linux/mm/page_isolation.c
David Hildenbrand aa218795cb mm: Allow to offline unmovable PageOffline() pages via MEM_GOING_OFFLINE
virtio-mem wants to allow to offline memory blocks of which some parts
were unplugged (allocated via alloc_contig_range()), especially, to later
offline and remove completely unplugged memory blocks. The important part
is that PageOffline() has to remain set until the section is offline, so
these pages will never get accessed (e.g., when dumping). The pages should
not be handed back to the buddy (which would require clearing PageOffline()
and result in issues if offlining fails and the pages are suddenly in the
buddy).

Let's allow to do that by allowing to isolate any PageOffline() page
when offlining. This way, we can reach the memory hotplug notifier
MEM_GOING_OFFLINE, where the driver can signal that he is fine with
offlining this page by dropping its reference count. PageOffline() pages
with a reference count of 0 can then be skipped when offlining the
pages (like if they were free, however they are not in the buddy).

Anybody who uses PageOffline() pages and does not agree to offline them
(e.g., Hyper-V balloon, XEN balloon, VMWare balloon for 2MB pages) will not
decrement the reference count and make offlining fail when trying to
migrate such an unmovable page. So there should be no observable change.
Same applies to balloon compaction users (movable PageOffline() pages), the
pages will simply be migrated.

Note 1: If offlining fails, a driver has to increment the reference
	count again in MEM_CANCEL_OFFLINE.

Note 2: A driver that makes use of this has to be aware that re-onlining
	the memory block has to be handled by hooking into onlining code
	(online_page_callback_t), resetting the page PageOffline() and
	not giving them to the buddy.

Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Tested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Juergen Gross <jgross@suse.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Pavel Tatashin <pavel.tatashin@microsoft.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Anthony Yznaga <anthony.yznaga@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Pingfan Liu <kernelfans@gmail.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200507140139.17083-7-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2020-06-04 15:36:52 -04:00

314 lines
8.8 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* 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 <linux/migrate.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/page_isolation.h>
static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
{
struct page *unmovable = NULL;
struct zone *zone;
unsigned long flags;
int ret = -EBUSY;
zone = page_zone(page);
spin_lock_irqsave(&zone->lock, flags);
/*
* We assume the caller intended to SET migrate type to isolate.
* If it is already set, then someone else must have raced and
* set it before us. Return -EBUSY
*/
if (is_migrate_isolate_page(page))
goto out;
/*
* FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
* We just check MOVABLE pages.
*/
unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags);
if (!unmovable) {
unsigned long nr_pages;
int mt = 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, mt);
ret = 0;
}
out:
spin_unlock_irqrestore(&zone->lock, flags);
if (!ret) {
drain_all_pages(zone);
} else {
WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
if ((isol_flags & REPORT_FAILURE) && unmovable)
/*
* printk() with zone->lock held will likely trigger a
* lockdep splat, so defer it here.
*/
dump_page(unmovable, "unmovable page");
}
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);
if (isolated_page)
__putback_isolated_page(page, order, migratetype);
zone->nr_isolate_pageblock--;
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++) {
struct page *page;
page = pfn_to_online_page(pfn + i);
if (!page)
continue;
return page;
}
return NULL;
}
/**
* 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.
* start_pfn/end_pfn must be aligned to pageblock_order.
* @migratetype: Migrate type to set in error recovery.
* @flags: The following flags are allowed (they can be combined in
* a bit mask)
* MEMORY_OFFLINE - isolate to offline (!allocate) memory
* e.g., skip over PageHWPoison() pages
* and PageOffline() pages.
* REPORT_FAILURE - report details about the failure to
* isolate the range
*
* 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. If specified range includes migrate types
* other than MOVABLE or CMA, this will fail with -EBUSY. For isolating all
* pages in the range finally, the caller have to free all pages in the range.
* test_page_isolated() can be used for test it.
*
* There is no high level synchronization mechanism that prevents two threads
* from trying to isolate overlapping ranges. If this happens, one thread
* will notice pageblocks in the overlapping range already set to isolate.
* This happens in set_migratetype_isolate, and set_migratetype_isolate
* returns an error. We then clean up by restoring the migration type on
* pageblocks we may have modified and return -EBUSY to caller. This
* prevents two threads from simultaneously working on overlapping ranges.
*
* Return: the number of isolated pageblocks 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, int flags)
{
unsigned long pfn;
unsigned long undo_pfn;
struct page *page;
int nr_isolate_pageblock = 0;
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) {
if (set_migratetype_isolate(page, migratetype, flags)) {
undo_pfn = pfn;
goto undo;
}
nr_isolate_pageblock++;
}
}
return nr_isolate_pageblock;
undo:
for (pfn = start_pfn;
pfn < undo_pfn;
pfn += pageblock_nr_pages) {
struct page *page = pfn_to_online_page(pfn);
if (!page)
continue;
unset_migratetype_isolate(page, migratetype);
}
return -EBUSY;
}
/*
* Make isolated pages available again.
*/
void 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);
}
}
/*
* 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,
int flags)
{
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 ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
/* A HWPoisoned page cannot be also PageBuddy */
pfn++;
else if ((flags & MEMORY_OFFLINE) && PageOffline(page) &&
!page_count(page))
/*
* The responsible driver agreed to skip PageOffline()
* pages when offlining memory by dropping its
* reference in MEM_GOING_OFFLINE.
*/
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,
int isol_flags)
{
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, isol_flags);
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)
{
return new_page_nodemask(page, numa_node_id(), &node_states[N_MEMORY]);
}