Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Vincent Guittot <vincent.guittot@linaro.org>
To:     mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com,
        dietmar.eggemann@arm.com, rostedt@goodmis.org, bsegall@google.com,
        mgorman@suse.de, linux-kernel@vger.kernel.org, parth@linux.ibm.com
Cc:     qais.yousef@arm.com, chris.hyser@oracle.com,
        pkondeti@codeaurora.org, valentin.schneider@arm.com,
        patrick.bellasi@matbug.net, David.Laight@aculab.com,
        pjt@google.com, pavel@ucw.cz, tj@kernel.org,
        dhaval.giani@oracle.com, qperret@google.com,
        tim.c.chen@linux.intel.com,
        Vincent Guittot <vincent.guittot@linaro.org>
Subject: [PATCH 3/6] sched: Allow sched_{get,set}attr to change latency_nice of the task
Date:   Fri, 11 Mar 2022 17:14:03 +0100
Message-Id: <20220311161406.23497-4-vincent.guittot@linaro.org>
In-Reply-To: <20220311161406.23497-1-vincent.guittot@linaro.org>
References: <20220311161406.23497-1-vincent.guittot@linaro.org>
Precedence: bulk

From: Parth Shah <parth@linux.ibm.com>

Introduce the latency_nice attribute to sched_attr and provide a
mechanism to change the value with the use of sched_setattr/sched_getattr
syscall.

Also add new flag "SCHED_FLAG_LATENCY_NICE" to hint the change in
latency_nice of the task on every sched_setattr syscall.

Signed-off-by: Parth Shah <parth@linux.ibm.com>
[rebase and add a dedicated __setscheduler_latency ]
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/uapi/linux/sched.h       |  4 +++-
 include/uapi/linux/sched/types.h | 19 +++++++++++++++++++
 kernel/sched/core.c              | 26 ++++++++++++++++++++++++++
 tools/include/uapi/linux/sched.h |  4 +++-
 4 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..b2e932c25be6 100644
--- 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 */
diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h
index f2c4589d4dbf..0aa4e3b6ed59 100644
--- 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
+ * [LATENCY_NICE_MIN..LATENCY_NICE_MAX].
+ *
+ * A task with latency_nice with the value of LATENCY_NICE_MIN can be
+ * taken for a task with lower latency requirements 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 */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 157eef880d1d..3edba1a38ecb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7219,6 +7219,16 @@ static void __setscheduler_params(struct task_struct *p,
 	p->rt_priority = attr->sched_priority;
 	p->normal_prio = normal_prio(p);
 	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_LATENCY(attr->sched_latency_nice);
+		set_latency_weight(p);
+	}
 }
 
 /*
@@ -7345,6 +7355,13 @@ static int __sched_setscheduler(struct task_struct *p,
 			return retval;
 	}
 
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+		if (attr->sched_latency_nice > MAX_LATENCY_NICE)
+			return -EINVAL;
+		if (attr->sched_latency_nice < MIN_LATENCY_NICE)
+			return -EINVAL;
+	}
+
 	if (pi)
 		cpuset_read_lock();
 
@@ -7379,6 +7396,9 @@ static int __sched_setscheduler(struct task_struct *p,
 			goto change;
 		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)
+			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
 		retval = 0;
@@ -7467,6 +7487,7 @@ static int __sched_setscheduler(struct task_struct *p,
 		__setscheduler_params(p, attr);
 		__setscheduler_prio(p, newprio);
 	}
+	__setscheduler_latency(p, attr);
 	__setscheduler_uclamp(p, attr);
 
 	if (queued) {
@@ -7677,6 +7698,9 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	    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?
@@ -7914,6 +7938,8 @@ 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;
+
 #ifdef CONFIG_UCLAMP_TASK
 	/*
 	 * This could race with another potential updater, but this is fine
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 3bac0a8ceab2..ecc4884bfe4b 100644
--- 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 */
-- 
2.17.1