[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>

6 files changed, 12 insertions, 0 deletions

diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index c0caf433a7d7..c74521157461 100644
--- a/include/asm-generic/percpu.h
+++ b/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 */
 
diff --git a/include/asm-ia64/percpu.h b/include/asm-ia64/percpu.h
index ae357d504fba..24d898b650c5 100644
--- a/include/asm-ia64/percpu.h
+++ b/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 */
diff --git a/include/asm-powerpc/percpu.h b/include/asm-powerpc/percpu.h
index 184a7a4d2fdf..faa1fc703053 100644
--- a/include/asm-powerpc/percpu.h
+++ b/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 */
 
diff --git a/include/asm-s390/percpu.h b/include/asm-s390/percpu.h
index 436d216601e5..d9a8cca9b653 100644
--- a/include/asm-s390/percpu.h
+++ b/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 */
diff --git a/include/asm-sparc64/percpu.h b/include/asm-sparc64/percpu.h
index baef13b58952..a6ece06b83db 100644
--- a/include/asm-sparc64/percpu.h
+++ b/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 */
 
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 7f33aaf9f7b1..549eb929b2c0 100644
--- a/include/asm-x86_64/percpu.h
+++ b/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 */