The use of CPU ops here avoids the offset calculations that we used to have
to do with per cpu operations. The result of this patch is that event counters
are coded with a single instruction the following way:
incq %gs:offset(%rip)
Without these patches this was:
mov %gs:0x8,%rdx
mov %eax,0x38(%rsp)
mov xxx(%rip),%eax
mov %eax,0x48(%rsp)
mov varoffset,%rax
incq 0x110(%rax,%rdx,1)
Signed-off-by: Christoph Lameter <clameter@sgi.com
---
include/linux/vmstat.h | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
Index: linux-2.6/include/linux/vmstat.h
===================================================================
--- linux-2.6.orig/include/linux/vmstat.h 2008-05-20 19:43:43.000000000 -0700
+++ linux-2.6/include/linux/vmstat.h 2008-05-20 21:40:32.000000000 -0700
@@ -63,24 +63,22 @@
static inline void __count_vm_event(enum vm_event_item item)
{
- __get_cpu_var(vm_event_states).event[item]++;
+ __CPU_INC(per_cpu_var(vm_event_states).event[item]);
}
static inline void count_vm_event(enum vm_event_item item)
{
- get_cpu_var(vm_event_states).event[item]++;
- put_cpu();
+ _CPU_INC(per_cpu_var(vm_event_states).event[item]);
}
static inline void __count_vm_events(enum vm_event_item item, long delta)
{
- __get_cpu_var(vm_event_states).event[item] += delta;
+ __CPU_ADD(per_cpu_var(vm_event_states).event[item], delta);
}
static inline void count_vm_events(enum vm_event_item item, long delta)
{
- get_cpu_var(vm_event_states).event[item] += delta;
- put_cpu();
+ _CPU_ADD(per_cpu_var(vm_event_states).event[item], delta);
}
extern void all_vm_events(unsigned long *);
--
--
