@@ -567,6 +567,8 @@ struct sched_entity {
/* cached value of my_q->h_nr_running */
unsigned long runnable_weight;
#endif
+ /* preemption offset in ns */
+ long latency_offset;
#ifdef CONFIG_SMP
/*
@@ -783,7 +785,7 @@ struct task_struct {
int static_prio;
int normal_prio;
unsigned int rt_priority;
- int latency_nice;
+ int latency_prio;
struct sched_entity se;
struct sched_rt_entity rt;
@@ -78,7 +78,7 @@ struct task_struct init_task
.prio = MAX_PRIO - 20,
.static_prio = MAX_PRIO - 20,
.normal_prio = MAX_PRIO - 20,
- .latency_nice = DEFAULT_LATENCY_NICE,
+ .latency_prio = NICE_WIDTH - 20,
.policy = SCHED_NORMAL,
.cpus_ptr = &init_task.cpus_mask,
.user_cpus_ptr = NULL,
@@ -1284,6 +1284,16 @@ static void set_load_weight(struct task_struct *p, bool update_load)
}
}
+static void set_latency_offset(struct task_struct *p)
+{
+ long weight = sched_latency_to_weight[p->latency_prio];
+ s64 offset;
+
+ offset = weight * get_sched_latency(false);
+ offset = div_s64(offset, NICE_LATENCY_WEIGHT_MAX);
+ p->se.latency_offset = (long)offset;
+}
+
#ifdef CONFIG_UCLAMP_TASK
/*
* Serializes updates of utilization clamp values
@@ -4559,7 +4569,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
p->prio = p->normal_prio = p->static_prio;
set_load_weight(p, false);
- p->latency_nice = DEFAULT_LATENCY_NICE;
+ p->latency_prio = NICE_TO_LATENCY(0);
+ set_latency_offset(p);
+
/*
* We don't need the reset flag anymore after the fork. It has
* fulfilled its duty:
@@ -7324,8 +7336,10 @@ static void __setscheduler_params(struct task_struct *p,
static void __setscheduler_latency(struct task_struct *p,
const struct sched_attr *attr)
{
- if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE)
- p->latency_nice = attr->sched_latency_nice;
+ if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+ p->latency_prio = NICE_TO_LATENCY(attr->sched_latency_nice);
+ set_latency_offset(p);
+ }
}
/*
@@ -7510,7 +7524,7 @@ static int __sched_setscheduler(struct task_struct *p,
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
goto change;
if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE &&
- attr->sched_latency_nice != p->latency_nice)
+ attr->sched_latency_nice != LATENCY_TO_NICE(p->latency_prio))
goto change;
p->sched_reset_on_fork = reset_on_fork;
@@ -8051,7 +8065,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
get_params(p, &kattr);
kattr.sched_flags &= SCHED_FLAG_ALL;
- kattr.sched_latency_nice = p->latency_nice;
+ kattr.sched_latency_nice = LATENCY_TO_NICE(p->latency_prio);
#ifdef CONFIG_UCLAMP_TASK
/*
@@ -11204,6 +11218,20 @@ const u32 sched_prio_to_wmult[40] = {
/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
+/*
+ * latency weight for wakeup preemption
+ */
+const int sched_latency_to_weight[40] = {
+ /* -20 */ -1024, -973, -922, -870, -819,
+ /* -15 */ -768, -717, -666, -614, -563,
+ /* -10 */ -512, -461, -410, -358, -307,
+ /* -5 */ -256, -205, -154, -102, -51,
+ /* 0 */ 0, 51, 102, 154, 205,
+ /* 5 */ 256, 307, 358, 410, 461,
+ /* 10 */ 512, 563, 614, 666, 717,
+ /* 15 */ 768, 819, 870, 922, 973,
+};
+
void call_trace_sched_update_nr_running(struct rq *rq, int count)
{
trace_sched_update_nr_running_tp(rq, count);
@@ -1042,7 +1042,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
#endif
P(policy);
P(prio);
- P(latency_nice);
+ P(latency_prio);
if (task_has_dl_policy(p)) {
P(dl.runtime);
P(dl.deadline);
@@ -4558,6 +4558,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
update_idle_cfs_rq_clock_pelt(cfs_rq);
}
+static long wakeup_latency_gran(struct sched_entity *curr, struct sched_entity *se);
+
/*
* Preempt the current task with a newly woken task if needed:
*/
@@ -4566,7 +4568,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
unsigned long ideal_runtime, delta_exec;
struct sched_entity *se;
- s64 delta;
+ s64 delta, offset;
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
@@ -4591,10 +4593,12 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
se = __pick_first_entity(cfs_rq);
delta = curr->vruntime - se->vruntime;
- if (delta < 0)
+ offset = wakeup_latency_gran(curr, se);
+ if (delta < offset)
return;
- if (delta > ideal_runtime)
+ if ((delta > ideal_runtime) ||
+ (delta > get_latency_max()))
resched_curr(rq_of(cfs_rq));
}
@@ -5716,6 +5720,35 @@ static int sched_idle_cpu(int cpu)
}
#endif
+static void set_next_buddy(struct sched_entity *se);
+
+static void check_preempt_from_others(struct cfs_rq *cfs, struct sched_entity *se)
+{
+ struct sched_entity *next;
+
+ if (se->latency_offset >= 0)
+ return;
+
+ if (cfs->nr_running <= 1)
+ return;
+ /*
+ * When waking from another class, we don't need to check to preempt at
+ * wakeup and don't set next buddy as a candidate for being picked in
+ * priority.
+ * In case of simultaneous wakeup when current is another class, the
+ * latency sensitive tasks lost opportunity to preempt non sensitive
+ * tasks which woke up simultaneously.
+ */
+
+ if (cfs->next)
+ next = cfs->next;
+ else
+ next = __pick_first_entity(cfs);
+
+ if (next && wakeup_preempt_entity(next, se) == 1)
+ set_next_buddy(se);
+}
+
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
@@ -5802,14 +5835,15 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (!task_new)
update_overutilized_status(rq);
+ if (rq->curr->sched_class != &fair_sched_class)
+ check_preempt_from_others(cfs_rq_of(&p->se), &p->se);
+
enqueue_throttle:
assert_list_leaf_cfs_rq(rq);
hrtick_update(rq);
}
-static void set_next_buddy(struct sched_entity *se);
-
/*
* The dequeue_task method is called before nr_running is
* decreased. We remove the task from the rbtree and
@@ -7128,6 +7162,23 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
}
#endif /* CONFIG_SMP */
+static long wakeup_latency_gran(struct sched_entity *curr, struct sched_entity *se)
+{
+ long latency_offset = se->latency_offset;
+
+ /*
+ * A negative latency offset means that the sched_entity has latency
+ * requirement that needs to be evaluated versus other entity.
+ * Otherwise, use the latency weight to evaluate how much scheduling
+ * delay is acceptable by se.
+ */
+ if ((latency_offset < 0) || (curr->latency_offset < 0))
+ latency_offset -= curr->latency_offset;
+ latency_offset = min_t(long, latency_offset, get_latency_max());
+
+ return latency_offset;
+}
+
static unsigned long wakeup_gran(struct sched_entity *se)
{
unsigned long gran = sysctl_sched_wakeup_granularity;
@@ -7166,11 +7217,12 @@ static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
{
s64 gran, vdiff = curr->vruntime - se->vruntime;
+ s64 offset = wakeup_latency_gran(curr, se);
- if (vdiff <= 0)
+ if (vdiff < offset)
return -1;
- gran = wakeup_gran(se);
+ gran = offset + wakeup_gran(se);
/*
* At wake up, the vruntime of a task is capped to not be older than
@@ -142,6 +142,17 @@ extern int sched_rr_timeslice;
* Default tasks should be treated as a task with latency_nice = 0.
*/
#define DEFAULT_LATENCY_NICE 0
+#define DEFAULT_LATENCY_PRIO (DEFAULT_LATENCY_NICE + LATENCY_NICE_WIDTH/2)
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static latency [ 0..39 ],
+ * and back.
+ */
+#define NICE_TO_LATENCY(nice) ((nice) + DEFAULT_LATENCY_PRIO)
+#define LATENCY_TO_NICE(prio) ((prio) - DEFAULT_LATENCY_PRIO)
+#define NICE_LATENCY_SHIFT (SCHED_FIXEDPOINT_SHIFT)
+#define NICE_LATENCY_WEIGHT_MAX (1L << NICE_LATENCY_SHIFT)
/*
* Increase resolution of nice-level calculations for 64-bit architectures.
@@ -2116,6 +2127,7 @@ static_assert(WF_TTWU == SD_BALANCE_WAKE);
extern const int sched_prio_to_weight[40];
extern const u32 sched_prio_to_wmult[40];
+extern const int sched_latency_to_weight[40];
/*
* {de,en}queue flags: