Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Daniel Verkamp has contributed a memfd series ("mm/memfd: add
   F_SEAL_EXEC") which permits the setting of the memfd execute bit at
   memfd creation time, with the option of sealing the state of the X
   bit.

 - Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset()
   thread-safe for pmd unshare") which addresses a rare race condition
   related to PMD unsharing.

 - Several folioification patch serieses from Matthew Wilcox, Vishal
   Moola, Sidhartha Kumar and Lorenzo Stoakes

 - Johannes Weiner has a series ("mm: push down lock_page_memcg()")
   which does perform some memcg maintenance and cleanup work.

 - SeongJae Park has added DAMOS filtering to DAMON, with the series
   "mm/damon/core: implement damos filter".

   These filters provide users with finer-grained control over DAMOS's
   actions. SeongJae has also done some DAMON cleanup work.

 - Kairui Song adds a series ("Clean up and fixes for swap").

 - Vernon Yang contributed the series "Clean up and refinement for maple
   tree".

 - Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It
   adds to MGLRU an LRU of memcgs, to improve the scalability of global
   reclaim.

 - David Hildenbrand has added some userfaultfd cleanup work in the
   series "mm: uffd-wp + change_protection() cleanups".

 - Christoph Hellwig has removed the generic_writepages() library
   function in the series "remove generic_writepages".

 - Baolin Wang has performed some maintenance on the compaction code in
   his series "Some small improvements for compaction".

 - Sidhartha Kumar is doing some maintenance work on struct page in his
   series "Get rid of tail page fields".

 - David Hildenbrand contributed some cleanup, bugfixing and
   generalization of pte management and of pte debugging in his series
   "mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with
   swap PTEs".

 - Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation
   flag in the series "Discard __GFP_ATOMIC".

 - Sergey Senozhatsky has improved zsmalloc's memory utilization with
   his series "zsmalloc: make zspage chain size configurable".

 - Joey Gouly has added prctl() support for prohibiting the creation of
   writeable+executable mappings.

   The previous BPF-based approach had shortcomings. See "mm: In-kernel
   support for memory-deny-write-execute (MDWE)".

 - Waiman Long did some kmemleak cleanup and bugfixing in the series
   "mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF".

 - T.J. Alumbaugh has contributed some MGLRU cleanup work in his series
   "mm: multi-gen LRU: improve".

 - Jiaqi Yan has provided some enhancements to our memory error
   statistics reporting, mainly by presenting the statistics on a
   per-node basis. See the series "Introduce per NUMA node memory error
   statistics".

 - Mel Gorman has a second and hopefully final shot at fixing a CPU-hog
   regression in compaction via his series "Fix excessive CPU usage
   during compaction".

 - Christoph Hellwig does some vmalloc maintenance work in the series
   "cleanup vfree and vunmap".

 - Christoph Hellwig has removed block_device_operations.rw_page() in
   ths series "remove ->rw_page".

 - We get some maple_tree improvements and cleanups in Liam Howlett's
   series "VMA tree type safety and remove __vma_adjust()".

 - Suren Baghdasaryan has done some work on the maintainability of our
   vm_flags handling in the series "introduce vm_flags modifier
   functions".

 - Some pagemap cleanup and generalization work in Mike Rapoport's
   series "mm, arch: add generic implementation of pfn_valid() for
   FLATMEM" and "fixups for generic implementation of pfn_valid()"

 - Baoquan He has done some work to make /proc/vmallocinfo and
   /proc/kcore better represent the real state of things in his series
   "mm/vmalloc.c: allow vread() to read out vm_map_ram areas".

 - Jason Gunthorpe rationalized the GUP system's interface to the rest
   of the kernel in the series "Simplify the external interface for
   GUP".

 - SeongJae Park wishes to migrate people from DAMON's debugfs interface
   over to its sysfs interface. To support this, we'll temporarily be
   printing warnings when people use the debugfs interface. See the
   series "mm/damon: deprecate DAMON debugfs interface".

 - Andrey Konovalov provided the accurately named "lib/stackdepot: fixes
   and clean-ups" series.

 - Huang Ying has provided a dramatic reduction in migration's TLB flush
   IPI rates with the series "migrate_pages(): batch TLB flushing".

 - Arnd Bergmann has some objtool fixups in "objtool warning fixes".

* tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (505 commits)
  include/linux/migrate.h: remove unneeded externs
  mm/memory_hotplug: cleanup return value handing in do_migrate_range()
  mm/uffd: fix comment in handling pte markers
  mm: change to return bool for isolate_movable_page()
  mm: hugetlb: change to return bool for isolate_hugetlb()
  mm: change to return bool for isolate_lru_page()
  mm: change to return bool for folio_isolate_lru()
  objtool: add UACCESS exceptions for __tsan_volatile_read/write
  kmsan: disable ftrace in kmsan core code
  kasan: mark addr_has_metadata __always_inline
  mm: memcontrol: rename memcg_kmem_enabled()
  sh: initialize max_mapnr
  m68k/nommu: add missing definition of ARCH_PFN_OFFSET
  mm: percpu: fix incorrect size in pcpu_obj_full_size()
  maple_tree: reduce stack usage with gcc-9 and earlier
  mm: page_alloc: call panic() when memoryless node allocation fails
  mm: multi-gen LRU: avoid futile retries
  migrate_pages: move THP/hugetlb migration support check to simplify code
  migrate_pages: batch flushing TLB
  migrate_pages: share more code between _unmap and _move
  ...

1 files changed, 138 insertions, 95 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3bb3484563ed..ac1fc986af44 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -430,6 +430,8 @@ EXPORT_SYMBOL(nr_online_nodes);
 
 int page_group_by_mobility_disabled __read_mostly;
 
+bool deferred_struct_pages __meminitdata;
+
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 /*
  * During boot we initialize deferred pages on-demand, as needed, but once
@@ -443,15 +445,15 @@ static inline bool deferred_pages_enabled(void)
 	return static_branch_unlikely(&deferred_pages);
 }
 
-/* Returns true if the struct page for the pfn is uninitialised */
-static inline bool __meminit early_page_uninitialised(unsigned long pfn)
+/* Returns true if the struct page for the pfn is initialised */
+static inline bool __meminit early_page_initialised(unsigned long pfn)
 {
 	int nid = early_pfn_to_nid(pfn);
 
 	if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
-		return true;
+		return false;
 
-	return false;
+	return true;
 }
 
 /*
@@ -498,9 +500,9 @@ static inline bool deferred_pages_enabled(void)
 	return false;
 }
 
-static inline bool early_page_uninitialised(unsigned long pfn)
+static inline bool early_page_initialised(unsigned long pfn)
 {
-	return false;
+	return true;
 }
 
 static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
@@ -775,11 +777,13 @@ void free_compound_page(struct page *page)
 
 static void prep_compound_head(struct page *page, unsigned int order)
 {
+	struct folio *folio = (struct folio *)page;
+
 	set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
 	set_compound_order(page, order);
-	atomic_set(compound_mapcount_ptr(page), -1);
-	atomic_set(subpages_mapcount_ptr(page), 0);
-	atomic_set(compound_pincount_ptr(page), 0);
+	atomic_set(&folio->_entire_mapcount, -1);
+	atomic_set(&folio->_nr_pages_mapped, 0);
+	atomic_set(&folio->_pincount, 0);
 }
 
 static void prep_compound_tail(struct page *head, int tail_idx)
@@ -805,7 +809,7 @@ void prep_compound_page(struct page *page, unsigned int order)
 
 void destroy_large_folio(struct folio *folio)
 {
-	enum compound_dtor_id dtor = folio_page(folio, 1)->compound_dtor;
+	enum compound_dtor_id dtor = folio->_folio_dtor;
 
 	VM_BUG_ON_FOLIO(dtor >= NR_COMPOUND_DTORS, folio);
 	compound_page_dtors[dtor](&folio->page);
@@ -1291,6 +1295,7 @@ static inline bool free_page_is_bad(struct page *page)
 
 static int free_tail_pages_check(struct page *head_page, struct page *page)
 {
+	struct folio *folio = (struct folio *)head_page;
 	int ret = 1;
 
 	/*
@@ -1306,16 +1311,16 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 	switch (page - head_page) {
 	case 1:
 		/* the first tail page: these may be in place of ->mapping */
-		if (unlikely(head_compound_mapcount(head_page))) {
-			bad_page(page, "nonzero compound_mapcount");
+		if (unlikely(folio_entire_mapcount(folio))) {
+			bad_page(page, "nonzero entire_mapcount");
 			goto out;
 		}
-		if (unlikely(atomic_read(subpages_mapcount_ptr(head_page)))) {
-			bad_page(page, "nonzero subpages_mapcount");
+		if (unlikely(atomic_read(&folio->_nr_pages_mapped))) {
+			bad_page(page, "nonzero nr_pages_mapped");
 			goto out;
 		}
-		if (unlikely(head_compound_pincount(head_page))) {
-			bad_page(page, "nonzero compound_pincount");
+		if (unlikely(atomic_read(&folio->_pincount))) {
+			bad_page(page, "nonzero pincount");
 			goto out;
 		}
 		break;
@@ -1356,6 +1361,8 @@ out:
  *    see the comment next to it.
  * 3. Skipping poisoning is requested via __GFP_SKIP_KASAN_POISON,
  *    see the comment next to it.
+ * 4. The allocation is excluded from being checked due to sampling,
+ *    see the call to kasan_unpoison_pages.
  *
  * Poisoning pages during deferred memory init will greatly lengthen the
  * process and cause problem in large memory systems as the deferred pages
@@ -1403,7 +1410,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 		 * Do not let hwpoison pages hit pcplists/buddy
 		 * Untie memcg state and reset page's owner
 		 */
-		if (memcg_kmem_enabled() && PageMemcgKmem(page))
+		if (memcg_kmem_online() && PageMemcgKmem(page))
 			__memcg_kmem_uncharge_page(page, order);
 		reset_page_owner(page, order);
 		page_table_check_free(page, order);
@@ -1434,7 +1441,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	if (PageMappingFlags(page))
 		page->mapping = NULL;
-	if (memcg_kmem_enabled() && PageMemcgKmem(page))
+	if (memcg_kmem_online() && PageMemcgKmem(page))
 		__memcg_kmem_uncharge_page(page, order);
 	if (check_free && free_page_is_bad(page))
 		bad++;
@@ -1641,7 +1648,7 @@ static void __meminit init_reserved_page(unsigned long pfn)
 	pg_data_t *pgdat;
 	int nid, zid;
 
-	if (!early_page_uninitialised(pfn))
+	if (early_page_initialised(pfn))
 		return;
 
 	nid = early_pfn_to_nid(pfn);
@@ -1804,7 +1811,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
 void __init memblock_free_pages(struct page *page, unsigned long pfn,
 							unsigned int order)
 {
-	if (early_page_uninitialised(pfn))
+	if (!early_page_initialised(pfn))
 		return;
 	if (!kmsan_memblock_free_pages(page, order)) {
 		/* KMSAN will take care of these pages. */
@@ -2468,7 +2475,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 {
 	bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) &&
 			!should_skip_init(gfp_flags);
-	bool init_tags = init && (gfp_flags & __GFP_ZEROTAGS);
+	bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS);
+	bool reset_tags = true;
 	int i;
 
 	set_page_private(page, 0);
@@ -2491,30 +2499,43 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	 */
 
 	/*
-	 * If memory tags should be zeroed (which happens only when memory
-	 * should be initialized as well).
+	 * If memory tags should be zeroed
+	 * (which happens only when memory should be initialized as well).
 	 */
-	if (init_tags) {
-		/* Initialize both memory and tags. */
+	if (zero_tags) {
+		/* Initialize both memory and memory tags. */
 		for (i = 0; i != 1 << order; ++i)
 			tag_clear_highpage(page + i);
 
-		/* Note that memory is already initialized by the loop above. */
+		/* Take note that memory was initialized by the loop above. */
 		init = false;
 	}
 	if (!should_skip_kasan_unpoison(gfp_flags)) {
-		/* Unpoison shadow memory or set memory tags. */
-		kasan_unpoison_pages(page, order, init);
-
-		/* Note that memory is already initialized by KASAN. */
-		if (kasan_has_integrated_init())
-			init = false;
-	} else {
-		/* Ensure page_address() dereferencing does not fault. */
+		/* Try unpoisoning (or setting tags) and initializing memory. */
+		if (kasan_unpoison_pages(page, order, init)) {
+			/* Take note that memory was initialized by KASAN. */
+			if (kasan_has_integrated_init())
+				init = false;
+			/* Take note that memory tags were set by KASAN. */
+			reset_tags = false;
+		} else {
+			/*
+			 * KASAN decided to exclude this allocation from being
+			 * (un)poisoned due to sampling. Make KASAN skip
+			 * poisoning when the allocation is freed.
+			 */
+			SetPageSkipKASanPoison(page);
+		}
+	}
+	/*
+	 * If memory tags have not been set by KASAN, reset the page tags to
+	 * ensure page_address() dereferencing does not fault.
+	 */
+	if (reset_tags) {
 		for (i = 0; i != 1 << order; ++i)
 			page_kasan_tag_reset(page + i);
 	}
-	/* If memory is still not initialized, do it now. */
+	/* If memory is still not initialized, initialize it now. */
 	if (init)
 		kernel_init_pages(page, 1 << order);
 	/* Propagate __GFP_SKIP_KASAN_POISON to page flags. */
@@ -2582,10 +2603,10 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
  *
  * The other migratetypes do not have fallbacks.
  */
-static int fallbacks[MIGRATE_TYPES][3] = {
-	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_TYPES },
-	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
-	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_TYPES },
+static int fallbacks[MIGRATE_TYPES][MIGRATE_PCPTYPES - 1] = {
+	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE   },
+	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE },
+	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE   },
 };
 
 #ifdef CONFIG_CMA
@@ -2844,11 +2865,8 @@ int find_suitable_fallback(struct free_area *area, unsigned int order,
 		return -1;
 
 	*can_steal = false;
-	for (i = 0;; i++) {
+	for (i = 0; i < MIGRATE_PCPTYPES - 1 ; i++) {
 		fallback_mt = fallbacks[migratetype][i];
-		if (fallback_mt == MIGRATE_TYPES)
-			break;
-
 		if (free_area_empty(area, fallback_mt))
 			continue;
 
@@ -3706,10 +3724,20 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
 		 * reserved for high-order atomic allocation, so order-0
 		 * request should skip it.
 		 */
-		if (order > 0 && alloc_flags & ALLOC_HARDER)
+		if (alloc_flags & ALLOC_HIGHATOMIC)
 			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
 		if (!page) {
 			page = __rmqueue(zone, order, migratetype, alloc_flags);
+
+			/*
+			 * If the allocation fails, allow OOM handling access
+			 * to HIGHATOMIC reserves as failing now is worse than
+			 * failing a high-order atomic allocation in the
+			 * future.
+			 */
+			if (!page && (alloc_flags & ALLOC_OOM))
+				page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
+
 			if (!page) {
 				spin_unlock_irqrestore(&zone->lock, flags);
 				return NULL;
@@ -3939,15 +3967,14 @@ 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)
 {
-	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 	long unusable_free = (1 << order) - 1;
 
 	/*
-	 * If the caller does not have rights to ALLOC_HARDER then subtract
-	 * the high-atomic reserves. This will over-estimate the size of the
-	 * atomic reserve but it avoids a search.
+	 * If the caller does not have rights to reserves below the min
+	 * watermark then subtract the high-atomic reserves. This will
+	 * over-estimate the size of the atomic reserve but it avoids a search.
 	 */
-	if (likely(!alloc_harder))
+	if (likely(!(alloc_flags & ALLOC_RESERVES)))
 		unusable_free += z->nr_reserved_highatomic;
 
 #ifdef CONFIG_CMA
@@ -3971,25 +3998,37 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 {
 	long min = mark;
 	int o;
-	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 
 	/* free_pages may go negative - that's OK */
 	free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
 
-	if (alloc_flags & ALLOC_HIGH)
-		min -= min / 2;
+	if (unlikely(alloc_flags & ALLOC_RESERVES)) {
+		/*
+		 * __GFP_HIGH allows access to 50% of the min reserve as well
+		 * as OOM.
+		 */
+		if (alloc_flags & ALLOC_MIN_RESERVE) {
+			min -= min / 2;
+
+			/*
+			 * Non-blocking allocations (e.g. GFP_ATOMIC) can
+			 * access more reserves than just __GFP_HIGH. Other
+			 * non-blocking allocations requests such as GFP_NOWAIT
+			 * or (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) do not get
+			 * access to the min reserve.
+			 */
+			if (alloc_flags & ALLOC_NON_BLOCK)
+				min -= min / 4;
+		}
 
