5 files changed, 158 insertions, 40 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e07e27e846a2..a9963ceddd65 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1176,7 +1176,15 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
         if (vma) {
                 unsigned long off;
 
-                off = vma->vm_pgoff;
+                /*
+                 * for small pages, there is no difference between
+                 * shift and PAGE_SHIFT, so the bit-shift is safe.
+                 * for huge pages, since vm_pgoff is in units of small
+                 * pages, we need to shift off the always 0 bits to get
+                 * a useful offset.
+                 */
+                BUG_ON(shift < PAGE_SHIFT);
+                off = vma->vm_pgoff >> (shift - PAGE_SHIFT);
                 off += (addr - vma->vm_start) >> shift;
                 return offset_il_node(pol, vma, off);
         } else
diff --git a/mm/mempool.c b/mm/mempool.c
index fe6e05289cc5..ccd8cb8cd41f 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -238,8 +238,13 @@ repeat_alloc:
         init_wait(&wait);
         prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
         smp_mb();
-        if (!pool->curr_nr)
-                io_schedule();
+        if (!pool->curr_nr) {
+                /*
+                 * FIXME: this should be io_schedule().  The timeout is there
+                 * as a workaround for some DM problems in 2.6.18.
+                 */
+                io_schedule_timeout(5*HZ);
+        }
         finish_wait(&pool->wait, &wait);
 
         goto repeat_alloc;
diff --git a/mm/mmap.c b/mm/mmap.c
index c1868ecdbc5f..e66a0b524aff 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -30,6 +30,10 @@
 #include <asm/cacheflush.h>
 #include <asm/tlb.h>
 
+#ifndef arch_mmap_check
+#define arch_mmap_check(addr, len, flags)       (0)
+#endif
+
 static void unmap_region(struct mm_struct *mm,
                 struct vm_area_struct *vma, struct vm_area_struct *prev,
                 unsigned long start, unsigned long end);
@@ -913,6 +917,10 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
         if (!len)
                 return -EINVAL;
 
+        error = arch_mmap_check(addr, len, flags);
+        if (error)
+                return error;
+
         /* Careful about overflows.. */
         len = PAGE_ALIGN(len);
         if (!len || len > TASK_SIZE)
@@ -1859,6 +1867,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
         unsigned long flags;
         struct rb_node ** rb_link, * rb_parent;
         pgoff_t pgoff = addr >> PAGE_SHIFT;
+        int error;
 
         len = PAGE_ALIGN(len);
         if (!len)
@@ -1867,6 +1876,12 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
         if ((addr + len) > TASK_SIZE || (addr + len) < addr)
                 return -EINVAL;
 
+        flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+
+        error = arch_mmap_check(addr, len, flags);
+        if (error)
+                return error;
+
         /*
          * mlock MCL_FUTURE?
          */
@@ -1907,8 +1922,6 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
         if (security_vm_enough_memory(len >> PAGE_SHIFT))
                 return -ENOMEM;
 
-        flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
-
         /* Can we just expand an old private anonymous mapping? */
         if (vma_merge(mm, prev, addr, addr + len, flags,
                                         NULL, NULL, pgoff, NULL))
diff --git a/mm/truncate.c b/mm/truncate.c
index cf1b015df4a7..c6ab55ec6883 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -68,10 +68,10 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
                 return 0;
 
         write_lock_irq(&mapping->tree_lock);
-        if (PageDirty(page)) {
-                write_unlock_irq(&mapping->tree_lock);
-                return 0;
-        }
+        if (PageDirty(page))
+                goto failed;
+        if (page_count(page) != 2)      /* caller's ref + pagecache ref */
+                goto failed;
 
         BUG_ON(PagePrivate(page));
         __remove_from_page_cache(page);
@@ -79,6 +79,9 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
         ClearPageUptodate(page);
         page_cache_release(page);       /* pagecache ref */
         return 1;
+failed:
+        write_unlock_irq(&mapping->tree_lock);
+        return 0;
 }
 
 /**
diff --git a/mm/vmstat.c b/mm/vmstat.c
index dfdf24133901..c1b5f4106b38 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -12,6 +12,7 @@
 #include <linux/config.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/cpu.h>
 
 void __get_zone_counts(unsigned long *active, unsigned long *inactive,
                         unsigned long *free, struct pglist_data *pgdat)
@@ -114,17 +115,72 @@ EXPORT_SYMBOL(vm_stat);
 
 #ifdef CONFIG_SMP
 
-#define STAT_THRESHOLD 32
+static int calculate_threshold(struct zone *zone)
+{
+        int threshold;
+        int mem;        /* memory in 128 MB units */
+
+        /*
+         * The threshold scales with the number of processors and the amount
+         * of memory per zone. More memory means that we can defer updates for
+         * longer, more processors could lead to more contention.
+         * fls() is used to have a cheap way of logarithmic scaling.
+         *
+         * Some sample thresholds:
+         *
+         * Threshold    Processors      (fls)   Zonesize        fls(mem+1)
+         * ------------------------------------------------------------------
+         * 8            1               1       0.9-1 GB        4
+         * 16           2               2       0.9-1 GB        4
+         * 20           2               2       1-2 GB          5
+         * 24           2               2       2-4 GB          6
+         * 28           2               2       4-8 GB          7
+         * 32           2               2       8-16 GB         8
+         * 4            2               2       <128M           1
+         * 30           4               3       2-4 GB          5
+         * 48           4               3       8-16 GB         8
+         * 32           8               4       1-2 GB          4
+         * 32           8               4       0.9-1GB         4
+         * 10           16              5       <128M           1
+         * 40           16              5       900M            4
+         * 70           64              7       2-4 GB          5
+         * 84           64              7       4-8 GB          6
+         * 108          512             9       4-8 GB          6
+         * 125          1024            10      8-16 GB         8
+         * 125          1024            10      16-32 GB        9
+         */
+
+        mem = zone->present_pages >> (27 - PAGE_SHIFT);
+
+        threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem));
+
+        /*
+         * Maximum threshold is 125
+         */
+        threshold = min(125, threshold);
+
+        return threshold;
+}
 
 /*
- * Determine pointer to currently valid differential byte given a zone and
- * the item number.
- *
- * Preemption must be off
+ * Refresh the thresholds for each zone.
  */
-static inline s8 *diff_pointer(struct zone *zone, enum zone_stat_item item)
+static void refresh_zone_stat_thresholds(void)
 {
-        return &zone_pcp(zone, smp_processor_id())->vm_stat_diff[item];
+        struct zone *zone;
+        int cpu;
+        int threshold;
+
+        for_each_zone(zone) {
+
+                if (!zone->present_pages)
+                        continue;
+
+                threshold = calculate_threshold(zone);
+
+                for_each_online_cpu(cpu)
+                        zone_pcp(zone, cpu)->stat_threshold = threshold;
+        }
 }
 
 /*
@@ -133,17 +189,16 @@ static inline s8 *diff_pointer(struct zone *zone, enum zone_stat_item item)
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
                                 int delta)
 {
-        s8 *p;
+        struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+        s8 *p = pcp->vm_stat_diff + item;
         long x;
 
-        p = diff_pointer(zone, item);
         x = delta + *p;
 
-        if (unlikely(x > STAT_THRESHOLD || x < -STAT_THRESHOLD)) {
+        if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) {
                 zone_page_state_add(x, zone, item);
                 x = 0;
         }
-
         *p = x;
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
@@ -172,10 +227,12 @@ EXPORT_SYMBOL(mod_zone_page_state);
  * No overflow check is necessary and therefore the differential can be
  * incremented or decremented in place which may allow the compilers to
  * generate better code.
- *
  * The increment or decrement is known and therefore one boundary check can
  * be omitted.
  *
+ * NOTE: These functions are very performance sensitive. Change only
+ * with care.
+ *
  * Some processors have inc/dec instructions that are atomic vs an interrupt.
  * However, the code must first determine the differential location in a zone
  * based on the processor number and then inc/dec the counter. There is no
@@ -185,13 +242,16 @@ EXPORT_SYMBOL(mod_zone_page_state);
  */
 static void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-        s8 *p = diff_pointer(zone, item);
+        struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+        s8 *p = pcp->vm_stat_diff + item;
 
         (*p)++;
 
-        if (unlikely(*p > STAT_THRESHOLD)) {
-                zone_page_state_add(*p, zone, item);
-                *p = 0;
+        if (unlikely(*p > pcp->stat_threshold)) {
+                int overstep = pcp->stat_threshold / 2;
+
+                zone_page_state_add(*p + overstep, zone, item);
+                *p = -overstep;
         }
 }
 
@@ -204,13 +264,16 @@ EXPORT_SYMBOL(__inc_zone_page_state);
 void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
 {
         struct zone *zone = page_zone(page);
-        s8 *p = diff_pointer(zone, item);
+        struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+        s8 *p = pcp->vm_stat_diff + item;
 
         (*p)--;
 
-        if (unlikely(*p < -STAT_THRESHOLD)) {
-                zone_page_state_add(*p, zone, item);
-                *p = 0;
+        if (unlikely(*p < - pcp->stat_threshold)) {
+                int overstep = pcp->stat_threshold / 2;
+
+                zone_page_state_add(*p - overstep, zone, item);
+                *p = overstep;
         }
 }
 EXPORT_SYMBOL(__dec_zone_page_state);
@@ -239,19 +302,9 @@ EXPORT_SYMBOL(inc_zone_page_state);
 void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 {
         unsigned long flags;
-        struct zone *zone;
-        s8 *p;
 
-        zone = page_zone(page);
         local_irq_save(flags);
-        p = diff_pointer(zone, item);
-
-        (*p)--;
-
-        if (unlikely(*p < -STAT_THRESHOLD)) {
-                zone_page_state_add(*p, zone, item);
-                *p = 0;
-        }
+        __dec_zone_page_state(page, item);
         local_irq_restore(flags);
 }
 EXPORT_SYMBOL(dec_zone_page_state);
@@ -525,6 +578,10 @@ static int zoneinfo_show(struct seq_file *m, void *arg)
                                            pageset->pcp[j].high,
                                            pageset->pcp[j].batch);
                         }
+#ifdef CONFIG_SMP
+                        seq_printf(m, "\n  vm stats threshold: %d",
+                                        pageset->stat_threshold);
+#endif
                 }
                 seq_printf(m,
                            "\n  all_unreclaimable: %u"
@@ -613,3 +670,35 @@ struct seq_operations vmstat_op = {
 
 #endif /* CONFIG_PROC_FS */
 
+#ifdef CONFIG_SMP
+/*
+ * Use the cpu notifier to insure that the thresholds are recalculated
+ * when necessary.
+ */
+static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
+                unsigned long action,
+                void *hcpu)
+{
+        switch (action) {
+                case CPU_UP_PREPARE:
+                case CPU_UP_CANCELED:
+                case CPU_DEAD:
+                        refresh_zone_stat_thresholds();
+                        break;
+                default:
+                        break;
+        }
+        return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata vmstat_notifier =
+        { &vmstat_cpuup_callback, NULL, 0 };
+
+int __init setup_vmstat(void)
+{
+        refresh_zone_stat_thresholds();
+        register_cpu_notifier(&vmstat_notifier);
+        return 0;
+}
+module_init(setup_vmstat)
+#endif