sched: Defend cfs and rt bandwidth quota against overflow

When users write some huge number into cpu.cfs_quota_us or
cpu.rt_runtime_us, overflow might happen during to_ratio() shifts of
schedulable checks.

to_ratio() could be altered to avoid unnecessary internal overflow, but
min_cfs_quota_period is less than 1 << BW_SHIFT, so a cutoff would still
be needed. Set a cap MAX_BW for cfs_quota_us and rt_runtime_us to
prevent overflow.

Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Link: https://lkml.kernel.org/r/20200425105248.60093-1-changhuaixin@linux.alibaba.com

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 74fb89b..fa905b6 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7379,6 +7379,8 @@ static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
 static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+/* More than 203 days if BW_SHIFT equals 20. */
+static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -7407,6 +7409,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
                return -EINVAL;
 
        /*
+        * Bound quota to defend quota against overflow during bandwidth shift.
+        */
+       if (quota != RUNTIME_INF && quota > max_cfs_runtime)
+               return -EINVAL;
+
+       /*
         * Prevent race between setting of cfs_rq->runtime_enabled and
         * unthrottle_offline_cfs_rqs().
         */

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index df11d88..6d60ba2 100644 (file)
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -9,6 +9,8 @@
 
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+/* More than 4 hours if BW_SHIFT equals 20. */
+static const u64 max_rt_runtime = MAX_BW;
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
@@ -2585,6 +2587,12 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
        if (rt_period == 0)
                return -EINVAL;
 
+       /*
+        * Bound quota to defend quota against overflow during bandwidth shift.
+        */
+       if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime)
+               return -EINVAL;
+
        mutex_lock(&rt_constraints_mutex);
        err = __rt_schedulable(tg, rt_period, rt_runtime);
        if (err)
@@ -2702,7 +2710,9 @@ static int sched_rt_global_validate(void)
                return -EINVAL;
 
        if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
-               (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+               ((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
+                ((u64)sysctl_sched_rt_runtime *
+                       NSEC_PER_USEC > max_rt_runtime)))
                return -EINVAL;
 
        return 0;

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2bd2a22..f7ab633 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1915,6 +1915,8 @@ extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
 #define BW_SHIFT               20
 #define BW_UNIT                        (1 << BW_SHIFT)
 #define RATIO_SHIFT            8
+#define MAX_BW_BITS            (64 - BW_SHIFT)
+#define MAX_BW                 ((1ULL << MAX_BW_BITS) - 1)
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);