* [PATCH v5 1/5] KVM: arm64: Pass walk flags to kvm_pgtable_get_leaf()
2026-06-12 16:23 [PATCH v5 0/5] KVM: arm64: Add KVM_PRE_FAULT_MEMORY support Jack Thomson
@ 2026-06-12 16:23 ` Jack Thomson
2026-06-12 16:23 ` [PATCH v5 2/5] KVM: arm64: Add pre_fault_memory implementation Jack Thomson
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Jack Thomson @ 2026-06-12 16:23 UTC (permalink / raw)
To: maz, oupton, pbonzini
Cc: joey.gouly, seiden, suzuki.poulose, yuzenghui, catalin.marinas,
will, shuah, corbet, vladimir.murzin, linux-arm-kernel, kvmarm,
kvm, linux-kernel, linux-kselftest, linux-doc, isaku.yamahata,
Jack Thomson
From: Jack Thomson <jackabt@amazon.com>
Allow callers of kvm_pgtable_get_leaf() to specify the page-table walk
flags, in preparation for performing walks under the MMU read lock.
Reading a stage-2 leaf while only holding the read lock requires
KVM_PGTABLE_WALK_SHARED: parallel faults (which also only hold the read
lock) can unlink table pages and free them via RCU, so the walker must
be inside an RCU read-side critical section, which the shared walk flag
provides via kvm_pgtable_walk_begin().
All existing callers either hold the write lock, walk with interrupts
disabled, or run at hyp where shared walks are rejected; they keep the
current behaviour by passing no flags.
No functional change intended.
Signed-off-by: Jack Thomson <jackabt@amazon.com>
---
arch/arm64/include/asm/kvm_pgtable.h | 5 ++++-
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 10 +++++-----
arch/arm64/kvm/hyp/pgtable.c | 5 +++--
arch/arm64/kvm/mmu.c | 2 +-
arch/arm64/kvm/nested.c | 2 +-
5 files changed, 14 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 41a8687938eb..d0167f7dfbee 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -859,6 +859,8 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
* @addr: Input address for the start of the walk.
* @ptep: Pointer to storage for the retrieved PTE.
* @level: Pointer to storage for the level of the retrieved PTE.
+ * @flags: Flags to control the page-table walk
+ * (see struct kvm_pgtable_visit_ctx).
*
* The offset of @addr within a page is ignored.
*
@@ -869,7 +871,8 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
* Return: 0 on success, negative error code on failure.
*/
int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
- kvm_pte_t *ptep, s8 *level);
+ kvm_pte_t *ptep, s8 *level,
+ enum kvm_pgtable_walk_flags flags);
/**
* kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 25f04629014e..3b765c9ff7e8 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -522,7 +522,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
int ret;
hyp_assert_lock_held(&host_mmu.lock);
- ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr, &pte, &level);
+ ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr, &pte, &level, 0);
if (ret)
return ret;
@@ -890,7 +890,7 @@ static int get_valid_guest_pte(struct pkvm_hyp_vm *vm, u64 ipa, kvm_pte_t *ptep,
s8 level;
int ret;
- ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
+ ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
if (ret)
return ret;
if (guest_pte_is_poisoned(pte))
@@ -939,7 +939,7 @@ int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu)
ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(&hyp_vcpu->vcpu));
guest_lock_component(vm);
- ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
+ ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
if (ret)
goto unlock;
@@ -1293,7 +1293,7 @@ static int host_stage2_get_guest_info(phys_addr_t phys, struct pkvm_hyp_vm **vm,
return -EPERM;
}
- ret = kvm_pgtable_get_leaf(&host_mmu.pgt, phys, &pte, &level);
+ ret = kvm_pgtable_get_leaf(&host_mmu.pgt, phys, &pte, &level, 0);
if (ret)
return ret;
@@ -1522,7 +1522,7 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
s8 level;
int ret;
- ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
+ ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
if (ret)
return ret;
if (!kvm_pte_valid(pte))
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0c1defa5fb0f..6a839a32e246 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -298,12 +298,13 @@ static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
}
int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
- kvm_pte_t *ptep, s8 *level)
+ kvm_pte_t *ptep, s8 *level,
+ enum kvm_pgtable_walk_flags flags)
{
struct leaf_walk_data data;
struct kvm_pgtable_walker walker = {
.cb = leaf_walker,
- .flags = KVM_PGTABLE_WALK_LEAF,
+ .flags = flags | KVM_PGTABLE_WALK_LEAF,
.arg = &data,
};
int ret;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 4da9281312eb..c720f07cb82e 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -839,7 +839,7 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
* IPI-ing threads).
*/
local_irq_save(flags);
- ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level);
+ ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level, 0);
local_irq_restore(flags);
if (ret)
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 38f672e94087..e45aed6d9e65 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -559,7 +559,7 @@ static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr)
return 0;
tmp &= ~(sz - 1);
- if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL))
+ if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL, 0))
goto again;
if (!(pte & PTE_VALID))
goto again;
--
2.43.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v5 2/5] KVM: arm64: Add pre_fault_memory implementation
2026-06-12 16:23 [PATCH v5 0/5] KVM: arm64: Add KVM_PRE_FAULT_MEMORY support Jack Thomson
2026-06-12 16:23 ` [PATCH v5 1/5] KVM: arm64: Pass walk flags to kvm_pgtable_get_leaf() Jack Thomson
@ 2026-06-12 16:23 ` Jack Thomson
2026-06-12 16:23 ` [PATCH v5 3/5] KVM: selftests: Enable pre_fault_memory_test for arm64 Jack Thomson
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Jack Thomson @ 2026-06-12 16:23 UTC (permalink / raw)
To: maz, oupton, pbonzini
Cc: joey.gouly, seiden, suzuki.poulose, yuzenghui, catalin.marinas,
will, shuah, corbet, vladimir.murzin, linux-arm-kernel, kvmarm,
kvm, linux-kernel, linux-kselftest, linux-doc, isaku.yamahata,
Jack Thomson
From: Jack Thomson <jackabt@amazon.com>
Add arm64 support for KVM_PRE_FAULT_MEMORY by synthesizing a read data
abort and routing it through the existing stage-2 fault handlers. Treat
the requested GPA as an IPA in the userspace-owned VM's memslot space
and always target the canonical stage-2, even if the vCPU last ran with
a nested/shadow MMU selected.
If the vCPU last ran in a nested context, switch to the canonical
stage-2 with the vCPU put/load helpers so VMID, VNCR and shadow-MMU
refcount state stay consistent. Leave the switch in place for the ioctl;
vcpu_put() at ioctl exit drops the hw_mmu and the next vcpu_load()
reselects the correct MMU from vCPU state.
Check existing mappings with a shared page-table walk under the MMU read
lock, and use the resulting walk level when constructing the synthetic
fault. Report poisoned pages through the ioctl return path with
-EHWPOISON instead of also queueing SIGBUS, and use the installed
mapping size to advance the prefault range.
Advertise KVM_CAP_PRE_FAULT_MEMORY on arm64. Protected VMs remain
unsupported: pKVM filters the capability, and the ioctl returns
-EOPNOTSUPP if invoked anyway.
Signed-off-by: Jack Thomson <jackabt@amazon.com>
---
Documentation/virt/kvm/api.rst | 18 +++-
arch/arm64/kvm/Kconfig | 1 +
arch/arm64/kvm/arm.c | 1 +
arch/arm64/kvm/mmu.c | 162 +++++++++++++++++++++++++++++++++
4 files changed, 178 insertions(+), 4 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 52bbbb553ce1..657e05656fa6 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6462,7 +6462,7 @@ See KVM_SET_USER_MEMORY_REGION2 for additional details.
---------------------------
:Capability: KVM_CAP_PRE_FAULT_MEMORY
-:Architectures: none
+:Architectures: x86, arm64
:Type: vcpu ioctl
:Parameters: struct kvm_pre_fault_memory (in/out)
:Returns: 0 if at least one page is processed, < 0 on error
@@ -6470,11 +6470,14 @@ See KVM_SET_USER_MEMORY_REGION2 for additional details.
Errors:
========== ===============================================================
+ EAGAIN A memslot update raced with the ioctl before any page was
+ processed.
EINVAL The specified `gpa` and `size` were invalid (e.g. not
page aligned, causes an overflow, or size is zero).
ENOENT The specified `gpa` is outside defined memslots.
EINTR An unmasked signal is pending and no page was processed.
EFAULT The parameter address was invalid.
+ EHWPOISON A poisoned host page was encountered.
EOPNOTSUPP Mapping memory for a GPA is unsupported by the
hypervisor, and/or for the current vCPU state/mode.
EIO unexpected error conditions (also causes a WARN)
@@ -6494,7 +6497,14 @@ Errors:
KVM_PRE_FAULT_MEMORY populates KVM's stage-2 page tables used to map memory
for the current vCPU state. KVM maps memory as if the vCPU generated a
stage-2 read page fault, e.g. faults in memory as needed, but doesn't break
-CoW. However, KVM does not mark any newly created stage-2 PTE as Accessed.
+CoW. However, on x86, KVM does not mark any newly created stage-2 PTE as
+Accessed. On arm64, newly created stage-2 PTEs are marked Accessed.
+
+On arm64, `gpa` is interpreted as an IPA in the userspace-owned VM's
+memslot address space. If the vCPU most recently ran a nested guest, KVM
+still targets the VM's canonical stage-2, and does not interpret `gpa` as
+a nested guest IPA or target the nested/shadow stage-2 selected by the
+vCPU's last run state.
In the case of confidential VM types where there is an initial set up of
private guest memory before the guest is 'finalized'/measured, this ioctl
@@ -6507,9 +6517,9 @@ case, the ioctl can be called in parallel.
When the ioctl returns, the input values are updated to point to the
remaining range. If `size` > 0 on return, the caller can just issue
-the ioctl again with the same `struct kvm_map_memory` argument.
+the ioctl again with the same `struct kvm_pre_fault_memory` argument.
-Shadow page tables cannot support this ioctl because they
+On x86, shadow page tables cannot support this ioctl because they
are indexed by virtual address or nested guest physical address.
Calling this ioctl when the guest is using shadow page tables (for
example because it is running a nested guest with nested page tables)
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 449154f9a485..6b89262e8ba7 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -24,6 +24,7 @@ menuconfig KVM
select HAVE_KVM_CPU_RELAX_INTERCEPT
select KVM_MMIO
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ select KVM_GENERIC_PRE_FAULT_MEMORY
select VIRT_XFER_TO_GUEST_WORK
select KVM_VFIO
select HAVE_KVM_DIRTY_RING_ACQ_REL
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 9453321ef8c6..dcb92bee13af 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -392,6 +392,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_COUNTER_OFFSET:
case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS:
case KVM_CAP_ARM_SEA_TO_USER:
+ case KVM_CAP_PRE_FAULT_MEMORY:
r = 1;
break;
case KVM_CAP_SET_GUEST_DEBUG2:
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c720f07cb82e..4bf048bbcf8b 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1571,6 +1571,8 @@ struct kvm_s2_fault_desc {
struct kvm_s2_trans *nested;
struct kvm_memory_slot *memslot;
unsigned long hva;
+ unsigned long *page_size;
+ bool prefault;
};
static int gmem_abort(const struct kvm_s2_fault_desc *s2fd)
@@ -1882,6 +1884,13 @@ static int kvm_s2_fault_pin_pfn(const struct kvm_s2_fault_desc *s2fd,
&s2vi->map_writable, &s2vi->page);
if (unlikely(is_error_noslot_pfn(s2vi->pfn))) {
if (s2vi->pfn == KVM_PFN_ERR_HWPOISON) {
+ /*
+ * When prefaulting, report the poison via -EHWPOISON
+ * only; don't also queue a SIGBUS as the run path
+ * does for the faulting vCPU thread.
+ */
+ if (s2fd->prefault)
+ return -EHWPOISON;
kvm_send_hwpoison_signal(s2fd->hva, __ffs(s2vi->vma_pagesize));
return 0;
}
@@ -2053,6 +2062,9 @@ static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
kvm_release_faultin_page(kvm, s2vi->page, !!ret, writable);
kvm_fault_unlock(kvm);
+ if (s2fd->page_size && !ret)
+ *s2fd->page_size = mapping_size;
+
/*
* Mark the page dirty only if the fault is handled successfully,
* making sure we adjust the canonical IPA if the mapping size has
@@ -2757,3 +2769,153 @@ void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
}
+
+/*
+ * Prefaulting always targets the canonical stage-2. If the vCPU last ran
+ * in a nested context, swap in the canonical MMU via the vCPU put/load
+ * helpers so that preemption, VMID, VNCR fixmap and shadow-MMU refcount
+ * state stay consistent.
+ *
+ * The swap is deliberately not undone: nothing runs in between the
+ * per-page invocations of kvm_arch_vcpu_pre_fault_memory() except the
+ * generic prefault loop, and the vcpu_put() at ioctl exit discards
+ * vcpu->arch.hw_mmu anyway (see kvm_vcpu_put_hw_mmu()), so the next
+ * vcpu_load() re-derives the correct MMU from the vCPU's context. If the
+ * prefault task is preempted in the meantime, kvm_vcpu_put_hw_mmu()
+ * keeps the canonical MMU in place for the reload. Leaving the swap in
+ * place also bounds the cost to at most one put/load pair per ioctl,
+ * rather than two pairs per prefaulted page.
+ */
+static void kvm_pre_fault_load_canonical_mmu(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu_has_nv(vcpu) || vcpu->arch.hw_mmu == &vcpu->kvm->arch.mmu)
+ return;
+
+ preempt_disable();
+ kvm_arch_vcpu_put(vcpu);
+ vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+ kvm_arch_vcpu_load(vcpu, smp_processor_id());
+ preempt_enable();
+}
+
+long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
+ struct kvm_pre_fault_memory *range)
+{
+ struct kvm_vcpu_fault_info *fault_info = &vcpu->arch.fault;
+ struct kvm_vcpu_fault_info fault_backup = *fault_info;
+ s8 walk_level = KVM_PGTABLE_LAST_LEVEL;
+ unsigned long page_size = PAGE_SIZE;
+ struct kvm_memory_slot *memslot;
+ phys_addr_t gpa = range->gpa;
+ struct kvm_pgtable *pgt;
+ phys_addr_t end;
+ kvm_pte_t pte;
+ hva_t hva;
+ gfn_t gfn;
+ long ret;
+
+ if (vcpu_is_protected(vcpu))
+ return -EOPNOTSUPP;
+
+ /*
+ * Interpret range->gpa in the userspace-owned VM's IPA space, not in
+ * any nested guest IPA space that may have been active on the vCPU's
+ * last run. Always target the canonical stage-2.
+ */
+ kvm_pre_fault_load_canonical_mmu(vcpu);
+
+ if (gpa >= kvm_phys_size(vcpu->arch.hw_mmu)) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ gfn = gpa_to_gfn(gpa);
+ memslot = gfn_to_memslot(vcpu->kvm, gfn);
+ if (!memslot) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ /*
+ * A racing memslot deletion or move installs an invalid slot before
+ * zapping stage-2. Ask userspace to retry once the update settles.
+ */
+ if (memslot->flags & KVM_MEMSLOT_INVALID) {
+ ret = -EAGAIN;
+ goto out;
+ }
+
+ /*
+ * pKVM stage-2 mappings aren't directly walkable from the host; let
+ * the fault path handle both new and existing mappings.
+ */
+ if (!is_protected_kvm_enabled()) {
+ pgt = vcpu->arch.hw_mmu->pgt;
+ scoped_guard(read_lock, &vcpu->kvm->mmu_lock) {
+ ret = kvm_pgtable_get_leaf(pgt, gpa, &pte, &walk_level,
+ KVM_PGTABLE_WALK_SHARED);
+ }
+ if (ret)
+ goto out;
+
+ if (kvm_pte_valid(pte)) {
+ page_size = kvm_granule_size(walk_level);
+ if (!(pte & KVM_PTE_LEAF_ATTR_LO_S2_AF))
+ handle_access_fault(vcpu, gpa);
+ goto out_success;
+ }
+ }
+
+ /*
+ * Synthesize a read translation fault for the canonical IPA, at the
+ * level where the stage-2 walk currently ends (the last level under
+ * pKVM, where stage-2 isn't walkable from the host).
+ */
+ fault_info->esr_el2 = (ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT) |
+ ESR_ELx_IL | ESR_ELx_FSC_FAULT_L(walk_level);
+ fault_info->hpfar_el2 = HPFAR_EL2_NS |
+ FIELD_PREP(HPFAR_EL2_FIPA, gpa >> 12);
+
+ struct kvm_s2_fault_desc s2fd = {
+ .vcpu = vcpu,
+ .fault_ipa = gpa,
+ .nested = NULL,
+ .memslot = memslot,
+ .page_size = &page_size,
+ .prefault = true,
+ };
+
+ /*
+ * As in the run path, -EAGAIN from the abort handlers is treated as
+ * progress: either a parallel fault installed the mapping, or a racing
+ * invalidation is in flight and the next access will refault.
+ */
+ if (kvm_slot_has_gmem(memslot)) {
+ ret = gmem_abort(&s2fd);
+ } else {
+ hva = gfn_to_hva_memslot_prot(memslot, gfn, NULL);
+ if (kvm_is_error_hva(hva)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ s2fd.hva = hva;
+ ret = user_mem_abort(&s2fd);
+ }
+
+ if (ret < 0)
+ goto out;
+
+out_success:
+ end = ALIGN_DOWN(gpa, page_size) + page_size;
+ ret = min_t(u64, range->size, end - gpa);
+out:
+ /*
+ * Restore the synthetic fault state so a subsequent KVM_RUN does not
+ * observe it. kvm_handle_mmio_return() runs before guest entry can
+ * refresh fault.esr_el2 from hardware, so leaving the synthetic ESR
+ * in place would corrupt the completion of a pending MMIO exit.
+ */
+ *fault_info = fault_backup;
+ return ret;
+}
--
2.43.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v5 3/5] KVM: selftests: Enable pre_fault_memory_test for arm64
2026-06-12 16:23 [PATCH v5 0/5] KVM: arm64: Add KVM_PRE_FAULT_MEMORY support Jack Thomson
2026-06-12 16:23 ` [PATCH v5 1/5] KVM: arm64: Pass walk flags to kvm_pgtable_get_leaf() Jack Thomson
2026-06-12 16:23 ` [PATCH v5 2/5] KVM: arm64: Add pre_fault_memory implementation Jack Thomson
@ 2026-06-12 16:23 ` Jack Thomson
2026-06-12 16:23 ` [PATCH v5 4/5] KVM: selftests: Add option for different backing in pre-fault tests Jack Thomson
2026-06-12 16:23 ` [PATCH v5 5/5] KVM: selftests: Add nested pre-fault test for arm64 Jack Thomson
4 siblings, 0 replies; 6+ messages in thread
From: Jack Thomson @ 2026-06-12 16:23 UTC (permalink / raw)
To: maz, oupton, pbonzini
Cc: joey.gouly, seiden, suzuki.poulose, yuzenghui, catalin.marinas,
will, shuah, corbet, vladimir.murzin, linux-arm-kernel, kvmarm,
kvm, linux-kernel, linux-kselftest, linux-doc, isaku.yamahata,
Jack Thomson
From: Jack Thomson <jackabt@amazon.com>
Enable the pre_fault_memory_test to run on arm64 by making it work with
different guest page sizes and testing multiple guest configurations.
Update the test_assert to compare against the UCALL_EXIT_REASON, for
portability, as arm64 exits with KVM_EXIT_MMIO while x86 uses
KVM_EXIT_IO.
Signed-off-by: Jack Thomson <jackabt@amazon.com>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../selftests/kvm/pre_fault_memory_test.c | 115 ++++++++++++++----
2 files changed, 92 insertions(+), 24 deletions(-)
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 9118a5a51b89..4609d8f23e38 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -194,6 +194,7 @@ TEST_GEN_PROGS_arm64 += guest_memfd_test
TEST_GEN_PROGS_arm64 += mmu_stress_test
TEST_GEN_PROGS_arm64 += rseq_test
TEST_GEN_PROGS_arm64 += steal_time
+TEST_GEN_PROGS_arm64 += pre_fault_memory_test
TEST_GEN_PROGS_s390 = $(TEST_GEN_PROGS_COMMON)
TEST_GEN_PROGS_s390 += s390/memop
diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
index fcb57fd034e6..9f5f0d1a5db1 100644
--- a/tools/testing/selftests/kvm/pre_fault_memory_test.c
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -11,19 +11,29 @@
#include <kvm_util.h>
#include <processor.h>
#include <pthread.h>
+#include <guest_modes.h>
/* Arbitrarily chosen values */
-#define TEST_SIZE (SZ_2M + PAGE_SIZE)
-#define TEST_NPAGES (TEST_SIZE / PAGE_SIZE)
+#define TEST_BASE_SIZE SZ_2M
#define TEST_SLOT 10
+/* Storage of test info to share with guest code */
+struct test_config {
+ u64 page_size;
+ u64 test_size;
+ u64 test_num_pages;
+};
+
+static struct test_config test_config;
+
static void guest_code(u64 base_gva)
{
volatile u64 val __used;
+ struct test_config *config = &test_config;
int i;
- for (i = 0; i < TEST_NPAGES; i++) {
- u64 *src = (u64 *)(base_gva + i * PAGE_SIZE);
+ for (i = 0; i < config->test_num_pages; i++) {
+ u64 *src = (u64 *)(base_gva + i * config->page_size);
val = *src;
}
@@ -56,7 +66,7 @@ static void *delete_slot_worker(void *__data)
cpu_relax();
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, data->gpa,
- TEST_SLOT, TEST_NPAGES, data->flags);
+ TEST_SLOT, test_config.test_num_pages, data->flags);
return NULL;
}
@@ -149,8 +159,8 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
/*
* Assert success if prefaulting the entire range should succeed, i.e.
* complete with no bytes remaining. Otherwise prefaulting should have
- * failed due to ENOENT (due to RET_PF_EMULATE for emulated MMIO when
- * no memslot exists).
+ * failed due to ENOENT (no memslot exists for the GPA; on x86 this
+ * surfaces via RET_PF_EMULATE).
*/
if (!expected_left)
TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_PRE_FAULT_MEMORY, ret, vcpu->vm);
@@ -159,43 +169,70 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
KVM_PRE_FAULT_MEMORY, ret, vcpu->vm);
}
-static void __test_pre_fault_memory(unsigned long vm_type, bool private)
+struct test_params {
+ unsigned long vm_type;
+ bool private;
+};
+
+static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
{
- gpa_t gpa, gva, alignment, guest_page_size;
+ gpa_t gpa, gva, alignment, guest_page_size, host_page_size;
+ struct test_params *p = arg;
const struct vm_shape shape = {
- .mode = VM_MODE_DEFAULT,
- .type = vm_type,
+ .mode = guest_mode,
+ .type = p->vm_type,
};
struct kvm_vcpu *vcpu;
struct kvm_run *run;
struct kvm_vm *vm;
struct ucall uc;
+ pr_info("Testing guest mode: %s\n", vm_guest_mode_string(guest_mode));
+
vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code);
- alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size;
- gpa = (vm->max_gfn - TEST_NPAGES) * guest_page_size;
+ guest_page_size = vm_guest_mode_params[guest_mode].page_size;
+ host_page_size = getpagesize();
+
+ test_config.page_size = guest_page_size;
+ test_config.test_size = align_up(TEST_BASE_SIZE + test_config.page_size,
+ host_page_size);
+ test_config.test_num_pages = vm_calc_num_guest_pages(vm->mode, test_config.test_size);
+
+ gpa = (vm->max_gfn - test_config.test_num_pages) * test_config.page_size;
alignment = SZ_2M;
+ alignment = max(alignment, host_page_size);
gpa = align_down(gpa, alignment);
gva = gpa & ((1ULL << (vm->va_bits - 1)) - 1);
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, TEST_SLOT,
- TEST_NPAGES, private ? KVM_MEM_GUEST_MEMFD : 0);
- virt_map(vm, gva, gpa, TEST_NPAGES);
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ gpa, TEST_SLOT, test_config.test_num_pages,
+ p->private ? KVM_MEM_GUEST_MEMFD : 0);
+ virt_map(vm, gva, gpa, test_config.test_num_pages);
- if (private)
- vm_mem_set_private(vm, gpa, TEST_SIZE);
+ if (p->private)
+ vm_mem_set_private(vm, gpa, test_config.test_size);
- pre_fault_memory(vcpu, gpa, 0, SZ_2M, 0, private);
- pre_fault_memory(vcpu, gpa, SZ_2M, PAGE_SIZE * 2, PAGE_SIZE, private);
- pre_fault_memory(vcpu, gpa, TEST_SIZE, PAGE_SIZE, PAGE_SIZE, private);
+ pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+ /* Retry the same range after the first prefault attempt. */
+ pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+ pre_fault_memory(vcpu, gpa,
+ test_config.test_size - host_page_size,
+ host_page_size * 2, host_page_size, p->private);
+ pre_fault_memory(vcpu, gpa, test_config.test_size,
+ host_page_size, host_page_size, p->private);
vcpu_args_set(vcpu, 1, gva);
+
+ /* Export the shared variables to the guest. */
+ sync_global_to_guest(vm, test_config);
+
vcpu_run(vcpu);
run = vcpu->run;
- TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
- "Wanted KVM_EXIT_IO, got exit reason: %u (%s)",
+ TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
+ "Wanted %s, got exit reason: %u (%s)",
+ exit_reason_str(UCALL_EXIT_REASON),
run->exit_reason, exit_reason_str(run->exit_reason));
switch (get_ucall(vcpu, &uc)) {
@@ -214,16 +251,46 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private)
static void test_pre_fault_memory(unsigned long vm_type, bool private)
{
+ struct test_params p = {
+ .vm_type = vm_type,
+ .private = private,
+ };
+
if (vm_type && !(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(vm_type))) {
pr_info("Skipping tests for vm_type 0x%lx\n", vm_type);
return;
}
- __test_pre_fault_memory(vm_type, private);
+ for_each_guest_mode(__test_pre_fault_memory, &p);
+}
+
+static void help(char *name)
+{
+ puts("");
+ printf("usage: %s [-h] [-m mode]\n", name);
+ puts("");
+ guest_modes_help();
+ puts("");
}
int main(int argc, char *argv[])
{
+ int opt;
+
+ guest_modes_append_default();
+
+ while ((opt = getopt(argc, argv, "hm:")) != -1) {
+ switch (opt) {
+ case 'm':
+ guest_modes_cmdline(optarg);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ exit(0);
+ }
+ }
+
TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));
test_pre_fault_memory(0, false);
--
2.43.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v5 4/5] KVM: selftests: Add option for different backing in pre-fault tests
2026-06-12 16:23 [PATCH v5 0/5] KVM: arm64: Add KVM_PRE_FAULT_MEMORY support Jack Thomson
` (2 preceding siblings ...)
2026-06-12 16:23 ` [PATCH v5 3/5] KVM: selftests: Enable pre_fault_memory_test for arm64 Jack Thomson
@ 2026-06-12 16:23 ` Jack Thomson
2026-06-12 16:23 ` [PATCH v5 5/5] KVM: selftests: Add nested pre-fault test for arm64 Jack Thomson
4 siblings, 0 replies; 6+ messages in thread
From: Jack Thomson @ 2026-06-12 16:23 UTC (permalink / raw)
To: maz, oupton, pbonzini
Cc: joey.gouly, seiden, suzuki.poulose, yuzenghui, catalin.marinas,
will, shuah, corbet, vladimir.murzin, linux-arm-kernel, kvmarm,
kvm, linux-kernel, linux-kselftest, linux-doc, isaku.yamahata,
Jack Thomson
From: Jack Thomson <jackabt@amazon.com>
Add a -s option to specify different memory backing types for the
pre-fault tests (e.g. anonymous, hugetlb), allowing testing of the
pre-fault functionality across different memory configurations.
Signed-off-by: Jack Thomson <jackabt@amazon.com>
---
.../selftests/kvm/pre_fault_memory_test.c | 51 +++++++++++++------
1 file changed, 36 insertions(+), 15 deletions(-)
diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
index 9f5f0d1a5db1..c850cf28e86a 100644
--- a/tools/testing/selftests/kvm/pre_fault_memory_test.c
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -45,6 +45,7 @@ struct slot_worker_data {
struct kvm_vm *vm;
gpa_t gpa;
u32 flags;
+ enum vm_mem_backing_src_type mem_backing_src;
bool worker_ready;
bool prefault_ready;
bool recreate_slot;
@@ -65,14 +66,16 @@ static void *delete_slot_worker(void *__data)
while (!READ_ONCE(data->recreate_slot))
cpu_relax();
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, data->gpa,
+ vm_userspace_mem_region_add(vm, data->mem_backing_src, data->gpa,
TEST_SLOT, test_config.test_num_pages, data->flags);
return NULL;
}
static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
- u64 size, u64 expected_left, bool private)
+ u64 size, u64 expected_left,
+ enum vm_mem_backing_src_type mem_backing_src,
+ bool private)
{
struct kvm_pre_fault_memory range = {
.gpa = base_gpa + offset,
@@ -83,6 +86,7 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
.vm = vcpu->vm,
.gpa = base_gpa,
.flags = private ? KVM_MEM_GUEST_MEMFD : 0,
+ .mem_backing_src = mem_backing_src,
};
bool slot_recreated = false;
pthread_t slot_worker;
@@ -172,11 +176,13 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
struct test_params {
unsigned long vm_type;
bool private;
+ enum vm_mem_backing_src_type mem_backing_src;
};
static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
{
gpa_t gpa, gva, alignment, guest_page_size, host_page_size;
+ gpa_t backing_src_pagesz, mem_page_size;
struct test_params *p = arg;
const struct vm_shape shape = {
.mode = guest_mode,
@@ -188,24 +194,28 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
struct ucall uc;
pr_info("Testing guest mode: %s\n", vm_guest_mode_string(guest_mode));
+ pr_info("Testing memory backing src type: %s\n",
+ vm_mem_backing_src_alias(p->mem_backing_src)->name);
vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code);
guest_page_size = vm_guest_mode_params[guest_mode].page_size;
host_page_size = getpagesize();
+ backing_src_pagesz = get_backing_src_pagesz(p->mem_backing_src);
+ mem_page_size = max(host_page_size, backing_src_pagesz);
test_config.page_size = guest_page_size;
test_config.test_size = align_up(TEST_BASE_SIZE + test_config.page_size,
- host_page_size);
+ mem_page_size);
test_config.test_num_pages = vm_calc_num_guest_pages(vm->mode, test_config.test_size);
gpa = (vm->max_gfn - test_config.test_num_pages) * test_config.page_size;
alignment = SZ_2M;
- alignment = max(alignment, host_page_size);
+ alignment = max(alignment, mem_page_size);
gpa = align_down(gpa, alignment);
gva = gpa & ((1ULL << (vm->va_bits - 1)) - 1);
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ vm_userspace_mem_region_add(vm, p->mem_backing_src,
gpa, TEST_SLOT, test_config.test_num_pages,
p->private ? KVM_MEM_GUEST_MEMFD : 0);
virt_map(vm, gva, gpa, test_config.test_num_pages);
@@ -213,14 +223,18 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
if (p->private)
vm_mem_set_private(vm, gpa, test_config.test_size);
- pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+ pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0,
+ p->mem_backing_src, p->private);
/* Retry the same range after the first prefault attempt. */
- pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0, p->private);
+ pre_fault_memory(vcpu, gpa, 0, test_config.test_size, 0,
+ p->mem_backing_src, p->private);
pre_fault_memory(vcpu, gpa,
test_config.test_size - host_page_size,
- host_page_size * 2, host_page_size, p->private);
+ host_page_size * 2, host_page_size,
+ p->mem_backing_src, p->private);
pre_fault_memory(vcpu, gpa, test_config.test_size,
- host_page_size, host_page_size, p->private);
+ host_page_size, host_page_size,
+ p->mem_backing_src, p->private);
vcpu_args_set(vcpu, 1, gva);
@@ -249,11 +263,13 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg)
kvm_vm_free(vm);
}
-static void test_pre_fault_memory(unsigned long vm_type, bool private)
+static void test_pre_fault_memory(unsigned long vm_type, enum vm_mem_backing_src_type backing_src,
+ bool private)
{
struct test_params p = {
.vm_type = vm_type,
.private = private,
+ .mem_backing_src = backing_src,
};
if (vm_type && !(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(vm_type))) {
@@ -267,23 +283,28 @@ static void test_pre_fault_memory(unsigned long vm_type, bool private)
static void help(char *name)
{
puts("");
- printf("usage: %s [-h] [-m mode]\n", name);
+ printf("usage: %s [-h] [-m mode] [-s mem-type]\n", name);
puts("");
guest_modes_help();
+ backing_src_help("-s");
puts("");
}
int main(int argc, char *argv[])
{
+ enum vm_mem_backing_src_type backing = DEFAULT_VM_MEM_SRC;
int opt;
guest_modes_append_default();
- while ((opt = getopt(argc, argv, "hm:")) != -1) {
+ while ((opt = getopt(argc, argv, "hm:s:")) != -1) {
switch (opt) {
case 'm':
guest_modes_cmdline(optarg);
break;
+ case 's':
+ backing = parse_backing_src_type(optarg);
+ break;
case 'h':
default:
help(argv[0]);
@@ -293,10 +314,10 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));
- test_pre_fault_memory(0, false);
+ test_pre_fault_memory(0, backing, false);
#ifdef __x86_64__
- test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, false);
- test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, true);
+ test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, backing, false);
+ test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, backing, true);
#endif
return 0;
}
--
2.43.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v5 5/5] KVM: selftests: Add nested pre-fault test for arm64
2026-06-12 16:23 [PATCH v5 0/5] KVM: arm64: Add KVM_PRE_FAULT_MEMORY support Jack Thomson
` (3 preceding siblings ...)
2026-06-12 16:23 ` [PATCH v5 4/5] KVM: selftests: Add option for different backing in pre-fault tests Jack Thomson
@ 2026-06-12 16:23 ` Jack Thomson
4 siblings, 0 replies; 6+ messages in thread
From: Jack Thomson @ 2026-06-12 16:23 UTC (permalink / raw)
To: maz, oupton, pbonzini
Cc: joey.gouly, seiden, suzuki.poulose, yuzenghui, catalin.marinas,
will, shuah, corbet, vladimir.murzin, linux-arm-kernel, kvmarm,
kvm, linux-kernel, linux-kselftest, linux-doc, isaku.yamahata,
Jack Thomson
From: Jack Thomson <jackabt@amazon.com>
Add an arm64 nested-virt selftest for KVM_PRE_FAULT_MEMORY. The guest
enters vEL1 and exits to userspace with a nested/shadow stage-2 MMU as
the vCPU's last-run context.
Before prefaulting, userspace enables HCR_EL2.VM and points VTTBR_EL2 at
an empty nested stage-2 root. A prefault implementation that incorrectly
treats the userspace GPA as an L2 IPA will fail the ioctl; the correct
path swaps to the canonical stage-2 and succeeds.
Restore the original nested state before resuming the guest, then touch
the prefaulted range to check that vEL1 still runs correctly.
Signed-off-by: Jack Thomson <jackabt@amazon.com>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../kvm/arm64/nv_pre_fault_memory_test.c | 200 ++++++++++++++++++
2 files changed, 201 insertions(+)
create mode 100644 tools/testing/selftests/kvm/arm64/nv_pre_fault_memory_test.c
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 4609d8f23e38..63d79245b47d 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -170,6 +170,7 @@ TEST_GEN_PROGS_arm64 += arm64/debug-exceptions
TEST_GEN_PROGS_arm64 += arm64/hello_el2
TEST_GEN_PROGS_arm64 += arm64/host_sve
TEST_GEN_PROGS_arm64 += arm64/hypercalls
+TEST_GEN_PROGS_arm64 += arm64/nv_pre_fault_memory_test
TEST_GEN_PROGS_arm64 += arm64/external_aborts
TEST_GEN_PROGS_arm64 += arm64/page_fault_test
TEST_GEN_PROGS_arm64 += arm64/psci_test
diff --git a/tools/testing/selftests/kvm/arm64/nv_pre_fault_memory_test.c b/tools/testing/selftests/kvm/arm64/nv_pre_fault_memory_test.c
new file mode 100644
index 000000000000..2bbd5540599c
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/nv_pre_fault_memory_test.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * nv_pre_fault_memory_test - Test KVM_PRE_FAULT_MEMORY on a vCPU whose
+ * last-run context is nested.
+ *
+ * The guest starts at vEL2, mirrors its EL2 translation regime into the
+ * real EL1 registers, drops HCR_EL2.TGE and ERETs to vEL1, then exits to
+ * userspace from vEL1 so that the vCPU's last-run context selects a
+ * shadow stage-2 MMU. Userspace then enables an empty nested stage-2
+ * before prefaulting. Prefaulting must target the canonical stage-2,
+ * regardless of the vCPU's nested state.
+ */
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+#include "ucall.h"
+
+#include <asm/sysreg.h>
+#include <linux/sizes.h>
+
+#define TEST_MEM_SLOT 10
+#define NESTED_S2_ROOT_SLOT 11
+#define TEST_MEM_SIZE SZ_2M
+#define TEST_MEM_GPA SZ_1G
+#define NESTED_S2_ROOT_GPA (TEST_MEM_GPA + TEST_MEM_SIZE)
+
+struct nested_s2_state {
+ u64 hcr_el2;
+ u64 vttbr_el2;
+};
+
+static void guest_el1_code(void)
+{
+ u64 offset;
+
+ GUEST_ASSERT_EQ(get_current_el(), 1);
+
+ /* Exit to userspace with the vEL1 (nested) context live. */
+ GUEST_SYNC(1);
+
+ /*
+ * Touch the prefaulted range. vstage-2 is disabled, so the shadow
+ * stage-2 is a 1:1 view of the canonical IPA space.
+ */
+ for (offset = 0; offset < TEST_MEM_SIZE; offset += SZ_4K)
+ READ_ONCE(*(u64 *)(TEST_MEM_GPA + offset));
+
+ GUEST_DONE();
+}
+
+static void guest_code(void)
+{
+ u64 sp;
+
+ GUEST_ASSERT_EQ(get_current_el(), 2);
+
+ /*
+ * Mirror the EL2 translation regime into the real EL1 registers so
+ * that vEL1 runs on the test's stage-1 page tables. With E2H=1, the
+ * _EL1 accessors read the EL2 registers, and the _EL12 accessors
+ * write the real EL1 registers.
+ */
+ write_sysreg_s(read_sysreg(sctlr_el1), SYS_SCTLR_EL12);
+ write_sysreg_s(read_sysreg(tcr_el1), SYS_TCR_EL12);
+ write_sysreg_s(read_sysreg(ttbr0_el1), SYS_TTBR0_EL12);
+ write_sysreg_s(read_sysreg(mair_el1), SYS_MAIR_EL12);
+ write_sysreg_s(read_sysreg(cpacr_el1), SYS_CPACR_EL12);
+
+ /* Run vEL1 on the same stack. */
+ asm volatile("mov %0, sp" : "=r"(sp));
+ write_sysreg(sp, sp_el1);
+
+ /*
+ * Drop TGE so that vEL1 is a nested context rather than host EL0.
+ * KVM backs it with a shadow stage-2 MMU even though vstage-2 is
+ * disabled (HCR_EL2.VM=0).
+ */
+ write_sysreg(read_sysreg(hcr_el2) & ~HCR_EL2_TGE, hcr_el2);
+ isb();
+
+ write_sysreg(PSR_MODE_EL1h | PSR_F_BIT | PSR_I_BIT | PSR_A_BIT |
+ PSR_D_BIT, spsr_el2);
+ write_sysreg((u64)guest_el1_code, elr_el2);
+ asm volatile("eret");
+
+ GUEST_ASSERT(false);
+}
+
+static void pre_fault(struct kvm_vcpu *vcpu, u64 gpa, u64 size)
+{
+ struct kvm_pre_fault_memory range = {
+ .gpa = gpa,
+ .size = size,
+ };
+ int ret;
+
+ do {
+ ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range);
+ } while (ret < 0 && errno == EINTR);
+
+ TEST_ASSERT(!ret, "KVM_PRE_FAULT_MEMORY failed, ret: %d errno: %d",
+ ret, errno);
+ TEST_ASSERT_EQ(range.size, 0);
+}
+
+static struct nested_s2_state enable_empty_nested_s2(struct kvm_vcpu *vcpu)
+{
+ struct nested_s2_state state = {
+ .hcr_el2 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_HCR_EL2)),
+ .vttbr_el2 = vcpu_get_reg(vcpu,
+ KVM_ARM64_SYS_REG(SYS_VTTBR_EL2)),
+ };
+
+ TEST_ASSERT(!(state.hcr_el2 & HCR_EL2_TGE),
+ "vCPU should be in nested/vEL1 context");
+
+ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_VTTBR_EL2),
+ NESTED_S2_ROOT_GPA);
+ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_HCR_EL2),
+ state.hcr_el2 | HCR_EL2_VM);
+
+ return state;
+}
+
+static void restore_nested_s2(struct kvm_vcpu *vcpu,
+ struct nested_s2_state *state)
+{
+ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_HCR_EL2), state->hcr_el2);
+ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_VTTBR_EL2),
+ state->vttbr_el2);
+}
+
+int main(void)
+{
+ struct nested_s2_state s2;
+ struct kvm_vcpu_init init;
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ struct ucall uc;
+ u64 npages;
+
+ TEST_REQUIRE(kvm_check_cap(KVM_CAP_ARM_EL2));
+ TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));
+
+ vm = vm_create(1);
+
+ kvm_get_default_vcpu_target(vm, &init);
+ init.features[0] |= BIT(KVM_ARM_VCPU_HAS_EL2);
+ vcpu = aarch64_vcpu_add(vm, 0, &init, guest_code);
+ kvm_arch_vm_finalize_vcpus(vm);
+
+ npages = TEST_MEM_SIZE / vm->page_size;
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, TEST_MEM_GPA,
+ TEST_MEM_SLOT, npages, 0);
+ virt_map(vm, TEST_MEM_GPA, TEST_MEM_GPA, npages);
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ NESTED_S2_ROOT_GPA, NESTED_S2_ROOT_SLOT,
+ 1, 0);
+
+ /* Run the guest until it has ERET'd from vEL2 to vEL1. */
+ vcpu_run(vcpu);
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_SYNC:
+ TEST_ASSERT_EQ(uc.args[1], 1);
+ break;
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ break;
+ default:
+ TEST_FAIL("Unhandled ucall: %ld", uc.cmd);
+ }
+
+ /*
+ * The vCPU's last-run context is vEL1, backed by a shadow stage-2
+ * MMU. Enable nested stage-2 with an empty root so that the ioctl
+ * fails if it tries to interpret the userspace GPA as an L2 IPA.
+ * Prefault in two halves so that the second ioctl exercises a
+ * repeated shadow-MMU attach and canonical stage-2 swap.
+ */
+ s2 = enable_empty_nested_s2(vcpu);
+ pre_fault(vcpu, TEST_MEM_GPA, TEST_MEM_SIZE / 2);
+ pre_fault(vcpu, TEST_MEM_GPA + TEST_MEM_SIZE / 2, TEST_MEM_SIZE / 2);
+ restore_nested_s2(vcpu, &s2);
+
+ /* Resume at vEL1 and touch the prefaulted range. */
+ vcpu_run(vcpu);
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_DONE:
+ break;
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ break;
+ default:
+ TEST_FAIL("Unhandled ucall: %ld", uc.cmd);
+ }
+
+ kvm_vm_free(vm);
+ return 0;
+}
--
2.43.0
^ permalink raw reply related [flat|nested] 6+ messages in thread