summaryrefslogtreecommitdiff
path: root/net/socket.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/socket.c')
-rw-r--r--net/socket.c211
1 files changed, 120 insertions, 91 deletions
diff --git a/net/socket.c b/net/socket.c
index 88f759adf3af..c226aceee65b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -104,6 +104,12 @@
#include <linux/route.h>
#include <linux/sockios.h>
#include <linux/atalk.h>
+#include <net/busy_poll.h>
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+unsigned int sysctl_net_busy_read __read_mostly;
+unsigned int sysctl_net_busy_poll __read_mostly;
+#endif
static int sock_no_open(struct inode *irrelevant, struct file *dontcare);
static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
@@ -600,7 +606,7 @@ void sock_release(struct socket *sock)
}
EXPORT_SYMBOL(sock_release);
-int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags)
+void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags)
{
*tx_flags = 0;
if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE))
@@ -609,7 +615,6 @@ int sock_tx_timestamp(struct sock *sk, __u8 *tx_flags)
*tx_flags |= SKBTX_SW_TSTAMP;
if (sock_flag(sk, SOCK_WIFI_STATUS))
*tx_flags |= SKBTX_WIFI_STATUS;
- return 0;
}
EXPORT_SYMBOL(sock_tx_timestamp);
@@ -682,16 +687,6 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
}
EXPORT_SYMBOL(kernel_sendmsg);
-static int ktime2ts(ktime_t kt, struct timespec *ts)
-{
- if (kt.tv64) {
- *ts = ktime_to_timespec(kt);
- return 1;
- } else {
- return 0;
- }
-}
-
/*
* called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
*/
@@ -724,17 +719,15 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
memset(ts, 0, sizeof(ts));
- if (skb->tstamp.tv64 &&
- sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) {
- skb_get_timestampns(skb, ts + 0);
+ if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE) &&
+ ktime_to_timespec_cond(skb->tstamp, ts + 0))
empty = 0;
- }
if (shhwtstamps) {
if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) &&
- ktime2ts(shhwtstamps->syststamp, ts + 1))
+ ktime_to_timespec_cond(shhwtstamps->syststamp, ts + 1))
empty = 0;
if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE) &&
- ktime2ts(shhwtstamps->hwtstamp, ts + 2))
+ ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts + 2))
empty = 0;
}
if (!empty)
@@ -861,11 +854,6 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
}
EXPORT_SYMBOL(kernel_recvmsg);
-static void sock_aio_dtor(struct kiocb *iocb)
-{
- kfree(iocb->private);
-}
-
static ssize_t sock_sendpage(struct file *file, struct page *page,
int offset, size_t size, loff_t *ppos, int more)
{
@@ -896,12 +884,8 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
struct sock_iocb *siocb)
{
- if (!is_sync_kiocb(iocb)) {
- siocb = kmalloc(sizeof(*siocb), GFP_KERNEL);
- if (!siocb)
- return NULL;
- iocb->ki_dtor = sock_aio_dtor;
- }
+ if (!is_sync_kiocb(iocb))
+ BUG();
siocb->kiocb = iocb;
iocb->private = siocb;
@@ -938,7 +922,7 @@ static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
if (pos != 0)
return -ESPIPE;
- if (iocb->ki_left == 0) /* Match SYS5 behaviour */
+ if (iocb->ki_nbytes == 0) /* Match SYS5 behaviour */
return 0;
@@ -1155,13 +1139,24 @@ EXPORT_SYMBOL(sock_create_lite);
/* No kernel lock held - perfect */
static unsigned int sock_poll(struct file *file, poll_table *wait)
{
+ unsigned int busy_flag = 0;
struct socket *sock;
/*
* We can't return errors to poll, so it's either yes or no.
*/
sock = file->private_data;
- return sock->ops->poll(file, sock, wait);
+
+ if (sk_can_busy_loop(sock->sk)) {
+ /* this socket can poll_ll so tell the system call */
+ busy_flag = POLL_BUSY_LOOP;
+
+ /* once, only if requested by syscall */
+ if (wait && (wait->_key & POLL_BUSY_LOOP))
+ sk_busy_loop(sock->sk, 1);
+ }
+
+ return busy_flag | sock->ops->poll(file, sock, wait);
}
static int sock_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1173,15 +1168,6 @@ static int sock_mmap(struct file *file, struct vm_area_struct *vma)
static int sock_close(struct inode *inode, struct file *filp)
{
- /*
- * It was possible the inode is NULL we were
- * closing an unfinished socket.
- */
-
- if (!inode) {
- printk(KERN_DEBUG "sock_close: NULL inode\n");
- return 0;
- }
sock_release(SOCKET_I(inode));
return 0;
}
@@ -1978,7 +1964,17 @@ struct used_address {
unsigned int name_len;
};
-static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+ struct msghdr __user *umsg)
+{
+ if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
+ return -EFAULT;
+ if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+ return -EINVAL;
+ return 0;
+}
+
+static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
struct msghdr *msg_sys, unsigned int flags,
struct used_address *used_address)
{
@@ -1996,8 +1992,11 @@ static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
@@ -2093,22 +2092,30 @@ out:
* BSD sendmsg interface
*/
-SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags)
+long __sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags)
{
int fput_needed, err;
struct msghdr msg_sys;
- struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed);
+ struct socket *sock;
+ sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
- err = __sys_sendmsg(sock, msg, &msg_sys, flags, NULL);
+ err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL);
fput_light(sock->file, fput_needed);
out:
return err;
}
+SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned int, flags)
+{
+ if (flags & MSG_CMSG_COMPAT)
+ return -EINVAL;
+ return __sys_sendmsg(fd, msg, flags);
+}
+
/*
* Linux sendmmsg interface
*/
@@ -2139,15 +2146,16 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
while (datagrams < vlen) {
if (MSG_CMSG_COMPAT & flags) {
- err = __sys_sendmsg(sock, (struct msghdr __user *)compat_entry,
- &msg_sys, flags, &used_address);
+ err = ___sys_sendmsg(sock, (struct msghdr __user *)compat_entry,
+ &msg_sys, flags, &used_address);
if (err < 0)
break;
err = __put_user(err, &compat_entry->msg_len);
++compat_entry;
} else {
- err = __sys_sendmsg(sock, (struct msghdr __user *)entry,
- &msg_sys, flags, &used_address);
+ err = ___sys_sendmsg(sock,
+ (struct msghdr __user *)entry,
+ &msg_sys, flags, &used_address);
if (err < 0)
break;
err = put_user(err, &entry->msg_len);
@@ -2171,10 +2179,12 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg,
unsigned int, vlen, unsigned int, flags)
{
+ if (flags & MSG_CMSG_COMPAT)
+ return -EINVAL;
return __sys_sendmmsg(fd, mmsg, vlen, flags);
}
-static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
+static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
struct msghdr *msg_sys, unsigned int flags, int nosec)
{
struct compat_msghdr __user *msg_compat =
@@ -2194,8 +2204,11 @@ static int __sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
@@ -2266,23 +2279,31 @@ out:
* BSD recvmsg interface
*/
-SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg,
- unsigned int, flags)
+long __sys_recvmsg(int fd, struct msghdr __user *msg, unsigned flags)
{
int fput_needed, err;
struct msghdr msg_sys;
- struct socket *sock = sockfd_lookup_light(fd, &err, &fput_needed);
+ struct socket *sock;
+ sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
- err = __sys_recvmsg(sock, msg, &msg_sys, flags, 0);
+ err = ___sys_recvmsg(sock, msg, &msg_sys, flags, 0);
fput_light(sock->file, fput_needed);
out:
return err;
}
+SYSCALL_DEFINE3(recvmsg, int, fd, struct msghdr __user *, msg,
+ unsigned int, flags)
+{
+ if (flags & MSG_CMSG_COMPAT)
+ return -EINVAL;
+ return __sys_recvmsg(fd, msg, flags);
+}
+
/*
* Linux recvmmsg interface
*/
@@ -2320,17 +2341,18 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
* No need to ask LSM for more than the first datagram.
*/
if (MSG_CMSG_COMPAT & flags) {
- err = __sys_recvmsg(sock, (struct msghdr __user *)compat_entry,
- &msg_sys, flags & ~MSG_WAITFORONE,
- datagrams);
+ err = ___sys_recvmsg(sock, (struct msghdr __user *)compat_entry,
+ &msg_sys, flags & ~MSG_WAITFORONE,
+ datagrams);
if (err < 0)
break;
err = __put_user(err, &compat_entry->msg_len);
++compat_entry;
} else {
- err = __sys_recvmsg(sock, (struct msghdr __user *)entry,
- &msg_sys, flags & ~MSG_WAITFORONE,
- datagrams);
+ err = ___sys_recvmsg(sock,
+ (struct msghdr __user *)entry,
+ &msg_sys, flags & ~MSG_WAITFORONE,
+ datagrams);
if (err < 0)
break;
err = put_user(err, &entry->msg_len);
@@ -2397,6 +2419,9 @@ SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
int datagrams;
struct timespec timeout_sys;
+ if (flags & MSG_CMSG_COMPAT)
+ return -EINVAL;
+
if (!timeout)
return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL);
@@ -2434,7 +2459,7 @@ static const unsigned char nargs[21] = {
SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
{
- unsigned long a[6];
+ unsigned long a[AUDITSC_ARGS];
unsigned long a0, a1;
int err;
unsigned int len;
@@ -2450,7 +2475,9 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
if (copy_from_user(a, args, len))
return -EFAULT;
- audit_socketcall(nargs[call] / sizeof(unsigned long), a);
+ err = audit_socketcall(nargs[call] / sizeof(unsigned long), a);
+ if (err)
+ return err;
a0 = a[0];
a1 = a[1];
@@ -2632,7 +2659,9 @@ static int __init sock_init(void)
*/
#ifdef CONFIG_NETFILTER
- netfilter_init();
+ err = netfilter_init();
+ if (err)
+ goto out;
#endif
#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
@@ -3050,12 +3079,12 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
uifmap32 = &uifr32->ifr_ifru.ifru_map;
err = copy_from_user(&ifr, uifr32, sizeof(ifr.ifr_name));
- err |= __get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
- err |= __get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
- err |= __get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
- err |= __get_user(ifr.ifr_map.irq, &uifmap32->irq);
- err |= __get_user(ifr.ifr_map.dma, &uifmap32->dma);
- err |= __get_user(ifr.ifr_map.port, &uifmap32->port);
+ err |= get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
+ err |= get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
+ err |= get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
+ err |= get_user(ifr.ifr_map.irq, &uifmap32->irq);
+ err |= get_user(ifr.ifr_map.dma, &uifmap32->dma);
+ err |= get_user(ifr.ifr_map.port, &uifmap32->port);
if (err)
return -EFAULT;
@@ -3066,12 +3095,12 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
if (cmd == SIOCGIFMAP && !err) {
err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name));
- err |= __put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
- err |= __put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
- err |= __put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
- err |= __put_user(ifr.ifr_map.irq, &uifmap32->irq);
- err |= __put_user(ifr.ifr_map.dma, &uifmap32->dma);
- err |= __put_user(ifr.ifr_map.port, &uifmap32->port);
+ err |= put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start);
+ err |= put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end);
+ err |= put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr);
+ err |= put_user(ifr.ifr_map.irq, &uifmap32->irq);
+ err |= put_user(ifr.ifr_map.dma, &uifmap32->dma);
+ err |= put_user(ifr.ifr_map.port, &uifmap32->port);
if (err)
err = -EFAULT;
}
@@ -3145,25 +3174,25 @@ static int routing_ioctl(struct net *net, struct socket *sock,
struct in6_rtmsg32 __user *ur6 = argp;
ret = copy_from_user(&r6.rtmsg_dst, &(ur6->rtmsg_dst),
3 * sizeof(struct in6_addr));
- ret |= __get_user(r6.rtmsg_type, &(ur6->rtmsg_type));
- ret |= __get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
- ret |= __get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
- ret |= __get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric));
- ret |= __get_user(r6.rtmsg_info, &(ur6->rtmsg_info));
- ret |= __get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags));
- ret |= __get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));
+ ret |= get_user(r6.rtmsg_type, &(ur6->rtmsg_type));
+ ret |= get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len));
+ ret |= get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len));
+ ret |= get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric));
+ ret |= get_user(r6.rtmsg_info, &(ur6->rtmsg_info));
+ ret |= get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags));
+ ret |= get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex));
r = (void *) &r6;
} else { /* ipv4 */
struct rtentry32 __user *ur4 = argp;
ret = copy_from_user(&r4.rt_dst, &(ur4->rt_dst),
3 * sizeof(struct sockaddr));
- ret |= __get_user(r4.rt_flags, &(ur4->rt_flags));
- ret |= __get_user(r4.rt_metric, &(ur4->rt_metric));
- ret |= __get_user(r4.rt_mtu, &(ur4->rt_mtu));
- ret |= __get_user(r4.rt_window, &(ur4->rt_window));
- ret |= __get_user(r4.rt_irtt, &(ur4->rt_irtt));
- ret |= __get_user(rtdev, &(ur4->rt_dev));
+ ret |= get_user(r4.rt_flags, &(ur4->rt_flags));
+ ret |= get_user(r4.rt_metric, &(ur4->rt_metric));
+ ret |= get_user(r4.rt_mtu, &(ur4->rt_mtu));
+ ret |= get_user(r4.rt_window, &(ur4->rt_window));
+ ret |= get_user(r4.rt_irtt, &(ur4->rt_irtt));
+ ret |= get_user(rtdev, &(ur4->rt_dev));
if (rtdev) {
ret |= copy_from_user(devname, compat_ptr(rtdev), 15);
r4.rt_dev = (char __user __force *)devname;
generated by cgit (git 2.34.1) at 2025-08-14 09:56:00 +0000