summaryrefslogtreecommitdiff
path: root/net/smc
diff options
context:
space:
mode:
Diffstat (limited to 'net/smc')
-rw-r--r--net/smc/Kconfig13
-rw-r--r--net/smc/Makefile3
-rw-r--r--net/smc/af_smc.c213
-rw-r--r--net/smc/smc.h38
-rw-r--r--net/smc/smc_cdc.c36
-rw-r--r--net/smc/smc_clc.c6
-rw-r--r--net/smc/smc_clc.h26
-rw-r--r--net/smc/smc_core.c68
-rw-r--r--net/smc/smc_core.h1
-rw-r--r--net/smc/smc_inet.c159
-rw-r--r--net/smc/smc_inet.h22
-rw-r--r--net/smc/smc_ism.c88
-rw-r--r--net/smc/smc_ism.h10
-rw-r--r--net/smc/smc_loopback.c427
-rw-r--r--net/smc/smc_loopback.h61
-rw-r--r--net/smc/smc_rx.c4
-rw-r--r--net/smc/smc_stats.h2
-rw-r--r--net/smc/smc_sysctl.c8
-rw-r--r--net/smc/smc_tracepoint.h4
19 files changed, 1054 insertions, 135 deletions
diff --git a/net/smc/Kconfig b/net/smc/Kconfig
index 746be3996768..ba5e6a2dd2fd 100644
--- a/net/smc/Kconfig
+++ b/net/smc/Kconfig
@@ -20,3 +20,16 @@ config SMC_DIAG
smcss.
if unsure, say Y.
+
+config SMC_LO
+ bool "SMC intra-OS shortcut with loopback-ism"
+ depends on SMC
+ default n
+ help
+ SMC_LO enables the creation of an Emulated-ISM device named
+ loopback-ism in SMC and makes use of it for transferring data
+ when communication occurs within the same OS. This helps in
+ convenient testing of SMC-D since loopback-ism is independent
+ of architecture or hardware.
+
+ if unsure, say N.
diff --git a/net/smc/Makefile b/net/smc/Makefile
index 875efcd126a2..60f1c87d5212 100644
--- a/net/smc/Makefile
+++ b/net/smc/Makefile
@@ -4,5 +4,6 @@ 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
smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o
-smc-y += smc_tracepoint.o
+smc-y += smc_tracepoint.o smc_inet.o
smc-$(CONFIG_SYSCTL) += smc_sysctl.o
+smc-$(CONFIG_SMC_LO) += smc_loopback.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 4b52b3b159c0..8e3093938cd2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -53,6 +53,8 @@
#include "smc_stats.h"
#include "smc_tracepoint.h"
#include "smc_sysctl.h"
+#include "smc_loopback.h"
+#include "smc_inet.h"
static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group
* creation on server
@@ -169,11 +171,11 @@ static bool smc_hs_congested(const struct sock *sk)
return false;
}
-static struct smc_hashinfo smc_v4_hashinfo = {
+struct smc_hashinfo smc_v4_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock),
};
-static struct smc_hashinfo smc_v6_hashinfo = {
+struct smc_hashinfo smc_v6_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock),
};
@@ -191,7 +193,6 @@ int smc_hash_sk(struct sock *sk)
return 0;
}
-EXPORT_SYMBOL_GPL(smc_hash_sk);
void smc_unhash_sk(struct sock *sk)
{
@@ -202,13 +203,12 @@ void smc_unhash_sk(struct sock *sk)
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
write_unlock_bh(&h->lock);
}
-EXPORT_SYMBOL_GPL(smc_unhash_sk);
/* This will be called before user really release sock_lock. So do the
* work which we didn't do because of user hold the sock_lock in the
* BH context
*/
-static void smc_release_cb(struct sock *sk)
+void smc_release_cb(struct sock *sk)
{
struct smc_sock *smc = smc_sk(sk);
@@ -308,7 +308,7 @@ static int __smc_release(struct smc_sock *smc)
return rc;
}
-static int smc_release(struct socket *sock)
+int smc_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -362,25 +362,15 @@ static void smc_destruct(struct sock *sk)
return;
}
-static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
- int protocol)
+void smc_sk_init(struct net *net, struct sock *sk, int protocol)
{
- struct smc_sock *smc;
- struct proto *prot;
- struct sock *sk;
-
- prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto;
- sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0);
- if (!sk)
- return NULL;
+ struct smc_sock *smc = smc_sk(sk);
- sock_init_data(sock, sk); /* sets sk_refcnt to 1 */
sk->sk_state = SMC_INIT;
sk->sk_destruct = smc_destruct;
sk->sk_protocol = protocol;
WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem));
WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem));
- smc = smc_sk(sk);
INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
INIT_WORK(&smc->connect_work, smc_connect_work);
INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
@@ -390,12 +380,30 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
sk->sk_prot->hash(sk);
mutex_init(&smc->clcsock_release_lock);
smc_init_saved_callbacks(smc);
+ smc->limit_smc_hs = net->smc.limit_smc_hs;
+ smc->use_fallback = false; /* assume rdma capability first */
+ smc->fallback_rsn = 0;
+}
+
+static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
+ int protocol)
+{
+ struct proto *prot;
+ struct sock *sk;
+
+ prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto;
+ sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0);
+ if (!sk)
+ return NULL;
+
+ sock_init_data(sock, sk); /* sets sk_refcnt to 1 */
+ smc_sk_init(net, sk, protocol);
return sk;
}
-static int smc_bind(struct socket *sock, struct sockaddr *uaddr,
- int addr_len)
+int smc_bind(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len)
{
struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
struct sock *sk = sock->sk;
@@ -460,29 +468,11 @@ out:
static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk,
unsigned long mask)
{
- struct net *nnet = sock_net(nsk);
-
nsk->sk_userlocks = osk->sk_userlocks;
- if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) {
+ if (osk->sk_userlocks & SOCK_SNDBUF_LOCK)
nsk->sk_sndbuf = osk->sk_sndbuf;
- } else {
- if (mask == SK_FLAGS_SMC_TO_CLC)
- WRITE_ONCE(nsk->sk_sndbuf,
- READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1]));
- else
- WRITE_ONCE(nsk->sk_sndbuf,
- 2 * READ_ONCE(nnet->smc.sysctl_wmem));
- }
- if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) {
+ if (osk->sk_userlocks & SOCK_RCVBUF_LOCK)
nsk->sk_rcvbuf = osk->sk_rcvbuf;
- } else {
- if (mask == SK_FLAGS_SMC_TO_CLC)
- WRITE_ONCE(nsk->sk_rcvbuf,
- READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1]));
- else
- WRITE_ONCE(nsk->sk_rcvbuf,
- 2 * READ_ONCE(nnet->smc.sysctl_rmem));
- }
}
static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
@@ -1437,6 +1427,14 @@ static int smc_connect_ism(struct smc_sock *smc,
