This is a note to let you know that I've just added the patch titled
KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From d28b387fb74da95d69d2615732f50cceb38e9a4d Mon Sep 17 00:00:00 2001
From: KarimAllah Ahmed <karahmed@xxxxxxxxx>
Date: Thu, 1 Feb 2018 22:59:45 +0100
Subject: KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL
From: KarimAllah Ahmed <karahmed@xxxxxxxxx>
commit d28b387fb74da95d69d2615732f50cceb38e9a4d upstream.
[ Based on a patch from Ashok Raj <ashok.raj@xxxxxxxxx> ]
Add direct access to MSR_IA32_SPEC_CTRL for guests. This is needed for
guests that will only mitigate Spectre V2 through IBRS+IBPB and will not
be using a retpoline+IBPB based approach.
To avoid the overhead of saving and restoring the MSR_IA32_SPEC_CTRL for
guests that do not actually use the MSR, only start saving and restoring
when a non-zero is written to it.
No attempt is made to handle STIBP here, intentionally. Filtering STIBP
may be added in a future patch, which may require trapping all writes
if we don't want to pass it through directly to the guest.
[dwmw2: Clean up CPUID bits, save/restore manually, handle reset]
Signed-off-by: KarimAllah Ahmed <karahmed@xxxxxxxxx>
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Darren Kenny <darren.kenny@xxxxxxxxxx>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Reviewed-by: Jim Mattson <jmattson@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Jun Nakajima <jun.nakajima@xxxxxxxxx>
Cc: kvm@xxxxxxxxxxxxxxx
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Asit Mallick <asit.k.mallick@xxxxxxxxx>
Cc: Arjan Van De Ven <arjan.van.de.ven@xxxxxxxxx>
Cc: Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Ashok Raj <ashok.raj@xxxxxxxxx>
Link: https://lkml.kernel.org/r/1517522386-18410-5-git-send-email-karahmed@xxxxxxxxx
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kvm/cpuid.c | 8 ++-
arch/x86/kvm/cpuid.h | 11 +++++
arch/x86/kvm/vmx.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++-
arch/x86/kvm/x86.c | 2
4 files changed, 118 insertions(+), 6 deletions(-)
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -357,7 +357,7 @@ static inline int __do_cpuid_ent(struct
/* cpuid 0x80000008.ebx */
const u32 kvm_cpuid_8000_0008_ebx_x86_features =
- F(IBPB);
+ F(IBPB) | F(IBRS);
/* cpuid 0xC0000001.edx */
const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -382,7 +382,7 @@ static inline int __do_cpuid_ent(struct
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
- F(ARCH_CAPABILITIES);
+ F(SPEC_CTRL) | F(ARCH_CAPABILITIES);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
@@ -618,9 +618,11 @@ static inline int __do_cpuid_ent(struct
g_phys_as = phys_as;
entry->eax = g_phys_as | (virt_as << 8);
entry->edx = 0;
- /* IBPB isn't necessarily present in hardware cpuid */
+ /* IBRS and IBPB aren't necessarily present in hardware cpuid */
if (boot_cpu_has(X86_FEATURE_IBPB))
entry->ebx |= F(IBPB);
+ if (boot_cpu_has(X86_FEATURE_IBRS))
+ entry->ebx |= F(IBRS);
entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
break;
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -171,6 +171,17 @@ static inline bool guest_cpuid_has_ibpb(
return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL));
}
+static inline bool guest_cpuid_has_ibrs(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+ if (best && (best->ebx & bit(X86_FEATURE_IBRS)))
+ return true;
+ best = kvm_find_cpuid_entry(vcpu, 7, 0);
+ 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;
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -551,6 +551,7 @@ struct vcpu_vmx {
#endif
u64 arch_capabilities;
+ u64 spec_ctrl;
u32 vm_entry_controls_shadow;
u32 vm_exit_controls_shadow;
@@ -1854,6 +1855,29 @@ static void update_exception_bitmap(stru
}
/*
+ * Check if MSR is intercepted for currently loaded MSR bitmap.
+ */
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
+{
+ unsigned long *msr_bitmap;
+ int f = sizeof(unsigned long);
+
+ if (!cpu_has_vmx_msr_bitmap())
+ return true;
+
+ msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;
+
+ if (msr <= 0x1fff) {
+ return !!test_bit(msr, msr_bitmap + 0x800 / f);
+ } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+ msr &= 0x1fff;
+ return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+ }
+
+ return true;
+}
+
+/*
* Check if MSR is intercepted for L01 MSR bitmap.
*/
static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
@@ -2983,6 +3007,13 @@ static int vmx_get_msr(struct kvm_vcpu *
case MSR_IA32_TSC:
msr_info->data = guest_read_tsc(vcpu);
break;
+ case MSR_IA32_SPEC_CTRL:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has_ibrs(vcpu))
+ return 1;
+
+ msr_info->data = to_vmx(vcpu)->spec_ctrl;
+ break;
case MSR_IA32_ARCH_CAPABILITIES:
if (!msr_info->host_initiated &&
!guest_cpuid_has_arch_capabilities(vcpu))
@@ -3093,6 +3124,36 @@ static int vmx_set_msr(struct kvm_vcpu *
case MSR_IA32_TSC:
kvm_write_tsc(vcpu, msr_info);
break;
+ case MSR_IA32_SPEC_CTRL:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has_ibrs(vcpu))
+ return 1;
+
+ /* The STIBP bit doesn't fault even if it's not advertised */
+ if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+ return 1;
+
+ vmx->spec_ctrl = data;
+
+ if (!data)
+ break;
+
+ /*
+ * For non-nested:
+ * When it's written (to non-zero) for the first time, pass
+ * it through.
+ *
+ * For nested:
+ * The handling of the MSR bitmap for L2 guests is done in
+ * nested_vmx_merge_msr_bitmap. We should not touch the
+ * vmcs02.msr_bitmap here since it gets completely overwritten
+ * in the merging. We update the vmcs01 here for L1 as well
+ * since it will end up touching the MSR anyway now.
+ */
+ vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
+ MSR_IA32_SPEC_CTRL,
+ MSR_TYPE_RW);
+ break;
case MSR_IA32_PRED_CMD:
if (!msr_info->host_initiated &&
!guest_cpuid_has_ibpb(vcpu))
@@ -5245,6 +5306,7 @@ static void vmx_vcpu_reset(struct kvm_vc
u64 cr0;
vmx->rmode.vm86_active = 0;
+ vmx->spec_ctrl = 0;
vmx->soft_vnmi_blocked = 0;
@@ -8830,6 +8892,15 @@ static void __noclone vmx_vcpu_run(struc
vmx_arm_hv_timer(vcpu);
+ /*
+ * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+ * it's non-zero. Since vmentry is serialising on affected CPUs, there
+ * is no need to worry about the conditional branch over the wrmsr
+ * being speculatively taken.
+ */
+ if (vmx->spec_ctrl)
+ wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+
vmx->__launched = vmx->loaded_vmcs->launched;
asm(
/* Store host registers */
@@ -8948,6 +9019,27 @@ static void __noclone vmx_vcpu_run(struc
#endif
);
+ /*
+ * We do not use IBRS in the kernel. If this vCPU has used the
+ * SPEC_CTRL MSR it may have left it on; save the value and
+ * turn it off. This is much more efficient than blindly adding
+ * it to the atomic save/restore list. Especially as the former
+ * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+ *
+ * For non-nested case:
+ * If the L01 MSR bitmap does not intercept the MSR, then we need to
+ * save it.
+ *
+ * For nested case:
+ * If the L02 MSR bitmap does not intercept the MSR, then we need to
+ * save it.
+ */
+ if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
+ rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+
+ if (vmx->spec_ctrl)
+ wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+
/* Eliminate branch target predictions from guest mode */
vmexit_fill_RSB();
@@ -9507,7 +9599,7 @@ static inline bool nested_vmx_merge_msr_
unsigned long *msr_bitmap_l1;
unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
/*
- * pred_cmd is trying to verify two things:
+ * pred_cmd & spec_ctrl are trying to verify two things:
*
* 1. L0 gave a permission to L1 to actually passthrough the MSR. This
* ensures that we do not accidentally generate an L02 MSR bitmap
@@ -9520,9 +9612,10 @@ static inline bool nested_vmx_merge_msr_
* the MSR.
*/
bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+ bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
- !pred_cmd)
+ !pred_cmd && !spec_ctrl)
return false;
page = nested_get_page(vcpu, vmcs12->msr_bitmap);
@@ -9561,6 +9654,12 @@ static inline bool nested_vmx_merge_msr_
}
}
+ if (spec_ctrl)
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_SPEC_CTRL,
+ MSR_TYPE_R | MSR_TYPE_W);
+
if (pred_cmd)
nested_vmx_disable_intercept_for_msr(
msr_bitmap_l1, msr_bitmap_l0,
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -975,7 +975,7 @@ 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
+ MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
};
static unsigned num_msrs_to_save;
Patches currently in stable-queue which might be from karahmed@xxxxxxxxx are
queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch
queue-4.9/kvm-x86-add-ibpb-support.patch
queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch
queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch