Merge branch kvm-arm64/mmu/vmid-cleanups into kvmarm-master/next

* kvm-arm64/mmu/vmid-cleanups:
  : Cleanup the stage-2 configuration by providing a single helper,
  : and tidy up some of the ordering requirements for the VMID
  : allocator.
  KVM: arm64: Upgrade VMID accesses to {READ,WRITE}_ONCE
  KVM: arm64: Unify stage-2 programming behind __load_stage2()
  KVM: arm64: Move kern_hyp_va() usage in __load_guest_stage2() into the callers
Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_mmu.h

@@ -252,6 +252,11 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
 
 #define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)
 
+/*
+ * When this is (directly or indirectly) used on the TLB invalidation
+ * path, we rely on a previously issued DSB so that page table updates
+ * and VMID reads are correctly ordered.
+ */
 static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
 {
 	struct kvm_vmid *vmid = &mmu->vmid;
@@ -259,7 +264,7 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
 	u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
 
 	baddr = mmu->pgd_phys;
-	vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
+	vmid_field = (u64)READ_ONCE(vmid->vmid) << VTTBR_VMID_SHIFT;
 	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
 }
 
@@ -267,9 +272,10 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
  * Must be called from hyp code running at EL2 with an updated VTTBR
  * and interrupts disabled.
  */
-static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu, unsigned long vtcr)
+static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu,
+					  struct kvm_arch *arch)
 {
-	write_sysreg(vtcr, vtcr_el2);
+	write_sysreg(arch->vtcr, vtcr_el2);
 	write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
 
 	/*
@@ -280,11 +286,6 @@ static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu, unsigned long
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
-static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu)
-{
-	__load_stage2(mmu, kern_hyp_va(mmu->arch)->vtcr);
-}
-
 static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
 {
 	return container_of(mmu->arch, struct kvm, arch);

arch/arm64/kvm/arm.c

@@ -573,7 +573,7 @@ static void update_vmid(struct kvm_vmid *vmid)
 		kvm_call_hyp(__kvm_flush_vm_context);
 	}
 
-	vmid->vmid = kvm_next_vmid;
+	WRITE_ONCE(vmid->vmid, kvm_next_vmid);
 	kvm_next_vmid++;
 	kvm_next_vmid &= (1 << kvm_get_vmid_bits()) - 1;
 

arch/arm64/kvm/hyp/include/nvhe/mem_protect.h

@@ -60,7 +60,7 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt);
 static __always_inline void __load_host_stage2(void)
 {
 	if (static_branch_likely(&kvm_protected_mode_initialized))
-		__load_stage2(&host_kvm.arch.mmu, host_kvm.arch.vtcr);
+		__load_stage2(&host_kvm.arch.mmu, &host_kvm.arch);
 	else
 		write_sysreg(0, vttbr_el2);
 }

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

@@ -112,8 +112,8 @@ int kvm_host_prepare_stage2(void *pgt_pool_base)
 	mmu->pgd_phys = __hyp_pa(host_kvm.pgt.pgd);
 	mmu->arch = &host_kvm.arch;
 	mmu->pgt = &host_kvm.pgt;
-	mmu->vmid.vmid_gen = 0;
-	mmu->vmid.vmid = 0;
+	WRITE_ONCE(mmu->vmid.vmid_gen, 0);
+	WRITE_ONCE(mmu->vmid.vmid, 0);
 
 	return 0;
 }
@@ -129,7 +129,7 @@ int __pkvm_prot_finalize(void)
 	kvm_flush_dcache_to_poc(params, sizeof(*params));
 
 	write_sysreg(params->hcr_el2, hcr_el2);
-	__load_stage2(&host_kvm.arch.mmu, host_kvm.arch.vtcr);
+	__load_stage2(&host_kvm.arch.mmu, &host_kvm.arch);
 
 	/*
 	 * Make sure to have an ISB before the TLB maintenance below but only

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

@@ -170,6 +170,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
+	struct kvm_s2_mmu *mmu;
 	bool pmu_switch_needed;
 	u64 exit_code;
 
@@ -213,7 +214,8 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_state_nvhe(guest_ctxt);
 
-	__load_guest_stage2(kern_hyp_va(vcpu->arch.hw_mmu));
+	mmu = kern_hyp_va(vcpu->arch.hw_mmu);
+	__load_stage2(mmu, kern_hyp_va(mmu->arch));
 	__activate_traps(vcpu);
 
 	__hyp_vgic_restore_state(vcpu);

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

@@ -34,12 +34,12 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 	}
 
 	/*
-	 * __load_guest_stage2() includes an ISB only when the AT
+	 * __load_stage2() includes an ISB only when the AT
 	 * workaround is applied. Take care of the opposite condition,
 	 * ensuring that we always have an ISB, but not two ISBs back
 	 * to back.
 	 */
-	__load_guest_stage2(mmu);
+	__load_stage2(mmu, kern_hyp_va(mmu->arch));
 	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 

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

@@ -124,11 +124,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	 *
 	 * We have already configured the guest's stage 1 translation in
 	 * kvm_vcpu_load_sysregs_vhe above.  We must now call
-	 * __load_guest_stage2 before __activate_traps, because
-	 * __load_guest_stage2 configures stage 2 translation, and
+	 * __load_stage2 before __activate_traps, because
+	 * __load_stage2 configures stage 2 translation, and
 	 * __activate_traps clear HCR_EL2.TGE (among other things).
 	 */
-	__load_guest_stage2(vcpu->arch.hw_mmu);
+	__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
 	__activate_traps(vcpu);
 
 	__kvm_adjust_pc(vcpu);

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

@@ -50,10 +50,10 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 	 *
 	 * ARM erratum 1165522 requires some special handling (again),
 	 * as we need to make sure both stages of translation are in
-	 * place before clearing TGE. __load_guest_stage2() already
+	 * place before clearing TGE. __load_stage2() already
 	 * has an ISB in order to deal with this.
 	 */
-	__load_guest_stage2(mmu);
+	__load_stage2(mmu, mmu->arch);
 	val = read_sysreg(hcr_el2);
 	val &= ~HCR_TGE;
 	write_sysreg(val, hcr_el2);

arch/arm64/kvm/mmu.c

@@ -532,7 +532,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 	mmu->arch = &kvm->arch;
 	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
-	mmu->vmid.vmid_gen = 0;
+	WRITE_ONCE(mmu->vmid.vmid_gen, 0);
 	return 0;
 
 out_destroy_pgtable: