| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 5 Jan 2022 16:47:53 -0500
From: Zi Yan <zi.yan@...t.com>
To: David Hildenbrand <david@...hat.com>, linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org,
Michael Ellerman <mpe@...erman.id.au>,
Christoph Hellwig <hch@....de>,
Marek Szyprowski <m.szyprowski@...sung.com>,
Robin Murphy <robin.murphy@....com>,
linuxppc-dev@...ts.ozlabs.org,
virtualization@...ts.linux-foundation.org,
iommu@...ts.linux-foundation.org, Vlastimil Babka <vbabka@...e.cz>,
Mel Gorman <mgorman@...hsingularity.net>,
Eric Ren <renzhengeek@...il.com>, Zi Yan <ziy@...dia.com>
Subject: [RFC PATCH v3 5/8] mm: page_isolation: check specified range for unmovable pages during isolation.
From: Zi Yan <ziy@...dia.com>
Enable set_migratetype_isolate() to check specified sub-range for
unmovable pages during isolation. Page isolation is done
at max(MAX_ORDER_NR_PAEGS, pageblock_nr_pages) granularity, but not all
pages within that granularity are intended to be isolated. For example,
alloc_contig_range(), which uses page isolation, allows ranges without
alignment. This commit makes unmovable page check only look for
interesting pages, so that page isolation can succeed for any
non-overlapping ranges.
has_unmovable_pages() is moved to mm/page_isolation.c since it is only
used by page isolation.
Signed-off-by: Zi Yan <ziy@...dia.com>
---
include/linux/page-isolation.h | 3 +-
mm/memory_hotplug.c | 12 ++-
mm/page_alloc.c | 122 +--------------------------
mm/page_isolation.c | 148 +++++++++++++++++++++++++++++++--
4 files changed, 153 insertions(+), 132 deletions(-)
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 572458016331..a4d2687ed4e6 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -33,8 +33,6 @@ static inline bool is_migrate_isolate(int migratetype)
#define MEMORY_OFFLINE 0x1
#define REPORT_FAILURE 0x2
-struct page *has_unmovable_pages(struct zone *zone, struct page *page,
- int migratetype, int flags);
void set_pageblock_migratetype(struct page *page, int migratetype);
int move_freepages_block(struct zone *zone, struct page *page,
int migratetype, int *num_movable);
@@ -44,6 +42,7 @@ int move_freepages_block(struct zone *zone, struct page *page,
*/
int
start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long isolate_start, unsigned long isolate_end,
unsigned migratetype, int flags);
/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0139b77c51d5..5db84c3fa882 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1901,8 +1901,18 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
zone_pcp_disable(zone);
lru_cache_disable();
- /* set above range as isolated */
+ /*
+ * set above range as isolated
+ *
+ * start_pfn and end_pfn are the same as isolate_start and isolate_end,
+ * because start_pfn and end_pfn are already PAGES_PER_SECTION
+ * (>= MAX_ORDER_NR_PAGES) aligned; if start_pfn is
+ * pageblock_nr_pages aligned in memmap_on_memory case, there is no
+ * need to isolate pages before start_pfn, since they are used by
+ * memmap thus not user visible.
+ */
ret = start_isolate_page_range(start_pfn, end_pfn,
+ start_pfn, end_pfn,
MIGRATE_MOVABLE,
MEMORY_OFFLINE | REPORT_FAILURE);
if (ret) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e1c09ae54e31..faee7637740a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8864,125 +8864,6 @@ void *__init alloc_large_system_hash(const char *tablename,
return table;
}
-/*
- * This function checks whether pageblock includes unmovable pages or not.
- *
- * PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
- * check without lock_page also may miss some movable non-lru pages at
- * race condition. So you can't expect this function should be exact.
- *
- * Returns a page without holding a reference. If the caller wants to
- * dereference that page (e.g., dumping), it has to make sure that it
- * cannot get removed (e.g., via memory unplug) concurrently.
- *
- */
-struct page *has_unmovable_pages(struct zone *zone, struct page *page,
- int migratetype, int flags)
-{
- unsigned long iter = 0;
- unsigned long pfn = page_to_pfn(page);
- unsigned long offset = pfn % pageblock_nr_pages;
-
- if (is_migrate_cma_page(page)) {
- /*
- * CMA allocations (alloc_contig_range) really need to mark
- * isolate CMA pageblocks even when they are not movable in fact
- * so consider them movable here.
