---

yaml
---
r: 262757
b: refs/heads/master
c: 72fa599
h: refs/heads/master
i:
  262755: 296d235
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 1d229d54dbc26971142f61c3d271a68db236d178
+refs/heads/master: 72fa59970f8698023045ab0713d66f3f4f96945c

trunk/fs/exec.c

@@ -1459,6 +1459,23 @@ static int do_execve_common(const char *filename,
 	struct files_struct *displaced;
 	bool clear_in_exec;
 	int retval;
+	const struct cred *cred = current_cred();
+
+	/*
+	 * We move the actual failure in case of RLIMIT_NPROC excess from
+	 * set*uid() to execve() because too many poorly written programs
+	 * don't check setuid() return code.  Here we additionally recheck
+	 * whether NPROC limit is still exceeded.
+	 */
+	if ((current->flags & PF_NPROC_EXCEEDED) &&
+	    atomic_read(&cred->user->processes) > rlimit(RLIMIT_NPROC)) {
+		retval = -EAGAIN;
+		goto out_ret;
+	}
+
+	/* We're below the limit (still or again), so we don't want to make
+	 * further execve() calls fail. */
+	current->flags &= ~PF_NPROC_EXCEEDED;
 
 	retval = unshare_files(&displaced);
 	if (retval)

trunk/include/linux/sched.h

@@ -1767,6 +1767,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_DUMPCORE	0x00000200	/* dumped core */
 #define PF_SIGNALED	0x00000400	/* killed by a signal */
 #define PF_MEMALLOC	0x00000800	/* Allocating memory */
+#define PF_NPROC_EXCEEDED 0x00001000	/* set_user noticed that RLIMIT_NPROC was exceeded */
 #define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
 #define PF_FREEZING	0x00004000	/* freeze in progress. do not account to load */
 #define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */

trunk/kernel/cred.c

@@ -508,10 +508,8 @@ int commit_creds(struct cred *new)
 		key_fsgid_changed(task);
 
 	/* do it
-	 * - What if a process setreuid()'s and this brings the
-	 *   new uid over his NPROC rlimit?  We can check this now
-	 *   cheaply with the new uid cache, so if it matters
-	 *   we should be checking for it.  -DaveM
+	 * RLIMIT_NPROC limits on user->processes have already been checked
+	 * in set_user().
 	 */
 	alter_cred_subscribers(new, 2);
 	if (new->user != old->user)

trunk/kernel/fork.c

@@ -1111,6 +1111,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		    p->real_cred->user != INIT_USER)
 			goto bad_fork_free;
 	}
+	current->flags &= ~PF_NPROC_EXCEEDED;
 
 	retval = copy_creds(p, clone_flags);
 	if (retval < 0)

trunk/kernel/sys.c

@@ -621,11 +621,18 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
+	/*
+	 * We don't fail in case of NPROC limit excess here because too many
+	 * poorly written programs don't check set*uid() return code, assuming
+	 * it never fails if called by root.  We may still enforce NPROC limit
+	 * for programs doing set*uid()+execve() by harmlessly deferring the
+	 * failure to the execve() stage.
+	 */
 	if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
-			new_user != INIT_USER) {
-		free_uid(new_user);
-		return -EAGAIN;
-	}
+			new_user != INIT_USER)
+		current->flags |= PF_NPROC_EXCEEDED;
+	else
+		current->flags &= ~PF_NPROC_EXCEEDED;
 
 	free_uid(new->user);
 	new->user = new_user;