[PATCH 3.16 055/410] KVM/x86: Add IBPB support

[Ben Hutchings]

3.16.57-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Ashok Raj <ashok.raj@xxxxxxxxx>

commit 15d45071523d89b3fb7372e2135fbd72f6af9506 upstream.

The Indirect Branch Predictor Barrier (IBPB) is an indirect branch
control mechanism. It keeps earlier branches from influencing
later ones.

Unlike IBRS and STIBP, IBPB does not define a new mode of operation.
It's a command that ensures predicted branch targets aren't used after
the barrier. Although IBRS and IBPB are enumerated by the same CPUID
enumeration, IBPB is very different.

IBPB helps mitigate against three potential attacks:

* Mitigate guests from being attacked by other guests.
  - This is addressed by issing IBPB when we do a guest switch.

* Mitigate attacks from guest/ring3->host/ring3.
  These would require a IBPB during context switch in host, or after
  VMEXIT. The host process has two ways to mitigate
  - Either it can be compiled with retpoline
  - If its going through context switch, and has set !dumpable then
    there is a IBPB in that path.
    (Tim's patch: https://patchwork.kernel.org/patch/10192871)
  - The case where after a VMEXIT you return back to Qemu might make
    Qemu attackable from guest when Qemu isn't compiled with retpoline.
  There are issues reported when doing IBPB on every VMEXIT that resulted
  in some tsc calibration woes in guest.

* Mitigate guest/ring0->host/ring0 attacks.
  When host kernel is using retpoline it is safe against these attacks.
  If host kernel isn't using retpoline we might need to do a IBPB flush on
  every VMEXIT.

Even when using retpoline for indirect calls, in certain conditions 'ret'
can use the BTB on Skylake-era CPUs. There are other mitigations
available like RSB stuffing/clearing.

* IBPB is issued only for SVM during svm_free_vcpu().
  VMX has a vmclear and SVM doesn't.  Follow discussion here:
  https://lkml.org/lkml/2018/1/15/146

Please refer to the following spec for more details on the enumeration
and control.

Refer here to get documentation about mitigations.

https://software.intel.com/en-us/side-channel-security-support

[peterz: rebase and changelog rewrite]
[karahmed: - rebase
           - vmx: expose PRED_CMD if guest has it in CPUID
           - svm: only pass through IBPB if guest has it in CPUID
           - vmx: support !cpu_has_vmx_msr_bitmap()]
           - vmx: support nested]
[dwmw2: Expose CPUID bit too (AMD IBPB only for now as we lack IBRS)
        PRED_CMD is a write-only MSR]

Signed-off-by: Ashok Raj <ashok.raj@xxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: KarimAllah Ahmed <karahmed@xxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: kvm@xxxxxxxxxxxxxxx
Cc: Asit Mallick <asit.k.mallick@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Arjan Van De Ven <arjan.van.de.ven@xxxxxxxxx>
Cc: Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Jun Nakajima <jun.nakajima@xxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1515720739-43819-6-git-send-email-ashok.raj@xxxxxxxxx
Link: https://lkml.kernel.org/r/1517522386-18410-3-git-send-email-karahmed@xxxxxxxxx
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
[bwh: Backported to 3.16:
 - No support for nested MSR bitmaps in VMX
 - Use literal number for CPU feature word
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 arch/x86/kvm/cpuid.c | 11 ++++++++-
 arch/x86/kvm/cpuid.h | 12 ++++++++++
 arch/x86/kvm/svm.c   | 28 +++++++++++++++++++++++
 arch/x86/kvm/vmx.c   | 54 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 104 insertions(+), 1 deletion(-)

--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -300,6 +300,10 @@ static inline int __do_cpuid_ent(struct
 		F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
 		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
 
+	/* cpuid 0x80000008.ebx */
+	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
+		F(IBPB);
+
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_supported_word5_x86_features =
 		F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
@@ -512,7 +516,12 @@ static inline int __do_cpuid_ent(struct
 		if (!g_phys_as)
 			g_phys_as = phys_as;
 		entry->eax = g_phys_as | (virt_as << 8);
-		entry->ebx = entry->edx = 0;
+		entry->edx = 0;
+		/* IBPB isn't necessarily present in hardware cpuid */
+		if (boot_cpu_has(X86_FEATURE_IBPB))
+			entry->ebx |= F(IBPB);
+		entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
+		cpuid_mask(&entry->ebx, 11);
 		break;
 	}
 	case 0x80000019:
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -104,4 +104,16 @@ static inline bool guest_cpuid_has_mpx(s
 	return best && (best->ebx & bit(X86_FEATURE_MPX));
 }
 
+static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best && (best->ebx & bit(X86_FEATURE_IBPB)))
+		return true;
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL));
+}
+
+
 #endif
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -180,6 +180,7 @@ static const struct svm_direct_access_ms
 	{ .index = MSR_CSTAR,				.always = true  },
 	{ .index = MSR_SYSCALL_MASK,			.always = true  },
 #endif
+	{ .index = MSR_IA32_PRED_CMD,			.always = false },
 	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
@@ -409,6 +410,7 @@ struct svm_cpu_data {
 	struct kvm_ldttss_desc *tss_desc;
 
 	struct page *save_area;
+	struct vmcb *current_vmcb;
 };
 
 static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
@@ -1294,11 +1296,17 @@ static void svm_free_vcpu(struct kvm_vcp
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
+	/*
+	 * The vmcb page can be recycled, causing a false negative in
+	 * svm_vcpu_load(). So do a full IBPB now.
+	 */
+	indirect_branch_prediction_barrier();
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 	int i;
 
 	if (unlikely(cpu != vcpu->cpu)) {
@@ -1321,6 +1329,10 @@ static void svm_vcpu_load(struct kvm_vcp
 		__get_cpu_var(current_tsc_ratio) = svm->tsc_ratio;
 		wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio);
 	}
+	if (sd->current_vmcb != svm->vmcb) {
+		sd->current_vmcb = svm->vmcb;
+		indirect_branch_prediction_barrier();
+	}
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
@@ -3172,6 +3184,22 @@ static int svm_set_msr(struct kvm_vcpu *
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr);
 		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_ibpb(vcpu))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+		if (is_guest_mode(vcpu))
+			break;
+		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
+		break;
 	case MSR_STAR:
 		svm->vmcb->save.star = data;
 		break;
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -431,6 +431,7 @@ struct vcpu_vmx {
 	u64 		      msr_host_kernel_gs_base;
 	u64 		      msr_guest_kernel_gs_base;
 #endif
+
 	u32 vm_entry_controls_shadow;
 	u32 vm_exit_controls_shadow;
 	/*
@@ -756,6 +757,8 @@ static void copy_vmcs12_to_shadow(struct
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static bool vmx_mpx_supported(void);
 static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+							  u32 msr, int type);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -1507,6 +1510,29 @@ static void update_exception_bitmap(stru
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
 
+/*
+ * Check if MSR is intercepted for L01 MSR bitmap.
+ */
+static bool msr_write_intercepted_l01(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)->vmcs01.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;
+}
+
 static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 		unsigned long entry, unsigned long exit)
 {
@@ -1828,6 +1854,7 @@ static void vmx_vcpu_load(struct kvm_vcp
 	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
 		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
 		vmcs_load(vmx->loaded_vmcs->vmcs);
+		indirect_branch_prediction_barrier();
 	}
 
 	if (vmx->loaded_vmcs->cpu != cpu) {
@@ -2587,6 +2614,33 @@ static int vmx_set_msr(struct kvm_vcpu *
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_ibpb(vcpu))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+
+		/*
+		 * 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.
+		 */
+		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
+					      MSR_TYPE_W);
+		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))