From ce9c99af8d4b3b0b9463654fd252d8640d804dc3 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Fri, 8 Apr 2011 07:42:29 +0100 Subject: [PATCH 1/8] x86, cpu: Move AMD Elan Kconfig under "Processor family" Currently the option resides under X86_EXTENDED_PLATFORM due to historical nonstandard A20M# handling. However that is no longer the case and so Elan can be treated as part of the standard processor choice Kconfig option. Signed-off-by: Ian Campbell Link: http://lkml.kernel.org/r/1302245177.31620.47.camel@localhost.localdomain Cc: H. Peter Anvin Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 11 ----------- arch/x86/Kconfig.cpu | 16 ++++++++++------ arch/x86/Makefile_32.cpu | 2 +- arch/x86/include/asm/module.h | 2 +- arch/x86/kernel/cpu/cpufreq/Kconfig | 4 ++-- 5 files changed, 14 insertions(+), 21 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cc6c53a95bfd..f00a3f377cc0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -365,17 +365,6 @@ config X86_UV # Following is an alphabetically sorted list of 32 bit extended platforms # Please maintain the alphabetic order if and when there are additions -config X86_ELAN - bool "AMD Elan" - depends on X86_32 - depends on X86_EXTENDED_PLATFORM - ---help--- - Select this for an AMD Elan processor. - - Do not use this option for K6/Athlon/Opteron processors! - - If unsure, choose "PC-compatible" instead. - config X86_INTEL_CE bool "CE4100 TV platform" depends on PCI diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index d161e939df62..6a7cfdf8ff69 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -1,6 +1,4 @@ # Put here option for CPU selection and depending optimization -if !X86_ELAN - choice prompt "Processor family" default M686 if X86_32 @@ -203,6 +201,14 @@ config MWINCHIP3D stores for this CPU, which can increase performance of some operations. +config MELAN + bool "AMD Elan" + depends on X86_32 + ---help--- + Select this for an AMD Elan processor. + + Do not use this option for K6/Athlon/Opteron processors! + config MGEODEGX1 bool "GeodeGX1" depends on X86_32 @@ -292,8 +298,6 @@ config X86_GENERIC This is really intended for distributors who need more generic optimizations. -endif - # # Define implied options from the CPU selection here config X86_INTERNODE_CACHE_SHIFT @@ -312,7 +316,7 @@ config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || MPSC default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU - default "4" if X86_ELAN || M486 || M386 || MGEODEGX1 + default "4" if MELAN || M486 || M386 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX config X86_XADD @@ -358,7 +362,7 @@ config X86_POPAD_OK config X86_ALIGNMENT_16 def_bool y - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 config X86_INTEL_USERCOPY def_bool y diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index f2ee1abb1df9..86cee7b749e1 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -37,7 +37,7 @@ cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march= $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) # AMD Elan support -cflags-$(CONFIG_X86_ELAN) += -march=i486 +cflags-$(CONFIG_MELAN) += -march=i486 # Geode GX1 support cflags-$(CONFIG_MGEODEGX1) += -march=pentium-mmx diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index 67763c5d8b4e..9eae7752ae9b 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -35,7 +35,7 @@ #define MODULE_PROC_FAMILY "K7 " #elif defined CONFIG_MK8 #define MODULE_PROC_FAMILY "K8 " -#elif defined CONFIG_X86_ELAN +#elif defined CONFIG_MELAN #define MODULE_PROC_FAMILY "ELAN " #elif defined CONFIG_MCRUSOE #define MODULE_PROC_FAMILY "CRUSOE " diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig index 870e6cc6ad28..0ab9b22557c4 100644 --- a/arch/x86/kernel/cpu/cpufreq/Kconfig +++ b/arch/x86/kernel/cpu/cpufreq/Kconfig @@ -43,7 +43,7 @@ config X86_ACPI_CPUFREQ config ELAN_CPUFREQ tristate "AMD Elan SC400 and SC410" select CPU_FREQ_TABLE - depends on X86_ELAN + depends on MELAN ---help--- This adds the CPUFreq driver for AMD Elan SC400 and SC410 processors. @@ -59,7 +59,7 @@ config ELAN_CPUFREQ config SC520_CPUFREQ tristate "AMD Elan SC520" select CPU_FREQ_TABLE - depends on X86_ELAN + depends on MELAN ---help--- This adds the CPUFreq driver for AMD Elan SC520 processor. From b1e7734f024c9ce4393016a97c8d821e1f18d9b4 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 18 Apr 2011 15:18:02 -0700 Subject: [PATCH 2/8] x86, percpu: Use ASM_NOP4 instead of hardcoding P6_NOP4 For use in assembly constants, use the ASM_NOP* defines. Signed-off-by: H. Peter Anvin Cc: Christoph Lameter Cc: Tejun Heo Link: http://lkml.kernel.org/r/1303166160-10315-2-git-send-email-hpa@linux.intel.com --- arch/x86/include/asm/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index d475b4398d8b..751e7f3f705c 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -517,7 +517,7 @@ 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("call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP4, \ "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \ X86_FEATURE_CX16, \ ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \ From dc326fca2b640fc41aed7c015d0f456935a66255 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 18 Apr 2011 15:19:51 -0700 Subject: [PATCH 3/8] x86, cpu: Clean up and unify the NOP selection infrastructure Clean up and unify the NOP selection infrastructure: - Make the atomic 5-byte NOP a part of the selection system. - Pick NOPs once during early boot and then be done with it. Signed-off-by: H. Peter Anvin Cc: Tejun Heo Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Jason Baron Link: http://lkml.kernel.org/r/1303166160-10315-3-git-send-email-hpa@linux.intel.com --- arch/x86/include/asm/alternative.h | 8 -- arch/x86/include/asm/nops.h | 146 +++++++++++++---------- arch/x86/kernel/alternative.c | 184 ++++++++++++++++------------- arch/x86/kernel/ftrace.c | 4 +- arch/x86/kernel/jump_label.c | 5 +- arch/x86/kernel/setup.c | 6 +- 6 files changed, 191 insertions(+), 162 deletions(-) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 13009d1af99a..7da168225a9d 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -191,12 +191,4 @@ extern void *text_poke(void *addr, const void *opcode, size_t len); extern void *text_poke_smp(void *addr, const void *opcode, size_t len); extern void text_poke_smp_batch(struct text_poke_param *params, int n); -#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) -#define IDEAL_NOP_SIZE_5 5 -extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; -extern void arch_init_ideal_nop5(void); -#else -static inline void arch_init_ideal_nop5(void) {} -#endif - #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h index af788496020b..405b4032a60b 100644 --- a/arch/x86/include/asm/nops.h +++ b/arch/x86/include/asm/nops.h @@ -1,7 +1,13 @@ #ifndef _ASM_X86_NOPS_H #define _ASM_X86_NOPS_H -/* Define nops for use with alternative() */ +/* + * Define nops for use with alternative() and for tracing. + * + * *_NOP5_ATOMIC must be a single instruction. + */ + +#define NOP_DS_PREFIX 0x3e /* generic versions from gas 1: nop @@ -13,14 +19,15 @@ 6: leal 0x00000000(%esi),%esi 7: leal 0x00000000(,%esi,1),%esi */ -#define GENERIC_NOP1 ".byte 0x90\n" -#define GENERIC_NOP2 ".byte 0x89,0xf6\n" -#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n" -#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n" -#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4 -#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n" -#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n" -#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7 +#define GENERIC_NOP1 0x90 +#define GENERIC_NOP2 0x89,0xf6 +#define GENERIC_NOP3 0x8d,0x76,0x00 +#define GENERIC_NOP4 0x8d,0x74,0x26,0x00 +#define GENERIC_NOP5 GENERIC_NOP1,GENERIC_NOP4 +#define GENERIC_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00 +#define GENERIC_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00 +#define GENERIC_NOP8 GENERIC_NOP1,GENERIC_NOP7 +#define GENERIC_NOP5_ATOMIC NOP_DS_PREFIX,GENERIC_NOP4 /* Opteron 64bit nops 1: nop @@ -29,13 +36,14 @@ 4: osp osp osp nop */ #define K8_NOP1 GENERIC_NOP1 -#define K8_NOP2 ".byte 0x66,0x90\n" -#define K8_NOP3 ".byte 0x66,0x66,0x90\n" -#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n" -#define K8_NOP5 K8_NOP3 K8_NOP2 -#define K8_NOP6 K8_NOP3 K8_NOP3 -#define K8_NOP7 K8_NOP4 K8_NOP3 -#define K8_NOP8 K8_NOP4 K8_NOP4 +#define K8_NOP2 0x66,K8_NOP1 +#define K8_NOP3 0x66,K8_NOP2 +#define K8_NOP4 0x66,K8_NOP3 +#define K8_NOP5 K8_NOP3,K8_NOP2 +#define K8_NOP6 K8_NOP3,K8_NOP3 +#define K8_NOP7 K8_NOP4,K8_NOP3 +#define K8_NOP8 K8_NOP4,K8_NOP4 +#define K8_NOP5_ATOMIC 0x66,K8_NOP4 /* K7 nops uses eax dependencies (arbitrary choice) @@ -47,13 +55,14 @@ 7: leal 0x00000000(,%eax,1),%eax */ #define K7_NOP1 GENERIC_NOP1 -#define K7_NOP2 ".byte 0x8b,0xc0\n" -#define K7_NOP3 ".byte 0x8d,0x04,0x20\n" -#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n" -#define K7_NOP5 K7_NOP4 ASM_NOP1 -#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n" -#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n" -#define K7_NOP8 K7_NOP7 ASM_NOP1 +#define K7_NOP2 0x8b,0xc0 +#define K7_NOP3 0x8d,0x04,0x20 +#define K7_NOP4 0x8d,0x44,0x20,0x00 +#define K7_NOP5 K7_NOP4,K7_NOP1 +#define K7_NOP6 0x8d,0x80,0,0,0,0 +#define K7_NOP7 0x8D,0x04,0x05,0,0,0,0 +#define K7_NOP8 K7_NOP7,K7_NOP1 +#define K7_NOP5_ATOMIC NOP_DS_PREFIX,K7_NOP4 /* P6 nops uses eax dependencies (Intel-recommended choice) @@ -69,52 +78,65 @@ There is kernel code that depends on this. */ #define P6_NOP1 GENERIC_NOP1 -#define P6_NOP2 ".byte 0x66,0x90\n" -#define P6_NOP3 ".byte 0x0f,0x1f,0x00\n" -#define P6_NOP4 ".byte 0x0f,0x1f,0x40,0\n" -#define P6_NOP5 ".byte 0x0f,0x1f,0x44,0x00,0\n" -#define P6_NOP6 ".byte 0x66,0x0f,0x1f,0x44,0x00,0\n" -#define P6_NOP7 ".byte 0x0f,0x1f,0x80,0,0,0,0\n" -#define P6_NOP8 ".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n" +#define P6_NOP2 0x66,0x90 +#define P6_NOP3 0x0f,0x1f,0x00 +#define P6_NOP4 0x0f,0x1f,0x40,0 +#define P6_NOP5 0x0f,0x1f,0x44,0x00,0 +#define P6_NOP6 0x66,0x0f,0x1f,0x44,0x00,0 +#define P6_NOP7 0x0f,0x1f,0x80,0,0,0,0 +#define P6_NOP8 0x0f,0x1f,0x84,0x00,0,0,0,0 +#define P6_NOP5_ATOMIC P6_NOP5 + +#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n" #if defined(CONFIG_MK7) -#define ASM_NOP1 K7_NOP1 -#define ASM_NOP2 K7_NOP2 -#define ASM_NOP3 K7_NOP3 -#define ASM_NOP4 K7_NOP4 -#define ASM_NOP5 K7_NOP5 -#define ASM_NOP6 K7_NOP6 -#define ASM_NOP7 K7_NOP7 -#define ASM_NOP8 K7_NOP8 +#define ASM_NOP1 _ASM_MK_NOP(K7_NOP1) +#define ASM_NOP2 _ASM_MK_NOP(K7_NOP2) +#define ASM_NOP3 _ASM_MK_NOP(K7_NOP3) +#define ASM_NOP4 _ASM_MK_NOP(K7_NOP4) +#define ASM_NOP5 _ASM_MK_NOP(K7_NOP5) +#define ASM_NOP6 _ASM_MK_NOP(K7_NOP6) +#define ASM_NOP7 _ASM_MK_NOP(K7_NOP7) +#define ASM_NOP8 _ASM_MK_NOP(K7_NOP8) +#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K7_NOP5_ATOMIC) #elif defined(CONFIG_X86_P6_NOP) -#define ASM_NOP1 P6_NOP1 -#define ASM_NOP2 P6_NOP2 -#define ASM_NOP3 P6_NOP3 -#define ASM_NOP4 P6_NOP4 -#define ASM_NOP5 P6_NOP5 -#define ASM_NOP6 P6_NOP6 -#define ASM_NOP7 P6_NOP7 -#define ASM_NOP8 P6_NOP8 +#define ASM_NOP1 _ASM_MK_NOP(P6_NOP1) +#define ASM_NOP2 _ASM_MK_NOP(P6_NOP2) +#define ASM_NOP3 _ASM_MK_NOP(P6_NOP3) +#define ASM_NOP4 _ASM_MK_NOP(P6_NOP4) +#define ASM_NOP5 _ASM_MK_NOP(P6_NOP5) +#define ASM_NOP6 _ASM_MK_NOP(P6_NOP6) +#define ASM_NOP7 _ASM_MK_NOP(P6_NOP7) +#define ASM_NOP8 _ASM_MK_NOP(P6_NOP8) +#define ASM_NOP5_ATOMIC _ASM_MK_NOP(P6_NOP5_ATOMIC) #elif defined(CONFIG_X86_64) -#define ASM_NOP1 K8_NOP1 -#define ASM_NOP2 K8_NOP2 -#define ASM_NOP3 K8_NOP3 -#define ASM_NOP4 K8_NOP4 -#define ASM_NOP5 K8_NOP5 -#define ASM_NOP6 K8_NOP6 -#define ASM_NOP7 K8_NOP7 -#define ASM_NOP8 K8_NOP8 +#define ASM_NOP1 _ASM_MK_NOP(K8_NOP1) +#define ASM_NOP2 _ASM_MK_NOP(K8_NOP2) +#define ASM_NOP3 _ASM_MK_NOP(K8_NOP3) +#define ASM_NOP4 _ASM_MK_NOP(K8_NOP4) +#define ASM_NOP5 _ASM_MK_NOP(K8_NOP5) +#define ASM_NOP6 _ASM_MK_NOP(K8_NOP6) +#define ASM_NOP7 _ASM_MK_NOP(K8_NOP7) +#define ASM_NOP8 _ASM_MK_NOP(K8_NOP8) +#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K8_NOP5_ATOMIC) #else -#define ASM_NOP1 GENERIC_NOP1 -#define ASM_NOP2 GENERIC_NOP2 -#define ASM_NOP3 GENERIC_NOP3 -#define ASM_NOP4 GENERIC_NOP4 -#define ASM_NOP5 GENERIC_NOP5 -#define ASM_NOP6 GENERIC_NOP6 -#define ASM_NOP7 GENERIC_NOP7 -#define ASM_NOP8 GENERIC_NOP8 +#define ASM_NOP1 _ASM_MK_NOP(GENERIC_NOP1) +#define ASM_NOP2 _ASM_MK_NOP(GENERIC_NOP2) +#define ASM_NOP3 _ASM_MK_NOP(GENERIC_NOP3) +#define ASM_NOP4 _ASM_MK_NOP(GENERIC_NOP4) +#define ASM_NOP5 _ASM_MK_NOP(GENERIC_NOP5) +#define ASM_NOP6 _ASM_MK_NOP(GENERIC_NOP6) +#define ASM_NOP7 _ASM_MK_NOP(GENERIC_NOP7) +#define ASM_NOP8 _ASM_MK_NOP(GENERIC_NOP8) +#define ASM_NOP5_ATOMIC _ASM_MK_NOP(GENERIC_NOP5_ATOMIC) #endif #define ASM_NOP_MAX 8 +#define NOP_ATOMIC5 (ASM_NOP_MAX+1) /* Entry for the 5-byte atomic NOP */ + +#ifndef __ASSEMBLY__ +extern const unsigned char * const *ideal_nops; +extern void arch_init_ideal_nops(void); +#endif #endif /* _ASM_X86_NOPS_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4a234677e213..846f61eb89c1 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -67,17 +67,30 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt); #define DPRINTK(fmt, args...) if (debug_alternative) \ printk(KERN_DEBUG fmt, args) +/* + * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes + * that correspond to that nop. Getting from one nop to the next, we + * add to the array the offset that is equal to the sum of all sizes of + * nops preceding the one we are after. + * + * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the + * nice symmetry of sizes of the previous nops. + */ #if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64) -/* Use inline assembly to define this because the nops are defined - as inline assembly strings in the include files and we cannot - get them easily into strings. */ -asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nintelnops: " - GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6 - GENERIC_NOP7 GENERIC_NOP8 - "\t.previous"); -extern const unsigned char intelnops[]; -static const unsigned char *const __initconst_or_module -intel_nops[ASM_NOP_MAX+1] = { +static const unsigned char intelnops[] = +{ + GENERIC_NOP1, + GENERIC_NOP2, + GENERIC_NOP3, + GENERIC_NOP4, + GENERIC_NOP5, + GENERIC_NOP6, + GENERIC_NOP7, + GENERIC_NOP8, + GENERIC_NOP5_ATOMIC +}; +static const unsigned char * const intel_nops[ASM_NOP_MAX+2] = +{ NULL, intelnops, intelnops + 1, @@ -87,17 +100,25 @@ intel_nops[ASM_NOP_MAX+1] = { intelnops + 1 + 2 + 3 + 4 + 5, intelnops + 1 + 2 + 3 + 4 + 5 + 6, intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7, + intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8, }; #endif #ifdef K8_NOP1 -asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk8nops: " - K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 - K8_NOP7 K8_NOP8 - "\t.previous"); -extern const unsigned char k8nops[]; -static const unsigned char *const __initconst_or_module -k8_nops[ASM_NOP_MAX+1] = { +static const unsigned char k8nops[] = +{ + K8_NOP1, + K8_NOP2, + K8_NOP3, + K8_NOP4, + K8_NOP5, + K8_NOP6, + K8_NOP7, + K8_NOP8, + K8_NOP5_ATOMIC +}; +static const unsigned char * const k8_nops[ASM_NOP_MAX+2] = +{ NULL, k8nops, k8nops + 1, @@ -107,17 +128,25 @@ k8_nops[ASM_NOP_MAX+1] = { k8nops + 1 + 2 + 3 + 4 + 5, k8nops + 1 + 2 + 3 + 4 + 5 + 6, k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, + k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8, }; #endif #if defined(K7_NOP1) && !defined(CONFIG_X86_64) -asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk7nops: " - K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6 - K7_NOP7 K7_NOP8 - "\t.previous"); -extern const unsigned char k7nops[]; -static const unsigned char *const __initconst_or_module -k7_nops[ASM_NOP_MAX+1] = { +static const unsigned char k7nops[] = +{ + K7_NOP1, + K7_NOP2, + K7_NOP3, + K7_NOP4, + K7_NOP5, + K7_NOP6, + K7_NOP7, + K7_NOP8, + K7_NOP5_ATOMIC +}; +static const unsigned char * const k7_nops[ASM_NOP_MAX+2] = +{ NULL, k7nops, k7nops + 1, @@ -127,17 +156,25 @@ k7_nops[ASM_NOP_MAX+1] = { k7nops + 1 + 2 + 3 + 4 + 5, k7nops + 1 + 2 + 3 + 4 + 5 + 6, k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, + k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8, }; #endif #ifdef P6_NOP1 -asm("\t" __stringify(__INITRODATA_OR_MODULE) "\np6nops: " - P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6 - P6_NOP7 P6_NOP8 - "\t.previous"); -extern const unsigned char p6nops[]; -static const unsigned char *const __initconst_or_module -p6_nops[ASM_NOP_MAX+1] = { +static const unsigned char __initconst_or_module p6nops[] = +{ + P6_NOP1, + P6_NOP2, + P6_NOP3, + P6_NOP4, + P6_NOP5, + P6_NOP6, + P6_NOP7, + P6_NOP8, + P6_NOP5_ATOMIC +}; +static const unsigned char * const p6_nops[ASM_NOP_MAX+2] = +{ NULL, p6nops, p6nops + 1, @@ -147,47 +184,53 @@ p6_nops[ASM_NOP_MAX+1] = { p6nops + 1 + 2 + 3 + 4 + 5, p6nops + 1 + 2 + 3 + 4 + 5 + 6, p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, + p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8, }; #endif +/* Initialize these to a safe default */ #ifdef CONFIG_X86_64 +const unsigned char * const *ideal_nops = p6_nops; +#else +const unsigned char * const *ideal_nops = intel_nops; +#endif -extern char __vsyscall_0; -static const unsigned char *const *__init_or_module find_nop_table(void) +void __init arch_init_ideal_nops(void) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - boot_cpu_has(X86_FEATURE_NOPL)) - return p6_nops; - else - return k8_nops; + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + if (boot_cpu_has(X86_FEATURE_NOPL)) { + ideal_nops = p6_nops; + } else { +#ifdef CONFIG_X86_64 + ideal_nops = k8_nops; +#else + ideal_nops = intel_nops; +#endif + } + + default: +#ifdef CONFIG_X86_64 + ideal_nops = k8_nops; +#else + if (boot_cpu_has(X86_FEATURE_K8)) + ideal_nops = k8_nops; + else if (boot_cpu_has(X86_FEATURE_K7)) + ideal_nops = k7_nops; + else + ideal_nops = intel_nops; +#endif + } } -#else /* CONFIG_X86_64 */ - -static const unsigned char *const *__init_or_module find_nop_table(void) -{ - if (boot_cpu_has(X86_FEATURE_K8)) - return k8_nops; - else if (boot_cpu_has(X86_FEATURE_K7)) - return k7_nops; - else if (boot_cpu_has(X86_FEATURE_NOPL)) - return p6_nops; - else - return intel_nops; -} - -#endif /* CONFIG_X86_64 */ - /* Use this to add nops to a buffer, then text_poke the whole buffer. */ static void __init_or_module add_nops(void *insns, unsigned int len) { - const unsigned char *const *noptable = find_nop_table(); - while (len > 0) { unsigned int noplen = len; if (noplen > ASM_NOP_MAX) noplen = ASM_NOP_MAX; - memcpy(insns, noptable[noplen], noplen); + memcpy(insns, ideal_nops[noplen], noplen); insns += noplen; len -= noplen; } @@ -195,6 +238,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; +extern char __vsyscall_0; void *text_poke_early(void *addr, const void *opcode, size_t len); /* Replace instructions with better alternatives for this CPU type. @@ -678,29 +722,3 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) wrote_text = 0; __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); } - -#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) - -#ifdef CONFIG_X86_64 -unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 }; -#else -unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 }; -#endif - -void __init arch_init_ideal_nop5(void) -{ - /* - * There is no good nop for all x86 archs. This selection - * algorithm should be unified with the one in find_nop_table(), - * but this should be good enough for now. - * - * For cases other than the ones below, use the safe (as in - * always functional) defaults above. - */ -#ifdef CONFIG_X86_64 - /* Don't use these on 32 bits due to broken virtualizers */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - memcpy(ideal_nop5, p6_nops[5], 5); -#endif -} -#endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index a93742a57468..0ba15a6cc57e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -260,9 +260,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) return mod_code_status; } -static unsigned char *ftrace_nop_replace(void) +static const unsigned char *ftrace_nop_replace(void) { - return ideal_nop5; + return ideal_nops[NOP_ATOMIC5]; } static int diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 961b6b30ba90..3fee346ef545 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -34,7 +34,7 @@ void arch_jump_label_transform(struct jump_entry *entry, code.offset = entry->target - (entry->code + JUMP_LABEL_NOP_SIZE); } else - memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE); + memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); get_online_cpus(); mutex_lock(&text_mutex); text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); @@ -44,7 +44,8 @@ void arch_jump_label_transform(struct jump_entry *entry, void arch_jump_label_text_poke_early(jump_label_t addr) { - text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE); + text_poke_early((void *)addr, ideal_nops[NOP_ATOMIC5], + JUMP_LABEL_NOP_SIZE); } #endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 5a0484a95ad6..390a663894d8 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -691,8 +691,6 @@ early_param("reservelow", parse_reservelow); void __init setup_arch(char **cmdline_p) { - unsigned long flags; - #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); @@ -1036,9 +1034,7 @@ void __init setup_arch(char **cmdline_p) mcheck_init(); - local_irq_save(flags); - arch_init_ideal_nop5(); - local_irq_restore(flags); + arch_init_ideal_nops(); } #ifdef CONFIG_X86_32 From d8d9766c8c29f71c37bc4b74cc9fcf6a192c9bfd Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 18 Apr 2011 15:31:57 -0700 Subject: [PATCH 4/8] x86, cpu: Change NOP selection for certain Intel CPUs Due to a decoder implementation quirk, some specific Intel CPUs actually perform better with the "k8_nops" than with the SDM-recommended NOPs. For runtime-selected NOPs, if we detect those specific CPUs then use the k8_nops instead of the ones we would normally use. Signed-off-by: H. Peter Anvin Cc: Tejun Heo Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Jason Baron Link: http://lkml.kernel.org/r/1303166160-10315-4-git-send-email-hpa@linux.intel.com --- arch/x86/kernel/alternative.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 846f61eb89c1..c0501ea6b634 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -199,7 +199,19 @@ void __init arch_init_ideal_nops(void) { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: - if (boot_cpu_has(X86_FEATURE_NOPL)) { + /* + * Due to a decoder implementation quirk, some + * specific Intel CPUs actually perform better with + * the "k8_nops" than with the SDM-recommended NOPs. + */ + if (boot_cpu_data.x86 == 6 && + boot_cpu_data.x86_model >= 0x0f && + boot_cpu_data.x86_model != 0x1c && + boot_cpu_data.x86_model != 0x26 && + boot_cpu_data.x86_model != 0x27 && + boot_cpu_data.x86_model < 0x30) { + ideal_nops = k8_nops; + } else if (boot_cpu_has(X86_FEATURE_NOPL)) { ideal_nops = p6_nops; } else { #ifdef CONFIG_X86_64 From 50e7534427283afd997d58481778c07bea79eb63 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 16 May 2011 15:39:46 +0200 Subject: [PATCH 5/8] x86, AMD, cacheinfo: Fix fallout caused by max3 conversion 732eacc0542d0aa48797f675888b85d6065af837 converted code around the kernel using nested max() macros to use the new max3 macro but forgot to remove the old line in intel_cacheinfo.c. Fix it. Cc: Hagen Paul Pfeifer Cc: Frank Arnold Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1305553188-21061-2-git-send-email-bp@amd64.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/intel_cacheinfo.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 1ce1af2899df..31590a001e2a 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -327,7 +327,6 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3) l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9)); l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13)); - l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1; l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1; } From 42be450565b0fc4607fae3e3a7da038d367a23ed Mon Sep 17 00:00:00 2001 From: Frank Arnold Date: Mon, 16 May 2011 15:39:47 +0200 Subject: [PATCH 6/8] x86, AMD, cacheinfo: Fix L3 cache index disable checks We provide two slots to disable cache indices, and have a check to prevent both slots to be used for the same index. If the user disables the same index on different subcaches, both slots will hold the same index, e.g. $ echo 2047 > /sys/devices/system/cpu/cpu0/cache/index3/cache_disable_0 $ cat /sys/devices/system/cpu/cpu0/cache/index3/cache_disable_0 2047 $ echo 1050623 > /sys/devices/system/cpu/cpu0/cache/index3/cache_disable_1 $ cat /sys/devices/system/cpu/cpu0/cache/index3/cache_disable_1 2047 due to the fact that the check was looking only at index bits [11:0] and was ignoring writes to bits outside that range. The more correct fix is to simply check whether the index is within the bounds of [0..l3->indices]. While at it, cleanup comments and drop now-unused local macros. Signed-off-by: Frank Arnold Link: http://lkml.kernel.org/r/1305553188-21061-3-git-send-email-bp@amd64.org Signed-off-by: Borislav Petkov Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/intel_cacheinfo.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 31590a001e2a..c105c533ed94 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -453,27 +453,16 @@ int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot, { int ret = 0; -#define SUBCACHE_MASK (3UL << 20) -#define SUBCACHE_INDEX 0xfff - - /* - * check whether this slot is already used or - * the index is already disabled - */ + /* check if @slot is already used or the index is already disabled */ ret = amd_get_l3_disable_slot(l3, slot); if (ret >= 0) return -EINVAL; - /* - * check whether the other slot has disabled the - * same index already - */ - if (index == amd_get_l3_disable_slot(l3, !slot)) + if (index > l3->indices) return -EINVAL; - /* do not allow writes outside of allowed bits */ - if ((index & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || - ((index & SUBCACHE_INDEX) > l3->indices)) + /* check whether the other slot has disabled the same index already */ + if (index == amd_get_l3_disable_slot(l3, !slot)) return -EINVAL; amd_l3_disable_index(l3, cpu, slot, index); From eecaaba5b2e4ae762b4726fae2e3b22630e137ec Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 16 May 2011 15:39:48 +0200 Subject: [PATCH 7/8] Documentation, ABI: Update L3 cache index disable text Change contact person to AMD kernel mailing list, update text and external references, drop "Users:" tag. Cc: Randy Dunlap Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1305553188-21061-4-git-send-email-bp@amd64.org Acked-by: Greg Kroah-Hartman Signed-off-by: H. Peter Anvin --- .../ABI/testing/sysfs-devices-system-cpu | 32 +++++++++---------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 7564e88bfa43..e7be75b96e4b 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -183,21 +183,21 @@ Description: Discover and change clock speed of CPUs to learn how to control the knobs. -What: /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X -Date: August 2008 +What: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1} +Date: August 2008 KernelVersion: 2.6.27 -Contact: mark.langsdorf@amd.com -Description: These files exist in every cpu's cache index directories. - There are currently 2 cache_disable_# files in each - directory. Reading from these files on a supported - processor will return that cache disable index value - for that processor and node. Writing to one of these - files will cause the specificed cache index to be disabled. +Contact: discuss@x86-64.org +Description: Disable L3 cache indices - Currently, only AMD Family 10h Processors support cache index - disable, and only for their L3 caches. See the BIOS and - Kernel Developer's Guide at - http://support.amd.com/us/Embedded_TechDocs/31116-Public-GH-BKDG_3-28_5-28-09.pdf - for formatting information and other details on the - cache index disable. -Users: joachim.deguara@amd.com + These files exist in every CPU's cache/index3 directory. Each + cache_disable_{0,1} file corresponds to one disable slot which + can be used to disable a cache index. Reading from these files + on a processor with this functionality will return the currently + disabled index for that node. There is one L3 structure per + node, or per internal node on MCM machines. Writing a valid + index to one of these files will cause the specificed cache + index to be disabled. + + All AMD processors with L3 caches provide this functionality. + For details, see BKDGs at + http://developer.amd.com/documentation/guides/Pages/default.aspx From 865be7a81071a77014c83cd01536c989eed362b4 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Mon, 16 May 2011 21:38:08 +0200 Subject: [PATCH 8/8] x86, cpu: Fix detection of Celeron Covington stepping A1 and B0 Steppings A1 and B0 of Celeron Covington are currently misdetected as Pentium II (Dixon). Fix it by removing the stepping check. [ hpa: this fixes this specific bug... the CPUID documentation specifies that the L2 cache size can disambiguate additional CPUs; this patch does not fix that. ] Signed-off-by: Ondrej Zary Link: http://lkml.kernel.org/r/201105162138.15416.linux@rainbow-software.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/intel.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index df86bc8c859d..32e86aa52743 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -400,12 +400,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) switch (c->x86_model) { case 5: - if (c->x86_mask == 0) { - if (l2 == 0) - p = "Celeron (Covington)"; - else if (l2 == 256) - p = "Mobile Pentium II (Dixon)"; - } + if (l2 == 0) + p = "Celeron (Covington)"; + else if (l2 == 256) + p = "Mobile Pentium II (Dixon)"; break; case 6: