->count) + new->count +
+ (new->wrap + 0xffff - old->wrap) * size,
+ size);
+
+ return max_t(int, 0, (new->count - old->count));
+}
+
static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
union smc_host_cursor *local,
+ union smc_host_cursor *save,
struct smc_connection *conn)
{
- union smc_host_cursor temp;
-
- smc_curs_copy(&temp, local, conn);
- peer->count = htonl(temp.count);
- peer->wrap = htons(temp.wrap);
+ smc_curs_copy(save, local, conn);
+ peer->count = htonl(save->count);
+ peer->wrap = htons(save->wrap);
/* peer->reserved = htons(0); must be ensured by caller */
}
static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer,
- struct smc_host_cdc_msg *local,
- struct smc_connection *conn)
+ struct smc_connection *conn,
+ union smc_host_cursor *save)
{
+ struct smc_host_cdc_msg *local = &conn->local_tx_ctrl;
+
peer->common.type = local->common.type;
peer->len = local->len;
peer->seqno = htons(local->seqno);
peer->token = htonl(local->token);
- smc_host_cursor_to_cdc(&peer->prod, &local->prod, conn);
- smc_host_cursor_to_cdc(&peer->cons, &local->cons, conn);
+ smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn);
+ smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn);
peer->prod_flags = local->prod_flags;
peer->conn_state_flags = local->conn_state_flags;
}
@@ -220,14 +270,20 @@
}
static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local,
- struct smcd_cdc_msg *peer)
+ struct smcd_cdc_msg *peer,
+ struct smc_connection *conn)
{
- local->prod.wrap = peer->prod_wrap;
- local->prod.count = peer->prod_count;
- local->cons.wrap = peer->cons_wrap;
- local->cons.count = peer->cons_count;
- local->prod_flags = peer->prod_flags;
- local->conn_state_flags = peer->conn_state_flags;
+ union smc_host_cursor temp;
+
+ temp.wrap = peer->prod.wrap;
+ temp.count = peer->prod.count;
+ smc_curs_copy(&local->prod, &temp, conn);
+
+ temp.wrap = peer->cons.wrap;
+ temp.count = peer->cons.count;
+ smc_curs_copy(&local->cons, &temp, conn);
+ local->prod_flags = peer->cons.prod_flags;
+ local->conn_state_flags = peer->cons.conn_state_flags;
}
static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
@@ -235,15 +291,21 @@
struct smc_connection *conn)
{
if (conn->lgr->is_smcd)
- smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer);
+ smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer, conn);
else
smcr_cdc_msg_to_host(local, peer, conn);
}
-struct smc_cdc_tx_pend;
+struct smc_cdc_tx_pend {
+ struct smc_connection *conn; /* socket connection */
+ union smc_host_cursor cursor; /* tx sndbuf cursor sent */
+ union smc_host_cursor p_cursor; /* rx RMBE cursor produced */
+ u16 ctrl_seq; /* conn. tx sequence # */
+};
int smc_cdc_get_free_slot(struct smc_connection *conn,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_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 52241d6..49bcebf 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -97,17 +97,19 @@
struct smc_clc_msg_proposal_prefix *prop)
{
struct in_device *in_dev = __in_dev_get_rcu(dst->dev);
+ const struct in_ifaddr *ifa;
if (!in_dev)
return -ENODEV;
- for_ifa(in_dev) {
+
+ in_dev_for_each_ifa_rcu(ifa, in_dev) {
if (!inet_ifa_match(ipv4, ifa))
continue;
prop->prefix_len = inet_mask_len(ifa->ifa_mask);
prop->outgoing_subnet = ifa->ifa_address & ifa->ifa_mask;
/* prop->ipv6_prefixes_cnt = 0; already done by memset before */
return 0;
- } endfor_ifa(in_dev);
+ }
return -ENOENT;
}
@@ -190,14 +192,15 @@
struct smc_clc_msg_proposal_prefix *prop)
{
struct in_device *in_dev = __in_dev_get_rcu(dev);
+ const struct in_ifaddr *ifa;
if (!in_dev)
return -ENODEV;
- for_ifa(in_dev) {
+ in_dev_for_each_ifa_rcu(ifa, in_dev) {
if (prop->prefix_len == inet_mask_len(ifa->ifa_mask) &&
inet_ifa_match(prop->outgoing_subnet, ifa))
return 0;
- } endfor_ifa(in_dev);
+ }
return -ENOENT;
}
@@ -265,7 +268,7 @@
* clcsock error, -EINTR, -ECONNRESET, -EPROTO otherwise.
*/
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
- u8 expected_type)
+ u8 expected_type, unsigned long timeout)
{
long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
struct sock *clc_sk = smc->clcsock->sk;
@@ -285,8 +288,8 @@
* sizeof(struct smc_clc_msg_hdr)
*/
krflags = MSG_PEEK | MSG_WAITALL;
- smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1,
+ clc_sk->sk_rcvtimeo = timeout;
+ iov_iter_kvec(&msg.msg_iter, READ, &vec, 1,
sizeof(struct smc_clc_msg_hdr));
len = sock_recvmsg(smc->clcsock, &msg, krflags);
if (signal_pending(current)) {
@@ -297,7 +300,11 @@
}
if (clc_sk->sk_err) {
reason_code = -clc_sk->sk_err;
- smc->sk.sk_err = clc_sk->sk_err;
+ if (clc_sk->sk_err == EAGAIN &&
+ expected_type == SMC_CLC_DECLINE)
+ clc_sk->sk_err = 0; /* reset for fallback usage */
+ else
+ smc->sk.sk_err = clc_sk->sk_err;
goto out;
}
if (!len) { /* peer has performed orderly shutdown */
@@ -306,7 +313,8 @@
goto out;
}
if (len < 0) {
- smc->sk.sk_err = -len;
+ if (len != -EAGAIN || expected_type != SMC_CLC_DECLINE)
+ smc->sk.sk_err = -len;
reason_code = len;
goto out;
}
@@ -325,7 +333,7 @@
/* receive the complete CLC message */
memset(&msg, 0, sizeof(struct msghdr));
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
+ iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen);
krflags = MSG_WAITALL;
len = sock_recvmsg(smc->clcsock, &msg, krflags);
if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
@@ -346,7 +354,7 @@
}
out:
- smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
+ clc_sk->sk_rcvtimeo = rcvtimeo;
return reason_code;
}
@@ -373,17 +381,14 @@
vec.iov_len = sizeof(struct smc_clc_msg_decline);
len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
sizeof(struct smc_clc_msg_decline));
- if (len < sizeof(struct smc_clc_msg_decline))
- smc->sk.sk_err = EPROTO;
- if (len < 0)
- smc->sk.sk_err = -len;
- return sock_error(&smc->sk);
+ if (len < 0 || len < sizeof(struct smc_clc_msg_decline))
+ len = -EPROTO;
+ return len > 0 ? 0 : len;
}
/* 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, u8 gid[],
- struct smcd_dev *ismdev)
+ struct smc_init_info *ini)
{
struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
struct smc_clc_msg_proposal_prefix pclc_prfx;
@@ -413,8 +418,9 @@
/* add SMC-R specifics */
memcpy(pclc.lcl.id_for_peer, local_systemid,
sizeof(local_systemid));
- memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE);
- memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
+ memcpy(&pclc.lcl.gid, ini->ib_gid, SMC_GID_SIZE);
+ memcpy(&pclc.lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1],
+ ETH_ALEN);
pclc.iparea_offset = htons(0);
}
if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
@@ -422,7 +428,7 @@
memset(&pclc_smcd, 0, sizeof(pclc_smcd));
plen += sizeof(pclc_smcd);
pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET);
- pclc_smcd.gid = ismdev->local_gid;
+ pclc_smcd.gid = ini->ism_dev->local_gid;
}
pclc.hdr.length = htons(plen);
@@ -536,7 +542,6 @@
struct smc_link *link;
struct msghdr msg;
struct kvec vec;
- int rc = 0;
int len;
memset(&aclc, 0, sizeof(aclc));
@@ -589,13 +594,8 @@
vec.iov_len = ntohs(aclc.hdr.length);
len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1,
ntohs(aclc.hdr.length));
- if (len < ntohs(aclc.hdr.length)) {
- if (len >= 0)
- new_smc->sk.sk_err = EPROTO;
- else
- new_smc->sk.sk_err = new_smc->clcsock->sk->sk_err;
- rc = sock_error(&new_smc->sk);
- }
+ if (len < ntohs(aclc.hdr.length))
+ len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
- return rc;
+ return len > 0 ? 0 : len;
}
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 18da89b..ca20927 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -27,22 +27,29 @@
#define SMC_TYPE_D 1 /* SMC-D only */
#define SMC_TYPE_B 3 /* SMC-R and SMC-D */
#define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */
+#define CLC_WAIT_TIME_SHORT HZ /* short wait time on clcsock */
#define SMC_CLC_DECL_MEM 0x01010000 /* insufficient memory resources */
#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_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_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */
+#define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */
+#define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */
+#define SMC_CLC_DECL_SMCDNOTALK 0x03030003 /* SMC-D dev can't talk to peer */
#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_DIFFPREFIX 0x03070000 /* IP prefix / subnet mismatch */
+#define SMC_CLC_DECL_GETVLANERR 0x03080000 /* err to get vlan id of ip device*/
+#define SMC_CLC_DECL_ISMVLANERR 0x03090000 /* err to reg vlan id on ism dev */
#define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */
#define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */
-#define SMC_CLC_DECL_INTERR 0x99990000 /* internal error */
-#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 */
+#define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */
+#define SMC_CLC_DECL_ERR_RTOK 0x09990001 /* rtoken handling failed */
+#define SMC_CLC_DECL_ERR_RDYLNK 0x09990002 /* ib ready link failed */
+#define SMC_CLC_DECL_ERR_REGRMB 0x09990003 /* reg rmb failed */
struct smc_clc_msg_hdr { /* header1 of clc messages */
u8 eyecatcher[4]; /* eye catcher */
@@ -178,15 +185,15 @@
}
struct smcd_dev;
+struct smc_init_info;
int smc_clc_prfx_match(struct socket *clcsock,
struct smc_clc_msg_proposal_prefix *prop);
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
- u8 expected_type);
+ u8 expected_type, unsigned long timeout);
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, u8 gid[],
- struct smcd_dev *ismdev);
+ struct smc_init_info *ini);
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 ea2b87f..fc06720 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -21,6 +21,22 @@
#define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ)
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+ struct socket *tcp;
+
+ if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+ cancel_work_sync(&smc->smc_listen_work);
+ mutex_lock(&smc->clcsock_release_lock);
+ if (smc->clcsock) {
+ tcp = smc->clcsock;
+ smc->clcsock = NULL;
+ sock_release(tcp);
+ }
+ mutex_unlock(&smc->clcsock_release_lock);
+}
+
static void smc_close_cleanup_listen(struct sock *parent)
{
struct sock *sk;
@@ -321,6 +337,7 @@
close_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
struct smc_cdc_conn_state_flags *rxflags;
+ bool release_clcsock = false;
struct sock *sk = &smc->sk;
int old_state;
@@ -345,14 +362,7 @@
switch (sk->sk_state) {
case SMC_INIT:
- if (atomic_read(&conn->bytes_to_rcv) ||
- (rxflags->peer_done_writing &&
- !smc_cdc_rxed_any_close(conn))) {
- sk->sk_state = SMC_APPCLOSEWAIT1;
- } else {
- sk->sk_state = SMC_CLOSED;
- sock_put(sk); /* passive closing */
- }
+ sk->sk_state = SMC_APPCLOSEWAIT1;
break;
case SMC_ACTIVE:
sk->sk_state = SMC_APPCLOSEWAIT1;
@@ -405,10 +415,15 @@
if (old_state != sk->sk_state) {
sk->sk_state_change(sk);
if ((sk->sk_state == SMC_CLOSED) &&
- (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket))
+ (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
smc_conn_free(conn);
+ if (smc->clcsock)
+ release_clcsock = true;
+ }
}
release_sock(sk);
+ if (release_clcsock)
+ smc_clcsock_release(smc);
sock_put(sk); /* sock_hold done by schedulers of close_work */
}
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index 19eb6a2..e0e3b5d 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -23,5 +23,6 @@
int smc_close_active(struct smc_sock *smc);
int smc_close_shutdown_write(struct smc_sock *smc);
void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
#endif /* SMC_CLOSE_H */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 18daebc..2ba97ff 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -118,7 +118,6 @@
rb_erase(&conn->alert_node, &lgr->conns_all);
lgr->conns_num--;
conn->alert_token_local = 0;
- conn->lgr = NULL;
sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
}
@@ -128,6 +127,8 @@
{
struct smc_link_group *lgr = conn->lgr;
+ if (!lgr)
+ return;
write_lock_bh(&lgr->conns_lock);
if (conn->alert_token_local) {
__smc_lgr_unregister_conn(conn);
@@ -149,6 +150,8 @@
return -ENOTCONN;
}
+static void smc_lgr_free(struct smc_link_group *lgr);
+
static void smc_lgr_free_work(struct work_struct *work)
{
struct smc_link_group *lgr = container_of(to_delayed_work(work),
@@ -157,8 +160,6 @@
bool conns;
spin_lock_bh(&smc_lgr_list.lock);
- if (list_empty(&lgr->list))
- goto free;
read_lock_bh(&lgr->conns_lock);
conns = RB_EMPTY_ROOT(&lgr->conns_all);
read_unlock_bh(&lgr->conns_lock);
@@ -166,13 +167,16 @@
spin_unlock_bh(&smc_lgr_list.lock);
return;
}
- list_del_init(&lgr->list); /* remove from smc_lgr_list */
-free:
+ if (!list_empty(&lgr->list))
+ list_del_init(&lgr->list); /* remove from smc_lgr_list */
spin_unlock_bh(&smc_lgr_list.lock);
if (!lgr->is_smcd && !lgr->terminating) {
+ struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
/* try to send del link msg, on error free lgr immediately */
- if (!smc_link_send_delete(&lgr->lnk[SMC_SINGLE_LINK])) {
+ if (lnk->state == SMC_LNK_ACTIVE &&
+ !smc_link_send_delete(lnk)) {
/* reschedule in case we never receive a response */
smc_lgr_schedule_free_work(lgr);
return;
@@ -184,15 +188,14 @@
if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE)
smc_llc_link_inactive(lnk);
+ if (lgr->is_smcd)
+ smc_ism_signal_shutdown(lgr);
smc_lgr_free(lgr);
}
}
/* create a new SMC link group */
-static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
- struct smc_ib_device *smcibdev, u8 ibport,
- char *peer_systemid, unsigned short vlan_id,
- struct smcd_dev *smcismdev, u64 peer_gid)
+static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
{
struct smc_link_group *lgr;
struct smc_link *lnk;
@@ -200,20 +203,21 @@
int rc = 0;
int i;
- if (is_smcd && vlan_id) {
- rc = smc_ism_get_vlan(smcismdev, vlan_id);
- if (rc)
+ if (ini->is_smcd && ini->vlan_id) {
+ if (smc_ism_get_vlan(ini->ism_dev, ini->vlan_id)) {
+ rc = SMC_CLC_DECL_ISMVLANERR;
goto out;
+ }
}
lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
if (!lgr) {
- rc = -ENOMEM;
- goto out;
+ rc = SMC_CLC_DECL_MEM;
+ goto ism_put_vlan;
}
- lgr->is_smcd = is_smcd;
+ lgr->is_smcd = ini->is_smcd;
lgr->sync_err = 0;
- lgr->vlan_id = vlan_id;
+ lgr->vlan_id = ini->vlan_id;
rwlock_init(&lgr->sndbufs_lock);
rwlock_init(&lgr->rmbs_lock);
rwlock_init(&lgr->conns_lock);
@@ -225,29 +229,32 @@
memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE);
INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
lgr->conns_all = RB_ROOT;
- if (is_smcd) {
+ if (ini->is_smcd) {
/* SMC-D specific settings */
- lgr->peer_gid = peer_gid;
- lgr->smcd = smcismdev;
+ lgr->peer_gid = ini->ism_gid;
+ lgr->smcd = ini->ism_dev;
} else {
/* SMC-R specific settings */
lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
+ memcpy(lgr->peer_systemid, ini->ib_lcl->id_for_peer,
+ SMC_SYSTEMID_LEN);
lnk = &lgr->lnk[SMC_SINGLE_LINK];
/* initialize link */
lnk->state = SMC_LNK_ACTIVATING;
lnk->link_id = SMC_SINGLE_LINK;
- lnk->smcibdev = smcibdev;
- lnk->ibport = ibport;
- lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
- if (!smcibdev->initialized)
- smc_ib_setup_per_ibdev(smcibdev);
+ lnk->smcibdev = ini->ib_dev;
+ lnk->ibport = ini->ib_port;
+ lnk->path_mtu =
+ ini->ib_dev->pattr[ini->ib_port - 1].active_mtu;
+ if (!ini->ib_dev->initialized)
+ smc_ib_setup_per_ibdev(ini->ib_dev);
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);
+ ini->vlan_id, lnk->gid,
+ &lnk->sgid_index);
if (rc)
goto free_lgr;
rc = smc_llc_link_init(lnk);
@@ -282,7 +289,16 @@
smc_llc_link_clear(lnk);
free_lgr:
kfree(lgr);
+ism_put_vlan:
+ if (ini->is_smcd && ini->vlan_id)
+ smc_ism_put_vlan(ini->ism_dev, ini->vlan_id);
out:
+ if (rc < 0) {
+ if (rc == -ENOMEM)
+ rc = SMC_CLC_DECL_MEM;
+ else
+ rc = SMC_CLC_DECL_INTERR;
+ }
return rc;
}
@@ -293,7 +309,12 @@
conn->sndbuf_desc->used = 0;
if (conn->rmb_desc) {
if (!conn->rmb_desc->regerr) {
- conn->rmb_desc->reused = 1;
+ if (!lgr->is_smcd) {
+ /* unregister rmb with peer */
+ smc_llc_do_delete_rkey(
+ &lgr->lnk[SMC_SINGLE_LINK],
+ conn->rmb_desc);
+ }
conn->rmb_desc->used = 0;
} else {
/* buf registration failed, reuse not possible */
@@ -319,8 +340,9 @@
} else {
smc_cdc_tx_dismiss_slots(conn);
}
- smc_lgr_unregister_conn(conn); /* unsets conn->lgr */
+ smc_lgr_unregister_conn(conn);
smc_buf_unuse(conn, lgr); /* allow buffer reuse */
+ conn->lgr = NULL;
if (!lgr->conns_num)
smc_lgr_schedule_free_work(lgr);
@@ -408,7 +430,7 @@
}
/* remove a link group */
-void smc_lgr_free(struct smc_link_group *lgr)
+static void smc_lgr_free(struct smc_link_group *lgr)
{
smc_lgr_free_bufs(lgr);
if (lgr->is_smcd)
@@ -450,6 +472,7 @@
sock_hold(&smc->sk); /* sock_put in close work */
conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
__smc_lgr_unregister_conn(conn);
+ conn->lgr = NULL;
write_unlock_bh(&lgr->conns_lock);
if (!schedule_work(&conn->close_work))
sock_put(&smc->sk);
@@ -485,7 +508,7 @@
}
/* Called when SMC-D device is terminated or peer is lost */
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
{
struct smc_link_group *lgr, *l;
LIST_HEAD(lgr_free_list);
@@ -495,7 +518,7 @@
list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
if (lgr->is_smcd && lgr->smcd == dev &&
(!peer_gid || lgr->peer_gid == peer_gid) &&
- !list_empty(&lgr->list)) {
+ (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) {
__smc_lgr_terminate(lgr);
list_move(&lgr->list, &lgr_free_list);
}
@@ -506,6 +529,8 @@
list_for_each_entry_safe(lgr, l, &lgr_free_list, list) {
list_del_init(&lgr->list);
cancel_delayed_work_sync(&lgr->free_work);
+ if (!peer_gid && vlan == VLAN_VID_MASK) /* dev terminated? */
+ smc_ism_signal_shutdown(lgr);
smc_lgr_free(lgr);
}
}
@@ -513,13 +538,13 @@
/* Determine vlan of internal TCP socket.
* @vlan_id: address to store the determined vlan id into
*/
-int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
+int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
struct net_device *ndev;
int i, nest_lvl, rc = 0;
- *vlan_id = 0;
+ ini->vlan_id = 0;
if (!dst) {
rc = -ENOTCONN;
goto out;
@@ -531,12 +556,12 @@
ndev = dst->dev;
if (is_vlan_dev(ndev)) {
- *vlan_id = vlan_dev_vlan_id(ndev);
+ ini->vlan_id = vlan_dev_vlan_id(ndev);
goto out_rel;
}
rtnl_lock();
- nest_lvl = dev_get_nest_level(ndev);
+ nest_lvl = ndev->lower_level;
for (i = 0; i < nest_lvl; i++) {
struct list_head *lower = &ndev->adj_list.lower;
@@ -545,7 +570,7 @@
lower = lower->next;
ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower);
if (is_vlan_dev(ndev)) {
- *vlan_id = vlan_dev_vlan_id(ndev);
+ ini->vlan_id = vlan_dev_vlan_id(ndev);
break;
}
}
@@ -559,7 +584,7 @@
static bool smcr_lgr_match(struct smc_link_group *lgr,
struct smc_clc_msg_local *lcl,
- enum smc_lgr_role role)
+ enum smc_lgr_role role, u32 clcqpn)
{
return !memcmp(lgr->peer_systemid, lcl->id_for_peer,
SMC_SYSTEMID_LEN) &&
@@ -567,7 +592,9 @@
SMC_GID_SIZE) &&
!memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
sizeof(lcl->mac)) &&
- lgr->role == role;
+ lgr->role == role &&
+ (lgr->role == SMC_SERV ||
+ lgr->lnk[SMC_SINGLE_LINK].peer_qpn == clcqpn);
}
static bool smcd_lgr_match(struct smc_link_group *lgr,
@@ -577,24 +604,16 @@
}
/* create a new SMC connection (and a new link group if necessary) */
-int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
- struct smc_ib_device *smcibdev, u8 ibport,
- struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
- u64 peer_gid)
+int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
{
struct smc_connection *conn = &smc->conn;
- int local_contact = SMC_FIRST_CONTACT;
struct smc_link_group *lgr;
- unsigned short vlan_id;
enum smc_lgr_role role;
int rc = 0;
+ ini->cln_first_contact = SMC_FIRST_CONTACT;
role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- rc = smc_vlan_by_tcpsk(smc->clcsock, &vlan_id);
- if (rc)
- return rc;
-
- if ((role == SMC_CLNT) && srv_first_contact)
+ if (role == SMC_CLNT && ini->srv_first_contact)
/* create new link group as well */
goto create;
@@ -602,16 +621,19 @@
spin_lock_bh(&smc_lgr_list.lock);
list_for_each_entry(lgr, &smc_lgr_list.list, list) {
write_lock_bh(&lgr->conns_lock);
- if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
- smcr_lgr_match(lgr, lcl, role)) &&
+ if ((ini->is_smcd ?
+ smcd_lgr_match(lgr, ini->ism_dev, ini->ism_gid) :
+ smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) &&
!lgr->sync_err &&
- lgr->vlan_id == vlan_id &&
+ lgr->vlan_id == ini->vlan_id &&
(role == SMC_CLNT ||
lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
/* link group found */
- local_contact = SMC_REUSE_CONTACT;
+ ini->cln_first_contact = SMC_REUSE_CONTACT;
conn->lgr = lgr;
smc_lgr_register_conn(conn); /* add smc conn to lgr */
+ if (delayed_work_pending(&lgr->free_work))
+ cancel_delayed_work(&lgr->free_work);
write_unlock_bh(&lgr->conns_lock);
break;
}
@@ -619,27 +641,29 @@
}
spin_unlock_bh(&smc_lgr_list.lock);
- if (role == SMC_CLNT && !srv_first_contact &&
- (local_contact == SMC_FIRST_CONTACT)) {
+ if (role == SMC_CLNT && !ini->srv_first_contact &&
+ ini->cln_first_contact == SMC_FIRST_CONTACT) {
/* Server reuses a link group, but Client wants to start
* a new one
* send out_of_sync decline, reason synchr. error
*/
- return -ENOLINK;
+ return SMC_CLC_DECL_SYNCERR;
}
create:
- if (local_contact == SMC_FIRST_CONTACT) {
- rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport,
- lcl->id_for_peer, vlan_id, smcd, peer_gid);
+ if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
+ rc = smc_lgr_create(smc, ini);
if (rc)
goto out;
+ lgr = conn->lgr;
+ write_lock_bh(&lgr->conns_lock);
smc_lgr_register_conn(conn); /* add smc conn to lgr */
+ write_unlock_bh(&lgr->conns_lock);
}
conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
conn->urg_state = SMC_URG_READ;
- if (is_smcd) {
+ if (ini->is_smcd) {
conn->rx_off = sizeof(struct smcd_cdc_msg);
smcd_cdc_rx_init(conn); /* init tasklet for this conn */
}
@@ -648,7 +672,7 @@
#endif
out:
- return rc ? rc : local_contact;
+ return rc;
}
/* convert the RMB size into the compressed notation - minimum 16K.
@@ -1024,6 +1048,8 @@
smc_llc_link_inactive(lnk);
}
cancel_delayed_work_sync(&lgr->free_work);
+ if (lgr->is_smcd)
+ smc_ism_signal_shutdown(lgr);
smc_lgr_free(lgr); /* free link group */
}
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index c156674..c00ac61 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -52,6 +52,24 @@
FAILED /* ib_wr_reg_mr response: failure */
};
+struct smc_rdma_sge { /* sges for RDMA writes */
+ struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE];
+};
+
+#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per
+ * message send
+ */
+
+struct smc_rdma_sges { /* sges per message send */
+ struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES];
+};
+
+struct smc_rdma_wr { /* work requests per message
+ * send
+ */
+ struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES];
+};
+
struct smc_link {
struct smc_ib_device *smcibdev; /* ib-device */
u8 ibport; /* port - values 1 | 2 */
@@ -64,6 +82,8 @@
struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */
struct ib_send_wr *wr_tx_ibs; /* WR send meta data */
struct ib_sge *wr_tx_sges; /* WR send gather meta data */
+ struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/
+ struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */
struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */
/* above four vectors have wr_tx_cnt elements and use the same index */
dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */
@@ -109,6 +129,9 @@
int llc_testlink_time; /* testlink interval */
struct completion llc_confirm_rkey; /* wait 4 rx of cnf rkey */
int llc_confirm_rkey_rc; /* rc from cnf rkey msg */
+ struct completion llc_delete_rkey; /* wait 4 rx of del rkey */
+ int llc_delete_rkey_rc; /* rc from del rkey msg */
+ struct mutex llc_delete_rkey_mutex; /* serialize usage */
};
/* For now we just allow one parallel link per link group. The SMC protocol
@@ -127,7 +150,7 @@
struct page *pages;
int len; /* length of buffer */
u32 used; /* currently used / unused */
- u8 reused : 1; /* new created / reused */
+ u8 wr_reg : 1; /* mem region registered */
u8 regerr : 1; /* err during registration */
union {
struct { /* SMC-R */
@@ -206,6 +229,24 @@
};
};
+struct smc_clc_msg_local;
+
+struct smc_init_info {
+ u8 is_smcd;
+ unsigned short vlan_id;
+ int srv_first_contact;
+ int cln_first_contact;
+ /* SMC-R */
+ struct smc_clc_msg_local *ib_lcl;
+ struct smc_ib_device *ib_dev;
+ u8 ib_gid[SMC_GID_SIZE];
+ u8 ib_port;
+ u32 ib_clcqpn;
+ /* SMC-D */
+ u64 ism_gid;
+ struct smcd_dev *ism_dev;
+};
+
/* Find the connection associated with the given alert token in the link group.
* To use rbtrees we have to implement our own search core.
* Requires @conns_lock
@@ -243,11 +284,11 @@
struct smc_clc_msg_accept_confirm;
struct smc_clc_msg_local;
-void smc_lgr_free(struct smc_link_group *lgr);
void smc_lgr_forget(struct smc_link_group *lgr);
void smc_lgr_terminate(struct smc_link_group *lgr);
void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid);
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
+ unsigned short vlan);
int smc_buf_create(struct smc_sock *smc, bool is_smcd);
int smc_uncompress_bufsize(u8 compressed);
int smc_rmb_rtoken_handling(struct smc_connection *conn,
@@ -258,13 +299,10 @@
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);
-int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id);
+int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini);
void smc_conn_free(struct smc_connection *conn);
-int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
- struct smc_ib_device *smcibdev, u8 ibport,
- struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
- u64 peer_gid);
+int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini);
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);
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index dbf64a9..f38727e 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Shared Memory Communications over RDMA (SMC-R) and RoCE
*
@@ -38,6 +39,7 @@
{
struct smc_sock *smc = smc_sk(sk);
+ r->diag_family = sk->sk_family;
if (!smc->clcsock)
return;
r->id.idiag_sport = htons(smc->clcsock->sk->sk_num);
@@ -45,14 +47,12 @@
r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
sock_diag_save_cookie(sk, r->id.idiag_cookie);
if (sk->sk_protocol == SMCPROTO_SMC) {
- r->diag_family = PF_INET;
memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
#if IS_ENABLED(CONFIG_IPV6)
} else if (sk->sk_protocol == SMCPROTO_SMC6) {
- r->diag_family = PF_INET6;
memcpy(&r->id.idiag_src, &smc->clcsock->sk->sk_v6_rcv_saddr,
sizeof(smc->clcsock->sk->sk_v6_rcv_saddr));
memcpy(&r->id.idiag_dst, &smc->clcsock->sk->sk_v6_daddr,
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index e519ef2..d14ca4a 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -146,18 +146,13 @@
static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
{
const struct ib_gid_attr *attr;
- int rc = 0;
+ int rc;
attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0);
if (IS_ERR(attr))
return -ENODEV;
- if (attr->ndev)
- memcpy(smcibdev->mac[ibport - 1], attr->ndev->dev_addr,
- ETH_ALEN);
- else
- rc = -ENODEV;
-
+ rc = rdma_read_gid_l2_fields(attr, NULL, smcibdev->mac[ibport - 1]);
rdma_put_gid_attr(attr);
return rc;
}
@@ -185,6 +180,7 @@
unsigned short vlan_id, u8 gid[], u8 *sgid_index)
{
const struct ib_gid_attr *attr;
+ const struct net_device *ndev;
int i;
for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
@@ -192,11 +188,14 @@
if (IS_ERR(attr))
continue;
- if (attr->ndev &&
+ rcu_read_lock();
+ ndev = rdma_read_gid_attr_ndev_rcu(attr);
+ if (!IS_ERR(ndev) &&
((!vlan_id && !is_vlan_dev(attr->ndev)) ||
(vlan_id && is_vlan_dev(attr->ndev) &&
vlan_dev_vlan_id(attr->ndev) == vlan_id)) &&
attr->gid_type == IB_GID_TYPE_ROCE) {
+ rcu_read_unlock();
if (gid)
memcpy(gid, &attr->gid, SMC_GID_SIZE);
if (sgid_index)
@@ -204,6 +203,7 @@
rdma_put_gid_attr(attr);
return 0;
}
+ rcu_read_unlock();
rdma_put_gid_attr(attr);
}
return -ENODEV;
@@ -257,13 +257,21 @@
smcibdev = container_of(handler, struct smc_ib_device, event_handler);
switch (ibevent->event) {
- case IB_EVENT_PORT_ERR:
case IB_EVENT_DEVICE_FATAL:
- case IB_EVENT_PORT_ACTIVE:
- port_idx = ibevent->element.port_num - 1;
- set_bit(port_idx, &smcibdev->port_event_mask);
+ /* terminate all ports on device */
+ for (port_idx = 0; port_idx < SMC_MAX_PORTS; port_idx++)
+ set_bit(port_idx, &smcibdev->port_event_mask);
schedule_work(&smcibdev->port_event_work);
break;
+ case IB_EVENT_PORT_ERR:
+ case IB_EVENT_PORT_ACTIVE:
+ case IB_EVENT_GID_CHANGE:
+ port_idx = ibevent->element.port_num - 1;
+ if (port_idx < SMC_MAX_PORTS) {
+ set_bit(port_idx, &smcibdev->port_event_mask);
+ schedule_work(&smcibdev->port_event_work);
+ }
+ break;
default:
break;
}
@@ -289,18 +297,18 @@
static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
{
- struct smc_ib_device *smcibdev =
- (struct smc_ib_device *)ibevent->device;
+ struct smc_link *lnk = (struct smc_link *)priv;
+ struct smc_ib_device *smcibdev = lnk->smcibdev;
u8 port_idx;
switch (ibevent->event) {
- case IB_EVENT_DEVICE_FATAL:
- case IB_EVENT_GID_CHANGE:
- case IB_EVENT_PORT_ERR:
+ case IB_EVENT_QP_FATAL:
case IB_EVENT_QP_ACCESS_ERR:
- port_idx = ibevent->element.port_num - 1;
- set_bit(port_idx, &smcibdev->port_event_mask);
- schedule_work(&smcibdev->port_event_work);
+ port_idx = ibevent->element.qp->port - 1;
+ if (port_idx < SMC_MAX_PORTS) {
+ set_bit(port_idx, &smcibdev->port_event_mask);
+ schedule_work(&smcibdev->port_event_work);
+ }
break;
default:
break;
@@ -556,7 +564,6 @@
spin_lock(&smc_ib_devices.lock);
list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
spin_unlock(&smc_ib_devices.lock);
- smc_pnet_remove_by_ibdev(smcibdev);
smc_ib_cleanup_per_ibdev(smcibdev);
ib_unregister_event_handler(&smcibdev->event_handler);
kfree(smcibdev);
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index bac7fd6..da60ab9 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -42,6 +42,8 @@
/* mac address per port*/
u8 pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
/* pnetid per port */
+ bool pnetid_by_user[SMC_MAX_PORTS];
+ /* pnetid defined by user? */
u8 initialized : 1; /* ib dev CQ, evthdl done */
struct work_struct port_event_work;
unsigned long port_event_mask;
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index e36f21c..e89e918 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -187,22 +187,28 @@
#define ISM_EVENT_REQUEST 0x0001
#define ISM_EVENT_RESPONSE 0x0002
#define ISM_EVENT_REQUEST_IR 0x00000001
+#define ISM_EVENT_CODE_SHUTDOWN 0x80
#define ISM_EVENT_CODE_TESTLINK 0x83
+union smcd_sw_event_info {
+ u64 info;
+ struct {
+ u8 uid[SMC_LGR_ID_SIZE];
+ unsigned short vlan_id;
+ u16 code;
+ };
+};
+
static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
{
- union {
- u64 info;
- struct {
- u32 uid;
- unsigned short vlanid;
- u16 code;
- };
- } ev_info;
+ union smcd_sw_event_info ev_info;
+ ev_info.info = wrk->event.info;
switch (wrk->event.code) {
+ case ISM_EVENT_CODE_SHUTDOWN: /* Peer shut down DMBs */
+ smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id);
+ break;
case ISM_EVENT_CODE_TESTLINK: /* Activity timer */
- ev_info.info = wrk->event.info;
if (ev_info.code == ISM_EVENT_REQUEST) {
ev_info.code = ISM_EVENT_RESPONSE;
wrk->smcd->ops->signal_event(wrk->smcd,
@@ -215,6 +221,21 @@
}
}
+int smc_ism_signal_shutdown(struct smc_link_group *lgr)
+{
+ int rc;
+ union smcd_sw_event_info ev_info;
+
+ memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE);
+ ev_info.vlan_id = lgr->vlan_id;
+ ev_info.code = ISM_EVENT_REQUEST;
+ rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid,
+ ISM_EVENT_REQUEST_IR,
+ ISM_EVENT_CODE_SHUTDOWN,
+ ev_info.info);
+ return rc;
+}
+
/* worker for SMC-D events */
static void smc_ism_event_work(struct work_struct *work)
{
@@ -223,7 +244,7 @@
switch (wrk->event.type) {
case ISM_EVENT_GID: /* GID event, token is peer GID */
- smc_smcd_terminate(wrk->smcd, wrk->event.tok);
+ smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK);
break;
case ISM_EVENT_DMB:
break;
@@ -268,6 +289,11 @@
INIT_LIST_HEAD(&smcd->vlan);
smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
WQ_MEM_RECLAIM, name);
+ if (!smcd->event_wq) {
+ kfree(smcd->conn);
+ kfree(smcd);
+ return NULL;
+ }
return smcd;
}
EXPORT_SYMBOL_GPL(smcd_alloc_dev);
@@ -289,7 +315,7 @@
spin_unlock(&smcd_dev_list.lock);
flush_workqueue(smcd->event_wq);
destroy_workqueue(smcd->event_wq);
- smc_smcd_terminate(smcd, 0);
+ smc_smcd_terminate(smcd, 0, VLAN_VID_MASK);
device_del(&smcd->dev);
}
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index aee45b8..4da946c 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -45,4 +45,5 @@
int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
void *data, size_t len);
+int smc_ism_signal_shutdown(struct smc_link_group *lgr);
#endif
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 9c916c7..4fd60c5 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -166,7 +166,8 @@
{
int rc;
- rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend);
+ rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL,
+ pend);
if (rc < 0)
return rc;
BUILD_BUG_ON_MSG(
@@ -238,6 +239,29 @@
return rc;
}
+/* send LLC delete rkey request */
+static int smc_llc_send_delete_rkey(struct smc_link *link,
+ struct smc_buf_desc *rmb_desc)
+{
+ struct smc_llc_msg_delete_rkey *rkeyllc;
+ struct smc_wr_tx_pend_priv *pend;
+ struct smc_wr_buf *wr_buf;
+ int rc;
+
+ rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+ if (rc)
+ return rc;
+ rkeyllc = (struct smc_llc_msg_delete_rkey *)wr_buf;
+ memset(rkeyllc, 0, sizeof(*rkeyllc));
+ rkeyllc->hd.common.type = SMC_LLC_DELETE_RKEY;
+ rkeyllc->hd.length = sizeof(struct smc_llc_msg_delete_rkey);
+ rkeyllc->num_rkeys = 1;
+ rkeyllc->rkey[0] = htonl(rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+ /* send llc message */
+ rc = smc_wr_tx_send(link, pend);
+ return rc;
+}
+
/* 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[], u8 gid[],
@@ -509,7 +533,9 @@
int i, max;
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
- /* unused as long as we don't send this type of msg */
+ link->llc_delete_rkey_rc = llc->hd.flags &
+ SMC_LLC_FLAG_RKEY_NEG;
+ complete(&link->llc_delete_rkey);
} else {
max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX);
for (i = 0; i < max; i++) {
@@ -610,6 +636,8 @@
init_completion(&link->llc_add);
init_completion(&link->llc_add_resp);
init_completion(&link->llc_confirm_rkey);
+ init_completion(&link->llc_delete_rkey);
+ mutex_init(&link->llc_delete_rkey_mutex);
init_completion(&link->llc_testlink_resp);
INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work);
return 0;
@@ -650,8 +678,11 @@
{
int rc;
+ /* protected by mutex smc_create_lgr_pending */
reinit_completion(&link->llc_confirm_rkey);
- smc_llc_send_confirm_rkey(link, rmb_desc);
+ rc = smc_llc_send_confirm_rkey(link, rmb_desc);
+ if (rc)
+ return rc;
/* receive CONFIRM RKEY response from server over RoCE fabric */
rc = wait_for_completion_interruptible_timeout(&link->llc_confirm_rkey,
SMC_LLC_WAIT_TIME);
@@ -660,6 +691,29 @@
return 0;
}
+/* unregister an rtoken at the remote peer */
+int smc_llc_do_delete_rkey(struct smc_link *link,
+ struct smc_buf_desc *rmb_desc)
+{
+ int rc;
+
+ mutex_lock(&link->llc_delete_rkey_mutex);
+ reinit_completion(&link->llc_delete_rkey);
+ rc = smc_llc_send_delete_rkey(link, rmb_desc);
+ if (rc)
+ goto out;
+ /* receive DELETE RKEY response from server over RoCE fabric */
+ rc = wait_for_completion_interruptible_timeout(&link->llc_delete_rkey,
+ SMC_LLC_WAIT_TIME);
+ if (rc <= 0 || link->llc_delete_rkey_rc)
+ rc = -EFAULT;
+ else
+ rc = 0;
+out:
+ mutex_unlock(&link->llc_delete_rkey_mutex);
+ return rc;
+}
+
/***************************** init, exit, misc ******************************/
static struct smc_wr_rx_handler smc_llc_rx_handlers[] = {
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 9e2ff08..461c0c3 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -49,6 +49,8 @@
void smc_llc_link_clear(struct smc_link *link);
int smc_llc_do_confirm_rkey(struct smc_link *link,
struct smc_buf_desc *rmb_desc);
+int smc_llc_do_delete_rkey(struct smc_link *link,
+ struct smc_buf_desc *rmb_desc);
int smc_llc_init(void) __init;
#endif /* SMC_LLC_H */
diff --git a/net/smc/smc_netns.h b/net/smc/smc_netns.h
new file mode 100644
index 0000000..e7a8fc4
--- /dev/null
+++ b/net/smc/smc_netns.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Shared Memory Communications
+ *
+ * Network namespace definitions.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#ifndef SMC_NETNS_H
+#define SMC_NETNS_H
+
+#include "smc_pnet.h"
+
+extern unsigned int smc_net_id;
+
+/* per-network namespace private data */
+struct smc_net {
+ struct smc_pnettable pnettable;
+};
+#endif
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 7cb3e4f..571e6d8 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -20,14 +20,22 @@
#include <rdma/ib_verbs.h>
+#include <net/netns/generic.h>
+#include "smc_netns.h"
+
#include "smc_pnet.h"
#include "smc_ib.h"
#include "smc_ism.h"
+#include "smc_core.h"
+
+#define SMC_ASCII_BLANK 32
+
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev);
static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
[SMC_PNETID_NAME] = {
.type = NLA_NUL_STRING,
- .len = SMC_MAX_PNETID_LEN - 1
+ .len = SMC_MAX_PNETID_LEN
},
[SMC_PNETID_ETHNAME] = {
.type = NLA_NUL_STRING,
@@ -43,82 +51,107 @@
static struct genl_family smc_pnet_nl_family;
/**
- * struct smc_pnettable - SMC PNET table anchor
- * @lock: Lock for list action
- * @pnetlist: List of PNETIDs
- */
-static struct smc_pnettable {
- rwlock_t lock;
- struct list_head pnetlist;
-} smc_pnettable = {
- .pnetlist = LIST_HEAD_INIT(smc_pnettable.pnetlist),
- .lock = __RW_LOCK_UNLOCKED(smc_pnettable.lock)
-};
-
-/**
- * struct smc_pnetentry - pnet identifier name entry
+ * struct smc_user_pnetentry - pnet identifier name entry for/from user
* @list: List node.
* @pnet_name: Pnet identifier name
* @ndev: pointer to network device.
* @smcibdev: Pointer to IB device.
+ * @ib_port: Port of IB device.
+ * @smcd_dev: Pointer to smcd device.
*/
-struct smc_pnetentry {
+struct smc_user_pnetentry {
struct list_head list;
char pnet_name[SMC_MAX_PNETID_LEN + 1];
struct net_device *ndev;
struct smc_ib_device *smcibdev;
u8 ib_port;
+ struct smcd_dev *smcd_dev;
};
-/* Check if two RDMA device entries are identical. Use device name and port
- * number for comparison.
- */
-static bool smc_pnet_same_ibname(struct smc_pnetentry *pnetelem, char *ibname,
- u8 ibport)
-{
- return pnetelem->ib_port == ibport &&
- !strncmp(pnetelem->smcibdev->ibdev->name, ibname,
- sizeof(pnetelem->smcibdev->ibdev->name));
-}
+/* pnet entry stored in pnet table */
+struct smc_pnetentry {
+ struct list_head list;
+ char pnet_name[SMC_MAX_PNETID_LEN + 1];
+ struct net_device *ndev;
+};
-/* Find a pnetid in the pnet table.
- */
-static struct smc_pnetentry *smc_pnet_find_pnetid(char *pnet_name)
+/* Check if two given pnetids match */
+static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2)
{
- struct smc_pnetentry *pnetelem, *found_pnetelem = NULL;
+ int i;
- read_lock(&smc_pnettable.lock);
- list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
- if (!strncmp(pnetelem->pnet_name, pnet_name,
- sizeof(pnetelem->pnet_name))) {
- found_pnetelem = pnetelem;
+ for (i = 0; i < SMC_MAX_PNETID_LEN; i++) {
+ if ((pnetid1[i] == 0 || pnetid1[i] == SMC_ASCII_BLANK) &&
+ (pnetid2[i] == 0 || pnetid2[i] == SMC_ASCII_BLANK))
break;
- }
+ if (pnetid1[i] != pnetid2[i])
+ return false;
}
- read_unlock(&smc_pnettable.lock);
- return found_pnetelem;
+ return true;
}
/* Remove a pnetid from the pnet table.
*/
-static int smc_pnet_remove_by_pnetid(char *pnet_name)
+static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name)
{
struct smc_pnetentry *pnetelem, *tmp_pe;
+ struct smc_pnettable *pnettable;
+ struct smc_ib_device *ibdev;
+ struct smcd_dev *smcd_dev;
+ struct smc_net *sn;
int rc = -ENOENT;
+ int ibport;
- write_lock(&smc_pnettable.lock);
- list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
+ /* get pnettable for namespace */
+ sn = net_generic(net, smc_net_id);
+ pnettable = &sn->pnettable;
+
+ /* remove netdevices */
+ write_lock(&pnettable->lock);
+ list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist,
list) {
- if (!strncmp(pnetelem->pnet_name, pnet_name,
- sizeof(pnetelem->pnet_name))) {
+ if (!pnet_name ||
+ smc_pnet_match(pnetelem->pnet_name, pnet_name)) {
list_del(&pnetelem->list);
dev_put(pnetelem->ndev);
kfree(pnetelem);
rc = 0;
- break;
}
}
- write_unlock(&smc_pnettable.lock);
+ write_unlock(&pnettable->lock);
+
+ /* if this is not the initial namespace, stop here */
+ if (net != &init_net)
+ return rc;
+
+ /* remove ib devices */
+ spin_lock(&smc_ib_devices.lock);
+ list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+ for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) {
+ if (ibdev->pnetid_by_user[ibport] &&
+ (!pnet_name ||
+ smc_pnet_match(pnet_name,
+ ibdev->pnetid[ibport]))) {
+ memset(ibdev->pnetid[ibport], 0,
+ SMC_MAX_PNETID_LEN);
+ ibdev->pnetid_by_user[ibport] = false;
+ rc = 0;
+ }
+ }
+ }
+ spin_unlock(&smc_ib_devices.lock);
+ /* remove smcd devices */
+ spin_lock(&smcd_dev_list.lock);
+ list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
+ if (smcd_dev->pnetid_by_user &&
+ (!pnet_name ||
+ smc_pnet_match(pnet_name, smcd_dev->pnetid))) {
+ memset(smcd_dev->pnetid, 0, SMC_MAX_PNETID_LEN);
+ smcd_dev->pnetid_by_user = false;
+ rc = 0;
+ }
+ }
+ spin_unlock(&smcd_dev_list.lock);
return rc;
}
@@ -127,11 +160,17 @@
static int smc_pnet_remove_by_ndev(struct net_device *ndev)
{
struct smc_pnetentry *pnetelem, *tmp_pe;
+ struct smc_pnettable *pnettable;
+ struct net *net = dev_net(ndev);
+ struct smc_net *sn;
int rc = -ENOENT;
- write_lock(&smc_pnettable.lock);
- list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
- list) {
+ /* get pnettable for namespace */
+ sn = net_generic(net, smc_net_id);
+ pnettable = &sn->pnettable;
+
+ write_lock(&pnettable->lock);
+ list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) {
if (pnetelem->ndev == ndev) {
list_del(&pnetelem->list);
dev_put(pnetelem->ndev);
@@ -140,57 +179,84 @@
break;
}
}
- write_unlock(&smc_pnettable.lock);
- return rc;
-}
-
-/* Remove a pnet entry mentioning a given ib device from the pnet table.
- */
-int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev)
-{
- struct smc_pnetentry *pnetelem, *tmp_pe;
- int rc = -ENOENT;
-
- write_lock(&smc_pnettable.lock);
- list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
- list) {
- if (pnetelem->smcibdev == ibdev) {
- list_del(&pnetelem->list);
- dev_put(pnetelem->ndev);
- kfree(pnetelem);
- rc = 0;
- break;
- }
- }
- write_unlock(&smc_pnettable.lock);
+ write_unlock(&pnettable->lock);
return rc;
}
/* Append a pnetid to the end of the pnet table if not already on this list.
*/
-static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem)
+static int smc_pnet_enter(struct smc_pnettable *pnettable,
+ struct smc_user_pnetentry *new_pnetelem)
{
+ u8 pnet_null[SMC_MAX_PNETID_LEN] = {0};
+ u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+ struct smc_pnetentry *tmp_pnetelem;
struct smc_pnetentry *pnetelem;
- int rc = -EEXIST;
+ bool new_smcddev = false;
+ struct net_device *ndev;
+ bool new_netdev = true;
+ bool new_ibdev = false;
- write_lock(&smc_pnettable.lock);
- list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
- if (!strncmp(pnetelem->pnet_name, new_pnetelem->pnet_name,
- sizeof(new_pnetelem->pnet_name)) ||
- !strncmp(pnetelem->ndev->name, new_pnetelem->ndev->name,
- sizeof(new_pnetelem->ndev->name)) ||
- smc_pnet_same_ibname(pnetelem,
- new_pnetelem->smcibdev->ibdev->name,
- new_pnetelem->ib_port)) {
- dev_put(pnetelem->ndev);
- goto found;
+ if (new_pnetelem->smcibdev) {
+ struct smc_ib_device *ib_dev = new_pnetelem->smcibdev;
+ int ib_port = new_pnetelem->ib_port;
+
+ spin_lock(&smc_ib_devices.lock);
+ if (smc_pnet_match(ib_dev->pnetid[ib_port - 1], pnet_null)) {
+ memcpy(ib_dev->pnetid[ib_port - 1],
+ new_pnetelem->pnet_name, SMC_MAX_PNETID_LEN);
+ ib_dev->pnetid_by_user[ib_port - 1] = true;
+ new_ibdev = true;
}
+ spin_unlock(&smc_ib_devices.lock);
}
- list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
- rc = 0;
-found:
- write_unlock(&smc_pnettable.lock);
- return rc;
+ if (new_pnetelem->smcd_dev) {
+ struct smcd_dev *smcd_dev = new_pnetelem->smcd_dev;
+
+ spin_lock(&smcd_dev_list.lock);
+ if (smc_pnet_match(smcd_dev->pnetid, pnet_null)) {
+ memcpy(smcd_dev->pnetid, new_pnetelem->pnet_name,
+ SMC_MAX_PNETID_LEN);
+ smcd_dev->pnetid_by_user = true;
+ new_smcddev = true;
+ }
+ spin_unlock(&smcd_dev_list.lock);
+ }
+
+ if (!new_pnetelem->ndev)
+ return (new_ibdev || new_smcddev) ? 0 : -EEXIST;
+
+ /* check if (base) netdev already has a pnetid. If there is one, we do
+ * not want to add a pnet table entry
+ */
+ ndev = pnet_find_base_ndev(new_pnetelem->ndev);
+ if (!smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+ ndev_pnetid))
+ return (new_ibdev || new_smcddev) ? 0 : -EEXIST;
+
+ /* add a new netdev entry to the pnet table if there isn't one */
+ tmp_pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL);
+ if (!tmp_pnetelem)
+ return -ENOMEM;
+ memcpy(tmp_pnetelem->pnet_name, new_pnetelem->pnet_name,
+ SMC_MAX_PNETID_LEN);
+ tmp_pnetelem->ndev = new_pnetelem->ndev;
+
+ write_lock(&pnettable->lock);
+ list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
+ if (pnetelem->ndev == new_pnetelem->ndev)
+ new_netdev = false;
+ }
+ if (new_netdev) {
+ dev_hold(tmp_pnetelem->ndev);
+ list_add_tail(&tmp_pnetelem->list, &pnettable->pnetlist);
+ write_unlock(&pnettable->lock);
+ } else {
+ write_unlock(&pnettable->lock);
+ kfree(tmp_pnetelem);
+ }
+
+ return (new_netdev || new_ibdev || new_smcddev) ? 0 : -EEXIST;
}
/* The limit for pnetid is 16 characters.
@@ -228,7 +294,9 @@
spin_lock(&smc_ib_devices.lock);
list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
if (!strncmp(ibdev->ibdev->name, ib_name,
- sizeof(ibdev->ibdev->name))) {
+ sizeof(ibdev->ibdev->name)) ||
+ !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name,
+ IB_DEVICE_NAME_MAX - 1)) {
goto out;
}
}
@@ -238,10 +306,28 @@
return ibdev;
}
+/* Find an smcd device by a given name. The device might not exist. */
+static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name)
+{
+ struct smcd_dev *smcd_dev;
+
+ spin_lock(&smcd_dev_list.lock);
+ list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
+ if (!strncmp(dev_name(&smcd_dev->dev), smcd_name,
+ IB_DEVICE_NAME_MAX - 1))
+ goto out;
+ }
+ smcd_dev = NULL;
+out:
+ spin_unlock(&smcd_dev_list.lock);
+ return smcd_dev;
+}
+
/* Parse the supplied netlink attributes and fill a pnetentry structure.
* For ethernet and infiniband device names verify that the devices exist.
*/
-static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
+static int smc_pnet_fill_entry(struct net *net,
+ struct smc_user_pnetentry *pnetelem,
struct nlattr *tb[])
{
char *string, *ibname;
@@ -258,113 +344,101 @@
goto error;
rc = -EINVAL;
- if (!tb[SMC_PNETID_ETHNAME])
- goto error;
- rc = -ENOENT;
- string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
- pnetelem->ndev = dev_get_by_name(net, string);
- if (!pnetelem->ndev)
- goto error;
+ if (tb[SMC_PNETID_ETHNAME]) {
+ string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
+ pnetelem->ndev = dev_get_by_name(net, string);
+ if (!pnetelem->ndev)
+ goto error;
+ }
+
+ /* if this is not the initial namespace, stop here */
+ if (net != &init_net)
+ return 0;
rc = -EINVAL;
- if (!tb[SMC_PNETID_IBNAME])
- goto error;
- rc = -ENOENT;
- ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
- ibname = strim(ibname);
- pnetelem->smcibdev = smc_pnet_find_ib(ibname);
- if (!pnetelem->smcibdev)
- goto error;
-
- rc = -EINVAL;
- if (!tb[SMC_PNETID_IBPORT])
- goto error;
- pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
- if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS)
- goto error;
+ if (tb[SMC_PNETID_IBNAME]) {
+ ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
+ ibname = strim(ibname);
+ pnetelem->smcibdev = smc_pnet_find_ib(ibname);
+ pnetelem->smcd_dev = smc_pnet_find_smcd(ibname);
+ if (!pnetelem->smcibdev && !pnetelem->smcd_dev)
+ goto error;
+ if (pnetelem->smcibdev) {
+ if (!tb[SMC_PNETID_IBPORT])
+ goto error;
+ pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
+ if (pnetelem->ib_port < 1 ||
+ pnetelem->ib_port > SMC_MAX_PORTS)
+ goto error;
+ }
+ }
return 0;
error:
- if (pnetelem->ndev)
- dev_put(pnetelem->ndev);
return rc;
}
/* Convert an smc_pnetentry to a netlink attribute sequence */
-static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem)
+static int smc_pnet_set_nla(struct sk_buff *msg,
+ struct smc_user_pnetentry *pnetelem)
{
- if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name) ||
- nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->ndev->name) ||
- nla_put_string(msg, SMC_PNETID_IBNAME,
- pnetelem->smcibdev->ibdev->name) ||
- nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port))
+ if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name))
return -1;
+ if (pnetelem->ndev) {
+ if (nla_put_string(msg, SMC_PNETID_ETHNAME,
+ pnetelem->ndev->name))
+ return -1;
+ } else {
+ if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a"))
+ return -1;
+ }
+ if (pnetelem->smcibdev) {
+ if (nla_put_string(msg, SMC_PNETID_IBNAME,
+ dev_name(pnetelem->smcibdev->ibdev->dev.parent)) ||
+ nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port))
+ return -1;
+ } else if (pnetelem->smcd_dev) {
+ if (nla_put_string(msg, SMC_PNETID_IBNAME,
+ dev_name(&pnetelem->smcd_dev->dev)) ||
+ nla_put_u8(msg, SMC_PNETID_IBPORT, 1))
+ return -1;
+ } else {
+ if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") ||
+ nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff))
+ return -1;
+ }
+
return 0;
}
-/* Retrieve one PNETID entry */
-static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
-{
- struct smc_pnetentry *pnetelem;
- struct sk_buff *msg;
- void *hdr;
- int rc;
-
- if (!info->attrs[SMC_PNETID_NAME])
- return -EINVAL;
- pnetelem = smc_pnet_find_pnetid(
- (char *)nla_data(info->attrs[SMC_PNETID_NAME]));
- if (!pnetelem)
- return -ENOENT;
- msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!msg)
- return -ENOMEM;
-
- hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq,
- &smc_pnet_nl_family, 0, SMC_PNETID_GET);
- if (!hdr) {
- rc = -EMSGSIZE;
- goto err_out;
- }
-
- if (smc_pnet_set_nla(msg, pnetelem)) {
- rc = -ENOBUFS;
- goto err_out;
- }
-
- genlmsg_end(msg, hdr);
- return genlmsg_reply(msg, info);
-
-err_out:
- nlmsg_free(msg);
- return rc;
-}
-
static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
- struct smc_pnetentry *pnetelem;
+ struct smc_user_pnetentry pnetelem;
+ struct smc_pnettable *pnettable;
+ struct smc_net *sn;
int rc;
- pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL);
- if (!pnetelem)
- return -ENOMEM;
- rc = smc_pnet_fill_entry(net, pnetelem, info->attrs);
+ /* get pnettable for namespace */
+ sn = net_generic(net, smc_net_id);
+ pnettable = &sn->pnettable;
+
+ rc = smc_pnet_fill_entry(net, &pnetelem, info->attrs);
if (!rc)
- rc = smc_pnet_enter(pnetelem);
- if (rc) {
- kfree(pnetelem);
- return rc;
- }
+ rc = smc_pnet_enter(pnettable, &pnetelem);
+ if (pnetelem.ndev)
+ dev_put(pnetelem.ndev);
return rc;
}
static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info)
{
+ struct net *net = genl_info_net(info);
+
if (!info->attrs[SMC_PNETID_NAME])
return -EINVAL;
- return smc_pnet_remove_by_pnetid(
+ return smc_pnet_remove_by_pnetid(net,
(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
}
@@ -376,7 +450,7 @@
static int smc_pnet_dumpinfo(struct sk_buff *skb,
u32 portid, u32 seq, u32 flags,
- struct smc_pnetentry *pnetelem)
+ struct smc_user_pnetentry *pnetelem)
{
void *hdr;
@@ -392,41 +466,143 @@
return 0;
}
-static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb)
+static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid,
+ u32 seq, u8 *pnetid, int start_idx)
{
+ struct smc_user_pnetentry tmp_entry;
+ struct smc_pnettable *pnettable;
struct smc_pnetentry *pnetelem;
+ struct smc_ib_device *ibdev;
+ struct smcd_dev *smcd_dev;
+ struct smc_net *sn;
int idx = 0;
+ int ibport;
- read_lock(&smc_pnettable.lock);
- list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
- if (idx++ < cb->args[0])
+ /* get pnettable for namespace */
+ sn = net_generic(net, smc_net_id);
+ pnettable = &sn->pnettable;
+
+ /* dump netdevices */
+ read_lock(&pnettable->lock);
+ list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
+ if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid))
continue;
- if (smc_pnet_dumpinfo(skb, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI,
- pnetelem)) {
+ if (idx++ < start_idx)
+ continue;
+ memset(&tmp_entry, 0, sizeof(tmp_entry));
+ memcpy(&tmp_entry.pnet_name, pnetelem->pnet_name,
+ SMC_MAX_PNETID_LEN);
+ tmp_entry.ndev = pnetelem->ndev;
+ if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI,
+ &tmp_entry)) {
--idx;
break;
}
}
+ read_unlock(&pnettable->lock);
+
+ /* if this is not the initial namespace, stop here */
+ if (net != &init_net)
+ return idx;
+
+ /* dump ib devices */
+ spin_lock(&smc_ib_devices.lock);
+ list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+ for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) {
+ if (ibdev->pnetid_by_user[ibport]) {
+ if (pnetid &&
+ !smc_pnet_match(ibdev->pnetid[ibport],
+ pnetid))
+ continue;
+ if (idx++ < start_idx)
+ continue;
+ memset(&tmp_entry, 0, sizeof(tmp_entry));
+ memcpy(&tmp_entry.pnet_name,
+ ibdev->pnetid[ibport],
+ SMC_MAX_PNETID_LEN);
+ tmp_entry.smcibdev = ibdev;
+ tmp_entry.ib_port = ibport + 1;
+ if (smc_pnet_dumpinfo(skb, portid, seq,
+ NLM_F_MULTI,
+ &tmp_entry)) {
+ --idx;
+ break;
+ }
+ }
+ }
+ }
+ spin_unlock(&smc_ib_devices.lock);
+
+ /* dump smcd devices */
+ spin_lock(&smcd_dev_list.lock);
+ list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
+ if (smcd_dev->pnetid_by_user) {
+ if (pnetid && !smc_pnet_match(smcd_dev->pnetid, pnetid))
+ continue;
+ if (idx++ < start_idx)
+ continue;
+ memset(&tmp_entry, 0, sizeof(tmp_entry));
+ memcpy(&tmp_entry.pnet_name, smcd_dev->pnetid,
+ SMC_MAX_PNETID_LEN);
+ tmp_entry.smcd_dev = smcd_dev;
+ if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI,
+ &tmp_entry)) {
+ --idx;
+ break;
+ }
+ }
+ }
+ spin_unlock(&smcd_dev_list.lock);
+
+ return idx;
+}
+
+static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ int idx;
+
+ idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NULL, cb->args[0]);
+
cb->args[0] = idx;
- read_unlock(&smc_pnettable.lock);
return skb->len;
}
+/* Retrieve one PNETID entry */
+static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct sk_buff *msg;
+ void *hdr;
+
+ if (!info->attrs[SMC_PNETID_NAME])
+ return -EINVAL;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ _smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq,
+ nla_data(info->attrs[SMC_PNETID_NAME]), 0);
+
+ /* finish multi part message and send it */
+ hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0,
+ NLM_F_MULTI);
+ if (!hdr) {
+ nlmsg_free(msg);
+ return -EMSGSIZE;
+ }
+ return genlmsg_reply(msg, info);
+}
+
/* Remove and delete all pnetids from pnet table.
*/
static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
{
- struct smc_pnetentry *pnetelem, *tmp_pe;
+ struct net *net = genl_info_net(info);
- write_lock(&smc_pnettable.lock);
- list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
- list) {
- list_del(&pnetelem->list);
- dev_put(pnetelem->ndev);
- kfree(pnetelem);
- }
- write_unlock(&smc_pnettable.lock);
+ smc_pnet_remove_by_pnetid(net, NULL);
return 0;
}
@@ -434,28 +610,28 @@
static const struct genl_ops smc_pnet_ops[] = {
{
.cmd = SMC_PNETID_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.flags = GENL_ADMIN_PERM,
- .policy = smc_pnet_policy,
.doit = smc_pnet_get,
.dumpit = smc_pnet_dump,
.start = smc_pnet_dump_start
},
{
.cmd = SMC_PNETID_ADD,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.flags = GENL_ADMIN_PERM,
- .policy = smc_pnet_policy,
.doit = smc_pnet_add
},
{
.cmd = SMC_PNETID_DEL,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.flags = GENL_ADMIN_PERM,
- .policy = smc_pnet_policy,
.doit = smc_pnet_del
},
{
.cmd = SMC_PNETID_FLUSH,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.flags = GENL_ADMIN_PERM,
- .policy = smc_pnet_policy,
.doit = smc_pnet_flush
}
};
@@ -466,6 +642,7 @@
.name = SMCR_GENL_FAMILY_NAME,
.version = SMCR_GENL_FAMILY_VERSION,
.maxattr = SMC_PNETID_MAX,
+ .policy = smc_pnet_policy,
.netnsok = true,
.module = THIS_MODULE,
.ops = smc_pnet_ops,
@@ -491,6 +668,18 @@
.notifier_call = smc_pnet_netdev_event
};
+/* init network namespace */
+int smc_pnet_net_init(struct net *net)
+{
+ struct smc_net *sn = net_generic(net, smc_net_id);
+ struct smc_pnettable *pnettable = &sn->pnettable;
+
+ INIT_LIST_HEAD(&pnettable->pnetlist);
+ rwlock_init(&pnettable->lock);
+
+ return 0;
+}
+
int __init smc_pnet_init(void)
{
int rc;
@@ -504,9 +693,15 @@
return rc;
}
+/* exit network namespace */
+void smc_pnet_net_exit(struct net *net)
+{
+ /* flush pnet table */
+ smc_pnet_remove_by_pnetid(net, NULL);
+}
+
void smc_pnet_exit(void)
{
- smc_pnet_flush(NULL, NULL);
unregister_netdevice_notifier(&smc_netdev_notifier);
genl_unregister_family(&smc_pnet_nl_family);
}
@@ -521,7 +716,7 @@
int i, nest_lvl;
rtnl_lock();
- nest_lvl = dev_get_nest_level(ndev);
+ nest_lvl = ndev->lower_level;
for (i = 0; i < nest_lvl; i++) {
struct list_head *lower = &ndev->adj_list.lower;
@@ -534,14 +729,75 @@
return ndev;
}
+static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev,
+ u8 *pnetid)
+{
+ struct smc_pnettable *pnettable;
+ struct net *net = dev_net(ndev);
+ struct smc_pnetentry *pnetelem;
+ struct smc_net *sn;
+ int rc = -ENOENT;
+
+ /* get pnettable for namespace */
+ sn = net_generic(net, smc_net_id);
+ pnettable = &sn->pnettable;
+
+ read_lock(&pnettable->lock);
+ list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
+ if (ndev == pnetelem->ndev) {
+ /* get pnetid of netdev device */
+ memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN);
+ rc = 0;
+ break;
+ }
+ }
+ read_unlock(&pnettable->lock);
+ return rc;
+}
+
+/* if handshake network device belongs to a roce device, return its
+ * IB device and port
+ */
+static void smc_pnet_find_rdma_dev(struct net_device *netdev,
+ struct smc_init_info *ini)
+{
+ struct smc_ib_device *ibdev;
+
+ spin_lock(&smc_ib_devices.lock);
+ list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+ struct net_device *ndev;
+ int i;
+
+ for (i = 1; i <= SMC_MAX_PORTS; i++) {
+ if (!rdma_is_port_valid(ibdev->ibdev, i))
+ continue;
+ if (!ibdev->ibdev->ops.get_netdev)
+ continue;
+ ndev = ibdev->ibdev->ops.get_netdev(ibdev->ibdev, i);
+ if (!ndev)
+ continue;
+ dev_put(ndev);
+ if (netdev == ndev &&
+ smc_ib_port_active(ibdev, i) &&
+ !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
+ ini->ib_gid, NULL)) {
+ ini->ib_dev = ibdev;
+ ini->ib_port = i;
+ break;
+ }
+ }
+ }
+ spin_unlock(&smc_ib_devices.lock);
+}
+
/* Determine the corresponding IB device port based on the hardware PNETID.
* Searching stops at the first matching active IB device port with vlan_id
* configured.
+ * If nothing found, check pnetid table.
+ * If nothing found, try to use handshake device
*/
static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
- struct smc_ib_device **smcibdev,
- u8 *ibport, unsigned short vlan_id,
- u8 gid[])
+ struct smc_init_info *ini)
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct smc_ib_device *ibdev;
@@ -549,21 +805,23 @@
ndev = pnet_find_base_ndev(ndev);
if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
- ndev_pnetid))
+ ndev_pnetid) &&
+ smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) {
+ smc_pnet_find_rdma_dev(ndev, ini);
return; /* pnetid could not be determined */
+ }
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) &&
+ if (smc_pnet_match(ibdev->pnetid[i - 1], ndev_pnetid) &&
smc_ib_port_active(ibdev, i) &&
- !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
- NULL)) {
- *smcibdev = ibdev;
- *ibport = i;
+ !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
+ ini->ib_gid, NULL)) {
+ ini->ib_dev = ibdev;
+ ini->ib_port = i;
goto out;
}
}
@@ -573,76 +831,43 @@
}
static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
- struct smcd_dev **smcismdev)
+ struct smc_init_info *ini)
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
struct smcd_dev *ismdev;
ndev = pnet_find_base_ndev(ndev);
if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
- ndev_pnetid))
+ ndev_pnetid) &&
+ smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid))
return; /* pnetid could not be determined */
spin_lock(&smcd_dev_list.lock);
list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
- if (!memcmp(ismdev->pnetid, ndev_pnetid, SMC_MAX_PNETID_LEN)) {
- *smcismdev = ismdev;
+ if (smc_pnet_match(ismdev->pnetid, ndev_pnetid)) {
+ ini->ism_dev = ismdev;
break;
}
}
spin_unlock(&smcd_dev_list.lock);
}
-/* 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, unsigned short vlan_id,
- u8 gid[])
-{
- struct smc_pnetentry *pnetelem;
-
- read_lock(&smc_pnettable.lock);
- list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
- if (netdev == pnetelem->ndev) {
- if (smc_ib_port_active(pnetelem->smcibdev,
- pnetelem->ib_port) &&
- !smc_ib_determine_gid(pnetelem->smcibdev,
- pnetelem->ib_port, vlan_id,
- gid, NULL)) {
- *smcibdev = pnetelem->smcibdev;
- *ibport = pnetelem->ib_port;
- }
- break;
- }
- }
- read_unlock(&smc_pnettable.lock);
-}
-
/* PNET table analysis for a given sock:
* determine ib_device and port belonging to used internal TCP socket
* ethernet interface.
*/
-void smc_pnet_find_roce_resource(struct sock *sk,
- struct smc_ib_device **smcibdev, u8 *ibport,
- unsigned short vlan_id, u8 gid[])
+void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(sk);
- *smcibdev = NULL;
- *ibport = 0;
-
+ ini->ib_dev = NULL;
+ ini->ib_port = 0;
if (!dst)
goto out;
if (!dst->dev)
goto out_rel;
- /* if possible, lookup via hardware-defined pnetid */
- 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, vlan_id, gid);
+ smc_pnet_find_roce_by_pnetid(dst->dev, ini);
out_rel:
dst_release(dst);
@@ -650,18 +875,17 @@
return;
}
-void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev)
+void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini)
{
struct dst_entry *dst = sk_dst_get(sk);
- *smcismdev = NULL;
+ ini->ism_dev = NULL;
if (!dst)
goto out;
if (!dst->dev)
goto out_rel;
- /* if possible, lookup via hardware-defined pnetid */
- smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev);
+ smc_pnet_find_ism_by_pnetid(dst->dev, ini);
out_rel:
dst_release(dst);
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 8ff7776..4564e4d 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -18,6 +18,17 @@
struct smc_ib_device;
struct smcd_dev;
+struct smc_init_info;
+
+/**
+ * struct smc_pnettable - SMC PNET table anchor
+ * @lock: Lock for list action
+ * @pnetlist: List of PNETIDs
+ */
+struct smc_pnettable {
+ rwlock_t lock;
+ struct list_head pnetlist;
+};
static inline int smc_pnetid_by_dev_port(struct device *dev,
unsigned short port, u8 *pnetid)
@@ -30,11 +41,10 @@
}
int smc_pnet_init(void) __init;
+int smc_pnet_net_init(struct net *net);
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,
- unsigned short vlan_id, u8 gid[]);
-void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
+void smc_pnet_net_exit(struct net *net);
+void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini);
+void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini);
#endif
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index bbcf0fe..97e8369 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -136,7 +136,6 @@
}
static const struct pipe_buf_operations smc_pipe_ops = {
- .can_merge = 0,
.confirm = generic_pipe_buf_confirm,
.release = smc_rx_pipe_buf_release,
.steal = smc_rx_pipe_buf_nosteal,
@@ -212,8 +211,7 @@
rc = sk_wait_event(sk, timeo,
sk->sk_err ||
sk->sk_shutdown & RCV_SHUTDOWN ||
- fcrit(conn) ||
- smc_cdc_rxed_any_close_or_senddone(conn),
+ fcrit(conn),
&wait);
remove_wait_queue(sk_sleep(sk), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
@@ -263,6 +261,18 @@
return -EAGAIN;
}
+static bool smc_rx_recvmsg_data_available(struct smc_sock *smc)
+{
+ struct smc_connection *conn = &smc->conn;
+
+ if (smc_rx_data_available(conn))
+ return true;
+ else if (conn->urg_state == SMC_URG_VALID)
+ /* we received a single urgent Byte - skip */
+ smc_rx_update_cons(smc, 0);
+ return false;
+}
+
/* smc_rx_recvmsg - receive data from RMBE
* @msg: copy data to receive buffer
* @pipe: copy data to pipe if set - indicates splice() call
@@ -304,16 +314,18 @@
if (read_done >= target || (pipe && read_done))
break;
- if (atomic_read(&conn->bytes_to_rcv))
+ if (smc_rx_recvmsg_data_available(smc))
goto copy;
- else if (conn->urg_state == SMC_URG_VALID)
- /* we received a single urgent Byte - skip */
- smc_rx_update_cons(smc, 0);
if (sk->sk_shutdown & RCV_SHUTDOWN ||
- smc_cdc_rxed_any_close_or_senddone(conn) ||
- conn->local_tx_ctrl.conn_state_flags.peer_conn_abort)
+ conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) {
+ /* smc_cdc_msg_recv_action() could have run after
+ * above smc_rx_recvmsg_data_available()
+ */
+ if (smc_rx_recvmsg_data_available(smc))
+ goto copy;
break;
+ }
if (read_done) {
if (sk->sk_err ||
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index d8366ed..6c8f09c 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -24,10 +24,11 @@
#include "smc.h"
#include "smc_wr.h"
#include "smc_cdc.h"
+#include "smc_close.h"
#include "smc_ism.h"