}
smc_conn_save_peer_info(smc, aclc);
+
+ if (smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd)) {
+ rc = smcd_buf_attach(smc);
+ if (rc) {
+ rc = SMC_CLC_DECL_MEM; /* try to fallback */
+ goto connect_abort;
+ }
+ }
smc_close_init(smc);
smc_rx_init(smc);
smc_tx_init(smc);
@@ -1634,8 +1632,8 @@ out:
release_sock(&smc->sk);
}
-static int smc_connect(struct socket *sock, struct sockaddr *addr,
- int alen, int flags)
+int smc_connect(struct socket *sock, struct sockaddr *addr,
+ int alen, int flags)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -2541,6 +2539,14 @@ static void smc_listen_work(struct work_struct *work)
mutex_unlock(&smc_server_lgr_pending);
}
smc_conn_save_peer_info(new_smc, cclc);
+
+ if (ini->is_smcd &&
+ smc_ism_support_dmb_nocopy(new_smc->conn.lgr->smcd)) {
+ rc = smcd_buf_attach(new_smc);
+ if (rc)
+ goto out_decl;
+ }
+
smc_listen_out_connected(new_smc);
SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini);
goto out_free;
@@ -2608,7 +2614,7 @@ out:
read_unlock_bh(&listen_clcsock->sk_callback_lock);
}
-static int smc_listen(struct socket *sock, int backlog)
+int smc_listen(struct socket *sock, int backlog)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -2673,8 +2679,8 @@ out:
return rc;
}
-static int smc_accept(struct socket *sock, struct socket *new_sock,
- int flags, bool kern)
+int smc_accept(struct socket *sock, struct socket *new_sock,
+ struct proto_accept_arg *arg)
{
struct sock *sk = sock->sk, *nsk;
DECLARE_WAITQUEUE(wait, current);
@@ -2693,7 +2699,7 @@ static int smc_accept(struct socket *sock, struct socket *new_sock,
}
/* Wait for an incoming connection */
- timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
+ timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK);
add_wait_queue_exclusive(sk_sleep(sk), &wait);
while (!(nsk = smc_accept_dequeue(sk, new_sock))) {
set_current_state(TASK_INTERRUPTIBLE);
@@ -2720,7 +2726,7 @@ static int smc_accept(struct socket *sock, struct socket *new_sock,
if (rc)
goto out;
- if (lsmc->sockopt_defer_accept && !(flags & O_NONBLOCK)) {
+ if (lsmc->sockopt_defer_accept && !(arg->flags & O_NONBLOCK)) {
/* wait till data arrives on the socket */
timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept *
MSEC_PER_SEC);
@@ -2743,8 +2749,8 @@ out:
return rc;
}
-static int smc_getname(struct socket *sock, struct sockaddr *addr,
- int peer)
+int smc_getname(struct socket *sock, struct sockaddr *addr,
+ int peer)
{
struct smc_sock *smc;
@@ -2757,7 +2763,7 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr,
return smc->clcsock->ops->getname(smc->clcsock, addr, peer);
}
-static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -2795,8 +2801,8 @@ out:
return rc;
}
-static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
- int flags)
+int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -2845,8 +2851,8 @@ static __poll_t smc_accept_poll(struct sock *parent)
return mask;
}
-static __poll_t smc_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t smc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -2898,7 +2904,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
return mask;
}
-static int smc_shutdown(struct socket *sock, int how)
+int smc_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
bool do_shutdown = true;
@@ -3038,8 +3044,8 @@ static int __smc_setsockopt(struct socket *sock, int level, int optname,
return rc;
}
-static int smc_setsockopt(struct socket *sock, int level, int optname,
- sockptr_t optval, unsigned int optlen)
+int smc_setsockopt(struct socket *sock, int level, int optname,
+ sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -3125,8 +3131,8 @@ out:
return rc;
}
-static int smc_getsockopt(struct socket *sock, int level, int optname,
- char __user *optval, int __user *optlen)
+int smc_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen)
{
struct smc_sock *smc;
int rc;
@@ -3151,8 +3157,8 @@ static int smc_getsockopt(struct socket *sock, int level, int optname,
return rc;
}
-static int smc_ioctl(struct socket *sock, unsigned int cmd,
- unsigned long arg)
+int smc_ioctl(struct socket *sock, unsigned int cmd,
+ unsigned long arg)
{
union smc_host_cursor cons, urg;
struct smc_connection *conn;
@@ -3238,9 +3244,9 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
* Note that subsequent recv() calls have to wait till all splice() processing
* completed.
*/
-static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t len,
- unsigned int flags)
+ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -3306,6 +3312,29 @@ static const struct proto_ops smc_sock_ops = {
.splice_read = smc_splice_read,
};
+int smc_create_clcsk(struct net *net, struct sock *sk, int family)
+{
+ struct smc_sock *smc = smc_sk(sk);
+ int rc;
+
+ rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
+ &smc->clcsock);
+ if (rc)
+ return rc;
+
+ /* smc_clcsock_release() does not wait smc->clcsock->sk's
+ * destruction; its sk_state might not be TCP_CLOSE after
+ * smc->sk is close()d, and TCP timers can be fired later,
+ * which need net ref.
+ */
+ sk = smc->clcsock->sk;
+ __netns_tracker_free(net, &sk->ns_tracker, false);
+ sk->sk_net_refcnt = 1;
+ get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+ sock_inuse_add(net, 1);
+ return 0;
+}
+
static int __smc_create(struct net *net, struct socket *sock, int protocol,
int kern, struct socket *clcsock)
{
@@ -3331,35 +3360,15 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol,
/* create internal TCP socket for CLC handshake and fallback */
smc = smc_sk(sk);
- smc->use_fallback = false; /* assume rdma capability first */
- smc->fallback_rsn = 0;
-
- /* default behavior from limit_smc_hs in every net namespace */
- smc->limit_smc_hs = net->smc.limit_smc_hs;
rc = 0;
- if (!clcsock) {
- rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
- &smc->clcsock);
- if (rc) {
- sk_common_release(sk);
- goto out;
- }
-
- /* smc_clcsock_release() does not wait smc->clcsock->sk's
- * destruction; its sk_state might not be TCP_CLOSE after
- * smc->sk is close()d, and TCP timers can be fired later,
- * which need net ref.
- */
- sk = smc->clcsock->sk;
- __netns_tracker_free(net, &sk->ns_tracker, false);
- sk->sk_net_refcnt = 1;
- get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
- sock_inuse_add(net, 1);
- } else {
+ if (clcsock)
smc->clcsock = clcsock;
- }
+ else
+ rc = smc_create_clcsk(net, sk, family);
+ if (rc)
+ sk_common_release(sk);
out:
return rc;
}
@@ -3557,15 +3566,28 @@ static int __init smc_init(void)
goto out_sock;
}
- rc = tcp_register_ulp(&smc_ulp_ops);
+ rc = smc_loopback_init();
if (rc) {
- pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc);
+ pr_err("%s: smc_loopback_init fails with %d\n", __func__, rc);
goto out_ib;
}
+ rc = tcp_register_ulp(&smc_ulp_ops);
+ if (rc) {
+ pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc);
+ goto out_lo;
+ }
+ rc = smc_inet_init();
+ if (rc) {
+ pr_err("%s: smc_inet_init fails with %d\n", __func__, rc);
+ goto out_ulp;
+ }
static_branch_enable(&tcp_have_smc);
return 0;
-
+out_ulp:
+ tcp_unregister_ulp(&smc_ulp_ops);
+out_lo:
+ smc_loopback_exit();
out_ib:
smc_ib_unregister_client();
out_sock:
@@ -3600,9 +3622,11 @@ out_pernet_subsys:
static void __exit smc_exit(void)
{
static_branch_disable(&tcp_have_smc);
+ smc_inet_exit();
tcp_unregister_ulp(&smc_ulp_ops);
sock_unregister(PF_SMC);
smc_core_exit();
+ smc_loopback_exit();
smc_ib_unregister_client();
smc_ism_exit();
destroy_workqueue(smc_close_wq);
@@ -3626,4 +3650,9 @@ MODULE_DESCRIPTION("smc socket address family");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(PF_SMC);
MODULE_ALIAS_TCP_ULP("smc");
+/* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1);
+#if IS_ENABLED(CONFIG_IPV6)
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1);
+#endif /* CONFIG_IPV6 */
MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 18c8b7870198..34b781e463c4 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -34,6 +34,44 @@
extern struct proto smc_proto;
extern struct proto smc_proto6;
+extern struct smc_hashinfo smc_v4_hashinfo;
+extern struct smc_hashinfo smc_v6_hashinfo;
+
+int smc_hash_sk(struct sock *sk);
+void smc_unhash_sk(struct sock *sk);
+void smc_release_cb(struct sock *sk);
+
+int smc_release(struct socket *sock);
+int smc_bind(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len);
+int smc_connect(struct socket *sock, struct sockaddr *addr,
+ int alen, int flags);
+int smc_accept(struct socket *sock, struct socket *new_sock,
+ struct proto_accept_arg *arg);
+int smc_getname(struct socket *sock, struct sockaddr *addr,
+ int peer);
+__poll_t smc_poll(struct file *file, struct socket *sock,
+ poll_table *wait);
+int smc_ioctl(struct socket *sock, unsigned int cmd,
+ unsigned long arg);
+int smc_listen(struct socket *sock, int backlog);
+int smc_shutdown(struct socket *sock, int how);
+int smc_setsockopt(struct socket *sock, int level, int optname,
+ sockptr_t optval, unsigned int optlen);
+int smc_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen);
+int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len);
+int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags);
+ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags);
+
+/* smc sock initialization */
+void smc_sk_init(struct net *net, struct sock *sk, int protocol);
+/* clcsock initialization */
+int smc_create_clcsk(struct net *net, struct sock *sk, int family);
+
#ifdef ATOMIC64_INIT
#define KERNEL_HAS_ATOMIC64
#endif
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 3c06625ceb20..619b3bab3824 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -18,6 +18,7 @@
#include "smc_tx.h"
#include "smc_rx.h"
#include "smc_close.h"
+#include "smc_ism.h"
/********************************** send *************************************/
@@ -255,6 +256,14 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
return rc;
smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn);
conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
+
+ if (smc_ism_support_dmb_nocopy(conn->lgr->smcd))
+ /* if local sndbuf shares the same memory region with
+ * peer DMB, then don't update the tx_curs_fin
+ * and sndbuf_space until peer has consumed the data.
+ */
+ return 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);
@@ -266,7 +275,7 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
smc_curs_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn);
smc_tx_sndbuf_nonfull(smc);
- return rc;
+ return 0;
}
/********************************* receive ***********************************/
@@ -323,7 +332,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
{
union smc_host_cursor cons_old, prod_old;
struct smc_connection *conn = &smc->conn;
- int diff_cons, diff_prod;
+ int diff_cons, diff_prod, diff_tx;
smc_curs_copy(&prod_old, &conn->local_rx_ctrl.prod, conn);
smc_curs_copy(&cons_old, &conn->local_rx_ctrl.cons, conn);
@@ -339,6 +348,29 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
atomic_add(diff_cons, &conn->peer_rmbe_space);
/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
smp_mb__after_atomic();
+
+ /* if local sndbuf shares the same memory region with
+ * peer RMB, then update tx_curs_fin and sndbuf_space
+ * here since peer has already consumed the data.
+ */
+ if (conn->lgr->is_smcd &&
+ smc_ism_support_dmb_nocopy(conn->lgr->smcd)) {
+ /* Calculate consumed data and
+ * increment free send buffer space.
+ */
+ diff_tx = smc_curs_diff(conn->sndbuf_desc->len,
+ &conn->tx_curs_fin,
+ &conn->local_rx_ctrl.cons);
+ /* increase local sndbuf space and fin_curs */
+ smp_mb__before_atomic();
+ atomic_add(diff_tx, &conn->sndbuf_space);
+ /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+ smp_mb__after_atomic();
+ smc_curs_copy(&conn->tx_curs_fin,
+ &conn->local_rx_ctrl.cons, conn);
+
+ smc_tx_sndbuf_nonfull(smc);
+ }
}
diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index e55026c7529c..33fa787c28eb 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -853,8 +853,10 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
pclc_smcd = &pclc->pclc_smcd;
pclc_prfx = &pclc->pclc_prfx;
ipv6_prfx = pclc->pclc_prfx_ipv6;
- v2_ext = &pclc->pclc_v2_ext;
- smcd_v2_ext = &pclc->pclc_smcd_v2_ext;
+ v2_ext = container_of(&pclc->pclc_v2_ext,
+ struct smc_clc_v2_extension, fixed);
+ smcd_v2_ext = container_of(&pclc->pclc_smcd_v2_ext,
+ struct smc_clc_smcd_v2_extension, fixed);
gidchids = pclc->pclc_gidchids;
trl = &pclc->pclc_trl;
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 7cc7070b9772..467effb50cd6 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -134,12 +134,15 @@ struct smc_clc_smcd_gid_chid {
*/
struct smc_clc_v2_extension {
- struct smc_clnt_opts_area_hdr hdr;
- u8 roce[16]; /* RoCEv2 GID */
- u8 max_conns;
- u8 max_links;
- __be16 feature_mask;
- u8 reserved[12];
+ /* New members must be added within the struct_group() macro below. */
+ struct_group_tagged(smc_clc_v2_extension_fixed, fixed,
+ struct smc_clnt_opts_area_hdr hdr;
+ u8 roce[16]; /* RoCEv2 GID */
+ u8 max_conns;
+ u8 max_links;
+ __be16 feature_mask;
+ u8 reserved[12];
+ );
u8 user_eids[][SMC_MAX_EID_LEN];
};
@@ -159,8 +162,11 @@ struct smc_clc_msg_smcd { /* SMC-D GID information */
};
struct smc_clc_smcd_v2_extension {
- u8 system_eid[SMC_MAX_EID_LEN];
- u8 reserved[16];
+ /* New members must be added within the struct_group() macro below. */
+ struct_group_tagged(smc_clc_smcd_v2_extension_fixed, fixed,
+ u8 system_eid[SMC_MAX_EID_LEN];
+ u8 reserved[16];
+ );
struct smc_clc_smcd_gid_chid gidchid[];
};
@@ -183,9 +189,9 @@ struct smc_clc_msg_proposal_area {
struct smc_clc_msg_smcd pclc_smcd;
struct smc_clc_msg_proposal_prefix pclc_prfx;
struct smc_clc_ipv6_prefix pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX];
- struct smc_clc_v2_extension pclc_v2_ext;
+ struct smc_clc_v2_extension_fixed pclc_v2_ext;
u8 user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN];
- struct smc_clc_smcd_v2_extension pclc_smcd_v2_ext;
+ struct smc_clc_smcd_v2_extension_fixed pclc_smcd_v2_ext;
struct smc_clc_smcd_gid_chid
pclc_gidchids[SMCD_CLC_MAX_V2_GID_ENTRIES];
struct smc_clc_msg_trail pclc_trl;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 9b84d5897aa5..3b95828d9976 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1149,6 +1149,20 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
}
}
+static void smcd_buf_detach(struct smc_connection *conn)
+{
+ struct smcd_dev *smcd = conn->lgr->smcd;
+ u64 peer_token = conn->peer_token;
+
+ if (!conn->sndbuf_desc)
+ return;
+
+ smc_ism_detach_dmb(smcd, peer_token);
+
+ kfree(conn->sndbuf_desc);
+ conn->sndbuf_desc = NULL;
+}
+
static void smc_buf_unuse(struct smc_connection *conn,
struct smc_link_group *lgr)
{
@@ -1192,6 +1206,8 @@ void smc_conn_free(struct smc_connection *conn)
if (lgr->is_smcd) {
if (!list_empty(&lgr->list))
smc_ism_unset_conn(conn);
+ if (smc_ism_support_dmb_nocopy(lgr->smcd))
+ smcd_buf_detach(conn);
tasklet_kill(&conn->rx_tsklet);
} else {
smc_cdc_wait_pend_tx_wr(conn);
@@ -1445,6 +1461,8 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft)
smc_sk_wake_ups(smc);
if (conn->lgr->is_smcd) {
smc_ism_unset_conn(conn);
+ if (smc_ism_support_dmb_nocopy(conn->lgr->smcd))
+ smcd_buf_detach(conn);
if (soft)
tasklet_kill(&conn->rx_tsklet);
else
@@ -1988,7 +2006,7 @@ out:
}
#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */
-#define SMCR_RMBE_SIZES 5 /* 0 -> 16KB, 1 -> 32KB, .. 5 -> 512KB */
+#define SMCR_RMBE_SIZES 15 /* 0 -> 16KB, 1 -> 32KB, .. 15 -> 512MB */
/* convert the RMB size into the compressed notation (minimum 16K, see
* SMCD/R_DMBE_SIZES.
@@ -1997,7 +2015,6 @@ out:
*/
static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb)
{
- const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE;
u8 compressed;
if (size <= SMC_BUF_MIN_SIZE)
@@ -2007,9 +2024,11 @@ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb)
compressed = min_t(u8, ilog2(size) + 1,
is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES);
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
if (!is_smcd && is_rmb)
/* RMBs are backed by & limited to max size of scatterlists */
- compressed = min_t(u8, compressed, ilog2(max_scat >> 14));
+ compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14));
+#endif
return compressed;
}
@@ -2464,12 +2483,18 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd)
int rc;
/* create send buffer */
+ if (is_smcd &&
+ smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd))
+ goto create_rmb;
+
rc = __smc_buf_create(smc, is_smcd, false);
if (rc)
return rc;
+
+create_rmb:
/* create rmb */
rc = __smc_buf_create(smc, is_smcd, true);
- if (rc) {
+ if (rc && smc->conn.sndbuf_desc) {
down_write(&smc->conn.lgr->sndbufs_lock);
list_del(&smc->conn.sndbuf_desc->list);
up_write(&smc->conn.lgr->sndbufs_lock);
@@ -2479,6 +2504,41 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd)
return rc;
}
+int smcd_buf_attach(struct smc_sock *smc)
+{
+ struct smc_connection *conn = &smc->conn;
+ struct smcd_dev *smcd = conn->lgr->smcd;
+ u64 peer_token = conn->peer_token;
+ struct smc_buf_desc *buf_desc;
+ int rc;
+
+ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL);
+ if (!buf_desc)
+ return -ENOMEM;
+
+ /* The ghost sndbuf_desc describes the same memory region as
+ * peer RMB. Its lifecycle is consistent with the connection's
+ * and it will be freed with the connections instead of the
+ * link group.
+ */
+ rc = smc_ism_attach_dmb(smcd, peer_token, buf_desc);
+ if (rc)
+ goto free;
+
+ smc->sk.sk_sndbuf = buf_desc->len;
+ buf_desc->cpu_addr =
+ (u8 *)buf_desc->cpu_addr + sizeof(struct smcd_cdc_msg);
+ buf_desc->len -= sizeof(struct smcd_cdc_msg);
+ conn->sndbuf_desc = buf_desc;
+ conn->sndbuf_desc->used = 1;
+ atomic_set(&conn->sndbuf_space, conn->sndbuf_desc->len);
+ return 0;
+
+free:
+ kfree(buf_desc);
+ return rc;
+}
+
static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr)
{
int i;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 1f175376037b..d93cf51dbd7c 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -557,6 +557,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid,
void smc_smcd_terminate_all(struct smcd_dev *dev);
void smc_smcr_terminate_all(struct smc_ib_device *smcibdev);
int smc_buf_create(struct smc_sock *smc, bool is_smcd);
+int smcd_buf_attach(struct smc_sock *smc);
int smc_uncompress_bufsize(u8 compressed);
int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *link,
struct smc_clc_msg_accept_confirm *clc);
diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c
new file mode 100644
index 000000000000..bece346dd8e9
--- /dev/null
+++ b/net/smc/smc_inet.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Definitions for the IPPROTO_SMC (socket related)
+ *
+ * Copyright IBM Corp. 2016, 2018
+ * Copyright (c) 2024, Alibaba Inc.
+ *
+ * Author: D. Wythe <alibuda@linux.alibaba.com>
+ */
+
+#include <net/protocol.h>
+#include <net/sock.h>
+
+#include "smc_inet.h"
+#include "smc.h"
+
+static int smc_inet_init_sock(struct sock *sk);
+
+static struct proto smc_inet_prot = {
+ .name = "INET_SMC",
+ .owner = THIS_MODULE,
+ .init = smc_inet_init_sock,
+ .hash = smc_hash_sk,
+ .unhash = smc_unhash_sk,
+ .release_cb = smc_release_cb,
+ .obj_size = sizeof(struct smc_sock),
+ .h.smc_hash = &smc_v4_hashinfo,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
+};
+
+static const struct proto_ops smc_inet_stream_ops = {
+ .family = PF_INET,
+ .owner = THIS_MODULE,
+ .release = smc_release,
+ .bind = smc_bind,
+ .connect = smc_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = smc_accept,
+ .getname = smc_getname,
+ .poll = smc_poll,
+ .ioctl = smc_ioctl,
+ .listen = smc_listen,
+ .shutdown = smc_shutdown,
+ .setsockopt = smc_setsockopt,
+ .getsockopt = smc_getsockopt,
+ .sendmsg = smc_sendmsg,
+ .recvmsg = smc_recvmsg,
+ .mmap = sock_no_mmap,
+ .splice_read = smc_splice_read,
+};
+
+static struct inet_protosw smc_inet_protosw = {
+ .type = SOCK_STREAM,
+ .protocol = IPPROTO_SMC,
+ .prot = &smc_inet_prot,
+ .ops = &smc_inet_stream_ops,
+ .flags = INET_PROTOSW_ICSK,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static struct proto smc_inet6_prot = {
+ .name = "INET6_SMC",
+ .owner = THIS_MODULE,
+ .init = smc_inet_init_sock,
+ .hash = smc_hash_sk,
+ .unhash = smc_unhash_sk,
+ .release_cb = smc_release_cb,
+ .obj_size = sizeof(struct smc_sock),
+ .h.smc_hash = &smc_v6_hashinfo,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
+};
+
+static const struct proto_ops smc_inet6_stream_ops = {
+ .family = PF_INET6,
+ .owner = THIS_MODULE,
+ .release = smc_release,
+ .bind = smc_bind,
+ .connect = smc_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = smc_accept,
+ .getname = smc_getname,
+ .poll = smc_poll,
+ .ioctl = smc_ioctl,
+ .listen = smc_listen,
+ .shutdown = smc_shutdown,
+ .setsockopt = smc_setsockopt,
+ .getsockopt = smc_getsockopt,
+ .sendmsg = smc_sendmsg,
+ .recvmsg = smc_recvmsg,
+ .mmap = sock_no_mmap,
+ .splice_read = smc_splice_read,
+};
+
+static struct inet_protosw smc_inet6_protosw = {
+ .type = SOCK_STREAM,
+ .protocol = IPPROTO_SMC,
+ .prot = &smc_inet6_prot,
+ .ops = &smc_inet6_stream_ops,
+ .flags = INET_PROTOSW_ICSK,
+};
+#endif /* CONFIG_IPV6 */
+
+static int smc_inet_init_sock(struct sock *sk)
+{
+ struct net *net = sock_net(sk);
+
+ /* init common smc sock */
+ smc_sk_init(net, sk, IPPROTO_SMC);
+ /* create clcsock */
+ return smc_create_clcsk(net, sk, sk->sk_family);
+}
+
+int __init smc_inet_init(void)
+{
+ int rc;
+
+ rc = proto_register(&smc_inet_prot, 1);
+ if (rc) {
+ pr_err("%s: proto_register smc_inet_prot fails with %d\n",
+ __func__, rc);
+ return rc;
+ }
+ /* no return value */
+ inet_register_protosw(&smc_inet_protosw);
+
+#if IS_ENABLED(CONFIG_IPV6)
+ rc = proto_register(&smc_inet6_prot, 1);
+ if (rc) {
+ pr_err("%s: proto_register smc_inet6_prot fails with %d\n",
+ __func__, rc);
+ goto out_inet6_prot;
+ }
+ rc = inet6_register_protosw(&smc_inet6_protosw);
+ if (rc) {
+ pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n",
+ __func__, rc);
+ goto out_inet6_protosw;
+ }
+ return rc;
+out_inet6_protosw:
+ proto_unregister(&smc_inet6_prot);
+out_inet6_prot:
+ inet_unregister_protosw(&smc_inet_protosw);
+ proto_unregister(&smc_inet_prot);
+#endif /* CONFIG_IPV6 */
+ return rc;
+}
+
+void smc_inet_exit(void)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ inet6_unregister_protosw(&smc_inet6_protosw);
+ proto_unregister(&smc_inet6_prot);
+#endif /* CONFIG_IPV6 */
+ inet_unregister_protosw(&smc_inet_protosw);
+ proto_unregister(&smc_inet_prot);
+}
diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h
new file mode 100644
index 000000000000..a489c8a2b8ef
--- /dev/null
+++ b/net/smc/smc_inet.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Definitions for the IPPROTO_SMC (socket related)
+
+ * Copyright IBM Corp. 2016
+ * Copyright (c) 2024, Alibaba Inc.
+ *
+ * Author: D. Wythe <alibuda@linux.alibaba.com>
+ */
+#ifndef __INET_SMC
+#define __INET_SMC
+
+/* Initialize protocol registration on IPPROTO_SMC,
+ * @return 0 on success
+ */
+int smc_inet_init(void);
+
+void smc_inet_exit(void);
+
+#endif /* __INET_SMC */
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index ac88de2a06a0..84f98e18c7db 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -91,6 +91,11 @@ bool smc_ism_is_v2_capable(void)
return smc_ism_v2_capable;
}
+void smc_ism_set_v2_capable(void)
+{
+ smc_ism_v2_capable = true;
+}
+
/* Set a connection using this DMBE. */
void smc_ism_set_conn(struct smc_connection *conn)
{
@@ -126,6 +131,8 @@ int smc_ism_get_vlan(struct smcd_dev *smcd, unsigned short vlanid)
if (!vlanid) /* No valid vlan id */
return -EINVAL;
+ if (!smcd->ops->add_vlan_id)
+ return -EOPNOTSUPP;
/* create new vlan entry, in case we need it */
new_vlan = kzalloc(sizeof(*new_vlan), GFP_KERNEL);
@@ -171,6 +178,8 @@ int smc_ism_put_vlan(struct smcd_dev *smcd, unsigned short vlanid)
if (!vlanid) /* No valid vlan id */
return -EINVAL;
+ if (!smcd->ops->del_vlan_id)
+ return -EOPNOTSUPP;
spin_lock_irqsave(&smcd->lock, flags);
list_for_each_entry(vlan, &smcd->vlan, list) {
@@ -222,7 +231,6 @@ int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc)
int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
struct smc_buf_desc *dmb_desc)
{
-#if IS_ENABLED(CONFIG_ISM)
struct smcd_dmb dmb;
int rc;
@@ -231,7 +239,7 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
dmb.sba_idx = dmb_desc->sba_idx;
dmb.vlan_id = lgr->vlan_id;
dmb.rgid = lgr->peer_gid.gid;
- rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb, &smc_ism_client);
+ rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb, lgr->smcd->client);
if (!rc) {
dmb_desc->sba_idx = dmb.sba_idx;
dmb_desc->token = dmb.dmb_tok;
@@ -240,9 +248,46 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
dmb_desc->len = dmb.dmb_len;
}
return rc;
-#else
- return 0;
-#endif
+}
+
+bool smc_ism_support_dmb_nocopy(struct smcd_dev *smcd)
+{
+ /* for now only loopback-ism supports
+ * merging sndbuf with peer DMB to avoid
+ * data copies between them.
+ */
+ return (smcd->ops->support_dmb_nocopy &&
+ smcd->ops->support_dmb_nocopy(smcd));
+}
+
+int smc_ism_attach_dmb(struct smcd_dev *dev, u64 token,
+ struct smc_buf_desc *dmb_desc)
+{
+ struct smcd_dmb dmb;
+ int rc = 0;
+
+ if (!dev->ops->attach_dmb)
+ return -EINVAL;
+
+ memset(&dmb, 0, sizeof(dmb));
+ dmb.dmb_tok = token;
+ rc = dev->ops->attach_dmb(dev, &dmb);
+ if (!rc) {
+ dmb_desc->sba_idx = dmb.sba_idx;
+ dmb_desc->token = dmb.dmb_tok;
+ dmb_desc->cpu_addr = dmb.cpu_addr;
+ dmb_desc->dma_addr = dmb.dma_addr;
+ dmb_desc->len = dmb.dmb_len;
+ }
+ return rc;
+}
+
+int smc_ism_detach_dmb(struct smcd_dev *dev, u64 token)
+{
+ if (!dev->ops->detach_dmb)
+ return -EINVAL;
+
+ return dev->ops->detach_dmb(dev, token);
}
static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd,
@@ -322,6 +367,8 @@ static void smc_nl_prep_smcd_dev(struct smcd_dev_list *dev_list,
list_for_each_entry(smcd, &dev_list->list, list) {
if (num < snum)
goto next;
+ if (smc_ism_is_loopback(smcd))
+ goto next;
if (smc_nl_handle_smcd_dev(smcd, skb, cb))
goto errout;
next:
@@ -372,7 +419,8 @@ static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
smc_smcd_terminate(wrk->smcd, &peer_gid, ev_info.vlan_id);
break;
case ISM_EVENT_CODE_TESTLINK: /* Activity timer */
- if (ev_info.code == ISM_EVENT_REQUEST) {
+ if (ev_info.code == ISM_EVENT_REQUEST &&
+ wrk->smcd->ops->signal_event) {
ev_info.code = ISM_EVENT_RESPONSE;
wrk->smcd->ops->signal_event(wrk->smcd,
&peer_gid,
@@ -436,7 +484,7 @@ static struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
static void smcd_register_dev(struct ism_dev *ism)
{
const struct smcd_ops *ops = ism_get_smcd_ops();
- struct smcd_dev *smcd;
+ struct smcd_dev *smcd, *fentry;
if (!ops)
return;
@@ -446,20 +494,28 @@ static void smcd_register_dev(struct ism_dev *ism)
if (!smcd)
return;
smcd->priv = ism;
+ smcd->client = &smc_ism_client;
ism_set_priv(ism, &smc_ism_client, smcd);
if (smc_pnetid_by_dev_port(&ism->pdev->dev, 0, smcd->pnetid))
smc_pnetid_by_table_smcd(smcd);
+ if (smcd->ops->supports_v2())
+ smc_ism_set_v2_capable();
mutex_lock(&smcd_dev_list.mutex);
- if (list_empty(&smcd_dev_list.list)) {
- if (smcd->ops->supports_v2())
- smc_ism_v2_capable = true;
- }
- /* sort list: devices without pnetid before devices with pnetid */
- if (smcd->pnetid[0])
+ /* sort list:
+ * - devices without pnetid before devices with pnetid;
+ * - loopback-ism always at the very beginning;
+ */
+ if (!smcd->pnetid[0]) {
+ fentry = list_first_entry_or_null(&smcd_dev_list.list,
+ struct smcd_dev, list);
+ if (fentry && smc_ism_is_loopback(fentry))
+ list_add(&smcd->list, &fentry->list);
+ else
+ list_add(&smcd->list, &smcd_dev_list.list);
+ } else {
list_add_tail(&smcd->list, &smcd_dev_list.list);
- else
- list_add(&smcd->list, &smcd_dev_list.list);
+ }
mutex_unlock(&smcd_dev_list.mutex);
pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n",
@@ -541,6 +597,8 @@ int smc_ism_signal_shutdown(struct smc_link_group *lgr)
if (lgr->peer_shutdown)
return 0;
+ if (!lgr->smcd->ops->signal_event)
+ return 0;
memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE);
ev_info.vlan_id = lgr->vlan_id;
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index 165cd013404b..6763133dd8d0 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -48,10 +48,15 @@ int smc_ism_put_vlan(struct smcd_dev *dev, unsigned short vlan_id);
int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size,
struct smc_buf_desc *dmb_desc);
int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
+bool smc_ism_support_dmb_nocopy(struct smcd_dev *smcd);
+int smc_ism_attach_dmb(struct smcd_dev *dev, u64 token,
+ struct smc_buf_desc *dmb_desc);
+int smc_ism_detach_dmb(struct smcd_dev *dev, u64 token);
int smc_ism_signal_shutdown(struct smc_link_group *lgr);
void smc_ism_get_system_eid(u8 **eid);
u16 smc_ism_get_chid(struct smcd_dev *dev);
bool smc_ism_is_v2_capable(void);
+void smc_ism_set_v2_capable(void);
int smc_ism_init(void);
void smc_ism_exit(void);
int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
@@ -84,4 +89,9 @@ static inline bool smc_ism_is_emulated(struct smcd_dev *smcd)
return __smc_ism_is_emulated(chid);
}
+static inline bool smc_ism_is_loopback(struct smcd_dev *smcd)
+{
+ return (smcd->ops->get_chid(smcd) == 0xFFFF);
+}
+
#endif
diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c
new file mode 100644
index 000000000000..3c5f64ca4115
--- /dev/null
+++ b/net/smc/smc_loopback.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared Memory Communications Direct over loopback-ism device.
+ *
+ * Functions for loopback-ism device.
+ *
+ * Copyright (c) 2024, Alibaba Inc.
+ *
+ * Author: Wen Gu <guwen@linux.alibaba.com>
+ * Tony Lu <tonylu@linux.alibaba.com>
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/types.h>
+#include <net/smc.h>
+
+#include "smc_cdc.h"
+#include "smc_ism.h"
+#include "smc_loopback.h"
+
+#define SMC_LO_V2_CAPABLE 0x1 /* loopback-ism acts as ISMv2 */
+#define SMC_LO_SUPPORT_NOCOPY 0x1
+#define SMC_DMA_ADDR_INVALID (~(dma_addr_t)0)
+
+static const char smc_lo_dev_name[] = "loopback-ism";
+static struct smc_lo_dev *lo_dev;
+
+static void smc_lo_generate_ids(struct smc_lo_dev *ldev)
+{
+ struct smcd_gid *lgid = &ldev->local_gid;
+ uuid_t uuid;
+
+ uuid_gen(&uuid);
+ memcpy(&lgid->gid, &uuid, sizeof(lgid->gid));
+ memcpy(&lgid->gid_ext, (u8 *)&uuid + sizeof(lgid->gid),
+ sizeof(lgid->gid_ext));
+
+ ldev->chid = SMC_LO_RESERVED_CHID;
+}
+
+static int smc_lo_query_rgid(struct smcd_dev *smcd, struct smcd_gid *rgid,
+ u32 vid_valid, u32 vid)
+{
+ struct smc_lo_dev *ldev = smcd->priv;
+
+ /* rgid should be the same as lgid */
+ if (!ldev || rgid->gid != ldev->local_gid.gid ||
+ rgid->gid_ext != ldev->local_gid.gid_ext)
+ return -ENETUNREACH;
+ return 0;
+}
+
+static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb,
+ void *client_priv)
+{
+ struct smc_lo_dmb_node *dmb_node, *tmp_node;
+ struct smc_lo_dev *ldev = smcd->priv;
+ int sba_idx, rc;
+
+ /* check space for new dmb */
+ for_each_clear_bit(sba_idx, ldev->sba_idx_mask, SMC_LO_MAX_DMBS) {
+ if (!test_and_set_bit(sba_idx, ldev->sba_idx_mask))
+ break;
+ }
+ if (sba_idx == SMC_LO_MAX_DMBS)
+ return -ENOSPC;
+
+ dmb_node = kzalloc(sizeof(*dmb_node), GFP_KERNEL);
+ if (!dmb_node) {
+ rc = -ENOMEM;
+ goto err_bit;
+ }
+
+ dmb_node->sba_idx = sba_idx;
+ dmb_node->len = dmb->dmb_len;
+ dmb_node->cpu_addr = kzalloc(dmb_node->len, GFP_KERNEL |
+ __GFP_NOWARN | __GFP_NORETRY |
+ __GFP_NOMEMALLOC);
+ if (!dmb_node->cpu_addr) {
+ rc = -ENOMEM;
+ goto err_node;
+ }
+ dmb_node->dma_addr = SMC_DMA_ADDR_INVALID;
+ refcount_set(&dmb_node->refcnt, 1);
+
+again:
+ /* add new dmb into hash table */
+ get_random_bytes(&dmb_node->token, sizeof(dmb_node->token));
+ write_lock_bh(&ldev->dmb_ht_lock);
+ hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_node->token) {
+ if (tmp_node->token == dmb_node->token) {
+ write_unlock_bh(&ldev->dmb_ht_lock);
+ goto again;
+ }
+ }
+ hash_add(ldev->dmb_ht, &dmb_node->list, dmb_node->token);
+ write_unlock_bh(&ldev->dmb_ht_lock);
+ atomic_inc(&ldev->dmb_cnt);
+
+ dmb->sba_idx = dmb_node->sba_idx;
+ dmb->dmb_tok = dmb_node->token;
+ dmb->cpu_addr = dmb_node->cpu_addr;
+ dmb->dma_addr = dmb_node->dma_addr;
+ dmb->dmb_len = dmb_node->len;
+
+ return 0;
+
+err_node:
+ kfree(dmb_node);
+err_bit:
+ clear_bit(sba_idx, ldev->sba_idx_mask);
+ return rc;
+}
+
+static void __smc_lo_unregister_dmb(struct smc_lo_dev *ldev,
+ struct smc_lo_dmb_node *dmb_node)
+{
+ /* remove dmb from hash table */
+ write_lock_bh(&ldev->dmb_ht_lock);
+ hash_del(&dmb_node->list);
+ write_unlock_bh(&ldev->dmb_ht_lock);
+
+ clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask);
+ kvfree(dmb_node->cpu_addr);
+ kfree(dmb_node);
+
+ if (atomic_dec_and_test(&ldev->dmb_cnt))
+ wake_up(&ldev->ldev_release);
+}
+
+static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+ struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node;
+ struct smc_lo_dev *ldev = smcd->priv;
+
+ /* find dmb from hash table */
+ read_lock_bh(&ldev->dmb_ht_lock);
+ hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) {
+ if (tmp_node->token == dmb->dmb_tok) {
+ dmb_node = tmp_node;
+ break;
+ }
+ }
+ if (!dmb_node) {
+ read_unlock_bh(&ldev->dmb_ht_lock);
+ return -EINVAL;
+ }
+ read_unlock_bh(&ldev->dmb_ht_lock);
+
+ if (refcount_dec_and_test(&dmb_node->refcnt))
+ __smc_lo_unregister_dmb(ldev, dmb_node);
+ return 0;
+}
+
+static int smc_lo_support_dmb_nocopy(struct smcd_dev *smcd)
+{
+ return SMC_LO_SUPPORT_NOCOPY;
+}
+
+static int smc_lo_attach_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+ struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node;
+ struct smc_lo_dev *ldev = smcd->priv;
+
+ /* find dmb_node according to dmb->dmb_tok */
+ read_lock_bh(&ldev->dmb_ht_lock);
+ hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) {
+ if (tmp_node->token == dmb->dmb_tok) {
+ dmb_node = tmp_node;
+ break;
+ }
+ }
+ if (!dmb_node) {
+ read_unlock_bh(&ldev->dmb_ht_lock);
+ return -EINVAL;
+ }
+ read_unlock_bh(&ldev->dmb_ht_lock);
+
+ if (!refcount_inc_not_zero(&dmb_node->refcnt))
+ /* the dmb is being unregistered, but has
+ * not been removed from the hash table.
+ */
+ return -EINVAL;
+
+ /* provide dmb information */
+ dmb->sba_idx = dmb_node->sba_idx;
+ dmb->dmb_tok = dmb_node->token;
+ dmb->cpu_addr = dmb_node->cpu_addr;
+ dmb->dma_addr = dmb_node->dma_addr;
+ dmb->dmb_len = dmb_node->len;
+ return 0;
+}
+
+static int smc_lo_detach_dmb(struct smcd_dev *smcd, u64 token)
+{
+ struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node;
+ struct smc_lo_dev *ldev = smcd->priv;
+
+ /* find dmb_node according to dmb->dmb_tok */
+ read_lock_bh(&ldev->dmb_ht_lock);
+ hash_for_each_possible(ldev->dmb_ht, tmp_node, list, token) {
+ if (tmp_node->token == token) {
+ dmb_node = tmp_node;
+ break;
+ }
+ }
+ if (!dmb_node) {
+ read_unlock_bh(&ldev->dmb_ht_lock);
+ return -EINVAL;
+ }
+ read_unlock_bh(&ldev->dmb_ht_lock);
+
+ if (refcount_dec_and_test(&dmb_node->refcnt))
+ __smc_lo_unregister_dmb(ldev, dmb_node);
+ return 0;
+}
+
+static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok,
+ unsigned int idx, bool sf, unsigned int offset,
+ void *data, unsigned int size)
+{
+ struct smc_lo_dmb_node *rmb_node = NULL, *tmp_node;
+ struct smc_lo_dev *ldev = smcd->priv;
+ struct smc_connection *conn;
+
+ if (!sf)
+ /* since sndbuf is merged with peer DMB, there is
+ * no need to copy data from sndbuf to peer DMB.
+ */
+ return 0;
+
+ read_lock_bh(&ldev->dmb_ht_lock);
+ hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_tok) {
+ if (tmp_node->token == dmb_tok) {
+ rmb_node = tmp_node;
+ break;
+ }
+ }
+ if (!rmb_node) {
+ read_unlock_bh(&ldev->dmb_ht_lock);
+ return -EINVAL;
+ }
+ memcpy((char *)rmb_node->cpu_addr + offset, data, size);
+ read_unlock_bh(&ldev->dmb_ht_lock);
+
+ conn = smcd->conn[rmb_node->sba_idx];
+ if (!conn || conn->killed)
+ return -EPIPE;
+ tasklet_schedule(&conn->rx_tsklet);
+ return 0;
+}
+
+static int smc_lo_supports_v2(void)
+{
+ return SMC_LO_V2_CAPABLE;
+}
+
+static void smc_lo_get_local_gid(struct smcd_dev *smcd,
+ struct smcd_gid *smcd_gid)
+{
+ struct smc_lo_dev *ldev = smcd->priv;
+
+ smcd_gid->gid = ldev->local_gid.gid;
+ smcd_gid->gid_ext = ldev->local_gid.gid_ext;
+}
+
+static u16 smc_lo_get_chid(struct smcd_dev *smcd)
+{
+ return ((struct smc_lo_dev *)smcd->priv)->chid;
+}
+
+static struct device *smc_lo_get_dev(struct smcd_dev *smcd)
+{
+ return &((struct smc_lo_dev *)smcd->priv)->dev;
+}
+
+static const struct smcd_ops lo_ops = {
+ .query_remote_gid = smc_lo_query_rgid,
+ .register_dmb = smc_lo_register_dmb,
+ .unregister_dmb = smc_lo_unregister_dmb,
+ .support_dmb_nocopy = smc_lo_support_dmb_nocopy,
+ .attach_dmb = smc_lo_attach_dmb,
+ .detach_dmb = smc_lo_detach_dmb,
+ .add_vlan_id = NULL,
+ .del_vlan_id = NULL,
+ .set_vlan_required = NULL,
+ .reset_vlan_required = NULL,
+ .signal_event = NULL,
+ .move_data = smc_lo_move_data,
+ .supports_v2 = smc_lo_supports_v2,
+ .get_local_gid = smc_lo_get_local_gid,
+ .get_chid = smc_lo_get_chid,
+ .get_dev = smc_lo_get_dev,
+};
+
+static struct smcd_dev *smcd_lo_alloc_dev(const struct smcd_ops *ops,
+ int max_dmbs)
+{
+ struct smcd_dev *smcd;
+
+ smcd = kzalloc(sizeof(*smcd), GFP_KERNEL);
+ if (!smcd)
+ return NULL;
+
+ smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *),
+ GFP_KERNEL);
+ if (!smcd->conn)
+ goto out_smcd;
+
+ smcd->ops = ops;
+
+ spin_lock_init(&smcd->lock);
+ spin_lock_init(&smcd->lgr_lock);
+ INIT_LIST_HEAD(&smcd->vlan);
+ INIT_LIST_HEAD(&smcd->lgr_list);
+ init_waitqueue_head(&smcd->lgrs_deleted);
+ return smcd;
+
+out_smcd:
+ kfree(smcd);
+ return NULL;
+}
+
+static int smcd_lo_register_dev(struct smc_lo_dev *ldev)
+{
+ struct smcd_dev *smcd;
+
+ smcd = smcd_lo_alloc_dev(&lo_ops, SMC_LO_MAX_DMBS);
+ if (!smcd)
+ return -ENOMEM;
+ ldev->smcd = smcd;
+ smcd->priv = ldev;
+ smc_ism_set_v2_capable();
+ mutex_lock(&smcd_dev_list.mutex);
+ list_add(&smcd->list, &smcd_dev_list.list);
+ mutex_unlock(&smcd_dev_list.mutex);
+ pr_warn_ratelimited("smc: adding smcd device %s\n",
+ dev_name(&ldev->dev));
+ return 0;
+}
+
+static void smcd_lo_unregister_dev(struct smc_lo_dev *ldev)
+{
+ struct smcd_dev *smcd = ldev->smcd;
+
+ pr_warn_ratelimited("smc: removing smcd device %s\n",
+ dev_name(&ldev->dev));
+ smcd->going_away = 1;
+ smc_smcd_terminate_all(smcd);
+ mutex_lock(&smcd_dev_list.mutex);
+ list_del_init(&smcd->list);
+ mutex_unlock(&smcd_dev_list.mutex);
+ kfree(smcd->conn);
+ kfree(smcd);
+}
+
+static int smc_lo_dev_init(struct smc_lo_dev *ldev)
+{
+ smc_lo_generate_ids(ldev);
+ rwlock_init(&ldev->dmb_ht_lock);
+ hash_init(ldev->dmb_ht);
+ atomic_set(&ldev->dmb_cnt, 0);
+ init_waitqueue_head(&ldev->ldev_release);
+
+ return smcd_lo_register_dev(ldev);
+}
+
+static void smc_lo_dev_exit(struct smc_lo_dev *ldev)
+{
+ smcd_lo_unregister_dev(ldev);
+ if (atomic_read(&ldev->dmb_cnt))
+ wait_event(ldev->ldev_release, !atomic_read(&ldev->dmb_cnt));
+}
+
+static void smc_lo_dev_release(struct device *dev)
+{
+ struct smc_lo_dev *ldev =
+ container_of(dev, struct smc_lo_dev, dev);
+
+ kfree(ldev);
+}
+
+static int smc_lo_dev_probe(void)
+{
+ struct smc_lo_dev *ldev;
+ int ret;
+
+ ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
+ if (!ldev)
+ return -ENOMEM;
+
+ ldev->dev.parent = NULL;
+ ldev->dev.release = smc_lo_dev_release;
+ device_initialize(&ldev->dev);
+ dev_set_name(&ldev->dev, smc_lo_dev_name);
+
+ ret = smc_lo_dev_init(ldev);
+ if (ret)
+ goto free_dev;
+
+ lo_dev = ldev; /* global loopback device */
+ return 0;
+
+free_dev:
+ put_device(&ldev->dev);
+ return ret;
+}
+
+static void smc_lo_dev_remove(void)
+{
+ if (!lo_dev)
+ return;
+
+ smc_lo_dev_exit(lo_dev);
+ put_device(&lo_dev->dev); /* device_initialize in smc_lo_dev_probe */
+}
+
+int smc_loopback_init(void)
+{
+ return smc_lo_dev_probe();
+}
+
+void smc_loopback_exit(void)
+{
+ smc_lo_dev_remove();
+}
diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h
new file mode 100644
index 000000000000..6dd4292dae56
--- /dev/null
+++ b/net/smc/smc_loopback.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications Direct over loopback-ism device.
+ *
+ * SMC-D loopback-ism device structure definitions.
+ *
+ * Copyright (c) 2024, Alibaba Inc.
+ *
+ * Author: Wen Gu <guwen@linux.alibaba.com>
+ * Tony Lu <tonylu@linux.alibaba.com>
+ *
+ */
+
+#ifndef _SMC_LOOPBACK_H
+#define _SMC_LOOPBACK_H
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <net/smc.h>
+
+#if IS_ENABLED(CONFIG_SMC_LO)
+#define SMC_LO_MAX_DMBS 5000
+#define SMC_LO_DMBS_HASH_BITS 12
+#define SMC_LO_RESERVED_CHID 0xFFFF
+
+struct smc_lo_dmb_node {
+ struct hlist_node list;
+ u64 token;
+ u32 len;
+ u32 sba_idx;
+ void *cpu_addr;
+ dma_addr_t dma_addr;
+ refcount_t refcnt;
+};
+
+struct smc_lo_dev {
+ struct smcd_dev *smcd;
+ struct device dev;
+ u16 chid;
+ struct smcd_gid local_gid;
+ atomic_t dmb_cnt;
+ rwlock_t dmb_ht_lock;
+ DECLARE_BITMAP(sba_idx_mask, SMC_LO_MAX_DMBS);
+ DECLARE_HASHTABLE(dmb_ht, SMC_LO_DMBS_HASH_BITS);
+ wait_queue_head_t ldev_release;
+};
+
+int smc_loopback_init(void);
+void smc_loopback_exit(void);
+#else
+static inline int smc_loopback_init(void)
+{
+ return 0;
+}
+
+static inline void smc_loopback_exit(void)
+{
+}
+#endif
+
+#endif /* _SMC_LOOPBACK_H */
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 9a2f3638d161..f0cbe77a80b4 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -42,10 +42,10 @@ static void smc_rx_wake_up(struct sock *sk)
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
EPOLLRDNORM | EPOLLRDBAND);
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN);
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
(sk->sk_state == SMC_CLOSED))
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
+ sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_HUP);
rcu_read_unlock();
}
diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
index 9d32058db2b5..e19177ce4092 100644
--- a/net/smc/smc_stats.h
+++ b/net/smc/smc_stats.h
@@ -19,7 +19,7 @@
#include "smc_clc.h"
-#define SMC_MAX_FBACK_RSN_CNT 30
+#define SMC_MAX_FBACK_RSN_CNT 36
enum {
SMC_BUF_8K,
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index a5946d1b9d60..13f2bc092db1 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -90,11 +90,11 @@ static struct ctl_table smc_table[] = {
.extra1 = &conns_per_lgr_min,
.extra2 = &conns_per_lgr_max,
},
- { }
};
int __net_init smc_sysctl_net_init(struct net *net)
{
+ size_t table_size = ARRAY_SIZE(smc_table);
struct ctl_table *table;
table = smc_table;
@@ -105,12 +105,12 @@ int __net_init smc_sysctl_net_init(struct net *net)
if (!table)
goto err_alloc;
- for (i = 0; i < ARRAY_SIZE(smc_table) - 1; i++)
+ for (i = 0; i < table_size; i++)
table[i].data += (void *)net - (void *)&init_net;
}
net->smc.smc_hdr = register_net_sysctl_sz(net, "net/smc", table,
- ARRAY_SIZE(smc_table));
+ table_size);
if (!net->smc.smc_hdr)
goto err_reg;
@@ -133,7 +133,7 @@ err_alloc:
void __net_exit smc_sysctl_net_exit(struct net *net)
{
- struct ctl_table *table;
+ const struct ctl_table *table;
table = net->smc.smc_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->smc.smc_hdr);
diff --git a/net/smc/smc_tracepoint.h b/net/smc/smc_tracepoint.h
index 9fc5e586d24a..a9a6e3c1113a 100644
--- a/net/smc/smc_tracepoint.h
+++ b/net/smc/smc_tracepoint.h
@@ -60,7 +60,7 @@ DECLARE_EVENT_CLASS(smc_msg_event,
__entry->smc = smc;
__entry->net_cookie = sock_net(sk)->net_cookie;
__entry->len = len;
- __assign_str(name, smc->conn.lnk->ibname);
+ __assign_str(name);
),
TP_printk("smc=%p net=%llu len=%zu dev=%s",
@@ -104,7 +104,7 @@ TRACE_EVENT(smcr_link_down,
__entry->lgr = lgr;
__entry->net_cookie = lgr->net->net_cookie;
__entry->state = lnk->state;
- __assign_str(name, lnk->ibname);
+ __assign_str(name);
__entry->location = location;
),
generated by cgit v1.2.3-70-g09d2 (git 2.51.1) at 2025-10-25 15:04:06 +0000