diff options
Diffstat (limited to 'arch/x86')
66 files changed, 467 insertions, 278 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index fe361ae..52e18e6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,17 +26,10 @@ config X86 select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER -config DEFCONFIG_LIST +config ARCH_DEFCONFIG string - depends on X86_32 - option defconfig_list - default "arch/x86/configs/i386_defconfig" - -config DEFCONFIG_LIST - string - depends on X86_64 - option defconfig_list - default "arch/x86/configs/x86_64_defconfig" + default "arch/x86/configs/i386_defconfig" if X86_32 + default "arch/x86/configs/x86_64_defconfig" if X86_64 config GENERIC_LOCKBREAK @@ -1515,13 +1508,13 @@ config PCI_GOMMCONFIG config PCI_GODIRECT bool "Direct" -config PCI_GOANY - bool "Any" - config PCI_GOOLPC bool "OLPC" depends on OLPC +config PCI_GOANY + bool "Any" + endchoice config PCI_BIOS @@ -1538,9 +1531,8 @@ config PCI_MMCONFIG depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY) config PCI_OLPC - bool - depends on PCI && PCI_GOOLPC - default y + def_bool y + depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY) config PCI_DOMAINS def_bool y diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index ac1e31b..1836337 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -6,15 +6,19 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" config NONPROMISC_DEVMEM - bool "Disable promiscuous /dev/mem" + bool "Filter access to /dev/mem" help - The /dev/mem file by default only allows userspace access to PCI - space and the BIOS code and data regions. This is sufficient for - dosemu and X and all common users of /dev/mem. With this config - option, you allow userspace access to all of memory, including - kernel and userspace memory. Accidental access to this is - obviously disasterous, but specific access can be used by people - debugging the kernel. + If this option is left off, you allow userspace access to all + of memory, including kernel and userspace memory. Accidental + access to this is obviously disastrous, but specific access can + be used by people debugging the kernel. + + If this option is switched on, the /dev/mem file only allows + userspace access to PCI space and the BIOS code and data regions. + This is sufficient for dosemu and X and all common users of + /dev/mem. + + If in doubt, say Y. config EARLY_PRINTK bool "Early printk" if EMBEDDED diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c index 90943f8..e01aafd 100644 --- a/arch/x86/boot/a20.c +++ b/arch/x86/boot/a20.c @@ -115,8 +115,6 @@ static void enable_a20_fast(void) int enable_a20(void) { - int loops = A20_ENABLE_LOOPS; - #if defined(CONFIG_X86_ELAN) /* Elan croaks if we try to touch the KBC */ enable_a20_fast(); @@ -128,6 +126,7 @@ int enable_a20(void) enable_a20_kbc(); return 0; #else + int loops = A20_ENABLE_LOOPS; while (loops--) { /* First, check to see if A20 is already enabled (legacy free, etc.) */ diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c index c1d00c02..50e47cd 100644 --- a/arch/x86/boot/printf.c +++ b/arch/x86/boot/printf.c @@ -56,7 +56,7 @@ static char *number(char *str, long num, int base, int size, int precision, if (type & LEFT) type &= ~ZEROPAD; if (base < 2 || base > 36) - return 0; + return NULL; c = (type & ZEROPAD) ? '0' : ' '; sign = 0; if (type & SIGN) { diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index c49ebcc..33c5216 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -242,12 +242,19 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) static void __cpuinit acpi_register_lapic(int id, u8 enabled) { + unsigned int ver = 0; + if (!enabled) { ++disabled_cpus; return; } - generic_processor_info(id, 0); +#ifdef CONFIG_X86_32 + if (boot_cpu_physical_apicid != -1U) + ver = apic_version[boot_cpu_physical_apicid]; +#endif + + generic_processor_info(id, ver); } static int __init @@ -767,8 +774,13 @@ static void __init acpi_register_lapic_address(unsigned long address) mp_lapic_addr = address; set_fixmap_nocache(FIX_APIC_BASE, address); - if (boot_cpu_physical_apicid == -1U) + if (boot_cpu_physical_apicid == -1U) { boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id()); +#ifdef CONFIG_X86_32 + apic_version[boot_cpu_physical_apicid] = + GET_APIC_VERSION(apic_read(APIC_LVR)); +#endif + } } static int __init early_acpi_parse_madt_lapic_addr_ovr(void) diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S index 22fab6c..7da00b7 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S @@ -12,11 +12,6 @@ ENTRY(_start) SECTIONS { - . = HEADER_OFFSET; - .header : { - *(.header) - } - . = 0; .text : { *(.text*) @@ -50,6 +45,11 @@ SECTIONS __bss_end = .; } + . = HEADER_OFFSET; + .header : { + *(.header) + } + . = ALIGN(16); _end = .; diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 5910020..0633cfd 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -534,7 +534,7 @@ int setup_profiling_timer(unsigned int multiplier) */ void clear_local_APIC(void) { - int maxlvt = lapic_get_maxlvt(); + int maxlvt; u32 v; /* APIC hasn't been mapped yet */ diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c index af4a867..777a7ff 100644 --- a/arch/x86/kernel/cpu/cpufreq/longrun.c +++ b/arch/x86/kernel/cpu/cpufreq/longrun.c @@ -245,7 +245,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, if ((ecx > 95) || (ecx == 0) || (eax < ebx)) return -EIO; - edx = (eax - ebx) / (100 - ecx); + edx = ((eax - ebx) * 100) / (100 - ecx); *low_freq = edx * 1000; /* back to kHz */ dprintk("low frequency is %u kHz\n", *low_freq); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 46d4034..206791e 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1127,12 +1127,23 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) * an UP version, and is deprecated by AMD. */ if (num_online_cpus() != 1) { - printk(KERN_ERR PFX "MP systems not supported by PSB BIOS structure\n"); +#ifndef CONFIG_ACPI_PROCESSOR + printk(KERN_ERR PFX "ACPI Processor support is required " + "for SMP systems but is absent. Please load the " + "ACPI Processor module before starting this " + "driver.\n"); +#else + printk(KERN_ERR PFX "Your BIOS does not provide ACPI " + "_PSS objects in a way that Linux understands. " + "Please report this to the Linux ACPI maintainers" + " and complain to your BIOS vendor.\n"); +#endif kfree(data); return -ENODEV; } if (pol->cpu != 0) { - printk(KERN_ERR PFX "No _PSS objects for CPU other than CPU0\n"); + printk(KERN_ERR PFX "No ACPI _PSS objects for CPU other than " + "CPU0. Complain to your BIOS vendor.\n"); kfree(data); return -ENODEV; } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 2a609dc..c778e4f 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -248,6 +248,7 @@ ENTRY(resume_userspace) DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt # setting need_resched or sigpending # between sampling and the iret + TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx andl $_TIF_WORK_MASK, %ecx # is there any work to be done on # int/exception return? diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c index e8edd63..9b08e85 100644 --- a/arch/x86/kernel/geode_32.c +++ b/arch/x86/kernel/geode_32.c @@ -166,6 +166,8 @@ int geode_has_vsa2(void) static int has_vsa2 = -1; if (has_vsa2 == -1) { + u16 val; + /* * The VSA has virtual registers that we can query for a * signature. @@ -173,7 +175,8 @@ int geode_has_vsa2(void) outw(VSA_VR_UNLOCK, VSA_VRC_INDEX); outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX); - has_vsa2 = (inw(VSA_VRC_DATA) == VSA_SIG); + val = inw(VSA_VRC_DATA); + has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG); } return has_vsa2; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index b2cc737..f7357cc 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -189,7 +189,7 @@ default_entry: * this stage. */ -#define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */ +#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ xorl %ebx,%ebx /* %ebx is kept at zero */ diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index e03cc95..eb9ddd8 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -56,6 +56,11 @@ void __cpuinit mxcsr_feature_mask_init(void) void __init init_thread_xstate(void) { + if (!HAVE_HWFP) { + xstate_size = sizeof(struct i387_soft_struct); + return; + } + if (cpu_has_fxsr) xstate_size = sizeof(struct i387_fxsave_struct); #ifdef CONFIG_X86_32 @@ -94,7 +99,7 @@ void __cpuinit fpu_init(void) int init_fpu(struct task_struct *tsk) { if (tsk_used_math(tsk)) { - if (tsk == current) + if (HAVE_HWFP && tsk == current) unlazy_fpu(tsk); return 0; } @@ -109,6 +114,15 @@ int init_fpu(struct task_struct *tsk) return -ENOMEM; } +#ifdef CONFIG_X86_32 + if (!HAVE_HWFP) { + memset(tsk->thread.xstate, 0, xstate_size); + finit(); + set_stopped_child_used_math(tsk); + return 0; + } +#endif + if (cpu_has_fxsr) { struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave; @@ -330,13 +344,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; + if (!HAVE_HWFP) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, @@ -360,15 +374,15 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - if (!HAVE_HWFP) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - ret = init_fpu(target); if (ret) return ret; set_stopped_child_used_math(target); + if (!HAVE_HWFP) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + if (!cpu_has_fxsr) { return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fsave, 0, -1); @@ -474,18 +488,18 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf) int restore_i387_ia32(struct _fpstate_ia32 __user *buf) { int err; + struct task_struct *tsk = current; - if (HAVE_HWFP) { - struct task_struct *tsk = current; - + if (HAVE_HWFP) clear_fpu(tsk); - if (!used_math()) { - err = init_fpu(tsk); - if (err) - return err; - } + if (!used_math()) { + err = init_fpu(tsk); + if (err) + return err; + } + if (HAVE_HWFP) { if (cpu_has_fxsr) err = restore_i387_fxsave(buf); else diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c index 3d01e47..a4f93b4 100644 --- a/arch/x86/kernel/init_task.c +++ b/arch/x86/kernel/init_task.c @@ -11,7 +11,6 @@ #include <asm/desc.h> static struct fs_struct init_fs = INIT_FS; -static struct files_struct init_files = INIT_FILES; static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); struct mm_struct init_mm = INIT_MM(init_mm); diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index a40d54f..4dc8600d9 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -2130,14 +2130,10 @@ static inline void __init check_timer(void) { int apic1, pin1, apic2, pin2; int vector; - unsigned int ver; unsigned long flags; local_irq_save(flags); - ver = apic_read(APIC_LVR); - ver = GET_APIC_VERSION(ver); - /* * get/set the timer IRQ vector: */ @@ -2150,15 +2146,11 @@ static inline void __init check_timer(void) * mode for the 8259A whenever interrupts are routed * through I/O APICs. Also IRQ0 has to be enabled in * the 8259A which implies the virtual wire has to be - * disabled in the local APIC. Finally timer interrupts - * need to be acknowledged manually in the 8259A for - * timer_interrupt() and for the i82489DX when using - * the NMI watchdog. + * disabled in the local APIC. */ apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); - timer_ack = !cpu_has_tsc; - timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); + timer_ack = 1; if (timer_over_8254 > 0) enable_8259A_irq(0); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 4bc1be5..08a3098 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -53,7 +53,7 @@ static cycle_t kvm_clock_read(void); * have elapsed since the hypervisor wrote the data. So we try to account for * that with system time */ -unsigned long kvm_get_wallclock(void) +static unsigned long kvm_get_wallclock(void) { u32 wc_sec, wc_nsec; u64 delta; @@ -86,7 +86,7 @@ unsigned long kvm_get_wallclock(void) return ts.tv_sec + 1; } -int kvm_set_wallclock(unsigned long now) +static int kvm_set_wallclock(unsigned long now) { return 0; } diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 3cad17f..07c0f82 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -155,6 +155,7 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable) wrmsr(msr, value, dummy); return 0; } +EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event); int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable) { @@ -222,6 +223,7 @@ int geode_mfgpt_alloc_timer(int timer, int domain) /* No timers available - too bad */ return -1; } +EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer); #ifdef CONFIG_GEODE_MFGPT_TIMER diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c index 11b14bb..84160f7 100644 --- a/arch/x86/kernel/nmi_32.c +++ b/arch/x86/kernel/nmi_32.c @@ -26,7 +26,6 @@ #include <asm/smp.h> #include <asm/nmi.h> -#include <asm/timer.h> #include "mach_traps.h" @@ -82,7 +81,7 @@ int __init check_nmi_watchdog(void) prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL); if (!prev_nmi_count) - goto error; + return -1; printk(KERN_INFO "Testing NMI watchdog ... "); @@ -119,7 +118,7 @@ int __init check_nmi_watchdog(void) if (!atomic_read(&nmi_active)) { kfree(prev_nmi_count); atomic_set(&nmi_active, -1); - goto error; + return -1; } printk("OK.\n"); @@ -130,10 +129,6 @@ int __init check_nmi_watchdog(void) kfree(prev_nmi_count); return 0; -error: - timer_ack = !cpu_has_tsc; - - return -1; } static int __init setup_nmi_watchdog(char *str) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 0c37f16..dc00a13 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -378,6 +378,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, struct page *page; unsigned long dma_mask = 0; dma_addr_t bus; + int noretry = 0; /* ignore region specifiers */ gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); @@ -385,30 +386,37 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &memory)) return memory; - if (!dev) + if (!dev) { dev = &fallback_dev; + gfp |= GFP_DMA; + } dma_mask = dev->coherent_dma_mask; if (dma_mask == 0) - dma_mask = DMA_32BIT_MASK; + dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK; /* Device not DMA able */ if (dev->dma_mask == NULL) return NULL; - /* Don't invoke OOM killer */ - gfp |= __GFP_NORETRY; + /* Don't invoke OOM killer or retry in lower 16MB DMA zone */ + if (gfp & __GFP_DMA) + noretry = 1; #ifdef CONFIG_X86_64 /* Why <=? Even when the mask is smaller than 4GB it is often larger than 16MB and in this case we have a chance of finding fitting memory in the next higher zone first. If not retry with true GFP_DMA. -AK */ - if (dma_mask <= DMA_32BIT_MASK) + if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) { gfp |= GFP_DMA32; + if (dma_mask < DMA_32BIT_MASK) + noretry = 1; + } #endif again: - page = dma_alloc_pages(dev, gfp, get_order(size)); + page = dma_alloc_pages(dev, + noretry ? gfp | __GFP_NORETRY : gfp, get_order(size)); if (page == NULL) return NULL; diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index c07455d..aa8ec92 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -26,6 +26,7 @@ #include <linux/kdebug.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> +#include <linux/sysdev.h> #include <asm/atomic.h> #include <asm/io.h> #include <asm/mtrr.h> @@ -548,6 +549,28 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size) return aper_base; } +static int gart_resume(struct sys_device *dev) +{ + return 0; +} + +static int gart_suspend(struct sys_device *dev, pm_message_t state) +{ + return -EINVAL; +} + +static struct sysdev_class gart_sysdev_class = { + .name = "gart", + .suspend = gart_suspend, + .resume = gart_resume, + +}; + +static struct sys_device device_gart = { + .id = 0, + .cls = &gart_sysdev_class, +}; + /* * Private Northbridge GATT initialization in case we cannot use the * AGP driver for some reason. @@ -558,7 +581,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info) unsigned aper_base, new_aper_base; struct pci_dev *dev; void *gatt; - int i; + int i, error; printk(KERN_INFO "PCI-DMA: Disabling AGP.\n"); aper_size = aper_base = info->aper_size = 0; @@ -606,6 +629,12 @@ static __init int init_k8_gatt(struct agp_kern_info *info) pci_write_config_dword(dev, 0x90, ctl); } + + error = sysdev_class_register(&gart_sysdev_class); + if (!error) + error = sysdev_register(&device_gart); + if (error) + panic("Could not register gart_sysdev -- would corrupt data on next suspend"); flush_gart(); printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n", diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 67e9b4a..ba370dc 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -99,15 +99,6 @@ static void mwait_idle(void) local_irq_enable(); } - -static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) -{ - if (force_mwait) - return 1; - /* Any C1 states supported? */ - return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0; -} - /* * On SMP it's slightly faster (but much more power-consuming!) * to poll the ->work.need_resched flag instead of waiting for the @@ -119,6 +110,33 @@ static void poll_idle(void) cpu_relax(); } +/* + * mwait selection logic: + * + * It depends on the CPU. For AMD CPUs that support MWAIT this is + * wrong. Family 0x10 and 0x11 CPUs will enter C1 on HLT. Powersavings + * then depend on a clock divisor and current Pstate of the core. If + * all cores of a processor are in halt state (C1) the processor can + * enter the C1E (C1 enhanced) state. If mwait is used this will never + * happen. + * + * idle=mwait overrides this decision and forces the usage of mwait. + */ +static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) +{ + if (force_mwait) + return 1; + + if (c->x86_vendor == X86_VENDOR_AMD) { + switch(c->x86) { + case 0x10: + case 0x11: + return 0; + } + } + return 1; +} + void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { static int selected; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index f8476df..e2db9ac 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -333,6 +333,7 @@ void flush_thread(void) /* * Forget coprocessor state.. */ + tsk->fpu_counter = 0; clear_fpu(tsk); clear_used_math(); } @@ -649,8 +650,11 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct /* If the task has used fpu the last 5 timeslices, just do a full * restore of the math state immediately to avoid the trap; the * chances of needing FPU soon are obviously high now + * + * tsk_used_math() checks prevent calling math_state_restore(), + * which can sleep in the case of !tsk_used_math() */ - if (next_p->fpu_counter > 5) + if (tsk_used_math(next_p) && next_p->fpu_counter > 5) math_state_restore(); /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e2319f3..c6eb5c9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -294,6 +294,7 @@ void flush_thread(void) /* * Forget coprocessor state.. */ + tsk->fpu_counter = 0; clear_fpu(tsk); clear_used_math(); } @@ -658,8 +659,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* If the task has used fpu the last 5 timeslices, just do a full * restore of the math state immediately to avoid the trap; the * chances of needing FPU soon are obviously high now + * + * tsk_used_math() checks prevent calling math_state_restore(), + * which can sleep in the case of !tsk_used_math() */ - if (next_p->fpu_counter>5) + if (tsk_used_math(next_p) && next_p->fpu_counter > 5) math_state_restore(); return prev_p; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index fb03ef3..a7835f2 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1303,6 +1303,9 @@ static const struct user_regset_view user_x86_64_view = { #define genregs32_get genregs_get #define genregs32_set genregs_set +#define user_i387_ia32_struct user_i387_struct +#define user32_fxsr_struct user_fxsr_struct + #endif /* CONFIG_X86_64 */ #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION @@ -1315,13 +1318,13 @@ static const struct user_regset x86_32_regsets[] = { }, [REGSET_FP] = { .core_note_type = NT_PRFPREG, - .n = sizeof(struct user_i387_struct) / sizeof(u32), + .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = fpregs_active, .get = fpregs_get, .set = fpregs_set }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, - .n = sizeof(struct user_i387_struct) / sizeof(u32), + .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set }, diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 9615eee..05191bb 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -4,6 +4,8 @@ #include <linux/acpi.h> #include <linux/bcd.h> #include <linux/mc146818rtc.h> +#include <linux/platform_device.h> +#include <linux/pnp.h> #include <asm/time.h> #include <asm/vsyscall.h> @@ -197,3 +199,35 @@ unsigned long long native_read_tsc(void) } EXPORT_SYMBOL(native_read_tsc); + +static struct resource rtc_resources[] = { + [0] = { + .start = RTC_PORT(0), + .end = RTC_PORT(1), + .flags = IORESOURCE_IO, + }, + [1] = { + .start = RTC_IRQ, + .end = RTC_IRQ, + .flags = IORESOURCE_IRQ, + } +}; + +static struct platform_device rtc_device = { + .name = "rtc_cmos", + .id = -1, + .resource = rtc_resources, + .num_resources = ARRAY_SIZE(rtc_resources), +}; + +static __init int add_rtc_cmos(void) +{ +#ifdef CONFIG_PNP + if (!pnp_platform_devices) + platform_device_register(&rtc_device); +#else + platform_device_register(&rtc_device); +#endif /* CONFIG_PNP */ + return 0; +} +device_initcall(add_rtc_cmos); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c0c68c1..6f80b85 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -12,6 +12,7 @@ #include <asm/mpspec.h> #include <asm/apicdef.h> +#ifdef CONFIG_X86_LOCAL_APIC unsigned int num_processors; unsigned disabled_cpus __cpuinitdata; /* Processor that is doing the boot up */ @@ -23,8 +24,9 @@ EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid); /* Bitmask of physically existing CPUs */ physid_mask_t phys_cpu_present_map; +#endif -#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_SMP) +#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP) /* * Copy data used in early init routines from the initial arrays to the * per cpu data areas. These arrays then become expendable and the diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c index 2c5f8b2..5a2f8e0 100644 --- a/arch/x86/kernel/setup_32.c +++ b/arch/x86/kernel/setup_32.c @@ -532,10 +532,16 @@ static void __init reserve_crashkernel(void) (unsigned long)(crash_size >> 20), (unsigned long)(crash_base >> 20), (unsigned long)(total_mem >> 20)); + + if (reserve_bootmem(crash_base, crash_size, + BOOTMEM_EXCLUSIVE) < 0) { + printk(KERN_INFO "crashkernel reservation " + "failed - memory is in use\n"); + return; + } + crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; - reserve_bootmem(crash_base, crash_size, - BOOTMEM_DEFAULT); } else printk(KERN_INFO "crashkernel reservation failed - " "you have to specify a base address\n"); diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index f2fc8fe..6dff128 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -951,7 +951,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) { if (c->x86 == 0x6 && c->x86_model >= 0xf) - set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability); + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); } static void __cpuinit init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 8f75893..0cb7aad 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -231,7 +231,8 @@ native_smp_call_function_mask(cpumask_t mask, wmb(); /* Send a message to other CPUs */ - if (cpus_equal(mask, allbutself)) + if (cpus_equal(mask, allbutself) && + cpus_equal(cpu_online_map, cpu_callout_map)) send_IPI_allbutself(CALL_FUNCTION_VECTOR); else send_IPI_mask(mask, CALL_FUNCTION_VECTOR); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6b087ab..56078d6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -86,6 +86,7 @@ void *x86_bios_cpu_apicid_early_ptr; #ifdef CONFIG_X86_32 u8 apicid_2_node[MAX_APICID]; +static int low_mappings; #endif /* State of each CPU */ @@ -326,6 +327,12 @@ static void __cpuinit start_secondary(void *unused) enable_8259A_irq(0); } +#ifdef CONFIG_X86_32 + while (low_mappings) + cpu_relax(); + __flush_tlb_all(); +#endif + /* This must be done before setting cpu_online_map */ set_cpu_sibling_map(raw_smp_processor_id()); wmb(); @@ -1040,14 +1047,20 @@ int __cpuinit native_cpu_up(unsigned int cpu) #ifdef CONFIG_X86_32 /* init low mem mapping */ clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); + min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); flush_tlb_all(); -#endif + low_mappings = 1; + + err = do_boot_cpu(apicid, cpu); + zap_low_mappings(); + low_mappings = 0; +#else err = do_boot_cpu(apicid, cpu); - if (err < 0) { +#endif + if (err) { Dprintk("do_boot_cpu failed %d\n", err); - return err; + return -EIO; } /* @@ -1177,6 +1190,7 @@ static void __init smp_cpu_index_default(void) */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { + preempt_disable(); nmi_watchdog_default(); smp_cpu_index_default(); current_cpu_data = boot_cpu_data; @@ -1193,7 +1207,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) if (smp_sanity_check(max_cpus) < 0) { printk(KERN_INFO "SMP disabled\n"); disable_smp(); - return; + goto out; } preempt_disable(); @@ -1233,6 +1247,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) printk(KERN_INFO "CPU%d: ", 0); print_cpu_info(&cpu_data(0)); setup_boot_clock(); +out: + preempt_enable(); } /* * Early setup to make printk work. @@ -1259,9 +1275,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus) setup_ioapic_dest(); #endif check_nmi_watchdog(); -#ifdef CONFIG_X86_32 - zap_low_mappings(); -#endif } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c index bde6f63..08d752d 100644 --- a/arch/x86/kernel/traps_32.c +++ b/arch/x86/kernel/traps_32.c @@ -544,6 +544,7 @@ vm86_trap: #define DO_ERROR(trapnr, signr, str, name) \ void do_##name(struct pt_regs *regs, long error_code) \ { \ + trace_hardirqs_fixup(); \ if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ == NOTIFY_STOP) \ return; \ diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index e479072..65b7063 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -14,7 +14,10 @@ #include "mach_timer.h" -static int tsc_enabled; +/* native_sched_clock() is called before tsc_init(), so + we must start with the TSC soft disabled to prevent + erroneous rdtsc usage on !cpu_has_tsc processors */ +static int tsc_disabled = -1; /* * On some systems the TSC frequency does not @@ -28,8 +31,8 @@ EXPORT_SYMBOL_GPL(tsc_khz); static int __init tsc_setup(char *str) { printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC completely.\n"); - mark_tsc_unstable("user disabled TSC"); + "cannot disable TSC completely.\n"); + tsc_disabled = 1; return 1; } #else @@ -120,7 +123,7 @@ unsigned long long native_sched_clock(void) * very important for it to be as fast as the platform * can achive it. ) */ - if (unlikely(!tsc_enabled && !tsc_unstable)) + if (unlikely(tsc_disabled)) /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); @@ -322,7 +325,6 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; - tsc_enabled = 0; printk("Marking TSC unstable due to: %s.\n", reason); /* Can be called before registration */ if (clocksource_tsc.mult) @@ -336,7 +338,7 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable); static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d) { printk(KERN_NOTICE "%s detected: marking TSC unstable.\n", - d->ident); + d->ident); tsc_unstable = 1; return 0; } @@ -403,7 +405,7 @@ void __init tsc_init(void) { int cpu; - if (!cpu_has_tsc) + if (!cpu_has_tsc || tsc_disabled > 0) return; cpu_khz = calculate_cpu_khz(); @@ -414,6 +416,9 @@ void __init tsc_init(void) return; } + /* now allow native_sched_clock() to use rdtsc */ + tsc_disabled = 0; + printk("Detected %lu.%03lu MHz processor.\n", (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); @@ -441,8 +446,6 @@ void __init tsc_init(void) if (check_tsc_unstable()) { clocksource_tsc.rating = 0; clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; - } else - tsc_enabled = 1; - + } clocksource_register(&clocksource_tsc); } diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c index fcc16e5..1784b80 100644 --- a/arch/x86/kernel/tsc_64.c +++ b/arch/x86/kernel/tsc_64.c @@ -227,14 +227,14 @@ void __init tsc_calibrate(void) /* hpet or pmtimer available ? */ if (!hpet && !pm1 && !pm2) { printk(KERN_INFO "TSC calibrated against PIT\n"); - return; + goto out; } /* Check, whether the sampling was disturbed by an SMI */ if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) { printk(KERN_WARNING "TSC calibration disturbed by SMI, " "using PIT calibration result\n"); - return; + goto out; } tsc2 = (tsc2 - tsc1) * 1000000L; @@ -255,6 +255,7 @@ void __init tsc_calibrate(void) tsc_khz = tsc2 / tsc1; +out: for_each_possible_cpu(cpu) set_cyc2ns_scale(tsc_khz, cpu); } diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 58882f9..f6c05d0 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -2,6 +2,7 @@ All C exports should go in the respective C files. */ #include <linux/module.h> +#include <net/checksum.h> #include <linux/smp.h> #include <asm/processor.h> @@ -29,6 +30,8 @@ EXPORT_SYMBOL(__copy_from_user_inatomic); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); +EXPORT_SYMBOL(csum_partial); + /* * Export string functions. We normally rely on gcc builtin for most of these, * but gcc sometimes decides not to inline them. diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 3324d90..f2f5d26 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -200,7 +200,6 @@ int __pit_timer_fn(struct kvm_kpit_state *ps) atomic_inc(&pt->pending); smp_mb__after_atomic_inc(); - /* FIXME: handle case where the guest is in guest mode */ if (vcpu0 && waitqueue_active(&vcpu0->wq)) { vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE; wake_up_interruptible(&vcpu0->wq); @@ -216,7 +215,7 @@ int pit_has_pending_timer(struct kvm_vcpu *vcpu) { struct kvm_pit *pit = vcpu->kvm->arch.vpit; - if (pit && vcpu->vcpu_id == 0) + if (pit && vcpu->vcpu_id == 0 && pit->pit_state.inject_pending) return atomic_read(&pit->pit_state.pit_timer.pending); return 0; @@ -237,6 +236,19 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } +void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_pit *pit = vcpu->kvm->arch.vpit; + struct hrtimer *timer; + + if (vcpu->vcpu_id != 0 || !pit) + return; + + timer = &pit->pit_state.pit_timer.timer; + if (hrtimer_cancel(timer)) + hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); +} + static void destroy_pit_timer(struct kvm_kpit_timer *pt) { pr_debug("pit: execute del timer!\n"); diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index ce1f583..76d736b 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -94,3 +94,9 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int 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); + __kvm_migrate_pit_timer(vcpu); +} diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 1802134..2a15be2 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -84,6 +84,8 @@ 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_migrate_apic_timer(struct kvm_vcpu *vcpu); +void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu); +void __kvm_migrate_timers(struct kvm_vcpu *vcpu); int pit_has_pending_timer(struct kvm_vcpu *vcpu); int apic_has_pending_timer(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 36809d7..c297c50 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -957,7 +957,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *lapic = vcpu->arch.apic; - if (lapic) + if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT)) return atomic_read(&lapic->timer.pending); return 0; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 36c5406..ee3f530 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -658,7 +658,7 @@ static int is_empty_shadow_page(u64 *spt) u64 *end; for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) - if (*pos != shadow_trap_nonpresent_pte) { + if (is_shadow_present_pte(*pos)) { printk(KERN_ERR "%s: %p %llx\n", __func__, pos, *pos); return 0; @@ -1858,6 +1858,7 @@ static void free_mmu_pages(struct kvm_vcpu *vcpu) sp = container_of(vcpu->kvm->arch.active_mmu_pages.next, struct kvm_mmu_page, link); kvm_mmu_zap_page(vcpu->kvm, sp); + cond_resched(); } free_page((unsigned long)vcpu->arch.mmu.pae_root); } @@ -1996,7 +1997,7 @@ static struct shrinker mmu_shrinker = { .seeks = DEFAULT_SEEKS * 10, }; -void mmu_destroy_caches(void) +static void mmu_destroy_caches(void) { if (pte_chain_cache) kmem_cache_destroy(pte_chain_cache); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 156fe10..934c7b6 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -418,7 +418,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, /* mmio */ if (is_error_pfn(pfn)) { - pgprintk("gfn %x is mmio\n", walker.gfn); + pgprintk("gfn %lx is mmio\n", walker.gfn); kvm_release_pfn_clean(pfn); return 1; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ab22615..6b0d5fa 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -688,7 +688,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) delta = vcpu->arch.host_tsc - tsc_this; svm->vmcb->control.tsc_offset += delta; vcpu->cpu = cpu; - kvm_migrate_apic_timer(vcpu); + kvm_migrate_timers(vcpu); } for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bfe4db1..02efbe7 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -608,7 +608,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (vcpu->cpu != cpu) { vcpu_clear(vmx); - kvm_migrate_apic_timer(vcpu); + kvm_migrate_timers(vcpu); vpid_sync_vcpu_all(vmx); } @@ -1036,6 +1036,7 @@ static void hardware_enable(void *garbage) static void hardware_disable(void *garbage) { asm volatile (ASM_VMX_VMXOFF : : : "cc"); + write_cr4(read_cr4() & ~X86_CR4_VMXE); } static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 21338bd..00acf13 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2758,7 +2758,7 @@ again: if (vcpu->requests) { if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) - __kvm_migrate_apic_timer(vcpu); + __kvm_migrate_timers(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index f2a696d..932f216 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -677,8 +677,9 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, c->use_modrm_ea = 1; if (c->modrm_mod == 3) { - c->modrm_val = *(unsigned long *) - decode_register(c->modrm_rm, c->regs, c->d & ByteOp); + c->modrm_ptr = decode_register(c->modrm_rm, + c->regs, c->d & ByteOp); + c->modrm_val = *(unsigned long *)c->modrm_ptr; return rc; } @@ -1005,6 +1006,7 @@ done_prefixes: if ((c->d & ModRM) && c->modrm_mod == 3) { c->src.type = OP_REG; c->src.val = c->modrm_val; + c->src.ptr = c->modrm_ptr; break; } c->src.type = OP_MEM; @@ -1049,6 +1051,7 @@ done_prefixes: if ((c->d & ModRM) && c->modrm_mod == 3) { c->dst.type = OP_REG; c->dst.val = c->dst.orig_val = c->modrm_val; + c->dst.ptr = c->modrm_ptr; break; } c->dst.type = OP_MEM; @@ -1724,7 +1727,8 @@ twobyte_insn: if (rc) goto done; - kvm_emulate_hypercall(ctxt->vcpu); + /* Let the processor re-execute the fixed hypercall */ + c->eip = ctxt->vcpu->arch.rip; /* Disable writeback. */ c->dst.type = OP_NONE; break; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index af65b2d..5c7e2fd 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -582,8 +582,9 @@ static void __init lguest_init_IRQ(void) int vector = FIRST_EXTERNAL_VECTOR + i; if (vector != SYSCALL_VECTOR) { set_intr_gate(vector, interrupt[i]); - set_irq_chip_and_handler(i, &lguest_irq_controller, - handle_level_irq); + set_irq_chip_and_handler_name(i, &lguest_irq_controller, + handle_level_irq, + "level"); } } /* This call is required to set up for 4k stacks, where we have diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 70bebd3..ee1c3f6 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -217,19 +217,19 @@ ENTRY(copy_user_generic_unrolled) /* table sorted by exception address */ .section __ex_table,"a" .align 8 - .quad .Ls1,.Ls1e - .quad .Ls2,.Ls2e - .quad .Ls3,.Ls3e - .quad .Ls4,.Ls4e - .quad .Ld1,.Ls1e + .quad .Ls1,.Ls1e /* Ls1-Ls4 have copied zero bytes */ + .quad .Ls2,.Ls1e + .quad .Ls3,.Ls1e + .quad .Ls4,.Ls1e + .quad .Ld1,.Ls1e /* Ld1-Ld4 have copied 0-24 bytes */ .quad .Ld2,.Ls2e .quad .Ld3,.Ls3e .quad .Ld4,.Ls4e - .quad .Ls5,.Ls5e - .quad .Ls6,.Ls6e - .quad .Ls7,.Ls7e - .quad .Ls8,.Ls8e - .quad .Ld5,.Ls5e + .quad .Ls5,.Ls5e /* Ls5-Ls8 have copied 32 bytes */ + .quad .Ls6,.Ls5e + .quad .Ls7,.Ls5e + .quad .Ls8,.Ls5e + .quad .Ld5,.Ls5e /* Ld5-Ld8 have copied 32-56 bytes */ .quad .Ld6,.Ls6e .quad .Ld7,.Ls7e .quad .Ld8,.Ls8e @@ -244,11 +244,8 @@ ENTRY(copy_user_generic_unrolled) .quad .Le5,.Le_zero .previous - /* compute 64-offset for main loop. 8 bytes accuracy with error on the - pessimistic side. this is gross. it would be better to fix the - interface. */ /* eax: zero, ebx: 64 */ -.Ls1e: addl $8,%eax +.Ls1e: addl $8,%eax /* eax is bytes left uncopied within the loop (Ls1e: 64 .. Ls8e: 8) */ .Ls2e: addl $8,%eax .Ls3e: addl $8,%eax .Ls4e: addl $8,%eax diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S index 5196762..9d3d1ab 100644 --- a/arch/x86/lib/copy_user_nocache_64.S +++ b/arch/x86/lib/copy_user_nocache_64.S @@ -145,19 +145,19 @@ ENTRY(__copy_user_nocache) /* table sorted by exception address */ .section __ex_table,"a" .align 8 - .quad .Ls1,.Ls1e - .quad .Ls2,.Ls2e - .quad .Ls3,.Ls3e - .quad .Ls4,.Ls4e - .quad .Ld1,.Ls1e + .quad .Ls1,.Ls1e /* .Ls[1-4] - 0 bytes copied */ + .quad .Ls2,.Ls1e + .quad .Ls3,.Ls1e + .quad .Ls4,.Ls1e + .quad .Ld1,.Ls1e /* .Ld[1-4] - 0..24 bytes coped */ .quad .Ld2,.Ls2e .quad .Ld3,.Ls3e .quad .Ld4,.Ls4e - .quad .Ls5,.Ls5e - .quad .Ls6,.Ls6e - .quad .Ls7,.Ls7e - .quad .Ls8,.Ls8e - .quad .Ld5,.Ls5e + .quad .Ls5,.Ls5e /* .Ls[5-8] - 32 bytes copied */ + .quad .Ls6,.Ls5e + .quad .Ls7,.Ls5e + .quad .Ls8,.Ls5e + .quad .Ld5,.Ls5e /* .Ld[5-8] - 32..56 bytes copied */ .quad .Ld6,.Ls6e .quad .Ld7,.Ls7e .quad .Ld8,.Ls8e @@ -172,11 +172,8 @@ ENTRY(__copy_user_nocache) .quad .Le5,.Le_zero .previous - /* compute 64-offset for main loop. 8 bytes accuracy with error on the - pessimistic side. this is gross. it would be better to fix the - interface. */ /* eax: zero, ebx: 64 */ -.Ls1e: addl $8,%eax +.Ls1e: addl $8,%eax /* eax: bytes left uncopied: Ls1e: 64 .. Ls8e: 8 */ .Ls2e: addl $8,%eax .Ls3e: addl $8,%eax .Ls4e: addl $8,%eax diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index bc503f5..bf51144 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -136,8 +136,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) (__force u32)sum); } -EXPORT_SYMBOL(csum_partial); - /* * this routine is used for miscellaneous IP-like checksums, mainly * in icmp.c diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay_32.c index 4535e6d..d710f2d 100644 --- a/arch/x86/lib/delay_32.c +++ b/arch/x86/lib/delay_32.c @@ -44,13 +44,36 @@ static void delay_loop(unsigned long loops) static void delay_tsc(unsigned long loops) { unsigned long bclock, now; + int cpu; - preempt_disable(); /* TSC's are per-cpu */ + preempt_disable(); + cpu = smp_processor_id(); rdtscl(bclock); - do { - rep_nop(); + for (;;) { rdtscl(now); - } while ((now-bclock) < loops); + if ((now - bclock) >= loops) + break; + + /* Allow RT tasks to run */ + preempt_enable(); + rep_nop(); + preempt_disable(); + + /* + * It is possible that we moved to another CPU, and + * since TSC's are per-cpu we need to calculate + * that. The delay must guarantee that we wait "at + * least" the amount of time. Being moved to another + * CPU could make the wait longer but we just need to + * make sure we waited long enough. Rebalance the + * counter for this CPU. + */ + if (unlikely(cpu != smp_processor_id())) { + loops -= (now - bclock); + cpu = smp_processor_id(); + rdtscl(bclock); + } + } preempt_enable(); } diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c index bbc6105..4c441be 100644 --- a/arch/x86/lib/delay_64.c +++ b/arch/x86/lib/delay_64.c @@ -31,14 +31,36 @@ int __devinit read_current_timer(unsigned long *timer_value) void __delay(unsigned long loops) { unsigned bclock, now; + int cpu; - preempt_disable(); /* TSC's are pre-cpu */ + preempt_disable(); + cpu = smp_processor_id(); rdtscl(bclock); - do { - rep_nop(); + for (;;) { rdtscl(now); + if ((now - bclock) >= loops) + break; + + /* Allow RT tasks to run */ + preempt_enable(); + rep_nop(); + preempt_disable(); + + /* + * It is possible that we moved to another CPU, and + * since TSC's are per-cpu we need to calculate + * that. The delay must guarantee that we wait "at + * least" the amount of time. Being moved to another + * CPU could make the wait longer but we just need to + * make sure we waited long enough. Rebalance the + * counter for this CPU. + */ + if (unlikely(cpu != smp_processor_id())) { + loops -= (now - bclock); + cpu = smp_processor_id(); + rdtscl(bclock); + } } - while ((now-bclock) < loops); preempt_enable(); } EXPORT_SYMBOL(__delay); diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 6e38d87..c7b06fe 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -30,6 +30,7 @@ #include <asm/uaccess.h> #include <asm/desc.h> #include <asm/user.h> +#include <asm/i387.h> #include "fpu_system.h" #include "fpu_emu.h" @@ -146,6 +147,13 @@ asmlinkage void math_emulate(long arg) unsigned long code_limit = 0; /* Initialized to stop compiler warnings */ struct desc_struct code_descriptor; + if (!used_math()) { + if (init_fpu(current)) { + do_group_exit(SIGKILL); + return; + } + } + #ifdef RE_ENTRANT_CHECKING if (emulating) { printk("ERROR: wm-FPU-emu is not RE-ENTRANT!\n"); @@ -153,11 +161,6 @@ asmlinkage void math_emulate(long arg) RE_ENTRANT_CHECK_ON; #endif /* RE_ENTRANT_CHECKING */ - if (!used_math()) { - finit(); - set_used_math(); - } - SETUP_DATA_AREA(arg); FPU_ORIG_EIP = FPU_EIP; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fd7e179..8bcb6f4 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -497,6 +497,11 @@ static int vmalloc_fault(unsigned long address) unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; + + /* Make sure we are in vmalloc area */ + if (!(address >= VMALLOC_START && address < VMALLOC_END)) + return -1; + /* * Synchronize this task's top level page-table * with the 'reference' page table. diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index de236e4..ec30d10 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -438,8 +438,6 @@ void zap_low_mappings(void) { int i; - save_pg_dir(); - /* * Zap initial low-memory mappings. * @@ -663,16 +661,8 @@ void __init mem_init(void) test_wp_bit(); cpa_init(); - - /* - * Subtle. SMP is doing it's boot stuff late (because it has to - * fork idle threads) - but it also needs low mappings for the - * protected-mode entry to work. We zap these entries only after - * the WP-bit has been tested. - */ -#ifndef CONFIG_SMP + save_pg_dir(); zap_low_mappings(); -#endif } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 32ba13b..156e6d7 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -206,7 +206,7 @@ void __init cleanup_highmap(void) pmd_t *last_pmd = pmd + PTRS_PER_PMD; for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) { - if (!pmd_present(*pmd)) + if (pmd_none(*pmd)) continue; if (vaddr < (unsigned long) _text || vaddr > end) set_pmd(pmd, __pmd(0)); @@ -506,7 +506,7 @@ early_param("memtest", parse_memtest); static void __init early_memtest(unsigned long start, unsigned long end) { - unsigned long t_start, t_size; + u64 t_start, t_size; unsigned pattern; if (!memtest_pattern) @@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end) if (t_start + t_size > end) t_size = end - t_start; - printk(KERN_CONT "\n %016lx - %016lx pattern %d", + printk(KERN_CONT "\n %016llx - %016llx pattern %d", t_start, t_start + t_size, pattern); memtest(t_start, t_size, pattern); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 71bb315..2b2bb3f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -593,10 +593,11 @@ void __init early_iounmap(void *addr, unsigned long size) unsigned long offset; unsigned int nrpages; enum fixed_addresses idx; - unsigned int nesting; + int nesting; nesting = --early_ioremap_nested; - WARN_ON(nesting < 0); + if (WARN_ON(nesting < 0)) + return; if (early_ioremap_debug) { printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr, diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 60adbe2..06b7a1c 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -28,13 +28,13 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_wc_enabled = 1; -void __init pat_disable(char *reason) +void __cpuinit pat_disable(char *reason) { pat_wc_enabled = 0; printk(KERN_INFO "%s\n", reason); } -static int nopat(char *str) +static int __init nopat(char *str) { pat_disable("PAT support disabled."); return 0; @@ -151,32 +151,33 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot, unsigned long pat_type; u8 mtrr_type; - mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == 0xFF) { /* MTRR not enabled */ - *ret_prot = prot; - return 0; - } - if (mtrr_type == 0xFE) { /* MTRR match error */ - *ret_prot = _PAGE_CACHE_UC; - return -1; - } - if (mtrr_type != MTRR_TYPE_UNCACHABLE && - mtrr_type != MTRR_TYPE_WRBACK && - mtrr_type != MTRR_TYPE_WRCOMB) { /* MTRR type unhandled */ - *ret_prot = _PAGE_CACHE_UC; - return -1; - } - pat_type = prot & _PAGE_CACHE_MASK; prot &= (~_PAGE_CACHE_MASK); - /* Currently doing intersection by hand. Optimize it later. */ + /* + * We return the PAT request directly for types where PAT takes + * precedence with respect to MTRR and for UC_MINUS. + * Consistency checks with other PAT requests is done later + * while going through memtype list. + */ if (pat_type == _PAGE_CACHE_WC) { *ret_prot = prot | _PAGE_CACHE_WC; + return 0; } else if (pat_type == _PAGE_CACHE_UC_MINUS) { *ret_prot = prot | _PAGE_CACHE_UC_MINUS; - } else if (pat_type == _PAGE_CACHE_UC || - mtrr_type == MTRR_TYPE_UNCACHABLE) { + return 0; + } else if (pat_type == _PAGE_CACHE_UC) { + *ret_prot = prot | _PAGE_CACHE_UC; + return 0; + } + + /* + * Look for MTRR hint to get the effective type in case where PAT + * request is for WB. + */ + mtrr_type = mtrr_type_lookup(start, end); + + if (mtrr_type == MTRR_TYPE_UNCACHABLE) { *ret_prot = prot | _PAGE_CACHE_UC; } else if (mtrr_type == MTRR_TYPE_WRCOMB) { *ret_prot = prot | _PAGE_CACHE_WC; @@ -233,14 +234,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (req_type == -1) { /* - * Special case where caller wants to inherit from mtrr or - * existing pat mapping, defaulting to UC_MINUS in case of - * no match. + * Call mtrr_lookup to get the type hint. This is an + * optimization for /dev/mem mmap'ers into WB memory (BIOS + * tools and ACPI tools). Use WB request for WB memory and use + * UC_MINUS otherwise. */ u8 mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == 0xFE) { /* MTRR match error */ - err = -1; - } if (mtrr_type == MTRR_TYPE_WRBACK) { req_type = _PAGE_CACHE_WB; @@ -555,7 +554,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", current->comm, current->pid, cattr_name(flags), - offset, offset + size); + offset, (unsigned long long)(offset + size)); return 0; } @@ -576,7 +575,7 @@ void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n", current->comm, current->pid, cattr_name(want_flags), - addr, addr + size, + addr, (unsigned long long)(addr + size), cattr_name(flags)); } } diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 3890234..99649dc 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -97,36 +97,9 @@ static __init inline int srat_disabled(void) return numa_off || acpi_numa < 0; } -/* - * A lot of BIOS fill in 10 (= no distance) everywhere. This messes - * up the NUMA heuristics which wants the local node to have a smaller - * distance than the others. - * Do some quick checks here and only use the SLIT if it passes. - */ -static __init int slit_valid(struct acpi_table_slit *slit) -{ - int i, j; - int d = slit->locality_count; - for (i = 0; i < d; i++) { - for (j = 0; j < d; j++) { - u8 val = slit->entry[d*i + j]; - if (i == j) { - if (val != LOCAL_DISTANCE) - return 0; - } else if (val <= LOCAL_DISTANCE) - return 0; - } - } - return 1; -} - /* Callback for SLIT parsing */ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) { - if (!slit_valid(slit)) { - printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n"); - return; - } acpi_slit = slit; } diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 8545c8a..940185e 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -302,18 +302,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = { }, { .callback = set_bf_sort, - .ident = "HP ProLiant DL385 G2", + .ident = "HP ProLiant DL360", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), - DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"), }, }, { .callback = set_bf_sort, - .ident = "HP ProLiant DL585 G2", + .ident = "HP ProLiant DL380", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), - DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"), }, }, #ifdef __i386__ @@ -328,18 +328,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = { #endif { .callback = set_bf_sort, - .ident = "HP ProLiant DL385 G2", + .ident = "HP ProLiant DL360", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), - DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"), }, }, { .callback = set_bf_sort, - .ident = "HP ProLiant DL585 G2", + .ident = "HP ProLiant DL380", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), - DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"), }, }, {} diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 8af0f0b..10fb308 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -301,15 +301,13 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, prot = pgprot_val(vma->vm_page_prot); if (pat_wc_enabled && write_combine) prot |= _PAGE_CACHE_WC; - else if (pat_wc_enabled) + else if (pat_wc_enabled || boot_cpu_data.x86 > 3) /* * ioremap() and ioremap_nocache() defaults to UC MINUS for now. * To avoid attribute conflicts, request UC MINUS here * aswell. */ prot |= _PAGE_CACHE_UC_MINUS; - else if (boot_cpu_data.x86 > 3) - prot |= _PAGE_CACHE_UC; vma->vm_page_prot = __pgprot(prot); diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c index e70b9c5..b821f44 100644 --- a/arch/x86/pci/init.c +++ b/arch/x86/pci/init.c @@ -15,7 +15,8 @@ static __init int pci_access_init(void) pci_mmcfg_early_init(); #ifdef CONFIG_PCI_OLPC - pci_olpc_init(); + if (!pci_olpc_init()) + return 0; /* skip additional checks if it's an XO */ #endif #ifdef CONFIG_PCI_BIOS pci_pcbios_init(); diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 0908fca..ca8df9c 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -621,6 +621,13 @@ static __init int via_router_probe(struct irq_router *r, */ device = PCI_DEVICE_ID_VIA_8235; break; + case PCI_DEVICE_ID_VIA_8237: + /** + * Asus a7v600 bios wrongly reports 8237 + * as 586-compatible + */ + device = PCI_DEVICE_ID_VIA_8237; + break; } } diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c index 5e76365..e11e9e8 100644 --- a/arch/x86/pci/olpc.c +++ b/arch/x86/pci/olpc.c @@ -302,12 +302,13 @@ static struct pci_raw_ops pci_olpc_conf = { .write = pci_olpc_write, }; -void __init pci_olpc_init(void) +int __init pci_olpc_init(void) { if (!machine_is_olpc() || olpc_has_vsa()) - return; + return -ENODEV; printk(KERN_INFO "PCI: Using configuration type OLPC\n"); raw_pci_ops = &pci_olpc_conf; is_lx = is_geode_lx(); + return 0; } diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h index f3972b1..720c4c5 100644 --- a/arch/x86/pci/pci.h +++ b/arch/x86/pci/pci.h @@ -101,7 +101,7 @@ extern struct pci_raw_ops pci_direct_conf1; extern int pci_direct_probe(void); extern void pci_direct_init(int type); extern void pci_pcbios_init(void); -extern void pci_olpc_init(void); +extern int pci_olpc_init(void); /* pci-mmconfig.c */ diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 23476c2..efa2ba7 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -106,9 +106,9 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) do_realtime((struct timespec *)tv); tv->tv_usec /= 1000; if (unlikely(tz != NULL)) { - /* This relies on gcc inlining the memcpy. We'll notice - if it ever fails to do so. */ - memcpy(tz, >od->sys_tz, sizeof(struct timezone)); + /* Avoid memcpy. Some old compilers fail to inline it */ + tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest; + tz->tz_dsttime = gtod->sys_tz.tz_dsttime; } return 0; } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 126766d..3525ef5 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -60,7 +60,7 @@ xmaddr_t arbitrary_virt_to_machine(unsigned long address) { unsigned int level; pte_t *pte = lookup_address(address, &level); - unsigned offset = address & PAGE_MASK; + unsigned offset = address & ~PAGE_MASK; BUG_ON(pte == NULL); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index c39e1a5..52b2e38 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -12,6 +12,7 @@ #include <linux/clocksource.h> #include <linux/clockchips.h> #include <linux/kernel_stat.h> +#include <linux/math64.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -150,11 +151,7 @@ static void do_stolen_accounting(void) if (stolen < 0) stolen = 0; - ticks = 0; - while (stolen >= NS_PER_TICK) { - ticks++; - stolen -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __get_cpu_var(residual_stolen) = stolen; account_steal_time(NULL, ticks); @@ -166,11 +163,7 @@ static void do_stolen_accounting(void) if (blocked < 0) blocked = 0; - ticks = 0; - while (blocked >= NS_PER_TICK) { - ticks++; - blocked -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); __get_cpu_var(residual_blocked) = blocked; account_steal_time(idle_task(smp_processor_id()), ticks); } |