#include "smc_tx.h"
-#define SMC_TX_WORK_DELAY HZ
+#define SMC_TX_WORK_DELAY 0
#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */
/***************************** sndbuf producer *******************************/
@@ -75,13 +76,11 @@
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
- bool noblock;
long timeo;
int rc = 0;
/* similar to sk_stream_wait_memory */
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
- noblock = timeo ? false : true;
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -96,8 +95,8 @@
break;
}
if (!timeo) {
- if (noblock)
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ /* ensure EPOLLOUT is subsequently generated */
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
rc = -EAGAIN;
break;
}
@@ -165,12 +164,11 @@
conn->local_tx_ctrl.prod_flags.urg_data_pending = 1;
if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) {
+ if (send_done)
+ return send_done;
rc = smc_tx_wait(smc, msg->msg_flags);
- if (rc) {
- if (send_done)
- return send_done;
+ if (rc)
goto out_err;
- }
continue;
}
@@ -267,27 +265,23 @@
/* sndbuf consumer: actual data transfer of one target chunk with RDMA write */
static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset,
- int num_sges, struct ib_sge sges[])
+ int num_sges, struct ib_rdma_wr *rdma_wr)
{
struct smc_link_group *lgr = conn->lgr;
- struct ib_rdma_wr rdma_wr;
struct smc_link *link;
int rc;
- memset(&rdma_wr, 0, sizeof(rdma_wr));
link = &lgr->lnk[SMC_SINGLE_LINK];
- rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link);
- rdma_wr.wr.sg_list = sges;
- rdma_wr.wr.num_sge = num_sges;
- rdma_wr.wr.opcode = IB_WR_RDMA_WRITE;
- rdma_wr.remote_addr =
+ rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link);
+ rdma_wr->wr.num_sge = num_sges;
+ rdma_wr->remote_addr =
lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr +
/* RMBE within RMB */
conn->tx_off +
/* offset within RMBE */
peer_rmbe_offset;
- rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
- rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL);
+ rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey;
+ rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL);
if (rc) {
conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
smc_lgr_terminate(lgr);
@@ -314,24 +308,25 @@
/* SMC-R helper for smc_tx_rdma_writes() */
static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
size_t src_off, size_t src_len,
- size_t dst_off, size_t dst_len)
+ size_t dst_off, size_t dst_len,
+ struct smc_rdma_wr *wr_rdma_buf)
{
dma_addr_t dma_addr =
sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
- struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
int src_len_sum = src_len, dst_len_sum = dst_len;
- struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
int sent_count = src_off;
int srcchunk, dstchunk;
int num_sges;
int rc;
for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+ struct ib_sge *sge =
+ wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list;
+
num_sges = 0;
for (srcchunk = 0; srcchunk < 2; srcchunk++) {
- sges[srcchunk].addr = dma_addr + src_off;
- sges[srcchunk].length = src_len;
- sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
+ sge[srcchunk].addr = dma_addr + src_off;
+ sge[srcchunk].length = src_len;
num_sges++;
src_off += src_len;
@@ -344,7 +339,8 @@
src_len = dst_len - src_len; /* remainder */
src_len_sum += src_len;
}
- rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
+ rc = smc_tx_rdma_write(conn, dst_off, num_sges,
+ &wr_rdma_buf->wr_tx_rdma[dstchunk]);
if (rc)
return rc;
if (dst_len_sum == len)
@@ -403,7 +399,8 @@
/* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
* usable snd_wnd as max transmit
*/
-static int smc_tx_rdma_writes(struct smc_connection *conn)
+static int smc_tx_rdma_writes(struct smc_connection *conn,
+ struct smc_rdma_wr *wr_rdma_buf)
{
size_t len, src_len, dst_off, dst_len; /* current chunk values */
union smc_host_cursor sent, prep, prod, cons;
@@ -464,7 +461,7 @@
dst_off, dst_len);
else
rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len,
- dst_off, dst_len);
+ dst_off, dst_len, wr_rdma_buf);
if (rc)
return rc;
@@ -484,32 +481,31 @@
*/
static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
{
- struct smc_cdc_producer_flags *pflags;
+ struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
+ struct smc_rdma_wr *wr_rdma_buf;
struct smc_cdc_tx_pend *pend;
struct smc_wr_buf *wr_buf;
int rc;
- spin_lock_bh(&conn->send_lock);
- rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend);
+ rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend);
if (rc < 0) {
if (rc == -EBUSY) {
struct smc_sock *smc =
container_of(conn, struct smc_sock, conn);
- if (smc->sk.sk_err == ECONNABORTED) {
- rc = sock_error(&smc->sk);
- goto out_unlock;
- }
+ if (smc->sk.sk_err == ECONNABORTED)
+ return sock_error(&smc->sk);
rc = 0;
if (conn->alert_token_local) /* connection healthy */
mod_delayed_work(system_wq, &conn->tx_work,
SMC_TX_WORK_DELAY);
}
- goto out_unlock;
+ return rc;
}
- if (!conn->local_tx_ctrl.prod_flags.urg_data_present) {
- rc = smc_tx_rdma_writes(conn);
+ spin_lock_bh(&conn->send_lock);
+ if (!pflags->urg_data_present) {
+ rc = smc_tx_rdma_writes(conn, wr_rdma_buf);
if (rc) {
smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
(struct smc_wr_tx_pend_priv *)pend);
@@ -518,7 +514,6 @@
}
rc = smc_cdc_msg_send(conn, wr_buf, pend);
- pflags = &conn->local_tx_ctrl.prod_flags;
if (!rc && pflags->urg_data_present) {
pflags->urg_data_pending = 0;
pflags->urg_data_present = 0;
@@ -536,7 +531,7 @@
spin_lock_bh(&conn->send_lock);
if (!pflags->urg_data_present)
- rc = smc_tx_rdma_writes(conn);
+ rc = smc_tx_rdma_writes(conn, NULL);
if (!rc)
rc = smcd_cdc_msg_send(conn);
@@ -557,6 +552,12 @@
else
rc = smcr_tx_sndbuf_nonempty(conn);
+ if (!rc) {
+ /* trigger socket release if connection is closing */
+ struct smc_sock *smc = container_of(conn, struct smc_sock,
+ conn);
+ smc_close_wake_tx_prepared(smc);
+ }
return rc;
}
@@ -598,7 +599,8 @@
if (to_confirm > conn->rmbe_update_limit) {
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);
+ smc_curs_diff_large(conn->rmb_desc->len,
+ &cfed, &prod);
}
if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
@@ -612,9 +614,6 @@
SMC_TX_WORK_DELAY);
return;
}
- 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 &&
!atomic_read(&conn->bytes_to_rcv))
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 3c458d2..253aa75 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -160,6 +160,7 @@
* @link: Pointer to smc_link used to later send the message.
* @handler: Send completion handler function pointer.
* @wr_buf: Out value returns pointer to message buffer.
+ * @wr_rdma_buf: Out value returns pointer to rdma work request.
* @wr_pend_priv: Out value returns pointer serving as handler context.
*
* Return: 0 on success, or -errno on error.
@@ -167,6 +168,7 @@
int smc_wr_tx_get_free_slot(struct smc_link *link,
smc_wr_tx_handler handler,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wr_rdma_buf,
struct smc_wr_tx_pend_priv **wr_pend_priv)
{
struct smc_wr_tx_pend *wr_pend;
@@ -204,6 +206,8 @@
wr_ib = &link->wr_tx_ibs[idx];
wr_ib->wr_id = wr_id;
*wr_buf = &link->wr_tx_bufs[idx];
+ if (wr_rdma_buf)
+ *wr_rdma_buf = &link->wr_tx_rdmas[idx];
*wr_pend_priv = &wr_pend->priv;
return 0;
}
@@ -215,12 +219,14 @@
pend = container_of(wr_pend_priv, struct smc_wr_tx_pend, priv);
if (pend->idx < link->wr_tx_cnt) {
+ u32 idx = pend->idx;
+
/* clear the full struct smc_wr_tx_pend including .priv */
- memset(&link->wr_tx_pends[pend->idx], 0,
- sizeof(link->wr_tx_pends[pend->idx]));
- memset(&link->wr_tx_bufs[pend->idx], 0,
- sizeof(link->wr_tx_bufs[pend->idx]));
- test_and_clear_bit(pend->idx, link->wr_tx_mask);
+ memset(&link->wr_tx_pends[idx], 0,
+ sizeof(link->wr_tx_pends[idx]));
+ memset(&link->wr_tx_bufs[idx], 0,
+ sizeof(link->wr_tx_bufs[idx]));
+ test_and_clear_bit(idx, link->wr_tx_mask);
return 1;
}
@@ -463,12 +469,26 @@
lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE;
lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE;
lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey =
+ lnk->roce_pd->local_dma_lkey;
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey =
+ lnk->roce_pd->local_dma_lkey;
lnk->wr_tx_ibs[i].next = NULL;
lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i];
lnk->wr_tx_ibs[i].num_sge = 1;
lnk->wr_tx_ibs[i].opcode = IB_WR_SEND;
lnk->wr_tx_ibs[i].send_flags =
IB_SEND_SIGNALED | IB_SEND_SOLICITED;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list =
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge;
+ lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list =
+ lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge;
}
for (i = 0; i < lnk->wr_rx_cnt; i++) {
lnk->wr_rx_sges[i].addr =
@@ -519,8 +539,12 @@
lnk->wr_tx_mask = NULL;
kfree(lnk->wr_tx_sges);
lnk->wr_tx_sges = NULL;
+ kfree(lnk->wr_tx_rdma_sges);
+ lnk->wr_tx_rdma_sges = NULL;
kfree(lnk->wr_rx_sges);
lnk->wr_rx_sges = NULL;
+ kfree(lnk->wr_tx_rdmas);
+ lnk->wr_tx_rdmas = NULL;
kfree(lnk->wr_rx_ibs);
lnk->wr_rx_ibs = NULL;
kfree(lnk->wr_tx_ibs);
@@ -550,10 +574,20 @@
GFP_KERNEL);
if (!link->wr_rx_ibs)
goto no_mem_wr_tx_ibs;
+ link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT,
+ sizeof(link->wr_tx_rdmas[0]),
+ GFP_KERNEL);
+ if (!link->wr_tx_rdmas)
+ goto no_mem_wr_rx_ibs;
+ link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT,
+ sizeof(link->wr_tx_rdma_sges[0]),
+ GFP_KERNEL);
+ if (!link->wr_tx_rdma_sges)
+ goto no_mem_wr_tx_rdmas;
link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]),
GFP_KERNEL);
if (!link->wr_tx_sges)
- goto no_mem_wr_rx_ibs;
+ goto no_mem_wr_tx_rdma_sges;
link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3,
sizeof(link->wr_rx_sges[0]),
GFP_KERNEL);
@@ -577,6 +611,10 @@
kfree(link->wr_rx_sges);
no_mem_wr_tx_sges:
kfree(link->wr_tx_sges);
+no_mem_wr_tx_rdma_sges:
+ kfree(link->wr_tx_rdma_sges);
+no_mem_wr_tx_rdmas:
+ kfree(link->wr_tx_rdmas);
no_mem_wr_rx_ibs:
kfree(link->wr_rx_ibs);
no_mem_wr_tx_ibs:
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index 1d85bb1..09bf32f 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -85,6 +85,7 @@
int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler,
struct smc_wr_buf **wr_buf,
+ struct smc_rdma_wr **wrs,
struct smc_wr_tx_pend_priv **wr_pend_priv);
int smc_wr_tx_put_slot(struct smc_link *link,
struct smc_wr_tx_pend_priv *wr_pend_priv);