linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Zi Yan <zi.yan@sent.com>
To: David Hildenbrand <david@redhat.com>, linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org,
	Michael Ellerman <mpe@ellerman.id.au>,
	Christoph Hellwig <hch@lst.de>,
	Marek Szyprowski <m.szyprowski@samsung.com>,
	Robin Murphy <robin.murphy@arm.com>,
	linuxppc-dev@lists.ozlabs.org,
	virtualization@lists.linux-foundation.org,
	iommu@lists.linux-foundation.org,
	Vlastimil Babka <vbabka@suse.cz>,
	Mel Gorman <mgorman@techsingularity.net>,
	Eric Ren <renzhengeek@gmail.com>, Mike Rapoport <rppt@kernel.org>,
	Oscar Salvador <osalvador@suse.de>, Zi Yan <ziy@nvidia.com>
Subject: [PATCH v5 2/6] mm: page_isolation: check specified range for unmovable pages
Date: Fri, 11 Feb 2022 11:41:31 -0500	[thread overview]
Message-ID: <20220211164135.1803616-3-zi.yan@sent.com> (raw)
In-Reply-To: <20220211164135.1803616-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.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.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/page-isolation.h | 12 +++++++++
 mm/page_alloc.c                | 15 +----------
 mm/page_isolation.c            | 46 +++++++++++++++++++++-------------
 3 files changed, 41 insertions(+), 32 deletions(-)

diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index e14eddf6741a..4ef7be6def83 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -15,6 +15,18 @@ static inline bool is_migrate_isolate(int migratetype)
 {
 	return migratetype == MIGRATE_ISOLATE;
 }
+static inline unsigned long pfn_max_align_down(unsigned long pfn)
+{
+	return ALIGN_DOWN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
+				     pageblock_nr_pages));
+}
+
+static inline unsigned long pfn_max_align_up(unsigned long pfn)
+{
+	return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
+				pageblock_nr_pages));
+}
+
 #else
 static inline bool has_isolate_pageblock(struct zone *zone)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e2c6a67fc386..62ef78f3d771 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8963,18 +8963,6 @@ void *__init alloc_large_system_hash(const char *tablename,
 }
 
 #ifdef CONFIG_CONTIG_ALLOC
-static unsigned long pfn_max_align_down(unsigned long pfn)
-{
-	return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
-			     pageblock_nr_pages) - 1);
-}
-
-static unsigned long pfn_max_align_up(unsigned long pfn)
-{
-	return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
-				pageblock_nr_pages));
-}
-
 #if defined(CONFIG_DYNAMIC_DEBUG) || \
 	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* Usage: See admin-guide/dynamic-debug-howto.rst */
@@ -9119,8 +9107,7 @@ 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(pfn_max_align_down(start),
-				       pfn_max_align_up(end), migratetype, 0);
+	ret = start_isolate_page_range(start, end, migratetype, 0);
 	if (ret)
 		return ret;
 
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index b34f1310aeaa..64d093ab83ec 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -16,7 +16,8 @@
 #include <trace/events/page_isolation.h>
 
 /*
- * This function checks whether pageblock includes unmovable pages or not.
+ * 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
@@ -29,11 +30,14 @@
  *
  */
 static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
-				 int migratetype, int flags)
+				 int migratetype, int flags,
+				 unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long iter = 0;
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset = pfn % pageblock_nr_pages;
+	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)) {
 		/*
@@ -47,8 +51,8 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 		return page;
 	}
 
-	for (; iter < pageblock_nr_pages - offset; iter++) {
-		page = pfn_to_page(pfn + iter);
+	for (pfn = first_pfn; pfn < last_pfn; pfn++) {
+		page = pfn_to_page(pfn);
 
 		/*
 		 * Both, bootmem allocations and memory holes are marked
@@ -85,7 +89,7 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 			}
 
 			skip_pages = compound_nr(head) - (page - head);
-			iter += skip_pages - 1;
+			pfn += skip_pages - 1;
 			continue;
 		}
 
@@ -97,7 +101,7 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 		 */
 		if (!page_ref_count(page)) {
 			if (PageBuddy(page))
-				iter += (1 << buddy_order(page)) - 1;
+				pfn += (1 << buddy_order(page)) - 1;
 			continue;
 		}
 
@@ -134,7 +138,13 @@ static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 	return NULL;
 }
 
-static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
+/*
+ * 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;
@@ -156,7 +166,7 @@ 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);
@@ -267,7 +277,6 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * 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)
@@ -309,15 +318,16 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long pfn;
 	struct page *page;
 
-	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
-	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
+	unsigned long isolate_start = pfn_max_align_down(start_pfn);
+	unsigned long isolate_end = pfn_max_align_up(end_pfn);
 
-	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



  parent reply	other threads:[~2022-02-11 16:41 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-11 16:41 [PATCH v5 0/6] Use pageblock_order for cma and alloc_contig_range alignment Zi Yan
2022-02-11 16:41 ` [PATCH v5 1/6] mm: page_isolation: move has_unmovable_pages() to mm/page_isolation.c Zi Yan
2022-02-14 10:44   ` Mike Rapoport
2022-02-11 16:41 ` Zi Yan [this message]
2022-02-11 16:41 ` [PATCH v5 3/6] mm: make alloc_contig_range work at pageblock granularity Zi Yan
2022-02-14  7:26   ` Christoph Hellwig
2022-02-14 15:46     ` Zi Yan
2022-02-14  7:59   ` Christophe Leroy
2022-02-14 16:03     ` Zi Yan
2022-02-11 16:41 ` [PATCH v5 4/6] mm: cma: use pageblock_order as the single alignment Zi Yan
2022-02-11 16:41 ` [PATCH v5 5/6] drivers: virtio_mem: use pageblock size as the minimum virtio_mem size Zi Yan
2022-02-11 16:41 ` [PATCH v5 6/6] arch: powerpc: adjust fadump alignment to be pageblock aligned Zi Yan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220211164135.1803616-3-zi.yan@sent.com \
    --to=zi.yan@sent.com \
    --cc=david@redhat.com \
    --cc=hch@lst.de \
    --cc=iommu@lists.linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=m.szyprowski@samsung.com \
    --cc=mgorman@techsingularity.net \
    --cc=mpe@ellerman.id.au \
    --cc=osalvador@suse.de \
    --cc=renzhengeek@gmail.com \
    --cc=robin.murphy@arm.com \
    --cc=rppt@kernel.org \
    --cc=vbabka@suse.cz \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=ziy@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox