From: Jack Thomson jackabt@amazon.com

Add kvm_arch_vcpu_pre_fault_memory() for arm64. The implementation hands off the stage-2 faulting logic to either gmem_abort() or user_mem_abort().

Add an optional page_size output parameter to user_mem_abort() to return the VMA page size, which is needed when pre-faulting.

Update the documentation to clarify x86 specific behaviour.

Signed-off-by: Jack Thomson jackabt@amazon.com --- Documentation/virt/kvm/api.rst | 3 +- arch/arm64/kvm/Kconfig | 1 + arch/arm64/kvm/arm.c | 1 + arch/arm64/kvm/mmu.c | 73 ++++++++++++++++++++++++++++++++-- 4 files changed, 73 insertions(+), 5 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c17a87a0a5ac..9e8cc4eb505d 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6461,7 +6461,8 @@ 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.

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 diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index bff62e75d681..1ac0605f86cb 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -25,6 +25,7 @@ menuconfig KVM select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_GENERIC_DIRTYLOG_READ_PROTECT + select KVM_GENERIC_PRE_FAULT_MEMORY select KVM_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 888f7c7abf54..65654a742864 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -322,6 +322,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_COUNTER_OFFSET: case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS: + 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 a36426ccd9b5..82f122e4b08c 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1597,8 +1597,8 @@ static int gmem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,

static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_s2_trans *nested, - struct kvm_memory_slot *memslot, unsigned long hva, - bool fault_is_perm) + struct kvm_memory_slot *memslot, long *page_size, + unsigned long hva, bool fault_is_perm) { int ret = 0; bool topup_memcache; @@ -1871,6 +1871,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_release_faultin_page(kvm, page, !!ret, writable); kvm_fault_unlock(kvm);

+ if (page_size) + *page_size = vma_pagesize; + /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) mark_page_dirty_in_slot(kvm, memslot, gfn); @@ -2069,8 +2072,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) ret = gmem_abort(vcpu, fault_ipa, nested, memslot, esr_fsc_is_permission_fault(esr)); else - ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva, - esr_fsc_is_permission_fault(esr)); + ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, NULL, + hva, esr_fsc_is_permission_fault(esr)); if (ret == 0) ret = 1; out: @@ -2446,3 +2449,65 @@ void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)

trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); } + +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range) +{ + int ret, idx; + hva_t hva; + phys_addr_t end; + struct kvm_memory_slot *memslot; + struct kvm_vcpu_fault_info stored_fault, *fault_info; + + long page_size = PAGE_SIZE; + phys_addr_t ipa = range->gpa; + gfn_t gfn = gpa_to_gfn(range->gpa); + + idx = srcu_read_lock(&vcpu->kvm->srcu); + + if (ipa >= kvm_phys_size(vcpu->arch.hw_mmu)) { + ret = -ENOENT; + goto out_unlock; + } + + memslot = gfn_to_memslot(vcpu->kvm, gfn); + if (!memslot) { + ret = -ENOENT; + goto out_unlock; + } + + fault_info = &vcpu->arch.fault; + stored_fault = *fault_info; + + /* Generate a synthetic abort for the pre-fault address */ + fault_info->esr_el2 = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_DABT_CUR); + fault_info->esr_el2 &= ~ESR_ELx_ISV; + fault_info->esr_el2 |= ESR_ELx_FSC_FAULT_L(KVM_PGTABLE_LAST_LEVEL); + + fault_info->hpfar_el2 = HPFAR_EL2_NS | + FIELD_PREP(HPFAR_EL2_FIPA, ipa >> 12); + + if (kvm_slot_has_gmem(memslot)) { + ret = gmem_abort(vcpu, ipa, NULL, memslot, false); + } else { + hva = gfn_to_hva_memslot_prot(memslot, gfn, NULL); + if (kvm_is_error_hva(hva)) { + ret = -EFAULT; + goto out; + } + ret = user_mem_abort(vcpu, ipa, NULL, memslot, &page_size, hva, + false); + } + + if (ret < 0) + goto out; + + end = (range->gpa & ~(page_size - 1)) + page_size; + ret = min(range->size, end - range->gpa); + +out: + *fault_info = stored_fault; +out_unlock: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + return ret; +}

From: Jack Thomson jackabt@amazon.com

When creating a VM using mmap with huge pages, and the memory amount does not align with the underlying page size. The stored mmap_size value does not account for the fact that mmap will automatically align the length to a multiple of the underlying page size. During the teardown of the test, munmap is used. However, munmap requires the length to be a multiple of the underlying page size.

Update the vm_mem_add method to ensure the mmap_size is aligned to the underlying page size.

Signed-off-by: Jack Thomson jackabt@amazon.com --- tools/testing/selftests/kvm/lib/kvm_util.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index c3f5142b0a54..b106fbed999c 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1051,7 +1051,6 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, /* Allocate and initialize new mem region structure. */ region = calloc(1, sizeof(*region)); TEST_ASSERT(region != NULL, "Insufficient Memory"); - region->mmap_size = mem_size;

#ifdef __s390x__ /* On s390x, the host address must be aligned to 1M (due to PGSTEs) */ @@ -1060,6 +1059,11 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, alignment = 1; #endif

+ alignment = max(backing_src_pagesz, alignment); + region->mmap_size = align_up(mem_size, alignment); + + TEST_ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); + /* * When using THP mmap is not guaranteed to returned a hugepage aligned * address so we have to pad the mmap. Padding is not needed for HugeTLB @@ -1067,12 +1071,6 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, * page size. */ if (src_type == VM_MEM_SRC_ANONYMOUS_THP) - alignment = max(backing_src_pagesz, alignment); - - TEST_ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); - - /* Add enough memory to align up if necessary */ - if (alignment > 1) region->mmap_size += alignment;

region->fd = -1;

From: Jack Thomson jackabt@amazon.com

Add a -m 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 | 31 ++++++++++++++++--- 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c index ed9848a8af60..22e2e53945d9 100644 --- a/tools/testing/selftests/kvm/pre_fault_memory_test.c +++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c @@ -76,6 +76,7 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size, 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) @@ -94,7 +95,11 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg) uint64_t guest_test_virt_mem; uint64_t alignment, guest_page_size;

+ size_t backing_src_pagesz = get_backing_src_pagesz(p->mem_backing_src); + 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);

@@ -110,10 +115,11 @@ static void __test_pre_fault_memory(enum vm_guest_mode guest_mode, void *arg) #else alignment = SZ_2M; #endif + alignment = max(alignment, backing_src_pagesz); guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); guest_test_virt_mem = guest_test_phys_mem & ((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, guest_test_phys_mem, TEST_SLOT, test_config.test_num_pages, p->private ? KVM_MEM_GUEST_MEMFD : 0); virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, test_config.test_num_pages); @@ -155,7 +161,8 @@ 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) { 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); @@ -165,6 +172,7 @@ static void test_pre_fault_memory(unsigned long vm_type, bool private) struct test_params p = { .vm_type = vm_type, .private = private, + .mem_backing_src = backing_src, };

for_each_guest_mode(__test_pre_fault_memory, &p); @@ -174,10 +182,23 @@ int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));

- test_pre_fault_memory(0, false); + int opt; + enum vm_mem_backing_src_type backing = VM_MEM_SRC_ANONYMOUS; + + while ((opt = getopt(argc, argv, "m:")) != -1) { + switch (opt) { + case 'm': + backing = parse_backing_src_type(optarg); + break; + default: + break; + } + } + + 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; }