Merge linux-block/for-4.3/core into md/for-linux

There were a few conflicts that are fairly easy to resolve.

Signed-off-by: NeilBrown <neilb@suse.com>

20 files changed, 282 insertions, 96 deletions

diff --git a/mm/cma.h b/mm/cma.h
index 1132d73..17c75a4 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -16,7 +16,7 @@ struct cma {
 extern struct cma cma_areas[MAX_CMA_AREAS];
 extern unsigned cma_area_count;
 
-static unsigned long cma_bitmap_maxno(struct cma *cma)
+static inline unsigned long cma_bitmap_maxno(struct cma *cma)
 {
 	return cma->count >> cma->order_per_bit;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c107094..097c7a4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1676,12 +1676,7 @@ static void __split_huge_page_refcount(struct page *page,
 		/* after clearing PageTail the gup refcount can be released */
 		smp_mb__after_atomic();
 
-		/*
-		 * retain hwpoison flag of the poisoned tail page:
-		 *   fix for the unsuitable process killed on Guest Machine(KVM)
-		 *   by the memory-failure.
-		 */
-		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
+		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 		page_tail->flags |= (page->flags &
 				     ((1L << PG_referenced) |
 				      (1L << PG_swapbacked) |
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index bd837b8..6471014 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -5,4 +5,4 @@ CFLAGS_REMOVE_kasan.o = -pg
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
 CFLAGS_kasan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
-obj-y := kasan.o report.o
+obj-y := kasan.o report.o kasan_init.o
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 6c513a6..7b28e9c 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -2,7 +2,7 @@
  * This file contains shadow memory manipulation code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
- * Author: Andrey Ryabinin <a.ryabinin@samsung.com>
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
  * Some of code borrowed from https://github.com/xairy/linux by
  *        Andrey Konovalov <adech.fo@gmail.com>
diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c
new file mode 100644
index 0000000..3f9a41c
--- /dev/null
+++ b/mm/kasan/kasan_init.c
@@ -0,0 +1,152 @@
+/*
+ * This file contains some kasan initialization code.
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <linux/pfn.h>
+
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+
+/*
+ * This page serves two purposes:
+ *   - It used as early shadow memory. The entire shadow region populated
+ *     with this page, before we will be able to setup normal shadow memory.
+ *   - Latter it reused it as zero shadow to cover large ranges of memory
+ *     that allowed to access, but not handled by kasan (vmalloc/vmemmap ...).
+ */
+unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
+
+#if CONFIG_PGTABLE_LEVELS > 3
+pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
+#endif
+#if CONFIG_PGTABLE_LEVELS > 2
+pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss;
+#endif
+pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss;
+
+static __init void *early_alloc(size_t size, int node)
+{
+	return memblock_virt_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS),
+					BOOTMEM_ALLOC_ACCESSIBLE, node);
+}
+
+static void __init zero_pte_populate(pmd_t *pmd, unsigned long addr,
+				unsigned long end)
+{
+	pte_t *pte = pte_offset_kernel(pmd, addr);
+	pte_t zero_pte;
+
+	zero_pte = pfn_pte(PFN_DOWN(__pa(kasan_zero_page)), PAGE_KERNEL);
+	zero_pte = pte_wrprotect(zero_pte);
+
+	while (addr + PAGE_SIZE <= end) {
+		set_pte_at(&init_mm, addr, pte, zero_pte);
+		addr += PAGE_SIZE;
+		pte = pte_offset_kernel(pmd, addr);
+	}
+}
+
+static void __init zero_pmd_populate(pud_t *pud, unsigned long addr,
+				unsigned long end)
+{
+	pmd_t *pmd = pmd_offset(pud, addr);
+	unsigned long next;
+
+	do {
+		next = pmd_addr_end(addr, end);
+
+		if (IS_ALIGNED(addr, PMD_SIZE) && end - addr >= PMD_SIZE) {
+			pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
+			continue;
+		}
+
+		if (pmd_none(*pmd)) {
+			pmd_populate_kernel(&init_mm, pmd,
+					early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+		}
+		zero_pte_populate(pmd, addr, next);
+	} while (pmd++, addr = next, addr != end);
+}
+
+static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
+				unsigned long end)
+{
+	pud_t *pud = pud_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = pud_addr_end(addr, end);
+		if (IS_ALIGNED(addr, PUD_SIZE) && end - addr >= PUD_SIZE) {
+			pmd_t *pmd;
+
+			pud_populate(&init_mm, pud, kasan_zero_pmd);
+			pmd = pmd_offset(pud, addr);
+			pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
+			continue;
+		}
+
+		if (pud_none(*pud)) {
+			pud_populate(&init_mm, pud,
+				early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+		}
+		zero_pmd_populate(pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+}
+
+/**
+ * kasan_populate_zero_shadow - populate shadow memory region with
+ *                               kasan_zero_page
+ * @shadow_start - start of the memory range to populate
+ * @shadow_end   - end of the memory range to populate
+ */
+void __init kasan_populate_zero_shadow(const void *shadow_start,
+				const void *shadow_end)
+{
+	unsigned long addr = (unsigned long)shadow_start;
+	unsigned long end = (unsigned long)shadow_end;
+	pgd_t *pgd = pgd_offset_k(addr);
+	unsigned long next;
+
+	do {
+		next = pgd_addr_end(addr, end);
+
+		if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) {
+			pud_t *pud;
+			pmd_t *pmd;
+
+			/*
+			 * kasan_zero_pud should be populated with pmds
+			 * at this moment.
+			 * [pud,pmd]_populate*() below needed only for
+			 * 3,2 - level page tables where we don't have
+			 * puds,pmds, so pgd_populate(), pud_populate()
+			 * is noops.
+			 */
+			pgd_populate(&init_mm, pgd, kasan_zero_pud);
+			pud = pud_offset(pgd, addr);
+			pud_populate(&init_mm, pud, kasan_zero_pmd);
+			pmd = pmd_offset(pud, addr);
+			pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
+			continue;
+		}
+
+		if (pgd_none(*pgd)) {
+			pgd_populate(&init_mm, pgd,
+				early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+		}
+		zero_pud_populate(pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 680ceed..e07c94f 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -2,7 +2,7 @@
  * This file contains error reporting code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
- * Author: Andrey Ryabinin <a.ryabinin@samsung.com>
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
  * Some of code borrowed from https://github.com/xairy/linux by
  *        Andrey Konovalov <adech.fo@gmail.com>
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c53543d..1f4446a9 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -909,6 +909,18 @@ int get_hwpoison_page(struct page *page)
 	 * directly for tail pages.
 	 */
 	if (PageTransHuge(head)) {
+		/*
+		 * Non anonymous thp exists only in allocation/free time. We
+		 * can't handle such a case correctly, so let's give it up.
+		 * This should be better than triggering BUG_ON when kernel
+		 * tries to touch the "partially handled" page.
+		 */
+		if (!PageAnon(head)) {
+			pr_err("MCE: %#lx: non anonymous thp\n",
+				page_to_pfn(page));
+			return 0;
+		}
+
 		if (get_page_unless_zero(head)) {
 			if (PageTail(page))
 				get_page(page);
@@ -1134,17 +1146,11 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	}
 
 	if (!PageHuge(p) && PageTransHuge(hpage)) {
-		if (!PageAnon(hpage)) {
-			pr_err("MCE: %#lx: non anonymous thp\n", pfn);
-			if (TestClearPageHWPoison(p))
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-			put_page(p);
-			if (p != hpage)
-				put_page(hpage);
-			return -EBUSY;
-		}
-		if (unlikely(split_huge_page(hpage))) {
-			pr_err("MCE: %#lx: thp split failed\n", pfn);
+		if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
+			if (!PageAnon(hpage))
+				pr_err("MCE: %#lx: non anonymous thp\n", pfn);
+			else
+				pr_err("MCE: %#lx: thp split failed\n", pfn);
 			if (TestClearPageHWPoison(p))
 				atomic_long_sub(nr_pages, &num_poisoned_pages);
 			put_page(p);
@@ -1209,9 +1215,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
 		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		unlock_page(hpage);
 		put_page(hpage);
-		res = 0;
-		goto out;
+		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
@@ -1535,6 +1541,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		 */
 		ret = __get_any_page(page, pfn, 0);
 		if (!PageLRU(page)) {
+			/* Drop page reference which is from __get_any_page() */
+			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
 				pfn, page->flags);
 			return -EIO;
@@ -1564,13 +1572,12 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	unlock_page(hpage);
 
 	ret = isolate_huge_page(hpage, &pagelist);
-	if (ret) {
-		/*
-		 * get_any_page() and isolate_huge_page() takes a refcount each,
-		 * so need to drop one here.
-		 */
-		put_page(hpage);
-	} else {
+	/*
+	 * get_any_page() and isolate_huge_page() takes a refcount each,
+	 * so need to drop one here.
+	 */
+	put_page(hpage);
+	if (!ret) {
 		pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
 		return -EBUSY;
 	}
@@ -1656,6 +1663,8 @@ static int __soft_offline_page(struct page *page, int flags)
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
+		if (!TestSetPageHWPoison(page))
+			atomic_long_inc(&num_poisoned_pages);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
@@ -1670,9 +1679,8 @@ static int __soft_offline_page(struct page *page, int flags)
 				pfn, ret, page->flags);
 			if (ret > 0)
 				ret = -EIO;
-		} else {
-			SetPageHWPoison(page);
-			atomic_long_inc(&num_poisoned_pages);
+			if (TestClearPageHWPoison(page))
+				atomic_long_dec(&num_poisoned_pages);
 		}
 	} else {
 		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 26fbba7..6da82bc 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -446,7 +446,7 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 	int nr_pages = PAGES_PER_SECTION;
 	int nid = pgdat->node_id;
 	int zone_type;
-	unsigned long flags;
+	unsigned long flags, pfn;
 	int ret;
 
 	zone_type = zone - pgdat->node_zones;
@@ -461,6 +461,14 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 	memmap_init_zone(nr_pages, nid, zone_type,
 			 phys_start_pfn, MEMMAP_HOTPLUG);
+
+	/* online_page_range is called later and expects pages reserved */
+	for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) {
+		if (!pfn_valid(pfn))
+			continue;
+
+		SetPageReserved(pfn_to_page(pfn));
+	}
 	return 0;
 }
 
@@ -1269,6 +1277,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
 
 	/* create new memmap entry */
 	firmware_map_add_hotplug(start, start + size, "System RAM");
+	memblock_add_node(start, size, nid);
 
 	goto out;
 
@@ -2005,6 +2014,8 @@ void __ref remove_memory(int nid, u64 start, u64 size)
 
 	/* remove memmap entry */
 	firmware_map_remove(start, start + size, "System RAM");
+	memblock_free(start, size);
+	memblock_remove(start, size);
 
 	arch_remove_memory(start, size);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index ee401e4..eb426710 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -880,7 +880,8 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	/* Establish migration ptes or remove ptes */
 	if (page_mapped(page)) {
 		try_to_unmap(page,
-			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
+			TTU_IGNORE_HWPOISON);
 		page_was_mapped = 1;
 	}
 
@@ -950,7 +951,10 @@ out:
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		if (reason != MR_MEMORY_FAILURE)
+		/* Soft-offlined page shouldn't go through lru cache list */
+		if (reason == MR_MEMORY_FAILURE)
+			put_page(page);
+		else
 			putback_lru_page(page);
 	}
 
diff --git a/mm/mmap.c b/mm/mmap.c
index aa632ad..f126923 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1268,7 +1268,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	 *  mounted, in which case we dont add PROT_EXEC.)
 	 */
 	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
-		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
+		if (!(file && path_noexec(&file->f_path)))
 			prot |= PROT_EXEC;
 
 	if (!(flags & MAP_FIXED))
@@ -1337,7 +1337,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 		case MAP_PRIVATE:
 			if (!(file->f_mode & FMODE_READ))
 				return -EACCES;
-			if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
+			if (path_noexec(&file->f_path)) {
 				if (vm_flags & VM_EXEC)
 					return -EPERM;
 				vm_flags &= ~VM_MAYEXEC;
diff --git a/mm/nommu.c b/mm/nommu.c
index 58ea364..1cc0709 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -324,12 +324,12 @@ long vwrite(char *buf, char *addr, unsigned long count)
 }
 
 /*
- *	vmalloc  -  allocate virtually continguos memory
+ *	vmalloc  -  allocate virtually contiguous memory
  *
  *	@size:		allocation size
  *
  *	Allocate enough pages to cover @size from the page level
- *	allocator and map them into continguos kernel virtual space.
+ *	allocator and map them into contiguous kernel virtual space.
  *
  *	For tight control over page level allocator and protection flags
  *	use __vmalloc() instead.
@@ -341,12 +341,12 @@ void *vmalloc(unsigned long size)
 EXPORT_SYMBOL(vmalloc);
 
 /*
- *	vzalloc - allocate virtually continguos memory with zero fill
+ *	vzalloc - allocate virtually contiguous memory with zero fill
  *
  *	@size:		allocation size
  *
  *	Allocate enough pages to cover @size from the page level
- *	allocator and map them into continguos kernel virtual space.
+ *	allocator and map them into contiguous kernel virtual space.
  *	The memory allocated is set to zero.
  *
  *	For tight control over page level allocator and protection flags
@@ -420,7 +420,7 @@ void *vmalloc_exec(unsigned long size)
  *	@size:		allocation size
  *
  *	Allocate enough 32bit PA addressable pages to cover @size from the
- *	page level allocator and map them into continguos kernel virtual space.
+ *	page level allocator and map them into contiguous kernel virtual space.
  */
 void *vmalloc_32(unsigned long size)
 {
@@ -1035,7 +1035,7 @@ static int validate_mmap_request(struct file *file,
 
 		/* handle executable mappings and implied executable
 		 * mappings */
-		if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
+		if (path_noexec(&file->f_path)) {
 			if (prot & PROT_EXEC)
 				return -EPERM;
 		} else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 22cddd3..5cccc12 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2063,10 +2063,10 @@ static struct notifier_block ratelimit_nb = {
  */
 void __init page_writeback_init(void)
 {
+	BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
+
 	writeback_set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
-
-	BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef19f22..5b5240b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -18,7 +18,6 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/interrupt.h>
-#include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
@@ -981,21 +980,21 @@ static void __init __free_pages_boot_core(struct page *page,
 
 #if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
 	defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
-/* Only safe to use early in boot when initialisation is single-threaded */
+
 static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
 
 int __meminit early_pfn_to_nid(unsigned long pfn)
 {
+	static DEFINE_SPINLOCK(early_pfn_lock);
 	int nid;
 
-	/* The system will behave unpredictably otherwise */
-	BUG_ON(system_state != SYSTEM_BOOTING);
-
+	spin_lock(&early_pfn_lock);
 	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
-	if (nid >= 0)
-		return nid;
-	/* just returns 0 */
-	return 0;
+	if (nid < 0)
+		nid = 0;
+	spin_unlock(&early_pfn_lock);
+
+	return nid;
 }
 #endif
 
@@ -1060,7 +1059,15 @@ static void __init deferred_free_range(struct page *page,
 		__free_pages_boot_core(page, pfn, 0);
 }
 
-static __initdata DECLARE_RWSEM(pgdat_init_rwsem);
+/* Completion tracking for deferred_init_memmap() threads */
+static atomic_t pgdat_init_n_undone __initdata;
+static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
+
+static inline void __init pgdat_init_report_one_done(void)
+{
+	if (atomic_dec_and_test(&pgdat_init_n_undone))
+		complete(&pgdat_init_all_done_comp);
+}
 
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
@@ -1077,7 +1084,7 @@ static int __init deferred_init_memmap(void *data)
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
 	if (first_init_pfn == ULONG_MAX) {
-		up_read(&pgdat_init_rwsem);
+		pgdat_init_report_one_done();
 		return 0;
 	}
 
@@ -1177,7 +1184,8 @@ free_range:
 
 	pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
 					jiffies_to_msecs(jiffies - start));
-	up_read(&pgdat_init_rwsem);
+
+	pgdat_init_report_one_done();
 	return 0;
 }
 
@@ -1185,14 +1193,17 @@ void __init page_alloc_init_late(void)
 {
 	int nid;
 
+	/* There will be num_node_state(N_MEMORY) threads */
+	atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
 	for_each_node_state(nid, N_MEMORY) {
-		down_read(&pgdat_init_rwsem);
 		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
 	}
 
 	/* Block until all are initialised */
-	down_write(&pgdat_init_rwsem);
-	up_write(&pgdat_init_rwsem);
+	wait_for_completion(&pgdat_init_all_done_comp);
+
+	/* Reinit limits that are based on free pages after the kernel is up */
+	files_maxfiles_init();
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
@@ -1285,6 +1296,10 @@ static inline int check_new_page(struct page *page)
 		bad_reason = "non-NULL mapping";
 	if (unlikely(atomic_read(&page->_count) != 0))
 		bad_reason = "nonzero _count";
+	if (unlikely(page->flags & __PG_HWPOISON)) {
+		bad_reason = "HWPoisoned (hardware-corrupted)";
+		bad_flags = __PG_HWPOISON;
+	}
 	if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
 		bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
@@ -1328,12 +1343,15 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 	set_page_owner(page, order, gfp_flags);
 
 	/*
-	 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was necessary to
+	 * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
 	 * allocate the page. The expectation is that the caller is taking
 	 * steps that will free more memory. The caller should avoid the page
 	 * being used for !PFMEMALLOC purposes.
 	 */
-	page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
+	if (alloc_flags & ALLOC_NO_WATERMARKS)
+		set_page_pfmemalloc(page);
+	else
+		clear_page_pfmemalloc(page);
 
 	return 0;
 }
@@ -3330,7 +3348,7 @@ refill:
 		atomic_add(size - 1, &page->_count);
 
 		/* reset page count bias and offset to start of new frag */
-		nc->pfmemalloc = page->pfmemalloc;
+		nc->pfmemalloc = page_is_pfmemalloc(page);
 		nc->pagecnt_bias = size;
 		nc->offset = size;
 	}
@@ -5045,6 +5063,10 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
 {
 	unsigned long zone_start_pfn, zone_end_pfn;
 
+	/* When hotadd a new node, the node should be empty */
+	if (!node_start_pfn && !node_end_pfn)
+		return 0;
+
 	/* Get the start and end of the zone */
 	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
 	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
@@ -5108,6 +5130,10 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
 	unsigned long zone_start_pfn, zone_end_pfn;
 
+	/* When hotadd a new node, the node should be empty */
+	if (!node_start_pfn && !node_end_pfn)
+		return 0;
+
 	zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
 	zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
 
diff --git a/mm/page_io.c b/mm/page_io.c
index 520baa4b..b995a5b 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -33,22 +33,19 @@ static struct bio *get_swap_bio(gfp_t gfp_flags,
 	if (bio) {
 		bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
 		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
-		bio->bi_io_vec[0].bv_page = page;
-		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
-		bio->bi_io_vec[0].bv_offset = 0;
-		bio->bi_vcnt = 1;
-		bio->bi_iter.bi_size = PAGE_SIZE;
 		bio->bi_end_io = end_io;
+
+		bio_add_page(bio, page, PAGE_SIZE, 0);
+		BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE);
 	}
 	return bio;
 }
 
-void end_swap_bio_write(struct bio *bio, int err)
+void end_swap_bio_write(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		SetPageError(page);
 		/*
 		 * We failed to write the page out to swap-space.
@@ -69,12 +66,11 @@ void end_swap_bio_write(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-static void end_swap_bio_read(struct bio *bio, int err)
+static void end_swap_bio_read(struct bio *bio)
 {
-	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		SetPageError(page);
 		ClearPageUptodate(page);
 		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
@@ -254,7 +250,7 @@ static sector_t swap_page_sector(struct page *page)
 }
 
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
-	void (*end_write_func)(struct bio *, int))
+		bio_end_io_t end_write_func)
 {
 	struct bio *bio;
 	int ret, rw = WRITE;
diff --git a/mm/percpu.c b/mm/percpu.c
index 2dd7448..a63b4d8 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1668,9 +1668,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	schunk->map[1] = ai->static_size;
 	schunk->map_used = 1;
 	if (schunk->free_size)
-		schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size);
-	else
-		schunk->map[1] |= 1;
+		schunk->map[++schunk->map_used] = ai->static_size + schunk->free_size;
+	schunk->map[schunk->map_used] |= 1;
 
 	/* init dynamic chunk if necessary */
 	if (dyn_size) {
diff --git a/mm/shmem.c b/mm/shmem.c
index 4caf8ed..dbe0c1e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3363,8 +3363,8 @@ put_path:
  * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
  * 	kernel internal.  There will be NO LSM permission checks against the
  * 	underlying inode.  So users of this interface must do LSM checks at a
- * 	higher layer.  The one user is the big_key implementation.  LSM checks
- * 	are provided at the key level rather than the inode level.
+ *	higher layer.  The users are the big_key and shm implementations.  LSM
+ *	checks are provided at the key or shm level rather than the inode.
  * @name: name for dentry (to be seen in /proc/<pid>/maps
  * @size: size to be set for the file
  * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
diff --git a/mm/slab.c b/mm/slab.c
index 200e224..bbd0b47 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1603,7 +1603,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 	}
 
 	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
-	if (unlikely(page->pfmemalloc))
+	if (page_is_pfmemalloc(page))
 		pfmemalloc_active = true;
 
 	nr_pages = (1 << cachep->gfporder);
@@ -1614,7 +1614,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 		add_zone_page_state(page_zone(page),
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
 	__SetPageSlab(page);
-	if (page->pfmemalloc)
+	if (page_is_pfmemalloc(page))
 		SetPageSlabPfmemalloc(page);
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3e5f8f2..8683110 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -37,8 +37,7 @@ struct kmem_cache *kmem_cache;
 		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
 		SLAB_FAILSLAB)
 
-#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
-		SLAB_CACHE_DMA | SLAB_NOTRACK)
+#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK)
 
 /*
  * Merge control. If this is set then no merging of slab caches will occur.
diff --git a/mm/slub.c b/mm/slub.c
index 816df00..f68c0e5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1427,7 +1427,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab_cache = s;
 	__SetPageSlab(page);
-	if (page->pfmemalloc)
+	if (page_is_pfmemalloc(page))
 		SetPageSlabPfmemalloc(page);
 
 	start = page_address(page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e61445d..8286938 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -973,22 +973,18 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 *    caller can stall after page list has been processed.
 		 *
 		 * 2) Global or new memcg reclaim encounters a page that is
-		 *    not marked for immediate reclaim or the caller does not
-		 *    have __GFP_IO. In this case mark the page for immediate
+		 *    not marked for immediate reclaim, or the caller does not
+		 *    have __GFP_FS (or __GFP_IO if it's simply going to swap,
+		 *    not to fs). In this case mark the page for immediate
 		 *    reclaim and continue scanning.
 		 *
-		 *    __GFP_IO is checked  because a loop driver thread might
+		 *    Require may_enter_fs because we would wait on fs, which
+		 *    may not have submitted IO yet. And the loop driver might
 		 *    enter reclaim, and deadlock if it waits on a page for
 		 *    which it is needed to do the write (loop masks off
 		 *    __GFP_IO|__GFP_FS for this reason); but more thought
 		 *    would probably show more reasons.
 		 *
-		 *    Don't require __GFP_FS, since we're not going into the
-		 *    FS, just waiting on its writeback completion. Worryingly,
-		 *    ext4 gfs2 and xfs allocate pages with
-		 *    grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing
-		 *    may_enter_fs here is liable to OOM on them.
-		 *
 		 * 3) Legacy memcg encounters a page that is not already marked
 		 *    PageReclaim. memcg does not have any dirty pages
 		 *    throttling so we could easily OOM just because too many
@@ -1005,7 +1001,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 			/* Case 2 above */
 			} else if (sane_reclaim(sc) ||
-			    !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
+			    !PageReclaim(page) || !may_enter_fs) {
 				/*
 				 * This is slightly racy - end_page_writeback()
 				 * might have just cleared PageReclaim, then