KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES

commit 28c1c9fabf48d6ad596273a11c46e0d0da3e14cd upstream.

Intel processors use MSR_IA32_ARCH_CAPABILITIES MSR to indicate RDCL_NO
(bit 0) and IBRS_ALL (bit 1). This is a read-only MSR. By default the
contents will come directly from the hardware, but user-space can still
override it.

[dwmw2: The bit in kvm_cpuid_7_0_edx_x86_features can be unconditional]

Signed-off-by: KarimAllah Ahmed <karahmed@amazon.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>
Cc: kvm@vger.kernel.org
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Asit Mallick <asit.k.mallick@intel.com>
Cc: Arjan Van De Ven <arjan.van.de.ven@intel.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Link: https://lkml.kernel.org/r/1517522386-18410-4-git-send-email-karahmed@amazon.de
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Backported to 4.4: adjust context]
Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 33 insertions, 2 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 35196f8e1ba6..2f3483e395bf 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -362,6 +362,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_supported_word10_x86_features =
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves;
 
+	/* cpuid 7.0.edx*/
+	const u32 kvm_cpuid_7_0_edx_x86_features =
+		F(ARCH_CAPABILITIES);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -439,11 +443,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			cpuid_mask(&entry->ebx, 9);
 			// TSC_ADJUST is emulated
 			entry->ebx |= F(TSC_ADJUST);
-		} else
+			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+			cpuid_mask(&entry->edx, CPUID_7_EDX);
+		} else {
 			entry->ebx = 0;
+			entry->edx = 0;
+		}
 		entry->eax = 0;
 		entry->ecx = 0;
-		entry->edx = 0;
 		break;
 	}
 	case 9:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 213102389795..67c35486d8d0 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -170,6 +170,14 @@ static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu)
 	return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL));
 }
 
+static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & bit(X86_FEATURE_ARCH_CAPABILITIES));
+}
+
 
 /*
  * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a19116fad680..3a513997b1cb 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -545,6 +545,8 @@ struct vcpu_vmx {
 	u64 		      msr_guest_kernel_gs_base;
 #endif
 
+	u64 		      arch_capabilities;
+
 	u32 vm_entry_controls_shadow;
 	u32 vm_exit_controls_shadow;
 	/*
@@ -2832,6 +2834,12 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		msr_info->data = guest_read_tsc(vcpu);
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_arch_capabilities(vcpu))
+			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;
@@ -2958,6 +2966,11 @@ 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))
@@ -5002,6 +5015,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e6ab034f0bc7..276f978efeed 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -961,6 +961,7 @@ static u32 msrs_to_save[] = {
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
+	MSR_IA32_ARCH_CAPABILITIES
 };
 
 static unsigned num_msrs_to_save;