- */
- if (is_migrate_cma(migratetype))
- return NULL;
-
- return page;
- }
-
- for (; iter < pageblock_nr_pages - offset; iter++) {
- page = pfn_to_page(pfn + iter);
-
- /*
- * Both, bootmem allocations and memory holes are marked
- * PG_reserved and are unmovable. We can even have unmovable
- * allocations inside ZONE_MOVABLE, for example when
- * specifying "movablecore".
- */
- if (PageReserved(page))
- return page;
-
- /*
- * If the zone is movable and we have ruled out all reserved
- * pages then it should be reasonably safe to assume the rest
- * is movable.
- */
- if (zone_idx(zone) == ZONE_MOVABLE)
- continue;
-
- /*
- * Hugepages are not in LRU lists, but they're movable.
- * THPs are on the LRU, but need to be counted as #small pages.
- * We need not scan over tail pages because we don't
- * handle each tail page individually in migration.
- */
- if (PageHuge(page) || PageTransCompound(page)) {
- struct page *head = compound_head(page);
- unsigned int skip_pages;
-
- if (PageHuge(page)) {
- if (!hugepage_migration_supported(page_hstate(head)))
- return page;
- } else if (!PageLRU(head) && !__PageMovable(head)) {
- return page;
- }
-
- skip_pages = compound_nr(head) - (page - head);
- iter += skip_pages - 1;
- continue;
- }
-
- /*
- * We can't use page_count without pin a page
- * because another CPU can free compound page.
- * This check already skips compound tails of THP
- * because their page->_refcount is zero at all time.
- */
- if (!page_ref_count(page)) {
- if (PageBuddy(page))
- iter += (1 << buddy_order(page)) - 1;
- continue;
- }
-
- /*
- * The HWPoisoned page may be not in buddy system, and
- * page_count() is not 0.
- */
- if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
- continue;
-
- /*
- * We treat all PageOffline() pages as movable when offlining
- * to give drivers a chance to decrement their reference count
- * in MEM_GOING_OFFLINE in order to indicate that these pages
- * can be offlined as there are no direct references anymore.
- * For actually unmovable PageOffline() where the driver does
- * not support this, we will fail later when trying to actually
- * move these pages that still have a reference count > 0.
- * (false negatives in this function only)
- */
- if ((flags & MEMORY_OFFLINE) && PageOffline(page))
- continue;
-
- if (__PageMovable(page) || PageLRU(page))
- continue;
-
- /*
- * If there are RECLAIMABLE pages, we need to check
- * it. But now, memory offline itself doesn't call
- * shrink_node_slabs() and it still to be fixed.
- */
- return page;
- }
- return NULL;
-}
-
#ifdef CONFIG_CONTIG_ALLOC
static unsigned long pfn_max_align_down(unsigned long pfn)
{
@@ -9226,7 +9107,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
* put back to page allocator so that buddy can use them.
*/
- ret = start_isolate_page_range(isolate_start, isolate_end, migratetype, 0);
+ ret = start_isolate_page_range(start, end, isolate_start, isolate_end,
+ migratetype, 0);
if (ret)
goto done;
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 6a0ddda6b3c5..7a7991460eb9 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -15,12 +15,143 @@
#define CREATE_TRACE_POINTS
#include <trace/events/page_isolation.h>
-static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
+/*
+ * This function checks whether pageblock within [start_pfn, end_pfn) includes
+ * unmovable pages or not.
+ *
+ * PageLRU check without isolation or lru_lock could race so that
+ * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
+ * check without lock_page also may miss some movable non-lru pages at
+ * race condition. So you can't expect this function should be exact.
+ *
+ * Returns a page without holding a reference. If the caller wants to
+ * dereference that page (e.g., dumping), it has to make sure that it
+ * cannot get removed (e.g., via memory unplug) concurrently.
+ *
+ */
+static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+ int migratetype, int flags,
+ unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long first_pfn = max(page_to_pfn(page), start_pfn);
+ unsigned long pfn = first_pfn;
+ unsigned long last_pfn = min(ALIGN(pfn + 1, pageblock_nr_pages), end_pfn);
+
+ page = pfn_to_page(pfn);
+
+ if (is_migrate_cma_page(page)) {
+ /*
+ * CMA allocations (alloc_contig_range) really need to mark
+ * isolate CMA pageblocks even when they are not movable in fact
+ * so consider them movable here.
