The patch titled
mem-hotplug: fix potential race while building zonelist for new populated zone
has been added to the -mm tree. Its filename is
mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mem-hotplug: fix potential race while building zonelist for new populated zone
From: Haicheng Li <haicheng.li@xxxxxxxxxxxxxxx>
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@xxxxxxxxxxxxxxx>
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Reviewed-by: Andi Kleen <andi.kleen@xxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: Mel Gorman <mel@xxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 1 +
mm/memory_hotplug.c | 11 +++--------
mm/page_alloc.c | 15 ++++++++++++++-
3 files changed, 18 insertions(+), 9 deletions(-)
diff -puN include/linux/mmzone.h~mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone include/linux/mmzone.h
--- a/include/linux/mmzone.h~mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone
+++ a/include/linux/mmzone.h
@@ -650,6 +650,7 @@ 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 -puN mm/memory_hotplug.c~mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone mm/memory_hotplug.c
--- a/mm/memory_hotplug.c~mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone
+++ a/mm/memory_hotplug.c
@@ -389,11 +389,6 @@ int online_pages(unsigned long pfn, unsi
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, unsi
* 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, unsi
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 -puN mm/page_alloc.c~mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone mm/page_alloc.c
--- a/mm/page_alloc.c~mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone
+++ a/mm/page_alloc.c
@@ -2571,8 +2571,11 @@ int numa_zonelist_order_handler(ctl_tabl
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);
@@ -2924,6 +2927,12 @@ static void setup_pageset(struct per_cpu
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)
{
@@ -2967,6 +2976,10 @@ static __init_refok int __build_all_zone
return 0;
}
+/*
+ * Called with zonelists_mutex held always
+ * unless system_state == SYSTEM_BOOTING.
+ */
void build_all_zonelists(void *data)
{
set_zonelist_order();
_
Patches currently in -mm which might be from haicheng.li@xxxxxxxxxxxxxxx are
mem-hotplug-separate-setup_per_cpu_pageset-into-separate-functions.patch
mem-hotplug-avoid-multiple-zones-sharing-same-boot-strapping-boot_pageset.patch
mem-hotplug-fix-potential-race-while-building-zonelist-for-new-populated-zone.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
