1 files changed, 45 insertions, 70 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a0e8cb24af35..79687d5a95ac 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -118,6 +118,8 @@
 #include <linux/security.h>
 #include <linux/freezer.h>
 
+#include "scm.h"
+
 struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
 EXPORT_SYMBOL_GPL(unix_socket_table);
 DEFINE_SPINLOCK(unix_table_lock);
@@ -1504,78 +1506,51 @@ out:
 	return err;
 }
 
-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_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);
-}
-
-/*
- * 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)
+static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
-	int i;
-	unsigned char max_level = 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]);
-
-		if (sk)
-			max_level = max(max_level,
-					unix_sk(sk)->recursion_level);
-	}
-	if (unlikely(max_level > MAX_RECURSION_LEVEL))
-		return -ETOOMANYREFS;
+	scm->fp = scm_fp_dup(UNIXCB(skb).fp);
 
 	/*
-	 * 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.
+	 * Garbage collection of unix sockets starts by selecting a set of
+	 * candidate sockets which have reference only from being in flight
+	 * (total_refs == inflight_refs).  This condition is checked once during
+	 * the candidate collection phase, and candidates are marked as such, so
+	 * that non-candidates can later be ignored.  While inflight_refs is
+	 * protected by unix_gc_lock, total_refs (file count) is not, hence this
+	 * is an instantaneous decision.
+	 *
+	 * Once a candidate, however, the socket must not be reinstalled into a
+	 * file descriptor while the garbage collection is in progress.
+	 *
+	 * If the above conditions are met, then the directed graph of
+	 * candidates (*) does not change while unix_gc_lock is held.
+	 *
+	 * Any operations that changes the file count through file descriptors
+	 * (dup, close, sendmsg) does not change the graph since candidates are
+	 * not installed in fds.
+	 *
+	 * Dequeing a candidate via recvmsg would install it into an fd, but
+	 * that takes unix_gc_lock to decrement the inflight count, so it's
+	 * serialized with garbage collection.
+	 *
+	 * MSG_PEEK is special in that it does not change the inflight count,
+	 * yet does install the socket into an fd.  The following lock/unlock
+	 * pair is to ensure serialization with garbage collection.  It must be
+	 * done between incrementing the file count and installing the file into
+	 * an fd.
+	 *
+	 * If garbage collection starts after the barrier provided by the
+	 * lock/unlock, then it will see the elevated refcount and not mark this
+	 * as a candidate.  If a garbage collection is already in progress
+	 * before the file count was incremented, then the lock/unlock pair will
+	 * ensure that garbage collection is finished before progressing to
+	 * installing the fd.
+	 *
+	 * (*) A -> B where B is on the queue of A or B is on the queue of C
+	 * which is on the queue of listening socket A.
 	 */
-	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 max_level;
+	spin_lock(&unix_gc_lock);
+	spin_unlock(&unix_gc_lock);
 }
 
 static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
@@ -2203,7 +2178,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 		sk_peek_offset_fwd(sk, size);
 
 		if (UNIXCB(skb).fp)
-			scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+			unix_peek_fds(&scm, skb);
 	}
 	err = (flags & MSG_TRUNC) ? skb->len - skip : size;
 
@@ -2448,7 +2423,7 @@ unlock:
 			/* It is questionable, see note in unix_dgram_recvmsg.
 			 */
 			if (UNIXCB(skb).fp)
-				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+				unix_peek_fds(&scm, skb);
 
 			sk_peek_offset_fwd(sk, chunk);