summaryrefslogtreecommitdiff
path: root/net/smc
diff options
context:
space:
mode:
Diffstat (limited to 'net/smc')
-rw-r--r--net/smc/af_smc.c26
-rw-r--r--net/smc/smc.h8
-rw-r--r--net/smc/smc_pnet.c8
-rw-r--r--net/smc/smc_rx.c37
-rw-r--r--net/smc/smc_rx.h8
5 files changed, 55 insertions, 32 deletions
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 6cc7b846cff1..cdd445d40b94 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -30,6 +30,10 @@
#include <linux/splice.h>
#include <net/sock.h>
+#include <net/inet_common.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#endif
#include <net/tcp.h>
#include <net/smc.h>
#include <asm/ioctls.h>
@@ -360,8 +364,21 @@ static void smc_destruct(struct sock *sk)
return;
if (!sock_flag(sk, SOCK_DEAD))
return;
+ switch (sk->sk_family) {
+ case AF_INET:
+ inet_sock_destruct(sk);
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ inet6_sock_destruct(sk);
+ break;
+#endif
+ }
}
+static struct lock_class_key smc_key;
+static struct lock_class_key smc_slock_key;
+
void smc_sk_init(struct net *net, struct sock *sk, int protocol)
{
struct smc_sock *smc = smc_sk(sk);
@@ -375,6 +392,8 @@ void smc_sk_init(struct net *net, struct sock *sk, int protocol)
INIT_WORK(&smc->connect_work, smc_connect_work);
INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
INIT_LIST_HEAD(&smc->accept_q);
+ sock_lock_init_class_and_name(sk, "slock-AF_SMC", &smc_slock_key,
+ "sk_lock-AF_SMC", &smc_key);
spin_lock_init(&smc->accept_q_lock);
spin_lock_init(&smc->conn.send_lock);
sk->sk_prot->hash(sk);
@@ -2738,7 +2757,7 @@ int smc_accept(struct socket *sock, struct socket *new_sock,
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);
+ smc_rx_wait(smc_sk(nsk), &timeo, 0, smc_rx_data_available);
release_sock(nsk);
}
}
@@ -3334,10 +3353,7 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family)
* 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);
+ sk_net_refcnt_upgrade(sk);
return 0;
}
diff --git a/net/smc/smc.h b/net/smc/smc.h
index ad77d6b6b8d3..7579f9622e01 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -283,10 +283,10 @@ struct smc_connection {
};
struct smc_sock { /* smc sock container */
- struct sock sk;
-#if IS_ENABLED(CONFIG_IPV6)
- struct ipv6_pinfo *pinet6;
-#endif
+ union {
+ struct sock sk;
+ struct inet_sock icsk_inet;
+ };
struct socket *clcsock; /* internal tcp socket */
void (*clcsk_state_change)(struct sock *sk);
/* original stat_change fct. */
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 716808f374a8..b391c2ef463f 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -1079,14 +1079,16 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
struct smc_init_info *ini)
{
u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+ struct net_device *base_ndev;
struct net *net;
- ndev = pnet_find_base_ndev(ndev);
+ base_ndev = pnet_find_base_ndev(ndev);
net = dev_net(ndev);
- if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+ if (smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port,
ndev_pnetid) &&
+ smc_pnet_find_ndev_pnetid_by_table(base_ndev, ndev_pnetid) &&
smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) {
- smc_pnet_find_rdma_dev(ndev, ini);
+ smc_pnet_find_rdma_dev(base_ndev, ini);
return; /* pnetid could not be determined */
}
_smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net);
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index f0cbe77a80b4..79047721df51 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -238,22 +238,23 @@ out:
return -ENOMEM;
}
-static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn)
+static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn, size_t peeked)
{
- return atomic_read(&conn->bytes_to_rcv) &&
+ return smc_rx_data_available(conn, peeked) &&
!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
+ * @peeked number of bytes already peeked
* @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).
*/
-int smc_rx_wait(struct smc_sock *smc, long *timeo,
- int (*fcrit)(struct smc_connection *conn))
+int smc_rx_wait(struct smc_sock *smc, long *timeo, size_t peeked,
+ int (*fcrit)(struct smc_connection *conn, size_t baseline))
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct smc_connection *conn = &smc->conn;
@@ -262,7 +263,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo,
struct sock *sk = &smc->sk;
int rc;
- if (fcrit(conn))
+ if (fcrit(conn, peeked))
return 1;
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
add_wait_queue(sk_sleep(sk), &wait);
@@ -271,7 +272,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo,
cflags->peer_conn_abort ||
READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN ||
conn->killed ||
- fcrit(conn),
+ fcrit(conn, peeked),
&wait);
remove_wait_queue(sk_sleep(sk), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
@@ -322,11 +323,11 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len,
return -EAGAIN;
}
-static bool smc_rx_recvmsg_data_available(struct smc_sock *smc)
+static bool smc_rx_recvmsg_data_available(struct smc_sock *smc, size_t peeked)
{
struct smc_connection *conn = &smc->conn;
- if (smc_rx_data_available(conn))
+ if (smc_rx_data_available(conn, peeked))
return true;
else if (conn->urg_state == SMC_URG_VALID)
/* we received a single urgent Byte - skip */
@@ -344,10 +345,10 @@ static bool smc_rx_recvmsg_data_available(struct smc_sock *smc)
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 copylen, read_done = 0, read_remaining = len, peeked_bytes = 0;
size_t chunk_len, chunk_off, chunk_len_sum;
struct smc_connection *conn = &smc->conn;
- int (*func)(struct smc_connection *conn);
+ int (*func)(struct smc_connection *conn, size_t baseline);
union smc_host_cursor cons;
int readable, chunk;
char *rcvbuf_base;
@@ -384,14 +385,14 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
if (conn->killed)
break;
- if (smc_rx_recvmsg_data_available(smc))
+ if (smc_rx_recvmsg_data_available(smc, peeked_bytes))
goto copy;
if (sk->sk_shutdown & RCV_SHUTDOWN) {
/* smc_cdc_msg_recv_action() could have run after
* above smc_rx_recvmsg_data_available()
*/
- if (smc_rx_recvmsg_data_available(smc))
+ if (smc_rx_recvmsg_data_available(smc, peeked_bytes))
goto copy;
break;
}
@@ -425,26 +426,28 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
}
}
- if (!smc_rx_data_available(conn)) {
- smc_rx_wait(smc, &timeo, smc_rx_data_available);
+ if (!smc_rx_data_available(conn, peeked_bytes)) {
+ smc_rx_wait(smc, &timeo, peeked_bytes, smc_rx_data_available);
continue;
}
copy:
/* initialize variables for 1st iteration of subsequent loop */
/* could be just 1 byte, even after waiting on data above */
- readable = atomic_read(&conn->bytes_to_rcv);
+ readable = smc_rx_data_available(conn, peeked_bytes);
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);
+ smc_rx_wait(smc, &timeo, peeked_bytes, func);
continue;
}
smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+ if ((flags & MSG_PEEK) && peeked_bytes)
+ smc_curs_add(conn->rmb_desc->len, &cons, peeked_bytes);
/* subsequent splice() calls pick up where previous left */
if (splbytes)
smc_curs_add(conn->rmb_desc->len, &cons, splbytes);
@@ -480,6 +483,8 @@ copy:
}
read_remaining -= chunk_len;
read_done += chunk_len;
+ if (flags & MSG_PEEK)
+ peeked_bytes += chunk_len;
if (chunk_len_sum == copylen)
break; /* either on 1st or 2nd iteration */
diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h
index db823c97d824..994f5e42d1ba 100644
--- a/net/smc/smc_rx.h
+++ b/net/smc/smc_rx.h
@@ -21,11 +21,11 @@ void smc_rx_init(struct smc_sock *smc);
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)
+int smc_rx_wait(struct smc_sock *smc, long *timeo, size_t peeked,
+ int (*fcrit)(struct smc_connection *conn, size_t baseline));
+static inline int smc_rx_data_available(struct smc_connection *conn, size_t peeked)
{
- return atomic_read(&conn->bytes_to_rcv);
+ return atomic_read(&conn->bytes_to_rcv) - peeked;
}
#endif /* SMC_RX_H */
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-25 08:35:05 +0300