diff options
Diffstat (limited to 'arch/x86/include/asm')
47 files changed, 661 insertions, 312 deletions
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index a54ee1d054d..aaac3b2fb74 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -19,7 +19,7 @@ extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); extern int amd_numa_init(void); extern int amd_get_subcaches(int); -extern int amd_set_subcaches(int, int); +extern int amd_set_subcaches(int, unsigned long); struct amd_l3_cache { unsigned indices; diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h index 0d9ec770f2f..e6a92455740 100644 --- a/arch/x86/include/asm/archrandom.h +++ b/arch/x86/include/asm/archrandom.h @@ -39,6 +39,20 @@ #ifdef CONFIG_ARCH_RANDOM +/* Instead of arch_get_random_long() when alternatives haven't run. */ +static inline int rdrand_long(unsigned long *v) +{ + int ok; + asm volatile("1: " RDRAND_LONG "\n\t" + "jc 2f\n\t" + "decl %0\n\t" + "jnz 1b\n\t" + "2:" + : "=r" (ok), "=a" (*v) + : "0" (RDRAND_RETRY_LOOPS)); + return ok; +} + #define GET_RANDOM(name, type, rdrand, nop) \ static inline int name(type *v) \ { \ @@ -68,6 +82,13 @@ GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3); #endif /* CONFIG_X86_64 */ +#else + +static inline int rdrand_long(unsigned long *v) +{ + return 0; +} + #endif /* CONFIG_ARCH_RANDOM */ extern void x86_init_rdrand(struct cpuinfo_x86 *c); diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index c6cd358a1ee..04a48903b2e 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -92,12 +92,53 @@ #endif #define smp_read_barrier_depends() read_barrier_depends() #define set_mb(var, value) do { (void)xchg(&var, value); } while (0) -#else +#else /* !SMP */ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() #define smp_read_barrier_depends() do { } while (0) #define set_mb(var, value) do { var = value; barrier(); } while (0) +#endif /* SMP */ + +#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) + +/* + * For either of these options x86 doesn't have a strong TSO memory + * model and we should fall back to full barriers. + */ + +#define smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + smp_mb(); \ + ACCESS_ONCE(*p) = (v); \ +} while (0) + +#define smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + smp_mb(); \ + ___p1; \ +}) + +#else /* regular x86 TSO memory ordering */ + +#define smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + barrier(); \ + ACCESS_ONCE(*p) = (v); \ +} while (0) + +#define smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + barrier(); \ + ___p1; \ +}) + #endif /* diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 89270b4318d..e099f9502ac 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -216,6 +216,7 @@ #define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */ #define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */ #define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_MPX (9*32+14) /* Memory Protection Extension */ #define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */ diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index fd8f9e2ca35..535192f6bfa 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -13,7 +13,9 @@ static __always_inline __init void *dmi_alloc(unsigned len) } /* Use early IO mappings for DMI because it's initialized early */ -#define dmi_ioremap early_ioremap -#define dmi_iounmap early_iounmap +#define dmi_early_remap early_ioremap +#define dmi_early_unmap early_iounmap +#define dmi_remap ioremap +#define dmi_unmap iounmap #endif /* _ASM_X86_DMI_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 65c6e6e3a55..3d6b9f81cc6 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -1,6 +1,24 @@ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H +/* + * We map the EFI regions needed for runtime services non-contiguously, + * with preserved alignment on virtual addresses starting from -4G down + * for a total max space of 64G. This way, we provide for stable runtime + * services addresses across kernels so that a kexec'd kernel can still + * use them. + * + * This is the main reason why we're doing stable VA mappings for RT + * services. + * + * This flag is used in conjuction with a chicken bit called + * "efi=old_map" which can be used as a fallback to the old runtime + * services mapping method in case there's some b0rkage with a + * particular EFI implementation (haha, it is hard to hold up the + * sarcasm here...). + */ +#define EFI_OLD_MEMMAP EFI_ARCH_1 + #ifdef CONFIG_X86_32 #define EFI_LOADER_SIGNATURE "EL32" @@ -69,24 +87,31 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, efi_call6((f), (u64)(a1), (u64)(a2), (u64)(a3), \ (u64)(a4), (u64)(a5), (u64)(a6)) +#define _efi_call_virtX(x, f, ...) \ +({ \ + efi_status_t __s; \ + \ + efi_sync_low_kernel_mappings(); \ + preempt_disable(); \ + __s = efi_call##x((void *)efi.systab->runtime->f, __VA_ARGS__); \ + preempt_enable(); \ + __s; \ +}) + #define efi_call_virt0(f) \ - efi_call0((efi.systab->runtime->f)) -#define efi_call_virt1(f, a1) \ - efi_call1((efi.systab->runtime->f), (u64)(a1)) -#define efi_call_virt2(f, a1, a2) \ - efi_call2((efi.systab->runtime->f), (u64)(a1), (u64)(a2)) -#define efi_call_virt3(f, a1, a2, a3) \ - efi_call3((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3)) -#define efi_call_virt4(f, a1, a2, a3, a4) \ - efi_call4((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3), (u64)(a4)) -#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ - efi_call5((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3), (u64)(a4), (u64)(a5)) -#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ - efi_call6((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ - (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) + _efi_call_virtX(0, f) +#define efi_call_virt1(f, a1) \ + _efi_call_virtX(1, f, (u64)(a1)) +#define efi_call_virt2(f, a1, a2) \ + _efi_call_virtX(2, f, (u64)(a1), (u64)(a2)) +#define efi_call_virt3(f, a1, a2, a3) \ + _efi_call_virtX(3, f, (u64)(a1), (u64)(a2), (u64)(a3)) +#define efi_call_virt4(f, a1, a2, a3, a4) \ + _efi_call_virtX(4, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4)) +#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ + _efi_call_virtX(5, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5)) +#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ + _efi_call_virtX(6, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); @@ -95,12 +120,30 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, extern int add_efi_memmap; extern unsigned long x86_efi_facility; +extern struct efi_scratch efi_scratch; extern void efi_set_executable(efi_memory_desc_t *md, bool executable); extern int efi_memblock_x86_reserve_range(void); extern void efi_call_phys_prelog(void); extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); +extern void __init efi_map_region(efi_memory_desc_t *md); +extern void __init efi_map_region_fixed(efi_memory_desc_t *md); +extern void efi_sync_low_kernel_mappings(void); +extern void efi_setup_page_tables(void); +extern void __init old_map_region(efi_memory_desc_t *md); +extern void __init runtime_code_page_mkexec(void); +extern void __init efi_runtime_mkexec(void); + +struct efi_setup_data { + u64 fw_vendor; + u64 runtime; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +extern u64 efi_setup; #ifdef CONFIG_EFI @@ -110,7 +153,7 @@ static inline bool efi_is_native(void) } extern struct console early_efi_console; - +extern void parse_efi_setup(u64 phys_addr, u32 data_len); #else /* * IF EFI is not configured, have the EFI calls return -ENOSYS. @@ -122,6 +165,7 @@ extern struct console early_efi_console; #define efi_call4(_f, _a1, _a2, _a3, _a4) (-ENOSYS) #define efi_call5(_f, _a1, _a2, _a3, _a4, _a5) (-ENOSYS) #define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6) (-ENOSYS) +static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {} #endif /* CONFIG_EFI */ #endif /* _ASM_X86_EFI_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index e846225265e..7252cd33917 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -175,64 +175,7 @@ static inline void __set_fixmap(enum fixed_addresses idx, } #endif -#define set_fixmap(idx, phys) \ - __set_fixmap(idx, phys, PAGE_KERNEL) - -/* - * Some hardware wants to get fixmapped without caching. - */ -#define set_fixmap_nocache(idx, phys) \ - __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE) - -#define clear_fixmap(idx) \ - __set_fixmap(idx, 0, __pgprot(0)) - -#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT)) -#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT) - -extern void __this_fixmap_does_not_exist(void); - -/* - * 'index to address' translation. If anyone tries to use the idx - * directly without translation, we catch the bug with a NULL-deference - * kernel oops. Illegal ranges of incoming indices are caught too. - */ -static __always_inline unsigned long fix_to_virt(const unsigned int idx) -{ - /* - * this branch gets completely eliminated after inlining, - * except when someone tries to use fixaddr indices in an - * illegal way. (such as mixing up address types or using - * out-of-range indices). - * - * If it doesn't get removed, the linker will complain - * loudly with a reasonably clear error message.. - */ - if (idx >= __end_of_fixed_addresses) - __this_fixmap_does_not_exist(); - - return __fix_to_virt(idx); -} - -static inline unsigned long virt_to_fix(const unsigned long vaddr) -{ - BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); - return __virt_to_fix(vaddr); -} - -/* Return an pointer with offset calculated */ -static __always_inline unsigned long -__set_fixmap_offset(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) -{ - __set_fixmap(idx, phys, flags); - return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1)); -} - -#define set_fixmap_offset(idx, phys) \ - __set_fixmap_offset(idx, phys, PAGE_KERNEL) - -#define set_fixmap_offset_nocache(idx, phys) \ - __set_fixmap_offset(idx, phys, PAGE_KERNEL_NOCACHE) +#include <asm-generic/fixmap.h> #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index c49a613c645..cea1c76d49b 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -293,12 +293,13 @@ static inline int restore_fpu_checking(struct task_struct *tsk) /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is pending. Clear the x87 state here by setting it to fixed values. "m" is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (tsk->thread.fpu.has_fpu)); + if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) { + asm volatile( + "fnclex\n\t" + "emms\n\t" + "fildl %P[addr]" /* set F?P to defined value */ + : : [addr] "m" (tsk->thread.fpu.has_fpu)); + } return fpu_restore_checking(&tsk->thread.fpu); } diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index be27ba1e947..b4c1f545343 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -110,26 +110,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { - int ret = 0; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - - asm volatile("\t" ASM_STAC "\n" - "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" - "2:\t" ASM_CLAC "\n" - "\t.section .fixup, \"ax\"\n" - "3:\tmov %3, %0\n" - "\tjmp 2b\n" - "\t.previous\n" - _ASM_EXTABLE(1b, 3b) - : "+r" (ret), "=a" (oldval), "+m" (*uaddr) - : "i" (-EFAULT), "r" (newval), "1" (oldval) - : "memory" - ); - - *uval = oldval; - return ret; + return user_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval); } #endif diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h new file mode 100644 index 00000000000..e8c58f88b1d --- /dev/null +++ b/arch/x86/include/asm/hash.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_HASH_H +#define _ASM_X86_HASH_H + +struct fast_hash_ops; +extern void setup_arch_fast_hash(struct fast_hash_ops *ops); + +#endif /* _ASM_X86_HASH_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index cba45d99ac1..67d69b8e2d2 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -191,6 +191,9 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); #define trace_interrupt interrupt #endif +#define VECTOR_UNDEFINED -1 +#define VECTOR_RETRIGGERED -2 + typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); extern void setup_vector_irq(int cpu); diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 459769d3926..e34e097b6f9 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -51,10 +51,41 @@ struct devs_id { enum intel_mid_cpu_type { /* 1 was Moorestown */ INTEL_MID_CPU_CHIP_PENWELL = 2, + INTEL_MID_CPU_CHIP_CLOVERVIEW, + INTEL_MID_CPU_CHIP_TANGIER, }; extern enum intel_mid_cpu_type __intel_mid_cpu_chip; +/** + * struct intel_mid_ops - Interface between intel-mid & sub archs + * @arch_setup: arch_setup function to re-initialize platform + * structures (x86_init, x86_platform_init) + * + * This structure can be extended if any new interface is required + * between intel-mid & its sub arch files. + */ +struct intel_mid_ops { + void (*arch_setup)(void); +}; + +/* Helper API's for INTEL_MID_OPS_INIT */ +#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid) \ + [cpuid] = get_##cpuname##_ops + +/* Maximum number of CPU ops */ +#define MAX_CPU_OPS(a) (sizeof(a)/sizeof(void *)) + +/* + * For every new cpu addition, a weak get_<cpuname>_ops() function needs be + * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h. + */ +#define INTEL_MID_OPS_INIT {\ + DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL), \ + DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW), \ + DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER) \ +}; + #ifdef CONFIG_X86_INTEL_MID static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void) @@ -86,8 +117,21 @@ extern enum intel_mid_timer_options intel_mid_timer_options; * Penwell uses spread spectrum clock, so the freq number is not exactly * the same as reported by MSR based on SDM. */ -#define PENWELL_FSB_FREQ_83SKU 83200 -#define PENWELL_FSB_FREQ_100SKU 99840 +#define FSB_FREQ_83SKU 83200 +#define FSB_FREQ_100SKU 99840 +#define FSB_FREQ_133SKU 133000 + +#define FSB_FREQ_167SKU 167000 +#define FSB_FREQ_200SKU 200000 +#define FSB_FREQ_267SKU 267000 +#define FSB_FREQ_333SKU 333000 +#define FSB_FREQ_400SKU 400000 + +/* Bus Select SoC Fuse value */ +#define BSEL_SOC_FUSE_MASK 0x7 +#define BSEL_SOC_FUSE_001 0x1 /* FSB 133MHz */ +#define BSEL_SOC_FUSE_101 0x5 /* FSB 100MHz */ +#define BSEL_SOC_FUSE_111 0x7 /* FSB 83MHz */ #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h new file mode 100644 index 00000000000..8e71c794176 --- /dev/null +++ b/arch/x86/include/asm/iosf_mbi.h @@ -0,0 +1,90 @@ +/* + * iosf_mbi.h: Intel OnChip System Fabric MailBox access support + */ + +#ifndef IOSF_MBI_SYMS_H +#define IOSF_MBI_SYMS_H + +#define MBI_MCR_OFFSET 0xD0 +#define MBI_MDR_OFFSET 0xD4 +#define MBI_MCRX_OFFSET 0xD8 + +#define MBI_RD_MASK 0xFEFFFFFF +#define MBI_WR_MASK 0X01000000 + +#define MBI_MASK_HI 0xFFFFFF00 +#define MBI_MASK_LO 0x000000FF +#define MBI_ENABLE 0xF0 + +/* Baytrail available units */ +#define BT_MBI_UNIT_AUNIT 0x00 +#define BT_MBI_UNIT_SMC 0x01 +#define BT_MBI_UNIT_CPU 0x02 +#define BT_MBI_UNIT_BUNIT 0x03 +#define BT_MBI_UNIT_PMC 0x04 +#define BT_MBI_UNIT_GFX 0x06 +#define BT_MBI_UNIT_SMI 0x0C +#define BT_MBI_UNIT_USB 0x43 +#define BT_MBI_UNIT_SATA 0xA3 +#define BT_MBI_UNIT_PCIE 0xA6 + +/* Baytrail read/write opcodes */ +#define BT_MBI_AUNIT_READ 0x10 +#define BT_MBI_AUNIT_WRITE 0x11 +#define BT_MBI_SMC_READ 0x10 +#define BT_MBI_SMC_WRITE 0x11 +#define BT_MBI_CPU_READ 0x10 +#define BT_MBI_CPU_WRITE 0x11 +#define BT_MBI_BUNIT_READ 0x10 +#define BT_MBI_BUNIT_WRITE 0x11 +#define BT_MBI_PMC_READ 0x06 +#define BT_MBI_PMC_WRITE 0x07 +#define BT_MBI_GFX_READ 0x00 +#define BT_MBI_GFX_WRITE 0x01 +#define BT_MBI_SMIO_READ 0x06 +#define BT_MBI_SMIO_WRITE 0x07 +#define BT_MBI_USB_READ 0x06 +#define BT_MBI_USB_WRITE 0x07 +#define BT_MBI_SATA_READ 0x00 +#define BT_MBI_SATA_WRITE 0x01 +#define BT_MBI_PCIE_READ 0x00 +#define BT_MBI_PCIE_WRITE 0x01 + +/** + * iosf_mbi_read() - MailBox Interface read command + * @port: port indicating subunit being accessed + * @opcode: port specific read or write opcode + * @offset: register address offset + * @mdr: register data to be read + * + * Locking is handled by spinlock - cannot sleep. + * Return: Nonzero on error + */ +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr); + +/** + * iosf_mbi_write() - MailBox unmasked write command + * @port: port indicating subunit being accessed + * @opcode: port specific read or write opcode + * @offset: register address offset + * @mdr: register data to be written + * + * Locking is handled by spinlock - cannot sleep. + * Return: Nonzero on error + */ +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); + +/** + * iosf_mbi_modify() - MailBox masked write command + * @port: port indicating subunit being accessed + * @opcode: port specific read or write opcode + * @offset: register address offset + * @mdr: register data being modified + * @mask: mask indicating bits in mdr to be modified + * + * Locking is handled by spinlock - cannot sleep. + * Return: Nonzero on error + */ +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); + +#endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 0ea10f27d61..cb6cfcd034c 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -25,6 +25,7 @@ extern void irq_ctx_init(int cpu); #ifdef CONFIG_HOTPLUG_CPU #include <linux/cpumask.h> +extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); extern void irq_force_complete_move(int); #endif diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ae5d7830855..fdf83afbb7d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -605,6 +605,7 @@ struct kvm_arch { /* fields used by HYPER-V emulation */ u64 hv_guest_os_id; u64 hv_hypercall; + u64 hv_tsc_page; #ifdef CONFIG_KVM_MMU_AUDIT int audit_point; @@ -699,6 +700,8 @@ struct kvm_x86_ops { void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + u64 (*get_dr6)(struct kvm_vcpu *vcpu); + void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 1df11590975..c7678e43465 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -85,28 +85,9 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, return ret; } -static inline uint32_t kvm_cpuid_base(void) -{ - if (boot_cpu_data.cpuid_level < 0) - return 0; /* So we don't blow up on old processors */ - - if (cpu_has_hypervisor) - return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); - - return 0; -} - -static inline bool kvm_para_available(void) -{ - return kvm_cpuid_base() != 0; -} - -static inline unsigned int kvm_arch_para_features(void) -{ - return cpuid_eax(KVM_CPUID_FEATURES); -} - #ifdef CONFIG_KVM_GUEST +bool kvm_para_available(void); +unsigned int kvm_arch_para_features(void); void __init kvm_guest_init(void); void kvm_async_pf_task_wait(u32 token); void kvm_async_pf_task_wake(u32 token); @@ -126,6 +107,16 @@ static inline void kvm_spinlock_init(void) #define kvm_async_pf_task_wait(T) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) +static inline bool kvm_para_available(void) +{ + return 0; +} + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + static inline u32 kvm_read_and_reset_pf_reason(void) { return 0; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c696a868756..6e4ce2df87c 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -118,7 +118,6 @@ extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); #include <linux/percpu.h> -#include <linux/init.h> #include <linux/atomic.h> extern int mce_p5_enabled; diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index f98bd662531..b59827e7652 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,6 +1,21 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#define native_rdmsr(msr, val1, val2) \ +do { \ + u64 __val = native_read_msr((msr)); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ +} while (0) + +#define native_wrmsr(msr, low, high) \ + native_write_msr(msr, low, high) + +#define native_wrmsrl(msr, val) \ + native_write_msr((msr), \ + (u32)((u64)(val)), \ + (u32)((u64)(val) >> 32)) + struct cpu_signature { unsigned int sig; unsigned int pf; diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 4c019179a57..b7b10b82d3e 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -61,11 +61,10 @@ extern int __apply_microcode_amd(struct microcode_amd *mc_amd); extern int apply_microcode_amd(int cpu); extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); +#define PATCH_MAX_SIZE PAGE_SIZE +extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; + #ifdef CONFIG_MICROCODE_AMD_EARLY -#ifdef CONFIG_X86_32 -#define MPB_MAX_SIZE PAGE_SIZE -extern u8 amd_bsp_mpb[MPB_MAX_SIZE]; -#endif extern void __init load_ucode_amd_bsp(void); extern void load_ucode_amd_ap(void); extern int __init save_microcode_in_initrd_amd(void); diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 3142a94c7b4..3e6b4920ef5 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_MPSPEC_H #define _ASM_X86_MPSPEC_H -#include <linux/init.h> #include <asm/mpspec_def.h> #include <asm/x86_init.h> diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 2f366d0ac6b..1da25a5f96f 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_MWAIT_H #define _ASM_X86_MWAIT_H +#include <linux/sched.h> + #define MWAIT_SUBSTATE_MASK 0xf #define MWAIT_CSTATE_MASK 0xf #define MWAIT_SUBSTATE_SIZE 4 @@ -13,4 +15,45 @@ #define MWAIT_ECX_INTERRUPT_BREAK 0x1 +static inline void __monitor(const void *eax, unsigned long ecx, + unsigned long edx) +{ + /* "monitor %eax, %ecx, %edx;" */ + asm volatile(".byte 0x0f, 0x01, 0xc8;" + :: "a" (eax), "c" (ecx), "d"(edx)); +} + +static inline void __mwait(unsigned long eax, unsigned long ecx) +{ + /* "mwait %eax, %ecx;" */ + asm volatile(".byte 0x0f, 0x01, 0xc9;" + :: "a" (eax), "c" (ecx)); +} + +/* + * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, + * which can obviate IPI to trigger checking of need_resched. + * We execute MONITOR against need_resched and enter optimized wait state + * through MWAIT. Whenever someone changes need_resched, we would be woken + * up from MWAIT (without an IPI). + * + * New with Core Duo processors, MWAIT can take some hints based on CPU + * capability. + */ +static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) +{ + if (!current_set_polling_and_test()) { + if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) { + mb(); + clflush((void *)¤t_thread_info()->flags); + mb(); + } + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + if (!need_resched()) + __mwait(eax, ecx); + } + current_clr_polling(); +} + #endif /* _ASM_X86_MWAIT_H */ diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index c87892442e5..775873d3be5 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -71,6 +71,7 @@ extern bool __virt_addr_valid(unsigned long kaddr); #include <asm-generic/getorder.h> #define __HAVE_ARCH_GATE_AREA 1 +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #endif /* __KERNEL__ */ #endif /* _ASM_X86_PAGE_H */ diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h index 4d550d04b60..904f528cc8e 100644 --- a/arch/x86/include/asm/page_32.h +++ b/arch/x86/include/asm/page_32.h @@ -5,10 +5,6 @@ #ifndef __ASSEMBLY__ -#ifdef CONFIG_HUGETLB_PAGE -#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA -#endif - #define __phys_addr_nodebug(x) ((x) - PAGE_OFFSET) #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 43dcd804ebd..8de6d9cf3b9 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -39,9 +39,18 @@ #define __VIRTUAL_MASK_SHIFT 47 /* - * Kernel image size is limited to 512 MB (see level2_kernel_pgt in - * arch/x86/kernel/head_64.S), and it is mapped here: + * Kernel image size is limited to 1GiB due to the fixmap living in the + * next 1GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S). Use + * 512MiB by default, leaving 1.5GiB for modules once the page tables + * are fully set up. If kernel ASLR is configured, it can extend the + * kernel page table mapping, reducing the size of the modules area. */ -#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) +#define KERNEL_IMAGE_SIZE_DEFAULT (512 * 1024 * 1024) +#if defined(CONFIG_RANDOMIZE_BASE) && \ + CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE_DEFAULT +#define KERNEL_IMAGE_SIZE CONFIG_RANDOMIZE_BASE_MAX_OFFSET +#else +#define KERNEL_IMAGE_SIZE KERNEL_IMAGE_SIZE_DEFAULT +#endif #endif /* _ASM_X86_PAGE_64_DEFS_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 401f350ef71..cd6e1610e29 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -781,9 +781,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, */ #define PV_CALLEE_SAVE_REGS_THUNK(func) \ extern typeof(func) __raw_callee_save_##func; \ - static void *__##func##__ __used = func; \ \ asm(".pushsection .text;" \ + ".globl __raw_callee_save_" #func " ; " \ "__raw_callee_save_" #func ": " \ PV_SAVE_ALL_CALLER_REGS \ "call " #func ";" \ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index aab8f671b52..7549b8b369e 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -388,10 +388,11 @@ extern struct pv_lock_ops pv_lock_ops; _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]") /* Simple instruction patching code. */ -#define DEF_NATIVE(ops, name, code) \ - extern const char start_##ops##_##name[] __visible, \ - end_##ops##_##name[] __visible; \ - asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") +#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t" + +#define DEF_NATIVE(ops, name, code) \ + __visible extern const char start_##ops##_##name[], end_##ops##_##name[]; \ + asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name)) unsigned paravirt_patch_nop(void); unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 947b5c417e8..1ac6114c9ea 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -104,7 +104,7 @@ extern void pci_iommu_alloc(void); struct msi_desc; int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void native_teardown_msi_irq(unsigned int irq); -void native_restore_msi_irqs(struct pci_dev *dev, int irq); +void native_restore_msi_irqs(struct pci_dev *dev); int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, unsigned int irq_base, unsigned int irq_offset); #else @@ -125,7 +125,6 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, /* generic pci stuff */ #include <asm-generic/pci.h> -#define PCIBIOS_MAX_MEM_32 0xffffffff #ifdef CONFIG_NUMA /* Returns the node based on pci bus */ diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 3bf2dd0cf61..0d193e23464 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -55,6 +55,13 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) #endif +/* Bit manipulation helper on pte/pgoff entry */ +static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshift, + unsigned long mask, unsigned int leftshift) +{ + return ((value >> rightshift) & mask) << leftshift; +} + #ifdef CONFIG_MEM_SOFT_DIRTY /* @@ -71,31 +78,34 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) #define PTE_FILE_BITS3 (PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1) -#define pte_to_pgoff(pte) \ - ((((pte).pte_low >> (PTE_FILE_SHIFT1)) \ - & ((1U << PTE_FILE_BITS1) - 1))) \ - + ((((pte).pte_low >> (PTE_FILE_SHIFT2)) \ - & ((1U << PTE_FILE_BITS2) - 1)) \ - << (PTE_FILE_BITS1)) \ - + ((((pte).pte_low >> (PTE_FILE_SHIFT3)) \ - & ((1U << PTE_FILE_BITS3) - 1)) \ - << (PTE_FILE_BITS1 + PTE_FILE_BITS2)) \ - + ((((pte).pte_low >> (PTE_FILE_SHIFT4))) \ - << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)) - -#define pgoff_to_pte(off) \ - ((pte_t) { .pte_low = \ - ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1) \ - + ((((off) >> PTE_FILE_BITS1) \ - & ((1U << PTE_FILE_BITS2) - 1)) \ - << PTE_FILE_SHIFT2) \ - + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2)) \ - & ((1U << PTE_FILE_BITS3) - 1)) \ - << PTE_FILE_SHIFT3) \ - + ((((off) >> \ - (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))) \ - << PTE_FILE_SHIFT4) \ - + _PAGE_FILE }) +#define PTE_FILE_MASK1 ((1U << PTE_FILE_BITS1) - 1) +#define PTE_FILE_MASK2 ((1U << PTE_FILE_BITS2) - 1) +#define PTE_FILE_MASK3 ((1U << PTE_FILE_BITS3) - 1) + +#define PTE_FILE_LSHIFT2 (PTE_FILE_BITS1) +#define PTE_FILE_LSHIFT3 (PTE_FILE_BITS1 + PTE_FILE_BITS2) +#define PTE_FILE_LSHIFT4 (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3) + +static __always_inline pgoff_t pte_to_pgoff(pte_t pte) +{ + return (pgoff_t) + (pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1, 0) + + pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2, PTE_FILE_LSHIFT2) + + pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, PTE_FILE_MASK3, PTE_FILE_LSHIFT3) + + pte_bitop(pte.pte_low, PTE_FILE_SHIFT4, -1UL, PTE_FILE_LSHIFT4)); +} + +static __always_inline pte_t pgoff_to_pte(pgoff_t off) +{ + return (pte_t){ + .pte_low = + pte_bitop(off, 0, PTE_FILE_MASK1, PTE_FILE_SHIFT1) + + pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2, PTE_FILE_SHIFT2) + + pte_bitop(off, PTE_FILE_LSHIFT3, PTE_FILE_MASK3, PTE_FILE_SHIFT3) + + pte_bitop(off, PTE_FILE_LSHIFT4, -1UL, PTE_FILE_SHIFT4) + + _PAGE_FILE, + }; +} #else /* CONFIG_MEM_SOFT_DIRTY */ @@ -115,22 +125,30 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) #define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) -#define pte_to_pgoff(pte) \ - ((((pte).pte_low >> PTE_FILE_SHIFT1) \ - & ((1U << PTE_FILE_BITS1) - 1)) \ - + ((((pte).pte_low >> PTE_FILE_SHIFT2) \ - & ((1U << PTE_FILE_BITS2) - 1)) << PTE_FILE_BITS1) \ - + (((pte).pte_low >> PTE_FILE_SHIFT3) \ - << (PTE_FILE_BITS1 + PTE_FILE_BITS2))) - -#define pgoff_to_pte(off) \ - ((pte_t) { .pte_low = \ - (((off) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1) \ - + ((((off) >> PTE_FILE_BITS1) & ((1U << PTE_FILE_BITS2) - 1)) \ - << PTE_FILE_SHIFT2) \ - + (((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2)) \ - << PTE_FILE_SHIFT3) \ - + _PAGE_FILE }) +#define PTE_FILE_MASK1 ((1U << PTE_FILE_BITS1) - 1) +#define PTE_FILE_MASK2 ((1U << PTE_FILE_BITS2) - 1) + +#define PTE_FILE_LSHIFT2 (PTE_FILE_BITS1) +#define PTE_FILE_LSHIFT3 (PTE_FILE_BITS1 + PTE_FILE_BITS2) + +static __always_inline pgoff_t pte_to_pgoff(pte_t pte) +{ + return (pgoff_t) + (pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1, 0) + + pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2, PTE_FILE_LSHIFT2) + + pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, -1UL, PTE_FILE_LSHIFT3)); +} + +static __always_inline pte_t pgoff_to_pte(pgoff_t off) +{ + return (pte_t){ + .pte_low = + pte_bitop(off, 0, PTE_FILE_MASK1, PTE_FILE_SHIFT1) + + pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2, PTE_FILE_SHIFT2) + + pte_bitop(off, PTE_FILE_LSHIFT3, -1UL, PTE_FILE_SHIFT3) + + _PAGE_FILE, + }; +} #endif /* CONFIG_MEM_SOFT_DIRTY */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 3d199945870..5ad38ad0789 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -445,16 +445,33 @@ static inline int pte_same(pte_t a, pte_t b) return a.pte == b.pte; } +static inline int pteval_present(pteval_t pteval) +{ + /* + * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this + * way clearly states that the intent is that protnone and numa + * hinting ptes are considered present for the purposes of + * pagetable operations like zapping, protection changes, gup etc. + */ + return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA); +} + static inline int pte_present(pte_t a) { - return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE | - _PAGE_NUMA); + return pteval_present(pte_flags(a)); } #define pte_accessible pte_accessible -static inline int pte_accessible(pte_t a) +static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { - return pte_flags(a) & _PAGE_PRESENT; + if (pte_flags(a) & _PAGE_PRESENT) + return true; + + if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) && + mm_tlb_flush_pending(mm)) + return true; + + return false; } static inline int pte_hidden(pte_t pte) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 2d883440cb9..c883bf72639 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -58,7 +58,7 @@ typedef struct { pteval_t pte; } pte_t; #define VMALLOC_START _AC(0xffffc90000000000, UL) #define VMALLOC_END _AC(0xffffe8ffffffffff, UL) #define VMEMMAP_START _AC(0xffffea0000000000, UL) -#define MODULES_VADDR _AC(0xffffffffa0000000, UL) +#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) #define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0ecac257fb2..1aa9ccd4322 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -121,7 +121,8 @@ /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ - _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY) + _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ + _PAGE_SOFT_DIRTY) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) @@ -382,7 +383,8 @@ static inline void update_page_count(int level, unsigned long pages) { } */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern phys_addr_t slow_virt_to_phys(void *__address); - +extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, + unsigned numpages, unsigned long page_flags); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_DEFS_H */ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 8729723636f..c8b051933b1 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -8,6 +8,12 @@ DECLARE_PER_CPU(int, __preempt_count); /* + * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such + * that a decrement hitting 0 means we can and should reschedule. + */ +#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) + +/* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ @@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val) __this_cpu_add_4(__preempt_count, -val); } +/* + * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ static __always_inline bool __preempt_count_dec_and_test(void) { GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e"); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7b034a4057f..fdedd38fd0f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -27,7 +27,6 @@ struct mm_struct; #include <linux/cache.h> #include <linux/threads.h> #include <linux/math64.h> -#include <linux/init.h> #include <linux/err.h> #include <linux/irqflags.h> @@ -72,6 +71,7 @@ extern u16 __read_mostly tlb_lli_4m[NR_INFO]; extern u16 __read_mostly tlb_lld_4k[NR_INFO]; extern u16 __read_mostly tlb_lld_2m[NR_INFO]; extern u16 __read_mostly tlb_lld_4m[NR_INFO]; +extern u16 __read_mostly tlb_lld_1g[NR_INFO]; extern s8 __read_mostly tlb_flushall_shift; /* @@ -370,6 +370,20 @@ struct ymmh_struct { u32 ymmh_space[64]; }; +/* We don't support LWP yet: */ +struct lwp_struct { + u8 reserved[128]; +}; + +struct bndregs_struct { + u64 bndregs[8]; +} __packed; + +struct bndcsr_struct { + u64 cfg_reg_u; + u64 status_reg; +} __packed; + struct xsave_hdr_struct { u64 xstate_bv; u64 reserved1[2]; @@ -380,6 +394,9 @@ struct xsave_struct { struct i387_fxsave_struct i387; struct xsave_hdr_struct xsave_hdr; struct ymmh_struct ymmh; + struct lwp_struct lwp; + struct bndregs_struct bndregs; + struct bndcsr_struct bndcsr; /* new processor state extensions will go here */ } __attribute__ ((packed, aligned (64))); @@ -700,29 +717,6 @@ static inline void sync_core(void) #endif } -static inline void __monitor(const void *eax, unsigned long ecx, - unsigned long edx) -{ - /* "monitor %eax, %ecx, %edx;" */ - asm volatile(".byte 0x0f, 0x01, 0xc8;" - :: "a" (eax), "c" (ecx), "d"(edx)); -} - -static inline void __mwait(unsigned long eax, unsigned long ecx) -{ - /* "mwait %eax, %ecx;" */ - asm volatile(".byte 0x0f, 0x01, 0xc9;" - :: "a" (eax), "c" (ecx)); -} - -static inline void __sti_mwait(unsigned long eax, unsigned long ecx) -{ - trace_hardirqs_on(); - /* "mwait %eax, %ecx;" */ - asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" - :: "a" (eax), "c" (ecx)); -} - extern void select_idle_routine(const struct cpuinfo_x86 *c); extern void init_amd_e400_c1e_mask(void); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 942a08623a1..14fd6fd75a1 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -60,7 +60,6 @@ struct pt_regs { #endif /* !__i386__ */ -#include <linux/init.h> #ifdef CONFIG_PARAVIRT #include <asm/paravirt_types.h> #endif diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 59bcf4e2241..d62c9f809bc 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -3,7 +3,6 @@ #include <uapi/asm/setup.h> - #define COMMAND_LINE_SIZE 2048 #include <linux/linkage.h> @@ -29,6 +28,8 @@ #include <asm/bootparam.h> #include <asm/x86_init.h> +extern u64 relocated_ramdisk; + /* Interrupt control for vSMPowered x86_64 systems */ #ifdef CONFIG_X86_64 void vsmp_init(void); diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4137890e88e..8cd27e08e23 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -2,7 +2,6 @@ #define _ASM_X86_SMP_H #ifndef __ASSEMBLY__ #include <linux/cpumask.h> -#include <linux/init.h> #include <asm/percpu.h> /* diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 3ba3de457d0..e1940c06ed0 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -163,9 +163,11 @@ struct thread_info { */ #ifndef __ASSEMBLY__ - -/* how to get the current stack pointer from C */ -register unsigned long current_stack_pointer asm("esp") __used; +#define current_stack_pointer ({ \ + unsigned long sp; \ + asm("mov %%esp,%0" : "=g" (sp)); \ + sp; \ +}) /* how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 34baa0eb5d0..a04eabd43d0 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -1,9 +1,9 @@ #ifndef _ASM_X86_TIMER_H #define _ASM_X86_TIMER_H -#include <linux/init.h> #include <linux/pm.h> #include <linux/percpu.h> #include <linux/interrupt.h> +#include <linux/math64.h> #define TICK_SIZE (tick_nsec / 1000) @@ -12,68 +12,26 @@ extern int recalibrate_cpu_khz(void); extern int no_timer_check; -/* Accelerators for sched_clock() - * convert from cycles(64bits) => nanoseconds (64bits) - * basic equation: - * ns = cycles / (freq / ns_per_sec) - * ns = cycles * (ns_per_sec / freq) - * ns = cycles * (10^9 / (cpu_khz * 10^3)) - * ns = cycles * (10^6 / cpu_khz) +/* + * We use the full linear equation: f(x) = a + b*x, in order to allow + * a continuous function in the face of dynamic freq changes. * - * Then we use scaling math (suggested by george@mvista.com) to get: - * ns = cycles * (10^6 * SC / cpu_khz) / SC - * ns = cycles * cyc2ns_scale / SC + * Continuity means that when our frequency changes our slope (b); we want to + * ensure that: f(t) == f'(t), which gives: a + b*t == a' + b'*t. * - * And since SC is a constant power of two, we can convert the div - * into a shift. + * Without an offset (a) the above would not be possible. * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. - * (mathieu.desnoyers@polymtl.ca) - * - * -johnstul@us.ibm.com "math is hard, lets go shopping!" - * - * In: - * - * ns = cycles * cyc2ns_scale / SC - * - * Although we may still have enough bits to store the value of ns, - * in some cases, we may not have enough bits to store cycles * cyc2ns_scale, - * leading to an incorrect result. - * - * To avoid this, we can decompose 'cycles' into quotient and remainder - * of division by SC. Then, - * - * ns = (quot * SC + rem) * cyc2ns_scale / SC - * = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC - * - * - sqazi@google.com + * See the comment near cycles_2_ns() for details on how we compute (b). */ - -DECLARE_PER_CPU(unsigned long, cyc2ns); -DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); - -#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ - -static inline unsigned long long __cycles_2_ns(unsigned long long cyc) -{ - int cpu = smp_processor_id(); - unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), - (1UL << CYC2NS_SCALE_FACTOR)); - return ns; -} - -static inline unsigned long long cycles_2_ns(unsigned long long cyc) -{ - unsigned long long ns; - unsigned long flags; - - local_irq_save(flags); - ns = __cycles_2_ns(cyc); - local_irq_restore(flags); - - return ns; -} +struct cyc2ns_data { + u32 cyc2ns_mul; + u32 cyc2ns_shift; + u64 cyc2ns_offset; + u32 __count; + /* u32 hole */ +}; /* 24 bytes -- do not grow */ + +extern struct cyc2ns_data *cyc2ns_read_begin(void); +extern void cyc2ns_read_end(struct cyc2ns_data *); #endif /* _ASM_X86_TIMER_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index e6d90babc24..04905bfc508 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr) */ static inline void __flush_tlb_up(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); } static inline void flush_tlb_all(void) { - count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb_all(); } diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 235be70d5bb..57ae63cd6ee 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -65,4 +65,7 @@ extern int notsc_setup(char *); extern void tsc_save_sched_clock_state(void); extern void tsc_restore_sched_clock_state(void); +/* MSR based TSC calibration for Intel Atom SoC platforms */ +int try_msr_calibrate_tsc(unsigned long *fast_calibrate); + #endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 8ec57c07b12..0d592e0a5b8 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -40,22 +40,30 @@ /* * Test whether a block of memory is a valid user space address. * Returns 0 if the range is valid, nonzero otherwise. - * - * This is equivalent to the following test: - * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64) - * - * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry... */ +static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit) +{ + /* + * If we have used "sizeof()" for the size, + * we know it won't overflow the limit (but + * it might overflow the 'addr', so it's + * important to subtract the size from the + * limit, not add it to the address). + */ + if (__builtin_constant_p(size)) + return addr > limit - size; + + /* Arbitrary sizes? Be careful about overflow */ + addr += size; + if (addr < size) + return true; + return addr > limit; +} #define __range_not_ok(addr, size, limit) \ ({ \ - unsigned long flag, roksum; \ __chk_user_ptr(addr); \ - asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \ - : "=&r" (flag), "=r" (roksum) \ - : "1" (addr), "g" ((long)(size)), \ - "rm" (limit)); \ - flag; \ + __chk_range_not_ok((unsigned long __force)(addr), size, limit); \ }) /** @@ -78,7 +86,7 @@ * this function, memory access functions may still return -EFAULT. */ #define access_ok(type, addr, size) \ - (likely(__range_not_ok(addr, size, user_addr_max()) == 0)) + likely(!__range_not_ok(addr, size, user_addr_max())) /* * The exception table consists of pairs of addresses relative to the @@ -525,6 +533,98 @@ extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); +extern void __cmpxchg_wrong_size(void) + __compiletime_error("Bad argument size for cmpxchg"); + +#define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size) \ +({ \ + int __ret = 0; \ + __typeof__(ptr) __uval = (uval); \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case 1: \ + { \ + asm volatile("\t" ASM_STAC "\n" \ + "1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n" \ + "2:\t" ASM_CLAC "\n" \ + "\t.section .fixup, \"ax\"\n" \ + "3:\tmov %3, %0\n" \ + "\tjmp 2b\n" \ + "\t.previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ + : "i" (-EFAULT), "q" (__new), "1" (__old) \ + : "memory" \ + ); \ + break; \ + } \ + case 2: \ + { \ + asm volatile("\t" ASM_STAC "\n" \ + "1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n" \ + "2:\t" ASM_CLAC "\n" \ + "\t.section .fixup, \"ax\"\n" \ + "3:\tmov %3, %0\n" \ + "\tjmp 2b\n" \ + "\t.previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ + : "i" (-EFAULT), "r" (__new), "1" (__old) \ + : "memory" \ + ); \ + break; \ + } \ + case 4: \ + { \ + asm volatile("\t" ASM_STAC "\n" \ + "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" \ + "2:\t" ASM_CLAC "\n" \ + "\t.section .fixup, \"ax\"\n" \ + "3:\tmov %3, %0\n" \ + "\tjmp 2b\n" \ + "\t.previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ + : "i" (-EFAULT), "r" (__new), "1" (__old) \ + : "memory" \ + ); \ + break; \ + } \ + case 8: \ + { \ + if (!IS_ENABLED(CONFIG_X86_64)) \ + __cmpxchg_wrong_size(); \ + \ + asm volatile("\t" ASM_STAC "\n" \ + "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" \ + "2:\t" ASM_CLAC "\n" \ + "\t.section .fixup, \"ax\"\n" \ + "3:\tmov %3, %0\n" \ + "\tjmp 2b\n" \ + "\t.previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ + : "i" (-EFAULT), "r" (__new), "1" (__old) \ + : "memory" \ + ); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + *__uval = __old; \ + __ret; \ +}) + +#define user_atomic_cmpxchg_inatomic(uval, ptr, old, new) \ +({ \ + access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr))) ? \ + __user_atomic_cmpxchg_inatomic((uval), (ptr), \ + (old), (new), sizeof(*(ptr))) : \ + -EFAULT; \ +}) + /* * movsl can be slow when source and dest are not both 8-byte aligned */ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 190413d0de5..12a26b979bf 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -204,13 +204,13 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size) static __must_check __always_inline int __copy_from_user_inatomic(void *dst, const void __user *src, unsigned size) { - return __copy_from_user_nocheck(dst, (__force const void *)src, size); + return __copy_from_user_nocheck(dst, src, size); } static __must_check __always_inline int __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) { - return __copy_to_user_nocheck((__force void *)dst, src, size); + return __copy_to_user_nocheck(dst, src, size); } extern long __copy_user_nocache(void *dst, const void __user *src, diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 6b964a0b86d..062921ef34e 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -12,7 +12,6 @@ extern enum uv_system_type get_uv_system_type(void); extern int is_uv_system(void); extern void uv_cpu_init(void); extern void uv_nmi_init(void); -extern void uv_register_nmi_notifier(void); extern void uv_system_init(void); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, @@ -26,7 +25,6 @@ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } static inline int is_uv_system(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline void uv_register_nmi_notifier(void) { } static inline const struct cpumask * uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start, unsigned long end, unsigned int cpu) diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 966502d4682..2067264fb7f 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -100,6 +100,7 @@ #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f #define VMX_MISC_SAVE_EFER_LMA 0x00000020 +#define VMX_MISC_ACTIVITY_HLT 0x00000040 /* VMCS Encodings */ enum vmcs_field { diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 0f1be11e43d..e45e4da96bf 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -181,7 +181,7 @@ struct x86_msi_ops { u8 hpet_id); void (*teardown_msi_irq)(unsigned int irq); void (*teardown_msi_irqs)(struct pci_dev *dev); - void (*restore_msi_irqs)(struct pci_dev *dev, int irq); + void (*restore_msi_irqs)(struct pci_dev *dev); int (*setup_hpet_msi)(unsigned int irq, unsigned int id); u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag); u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag); diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index b913915e8e6..3e276eb23d1 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -167,7 +167,12 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) */ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) { - unsigned long pfn = mfn_to_pfn(mfn); + unsigned long pfn; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return mfn; + + pfn = mfn_to_pfn(mfn); if (get_phys_to_machine(pfn) != mfn) return -1; /* force !pfn_valid() */ return pfn; @@ -222,5 +227,6 @@ void make_lowmem_page_readonly(void *vaddr); void make_lowmem_page_readwrite(void *vaddr); #define xen_remap(cookie, size) ioremap((cookie), (size)); +#define xen_unmap(cookie) iounmap((cookie)) #endif /* _ASM_X86_XEN_PAGE_H */ diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 0415cdabb5a..554738963b2 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -9,6 +9,8 @@ #define XSTATE_FP 0x1 #define XSTATE_SSE 0x2 #define XSTATE_YMM 0x4 +#define XSTATE_BNDREGS 0x8 +#define XSTATE_BNDCSR 0x10 #define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) @@ -20,10 +22,14 @@ #define XSAVE_YMM_SIZE 256 #define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) -/* - * These are the features that the OS can handle currently. - */ -#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) +/* Supported features which support lazy state saving */ +#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) + +/* Supported features which require eager state saving */ +#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) + +/* All currently supported features */ +#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " |