Merge branch 'akpm-current/current'

36 files changed, 1231 insertions, 422 deletions

diff --git a/include/linux/crc64_ecma.h b/include/linux/crc64_ecma.h
new file mode 100644
index 000000000000..bba7a4d692b3
--- /dev/null
+++ b/include/linux/crc64_ecma.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __CRC64_ECMA_H_
+#define __CRC64_ECMA_H_
+
+#include <linux/types.h>
+
+
+#define CRC64_DEFAULT_INITVAL           0xFFFFFFFFFFFFFFFFULL
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * @pdata:	pointer to the data to compute checksum for.
+ * @nbytes:	number of bytes in data buffer.
+ * @seed:	CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed);
+
+#endif /* __CRC64_ECMA_H_ */
diff --git a/include/linux/dax.h b/include/linux/dax.h
new file mode 100644
index 000000000000..b415e521528d
--- /dev/null
+++ b/include/linux/dax.h
@@ -0,0 +1,39 @@
+#ifndef _LINUX_DAX_H
+#define _LINUX_DAX_H
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <asm/pgtable.h>
+
+ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
+		  get_block_t, dio_iodone_t, int flags);
+int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
+int dax_truncate_page(struct inode *, loff_t from, get_block_t);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+		dax_iodone_t);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+		dax_iodone_t);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+#else
+static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t *pmd, unsigned int flags, get_block_t gb,
+				dax_iodone_t di)
+{
+	return VM_FAULT_FALLBACK;
+}
+#define __dax_pmd_fault dax_pmd_fault
+#endif
+int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
+#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
+#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
+
+static inline bool vma_is_dax(struct vm_area_struct *vma)
+{
+	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
+}
+#endif
diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h
index e1043f79122f..53ba737505df 100644
--- a/include/linux/dmapool.h
+++ b/include/linux/dmapool.h
@@ -24,6 +24,12 @@ void dma_pool_destroy(struct dma_pool *pool);
 void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 		     dma_addr_t *handle);
 
+static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
+				    dma_addr_t *handle)
+{
+	return dma_pool_alloc(pool, mem_flags | __GFP_ZERO, handle);
+}
+
 void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr);
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b2f9b9c25e41..72d8a844c692 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -52,7 +52,6 @@ struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
 struct iov_iter;
-struct vm_fault;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -2678,19 +2677,6 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
-ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
-		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
-int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
-int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
-int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
-
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
 			    loff_t file_offset);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index ad35f300b9a4..f92cbd2f4450 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -63,7 +63,10 @@ struct vm_area_struct;
  * but it is definitely preferable to use the flag rather than opencode endless
  * loop around allocator.
  *
- * __GFP_NORETRY: The VM implementation must not retry indefinitely.
+ * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
+ * return NULL when direct reclaim and memory compaction have failed to allow
+ * the allocation to succeed.  The OOM killer is not called with the current
+ * implementation.
  *
  * __GFP_MOVABLE: Flag that this page will be movable by the page migration
  * mechanism or reclaimed
@@ -300,22 +303,31 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
 }
 
-static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
-						unsigned int order)
+/*
+ * Allocate pages, preferring the node given as nid. The node must be valid and
+ * online. For more general interface, see alloc_pages_node().
+ */
+static inline struct page *
+__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
-	/* Unknown node is current node */
-	if (nid < 0)
-		nid = numa_node_id();
+	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
+	VM_WARN_ON(!node_online(nid));
 
 	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
 }
 
-static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask,
+/*
+ * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
+ * prefer the current CPU's closest node. Otherwise node must be valid and
+ * online.
+ */
+static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 						unsigned int order)
 {
-	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid));
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
-	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
+	return __alloc_pages_node(nid, gfp_mask, order);
 }
 
 #ifdef CONFIG_NUMA
@@ -354,7 +366,6 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
 void free_pages_exact(void *virt, size_t size);
-/* This is different from alloc_pages_exact_node !!! */
 void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 #define __get_free_page(gfp_mask) \
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f10b20f05159..412013b0bf2f 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
+extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, unsigned long addr);
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr);
@@ -33,6 +36,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma,
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
 			int prot_numa);
+int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
+			unsigned long pfn, bool write);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
@@ -56,6 +61,7 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 				     unsigned long address,
 				     enum page_check_address_pmd_flag flag,
 				     spinlock_t **ptl);
+extern int pmd_freeable(pmd_t pmd);
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
@@ -122,7 +128,7 @@ extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
 #endif
 extern int hugepage_madvise(struct vm_area_struct *vma,
 			    unsigned long *vm_flags, int advice);
-extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
@@ -138,15 +144,6 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 	else
 		return 0;
 }
-static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
-					 unsigned long start,
-					 unsigned long end,
-					 long adjust_next)
-{
-	if (!vma->anon_vma || vma->vm_ops)
-		return;
-	__vma_adjust_trans_huge(vma, start, end, adjust_next);
-}
 static inline int hpage_nr_pages(struct page *page)
 {
 	if (unlikely(PageTransHuge(page)))
@@ -164,6 +161,13 @@ static inline bool is_huge_zero_page(struct page *page)
 	return ACCESS_ONCE(huge_zero_page) == page;
 }
 
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+	return is_huge_zero_page(pmd_page(pmd));
+}
+
+struct page *get_huge_zero_page(void);
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d891f949466a..329b59811159 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -35,6 +35,9 @@ struct resv_map {
 	struct kref refs;
 	spinlock_t lock;
 	struct list_head regions;
+	long adds_in_progress;
+	struct list_head region_cache;
+	long region_cache_count;
 };
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
@@ -80,11 +83,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
-void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
+long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
+						long freed);
 int dequeue_hwpoisoned_huge_page(struct page *page);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
 void free_huge_page(struct page *page);
+void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve);
+extern struct mutex *hugetlb_fault_mutex_table;
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+				struct vm_area_struct *vma,
+				struct address_space *mapping,
+				pgoff_t idx, unsigned long address);
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
@@ -320,9 +330,13 @@ struct huge_bootmem_page {
 #endif
 };
 
+struct page *alloc_huge_page(struct vm_area_struct *vma,
+				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
+int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
+			pgoff_t idx);
 
 /* arch callback */
 int __init alloc_bootmem_huge_page(struct hstate *h);
@@ -469,8 +483,28 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 #define hugepages_supported() (HPAGE_SHIFT != 0)
 #endif
 
+struct hugetlb_usage {
+	atomic_long_t count[HUGE_MAX_HSTATE];
+};
+
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm);
+void exit_hugetlb_mmap(struct mm_struct *mm);
+int hugetlb_fork(struct mm_struct *new, struct mm_struct *old);
+
+static inline void inc_hugetlb_count(struct mm_struct *mm, struct hstate *h)
+{
+	VM_BUG_ON_MM(!mm->hugetlb_usage, mm);
+	atomic_long_inc(&mm->hugetlb_usage->count[hstate_index(h)]);
+}
+
+static inline void dec_hugetlb_count(struct mm_struct *mm, struct hstate *h)
+{
+	VM_BUG_ON_MM(!mm->hugetlb_usage, mm);
+	atomic_long_dec(&mm->hugetlb_usage->count[hstate_index(h)]);
+}
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
+#define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
 #define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
@@ -504,6 +538,23 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 {
 	return &mm->page_table_lock;
 }
+
+static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
+{
+}
+
+static inline void exit_hugetlb_mmap(struct mm_struct *mm)
+{
+}
+
+static inline int hugetlb_fork(struct mm_struct *new, struct mm_struct *old)
+{
+	return 0;
+}
+
+static inline void dec_hugetlb_count(struct mm_struct *mm, struct hstate *h)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5582410727cb..45a9fdcc0844 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -10,6 +10,7 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/typecheck.h>
+#include <linux/parse-integer.h>
 #include <linux/printk.h>
 #include <linux/dynamic_debug.h>
 #include <asm/byteorder.h>
@@ -264,132 +265,10 @@ void do_exit(long error_code)
 void complete_and_exit(struct completion *, long)
 	__noreturn;
 
-/* Internal, do not use. */
-int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
-int __must_check _kstrtol(const char *s, unsigned int base, long *res);
-
-int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res);
-int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
-
-/**
- * kstrtoul - convert a string to an unsigned long
- * @s: The start of the string. The string must be null-terminated, and may also
- *  include a single newline before its terminating null. The first character
- *  may also be a plus sign, but not a minus sign.
- * @base: The number base to use. The maximum supported base is 16. If base is
- *  given as 0, then the base of the string is automatically detected with the
- *  conventional semantics - If it begins with 0x the number will be parsed as a
- *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
- *  parsed as an octal number. Otherwise it will be parsed as a decimal.
- * @res: Where to write the result of the conversion on success.
- *
- * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
- * be checked.
-*/
-static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
-{
-	/*
-	 * We want to shortcut function call, but
-	 * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0.
-	 */
-	if (sizeof(unsigned long) == sizeof(unsigned long long) &&
-	    __alignof__(unsigned long) == __alignof__(unsigned long long))
-		return kstrtoull(s, base, (unsigned long long *)res);
-	else
-		return _kstrtoul(s, base, res);
-}
-
-/**
- * kstrtol - convert a string to a long
- * @s: The start of the string. The string must be null-terminated, and may also
- *  include a single newline before its terminating null. The first character
- *  may also be a plus sign or a minus sign.
- * @base: The number base to use. The maximum supported base is 16. If base is
- *  given as 0, then the base of the string is automatically detected with the
- *  conventional semantics - If it begins with 0x the number will be parsed as a
- *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
- *  parsed as an octal number. Otherwise it will be parsed as a decimal.
- * @res: Where to write the result of the conversion on success.
- *
- * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
- * Used as a replacement for the obsolete simple_strtoull. Return code must
- * be checked.
+/*
+ * Obsolete, do not use.
+ * Use parse_integer(), kstrto*(), kstrto*_from_user(), sscanf().
  */
-static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
-{
-	/*
-	 * We want to shortcut function call, but
-	 * __builtin_types_compatible_p(long, long long) = 0.
-	 */
-	if (sizeof(long) == sizeof(long long) &&
-	    __alignof__(long) == __alignof__(long long))
-		return kstrtoll(s, base, (long long *)res);
-	else
-		return _kstrtol(s, base, res);
-}
-
-int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res);
-int __must_check kstrtoint(const char *s, unsigned int base, int *res);
-
-static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res)
-{
-	return kstrtoull(s, base, res);
-}
-
-static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res)
-{
-	return kstrtoll(s, base, res);
-}
-
-static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res)
-{
-	return kstrtouint(s, base, res);
-}
-
-static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res)
-{
-	return kstrtoint(s, base, res);
-}
-
-int __must_check kstrtou16(const char *s, unsigned int base, u16 *res);
-int __must_check kstrtos16(const char *s, unsigned int base, s16 *res);
-int __must_check kstrtou8(const char *s, unsigned int base, u8 *res);
-int __must_check kstrtos8(const char *s, unsigned int base, s8 *res);
-
-int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res);
-int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res);
-int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res);
-int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res);
-int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res);
-int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res);
-int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res);
-int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res);
-int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res);
-int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res);
-
-static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res)
-{
-	return kstrtoull_from_user(s, count, base, res);
-}
-
-static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res)
-{
-	return kstrtoll_from_user(s, count, base, res);
-}
-
-static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res)
-{
-	return kstrtouint_from_user(s, count, base, res);
-}
-
-static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res)
-{
-	return kstrtoint_from_user(s, count, base, res);
-}
-
-/* Obsolete, do not use.  Use kstrto<foo> instead */
-
 extern unsigned long simple_strtoul(const char *,char **,unsigned int);
 extern long simple_strtol(const char *,char **,unsigned int);
 extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index b63218f68c4b..2da38f093391 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -16,7 +16,7 @@
 
 #include <uapi/linux/kexec.h>
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 #include <linux/list.h>
 #include <linux/linkage.h>
 #include <linux/compat.h>
@@ -269,6 +269,8 @@ unsigned long paddr_vmcoreinfo_note(void);
 	vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
 #define VMCOREINFO_CONFIG(name) \
 	vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
+#define VMCOREINFO_PHYS_BASE(value) \
+	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
@@ -318,13 +320,24 @@ int crash_shrink_memory(unsigned long new_size);
 size_t crash_get_memory_size(void);
 void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
 
-#else /* !CONFIG_KEXEC */
+int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
+					 unsigned long buf_len);
+void * __weak arch_kexec_kernel_image_load(struct kimage *image);
+int __weak arch_kimage_file_post_load_cleanup(struct kimage *image);
+int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
+					unsigned long buf_len);
+int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
+					Elf_Shdr *sechdrs, unsigned int relsec);
+int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+					unsigned int relsec);
+
+#else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
 static inline void crash_kexec(struct pt_regs *regs) { }
 static inline int kexec_should_crash(struct task_struct *p) { return 0; }
 #define kexec_in_progress false
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* !defined(__ASSEBMLY__) */
 
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index 0555cc66a15b..fcfd2bf14d3f 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -85,8 +85,6 @@ enum umh_disable_depth {
 	UMH_DISABLED,
 };
 
-extern void usermodehelper_init(void);
-
 extern int __usermodehelper_disable(enum umh_disable_depth depth);
 extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth);
 
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index cc4b01972060..c518eb589260 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -77,6 +77,8 @@ int memblock_remove(phys_addr_t base, phys_addr_t size);
 int memblock_free(phys_addr_t base, phys_addr_t size);
 int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
+bool memblock_overlaps_region(struct memblock_type *type,
+			      phys_addr_t base, phys_addr_t size);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
@@ -323,7 +325,7 @@ void memblock_enforce_memory_limit(phys_addr_t memory_limit);
 int memblock_is_memory(phys_addr_t addr);
 int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
 int memblock_is_reserved(phys_addr_t addr);
-int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
+bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
 extern void __memblock_dump_all(void);
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 73b02b0a8f60..ad800e62cb7a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,6 +23,11 @@
 #include <linux/vm_event_item.h>
 #include <linux/hardirq.h>
 #include <linux/jump_label.h>
+#include <linux/page_counter.h>
+#include <linux/vmpressure.h>
+#include <linux/eventfd.h>
+#include <linux/mmzone.h>
+#include <linux/writeback.h>
 
 struct mem_cgroup;
 struct page;
@@ -67,12 +72,221 @@ enum mem_cgroup_events_index {
 	MEMCG_NR_EVENTS,
 };
 
+/*
+ * Per memcg event counter is incremented at every pagein/pageout. With THP,
+ * it will be incremated by the number of pages. This counter is used for
+ * for trigger some periodic events. This is straightforward and better
+ * than using jiffies etc. to handle periodic memcg event.
+ */
+enum mem_cgroup_events_target {
+	MEM_CGROUP_TARGET_THRESH,
+	MEM_CGROUP_TARGET_SOFTLIMIT,
+	MEM_CGROUP_TARGET_NUMAINFO,
+	MEM_CGROUP_NTARGETS,
+};
+
+/*
+ * Bits in struct cg_proto.flags
+ */
+enum cg_proto_flags {
+	/* Currently active and new sockets should be assigned to cgroups */
+	MEMCG_SOCK_ACTIVE,
+	/* It was ever activated; we must disarm static keys on destruction */
+	MEMCG_SOCK_ACTIVATED,
+};
+
+struct cg_proto {
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
+	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
+	int			memory_pressure;
+	long			sysctl_mem[3];
+	unsigned long		flags;
+	/*
+	 * memcg field is used to find which memcg we belong directly
+	 * Each memcg struct can hold more than one cg_proto, so container_of
+	 * won't really cut.
+	 *
+	 * The elegant solution would be having an inverse function to
+	 * proto_cgroup in struct proto, but that means polluting the structure
+	 * for everybody, instead of just for memcg users.
+	 */
+	struct mem_cgroup	*memcg;
+};
+
 #ifdef CONFIG_MEMCG
+struct mem_cgroup_stat_cpu {
+	long count[MEM_CGROUP_STAT_NSTATS];
+	unsigned long events[MEMCG_NR_EVENTS];
+	unsigned long nr_page_events;
+	unsigned long targets[MEM_CGROUP_NTARGETS];
+};
+
+struct mem_cgroup_reclaim_iter {
+	struct mem_cgroup *position;
+	/* scan generation, increased every round-trip */
+	unsigned int generation;
+};
+
+/*
+ * per-zone information in memory controller.
+ */
+struct mem_cgroup_per_zone {
+	struct lruvec		lruvec;
+	unsigned long		lru_size[NR_LRU_LISTS];
+
+	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
+
+	struct rb_node		tree_node;	/* RB tree node */
+	unsigned long		usage_in_excess;/* Set to the value by which */
+						/* the soft limit is exceeded*/
+	bool			on_tree;
+	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
+						/* use container_of	   */
+};
+
+struct mem_cgroup_per_node {
+	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
+};
+
+struct mem_cgroup_threshold {
+	struct eventfd_ctx *eventfd;
+	unsigned long threshold;
+};
+
+/* For threshold */
+struct mem_cgroup_threshold_ary {
+	/* An array index points to threshold just below or equal to usage. */
+	int current_threshold;
+	/* Size of entries[] */
+	unsigned int size;
+	/* Array of thresholds */
+	struct mem_cgroup_threshold entries[0];
+};
+
+struct mem_cgroup_thresholds {
+	/* Primary thresholds array */
+	struct mem_cgroup_threshold_ary *primary;
+	/*
+	 * Spare threshold array.
+	 * This is needed to make mem_cgroup_unregister_event() "never fail".
+	 * It must be able to store at least primary->size - 1 entries.
+	 */
+	struct mem_cgroup_threshold_ary *spare;
+};
+
+/*
+ * The memory controller data structure. The memory controller controls both
+ * page cache and RSS per cgroup. We would eventually like to provide
+ * statistics based on the statistics developed by Rik Van Riel for clock-pro,
+ * to help the administrator determine what knobs to tune.
+ */
+struct mem_cgroup {
+	struct cgroup_subsys_state css;
+
+	/* Accounted resources */
+	struct page_counter memory;
+	struct page_counter memsw;
+	struct page_counter kmem;
+
+	/* Normal memory consumption range */
+	unsigned long low;
+	unsigned long high;
+
+	unsigned long soft_limit;
+
+	/* vmpressure notifications */
+	struct vmpressure vmpressure;
+
+	/* css_online() has been completed */
+	int initialized;
+
+	/*
+	 * Should the accounting and control be hierarchical, per subtree?
+	 */
+	bool use_hierarchy;
+
+	/* protected by memcg_oom_lock */
+	bool		oom_lock;
+	int		under_oom;
+
+	int	swappiness;
+	/* OOM-Killer disable */
+	int		oom_kill_disable;
+
+	/* protect arrays of thresholds */
+	struct mutex thresholds_lock;
+
+	/* thresholds for memory usage. RCU-protected */
+	struct mem_cgroup_thresholds thresholds;
+
+	/* thresholds for mem+swap usage. RCU-protected */
+	struct mem_cgroup_thresholds memsw_thresholds;
+
+	/* For oom notifier event fd */
+	struct list_head oom_notify;
+
+	/*
+	 * Should we move charges of a task when a task is moved into this
+	 * mem_cgroup ? And what type of charges should we move ?
+	 */
+	unsigned long move_charge_at_immigrate;
+	/*
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 */
+	atomic_t		moving_account;
+	/* taken only while moving_account > 0 */
+	spinlock_t		move_lock;
+	struct task_struct	*move_lock_task;
+	unsigned long		move_lock_flags;
+	/*
+	 * percpu counter.
+	 */
+	struct mem_cgroup_stat_cpu __percpu *stat;
+	spinlock_t pcp_counter_lock;
+
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
+	struct cg_proto tcp_mem;
+#endif
+#if defined(CONFIG_MEMCG_KMEM)
+        /* Index in the kmem_cache->memcg_params.memcg_caches array */
+	int kmemcg_id;
+	bool kmem_acct_activated;
+	bool kmem_acct_active;
+#endif
+
+	int last_scanned_node;
+#if MAX_NUMNODES > 1
+	nodemask_t	scan_nodes;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
+#endif
+
+#ifdef CONFIG_CGROUP_WRITEBACK
+	struct list_head cgwb_list;
+	struct wb_domain cgwb_domain;
+#endif
+
+	/* List of events which userspace want to receive */
+	struct list_head event_list;
+	spinlock_t event_list_lock;
+
+	struct mem_cgroup_per_node *nodeinfo[0];
+	/* WARNING: nodeinfo must be the last member here */
+};
 extern struct cgroup_subsys_state *mem_cgroup_root_css;
 
-void mem_cgroup_events(struct mem_cgroup *memcg,
+/**
+ * mem_cgroup_events - count memory events against a cgroup
+ * @memcg: the memory cgroup
+ * @idx: the event index
+ * @nr: the number of events to account for
+ */
+static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 		       enum mem_cgroup_events_index idx,
-		       unsigned int nr);
+		       unsigned int nr)
+{
+	this_cpu_add(memcg->stat->events[idx], nr);
+}
 
 bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
 
@@ -90,15 +304,29 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
-bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
-			      struct mem_cgroup *root);
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
+struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 
-extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
-extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+static inline
+struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
+	return css ? container_of(css, struct mem_cgroup, css) : NULL;
+}
 
-extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
-extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
+				   struct mem_cgroup *,
+				   struct mem_cgroup_reclaim_cookie *);
+void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
+
+static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
+			      struct mem_cgroup *root)
+{
+	if (root == memcg)
+		return true;
+	if (!root->use_hierarchy)
+		return false;
+	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
+}
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 				   struct mem_cgroup *memcg)
@@ -114,24 +342,68 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	return match;
 }
 
-extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
-extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
+struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
+ino_t page_cgroup_ino(struct page *page);
 
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
-				   struct mem_cgroup *,
-				   struct mem_cgroup_reclaim_cookie *);
-void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
+static inline bool mem_cgroup_disabled(void)
+{
+	if (memory_cgrp_subsys.disabled)
+		return true;
+	return false;
+}
 
 /*
  * For memory reclaim.
  */
-int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec);
-bool mem_cgroup_lruvec_online(struct lruvec *lruvec);
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
-unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
-void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
-extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
-					struct task_struct *p);
+
+void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
+		int nr_pages);
+
+static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+{
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return true;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	memcg = mz->memcg;
+
+	return !!(memcg->css.flags & CSS_ONLINE);
+}
+
+static inline
+unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
+{
+	struct mem_cgroup_per_zone *mz;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	return mz->lru_size[lru];
+}
+
+static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
+{
+	unsigned long inactive_ratio;
+	unsigned long inactive;
+	unsigned long active;
+	unsigned long gb;
+
+	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
+	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);
+
+	gb = (inactive + active) >> (30 - PAGE_SHIFT);
+	if (gb)
+		inactive_ratio = int_sqrt(10 * gb);
+	else
+		inactive_ratio = 1;
+
+	return inactive * inactive_ratio < active;
+}
+
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+				struct task_struct *p);
 
 static inline void mem_cgroup_oom_enable(void)
 {
@@ -156,18 +428,26 @@ bool mem_cgroup_oom_synchronize(bool wait);
 extern int do_swap_account;
 #endif
 
-static inline bool mem_cgroup_disabled(void)
-{
-	if (memory_cgrp_subsys.disabled)
-		return true;
-	return false;
-}
-
 struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
-void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx, int val);
 void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
 
+/**
+ * mem_cgroup_update_page_stat - update page state statistics
+ * @memcg: memcg to account against
+ * @idx: page state item to account
+ * @val: number of pages (positive or negative)
+ *
+ * See mem_cgroup_begin_page_stat() for locking requirements.
+ */
+static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
+				 enum mem_cgroup_stat_index idx, int val)
+{
+	VM_BUG_ON(!rcu_read_lock_held());
+
+	if (memcg)
+		this_cpu_add(memcg->stat->count[idx], val);
+}
+
 static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
 					    enum mem_cgroup_stat_index idx)
 {
@@ -184,13 +464,31 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
-void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 					     enum vm_event_item idx)
 {
+	struct mem_cgroup *memcg;
+
 	if (mem_cgroup_disabled())
 		return;
-	__mem_cgroup_count_vm_event(mm, idx);
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!memcg))
+		goto out;
+
+	switch (idx) {
+	case PGFAULT:
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
+		break;
+	case PGMAJFAULT:
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
+		break;
+	default:
+		BUG();
+	}
+out:
+	rcu_read_unlock();
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
@@ -199,8 +497,6 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
-#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
-
 static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 				     enum mem_cgroup_events_index idx,
 				     unsigned int nr)
@@ -258,11 +554,6 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 	return &zone->lruvec;
 }
 
-static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
-{
-	return NULL;
-}
-
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 		struct mem_cgroup *memcg)
 {
@@ -275,12 +566,6 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
-static inline struct cgroup_subsys_state
-		*mem_cgroup_css(struct mem_cgroup *memcg)
-{
-	return NULL;
-}
-
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -428,8 +713,8 @@ static inline void sock_release_memcg(struct sock *sk)
 extern struct static_key memcg_kmem_enabled_key;
 
 extern int memcg_nr_cache_ids;
-extern void memcg_get_cache_ids(void);
-extern void memcg_put_cache_ids(void);
+void memcg_get_cache_ids(void);
+void memcg_put_cache_ids(void);
 
 /*
  * Helper macro to loop through all memcg-specific caches. Callers must still
@@ -444,7 +729,10 @@ static inline bool memcg_kmem_enabled(void)
 	return static_key_false(&memcg_kmem_enabled_key);
 }
 
-bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+	return memcg->kmem_acct_active;
+}
 
 /*
  * In general, we'll do everything in our power to not incur in any overhead
@@ -463,7 +751,15 @@ void __memcg_kmem_commit_charge(struct page *page,
 				       struct mem_cgroup *memcg, int order);
 void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
-int memcg_cache_id(struct mem_cgroup *memcg);
+/*
+ * helper for acessing a memcg's index. It will be used as an index in the
+ * child cache array in kmem_cache, and also to derive its name. This function
+ * will return -1 when this is not a kmem-limited memcg.
+ */
+static inline int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return memcg ? memcg->kmemcg_id : -1;
+}
 
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2c92ac098a93..9dd5da678005 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -139,6 +139,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
+#define VM_LOCKONFAULT	0x00080000	/* Lock the pages covered when they are faulted in */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
@@ -250,6 +251,8 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
+						pmd_t *, unsigned int flags);
 	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
@@ -308,18 +311,6 @@ struct inode;
 #define page_private(page)		((page)->private)
 #define set_page_private(page, v)	((page)->private = (v))
 
-/* It's valid only if the page is free path or free_list */
-static inline void set_freepage_migratetype(struct page *page, int migratetype)
-{
-	page->index = migratetype;
-}
-
-/* It's valid only if the page is free path or free_list */
-static inline int get_freepage_migratetype(struct page *page)
-{
-	return page->index;
-}
-
 /*
  * FIXME: take this include out, include page-flags.h in
  * files which need it (119 of them)
@@ -360,18 +351,6 @@ static inline int get_page_unless_zero(struct page *page)
 	return atomic_inc_not_zero(&page->_count);
 }
 
-/*
- * Try to drop a ref unless the page has a refcount of one, return false if
- * that is the case.
- * This is to make sure that the refcount won't become zero after this drop.
- * This can be called when MMU is off so it must not access
- * any of the virtual mappings.
- */
-static inline int put_page_unless_one(struct page *page)
-{
-	return atomic_add_unless(&page->_count, -1, 1);
-}
-
 extern int page_is_ram(unsigned long pfn);
 
 enum {
@@ -448,46 +427,6 @@ static inline void compound_unlock_irqrestore(struct page *page,
 #endif
 }
 
-static inline struct page *compound_head_by_tail(struct page *tail)
-{
-	struct page *head = tail->first_page;
-
-	/*
-	 * page->first_page may be a dangling pointer to an old
-	 * compound page, so recheck that it is still a tail
-	 * page before returning.
-	 */
-	smp_rmb();
-	if (likely(PageTail(tail)))
-		return head;
-	return tail;
-}
-
-/*
- * Since either compound page could be dismantled asynchronously in THP
- * or we access asynchronously arbitrary positioned struct page, there
- * would be tail flag race. To handle this race, we should call
- * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
- */
-static inline struct page *compound_head(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return compound_head_by_tail(page);
-	return page;
-}
-
-/*
- * If we access compound page synchronously such as access to
- * allocated page, there is no need to handle tail flag race, so we can
- * check tail flag directly without any synchronization primitive.
- */
-static inline struct page *compound_head_fast(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return page->first_page;
-	return page;
-}
-
 /*
  * The atomic page->_mapcount, starts from -1: so that transitions
  * both from it and to it can be tracked, using atomic_inc_and_test
@@ -1311,6 +1250,11 @@ static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
 	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
 }
 
+static inline bool vma_is_anonymous(struct vm_area_struct *vma)
+{
+	return !vma->vm_ops;
+}
+
 static inline int stack_guard_page_start(struct vm_area_struct *vma,
 					     unsigned long addr)
 {
@@ -2125,6 +2069,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
+#define FOLL_MLOCK	0x1000	/* lock present pages */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
@@ -2237,6 +2182,7 @@ extern int memory_failure(unsigned long pfn, int trapno, int flags);
 extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
 extern int unpoison_memory(unsigned long pfn);
 extern int get_hwpoison_page(struct page *page);
+extern void put_hwpoison_page(struct page *page);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index c8d0a73d64c4..3d85b27a389c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -235,7 +235,7 @@ struct page_frag_cache {
 	bool pfmemalloc;
 };
 
-typedef unsigned long __nocast vm_flags_t;
+typedef unsigned long vm_flags_t;
 
 /*
  * A region containing a mapping of a non-memory backed file under NOMMU
@@ -366,6 +366,10 @@ struct mm_rss_stat {
 	atomic_long_t count[NR_MM_COUNTERS];
 };
 
+#ifdef CONFIG_HUGETLB_PAGE
+struct hugetlb_usage;
+#endif
+
 struct kioctx_table;
 struct mm_struct {
 	struct vm_area_struct *mmap;		/* list of VMAs */
@@ -486,6 +490,9 @@ struct mm_struct {
 	/* address of the bounds directory */
 	void __user *bd_addr;
 #endif
+#ifdef CONFIG_HUGETLB_PAGE
+	struct hugetlb_usage *hugetlb_usage;
+#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 61cd67f4d788..a1a210d59961 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -66,6 +66,16 @@ struct mmu_notifier_ops {
 				 unsigned long end);
 
 	/*
+	 * clear_young is a lightweight version of clear_flush_young. Like the
+	 * latter, it is supposed to test-and-clear the young/accessed bitflag
+	 * in the secondary pte, but it may omit flushing the secondary tlb.
+	 */
+	int (*clear_young)(struct mmu_notifier *mn,
+			   struct mm_struct *mm,
+			   unsigned long start,
+			   unsigned long end);
+
+	/*
 	 * test_young is called to check the young/accessed bitflag in
 	 * the secondary pte. This is used to know if the page is
 	 * frequently used without actually clearing the flag or tearing
@@ -203,6 +213,9 @@ extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					  unsigned long start,
 					  unsigned long end);
+extern int __mmu_notifier_clear_young(struct mm_struct *mm,
+				      unsigned long start,
+				      unsigned long end);
 extern int __mmu_notifier_test_young(struct mm_struct *mm,
 				     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,
@@ -231,6 +244,15 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
 	return 0;
 }
 
+static inline int mmu_notifier_clear_young(struct mm_struct *mm,
+					   unsigned long start,
+					   unsigned long end)
+{
+	if (mm_has_notifiers(mm))
+		return __mmu_notifier_clear_young(mm, start, end);
+	return 0;
+}
+
 static inline int mmu_notifier_test_young(struct mm_struct *mm,
 					  unsigned long address)
 {
@@ -311,6 +333,28 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	__young;							\
 })
 
+#define ptep_clear_young_notify(__vma, __address, __ptep)		\
+({									\
+	int __young;							\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	__young = ptep_test_and_clear_young(___vma, ___address, __ptep);\
+	__young |= mmu_notifier_clear_young(___vma->vm_mm, ___address,	\
+					    ___address + PAGE_SIZE);	\
+	__young;							\
+})
+
+#define pmdp_clear_young_notify(__vma, __address, __pmdp)		\
+({									\
+	int __young;							\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	__young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\
+	__young |= mmu_notifier_clear_young(___vma->vm_mm, ___address,	\
+					    ___address + PMD_SIZE);	\
+	__young;							\
+})
+
 #define	ptep_clear_flush_notify(__vma, __address, __ptep)		\
 ({									\
 	unsigned long ___addr = __address & PAGE_MASK;			\
@@ -427,6 +471,8 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 
 #define ptep_clear_flush_young_notify ptep_clear_flush_young
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
+#define ptep_clear_young_notify ptep_test_and_clear_young
+#define pmdp_clear_young_notify pmdp_test_and_clear_young
 #define	ptep_clear_flush_notify ptep_clear_flush
 #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
 #define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 7deecb7bca5e..03e6257321f0 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -13,6 +13,27 @@ struct mem_cgroup;
 struct task_struct;
 
 /*
+ * Details of the page allocation that triggered the oom killer that are used to
+ * determine what should be killed.
+ */
+struct oom_control {
+	/* Used to determine cpuset */
+	struct zonelist *zonelist;
+
+	/* Used to determine mempolicy */
+	nodemask_t *nodemask;
+
+	/* Used to determine cpuset and node locality requirement */
+	const gfp_t gfp_mask;
+
+	/*
+	 * order == -1 means the oom kill is required by sysrq, otherwise only
+	 * for display purposes.
+	 */
+	const int order;
+};
+
+/*
  * Types of limitations to the nodes from which allocations may occur
  */
 enum oom_constraint {
@@ -57,21 +78,18 @@ extern unsigned long oom_badness(struct task_struct *p,
 
 extern int oom_kills_count(void);
 extern void note_oom_kill(void);
-extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+extern void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 			     unsigned int points, unsigned long totalpages,
-			     struct mem_cgroup *memcg, nodemask_t *nodemask,
-			     const char *message);
+			     struct mem_cgroup *memcg, const char *message);
 
-extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-			       int order, const nodemask_t *nodemask,
+extern void check_panic_on_oom(struct oom_control *oc,
+			       enum oom_constraint constraint,
 			       struct mem_cgroup *memcg);
 
-extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
-		unsigned long totalpages, const nodemask_t *nodemask,
-		bool force_kill);
+extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc,
+		struct task_struct *task, unsigned long totalpages);
 
-extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *mask, bool force_kill);
+extern bool out_of_memory(struct oom_control *oc);
 
 extern void exit_oom_victim(void);
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 41c93844fb1d..4de152cd01b5 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -109,6 +109,10 @@ enum pageflags {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	PG_compound_lock,
 #endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+	PG_young,
+	PG_idle,
+#endif
 	__NR_PAGEFLAGS,
 
 	/* Filesystems */
@@ -134,49 +138,68 @@ enum pageflags {
 
 #ifndef __GENERATING_BOUNDS_H
 
+/* Page flags policies wrt compound pages */
+#define PF_ANY(page, enforce)	page
+#define PF_HEAD(page, enforce)	compound_head(page)
+#define PF_NO_TAIL(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageTail(page), page);		\
+		else							\
+			page = compound_head(page);			\
+		page;})
+#define PF_NO_COMPOUND(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageCompound(page), page);	\
+		page;})
+
 /*
  * Macros to create function definitions for page flags
  */
-#define TESTPAGEFLAG(uname, lname)					\
-static inline int Page##uname(const struct page *page)			\
-			{ return test_bit(PG_##lname, &page->flags); }
+#define TESTPAGEFLAG(uname, lname, policy)				\
+static inline int Page##uname(struct page *page)			\
+	{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
 
-#define SETPAGEFLAG(uname, lname)					\
+#define SETPAGEFLAG(uname, lname, policy)				\
 static inline void SetPage##uname(struct page *page)			\
-			{ set_bit(PG_##lname, &page->flags); }
+	{ set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define CLEARPAGEFLAG(uname, lname)					\
+#define CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void ClearPage##uname(struct page *page)			\
-			{ clear_bit(PG_##lname, &page->flags); }
+	{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __SETPAGEFLAG(uname, lname)					\
+#define __SETPAGEFLAG(uname, lname, policy)				\
 static inline void __SetPage##uname(struct page *page)			\
-			{ __set_bit(PG_##lname, &page->flags); }
+	{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __CLEARPAGEFLAG(uname, lname)					\
+#define __CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void __ClearPage##uname(struct page *page)		\
-			{ __clear_bit(PG_##lname, &page->flags); }
+	{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTSETFLAG(uname, lname)					\
+#define TESTSETFLAG(uname, lname, policy)				\
 static inline int TestSetPage##uname(struct page *page)			\
-		{ return test_and_set_bit(PG_##lname, &page->flags); }
+	{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTCLEARFLAG(uname, lname)					\
+#define TESTCLEARFLAG(uname, lname, policy)				\
 static inline int TestClearPage##uname(struct page *page)		\
-		{ return test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __TESTCLEARFLAG(uname, lname)					\
+#define __TESTCLEARFLAG(uname, lname, policy)				\
 static inline int __TestClearPage##uname(struct page *page)		\
-		{ return __test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return __test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname)
+#define PAGEFLAG(uname, lname, policy)					\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	SETPAGEFLAG(uname, lname, policy)				\
+	CLEARPAGEFLAG(uname, lname, policy)
 
-#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	__SETPAGEFLAG(uname, lname)  __CLEARPAGEFLAG(uname, lname)
+#define __PAGEFLAG(uname, lname, policy)				\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	__SETPAGEFLAG(uname, lname, policy)				\
+	__CLEARPAGEFLAG(uname, lname, policy)
 
-#define TESTSCFLAG(uname, lname)					\
-	TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
+#define TESTSCFLAG(uname, lname, policy)				\
+	TESTSETFLAG(uname, lname, policy)				\
+	TESTCLEARFLAG(uname, lname, policy)
 
 #define TESTPAGEFLAG_FALSE(uname)					\
 static inline int Page##uname(const struct page *page) { return 0; }
@@ -205,47 +228,100 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; }
 #define TESTSCFLAG_FALSE(uname)						\
 	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
 
-struct page;	/* forward declaration */
-
-TESTPAGEFLAG(Locked, locked)
-PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error)
-PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
-	__SETPAGEFLAG(Referenced, referenced)
-PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
-PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
-PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
-	TESTCLEARFLAG(Active, active)
-__PAGEFLAG(Slab, slab)
-PAGEFLAG(Checked, checked)		/* Used by some filesystems */
-PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
-PAGEFLAG(SavePinned, savepinned);			/* Xen */
-PAGEFLAG(Foreign, foreign);				/* Xen */
-PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
-	__SETPAGEFLAG(SwapBacked, swapbacked)
-
-__PAGEFLAG(SlobFree, slob_free)
+/* Forward declarations */
+struct page;
+static inline int PageCompound(struct page *page);
+static inline int PageTail(struct page *page);
+
+static inline struct page *compound_head_by_tail(struct page *tail)
+{
+	struct page *head = tail->first_page;
+
+	/*
+	 * page->first_page may be a dangling pointer to an old
+	 * compound page, so recheck that it is still a tail
+	 * page before returning.
+	 */
+	smp_rmb();
+	if (likely(PageTail(tail)))
+		return head;
+	return tail;
+}
+
+/*
+ * Since either compound page could be dismantled asynchronously in THP
+ * or we access asynchronously arbitrary positioned struct page, there
+ * would be tail flag race. To handle this race, we should call
+ * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
+ */
+static inline struct page *compound_head(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		return compound_head_by_tail(page);
+	return page;
+}
+
+/*
+ * If we access compound page synchronously such as access to
+ * allocated page, there is no need to handle tail flag race, so we can
+ * check tail flag directly without any synchronization primitive.
+ */
+static inline struct page *compound_head_fast(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		return page->first_page;
+	return page;
+}
+
+__PAGEFLAG(Locked, locked, PF_NO_TAIL)
+PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
+PAGEFLAG(Referenced, referenced, PF_HEAD)
+	TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
+	__SETPAGEFLAG(Referenced, referenced, PF_HEAD)
+PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
+	__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
+PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
+PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
+	TESTCLEARFLAG(Active, active, PF_HEAD)
+__PAGEFLAG(Slab, slab, PF_NO_TAIL)
+__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL)
+PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */
+
+/* Xen */
+PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND)
+PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND)
+PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND)
+
+PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
+	__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
+PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
+	__CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
+	__SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
 
 /*
  * Private page markings that may be used by the filesystem that owns the page
  * for its own purposes.
  * - PG_private and PG_private_2 cause releasepage() and co to be invoked
  */
-PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
-	__CLEARPAGEFLAG(Private, private)
-PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
-PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY)
+	__CLEARPAGEFLAG(Private, private, PF_ANY)
+PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
+PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
+	TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
 
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
-TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-PAGEFLAG(MappedToDisk, mappedtodisk)
+TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND)
+	TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND)
+PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_COMPOUND)
 
 /* PG_readahead is only used for reads; PG_reclaim is only for writes */
-PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
-PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim)
+PAGEFLAG(Reclaim, reclaim, PF_NO_COMPOUND)
+	TESTCLEARFLAG(Reclaim, reclaim, PF_NO_COMPOUND)
+PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
+	TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND)
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -258,37 +334,46 @@ PAGEFLAG_FALSE(HighMem)
 #endif
 
 #ifdef CONFIG_SWAP
-PAGEFLAG(SwapCache, swapcache)
+PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
 
-PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
-	TESTCLEARFLAG(Unevictable, unevictable)
+PAGEFLAG(Unevictable, unevictable, PF_HEAD)
+	__CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD)
+	TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD)
 
 #ifdef CONFIG_MMU
-PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked)
-	TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked)
+PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
+	TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL)
+	__TESTCLEARFLAG(Mlocked, mlocked, PF_NO_TAIL)
 #else
 PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
 	TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
 #endif
 
 #ifdef CONFIG_ARCH_USES_PG_UNCACHED
-PAGEFLAG(Uncached, uncached)
+PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(Uncached)
 #endif
 
 #ifdef CONFIG_MEMORY_FAILURE
-PAGEFLAG(HWPoison, hwpoison)
-TESTSCFLAG(HWPoison, hwpoison)
+PAGEFLAG(HWPoison, hwpoison, PF_ANY)
+TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 #else
 PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif
 
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+TESTPAGEFLAG(Young, young, PF_ANY)
+SETPAGEFLAG(Young, young, PF_ANY)
+TESTCLEARFLAG(Young, young, PF_ANY)
+PAGEFLAG(Idle, idle, PF_ANY)
+#endif
+
 /*
  * On an anonymous page mapped into a user virtual memory area,
  * page->mapping points to its anon_vma, not to a struct address_space;
@@ -311,6 +396,7 @@ PAGEFLAG_FALSE(HWPoison)
 
 static inline int PageAnon(struct page *page)
 {
+	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
 }
 
@@ -323,6 +409,7 @@ static inline int PageAnon(struct page *page)
  */
 static inline int PageKsm(struct page *page)
 {
+	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
 				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
 }
@@ -334,8 +421,9 @@ u64 stable_page_flags(struct page *page);
 
 static inline int PageUptodate(struct page *page)
 {
-	int ret = test_bit(PG_uptodate, &(page)->flags);
-
+	int ret;
+	page = compound_head(page);
+	ret = test_bit(PG_uptodate, &(page)->flags);
 	/*
 	 * Must ensure that the data we read out of the page is loaded
 	 * _after_ we've loaded page->flags to check for PageUptodate.
@@ -352,22 +440,24 @@ static inline int PageUptodate(struct page *page)
 
 static inline void __SetPageUptodate(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	smp_wmb();
-	__set_bit(PG_uptodate, &(page)->flags);
+	__set_bit(PG_uptodate, &page->flags);
 }
 
 static inline void SetPageUptodate(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	/*
 	 * Memory barrier must be issued before setting the PG_uptodate bit,
 	 * so that all previous stores issued in order to bring the page
 	 * uptodate are actually visible before PageUptodate becomes true.
 	 */
 	smp_wmb();
-	set_bit(PG_uptodate, &(page)->flags);
+	set_bit(PG_uptodate, &page->flags);
 }
 
-CLEARPAGEFLAG(Uptodate, uptodate)
+CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
 
 int test_clear_page_writeback(struct page *page);
 int __test_set_page_writeback(struct page *page, bool keep_write);
@@ -396,8 +486,8 @@ static inline void set_page_writeback_keepwrite(struct page *page)
  * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
  * and avoid handling those in real mode.
  */
-__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
-__PAGEFLAG(Tail, tail)
+__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
+__PAGEFLAG(Tail, tail, PF_ANY)
 
 static inline int PageCompound(struct page *page)
 {
@@ -421,8 +511,8 @@ static inline void ClearPageCompound(struct page *page)
  * because PageCompound is always set for compound pages and not for
  * pages on the LRU and/or pagecache.
  */
-TESTPAGEFLAG(Compound, compound)
-__SETPAGEFLAG(Head, compound)  __CLEARPAGEFLAG(Head, compound)
+TESTPAGEFLAG(Compound, compound, PF_ANY)
+__SETPAGEFLAG(Head, compound, PF_ANY)  __CLEARPAGEFLAG(Head, compound, PF_ANY)
 
 /*
  * PG_reclaim is used in combination with PG_compound to mark the
@@ -518,21 +608,9 @@ static inline int PageTransTail(struct page *page)
 }
 
 #else
-
-static inline int PageTransHuge(struct page *page)
-{
-	return 0;
-}
-
-static inline int PageTransCompound(struct page *page)
-{
-	return 0;
-}
-
-static inline int PageTransTail(struct page *page)
-{
-	return 0;
-}
+TESTPAGEFLAG_FALSE(TransHuge)
+TESTPAGEFLAG_FALSE(TransCompound)
+TESTPAGEFLAG_FALSE(TransTail)
 #endif
 
 /*
@@ -659,6 +737,10 @@ static inline int page_has_private(struct page *page)
 	return !!(page->flags & PAGE_FLAGS_PRIVATE);
 }
 
+#undef PF_ANY
+#undef PF_HEAD
+#undef PF_NO_TAIL
+#undef PF_NO_COMPOUND
 #endif /* !__GENERATING_BOUNDS_H */
 
 #endif	/* PAGE_FLAGS_H */
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 2dc1e1697b45..047d64706f2a 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -65,11 +65,6 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 			bool skip_hwpoisoned_pages);
 
-/*
- * Internal functions. Changes pageblock's migrate type.
- */
-int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages);
-void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 struct page *alloc_migrate_target(struct page *page, unsigned long private,
 				int **resultp);
 
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index c42981cd99aa..17f118a82854 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -26,6 +26,10 @@ enum page_ext_flags {
 	PAGE_EXT_DEBUG_POISON,		/* Page is poisoned */
 	PAGE_EXT_DEBUG_GUARD,
 	PAGE_EXT_OWNER,
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+	PAGE_EXT_YOUNG,
+	PAGE_EXT_IDLE,
+#endif
 };
 
 /*
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
new file mode 100644
index 000000000000..bf268fa92c5b
--- /dev/null
+++ b/include/linux/page_idle.h
@@ -0,0 +1,110 @@
+#ifndef _LINUX_MM_PAGE_IDLE_H
+#define _LINUX_MM_PAGE_IDLE_H
+
+#include <linux/bitops.h>
+#include <linux/page-flags.h>
+#include <linux/page_ext.h>
+
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+
+#ifdef CONFIG_64BIT
+static inline bool page_is_young(struct page *page)
+{
+	return PageYoung(page);
+}
+
+static inline void set_page_young(struct page *page)
+{
+	SetPageYoung(page);
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+	return TestClearPageYoung(page);
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+	return PageIdle(page);
+}
+
+static inline void set_page_idle(struct page *page)
+{
+	SetPageIdle(page);
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+	ClearPageIdle(page);
+}
+#else /* !CONFIG_64BIT */
+/*
+ * If there is not enough space to store Idle and Young bits in page flags, use
+ * page ext flags instead.
+ */
+extern struct page_ext_operations page_idle_ops;
+
+static inline bool page_is_young(struct page *page)
+{
+	return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+}
+
+static inline void set_page_young(struct page *page)
+{
+	set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+	return test_and_clear_bit(PAGE_EXT_YOUNG,
+				  &lookup_page_ext(page)->flags);
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+	return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+
+static inline void set_page_idle(struct page *page)
+{
+	set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+	clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+#endif /* CONFIG_64BIT */
+
+#else /* !CONFIG_IDLE_PAGE_TRACKING */
+
+static inline bool page_is_young(struct page *page)
+{
+	return false;
+}
+
+static inline void set_page_young(struct page *page)
+{
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+	return false;
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+	return false;
+}
+
+static inline void set_page_idle(struct page *page)
+{
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+}
+
+#endif /* CONFIG_IDLE_PAGE_TRACKING */
+
+#endif /* _LINUX_MM_PAGE_IDLE_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a6c78e00ea96..3e95fb6a77af 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -426,18 +426,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
 
-static inline void __set_page_locked(struct page *page)
-{
-	__set_bit(PG_locked, &page->flags);
-}
-
-static inline void __clear_page_locked(struct page *page)
-{
-	__clear_bit(PG_locked, &page->flags);
-}
-
 static inline int trylock_page(struct page *page)
 {
+	page = compound_head(page);
 	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
 }
 
@@ -490,9 +481,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page,
 
 static inline int wait_on_page_locked_killable(struct page *page)
 {
-	if (PageLocked(page))
-		return wait_on_page_bit_killable(page, PG_locked);
-	return 0;
+	if (!PageLocked(page))
+		return 0;
+	return wait_on_page_bit_killable(compound_head(page), PG_locked);
 }
 
 extern wait_queue_head_t *page_waitqueue(struct page *page);
@@ -511,7 +502,7 @@ static inline void wake_up_page(struct page *page, int bit)
 static inline void wait_on_page_locked(struct page *page)
 {
 	if (PageLocked(page))
-		wait_on_page_bit(page, PG_locked);
+		wait_on_page_bit(compound_head(page), PG_locked);
 }
 
 /* 
@@ -657,17 +648,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
- * the page is new, so we can just run __set_page_locked() against it.
+ * the page is new, so we can just run __SetPageLocked() against it.
  */
 static inline int add_to_page_cache(struct page *page,
 		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
 {
 	int error;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
 	if (unlikely(error))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	return error;
 }
 
diff --git a/include/linux/parse-integer.h b/include/linux/parse-integer.h
new file mode 100644
index 000000000000..ba620cdf3df6
--- /dev/null
+++ b/include/linux/parse-integer.h
@@ -0,0 +1,188 @@
+#ifndef _PARSE_INTEGER_H
+#define _PARSE_INTEGER_H
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+/*
+ * int parse_integer(const char *s, unsigned int base, T *val);
+ *
+ * Convert integer string representation to an integer.
+ * Range of accepted values equals to that of type T.
+ *
+ * Conversion to unsigned integer accepts sign "+".
+ * Conversion to signed integer accepts sign "+" and sign "-".
+ *
+ * Radix 0 means autodetection: leading "0x" implies radix 16,
+ * leading "0" implies radix 8, otherwise radix is 10.
+ * Autodetection hint works after optional sign, but not before.
+ *
+ * Return number of characters parsed or -E.
+ *
+ * "T=char" case is not supported because -f{un,}signed-char can silently
+ * change range of accepted values.
+ */
+#define parse_integer(s, base, val)	\
+({					\
+	const char *_s = (s);		\
+	unsigned int _base = (base);	\
+	typeof(&(val)[0]) _val = (val);	\
+					\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), signed char *),	\
+	_parse_integer_sc(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), unsigned char *),	\
+	_parse_integer_uc(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), short *),		\
+	_parse_integer_s(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), unsigned short *),	\
+	_parse_integer_us(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), int *),		\
+	_parse_integer_i(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), unsigned int *),	\
+	_parse_integer_u(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), long *) && sizeof(long) == 4,\
+	_parse_integer_i(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), long *) && sizeof(long) == 8,\
+	_parse_integer_ll(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), unsigned long *) && sizeof(unsigned long) == 4,\
+	_parse_integer_u(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), unsigned long *) && sizeof(unsigned long) == 8,\
+	_parse_integer_ull(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), long long *),	\
+	_parse_integer_ll(_s, _base, (void *)_val),			\
+	__builtin_choose_expr(						\
+	__builtin_types_compatible_p(typeof(_val), unsigned long long *),\
+	_parse_integer_ull(_s, _base, (void *)_val),			\
+	_parse_integer_link_time_error()))))))))))));	\
+})
+/* internal, do not use */
+int _parse_integer_sc(const char *s, unsigned int base, signed char *val);
+int _parse_integer_uc(const char *s, unsigned int base, unsigned char *val);
+int _parse_integer_s(const char *s, unsigned int base, short *val);
+int _parse_integer_us(const char *s, unsigned int base, unsigned short *val);
+int _parse_integer_i(const char *s, unsigned int base, int *val);
+int _parse_integer_u(const char *s, unsigned int base, unsigned int *val);
+int _parse_integer_ll(const char *s, unsigned int base, long long *val);
+int _parse_integer_ull(const char *s, unsigned int base, unsigned long long *val);
+void _parse_integer_link_time_error(void);
+const char *_parse_integer_fixup_radix(const char *s, unsigned int *base);
+#define PARSE_INTEGER_NEWLINE 0x80000000u
+
+/*
+ * Convert integer string representation terminated by \n\0 or \0 to an integer.
+ *
+ * Return 0 on success or -E.
+ *
+ * See parse_integer().
+ */
+static inline int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtoll(const char *s, unsigned int base, long long *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtoint(const char *s, unsigned int base, int *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res)
+{
+	return kstrtoull(s, base, res);
+}
+
+static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res)
+{
+	return kstrtoll(s, base, res);
+}
+
+static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res)
+{
+	return kstrtouint(s, base, res);
+}
+
+static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res)
+{
+	return kstrtoint(s, base, res);
+}
+
+static inline int __must_check kstrtou16(const char *s, unsigned int base, u16 *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtos16(const char *s, unsigned int base, s16 *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtou8(const char *s, unsigned int base, u8 *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+static inline int __must_check kstrtos8(const char *s, unsigned int base, s8 *res)
+{
+	return parse_integer(s, base | PARSE_INTEGER_NEWLINE, res);
+}
+
+int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res);
+int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res);
+int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res);
+int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res);
+int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res);
+int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res);
+int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res);
+int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res);
+int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res);
+int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res);
+
+static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res)
+{
+	return kstrtoull_from_user(s, count, base, res);
+}
+
+static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res)
+{
+	return kstrtoll_from_user(s, count, base, res);
+}
+
+static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res)
+{
+	return kstrtouint_from_user(s, count, base, res);
+}
+
+static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res)
+{
+	return kstrtoint_from_user(s, count, base, res);
+}
+#endif
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 1a64733c48c7..e90eb22de628 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1227,6 +1227,8 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 		dma_pool_create(name, &pdev->dev, size, align, allocation)
 #define	pci_pool_destroy(pool) dma_pool_destroy(pool)
 #define	pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle)
+#define	pci_pool_zalloc(pool, flags, handle) \
+		dma_pool_zalloc(pool, flags, handle)
 #define	pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr)
 
 struct msix_entry {
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 2110a81c5e2a..4a27153574e2 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -19,19 +19,23 @@
  * under normal circumstances, used to verify that nobody uses
  * non-initialized list entries.
  */
-#define LIST_POISON1  ((void *) 0x00100100 + POISON_POINTER_DELTA)
-#define LIST_POISON2  ((void *) 0x00200200 + POISON_POINTER_DELTA)
+#define LIST_POISON1  ((void *) 0x100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void *) 0x200 + POISON_POINTER_DELTA)
 
 /********** include/linux/timer.h **********/
 /*
  * Magic number "tsta" to indicate a static timer initializer
  * for the object debugging code.
  */
-#define TIMER_ENTRY_STATIC	((void *) 0x74737461)
+#define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
 
 /********** mm/debug-pagealloc.c **********/
 #define PAGE_POISON 0xaa
 
+/********** mm/page_alloc.c ************/
+
+#define TAIL_MAPPING	((void *) 0x400 + POISON_POINTER_DELTA)
+
 /********** mm/slab.c **********/
 /*
  * Magic nums for obj red zoning.
@@ -69,10 +73,6 @@
 #define ATM_POISON_FREE		0x12
 #define ATM_POISON		0xdeadbeef
 
-/********** net/ **********/
-#define NEIGHBOR_DEAD		0xdeadbeef
-#define NETFILTER_LINK_POISON	0xdead57ac
-
 /********** kernel/mutexes **********/
 #define MUTEX_DEBUG_INIT	0x11
 #define MUTEX_DEBUG_FREE	0x22
@@ -83,7 +83,4 @@
 /********** security/ **********/
 #define KEY_DESTROY		0xbd
 
-/********** sound/oss/ **********/
-#define OSS_POISON_FREE		0xAB
-
 #endif
diff --git a/include/linux/printk.h b/include/linux/printk.h
index a6298b27ac99..9729565c25ff 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -404,10 +404,10 @@ do {									\
 	static DEFINE_RATELIMIT_STATE(_rs,				\
 				      DEFAULT_RATELIMIT_INTERVAL,	\
 				      DEFAULT_RATELIMIT_BURST);		\
-	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt));		\
 	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
 	    __ratelimit(&_rs))						\
-		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+		__dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__);	\
 } while (0)
 #elif defined(DEBUG)
 #define pr_debug_ratelimited(fmt, ...)					\
@@ -456,11 +456,17 @@ static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
 			     groupsize, buf, len, ascii)	\
 	dynamic_hex_dump(prefix_str, prefix_type, rowsize,	\
 			 groupsize, buf, len, ascii)
-#else
+#elif defined(DEBUG)
 #define print_hex_dump_debug(prefix_str, prefix_type, rowsize,		\
 			     groupsize, buf, len, ascii)		\
 	print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize,	\
 		       groupsize, buf, len, ascii)
-#endif /* defined(CONFIG_DYNAMIC_DEBUG) */
+#else
+static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type,
+					int rowsize, int groupsize,
+					const void *buf, size_t len, bool ascii)
+{
+}
+#endif
 
 #endif
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 29446aeef36e..0860336c6c40 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -85,6 +85,7 @@ enum ttu_flags {
 	TTU_UNMAP = 1,			/* unmap mode */
 	TTU_MIGRATION = 2,		/* migration mode */
 	TTU_MUNLOCK = 4,		/* munlock mode */
+	TTU_FREE = 8,			/* free mode */
 
 	TTU_IGNORE_MLOCK = (1 << 8),	/* ignore mlock */
 	TTU_IGNORE_ACCESS = (1 << 9),	/* don't age */
@@ -186,7 +187,8 @@ static inline void page_dup_rmap(struct page *page)
  * Called from mm/vmscan.c to handle paging out
  */
 int page_referenced(struct page *, int is_locked,
-			struct mem_cgroup *memcg, unsigned long *vm_flags);
+			struct mem_cgroup *memcg, unsigned long *vm_flags,
+			int *is_pte_dirty);
 
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 
@@ -263,9 +265,12 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
 
 static inline int page_referenced(struct page *page, int is_locked,
 				  struct mem_cgroup *memcg,
-				  unsigned long *vm_flags)
+				  unsigned long *vm_flags,
+				  int *is_pte_dirty)
 {
 	*vm_flags = 0;
+	if (is_pte_dirty)
+		*is_pte_dirty = 0;
 	return 0;
 }
 
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index d4c7271382cb..adeadbd6d7bf 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -122,6 +122,10 @@ int seq_write(struct seq_file *seq, const void *data, size_t len);
 __printf(2, 3) int seq_printf(struct seq_file *, const char *, ...);
 __printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args);
 
+void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type,
+		  int rowsize, int groupsize, const void *buf, size_t len,
+		  bool ascii);
+
 int seq_path(struct seq_file *, const struct path *, const char *);
 int seq_file_path(struct seq_file *, struct file *, const char *);
 int seq_dentry(struct seq_file *, struct dentry *, const char *);
diff --git a/include/linux/string.h b/include/linux/string.h
index a8d90db9c4b0..d5dfe3e75572 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -118,6 +118,7 @@ extern void kfree_const(const void *x);
 extern char *kstrdup(const char *s, gfp_t gfp);
 extern const char *kstrdup_const(const char *s, gfp_t gfp);
 extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
+extern char *kstrimdup(const char *s, gfp_t gfp);
 extern void *kmemdup(const void *src, size_t len, gfp_t gfp);
 
 extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 71f711db4500..dabe643eb5fa 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -48,24 +48,24 @@ static inline int string_unescape_any_inplace(char *buf)
 #define ESCAPE_HEX		0x20
 
 int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
-		unsigned int flags, const char *esc);
+		unsigned int flags, const char *only);
 
 static inline int string_escape_mem_any_np(const char *src, size_t isz,
-		char *dst, size_t osz, const char *esc)
+		char *dst, size_t osz, const char *only)
 {
-	return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, esc);
+	return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, only);
 }
 
 static inline int string_escape_str(const char *src, char *dst, size_t sz,
-		unsigned int flags, const char *esc)
+		unsigned int flags, const char *only)
 {
-	return string_escape_mem(src, strlen(src), dst, sz, flags, esc);
+	return string_escape_mem(src, strlen(src), dst, sz, flags, only);
 }
 
 static inline int string_escape_str_any_np(const char *src, char *dst,
-		size_t sz, const char *esc)
+		size_t sz, const char *only)
 {
-	return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, esc);
+	return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, only);
 }
 
 #endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 31496d201fdc..b0f9d6a7a799 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -154,7 +154,7 @@ enum {
 	SWP_SCANNING	= (1 << 10),	/* refcount in scan_swap_map */
 };
 
-#define SWAP_CLUSTER_MAX 32UL
+#define SWAP_CLUSTER_MAX 256UL
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
 /*
@@ -308,6 +308,7 @@ extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_file_page(struct page *page);
+extern void deactivate_page(struct page *page);
 extern void swap_setup(void);
 
 extern void add_page_to_unevictable_list(struct page *page);
@@ -351,7 +352,15 @@ extern void check_move_unevictable_pages(struct page **, int nr_pages);
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
 #ifdef CONFIG_MEMCG
-extern int mem_cgroup_swappiness(struct mem_cgroup *mem);
+static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
+{
+	/* root ? */
+	if (mem_cgroup_disabled() || !memcg->css.parent)
+		return vm_swappiness;
+
+	return memcg->swappiness;
+}
+
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 {
@@ -398,6 +407,9 @@ extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t);
 extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr);
+extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
+			struct vm_area_struct *vma, unsigned long addr,
+			bool *new_page_allocated);
 extern struct page *swapin_readahead(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr);
 
@@ -431,6 +443,7 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
+extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
 extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
@@ -522,6 +535,11 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
+static inline int swp_swapcount(swp_entry_t entry)
+{
+	return 0;
+}
+
 #define reuse_swap_page(page)	(page_mapcount(page) == 1)
 
 static inline int try_to_free_swap(struct page *page)
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index cedf3d3c373f..5c3a5f3e7eec 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -164,6 +164,9 @@ static inline int is_write_migration_entry(swp_entry_t entry)
 #endif
 
 #ifdef CONFIG_MEMORY_FAILURE
+
+extern atomic_long_t num_poisoned_pages __read_mostly;
+
 /*
  * Support for hardware poisoned pages
  */
@@ -177,6 +180,31 @@ static inline int is_hwpoison_entry(swp_entry_t entry)
 {
 	return swp_type(entry) == SWP_HWPOISON;
 }
+
+static inline bool test_set_page_hwpoison(struct page *page)
+{
+	return TestSetPageHWPoison(page);
+}
+
+static inline void num_poisoned_pages_inc(void)
+{
+	atomic_long_inc(&num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_dec(void)
+{
+	atomic_long_dec(&num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_add(long num)
+{
+	atomic_long_add(num, &num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_sub(long num)
+{
+	atomic_long_sub(num, &num_poisoned_pages);
+}
 #else
 
 static inline swp_entry_t make_hwpoison_entry(struct page *page)
@@ -188,6 +216,15 @@ static inline int is_hwpoison_entry(swp_entry_t swp)
 {
 	return 0;
 }
+
+static inline bool test_set_page_hwpoison(struct page *page)
+{
+	return false;
+}
+
+static inline void num_poisoned_pages_inc(void)
+{
+}
 #endif
 
 #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 08001317aee7..890632cbf353 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -885,4 +885,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 			const char __user *const __user *argv,
 			const char __user *const __user *envp, int flags);
 
+asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
+
 #endif
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 9246d32dc973..2b1cef88b827 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
+		PGLAZYFREED,
 		FOR_ALL_ZONES(PGREFILL),
 		FOR_ALL_ZONES(PGSTEAL_KSWAPD),
 		FOR_ALL_ZONES(PGSTEAL_DIRECT),
diff --git a/include/linux/zbud.h b/include/linux/zbud.h
index f9d41a6e361f..e183a0a65ac1 100644
--- a/include/linux/zbud.h
+++ b/include/linux/zbud.h
@@ -9,7 +9,7 @@ struct zbud_ops {
 	int (*evict)(struct zbud_pool *pool, unsigned long handle);
 };
 
-struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops);
+struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops);
 void zbud_destroy_pool(struct zbud_pool *pool);
 int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp,
 	unsigned long *handle);
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index d30eff3d84d5..42f8ec992452 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -36,8 +36,10 @@ enum zpool_mapmode {
 	ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
 };
 
+bool zpool_has_pool(char *type);
+
 struct zpool *zpool_create_pool(char *type, char *name,
-			gfp_t gfp, struct zpool_ops *ops);
+			gfp_t gfp, const struct zpool_ops *ops);
 
 char *zpool_get_type(struct zpool *pool);
 
@@ -81,7 +83,7 @@ struct zpool_driver {
 	atomic_t refcount;
 	struct list_head list;
 
-	void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops,
+	void *(*create)(char *name, gfp_t gfp, const struct zpool_ops *ops,
 			struct zpool *zpool);
 	void (*destroy)(void *pool);
 
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 1338190b5478..6398dfae53f1 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -34,6 +34,11 @@ enum zs_mapmode {
 	 */
 };
 
+struct zs_pool_stats {
+	/* How many pages were migrated (freed) */
+	unsigned long pages_compacted;
+};
+
 struct zs_pool;
 
 struct zs_pool *zs_create_pool(char *name, gfp_t flags);
@@ -49,4 +54,5 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
 unsigned long zs_get_total_pages(struct zs_pool *pool);
 unsigned long zs_compact(struct zs_pool *pool);
 
+void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats);
 #endif