From 1d10f3aec2bb734b4b594afe8c1bd0aa656a7e4d Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 15 Oct 2023 22:24:40 +0200 Subject: [PATCH] x86/percpu: Use C for arch_raw_cpu_ptr(), to improve code generation Implement arch_raw_cpu_ptr() in C to allow the compiler to perform better optimizations, such as setting an appropriate base to compute the address. The compiler is free to choose either MOV or ADD from this_cpu_off address to construct the optimal final address. There are some other issues when memory access to the percpu area is implemented with an asm. Compilers can not eliminate asm common subexpressions over basic block boundaries, but are extremely good at optimizing memory access. By implementing arch_raw_cpu_ptr() in C, the compiler can eliminate additional redundant loads from this_cpu_off, further reducing the number of percpu offset reads from 1646 to 1631 on a test build, a -0.9% reduction. Co-developed-by: Nadav Amit Signed-off-by: Nadav Amit Signed-off-by: Uros Bizjak Signed-off-by: Ingo Molnar Cc: Andy Lutomirski Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Josh Poimboeuf Cc: Uros Bizjak Cc: Sean Christopherson Link: https://lore.kernel.org/r/20231015202523.189168-2-ubizjak@gmail.com --- arch/x86/include/asm/percpu.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 915675f3ad605..54746903b8c3c 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -49,6 +49,21 @@ #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); \ + \ + tcp_ptr__ += (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. @@ -63,6 +78,8 @@ tcp_ptr__ += (unsigned long)(ptr); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) +#endif /* CONFIG_USE_X86_SEG_SUPPORT */ + #else /* CONFIG_SMP */ #define __percpu_seg_override #define __percpu_prefix "" -- 2.30.2