1 files changed, 82 insertions, 103 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 6c4acf1f0220..e4f40b175acb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -113,6 +113,7 @@
 #include <linux/static_key.h>
 #include <linux/memcontrol.h>
 #include <linux/prefetch.h>
+#include <linux/compat.h>
 
 #include <linux/uaccess.h>
 
@@ -360,7 +361,8 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
 	return sizeof(tv);
 }
 
-static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval)
+static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
+			    bool old_timeval)
 {
 	struct __kernel_sock_timeval tv;
 
@@ -370,7 +372,7 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool
 		if (optlen < sizeof(tv32))
 			return -EINVAL;
 
-		if (copy_from_user(&tv32, optval, sizeof(tv32)))
+		if (copy_from_sockptr(&tv32, optval, sizeof(tv32)))
 			return -EFAULT;
 		tv.tv_sec = tv32.tv_sec;
 		tv.tv_usec = tv32.tv_usec;
@@ -379,14 +381,14 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool
 
 		if (optlen < sizeof(old_tv))
 			return -EINVAL;
-		if (copy_from_user(&old_tv, optval, sizeof(old_tv)))
+		if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv)))
 			return -EFAULT;
 		tv.tv_sec = old_tv.tv_sec;
 		tv.tv_usec = old_tv.tv_usec;
 	} else {
 		if (optlen < sizeof(tv))
 			return -EINVAL;
-		if (copy_from_user(&tv, optval, sizeof(tv)))
+		if (copy_from_sockptr(&tv, optval, sizeof(tv)))
 			return -EFAULT;
 	}
 	if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
@@ -608,8 +610,7 @@ int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk)
 }
 EXPORT_SYMBOL(sock_bindtoindex);
 
-static int sock_setbindtodevice(struct sock *sk, char __user *optval,
-				int optlen)
+static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen)
 {
 	int ret = -ENOPROTOOPT;
 #ifdef CONFIG_NETDEVICES
@@ -631,7 +632,7 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
 	memset(devname, 0, sizeof(devname));
 
 	ret = -EFAULT;
-	if (copy_from_user(devname, optval, optlen))
+	if (copy_from_sockptr(devname, optval, optlen))
 		goto out;
 
 	index = 0;
@@ -695,15 +696,6 @@ out:
 	return ret;
 }
 
-static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit,
-				     int valbool)
-{
-	if (valbool)
-		sock_set_flag(sk, bit);
-	else
-		sock_reset_flag(sk, bit);
-}
-
 bool sk_mc_loop(struct sock *sk)
 {
 	if (dev_recursion_level())
@@ -718,7 +710,7 @@ bool sk_mc_loop(struct sock *sk)
 		return inet6_sk(sk)->mc_loop;
 #endif
 	}
-	WARN_ON(1);
+	WARN_ON_ONCE(1);
 	return true;
 }
 EXPORT_SYMBOL(sk_mc_loop);
@@ -828,13 +820,21 @@ void sock_set_rcvbuf(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(sock_set_rcvbuf);
 
+void sock_set_mark(struct sock *sk, u32 val)
+{
+	lock_sock(sk);
+	sk->sk_mark = val;
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sock_set_mark);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
  */
 
 int sock_setsockopt(struct socket *sock, int level, int optname,
-		    char __user *optval, unsigned int optlen)
+		    sockptr_t optval, unsigned int optlen)
 {
 	struct sock_txtime sk_txtime;
 	struct sock *sk = sock->sk;
@@ -853,7 +853,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
-	if (get_user(val, (int __user *)optval))
+	if (copy_from_sockptr(&val, optval, sizeof(val)))
 		return -EFAULT;
 
 	valbool = val ? 1 : 0;
@@ -966,7 +966,7 @@ set_sndbuf:
 			ret = -EINVAL;	/* 1003.1g */
 			break;
 		}
-		if (copy_from_user(&ling, optval, sizeof(ling))) {
+		if (copy_from_sockptr(&ling, optval, sizeof(ling))) {
 			ret = -EFAULT;
 			break;
 		}
@@ -1060,60 +1060,52 @@ set_sndbuf:
 
 	case SO_RCVTIMEO_OLD:
 	case SO_RCVTIMEO_NEW:
-		ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD);
+		ret = sock_set_timeout(&sk->sk_rcvtimeo, optval,
+				       optlen, optname == SO_RCVTIMEO_OLD);
 		break;
 
 	case SO_SNDTIMEO_OLD:
 	case SO_SNDTIMEO_NEW:
-		ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD);
+		ret = sock_set_timeout(&sk->sk_sndtimeo, optval,
+				       optlen, optname == SO_SNDTIMEO_OLD);
 		break;
 
-	case SO_ATTACH_FILTER:
-		ret = -EINVAL;
-		if (optlen == sizeof(struct sock_fprog)) {
-			struct sock_fprog fprog;
-
-			ret = -EFAULT;
-			if (copy_from_user(&fprog, optval, sizeof(fprog)))
-				break;
+	case SO_ATTACH_FILTER: {
+		struct sock_fprog fprog;
 
+		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
+		if (!ret)
 			ret = sk_attach_filter(&fprog, sk);
-		}
 		break;
-
+	}
 	case SO_ATTACH_BPF:
 		ret = -EINVAL;
 		if (optlen == sizeof(u32)) {
 			u32 ufd;
 
 			ret = -EFAULT;
-			if (copy_from_user(&ufd, optval, sizeof(ufd)))
+			if (copy_from_sockptr(&ufd, optval, sizeof(ufd)))
 				break;
 
 			ret = sk_attach_bpf(ufd, sk);
 		}
 		break;
 
-	case SO_ATTACH_REUSEPORT_CBPF:
-		ret = -EINVAL;
-		if (optlen == sizeof(struct sock_fprog)) {
-			struct sock_fprog fprog;
-
-			ret = -EFAULT;
-			if (copy_from_user(&fprog, optval, sizeof(fprog)))
-				break;
+	case SO_ATTACH_REUSEPORT_CBPF: {
+		struct sock_fprog fprog;
 
+		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
+		if (!ret)
 			ret = sk_reuseport_attach_filter(&fprog, sk);
-		}
 		break;
-
+	}
 	case SO_ATTACH_REUSEPORT_EBPF:
 		ret = -EINVAL;
 		if (optlen == sizeof(u32)) {
 			u32 ufd;
 
 			ret = -EFAULT;
-			if (copy_from_user(&ufd, optval, sizeof(ufd)))
+			if (copy_from_sockptr(&ufd, optval, sizeof(ufd)))
 				break;
 
 			ret = sk_reuseport_attach_bpf(ufd, sk);
@@ -1193,7 +1185,7 @@ set_sndbuf:
 
 		if (sizeof(ulval) != sizeof(val) &&
 		    optlen >= sizeof(ulval) &&
-		    get_user(ulval, (unsigned long __user *)optval)) {
+		    copy_from_sockptr(&ulval, optval, sizeof(ulval))) {
 			ret = -EFAULT;
 			break;
 		}
@@ -1236,7 +1228,7 @@ set_sndbuf:
 		if (optlen != sizeof(struct sock_txtime)) {
 			ret = -EINVAL;
 			break;
-		} else if (copy_from_user(&sk_txtime, optval,
+		} else if (copy_from_sockptr(&sk_txtime, optval,
 			   sizeof(struct sock_txtime))) {
 			ret = -EFAULT;
 			break;
@@ -1767,6 +1759,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		cgroup_sk_alloc(&sk->sk_cgrp_data);
 		sock_update_classid(&sk->sk_cgrp_data);
 		sock_update_netprioidx(&sk->sk_cgrp_data);
+		sk_tx_queue_clear(sk);
 	}
 
 	return sk;
@@ -1925,7 +1918,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		/* sk->sk_memcg will be populated at accept() time */
 		newsk->sk_memcg = NULL;
 
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
+		cgroup_sk_clone(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
 		filter = rcu_dereference(sk->sk_filter);
@@ -1972,7 +1965,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
-		 * (Documentation/RCU/rculist_nulls.txt for details)
+		 * (Documentation/RCU/rculist_nulls.rst for details)
 		 */
 		smp_wmb();
 		refcount_set(&newsk->sk_refcnt, 2);
@@ -1990,6 +1983,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
+		sk_tx_queue_clear(newsk);
 		RCU_INIT_POINTER(newsk->sk_wq, NULL);
 
 		if (newsk->sk_prot->sockets_allocated)
@@ -2271,7 +2265,7 @@ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
 	if (WARN_ON_ONCE(!mem))
 		return;
 	if (nullify)
-		kzfree(mem);
+		kfree_sensitive(mem);
 	else
 		kfree(mem);
 	atomic_sub(size, &sk->sk_omem_alloc);
@@ -2800,20 +2794,6 @@ int sock_no_shutdown(struct socket *sock, int how)
 }
 EXPORT_SYMBOL(sock_no_shutdown);
 
-int sock_no_setsockopt(struct socket *sock, int level, int optname,
-		    char __user *optval, unsigned int optlen)
-{
-	return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL(sock_no_setsockopt);
-
-int sock_no_getsockopt(struct socket *sock, int level, int optname,
-		    char __user *optval, int __user *optlen)
-{
-	return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL(sock_no_getsockopt);
-
 int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 {
 	return -EOPNOTSUPP;
@@ -2840,6 +2820,27 @@ int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *
 }
 EXPORT_SYMBOL(sock_no_mmap);
 
+/*
+ * When a file is received (via SCM_RIGHTS, etc), we must bump the
+ * various sock-based usage counts.
+ */
+void __receive_sock(struct file *file)
+{
+	struct socket *sock;
+	int error;
+
+	/*
+	 * The resulting value of "error" is ignored here since we only
+	 * need to take action when the file is a socket and testing
+	 * "sock" for NULL is sufficient.
+	 */
+	sock = sock_from_file(file, &error);
+	if (sock) {
+		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
+		sock_update_classid(&sock->sk->sk_cgrp_data);
+	}
+}
+
 ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
 {
 	ssize_t res;
@@ -3033,7 +3034,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk_rx_queue_clear(sk);
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
-	 * (Documentation/RCU/rculist_nulls.txt for details)
+	 * (Documentation/RCU/rculist_nulls.rst for details)
 	 */
 	smp_wmb();
 	refcount_set(&sk->sk_refcnt, 1);
@@ -3220,20 +3221,6 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname,
 }
 EXPORT_SYMBOL(sock_common_getsockopt);
 
-#ifdef CONFIG_COMPAT
-int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
-				  char __user *optval, int __user *optlen)
-{
-	struct sock *sk = sock->sk;
-
-	if (sk->sk_prot->compat_getsockopt != NULL)
-		return sk->sk_prot->compat_getsockopt(sk, level, optname,
-						      optval, optlen);
-	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
-}
-EXPORT_SYMBOL(compat_sock_common_getsockopt);
-#endif
-
 int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 			int flags)
 {
@@ -3253,7 +3240,7 @@ EXPORT_SYMBOL(sock_common_recvmsg);
  *	Set socket options on an inet socket.
  */
 int sock_common_setsockopt(struct socket *sock, int level, int optname,
-			   char __user *optval, unsigned int optlen)
+			   sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = sock->sk;
 
@@ -3261,20 +3248,6 @@ int sock_common_setsockopt(struct socket *sock, int level, int optname,
 }
 EXPORT_SYMBOL(sock_common_setsockopt);
 
-#ifdef CONFIG_COMPAT
-int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
-				  char __user *optval, unsigned int optlen)
-{
-	struct sock *sk = sock->sk;
-
-	if (sk->sk_prot->compat_setsockopt != NULL)
-		return sk->sk_prot->compat_setsockopt(sk, level, optname,
-						      optval, optlen);
-	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
-}
-EXPORT_SYMBOL(compat_sock_common_setsockopt);
-#endif
-
 void sk_common_release(struct sock *sk)
 {
 	if (sk->sk_prot->destroy)
@@ -3441,6 +3414,16 @@ static void sock_inuse_add(struct net *net, int val)
 }
 #endif
 
+static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
+{
+	if (!twsk_prot)
+		return;
+	kfree(twsk_prot->twsk_slab_name);
+	twsk_prot->twsk_slab_name = NULL;
+	kmem_cache_destroy(twsk_prot->twsk_slab);
+	twsk_prot->twsk_slab = NULL;
+}
+
 static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 {
 	if (!rsk_prot)
@@ -3511,7 +3494,7 @@ int proto_register(struct proto *prot, int alloc_slab)
 						  prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)
-				goto out_free_timewait_sock_slab_name;
+				goto out_free_timewait_sock_slab;
 		}
 	}
 
@@ -3519,15 +3502,15 @@ int proto_register(struct proto *prot, int alloc_slab)
 	ret = assign_proto_idx(prot);
 	if (ret) {
 		mutex_unlock(&proto_list_mutex);
-		goto out_free_timewait_sock_slab_name;
+		goto out_free_timewait_sock_slab;
 	}
 	list_add(&prot->node, &proto_list);
 	mutex_unlock(&proto_list_mutex);
 	return ret;
 
-out_free_timewait_sock_slab_name:
+out_free_timewait_sock_slab:
 	if (alloc_slab && prot->twsk_prot)
-		kfree(prot->twsk_prot->twsk_slab_name);
+		tw_prot_cleanup(prot->twsk_prot);
 out_free_request_sock_slab:
 	if (alloc_slab) {
 		req_prot_cleanup(prot->rsk_prot);
@@ -3551,12 +3534,7 @@ void proto_unregister(struct proto *prot)
 	prot->slab = NULL;
 
 	req_prot_cleanup(prot->rsk_prot);
-
-	if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
-		kmem_cache_destroy(prot->twsk_prot->twsk_slab);
-		kfree(prot->twsk_prot->twsk_slab_name);
-		prot->twsk_prot->twsk_slab = NULL;
-	}
+	tw_prot_cleanup(prot->twsk_prot);
 }
 EXPORT_SYMBOL(proto_unregister);
 
@@ -3573,6 +3551,7 @@ int sock_load_diag_module(int family, int protocol)
 #ifdef CONFIG_INET
 	if (family == AF_INET &&
 	    protocol != IPPROTO_RAW &&
+	    protocol < MAX_INET_PROTOS &&
 	    !rcu_access_pointer(inet_protos[protocol]))
 		return -ENOENT;
 #endif