1 files changed, 122 insertions, 87 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a663202045..14d39f34d3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -32,6 +32,7 @@
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
+#include <linux/pagevec.h>
 #include <linux/memory_hotplug.h>
 #include <linux/nodemask.h>
 #include <linux/vmstat.h>
@@ -464,19 +465,19 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 /*
  * Temporary debugging check for pages not lying within a given zone.
  */
-static int __maybe_unused bad_range(struct zone *zone, struct page *page)
+static bool __maybe_unused bad_range(struct zone *zone, struct page *page)
 {
 	if (page_outside_zone_boundaries(zone, page))
-		return 1;
+		return true;
 	if (zone != page_zone(page))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 #else
-static inline int __maybe_unused bad_range(struct zone *zone, struct page *page)
+static inline bool __maybe_unused bad_range(struct zone *zone, struct page *page)
 {
-	return 0;
+	return false;
 }
 #endif
 
@@ -1061,7 +1062,7 @@ out:
  * on-demand allocation and then freed again before the deferred pages
  * initialization is done, but this is not likely to happen.
  */
-static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
+static inline bool should_skip_kasan_poison(struct page *page)
 {
 	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
 		return deferred_pages_enabled();
@@ -1080,11 +1081,11 @@ static void kernel_init_pages(struct page *page, int numpages)
 	kasan_enable_current();
 }
 
-static __always_inline bool free_pages_prepare(struct page *page,
-			unsigned int order, fpi_t fpi_flags)
+__always_inline bool free_pages_prepare(struct page *page,
+			unsigned int order)
 {
 	int bad = 0;
-	bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
+	bool skip_kasan_poison = should_skip_kasan_poison(page);
 	bool init = want_init_on_free();
 	bool compound = PageCompound(page);
 
@@ -1266,7 +1267,7 @@ static void __free_pages_ok(struct page *page, unsigned int order,
 	unsigned long pfn = page_to_pfn(page);
 	struct zone *zone = page_zone(page);
 
-	if (!free_pages_prepare(page, order, fpi_flags))
+	if (!free_pages_prepare(page, order))
 		return;
 
 	/*
@@ -1422,14 +1423,14 @@ static void check_new_page_bad(struct page *page)
 /*
  * This page is about to be returned from the page allocator
  */
-static int check_new_page(struct page *page)
+static bool check_new_page(struct page *page)
 {
 	if (likely(page_expected_state(page,
 				PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON)))
-		return 0;
+		return false;
 
 	check_new_page_bad(page);
-	return 1;
+	return true;
 }
 
 static inline bool check_new_pages(struct page *page, unsigned int order)
@@ -2343,7 +2344,7 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn,
 {
 	int migratetype;
 
-	if (!free_pages_prepare(page, order, FPI_NONE))
+	if (!free_pages_prepare(page, order))
 		return false;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
@@ -2515,66 +2516,70 @@ void free_unref_page(struct page *page, unsigned int order)
 }
 
 /*
- * Free a list of 0-order pages
+ * Free a batch of folios
  */
-void free_unref_page_list(struct list_head *list)
+void free_unref_folios(struct folio_batch *folios)
 {
 	unsigned long __maybe_unused UP_flags;
-	struct page *page, *next;
 	struct per_cpu_pages *pcp = NULL;
 	struct zone *locked_zone = NULL;
-	int batch_count = 0;
-	int migratetype;
+	int i, j, migratetype;
 
-	/* Prepare pages for freeing */
-	list_for_each_entry_safe(page, next, list, lru) {
-		unsigned long pfn = page_to_pfn(page);
-		if (!free_unref_page_prepare(page, pfn, 0)) {
-			list_del(&page->lru);
+	/* Prepare folios for freeing */
+	for (i = 0, j = 0; i < folios->nr; i++) {
+		struct folio *folio = folios->folios[i];
+		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);
+		if (!free_unref_page_prepare(&folio->page, pfn, order))
 			continue;
-		}
 
 		/*
-		 * Free isolated pages directly to the allocator, see
-		 * comment in free_unref_page.
+		 * Free isolated folios and orders not handled on the PCP
+		 * directly to the allocator, see comment in free_unref_page.
 		 */
-		migratetype = get_pcppage_migratetype(page);
-		if (unlikely(is_migrate_isolate(migratetype))) {
-			list_del(&page->lru);
-			free_one_page(page_zone(page), page, pfn, 0, migratetype, FPI_NONE);
+		migratetype = get_pcppage_migratetype(&folio->page);
+		if (!pcp_allowed_order(order) ||
+		    is_migrate_isolate(migratetype)) {
+			free_one_page(folio_zone(folio), &folio->page, pfn,
+					order, migratetype, FPI_NONE);
 			continue;
 		}
+		folio->private = (void *)(unsigned long)order;
+		if (j != i)
+			folios->folios[j] = folio;
+		j++;
 	}
+	folios->nr = j;
 
-	list_for_each_entry_safe(page, next, list, lru) {
-		struct zone *zone = page_zone(page);
+	for (i = 0; i < folios->nr; i++) {
+		struct folio *folio = folios->folios[i];
+		struct zone *zone = folio_zone(folio);
+		unsigned int order = (unsigned long)folio->private;
 
-		list_del(&page->lru);
-		migratetype = get_pcppage_migratetype(page);
+		folio->private = NULL;
+		migratetype = get_pcppage_migratetype(&folio->page);
 
-		/*
-		 * Either different zone requiring a different pcp lock or
-		 * excessive lock hold times when freeing a large list of
-		 * pages.
-		 */
-		if (zone != locked_zone || batch_count == SWAP_CLUSTER_MAX) {
+		/* Different zone requires a different pcp lock */
+		if (zone != locked_zone) {
 			if (pcp) {
 				pcp_spin_unlock(pcp);
 				pcp_trylock_finish(UP_flags);
 			}
 
-			batch_count = 0;
-
 			/*
-			 * trylock is necessary as pages may be getting freed
+			 * trylock is necessary as folios may be getting freed
 			 * from IRQ or SoftIRQ context after an IO completion.
 			 */
 			pcp_trylock_prepare(UP_flags);
 			pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 			if (unlikely(!pcp)) {
 				pcp_trylock_finish(UP_flags);
-				free_one_page(zone, page, page_to_pfn(page),
-					      0, migratetype, FPI_NONE);
+				free_one_page(zone, &folio->page,
+						folio_pfn(folio), order,
+						migratetype, FPI_NONE);
 				locked_zone = NULL;
 				continue;
 			}
@@ -2588,15 +2593,16 @@ void free_unref_page_list(struct list_head *list)
 		if (unlikely(migratetype >= MIGRATE_PCPTYPES))
 			migratetype = MIGRATE_MOVABLE;
 
-		trace_mm_page_free_batched(page);
-		free_unref_page_commit(zone, pcp, page, migratetype, 0);
-		batch_count++;
+		trace_mm_page_free_batched(&folio->page);
+		free_unref_page_commit(zone, pcp, &folio->page, migratetype,
+				order);
 	}
 
 	if (pcp) {
 		pcp_spin_unlock(pcp);
 		pcp_trylock_finish(UP_flags);
 	}
+	folio_batch_reinit(folios);
 }
 
 /*
@@ -2616,8 +2622,8 @@ void split_page(struct page *page, unsigned int order)
 
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
-	split_page_owner(page, 1 << order);
-	split_page_memcg(page, 1 << order);
+	split_page_owner(page, order, 0);
+	split_page_memcg(page, order, 0);
 }
 EXPORT_SYMBOL_GPL(split_page);
 
@@ -4687,8 +4693,8 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 	gfp_t gfp = gfp_mask;
 
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
-		    __GFP_NOMEMALLOC;
+	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
+		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
 	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
 				PAGE_FRAG_CACHE_MAX_ORDER);
 	nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
@@ -4701,6 +4707,16 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 	return page;
 }
 
+void page_frag_cache_drain(struct page_frag_cache *nc)
+{
+	if (!nc->va)
+		return;
+
+	__page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
+	nc->va = NULL;
+}
+EXPORT_SYMBOL(page_frag_cache_drain);
+
 void __page_frag_cache_drain(struct page *page, unsigned int count)
 {
 	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
@@ -4710,9 +4726,9 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
-void *page_frag_alloc_align(struct page_frag_cache *nc,
-		      unsigned int fragsz, gfp_t gfp_mask,
-		      unsigned int align_mask)
+void *__page_frag_alloc_align(struct page_frag_cache *nc,
+			      unsigned int fragsz, gfp_t gfp_mask,
+			      unsigned int align_mask)
 {
 	unsigned int size = PAGE_SIZE;
 	struct page *page;
@@ -4781,7 +4797,7 @@ refill:
 
 	return nc->va + offset;
 }
-EXPORT_SYMBOL(page_frag_alloc_align);
+EXPORT_SYMBOL(__page_frag_alloc_align);
 
 /*
  * Frees a page fragment allocated out of either a compound or order 0 page.
@@ -4803,8 +4819,8 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		struct page *page = virt_to_page((void *)addr);
 		struct page *last = page + nr;
 
-		split_page_owner(page, 1 << order);
-		split_page_memcg(page, 1 << order);
+		split_page_owner(page, order, 0);
+		split_page_memcg(page, order, 0);
 		while (page < --last)
 			set_page_refcounted(last);
 
@@ -5574,37 +5590,34 @@ static void zone_pcp_update(struct zone *zone, int cpu_online)
 	mutex_unlock(&pcp_batch_high_lock);
 }
 
-static void zone_pcp_update_cacheinfo(struct zone *zone)
+static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu)
 {
-	int cpu;
 	struct per_cpu_pages *pcp;
 	struct cpu_cacheinfo *cci;
 
-	for_each_online_cpu(cpu) {
-		pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
-		cci = get_cpu_cacheinfo(cpu);
-		/*
-		 * If data cache slice of CPU is large enough, "pcp->batch"
-		 * pages can be preserved in PCP before draining PCP for
-		 * consecutive high-order pages freeing without allocation.
-		 * This can reduce zone lock contention without hurting
-		 * cache-hot pages sharing.
-		 */
-		spin_lock(&pcp->lock);
-		if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch)
-			pcp->flags |= PCPF_FREE_HIGH_BATCH;
-		else
-			pcp->flags &= ~PCPF_FREE_HIGH_BATCH;
-		spin_unlock(&pcp->lock);
-	}
+	pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+	cci = get_cpu_cacheinfo(cpu);
+	/*
+	 * If data cache slice of CPU is large enough, "pcp->batch"
+	 * pages can be preserved in PCP before draining PCP for
+	 * consecutive high-order pages freeing without allocation.
+	 * This can reduce zone lock contention without hurting
+	 * cache-hot pages sharing.
+	 */
+	spin_lock(&pcp->lock);
+	if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch)
+		pcp->flags |= PCPF_FREE_HIGH_BATCH;
+	else
+		pcp->flags &= ~PCPF_FREE_HIGH_BATCH;
+	spin_unlock(&pcp->lock);
 }
 
-void setup_pcp_cacheinfo(void)
+void setup_pcp_cacheinfo(unsigned int cpu)
 {
 	struct zone *zone;
 
 	for_each_populated_zone(zone)
-		zone_pcp_update_cacheinfo(zone);
+		zone_pcp_update_cacheinfo(zone, cpu);
 }
 
 /*
@@ -5847,7 +5860,7 @@ static void __setup_per_zone_wmarks(void)
 
 		spin_lock_irqsave(&zone->lock, flags);
 		tmp = (u64)pages_min * zone_managed_pages(zone);
-		do_div(tmp, lowmem_pages);
+		tmp = div64_ul(tmp, lowmem_pages);
 		if (is_highmem(zone) || zone_idx(zone) == ZONE_MOVABLE) {
 			/*
 			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -6221,9 +6234,14 @@ static void alloc_contig_dump_pages(struct list_head *page_list)
 	}
 }
 
-/* [start, end) must belong to a single zone. */
+/*
+ * [start, end) must belong to a single zone.
+ * @migratetype: using migratetype to filter the type of migration in
+ *		trace_mm_alloc_contig_migrate_range_info.
+ */
 int __alloc_contig_migrate_range(struct compact_control *cc,
-					unsigned long start, unsigned long end)
+					unsigned long start, unsigned long end,
+					int migratetype)
 {
 	/* This function is based on compact_zone() from compaction.c. */
 	unsigned int nr_reclaimed;
@@ -6234,6 +6252,10 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 		.nid = zone_to_nid(cc->zone),
 		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
 	};
+	struct page *page;
+	unsigned long total_mapped = 0;
+	unsigned long total_migrated = 0;
+	unsigned long total_reclaimed = 0;
 
 	lru_cache_disable();
 
@@ -6259,9 +6281,18 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 							&cc->migratepages);
 		cc->nr_migratepages -= nr_reclaimed;
 
+		if (trace_mm_alloc_contig_migrate_range_info_enabled()) {
+			total_reclaimed += nr_reclaimed;
+			list_for_each_entry(page, &cc->migratepages, lru)
+				total_mapped += page_mapcount(page);
+		}
+
 		ret = migrate_pages(&cc->migratepages, alloc_migration_target,
 			NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE, NULL);
 
+		if (trace_mm_alloc_contig_migrate_range_info_enabled() && !ret)
+			total_migrated += cc->nr_migratepages;
+
 		/*
 		 * On -ENOMEM, migrate_pages() bails out right away. It is pointless
 		 * to retry again over this error, so do the same here.
@@ -6275,9 +6306,13 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 		if (!(cc->gfp_mask & __GFP_NOWARN) && ret == -EBUSY)
 			alloc_contig_dump_pages(&cc->migratepages);
 		putback_movable_pages(&cc->migratepages);
-		return ret;
 	}
-	return 0;
+
+	trace_mm_alloc_contig_migrate_range_info(start, end, migratetype,
+						 total_migrated,
+						 total_reclaimed,
+						 total_mapped);
+	return (ret < 0) ? ret : 0;
 }
 
 /**
@@ -6357,7 +6392,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 * allocated.  So, if we fall through be sure to clear ret so that
 	 * -EBUSY is not accidentally used or returned to caller.
 	 */
-	ret = __alloc_contig_migrate_range(&cc, start, end);
+	ret = __alloc_contig_migrate_range(&cc, start, end, migratetype);
 	if (ret && ret != -EBUSY)
 		goto done;
 	ret = 0;