#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/moduleparam.h>
+#include <linux/ftrace_event.h>
+#include <linux/slab.h>
#include "kvm_cache_regs.h"
#include "x86.h"
#include <asm/virtext.h>
#include <asm/mce.h>
+#include "trace.h"
+
#define __ex(x) __kvm_handle_fault_on_reboot(x)
MODULE_AUTHOR("Qumranet");
static int __read_mostly enable_ept = 1;
module_param_named(ept, enable_ept, bool, S_IRUGO);
+static int __read_mostly enable_unrestricted_guest = 1;
+module_param_named(unrestricted_guest,
+ enable_unrestricted_guest, bool, S_IRUGO);
+
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)
+
+/*
+ * 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
+ * executions of PAUSE in a loop. Also indicate if ple enabled.
+ * According to test, this time is usually small than 41 cycles.
+ * ple_window: upper bound on the amount of time a guest is allowed to execute
+ * in a PAUSE loop. Tests indicate that most spinlocks are held for
+ * less than 2^12 cycles
+ * Time is measured based on a counter that runs at the same rate as the TSC,
+ * refer SDM volume 3b section 21.6.13 & 22.1.3.
+ */
+#define KVM_VMX_DEFAULT_PLE_GAP 41
+#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
+static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
+module_param(ple_gap, int, S_IRUGO);
+
+static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
+module_param(ple_window, int, S_IRUGO);
+
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 {
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;
+ struct kvm_save_segment {
+ u16 selector;
+ unsigned long base;
+ u32 limit;
+ u32 ar;
+ } tr, es, ds, fs, gs;
struct {
bool pending;
u8 vector;
} rmode;
int vpid;
bool emulation_required;
- enum emulation_result invalid_state_emulation_result;
/* Support for vnmi-less CPUs */
int soft_vnmi_blocked;
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);
+
/*
* Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it
* away by decrementing the array size.
*/
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)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
cpu_has_vmx_virtualize_apic_accesses();
}
+static inline bool cpu_has_vmx_ept_execute_only(void)
+{
+ 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);
+}
+
+static inline bool cpu_has_vmx_eptp_writeback(void)
+{
+ 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);
+}
+
+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)
{
return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
SECONDARY_EXEC_ENABLE_EPT;
}
+static inline int 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)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_PAUSE_LOOP_EXITING;
+}
+
static inline int 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)
SECONDARY_EXEC_ENABLE_VPID;
}
+static inline int cpu_has_vmx_rdtscp(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_RDTSCP;
+}
+
static inline int 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;
- if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
- if (vcpu->guest_debug &
- (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
- eb |= 1u << DB_VECTOR;
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
- eb |= 1u << BP_VECTOR;
- }
- if (vcpu->arch.rmode.vm86_active)
+ 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);
}
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 = vmx->host_msrs[efer_offset].data;
- u64 guest_efer = vmx->guest_msrs[efer_offset].data;
+ u64 guest_efer;
u64 ignore_bits;
- if (efer_offset < 0)
- return;
+ guest_efer = vmx->vcpu.arch.efer;
+
/*
* NX is emulated; LMA and LME handled by hardware; SCE meaninless
* outside long mode
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++;
-}
-
-static void reload_host_efer(struct vcpu_vmx *vmx)
-{
- if (vmx->host_state.guest_efer_loaded) {
- vmx->host_state.guest_efer_loaded = 0;
- load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1);
- }
+ vmx->guest_msrs[efer_offset].data = guest_efer;
+ vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+ return true;
}
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) {
vcpu_clear(vmx);
kvm_migrate_timers(vcpu);
- vpid_sync_vcpu_all(vmx);
+ set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
local_irq_disable();
list_add(&vmx->local_vcpus_link,
&per_cpu(vcpus_on_cpu, cpu));
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)
{
- return vmcs_readl(GUEST_RFLAGS);
+ unsigned long rflags;
+
+ rflags = vmcs_readl(GUEST_RFLAGS);
+ if (to_vmx(vcpu)->rmode.vm86_active)
+ rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
+ return rflags;
}
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
- if (vcpu->arch.rmode.vm86_active)
+ if (to_vmx(vcpu)->rmode.vm86_active)
rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
vmcs_writel(GUEST_RFLAGS, rflags);
}
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
}
- if (vcpu->arch.rmode.vm86_active) {
+ if (vmx->rmode.vm86_active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = nr;
vmx->rmode.irq.rip = kvm_rip_read(vcpu);
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));
data = msr->data;
break;
}
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);
rdtscll(host_tsc);
guest_write_tsc(data, host_tsc);
break;
- case MSR_P6_PERFCTR0:
- case MSR_P6_PERFCTR1:
- case MSR_P6_EVNTSEL0:
- case MSR_P6_EVNTSEL1:
- /*
- * Just discard all writes to the performance counters; this
- * should keep both older linux and windows 64-bit guests
- * happy
- */
- pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data);
-
- break;
case MSR_IA32_CR_PAT:
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
vmcs_write64(GUEST_IA32_PAT, 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:
- vmx_load_host_state(vmx);
msr = find_msr_entry(vmx, msr_index);
if (msr) {
+ vmx_load_host_state(vmx);
msr->data = data;
break;
}
case VCPU_REGS_RIP:
vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP);
break;
+ case VCPU_EXREG_PDPTR:
+ if (enable_ept)
+ ept_save_pdptrs(vcpu);
+ break;
default:
break;
}
}
-static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
+static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
{
- int old_debug = vcpu->guest_debug;
- unsigned long flags;
-
- 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)
vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]);
else
vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
- flags = vmcs_readl(GUEST_RFLAGS);
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
- flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
- else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
- flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
- vmcs_writel(GUEST_RFLAGS, flags);
-
update_exception_bitmap(vcpu);
-
- return 0;
}
static __init int cpu_has_kvm_support(void)
/* locked but not enabled */
}
-static void hardware_enable(void *garbage)
+static int hardware_enable(void *garbage)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
u64 old;
+ 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 |
asm volatile (ASM_VMX_VMXON_RAX
: : "a"(&phys_addr), "m"(phys_addr)
: "memory", "cc");
+
+ ept_sync_global();
+
+ return 0;
}
static void vmclear_local_vcpus(void)
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 |
opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_WBINVD_EXITING |
SECONDARY_EXEC_ENABLE_VPID |
- SECONDARY_EXEC_ENABLE_EPT;
+ SECONDARY_EXEC_ENABLE_EPT |
+ SECONDARY_EXEC_UNRESTRICTED_GUEST |
+ 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)
if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
/* CR3 accesses and invlpg don't need to cause VM Exits when EPT
enabled */
- min &= ~(CPU_BASED_CR3_LOAD_EXITING |
- CPU_BASED_CR3_STORE_EXITING |
- CPU_BASED_INVLPG_EXITING);
- if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
- &_cpu_based_exec_control) < 0)
- return -EIO;
+ _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
+ CPU_BASED_CR3_STORE_EXITING |
+ CPU_BASED_INVLPG_EXITING);
rdmsr(MSR_IA32_VMX_EPT_VPID_CAP,
vmx_capability.ept, vmx_capability.vpid);
}
{
int cpu;
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu) {
free_vmcs(per_cpu(vmxarea, cpu));
+ per_cpu(vmxarea, cpu) = NULL;
+ }
}
static __init int alloc_kvm_area(void)
{
int cpu;
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
struct vmcs *vmcs;
vmcs = alloc_vmcs_cpu(cpu);
if (!cpu_has_vmx_vpid())
enable_vpid = 0;
- if (!cpu_has_vmx_ept())
+ if (!cpu_has_vmx_ept()) {
enable_ept = 0;
+ enable_unrestricted_guest = 0;
+ }
+
+ if (!cpu_has_vmx_unrestricted_guest())
+ enable_unrestricted_guest = 0;
if (!cpu_has_vmx_flexpriority())
flexpriority_enabled = 0;
if (!cpu_has_vmx_tpr_shadow())
kvm_x86_ops->update_cr8_intercept = NULL;
+ if (enable_ept && !cpu_has_vmx_ept_2m_page())
+ kvm_disable_largepages();
+
+ if (!cpu_has_vmx_ple())
+ ple_gap = 0;
+
return alloc_kvm_area();
}
struct vcpu_vmx *vmx = to_vmx(vcpu);
vmx->emulation_required = 1;
- vcpu->arch.rmode.vm86_active = 0;
+ vmx->rmode.vm86_active = 0;
- vmcs_writel(GUEST_TR_BASE, vcpu->arch.rmode.tr.base);
- vmcs_write32(GUEST_TR_LIMIT, vcpu->arch.rmode.tr.limit);
- vmcs_write32(GUEST_TR_AR_BYTES, vcpu->arch.rmode.tr.ar);
+ vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base);
+ vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit);
+ vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
flags = vmcs_readl(GUEST_RFLAGS);
flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
- flags |= (vcpu->arch.rmode.save_iopl << IOPL_SHIFT);
+ flags |= (vmx->rmode.save_iopl << IOPL_SHIFT);
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
if (emulate_invalid_guest_state)
return;
- fix_pmode_dataseg(VCPU_SREG_ES, &vcpu->arch.rmode.es);
- fix_pmode_dataseg(VCPU_SREG_DS, &vcpu->arch.rmode.ds);
- fix_pmode_dataseg(VCPU_SREG_GS, &vcpu->arch.rmode.gs);
- fix_pmode_dataseg(VCPU_SREG_FS, &vcpu->arch.rmode.fs);
+ fix_pmode_dataseg(VCPU_SREG_ES, &vmx->rmode.es);
+ fix_pmode_dataseg(VCPU_SREG_DS, &vmx->rmode.ds);
+ fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs);
+ fix_pmode_dataseg(VCPU_SREG_FS, &vmx->rmode.fs);
vmcs_write16(GUEST_SS_SELECTOR, 0);
vmcs_write32(GUEST_SS_AR_BYTES, 0x93);
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 = rcu_dereference(kvm->memslots);
+ base_gfn = kvm->memslots->memslots[0].base_gfn +
+ kvm->memslots->memslots[0].npages - 3;
return base_gfn << PAGE_SHIFT;
}
return kvm->arch.tss_addr;
unsigned long flags;
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (enable_unrestricted_guest)
+ return;
+
vmx->emulation_required = 1;
- vcpu->arch.rmode.vm86_active = 1;
+ vmx->rmode.vm86_active = 1;
- vcpu->arch.rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
+ vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
- vcpu->arch.rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT);
+ vmx->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT);
vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
- vcpu->arch.rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES);
+ vmx->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES);
vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
flags = vmcs_readl(GUEST_RFLAGS);
- vcpu->arch.rmode.save_iopl
+ vmx->rmode.save_iopl
= (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
vmcs_writel(GUEST_CS_BASE, 0xf0000);
vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4);
- fix_rmode_seg(VCPU_SREG_ES, &vcpu->arch.rmode.es);
- fix_rmode_seg(VCPU_SREG_DS, &vcpu->arch.rmode.ds);
- fix_rmode_seg(VCPU_SREG_GS, &vcpu->arch.rmode.gs);
- fix_rmode_seg(VCPU_SREG_FS, &vcpu->arch.rmode.fs);
+ fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es);
+ fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds);
+ fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs);
+ fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs);
continue_rmode:
kvm_mmu_reset_context(vcpu);
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)
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)
{
+ if (!test_bit(VCPU_EXREG_PDPTR,
+ (unsigned long *)&vcpu->arch.regs_dirty))
+ return;
+
if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
- if (!load_pdptrs(vcpu, vcpu->arch.cr3)) {
- printk(KERN_ERR "EPT: Fail to load pdptrs!\n");
- return;
- }
vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]);
vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]);
vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]);
}
}
+static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
+{
+ if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
+ vcpu->arch.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+ vcpu->arch.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+ vcpu->arch.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+ vcpu->arch.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+ }
+
+ __set_bit(VCPU_EXREG_PDPTR,
+ (unsigned long *)&vcpu->arch.regs_avail);
+ __set_bit(VCPU_EXREG_PDPTR,
+ (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
- vmx_set_cr4(vcpu, vcpu->arch.cr4);
- *hw_cr0 |= X86_CR0_PE | X86_CR0_PG;
- *hw_cr0 &= ~X86_CR0_WP;
+ 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);
- if (!(vcpu->arch.cr0 & X86_CR0_WP))
- *hw_cr0 &= ~X86_CR0_WP;
+ vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
}
-}
-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;
+ if (!(cr0 & X86_CR0_WP))
+ *hw_cr0 &= ~X86_CR0_WP;
}
static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
- unsigned long hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) |
- KVM_VM_CR0_ALWAYS_ON;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long hw_cr0;
- vmx_fpu_deactivate(vcpu);
+ if (enable_unrestricted_guest)
+ hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST)
+ | KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
+ else
+ hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON;
- if (vcpu->arch.rmode.vm86_active && (cr0 & X86_CR0_PE))
+ if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
enter_pmode(vcpu);
- if (!vcpu->arch.rmode.vm86_active && !(cr0 & X86_CR0_PE))
+ if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE))
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)
if (enable_ept) {
eptp = construct_eptp(cr3);
vmcs_write64(EPT_POINTER, eptp);
- ept_sync_context(eptp);
- ept_load_pdptrs(vcpu);
guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 :
- VMX_EPT_IDENTITY_PAGETABLE_ADDR;
+ 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)
{
- unsigned long hw_cr4 = cr4 | (vcpu->arch.rmode.vm86_active ?
+ unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ?
