[PATCH 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[PATCH 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[Haicheng Li]

Make "zone->present_pages gets increased" and "building zonelist" an
atomic operation to prevent possible race.

It is merely a theoretical race: after new zone gets populated,
its pages might be allocated by others before itself building zonelist.

Besides, atomic operation ensures alloc_percpu() will never fail since
there is a new fresh memory block added.

Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Andi Kleen <andi.kleen@intel.com>
---
  include/linux/memory_hotplug.h |    8 ++++++++
  mm/memory_hotplug.c            |   15 +++++++++------
  mm/page_alloc.c                |   20 ++++++++++++++++----
  3 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 35b07b7..42b1416 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -157,6 +157,14 @@ extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
  extern void put_page_bootmem(struct page *page);
  #endif

+/* online_pages() will pass such zone info to build_all_zonelists()
+ * when it needs to initialize a new zone.
+ */
+struct zone_online_info {
+	struct zone *zone;
+	unsigned long onlined_pages;
+};
+
  #else /* ! CONFIG_MEMORY_HOTPLUG */
  /*
   * Stub functions for when hotplug is off
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b564b6a..06738b2 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,6 +389,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  	int nid;
  	int ret;
  	struct memory_notify arg;
+	struct zone_online_info zone_online_info;
  	/*
  	 * mutex to protect zone->pageset when it's still shared
  	 * in onlined_pages()
@@ -434,13 +435,15 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  		return ret;
  	}

-	zone->present_pages += onlined_pages;
-	zone->zone_pgdat->node_present_pages += onlined_pages;
-	if (need_zonelists_rebuild)
-		build_all_zonelists(zone);
-	else
+	if (need_zonelists_rebuild) {
+		zone_online_info.zone = zone;
+		zone_online_info.onlined_pages = onlined_pages;
+		build_all_zonelists(&zone_online_info);
+	} else {
+		zone->present_pages += onlined_pages;
+		zone->zone_pgdat->node_present_pages += onlined_pages;
  		zone_pcp_update(zone);
-
+	}
  	mutex_unlock(&zone_pageset_mutex);
  	setup_per_zone_wmarks();
  	calculate_zone_inactive_ratio(zone);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 72c1211..0729a82 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2783,6 +2783,20 @@ static __init_refok int __build_all_zonelists(void *data)
  {
  	int nid;
  	int cpu;
+#ifdef CONFIG_MEMORY_HOTPLUG
+	struct zone_online_info *new = (struct zone_online_info *)data;
+
+	/*
+	 * Populate the new zone before build zonelists, which could
+	 * happen only when onlining a new node after system is booted.
+	 */
+	if (new) {
+		/* We are expecting a new memory block here. */
+		WARN_ON(!new->onlined_pages);
+		new->zone->present_pages += new->onlined_pages;
+		new->zone->zone_pgdat->node_present_pages += new->onlined_pages;
+	}
+#endif

  #ifdef CONFIG_NUMA
  	memset(node_load, 0, sizeof(node_load));
@@ -2796,10 +2810,8 @@ static __init_refok int __build_all_zonelists(void *data)

  #ifdef CONFIG_MEMORY_HOTPLUG
  	/* Setup real pagesets for the new zone */
-	if (data) {
-		struct zone *zone = data;
-		setup_zone_pageset(zone);
-	}
+	if (new)
+		setup_zone_pageset(new->zone);
  #endif

  	/*
-- 
1.6.0.rc1


--
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 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[Christoph Lameter]

On Mon, 17 May 2010, Haicheng Li wrote:

> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 72c1211..0729a82 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -2783,6 +2783,20 @@ static __init_refok int __build_all_zonelists(void
> *data)
>  {
>  	int nid;
>  	int cpu;
> +#ifdef CONFIG_MEMORY_HOTPLUG
> +	struct zone_online_info *new = (struct zone_online_info *)data;
> +
> +	/*
> +	 * Populate the new zone before build zonelists, which could
> +	 * happen only when onlining a new node after system is booted.
> +	 */
> +	if (new) {
> +		/* We are expecting a new memory block here. */
> +		WARN_ON(!new->onlined_pages);
> +		new->zone->present_pages += new->onlined_pages;
> +		new->zone->zone_pgdat->node_present_pages +=
> new->onlined_pages;
> +	}
> +#endif


Building a zonelist now has the potential side effect of changes to the
size of the zone?

Can we have a global mutex that protects against size modification of
zonelists instead? And it could also serialize the pageset setup?



--
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 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[Wu Fengguang]

On Tue, May 18, 2010 at 12:09:31AM +0800, Christoph Lameter wrote:
> On Mon, 17 May 2010, Haicheng Li wrote:
> 
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index 72c1211..0729a82 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -2783,6 +2783,20 @@ static __init_refok int __build_all_zonelists(void
> > *data)
> >  {
> >  	int nid;
> >  	int cpu;
> > +#ifdef CONFIG_MEMORY_HOTPLUG
> > +	struct zone_online_info *new = (struct zone_online_info *)data;
> > +
> > +	/*
> > +	 * Populate the new zone before build zonelists, which could
> > +	 * happen only when onlining a new node after system is booted.
> > +	 */
> > +	if (new) {
> > +		/* We are expecting a new memory block here. */
> > +		WARN_ON(!new->onlined_pages);
> > +		new->zone->present_pages += new->onlined_pages;
> > +		new->zone->zone_pgdat->node_present_pages +=
> > new->onlined_pages;
> > +	}
> > +#endif
> 
> 
> Building a zonelist now has the potential side effect of changes to the
> size of the zone?

Yeah, this sounds a bit hacky.

> Can we have a global mutex that protects against size modification of
> zonelists instead? And it could also serialize the pageset setup?

Good suggestion. We could make zone_pageset_mutex a global mutex and
take it in all the functions that call build_all_zonelists() --
currently only online_pages() and numa_zonelist_order_handler().

This can equally fix the possible race:

    CPU0                                    CPU1                            CPU2
(1) zone->present_pages += online_pages;
(2)                                         build_all_zonelists();
(3)                                                                 alloc_page();
(4)                                                                 free_page();
(5) build_all_zonelists();
(6)   __build_all_zonelists();
(7)     zone->pageset = alloc_percpu();

In step (3,4), zone->pageset still points to boot_pageset, so bad
things may happen if 2+ nodes are in this state. Even if only 1 node
is accessing the boot_pageset, (3) may still consume too much memory
to fail the memory allocations in step (7).

Thanks,
Fengguang

--
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>

[RESEND][PATCH 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[Haicheng Li]

Wu Fengguang wrote:
> On Tue, May 18, 2010 at 12:09:31AM +0800, Christoph Lameter wrote:
>> Building a zonelist now has the potential side effect of changes to the
>> size of the zone?
> 
> Yeah, this sounds a bit hacky.
> 
>> Can we have a global mutex that protects against size modification of
>> zonelists instead? And it could also serialize the pageset setup?
> 
> Good suggestion. We could make zone_pageset_mutex a global mutex and
> take it in all the functions that call build_all_zonelists() --
> currently only online_pages() and numa_zonelist_order_handler().

Yes, if we don't mind adding a global mutex, it's another way to fix the race.

> This can equally fix the possible race:
> 
>     CPU0                                    CPU1                            CPU2
> (1) zone->present_pages += online_pages;
> (2)                                         build_all_zonelists();
> (3)                                                                 alloc_page();
> (4)                                                                 free_page();
> (5) build_all_zonelists();
> (6)   __build_all_zonelists();
> (7)     zone->pageset = alloc_percpu();
> 
> In step (3,4), zone->pageset still points to boot_pageset, so bad
> things may happen if 2+ nodes are in this state. Even if only 1 node
> is accessing the boot_pageset, (3) may still consume too much memory
> to fail the memory allocations in step (7).

Fengguang, this is a nice description of the possible race,
I'd include it into the changelog of this patch.

So how about the revised patch below?

---
 From 0b1e776dc6c135b1d0c9a0bfb35daa9e9cfb046d Mon Sep 17 00:00:00 2001
From: Haicheng Li <haicheng.li@linux.intel.com>
Date: Tue, 18 May 2010 15:53:28 +0800
Subject: [PATCH] mem-hotplug: fix potential setup_zone_pageset race

Add global mutex zonelists_pageset_mutex to fix the possible race:

     CPU0                                  CPU1                    CPU2
(1) zone->present_pages += online_pages;
(2)                                       build_all_zonelists();
(3)                                                               alloc_page();
(4)                                                               free_page();
(5) build_all_zonelists();
(6)   __build_all_zonelists();
(7)     zone->pageset = alloc_percpu();

In step (3,4), zone->pageset still points to boot_pageset, so bad
things may happen if 2+ nodes are in this state. Even if only 1 node
is accessing the boot_pageset, (3) may still consume too much memory
to fail the memory allocations in step (7).

Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Andi Kleen <andi.kleen@intel.com>
---
  include/linux/mmzone.h |    1 +
  mm/memory_hotplug.c    |   11 +++--------
  mm/page_alloc.c        |   15 ++++++++++++++-
  3 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index dbbcd50..5103747 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -641,6 +641,7 @@ typedef struct pglist_data {

  #include <linux/memory_hotplug.h>

+extern struct mutex zonelists_pageset_mutex;
  void get_zone_counts(unsigned long *active, unsigned long *inactive,
  			unsigned long *free);
  void build_all_zonelists(void *data);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b564b6a..b32f3eb 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,11 +389,6 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  	int nid;
  	int ret;
  	struct memory_notify arg;
-	/*
-	 * mutex to protect zone->pageset when it's still shared
-	 * in onlined_pages()
-	 */
-	static DEFINE_MUTEX(zone_pageset_mutex);

  	arg.start_pfn = pfn;
  	arg.nr_pages = nr_pages;
@@ -420,14 +415,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  	 * This means the page allocator ignores this zone.
  	 * So, zonelist must be updated after online.
  	 */
-	mutex_lock(&zone_pageset_mutex);
+	mutex_lock(&zonelists_pageset_mutex);
  	if (!populated_zone(zone))
  		need_zonelists_rebuild = 1;

  	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
  		online_pages_range);
  	if (ret) {
-		mutex_unlock(&zone_pageset_mutex);
+		mutex_unlock(&zonelists_pageset_mutex);
  		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
  			nr_pages, pfn);
  		memory_notify(MEM_CANCEL_ONLINE, &arg);
@@ -441,7 +436,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  	else
  		zone_pcp_update(zone);

-	mutex_unlock(&zone_pageset_mutex);
+	mutex_unlock(&zonelists_pageset_mutex);
  	setup_per_zone_wmarks();
  	calculate_zone_inactive_ratio(zone);
  	if (onlined_pages) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 72c1211..602c4b7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2434,8 +2434,11 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
  			strncpy((char*)table->data, saved_string,
  				NUMA_ZONELIST_ORDER_LEN);
  			user_zonelist_order = oldval;
-		} else if (oldval != user_zonelist_order)
+		} else if (oldval != user_zonelist_order) {
+			mutex_lock(&zonelists_pageset_mutex);
  			build_all_zonelists(NULL);
+			mutex_unlock(&zonelists_pageset_mutex);
+		}
  	}
  out:
  	mutex_unlock(&zl_order_mutex);
@@ -2778,6 +2781,12 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
  static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
  static void setup_zone_pageset(struct zone *zone);

+/*
+ * Global mutex to protect size modification of zonelists
+ * as well as to serialize pageset setup for a new populated zone.
+ */
+DEFINE_MUTEX(zonelists_pageset_mutex);
+
  /* return values int ....just for stop_machine() */
  static __init_refok int __build_all_zonelists(void *data)
  {
@@ -2821,6 +2830,10 @@ static __init_refok int __build_all_zonelists(void *data)
  	return 0;
  }

+/*
+ * Called with zonelists_pageset_mutex held always
+ * unless system_state == SYSTEM_BOOTING.
+ */
  void build_all_zonelists(void *data)
  {
  	set_zonelist_order();
-- 
1.5.6.1


--
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: [RESEND][PATCH 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[Christoph Lameter]

On Tue, 18 May 2010, Haicheng Li wrote:

> +extern struct mutex zonelists_pageset_mutex;

The mutext is used for multiple serializations having to do with zones.
"pageset" suggests its only for pagesets.

So

	zones_mutex?

or

	zonelists_mutex?

--
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>

[RESEND -v2][PATCH 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[Haicheng Li]

Christoph Lameter wrote:
> On Tue, 18 May 2010, Haicheng Li wrote:
> 
>> +extern struct mutex zonelists_pageset_mutex;
> 
> The mutext is used for multiple serializations having to do with zones.
> "pageset" suggests its only for pagesets.

hmm yes, "pageset" sounds a little bit confusing.

> So
> 
> 	zones_mutex?
> 
> or
> 
> 	zonelists_mutex?

I prefer zonelists_mutex.

Christoph, how about below patch? Thanks.

---
 From 3ccfd04d6ae9127bf0f5472db0b266e7b3f158bd Mon Sep 17 00:00:00 2001
From: Haicheng Li <haicheng.li@linux.intel.com>
Date: Wed, 19 May 2010 11:07:21 +0800
Subject: [PATCH] mem-hotplug: fix potential race while building zonelist for new populated zone

Add global mutex zonelists_mutex to fix the possible race:

     CPU0                                  CPU1                    CPU2
(1) zone->present_pages += online_pages;
(2)                                       build_all_zonelists();
(3)                                                               alloc_page();
(4)                                                               free_page();
(5) build_all_zonelists();
(6)   __build_all_zonelists();
(7)     zone->pageset = alloc_percpu();

In step (3,4), zone->pageset still points to boot_pageset, so bad
things may happen if 2+ nodes are in this state. Even if only 1 node
is accessing the boot_pageset, (3) may still consume too much memory
to fail the memory allocations in step (7).

Besides, atomic operation ensures alloc_percpu() in step (7) will never fail
since there is a new fresh memory block added in step(6).

Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Andi Kleen <andi.kleen@intel.com>
---
  include/linux/mmzone.h |    1 +
  mm/memory_hotplug.c    |   11 +++--------
  mm/page_alloc.c        |   15 ++++++++++++++-
  3 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index dbbcd50..4d87baa 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -641,6 +641,7 @@ typedef struct pglist_data {

  #include <linux/memory_hotplug.h>

+extern struct mutex zonelists_mutex;
  void get_zone_counts(unsigned long *active, unsigned long *inactive,
  			unsigned long *free);
  void build_all_zonelists(void *data);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b564b6a..bc4a942 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,11 +389,6 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  	int nid;
  	int ret;
  	struct memory_notify arg;
-	/*
-	 * mutex to protect zone->pageset when it's still shared
-	 * in onlined_pages()
-	 */
-	static DEFINE_MUTEX(zone_pageset_mutex);

  	arg.start_pfn = pfn;
  	arg.nr_pages = nr_pages;
@@ -420,14 +415,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  	 * This means the page allocator ignores this zone.
  	 * So, zonelist must be updated after online.
  	 */
-	mutex_lock(&zone_pageset_mutex);
+	mutex_lock(&zonelists_mutex);
  	if (!populated_zone(zone))
  		need_zonelists_rebuild = 1;

  	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
  		online_pages_range);
  	if (ret) {
-		mutex_unlock(&zone_pageset_mutex);
+		mutex_unlock(&zonelists_mutex);
  		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
  			nr_pages, pfn);
  		memory_notify(MEM_CANCEL_ONLINE, &arg);
@@ -441,7 +436,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
  	else
  		zone_pcp_update(zone);

-	mutex_unlock(&zone_pageset_mutex);
+	mutex_unlock(&zonelists_mutex);
  	setup_per_zone_wmarks();
  	calculate_zone_inactive_ratio(zone);
  	if (onlined_pages) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 72c1211..c8e6146 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2434,8 +2434,11 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
  			strncpy((char*)table->data, saved_string,
  				NUMA_ZONELIST_ORDER_LEN);
  			user_zonelist_order = oldval;
-		} else if (oldval != user_zonelist_order)
+		} else if (oldval != user_zonelist_order) {
+			mutex_lock(&zonelists_mutex);
  			build_all_zonelists(NULL);
+			mutex_unlock(&zonelists_mutex);
+		}
  	}
  out:
  	mutex_unlock(&zl_order_mutex);
@@ -2778,6 +2781,12 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
  static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
  static void setup_zone_pageset(struct zone *zone);

+/*
+ * Global mutex to protect against size modification of zonelists
+ * as well as to serialize pageset setup for the new populated zone.
+ */
+DEFINE_MUTEX(zonelists_mutex);
+
  /* return values int ....just for stop_machine() */
  static __init_refok int __build_all_zonelists(void *data)
  {
@@ -2821,6 +2830,10 @@ static __init_refok int __build_all_zonelists(void *data)
  	return 0;
  }

+/*
+ * Called with zonelists_mutex held always
+ * unless system_state == SYSTEM_BOOTING.
+ */
  void build_all_zonelists(void *data)
  {
  	set_zonelist_order();
-- 
1.5.6.1




-haicheng

--
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: [RESEND -v2][PATCH 3/3] mem-hotplug: fix potential race while building zonelist for new populated zone

[Christoph Lameter]

Looks good on its own....

On Wed, 19 May 2010, Haicheng Li wrote:

> Christoph Lameter wrote:
> > On Tue, 18 May 2010, Haicheng Li wrote:
> >
> > > +extern struct mutex zonelists_pageset_mutex;
> >
> > The mutext is used for multiple serializations having to do with zones.
> > "pageset" suggests its only for pagesets.
>
> hmm yes, "pageset" sounds a little bit confusing.
>
> > So
> >
> > 	zones_mutex?
> >
> > or
> >
> > 	zonelists_mutex?
>
> I prefer zonelists_mutex.
>
> Christoph, how about below patch? Thanks.
>
> ---
> From 3ccfd04d6ae9127bf0f5472db0b266e7b3f158bd Mon Sep 17 00:00:00 2001
> From: Haicheng Li <haicheng.li@linux.intel.com>
> Date: Wed, 19 May 2010 11:07:21 +0800
> Subject: [PATCH] mem-hotplug: fix potential race while building zonelist for
> new populated zone
>
> Add global mutex zonelists_mutex to fix the possible race:
>
>     CPU0                                  CPU1                    CPU2
> (1) zone->present_pages += online_pages;
> (2)                                       build_all_zonelists();
> (3)
> alloc_page();
> (4)                                                               free_page();
> (5) build_all_zonelists();
> (6)   __build_all_zonelists();
> (7)     zone->pageset = alloc_percpu();
>
> In step (3,4), zone->pageset still points to boot_pageset, so bad
> things may happen if 2+ nodes are in this state. Even if only 1 node
> is accessing the boot_pageset, (3) may still consume too much memory
> to fail the memory allocations in step (7).
>
> Besides, atomic operation ensures alloc_percpu() in step (7) will never fail
> since there is a new fresh memory block added in step(6).
>
> Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
> Reviewed-by: Andi Kleen <andi.kleen@intel.com>
> ---
>  include/linux/mmzone.h |    1 +
>  mm/memory_hotplug.c    |   11 +++--------
>  mm/page_alloc.c        |   15 ++++++++++++++-
>  3 files changed, 18 insertions(+), 9 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index dbbcd50..4d87baa 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -641,6 +641,7 @@ typedef struct pglist_data {
>
>  #include <linux/memory_hotplug.h>
>
> +extern struct mutex zonelists_mutex;
>  void get_zone_counts(unsigned long *active, unsigned long *inactive,
>  			unsigned long *free);
>  void build_all_zonelists(void *data);
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index b564b6a..bc4a942 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -389,11 +389,6 @@ int online_pages(unsigned long pfn, unsigned long
> nr_pages)
>  	int nid;
>  	int ret;
>  	struct memory_notify arg;
> -	/*
> -	 * mutex to protect zone->pageset when it's still shared
> -	 * in onlined_pages()
> -	 */
> -	static DEFINE_MUTEX(zone_pageset_mutex);
>
>  	arg.start_pfn = pfn;
>  	arg.nr_pages = nr_pages;
> @@ -420,14 +415,14 @@ int online_pages(unsigned long pfn, unsigned long
> nr_pages)
>  	 * This means the page allocator ignores this zone.
>  	 * So, zonelist must be updated after online.
>  	 */
> -	mutex_lock(&zone_pageset_mutex);
> +	mutex_lock(&zonelists_mutex);
>  	if (!populated_zone(zone))
>  		need_zonelists_rebuild = 1;
>
>  	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
>  		online_pages_range);
>  	if (ret) {
> -		mutex_unlock(&zone_pageset_mutex);
> +		mutex_unlock(&zonelists_mutex);
>  		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
>  			nr_pages, pfn);
>  		memory_notify(MEM_CANCEL_ONLINE, &arg);
> @@ -441,7 +436,7 @@ int online_pages(unsigned long pfn, unsigned long
> nr_pages)
>  	else
>  		zone_pcp_update(zone);
>
> -	mutex_unlock(&zone_pageset_mutex);
> +	mutex_unlock(&zonelists_mutex);
>  	setup_per_zone_wmarks();
>  	calculate_zone_inactive_ratio(zone);
>  	if (onlined_pages) {
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 72c1211..c8e6146 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -2434,8 +2434,11 @@ int numa_zonelist_order_handler(ctl_table *table, int
> write,
>  			strncpy((char*)table->data, saved_string,
>  				NUMA_ZONELIST_ORDER_LEN);
>  			user_zonelist_order = oldval;
> -		} else if (oldval != user_zonelist_order)
> +		} else if (oldval != user_zonelist_order) {
> +			mutex_lock(&zonelists_mutex);
>  			build_all_zonelists(NULL);
> +			mutex_unlock(&zonelists_mutex);
> +		}
>  	}
>  out:
>  	mutex_unlock(&zl_order_mutex);
> @@ -2778,6 +2781,12 @@ static void setup_pageset(struct per_cpu_pageset *p,
> unsigned long batch);
>  static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
>  static void setup_zone_pageset(struct zone *zone);
>
> +/*
> + * Global mutex to protect against size modification of zonelists
> + * as well as to serialize pageset setup for the new populated zone.
> + */
> +DEFINE_MUTEX(zonelists_mutex);
> +
>  /* return values int ....just for stop_machine() */
>  static __init_refok int __build_all_zonelists(void *data)
>  {
> @@ -2821,6 +2830,10 @@ static __init_refok int __build_all_zonelists(void
> *data)
>  	return 0;
>  }
>
> +/*
> + * Called with zonelists_mutex held always
> + * unless system_state == SYSTEM_BOOTING.
> + */
>  void build_all_zonelists(void *data)
>  {
>  	set_zonelist_order();
>

--
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>