| Message ID | 20240419085927.3648704-7-pbonzini@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | KVM: Guest Memory Pre-Population API | expand |
On Fri, Apr 19, 2024 at 04:59:27AM -0400, Paolo Bonzini <pbonzini@redhat.com> wrote: > From: Isaku Yamahata <isaku.yamahata@intel.com> > > Add a test case to exercise KVM_PRE_FAULT_MEMORY and run the guest to access the > pre-populated area. It tests KVM_PRE_FAULT_MEMORY ioctl for KVM_X86_DEFAULT_VM > and KVM_X86_SW_PROTECTED_VM. > > Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com> > Message-ID: <32427791ef42e5efaafb05d2ac37fa4372715f47.1712785629.git.isaku.yamahata@intel.com> > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > tools/include/uapi/linux/kvm.h | 8 + > tools/testing/selftests/kvm/Makefile | 1 + > .../selftests/kvm/pre_fault_memory_test.c | 146 ++++++++++++++++++ > 3 files changed, 155 insertions(+) > create mode 100644 tools/testing/selftests/kvm/pre_fault_memory_test.c > > diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h > index c3308536482b..4d66d8afdcd1 100644 > --- a/tools/include/uapi/linux/kvm.h > +++ b/tools/include/uapi/linux/kvm.h > @@ -2227,4 +2227,12 @@ struct kvm_create_guest_memfd { > __u64 reserved[6]; > }; > > +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) > + > +struct kvm_pre_fault_memory { > + __u64 gpa; > + __u64 size; > + __u64 flags; nitpick: catch up for struct update. + __u64 padding[5]; > +}; > + > #endif /* __LINUX_KVM_H */
On 4/19/2024 4:59 PM, Paolo Bonzini wrote: ... > +static void __test_pre_fault_memory(unsigned long vm_type, bool private) > +{ > + const struct vm_shape shape = { > + .mode = VM_MODE_DEFAULT, > + .type = vm_type, > + }; > + struct kvm_vcpu *vcpu; > + struct kvm_run *run; > + struct kvm_vm *vm; > + struct ucall uc; > + > + uint64_t guest_test_phys_mem; > + uint64_t guest_test_virt_mem; > + uint64_t alignment, guest_page_size; > + > + vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code); > + > + alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size; > + guest_test_phys_mem = (vm->max_gfn - TEST_NPAGES) * guest_page_size; > +#ifdef __s390x__ > + alignment = max(0x100000UL, guest_page_size); > +#else > + alignment = SZ_2M; > +#endif > + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); > + guest_test_virt_mem = guest_test_phys_mem; guest_test_virt_mem cannot be assigned as guest_test_phys_mem, which leads to following virt_map() fails with ==== Test Assertion Failure ==== lib/x86_64/processor.c:197: sparsebit_is_set(vm->vpages_valid, (vaddr >> vm->page_shift)) pid=4773 tid=4773 errno=0 - Success 1 0x000000000040f55c: __virt_pg_map at processor.c:197 2 0x000000000040605e: virt_pg_map at kvm_util_base.h:1065 3 (inlined by) virt_map at kvm_util.c:1571 4 0x0000000000402b75: __test_pre_fault_memory at pre_fault_memory_test.c:96 5 0x000000000040246e: test_pre_fault_memory at pre_fault_memory_test.c:133 (discriminator 3) 6 (inlined by) main at pre_fault_memory_test.c:140 (discriminator 3) 7 0x00007fcb68429d8f: ?? ??:0 8 0x00007fcb68429e3f: ?? ??:0 9 0x00000000004024e4: _start at ??:? Invalid virtual address, vaddr: 0xfffffffc00000 > + > + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, > + guest_test_phys_mem, TEST_SLOT, TEST_NPAGES, > + private ? KVM_MEM_GUEST_MEMFD : 0); > + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, TEST_NPAGES);
On 4/23/2024 11:18 PM, Xiaoyao Li wrote: > On 4/19/2024 4:59 PM, Paolo Bonzini wrote: > > ... > >> +static void __test_pre_fault_memory(unsigned long vm_type, bool private) >> +{ >> + const struct vm_shape shape = { >> + .mode = VM_MODE_DEFAULT, >> + .type = vm_type, >> + }; >> + struct kvm_vcpu *vcpu; >> + struct kvm_run *run; >> + struct kvm_vm *vm; >> + struct ucall uc; >> + >> + uint64_t guest_test_phys_mem; >> + uint64_t guest_test_virt_mem; >> + uint64_t alignment, guest_page_size; >> + >> + vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code); >> + >> + alignment = guest_page_size = >> vm_guest_mode_params[VM_MODE_DEFAULT].page_size; >> + guest_test_phys_mem = (vm->max_gfn - TEST_NPAGES) * guest_page_size; >> +#ifdef __s390x__ >> + alignment = max(0x100000UL, guest_page_size); >> +#else >> + alignment = SZ_2M; >> +#endif >> + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); >> + guest_test_virt_mem = guest_test_phys_mem; > > guest_test_virt_mem cannot be assigned as guest_test_phys_mem, which > leads to following virt_map() fails with The root cause is that vm->pa_bits is 52 while vm->va_bits is 48. So vm->max_gfn is beyond the capability of va space > ==== Test Assertion Failure ==== > lib/x86_64/processor.c:197: sparsebit_is_set(vm->vpages_valid, (vaddr > >> vm->page_shift)) > pid=4773 tid=4773 errno=0 - Success > 1 0x000000000040f55c: __virt_pg_map at processor.c:197 > 2 0x000000000040605e: virt_pg_map at kvm_util_base.h:1065 > 3 (inlined by) virt_map at kvm_util.c:1571 > 4 0x0000000000402b75: __test_pre_fault_memory at > pre_fault_memory_test.c:96 > 5 0x000000000040246e: test_pre_fault_memory at > pre_fault_memory_test.c:133 (discriminator 3) > 6 (inlined by) main at pre_fault_memory_test.c:140 > (discriminator 3) > 7 0x00007fcb68429d8f: ?? ??:0 > 8 0x00007fcb68429e3f: ?? ??:0 > 9 0x00000000004024e4: _start at ??:? > Invalid virtual address, vaddr: 0xfffffffc00000 > >> + >> + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, >> + guest_test_phys_mem, TEST_SLOT, TEST_NPAGES, >> + private ? KVM_MEM_GUEST_MEMFD : 0); >> + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, TEST_NPAGES); > > > > >
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c3308536482b..4d66d8afdcd1 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -2227,4 +2227,12 @@ struct kvm_create_guest_memfd { __u64 reserved[6]; }; +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; +}; + #endif /* __LINUX_KVM_H */ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 871e2de3eb05..61d581a4bab4 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -144,6 +144,7 @@ TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test TEST_GEN_PROGS_x86_64 += system_counter_offset_test +TEST_GEN_PROGS_x86_64 += pre_fault_memory_test # Compiled outputs used by test targets TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c new file mode 100644 index 000000000000..e56eed2c1f05 --- /dev/null +++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Intel, Inc + * + * Author: + * Isaku Yamahata <isaku.yamahata at gmail.com> + */ +#include <linux/sizes.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +/* Arbitrarily chosen values */ +#define TEST_SIZE (SZ_2M + PAGE_SIZE) +#define TEST_NPAGES (TEST_SIZE / PAGE_SIZE) +#define TEST_SLOT 10 + +static void guest_code(uint64_t base_gpa) +{ + volatile uint64_t val __used; + int i; + + for (i = 0; i < TEST_NPAGES; i++) { + uint64_t *src = (uint64_t *)(base_gpa + i * PAGE_SIZE); + + val = *src; + } + + GUEST_DONE(); +} + +static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size, + u64 left) +{ + struct kvm_pre_fault_memory range = { + .gpa = gpa, + .size = size, + .flags = 0, + }; + u64 prev; + int ret, save_errno; + + do { + prev = range.size; + ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range); + save_errno = errno; + TEST_ASSERT((range.size < prev) ^ (ret < 0), + "%sexpecting range.size to change on %s", + ret < 0 ? "not " : "", + ret < 0 ? "failure" : "success"); + } while (ret >= 0 ? range.size : save_errno == EINTR); + + TEST_ASSERT(range.size == left, + "Completed with %lld bytes left, expected %" PRId64, + range.size, left); + + if (left == 0) + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm); + else + /* No memory slot causes RET_PF_EMULATE. it results in -ENOENT. */ + __TEST_ASSERT_VM_VCPU_IOCTL(ret && save_errno == ENOENT, + "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm); +} + +static void __test_pre_fault_memory(unsigned long vm_type, bool private) +{ + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = vm_type, + }; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + + uint64_t guest_test_phys_mem; + uint64_t guest_test_virt_mem; + uint64_t alignment, guest_page_size; + + vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code); + + alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size; + guest_test_phys_mem = (vm->max_gfn - TEST_NPAGES) * guest_page_size; +#ifdef __s390x__ + alignment = max(0x100000UL, guest_page_size); +#else + alignment = SZ_2M; +#endif + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); + guest_test_virt_mem = guest_test_phys_mem; + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, TEST_SLOT, TEST_NPAGES, + private ? KVM_MEM_GUEST_MEMFD : 0); + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, TEST_NPAGES); + + if (private) + vm_mem_set_private(vm, guest_test_phys_mem, TEST_SIZE); + pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, 0); + pre_fault_memory(vcpu, guest_test_phys_mem + SZ_2M, PAGE_SIZE * 2, PAGE_SIZE); + pre_fault_memory(vcpu, guest_test_phys_mem + TEST_SIZE, PAGE_SIZE, PAGE_SIZE); + + vcpu_args_set(vcpu, 1, guest_test_virt_mem); + vcpu_run(vcpu); + + run = vcpu->run; + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Wanted KVM_EXIT_IO, got exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + break; + } + + kvm_vm_free(vm); +} + +static void test_pre_fault_memory(unsigned long vm_type, 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); + return; + } + + __test_pre_fault_memory(vm_type, private); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY)); + + test_pre_fault_memory(0, false); +#ifdef __x86_64__ + test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, false); + test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, true); +#endif + return 0; +}