[PATCH] Define __raw_get_cpu_var and use it

There are several instances of per_cpu(foo, raw_smp_processor_id()), which
is semantically equivalent to __get_cpu_var(foo) but without the warning
that smp_processor_id() can give if CONFIG_DEBUG_PREEMPT is enabled.  For
those architectures with optimized per-cpu implementations, namely ia64,
powerpc, s390, sparc64 and x86_64, per_cpu() turns into more and slower
code than __get_cpu_var(), so it would be preferable to use __get_cpu_var
on those platforms.

This defines a __raw_get_cpu_var(x) macro which turns into per_cpu(x,
raw_smp_processor_id()) on architectures that use the generic per-cpu
implementation, and turns into __get_cpu_var(x) on the architectures that
have an optimized per-cpu implementation.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/asm-generic/percpu.h

@@ -14,6 +14,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]))
 #define __get_cpu_var(var) per_cpu(var, smp_processor_id())
+#define __raw_get_cpu_var(var) per_cpu(var, raw_smp_processor_id())
 
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
@@ -30,6 +31,7 @@ do {								\
 
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
+#define __raw_get_cpu_var(var)			per_cpu__##var
 
 #endif	/* SMP */
 

include/asm-ia64/percpu.h

@@ -42,6 +42,7 @@ DECLARE_PER_CPU(unsigned long, local_per_cpu_offset);
 
 #define per_cpu(var, cpu)  (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]))
 #define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __ia64_per_cpu_var(local_per_cpu_offset)))
+#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __ia64_per_cpu_var(local_per_cpu_offset)))
 
 extern void percpu_modcopy(void *pcpudst, const void *src, unsigned long size);
 extern void setup_per_cpu_areas (void);
@@ -51,6 +52,7 @@ extern void *per_cpu_init(void);
 
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
+#define __raw_get_cpu_var(var)			per_cpu__##var
 #define per_cpu_init()				(__phys_per_cpu_start)
 
 #endif	/* SMP */

include/asm-powerpc/percpu.h

@@ -22,6 +22,7 @@
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
 #define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
+#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
 
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
@@ -41,6 +42,7 @@ extern void setup_per_cpu_areas(void);
 
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
+#define __raw_get_cpu_var(var)			per_cpu__##var
 
 #endif	/* SMP */
 

include/asm-s390/percpu.h

@@ -40,6 +40,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
     __typeof__(type) per_cpu__##name
 
 #define __get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
+#define __raw_get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
 #define per_cpu(var,cpu) __reloc_hide(var,__per_cpu_offset[cpu])
 
 /* A macro to avoid #include hell... */
@@ -57,6 +58,7 @@ do {								\
     __typeof__(type) per_cpu__##name
 
 #define __get_cpu_var(var) __reloc_hide(var,0)
+#define __raw_get_cpu_var(var) __reloc_hide(var,0)
 #define per_cpu(var,cpu) __reloc_hide(var,0)
 
 #endif /* SMP */

include/asm-sparc64/percpu.h

@@ -21,6 +21,7 @@ register unsigned long __local_per_cpu_offset asm("g5");
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
 #define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __local_per_cpu_offset))
+#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __local_per_cpu_offset))
 
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
@@ -37,6 +38,7 @@ do {								\
 
 #define per_cpu(var, cpu)			(*((void)cpu, &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
+#define __raw_get_cpu_var(var)			per_cpu__##var
 
 #endif	/* SMP */
 

include/asm-x86_64/percpu.h

@@ -21,6 +21,7 @@
 /* var is in discarded region: offset to particular copy we want */
 #define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
 #define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
+#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
 
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
@@ -40,6 +41,7 @@ extern void setup_per_cpu_areas(void);
 
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
+#define __raw_get_cpu_var(var)			per_cpu__##var
 
 #endif	/* SMP */
 

kernel/hrtimer.c

@@ -576,7 +576,7 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
-	bases = per_cpu(hrtimer_bases, raw_smp_processor_id());
+	bases = __raw_get_cpu_var(hrtimer_bases);
 
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS)
 		clock_id = CLOCK_MONOTONIC;
@@ -599,7 +599,7 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
 	struct hrtimer_base *bases;
 
-	bases = per_cpu(hrtimer_bases, raw_smp_processor_id());
+	bases = __raw_get_cpu_var(hrtimer_bases);
 	*tp = ktime_to_timespec(bases[which_clock].resolution);
 
 	return 0;

kernel/sched.c

@@ -4152,7 +4152,7 @@ EXPORT_SYMBOL(yield);
  */
 void __sched io_schedule(void)
 {
-	struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
+	struct runqueue *rq = &__raw_get_cpu_var(runqueues);
 
 	atomic_inc(&rq->nr_iowait);
 	schedule();
@@ -4163,7 +4163,7 @@ EXPORT_SYMBOL(io_schedule);
 
 long __sched io_schedule_timeout(long timeout)
 {
-	struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
+	struct runqueue *rq = &__raw_get_cpu_var(runqueues);
 	long ret;
 
 	atomic_inc(&rq->nr_iowait);

kernel/softlockup.c

@@ -36,7 +36,7 @@ static struct notifier_block panic_block = {
 
 void touch_softlockup_watchdog(void)
 {
-	per_cpu(touch_timestamp, raw_smp_processor_id()) = jiffies;
+	__raw_get_cpu_var(touch_timestamp) = jiffies;
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 

kernel/timer.c

@@ -146,7 +146,7 @@ static void internal_add_timer(tvec_base_t *base, struct timer_list *timer)
 void fastcall init_timer(struct timer_list *timer)
 {
 	timer->entry.next = NULL;
-	timer->base = per_cpu(tvec_bases, raw_smp_processor_id());
+	timer->base = __raw_get_cpu_var(tvec_bases);
 }
 EXPORT_SYMBOL(init_timer);
 

net/ipv4/route.c

@@ -244,7 +244,7 @@ static unsigned int		rt_hash_rnd;
 
 static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
 #define RT_CACHE_STAT_INC(field) \
-	(per_cpu(rt_cache_stat, raw_smp_processor_id()).field++)
+	(__raw_get_cpu_var(rt_cache_stat).field++)
 
 static int rt_intern_hash(unsigned hash, struct rtable *rth,
 				struct rtable **res);