Revert "mm/cma: manage the memory of the CMA area by using the ZONE_MOVABLE"

This reverts the following commits that change CMA design in MM.

 3d2054ad8c2d ("ARM: CMA: avoid double mapping to the CMA area if CONFIG_HIGHMEM=y")

 1d47a3ec09b5 ("mm/cma: remove ALLOC_CMA")

 bad8c6c0b114 ("mm/cma: manage the memory of the CMA area by using the ZONE_MOVABLE")

Ville reported a following error on i386.

  Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
  microcode: microcode updated early to revision 0x4, date = 2013-06-28
  Initializing CPU#0
  Initializing HighMem for node 0 (000377fe:00118000)
  Initializing Movable for node 0 (00000001:00118000)
  BUG: Bad page state in process swapper  pfn:377fe
  page:f53effc0 count:0 mapcount:-127 mapping:00000000 index:0x0
  flags: 0x80000000()
  raw: 80000000 00000000 00000000 ffffff80 00000000 00000100 00000200 00000001
  page dumped because: nonzero mapcount
  Modules linked in:
  CPU: 0 PID: 0 Comm: swapper Not tainted 4.17.0-rc5-elk+ #145
  Hardware name: Dell Inc. Latitude E5410/03VXMC, BIOS A15 07/11/2013
  Call Trace:
   dump_stack+0x60/0x96
   bad_page+0x9a/0x100
   free_pages_check_bad+0x3f/0x60
   free_pcppages_bulk+0x29d/0x5b0
   free_unref_page_commit+0x84/0xb0
   free_unref_page+0x3e/0x70
   __free_pages+0x1d/0x20
   free_highmem_page+0x19/0x40
   add_highpages_with_active_regions+0xab/0xeb
   set_highmem_pages_init+0x66/0x73
   mem_init+0x1b/0x1d7
   start_kernel+0x17a/0x363
   i386_start_kernel+0x95/0x99
   startup_32_smp+0x164/0x168

The reason for this error is that the span of MOVABLE_ZONE is extended
to whole node span for future CMA initialization, and, normal memory is
wrongly freed here.  I submitted the fix and it seems to work, but,
another problem happened.

It's so late time to fix the later problem so I decide to reverting the
series.

Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Laura Abbott <labbott@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 30 insertions, 53 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 905db9d7962f..511a7124d7f9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1743,38 +1743,16 @@ void __init page_alloc_init_late(void)
 }
 
 #ifdef CONFIG_CMA
-static void __init adjust_present_page_count(struct page *page, long count)
-{
-	struct zone *zone = page_zone(page);
-
-	/* We don't need to hold a lock since it is boot-up process */
-	zone->present_pages += count;
-}
-
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void __init init_cma_reserved_pageblock(struct page *page)
 {
 	unsigned i = pageblock_nr_pages;
-	unsigned long pfn = page_to_pfn(page);
 	struct page *p = page;
-	int nid = page_to_nid(page);
-
-	/*
-	 * ZONE_MOVABLE will steal present pages from other zones by
-	 * changing page links so page_zone() is changed. Before that,
-	 * we need to adjust previous zone's page count first.
-	 */
-	adjust_present_page_count(page, -pageblock_nr_pages);
 
 	do {
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
-
-		/* Steal pages from other zones */
-		set_page_links(p, ZONE_MOVABLE, nid, pfn);
-	} while (++p, ++pfn, --i);
-
-	adjust_present_page_count(page, pageblock_nr_pages);
+	} while (++p, --i);
 
 	set_pageblock_migratetype(page, MIGRATE_CMA);
 
@@ -2889,7 +2867,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		 * exists.
 		 */
 		watermark = min_wmark_pages(zone) + (1UL << order);
-		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+		if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
 			return 0;
 
 		__mod_zone_freepage_state(zone, -(1UL << order), mt);
@@ -3165,6 +3143,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 	}
 
 
+#ifdef CONFIG_CMA
+	/* If allocation can't use CMA areas don't use free CMA pages */
+	if (!(alloc_flags & ALLOC_CMA))
+		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
 	/*
 	 * Check watermarks for an order-0 allocation request. If these
 	 * are not met, then a high-order request also cannot go ahead
@@ -3191,8 +3175,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		}
 
 #ifdef CONFIG_CMA
-		if (!list_empty(&area->free_list[MIGRATE_CMA]))
+		if ((alloc_flags & ALLOC_CMA) &&
+		    !list_empty(&area->free_list[MIGRATE_CMA])) {
 			return true;
+		}
 #endif
 		if (alloc_harder &&
 			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
@@ -3212,6 +3198,13 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 		unsigned long mark, int classzone_idx, unsigned int alloc_flags)
 {
 	long free_pages = zone_page_state(z, NR_FREE_PAGES);
+	long cma_pages = 0;
+
+#ifdef CONFIG_CMA
+	/* If allocation can't use CMA areas don't use free CMA pages */
+	if (!(alloc_flags & ALLOC_CMA))
+		cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
 
 	/*
 	 * Fast check for order-0 only. If this fails then the reserves
@@ -3220,7 +3213,7 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	 * the caller is !atomic then it'll uselessly search the free
 	 * list. That corner case is then slower but it is harmless.
 	 */
-	if (!order && free_pages > mark + z->lowmem_reserve[classzone_idx])
+	if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
 		return true;
 
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
@@ -3856,6 +3849,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
+#ifdef CONFIG_CMA
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+		alloc_flags |= ALLOC_CMA;
+#endif
 	return alloc_flags;
 }
 
@@ -4322,6 +4319,9 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 	if (should_fail_alloc_page(gfp_mask, order))
 		return false;
 
+	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
+		*alloc_flags |= ALLOC_CMA;
+
 	return true;
 }
 
@@ -6204,7 +6204,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
-	unsigned long node_end_pfn = 0;
 
 	pgdat_resize_init(pgdat);
 #ifdef CONFIG_NUMA_BALANCING
@@ -6232,13 +6231,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, freesize, memmap_pages;
 		unsigned long zone_start_pfn = zone->zone_start_pfn;
-		unsigned long movable_size = 0;
 
 		size = zone->spanned_pages;
 		realsize = freesize = zone->present_pages;
-		if (zone_end_pfn(zone) > node_end_pfn)
-			node_end_pfn = zone_end_pfn(zone);
-
 
 		/*
 		 * Adjust freesize so that it accounts for how much memory
@@ -6287,30 +6282,12 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone_seqlock_init(zone);
 		zone_pcp_init(zone);
 
-		/*
-		 * The size of the CMA area is unknown now so we need to
-		 * prepare the memory for the usemap at maximum.
-		 */
-		if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE &&
-			pgdat->node_spanned_pages) {
-			movable_size = node_end_pfn - pgdat->node_start_pfn;
-		}
-
-		if (!size && !movable_size)
+		if (!size)
 			continue;
 
 		set_pageblock_order();
-		if (movable_size) {
-			zone->zone_start_pfn = pgdat->node_start_pfn;
-			zone->spanned_pages = movable_size;
-			setup_usemap(pgdat, zone,
-				pgdat->node_start_pfn, movable_size);
-			init_currently_empty_zone(zone,
-				pgdat->node_start_pfn, movable_size);
-		} else {
-			setup_usemap(pgdat, zone, zone_start_pfn, size);
-			init_currently_empty_zone(zone, zone_start_pfn, size);
-		}
+		setup_usemap(pgdat, zone, zone_start_pfn, size);
+		init_currently_empty_zone(zone, zone_start_pfn, size);
 		memmap_init(size, nid, j, zone_start_pfn);
 	}
 }
@@ -7951,7 +7928,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 }
 #endif
 
-#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
  * page high values need to be recalulated.