diff options
Diffstat (limited to 'arch/x86/include')
28 files changed, 441 insertions, 270 deletions
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 091508b533b4..952bd0100c5c 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -4,10 +4,10 @@ #ifdef CONFIG_SMP .macro LOCK_PREFIX -1: lock +672: lock .section .smp_locks,"a" .balign 4 - .long 1b - . + .long 672b - . .previous .endm #else diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 1a6c09af048f..3ab9bdd87e79 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -176,6 +176,7 @@ static inline u64 native_x2apic_icr_read(void) } extern int x2apic_phys; +extern int x2apic_preenabled; extern void check_x2apic(void); extern void enable_x2apic(void); extern void x2apic_icr_write(u32 low, u32 id); @@ -198,6 +199,9 @@ static inline void x2apic_force_phys(void) x2apic_phys = 1; } #else +static inline void disable_x2apic(void) +{ +} static inline void check_x2apic(void) { } @@ -212,6 +216,7 @@ static inline void x2apic_force_phys(void) { } +#define nox2apic 0 #define x2apic_preenabled 0 #define x2apic_supported() 0 #endif @@ -410,6 +415,7 @@ extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); #endif #ifdef CONFIG_X86_LOCAL_APIC + static inline u32 apic_read(u32 reg) { return apic->read(reg); diff --git a/arch/x86/include/asm/apic_flat_64.h b/arch/x86/include/asm/apic_flat_64.h new file mode 100644 index 000000000000..a2d312796440 --- /dev/null +++ b/arch/x86/include/asm/apic_flat_64.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_APIC_FLAT_64_H +#define _ASM_X86_APIC_FLAT_64_H + +extern void flat_init_apic_ldr(void); + +#endif + diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 3925d8007864..134bba00df09 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -144,6 +144,7 @@ #define APIC_BASE (fix_to_virt(FIX_APIC_BASE)) #define APIC_BASE_MSR 0x800 +#define XAPIC_ENABLE (1UL << 11) #define X2APIC_ENABLE (1UL << 10) #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 1775d6e5920e..b97596e2b68c 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -380,6 +380,8 @@ static inline unsigned long __fls(unsigned long word) return word; } +#undef ADDR + #ifdef __KERNEL__ /** * ffs - find first set bit in word @@ -395,10 +397,25 @@ static inline unsigned long __fls(unsigned long word) static inline int ffs(int x) { int r; -#ifdef CONFIG_X86_CMOV + +#ifdef CONFIG_X86_64 + /* + * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the + * dest reg is undefined if x==0, but their CPU architect says its + * value is written to set it to the same as before, except that the + * top 32 bits will be cleared. + * + * We cannot do this on 32 bits because at the very least some + * 486 CPUs did not behave this way. + */ + long tmp = -1; + asm("bsfl %1,%0" + : "=r" (r) + : "rm" (x), "0" (tmp)); +#elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" - : "=r" (r) : "rm" (x), "r" (-1)); + : "=&r" (r) : "rm" (x), "r" (-1)); #else asm("bsfl %1,%0\n\t" "jnz 1f\n\t" @@ -422,7 +439,22 @@ static inline int ffs(int x) static inline int fls(int x) { int r; -#ifdef CONFIG_X86_CMOV + +#ifdef CONFIG_X86_64 + /* + * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the + * dest reg is undefined if x==0, but their CPU architect says its + * value is written to set it to the same as before, except that the + * top 32 bits will be cleared. + * + * We cannot do this on 32 bits because at the very least some + * 486 CPUs did not behave this way. + */ + long tmp = -1; + asm("bsrl %1,%0" + : "=r" (r) + : "rm" (x), "0" (tmp)); +#elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "rm" (-1)); @@ -434,11 +466,35 @@ static inline int fls(int x) #endif return r + 1; } -#endif /* __KERNEL__ */ - -#undef ADDR -#ifdef __KERNEL__ +/** + * fls64 - find last set bit in a 64-bit word + * @x: the word to search + * + * This is defined in a similar way as the libc and compiler builtin + * ffsll, but returns the position of the most significant set bit. + * + * fls64(value) returns 0 if value is 0 or the position of the last + * set bit if value is nonzero. The last (most significant) bit is + * at position 64. + */ +#ifdef CONFIG_X86_64 +static __always_inline int fls64(__u64 x) +{ + long bitpos = -1; + /* + * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the + * dest reg is undefined if x==0, but their CPU architect says its + * value is written to set it to the same as before. + */ + asm("bsrq %1,%0" + : "+r" (bitpos) + : "rm" (x)); + return bitpos + 1; +} +#else +#include <asm-generic/bitops/fls64.h> +#endif #include <asm-generic/bitops/find.h> @@ -450,12 +506,6 @@ static inline int fls(int x) #include <asm-generic/bitops/const_hweight.h> -#endif /* __KERNEL__ */ - -#include <asm-generic/bitops/fls64.h> - -#ifdef __KERNEL__ - #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 5d3acdf5a7a6..0c9fa2745f13 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -14,6 +14,8 @@ extern void __cmpxchg_wrong_size(void) __compiletime_error("Bad argument size for cmpxchg"); extern void __xadd_wrong_size(void) __compiletime_error("Bad argument size for xadd"); +extern void __add_wrong_size(void) + __compiletime_error("Bad argument size for add"); /* * Constants for operation sizes. On 32-bit, the 64-bit size it set to @@ -31,60 +33,47 @@ extern void __xadd_wrong_size(void) #define __X86_CASE_Q -1 /* sizeof will never return -1 */ #endif +/* + * An exchange-type operation, which takes a value and a pointer, and + * returns a the old value. + */ +#define __xchg_op(ptr, arg, op, lock) \ + ({ \ + __typeof__ (*(ptr)) __ret = (arg); \ + switch (sizeof(*(ptr))) { \ + case __X86_CASE_B: \ + asm volatile (lock #op "b %b0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_W: \ + asm volatile (lock #op "w %w0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_L: \ + asm volatile (lock #op "l %0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_Q: \ + asm volatile (lock #op "q %q0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + default: \ + __ ## op ## _wrong_size(); \ + } \ + __ret; \ + }) + /* * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. * Since this is generally used to protect other memory information, we * use "asm volatile" and "memory" clobbers to prevent gcc from moving * information around. */ -#define __xchg(x, ptr, size) \ -({ \ - __typeof(*(ptr)) __x = (x); \ - switch (size) { \ - case __X86_CASE_B: \ - { \ - volatile u8 *__ptr = (volatile u8 *)(ptr); \ - asm volatile("xchgb %0,%1" \ - : "=q" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case __X86_CASE_W: \ - { \ - volatile u16 *__ptr = (volatile u16 *)(ptr); \ - asm volatile("xchgw %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case __X86_CASE_L: \ - { \ - volatile u32 *__ptr = (volatile u32 *)(ptr); \ - asm volatile("xchgl %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case __X86_CASE_Q: \ - { \ - volatile u64 *__ptr = (volatile u64 *)(ptr); \ - asm volatile("xchgq %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - default: \ - __xchg_wrong_size(); \ - } \ - __x; \ -}) - -#define xchg(ptr, v) \ - __xchg((v), (ptr), sizeof(*ptr)) +#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") /* * Atomic compare and exchange. Compare OLD with MEM, if identical, @@ -165,46 +154,80 @@ extern void __xadd_wrong_size(void) __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) #endif -#define __xadd(ptr, inc, lock) \ +/* + * xadd() adds "inc" to "*ptr" and atomically returns the previous + * value of "*ptr". + * + * xadd() is locked when multiple CPUs are online + * xadd_sync() is always locked + * xadd_local() is never locked + */ +#define __xadd(ptr, inc, lock) __xchg_op((ptr), (inc), xadd, lock) +#define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX) +#define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ") +#define xadd_local(ptr, inc) __xadd((ptr), (inc), "") + +#define __add(ptr, inc, lock) \ ({ \ __typeof__ (*(ptr)) __ret = (inc); \ switch (sizeof(*(ptr))) { \ case __X86_CASE_B: \ - asm volatile (lock "xaddb %b0, %1\n" \ - : "+r" (__ret), "+m" (*(ptr)) \ - : : "memory", "cc"); \ + asm volatile (lock "addb %b1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ break; \ case __X86_CASE_W: \ - asm volatile (lock "xaddw %w0, %1\n" \ - : "+r" (__ret), "+m" (*(ptr)) \ - : : "memory", "cc"); \ + asm volatile (lock "addw %w1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ break; \ case __X86_CASE_L: \ - asm volatile (lock "xaddl %0, %1\n" \ - : "+r" (__ret), "+m" (*(ptr)) \ - : : "memory", "cc"); \ + asm volatile (lock "addl %1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ break; \ case __X86_CASE_Q: \ - asm volatile (lock "xaddq %q0, %1\n" \ - : "+r" (__ret), "+m" (*(ptr)) \ - : : "memory", "cc"); \ + asm volatile (lock "addq %1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ break; \ default: \ - __xadd_wrong_size(); \ + __add_wrong_size(); \ } \ __ret; \ }) /* - * xadd() adds "inc" to "*ptr" and atomically returns the previous - * value of "*ptr". + * add_*() adds "inc" to "*ptr" * - * xadd() is locked when multiple CPUs are online - * xadd_sync() is always locked - * xadd_local() is never locked + * __add() takes a lock prefix + * add_smp() is locked when multiple CPUs are online + * add_sync() is always locked */ -#define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX) -#define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ") -#define xadd_local(ptr, inc) __xadd((ptr), (inc), "") +#define add_smp(ptr, inc) __add((ptr), (inc), LOCK_PREFIX) +#define add_sync(ptr, inc) __add((ptr), (inc), "lock; ") + +#define __cmpxchg_double(pfx, p1, p2, o1, o2, n1, n2) \ +({ \ + bool __ret; \ + __typeof__(*(p1)) __old1 = (o1), __new1 = (n1); \ + __typeof__(*(p2)) __old2 = (o2), __new2 = (n2); \ + BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long)); \ + BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long)); \ + VM_BUG_ON((unsigned long)(p1) % (2 * sizeof(long))); \ + VM_BUG_ON((unsigned long)((p1) + 1) != (unsigned long)(p2)); \ + asm volatile(pfx "cmpxchg%c4b %2; sete %0" \ + : "=a" (__ret), "+d" (__old2), \ + "+m" (*(p1)), "+m" (*(p2)) \ + : "i" (2 * sizeof(long)), "a" (__old1), \ + "b" (__new1), "c" (__new2)); \ + __ret; \ +}) + +#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \ + __cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2) + +#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ + __cmpxchg_double(, p1, p2, o1, o2, n1, n2) #endif /* ASM_X86_CMPXCHG_H */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index fbebb07dd80b..53f4b219336b 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -166,52 +166,6 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old, #endif -#define cmpxchg8b(ptr, o1, o2, n1, n2) \ -({ \ - char __ret; \ - __typeof__(o2) __dummy; \ - __typeof__(*(ptr)) __old1 = (o1); \ - __typeof__(o2) __old2 = (o2); \ - __typeof__(*(ptr)) __new1 = (n1); \ - __typeof__(o2) __new2 = (n2); \ - asm volatile(LOCK_PREFIX "cmpxchg8b %2; setz %1" \ - : "=d"(__dummy), "=a" (__ret), "+m" (*ptr)\ - : "a" (__old1), "d"(__old2), \ - "b" (__new1), "c" (__new2) \ - : "memory"); \ - __ret; }) - - -#define cmpxchg8b_local(ptr, o1, o2, n1, n2) \ -({ \ - char __ret; \ - __typeof__(o2) __dummy; \ - __typeof__(*(ptr)) __old1 = (o1); \ - __typeof__(o2) __old2 = (o2); \ - __typeof__(*(ptr)) __new1 = (n1); \ - __typeof__(o2) __new2 = (n2); \ - asm volatile("cmpxchg8b %2; setz %1" \ - : "=d"(__dummy), "=a"(__ret), "+m" (*ptr)\ - : "a" (__old), "d"(__old2), \ - "b" (__new1), "c" (__new2), \ - : "memory"); \ - __ret; }) - - -#define cmpxchg_double(ptr, o1, o2, n1, n2) \ -({ \ - BUILD_BUG_ON(sizeof(*(ptr)) != 4); \ - VM_BUG_ON((unsigned long)(ptr) % 8); \ - cmpxchg8b((ptr), (o1), (o2), (n1), (n2)); \ -}) - -#define cmpxchg_double_local(ptr, o1, o2, n1, n2) \ -({ \ - BUILD_BUG_ON(sizeof(*(ptr)) != 4); \ - VM_BUG_ON((unsigned long)(ptr) % 8); \ - cmpxchg16b_local((ptr), (o1), (o2), (n1), (n2)); \ -}) - #define system_has_cmpxchg_double() cpu_has_cx8 #endif /* _ASM_X86_CMPXCHG_32_H */ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 285da02c38fa..614be87f1a9b 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -20,49 +20,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) cmpxchg_local((ptr), (o), (n)); \ }) -#define cmpxchg16b(ptr, o1, o2, n1, n2) \ -({ \ - char __ret; \ - __typeof__(o2) __junk; \ - __typeof__(*(ptr)) __old1 = (o1); \ - __typeof__(o2) __old2 = (o2); \ - __typeof__(*(ptr)) __new1 = (n1); \ - __typeof__(o2) __new2 = (n2); \ - asm volatile(LOCK_PREFIX "cmpxchg16b %2;setz %1" \ - : "=d"(__junk), "=a"(__ret), "+m" (*ptr) \ - : "b"(__new1), "c"(__new2), \ - "a"(__old1), "d"(__old2)); \ - __ret; }) - - -#define cmpxchg16b_local(ptr, o1, o2, n1, n2) \ -({ \ - char __ret; \ - __typeof__(o2) __junk; \ - __typeof__(*(ptr)) __old1 = (o1); \ - __typeof__(o2) __old2 = (o2); \ - __typeof__(*(ptr)) __new1 = (n1); \ - __typeof__(o2) __new2 = (n2); \ - asm volatile("cmpxchg16b %2;setz %1" \ - : "=d"(__junk), "=a"(__ret), "+m" (*ptr) \ - : "b"(__new1), "c"(__new2), \ - "a"(__old1), "d"(__old2)); \ - __ret; }) - -#define cmpxchg_double(ptr, o1, o2, n1, n2) \ -({ \ - BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - VM_BUG_ON((unsigned long)(ptr) % 16); \ - cmpxchg16b((ptr), (o1), (o2), (n1), (n2)); \ -}) - -#define cmpxchg_double_local(ptr, o1, o2, n1, n2) \ -({ \ - BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - VM_BUG_ON((unsigned long)(ptr) % 16); \ - cmpxchg16b_local((ptr), (o1), (o2), (n1), (n2)); \ -}) - #define system_has_cmpxchg_double() cpu_has_cx16 #endif /* _ASM_X86_CMPXCHG_64_H */ diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index 9a2d644c08ef..ced283ac79df 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -4,6 +4,7 @@ #ifdef CONFIG_X86_32 #include <linux/types.h> +#include <linux/log2.h> /* * do_div() is NOT a C function. It wants to return @@ -21,15 +22,20 @@ ({ \ unsigned long __upper, __low, __high, __mod, __base; \ __base = (base); \ - asm("":"=a" (__low), "=d" (__high) : "A" (n)); \ - __upper = __high; \ - if (__high) { \ - __upper = __high % (__base); \ - __high = __high / (__base); \ + if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \ + __mod = n & (__base - 1); \ + n >>= ilog2(__base); \ + } else { \ + asm("" : "=a" (__low), "=d" (__high) : "A" (n));\ + __upper = __high; \ + if (__high) { \ + __upper = __high % (__base); \ + __high = __high / (__base); \ + } \ + asm("divl %2" : "=a" (__low), "=d" (__mod) \ + : "rm" (__base), "0" (__low), "1" (__upper)); \ + asm("" : "=A" (n) : "a" (__low), "d" (__high)); \ } \ - asm("divl %2":"=a" (__low), "=d" (__mod) \ - : "rm" (__base), "0" (__low), "1" (__upper)); \ - asm("":"=A" (n) : "a" (__low), "d" (__high)); \ __mod; \ }) diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 908b96957d88..37782566af24 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -117,7 +117,7 @@ static inline void early_memtest(unsigned long start, unsigned long end) extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); -extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); +extern u64 early_reserve_e820(u64 sizet, u64 align); void memblock_x86_fill(void); void memblock_find_dma_reserve(void); diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 55e4de613f0e..da0b3ca815b7 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -11,6 +11,7 @@ typedef struct { #ifdef CONFIG_X86_LOCAL_APIC unsigned int apic_timer_irqs; /* arch dependent */ unsigned int irq_spurious_count; + unsigned int icr_read_retry_count; #endif unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index c9e09ea05644..6919e936345b 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -218,7 +218,7 @@ static inline void fpu_fxsave(struct fpu *fpu) #ifdef CONFIG_SMP #define safe_address (__per_cpu_offset[0]) #else -#define safe_address (kstat_cpu(0).cpustat.user) +#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER]) #endif /* diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 88c765e16410..74df3f1eddfd 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -137,6 +137,13 @@ static inline int insn_is_avx(struct insn *insn) return (insn->vex_prefix.value != 0); } +/* Ensure this instruction is decoded completely */ +static inline int insn_complete(struct insn *insn) +{ + return insn->opcode.got && insn->modrm.got && insn->sib.got && + insn->displacement.got && insn->immediate.got; +} + static inline insn_byte_t insn_vex_m_bits(struct insn *insn) { if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ diff --git a/arch/x86/include/asm/mach_timer.h b/arch/x86/include/asm/mach_timer.h index 853728519ae9..88d0c3c74c13 100644 --- a/arch/x86/include/asm/mach_timer.h +++ b/arch/x86/include/asm/mach_timer.h @@ -15,7 +15,7 @@ #define CALIBRATE_TIME_MSEC 30 /* 30 msecs */ #define CALIBRATE_LATCH \ - ((CLOCK_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000) + ((PIT_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000) static inline void mach_prepare_counter(void) { diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 01fdf5674e24..0e8e85bb7c51 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -81,8 +81,8 @@ static inline unsigned char current_lock_cmos_reg(void) #else #define lock_cmos_prefix(reg) do {} while (0) #define lock_cmos_suffix(reg) do {} while (0) -#define lock_cmos(reg) -#define unlock_cmos() +#define lock_cmos(reg) do { } while (0) +#define unlock_cmos() do { } while (0) #define do_i_have_lock_cmos() 0 #define current_lock_cmos_reg() 0 #endif diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h deleted file mode 100644 index 0cd3800f33b9..000000000000 --- a/arch/x86/include/asm/memblock.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _X86_MEMBLOCK_H -#define _X86_MEMBLOCK_H - -#define ARCH_DISCARD_MEMBLOCK - -u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align); - -void memblock_x86_reserve_range(u64 start, u64 end, char *name); -void memblock_x86_free_range(u64 start, u64 end); -struct range; -int __get_free_all_memory_range(struct range **range, int nodeid, - unsigned long start_pfn, unsigned long end_pfn); -int get_free_all_memory_range(struct range **rangep, int nodeid); - -void memblock_x86_register_active_regions(int nid, unsigned long start_pfn, - unsigned long last_pfn); -u64 memblock_x86_hole_size(u64 start, u64 end); -u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align); -u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit); -u64 memblock_x86_memory_in_range(u64 addr, u64 limit); -bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align); - -#endif diff --git a/arch/x86/include/asm/numachip/numachip_csr.h b/arch/x86/include/asm/numachip/numachip_csr.h new file mode 100644 index 000000000000..660f843df928 --- /dev/null +++ b/arch/x86/include/asm/numachip/numachip_csr.h @@ -0,0 +1,167 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Numascale NumaConnect-Specific Header file + * + * Copyright (C) 2011 Numascale AS. All rights reserved. + * + * Send feedback to <support@numascale.com> + * + */ + +#ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H +#define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H + +#include <linux/numa.h> +#include <linux/percpu.h> +#include <linux/io.h> +#include <linux/swab.h> +#include <asm/types.h> +#include <asm/processor.h> + +#define CSR_NODE_SHIFT 16 +#define CSR_NODE_BITS(p) (((unsigned long)(p)) << CSR_NODE_SHIFT) +#define CSR_NODE_MASK 0x0fff /* 4K nodes */ + +/* 32K CSR space, b15 indicates geo/non-geo */ +#define CSR_OFFSET_MASK 0x7fffUL + +/* Global CSR space covers all 4K possible nodes with 64K CSR space per node */ +#define NUMACHIP_GCSR_BASE 0x3fff00000000ULL +#define NUMACHIP_GCSR_LIM 0x3fff0fffffffULL +#define NUMACHIP_GCSR_SIZE (NUMACHIP_GCSR_LIM - NUMACHIP_GCSR_BASE + 1) + +/* + * Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however + * when using the direct mapping on x86_64, both start and size needs to be + * aligned with PMD_SIZE which is 2M + */ +#define NUMACHIP_LCSR_BASE 0x3ffffe000000ULL +#define NUMACHIP_LCSR_LIM 0x3fffffffffffULL +#define NUMACHIP_LCSR_SIZE (NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1) + +static inline void *gcsr_address(int node, unsigned long offset) +{ + return __va(NUMACHIP_GCSR_BASE | (1UL << 15) | + CSR_NODE_BITS(node & CSR_NODE_MASK) | (offset & CSR_OFFSET_MASK)); +} + +static inline void *lcsr_address(unsigned long offset) +{ + return __va(NUMACHIP_LCSR_BASE | (1UL << 15) | + CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK)); +} + +static inline unsigned int read_gcsr(int node, unsigned long offset) +{ + return swab32(readl(gcsr_address(node, offset))); +} + +static inline void write_gcsr(int node, unsigned long offset, unsigned int val) +{ + writel(swab32(val), gcsr_address(node, offset)); +} + +static inline unsigned int read_lcsr(unsigned long offset) +{ + return swab32(readl(lcsr_address(offset))); +} + +static inline void write_lcsr(unsigned long offset, unsigned int val) +{ + writel(swab32(val), lcsr_address(offset)); +} + +/* ========================================================================= */ +/* CSR_G0_STATE_CLEAR */ +/* ========================================================================= */ + +#define CSR_G0_STATE_CLEAR (0x000 + (0 << 12)) +union numachip_csr_g0_state_clear { + unsigned int v; + struct numachip_csr_g0_state_clear_s { + unsigned int _state:2; + unsigned int _rsvd_2_6:5; + unsigned int _lost:1; + unsigned int _rsvd_8_31:24; + } s; +}; + +/* ========================================================================= */ +/* CSR_G0_NODE_IDS */ +/* ========================================================================= */ + +#define CSR_G0_NODE_IDS (0x008 + (0 << 12)) +union numachip_csr_g0_node_ids { + unsigned int v; + struct numachip_csr_g0_node_ids_s { + unsigned int _initialid:16; + unsigned int _nodeid:12; + unsigned int _rsvd_28_31:4; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_EXT_IRQ_GEN */ +/* ========================================================================= */ + +#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12)) +union numachip_csr_g3_ext_irq_gen { + unsigned int v; + struct numachip_csr_g3_ext_irq_gen_s { + unsigned int _vector:8; + unsigned int _msgtype:3; + unsigned int _index:5; + unsigned int _destination_apic_id:16; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_EXT_IRQ_STATUS */ +/* ========================================================================= */ + +#define CSR_G3_EXT_IRQ_STATUS (0x034 + (3 << 12)) +union numachip_csr_g3_ext_irq_status { + unsigned int v; + struct numachip_csr_g3_ext_irq_status_s { + unsigned int _result:32; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_EXT_IRQ_DEST */ +/* ========================================================================= */ + +#define CSR_G3_EXT_IRQ_DEST (0x038 + (3 << 12)) +union numachip_csr_g3_ext_irq_dest { + unsigned int v; + struct numachip_csr_g3_ext_irq_dest_s { + unsigned int _irq:8; + unsigned int _rsvd_8_31:24; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_NC_ATT_MAP_SELECT */ +/* ========================================================================= */ + +#define CSR_G3_NC_ATT_MAP_SELECT (0x7fc + (3 << 12)) +union numachip_csr_g3_nc_att_map_select { + unsigned int v; + struct numachip_csr_g3_nc_att_map_select_s { + unsigned int _upper_address_bits:4; + unsigned int _select_ram:4; + unsigned int _rsvd_8_31:24; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_NC_ATT_MAP_SELECT_0-255 */ +/* ========================================================================= */ + +#define CSR_G3_NC_ATT_MAP_SELECT_0 (0x800 + (3 << 12)) + +#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */ + diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 3470c9d0ebba..529bf07e8067 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -451,23 +451,20 @@ do { \ #endif /* !CONFIG_M386 */ #ifdef CONFIG_X86_CMPXCHG64 -#define percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) \ +#define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2) \ ({ \ - char __ret; \ - typeof(o1) __o1 = o1; \ - typeof(o1) __n1 = n1; \ - typeof(o2) __o2 = o2; \ - typeof(o2) __n2 = n2; \ - typeof(o2) __dummy = n2; \ + bool __ret; \ + typeof(pcp1) __o1 = (o1), __n1 = (n1); \ + typeof(pcp2) __o2 = (o2), __n2 = (n2); \ asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \ - : "=a"(__ret), "=m" (pcp1), "=d"(__dummy) \ - : "b"(__n1), "c"(__n2), "a"(__o1), "d"(__o2)); \ + : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \ + : "b" (__n1), "c" (__n2), "a" (__o1)); \ __ret; \ }) -#define __this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) -#define this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) -#define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) +#define __this_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double +#define this_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double +#define irqsafe_cpu_cmpxchg_double_4 percpu_cmpxchg8b_double #endif /* CONFIG_X86_CMPXCHG64 */ /* @@ -508,31 +505,23 @@ 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" ASM_NOP3 -#else -#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP2 -#endif -#define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) \ +#define percpu_cmpxchg16b_double(pcp1, pcp2, o1, o2, n1, n2) \ ({ \ - char __ret; \ - typeof(o1) __o1 = o1; \ - typeof(o1) __n1 = n1; \ - typeof(o2) __o2 = o2; \ - typeof(o2) __n2 = n2; \ - typeof(o2) __dummy; \ - alternative_io(CMPXCHG16B_EMU_CALL, \ - "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \ + bool __ret; \ + typeof(pcp1) __o1 = (o1), __n1 = (n1); \ + typeof(pcp2) __o2 = (o2), __n2 = (n2); \ + alternative_io("leaq %P1,%%rsi\n\tcall this_cpu_cmpxchg16b_emu\n\t", \ + "cmpxchg16b " __percpu_arg(1) "\n\tsetz %0\n\t", \ X86_FEATURE_CX16, \ - ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \ - "S" (&pcp1), "b"(__n1), "c"(__n2), \ - "a"(__o1), "d"(__o2) : "memory"); \ + ASM_OUTPUT2("=a" (__ret), "+m" (pcp1), \ + "+m" (pcp2), "+d" (__o2)), \ + "b" (__n1), "c" (__n2), "a" (__o1) : "rsi"); \ __ret; \ }) -#define __this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) -#define this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) -#define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) +#define __this_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double +#define this_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double +#define irqsafe_cpu_cmpxchg_double_8 percpu_cmpxchg16b_double #endif diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index f61c62f7d5d8..096c975e099f 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -57,6 +57,7 @@ (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX)) #define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6 +#define ARCH_PERFMON_EVENTS_COUNT 7 /* * Intel "Architectural Performance Monitoring" CPUID @@ -72,6 +73,19 @@ union cpuid10_eax { unsigned int full; }; +union cpuid10_ebx { + struct { + unsigned int no_unhalted_core_cycles:1; + unsigned int no_instructions_retired:1; + unsigned int no_unhalted_reference_cycles:1; + unsigned int no_llc_reference:1; + unsigned int no_llc_misses:1; + unsigned int no_branch_instruction_retired:1; + unsigned int no_branch_misses_retired:1; + } split; + unsigned int full; +}; + union cpuid10_edx { struct { unsigned int num_counters_fixed:5; @@ -81,6 +95,15 @@ union cpuid10_edx { unsigned int full; }; +struct x86_pmu_capability { + int version; + int num_counters_gp; + int num_counters_fixed; + int bit_width_gp; + int bit_width_fixed; + unsigned int events_mask; + int events_mask_len; +}; /* * Fixed-purpose performance events: @@ -89,23 +112,24 @@ union cpuid10_edx { /* * All 3 fixed-mode PMCs are configured via this single MSR: */ -#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d +#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d /* * The counts are available in three separate MSRs: */ /* Instr_Retired.Any: */ -#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309 -#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0) +#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309 +#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0) /* CPU_CLK_Unhalted.Core: */ -#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a -#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1) +#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a +#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1) /* CPU_CLK_Unhalted.Ref: */ -#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b -#define X86_PMC_IDX_FIXED_BUS_CYCLES (X86_PMC_IDX_FIXED + 2) +#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b +#define X86_PMC_IDX_FIXED_REF_CYCLES (X86_PMC_IDX_FIXED + 2) +#define X86_PMC_MSK_FIXED_REF_CYCLES (1ULL << X86_PMC_IDX_FIXED_REF_CYCLES) /* * We model BTS tracing as another fixed-mode PMC. @@ -202,6 +226,7 @@ struct perf_guest_switch_msr { }; extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); +extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); #else static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr) { @@ -209,6 +234,11 @@ static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr) return NULL; } +static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) +{ + memset(cap, 0, sizeof(*cap)); +} + static inline void perf_events_lapic_init(void) { } #endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 18601c86fab1..49afb3f41eb6 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -703,7 +703,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, pte_update(mm, addr, ptep); } -#define flush_tlb_fix_spurious_fault(vma, address) +#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 2dddb317bb39..f8ab3eaad128 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -6,6 +6,7 @@ * EFLAGS bits */ #define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ +#define X86_EFLAGS_BIT1 0x00000002 /* Bit 1 - always on */ #define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ #define X86_EFLAGS_AF 0x00000010 /* Auxiliary carry Flag */ #define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b650435ffb53..aa9088c26931 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -99,7 +99,6 @@ struct cpuinfo_x86 { u16 apicid; u16 initial_apicid; u16 x86_clflush_size; -#ifdef CONFIG_SMP /* number of cores as seen by the OS: */ u16 booted_cores; /* Physical processor id: */ @@ -110,7 +109,6 @@ struct cpuinfo_x86 { u8 compute_unit_id; /* Index into per_cpu list: */ u16 cpu_index; -#endif u32 microcode; } __attribute__((__aligned__(SMP_CACHE_BYTES))); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 972c260919a3..a82c2bf504b6 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -79,23 +79,10 @@ static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail; } -#if (NR_CPUS < 256) static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) { - asm volatile(UNLOCK_LOCK_PREFIX "incb %0" - : "+m" (lock->head_tail) - : - : "memory", "cc"); + __add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX); } -#else -static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) -{ - asm volatile(UNLOCK_LOCK_PREFIX "incw %0" - : "+m" (lock->head_tail) - : - : "memory", "cc"); -} -#endif static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) { diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index a1fe5c127b52..185b719ec61a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -40,7 +40,8 @@ struct thread_info { */ __u8 supervisor_stack[0]; #endif - int uaccess_err; + int sig_on_uaccess_error:1; + int uaccess_err:1; /* uaccess failed */ }; #define INIT_THREAD_INFO(tsk) \ @@ -231,6 +232,12 @@ static inline struct thread_info *current_thread_info(void) movq PER_CPU_VAR(kernel_stack),reg ; \ subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg +/* + * Same if PER_CPU_VAR(kernel_stack) is, perhaps with some offset, already in + * a certain register (to be used in assembler memory operands). + */ +#define THREAD_INFO(reg, off) KERNEL_STACK_OFFSET+(off)-THREAD_SIZE(reg) + #endif #endif /* !X86_32 */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index c00692476e9f..800f77c60051 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -130,10 +130,8 @@ extern void setup_node_to_cpumask_map(void); .balance_interval = 1, \ } -#ifdef CONFIG_X86_64 extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) -#endif #else /* !CONFIG_NUMA */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 83e2efd181e2..15d99153a96d 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -51,6 +51,8 @@ extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern unsigned long native_calibrate_tsc(void); +extern int tsc_clocksource_reliable; + /* * Boot-time check whether the TSCs are synchronized across * all CPUs/cores: diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 36361bf6fdd1..8be5f54d9360 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -462,7 +462,7 @@ struct __large_struct { unsigned long buf[100]; }; barrier(); #define uaccess_catch(err) \ - (err) |= current_thread_info()->uaccess_err; \ + (err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0); \ current_thread_info()->uaccess_err = prev_err; \ } while (0) diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 1971e652d24b..1ac860a09849 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -7,6 +7,7 @@ struct mpc_bus; struct mpc_cpu; struct mpc_table; +struct cpuinfo_x86; /** * struct x86_init_mpparse - platform specific mpparse ops @@ -147,6 +148,7 @@ struct x86_init_ops { */ struct x86_cpuinit_ops { void (*setup_percpu_clockev)(void); + void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); }; /** @@ -186,5 +188,6 @@ extern struct x86_msi_ops x86_msi; extern void x86_init_noop(void); extern void x86_init_uint_noop(unsigned int unused); +extern void x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node); #endif |