[PATCH v4 13/17] KVM: arm64: Alloc pkvm_hyp_vm using pKVM heap allocator
Fuad Tabba
fuad.tabba at linux.dev
Mon Aug 17 06:38:51 PDT 2026
On Fri, 31 Jul 2026 at 15:36, Vincent Donnefort <vdonnefort at google.com> wrote:
>
> Transition the allocation of the hypervisor VM state structure
> (pkvm_hyp_vm) from the host to the hypervisor using
> the new pKVM heap allocator (hyp_alloc()).
>
> Previously, the host was responsible for calculating the size of,
> allocating, and donating memory for pkvm_hyp_vm during VM creation. With
> the heap allocator in place, the hypervisor now allocates this structure
> dynamically at EL2.
>
> Use the pkvm_call_hyp_req() wrapper in the host to invoke
> __pkvm_init_vm, which automatically handles any top-up requests if the
> hypervisor runs out of heap memory during allocation.
>
> Tested-by: Fuad Tabba <fuad.tabba at linux.dev>
> Signed-off-by: Vincent Donnefort <vdonnefort at google.com>
Reviewed-by: Fuad Tabba <fuad.tabba at linux.dev>
Cheers,
/fuad
>
> diff --git a/arch/arm64/kvm/hyp/hyp-constants.c b/arch/arm64/kvm/hyp/hyp-constants.c
> index b257a3b4bfc5..501ab35a3840 100644
> --- a/arch/arm64/kvm/hyp/hyp-constants.c
> +++ b/arch/arm64/kvm/hyp/hyp-constants.c
> @@ -7,7 +7,6 @@
> int main(void)
> {
> DEFINE(STRUCT_HYP_PAGE_SIZE, sizeof(struct hyp_page));
> - DEFINE(PKVM_HYP_VM_SIZE, sizeof(struct pkvm_hyp_vm));
> DEFINE(PKVM_HYP_VCPU_SIZE, sizeof(struct pkvm_hyp_vcpu));
> return 0;
> }
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> index 624367d0ef5b..8e930c8729af 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> @@ -82,8 +82,7 @@ void pkvm_hyp_vm_table_init(void *tbl);
>
> int __pkvm_reserve_vm(void);
> void __pkvm_unreserve_vm(pkvm_handle_t handle);
> -int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
> - unsigned long pgd_hva);
> +int __pkvm_init_vm(struct kvm *host_kvm, void *pgd);
> int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu,
> unsigned long vcpu_hva);
>
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index d99c9b1b0c82..c1aa6d773c26 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -575,14 +575,35 @@ static void handle___pkvm_unreserve_vm(struct kvm_cpu_context *host_ctxt)
> __pkvm_unreserve_vm(handle);
> }
>
> +static void errno_to_smccc(int ret, struct kvm_cpu_context *host_ctxt)
> +{
> + struct pkvm_hyp_req req = { .type = PKVM_HYP_NO_REQ };
> +
> + switch (ret) {
> + case -ENOMEM: {
> + u32 nr_pages = hyp_alloc_topup_needed();
> +
> + if (nr_pages) {
> + req.type = PKVM_HYP_REQ_HYP_ALLOC;
> + req.mem.nr_pages = nr_pages;
> + }
> + break;
> + }
> + }
> +
> + cpu_reg(host_ctxt, 1) = ret;
> + pkvm_hyp_req_to_smccc(host_ctxt, &req);
> +}
> +
> static void handle___pkvm_init_vm(struct kvm_cpu_context *host_ctxt)
> {
> DECLARE_REG(struct kvm *, host_kvm, host_ctxt, 1);
> - DECLARE_REG(unsigned long, vm_hva, host_ctxt, 2);
> - DECLARE_REG(unsigned long, pgd_hva, host_ctxt, 3);
> + DECLARE_REG(unsigned long, pgd_hva, host_ctxt, 2);
> + void *pgd;
>
> host_kvm = kern_hyp_va(host_kvm);
> - cpu_reg(host_ctxt, 1) = __pkvm_init_vm(host_kvm, vm_hva, pgd_hva);
> + pgd = (void *)kern_hyp_va(pgd_hva);
> + errno_to_smccc(__pkvm_init_vm(host_kvm, pgd), host_ctxt);
> }
>
> static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt)
> diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> index 079d6f397893..09f609db8556 100644
> --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> @@ -11,6 +11,7 @@
>
> #include <asm/kvm_emulate.h>
>
> +#include <nvhe/alloc.h>
> #include <nvhe/mem_protect.h>
> #include <nvhe/memory.h>
> #include <nvhe/pkvm.h>
> @@ -797,24 +798,22 @@ void teardown_selftest_vm(void)
> * Unmap the donated memory from the host at stage 2.
> *
> * host_kvm: A pointer to the host's struct kvm.
> - * vm_hva: The host va of the area being donated for the VM state.
> - * Must be page aligned.
> - * pgd_hva: The host va of the area being donated for the stage-2 PGD for
> - * the VM. Must be page aligned. Its size is implied by the VM's
> - * VTCR.
> + * pgd: The va of the area being donated for the stage-2 PGD for the VM. Must
> + * be page aligned. Its size is implied by the VM's VTCR.
> *
> * Return 0 success, negative error code on failure.
> */
> -int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
> - unsigned long pgd_hva)
> +int __pkvm_init_vm(struct kvm *host_kvm, void *pgd)
> {
> struct pkvm_hyp_vm *hyp_vm = NULL;
> size_t vm_size, pgd_size;
> unsigned int nr_vcpus;
> pkvm_handle_t handle;
> - void *pgd = NULL;
> int ret;
>
> + if (!PAGE_ALIGNED(pgd))
> + return -EINVAL;
> +
> ret = hyp_pin_shared_mem(host_kvm, host_kvm + 1);
> if (ret)
> return ret;
> @@ -834,15 +833,15 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
> vm_size = pkvm_get_hyp_vm_size(nr_vcpus);
> pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.mmu.vtcr);
>
> - ret = -ENOMEM;
> + hyp_vm = hyp_alloc(vm_size);
> + if (!hyp_vm) {
> + ret = hyp_alloc_errno();
> + goto err_unpin_kvm;
> + }
>
> - hyp_vm = map_donated_memory(vm_hva, vm_size);
> - if (!hyp_vm)
> - goto err_remove_mappings;
> -
> - pgd = map_donated_memory_noclear(pgd_hva, pgd_size);
> - if (!pgd)
> - goto err_remove_mappings;
> + ret = __pkvm_host_donate_hyp(hyp_virt_to_pfn(pgd), PAGE_ALIGN(pgd_size) >> PAGE_SHIFT);
> + if (ret)
> + goto err_free_hyp_vm;
>
> init_pkvm_hyp_vm(host_kvm, hyp_vm, nr_vcpus, handle);
>
> @@ -860,8 +859,9 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
> err_destroy_stage2:
> kvm_guest_destroy_stage2(hyp_vm);
> err_remove_mappings:
> - unmap_donated_memory(hyp_vm, vm_size);
> unmap_donated_memory(pgd, pgd_size);
> +err_free_hyp_vm:
> + hyp_free(hyp_vm);
> err_unpin_kvm:
> hyp_unpin_shared_mem(host_kvm, host_kvm + 1);
> return ret;
> @@ -997,7 +997,6 @@ int __pkvm_finalize_teardown_vm(pkvm_handle_t handle)
> struct pkvm_hyp_vm *hyp_vm;
> struct kvm *host_kvm;
> unsigned int idx;
> - size_t vm_size;
> int err;
>
> hyp_spin_lock(&vm_table_lock);
> @@ -1040,8 +1039,7 @@ int __pkvm_finalize_teardown_vm(pkvm_handle_t handle)
> teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu));
> }
>
> - vm_size = pkvm_get_hyp_vm_size(hyp_vm->kvm.created_vcpus);
> - teardown_donated_memory(mc, hyp_vm, vm_size);
> + hyp_free(hyp_vm);
> hyp_unpin_shared_mem(host_kvm, host_kvm + 1);
> return 0;
>
> diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
> index bfbb1266491d..a9b85ad37787 100644
> --- a/arch/arm64/kvm/pkvm.c
> +++ b/arch/arm64/kvm/pkvm.c
> @@ -191,8 +191,8 @@ static int __pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu)
> */
> static int __pkvm_create_hyp_vm(struct kvm *kvm)
> {
> - size_t pgd_sz, hyp_vm_sz;
> - void *pgd, *hyp_vm;
> + size_t pgd_sz;
> + void *pgd;
> int ret;
>
> if (kvm->created_vcpus < 1)
> @@ -209,28 +209,15 @@ static int __pkvm_create_hyp_vm(struct kvm *kvm)
> if (!pgd)
> return -ENOMEM;
>
> - /* Allocate memory to donate to hyp for vm and vcpu pointers. */
> - hyp_vm_sz = PAGE_ALIGN(size_add(PKVM_HYP_VM_SIZE,
> - size_mul(sizeof(void *),
> - kvm->created_vcpus)));
> - hyp_vm = alloc_pages_exact(hyp_vm_sz, GFP_KERNEL_ACCOUNT);
> - if (!hyp_vm) {
> - ret = -ENOMEM;
> - goto free_pgd;
> - }
> -
> - /* Donate the VM memory to hyp and let hyp initialize it. */
> - ret = kvm_call_hyp_nvhe(__pkvm_init_vm, kvm, hyp_vm, pgd);
> + ret = pkvm_call_hyp_req(__pkvm_init_vm, kvm, pgd);
> if (ret)
> - goto free_vm;
> + goto free_pgd;
>
> kvm->arch.pkvm.is_created = true;
> init_hyp_stage2_memcache(&kvm->arch.pkvm.stage2_teardown_mc);
> kvm_account_pgtable_pages(pgd, pgd_sz / PAGE_SIZE);
>
> return 0;
> -free_vm:
> - free_pages_exact(hyp_vm, hyp_vm_sz);
> free_pgd:
> free_pages_exact(pgd, pgd_sz);
> return ret;
> --
> 2.55.0.508.g3f0d502094-goog
>
More information about the linux-arm-kernel
mailing list