summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/vmx.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/vmx.c')
-rw-r--r--arch/x86/kvm/vmx.c667
1 files changed, 425 insertions, 242 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 14873b9f8430..27a0222c2946 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5,6 +5,7 @@
* machines without emulation or binary translation.
*
* Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2010 Red Hat, Inc. and/or its affilates.
*
* Authors:
* Avi Kivity <avi@qumranet.com>
@@ -26,6 +27,8 @@
#include <linux/sched.h>
#include <linux/moduleparam.h>
#include <linux/ftrace_event.h>
+#include <linux/slab.h>
+#include <linux/tboot.h>
#include "kvm_cache_regs.h"
#include "x86.h"
@@ -34,6 +37,8 @@
#include <asm/vmx.h>
#include <asm/virtext.h>
#include <asm/mce.h>
+#include <asm/i387.h>
+#include <asm/xcr.h>
#include "trace.h"
@@ -61,6 +66,9 @@ module_param_named(unrestricted_guest,
static int __read_mostly emulate_invalid_guest_state = 0;
module_param(emulate_invalid_guest_state, bool, S_IRUGO);
+static int __read_mostly vmm_exclusive = 1;
+module_param(vmm_exclusive, bool, S_IRUGO);
+
#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \
(X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
#define KVM_GUEST_CR0_MASK \
@@ -76,6 +84,8 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
+#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
+
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* ple_gap: upper bound on the amount of time between two successive
@@ -95,6 +105,8 @@ module_param(ple_gap, int, S_IRUGO);
static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);
+#define NR_AUTOLOAD_MSRS 1
+
struct vmcs {
u32 revision_id;
u32 abort;
@@ -122,6 +134,11 @@ struct vcpu_vmx {
u64 msr_guest_kernel_gs_base;
#endif
struct vmcs *vmcs;
+ struct msr_autoload {
+ unsigned nr;
+ struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
+ struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+ } msr_autoload;
struct {
int loaded;
u16 fs_sel, gs_sel, ldt_sel;
@@ -130,7 +147,7 @@ struct vcpu_vmx {
} host_state;
struct {
int vm86_active;
- u8 save_iopl;
+ ulong save_rflags;
struct kvm_save_segment {
u16 selector;
unsigned long base;
@@ -162,10 +179,13 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
static int init_rmode(struct kvm *kvm);
static u64 construct_eptp(unsigned long root_hpa);
+static void kvm_cpu_vmxon(u64 addr);
+static void kvm_cpu_vmxoff(void);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu);
+static DEFINE_PER_CPU(struct desc_ptr, host_gdt);
static unsigned long *vmx_io_bitmap_a;
static unsigned long *vmx_io_bitmap_b;
@@ -231,56 +251,56 @@ static const u32 vmx_msr_index[] = {
};
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
-static inline int is_page_fault(u32 intr_info)
+static inline bool is_page_fault(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int is_no_device(u32 intr_info)
+static inline bool is_no_device(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int is_invalid_opcode(u32 intr_info)
+static inline bool is_invalid_opcode(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int is_external_interrupt(u32 intr_info)
+static inline bool is_external_interrupt(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
-static inline int is_machine_check(u32 intr_info)
+static inline bool is_machine_check(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int cpu_has_vmx_msr_bitmap(void)
+static inline bool cpu_has_vmx_msr_bitmap(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
}
-static inline int cpu_has_vmx_tpr_shadow(void)
+static inline bool cpu_has_vmx_tpr_shadow(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
}
-static inline int vm_need_tpr_shadow(struct kvm *kvm)
+static inline bool vm_need_tpr_shadow(struct kvm *kvm)
{
return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
}
-static inline int cpu_has_secondary_exec_ctrls(void)
+static inline bool cpu_has_secondary_exec_ctrls(void)
{
return vmcs_config.cpu_based_exec_ctrl &
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
@@ -300,84 +320,105 @@ static inline bool cpu_has_vmx_flexpriority(void)
static inline bool cpu_has_vmx_ept_execute_only(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT);
+ return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
}
static inline bool cpu_has_vmx_eptp_uncacheable(void)
{
- return !!(vmx_capability.ept & VMX_EPTP_UC_BIT);
+ return vmx_capability.ept & VMX_EPTP_UC_BIT;
}
static inline bool cpu_has_vmx_eptp_writeback(void)
{
- return !!(vmx_capability.ept & VMX_EPTP_WB_BIT);
+ return vmx_capability.ept & VMX_EPTP_WB_BIT;
}
static inline bool cpu_has_vmx_ept_2m_page(void)
{
- return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
+ return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
}
static inline bool cpu_has_vmx_ept_1g_page(void)
{
- return !!(vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT);
+ return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_4levels(void)
+{
+ return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
+}
+
+static inline bool cpu_has_vmx_invept_individual_addr(void)
+{
+ return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT;
}
-static inline int cpu_has_vmx_invept_individual_addr(void)
+static inline bool cpu_has_vmx_invept_context(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
}
-static inline int cpu_has_vmx_invept_context(void)
+static inline bool cpu_has_vmx_invept_global(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}
-static inline int cpu_has_vmx_invept_global(void)
+static inline bool cpu_has_vmx_invvpid_single(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT);
+ return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
}
-static inline int cpu_has_vmx_ept(void)
+static inline bool cpu_has_vmx_invvpid_global(void)
+{
+ return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
+}
+
+static inline bool cpu_has_vmx_ept(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_EPT;
}
-static inline int cpu_has_vmx_unrestricted_guest(void)
+static inline bool cpu_has_vmx_unrestricted_guest(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_UNRESTRICTED_GUEST;
}
-static inline int cpu_has_vmx_ple(void)
+static inline bool cpu_has_vmx_ple(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}
-static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
+static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
{
return flexpriority_enabled && irqchip_in_kernel(kvm);
}
-static inline int cpu_has_vmx_vpid(void)
+static inline bool cpu_has_vmx_vpid(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_VPID;
}
-static inline int cpu_has_vmx_rdtscp(void)
+static inline bool cpu_has_vmx_rdtscp(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_RDTSCP;
}
-static inline int cpu_has_virtual_nmis(void)
+static inline bool cpu_has_virtual_nmis(void)
{
return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
}
+static inline bool cpu_has_vmx_wbinvd_exit(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_WBINVD_EXITING;
+}
+
static inline bool report_flexpriority(void)
{
return flexpriority_enabled;
@@ -442,6 +483,19 @@ static void vmcs_clear(struct vmcs *vmcs)
vmcs, phys_addr);
}
+static void vmcs_load(struct vmcs *vmcs)
+{
+ u64 phys_addr = __pa(vmcs);
+ u8 error;
+
+ asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0"
+ : "=g"(error) : "a"(&phys_addr), "m"(phys_addr)
+ : "cc", "memory");
+ if (error)
+ printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n",
+ vmcs, phys_addr);
+}
+
static void __vcpu_clear(void *arg)
{
struct vcpu_vmx *vmx = arg;
@@ -464,12 +518,27 @@ static void vcpu_clear(struct vcpu_vmx *vmx)
smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1);
}
-static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx)
+static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx)
{
if (vmx->vpid == 0)
return;
- __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0);
+ if (cpu_has_vmx_invvpid_single())
+ __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0);
+}
+
+static inline void vpid_sync_vcpu_global(void)
+{
+ if (cpu_has_vmx_invvpid_global())
+ __invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0);
+}
+
+static inline void vpid_sync_context(struct vcpu_vmx *vmx)
+{
+ if (cpu_has_vmx_invvpid_single())
+ vpid_sync_vcpu_single(vmx);
+ else
+ vpid_sync_vcpu_global();
}
static inline void ept_sync_global(void)
@@ -592,16 +661,56 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
vmcs_write32(EXCEPTION_BITMAP, eb);
}
+static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
+{
+ unsigned i;
+ struct msr_autoload *m = &vmx->msr_autoload;
+
+ for (i = 0; i < m->nr; ++i)
+ if (m->guest[i].index == msr)
+ break;
+
+ if (i == m->nr)
+ return;
+ --m->nr;
+ m->guest[i] = m->guest[m->nr];
+ m->host[i] = m->host[m->nr];
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+}
+
+static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
+ u64 guest_val, u64 host_val)
+{
+ unsigned i;
+ struct msr_autoload *m = &vmx->msr_autoload;
+
+ for (i = 0; i < m->nr; ++i)
+ if (m->guest[i].index == msr)
+ break;
+
+ if (i == m->nr) {
+ ++m->nr;
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+ }
+
+ m->guest[i].index = msr;
+ m->guest[i].value = guest_val;
+ m->host[i].index = msr;
+ m->host[i].value = host_val;
+}
+
static void reload_tss(void)
{
/*
* VT restores TR but not its size. Useless.
*/
- struct descriptor_table gdt;
+ struct desc_ptr gdt;
struct desc_struct *descs;
- kvm_get_gdt(&gdt);
- descs = (void *)gdt.base;
+ native_store_gdt(&gdt);
+ descs = (void *)gdt.address;
descs[GDT_ENTRY_TSS].type = 9; /* available TSS */
load_TR_desc();
}
@@ -628,9 +737,57 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
guest_efer |= host_efer & ignore_bits;
vmx->guest_msrs[efer_offset].data = guest_efer;
vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+ clear_atomic_switch_msr(vmx, MSR_EFER);
+ /* On ept, can't emulate nx, and must switch nx atomically */
+ if (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX)) {
+ guest_efer = vmx->vcpu.arch.efer;
+ if (!(guest_efer & EFER_LMA))
+ guest_efer &= ~EFER_LME;
+ add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer);
+ return false;
+ }
+
return true;
}
+static unsigned long segment_base(u16 selector)
+{
+ struct desc_ptr gdt;
+ struct desc_struct *d;
+ unsigned long table_base;
+ unsigned long v;
+
+ if (!(selector & ~3))
+ return 0;
+
+ native_store_gdt(&gdt);
+ table_base = gdt.address;
+
+ if (selector & 4) { /* from ldt */
+ u16 ldt_selector = kvm_read_ldt();
+
+ if (!(ldt_selector & ~3))
+ return 0;
+
+ table_base = segment_base(ldt_selector);
+ }
+ d = (struct desc_struct *)(table_base + (selector & ~7));
+ v = get_desc_base(d);
+#ifdef CONFIG_X86_64
+ if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+ v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
+#endif
+ return v;
+}
+
+static inline unsigned long kvm_read_tr_base(void)
+{
+ u16 tr;
+ asm("str %0" : "=g"(tr));
+ return segment_base(tr);
+}
+
static void vmx_save_host_state(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -713,6 +870,9 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
}
#endif
+ if (current_thread_info()->status & TS_USEDFPU)
+ clts();
+ load_gdt(&__get_cpu_var(host_gdt));
}
static void vmx_load_host_state(struct vcpu_vmx *vmx)
@@ -729,43 +889,38 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx)
static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u64 phys_addr = __pa(vmx->vmcs);
u64 tsc_this, delta, new_offset;
+ u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
- if (vcpu->cpu != cpu) {
+ if (!vmm_exclusive)
+ kvm_cpu_vmxon(phys_addr);
+ else if (vcpu->cpu != cpu)
vcpu_clear(vmx);
- kvm_migrate_timers(vcpu);
- set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
- local_irq_disable();
- list_add(&vmx->local_vcpus_link,
- &per_cpu(vcpus_on_cpu, cpu));
- local_irq_enable();
- }
if (per_cpu(current_vmcs, cpu) != vmx->vmcs) {
- u8 error;
-
per_cpu(current_vmcs, cpu) = vmx->vmcs;
- asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0"
- : "=g"(error) : "a"(&phys_addr), "m"(phys_addr)
- : "cc");
- if (error)
- printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n",
- vmx->vmcs, phys_addr);
+ vmcs_load(vmx->vmcs);
}
if (vcpu->cpu != cpu) {
- struct descriptor_table dt;
+ struct desc_ptr dt;
unsigned long sysenter_esp;
+ kvm_migrate_timers(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ local_irq_disable();
+ list_add(&vmx->local_vcpus_link,
+ &per_cpu(vcpus_on_cpu, cpu));
+ local_irq_enable();
+
vcpu->cpu = cpu;
/*
* Linux uses per-cpu TSS and GDT, so set these when switching
* processors.
