From 0415b00d175e0d8945e6785aad21b5f157976ce0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 24 Mar 2011 18:50:09 +0100 Subject: percpu: Always align percpu output section to PAGE_SIZE Percpu allocator honors alignment request upto PAGE_SIZE and both the percpu addresses in the percpu address space and the translated kernel addresses should be aligned accordingly. The calculation of the former depends on the alignment of percpu output section in the kernel image. The linker script macros PERCPU_VADDR() and PERCPU() are used to define this output section and the latter takes @align parameter. Several architectures are using @align smaller than PAGE_SIZE breaking percpu memory alignment. This patch removes @align parameter from PERCPU(), renames it to PERCPU_SECTION() and makes it always align to PAGE_SIZE. While at it, add PCPU_SETUP_BUG_ON() checks such that alignment problems are reliably detected and remove percpu alignment comment recently added in workqueue.c as the condition would trigger BUG way before reaching there. For um, this patch raises the alignment of percpu area. As the area is in .init, there shouldn't be any noticeable difference. This problem was discovered by David Howells while debugging boot failure on mn10300. Signed-off-by: Tejun Heo Acked-by: Mike Frysinger Cc: uclinux-dist-devel@blackfin.uclinux.org Cc: David Howells Cc: Jeff Dike Cc: user-mode-linux-devel@lists.sourceforge.net --- arch/x86/kernel/vmlinux.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 624a201..3e9fb5d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -319,7 +319,7 @@ SECTIONS } #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP) - PERCPU(INTERNODE_CACHE_BYTES, PAGE_SIZE) + PERCPU_SECTION(INTERNODE_CACHE_BYTES) #endif . = ALIGN(PAGE_SIZE); -- cgit v1.1 From 5f55924deaa62d6df687c131fb92aebe071ec787 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 28 Mar 2011 18:06:58 +0200 Subject: percpu: Avoid extra NOP in percpu_cmpxchg16b_double percpu_cmpxchg16b_double() uses alternative_io() and looks like : e8 .. .. .. .. call this_cpu_cmpxchg16b_emu X bytes NOPX or, once patched (if cpu supports native instruction) on SMP build : 65 48 0f c7 0e cmpxchg16b %gs:(%rsi) 0f 94 c0 sete %al on !SMP build : 48 0f c7 0e cmpxchg16b (%rsi) 0f 94 c0 sete %al Therefore, NOPX should be : P6_NOP3 on SMP P6_NOP2 on !SMP Signed-off-by: Eric Dumazet Acked-by: Christoph Lameter Cc: Ingo Molnar Cc: Pekka Enberg Signed-off-by: Tejun Heo --- arch/x86/include/asm/percpu.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index d475b43..d68fca6 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -509,6 +509,11 @@ do { \ * it in software. The address used in the cmpxchg16 instruction must be * aligned to a 16 byte boundary. */ +#ifdef CONFIG_SMP +#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" P6_NOP3 +#else +#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" P6_NOP2 +#endif #define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) \ ({ \ char __ret; \ @@ -517,7 +522,7 @@ do { \ typeof(o2) __o2 = o2; \ typeof(o2) __n2 = n2; \ typeof(o2) __dummy; \ - alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4, \ + alternative_io(CMPXCHG16B_EMU_CALL, \ "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \ X86_FEATURE_CX16, \ ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \ -- cgit v1.1