15 files changed, 83 insertions, 86 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 379ff0bcbf6e..1b60f30cebfa 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 28c655ba9353..e83ad2c9228c 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/madvise.c b/mm/madvise.c
index 36d6ea2b6340..b9ce574827c8 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -112,14 +112,6 @@ static long madvise_willneed(struct vm_area_struct * vma,
         if (!file)
                 return -EBADF;
 
-        /*
-         * Page cache readahead assumes page cache pages are order-0 which
-         * is not the case for hugetlbfs. Do not give a bad return value
-         * but ignore the advice.
-         */
-        if (vma->vm_flags & VM_HUGETLB)
-                return 0;
-
         if (file->f_mapping->a_ops->get_xip_mem) {
                 /* no bad return value, but ignore advice */
                 return 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 01c2d8f14685..78eb8552818b 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/mmzone.c b/mm/mmzone.c
index 16ce8b955dcf..f5b7d1760213 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -6,6 +6,7 @@
 
 
 #include <linux/stddef.h>
+#include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/module.h>
 
@@ -72,3 +73,17 @@ struct zoneref *next_zones_zonelist(struct zoneref *z,
         *zone = zonelist_zone(z);
         return z;
 }
+
+#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
+int memmap_valid_within(unsigned long pfn,
+                                        struct page *page, struct zone *zone)
+{
+        if (page_to_pfn(page) != pfn)
+                return 0;
+
+        if (page_zone(page) != zone)
+                return 0;
+
+        return 1;
+}
+#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 92bcf1db16b2..a7b2460e922b 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-writeback.c b/mm/page-writeback.c
index 30351f0063ac..bb553c3e955d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -94,12 +94,12 @@ unsigned long vm_dirty_bytes;
 /*
  * The interval between `kupdate'-style writebacks
  */
-unsigned int dirty_writeback_interval = 5 * 100; /* sentiseconds */
+unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */
 
 /*
  * The longest time for which data is allowed to remain dirty
  */
-unsigned int dirty_expire_interval = 30 * 100; /* sentiseconds */
+unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */
 
 /*
  * Flag that makes the machine dump writes/reads and block dirtyings.
@@ -770,7 +770,7 @@ static void wb_kupdate(unsigned long arg)
 
         sync_supers();
 
-        oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval);
+        oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10);
         start_jif = jiffies;
         next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
         nr_to_write = global_page_state(NR_FILE_DIRTY) +
diff --git a/mm/pdflush.c b/mm/pdflush.c
index f2caf96993f8..235ac440c44e 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -58,14 +58,6 @@ static DEFINE_SPINLOCK(pdflush_lock);
 int nr_pdflush_threads = 0;
 
 /*
- * The max/min number of pdflush threads. R/W by sysctl at
- * /proc/sys/vm/nr_pdflush_threads_max/min
- */
-int nr_pdflush_threads_max __read_mostly = MAX_PDFLUSH_THREADS;
-int nr_pdflush_threads_min __read_mostly = MIN_PDFLUSH_THREADS;
-
-
-/*
  * The time at which the pdflush thread pool last went empty
  */
 static unsigned long last_empty_jifs;
@@ -76,7 +68,7 @@ static unsigned long last_empty_jifs;
  * Thread pool management algorithm:
  * 
  * - The minimum and maximum number of pdflush instances are bound
- *   by nr_pdflush_threads_min and nr_pdflush_threads_max.
+ *   by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
  * 
  * - If there have been no idle pdflush instances for 1 second, create
  *   a new one.
@@ -142,13 +134,14 @@ static int __pdflush(struct pdflush_work *my_work)
                  * To throttle creation, we reset last_empty_jifs.
                  */
                 if (time_after(jiffies, last_empty_jifs + 1 * HZ)) {
-                        if (list_empty(&pdflush_list) &&
-                            nr_pdflush_threads < nr_pdflush_threads_max) {
-                                last_empty_jifs = jiffies;
-                                nr_pdflush_threads++;
-                                spin_unlock_irq(&pdflush_lock);
-                                start_one_pdflush_thread();
-                                spin_lock_irq(&pdflush_lock);
+                        if (list_empty(&pdflush_list)) {
+                                if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) {
+                                        last_empty_jifs = jiffies;
+                                        nr_pdflush_threads++;
+                                        spin_unlock_irq(&pdflush_lock);
+                                        start_one_pdflush_thread();
+                                        spin_lock_irq(&pdflush_lock);
+                                }
                         }
                 }
 
@@ -160,7 +153,7 @@ static int __pdflush(struct pdflush_work *my_work)
                  */
                 if (list_empty(&pdflush_list))
                         continue;
-                if (nr_pdflush_threads <= nr_pdflush_threads_min)
+                if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
                         continue;
                 pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
                 if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) {
@@ -266,9 +259,9 @@ static int __init pdflush_init(void)
          * Pre-set nr_pdflush_threads...  If we fail to create,
          * the count will be decremented.
          */
-        nr_pdflush_threads = nr_pdflush_threads_min;
+        nr_pdflush_threads = MIN_PDFLUSH_THREADS;
 
-        for (i = 0; i < nr_pdflush_threads_min; i++)
+        for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
                 start_one_pdflush_thread();
         return 0;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 16521664010d..23122af32611 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/slob.c b/mm/slob.c
index a2d4ab32198d..f92e66d558bd 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -60,6 +60,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/swap.h> /* struct reclaim_state */
 #include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -255,6 +256,8 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 
 static void slob_free_pages(void *b, int order)
 {
+        if (current->reclaim_state)
+                current->reclaim_state->reclaimed_slab += 1 << order;
         free_pages((unsigned long)b, order);
 }
 
@@ -407,7 +410,7 @@ static void slob_free(void *block, int size)
                 spin_unlock_irqrestore(&slob_lock, flags);
                 clear_slob_page(sp);
                 free_slob_page(sp);
-                free_page((unsigned long)b);
+                slob_free_pages(b, 0);
                 return;
         }
 
diff --git a/mm/slub.c b/mm/slub.c
index 7ab54ecbd3f3..65ffda5934b0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/swap.h> /* struct reclaim_state */
 #include <linux/module.h>
 #include <linux/bit_spinlock.h>
 #include <linux/interrupt.h>
@@ -1170,6 +1171,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
         __ClearPageSlab(page);
         reset_page_mapcount(page);
+        if (current->reclaim_state)
+                current->reclaim_state->reclaimed_slab += pages;
         __free_pages(page, order);
 }
 
@@ -1909,7 +1912,7 @@ static inline int calculate_order(int size)
          * Doh this slab cannot be placed using slub_max_order.
          */
         order = slab_order(size, 1, MAX_ORDER, 1);
-        if (order <= MAX_ORDER)
+        if (order < MAX_ORDER)
                 return order;
         return -ENOSYS;
 }
@@ -2522,6 +2525,7 @@ __setup("slub_min_order=", setup_slub_min_order);
 static int __init setup_slub_max_order(char *str)
 {
         get_option(&str, &slub_max_order);
+        slub_max_order = min(slub_max_order, MAX_ORDER - 1);
 
         return 1;
 }
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3ecea98ecb45..1416e7e9e02d 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 55206fab7b99..12e1579f9165 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/vmscan.c b/mm/vmscan.c
index 5fa3eda1f03f..d254306562cd 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;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 66f6130976cb..74d66dba0cbe 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -509,22 +509,11 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m,
                         continue;
 
                 page = pfn_to_page(pfn);
-#ifdef CONFIG_ARCH_FLATMEM_HAS_HOLES
-                /*
-                 * Ordinarily, memory holes in flatmem still have a valid
-                 * memmap for the PFN range. However, an architecture for
-                 * embedded systems (e.g. ARM) can free up the memmap backing
-                 * holes to save memory on the assumption the memmap is
-                 * never used. The page_zone linkages are then broken even
-                 * though pfn_valid() returns true. Skip the page if the
-                 * linkages are broken. Even if this test passed, the impact
-                 * is that the counters for the movable type are off but
-                 * fragmentation monitoring is likely meaningless on small
-                 * systems.
-                 */
-                if (page_zone(page) != zone)
+
+                /* Watch for unexpected holes punched in the memmap */
+                if (!memmap_valid_within(pfn, page, zone))
                         continue;
-#endif
+
                 mtype = get_pageblock_migratetype(page);
 
                 if (mtype < MIGRATE_TYPES)