#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"
static int __read_mostly emulate_invalid_guest_state = 0;
module_param(emulate_invalid_guest_state, 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 \
+ (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE)
+#define KVM_VM_CR0_ALWAYS_ON \
+ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_CR4_GUEST_OWNED_BITS \
+ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
+ | X86_CR4_OSXMMEXCPT)
+
+#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
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;
char data[0];
};
+struct shared_msr_entry {
+ unsigned index;
+ u64 data;
+ u64 mask;
+};
+
struct vcpu_vmx {
struct kvm_vcpu vcpu;
struct list_head local_vcpus_link;
int launched;
u8 fail;
u32 idt_vectoring_info;
- struct kvm_msr_entry *guest_msrs;
- struct kvm_msr_entry *host_msrs;
+ struct shared_msr_entry *guest_msrs;
int nmsrs;
int save_nmsrs;
- int msr_offset_efer;
#ifdef CONFIG_X86_64
- int msr_offset_kernel_gs_base;
+ u64 msr_host_kernel_gs_base;
+ 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;
int gs_ldt_reload_needed;
int fs_reload_needed;
- int guest_efer_loaded;
} host_state;
struct {
int vm86_active;
- u8 save_iopl;
+ ulong save_rflags;
struct kvm_save_segment {
u16 selector;
unsigned long base;
ktime_t entry_time;
s64 vnmi_blocked_time;
u32 exit_reason;
+
+ bool rdtscp_enabled;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
VMX_SEGMENT_FIELD(LDTR),
};
+static u64 host_efer;
+
static void ept_save_pdptrs(struct kvm_vcpu *vcpu);
/*
*/
static const u32 vmx_msr_index[] = {
#ifdef CONFIG_X86_64
- MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE,
+ MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
#endif
- MSR_EFER, MSR_K6_STAR,
+ MSR_EFER, MSR_TSC_AUX, MSR_K6_STAR,
};
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
-static void load_msrs(struct kvm_msr_entry *e, int n)
-{
- int i;
-
- for (i = 0; i < n; ++i)
- wrmsrl(e[i].index, e[i].data);
-}
-
-static void save_msrs(struct kvm_msr_entry *e, int n)
-{
- int i;
-
- for (i = 0; i < n; ++i)
- rdmsrl(e[i].index, e[i].data);
-}
-
-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;
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;
}
-static inline int cpu_has_vmx_invept_individual_addr(void)
+static inline bool cpu_has_vmx_invept_individual_addr(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT;
}
-static inline int cpu_has_vmx_invept_context(void)
+static inline bool cpu_has_vmx_invept_context(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
}
-static inline int cpu_has_vmx_invept_global(void)
+static inline bool cpu_has_vmx_invept_global(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}
-static inline int cpu_has_vmx_ept(void)
+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 &&
- (cpu_has_vmx_virtualize_apic_accesses()) &&
- (irqchip_in_kernel(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_virtual_nmis(void)
+static inline bool cpu_has_vmx_rdtscp(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_RDTSCP;
+}
+
+static inline bool cpu_has_virtual_nmis(void)
{
return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
}
int i;
for (i = 0; i < vmx->nmsrs; ++i)
- if (vmx->guest_msrs[i].index == msr)
+ if (vmx_msr_index[vmx->guest_msrs[i].index] == msr)
return i;
return -1;
}
: : "a" (&operand), "c" (ext) : "cc", "memory");
}
-static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
+static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
{
int i;
{
u32 eb;
- eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR);
- if (!vcpu->fpu_active)
- eb |= 1u << NM_VECTOR;
- /*
- * Unconditionally intercept #DB so we can maintain dr6 without
- * reading it every exit.
- */
- eb |= 1u << DB_VECTOR;
- if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
- eb |= 1u << BP_VECTOR;
- }
+ eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
+ (1u << NM_VECTOR) | (1u << DB_VECTOR);
+ if ((vcpu->guest_debug &
+ (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
+ (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP))
+ eb |= 1u << BP_VECTOR;
if (to_vmx(vcpu)->rmode.vm86_active)
eb = ~0;
if (enable_ept)
eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
+ if (vcpu->fpu_active)
+ eb &= ~(1u << NM_VECTOR);
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();
}
-static void load_transition_efer(struct vcpu_vmx *vmx)
+static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
{
- int efer_offset = vmx->msr_offset_efer;
- u64 host_efer;
u64 guest_efer;
u64 ignore_bits;
- if (efer_offset < 0)
- return;
- host_efer = vmx->host_msrs[efer_offset].data;
- guest_efer = vmx->guest_msrs[efer_offset].data;
+ guest_efer = vmx->vcpu.arch.efer;
/*
* NX is emulated; LMA and LME handled by hardware; SCE meaninless
if (guest_efer & EFER_LMA)
ignore_bits &= ~(u64)EFER_SCE;
#endif
- if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits))
- return;
-
- vmx->host_state.guest_efer_loaded = 1;
guest_efer &= ~ignore_bits;
guest_efer |= host_efer & ignore_bits;
- wrmsrl(MSR_EFER, guest_efer);
- vmx->vcpu.stat.efer_reload++;
+ 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 void reload_host_efer(struct vcpu_vmx *vmx)
+static unsigned long segment_base(u16 selector)
{
- if (vmx->host_state.guest_efer_loaded) {
- vmx->host_state.guest_efer_loaded = 0;
- load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1);
+ 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);
+ int i;
if (vmx->host_state.loaded)
return;
#endif
#ifdef CONFIG_X86_64
- if (is_long_mode(&vmx->vcpu))
- save_msrs(vmx->host_msrs +
- vmx->msr_offset_kernel_gs_base, 1);
-
+ if (is_long_mode(&vmx->vcpu)) {
+ rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+ wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ }
#endif
- load_msrs(vmx->guest_msrs, vmx->save_nmsrs);
- load_transition_efer(vmx);
+ for (i = 0; i < vmx->save_nmsrs; ++i)
+ kvm_set_shared_msr(vmx->guest_msrs[i].index,
+ vmx->guest_msrs[i].data,
+ vmx->guest_msrs[i].mask);
}
static void __vmx_load_host_state(struct vcpu_vmx *vmx)
local_irq_restore(flags);
}
reload_tss();
- save_msrs(vmx->guest_msrs, vmx->save_nmsrs);
- load_msrs(vmx->host_msrs, vmx->save_nmsrs);
- reload_host_efer(vmx);
+#ifdef CONFIG_X86_64
+ if (is_long_mode(&vmx->vcpu)) {
+ rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+ }
+#endif
}
static void vmx_load_host_state(struct vcpu_vmx *vmx)
}
if (vcpu->cpu != cpu) {
- struct descriptor_table dt;
+ struct desc_ptr dt;
unsigned long sysenter_esp;
vcpu->cpu = cpu;
* 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 */
static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
{
+ ulong cr0;
+
if (vcpu->fpu_active)
return;
vcpu->fpu_active = 1;
- vmcs_clear_bits(GUEST_CR0, X86_CR0_TS);
- if (vcpu->arch.cr0 & X86_CR0_TS)
- vmcs_set_bits(GUEST_CR0, X86_CR0_TS);
+ cr0 = vmcs_readl(GUEST_CR0);
+ cr0 &= ~(X86_CR0_TS | X86_CR0_MP);
+ cr0 |= kvm_read_cr0_bits(vcpu, X86_CR0_TS | X86_CR0_MP);
+ vmcs_writel(GUEST_CR0, cr0);
update_exception_bitmap(vcpu);
+ vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
}
+static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
+
static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
{
- if (!vcpu->fpu_active)
- return;
- vcpu->fpu_active = 0;
- vmcs_set_bits(GUEST_CR0, X86_CR0_TS);
+ vmx_decache_cr0_guest_bits(vcpu);
+ vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP);
update_exception_bitmap(vcpu);
+ vcpu->arch.cr0_guest_owned_bits = 0;
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
+ vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
}
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);
}
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;
}
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))
}
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;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
}
+static bool vmx_rdtscp_supported(void)
+{
+ return cpu_has_vmx_rdtscp();
+}
+
/*
* Swap MSR entry in host/guest MSR entry array.
