diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 7897 |
1 files changed, 6092 insertions, 1805 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6b01552bd1f..ef432f891d3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4,10 +4,15 @@ * derived from drivers/kvm/kvm_main.c * * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> + * Amit Shah <amit.shah@qumranet.com> + * Ben-Ami Yassour <benami@il.ibm.com> * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. @@ -15,41 +20,112 @@ */ #include <linux/kvm_host.h> -#include "segment_descriptor.h" #include "irq.h" #include "mmu.h" - +#include "i8254.h" +#include "tss.h" +#include "kvm_cache_regs.h" +#include "x86.h" +#include "cpuid.h" + +#include <linux/clocksource.h> +#include <linux/interrupt.h> #include <linux/kvm.h> #include <linux/fs.h> #include <linux/vmalloc.h> #include <linux/module.h> #include <linux/mman.h> #include <linux/highmem.h> - -#include <asm/uaccess.h> +#include <linux/iommu.h> +#include <linux/intel-iommu.h> +#include <linux/cpufreq.h> +#include <linux/user-return-notifier.h> +#include <linux/srcu.h> +#include <linux/slab.h> +#include <linux/perf_event.h> +#include <linux/uaccess.h> +#include <linux/hash.h> +#include <linux/pci.h> +#include <linux/timekeeper_internal.h> +#include <linux/pvclock_gtod.h> +#include <trace/events/kvm.h> + +#define CREATE_TRACE_POINTS +#include "trace.h" + +#include <asm/debugreg.h> #include <asm/msr.h> +#include <asm/desc.h> +#include <asm/mtrr.h> +#include <asm/mce.h> +#include <asm/i387.h> +#include <asm/fpu-internal.h> /* Ugh! */ +#include <asm/xcr.h> +#include <asm/pvclock.h> +#include <asm/div64.h> #define MAX_IO_MSRS 256 -#define CR0_RESERVED_BITS \ - (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ - | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ - | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR4_RESERVED_BITS \ - (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ - | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ - | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) - -#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) -#define EFER_RESERVED_BITS 0xfffffffffffff2fe +#define KVM_MAX_MCE_BANKS 32 +#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P) + +#define emul_to_vcpu(ctxt) \ + container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt) + +/* EFER defaults: + * - enable syscall per default because its emulated by KVM + * - enable LME and LMA per default on 64 bit KVM + */ +#ifdef CONFIG_X86_64 +static +u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); +#else +static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); +#endif #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU -static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); +static void update_cr8_intercept(struct kvm_vcpu *vcpu); +static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; +EXPORT_SYMBOL_GPL(kvm_x86_ops); + +static bool ignore_msrs = 0; +module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); + +unsigned int min_timer_period_us = 500; +module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); + +bool kvm_has_tsc_control; +EXPORT_SYMBOL_GPL(kvm_has_tsc_control); +u32 kvm_max_guest_tsc_khz; +EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); + +/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ +static u32 tsc_tolerance_ppm = 250; +module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); + +static bool backwards_tsc_observed = false; + +#define KVM_NR_SHARED_MSRS 16 + +struct kvm_shared_msrs_global { + int nr; + u32 msrs[KVM_NR_SHARED_MSRS]; +}; + +struct kvm_shared_msrs { + struct user_return_notifier urn; + bool registered; + struct kvm_shared_msr_values { + u64 host; + u64 curr; + } values[KVM_NR_SHARED_MSRS]; +}; + +static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; +static struct kvm_shared_msrs __percpu *shared_msrs; struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, @@ -61,8 +137,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmio_exits", VCPU_STAT(mmio_exits) }, { "signal_exits", VCPU_STAT(signal_exits) }, { "irq_window", VCPU_STAT(irq_window_exits) }, + { "nmi_window", VCPU_STAT(nmi_window_exits) }, { "halt_exits", VCPU_STAT(halt_exits) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, + { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, { "irq_exits", VCPU_STAT(irq_exits) }, { "host_state_reload", VCPU_STAT(host_state_reload) }, @@ -70,6 +148,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "fpu_reload", VCPU_STAT(fpu_reload) }, { "insn_emulation", VCPU_STAT(insn_emulation) }, { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, + { "irq_injections", VCPU_STAT(irq_injections) }, + { "nmi_injections", VCPU_STAT(nmi_injections) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, @@ -77,389 +157,806 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_flooded", VM_STAT(mmu_flooded) }, { "mmu_recycled", VM_STAT(mmu_recycled) }, { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, + { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, + { "largepages", VM_STAT(lpages) }, { NULL } }; +u64 __read_mostly host_xcr0; -unsigned long segment_base(u16 selector) +static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); + +static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { - struct descriptor_table gdt; - struct segment_descriptor *d; - unsigned long table_base; - unsigned long v; + int i; + for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU); i++) + vcpu->arch.apf.gfns[i] = ~0; +} - if (selector == 0) - return 0; +static void kvm_on_user_return(struct user_return_notifier *urn) +{ + unsigned slot; + struct kvm_shared_msrs *locals + = container_of(urn, struct kvm_shared_msrs, urn); + struct kvm_shared_msr_values *values; - asm("sgdt %0" : "=m"(gdt)); - table_base = gdt.base; + for (slot = 0; slot < shared_msrs_global.nr; ++slot) { + values = &locals->values[slot]; + if (values->host != values->curr) { + wrmsrl(shared_msrs_global.msrs[slot], values->host); + values->curr = values->host; + } + } + locals->registered = false; + user_return_notifier_unregister(urn); +} - if (selector & 4) { /* from ldt */ - u16 ldt_selector; +static void shared_msr_update(unsigned slot, u32 msr) +{ + u64 value; + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); - asm("sldt %0" : "=g"(ldt_selector)); - table_base = segment_base(ldt_selector); + /* only read, and nobody should modify it at this time, + * so don't need lock */ + if (slot >= shared_msrs_global.nr) { + printk(KERN_ERR "kvm: invalid MSR slot!"); + return; } - d = (struct segment_descriptor *)(table_base + (selector & ~7)); - v = d->base_low | ((unsigned long)d->base_mid << 16) | - ((unsigned long)d->base_high << 24); -#ifdef CONFIG_X86_64 - if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long) \ - ((struct segment_descriptor_64 *)d)->base_higher) << 32; -#endif - return v; + rdmsrl_safe(msr, &value); + smsr->values[slot].host = value; + smsr->values[slot].curr = value; +} + +void kvm_define_shared_msr(unsigned slot, u32 msr) +{ + if (slot >= shared_msrs_global.nr) + shared_msrs_global.nr = slot + 1; + shared_msrs_global.msrs[slot] = msr; + /* we need ensured the shared_msr_global have been updated */ + smp_wmb(); +} +EXPORT_SYMBOL_GPL(kvm_define_shared_msr); + +static void kvm_shared_msr_cpu_online(void) +{ + unsigned i; + + for (i = 0; i < shared_msrs_global.nr; ++i) + shared_msr_update(i, shared_msrs_global.msrs[i]); +} + +void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +{ + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + + if (((value ^ smsr->values[slot].curr) & mask) == 0) + return; + smsr->values[slot].curr = value; + wrmsrl(shared_msrs_global.msrs[slot], value); + if (!smsr->registered) { + smsr->urn.on_user_return = kvm_on_user_return; + user_return_notifier_register(&smsr->urn); + smsr->registered = true; + } +} +EXPORT_SYMBOL_GPL(kvm_set_shared_msr); + +static void drop_user_return_notifiers(void *ignore) +{ + unsigned int cpu = smp_processor_id(); + struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + + if (smsr->registered) + kvm_on_user_return(&smsr->urn); } -EXPORT_SYMBOL_GPL(segment_base); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) { - if (irqchip_in_kernel(vcpu->kvm)) - return vcpu->arch.apic_base; - else - return vcpu->arch.apic_base; + return vcpu->arch.apic_base; } EXPORT_SYMBOL_GPL(kvm_get_apic_base); -void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data) -{ - /* TODO: reserve bits check */ - if (irqchip_in_kernel(vcpu->kvm)) - kvm_lapic_set_base(vcpu, data); - else - vcpu->arch.apic_base = data; +int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + u64 old_state = vcpu->arch.apic_base & + (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + u64 new_state = msr_info->data & + (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | + 0x2ff | (guest_cpuid_has_x2apic(vcpu) ? 0 : X2APIC_ENABLE); + + if (!msr_info->host_initiated && + ((msr_info->data & reserved_bits) != 0 || + new_state == X2APIC_ENABLE || + (new_state == MSR_IA32_APICBASE_ENABLE && + old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) || + (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) && + old_state == 0))) + return 1; + + kvm_lapic_set_base(vcpu, msr_info->data); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_apic_base); +asmlinkage __visible void kvm_spurious_fault(void) +{ + /* Fault while not rebooting. We want the trace. */ + BUG(); +} +EXPORT_SYMBOL_GPL(kvm_spurious_fault); + +#define EXCPT_BENIGN 0 +#define EXCPT_CONTRIBUTORY 1 +#define EXCPT_PF 2 + +static int exception_class(int vector) +{ + switch (vector) { + case PF_VECTOR: + return EXCPT_PF; + case DE_VECTOR: + case TS_VECTOR: + case NP_VECTOR: + case SS_VECTOR: + case GP_VECTOR: + return EXCPT_CONTRIBUTORY; + default: + break; + } + return EXCPT_BENIGN; +} + +static void kvm_multiple_exception(struct kvm_vcpu *vcpu, + unsigned nr, bool has_error, u32 error_code, + bool reinject) +{ + u32 prev_nr; + int class1, class2; + + kvm_make_request(KVM_REQ_EVENT, vcpu); + + if (!vcpu->arch.exception.pending) { + queue: + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = has_error; + vcpu->arch.exception.nr = nr; + vcpu->arch.exception.error_code = error_code; + vcpu->arch.exception.reinject = reinject; + return; + } + + /* to check exception */ + prev_nr = vcpu->arch.exception.nr; + if (prev_nr == DF_VECTOR) { + /* triple fault -> shutdown */ + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return; + } + class1 = exception_class(prev_nr); + class2 = exception_class(nr); + if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) + || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { + /* generate double fault per SDM Table 5-5 */ + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = true; + vcpu->arch.exception.nr = DF_VECTOR; + vcpu->arch.exception.error_code = 0; + } else + /* replace previous exception with a new one in a hope + that instruction re-execution will regenerate lost + exception */ + goto queue; +} + void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) { - WARN_ON(vcpu->arch.exception.pending); - vcpu->arch.exception.pending = true; - vcpu->arch.exception.has_error_code = false; - vcpu->arch.exception.nr = nr; + kvm_multiple_exception(vcpu, nr, false, 0, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception); -void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, - u32 error_code) +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) +{ + kvm_multiple_exception(vcpu, nr, false, 0, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception); + +void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) +{ + if (err) + kvm_inject_gp(vcpu, 0); + else + kvm_x86_ops->skip_emulated_instruction(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); + +void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; - if (vcpu->arch.exception.pending && vcpu->arch.exception.nr == PF_VECTOR) { - printk(KERN_DEBUG "kvm: inject_page_fault:" - " double fault 0x%lx\n", addr); - vcpu->arch.exception.nr = DF_VECTOR; - vcpu->arch.exception.error_code = 0; - return; - } - vcpu->arch.cr2 = addr; - kvm_queue_exception_e(vcpu, PF_VECTOR, error_code); + vcpu->arch.cr2 = fault->address; + kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); +} +EXPORT_SYMBOL_GPL(kvm_inject_page_fault); + +void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) +{ + if (mmu_is_nested(vcpu) && !fault->nested_page_fault) + vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault); + else + vcpu->arch.mmu.inject_page_fault(vcpu, fault); } +void kvm_inject_nmi(struct kvm_vcpu *vcpu) +{ + atomic_inc(&vcpu->arch.nmi_queued); + kvm_make_request(KVM_REQ_NMI, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_inject_nmi); + void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { - WARN_ON(vcpu->arch.exception.pending); - vcpu->arch.exception.pending = true; - vcpu->arch.exception.has_error_code = true; - vcpu->arch.exception.nr = nr; - vcpu->arch.exception.error_code = error_code; + kvm_multiple_exception(vcpu, nr, true, error_code, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception_e); -static void __queue_exception(struct kvm_vcpu *vcpu) +void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { - kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); + kvm_multiple_exception(vcpu, nr, true, error_code, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); + +/* + * Checks if cpl <= required_cpl; if true, return true. Otherwise queue + * a #GP and return false. + */ +bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) +{ + if (kvm_x86_ops->get_cpl(vcpu) <= required_cpl) + return true; + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return false; +} +EXPORT_SYMBOL_GPL(kvm_require_cpl); + +/* + * This function will be used to read from the physical memory of the currently + * running guest. The difference to kvm_read_guest_page is that this function + * can read from guest physical or from the guest's guest physical memory. + */ +int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gfn_t ngfn, void *data, int offset, int len, + u32 access) +{ + gfn_t real_gfn; + gpa_t ngpa; + + ngpa = gfn_to_gpa(ngfn); + real_gfn = mmu->translate_gpa(vcpu, ngpa, access); + if (real_gfn == UNMAPPED_GVA) + return -EFAULT; + + real_gfn = gpa_to_gfn(real_gfn); + + return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); + +int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, + void *data, int offset, int len, u32 access) +{ + return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn, + data, offset, len, access); } /* * Load the pae pdptrs. Return true is they are all valid. */ -int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) +int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) { gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2; int i; int ret; - u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)]; + u64 pdpte[ARRAY_SIZE(mmu->pdptrs)]; - down_read(&vcpu->kvm->slots_lock); - ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte, - offset * sizeof(u64), sizeof(pdpte)); + ret = kvm_read_guest_page_mmu(vcpu, mmu, pdpt_gfn, pdpte, + offset * sizeof(u64), sizeof(pdpte), + PFERR_USER_MASK|PFERR_WRITE_MASK); if (ret < 0) { ret = 0; goto out; } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { - if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) { + if (is_present_gpte(pdpte[i]) && + (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) { ret = 0; goto out; } } ret = 1; - memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs)); + memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_dirty); out: - up_read(&vcpu->kvm->slots_lock); return ret; } +EXPORT_SYMBOL_GPL(load_pdptrs); static bool pdptrs_changed(struct kvm_vcpu *vcpu) { - u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)]; + u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)]; bool changed = true; + int offset; + gfn_t gfn; int r; if (is_long_mode(vcpu) || !is_pae(vcpu)) return false; - down_read(&vcpu->kvm->slots_lock); - r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte)); + if (!test_bit(VCPU_EXREG_PDPTR, + (unsigned long *)&vcpu->arch.regs_avail)) + return true; + + gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT; + offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1); + r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte), + PFERR_USER_MASK | PFERR_WRITE_MASK); if (r < 0) goto out; - changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0; + changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0; out: - up_read(&vcpu->kvm->slots_lock); return changed; } -void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { - if (cr0 & CR0_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", - cr0, vcpu->arch.cr0); - kvm_inject_gp(vcpu, 0); - return; - } + unsigned long old_cr0 = kvm_read_cr0(vcpu); + unsigned long update_bits = X86_CR0_PG | X86_CR0_WP | + X86_CR0_CD | X86_CR0_NW; - if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) { - printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n"); - kvm_inject_gp(vcpu, 0); - return; - } + cr0 |= X86_CR0_ET; - if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) { - printk(KERN_DEBUG "set_cr0: #GP, set PG flag " - "and a clear PE flag\n"); - kvm_inject_gp(vcpu, 0); - return; - } +#ifdef CONFIG_X86_64 + if (cr0 & 0xffffffff00000000UL) + return 1; +#endif + + cr0 &= ~CR0_RESERVED_BITS; + + if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) + return 1; + + if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) + return 1; if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { #ifdef CONFIG_X86_64 - if ((vcpu->arch.shadow_efer & EFER_LME)) { + if ((vcpu->arch.efer & EFER_LME)) { int cs_db, cs_l; - if (!is_pae(vcpu)) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while PAE is disabled\n"); - kvm_inject_gp(vcpu, 0); - return; - } + if (!is_pae(vcpu)) + return 1; kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - if (cs_l) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while CS.L == 1\n"); - kvm_inject_gp(vcpu, 0); - return; - - } + if (cs_l) + return 1; } else #endif - if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - printk(KERN_DEBUG "set_cr0: #GP, pdptrs " - "reserved bits\n"); - kvm_inject_gp(vcpu, 0); - return; - } - + if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, + kvm_read_cr3(vcpu))) + return 1; } + if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + return 1; + kvm_x86_ops->set_cr0(vcpu, cr0); - vcpu->arch.cr0 = cr0; - kvm_mmu_reset_context(vcpu); - return; + if ((cr0 ^ old_cr0) & X86_CR0_PG) { + kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + } + + if ((cr0 ^ old_cr0) & update_bits) + kvm_mmu_reset_context(vcpu); + return 0; } -EXPORT_SYMBOL_GPL(set_cr0); +EXPORT_SYMBOL_GPL(kvm_set_cr0); -void lmsw(struct kvm_vcpu *vcpu, unsigned long msw) +void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { - set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)); + (void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f)); } -EXPORT_SYMBOL_GPL(lmsw); +EXPORT_SYMBOL_GPL(kvm_lmsw); -void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { - if (cr4 & CR4_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); - kvm_inject_gp(vcpu, 0); - return; + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && + !vcpu->guest_xcr0_loaded) { + /* kvm_set_xcr() also depends on this */ + xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); + vcpu->guest_xcr0_loaded = 1; } +} - if (is_long_mode(vcpu)) { - if (!(cr4 & X86_CR4_PAE)) { - printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while " - "in long mode\n"); - kvm_inject_gp(vcpu, 0); - return; - } - } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE) - && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); - kvm_inject_gp(vcpu, 0); - return; +static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +{ + if (vcpu->guest_xcr0_loaded) { + if (vcpu->arch.xcr0 != host_xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); + vcpu->guest_xcr0_loaded = 0; } +} - if (cr4 & X86_CR4_VMXE) { - printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n"); +int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +{ + u64 xcr0 = xcr; + u64 old_xcr0 = vcpu->arch.xcr0; + u64 valid_bits; + + /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ + if (index != XCR_XFEATURE_ENABLED_MASK) + return 1; + if (!(xcr0 & XSTATE_FP)) + return 1; + if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) + return 1; + + /* + * Do not allow the guest to set bits that we do not support + * saving. However, xcr0 bit 0 is always set, even if the + * emulated CPU does not support XSAVE (see fx_init). + */ + valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP; + if (xcr0 & ~valid_bits) + return 1; + + if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR))) + return 1; + + kvm_put_guest_xcr0(vcpu); + vcpu->arch.xcr0 = xcr0; + + if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK) + kvm_update_cpuid(vcpu); + return 0; +} + +int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) +{ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || + __kvm_set_xcr(vcpu, index, xcr)) { kvm_inject_gp(vcpu, 0); - return; + return 1; } - kvm_x86_ops->set_cr4(vcpu, cr4); - vcpu->arch.cr4 = cr4; - kvm_mmu_reset_context(vcpu); + return 0; } -EXPORT_SYMBOL_GPL(set_cr4); +EXPORT_SYMBOL_GPL(kvm_set_xcr); -void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) { - kvm_mmu_flush_tlb(vcpu); - return; - } + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | + X86_CR4_PAE | X86_CR4_SMEP; + if (cr4 & CR4_RESERVED_BITS) + return 1; + + if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE)) + return 1; + + if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP)) + return 1; + + if (!guest_cpuid_has_smap(vcpu) && (cr4 & X86_CR4_SMAP)) + return 1; + + if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE)) + return 1; if (is_long_mode(vcpu)) { - if (cr3 & CR3_L_MODE_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n"); - kvm_inject_gp(vcpu, 0); - return; - } - } else { - if (is_pae(vcpu)) { - if (cr3 & CR3_PAE_RESERVED_BITS) { - printk(KERN_DEBUG - "set_cr3: #GP, reserved bits\n"); - kvm_inject_gp(vcpu, 0); - return; - } - if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) { - printk(KERN_DEBUG "set_cr3: #GP, pdptrs " - "reserved bits\n"); - kvm_inject_gp(vcpu, 0); - return; - } - } - /* - * We don't check reserved bits in nonpae mode, because - * this isn't enforced, and VMware depends on this. - */ - } + if (!(cr4 & X86_CR4_PAE)) + return 1; + } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) + && ((cr4 ^ old_cr4) & pdptr_bits) + && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, + kvm_read_cr3(vcpu))) + return 1; - down_read(&vcpu->kvm->slots_lock); - /* - * Does the new cr3 value map to physical memory? (Note, we - * catch an invalid cr3 even in real-mode, because it would - * cause trouble later on when we turn on paging anyway.) - * - * A real CPU would silently accept an invalid cr3 and would - * attempt to use it - with largely undefined (and often hard - * to debug) behavior on the guest side. - */ - if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT))) - kvm_inject_gp(vcpu, 0); - else { - vcpu->arch.cr3 = cr3; - vcpu->arch.mmu.new_cr3(vcpu); + if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { + if (!guest_cpuid_has_pcid(vcpu)) + return 1; + + /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ + if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) + return 1; } - up_read(&vcpu->kvm->slots_lock); + + if (kvm_x86_ops->set_cr4(vcpu, cr4)) + return 1; + + if (((cr4 ^ old_cr4) & pdptr_bits) || + (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) + kvm_mmu_reset_context(vcpu); + + if ((cr4 ^ old_cr4) & X86_CR4_SMAP) + update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false); + + if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) + kvm_update_cpuid(vcpu); + + return 0; } -EXPORT_SYMBOL_GPL(set_cr3); +EXPORT_SYMBOL_GPL(kvm_set_cr4); -void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) +int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { - if (cr8 & CR8_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8); - kvm_inject_gp(vcpu, 0); - return; + if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { + kvm_mmu_sync_roots(vcpu); + kvm_mmu_flush_tlb(vcpu); + return 0; } + + if (is_long_mode(vcpu)) { + if (cr3 & CR3_L_MODE_RESERVED_BITS) + return 1; + } else if (is_pae(vcpu) && is_paging(vcpu) && + !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + return 1; + + vcpu->arch.cr3 = cr3; + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + kvm_mmu_new_cr3(vcpu); + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_cr3); + +int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) +{ + if (cr8 & CR8_RESERVED_BITS) + return 1; if (irqchip_in_kernel(vcpu->kvm)) kvm_lapic_set_tpr(vcpu, cr8); else vcpu->arch.cr8 = cr8; + return 0; } -EXPORT_SYMBOL_GPL(set_cr8); +EXPORT_SYMBOL_GPL(kvm_set_cr8); -unsigned long get_cr8(struct kvm_vcpu *vcpu) +unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) return kvm_lapic_get_cr8(vcpu); else return vcpu->arch.cr8; } -EXPORT_SYMBOL_GPL(get_cr8); +EXPORT_SYMBOL_GPL(kvm_get_cr8); + +static void kvm_update_dr6(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + kvm_x86_ops->set_dr6(vcpu, vcpu->arch.dr6); +} + +static void kvm_update_dr7(struct kvm_vcpu *vcpu) +{ + unsigned long dr7; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + dr7 = vcpu->arch.guest_debug_dr7; + else + dr7 = vcpu->arch.dr7; + kvm_x86_ops->set_dr7(vcpu, dr7); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; + if (dr7 & DR7_BP_EN_MASK) + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; +} + +static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +{ + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ + /* fall through */ + case 6: + if (val & 0xffffffff00000000ULL) + return -1; /* #GP */ + vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; + kvm_update_dr6(vcpu); + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; /* #UD */ + /* fall through */ + default: /* 7 */ + if (val & 0xffffffff00000000ULL) + return -1; /* #GP */ + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + kvm_update_dr7(vcpu); + break; + } + + return 0; +} + +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +{ + int res; + + res = __kvm_set_dr(vcpu, dr, val); + if (res > 0) + kvm_queue_exception(vcpu, UD_VECTOR); + else if (res < 0) + kvm_inject_gp(vcpu, 0); + + return res; +} +EXPORT_SYMBOL_GPL(kvm_set_dr); + +static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + switch (dr) { + case 0 ... 