mm: page_isolation: check specified range for unmovable pages

Enable set_migratetype_isolate() to check specified range for unmovable
pages during isolation to prepare arbitrary range page isolation.  The
functionality will take effect in upcoming commits by adjusting the
callers of start_isolate_page_range(), which uses
set_migratetype_isolate().

For example, alloc_contig_range(), which calls start_isolate_page_range(),
accepts unaligned ranges, but because page isolation is currently done at
MAX_ORDER_NR_PAEGS granularity, pages that are out of the specified range
but withint MAX_ORDER_NR_PAEGS alignment might be attempted for isolation
and the failure of isolating these unrelated pages fails the whole
operation undesirably.

Link: https://lkml.kernel.org/r/20220425143118.2850746-3-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Eric Ren <renzhengeek@gmail.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index df49f86..c2f7a8b 100644 (file)
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -16,7 +16,9 @@
 #include <trace/events/page_isolation.h>
 
 /*
- * This function checks whether pageblock includes unmovable pages or not.
+ * This function checks whether the range [start_pfn, end_pfn) includes
+ * unmovable pages or not. The range must fall into a single pageblock and
+ * consequently belong to a single zone.
  *
  * PageLRU check without isolation or lru_lock could race so that
  * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
@@ -28,12 +30,15 @@
  * 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)
+static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long end_pfn,
+                               int migratetype, int flags)
 {
-       unsigned long iter = 0;
-       unsigned long pfn = page_to_pfn(page);
-       unsigned long offset = pfn % pageblock_nr_pages;
+       struct page *page = pfn_to_page(start_pfn);
+       struct zone *zone = page_zone(page);
+       unsigned long pfn;
+
+       VM_BUG_ON(ALIGN_DOWN(start_pfn, pageblock_nr_pages) !=
+                 ALIGN_DOWN(end_pfn - 1, pageblock_nr_pages));
 
        if (is_migrate_cma_page(page)) {
                /*
@@ -47,8 +52,8 @@ 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 = start_pfn; pfn < end_pfn; pfn++) {
+               page = pfn_to_page(pfn);
 
                /*
                 * Both, bootmem allocations and memory holes are marked
@@ -85,7 +90,7 @@ 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 +102,7 @@ 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;
                }
 
@@ -134,11 +139,18 @@ 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 intersect with
+ * [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;
+       unsigned long check_unmovable_start, check_unmovable_end;
 
        spin_lock_irqsave(&zone->lock, flags);
 
@@ -155,8 +167,16 @@ 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.
+        *
+        * Pass the intersection of [start_pfn, end_pfn) and the page's pageblock
+        * to avoid redundant checks.
         */
-       unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags);
+       check_unmovable_start = max(page_to_pfn(page), start_pfn);
+       check_unmovable_end = min(ALIGN(page_to_pfn(page) + 1, pageblock_nr_pages),
+                                 end_pfn);
+
+       unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
+                       migratetype, isol_flags);
        if (!unmovable) {
                unsigned long nr_pages;
                int mt = get_pageblock_migratetype(page);
@@ -313,7 +333,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
             pfn < end_pfn;
             pfn += pageblock_nr_pages) {
                page = __first_valid_page(pfn, pageblock_nr_pages);
-               if (page && set_migratetype_isolate(page, migratetype, flags)) {
+               if (page && set_migratetype_isolate(page, migratetype, flags,
+                                       start_pfn, end_pfn)) {
                        undo_isolate_page_range(start_pfn, pfn, migratetype);
                        return -EBUSY;
                }