Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - the rest of MM

 - various misc things

 - procfs updates

 - lib/ updates

 - checkpatch updates

 - kdump/kexec updates

 - add kvmalloc helpers, use them

 - time helper updates for Y2038 issues. We're almost ready to remove
   current_fs_time() but that awaits a btrfs merge.

 - add tracepoints to DAX

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (114 commits)
  drivers/staging/ccree/ssi_hash.c: fix build with gcc-4.4.4
  selftests/vm: add a test for virtual address range mapping
  dax: add tracepoint to dax_insert_mapping()
  dax: add tracepoint to dax_writeback_one()
  dax: add tracepoints to dax_writeback_mapping_range()
  dax: add tracepoints to dax_load_hole()
  dax: add tracepoints to dax_pfn_mkwrite()
  dax: add tracepoints to dax_iomap_pte_fault()
  mtd: nand: nandsim: convert to memalloc_noreclaim_*()
  treewide: convert PF_MEMALLOC manipulations to new helpers
  mm: introduce memalloc_noreclaim_{save,restore}
  mm: prevent potential recursive reclaim due to clearing PF_MEMALLOC
  mm/huge_memory.c: deposit a pgtable for DAX PMD faults when required
  mm/huge_memory.c: use zap_deposited_table() more
  time: delete CURRENT_TIME_SEC and CURRENT_TIME
  gfs2: replace CURRENT_TIME with current_time
  apparmorfs: replace CURRENT_TIME with current_time()
  lustre: replace CURRENT_TIME macro
  fs: ubifs: replace CURRENT_TIME_SEC with current_time
  fs: ufs: use ktime_get_real_ts64() for birthtime
  ...

mm/compaction.c

@@ -89,11 +89,6 @@ static void map_pages(struct list_head *list)
 	list_splice(&tmp_list, list);
 }
 
-static inline bool migrate_async_suitable(int migratetype)
-{
-	return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
-}
-
 #ifdef CONFIG_COMPACTION
 
 int PageMovable(struct page *page)
@@ -988,6 +983,22 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 #endif /* CONFIG_COMPACTION || CONFIG_CMA */
 #ifdef CONFIG_COMPACTION
 
+static bool suitable_migration_source(struct compact_control *cc,
+							struct page *page)
+{
+	int block_mt;
+
+	if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction)
+		return true;
+
+	block_mt = get_pageblock_migratetype(page);
+
+	if (cc->migratetype == MIGRATE_MOVABLE)
+		return is_migrate_movable(block_mt);
+	else
+		return block_mt == cc->migratetype;
+}
+
 /* Returns true if the page is within a block suitable for migration to */
 static bool suitable_migration_target(struct compact_control *cc,
 							struct page *page)
@@ -1007,7 +1018,7 @@ static bool suitable_migration_target(struct compact_control *cc,
 		return true;
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
-	if (migrate_async_suitable(get_pageblock_migratetype(page)))
+	if (is_migrate_movable(get_pageblock_migratetype(page)))
 		return true;
 
 	/* Otherwise skip the block */
@@ -1242,8 +1253,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		 * Async compaction is optimistic to see if the minimum amount
 		 * of work satisfies the allocation.
 		 */
-		if (cc->mode == MIGRATE_ASYNC &&
-		    !migrate_async_suitable(get_pageblock_migratetype(page)))
+		if (!suitable_migration_source(cc, page))
 			continue;
 
 		/* Perform the isolation */
@@ -1276,11 +1286,11 @@ static inline bool is_via_compact_memory(int order)
 	return order == -1;
 }
 
-static enum compact_result __compact_finished(struct zone *zone, struct compact_control *cc,
-			    const int migratetype)
+static enum compact_result __compact_finished(struct zone *zone,
+						struct compact_control *cc)
 {
 	unsigned int order;
-	unsigned long watermark;
+	const int migratetype = cc->migratetype;
 
 	if (cc->contended || fatal_signal_pending(current))
 		return COMPACT_CONTENDED;
@@ -1308,12 +1318,16 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_
 	if (is_via_compact_memory(cc->order))
 		return COMPACT_CONTINUE;
 
-	/* Compaction run is not finished if the watermark is not met */
-	watermark = zone->watermark[cc->alloc_flags & ALLOC_WMARK_MASK];
-
-	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
-							cc->alloc_flags))
-		return COMPACT_CONTINUE;
+	if (cc->finishing_block) {
+		/*
+		 * We have finished the pageblock, but better check again that
+		 * we really succeeded.
+		 */
+		if (IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages))
+			cc->finishing_block = false;
+		else
+			return COMPACT_CONTINUE;
+	}
 