3: + *val = vcpu->arch.db[dr]; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; + /* fall through */ + case 6: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + *val = vcpu->arch.dr6; + else + *val = kvm_x86_ops->get_dr6(vcpu); + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + return 1; + /* fall through */ + default: /* 7 */ + *val = vcpu->arch.dr7; + break; + } + + return 0; +} + +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + if (_kvm_get_dr(vcpu, dr, val)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_dr); + +bool kvm_rdpmc(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + u64 data; + int err; + + err = kvm_pmu_read_pmc(vcpu, ecx, &data); + if (err) + return err; + kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); + kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32); + return err; +} +EXPORT_SYMBOL_GPL(kvm_rdpmc); /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * * This list is modified at module load time to reflect the - * capabilities of the host cpu. + * capabilities of the host cpu. This capabilities test skips MSRs that are + * kvm-specific. Those are put in the beginning of the list. */ + +#define KVM_SAVE_MSRS_BEGIN 12 static u32 msrs_to_save[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_K6_STAR, + MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TIME_STAMP_COUNTER, + MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS }; static unsigned num_msrs_to_save; -static u32 emulated_msrs[] = { +static const u32 emulated_msrs[] = { + MSR_IA32_TSC_ADJUST, + MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, }; -#ifdef CONFIG_X86_64 - -static void set_efer(struct kvm_vcpu *vcpu, u64 efer) +bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & EFER_RESERVED_BITS) { - printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n", - efer); - kvm_inject_gp(vcpu, 0); - return; + if (efer & efer_reserved_bits) + return false; + + if (efer & EFER_FFXSR) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) + return false; } - if (is_paging(vcpu) - && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) { - printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n"); - kvm_inject_gp(vcpu, 0); - return; + if (efer & EFER_SVME) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) + return false; } - kvm_x86_ops->set_efer(vcpu, efer); + return true; +} +EXPORT_SYMBOL_GPL(kvm_valid_efer); + +static int set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + u64 old_efer = vcpu->arch.efer; + + if (!kvm_valid_efer(vcpu, efer)) + return 1; + + if (is_paging(vcpu) + && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) + return 1; efer &= ~EFER_LMA; - efer |= vcpu->arch.shadow_efer & EFER_LMA; + efer |= vcpu->arch.efer & EFER_LMA; + + kvm_x86_ops->set_efer(vcpu, efer); + + /* Update reserved bits */ + if ((efer ^ old_efer) & EFER_NX) + kvm_mmu_reset_context(vcpu); + + return 0; +} - vcpu->arch.shadow_efer = efer; +void kvm_enable_efer_bits(u64 mask) +{ + efer_reserved_bits &= ~mask; } +EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); -#endif /* * Writes msr value into into the appropriate "register". * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) +int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { - return kvm_x86_ops->set_msr(vcpu, msr_index, data); + return kvm_x86_ops->set_msr(vcpu, msr); } /* @@ -467,43 +964,1276 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) */ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { - return kvm_set_msr(vcpu, index, *data); + struct msr_data msr; + + msr.data = *data; + msr.index = index; + msr.host_initiated = true; + return kvm_set_msr(vcpu, &msr); } +#ifdef CONFIG_X86_64 +struct pvclock_gtod_data { + seqcount_t seq; + + struct { /* extract of a clocksource struct */ + int vclock_mode; + cycle_t cycle_last; + cycle_t mask; + u32 mult; + u32 shift; + } clock; + + /* open coded 'struct timespec' */ + u64 monotonic_time_snsec; + time_t monotonic_time_sec; +}; + +static struct pvclock_gtod_data pvclock_gtod_data; -int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) +static void update_pvclock_gtod(struct timekeeper *tk) { - switch (msr) { + struct pvclock_gtod_data *vdata = &pvclock_gtod_data; + + write_seqcount_begin(&vdata->seq); + + /* copy pvclock gtod data */ + vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->clock->cycle_last; + vdata->clock.mask = tk->clock->mask; + vdata->clock.mult = tk->mult; + vdata->clock.shift = tk->shift; + + vdata->monotonic_time_sec = tk->xtime_sec + + tk->wall_to_monotonic.tv_sec; + vdata->monotonic_time_snsec = tk->xtime_nsec + + (tk->wall_to_monotonic.tv_nsec + << tk->shift); + while (vdata->monotonic_time_snsec >= + (((u64)NSEC_PER_SEC) << tk->shift)) { + vdata->monotonic_time_snsec -= + ((u64)NSEC_PER_SEC) << tk->shift; + vdata->monotonic_time_sec++; + } + + write_seqcount_end(&vdata->seq); +} +#endif + + +static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) +{ + int version; + int r; + struct pvclock_wall_clock wc; + struct timespec boot; + + if (!wall_clock) + return; + + r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version)); + if (r) + return; + + if (version & 1) + ++version; /* first time write, random junk */ + + ++version; + + kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); + + /* + * The guest calculates current wall clock time by adding + * system time (updated by kvm_guest_time_update 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. + */ + getboottime(&boot); + + if (kvm->arch.kvmclock_offset) { + struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset); + boot = timespec_sub(boot, ts); + } + wc.sec = boot.tv_sec; + wc.nsec = boot.tv_nsec; + wc.version = version; + + kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); + + version++; + 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_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, + s8 *pshift, u32 *pmultiplier) +{ + uint64_t scaled64; + int32_t shift = 0; + uint64_t tps64; + uint32_t tps32; + + tps64 = base_khz * 1000LL; + scaled64 = scaled_khz * 1000LL; + while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) { + tps64 >>= 1; + shift--; + } + + tps32 = (uint32_t)tps64; + while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) { + if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000) + scaled64 >>= 1; + else + tps32 <<= 1; + shift++; + } + + *pshift = shift; + *pmultiplier = div_frac(scaled64, tps32); + + pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n", + __func__, base_khz, scaled_khz, shift, *pmultiplier); +} + +static inline u64 get_kernel_ns(void) +{ + struct timespec ts; + + ktime_get_ts(&ts); + monotonic_to_bootbased(&ts); + return timespec_to_ns(&ts); +} + #ifdef CONFIG_X86_64 - case MSR_EFER: - set_efer(vcpu, data); - break; +static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); #endif - case MSR_IA32_MC0_STATUS: - pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n", - __FUNCTION__, data); - break; + +static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); +unsigned long max_tsc_khz; + +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +{ + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); +} + +static u32 adjust_tsc_khz(u32 khz, s32 ppm) +{ + u64 v = (u64)khz * (1000000 + ppm); + do_div(v, 1000000); + return v; +} + +static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) +{ + u32 thresh_lo, thresh_hi; + int use_scaling = 0; + + /* tsc_khz can be zero if TSC calibration fails */ + if (this_tsc_khz == 0) + return; + + /* Compute a scale to convert nanoseconds in TSC cycles */ + kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, + &vcpu->arch.virtual_tsc_shift, + &vcpu->arch.virtual_tsc_mult); + vcpu->arch.virtual_tsc_khz = this_tsc_khz; + + /* + * Compute the variation in TSC rate which is acceptable + * within the range of tolerance and decide if the + * rate being applied is within that bounds of the hardware + * rate. If so, no scaling or compensation need be done. + */ + thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); + thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); + if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) { + pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi); + use_scaling = 1; + } + kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling); +} + +static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) +{ + u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec, + vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); + tsc += vcpu->arch.this_tsc_write; + return tsc; +} + +void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + bool vcpus_matched; + bool do_request = false; + struct kvm_arch *ka = &vcpu->kvm->arch; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&vcpu->kvm->online_vcpus)); + + if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC) + if (!ka->use_master_clock) + do_request = 1; + + if (!vcpus_matched && ka->use_master_clock) + do_request = 1; + + if (do_request) + kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); + + trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, + atomic_read(&vcpu->kvm->online_vcpus), + ka->use_master_clock, gtod->clock.vclock_mode); +#endif +} + +static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) +{ + u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu); + vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; +} + +void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) +{ + struct kvm *kvm = vcpu->kvm; + u64 offset, ns, elapsed; + unsigned long flags; + s64 usdiff; + bool matched; + u64 data = msr->data; + + raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); + offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + ns = get_kernel_ns(); + elapsed = ns - kvm->arch.last_tsc_nsec; + + if (vcpu->arch.virtual_tsc_khz) { + int faulted = 0; + + /* n.b - signed multiplication and division required */ + usdiff = data - kvm->arch.last_tsc_write; +#ifdef CONFIG_X86_64 + usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; +#else + /* do_div() only does unsigned */ + asm("1: idivl %[divisor]\n" + "2: xor %%edx, %%edx\n" + " movl $0, %[faulted]\n" + "3:\n" + ".section .fixup,\"ax\"\n" + "4: movl $1, %[faulted]\n" + " jmp 3b\n" + ".previous\n" + + _ASM_EXTABLE(1b, 4b) + + : "=A"(usdiff), [faulted] "=r" (faulted) + : "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz)); + +#endif + do_div(elapsed, 1000); + usdiff -= elapsed; + if (usdiff < 0) + usdiff = -usdiff; + + /* idivl overflow => difference is larger than USEC_PER_SEC */ + if (faulted) + usdiff = USEC_PER_SEC; + } else + usdiff = USEC_PER_SEC; /* disable TSC match window below */ + + /* + * Special case: TSC write with a small delta (1 second) of virtual + * cycle time against real time is interpreted as an attempt to + * synchronize the CPU. + * + * For a reliable TSC, we can match TSC offsets, and for an unstable + * TSC, we add elapsed time in this computation. We could let the + * compensation code attempt to catch up if we fall behind, but + * it's better to try to match offsets from the beginning. + */ + if (usdiff < USEC_PER_SEC && + vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { + if (!check_tsc_unstable()) { + offset = kvm->arch.cur_tsc_offset; + pr_debug("kvm: matched tsc offset for %llu\n", data); + } else { + u64 delta = nsec_to_cycles(vcpu, elapsed); + data += delta; + offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + pr_debug("kvm: adjusted tsc offset by %llu\n", delta); + } + matched = true; + } else { + /* + * We split periods of matched TSC writes into generations. + * For each generation, we track the original measured + * nanosecond time, offset, and write, so if TSCs are in + * sync, we can match exact offset, and if not, we can match + * exact software computation in compute_guest_tsc() + * + * These values are tracked in kvm->arch.cur_xxx variables. + */ + kvm->arch.cur_tsc_generation++; + kvm->arch.cur_tsc_nsec = ns; + kvm->arch.cur_tsc_write = data; + kvm->arch.cur_tsc_offset = offset; + matched = false; + pr_debug("kvm: new tsc generation %u, clock %llu\n", + kvm->arch.cur_tsc_generation, data); + } + + /* + * We also track th most recent recorded KHZ, write and time to + * allow the matching interval to be extended at each write. + */ + kvm->arch.last_tsc_nsec = ns; + kvm->arch.last_tsc_write = data; + kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; + + vcpu->arch.last_guest_tsc = data; + + /* Keep track of which generation this VCPU has synchronized to */ + vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; + vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; + vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; + + if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated) + update_ia32_tsc_adjust_msr(vcpu, offset); + kvm_x86_ops->write_tsc_offset(vcpu, offset); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + + spin_lock(&kvm->arch.pvclock_gtod_sync_lock); + if (matched) + kvm->arch.nr_vcpus_matched_tsc++; + else + kvm->arch.nr_vcpus_matched_tsc = 0; + + kvm_track_tsc_matching(vcpu); + spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); +} + +EXPORT_SYMBOL_GPL(kvm_write_tsc); + +#ifdef CONFIG_X86_64 + +static cycle_t read_tsc(void) +{ + cycle_t ret; + u64 last; + + /* + * Empirically, a fence (of type that depends on the CPU) + * before rdtsc is enough to ensure that rdtsc is ordered + * with respect to loads. The various CPU manuals are unclear + * as to whether rdtsc can be reordered with later loads, + * but no one has ever seen it happen. + */ + rdtsc_barrier(); + ret = (cycle_t)vget_cycles(); + + last = pvclock_gtod_data.clock.cycle_last; + + if (likely(ret >= last)) + return ret; + + /* + * GCC likes to generate cmov here, but this branch is extremely + * predictable (it's just a funciton of time and the likely is + * very likely) and there's a data dependence, so force GCC + * to generate a branch instead. I don't barrier() because + * we don't actually need a barrier, and if this function + * ever gets inlined it will generate worse code. + */ + asm volatile (""); + return last; +} + +static inline u64 vgettsc(cycle_t *cycle_now) +{ + long v; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + *cycle_now = read_tsc(); + + v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask; + return v * gtod->clock.mult; +} + +static int do_monotonic(struct timespec *ts, cycle_t *cycle_now) +{ + unsigned long seq; + u64 ns; + int mode; + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + + ts->tv_nsec = 0; + do { + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ts->tv_sec = gtod->monotonic_time_sec; + ns = gtod->monotonic_time_snsec; + ns += vgettsc(cycle_now); + ns >>= gtod->clock.shift; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + timespec_add_ns(ts, ns); + + return mode; +} + +/* returns true if host is using tsc clocksource */ +static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now) +{ + struct timespec ts; + + /* checked again under seqlock below */ + if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + return false; + + if (do_monotonic(&ts, cycle_now) != VCLOCK_TSC) + return false; + + monotonic_to_bootbased(&ts); + *kernel_ns = timespec_to_ns(&ts); + + return true; +} +#endif + +/* + * + * Assuming a stable TSC across physical CPUS, and a stable TSC + * across virtual CPUs, the following condition is possible. + * Each numbered line represents an event visible to both + * CPUs at the next numbered event. + * + * "timespecX" represents host monotonic time. "tscX" represents + * RDTSC value. + * + * VCPU0 on CPU0 | VCPU1 on CPU1 + * + * 1. read timespec0,tsc0 + * 2. | timespec1 = timespec0 + N + * | tsc1 = tsc0 + M + * 3. transition to guest | transition to guest + * 4. ret0 = timespec0 + (rdtsc - tsc0) | + * 5. | ret1 = timespec1 + (rdtsc - tsc1) + * | ret1 = timespec0 + N + (rdtsc - (tsc0 + M)) + * + * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity: + * + * - ret0 < ret1 + * - timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M)) + * ... + * - 0 < N - M => M < N + * + * That is, when timespec0 != timespec1, M < N. Unfortunately that is not + * always the case (the difference between two distinct xtime instances + * might be smaller then the difference between corresponding TSC reads, + * when updating guest vcpus pvclock areas). + * + * To avoid that problem, do not allow visibility of distinct + * system_timestamp/tsc_timestamp values simultaneously: use a master + * copy of host monotonic time values. Update that master copy + * in lockstep. + * + * Rely on synchronization of host TSCs and guest TSCs for monotonicity. + * + */ + +static void pvclock_update_vm_gtod_copy(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + struct kvm_arch *ka = &kvm->arch; + int vclock_mode; + bool host_tsc_clocksource, vcpus_matched; + + vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&kvm->online_vcpus)); + + /* + * If the host uses TSC clock, then passthrough TSC as stable + * to the guest. + */ + host_tsc_clocksource = kvm_get_time_and_clockread( + &ka->master_kernel_ns, + &ka->master_cycle_now); + + ka->use_master_clock = host_tsc_clocksource && vcpus_matched + && !backwards_tsc_observed; + + if (ka->use_master_clock) + atomic_set(&kvm_guest_has_master_clock, 1); + + vclock_mode = pvclock_gtod_data.clock.vclock_mode; + trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode, + vcpus_matched); +#endif +} + +static void kvm_gen_update_masterclock(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + int i; + struct kvm_vcpu *vcpu; + struct kvm_arch *ka = &kvm->arch; + + spin_lock(&ka->pvclock_gtod_sync_lock); + kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + pvclock_update_vm_gtod_copy(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + + /* guest entries allowed */ + kvm_for_each_vcpu(i, vcpu, kvm) + clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests); + + spin_unlock(&ka->pvclock_gtod_sync_lock); +#endif +} + +static int kvm_guest_time_update(struct kvm_vcpu *v) +{ + unsigned long flags, this_tsc_khz; + struct kvm_vcpu_arch *vcpu = &v->arch; + struct kvm_arch *ka = &v->kvm->arch; + s64 kernel_ns; + u64 tsc_timestamp, host_tsc; + struct pvclock_vcpu_time_info guest_hv_clock; + u8 pvclock_flags; + bool use_master_clock; + + kernel_ns = 0; + host_tsc = 0; + + /* + * If the host uses TSC clock, then passthrough TSC as stable + * to the guest. + */ + spin_lock(&ka->pvclock_gtod_sync_lock); + use_master_clock = ka->use_master_clock; + if (use_master_clock) { + host_tsc = ka->master_cycle_now; + kernel_ns = ka->master_kernel_ns; + } + spin_unlock(&ka->pvclock_gtod_sync_lock); + + /* Keep irq disabled to prevent changes to the clock */ + local_irq_save(flags); + this_tsc_khz = __get_cpu_var(cpu_tsc_khz); + if (unlikely(this_tsc_khz == 0)) { + local_irq_restore(flags); + kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); + return 1; + } + if (!use_master_clock) { + host_tsc = native_read_tsc(); + kernel_ns = get_kernel_ns(); + } + + tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc); + + /* + * We may have to catch up the TSC to match elapsed wall clock + * time for two reasons, even if kvmclock is used. + * 1) CPU could have been running below the maximum TSC rate + * 2) Broken TSC compensation resets the base at each VCPU + * entry to avoid unknown leaps of TSC even when running + * again on the same CPU. This may cause apparent elapsed + * time to disappear, and the guest to stand still or run + * very slowly. + */ + if (vcpu->tsc_catchup) { + u64 tsc = compute_guest_tsc(v, kernel_ns); + if (tsc > tsc_timestamp) { + adjust_tsc_offset_guest(v, tsc - tsc_timestamp); + tsc_timestamp = tsc; + } + } + + local_irq_restore(flags); + + if (!vcpu->pv_time_enabled) + return 0; + + if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) { + kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz, + &vcpu->hv_clock.tsc_shift, + &vcpu->hv_clock.tsc_to_system_mul); + vcpu->hw_tsc_khz = this_tsc_khz; + } + + /* With all the info we got, fill in the values */ + vcpu->hv_clock.tsc_timestamp = tsc_timestamp; + vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; + vcpu->last_guest_tsc = tsc_timestamp; + + /* + * 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 increase by 2 at the end. + */ + vcpu->hv_clock.version += 2; + + if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + &guest_hv_clock, sizeof(guest_hv_clock)))) + return 0; + + /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ + pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); + + if (vcpu->pvclock_set_guest_stopped_request) { + pvclock_flags |= PVCLOCK_GUEST_STOPPED; + vcpu->pvclock_set_guest_stopped_request = false; + } + + /* If the host uses TSC clocksource, then it is stable */ + if (use_master_clock) + pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; + + vcpu->hv_clock.flags = pvclock_flags; + + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); + return 0; +} + +/* + * kvmclock updates which are isolated to a given vcpu, such as + * vcpu->cpu migration, should not allow system_timestamp from + * the rest of the vcpus to remain static. Otherwise ntp frequency + * correction applies to one vcpu's system_timestamp but not + * the others. + * + * So in those cases, request a kvmclock update for all vcpus. + * We need to rate-limit these requests though, as they can + * considerably slow guests that have a large number of vcpus. + * The time for a remote vcpu to update its kvmclock is bound + * by the delay we use to rate-limit the updates. + */ + +#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100) + +static void kvmclock_update_fn(struct work_struct *work) +{ + int i; + struct delayed_work *dwork = to_delayed_work(work); + struct kvm_arch *ka = container_of(dwork, struct kvm_arch, + kvmclock_update_work); + struct kvm *kvm = container_of(ka, struct kvm, arch); + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + kvm_vcpu_kick(vcpu); + } +} + +static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) +{ + struct kvm *kvm = v->kvm; + + set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests); + schedule_delayed_work(&kvm->arch.kvmclock_update_work, + KVMCLOCK_UPDATE_DELAY); +} + +#define KVMCLOCK_SYNC_PERIOD (300 * HZ) + +static void kvmclock_sync_fn(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct kvm_arch *ka = container_of(dwork, struct kvm_arch, + kvmclock_sync_work); + struct kvm *kvm = container_of(ka, struct kvm, arch); + + schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, + KVMCLOCK_SYNC_PERIOD); +} + +static bool msr_mtrr_valid(unsigned msr) +{ + switch (msr) { + case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: + case MSR_MTRRfix64K_00000: + case MSR_MTRRfix16K_80000: + case MSR_MTRRfix16K_A0000: + case MSR_MTRRfix4K_C0000: + case MSR_MTRRfix4K_C8000: + case MSR_MTRRfix4K_D0000: + case MSR_MTRRfix4K_D8000: + case MSR_MTRRfix4K_E0000: + case MSR_MTRRfix4K_E8000: + case MSR_MTRRfix4K_F0000: + case MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: + case MSR_IA32_CR_PAT: + return true; + case 0x2f8: + return true; + } + return false; +} + +static bool valid_pat_type(unsigned t) +{ + return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ +} + +static bool valid_mtrr_type(unsigned t) +{ + return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ +} + +static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int i; + + if (!msr_mtrr_valid(msr)) + return false; + + if (msr == MSR_IA32_CR_PAT) { + for (i = 0; i < 8; i++) + if (!valid_pat_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } else if (msr == MSR_MTRRdefType) { + if (data & ~0xcff) + return false; + return valid_mtrr_type(data & 0xff); + } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { + for (i = 0; i < 8 ; i++) + if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } + + /* variable MTRRs */ + return valid_mtrr_type(data & 0xff); +} + +static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + + if (!mtrr_valid(vcpu, msr, data)) + return 1; + + if (msr == MSR_MTRRdefType) { + vcpu->arch.mtrr_state.def_type = data; + vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; + } else if (msr == MSR_MTRRfix64K_00000) + p[0] = data; + else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) + p[1 + msr - MSR_MTRRfix16K_80000] = data; + else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) + p[3 + msr - MSR_MTRRfix4K_C0000] = data; + else if (msr == MSR_IA32_CR_PAT) + vcpu->arch.pat = data; + else { /* Variable MTRRs */ + int idx, is_mtrr_mask; + u64 *pt; + + idx = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * idx; + if (!is_mtrr_mask) + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + else + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; + *pt = data; + } + + kvm_mmu_reset_context(vcpu); + return 0; +} + +static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; + + switch (msr) { case MSR_IA32_MCG_STATUS: - pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", - __FUNCTION__, data); + vcpu->arch.mcg_status = data; break; case MSR_IA32_MCG_CTL: - pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n", - __FUNCTION__, data); + if (!(mcg_cap & MCG_CTL_P)) + return 1; + if (data != 0 && data != ~(u64)0) + return -1; + vcpu->arch.mcg_ctl = data; + break; + default: + if (msr >= MSR_IA32_MC0_CTL && + msr < MSR_IA32_MC0_CTL + 4 * bank_num) { + u32 offset = msr - MSR_IA32_MC0_CTL; + /* only 0 or all 1s can be written to IA32_MCi_CTL + * some Linux kernels though clear bit 10 in bank 4 to + * workaround a BIOS/GART TBL issue on AMD K8s, ignore + * this to avoid an uncatched #GP in the guest + */ + if ((offset & 0x3) == 0 && + data != 0 && (data | (1 << 10)) != ~(u64)0) + return -1; + vcpu->arch.mce_banks[offset] = data; + break; + } + return 1; + } + return 0; +} + +static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + int lm = is_long_mode(vcpu); + u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 + : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + u8 *page; + int r; + + r = -E2BIG; + if (page_num >= blob_size) + goto out; + r = -ENOMEM; + page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE); + if (IS_ERR(page)) { + r = PTR_ERR(page); + goto out; + } + if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + goto out_free; + r = 0; +out_free: + kfree(page); +out: + return r; +} + +static bool kvm_hv_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; +} + +static bool kvm_hv_msr_partition_wide(u32 msr) +{ + bool r = false; + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + case HV_X64_MSR_REFERENCE_TSC: + case HV_X64_MSR_TIME_REF_COUNT: + r = true; + break; + } + + return r; +} + +static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + kvm->arch.hv_guest_os_id = data; + /* setting guest os id to zero disables hypercall page */ + if (!kvm->arch.hv_guest_os_id) + kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; + break; + case HV_X64_MSR_HYPERCALL: { + u64 gfn; + unsigned long addr; + u8 instructions[4]; + + /* if guest os id is not set hypercall should remain disabled */ + if (!kvm->arch.hv_guest_os_id) + break; + if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { + kvm->arch.hv_hypercall = data; + break; + } + gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + kvm_x86_ops->patch_hypercall(vcpu, instructions); + ((unsigned char *)instructions)[3] = 0xc3; /* ret */ + if (__copy_to_user((void __user *)addr, instructions, 4)) + return 1; + kvm->arch.hv_hypercall = data; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_REFERENCE_TSC: { + u64 gfn; + HV_REFERENCE_TSC_PAGE tsc_ref; + memset(&tsc_ref, 0, sizeof(tsc_ref)); + kvm->arch.hv_tsc_page = data; + if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + break; + gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, + &tsc_ref, sizeof(tsc_ref))) + return 1; + mark_page_dirty(kvm, gfn); break; + } + default: + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + return 0; +} + +static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + switch (msr) { + case HV_X64_MSR_APIC_ASSIST_PAGE: { + u64 gfn; + unsigned long addr; + + if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { + vcpu->arch.hv_vapic = data; + if (kvm_lapic_enable_pv_eoi(vcpu, 0)) + return 1; + break; + } + gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(vcpu->kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + if (__clear_user((void __user *)addr, PAGE_SIZE)) + return 1; + vcpu->arch.hv_vapic = data; + mark_page_dirty(vcpu->kvm, gfn); + if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) + return 1; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); + default: + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + + return 0; +} + +static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) +{ + gpa_t gpa = data & ~0x3f; + + /* Bits 2:5 are reserved, Should be zero */ + if (data & 0x3c) + return 1; + + vcpu->arch.apf.msr_val = data; + + if (!(data & KVM_ASYNC_PF_ENABLED)) { + kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + return 0; + } + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + sizeof(u32))) + return 1; + + vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); + kvm_async_pf_wakeup_all(vcpu); + return 0; +} + +static void kvmclock_reset(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pv_time_enabled = false; +} + +static void accumulate_steal_time(struct kvm_vcpu *vcpu) +{ + u64 delta; + + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) + return; + + delta = current->sched_info.run_delay - vcpu->arch.st.last_steal; + vcpu->arch.st.last_steal = current->sched_info.run_delay; + vcpu->arch.st.accum_steal = delta; +} + +static void record_steal_time(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) + return; + + if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) + return; + + vcpu->arch.st.steal.steal += vcpu->arch.st.accum_steal; + vcpu->arch.st.steal.version += 2; + vcpu->arch.st.accum_steal = 0; + + kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); +} + +int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + bool pr = false; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + switch (msr) { + case MSR_AMD64_NB_CFG: case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: - case 0x200 ... 0x2ff: /* MTRRs */ + case MSR_VM_HSAVE_PA: + case MSR_AMD64_PATCH_LOADER: + case MSR_AMD64_BU_CFG2: + break; + + case MSR_EFER: + return set_efer(vcpu, data); + case MSR_K7_HWCR: + data &= ~(u64)0x40; /* ignore flush filter disable */ + data &= ~(u64)0x100; /* ignore ignne emulation enable */ + data &= ~(u64)0x8; /* ignore TLB cache disable */ + if (data != 0) { + vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", + data); + return 1; + } + break; + case MSR_FAM10H_MMIO_CONF_BASE: + if (data != 0) { + vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " + "0x%llx\n", data); + return 1; + } + break; + case MSR_IA32_DEBUGCTLMSR: + if (!data) { + /* We support the non-activated case already */ + break; + } else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) { + /* Values other than LBR and BTF are vendor-specific, + thus reserved and should throw a #GP */ + return 1; + } + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); break; + case 0x200 ... 0x2ff: + return set_msr_mtrr(vcpu, msr, data); case MSR_IA32_APICBASE: - kvm_set_apic_base(vcpu, data); + return kvm_set_apic_base(vcpu, msr_info); + case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + return kvm_x2apic_msr_write(vcpu, msr, data); + case MSR_IA32_TSCDEADLINE: + kvm_set_lapic_tscdeadline_msr(vcpu, data); + break; + case MSR_IA32_TSC_ADJUST: + if (guest_cpuid_has_tsc_adjust(vcpu)) { + if (!msr_info->host_initiated) { + u64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; + kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true); + } + vcpu->arch.ia32_tsc_adjust_msr = data; + } break; case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; + case MSR_KVM_WALL_CLOCK_NEW: + case MSR_KVM_WALL_CLOCK: + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data); + break; + case MSR_KVM_SYSTEM_TIME_NEW: + case MSR_KVM_SYSTEM_TIME: { + u64 gpa_offset; + kvmclock_reset(vcpu); + + vcpu->arch.time = data; + kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); + + /* we verify if the enable bit is set... */ + if (!(data & 1)) + break; + + gpa_offset = data & ~(PAGE_MASK | 1); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.pv_time, data & ~1ULL, + sizeof(struct pvclock_vcpu_time_info))) + vcpu->arch.pv_time_enabled = false; + else + vcpu->arch.pv_time_enabled = true; + + break; + } + case MSR_KVM_ASYNC_PF_EN: + if (kvm_pv_enable_async_pf(vcpu, data)) + return 1; + break; + case MSR_KVM_STEAL_TIME: + + if (unlikely(!sched_info_on())) + return 1; + + if (data & KVM_STEAL_RESERVED_MASK) + return 1; + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, + data & KVM_STEAL_VALID_BITS, + sizeof(struct kvm_steal_time))) + return 1; + + vcpu->arch.st.msr_val = data; + + if (!(data & KVM_MSR_ENABLED)) + break; + + vcpu->arch.st.last_steal = current->sched_info.run_delay; + + preempt_disable(); + accumulate_steal_time(vcpu); + preempt_enable(); + + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + + break; + case MSR_KVM_PV_EOI_EN: + if (kvm_lapic_enable_pv_eoi(vcpu, data)) + return 1; + break; + + case MSR_IA32_MCG_CTL: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: + return set_msr_mce(vcpu, msr, data); + + /* Performance counters are not protected by a CPUID bit, + * so we should check all of them in the generic path for the sake of + * cross vendor migration. + * Writing a zero into the event select MSRs disables them, + * which we perfectly emulate ;-). Any other value should be at least + * reported, some guests depend on them. + */ + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + if (data != 0) + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; + /* at least RHEL 4 unconditionally writes to the perfctr registers, + * so we ignore writes to make it happy. + */ + case MSR_K7_PERFCTR0: + case MSR_K7_PERFCTR1: + case MSR_K7_PERFCTR2: + case MSR_K7_PERFCTR3: + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: + pr = true; + case MSR_P6_EVNTSEL0: + case MSR_P6_EVNTSEL1: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr_info); + + if (pr || data != 0) + vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); + break; + case MSR_K7_CLK_CTL: + /* + * Ignore all writes to this no longer documented MSR. + * Writes are only relevant for old K7 processors, + * all pre-dating SVM, but a recommended workaround from + * AMD for these chips. It is possible to specify the + * affected processor models on the command line, hence + * the need to ignore the workaround. + */ + break; + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = set_msr_hyperv_pw(vcpu, msr, data); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return set_msr_hyperv(vcpu, msr, data); + break; + case MSR_IA32_BBL_CR_CTL3: + /* Drop writes to this legacy MSR -- see rdmsr + * counterpart for further detail. + */ + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); + break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.length = data; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + vcpu->arch.osvw.status = data; + break; default: - pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); - return 1; + if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) + return xen_hvm_config(vcpu, data); + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr_info); + if (!ignore_msrs) { + vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", + msr, data); + return 1; + } else { + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", + msr, data); + break; + } } return 0; } @@ -520,50 +2250,299 @@ int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); } -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; + + if (!msr_mtrr_valid(msr)) + return 1; + + if (msr == MSR_MTRRdefType) + *pdata = vcpu->arch.mtrr_state.def_type + + (vcpu->arch.mtrr_state.enabled << 10); + else if (msr == MSR_MTRRfix64K_00000) + *pdata = p[0]; + else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) + *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; + else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) + *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; + else if (msr == MSR_IA32_CR_PAT) + *pdata = vcpu->arch.pat; + else { /* Variable MTRRs */ + int idx, is_mtrr_mask; + u64 *pt; + + idx = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * idx; + if (!is_mtrr_mask) + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; + else + pt = + (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; + *pdata = *pt; + } + + return 0; +} + +static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 data; + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; switch (msr) { - case 0xc0010010: /* SYSCFG */ - case 0xc0010015: /* HWCR */ - case MSR_IA32_PLATFORM_ID: case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: - case MSR_IA32_MC0_CTL: - case MSR_IA32_MCG_STATUS: + data = 0; + break; case MSR_IA32_MCG_CAP: + data = vcpu->arch.mcg_cap; + break; case MSR_IA32_MCG_CTL: - case MSR_IA32_MC0_MISC: - case MSR_IA32_MC0_MISC+4: - case MSR_IA32_MC0_MISC+8: - case MSR_IA32_MC0_MISC+12: - case MSR_IA32_MC0_MISC+16: - case MSR_IA32_UCODE_REV: - case MSR_IA32_PERF_STATUS: + if (!(mcg_cap & MCG_CTL_P)) + return 1; + data = vcpu->arch.mcg_ctl; + break; + case MSR_IA32_MCG_STATUS: + data = vcpu->arch.mcg_status; + break; + default: + if (msr >= MSR_IA32_MC0_CTL && + msr < MSR_IA32_MC0_CTL + 4 * bank_num) { + u32 offset = msr - MSR_IA32_MC0_CTL; + data = vcpu->arch.mce_banks[offset]; + break; + } + return 1; + } + *pdata = data; + return 0; +} + +static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + data = kvm->arch.hv_guest_os_id; + break; + case HV_X64_MSR_HYPERCALL: + data = kvm->arch.hv_hypercall; + break; + case HV_X64_MSR_TIME_REF_COUNT: { + data = + div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + break; + } + case HV_X64_MSR_REFERENCE_TSC: + data = kvm->arch.hv_tsc_page; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + + *pdata = data; + return 0; +} + +static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + + switch (msr) { + case HV_X64_MSR_VP_INDEX: { + int r; + struct kvm_vcpu *v; + kvm_for_each_vcpu(r, v, vcpu->kvm) { + if (v == vcpu) { + data = r; + break; + } + } + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = vcpu->arch.hv_vapic; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} + +int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data; + + switch (msr) { + case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: - /* MTRR registers */ - case 0xfe: - case 0x200 ... 0x2ff: + case MSR_IA32_DEBUGCTLMSR: + case MSR_IA32_LASTBRANCHFROMIP: + case MSR_IA32_LASTBRANCHTOIP: + case MSR_IA32_LASTINTFROMIP: + case MSR_IA32_LASTINTTOIP: + case MSR_K8_SYSCFG: + case MSR_K7_HWCR: + case MSR_VM_HSAVE_PA: + case MSR_K7_EVNTSEL0: + case MSR_K7_PERFCTR0: + case MSR_K8_INT_PENDING_MSG: + case MSR_AMD64_NB_CFG: + case MSR_FAM10H_MMIO_CONF_BASE: + case MSR_AMD64_BU_CFG2: + data = 0; + break; + case MSR_P6_PERFCTR0: + case MSR_P6_PERFCTR1: + case MSR_P6_EVNTSEL0: + case MSR_P6_EVNTSEL1: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_get_msr(vcpu, msr, pdata); data = 0; break; + case MSR_IA32_UCODE_REV: + data = 0x100000000ULL; + break; + case MSR_MTRRcap: + data = 0x500 | KVM_NR_VAR_MTRR; + break; + case 0x200 ... 0x2ff: + return get_msr_mtrr(vcpu, msr, pdata); case 0xcd: /* fsb frequency */ data = 3; break; + /* + * MSR_EBC_FREQUENCY_ID + * Conservative value valid for even the basic CPU models. + * Models 0,1: 000 in bits 23:21 indicating a bus speed of + * 100MHz, model 2 000 in bits 18:16 indicating 100MHz, + * and 266MHz for model 3, or 4. Set Core Clock + * Frequency to System Bus Frequency Ratio to 1 (bits + * 31:24) even though these are only valid for CPU + * models > 2, however guests may end up dividing or + * multiplying by zero otherwise. + */ + case MSR_EBC_FREQUENCY_ID: + data = 1 << 24; + break; case MSR_IA32_APICBASE: data = kvm_get_apic_base(vcpu); break; + case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + return kvm_x2apic_msr_read(vcpu, msr, pdata); + break; + case MSR_IA32_TSCDEADLINE: + data = kvm_get_lapic_tscdeadline_msr(vcpu); + break; + case MSR_IA32_TSC_ADJUST: + data = (u64)vcpu->arch.ia32_tsc_adjust_msr; + break; case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; -#ifdef CONFIG_X86_64 + case MSR_IA32_PERF_STATUS: + /* TSC increment by tick */ + data = 1000ULL; + /* CPU multiplier */ + data |= (((uint64_t)4ULL) << 40); + break; case MSR_EFER: - data = vcpu->arch.shadow_efer; + data = vcpu->arch.efer; + break; + case MSR_KVM_WALL_CLOCK: + case MSR_KVM_WALL_CLOCK_NEW: + data = vcpu->kvm->arch.wall_clock; + break; + case MSR_KVM_SYSTEM_TIME: + case MSR_KVM_SYSTEM_TIME_NEW: + data = vcpu->arch.time; + break; + case MSR_KVM_ASYNC_PF_EN: + data = vcpu->arch.apf.msr_val; + break; + case MSR_KVM_STEAL_TIME: + data = vcpu->arch.st.msr_val; + break; + case MSR_KVM_PV_EOI_EN: + data = vcpu->arch.pv_eoi.msr_val; + break; + case MSR_IA32_P5_MC_ADDR: + case MSR_IA32_P5_MC_TYPE: + case MSR_IA32_MCG_CAP: + case MSR_IA32_MCG_CTL: + case MSR_IA32_MCG_STATUS: + case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: + return get_msr_mce(vcpu, msr, pdata); + case MSR_K7_CLK_CTL: + /* + * Provide expected ramp-up count for K7. All other + * are set to zero, indicating minimum divisors for + * every field. + * + * This prevents guest kernels on AMD host with CPU + * type 6, model 8 and higher from exploding due to + * the rdmsr failing. + */ + data = 0x20000000; + break; + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = get_msr_hyperv_pw(vcpu, msr, pdata); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return get_msr_hyperv(vcpu, msr, pdata); + break; + case MSR_IA32_BBL_CR_CTL3: + /* This legacy MSR exists but isn't fully documented in current + * silicon. It is however accessed by winxp in very narrow + * scenarios where it sets bit #19, itself documented as + * a "reserved" bit. Best effort attempt to source coherent + * read data here should the balance of the register be + * interpreted by the guest: + * + * L2 cache control register 3: 64GB range, 256KB size, + * enabled, latency 0x1, configured + */ + data = 0xbe702111; + break; + case MSR_AMD64_OSVW_ID_LENGTH: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.length; + break; + case MSR_AMD64_OSVW_STATUS: + if (!guest_cpuid_has_osvw(vcpu)) + return 1; + data = vcpu->arch.osvw.status; break; -#endif default: - pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); - return 1; + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_get_msr(vcpu, msr, pdata); + if (!ignore_msrs) { + vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + return 1; + } else { + vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); + data = 0; + } + break; } *pdata = data; return 0; @@ -580,15 +2559,13 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { - int i; - - vcpu_load(vcpu); + int i, idx; + idx = srcu_read_lock(&vcpu->kvm->srcu); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; - - vcpu_put(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); return i; } @@ -616,15 +2593,12 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, if (msrs.nmsrs >= MAX_IO_MSRS) goto out; - r = -ENOMEM; size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; - entries = vmalloc(size); - if (!entries) + entries = memdup_user(user_msrs->entries, size); + if (IS_ERR(entries)) { + r = PTR_ERR(entries); goto out; - - r = -EFAULT; - if (copy_from_user(entries, user_msrs->entries, size)) - goto out_free; + } r = n = __msr_io(vcpu, &msrs, entries, do_msr); if (r < 0) @@ -637,46 +2611,11 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, r = n; out_free: - vfree(entries); + kfree(entries); out: return r; } -/* - * Make sure that a cpu that is being hot-unplugged does not have any vcpus - * cached on it. - */ -void decache_vcpus_on_cpu(int cpu) -{ - struct kvm *vm; - struct kvm_vcpu *vcpu; - int i; - - spin_lock(&kvm_lock); - list_for_each_entry(vm, &vm_list, vm_list) - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = vm->vcpus[i]; - if (!vcpu) - continue; - /* - * If the vcpu is locked, then it is running on some - * other cpu and therefore it is not cached on the - * cpu in question. - * - * If it's not locked, check the last cpu it executed - * on. - */ - if (mutex_trylock(&vcpu->mutex)) { - if (vcpu->cpu == cpu) { - kvm_x86_ops->vcpu_decache(vcpu); - vcpu->cpu = -1; - } - mutex_unlock(&vcpu->mutex); - } - } - spin_unlock(&kvm_lock); -} - int kvm_dev_ioctl_check_extension(long ext) { int r; @@ -685,14 +2624,80 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IRQCHIP: case KVM_CAP_HLT: case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: - case KVM_CAP_USER_MEMORY: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_EXT_EMUL_CPUID: + case KVM_CAP_CLOCKSOURCE: + case KVM_CAP_PIT: + case KVM_CAP_NOP_IO_DELAY: + case KVM_CAP_MP_STATE: + case KVM_CAP_SYNC_MMU: + case KVM_CAP_USER_NMI: + case KVM_CAP_REINJECT_CONTROL: + case KVM_CAP_IRQ_INJECT_STATUS: + case KVM_CAP_IRQFD: + case KVM_CAP_IOEVENTFD: + case KVM_CAP_IOEVENTFD_NO_LENGTH: + case KVM_CAP_PIT2: + case KVM_CAP_PIT_STATE2: + case KVM_CAP_SET_IDENTITY_MAP_ADDR: + case KVM_CAP_XEN_HVM: + case KVM_CAP_ADJUST_CLOCK: + case KVM_CAP_VCPU_EVENTS: + case KVM_CAP_HYPERV: + case KVM_CAP_HYPERV_VAPIC: + case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_PCI_SEGMENT: + case KVM_CAP_DEBUGREGS: + case KVM_CAP_X86_ROBUST_SINGLESTEP: + case KVM_CAP_XSAVE: + case KVM_CAP_ASYNC_PF: + case KVM_CAP_GET_TSC_KHZ: + case KVM_CAP_KVMCLOCK_CTRL: + case KVM_CAP_READONLY_MEM: + case KVM_CAP_HYPERV_TIME: + case KVM_CAP_IOAPIC_POLARITY_IGNORED: +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT + case KVM_CAP_ASSIGN_DEV_IRQ: + case KVM_CAP_PCI_2_3: +#endif r = 1; break; + case KVM_CAP_COALESCED_MMIO: + r = KVM_COALESCED_MMIO_PAGE_OFFSET; + break; case KVM_CAP_VAPIC: r = !kvm_x86_ops->cpu_has_accelerated_tpr(); break; + case KVM_CAP_NR_VCPUS: + r = KVM_SOFT_MAX_VCPUS; + break; + case KVM_CAP_MAX_VCPUS: + r = KVM_MAX_VCPUS; + break; + case KVM_CAP_NR_MEMSLOTS: + r = KVM_USER_MEM_SLOTS; + break; + case KVM_CAP_PV_MMU: /* obsolete */ + r = 0; + break; +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT + case KVM_CAP_IOMMU: + r = iommu_present(&pci_bus_type); + break; +#endif + case KVM_CAP_MCE: + r = KVM_MAX_MCE_BANKS; + break; + case KVM_CAP_XCRS: + r = cpu_has_xsave; + break; + case KVM_CAP_TSC_CONTROL: + r = kvm_has_tsc_control; + break; + case KVM_CAP_TSC_DEADLINE_TIMER: + r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER); + break; default: r = 0; break; @@ -721,29 +2726,30 @@ long kvm_arch_dev_ioctl(struct file *filp, if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) goto out; r = -E2BIG; - if (n < num_msrs_to_save) + if (n < msr_list.nmsrs) goto out; r = -EFAULT; if (copy_to_user(user_msr_list->indices, &msrs_to_save, num_msrs_to_save * sizeof(u32))) goto out; - if (copy_to_user(user_msr_list->indices - + num_msrs_to_save * sizeof(u32), + if (copy_to_user(user_msr_list->indices + num_msrs_to_save, &emulated_msrs, ARRAY_SIZE(emulated_msrs) * sizeof(u32))) goto out; r = 0; break; } - case KVM_GET_SUPPORTED_CPUID: { + case KVM_GET_SUPPORTED_CPUID: + case KVM_GET_EMULATED_CPUID: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; - r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, - cpuid_arg->entries); + + r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, + ioctl); if (r) goto out; @@ -753,6 +2759,16 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } + case KVM_X86_GET_MCE_CAP_SUPPORTED: { + u64 mce_cap; + + mce_cap = KVM_MCE_CAP_SUPPORTED; + r = -EFAULT; + if (copy_to_user(argp, &mce_cap, sizeof mce_cap)) + goto out; + r = 0; + break; + } default: r = -EINVAL; } @@ -760,331 +2776,375 @@ out: return r; } +static void wbinvd_ipi(void *garbage) +{ + wbinvd(); +} + +static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + return kvm_arch_has_noncoherent_dma(vcpu->kvm); +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + /* Address WBINVD may be executed by guest */ + if (need_emulate_wbinvd(vcpu)) { + if (kvm_x86_ops->has_wbinvd_exit()) + cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); + else if (vcpu->cpu != -1 && vcpu->cpu != cpu) + smp_call_function_single(vcpu->cpu, + wbinvd_ipi, NULL, 1); + } + kvm_x86_ops->vcpu_load(vcpu, cpu); + + /* Apply any externally detected TSC adjustments (due to suspend) */ + if (unlikely(vcpu->arch.tsc_offset_adjustment)) { + adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); + vcpu->arch.tsc_offset_adjustment = 0; + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + } + + if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { + s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : + native_read_tsc() - vcpu->arch.last_host_tsc; + if (tsc_delta < 0) + mark_tsc_unstable("KVM discovered backwards TSC"); + if (check_tsc_unstable()) { + u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu, + vcpu->arch.last_guest_tsc); + kvm_x86_ops->write_tsc_offset(vcpu, offset); + vcpu->arch.tsc_catchup = 1; + } + /* + * On a host with synchronized TSC, there is no need to update + * kvmclock on vcpu->cpu migration + */ + if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) + kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); + if (vcpu->cpu != cpu) + kvm_migrate_timers(vcpu); + vcpu->cpu = cpu; + } + + accumulate_steal_time(vcpu); + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); + vcpu->arch.last_host_tsc = native_read_tsc(); } -static int is_efer_nx(void) +static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s) { - u64 efer; + kvm_x86_ops->sync_pir_to_irr(vcpu); + memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); - rdmsrl(MSR_EFER, efer); - return efer & EFER_NX; + return 0; } -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) +static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s) { - int i; - struct kvm_cpuid_entry2 *e, *entry; + kvm_apic_post_state_restore(vcpu, s); + update_cr8_intercept(vcpu); - entry = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) { - entry->edx &= ~(1 << 20); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } + return 0; } -/* when an old userspace process fills a new kernel module */ -static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, - struct kvm_cpuid *cpuid, - struct kvm_cpuid_entry __user *entries) +static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, + struct kvm_interrupt *irq) { - int r, i; - struct kvm_cpuid_entry *cpuid_entries; + if (irq->irq >= KVM_NR_INTERRUPTS) + return -EINVAL; + if (irqchip_in_kernel(vcpu->kvm)) + return -ENXIO; - r = -E2BIG; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - goto out; - r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent); - if (!cpuid_entries) - goto out; - r = -EFAULT; - if (copy_from_user(cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry))) - goto out_free; - for (i = 0; i < cpuid->nent; i++) { - vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; - vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; - vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx; - vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx; - vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx; - vcpu->arch.cpuid_entries[i].index = 0; - vcpu->arch.cpuid_entries[i].flags = 0; - vcpu->arch.cpuid_entries[i].padding[0] = 0; - vcpu->arch.cpuid_entries[i].padding[1] = 0; - vcpu->arch.cpuid_entries[i].padding[2] = 0; - } - vcpu->arch.cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); - r = 0; + kvm_queue_interrupt(vcpu, irq->irq, false); + kvm_make_request(KVM_REQ_EVENT, vcpu); -out_free: - vfree(cpuid_entries); -out: - return r; + return 0; } -static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) { - int r; + kvm_inject_nmi(vcpu); - r = -E2BIG; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - goto out; - r = -EFAULT; - if (copy_from_user(&vcpu->arch.cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry2))) - goto out; - vcpu->arch.cpuid_nent = cpuid->nent; return 0; +} -out: - return r; +static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, + struct kvm_tpr_access_ctl *tac) +{ + if (tac->flags) + return -EINVAL; + vcpu->arch.tpr_access_reporting = !!tac->enabled; + return 0; } -static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, + u64 mcg_cap) { int r; + unsigned bank_num = mcg_cap & 0xff, bank; - r = -E2BIG; - if (cpuid->nent < vcpu->arch.cpuid_nent) + r = -EINVAL; + if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) goto out; - r = -EFAULT; - if (copy_to_user(entries, &vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) + if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000)) goto out; - return 0; - + r = 0; + vcpu->arch.mcg_cap = mcg_cap; + /* Init IA32_MCG_CTL to all 1s */ + if (mcg_cap & MCG_CTL_P) + vcpu->arch.mcg_ctl = ~(u64)0; + /* Init IA32_MCi_CTL to all 1s */ + for (bank = 0; bank < bank_num; bank++) + vcpu->arch.mce_banks[bank*4] = ~(u64)0; out: - cpuid->nent = vcpu->arch.cpuid_nent; return r; } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - -static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index) -{ - entry->function = function; - entry->index = index; - cpuid_count(entry->function, entry->index, - &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; -} - -static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) -{ - const u32 kvm_supported_word0_x86_features = bit(X86_FEATURE_FPU) | - bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) | - bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) | - bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) | - bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) | - bit(X86_FEATURE_SEP) | bit(X86_FEATURE_PGE) | - bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) | - bit(X86_FEATURE_CLFLSH) | bit(X86_FEATURE_MMX) | - bit(X86_FEATURE_FXSR) | bit(X86_FEATURE_XMM) | - bit(X86_FEATURE_XMM2) | bit(X86_FEATURE_SELFSNOOP); - const u32 kvm_supported_word1_x86_features = bit(X86_FEATURE_FPU) | - bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) | - bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) | - bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) | - bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) | - bit(X86_FEATURE_PGE) | - bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) | - bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) | - bit(X86_FEATURE_SYSCALL) | - (bit(X86_FEATURE_NX) && is_efer_nx()) | -#ifdef CONFIG_X86_64 - bit(X86_FEATURE_LM) | -#endif - bit(X86_FEATURE_MMXEXT) | - bit(X86_FEATURE_3DNOWEXT) | - bit(X86_FEATURE_3DNOW); - const u32 kvm_supported_word3_x86_features = - bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16); - const u32 kvm_supported_word6_x86_features = - bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY); - - /* all func 2 cpuid_count() should be called on the same cpu */ - get_cpu(); - do_cpuid_1_ent(entry, function, index); - ++*nent; - - switch (function) { - case 0: - entry->eax = min(entry->eax, (u32)0xb); - break; - case 1: - entry->edx &= kvm_supported_word0_x86_features; - entry->ecx &= kvm_supported_word3_x86_features; - break; - /* function 2 entries are STATEFUL. That is, repeated cpuid commands - * may return different values. This forces us to get_cpu() before - * issuing the first command, and also to emulate this annoying behavior - * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ - case 2: { - int t, times = entry->eax & 0xff; - - entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - for (t = 1; t < times && *nent < maxnent; ++t) { - do_cpuid_1_ent(&entry[t], function, 0); - entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - ++*nent; - } - break; - } - /* function 4 and 0xb have additional index. */ - case 4: { - int index, cache_type; - - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* read more entries until cache_type is zero */ - for (index = 1; *nent < maxnent; ++index) { - cache_type = entry[index - 1].eax & 0x1f; - if (!cache_type) - break; - do_cpuid_1_ent(&entry[index], function, index); - entry[index].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; - } - break; - } - case 0xb: { - int index, level_type; +static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, + struct kvm_x86_mce *mce) +{ + u64 mcg_cap = vcpu->arch.mcg_cap; + unsigned bank_num = mcg_cap & 0xff; + u64 *banks = vcpu->arch.mce_banks; - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* read more entries until level_type is zero */ - for (index = 1; *nent < maxnent; ++index) { - level_type = entry[index - 1].ecx & 0xff; - if (!level_type) - break; - do_cpuid_1_ent(&entry[index], function, index); - entry[index].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; + if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL)) + return -EINVAL; + /* + * if IA32_MCG_CTL is not all 1s, the uncorrected error + * reporting is disabled + */ + if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) && + vcpu->arch.mcg_ctl != ~(u64)0) + return 0; + banks += 4 * mce->bank; + /* + * if IA32_MCi_CTL is not all 1s, the uncorrected error + * reporting is disabled for the bank + */ + if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0) + return 0; + if (mce->status & MCI_STATUS_UC) { + if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || + !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) { + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return 0; } - break; - } - case 0x80000000: - entry->eax = min(entry->eax, 0x8000001a); - break; - case 0x80000001: - entry->edx &= kvm_supported_word1_x86_features; - entry->ecx &= kvm_supported_word6_x86_features; - break; - } - put_cpu(); + if (banks[1] & MCI_STATUS_VAL) + mce->status |= MCI_STATUS_OVER; + banks[2] = mce->addr; + banks[3] = mce->misc; + vcpu->arch.mcg_status = mce->mcg_status; + banks[1] = mce->status; + kvm_queue_exception(vcpu, MC_VECTOR); + } else if (!(banks[1] & MCI_STATUS_VAL) + || !(banks[1] & MCI_STATUS_UC)) { + if (banks[1] & MCI_STATUS_VAL) + mce->status |= MCI_STATUS_OVER; + banks[2] = mce->addr; + banks[3] = mce->misc; + banks[1] = mce->status; + } else + banks[1] |= MCI_STATUS_OVER; + return 0; } -static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) { - struct kvm_cpuid_entry2 *cpuid_entries; - int limit, nent = 0, r = -E2BIG; - u32 func; + process_nmi(vcpu); + events->exception.injected = + vcpu->arch.exception.pending && + !kvm_exception_is_soft(vcpu->arch.exception.nr); + events->exception.nr = vcpu->arch.exception.nr; + events->exception.has_error_code = vcpu->arch.exception.has_error_code; + events->exception.pad = 0; + events->exception.error_code = vcpu->arch.exception.error_code; - if (cpuid->nent < 1) - goto out; - r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); - if (!cpuid_entries) - goto out; + events->interrupt.injected = + vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft; + events->interrupt.nr = vcpu->arch.interrupt.nr; + events->interrupt.soft = 0; + events->interrupt.shadow = + kvm_x86_ops->get_interrupt_shadow(vcpu, + KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); - do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent); - limit = cpuid_entries[0].eax; - for (func = 1; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; + events->nmi.injected = vcpu->arch.nmi_injected; + events->nmi.pending = vcpu->arch.nmi_pending != 0; + events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + events->nmi.pad = 0; - do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent); - limit = cpuid_entries[nent - 1].eax; - for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - r = -EFAULT; - if (copy_to_user(entries, cpuid_entries, - nent * sizeof(struct kvm_cpuid_entry2))) - goto out_free; - cpuid->nent = nent; - r = 0; + events->sipi_vector = 0; /* never valid when reporting to user space */ -out_free: - vfree(cpuid_entries); -out: - return r; + events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SHADOW); + memset(&events->reserved, 0, sizeof(events->reserved)); } -static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) +static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) { - vcpu_load(vcpu); - memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); - vcpu_put(vcpu); + if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW)) + return -EINVAL; + + process_nmi(vcpu); + vcpu->arch.exception.pending = events->exception.injected; + vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.has_error_code = events->exception.has_error_code; + vcpu->arch.exception.error_code = events->exception.error_code; + + vcpu->arch.interrupt.pending = events->interrupt.injected; + vcpu->arch.interrupt.nr = events->interrupt.nr; + vcpu->arch.interrupt.soft = events->interrupt.soft; + if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) + kvm_x86_ops->set_interrupt_shadow(vcpu, + events->interrupt.shadow); + + vcpu->arch.nmi_injected = events->nmi.injected; + if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) + vcpu->arch.nmi_pending = events->nmi.pending; + kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + + if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && + kvm_vcpu_has_lapic(vcpu)) + vcpu->arch.apic->sipi_vector = events->sipi_vector; + + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } -static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) +static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) { - vcpu_load(vcpu); - memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s); - kvm_apic_post_state_restore(vcpu); - vcpu_put(vcpu); + unsigned long val; - return 0; + memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); + _kvm_get_dr(vcpu, 6, &val); + dbgregs->dr6 = val; + dbgregs->dr7 = vcpu->arch.dr7; + dbgregs->flags = 0; + memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } -static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, - struct kvm_interrupt *irq) +static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) { - if (irq->irq < 0 || irq->irq >= 256) + if (dbgregs->flags) return -EINVAL; - if (irqchip_in_kernel(vcpu->kvm)) - return -ENXIO; - vcpu_load(vcpu); - set_bit(irq->irq, vcpu->arch.irq_pending); - set_bit(irq->irq / BITS_PER_LONG, &vcpu->arch.irq_summary); + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = dbgregs->dr6; + kvm_update_dr6(vcpu); + vcpu->arch.dr7 = dbgregs->dr7; + kvm_update_dr7(vcpu); - vcpu_put(vcpu); + return 0; +} +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + if (cpu_has_xsave) { + memcpy(guest_xsave->region, + &vcpu->arch.guest_fpu.state->xsave, + vcpu->arch.guest_xstate_size); + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &= + vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE; + } else { + memcpy(guest_xsave->region, + &vcpu->arch.guest_fpu.state->fxsave, + sizeof(struct i387_fxsave_struct)); + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = + XSTATE_FPSSE; + } +} + +static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + u64 xstate_bv = + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + + if (cpu_has_xsave) { + /* + * Here we allow setting states that are not present in + * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility + * with old userspace. + */ + if (xstate_bv & ~kvm_supported_xcr0()) + return -EINVAL; + memcpy(&vcpu->arch.guest_fpu.state->xsave, + guest_xsave->region, vcpu->arch.guest_xstate_size); + } else { + if (xstate_bv & ~XSTATE_FPSSE) + return -EINVAL; + memcpy(&vcpu->arch.guest_fpu.state->fxsave, + guest_xsave->region, sizeof(struct i387_fxsave_struct)); + } return 0; } -static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, - struct kvm_tpr_access_ctl *tac) +static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) { - if (tac->flags) + if (!cpu_has_xsave) { + guest_xcrs->nr_xcrs = 0; + return; + } + + guest_xcrs->nr_xcrs = 1; + guest_xcrs->flags = 0; + guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; + guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; +} + +static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, + struct kvm_xcrs *guest_xcrs) +{ + int i, r = 0; + + if (!cpu_has_xsave) return -EINVAL; - vcpu->arch.tpr_access_reporting = !!tac->enabled; + + if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags) + return -EINVAL; + + for (i = 0; i < guest_xcrs->nr_xcrs; i++) + /* Only support XCR0 currently */ + if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) { + r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK, + guest_xcrs->xcrs[i].value); + break; + } + if (r) + r = -EINVAL; + return r; +} + +/* + * kvm_set_guest_paused() indicates to the guest kernel that it has been + * stopped by the hypervisor. This function will be called from the host only. + * EINVAL is returned when the host attempts to set the flag for a guest that + * does not support pv clocks. + */ +static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.pv_time_enabled) + return -EINVAL; + vcpu->arch.pvclock_set_guest_stopped_request = true; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); return 0; } @@ -1094,31 +3154,42 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; - + union { + struct kvm_lapic_state *lapic; + struct kvm_xsave *xsave; + struct kvm_xcrs *xcrs; + void *buffer; + } u; + + u.buffer = NULL; switch (ioctl) { case KVM_GET_LAPIC: { - struct kvm_lapic_state lapic; + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; + u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); - memset(&lapic, 0, sizeof lapic); - r = kvm_vcpu_ioctl_get_lapic(vcpu, &lapic); + r = -ENOMEM; + if (!u.lapic) + goto out; + r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic); if (r) goto out; r = -EFAULT; - if (copy_to_user(argp, &lapic, sizeof lapic)) + if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state))) goto out; r = 0; break; } case KVM_SET_LAPIC: { - struct kvm_lapic_state lapic; - - r = -EFAULT; - if (copy_from_user(&lapic, argp, sizeof lapic)) - goto out; - r = kvm_vcpu_ioctl_set_lapic(vcpu, &lapic);; - if (r) + r = -EINVAL; + if (!vcpu->arch.apic) goto out; - r = 0; + u.lapic = memdup_user(argp, sizeof(*u.lapic)); + if (IS_ERR(u.lapic)) + return PTR_ERR(u.lapic); + + r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); break; } case KVM_INTERRUPT: { @@ -1128,9 +3199,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&irq, argp, sizeof irq)) goto out; r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); - if (r) - goto out; - r = 0; + break; + } + case KVM_NMI: { + r = kvm_vcpu_ioctl_nmi(vcpu); break; } case KVM_SET_CPUID: { @@ -1141,8 +3213,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); - if (r) - goto out; break; } case KVM_SET_CPUID2: { @@ -1153,9 +3223,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, - cpuid_arg->entries); - if (r) - goto out; + cpuid_arg->entries); break; } case KVM_GET_CPUID2: { @@ -1166,7 +3234,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid, - cpuid_arg->entries); + cpuid_arg->entries); if (r) goto out; r = -EFAULT; @@ -1205,107 +3273,189 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&va, argp, sizeof va)) goto out; + r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); + break; + } + case KVM_X86_SETUP_MCE: { + u64 mcg_cap; + + r = -EFAULT; + if (copy_from_user(&mcg_cap, argp, sizeof mcg_cap)) + goto out; + r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap); + break; + } + case KVM_X86_SET_MCE: { + struct kvm_x86_mce mce; + + r = -EFAULT; + if (copy_from_user(&mce, argp, sizeof mce)) + goto out; + r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); + break; + } + case KVM_GET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); + + r = -EFAULT; + if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) + break; r = 0; - kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); break; } + case KVM_SET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + r = -EFAULT; + if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) + break; + + r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + break; + } + case KVM_GET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + + r = -EFAULT; + if (copy_to_user(argp, &dbgregs, + sizeof(struct kvm_debugregs))) + break; + r = 0; + break; + } + case KVM_SET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + r = -EFAULT; + if (copy_from_user(&dbgregs, argp, + sizeof(struct kvm_debugregs))) + break; + + r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs); + break; + } + case KVM_GET_XSAVE: { + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); + r = -ENOMEM; + if (!u.xsave) + break; + + kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); + + r = -EFAULT; + if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) + break; + r = 0; + break; + } + case KVM_SET_XSAVE: { + u.xsave = memdup_user(argp, sizeof(*u.xsave)); + if (IS_ERR(u.xsave)) + return PTR_ERR(u.xsave); + + r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); + break; + } + case KVM_GET_XCRS: { + u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); + r = -ENOMEM; + if (!u.xcrs) + break; + + kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); + + r = -EFAULT; + if (copy_to_user(argp, u.xcrs, + sizeof(struct kvm_xcrs))) + break; + r = 0; + break; + } + case KVM_SET_XCRS: { + u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); + if (IS_ERR(u.xcrs)) + return PTR_ERR(u.xcrs); + + r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); + break; + } + case KVM_SET_TSC_KHZ: { + u32 user_tsc_khz; + + r = -EINVAL; + user_tsc_khz = (u32)arg; + + if (user_tsc_khz >= kvm_max_guest_tsc_khz) + goto out; + + if (user_tsc_khz == 0) + user_tsc_khz = tsc_khz; + + kvm_set_tsc_khz(vcpu, user_tsc_khz); + + r = 0; + goto out; + } + case KVM_GET_TSC_KHZ: { + r = vcpu->arch.virtual_tsc_khz; + goto out; + } + case KVM_KVMCLOCK_CTRL: { + r = kvm_set_guest_paused(vcpu); + goto out; + } default: r = -EINVAL; } out: + kfree(u.buffer); return r; } +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) { int ret; if (addr > (unsigned int)(-3 * PAGE_SIZE)) - return -1; + return -EINVAL; ret = kvm_x86_ops->set_tss_addr(kvm, addr); return ret; } +static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, + u64 ident_addr) +{ + kvm->arch.ept_identity_map_addr = ident_addr; + return 0; +} + static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, u32 kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; } static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) { - return kvm->arch.n_alloc_mmu_pages; -} - -gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) -{ - int i; - struct kvm_mem_alias *alias; - - for (i = 0; i < kvm->arch.naliases; ++i) { - alias = &kvm->arch.aliases[i]; - if (gfn >= alias->base_gfn - && gfn < alias->base_gfn + alias->npages) - return alias->target_gfn + gfn - alias->base_gfn; - } - return gfn; -} - -/* - * Set a new alias region. Aliases map a portion of physical memory into - * another portion. This is useful for memory windows, for example the PC - * VGA region. - */ -static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, - struct kvm_memory_alias *alias) -{ - int r, n; - struct kvm_mem_alias *p; - - r = -EINVAL; - /* General sanity checks */ - if (alias->memory_size & (PAGE_SIZE - 1)) - goto out; - if (alias->guest_phys_addr & (PAGE_SIZE - 1)) - goto out; - if (alias->slot >= KVM_ALIAS_SLOTS) - goto out; - if (alias->guest_phys_addr + alias->memory_size - < alias->guest_phys_addr) - goto out; - if (alias->target_phys_addr + alias->memory_size - < alias->target_phys_addr) - goto out; - - down_write(&kvm->slots_lock); - - p = &kvm->arch.aliases[alias->slot]; - p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; - p->npages = alias->memory_size >> PAGE_SHIFT; - p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT; - - for (n = KVM_ALIAS_SLOTS; n > 0; --n) - if (kvm->arch.aliases[n - 1].npages) - break; - kvm->arch.naliases = n; - - kvm_mmu_zap_all(kvm); - - up_write(&kvm->slots_lock); - - return 0; - -out: - return r; + return kvm->arch.n_max_mmu_pages; } static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) @@ -1325,9 +3475,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -1343,19 +3491,21 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_PIC_MASTER: + spin_lock(&pic_irqchip(kvm)->lock); memcpy(&pic_irqchip(kvm)->pics[0], &chip->chip.pic, sizeof(struct kvm_pic_state)); + spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_PIC_SLAVE: + spin_lock(&pic_irqchip(kvm)->lock); memcpy(&pic_irqchip(kvm)->pics[1], &chip->chip.pic, sizeof(struct kvm_pic_state)); + spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_IOAPIC: - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -1365,153 +3515,419 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) return r; } -/* - * Get (and clear) the dirty memory log for a memory slot. +static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + int r = 0; + + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state)); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) +{ + int r = 0; + + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); + kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + int r = 0; + + mutex_lock(&kvm->arch.vpit->pit_state.lock); + memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, + sizeof(ps->channels)); + ps->flags = kvm->arch.vpit->pit_state.flags; + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + memset(&ps->reserved, 0, sizeof(ps->reserved)); + return r; +} + +static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) +{ + int r = 0, start = 0; + u32 prev_legacy, cur_legacy; + mutex_lock(&kvm->arch.vpit->pit_state.lock); + prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; + cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; + if (!prev_legacy && cur_legacy) + start = 1; + memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, + sizeof(kvm->arch.vpit->pit_state.channels)); + kvm->arch.vpit->pit_state.flags = ps->flags; + kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return r; +} + +static int kvm_vm_ioctl_reinject(struct kvm *kvm, + struct kvm_reinject_control *control) +{ + if (!kvm->arch.vpit) + return -ENXIO; + mutex_lock(&kvm->arch.vpit->pit_state.lock); + kvm->arch.vpit->pit_state.reinject = control->pit_reinject; + mutex_unlock(&kvm->arch.vpit->pit_state.lock); + return 0; +} + +/** + * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot + * @kvm: kvm instance + * @log: slot id and address to which we copy the log + * + * We need to keep it in mind that VCPU threads can write to the bitmap + * concurrently. So, to avoid losing data, we keep the following order for + * each bit: + * + * 1. Take a snapshot of the bit and clear it if needed. + * 2. Write protect the corresponding page. + * 3. Flush TLB's if needed. + * 4. Copy the snapshot to the userspace. + * + * Between 2 and 3, the guest may write to the page using the remaining TLB + * entry. This is not a problem because the page will be reported dirty at + * step 4 using the snapshot taken before and step 3 ensures that successive + * writes will be logged for the next call. */ -int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log) +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { int r; - int n; struct kvm_memory_slot *memslot; - int is_dirty = 0; + unsigned long n, i; + unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap_buffer; + bool is_dirty = false; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); - r = kvm_get_dirty_log(kvm, log, &is_dirty); - if (r) + r = -EINVAL; + if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - /* If nothing is dirty, don't bother messing with page tables. */ - if (is_dirty) { - kvm_mmu_slot_remove_write_access(kvm, log->slot); - kvm_flush_remote_tlbs(kvm); - memslot = &kvm->memslots[log->slot]; - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; - memset(memslot->dirty_bitmap, 0, n); + memslot = id_to_memslot(kvm->memslots, log->slot); + + dirty_bitmap = memslot->dirty_bitmap; + r = -ENOENT; + if (!dirty_bitmap) + goto out; + + n = kvm_dirty_bitmap_bytes(memslot); + + dirty_bitmap_buffer = dirty_bitmap + n / sizeof(long); + memset(dirty_bitmap_buffer, 0, n); + + spin_lock(&kvm->mmu_lock); + + for (i = 0; i < n / sizeof(long); i++) { + unsigned long mask; + gfn_t offset; + + if (!dirty_bitmap[i]) + continue; + + is_dirty = true; + + mask = xchg(&dirty_bitmap[i], 0); + dirty_bitmap_buffer[i] = mask; + + offset = i * BITS_PER_LONG; + kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask); } + + spin_unlock(&kvm->mmu_lock); + + /* See the comments in kvm_mmu_slot_remove_write_access(). */ + lockdep_assert_held(&kvm->slots_lock); + + /* + * All the TLBs can be flushed out of mmu lock, see the comments in + * kvm_mmu_slot_remove_write_access(). + */ + if (is_dirty) + kvm_flush_remote_tlbs(kvm); + + r = -EFAULT; + if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) + goto out; + r = 0; out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, + bool line_status) +{ + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event->irq, irq_event->level, + line_status); + return 0; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; + /* + * This union makes it completely explicit to gcc-3.x + * that these two variables' stack usage should be + * combined, not added together. + */ + union { + struct kvm_pit_state ps; + struct kvm_pit_state2 ps2; + struct kvm_pit_config pit_config; + } u; switch (ioctl) { case KVM_SET_TSS_ADDR: r = kvm_vm_ioctl_set_tss_addr(kvm, arg); - if (r < 0) - goto out; break; - case KVM_SET_MEMORY_REGION: { - struct kvm_memory_region kvm_mem; - struct kvm_userspace_memory_region kvm_userspace_mem; + case KVM_SET_IDENTITY_MAP_ADDR: { + u64 ident_addr; r = -EFAULT; - if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem)) - goto out; - kvm_userspace_mem.slot = kvm_mem.slot; - kvm_userspace_mem.flags = kvm_mem.flags; - kvm_userspace_mem.guest_phys_addr = kvm_mem.guest_phys_addr; - kvm_userspace_mem.memory_size = kvm_mem.memory_size; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 0); - if (r) + if (copy_from_user(&ident_addr, argp, sizeof ident_addr)) goto out; + r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr); break; } case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); - if (r) - goto out; break; case KVM_GET_NR_MMU_PAGES: r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); break; - case KVM_SET_MEMORY_ALIAS: { - struct kvm_memory_alias alias; + case KVM_CREATE_IRQCHIP: { + struct kvm_pic *vpic; - r = -EFAULT; - if (copy_from_user(&alias, argp, sizeof alias)) - goto out; - r = kvm_vm_ioctl_set_memory_alias(kvm, &alias); - if (r) - goto out; - break; - } - case KVM_CREATE_IRQCHIP: + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpic) + goto create_irqchip_unlock; + r = -EINVAL; + if (atomic_read(&kvm->online_vcpus)) + goto create_irqchip_unlock; r = -ENOMEM; - kvm->arch.vpic = kvm_create_pic(kvm); - if (kvm->arch.vpic) { + vpic = kvm_create_pic(kvm); + if (vpic) { r = kvm_ioapic_init(kvm); if (r) { - kfree(kvm->arch.vpic); - kvm->arch.vpic = NULL; - goto out; + mutex_lock(&kvm->slots_lock); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_master); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_slave); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_eclr); + mutex_unlock(&kvm->slots_lock); + kfree(vpic); + goto create_irqchip_unlock; } } else - goto out; + goto create_irqchip_unlock; + smp_wmb(); + kvm->arch.vpic = vpic; + smp_wmb(); + r = kvm_setup_default_irq_routing(kvm); + if (r) { + mutex_lock(&kvm->slots_lock); + mutex_lock(&kvm->irq_lock); + kvm_ioapic_destroy(kvm); + kvm_destroy_pic(kvm); + mutex_unlock(&kvm->irq_lock); + mutex_unlock(&kvm->slots_lock); + } + create_irqchip_unlock: + mutex_unlock(&kvm->lock); break; - case KVM_IRQ_LINE: { - struct kvm_irq_level irq_event; - + } + case KVM_CREATE_PIT: + u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; + goto create_pit; + case KVM_CREATE_PIT2: r = -EFAULT; - if (copy_from_user(&irq_event, argp, sizeof irq_event)) + if (copy_from_user(&u.pit_config, argp, + sizeof(struct kvm_pit_config))) goto out; - if (irqchip_in_kernel(kvm)) { - mutex_lock(&kvm->lock); - if (irq_event.irq < 16) - kvm_pic_set_irq(pic_irqchip(kvm), - irq_event.irq, - irq_event.level); - kvm_ioapic_set_irq(kvm->arch.vioapic, - irq_event.irq, - irq_event.level); - mutex_unlock(&kvm->lock); + create_pit: + mutex_lock(&kvm->slots_lock); + r = -EEXIST; + if (kvm->arch.vpit) + goto create_pit_unlock; + r = -ENOMEM; + kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); + if (kvm->arch.vpit) r = 0; - } + create_pit_unlock: + mutex_unlock(&kvm->slots_lock); break; - } case KVM_GET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip chip; + struct kvm_irqchip *chip; + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); + goto out; + } + + r = -ENXIO; + if (!irqchip_in_kernel(kvm)) + goto get_irqchip_out; + r = kvm_vm_ioctl_get_irqchip(kvm, chip); + if (r) + goto get_irqchip_out; r = -EFAULT; - if (copy_from_user(&chip, argp, sizeof chip)) + if (copy_to_user(argp, chip, sizeof *chip)) + goto get_irqchip_out; + r = 0; + get_irqchip_out: + kfree(chip); + break; + } + case KVM_SET_IRQCHIP: { + /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ + struct kvm_irqchip *chip; + + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); goto out; + } + r = -ENXIO; if (!irqchip_in_kernel(kvm)) + goto set_irqchip_out; + r = kvm_vm_ioctl_set_irqchip(kvm, chip); + if (r) + goto set_irqchip_out; + r = 0; + set_irqchip_out: + kfree(chip); + break; + } + case KVM_GET_PIT: { + r = -EFAULT; + if (copy_from_user(&u.ps, argp, sizeof(struct kvm_pit_state))) goto out; - r = kvm_vm_ioctl_get_irqchip(kvm, &chip); + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_get_pit(kvm, &u.ps); if (r) goto out; r = -EFAULT; - if (copy_to_user(argp, &chip, sizeof chip)) + if (copy_to_user(argp, &u.ps, sizeof(struct kvm_pit_state))) goto out; r = 0; break; } - case KVM_SET_IRQCHIP: { - /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip chip; - + case KVM_SET_PIT: { r = -EFAULT; - if (copy_from_user(&chip, argp, sizeof chip)) + if (copy_from_user(&u.ps, argp, sizeof u.ps)) goto out; r = -ENXIO; - if (!irqchip_in_kernel(kvm)) + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_set_pit(kvm, &u.ps); + break; + } + case KVM_GET_PIT2: { + r = -ENXIO; + if (!kvm->arch.vpit) goto out; - r = kvm_vm_ioctl_set_irqchip(kvm, &chip); + r = kvm_vm_ioctl_get_pit2(kvm, &u.ps2); if (r) goto out; + r = -EFAULT; + if (copy_to_user(argp, &u.ps2, sizeof(u.ps2))) + goto out; + r = 0; + break; + } + case KVM_SET_PIT2: { + r = -EFAULT; + if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) + goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; + r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); + break; + } + case KVM_REINJECT_CONTROL: { + struct kvm_reinject_control control; + r = -EFAULT; + if (copy_from_user(&control, argp, sizeof(control))) + goto out; + r = kvm_vm_ioctl_reinject(kvm, &control); + break; + } + case KVM_XEN_HVM_CONFIG: { + r = -EFAULT; + if (copy_from_user(&kvm->arch.xen_hvm_config, argp, + sizeof(struct kvm_xen_hvm_config))) + goto out; + r = -EINVAL; + if (kvm->arch.xen_hvm_config.flags) + goto out; + r = 0; + break; + } + case KVM_SET_CLOCK: { + struct kvm_clock_data user_ns; + u64 now_ns; + s64 delta; + + r = -EFAULT; + if (copy_from_user(&user_ns, argp, sizeof(user_ns))) + goto out; + + r = -EINVAL; + if (user_ns.flags) + goto out; + + r = 0; + local_irq_disable(); + now_ns = get_kernel_ns(); + delta = user_ns.clock - now_ns; + local_irq_enable(); + kvm->arch.kvmclock_offset = delta; + kvm_gen_update_masterclock(kvm); + break; + } + case KVM_GET_CLOCK: { + struct kvm_clock_data user_ns; + u64 now_ns; + + local_irq_disable(); + now_ns = get_kernel_ns(); + user_ns.clock = kvm->arch.kvmclock_offset + now_ns; + local_irq_enable(); + user_ns.flags = 0; + memset(&user_ns.pad, 0, sizeof(user_ns.pad)); + + r = -EFAULT; + if (copy_to_user(argp, &user_ns, sizeof(user_ns))) + goto out; r = 0; break; } + default: ; } @@ -1524,9 +3940,27 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { + /* skip the first msrs in the list. KVM-specific */ + for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; + + /* + * Even MSRs that are valid in the host may not be exposed + * to the guests in some cases. We could work around this + * in VMX with the generic MSR save/load machinery, but it + * is not really worthwhile since it will really only + * happen with nested virtualization. + */ + switch (msrs_to_save[i]) { + case MSR_IA32_BNDCFGS: + if (!kvm_x86_ops->mpx_supported()) + continue; + break; + default: + break; + } + if (j < i) msrs_to_save[j] = msrs_to_save[i]; j++; @@ -1534,247 +3968,577 @@ static void kvm_init_msr_list(void) num_msrs_to_save = j; } -/* - * Only apic need an MMIO device hook, so shortcut now.. - */ -static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu, - gpa_t addr) +static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, + const void *v) { - struct kvm_io_device *dev; + int handled = 0; + int n; - if (vcpu->arch.apic) { - dev = &vcpu->arch.apic->dev; - if (dev->in_range(dev, addr)) - return dev; - } - return NULL; + do { + n = min(len, 8); + if (!(vcpu->arch.apic && + !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + break; + handled += n; + addr += n; + len -= n; + v += n; + } while (len); + + return handled; } +static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) +{ + int handled = 0; + int n; + + do { + n = min(len, 8); + if (!(vcpu->arch.apic && + !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + break; + trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); + handled += n; + addr += n; + len -= n; + v += n; + } while (len); -static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, - gpa_t addr) + return handled; +} + +static void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->set_segment(vcpu, var, seg); +} + +void kvm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->get_segment(vcpu, var, seg); +} + +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) +{ + gpa_t t_gpa; + struct x86_exception exception; + + BUG_ON(!mmu_is_nested(vcpu)); + + /* NPT walks are always user-walks */ + access |= PFERR_USER_MASK; + t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &exception); + + return t_gpa; +} + +gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) { - struct kvm_io_device *dev; + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); +} - dev = vcpu_find_pervcpu_dev(vcpu, addr); - if (dev == NULL) - dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr); - return dev; + gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + access |= PFERR_FETCH_MASK; + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); +} + +gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + access |= PFERR_WRITE_MASK; + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) +/* uses this to access any guest's mapped memory without checking CPL */ +gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, + struct x86_exception *exception) +{ + return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception); +} + +static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu, u32 access, + struct x86_exception *exception) { void *data = val; int r = X86EMUL_CONTINUE; - down_read(&vcpu->kvm->slots_lock); while (bytes) { - gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access, + exception); unsigned offset = addr & (PAGE_SIZE-1); - unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); + unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; - if (gpa == UNMAPPED_GVA) { - r = X86EMUL_PROPAGATE_FAULT; + if (gpa == UNMAPPED_GVA) + return X86EMUL_PROPAGATE_FAULT; + ret = kvm_read_guest(vcpu->kvm, gpa, data, toread); + if (ret < 0) { + r = X86EMUL_IO_NEEDED; goto out; } - ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy); + + bytes -= toread; + data += toread; + addr += toread; + } +out: + return r; +} + +/* used for instruction fetching */ +static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, + access | PFERR_FETCH_MASK, + exception); +} + +int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, + exception); +} +EXPORT_SYMBOL_GPL(kvm_read_guest_virt); + +static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception); +} + +int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, + gva_t addr, void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + void *data = val; + int r = X86EMUL_CONTINUE; + + while (bytes) { + gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, + PFERR_WRITE_MASK, + exception); + unsigned offset = addr & (PAGE_SIZE-1); + unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); + int ret; + + if (gpa == UNMAPPED_GVA) + return X86EMUL_PROPAGATE_FAULT; + ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); if (ret < 0) { - r = X86EMUL_UNHANDLEABLE; + r = X86EMUL_IO_NEEDED; goto out; } - bytes -= tocopy; - data += tocopy; - addr += tocopy; + bytes -= towrite; + data += towrite; + addr += towrite; } out: - up_read(&vcpu->kvm->slots_lock); return r; } -EXPORT_SYMBOL_GPL(emulator_read_std); +EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); -static int emulator_read_emulated(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) +static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, + gpa_t *gpa, struct x86_exception *exception, + bool write) { - struct kvm_io_device *mmio_dev; - gpa_t gpa; + u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) + | (write ? PFERR_WRITE_MASK : 0); - if (vcpu->mmio_read_completed) { - memcpy(val, vcpu->mmio_data, bytes); - vcpu->mmio_read_completed = 0; - return X86EMUL_CONTINUE; + if (vcpu_match_mmio_gva(vcpu, gva) + && !permission_fault(vcpu, vcpu->arch.walk_mmu, + vcpu->arch.access, access)) { + *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | + (gva & (PAGE_SIZE - 1)); + trace_vcpu_match_mmio(gva, *gpa, write, false); + return 1; } - down_read(&vcpu->kvm->slots_lock); - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(&vcpu->kvm->slots_lock); + *gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); - /* For APIC access vmexit */ - if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - goto mmio; + if (*gpa == UNMAPPED_GVA) + return -1; - if (emulator_read_std(addr, val, bytes, vcpu) - == X86EMUL_CONTINUE) - return X86EMUL_CONTINUE; - if (gpa == UNMAPPED_GVA) - return X86EMUL_PROPAGATE_FAULT; + /* For APIC access vmexit */ + if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + return 1; -mmio: - /* - * Is this MMIO handled locally? - */ - mutex_lock(&vcpu->kvm->lock); - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); - if (mmio_dev) { - kvm_iodevice_read(mmio_dev, gpa, bytes, val); - mutex_unlock(&vcpu->kvm->lock); - return X86EMUL_CONTINUE; + if (vcpu_match_mmio_gpa(vcpu, *gpa)) { + trace_vcpu_match_mmio(gva, *gpa, write, true); + return 1; } - mutex_unlock(&vcpu->kvm->lock); - vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 0; - - return X86EMUL_UNHANDLEABLE; + return 0; } -static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, - const void *val, int bytes) +int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes) { int ret; - down_read(&vcpu->kvm->slots_lock); ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); - if (ret < 0) { - up_read(&vcpu->kvm->slots_lock); + if (ret < 0) return 0; - } kvm_mmu_pte_write(vcpu, gpa, val, bytes); - up_read(&vcpu->kvm->slots_lock); return 1; } -static int emulator_write_emulated_onepage(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) +struct read_write_emulator_ops { + int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val, + int bytes); + int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + int bytes, void *val); + int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + bool write; +}; + +static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) { - struct kvm_io_device *mmio_dev; - gpa_t gpa; + if (vcpu->mmio_read_completed) { + trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, + vcpu->mmio_fragments[0].gpa, *(u64 *)val); + vcpu->mmio_read_completed = 0; + return 1; + } - down_read(&vcpu->kvm->slots_lock); - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); - up_read(&vcpu->kvm->slots_lock); + return 0; +} - if (gpa == UNMAPPED_GVA) { - kvm_inject_page_fault(vcpu, addr, 2); +static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); +} + +static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return emulator_write_phys(vcpu, gpa, val, bytes); +} + +static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + return vcpu_mmio_write(vcpu, gpa, bytes, val); +} + +static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); + return X86EMUL_IO_NEEDED; +} + +static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0]; + + memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len)); + return X86EMUL_CONTINUE; +} + +static const struct read_write_emulator_ops read_emultor = { + .read_write_prepare = read_prepare, + .read_write_emulate = read_emulate, + .read_write_mmio = vcpu_mmio_read, + .read_write_exit_mmio = read_exit_mmio, +}; + +static const struct read_write_emulator_ops write_emultor = { + .read_write_emulate = write_emulate, + .read_write_mmio = write_mmio, + .read_write_exit_mmio = write_exit_mmio, + .write = true, +}; + +static int emulator_read_write_onepage(unsigned long addr, void *val, + unsigned int bytes, + struct x86_exception *exception, + struct kvm_vcpu *vcpu, + const struct read_write_emulator_ops *ops) +{ + gpa_t gpa; + int handled, ret; + bool write = ops->write; + struct kvm_mmio_fragment *frag; + + ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); + + if (ret < 0) return X86EMUL_PROPAGATE_FAULT; - } /* For APIC access vmexit */ - if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + if (ret) goto mmio; - if (emulator_write_phys(vcpu, gpa, val, bytes)) + if (ops->read_write_emulate(vcpu, gpa, val, bytes)) return X86EMUL_CONTINUE; mmio: /* * Is this MMIO handled locally? */ - mutex_lock(&vcpu->kvm->lock); - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); - if (mmio_dev) { - kvm_iodevice_write(mmio_dev, gpa, bytes, val); - mutex_unlock(&vcpu->kvm->lock); + handled = ops->read_write_mmio(vcpu, gpa, bytes, val); + if (handled == bytes) return X86EMUL_CONTINUE; - } - mutex_unlock(&vcpu->kvm->lock); - vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 1; - memcpy(vcpu->mmio_data, val, bytes); + gpa += handled; + bytes -= handled; + val += handled; + WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS); + frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++]; + frag->gpa = gpa; + frag->data = val; + frag->len = bytes; return X86EMUL_CONTINUE; } -int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) +int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, + void *val, unsigned int bytes, + struct x86_exception *exception, + const struct read_write_emulator_ops *ops) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + gpa_t gpa; + int rc; + + if (ops->read_write_prepare && + ops->read_write_prepare(vcpu, val, bytes)) + return X86EMUL_CONTINUE; + + vcpu->mmio_nr_fragments = 0; + /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { - int rc, now; + int now; now = -addr & ~PAGE_MASK; - rc = emulator_write_emulated_onepage(addr, val, now, vcpu); + rc = emulator_read_write_onepage(addr, val, now, exception, + vcpu, ops); + if (rc != X86EMUL_CONTINUE) return rc; addr += now; val += now; bytes -= now; } - return emulator_write_emulated_onepage(addr, val, bytes, vcpu); + + rc = emulator_read_write_onepage(addr, val, bytes, exception, + vcpu, ops); + if (rc != X86EMUL_CONTINUE) + return rc; + + if (!vcpu->mmio_nr_fragments) + return rc; + + gpa = vcpu->mmio_fragments[0].gpa; + + vcpu->mmio_needed = 1; + vcpu->mmio_cur_fragment = 0; + + vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len); + vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write; + vcpu->run->exit_reason = KVM_EXIT_MMIO; + vcpu->run->mmio.phys_addr = gpa; + + return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); +} + +static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, val, bytes, + exception, &read_emultor); } -EXPORT_SYMBOL_GPL(emulator_write_emulated); -static int emulator_cmpxchg_emulated(unsigned long addr, +int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + const void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, (void *)val, bytes, + exception, &write_emultor); +} + +#define CMPXCHG_TYPE(t, ptr, old, new) \ + (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old)) + +#ifdef CONFIG_X86_64 +# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new) +#else +# define CMPXCHG64(ptr, old, new) \ + (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) +#endif + +static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, const void *old, const void *new, unsigned int bytes, - struct kvm_vcpu *vcpu) + struct x86_exception *exception) { - static int reported; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + gpa_t gpa; + struct page *page; + char *kaddr; + bool exchanged; - if (!reported) { - reported = 1; - printk(KERN_WARNING "kvm: emulating exchange as write\n"); - } -#ifndef CONFIG_X86_64 /* guests cmpxchg8b have to be emulated atomically */ - if (bytes == 8) { - gpa_t gpa; - struct page *page; - char *kaddr; - u64 val; + if (bytes > 8 || (bytes & (bytes - 1))) + goto emul_write; - down_read(&vcpu->kvm->slots_lock); - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); - if (gpa == UNMAPPED_GVA || - (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - goto emul_write; + if (gpa == UNMAPPED_GVA || + (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto emul_write; - if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) - goto emul_write; + if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + goto emul_write; - val = *(u64 *)new; + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + if (is_error_page(page)) + goto emul_write; - down_read(¤t->mm->mmap_sem); - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); + kaddr = kmap_atomic(page); + kaddr += offset_in_page(gpa); + switch (bytes) { + case 1: + exchanged = CMPXCHG_TYPE(u8, kaddr, old, new); + break; + case 2: + exchanged = CMPXCHG_TYPE(u16, kaddr, old, new); + break; + case 4: + exchanged = CMPXCHG_TYPE(u32, kaddr, old, new); + break; + case 8: + exchanged = CMPXCHG64(kaddr, old, new); + break; + default: + BUG(); + } + kunmap_atomic(kaddr); + kvm_release_page_dirty(page); + + if (!exchanged) + return X86EMUL_CMPXCHG_FAILED; + + mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); + kvm_mmu_pte_write(vcpu, gpa, new, bytes); + + return X86EMUL_CONTINUE; + +emul_write: + printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); + + return emulator_write_emulated(ctxt, addr, new, bytes, exception); +} + +static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) +{ + /* TODO: String I/O for in kernel device */ + int r; + + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + return r; +} + +static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, + unsigned int count, bool in) +{ + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = in; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; - kaddr = kmap_atomic(page, KM_USER0); - set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); - kunmap_atomic(kaddr, KM_USER0); - kvm_release_page_dirty(page); - emul_write: - up_read(&vcpu->kvm->slots_lock); + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + vcpu->arch.pio.count = 0; + return 1; } -#endif - return emulator_write_emulated(addr, new, bytes, vcpu); + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; +} + +static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int ret; + + if (vcpu->arch.pio.count) + goto data_avail; + + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); + if (ret) { +data_avail: + memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); + vcpu->arch.pio.count = 0; + return 1; + } + + return 0; +} + +static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, + const void *val, unsigned int count) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + memcpy(vcpu->arch.pio_data, val, size * count); + trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); + return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) @@ -1782,421 +4546,1031 @@ static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) return kvm_x86_ops->get_segment_base(vcpu, seg); } -int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) +static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) { - return X86EMUL_CONTINUE; + kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } -int emulate_clts(struct kvm_vcpu *vcpu) +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) { - kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS); + if (!need_emulate_wbinvd(vcpu)) + return X86EMUL_CONTINUE; + + if (kvm_x86_ops->has_wbinvd_exit()) { + int cpu = get_cpu(); + + cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); + smp_call_function_many(vcpu->arch.wbinvd_dirty_mask, + wbinvd_ipi, NULL, 1); + put_cpu(); + cpumask_clear(vcpu->arch.wbinvd_dirty_mask); + } else + wbinvd(); return X86EMUL_CONTINUE; } +EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); + +static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) +{ + kvm_emulate_wbinvd(emul_to_vcpu(ctxt)); +} int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) { - struct kvm_vcpu *vcpu = ctxt->vcpu; + return _kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); +} - switch (dr) { - case 0 ... 3: - *dest = kvm_x86_ops->get_dr(vcpu, dr); - return X86EMUL_CONTINUE; +int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +{ + + return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); +} + +static u64 mk_cr_64(u64 curr_cr, u32 new_val) +{ + return (curr_cr & ~((1ULL << 32) - 1)) | new_val; +} + +static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + unsigned long value; + + switch (cr) { + case 0: + value = kvm_read_cr0(vcpu); + break; + case 2: + value = vcpu->arch.cr2; + break; + case 3: + value = kvm_read_cr3(vcpu); + break; + case 4: + value = kvm_read_cr4(vcpu); + break; + case 8: + value = kvm_get_cr8(vcpu); + break; default: - pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr); - return X86EMUL_UNHANDLEABLE; + kvm_err("%s: unexpected cr %u\n", __func__, cr); + return 0; } + + return value; } -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) { - unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; - int exception; + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int res = 0; - kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception); - if (exception) { - /* FIXME: better handling */ - return X86EMUL_UNHANDLEABLE; + switch (cr) { + case 0: + res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); + break; + case 2: + vcpu->arch.cr2 = val; + break; + case 3: + res = kvm_set_cr3(vcpu, val); + break; + case 4: + res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); + break; + case 8: + res = kvm_set_cr8(vcpu, val); + break; + default: + kvm_err("%s: unexpected cr %u\n", __func__, cr); + res = -1; } - return X86EMUL_CONTINUE; + + return res; } -void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) +static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { - static int reported; - u8 opcodes[4]; - unsigned long rip = vcpu->arch.rip; - unsigned long rip_linear; + return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); +} - rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); +static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->get_gdt(emul_to_vcpu(ctxt), dt); +} - if (reported) - return; +static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->get_idt(emul_to_vcpu(ctxt), dt); +} + +static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->set_gdt(emul_to_vcpu(ctxt), dt); +} + +static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) +{ + kvm_x86_ops->set_idt(emul_to_vcpu(ctxt), dt); +} + +static unsigned long emulator_get_cached_segment_base( + struct x86_emulate_ctxt *ctxt, int seg) +{ + return get_segment_base(emul_to_vcpu(ctxt), seg); +} + +static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, + struct desc_struct *desc, u32 *base3, + int seg) +{ + struct kvm_segment var; + + kvm_get_segment(emul_to_vcpu(ctxt), &var, seg); + *selector = var.selector; + + if (var.unusable) { + memset(desc, 0, sizeof(*desc)); + return false; + } + + if (var.g) + var.limit >>= 12; + set_desc_limit(desc, var.limit); + set_desc_base(desc, (unsigned long)var.base); +#ifdef CONFIG_X86_64 + if (base3) + *base3 = var.base >> 32; +#endif + desc->type = var.type; + desc->s = var.s; + desc->dpl = var.dpl; + desc->p = var.present; + desc->avl = var.avl; + desc->l = var.l; + desc->d = var.db; + desc->g = var.g; + + return true; +} + +static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, + struct desc_struct *desc, u32 base3, + int seg) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + struct kvm_segment var; + + var.selector = selector; + var.base = get_desc_base(desc); +#ifdef CONFIG_X86_64 + var.base |= ((u64)base3) << 32; +#endif + var.limit = get_desc_limit(desc); + if (desc->g) + var.limit = (var.limit << 12) | 0xfff; + var.type = desc->type; + var.present = desc->p; + var.dpl = desc->dpl; + var.db = desc->d; + var.s = desc->s; + var.l = desc->l; + var.g = desc->g; + var.avl = desc->avl; + var.present = desc->p; + var.unusable = !var.present; + var.padding = 0; + + kvm_set_segment(vcpu, &var, seg); + return; +} + +static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) +{ + return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); +} + +static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 data) +{ + struct msr_data msr; + + msr.data = data; + msr.index = msr_index; + msr.host_initiated = false; + return kvm_set_msr(emul_to_vcpu(ctxt), &msr); +} + +static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, + u32 pmc, u64 *pdata) +{ + return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata); +} + +static void emulator_halt(struct x86_emulate_ctxt *ctxt) +{ + emul_to_vcpu(ctxt)->arch.halt_request = 1; +} + +static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt) +{ + preempt_disable(); + kvm_load_guest_fpu(emul_to_vcpu(ctxt)); + /* + * CR0.TS may reference the host fpu state, not the guest fpu state, + * so it may be clear at this point. + */ + clts(); +} + +static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt) +{ + preempt_enable(); +} + +static int emulator_intercept(struct x86_emulate_ctxt *ctxt, + struct x86_instruction_info *info, + enum x86_intercept_stage stage) +{ + return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); +} + +static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx); +} - emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu); +static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) +{ + return kvm_register_read(emul_to_vcpu(ctxt), reg); +} - printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", - context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); - reported = 1; +static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val) +{ + kvm_register_write(emul_to_vcpu(ctxt), reg, val); } -EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); -struct x86_emulate_ops emulate_ops = { - .read_std = emulator_read_std, +static const struct x86_emulate_ops emulate_ops = { + .read_gpr = emulator_read_gpr, + .write_gpr = emulator_write_gpr, + .read_std = kvm_read_guest_virt_system, + .write_std = kvm_write_guest_virt_system, + .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, + .invlpg = emulator_invlpg, + .pio_in_emulated = emulator_pio_in_emulated, + .pio_out_emulated = emulator_pio_out_emulated, + .get_segment = emulator_get_segment, + .set_segment = emulator_set_segment, + .get_cached_segment_base = emulator_get_cached_segment_base, + .get_gdt = emulator_get_gdt, + .get_idt = emulator_get_idt, + .set_gdt = emulator_set_gdt, + .set_idt = emulator_set_idt, + .get_cr = emulator_get_cr, + .set_cr = emulator_set_cr, + .cpl = emulator_get_cpl, + .get_dr = emulator_get_dr, + .set_dr = emulator_set_dr, + .set_msr = emulator_set_msr, + .get_msr = emulator_get_msr, + .read_pmc = emulator_read_pmc, + .halt = emulator_halt, + .wbinvd = emulator_wbinvd, + .fix_hypercall = emulator_fix_hypercall, + .get_fpu = emulator_get_fpu, + .put_fpu = emulator_put_fpu, + .intercept = emulator_intercept, + .get_cpuid = emulator_get_cpuid, }; -int emulate_instruction(struct kvm_vcpu *vcpu, - struct kvm_run *run, - unsigned long cr2, - u16 error_code, - int emulation_type) +static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { - int r; - struct decode_cache *c; + u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu, mask); + /* + * an sti; sti; sequence only disable interrupts for the first + * instruction. So, if the last instruction, be it emulated or + * not, left the system with the INT_STI flag enabled, it + * means that the last instruction is an sti. We should not + * leave the flag on in this case. The same goes for mov ss + */ + if (!(int_shadow & mask)) + kvm_x86_ops->set_interrupt_shadow(vcpu, mask); +} - vcpu->arch.mmio_fault_cr2 = cr2; - kvm_x86_ops->cache_regs(vcpu); +static void inject_emulated_exception(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + if (ctxt->exception.vector == PF_VECTOR) + kvm_propagate_fault(vcpu, &ctxt->exception); + else if (ctxt->exception.error_code_valid) + kvm_queue_exception_e(vcpu, ctxt->exception.vector, + ctxt->exception.error_code); + else + kvm_queue_exception(vcpu, ctxt->exception.vector); +} - vcpu->mmio_is_write = 0; - vcpu->arch.pio.string = 0; +static void init_decode_cache(struct x86_emulate_ctxt *ctxt) +{ + memset(&ctxt->opcode_len, 0, + (void *)&ctxt->_regs - (void *)&ctxt->opcode_len); - if (!(emulation_type & EMULTYPE_NO_DECODE)) { - int cs_db, cs_l; - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - - vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); - vcpu->arch.emulate_ctxt.mode = - (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) - ? X86EMUL_MODE_REAL : cs_l - ? X86EMUL_MODE_PROT64 : cs_db - ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - - if (vcpu->arch.emulate_ctxt.mode == X86EMUL_MODE_PROT64) { - vcpu->arch.emulate_ctxt.cs_base = 0; - vcpu->arch.emulate_ctxt.ds_base = 0; - vcpu->arch.emulate_ctxt.es_base = 0; - vcpu->arch.emulate_ctxt.ss_base = 0; + ctxt->fetch.start = 0; + ctxt->fetch.end = 0; + ctxt->io_read.pos = 0; + ctxt->io_read.end = 0; + ctxt->mem_read.pos = 0; + ctxt->mem_read.end = 0; +} + +static void init_emulate_ctxt(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + int cs_db, cs_l; + + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + + ctxt->eflags = kvm_get_rflags(vcpu); + ctxt->eip = kvm_rip_read(vcpu); + ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : + (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : + (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : + cs_db ? X86EMUL_MODE_PROT32 : + X86EMUL_MODE_PROT16; + ctxt->guest_mode = is_guest_mode(vcpu); + + init_decode_cache(ctxt); + vcpu->arch.emulate_regs_need_sync_from_vcpu = false; +} + +int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + int ret; + + init_emulate_ctxt(vcpu); + + ctxt->op_bytes = 2; + ctxt->ad_bytes = 2; + ctxt->_eip = ctxt->eip + inc_eip; + ret = emulate_int_real(ctxt, irq); + + if (ret != X86EMUL_CONTINUE) + return EMULATE_FAIL; + + ctxt->eip = ctxt->_eip; + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); + + if (irq == NMI_VECTOR) + vcpu->arch.nmi_pending = 0; + else + vcpu->arch.interrupt.pending = false; + + return EMULATE_DONE; +} +EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); + +static int handle_emulation_failure(struct kvm_vcpu *vcpu) +{ + int r = EMULATE_DONE; + + ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); + if (!is_guest_mode(vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + r = EMULATE_FAIL; + } + kvm_queue_exception(vcpu, UD_VECTOR); + + return r; +} + +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, + bool write_fault_to_shadow_pgtable, + int emulation_type) +{ + gpa_t gpa = cr2; + pfn_t pfn; + + if (emulation_type & EMULTYPE_NO_REEXECUTE) + return false; + + if (!vcpu->arch.mmu.direct_map) { + /* + * Write permission should be allowed since only + * write access need to be emulated. + */ + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + + /* + * If the mapping is invalid in guest, let cpu retry + * it to generate fault. + */ + if (gpa == UNMAPPED_GVA) + return true; + } + + /* + * Do not retry the unhandleable instruction if it faults on the + * readonly host memory, otherwise it will goto a infinite loop: + * retry instruction -> write #PF -> emulation fail -> retry + * instruction -> ... + */ + pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); + + /* + * If the instruction failed on the error pfn, it can not be fixed, + * report the error to userspace. + */ + if (is_error_noslot_pfn(pfn)) + return false; + + kvm_release_pfn_clean(pfn); + + /* The instructions are well-emulated on direct mmu. */ + if (vcpu->arch.mmu.direct_map) { + unsigned int indirect_shadow_pages; + + spin_lock(&vcpu->kvm->mmu_lock); + indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; + spin_unlock(&vcpu->kvm->mmu_lock); + + if (indirect_shadow_pages) + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + + return true; + } + + /* + * if emulation was due to access to shadowed page table + * and it failed try to unshadow page and re-enter the + * guest to let CPU execute the instruction. + */ + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + + /* + * If the access faults on its page table, it can not + * be fixed by unprotecting shadow page and it should + * be reported to userspace. + */ + return !write_fault_to_shadow_pgtable; +} + +static bool retry_instruction(struct x86_emulate_ctxt *ctxt, + unsigned long cr2, int emulation_type) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + + last_retry_eip = vcpu->arch.last_retry_eip; + last_retry_addr = vcpu->arch.last_retry_addr; + + /* + * If the emulation is caused by #PF and it is non-page_table + * writing instruction, it means the VM-EXIT is caused by shadow + * page protected, we can zap the shadow page and retry this + * instruction directly. + * + * Note: if the guest uses a non-page-table modifying instruction + * on the PDE that points to the instruction, then we will unmap + * the instruction and go to an infinite loop. So, we cache the + * last retried eip and the last fault address, if we meet the eip + * and the address again, we can break out of the potential infinite + * loop. + */ + vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; + + if (!(emulation_type & EMULTYPE_RETRY)) + return false; + + if (x86_page_table_writing_insn(ctxt)) + return false; + + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + return false; + + vcpu->arch.last_retry_eip = ctxt->eip; + vcpu->arch.last_retry_addr = cr2; + + if (!vcpu->arch.mmu.direct_map) + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + + return true; +} + +static int complete_emulated_mmio(struct kvm_vcpu *vcpu); +static int complete_emulated_pio(struct kvm_vcpu *vcpu); + +static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, + unsigned long *db) +{ + u32 dr6 = 0; + int i; + u32 enable, rwlen; + + enable = dr7; + rwlen = dr7 >> 16; + for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4) + if ((enable & 3) && (rwlen & 15) == type && db[i] == addr) + dr6 |= (1 << i); + return dr6; +} + +static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r) +{ + struct kvm_run *kvm_run = vcpu->run; + + /* + * Use the "raw" value to see if TF was passed to the processor. + * Note that the new value of the flags has not been saved yet. + * + * This is correct even for TF set by the guest, because "the + * processor will not generate this exception after the instruction + * that sets the TF flag". + */ + unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + + if (unlikely(rflags & X86_EFLAGS_TF)) { + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1; + kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; } else { - vcpu->arch.emulate_ctxt.cs_base = - get_segment_base(vcpu, VCPU_SREG_CS); - vcpu->arch.emulate_ctxt.ds_base = - get_segment_base(vcpu, VCPU_SREG_DS); - vcpu->arch.emulate_ctxt.es_base = - get_segment_base(vcpu, VCPU_SREG_ES); - vcpu->arch.emulate_ctxt.ss_base = - get_segment_base(vcpu, VCPU_SREG_SS); + vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF; + /* + * "Certain debug exceptions may clear bit 0-3. The + * remaining contents of the DR6 register are never + * cleared by the processor". + */ + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= DR6_BS; + kvm_queue_exception(vcpu, DB_VECTOR); } + } +} + +static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) +{ + struct kvm_run *kvm_run = vcpu->run; + unsigned long eip = vcpu->arch.emulate_ctxt.eip; + u32 dr6 = 0; + + if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && + (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { + dr6 = kvm_vcpu_check_hw_bp(eip, 0, + vcpu->arch.guest_debug_dr7, + vcpu->arch.eff_db); + + if (dr6 != 0) { + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; + kvm_run->debug.arch.pc = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + return true; + } + } + + if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK)) { + dr6 = kvm_vcpu_check_hw_bp(eip, 0, + vcpu->arch.dr7, + vcpu->arch.db); + + if (dr6 != 0) { + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= dr6; + kvm_queue_exception(vcpu, DB_VECTOR); + *r = EMULATE_DONE; + return true; + } + } - vcpu->arch.emulate_ctxt.gs_base = - get_segment_base(vcpu, VCPU_SREG_GS); - vcpu->arch.emulate_ctxt.fs_base = - get_segment_base(vcpu, VCPU_SREG_FS); + return false; +} + +int x86_emulate_instruction(struct kvm_vcpu *vcpu, + unsigned long cr2, + int emulation_type, + void *insn, + int insn_len) +{ + int r; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + bool writeback = true; + bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; - r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); + /* + * Clear write_fault_to_shadow_pgtable here to ensure it is + * never reused. + */ + vcpu->arch.write_fault_to_shadow_pgtable = false; + kvm_clear_exception_queue(vcpu); - /* Reject the instructions other than VMCALL/VMMCALL when - * try to emulate invalid opcode */ - c = &vcpu->arch.emulate_ctxt.decode; - if ((emulation_type & EMULTYPE_TRAP_UD) && - (!(c->twobyte && c->b == 0x01 && - (c->modrm_reg == 0 || c->modrm_reg == 3) && - c->modrm_mod == 3 && c->modrm_rm == 1))) - return EMULATE_FAIL; + if (!(emulation_type & EMULTYPE_NO_DECODE)) { + init_emulate_ctxt(vcpu); + /* + * We will reenter on the same instruction since + * we do not set complete_userspace_io. This does not + * handle watchpoints yet, those would be handled in + * the emulate_ops. + */ + if (kvm_vcpu_check_breakpoint(vcpu, &r)) + return r; + + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->perm_ok = false; + + ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; + + r = x86_decode_insn(ctxt, insn, insn_len); + + trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; - if (r) { - ++vcpu->stat.insn_emulation_fail; - if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) + if (r != EMULATION_OK) { + if (emulation_type & EMULTYPE_TRAP_UD) + return EMULATE_FAIL; + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + emulation_type)) return EMULATE_DONE; - return EMULATE_FAIL; + if (emulation_type & EMULTYPE_SKIP) + return EMULATE_FAIL; + return handle_emulation_failure(vcpu); } } - r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); + if (emulation_type & EMULTYPE_SKIP) { + kvm_rip_write(vcpu, ctxt->_eip); + return EMULATE_DONE; + } - if (vcpu->arch.pio.string) - return EMULATE_DO_MMIO; + if (retry_instruction(ctxt, cr2, emulation_type)) + return EMULATE_DONE; - if ((r || vcpu->mmio_is_write) && run) { - run->exit_reason = KVM_EXIT_MMIO; - run->mmio.phys_addr = vcpu->mmio_phys_addr; - memcpy(run->mmio.data, vcpu->mmio_data, 8); - run->mmio.len = vcpu->mmio_size; - run->mmio.is_write = vcpu->mmio_is_write; + /* this is needed for vmware backdoor interface to work since it + changes registers values during IO operation */ + if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { + vcpu->arch.emulate_regs_need_sync_from_vcpu = false; + emulator_invalidate_register_cache(ctxt); } - if (r) { - if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) +restart: + r = x86_emulate_insn(ctxt); + + if (r == EMULATION_INTERCEPTED) + return EMULATE_DONE; + + if (r == EMULATION_FAILED) { + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + emulation_type)) return EMULATE_DONE; - if (!vcpu->mmio_needed) { - kvm_report_emulation_failure(vcpu, "mmio"); - return EMULATE_FAIL; - } - return EMULATE_DO_MMIO; + + return handle_emulation_failure(vcpu); } - kvm_x86_ops->decache_regs(vcpu); - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + if (ctxt->have_exception) { + inject_emulated_exception(vcpu); + r = EMULATE_DONE; + } else if (vcpu->arch.pio.count) { + if (!vcpu->arch.pio.in) { + /* FIXME: return into emulator if single-stepping. */ + vcpu->arch.pio.count = 0; + } else { + writeback = false; + vcpu->arch.complete_userspace_io = complete_emulated_pio; + } + r = EMULATE_USER_EXIT; + } else if (vcpu->mmio_needed) { + if (!vcpu->mmio_is_write) + writeback = false; + r = EMULATE_USER_EXIT; + vcpu->arch.complete_userspace_io = complete_emulated_mmio; + } else if (r == EMULATION_RESTART) + goto restart; + else + r = EMULATE_DONE; + + if (writeback) { + toggle_interruptibility(vcpu, ctxt->interruptibility); + kvm_make_request(KVM_REQ_EVENT, vcpu); + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + kvm_rip_write(vcpu, ctxt->eip); + if (r == EMULATE_DONE) + kvm_vcpu_check_singlestep(vcpu, &r); + kvm_set_rflags(vcpu, ctxt->eflags); + } else + vcpu->arch.emulate_regs_need_sync_to_vcpu = true; - if (vcpu->mmio_is_write) { - vcpu->mmio_needed = 0; - return EMULATE_DO_MMIO; - } + return r; +} +EXPORT_SYMBOL_GPL(x86_emulate_instruction); - return EMULATE_DONE; +int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) +{ + unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); + int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, + size, port, &val, 1); + /* do not return to emulator after return from userspace */ + vcpu->arch.pio.count = 0; + return ret; } -EXPORT_SYMBOL_GPL(emulate_instruction); +EXPORT_SYMBOL_GPL(kvm_fast_pio_out); -static void free_pio_guest_pages(struct kvm_vcpu *vcpu) +static void tsc_bad(void *info) { - int i; + __this_cpu_write(cpu_tsc_khz, 0); +} - for (i = 0; i < ARRAY_SIZE(vcpu->arch.pio.guest_pages); ++i) - if (vcpu->arch.pio.guest_pages[i]) { - kvm_release_page_dirty(vcpu->arch.pio.guest_pages[i]); - vcpu->arch.pio.guest_pages[i] = NULL; - } +static void tsc_khz_changed(void *data) +{ + struct cpufreq_freqs *freq = data; + unsigned long khz = 0; + + if (data) + khz = freq->new; + else if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + khz = cpufreq_quick_get(raw_smp_processor_id()); + if (!khz) + khz = tsc_khz; + __this_cpu_write(cpu_tsc_khz, khz); } -static int pio_copy_data(struct kvm_vcpu *vcpu) +static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, + void *data) { - void *p = vcpu->arch.pio_data; - void *q; - unsigned bytes; - int nr_pages = vcpu->arch.pio.guest_pages[1] ? 2 : 1; + struct cpufreq_freqs *freq = data; + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int i, send_ipi = 0; - q = vmap(vcpu->arch.pio.guest_pages, nr_pages, VM_READ|VM_WRITE, - PAGE_KERNEL); - if (!q) { - free_pio_guest_pages(vcpu); - return -ENOMEM; + /* + * We allow guests to temporarily run on slowing clocks, + * provided we notify them after, or to run on accelerating + * clocks, provided we notify them before. Thus time never + * goes backwards. + * + * However, we have a problem. We can't atomically update + * the frequency of a given CPU from this function; it is + * merely a notifier, which can be called from any CPU. + * Changing the TSC frequency at arbitrary points in time + * requires a recomputation of local variables related to + * the TSC for each VCPU. We must flag these local variables + * to be updated and be sure the update takes place with the + * new frequency before any guests proceed. + * + * Unfortunately, the combination of hotplug CPU and frequency + * change creates an intractable locking scenario; the order + * of when these callouts happen is undefined with respect to + * CPU hotplug, and they can race with each other. As such, + * merely setting per_cpu(cpu_tsc_khz) = X during a hotadd is + * undefined; you can actually have a CPU frequency change take + * place in between the computation of X and the setting of the + * variable. To protect against this problem, all updates of + * the per_cpu tsc_khz variable are done in an interrupt + * protected IPI, and all callers wishing to update the value + * must wait for a synchronous IPI to complete (which is trivial + * if the caller is on the CPU already). This establishes the + * necessary total order on variable updates. + * + * Note that because a guest time update may take place + * anytime after the setting of the VCPU's request bit, the + * correct TSC value must be set before the request. However, + * to ensure the update actually makes it to any guest which + * starts running in hardware virtualization between the set + * and the acquisition of the spinlock, we must also ping the + * CPU after setting the request bit. + * + */ + + if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) + return 0; + if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) + return 0; + + smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->cpu != freq->cpu) + continue; + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + if (vcpu->cpu != smp_processor_id()) + send_ipi = 1; + } + } + spin_unlock(&kvm_lock); + + if (freq->old < freq->new && send_ipi) { + /* + * We upscale the frequency. Must make the guest + * doesn't see old kvmclock values while running with + * the new frequency, otherwise we risk the guest sees + * time go backwards. + * + * In case we update the frequency for another cpu + * (which might be in guest context) send an interrupt + * to kick the cpu out of guest context. Next time + * guest context is entered kvmclock will be updated, + * so the guest will not see stale values. + */ + smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); } - q += vcpu->arch.pio.guest_page_offset; - bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; - if (vcpu->arch.pio.in) - memcpy(q, p, bytes); - else - memcpy(p, q, bytes); - q -= vcpu->arch.pio.guest_page_offset; - vunmap(q); - free_pio_guest_pages(vcpu); return 0; } -int complete_pio(struct kvm_vcpu *vcpu) +static struct notifier_block kvmclock_cpufreq_notifier_block = { + .notifier_call = kvmclock_cpufreq_notifier +}; + +static int kvmclock_cpu_notifier(struct notifier_block *nfb, + unsigned long action, void *hcpu) { - struct kvm_pio_request *io = &vcpu->arch.pio; - long delta; - int r; + unsigned int cpu = (unsigned long)hcpu; - kvm_x86_ops->cache_regs(vcpu); + switch (action) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + smp_call_function_single(cpu, tsc_khz_changed, NULL, 1); + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, tsc_bad, NULL, 1); + break; + } + return NOTIFY_OK; +} - if (!io->string) { - if (io->in) - memcpy(&vcpu->arch.regs[VCPU_REGS_RAX], vcpu->arch.pio_data, - io->size); - } else { - if (io->in) { - r = pio_copy_data(vcpu); - if (r) { - kvm_x86_ops->cache_regs(vcpu); - return r; - } - } +static struct notifier_block kvmclock_cpu_notifier_block = { + .notifier_call = kvmclock_cpu_notifier, + .priority = -INT_MAX +}; - delta = 1; - if (io->rep) { - delta *= io->cur_count; - /* - * The size of the register should really depend on - * current address size. - */ - vcpu->arch.regs[VCPU_REGS_RCX] -= delta; - } - if (io->down) - delta = -delta; - delta *= io->size; - if (io->in) - vcpu->arch.regs[VCPU_REGS_RDI] += delta; - else - vcpu->arch.regs[VCPU_REGS_RSI] += delta; +static void kvm_timer_init(void) +{ + int cpu; + + max_tsc_khz = tsc_khz; + + cpu_notifier_register_begin(); + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { +#ifdef CONFIG_CPU_FREQ + struct cpufreq_policy policy; + memset(&policy, 0, sizeof(policy)); + cpu = get_cpu(); + cpufreq_get_policy(&policy, cpu); + if (policy.cpuinfo.max_freq) + max_tsc_khz = policy.cpuinfo.max_freq; + put_cpu(); +#endif + cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); } + pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz); + for_each_online_cpu(cpu) + smp_call_function_single(cpu, tsc_khz_changed, NULL, 1); - kvm_x86_ops->decache_regs(vcpu); + __register_hotcpu_notifier(&kvmclock_cpu_notifier_block); + cpu_notifier_register_done(); - io->count -= io->cur_count; - io->cur_count = 0; +} - return 0; +static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); + +int kvm_is_in_guest(void) +{ + return __this_cpu_read(current_vcpu) != NULL; } -static void kernel_pio(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu, - void *pd) +static int kvm_is_user_mode(void) { - /* TODO: String I/O for in kernel device */ + int user_mode = 3; - mutex_lock(&vcpu->kvm->lock); - if (vcpu->arch.pio.in) - kvm_iodevice_read(pio_dev, vcpu->arch.pio.port, - vcpu->arch.pio.size, - pd); - else - kvm_iodevice_write(pio_dev, vcpu->arch.pio.port, - vcpu->arch.pio.size, - pd); - mutex_unlock(&vcpu->kvm->lock); + if (__this_cpu_read(current_vcpu)) + user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu)); + + return user_mode != 0; } -static void pio_string_write(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu) +static unsigned long kvm_get_guest_ip(void) { - struct kvm_pio_request *io = &vcpu->arch.pio; - void *pd = vcpu->arch.pio_data; - int i; + unsigned long ip = 0; - mutex_lock(&vcpu->kvm->lock); - for (i = 0; i < io->cur_count; i++) { - kvm_iodevice_write(pio_dev, io->port, - io->size, - pd); - pd += io->size; - } - mutex_unlock(&vcpu->kvm->lock); + if (__this_cpu_read(current_vcpu)) + ip = kvm_rip_read(__this_cpu_read(current_vcpu)); + + return ip; } -static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu, - gpa_t addr) +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .is_in_guest = kvm_is_in_guest, + .is_user_mode = kvm_is_user_mode, + .get_guest_ip = kvm_get_guest_ip, +}; + +void kvm_before_handle_nmi(struct kvm_vcpu *vcpu) { - return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr); + __this_cpu_write(current_vcpu, vcpu); } +EXPORT_SYMBOL_GPL(kvm_before_handle_nmi); -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port) +void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) { - struct kvm_io_device *pio_dev; + __this_cpu_write(current_vcpu, NULL); +} +EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->arch.pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 0; - vcpu->arch.pio.down = 0; - vcpu->arch.pio.guest_page_offset = 0; - vcpu->arch.pio.rep = 0; +static void kvm_set_mmio_spte_mask(void) +{ + u64 mask; + int maxphyaddr = boot_cpu_data.x86_phys_bits; - kvm_x86_ops->cache_regs(vcpu); - memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4); - kvm_x86_ops->decache_regs(vcpu); + /* + * Set the reserved bits and the present bit of an paging-structure + * entry to generate page fault with PFER.RSV = 1. + */ + /* Mask the reserved physical address bits. */ + mask = ((1ull << (51 - maxphyaddr + 1)) - 1) << maxphyaddr; - kvm_x86_ops->skip_emulated_instruction(vcpu); + /* Bit 62 is always reserved for 32bit host. */ + mask |= 0x3ull << 62; - pio_dev = vcpu_find_pio_dev(vcpu, port); - if (pio_dev) { - kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data); - complete_pio(vcpu); - return 1; - } - return 0; + /* Set the present bit. */ + mask |= 1ull; + +#ifdef CONFIG_X86_64 + /* + * If reserved bit is not supported, clear the present bit to disable + * mmio page fault. + */ + if (maxphyaddr == 52) + mask &= ~1ull; +#endif + + kvm_mmu_set_mmio_spte_mask(mask); } -EXPORT_SYMBOL_GPL(kvm_emulate_pio); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port) +#ifdef CONFIG_X86_64 +static void pvclock_gtod_update_fn(struct work_struct *work) { - unsigned now, in_page; - int i, ret = 0; - int nr_pages = 1; - struct page *page; - struct kvm_io_device *pio_dev; + struct kvm *kvm; - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->arch.pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 1; - vcpu->arch.pio.down = down; - vcpu->arch.pio.guest_page_offset = offset_in_page(address); - vcpu->arch.pio.rep = rep; + struct kvm_vcpu *vcpu; + int i; - if (!count) { - kvm_x86_ops->skip_emulated_instruction(vcpu); - return 1; - } + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) + kvm_for_each_vcpu(i, vcpu, kvm) + set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests); + atomic_set(&kvm_guest_has_master_clock, 0); + spin_unlock(&kvm_lock); +} - if (!down) - in_page = PAGE_SIZE - offset_in_page(address); - else - in_page = offset_in_page(address) + size; - now = min(count, (unsigned long)in_page / size); - if (!now) { - /* - * String I/O straddles page boundary. Pin two guest pages - * so that we satisfy atomicity constraints. Do just one - * transaction to avoid complexity. - */ - nr_pages = 2; - now = 1; - } - if (down) { - /* - * String I/O in reverse. Yuck. Kill the guest, fix later. - */ - pr_unimpl(vcpu, "guest string pio down\n"); - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->run->io.count = now; - vcpu->arch.pio.cur_count = now; +static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); - if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count) - kvm_x86_ops->skip_emulated_instruction(vcpu); +/* + * Notification about pvclock gtod data update. + */ +static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, + void *priv) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + struct timekeeper *tk = priv; - for (i = 0; i < nr_pages; ++i) { - down_read(&vcpu->kvm->slots_lock); - page = gva_to_page(vcpu, address + i * PAGE_SIZE); - vcpu->arch.pio.guest_pages[i] = page; - up_read(&vcpu->kvm->slots_lock); - if (!page) { - kvm_inject_gp(vcpu, 0); - free_pio_guest_pages(vcpu); - return 1; - } - } + update_pvclock_gtod(tk); - pio_dev = vcpu_find_pio_dev(vcpu, port); - if (!vcpu->arch.pio.in) { - /* string PIO write */ - ret = pio_copy_data(vcpu); - if (ret >= 0 && pio_dev) { - pio_string_write(pio_dev, vcpu); - complete_pio(vcpu); - if (vcpu->arch.pio.count == 0) - ret = 1; - } - } else if (pio_dev) - pr_unimpl(vcpu, "no string pio read support yet, " - "port %x size %d count %ld\n", - port, size, count); + /* disable master clock if host does not trust, or does not + * use, TSC clocksource + */ + if (gtod->clock.vclock_mode != VCLOCK_TSC && + atomic_read(&kvm_guest_has_master_clock) != 0) + queue_work(system_long_wq, &pvclock_gtod_work); - return ret; + return 0; } -EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); + +static struct notifier_block pvclock_gtod_notifier = { + .notifier_call = pvclock_gtod_notify, +}; +#endif int kvm_arch_init(void *opaque) { int r; - struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; + struct kvm_x86_ops *ops = opaque; if (kvm_x86_ops) { printk(KERN_ERR "kvm: already loaded the other module\n"); @@ -2215,34 +5589,66 @@ int kvm_arch_init(void *opaque) goto out; } + r = -ENOMEM; + shared_msrs = alloc_percpu(struct kvm_shared_msrs); + if (!shared_msrs) { + printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n"); + goto out; + } + r = kvm_mmu_module_init(); if (r) - goto out; + goto out_free_percpu; - kvm_init_msr_list(); + kvm_set_mmio_spte_mask(); kvm_x86_ops = ops; - kvm_mmu_set_nonpresent_ptes(0ull, 0ull); + kvm_init_msr_list(); + + kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, + PT_DIRTY_MASK, PT64_NX_MASK, 0); + + kvm_timer_init(); + + perf_register_guest_info_callbacks(&kvm_guest_cbs); + + if (cpu_has_xsave) + host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + + kvm_lapic_init(); +#ifdef CONFIG_X86_64 + pvclock_gtod_register_notifier(&pvclock_gtod_notifier); +#endif + return 0; +out_free_percpu: + free_percpu(shared_msrs); out: return r; } void kvm_arch_exit(void) { + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); + + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + unregister_hotcpu_notifier(&kvmclock_cpu_notifier_block); +#ifdef CONFIG_X86_64 + pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); +#endif kvm_x86_ops = NULL; kvm_mmu_module_exit(); + free_percpu(shared_msrs); } int kvm_emulate_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->arch.mp_state = VCPU_MP_STATE_HALTED; - kvm_vcpu_block(vcpu); - if (vcpu->arch.mp_state != VCPU_MP_STATE_RUNNABLE) - return -EINTR; + vcpu->arch.mp_state = KVM_MP_STATE_HALTED; return 1; } else { vcpu->run->exit_reason = KVM_EXIT_HLT; @@ -2251,17 +5657,100 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + u64 param, ingpa, outgpa, ret; + uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; + bool fast, longmode; + int cs_db, cs_l; + + /* + * hypercall generates UD from non zero cpl and real mode + * per HYPER-V spec + */ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 0; + } + + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + longmode = is_long_mode(vcpu) && cs_l == 1; + + if (!longmode) { + param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); + ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); + outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); + } +#ifdef CONFIG_X86_64 + else { + param = kvm_register_read(vcpu, VCPU_REGS_RCX); + ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); + outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); + } +#endif + + code = param & 0xffff; + fast = (param >> 16) & 0x1; + rep_cnt = (param >> 32) & 0xfff; + rep_idx = (param >> 48) & 0xfff; + + trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + + switch (code) { + case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + kvm_vcpu_on_spin(vcpu); + break; + default: + res = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } + + ret = res | (((u64)rep_done & 0xfff) << 32); + if (longmode) { + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + } else { + kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); + } + + return 1; +} + +/* + * kvm_pv_kick_cpu_op: Kick a vcpu. + * + * @apicid - apicid of vcpu to be kicked. + */ +static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) +{ + struct kvm_lapic_irq lapic_irq; + + lapic_irq.shorthand = 0; + lapic_irq.dest_mode = 0; + lapic_irq.dest_id = apicid; + + lapic_irq.delivery_mode = APIC_DM_REMRD; + kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; + int r = 1; - kvm_x86_ops->cache_regs(vcpu); + if (kvm_hv_hypercall_enabled(vcpu->kvm)) + return kvm_hv_hypercall(vcpu); - nr = vcpu->arch.regs[VCPU_REGS_RAX]; - a0 = vcpu->arch.regs[VCPU_REGS_RBX]; - a1 = vcpu->arch.regs[VCPU_REGS_RCX]; - a2 = vcpu->arch.regs[VCPU_REGS_RDX]; - a3 = vcpu->arch.regs[VCPU_REGS_RSI]; + nr = kvm_register_read(vcpu, VCPU_REGS_RAX); + a0 = kvm_register_read(vcpu, VCPU_REGS_RBX); + a1 = kvm_register_read(vcpu, VCPU_REGS_RCX); + a2 = kvm_register_read(vcpu, VCPU_REGS_RDX); + a3 = kvm_register_read(vcpu, VCPU_REGS_RSI); + + trace_kvm_hypercall(nr, a0, a1, a2, a3); if (!is_long_mode(vcpu)) { nr &= 0xFFFFFFFF; @@ -2271,321 +5760,361 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } + if (kvm_x86_ops->get_cpl(vcpu) != 0) { + ret = -KVM_EPERM; + goto out; + } + switch (nr) { case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; + case KVM_HC_KICK_CPU: + kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + ret = 0; + break; default: ret = -KVM_ENOSYS; break; } - vcpu->arch.regs[VCPU_REGS_RAX] = ret; - kvm_x86_ops->decache_regs(vcpu); - return 0; +out: + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + ++vcpu->stat.hypercalls; + return r; } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); -int kvm_fix_hypercall(struct kvm_vcpu *vcpu) +static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) { + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); char instruction[3]; - int ret = 0; - - - /* - * Blow out the MMU to ensure that no other VCPU has an active mapping - * to ensure that the updated hypercall appears atomically across all - * VCPUs. - */ - kvm_mmu_zap_all(vcpu->kvm); + unsigned long rip = kvm_rip_read(vcpu); - kvm_x86_ops->cache_regs(vcpu); kvm_x86_ops->patch_hypercall(vcpu, instruction); - if (emulator_write_emulated(vcpu->arch.rip, instruction, 3, vcpu) - != X86EMUL_CONTINUE) - ret = -EFAULT; - return ret; + return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -static u64 mk_cr_64(u64 curr_cr, u32 new_val) +/* + * Check if userspace requested an interrupt window, and that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { - return (curr_cr & ~((1ULL << 32) - 1)) | new_val; + return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && + vcpu->run->request_interrupt_window && + kvm_arch_interrupt_allowed(vcpu)); } -void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) +static void post_kvm_run_save(struct kvm_vcpu *vcpu) { - struct descriptor_table dt = { limit, base }; + struct kvm_run *kvm_run = vcpu->run; - kvm_x86_ops->set_gdt(vcpu, &dt); + kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->cr8 = kvm_get_cr8(vcpu); + kvm_run->apic_base = kvm_get_apic_base(vcpu); + if (irqchip_in_kernel(vcpu->kvm)) + kvm_run->ready_for_interrupt_injection = 1; + else + kvm_run->ready_for_interrupt_injection = + kvm_arch_interrupt_allowed(vcpu) && + !kvm_cpu_has_interrupt(vcpu) && + !kvm_event_needs_reinjection(vcpu); } -void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) +static void update_cr8_intercept(struct kvm_vcpu *vcpu) { - struct descriptor_table dt = { limit, base }; + int max_irr, tpr; - kvm_x86_ops->set_idt(vcpu, &dt); -} + if (!kvm_x86_ops->update_cr8_intercept) + return; -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags) -{ - lmsw(vcpu, msw); - *rflags = kvm_x86_ops->get_rflags(vcpu); -} + if (!vcpu->arch.apic) + return; -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) -{ - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - switch (cr) { - case 0: - return vcpu->arch.cr0; - case 2: - return vcpu->arch.cr2; - case 3: - return vcpu->arch.cr3; - case 4: - return vcpu->arch.cr4; - case 8: - return get_cr8(vcpu); - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); - return 0; - } -} + if (!vcpu->arch.apic->vapic_addr) + max_irr = kvm_lapic_find_highest_irr(vcpu); + else + max_irr = -1; -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, - unsigned long *rflags) -{ - switch (cr) { - case 0: - set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); - *rflags = kvm_x86_ops->get_rflags(vcpu); - break; - case 2: - vcpu->arch.cr2 = val; - break; - case 3: - set_cr3(vcpu, val); - break; - case 4: - set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val)); - break; - case 8: - set_cr8(vcpu, val & 0xfUL); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); - } -} + if (max_irr != -1) + max_irr >>= 4; -static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) -{ - struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - int j, nent = vcpu->arch.cpuid_nent; + tpr = kvm_lapic_get_cr8(vcpu); - e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; - /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; j == i; j = (j + 1) % nent) { - struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; - if (ej->function == e->function) { - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - return j; - } - } - return 0; /* silence gcc, even though control never reaches here */ + kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -/* find an entry with matching function, matching index (if needed), and that - * should be read next (if it's stateful) */ -static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, - u32 function, u32 index) +static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) { - if (e->function != function) + int r; + + /* try to reinject previous events if any */ + if (vcpu->arch.exception.pending) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code); + kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code, + vcpu->arch.exception.reinject); return 0; - if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) + } + + if (vcpu->arch.nmi_injected) { + kvm_x86_ops->set_nmi(vcpu); return 0; - if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && - !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) + } + + if (vcpu->arch.interrupt.pending) { + kvm_x86_ops->set_irq(vcpu); return 0; - return 1; -} + } -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) -{ - int i; - u32 function, index; - struct kvm_cpuid_entry2 *e, *best; - - kvm_x86_ops->cache_regs(vcpu); - function = vcpu->arch.regs[VCPU_REGS_RAX]; - index = vcpu->arch.regs[VCPU_REGS_RCX]; - vcpu->arch.regs[VCPU_REGS_RAX] = 0; - vcpu->arch.regs[VCPU_REGS_RBX] = 0; - vcpu->arch.regs[VCPU_REGS_RCX] = 0; - vcpu->arch.regs[VCPU_REGS_RDX] = 0; - best = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (is_matching_cpuid_entry(e, function, index)) { - if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) - move_to_next_stateful_cpuid_entry(vcpu, i); - best = e; - break; + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { + r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (r != 0) + return r; + } + + /* try to inject new event if pending */ + if (vcpu->arch.nmi_pending) { + if (kvm_x86_ops->nmi_allowed(vcpu)) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops->set_nmi(vcpu); } + } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* - * Both basic or both extended? + * Because interrupts can be injected asynchronously, we are + * calling check_nested_events again here to avoid a race condition. + * See https://lkml.org/lkml/2014/7/2/60 for discussion about this + * proposal and current concerns. Perhaps we should be setting + * KVM_REQ_EVENT only on certain events and not unconditionally? */ - if (((e->function ^ function) & 0x80000000) == 0) - if (!best || e->function > best->function) - best = e; - } - if (best) { - vcpu->arch.regs[VCPU_REGS_RAX] = best->eax; - vcpu->arch.regs[VCPU_REGS_RBX] = best->ebx; - vcpu->arch.regs[VCPU_REGS_RCX] = best->ecx; - vcpu->arch.regs[VCPU_REGS_RDX] = best->edx; + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) { + r = kvm_x86_ops->check_nested_events(vcpu, req_int_win); + if (r != 0) + return r; + } + if (kvm_x86_ops->interrupt_allowed(vcpu)) { + kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), + false); + kvm_x86_ops->set_irq(vcpu); + } } - kvm_x86_ops->decache_regs(vcpu); - kvm_x86_ops->skip_emulated_instruction(vcpu); -} -EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); - -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ -static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - return (!vcpu->arch.irq_summary && - kvm_run->request_interrupt_window && - vcpu->arch.interrupt_window_open && - (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF)); -} - -static void post_kvm_run_save(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - kvm_run->cr8 = get_cr8(vcpu); - kvm_run->apic_base = kvm_get_apic_base(vcpu); - if (irqchip_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = 1; - else - kvm_run->ready_for_interrupt_injection = - (vcpu->arch.interrupt_window_open && - vcpu->arch.irq_summary == 0); + return 0; } -static void vapic_enter(struct kvm_vcpu *vcpu) +static void process_nmi(struct kvm_vcpu *vcpu) { - struct kvm_lapic *apic = vcpu->arch.apic; - struct page *page; - - if (!apic || !apic->vapic_addr) - return; + unsigned limit = 2; - down_read(¤t->mm->mmap_sem); - page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); + /* + * x86 is limited to one NMI running, and one NMI pending after it. + * If an NMI is already in progress, limit further NMIs to just one. + * Otherwise, allow two (and we'll inject the first one immediately). + */ + if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + limit = 1; - vcpu->arch.apic->vapic_page = page; + vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); + kvm_make_request(KVM_REQ_EVENT, vcpu); } -static void vapic_exit(struct kvm_vcpu *vcpu) +static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { - struct kvm_lapic *apic = vcpu->arch.apic; + u64 eoi_exit_bitmap[4]; + u32 tmr[8]; - if (!apic || !apic->vapic_addr) + if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - kvm_release_page_dirty(apic->vapic_page); - mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); + memset(eoi_exit_bitmap, 0, 32); + memset(tmr, 0, 32); + + kvm_ioapic_scan_entry(vcpu, eoi_exit_bitmap, tmr); + kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_apic_update_tmr(vcpu, tmr); } -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +/* + * Returns 1 to let __vcpu_run() continue the guest execution loop without + * exiting to the userspace. Otherwise, the value will be returned to the + * userspace. + */ +static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; + bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && + vcpu->run->request_interrupt_window; + bool req_immediate_exit = false; - if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) { - pr_debug("vcpu %d received sipi with vector # %x\n", - vcpu->vcpu_id, vcpu->arch.sipi_vector); - kvm_lapic_reset(vcpu); - r = kvm_x86_ops->vcpu_reset(vcpu); - if (r) - return r; - vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + if (vcpu->requests) { + if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) + kvm_mmu_unload(vcpu); + if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) + __kvm_migrate_timers(vcpu); + if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) + kvm_gen_update_masterclock(vcpu->kvm); + if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu)) + kvm_gen_kvmclock_update(vcpu); + if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { + r = kvm_guest_time_update(vcpu); + if (unlikely(r)) + goto out; + } + if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) + kvm_mmu_sync_roots(vcpu); + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) + kvm_x86_ops->tlb_flush(vcpu); + if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) { + vcpu->fpu_active = 0; + kvm_x86_ops->fpu_deactivate(vcpu); + } + if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { + /* Page is swapped out. Do synthetic halt */ + vcpu->arch.apf.halted = true; + r = 1; + goto out; + } + if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) + record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_NMI, vcpu)) + process_nmi(vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_handle_pmu_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_deliver_pmi(vcpu); + if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) + vcpu_scan_ioapic(vcpu); } - vapic_enter(vcpu); + if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + kvm_apic_accept_events(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { + r = 1; + goto out; + } -preempted: - if (vcpu->guest_debug.enabled) - kvm_x86_ops->guest_debug_pre(vcpu); + if (inject_pending_event(vcpu, req_int_win) != 0) + req_immediate_exit = true; + /* enable NMI/IRQ window open exits if needed */ + else if (vcpu->arch.nmi_pending) + kvm_x86_ops->enable_nmi_window(vcpu); + else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) + kvm_x86_ops->enable_irq_window(vcpu); -again: - r = kvm_mmu_reload(vcpu); - if (unlikely(r)) - goto out; - - if (vcpu->requests) { - if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) - __kvm_migrate_apic_timer(vcpu); - if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, - &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; - r = 0; - goto out; + if (kvm_lapic_enabled(vcpu)) { + /* + * Update architecture specific hints for APIC + * virtual interrupt delivery. + */ + if (kvm_x86_ops->hwapic_irr_update) + kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_lapic_find_highest_irr(vcpu)); + update_cr8_intercept(vcpu); + kvm_lapic_sync_to_vapic(vcpu); } } - kvm_inject_pending_timer_irqs(vcpu); + r = kvm_mmu_reload(vcpu); + if (unlikely(r)) { + goto cancel_injection; + } preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); - kvm_load_guest_fpu(vcpu); + if (vcpu->fpu_active) + kvm_load_guest_fpu(vcpu); + kvm_load_guest_xcr0(vcpu); + + vcpu->mode = IN_GUEST_MODE; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + + /* We should set ->mode before check ->requests, + * see the comment in make_all_cpus_request. + */ + smp_mb__after_srcu_read_unlock(); local_irq_disable(); - if (need_resched()) { + if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests + || need_resched() || signal_pending(current)) { + vcpu->mode = OUTSIDE_GUEST_MODE; + smp_wmb(); local_irq_enable(); preempt_enable(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = 1; - goto out; + goto cancel_injection; } - if (signal_pending(current)) { - local_irq_enable(); - preempt_enable(); - r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.signal_exits; - goto out; + if (req_immediate_exit) + smp_send_reschedule(vcpu->cpu); + + kvm_guest_enter(); + + if (unlikely(vcpu->arch.switch_db_regs)) { + set_debugreg(0, 7); + set_debugreg(vcpu->arch.eff_db[0], 0); + set_debugreg(vcpu->arch.eff_db[1], 1); + set_debugreg(vcpu->arch.eff_db[2], 2); + set_debugreg(vcpu->arch.eff_db[3], 3); + set_debugreg(vcpu->arch.dr6, 6); } - if (vcpu->arch.exception.pending) - __queue_exception(vcpu); - else if (irqchip_in_kernel(vcpu->kvm)) - kvm_x86_ops->inject_pending_irq(vcpu); - else - kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run); + trace_kvm_entry(vcpu->vcpu_id); + kvm_x86_ops->run(vcpu); - kvm_lapic_sync_to_vapic(vcpu); + /* + * Do this here before restoring debug registers on the host. And + * since we do this before handling the vmexit, a DR access vmexit + * can (a) read the correct value of the debug registers, (b) set + * KVM_DEBUGREG_WONT_EXIT again. + */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { + int i; - vcpu->guest_mode = 1; - kvm_guest_enter(); + WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); + kvm_x86_ops->sync_dirty_debug_regs(vcpu); + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + } - if (vcpu->requests) - if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) - kvm_x86_ops->tlb_flush(vcpu); + /* + * If the guest has used debug registers, at least dr7 + * will be disabled while returning to the host. + * If we don't have active breakpoints in the host, we don't + * care about the messed up debug address registers. But if + * we have some of them active, restore the old state. + */ + if (hw_breakpoint_active()) + hw_breakpoint_restore(); - kvm_x86_ops->run(vcpu, kvm_run); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, + native_read_tsc()); - vcpu->guest_mode = 0; - local_irq_enable(); + vcpu->mode = OUTSIDE_GUEST_MODE; + smp_wmb(); + + /* Interrupt is enabled by handle_external_intr() */ + kvm_x86_ops->handle_external_intr(vcpu); ++vcpu->stat.exits; @@ -2601,186 +6130,306 @@ again: preempt_enable(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + /* * Profile KVM exit RIPs: */ if (unlikely(prof_on == KVM_PROFILING)) { - kvm_x86_ops->cache_regs(vcpu); - profile_hit(KVM_PROFILING, (void *)vcpu->arch.rip); + unsigned long rip = kvm_rip_read(vcpu); + profile_hit(KVM_PROFILING, (void *)rip); } - if (vcpu->arch.exception.pending && kvm_x86_ops->exception_injected(vcpu)) - vcpu->arch.exception.pending = false; + if (unlikely(vcpu->arch.tsc_always_catchup)) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - kvm_lapic_sync_from_vapic(vcpu); + if (vcpu->arch.apic_attention) + kvm_lapic_sync_from_vapic(vcpu); - r = kvm_x86_ops->handle_exit(kvm_run, vcpu); + r = kvm_x86_ops->handle_exit(vcpu); + return r; + +cancel_injection: + kvm_x86_ops->cancel_injection(vcpu); + if (unlikely(vcpu->arch.apic_attention)) + kvm_lapic_sync_from_vapic(vcpu); +out: + return r; +} - if (r > 0) { - if (dm_request_for_irq_injection(vcpu, kvm_run)) { + +static int __vcpu_run(struct kvm_vcpu *vcpu) +{ + int r; + struct kvm *kvm = vcpu->kvm; + + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + r = 1; + while (r > 0) { + if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted) + r = vcpu_enter_guest(vcpu); + else { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { + kvm_apic_accept_events(vcpu); + switch(vcpu->arch.mp_state) { + case KVM_MP_STATE_HALTED: + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.mp_state = + KVM_MP_STATE_RUNNABLE; + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.apf.halted = false; + break; + case KVM_MP_STATE_INIT_RECEIVED: + break; + default: + r = -EINTR; + break; + } + } + } + + if (r <= 0) + break; + + clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); + if (kvm_cpu_has_pending_timer(vcpu)) + kvm_inject_pending_timer_irqs(vcpu); + + if (dm_request_for_irq_injection(vcpu)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; - goto out; } - if (!need_resched()) - goto again; + + kvm_check_async_pf_completion(vcpu); + + if (signal_pending(current)) { + r = -EINTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; + ++vcpu->stat.signal_exits; + } + if (need_resched()) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + cond_resched(); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + } } -out: - if (r > 0) { - kvm_resched(vcpu); - goto preempted; + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + + return r; +} + +static inline int complete_emulated_io(struct kvm_vcpu *vcpu) +{ + int r; + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (r != EMULATE_DONE) + return 0; + return 1; +} + +static int complete_emulated_pio(struct kvm_vcpu *vcpu) +{ + BUG_ON(!vcpu->arch.pio.count); + + return complete_emulated_io(vcpu); +} + +/* + * Implements the following, as a state machine: + * + * read: + * for each fragment + * for each mmio piece in the fragment + * write gpa, len + * exit + * copy data + * execute insn + * + * write: + * for each fragment + * for each mmio piece in the fragment + * write gpa, len + * copy data + * exit + */ +static int complete_emulated_mmio(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct kvm_mmio_fragment *frag; + unsigned len; + + BUG_ON(!vcpu->mmio_needed); + + /* Complete previous fragment */ + frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; + len = min(8u, frag->len); + if (!vcpu->mmio_is_write) + memcpy(frag->data, run->mmio.data, len); + + if (frag->len <= 8) { + /* Switch to the next fragment. */ + frag++; + vcpu->mmio_cur_fragment++; + } else { + /* Go forward to the next mmio piece. */ + frag->data += len; + frag->gpa += len; + frag->len -= len; } - post_kvm_run_save(vcpu, kvm_run); + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { + vcpu->mmio_needed = 0; - vapic_exit(vcpu); + /* FIXME: return into emulator if single-stepping. */ + if (vcpu->mmio_is_write) + return 1; + vcpu->mmio_read_completed = 1; + return complete_emulated_io(vcpu); + } - return r; + run->exit_reason = KVM_EXIT_MMIO; + run->mmio.phys_addr = frag->gpa; + if (vcpu->mmio_is_write) + memcpy(run->mmio.data, frag->data, min(8u, frag->len)); + run->mmio.len = min(8u, frag->len); + run->mmio.is_write = vcpu->mmio_is_write; + vcpu->arch.complete_userspace_io = complete_emulated_mmio; + return 0; } + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; sigset_t sigsaved; - vcpu_load(vcpu); - - if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_UNINITIALIZED)) { - kvm_vcpu_block(vcpu); - vcpu_put(vcpu); - return -EAGAIN; - } + if (!tsk_used_math(current) && init_fpu(current)) + return -ENOMEM; if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); - /* re-sync apic's tpr */ - if (!irqchip_in_kernel(vcpu->kvm)) - set_cr8(vcpu, kvm_run->cr8); - - if (vcpu->arch.pio.cur_count) { - r = complete_pio(vcpu); - if (r) - goto out; + if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { + kvm_vcpu_block(vcpu); + kvm_apic_accept_events(vcpu); + clear_bit(KVM_REQ_UNHALT, &vcpu->requests); + r = -EAGAIN; + goto out; } -#if CONFIG_HAS_IOMEM - if (vcpu->mmio_needed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); - vcpu->mmio_read_completed = 1; - vcpu->mmio_needed = 0; - r = emulate_instruction(vcpu, kvm_run, - vcpu->arch.mmio_fault_cr2, 0, - EMULTYPE_NO_DECODE); - if (r == EMULATE_DO_MMIO) { - /* - * Read-modify-write. Back to userspace. - */ - r = 0; + + /* re-sync apic's tpr */ + if (!irqchip_in_kernel(vcpu->kvm)) { + if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) { + r = -EINVAL; goto out; } } -#endif - if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) { - kvm_x86_ops->cache_regs(vcpu); - vcpu->arch.regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret; - kvm_x86_ops->decache_regs(vcpu); - } - r = __vcpu_run(vcpu, kvm_run); + if (unlikely(vcpu->arch.complete_userspace_io)) { + int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; + vcpu->arch.complete_userspace_io = NULL; + r = cui(vcpu); + if (r <= 0) + goto out; + } else + WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); + + r = __vcpu_run(vcpu); out: + post_kvm_run_save(vcpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - vcpu_put(vcpu); return r; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { - vcpu_load(vcpu); - - kvm_x86_ops->cache_regs(vcpu); - - regs->rax = vcpu->arch.regs[VCPU_REGS_RAX]; - regs->rbx = vcpu->arch.regs[VCPU_REGS_RBX]; - regs->rcx = vcpu->arch.regs[VCPU_REGS_RCX]; - regs->rdx = vcpu->arch.regs[VCPU_REGS_RDX]; - regs->rsi = vcpu->arch.regs[VCPU_REGS_RSI]; - regs->rdi = vcpu->arch.regs[VCPU_REGS_RDI]; - regs->rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - regs->rbp = vcpu->arch.regs[VCPU_REGS_RBP]; + if (vcpu->arch.emulate_regs_need_sync_to_vcpu) { + /* + * We are here if userspace calls get_regs() in the middle of + * instruction emulation. Registers state needs to be copied + * back from emulation context to vcpu. Userspace shouldn't do + * that usually, but some bad designed PV devices (vmware + * backdoor interface) need this to work + */ + emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt); + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + } + regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX); + regs->rbx = kvm_register_read(vcpu, VCPU_REGS_RBX); + regs->rcx = kvm_register_read(vcpu, VCPU_REGS_RCX); + regs->rdx = kvm_register_read(vcpu, VCPU_REGS_RDX); + regs->rsi = kvm_register_read(vcpu, VCPU_REGS_RSI); + regs->rdi = kvm_register_read(vcpu, VCPU_REGS_RDI); + regs->rsp = kvm_register_read(vcpu, VCPU_REGS_RSP); + regs->rbp = kvm_register_read(vcpu, VCPU_REGS_RBP); #ifdef CONFIG_X86_64 - regs->r8 = vcpu->arch.regs[VCPU_REGS_R8]; - regs->r9 = vcpu->arch.regs[VCPU_REGS_R9]; - regs->r10 = vcpu->arch.regs[VCPU_REGS_R10]; - regs->r11 = vcpu->arch.regs[VCPU_REGS_R11]; - regs->r12 = vcpu->arch.regs[VCPU_REGS_R12]; - regs->r13 = vcpu->arch.regs[VCPU_REGS_R13]; - regs->r14 = vcpu->arch.regs[VCPU_REGS_R14]; - regs->r15 = vcpu->arch.regs[VCPU_REGS_R15]; + regs->r8 = kvm_register_read(vcpu, VCPU_REGS_R8); + regs->r9 = kvm_register_read(vcpu, VCPU_REGS_R9); + regs->r10 = kvm_register_read(vcpu, VCPU_REGS_R10); + regs->r11 = kvm_register_read(vcpu, VCPU_REGS_R11); + regs->r12 = kvm_register_read(vcpu, VCPU_REGS_R12); + regs->r13 = kvm_register_read(vcpu, VCPU_REGS_R13); + regs->r14 = kvm_register_read(vcpu, VCPU_REGS_R14); + regs->r15 = kvm_register_read(vcpu, VCPU_REGS_R15); #endif - regs->rip = vcpu->arch.rip; - regs->rflags = kvm_x86_ops->get_rflags(vcpu); - - /* - * Don't leak debug flags in case they were set for guest debugging - */ - if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) - regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - - vcpu_put(vcpu); + regs->rip = kvm_rip_read(vcpu); + regs->rflags = kvm_get_rflags(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { - vcpu_load(vcpu); - - vcpu->arch.regs[VCPU_REGS_RAX] = regs->rax; - vcpu->arch.regs[VCPU_REGS_RBX] = regs->rbx; - vcpu->arch.regs[VCPU_REGS_RCX] = regs->rcx; - vcpu->arch.regs[VCPU_REGS_RDX] = regs->rdx; - vcpu->arch.regs[VCPU_REGS_RSI] = regs->rsi; - vcpu->arch.regs[VCPU_REGS_RDI] = regs->rdi; - vcpu->arch.regs[VCPU_REGS_RSP] = regs->rsp; - vcpu->arch.regs[VCPU_REGS_RBP] = regs->rbp; + vcpu->arch.emulate_regs_need_sync_from_vcpu = true; + vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + + kvm_register_write(vcpu, VCPU_REGS_RAX, regs->rax); + kvm_register_write(vcpu, VCPU_REGS_RBX, regs->rbx); + kvm_register_write(vcpu, VCPU_REGS_RCX, regs->rcx); + kvm_register_write(vcpu, VCPU_REGS_RDX, regs->rdx); + kvm_register_write(vcpu, VCPU_REGS_RSI, regs->rsi); + kvm_register_write(vcpu, VCPU_REGS_RDI, regs->rdi); + kvm_register_write(vcpu, VCPU_REGS_RSP, regs->rsp); + kvm_register_write(vcpu, VCPU_REGS_RBP, regs->rbp); #ifdef CONFIG_X86_64 - vcpu->arch.regs[VCPU_REGS_R8] = regs->r8; - vcpu->arch.regs[VCPU_REGS_R9] = regs->r9; - vcpu->arch.regs[VCPU_REGS_R10] = regs->r10; - vcpu->arch.regs[VCPU_REGS_R11] = regs->r11; - vcpu->arch.regs[VCPU_REGS_R12] = regs->r12; - vcpu->arch.regs[VCPU_REGS_R13] = regs->r13; - vcpu->arch.regs[VCPU_REGS_R14] = regs->r14; - vcpu->arch.regs[VCPU_REGS_R15] = regs->r15; + kvm_register_write(vcpu, VCPU_REGS_R8, regs->r8); + kvm_register_write(vcpu, VCPU_REGS_R9, regs->r9); + kvm_register_write(vcpu, VCPU_REGS_R10, regs->r10); + kvm_register_write(vcpu, VCPU_REGS_R11, regs->r11); + kvm_register_write(vcpu, VCPU_REGS_R12, regs->r12); + kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); + kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); + kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); #endif - vcpu->arch.rip = regs->rip; - kvm_x86_ops->set_rflags(vcpu, regs->rflags); + kvm_rip_write(vcpu, regs->rip); + kvm_set_rflags(vcpu, regs->rflags); - kvm_x86_ops->decache_regs(vcpu); + vcpu->arch.exception.pending = false; - vcpu_put(vcpu); + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } -static void get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - return kvm_x86_ops->get_segment(vcpu, var, seg); -} - void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { struct kvm_segment cs; - get_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); *db = cs.db; *l = cs.l; } @@ -2789,172 +6438,229 @@ EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - struct descriptor_table dt; - int pending_vec; + struct desc_ptr dt; - vcpu_load(vcpu); + kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); + kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); + kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); + kvm_get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); + kvm_get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); + kvm_get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); - get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); - get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); - get_segment(vcpu, &sregs->es, VCPU_SREG_ES); - get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); - get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); - get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); - - get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); - get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); + kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); kvm_x86_ops->get_idt(vcpu, &dt); - sregs->idt.limit = dt.limit; - sregs->idt.base = dt.base; + sregs->idt.limit = dt.size; + sregs->idt.base = dt.address; kvm_x86_ops->get_gdt(vcpu, &dt); - sregs->gdt.limit = dt.limit; - sregs->gdt.base = dt.base; + sregs->gdt.limit = dt.size; + sregs->gdt.base = dt.address; - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - sregs->cr0 = vcpu->arch.cr0; + sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr2 = vcpu->arch.cr2; - sregs->cr3 = vcpu->arch.cr3; - sregs->cr4 = vcpu->arch.cr4; - sregs->cr8 = get_cr8(vcpu); - sregs->efer = vcpu->arch.shadow_efer; + sregs->cr3 = kvm_read_cr3(vcpu); + sregs->cr4 = kvm_read_cr4(vcpu); + sregs->cr8 = kvm_get_cr8(vcpu); + sregs->efer = vcpu->arch.efer; sregs->apic_base = kvm_get_apic_base(vcpu); - if (irqchip_in_kernel(vcpu->kvm)) { - memset(sregs->interrupt_bitmap, 0, - sizeof sregs->interrupt_bitmap); - pending_vec = kvm_x86_ops->get_irq(vcpu); - if (pending_vec >= 0) - set_bit(pending_vec, - (unsigned long *)sregs->interrupt_bitmap); - } else - memcpy(sregs->interrupt_bitmap, vcpu->arch.irq_pending, - sizeof sregs->interrupt_bitmap); + memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap); - vcpu_put(vcpu); + if (vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft) + set_bit(vcpu->arch.interrupt.nr, + (unsigned long *)sregs->interrupt_bitmap); return 0; } -static void set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) { - return kvm_x86_ops->set_segment(vcpu, var, seg); + kvm_apic_accept_events(vcpu); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && + vcpu->arch.pv.pv_unhalted) + mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + else + mp_state->mp_state = vcpu->arch.mp_state; + + return 0; } +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + if (!kvm_vcpu_has_lapic(vcpu) && + mp_state->mp_state != KVM_MP_STATE_RUNNABLE) + return -EINVAL; + + if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { + vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; + set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); + } else + vcpu->arch.mp_state = mp_state->mp_state; + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; +} + +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, + int reason, bool has_error_code, u32 error_code) +{ + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + int ret; + + init_emulate_ctxt(vcpu); + + ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, + has_error_code, error_code); + + if (ret) + return EMULATE_FAIL; + + kvm_rip_write(vcpu, ctxt->eip); + kvm_set_rflags(vcpu, ctxt->eflags); + kvm_make_request(KVM_REQ_EVENT, vcpu); + return EMULATE_DONE; +} +EXPORT_SYMBOL_GPL(kvm_task_switch); + int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + struct msr_data apic_base_msr; int mmu_reset_needed = 0; - int i, pending_vec, max_bits; - struct descriptor_table dt; + int pending_vec, max_bits, idx; + struct desc_ptr dt; - vcpu_load(vcpu); + if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE)) + return -EINVAL; - dt.limit = sregs->idt.limit; - dt.base = sregs->idt.base; + dt.size = sregs->idt.limit; + dt.address = sregs->idt.base; kvm_x86_ops->set_idt(vcpu, &dt); - dt.limit = sregs->gdt.limit; - dt.base = sregs->gdt.base; + dt.size = sregs->gdt.limit; + dt.address = sregs->gdt.base; kvm_x86_ops->set_gdt(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; - mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3; + mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); - set_cr8(vcpu, sregs->cr8); + kvm_set_cr8(vcpu, sregs->cr8); - mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer; -#ifdef CONFIG_X86_64 + mmu_reset_needed |= vcpu->arch.efer != sregs->efer; kvm_x86_ops->set_efer(vcpu, sregs->efer); -#endif - kvm_set_apic_base(vcpu, sregs->apic_base); - - kvm_x86_ops->decache_cr4_guest_bits(vcpu); + apic_base_msr.data = sregs->apic_base; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(vcpu, &apic_base_msr); - mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0; + mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; kvm_x86_ops->set_cr0(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; - mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; + mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (!is_long_mode(vcpu) && is_pae(vcpu)) - load_pdptrs(vcpu, vcpu->arch.cr3); + if (sregs->cr4 & X86_CR4_OSXSAVE) + kvm_update_cpuid(vcpu); + + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (!is_long_mode(vcpu) && is_pae(vcpu)) { + load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + mmu_reset_needed = 1; + } + srcu_read_unlock(&vcpu->kvm->srcu, idx); if (mmu_reset_needed) kvm_mmu_reset_context(vcpu); - if (!irqchip_in_kernel(vcpu->kvm)) { - memcpy(vcpu->arch.irq_pending, sregs->interrupt_bitmap, - sizeof vcpu->arch.irq_pending); - vcpu->arch.irq_summary = 0; - for (i = 0; i < ARRAY_SIZE(vcpu->arch.irq_pending); ++i) - if (vcpu->arch.irq_pending[i]) - __set_bit(i, &vcpu->arch.irq_summary); - } else { - max_bits = (sizeof sregs->interrupt_bitmap) << 3; - pending_vec = find_first_bit( - (const unsigned long *)sregs->interrupt_bitmap, - max_bits); - /* Only pending external irq is handled here */ - if (pending_vec < max_bits) { - kvm_x86_ops->set_irq(vcpu, pending_vec); - pr_debug("Set back pending irq %d\n", - pending_vec); - } + max_bits = KVM_NR_INTERRUPTS; + pending_vec = find_first_bit( + (const unsigned long *)sregs->interrupt_bitmap, max_bits); + if (pending_vec < max_bits) { + kvm_queue_interrupt(vcpu, pending_vec, false); + pr_debug("Set back pending irq %d\n", pending_vec); } - set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); - set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); - set_segment(vcpu, &sregs->es, VCPU_SREG_ES); - set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); - set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); - set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); + kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); + kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); + kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES); + kvm_set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); + kvm_set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); + kvm_set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); - set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); - set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); + kvm_set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); + kvm_set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - vcpu_put(vcpu); + update_cr8_intercept(vcpu); + + /* Older userspace won't unhalt the vcpu on reset. */ + if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 && + sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 && + !is_protmode(vcpu)) + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { - int r; + unsigned long rflags; + int i, r; - vcpu_load(vcpu); + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { + r = -EBUSY; + if (vcpu->arch.exception.pending) + goto out; + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else + kvm_queue_exception(vcpu, BP_VECTOR); + } - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + /* + * Read rflags as long as potentially injected trace flags are still + * filtered out. + */ + rflags = kvm_get_rflags(vcpu); - vcpu_put(vcpu); + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { + for (i = 0; i < KVM_NR_DB_REGS; ++i) + vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; + vcpu->arch.guest_debug_dr7 = dbg->arch.debugreg[7]; + } else { + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + } + kvm_update_dr7(vcpu); + + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + /* + * Trigger an rflags update that will inject or remove the trace + * flags. + */ + kvm_set_rflags(vcpu, rflags); + + kvm_x86_ops->update_db_bp_intercept(vcpu); + + r = 0; + +out: return r; } /* - * fxsave fpu state. Taken from x86_64/processor.h. To be killed when - * we have asm/x86/processor.h - */ -struct fxsave { - u16 cwd; - u16 swd; - u16 twd; - u16 fop; - u64 rip; - u64 rdp; - u32 mxcsr; - u32 mxcsr_mask; - u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ -#ifdef CONFIG_X86_64 - u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */ -#else - u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ -#endif -}; - -/* * Translate a guest virtual address to a guest physical address. */ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, @@ -2962,25 +6668,23 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, { unsigned long vaddr = tr->linear_address; gpa_t gpa; + int idx; - vcpu_load(vcpu); - down_read(&vcpu->kvm->slots_lock); - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr); - up_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); + gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); + srcu_read_unlock(&vcpu->kvm->srcu, idx); tr->physical_address = gpa; tr->valid = gpa != UNMAPPED_GVA; tr->writeable = 1; tr->usermode = 0; - vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image; - - vcpu_load(vcpu); + struct i387_fxsave_struct *fxsave = + &vcpu->arch.guest_fpu.state->fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; @@ -2991,16 +6695,13 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fpu->last_dp = fxsave->rdp; memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); - vcpu_put(vcpu); - return 0; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image; - - vcpu_load(vcpu); + struct i387_fxsave_struct *fxsave = + &vcpu->arch.guest_fpu.state->fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -3011,62 +6712,83 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fxsave->rdp = fpu->last_dp; memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); - vcpu_put(vcpu); - return 0; } -void fx_init(struct kvm_vcpu *vcpu) +int fx_init(struct kvm_vcpu *vcpu) { - unsigned after_mxcsr_mask; + int err; - /* Initialize guest FPU by resetting ours and saving into guest's */ - preempt_disable(); - fx_save(&vcpu->arch.host_fx_image); - fpu_init(); - fx_save(&vcpu->arch.guest_fx_image); - fx_restore(&vcpu->arch.host_fx_image); - preempt_enable(); + err = fpu_alloc(&vcpu->arch.guest_fpu); + if (err) + return err; + + fpu_finit(&vcpu->arch.guest_fpu); + + /* + * Ensure guest xcr0 is valid for loading + */ + vcpu->arch.xcr0 = XSTATE_FP; vcpu->arch.cr0 |= X86_CR0_ET; - after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space); - vcpu->arch.guest_fx_image.mxcsr = 0x1f80; - memset((void *)&vcpu->arch.guest_fx_image + after_mxcsr_mask, - 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask); + + return 0; } EXPORT_SYMBOL_GPL(fx_init); +static void fx_free(struct kvm_vcpu *vcpu) +{ + fpu_free(&vcpu->arch.guest_fpu); +} + void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { - if (!vcpu->fpu_active || vcpu->guest_fpu_loaded) + if (vcpu->guest_fpu_loaded) return; + /* + * Restore all possible states in the guest, + * and assume host would use all available bits. + * Guest xcr0 would be loaded later. + */ + kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; - fx_save(&vcpu->arch.host_fx_image); - fx_restore(&vcpu->arch.guest_fx_image); + __kernel_fpu_begin(); + fpu_restore_checking(&vcpu->arch.guest_fpu); + trace_kvm_fpu(1); } -EXPORT_SYMBOL_GPL(kvm_load_guest_fpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { + kvm_put_guest_xcr0(vcpu); + if (!vcpu->guest_fpu_loaded) return; vcpu->guest_fpu_loaded = 0; - fx_save(&vcpu->arch.guest_fx_image); - fx_restore(&vcpu->arch.host_fx_image); + fpu_save_init(&vcpu->arch.guest_fpu); + __kernel_fpu_end(); ++vcpu->stat.fpu_reload; + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + trace_kvm_fpu(0); } -EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + kvmclock_reset(vcpu); + + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { + if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + printk_once(KERN_WARNING + "kvm: SMP vm created on host with unstable TSC; " + "guest TSC will not be reliable\n"); return kvm_x86_ops->vcpu_create(kvm, id); } @@ -3074,45 +6796,190 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int r; - /* We do fxsave: this must be aligned. */ - BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF); + vcpu->arch.mtrr_state.have_fixed = 1; + r = vcpu_load(vcpu); + if (r) + return r; + kvm_vcpu_reset(vcpu); + kvm_mmu_setup(vcpu); + vcpu_put(vcpu); + + return r; +} - vcpu_load(vcpu); - r = kvm_arch_vcpu_reset(vcpu); - if (r == 0) - r = kvm_mmu_setup(vcpu); +int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + int r; + struct msr_data msr; + struct kvm *kvm = vcpu->kvm; + + r = vcpu_load(vcpu); + if (r) + return r; + msr.data = 0x0; + msr.index = MSR_IA32_TSC; + msr.host_initiated = true; + kvm_write_tsc(vcpu, &msr); vcpu_put(vcpu); - if (r < 0) - goto free_vcpu; - return 0; -free_vcpu: - kvm_x86_ops->vcpu_free(vcpu); + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, + KVMCLOCK_SYNC_PERIOD); + return r; } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu_load(vcpu); + int r; + vcpu->arch.apf.msr_val = 0; + + r = vcpu_load(vcpu); + BUG_ON(r); kvm_mmu_unload(vcpu); vcpu_put(vcpu); + fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } -int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) +void kvm_vcpu_reset(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->vcpu_reset(vcpu); + atomic_set(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = 0; + vcpu->arch.nmi_injected = false; + + memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = DR6_FIXED_1; + kvm_update_dr6(vcpu); + vcpu->arch.dr7 = DR7_FIXED_1; + kvm_update_dr7(vcpu); + + kvm_make_request(KVM_REQ_EVENT, vcpu); + vcpu->arch.apf.msr_val = 0; + vcpu->arch.st.msr_val = 0; + + kvmclock_reset(vcpu); + + kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + vcpu->arch.apf.halted = false; + + kvm_pmu_reset(vcpu); + + memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; + + kvm_x86_ops->vcpu_reset(vcpu); } -void kvm_arch_hardware_enable(void *garbage) +void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector) { - kvm_x86_ops->hardware_enable(garbage); + struct kvm_segment cs; + + kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); + cs.selector = vector << 8; + cs.base = vector << 12; + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_rip_write(vcpu, 0); +} + +int kvm_arch_hardware_enable(void *garbage) +{ + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int i; + int ret; + u64 local_tsc; + u64 max_tsc = 0; + bool stable, backwards_tsc = false; + + kvm_shared_msr_cpu_online(); + ret = kvm_x86_ops->hardware_enable(garbage); + if (ret != 0) + return ret; + + local_tsc = native_read_tsc(); + stable = !check_tsc_unstable(); + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!stable && vcpu->cpu == smp_processor_id()) + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + if (stable && vcpu->arch.last_host_tsc > local_tsc) { + backwards_tsc = true; + if (vcpu->arch.last_host_tsc > max_tsc) + max_tsc = vcpu->arch.last_host_tsc; + } + } + } + + /* + * Sometimes, even reliable TSCs go backwards. This happens on + * platforms that reset TSC during suspend or hibernate actions, but + * maintain synchronization. We must compensate. Fortunately, we can + * detect that condition here, which happens early in CPU bringup, + * before any KVM threads can be running. Unfortunately, we can't + * bring the TSCs fully up to date with real time, as we aren't yet far + * enough into CPU bringup that we know how much real time has actually + * elapsed; our helper function, get_kernel_ns() will be using boot + * variables that haven't been updated yet. + * + * So we simply find the maximum observed TSC above, then record the + * adjustment to TSC in each VCPU. When the VCPU later gets loaded, + * the adjustment will be applied. Note that we accumulate + * adjustments, in case multiple suspend cycles happen before some VCPU + * gets a chance to run again. In the event that no KVM threads get a + * chance to run, we will miss the entire elapsed period, as we'll have + * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may + * loose cycle time. This isn't too big a deal, since the loss will be + * uniform across all VCPUs (not to mention the scenario is extremely + * unlikely). It is possible that a second hibernate recovery happens + * much faster than a first, causing the observed TSC here to be + * smaller; this would require additional padding adjustment, which is + * why we set last_host_tsc to the local tsc observed here. + * + * N.B. - this code below runs only on platforms with reliable TSC, + * as that is the only way backwards_tsc is set above. Also note + * that this runs for ALL vcpus, which is not a bug; all VCPUs should + * have the same delta_cyc adjustment applied if backwards_tsc + * is detected. Note further, this adjustment is only done once, + * as we reset last_host_tsc on all VCPUs to stop this from being + * called multiple times (one for each physical CPU bringup). + * + * Platforms with unreliable TSCs don't have to deal with this, they + * will be compensated by the logic in vcpu_load, which sets the TSC to + * catchup mode. This will catchup all VCPUs to real time, but cannot + * guarantee that they stay in perfect synchronization. + */ + if (backwards_tsc) { + u64 delta_cyc = max_tsc - local_tsc; + backwards_tsc_observed = true; + list_for_each_entry(kvm, &vm_list, vm_list) { + kvm_for_each_vcpu(i, vcpu, kvm) { + vcpu->arch.tsc_offset_adjustment += delta_cyc; + vcpu->arch.last_host_tsc = local_tsc; + set_bit(KVM_REQ_MASTERCLOCK_UPDATE, + &vcpu->requests); + } + + /* + * We have to disable TSC offset matching.. if you were + * booting a VM while issuing an S4 host suspend.... + * you may have some problem. Solving this issue is + * left as an exercise to the reader. + */ + kvm->arch.last_tsc_nsec = 0; + kvm->arch.last_tsc_write = 0; + } + + } + return 0; } void kvm_arch_hardware_disable(void *garbage) { kvm_x86_ops->hardware_disable(garbage); + drop_user_return_notifiers(garbage); } int kvm_arch_hardware_setup(void) @@ -3130,6 +6997,13 @@ void kvm_arch_check_processor_compat(void *rtn) kvm_x86_ops->check_processor_compatibility(rtn); } +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) +{ + return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); +} + +struct static_key kvm_no_apic_vcpu __read_mostly; + int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { struct page *page; @@ -3139,11 +7013,12 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) BUG_ON(vcpu->kvm == NULL); kvm = vcpu->kvm; - vcpu->arch.mmu.root_hpa = INVALID_PAGE; - if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0) - vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE; + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.emulate_ctxt.ops = &emulate_ops; + if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else - vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED; + vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { @@ -3152,6 +7027,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) } vcpu->arch.pio_data = page_address(page); + kvm_set_tsc_khz(vcpu, max_tsc_khz); + r = kvm_mmu_create(vcpu); if (r < 0) goto fail_free_pio_data; @@ -3160,10 +7037,42 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) r = kvm_create_lapic(vcpu); if (r < 0) goto fail_mmu_destroy; + } else + static_key_slow_inc(&kvm_no_apic_vcpu); + + vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, + GFP_KERNEL); + if (!vcpu->arch.mce_banks) { + r = -ENOMEM; + goto fail_free_lapic; } + vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; - return 0; + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) { + r = -ENOMEM; + goto fail_free_mce_banks; + } + + r = fx_init(vcpu); + if (r) + goto fail_free_wbinvd_dirty_mask; + + vcpu->arch.ia32_tsc_adjust_msr = 0x0; + vcpu->arch.pv_time_enabled = false; + + vcpu->arch.guest_supported_xcr0 = 0; + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + kvm_async_pf_hash_reset(vcpu); + kvm_pmu_init(vcpu); + + return 0; +fail_free_wbinvd_dirty_mask: + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); +fail_free_mce_banks: + kfree(vcpu->arch.mce_banks); +fail_free_lapic: + kvm_free_lapic(vcpu); fail_mmu_destroy: kvm_mmu_destroy(vcpu); fail_free_pio_data: @@ -3174,26 +7083,52 @@ fail: void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { + int idx; + + kvm_pmu_destroy(vcpu); + kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_mmu_destroy(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); + if (!irqchip_in_kernel(vcpu->kvm)) + static_key_slow_dec(&kvm_no_apic_vcpu); } -struct kvm *kvm_arch_create_vm(void) +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); - - if (!kvm) - return ERR_PTR(-ENOMEM); + if (type) + return -EINVAL; INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); + atomic_set(&kvm->arch.noncoherent_dma_count, 0); - return kvm; + /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ + set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + /* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */ + set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + &kvm->arch.irq_sources_bitmap); + + raw_spin_lock_init(&kvm->arch.tsc_write_lock); + mutex_init(&kvm->arch.apic_map_lock); + spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock); + + pvclock_update_vm_gtod_copy(kvm); + + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); + INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); + + return 0; } static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { - vcpu_load(vcpu); + int r; + r = vcpu_load(vcpu); + BUG_ON(r); kvm_mmu_unload(vcpu); vcpu_put(vcpu); } @@ -3201,103 +7136,455 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { unsigned int i; + struct kvm_vcpu *vcpu; /* * Unpin any mmu pages first. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i]) - kvm_unload_vcpu_mmu(kvm->vcpus[i]); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_arch_vcpu_free(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_clear_async_pf_completion_queue(vcpu); + kvm_unload_vcpu_mmu(vcpu); } + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_arch_vcpu_free(vcpu); + mutex_lock(&kvm->lock); + for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) + kvm->vcpus[i] = NULL; + + atomic_set(&kvm->online_vcpus, 0); + mutex_unlock(&kvm->lock); +} + +void kvm_arch_sync_events(struct kvm *kvm) +{ + cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work); + cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work); + kvm_free_all_assigned_devices(kvm); + kvm_free_pit(kvm); } void kvm_arch_destroy_vm(struct kvm *kvm) { + if (current->mm == kvm->mm) { + /* + * Free memory regions allocated on behalf of userspace, + * unless the the memory map has changed due to process exit + * or fd copying. + */ + struct kvm_userspace_memory_region mem; + memset(&mem, 0, sizeof(mem)); + mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + + mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + + mem.slot = TSS_PRIVATE_MEMSLOT; + kvm_set_memory_region(kvm, &mem); + } + kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); kvm_free_vcpus(kvm); - kvm_free_physmem(kvm); - kfree(kvm); + if (kvm->arch.apic_access_page) + put_page(kvm->arch.apic_access_page); + if (kvm->arch.ept_identity_pagetable) + put_page(kvm->arch.ept_identity_pagetable); + kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); } -int kvm_arch_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - int user_alloc) +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) { - int npages = mem->memory_size >> PAGE_SHIFT; - struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot]; + int i; - /*To keep backward compatibility with older userspace, - *x86 needs to hanlde !user_alloc case. - */ - if (!user_alloc) { - if (npages && !old.rmap) { - down_write(¤t->mm->mmap_sem); - memslot->userspace_addr = do_mmap(NULL, 0, - npages * PAGE_SIZE, - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, - 0); - up_write(¤t->mm->mmap_sem); - - if (IS_ERR((void *)memslot->userspace_addr)) - return PTR_ERR((void *)memslot->userspace_addr); - } else { - if (!old.user_alloc && old.rmap) { - int ret; - - down_write(¤t->mm->mmap_sem); - ret = do_munmap(current->mm, old.userspace_addr, - old.npages * PAGE_SIZE); - up_write(¤t->mm->mmap_sem); - if (ret < 0) - printk(KERN_WARNING - "kvm_vm_ioctl_set_memory_region: " - "failed to munmap memory\n"); - } + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { + kvm_kvfree(free->arch.rmap[i]); + free->arch.rmap[i] = NULL; + } + if (i == 0) + continue; + + if (!dont || free->arch.lpage_info[i - 1] != + dont->arch.lpage_info[i - 1]) { + kvm_kvfree(free->arch.lpage_info[i - 1]); + free->arch.lpage_info[i - 1] = NULL; } } +} - if (!kvm->arch.n_requested_mmu_pages) { - unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); - kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) +{ + int i; + + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + unsigned long ugfn; + int lpages; + int level = i + 1; + + lpages = gfn_to_index(slot->base_gfn + npages - 1, + slot->base_gfn, level) + 1; + + slot->arch.rmap[i] = + kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i])); + if (!slot->arch.rmap[i]) + goto out_free; + if (i == 0) + continue; + + slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages * + sizeof(*slot->arch.lpage_info[i - 1])); + if (!slot->arch.lpage_info[i - 1]) + goto out_free; + + if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i - 1][0].write_count = 1; + if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) + slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1; + ugfn = slot->userspace_addr >> PAGE_SHIFT; + /* + * If the gfn and userspace address are not aligned wrt each + * other, or if explicitly asked to, disable large page + * support for this slot + */ + if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || + !kvm_largepages_enabled()) { + unsigned long j; + + for (j = 0; j < lpages; ++j) + slot->arch.lpage_info[i - 1][j].write_count = 1; + } } - kvm_mmu_slot_remove_write_access(kvm, mem->slot); - kvm_flush_remote_tlbs(kvm); + return 0; + +out_free: + for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + kvm_kvfree(slot->arch.rmap[i]); + slot->arch.rmap[i] = NULL; + if (i == 0) + continue; + + kvm_kvfree(slot->arch.lpage_info[i - 1]); + slot->arch.lpage_info[i - 1] = NULL; + } + return -ENOMEM; +} + +void kvm_arch_memslots_updated(struct kvm *kvm) +{ + /* + * memslots->generation has been incremented. + * mmio generation may have reached its maximum value. + */ + kvm_mmu_invalidate_mmio_sptes(kvm); +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) +{ + /* + * Only private memory slots need to be mapped here since + * KVM_SET_MEMORY_REGION ioctl is no longer supported. + */ + if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) { + unsigned long userspace_addr; + + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); + + if (IS_ERR((void *)userspace_addr)) + return PTR_ERR((void *)userspace_addr); + + memslot->userspace_addr = userspace_addr; + } return 0; } +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + enum kvm_mr_change change) +{ + + int nr_mmu_pages = 0; + + if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) { + int ret; + + ret = vm_munmap(old->userspace_addr, + old->npages * PAGE_SIZE); + if (ret < 0) + printk(KERN_WARNING + "kvm_vm_ioctl_set_memory_region: " + "failed to munmap memory\n"); + } + + if (!kvm->arch.n_requested_mmu_pages) + nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); + + if (nr_mmu_pages) + kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + /* + * Write protect all pages for dirty logging. + * + * All the sptes including the large sptes which point to this + * slot are set to readonly. We can not create any new large + * spte on this slot until the end of the logging. + * + * See the comments in fast_page_fault(). + */ + if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) + kvm_mmu_slot_remove_write_access(kvm, mem->slot); +} + +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ + kvm_mmu_invalidate_zap_all_pages(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + kvm_mmu_invalidate_zap_all_pages(kvm); +} + int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - return vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE - || vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED; + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) + kvm_x86_ops->check_nested_events(vcpu, false); + + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted) + || !list_empty_careful(&vcpu->async_pf.done) + || kvm_apic_has_events(vcpu) + || vcpu->arch.pv.pv_unhalted + || atomic_read(&vcpu->arch.nmi_queued) || + (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)); } -static void vcpu_kick_intr(void *info) +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { -#ifdef DEBUG - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info; - printk(KERN_DEBUG "vcpu_kick_intr %p \n", vcpu); -#endif + return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) +int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - int ipi_pcpu = vcpu->cpu; + return kvm_x86_ops->interrupt_allowed(vcpu); +} + +bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) +{ + unsigned long current_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + return current_rip == linear_rip; +} +EXPORT_SYMBOL_GPL(kvm_is_linear_rip); + +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~X86_EFLAGS_TF; + return rflags; +} +EXPORT_SYMBOL_GPL(kvm_get_rflags); + +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) + rflags |= X86_EFLAGS_TF; + kvm_x86_ops->set_rflags(vcpu, rflags); + kvm_make_request(KVM_REQ_EVENT, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_set_rflags); + +void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) +{ + int r; + + if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) || + work->wakeup_all) + return; + + r = kvm_mmu_reload(vcpu); + if (unlikely(r)) + return; + + if (!vcpu->arch.mmu.direct_map && + work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu)) + return; + + vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true); +} + +static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) +{ + return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU)); +} + +static inline u32 kvm_async_pf_next_probe(u32 key) +{ + return (key + 1) & (roundup_pow_of_two(ASYNC_PF_PER_VCPU) - 1); +} + +static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + u32 key = kvm_async_pf_hash_fn(gfn); + + while (vcpu->arch.apf.gfns[key] != ~0) + key = kvm_async_pf_next_probe(key); + + vcpu->arch.apf.gfns[key] = gfn; +} + +static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + int i; + u32 key = kvm_async_pf_hash_fn(gfn); + + for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU) && + (vcpu->arch.apf.gfns[key] != gfn && + vcpu->arch.apf.gfns[key] != ~0); i++) + key = kvm_async_pf_next_probe(key); - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); - ++vcpu->stat.halt_wakeup; + return key; +} + +bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn; +} + +static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + u32 i, j, k; + + i = j = kvm_async_pf_gfn_slot(vcpu, gfn); + while (true) { + vcpu->arch.apf.gfns[i] = ~0; + do { + j = kvm_async_pf_next_probe(j); + if (vcpu->arch.apf.gfns[j] == ~0) + return; + k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]); + /* + * k lies cyclically in ]i,j] + * | i.k.j | + * |....j i.k.| or |.k..j i...| + */ + } while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); + vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j]; + i = j; + } +} + +static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) +{ + + return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, + sizeof(val)); +} + +void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ + struct x86_exception fault; + + trace_kvm_async_pf_not_present(work->arch.token, work->gva); + kvm_add_async_pf_gfn(vcpu, work->arch.gfn); + + if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || + (vcpu->arch.apf.send_user_only && + kvm_x86_ops->get_cpl(vcpu) == 0)) + kvm_make_request(KVM_REQ_APF_HALT, vcpu); + else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) { + fault.vector = PF_VECTOR; + fault.error_code_valid = true; + fault.error_code = 0; + fault.nested_page_fault = false; + fault.address = work->arch.token; + kvm_inject_page_fault(vcpu, &fault); } - if (vcpu->guest_mode) - smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0); } + +void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work) +{ + struct x86_exception fault; + + trace_kvm_async_pf_ready(work->arch.token, work->gva); + if (work->wakeup_all) + work->arch.token = ~0; /* broadcast wakeup */ + else + kvm_del_async_pf_gfn(vcpu, work->arch.gfn); + + if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && + !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { + fault.vector = PF_VECTOR; + fault.error_code_valid = true; + fault.error_code = 0; + fault.nested_page_fault = false; + fault.address = work->arch.token; + kvm_inject_page_fault(vcpu, &fault); + } + vcpu->arch.apf.halted = false; + vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; +} + +bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) + return true; + else + return !kvm_event_needs_reinjection(vcpu) && + kvm_x86_ops->interrupt_allowed(vcpu); +} + +void kvm_arch_register_noncoherent_dma(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); + +void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); + +bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); + +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); |