1 files changed, 95 insertions, 66 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9ecf99190ea2..c565de8f48e9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes);
 
 static bool page_contains_unaccepted(struct page *page, unsigned int order);
 static void accept_page(struct page *page, unsigned int order);
-static bool try_to_accept_memory(struct zone *zone, unsigned int order);
+static bool cond_accept_memory(struct zone *zone, unsigned int order);
 static inline bool has_unaccepted_memory(void);
 static bool __free_unaccepted(struct page *page);
 
@@ -498,7 +498,8 @@ static void bad_page(struct page *page, const char *reason)
 	dump_stack();
 out:
 	/* Leave bad fields for debug, except PageBuddy could make trouble */
-	page_mapcount_reset(page); /* remove PageBuddy */
+	if (PageBuddy(page))
+		__ClearPageBuddy(page);
 	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 }
 
@@ -711,12 +712,12 @@ static inline struct page *get_page_from_free_area(struct free_area *area,
 }
 
 /*
- * If this is not the largest possible page, check if the buddy
- * of the next-highest order is free. If it is, it's possible
+ * If this is less than the 2nd largest possible page, check if the buddy
+ * of the next-higher order is free. If it is, it's possible
  * that pages are being freed that will coalesce soon. In case,
  * that is happening, add the free page to the tail of the list
  * so it's less likely to be used soon and more likely to be merged
- * as a higher order page
+ * as a 2-level higher order page
  */
 static inline bool
 buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
@@ -1218,7 +1219,8 @@ static void __free_pages_ok(struct page *page, unsigned int order,
 	__count_vm_events(PGFREE, 1 << order);
 }
 
-void __free_pages_core(struct page *page, unsigned int order)
+void __meminit __free_pages_core(struct page *page, unsigned int order,
+		enum meminit_context context)
 {
 	unsigned int nr_pages = 1 << order;
 	struct page *p = page;
@@ -1228,17 +1230,34 @@ void __free_pages_core(struct page *page, unsigned int order)
 	 * When initializing the memmap, __init_single_page() sets the refcount
 	 * of all pages to 1 ("allocated"/"not free"). We have to set the
 	 * refcount of all involved pages to 0.
+	 *
+	 * Note that hotplugged memory pages are initialized to PageOffline().
+	 * Pages freed from memblock might be marked as reserved.
 	 */
-	prefetchw(p);
-	for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
-		prefetchw(p + 1);
-		__ClearPageReserved(p);
-		set_page_count(p, 0);
-	}
-	__ClearPageReserved(p);
-	set_page_count(p, 0);
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) &&
+	    unlikely(context == MEMINIT_HOTPLUG)) {
+		for (loop = 0; loop < nr_pages; loop++, p++) {
+			VM_WARN_ON_ONCE(PageReserved(p));
+			__ClearPageOffline(p);
+			set_page_count(p, 0);
+		}
+
+		/*
+		 * Freeing the page with debug_pagealloc enabled will try to
+		 * unmap it; some archs don't like double-unmappings, so
+		 * map it first.
+		 */
+		debug_pagealloc_map_pages(page, nr_pages);
+		adjust_managed_page_count(page, nr_pages);
+	} else {
+		for (loop = 0; loop < nr_pages; loop++, p++) {
+			__ClearPageReserved(p);
+			set_page_count(p, 0);
+		}
 
-	atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
+		/* memblock adjusts totalram_pages() manually. */
+		atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
+	}
 
 	if (page_contains_unaccepted(page, order)) {
 		if (order == MAX_PAGE_ORDER && __free_unaccepted(page))
@@ -1351,7 +1370,8 @@ static void check_new_page_bad(struct page *page)
 {
 	if (unlikely(page->flags & __PG_HWPOISON)) {
 		/* Don't complain about hwpoisoned pages */
-		page_mapcount_reset(page); /* remove PageBuddy */
+		if (PageBuddy(page))
+			__ClearPageBuddy(page);
 		return;
 	}
 
@@ -2323,16 +2343,20 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
-	int count = READ_ONCE(pcp->count);
-
-	while (count) {
-		int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
-		count -= to_drain;
+	int count;
 