 	/* Direct compactor: Is a suitable page free? */
 	for (order = cc->order; order < MAX_ORDER; order++) {
@@ -1335,20 +1349,40 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_
 		 * other migratetype buddy lists.
 		 */
 		if (find_suitable_fallback(area, order, migratetype,
-						true, &can_steal) != -1)
-			return COMPACT_SUCCESS;
+						true, &can_steal) != -1) {
+
+			/* movable pages are OK in any pageblock */
+			if (migratetype == MIGRATE_MOVABLE)
+				return COMPACT_SUCCESS;
+
+			/*
+			 * We are stealing for a non-movable allocation. Make
+			 * sure we finish compacting the current pageblock
+			 * first so it is as free as possible and we won't
+			 * have to steal another one soon. This only applies
+			 * to sync compaction, as async compaction operates
+			 * on pageblocks of the same migratetype.
+			 */
+			if (cc->mode == MIGRATE_ASYNC ||
+					IS_ALIGNED(cc->migrate_pfn,
+							pageblock_nr_pages)) {
+				return COMPACT_SUCCESS;
+			}
+
+			cc->finishing_block = true;
+			return COMPACT_CONTINUE;
+		}
 	}
 
 	return COMPACT_NO_SUITABLE_PAGE;
 }
 
 static enum compact_result compact_finished(struct zone *zone,
-			struct compact_control *cc,
-			const int migratetype)
+			struct compact_control *cc)
 {
 	int ret;
 
-	ret = __compact_finished(zone, cc, migratetype);
+	ret = __compact_finished(zone, cc);
 	trace_mm_compaction_finished(zone, cc->order, ret);
 	if (ret == COMPACT_NO_SUITABLE_PAGE)
 		ret = COMPACT_CONTINUE;
@@ -1481,9 +1515,9 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 	enum compact_result ret;
 	unsigned long start_pfn = zone->zone_start_pfn;
 	unsigned long end_pfn = zone_end_pfn(zone);
-	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 
+	cc->migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
 							cc->classzone_idx);
 	/* Compaction is likely to fail */
@@ -1533,8 +1567,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 
 	migrate_prep_local();
 
-	while ((ret = compact_finished(zone, cc, migratetype)) ==
-						COMPACT_CONTINUE) {
+	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
 		int err;
 
 		switch (isolate_migratepages(zone, cc)) {

mm/filemap.c

@@ -2791,12 +2791,6 @@ ssize_t generic_perform_write(struct file *file,
 	ssize_t written = 0;
 	unsigned int flags = 0;
 
-	/*
-	 * Copies from kernel address space cannot fail (NFSD is a big user).
-	 */
-	if (!iter_is_iovec(i))
-		flags |= AOP_FLAG_UNINTERRUPTIBLE;
-
 	do {
 		struct page *page;
 		unsigned long offset;	/* Offset into pagecache page */

mm/frame_vector.c

@@ -200,10 +200,7 @@ struct frame_vector *frame_vector_create(unsigned int nr_frames)
 	 * Avoid higher order allocations, use vmalloc instead. It should
 	 * be rare anyway.
 	 */
-	if (size <= PAGE_SIZE)
-		vec = kmalloc(size, GFP_KERNEL);
-	else
-		vec = vmalloc(size);
+	vec = kvmalloc(size, GFP_KERNEL);
 	if (!vec)
 		return NULL;
 	vec->nr_allocated = nr_frames;

mm/huge_memory.c

@@ -715,7 +715,8 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 }
 
 static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write)
+		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write,
+		pgtable_t pgtable)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t entry;
@@ -729,6 +730,12 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 		entry = pmd_mkyoung(pmd_mkdirty(entry));
 		entry = maybe_pmd_mkwrite(entry, vma);
 	}
+
+	if (pgtable) {
+		pgtable_trans_huge_deposit(mm, pmd, pgtable);
+		atomic_long_inc(&mm->nr_ptes);
+	}
+
 	set_pmd_at(mm, addr, pmd, entry);
 	update_mmu_cache_pmd(vma, addr, pmd);
 	spin_unlock(ptl);
@@ -738,6 +745,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 			pmd_t *pmd, pfn_t pfn, bool write)
 {
 	pgprot_t pgprot = vma->vm_page_prot;
+	pgtable_t pgtable = NULL;
 	/*
 	 * If we had pmd_special, we could avoid all these restrictions,
 	 * but we need to be consistent with PTEs and architectures that
@@ -752,9 +760,15 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;
 
