1 files changed, 145 insertions, 88 deletions

diff --git a/net/socket.c b/net/socket.c
index 7f64a6eccf63..00da9ce3dba0 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -52,6 +52,7 @@
  *	Based upon Swansea University Computer Society NET3.039
  */
 
+#include <linux/bpf-cgroup.h>
 #include <linux/ethtool.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
@@ -300,7 +301,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 {
 	struct socket_alloc *ei;
 
-	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
+	ei = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
 	init_waitqueue_head(&ei->socket.wq.wait);
@@ -354,7 +355,7 @@ static const struct super_operations sockfs_ops = {
  */
 static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen)
 {
-	return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]",
+	return dynamic_dname(buffer, buflen, "socket:[%lu]",
 				d_inode(dentry)->i_ino);
 }
 
@@ -503,7 +504,7 @@ static int sock_map_fd(struct socket *sock, int flags)
 struct socket *sock_from_file(struct file *file)
 {
 	if (file->f_op == &socket_file_ops)
-		return file->private_data;	/* set in sock_map_fd */
+		return file->private_data;	/* set in sock_alloc_file */
 
 	return NULL;
 }
@@ -682,9 +683,18 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
 {
 	u8 flags = *tx_flags;
 
-	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE)
+	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) {
 		flags |= SKBTX_HW_TSTAMP;
 
+		/* PTP hardware clocks can provide a free running cycle counter
+		 * as a time base for virtual clocks. Tell driver to use the
+		 * free running cycle counter for timestamp if socket is bound
+		 * to virtual clock.
+		 */
+		if (tsflags & SOF_TIMESTAMPING_BIND_PHC)
+			flags |= SKBTX_HW_TSTAMP_USE_CYCLES;
+	}
+
 	if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)
 		flags |= SKBTX_SW_TSTAMP;
 
@@ -795,7 +805,28 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp)
 	return skb->tstamp && !false_tstamp && skb_is_err_queue(skb);
 }
 
-static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
+static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index)
+{
+	bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC;
+	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
+	struct net_device *orig_dev;
+	ktime_t hwtstamp;
+
+	rcu_read_lock();
+	orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
+	if (orig_dev) {
+		*if_index = orig_dev->ifindex;
+		hwtstamp = netdev_get_tstamp(orig_dev, shhwtstamps, cycles);
+	} else {
+		hwtstamp = shhwtstamps->hwtstamp;
+	}
+	rcu_read_unlock();
+
+	return hwtstamp;
+}
+
+static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb,
+			   int if_index)
 {
 	struct scm_ts_pktinfo ts_pktinfo;
 	struct net_device *orig_dev;
@@ -805,11 +836,14 @@ static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 
 	memset(&ts_pktinfo, 0, sizeof(ts_pktinfo));
 
-	rcu_read_lock();
-	orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
-	if (orig_dev)
-		ts_pktinfo.if_index = orig_dev->ifindex;
-	rcu_read_unlock();
+	if (!if_index) {
+		rcu_read_lock();
+		orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
+		if (orig_dev)
+			if_index = orig_dev->ifindex;
+		rcu_read_unlock();
+	}
+	ts_pktinfo.if_index = if_index;
 
 	ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb);
 	put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO,
@@ -829,6 +863,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	int empty = 1, false_tstamp = 0;
 	struct skb_shared_hwtstamps *shhwtstamps =
 		skb_hwtstamps(skb);
+	int if_index;
+	ktime_t hwtstamp;
 
 	/* Race occurred between timestamp enabling and packet
 	   receiving.  Fill in the current time for now. */
@@ -876,16 +912,22 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	if (shhwtstamps &&
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
 	    !skb_is_swtx_tstamp(skb, false_tstamp)) {
+		if_index = 0;
+		if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV)
+			hwtstamp = get_timestamp(sk, skb, &if_index);
+		else
+			hwtstamp = shhwtstamps->hwtstamp;
+
 		if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
-			ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc);
+			hwtstamp = ptp_convert_timestamp(&hwtstamp,
+							 sk->sk_bind_phc);
 
-		if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp,
-					     tss.ts + 2)) {
+		if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) {
 			empty = 0;
 
 			if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
 			    !skb_is_err_queue(skb))
-				put_ts_pktinfo(msg, skb);
+				put_ts_pktinfo(msg, skb, if_index);
 		}
 	}
 	if (!empty) {
@@ -926,13 +968,22 @@ static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
 			sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount);
 }
 
-void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
-	struct sk_buff *skb)
+static void sock_recv_mark(struct msghdr *msg, struct sock *sk,
+			   struct sk_buff *skb)
+{
+	if (sock_flag(sk, SOCK_RCVMARK) && skb)
+		put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32),
+			 &skb->mark);
+}
+
+void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
+		       struct sk_buff *skb)
 {
 	sock_recv_timestamp(msg, sk, skb);
 	sock_recv_drops(msg, sk, skb);
+	sock_recv_mark(msg, sk, skb);
 }
-EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
+EXPORT_SYMBOL_GPL(__sock_recv_cmsgs);
 
 INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *,
 					   size_t, int));
@@ -1534,11 +1585,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct
 }
 EXPORT_SYMBOL(sock_create_kern);
 
-int __sys_socket(int family, int type, int protocol)
+static struct socket *__sys_socket_create(int family, int type, int protocol)
 {
-	int retval;
 	struct socket *sock;
-	int flags;
+	int retval;
 
 	/* Check the SOCK_* constants for consistency.  */
 	BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
@@ -1546,17 +1596,50 @@ int __sys_socket(int family, int type, int protocol)
 	BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
 	BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);
 
-	flags = type & ~SOCK_TYPE_MASK;
-	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
-		return -EINVAL;
+	if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+		return ERR_PTR(-EINVAL);
 	type &= SOCK_TYPE_MASK;
 
+	retval = sock_create(family, type, protocol, &sock);
+	if (retval < 0)
+		return ERR_PTR(retval);
+
+	return sock;
+}
+
+struct file *__sys_socket_file(int family, int type, int protocol)
+{
+	struct socket *sock;
+	struct file *file;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return ERR_CAST(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	retval = sock_create(family, type, protocol, &sock);
-	if (retval < 0)
-		return retval;
+	file = sock_alloc_file(sock, flags, NULL);
+	if (IS_ERR(file))
+		sock_release(sock);
+
+	return file;
+}
+
+int __sys_socket(int family, int type, int protocol)
+{
+	struct socket *sock;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return PTR_ERR(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
+	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
+		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
 	return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
 }
@@ -1718,7 +1801,7 @@ int __sys_listen(int fd, int backlog)
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock) {
-		somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
+		somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn);
 		if ((unsigned int)backlog > somaxconn)
 			backlog = somaxconn;
 
@@ -1795,10 +1878,8 @@ out_fd:
 	return ERR_PTR(err);
 }
 
-int __sys_accept4_file(struct file *file, unsigned file_flags,
-		       struct sockaddr __user *upeer_sockaddr,
-		       int __user *upeer_addrlen, int flags,
-		       unsigned long nofile)
+static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr,
+			      int __user *upeer_addrlen, int flags)
 {
 	struct file *newfile;
 	int newfd;
@@ -1809,11 +1890,11 @@ int __sys_accept4_file(struct file *file, unsigned file_flags,
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	newfd = __get_unused_fd_flags(flags, nofile);
+	newfd = get_unused_fd_flags(flags);
 	if (unlikely(newfd < 0))
 		return newfd;
 
-	newfile = do_accept(file, file_flags, upeer_sockaddr, upeer_addrlen,
+	newfile = do_accept(file, 0, upeer_sockaddr, upeer_addrlen,
 			    flags);
 	if (IS_ERR(newfile)) {
 		put_unused_fd(newfd);
@@ -1843,9 +1924,8 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 
 	f = fdget(fd);
 	if (f.file) {
-		ret = __sys_accept4_file(f.file, 0, upeer_sockaddr,
-						upeer_addrlen, flags,
-						rlimit(RLIMIT_NOFILE));
+		ret = __sys_accept4_file(f.file, upeer_sockaddr,
+					 upeer_addrlen, flags);
 		fdput(f);
 	}
 
@@ -1946,7 +2026,7 @@ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
 	err = sock->ops->getname(sock, (struct sockaddr *)&address, 0);
 	if (err < 0)
 		goto out_put;
-        /* "err" is actually length in this case */
+	/* "err" is actually length in this case */
 	err = move_addr_to_user(&address, err, usockaddr, usockaddr_len);
 
 out_put:
@@ -2023,6 +2103,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
+	msg.msg_ubuf = NULL;
 	if (addr) {
 		err = move_addr_to_kernel(addr, addr_len, &address);
 		if (err < 0)
@@ -2066,10 +2147,13 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
 int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
 		   struct sockaddr __user *addr, int __user *addr_len)
 {
+	struct sockaddr_storage address;
+	struct msghdr msg = {
+		/* Save some cycles and don't copy the address if not needed */
+		.msg_name = addr ? (struct sockaddr *)&address : NULL,
+	};
 	struct socket *sock;
 	struct iovec iov;
-	struct msghdr msg;
-	struct sockaddr_storage address;
 	int err, err2;
 	int fput_needed;
 
@@ -2080,14 +2164,6 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
 	if (!sock)
 		goto out;
 
-	msg.msg_control = NULL;
-	msg.msg_controllen = 0;
-	/* Save some cycles and don't copy the address if not needed */
-	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
-	/* We assume all kernel code knows the size of sockaddr_storage */
-	msg.msg_namelen = 0;
-	msg.msg_iocb = NULL;
-	msg.msg_flags = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, flags);
@@ -2280,24 +2356,20 @@ struct used_address {
 	unsigned int name_len;
 };
 
