[PATCH v2 -tip] x86/percpu: Use C for arch_raw_cpu_ptr()

[Uros Bizjak]

Implementing arch_raw_cpu_ptr() in C, allows the compiler to perform
better optimizations, such as setting an appropriate base to compute
the address instead of an add instruction.

E.g.: address calcuation in amd_pmu_enable_virt() improves from:

    48 c7 c0 00 00 00 00 	mov    $0x0,%rax
	87b7: R_X86_64_32S	cpu_hw_events

    65 48 03 05 00 00 00 	add    %gs:0x0(%rip),%rax
    00
	87bf: R_X86_64_PC32	this_cpu_off-0x4

    48 c7 80 28 13 00 00 	movq   $0x0,0x1328(%rax)
    00 00 00 00

to:

    65 48 8b 05 00 00 00 	mov    %gs:0x0(%rip),%rax
    00
	8798: R_X86_64_PC32	this_cpu_off-0x4
    48 c7 80 00 00 00 00 	movq   $0x0,0x0(%rax)
    00 00 00 00
	87a6: R_X86_64_32S	cpu_hw_events+0x1328

Co-developed-by: Nadav Amit <namit@xxxxxxxxxx>
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
Signed-off-by: Uros Bizjak <ubizjak@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
 arch/x86/include/asm/percpu.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 60ea7755c0fe..cdc188279c5a 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -49,6 +49,19 @@
 #define __force_percpu_prefix	"%%"__stringify(__percpu_seg)":"
 #define __my_cpu_offset		this_cpu_read(this_cpu_off)
 
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+/*
+ * Efficient implementation for cases in which the compiler supports
+ * named address spaces.  Allows the compiler to perform additional
+ * optimizations that can save more instructions.
+ */
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	tcp_ptr__ = __raw_cpu_read(, this_cpu_off) + (unsigned long)(ptr); \
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
+})
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
 /*
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
@@ -61,6 +74,8 @@
 	     : "m" (__my_cpu_var(this_cpu_off)), "0" (ptr));	\
 	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
 })
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
 #else /* CONFIG_SMP */
 #define __percpu_seg_override
 #define __percpu_prefix		""
-- 
2.41.0