[PATCH 07/22] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[PATCH 07/22] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[Sebastian Andrzej Siewior]

Both functions are called with protection against cpu hotplug already so
*_online_cpus() could be dropped.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/vmstat.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 604f26a4f696..0b63ffb5c407 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1722,24 +1722,19 @@ static void __init init_cpu_node_state(void)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		node_set_state(cpu_to_node(cpu), N_CPU);
-	put_online_cpus();
 }
 
 static void vmstat_cpu_dead(int node)
 {
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu)
 		if (cpu_to_node(cpu) == node)
-			goto end;
+			return;
 
 	node_clear_state(node, N_CPU);
-end:
-	put_online_cpus();
 }
 
 /*
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 07/22] mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()

[Michal Hocko]

On Sun 27-11-16 00:13:35, Sebastian Andrzej Siewior wrote:
> Both functions are called with protection against cpu hotplug already so
> *_online_cpus() could be dropped.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: linux-mm@kvack.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  mm/vmstat.c | 7 +------
>  1 file changed, 1 insertion(+), 6 deletions(-)
> 
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 604f26a4f696..0b63ffb5c407 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1722,24 +1722,19 @@ static void __init init_cpu_node_state(void)
>  {
>  	int cpu;
>  
> -	get_online_cpus();
>  	for_each_online_cpu(cpu)
>  		node_set_state(cpu_to_node(cpu), N_CPU);
> -	put_online_cpus();
>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
>  	int cpu;
>  
> -	get_online_cpus();
>  	for_each_online_cpu(cpu)
>  		if (cpu_to_node(cpu) == node)
> -			goto end;
> +			return;
>  
>  	node_clear_state(node, N_CPU);
> -end:
> -	put_online_cpus();
>  }
>  
>  /*
> -- 
> 2.10.2
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Sebastian Andrzej Siewior]

Both iterations over online cpus can be replaced by the proper node
specific functions.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/vmstat.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0b63ffb5c407..b96dcec7e7d7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1720,19 +1720,19 @@ static void __init start_shepherd_timer(void)
 
 static void __init init_cpu_node_state(void)
 {
-	int cpu;
+	int node;
 
-	for_each_online_cpu(cpu)
-		node_set_state(cpu_to_node(cpu), N_CPU);
+	for_each_online_node(node)
+		node_set_state(node, N_CPU);
 }
 
 static void vmstat_cpu_dead(int node)
 {
-	int cpu;
+	const struct cpumask *node_cpus;
 
-	for_each_online_cpu(cpu)
-		if (cpu_to_node(cpu) == node)
-			return;
+	node_cpus = cpumask_of_node(node);
+	if (cpumask_weight(node_cpus) > 0)
+		return;
 
 	node_clear_state(node, N_CPU);
 }
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
[...]
>  static void __init init_cpu_node_state(void)
>  {
> -	int cpu;
> +	int node;
>  
> -	for_each_online_cpu(cpu)
> -		node_set_state(cpu_to_node(cpu), N_CPU);
> +	for_each_online_node(node)
> +		node_set_state(node, N_CPU);

Is this really correct? The point of the original code was to mark only
those nodes which have at least one CPU. Or am I missing something?

>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
> -	int cpu;
> +	const struct cpumask *node_cpus;
>  
> -	for_each_online_cpu(cpu)
> -		if (cpu_to_node(cpu) == node)
> -			return;
> +	node_cpus = cpumask_of_node(node);
> +	if (cpumask_weight(node_cpus) > 0)
> +		return;

This looks OK

>  
>  	node_clear_state(node, N_CPU);
>  }
> -- 
> 2.10.2
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Thomas Gleixner]

On Mon, 28 Nov 2016, Michal Hocko wrote:
> On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
> [...]
> >  static void __init init_cpu_node_state(void)
> >  {
> > -	int cpu;
> > +	int node;
> >  
> > -	for_each_online_cpu(cpu)
> > -		node_set_state(cpu_to_node(cpu), N_CPU);
> > +	for_each_online_node(node)
> > +		node_set_state(node, N_CPU);
> 
> Is this really correct? The point of the original code was to mark only
> those nodes which have at least one CPU. Or am I missing something?

You're right. An online node does not necessarily have an online CPU.

	for_each_online_node(node) {
		if (cpumask_weight(cpumask_of_node(node)) > 0)
			node_set_state(node, N_CPU);
	}

is probably more correct.

Thanks,

	tglx

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Tue 29-11-16 15:08:10, Thomas Gleixner wrote:
> On Mon, 28 Nov 2016, Michal Hocko wrote:
> > On Sun 27-11-16 00:13:36, Sebastian Andrzej Siewior wrote:
> > [...]
> > >  static void __init init_cpu_node_state(void)
> > >  {
> > > -	int cpu;
> > > +	int node;
> > >  
> > > -	for_each_online_cpu(cpu)
> > > -		node_set_state(cpu_to_node(cpu), N_CPU);
> > > +	for_each_online_node(node)
> > > +		node_set_state(node, N_CPU);
> > 
> > Is this really correct? The point of the original code was to mark only
> > those nodes which have at least one CPU. Or am I missing something?
> 
> You're right. An online node does not necessarily have an online CPU.
> 
> 	for_each_online_node(node) {
> 		if (cpumask_weight(cpumask_of_node(node)) > 0)
> 			node_set_state(node, N_CPU);
> 	}
> 
> is probably more correct.

Yes, this looks correct. Considering that the same cpumask_weight is
used in another function I guess a small helper would be nice. E.g.
bool node_has_cpus(int node)
{
	return cpumask_weight(cpumask_of_node(node)) > 0;
}

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 08/22 v2] mm/vmstat: Avoid on each online CPU loops

[Sebastian Andrzej Siewior]

Both iterations over online cpus can be replaced by the proper node
specific functions.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
v1…v2: take into account that we may have online nodes with no CPUs.

 mm/vmstat.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0b63ffb5c407..5152cd1c490f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1720,19 +1720,21 @@ static void __init start_shepherd_timer(void)
 
 static void __init init_cpu_node_state(void)
 {
-	int cpu;
+	int node;
 
-	for_each_online_cpu(cpu)
-		node_set_state(cpu_to_node(cpu), N_CPU);
+	for_each_online_node(node) {
+		if (cpumask_weight(cpumask_of_node(node)) > 0)
+			node_set_state(node, N_CPU);
+	}
 }
 
 static void vmstat_cpu_dead(int node)
 {
-	int cpu;
+	const struct cpumask *node_cpus;
 
-	for_each_online_cpu(cpu)
-		if (cpu_to_node(cpu) == node)
-			return;
+	node_cpus = cpumask_of_node(node);
+	if (cpumask_weight(node_cpus) > 0)
+		return;
 
 	node_clear_state(node, N_CPU);
 }
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 08/22 v2] mm/vmstat: Avoid on each online CPU loops

[Michal Hocko]

On Tue 29-11-16 15:51:14, Sebastian Andrzej Siewior wrote:
> Both iterations over online cpus can be replaced by the proper node
> specific functions.
> 
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: linux-mm@kvack.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
> v1a?|v2: take into account that we may have online nodes with no CPUs.
> 
>  mm/vmstat.c | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
> 
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 0b63ffb5c407..5152cd1c490f 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1720,19 +1720,21 @@ static void __init start_shepherd_timer(void)
>  
>  static void __init init_cpu_node_state(void)
>  {
> -	int cpu;
> +	int node;
>  
> -	for_each_online_cpu(cpu)
> -		node_set_state(cpu_to_node(cpu), N_CPU);
> +	for_each_online_node(node) {
> +		if (cpumask_weight(cpumask_of_node(node)) > 0)
> +			node_set_state(node, N_CPU);
> +	}
>  }
>  
>  static void vmstat_cpu_dead(int node)
>  {
> -	int cpu;
> +	const struct cpumask *node_cpus;
>  
> -	for_each_online_cpu(cpu)
> -		if (cpu_to_node(cpu) == node)
> -			return;
> +	node_cpus = cpumask_of_node(node);
> +	if (cpumask_weight(node_cpus) > 0)
> +		return;
>  
>  	node_clear_state(node, N_CPU);
>  }
> -- 
> 2.10.2

-- 
Michal Hocko
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 09/22] mm/vmstat: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine, but do not invoke them as we
can initialize the node state without calling the callbacks on all online
CPUs.

start_shepherd_timer() is now called outside the get_online_cpus() block
which is safe as it only operates on cpu possible mask.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/vmstat.c                | 76 +++++++++++++++++++++-------------------------
 2 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 18bcfeb2463e..4ebd1bc27f8d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -20,6 +20,7 @@ enum cpuhp_state {
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
 	CPUHP_CPUIDLE_DEAD,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b96dcec7e7d7..dfe3cb9f2c36 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1726,64 +1726,58 @@ static void __init init_cpu_node_state(void)
 		node_set_state(node, N_CPU);
 }
 
-static void vmstat_cpu_dead(int node)
+static int vmstat_cpu_online(unsigned int cpu)
+{
+	refresh_zone_stat_thresholds();
+	node_set_state(cpu_to_node(cpu), N_CPU);
+	return 0;
+}
+
+static int vmstat_cpu_down_prep(unsigned int cpu)
+{
+	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	return 0;
+}
+
+static int vmstat_cpu_dead(unsigned int cpu)
 {
 	const struct cpumask *node_cpus;
+	int node;
 
+	node = cpu_to_node(cpu);
+
+	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
 	if (cpumask_weight(node_cpus) > 0)
-		return;
+		return 0;
 
 	node_clear_state(node, N_CPU);
+	return 0;
 }
 
-/*
- * Use the cpu notifier to insure that the thresholds are recalculated
- * when necessary.
- */
-static int vmstat_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action,
-		void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		refresh_zone_stat_thresholds();
-		node_set_state(cpu_to_node(cpu), N_CPU);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		refresh_zone_stat_thresholds();
-		vmstat_cpu_dead(cpu_to_node(cpu));
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vmstat_notifier =
-	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	cpu_notifier_register_begin();
-	__register_cpu_notifier(&vmstat_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
+					NULL, vmstat_cpu_dead);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'dead' hotplug state\n");
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
+					vmstat_cpu_online,
+					vmstat_cpu_down_prep);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'online' hotplug state\n");
+
+	get_online_cpus();
 	init_cpu_node_state();
+	put_online_cpus();
 
 	start_shepherd_timer();
-	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 09/22 v2] mm/vmstat: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine, but do not invoke them as we
can initialize the node state without calling the callbacks on all online
CPUs.

start_shepherd_timer() is now called outside the get_online_cpus() block
which is safe as it only operates on cpu possible mask.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
v1…v2: rebase on top of PATCH 08/22 v2.

 include/linux/cpuhotplug.h |  1 +
 mm/vmstat.c                | 76 +++++++++++++++++++++-------------------------
 2 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 18bcfeb2463e..4ebd1bc27f8d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -20,6 +20,7 @@ enum cpuhp_state {
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
 	CPUHP_CPUIDLE_DEAD,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 5152cd1c490f..7c28df36f50f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1728,64 +1728,58 @@ static void __init init_cpu_node_state(void)
 	}
 }
 
-static void vmstat_cpu_dead(int node)
+static int vmstat_cpu_online(unsigned int cpu)
+{
+	refresh_zone_stat_thresholds();
+	node_set_state(cpu_to_node(cpu), N_CPU);
+	return 0;
+}
+
+static int vmstat_cpu_down_prep(unsigned int cpu)
+{
+	cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+	return 0;
+}
+
+static int vmstat_cpu_dead(unsigned int cpu)
 {
 	const struct cpumask *node_cpus;
+	int node;
 
+	node = cpu_to_node(cpu);
+
+	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
 	if (cpumask_weight(node_cpus) > 0)
-		return;
+		return 0;
 
 	node_clear_state(node, N_CPU);
+	return 0;
 }
 
-/*
- * Use the cpu notifier to insure that the thresholds are recalculated
- * when necessary.
- */
-static int vmstat_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action,
-		void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		refresh_zone_stat_thresholds();
-		node_set_state(cpu_to_node(cpu), N_CPU);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		refresh_zone_stat_thresholds();
-		vmstat_cpu_dead(cpu_to_node(cpu));
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vmstat_notifier =
-	{ &vmstat_cpuup_callback, NULL, 0 };
 #endif
 
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	cpu_notifier_register_begin();
-	__register_cpu_notifier(&vmstat_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
+					NULL, vmstat_cpu_dead);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'dead' hotplug state\n");
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/vmstat:online",
+					vmstat_cpu_online,
+					vmstat_cpu_down_prep);
+	if (ret < 0)
+		pr_err("vmstat: failed to register 'online' hotplug state\n");
+
+	get_online_cpus();
 	init_cpu_node_state();
+	put_online_cpus();
 
 	start_shepherd_timer();
-	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 10/22] mm/zsmalloc: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
CC: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zsmalloc.c              | 67 +++++++++-------------------------------------
 2 files changed, 14 insertions(+), 54 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4ebd1bc27f8d..9f29dd996088 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -64,6 +64,7 @@ enum cpuhp_state {
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
+	CPUHP_MM_ZS_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b0bc023d25c5..9cc3c0b2c2c1 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1284,61 +1284,21 @@ static void __zs_unmap_object(struct mapping_area *area,
 
 #endif /* CONFIG_PGTABLE_MAPPING */
 
-static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
-				void *pcpu)
+static int zs_cpu_prepare(unsigned int cpu)
 {
-	int ret, cpu = (long)pcpu;
 	struct mapping_area *area;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		area = &per_cpu(zs_map_area, cpu);
-		ret = __zs_cpu_up(area);
-		if (ret)
-			return notifier_from_errno(ret);
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		area = &per_cpu(zs_map_area, cpu);
-		__zs_cpu_down(area);
-		break;
-	}
-
-	return NOTIFY_OK;
+	area = &per_cpu(zs_map_area, cpu);
+	return __zs_cpu_up(area);
 }
 
-static struct notifier_block zs_cpu_nb = {
-	.notifier_call = zs_cpu_notifier
-};
-
-static int zs_register_cpu_notifier(void)
+static int zs_cpu_dead(unsigned int cpu)
 {
-	int cpu, uninitialized_var(ret);
+	struct mapping_area *area;
 
-	cpu_notifier_register_begin();
-
-	__register_cpu_notifier(&zs_cpu_nb);
-	for_each_online_cpu(cpu) {
-		ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-		if (notifier_to_errno(ret))
-			break;
-	}
-
-	cpu_notifier_register_done();
-	return notifier_to_errno(ret);
-}
-
-static void zs_unregister_cpu_notifier(void)
-{
-	int cpu;
-
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(cpu)
-		zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
-	__unregister_cpu_notifier(&zs_cpu_nb);
-
-	cpu_notifier_register_done();
+	area = &per_cpu(zs_map_area, cpu);
+	__zs_cpu_down(area);
+	return 0;
 }
 
 static void __init init_zs_size_classes(void)
@@ -2534,10 +2494,10 @@ static int __init zs_init(void)
 	if (ret)
 		goto out;
 
-	ret = zs_register_cpu_notifier();
-
+	ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare",
+				zs_cpu_prepare, zs_cpu_dead);
 	if (ret)
-		goto notifier_fail;
+		goto hp_setup_fail;
 
 	init_zs_size_classes();
 
@@ -2549,8 +2509,7 @@ static int __init zs_init(void)
 
 	return 0;
 
-notifier_fail:
-	zs_unregister_cpu_notifier();
+hp_setup_fail:
 	zsmalloc_unmount();
 out:
 	return ret;
@@ -2562,7 +2521,7 @@ static void __exit zs_exit(void)
 	zpool_unregister_driver(&zs_zpool_driver);
 #endif
 	zsmalloc_unmount();
-	zs_unregister_cpu_notifier();
+	cpuhp_remove_state(CPUHP_MM_ZS_PREPARE);
 
 	zs_stat_exit();
 }
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 11/22] mm/zswap: Convert dst-mem to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.

Cc: Seth Jennings <sjenning@redhat.com>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 75 +++++++++++-----------------------------------
 2 files changed, 19 insertions(+), 57 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 9f29dd996088..62f51a4e8676 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -65,6 +65,7 @@ enum cpuhp_state {
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
+	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index 275b22cc8df4..b13aa5706348 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -352,70 +352,28 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 **********************************/
 static DEFINE_PER_CPU(u8 *, zswap_dstmem);
 
-static int __zswap_cpu_dstmem_notifier(unsigned long action, unsigned long cpu)
+static int zswap_dstmem_prepare(unsigned int cpu)
 {
 	u8 *dst;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-		if (!dst) {
-			pr_err("can't allocate compressor buffer\n");
-			return NOTIFY_BAD;
-		}
-		per_cpu(zswap_dstmem, cpu) = dst;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		dst = per_cpu(zswap_dstmem, cpu);
-		kfree(dst);
-		per_cpu(zswap_dstmem, cpu) = NULL;
-		break;
-	default:
-		break;
+	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!dst) {
+		pr_err("can't allocate compressor buffer\n");
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_dstmem_notifier(struct notifier_block *nb,
-				     unsigned long action, void *pcpu)
-{
-	return __zswap_cpu_dstmem_notifier(action, (unsigned long)pcpu);
-}
-
-static struct notifier_block zswap_dstmem_notifier = {
-	.notifier_call =	zswap_cpu_dstmem_notifier,
-};
-
-static int __init zswap_cpu_dstmem_init(void)
-{
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_dstmem_notifier(CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
+	per_cpu(zswap_dstmem, cpu) = dst;
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
 }
 
-static void zswap_cpu_dstmem_destroy(void)
+static int zswap_dstmem_dead(unsigned int cpu)
 {
-	unsigned long cpu;
+	u8 *dst;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&zswap_dstmem_notifier);
-	cpu_notifier_register_done();
+	dst = per_cpu(zswap_dstmem, cpu);
+	kfree(dst);
+	per_cpu(zswap_dstmem, cpu) = NULL;
+
+	return 0;
 }
 
 static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
@@ -1238,6 +1196,7 @@ static void __exit zswap_debugfs_exit(void) { }
 static int __init init_zswap(void)
 {
 	struct zswap_pool *pool;
+	int ret;
 
 	zswap_init_started = true;
 
@@ -1246,7 +1205,9 @@ static int __init init_zswap(void)
 		goto cache_fail;
 	}
 
-	if (zswap_cpu_dstmem_init()) {
+	ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
+				zswap_dstmem_prepare, zswap_dstmem_dead);
+	if (ret) {
 		pr_err("dstmem alloc failed\n");
 		goto dstmem_fail;
 	}
@@ -1267,7 +1228,7 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
-	zswap_cpu_dstmem_destroy();
+	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();
 cache_fail:
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 12/22] mm/zswap: Convert pool to hotplug state machine

[Sebastian Andrzej Siewior]

Install the callbacks via the state machine. Multi state is used to address the
per-pool notifier. Uppon adding of the intance the callback is invoked for all
online CPUs so the manual init can go.

Cc: Seth Jennings <sjenning@redhat.com>
Cc: linux-mm@kvack.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/cpuhotplug.h |  1 +
 mm/zswap.c                 | 99 ++++++++++++++++------------------------------
 2 files changed, 35 insertions(+), 65 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 62f51a4e8676..c7d0d76ef0ee 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -66,6 +66,7 @@ enum cpuhp_state {
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
 	CPUHP_MM_ZSWP_MEM_PREPARE,
+	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_TIMERS_DEAD,
 	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index b13aa5706348..067a0d62f318 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -118,7 +118,7 @@ struct zswap_pool {
 	struct kref kref;
 	struct list_head list;
 	struct work_struct work;
-	struct notifier_block notifier;
+	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
 
@@ -376,77 +376,34 @@ static int zswap_dstmem_dead(unsigned int cpu)
 	return 0;
 }
 
-static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
-				     unsigned long action, unsigned long cpu)
+static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_comp *tfm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
-			break;
-		tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
-		if (IS_ERR_OR_NULL(tfm)) {
-			pr_err("could not alloc crypto comp %s : %ld\n",
-			       pool->tfm_name, PTR_ERR(tfm));
-			return NOTIFY_BAD;
-		}
-		*per_cpu_ptr(pool->tfm, cpu) = tfm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		tfm = *per_cpu_ptr(pool->tfm, cpu);
-		if (!IS_ERR_OR_NULL(tfm))
-			crypto_free_comp(tfm);
-		*per_cpu_ptr(pool->tfm, cpu) = NULL;
-		break;
-	default:
-		break;
+	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+		return 0;
+
+	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
+	if (IS_ERR_OR_NULL(tfm)) {
+		pr_err("could not alloc crypto comp %s : %ld\n",
+		       pool->tfm_name, PTR_ERR(tfm));
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
-}
-
-static int zswap_cpu_comp_notifier(struct notifier_block *nb,
-				   unsigned long action, void *pcpu)
-{
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zswap_pool *pool = container_of(nb, typeof(*pool), notifier);
-
-	return __zswap_cpu_comp_notifier(pool, action, cpu);
-}
-
-static int zswap_cpu_comp_init(struct zswap_pool *pool)
-{
-	unsigned long cpu;
-
-	memset(&pool->notifier, 0, sizeof(pool->notifier));
-	pool->notifier.notifier_call = zswap_cpu_comp_notifier;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		if (__zswap_cpu_comp_notifier(pool, CPU_UP_PREPARE, cpu) ==
-		    NOTIFY_BAD)
-			goto cleanup;
-	__register_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	*per_cpu_ptr(pool->tfm, cpu) = tfm;
 	return 0;
-
-cleanup:
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
 }
 
-static void zswap_cpu_comp_destroy(struct zswap_pool *pool)
+static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu;
+	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
+	struct crypto_comp *tfm;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&pool->notifier);
-	cpu_notifier_register_done();
+	tfm = *per_cpu_ptr(pool->tfm, cpu);
+	if (!IS_ERR_OR_NULL(tfm))
+		crypto_free_comp(tfm);
+	*per_cpu_ptr(pool->tfm, cpu) = NULL;
+	return 0;
 }
 
 /*********************************
@@ -527,6 +484,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+	int ret;
 
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool) {
@@ -551,7 +509,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
-	if (zswap_cpu_comp_init(pool))
+	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
+				       &pool->node);
+	if (ret)
 		goto error;
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
@@ -605,7 +565,7 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 {
 	zswap_pool_debug("destroying", pool);
 
-	zswap_cpu_comp_destroy(pool);
+	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->tfm);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -1212,6 +1172,13 @@ static int __init init_zswap(void)
 		goto dstmem_fail;
 	}
 
+	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
+				      "mm/zswap_pool:prepare",
+				      zswap_cpu_comp_prepare,
+				      zswap_cpu_comp_dead);
+	if (ret)
+		goto hp_fail;
+
 	pool = __zswap_pool_create_fallback();
 	if (!pool) {
 		pr_err("pool creation failed\n");
@@ -1228,6 +1195,8 @@ static int __init init_zswap(void)
 	return 0;
 
 pool_fail:
+	cpuhp_remove_state_nocalls(CPUHP_MM_ZSWP_POOL_PREPARE);
+hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
 	zswap_entry_cache_destroy();
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 14/22] mm/compaction: Convert to hotplug state machine

[Sebastian Andrzej Siewior]

From: Anna-Maria Gleixner <anna-maria@linutronix.de>

Install the callbacks via the state machine. Should the hotplug init fail then
no threads are spawned.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: linux-mm@kvack.org
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 mm/compaction.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 0409a4ad6ea1..0d37192d9423 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2043,33 +2043,38 @@ void kcompactd_stop(int nid)
  * away, we get changed to run anywhere: as the first one comes back,
  * restore their cpu bindings.
  */
-static int cpu_callback(struct notifier_block *nfb, unsigned long action,
-			void *hcpu)
+static int kcompactd_cpu_online(unsigned int cpu)
 {
 	int nid;
 
-	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
-		for_each_node_state(nid, N_MEMORY) {
-			pg_data_t *pgdat = NODE_DATA(nid);
-			const struct cpumask *mask;
+	for_each_node_state(nid, N_MEMORY) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		const struct cpumask *mask;
 
-			mask = cpumask_of_node(pgdat->node_id);
+		mask = cpumask_of_node(pgdat->node_id);
 
-			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
-				/* One of our CPUs online: restore mask */
-				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
-		}
+		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
+			/* One of our CPUs online: restore mask */
+			set_cpus_allowed_ptr(pgdat->kcompactd, mask);
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
 static int __init kcompactd_init(void)
 {
 	int nid;
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"mm/compaction:online",
+					kcompactd_cpu_online, NULL);
+	if (ret < 0) {
+		pr_err("kcompactd: failed to register hotplug callbacks.\n");
+		return ret;
+	}
 
 	for_each_node_state(nid, N_MEMORY)
 		kcompactd_run(nid);
-	hotcpu_notifier(cpu_callback, 0);
 	return 0;
 }
 subsys_initcall(kcompactd_init)
-- 
2.10.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>