Merge branch 'akpm' (patches from Andrew Morton)

Merge first patch-bomb from Andrew Morton:
 - Some pidns/fork/exec tweaks
 - OCFS2 updates
 - Most of MM - there remain quite a few memcg parts which depend on
   pending core cgroups changes.  Which might have been already merged -
   I'll check tomorrow...
 - Various misc stuff all over the place
 - A few block bits which I never got around to sending to Jens -
   relatively minor things.
 - MAINTAINERS maintenance
 - A small number of lib/ updates
 - checkpatch updates
 - epoll
 - firmware/dmi-scan
 - Some kprobes work for S390
 - drivers/rtc updates
 - hfsplus feature work
 - vmcore feature work
 - rbtree upgrades
 - AOE updates
 - pktcdvd cleanups
 - PPS
 - memstick
 - w1
 - New "inittmpfs" feature, which does the obvious
 - More IPC work from Davidlohr.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (303 commits)
  lz4: fix compression/decompression signedness mismatch
  ipc: drop ipc_lock_check
  ipc, shm: drop shm_lock_check
  ipc: drop ipc_lock_by_ptr
  ipc, shm: guard against non-existant vma in shmdt(2)
  ipc: document general ipc locking scheme
  ipc,msg: drop msg_unlock
  ipc: rename ids->rw_mutex
  ipc,shm: shorten critical region for shmat
  ipc,shm: cleanup do_shmat pasta
  ipc,shm: shorten critical region for shmctl
  ipc,shm: make shmctl_nolock lockless
  ipc,shm: introduce shmctl_nolock
  ipc: drop ipcctl_pre_down
  ipc,shm: shorten critical region in shmctl_down
  ipc,shm: introduce lockless functions to obtain the ipc object
  initmpfs: use initramfs if rootfstype= or root= specified
  initmpfs: make rootfs use tmpfs when CONFIG_TMPFS enabled
  initmpfs: move rootfs code from fs/ramfs/ to init/
  initmpfs: move bdi setup from init_rootfs to init_ramfs
  ...

28 files changed, 252 insertions, 120 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c388155..5f66d51 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -243,6 +243,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_EXEC_MAP:       Can be mapped for execution
  *
  * BDI_CAP_SWAP_BACKED:    Count shmem/tmpfs objects as swap-backed.
+ *
+ * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
@@ -254,6 +256,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_NO_ACCT_WB	0x00000080
 #define BDI_CAP_SWAP_BACKED	0x00000100
 #define BDI_CAP_STABLE_WRITES	0x00000200
+#define BDI_CAP_STRICTLIMIT	0x00000400
 
 #define BDI_CAP_VMFLAGS \
 	(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 70cf138..e8112ae 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -31,7 +31,7 @@ struct linux_binprm {
 #ifdef __alpha__
 	unsigned int taso:1;
 #endif
-	unsigned int recursion_depth;
+	unsigned int recursion_depth; /* only for search_binary_handler() */
 	struct file * file;
 	struct cred *cred;	/* new credentials */
 	int unsafe;		/* how unsafe this exec is (mask of LSM_UNSAFE_*) */
diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h
new file mode 100644
index 0000000..98e892e
--- /dev/null
+++ b/include/linux/cmdline-parser.h
@@ -0,0 +1,43 @@
+/*
+ * Parsing command line, get the partitions information.
+ *
+ * Written by Cai Zhiyong <caizhiyong@huawei.com>
+ *
+ */
+#ifndef CMDLINEPARSEH
+#define CMDLINEPARSEH
+
+#include <linux/blkdev.h>
+
+/* partition flags */
+#define PF_RDONLY                   0x01 /* Device is read only */
+#define PF_POWERUP_LOCK             0x02 /* Always locked after reset */
+
+struct cmdline_subpart {
+	char name[BDEVNAME_SIZE]; /* partition name, such as 'rootfs' */
+	sector_t from;
+	sector_t size;
+	int flags;
+	struct cmdline_subpart *next_subpart;
+};
+
+struct cmdline_parts {
+	char name[BDEVNAME_SIZE]; /* block device, such as 'mmcblk0' */
+	unsigned int nr_subparts;
+	struct cmdline_subpart *subpart;
+	struct cmdline_parts *next_parts;
+};
+
+void cmdline_parts_free(struct cmdline_parts **parts);
+
+int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline);
+
+struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts,
+					 const char *bdev);
+
+void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
+		       int slot,
+		       int (*add_part)(int, struct cmdline_subpart *, void *),
+		       void *param);
+
+#endif /* CMDLINEPARSEH */
diff --git a/include/linux/compat.h b/include/linux/compat.h
index ec1aee4..345da00a 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -43,6 +43,7 @@
 #define COMPAT_SYSCALL_DEFINEx(x, name, ...)				\
 	asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
 	static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
+	asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\
 	asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
 	{								\
 		return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));	\
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 37e4f8d..fe68a5a 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -12,6 +12,15 @@
 extern unsigned long long elfcorehdr_addr;
 extern unsigned long long elfcorehdr_size;
 
+extern int __weak elfcorehdr_alloc(unsigned long long *addr,
+				   unsigned long long *size);
+extern void __weak elfcorehdr_free(unsigned long long addr);
+extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos);
+extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+					 unsigned long from, unsigned long pfn,
+					 unsigned long size, pgprot_t prot);
+
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
 
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 661d374..f8d41cb 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -66,8 +66,8 @@ struct gen_pool_chunk {
 	struct list_head next_chunk;	/* next chunk in pool */
 	atomic_t avail;
 	phys_addr_t phys_addr;		/* physical starting address of memory chunk */
-	unsigned long start_addr;	/* starting address of memory chunk */
-	unsigned long end_addr;		/* ending address of memory chunk */
+	unsigned long start_addr;	/* start address of memory chunk */
+	unsigned long end_addr;		/* end address of memory chunk (inclusive) */
 	unsigned long bits[0];		/* bitmap for allocating memory chunk */
 };
 
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index c2b1801..0393270 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -66,6 +66,9 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						vm_flags_t vm_flags);
 void hugetlb_unreserve_pages(struct inode *inode, long offset, 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);
+bool is_hugepage_active(struct page *page);
 void copy_huge_page(struct page *dst, struct page *src);
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
@@ -134,6 +137,9 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page)
 	return 0;
 }
 
+#define isolate_huge_page(p, l) false
+#define putback_active_hugepage(p)	do {} while (0)
+#define is_hugepage_active(x)	false
 static inline void copy_huge_page(struct page *dst, struct page *src)
 {
 }
@@ -261,6 +267,8 @@ struct huge_bootmem_page {
 };
 
 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);
 
 /* arch callback */
 int __init alloc_bootmem_huge_page(struct hstate *h);
@@ -371,9 +379,23 @@ static inline pgoff_t basepage_index(struct page *page)
 	return __basepage_index(page);
 }
 
+extern void dissolve_free_huge_pages(unsigned long start_pfn,
+				     unsigned long end_pfn);
+int pmd_huge_support(void);
+/*
+ * Currently hugepage migration is enabled only for pmd-based hugepage.
+ * This function will be updated when hugepage migration is more widely
+ * supported.
+ */
+static inline int hugepage_migration_support(struct hstate *h)
+{
+	return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
+#define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
 #define hstate_sizelog(s) NULL
@@ -396,6 +418,9 @@ static inline pgoff_t basepage_index(struct page *page)
 {
 	return page->index;
 }
+#define dissolve_free_huge_pages(s, e)	do {} while (0)
+#define pmd_huge_support()	0
+#define hugepage_migration_support(h)	0
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/init.h b/include/linux/init.h
index e73f2b7..f1c27a7 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -153,6 +153,7 @@ extern unsigned int reset_devices;
 void setup_arch(char **);
 void prepare_namespace(void);
 void __init load_default_modules(void);
+int __init init_rootfs(void);
 
 extern void (*late_time_init)(void);
 
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index c4d870b..19c19a5 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -22,7 +22,7 @@ struct ipc_ids {
 	int in_use;
 	unsigned short seq;
 	unsigned short seq_max;
-	struct rw_semaphore rw_mutex;
+	struct rw_semaphore rwsem;
 	struct idr ipcs_idr;
 	int next_id;
 };
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index ca1d27a..925eaf2 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -264,10 +264,36 @@ extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
 extern void show_registers(struct pt_regs *regs);
-extern kprobe_opcode_t *get_insn_slot(void);
-extern void free_insn_slot(kprobe_opcode_t *slot, int dirty);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 
+struct kprobe_insn_cache {
+	struct mutex mutex;
+	void *(*alloc)(void);	/* allocate insn page */
+	void (*free)(void *);	/* free insn page */
+	struct list_head pages; /* list of kprobe_insn_page */
+	size_t insn_size;	/* size of instruction slot */
+	int nr_garbage;
+};
+
+extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c);
+extern void __free_insn_slot(struct kprobe_insn_cache *c,
+			     kprobe_opcode_t *slot, int dirty);
+
+#define DEFINE_INSN_CACHE_OPS(__name)					\
+extern struct kprobe_insn_cache kprobe_##__name##_slots;		\
+									\
+static inline kprobe_opcode_t *get_##__name##_slot(void)		\
+{									\
+	return __get_insn_slot(&kprobe_##__name##_slots);		\
+}									\
+									\
+static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\
+{									\
+	__free_insn_slot(&kprobe_##__name##_slots, slot, dirty);	\
+}									\
+
+DEFINE_INSN_CACHE_OPS(insn);
+
 #ifdef CONFIG_OPTPROBES
 /*
  * Internal structure for direct jump optimized probe
@@ -287,13 +313,13 @@ extern void arch_optimize_kprobes(struct list_head *oplist);
 extern void arch_unoptimize_kprobes(struct list_head *oplist,
 				    struct list_head *done_list);
 extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
-extern kprobe_opcode_t *get_optinsn_slot(void);
-extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty);
 extern int arch_within_optimized_kprobe(struct optimized_kprobe *op,
 					unsigned long addr);
 
 extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs);
 
+DEFINE_INSN_CACHE_OPS(optinsn);
+
 #ifdef CONFIG_SYSCTL
 extern int sysctl_kprobes_optimization;
 extern int proc_kprobes_optimization_handler(struct ctl_table *table,
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
index d21c13f..4356686 100644
--- a/include/linux/lz4.h
+++ b/include/linux/lz4.h
@@ -67,8 +67,8 @@ int lz4hc_compress(const unsigned char *src, size_t src_len,
  *	note :  Destination buffer must be already allocated.
  *		slightly faster than lz4_decompress_unknownoutputsize()
  */
-int lz4_decompress(const char *src, size_t *src_len, char *dest,
-		size_t actual_dest_len);
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+		unsigned char *dest, size_t actual_dest_len);
 
 /*
  * lz4_decompress_unknownoutputsize()
@@ -82,6 +82,6 @@ int lz4_decompress(const char *src, size_t *src_len, char *dest,
  *		  Error if return (< 0)
  *	note :  Destination buffer must be already allocated.
  */
-int lz4_decompress_unknownoutputsize(const char *src, size_t src_len,
-		char *dest, size_t *dest_len);
+int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
+		unsigned char *dest, size_t *dest_len);
 #endif
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index f388203..31e95ac 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -60,6 +60,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
+			    unsigned long  *end_pfn);
 void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 			  unsigned long *out_end_pfn, int *out_nid);
 
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 0d7df39..da6716b 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -91,7 +91,6 @@ static inline struct mempolicy *mpol_dup(struct mempolicy *pol)
 }
 
 #define vma_policy(vma) ((vma)->vm_policy)
-#define vma_set_policy(vma, pol) ((vma)->vm_policy = (pol))
 
 static inline void mpol_get(struct mempolicy *pol)
 {
@@ -126,6 +125,7 @@ struct shared_policy {
 	spinlock_t lock;
 };
 
+int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst);
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
 int mpol_set_shared_policy(struct shared_policy *info,
 				struct vm_area_struct *vma,
@@ -173,7 +173,7 @@ extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
 /* Check if a vma is migratable */
 static inline int vma_migratable(struct vm_area_struct *vma)
 {
-	if (vma->vm_flags & (VM_IO | VM_HUGETLB | VM_PFNMAP))
+	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
 		return 0;
 	/*
 	 * Migration allocates pages in the highest zone. If we cannot
@@ -240,7 +240,12 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
 }
 
 #define vma_policy(vma) NULL
-#define vma_set_policy(vma, pol) do {} while(0)
+
+static inline int
+vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
+{
+	return 0;
+}
 
 static inline void numa_policy_init(void)
 {
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index a405d3dc..6fe5214 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -41,8 +41,6 @@ extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 extern int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, enum migrate_mode mode, int reason);
-extern int migrate_huge_page(struct page *, new_page_t x,
-		unsigned long private, enum migrate_mode mode);
 
 extern int fail_migrate_page(struct address_space *,
 			struct page *, struct page *);
@@ -62,9 +60,6 @@ static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, enum migrate_mode mode, int reason)
 	{ return -ENOSYS; }
-static inline int migrate_huge_page(struct page *page, new_page_t x,
-		unsigned long private, enum migrate_mode mode)
-	{ return -ENOSYS; }
 
 static inline int migrate_prep(void) { return -ENOSYS; }
 static inline int migrate_prep_local(void) { return -ENOSYS; }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d2d59b4..caf543c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -115,6 +115,12 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
 #define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
+# define VM_SOFTDIRTY	0x08000000	/* Not soft dirty clean area */
+#else
+# define VM_SOFTDIRTY	0
+#endif
+
 #define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
 #define VM_HUGEPAGE	0x20000000	/* MADV_HUGEPAGE marked this vma */
 #define VM_NOHUGEPAGE	0x40000000	/* MADV_NOHUGEPAGE marked this vma */
@@ -489,20 +495,6 @@ static inline int compound_order(struct page *page)
 	return (unsigned long)page[1].lru.prev;
 }
 
-static inline int compound_trans_order(struct page *page)
-{
-	int order;
-	unsigned long flags;
-
-	if (!PageHead(page))
-		return 0;
-
-	flags = compound_lock_irqsave(page);
-	order = compound_order(page);
-	compound_unlock_irqrestore(page, flags);
-	return order;
-}
-
 static inline void set_compound_order(struct page *page, unsigned long order)
 {
 	page[1].lru.prev = (void *)order;
@@ -637,12 +629,12 @@ static inline enum zone_type page_zonenum(const struct page *page)
 #endif
 
 /*
- * The identification function is only used by the buddy allocator for
- * determining if two pages could be buddies. We are not really
- * identifying a zone since we could be using a the section number
- * id if we have not node id available in page flags.
- * We guarantee only that it will return the same value for two
- * combinable pages in a zone.
+ * The identification function is mainly used by the buddy allocator for
+ * determining if two pages could be buddies. We are not really identifying
+ * the zone since we could be using the section number id if we do not have
+ * node id available in page flags.
+ * We only guarantee that it will return the same value for two combinable
+ * pages in a zone.
  */
 static inline int page_zone_id(struct page *page)
 {
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 1397ccf..cf55945 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -2,6 +2,7 @@
 #define LINUX_MM_INLINE_H
 
 #include <linux/huge_mm.h>
+#include <linux/swap.h>
 
 /**
  * page_is_file_cache - should the page be on a file LRU or anon LRU?
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index af4a3b7..bd791e4 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -105,6 +105,7 @@ struct zone_padding {
 enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
+	NR_ALLOC_BATCH,
 	NR_LRU_BASE,
 	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
 	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
@@ -352,7 +353,6 @@ struct zone {
 	 * free areas of different sizes
 	 */
 	spinlock_t		lock;
-	int                     all_unreclaimable; /* All pages pinned */
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 	/* Set to true when the PG_migrate_skip bits should be cleared */
 	bool			compact_blockskip_flush;
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index ffc444c..4039407 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -231,6 +231,7 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root,
 unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
+int radix_tree_maybe_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,
 			unsigned long index, unsigned int tag);
diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h
index 69e37c2..753207c 100644
--- a/include/linux/ramfs.h
+++ b/include/linux/ramfs.h
@@ -25,7 +25,7 @@ extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
 
 extern const struct file_operations ramfs_file_operations;
 extern const struct vm_operations_struct generic_file_vm_ops;
-extern int __init init_rootfs(void);
+extern int __init init_ramfs_fs(void);
 
 int ramfs_fill_super(struct super_block *sb, void *data, int silent);
 
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 0022c1b..aa870a4 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -68,6 +68,10 @@ extern struct rb_node *rb_prev(const struct rb_node *);
 extern struct rb_node *rb_first(const struct rb_root *);
 extern struct rb_node *rb_last(const struct rb_root *);
 
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
 /* Fast replacement of a single node without remove/rebalance/add/rebalance */
 extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, 
 			    struct rb_root *root);
@@ -81,4 +85,22 @@ static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
 	*rb_link = node;
 }
 
+/**
+ * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of
+ * given type safe against removal of rb_node entry
+ *
+ * @pos:	the 'type *' to use as a loop cursor.
+ * @n:		another 'type *' to use as temporary storage
+ * @root:	'rb_root *' of the rbtree.
+ * @field:	the name of the rb_node field within 'type'.
+ */
+#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
+	for (pos = rb_entry(rb_first_postorder(root), typeof(*pos), field),\
+		n = rb_entry(rb_next_postorder(&pos->field), \
+			typeof(*pos), field); \
+	     &pos->field; \
+	     pos = n, \
+		n = rb_entry(rb_next_postorder(&pos->field), \
+			typeof(*pos), field))
+
 #endif	/* _LINUX_RBTREE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ce1e1c0..45f254d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2169,15 +2169,15 @@ static inline bool thread_group_leader(struct task_struct *p)
  * all we care about is that we have a task with the appropriate
  * pid, we don't actually care if we have the right task.
  */
-static inline int has_group_leader_pid(struct task_struct *p)
+static inline bool has_group_leader_pid(struct task_struct *p)
 {
-	return p->pid == p->tgid;
+	return task_pid(p) == p->signal->leader_pid;
 }
 
 static inline
-int same_thread_group(struct task_struct *p1, struct task_struct *p2)
+bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
 {
-	return p1->tgid == p2->tgid;
+	return p1->signal == p2->signal;
 }
 
 static inline struct task_struct *next_thread(const struct task_struct *p)
diff --git a/include/linux/smp.h b/include/linux/smp.h
index c181399..cfb7ca0 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -28,6 +28,27 @@ extern unsigned int total_cpus;
 int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
 			     int wait);
 
+/*
+ * Call a function on all processors
+ */
+int on_each_cpu(smp_call_func_t func, void *info, int wait);
+
+/*
+ * Call a function on processors specified by mask, which might include
+ * the local one.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+		void *info, bool wait);
+
+/*
+ * Call a function on each processor for which the supplied function
+ * cond_func returns a positive value. This may include the local
+ * processor.
+ */
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+		smp_call_func_t func, void *info, bool wait,
+		gfp_t gfp_flags);
+
 #ifdef CONFIG_SMP
 
 #include <linux/preempt.h>
@@ -95,27 +116,6 @@ static inline void call_function_init(void) { }
 #endif
 
 /*
- * Call a function on all processors
- */
-int on_each_cpu(smp_call_func_t func, void *info, int wait);
-
-/*
- * Call a function on processors specified by mask, which might include
- * the local one.
- */
-void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
-		void *info, bool wait);
-
-/*
- * Call a function on each processor for which the supplied function
- * cond_func returns a positive value. This may include the local
- * processor.
- */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-		smp_call_func_t func, void *info, bool wait,
-		gfp_t gfp_flags);
-
-/*
  * Mark the boot cpu "online" so that it can call console drivers in
  * printk() and can access its per-cpu storage.
  */
@@ -139,43 +139,6 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info)
 }
 #define smp_call_function(func, info, wait) \
 			(up_smp_call_function(func, info))
-#define on_each_cpu(func, info, wait)		\
-	({					\
-		unsigned long __flags;		\
-		local_irq_save(__flags);	\
-		func(info);			\
-		local_irq_restore(__flags);	\
-		0;				\
-	})
-/*
- * Note we still need to test the mask even for UP
- * because we actually can get an empty mask from
- * code that on SMP might call us without the local
- * CPU in the mask.
- */
-#define on_each_cpu_mask(mask, func, info, wait) \
-	do {						\
-		if (cpumask_test_cpu(0, (mask))) {	\
-			local_irq_disable();		\
-			(func)(info);			\
-			local_irq_enable();		\
-		}					\
-	} while (0)
-/*
- * Preemption is disabled here to make sure the cond_func is called under the
- * same condtions in UP and SMP.
- */
-#define on_each_cpu_cond(cond_func, func, info, wait, gfp_flags)\
-	do {							\
-		void *__info = (info);				\
-		preempt_disable();				\
-		if ((cond_func)(0, __info)) {			\
-			local_irq_disable();			\
-			(func)(__info);				\
-			local_irq_enable();			\
-		}						\
-		preempt_enable();				\
-	} while (0)
 
 static inline void smp_send_reschedule(int cpu) { }
 #define smp_prepare_boot_cpu()			do {} while (0)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index d95cde5..c03c139 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -182,6 +182,33 @@ enum {
 #define SWAP_MAP_SHMEM	0xbf	/* Owned by shmem/tmpfs, in first swap_map */
 
 /*
+ * We use this to track usage of a cluster. A cluster is a block of swap disk
+ * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
+ * free clusters are organized into a list. We fetch an entry from the list to
+ * get a free cluster.
+ *
+ * The data field stores next cluster if the cluster is free or cluster usage
+ * counter otherwise. The flags field determines if a cluster is free. This is
+ * protected by swap_info_struct.lock.
+ */
+struct swap_cluster_info {
+	unsigned int data:24;
+	unsigned int flags:8;
+};
+#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
+#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+
+/*
+ * We assign a cluster to each CPU, so each CPU can allocate swap entry from
+ * its own cluster and swapout sequentially. The purpose is to optimize swapout
+ * throughput.
+ */
+struct percpu_cluster {
+	struct swap_cluster_info index; /* Current cluster index */
+	unsigned int next; /* Likely next allocation offset */
+};
+
+/*
  * The in-memory structure used to track swap areas.
  */
 struct swap_info_struct {
@@ -191,14 +218,16 @@ struct swap_info_struct {
 	signed char	next;		/* next type on the swap list */
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
+	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
+	struct swap_cluster_info free_cluster_head; /* free cluster list head */
+	struct swap_cluster_info free_cluster_tail; /* free cluster list tail */
 	unsigned int lowest_bit;	/* index of first free in swap_map */
 	unsigned int highest_bit;	/* index of last free in swap_map */
 	unsigned int pages;		/* total of usable pages of swap */
 	unsigned int inuse_pages;	/* number of those currently in use */
 	unsigned int cluster_next;	/* likely index for next allocation */
 	unsigned int cluster_nr;	/* countdown to next cluster search */
-	unsigned int lowest_alloc;	/* while preparing discard cluster */
-	unsigned int highest_alloc;	/* while preparing discard cluster */
+	struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
 	struct swap_extent *curr_swap_extent;
 	struct swap_extent first_swap_extent;
 	struct block_device *bdev;	/* swap device or bdev of swap file */
@@ -212,14 +241,18 @@ struct swap_info_struct {
 					 * protect map scan related fields like
 					 * swap_map, lowest_bit, highest_bit,
 					 * inuse_pages, cluster_next,
-					 * cluster_nr, lowest_alloc and
-					 * highest_alloc. other fields are only
-					 * changed at swapon/swapoff, so are
-					 * protected by swap_lock. changing
-					 * flags need hold this lock and
-					 * swap_lock. If both locks need hold,
-					 * hold swap_lock first.
+					 * cluster_nr, lowest_alloc,
+					 * highest_alloc, free/discard cluster
+					 * list. other fields are only changed
+					 * at swapon/swapoff, so are protected
+					 * by swap_lock. changing flags need
+					 * hold this lock and swap_lock. If
+					 * both locks need hold, hold swap_lock
+					 * first.
 					 */
+	struct work_struct discard_work; /* discard worker */
+	struct swap_cluster_info discard_cluster_head; /* list head of discard clusters */
+	struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */
 };
 
 struct swap_list_t {
@@ -414,6 +447,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 
 #else /* CONFIG_SWAP */
 
+#define swap_address_space(entry)		(NULL)
 #define get_nr_swap_pages()			0L
 #define total_swap_pages			0L
 #define total_swapcache_pages()			0UL
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 84662ec..7fac04e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -186,6 +186,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 #define __SYSCALL_DEFINEx(x, name, ...)					\
 	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
 	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
 	{								\
 		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index bd6cf61..1855f0a 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -70,6 +70,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+#ifdef CONFIG_SMP
+		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
+		NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
+#endif
+		NR_TLB_LOCAL_FLUSH_ALL,
+		NR_TLB_LOCAL_FLUSH_ONE,
 		NR_VM_EVENT_ITEMS
 };
 
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index c586679..e4b9480 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -143,7 +143,6 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 }
 
 extern unsigned long global_reclaimable_pages(void);
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
 
 #ifdef CONFIG_NUMA
 /*
@@ -198,7 +197,7 @@ extern void __inc_zone_state(struct zone *, enum zone_stat_item);
 extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
-void refresh_cpu_vm_stats(int);
+void cpu_vm_stats_fold(int cpu);
 void refresh_zone_stat_thresholds(void);
 
 void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
@@ -255,6 +254,7 @@ static inline void __dec_zone_page_state(struct page *page,
 
 static inline void refresh_cpu_vm_stats(int cpu) { }
 static inline void refresh_zone_stat_thresholds(void) { }
+static inline void cpu_vm_stats_fold(int cpu) { }
 
 static inline void drain_zonestat(struct zone *zone,
 			struct per_cpu_pageset *pset) { }
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 4e198ca..021b8a3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -98,8 +98,6 @@ int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 				  enum wb_reason reason);
 void sync_inodes_sb(struct super_block *);
-long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
-				enum wb_reason reason);
 void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
 void inode_wait_for_writeback(struct inode *inode);
 
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 6bc943e..d0c6134 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -268,11 +268,13 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 
 	TP_PROTO(struct page *page,
 			int alloc_order, int fallback_order,
-			int alloc_migratetype, int fallback_migratetype),
+			int alloc_migratetype, int fallback_migratetype,
+			int change_ownership),
 
 	TP_ARGS(page,
 		alloc_order, fallback_order,
-		alloc_migratetype, fallback_migratetype),
+		alloc_migratetype, fallback_migratetype,
+		change_ownership),
 
 	TP_STRUCT__entry(
 		__field(	struct page *,	page			)
@@ -280,6 +282,7 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__field(	int,		fallback_order		)
 		__field(	int,		alloc_migratetype	)
 		__field(	int,		fallback_migratetype	)
+		__field(	int,		change_ownership	)
 	),
 
 	TP_fast_assign(
@@ -288,6 +291,7 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->fallback_order		= fallback_order;
 		__entry->alloc_migratetype	= alloc_migratetype;
 		__entry->fallback_migratetype	= fallback_migratetype;
+		__entry->change_ownership	= change_ownership;
 	),
 
 	TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
@@ -299,7 +303,7 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->alloc_migratetype,
 		__entry->fallback_migratetype,
 		__entry->fallback_order < pageblock_order,
-		__entry->alloc_migratetype == __entry->fallback_migratetype)
+		__entry->change_ownership)
 );
 
 #endif /* _TRACE_KMEM_H */