Merge branch 'akpm' (second patch-bomb from Andrew)

Merge second patchbomb from Andrew Morton:
 - the rest of MM
 - misc fs fixes
 - add execveat() syscall
 - new ratelimit feature for fault-injection
 - decompressor updates
 - ipc/ updates
 - fallocate feature creep
 - fsnotify cleanups
 - a few other misc things

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (99 commits)
  cgroups: Documentation: fix trivial typos and wrong paragraph numberings
  parisc: percpu: update comments referring to __get_cpu_var
  percpu: update local_ops.txt to reflect this_cpu operations
  percpu: remove __get_cpu_var and __raw_get_cpu_var macros
  fsnotify: remove destroy_list from fsnotify_mark
  fsnotify: unify inode and mount marks handling
  fallocate: create FAN_MODIFY and IN_MODIFY events
  mm/cma: make kmemleak ignore CMA regions
  slub: fix cpuset check in get_any_partial
  slab: fix cpuset check in fallback_alloc
  shmdt: use i_size_read() instead of ->i_size
  ipc/shm.c: fix overly aggressive shmdt() when calls span multiple segments
  ipc/msg: increase MSGMNI, remove scaling
  ipc/sem.c: increase SEMMSL, SEMMNI, SEMOPM
  ipc/sem.c: change memory barrier in sem_lock() to smp_rmb()
  lib/decompress.c: consistency of compress formats for kernel image
  decompress_bunzip2: off by one in get_next_block()
  usr/Kconfig: make initrd compression algorithm selection not expert
  fault-inject: add ratelimit option
  ratelimit: add initialization macro
  ...

1 files changed, 101 insertions, 36 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index df542feaac3b..fa974d87f60d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,6 +48,7 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
+#include <linux/page_ext.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
@@ -55,9 +56,10 @@
 #include <linux/prefetch.h>
 #include <linux/mm_inline.h>
 #include <linux/migrate.h>
-#include <linux/page-debug-flags.h>
+#include <linux/page_ext.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
+#include <linux/page_owner.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -424,6 +426,42 @@ static inline void prep_zero_page(struct page *page, unsigned int order,
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
+bool _debug_pagealloc_enabled __read_mostly;
+bool _debug_guardpage_enabled __read_mostly;
+
+static int __init early_debug_pagealloc(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (strcmp(buf, "on") == 0)
+		_debug_pagealloc_enabled = true;
+
+	return 0;
+}
+early_param("debug_pagealloc", early_debug_pagealloc);
+
+static bool need_debug_guardpage(void)
+{
+	/* If we don't use debug_pagealloc, we don't need guard page */
+	if (!debug_pagealloc_enabled())
+		return false;
+
+	return true;
+}
+
+static void init_debug_guardpage(void)
+{
+	if (!debug_pagealloc_enabled())
+		return;
+
+	_debug_guardpage_enabled = true;
+}
+
+struct page_ext_operations debug_guardpage_ops = {
+	.need = need_debug_guardpage,
+	.init = init_debug_guardpage,
+};
 
 static int __init debug_guardpage_minorder_setup(char *buf)
 {
@@ -439,18 +477,44 @@ static int __init debug_guardpage_minorder_setup(char *buf)
 }
 __setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
 
-static inline void set_page_guard_flag(struct page *page)
+static inline void set_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype)
 {
-	__set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	if (!debug_guardpage_enabled())
+		return;
+
+	page_ext = lookup_page_ext(page);
+	__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
+
+	INIT_LIST_HEAD(&page->lru);
+	set_page_private(page, order);
+	/* Guard pages are not available for any usage */
+	__mod_zone_freepage_state(zone, -(1 << order), migratetype);
 }
 
-static inline void clear_page_guard_flag(struct page *page)
+static inline void clear_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype)
 {
-	__clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+	struct page_ext *page_ext;
+
+	if (!debug_guardpage_enabled())
+		return;
+
+	page_ext = lookup_page_ext(page);
+	__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
+
+	set_page_private(page, 0);
+	if (!is_migrate_isolate(migratetype))
+		__mod_zone_freepage_state(zone, (1 << order), migratetype);
 }
 #else
-static inline void set_page_guard_flag(struct page *page) { }
-static inline void clear_page_guard_flag(struct page *page) { }
+struct page_ext_operations debug_guardpage_ops = { NULL, };
+static inline void set_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype) {}
+static inline void clear_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype) {}
 #endif
 
 static inline void set_page_order(struct page *page, unsigned int order)
@@ -581,12 +645,7 @@ static inline void __free_one_page(struct page *page,
 		 * merge with it and move up one order.
 		 */
 		if (page_is_guard(buddy)) {
-			clear_page_guard_flag(buddy);
-			set_page_private(buddy, 0);
-			if (!is_migrate_isolate(migratetype)) {
-				__mod_zone_freepage_state(zone, 1 << order,
-							  migratetype);
-			}
+			clear_page_guard(zone, buddy, order, migratetype);
 		} else {
 			list_del(&buddy->lru);
 			zone->free_area[order].nr_free--;
@@ -755,6 +814,8 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	if (bad)
 		return false;
 
+	reset_page_owner(page, order);
+
 	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page),
 					   PAGE_SIZE << order);
@@ -861,23 +922,18 @@ static inline void expand(struct zone *zone, struct page *page,
 		size >>= 1;
 		VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-		if (high < debug_guardpage_minorder()) {
+		if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
+			debug_guardpage_enabled() &&
+			high < debug_guardpage_minorder()) {
 			/*
 			 * Mark as guard pages (or page), that will allow to
 			 * merge back to allocator when buddy will be freed.
 			 * Corresponding page table entries will not be touched,
 			 * pages will stay not present in virtual address space
 			 */
-			INIT_LIST_HEAD(&page[size].lru);
-			set_page_guard_flag(&page[size]);
-			set_page_private(&page[size], high);
-			/* Guard pages are not available for any usage */
-			__mod_zone_freepage_state(zone, -(1 << high),
-						  migratetype);
+			set_page_guard(zone, &page[size], high, migratetype);
 			continue;
 		}
-#endif
 		list_add(&page[size].lru, &area->free_list[migratetype]);
 		area->nr_free++;
 		set_page_order(&page[size], high);
@@ -935,6 +991,8 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags)
 	if (order && (gfp_flags & __GFP_COMP))
 		prep_compound_page(page, order);
 
+	set_page_owner(page, order, gfp_flags);
+
 	return 0;
 }
 
@@ -1507,8 +1565,11 @@ void split_page(struct page *page, unsigned int order)
 		split_page(virt_to_page(page[0].shadow), order);
 #endif
 
-	for (i = 1; i < (1 << order); i++)
+	set_page_owner(page, 0, 0);
+	for (i = 1; i < (1 << order); i++) {
 		set_page_refcounted(page + i);
+		set_page_owner(page + i, 0, 0);
+	}
 }
 EXPORT_SYMBOL_GPL(split_page);
 
@@ -1548,6 +1609,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		}
 	}
 
+	set_page_owner(page, order, 0);
 	return 1UL << order;
 }
 
@@ -4856,6 +4918,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 #endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
+	pgdat_page_ext_init(pgdat);
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
@@ -4874,16 +4937,18 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		 * and per-cpu initialisations
 		 */
 		memmap_pages = calc_memmap_size(size, realsize);
-		if (freesize >= memmap_pages) {
-			freesize -= memmap_pages;
-			if (memmap_pages)
-				printk(KERN_DEBUG
-				       "  %s zone: %lu pages used for memmap\n",
-				       zone_names[j], memmap_pages);
-		} else
-			printk(KERN_WARNING
-				"  %s zone: %lu pages exceeds freesize %lu\n",
-				zone_names[j], memmap_pages, freesize);
+		if (!is_highmem_idx(j)) {
+			if (freesize >= memmap_pages) {
+				freesize -= memmap_pages;
+				if (memmap_pages)
+					printk(KERN_DEBUG
+					       "  %s zone: %lu pages used for memmap\n",
+					       zone_names[j], memmap_pages);
+			} else
+				printk(KERN_WARNING
+					"  %s zone: %lu pages exceeds freesize %lu\n",
+					zone_names[j], memmap_pages, freesize);
+		}
 
 		/* Account for reserved pages */
 		if (j == 0 && freesize > dma_reserve) {
@@ -6221,9 +6286,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		if (!PageLRU(page))
 			found++;
 		/*
-		 * If there are RECLAIMABLE pages, we need to check it.
-		 * But now, memory offline itself doesn't call shrink_slab()
-		 * and it still to be fixed.
+		 * If there are RECLAIMABLE pages, we need to check
+		 * 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.