+	if (arch_needs_pgtable_deposit()) {
+		pgtable = pte_alloc_one(vma->vm_mm, addr);
+		if (!pgtable)
+			return VM_FAULT_OOM;
+	}
+
 	track_pfn_insert(vma, &pgprot, pfn);
 
-	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
+	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write, pgtable);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
@@ -1611,12 +1625,13 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			tlb->fullmm);
 	tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 	if (vma_is_dax(vma)) {
+		if (arch_needs_pgtable_deposit())
+			zap_deposited_table(tlb->mm, pmd);
 		spin_unlock(ptl);
 		if (is_huge_zero_pmd(orig_pmd))
 			tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
 	} else if (is_huge_zero_pmd(orig_pmd)) {
-		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
-		atomic_long_dec(&tlb->mm->nr_ptes);
+		zap_deposited_table(tlb->mm, pmd);
 		spin_unlock(ptl);
 		tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
 	} else {
@@ -1625,10 +1640,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
 		VM_BUG_ON_PAGE(!PageHead(page), page);
 		if (PageAnon(page)) {
-			pgtable_t pgtable;
-			pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
-			pte_free(tlb->mm, pgtable);
-			atomic_long_dec(&tlb->mm->nr_ptes);
+			zap_deposited_table(tlb->mm, pmd);
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 		} else {
 			if (arch_needs_pgtable_deposit())

mm/internal.h

@@ -183,6 +183,7 @@ extern int user_min_free_kbytes;
 struct compact_control {
 	struct list_head freepages;	/* List of free pages to migrate to */
 	struct list_head migratepages;	/* List of pages being migrated */
+	struct zone *zone;
 	unsigned long nr_freepages;	/* Number of isolated free pages */
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
 	unsigned long total_migrate_scanned;
@@ -190,17 +191,18 @@ struct compact_control {
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
+	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
+	int order;			/* order a direct compactor needs */
+	int migratetype;		/* migratetype of direct compactor */
+	const unsigned int alloc_flags;	/* alloc flags of a direct compactor */
+	const int classzone_idx;	/* zone index of a direct compactor */
 	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
 	bool ignore_block_suitable;	/* Scan blocks considered unsuitable */
 	bool direct_compaction;		/* False from kcompactd or /proc/... */
 	bool whole_zone;		/* Whole zone should/has been scanned */
-	int order;			/* order a direct compactor needs */
-	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
-	const unsigned int alloc_flags;	/* alloc flags of a direct compactor */
-	const int classzone_idx;	/* zone index of a direct compactor */
-	struct zone *zone;
 	bool contended;			/* Signal lock or sched contention */
+	bool finishing_block;		/* Finishing current pageblock */
 };
 
 unsigned long

mm/kasan/kasan.c

@@ -691,7 +691,7 @@ int kasan_module_alloc(void *addr, size_t size)
 
 	ret = __vmalloc_node_range(shadow_size, 1, shadow_start,
 			shadow_start + shadow_size,
-			GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+			GFP_KERNEL | __GFP_ZERO,
 			PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
 			__builtin_return_address(0));
 

mm/nommu.c

@@ -237,12 +237,16 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 }
 EXPORT_SYMBOL(__vmalloc);
 
+void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags)
+{
+	return __vmalloc(size, flags, PAGE_KERNEL);
+}
+
 void *vmalloc_user(unsigned long size)
 {
 	void *ret;
 
-	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
-			PAGE_KERNEL);
+	ret = __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
 	if (ret) {
 		struct vm_area_struct *vma;
 

mm/page_alloc.c

@@ -1832,9 +1832,9 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
  * Note that start_page and end_pages are not aligned on a pageblock
  * boundary. If alignment is required, use move_freepages_block()
  */
-int move_freepages(struct zone *zone,
+static int move_freepages(struct zone *zone,
 			  struct page *start_page, struct page *end_page,
-			  int migratetype)
+			  int migratetype, int *num_movable)
 {
 	struct page *page;
 	unsigned int order;
@@ -1851,6 +1851,9 @@ int move_freepages(struct zone *zone,
 	VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
 #endif
 
+	if (num_movable)
+		*num_movable = 0;
+
 	for (page = start_page; page <= end_page;) {
 		if (!pfn_valid_within(page_to_pfn(page))) {
 			page++;
@@ -1861,6 +1864,15 @@ int move_freepages(struct zone *zone,
 		VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
 
 		if (!PageBuddy(page)) {
+			/*
+			 * We assume that pages that could be isolated for
+			 * migration are movable. But we don't actually try
+			 * isolating, as that would be expensive.
+			 */
+			if (num_movable &&
+					(PageLRU(page) || __PageMovable(page)))
+				(*num_movable)++;
+
 			page++;
 			continue;
 		}
@@ -1876,7 +1888,7 @@ int move_freepages(struct zone *zone,
 }
 
 int move_freepages_block(struct zone *zone, struct page *page,
-				int migratetype)
+				int migratetype, int *num_movable)
 {
 	unsigned long start_pfn, end_pfn;
 	struct page *start_page, *end_page;
@@ -1893,7 +1905,8 @@ int move_freepages_block(struct zone *zone, struct page *page,
 	if (!zone_spans_pfn(zone, end_pfn))
 		return 0;
 
-	return move_freepages(zone, start_page, end_page, migratetype);
+	return move_freepages(zone, start_page, end_page, migratetype,
+								num_movable);
 }
 
 static void change_pageblock_range(struct page *pageblock_page,
@@ -1943,28 +1956,79 @@ static bool can_steal_fallback(unsigned int order, int start_mt)
 /*
  * This function implements actual steal behaviour. If order is large enough,
  * we can steal whole pageblock. If not, we first move freepages in this
- * pageblock and check whether half of pages are moved or not. If half of
- * pages are moved, we can change migratetype of pageblock and permanently
- * use it's pages as requested migratetype in the future.
+ * pageblock to our migratetype and determine how many already-allocated pages
+ * are there in the pageblock with a compatible migratetype. If at least half
+ * of pages are free or compatible, we can change migratetype of the pageblock
+ * itself, so pages freed in the future will be put on the correct free list.
  */
 static void steal_suitable_fallback(struct zone *zone, struct page *page,
-							  int start_type)
+					int start_type, bool whole_block)
 {
 	unsigned int current_order = page_order(page);
-	int pages;
+	struct free_area *area;
+	int free_pages, movable_pages, alike_pages;
+	int old_block_type;
+
+	old_block_type = get_pageblock_migratetype(page);
+
+	/*
+	 * This can happen due to races and we want to prevent broken
+	 * highatomic accounting.
+	 */
+	if (is_migrate_highatomic(old_block_type))
+		goto single_page;
 
 	/* Take ownership for orders >= pageblock_order */
 	if (current_order >= pageblock_order) {
 		change_pageblock_range(page, current_order, start_type);
-		return;
+		goto single_page;
 	}
 
-	pages = move_freepages_block(zone, page, start_type);
+	/* We are not allowed to try stealing from the whole block */
+	if (!whole_block)
+		goto single_page;
 
-	/* Claim the whole block if over half of it is free */
-	if (pages >= (1 << (pageblock_order-1)) ||
+	free_pages = move_freepages_block(zone, page, start_type,
+						&movable_pages);
+	/*
+	 * Determine how many pages are compatible with our allocation.
+	 * For movable allocation, it's the number of movable pages which
+	 * we just obtained. For other types it's a bit more tricky.
+	 */
+	if (start_type == MIGRATE_MOVABLE) {
+		alike_pages = movable_pages;
+	} else {
+		/*
+		 * If we are falling back a RECLAIMABLE or UNMOVABLE allocation
+		 * to MOVABLE pageblock, consider all non-movable pages as
+		 * compatible. If it's UNMOVABLE falling back to RECLAIMABLE or
+		 * vice versa, be conservative since we can't distinguish the
+		 * exact migratetype of non-movable pages.
+		 */
+		if (old_block_type == MIGRATE_MOVABLE)
+			alike_pages = pageblock_nr_pages
+						- (free_pages + movable_pages);
+		else
+			alike_pages = 0;
+	}
+
+	/* moving whole block can fail due to zone boundary conditions */
+	if (!free_pages)
+		goto single_page;
+
+	/*
+	 * If a sufficient number of pages in the block are either free or of
+	 * comparable migratability as our allocation, claim the whole block.
+	 */
+	if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
 			page_group_by_mobility_disabled)
 		set_pageblock_migratetype(page, start_type);
+
+	return;
+
+single_page:
+	area = &zone->free_area[current_order];
+	list_move(&page->lru, &area->free_list[start_type]);
 }
 
 /*
@@ -2034,7 +2098,7 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone,
 	    && !is_migrate_cma(mt)) {
 		zone->nr_reserved_highatomic += pageblock_nr_pages;
 		set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
-		move_freepages_block(zone, page, MIGRATE_HIGHATOMIC);
+		move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL);
 	}
 
 out_unlock:
@@ -2111,7 +2175,8 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 			 * may increase.
 			 */
 			set_pageblock_migratetype(page, ac->migratetype);
-			ret = move_freepages_block(zone, page, ac->migratetype);
+			ret = move_freepages_block(zone, page, ac->migratetype,
+									NULL);
 			if (ret) {
 				spin_unlock_irqrestore(&zone->lock, flags);
 				return ret;
@@ -2123,8 +2188,13 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 	return false;
 }
 
-/* Remove an element from the buddy allocator from the fallback list */
-static inline struct page *
+/*
+ * Try finding a free buddy page on the fallback list and put it on the free
+ * list of requested migratetype, possibly along with other pages from the same
+ * block, depending on fragmentation avoidance heuristics. Returns true if
+ * fallback was found so that __rmqueue_smallest() can grab it.
+ */
+static inline bool
 __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 {
 	struct free_area *area;
@@ -2145,32 +2215,17 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 
 		page = list_first_entry(&area->free_list[fallback_mt],
 						struct page, lru);
-		if (can_steal && !is_migrate_highatomic_page(page))
-			steal_suitable_fallback(zone, page, start_migratetype);
 
-		/* Remove the page from the freelists */
-		area->nr_free--;
-		list_del(&page->lru);
-		rmv_page_order(page);
-
-		expand(zone, page, order, current_order, area,
-					start_migratetype);
-		/*
-		 * The pcppage_migratetype may differ from pageblock's
-		 * migratetype depending on the decisions in
-		 * find_suitable_fallback(). This is OK as long as it does not
-		 * differ for MIGRATE_CMA pageblocks. Those can be used as
-		 * fallback only via special __rmqueue_cma_fallback() function
-		 */
-		set_pcppage_migratetype(page, start_migratetype);
+		steal_suitable_fallback(zone, page, start_migratetype,
+								can_steal);
 
 		trace_mm_page_alloc_extfrag(page, order, current_order,
 			start_migratetype, fallback_mt);
 
-		return page;
+		return true;
 	}
 
-	return NULL;
+	return false;
 }
 
 /*
@@ -2182,13 +2237,14 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order,
 {
 	struct page *page;
 
+retry:
 	page = __rmqueue_smallest(zone, order, migratetype);
 	if (unlikely(!page)) {
 		if (migratetype == MIGRATE_MOVABLE)
 			page = __rmqueue_cma_fallback(zone, order);
 
-		if (!page)
-			page = __rmqueue_fallback(zone, order, migratetype);
+		if (!page && __rmqueue_fallback(zone, order, migratetype))
+			goto retry;
 	}
 
 	trace_mm_page_alloc_zone_locked(page, order, migratetype);
@@ -3227,14 +3283,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		enum compact_priority prio, enum compact_result *compact_result)
 {
 	struct page *page;
+	unsigned int noreclaim_flag;
 
 	if (!order)
 		return NULL;
 
-	current->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
 									prio);
-	current->flags &= ~PF_MEMALLOC;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	if (*compact_result <= COMPACT_INACTIVE)
 		return NULL;
@@ -3381,12 +3438,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 {
 	struct reclaim_state reclaim_state;
 	int progress;
+	unsigned int noreclaim_flag;
 
 	cond_resched();
 
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
-	current->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
@@ -3396,7 +3454,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 
 	current->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
-	current->flags &= ~PF_MEMALLOC;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	cond_resched();
 
@@ -3609,6 +3667,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 						struct alloc_context *ac)
 {
 	bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
+	const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
 	struct page *page = NULL;
 	unsigned int alloc_flags;
 	unsigned long did_some_progress;
@@ -3676,12 +3735,17 @@ retry_cpuset:
 
 	/*
 	 * For costly allocations, try direct compaction first, as it's likely
-	 * that we have enough base pages and don't need to reclaim. Don't try
-	 * that for allocations that are allowed to ignore watermarks, as the
-	 * ALLOC_NO_WATERMARKS attempt didn't yet happen.
+	 * that we have enough base pages and don't need to reclaim. For non-
+	 * movable high-order allocations, do that as well, as compaction will
+	 * try prevent permanent fragmentation by migrating from blocks of the
+	 * same migratetype.
+	 * Don't try this for allocations that are allowed to ignore
+	 * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
 	 */
-	if (can_direct_reclaim && order > PAGE_ALLOC_COSTLY_ORDER &&
-		!gfp_pfmemalloc_allowed(gfp_mask)) {
+	if (can_direct_reclaim &&
+			(costly_order ||
+			   (order > 0 && ac->migratetype != MIGRATE_MOVABLE))
+			&& !gfp_pfmemalloc_allowed(gfp_mask)) {
 		page = __alloc_pages_direct_compact(gfp_mask, order,
 						alloc_flags, ac,
 						INIT_COMPACT_PRIORITY,
@@ -3693,7 +3757,7 @@ retry_cpuset:
 		 * Checks for costly allocations with __GFP_NORETRY, which
 		 * includes THP page fault allocations
 		 */
-		if (gfp_mask & __GFP_NORETRY) {
+		if (costly_order && (gfp_mask & __GFP_NORETRY)) {
 			/*
 			 * If compaction is deferred for high-order allocations,
 			 * it is because sync compaction recently failed. If
@@ -3774,7 +3838,7 @@ retry:
 	 * Do not retry costly high order allocations unless they are
 	 * __GFP_REPEAT
 	 */
-	if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT))
+	if (costly_order && !(gfp_mask & __GFP_REPEAT))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,

mm/page_isolation.c

@@ -66,7 +66,8 @@ out:
 
 		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
 		zone->nr_isolate_pageblock++;
-		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
+		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE,
+									NULL);
 
 		__mod_zone_freepage_state(zone, -nr_pages, migratetype);
 	}
@@ -120,7 +121,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 	 * pageblock scanning for freepage moving.
 	 */
 	if (!isolated_page) {
-		nr_pages = move_freepages_block(zone, page, migratetype);
+		nr_pages = move_freepages_block(zone, page, migratetype, NULL);
 		__mod_zone_freepage_state(zone, nr_pages, migratetype);
 	}
 	set_pageblock_migratetype(page, migratetype);

mm/swap_slots.c

@@ -31,6 +31,7 @@
 #include <linux/cpumask.h>
 #include <linux/vmalloc.h>
 #include <linux/mutex.h>
+#include <linux/mm.h>
 
 #ifdef CONFIG_SWAP
 
@@ -119,16 +120,18 @@ static int alloc_swap_slot_cache(unsigned int cpu)
 
 	/*
 	 * Do allocation outside swap_slots_cache_mutex
-	 * as vzalloc could trigger reclaim and get_swap_page,
+	 * as kvzalloc could trigger reclaim and get_swap_page,
 	 * which can lock swap_slots_cache_mutex.
 	 */
-	slots = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE);
+	slots = kvzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE,
+			 GFP_KERNEL);
 	if (!slots)
 		return -ENOMEM;
 
-	slots_ret = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE);
+	slots_ret = kvzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE,
+			     GFP_KERNEL);
 	if (!slots_ret) {
-		vfree(slots);
+		kvfree(slots);
 		return -ENOMEM;
 	}
 
@@ -152,9 +155,9 @@ static int alloc_swap_slot_cache(unsigned int cpu)
 out:
 	mutex_unlock(&swap_slots_cache_mutex);
 	if (slots)
-		vfree(slots);
+		kvfree(slots);
 	if (slots_ret)
-		vfree(slots_ret);
+		kvfree(slots_ret);
 	return 0;
 }
 
@@ -171,7 +174,7 @@ static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type,
 		cache->cur = 0;
 		cache->nr = 0;
 		if (free_slots && cache->slots) {
-			vfree(cache->slots);
+			kvfree(cache->slots);
 			cache->slots = NULL;
 		}
 		mutex_unlock(&cache->alloc_lock);
@@ -186,7 +189,7 @@ static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type,
 		}
 		spin_unlock_irq(&cache->free_lock);
 		if (slots)
-			vfree(slots);
+			kvfree(slots);
 	}
 }
 

mm/swap_state.c

@@ -523,7 +523,7 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages)
 	unsigned int i, nr;
 
 	nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
-	spaces = vzalloc(sizeof(struct address_space) * nr);
+	spaces = kvzalloc(sizeof(struct address_space) * nr, GFP_KERNEL);
 	if (!spaces)
 		return -ENOMEM;
 	for (i = 0; i < nr; i++) {

mm/swapfile.c

@@ -2270,8 +2270,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	free_percpu(p->percpu_cluster);
 	p->percpu_cluster = NULL;
 	vfree(swap_map);
-	vfree(cluster_info);
-	vfree(frontswap_map);
+	kvfree(cluster_info);
+	kvfree(frontswap_map);
 	/* Destroy swap account information */
 	swap_cgroup_swapoff(p->type);
 	exit_swap_address_space(p->type);
@@ -2794,7 +2794,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		p->cluster_next = 1 + (prandom_u32() % p->highest_bit);
 		nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
 
-		cluster_info = vzalloc(nr_cluster * sizeof(*cluster_info));
+		cluster_info = kvzalloc(nr_cluster * sizeof(*cluster_info),
+					GFP_KERNEL);
 		if (!cluster_info) {
 			error = -ENOMEM;
 			goto bad_swap;
@@ -2827,7 +2828,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	}
 	/* frontswap enabled? set up bit-per-page map for frontswap */
 	if (IS_ENABLED(CONFIG_FRONTSWAP))
-		frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long));
+		frontswap_map = kvzalloc(BITS_TO_LONGS(maxpages) * sizeof(long),
+					 GFP_KERNEL);
 
 	if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
 		/*

mm/util.c

@@ -329,6 +329,63 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_mmap);
 
+/**
+ * kvmalloc_node - attempt to allocate physically contiguous memory, but upon
+ * failure, fall back to non-contiguous (vmalloc) allocation.
+ * @size: size of the request.
+ * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL.
+ * @node: numa node to allocate from
+ *
+ * Uses kmalloc to get the memory but if the allocation fails then falls back
+ * to the vmalloc allocator. Use kvfree for freeing the memory.
+ *
+ * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT
+ * is supported only for large (>32kB) allocations, and it should be used only if
+ * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks.
+ *
+ * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people.
+ */
+void *kvmalloc_node(size_t size, gfp_t flags, int node)
+{
+	gfp_t kmalloc_flags = flags;
+	void *ret;
+
+	/*
+	 * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables)
+	 * so the given set of flags has to be compatible.
+	 */
+	WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL);
+
+	/*
+	 * Make sure that larger requests are not too disruptive - no OOM
+	 * killer and no allocation failure warnings as we have a fallback
+	 */
+	if (size > PAGE_SIZE) {
+		kmalloc_flags |= __GFP_NOWARN;
+
+		/*
+		 * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly
+		 * requests because there is no other way to tell the allocator
+		 * that we want to fail rather than retry endlessly.
+		 */
+		if (!(kmalloc_flags & __GFP_REPEAT) ||
+				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+			kmalloc_flags |= __GFP_NORETRY;
+	}
+
+	ret = kmalloc_node(size, kmalloc_flags, node);
+
+	/*
+	 * It doesn't really make sense to fallback to vmalloc for sub page
+	 * requests
+	 */
+	if (ret || size <= PAGE_SIZE)
+		return ret;
+
+	return __vmalloc_node_flags(size, node, flags);
+}
+EXPORT_SYMBOL(kvmalloc_node);
+
 void kvfree(const void *addr)
 {
 	if (is_vmalloc_addr(addr))

mm/vmalloc.c

@@ -1649,16 +1649,13 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
-static void *__vmalloc_node(unsigned long size, unsigned long align,
-			    gfp_t gfp_mask, pgprot_t prot,
-			    int node, const void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node)
 {
 	struct page **pages;
 	unsigned int nr_pages, array_size, i;
 	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
-	const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
+	const gfp_t alloc_mask = gfp_mask | __GFP_HIGHMEM | __GFP_NOWARN;
 
 	nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
 	array_size = (nr_pages * sizeof(struct page *));
@@ -1786,8 +1783,15 @@ fail:
  *	Allocate enough pages to cover @size from the page level
  *	allocator with @gfp_mask flags.  Map them into contiguous
  *	kernel virtual space, using a pagetable protection of @prot.
+ *
+ *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT
+ *	and __GFP_NOFAIL are not supported
+ *
+ *	Any use of gfp flags outside of GFP_KERNEL should be consulted
+ *	with mm people.
+ *
  */
-static void *__vmalloc_node(unsigned long size, unsigned long align,
+void *__vmalloc_node(unsigned long size, unsigned long align,
 			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, const void *caller)
 {
@@ -1802,13 +1806,6 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 }
 EXPORT_SYMBOL(__vmalloc);
 
-static inline void *__vmalloc_node_flags(unsigned long size,
-					int node, gfp_t flags)
-{
-	return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
-					node, __builtin_return_address(0));
-}
-
 /**
  *	vmalloc  -  allocate virtually contiguous memory
  *	@size:		allocation size
@@ -1821,7 +1818,7 @@ static inline void *__vmalloc_node_flags(unsigned long size,
 void *vmalloc(unsigned long size)
 {
 	return __vmalloc_node_flags(size, NUMA_NO_NODE,
-				    GFP_KERNEL | __GFP_HIGHMEM);
+				    GFP_KERNEL);
 }
 EXPORT_SYMBOL(vmalloc);
 
@@ -1838,7 +1835,7 @@ EXPORT_SYMBOL(vmalloc);
 void *vzalloc(unsigned long size)
 {
 	return __vmalloc_node_flags(size, NUMA_NO_NODE,
-				GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+				GFP_KERNEL | __GFP_ZERO);
 }
 EXPORT_SYMBOL(vzalloc);
 
@@ -1855,7 +1852,7 @@ void *vmalloc_user(unsigned long size)
 	void *ret;
 
 	ret = __vmalloc_node(size, SHMLBA,
-			     GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+			     GFP_KERNEL | __GFP_ZERO,
 			     PAGE_KERNEL, NUMA_NO_NODE,
 			     __builtin_return_address(0));
 	if (ret) {
@@ -1879,7 +1876,7 @@ EXPORT_SYMBOL(vmalloc_user);
  */
 void *vmalloc_node(unsigned long size, int node)
 {
-	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+	return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL,
 					node, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc_node);
@@ -1899,7 +1896,7 @@ EXPORT_SYMBOL(vmalloc_node);
 void *vzalloc_node(unsigned long size, int node)
 {
 	return __vmalloc_node_flags(size, node,
-			 GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+			 GFP_KERNEL | __GFP_ZERO);
 }
 EXPORT_SYMBOL(vzalloc_node);
 
@@ -1921,7 +1918,7 @@ EXPORT_SYMBOL(vzalloc_node);
 
 void *vmalloc_exec(unsigned long size)
 {
-	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
+	return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC,
 			      NUMA_NO_NODE, __builtin_return_address(0));
 }
 

mm/vmscan.c

@@ -3036,6 +3036,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
 	int nid;
+	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
@@ -3062,9 +3063,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.gfp_mask,
 					    sc.reclaim_idx);
 
-	current->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
-	current->flags &= ~PF_MEMALLOC;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -3589,8 +3590,9 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
 	struct task_struct *p = current;
 	unsigned long nr_reclaimed;
+	unsigned int noreclaim_flag;
 
-	p->flags |= PF_MEMALLOC;
+	noreclaim_flag = memalloc_noreclaim_save();
 	lockdep_set_current_reclaim_state(sc.gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
@@ -3599,7 +3601,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 
 	p->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
-	p->flags &= ~PF_MEMALLOC;
+	memalloc_noreclaim_restore(noreclaim_flag);
 
 	return nr_reclaimed;
 }
@@ -3764,6 +3766,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
 	int classzone_idx = gfp_zone(gfp_mask);
+	unsigned int noreclaim_flag;
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (gfp_mask = current_gfp_context(gfp_mask)),
@@ -3781,7 +3784,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	 * and we also need to be able to write out pages for RECLAIM_WRITE
 	 * and RECLAIM_UNMAP.
 	 */
-	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
+	noreclaim_flag = memalloc_noreclaim_save();
+	p->flags |= PF_SWAPWRITE;
 	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
@@ -3797,7 +3801,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	}
 
 	p->reclaim_state = NULL;
-	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
+	current->flags &= ~PF_SWAPWRITE;
+	memalloc_noreclaim_restore(noreclaim_flag);
 	lockdep_clear_current_reclaim_state();
 	return sc.nr_reclaimed >= nr_pages;
 }