[PATCH v3 19/23] KVM: arm64: Add __pkvm_host_split_guest HVC
Vincent Donnefort
vdonnefort at google.com
Mon Nov 2 12:46:24 PST 2026
This HVC allows the host to break an existing block in a protected VM. This
will later allow the guest to share a sub-region of an existing
huge-mapping with the host.
Signed-off-by: Vincent Donnefort <vdonnefort at google.com>
---
arch/arm64/include/asm/kvm_asm.h | 1 +
arch/arm64/include/asm/kvm_hcall.h | 2 +
arch/arm64/kvm/hyp/include/nvhe/mem_protect.h | 1 +
arch/arm64/kvm/hyp/nvhe/hyp-main.c | 18 +++
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 127 ++++++++++++++++--
5 files changed, 136 insertions(+), 13 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 872185f9ac53..9efbd3b50901 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -112,6 +112,7 @@ enum __kvm_host_smccc_func {
__KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
__KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
__KVM_HOST_SMCCC_FUNC___pkvm_host_mkyoung_guest,
+ __KVM_HOST_SMCCC_FUNC___pkvm_host_split_guest,
__KVM_HOST_SMCCC_FUNC___pkvm_reserve_vm,
__KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm,
__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
diff --git a/arch/arm64/include/asm/kvm_hcall.h b/arch/arm64/include/asm/kvm_hcall.h
index e54a4631a378..94eecb24d2c5 100644
--- a/arch/arm64/include/asm/kvm_hcall.h
+++ b/arch/arm64/include/asm/kvm_hcall.h
@@ -234,6 +234,8 @@ DECLARE_KVM_HOST_HCALL(int, __pkvm_host_test_clear_young_guest,
pkvm_handle_t, handle, u64, gfn, u64, nr_pages, bool, mkold)
DECLARE_KVM_HOST_HCALL(int, __pkvm_host_mkyoung_guest,
u64, gfn)
+DECLARE_KVM_HOST_HCALL(int, __pkvm_host_split_guest,
+ u64, gfn, u64, nr_pages)
DECLARE_KVM_HOST_HCALL0(int, __pkvm_reserve_vm)
DECLARE_KVM_HOST_HCALL(void, __pkvm_unreserve_vm,
pkvm_handle_t, handle)
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index a991be3d4c9a..c82b1d6352d5 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -50,6 +50,7 @@ int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_
int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm);
int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm);
int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu);
+int __pkvm_host_split_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu);
bool addr_is_memory(phys_addr_t phys);
bool addr_is_hyp_text(phys_addr_t phys);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 41817f45115d..e7b798253dc3 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -1072,6 +1072,23 @@ DEFINE_KVM_HOST_HCALL(int, __pkvm_host_mkyoung_guest,
return __pkvm_host_mkyoung_guest(gfn, hyp_vcpu);
}
+DEFINE_KVM_HOST_HCALL(int, __pkvm_host_split_guest,
+ u64, gfn, u64, nr_pages)
+{
+ struct pkvm_hyp_vcpu *hyp_vcpu;
+ int ret;
+
+ hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+ if (!hyp_vcpu || !pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+ return -EINVAL;
+
+ ret = pkvm_refill_memcache(hyp_vcpu);
+ if (ret)
+ return ret;
+
+ return __pkvm_host_split_guest(gfn, nr_pages, hyp_vcpu);
+}
+
/*
* PKVM_HOST_STATE_DIRTY names the authoritative copy, the host's when set.
* A loaded protected vCPU takes the request at its next entry instead.
@@ -1599,6 +1616,7 @@ static const hcall_t host_hcall[] = {
HANDLE_FUNC(__pkvm_host_wrprotect_guest),
HANDLE_FUNC(__pkvm_host_test_clear_young_guest),
HANDLE_FUNC(__pkvm_host_mkyoung_guest),
+ HANDLE_FUNC(__pkvm_host_split_guest),
HANDLE_FUNC(__pkvm_reserve_vm),
HANDLE_FUNC(__pkvm_unreserve_vm),
HANDLE_FUNC(__pkvm_init_vm),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 88af0aec1ea9..7ecf4c98d7b5 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -589,6 +589,12 @@ static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_
#define KVM_HOST_DONATION_PTE_OWNER_MASK GENMASK(3, 1)
#define KVM_HOST_DONATION_PTE_EXTRA_MASK GENMASK(59, 4)
+static kvm_pte_t host_stage2_encode_annotation(u8 owner_id, u64 meta)
+{
+ return FIELD_PREP(KVM_HOST_DONATION_PTE_OWNER_MASK, owner_id) |
+ FIELD_PREP(KVM_HOST_DONATION_PTE_EXTRA_MASK, meta);
+}
+
static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size,
u8 owner_id, u64 meta)
{
@@ -607,8 +613,7 @@ static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size,
if (!FIELD_FIT(KVM_HOST_DONATION_PTE_EXTRA_MASK, meta))
return -EINVAL;
- annotation = FIELD_PREP(KVM_HOST_DONATION_PTE_OWNER_MASK, owner_id) |
- FIELD_PREP(KVM_HOST_DONATION_PTE_EXTRA_MASK, meta);
+ annotation = host_stage2_encode_annotation(owner_id, meta);
ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt,
addr, size, &host_s2_pool,
KVM_HOST_INVALID_PTE_TYPE_DONATION, annotation);
@@ -672,10 +677,8 @@ static u64 host_stage2_encode_gfn_meta(struct pkvm_hyp_vm *vm, u64 gfn)
FIELD_PREP(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, gfn);
}
-static int host_stage2_decode_gfn_meta(kvm_pte_t pte, struct pkvm_hyp_vm **vm,
- u64 *gfn)
+static int host_stage2_decode_gfn_meta(kvm_pte_t pte, pkvm_handle_t *handle, u64 *gfn)
{
- pkvm_handle_t handle;
u64 meta;
if (WARN_ON(kvm_pte_valid(pte)))
@@ -690,17 +693,59 @@ static int host_stage2_decode_gfn_meta(kvm_pte_t pte, struct pkvm_hyp_vm **vm,
return -EPERM;
meta = FIELD_GET(KVM_HOST_DONATION_PTE_EXTRA_MASK, pte);
- handle = FIELD_GET(KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK, meta);
- *vm = get_vm_by_handle(handle);
- if (!*vm) {
- /* We probably raced with teardown; try again */
- return -EAGAIN;
- }
-
+ *handle = FIELD_GET(KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK, meta);
*gfn = FIELD_GET(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, meta);
return 0;
}
+static int host_stage2_split_gfn_meta(phys_addr_t phys, u64 ipa, u64 size, struct pkvm_hyp_vm *vm)
+{
+ struct kvm_pgtable_mm_ops *mm_ops = &host_mmu.mm_ops;
+ struct kvm_pgtable *pgt = &host_mmu.pgt;
+ kvm_pte_t pte, *table, *ptep;
+ pkvm_handle_t handle;
+ s8 level;
+ u64 gfn;
+ int ret;
+
+ ret = kvm_pgtable_get_leaf(pgt, phys, &pte, &level, 0);
+ if (ret)
+ return ret;
+
+ if (kvm_granule_size(level) != size)
+ return -EINVAL;
+
+ ret = host_stage2_decode_gfn_meta(pte, &handle, &gfn);
+ if (ret)
+ return ret;
+
+ if (handle != vm->kvm.arch.pkvm.handle || gfn != (ipa >> PAGE_SHIFT))
+ return -EINVAL;
+
+ table = mm_ops->zalloc_page(&host_s2_pool);
+ if (!table)
+ return -ENOMEM;
+
+ ptep = table;
+ while (ptep < table + PTRS_PER_PTE) {
+ u64 meta = host_stage2_encode_gfn_meta(vm, gfn);
+ kvm_pte_t annotation = host_stage2_encode_annotation(PKVM_ID_GUEST, meta);
+
+ *ptep = FIELD_PREP(KVM_INVALID_PTE_TYPE_MASK, KVM_HOST_INVALID_PTE_TYPE_DONATION) |
+ annotation;
+
+ mm_ops->get_page(ptep);
+ ptep++;
+ gfn++;
+ }
+
+ ret = kvm_pgtable_stage2_table_install(pgt, phys, size, table);
+ if (ret)
+ kvm_pgtable_stage2_free_unlinked(mm_ops, table, level);
+
+ return ret;
+}
+
static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
{
/*
@@ -1351,6 +1396,7 @@ static int host_stage2_get_guest_info(phys_addr_t phys, u64 *size, struct pkvm_h
u64 *gfn)
{
enum pkvm_page_state state;
+ pkvm_handle_t handle;
kvm_pte_t pte;
s8 level;
int ret;
@@ -1379,10 +1425,16 @@ static int host_stage2_get_guest_info(phys_addr_t phys, u64 *size, struct pkvm_h
if (level < KVM_PGTABLE_LAST_LEVEL - 1)
return -E2BIG;
- ret = host_stage2_decode_gfn_meta(pte, vm, gfn);
+ ret = host_stage2_decode_gfn_meta(pte, &handle, gfn);
if (ret)
return ret;
+ *vm = get_vm_by_handle(handle);
+ if (!*vm) {
+ /* We probably raced with teardown; try again */
+ return -EAGAIN;
+ }
+
*size = kvm_granule_size(level);
return 0;
@@ -1778,6 +1830,55 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
return 0;
}
+int __pkvm_host_split_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu)
+{
+ struct kvm_hyp_memcache *mc = &vcpu->vcpu.arch.stage2_mc;
+ struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+ u64 size = nr_pages << PAGE_SHIFT;
+ u64 ipa = hyp_pfn_to_phys(gfn);
+ kvm_pte_t pte, *table;
+ phys_addr_t phys;
+ s8 level;
+ int ret;
+
+ if (!mc->nr_pages)
+ return -ENOMEM;
+
+ if (size != PMD_SIZE || !IS_ALIGNED(ipa, PMD_SIZE))
+ return -EINVAL;
+
+ level = KVM_PGTABLE_LAST_LEVEL - 1;
+
+ host_lock_component();
+ guest_lock_component(vm);
+
+ ret = get_valid_guest_pte(vm, ipa, size, &pte, &phys);
+ if (ret)
+ goto unlock;
+
+ table = kvm_pgtable_stage2_create_unlinked(&vm->pgt, kvm_pte_to_phys(pte), level,
+ kvm_pgtable_stage2_pte_prot(pte),
+ mc, true);
+ if (IS_ERR(table)) {
+ ret = PTR_ERR(table);
+ goto unlock;
+ }
+
+ ret = host_stage2_split_gfn_meta(phys, ipa, size, vm);
+ if (ret) {
+ kvm_pgtable_stage2_free_unlinked(&vm->mm_ops, table, level);
+ goto unlock;
+ }
+
+ WARN_ON(kvm_pgtable_stage2_table_install(&vm->pgt, ipa, size, table));
+
+unlock:
+ guest_unlock_component(vm);
+ host_unlock_component();
+
+ return ret;
+}
+
#ifdef CONFIG_NVHE_EL2_DEBUG
struct pkvm_expected_state {
enum pkvm_page_state host;
--
2.56.0.385.gac671c819a-goog
More information about the linux-arm-kernel
mailing list