linux/mm/page_isolation.c

260 lines
7.0 KiB
C
Raw Normal View History

/*
* linux/mm/page_isolation.c
*/
#include <linux/mm.h>
#include <linux/page-isolation.h>
#include <linux/pageblock-flags.h>
#include <linux/memory.h>
#include "internal.h"
int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
{
struct zone *zone;
unsigned long flags, pfn;
struct memory_isolate_notify arg;
int notifier_ret;
int ret = -EBUSY;
zone = page_zone(page);
spin_lock_irqsave(&zone->lock, flags);
pfn = page_to_pfn(page);
arg.start_pfn = pfn;
arg.nr_pages = pageblock_nr_pages;
arg.pages_found = 0;
/*
* It may be possible to isolate a pageblock even if the
* migratetype is not MIGRATE_MOVABLE. The memory isolation
* notifier chain is used by balloon drivers to return the
* number of pages in a range that are held by the balloon
* driver to shrink memory. If all the pages are accounted for
* by balloons, are free, or on the LRU, isolation can continue.
* Later, for example, when memory hotplug notifier runs, these
* pages reported as "can be isolated" should be isolated(freed)
* by the balloon driver through the memory notifier chain.
*/
notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
notifier_ret = notifier_to_errno(notifier_ret);
if (notifier_ret)
goto out;
/*
* FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
* We just check MOVABLE pages.
*/
if (!has_unmovable_pages(zone, page, arg.pages_found,
skip_hwpoisoned_pages))
ret = 0;
/*
* immobile means "not-on-lru" paes. If immobile is larger than
* removable-by-driver pages reported by notifier, we'll fail.
*/
out:
if (!ret) {
unsigned long nr_pages;
int migratetype = get_pageblock_migratetype(page);
set_pageblock_migratetype(page, MIGRATE_ISOLATE);
nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
__mod_zone_freepage_state(zone, -nr_pages, migratetype);
}
spin_unlock_irqrestore(&zone->lock, flags);
if (!ret)
drain_all_pages();
return ret;
}
void unset_migratetype_isolate(struct page *page, unsigned migratetype)
{
struct zone *zone;
unsigned long flags, nr_pages;
zone = page_zone(page);
spin_lock_irqsave(&zone->lock, flags);
if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
goto out;
nr_pages = move_freepages_block(zone, page, migratetype);
__mod_zone_freepage_state(zone, nr_pages, migratetype);
set_pageblock_migratetype(page, migratetype);
out:
spin_unlock_irqrestore(&zone->lock, flags);
}
static inline struct page *
__first_valid_page(unsigned long pfn, unsigned long nr_pages)
{
int i;
for (i = 0; i < nr_pages; i++)
if (pfn_valid_within(pfn + i))
break;
if (unlikely(i == nr_pages))
return NULL;
return pfn_to_page(pfn + i);
}
/*
* start_isolate_page_range() -- make page-allocation-type of range of pages
* to be MIGRATE_ISOLATE.
* @start_pfn: The lower PFN of the range to be isolated.
* @end_pfn: The upper PFN of the range to be isolated.
* @migratetype: migrate type to set in error recovery.
*
* Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
* the range will never be allocated. Any free pages and pages freed in the
* future will not be allocated again.
*
* start_pfn/end_pfn must be aligned to pageblock_order.
* Returns 0 on success and -EBUSY if any part of range cannot be isolated.
*/
int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
unsigned migratetype, bool skip_hwpoisoned_pages)
{
unsigned long pfn;
unsigned long undo_pfn;
struct page *page;
BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
for (pfn = start_pfn;
pfn < end_pfn;
pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
if (page &&
set_migratetype_isolate(page, skip_hwpoisoned_pages)) {
undo_pfn = pfn;
goto undo;
}
}
return 0;
undo:
for (pfn = start_pfn;
pfn < undo_pfn;
pfn += pageblock_nr_pages)
unset_migratetype_isolate(pfn_to_page(pfn), migratetype);
return -EBUSY;
}
/*
* Make isolated pages available again.
*/
int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
unsigned migratetype)
{
unsigned long pfn;
struct page *page;
BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
for (pfn = start_pfn;
pfn < end_pfn;
pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
continue;
unset_migratetype_isolate(page, migratetype);
}
return 0;
}
/*
* Test all pages in the range is free(means isolated) or not.
* all pages in [start_pfn...end_pfn) must be in the same zone.
* zone->lock must be held before call this.
*
* Returns 1 if all pages in the range are isolated.
*/
static int
__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
bool skip_hwpoisoned_pages)
{
struct page *page;
while (pfn < end_pfn) {
if (!pfn_valid_within(pfn)) {
pfn++;
continue;
}
page = pfn_to_page(pfn);
memory-hotplug: bug fix race between isolation and allocation Like below, memory-hotplug makes race between page-isolation and page-allocation so it can hit BUG_ON in __offline_isolated_pages. CPU A CPU B start_isolate_page_range set_migratetype_isolate spin_lock_irqsave(zone->lock) free_hot_cold_page(Page A) /* without zone->lock */ migratetype = get_pageblock_migratetype(Page A); /* * Page could be moved into MIGRATE_MOVABLE * of per_cpu_pages */ list_add_tail(&page->lru, &pcp->lists[migratetype]); set_pageblock_isolate move_freepages_block drain_all_pages /* Page A could be in MIGRATE_MOVABLE of free_list. */ check_pages_isolated __test_page_isolated_in_pageblock /* * We can't catch freed page which * is free_list[MIGRATE_MOVABLE] */ if (PageBuddy(page A)) pfn += 1 << page_order(page A); /* So, Page A could be allocated */ __offline_isolated_pages /* * BUG_ON hit or offline page * which is used by someone */ BUG_ON(!PageBuddy(page A)); This patch checks page's migratetype in freelist in __test_page_isolated_in_pageblock. So now __test_page_isolated_in_pageblock can check the page caused by above race and can fail of memory offlining. Signed-off-by: Minchan Kim <minchan@kernel.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-08 23:32:14 +00:00
if (PageBuddy(page)) {
/*
* If race between isolatation and allocation happens,
* some free pages could be in MIGRATE_MOVABLE list
* although pageblock's migratation type of the page
* is MIGRATE_ISOLATE. Catch it and move the page into
* MIGRATE_ISOLATE list.
*/
if (get_freepage_migratetype(page) != MIGRATE_ISOLATE) {
struct page *end_page;
end_page = page + (1 << page_order(page)) - 1;
move_freepages(page_zone(page), page, end_page,
MIGRATE_ISOLATE);
}
pfn += 1 << page_order(page);
memory-hotplug: bug fix race between isolation and allocation Like below, memory-hotplug makes race between page-isolation and page-allocation so it can hit BUG_ON in __offline_isolated_pages. CPU A CPU B start_isolate_page_range set_migratetype_isolate spin_lock_irqsave(zone->lock) free_hot_cold_page(Page A) /* without zone->lock */ migratetype = get_pageblock_migratetype(Page A); /* * Page could be moved into MIGRATE_MOVABLE * of per_cpu_pages */ list_add_tail(&page->lru, &pcp->lists[migratetype]); set_pageblock_isolate move_freepages_block drain_all_pages /* Page A could be in MIGRATE_MOVABLE of free_list. */ check_pages_isolated __test_page_isolated_in_pageblock /* * We can't catch freed page which * is free_list[MIGRATE_MOVABLE] */ if (PageBuddy(page A)) pfn += 1 << page_order(page A); /* So, Page A could be allocated */ __offline_isolated_pages /* * BUG_ON hit or offline page * which is used by someone */ BUG_ON(!PageBuddy(page A)); This patch checks page's migratetype in freelist in __test_page_isolated_in_pageblock. So now __test_page_isolated_in_pageblock can check the page caused by above race and can fail of memory offlining. Signed-off-by: Minchan Kim <minchan@kernel.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-08 23:32:14 +00:00
}
else if (page_count(page) == 0 &&
get_freepage_migratetype(page) == MIGRATE_ISOLATE)
pfn += 1;
else if (skip_hwpoisoned_pages && PageHWPoison(page)) {
/*
* The HWPoisoned page may be not in buddy
* system, and page_count() is not 0.
*/
pfn++;
continue;
}
else
break;
}
if (pfn < end_pfn)
return 0;
return 1;
}
int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
bool skip_hwpoisoned_pages)
{
memory hotplug: missing zone->lock in test_pages_isolated() __test_page_isolated_in_pageblock() in mm/page_isolation.c has a comment saying that the caller must hold zone->lock. But the only caller of that function, test_pages_isolated(), does not hold zone->lock and the lock is also not acquired anywhere before. This patch adds the missing zone->lock to test_pages_isolated(). We reproducibly run into BUG_ON(!PageBuddy(page)) in __offline_isolated_pages() during memory hotplug stress test, see trace below. This patch fixes that problem, it would be good if we could have it in 2.6.27. kernel BUG at /home/autobuild/BUILD/linux-2.6.26-20080909/mm/page_alloc.c:4561! illegal operation: 0001 [#1] PREEMPT SMP Modules linked in: dm_multipath sunrpc bonding qeth_l3 dm_mod qeth ccwgroup vmur CPU: 1 Not tainted 2.6.26-29.x.20080909-s390default #1 Process memory_loop_all (pid: 10025, task: 2f444028, ksp: 2b10dd28) Krnl PSW : 040c0000 801727ea (__offline_isolated_pages+0x18e/0x1c4) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:0 CC:0 PM:0 Krnl GPRS: 00000000 7e27fc00 00000000 7e27fc00 00000000 00000400 00014000 7e27fc01 00606f00 7e27fc00 00013fe0 2b10dd28 00000005 80172662 801727b2 2b10dd28 Krnl Code: 801727de: 5810900c l %r1,12(%r9) 801727e2: a7f4ffb3 brc 15,80172748 801727e6: a7f40001 brc 15,801727e8 >801727ea: a7f4ffbc brc 15,80172762 801727ee: a7f40001 brc 15,801727f0 801727f2: a7f4ffaf brc 15,80172750 801727f6: 0707 bcr 0,%r7 801727f8: 0017 unknown Call Trace: ([<0000000000172772>] __offline_isolated_pages+0x116/0x1c4) [<00000000001953a2>] offline_isolated_pages_cb+0x22/0x34 [<000000000013164c>] walk_memory_resource+0xcc/0x11c [<000000000019520e>] offline_pages+0x36a/0x498 [<00000000001004d6>] remove_memory+0x36/0x44 [<000000000028fb06>] memory_block_change_state+0x112/0x150 [<000000000028ffb8>] store_mem_state+0x90/0xe4 [<0000000000289c00>] sysdev_store+0x34/0x40 [<00000000001ee048>] sysfs_write_file+0xd0/0x178 [<000000000019b1a8>] vfs_write+0x74/0x118 [<000000000019b9ae>] sys_write+0x46/0x7c [<000000000011160e>] sysc_do_restart+0x12/0x16 [<0000000077f3e8ca>] 0x77f3e8ca Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-02 21:50:16 +00:00
unsigned long pfn, flags;
struct page *page;
memory hotplug: missing zone->lock in test_pages_isolated() __test_page_isolated_in_pageblock() in mm/page_isolation.c has a comment saying that the caller must hold zone->lock. But the only caller of that function, test_pages_isolated(), does not hold zone->lock and the lock is also not acquired anywhere before. This patch adds the missing zone->lock to test_pages_isolated(). We reproducibly run into BUG_ON(!PageBuddy(page)) in __offline_isolated_pages() during memory hotplug stress test, see trace below. This patch fixes that problem, it would be good if we could have it in 2.6.27. kernel BUG at /home/autobuild/BUILD/linux-2.6.26-20080909/mm/page_alloc.c:4561! illegal operation: 0001 [#1] PREEMPT SMP Modules linked in: dm_multipath sunrpc bonding qeth_l3 dm_mod qeth ccwgroup vmur CPU: 1 Not tainted 2.6.26-29.x.20080909-s390default #1 Process memory_loop_all (pid: 10025, task: 2f444028, ksp: 2b10dd28) Krnl PSW : 040c0000 801727ea (__offline_isolated_pages+0x18e/0x1c4) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:0 CC:0 PM:0 Krnl GPRS: 00000000 7e27fc00 00000000 7e27fc00 00000000 00000400 00014000 7e27fc01 00606f00 7e27fc00 00013fe0 2b10dd28 00000005 80172662 801727b2 2b10dd28 Krnl Code: 801727de: 5810900c l %r1,12(%r9) 801727e2: a7f4ffb3 brc 15,80172748 801727e6: a7f40001 brc 15,801727e8 >801727ea: a7f4ffbc brc 15,80172762 801727ee: a7f40001 brc 15,801727f0 801727f2: a7f4ffaf brc 15,80172750 801727f6: 0707 bcr 0,%r7 801727f8: 0017 unknown Call Trace: ([<0000000000172772>] __offline_isolated_pages+0x116/0x1c4) [<00000000001953a2>] offline_isolated_pages_cb+0x22/0x34 [<000000000013164c>] walk_memory_resource+0xcc/0x11c [<000000000019520e>] offline_pages+0x36a/0x498 [<00000000001004d6>] remove_memory+0x36/0x44 [<000000000028fb06>] memory_block_change_state+0x112/0x150 [<000000000028ffb8>] store_mem_state+0x90/0xe4 [<0000000000289c00>] sysdev_store+0x34/0x40 [<00000000001ee048>] sysfs_write_file+0xd0/0x178 [<000000000019b1a8>] vfs_write+0x74/0x118 [<000000000019b9ae>] sys_write+0x46/0x7c [<000000000011160e>] sysc_do_restart+0x12/0x16 [<0000000077f3e8ca>] 0x77f3e8ca Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-02 21:50:16 +00:00
struct zone *zone;
int ret;
/*
* Note: pageblock_nr_page != MAX_ORDER. Then, chunks of free page
* is not aligned to pageblock_nr_pages.
* Then we just check pagetype fist.
*/
for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
if (page && get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
break;
}
page = __first_valid_page(start_pfn, end_pfn - start_pfn);
if ((pfn < end_pfn) || !page)
return -EBUSY;
/* Check all pages are free or Marked as ISOLATED */
zone = page_zone(page);
memory hotplug: missing zone->lock in test_pages_isolated() __test_page_isolated_in_pageblock() in mm/page_isolation.c has a comment saying that the caller must hold zone->lock. But the only caller of that function, test_pages_isolated(), does not hold zone->lock and the lock is also not acquired anywhere before. This patch adds the missing zone->lock to test_pages_isolated(). We reproducibly run into BUG_ON(!PageBuddy(page)) in __offline_isolated_pages() during memory hotplug stress test, see trace below. This patch fixes that problem, it would be good if we could have it in 2.6.27. kernel BUG at /home/autobuild/BUILD/linux-2.6.26-20080909/mm/page_alloc.c:4561! illegal operation: 0001 [#1] PREEMPT SMP Modules linked in: dm_multipath sunrpc bonding qeth_l3 dm_mod qeth ccwgroup vmur CPU: 1 Not tainted 2.6.26-29.x.20080909-s390default #1 Process memory_loop_all (pid: 10025, task: 2f444028, ksp: 2b10dd28) Krnl PSW : 040c0000 801727ea (__offline_isolated_pages+0x18e/0x1c4) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:0 CC:0 PM:0 Krnl GPRS: 00000000 7e27fc00 00000000 7e27fc00 00000000 00000400 00014000 7e27fc01 00606f00 7e27fc00 00013fe0 2b10dd28 00000005 80172662 801727b2 2b10dd28 Krnl Code: 801727de: 5810900c l %r1,12(%r9) 801727e2: a7f4ffb3 brc 15,80172748 801727e6: a7f40001 brc 15,801727e8 >801727ea: a7f4ffbc brc 15,80172762 801727ee: a7f40001 brc 15,801727f0 801727f2: a7f4ffaf brc 15,80172750 801727f6: 0707 bcr 0,%r7 801727f8: 0017 unknown Call Trace: ([<0000000000172772>] __offline_isolated_pages+0x116/0x1c4) [<00000000001953a2>] offline_isolated_pages_cb+0x22/0x34 [<000000000013164c>] walk_memory_resource+0xcc/0x11c [<000000000019520e>] offline_pages+0x36a/0x498 [<00000000001004d6>] remove_memory+0x36/0x44 [<000000000028fb06>] memory_block_change_state+0x112/0x150 [<000000000028ffb8>] store_mem_state+0x90/0xe4 [<0000000000289c00>] sysdev_store+0x34/0x40 [<00000000001ee048>] sysfs_write_file+0xd0/0x178 [<000000000019b1a8>] vfs_write+0x74/0x118 [<000000000019b9ae>] sys_write+0x46/0x7c [<000000000011160e>] sysc_do_restart+0x12/0x16 [<0000000077f3e8ca>] 0x77f3e8ca Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-02 21:50:16 +00:00
spin_lock_irqsave(&zone->lock, flags);
ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn,
skip_hwpoisoned_pages);
memory hotplug: missing zone->lock in test_pages_isolated() __test_page_isolated_in_pageblock() in mm/page_isolation.c has a comment saying that the caller must hold zone->lock. But the only caller of that function, test_pages_isolated(), does not hold zone->lock and the lock is also not acquired anywhere before. This patch adds the missing zone->lock to test_pages_isolated(). We reproducibly run into BUG_ON(!PageBuddy(page)) in __offline_isolated_pages() during memory hotplug stress test, see trace below. This patch fixes that problem, it would be good if we could have it in 2.6.27. kernel BUG at /home/autobuild/BUILD/linux-2.6.26-20080909/mm/page_alloc.c:4561! illegal operation: 0001 [#1] PREEMPT SMP Modules linked in: dm_multipath sunrpc bonding qeth_l3 dm_mod qeth ccwgroup vmur CPU: 1 Not tainted 2.6.26-29.x.20080909-s390default #1 Process memory_loop_all (pid: 10025, task: 2f444028, ksp: 2b10dd28) Krnl PSW : 040c0000 801727ea (__offline_isolated_pages+0x18e/0x1c4) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:0 CC:0 PM:0 Krnl GPRS: 00000000 7e27fc00 00000000 7e27fc00 00000000 00000400 00014000 7e27fc01 00606f00 7e27fc00 00013fe0 2b10dd28 00000005 80172662 801727b2 2b10dd28 Krnl Code: 801727de: 5810900c l %r1,12(%r9) 801727e2: a7f4ffb3 brc 15,80172748 801727e6: a7f40001 brc 15,801727e8 >801727ea: a7f4ffbc brc 15,80172762 801727ee: a7f40001 brc 15,801727f0 801727f2: a7f4ffaf brc 15,80172750 801727f6: 0707 bcr 0,%r7 801727f8: 0017 unknown Call Trace: ([<0000000000172772>] __offline_isolated_pages+0x116/0x1c4) [<00000000001953a2>] offline_isolated_pages_cb+0x22/0x34 [<000000000013164c>] walk_memory_resource+0xcc/0x11c [<000000000019520e>] offline_pages+0x36a/0x498 [<00000000001004d6>] remove_memory+0x36/0x44 [<000000000028fb06>] memory_block_change_state+0x112/0x150 [<000000000028ffb8>] store_mem_state+0x90/0xe4 [<0000000000289c00>] sysdev_store+0x34/0x40 [<00000000001ee048>] sysfs_write_file+0xd0/0x178 [<000000000019b1a8>] vfs_write+0x74/0x118 [<000000000019b9ae>] sys_write+0x46/0x7c [<000000000011160e>] sysc_do_restart+0x12/0x16 [<0000000077f3e8ca>] 0x77f3e8ca Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-02 21:50:16 +00:00
spin_unlock_irqrestore(&zone->lock, flags);
return ret ? 0 : -EBUSY;
}
struct page *alloc_migrate_target(struct page *page, unsigned long private,
int **resultp)
{
gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
if (PageHighMem(page))
gfp_mask |= __GFP_HIGHMEM;
return alloc_page(gfp_mask);
}