[PATCH UPDATED 1/2] x86, percpu: Optimize this_cpu_ptr

[Tejun Heo]

Allow arches to implement __this_cpu_ptr, and provide an x86 version.

Before:
	movq $foo, %rax
	movq %gs:this_cpu_off, %rdx
	addq %rdx, %rax

After:
	movq $foo, %rax
	addq %gs:this_cpu_off, %rax

The benefit is doing it in one less instruction and not clobbering
a temporary register.

tj: beefed up the comment a bit and renamed in-macro temp variable to
    match neighboring macros.

Signed-off-by: Brian Gerst <brgerst@xxxxxxxxx>
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
---
Applied both patches to the following branch.  I updated the first
patch slightly.

  git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git for-next

Thank you.

 arch/x86/include/asm/percpu.h |   14 ++++++++++++++
 include/asm-generic/percpu.h  |    9 +++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

Index: percpu/arch/x86/include/asm/percpu.h
===================================================================
--- percpu.orig/arch/x86/include/asm/percpu.h
+++ percpu/arch/x86/include/asm/percpu.h
@@ -47,6 +47,20 @@
 #ifdef CONFIG_SMP
 #define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
 #define __my_cpu_offset		percpu_read(this_cpu_off)
+
+/*
+ * Compared to the generic __my_cpu_offset version, the following
+ * saves one instruction and avoids clobbering a temp register.
+ */
+#define __this_cpu_ptr(ptr)				\
+({							\
+	typeof(ptr) tcp_ptr__ = (ptr);			\
+	__verify_pcpu_ptr(ptr);				\
+	asm volatile("add " __percpu_arg(1) ", %0"	\
+		     : "+r" (tcp_ptr__)			\
+		     : "m" (this_cpu_off));		\
+	tcp_ptr__;					\
+})
 #else
 #define __percpu_arg(x)		"%P" #x
 #endif
Index: percpu/include/asm-generic/percpu.h
===================================================================
--- percpu.orig/include/asm-generic/percpu.h
+++ percpu/include/asm-generic/percpu.h
@@ -60,9 +60,14 @@ extern unsigned long __per_cpu_offset[NR
 #define __raw_get_cpu_var(var) \
 	(*SHIFT_PERCPU_PTR(&(var), __my_cpu_offset))

-#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#ifndef __this_cpu_ptr
 #define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
-
+#endif
+#ifdef CONFIG_DEBUG_PREEMPT
+#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#else
+#define this_cpu_ptr(ptr) __this_cpu_ptr(ptr)
+#endif

 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void setup_per_cpu_areas(void);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/