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)
{
- struct kvm_segment kvm_seg;
-
- 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 */
return 3;
- vmx_get_segment(vcpu, &kvm_seg, VCPU_SREG_CS);
- return kvm_seg.selector & 3;
+ return vmcs_read16(GUEST_CS_SELECTOR) & 3;
}
static u32 vmx_segment_access_rights(struct kvm_segment *var)
static void vmx_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
u32 ar;
- if (vcpu->arch.rmode.vm86_active && seg == VCPU_SREG_TR) {
- vcpu->arch.rmode.tr.selector = var->selector;
- vcpu->arch.rmode.tr.base = var->base;
- vcpu->arch.rmode.tr.limit = var->limit;
- vcpu->arch.rmode.tr.ar = vmx_segment_access_rights(var);
+ if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) {
+ vmx->rmode.tr.selector = var->selector;
+ vmx->rmode.tr.base = var->base;
+ vmx->rmode.tr.limit = var->limit;
+ vmx->rmode.tr.ar = vmx_segment_access_rights(var);
return;
}
vmcs_writel(sf->base, var->base);
vmcs_write32(sf->limit, var->limit);
vmcs_write16(sf->selector, var->selector);
- if (vcpu->arch.rmode.vm86_active && var->s) {
+ if (vmx->rmode.vm86_active && var->s) {
/*
* Hack real-mode segments into vm86 compatibility.
*/
ar = 0xf3;
} else
ar = vmx_segment_access_rights(var);
+
+ /*
+ * Fix the "Accessed" bit in AR field of segment registers for older
+ * qemu binaries.
+ * IA32 arch specifies that at the time of processor reset the
+ * "Accessed" bit in the AR field of segment registers is 1. And qemu
+ * is setting it to 0 in the usedland code. This causes invalid guest
+ * state vmexit when "unrestricted guest" mode is turned on.
+ * Fix for this setup issue in cpu_reset is being pushed in the qemu
+ * tree. Newer qemu binaries with that qemu fix would not need this
+ * kvm hack.
+ */
+ if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
+ ar |= 0x1; /* Accessed */
+
vmcs_write32(sf->ar_bytes, ar);
}
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))
if (likely(kvm->arch.ept_identity_pagetable_done))
return 1;
ret = 0;
- identity_map_pfn = VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT;
+ identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT;
r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
if (r < 0)
goto out;
static void seg_setup(int seg)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+ unsigned int ar;
vmcs_write16(sf->selector, 0);
vmcs_writel(sf->base, 0);
vmcs_write32(sf->limit, 0xffff);
- vmcs_write32(sf->ar_bytes, 0xf3);
+ if (enable_unrestricted_guest) {
+ ar = 0x93;
+ if (seg == VCPU_SREG_CS)
+ ar |= 0x08; /* code segment */
+ } else
+ ar = 0xf3;
+
+ vmcs_write32(sf->ar_bytes, ar);
}
static int alloc_apic_access_page(struct kvm *kvm)
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_userspace_mem.flags = 0;
- kvm_userspace_mem.guest_phys_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
+ kvm_userspace_mem.guest_phys_addr =
+ kvm->arch.ept_identity_map_addr;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0);
if (r)
goto out;
kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
- VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT);
+ kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
out:
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
return r;
}
~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)
+ exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
+ if (ple_gap) {
+ vmcs_write32(PLE_GAP, ple_gap);
+ vmcs_write32(PLE_WINDOW, ple_window);
+ }
+
vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf);
vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */
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;
}
- vmx->vcpu.arch.rmode.vm86_active = 0;
+ vmx->rmode.vm86_active = 0;
vmx->soft_vnmi_blocked = 0;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(&vmx->vcpu, 0);
msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
- if (vmx->vcpu.vcpu_id == 0)
+ if (kvm_vcpu_is_bsp(&vmx->vcpu))
msr |= MSR_IA32_APICBASE_BSP;
kvm_set_apic_base(&vmx->vcpu, msr);
* GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
* insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh.
*/
- if (vmx->vcpu.vcpu_id == 0) {
+ if (kvm_vcpu_is_bsp(&vmx->vcpu)) {
vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
vmcs_writel(GUEST_CS_BASE, 0x000f0000);
} else {
vmcs_writel(GUEST_SYSENTER_EIP, 0);
vmcs_writel(GUEST_RFLAGS, 0x02);
- if (vmx->vcpu.vcpu_id == 0)
+ if (kvm_vcpu_is_bsp(&vmx->vcpu))
kvm_rip_write(vcpu, 0xfff0);
else
kvm_rip_write(vcpu, 0);
if (vmx->vpid != 0)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
- vmx->vcpu.arch.cr0 = 0x60000010;
- vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */
+ vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+ 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;
}
uint32_t intr;
int irq = vcpu->arch.interrupt.nr;
- KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler);
+ trace_kvm_inj_virq(irq);
++vcpu->stat.irq_injections;
- if (vcpu->arch.rmode.vm86_active) {
+ if (vmx->rmode.vm86_active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = irq;
vmx->rmode.irq.rip = kvm_rip_read(vcpu);
}
++vcpu->stat.nmi_injections;
- if (vcpu->arch.rmode.vm86_active) {
+ if (vmx->rmode.vm86_active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = NMI_VECTOR;
vmx->rmode.irq.rip = kvm_rip_read(vcpu);
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)
{
return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
* Cause the #SS fault with 0 error code in VM86 mode.
