1 files changed, 76 insertions, 30 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ac1f2bc18fc9..5b41e2321209 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -118,8 +118,6 @@
 #include <linux/btf_ids.h>
 #include <linux/bpf-cgroup.h>
 
-#include "scm.h"
-
 static atomic_long_t unix_nr_socks;
 static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2];
 static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
@@ -782,19 +780,6 @@ static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t,
 				  int);
 
-static int unix_set_peek_off(struct sock *sk, int val)
-{
-	struct unix_sock *u = unix_sk(sk);
-
-	if (mutex_lock_interruptible(&u->iolock))
-		return -EINTR;
-
-	WRITE_ONCE(sk->sk_peek_off, val);
-	mutex_unlock(&u->iolock);
-
-	return 0;
-}
-
 #ifdef CONFIG_PROC_FS
 static int unix_count_nr_fds(struct sock *sk)
 {
@@ -862,7 +847,7 @@ static const struct proto_ops unix_stream_ops = {
 	.read_skb =	unix_stream_read_skb,
 	.mmap =		sock_no_mmap,
 	.splice_read =	unix_stream_splice_read,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -886,7 +871,7 @@ static const struct proto_ops unix_dgram_ops = {
 	.read_skb =	unix_read_skb,
 	.recvmsg =	unix_dgram_recvmsg,
 	.mmap =		sock_no_mmap,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -909,7 +894,7 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.sendmsg =	unix_seqpacket_sendmsg,
 	.recvmsg =	unix_seqpacket_recvmsg,
 	.mmap =		sock_no_mmap,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -993,11 +978,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	sk->sk_write_space	= unix_write_space;
 	sk->sk_max_ack_backlog	= net->unx.sysctl_max_dgram_qlen;
 	sk->sk_destruct		= unix_sock_destructor;
-	u	  = unix_sk(sk);
+	u = unix_sk(sk);
+	u->inflight = 0;
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	spin_lock_init(&u->lock);
-	atomic_long_set(&u->inflight, 0);
 	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->iolock); /* single task reading lock */
 	mutex_init(&u->bindlock); /* single task binding lock */
@@ -1344,13 +1329,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
-	if (sk1 < sk2) {
-		unix_state_lock(sk1);
-		unix_state_lock_nested(sk2);
-	} else {
-		unix_state_lock(sk2);
-		unix_state_lock_nested(sk1);
-	}
+	if (sk1 > sk2)
+		swap(sk1, sk2);
+
+	unix_state_lock(sk1);
+	unix_state_lock_nested(sk2, U_LOCK_SECOND);
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
@@ -1591,7 +1574,7 @@ restart:
 		goto out_unlock;
 	}
 
-	unix_state_lock_nested(sk);
+	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
 	if (sk->sk_state != st) {
 		unix_state_unlock(sk);
@@ -1790,6 +1773,52 @@ out:
 	return err;
 }
 
+/* The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
+static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	int i;
+
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
+	/* Need to duplicate file references for the sake of garbage
+	 * collection.  Otherwise a socket in the fps might become a
+	 * candidate for GC while the skb is not yet queued.
+	 */
+	UNIXCB(skb).fp = scm_fp_dup(scm->fp);
+	if (!UNIXCB(skb).fp)
+		return -ENOMEM;
+
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_inflight(scm->fp->user, scm->fp->fp[i]);
+
+	return 0;
+}
+
+static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	int i;
+
+	scm->fp = UNIXCB(skb).fp;
+	UNIXCB(skb).fp = NULL;
+
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
+}
+
 static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
 	scm->fp = scm_fp_dup(UNIXCB(skb).fp);
@@ -1837,6 +1866,21 @@ static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	spin_unlock(&unix_gc_lock);
 }
 
+static void unix_destruct_scm(struct sk_buff *skb)
+{
+	struct scm_cookie scm;
+
+	memset(&scm, 0, sizeof(scm));
+	scm.pid  = UNIXCB(skb).pid;
+	if (UNIXCB(skb).fp)
+		unix_detach_fds(&scm, skb);
+
+	/* Alas, it calls VFS */
+	/* So fscking what? fput() had been SMP-safe since the last Summer */
+	scm_destroy(&scm);
+	sock_wfree(skb);
+}
+
 static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
 {
 	int err = 0;
@@ -1923,11 +1967,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	long timeo;
 	int err;
 
-	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
+	wait_for_unix_gc(scm.fp);
+
 	err = -EOPNOTSUPP;
 	if (msg->msg_flags&MSG_OOB)
 		goto out;
@@ -2199,11 +2244,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	bool fds_sent = false;
 	int data_len;
 
-	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
+	wait_for_unix_gc(scm.fp);
+
 	err = -EOPNOTSUPP;
 	if (msg->msg_flags & MSG_OOB) {
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)