mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![Vlastimil Babka](/assets/img/avatar_default.png)
When stealing pages from pageblock of a different migratetype, we count how many free pages were stolen, and change the pageblock's migratetype if more than half of the pageblock was free. This might be too conservative, as there might be other pages that are not free, but were allocated with the same migratetype as our allocation requested. While we cannot determine the migratetype of allocated pages precisely (at least without the page_owner functionality enabled), we can count pages that compaction would try to isolate for migration - those are either on LRU or __PageMovable(). The rest can be assumed to be MIGRATE_RECLAIMABLE or MIGRATE_UNMOVABLE, which we cannot easily distinguish. This counting can be done as part of free page stealing with little additional overhead. The page stealing code is changed so that it considers free pages plus pages of the "good" migratetype for the decision whether to change pageblock's migratetype. The result should be more accurate migratetype of pageblocks wrt the actual pages in the pageblocks, when stealing from semi-occupied pageblocks. This should help the efficiency of page grouping by mobility. In testing based on 4.9 kernel with stress-highalloc from mmtests configured for order-4 GFP_KERNEL allocations, this patch has reduced the number of unmovable allocations falling back to movable pageblocks by 47%. The number of movable allocations falling back to other pageblocks are increased by 55%, but these events don't cause permanent fragmentation, so the tradeoff should be positive. Later patches also offset the movable fallback increase to some extent. [akpm@linux-foundation.org: merge fix] Link: http://lkml.kernel.org/r/20170307131545.28577-5-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
303 lines
8.3 KiB
C
303 lines
8.3 KiB
C
/*
|
|
* linux/mm/page_isolation.c
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/page-isolation.h>
|
|
#include <linux/pageblock-flags.h>
|
|
#include <linux/memory.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/page_owner.h>
|
|
#include "internal.h"
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/page_isolation.h>
|
|
|
|
static 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" pages. 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);
|
|
zone->nr_isolate_pageblock++;
|
|
nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE,
|
|
NULL);
|
|
|
|
__mod_zone_freepage_state(zone, -nr_pages, migratetype);
|
|
}
|
|
|
|
spin_unlock_irqrestore(&zone->lock, flags);
|
|
if (!ret)
|
|
drain_all_pages(zone);
|
|
return ret;
|
|
}
|
|
|
|
static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
|
|
{
|
|
struct zone *zone;
|
|
unsigned long flags, nr_pages;
|
|
bool isolated_page = false;
|
|
unsigned int order;
|
|
unsigned long pfn, buddy_pfn;
|
|
struct page *buddy;
|
|
|
|
zone = page_zone(page);
|
|
spin_lock_irqsave(&zone->lock, flags);
|
|
if (!is_migrate_isolate_page(page))
|
|
goto out;
|
|
|
|
/*
|
|
* Because freepage with more than pageblock_order on isolated
|
|
* pageblock is restricted to merge due to freepage counting problem,
|
|
* it is possible that there is free buddy page.
|
|
* move_freepages_block() doesn't care of merge so we need other
|
|
* approach in order to merge them. Isolation and free will make
|
|
* these pages to be merged.
|
|
*/
|
|
if (PageBuddy(page)) {
|
|
order = page_order(page);
|
|
if (order >= pageblock_order) {
|
|
pfn = page_to_pfn(page);
|
|
buddy_pfn = __find_buddy_pfn(pfn, order);
|
|
buddy = page + (buddy_pfn - pfn);
|
|
|
|
if (pfn_valid_within(buddy_pfn) &&
|
|
!is_migrate_isolate_page(buddy)) {
|
|
__isolate_free_page(page, order);
|
|
isolated_page = true;
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If we isolate freepage with more than pageblock_order, there
|
|
* should be no freepage in the range, so we could avoid costly
|
|
* pageblock scanning for freepage moving.
|
|
*/
|
|
if (!isolated_page) {
|
|
nr_pages = move_freepages_block(zone, page, migratetype, NULL);
|
|
__mod_zone_freepage_state(zone, nr_pages, migratetype);
|
|
}
|
|
set_pageblock_migratetype(page, migratetype);
|
|
zone->nr_isolate_pageblock--;
|
|
out:
|
|
spin_unlock_irqrestore(&zone->lock, flags);
|
|
if (isolated_page) {
|
|
post_alloc_hook(page, order, __GFP_MOVABLE);
|
|
__free_pages(page, order);
|
|
}
|
|
}
|
|
|
|
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(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
|
|
BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
|
|
|
|
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(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
|
|
BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
|
|
|
|
for (pfn = start_pfn;
|
|
pfn < end_pfn;
|
|
pfn += pageblock_nr_pages) {
|
|
page = __first_valid_page(pfn, pageblock_nr_pages);
|
|
if (!page || !is_migrate_isolate_page(page))
|
|
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 the last tested pfn.
|
|
*/
|
|
static unsigned long
|
|
__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);
|
|
if (PageBuddy(page))
|
|
/*
|
|
* If the page is on a free list, it has to be on
|
|
* the correct MIGRATE_ISOLATE freelist. There is no
|
|
* simple way to verify that as VM_BUG_ON(), though.
|
|
*/
|
|
pfn += 1 << page_order(page);
|
|
else if (skip_hwpoisoned_pages && PageHWPoison(page))
|
|
/* A HWPoisoned page cannot be also PageBuddy */
|
|
pfn++;
|
|
else
|
|
break;
|
|
}
|
|
|
|
return pfn;
|
|
}
|
|
|
|
/* Caller should ensure that requested range is in a single zone */
|
|
int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
|
|
bool skip_hwpoisoned_pages)
|
|
{
|
|
unsigned long pfn, flags;
|
|
struct page *page;
|
|
struct zone *zone;
|
|
|
|
/*
|
|
* Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
|
|
* are not aligned to pageblock_nr_pages.
|
|
* Then we just check migratetype first.
|
|
*/
|
|
for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
|
|
page = __first_valid_page(pfn, pageblock_nr_pages);
|
|
if (page && !is_migrate_isolate_page(page))
|
|
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);
|
|
spin_lock_irqsave(&zone->lock, flags);
|
|
pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn,
|
|
skip_hwpoisoned_pages);
|
|
spin_unlock_irqrestore(&zone->lock, flags);
|
|
|
|
trace_test_pages_isolated(start_pfn, end_pfn, pfn);
|
|
|
|
return pfn < end_pfn ? -EBUSY : 0;
|
|
}
|
|
|
|
struct page *alloc_migrate_target(struct page *page, unsigned long private,
|
|
int **resultp)
|
|
{
|
|
gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
|
|
|
|
/*
|
|
* TODO: allocate a destination hugepage from a nearest neighbor node,
|
|
* accordance with memory policy of the user process if possible. For
|
|
* now as a simple work-around, we use the next node for destination.
|
|
*/
|
|
if (PageHuge(page))
|
|
return alloc_huge_page_node(page_hstate(compound_head(page)),
|
|
next_node_in(page_to_nid(page),
|
|
node_online_map));
|
|
|
|
if (PageHighMem(page))
|
|
gfp_mask |= __GFP_HIGHMEM;
|
|
|
|
return alloc_page(gfp_mask);
|
|
}
|