*/
if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0)
- if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE)
+ if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE)
return 1;
/*
* Forward all other exceptions that are valid in real mode.
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 */
#endif
}
-static int handle_machine_check(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_machine_check(struct kvm_vcpu *vcpu)
{
/* already handled by vcpu_run */
return 1;
}
-static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct kvm_run *kvm_run = vcpu->run;
u32 intr_info, ex_no, error_code;
unsigned long cr2, rip, dr6;
u32 vect_info;
intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
if (is_machine_check(intr_info))
- return handle_machine_check(vcpu, kvm_run);
+ 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() */
}
if (is_invalid_opcode(intr_info)) {
- er = emulate_instruction(vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD);
+ er = emulate_instruction(vcpu, 0, 0, EMULTYPE_TRAP_UD);
if (er != EMULATE_DONE)
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
if (enable_ept)
BUG();
cr2 = vmcs_readl(EXIT_QUALIFICATION);
- KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2,
- (u32)((u64)cr2 >> 32), handler);
+ trace_kvm_page_fault(cr2, error_code);
+
if (kvm_event_needs_reinjection(vcpu))
kvm_mmu_unprotect_page_virt(vcpu, cr2);
return kvm_mmu_page_fault(vcpu, cr2, error_code);
}
- if (vcpu->arch.rmode.vm86_active &&
+ if (vmx->rmode.vm86_active &&
handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK,
error_code)) {
if (vcpu->arch.halt_request) {
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;
return 0;
}
-static int handle_external_interrupt(struct kvm_vcpu *vcpu,
- struct kvm_run *kvm_run)
+static int handle_external_interrupt(struct kvm_vcpu *vcpu)
{
++vcpu->stat.irq_exits;
- KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler);
return 1;
}
-static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_triple_fault(struct kvm_vcpu *vcpu)
{
- kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+ vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
return 0;
}
-static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_io(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
int size, in, string;
string = (exit_qualification & 16) != 0;
if (string) {
- if (emulate_instruction(vcpu,
- kvm_run, 0, 0, 0) == EMULATE_DO_MMIO)
+ if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO)
return 0;
return 1;
}
port = exit_qualification >> 16;
skip_emulated_instruction(vcpu);
- return kvm_emulate_pio(vcpu, kvm_run, in, size, port);
+ return kvm_emulate_pio(vcpu, in, size, port);
}
static void
hypercall[2] = 0xc1;
}
-static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_cr(struct kvm_vcpu *vcpu)
{
- unsigned long exit_qualification;
+ unsigned long exit_qualification, val;
int cr;
int reg;
reg = (exit_qualification >> 8) & 15;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
- KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr,
- (u32)kvm_register_read(vcpu, reg),
- (u32)((u64)kvm_register_read(vcpu, reg) >> 32),
- handler);
+ val = kvm_register_read(vcpu, reg);
+ trace_kvm_cr_write(cr, val);
switch (cr) {
case 0:
- kvm_set_cr0(vcpu, kvm_register_read(vcpu, reg));
+ kvm_set_cr0(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
case 3:
- kvm_set_cr3(vcpu, kvm_register_read(vcpu, reg));
+ kvm_set_cr3(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
case 4:
- kvm_set_cr4(vcpu, kvm_register_read(vcpu, reg));
+ kvm_set_cr4(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
case 8: {
return 1;
if (cr8_prev <= cr8)
return 1;
- kvm_run->exit_reason = KVM_EXIT_SET_TPR;
+ vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
return 0;
}
};
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);
- KVMTRACE_0D(CLTS, vcpu, handler);
+ 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) {
case 3:
kvm_register_write(vcpu, reg, vcpu->arch.cr3);
- KVMTRACE_3D(CR_READ, vcpu, (u32)cr,
- (u32)kvm_register_read(vcpu, reg),
- (u32)((u64)kvm_register_read(vcpu, reg) >> 32),
- handler);
+ trace_kvm_cr_read(cr, vcpu->arch.cr3);
skip_emulated_instruction(vcpu);
return 1;
case 8:
- kvm_register_write(vcpu, reg, kvm_get_cr8(vcpu));
- KVMTRACE_2D(CR_READ, vcpu, (u32)cr,
- (u32)kvm_register_read(vcpu, reg), handler);
+ val = kvm_get_cr8(vcpu);
+ kvm_register_write(vcpu, reg, val);
+ trace_kvm_cr_read(cr, val);
skip_emulated_instruction(vcpu);
return 1;
}
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;
default:
break;
}
- kvm_run->exit_reason = 0;
+ vcpu->run->exit_reason = 0;
pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n",
(int)(exit_qualification >> 4) & 3, cr);
return 0;
}
-static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+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 */
+ if (!kvm_require_cpl(vcpu, 0))
+ return 1;
dr = vmcs_readl(GUEST_DR7);
if (dr & DR7_GD) {
/*
* guest debugging itself.
