summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/vmx
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/vmx')
-rw-r--r--arch/x86/kvm/vmx/nested.c130
-rw-r--r--arch/x86/kvm/vmx/vmenter.S12
-rw-r--r--arch/x86/kvm/vmx/vmx.c61
-rw-r--r--arch/x86/kvm/vmx/vmx.h3
4 files changed, 142 insertions, 64 deletions
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f24a2c225070..0c601d079cd2 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -500,6 +500,17 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
}
}
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+ int msr;
+
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+
+ msr_bitmap[word] = ~0;
+ msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+ }
+}
+
/*
* Merge L0's and L1's MSR bitmap, return false to indicate that
* we do not use the hardware.
@@ -541,39 +552,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
return false;
msr_bitmap_l1 = (unsigned long *)kmap(page);
- if (nested_cpu_has_apic_reg_virt(vmcs12)) {
- /*
- * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
- * just lets the processor take the value from the virtual-APIC page;
- * take those 256 bits directly from the L1 bitmap.
- */
- for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
- unsigned word = msr / BITS_PER_LONG;
- msr_bitmap_l0[word] = msr_bitmap_l1[word];
- msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
- }
- } else {
- for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
- unsigned word = msr / BITS_PER_LONG;
- msr_bitmap_l0[word] = ~0;
- msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
- }
- }
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_TASKPRI),
- MSR_TYPE_W);
+ /*
+ * To keep the control flow simple, pay eight 8-byte writes (sixteen
+ * 4-byte writes on 32-bit systems) up front to enable intercepts for
+ * the x2APIC MSR range and selectively disable them below.
+ */
+ enable_x2apic_msr_intercepts(msr_bitmap_l0);
+
+ if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
+ if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+ /*
+ * L0 need not intercept reads for MSRs between 0x800
+ * and 0x8ff, it just lets the processor take the value
+ * from the virtual-APIC page; take those 256 bits
+ * directly from the L1 bitmap.
+ */
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+
+ msr_bitmap_l0[word] = msr_bitmap_l1[word];
+ }
+ }
- if (nested_cpu_has_vid(vmcs12)) {
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_EOI),
- MSR_TYPE_W);
nested_vmx_disable_intercept_for_msr(
msr_bitmap_l1, msr_bitmap_l0,
- X2APIC_MSR(APIC_SELF_IPI),
- MSR_TYPE_W);
+ X2APIC_MSR(APIC_TASKPRI),
+ MSR_TYPE_R | MSR_TYPE_W);
+
+ if (nested_cpu_has_vid(vmcs12)) {
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_EOI),
+ MSR_TYPE_W);
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_SELF_IPI),
+ MSR_TYPE_W);
+ }
}
if (spec_ctrl)
@@ -2585,6 +2601,11 @@ static int nested_check_host_control_regs(struct kvm_vcpu *vcpu,
!nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
!nested_cr3_valid(vcpu, vmcs12->host_cr3))
return -EINVAL;
+
+ if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) ||
+ is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))
+ return -EINVAL;
+
/*
* If the load IA32_EFER VM-exit control is 1, bits reserved in the
* IA32_EFER MSR must be 0 in the field for that register. In addition,
@@ -2852,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
/*
* If translation failed, VM entry will fail because
* prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
- * Failing the vm entry is _not_ what the processor
- * does but it's basically the only possibility we
- * have. We could still enter the guest if CR8 load
- * exits are enabled, CR8 store exits are enabled, and
- * virtualize APIC access is disabled; in this case
- * the processor would never use the TPR shadow and we
- * could simply clear the bit from the execution
- * control. But such a configuration is useless, so
- * let's keep the code simple.
*/
if (!is_error_page(page)) {
vmx->nested.virtual_apic_page = page;
hpa = page_to_phys(vmx->nested.virtual_apic_page);
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+ } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+ nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+ !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /*
+ * The processor will never use the TPR shadow, simply
+ * clear the bit from the execution control. Such a
+ * configuration is useless, but it happens in tests.
+ * For any other configuration, failing the vm entry is
+ * _not_ what the processor does but it's basically the
+ * only possibility we have.
+ */
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_TPR_SHADOW);
+ } else {
+ printk("bad virtual-APIC page address\n");
+ dump_vmcs();
}
}
@@ -3768,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
nested_ept_uninit_mmu_context(vcpu);
- vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+ * points to shadow pages! Fortunately we only get here after a WARN_ON
+ * if EPT is disabled, so a VMabort is perfectly fine.
+ */
+ if (enable_ept) {
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ } else {
+ nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+ }
/*
* Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -5385,7 +5423,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
return ret;
/* Empty 'VMXON' state is permitted */
- if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
+ if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
return 0;
if (kvm_state->vmx.vmcs_pa != -1ull) {
@@ -5429,7 +5467,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
vmcs12->vmcs_link_pointer != -1ull) {
struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
- if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12))
+ if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12))
return -EINVAL;
if (copy_from_user(shadow_vmcs12,
@@ -5717,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
{
int i;
+ /*
+ * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+ * VMfail, because they are not available in vmcs01. Just always
+ * use hardware checks.
+ */
+ if (!enable_ept)
+ nested_early_check = 1;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs) {
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 7b272738c576..d4cb1945b2e3 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -3,6 +3,7 @@
#include <asm/asm.h>
#include <asm/bitsperlong.h>
#include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
#define WORD_SIZE (BITS_PER_LONG / 8)
@@ -77,6 +78,17 @@ ENDPROC(vmx_vmenter)
* referred to by VMCS.HOST_RIP.
*/
ENTRY(vmx_vmexit)
+#ifdef CONFIG_RETPOLINE
+ ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
+ /* Preserve guest's RAX, it's used to stuff the RSB. */
+ push %_ASM_AX
+
+ /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+
+ pop %_ASM_AX
+.Lvmexit_skip_rsb:
+#endif
ret
ENDPROC(vmx_vmexit)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index c73375e01ab8..0c955bb286ff 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1683,12 +1683,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = to_vmx(vcpu)->spec_ctrl;
break;
- case MSR_IA32_ARCH_CAPABILITIES:
- if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
- return 1;
- msr_info->data = to_vmx(vcpu)->arch_capabilities;
- break;
case MSR_IA32_SYSENTER_CS:
msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
break;
@@ -1895,11 +1889,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
MSR_TYPE_W);
break;
- case MSR_IA32_ARCH_CAPABILITIES:
- if (!msr_info->host_initiated)
- return 1;
- vmx->arch_capabilities = data;
- break;
case MSR_IA32_CR_PAT:
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
@@ -4088,8 +4077,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
++vmx->nmsrs;
}
- vmx->arch_capabilities = kvm_get_arch_capabilities();
-
vm_exit_controls_init(vmx, vmx_vmexit_ctrl());
/* 22.2.1, 20.8.1 */
@@ -5616,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
}
-static void dump_vmcs(void)
+void dump_vmcs(void)
{
u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
@@ -6423,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ kvm_load_guest_xcr0(vcpu);
+
if (static_cpu_has(X86_FEATURE_PKU) &&
kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
vcpu->arch.pkru != vmx->host_pkru)
@@ -6473,9 +6462,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
- /* Eliminate branch target predictions from guest mode */
- vmexit_fill_RSB();
-
/* All fields are clean at this point */
if (static_branch_unlikely(&enable_evmcs))
current_evmcs->hv_clean_fields |=
@@ -6519,6 +6505,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
__write_pkru(vmx->host_pkru);
}
+ kvm_put_guest_xcr0(vcpu);
+
vmx->nested.nested_run_pending = 0;
vmx->idt_vectoring_info = 0;
@@ -6865,6 +6853,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
}
}
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *entry;
+ union cpuid10_eax eax;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return false;
+
+ eax.full = entry->eax;
+ return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+ if (pmu_enabled)
+ vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+ else
+ vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6953,6 +6965,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
nested_vmx_entry_exit_ctls_update(vcpu);
+ nested_vmx_procbased_ctls_update(vcpu);
}
if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
@@ -7016,6 +7029,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
{
struct vcpu_vmx *vmx;
u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
+ struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer;
if (kvm_mwait_in_guest(vcpu->kvm))
return -EOPNOTSUPP;
@@ -7024,7 +7038,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
tscl = rdtsc();
guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
- lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+ lapic_timer_advance_cycles = nsec_to_cycles(vcpu,
+ ktimer->timer_advance_ns);
if (delta_tsc > lapic_timer_advance_cycles)
delta_tsc -= lapic_timer_advance_cycles;
@@ -7382,7 +7397,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
@@ -7393,9 +7408,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
}
if (vmx->nested.smm.guest_mode) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
ret = nested_vmx_enter_non_root_mode(vcpu, false);
- vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
@@ -7409,6 +7422,11 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
return 0;
}
+static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
static __init int hardware_setup(void)
{
unsigned long host_bndcfgs;
@@ -7711,6 +7729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.set_nested_state = NULL,
.get_vmcs12_pages = NULL,
.nested_enable_evmcs = NULL,
+ .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
};
static void vmx_cleanup_l1d_flush(void)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 1554cb45b393..f879529906b4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -190,7 +190,6 @@ struct vcpu_vmx {
u64 msr_guest_kernel_gs_base;
#endif
- u64 arch_capabilities;
u64 spec_ctrl;
u32 vm_entry_controls_shadow;
@@ -518,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}
+void dump_vmcs(void);
+
#endif /* __KVM_X86_VMX_H */
generated by cgit (git 2.34.1) at 2024-06-01 16:18:06 +0000