21 files changed, 211 insertions, 417 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 27b0c9105da5..641e56494a92 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -113,6 +113,19 @@ static inline void css_get(struct cgroup_subsys_state *css)
 }
 
 /**
+ * css_get_many - obtain references on the specified css
+ * @css: target css
+ * @n: number of references to get
+ *
+ * The caller must already have a reference.
+ */
+static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_get_many(&css->refcnt, n);
+}
+
+/**
  * css_tryget - try to obtain a reference on the specified css
  * @css: target css
  *
@@ -159,6 +172,19 @@ static inline void css_put(struct cgroup_subsys_state *css)
 		percpu_ref_put(&css->refcnt);
 }
 
+/**
+ * css_put_many - put css references
+ * @css: target css
+ * @n: number of references to put
+ *
+ * Put references obtained via css_get() and css_tryget_online().
+ */
+static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_put_many(&css->refcnt, n);
+}
+
 /* bits in struct cgroup flags field */
 enum {
 	/* Control Group requires release notifications to userspace */
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 60bdf8dc02a3..3238ffa33f68 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -33,10 +33,11 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone);
+			int alloc_flags, int classzone_idx);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
-extern unsigned long compaction_suitable(struct zone *zone, int order);
+extern unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -103,7 +104,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	return COMPACT_CONTINUE;
 }
@@ -116,7 +117,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 {
 }
 
-static inline unsigned long compaction_suitable(struct zone *zone, int order)
+static inline unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	return COMPACT_SKIPPED;
 }
diff --git a/include/linux/file.h b/include/linux/file.h
index 4d69123377a2..f87d30882a24 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -66,7 +66,6 @@ extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
 extern void put_filp(struct file *);
 extern int get_unused_fd_flags(unsigned flags);
-#define get_unused_fd() get_unused_fd_flags(0)
 extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 41b30fd4d041..07d2699cdb51 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -381,8 +381,8 @@ extern void free_kmem_pages(unsigned long addr, unsigned int order);
 
 void page_alloc_init(void);
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
-void drain_all_pages(void);
-void drain_local_pages(void *dummy);
+void drain_all_pages(struct zone *zone);
+void drain_local_pages(struct zone *zone);
 
 /*
  * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6e6d338641fe..cdd149ca5cc0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -311,7 +311,8 @@ static inline struct hstate *hstate_sizelog(int page_size_log)
 {
 	if (!page_size_log)
 		return &default_hstate;
-	return size_to_hstate(1 << page_size_log);
+
+	return size_to_hstate(1UL << page_size_log);
 }
 
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 0129f89cf98d..bcc853eccc85 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -16,7 +16,6 @@
 #define _LINUX_HUGETLB_CGROUP_H
 
 #include <linux/mmdebug.h>
-#include <linux/res_counter.h>
 
 struct hugetlb_cgroup;
 /*
diff --git a/include/linux/kern_levels.h b/include/linux/kern_levels.h
index 866caaa9e2bb..c2ce155d83cc 100644
--- a/include/linux/kern_levels.h
+++ b/include/linux/kern_levels.h
@@ -22,4 +22,17 @@
  */
 #define KERN_CONT	""
 
+/* integer equivalents of KERN_<LEVEL> */
+#define LOGLEVEL_SCHED		-2	/* Deferred messages from sched code
+					 * are set to this special level */
+#define LOGLEVEL_DEFAULT	-1	/* default (or last) loglevel */
+#define LOGLEVEL_EMERG		0	/* system is unusable */
+#define LOGLEVEL_ALERT		1	/* action must be taken immediately */
+#define LOGLEVEL_CRIT		2	/* critical conditions */
+#define LOGLEVEL_ERR		3	/* error conditions */
+#define LOGLEVEL_WARNING	4	/* warning conditions */
+#define LOGLEVEL_NOTICE		5	/* normal but significant condition */
+#define LOGLEVEL_INFO		6	/* informational */
+#define LOGLEVEL_DEBUG		7	/* debug-level messages */
+
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 446d76a87ba1..233ea8107038 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -427,6 +427,7 @@ extern int panic_timeout;
 extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
+extern int panic_on_warn;
 extern int sysctl_panic_on_stackoverflow;
 /*
  * Only to be used by arch init code. If the user over-wrote the default
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6b75640ef5ab..6ea9f919e888 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -25,7 +25,6 @@
 #include <linux/jump_label.h>
 
 struct mem_cgroup;
-struct page_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
@@ -68,10 +67,9 @@ 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_same_or_subtree(const struct mem_cgroup *root_memcg,
-				  struct mem_cgroup *memcg);
-bool task_in_mem_cgroup(struct task_struct *task,
-			const struct mem_cgroup *memcg);
+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);
 
 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);
@@ -79,15 +77,16 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
 
-static inline
-bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
+static inline bool mm_match_cgroup(struct mm_struct *mm,
+				   struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *task_memcg;
-	bool match;
+	bool match = false;
 
 	rcu_read_lock();
 	task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	match = __mem_cgroup_same_or_subtree(memcg, task_memcg);
+	if (task_memcg)
+		match = mem_cgroup_is_descendant(task_memcg, memcg);
 	rcu_read_unlock();
 	return match;
 }
@@ -141,8 +140,8 @@ static inline bool mem_cgroup_disabled(void)
 
 struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked,
 					      unsigned long *flags);
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked,
-			      unsigned long flags);
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
+			      unsigned long *flags);
 void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
 				 enum mem_cgroup_stat_index idx, int val);
 
@@ -174,10 +173,6 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
 
-#ifdef CONFIG_DEBUG_VM
-bool mem_cgroup_bad_page_check(struct page *page);
-void mem_cgroup_print_bad_page(struct page *page);
-#endif
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
@@ -297,7 +292,7 @@ static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
 }
 
 static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg,
-					bool locked, unsigned long flags)
+					bool *locked, unsigned long *flags)
 {
 }
 
@@ -347,19 +342,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
-#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
-static inline bool
-mem_cgroup_bad_page_check(struct page *page)
-{
-	return false;
-}
-
-static inline void
-mem_cgroup_print_bad_page(struct page *page)
-{
-}
-#endif
-
 enum {
 	UNDER_LIMIT,
 	SOFT_LIMIT,
@@ -447,9 +429,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 	/*
 	 * __GFP_NOFAIL allocations will move on even if charging is not
 	 * possible. Therefore we don't even try, and have this allocation
-	 * unaccounted. We could in theory charge it with
-	 * res_counter_charge_nofail, but we hope those allocations are rare,
-	 * and won't be worth the trouble.
+	 * unaccounted. We could in theory charge it forcibly, but we hope
+	 * those allocations are rare, and won't be worth the trouble.
 	 */
 	if (gfp & __GFP_NOFAIL)
 		return true;
@@ -467,8 +448,6 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
  * memcg_kmem_uncharge_pages: uncharge pages from memcg
  * @page: pointer to struct page being freed
  * @order: allocation order.
- *
- * there is no need to specify memcg here, since it is embedded in page_cgroup
  */
 static inline void
 memcg_kmem_uncharge_pages(struct page *page, int order)
@@ -485,8 +464,7 @@ memcg_kmem_uncharge_pages(struct page *page, int order)
  *
  * Needs to be called after memcg_kmem_newpage_charge, regardless of success or
  * failure of the allocation. if @page is NULL, this function will revert the
- * charges. Otherwise, it will commit the memcg given by @memcg to the
- * corresponding page_cgroup.
+ * charges. Otherwise, it will commit @page to @memcg.
  */
 static inline void
 memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 004e9d17b47e..bf9f57529dcf 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -22,6 +22,7 @@
 #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
 
 struct address_space;
+struct mem_cgroup;
 
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 #define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
@@ -167,6 +168,10 @@ struct page {
 		struct page *first_page;	/* Compound tail pages */
 	};
 
+#ifdef CONFIG_MEMCG
+	struct mem_cgroup *mem_cgroup;
+#endif
+
 	/*
 	 * On machines where all RAM is mapped into kernel address space,
 	 * we can simply calculate the virtual address. On machines with
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ffe66e381c04..3879d7664dfc 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -722,9 +722,6 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
-#ifdef CONFIG_MEMCG
-	struct page_cgroup *node_page_cgroup;
-#endif
 #endif
 #ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
@@ -1078,7 +1075,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 struct page;
-struct page_cgroup;
 struct mem_section {
 	/*
 	 * This is, logically, a pointer to an array of struct
@@ -1096,14 +1092,6 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
-#ifdef CONFIG_MEMCG
-	/*
-	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
-	 * section. (see memcontrol.h/page_cgroup.h about this.)
-	 */
-	struct page_cgroup *page_cgroup;
-	unsigned long pad;
-#endif
 	/*
 	 * WARNING: mem_section must be a power-of-2 in size for the
 	 * calculation and use of SECTION_ROOT_MASK to make sense.
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
deleted file mode 100644
index 5c831f1eca79..000000000000
--- a/include/linux/page_cgroup.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef __LINUX_PAGE_CGROUP_H
-#define __LINUX_PAGE_CGROUP_H
-
-enum {
-	/* flags for mem_cgroup */
-	PCG_USED = 0x01,	/* This page is charged to a memcg */
-	PCG_MEM = 0x02,		/* This page holds a memory charge */
-	PCG_MEMSW = 0x04,	/* This page holds a memory+swap charge */
-};
-
-struct pglist_data;
-
-#ifdef CONFIG_MEMCG
-struct mem_cgroup;
-
-/*
- * Page Cgroup can be considered as an extended mem_map.
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- * All page cgroups are allocated at boot or memory hotplug event,
- * then the page cgroup for pfn always exists.
- */
-struct page_cgroup {
-	unsigned long flags;
-	struct mem_cgroup *mem_cgroup;
-};
-
-extern void pgdat_page_cgroup_init(struct pglist_data *pgdat);
-
-#ifdef CONFIG_SPARSEMEM
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-extern void page_cgroup_init(void);
-#else
-extern void page_cgroup_init_flatmem(void);
-static inline void page_cgroup_init(void)
-{
-}
-#endif
-
-struct page_cgroup *lookup_page_cgroup(struct page *page);
-
-static inline int PageCgroupUsed(struct page_cgroup *pc)
-{
-	return !!(pc->flags & PCG_USED);
-}
-#else /* !CONFIG_MEMCG */
-struct page_cgroup;
-
-static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-}
-
-static inline struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	return NULL;
-}
-
-static inline void page_cgroup_init(void)
-{
-}
-
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-#endif /* CONFIG_MEMCG */
-
-#include <linux/swap.h>
-
-#ifdef CONFIG_MEMCG_SWAP
-extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
-					unsigned short old, unsigned short new);
-extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
-extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
-extern int swap_cgroup_swapon(int type, unsigned long max_pages);
-extern void swap_cgroup_swapoff(int type);
-#else
-
-static inline
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
-{
-	return 0;
-}
-
-static inline
-unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
-{
-	return 0;
-}
-
-static inline int
-swap_cgroup_swapon(int type, unsigned long max_pages)
-{
-	return 0;
-}
-
-static inline void swap_cgroup_swapoff(int type)
-{
-	return;
-}
-
-#endif /* CONFIG_MEMCG_SWAP */
-
-#endif /* __LINUX_PAGE_CGROUP_H */
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
new file mode 100644
index 000000000000..955421575d16
--- /dev/null
+++ b/include/linux/page_counter.h
@@ -0,0 +1,51 @@
+#ifndef _LINUX_PAGE_COUNTER_H
+#define _LINUX_PAGE_COUNTER_H
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+struct page_counter {
+	atomic_long_t count;
+	unsigned long limit;
+	struct page_counter *parent;
+
+	/* legacy */
+	unsigned long watermark;
+	unsigned long failcnt;
+};
+
+#if BITS_PER_LONG == 32
+#define PAGE_COUNTER_MAX LONG_MAX
+#else
+#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
+#endif
+
+static inline void page_counter_init(struct page_counter *counter,
+				     struct page_counter *parent)
+{
+	atomic_long_set(&counter->count, 0);
+	counter->limit = PAGE_COUNTER_MAX;
+	counter->parent = parent;
+}
+
+static inline unsigned long page_counter_read(struct page_counter *counter)
+{
+	return atomic_long_read(&counter->count);
+}
+
+void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail);
+void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_limit(struct page_counter *counter, unsigned long limit);
+int page_counter_memparse(const char *buf, unsigned long *nr_pages);
+
+static inline void page_counter_reset_watermark(struct page_counter *counter)
+{
+	counter->watermark = page_counter_read(counter);
+}
+
+#endif /* _LINUX_PAGE_COUNTER_H */
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 51ce60c35f4c..530b249f7ea4 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -147,28 +147,42 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 }
 
 /**
- * percpu_ref_get - increment a percpu refcount
+ * percpu_ref_get_many - increment a percpu refcount
  * @ref: percpu_ref to get
+ * @nr: number of references to get
  *
- * Analagous to atomic_long_inc().
+ * Analogous to atomic_long_add().
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_get(struct percpu_ref *ref)
+static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_inc(*percpu_count);
+		this_cpu_add(*percpu_count, nr);
 	else
-		atomic_long_inc(&ref->count);
+		atomic_long_add(nr, &ref->count);
 
 	rcu_read_unlock_sched();
 }
 
 /**
+ * percpu_ref_get - increment a percpu refcount
+ * @ref: percpu_ref to get
+ *
+ * Analagous to atomic_long_inc().
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_get(struct percpu_ref *ref)
+{
+	percpu_ref_get_many(ref, 1);
+}
+
+/**
  * percpu_ref_tryget - try to increment a percpu refcount
  * @ref: percpu_ref to try-get
  *
@@ -231,29 +245,44 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 }
 
 /**
- * percpu_ref_put - decrement a percpu refcount
+ * percpu_ref_put_many - decrement a percpu refcount
  * @ref: percpu_ref to put
+ * @nr: number of references to put
  *
  * Decrement the refcount, and if 0, call the release function (which was passed
  * to percpu_ref_init())
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_put(struct percpu_ref *ref)
+static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_dec(*percpu_count);
-	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
+		this_cpu_sub(*percpu_count, nr);
+	else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
 		ref->release(ref);
 
 	rcu_read_unlock_sched();
 }
 
 /**
+ * percpu_ref_put - decrement a percpu refcount
+ * @ref: percpu_ref to put
+ *
+ * Decrement the refcount, and if 0, call the release function (which was passed
+ * to percpu_ref_init())
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_put(struct percpu_ref *ref)
+{
+	percpu_ref_put_many(ref, 1);
+}
+
+/**
  * percpu_ref_is_zero - test whether a percpu refcount reached zero
  * @ref: percpu_ref to test
  *
diff --git a/include/linux/printk.h b/include/linux/printk.h
index d78125f73ac4..3dd489f2dedc 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -118,7 +118,6 @@ int no_printk(const char *fmt, ...)
 #ifdef CONFIG_EARLY_PRINTK
 extern asmlinkage __printf(1, 2)
 void early_printk(const char *fmt, ...);
-void early_vprintk(const char *fmt, va_list ap);
 #else
 static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index cc79eff4a1ad..987a73a40ef8 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -52,7 +52,7 @@ extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
-extern void exit_ptrace(struct task_struct *tracer);
+extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
 #define PTRACE_MODE_READ	0x01
 #define PTRACE_MODE_ATTACH	0x02
 #define PTRACE_MODE_NOAUDIT	0x04
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
deleted file mode 100644
index 56b7bc32db4f..000000000000
--- a/include/linux/res_counter.h
+++ /dev/null
@@ -1,223 +0,0 @@
-#ifndef __RES_COUNTER_H__
-#define __RES_COUNTER_H__
-
-/*
- * Resource Counters
- * Contain common data types and routines for resource accounting
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- * See Documentation/cgroups/resource_counter.txt for more
- * info about what this counter is.
- */
-
-#include <linux/spinlock.h>
-#include <linux/errno.h>
-
-/*
- * The core object. the cgroup that wishes to account for some
- * resource may include this counter into its structures and use
- * the helpers described beyond
- */
-
-struct res_counter {
-	/*
-	 * the current resource consumption level
-	 */
-	unsigned long long usage;
-	/*
-	 * the maximal value of the usage from the counter creation
-	 */
-	unsigned long long max_usage;
-	/*
-	 * the limit that usage cannot exceed
-	 */
-	unsigned long long limit;
-	/*
-	 * the limit that usage can be exceed
-	 */
-	unsigned long long soft_limit;
-	/*
-	 * the number of unsuccessful attempts to consume the resource
-	 */
-	unsigned long long failcnt;
-	/*
-	 * the lock to protect all of the above.
-	 * the routines below consider this to be IRQ-safe
-	 */
-	spinlock_t lock;
-	/*
-	 * Parent counter, used for hierarchial resource accounting
-	 */
-	struct res_counter *parent;
-};
-
-#define RES_COUNTER_MAX ULLONG_MAX
-
-/**
- * Helpers to interact with userspace
- * res_counter_read_u64() - returns the value of the specified member.
- * res_counter_read/_write - put/get the specified fields from the
- * res_counter struct to/from the user
- *
- * @counter:     the counter in question
- * @member:  the field to work with (see RES_xxx below)
- * @buf:     the buffer to opeate on,...
- * @nbytes:  its size...
- * @pos:     and the offset.
- */
-
-u64 res_counter_read_u64(struct res_counter *counter, int member);
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *buf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *s));
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *res);
-
-/*
- * the field descriptors. one for each member of res_counter
- */
-
-enum {
-	RES_USAGE,
-	RES_MAX_USAGE,
-	RES_LIMIT,
-	RES_FAILCNT,
-	RES_SOFT_LIMIT,
-};
-
-/*
- * helpers for accounting
- */
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent);
-
-/*
- * charge - try to consume more resource.
- *
- * @counter: the counter
- * @val: the amount of the resource. each controller defines its own
- *       units, e.g. numbers, bytes, Kbytes, etc
- *
- * returns 0 on success and <0 if the counter->usage will exceed the
- * counter->limit
- *
- * charge_nofail works the same, except that it charges the resource
- * counter unconditionally, and returns < 0 if the after the current
- * charge we are over limit.
- */
-
-int __must_check res_counter_charge(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-int res_counter_charge_nofail(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-
-/*
- * uncharge - tell that some portion of the resource is released
- *
- * @counter: the counter
- * @val: the amount of the resource
- *
- * these calls check for usage underflow and show a warning on the console
- *
- * returns the total charges still present in @counter.
- */
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val);
-/**
- * res_counter_margin - calculate chargeable space of a counter
- * @cnt: the counter
- *
- * Returns the difference between the hard limit and the current usage
- * of resource counter @cnt.
- */
-static inline unsigned long long res_counter_margin(struct res_counter *cnt)
-{
-	unsigned long long margin;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->limit > cnt->usage)
-		margin = cnt->limit - cnt->usage;
-	else
-		margin = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return margin;
-}
-
-/**
- * Get the difference between the usage and the soft limit
- * @cnt: The counter
- *
- * Returns 0 if usage is less than or equal to soft limit
- * The difference between usage and soft limit, otherwise.
- */
-static inline unsigned long long
-res_counter_soft_limit_excess(struct res_counter *cnt)
-{
-	unsigned long long excess;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= cnt->soft_limit)
-		excess = 0;
-	else
-		excess = cnt->usage - cnt->soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return excess;
-}
-
-static inline void res_counter_reset_max(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->max_usage = cnt->usage;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline void res_counter_reset_failcnt(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->failcnt = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline int res_counter_set_limit(struct res_counter *cnt,
-		unsigned long long limit)
-{
-	unsigned long flags;
-	int ret = -EBUSY;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= limit) {
-		cnt->limit = limit;
-		ret = 0;
-	}
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return ret;
-}
-
-static inline int
-res_counter_set_soft_limit(struct res_counter *cnt,
-				unsigned long long soft_limit)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->soft_limit = soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return 0;
-}
-
-#endif
diff --git a/include/linux/slab.h b/include/linux/slab.h
index c265bec6a57d..8a2457d42fc8 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -513,10 +513,6 @@ struct memcg_cache_params {
 
 int memcg_update_all_caches(int num_memcgs);
 
-struct seq_file;
-int cache_show(struct kmem_cache *s, struct seq_file *m);
-void print_slabinfo_header(struct seq_file *m);
-
 /**
  * kmalloc_array - allocate memory for an array.
  * @n: number of elements.
diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
new file mode 100644
index 000000000000..145306bdc92f
--- /dev/null
+++ b/include/linux/swap_cgroup.h
@@ -0,0 +1,42 @@
+#ifndef __LINUX_SWAP_CGROUP_H
+#define __LINUX_SWAP_CGROUP_H
+
+#include <linux/swap.h>
+
+#ifdef CONFIG_MEMCG_SWAP
+
+extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
+					unsigned short old, unsigned short new);
+extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
+extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
+extern int swap_cgroup_swapon(int type, unsigned long max_pages);
+extern void swap_cgroup_swapoff(int type);
+
+#else
+
+static inline
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+{
+	return 0;
+}
+
+static inline
+unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
+{
+	return 0;
+}
+
+static inline int
+swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	return 0;
+}
+
+static inline void swap_cgroup_swapoff(int type)
+{
+	return;
+}
+
+#endif /* CONFIG_MEMCG_SWAP */
+
+#endif /* __LINUX_SWAP_CGROUP_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index e6f235ebf6c9..7ff44e062a38 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,8 +54,8 @@
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
-#include <linux/res_counter.h>
 #include <linux/static_key.h>
 #include <linux/aio.h>
 #include <linux/sched.h>
@@ -1062,7 +1062,7 @@ enum cg_proto_flags {
 };
 
 struct cg_proto {
-	struct res_counter	memory_allocated;	/* Current allocated memory. */
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
 	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
 	int			memory_pressure;
 	long			sysctl_mem[3];
@@ -1214,34 +1214,26 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 					      unsigned long amt,
 					      int *parent_status)
 {
-	struct res_counter *fail;
-	int ret;
+	page_counter_charge(&prot->memory_allocated, amt);
 
-	ret = res_counter_charge_nofail(&prot->memory_allocated,
-					amt << PAGE_SHIFT, &fail);
-	if (ret < 0)
+	if (page_counter_read(&prot->memory_allocated) >
+	    prot->memory_allocated.limit)
 		*parent_status = OVER_LIMIT;
 }
 
 static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
 					      unsigned long amt)
 {
-	res_counter_uncharge(&prot->memory_allocated, amt << PAGE_SHIFT);
-}
-
-static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
-{
-	u64 ret;
-	ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
-	return ret >> PAGE_SHIFT;
+	page_counter_uncharge(&prot->memory_allocated, amt);
 }
 
 static inline long
 sk_memory_allocated(const struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 
 	return atomic_long_read(prot->memory_allocated);
 }
@@ -1255,7 +1247,7 @@ sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
 		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
 		/* update the root cgroup regardless */
 		atomic_long_add_return(amt, prot->memory_allocated);
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 	}
 
 	return atomic_long_add_return(amt, prot->memory_allocated);
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 43aaba1cc037..0956373b56db 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -153,6 +153,7 @@ enum
 	KERN_MAX_LOCK_DEPTH=74, /* int: rtmutex's maximum lock depth */
 	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
 	KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */
+	KERN_PANIC_ON_WARN=77, /* int: call panic() in WARN() functions */
 };