-int __copy_msghdr_from_user(struct msghdr *kmsg,
-			    struct user_msghdr __user *umsg,
-			    struct sockaddr __user **save_addr,
-			    struct iovec __user **uiov, size_t *nsegs)
+int __copy_msghdr(struct msghdr *kmsg,
+		  struct user_msghdr *msg,
+		  struct sockaddr __user **save_addr)
 {
-	struct user_msghdr msg;
 	ssize_t err;
 
-	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
-		return -EFAULT;
-
 	kmsg->msg_control_is_user = true;
-	kmsg->msg_control_user = msg.msg_control;
-	kmsg->msg_controllen = msg.msg_controllen;
-	kmsg->msg_flags = msg.msg_flags;
+	kmsg->msg_get_inq = 0;
+	kmsg->msg_control_user = msg->msg_control;
+	kmsg->msg_controllen = msg->msg_controllen;
+	kmsg->msg_flags = msg->msg_flags;
 
-	kmsg->msg_namelen = msg.msg_namelen;
-	if (!msg.msg_name)
+	kmsg->msg_namelen = msg->msg_namelen;
+	if (!msg->msg_name)
 		kmsg->msg_namelen = 0;
 
 	if (kmsg->msg_namelen < 0)
@@ -2307,11 +2379,11 @@ int __copy_msghdr_from_user(struct msghdr *kmsg,
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 
 	if (save_addr)
-		*save_addr = msg.msg_name;
+		*save_addr = msg->msg_name;
 
-	if (msg.msg_name && kmsg->msg_namelen) {
+	if (msg->msg_name && kmsg->msg_namelen) {
 		if (!save_addr) {
-			err = move_addr_to_kernel(msg.msg_name,
+			err = move_addr_to_kernel(msg->msg_name,
 						  kmsg->msg_namelen,
 						  kmsg->msg_name);
 			if (err < 0)
@@ -2322,12 +2394,11 @@ int __copy_msghdr_from_user(struct msghdr *kmsg,
 		kmsg->msg_namelen = 0;
 	}
 
-	if (msg.msg_iovlen > UIO_MAXIOV)
+	if (msg->msg_iovlen > UIO_MAXIOV)
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
-	*uiov = msg.msg_iov;
-	*nsegs = msg.msg_iovlen;
+	kmsg->msg_ubuf = NULL;
 	return 0;
 }
 
@@ -2339,8 +2410,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 	struct user_msghdr msg;
 	ssize_t err;
 
-	err = __copy_msghdr_from_user(kmsg, umsg, save_addr, &msg.msg_iov,
-					&msg.msg_iovlen);
+	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
+		return -EFAULT;
+
+	err = __copy_msghdr(kmsg, &msg, save_addr);
 	if (err)
 		return err;
 
@@ -3233,21 +3306,6 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd,
 	return dev_ioctl(net, cmd, &ifreq, data, NULL);
 }
 
-/* Since old style bridge ioctl's endup using SIOCDEVPRIVATE
- * for some operations; this forces use of the newer bridge-utils that
- * use compatible ioctls
- */
-static int old_bridge_ioctl(compat_ulong_t __user *argp)
-{
-	compat_ulong_t tmp;
-
-	if (get_user(tmp, argp))
-		return -EFAULT;
-	if (tmp == BRCTL_GET_VERSION)
-		return BRCTL_VERSION + 1;
-	return -EINVAL;
-}
-
 static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 			 unsigned int cmd, unsigned long arg)
 {
@@ -3259,9 +3317,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 		return sock_ioctl(file, cmd, (unsigned long)argp);
 
 	switch (cmd) {
-	case SIOCSIFBR:
-	case SIOCGIFBR:
-		return old_bridge_ioctl(argp);
 	case SIOCWANDEV:
 		return compat_siocwandev(net, argp);
 	case SIOCGSTAMP_OLD:
@@ -3290,6 +3345,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGSTAMP_NEW:
 	case SIOCGSTAMPNS_NEW:
 	case SIOCGIFCONF:
+	case SIOCSIFBR:
+	case SIOCGIFBR:
 		return sock_ioctl(file, cmd, arg);
 
 	case SIOCGIFFLAGS:
@@ -3460,7 +3517,7 @@ EXPORT_SYMBOL(kernel_connect);
  *	@addr: address holder
  *
  * 	Fills the @addr pointer with the address which the socket is bound.
- *	Returns 0 or an error code.
+ *	Returns the length of the address in bytes or an error code.
  */
 
 int kernel_getsockname(struct socket *sock, struct sockaddr *addr)
@@ -3475,7 +3532,7 @@ EXPORT_SYMBOL(kernel_getsockname);
  *	@addr: address holder
  *
  * 	Fills the @addr pointer with the address which the socket is connected.
- *	Returns 0 or an error code.
+ *	Returns the length of the address in bytes or an error code.
  */
 
 int kernel_getpeername(struct socket *sock, struct sockaddr *addr)