-	if (unlikely(alloc_harder)) {
 		/*
-		 * OOM victims can try even harder than normal ALLOC_HARDER
+		 * OOM victims can try even harder than the normal reserve
 		 * users on the grounds that it's definitely going to be in
 		 * the exit path shortly and free memory. Any allocation it
 		 * makes during the free path will be small and short-lived.
 		 */
 		if (alloc_flags & ALLOC_OOM)
 			min -= min / 2;
-		else
-			min -= min / 4;
 	}
 
 	/*
@@ -4023,8 +4062,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 			return true;
 		}
 #endif
-		if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
+		if ((alloc_flags & (ALLOC_HIGHATOMIC|ALLOC_OOM)) &&
+		    !free_area_empty(area, MIGRATE_HIGHATOMIC)) {
 			return true;
+		}
 	}
 	return false;
 }
@@ -4064,13 +4105,14 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
 					free_pages))
 		return true;
+
 	/*
-	 * Ignore watermark boosting for GFP_ATOMIC order-0 allocations
+	 * Ignore watermark boosting for __GFP_HIGH order-0 allocations
 	 * when checking the min watermark. The min watermark is the
 	 * point where boosting is ignored so that kswapd is woken up
 	 * when below the low watermark.
 	 */
-	if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost
+	if (unlikely(!order && (alloc_flags & ALLOC_MIN_RESERVE) && z->watermark_boost
 		&& ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) {
 		mark = z->_watermark[WMARK_MIN];
 		return __zone_watermark_ok(z, order, mark, highest_zoneidx,
@@ -4244,7 +4286,7 @@ retry:
 			 * Watermark failed for this zone, but see if we can
 			 * grow this zone if it contains deferred pages.
 			 */
-			if (static_branch_unlikely(&deferred_pages)) {
+			if (deferred_pages_enabled()) {
 				if (_deferred_grow_zone(zone, order))
 					goto try_this_zone;
 			}
@@ -4286,14 +4328,14 @@ try_this_zone:
 			 * If this is a high-order atomic allocation then check
 			 * if the pageblock should be reserved for the future
 			 */
-			if (unlikely(order && (alloc_flags & ALLOC_HARDER)))
+			if (unlikely(alloc_flags & ALLOC_HIGHATOMIC))
 				reserve_highatomic_pageblock(page, zone, order);
 
 			return page;
 		} else {
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 			/* Try again if zone has deferred pages */
-			if (static_branch_unlikely(&deferred_pages)) {
+			if (deferred_pages_enabled()) {
 				if (_deferred_grow_zone(zone, order))
 					goto try_this_zone;
 			}
@@ -4813,41 +4855,48 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
 }
 
 static inline unsigned int
-gfp_to_alloc_flags(gfp_t gfp_mask)
+gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
 {
 	unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
 
 	/*
-	 * __GFP_HIGH is assumed to be the same as ALLOC_HIGH
+	 * __GFP_HIGH is assumed to be the same as ALLOC_MIN_RESERVE
 	 * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
 	 * to save two branches.
 	 */
-	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
+	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_MIN_RESERVE);
 	BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
 
 	/*
 	 * The caller may dip into page reserves a bit more if the caller
 	 * cannot run direct reclaim, or if the caller has realtime scheduling
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
+	 * set both ALLOC_NON_BLOCK and ALLOC_MIN_RESERVE(__GFP_HIGH).
 	 */
 	alloc_flags |= (__force int)
 		(gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
 
-	if (gfp_mask & __GFP_ATOMIC) {
+	if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) {
 		/*
 		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
 		 * if it can't schedule.
 		 */
-		if (!(gfp_mask & __GFP_NOMEMALLOC))
-			alloc_flags |= ALLOC_HARDER;
+		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
+			alloc_flags |= ALLOC_NON_BLOCK;
+
+			if (order > 0)
+				alloc_flags |= ALLOC_HIGHATOMIC;
+		}
+
 		/*
-		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
-		 * comment for __cpuset_node_allowed().
+		 * Ignore cpuset mems for non-blocking __GFP_HIGH (probably
+		 * GFP_ATOMIC) rather than fail, see the comment for
+		 * __cpuset_node_allowed().
 		 */
-		alloc_flags &= ~ALLOC_CPUSET;
+		if (alloc_flags & ALLOC_MIN_RESERVE)
+			alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && in_task())
-		alloc_flags |= ALLOC_HARDER;
+		alloc_flags |= ALLOC_MIN_RESERVE;
 
 	alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags);
 
@@ -5028,14 +5077,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned int zonelist_iter_cookie;
 	int reserve_flags;
 
-	/*
-	 * We also sanity check to catch abuse of atomic reserves being used by
-	 * callers that are not in atomic context.
-	 */
-	if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) ==
-				(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
-		gfp_mask &= ~__GFP_ATOMIC;
-
 restart:
 	compaction_retries = 0;
 	no_progress_loops = 0;
@@ -5048,7 +5089,7 @@ restart:
 	 * kswapd needs to be woken up, and to avoid the cost of setting up
 	 * alloc_flags precisely. So we do that now.
 	 */
-	alloc_flags = gfp_to_alloc_flags(gfp_mask);
+	alloc_flags = gfp_to_alloc_flags(gfp_mask, order);
 
 	/*
 	 * We need to recalculate the starting point for the zonelist iterator
@@ -5276,12 +5317,13 @@ nopage:
 		WARN_ON_ONCE_GFP(costly_order, gfp_mask);
 
 		/*
-		 * Help non-failing allocations by giving them access to memory
-		 * reserves but do not use ALLOC_NO_WATERMARKS because this
+		 * Help non-failing allocations by giving some access to memory
+		 * reserves normally used for high priority non-blocking
+		 * allocations but do not use ALLOC_NO_WATERMARKS because this
 		 * could deplete whole memory reserves which would just make
-		 * the situation worse
+		 * the situation worse.
 		 */
-		page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
+		page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE, ac);
 		if (page)
 			goto got_pg;
 
@@ -5390,7 +5432,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 		goto out;
 
 	/* Bulk allocator does not support memcg accounting. */
-	if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT))
+	if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT))
 		goto failed;
 
 	/* Use the single page allocator for one page. */
@@ -5562,7 +5604,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 	page = __alloc_pages_slowpath(alloc_gfp, order, &ac);
 
 out:
-	if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT) && page &&
+	if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page &&
 	    unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) {
 		__free_pages(page, order);
 		page = NULL;
@@ -6764,8 +6806,10 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
 		if (context == MEMINIT_EARLY) {
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
-			if (defer_init(nid, pfn, zone_end_pfn))
+			if (defer_init(nid, pfn, zone_end_pfn)) {
+				deferred_struct_pages = true;
 				break;
+			}
 		}
 
 		page = pfn_to_page(pfn);
@@ -7929,6 +7973,7 @@ static void __init free_area_init_node(int nid)
 	pgdat_set_deferred_range(pgdat);
 
 	free_area_init_core(pgdat);
+	lru_gen_init_pgdat(pgdat);
 }
 
 static void __init free_area_init_memoryless_node(int nid)
@@ -8363,11 +8408,9 @@ void __init free_area_init(unsigned long *max_zone_pfn)
 
 			/* Allocator not initialized yet */
 			pgdat = arch_alloc_nodedata(nid);
-			if (!pgdat) {
-				pr_err("Cannot allocate %zuB for node %d.\n",
-						sizeof(*pgdat), nid);
-				continue;
-			}
+			if (!pgdat)
+				panic("Cannot allocate %zuB for node %d.\n",
+				       sizeof(*pgdat), nid);
 			arch_refresh_nodedata(nid, pgdat);
 			free_area_init_memoryless_node(nid);
 
@@ -8571,7 +8614,7 @@ static int page_alloc_cpu_dead(unsigned int cpu)
 	struct zone *zone;
 
 	lru_add_drain_cpu(cpu);
-	mlock_page_drain_remote(cpu);
+	mlock_drain_remote(cpu);
 	drain_pages(cpu);
 
 	/*