diff options
Diffstat (limited to 'arch/x86')
49 files changed, 858 insertions, 182 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cb9a1044a771..efb42949cc09 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -390,7 +390,7 @@ config X86_INTEL_CE This option compiles in support for the CE4100 SOC for settop boxes and media devices. -config X86_INTEL_MID +config X86_WANT_INTEL_MID bool "Intel MID platform support" depends on X86_32 depends on X86_EXTENDED_PLATFORM @@ -399,7 +399,10 @@ config X86_INTEL_MID systems which do not have the PCI legacy interfaces (Moorestown, Medfield). If you are building for a PC class system say N here. -if X86_INTEL_MID +if X86_WANT_INTEL_MID + +config X86_INTEL_MID + bool config X86_MRST bool "Moorestown MID platform" @@ -411,6 +414,7 @@ config X86_MRST select SPI select INTEL_SCU_IPC select X86_PLATFORM_DEVICES + select X86_INTEL_MID ---help--- Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin Internet Device(MID) platform. Moorestown consists of two chips: diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 9b7273cb2193..1a6c09af048f 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -49,6 +49,7 @@ extern unsigned int apic_verbosity; extern int local_apic_timer_c2_ok; extern int disable_apic; +extern unsigned int lapic_timer_frequency; #ifdef CONFIG_SMP extern void __inquire_remote_apic(int apicid); diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 078ad0caefc6..b903d5ea3941 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -101,6 +101,28 @@ extern void aout_dump_debugregs(struct user *dump); extern void hw_breakpoint_restore(void); +#ifdef CONFIG_X86_64 +DECLARE_PER_CPU(int, debug_stack_usage); +static inline void debug_stack_usage_inc(void) +{ + __get_cpu_var(debug_stack_usage)++; +} +static inline void debug_stack_usage_dec(void) +{ + __get_cpu_var(debug_stack_usage)--; +} +int is_debug_stack(unsigned long addr); +void debug_stack_set_zero(void); +void debug_stack_reset(void); +#else /* !X86_64 */ +static inline int is_debug_stack(unsigned long addr) { return 0; } +static inline void debug_stack_set_zero(void) { } +static inline void debug_stack_reset(void) { } +static inline void debug_stack_usage_inc(void) { } +static inline void debug_stack_usage_dec(void) { } +#endif /* X86_64 */ + + #endif /* __KERNEL__ */ #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 41935fadfdfc..e95822d683f4 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -35,6 +35,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in extern struct desc_ptr idt_descr; extern gate_desc idt_table[]; +extern struct desc_ptr nmi_idt_descr; +extern gate_desc nmi_idt_table[]; struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; @@ -307,6 +309,16 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) desc->limit = (limit >> 16) & 0xf; } +#ifdef CONFIG_X86_64 +static inline void set_nmi_gate(int gate, void *addr) +{ + gate_desc s; + + pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); + write_idt_entry(nmi_idt_table, gate, &s); +} +#endif + static inline void _set_gate(int gate, unsigned type, void *addr, unsigned dpl, unsigned ist, unsigned seg) { diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 4420993acc47..925b605eb5c6 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -3,11 +3,15 @@ #include <linux/notifier.h> -#define IPCMSG_VRTC 0xFA /* Set vRTC device */ - -/* Command id associated with message IPCMSG_VRTC */ -#define IPC_CMD_VRTC_SETTIME 1 /* Set time */ -#define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */ +#define IPCMSG_WARM_RESET 0xF0 +#define IPCMSG_COLD_RESET 0xF1 +#define IPCMSG_SOFT_RESET 0xF2 +#define IPCMSG_COLD_BOOT 0xF3 + +#define IPCMSG_VRTC 0xFA /* Set vRTC device */ + /* Command id associated with message IPCMSG_VRTC */ + #define IPC_CMD_VRTC_SETTIME 1 /* Set time */ + #define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */ /* Read single register */ int intel_scu_ipc_ioread8(u16 addr, u8 *data); diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h index 72a8b52e7dfd..a01e7ec7d237 100644 --- a/arch/x86/include/asm/mach_traps.h +++ b/arch/x86/include/asm/mach_traps.h @@ -17,7 +17,7 @@ #define NMI_REASON_CLEAR_IOCHK 0x08 #define NMI_REASON_CLEAR_MASK 0x0f -static inline unsigned char get_nmi_reason(void) +static inline unsigned char default_get_nmi_reason(void) { return inb(NMI_REASON_PORT); } diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c9321f34e55b..0e8ae57d3656 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -201,7 +201,10 @@ int mce_notify_irq(void); void mce_notify_process(void); DECLARE_PER_CPU(struct mce, injectm); -extern struct file_operations mce_chrdev_ops; + +extern void register_mce_write_callback(ssize_t (*)(struct file *filp, + const char __user *ubuf, + size_t usize, loff_t *off)); /* * Exception handler diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 719f00b28ff5..93f79094c224 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -31,11 +31,20 @@ enum mrst_cpu_type { }; extern enum mrst_cpu_type __mrst_cpu_chip; + +#ifdef CONFIG_X86_INTEL_MID + static inline enum mrst_cpu_type mrst_identify_cpu(void) { return __mrst_cpu_chip; } +#else /* !CONFIG_X86_INTEL_MID */ + +#define mrst_identify_cpu() (0) + +#endif /* !CONFIG_X86_INTEL_MID */ + enum mrst_timer_options { MRST_TIMER_DEFAULT, MRST_TIMER_APBT_ONLY, @@ -44,6 +53,13 @@ enum mrst_timer_options { extern enum mrst_timer_options mrst_timer_options; +/* + * Penwell uses spread spectrum clock, so the freq number is not exactly + * the same as reported by MSR based on SDM. + */ +#define PENWELL_FSB_FREQ_83SKU 83200 +#define PENWELL_FSB_FREQ_100SKU 99840 + #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 084ef95274cd..95203d40ffdd 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -169,7 +169,14 @@ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high) return native_write_msr_safe(msr, low, high); } -/* rdmsr with exception handling */ +/* + * rdmsr with exception handling. + * + * Please note that the exception handling works only after we've + * switched to the "smart" #GP handler in trap_init() which knows about + * exception tables - using this macro earlier than that causes machine + * hangs on boxes which do not implement the @msr in the first argument. + */ #define rdmsr_safe(msr, p1, p2) \ ({ \ int __err; \ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index b50e9d15aae0..096c975e099f 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -112,23 +112,24 @@ struct x86_pmu_capability { /* * All 3 fixed-mode PMCs are configured via this single MSR: */ -#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d +#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d /* * The counts are available in three separate MSRs: */ /* Instr_Retired.Any: */ -#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309 -#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0) +#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309 +#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0) /* CPU_CLK_Unhalted.Core: */ -#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a -#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1) +#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a +#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1) /* CPU_CLK_Unhalted.Ref: */ -#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b -#define X86_PMC_IDX_FIXED_BUS_CYCLES (X86_PMC_IDX_FIXED + 2) +#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b +#define X86_PMC_IDX_FIXED_REF_CYCLES (X86_PMC_IDX_FIXED + 2) +#define X86_PMC_MSK_FIXED_REF_CYCLES (1ULL << X86_PMC_IDX_FIXED_REF_CYCLES) /* * We model BTS tracing as another fixed-mode PMC. diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index c2ff2a1d845e..2d2f01ce6dcb 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -401,6 +401,7 @@ extern unsigned long arch_align_stack(unsigned long sp); extern void free_init_pages(char *what, unsigned long begin, unsigned long end); void default_idle(void); +bool set_pm_idle_to_default(void); void stop_this_cpu(void *dummy); diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index fa7b9176b76c..431793e5d484 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -32,6 +32,22 @@ extern int no_timer_check; * (mathieu.desnoyers@polymtl.ca) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" + * + * In: + * + * ns = cycles * cyc2ns_scale / SC + * + * Although we may still have enough bits to store the value of ns, + * in some cases, we may not have enough bits to store cycles * cyc2ns_scale, + * leading to an incorrect result. + * + * To avoid this, we can decompose 'cycles' into quotient and remainder + * of division by SC. Then, + * + * ns = (quot * SC + rem) * cyc2ns_scale / SC + * = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC + * + * - sqazi@google.com */ DECLARE_PER_CPU(unsigned long, cyc2ns); @@ -41,9 +57,14 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); static inline unsigned long long __cycles_2_ns(unsigned long long cyc) { + unsigned long long quot; + unsigned long long rem; int cpu = smp_processor_id(); unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR; + quot = (cyc >> CYC2NS_SCALE_FACTOR); + rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1); + ns += quot * per_cpu(cyc2ns, cpu) + + ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR); return ns; } diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index 10474fb1185d..cf1d73643f60 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -57,6 +57,7 @@ #define UV1_HUB_PART_NUMBER 0x88a5 #define UV2_HUB_PART_NUMBER 0x8eb8 +#define UV2_HUB_PART_NUMBER_X 0x1111 /* Compat: if this #define is present, UV headers support UV2 */ #define UV2_HUB_IS_SUPPORTED 1 diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index d3d859035af9..1971e652d24b 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -152,6 +152,7 @@ struct x86_cpuinit_ops { /** * struct x86_platform_ops - platform specific runtime functions * @calibrate_tsc: calibrate TSC + * @wallclock_init: init the wallclock device * @get_wallclock: get time from HW clock like RTC etc. * @set_wallclock: set time back to HW clock * @is_untracked_pat_range exclude from PAT logic @@ -160,11 +161,13 @@ struct x86_cpuinit_ops { */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); + void (*wallclock_init)(void); unsigned long (*get_wallclock)(void); int (*set_wallclock)(unsigned long nowtime); void (*iommu_shutdown)(void); bool (*is_untracked_pat_range)(u64 start, u64 end); void (*nmi_init)(void); + unsigned char (*get_nmi_reason)(void); int (*i8042_detect)(void); }; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c63822816249..1f84794f0759 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -738,5 +738,5 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) atomic_set(&stop_machine_first, 1); wrote_text = 0; - __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); + __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a2fd72e0ab35..f98d84caf94c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -186,7 +186,7 @@ static struct resource lapic_resource = { .flags = IORESOURCE_MEM | IORESOURCE_BUSY, }; -static unsigned int calibration_result; +unsigned int lapic_timer_frequency = 0; static void apic_pm_activate(void); @@ -454,7 +454,7 @@ static void lapic_timer_setup(enum clock_event_mode mode, switch (mode) { case CLOCK_EVT_MODE_PERIODIC: case CLOCK_EVT_MODE_ONESHOT: - __setup_APIC_LVTT(calibration_result, + __setup_APIC_LVTT(lapic_timer_frequency, mode != CLOCK_EVT_MODE_PERIODIC, 1); break; case CLOCK_EVT_MODE_UNUSED: @@ -638,6 +638,25 @@ static int __init calibrate_APIC_clock(void) long delta, deltatsc; int pm_referenced = 0; + /** + * check if lapic timer has already been calibrated by platform + * specific routine, such as tsc calibration code. if so, we just fill + * in the clockevent structure and return. + */ + + if (lapic_timer_frequency) { + apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", + lapic_timer_frequency); + lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, + TICK_NSEC, lapic_clockevent.shift); + lapic_clockevent.max_delta_ns = + clockevent_delta2ns(0x7FFFFF, &lapic_clockevent); + lapic_clockevent.min_delta_ns = + clockevent_delta2ns(0xF, &lapic_clockevent); + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY; + return 0; + } + local_irq_disable(); /* Replace the global interrupt handler */ @@ -679,12 +698,12 @@ static int __init calibrate_APIC_clock(void) lapic_clockevent.min_delta_ns = clockevent_delta2ns(0xF, &lapic_clockevent); - calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; + lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta); apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult); apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", - calibration_result); + lapic_timer_frequency); if (cpu_has_tsc) { apic_printk(APIC_VERBOSE, "..... CPU clock speed is " @@ -695,13 +714,13 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "..... host bus clock speed is " "%u.%04u MHz.\n", - calibration_result / (1000000 / HZ), - calibration_result % (1000000 / HZ)); + lapic_timer_frequency / (1000000 / HZ), + lapic_timer_frequency % (1000000 / HZ)); /* * Do a sanity check on the APIC calibration result */ - if (calibration_result < (1000000 / HZ)) { + if (lapic_timer_frequency < (1000000 / HZ)) { local_irq_enable(); pr_warning("APIC frequency too slow, disabling apic timer\n"); return -1; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 3c31fa98af6d..6d939d7847e2 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -193,10 +193,8 @@ int __init arch_early_irq_init(void) struct irq_cfg *cfg; int count, node, i; - if (!legacy_pic->nr_legacy_irqs) { - nr_irqs_gsi = 0; + if (!legacy_pic->nr_legacy_irqs) io_apic_irqs = ~0UL; - } for (i = 0; i < nr_ioapics; i++) { ioapics[i].saved_registers = @@ -1696,6 +1694,7 @@ __apicdebuginit(void) print_IO_APICs(void) int ioapic_idx; struct irq_cfg *cfg; unsigned int irq; + struct irq_chip *chip; printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) @@ -1716,6 +1715,10 @@ __apicdebuginit(void) print_IO_APICs(void) for_each_active_irq(irq) { struct irq_pin_list *entry; + chip = irq_get_chip(irq); + if (chip != &ioapic_chip) + continue; + cfg = irq_get_chip_data(irq); if (!cfg) continue; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 62ae3001ae02..9d59bbacd4e3 