+ */
+ if (is_migrate_cma(migratetype))
+ return NULL;
+
+ return page;
+ }
+
+ for (pfn = first_pfn; pfn < last_pfn; pfn++) {
+ page = pfn_to_page(pfn);
+
+ /*
+ * Both, bootmem allocations and memory holes are marked
+ * PG_reserved and are unmovable. We can even have unmovable
+ * allocations inside ZONE_MOVABLE, for example when
+ * specifying "movablecore".
+ */
+ if (PageReserved(page))
+ return page;
+
+ /*
+ * If the zone is movable and we have ruled out all reserved
+ * pages then it should be reasonably safe to assume the rest
+ * is movable.
+ */
+ if (zone_idx(zone) == ZONE_MOVABLE)
+ continue;
+
+ /*
+ * Hugepages are not in LRU lists, but they're movable.
+ * THPs are on the LRU, but need to be counted as #small pages.
+ * We need not scan over tail pages because we don't
+ * handle each tail page individually in migration.
+ */
+ if (PageHuge(page) || PageTransCompound(page)) {
+ struct page *head = compound_head(page);
+ unsigned int skip_pages;
+
+ if (PageHuge(page)) {
+ if (!hugepage_migration_supported(page_hstate(head)))
+ return page;
+ } else if (!PageLRU(head) && !__PageMovable(head)) {
+ return page;
+ }
+
+ skip_pages = compound_nr(head) - (page - head);
+ pfn += skip_pages - 1;
+ continue;
+ }
+
+ /*
+ * We can't use page_count without pin a page
+ * because another CPU can free compound page.
+ * This check already skips compound tails of THP
+ * because their page->_refcount is zero at all time.
+ */
+ if (!page_ref_count(page)) {
+ if (PageBuddy(page))
+ pfn += (1 << buddy_order(page)) - 1;
+ continue;
+ }
+
+ /*
+ * The HWPoisoned page may be not in buddy system, and
+ * page_count() is not 0.
+ */
+ if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
+ continue;
+
+ /*
+ * We treat all PageOffline() pages as movable when offlining
+ * to give drivers a chance to decrement their reference count
+ * in MEM_GOING_OFFLINE in order to indicate that these pages
+ * can be offlined as there are no direct references anymore.
+ * For actually unmovable PageOffline() where the driver does
+ * not support this, we will fail later when trying to actually
+ * move these pages that still have a reference count > 0.
+ * (false negatives in this function only)
+ */
+ if ((flags & MEMORY_OFFLINE) && PageOffline(page))
+ continue;
+
+ if (__PageMovable(page) || PageLRU(page))
+ continue;
+
+ /*
+ * If there are RECLAIMABLE pages, we need to check
+ * it. But now, memory offline itself doesn't call
+ * shrink_node_slabs() and it still to be fixed.
+ */
+ return page;
+ }
+ return NULL;
+}
+
+/*
+ * This function set pageblock migratetype to isolate if no unmovable page is
+ * present in [start_pfn, end_pfn). The pageblock must be within
+ * [start_pfn, end_pfn).
+ */
+static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags,
+ unsigned long start_pfn, unsigned long end_pfn)
{
struct zone *zone = page_zone(page);
struct page *unmovable;
unsigned long flags;
+ VM_BUG_ON(page_to_pfn(page) < start_pfn || page_to_pfn(page) >= end_pfn);
+
spin_lock_irqsave(&zone->lock, flags);
/*
@@ -37,7 +168,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
* 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);
+ unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags, start_pfn, end_pfn);
if (!unmovable) {
unsigned long nr_pages;
int mt = get_pageblock_migratetype(page);
@@ -185,20 +316,19 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
* Return: 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 long isolate_start, unsigned long isolate_end,
unsigned migratetype, int flags)
{
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;
+ for (pfn = isolate_start;
+ pfn < isolate_end;
pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
- if (page && set_migratetype_isolate(page, migratetype, flags)) {
- undo_isolate_page_range(start_pfn, pfn, migratetype);
+ if (page && set_migratetype_isolate(page, migratetype, flags,
+ start_pfn, end_pfn)) {
+ undo_isolate_page_range(isolate_start, pfn, migratetype);
return -EBUSY;
}
}
--
2.34.1
Powered by blists - more mailing lists