Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "11 mm fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: khugepaged: add trace status description for SCAN_PAGE_HAS_PRIVATE
  mm: memcg/slab: call flush_memcg_workqueue() only if memcg workqueue is valid
  mm/page-writeback.c: improve arithmetic divisions
  mm/page-writeback.c: use div64_ul() for u64-by-unsigned-long divide
  mm/page-writeback.c: avoid potential division by zero in wb_min_max_ratio()
  mm, debug_pagealloc: don't rely on static keys too early
  mm: memcg/slab: fix percpu slab vmstats flushing
  mm/shmem.c: thp, shmem: fix conflict of above-47bit hint address and PMD alignment
  mm/huge_memory.c: thp: fix conflict of above-47bit hint address and PMD alignment
  mm/memory_hotplug: don't free usage map when removing a re-added early section
  mm, thp: tweak reclaim/compaction effort of local-only and all-node allocations

include/linux/mm.h

@@ -2658,13 +2658,25 @@ static inline bool want_init_on_free(void)
 	       !page_poisoning_enabled();
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
-DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled);
+#ifdef CONFIG_DEBUG_PAGEALLOC
+extern void init_debug_pagealloc(void);
 #else
-DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
+static inline void init_debug_pagealloc(void) {}
 #endif
+extern bool _debug_pagealloc_enabled_early;
+DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
 
 static inline bool debug_pagealloc_enabled(void)
+{
+	return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
+		_debug_pagealloc_enabled_early;
+}
+
+/*
+ * For use in fast paths after init_debug_pagealloc() has run, or when a
+ * false negative result is not harmful when called too early.
+ */
+static inline bool debug_pagealloc_enabled_static(void)
 {
 	if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC))
 		return false;

include/linux/mmzone.h

@@ -215,9 +215,8 @@ enum node_stat_item {
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
-	NR_SLAB_RECLAIMABLE,	/* Please do not reorder this item */
-	NR_SLAB_UNRECLAIMABLE,	/* and this one without looking at
-				 * memcg_flush_percpu_vmstats() first. */
+	NR_SLAB_RECLAIMABLE,
+	NR_SLAB_UNRECLAIMABLE,
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_NODES,

include/trace/events/huge_memory.h

@@ -31,7 +31,8 @@
 	EM( SCAN_ALLOC_HUGE_PAGE_FAIL,	"alloc_huge_page_failed")	\
 	EM( SCAN_CGROUP_CHARGE_FAIL,	"ccgroup_charge_failed")	\
 	EM( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")		\
-	EMe(SCAN_TRUNCATED,		"truncated")			\
+	EM( SCAN_TRUNCATED,		"truncated")			\
+	EMe(SCAN_PAGE_HAS_PRIVATE,	"page_has_private")		\
 
 #undef EM
 #undef EMe

init/main.c

@@ -553,6 +553,7 @@ static void __init mm_init(void)
 	 * bigger than MAX_ORDER unless SPARSEMEM.
 	 */
 	page_ext_init_flatmem();
+	init_debug_pagealloc();
 	report_meminit();
 	mem_init();
 	kmem_cache_init();

mm/huge_memory.c

@@ -527,13 +527,13 @@ void prep_transhuge_page(struct page *page)
 	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
 }
 
-static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+static unsigned long __thp_get_unmapped_area(struct file *filp,
+		unsigned long addr, unsigned long len,
 		loff_t off, unsigned long flags, unsigned long size)
 {
-	unsigned long addr;
 	loff_t off_end = off + len;
 	loff_t off_align = round_up(off, size);
-	unsigned long len_pad;
+	unsigned long len_pad, ret;
 
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
@@ -542,30 +542,40 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long le
 	if (len_pad < len || (off + len_pad) < off)
 		return 0;
 
-	addr = current->mm->get_unmapped_area(filp, 0, len_pad,
+	ret = current->mm->get_unmapped_area(filp, addr, len_pad,
 					      off >> PAGE_SHIFT, flags);
-	if (IS_ERR_VALUE(addr))
+
+	/*
+	 * The failure might be due to length padding. The caller will retry
+	 * without the padding.
+	 */
+	if (IS_ERR_VALUE(ret))
 		return 0;
 
-	addr += (off - addr) & (size - 1);
+	/*
+	 * Do not try to align to THP boundary if allocation at the address
+	 * hint succeeds.
+	 */
+	if (ret == addr)
 		return addr;
+
+	ret += (off - ret) & (size - 1);
+	return ret;
 }
 
 unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
+	unsigned long ret;
 	loff_t off = (loff_t)pgoff << PAGE_SHIFT;
 
-	if (addr)
-		goto out;
 	if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
 		goto out;
 
-	addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE);
-	if (addr)
-		return addr;
-
- out:
+	ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE);
+	if (ret)
+		return ret;
+out:
 	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
 }
 EXPORT_SYMBOL_GPL(thp_get_unmapped_area);

mm/memcontrol.c

@@ -3287,49 +3287,34 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	}
 }
 
-static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only)
+static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg)
 {
-	unsigned long stat[MEMCG_NR_STAT];
+	unsigned long stat[MEMCG_NR_STAT] = {0};
 	struct mem_cgroup *mi;
 	int node, cpu, i;
-	int min_idx, max_idx;
-
-	if (slab_only) {
-		min_idx = NR_SLAB_RECLAIMABLE;
-		max_idx = NR_SLAB_UNRECLAIMABLE;
-	} else {
-		min_idx = 0;
-		max_idx = MEMCG_NR_STAT;
-	}
-
-	for (i = min_idx; i < max_idx; i++)
-		stat[i] = 0;
 
 	for_each_online_cpu(cpu)
-		for (i = min_idx; i < max_idx; i++)
+		for (i = 0; i < MEMCG_NR_STAT; i++)
 			stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);
 
 	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
-		for (i = min_idx; i < max_idx; i++)
+		for (i = 0; i < MEMCG_NR_STAT; i++)
 			atomic_long_add(stat[i], &mi->vmstats[i]);
 
-	if (!slab_only)
-		max_idx = NR_VM_NODE_STAT_ITEMS;
-
 	for_each_node(node) {
 		struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
 		struct mem_cgroup_per_node *pi;
 
-		for (i = min_idx; i < max_idx; i++)
+		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
 			stat[i] = 0;
 
 		for_each_online_cpu(cpu)
-			for (i = min_idx; i < max_idx; i++)
+			for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
 				stat[i] += per_cpu(
 					pn->lruvec_stat_cpu->count[i], cpu);
 
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
-			for (i = min_idx; i < max_idx; i++)
+			for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
 				atomic_long_add(stat[i], &pi->lruvec_stat[i]);
 	}
 }
@@ -3403,13 +3388,9 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 		parent = root_mem_cgroup;
 
 	/*
-	 * Deactivate and reparent kmem_caches. Then flush percpu
-	 * slab statistics to have precise values at the parent and
-	 * all ancestor levels. It's required to keep slab stats
-	 * accurate after the reparenting of kmem_caches.
+	 * Deactivate and reparent kmem_caches.
 	 */
 	memcg_deactivate_kmem_caches(memcg, parent);
-	memcg_flush_percpu_vmstats(memcg, true);
 
 	kmemcg_id = memcg->kmemcg_id;
 	BUG_ON(kmemcg_id < 0);
@@ -4913,7 +4894,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 	 * Flush percpu vmstats and vmevents to guarantee the value correctness
 	 * on parent's and all ancestor levels.
 	 */
-	memcg_flush_percpu_vmstats(memcg, false);
+	memcg_flush_percpu_vmstats(memcg);
 	memcg_flush_percpu_vmevents(memcg);
 	__mem_cgroup_free(memcg);
 }

mm/mempolicy.c

@@ -2148,18 +2148,22 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		nmask = policy_nodemask(gfp, pol);
 		if (!nmask || node_isset(hpage_node, *nmask)) {
 			mpol_cond_put(pol);
+			/*
+			 * First, try to allocate THP only on local node, but
+			 * don't reclaim unnecessarily, just compact.
+			 */
 			page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_THISNODE, order);
+				gfp | __GFP_THISNODE | __GFP_NORETRY, order);
 
 			/*
 			 * If hugepage allocations are configured to always
 			 * synchronous compact or the vma has been madvised
 			 * to prefer hugepage backing, retry allowing remote
-			 * memory as well.
+			 * memory with both reclaim and compact as well.
 			 */
 			if (!page && (gfp & __GFP_DIRECT_RECLAIM))
 				page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_NORETRY, order);
+								gfp, order);
 
 			goto out;
 		}

mm/page-writeback.c

@@ -201,11 +201,11 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
 	if (this_bw < tot_bw) {
 		if (min) {
 			min *= this_bw;
-			do_div(min, tot_bw);
+			min = div64_ul(min, tot_bw);
 		}
 		if (max < 100) {
 			max *= this_bw;
-			do_div(max, tot_bw);
+			max = div64_ul(max, tot_bw);
 		}
 	}
 
@@ -766,7 +766,7 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc)
 	struct wb_domain *dom = dtc_dom(dtc);
 	unsigned long thresh = dtc->thresh;
 	u64 wb_thresh;
-	long numerator, denominator;
+	unsigned long numerator, denominator;
 	unsigned long wb_min_ratio, wb_max_ratio;
 
 	/*
@@ -777,7 +777,7 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc)
 
 	wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100;
 	wb_thresh *= numerator;
-	do_div(wb_thresh, denominator);
+	wb_thresh = div64_ul(wb_thresh, denominator);
 
 	wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio);
 
@@ -1102,7 +1102,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb,
 	bw = written - min(written, wb->written_stamp);
 	bw *= HZ;
 	if (unlikely(elapsed > period)) {
-		do_div(bw, elapsed);
+		bw = div64_ul(bw, elapsed);
 		avg = bw;
 		goto out;
 	}

mm/page_alloc.c

@@ -694,34 +694,27 @@ void prep_compound_page(struct page *page, unsigned int order)
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
 
-#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
-DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled);
-#else
+bool _debug_pagealloc_enabled_early __read_mostly
+			= IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
+EXPORT_SYMBOL(_debug_pagealloc_enabled_early);
 DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
-#endif
 EXPORT_SYMBOL(_debug_pagealloc_enabled);
 
 DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
 
 static int __init early_debug_pagealloc(char *buf)
 {
-	bool enable = false;
-
-	if (kstrtobool(buf, &enable))
-		return -EINVAL;
-
-	if (enable)
-		static_branch_enable(&_debug_pagealloc_enabled);
-
-	return 0;
+	return kstrtobool(buf, &_debug_pagealloc_enabled_early);
 }
 early_param("debug_pagealloc", early_debug_pagealloc);
 
-static void init_debug_guardpage(void)
+void init_debug_pagealloc(void)
 {
 	if (!debug_pagealloc_enabled())
 		return;
 
+	static_branch_enable(&_debug_pagealloc_enabled);
+
 	if (!debug_guardpage_minorder())
 		return;
 
@@ -1186,7 +1179,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	 */
 	arch_free_page(page, order);
 
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		kernel_map_pages(page, 1 << order, 0);
 
 	kasan_free_nondeferred_pages(page, order);
@@ -1207,7 +1200,7 @@ static bool free_pcp_prepare(struct page *page)
 
 static bool bulkfree_pcp_prepare(struct page *page)
 {
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		return free_pages_check(page);
 	else
 		return false;
@@ -1221,7 +1214,7 @@ static bool bulkfree_pcp_prepare(struct page *page)
  */
 static bool free_pcp_prepare(struct page *page)
 {
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		return free_pages_prepare(page, 0, true);
 	else
 		return free_pages_prepare(page, 0, false);
@@ -1973,10 +1966,6 @@ void __init page_alloc_init_late(void)
 
 	for_each_populated_zone(zone)
 		set_zone_contiguous(zone);
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	init_debug_guardpage();
-#endif
 }
 
 #ifdef CONFIG_CMA
@@ -2106,7 +2095,7 @@ static inline bool free_pages_prezeroed(void)
  */
 static inline bool check_pcp_refill(struct page *page)
 {
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		return check_new_page(page);
 	else
 		return false;
@@ -2128,7 +2117,7 @@ static inline bool check_pcp_refill(struct page *page)
 }
 static inline bool check_new_pcp(struct page *page)
 {
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		return check_new_page(page);
 	else
 		return false;
@@ -2155,7 +2144,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		kernel_map_pages(page, 1 << order, 1);
 	kasan_alloc_pages(page, order);
 	kernel_poison_pages(page, 1 << order, 1);
@@ -4476,8 +4465,11 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		if (page)
 			goto got_pg;
 
-		 if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
-		     !(gfp_mask & __GFP_RETRY_MAYFAIL)) {
+		/*
+		 * Checks for costly allocations with __GFP_NORETRY, which
+		 * includes some THP page fault allocations
+		 */
+		if (costly_order && (gfp_mask & __GFP_NORETRY)) {
 			/*
 			 * If allocating entire pageblock(s) and compaction
 			 * failed because all zones are below low watermarks
@@ -4498,23 +4490,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 			if (compact_result == COMPACT_SKIPPED ||
 			    compact_result == COMPACT_DEFERRED)
 				goto nopage;
-		}
-
-		/*
-		 * Checks for costly allocations with __GFP_NORETRY, which
-		 * includes THP page fault allocations
-		 */
-		if (costly_order && (gfp_mask & __GFP_NORETRY)) {
-			/*
-			 * If compaction is deferred for high-order allocations,
-			 * it is because sync compaction recently failed. If
-			 * this is the case and the caller requested a THP
-			 * allocation, we do not want to heavily disrupt the
-			 * system, so we fail the allocation instead of entering
-			 * direct reclaim.
-			 */
-			if (compact_result == COMPACT_DEFERRED)
-				goto nopage;
 
 			/*
 			 * Looks like reclaim/compaction is worth trying, but

mm/shmem.c

@@ -2107,9 +2107,10 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 	/*
 	 * Our priority is to support MAP_SHARED mapped hugely;
 	 * and support MAP_PRIVATE mapped hugely too, until it is COWed.
-	 * But if caller specified an address hint, respect that as before.
+	 * But if caller specified an address hint and we allocated area there
+	 * successfully, respect that as before.
 	 */
-	if (uaddr)
+	if (uaddr == addr)
 		return addr;
 
 	if (shmem_huge != SHMEM_HUGE_FORCE) {
@@ -2143,7 +2144,7 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 	if (inflated_len < len)
 		return addr;
 
-	inflated_addr = get_area(NULL, 0, inflated_len, 0, flags);
+	inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags);
 	if (IS_ERR_VALUE(inflated_addr))
 		return addr;
 	if (inflated_addr & ~PAGE_MASK)

mm/slab.c

@@ -1416,7 +1416,7 @@ static void kmem_rcu_free(struct rcu_head *head)
 #if DEBUG
 static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
 {
-	if (debug_pagealloc_enabled() && OFF_SLAB(cachep) &&
+	if (debug_pagealloc_enabled_static() && OFF_SLAB(cachep) &&
 		(cachep->size % PAGE_SIZE) == 0)
 		return true;
 
@@ -2008,7 +2008,7 @@ int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags)
 	 * to check size >= 256. It guarantees that all necessary small
 	 * sized slab is initialized in current slab initialization sequence.
 	 */
-	if (debug_pagealloc_enabled() && (flags & SLAB_POISON) &&
+	if (debug_pagealloc_enabled_static() && (flags & SLAB_POISON) &&
 		size >= 256 && cachep->object_size > cache_line_size()) {
 		if (size < PAGE_SIZE || size % PAGE_SIZE == 0) {
 			size_t tmp_size = ALIGN(size, PAGE_SIZE);

mm/slab_common.c

@@ -903,6 +903,7 @@ static void flush_memcg_workqueue(struct kmem_cache *s)
 	 * deactivates the memcg kmem_caches through workqueue. Make sure all
 	 * previous workitems on workqueue are processed.
 	 */
+	if (likely(memcg_kmem_cache_wq))
 		flush_workqueue(memcg_kmem_cache_wq);
 
 	/*

mm/slub.c

@@ -288,7 +288,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
 	unsigned long freepointer_addr;
 	void *p;
 
-	if (!debug_pagealloc_enabled())
+	if (!debug_pagealloc_enabled_static())
 		return get_freepointer(s, object);
 
 	freepointer_addr = (unsigned long)object + s->offset;

mm/sparse.c

@@ -777,7 +777,14 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) {
 		unsigned long section_nr = pfn_to_section_nr(pfn);
 
-		if (!section_is_early) {
+		/*
+		 * When removing an early section, the usage map is kept (as the
+		 * usage maps of other sections fall into the same page). It
+		 * will be re-used when re-adding the section - which is then no
+		 * longer an early section. If the usage map is PageReserved, it
+		 * was allocated during boot.
+		 */
+		if (!PageReserved(virt_to_page(ms->usage))) {
 			kfree(ms->usage);
 			ms->usage = NULL;
 		}

mm/vmalloc.c

@@ -1383,7 +1383,7 @@ static void free_unmap_vmap_area(struct vmap_area *va)
 {
 	flush_cache_vunmap(va->va_start, va->va_end);
 	unmap_vmap_area(va);
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		flush_tlb_kernel_range(va->va_start, va->va_end);
 
 	free_vmap_area_noflush(va);
@@ -1681,7 +1681,7 @@ static void vb_free(const void *addr, unsigned long size)
 
 	vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
 
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_static())
 		flush_tlb_kernel_range((unsigned long)addr,
 					(unsigned long)addr + size);