Merge branch 'for-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (30 commits)
  gameport: use this_cpu_read instead of lookup
  x86: udelay: Use this_cpu_read to avoid address calculation
  x86: Use this_cpu_inc_return for nmi counter
  x86: Replace uses of current_cpu_data with this_cpu ops
  x86: Use this_cpu_ops to optimize code
  vmstat: User per cpu atomics to avoid interrupt disable / enable
  irq_work: Use per cpu atomics instead of regular atomics
  cpuops: Use cmpxchg for xchg to avoid lock semantics
  x86: this_cpu_cmpxchg and this_cpu_xchg operations
  percpu: Generic this_cpu_cmpxchg() and this_cpu_xchg support
  percpu,x86: relocate this_cpu_add_return() and friends
  connector: Use this_cpu operations
  xen: Use this_cpu_inc_return
  taskstats: Use this_cpu_ops
  random: Use this_cpu_inc_return
  fs: Use this_cpu_inc_return in buffer.c
  highmem: Use this_cpu_xx_return() operations
  vmstat: Use this_cpu_inc_return for vm statistics
  x86: Support for this_cpu_add, sub, dec, inc_return
  percpu: Generic support for this_cpu_add, sub, dec, inc_return
  ...

Fixed up conflicts: in arch/x86/kernel/{apic/nmi.c, apic/x2apic_uv_x.c, process.c}
as per Tejun.

1 files changed, 113 insertions, 36 deletions

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 33c33e7a0f9b..312d728976f1 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -167,36 +167,24 @@ static void refresh_zone_stat_thresholds(void)
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
                                 int delta)
 {
-        struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-
-        s8 *p = pcp->vm_stat_diff + item;
+        struct per_cpu_pageset __percpu *pcp = zone->pageset;
+        s8 __percpu *p = pcp->vm_stat_diff + item;
         long x;
+        long t;
+
+        x = delta + __this_cpu_read(*p);
 
-        x = delta + *p;
+        t = __this_cpu_read(pcp->stat_threshold);
 
-        if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) {
+        if (unlikely(x > t || x < -t)) {
                 zone_page_state_add(x, zone, item);
                 x = 0;
         }
-        *p = x;
+        __this_cpu_write(*p, x);
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
 
 /*
- * For an unknown interrupt state
- */
-void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-                                        int delta)
-{
-        unsigned long flags;
-
-        local_irq_save(flags);
-        __mod_zone_page_state(zone, item, delta);
-        local_irq_restore(flags);
-}
-EXPORT_SYMBOL(mod_zone_page_state);
-
-/*
  * Optimized increment and decrement functions.
  *
  * These are only for a single page and therefore can take a struct page *
@@ -221,16 +209,17 @@ EXPORT_SYMBOL(mod_zone_page_state);
  */
 void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-        struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-        s8 *p = pcp->vm_stat_diff + item;
+        struct per_cpu_pageset __percpu *pcp = zone->pageset;
+        s8 __percpu *p = pcp->vm_stat_diff + item;
+        s8 v, t;
 
-        (*p)++;
+        v = __this_cpu_inc_return(*p);
+        t = __this_cpu_read(pcp->stat_threshold);
+        if (unlikely(v > t)) {
+                s8 overstep = t >> 1;
 
-        if (unlikely(*p > pcp->stat_threshold)) {
-                int overstep = pcp->stat_threshold / 2;
-
-                zone_page_state_add(*p + overstep, zone, item);
-                *p = -overstep;
+                zone_page_state_add(v + overstep, zone, item);
+                __this_cpu_write(*p, -overstep);
         }
 }
 
@@ -242,16 +231,17 @@ EXPORT_SYMBOL(__inc_zone_page_state);
 
 void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-        struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-        s8 *p = pcp->vm_stat_diff + item;
-
-        (*p)--;
+        struct per_cpu_pageset __percpu *pcp = zone->pageset;
+        s8 __percpu *p = pcp->vm_stat_diff + item;
+        s8 v, t;
 
-        if (unlikely(*p < - pcp->stat_threshold)) {
-                int overstep = pcp->stat_threshold / 2;
+        v = __this_cpu_dec_return(*p);
+        t = __this_cpu_read(pcp->stat_threshold);
+        if (unlikely(v < - t)) {
+                s8 overstep = t >> 1;
 
-                zone_page_state_add(*p - overstep, zone, item);
-                *p = overstep;
+                zone_page_state_add(v - overstep, zone, item);
+                __this_cpu_write(*p, overstep);
         }
 }
 
@@ -261,6 +251,92 @@ void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
 }
 EXPORT_SYMBOL(__dec_zone_page_state);
 
+#ifdef CONFIG_CMPXCHG_LOCAL
+/*
+ * If we have cmpxchg_local support then we do not need to incur the overhead
+ * that comes with local_irq_save/restore if we use this_cpu_cmpxchg.
+ *
+ * mod_state() modifies the zone counter state through atomic per cpu
+ * operations.
+ *
+ * Overstep mode specifies how overstep should handled:
+ *     0       No overstepping
+ *     1       Overstepping half of threshold
+ *     -1      Overstepping minus half of threshold
+*/
+static inline void mod_state(struct zone *zone,
+       enum zone_stat_item item, int delta, int overstep_mode)
+{
+        struct per_cpu_pageset __percpu *pcp = zone->pageset;
+        s8 __percpu *p = pcp->vm_stat_diff + item;
+        long o, n, t, z;
+
+        do {
+                z = 0;  /* overflow to zone counters */
+
+                /*
+                 * The fetching of the stat_threshold is racy. We may apply
+                 * a counter threshold to the wrong the cpu if we get
+                 * rescheduled while executing here. However, the following
+                 * will apply the threshold again and therefore bring the
+                 * counter under the threshold.
+                 */
+                t = this_cpu_read(pcp->stat_threshold);
+
+                o = this_cpu_read(*p);
+                n = delta + o;
+
+                if (n > t || n < -t) {
+                        int os = overstep_mode * (t >> 1) ;
+
+                        /* Overflow must be added to zone counters */
+                        z = n + os;
+                        n = -os;
+                }
+        } while (this_cpu_cmpxchg(*p, o, n) != o);
+
+        if (z)
+                zone_page_state_add(z, zone, item);
+}
+
+void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+                                        int delta)
+{
+        mod_state(zone, item, delta, 0);
+}
+EXPORT_SYMBOL(mod_zone_page_state);
+
+void inc_zone_state(struct zone *zone, enum zone_stat_item item)
+{
+        mod_state(zone, item, 1, 1);
+}
+
+void inc_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+        mod_state(page_zone(page), item, 1, 1);
+}
+EXPORT_SYMBOL(inc_zone_page_state);
+
+void dec_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+        mod_state(page_zone(page), item, -1, -1);
+}
+EXPORT_SYMBOL(dec_zone_page_state);
+#else
+/*
+ * Use interrupt disable to serialize counter updates
+ */
+void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+                                        int delta)
+{
+        unsigned long flags;
+
+        local_irq_save(flags);
+        __mod_zone_page_state(zone, item, delta);
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_zone_page_state);
+
 void inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
         unsigned long flags;
@@ -291,6 +367,7 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
         local_irq_restore(flags);
 }
 EXPORT_SYMBOL(dec_zone_page_state);
+#endif
 
 /*
  * Update the zone counters for one cpu.