*/
vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */
- kvm_get_gdt(&dt);
- vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */
+ native_store_gdt(&dt);
+ vmcs_writel(HOST_GDTR_BASE, dt.address); /* 22.2.4 */
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
@@ -785,6 +940,10 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
__vmx_load_host_state(to_vmx(vcpu));
+ if (!vmm_exclusive) {
+ __vcpu_clear(to_vmx(vcpu));
+ kvm_cpu_vmxoff();
+ }
}
static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
@@ -817,18 +976,23 @@ static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
- unsigned long rflags;
+ unsigned long rflags, save_rflags;
rflags = vmcs_readl(GUEST_RFLAGS);
- if (to_vmx(vcpu)->rmode.vm86_active)
- rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
+ if (to_vmx(vcpu)->rmode.vm86_active) {
+ rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+ save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+ rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+ }
return rflags;
}
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
- if (to_vmx(vcpu)->rmode.vm86_active)
+ if (to_vmx(vcpu)->rmode.vm86_active) {
+ to_vmx(vcpu)->rmode.save_rflags = rflags;
rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
+ }
vmcs_writel(GUEST_RFLAGS, rflags);
}
@@ -838,9 +1002,9 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
int ret = 0;
if (interruptibility & GUEST_INTR_STATE_STI)
- ret |= X86_SHADOW_INT_STI;
+ ret |= KVM_X86_SHADOW_INT_STI;
if (interruptibility & GUEST_INTR_STATE_MOV_SS)
- ret |= X86_SHADOW_INT_MOV_SS;
+ ret |= KVM_X86_SHADOW_INT_MOV_SS;
return ret & mask;
}
@@ -852,9 +1016,9 @@ static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
- if (mask & X86_SHADOW_INT_MOV_SS)
+ if (mask & KVM_X86_SHADOW_INT_MOV_SS)
interruptibility |= GUEST_INTR_STATE_MOV_SS;
- if (mask & X86_SHADOW_INT_STI)
+ else if (mask & KVM_X86_SHADOW_INT_STI)
interruptibility |= GUEST_INTR_STATE_STI;
if ((interruptibility != interruptibility_old))
@@ -874,7 +1038,8 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
}
static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code)
+ bool has_error_code, u32 error_code,
+ bool reinject)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info = nr | INTR_INFO_VALID_MASK;
@@ -1168,37 +1333,55 @@ static __init int vmx_disabled_by_bios(void)
u64 msr;
rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
- return (msr & (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
- == FEATURE_CONTROL_LOCKED;
+ if (msr & FEATURE_CONTROL_LOCKED) {
+ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
+ && tboot_enabled())
+ return 1;
+ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
+ && !tboot_enabled())
+ return 1;
+ }
+
+ return 0;
/* locked but not enabled */
}
+static void kvm_cpu_vmxon(u64 addr)
+{
+ asm volatile (ASM_VMX_VMXON_RAX
+ : : "a"(&addr), "m"(addr)
+ : "memory", "cc");
+}
+
static int hardware_enable(void *garbage)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
- u64 old;
+ u64 old, test_bits;
if (read_cr4() & X86_CR4_VMXE)
return -EBUSY;
INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu));
rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
- if ((old & (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
- != (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
+
+ test_bits = FEATURE_CONTROL_LOCKED;
+ test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ if (tboot_enabled())
+ test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;
+
+ if ((old & test_bits) != test_bits) {
/* enable and lock */
- wrmsrl(MSR_IA32_FEATURE_CONTROL, old |
- FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED);
+ wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
+ }
write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */
- asm volatile (ASM_VMX_VMXON_RAX
- : : "a"(&phys_addr), "m"(phys_addr)
- : "memory", "cc");
- ept_sync_global();
+ if (vmm_exclusive) {
+ kvm_cpu_vmxon(phys_addr);
+ ept_sync_global();
+ }
+
+ store_gdt(&__get_cpu_var(host_gdt));
return 0;
}
@@ -1220,13 +1403,15 @@ static void vmclear_local_vcpus(void)
static void kvm_cpu_vmxoff(void)
{
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
- write_cr4(read_cr4() & ~X86_CR4_VMXE);
}
static void hardware_disable(void *garbage)
{
- vmclear_local_vcpus();
- kvm_cpu_vmxoff();
+ if (vmm_exclusive) {
+ vmclear_local_vcpus();
+ kvm_cpu_vmxoff();
+ }
+ write_cr4(read_cr4() & ~X86_CR4_VMXE);
}
static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
@@ -1425,7 +1610,8 @@ static __init int hardware_setup(void)
if (!cpu_has_vmx_vpid())
enable_vpid = 0;
- if (!cpu_has_vmx_ept()) {
+ if (!cpu_has_vmx_ept() ||
+ !cpu_has_vmx_ept_4levels()) {
enable_ept = 0;
enable_unrestricted_guest = 0;
}
@@ -1482,8 +1668,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
flags = vmcs_readl(GUEST_RFLAGS);
- flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
- flags |= (vmx->rmode.save_iopl << IOPL_SHIFT);
+ flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+ flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
@@ -1513,8 +1699,8 @@ static gva_t rmode_tss_base(struct kvm *kvm)
struct kvm_memslots *slots;
gfn_t base_gfn;
- slots = rcu_dereference(kvm->memslots);
- base_gfn = kvm->memslots->memslots[0].base_gfn +
+ slots = kvm_memslots(kvm);
+ base_gfn = slots->memslots[0].base_gfn +
kvm->memslots->memslots[0].npages - 3;
return base_gfn << PAGE_SHIFT;
}
@@ -1556,8 +1742,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
flags = vmcs_readl(GUEST_RFLAGS);
- vmx->rmode.save_iopl
- = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
+ vmx->rmode.save_rflags = flags;
flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
@@ -1631,26 +1816,27 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
}
- vcpu->arch.efer |= EFER_LMA;
- vmx_set_efer(vcpu, vcpu->arch.efer);
+ vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
}
static void exit_lmode(struct kvm_vcpu *vcpu)
{
- vcpu->arch.efer &= ~EFER_LMA;
-
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS)
& ~VM_ENTRY_IA32E_MODE);
+ vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
}
#endif
static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
{
- vpid_sync_vcpu_all(to_vmx(vcpu));
- if (enable_ept)
+ vpid_sync_context(to_vmx(vcpu));
+ if (enable_ept) {
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return;
ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa));
+ }
}
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
@@ -1927,28 +2113,28 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
*l = (ar >> 13) & 1;
}
-static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- dt->limit = vmcs_read32(GUEST_IDTR_LIMIT);
- dt->base = vmcs_readl(GUEST_IDTR_BASE);
+ dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
+ dt->address = vmcs_readl(GUEST_IDTR_BASE);
}
-static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- vmcs_write32(GUEST_IDTR_LIMIT, dt->limit);
- vmcs_writel(GUEST_IDTR_BASE, dt->base);
+ vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
+ vmcs_writel(GUEST_IDTR_BASE, dt->address);
}
-static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- dt->limit = vmcs_read32(GUEST_GDTR_LIMIT);
- dt->base = vmcs_readl(GUEST_GDTR_BASE);
+ dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
+ dt->address = vmcs_readl(GUEST_GDTR_BASE);
}
-static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- vmcs_write32(GUEST_GDTR_LIMIT, dt->limit);
- vmcs_writel(GUEST_GDTR_BASE, dt->base);
+ vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
+ vmcs_writel(GUEST_GDTR_BASE, dt->address);
}
static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
@@ -2289,6 +2475,16 @@ static void allocate_vpid(struct vcpu_vmx *vmx)
spin_unlock(&vmx_vpid_lock);
}
+static void free_vpid(struct vcpu_vmx *vmx)
+{
+ if (!enable_vpid)
+ return;
+ spin_lock(&vmx_vpid_lock);
+ if (vmx->vpid != 0)
+ __clear_bit(vmx->vpid, vmx_vpid_bitmap);
+ spin_unlock(&vmx_vpid_lock);
+}
+
static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
{
int f = sizeof(unsigned long);
@@ -2327,7 +2523,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
u32 junk;
u64 host_pat, tsc_this, tsc_base;
unsigned long a;
- struct descriptor_table dt;
+ struct desc_ptr dt;
int i;
unsigned long kvm_vmx_return;
u32 exec_control;
@@ -2386,7 +2582,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */
- vmcs_writel(HOST_CR0, read_cr0()); /* 22.2.3 */
+ vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 22.2.3 */
vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */
vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */
@@ -2408,14 +2604,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */
- kvm_get_idt(&dt);
- vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */
+ native_store_idt(&dt);
+ vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk);
vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs);
@@ -2476,21 +2674,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
static int init_rmode(struct kvm *kvm)
{
+ int idx, ret = 0;
+
+ idx = srcu_read_lock(&kvm->srcu);
if (!init_rmode_tss(kvm))
- return 0;
+ goto exit;
if (!init_rmode_identity_map(kvm))
- return 0;
- return 1;
+ goto exit;
+
+ ret = 1;
+exit:
+ srcu_read_unlock(&kvm->srcu, idx);
+ return ret;
}
static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 msr;
- int ret, idx;
+ int ret;
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
- idx = srcu_read_lock(&vcpu->kvm->srcu);
if (!init_rmode(vmx->vcpu.kvm)) {
ret = -ENOMEM;
goto out;
@@ -2507,7 +2711,9 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
msr |= MSR_IA32_APICBASE_BSP;
kvm_set_apic_base(&vmx->vcpu, msr);
- fx_init(&vmx->vcpu);
+ ret = fx_init(&vmx->vcpu);
+ if (ret != 0)
+ goto out;
seg_setup(VCPU_SREG_CS);
/*
@@ -2590,7 +2796,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx_fpu_activate(&vmx->vcpu);
update_exception_bitmap(&vmx->vcpu);
- vpid_sync_vcpu_all(vmx);
+ vpid_sync_context(vmx);
ret = 0;
@@ -2598,7 +2804,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->emulation_required = 0;
out:
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
}
@@ -2696,17 +2901,14 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
return 0;
return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
- (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS |
- GUEST_INTR_STATE_NMI));
+ (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_NMI));
}
static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
{
if (!cpu_has_virtual_nmis())
return to_vmx(vcpu)->soft_vnmi_blocked;
- else
- return !!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
- GUEST_INTR_STATE_NMI);
+ return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
}
static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
@@ -2941,22 +3143,20 @@ static int handle_io(struct kvm_vcpu *vcpu)
int size, in, string;
unsigned port;
- ++vcpu->stat.io_exits;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
string = (exit_qualification & 16) != 0;
+ in = (exit_qualification & 8) != 0;
- if (string) {
- if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO)
- return 0;
- return 1;
- }
+ ++vcpu->stat.io_exits;
- size = (exit_qualification & 7) + 1;
- in = (exit_qualification & 8) != 0;
- port = exit_qualification >> 16;
+ if (string || in)
+ return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
+ port = exit_qualification >> 16;
+ size = (exit_qualification & 7) + 1;
skip_emulated_instruction(vcpu);
- return kvm_emulate_pio(vcpu, in, size, port);
+
+ return kvm_fast_pio_out(vcpu, size, port);
}
static void
@@ -2970,11 +3170,20 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
hypercall[2] = 0xc1;
}
+static void complete_insn_gp(struct kvm_vcpu *vcpu, int err)
+{
+ if (err)
+ kvm_inject_gp(vcpu, 0);
+ else
+ skip_emulated_instruction(vcpu);
+}
+
static int handle_cr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification, val;
int cr;
int reg;
+ int err;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
cr = exit_qualification & 15;
@@ -2985,16 +3194,16 @@ static int handle_cr(struct kvm_vcpu *vcpu)
trace_kvm_cr_write(cr, val);
switch (cr) {
case 0:
- kvm_set_cr0(vcpu, val);
- skip_emulated_instruction(vcpu);
+ err = kvm_set_cr0(vcpu, val);
+ complete_insn_gp(vcpu, err);
return 1;
case 3:
- kvm_set_cr3(vcpu, val);
- skip_emulated_instruction(vcpu);
+ err = kvm_set_cr3(vcpu, val);
+ complete_insn_gp(vcpu, err);
return 1;
case 4:
- kvm_set_cr4(vcpu, val);
- skip_emulated_instruction(vcpu);
+ err = kvm_set_cr4(vcpu, val);
+ complete_insn_gp(vcpu, err);
return 1;
case 8: {
u8 cr8_prev = kvm_get_cr8(vcpu);
@@ -3047,19 +3256,9 @@ static int handle_cr(struct kvm_vcpu *vcpu)
return 0;
}
-static int check_dr_alias(struct kvm_vcpu *vcpu)
-{
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
- return -1;
- }
- return 0;
-}
-
static int handle_dr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
- unsigned long val;
int dr, reg;
/* Do not handle if the CPL > 0, will trigger GP on re-entry */
@@ -3094,67 +3293,20 @@ static int handle_dr(struct kvm_vcpu *vcpu)
dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
reg = DEBUG_REG_ACCESS_REG(exit_qualification);
if (exit_qualification & TYPE_MOV_FROM_DR) {
- switch (dr) {
- case 0 ... 3:
- val = vcpu->arch.db[dr];
- break;
- case 4:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- case 6:
- val = vcpu->arch.dr6;
- break;
- case 5:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- default: /* 7 */
- val = vcpu->arch.dr7;
- break;
- }
- kvm_register_write(vcpu, reg, val);
- } else {
- val = vcpu->arch.regs[reg];
- 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 (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- case 6:
- if (val & 0xffffffff00000000ULL) {
- kvm_inject_gp(vcpu, 0);
- return 1;
- }
- vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
- break;
- case 5:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- default: /* 7 */
- if (val & 0xffffffff00000000ULL) {
- kvm_inject_gp(vcpu, 0);
- return 1;
- }
- vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
- vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
- vcpu->arch.switch_db_regs =
- (val & DR7_BP_EN_MASK);
- }
- break;
- }
- }
+ unsigned long val;
+ if (!kvm_get_dr(vcpu, dr, &val))
+ kvm_register_write(vcpu, reg, val);
+ } else
+ kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
}
+static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ vmcs_writel(GUEST_DR7, val);
+}
+
static int handle_cpuid(struct kvm_vcpu *vcpu)
{
kvm_emulate_cpuid(vcpu);
@@ -3258,34 +3410,31 @@ static int handle_invlpg(struct kvm_vcpu *vcpu)
static int handle_wbinvd(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
- /* TODO: Add support for VT-d/pass-through device */
+ kvm_emulate_wbinvd(vcpu);
return 1;
}
-static int handle_apic_access(struct kvm_vcpu *vcpu)
+static int handle_xsetbv(struct kvm_vcpu *vcpu)
{
- unsigned long exit_qualification;
- enum emulation_result er;
- unsigned long offset;
+ u64 new_bv = kvm_read_edx_eax(vcpu);
+ u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX);
- exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
- offset = exit_qualification & 0xffful;
-
- er = emulate_instruction(vcpu, 0, 0, 0);
-
- if (er != EMULATE_DONE) {
- printk(KERN_ERR
- "Fail to handle apic access vmexit! Offset is 0x%lx\n",
- offset);
- return -ENOEXEC;
- }
+ if (kvm_set_xcr(vcpu, index, new_bv) == 0)
+ skip_emulated_instruction(vcpu);
return 1;
}
+static int handle_apic_access(struct kvm_vcpu *vcpu)
+{
+ return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
+}
+
static int handle_task_switch(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qualification;
+ bool has_error_code = false;
+ u32 error_code = 0;
u16 tss_selector;
int reason, type, idt_v;
@@ -3308,6 +3457,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
kvm_clear_interrupt_queue(vcpu);
break;
case INTR_TYPE_HARD_EXCEPTION:
+ if (vmx->idt_vectoring_info &
+ VECTORING_INFO_DELIVER_CODE_MASK) {
+ has_error_code = true;
+ error_code =
+ vmcs_read32(IDT_VECTORING_ERROR_CODE);
+ }
+ /* fall through */
case INTR_TYPE_SOFT_EXCEPTION:
kvm_clear_exception_queue(vcpu);
break;
@@ -3322,8 +3478,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
type != INTR_TYPE_NMI_INTR))
skip_emulated_instruction(vcpu);
- if (!kvm_task_switch(vcpu, tss_selector, reason))
+ if (kvm_task_switch(vcpu, tss_selector, reason,
+ has_error_code, error_code) == EMULATE_FAIL) {
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
return 0;
+ }
/* clear all local breakpoint enable flags */
vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
@@ -3477,13 +3638,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
goto out;
}
- if (err != EMULATE_DONE) {
- vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
- vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
- vcpu->run->internal.ndata = 0;
- ret = 0;
- goto out;
- }
+ if (err != EMULATE_DONE)
+ return 0;
if (signal_pending(current))
goto out;
@@ -3546,6 +3702,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,
[EXIT_REASON_APIC_ACCESS] = handle_apic_access,
[EXIT_REASON_WBINVD] = handle_wbinvd,
+ [EXIT_REASON_XSETBV] = handle_xsetbv,
[EXIT_REASON_TASK_SWITCH] = handle_task_switch,
[EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check,
[EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
@@ -3568,7 +3725,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
u32 exit_reason = vmx->exit_reason;
u32 vectoring_info = vmx->idt_vectoring_info;
- trace_kvm_exit(exit_reason, kvm_rip_read(vcpu));
+ trace_kvm_exit(exit_reason, vcpu);
/* If guest state is invalid, start emulating */
if (vmx->emulation_required && emulate_invalid_guest_state)
@@ -3579,6 +3736,13 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
if (enable_ept && is_paging(vcpu))
vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
+ vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ vcpu->run->fail_entry.hardware_entry_failure_reason
+ = exit_reason;
+ return 0;
+ }
+
if (unlikely(vmx->fail)) {
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
vcpu->run->fail_entry.hardware_entry_failure_reason
@@ -3653,8 +3817,11 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
/* We need to handle NMIs before interrupts are enabled */
if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
- (exit_intr_info & INTR_INFO_VALID_MASK))
+ (exit_intr_info & INTR_INFO_VALID_MASK)) {
+ kvm_before_handle_nmi(&vmx->vcpu);
asm("int $2");
+ kvm_after_handle_nmi(&vmx->vcpu);
+ }
idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
@@ -3781,11 +3948,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
- /*
- * Loading guest fpu may have cleared host cr0.ts
- */
- vmcs_writel(HOST_CR0, read_cr0());
-
asm(
/* Store host registers */
"push %%"R"dx; push %%"R"bp;"
@@ -3914,16 +4076,26 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- spin_lock(&vmx_vpid_lock);
- if (vmx->vpid != 0)
- __clear_bit(vmx->vpid, vmx_vpid_bitmap);
- spin_unlock(&vmx_vpid_lock);
+ free_vpid(vmx);
vmx_free_vmcs(vcpu);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
}
+static inline void vmcs_init(struct vmcs *vmcs)
+{
+ u64 phys_addr = __pa(per_cpu(vmxarea, raw_smp_processor_id()));
+
+ if (!vmm_exclusive)
+ kvm_cpu_vmxon(phys_addr);
+
+ vmcs_clear(vmcs);
+
+ if (!vmm_exclusive)
+ kvm_cpu_vmxoff();
+}
+
static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
{
int err;
@@ -3949,7 +4121,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
if (!vmx->vmcs)
goto free_msrs;
- vmcs_clear(vmx->vmcs);
+ vmcs_init(vmx->vmcs);
cpu = get_cpu();
vmx_vcpu_load(&vmx->vcpu, cpu);
@@ -3979,6 +4151,7 @@ free_msrs:
uninit_vcpu:
kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
+ free_vpid(vmx);
kmem_cache_free(kvm_vcpu_cache, vmx);
return ERR_PTR(err);
}
@@ -4109,6 +4282,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
}
}
+static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+{
+}
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
@@ -4145,6 +4322,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.set_idt = vmx_set_idt,
.get_gdt = vmx_get_gdt,
.set_gdt = vmx_set_gdt,
+ .set_dr7 = vmx_set_dr7,
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
@@ -4180,6 +4358,10 @@ static struct kvm_x86_ops vmx_x86_ops = {
.cpuid_update = vmx_cpuid_update,
.rdtscp_supported = vmx_rdtscp_supported,
+
+ .set_supported_cpuid = vmx_set_supported_cpuid,
+
+ .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
};
static int __init vmx_init(void)
@@ -4227,7 +4409,8 @@ static int __init vmx_init(void)
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
- r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
if (r)
goto out3;
OpenPOWER on IntegriCloud