diff options
Diffstat (limited to 'arch/x86')
55 files changed, 698 insertions, 521 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dcbec34154c..e0edaaa6920 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -383,6 +383,7 @@ config VMI config KVM_CLOCK bool "KVM paravirtualized clock" select PARAVIRT + select PARAVIRT_CLOCK depends on !(X86_VISWS || X86_VOYAGER) help Turning on this option will allow you to run a paravirtualized clock @@ -410,6 +411,10 @@ config PARAVIRT over full virtualization. However, when run without a hypervisor the kernel is theoretically slower and slightly larger. +config PARAVIRT_CLOCK + bool + default n + endif config MEMTEST_BOOTPARAM @@ -1508,13 +1513,13 @@ 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 @@ -1531,9 +1536,8 @@ 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 ac1e31ba479..18363374d51 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 90943f83e84..e01aafd03bd 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/kernel/Makefile b/arch/x86/kernel/Makefile index 5e618c3b472..77807d4769c 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -82,6 +82,7 @@ obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o obj-$(CONFIG_KVM_GUEST) += kvm.o obj-$(CONFIG_KVM_CLOCK) += kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o +obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index c49ebcc6c41..33c5216fd3e 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/entry_32.S b/arch/x86/kernel/entry_32.S index 2a609dc3271..c778e4fa55a 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 e8edd63ab00..9b08e852fd1 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 b2cc73768a9..f7357cc0162 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 e03cc952f23..eb9ddd8efb8 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/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index a40d54fc1fd..4dc8600d9d2 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 08a30986d47..87edf1ceb1d 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -18,6 +18,7 @@ #include <linux/clocksource.h> #include <linux/kvm_para.h> +#include <asm/pvclock.h> #include <asm/arch_hooks.h> #include <asm/msr.h> #include <asm/apic.h> @@ -36,18 +37,9 @@ static int parse_no_kvmclock(char *arg) early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock); -#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field +static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock); +static struct pvclock_wall_clock wall_clock; -static inline u64 kvm_get_delta(u64 last_tsc) -{ - int cpu = smp_processor_id(); - u64 delta = native_read_tsc() - last_tsc; - return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE; -} - -static struct kvm_wall_clock wall_clock; -static cycle_t kvm_clock_read(void); /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -55,64 +47,37 @@ static cycle_t kvm_clock_read(void); */ static unsigned long kvm_get_wallclock(void) { - u32 wc_sec, wc_nsec; - u64 delta; + struct pvclock_vcpu_time_info *vcpu_time; struct timespec ts; - int version, nsec; int low, high; low = (int)__pa(&wall_clock); high = ((u64)__pa(&wall_clock) >> 32); + native_write_msr(MSR_KVM_WALL_CLOCK, low, high); - delta = kvm_clock_read(); + vcpu_time = &get_cpu_var(hv_clock); + pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); + put_cpu_var(hv_clock); - native_write_msr(MSR_KVM_WALL_CLOCK, low, high); - do { - version = wall_clock.wc_version; - rmb(); - wc_sec = wall_clock.wc_sec; - wc_nsec = wall_clock.wc_nsec; - rmb(); - } while ((wall_clock.wc_version != version) || (version & 1)); - - delta = kvm_clock_read() - delta; - delta += wc_nsec; - nsec = do_div(delta, NSEC_PER_SEC); - set_normalized_timespec(&ts, wc_sec + delta, nsec); - /* - * Of all mechanisms of time adjustment I've tested, this one - * was the champion! - */ - return ts.tv_sec + 1; + return ts.tv_sec; } static int kvm_set_wallclock(unsigned long now) { - return 0; + return -1; } -/* - * This is our read_clock function. The host puts an tsc timestamp each time - * it updates a new time. Without the tsc adjustment, we can have a situation - * in which a vcpu starts to run earlier (smaller system_time), but probes - * time later (compared to another vcpu), leading to backwards time - */ static cycle_t kvm_clock_read(void) { - u64 last_tsc, now; - int cpu; + struct pvclock_vcpu_time_info *src; + cycle_t ret; - preempt_disable(); - cpu = smp_processor_id(); - - last_tsc = get_clock(cpu, tsc_timestamp); - now = get_clock(cpu, system_time); - - now += kvm_get_delta(last_tsc); - preempt_enable(); - - return now; + src = &get_cpu_var(hv_clock); + ret = pvclock_clocksource_read(src); + put_cpu_var(hv_clock); + return ret; } + static struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_read, @@ -123,13 +88,14 @@ static struct clocksource kvm_clock = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static int kvm_register_clock(void) +static int kvm_register_clock(char *txt) { int cpu = smp_processor_id(); int low, high; low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1; high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32); - + printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n", + cpu, high, low, txt); return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high); } @@ -140,12 +106,20 @@ static void kvm_setup_secondary_clock(void) * Now that the first cpu already had this clocksource initialized, * we shouldn't fail. */ - WARN_ON(kvm_register_clock()); + WARN_ON(kvm_register_clock("secondary cpu clock")); /* ok, done with our trickery, call native */ setup_secondary_APIC_clock(); } #endif +#ifdef CONFIG_SMP +void __init kvm_smp_prepare_boot_cpu(void) +{ + WARN_ON(kvm_register_clock("primary cpu clock")); + native_smp_prepare_boot_cpu(); +} +#endif + /* * After the clock is registered, the host will keep writing to the * registered memory location. If the guest happens to shutdown, this memory @@ -174,7 +148,7 @@ void __init kvmclock_init(void) return; if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { - if (kvm_register_clock()) + if (kvm_register_clock("boot clock")) return; pv_time_ops.get_wallclock = kvm_get_wallclock; pv_time_ops.set_wallclock = kvm_set_wallclock; @@ -182,6 +156,9 @@ void __init kvmclock_init(void) #ifdef CONFIG_X86_LOCAL_APIC pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock; #endif +#ifdef CONFIG_SMP + smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; +#endif machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC machine_ops.crash_shutdown = kvm_crash_shutdown; diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 3cad17fe026..07c0f828f48 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 11b14bbaa61..84160f74eeb 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 c5ef1af8e79..dc00a1331ac 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); @@ -397,20 +398,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, 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 && !(gfp & GFP_DMA)) + 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 c07455d1695..aa8ec928caa 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_32.c b/arch/x86/kernel/process_32.c index f8476dfbb60..e2db9ac5c61 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 e2319f39988..c6eb5c91e5f 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/pvclock.c b/arch/x86/kernel/pvclock.c new file mode 100644 index 00000000000..05fbe9a0325 --- /dev/null +++ b/arch/x86/kernel/pvclock.c @@ -0,0 +1,141 @@ +/* paravirtual clock -- common code used by kvm/xen + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA +*/ + +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <asm/pvclock.h> + +/* + * These are perodically updated + * xen: magic shared_info page + * kvm: gpa registered via msr + * and then copied here. + */ +struct pvclock_shadow_time { + u64 tsc_timestamp; /* TSC at last update of time vals. */ + u64 system_timestamp; /* Time, in nanosecs, since boot. */ + u32 tsc_to_nsec_mul; + int tsc_shift; + u32 version; +}; + +/* + * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, + * yielding a 64-bit result. + */ +static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift) +{ + u64 product; +#ifdef __i386__ + u32 tmp1, tmp2; +#endif + + if (shift < 0) + delta >>= -shift; + else + delta <<= shift; + +#ifdef __i386__ + __asm__ ( + "mul %5 ; " + "mov %4,%%eax ; " + "mov %%edx,%4 ; " + "mul %5 ; " + "xor %5,%5 ; " + "add %4,%%eax ; " + "adc %5,%%edx ; " + : "=A" (product), "=r" (tmp1), "=r" (tmp2) + : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); +#elif __x86_64__ + __asm__ ( + "mul %%rdx ; shrd $32,%%rdx,%%rax" + : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); +#else +#error implement me! +#endif + + return product; +} + +static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow) +{ + u64 delta = native_read_tsc() - shadow->tsc_timestamp; + return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift); +} + +/* + * Reads a consistent set of time-base values from hypervisor, + * into a shadow data area. + */ +static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst, + struct pvclock_vcpu_time_info *src) +{ + do { + dst->version = src->version; + rmb(); /* fetch version before data */ + dst->tsc_timestamp = src->tsc_timestamp; + dst->system_timestamp = src->system_time; + dst->tsc_to_nsec_mul = src->tsc_to_system_mul; + dst->tsc_shift = src->tsc_shift; + rmb(); /* test version after fetching data */ + } while ((src->version & 1) || (dst->version != src->version)); + + return dst->version; +} + +cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) +{ + struct pvclock_shadow_time shadow; + unsigned version; + cycle_t ret, offset; + + do { + version = pvclock_get_time_values(&shadow, src); + barrier(); + offset = pvclock_get_nsec_offset(&shadow); + ret = shadow.system_timestamp + offset; + barrier(); + } while (version != src->version); + + return ret; +} + +void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, + struct pvclock_vcpu_time_info *vcpu_time, + struct timespec *ts) +{ + u32 version; + u64 delta; + struct timespec now; + + /* get wallclock at system boot */ + do { + version = wall_clock->version; + rmb(); /* fetch version before time */ + now.tv_sec = wall_clock->sec; + now.tv_nsec = wall_clock->nsec; + rmb(); /* fetch time before checking version */ + } while ((wall_clock->version & 1) || (version != wall_clock->version)); + + delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */ + delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec; + + now.tv_nsec = do_div(delta, NSEC_PER_SEC); + now.tv_sec = delta; + + set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); +} diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 9615eee9b77..05191bbc68b 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_32.c b/arch/x86/kernel/setup_32.c index 2c5f8b213e8..5a2f8e06388 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/smpboot.c b/arch/x86/kernel/smpboot.c index 38988491c62..56078d61c79 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1190,6 +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; @@ -1206,7 +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(); @@ -1246,6 +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. diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c index bde6f63e15d..08d752de4ee 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 068759db63d..65b70637ad9 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_disabled; +/* 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 @@ -402,25 +405,20 @@ void __init tsc_init(void) { int cpu; - if (!cpu_has_tsc || tsc_disabled) { - /* Disable the TSC in case of !cpu_has_tsc */ - tsc_disabled = 1; + if (!cpu_has_tsc || tsc_disabled > 0) return; - } cpu_khz = calculate_cpu_khz(); tsc_khz = cpu_khz; if (!cpu_khz) { mark_tsc_unstable("could not calculate TSC khz"); - /* - * We need to disable the TSC completely in this case - * to prevent sched_clock() from using it. - */ - tsc_disabled = 1; 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); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 7c077a9d977..3829aa7b663 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -200,10 +200,12 @@ 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); + if (vcpu0) { + set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests); + if (waitqueue_active(&vcpu0->wq)) { + vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE; + wake_up_interruptible(&vcpu0->wq); + } } pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period); @@ -237,6 +239,19 @@ 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 ce1f583459b..76d736b5f66 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 1802134b836..2a15be2275c 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 c297c50eba6..ebc03f5ae16 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -940,6 +940,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic) wait_queue_head_t *q = &apic->vcpu->wq; atomic_inc(&apic->timer.pending); + set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests); if (waitqueue_active(q)) { apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; wake_up_interruptible(q); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7246b60afb9..7e7c3969f7a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -640,6 +640,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn) rmap_remove(kvm, spte); --kvm->stat.lpages; set_shadow_pte(spte, shadow_trap_nonpresent_pte); + spte = NULL; write_protected = 1; } spte = rmap_next(kvm, rmapp, spte); @@ -658,7 +659,7 @@ 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; @@ -1082,10 +1083,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, struct kvm_mmu_page *shadow; spte |= PT_WRITABLE_MASK; - if (user_fault) { - mmu_unshadow(vcpu->kvm, gfn); - goto unshadowed; - } shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn); if (shadow || @@ -1102,8 +1099,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, } } -unshadowed: - if (pte_access & ACC_WRITE_MASK) mark_page_dirty(vcpu->kvm, gfn); @@ -1580,11 +1575,13 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, u64 *spte, const void *new) { - if ((sp->role.level != PT_PAGE_TABLE_LEVEL) - && !vcpu->arch.update_pte.largepage) { - ++vcpu->kvm->stat.mmu_pde_zapped; - return; - } + if (sp->role.level != PT_PAGE_TABLE_LEVEL) { + if (!vcpu->arch.update_pte.largepage || + sp->role.glevels == PT32_ROOT_LEVEL) { + ++vcpu->kvm->stat.mmu_pde_zapped; + return; + } + } ++vcpu->kvm->stat.mmu_pte_updated; if (sp->role.glevels == PT32_ROOT_LEVEL) @@ -1858,6 +1855,7 @@ 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); } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 156fe10288a..934c7b61939 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 ab22615eee8..6b0d5fa5bab 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 bfe4db11989..540e9517907 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -566,7 +566,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) load_transition_efer(vmx); } -static void vmx_load_host_state(struct vcpu_vmx *vmx) +static void __vmx_load_host_state(struct vcpu_vmx *vmx) { unsigned long flags; @@ -596,6 +596,13 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx) reload_host_efer(vmx); } +static void vmx_load_host_state(struct vcpu_vmx *vmx) +{ + preempt_disable(); + __vmx_load_host_state(vmx); + preempt_enable(); +} + /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -608,7 +615,7 @@ 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); } @@ -654,7 +661,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { - vmx_load_host_state(to_vmx(vcpu)); + __vmx_load_host_state(to_vmx(vcpu)); } static void vmx_fpu_activate(struct kvm_vcpu *vcpu) @@ -884,11 +891,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) switch (msr_index) { #ifdef CONFIG_X86_64 case MSR_EFER: + vmx_load_host_state(vmx); ret = kvm_set_msr_common(vcpu, msr_index, data); - if (vmx->host_state.loaded) { - reload_host_efer(vmx); - load_transition_efer(vmx); - } break; case MSR_FS_BASE: vmcs_writel(GUEST_FS_BASE, data); @@ -910,11 +914,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) guest_write_tsc(data); break; default: + vmx_load_host_state(vmx); msr = find_msr_entry(vmx, msr_index); if (msr) { msr->data = data; - if (vmx->host_state.loaded) - load_msrs(vmx->guest_msrs, vmx->save_nmsrs); break; } ret = kvm_set_msr_common(vcpu, msr_index, data); @@ -1036,6 +1039,7 @@ 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 21338bdb28f..63a77caa59f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -492,8 +492,8 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) { static int version; - struct kvm_wall_clock wc; - struct timespec wc_ts; + struct pvclock_wall_clock wc; + struct timespec now, sys, boot; if (!wall_clock) return; @@ -502,10 +502,19 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); - wc_ts = current_kernel_time(); - wc.wc_sec = wc_ts.tv_sec; - wc.wc_nsec = wc_ts.tv_nsec; - wc.wc_version = version; + /* + * The guest calculates current wall clock time by adding + * system time (updated by kvm_write_guest_time below) to the + * wall clock specified here. guest system time equals host + * system time for us, thus we must fill in host boot time here. + */ + now = current_kernel_time(); + ktime_get_ts(&sys); + boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys)); + + wc.sec = boot.tv_sec; + wc.nsec = boot.tv_nsec; + wc.version = version; kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); @@ -513,6 +522,45 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); } +static uint32_t div_frac(uint32_t dividend, uint32_t divisor) +{ + uint32_t quotient, remainder; + + /* Don't try to replace with do_div(), this one calculates + * "(dividend << 32) / divisor" */ + __asm__ ( "divl %4" + : "=a" (quotient), "=d" (remainder) + : "0" (0), "1" (dividend), "r" (divisor) ); + return quotient; +} + +static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock) +{ + uint64_t nsecs = 1000000000LL; + int32_t shift = 0; + uint64_t tps64; + uint32_t tps32; + + tps64 = tsc_khz * 1000LL; + while (tps64 > nsecs*2) { + tps64 >>= 1; + shift--; + } + + tps32 = (uint32_t)tps64; + while (tps32 <= (uint32_t)nsecs) { + tps32 <<= 1; + shift++; + } + + hv_clock->tsc_shift = shift; + hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32); + + pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n", + __FUNCTION__, tsc_khz, hv_clock->tsc_shift, + hv_clock->tsc_to_system_mul); +} + static void kvm_write_guest_time(struct kvm_vcpu *v) { struct timespec ts; @@ -523,6 +571,11 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) if ((!vcpu->time_page)) return; + if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) { + kvm_set_time_scale(tsc_khz, &vcpu->hv_clock); + vcpu->hv_clock_tsc_khz = tsc_khz; + } + /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER, @@ -537,14 +590,14 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate - * state, we just write "2" at the end + * state, we just increase by 2 at the end. */ - vcpu->hv_clock.version = 2; + vcpu->hv_clock.version += 2; shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0); memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + sizeof(vcpu->hv_clock)); kunmap_atomic(shared_kaddr, KM_USER0); @@ -599,10 +652,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* ...but clean it before doing the actual write */ vcpu->arch.time_offset = data & ~(PAGE_MASK | 1); - vcpu->arch.hv_clock.tsc_to_system_mul = - clocksource_khz2mult(tsc_khz, 22); - vcpu->arch.hv_clock.tsc_shift = 22; - down_read(¤t->mm->mmap_sem); vcpu->arch.time_page = gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT); @@ -2758,7 +2807,9 @@ 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_TLB_FLUSH, &vcpu->requests)) + kvm_x86_ops->tlb_flush(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -2772,6 +2823,7 @@ again: } } + clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); kvm_inject_pending_timer_irqs(vcpu); preempt_disable(); @@ -2781,21 +2833,13 @@ again: local_irq_disable(); - if (need_resched()) { + if (vcpu->requests || need_resched()) { local_irq_enable(); preempt_enable(); r = 1; goto out; } - if (vcpu->requests) - if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) { - local_irq_enable(); - preempt_enable(); - r = 1; - goto out; - } - if (signal_pending(current)) { local_irq_enable(); preempt_enable(); @@ -2825,9 +2869,6 @@ again: kvm_guest_enter(); - if (vcpu->requests) - if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) - kvm_x86_ops->tlb_flush(vcpu); KVMTRACE_0D(VMENTRY, vcpu, entryexit); kvm_x86_ops->run(vcpu, kvm_run); diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index 8a96320ab07..932f216d890 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -1727,7 +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 af65b2da3ba..5c7e2fd5207 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 70bebd31040..ee1c3f63515 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 5196762b3b0..9d3d1ab8376 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/delay_32.c b/arch/x86/lib/delay_32.c index 4535e6d147a..d710f2d167b 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 bbc61051851..4c441be9264 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 6e38d877ea7..c7b06feb139 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 fd7e1798c75..8bcb6f40ccb 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_64.c b/arch/x86/mm/init_64.c index 32ba13b0f81..156e6d7b0e3 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 71bb3159031..2b2bb3f9b68 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 de3a9981245..06b7a1c90fb 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -34,7 +34,7 @@ void __cpuinit pat_disable(char *reason) 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; diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 3890234e5b2..99649dccad2 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 6e64aaf00d1..940185ecaed 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -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/init.c b/arch/x86/pci/init.c index e70b9c57b88..b821f4462d9 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 0908fca901b..ca8df9c260b 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 5e7636558c0..e11e9e803d5 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 f3972b12c60..720c4c55453 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/xen/Kconfig b/arch/x86/xen/Kconfig index 2e641be2737..6c388e593bc 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -5,8 +5,9 @@ config XEN bool "Xen guest support" select PARAVIRT + select PARAVIRT_CLOCK depends on X86_32 - depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER) + depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER) help This is the Linux Xen port. Enabling this will allow the kernel to boot in a paravirtualized environment under the diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c8a56e457d6..f09c1c69c37 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -785,38 +785,35 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) static __init void xen_pagetable_setup_start(pgd_t *base) { pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base; + int i; /* special set_pte for pagetable initialization */ pv_mmu_ops.set_pte = xen_set_pte_init; init_mm.pgd = base; /* - * copy top-level of Xen-supplied pagetable into place. For - * !PAE we can use this as-is, but for PAE it is a stand-in - * while we copy the pmd pages. + * copy top-level of Xen-supplied pagetable into place. This + * is a stand-in while we copy the pmd pages. */ memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t)); - if (PTRS_PER_PMD > 1) { - int i; - /* - * For PAE, need to allocate new pmds, rather than - * share Xen's, since Xen doesn't like pmd's being - * shared between address spaces. - */ - for (i = 0; i < PTRS_PER_PGD; i++) { - if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) { - pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); + /* + * For PAE, need to allocate new pmds, rather than + * share Xen's, since Xen doesn't like pmd's being + * shared between address spaces. + */ + for (i = 0; i < PTRS_PER_PGD; i++) { + if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) { + pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE); - memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]), - PAGE_SIZE); + memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]), + PAGE_SIZE); - make_lowmem_page_readonly(pmd); + make_lowmem_page_readonly(pmd); - set_pgd(&base[i], __pgd(1 + __pa(pmd))); - } else - pgd_clear(&base[i]); - } + set_pgd(&base[i], __pgd(1 + __pa(pmd))); + } else + pgd_clear(&base[i]); } /* make sure zero_page is mapped RO so we can use it in pagetables */ @@ -873,17 +870,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base) /* Actually pin the pagetable down, but we can't set PG_pinned yet because the page structures don't exist yet. */ - { - unsigned level; - -#ifdef CONFIG_X86_PAE - level = MMUEXT_PIN_L3_TABLE; -#else - level = MMUEXT_PIN_L2_TABLE; -#endif - - pin_pagetable_pfn(level, PFN_DOWN(__pa(base))); - } + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base))); } /* This is called once we have the cpu_possible_map */ @@ -1093,7 +1080,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .make_pte = xen_make_pte, .make_pgd = xen_make_pgd, -#ifdef CONFIG_X86_PAE .set_pte_atomic = xen_set_pte_atomic, .set_pte_present = xen_set_pte_at, .set_pud = xen_set_pud, @@ -1102,7 +1088,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .make_pmd = xen_make_pmd, .pmd_val = xen_pmd_val, -#endif /* PAE */ .activate_mm = xen_activate_mm, .dup_mmap = xen_dup_mmap, @@ -1228,6 +1213,11 @@ asmlinkage void __init xen_start_kernel(void) if (xen_feature(XENFEAT_supervisor_mode_kernel)) pv_info.kernel_rpl = 0; + /* Prevent unwanted bits from being set in PTEs. */ + __supported_pte_mask &= ~_PAGE_GLOBAL; + if (!is_initial_xendomain()) + __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); + /* set the limit of our address space */ xen_reserve_top(); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3525ef523a7..df40bf74ea7 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -179,50 +179,56 @@ out: preempt_enable(); } -pteval_t xen_pte_val(pte_t pte) +/* Assume pteval_t is equivalent to all the other *val_t types. */ +static pteval_t pte_mfn_to_pfn(pteval_t val) +{ + if (val & _PAGE_PRESENT) { + unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT; + pteval_t flags = val & ~PTE_MASK; + val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags; + } + + return val; +} + +static pteval_t pte_pfn_to_mfn(pteval_t val) { - pteval_t ret = pte.pte; + if (val & _PAGE_PRESENT) { + unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT; + pteval_t flags = val & ~PTE_MASK; + val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags; + } - if (ret & _PAGE_PRESENT) - ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; + return val; +} - return ret; +pteval_t xen_pte_val(pte_t pte) +{ + return pte_mfn_to_pfn(pte.pte); } pgdval_t xen_pgd_val(pgd_t pgd) { - pgdval_t ret = pgd.pgd; - if (ret & _PAGE_PRESENT) - ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; - return ret; + return pte_mfn_to_pfn(pgd.pgd); } pte_t xen_make_pte(pteval_t pte) { - if (pte & _PAGE_PRESENT) { - pte = phys_to_machine(XPADDR(pte)).maddr; - pte &= ~(_PAGE_PCD | _PAGE_PWT); - } - - return (pte_t){ .pte = pte }; + pte = pte_pfn_to_mfn(pte); + return native_make_pte(pte); } pgd_t xen_make_pgd(pgdval_t pgd) { - if (pgd & _PAGE_PRESENT) - pgd = phys_to_machine(XPADDR(pgd)).maddr; - - return (pgd_t){ pgd }; + pgd = pte_pfn_to_mfn(pgd); + return native_make_pgd(pgd); } pmdval_t xen_pmd_val(pmd_t pmd) { - pmdval_t ret = native_pmd_val(pmd); - if (ret & _PAGE_PRESENT) - ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT; - return ret; + return pte_mfn_to_pfn(pmd.pmd); } -#ifdef CONFIG_X86_PAE + void xen_set_pud(pud_t *ptr, pud_t val) { struct multicall_space mcs; @@ -267,17 +273,9 @@ void xen_pmd_clear(pmd_t *pmdp) pmd_t xen_make_pmd(pmdval_t pmd) { - if (pmd & _PAGE_PRESENT) - pmd = phys_to_machine(XPADDR(pmd)).maddr; - + pmd = pte_pfn_to_mfn(pmd); return native_make_pmd(pmd); } -#else /* !PAE */ -void xen_set_pte(pte_t *ptep, pte_t pte) -{ - *ptep = pte; -} -#endif /* CONFIG_X86_PAE */ /* (Yet another) pagetable walker. This one is intended for pinning a @@ -430,8 +428,6 @@ static int pin_page(struct page *page, enum pt_level level) read-only, and can be pinned. */ void xen_pgd_pin(pgd_t *pgd) { - unsigned level; - xen_mc_batch(); if (pgd_walk(pgd, pin_page, TASK_SIZE)) { @@ -441,14 +437,7 @@ void xen_pgd_pin(pgd_t *pgd) xen_mc_batch(); } -#ifdef CONFIG_X86_PAE - level = MMUEXT_PIN_L3_TABLE; -#else - level = MMUEXT_PIN_L2_TABLE; -#endif - - xen_do_pin(level, PFN_DOWN(__pa(pgd))); - + xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd))); xen_mc_issue(0); } diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index b5e189b1519..5fe961caffd 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -37,14 +37,13 @@ void xen_exit_mmap(struct mm_struct *mm); void xen_pgd_pin(pgd_t *pgd); //void xen_pgd_unpin(pgd_t *pgd); -#ifdef CONFIG_X86_PAE -unsigned long long xen_pte_val(pte_t); -unsigned long long xen_pmd_val(pmd_t); -unsigned long long xen_pgd_val(pgd_t); +pteval_t xen_pte_val(pte_t); +pmdval_t xen_pmd_val(pmd_t); +pgdval_t xen_pgd_val(pgd_t); -pte_t xen_make_pte(unsigned long long); -pmd_t xen_make_pmd(unsigned long long); -pgd_t xen_make_pgd(unsigned long long); +pte_t xen_make_pte(pteval_t); +pmd_t xen_make_pmd(pmdval_t); +pgd_t xen_make_pgd(pgdval_t); void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval); @@ -53,15 +52,4 @@ void xen_set_pud(pud_t *ptr, pud_t val); void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void xen_pmd_clear(pmd_t *pmdp); - -#else -unsigned long xen_pte_val(pte_t); -unsigned long xen_pmd_val(pmd_t); -unsigned long xen_pgd_val(pgd_t); - -pte_t xen_make_pte(unsigned long); -pmd_t xen_make_pmd(unsigned long); -pgd_t xen_make_pgd(unsigned long); -#endif - #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index c39e1a5aa24..41e217503c9 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -12,7 +12,9 @@ #include <linux/clocksource.h> #include <linux/clockchips.h> #include <linux/kernel_stat.h> +#include <linux/math64.h> +#include <asm/pvclock.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -30,17 +32,6 @@ static cycle_t xen_clocksource_read(void); -/* These are perodically updated in shared_info, and then copied here. */ -struct shadow_time_info { - u64 tsc_timestamp; /* TSC at last update of time vals. */ - u64 system_timestamp; /* Time, in nanosecs, since boot. */ - u32 tsc_to_nsec_mul; - int tsc_shift; - u32 version; -}; - -static DEFINE_PER_CPU(struct shadow_time_info, shadow_time); - /* runstate info updated by Xen */ static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate); @@ -150,11 +141,7 @@ 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 +153,7 @@ 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); } @@ -218,7 +201,7 @@ unsigned long long xen_sched_clock(void) unsigned long xen_cpu_khz(void) { u64 xen_khz = 1000000ULL << 32; - const struct vcpu_time_info *info = + const struct pvclock_vcpu_time_info *info = &HYPERVISOR_shared_info->vcpu_info[0].time; do_div(xen_khz, info->tsc_to_system_mul); @@ -230,121 +213,26 @@ unsigned long xen_cpu_khz(void) return xen_khz; } -/* - * Reads a consistent set of time-base values from Xen, into a shadow data - * area. - */ -static unsigned get_time_values_from_xen(void) -{ - struct vcpu_time_info *src; - struct shadow_time_info *dst; - - /* src is shared memory with the hypervisor, so we need to - make sure we get a consistent snapshot, even in the face of - being preempted. */ - src = &__get_cpu_var(xen_vcpu)->time; - dst = &__get_cpu_var(shadow_time); - - do { - dst->version = src->version; - rmb(); /* fetch version before data */ - dst->tsc_timestamp = src->tsc_timestamp; - dst->system_timestamp = src->system_time; - dst->tsc_to_nsec_mul = src->tsc_to_system_mul; - dst->tsc_shift = src->tsc_shift; - rmb(); /* test version after fetching data */ - } while ((src->version & 1) | (dst->version ^ src->version)); - - return dst->version; -} - -/* - * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, - * yielding a 64-bit result. - */ -static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift) -{ - u64 product; -#ifdef __i386__ - u32 tmp1, tmp2; -#endif - - if (shift < 0) - delta >>= -shift; - else - delta <<= shift; - -#ifdef __i386__ - __asm__ ( - "mul %5 ; " - "mov %4,%%eax ; " - "mov %%edx,%4 ; " - "mul %5 ; " - "xor %5,%5 ; " - "add %4,%%eax ; " - "adc %5,%%edx ; " - : "=A" (product), "=r" (tmp1), "=r" (tmp2) - : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); -#elif __x86_64__ - __asm__ ( - "mul %%rdx ; shrd $32,%%rdx,%%rax" - : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); -#else -#error implement me! -#endif - - return product; -} - -static u64 get_nsec_offset(struct shadow_time_info *shadow) -{ - u64 now, delta; - now = native_read_tsc(); - delta = now - shadow->tsc_timestamp; - return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift); -} - static cycle_t xen_clocksource_read(void) { - struct shadow_time_info *shadow = &get_cpu_var(shadow_time); + struct pvclock_vcpu_time_info *src; cycle_t ret; - unsigned version; - - do { - version = get_time_values_from_xen(); - barrier(); - ret = shadow->system_timestamp + get_nsec_offset(shadow); - barrier(); - } while (version != __get_cpu_var(xen_vcpu)->time.version); - - put_cpu_var(shadow_time); + src = &get_cpu_var(xen_vcpu)->time; + ret = pvclock_clocksource_read(src); + put_cpu_var(xen_vcpu); return ret; } static void xen_read_wallclock(struct timespec *ts) { - const struct shared_info *s = HYPERVISOR_shared_info; - u32 version; - u64 delta; - struct timespec now; - - /* get wallclock at system boot */ - do { - version = s->wc_version; - rmb(); /* fetch version before time */ - now.tv_sec = s->wc_sec; - now.tv_nsec = s->wc_nsec; - rmb(); /* fetch time before checking version */ - } while ((s->wc_version & 1) | (version ^ s->wc_version)); + struct shared_info *s = HYPERVISOR_shared_info; + struct pvclock_wall_clock *wall_clock = &(s->wc); + struct pvclock_vcpu_time_info *vcpu_time; - delta = xen_clocksource_read(); /* time since system boot */ - delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec; - - now.tv_nsec = do_div(delta, NSEC_PER_SEC); - now.tv_sec = delta; - - set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); + vcpu_time = &get_cpu_var(xen_vcpu)->time; + pvclock_read_wallclock(wall_clock, vcpu_time, ts); + put_cpu_var(xen_vcpu); } unsigned long xen_get_wallclock(void) @@ -352,7 +240,6 @@ unsigned long xen_get_wallclock(void) struct timespec ts; xen_read_wallclock(&ts); - return ts.tv_sec; } @@ -576,8 +463,6 @@ __init void xen_time_init(void) { int cpu = smp_processor_id(); - get_time_values_from_xen(); - clocksource_register(&xen_clocksource); if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) { diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 288d587ce73..6ec3b4f7719 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -17,7 +17,7 @@ ENTRY(startup_xen) __FINIT -.pushsection .bss.page_aligned +.pushsection .text .align PAGE_SIZE_asm ENTRY(hypercall_page) .skip 0x1000 @@ -30,11 +30,7 @@ ENTRY(hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, .long startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .asciz "!writable_page_tables|pae_pgdir_above_4gb") -#ifdef CONFIG_X86_PAE ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "yes") -#else - ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "no") -#endif ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") #endif /*CONFIG_XEN */ |