aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched/core.c68
-rw-r--r--kernel/sched/fair.c14
-rw-r--r--kernel/sched/sched.h1
3 files changed, 73 insertions, 10 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fc231d61bcda..2883c22eef10 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9780,7 +9780,8 @@ static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
-static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
+static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
+ u64 burst)
{
int i, ret = 0, runtime_enabled, runtime_was_enabled;
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
@@ -9810,6 +9811,10 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
if (quota != RUNTIME_INF && quota > max_cfs_runtime)
return -EINVAL;
+ if (quota != RUNTIME_INF && (burst > quota ||
+ burst + quota > max_cfs_runtime))
+ return -EINVAL;
+
/*
* Prevent race between setting of cfs_rq->runtime_enabled and
* unthrottle_offline_cfs_rqs().
@@ -9831,6 +9836,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
raw_spin_lock_irq(&cfs_b->lock);
cfs_b->period = ns_to_ktime(period);
cfs_b->quota = quota;
+ cfs_b->burst = burst;
__refill_cfs_bandwidth_runtime(cfs_b);
@@ -9864,9 +9870,10 @@ out_unlock:
static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{
- u64 quota, period;
+ u64 quota, period, burst;
period = ktime_to_ns(tg->cfs_bandwidth.period);
+ burst = tg->cfs_bandwidth.burst;
if (cfs_quota_us < 0)
quota = RUNTIME_INF;
else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
@@ -9874,7 +9881,7 @@ static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
else
return -EINVAL;
- return tg_set_cfs_bandwidth(tg, period, quota);
+ return tg_set_cfs_bandwidth(tg, period, quota, burst);
}
static long tg_get_cfs_quota(struct task_group *tg)
@@ -9892,15 +9899,16 @@ static long tg_get_cfs_quota(struct task_group *tg)
static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{
- u64 quota, period;
+ u64 quota, period, burst;
if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
return -EINVAL;
period = (u64)cfs_period_us * NSEC_PER_USEC;
quota = tg->cfs_bandwidth.quota;
+ burst = tg->cfs_bandwidth.burst;
- return tg_set_cfs_bandwidth(tg, period, quota);
+ return tg_set_cfs_bandwidth(tg, period, quota, burst);
}
static long tg_get_cfs_period(struct task_group *tg)
@@ -9913,6 +9921,30 @@ static long tg_get_cfs_period(struct task_group *tg)
return cfs_period_us;
}
+static int tg_set_cfs_burst(struct task_group *tg, long cfs_burst_us)
+{
+ u64 quota, period, burst;
+
+ if ((u64)cfs_burst_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+
+ burst = (u64)cfs_burst_us * NSEC_PER_USEC;
+ period = ktime_to_ns(tg->cfs_bandwidth.period);
+ quota = tg->cfs_bandwidth.quota;
+
+ return tg_set_cfs_bandwidth(tg, period, quota, burst);
+}
+
+static long tg_get_cfs_burst(struct task_group *tg)
+{
+ u64 burst_us;
+
+ burst_us = tg->cfs_bandwidth.burst;
+ do_div(burst_us, NSEC_PER_USEC);
+
+ return burst_us;
+}
+
static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -9937,6 +9969,18 @@ static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
return tg_set_cfs_period(css_tg(css), cfs_period_us);
}
+static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
+ struct cftype *cft)
+{
+ return tg_get_cfs_burst(css_tg(css));
+}
+
+static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
+ struct cftype *cftype, u64 cfs_burst_us)
+{
+ return tg_set_cfs_burst(css_tg(css), cfs_burst_us);
+}
+
struct cfs_schedulable_data {
struct task_group *tg;
u64 period, quota;
@@ -10090,6 +10134,11 @@ static struct cftype cpu_legacy_files[] = {
.write_u64 = cpu_cfs_period_write_u64,
},
{
+ .name = "cfs_burst_us",
+ .read_u64 = cpu_cfs_burst_read_u64,
+ .write_u64 = cpu_cfs_burst_write_u64,
+ },
+ {
.name = "stat",
.seq_show = cpu_cfs_stat_show,
},
@@ -10254,12 +10303,13 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
{
struct task_group *tg = css_tg(of_css(of));
u64 period = tg_get_cfs_period(tg);
+ u64 burst = tg_get_cfs_burst(tg);
u64 quota;
int ret;
ret = cpu_period_quota_parse(buf, &period, &quota);
if (!ret)
- ret = tg_set_cfs_bandwidth(tg, period, quota);
+ ret = tg_set_cfs_bandwidth(tg, period, quota, burst);
return ret ?: nbytes;
}
#endif
@@ -10286,6 +10336,12 @@ static struct cftype cpu_files[] = {
.seq_show = cpu_max_show,
.write = cpu_max_write,
},
+ {
+ .name = "max.burst",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .read_u64 = cpu_cfs_burst_read_u64,
+ .write_u64 = cpu_cfs_burst_write_u64,
+ },
#endif
#ifdef CONFIG_UCLAMP_TASK_GROUP
{
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7b8990fd4896..4a3e61a88acc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4626,8 +4626,11 @@ static inline u64 sched_cfs_bandwidth_slice(void)
*/
void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
{
- if (cfs_b->quota != RUNTIME_INF)
- cfs_b->runtime = cfs_b->quota;
+ if (unlikely(cfs_b->quota == RUNTIME_INF))
+ return;
+
+ cfs_b->runtime += cfs_b->quota;
+ cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst);
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4988,6 +4991,9 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
cfs_b->nr_periods += overrun;
+ /* Refill extra burst quota even if cfs_b->idle */
+ __refill_cfs_bandwidth_runtime(cfs_b);
+
/*
* idle depends on !throttled (for the case of a large deficit), and if
* we're going inactive then everything else can be deferred
@@ -4995,8 +5001,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
if (cfs_b->idle && !throttled)
goto out_deactivate;
- __refill_cfs_bandwidth_runtime(cfs_b);
-
if (!throttled) {
/* mark as potentially idle for the upcoming period */
cfs_b->idle = 1;
@@ -5246,6 +5250,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
if (new < max_cfs_quota_period) {
cfs_b->period = ns_to_ktime(new);
cfs_b->quota *= 2;
+ cfs_b->burst *= 2;
pr_warn_ratelimited(
"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
@@ -5277,6 +5282,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
cfs_b->runtime = 0;
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
+ cfs_b->burst = 0;
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 01e48f682d54..c80d42e9589b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -366,6 +366,7 @@ struct cfs_bandwidth {
ktime_t period;
u64 quota;
u64 runtime;
+ u64 burst;
s64 hierarchical_quota;
u8 idle;
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-25 04:53:05 +0000