From: Will Deacon Date: Mon, 30 Mar 2026 14:48:12 +0000 (+0100) Subject: KVM: arm64: Split teardown hypercall into two phases X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=6c58f914eb9c4ce5225d03183ae1290d72b5f639;p=thirdparty%2Fkernel%2Flinux.git KVM: arm64: Split teardown hypercall into two phases In preparation for reclaiming protected guest VM pages from the host during teardown, split the current 'pkvm_teardown_vm' hypercall into separate 'start' and 'finalise' calls. The 'pkvm_start_teardown_vm' hypercall puts the VM into a new 'is_dying' state, which is a point of no return past which no vCPU of the pVM is allowed to run any more. Once in this new state, 'pkvm_finalize_teardown_vm' can be used to reclaim meta-data and page-table pages from the VM. A subsequent patch will add support for reclaiming the individual guest memory pages. Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Tested-by: Mostafa Saleh Co-developed-by: Quentin Perret Signed-off-by: Quentin Perret Signed-off-by: Will Deacon Link: https://patch.msgid.link/20260330144841.26181-12-will@kernel.org Signed-off-by: Marc Zyngier --- diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 7b72aac4730d9..df6b661701b6f 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -89,7 +89,8 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm, __KVM_HOST_SMCCC_FUNC___pkvm_init_vm, __KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu, - __KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm, + __KVM_HOST_SMCCC_FUNC___pkvm_start_teardown_vm, + __KVM_HOST_SMCCC_FUNC___pkvm_finalize_teardown_vm, __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load, __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put, __KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid, diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 70cb9cfd760a3..31b9454bb74db 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -255,6 +255,13 @@ struct kvm_protected_vm { struct kvm_hyp_memcache stage2_teardown_mc; bool is_protected; bool is_created; + + /* + * True when the guest is being torn down. When in this state, the + * guest's vCPUs can't be loaded anymore, but its pages can be + * reclaimed by the host. + */ + bool is_dying; }; struct kvm_mpidr_data { diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h index 184ad7a399507..04c7ca7030144 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h @@ -73,7 +73,9 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva, unsigned long pgd_hva); int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, unsigned long vcpu_hva); -int __pkvm_teardown_vm(pkvm_handle_t handle); + +int __pkvm_start_teardown_vm(pkvm_handle_t handle); +int __pkvm_finalize_teardown_vm(pkvm_handle_t handle); struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, unsigned int vcpu_idx); diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 127decc2dd2b8..634ea27662407 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -553,11 +553,18 @@ static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva); } -static void handle___pkvm_teardown_vm(struct kvm_cpu_context *host_ctxt) +static void handle___pkvm_start_teardown_vm(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); - cpu_reg(host_ctxt, 1) = __pkvm_teardown_vm(handle); + cpu_reg(host_ctxt, 1) = __pkvm_start_teardown_vm(handle); +} + +static void handle___pkvm_finalize_teardown_vm(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_finalize_teardown_vm(handle); } typedef void (*hcall_t)(struct kvm_cpu_context *); @@ -598,7 +605,8 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__pkvm_unreserve_vm), HANDLE_FUNC(__pkvm_init_vm), HANDLE_FUNC(__pkvm_init_vcpu), - HANDLE_FUNC(__pkvm_teardown_vm), + HANDLE_FUNC(__pkvm_start_teardown_vm), + HANDLE_FUNC(__pkvm_finalize_teardown_vm), HANDLE_FUNC(__pkvm_vcpu_load), HANDLE_FUNC(__pkvm_vcpu_put), HANDLE_FUNC(__pkvm_tlb_flush_vmid), diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 2f029bfe4755a..61e69e24656a5 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -255,7 +255,10 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, hyp_spin_lock(&vm_table_lock); hyp_vm = get_vm_by_handle(handle); - if (!hyp_vm || hyp_vm->kvm.created_vcpus <= vcpu_idx) + if (!hyp_vm || hyp_vm->kvm.arch.pkvm.is_dying) + goto unlock; + + if (hyp_vm->kvm.created_vcpus <= vcpu_idx) goto unlock; hyp_vcpu = hyp_vm->vcpus[vcpu_idx]; @@ -301,8 +304,14 @@ struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle) hyp_spin_lock(&vm_table_lock); hyp_vm = get_vm_by_handle(handle); - if (hyp_vm) + if (!hyp_vm) + goto unlock; + + if (hyp_vm->kvm.arch.pkvm.is_dying) + hyp_vm = NULL; + else hyp_page_ref_inc(hyp_virt_to_page(hyp_vm)); +unlock: hyp_spin_unlock(&vm_table_lock); return hyp_vm; @@ -859,7 +868,32 @@ teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size) unmap_donated_memory_noclear(addr, size); } -int __pkvm_teardown_vm(pkvm_handle_t handle) +int __pkvm_start_teardown_vm(pkvm_handle_t handle) +{ + struct pkvm_hyp_vm *hyp_vm; + int ret = 0; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_vm_by_handle(handle); + if (!hyp_vm) { + ret = -ENOENT; + goto unlock; + } else if (WARN_ON(hyp_page_count(hyp_vm))) { + ret = -EBUSY; + goto unlock; + } else if (hyp_vm->kvm.arch.pkvm.is_dying) { + ret = -EINVAL; + goto unlock; + } + + hyp_vm->kvm.arch.pkvm.is_dying = true; +unlock: + hyp_spin_unlock(&vm_table_lock); + + return ret; +} + +int __pkvm_finalize_teardown_vm(pkvm_handle_t handle) { struct kvm_hyp_memcache *mc, *stage2_mc; struct pkvm_hyp_vm *hyp_vm; @@ -873,9 +907,7 @@ int __pkvm_teardown_vm(pkvm_handle_t handle) if (!hyp_vm) { err = -ENOENT; goto err_unlock; - } - - if (WARN_ON(hyp_page_count(hyp_vm))) { + } else if (!hyp_vm->kvm.arch.pkvm.is_dying) { err = -EBUSY; goto err_unlock; } diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 94b70eb80aa81..ea7f267ee7ad3 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -88,7 +88,7 @@ void __init kvm_hyp_reserve(void) static void __pkvm_destroy_hyp_vm(struct kvm *kvm) { if (pkvm_hyp_vm_is_created(kvm)) { - WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, + WARN_ON(kvm_call_hyp_nvhe(__pkvm_finalize_teardown_vm, kvm->arch.pkvm.handle)); } else if (kvm->arch.pkvm.handle) { /* @@ -356,6 +356,11 @@ void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, if (!handle) return; + if (pkvm_hyp_vm_is_created(kvm) && !kvm->arch.pkvm.is_dying) { + WARN_ON(kvm_call_hyp_nvhe(__pkvm_start_teardown_vm, handle)); + kvm->arch.pkvm.is_dying = true; + } + __pkvm_pgtable_stage2_unshare(pgt, addr, addr + size); }