+	do {
 		spin_lock(&pcp->lock);
-		free_pcppages_bulk(zone, to_drain, pcp, 0);
+		count = pcp->count;
+		if (count) {
+			int to_drain = min(count,
+				pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
+
+			free_pcppages_bulk(zone, to_drain, pcp, 0);
+			count -= to_drain;
+		}
 		spin_unlock(&pcp->lock);
-	}
+	} while (count);
 }
 
 /*
@@ -2632,8 +2656,7 @@ void free_unref_folios(struct folio_batch *folios)
 		unsigned long pfn = folio_pfn(folio);
 		unsigned int order = folio_order(folio);
 
-		if (order > 0 && folio_test_large_rmappable(folio))
-			folio_undo_large_rmappable(folio);
+		folio_undo_large_rmappable(folio);
 		if (!free_pages_prepare(&folio->page, order))
 			continue;
 		/*
@@ -3031,12 +3054,6 @@ out:
 	return page;
 }
 
-noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
-{
-	return __should_fail_alloc_page(gfp_mask, order);
-}
-ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
-
 static inline long __zone_watermark_unusable_free(struct zone *z,
 				unsigned int order, unsigned int alloc_flags)
 {
@@ -3055,9 +3072,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z,
 	if (!(alloc_flags & ALLOC_CMA))
 		unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
-#ifdef CONFIG_UNACCEPTED_MEMORY
-	unusable_free += zone_page_state(z, NR_UNACCEPTED);
-#endif
 
 	return unusable_free;
 }
@@ -3351,6 +3365,8 @@ retry:
 			}
 		}
 
+		cond_accept_memory(zone, order);
+
 		/*
 		 * Detect whether the number of free pages is below high
 		 * watermark.  If so, we will decrease pcp->high and free
@@ -3376,10 +3392,8 @@ check_alloc_wmark:
 				       gfp_mask)) {
 			int ret;
 
-			if (has_unaccepted_memory()) {
-				if (try_to_accept_memory(zone, order))
-					goto try_this_zone;
-			}
+			if (cond_accept_memory(zone, order))
+				goto try_this_zone;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 			/*
@@ -3433,10 +3447,8 @@ try_this_zone:
 
 			return page;
 		} else {
-			if (has_unaccepted_memory()) {
-				if (try_to_accept_memory(zone, order))
-					goto try_this_zone;
-			}
+			if (cond_accept_memory(zone, order))
+				goto try_this_zone;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 			/* Try again if zone has deferred pages */
@@ -5114,7 +5126,7 @@ static char numa_zonelist_order[] = "Node";
 /*
  * sysctl handler for numa_zonelist_order
  */
-static int numa_zonelist_order_handler(struct ctl_table *table, int write,
+static int numa_zonelist_order_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
@@ -5213,7 +5225,7 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
 }
 
 /*
- * Build gfp_thisnode zonelists
+ * Build __GFP_THISNODE zonelists
  */
 static void build_thisnode_zonelists(pg_data_t *pgdat)
 {
@@ -5762,10 +5774,6 @@ void adjust_managed_page_count(struct page *page, long count)
 {
 	atomic_long_add(count, &page_zone(page)->managed_pages);
 	totalram_pages_add(count);
-#ifdef CONFIG_HIGHMEM
-	if (PageHighMem(page))
-		totalhigh_pages_add(count);
-#endif
 }
 EXPORT_SYMBOL(adjust_managed_page_count);
 
@@ -5805,6 +5813,16 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 	return pages;
 }
 
+void free_reserved_page(struct page *page)
+{
+	clear_page_tag_ref(page);
+	ClearPageReserved(page);
+	init_page_count(page);
+	__free_page(page);
+	adjust_managed_page_count(page, 1);
+}
+EXPORT_SYMBOL(free_reserved_page);
+
 static int page_alloc_cpu_dead(unsigned int cpu)
 {
 	struct zone *zone;
@@ -6081,7 +6099,7 @@ postcore_initcall(init_per_zone_wmark_min)
  *	that we can call two helper functions whenever min_free_kbytes
  *	changes.
  */
-static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
+static int min_free_kbytes_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6097,7 +6115,7 @@ static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
 	return 0;
 }
 
-static int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
+static int watermark_scale_factor_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6127,7 +6145,7 @@ static void setup_min_unmapped_ratio(void)
 }
 
 
-static int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_unmapped_ratio_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6154,7 +6172,7 @@ static void setup_min_slab_ratio(void)
 						     sysctl_min_slab_ratio) / 100;
 }
 
-static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_slab_ratio_sysctl_handler(const struct ctl_table *table, int write,
 		void *buffer, size_t *length, loff_t *ppos)
 {
 	int rc;
@@ -6178,7 +6196,7 @@ static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int wri
  * minimum watermarks. The lowmem reserve ratio can only make sense
  * if in function of the boot time zone sizes.
  */
-static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table,
+static int lowmem_reserve_ratio_sysctl_handler(const struct ctl_table *table,
 		int write, void *buffer, size_t *length, loff_t *ppos)
 {
 	int i;
@@ -6199,7 +6217,7 @@ static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table,
  * cpu. It is the fraction of total pages in each zone that a hot per cpu
  * pagelist can have before it gets flushed back to buddy allocator.
  */
-static int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table,
+static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table *table,
 		int write, void *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
@@ -6690,14 +6708,19 @@ void zone_pcp_reset(struct zone *zone)
 /*
  * All pages in the range must be in a single zone, must not contain holes,
  * must span full sections, and must be isolated before calling this function.
+ *
+ * Returns the number of managed (non-PageOffline()) pages in the range: the
+ * number of pages for which memory offlining code must adjust managed page
+ * counters using adjust_managed_page_count().
  */
-void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+unsigned long __offline_isolated_pages(unsigned long start_pfn,
+		unsigned long end_pfn)
 {
+	unsigned long already_offline = 0, flags;
 	unsigned long pfn = start_pfn;
 	struct page *page;
 	struct zone *zone;
 	unsigned int order;
-	unsigned long flags;
 
 	offline_mem_sections(pfn, end_pfn);
 	zone = page_zone(pfn_to_page(pfn));
@@ -6719,6 +6742,7 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		if (PageOffline(page)) {
 			BUG_ON(page_count(page));
 			BUG_ON(PageBuddy(page));
+			already_offline++;
 			pfn++;
 			continue;
 		}
@@ -6731,6 +6755,8 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		pfn += (1 << order);
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);
+
+	return end_pfn - start_pfn - already_offline;
 }
 #endif
 
@@ -6912,9 +6938,6 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	struct page *page;
 	bool last;
 
-	if (list_empty(&zone->unaccepted_pages))
-		return false;
-
 	spin_lock_irqsave(&zone->lock, flags);
 	page = list_first_entry_or_null(&zone->unaccepted_pages,
 					struct page, lru);
@@ -6940,23 +6963,29 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	return true;
 }
 
-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order)
 {
 	long to_accept;
-	int ret = false;
+	bool ret = false;
+
+	if (!has_unaccepted_memory())
+		return false;
+
+	if (list_empty(&zone->unaccepted_pages))
+		return false;
 
 	/* How much to accept to get to high watermark? */
 	to_accept = high_wmark_pages(zone) -
 		    (zone_page_state(zone, NR_FREE_PAGES) -
-		    __zone_watermark_unusable_free(zone, order, 0));
+		    __zone_watermark_unusable_free(zone, order, 0) -
+		    zone_page_state(zone, NR_UNACCEPTED));
 
-	/* Accept at least one page */
-	do {
+	while (to_accept > 0) {
 		if (!try_to_accept_memory_one(zone))
 			break;
 		ret = true;
 		to_accept -= MAX_ORDER_NR_PAGES;
-	} while (to_accept > 0);
+	}
 
 	return ret;
 }
@@ -6999,7 +7028,7 @@ static void accept_page(struct page *page, unsigned int order)
 {
 }
 
-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+static bool cond_accept_memory(struct zone *zone, unsigned int order)
 {
 	return false;
 }