KVM: arm64: Ensure I-cache isolation between vcpus of a same VM

It recently became apparent that the ARMv8 architecture has interesting
rules regarding attributes being used when fetching instructions
if the MMU is off at Stage-1.

In this situation, the CPU is allowed to fetch from the PoC and
allocate into the I-cache (unless the memory is mapped with
the XN attribute at Stage-2).

If we transpose this to vcpus sharing a single physical CPU,
it is possible for a vcpu running with its MMU off to influence
another vcpu running with its MMU on, as the latter is expected to
fetch from the PoU (and self-patching code doesn't flush below that
level).

In order to solve this, reuse the vcpu-private TLB invalidation
code to apply the same policy to the I-cache, nuking it every time
the vcpu runs on a physical CPU that ran another vcpu of the same
VM in the past.

This involve renaming __kvm_tlb_flush_local_vmid() to
__kvm_flush_cpu_context(), and inserting a local i-cache invalidation
there.

Cc: stable@vger.kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20210303164505.68492-1-maz@kernel.org

arch/arm64/include/asm/kvm_asm.h

@@ -47,7 +47,7 @@
 #define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context		2
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa		3
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid		4
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid	5
+#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context		5
 #define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff		6
 #define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs			7
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config		8
@@ -183,10 +183,10 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
 
 extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 				     int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 

arch/arm64/kvm/arm.c

@@ -385,11 +385,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
+	 * We guarantee that both TLBs and I-cache are private to each
+	 * vcpu. If detecting that a vcpu from the same VM has
+	 * previously run on the same physical CPU, call into the
+	 * hypervisor code to nuke the relevant contexts.
+	 *
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
 	if (*last_ran != vcpu->vcpu_id) {
-		kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
+		kvm_call_hyp(__kvm_flush_cpu_context, mmu);
 		*last_ran = vcpu->vcpu_id;
 	}
 

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -46,11 +46,11 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
 }
 
-static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt)
+static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
 
-	__kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
+	__kvm_flush_cpu_context(kern_hyp_va(mmu));
 }
 
 static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
@@ -115,7 +115,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
-	HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
+	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__kvm_enable_ssbs),
 	HANDLE_FUNC(__vgic_v3_get_gic_config),

arch/arm64/kvm/hyp/nvhe/tlb.c

@@ -123,7 +123,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -131,6 +131,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 

arch/arm64/kvm/hyp/vhe/tlb.c

@@ -127,7 +127,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -135,6 +135,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();