From 52bf84aa206cd2c2516dfa3e03b578edf8a3242f Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:40 -0500
Subject: sched/numa, mm: Remove p->numa_migrate_deferred

Excessive migration of pages can hurt the performance of workloads
that span multiple NUMA nodes.  However, it turns out that the
p->numa_migrate_deferred knob is a really big hammer, which does
reduce migration rates, but does not actually help performance.

Now that the second stage of the automatic numa balancing code
has stabilized, it is time to replace the simplistic migration
deferral code with something smarter.

Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-2-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 8 --------
 kernel/sysctl.c     | 7 -------
 2 files changed, 15 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index efe6457ac5c8..7cdde913b4dc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -819,14 +819,6 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
 /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
 unsigned int sysctl_numa_balancing_scan_delay = 1000;
 
-/*
- * After skipping a page migration on a shared page, skip N more numa page
- * migrations unconditionally. This reduces the number of NUMA migrations
- * in shared memory workloads, and has the effect of pulling tasks towards
- * where their memory lives, over pulling the memory towards the task.
- */
-unsigned int sysctl_numa_balancing_migrate_deferred = 16;
-
 static unsigned int task_nr_scan_windows(struct task_struct *p)
 {
 	unsigned long rss = 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c8da99f905cf..b41d61d95c14 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -384,13 +384,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname       = "numa_balancing_migrate_deferred",
-		.data           = &sysctl_numa_balancing_migrate_deferred,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
-- 
cgit v1.2.3


From ff1df896aef8e0ec1556a5c44f424bd45bfa2cbe Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:41 -0500
Subject: sched/numa: Rename p->numa_faults to numa_faults_memory

In order to get a more consistent naming scheme, making it clear
which fault statistics track memory locality, and which track
CPU locality, rename the memory fault statistics.

Suggested-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-3-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  |  4 ++--
 kernel/sched/debug.c |  6 +++---
 kernel/sched/fair.c  | 56 ++++++++++++++++++++++++++--------------------------
 3 files changed, 33 insertions(+), 33 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 81343d6bd9cb..bc708c53bf03 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1744,8 +1744,8 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
-	p->numa_faults = NULL;
-	p->numa_faults_buffer = NULL;
+	p->numa_faults_memory = NULL;
+	p->numa_faults_buffer_memory = NULL;
 
 	INIT_LIST_HEAD(&p->numa_entry);
 	p->numa_group = NULL;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index dd52e7ffb10e..31b908daaa1b 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -533,15 +533,15 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 			unsigned long nr_faults = -1;
 			int cpu_current, home_node;
 
-			if (p->numa_faults)
-				nr_faults = p->numa_faults[2*node + i];
+			if (p->numa_faults_memory)
+				nr_faults = p->numa_faults_memory[2*node + i];
 
 			cpu_current = !i ? (task_node(p) == node) :
 				(pol && node_isset(node, pol->v.nodes));
 
 			home_node = (p->numa_preferred_nid == node);
 
-			SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+			SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
 				i, node, cpu_current, home_node, nr_faults);
 		}
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7cdde913b4dc..3e616d704f67 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -901,11 +901,11 @@ static inline int task_faults_idx(int nid, int priv)
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
 {
-	if (!p->numa_faults)
+	if (!p->numa_faults_memory)
 		return 0;
 
-	return p->numa_faults[task_faults_idx(nid, 0)] +
-		p->numa_faults[task_faults_idx(nid, 1)];
+	return p->numa_faults_memory[task_faults_idx(nid, 0)] +
+		p->numa_faults_memory[task_faults_idx(nid, 1)];
 }
 
 static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -927,7 +927,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid)
 {
 	unsigned long total_faults;
 
-	if (!p->numa_faults)
+	if (!p->numa_faults_memory)
 		return 0;
 
 	total_faults = p->total_numa_faults;
@@ -1255,7 +1255,7 @@ static int task_numa_migrate(struct task_struct *p)
 static void numa_migrate_preferred(struct task_struct *p)
 {
 	/* This task has no NUMA fault statistics yet */
-	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
+	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
 		return;
 
 	/* Periodically retry migrating the task to the preferred node */
@@ -1371,16 +1371,16 @@ static void task_numa_placement(struct task_struct *p)
 			long diff;
 
 			i = task_faults_idx(nid, priv);
-			diff = -p->numa_faults[i];
+			diff = -p->numa_faults_memory[i];
 
 			/* Decay existing window, copy faults since last scan */
-			p->numa_faults[i] >>= 1;
-			p->numa_faults[i] += p->numa_faults_buffer[i];
-			fault_types[priv] += p->numa_faults_buffer[i];
-			p->numa_faults_buffer[i] = 0;
+			p->numa_faults_memory[i] >>= 1;
+			p->numa_faults_memory[i] += p->numa_faults_buffer_memory[i];
+			fault_types[priv] += p->numa_faults_buffer_memory[i];
+			p->numa_faults_buffer_memory[i] = 0;
 
-			faults += p->numa_faults[i];
-			diff += p->numa_faults[i];
+			faults += p->numa_faults_memory[i];
+			diff += p->numa_faults_memory[i];
 			p->total_numa_faults += diff;
 			if (p->numa_group) {
 				/* safe because we can only change our own group */
@@ -1465,7 +1465,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		grp->gid = p->pid;
 
 		for (i = 0; i < 2*nr_node_ids; i++)
-			grp->faults[i] = p->numa_faults[i];
+			grp->faults[i] = p->numa_faults_memory[i];
 
 		grp->total_faults = p->total_numa_faults;
 
@@ -1523,8 +1523,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 	double_lock(&my_grp->lock, &grp->lock);
 
 	for (i = 0; i < 2*nr_node_ids; i++) {
-		my_grp->faults[i] -= p->numa_faults[i];
-		grp->faults[i] += p->numa_faults[i];
+		my_grp->faults[i] -= p->numa_faults_memory[i];
+		grp->faults[i] += p->numa_faults_memory[i];
 	}
 	my_grp->total_faults -= p->total_numa_faults;
 	grp->total_faults += p->total_numa_faults;
@@ -1550,12 +1550,12 @@ void task_numa_free(struct task_struct *p)
 {
 	struct numa_group *grp = p->numa_group;
 	int i;
-	void *numa_faults = p->numa_faults;
+	void *numa_faults = p->numa_faults_memory;
 
 	if (grp) {
 		spin_lock(&grp->lock);
 		for (i = 0; i < 2*nr_node_ids; i++)
-			grp->faults[i] -= p->numa_faults[i];
+			grp->faults[i] -= p->numa_faults_memory[i];
 		grp->total_faults -= p->total_numa_faults;
 
 		list_del(&p->numa_entry);
@@ -1565,8 +1565,8 @@ void task_numa_free(struct task_struct *p)
 		put_numa_group(grp);
 	}
 
-	p->numa_faults = NULL;
-	p->numa_faults_buffer = NULL;
+	p->numa_faults_memory = NULL;
+	p->numa_faults_buffer_memory = NULL;
 	kfree(numa_faults);
 }
 
@@ -1591,16 +1591,16 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 		return;
 
 	/* Allocate buffer to track faults on a per-node basis */
-	if (unlikely(!p->numa_faults)) {
-		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
+	if (unlikely(!p->numa_faults_memory)) {
+		int size = sizeof(*p->numa_faults_memory) * 2 * nr_node_ids;
 
 		/* numa_faults and numa_faults_buffer share the allocation */
-		p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
-		if (!p->numa_faults)
+		p->numa_faults_memory = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults_memory)
 			return;
 
-		BUG_ON(p->numa_faults_buffer);
-		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+		BUG_ON(p->numa_faults_buffer_memory);
+		p->numa_faults_buffer_memory = p->numa_faults_memory + (2 * nr_node_ids);
 		p->total_numa_faults = 0;
 		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
@@ -1629,7 +1629,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 	if (migrated)
 		p->numa_pages_migrated += pages;
 
-	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+	p->numa_faults_buffer_memory[task_faults_idx(node, priv)] += pages;
 	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
@@ -4771,7 +4771,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 {
 	int src_nid, dst_nid;
 
-	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
 	    !(env->sd->flags & SD_NUMA)) {
 		return false;
 	}
@@ -4802,7 +4802,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
 		return false;
 
-	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+	if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
 		return false;
 
 	src_nid = cpu_to_node(env->src_cpu);
-- 
cgit v1.2.3


From 50ec8a401fed6d246ab65e6011d61ac91c34af70 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:42 -0500
Subject: sched/numa: Track from which nodes NUMA faults are triggered

Track which nodes NUMA faults are triggered from, in other words
the CPUs on which the NUMA faults happened. This uses a similar
mechanism to what is used to track the memory involved in numa faults.

The next patches use this to build up a bitmap of which nodes a
workload is actively running on.

Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-4-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3e616d704f67..4841aaff7394 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -886,6 +886,7 @@ struct numa_group {
 
 	struct rcu_head rcu;
 	unsigned long total_faults;
+	unsigned long *faults_cpu;
 	unsigned long faults[0];
 };
 
@@ -1368,10 +1369,11 @@ static void task_numa_placement(struct task_struct *p)
 		int priv, i;
 
 		for (priv = 0; priv < 2; priv++) {
-			long diff;
+			long diff, f_diff;
 
 			i = task_faults_idx(nid, priv);
 			diff = -p->numa_faults_memory[i];
+			f_diff = -p->numa_faults_cpu[i];
 
 			/* Decay existing window, copy faults since last scan */
 			p->numa_faults_memory[i] >>= 1;
@@ -1379,12 +1381,18 @@ static void task_numa_placement(struct task_struct *p)
 			fault_types[priv] += p->numa_faults_buffer_memory[i];
 			p->numa_faults_buffer_memory[i] = 0;
 
+			p->numa_faults_cpu[i] >>= 1;
+			p->numa_faults_cpu[i] += p->numa_faults_buffer_cpu[i];
+			p->numa_faults_buffer_cpu[i] = 0;
+
 			faults += p->numa_faults_memory[i];
 			diff += p->numa_faults_memory[i];
+			f_diff += p->numa_faults_cpu[i];
 			p->total_numa_faults += diff;
 			if (p->numa_group) {
 				/* safe because we can only change our own group */
 				p->numa_group->faults[i] += diff;
+				p->numa_group->faults_cpu[i] += f_diff;
 				p->numa_group->total_faults += diff;
 				group_faults += p->numa_group->faults[i];
 			}
@@ -1453,7 +1461,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 	if (unlikely(!p->numa_group)) {
 		unsigned int size = sizeof(struct numa_group) +
-				    2*nr_node_ids*sizeof(unsigned long);
+				    4*nr_node_ids*sizeof(unsigned long);
 
 		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!grp)
@@ -1463,8 +1471,10 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		spin_lock_init(&grp->lock);
 		INIT_LIST_HEAD(&grp->task_list);
 		grp->gid = p->pid;
+		/* Second half of the array tracks nids where faults happen */
+		grp->faults_cpu = grp->faults + 2 * nr_node_ids;
 
-		for (i = 0; i < 2*nr_node_ids; i++)
+		for (i = 0; i < 4*nr_node_ids; i++)
 			grp->faults[i] = p->numa_faults_memory[i];
 
 		grp->total_faults = p->total_numa_faults;
@@ -1522,7 +1532,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 	double_lock(&my_grp->lock, &grp->lock);
 
-	for (i = 0; i < 2*nr_node_ids; i++) {
+	for (i = 0; i < 4*nr_node_ids; i++) {
 		my_grp->faults[i] -= p->numa_faults_memory[i];
 		grp->faults[i] += p->numa_faults_memory[i];
 	}
@@ -1554,7 +1564,7 @@ void task_numa_free(struct task_struct *p)
 
 	if (grp) {
 		spin_lock(&grp->lock);
-		for (i = 0; i < 2*nr_node_ids; i++)
+		for (i = 0; i < 4*nr_node_ids; i++)
 			grp->faults[i] -= p->numa_faults_memory[i];
 		grp->total_faults -= p->total_numa_faults;
 
@@ -1567,6 +1577,8 @@ void task_numa_free(struct task_struct *p)
 
 	p->numa_faults_memory = NULL;
 	p->numa_faults_buffer_memory = NULL;
+	p->numa_faults_cpu= NULL;
+	p->numa_faults_buffer_cpu = NULL;
 	kfree(numa_faults);
 }
 
@@ -1577,6 +1589,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 {
 	struct task_struct *p = current;
 	bool migrated = flags & TNF_MIGRATED;
+	int this_node = task_node(current);
 	int priv;
 
 	if (!numabalancing_enabled)
@@ -1592,7 +1605,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults_memory)) {
-		int size = sizeof(*p->numa_faults_memory) * 2 * nr_node_ids;
+		int size = sizeof(*p->numa_faults_memory) * 4 * nr_node_ids;
 
 		/* numa_faults and numa_faults_buffer share the allocation */
 		p->numa_faults_memory = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
@@ -1600,7 +1613,9 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 			return;
 
 		BUG_ON(p->numa_faults_buffer_memory);
-		p->numa_faults_buffer_memory = p->numa_faults_memory + (2 * nr_node_ids);
+		p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
+		p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
+		p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
 		p->total_numa_faults = 0;
 		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
@@ -1630,6 +1645,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 		p->numa_pages_migrated += pages;
 
 	p->numa_faults_buffer_memory[task_faults_idx(node, priv)] += pages;
+	p->numa_faults_buffer_cpu[task_faults_idx(this_node, priv)] += pages;
 	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
-- 
cgit v1.2.3


From 20e07dea286a90f096a779706861472d296397c6 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:43 -0500
Subject: sched/numa: Build per numa_group active node mask from
 numa_faults_cpu statistics

The numa_faults_cpu statistics are used to maintain an active_nodes nodemask
per numa_group. This allows us to be smarter about when to do numa migrations.

Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-5-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4841aaff7394..1ee921f1ec35 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -885,6 +885,7 @@ struct numa_group {
 	struct list_head task_list;
 
 	struct rcu_head rcu;
+	nodemask_t active_nodes;
 	unsigned long total_faults;
 	unsigned long *faults_cpu;
 	unsigned long faults[0];
@@ -918,6 +919,12 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 		p->numa_group->faults[task_faults_idx(nid, 1)];
 }
 
+static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
+{
+	return group->faults_cpu[task_faults_idx(nid, 0)] +
+		group->faults_cpu[task_faults_idx(nid, 1)];
+}
+
 /*
  * These return the fraction of accesses done by a particular task, or
  * task group, on a particular numa node.  The group weight is given a
@@ -1270,6 +1277,38 @@ static void numa_migrate_preferred(struct task_struct *p)
 	task_numa_migrate(p);
 }
 
+/*
+ * Find the nodes on which the workload is actively running. We do this by
+ * tracking the nodes from which NUMA hinting faults are triggered. This can
+ * be different from the set of nodes where the workload's memory is currently
+ * located.
+ *
+ * The bitmask is used to make smarter decisions on when to do NUMA page
+ * migrations, To prevent flip-flopping, and excessive page migrations, nodes
+ * are added when they cause over 6/16 of the maximum number of faults, but
+ * only removed when they drop below 3/16.
+ */
+static void update_numa_active_node_mask(struct numa_group *numa_group)
+{
+	unsigned long faults, max_faults = 0;
+	int nid;
+
+	for_each_online_node(nid) {
+		faults = group_faults_cpu(numa_group, nid);
+		if (faults > max_faults)
+			max_faults = faults;
+	}
+
+	for_each_online_node(nid) {
+		faults = group_faults_cpu(numa_group, nid);
+		if (!node_isset(nid, numa_group->active_nodes)) {
+			if (faults > max_faults * 6 / 16)
+				node_set(nid, numa_group->active_nodes);
+		} else if (faults < max_faults * 3 / 16)
+			node_clear(nid, numa_group->active_nodes);
+	}
+}
+
 /*
  * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
  * increments. The more local the fault statistics are, the higher the scan
@@ -1412,6 +1451,7 @@ static void task_numa_placement(struct task_struct *p)
 	update_task_scan_period(p, fault_types[0], fault_types[1]);
 
 	if (p->numa_group) {
+		update_numa_active_node_mask(p->numa_group);
 		/*
 		 * If the preferred task and group nids are different,
 		 * iterate over the nodes again to find the best place.
@@ -1474,6 +1514,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		/* Second half of the array tracks nids where faults happen */
 		grp->faults_cpu = grp->faults + 2 * nr_node_ids;
 
+		node_set(task_node(current), grp->active_nodes);
+
 		for (i = 0; i < 4*nr_node_ids; i++)
 			grp->faults[i] = p->numa_faults_memory[i];
 
-- 
cgit v1.2.3


From 10f39042711ba21773763f267b4943a2c66c8bef Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:44 -0500
Subject: sched/numa, mm: Use active_nodes nodemask to limit numa migrations

Use the active_nodes nodemask to make smarter decisions on NUMA migrations.

In order to maximize performance of workloads that do not fit in one NUMA
node, we want to satisfy the following criteria:

  1) keep private memory local to each thread

  2) avoid excessive NUMA migration of pages

  3) distribute shared memory across the active nodes, to
     maximize memory bandwidth available to the workload

This patch accomplishes that by implementing the following policy for
NUMA migrations:

  1) always migrate on a private fault

  2) never migrate to a node that is not in the set of active nodes
     for the numa_group

  3) always migrate from a node outside of the set of active nodes,
     to a node that is in that set

  4) within the set of active nodes in the numa_group, only migrate
     from a node with more NUMA page faults, to a node with fewer
     NUMA page faults, with a 25% margin to avoid ping-ponging

This results in most pages of a workload ending up on the actively
used nodes, with reduced ping-ponging of pages between those nodes.

Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-6-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1ee921f1ec35..eeabb33f349e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -954,6 +954,69 @@ static inline unsigned long group_weight(struct task_struct *p, int nid)
 	return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
 }
 
+bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+				int src_nid, int dst_cpu)
+{
+	struct numa_group *ng = p->numa_group;
+	int dst_nid = cpu_to_node(dst_cpu);
+	int last_cpupid, this_cpupid;
+
+	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+
+	/*
+	 * Multi-stage node selection is used in conjunction with a periodic
+	 * migration fault to build a temporal task<->page relation. By using
+	 * a two-stage filter we remove short/unlikely relations.
+	 *
+	 * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
+	 * a task's usage of a particular page (n_p) per total usage of this
+	 * page (n_t) (in a given time-span) to a probability.
+	 *
+	 * Our periodic faults will sample this probability and getting the
+	 * same result twice in a row, given these samples are fully
+	 * independent, is then given by P(n)^2, provided our sample period
+	 * is sufficiently short compared to the usage pattern.
+	 *
+	 * This quadric squishes small probabilities, making it less likely we
+	 * act on an unlikely task<->page relation.
+	 */
+	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+	if (!cpupid_pid_unset(last_cpupid) &&
+				cpupid_to_nid(last_cpupid) != dst_nid)
+		return false;
+
+	/* Always allow migrate on private faults */
+	if (cpupid_match_pid(p, last_cpupid))
+		return true;
+
+	/* A shared fault, but p->numa_group has not been set up yet. */
+	if (!ng)
+		return true;
+
+	/*
+	 * Do not migrate if the destination is not a node that
+	 * is actively used by this numa group.
+	 */
+	if (!node_isset(dst_nid, ng->active_nodes))
+		return false;
+
+	/*
+	 * Source is a node that is not actively used by this
+	 * numa group, while the destination is. Migrate.
+	 */
+	if (!node_isset(src_nid, ng->active_nodes))
+		return true;
+
+	/*
+	 * Both source and destination are nodes in active
+	 * use by this numa group. Maximize memory bandwidth
+	 * by migrating from more heavily used groups, to less
+	 * heavily used ones, spreading the load around.
+	 * Use a 1/4 hysteresis to avoid spurious page movement.
+	 */
+	return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
+}
+
 static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
-- 
cgit v1.2.3


From 7e2703e6099609adc93679c4d45cd6247f565971 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:45 -0500
Subject: sched/numa: Normalize faults_cpu stats and weigh by CPU use

Tracing the code that decides the active nodes has made it abundantly clear
that the naive implementation of the faults_from code has issues.

Specifically, the garbage collector in some workloads will access orders
of magnitudes more memory than the threads that do all the active work.
This resulted in the node with the garbage collector being marked the only
active node in the group.

This issue is avoided if we weigh the statistics by CPU use of each task in
the numa group, instead of by how many faults each thread has occurred.

To achieve this, we normalize the number of faults to the fraction of faults
that occurred on each node, and then multiply that fraction by the fraction
of CPU time the task has used since the last time task_numa_placement was
invoked.

This way the nodes in the active node mask will be the ones where the tasks
from the numa group are most actively running, and the influence of eg. the
garbage collector and other do-little threads is properly minimized.

On a 4 node system, using CPU use statistics calculated over a longer interval
results in about 1% fewer page migrations with two 32-warehouse specjbb runs
on a 4 node system, and about 5% fewer page migrations, as well as 1% better
throughput, with two 8-warehouse specjbb runs, as compared with the shorter
term statistics kept by the scheduler.

Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-7-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c |  2 ++
 kernel/sched/fair.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 53 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bc708c53bf03..a561c9e8e382 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1746,6 +1746,8 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults_memory = NULL;
 	p->numa_faults_buffer_memory = NULL;
+	p->last_task_numa_placement = 0;
+	p->last_sum_exec_runtime = 0;
 
 	INIT_LIST_HEAD(&p->numa_entry);
 	p->numa_group = NULL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index eeabb33f349e..8fc3a8234817 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -887,6 +887,11 @@ struct numa_group {
 	struct rcu_head rcu;
 	nodemask_t active_nodes;
 	unsigned long total_faults;
+	/*
+	 * Faults_cpu is used to decide whether memory should move
+	 * towards the CPU. As a consequence, these stats are weighted
+	 * more by CPU use than by memory faults.
+	 */
 	unsigned long *faults_cpu;
 	unsigned long faults[0];
 };
@@ -1446,11 +1451,41 @@ static void update_task_scan_period(struct task_struct *p,
 	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 }
 
+/*
+ * Get the fraction of time the task has been running since the last
+ * NUMA placement cycle. The scheduler keeps similar statistics, but
+ * decays those on a 32ms period, which is orders of magnitude off
+ * from the dozens-of-seconds NUMA balancing period. Use the scheduler
+ * stats only if the task is so new there are no NUMA statistics yet.
+ */
+static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
+{
+	u64 runtime, delta, now;
+	/* Use the start of this time slice to avoid calculations. */
+	now = p->se.exec_start;
+	runtime = p->se.sum_exec_runtime;
+
+	if (p->last_task_numa_placement) {
+		delta = runtime - p->last_sum_exec_runtime;
+		*period = now - p->last_task_numa_placement;
+	} else {
+		delta = p->se.avg.runnable_avg_sum;
+		*period = p->se.avg.runnable_avg_period;
+	}
+
+	p->last_sum_exec_runtime = runtime;
+	p->last_task_numa_placement = now;
+
+	return delta;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1, max_group_nid = -1;
 	unsigned long max_faults = 0, max_group_faults = 0;
 	unsigned long fault_types[2] = { 0, 0 };
+	unsigned long total_faults;
+	u64 runtime, period;
 	spinlock_t *group_lock = NULL;
 
 	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -1459,6 +1494,10 @@ static void task_numa_placement(struct task_struct *p)
 	p->numa_scan_seq = seq;
 	p->numa_scan_period_max = task_scan_max(p);
 
+	total_faults = p->numa_faults_locality[0] +
+		       p->numa_faults_locality[1];
+	runtime = numa_get_avg_runtime(p, &period);
+
 	/* If the task is part of a group prevent parallel updates to group stats */
 	if (p->numa_group) {
 		group_lock = &p->numa_group->lock;
@@ -1471,7 +1510,7 @@ static void task_numa_placement(struct task_struct *p)
 		int priv, i;
 
 		for (priv = 0; priv < 2; priv++) {
-			long diff, f_diff;
+			long diff, f_diff, f_weight;
 
 			i = task_faults_idx(nid, priv);
 			diff = -p->numa_faults_memory[i];
@@ -1483,8 +1522,18 @@ static void task_numa_placement(struct task_struct *p)
 			fault_types[priv] += p->numa_faults_buffer_memory[i];
 			p->numa_faults_buffer_memory[i] = 0;
 
+			/*
+			 * Normalize the faults_from, so all tasks in a group
+			 * count according to CPU use, instead of by the raw
+			 * number of faults. Tasks with little runtime have
+			 * little over-all impact on throughput, and thus their
+			 * faults are less important.
+			 */
+			f_weight = div64_u64(runtime << 16, period + 1);
+			f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+				   (total_faults + 1);
 			p->numa_faults_cpu[i] >>= 1;
-			p->numa_faults_cpu[i] += p->numa_faults_buffer_cpu[i];
+			p->numa_faults_cpu[i] += f_weight;
 			p->numa_faults_buffer_cpu[i] = 0;
 
 			faults += p->numa_faults_memory[i];
-- 
cgit v1.2.3


From 35664fd41e1c8cc4f0b89f6a51db5af39ba50640 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:46 -0500
Subject: sched/numa: Do statistics calculation using local variables only

The current code in task_numa_placement calculates the difference
between the old and the new value, but also temporarily stores half
of the old value in the per-process variables.

The NUMA balancing code looks at those per-process variables, and
having other tasks temporarily see halved statistics could lead to
unwanted numa migrations. This can be avoided by doing all the math
in local variables.

This change also simplifies the code a little.

Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-8-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8fc3a8234817..4c449907a10e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1513,12 +1513,9 @@ static void task_numa_placement(struct task_struct *p)
 			long diff, f_diff, f_weight;
 
 			i = task_faults_idx(nid, priv);
-			diff = -p->numa_faults_memory[i];
-			f_diff = -p->numa_faults_cpu[i];
 
 			/* Decay existing window, copy faults since last scan */
-			p->numa_faults_memory[i] >>= 1;
-			p->numa_faults_memory[i] += p->numa_faults_buffer_memory[i];
+			diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
 			fault_types[priv] += p->numa_faults_buffer_memory[i];
 			p->numa_faults_buffer_memory[i] = 0;
 
@@ -1532,13 +1529,12 @@ static void task_numa_placement(struct task_struct *p)
 			f_weight = div64_u64(runtime << 16, period + 1);
 			f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
 				   (total_faults + 1);
-			p->numa_faults_cpu[i] >>= 1;
-			p->numa_faults_cpu[i] += f_weight;
+			f_diff = f_weight - p->numa_faults_cpu[i] / 2;
 			p->numa_faults_buffer_cpu[i] = 0;
 
+			p->numa_faults_memory[i] += diff;
+			p->numa_faults_cpu[i] += f_diff;
 			faults += p->numa_faults_memory[i];
-			diff += p->numa_faults_memory[i];
-			f_diff += p->numa_faults_cpu[i];
 			p->total_numa_faults += diff;
 			if (p->numa_group) {
 				/* safe because we can only change our own group */
-- 
cgit v1.2.3


From 58b46da336a9312b2e21bb576d1c2c484dbf6257 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:47 -0500
Subject: sched/numa: Rename variables in task_numa_fault()

We track both the node of the memory after a NUMA fault, and the node
of the CPU on which the fault happened. Rename the local variables in
task_numa_fault to make things more explicit.

Suggested-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-9-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4c449907a10e..d5832c367d87 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1735,11 +1735,11 @@ void task_numa_free(struct task_struct *p)
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int last_cpupid, int node, int pages, int flags)
+void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 {
 	struct task_struct *p = current;
 	bool migrated = flags & TNF_MIGRATED;
-	int this_node = task_node(current);
+	int cpu_node = task_node(current);
 	int priv;
 
 	if (!numabalancing_enabled)
@@ -1794,8 +1794,8 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 	if (migrated)
 		p->numa_pages_migrated += pages;
 
-	p->numa_faults_buffer_memory[task_faults_idx(node, priv)] += pages;
-	p->numa_faults_buffer_cpu[task_faults_idx(this_node, priv)] += pages;
+	p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
+	p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
 	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
-- 
cgit v1.2.3


From be1e4e760d940c14d119bffef5eb007dfdf29046 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 27 Jan 2014 17:03:48 -0500
Subject: sched/numa: Turn some magic numbers into #defines

Cleanup suggested by Mel Gorman. Now the code contains some more
hints on what statistics go where.

Suggested-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chegu Vinod <chegu_vinod@hp.com>
Link: http://lkml.kernel.org/r/1390860228-21539-10-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d5832c367d87..1f41b122198e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -896,6 +896,15 @@ struct numa_group {
 	unsigned long faults[0];
 };
 
+/* Shared or private faults. */
+#define NR_NUMA_HINT_FAULT_TYPES 2
+
+/* Memory and CPU locality */
+#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)
+
+/* Averaged statistics, and temporary buffers. */
+#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)
+
 pid_t task_numa_group_id(struct task_struct *p)
 {
 	return p->numa_group ? p->numa_group->gid : 0;
@@ -903,7 +912,7 @@ pid_t task_numa_group_id(struct task_struct *p)
 
 static inline int task_faults_idx(int nid, int priv)
 {
-	return 2 * nid + priv;
+	return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
 }
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
@@ -1509,7 +1518,7 @@ static void task_numa_placement(struct task_struct *p)
 		unsigned long faults = 0, group_faults = 0;
 		int priv, i;
 
-		for (priv = 0; priv < 2; priv++) {
+		for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
 			long diff, f_diff, f_weight;
 
 			i = task_faults_idx(nid, priv);
@@ -1620,11 +1629,12 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		INIT_LIST_HEAD(&grp->task_list);
 		grp->gid = p->pid;
 		/* Second half of the array tracks nids where faults happen */
-		grp->faults_cpu = grp->faults + 2 * nr_node_ids;
+		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
+						nr_node_ids;
 
 		node_set(task_node(current), grp->active_nodes);
 
-		for (i = 0; i < 4*nr_node_ids; i++)
+		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
 			grp->faults[i] = p->numa_faults_memory[i];
 
 		grp->total_faults = p->total_numa_faults;
@@ -1682,7 +1692,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 	double_lock(&my_grp->lock, &grp->lock);
 
-	for (i = 0; i < 4*nr_node_ids; i++) {
+	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
 		my_grp->faults[i] -= p->numa_faults_memory[i];
 		grp->faults[i] += p->numa_faults_memory[i];
 	}
@@ -1714,7 +1724,7 @@ void task_numa_free(struct task_struct *p)
 
 	if (grp) {
 		spin_lock(&grp->lock);
-		for (i = 0; i < 4*nr_node_ids; i++)
+		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
 			grp->faults[i] -= p->numa_faults_memory[i];
 		grp->total_faults -= p->total_numa_faults;
 
@@ -1755,14 +1765,20 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults_memory)) {
-		int size = sizeof(*p->numa_faults_memory) * 4 * nr_node_ids;
+		int size = sizeof(*p->numa_faults_memory) *
+			   NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
 
-		/* numa_faults and numa_faults_buffer share the allocation */
-		p->numa_faults_memory = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
+		p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
 		if (!p->numa_faults_memory)
 			return;
 
 		BUG_ON(p->numa_faults_buffer_memory);
+		/*
+		 * The averaged statistics, shared & private, memory & cpu,
+		 * occupy the first half of the array. The second half of the
+		 * array is for current counters, which are averaged into the
+		 * first set by task_numa_placement.
+		 */
 		p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
 		p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
 		p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
-- 
cgit v1.2.3


From 390f3258cb2d031f1c17aa32e771ebd336e89073 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@parallels.com>
Date: Tue, 28 Jan 2014 11:26:14 +0400
Subject: sched/deadline: Skip in switched_to_dl() if task is current

When p is current and it's not of dl class, then there are no other
dl taks in the rq. If we had had pushable tasks in some other rq,
they would have been pushed earlier. So, skip "p == rq->curr" case.

Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Acked-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140128072421.32315.25300.stgit@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0dd5e0971a07..b5700bceee55 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1560,7 +1560,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	if (unlikely(p->dl.dl_throttled))
 		return;
 
-	if (p->on_rq || rq->curr != p) {
+	if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
 			/* Only reschedule if pushing failed */
-- 
cgit v1.2.3


From 6b6350f155afdfdf888e18c7bf26950a6d10b0c2 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Mon, 27 Jan 2014 17:15:38 -0500
Subject: sched: Expose some macros related to priority

Some macros in kernel/sched/sched.h about priority are
private to kernel/sched. But they are useful to other
parts of the core kernel.

This patch moves these macros from kernel/sched/sched.h to
include/linux/sched/prio.h so that they are available to
other subsystems.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: raistlin@linux.it
Cc: juri.lelli@gmail.com
Cc: clark.williams@gmail.com
Cc: rostedt@goodmis.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/2b022810905b52d13238466807f4b2a691577180.1390859827.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/sched.h | 18 ------------------
 1 file changed, 18 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2119fd20f8b..b44720d38ae9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -23,24 +23,6 @@ extern atomic_long_t calc_load_tasks;
 extern long calc_load_fold_active(struct rq *this_rq);
 extern void update_cpu_load_active(struct rq *this_rq);
 
-/*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
- * and back.
- */
-#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
-#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
-#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
-
-/*
- * 'User priority' is the nice value converted to something we
- * can work with better when scaling various scheduler parameters,
- * it's a [ 0 ... 39 ] range.
- */
-#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
-#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
-#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
-
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
-- 
cgit v1.2.3


From d0ea026808ad81de2af14938448419a95211b938 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Mon, 27 Jan 2014 22:00:45 -0500
Subject: sched: Implement task_nice() as static inline function

As patch "sched: Move the priority specific bits into a new header file" exposes
the priority related macros in linux/sched/prio.h, we don't have to implement
task_nice() in kernel/sched/core.c any more.

This patch implements it in linux/sched/sched.h as static inline function,
saving the kernel stack and enhancing performance a bit.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: clark.williams@gmail.com
Cc: rostedt@goodmis.org
Cc: raistlin@linux.it
Cc: juri.lelli@gmail.com
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1390878045-7096-1-git-send-email-yangds.fnst@cn.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c    | 26 +++++++-------------------
 kernel/sched/cputime.c |  4 ++--
 2 files changed, 9 insertions(+), 21 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 210a12acf2cd..104c8164e04f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3000,7 +3000,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	unsigned long flags;
 	struct rq *rq;
 
-	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+	if (task_nice(p) == nice || nice < -20 || nice > 19)
 		return;
 	/*
 	 * We have to be careful, if called from sys_setpriority(),
@@ -3078,7 +3078,7 @@ SYSCALL_DEFINE1(nice, int, increment)
 	if (increment > 40)
 		increment = 40;
 
-	nice = TASK_NICE(current) + increment;
+	nice = task_nice(current) + increment;
 	if (nice < -20)
 		nice = -20;
 	if (nice > 19)
@@ -3110,18 +3110,6 @@ int task_prio(const struct task_struct *p)
 	return p->prio - MAX_RT_PRIO;
 }
 
-/**
- * task_nice - return the nice value of a given task.
- * @p: the task in question.
- *
- * Return: The nice value [ -20 ... 0 ... 19 ].
- */
-int task_nice(const struct task_struct *p)
-{
-	return TASK_NICE(p);
-}
-EXPORT_SYMBOL(task_nice);
-
 /**
  * idle_cpu - is a given cpu idle currently?
  * @cpu: the processor in question.
@@ -3321,7 +3309,7 @@ recheck:
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
 		if (fair_policy(policy)) {
-			if (attr->sched_nice < TASK_NICE(p) &&
+			if (attr->sched_nice < task_nice(p) &&
 			    !can_nice(p, attr->sched_nice))
 				return -EPERM;
 		}
@@ -3345,7 +3333,7 @@ recheck:
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
 		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
-			if (!can_nice(p, TASK_NICE(p)))
+			if (!can_nice(p, task_nice(p)))
 				return -EPERM;
 		}
 
@@ -3385,7 +3373,7 @@ recheck:
 	 * If not changing anything there's no need to proceed further:
 	 */
 	if (unlikely(policy == p->policy)) {
-		if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
@@ -3837,7 +3825,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	else if (task_has_rt_policy(p))
 		attr.sched_priority = p->rt_priority;
 	else
-		attr.sched_nice = TASK_NICE(p);
+		attr.sched_nice = task_nice(p);
 
 	rcu_read_unlock();
 
@@ -7010,7 +6998,7 @@ void normalize_rt_tasks(void)
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
 			 */
-			if (TASK_NICE(p) < 0 && p->mm)
+			if (task_nice(p) < 0 && p->mm)
 				set_user_nice(p, 0);
 			continue;
 		}
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 99947919e30b..58624a65f124 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -142,7 +142,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
 	p->utimescaled += cputime_scaled;
 	account_group_user_time(p, cputime);
 
-	index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+	index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
 
 	/* Add user time to cpustat. */
 	task_group_account_field(p, index, (__force u64) cputime);
@@ -169,7 +169,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
 	p->gtime += cputime;
 
 	/* Add guest time to cpustat. */
-	if (TASK_NICE(p) > 0) {
+	if (task_nice(p) > 0) {
 		cpustat[CPUTIME_NICE] += (__force u64) cputime;
 		cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
 	} else {
-- 
cgit v1.2.3


From b4f2ab43615e5b36c48fffa99f26aca381839ac6 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Fri, 17 Jan 2014 10:04:01 +0100
Subject: sched: Remove 'cpu' parameter from idle_balance()

The cpu parameter passed to idle_balance() is not needed as it could
be retrieved from 'struct rq.'

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: alex.shi@linaro.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389949444-14821-1-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  | 2 +-
 kernel/sched/fair.c  | 3 ++-
 kernel/sched/sched.h | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 104c8164e04f..74dd565c2e1b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2705,7 +2705,7 @@ need_resched:
 	pre_schedule(rq, prev);
 
 	if (unlikely(!rq->nr_running))
-		idle_balance(cpu, rq);
+		idle_balance(rq);
 
 	put_prev_task(rq, prev);
 	next = pick_next_task(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4caa8030824d..428bc9d2c383 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6531,12 +6531,13 @@ out:
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-void idle_balance(int this_cpu, struct rq *this_rq)
+void idle_balance(struct rq *this_rq)
 {
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 	u64 curr_cost = 0;
+	int this_cpu = this_rq->cpu;
 
 	this_rq->idle_stamp = rq_clock(this_rq);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b44720d38ae9..82c0e02f2a58 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1158,7 +1158,7 @@ extern const struct sched_class idle_sched_class;
 extern void update_group_power(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
-extern void idle_balance(int this_cpu, struct rq *this_rq);
+extern void idle_balance(struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
-- 
cgit v1.2.3


From e5fc66119ec97054eefc83f173a7ee9e133c3c3a Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Fri, 17 Jan 2014 10:04:02 +0100
Subject: sched: Fix race in idle_balance()

The scheduler main function 'schedule()' checks if there are no more tasks
on the runqueue. Then it checks if a task should be pulled in the current
runqueue in idle_balance() assuming it will go to idle otherwise.

But idle_balance() releases the rq->lock in order to look up the sched
domains and takes the lock again right after. That opens a window where
another cpu may put a task in our runqueue, so we won't go to idle but
we have filled the idle_stamp, thinking we will.

This patch closes the window by checking if the runqueue has been modified
but without pulling a task after taking the lock again, so we won't go to idle
right after in the __schedule() function.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: alex.shi@linaro.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389949444-14821-2-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 428bc9d2c383..5ebc6817c036 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6589,6 +6589,13 @@ void idle_balance(struct rq *this_rq)
 
 	raw_spin_lock(&this_rq->lock);
 
+	/*
+	 * While browsing the domains, we released the rq lock.
+	 * A task could have be enqueued in the meantime
+	 */
+	if (this_rq->nr_running && !pulled_task)
+		return;
+
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
 		 * We are going idle. next_balance may be set based on
-- 
cgit v1.2.3


From 3c4017c13f91069194fce3160944efec50f15a6e Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Fri, 17 Jan 2014 10:04:03 +0100
Subject: sched: Move rq->idle_stamp up to the core

idle_balance() modifies the rq->idle_stamp field, making this information
shared across core.c and fair.c.

As we know if the cpu is going to idle or not with the previous patch, let's
encapsulate the rq->idle_stamp information in core.c by moving it up to the
caller.

The idle_balance() function returns true in case a balancing occured and the
cpu won't be idle, false if no balance happened and the cpu is going idle.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: alex.shi@linaro.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389949444-14821-3-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  | 11 +++++++++--
 kernel/sched/fair.c  | 14 ++++++--------
 kernel/sched/sched.h |  2 +-
 3 files changed, 16 insertions(+), 11 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 74dd565c2e1b..417cf657a606 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2704,8 +2704,15 @@ need_resched:
 
 	pre_schedule(rq, prev);
 
-	if (unlikely(!rq->nr_running))
-		idle_balance(rq);
+	if (unlikely(!rq->nr_running)) {
+		/*
+		 * We must set idle_stamp _before_ calling idle_balance(), such
+		 * that we measure the duration of idle_balance() as idle time.
+		 */
+		rq->idle_stamp = rq_clock(rq);
+		if (idle_balance(rq))
+			rq->idle_stamp = 0;
+	}
 
 	put_prev_task(rq, prev);
 	next = pick_next_task(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5ebc6817c036..04fea7744a9f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6531,7 +6531,7 @@ out:
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-void idle_balance(struct rq *this_rq)
+int idle_balance(struct rq *this_rq)
 {
 	struct sched_domain *sd;
 	int pulled_task = 0;
@@ -6539,10 +6539,8 @@ void idle_balance(struct rq *this_rq)
 	u64 curr_cost = 0;
 	int this_cpu = this_rq->cpu;
 
-	this_rq->idle_stamp = rq_clock(this_rq);
-
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
-		return;
+		return 0;
 
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
@@ -6580,10 +6578,8 @@ void idle_balance(struct rq *this_rq)
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task) {
-			this_rq->idle_stamp = 0;
+		if (pulled_task)
 			break;
-		}
 	}
 	rcu_read_unlock();
 
@@ -6594,7 +6590,7 @@ void idle_balance(struct rq *this_rq)
 	 * A task could have be enqueued in the meantime
 	 */
 	if (this_rq->nr_running && !pulled_task)
-		return;
+		return 1;
 
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
@@ -6606,6 +6602,8 @@ void idle_balance(struct rq *this_rq)
 
 	if (curr_cost > this_rq->max_idle_balance_cost)
 		this_rq->max_idle_balance_cost = curr_cost;
+
+	return pulled_task;
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 82c0e02f2a58..bb89991ee409 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1158,7 +1158,7 @@ extern const struct sched_class idle_sched_class;
 extern void update_group_power(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
-extern void idle_balance(struct rq *this_rq);
+extern int idle_balance(struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
-- 
cgit v1.2.3


From fed14d45f945042a15b09de48d7d3d58d9455fc4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 11 Feb 2012 06:05:00 +0100
Subject: sched/fair: Track cgroup depth

Track depth in cgroup tree, this is useful for things like
find_matching_se() where you need to get to a common parent of two
sched entities.

Keeping the depth avoids having to calculate it on the spot, which
saves a number of possible cache-misses.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1328936700.2476.17.camel@laptop
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 47 +++++++++++++++++++++--------------------------
 1 file changed, 21 insertions(+), 26 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 04fea7744a9f..748a7ac3388f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -322,13 +322,13 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
-static inline int
+static inline struct cfs_rq *
 is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
 	if (se->cfs_rq == pse->cfs_rq)
-		return 1;
+		return se->cfs_rq;
 
-	return 0;
+	return NULL;
 }
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -336,17 +336,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 	return se->parent;
 }
 
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
-	int depth = 0;
-
-	for_each_sched_entity(se)
-		depth++;
-
-	return depth;
-}
-
 static void
 find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 {
@@ -360,8 +349,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 	 */
 
 	/* First walk up until both entities are at same depth */
-	se_depth = depth_se(*se);
-	pse_depth = depth_se(*pse);
+	se_depth = (*se)->depth;
+	pse_depth = (*pse)->depth;
 
 	while (se_depth > pse_depth) {
 		se_depth--;
@@ -426,10 +415,10 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
 		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
-static inline int
+static inline struct cfs_rq *
 is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
-	return 1;
+	return cfs_rq_of(se); /* always the same rq */
 }
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -7262,7 +7251,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void task_move_group_fair(struct task_struct *p, int on_rq)
 {
+	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq;
+
 	/*
 	 * If the task was not on the rq at the time of this cgroup movement
 	 * it must have been asleep, sleeping tasks keep their ->vruntime
@@ -7288,23 +7279,24 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
 	 * To prevent boost or penalty in the new cfs_rq caused by delta
 	 * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
 	 */
-	if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
+	if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING))
 		on_rq = 1;
 
 	if (!on_rq)
-		p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+		se->vruntime -= cfs_rq_of(se)->min_vruntime;
 	set_task_rq(p, task_cpu(p));
+	se->depth = se->parent ? se->parent->depth + 1 : 0;
 	if (!on_rq) {
-		cfs_rq = cfs_rq_of(&p->se);
-		p->se.vruntime += cfs_rq->min_vruntime;
+		cfs_rq = cfs_rq_of(se);
+		se->vruntime += cfs_rq->min_vruntime;
 #ifdef CONFIG_SMP
 		/*
 		 * migrate_task_rq_fair() will have removed our previous
 		 * contribution, but we must synchronize for ongoing future
 		 * decay.
 		 */
-		p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
-		cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib;
+		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
+		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 #endif
 	}
 }
@@ -7400,10 +7392,13 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	if (!se)
 		return;
 
-	if (!parent)
+	if (!parent) {
 		se->cfs_rq = &rq->cfs;
-	else
+		se->depth = 0;
+	} else {
 		se->cfs_rq = parent->my_q;
+		se->depth = parent->depth + 1;
+	}
 
 	se->my_q = cfs_rq;
 	/* guarantee group entities always have weight */
-- 
cgit v1.2.3


From 606dba2e289446600a0b68422ed2019af5355c12 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 11 Feb 2012 06:05:00 +0100
Subject: sched: Push put_prev_task() into pick_next_task()

In order to avoid having to do put/set on a whole cgroup hierarchy
when we context switch, push the put into pick_next_task() so that
both operations are in the same function. Further changes then allow
us to possibly optimize away redundant work.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1328936700.2476.17.camel@laptop
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c      | 21 ++++++++-------------
 kernel/sched/deadline.c  |  5 ++++-
 kernel/sched/fair.c      |  6 +++++-
 kernel/sched/idle_task.c |  6 +++++-
 kernel/sched/rt.c        | 27 ++++++++++++++++-----------
 kernel/sched/sched.h     |  8 +++++++-
 kernel/sched/stop_task.c | 16 ++++++++++------
 7 files changed, 55 insertions(+), 34 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 417cf657a606..dedb5f07666e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2579,18 +2579,11 @@ static inline void schedule_debug(struct task_struct *prev)
 	schedstat_inc(this_rq(), sched_count);
 }
 
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
-	if (prev->on_rq || rq->skip_clock_update < 0)
-		update_rq_clock(rq);
-	prev->sched_class->put_prev_task(rq, prev);
-}
-
 /*
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -2600,13 +2593,13 @@ pick_next_task(struct rq *rq)
 	 * the fair class we can call that function directly:
 	 */
 	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
-		p = fair_sched_class.pick_next_task(rq);
+		p = fair_sched_class.pick_next_task(rq, prev);
 		if (likely(p))
 			return p;
 	}
 
 	for_each_class(class) {
-		p = class->pick_next_task(rq);
+		p = class->pick_next_task(rq, prev);
 		if (p)
 			return p;
 	}
@@ -2714,8 +2707,10 @@ need_resched:
 			rq->idle_stamp = 0;
 	}
 
-	put_prev_task(rq, prev);
-	next = pick_next_task(rq);
+	if (prev->on_rq || rq->skip_clock_update < 0)
+		update_rq_clock(rq);
+
+	next = pick_next_task(rq, prev);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 	rq->skip_clock_update = 0;
@@ -4748,7 +4743,7 @@ static void migrate_tasks(unsigned int dead_cpu)
 		if (rq->nr_running == 1)
 			break;
 
-		next = pick_next_task(rq);
+		next = pick_next_task(rq, NULL);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b5700bceee55..50797d576080 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -990,7 +990,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
 	return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-struct task_struct *pick_next_task_dl(struct rq *rq)
+struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 {
 	struct sched_dl_entity *dl_se;
 	struct task_struct *p;
@@ -1001,6 +1001,9 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 	if (unlikely(!dl_rq->dl_nr_running))
 		return NULL;
 
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 748a7ac3388f..c4bb0ac26a7c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4655,7 +4655,8 @@ preempt:
 		set_last_buddy(se);
 }
 
-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 {
 	struct task_struct *p;
 	struct cfs_rq *cfs_rq = &rq->cfs;
@@ -4664,6 +4665,9 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 	if (!cfs_rq->nr_running)
 		return NULL;
 
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
 	do {
 		se = pick_next_entity(cfs_rq);
 		set_next_entity(cfs_rq, se);
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 516c3d9ceea1..e5c922ac40ce 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -33,8 +33,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 	resched_task(rq->idle);
 }
 
-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
 	schedstat_inc(rq, sched_goidle);
 #ifdef CONFIG_SMP
 	/* Trigger the post schedule to do an idle_enter for CFS */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a2740b775b45..a15ca1c0c7bf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1310,15 +1310,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 {
 	struct sched_rt_entity *rt_se;
 	struct task_struct *p;
-	struct rt_rq *rt_rq;
-
-	rt_rq = &rq->rt;
-
-	if (!rt_rq->rt_nr_running)
-		return NULL;
-
-	if (rt_rq_throttled(rt_rq))
-		return NULL;
+	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
 		rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1332,9 +1324,22 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *p = _pick_next_task_rt(rq);
+	struct task_struct *p;
+	struct rt_rq *rt_rq = &rq->rt;
+
+	if (!rt_rq->rt_nr_running)
+		return NULL;
+
+	if (rt_rq_throttled(rt_rq))
+		return NULL;
+
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
+	p = _pick_next_task_rt(rq);
 
 	/* The running task is never eligible for pushing */
 	if (p)
diff --git a/kernel/sched/sched.h b/