[RFC PATCH 5/7] sched/cache: Allow a process to enable cache aware scheduling via prctl

[Tim Chen <tim.c.chen@linux.intel.com>]

Add the PR_SCHED_CACHE_ENABLE and PR_SCHED_CACHE_DISABLE subops to the
PR_SCHED_CACHE prctl interface, allowing a process to turn cache aware
scheduling on or off.

int prctl(PR_SCHED_CACHE, unsigned long subop, pid_t pid,
          unsigned long cookie, unsigned long type);

/* disable cache aware scheduling for this task */
prctl(PR_SCHED_CACHE, PR_SCHED_CACHE_DISABLE, 0, 0, PIDTYPE_PID);

/* enable cache aware scheduling for this task */
prctl(PR_SCHED_CACHE, PR_SCHED_CACHE_ENABLE, 0, 0, PIDTYPE_PID);

pid 0 targets the calling task; otherwise the group of the given pid is
used. Both return -ENOENT when the task has no cache scheduling group.

Co-developed-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 include/linux/sched.h      |  1 +
 include/uapi/linux/prctl.h |  4 +++-
 kernel/sched/cache_sched.c | 15 +++++++++++++++
 kernel/sched/fair.c        |  6 ++++++
 4 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 79f0079c3aa1..1529730c91a5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2399,6 +2399,7 @@ struct sched_cache_group {
 	unsigned long next_scan;
 	unsigned long footprint;
 	int cpu;
+	int enabled;
 	refcount_t refcnt;
 	struct rcu_head rcu;
 } ____cacheline_aligned_in_smp;
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index fed7bb028f9a..3fb31c4ab7b5 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -421,6 +421,8 @@ struct prctl_mm_map {
 # define PR_SCHED_CACHE_GET		0
 # define PR_SCHED_CACHE_CREATE		1
 # define PR_SCHED_CACHE_SHARE_FROM	2
-# define PR_SCHED_CACHE_MAX		3
+# define PR_SCHED_CACHE_DISABLE		3
+# define PR_SCHED_CACHE_ENABLE		4
+# define PR_SCHED_CACHE_MAX		5
 
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sched/cache_sched.c b/kernel/sched/cache_sched.c
index d1932f0c5ee8..c4ec6c553cca 100644
--- a/kernel/sched/cache_sched.c
+++ b/kernel/sched/cache_sched.c
@@ -60,6 +60,7 @@ static void sched_cache_group_init(struct sched_cache_group *grp,
 	grp->next_scan = jiffies;
 	grp->nr_running_avg = 0;
 	grp->footprint = 0;
+	grp->enabled = 1;
 	refcount_set(&grp->refcnt, 1);
 	/*
 	 * The update to grp->pcpu_sched should not be reordered
@@ -261,6 +262,20 @@ int sched_cache_prctl(int option, unsigned long arg2, unsigned long arg3,
 	}
 
 	switch (arg2) {
+	case PR_SCHED_CACHE_DISABLE:
+	case PR_SCHED_CACHE_ENABLE:
+		/*
+		 * Setting a single task is OK, because the sched_cache_group is
+		 * shared by multiple tasks, setting one equals to setting all.
+		 */
+		grp = task_cache_group_get(dst);
+		if (!grp) {
+			err = -ENOENT;
+			goto out_task;
+		}
+		WRITE_ONCE(grp->enabled, arg2 == PR_SCHED_CACHE_ENABLE);
+
+		goto out_group;
 	case PR_SCHED_CACHE_GET: {
 		unsigned long id = 0;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d422b62ba987..e7c8b031946c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1652,6 +1652,9 @@ static int get_pref_llc(struct task_struct *p, struct sched_cache_group *grp)
 	if (!grp)
 		return -1;
 
+	if (!READ_ONCE(grp->enabled))
+		return -1;
+
 	mm_sched_cpu = READ_ONCE(grp->cpu);
 	if (mm_sched_cpu != -1) {
 		mm_sched_llc = llc_id(mm_sched_cpu);
@@ -1743,6 +1746,9 @@ static void task_tick_cache(struct rq *rq, struct task_struct *p)
 	    !grp->pcpu_sched)
 		return;
 
+	if (!READ_ONCE(grp->enabled))
+		return;
+
 	epoch = rq->cpu_epoch;
 	/* avoid moving backwards */
 	if (time_after_eq(grp->epoch, epoch))
-- 
2.32.0