1 files changed, 56 insertions, 58 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fab5e97dc9ca..05fe1ddb033c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
 #include <linux/nmi.h>
 #include <linux/psi.h>
 #include <linux/padata.h>
+#include <linux/khugepaged.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -155,16 +156,16 @@ static int __init early_init_on_alloc(char *buf)
 	int ret;
 	bool bool_result;
 
-	if (!buf)
-		return -EINVAL;
 	ret = kstrtobool(buf, &bool_result);
+	if (ret)
+		return ret;
 	if (bool_result && page_poisoning_enabled())
 		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n");
 	if (bool_result)
 		static_branch_enable(&init_on_alloc);
 	else
 		static_branch_disable(&init_on_alloc);
-	return ret;
+	return 0;
 }
 early_param("init_on_alloc", early_init_on_alloc);
 
@@ -173,16 +174,16 @@ static int __init early_init_on_free(char *buf)
 	int ret;
 	bool bool_result;
 
-	if (!buf)
-		return -EINVAL;
 	ret = kstrtobool(buf, &bool_result);
+	if (ret)
+		return ret;
 	if (bool_result && page_poisoning_enabled())
 		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n");
 	if (bool_result)
 		static_branch_enable(&init_on_free);
 	else
 		static_branch_disable(&init_on_free);
-	return ret;
+	return 0;
 }
 early_param("init_on_free", early_init_on_free);
 
@@ -3367,9 +3368,16 @@ struct page *rmqueue(struct zone *preferred_zone,
 	struct page *page;
 
 	if (likely(order == 0)) {
-		page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
+		/*
+		 * MIGRATE_MOVABLE pcplist could have the pages on CMA area and
+		 * we need to skip it when CMA area isn't allowed.
+		 */
+		if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA ||
+				migratetype != MIGRATE_MOVABLE) {
+			page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
 					migratetype, alloc_flags);
-		goto out;
+			goto out;
+		}
 	}
 
 	/*
@@ -3381,7 +3389,13 @@ struct page *rmqueue(struct zone *preferred_zone,
 
 	do {
 		page = NULL;
-		if (alloc_flags & ALLOC_HARDER) {
+		/*
+		 * order-0 request can reach here when the pcplist is skipped
+		 * due to non-CMA allocation context. HIGHATOMIC area is
+		 * reserved for high-order atomic allocation, so order-0
+		 * request should skip it.
+		 */
+		if (order > 0 && alloc_flags & ALLOC_HARDER) {
 			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
 			if (page)
 				trace_mm_page_alloc_zone_locked(page, order, migratetype);
@@ -3727,8 +3741,8 @@ retry:
 	 */
 	no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
 	z = ac->preferred_zoneref;
-	for_next_zone_zonelist_nodemask(zone, z, ac->zonelist,
-					ac->highest_zoneidx, ac->nodemask) {
+	for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx,
+					ac->nodemask) {
 		struct page *page;
 		unsigned long mark;
 
@@ -3972,8 +3986,10 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	 * success so it is time to admit defeat. We will skip the OOM killer
 	 * because it is very likely that the caller has a more reasonable
 	 * fallback than shooting a random task.
+	 *
+	 * The OOM killer may not free memory on a specific node.
 	 */
-	if (gfp_mask & __GFP_RETRY_MAYFAIL)
+	if (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_THISNODE))
 		goto out;
 	/* The OOM killer does not needlessly kill tasks for lowmem */
 	if (ac->highest_zoneidx < ZONE_NORMAL)
@@ -3990,10 +4006,6 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	 * failures more gracefully we should just bail out here.
 	 */
 
-	/* The OOM killer may not free memory on a specific node */
-	if (gfp_mask & __GFP_THISNODE)
-		goto out;
-
 	/* Exhausted what can be done so it's blame time */
 	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
 		*did_some_progress = 1;
@@ -4241,13 +4253,12 @@ EXPORT_SYMBOL_GPL(fs_reclaim_release);
 #endif
 
 /* Perform direct synchronous page reclaim */
-static int
+static unsigned long
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 					const struct alloc_context *ac)
 {
-	int progress;
 	unsigned int noreclaim_flag;
-	unsigned long pflags;
+	unsigned long pflags, progress;
 
 	cond_resched();
 
@@ -4826,12 +4837,6 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 
 	*alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags);
 
-	return true;
-}
-
-/* Determine whether to spread dirty pages and what the first usable zone */
-static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac)
-{
 	/* Dirty zone balancing only done in the fast path */
 	ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
@@ -4842,6 +4847,8 @@ static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac)
 	 */
 	ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
 					ac->highest_zoneidx, ac->nodemask);
+
+	return true;
 }
 
 /*
@@ -4870,8 +4877,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
 	if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags))
 		return NULL;
 
-	finalise_ac(gfp_mask, &ac);
-
 	/*
 	 * Forbid the first pass from falling back to types that fragment
 	 * memory until all local zones are considered.
@@ -4947,6 +4952,9 @@ void __free_pages(struct page *page, unsigned int order)
 {
 	if (put_page_testzero(page))
 		free_the_page(page, order);
+	else if (!PageHead(page))
+		while (order-- > 0)
+			free_the_page(page + (1 << order), order);
 }
 EXPORT_SYMBOL(__free_pages);
 
@@ -5637,7 +5645,6 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 	int n, val;
 	int min_val = INT_MAX;
 	int best_node = NUMA_NO_NODE;
-	const struct cpumask *tmp = cpumask_of_node(0);
 
 	/* Use the local node if we haven't already */
 	if (!node_isset(node, *used_node_mask)) {
@@ -5658,8 +5665,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 		val += (n < node);
 
 		/* Give preference to headless and unused nodes */
-		tmp = cpumask_of_node(n);
-		if (!cpumask_empty(tmp))
+		if (!cpumask_empty(cpumask_of_node(n)))
 			val += PENALTY_FOR_NODE_WITH_CPUS;
 
 		/* Slight preference for less loaded node */
@@ -5955,7 +5961,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
 
 	if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
 		if (!r || *pfn >= memblock_region_memory_end_pfn(r)) {
-			for_each_memblock(memory, r) {
+			for_each_mem_region(r) {
 				if (*pfn < memblock_region_memory_end_pfn(r))
 					break;
 			}
@@ -5975,7 +5981,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * done. Non-atomic initialization, single-pass.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn, enum memmap_context context,
+		unsigned long start_pfn, enum meminit_context context,
 		struct vmem_altmap *altmap)
 {
 	unsigned long pfn, end_pfn = start_pfn + size;
@@ -6007,7 +6013,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		 * There can be holes in boot-time mem_map[]s handed to this
 		 * function.  They do not exist on hotplugged memory.
 		 */
-		if (context == MEMMAP_EARLY) {
+		if (context == MEMINIT_EARLY) {
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
 			if (defer_init(nid, pfn, end_pfn))
@@ -6016,7 +6022,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 
 		page = pfn_to_page(pfn);
 		__init_single_page(page, pfn, zone, nid);
-		if (context == MEMMAP_HOTPLUG)
+		if (context == MEMINIT_HOTPLUG)
 			__SetPageReserved(page);
 
 		/*
@@ -6099,7 +6105,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 		 * check here not to call set_pageblock_migratetype() against
 		 * pfn out of zone.
 		 *
-		 * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+		 * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
 		 * because this is done early in section_activate()
 		 */
 		if (!(pfn & (pageblock_nr_pages - 1))) {
@@ -6137,7 +6143,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
 			memmap_init_zone(size, nid, zone, start_pfn,
-					 MEMMAP_EARLY, NULL);
+					 MEMINIT_EARLY, NULL);
 		}
 	}
 }
@@ -6540,7 +6546,7 @@ static unsigned long __init zone_absent_pages_in_node(int nid,
 		unsigned long start_pfn, end_pfn;
 		struct memblock_region *r;
 
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			start_pfn = clamp(memblock_region_memory_base_pfn(r),
 					  zone_start_pfn, zone_end_pfn);
 			end_pfn = clamp(memblock_region_memory_end_pfn(r),
@@ -6984,8 +6990,7 @@ static void __init init_unavailable_mem(void)
 	 * Loop through unavailable ranges not covered by memblock.memory.
 	 */
 	pgcnt = 0;
-	for_each_mem_range(i, &memblock.memory, NULL,
-			NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range(i, &start, &end) {
 		if (next < start)
 			pgcnt += init_unavailable_range(PFN_DOWN(next),
 							PFN_UP(start));
@@ -7135,7 +7140,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	 * options.
 	 */
 	if (movable_node_is_enabled()) {
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			if (!memblock_is_hotpluggable(r))
 				continue;
 
@@ -7156,7 +7161,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	if (mirrored_kernelcore) {
 		bool mem_below_4gb_not_mirrored = false;
 
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			if (memblock_is_mirror(r))
 				continue;
 
@@ -7891,6 +7896,8 @@ int __meminit init_per_zone_wmark_min(void)
 	setup_min_slab_ratio();
 #endif
 
+	khugepaged_min_free_kbytes_update();
+
 	return 0;
 }
 postcore_initcall(init_per_zone_wmark_min)
@@ -8218,14 +8225,7 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 {
 	unsigned long iter = 0;
 	unsigned long pfn = page_to_pfn(page);
-
-	/*
-	 * TODO we could make this much more efficient by not checking every
-	 * page in the range if we know all of them are in MOVABLE_ZONE and
-	 * that the movable zone guarantees that pages are migratable but
-	 * the later is not the case right now unfortunatelly. E.g. movablecore
-	 * can still lead to having bootmem allocations in zone_movable.
-	 */
+	unsigned long offset = pfn % pageblock_nr_pages;
 
 	if (is_migrate_cma_page(page)) {
 		/*
@@ -8239,12 +8239,18 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 		return page;
 	}
 
-	for (; iter < pageblock_nr_pages; iter++) {
+	for (; iter < pageblock_nr_pages - offset; iter++) {
 		if (!pfn_valid_within(pfn + iter))
 			continue;
 
 		page = pfn_to_page(pfn + iter);
 
+		/*
+		 * Both, bootmem allocations and memory holes are marked
+		 * PG_reserved and are unmovable. We can even have unmovable
+		 * allocations inside ZONE_MOVABLE, for example when
+		 * specifying "movablecore".
+		 */
 		if (PageReserved(page))
 			return page;
 
@@ -8318,14 +8324,6 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 		 * it.  But now, memory offline itself doesn't call
 		 * shrink_node_slabs() and it still to be fixed.
 		 */
-		/*
-		 * If the page is not RAM, page_count()should be 0.
-		 * we don't need more check. This is an _used_ not-movable page.
-		 *
-		 * The problematic thing here is PG_reserved pages. PG_reserved
-		 * is set to both of a memory hole page and a _used_ kernel
-		 * page at boot.
-		 */
 		return page;
 	}
 	return NULL;