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -93,6 +93,8 @@ static int __init early_get_pnodeid(void) if (node_id.s.part_number == UV2_HUB_PART_NUMBER) uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1; + if (node_id.s.part_number == UV2_HUB_PART_NUMBER_X) + uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1; uv_hub_info->hub_revision = uv_min_hub_revision_id; pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c7e46cb35327..0bab2b18bb20 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -442,8 +442,6 @@ static void __cpuinit bsp_init_amd(struct cpuinfo_x86 *c) static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) { - u32 dummy; - early_init_amd_mc(c); /* @@ -473,12 +471,12 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); } #endif - - rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); } static void __cpuinit init_amd(struct cpuinfo_x86 *c) { + u32 dummy; + #ifdef CONFIG_SMP unsigned long long value; @@ -657,6 +655,8 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask); } } + + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index aa003b13a831..266e4649b1da 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1026,6 +1026,8 @@ __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; +struct desc_ptr nmi_idt_descr = { NR_VECTORS * 16 - 1, + (unsigned long) nmi_idt_table }; DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE); @@ -1090,6 +1092,26 @@ unsigned long kernel_eflags; */ DEFINE_PER_CPU(struct orig_ist, orig_ist); +static DEFINE_PER_CPU(unsigned long, debug_stack_addr); +DEFINE_PER_CPU(int, debug_stack_usage); + +int is_debug_stack(unsigned long addr) +{ + return __get_cpu_var(debug_stack_usage) || + (addr <= __get_cpu_var(debug_stack_addr) && + addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); +} + +void debug_stack_set_zero(void) +{ + load_idt((const struct desc_ptr *)&nmi_idt_descr); +} + +void debug_stack_reset(void) +{ + load_idt((const struct desc_ptr *)&idt_descr); +} + #else /* CONFIG_X86_64 */ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; @@ -1208,6 +1230,8 @@ void __cpuinit cpu_init(void) estacks += exception_stack_sizes[v]; oist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; + if (v == DEBUG_STACK-1) + per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks; } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 6199232161cf..319882ef848d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -208,7 +208,7 @@ static int inject_init(void) if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) return -ENOMEM; printk(KERN_INFO "Machine check injector initialized\n"); - mce_chrdev_ops.write = mce_write; + register_mce_write_callback(mce_write); register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify"); return 0; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 362056aefeb4..2af127d4c3d1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1634,16 +1634,35 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, } } -/* Modified in mce-inject.c, so not static or const */ -struct file_operations mce_chrdev_ops = { +static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off); + +void register_mce_write_callback(ssize_t (*fn)(struct file *filp, + const char __user *ubuf, + size_t usize, loff_t *off)) +{ + mce_write = fn; +} +EXPORT_SYMBOL_GPL(register_mce_write_callback); + +ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) +{ + if (mce_write) + return mce_write(filp, ubuf, usize, off); + else + return -EINVAL; +} + +static const struct file_operations mce_chrdev_ops = { .open = mce_chrdev_open, .release = mce_chrdev_release, .read = mce_chrdev_read, + .write = mce_chrdev_write, .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, .llseek = no_llseek, }; -EXPORT_SYMBOL_GPL(mce_chrdev_ops); static struct miscdevice mce_chrdev_device = { MISC_MCELOG_MINOR, diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index a71efcdbb092..97b26356e9ee 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -547,6 +547,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, if (tmp != mask_lo) { printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); + add_taint(TAINT_FIRMWARE_WORKAROUND); mask_lo = tmp; } } @@ -693,6 +694,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) /* Disable MTRRs, and set the default type to uncached */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi); + wbinvd(); } static void post_set(void) __releases(set_atomicity_lock) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 930fe4879542..5adce1040b11 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1304,9 +1304,15 @@ static int __init init_hw_perf_events(void) 0, x86_pmu.num_counters, 0); if (x86_pmu.event_constraints) { + /* + * event on fixed counter2 (REF_CYCLES) only works on this + * counter, so do not extend mask to generic counters + */ for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != X86_RAW_EVENT_MASK) + if (c->cmask != X86_RAW_EVENT_MASK + || c->idxmsk64 == X86_PMC_MSK_FIXED_REF_CYCLES) { continue; + } c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; c->weight += x86_pmu.num_counters; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 2c3bf53d0302..cbfaaa2475ea 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -28,6 +28,7 @@ static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly = [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, + [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */ }; static struct event_constraint intel_core_event_constraints[] __read_mostly = @@ -45,12 +46,7 @@ static struct event_constraint intel_core2_event_constraints[] __read_mostly = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ - /* - * Core2 has Fixed Counter 2 listed as CPU_CLK_UNHALTED.REF and event - * 0x013c as CPU_CLK_UNHALTED.BUS and specifies there is a fixed - * ratio between these counters. - */ - /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */ INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */ INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */ @@ -68,7 +64,7 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ - /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */ INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */ INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */ @@ -90,7 +86,7 @@ static struct event_constraint intel_westmere_event_constraints[] __read_mostly { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ - /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */ @@ -102,7 +98,7 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ - /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ @@ -125,7 +121,7 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ - /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index faf8d5e74b0b..b62aa298df7f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1475,62 +1475,214 @@ ENTRY(error_exit) CFI_ENDPROC END(error_exit) +/* + * Test if a given stack is an NMI stack or not. + */ + .macro test_in_nmi reg stack nmi_ret normal_ret + cmpq %\reg, \stack + ja \normal_ret + subq $EXCEPTION_STKSZ, %\reg + cmpq %\reg, \stack + jb \normal_ret + jmp \nmi_ret + .endm /* runs on exception stack */ ENTRY(nmi) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 + /* + * We allow breakpoints in NMIs. If a breakpoint occurs, then + * the iretq it performs will take us out of NMI context. + * This means that we can have nested NMIs where the next + * NMI is using the top of the stack of the previous NMI. We + * can't let it execute because the nested NMI will corrupt the + * stack of the previous NMI. NMI handlers are not re-entrant + * anyway. + * + * To handle this case we do the following: + * Check the a special location on the stack that contains + * a variable that is set when NMIs are executing. + * The interrupted task's stack is also checked to see if it + * is an NMI stack. + * If the variable is not set and the stack is not the NMI + * stack then: + * o Set the special variable on the stack + * o Copy the interrupt frame into a "saved" location on the stack + * o Copy the interrupt frame into a "copy" location on the stack + * o Continue processing the NMI + * If the variable is set or the previous stack is the NMI stack: + * o Modify the "copy" location to jump to the repeate_nmi + * o return back to the first NMI + * + * Now on exit of the first NMI, we first clear the stack variable + * The NMI stack will tell any nested NMIs at that point that it is + * nested. Then we pop the stack normally with iret, and if there was + * a nested NMI that updated the copy interrupt stack frame, a + * jump will be made to the repeat_nmi code that will handle the second + * NMI. + */ + + /* Use %rdx as out temp variable throughout */ + pushq_cfi %rdx + + /* + * Check the special variable on the stack to see if NMIs are + * executing. + */ + cmp $1, -8(%rsp) + je nested_nmi + + /* + * Now test if the previous stack was an NMI stack. + * We need the double check. We check the NMI stack to satisfy the + * race when the first NMI clears the variable before returning. + * We check the variable because the first NMI could be in a + * breakpoint routine using a breakpoint stack. + */ + lea 6*8(%rsp), %rdx + test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi + +nested_nmi: + /* + * Do nothing if we interrupted the fixup in repeat_nmi. + * It's about to repeat the NMI handler, so we are fine + * with ignoring this one. + */ + movq $repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja 1f + movq $end_repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja nested_nmi_out + +1: + /* Set up the interrupted NMIs stack to jump to repeat_nmi */ + leaq -6*8(%rsp), %rdx + movq %rdx, %rsp + CFI_ADJUST_CFA_OFFSET 6*8 + pushq_cfi $__KERNEL_DS + pushq_cfi %rdx + pushfq_cfi + pushq_cfi $__KERNEL_CS + pushq_cfi $repeat_nmi + + /* Put stack back */ + addq $(11*8), %rsp + CFI_ADJUST_CFA_OFFSET -11*8 + +nested_nmi_out: + popq_cfi %rdx + + /* No need to check faults here */ + INTERRUPT_RETURN + +first_nmi: + /* + * Because nested NMIs will use the pushed location that we + * stored in rdx, we must keep that space available. + * Here's what our stack frame will look like: + * +-------------------------+ + * | original SS | + * | original Return RSP | + * | original RFLAGS | + * | original CS | + * | original RIP | + * +-------------------------+ + * | temp storage for rdx | + * +-------------------------+ + * | NMI executing variable | + * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ + * | copied SS | + * | copied Return RSP | + * | copied RFLAGS | + * | copied CS | + * | copied RIP | + * +-------------------------+ + * | pt_regs | + * +-------------------------+ + * + * The saved RIP is used to fix up the copied RIP that a nested + * NMI may zero out. The original stack frame and the temp storage + * is also used by nested NMIs and can not be trusted on exit. + */ + /* Set the NMI executing variable on the stack. */ + pushq_cfi $1 + + /* Copy the stack frame to the Saved frame */ + .rept 5 + pushq_cfi 6*8(%rsp) + .endr + + /* Make another copy, this one may be modified by nested NMIs */ + .rept 5 + pushq_cfi 4*8(%rsp) + .endr + + /* Do not pop rdx, nested NMIs will corrupt it */ + movq 11*8(%rsp), %rdx + + /* + * Everything below this point can be preempted by a nested + * NMI if the first NMI took an exception. Repeated NMIs + * caused by an exception and nested NMI will start here, and + * can still be preempted by another NMI. + */ +restart_nmi: + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + /* + * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit + * as we should not be calling schedule in NMI context. + * Even with normal interrupts enabled. An NMI should not be + * setting NEED_RESCHED or anything that normal interrupts and + * exceptions might do. + */ call save_paranoid DEFAULT_FRAME 0 /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp,%rdi movq $-1,%rsi call do_nmi -#ifdef CONFIG_TRACE_IRQFLAGS - /* paranoidexit; without TRACE_IRQS_OFF */ - /* ebx: no swapgs flag */ - DISABLE_INTERRUPTS(CLBR_NONE) testl %ebx,%ebx /* swapgs needed? */ jnz nmi_restore - testl $3,CS(%rsp) - jnz nmi_userspace nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_ALL 8 + /* Clear the NMI executing stack variable */ + movq $0, 10*8(%rsp) jmp irq_return -nmi_userspace: - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%ebx - andl $_TIF_WORK_MASK,%ebx - jz nmi_swapgs - movq %rsp,%rdi /* &pt_regs */ - call sync_regs - movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx - jnz nmi_schedule - movl %ebx,%edx /* arg3: thread flags */ - ENABLE_INTERRUPTS(CLBR_NONE) - xorl %esi,%esi /* arg2: oldset */ - movq %rsp,%rdi /* arg1: &pt_regs */ - call do_notify_resume - DISABLE_INTERRUPTS(CLBR_NONE) - jmp nmi_userspace -nmi_schedule: - ENABLE_INTERRUPTS(CLBR_ANY) - call schedule - DISABLE_INTERRUPTS(CLBR_ANY) - jmp nmi_userspace - CFI_ENDPROC -#else - jmp paranoid_exit CFI_ENDPROC -#endif END(nmi) + /* + * If an NMI hit an iret because of an exception or breakpoint, + * it can lose its NMI context, and a nested NMI may come in. + * In that case, the nested NMI will change the preempted NMI's + * stack to jump to here when it does the final iret. + */ +repeat_nmi: + INTR_FRAME + /* Update the stack variable to say we are still in NMI */ + movq $1, 5*8(%rsp) + + /* copy the saved stack back to copy stack */ + .rept 5 + pushq_cfi 4*8(%rsp) + .endr + + jmp restart_nmi + CFI_ENDPROC +end_repeat_nmi: + ENTRY(ignore_sysret) CFI_STARTPROC mov $-ENOSYS,%eax diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index e11e39478a49..40f4eb3766d1 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -417,6 +417,10 @@ ENTRY(phys_base) ENTRY(idt_table) .skip IDT_ENTRIES * 16 + .align L1_CACHE_BYTES +ENTRY(nmi_idt_table) + .skip IDT_ENTRIES * 16 + __PAGE_ALIGNED_BSS .align PAGE_SIZE ENTRY(empty_zero_page) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index b946a9eac7d9..1bb0bf4d92cd 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1049,6 +1049,14 @@ int hpet_rtc_timer_init(void) } EXPORT_SYMBOL_GPL(hpet_rtc_timer_init); +static void hpet_disable_rtc_channel(void) +{ + unsigned long cfg; + cfg = hpet_readl(HPET_T1_CFG); + cfg &= ~HPET_TN_ENABLE; + hpet_writel(cfg, HPET_T1_CFG); +} + /* * The functions below are called from rtc driver. * Return 0 if HPET is not being used. @@ -1060,6 +1068,9 @@ int hpet_mask_rtc_irq_bit(unsigned long bit_mask) return 0; hpet_rtc_flags &= ~bit_mask; + if (unlikely(!hpet_rtc_flags)) + hpet_disable_rtc_channel(); + return 1; } EXPORT_SYMBOL_GPL(hpet_mask_rtc_irq_bit); @@ -1125,15 +1136,11 @@ EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq); static void hpet_rtc_timer_reinit(void) { - unsigned int cfg, delta; + unsigned int delta; int lost_ints = -1; - if (unlikely(!hpet_rtc_flags)) { - cfg = hpet_readl(HPET_T1_CFG); - cfg &= ~HPET_TN_ENABLE; - hpet_writel(cfg, HPET_T1_CFG); - return; - } + if (unlikely(!hpet_rtc_flags)) + hpet_disable_rtc_channel(); if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit) delta = hpet_default_delta; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index acf8fbf8fbda..69bca468c47a 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -38,6 +38,9 @@ static inline void stack_overflow_check(struct pt_regs *regs) #ifdef CONFIG_DEBUG_STACKOVERFLOW u64 curbase = (u64)task_stack_page(current); + if (user_mode_vm(regs)) + return; + WARN_ONCE(regs->sp >= curbase && regs->sp <= curbase + THREAD_SIZE && regs->sp < curbase + sizeof(struct thread_info) + diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index c1a0188e29ae..44842d756b29 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -74,9 +74,10 @@ static cycle_t kvm_clock_read(void) struct pvclock_vcpu_time_info *src; cycle_t ret; - src = &get_cpu_var(hv_clock); + preempt_disable_notrace(); + src = &__get_cpu_var(hv_clock); ret = pvclock_clocksource_read(src); - put_cpu_var(hv_clock); + preempt_enable_notrace(); return ret; } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index f2d2a664e797..9d46f5e43b51 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -256,7 +256,7 @@ static int __init microcode_dev_init(void) return 0; } -static void microcode_dev_exit(void) +static void __exit microcode_dev_exit(void) { misc_deregister(µcode_dev); } @@ -519,10 +519,8 @@ static int __init microcode_init(void) microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0); - if (IS_ERR(microcode_pdev)) { - microcode_dev_exit(); + if (IS_ERR(microcode_pdev)) return PTR_ERR(microcode_pdev); - } get_online_cpus(); mutex_lock(µcode_mutex); @@ -532,14 +530,12 @@ static int __init microcode_init(void) mutex_unlock(µcode_mutex); put_online_cpus(); - if (error) { - platform_device_unregister(microcode_pdev); - return error; - } + if (error) + goto out_pdev; error = microcode_dev_init(); if (error) - return error; + goto out_sysdev_driver; register_syscore_ops(&mc_syscore_ops); register_hotcpu_notifier(&mc_cpu_notifier); @@ -548,6 +544,20 @@ static int __init microcode_init(void) " <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n"); return 0; + +out_sysdev_driver: + get_online_cpus(); + mutex_lock(µcode_mutex); + + sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver); + + mutex_unlock(µcode_mutex); + put_online_cpus(); + +out_pdev: + platform_device_unregister(microcode_pdev); + return error; + } module_init(microcode_init); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 9103b89c145a..0741b062a304 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -95,8 +95,8 @@ static void __init MP_bus_info(struct mpc_bus *m) } #endif + set_bit(m->busid, mp_bus_not_pci); if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA) - 1) == 0) { - set_bit(m->busid, mp_bus_not_pci); #if defined(CONFIG_EISA) || defined(CONFIG_MCA) mp_bus_id_to_type[m->busid] = MP_BUS_ISA; #endif diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index b9c8628974af..47acaf319165 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -29,6 +29,7 @@ #include <asm/traps.h> #include <asm/mach_traps.h> #include <asm/nmi.h> +#include <asm/x86_init.h> #define NMI_MAX_NAMELEN 16 struct nmiaction { @@ -348,7 +349,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ raw_spin_lock(&nmi_reason_lock); - reason = get_nmi_reason(); + reason = x86_platform.get_nmi_reason(); if (reason & NMI_REASON_MASK) { if (reason & NMI_REASON_SERR) @@ -404,9 +405,108 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) unknown_nmi_error(reason, regs); } +/* + * NMIs can hit breakpoints which will cause it to lose its + * NMI context with the CPU when the breakpoint does an iret. + */ +#ifdef CONFIG_X86_32 +/* + * For i386, NMIs use the same stack as the kernel, and we can + * add a workaround to the iret problem in C. Simply have 3 states + * the NMI can be in. + * + * 1) not running + * 2) executing + * 3) latched + * + * When no NMI is in progress, it is in the "not running" state. + * When an NMI comes in, it goes into the "executing" state. + * Normally, if another NMI is triggered, it does not interrupt + * the running NMI and the HW will simply latch it so that when + * the first NMI finishes, it will restart the second NMI. + * (Note, the latch is binary, thus multiple NMIs triggering, + * when one is running, are ignored. Only one NMI is restarted.) + * + * If an NMI hits a breakpoint that executes an iret, another + * NMI can preempt it. We do not want to allow this new NMI + * to run, but we want to execute it when the first one finishes. + * We set the state to "latched", and the first NMI will perform + * an cmpxchg on the state, and if it doesn't successfully + * reset the state to "not running" it will restart the next + * NMI. + */ +enum nmi_states { + NMI_NOT_RUNNING, + NMI_EXECUTING, + NMI_LATCHED, +}; +static DEFINE_PER_CPU(enum nmi_states, nmi_state); + +#define nmi_nesting_preprocess(regs) \ + do { \ + if (__get_cpu_var(nmi_state) != NMI_NOT_RUNNING) { \ + __get_cpu_var(nmi_state) = NMI_LATCHED; \ + return; \ + } \ + nmi_restart: \ + __get_cpu_var(nmi_state) = NMI_EXECUTING; \ + } while (0) + +#define nmi_nesting_postprocess() \ + do { \ + if (cmpxchg(&__get_cpu_var(nmi_state), \ + NMI_EXECUTING, NMI_NOT_RUNNING) != NMI_EXECUTING) \ + goto nmi_restart; \ + } while (0) +#else /* x86_64 */ +/* + * In x86_64 things are a bit more difficult. This has the same problem + * where an NMI hitting a breakpoint that calls iret will remove the + * NMI context, allowing a nested NMI to enter. What makes this more + * difficult is that both NMIs and breakpoints have their own stack. + * When a new NMI or breakpoint is executed, the stack is set to a fixed + * point. If an NMI is nested, it will have its stack set at that same + * fixed address that the first NMI had, and will start corrupting the + * stack. This is handled in entry_64.S, but the same problem exists with + * the breakpoint stack. + * + * If a breakpoint is being processed, and the debug stack is being used, + * if an NMI comes in and also hits a breakpoint, the stack pointer + * will be set to the same fixed address as the breakpoint that was + * interrupted, causing that stack to be corrupted. To handle this case, + * check if the stack that was interrupted is the debug stack, and if + * so, change the IDT so that new breakpoints will use the current stack + * and not switch to the fixed address. On return of the NMI, switch back + * to the original IDT. + */ +static DEFINE_PER_CPU(int, update_debug_stack); + +static inline void nmi_nesting_preprocess(struct pt_regs *regs) +{ + /* + * If we interrupted a breakpoint, it is possible that + * the nmi handler will have breakpoints too. We need to + * change the IDT such that breakpoints that happen here + * continue to use the NMI stack. + */ + if (unlikely(is_debug_stack(regs->sp))) { + debug_stack_set_zero(); + __get_cpu_var(update_debug_stack) = 1; + } +} + +static inline void nmi_nesting_postprocess(void) +{ + if (unlikely(__get_cpu_var(update_debug_stack))) + debug_stack_reset(); +} +#endif + dotraplinkage notrace __kprobes void do_nmi(struct pt_regs *regs, long error_code) { + nmi_nesting_preprocess(regs); + nmi_enter(); inc_irq_stat(__nmi_count); @@ -415,6 +515,9 @@ do_nmi(struct pt_regs *regs, long error_code) default_do_nmi(regs); nmi_exit(); + + /* On i386, may loop back to preprocess */ + nmi_nesting_postprocess(); } void stop_nmi(void) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b9b3b1a51643..ee5d4fbd53b4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -403,6 +403,14 @@ void default_idle(void) EXPORT_SYMBOL(default_idle); #endif +bool set_pm_idle_to_default(void) +{ + bool ret = !!pm_idle; + + pm_idle = default_idle; + + return ret; +} void stop_this_cpu(void *dummy) { local_irq_disable(); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index b78643d0f9a5..03920a15a632 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -553,4 +553,17 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC, quirk_amd_nb_node); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK, quirk_amd_nb_node); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F0, + quirk_amd_nb_node); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F1, + quirk_amd_nb_node); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F2, + quirk_amd_nb_node); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3, + quirk_amd_nb_node); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4, + quirk_amd_nb_node); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5, + quirk_amd_nb_node); + #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index e334be1182b9..37a458b521a6 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -124,7 +124,7 @@ __setup("reboot=", reboot_setup); */ /* - * Some machines require the "reboot=b" commandline option, + * Some machines require the "reboot=b" or "reboot=k" commandline options, * this quirk makes that automatic. */ static int __init set_bios_reboot(const struct dmi_system_id *d) @@ -136,6 +136,15 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) return 0; } +static int __init set_kbd_reboot(const struct dmi_system_id *d) +{ + if (reboot_type != BOOT_KBD) { + reboot_type = BOOT_KBD; + printk(KERN_INFO "%s series board detected. Selecting KBD-method for reboot.\n", d->ident); + } + return 0; +} + static struct dmi_system_id __initdata reboot_dmi_table[] = { { /* Handle problems with rebooting on Dell E520's */ .callback = set_bios_reboot, @@ -295,7 +304,7 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, }, { /* Handle reboot issue on Acer Aspire one */ - .callback = set_bios_reboot, + .callback = set_kbd_reboot, .ident = "Acer Aspire One A110", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), @@ -443,6 +452,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"), }, }, + { /* Handle problems with rebooting on the OptiPlex 990. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), + }, + }, { } }; diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 348ce016a835..af6db6ec5b2a 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -12,6 +12,7 @@ #include <asm/vsyscall.h> #include <asm/x86_init.h> #include <asm/time.h> +#include <asm/mrst.h> #ifdef CONFIG_X86_32 /* @@ -242,6 +243,10 @@ static __init int add_rtc_cmos(void) if (of_have_populated_dt()) return 0; + /* Intel MID platforms don't have ioport rtc */ + if (mrst_identify_cpu()) + return -ENODEV; + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index afaf38447ef5..cf0ef986cb6d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1045,6 +1045,8 @@ void __init setup_arch(char **cmdline_p) x86_init.timers.wallclock_init(); + x86_platform.wallclock_init(); + mcheck_init(); arch_init_ideal_nops(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a8e3eb83466c..0072b38e3ea1 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -316,9 +316,15 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) return; #endif + /* + * Let others (NMI) know that the debug stack is in use + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); preempt_conditional_sti(regs); do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); preempt_conditional_cli(regs); + debug_stack_usage_dec(); } #ifdef CONFIG_X86_64 @@ -411,6 +417,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) SIGTRAP) == NOTIFY_STOP) return; + /* + * Let others (NMI) know that the debug stack is in use + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); + /* It's safe to allow irq's after DR6 has been saved */ preempt_conditional_sti(regs); @@ -418,6 +430,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); preempt_conditional_cli(regs); + debug_stack_usage_dec(); return; } @@ -437,6 +450,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); preempt_conditional_cli(regs); + debug_stack_usage_dec(); return; } @@ -723,4 +737,10 @@ void __init trap_init(void) cpu_init(); x86_init.irqs.trap_init(); + +#ifdef CONFIG_X86_64 + memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16); + set_nmi_gate(1, &debug); + set_nmi_gate(3, &int3); +#endif } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 6f164bd5e14d..c1d6cd549397 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -21,12 +21,14 @@ #include <asm/pat.h> #include <asm/tsc.h> #include <asm/iommu.h> +#include <asm/mach_traps.h> void __cpuinit x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } void __init x86_init_pgd_noop(pgd_t *unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } +void wallclock_init_noop(void) { } /* * The platform setup functions are preset with the default functions @@ -97,11 +99,13 @@ static int default_i8042_detect(void) { return 1; }; struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, + .wallclock_init = wallclock_init_noop, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, + .get_nmi_reason = default_get_nmi_reason, .i8042_detect = default_i8042_detect }; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a0d6bd9ad442..579a0b51696a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -39,6 +39,7 @@ #include <asm/mce.h> #include <asm/i387.h> #include <asm/xcr.h> +#include <asm/perf_event.h> #include "trace.h" @@ -118,7 +119,7 @@ module_param(ple_gap, int, S_IRUGO); static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, int, S_IRUGO); -#define NR_AUTOLOAD_MSRS 1 +#define NR_AUTOLOAD_MSRS 8 #define VMCS02_POOL_SIZE 1 struct vmcs { @@ -622,6 +623,7 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static bool cpu_has_load_ia32_efer; +static bool cpu_has_load_perf_global_ctrl; static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); @@ -1191,15 +1193,34 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +static void clear_atomic_switch_msr_special(unsigned long entry, + unsigned long exit) +{ + vmcs_clear_bits(VM_ENTRY_CONTROLS, entry); + vmcs_clear_bits(VM_EXIT_CONTROLS, exit); +} + static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) { unsigned i; struct msr_autoload *m = &vmx->msr_autoload; - if (msr == MSR_EFER && cpu_has_load_ia32_efer) { - vmcs_clear_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER); - vmcs_clear_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER); - return; + switch (msr) { + case MSR_EFER: + if (cpu_has_load_ia32_efer) { + clear_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER, + VM_EXIT_LOAD_IA32_EFER); + return; + } + break; + case MSR_CORE_PERF_GLOBAL_CTRL: + if (cpu_has_load_perf_global_ctrl) { + clear_atomic_switch_msr_special( + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); + return; + } + break; } for (i = 0; i < m->nr; ++i) @@ -1215,25 +1236,55 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); } +static void add_atomic_switch_msr_special(unsigned long entry, + unsigned long exit, unsigned long guest_val_vmcs, + unsigned long host_val_vmcs, u64 guest_val, u64 host_val) +{ + vmcs_write64(guest_val_vmcs, guest_val); + vmcs_write64(host_val_vmcs, host_val); + vmcs_set_bits(VM_ENTRY_CONTROLS, entry); + vmcs_set_bits(VM_EXIT_CONTROLS, exit); +} + static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, u64 guest_val, u64 host_val) { unsigned i; struct msr_autoload *m = &vmx->msr_autoload; - if (msr == MSR_EFER && cpu_has_load_ia32_efer) { - vmcs_write64(GUEST_IA32_EFER, guest_val); - vmcs_write64(HOST_IA32_EFER, host_val); - vmcs_set_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER); - vmcs_set_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER); - return; + switch (msr) { + case MSR_EFER: + if (cpu_has_load_ia32_efer) { + add_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER, + VM_EXIT_LOAD_IA32_EFER, + GUEST_IA32_EFER, + HOST_IA32_EFER, + guest_val, host_val); + return; + } + break; + case MSR_CORE_PERF_GLOBAL_CTRL: + if (cpu_has_load_perf_global_ctrl) { + add_atomic_switch_msr_special( + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL, + GUEST_IA32_PERF_GLOBAL_CTRL, + HOST_IA32_PERF_GLOBAL_CTRL, + guest_val, host_val); + return; + } + break; } for (i = 0; i < m->nr; ++i) if (m->guest[i].index == msr) break; - if (i == m->nr) { + if (i == NR_AUTOLOAD_MSRS) { + printk_once(KERN_WARNING"Not enough mst switch entries. " + "Can't add msr %x\n", msr); + return; + } else if (i == m->nr) { ++m->nr; vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); @@ -2455,6 +2506,42 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) && allow_1_setting(MSR_IA32_VMX_EXIT_CTLS, VM_EXIT_LOAD_IA32_EFER); + cpu_has_load_perf_global_ctrl = + allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS, + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) + && allow_1_setting(MSR_IA32_VMX_EXIT_CTLS, + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); + + /* + * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL + * but due to arrata below it can't be used. Workaround is to use + * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL. + * + * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32] + * + * AAK155 (model 26) + * AAP115 (model 30) + * AAT100 (model 37) + * BC86,AAY89,BD102 (model 44) + * BA97 (model 46) + * + */ + if (cpu_has_load_perf_global_ctrl && boot_cpu_data.x86 == 0x6) { + switch (boot_cpu_data.x86_model) { + case 26: + case 30: + case 37: + case 44: + case 46: + cpu_has_load_perf_global_ctrl = false; + printk_once(KERN_WARNING"kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + "does not work properly. Using workaround\n"); + break; + default: + break; + } + } + return 0; } @@ -5968,6 +6055,24 @@ static void vmx_cancel_injection(struct kvm_vcpu *vcpu) vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } +static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) +{ + int i, nr_msrs; + struct perf_guest_switch_msr *msrs; + + msrs = perf_guest_get_msrs(&nr_msrs); + + if (!msrs) + return; + + for (i = 0; i < nr_msrs; i++) + if (msrs[i].host == msrs[i].guest) + clear_atomic_switch_msr(vmx, msrs[i].msr); + else + add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest, + msrs[i].host); +} + #ifdef CONFIG_X86_64 #define R "r" #define Q "q" @@ -6017,6 +6122,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); + atomic_switch_perf_msrs(vmx); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index ea305856151c..dd74e46828c0 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -201,6 +201,8 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; + if (PageTail(page)) + get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index b49962662101..f4f29b19fac5 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -45,6 +45,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte-idx))); set_pte(kmap_pte-idx, mk_pte(page, prot)); + arch_flush_lazy_mmu_mode(); return (void *)vaddr; } @@ -88,6 +89,7 @@ void __kunmap_atomic(void *kvaddr) */ kpte_clear_flush(kmap_pte-idx, vaddr); kmap_atomic_idx_pop(); + arch_flush_lazy_mmu_mode(); } #ifdef CONFIG_DEBUG_HIGHMEM else { diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index e36bf714cb77..40e446941dd7 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -39,43 +39,14 @@ */ static unsigned long efi_rt_eflags; -static pgd_t efi_bak_pg_dir_pointer[2]; void efi_call_phys_prelog(void) { - unsigned long cr4; - unsigned long temp; struct desc_ptr gdt_descr; local_irq_save(efi_rt_eflags); - /* - * If I don't have PAE, I should just duplicate two entries in page - * directory. If I have PAE, I just need to duplicate one entry in - * page directory. - */ - cr4 = read_cr4_safe(); - - if (cr4 & X86_CR4_PAE) { - efi_bak_pg_dir_pointer[0].pgd = - swapper_pg_dir[pgd_index(0)].pgd; - swapper_pg_dir[0].pgd = - swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd; - } else { - efi_bak_pg_dir_pointer[0].pgd = - swapper_pg_dir[pgd_index(0)].pgd; - efi_bak_pg_dir_pointer[1].pgd = - swapper_pg_dir[pgd_index(0x400000)].pgd; - swapper_pg_dir[pgd_index(0)].pgd = - swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd; - temp = PAGE_OFFSET + 0x400000; - swapper_pg_dir[pgd_index(0x400000)].pgd = - swapper_pg_dir[pgd_index(temp)].pgd; - } - - /* - * After the lock is released, the original page table is restored. - */ + load_cr3(initial_page_table); __flush_tlb_all(); gdt_descr.address = __pa(get_cpu_gdt_table(0)); @@ -85,28 +56,13 @@ void efi_call_phys_prelog(void) void efi_call_phys_epilog(void) { - unsigned long cr4; struct desc_ptr gdt_descr; gdt_descr.address = (unsigned long)get_cpu_gdt_table(0); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); - cr4 = read_cr4_safe(); - - if (cr4 & X86_CR4_PAE) { - swapper_pg_dir[pgd_index(0)].pgd = - efi_bak_pg_dir_pointer[0].pgd; - } else { - swapper_pg_dir[pgd_index(0)].pgd = - efi_bak_pg_dir_pointer[0].pgd; - swapper_pg_dir[pgd_index(0x400000)].pgd = - efi_bak_pg_dir_pointer[1].pgd; - } - - /* - * After the lock is released, the original page table is restored. - */ + load_cr3(swapper_pg_dir); __flush_tlb_all(); local_irq_restore(efi_rt_eflags); diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 541020df0da6..ad4ec1cb097e 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -76,6 +76,20 @@ struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX]; EXPORT_SYMBOL_GPL(sfi_mrtc_array); int sfi_mrtc_num; +static void mrst_power_off(void) +{ + if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) + intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 1); +} + +static void mrst_reboot(void) +{ + if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) + intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); + else + intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0); +} + /* parse all the mtimer info to a static mtimer array */ static int __init sfi_parse_mtmr(struct sfi_table_header *table) { @@ -187,11 +201,34 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) static unsigned long __init mrst_calibrate_tsc(void) { unsigned long flags, fast_calibrate; - - local_irq_save(flags); - fast_calibrate = apbt_quick_calibrate(); - local_irq_restore(flags); - + if (__mrst_cpu_chip == MRST_CPU_CHIP_PENWELL) { + u32 lo, hi, ratio, fsb; + + rdmsr(MSR_IA32_PERF_STATUS, lo, hi); + pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi); + ratio = (hi >> 8) & 0x1f; + pr_debug("ratio is %d\n", ratio); + if (!ratio) { + pr_err("read a zero ratio, should be incorrect!\n"); + pr_err("force tsc ratio to 16 ...\n"); + ratio = 16; + } + rdmsr(MSR_FSB_FREQ, lo, hi); + if ((lo & 0x7) == 0x7) + fsb = PENWELL_FSB_FREQ_83SKU; + else + fsb = PENWELL_FSB_FREQ_100SKU; + fast_calibrate = ratio * fsb; + pr_debug("read penwell tsc %lu khz\n", fast_calibrate); + lapic_timer_frequency = fsb * 1000 / HZ; + /* mark tsc clocksource as reliable */ + set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE); + } else { + local_irq_save(flags); + fast_calibrate = apbt_quick_calibrate(); + local_irq_restore(flags); + } + if (fast_calibrate) return fast_calibrate; @@ -242,15 +279,15 @@ static int mrst_i8042_detect(void) return 0; } -/* Reboot and power off are handled by the SCU on a MID device */ -static void mrst_power_off(void) -{ - intel_scu_ipc_simple_command(0xf1, 1); -} - -static void mrst_reboot(void) +/* + * Moorestown does not have external NMI source nor port 0x61 to report + * NMI status. The possible NMI sources are from pmu as a result of NMI + * watchdog or lock debug. Reading io port 0x61 results in 0xff which + * misled NMI handler. + */ +static unsigned char mrst_get_nmi_reason(void) { - intel_scu_ipc_simple_command(0xf1, 0); + return 0; } /* @@ -274,6 +311,8 @@ void __init x86_mrst_early_setup(void) x86_platform.calibrate_tsc = mrst_calibrate_tsc; x86_platform.i8042_detect = mrst_i8042_detect; x86_init.timers.wallclock_init = mrst_rtc_init; + x86_platform.get_nmi_reason = mrst_get_nmi_reason; + x86_init.pci.init = pci_mrst_init; x86_init.pci.fixup_irqs = x86_init_noop; @@ -448,6 +487,46 @@ static void __init *max7315_platform_data(void *info) return max7315; } +static void *tca6416_platform_data(void *info) +{ + static struct pca953x_platform_data tca6416; + struct i2c_board_info *i2c_info = info; + int gpio_base, intr; + char base_pin_name[SFI_NAME_LEN + 1]; + char intr_pin_name[SFI_NAME_LEN + 1]; + + strcpy(i2c_info->type, "tca6416"); + strcpy(base_pin_name, "tca6416_base"); + strcpy(intr_pin_name, "tca6416_int"); + + gpio_base = get_gpio_by_name(base_pin_name); + intr = get_gpio_by_name(intr_pin_name); + + if (gpio_base == -1) + return NULL; + tca6416.gpio_base = gpio_base; + if (intr != -1) { + i2c_info->irq = intr + MRST_IRQ_OFFSET; + tca6416.irq_base = gpio_base + MRST_IRQ_OFFSET; + } else { + i2c_info->irq = -1; + tca6416.irq_base = -1; + } + return &tca6416; +} + +static void *mpu3050_platform_data(void *info) +{ + struct i2c_board_info *i2c_info = info; + int intr = get_gpio_by_name("mpu3050_int"); + + if (intr == -1) + return NULL; + + i2c_info->irq = intr + MRST_IRQ_OFFSET; + return NULL; +} + static void __init *emc1403_platform_data(void *info) { static short intr2nd_pdata; @@ -610,12 +689,15 @@ static void *msic_ocd_platform_data(void *info) static const struct devs_id __initconst device_ids[] = { {"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data}, {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data}, + {"pmic_gpio", SFI_DEV_TYPE_IPC, 1, &pmic_gpio_platform_data}, {"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data}, {"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data}, {"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data}, + {"tca6416", SFI_DEV_TYPE_I2C, 1, &tca6416_platform_data}, {"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data}, {"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data}, {"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data}, + {"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data}, /* MSIC subdevices */ {"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data}, diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index 118c143a9cb4..2c32df6fe231 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -11,7 +11,7 @@ #endif #define KSTK_EIP(tsk) KSTK_REG(tsk, HOST_IP) -#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_IP) +#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_SP) #define KSTK_EBP(tsk) KSTK_REG(tsk, HOST_BP) #define ARCH_IS_STACKGROW(address) \ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index da8afd576a6b..1f928659c338 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1356,7 +1356,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, int cpu = (long)hcpu; switch (action) { case CPU_UP_PREPARE: - per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + xen_vcpu_setup(cpu); if (xen_have_vector_callback) xen_init_lock_cpu(cpu); break; @@ -1386,7 +1386,6 @@ static void __init xen_hvm_guest_init(void) xen_hvm_smp_init(); register_cpu_notifier(&xen_hvm_cpu_notifier); xen_unplug_emulated_devices(); - have_vcpu_info_placement = 0; x86_init.irqs.intr_init = xen_init_IRQ; xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index 6bbfd7ac5e81..5a40d24ba331 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -71,7 +71,7 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, if (shared == NULL) { struct vm_struct *area = - alloc_vm_area(PAGE_SIZE * max_nr_gframes); + alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL); BUG_ON(area == NULL); shared = area->addr; *__shared = shared; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 38d0af4fefec..b2c7179fa263 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -173,9 +173,21 @@ static unsigned long __init xen_get_max_pages(void) domid_t domid = DOMID_SELF; int ret; - ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid); - if (ret > 0) - max_pages = ret; + /* + * For the initial domain we use the maximum reservation as + * the maximum page. + * + * For guest domains the current maximum reservation reflects + * the current maximum rather than the static maximum. In this + * case the e820 map provided to us will cover the static + * maximum region. + */ + if (xen_initial_domain()) { + ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid); + if (ret > 0) + max_pages = ret; + } + return min(max_pages, MAX_DOMAIN_PAGES); } @@ -410,6 +422,6 @@ void __init xen_arch_setup(void) #endif disable_cpuidle(); boot_option_idle_override = IDLE_HALT; - + WARN_ON(set_pm_idle_to_default()); fiddle_vdso(); } |
