[PATCH 01/17] sched: Introduce latency-nice as a per-task attribute

From: Peter Zijlstra
Date: Tue Mar 28 2023 - 07:07:40 EST


From: Parth Shah <parth@xxxxxxxxxxxxx>

Latency-nice indicates the latency requirements of a task with respect
to the other tasks in the system. The value of the attribute can be within
the range of [-20, 19] both inclusive to be in-line with the values just
like task nice values.

Just like task nice, -20 is the 'highest' priority and conveys this
task should get minimal latency, conversely 19 is the lowest priority
and conveys this task will get the least consideration and will thus
receive maximal latency.

[peterz: rebase, squash]
Signed-off-by: Parth Shah <parth@xxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
include/linux/sched.h | 1 +
include/uapi/linux/sched.h | 4 +++-
include/uapi/linux/sched/types.h | 19 +++++++++++++++++++
init/init_task.c | 3 ++-
kernel/sched/core.c | 27 ++++++++++++++++++++++++++-
kernel/sched/debug.c | 1 +
tools/include/uapi/linux/sched.h | 4 +++-
7 files changed, 55 insertions(+), 4 deletions(-)

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -784,6 +784,7 @@ struct task_struct {
int static_prio;
int normal_prio;
unsigned int rt_priority;
+ int latency_prio;

struct sched_entity se;
struct sched_rt_entity rt;
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ struct clone_args {
#define SCHED_FLAG_KEEP_PARAMS 0x10
#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+#define SCHED_FLAG_LATENCY_NICE 0x80

#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ struct clone_args {
SCHED_FLAG_RECLAIM | \
SCHED_FLAG_DL_OVERRUN | \
SCHED_FLAG_KEEP_ALL | \
- SCHED_FLAG_UTIL_CLAMP)
+ SCHED_FLAG_UTIL_CLAMP | \
+ SCHED_FLAG_LATENCY_NICE)

#endif /* _UAPI_LINUX_SCHED_H */
--- a/include/uapi/linux/sched/types.h
+++ b/include/uapi/linux/sched/types.h
@@ -10,6 +10,7 @@ struct sched_param {

#define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */
#define SCHED_ATTR_SIZE_VER1 56 /* add: util_{min,max} */
+#define SCHED_ATTR_SIZE_VER2 60 /* add: latency_nice */

/*
* Extended scheduling parameters data structure.
@@ -98,6 +99,22 @@ struct sched_param {
* scheduled on a CPU with no more capacity than the specified value.
*
* A task utilization boundary can be reset by setting the attribute to -1.
+ *
+ * Latency Tolerance Attributes
+ * ===========================
+ *
+ * A subset of sched_attr attributes allows to specify the relative latency
+ * requirements of a task with respect to the other tasks running/queued in the
+ * system.
+ *
+ * @ sched_latency_nice task's latency_nice value
+ *
+ * The latency_nice of a task can have any value in a range of
+ * [MIN_LATENCY_NICE..MAX_LATENCY_NICE].
+ *
+ * A task with latency_nice with the value of LATENCY_NICE_MIN can be
+ * taken for a task requiring a lower latency as opposed to the task with
+ * higher latency_nice.
*/
struct sched_attr {
__u32 size;
@@ -120,6 +137,8 @@ struct sched_attr {
__u32 sched_util_min;
__u32 sched_util_max;

+ /* latency requirement hints */
+ __s32 sched_latency_nice;
};

#endif /* _UAPI_LINUX_SCHED_TYPES_H */
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -78,6 +78,7 @@ struct task_struct init_task
.prio = MAX_PRIO - 20,
.static_prio = MAX_PRIO - 20,
.normal_prio = MAX_PRIO - 20,
+ .latency_prio = DEFAULT_PRIO,
.policy = SCHED_NORMAL,
.cpus_ptr = &init_task.cpus_mask,
.user_cpus_ptr = NULL,
@@ -89,7 +90,7 @@ struct task_struct init_task
.fn = do_no_restart_syscall,
},
.se = {
- .group_node = LIST_HEAD_INIT(init_task.se.group_node),
+ .group_node = LIST_HEAD_INIT(init_task.se.group_node),
},
.rt = {
.run_list = LIST_HEAD_INIT(init_task.rt.run_list),
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4684,6 +4684,8 @@ int sched_fork(unsigned long clone_flags
p->prio = p->normal_prio = p->static_prio;
set_load_weight(p, false);

+ p->latency_prio = NICE_TO_PRIO(0);
+
/*
* We don't need the reset flag anymore after the fork. It has
* fulfilled its duty:
@@ -7428,7 +7430,7 @@ static struct task_struct *find_process_
#define SETPARAM_POLICY -1

static void __setscheduler_params(struct task_struct *p,
- const struct sched_attr *attr)
+ const struct sched_attr *attr)
{
int policy = attr->sched_policy;

@@ -7452,6 +7454,13 @@ static void __setscheduler_params(struct
set_load_weight(p, true);
}

+static void __setscheduler_latency(struct task_struct *p,
+ const struct sched_attr *attr)
+{
+ if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE)
+ p->latency_prio = NICE_TO_PRIO(attr->sched_latency_nice);
+}
+
/*
* Check the target process has a UID that matches the current process's:
*/
@@ -7592,6 +7601,13 @@ static int __sched_setscheduler(struct t
return retval;
}

+ if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+ if (attr->sched_latency_nice > MAX_NICE)
+ return -EINVAL;
+ if (attr->sched_latency_nice < MIN_NICE)
+ return -EINVAL;
+ }
+
if (pi)
cpuset_read_lock();

@@ -7626,6 +7642,9 @@ static int __sched_setscheduler(struct t
goto change;
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
goto change;
+ if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE &&
+ attr->sched_latency_nice != PRIO_TO_NICE(p->latency_prio))
+ goto change;

p->sched_reset_on_fork = reset_on_fork;
retval = 0;
@@ -7714,6 +7733,7 @@ static int __sched_setscheduler(struct t
__setscheduler_params(p, attr);
__setscheduler_prio(p, newprio);
}
+ __setscheduler_latency(p, attr);
__setscheduler_uclamp(p, attr);

if (queued) {
@@ -7924,6 +7944,9 @@ static int sched_copy_attr(struct sched_
size < SCHED_ATTR_SIZE_VER1)
return -EINVAL;

+ if ((attr->sched_flags & SCHED_FLAG_LATENCY_NICE) &&
+ size < SCHED_ATTR_SIZE_VER2)
+ return -EINVAL;
/*
* XXX: Do we want to be lenient like existing syscalls; or do we want
* to be strict and return an error on out-of-bounds values?
@@ -8161,6 +8184,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pi
get_params(p, &kattr);
kattr.sched_flags &= SCHED_FLAG_ALL;

+ kattr.sched_latency_nice = PRIO_TO_NICE(p->latency_prio);
+
#ifdef CONFIG_UCLAMP_TASK
/*
* This could race with another potential updater, but this is fine
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1043,6 +1043,7 @@ void proc_sched_show_task(struct task_st
#endif
P(policy);
P(prio);
+ P(latency_prio);
if (task_has_dl_policy(p)) {
P(dl.runtime);
P(dl.deadline);
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ struct clone_args {
#define SCHED_FLAG_KEEP_PARAMS 0x10
#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+#define SCHED_FLAG_LATENCY_NICE 0x80

#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ struct clone_args {
SCHED_FLAG_RECLAIM | \
SCHED_FLAG_DL_OVERRUN | \
SCHED_FLAG_KEEP_ALL | \
- SCHED_FLAG_UTIL_CLAMP)
+ SCHED_FLAG_UTIL_CLAMP | \
+ SCHED_FLAG_LATENCY_NICE)

#endif /* _UAPI_LINUX_SCHED_H */