aboutsummaryrefslogtreecommitdiff
path: root/net/core/sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c239
1 files changed, 166 insertions, 73 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index 5440e67bcfe3..c9cffb7acbea 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -114,6 +114,9 @@
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
#include <linux/compat.h>
+#include <linux/mroute.h>
+#include <linux/mroute6.h>
+#include <linux/icmpv6.h>
#include <linux/uaccess.h>
@@ -138,6 +141,7 @@
#include <net/tcp.h>
#include <net/busy_poll.h>
+#include <net/phonet/phonet.h>
#include <linux/ethtool.h>
@@ -425,6 +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;
@@ -435,7 +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",
@@ -443,11 +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;
}
@@ -800,7 +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);
@@ -809,9 +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);
@@ -984,7 +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);
}
}
@@ -1003,7 +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);
}
@@ -1040,7 +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;
}
@@ -1209,7 +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;
@@ -1246,6 +1253,13 @@ set_sndbuf:
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
+ case SO_PASSPIDFD:
+ if (valbool)
+ set_bit(SOCK_PASSPIDFD, &sock->flags);
+ else
+ clear_bit(SOCK_PASSPIDFD, &sock->flags);
+ break;
+
case SO_TIMESTAMP_OLD:
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
@@ -1362,12 +1376,6 @@ set_sndbuf:
__sock_set_mark(sk, val);
break;
case SO_RCVMARK:
- if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
- !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
- ret = -EPERM;
- break;
- }
-
sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
break;
@@ -1433,7 +1441,8 @@ 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;
}
@@ -1528,7 +1537,9 @@ 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;
@@ -1628,11 +1639,11 @@ 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:
@@ -1674,7 +1685,7 @@ 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:
@@ -1712,16 +1723,18 @@ 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:
@@ -1732,6 +1745,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
break;
+ case SO_PASSPIDFD:
+ v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags);
+ break;
+
case SO_PEERCRED:
{
struct ucred peercred;
@@ -1747,6 +1764,39 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
goto lenout;
}
+ case SO_PEERPIDFD:
+ {
+ struct pid *peer_pid;
+ struct file *pidfd_file = NULL;
+ int pidfd;
+
+ if (len > sizeof(pidfd))
+ len = sizeof(pidfd);
+
+ spin_lock(&sk->sk_peer_lock);
+ peer_pid = get_pid(sk->sk_peer_pid);
+ spin_unlock(&sk->sk_peer_lock);
+
+ if (!peer_pid)
+ return -ENODATA;
+
+ pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file);
+ put_pid(peer_pid);
+ if (pidfd < 0)
+ return pidfd;
+
+ if (copy_to_sockptr(optval, &pidfd, len) ||
+ copy_to_sockptr(optlen, &len, sizeof(int))) {
+ put_unused_fd(pidfd);
+ fput(pidfd_file);
+
+ return -EFAULT;
+ }
+
+ fd_install(pidfd, pidfd_file);
+ return 0;
+ }
+
case SO_PEERGROUPS:
{
const struct cred *cred;
@@ -1801,7 +1851,7 @@ 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:
@@ -1820,7 +1870,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
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);
@@ -1850,7 +1900,7 @@ 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);
@@ -1858,12 +1908,14 @@ 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;
@@ -1931,11 +1983,12 @@ 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:
@@ -2381,7 +2434,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
- sk_dst_set(sk, dst);
sk->sk_route_caps = dst->dev->features;
if (sk_is_tcp(sk))
sk->sk_route_caps |= NETIF_F_GSO;
@@ -2400,6 +2452,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
}
}
sk->sk_gso_max_segs = max_segs;
+ sk_dst_set(sk, dst);
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
@@ -2556,13 +2609,24 @@ kuid_t sock_i_uid(struct sock *sk)
}
EXPORT_SYMBOL(sock_i_uid);
-unsigned long sock_i_ino(struct sock *sk)
+unsigned long __sock_i_ino(struct sock *sk)
{
unsigned long ino;
- read_lock_bh(&sk->sk_callback_lock);
+ read_lock(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
- read_unlock_bh(&sk->sk_callback_lock);
+ read_unlock(&sk->sk_callback_lock);
+ return ino;
+}
+EXPORT_SYMBOL(__sock_i_ino);
+
+unsigned long sock_i_ino(struct sock *sk)
+{
+ unsigned long ino;
+
+ local_bh_disable();
+ ino = __sock_i_ino(sk);
+ local_bh_enable();
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
@@ -3095,7 +3159,7 @@ 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);
}
@@ -3115,7 +3179,7 @@ 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);
@@ -3219,36 +3283,6 @@ void __receive_sock(struct file *file)
}
}
-ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
-{
- ssize_t res;
- struct msghdr msg = {.msg_flags = flags};
- struct kvec iov;
- char *kaddr = kmap(page);
- iov.iov_base = kaddr + offset;
- iov.iov_len = size;
- res = kernel_sendmsg(sock, &msg, &iov, 1, size);
- kunmap(page);
- return res;
-}
-EXPORT_SYMBOL(sock_no_sendpage);
-
-ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page,
- int offset, size_t size, int flags)
-{
- ssize_t res;
- struct msghdr msg = {.msg_flags = flags};
- struct kvec iov;
- char *kaddr = kmap(page);
-
- iov.iov_base = kaddr + offset;
- iov.iov_len = size;
- res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size);
- kunmap(page);
- return res;
-}
-EXPORT_SYMBOL(sock_no_sendpage_locked);
-
/*
* Default Socket Callbacks
*/
@@ -4004,7 +4038,7 @@ static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s "
- "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
+ "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
proto->name,
proto->obj_size,
sock_prot_inuse_get(seq_file_net(seq), proto),
@@ -4025,7 +4059,6 @@ static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
proto_method_implemented(proto->getsockopt),
proto_method_implemented(proto->sendmsg),
proto_method_implemented(proto->recvmsg),
- proto_method_implemented(proto->sendpage),
proto_method_implemented(proto->bind),
proto_method_implemented(proto->backlog_rcv),
proto_method_implemented(proto->hash),
@@ -4046,7 +4079,7 @@ static int proto_seq_show(struct seq_file *seq, void *v)
"maxhdr",
"slab",
"module",
- "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
+ "cl co di ac io in de sh ss gs se re bi br ha uh gp em\n");
else
proto_seq_printf(seq, list_entry(v, struct proto, node));
return 0;
@@ -4106,3 +4139,63 @@ int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len)
return sk->sk_prot->bind_add(sk, addr, addr_len);
}
EXPORT_SYMBOL(sock_bind_add);
+
+/* Copy 'size' bytes from userspace and return `size` back to userspace */
+int sock_ioctl_inout(struct sock *sk, unsigned int cmd,
+ void __user *arg, void *karg, size_t size)
+{
+ int ret;
+
+ if (copy_from_user(karg, arg, size))
+ return -EFAULT;
+
+ ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, karg);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(arg, karg, size))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL(sock_ioctl_inout);
+
+/* This is the most common ioctl prep function, where the result (4 bytes) is
+ * copied back to userspace if the ioctl() returns successfully. No input is
+ * copied from userspace as input argument.
+ */
+static int sock_ioctl_out(struct sock *sk, unsigned int cmd, void __user *arg)
+{
+ int ret, karg = 0;
+
+ ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, &karg);
+ if (ret)
+ return ret;
+
+ return put_user(karg, (int __user *)arg);
+}
+
+/* A wrapper around sock ioctls, which copies the data from userspace
+ * (depending on the protocol/ioctl), and copies back the result to userspace.
+ * The main motivation for this function is to pass kernel memory to the
+ * protocol ioctl callbacks, instead of userspace memory.
+ */
+int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
+{
+ int rc = 1;
+
+ if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET)
+ rc = ipmr_sk_ioctl(sk, cmd, arg);
+ else if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET6)
+ rc = ip6mr_sk_ioctl(sk, cmd, arg);
+ else if (sk_is_phonet(sk))
+ rc = phonet_sk_ioctl(sk, cmd, arg);
+
+ /* If ioctl was processed, returns its value */
+ if (rc <= 0)
+ return rc;
+
+ /* Otherwise call the default handler */
+ return sock_ioctl_out(sk, cmd, arg);
+}
+EXPORT_SYMBOL(sk_ioctl);
Powered by cgit, Gruvboxed by Blaster4385.