[PATCH] nice and rt-prio rlimits

Add a pair of rlimits for allowing non-root tasks to raise nice and rt
priorities. Defaults to traditional behavior. Originally written by
Chris Wright.

The patch implements a simple rlimit ceiling for the RT (and nice) priorities
a task can set. The rlimit defaults to 0, meaning no change in behavior by
default. A value of 50 means RT priority levels 1-50 are allowed. A value of
100 means all 99 privilege levels from 1 to 99 are allowed. CAP_SYS_NICE is
blanket permission.

(akpm: see http://www.uwsg.iu.edu/hypermail/linux/kernel/0503.1/1921.html for
tips on integrating this with PAM).

Signed-off-by: Matt Mackall <[e-mail]>
Acked-by: Ingo Molnar <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/asm-generic/resource.h

···
 #define RLIMIT_LOCKS		10	/* maximum file locks held */
 #define RLIMIT_SIGPENDING	11	/* max number of pending signals */
 #define RLIMIT_MSGQUEUE		12	/* maximum bytes in POSIX mqueues */
+#define RLIMIT_NICE		13	/* max nice prio allowed to raise to
+					   0-39 for nice level 19 .. -20 */
+#define RLIMIT_RTPRIO		14	/* maximum realtime priority */
 
-#define RLIM_NLIMITS		13
+#define RLIM_NLIMITS		15
 
 /*
  * SuS says limits have to be unsigned.
···
 	[RLIMIT_LOCKS]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
 	[RLIMIT_SIGPENDING]	= { 		0,	       0 },	\
 	[RLIMIT_MSGQUEUE]	= {   MQ_BYTES_MAX,   MQ_BYTES_MAX },	\
+	[RLIMIT_NICE]		= { 0, 0 },				\
+	[RLIMIT_RTPRIO]		= { 0, 0 },				\
 }
 
 #endif	/* __KERNEL__ */

include/linux/sched.h

···
 extern void set_user_nice(task_t *p, long nice);
 extern int task_prio(const task_t *p);
 extern int task_nice(const task_t *p);
+extern int can_nice(const task_t *p, const int nice);
 extern int task_curr(const task_t *p);
 extern int idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);

kernel/sched.c

···
 
 EXPORT_SYMBOL(set_user_nice);
 
+/*
+ * can_nice - check if a task can reduce its nice value
+ * @p: task
+ * @nice: nice value
+ */
+int can_nice(const task_t *p, const int nice)
+{
+	/* convert nice value [19,-20] to rlimit style value [0,39] */
+	int nice_rlim = 19 - nice;
+	return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+		capable(CAP_SYS_NICE));
+}
+
 #ifdef __ARCH_WANT_SYS_NICE
 
 /*
···
 	 * We don't have to worry. Conceptually one call occurs first
 	 * and we have a single winner.
 	 */
-	if (increment < 0) {
-		if (!capable(CAP_SYS_NICE))
-			return -EPERM;
-		if (increment < -40)
-			increment = -40;
-	}
+	if (increment < -40)
+		increment = -40;
 	if (increment > 40)
 		increment = 40;
 
···
 		nice = -20;
 	if (nice > 19)
 		nice = 19;
+
+	if (increment < 0 && !can_nice(current, nice))
+		return -EPERM;
 
 	retval = security_task_setnice(current, nice);
 	if (retval)
···
 		return -EINVAL;
 
 	if ((policy == SCHED_FIFO || policy == SCHED_RR) &&
+	    param->sched_priority > p->signal->rlim[RLIMIT_RTPRIO].rlim_cur &&
 	    !capable(CAP_SYS_NICE))
 		return -EPERM;
 	if ((current->euid != p->euid) && (current->euid != p->uid) &&

kernel/sys.c

···
 		error = -EPERM;
 		goto out;
 	}
-	if (niceval < task_nice(p) && !capable(CAP_SYS_NICE)) {
+	if (niceval < task_nice(p) && !can_nice(p, niceval)) {
 		error = -EACCES;
 		goto out;
 	}