summaryrefslogtreecommitdiffstats
path: root/net/smc
diff options
context:
space:
mode:
Diffstat (limited to 'net/smc')
-rw-r--r--net/smc/af_smc.c175
-rw-r--r--net/smc/smc.h7
-rw-r--r--net/smc/smc_cdc.c2
-rw-r--r--net/smc/smc_cdc.h2
-rw-r--r--net/smc/smc_core.c46
-rw-r--r--net/smc/smc_core.h5
-rw-r--r--net/smc/smc_diag.c39
-rw-r--r--net/smc/smc_llc.c62
-rw-r--r--net/smc/smc_llc.h3
-rw-r--r--net/smc/smc_rx.c200
-rw-r--r--net/smc/smc_rx.h11
-rw-r--r--net/smc/smc_tx.c24
-rw-r--r--net/smc/smc_wr.c1
13 files changed, 496 insertions, 81 deletions
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 544bab42f925..17688a02035b 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -29,6 +29,7 @@
#include <net/sock.h>
#include <net/tcp.h>
#include <net/smc.h>
+#include <asm/ioctls.h>
#include "smc.h"
#include "smc_clc.h"
@@ -305,6 +306,7 @@ static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc)
static int smc_clnt_conf_first_link(struct smc_sock *smc)
{
+ struct net *net = sock_net(smc->clcsock->sk);
struct smc_link_group *lgr = smc->conn.lgr;
struct smc_link *link;
int rest;
@@ -362,7 +364,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
if (rc < 0)
return SMC_CLC_DECL_TCL;
- link->state = SMC_LNK_ACTIVE;
+ smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
return 0;
}
@@ -400,6 +402,9 @@ static int smc_connect_rdma(struct smc_sock *smc)
sock_hold(&smc->sk); /* sock put in passive closing */
+ if (smc->use_fallback)
+ goto out_connected;
+
if (!tcp_sk(smc->clcsock->sk)->syn_smc) {
/* peer has not signalled SMC-capability */
smc->use_fallback = true;
@@ -716,6 +721,7 @@ void smc_close_non_accepted(struct sock *sk)
static int smc_serv_conf_first_link(struct smc_sock *smc)
{
+ struct net *net = sock_net(smc->clcsock->sk);
struct smc_link_group *lgr = smc->conn.lgr;
struct smc_link *link;
int rest;
@@ -768,7 +774,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
return rc;
}
- link->state = SMC_LNK_ACTIVE;
+ smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
return 0;
}
@@ -792,6 +798,9 @@ static void smc_listen_work(struct work_struct *work)
int rc = 0;
u8 ibport;
+ if (new_smc->use_fallback)
+ goto out_connected;
+
/* check if peer is smc capable */
if (!tcp_sk(newclcsock->sk)->syn_smc) {
new_smc->use_fallback = true;
@@ -965,7 +974,7 @@ static void smc_tcp_listen_work(struct work_struct *work)
continue;
new_smc->listen_smc = lsmc;
- new_smc->use_fallback = false; /* assume rdma capability first*/
+ new_smc->use_fallback = lsmc->use_fallback;
sock_hold(lsk); /* sock_put in smc_listen_work */
INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
smc_copy_sock_settings_to_smc(new_smc);
@@ -1001,7 +1010,8 @@ static int smc_listen(struct socket *sock, int backlog)
* them to the clc socket -- copy smc socket options to clc socket
*/
smc_copy_sock_settings_to_clc(smc);
- tcp_sk(smc->clcsock->sk)->syn_smc = 1;
+ if (!smc->use_fallback)
+ tcp_sk(smc->clcsock->sk)->syn_smc = 1;
rc = kernel_listen(smc->clcsock, backlog);
if (rc)
@@ -1034,6 +1044,7 @@ static int smc_accept(struct socket *sock, struct socket *new_sock,
if (lsmc->sk.sk_state != SMC_LISTEN) {
rc = -EINVAL;
+ release_sock(sk);
goto out;
}
@@ -1061,9 +1072,29 @@ static int smc_accept(struct socket *sock, struct socket *new_sock,
if (!rc)
rc = sock_error(nsk);
+ release_sock(sk);
+ if (rc)
+ goto out;
+
+ if (lsmc->sockopt_defer_accept && !(flags & O_NONBLOCK)) {
+ /* wait till data arrives on the socket */
+ timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept *
+ MSEC_PER_SEC);
+ if (smc_sk(nsk)->use_fallback) {
+ struct sock *clcsk = smc_sk(nsk)->clcsock->sk;
+
+ lock_sock(clcsk);
+ if (skb_queue_empty(&clcsk->sk_receive_queue))
+ sk_wait_data(clcsk, &timeo, NULL);
+ release_sock(clcsk);
+ } else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) {
+ lock_sock(nsk);
+ smc_rx_wait(smc_sk(nsk), &timeo, smc_rx_data_available);
+ release_sock(nsk);
+ }
+ }
out:
- release_sock(sk);
sock_put(sk); /* sock_hold above */
return rc;
}
@@ -1094,6 +1125,16 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
(sk->sk_state != SMC_APPCLOSEWAIT1) &&
(sk->sk_state != SMC_INIT))
goto out;
+
+ if (msg->msg_flags & MSG_FASTOPEN) {
+ if (sk->sk_state == SMC_INIT) {
+ smc->use_fallback = true;
+ } else {
+ rc = -EINVAL;
+ goto out;
+ }
+ }
+
if (smc->use_fallback)
rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len);
else
@@ -1122,10 +1163,12 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
goto out;
}
- if (smc->use_fallback)
+ if (smc->use_fallback) {
rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags);
- else
- rc = smc_rx_recvmsg(smc, msg, len, flags);
+ } else {
+ msg->msg_namelen = 0;
+ rc = smc_rx_recvmsg(smc, msg, NULL, len, flags);
+ }
out:
release_sock(sk);
@@ -1273,14 +1316,64 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
+ int val, rc;
smc = smc_sk(sk);
/* generic setsockopts reaching us here always apply to the
* CLC socket
*/
- return smc->clcsock->ops->setsockopt(smc->clcsock, level, optname,
- optval, optlen);
+ rc = smc->clcsock->ops->setsockopt(smc->clcsock, level, optname,
+ optval, optlen);
+ if (smc->clcsock->sk->sk_err) {
+ sk->sk_err = smc->clcsock->sk->sk_err;
+ sk->sk_error_report(sk);
+ }
+ if (rc)
+ return rc;
+
+ if (optlen < sizeof(int))
+ return rc;
+ get_user(val, (int __user *)optval);
+
+ lock_sock(sk);
+ switch (optname) {
+ case TCP_ULP:
+ case TCP_FASTOPEN:
+ case TCP_FASTOPEN_CONNECT:
+ case TCP_FASTOPEN_KEY:
+ case TCP_FASTOPEN_NO_COOKIE:
+ /* option not supported by SMC */
+ if (sk->sk_state == SMC_INIT) {
+ smc->use_fallback = true;
+ } else {
+ if (!smc->use_fallback)
+ rc = -EINVAL;
+ }
+ break;
+ case TCP_NODELAY:
+ if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+ if (val)
+ 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 (!val)
+ mod_delayed_work(system_wq, &smc->conn.tx_work,
+ 0);
+ }
+ break;
+ case TCP_DEFER_ACCEPT:
+ smc->sockopt_defer_accept = val;
+ break;
+ default:
+ break;
+ }
+ release_sock(sk);
+
+ return rc;
}
static int smc_getsockopt(struct socket *sock, int level, int optname,
@@ -1298,12 +1391,38 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
unsigned long arg)
{
struct smc_sock *smc;
+ int answ;
smc = smc_sk(sock->sk);
- if (smc->use_fallback)
+ if (smc->use_fallback) {
+ if (!smc->clcsock)
+ return -EBADF;
return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
- else
- return sock_no_ioctl(sock, cmd, arg);
+ }
+ switch (cmd) {
+ case SIOCINQ: /* same as FIONREAD */
+ if (smc->sk.sk_state == SMC_LISTEN)
+ return -EINVAL;
+ answ = atomic_read(&smc->conn.bytes_to_rcv);
+ break;
+ case SIOCOUTQ:
+ /* output queue size (not send + not acked) */
+ if (smc->sk.sk_state == SMC_LISTEN)
+ return -EINVAL;
+ answ = smc->conn.sndbuf_size -
+ atomic_read(&smc->conn.sndbuf_space);
+ break;
+ case SIOCOUTQNSD:
+ /* output queue size (not send only) */
+ if (smc->sk.sk_state == SMC_LISTEN)
+ return -EINVAL;
+ answ = smc_tx_prepared_sends(&smc->conn);
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+
+ return put_user(answ, (int __user *)arg);
}
static ssize_t smc_sendpage(struct socket *sock, struct page *page,
@@ -1330,9 +1449,15 @@ out:
return rc;
}
+/* Map the affected portions of the rmbe into an spd, note the number of bytes
+ * to splice in conn->splice_pending, and press 'go'. Delays consumer cursor
+ * updates till whenever a respective page has been fully processed.
+ * 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)
+ unsigned int flags)
{
struct sock *sk = sock->sk;
struct smc_sock *smc;
@@ -1340,16 +1465,34 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
smc = smc_sk(sk);
lock_sock(sk);
- if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_CLOSED))
+
+ if (sk->sk_state == SMC_INIT ||
+ sk->sk_state == SMC_LISTEN ||
+ sk->sk_state == SMC_CLOSED)
goto out;
+
+ if (sk->sk_state == SMC_PEERFINCLOSEWAIT) {
+ rc = 0;
+ goto out;
+ }
+
if (smc->use_fallback) {
rc = smc->clcsock->ops->splice_read(smc->clcsock, ppos,
pipe, len, flags);
} else {
- rc = -EOPNOTSUPP;
+ if (*ppos) {
+ rc = -ESPIPE;
+ goto out;
+ }
+ if (flags & SPLICE_F_NONBLOCK)
+ flags = MSG_DONTWAIT;
+ else
+ flags = 0;
+ rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags);
}
out:
release_sock(sk);
+
return rc;
}
diff --git a/net/smc/smc.h b/net/smc/smc.h
index e4829a2f46ba..ec209cd48d42 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -164,6 +164,9 @@ struct smc_connection {
atomic_t bytes_to_rcv; /* arrived data,
* not yet received
*/
+ atomic_t splice_pending; /* number of spliced bytes
+ * pending processing
+ */
#ifndef KERNEL_HAS_ATOMIC64
spinlock_t acurs_lock; /* protect cursors */
#endif
@@ -180,6 +183,10 @@ struct smc_sock { /* smc sock container */
struct list_head accept_q; /* sockets to be accepted */
spinlock_t accept_q_lock; /* protects accept_q */
bool use_fallback; /* fallback to tcp */
+ int sockopt_defer_accept;
+ /* sockopt TCP_DEFER_ACCEPT
+ * value
+ */
u8 wait_close_tx_prepared : 1;
/* shutdown wr or close
* started, waiting for unsent
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index b42395d24cba..42ad57365eca 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -82,7 +82,7 @@ static inline void smc_cdc_add_pending_send(struct smc_connection *conn,
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(
- offsetof(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE,
+ sizeof(struct smc_cdc_msg) != 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,
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index ab240b37ad11..d2012fd22100 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -48,7 +48,7 @@ struct smc_cdc_msg {
struct smc_cdc_producer_flags prod_flags;
struct smc_cdc_conn_state_flags conn_state_flags;
u8 reserved[18];
-} __aligned(8);
+} __packed; /* format defined in RFC7609 */
static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn)
{
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index d4bd01bb44e1..9c74844e2008 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -290,8 +290,8 @@ static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk,
DMA_TO_DEVICE);
}
sg_free_table(&buf_desc->sgt[SMC_SINGLE_LINK]);
- if (buf_desc->cpu_addr)
- free_pages((unsigned long)buf_desc->cpu_addr, buf_desc->order);
+ if (buf_desc->pages)
+ __free_pages(buf_desc->pages, buf_desc->order);
kfree(buf_desc);
}
@@ -326,6 +326,7 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr)
/* remove a link group */
void smc_lgr_free(struct smc_link_group *lgr)
{
+ smc_llc_link_flush(&lgr->lnk[SMC_SINGLE_LINK]);
smc_lgr_free_bufs(lgr);
smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
kfree(lgr);
@@ -348,6 +349,7 @@ void smc_lgr_terminate(struct smc_link_group *lgr)
struct rb_node *node;
smc_lgr_forget(lgr);
+ smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
write_lock_bh(&lgr->conns_lock);
node = rb_first(&lgr->conns_all);
@@ -374,7 +376,8 @@ void smc_lgr_terminate(struct smc_link_group *lgr)
static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
- int rc = 0;
+ struct net_device *ndev;
+ int i, nest_lvl, rc = 0;
*vlan_id = 0;
if (!dst) {
@@ -386,8 +389,27 @@ static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
goto out_rel;
}
- if (is_vlan_dev(dst->dev))
- *vlan_id = vlan_dev_vlan_id(dst->dev);
+ ndev = dst->dev;
+ if (is_vlan_dev(ndev)) {
+ *vlan_id = vlan_dev_vlan_id(ndev);
+ goto out_rel;
+ }
+
+ rtnl_lock();
+ nest_lvl = dev_get_nest_level(ndev);
+ for (i = 0; i < nest_lvl; i++) {
+ struct list_head *lower = &ndev->adj_list.lower;
+
+ if (list_empty(lower))
+ break;
+ 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);
+ break;
+ }
+ }
+ rtnl_unlock();
out_rel:
dst_release(dst);
@@ -544,16 +566,16 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr,
if (!buf_desc)
return ERR_PTR(-ENOMEM);
- buf_desc->cpu_addr =
- (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN |
- __GFP_NOMEMALLOC |
- __GFP_NORETRY | __GFP_ZERO,
- get_order(bufsize));
- if (!buf_desc->cpu_addr) {
+ buf_desc->order = get_order(bufsize);
+ buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN |
+ __GFP_NOMEMALLOC | __GFP_COMP |
+ __GFP_NORETRY | __GFP_ZERO,
+ buf_desc->order);
+ if (!buf_desc->pages) {
kfree(buf_desc);
return ERR_PTR(-EAGAIN);
}
- buf_desc->order = get_order(bufsize);
+ buf_desc->cpu_addr = (void *)page_address(buf_desc->pages);
/* build the sg table from the pages */
lnk = &lgr->lnk[SMC_SINGLE_LINK];
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 5dfcb15d529f..fca8624e5e71 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -79,6 +79,7 @@ struct smc_link {
dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */
u64 wr_rx_id; /* seq # of last recv WR */
u32 wr_rx_cnt; /* number of WR recv buffers */
+ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */
struct ib_reg_wr wr_reg; /* WR register memory region */
wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */
@@ -101,6 +102,9 @@ struct smc_link {
int llc_confirm_resp_rc; /* rc from conf_resp msg */
struct completion llc_add; /* wait for rx of add link */
struct completion llc_add_resp; /* wait for rx of add link rsp*/
+ struct delayed_work llc_testlink_wrk; /* testlink worker */
+ struct completion llc_testlink_resp; /* wait for rx of testlink */
+ int llc_testlink_time; /* testlink interval */
};
/* For now we just allow one parallel link per link group. The SMC protocol
@@ -116,6 +120,7 @@ struct smc_link {
struct smc_buf_desc {
struct list_head list;
void *cpu_addr; /* virtual address of buffer */
+ struct page *pages;
struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */
struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX];
/* for rmb only: memory region
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 427b91c1c964..05dd7e6d314d 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -38,17 +38,27 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk)
{
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);
r->id.idiag_dport = smc->clcsock->sk->sk_dport;
r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
sock_diag_save_cookie(sk, r->id.idiag_cookie);
- 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 (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,
+ sizeof(smc->clcsock->sk->sk_v6_daddr));
+#endif
+ }
}
static int smc_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
@@ -153,7 +163,8 @@ errout:
return -EMSGSIZE;
}
-static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb,
+ struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct nlattr *bc = NULL;
@@ -161,8 +172,8 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
struct sock *sk;
int rc = 0;
- read_lock(&smc_proto.h.smc_hash->lock);
- head = &smc_proto.h.smc_hash->ht;
+ read_lock(&prot->h.smc_hash->lock);
+ head = &prot->h.smc_hash->ht;
if (hlist_empty(head))
goto out;
@@ -175,7 +186,17 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
}
out:
- read_unlock(&smc_proto.h.smc_hash->lock);
+ read_unlock(&prot->h.smc_hash->lock);
+ return rc;
+}
+
+static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ int rc = 0;
+
+ rc = smc_diag_dump_proto(&smc_proto, skb, cb);
+ if (!rc)
+ rc = smc_diag_dump_proto(&smc_proto6, skb, cb);
return rc;
}
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index ea4b21981b4b..33b4d856f4c6 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -397,7 +397,8 @@ static void smc_llc_rx_test_link(struct smc_link *link,
struct smc_llc_msg_test_link *llc)
{
if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
- /* unused as long as we don't send this type of msg */
+ if (link->state == SMC_LNK_ACTIVE)
+ complete(&link->llc_testlink_resp);
} else {
smc_llc_send_test_link(link, llc->user_data, SMC_LLC_RESP);
}
@@ -502,6 +503,65 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf)
}
}
+/***************************** worker ****************************************/
+
+static void smc_llc_testlink_work(struct work_struct *work)
+{
+ struct smc_link *link = container_of(to_delayed_work(work),
+ struct smc_link, llc_testlink_wrk);
+ unsigned long next_interval;
+ struct smc_link_group *lgr;
+ unsigned long expire_time;
+ u8 user_data[16] = { 0 };
+ int rc;
+
+ lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+ if (link->state != SMC_LNK_ACTIVE)
+ return; /* don't reschedule worker */
+ expire_time = link->wr_rx_tstamp + link->llc_testlink_time;
+ if (time_is_after_jiffies(expire_time)) {
+ next_interval = expire_time - jiffies;
+ goto out;
+ }
+ reinit_completion(&link->llc_testlink_resp);
+ smc_llc_send_test_link(link, user_data, SMC_LLC_REQ);
+ /* receive TEST LINK response over RoCE fabric */
+ rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp,
+ SMC_LLC_WAIT_TIME);
+ if (rc <= 0) {
+ smc_lgr_terminate(lgr);
+ return;
+ }
+ next_interval = link->llc_testlink_time;
+out:
+ schedule_delayed_work(&link->llc_testlink_wrk, next_interval);
+}
+
+void smc_llc_link_active(struct smc_link *link, int testlink_time)
+{
+ init_completion(&link->llc_testlink_resp);
+ INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work);
+ link->state = SMC_LNK_ACTIVE;
+ if (testlink_time) {
+ link->llc_testlink_time = testlink_time * HZ;
+ schedule_delayed_work(&link->llc_testlink_wrk,
+ link->llc_testlink_time);
+ }
+}
+
+/* called in tasklet context */
+void smc_llc_link_inactive(struct smc_link *link)
+{
+ link->state = SMC_LNK_INACTIVE;
+ cancel_delayed_work(&link->llc_testlink_wrk);
+}
+
+/* called in worker context */
+void smc_llc_link_flush(struct smc_link *link)
+{
+ cancel_delayed_work_sync(&link->llc_testlink_wrk);
+}
+
/***************************** 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 e4a7d5e234d5..d6e42116485e 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -44,6 +44,9 @@ int smc_llc_send_delete_link(struct smc_link *link,
enum smc_llc_reqresp reqresp);
int smc_llc_send_test_link(struct smc_link *lnk, u8 user_data[16],
enum smc_llc_reqresp reqresp);
+void smc_llc_link_active(struct smc_link *link, int testlink_time);
+void smc_llc_link_inactive(struct smc_link *link);
+void smc_llc_link_flush(struct smc_link *link);
int smc_llc_init(void) __init;
#endif /* SMC_LLC_H */
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index eff4e0d0bb31..ed45569289f5 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -22,11 +22,10 @@
#include "smc_tx.h" /* smc_tx_consumer_update() */
#include "smc_rx.h"
-/* callback implementation for sk.sk_data_ready()
- * to wakeup rcvbuf consumers that blocked with smc_rx_wait_data().
+/* callback implementation to wakeup consumers blocked with smc_rx_wait().
* indirectly called by smc_cdc_msg_recv_action().
*/
-static void smc_rx_data_ready(struct sock *sk)
+static void smc_rx_wake_up(struct sock *sk)
{
struct socket_wq *wq;
@@ -44,28 +43,140 @@ static void smc_rx_data_ready(struct sock *sk)
rcu_read_unlock();
}
+/* Update consumer cursor
+ * @conn connection to update
+ * @cons consumer cursor
+ * @len number of Bytes consumed
+ */
+static void smc_rx_update_consumer(struct smc_connection *conn,
+ union smc_host_cursor cons, size_t len)
+{
+ smc_curs_add(conn->rmbe_size, &cons, len);
+ smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn),
+ conn);
+ /* send consumer cursor update if required */
+ /* similar to advertising new TCP rcv_wnd if required */
+ smc_tx_consumer_update(conn);
+}
+
+struct smc_spd_priv {
+ struct smc_sock *smc;
+ size_t len;
+};
+
+static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private;
+ struct smc_sock *smc = priv->smc;
+ struct smc_connection *conn;
+ union smc_host_cursor cons;
+ struct sock *sk = &smc->sk;
+
+ if (sk->sk_state == SMC_CLOSED ||
+ sk->sk_state == SMC_PEERFINCLOSEWAIT ||
+ sk->sk_state == SMC_APPFINCLOSEWAIT)
+ goto out;
+ conn = &smc->conn;
+ lock_sock(sk);
+ smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn),
+ conn);
+ smc_rx_update_consumer(conn, cons, priv->len);
+ release_sock(sk);
+ if (atomic_sub_and_test(priv->len, &conn->splice_pending))
+ smc_rx_wake_up(sk);
+out:
+ kfree(priv);
+ put_page(buf->page);
+ sock_put(sk);
+}
+
+static int smc_rx_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ return 1;
+}
+
+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,
+ .get = generic_pipe_buf_get
+};
+
+static void smc_rx_spd_release(struct splice_pipe_desc *spd,
+ unsigned int i)
+{
+ put_page(spd->pages[i]);
+}
+
+static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
+ struct smc_sock *smc)
+{
+ struct splice_pipe_desc spd;
+ struct partial_page partial;
+ struct smc_spd_priv *priv;
+ struct page *page;
+ int bytes;
+
+ page = virt_to_page(smc->conn.rmb_desc->cpu_addr);
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+ priv->len = len;
+ priv->smc = smc;
+ partial.offset = src - (char *)smc->conn.rmb_desc->cpu_addr;
+ partial.len = len;
+ partial.private = (unsigned long)priv;
+
+ spd.nr_pages_max = 1;
+ spd.nr_pages = 1;
+ spd.pages = &page;
+ spd.partial = &partial;
+ spd.ops = &smc_pipe_ops;
+ spd.spd_release = smc_rx_spd_release;
+
+ bytes = splice_to_pipe(pipe, &spd);
+ if (bytes > 0) {
+ sock_hold(&smc->sk);
+ get_page(smc->conn.rmb_desc->pages);
+ atomic_add(bytes, &smc->conn.splice_pending);
+ }
+
+ return bytes;
+}
+
+static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn)
+{
+ return atomic_read(&conn->bytes_to_rcv) &&
+ !atomic_read(&conn->splice_pending);
+}
+
/* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted
* @smc smc socket
* @timeo pointer to max seconds to wait, pointer to value 0 for no timeout
+ * @fcrit add'l criterion to evaluate as function pointer
* Returns:
* 1 if at least 1 byte available in rcvbuf or if socket error/shutdown.
* 0 otherwise (nothing in rcvbuf nor timeout, e.g. interrupted).
*/
-static int smc_rx_wait_data(struct smc_sock *smc, long *timeo)
+int smc_rx_wait(struct smc_sock *smc, long *timeo,
+ int (*fcrit)(struct smc_connection *conn))
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
int rc;
- if (atomic_read(&conn->bytes_to_rcv))
+ if (fcrit(conn))
return 1;
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
add_wait_queue(sk_sleep(sk), &wait);
rc = sk_wait_event(sk, timeo,
sk->sk_err ||
sk->sk_shutdown & RCV_SHUTDOWN ||
- atomic_read(&conn->bytes_to_rcv) ||
+ fcrit(conn) ||
smc_cdc_rxed_any_close_or_senddone(conn),
&wait);
remove_wait_queue(sk_sleep(sk), &wait);
@@ -73,19 +184,25 @@ static int smc_rx_wait_data(struct smc_sock *smc, long *timeo)
return rc;
}
-/* rcvbuf consumer: main API called by socket layer.
- * called under sk lock.
+/* smc_rx_recvmsg - receive data from RMBE
+ * @msg: copy data to receive buffer
+ * @pipe: copy data to pipe if set - indicates splice() call
+ *
+ * rcvbuf consumer: main API called by socket layer.
+ * Called under sk lock.
*/
-int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
- int flags)
+int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
+ struct pipe_inode_info *pipe, size_t len, int flags)
{
size_t copylen, read_done = 0, read_remaining = len;
size_t chunk_len, chunk_off, chunk_len_sum;
struct smc_connection *conn = &smc->conn;
+ int (*func)(struct smc_connection *conn);
union smc_host_cursor cons;
int readable, chunk;
char *rcvbuf_base;
struct sock *sk;
+ int splbytes;
long timeo;
int target; /* Read at least these many bytes */
int rc;
@@ -101,37 +218,32 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
- msg->msg_namelen = 0;
/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
rcvbuf_base = conn->rmb_desc->cpu_addr;
do { /* while (read_remaining) */
- if (read_done >= target)
+ if (read_done >= target || (pipe && read_done))
break;
if (atomic_read(&conn->bytes_to_rcv))
goto copy;
+ if (sk->sk_shutdown & RCV_SHUTDOWN ||
+ smc_cdc_rxed_any_close_or_senddone(conn) ||
+ conn->local_tx_ctrl.conn_state_flags.peer_conn_abort)
+ break;
+
if (read_done) {
if (sk->sk_err ||
sk->sk_state == SMC_CLOSED ||
- sk->sk_shutdown & RCV_SHUTDOWN ||
!timeo ||
- signal_pending(current) ||
- smc_cdc_rxed_any_close_or_senddone(conn) ||
- conn->local_tx_ctrl.conn_state_flags.
- peer_conn_abort)
+ signal_pending(current))
break;
} else {
if (sk->sk_err) {
read_done = sock_error(sk);
break;
}
- if (sk->sk_shutdown & RCV_SHUTDOWN ||
- smc_cdc_rxed_any_close_or_senddone(conn) ||
- conn->local_tx_ctrl.conn_state_flags.
- peer_conn_abort)
- break;
if (sk->sk_state == SMC_CLOSED) {
if (!sock_flag(sk, SOCK_DONE)) {
/* This occurs when user tries to read
@@ -150,20 +262,33 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
return -EAGAIN;
}
- if (!atomic_read(&conn->bytes_to_rcv)) {
- smc_rx_wait_data(smc, &timeo);
+ if (!smc_rx_data_available(conn)) {
+ smc_rx_wait(smc, &timeo, smc_rx_data_available);
continue;
}
copy:
/* initialize variables for 1st iteration of subsequent loop */
- /* could be just 1 byte, even after smc_rx_wait_data above */
+ /* could be just 1 byte, even after waiting on data above */
readable = atomic_read(&conn->bytes_to_rcv);
+ splbytes = atomic_read(&conn->splice_pending);
+ if (!readable || (msg && splbytes)) {
+ if (splbytes)
+ func = smc_rx_data_available_and_no_splice_pend;
+ else
+ func = smc_rx_data_available;
+ smc_rx_wait(smc, &timeo, func);
+ continue;
+ }
+
/* not more than what user space asked for */
copylen = min_t(size_t, read_remaining, readable);
smc_curs_write(&cons,
smc_curs_read(&conn->local_tx_ctrl.cons, conn),
conn);
+ /* subsequent splice() calls pick up where previous left */
+ if (splbytes)
+ smc_curs_add(conn->rmbe_size, &cons, splbytes);
/* determine chunks where to read from rcvbuf */
/* either unwrapped case, or 1st chunk of wrapped case */
chunk_len = min_t(size_t,
@@ -173,9 +298,16 @@ copy:
smc_rmb_sync_sg_for_cpu(conn);
for (chunk = 0; chunk < 2; chunk++) {
if (!(flags & MSG_TRUNC)) {
- rc = memcpy_to_msg(msg, rcvbuf_base + chunk_off,
- chunk_len);
- if (rc) {
+ if (msg) {
+ rc = memcpy_to_msg(msg, rcvbuf_base +
+ chunk_off,
+ chunk_len);
+ } else {
+ rc = smc_rx_splice(pipe, rcvbuf_base +
+ chunk_off, chunk_len,
+ smc);
+ }
+ if (rc < 0) {
if (!read_done)
read_done = -EFAULT;
smc_rmb_sync_sg_for_device(conn);
@@ -196,18 +328,13 @@ copy:
/* update cursors */
if (!(flags & MSG_PEEK)) {
- smc_curs_add(conn->rmbe_size, &cons, copylen);
/* increased in recv tasklet smc_cdc_msg_rcv() */
smp_mb__before_atomic();
atomic_sub(copylen, &conn->bytes_to_rcv);
/* guarantee 0 <= bytes_to_rcv <= rmbe_size */
smp_mb__after_atomic();
- smc_curs_write(&conn->local_tx_ctrl.cons,
- smc_curs_read(&cons, conn),
- conn);
- /* send consumer cursor update if required */
- /* similar to advertising new TCP rcv_wnd if required */
- smc_tx_consumer_update(conn);
+ if (msg)
+ smc_rx_update_consumer(conn, cons, copylen);
}
} while (read_remaining);
out:
@@ -217,5 +344,6 @@ out:
/* Initialize receive properties on connection establishment. NB: not __init! */
void smc_rx_init(struct smc_sock *smc)
{
- smc->sk.sk_data_ready = smc_rx_data_ready;
+ smc->sk.sk_data_ready = smc_rx_wake_up;
+ atomic_set(&smc->conn.splice_pending, 0);
}
diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h
index 3a32b59bf06c..db823c97d824 100644
--- a/net/smc/smc_rx.h
+++ b/net/smc/smc_rx.h
@@ -18,7 +18,14 @@
#include "smc.h"
void smc_rx_init(struct smc_sock *smc);
-int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
- int flags);
+
+int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
+ struct pipe_inode_info *pipe, size_t len, int flags);
+int smc_rx_wait(struct smc_sock *smc, long *timeo,
+ int (*fcrit)(struct smc_connection *conn));
+static inline int smc_rx_data_available(struct smc_connection *conn)
+{
+ return atomic_read(&conn->bytes_to_rcv);
+}
#endif /* SMC_RX_H */
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 72f004c9c9b1..58dfe0bd9d60 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -19,6 +19,7 @@
#include <linux/sched/signal.h>
#include <net/sock.h>
+#include <net/tcp.h>
#include "smc.h"
#include "smc_wr.h"
@@ -26,6 +27,7 @@
#include "smc_tx.h"
#define SMC_TX_WORK_DELAY HZ
+#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */
/***************************** sndbuf producer *******************************/
@@ -115,6 +117,13 @@ static int smc_tx_wait_memory(struct smc_sock *smc, int flags)
return rc;
}
+static bool smc_tx_is_corked(struct smc_sock *smc)
+{
+ struct tcp_sock *tp = tcp_sk(smc->clcsock->sk);
+
+ return (tp->nonagle & TCP_NAGLE_CORK) ? true : false;
+}
+
/* sndbuf producer: main API called by socket layer.
* called under sock lock.
*/
@@ -209,7 +218,16 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
/* since we just produced more new data into sndbuf,
* trigger sndbuf consumer: RDMA write into peer RMBE and CDC
*/
- smc_tx_sndbuf_nonempty(conn);
+ if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) &&
+ (atomic_read(&conn->sndbuf_space) >
+ (conn->sndbuf_size >> 1)))
+ /* for a corked socket defer the RDMA writes if there
+ * is still sufficient sndbuf_space available
+ */
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_CORK_DELAY);
+ else
+ smc_tx_sndbuf_nonempty(conn);
} /* while (msg_data_left(msg)) */
return send_done;
@@ -409,8 +427,8 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
}
rc = 0;
if (conn->alert_token_local) /* connection healthy */
- schedule_delayed_work(&conn->tx_work,
- SMC_TX_WORK_DELAY);
+ mod_delayed_work(system_wq, &conn->tx_work,
+ SMC_TX_WORK_DELAY);
}
goto out_unlock;
}
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 1b8af23e6e2b..cc7c1bb60fe8 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -376,6 +376,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
for (i = 0; i < num; i++) {
link = wc[i].qp->qp_context;
if (wc[i].status == IB_WC_SUCCESS) {
+ link->wr_rx_tstamp = jiffies;
smc_wr_rx_demultiplex(&wc[i]);
smc_wr_rx_post(link); /* refill WR RX */
} else {
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-04 22:36:12 +0100