summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c161
1 files changed, 72 insertions, 89 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e03e08745308..b1559481898d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk)
WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
+ tcp_scaling_ratio_init(sk);
set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
sk_sockets_allocated_inc(sk);
@@ -582,7 +583,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (urg_data & TCP_URG_VALID)
mask |= EPOLLPRI;
- } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+ } else if (state == TCP_SYN_SENT &&
+ inet_test_bit(DEFER_CONNECT, sk)) {
/* Active TCP fastopen socket with defer_connect
* Return EPOLLOUT so application can call write()
* in order for kernel to generate SYN+data
@@ -1006,7 +1008,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
tp->fastopen_req->size = size;
tp->fastopen_req->uarg = uarg;
- if (inet->defer_connect) {
+ if (inet_test_bit(DEFER_CONNECT, sk)) {
err = tcp_connect(sk);
/* Same failure procedure as in tcp_v4/6_connect */
if (err) {
@@ -1024,7 +1026,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
if (tp->fastopen_req) {
*copied = tp->fastopen_req->copied;
tcp_free_fastopen_req(tp);
- inet->defer_connect = 0;
+ inet_clear_bit(DEFER_CONNECT, sk);
}
return err;
}
@@ -1065,7 +1067,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
zc = MSG_SPLICE_PAGES;
}
- if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+ if (unlikely(flags & MSG_FASTOPEN ||
+ inet_test_bit(DEFER_CONNECT, sk)) &&
!tp->repair) {
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg);
if (err == -EINPROGRESS && copied_syn > 0)
@@ -1700,7 +1703,7 @@ EXPORT_SYMBOL(tcp_peek_len);
/* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */
int tcp_set_rcvlowat(struct sock *sk, int val)
{
- int cap;
+ int space, cap;
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
cap = sk->sk_rcvbuf >> 1;
@@ -1715,10 +1718,10 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
return 0;
- val <<= 1;
- if (val > sk->sk_rcvbuf) {
- WRITE_ONCE(sk->sk_rcvbuf, val);
- tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
+ space = tcp_space_from_win(sk, val);
+ if (space > sk->sk_rcvbuf) {
+ WRITE_ONCE(sk->sk_rcvbuf, space);
+ tcp_sk(sk)->window_clamp = val;
}
return 0;
}
@@ -1739,7 +1742,7 @@ void tcp_update_recv_tstamps(struct sk_buff *skb,
}
#ifdef CONFIG_MMU
-const struct vm_operations_struct tcp_vm_ops = {
+static const struct vm_operations_struct tcp_vm_ops = {
};
int tcp_mmap(struct file *file, struct socket *sock,
@@ -2042,13 +2045,10 @@ static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
unsigned long address,
bool *mmap_locked)
{
- struct vm_area_struct *vma = NULL;
+ struct vm_area_struct *vma = lock_vma_under_rcu(mm, address);
-#ifdef CONFIG_PER_VMA_LOCK
- vma = lock_vma_under_rcu(mm, address);
-#endif
if (vma) {
- if (!vma_is_tcp(vma)) {
+ if (vma->vm_ops != &tcp_vm_ops) {
vma_end_read(vma);
return NULL;
}
@@ -2058,7 +2058,7 @@ static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
mmap_read_lock(mm);
vma = vma_lookup(mm, address);
- if (!vma || !vma_is_tcp(vma)) {
+ if (!vma || vma->vm_ops != &tcp_vm_ops) {
mmap_read_unlock(mm);
return NULL;
}
@@ -2864,7 +2864,7 @@ adjudge_to_death:
if (sk->sk_state == TCP_FIN_WAIT2) {
struct tcp_sock *tp = tcp_sk(sk);
- if (tp->linger2 < 0) {
+ if (READ_ONCE(tp->linger2) < 0) {
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, GFP_ATOMIC);
__NET_INC_STATS(sock_net(sk),
@@ -3087,7 +3087,7 @@ int tcp_disconnect(struct sock *sk, int flags)
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
- inet->defer_connect = 0;
+ inet_clear_bit(DEFER_CONNECT, sk);
tp->fastopen_client_fail = 0;
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
@@ -3290,18 +3290,21 @@ int tcp_sock_set_syncnt(struct sock *sk, int val)
if (val < 1 || val > MAX_TCP_SYNCNT)
return -EINVAL;
- lock_sock(sk);
- inet_csk(sk)->icsk_syn_retries = val;
- release_sock(sk);
+ WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val);
return 0;
}
EXPORT_SYMBOL(tcp_sock_set_syncnt);
-void tcp_sock_set_user_timeout(struct sock *sk, u32 val)
+int tcp_sock_set_user_timeout(struct sock *sk, int val)
{
- lock_sock(sk);
- inet_csk(sk)->icsk_user_timeout = val;
- release_sock(sk);
+ /* Cap the max time in ms TCP will retry or probe the window
+ * before giving up and aborting (ETIMEDOUT) a connection.
+ */
+ if (val < 0)
+ return -EINVAL;
+
+ WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val);
+ return 0;
}
EXPORT_SYMBOL(tcp_sock_set_user_timeout);
@@ -3312,7 +3315,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val)
if (val < 1 || val > MAX_TCP_KEEPIDLE)
return -EINVAL;
- tp->keepalive_time = val * HZ;
+ /* Paired with WRITE_ONCE() in keepalive_time_when() */
+ WRITE_ONCE(tp->keepalive_time, val * HZ);
if (sock_flag(sk, SOCK_KEEPOPEN) &&
!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
u32 elapsed = keepalive_time_elapsed(tp);
@@ -3343,9 +3347,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val)
if (val < 1 || val > MAX_TCP_KEEPINTVL)
return -EINVAL;
- lock_sock(sk);
- tcp_sk(sk)->keepalive_intvl = val * HZ;
- release_sock(sk);
+ WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ);
return 0;
}
EXPORT_SYMBOL(tcp_sock_set_keepintvl);
@@ -3355,9 +3357,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val)
if (val < 1 || val > MAX_TCP_KEEPCNT)
return -EINVAL;
- lock_sock(sk);
- tcp_sk(sk)->keepalive_probes = val;
- release_sock(sk);
+ /* Paired with READ_ONCE() in keepalive_probes() */
+ WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val);
return 0;
}
EXPORT_SYMBOL(tcp_sock_set_keepcnt);
@@ -3459,6 +3460,32 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
if (copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
+ /* Handle options that can be set without locking the socket. */
+ switch (optname) {
+ case TCP_SYNCNT:
+ return tcp_sock_set_syncnt(sk, val);
+ case TCP_USER_TIMEOUT:
+ return tcp_sock_set_user_timeout(sk, val);
+ case TCP_KEEPINTVL:
+ return tcp_sock_set_keepintvl(sk, val);
+ case TCP_KEEPCNT:
+ return tcp_sock_set_keepcnt(sk, val);
+ case TCP_LINGER2:
+ if (val < 0)
+ WRITE_ONCE(tp->linger2, -1);
+ else if (val > TCP_FIN_TIMEOUT_MAX / HZ)
+ WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX);
+ else
+ WRITE_ONCE(tp->linger2, val * HZ);
+ return 0;
+ case TCP_DEFER_ACCEPT:
+ /* Translate value in seconds to number of retransmits */
+ WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept,
+ secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+ TCP_RTO_MAX / HZ));
+ return 0;
+ }
+
sockopt_lock_sock(sk);
switch (optname) {
@@ -3554,25 +3581,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
case TCP_KEEPIDLE:
err = tcp_sock_set_keepidle_locked(sk, val);
break;
- case TCP_KEEPINTVL:
- if (val < 1 || val > MAX_TCP_KEEPINTVL)
- err = -EINVAL;
- else
- tp->keepalive_intvl = val * HZ;
- break;
- case TCP_KEEPCNT:
- if (val < 1 || val > MAX_TCP_KEEPCNT)
- err = -EINVAL;
- else
- tp->keepalive_probes = val;
- break;
- case TCP_SYNCNT:
- if (val < 1 || val > MAX_TCP_SYNCNT)
- err = -EINVAL;
- else
- icsk->icsk_syn_retries = val;
- break;
-
case TCP_SAVE_SYN:
/* 0: disable, 1: enable, 2: start from ether_header */
if (val < 0 || val > 2)
@@ -3581,22 +3589,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
tp->save_syn = val;
break;
- case TCP_LINGER2:
- if (val < 0)
- tp->linger2 = -1;
- else if (val > TCP_FIN_TIMEOUT_MAX / HZ)
- tp->linger2 = TCP_FIN_TIMEOUT_MAX;
- else
- tp->linger2 = val * HZ;
- break;
-
- case TCP_DEFER_ACCEPT:
- /* Translate value in seconds to number of retransmits */
- icsk->icsk_accept_queue.rskq_defer_accept =
- secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
- TCP_RTO_MAX / HZ);
- break;
-
case TCP_WINDOW_CLAMP:
err = tcp_set_window_clamp(sk, val);
break;
@@ -3611,16 +3603,6 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
break;
#endif
- case TCP_USER_TIMEOUT:
- /* Cap the max time in ms TCP will retry or probe the window
- * before giving up and aborting (ETIMEDOUT) a connection.
- */
- if (val < 0)
- err = -EINVAL;
- else
- icsk->icsk_user_timeout = val;
- break;
-
case TCP_FASTOPEN:
if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
TCPF_LISTEN))) {
@@ -3656,13 +3638,13 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
if (!tp->repair)
err = -EPERM;
else
- tp->tsoffset = val - tcp_time_stamp_raw();
+ WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw());
break;
case TCP_REPAIR_WINDOW:
err = tcp_repair_set_window(tp, optval, optlen);
break;
case TCP_NOTSENT_LOWAT:
- tp->notsent_lowat = val;
+ WRITE_ONCE(tp->notsent_lowat, val);
sk->sk_write_space(sk);
break;
case TCP_INQ:
@@ -3674,7 +3656,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
case TCP_TX_DELAY:
if (val)
tcp_enable_tx_delay();
- tp->tcp_tx_delay = val;
+ WRITE_ONCE(tp->tcp_tx_delay, val);
break;
default:
err = -ENOPROTOOPT;
@@ -3991,17 +3973,18 @@ int do_tcp_getsockopt(struct sock *sk, int level,
val = keepalive_probes(tp);
break;
case TCP_SYNCNT:
- val = icsk->icsk_syn_retries ? :
+ val = READ_ONCE(icsk->icsk_syn_retries) ? :
READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
break;
case TCP_LINGER2:
- val = tp->linger2;
+ val = READ_ONCE(tp->linger2);
if (val >= 0)
val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
break;
case TCP_DEFER_ACCEPT:
- val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
- TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
+ val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept);
+ val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ,
+ TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
val = tp->window_clamp;
@@ -4138,11 +4121,11 @@ int do_tcp_getsockopt(struct sock *sk, int level,
break;
case TCP_USER_TIMEOUT:
- val = icsk->icsk_user_timeout;
+ val = READ_ONCE(icsk->icsk_user_timeout);
break;
case TCP_FASTOPEN:
- val = icsk->icsk_accept_queue.fastopenq.max_qlen;
+ val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen);
break;
case TCP_FASTOPEN_CONNECT:
@@ -4154,14 +4137,14 @@ int do_tcp_getsockopt(struct sock *sk, int level,
break;
case TCP_TX_DELAY:
- val = tp->tcp_tx_delay;
+ val = READ_ONCE(tp->tcp_tx_delay);
break;
case TCP_TIMESTAMP:
- val = tcp_time_stamp_raw() + tp->tsoffset;
+ val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset);
break;
case TCP_NOTSENT_LOWAT:
- val = tp->notsent_lowat;
+ val = READ_ONCE(tp->notsent_lowat);
break;
case TCP_INQ:
val = tp->recvmsg_inq;
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-18 11:25:23 +0300