*/
-#ifdef CONFIG_X86_64
static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
{
- struct kvm_msr_entry tmp;
+ struct shared_msr_entry tmp;
tmp = vmx->guest_msrs[to];
vmx->guest_msrs[to] = vmx->guest_msrs[from];
vmx->guest_msrs[from] = tmp;
- tmp = vmx->host_msrs[to];
- vmx->host_msrs[to] = vmx->host_msrs[from];
- vmx->host_msrs[from] = tmp;
}
-#endif
/*
* Set up the vmcs to automatically save and restore system
*/
static void setup_msrs(struct vcpu_vmx *vmx)
{
- int save_nmsrs;
+ int save_nmsrs, index;
unsigned long *msr_bitmap;
vmx_load_host_state(vmx);
save_nmsrs = 0;
#ifdef CONFIG_X86_64
if (is_long_mode(&vmx->vcpu)) {
- int index;
-
index = __find_msr_index(vmx, MSR_SYSCALL_MASK);
if (index >= 0)
move_msr_up(vmx, index, save_nmsrs++);
index = __find_msr_index(vmx, MSR_CSTAR);
if (index >= 0)
move_msr_up(vmx, index, save_nmsrs++);
- index = __find_msr_index(vmx, MSR_KERNEL_GS_BASE);
- if (index >= 0)
+ index = __find_msr_index(vmx, MSR_TSC_AUX);
+ if (index >= 0 && vmx->rdtscp_enabled)
move_msr_up(vmx, index, save_nmsrs++);
/*
* MSR_K6_STAR is only needed on long mode guests, and only
* if efer.sce is enabled.
*/
index = __find_msr_index(vmx, MSR_K6_STAR);
- if ((index >= 0) && (vmx->vcpu.arch.shadow_efer & EFER_SCE))
+ if ((index >= 0) && (vmx->vcpu.arch.efer & EFER_SCE))
move_msr_up(vmx, index, save_nmsrs++);
}
#endif
- vmx->save_nmsrs = save_nmsrs;
+ index = __find_msr_index(vmx, MSR_EFER);
+ if (index >= 0 && update_transition_efer(vmx, index))
+ move_msr_up(vmx, index, save_nmsrs++);
-#ifdef CONFIG_X86_64
- vmx->msr_offset_kernel_gs_base =
- __find_msr_index(vmx, MSR_KERNEL_GS_BASE);
-#endif
- vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER);
+ vmx->save_nmsrs = save_nmsrs;
if (cpu_has_vmx_msr_bitmap()) {
if (is_long_mode(&vmx->vcpu))
static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
u64 data;
- struct kvm_msr_entry *msr;
+ struct shared_msr_entry *msr;
if (!pdata) {
printk(KERN_ERR "BUG: get_msr called with NULL pdata\n");
case MSR_GS_BASE:
data = vmcs_readl(GUEST_GS_BASE);
break;
+ case MSR_KERNEL_GS_BASE:
+ vmx_load_host_state(to_vmx(vcpu));
+ data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
+ break;
+#endif
case MSR_EFER:
return kvm_get_msr_common(vcpu, msr_index, pdata);
-#endif
case MSR_IA32_TSC:
data = guest_read_tsc();
break;
case MSR_IA32_SYSENTER_ESP:
data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
+ case MSR_TSC_AUX:
+ if (!to_vmx(vcpu)->rdtscp_enabled)
+ return 1;
+ /* Otherwise falls through */
default:
+ vmx_load_host_state(to_vmx(vcpu));
msr = find_msr_entry(to_vmx(vcpu), msr_index);
if (msr) {
vmx_load_host_state(to_vmx(vcpu));
static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct kvm_msr_entry *msr;
+ struct shared_msr_entry *msr;
u64 host_tsc;
int ret = 0;
case MSR_GS_BASE:
vmcs_writel(GUEST_GS_BASE, data);
break;
+ case MSR_KERNEL_GS_BASE:
+ vmx_load_host_state(vmx);
+ vmx->msr_guest_kernel_gs_base = data;
+ break;
#endif
case MSR_IA32_SYSENTER_CS:
vmcs_write32(GUEST_SYSENTER_CS, data);
vcpu->arch.pat = data;
break;
}
- /* Otherwise falls through to kvm_set_msr_common */
+ ret = kvm_set_msr_common(vcpu, msr_index, data);
+ break;
+ case MSR_TSC_AUX:
+ if (!vmx->rdtscp_enabled)
+ return 1;
+ /* Check reserved bit, higher 32 bits should be zero */
+ if ((data >> 32) != 0)
+ return 1;
+ /* Otherwise falls through */
default:
msr = find_msr_entry(vmx, msr_index);
if (msr) {
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 */
}
{
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)
CPU_BASED_USE_IO_BITMAPS |
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING |
+ CPU_BASED_MWAIT_EXITING |
+ CPU_BASED_MONITOR_EXITING |
CPU_BASED_INVLPG_EXITING;
opt = CPU_BASED_TPR_SHADOW |
CPU_BASED_USE_MSR_BITMAPS |
SECONDARY_EXEC_ENABLE_VPID |
SECONDARY_EXEC_ENABLE_EPT |
SECONDARY_EXEC_UNRESTRICTED_GUEST |
- SECONDARY_EXEC_PAUSE_LOOP_EXITING;
+ SECONDARY_EXEC_PAUSE_LOOP_EXITING |
+ SECONDARY_EXEC_RDTSCP;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
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) |
static gva_t rmode_tss_base(struct kvm *kvm)
{
if (!kvm->arch.tss_addr) {
- gfn_t base_gfn = kvm->memslots[0].base_gfn +
- kvm->memslots[0].npages - 3;
+ struct kvm_memslots *slots;
+ gfn_t base_gfn;
+
+ slots = kvm_memslots(kvm);
+ base_gfn = kvm->memslots->memslots[0].base_gfn +
+ kvm->memslots->memslots[0].npages - 3;
return base_gfn << PAGE_SHIFT;
}
return kvm->arch.tss_addr;
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;
static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
+ struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
- vcpu->arch.shadow_efer = efer;
if (!msr)
return;
+
+ /*
+ * Force kernel_gs_base reloading before EFER changes, as control
+ * of this msr depends on is_long_mode().
+ */
+ vmx_load_host_state(to_vmx(vcpu));
+ vcpu->arch.efer = efer;
if (efer & EFER_LMA) {
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS) |
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
}
- vcpu->arch.shadow_efer |= EFER_LMA;
- vmx_set_efer(vcpu, vcpu->arch.shadow_efer);
+ vcpu->arch.efer |= EFER_LMA;
+ vmx_set_efer(vcpu, vcpu->arch.efer);
}
static void exit_lmode(struct kvm_vcpu *vcpu)
{
- vcpu->arch.shadow_efer &= ~EFER_LMA;
+ 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);
}
#endif
ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa));
}
+static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
+{
+ ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
+
+ vcpu->arch.cr0 &= ~cr0_guest_owned_bits;
+ vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
+}
+
static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
- vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK;
- vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK;
+ ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
+
+ vcpu->arch.cr4 &= ~cr4_guest_owned_bits;
+ vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits;
}
static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
- vmx_set_cr4(vcpu, vcpu->arch.cr4);
+ vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
} else if (!is_paging(vcpu)) {
/* From nonpaging to paging */
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
~(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
- vmx_set_cr4(vcpu, vcpu->arch.cr4);
+ vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
}
if (!(cr0 & X86_CR0_WP))
*hw_cr0 &= ~X86_CR0_WP;
}
-static void ept_update_paging_mode_cr4(unsigned long *hw_cr4,
- struct kvm_vcpu *vcpu)
-{
- if (!is_paging(vcpu)) {
- *hw_cr4 &= ~X86_CR4_PAE;
- *hw_cr4 |= X86_CR4_PSE;
- } else if (!(vcpu->arch.cr4 & X86_CR4_PAE))
- *hw_cr4 &= ~X86_CR4_PAE;
-}
-
static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
else
hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON;
- vmx_fpu_deactivate(vcpu);
-
if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
enter_pmode(vcpu);
enter_rmode(vcpu);
#ifdef CONFIG_X86_64
- if (vcpu->arch.shadow_efer & EFER_LME) {
+ if (vcpu->arch.efer & EFER_LME) {
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG))
enter_lmode(vcpu);
if (is_paging(vcpu) && !(cr0 & X86_CR0_PG))
if (enable_ept)
ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
+ if (!vcpu->fpu_active)
+ hw_cr0 |= X86_CR0_TS | X86_CR0_MP;
+
vmcs_writel(CR0_READ_SHADOW, cr0);
vmcs_writel(GUEST_CR0, hw_cr0);
vcpu->arch.cr0 = cr0;
-
- if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE))
- vmx_fpu_activate(vcpu);
}
static u64 construct_eptp(unsigned long root_hpa)
vmcs_write64(EPT_POINTER, eptp);
guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 :
vcpu->kvm->arch.ept_identity_map_addr;
+ ept_load_pdptrs(vcpu);
}
vmx_flush_tlb(vcpu);
vmcs_writel(GUEST_CR3, guest_cr3);
- if (vcpu->arch.cr0 & X86_CR0_PE)
- vmx_fpu_deactivate(vcpu);
}
static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
vcpu->arch.cr4 = cr4;
- if (enable_ept)
- ept_update_paging_mode_cr4(&hw_cr4, vcpu);
+ if (enable_ept) {
+ if (!is_paging(vcpu)) {
+ hw_cr4 &= ~X86_CR4_PAE;
+ hw_cr4 |= X86_CR4_PSE;
+ } else if (!(cr4 & X86_CR4_PAE)) {
+ hw_cr4 &= ~X86_CR4_PAE;
+ }
+ }
vmcs_writel(CR4_READ_SHADOW, cr4);
vmcs_writel(GUEST_CR4, hw_cr4);
static int vmx_get_cpl(struct kvm_vcpu *vcpu)
{
- if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */
+ if (!is_protmode(vcpu))
return 0;
if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */
*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)
static bool guest_state_valid(struct kvm_vcpu *vcpu)
{
/* real mode guest state checks */
- if (!(vcpu->arch.cr0 & X86_CR0_PE)) {
+ if (!is_protmode(vcpu)) {
if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
return false;
if (!rmode_segment_valid(vcpu, VCPU_SREG_SS))
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
- down_write(&kvm->slots_lock);
+ mutex_lock(&kvm->slots_lock);
if (kvm->arch.apic_access_page)
goto out;
kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
out:
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
return r;
}
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
- down_write(&kvm->slots_lock);
+ mutex_lock(&kvm->slots_lock);
if (kvm->arch.ept_identity_pagetable)
goto out;
kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
out:
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
return r;
}
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);
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;
~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
if (vmx->vpid == 0)
exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
- if (!enable_ept)
+ if (!enable_ept) {
exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
+ enable_unrestricted_guest = 0;
+ }
if (!enable_unrestricted_guest)
exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
if (!ple_gap)
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);
for (i = 0; i < NR_VMX_MSR; ++i) {
u32 index = vmx_msr_index[i];
u32 data_low, data_high;
- u64 data;
int j = vmx->nmsrs;
if (rdmsr_safe(index, &data_low, &data_high) < 0)
continue;
if (wrmsr_safe(index, data_low, data_high) < 0)
continue;
- data = data_low | ((u64)data_high << 32);
- vmx->host_msrs[j].index = index;
- vmx->host_msrs[j].reserved = 0;
- vmx->host_msrs[j].data = data;
- vmx->guest_msrs[j] = vmx->host_msrs[j];
+ vmx->guest_msrs[j].index = i;
+ vmx->guest_msrs[j].data = 0;
+ vmx->guest_msrs[j].mask = -1ull;
++vmx->nmsrs;
}
vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl);
vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
- vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);
+ vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
+ if (enable_ept)
+ vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
+ vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc;
rdtscll(tsc_this);
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 msr;
- int ret;
+ int ret, idx;
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
- down_read(&vcpu->kvm->slots_lock);
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
if (!init_rmode(vmx->vcpu.kvm)) {
ret = -ENOMEM;
goto out;
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */
+ vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
vmx_set_cr4(&vmx->vcpu, 0);
vmx_set_efer(&vmx->vcpu, 0);
vmx_fpu_activate(&vmx->vcpu);
vmx->emulation_required = 0;
out:
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
}
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);
+}
+
+static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (!cpu_has_virtual_nmis()) {
+ if (vmx->soft_vnmi_blocked != masked) {
+ vmx->soft_vnmi_blocked = masked;
+ vmx->vnmi_blocked_time = 0;
+ }
+ } else {
+ if (masked)
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ else
+ vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ }
}
static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
kvm_queue_exception(vcpu, vec);
return 1;
case BP_VECTOR:
+ /*
+ * Update instruction length as we may reinject the exception
+ * from user space while in guest debugging mode.
+ */
+ to_vmx(vcpu)->vcpu.arch.event_exit_inst_len =
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
return 0;
/* fall through */
return handle_machine_check(vcpu);
if ((vect_info & VECTORING_INFO_VALID_MASK) &&
- !is_page_fault(intr_info))
- printk(KERN_ERR "%s: unexpected, vectoring info 0x%x "
- "intr info 0x%x\n", __func__, vect_info, intr_info);
+ !is_page_fault(intr_info)) {
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX;
+ vcpu->run->internal.ndata = 2;
+ vcpu->run->internal.data[0] = vect_info;
+ vcpu->run->internal.data[1] = intr_info;
+ return 0;
+ }
if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
return 1; /* already handled by vmx_vcpu_run() */
kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
/* fall through */
case BP_VECTOR:
+ /*
+ * Update instruction length as we may reinject #BP from
+ * user space while in guest debugging mode. Reading it for
+ * #DB as well causes no harm, it is not used in that case.
+ */
+ vmx->vcpu.arch.event_exit_inst_len =
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
kvm_run->debug.arch.exception = ex_no;
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_DO_MMIO);
+ 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
};
break;
case 2: /* clts */
- vmx_fpu_deactivate(vcpu);
- vcpu->arch.cr0 &= ~X86_CR0_TS;
- vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
- vmx_fpu_activate(vcpu);
+ vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
+ trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
skip_emulated_instruction(vcpu);
+ vmx_fpu_activate(vcpu);
return 1;
case 1: /*mov from cr*/
switch (cr) {
}
break;
case 3: /* lmsw */
- kvm_lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
+ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
+ trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
+ kvm_lmsw(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
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 */
if (!kvm_require_cpl(vcpu, 0))
return 1;
dr = vmcs_readl(GUEST_DR7);
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 6:
- val = vcpu->arch.dr6;
- break;
- case 7:
- val = vcpu->arch.dr7;
- break;
- default:
- val = 0;
- }
- 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 ... 5:
- if (vcpu->arch.cr4 & X86_CR4_DE)
- kvm_queue_exception(vcpu, UD_VECTOR);
- break;
- case 6:
- if (val & 0xffffffff00000000ULL) {
- kvm_queue_exception(vcpu, GP_VECTOR);
- break;
- }
- vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
- break;
- case 7:
- if (val & 0xffffffff00000000ULL) {
- kvm_queue_exception(vcpu, GP_VECTOR);
- break;
- }
- 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);
u64 data;
if (vmx_get_msr(vcpu, ecx, &data)) {
+ trace_kvm_msr_read_ex(ecx);
kvm_inject_gp(vcpu, 0);
return 1;
}
u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
- trace_kvm_msr_write(ecx, data);
-
if (vmx_set_msr(vcpu, ecx, data) != 0) {
+ trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(vcpu, 0);
return 1;
}
+ trace_kvm_msr_write(ecx, data);
skip_emulated_instruction(vcpu);
return 1;
}
{
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;
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;
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);
}
if (err != EMULATE_DONE) {
- kvm_report_emulation_failure(vcpu, "emulation failure");
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;
}
return 1;
}
+static int handle_invalid_op(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
[EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
[EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig,
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
+ [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op,
+ [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op,
};
static const int kvm_vmx_max_exit_handlers =
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)
/* 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;
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (enable_ept && is_paging(vcpu)) {
- vmcs_writel(GUEST_CR3, vcpu->arch.cr3);
- ept_load_pdptrs(vcpu);
- }
/* Record the guest's net vcpu time for enforced NMI injections. */
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
vmx->entry_time = ktime_get();
*/
vmcs_writel(HOST_CR0, read_cr0());
- if (vcpu->arch.switch_db_regs)
- set_debugreg(vcpu->arch.dr6, 6);
-
asm(
/* Store host registers */
"push %%"R"dx; push %%"R"bp;"
| (1 << VCPU_EXREG_PDPTR));
vcpu->arch.regs_dirty = 0;
- if (vcpu->arch.switch_db_regs)
- get_debugreg(vcpu->arch.dr6, 6);
-
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
if (vmx->rmode.irq.pending)
fixup_rmode_irq(vmx);
{
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->host_msrs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
goto uninit_vcpu;
}
- vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (!vmx->host_msrs)
- goto free_guest_msrs;
-
vmx->vmcs = alloc_vmcs();
if (!vmx->vmcs)
goto free_msrs;
free_vmcs:
free_vmcs(vmx->vmcs);
free_msrs:
- kfree(vmx->host_msrs);
-free_guest_msrs:
kfree(vmx->guest_msrs);
uninit_vcpu:
kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
+ free_vpid(vmx);
kmem_cache_free(kvm_vcpu_cache, vmx);
return ERR_PTR(err);
}
* b. VT-d with snooping control feature: snooping control feature of
* VT-d engine can guarantee the cache correctness. Just set it
* to WB to keep consistent with host. So the same as item 3.
- * 3. EPT without VT-d: always map as WB and set IGMT=1 to keep
+ * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
* consistent with host MTRR
*/
if (is_mmio)
VMX_EPT_MT_EPTE_SHIFT;
else
ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT)
- | VMX_EPT_IGMT_BIT;
+ | VMX_EPT_IPAT_BIT;
return ret;
}
+#define _ER(x) { EXIT_REASON_##x, #x }
+
static const struct trace_print_flags vmx_exit_reasons_str[] = {
- { EXIT_REASON_EXCEPTION_NMI, "exception" },
- { EXIT_REASON_EXTERNAL_INTERRUPT, "ext_irq" },
- { EXIT_REASON_TRIPLE_FAULT, "triple_fault" },
- { EXIT_REASON_NMI_WINDOW, "nmi_window" },
- { EXIT_REASON_IO_INSTRUCTION, "io_instruction" },
- { EXIT_REASON_CR_ACCESS, "cr_access" },
- { EXIT_REASON_DR_ACCESS, "dr_access" },
- { EXIT_REASON_CPUID, "cpuid" },
- { EXIT_REASON_MSR_READ, "rdmsr" },
- { EXIT_REASON_MSR_WRITE, "wrmsr" },
- { EXIT_REASON_PENDING_INTERRUPT, "interrupt_window" },
- { EXIT_REASON_HLT, "halt" },
- { EXIT_REASON_INVLPG, "invlpg" },
- { EXIT_REASON_VMCALL, "hypercall" },
- { EXIT_REASON_TPR_BELOW_THRESHOLD, "tpr_below_thres" },
- { EXIT_REASON_APIC_ACCESS, "apic_access" },
- { EXIT_REASON_WBINVD, "wbinvd" },
- { EXIT_REASON_TASK_SWITCH, "task_switch" },
- { EXIT_REASON_EPT_VIOLATION, "ept_violation" },
+ _ER(EXCEPTION_NMI),
+ _ER(EXTERNAL_INTERRUPT),
+ _ER(TRIPLE_FAULT),
+ _ER(PENDING_INTERRUPT),
+ _ER(NMI_WINDOW),
+ _ER(TASK_SWITCH),
+ _ER(CPUID),
+ _ER(HLT),
+ _ER(INVLPG),
+ _ER(RDPMC),
+ _ER(RDTSC),
+ _ER(VMCALL),
+ _ER(VMCLEAR),
+ _ER(VMLAUNCH),
+ _ER(VMPTRLD),
+ _ER(VMPTRST),
+ _ER(VMREAD),
+ _ER(VMRESUME),
+ _ER(VMWRITE),
+ _ER(VMOFF),
+ _ER(VMON),
+ _ER(CR_ACCESS),
+ _ER(DR_ACCESS),
+ _ER(IO_INSTRUCTION),
+ _ER(MSR_READ),
+ _ER(MSR_WRITE),
+ _ER(MWAIT_INSTRUCTION),
+ _ER(MONITOR_INSTRUCTION),
+ _ER(PAUSE_INSTRUCTION),
+ _ER(MCE_DURING_VMENTRY),
+ _ER(TPR_BELOW_THRESHOLD),
+ _ER(APIC_ACCESS),
+ _ER(EPT_VIOLATION),
+ _ER(EPT_MISCONFIG),
+ _ER(WBINVD),
{ -1, NULL }
};
-static bool vmx_gb_page_enable(void)
+#undef _ER
+
+static int vmx_get_lpage_level(void)
+{
+ if (enable_ept && !cpu_has_vmx_ept_1g_page())
+ return PT_DIRECTORY_LEVEL;
+ else
+ /* For shadow and EPT supported 1GB page */
+ return PT_PDPE_LEVEL;
+}
+
+static inline u32 bit(int bitno)
+{
+ return 1 << (bitno & 31);
+}
+
+static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 exec_control;
+
+ vmx->rdtscp_enabled = false;
+ if (vmx_rdtscp_supported()) {
+ exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+ if (exec_control & SECONDARY_EXEC_RDTSCP) {
+ best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+ if (best && (best->edx & bit(X86_FEATURE_RDTSCP)))
+ vmx->rdtscp_enabled = true;
+ else {
+ exec_control &= ~SECONDARY_EXEC_RDTSCP;
+ vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+ exec_control);
+ }
+ }
+ }
+}
+
+static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
{
- return false;
}
static struct kvm_x86_ops vmx_x86_ops = {
.set_segment = vmx_set_segment,
.get_cpl = vmx_get_cpl,
.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
+ .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
.set_cr0 = vmx_set_cr0,
.set_cr3 = vmx_set_cr3,
.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,
+ .fpu_activate = vmx_fpu_activate,
+ .fpu_deactivate = vmx_fpu_deactivate,
.tlb_flush = vmx_flush_tlb,
.queue_exception = vmx_queue_exception,
.interrupt_allowed = vmx_interrupt_allowed,
.nmi_allowed = vmx_nmi_allowed,
+ .get_nmi_mask = vmx_get_nmi_mask,
+ .set_nmi_mask = vmx_set_nmi_mask,
.enable_nmi_window = enable_nmi_window,
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
.get_mt_mask = vmx_get_mt_mask,
.exit_reasons_str = vmx_exit_reasons_str,
- .gb_page_enable = vmx_gb_page_enable,
+ .get_lpage_level = vmx_get_lpage_level,
+
+ .cpuid_update = vmx_cpuid_update,
+
+ .rdtscp_supported = vmx_rdtscp_supported,
+
+ .set_supported_cpuid = vmx_set_supported_cpuid,
};
static int __init vmx_init(void)
{
- int r;
+ int r, i;
+
+ rdmsrl_safe(MSR_EFER, &host_efer);
+
+ for (i = 0; i < NR_VMX_MSR; ++i)
+ kvm_define_shared_msr(i, vmx_msr_index[i]);
vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_io_bitmap_a)
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;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff