summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/kvm/svm/svm.c8
-rw-r--r--arch/x86/kvm/vmx/vmx.c37
-rw-r--r--arch/x86/kvm/vmx/vmx.h5
-rw-r--r--arch/x86/kvm/x86.c22
-rw-r--r--arch/x86/lib/usercopy_64.c2
5 files changed, 52 insertions, 22 deletions
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c44f3e9140d5..91ea74ae71b8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm)
return 1;
}
+static int invd_interception(struct vcpu_svm *svm)
+{
+ /* Treat an INVD instruction as a NOP and just skip it. */
+ return kvm_skip_emulated_instruction(&svm->vcpu);
+}
+
static int invlpg_interception(struct vcpu_svm *svm)
{
if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
@@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_RDPMC] = rdpmc_interception,
[SVM_EXIT_CPUID] = cpuid_interception,
[SVM_EXIT_IRET] = iret_interception,
- [SVM_EXIT_INVD] = emulate_on_interception,
+ [SVM_EXIT_INVD] = invd_interception,
[SVM_EXIT_PAUSE] = pause_interception,
[SVM_EXIT_HLT] = halt_interception,
[SVM_EXIT_INVLPG] = invlpg_interception,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 8646a797b7a8..96979c09ebd1 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1;
module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
#endif
+extern bool __read_mostly allow_smaller_maxphyaddr;
+module_param(allow_smaller_maxphyaddr, bool, S_IRUGO);
+
#define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
#define KVM_VM_CR0_ALWAYS_ON \
@@ -791,6 +794,18 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu)
*/
if (is_guest_mode(vcpu))
eb |= get_vmcs12(vcpu)->exception_bitmap;
+ else {
+ /*
+ * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched
+ * between guest and host. In that case we only care about present
+ * faults. For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in
+ * prepare_vmcs02_rare.
+ */
+ bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR));
+ int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0;
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask);
+ }
vmcs_write32(EXCEPTION_BITMAP, eb);
}
@@ -4352,16 +4367,6 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmx->pt_desc.guest.output_mask = 0x7F;
vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
}
-
- /*
- * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched
- * between guest and host. In that case we only care about present
- * faults.
- */
- if (enable_ept) {
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, PFERR_PRESENT_MASK);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, PFERR_PRESENT_MASK);
- }
}
static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -4803,6 +4808,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
* EPT will cause page fault only if we need to
* detect illegal GPAs.
*/
+ WARN_ON_ONCE(!allow_smaller_maxphyaddr);
kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code);
return 1;
} else
@@ -5331,7 +5337,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
* would also use advanced VM-exit information for EPT violations to
* reconstruct the page fault error code.
*/
- if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa)))
+ if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa)))
return kvm_emulate_instruction(vcpu, 0);
return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
@@ -8305,11 +8311,12 @@ static int __init vmx_init(void)
vmx_check_vmcs12_offsets();
/*
- * Intel processors don't have problems with
- * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable
- * it for VMX by default
+ * Shadow paging doesn't have a (further) performance penalty
+ * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it
+ * by default
*/
- allow_smaller_maxphyaddr = true;
+ if (!enable_ept)
+ allow_smaller_maxphyaddr = true;
return 0;
}
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a2f82127c170..a0e47720f60c 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -552,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
{
- return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
+ if (!enable_ept)
+ return true;
+
+ return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
}
void dump_vmcs(void);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1994602a0851..ce856e0ece84 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs;
u64 __read_mostly host_efer;
EXPORT_SYMBOL_GPL(host_efer);
-bool __read_mostly allow_smaller_maxphyaddr;
+bool __read_mostly allow_smaller_maxphyaddr = 0;
EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
static u64 __read_mostly host_xss;
@@ -976,6 +976,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
unsigned long old_cr4 = kvm_read_cr4(vcpu);
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
X86_CR4_SMEP;
+ unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
if (kvm_valid_cr4(vcpu, cr4))
return 1;
@@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
if (kvm_x86_ops.set_cr4(vcpu, cr4))
return 1;
- if (((cr4 ^ old_cr4) & pdptr_bits) ||
+ if (((cr4 ^ old_cr4) & mmu_role_bits) ||
(!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
kvm_mmu_reset_context(vcpu);
@@ -3221,9 +3222,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_POWER_CTL:
msr_info->data = vcpu->arch.msr_ia32_power_ctl;
break;
- case MSR_IA32_TSC:
- msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+ case MSR_IA32_TSC: {
+ /*
+ * Intel SDM states that MSR_IA32_TSC read adds the TSC offset
+ * even when not intercepted. AMD manual doesn't explicitly
+ * state this but appears to behave the same.
+ *
+ * On userspace reads and writes, however, we unconditionally
+ * operate L1's TSC value to ensure backwards-compatible
+ * behavior for migration.
+ */
+ u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset :
+ vcpu->arch.tsc_offset;
+
+ msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset;
break;
+ }
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b0dfac3d3df7..1847e993ac63 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
*/
if (size < 8) {
if (!IS_ALIGNED(dest, 4) || size != 4)
- clean_cache_range(dst, 1);
+ clean_cache_range(dst, size);
} else {
if (!IS_ALIGNED(dest, 8)) {
dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
generated by cgit (git 2.34.1) at 2024-05-26 06:13:27 +0000