Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

16 files changed, 113 insertions, 249 deletions

diff --git a/mm/bounce.c b/mm/bounce.c
index e590272fe7a..65f5e17e411 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -14,16 +14,15 @@
 #include <linux/hash.h>
 #include <linux/highmem.h>
 #include <linux/blktrace_api.h>
-#include <trace/block.h>
 #include <asm/tlbflush.h>
 
+#include <trace/events/block.h>
+
 #define POOL_SIZE	64
 #define ISA_POOL_SIZE	16
 
 static mempool_t *page_pool, *isa_page_pool;
 
-DEFINE_TRACE(block_bio_bounce);
-
 #ifdef CONFIG_HIGHMEM
 static __init int init_emergency_pool(void)
 {
diff --git a/mm/filemap.c b/mm/filemap.c
index 379ff0bcbf6..1b60f30cebf 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -121,7 +121,6 @@ void __remove_from_page_cache(struct page *page)
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	BUG_ON(page_mapped(page));
-	mem_cgroup_uncharge_cache_page(page);
 
 	/*
 	 * Some filesystems seem to re-dirty the page even after
@@ -145,6 +144,7 @@ void remove_from_page_cache(struct page *page)
 	spin_lock_irq(&mapping->tree_lock);
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
+	mem_cgroup_uncharge_cache_page(page);
 }
 
 static int sync_page(void *word)
@@ -476,13 +476,13 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 		if (likely(!error)) {
 			mapping->nrpages++;
 			__inc_zone_page_state(page, NR_FILE_PAGES);
+			spin_unlock_irq(&mapping->tree_lock);
 		} else {
 			page->mapping = NULL;
+			spin_unlock_irq(&mapping->tree_lock);
 			mem_cgroup_uncharge_cache_page(page);
 			page_cache_release(page);
 		}
-
-		spin_unlock_irq(&mapping->tree_lock);
 		radix_tree_preload_end();
 	} else
 		mem_cgroup_uncharge_cache_page(page);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 28c655ba935..e83ad2c9228 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -316,7 +316,7 @@ static void resv_map_release(struct kref *ref)
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 {
 	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	if (!(vma->vm_flags & VM_SHARED))
+	if (!(vma->vm_flags & VM_MAYSHARE))
 		return (struct resv_map *)(get_vma_private_data(vma) &
 							~HPAGE_RESV_MASK);
 	return NULL;
@@ -325,7 +325,7 @@ static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 {
 	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	VM_BUG_ON(vma->vm_flags & VM_SHARED);
+	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
 
 	set_vma_private_data(vma, (get_vma_private_data(vma) &
 				HPAGE_RESV_MASK) | (unsigned long)map);
@@ -334,7 +334,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
 {
 	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	VM_BUG_ON(vma->vm_flags & VM_SHARED);
+	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
 
 	set_vma_private_data(vma, get_vma_private_data(vma) | flags);
 }
@@ -353,7 +353,7 @@ static void decrement_hugepage_resv_vma(struct hstate *h,
 	if (vma->vm_flags & VM_NORESERVE)
 		return;
 
-	if (vma->vm_flags & VM_SHARED) {
+	if (vma->vm_flags & VM_MAYSHARE) {
 		/* Shared mappings always use reserves */
 		h->resv_huge_pages--;
 	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
@@ -369,14 +369,14 @@ static void decrement_hugepage_resv_vma(struct hstate *h,
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
 	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	if (!(vma->vm_flags & VM_SHARED))
+	if (!(vma->vm_flags & VM_MAYSHARE))
 		vma->vm_private_data = (void *)0;
 }
 
 /* Returns true if the VMA has associated reserve pages */
 static int vma_has_reserves(struct vm_area_struct *vma)
 {
-	if (vma->vm_flags & VM_SHARED)
+	if (vma->vm_flags & VM_MAYSHARE)
 		return 1;
 	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		return 1;
@@ -924,7 +924,7 @@ static long vma_needs_reservation(struct hstate *h,
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct inode *inode = mapping->host;
 
-	if (vma->vm_flags & VM_SHARED) {
+	if (vma->vm_flags & VM_MAYSHARE) {
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
 		return region_chg(&inode->i_mapping->private_list,
 							idx, idx + 1);
@@ -949,7 +949,7 @@ static void vma_commit_reservation(struct hstate *h,
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct inode *inode = mapping->host;
 
-	if (vma->vm_flags & VM_SHARED) {
+	if (vma->vm_flags & VM_MAYSHARE) {
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
 		region_add(&inode->i_mapping->private_list, idx, idx + 1);
 
@@ -1893,7 +1893,7 @@ retry_avoidcopy:
 	 * at the time of fork() could consume its reserves on COW instead
 	 * of the full address range.
 	 */
-	if (!(vma->vm_flags & VM_SHARED) &&
+	if (!(vma->vm_flags & VM_MAYSHARE) &&
 			is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
 			old_page != pagecache_page)
 		outside_reserve = 1;
@@ -2000,7 +2000,7 @@ retry:
 		clear_huge_page(page, address, huge_page_size(h));
 		__SetPageUptodate(page);
 
-		if (vma->vm_flags & VM_SHARED) {
+		if (vma->vm_flags & VM_MAYSHARE) {
 			int err;
 			struct inode *inode = mapping->host;
 
@@ -2104,7 +2104,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			goto out_mutex;
 		}
 
-		if (!(vma->vm_flags & VM_SHARED))
+		if (!(vma->vm_flags & VM_MAYSHARE))
 			pagecache_page = hugetlbfs_pagecache_page(h,
 								vma, address);
 	}
@@ -2289,7 +2289,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * to reserve the full area even if read-only as mprotect() may be
 	 * called to make the mapping read-write. Assume !vma is a shm mapping
 	 */
-	if (!vma || vma->vm_flags & VM_SHARED)
+	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		chg = region_chg(&inode->i_mapping->private_list, from, to);
 	else {
 		struct resv_map *resv_map = resv_map_alloc();
@@ -2330,7 +2330,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * consumed reservations are stored in the map. Hence, nothing
 	 * else has to be done for private mappings here
 	 */
-	if (!vma || vma->vm_flags & VM_SHARED)
+	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 01c2d8f1468..78eb8552818 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -314,14 +314,6 @@ static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return mem;
 }
 
-static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
-{
-	if (!mem)
-		return true;
-	return css_is_removed(&mem->css);
-}
-
-
 /*
  * Call callback function against all cgroup under hierarchy tree.
  */
@@ -932,7 +924,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	if (unlikely(!mem))
 		return 0;
 
-	VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem));
+	VM_BUG_ON(css_is_removed(&mem->css));
 
 	while (1) {
 		int ret;
@@ -1488,8 +1480,9 @@ void mem_cgroup_uncharge_cache_page(struct page *page)
 	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
 }
 
+#ifdef CONFIG_SWAP
 /*
- * called from __delete_from_swap_cache() and drop "page" account.
+ * called after __delete_from_swap_cache() and drop "page" account.
  * memcg information is recorded to swap_cgroup of "ent"
  */
 void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
@@ -1506,6 +1499,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 	if (memcg)
 		css_put(&memcg->css);
 }
+#endif
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 /*
diff --git a/mm/mlock.c b/mm/mlock.c
index cbe9e0581b7..ac130433c7d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -629,52 +629,43 @@ void user_shm_unlock(size_t size, struct user_struct *user)
 	free_uid(user);
 }
 
-void *alloc_locked_buffer(size_t size)
+int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+			  size_t size)
 {
-	unsigned long rlim, vm, pgsz;
-	void *buffer = NULL;
+	unsigned long lim, vm, pgsz;
+	int error = -ENOMEM;
 
 	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
-	down_write(&current->mm->mmap_sem);
-
-	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
-	vm   = current->mm->total_vm + pgsz;
-	if (rlim < vm)
-		goto out;
+	down_write(&mm->mmap_sem);
 
-	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
-	vm   = current->mm->locked_vm + pgsz;
-	if (rlim < vm)
+	lim = rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+	vm   = mm->total_vm + pgsz;
+	if (lim < vm)
 		goto out;
 
-	buffer = kzalloc(size, GFP_KERNEL);
-	if (!buffer)
+	lim = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+	vm   = mm->locked_vm + pgsz;
+	if (lim < vm)
 		goto out;
 
-	current->mm->total_vm  += pgsz;
-	current->mm->locked_vm += pgsz;
+	mm->total_vm  += pgsz;
+	mm->locked_vm += pgsz;
 
+	error = 0;
  out:
-	up_write(&current->mm->mmap_sem);
-	return buffer;
+	up_write(&mm->mmap_sem);
+	return error;
 }
 
-void release_locked_buffer(void *buffer, size_t size)
+void refund_locked_memory(struct mm_struct *mm, size_t size)
 {
 	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
-	down_write(&current->mm->mmap_sem);
-
-	current->mm->total_vm  -= pgsz;
-	current->mm->locked_vm -= pgsz;
-
-	up_write(&current->mm->mmap_sem);
-}
+	down_write(&mm->mmap_sem);
 
-void free_locked_buffer(void *buffer, size_t size)
-{
-	release_locked_buffer(buffer, size);
+	mm->total_vm  -= pgsz;
+	mm->locked_vm -= pgsz;
 
-	kfree(buffer);
+	up_write(&mm->mmap_sem);
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 92bcf1db16b..a7b2460e922 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -284,22 +284,28 @@ static void dump_tasks(const struct mem_cgroup *mem)
 	printk(KERN_INFO "[ pid ]   uid  tgid total_vm      rss cpu oom_adj "
 	       "name\n");
 	do_each_thread(g, p) {
-		/*
-		 * total_vm and rss sizes do not exist for tasks with a
-		 * detached mm so there's no need to report them.
-		 */
-		if (!p->mm)
-			continue;
+		struct mm_struct *mm;
+
 		if (mem && !task_in_mem_cgroup(p, mem))
 			continue;
 		if (!thread_group_leader(p))
 			continue;
 
 		task_lock(p);
+		mm = p->mm;
+		if (!mm) {
+			/*
+			 * total_vm and rss sizes do not exist for tasks with no
+			 * mm so there's no need to report them; they can't be
+			 * oom killed anyway.
+			 */
+			task_unlock(p);
+			continue;
+		}
 		printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
-		       p->pid, __task_cred(p)->uid, p->tgid,
-		       p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p),
-		       p->oomkilladj, p->comm);
+		       p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
+		       get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj,
+		       p->comm);
 		task_unlock(p);
 	} while_each_thread(g, p);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fe753ecf2aa..474c7e9dd51 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -149,10 +149,6 @@ static unsigned long __meminitdata dma_reserve;
   static int __meminitdata nr_nodemap_entries;
   static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
   static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-  static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
-  static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
   static unsigned long __initdata required_kernelcore;
   static unsigned long __initdata required_movablecore;
   static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
@@ -3103,64 +3099,6 @@ void __init sparse_memory_present_with_active_regions(int nid)
 }
 
 /**
- * push_node_boundaries - Push node boundaries to at least the requested boundary
- * @nid: The nid of the node to push the boundary for
- * @start_pfn: The start pfn of the node
- * @end_pfn: The end pfn of the node
- *
- * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
- * time. Specifically, on x86_64, SRAT will report ranges that can potentially
- * be hotplugged even though no physical memory exists. This function allows
- * an arch to push out the node boundaries so mem_map is allocated that can
- * be used later.
- */
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-void __init push_node_boundaries(unsigned int nid,
-		unsigned long start_pfn, unsigned long end_pfn)
-{
-	mminit_dprintk(MMINIT_TRACE, "zoneboundary",
-			"Entering push_node_boundaries(%u, %lu, %lu)\n",
-			nid, start_pfn, end_pfn);
-
-	/* Initialise the boundary for this node if necessary */
-	if (node_boundary_end_pfn[nid] == 0)
-		node_boundary_start_pfn[nid] = -1UL;
-
-	/* Update the boundaries */
-	if (node_boundary_start_pfn[nid] > start_pfn)
-		node_boundary_start_pfn[nid] = start_pfn;
-	if (node_boundary_end_pfn[nid] < end_pfn)
-		node_boundary_end_pfn[nid] = end_pfn;
-}
-
-/* If necessary, push the node boundary out for reserve hotadd */
-static void __meminit account_node_boundary(unsigned int nid,
-		unsigned long *start_pfn, unsigned long *end_pfn)
-{
-	mminit_dprintk(MMINIT_TRACE, "zoneboundary",
-			"Entering account_node_boundary(%u, %lu, %lu)\n",
-			nid, *start_pfn, *end_pfn);
-
-	/* Return if boundary information has not been provided */
-	if (node_boundary_end_pfn[nid] == 0)
-		return;
-
-	/* Check the boundaries and update if necessary */
-	if (node_boundary_start_pfn[nid] < *start_pfn)
-		*start_pfn = node_boundary_start_pfn[nid];
-	if (node_boundary_end_pfn[nid] > *end_pfn)
-		*end_pfn = node_boundary_end_pfn[nid];
-}
-#else
-void __init push_node_boundaries(unsigned int nid,
-		unsigned long start_pfn, unsigned long end_pfn) {}
-
-static void __meminit account_node_boundary(unsigned int nid,
-		unsigned long *start_pfn, unsigned long *end_pfn) {}
-#endif
-
-
-/**
  * get_pfn_range_for_nid - Return the start and end page frames for a node
  * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
  * @start_pfn: Passed by reference. On return, it will have the node start_pfn.
@@ -3185,9 +3123,6 @@ void __meminit get_pfn_range_for_nid(unsigned int nid,
 
 	if (*start_pfn == -1UL)
 		*start_pfn = 0;
-
-	/* Push the node boundaries out if requested */
-	account_node_boundary(nid, start_pfn, end_pfn);
 }
 
 /*
@@ -3793,10 +3728,6 @@ void __init remove_all_active_ranges(void)
 {
 	memset(early_node_map, 0, sizeof(early_node_map));
 	nr_nodemap_entries = 0;
-#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
-	memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn));
-	memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn));
-#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
 }
 
 /* Compare two active node_active_regions */
diff --git a/mm/percpu.c b/mm/percpu.c
index 1aa5d8fbca1..c0b2c1a76e8 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -23,7 +23,7 @@
  * Allocation is done in offset-size areas of single unit space.  Ie,
  * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0,
  * c1:u1, c1:u2 and c1:u3.  Percpu access can be done by configuring
- * percpu base registers UNIT_SIZE apart.
+ * percpu base registers pcpu_unit_size apart.
  *
  * There are usually many small percpu allocations many of them as
  * small as 4 bytes.  The allocator organizes chunks into lists
@@ -38,8 +38,8 @@
  * region and negative allocated.  Allocation inside a chunk is done
  * by scanning this map sequentially and serving the first matching
  * entry.  This is mostly copied from the percpu_modalloc() allocator.
- * Chunks are also linked into a rb tree to ease address to chunk
- * mapping during free.
+ * Chunks can be determined from the address using the index field
+ * in the page struct. The index field contains a pointer to the chunk.
  *
  * To use this allocator, arch code should do the followings.
  *
@@ -61,7 +61,6 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/pfn.h>
-#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
@@ -88,7 +87,6 @@
 
 struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
-	struct rb_node		rb_node;	/* key is chunk->vm->addr */
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
 	struct vm_struct	*vm;		/* mapped vmalloc region */
@@ -110,9 +108,21 @@ static size_t pcpu_chunk_struct_size __read_mostly;
 void *pcpu_base_addr __read_mostly;
 EXPORT_SYMBOL_GPL(pcpu_base_addr);
 
-/* optional reserved chunk, only accessible for reserved allocations */
+/*
+ * The first chunk which always exists.  Note that unlike other
+ * chunks, this one can be allocated and mapped in several different
+ * ways and thus often doesn't live in the vmalloc area.
+ */
+static struct pcpu_chunk *pcpu_first_chunk;
+
+/*
+ * Optional reserved chunk.  This chunk reserves part of the first
+ * chunk and serves it for reserved allocations.  The amount of
+ * reserved offset is in pcpu_reserved_chunk_limit.  When reserved
+ * area doesn't exist, the following variables contain NULL and 0
+ * respectively.
+ */
 static struct pcpu_chunk *pcpu_reserved_chunk;
-/* offset limit of the reserved chunk */
 static int pcpu_reserved_chunk_limit;
 
 /*
@@ -121,7 +131,7 @@ static int pcpu_reserved_chunk_limit;
  * There are two locks - pcpu_alloc_mutex and pcpu_lock.  The former
  * protects allocation/reclaim paths, chunks and chunk->page arrays.
  * The latter is a spinlock and protects the index data structures -
- * chunk slots, rbtree, chunks and area maps in chunks.
+ * chunk slots, chunks and area maps in chunks.
  *
  * During allocation, pcpu_alloc_mutex is kept locked all the time and
  * pcpu_lock is grabbed and released as necessary.  All actual memory
@@ -140,7 +150,6 @@ static DEFINE_MUTEX(pcpu_alloc_mutex);	/* protects whole alloc and reclaim */
 static DEFINE_SPINLOCK(pcpu_lock);	/* protects index data structures */
 
 static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
-static struct rb_root pcpu_addr_root = RB_ROOT;	/* chunks by address */
 
 /* reclaim work to release fully free chunks, scheduled from free path */
 static void pcpu_reclaim(struct work_struct *work);
@@ -191,6 +200,18 @@ static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk,
 	return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
 }
 
+/* set the pointer to a chunk in a page struct */
+static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
+{
+	page->index = (unsigned long)pcpu;
+}
+
+/* obtain pointer to a chunk from a page struct */
+static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
+{
+	return (struct pcpu_chunk *)page->index;
+}
+
 /**
  * pcpu_mem_alloc - allocate memory
  * @size: bytes to allocate
@@ -257,93 +278,26 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
 	}
 }
 
-static struct rb_node **pcpu_chunk_rb_search(void *addr,
-					     struct rb_node **parentp)
-{
-	struct rb_node **p = &pcpu_addr_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct pcpu_chunk *chunk;
-
-	while (*p) {
-		parent = *p;
-		chunk = rb_entry(parent, struct pcpu_chunk, rb_node);
-
-		if (addr < chunk->vm->addr)
-			p = &(*p)->rb_left;
-		else if (addr > chunk->vm->addr)
-			p = &(*p)->rb_right;
-		else
-			break;
-	}
-
-	if (parentp)
-		*parentp = parent;
-	return p;
-}
-
 /**
- * pcpu_chunk_addr_search - search for chunk containing specified address
- * @addr: address to search for
- *
- * Look for chunk which might contain @addr.  More specifically, it
- * searchs for the chunk with the highest start address which isn't
- * beyond @addr.
- *
- * CONTEXT:
- * pcpu_lock.
+ * pcpu_chunk_addr_search - determine chunk containing specified address
+ * @addr: address for which the chunk needs to be determined.
  *
  * RETURNS:
  * The address of the found chunk.
  */
 static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 {
-	struct rb_node *n, *parent;
-	struct pcpu_chunk *chunk;
+	void *first_start = pcpu_first_chunk->vm->addr;
 
-	/* is it in the reserved chunk? */
-	if (pcpu_reserved_chunk) {
-		void *start = pcpu_reserved_chunk->vm->addr;
-
-		if (addr >= start && addr < start + pcpu_reserved_chunk_limit)
+	/* is it in the first chunk? */
+	if (addr >= first_start && addr < first_start + pcpu_chunk_size) {
+		/* is it in the reserved area? */
+		if (addr < first_start + pcpu_reserved_chunk_limit)
 			return pcpu_reserved_chunk;
+		return pcpu_first_chunk;
 	}
 
-	/* nah... search the regular ones */
-	n = *pcpu_chunk_rb_search(addr, &parent);
-	if (!n) {
-		/* no exactly matching chunk, the parent is the closest */
-		n = parent;
-		BUG_ON(!n);
-	}
-	chunk = rb_entry(n, struct pcpu_chunk, rb_node);
-
-	if (addr < chunk->vm->addr) {
-		/* the parent was the next one, look for the previous one */
-		n = rb_prev(n);
-		BUG_ON(!n);
-		chunk = rb_entry(n, struct pcpu_chunk, rb_node);
-	}
-
-	return chunk;
-}
-
-/**
- * pcpu_chunk_addr_insert - insert chunk into address rb tree
- * @new: chunk to insert
- *
- * Insert @new into address rb tree.
- *
- * CONTEXT:
- * pcpu_lock.
- */
-static void pcpu_chunk_addr_insert(struct pcpu_chunk *new)
-{
-	struct rb_node **p, *parent;
-
-	p = pcpu_chunk_rb_search(new->vm->addr, &parent);
-	BUG_ON(*p);
-	rb_link_node(&new->rb_node, parent, p);
-	rb_insert_color(&new->rb_node, &pcpu_addr_root);
+	return pcpu_get_page_chunk(vmalloc_to_page(addr));
 }
 
 /**
@@ -755,6 +709,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 						  alloc_mask, 0);
 			if (!*pagep)
 				goto err;
+			pcpu_set_page_chunk(*pagep, chunk);
 		}
 	}
 
@@ -879,7 +834,6 @@ restart:
 
 	spin_lock_irq(&pcpu_lock);
 	pcpu_chunk_relocate(chunk, -1);
-	pcpu_chunk_addr_insert(chunk);
 	goto restart;
 
 area_found:
@@ -968,7 +922,6 @@ static void pcpu_reclaim(struct work_struct *work)
 		if (chunk == list_first_entry(head, struct pcpu_chunk, list))
 			continue;
 
-		rb_erase(&chunk->rb_node, &pcpu_addr_root);
 		list_move(&chunk->list, &todo);
 	}
 
@@ -1147,7 +1100,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 
 	if (reserved_size) {
 		schunk->free_size = reserved_size;
-		pcpu_reserved_chunk = schunk;	/* not for dynamic alloc */
+		pcpu_reserved_chunk = schunk;
+		pcpu_reserved_chunk_limit = static_size + reserved_size;
 	} else {
 		schunk->free_size = dyn_size;
 		dyn_size = 0;			/* dynamic area covered */
@@ -1158,8 +1112,6 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 	if (schunk->free_size)
 		schunk->map[schunk->map_used++] = schunk->free_size;
 
-	pcpu_reserved_chunk_limit = static_size + schunk->free_size;
-
 	/* init dynamic chunk if necessary */
 	if (dyn_size) {
 		dchunk = alloc_bootmem(sizeof(struct pcpu_chunk));
@@ -1226,13 +1178,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 	}
 
 	/* link the first chunk in */
-	if (!dchunk) {
-		pcpu_chunk_relocate(schunk, -1);
-		pcpu_chunk_addr_insert(schunk);
-	} else {
-		pcpu_chunk_relocate(dchunk, -1);
-		pcpu_chunk_addr_insert(dchunk);
-	}
+	pcpu_first_chunk = dchunk ?: schunk;
+	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	/* we're done */
 	pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
diff --git a/mm/rmap.c b/mm/rmap.c
index 16521664010..23122af3261 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -14,7 +14,7 @@
  * Original design by Rik van Riel <riel@conectiva.com.br> 2001
  * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
  * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
- * Contributions by Hugh Dickins <hugh@veritas.com> 2003, 2004
+ * Contributions by Hugh Dickins 2003, 2004
  */
 
 /*
diff --git a/mm/slab.c b/mm/slab.c
index 9a90b00d2f9..f85831da908 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -102,7 +102,7 @@
 #include	<linux/cpu.h>
 #include	<linux/sysctl.h>
 #include	<linux/module.h>
-#include	<trace/kmemtrace.h>
+#include	<linux/kmemtrace.h>
 #include	<linux/rcupdate.h>
 #include	<linux/string.h>
 #include	<linux/uaccess.h>
diff --git a/mm/slob.c b/mm/slob.c
index f92e66d558b..9b1737b0787 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -66,7 +66,7 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 #include <asm/atomic.h>
 
 /*
diff --git a/mm/slub.c b/mm/slub.c
index 65ffda5934b..5e805a6fe36 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -17,7 +17,7 @@
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3ecea98ecb4..1416e7e9e02 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -109,8 +109,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
  */
 void __delete_from_swap_cache(struct page *page)
 {
-	swp_entry_t ent = {.val = page_private(page)};
-
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(!PageSwapCache(page));
 	VM_BUG_ON(PageWriteback(page));
@@ -121,7 +119,6 @@ void __delete_from_swap_cache(struct page *page)
 	total_swapcache_pages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	INC_CACHE_INFO(del_total);
-	mem_cgroup_uncharge_swapcache(page, ent);
 }
 
 /**
@@ -191,6 +188,7 @@ void delete_from_swap_cache(struct page *page)
 	__delete_from_swap_cache(page);
 	spin_unlock_irq(&swapper_space.tree_lock);
 
+	mem_cgroup_uncharge_swapcache(page, entry);
 	swap_free(entry);
 	page_cache_release(page);
 }
diff --git a/mm/truncate.c b/mm/truncate.c
index 55206fab7b9..12e1579f916 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -359,6 +359,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	BUG_ON(page_has_private(page));
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
+	mem_cgroup_uncharge_cache_page(page);
 	page_cache_release(page);	/* pagecache ref */
 	return 1;
 failed:
diff --git a/mm/util.c b/mm/util.c
index 55bef160b9f..abc65aa7cdf 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,9 +4,11 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/sched.h>
-#include <linux/tracepoint.h>
 #include <asm/uaccess.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/kmem.h>
+
 /**
  * kstrdup - allocate space for and copy an existing string
  * @s: the string to duplicate
@@ -255,13 +257,6 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
 /* Tracepoints definitions. */
-DEFINE_TRACE(kmalloc);
-DEFINE_TRACE(kmem_cache_alloc);
-DEFINE_TRACE(kmalloc_node);
-DEFINE_TRACE(kmem_cache_alloc_node);
-DEFINE_TRACE(kfree);
-DEFINE_TRACE(kmem_cache_free);
-
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
 EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5fa3eda1f03..d254306562c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -470,10 +470,12 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 		swp_entry_t swap = { .val = page_private(page) };
 		__delete_from_swap_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
+		mem_cgroup_uncharge_swapcache(page, swap);
 		swap_free(swap);
 	} else {
 		__remove_from_page_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
+		mem_cgroup_uncharge_cache_page(page);
 	}
 
 	return 1;