#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"
#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 | X86_CR0_TS | X86_CR0_MP)
+ (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 \
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);
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)
{
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);
}
u64 guest_efer;
u64 ignore_bits;
- guest_efer = vmx->vcpu.arch.shadow_efer;
+ guest_efer = vmx->vcpu.arch.efer;
/*
* NX is emulated; LMA and LME handled by hardware; SCE meaninless
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)
* 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
* of this msr depends on is_long_mode().
*/
vmx_load_host_state(to_vmx(vcpu));
- vcpu->arch.shadow_efer = efer;
- if (!msr)
- return;
+ 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)
{
ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
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)
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)
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 */
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;
}
{
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;
}
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 */
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;
};
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;
return 0;
}
+static int check_dr_alias(struct kvm_vcpu *vcpu)
+{
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return -1;
+ }
+ return 0;
+}
+
static int handle_dr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
unsigned long val;
int dr, reg;
+ /* Do not handle if the CPL > 0, will trigger GP on re-entry */
if (!kvm_require_cpl(vcpu, 0))
return 1;
dr = vmcs_readl(GUEST_DR7);
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);
} else {
if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
vcpu->arch.eff_db[dr] = val;
break;
- case 4 ... 5:
- if (kvm_read_cr4_bits(vcpu, 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)) {
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;
}
}
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;
*/
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);
* 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)
{
- return false;
+ 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)
.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,
.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,