diff options
Diffstat (limited to 'arch/x86')
85 files changed, 770 insertions, 573 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 73f7fe8fd4d..bc2fbadff9f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1802,6 +1802,17 @@ config DMAR and include PCI device scope covered by these DMA remapping devices. +config DMAR_DEFAULT_ON + def_bool y + prompt "Enable DMA Remapping Devices by default" + depends on DMAR + help + Selecting this option will enable a DMAR device at boot time if + one is found. If this option is not selected, DMAR support can + be enabled by passing intel_iommu=on to the kernel. It is + recommended you say N here while the DMAR code remains + experimental. + config DMAR_GFX_WA def_bool y prompt "Support for Graphics workaround" diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 8078955845a..c98d52e8296 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -167,9 +167,9 @@ config MK7 config MK8 bool "Opteron/Athlon64/Hammer/K8" help - Select this for an AMD Opteron or Athlon64 Hammer-family processor. Enables - use of some extended instructions, and passes appropriate optimization - flags to GCC. + Select this for an AMD Opteron or Athlon64 Hammer-family processor. + Enables use of some extended instructions, and passes appropriate + optimization flags to GCC. config MCRUSOE bool "Crusoe" @@ -256,9 +256,11 @@ config MPSC config MCORE2 bool "Core 2/newer Xeon" help - Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and 53xx) - CPUs. You can distinguish newer from older Xeons by the CPU family - in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo) + + Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and + 53xx) CPUs. You can distinguish newer from older Xeons by the CPU + family in /proc/cpuinfo. Newer ones have 6 and older ones 15 + (not a typo) config GENERIC_CPU bool "Generic-x86-64" @@ -320,14 +322,14 @@ config X86_PPRO_FENCE bool "PentiumPro memory ordering errata workaround" depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1 help - Old PentiumPro multiprocessor systems had errata that could cause memory - operations to violate the x86 ordering standard in rare cases. Enabling this - option will attempt to work around some (but not all) occurances of - this problem, at the cost of much heavier spinlock and memory barrier - operations. + Old PentiumPro multiprocessor systems had errata that could cause + memory operations to violate the x86 ordering standard in rare cases. + Enabling this option will attempt to work around some (but not all) + occurances of this problem, at the cost of much heavier spinlock and + memory barrier operations. - If unsure, say n here. Even distro kernels should think twice before enabling - this: there are few systems, and an unlikely bug. + If unsure, say n here. Even distro kernels should think twice before + enabling this: there are few systems, and an unlikely bug. config X86_F00F_BUG def_bool y diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 10d6cc3fd05..e1983fa025d 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -174,28 +174,8 @@ config IOMMU_LEAK Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. -config MMIOTRACE - bool "Memory mapped IO tracing" - depends on DEBUG_KERNEL && PCI - select TRACING - help - Mmiotrace traces Memory Mapped I/O access and is meant for - debugging and reverse engineering. It is called from the ioremap - implementation and works via page faults. Tracing is disabled by - default and can be enabled at run-time. - - See Documentation/tracers/mmiotrace.txt. - If you are not helping to develop drivers, say N. - -config MMIOTRACE_TEST - tristate "Test module for mmiotrace" - depends on MMIOTRACE && m - help - This is a dumb module for testing mmiotrace. It is very dangerous - as it will write garbage to IO memory starting at a given address. - However, it should be safe to use on e.g. unused portion of VRAM. - - Say N, unless you absolutely know what you are doing. +config HAVE_MMIOTRACE_SUPPORT + def_bool y # # IO delay types: diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h index 37822206083..3c601f8224b 100644 --- a/arch/x86/include/asm/a.out-core.h +++ b/arch/x86/include/asm/a.out-core.h @@ -23,8 +23,6 @@ */ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) { - u16 gs; - /* changed the size calculations - should hopefully work better. lbt */ dump->magic = CMAGIC; dump->start_code = 0; @@ -57,7 +55,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) dump->regs.ds = (u16)regs->ds; dump->regs.es = (u16)regs->es; dump->regs.fs = (u16)regs->fs; - savesegment(gs, gs); + savesegment(gs, dump->regs.gs); dump->regs.orig_ax = regs->orig_ax; dump->regs.ip = regs->ip; dump->regs.cs = (u16)regs->cs; diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ea408dcba51..7301e60dc4a 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -93,6 +93,7 @@ #define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ +#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index ca5ffb2856b..edc90f23e70 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -37,8 +37,6 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #else /* !CONFIG_X86_32 */ -#define MAX_EFI_IO_PAGES 100 - extern u64 efi_call0(void *fp); extern u64 efi_call1(void *fp, u64 arg1); extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); diff --git a/arch/x86/include/asm/fixmap_64.h b/arch/x86/include/asm/fixmap_64.h index 00a30ab9b1a..8be740977db 100644 --- a/arch/x86/include/asm/fixmap_64.h +++ b/arch/x86/include/asm/fixmap_64.h @@ -16,7 +16,6 @@ #include <asm/apicdef.h> #include <asm/page.h> #include <asm/vsyscall.h> -#include <asm/efi.h> /* * Here we define all the compile-time 'special' virtual @@ -43,9 +42,6 @@ enum fixed_addresses { FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ FIX_IO_APIC_BASE_0, FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, - FIX_EFI_IO_MAP_LAST_PAGE, - FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE - + MAX_EFI_IO_PAGES - 1, #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 48f0004db8c..71c9e518398 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -172,7 +172,13 @@ static inline void __save_init_fpu(struct task_struct *tsk) #else /* CONFIG_X86_32 */ -extern void finit(void); +#ifdef CONFIG_MATH_EMULATION +extern void finit_task(struct task_struct *tsk); +#else +static inline void finit_task(struct task_struct *tsk) +{ +} +#endif static inline void tolerant_fwait(void) { diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h index c1f06289b14..86af26091d6 100644 --- a/arch/x86/include/asm/iomap.h +++ b/arch/x86/include/asm/iomap.h @@ -23,6 +23,9 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> +int +is_io_mapping_possible(resource_size_t base, unsigned long size); + void * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index d2e3bf3608a..886c9402ec4 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -9,6 +9,13 @@ #include <linux/types.h> #include <linux/ioctl.h> +/* Select x86 specific features in <linux/kvm.h> */ +#define __KVM_HAVE_PIT +#define __KVM_HAVE_IOAPIC +#define __KVM_HAVE_DEVICE_ASSIGNMENT +#define __KVM_HAVE_MSI +#define __KVM_HAVE_USER_NMI + /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h index 5a65b107ad5..031f6266f42 100644 --- a/arch/x86/include/asm/math_emu.h +++ b/arch/x86/include/asm/math_emu.h @@ -1,31 +1,18 @@ #ifndef _ASM_X86_MATH_EMU_H #define _ASM_X86_MATH_EMU_H +#include <asm/ptrace.h> +#include <asm/vm86.h> + /* This structure matches the layout of the data saved to the stack following a device-not-present interrupt, part of it saved automatically by the 80386/80486. */ -struct info { +struct math_emu_info { long ___orig_eip; - long ___ebx; - long ___ecx; - long ___edx; - long ___esi; - long ___edi; - long ___ebp; - long ___eax; - long ___ds; - long ___es; - long ___fs; - long ___orig_eax; - long ___eip; - long ___cs; - long ___eflags; - long ___esp; - long ___ss; - long ___vm86_es; /* This and the following only in vm86 mode */ - long ___vm86_ds; - long ___vm86_fs; - long ___vm86_gs; + union { + struct pt_regs *regs; + struct kernel_vm86_regs *vm86; + }; }; #endif /* _ASM_X86_MATH_EMU_H */ diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 07f1af494ca..105fb90a063 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -32,8 +32,6 @@ static inline void get_memcfg_numa(void) get_memcfg_numa_flat(); } -extern int early_pfn_to_nid(unsigned long pfn); - extern void resume_map_numa_kva(pgd_t *pgd); #else /* !CONFIG_NUMA */ diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index a5b3817d4b9..a29f48c2a32 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -40,8 +40,6 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr) #define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ NODE_DATA(nid)->node_spanned_pages) -extern int early_pfn_to_nid(unsigned long pfn); - #ifdef CONFIG_NUMA_EMU #define FAKE_NODE_MIN_SIZE (64 * 1024 * 1024) #define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 62d14ce3cd0..bd22f2a3713 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -60,6 +60,7 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi); extern void mp_config_acpi_legacy_irqs(void); extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low); +extern int acpi_probe_gsi(void); #ifdef CONFIG_X86_IO_APIC extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin, u32 gsi, int triggering, int polarity); @@ -71,6 +72,11 @@ mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin, return 0; } #endif +#else /* !CONFIG_ACPI: */ +static inline int acpi_probe_gsi(void) +{ + return 0; +} #endif /* CONFIG_ACPI */ #define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_APICS) diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index e9873a2e869..776579119a0 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -57,7 +57,6 @@ typedef struct { pgdval_t pgd; } pgd_t; typedef struct { pgprotval_t pgprot; } pgprot_t; extern int page_is_ram(unsigned long pagenr); -extern int pagerange_is_ram(unsigned long start, unsigned long end); extern int devmem_is_allowed(unsigned long pagenr); extern void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index ba3e2ff6aed..e299287e8e3 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -1352,14 +1352,7 @@ static inline void arch_leave_lazy_cpu_mode(void) PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave); } -static inline void arch_flush_lazy_cpu_mode(void) -{ - if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)) { - arch_leave_lazy_cpu_mode(); - arch_enter_lazy_cpu_mode(); - } -} - +void arch_flush_lazy_cpu_mode(void); #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE static inline void arch_enter_lazy_mmu_mode(void) @@ -1372,13 +1365,7 @@ static inline void arch_leave_lazy_mmu_mode(void) PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); } -static inline void arch_flush_lazy_mmu_mode(void) -{ - if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU)) { - arch_leave_lazy_mmu_mode(); - arch_enter_lazy_mmu_mode(); - } -} +void arch_flush_lazy_mmu_mode(void); static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, unsigned long phys, pgprot_t flags) @@ -1402,6 +1389,7 @@ static inline int __raw_spin_is_contended(struct raw_spinlock *lock) { return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock); } +#define __raw_spin_is_contended __raw_spin_is_contended static __always_inline void __raw_spin_lock(struct raw_spinlock *lock) { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 06bbcbd66e9..4f5af8447d5 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -302,16 +302,30 @@ static inline pte_t pte_mkspecial(pte_t pte) extern pteval_t __supported_pte_mask; +/* + * Mask out unsupported bits in a present pgprot. Non-present pgprots + * can use those bits for other purposes, so leave them be. + */ +static inline pgprotval_t massage_pgprot(pgprot_t pgprot) +{ + pgprotval_t protval = pgprot_val(pgprot); + + if (protval & _PAGE_PRESENT) + protval &= __supported_pte_mask; + + return protval; +} + static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) | - pgprot_val(pgprot)) & __supported_pte_mask); + return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) | + massage_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) | - pgprot_val(pgprot)) & __supported_pte_mask); + return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) | + massage_pgprot(pgprot)); } static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) @@ -323,7 +337,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * the newprot (if present): */ val &= _PAGE_CHG_MASK; - val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask; + val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK; return __pte(val); } @@ -339,7 +353,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK) -#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask) +#define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline int is_new_memtype_allowed(unsigned long flags, unsigned long new_flags) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 091cd8855f2..3bfd5235a9e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -353,7 +353,7 @@ struct i387_soft_struct { u8 no_update; u8 rm; u8 alimit; - struct info *info; + struct math_emu_info *info; u32 entry_eip; }; diff --git a/arch/x86/include/asm/seccomp_32.h b/arch/x86/include/asm/seccomp_32.h index a6ad87b352c..b811d6f5780 100644 --- a/arch/x86/include/asm/seccomp_32.h +++ b/arch/x86/include/asm/seccomp_32.h @@ -1,12 +1,6 @@ #ifndef _ASM_X86_SECCOMP_32_H #define _ASM_X86_SECCOMP_32_H -#include <linux/thread_info.h> - -#ifdef TIF_32BIT -#error "unexpected TIF_32BIT on i386" -#endif - #include <linux/unistd.h> #define __NR_seccomp_read __NR_read diff --git a/arch/x86/include/asm/seccomp_64.h b/arch/x86/include/asm/seccomp_64.h index 4171bb794e9..84ec1bd161a 100644 --- a/arch/x86/include/asm/seccomp_64.h +++ b/arch/x86/include/asm/seccomp_64.h @@ -1,14 +1,6 @@ #ifndef _ASM_X86_SECCOMP_64_H #define _ASM_X86_SECCOMP_64_H -#include <linux/thread_info.h> - -#ifdef TIF_32BIT -#error "unexpected TIF_32BIT on x86_64" -#else -#define TIF_32BIT TIF_IA32 -#endif - #include <linux/unistd.h> #include <asm/ia32_unistd.h> diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index d17c91981da..8247e94ac6b 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -245,6 +245,7 @@ static inline int __raw_spin_is_contended(raw_spinlock_t *lock) { return __ticket_spin_is_contended(lock); } +#define __raw_spin_is_contended __raw_spin_is_contended static __always_inline void __raw_spin_lock(raw_spinlock_t *lock) { diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 2ee0a3bceed..cf3bb053da0 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -41,7 +41,7 @@ dotraplinkage void do_int3(struct pt_regs *, long); dotraplinkage void do_overflow(struct pt_regs *, long); dotraplinkage void do_bounds(struct pt_regs *, long); dotraplinkage void do_invalid_op(struct pt_regs *, long); -dotraplinkage void do_device_not_available(struct pt_regs *, long); +dotraplinkage void do_device_not_available(struct pt_regs); dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long); dotraplinkage void do_invalid_TSS(struct pt_regs *, long); dotraplinkage void do_segment_not_present(struct pt_regs *, long); @@ -77,7 +77,7 @@ extern int panic_on_unrecovered_nmi; extern int kstack_depth_to_print; void math_error(void __user *); -asmlinkage void math_emulate(long); +void math_emulate(struct math_emu_info *); #ifdef CONFIG_X86_32 unsigned long patch_espfix_desc(unsigned long, unsigned long); #else diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 7ef617ef1df..4bd990ee43d 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -137,7 +137,7 @@ static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) pte_t pte; pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) | - (pgprot_val(pgprot) & __supported_pte_mask); + massage_pgprot(pgprot); return pte; } diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index d37593c2f43..7678f10c456 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -973,6 +973,29 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) nr_ioapics++; } +int __init acpi_probe_gsi(void) +{ + int idx; + int gsi; + int max_gsi = 0; + + if (acpi_disabled) + return 0; + + if (!acpi_ioapic) + return 0; + + max_gsi = 0; + for (idx = 0; idx < nr_ioapics; idx++) { + gsi = mp_ioapic_routing[idx].gsi_end; + + if (gsi > max_gsi) + max_gsi = gsi; + } + + return max_gsi + 1; +} + static void assign_to_mp_irq(struct mp_config_intsrc *m, struct mp_config_intsrc *mp_irq) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 707c1f6f95f..a60c1f3bcb8 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -156,11 +156,11 @@ static int __init acpi_sleep_setup(char *str) #ifdef CONFIG_HIBERNATION if (strncmp(str, "s4_nohwsig", 10) == 0) acpi_no_s4_hw_signature(); + if (strncmp(str, "s4_nonvs", 8) == 0) + acpi_s4_no_nvs(); #endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); - if (strncmp(str, "s4_nonvs", 8) == 0) - acpi_s4_no_nvs(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index bcc293423a7..96258d9dc97 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -13,7 +13,6 @@ * Hooray, we are in Long 64-bit mode (but still running in low memory) */ ENTRY(wakeup_long64) -wakeup_long64: movq saved_magic, %rax movq $0x123456789abcdef0, %rdx cmpq %rdx, %rax @@ -34,16 +33,12 @@ wakeup_long64: movq saved_rip, %rax jmp *%rax +ENDPROC(wakeup_long64) bogus_64_magic: jmp bogus_64_magic - .align 2 - .p2align 4,,15 -.globl do_suspend_lowlevel - .type do_suspend_lowlevel,@function -do_suspend_lowlevel: -.LFB5: +ENTRY(do_suspend_lowlevel) subq $8, %rsp xorl %eax, %eax call save_processor_state @@ -67,7 +62,7 @@ do_suspend_lowlevel: pushfq popq pt_regs_flags(%rax) - movq $.L97, saved_rip(%rip) + movq $resume_point, saved_rip(%rip) movq %rsp, saved_rsp movq %rbp, saved_rbp @@ -78,14 +73,12 @@ do_suspend_lowlevel: addq $8, %rsp movl $3, %edi xorl %eax, %eax - jmp acpi_enter_sleep_state -.L97: - .p2align 4,,7 -.L99: - .align 4 - movl $24, %eax - movw %ax, %ds + call acpi_enter_sleep_state + /* in case something went wrong, restore the machine status and go on */ + jmp resume_point + .align 4 +resume_point: /* We don't restore %rax, it must be 0 anyway */ movq $saved_context, %rax movq saved_context_cr4(%rax), %rbx @@ -117,12 +110,9 @@ do_suspend_lowlevel: xorl %eax, %eax addq $8, %rsp jmp restore_processor_state -.LFE5: -.Lfe5: - .size do_suspend_lowlevel, .Lfe5-do_suspend_lowlevel - +ENDPROC(do_suspend_lowlevel) + .data -ALIGN ENTRY(saved_rbp) .quad 0 ENTRY(saved_rsi) .quad 0 ENTRY(saved_rdi) .quad 0 diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c index 115449f869e..570f36e44e5 100644 --- a/arch/x86/kernel/apic.c +++ b/arch/x86/kernel/apic.c @@ -862,7 +862,7 @@ void clear_local_APIC(void) } /* lets not touch this if we didn't frob it */ -#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL) +#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL) if (maxlvt >= 5) { v = apic_read(APIC_LVTTHMR); apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 98807bb095a..266ec6c18b6 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1192,6 +1192,7 @@ static int suspend(int vetoable) device_suspend(PMSG_SUSPEND); local_irq_disable(); device_power_down(PMSG_SUSPEND); + sysdev_suspend(PMSG_SUSPEND); local_irq_enable(); @@ -1208,6 +1209,7 @@ static int suspend(int vetoable) if (err != APM_SUCCESS) apm_error("suspend", err); err = (err == APM_SUCCESS) ? 0 : -EIO; + sysdev_resume(); device_power_up(PMSG_RESUME); local_irq_enable(); device_resume(PMSG_RESUME); @@ -1228,6 +1230,7 @@ static void standby(void) local_irq_disable(); device_power_down(PMSG_SUSPEND); + sysdev_suspend(PMSG_SUSPEND); local_irq_enable(); err = set_system_power_state(APM_STATE_STANDBY); @@ -1235,6 +1238,7 @@ static void standby(void) apm_error("standby", err); local_irq_disable(); + sysdev_resume(); device_power_up(PMSG_RESUME); local_irq_enable(); } diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig index efae3b22a0f..65792c2cc46 100644 --- a/arch/x86/kernel/cpu/cpufreq/Kconfig +++ b/arch/x86/kernel/cpu/cpufreq/Kconfig @@ -245,17 +245,6 @@ config X86_E_POWERSAVER comment "shared options" -config X86_ACPI_CPUFREQ_PROC_INTF - bool "/proc/acpi/processor/../performance interface (deprecated)" - depends on PROC_FS - depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI - help - This enables the deprecated /proc/acpi/processor/../performance - interface. While it is helpful for debugging, the generic, - cross-architecture cpufreq interfaces should be used. - - If in doubt, say N. - config X86_SPEEDSTEP_LIB tristate default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD) diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index b585e04cbc9..3178c3acd97 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -277,7 +277,6 @@ static struct cpufreq_driver p4clockmod_driver = { .name = "p4-clockmod", .owner = THIS_MODULE, .attr = p4clockmod_attr, - .hide_interface = 1, }; diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 5c28b37dea1..6428aa17b40 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -939,10 +939,25 @@ static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) free_cpumask_var(data->acpi_data.shared_cpu_map); } +static int get_transition_latency(struct powernow_k8_data *data) +{ + int max_latency = 0; + int i; + for (i = 0; i < data->acpi_data.state_count; i++) { + int cur_latency = data->acpi_data.states[i].transition_latency + + data->acpi_data.states[i].bus_master_latency; + if (cur_latency > max_latency) + max_latency = cur_latency; + } + /* value in usecs, needs to be in nanoseconds */ + return 1000 * max_latency; +} + #else static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; } static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; } static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; } +static int get_transition_latency(struct powernow_k8_data *data) { return 0; } #endif /* CONFIG_X86_POWERNOW_K8_ACPI */ /* Take a frequency, and issue the fid/vid transition command */ @@ -1142,8 +1157,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) data->cpu = pol->cpu; data->currpstate = HW_PSTATE_INVALID; - rc = powernow_k8_cpu_init_acpi(data); - if (rc) { + if (powernow_k8_cpu_init_acpi(data)) { /* * Use the PSB BIOS structure. This is only availabe on * an UP version, and is deprecated by AMD. @@ -1161,19 +1175,28 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) "ACPI maintainers and complain to your BIOS " "vendor.\n"); #endif - goto err_out; + kfree(data); + return -ENODEV; } if (pol->cpu != 0) { printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for " "CPU other than CPU0. Complain to your BIOS " "vendor.\n"); - goto err_out; + kfree(data); + return -ENODEV; } rc = find_psb_table(data); if (rc) { - goto err_out; + kfree(data); + return -ENODEV; } - } + /* Take a crude guess here. + * That guess was in microseconds, so multiply with 1000 */ + pol->cpuinfo.transition_latency = ( + ((data->rvo + 8) * data->vstable * VST_UNITS_20US) + + ((1 << data->irt) * 30)) * 1000; + } else /* ACPI _PSS objects available */ + pol->cpuinfo.transition_latency = get_transition_latency(data); /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; @@ -1204,11 +1227,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu)); data->available_cores = pol->cpus; - /* Take a crude guess here. - * That guess was in microseconds, so multiply with 1000 */ - pol->cpuinfo.transition_latency = (((data->rvo + 8) * data->vstable * VST_UNITS_20US) - + (3 * (1 << data->irt) * 10)) * 1000; - if (cpu_family == CPU_HW_PSTATE) pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); else diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 430e5c38a54..24ff26a38ad 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -291,6 +291,9 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) ds_init_intel(c); } + if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) + set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR); + #ifdef CONFIG_X86_64 if (c->x86 == 15) c->x86_cache_alignment = c->x86_clflush_size * 2; diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 1c838032fd3..fe79985ce0f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -295,11 +295,11 @@ void do_machine_check(struct pt_regs * regs, long error_code) * If we know that the error was in user space, send a * SIGBUS. Otherwise, panic if tolerance is low. * - * do_exit() takes an awful lot of locks and has a slight + * force_sig() takes an awful lot of locks and has a slight * risk of deadlocking. */ if (user_space) { - do_exit(SIGBUS); + force_sig(SIGBUS, current); } else if (panic_on_oops || tolerant < 2) { mce_panic("Uncorrected machine check", &panicm, mcestart); @@ -490,7 +490,7 @@ static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) } -static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c) +static void mce_cpu_features(struct cpuinfo_x86 *c) { switch (c->x86_vendor) { case X86_VENDOR_INTEL: @@ -734,6 +734,7 @@ __setup("mce=", mcheck_enable); static int mce_resume(struct sys_device *dev) { mce_init(NULL); + mce_cpu_features(¤t_cpu_data); return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 8ae8c4ff094..f2ee0ae29bd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -121,7 +121,7 @@ static long threshold_restart_bank(void *_tr) } /* cpu init entry point, called from mce.c with preempt off */ -void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c) +void mce_amd_feature_init(struct cpuinfo_x86 *c) { unsigned int bank, block; unsigned int cpu = smp_processor_id(); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index 4b48f251fd3..f44c3662436 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -30,7 +30,7 @@ asmlinkage void smp_thermal_interrupt(void) irq_exit(); } -static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c) +static void intel_init_thermal(struct cpuinfo_x86 *c) { u32 l, h; int tm2 = 0; @@ -84,7 +84,7 @@ static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c) return; } -void __cpuinit mce_intel_feature_init(struct cpuinfo_x86 *c) +void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); } diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c index 169a120587b..87b67e3a765 100644 --- a/arch/x86/kernel/ds.c +++ b/arch/x86/kernel/ds.c @@ -729,7 +729,7 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task, spin_unlock_irqrestore(&ds_lock, irq); - ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts); + ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs); ds_resume_pebs(tracer); return tracer; @@ -1029,5 +1029,4 @@ void ds_copy_thread(struct task_struct *tsk, struct task_struct *father) void ds_exit_thread(struct task_struct *tsk) { - WARN_ON(tsk->thread.ds_ctx); } diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index 1119d247fe1..eb1ef3b67dd 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -467,7 +467,7 @@ void __init efi_enter_virtual_mode(void) efi_memory_desc_t *md; efi_status_t status; unsigned long size; - u64 end, systab, addr, npages; + u64 end, systab, addr, npages, end_pfn; void *p, *va; efi.systab = NULL; @@ -479,7 +479,10 @@ void __init efi_enter_virtual_mode(void) size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; - if (PFN_UP(end) <= max_low_pfn_mapped) + end_pfn = PFN_UP(end); + if (end_pfn <= max_low_pfn_mapped + || (end_pfn > (1UL << (32 - PAGE_SHIFT)) + && end_pfn <= max_pfn_mapped)) va = __va(md->phys_addr); else va = efi_ioremap(md->phys_addr, size); diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index 652c5287215..cb783b92c50 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -99,24 +99,11 @@ void __init efi_call_phys_epilog(void) void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size) { - static unsigned pages_mapped __initdata; - unsigned i, pages; - unsigned long offset; + unsigned long last_map_pfn; - pages = PFN_UP(phys_addr + size) - PFN_DOWN(phys_addr); - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - - if (pages_mapped + pages > MAX_EFI_IO_PAGES) + last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); + if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) return NULL; - for (i = 0; i < pages; i++) { - __set_fixmap(FIX_EFI_IO_MAP_FIRST_PAGE - pages_mapped, - phys_addr, PAGE_KERNEL); - phys_addr += PAGE_SIZE; - pages_mapped++; - } - - return (void __iomem *)__fix_to_virt(FIX_EFI_IO_MAP_FIRST_PAGE - \ - (pages_mapped - pages)) + offset; + return (void __iomem *)__va(phys_addr); } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1b43086b097..231bdd3c5b1 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -488,20 +488,21 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) * ignore such a protection. */ asm volatile( - "1: " _ASM_MOV " (%[parent_old]), %[old]\n" - "2: " _ASM_MOV " %[return_hooker], (%[parent_replaced])\n" + "1: " _ASM_MOV " (%[parent]), %[old]\n" + "2: " _ASM_MOV " %[return_hooker], (%[parent])\n" " movl $0, %[faulted]\n" + "3:\n" ".section .fixup, \"ax\"\n" - "3: movl $1, %[faulted]\n" + "4: movl $1, %[faulted]\n" + " jmp 3b\n" ".previous\n" - _ASM_EXTABLE(1b, 3b) - _ASM_EXTABLE(2b, 3b) + _ASM_EXTABLE(1b, 4b) + _ASM_EXTABLE(2b, 4b) - : [parent_replaced] "=r" (parent), [old] "=r" (old), - [faulted] "=r" (faulted) - : [parent_old] "0" (parent), [return_hooker] "r" (return_hooker) + : [old] "=r" (old), [faulted] "=r" (faulted) + : [parent] "r" (parent), [return_hooker] "r" (return_hooker) : "memory" ); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 388254f69a2..a00545fe5cd 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -269,6 +269,8 @@ static void hpet_set_mode(enum clock_event_mode mode, now = hpet_readl(HPET_COUNTER); cmp = now + (unsigned long) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); + /* Make sure we use edge triggered interrupts */ + cfg &= ~HPET_TN_LEVEL; cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | HPET_TN_32BIT; hpet_writel(cfg, HPET_Tn_CFG(timer)); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index b0f61f0dcd0..f2f8540a7f3 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -136,7 +136,7 @@ int init_fpu(struct task_struct *tsk) #ifdef CONFIG_X86_32 if (!HAVE_HWFP) { memset(tsk->thread.xstate, 0, xstate_size); - finit(); + finit_task(tsk); set_stopped_child_used_math(tsk); return 0; } diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c index dbd6c1d1b63..b42ca694dc6 100644 --- a/arch/x86/kernel/i8237.c +++ b/arch/x86/kernel/i8237.c @@ -28,10 +28,10 @@ static int i8237A_resume(struct sys_device *dev) flags = claim_dma_lock(); - dma_outb(DMA1_RESET_REG, 0); - dma_outb(DMA2_RESET_REG, 0); + dma_outb(0, DMA1_RESET_REG); + dma_outb(0, DMA2_RESET_REG); - for (i = 0;i < 8;i++) { + for (i = 0; i < 8; i++) { set_dma_addr(i, 0x000000); /* DMA count is a bit weird so this is not 0 */ set_dma_count(i, 1); @@ -51,14 +51,14 @@ static int i8237A_suspend(struct sys_device *dev, pm_message_t state) } static struct sysdev_class i8237_sysdev_class = { - .name = "i8237", - .suspend = i8237A_suspend, - .resume = i8237A_resume, + .name = "i8237", + .suspend = i8237A_suspend, + .resume = i8237A_resume, }; static struct sys_device device_i8237A = { - .id = 0, - .cls = &i8237_sysdev_class, + .id = 0, + .cls = &i8237_sysdev_class, }; static int __init i8237A_init_sysfs(void) @@ -68,5 +68,4 @@ static int __init i8237A_init_sysfs(void) error = sysdev_register(&device_i8237A); return error; } - device_initcall(i8237A_init_sysfs); diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index 9b0c480c383..bc7ac4da90d 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -3841,14 +3841,24 @@ int __init io_apic_get_redir_entries (int ioapic) void __init probe_nr_irqs_gsi(void) { - int idx; int nr = 0; - for (idx = 0; idx < nr_ioapics; idx++) - nr += io_apic_get_redir_entries(idx) + 1; - - if (nr > nr_irqs_gsi) + nr = acpi_probe_gsi(); + if (nr > nr_irqs_gsi) { nr_irqs_gsi = nr; + } else { + /* for acpi=off or acpi is not compiled in */ + int idx; + + nr = 0; + for (idx = 0; idx < nr_ioapics; idx++) + nr += io_apic_get_redir_entries(idx) + 1; + + if (nr > nr_irqs_gsi) + nr_irqs_gsi = nr; + } + + printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); } /* -------------------------------------------------------------------------- diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e948b28a5a9..4558dd3918c 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -193,6 +193,9 @@ static int __kprobes can_boost(kprobe_opcode_t *opcodes) kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; + if (search_exception_tables(opcodes)) + return 0; /* Page fault may occur on this address. */ + retry: if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1) return 0; diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c index 7a13fac63a1..4006c522adc 100644 --- a/arch/x86/kernel/olpc.c +++ b/arch/x86/kernel/olpc.c @@ -203,7 +203,7 @@ static void __init platform_detect(void) static void __init platform_detect(void) { /* stopgap until OFW support is added to the kernel */ - olpc_platform_info.boardrev = 0xc2; + olpc_platform_info.boardrev = olpc_board(0xc2); } #endif diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index e4c8fb60887..c6520a4e85d 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -268,6 +268,32 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return __get_cpu_var(paravirt_lazy_mode); } +void arch_flush_lazy_mmu_mode(void) +{ + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { + WARN_ON(preempt_count() == 1); + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); +} + +void arch_flush_lazy_cpu_mode(void) +{ + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) { + WARN_ON(preempt_count() == 1); + arch_leave_lazy_cpu_mode(); + arch_enter_lazy_cpu_mode(); + } + + preempt_enable(); +} + struct pv_info pv_info = { .name = "bare hardware", .paravirt_enabled = 0, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e68bb9e3086..6d12f7e37f8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -180,6 +180,9 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) trace_power_start(&it, POWER_CSTATE, (ax>>4)+1); if (!need_resched()) { + if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) + clflush((void *)¤t_thread_info()->flags); + __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); if (!need_resched()) @@ -194,6 +197,9 @@ static void mwait_idle(void) struct power_trace it; if (!need_resched()) { trace_power_start(&it, POWER_CSTATE, 1); + if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) + clflush((void *)¤t_thread_info()->flags); + __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); if (!need_resched()) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a546f55c77b..bd4da2af08a 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -104,9 +104,6 @@ void cpu_idle(void) check_pgt_cache(); rmb(); - if (rcu_pending(cpu)) - rcu_check_callbacks(cpu, 0); - if (cpu_is_offline(cpu)) play_dead(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 416fb9282f4..85b4cb5c198 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -40,6 +40,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> +#include <linux/dmi.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -151,14 +152,18 @@ void __show_regs(struct pt_regs *regs, int all) unsigned long d0, d1, d2, d3, d6, d7; unsigned int fsindex, gsindex; unsigned int ds, cs, es; + const char *board; printk("\n"); print_modules(); - printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n", + board = dmi_get_system_info(DMI_PRODUCT_NAME); + if (!board) + board = ""; + printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n", current->pid, current->comm, print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); + init_utsname()->version, board); printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); printk_address(regs->ip, 1); printk(KERN_INFO "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 0a5df5f82fb..06ca07f6ad8 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -810,12 +810,16 @@ static void ptrace_bts_untrace(struct task_struct *child) static void ptrace_bts_detach(struct task_struct *child) { - if (unlikely(child->bts)) { - ds_release_bts(child->bts); - child->bts = NULL; - - ptrace_bts_free_buffer(child); - } + /* + * Ptrace_detach() races with ptrace_untrace() in case + * the child dies and is reaped by another thread. + * + * We only do the memory accounting at this point and + * leave the buffer deallocation and the bts tracer + * release to ptrace_bts_untrace() which will be called + * later on with tasklist_lock held. + */ + release_locked_buffer(child->bts_buffer, child->bts_size); } #else static inline void ptrace_bts_fork(struct task_struct *tsk) {} @@ -1384,7 +1388,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, #ifdef CONFIG_X86_32 # define IS_IA32 1 #elif defined CONFIG_IA32_EMULATION -# define IS_IA32 test_thread_flag(TIF_IA32) +# define IS_IA32 is_compat_task() #else # define IS_IA32 0 #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2b46eb41643..4526b3a75ed 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -217,6 +217,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"), }, }, + { /* Handle problems with rebooting on Dell XPS710 */ + .callback = set_bios_reboot, + .ident = "Dell XPS710", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ae0d8042cf6..6a8811a6932 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -607,7 +607,7 @@ struct x86_quirks *x86_quirks __initdata = &default_x86_quirks; static int __init dmi_low_memory_corruption(const struct dmi_system_id *d) { printk(KERN_NOTICE - "%s detected: BIOS may corrupt low RAM, working it around.\n", + "%s detected: BIOS may corrupt low RAM, working around it.\n", d->ident); e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED); @@ -770,6 +770,9 @@ void __init setup_arch(char **cmdline_p) finish_e820_parsing(); + if (efi_enabled) + efi_init(); + dmi_scan_machine(); dmi_check_system(bad_bios_dmi_table); @@ -789,8 +792,6 @@ void __init setup_arch(char **cmdline_p) insert_resource(&iomem_resource, &data_resource); insert_resource(&iomem_resource, &bss_resource); - if (efi_enabled) - efi_init(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index e6e695acd72..241ec3923f6 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -115,7 +115,7 @@ unsigned long __init calibrate_cpu(void) static struct irqaction irq0 = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING, + .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER, .mask = CPU_MASK_NONE, .name = "timer" }; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 98c2d055284..a9e7548e179 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -99,6 +99,12 @@ static inline void preempt_conditional_sti(struct pt_regs *regs) local_irq_enable(); } +static inline void conditional_cli(struct pt_regs *regs) +{ + if (regs->flags & X86_EFLAGS_IF) + local_irq_disable(); +} + static inline void preempt_conditional_cli(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) @@ -626,8 +632,10 @@ clear_dr7: #ifdef CONFIG_X86_32 debug_vm86: + /* reenable preemption: handle_vm86_trap() might sleep */ + dec_preempt_count(); handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); - preempt_conditional_cli(regs); + conditional_cli(regs); return; #endif @@ -896,7 +904,7 @@ asmlinkage void math_state_restore(void) EXPORT_SYMBOL_GPL(math_state_restore); #ifndef CONFIG_MATH_EMULATION -asmlinkage void math_emulate(long arg) +void math_emulate(struct math_emu_info *info) { printk(KERN_EMERG "math-emulation not enabled and no coprocessor found.\n"); @@ -906,16 +914,19 @@ asmlinkage void math_emulate(long arg) } #endif /* CONFIG_MATH_EMULATION */ -dotraplinkage void __kprobes -do_device_not_available(struct pt_regs *regs, long error) +dotraplinkage void __kprobes do_device_not_available(struct pt_regs regs) { #ifdef CONFIG_X86_32 if (read_cr0() & X86_CR0_EM) { - conditional_sti(regs); - math_emulate(0); + struct math_emu_info info = { }; + + conditional_sti(®s); + + info.regs = ®s; + math_emulate(&info); } else { math_state_restore(); /* interrupts still off */ - conditional_sti(regs); + conditional_sti(®s); } #else math_state_restore(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 599e5816863..d5cebb52d45 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -273,30 +273,43 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) * use the TSC value at the transitions to calculate a pretty * good value for the TSC frequencty. */ -static inline int pit_expect_msb(unsigned char val) +static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { - int count = 0; + int count; + u64 tsc = 0; for (count = 0; count < 50000; count++) { /* Ignore LSB */ inb(0x42); if (inb(0x42) != val) break; + tsc = get_cycles(); } - return count > 50; + *deltap = get_cycles() - tsc; + *tscp = tsc; + + /* + * We require _some_ success, but the quality control + * will be based on the error terms on the TSC values. + */ + return count > 5; } /* - * How many MSB values do we want to see? We aim for a - * 15ms calibration, which assuming a 2us counter read - * error should give us roughly 150 ppm precision for - * the calibration. + * How many MSB values do we want to see? We aim for + * a maximum error rate of 500ppm (in practice the + * real error is much smaller), but refuse to spend + * more than 25ms on it. */ -#define QUICK_PIT_MS 15 -#define QUICK_PIT_ITERATIONS (QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) +#define MAX_QUICK_PIT_MS 25 +#define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) { + int i; + u64 tsc, delta; + unsigned long d1, d2; + /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); @@ -315,45 +328,52 @@ static unsigned long quick_pit_calibrate(void) outb(0xff, 0x42); outb(0xff, 0x42); - if (pit_expect_msb(0xff)) { - int i; - u64 t1, t2, delta; - unsigned char expect = 0xfe; - - t1 = get_cycles(); - for (i = 0; i < QUICK_PIT_ITERATIONS; i++, expect--) { - if (!pit_expect_msb(expect)) - goto failed; + /* + * The PIT starts counting at the next edge, so we + * need to delay for a microsecond. The easiest way + * to do that is to just read back the 16-bit counter + * once from the PIT. + */ + inb(0x42); + inb(0x42); + + if (pit_expect_msb(0xff, &tsc, &d1)) { + for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) { + if (!pit_expect_msb(0xff-i, &delta, &d2)) + break; + + /* + * Iterate until the error is less than 500 ppm + */ + delta -= tsc; + if (d1+d2 < delta >> 11) + goto success; } - t2 = get_cycles(); - - /* - * Make sure we can rely on the second TSC timestamp: - */ - if (!pit_expect_msb(expect)) - goto failed; - - /* - * Ok, if we get here, then we've seen the - * MSB of the PIT decrement QUICK_PIT_ITERATIONS - * times, and each MSB had many hits, so we never - * had any sudden jumps. - * - * As a result, we can depend on there not being - * any odd delays anywhere, and the TSC reads are - * reliable. - * - * kHz = ticks / time-in-seconds / 1000; - * kHz = (t2 - t1) / (QPI * 256 / PIT_TICK_RATE) / 1000 - * kHz = ((t2 - t1) * PIT_TICK_RATE) / (QPI * 256 * 1000) - */ - delta = (t2 - t1)*PIT_TICK_RATE; - do_div(delta, QUICK_PIT_ITERATIONS*256*1000); - printk("Fast TSC calibration using PIT\n"); - return delta; } -failed: + printk("Fast TSC calibration failed\n"); return 0; + +success: + /* + * Ok, if we get here, then we've seen the + * MSB of the PIT decrement 'i' times, and the + * error has shrunk to less than 500 ppm. + * + * As a result, we can depend on there not being + * any odd delays anywhere, and the TSC reads are + * reliable (within the error). We also adjust the + * delta to the middle of the error bars, just + * because it looks nicer. + * + * kHz = ticks / time-in-seconds / 1000; + * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 + * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) + */ + delta += (long)(d2 - d1)/2; + delta *= PIT_TICK_RATE; + do_div(delta, i*256*1000); + printk("Fast TSC calibration using PIT\n"); + return delta; } /** diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 1d3302cc2dd..bef58b4982d 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -321,6 +321,16 @@ static void vmi_release_pmd(unsigned long pfn) } /* + * We use the pgd_free hook for releasing the pgd page: + */ +static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + unsigned long pfn = __pa(pgd) >> PAGE_SHIFT; + + vmi_ops.release_page(pfn, VMI_PAGE_L2); +} + +/* * Helper macros for MMU update flags. We can defer updates until a flush * or page invalidation only if the update is to the current address space * (otherwise, there is no flush). We must check against init_mm, since @@ -762,6 +772,7 @@ static inline int __init activate_vmi(void) if (vmi_ops.release_page) { pv_mmu_ops.release_pte = vmi_release_pte; pv_mmu_ops.release_pmd = vmi_release_pmd; + pv_mmu_ops.pgd_free = vmi_pgd_free; } /* Set linear is needed in all cases */ diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index c4c1f9e0940..e5b088fffa4 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -202,7 +202,7 @@ static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id) static struct irqaction vmi_clock_action = { .name = "vmi-timer", .handler = vmi_timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER, .mask = CPU_MASK_ALL, }; @@ -283,10 +283,13 @@ void __devinit vmi_time_ap_init(void) #endif /** vmi clocksource */ +static struct clocksource clocksource_vmi; static cycle_t read_real_cycles(void) { - return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); + cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); + return ret >= clocksource_vmi.cycle_last ? + ret : clocksource_vmi.cycle_last; } static struct clocksource clocksource_vmi = { diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index e665d1c623c..72bd275a9b5 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -207,7 +207,7 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps) hrtimer_add_expires_ns(&pt->timer, pt->period); pt->scheduled = hrtimer_get_expires_ns(&pt->timer); if (pt->period) - ps->channels[0].count_load_time = hrtimer_get_expires(&pt->timer); + ps->channels[0].count_load_time = ktime_get(); return (pt->period == 0 ? 0 : 1); } diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index c019b8edcdb..cf17ed52f6f 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -87,13 +87,6 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); -void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec) -{ - kvm_apic_timer_intr_post(vcpu, vec); - /* TODO: PIT, RTC etc. */ -} -EXPORT_SYMBOL_GPL(kvm_timer_intr_post); - void __kvm_migrate_timers(struct kvm_vcpu *vcpu) { __kvm_migrate_apic_timer(vcpu); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 2bf32a03cee..82579ee538d 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -89,7 +89,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s); -void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index afac68c0815..f0b67f2cdd6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -35,6 +35,12 @@ #include "kvm_cache_regs.h" #include "irq.h" +#ifndef CONFIG_X86_64 +#define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) +#else +#define mod_64(x, y) ((x) % (y)) +#endif + #define PRId64 "d" #define PRIx64 "llx" #define PRIu64 "u" @@ -511,52 +517,22 @@ static void apic_send_ipi(struct kvm_lapic *apic) static u32 apic_get_tmcct(struct kvm_lapic *apic) { - u64 counter_passed; - ktime_t passed, now; + ktime_t remaining; + s64 ns; u32 tmcct; ASSERT(apic != NULL); - now = apic->timer.dev.base->get_time(); - tmcct = apic_get_reg(apic, APIC_TMICT); - /* if initial count is 0, current count should also be 0 */ - if (tmcct == 0) + if (apic_get_reg(apic, APIC_TMICT) == 0) return 0; - if (unlikely(ktime_to_ns(now) <= - ktime_to_ns(apic->timer.last_update))) { - /* Wrap around */ - passed = ktime_add(( { - (ktime_t) { - .tv64 = KTIME_MAX - - (apic->timer.last_update).tv64}; } - ), now); - apic_debug("time elapsed\n"); - } else - passed = ktime_sub(now, apic->timer.last_update); - - counter_passed = div64_u64(ktime_to_ns(passed), - (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); - - if (counter_passed > tmcct) { - if (unlikely(!apic_lvtt_period(apic))) { - /* one-shot timers stick at 0 until reset */ - tmcct = 0; - } else { - /* - * periodic timers reset to APIC_TMICT when they - * hit 0. The while loop simulates this happening N - * times. (counter_passed %= tmcct) would also work, - * but might be slower or not work on 32-bit?? - */ - while (counter_passed > tmcct) - counter_passed -= tmcct; - tmcct -= counter_passed; - } - } else { - tmcct -= counter_passed; - } + remaining = hrtimer_expires_remaining(&apic->timer.dev); + if (ktime_to_ns(remaining) < 0) + remaining = ktime_set(0, 0); + + ns = mod_64(ktime_to_ns(remaining), apic->timer.period); + tmcct = div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); return tmcct; } @@ -653,8 +629,6 @@ static void start_apic_timer(struct kvm_lapic *apic) { ktime_t now = apic->timer.dev.base->get_time(); - apic->timer.last_update = now; - apic->timer.period = apic_get_reg(apic, APIC_TMICT) * APIC_BUS_CYCLE_NS * apic->timer.divide_count; atomic_set(&apic->timer.pending, 0); @@ -1110,16 +1084,6 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) } } -void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - - if (apic && apic_lvt_vector(apic, APIC_LVTT) == vec) - apic->timer.last_update = ktime_add_ns( - apic->timer.last_update, - apic->timer.period); -} - int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) { int vector = kvm_apic_has_interrupt(vcpu); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 81858881287..45ab6ee7120 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -12,7 +12,6 @@ struct kvm_lapic { atomic_t pending; s64 period; /* unit: ns */ u32 divide_count; - ktime_t last_update; struct hrtimer dev; } timer; struct kvm_vcpu *vcpu; @@ -42,7 +41,6 @@ void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu); int kvm_lapic_enabled(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); -void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec); void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 83f11c7474a..2d4477c7147 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1698,8 +1698,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, if (largepage) spte |= PT_PAGE_SIZE_MASK; if (mt_mask) { - mt_mask = get_memory_type(vcpu, gfn) << - kvm_x86_ops->get_mt_mask_shift(); + if (!kvm_is_mmio_pfn(pfn)) { + mt_mask = get_memory_type(vcpu, gfn) << + kvm_x86_ops->get_mt_mask_shift(); + mt_mask |= VMX_EPT_IGMT_BIT; + } else + mt_mask = MTRR_TYPE_UNCACHABLE << + kvm_x86_ops->get_mt_mask_shift(); spte |= mt_mask; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1452851ae25..a9e769e4e25 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1600,7 +1600,6 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu) /* Okay, we can deliver the interrupt: grab it and update PIC state. */ intr_vector = kvm_cpu_get_interrupt(vcpu); svm_inject_irq(svm, intr_vector); - kvm_timer_intr_post(vcpu, intr_vector); out: update_cr8_intercept(vcpu); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6259d746764..7611af57682 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -903,6 +903,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) data = vmcs_readl(GUEST_SYSENTER_ESP); break; default: + vmx_load_host_state(to_vmx(vcpu)); msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { data = msr->data; @@ -3285,7 +3286,6 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu) } if (vcpu->arch.interrupt.pending) { vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr); - kvm_timer_intr_post(vcpu, vcpu->arch.interrupt.nr); if (kvm_cpu_has_interrupt(vcpu)) enable_irq_window(vcpu); } @@ -3687,8 +3687,7 @@ static int __init vmx_init(void) if (vm_need_ept()) { bypass_guest_pf = 0; kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK | - VMX_EPT_WRITABLE_MASK | - VMX_EPT_IGMT_BIT); + VMX_EPT_WRITABLE_MASK); kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull, VMX_EPT_EXECUTABLE_MASK, VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cc17546a240..758b7a155ae 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -967,7 +967,6 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: - case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: @@ -992,6 +991,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IOMMU: r = iommu_found(); break; + case KVM_CAP_CLOCKSOURCE: + r = boot_cpu_has(X86_FEATURE_CONSTANT_TSC); + break; default: r = 0; break; @@ -4127,9 +4129,13 @@ static void kvm_free_vcpus(struct kvm *kvm) } -void kvm_arch_destroy_vm(struct kvm *kvm) +void kvm_arch_sync_events(struct kvm *kvm) { kvm_free_all_assigned_devices(kvm); +} + +void kvm_arch_destroy_vm(struct kvm *kvm) +{ kvm_iommu_unmap_guest(kvm); kvm_free_pit(kvm); kfree(kvm->arch.vpic); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 92f1c6f3e19..960a8d9c049 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -343,6 +343,11 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, * flush_tlb_user() for both user and kernel mappings unless * the Page Global Enable (PGE) feature bit is set. */ *dx |= 0x00002000; + /* We also lie, and say we're family id 5. 6 or greater + * leads to a rdmsr in early_init_intel which we can't handle. + * Family ID is returned as bits 8-12 in ax. */ + *ax &= 0xFFFFF0FF; + *ax |= 0x00000500; break; case 0x80000000: /* Futureproof this a little: if they ask how much extended @@ -589,19 +594,21 @@ static void __init lguest_init_IRQ(void) /* Some systems map "vectors" to interrupts weirdly. Lguest has * a straightforward 1 to 1 mapping, so force that here. */ __get_cpu_var(vector_irq)[vector] = i; - if (vector != SYSCALL_VECTOR) { - set_intr_gate(vector, - interrupt[vector-FIRST_EXTERNAL_VECTOR]); - set_irq_chip_and_handler_name(i, &lguest_irq_controller, - handle_level_irq, - "level"); - } + if (vector != SYSCALL_VECTOR) + set_intr_gate(vector, interrupt[i]); } /* This call is required to set up for 4k stacks, where we have * separate stacks for hard and soft interrupts. */ irq_ctx_init(smp_processor_id()); } +void lguest_setup_irq(unsigned int irq) +{ + irq_to_desc_alloc_cpu(irq, 0); + set_irq_chip_and_handler_name(irq, &lguest_irq_controller, + handle_level_irq, "level"); +} + /* * Time. * diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c index a265a7c6319..50b59187112 100644 --- a/arch/x86/mach-default/setup.c +++ b/arch/x86/mach-default/setup.c @@ -96,7 +96,7 @@ void __init trap_init_hook(void) static struct irqaction irq0 = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, .mask = CPU_MASK_NONE, .name = "timer" }; diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c index d914a7996a6..8e5118371f0 100644 --- a/arch/x86/mach-voyager/setup.c +++ b/arch/x86/mach-voyager/setup.c @@ -56,7 +56,7 @@ void __init trap_init_hook(void) static struct irqaction irq0 = { .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, .mask = CPU_MASK_NONE, .name = "timer" }; diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c index 7ffcdeec463..b9cc84a2a4f 100644 --- a/arch/x86/mach-voyager/voyager_smp.c +++ b/arch/x86/mach-voyager/voyager_smp.c @@ -65,7 +65,7 @@ static volatile unsigned long smp_invalidate_needed; /* Bitmask of CPUs present in the system - exported by i386_syms.c, used * by scheduler but indexed physically */ -cpumask_t phys_cpu_present_map = CPU_MASK_NONE; +static cpumask_t voyager_phys_cpu_present_map = CPU_MASK_NONE; /* The internal functions */ static void send_CPI(__u32 cpuset, __u8 cpi); @@ -366,19 +366,19 @@ void __init find_smp_config(void) /* set up everything for just this CPU, we can alter * this as we start the other CPUs later */ /* now get the CPU disposition from the extended CMOS */ - cpus_addr(phys_cpu_present_map)[0] = + cpus_addr(voyager_phys_cpu_present_map)[0] = voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK); - cpus_addr(phys_cpu_present_map)[0] |= + cpus_addr(voyager_phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 1) << 8; - cpus_addr(phys_cpu_present_map)[0] |= + cpus_addr(voyager_phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 2) << 16; - cpus_addr(phys_cpu_present_map)[0] |= + cpus_addr(voyager_phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 3) << 24; - init_cpu_possible(&phys_cpu_present_map); - printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n", - cpus_addr(phys_cpu_present_map)[0]); + init_cpu_possible(&voyager_phys_cpu_present_map); + printk("VOYAGER SMP: voyager_phys_cpu_present_map = 0x%lx\n", + cpus_addr(voyager_phys_cpu_present_map)[0]); /* Here we set up the VIC to enable SMP */ /* enable the CPIs by writing the base vector to their register */ outb(VIC_DEFAULT_CPI_BASE, VIC_CPI_BASE_REGISTER); @@ -628,15 +628,15 @@ void __init smp_boot_cpus(void) /* now that the cat has probed the Voyager System Bus, sanity * check the cpu map */ if (((voyager_quad_processors | voyager_extended_vic_processors) - & cpus_addr(phys_cpu_present_map)[0]) != - cpus_addr(phys_cpu_present_map)[0]) { + & cpus_addr(voyager_phys_cpu_present_map)[0]) != + cpus_addr(voyager_phys_cpu_present_map)[0]) { /* should panic */ printk("\n\n***WARNING*** " "Sanity check of CPU present map FAILED\n"); } } else if (voyager_level == 4) voyager_extended_vic_processors = - cpus_addr(phys_cpu_present_map)[0]; + cpus_addr(voyager_phys_cpu_present_map)[0]; /* this sets up the idle task to run on the current cpu */ voyager_extended_cpus = 1; @@ -670,7 +670,7 @@ void __init smp_boot_cpus(void) /* loop over all the extended VIC CPUs and boot them. The * Quad CPUs must be bootstrapped by their extended VIC cpu */ for (i = 0; i < nr_cpu_ids; i++) { - if (i == boot_cpu_id || !cpu_isset(i, phys_cpu_present_map)) + if (i == boot_cpu_id || !cpu_isset(i, voyager_phys_cpu_present_map)) continue; do_boot_cpu(i); /* This udelay seems to be needed for the Quad boots diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index 491e737ce54..aa098708877 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -30,20 +30,29 @@ static void fclex(void) } /* Needs to be externally visible */ -void finit(void) +void finit_task(struct task_struct *tsk) { - control_word = 0x037f; - partial_status = 0; - top = 0; /* We don't keep top in the status word internally. */ - fpu_tag_word = 0xffff; + struct i387_soft_struct *soft = &tsk->thread.xstate->soft; + struct address *oaddr, *iaddr; + soft->cwd = 0x037f; + soft->swd = 0; + soft->ftop = 0; /* We don't keep top in the status word internally. */ + soft->twd = 0xffff; /* The behaviour is different from that detailed in Section 15.1.6 of the Intel manual */ - operand_address.offset = 0; - operand_address.selector = 0; - instruction_address.offset = 0; - instruction_address.selector = 0; - instruction_address.opcode = 0; - no_ip_update = 1; + oaddr = (struct address *)&soft->foo; + oaddr->offset = 0; + oaddr->selector = 0; + iaddr = (struct address *)&soft->fip; + iaddr->offset = 0; + iaddr->selector = 0; + iaddr->opcode = 0; + soft->no_update = 1; +} + +void finit(void) +{ + finit_task(current); } /* diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index c7b06feb139..5d87f586f8d 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -131,7 +131,7 @@ u_char emulating = 0; static int valid_prefix(u_char *Byte, u_char __user ** fpu_eip, overrides * override); -asmlinkage void math_emulate(long arg) +void math_emulate(struct math_emu_info *info) { u_char FPU_modrm, byte1; unsigned short code; @@ -161,7 +161,7 @@ asmlinkage void math_emulate(long arg) RE_ENTRANT_CHECK_ON; #endif /* RE_ENTRANT_CHECKING */ - SETUP_DATA_AREA(arg); + FPU_info = info; FPU_ORIG_EIP = FPU_EIP; @@ -659,7 +659,7 @@ static int valid_prefix(u_char *Byte, u_char __user **fpu_eip, } } -void math_abort(struct info *info, unsigned int signal) +void math_abort(struct math_emu_info *info, unsigned int signal) { FPU_EIP = FPU_ORIG_EIP; current->thread.trap_no = 16; diff --git a/arch/x86/math-emu/fpu_proto.h b/arch/x86/math-emu/fpu_proto.h index aa49b6a0d85..9779df436b7 100644 --- a/arch/x86/math-emu/fpu_proto.h +++ b/arch/x86/math-emu/fpu_proto.h @@ -51,8 +51,8 @@ extern void ffreep(void); extern void fst_i_(void); extern void fstp_i(void); /* fpu_entry.c */ -asmlinkage extern void math_emulate(long arg); -extern void math_abort(struct info *info, unsigned int signal); +extern void math_emulate(struct math_emu_info *info); +extern void math_abort(struct math_emu_info *info, unsigned int signal); /* fpu_etc.c */ extern void FPU_etc(void); /* fpu_tags.c */ diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 13488fa153e..50fa0ec2c8a 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -16,10 +16,6 @@ #include <linux/kernel.h> #include <linux/mm.h> -/* This sets the pointer FPU_info to point to the argument part - of the stack frame of math_emulate() */ -#define SETUP_DATA_AREA(arg) FPU_info = (struct info *) &arg - /* s is always from a cpu register, and the cpu does bounds checking * during register load --> no further bounds checks needed */ #define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3]) @@ -38,12 +34,12 @@ #define I387 (current->thread.xstate) #define FPU_info (I387->soft.info) -#define FPU_CS (*(unsigned short *) &(FPU_info->___cs)) -#define FPU_SS (*(unsigned short *) &(FPU_info->___ss)) -#define FPU_DS (*(unsigned short *) &(FPU_info->___ds)) -#define FPU_EAX (FPU_info->___eax) -#define FPU_EFLAGS (FPU_info->___eflags) -#define FPU_EIP (FPU_info->___eip) +#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs)) +#define FPU_SS (*(unsigned short *) &(FPU_info->regs->ss)) +#define FPU_DS (*(unsigned short *) &(FPU_info->regs->ds)) +#define FPU_EAX (FPU_info->regs->ax) +#define FPU_EFLAGS (FPU_info->regs->flags) +#define FPU_EIP (FPU_info->regs->ip) #define FPU_ORIG_EIP (FPU_info->___orig_eip) #define FPU_lookahead (I387->soft.lookahead) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index d701e2b39e4..420b3b6e391 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -29,46 +29,43 @@ #define FPU_WRITE_BIT 0x10 static int reg_offset[] = { - offsetof(struct info, ___eax), - offsetof(struct info, ___ecx), - offsetof(struct info, ___edx), - offsetof(struct info, ___ebx), - offsetof(struct info, ___esp), - offsetof(struct info, ___ebp), - offsetof(struct info, ___esi), - offsetof(struct info, ___edi) + offsetof(struct pt_regs, ax), + offsetof(struct pt_regs, cx), + offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, bx), + offsetof(struct pt_regs, sp), + offsetof(struct pt_regs, bp), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, di) }; -#define REG_(x) (*(long *)(reg_offset[(x)]+(u_char *) FPU_info)) +#define REG_(x) (*(long *)(reg_offset[(x)] + (u_char *)FPU_info->regs)) static int reg_offset_vm86[] = { - offsetof(struct info, ___cs), - offsetof(struct info, ___vm86_ds), - offsetof(struct info, ___vm86_es), - offsetof(struct info, ___vm86_fs), - offsetof(struct info, ___vm86_gs), - offsetof(struct info, ___ss), - offsetof(struct info, ___vm86_ds) + offsetof(struct pt_regs, cs), + offsetof(struct kernel_vm86_regs, ds), + offsetof(struct kernel_vm86_regs, es), + offsetof(struct kernel_vm86_regs, fs), + offsetof(struct kernel_vm86_regs, gs), + offsetof(struct pt_regs, ss), + offsetof(struct kernel_vm86_regs, ds) }; #define VM86_REG_(x) (*(unsigned short *) \ - (reg_offset_vm86[((unsigned)x)]+(u_char *) FPU_info)) - -/* This dummy, gs is not saved on the stack. */ -#define ___GS ___ds + (reg_offset_vm86[((unsigned)x)] + (u_char *)FPU_info->regs)) static int reg_offset_pm[] = { - offsetof(struct info, ___cs), - offsetof(struct info, ___ds), - offsetof(struct info, ___es), - offsetof(struct info, ___fs), - offsetof(struct info, ___GS), - offsetof(struct info, ___ss), - offsetof(struct info, ___ds) + offsetof(struct pt_regs, cs), + offsetof(struct pt_regs, ds), + offsetof(struct pt_regs, es), + offsetof(struct pt_regs, fs), + offsetof(struct pt_regs, ds), /* dummy, not saved on stack */ + offsetof(struct pt_regs, ss), + offsetof(struct pt_regs, ds) }; #define PM_REG_(x) (*(unsigned short *) \ - (reg_offset_pm[((unsigned)x)]+(u_char *) FPU_info)) + (reg_offset_pm[((unsigned)x)] + (u_char *)FPU_info->regs)) /* Decode the SIB byte. This function assumes mod != 0 */ static int sib(int mod, unsigned long *fpu_eip) @@ -349,34 +346,34 @@ void __user *FPU_get_address_16(u_char FPU_modrm, unsigned long *fpu_eip, } switch (rm) { case 0: - address += FPU_info->___ebx + FPU_info->___esi; + address += FPU_info->regs->bx + FPU_info->regs->si; break; case 1: - address += FPU_info->___ebx + FPU_info->___edi; + address += FPU_info->regs->bx + FPU_info->regs->di; break; case 2: - address += FPU_info->___ebp + FPU_info->___esi; + address += FPU_info->regs->bp + FPU_info->regs->si; if (addr_modes.override.segment == PREFIX_DEFAULT) addr_modes.override.segment = PREFIX_SS_; break; case 3: - address += FPU_info->___ebp + FPU_info->___edi; + address += FPU_info->regs->bp + FPU_info->regs->di; if (addr_modes.override.segment == PREFIX_DEFAULT) addr_modes.override.segment = PREFIX_SS_; break; case 4: - address += FPU_info->___esi; + address += FPU_info->regs->si; break; case 5: - address += FPU_info->___edi; + address += FPU_info->regs->di; break; case 6: - address += FPU_info->___ebp; + address += FPU_info->regs->bp; if (addr_modes.override.segment == PREFIX_DEFAULT) addr_modes.override.segment = PREFIX_SS_; break; case 7: - address += FPU_info->___ebx; + address += FPU_info->regs->bx; break; } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index e6d36b49025..b1352250096 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -714,6 +714,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, pos = start_pfn << PAGE_SHIFT; end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + if (end_pfn > (end >> PAGE_SHIFT)) + end_pfn = end >> PAGE_SHIFT; if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); pos = end_pfn << PAGE_SHIFT; diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index ca53224fc56..04102d42ff4 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -20,6 +20,17 @@ #include <asm/pat.h> #include <linux/module.h> +int is_io_mapping_possible(resource_size_t base, unsigned long size) +{ +#ifndef CONFIG_X86_PAE + /* There is no way to map greater than 1 << 32 address without PAE */ + if (base + size > 0x100000000ULL) + return 0; +#endif + return 1; +} +EXPORT_SYMBOL_GPL(is_io_mapping_possible); + /* Map 'pfn' using fixed map 'type' and protections 'prot' */ void * diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index af750ab973b..f45d5e29a72 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -134,25 +134,6 @@ int page_is_ram(unsigned long pagenr) return 0; } -int pagerange_is_ram(unsigned long start, unsigned long end) -{ - int ram_page = 0, not_rampage = 0; - unsigned long page_nr; - - for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT); - ++page_nr) { - if (page_is_ram(page_nr)) - ram_page = 1; - else - not_rampage = 1; - - if (ram_page == not_rampage) - return -1; - } - - return ram_page; -} - /* * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 93d82038af4..6a518dd08a3 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -32,11 +32,14 @@ struct kmmio_fault_page { struct list_head list; struct kmmio_fault_page *release_next; unsigned long page; /* location of the fault page */ + bool old_presence; /* page presence prior to arming */ + bool armed; /* * Number of times this page has been registered as a part * of a probe. If zero, page is disarmed and this may be freed. - * Used only by writers (RCU). + * Used only by writers (RCU) and post_kmmio_handler(). + * Protected by kmmio_lock, when linked into kmmio_page_table. */ int count; }; @@ -105,57 +108,85 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page) return NULL; } -static void set_page_present(unsigned long addr, bool present, - unsigned int *pglevel) +static void set_pmd_presence(pmd_t *pmd, bool present, bool *old) +{ + pmdval_t v = pmd_val(*pmd); + *old = !!(v & _PAGE_PRESENT); + v &= ~_PAGE_PRESENT; + if (present) + v |= _PAGE_PRESENT; + set_pmd(pmd, __pmd(v)); +} + +static void set_pte_presence(pte_t *pte, bool present, bool *old) +{ + pteval_t v = pte_val(*pte); + *old = !!(v & _PAGE_PRESENT); + v &= ~_PAGE_PRESENT; + if (present) + v |= _PAGE_PRESENT; + set_pte_atomic(pte, __pte(v)); +} + +static int set_page_presence(unsigned long addr, bool present, bool *old) { - pteval_t pteval; - pmdval_t pmdval; unsigned int level; - pmd_t *pmd; pte_t *pte = lookup_address(addr, &level); if (!pte) { pr_err("kmmio: no pte for page 0x%08lx\n", addr); - return; + return -1; } - if (pglevel) - *pglevel = level; - switch (level) { case PG_LEVEL_2M: - pmd = (pmd_t *)pte; - pmdval = pmd_val(*pmd) & ~_PAGE_PRESENT; - if (present) - pmdval |= _PAGE_PRESENT; - set_pmd(pmd, __pmd(pmdval)); + set_pmd_presence((pmd_t *)pte, present, old); break; - case PG_LEVEL_4K: - pteval = pte_val(*pte) & ~_PAGE_PRESENT; - if (present) - pteval |= _PAGE_PRESENT; - set_pte_atomic(pte, __pte(pteval)); + set_pte_presence(pte, present, old); break; - default: pr_err("kmmio: unexpected page level 0x%x.\n", level); - return; + return -1; } __flush_tlb_one(addr); + return 0; } -/** Mark the given page as not present. Access to it will trigger a fault. */ -static void arm_kmmio_fault_page(unsigned long page, unsigned int *pglevel) +/* + * Mark the given page as not present. Access to it will trigger a fault. + * + * Struct kmmio_fault_page is protected by RCU and kmmio_lock, but the + * protection is ignored here. RCU read lock is assumed held, so the struct + * will not disappear unexpectedly. Furthermore, the caller must guarantee, + * that double arming the same virtual address (page) cannot occur. + * + * Double disarming on the other hand is allowed, and may occur when a fault + * and mmiotrace shutdown happen simultaneously. + */ +static int arm_kmmio_fault_page(struct kmmio_fault_page *f) { - set_page_present(page & PAGE_MASK, false, pglevel); + int ret; + WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n"); + if (f->armed) { + pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n", + f->page, f->count, f->old_presence); + } + ret = set_page_presence(f->page, false, &f->old_presence); + WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page); + f->armed = true; + return ret; } -/** Mark the given page as present. */ -static void disarm_kmmio_fault_page(unsigned long page, unsigned int *pglevel) +/** Restore the given page to saved presence state. */ +static void disarm_kmmio_fault_page(struct kmmio_fault_page *f) { - set_page_present(page & PAGE_MASK, true, pglevel); + bool tmp; + int ret = set_page_presence(f->page, f->old_presence, &tmp); + WARN_ONCE(ret < 0, + KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page); + f->armed = false; } /* @@ -202,28 +233,32 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx = &get_cpu_var(kmmio_ctx); if (ctx->active) { - disarm_kmmio_fault_page(faultpage->page, NULL); if (addr == ctx->addr) { /* - * On SMP we sometimes get recursive probe hits on the - * same address. Context is already saved, fall out. + * A second fault on the same page means some other + * condition needs handling by do_page_fault(), the + * page really not being present is the most common. */ - pr_debug("kmmio: duplicate probe hit on CPU %d, for " - "address 0x%08lx.\n", - smp_processor_id(), addr); - ret = 1; - goto no_kmmio_ctx; - } - /* - * Prevent overwriting already in-flight context. - * This should not happen, let's hope disarming at least - * prevents a panic. - */ - pr_emerg("kmmio: recursive probe hit on CPU %d, " + pr_debug("kmmio: secondary hit for 0x%08lx CPU %d.\n", + addr, smp_processor_id()); + + if (!faultpage->old_presence) + pr_info("kmmio: unexpected secondary hit for " + "address 0x%08lx on CPU %d.\n", addr, + smp_processor_id()); + } else { + /* + * Prevent overwriting already in-flight context. + * This should not happen, let's hope disarming at + * least prevents a panic. + */ + pr_emerg("kmmio: recursive probe hit on CPU %d, " "for address 0x%08lx. Ignoring.\n", smp_processor_id(), addr); - pr_emerg("kmmio: previous hit was at 0x%08lx.\n", - ctx->addr); + pr_emerg("kmmio: previous hit was at 0x%08lx.\n", + ctx->addr); + disarm_kmmio_fault_page(faultpage); + } goto no_kmmio_ctx; } ctx->active++; @@ -244,7 +279,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) regs->flags &= ~X86_EFLAGS_IF; /* Now we set present bit in PTE and single step. */ - disarm_kmmio_fault_page(ctx->fpage->page, NULL); + disarm_kmmio_fault_page(ctx->fpage); /* * If another cpu accesses the same page while we are stepping, @@ -275,7 +310,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx); if (!ctx->active) { - pr_debug("kmmio: spurious debug trap on CPU %d.\n", + pr_warning("kmmio: spurious debug trap on CPU %d.\n", smp_processor_id()); goto out; } @@ -283,7 +318,11 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) if (ctx->probe && ctx->probe->post_handler) ctx->probe->post_handler(ctx->probe, condition, regs); - arm_kmmio_fault_page(ctx->fpage->page, NULL); + /* Prevent racing against release_kmmio_fault_page(). */ + spin_lock(&kmmio_lock); + if (ctx->fpage->count) + arm_kmmio_fault_page(ctx->fpage); + spin_unlock(&kmmio_lock); regs->flags &= ~X86_EFLAGS_TF; regs->flags |= ctx->saved_flags; @@ -315,20 +354,24 @@ static int add_kmmio_fault_page(unsigned long page) f = get_kmmio_fault_page(page); if (f) { if (!f->count) - arm_kmmio_fault_page(f->page, NULL); + arm_kmmio_fault_page(f); f->count++; return 0; } - f = kmalloc(sizeof(*f), GFP_ATOMIC); + f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) return -1; f->count = 1; f->page = page; - list_add_rcu(&f->list, kmmio_page_list(f->page)); - arm_kmmio_fault_page(f->page, NULL); + if (arm_kmmio_fault_page(f)) { + kfree(f); + return -1; + } + + list_add_rcu(&f->list, kmmio_page_list(f->page)); return 0; } @@ -347,7 +390,7 @@ static void release_kmmio_fault_page(unsigned long page, f->count--; BUG_ON(f->count < 0); if (!f->count) { - disarm_kmmio_fault_page(f->page, NULL); + disarm_kmmio_fault_page(f); f->release_next = *release_list; *release_list = f; } @@ -408,23 +451,24 @@ static void rcu_free_kmmio_fault_pages(struct rcu_head *head) static void remove_kmmio_fault_pages(struct rcu_head *head) { - struct kmmio_delayed_release *dr = container_of( - head, - struct kmmio_delayed_release, - rcu); + struct kmmio_delayed_release *dr = + container_of(head, struct kmmio_delayed_release, rcu); struct kmmio_fault_page *p = dr->release_list; struct kmmio_fault_page **prevp = &dr->release_list; unsigned long flags; + spin_lock_irqsave(&kmmio_lock, flags); while (p) { - if (!p->count) + if (!p->count) { list_del_rcu(&p->list); - else + prevp = &p->release_next; + } else { *prevp = p->release_next; - prevp = &p->release_next; + } p = p->release_next; } spin_unlock_irqrestore(&kmmio_lock, flags); + /* This is the real RCU destroy call. */ call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages); } diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 71a14f89f89..f3516da035d 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -145,7 +145,7 @@ int __init compute_hash_shift(struct bootnode *nodes, int numnodes, return shift; } -int early_pfn_to_nid(unsigned long pfn) +int __meminit __early_pfn_to_nid(unsigned long pfn) { return phys_to_nid(pfn << PAGE_SHIFT); } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 84ba74820ad..7233bd7e357 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -508,18 +508,24 @@ static int split_large_page(pte_t *kpte, unsigned long address) #endif /* - * Install the new, split up pagetable. Important details here: + * Install the new, split up pagetable. * - * On Intel the NX bit of all levels must be cleared to make a - * page executable. See section 4.13.2 of Intel 64 and IA-32 - * Architectures Software Developer's Manual). + * We use the standard kernel pagetable protections for the new + * pagetable protections, the actual ptes set above control the + * primary protection behavior: + */ + __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE))); + + /* + * Intel Atom errata AAH41 workaround. * - * Mark the entry present. The current mapping might be - * set to not present, which we preserved above. + * The real fix should be in hw or in a microcode update, but + * we also probabilistically try to reduce the window of having + * a large TLB mixed with 4K TLBs while instruction fetches are + * going on. */ - ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte))); - pgprot_val(ref_prot) |= _PAGE_PRESENT; - __set_pmd_pte(kpte, address, mk_pte(base, ref_prot)); + __flush_tlb_all(); + base = NULL; out_unlock: @@ -575,7 +581,6 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) address = cpa->vaddr[cpa->curpage]; else address = *cpa->vaddr; - repeat: kpte = lookup_address(address, &level); if (!kpte) @@ -812,6 +817,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, vm_unmap_aliases(); + /* + * If we're called with lazy mmu updates enabled, the + * in-memory pte state may be stale. Flush pending updates to + * bring them up to date. + */ + arch_flush_lazy_mmu_mode(); + cpa.vaddr = addr; cpa.numpages = numpages; cpa.mask_set = mask_set; @@ -854,6 +866,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, } else cpa_flush_all(cache); + /* + * If we've been called with lazy mmu updates enabled, then + * make sure that everything gets flushed out before we + * return. + */ + arch_flush_lazy_mmu_mode(); + out: return ret; } diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 7b61036427d..e0ab173b697 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -11,6 +11,7 @@ #include <linux/bootmem.h> #include <linux/debugfs.h> #include <linux/kernel.h> +#include <linux/module.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/fs.h> @@ -211,6 +212,33 @@ chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type) static struct memtype *cached_entry; static u64 cached_start; +static int pat_pagerange_is_ram(unsigned long start, unsigned long end) +{ + int ram_page = 0, not_rampage = 0; + unsigned long page_nr; + + for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT); + ++page_nr) { + /* + * For legacy reasons, physical address range in the legacy ISA + * region is tracked as non-RAM. This will allow users of + * /dev/mem to map portions of legacy ISA region, even when + * some of those portions are listed(or not even listed) with + * different e820 types(RAM/reserved/..) + */ + if (page_nr >= (ISA_END_ADDRESS >> PAGE_SHIFT) && + page_is_ram(page_nr)) + ram_page = 1; + else + not_rampage = 1; + + if (ram_page == not_rampage) + return -1; + } + + return ram_page; +} + /* * For RAM pages, mark the pages as non WB memory type using * PageNonWB (PG_arch_1). We allow only one set_memory_uc() or @@ -336,20 +364,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (new_type) *new_type = actual_type; - /* - * For legacy reasons, some parts of the physical address range in the - * legacy 1MB region is treated as non-RAM (even when listed as RAM in - * the e820 tables). So we will track the memory attributes of this - * legacy 1MB region using the linear memtype_list always. - */ - if (end >= ISA_END_ADDRESS) { - is_range_ram = pagerange_is_ram(start, end); - if (is_range_ram == 1) - return reserve_ram_pages_type(start, end, req_type, - new_type); - else if (is_range_ram < 0) - return -EINVAL; - } + is_range_ram = pat_pagerange_is_ram(start, end); + if (is_range_ram == 1) + return reserve_ram_pages_type(start, end, req_type, + new_type); + else if (is_range_ram < 0) + return -EINVAL; new = kmalloc(sizeof(struct memtype), GFP_KERNEL); if (!new) @@ -446,19 +466,11 @@ int free_memtype(u64 start, u64 end) if (is_ISA_range(start, end - 1)) return 0; - /* - * For legacy reasons, some parts of the physical address range in the - * legacy 1MB region is treated as non-RAM (even when listed as RAM in - * the e820 tables). So we will track the memory attributes of this - * legacy 1MB region using the linear memtype_list always. - */ - if (end >= ISA_END_ADDRESS) { - is_range_ram = pagerange_is_ram(start, end); - if (is_range_ram == 1) - return free_ram_pages_type(start, end); - else if (is_range_ram < 0) - return -EINVAL; - } + is_range_ram = pat_pagerange_is_ram(start, end); + if (is_range_ram == 1) + return free_ram_pages_type(start, end); + else if (is_range_ram < 0) + return -EINVAL; spin_lock(&memtype_lock); list_for_each_entry(entry, &memtype_list, nd) { @@ -626,17 +638,13 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, unsigned long flags; unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); - is_ram = pagerange_is_ram(paddr, paddr + size); + is_ram = pat_pagerange_is_ram(paddr, paddr + size); - if (is_ram != 0) { - /* - * For mapping RAM pages, drivers need to call - * set_memory_[uc|wc|wb] directly, for reserve and free, before - * setting up the PTE. - */ - WARN_ON_ONCE(1); - return 0; - } + /* + * reserve_pfn_range() doesn't support RAM pages. + */ + if (is_ram != 0) + return -EINVAL; ret = reserve_memtype(paddr, paddr + size, want_flags, &flags); if (ret) @@ -693,7 +701,7 @@ static void free_pfn_range(u64 paddr, unsigned long size) { int is_ram; - is_ram = pagerange_is_ram(paddr, paddr + size); + is_ram = pat_pagerange_is_ram(paddr, paddr + size); if (is_ram == 0) free_memtype(paddr, paddr + size); } @@ -861,6 +869,7 @@ pgprot_t pgprot_writecombine(pgprot_t prot) else return pgprot_noncached(prot); } +EXPORT_SYMBOL_GPL(pgprot_writecombine); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index ab50a8d7402..427fd1b56df 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -1,5 +1,5 @@ /* - * Written by Pekka Paalanen, 2008 <pq@iki.fi> + * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi> */ #include <linux/module.h> #include <linux/io.h> @@ -9,35 +9,74 @@ static unsigned long mmio_address; module_param(mmio_address, ulong, 0); -MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB."); +MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB " + "(or 8 MB if read_far is non-zero)."); + +static unsigned long read_far = 0x400100; +module_param(read_far, ulong, 0); +MODULE_PARM_DESC(read_far, " Offset of a 32-bit read within 8 MB " + "(default: 0x400100)."); + +static unsigned v16(unsigned i) +{ + return i * 12 + 7; +} + +static unsigned v32(unsigned i) +{ + return i * 212371 + 13; +} static void do_write_test(void __iomem *p) { unsigned int i; + pr_info(MODULE_NAME ": write test.\n"); mmiotrace_printk("Write test.\n"); + for (i = 0; i < 256; i++) iowrite8(i, p + i); + for (i = 1024; i < (5 * 1024); i += 2) - iowrite16(i * 12 + 7, p + i); + iowrite16(v16(i), p + i); + for (i = (5 * 1024); i < (16 * 1024); i += 4) - iowrite32(i * 212371 + 13, p + i); + iowrite32(v32(i), p + i); } static void do_read_test(void __iomem *p) { unsigned int i; + unsigned errs[3] = { 0 }; + pr_info(MODULE_NAME ": read test.\n"); mmiotrace_printk("Read test.\n"); + for (i = 0; i < 256; i++) - ioread8(p + i); + if (ioread8(p + i) != i) + ++errs[0]; + for (i = 1024; i < (5 * 1024); i += 2) - ioread16(p + i); + if (ioread16(p + i) != v16(i)) + ++errs[1]; + for (i = (5 * 1024); i < (16 * 1024); i += 4) - ioread32(p + i); + if (ioread32(p + i) != v32(i)) + ++errs[2]; + + mmiotrace_printk("Read errors: 8-bit %d, 16-bit %d, 32-bit %d.\n", + errs[0], errs[1], errs[2]); } -static void do_test(void) +static void do_read_far_test(void __iomem *p) { - void __iomem *p = ioremap_nocache(mmio_address, 0x4000); + pr_info(MODULE_NAME ": read far test.\n"); + mmiotrace_printk("Read far test.\n"); + + ioread32(p + read_far); +} + +static void do_test(unsigned long size) +{ + void __iomem *p = ioremap_nocache(mmio_address, size); if (!p) { pr_err(MODULE_NAME ": could not ioremap, aborting.\n"); return; @@ -45,11 +84,15 @@ static void do_test(void) mmiotrace_printk("ioremap returned %p.\n", p); do_write_test(p); do_read_test(p); + if (read_far && read_far < size - 4) + do_read_far_test(p); iounmap(p); } static int __init init(void) { + unsigned long size = (read_far) ? (8 << 20) : (16 << 10); + if (mmio_address == 0) { pr_err(MODULE_NAME ": you have to use the module argument " "mmio_address.\n"); @@ -58,10 +101,11 @@ static int __init init(void) return -ENXIO; } - pr_warning(MODULE_NAME ": WARNING: mapping 16 kB @ 0x%08lx " - "in PCI address space, and writing " - "rubbish in there.\n", mmio_address); - do_test(); + pr_warning(MODULE_NAME ": WARNING: mapping %lu kB @ 0x%08lx in PCI " + "address space, and writing 16 kB of rubbish in there.\n", + size >> 10, mmio_address); + do_test(size); + pr_info(MODULE_NAME ": All done.\n"); return 0; } diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index e9f80c744cf..10131fbdaad 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -78,8 +78,18 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs) if (cpu_has_arch_perfmon) { union cpuid10_eax eax; eax.full = cpuid_eax(0xa); - if (counter_width < eax.split.bit_width) - counter_width = eax.split.bit_width; + + /* + * For Core2 (family 6, model 15), don't reset the + * counter width: + */ + if (!(eax.split.version_id == 0 && + current_cpu_data.x86 == 6 && + current_cpu_data.x86_model == 15)) { + + if (counter_width < eax.split.bit_width) + counter_width = eax.split.bit_width; + } } /* clear all counters */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bea215230b2..b58e9633814 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1672,6 +1672,9 @@ asmlinkage void __init xen_start_kernel(void) possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; + local_irq_disable(); + early_boot_irqs_off(); + xen_raw_console_write("mapping kernel into physical memory\n"); pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages); |