From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/net/core/sock.c | 73 ++++++++++++++++++++++++++----------
1 files changed, 52 insertions(+), 21 deletions(-)
diff --git a/kernel/net/core/sock.c b/kernel/net/core/sock.c
index 0506590..76c3dfd 100644
--- a/kernel/net/core/sock.c
+++ b/kernel/net/core/sock.c
@@ -691,7 +691,8 @@
return false;
if (!sk)
return true;
- switch (sk->sk_family) {
+ /* IPV6_ADDRFORM can change sk->sk_family under us. */
+ switch (READ_ONCE(sk->sk_family)) {
case AF_INET:
return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
@@ -1184,7 +1185,8 @@
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;
}
@@ -1332,11 +1334,11 @@
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:
@@ -1423,7 +1425,7 @@
break;
case SO_RCVLOWAT:
- v.val = sk->sk_rcvlowat;
+ v.val = READ_ONCE(sk->sk_rcvlowat);
break;
case SO_SNDLOWAT:
@@ -1517,7 +1519,7 @@
if (!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);
@@ -1547,17 +1549,19 @@
#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;
#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;
@@ -1611,6 +1615,13 @@
case SO_BINDTOIFINDEX:
v.val = sk->sk_bound_dev_if;
+ break;
+
+ case SO_NETNS_COOKIE:
+ lv = sizeof(u64);
+ if (len != lv)
+ return -EINVAL;
+ v.val64 = atomic64_read(&sock_net(sk)->net_cookie);
break;
default:
@@ -2017,7 +2028,6 @@
{
u32 max_segs = 1;
- sk_dst_set(sk, dst);
sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
@@ -2032,6 +2042,7 @@
}
}
sk->sk_gso_max_segs = max_segs;
+ sk_dst_set(sk, dst);
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
@@ -2176,13 +2187,24 @@
}
EXPORT_SYMBOL(sock_i_uid);
+unsigned long __sock_i_ino(struct sock *sk)
+{
+ unsigned long ino;
+
+ read_lock(&sk->sk_callback_lock);
+ ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
+ read_unlock(&sk->sk_callback_lock);
+ return ino;
+}
+EXPORT_SYMBOL(__sock_i_ino);
+
unsigned long sock_i_ino(struct sock *sk)
{
unsigned long ino;
- read_lock_bh(&sk->sk_callback_lock);
- ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
- read_unlock_bh(&sk->sk_callback_lock);
+ local_bh_disable();
+ ino = __sock_i_ino(sk);
+ local_bh_enable();
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
@@ -2301,9 +2323,9 @@
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
break;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
break;
- if (sk->sk_err)
+ if (READ_ONCE(sk->sk_err))
break;
timeo = schedule_timeout(timeo);
}
@@ -2331,7 +2353,7 @@
goto failure;
err = -EPIPE;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
goto failure;
if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
@@ -2711,7 +2733,7 @@
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);
}
@@ -2732,7 +2754,7 @@
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);
@@ -2979,7 +3001,7 @@
}
EXPORT_SYMBOL(sk_stop_timer_sync);
-void sock_init_data(struct socket *sock, struct sock *sk)
+void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid)
{
sk_init_common(sk);
sk->sk_send_head = NULL;
@@ -2998,11 +3020,10 @@
sk->sk_type = sock->type;
RCU_INIT_POINTER(sk->sk_wq, &sock->wq);
sock->sk = sk;
- sk->sk_uid = SOCK_INODE(sock)->i_uid;
} else {
RCU_INIT_POINTER(sk->sk_wq, NULL);
- sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0);
}
+ sk->sk_uid = uid;
rwlock_init(&sk->sk_callback_lock);
if (sk->sk_kern_sock)
@@ -3060,6 +3081,16 @@
refcount_set(&sk->sk_refcnt, 1);
atomic_set(&sk->sk_drops, 0);
}
+EXPORT_SYMBOL(sock_init_data_uid);
+
+void sock_init_data(struct socket *sock, struct sock *sk)
+{
+ kuid_t uid = sock ?
+ SOCK_INODE(sock)->i_uid :
+ make_kuid(sock_net(sk)->user_ns, 0);
+
+ sock_init_data_uid(sock, sk, uid);
+}
EXPORT_SYMBOL(sock_init_data);
void lock_sock_nested(struct sock *sk, int subclass)
--
Gitblit v1.6.2