[PATCH 3.12 02/58] unix: properly account for FDs passed over unix sockets

[Jiri Slaby]

From: willy tarreau <w@xxxxxx>

3.12-stable review patch.  If anyone has any objections, please let me know.

===============

[ Upstream commit 712f4aad406bb1ed67f3f98d04c044191f0ff593 ]

It is possible for a process to allocate and accumulate far more FDs than
the process' limit by sending them over a unix socket then closing them
to keep the process' fd count low.

This change addresses this problem by keeping track of the number of FDs
in flight per user and preventing non-privileged processes from having
more FDs in flight than their configured FD limit.

Cc: Michal Kubecek <mkubecek@xxxxxxxx>
Reported-by: socketpair@xxxxxxxxx
Reported-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Acked-by: Hannes Frederic Sowa <hannes@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 include/linux/sched.h |  1 +
 net/unix/af_unix.c    | 24 ++++++++++++++++++++----
 net/unix/garbage.c    | 16 ++++++++++++----
 3 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a4d7d19fc338..3ecea51ea060 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -664,6 +664,7 @@ struct user_struct {
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c5536b7d8ce4..758edb3bd10b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1484,6 +1484,21 @@ static void unix_destruct_scm(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+/*
+ * 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(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
 #define MAX_RECURSION_LEVEL 4
 
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
@@ -1492,6 +1507,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	unsigned char max_level = 0;
 	int unix_sock_count = 0;
 
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
 	for (i = scm->fp->count - 1; i >= 0; i--) {
 		struct sock *sk = unix_get_socket(scm->fp->fp[i]);
 
@@ -1513,10 +1531,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	if (!UNIXCB(skb).fp)
 		return -ENOMEM;
 
-	if (unix_sock_count) {
-		for (i = scm->fp->count - 1; i >= 0; i--)
-			unix_inflight(scm->fp->fp[i]);
-	}
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_inflight(scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 9bc73f87f64a..06730fe6ad9d 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -125,9 +125,12 @@ struct sock *unix_get_socket(struct file *filp)
 void unix_inflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
-		spin_lock(&unix_gc_lock);
+
 		if (atomic_long_inc_return(&u->inflight) == 1) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
@@ -135,22 +138,27 @@ void unix_inflight(struct file *fp)
 			BUG_ON(list_empty(&u->link));
 		}
 		unix_tot_inflight++;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight++;
+	spin_unlock(&unix_gc_lock);
 }
 
 void unix_notinflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
-		spin_lock(&unix_gc_lock);
+
 		BUG_ON(list_empty(&u->link));
 		if (atomic_long_dec_and_test(&u->inflight))
 			list_del_init(&u->link);
 		unix_tot_inflight--;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight--;
+	spin_unlock(&unix_gc_lock);
 }
 
 static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
-- 
2.7.3