summaryrefslogtreecommitdiff
path: root/net/core/sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c136
1 files changed, 74 insertions, 62 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 9370fd50aa2c..666a17cab4f5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -429,6 +429,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
{
struct __kernel_sock_timeval tv;
int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval);
+ long val;
if (err)
return err;
@@ -439,7 +440,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
if (tv.tv_sec < 0) {
static int warned __read_mostly;
- *timeo_p = 0;
+ WRITE_ONCE(*timeo_p, 0);
if (warned < 10 && net_ratelimit()) {
warned++;
pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
@@ -447,11 +448,12 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
}
return 0;
}
- *timeo_p = MAX_SCHEDULE_TIMEOUT;
- if (tv.tv_sec == 0 && tv.tv_usec == 0)
- return 0;
- if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))
- *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ);
+ val = MAX_SCHEDULE_TIMEOUT;
+ if ((tv.tv_sec || tv.tv_usec) &&
+ (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)))
+ val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec,
+ USEC_PER_SEC / HZ);
+ WRITE_ONCE(*timeo_p, val);
return 0;
}
@@ -765,7 +767,7 @@ bool sk_mc_loop(struct sock *sk)
return true;
switch (sk->sk_family) {
case AF_INET:
- return inet_sk(sk)->mc_loop;
+ return inet_test_bit(MC_LOOP, sk);
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
return inet6_sk(sk)->mc_loop;
@@ -795,7 +797,7 @@ EXPORT_SYMBOL(sock_set_reuseport);
void sock_no_linger(struct sock *sk)
{
lock_sock(sk);
- sk->sk_lingertime = 0;
+ WRITE_ONCE(sk->sk_lingertime, 0);
sock_set_flag(sk, SOCK_LINGER);
release_sock(sk);
}
@@ -804,7 +806,7 @@ EXPORT_SYMBOL(sock_no_linger);
void sock_set_priority(struct sock *sk, u32 priority)
{
lock_sock(sk);
- sk->sk_priority = priority;
+ WRITE_ONCE(sk->sk_priority, priority);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_priority);
@@ -813,9 +815,9 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs)
{
lock_sock(sk);
if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
- sk->sk_sndtimeo = secs * HZ;
+ WRITE_ONCE(sk->sk_sndtimeo, secs * HZ);
else
- sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+ WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_sndtimeo);
@@ -988,7 +990,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf);
static void __sock_set_mark(struct sock *sk, u32 val)
{
if (val != sk->sk_mark) {
- sk->sk_mark = val;
+ WRITE_ONCE(sk->sk_mark, val);
sk_dst_reset(sk);
}
}
@@ -1007,7 +1009,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes)
bytes = round_down(bytes, PAGE_SIZE);
WARN_ON(bytes > sk->sk_reserved_mem);
- sk->sk_reserved_mem -= bytes;
+ WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes);
sk_mem_reclaim(sk);
}
@@ -1044,7 +1046,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
}
sk->sk_forward_alloc += pages << PAGE_SHIFT;
- sk->sk_reserved_mem += pages << PAGE_SHIFT;
+ WRITE_ONCE(sk->sk_reserved_mem,
+ sk->sk_reserved_mem + (pages << PAGE_SHIFT));
return 0;
}
@@ -1213,7 +1216,7 @@ set_sndbuf:
if ((val >= 0 && val <= 6) ||
sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- sk->sk_priority = val;
+ WRITE_ONCE(sk->sk_priority, val);
else
ret = -EPERM;
break;
@@ -1227,15 +1230,15 @@ set_sndbuf:
ret = -EFAULT;
break;
}
- if (!ling.l_onoff)
+ if (!ling.l_onoff) {
sock_reset_flag(sk, SOCK_LINGER);
- else {
-#if (BITS_PER_LONG == 32)
- if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
- sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
+ } else {
+ unsigned long t_sec = ling.l_linger;
+
+ if (t_sec >= MAX_SCHEDULE_TIMEOUT / HZ)
+ WRITE_ONCE(sk->sk_lingertime, MAX_SCHEDULE_TIMEOUT);
else
-#endif
- sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
+ WRITE_ONCE(sk->sk_lingertime, t_sec * HZ);
sock_set_flag(sk, SOCK_LINGER);
}
break;
@@ -1244,17 +1247,11 @@ set_sndbuf:
break;
case SO_PASSCRED:
- if (valbool)
- set_bit(SOCK_PASSCRED, &sock->flags);
- else
- clear_bit(SOCK_PASSCRED, &sock->flags);
+ assign_bit(SOCK_PASSCRED, &sock->flags, valbool);
break;
case SO_PASSPIDFD:
- if (valbool)
- set_bit(SOCK_PASSPIDFD, &sock->flags);
- else
- clear_bit(SOCK_PASSPIDFD, &sock->flags);
+ assign_bit(SOCK_PASSPIDFD, &sock->flags, valbool);
break;
case SO_TIMESTAMP_OLD:
@@ -1280,14 +1277,19 @@ set_sndbuf:
break;
case SO_RCVLOWAT:
+ {
+ int (*set_rcvlowat)(struct sock *sk, int val) = NULL;
+
if (val < 0)
val = INT_MAX;
- if (sock && sock->ops->set_rcvlowat)
- ret = sock->ops->set_rcvlowat(sk, val);
+ if (sock)
+ set_rcvlowat = READ_ONCE(sock->ops)->set_rcvlowat;
+ if (set_rcvlowat)
+ ret = set_rcvlowat(sk, val);
else
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
break;
-
+ }
case SO_RCVTIMEO_OLD:
case SO_RCVTIMEO_NEW:
ret = sock_set_timeout(&sk->sk_rcvtimeo, optval,
@@ -1358,10 +1360,7 @@ set_sndbuf:
break;
case SO_PASSSEC:
- if (valbool)
- set_bit(SOCK_PASSSEC, &sock->flags);
- else
- clear_bit(SOCK_PASSSEC, &sock->flags);
+ assign_bit(SOCK_PASSSEC, &sock->flags, valbool);
break;
case SO_MARK:
if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
@@ -1385,11 +1384,16 @@ set_sndbuf:
break;
case SO_PEEK_OFF:
- if (sock->ops->set_peek_off)
- ret = sock->ops->set_peek_off(sk, val);
+ {
+ int (*set_peek_off)(struct sock *sk, int val);
+
+ set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
+ if (set_peek_off)
+ ret = set_peek_off(sk, val);
else
ret = -EOPNOTSUPP;
break;
+ }
case SO_NOFCS:
sock_valbool_flag(sk, SOCK_NOFCS, valbool);
@@ -1438,7 +1442,8 @@ set_sndbuf:
cmpxchg(&sk->sk_pacing_status,
SK_PACING_NONE,
SK_PACING_NEEDED);
- sk->sk_max_pacing_rate = ulval;
+ /* Pairs with READ_ONCE() from sk_getsockopt() */
+ WRITE_ONCE(sk->sk_max_pacing_rate, ulval);
sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval);
break;
}
@@ -1533,7 +1538,9 @@ set_sndbuf:
}
if ((u8)val == SOCK_TXREHASH_DEFAULT)
val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
- /* Paired with READ_ONCE() in tcp_rtx_synack() */
+ /* Paired with READ_ONCE() in tcp_rtx_synack()
+ * and sk_getsockopt().
+ */
WRITE_ONCE(sk->sk_txrehash, (u8)val);
break;
@@ -1633,11 +1640,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_SNDBUF:
- v.val = sk->sk_sndbuf;
+ v.val = READ_ONCE(sk->sk_sndbuf);
break;
case SO_RCVBUF:
- v.val = sk->sk_rcvbuf;
+ v.val = READ_ONCE(sk->sk_rcvbuf);
break;
case SO_REUSEADDR:
@@ -1679,13 +1686,13 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_PRIORITY:
- v.val = sk->sk_priority;
+ v.val = READ_ONCE(sk->sk_priority);
break;
case SO_LINGER:
lv = sizeof(v.ling);
v.ling.l_onoff = sock_flag(sk, SOCK_LINGER);
- v.ling.l_linger = sk->sk_lingertime / HZ;
+ v.ling.l_linger = READ_ONCE(sk->sk_lingertime) / HZ;
break;
case SO_BSDCOMPAT:
@@ -1717,16 +1724,18 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
case SO_RCVTIMEO_OLD:
case SO_RCVTIMEO_NEW:
- lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname);
+ lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v,
+ SO_RCVTIMEO_OLD == optname);
break;
case SO_SNDTIMEO_OLD:
case SO_SNDTIMEO_NEW:
- lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname);
+ lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v,
+ SO_SNDTIMEO_OLD == optname);
break;
case SO_RCVLOWAT:
- v.val = sk->sk_rcvlowat;
+ v.val = READ_ONCE(sk->sk_rcvlowat);
break;
case SO_SNDLOWAT:
@@ -1770,7 +1779,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
spin_unlock(&sk->sk_peer_lock);
if (!peer_pid)
- return -ESRCH;
+ return -ENODATA;
pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file);
put_pid(peer_pid);
@@ -1815,14 +1824,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
case SO_PEERNAME:
{
- char address[128];
+ struct sockaddr_storage address;
- lv = sock->ops->getname(sock, (struct sockaddr *)address, 2);
+ lv = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 2);
if (lv < 0)
return -ENOTCONN;
if (lv < len)
return -EINVAL;
- if (copy_to_sockptr(optval, address, len))
+ if (copy_to_sockptr(optval, &address, len))
return -EFAULT;
goto lenout;
}
@@ -1843,7 +1852,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
optval, optlen, len);
case SO_MARK:
- v.val = sk->sk_mark;
+ v.val = READ_ONCE(sk->sk_mark);
break;
case SO_RCVMARK:
@@ -1859,10 +1868,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_PEEK_OFF:
- if (!sock->ops->set_peek_off)
+ if (!READ_ONCE(sock->ops)->set_peek_off)
return -EOPNOTSUPP;
- v.val = sk->sk_peek_off;
+ v.val = READ_ONCE(sk->sk_peek_off);
break;
case SO_NOFCS:
v.val = sock_flag(sk, SOCK_NOFCS);
@@ -1892,7 +1901,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
- v.val = sk->sk_ll_usec;
+ v.val = READ_ONCE(sk->sk_ll_usec);
break;
case SO_PREFER_BUSY_POLL:
v.val = READ_ONCE(sk->sk_prefer_busy_poll);
@@ -1900,12 +1909,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
#endif
case SO_MAX_PACING_RATE:
+ /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */
if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) {
lv = sizeof(v.ulval);
- v.ulval = sk->sk_max_pacing_rate;
+ v.ulval = READ_ONCE(sk->sk_max_pacing_rate);
} else {
/* 32bit version */
- v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U);
+ v.val = min_t(unsigned long, ~0U,
+ READ_ONCE(sk->sk_max_pacing_rate));
}
break;
@@ -1973,11 +1984,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_RESERVE_MEM:
- v.val = sk->sk_reserved_mem;
+ v.val = READ_ONCE(sk->sk_reserved_mem);
break;
case SO_TXREHASH:
- v.val = sk->sk_txrehash;
+ /* Paired with WRITE_ONCE() in sk_setsockopt() */
+ v.val = READ_ONCE(sk->sk_txrehash);
break;
default:
@@ -3148,7 +3160,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount)
if (mem_cgroup_sockets_enabled && sk->sk_memcg)
mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
- if (sk_under_memory_pressure(sk) &&
+ if (sk_under_global_memory_pressure(sk) &&
(sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
sk_leave_memory_pressure(sk);
}
@@ -3168,7 +3180,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim);
int sk_set_peek_off(struct sock *sk, int val)
{
- sk->sk_peek_off = val;
+ WRITE_ONCE(sk->sk_peek_off, val);
return 0;
}
EXPORT_SYMBOL_GPL(sk_set_peek_off);
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-05 12:21:47 +0000