*/
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
- kvm_run->debug.arch.dr6 = vcpu->arch.dr6;
- kvm_run->debug.arch.dr7 = dr;
- kvm_run->debug.arch.pc =
+ vcpu->run->debug.arch.dr6 = vcpu->arch.dr6;
+ vcpu->run->debug.arch.dr7 = dr;
+ vcpu->run->debug.arch.pc =
vmcs_readl(GUEST_CS_BASE) +
vmcs_readl(GUEST_RIP);
- kvm_run->debug.arch.exception = DB_VECTOR;
- kvm_run->exit_reason = KVM_EXIT_DEBUG;
+ vcpu->run->debug.arch.exception = DB_VECTOR;
+ vcpu->run->exit_reason = KVM_EXIT_DEBUG;
return 0;
} else {
vcpu->arch.dr7 &= ~DR7_GD;
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 7:
+ case 5:
+ if (check_dr_alias(vcpu) < 0)
+ return 1;
+ /* fall through */
+ default: /* 7 */
val = vcpu->arch.dr7;
break;
- default:
- val = 0;
}
kvm_register_write(vcpu, reg, val);
- KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
} else {
val = vcpu->arch.regs[reg];
switch (dr) {
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 4:
+ if (check_dr_alias(vcpu) < 0)
+ return 1;
+ /* fall through */
case 6:
if (val & 0xffffffff00000000ULL) {
- kvm_queue_exception(vcpu, GP_VECTOR);
- break;
+ kvm_inject_gp(vcpu, 0);
+ return 1;
}
vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
break;
- case 7:
+ case 5:
+ if (check_dr_alias(vcpu) < 0)
+ return 1;
+ /* fall through */
+ default: /* 7 */
if (val & 0xffffffff00000000ULL) {
- kvm_queue_exception(vcpu, GP_VECTOR);
- break;
+ 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)) {
}
break;
}
- KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler);
}
skip_emulated_instruction(vcpu);
return 1;
}
-static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_cpuid(struct kvm_vcpu *vcpu)
{
kvm_emulate_cpuid(vcpu);
return 1;
}
-static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_rdmsr(struct kvm_vcpu *vcpu)
{
u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
u64 data;
if (vmx_get_msr(vcpu, ecx, &data)) {
+ trace_kvm_msr_read_ex(ecx);
kvm_inject_gp(vcpu, 0);
return 1;
}
- KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32),
- handler);
+ trace_kvm_msr_read(ecx, data);
/* FIXME: handling of bits 32:63 of rax, rdx */
vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u;
return 1;
}
-static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_wrmsr(struct kvm_vcpu *vcpu)
{
u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
- KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32),
- handler);
-
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;
}
-static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu,
- struct kvm_run *kvm_run)
+static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
{
return 1;
}
-static int handle_interrupt_window(struct kvm_vcpu *vcpu,
- struct kvm_run *kvm_run)
+static int handle_interrupt_window(struct kvm_vcpu *vcpu)
{
u32 cpu_based_vm_exec_control;
cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
- KVMTRACE_0D(PEND_INTR, vcpu, handler);
++vcpu->stat.irq_window_exits;
/*
* possible
*/
if (!irqchip_in_kernel(vcpu->kvm) &&
- kvm_run->request_interrupt_window &&
+ vcpu->run->request_interrupt_window &&
!kvm_cpu_has_interrupt(vcpu)) {
- kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
+ vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
return 0;
}
return 1;
}
-static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_halt(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
return kvm_emulate_halt(vcpu);
}
-static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_vmcall(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
kvm_emulate_hypercall(vcpu);
return 1;
}
-static int handle_vmx_insn(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_vmx_insn(struct kvm_vcpu *vcpu)
{
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
-static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_invlpg(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
return 1;
}
-static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_wbinvd(struct kvm_vcpu *vcpu)
{
skip_emulated_instruction(vcpu);
/* TODO: Add support for VT-d/pass-through device */
return 1;
}
-static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_apic_access(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
enum emulation_result er;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
offset = exit_qualification & 0xffful;
- er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
+ 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 -ENOTSUPP;
+ return -ENOEXEC;
}
return 1;
}
-static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_task_switch(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qualification;
return 1;
}
-static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int handle_ept_violation(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
gpa_t gpa;
if (exit_qualification & (1 << 6)) {
printk(KERN_ERR "EPT: GPA exceeds GAW!\n");
- return -ENOTSUPP;
+ return -EINVAL;
}
gla_validity = (exit_qualification >> 7) & 0x3;
vmcs_readl(GUEST_LINEAR_ADDRESS));
printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
(long unsigned int)exit_qualification);
- kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
- kvm_run->hw.hardware_exit_reason = 0;
- return -ENOTSUPP;
+ vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
+ vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION;
+ return 0;
}
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+ trace_kvm_page_fault(gpa, exit_qualification);
return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
}
-static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static u64 ept_rsvd_mask(u64 spte, int level)
+{
+ int i;
+ u64 mask = 0;
+
+ for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
+ mask |= (1ULL << i);
+
+ if (level > 2)
+ /* bits 7:3 reserved */
+ mask |= 0xf8;
+ else if (level == 2) {
+ if (spte & (1ULL << 7))
+ /* 2MB ref, bits 20:12 reserved */
+ mask |= 0x1ff000;
+ else
+ /* bits 6:3 reserved */
+ mask |= 0x78;
+ }
+
+ return mask;
+}
+
+static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
+ int level)
+{
+ printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level);
+
+ /* 010b (write-only) */
+ WARN_ON((spte & 0x7) == 0x2);
+
+ /* 110b (write/execute) */
+ WARN_ON((spte & 0x7) == 0x6);
+
+ /* 100b (execute-only) and value not supported by logical processor */
+ if (!cpu_has_vmx_ept_execute_only())
+ WARN_ON((spte & 0x7) == 0x4);
+
+ /* not 000b */
+ if ((spte & 0x7)) {
+ u64 rsvd_bits = spte & ept_rsvd_mask(spte, level);
+
+ if (rsvd_bits != 0) {
+ printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n",
+ __func__, rsvd_bits);
+ WARN_ON(1);
+ }
+
+ if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) {
+ u64 ept_mem_type = (spte & 0x38) >> 3;
+
+ if (ept_mem_type == 2 || ept_mem_type == 3 ||
+ ept_mem_type == 7) {
+ printk(KERN_ERR "%s: ept_mem_type=0x%llx\n",
+ __func__, ept_mem_type);
+ WARN_ON(1);
+ }
+ }
+ }
+}
+
+static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
+{
+ u64 sptes[4];
+ int nr_sptes, i;
+ gpa_t gpa;
+
+ gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+
+ printk(KERN_ERR "EPT: Misconfiguration.\n");
+ printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
+
+ nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes);
+
+ for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i)
+ ept_misconfig_inspect_spte(vcpu, sptes[i-1], i);
+
+ vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
+ vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+
+ return 0;
+}
+
+static int handle_nmi_window(struct kvm_vcpu *vcpu)
{
u32 cpu_based_vm_exec_control;
return 1;
}
-static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
- struct kvm_run *kvm_run)
+static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
enum emulation_result err = EMULATE_DONE;
-
- local_irq_enable();
- preempt_enable();
+ int ret = 1;
while (!guest_state_valid(vcpu)) {
- err = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
+ err = emulate_instruction(vcpu, 0, 0, 0);
- if (err == EMULATE_DO_MMIO)
- break;
+ if (err == EMULATE_DO_MMIO) {
+ ret = 0;
+ goto out;
+ }
if (err != EMULATE_DONE) {
- kvm_report_emulation_failure(vcpu, "emulation failure");
- break;
+ 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 (signal_pending(current))
- break;
+ goto out;
if (need_resched())
schedule();
}
- preempt_disable();
- local_irq_disable();
+ vmx->emulation_required = 0;
+out:
+ return ret;
+}
+
+/*
+ * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
+ * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
+ */
+static int handle_pause(struct kvm_vcpu *vcpu)
+{
+ skip_emulated_instruction(vcpu);
+ kvm_vcpu_on_spin(vcpu);
+
+ return 1;
+}
- vmx->invalid_state_emulation_result = err;
+static int handle_invalid_op(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
}
/*
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
* to be done to userspace and return 0.
*/
-static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
- struct kvm_run *kvm_run) = {
+static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_EXCEPTION_NMI] = handle_exception,
[EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt,
[EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault,
[EXIT_REASON_APIC_ACCESS] = handle_apic_access,
[EXIT_REASON_WBINVD] = handle_wbinvd,
[EXIT_REASON_TASK_SWITCH] = handle_task_switch,
- [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
[EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check,
+ [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 =
* The guest has exited. See if we can fix it or if we need userspace
* assistance.
*/
-static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int vmx_handle_exit(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exit_reason = vmx->exit_reason;
u32 vectoring_info = vmx->idt_vectoring_info;
- KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)kvm_rip_read(vcpu),
- (u32)((u64)kvm_rip_read(vcpu) >> 32), entryexit);
+ trace_kvm_exit(exit_reason, kvm_rip_read(vcpu));
- /* If we need to emulate an MMIO from handle_invalid_guest_state
- * we just return 0 */
- if (vmx->emulation_required && emulate_invalid_guest_state) {
- if (guest_state_valid(vcpu))
- vmx->emulation_required = 0;
- return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO;
- }
+ /* If guest state is invalid, start emulating */
+ if (vmx->emulation_required && emulate_invalid_guest_state)
+ return handle_invalid_guest_state(vcpu);
/* Access CR3 don't cause VMExit in paging mode, so we need
* to sync with guest real CR3. */
- if (enable_ept && is_paging(vcpu)) {
+ if (enable_ept && is_paging(vcpu))
vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- ept_load_pdptrs(vcpu);
- }
if (unlikely(vmx->fail)) {
- kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
- kvm_run->fail_entry.hardware_entry_failure_reason
+ vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ vcpu->run->fail_entry.hardware_entry_failure_reason
= vmcs_read32(VM_INSTRUCTION_ERROR);
return 0;
}
if (exit_reason < kvm_vmx_max_exit_handlers
&& kvm_vmx_exit_handlers[exit_reason])
- return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run);
+ return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
- kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
- kvm_run->hw.hardware_exit_reason = exit_reason;
+ vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
+ vcpu->run->hw.hardware_exit_reason = exit_reason;
}
return 0;
}
/* 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)) {
- KVMTRACE_0D(NMI, &vmx->vcpu, handler);
+ (exit_intr_info & INTR_INFO_VALID_MASK))
asm("int $2");
- }
idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
#define Q "l"
#endif
-static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
vmx->entry_time = ktime_get();
- /* Handle invalid guest state instead of entering VMX */
- if (vmx->emulation_required && emulate_invalid_guest_state) {
- handle_invalid_guest_state(vcpu, kvm_run);
+ /* Don't enter VMX if guest state is invalid, let the exit handler
+ start emulation until we arrive back to a valid state */
+ if (vmx->emulation_required && emulate_invalid_guest_state)
return;
- }
if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
*/
vmcs_writel(HOST_CR0, read_cr0());
- set_debugreg(vcpu->arch.dr6, 6);
-
asm(
/* Store host registers */
"push %%"R"dx; push %%"R"bp;"
"mov %%"R"sp, %c[host_rsp](%0) \n\t"
__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
"1: \n\t"
+ /* Reload cr2 if changed */
+ "mov %c[cr2](%0), %%"R"ax \n\t"
+ "mov %%cr2, %%"R"dx \n\t"
+ "cmp %%"R"ax, %%"R"dx \n\t"
+ "je 2f \n\t"
+ "mov %%"R"ax, %%cr2 \n\t"
+ "2: \n\t"
/* Check if vmlaunch of vmresume is needed */
"cmpl $0, %c[launched](%0) \n\t"
/* Load guest registers. Don't clobber flags. */
- "mov %c[cr2](%0), %%"R"ax \n\t"
- "mov %%"R"ax, %%cr2 \n\t"
"mov %c[rax](%0), %%"R"ax \n\t"
"mov %c[rbx](%0), %%"R"bx \n\t"
"mov %c[rdx](%0), %%"R"dx \n\t"
#endif
);
- vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
+ vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
+ | (1 << VCPU_EXREG_PDPTR));
vcpu->arch.regs_dirty = 0;
- 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);
__clear_bit(vmx->vpid, vmx_vpid_bitmap);
spin_unlock(&vmx_vpid_lock);
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;
if (alloc_apic_access_page(kvm) != 0)
goto free_vmcs;
- if (enable_ept)
+ if (enable_ept) {
+ if (!kvm->arch.ept_identity_map_addr)
+ kvm->arch.ept_identity_map_addr =
+ VMX_EPT_IDENTITY_PAGETABLE_ADDR;
if (alloc_identity_pagetable(kvm) != 0)
goto free_vmcs;
+ }
return &vmx->vcpu;
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);
* 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[] = {
+ _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 }
+};
+
+#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 struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.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,
.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,
.set_tss_addr = vmx_set_tss_addr,
.get_tdp_level = get_ept_level,
.get_mt_mask = vmx_get_mt_mask,
+
+ .exit_reasons_str = vmx_exit_reasons_str,
+ .get_lpage_level = vmx_get_lpage_level,
+
+ .cpuid_update = vmx_cpuid_update,
+
+ .rdtscp_supported = vmx_rdtscp_supported,
};
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)
if (bypass_guest_pf)
kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
- ept_sync_global();
-
return 0;
out3:
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff