From: Erdem Aktas erdemaktas@google.com

Currently vm_create function only creates KVM_VM_TYPE_DEFAULT type VMs. Adding type parameter to ____vm_create to create new VM types.

Signed-off-by: Erdem Aktas erdemaktas@google.com Reviewed-by: David Matlack dmatlack@google.com Signed-off-by: Ryan Afranji afranji@google.com Signed-off-by: Sagi Shahar sagis@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- tools/testing/selftests/kvm/include/kvm_util_base.h | 6 ++++-- tools/testing/selftests/kvm/lib/kvm_util.c | 6 +++--- tools/testing/selftests/kvm/lib/x86_64/sev.c | 2 +- 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 0db5cd4b8383a..0fa4dab3d8e52 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -27,6 +27,8 @@

#define NSEC_PER_SEC 1000000000L

+#define KVM_VM_TYPE_DEFAULT 0 + typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */

@@ -686,13 +688,13 @@ uint64_t vm_nr_pages_required(enum vm_guest_mode mode, * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to * calculate the amount of memory needed for per-vCPU data, e.g. stacks. */ -struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages); +struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages, int type); struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, uint64_t nr_extra_pages);

static inline struct kvm_vm *vm_create_barebones(void) { - return ____vm_create(VM_MODE_DEFAULT, 0); + return ____vm_create(VM_MODE_DEFAULT, 0, KVM_VM_TYPE_DEFAULT); }

static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 5257bce6f546d..14246f0fd2e78 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -185,7 +185,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?");

-struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages) +struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages, int type) { struct kvm_vm *vm;

@@ -201,7 +201,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages) hash_init(vm->regions.slot_hash);

vm->mode = mode; - vm->type = 0; + vm->type = type;

vm->pa_bits = vm_guest_mode_params[mode].pa_bits; vm->va_bits = vm_guest_mode_params[mode].va_bits; @@ -337,7 +337,7 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, struct userspace_mem_region *slot0; struct kvm_vm *vm;

- vm = ____vm_create(mode, nr_pages); + vm = ____vm_create(mode, nr_pages, KVM_VM_TYPE_DEFAULT);

kvm_vm_elf_load(vm, program_invocation_name);

diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86_64/sev.c index faed2ebe63ac9..dedfd9f45cfb3 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/sev.c +++ b/tools/testing/selftests/kvm/lib/x86_64/sev.c @@ -221,7 +221,7 @@ struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code, uint64_t nr_pages = vm_nr_pages_required(mode, 1, 0); struct kvm_vm *vm;

- vm = ____vm_create(mode, nr_pages); + vm = ____vm_create(mode, nr_pages, KVM_VM_TYPE_DEFAULT);

kvm_sev_ioctl(vm, KVM_SEV_INIT, NULL);

TDX guests' registers cannot be initialized directly using vcpu_regs_set(), hence the stack pointer needs to be initialized by the guest itself, running boot code beginning at the reset vector.

We store the stack address as part of struct kvm_vcpu so that it can be accessible later to be passed to the boot code for rsp initialization.

Signed-off-by: Ackerley Tng ackerleytng@google.com --- tools/testing/selftests/kvm/include/kvm_util_base.h | 1 + tools/testing/selftests/kvm/lib/x86_64/processor.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 0fa4dab3d8e52..cdc204cfeb4c2 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -54,6 +54,7 @@ struct kvm_vcpu { int fd; struct kvm_vm *vm; struct kvm_run *run; + vm_vaddr_t initial_stack_addr; #ifdef __x86_64__ struct kvm_cpuid2 *cpuid; #endif diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 1bb07d3c025b0..3046b555fee49 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -673,10 +673,12 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); vcpu_setup(vm, vcpu);

+ vcpu->initial_stack_addr = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()); + /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, &regs); regs.rflags = regs.rflags | 0x2; - regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()); + regs.rsp = vcpu->initial_stack_addr; regs.rip = (unsigned long) guest_code; vcpu_regs_set(vcpu, &regs);

From: Erdem Aktas erdemaktas@google.com

TDX requires additional IOCTLs to initialize VM and vCPUs to add private memory and to finalize the VM memory. Also additional utility functions are provided to manipulate a TD, similar to those that manipulate a VM in the current selftest framework.

A TD's initial register state cannot be manipulated directly by setting the VM's memory, hence boot code is provided at the TD's reset vector. This boot code takes boot parameters loaded in the TD's memory and sets up the TD for the selftest.

Signed-off-by: Erdem Aktas erdemaktas@google.com Signed-off-by: Ryan Afranji afranji@google.com Signed-off-by: Sagi Shahar sagis@google.com Co-developed-by: Ackerley Tng ackerleytng@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- Changes RFCv2 -> RFCv3

+ Refactored out required cpuid changes as tdx_apply_cpuid_restrictions (a more meaningful function) + Also fixed logic for setting LBR and CET features to use sub-leaf 1 instead of 0 previously + Renamed ioctl calls to match names used in the kernel for easy referencing --- tools/testing/selftests/kvm/Makefile | 2 + .../kvm/include/x86_64/tdx/td_boot.h | 82 ++++ .../kvm/include/x86_64/tdx/td_boot_asm.h | 16 + .../kvm/include/x86_64/tdx/tdx_util.h | 16 + .../selftests/kvm/lib/x86_64/tdx/td_boot.S | 101 ++++ .../selftests/kvm/lib/x86_64/tdx/tdx_util.c | 438 ++++++++++++++++++ 6 files changed, 655 insertions(+) create mode 100644 tools/testing/selftests/kvm/include/x86_64/tdx/td_boot.h create mode 100644 tools/testing/selftests/kvm/include/x86_64/tdx/td_boot_asm.h create mode 100644 tools/testing/selftests/kvm/include/x86_64/tdx/tdx_util.h create mode 100644 tools/testing/selftests/kvm/lib/x86_64/tdx/td_boot.S create mode 100644 tools/testing/selftests/kvm/lib/x86_64/tdx/tdx_util.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 1eb9b2aa7c220..317927d9c55bd 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -59,6 +59,8 @@ LIBKVM_x86_64 += lib/x86_64/svm.c LIBKVM_x86_64 += lib/x86_64/ucall.c LIBKVM_x86_64 += lib/x86_64/vmx.c LIBKVM_x86_64 += lib/x86_64/sev.c +LIBKVM_x86_64 += lib/x86_64/tdx/tdx_util.c +LIBKVM_x86_64 += lib/x86_64/tdx/td_boot.S

LIBKVM_aarch64 += lib/aarch64/gic.c LIBKVM_aarch64 += lib/aarch64/gic_v3.c diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/td_boot.h b/tools/testing/selftests/kvm/include/x86_64/tdx/td_boot.h new file mode 100644 index 0000000000000..148057e569d69 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/td_boot.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_TDX_TD_BOOT_H +#define SELFTEST_TDX_TD_BOOT_H + +#include <stdint.h> +#include "tdx/td_boot_asm.h" + +/* + * Layout for boot section (not to scale) + * + * GPA + * ┌─────────────────────────────┬──0x1_0000_0000 (4GB) + * │ Boot code trampoline │ + * ├─────────────────────────────┼──0x0_ffff_fff0: Reset vector (16B below 4GB) + * │ Boot code │ + * ├─────────────────────────────┼──td_boot will be copied here, so that the + * │ │ jmp to td_boot is exactly at the reset vector + * │ Empty space │ + * │ │ + * ├─────────────────────────────┤ + * │ │ + * │ │ + * │ Boot parameters │ + * │ │ + * │ │ + * └─────────────────────────────┴──0x0_ffff_0000: TD_BOOT_PARAMETERS_GPA + */ +#define FOUR_GIGABYTES_GPA (4ULL << 30) + +/** + * The exact memory layout for LGDT or LIDT instructions. + */ +struct __packed td_boot_parameters_dtr { + uint16_t limit; + uint32_t base; +}; + +/** + * The exact layout in memory required for a ljmp, including the selector for + * changing code segment. + */ +struct __packed td_boot_parameters_ljmp_target { + uint32_t eip_gva; + uint16_t code64_sel; +}; + +/** + * Allows each vCPU to be initialized with different eip and esp. + */ +struct __packed td_per_vcpu_parameters { + uint32_t esp_gva; + struct td_boot_parameters_ljmp_target ljmp_target; +}; + +/** + * Boot parameters for the TD. + * + * Unlike a regular VM, we can't ask KVM to set registers such as esp, eip, etc + * before boot, so to run selftests, these registers' values have to be + * initialized by the TD. + * + * This struct is loaded in TD private memory at TD_BOOT_PARAMETERS_GPA. + * + * The TD boot code will read off parameters from this struct and set up the + * vcpu for executing selftests. + */ +struct __packed td_boot_parameters { + uint32_t cr0; + uint32_t cr3; + uint32_t cr4; + struct td_boot_parameters_dtr gdtr; + struct td_boot_parameters_dtr idtr; + struct td_per_vcpu_parameters per_vcpu[]; +}; + +extern void td_boot(void); +extern void reset_vector(void); +extern void td_boot_code_end(void); + +#define TD_BOOT_CODE_SIZE (td_boot_code_end - td_boot) + +#endif /* SELFTEST_TDX_TD_BOOT_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/td_boot_asm.h b/tools/testing/selftests/kvm/include/x86_64/tdx/td_boot_asm.h new file mode 100644 index 0000000000000..0a07104f7debf --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/td_boot_asm.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_TDX_TD_BOOT_ASM_H +#define SELFTEST_TDX_TD_BOOT_ASM_H + +/* + * GPA where TD boot parameters wil lbe loaded. + * + * TD_BOOT_PARAMETERS_GPA is arbitrarily chosen to + * + * + be within the 4GB address space + * + provide enough contiguous memory for the struct td_boot_parameters such + * that there is one struct td_per_vcpu_parameters for KVM_MAX_VCPUS + */ +#define TD_BOOT_PARAMETERS_GPA 0xffff0000 + +#endif // SELFTEST_TDX_TD_BOOT_ASM_H diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx_util.h b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx_util.h new file mode 100644 index 0000000000000..274b245f200bf --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx_util.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTESTS_TDX_KVM_UTIL_H +#define SELFTESTS_TDX_KVM_UTIL_H + +#include <stdint.h> + +#include "kvm_util_base.h" + +struct kvm_vcpu *td_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, void *guest_code); + +struct kvm_vm *td_create(void); +void td_initialize(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t attributes); +void td_finalize(struct kvm_vm *vm); + +#endif // SELFTESTS_TDX_KVM_UTIL_H diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/td_boot.S b/tools/testing/selftests/kvm/lib/x86_64/tdx/td_boot.S new file mode 100644 index 0000000000000..800e09264d4ec --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/td_boot.S @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "tdx/td_boot_asm.h" + +/* Offsets for reading struct td_boot_parameters */ +#define TD_BOOT_PARAMETERS_CR0 0 +#define TD_BOOT_PARAMETERS_CR3 4 +#define TD_BOOT_PARAMETERS_CR4 8 +#define TD_BOOT_PARAMETERS_GDT 12 +#define TD_BOOT_PARAMETERS_IDT 18 +#define TD_BOOT_PARAMETERS_PER_VCPU 24 + +/* Offsets for reading struct td_per_vcpu_parameters */ +#define TD_PER_VCPU_PARAMETERS_ESP_GVA 0 +#define TD_PER_VCPU_PARAMETERS_LJMP_TARGET 4 + +#define SIZEOF_TD_PER_VCPU_PARAMETERS 10 + +.code32 + +.globl td_boot +td_boot: + /* In this procedure, edi is used as a temporary register */ + cli + + /* Paging is off */ + + movl $TD_BOOT_PARAMETERS_GPA, %ebx + + /* + * Find the address of struct td_per_vcpu_parameters for this + * vCPU based on esi (TDX spec: initialized with vcpu id). Put + * struct address into register for indirect addressing + */ + movl $SIZEOF_TD_PER_VCPU_PARAMETERS, %eax + mul %esi + leal TD_BOOT_PARAMETERS_PER_VCPU(%ebx), %edi + addl %edi, %eax + + /* Setup stack */ + movl TD_PER_VCPU_PARAMETERS_ESP_GVA(%eax), %esp + + /* Setup GDT */ + leal TD_BOOT_PARAMETERS_GDT(%ebx), %edi + lgdt (%edi) + + /* Setup IDT */ + leal TD_BOOT_PARAMETERS_IDT(%ebx), %edi + lidt (%edi) + + /* + * Set up control registers (There are no instructions to + * mov from memory to control registers, hence we need to use ebx + * as a scratch register) + */ + movl TD_BOOT_PARAMETERS_CR4(%ebx), %edi + movl %edi, %cr4 + movl TD_BOOT_PARAMETERS_CR3(%ebx), %edi + movl %edi, %cr3 + movl TD_BOOT_PARAMETERS_CR0(%ebx), %edi + movl %edi, %cr0 + + /* Paging is on after setting the most significant bit on cr0 */ + + /* + * Jump to selftest guest code. Far jumps read <segment + * selector:new eip> from addr+4:addr. This location has + * already been set up in boot parameters, and we can read boot + * parameters because boot code and boot parameters are loaded so + * that GVA and GPA are mapped 1:1. + */ + ljmp *TD_PER_VCPU_PARAMETERS_LJMP_TARGET(%eax) + +.globl reset_vector +reset_vector: + jmp td_boot + /* + * Pad reset_vector to its full size of 16 bytes so that this + * can be loaded with the end of reset_vector aligned to GPA=4G + */ + int3 + int3 + int3 + int3 + int3 + int3 + int3 + int3 + int3 + int3 + int3 + int3 + int3 + int3 + +/* Leave marker so size of td_boot code can be computed */ +.globl td_boot_code_end +td_boot_code_end: + +/* Disable executable stack */ +.section .note.GNU-stack,"",%progbits diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx_util.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx_util.c new file mode 100644 index 0000000000000..3564059c0b89b --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx_util.c @@ -0,0 +1,438 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include <asm/kvm.h> +#include <asm/kvm_host.h> +#include <errno.h> +#include <linux/kvm.h> +#include <stdint.h> +#include <sys/ioctl.h> + +#include "kvm_util.h" +#include "test_util.h" +#include "tdx/td_boot.h" +#include "kvm_util_base.h" +#include "processor.h" + +/* + * TDX ioctls + */ + +static char *tdx_cmd_str[] = { + "KVM_TDX_CAPABILITIES", + "KVM_TDX_INIT_VM", + "KVM_TDX_INIT_VCPU", + "KVM_TDX_INIT_MEM_REGION", + "KVM_TDX_FINALIZE_VM" +}; +#define TDX_MAX_CMD_STR (ARRAY_SIZE(tdx_cmd_str)) + +static void tdx_ioctl(int fd, int ioctl_no, uint32_t flags, void *data) +{ + struct kvm_tdx_cmd tdx_cmd; + int r; + + TEST_ASSERT(ioctl_no < TDX_MAX_CMD_STR, "Unknown TDX CMD : %d\n", + ioctl_no); + + memset(&tdx_cmd, 0x0, sizeof(tdx_cmd)); + tdx_cmd.id = ioctl_no; + tdx_cmd.flags = flags; + tdx_cmd.data = (uint64_t)data; + + r = ioctl(fd, KVM_MEMORY_ENCRYPT_OP, &tdx_cmd); + TEST_ASSERT(r == 0, "%s failed: %d %d", tdx_cmd_str[ioctl_no], r, + errno); +} + +#define XFEATURE_LBR 15 +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_CET_U 11 +#define XFEATURE_CET_S 12 + +#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR) +#define XFEATURE_MASK_CET_U (1 << XFEATURE_CET_U) +#define XFEATURE_MASK_CET_S (1 << XFEATURE_CET_S) +#define XFEATURE_MASK_CET (XFEATURE_MASK_CET_U | XFEATURE_MASK_CET_S) +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +static void tdx_apply_cpuid_restrictions(struct kvm_cpuid2 *cpuid_data) +{ + for (int i = 0; i < cpuid_data->nent; i++) { + struct kvm_cpuid_entry2 *e = &cpuid_data->entries[i]; + + if (e->function == 0xd && e->index == 0) { + /* + * TDX module requires both XTILE_{CFG, DATA} to be set. + * Both bits are required for AMX to be functional. + */ + if ((e->eax & XFEATURE_MASK_XTILE) != + XFEATURE_MASK_XTILE) { + e->eax &= ~XFEATURE_MASK_XTILE; + } + } + if (e->function == 0xd && e->index == 1) { + /* + * TDX doesn't support LBR yet. + * Disable bits from the XCR0 register. + */ + e->ecx &= ~XFEATURE_MASK_LBR; + /* + * TDX modules requires both CET_{U, S} to be set even + * if only one is supported. + */ + if (e->ecx & XFEATURE_MASK_CET) + e->ecx |= XFEATURE_MASK_CET; + } + } +} + +static void tdx_td_init(struct kvm_vm *vm, uint64_t attributes) +{ + const struct kvm_cpuid2 *cpuid; + struct kvm_tdx_init_vm init_vm; + + memset(&init_vm, 0, sizeof(struct kvm_tdx_init_vm)); + + cpuid = kvm_get_supported_cpuid(); + + memcpy(&init_vm.cpuid, cpuid, kvm_cpuid2_size(cpuid->nent)); + init_vm.attributes = attributes; + + tdx_apply_cpuid_restrictions(&init_vm.cpuid); + + tdx_ioctl(vm->fd, KVM_TDX_INIT_VM, 0, &init_vm); +} + +static void tdx_td_vcpu_init(struct kvm_vcpu *vcpu) +{ + const struct kvm_cpuid2 *cpuid = kvm_get_supported_cpuid(); + + vcpu_init_cpuid(vcpu, cpuid); + tdx_ioctl(vcpu->fd, KVM_TDX_INIT_VCPU, 0, NULL); +} + +static void tdx_init_mem_region(struct kvm_vm *vm, void *source_pages, + uint64_t gpa, uint64_t size) +{ + struct kvm_tdx_init_mem_region mem_region = { + .source_addr = (uint64_t)source_pages, + .gpa = gpa, + .nr_pages = size / PAGE_SIZE, + }; + uint32_t metadata = KVM_TDX_MEASURE_MEMORY_REGION; + + TEST_ASSERT((mem_region.nr_pages > 0) && + ((mem_region.nr_pages * PAGE_SIZE) == size), + "Cannot add partial pages to the guest memory.\n"); + TEST_ASSERT(((uint64_t)source_pages & (PAGE_SIZE - 1)) == 0, + "Source memory buffer is not page aligned\n"); + tdx_ioctl(vm->fd, KVM_TDX_INIT_MEM_REGION, metadata, &mem_region); +} + +static void tdx_td_finalizemr(struct kvm_vm *vm) +{ + tdx_ioctl(vm->fd, KVM_TDX_FINALIZE_VM, 0, NULL); +} + +/* + * TD creation/setup/finalization + */ + +static void tdx_enable_capabilities(struct kvm_vm *vm) +{ + int rc; + + rc = kvm_check_cap(KVM_CAP_X2APIC_API); + TEST_ASSERT(rc, "TDX: KVM_CAP_X2APIC_API is not supported!"); + rc = kvm_check_cap(KVM_CAP_SPLIT_IRQCHIP); + TEST_ASSERT(rc, "TDX: KVM_CAP_SPLIT_IRQCHIP is not supported!"); + + vm_enable_cap(vm, KVM_CAP_X2APIC_API, + KVM_X2APIC_API_USE_32BIT_IDS | + KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK); + vm_enable_cap(vm, KVM_CAP_SPLIT_IRQCHIP, 24); +} + +static void tdx_configure_memory_encryption(struct kvm_vm *vm) +{ + /* Configure shared/enCrypted bit for this VM according to TDX spec */ + vm->arch.s_bit = 1ULL << (vm->pa_bits - 1); + vm->arch.c_bit = 0; + /* Set gpa_protected_mask so that tagging/untagging of GPAs works */ + vm->gpa_protected_mask = vm->arch.s_bit; + /* There's no need to mask any encryption bits for PTEs */ + vm->arch.pte_me_mask = 0; + /* This VM is protected (has memory encryption) */ + vm->protected = true; +} + +static void tdx_apply_cr4_restrictions(struct kvm_sregs *sregs) +{ + /* TDX spec 11.6.2: CR4 bit MCE is fixed to 1 */ + sregs->cr4 |= X86_CR4_MCE; + + /* Set this because UEFI also sets this up, to handle XMM exceptions */ + sregs->cr4 |= X86_CR4_OSXMMEXCPT; + + /* TDX spec 11.6.2: CR4 bit VMXE and SMXE are fixed to 0 */ + sregs->cr4 &= ~(X86_CR4_VMXE | X86_CR4_SMXE); +} + +static void load_td_boot_code(struct kvm_vm *vm) +{ + void *boot_code_hva = addr_gpa2hva(vm, FOUR_GIGABYTES_GPA - TD_BOOT_CODE_SIZE); + + TEST_ASSERT(td_boot_code_end - reset_vector == 16, + "The reset vector must be 16 bytes in size."); + memcpy(boot_code_hva, td_boot, TD_BOOT_CODE_SIZE); +} + +static void load_td_per_vcpu_parameters(struct td_boot_parameters *params, + struct kvm_sregs *sregs, + struct kvm_vcpu *vcpu, + void *guest_code) +{ + /* Store vcpu_index to match what the TDX module would store internally */ + static uint32_t vcpu_index; + + struct td_per_vcpu_parameters *vcpu_params = &params->per_vcpu[vcpu_index]; + + TEST_ASSERT(vcpu->initial_stack_addr != 0, + "initial stack address should not be 0"); + TEST_ASSERT(vcpu->initial_stack_addr <= 0xffffffff, + "initial stack address must fit in 32 bits"); + TEST_ASSERT((uint64_t)guest_code <= 0xffffffff, + "guest_code must fit in 32 bits"); + TEST_ASSERT(sregs->cs.selector != 0, "cs.selector should not be 0"); + + vcpu_params->esp_gva = (uint32_t)(uint64_t)vcpu->initial_stack_addr; + vcpu_params->ljmp_target.eip_gva = (uint32_t)(uint64_t)guest_code; + vcpu_params->ljmp_target.code64_sel = sregs->cs.selector; + + vcpu_index++; +} + +static void load_td_common_parameters(struct td_boot_parameters *params, + struct kvm_sregs *sregs) +{ + /* Set parameters! */ + params->cr0 = sregs->cr0; + params->cr3 = sregs->cr3; + params->cr4 = sregs->cr4; + params->gdtr.limit = sregs->gdt.limit; + params->gdtr.base = sregs->gdt.base; + params->idtr.limit = sregs->idt.limit; + params->idtr.base = sregs->idt.base; + + TEST_ASSERT(params->cr0 != 0, "cr0 should not be 0"); + TEST_ASSERT(params->cr3 != 0, "cr3 should not be 0"); + TEST_ASSERT(params->cr4 != 0, "cr4 should not be 0"); + TEST_ASSERT(params->gdtr.base != 0, "gdt base address should not be 0"); +} + +static void load_td_boot_parameters(struct td_boot_parameters *params, + struct kvm_vcpu *vcpu, void *guest_code) +{ + struct kvm_sregs sregs; + + /* Assemble parameters in sregs */ + memset(&sregs, 0, sizeof(struct kvm_sregs)); + vcpu_setup_mode_sregs(vcpu->vm, &sregs); + tdx_apply_cr4_restrictions(&sregs); + kvm_setup_idt(vcpu->vm, &sregs.idt); + + if (!params->cr0) + load_td_common_parameters(params, &sregs); + + load_td_per_vcpu_parameters(params, &sregs, vcpu, guest_code); +} + +/** + * Adds a vCPU to a TD (Trusted Domain) with minimum defaults. It will not set + * up any general purpose registers as they will be initialized by the TDX. In + * TDX, vCPUs RIP is set to 0xFFFFFFF0. See Intel TDX EAS Section "Initial State + * of Guest GPRs" for more information on vCPUs initial register values when + * entering the TD first time. + * + * Input Args: + * vm - Virtual Machine + * vcpuid - The id of the VCPU to add to the VM. + */ +struct kvm_vcpu *td_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, void *guest_code) +{ + struct kvm_vcpu *vcpu; + + /* + * TD setup will not use the value of rip set in vm_vcpu_add anyway, so + * NULL can be used for guest_code. + */ + vcpu = vm_vcpu_add(vm, vcpu_id, NULL); + + tdx_td_vcpu_init(vcpu); + + load_td_boot_parameters(addr_gpa2hva(vm, TD_BOOT_PARAMETERS_GPA), + vcpu, guest_code); + + return vcpu; +} + +/** + * Iterate over set ranges within sparsebit @s. In each iteration, + * @range_begin and @range_end will take the beginning and end of the set range, + * which are of type sparsebit_idx_t. + * + * For example, if the range [3, 7] (inclusive) is set, within the iteration, + * @range_begin will take the value 3 and @range_end will take the value 7. + * + * Ensure that there is at least one bit set before using this macro with + * sparsebit_any_set(), because sparsebit_first_set() will abort if none are + * set. + */ +#define sparsebit_for_each_set_range(s, range_begin, range_end) \ + for (range_begin = sparsebit_first_set(s), \ + range_end = sparsebit_next_clear(s, range_begin) - 1; \ + range_begin && range_end; \ + range_begin = sparsebit_next_set(s, range_end), \ + range_end = sparsebit_next_clear(s, range_begin) - 1) +/* + * sparsebit_next_clear() can return 0 if [x, 2**64-1] are all set, and the -1 + * would then cause an underflow back to 2**64 - 1. This is expected and + * correct. + * + * If the last range in the sparsebit is [x, y] and we try to iterate, + * sparsebit_next_set() will return 0, and sparsebit_next_clear() will try and + * find the first range, but that's correct because the condition expression + * would cause us to quit the loop. + */ + +static void load_td_memory_region(struct kvm_vm *vm, + struct userspace_mem_region *region) +{ + const struct sparsebit *pages = region->protected_phy_pages; + const uint64_t hva_base = region->region.userspace_addr; + const vm_paddr_t gpa_base = region->region.guest_phys_addr; + const sparsebit_idx_t lowest_page_in_region = gpa_base >> + vm->page_shift; + + sparsebit_idx_t i; + sparsebit_idx_t j; + + if (!sparsebit_any_set(pages)) + return; + + sparsebit_for_each_set_range(pages, i, j) { + const uint64_t size_to_load = (j - i + 1) * vm->page_size; + const uint64_t offset = + (i - lowest_page_in_region) * vm->page_size; + const uint64_t hva = hva_base + offset; + const uint64_t gpa = gpa_base + offset; + void *source_addr; + + /* + * KVM_TDX_INIT_MEM_REGION ioctl cannot encrypt memory in place, + * hence we have to make a copy if there's only one backing + * memory source + */ + source_addr = mmap(NULL, size_to_load, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + TEST_ASSERT( + source_addr, + "Could not allocate memory for loading memory region"); + + memcpy(source_addr, (void *)hva, size_to_load); + + tdx_init_mem_region(vm, source_addr, gpa, size_to_load); + + munmap(source_addr, size_to_load); + } +} + +static void load_td_private_memory(struct kvm_vm *vm) +{ + int ctr; + struct userspace_mem_region *region; + + hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) { + load_td_memory_region(vm, region); + } +} + +struct kvm_vm *td_create(void) +{ + return ____vm_create(VM_MODE_DEFAULT, 0, KVM_X86_TDX_VM); +} + +static void td_setup_boot_code(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type) +{ + vm_vaddr_t addr; + size_t boot_code_allocation = round_up(TD_BOOT_CODE_SIZE, PAGE_SIZE); + vm_paddr_t boot_code_base_gpa = FOUR_GIGABYTES_GPA - boot_code_allocation; + size_t npages = DIV_ROUND_UP(boot_code_allocation, PAGE_SIZE); + + vm_userspace_mem_region_add(vm, src_type, boot_code_base_gpa, 1, npages, 0); + addr = vm_vaddr_alloc_1to1(vm, boot_code_allocation, boot_code_base_gpa, 1); + ASSERT_EQ(addr, boot_code_base_gpa); + + load_td_boot_code(vm); +} + +static size_t td_boot_parameters_size(void) +{ + int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); + size_t total_per_vcpu_parameters_size = + max_vcpus * sizeof(struct td_per_vcpu_parameters); + + return sizeof(struct td_boot_parameters) + total_per_vcpu_parameters_size; +} + +static void td_setup_boot_parameters(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type) +{ + vm_vaddr_t addr; + size_t boot_params_size = td_boot_parameters_size(); + int npages = DIV_ROUND_UP(boot_params_size, PAGE_SIZE); + size_t total_size = npages * PAGE_SIZE; + + vm_userspace_mem_region_add(vm, src_type, TD_BOOT_PARAMETERS_GPA, 2, npages, 0); + addr = vm_vaddr_alloc_1to1(vm, total_size, TD_BOOT_PARAMETERS_GPA, 2); + ASSERT_EQ(addr, TD_BOOT_PARAMETERS_GPA); +} + +void td_initialize(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t attributes) +{ + uint64_t nr_pages_required; + + tdx_enable_capabilities(vm); + + tdx_configure_memory_encryption(vm); + + tdx_td_init(vm, attributes); + + nr_pages_required = vm_nr_pages_required(VM_MODE_DEFAULT, 1, 0); + + /* + * Add memory (add 0th memslot) for TD. This will be used to setup the + * CPU (provide stack space for the CPU) and to load the elf file. + */ + vm_userspace_mem_region_add(vm, src_type, 0, 0, nr_pages_required, 0); + + kvm_vm_elf_load(vm, program_invocation_name); + + vm_init_descriptor_tables(vm); + + td_setup_boot_code(vm, src_type); + td_setup_boot_parameters(vm, src_type); +} + +void td_finalize(struct kvm_vm *vm) +{ + sync_exception_handlers_to_guest(vm); + + load_td_private_memory(vm); + + tdx_td_finalizemr(vm); +} -- 2.39.0.246.g2a6d74b583-goog

Some SSE instructions assume a 16-byte aligned stack, and GCC compiles assuming the stack is aligned: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=40838. This combination results in a #GP in guests.

Adding this compiler flag will generate an alternate prologue and epilogue to realign the runtime stack, which makes selftest code slower and bigger, but this is okay since we do not need selftest code to be extremely performant.

Similar issue discussed at https://lore.kernel.org/all/CAGtprH9yKvuaF5yruh3BupQe4BxDGiBQk3ExtY2m39yP-tp...

Signed-off-by: Ackerley Tng ackerleytng@google.com --- tools/testing/selftests/kvm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 317927d9c55bd..5f9cc1e6ee67e 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -205,7 +205,7 @@ LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include else LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include endif -CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ +CFLAGS += -mstackrealign -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ -I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \

From: Erdem Aktas erdemaktas@google.com

Adding a test to verify TDX lifecycle by creating a TD and running a dummy TDG.VP.VMCALL <Instruction.IO> inside it.

Signed-off-by: Erdem Aktas erdemaktas@google.com Signed-off-by: Ryan Afranji afranji@google.com Signed-off-by: Sagi Shahar sagis@google.com Co-developed-by: Ackerley Tng ackerleytng@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- Changes RFCv2 -> RFCv3 + Add gitignore for tdx_vm_tests binary + Thanks to Isaku for the comment about saving rbp separately for gcc! In this revision, the assembly that wraps tdcall has been mostly taken from the kernel’s implementation, which would be familiar to you! + TDX test-related code is now grouped in tools/testing/selftests/kvm/include/x86_64/tdx/test_util.{c,h} and test-related functions and macros are prefixed with tdx_test to indicate its purpose. --- tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 4 + .../selftests/kvm/include/x86_64/tdx/tdcall.h | 35 ++++++++ .../selftests/kvm/include/x86_64/tdx/tdx.h | 12 +++ .../kvm/include/x86_64/tdx/test_util.h | 52 +++++++++++ .../selftests/kvm/lib/x86_64/tdx/tdcall.S | 90 +++++++++++++++++++ .../selftests/kvm/lib/x86_64/tdx/tdx.c | 27 ++++++ .../selftests/kvm/lib/x86_64/tdx/test_util.c | 34 +++++++ .../selftests/kvm/x86_64/tdx_vm_tests.c | 45 ++++++++++ 9 files changed, 300 insertions(+) create mode 100644 tools/testing/selftests/kvm/include/x86_64/tdx/tdcall.h create mode 100644 tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h create mode 100644 tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h create mode 100644 tools/testing/selftests/kvm/lib/x86_64/tdx/tdcall.S create mode 100644 tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c create mode 100644 tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c create mode 100644 tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 813e7610619d9..370d6430b32b4 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -65,6 +65,7 @@ /x86_64/xss_msr_test /x86_64/vmx_pmu_caps_test /x86_64/triple_fault_event_test +/x86_64/tdx_vm_tests /access_tracking_perf_test /demand_paging_test /dirty_log_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 5f9cc1e6ee67e..9f289322a4933 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -61,6 +61,9 @@ LIBKVM_x86_64 += lib/x86_64/vmx.c LIBKVM_x86_64 += lib/x86_64/sev.c LIBKVM_x86_64 += lib/x86_64/tdx/tdx_util.c LIBKVM_x86_64 += lib/x86_64/tdx/td_boot.S +LIBKVM_x86_64 += lib/x86_64/tdx/tdcall.S +LIBKVM_x86_64 += lib/x86_64/tdx/tdx.c +LIBKVM_x86_64 += lib/x86_64/tdx/test_util.c

LIBKVM_aarch64 += lib/aarch64/gic.c LIBKVM_aarch64 += lib/aarch64/gic_v3.c @@ -148,6 +151,7 @@ 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 += x86_64/tdx_vm_tests

# 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/include/x86_64/tdx/tdcall.h b/tools/testing/selftests/kvm/include/x86_64/tdx/tdcall.h new file mode 100644 index 0000000000000..78001bfec9c8d --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/tdcall.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Adapted from arch/x86/include/asm/shared/tdx.h */ + +#ifndef SELFTESTS_TDX_TDCALL_H +#define SELFTESTS_TDX_TDCALL_H + +#include <linux/bits.h> +#include <linux/types.h> + +#define TDG_VP_VMCALL_INSTRUCTION_IO_READ 0 +#define TDG_VP_VMCALL_INSTRUCTION_IO_WRITE 1 + +#define TDX_HCALL_HAS_OUTPUT BIT(0) + +#define TDX_HYPERCALL_STANDARD 0 + +/* + * Used in __tdx_hypercall() to pass down and get back registers' values of + * the TDCALL instruction when requesting services from the VMM. + * + * This is a software only structure and not part of the TDX module/VMM ABI. + */ +struct tdx_hypercall_args { + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; +}; + +/* Used to request services from the VMM */ +u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags); + +#endif // SELFTESTS_TDX_TDCALL_H diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h new file mode 100644 index 0000000000000..a7161efe4ee2e --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_TDX_TDX_H +#define SELFTEST_TDX_TDX_H + +#include <stdint.h> + +#define TDG_VP_VMCALL_INSTRUCTION_IO 30 + +uint64_t tdg_vp_vmcall_instruction_io(uint64_t port, uint64_t size, + uint64_t write, uint64_t *data); + +#endif // SELFTEST_TDX_TDX_H diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h b/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h new file mode 100644 index 0000000000000..b570b6d978ff1 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_TDX_TEST_UTIL_H +#define SELFTEST_TDX_TEST_UTIL_H + +#include <stdbool.h> + +#include "tdcall.h" + +#define TDX_TEST_SUCCESS_PORT 0x30 +#define TDX_TEST_SUCCESS_SIZE 4 + +/** + * Assert that tdx_test_success() was called in the guest. + */ +#define TDX_TEST_ASSERT_SUCCESS(VCPU) \ + (TEST_ASSERT( \ + ((VCPU)->run->exit_reason == KVM_EXIT_IO) && \ + ((VCPU)->run->io.port == TDX_TEST_SUCCESS_PORT) && \ + ((VCPU)->run->io.size == TDX_TEST_SUCCESS_SIZE) && \ + ((VCPU)->run->io.direction == \ + TDG_VP_VMCALL_INSTRUCTION_IO_WRITE), \ + "Unexpected exit values while waiting for test completion: %u (%s) %d %d %d\n", \ + (VCPU)->run->exit_reason, \ + exit_reason_str((VCPU)->run->exit_reason), \ + (VCPU)->run->io.port, (VCPU)->run->io.size, \ + (VCPU)->run->io.direction)) + +/** + * Run a test in a new process. + * + * There might be multiple tests we are running and if one test fails, it will + * prevent the subsequent tests to run due to how tests are failing with + * TEST_ASSERT function. The run_in_new_process function will run a test in a + * new process context and wait for it to finish or fail to prevent TEST_ASSERT + * to kill the main testing process. + */ +void run_in_new_process(void (*func)(void)); + +/** + * Verify that the TDX is supported by KVM. + */ +bool is_tdx_enabled(void); + +/** + * Report test success to userspace. + * + * Use TDX_TEST_ASSERT_SUCCESS() to assert that this function was called in the + * guest. + */ +void tdx_test_success(void); + +#endif // SELFTEST_TDX_TEST_UTIL_H diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdcall.S b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdcall.S new file mode 100644 index 0000000000000..df9c1ed4bb2d1 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdcall.S @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Adapted from arch/x86/coco/tdx/tdcall.S */ + +#define TDX_HYPERCALL_r10 0 /* offsetof(struct tdx_hypercall_args, r10) */ +#define TDX_HYPERCALL_r11 8 /* offsetof(struct tdx_hypercall_args, r11) */ +#define TDX_HYPERCALL_r12 16 /* offsetof(struct tdx_hypercall_args, r12) */ +#define TDX_HYPERCALL_r13 24 /* offsetof(struct tdx_hypercall_args, r13) */ +#define TDX_HYPERCALL_r14 32 /* offsetof(struct tdx_hypercall_args, r14) */ +#define TDX_HYPERCALL_r15 40 /* offsetof(struct tdx_hypercall_args, r15) */ + +/* + * Bitmasks of exposed registers (with VMM). + */ +#define TDX_R10 0x400 +#define TDX_R11 0x800 +#define TDX_R12 0x1000 +#define TDX_R13 0x2000 +#define TDX_R14 0x4000 +#define TDX_R15 0x8000 + +#define TDX_HCALL_HAS_OUTPUT 0x1 + +/* + * These registers are clobbered to hold arguments for each + * TDVMCALL. They are safe to expose to the VMM. + * Each bit in this mask represents a register ID. Bit field + * details can be found in TDX GHCI specification, section + * titled "TDCALL [TDG.VP.VMCALL] leaf". + */ +#define TDVMCALL_EXPOSE_REGS_MASK ( TDX_R10 | TDX_R11 | \ + TDX_R12 | TDX_R13 | \ + TDX_R14 | TDX_R15 ) + +.code64 +.section .text + +.globl __tdx_hypercall +.type __tdx_hypercall, @function +__tdx_hypercall: + /* Set up stack frame */ + push %rbp + movq %rsp, %rbp + + /* Save callee-saved GPRs as mandated by the x86_64 ABI */ + push %r15 + push %r14 + push %r13 + push %r12 + + /* Mangle function call ABI into TDCALL ABI: */ + /* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */ + xor %eax, %eax + + /* Copy hypercall registers from arg struct: */ + movq TDX_HYPERCALL_r10(%rdi), %r10 + movq TDX_HYPERCALL_r11(%rdi), %r11 + movq TDX_HYPERCALL_r12(%rdi), %r12 + movq TDX_HYPERCALL_r13(%rdi), %r13 + movq TDX_HYPERCALL_r14(%rdi), %r14 + movq TDX_HYPERCALL_r15(%rdi), %r15 + + movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx + + tdcall + + /* TDVMCALL leaf return code is in R10 */ + movq %r10, %rax + + /* Copy hypercall result registers to arg struct if needed */ + testq $TDX_HCALL_HAS_OUTPUT, %rsi + jz .Lout + + movq %r10, TDX_HYPERCALL_r10(%rdi) + movq %r11, TDX_HYPERCALL_r11(%rdi) + movq %r12, TDX_HYPERCALL_r12(%rdi) + movq %r13, TDX_HYPERCALL_r13(%rdi) + movq %r14, TDX_HYPERCALL_r14(%rdi) + movq %r15, TDX_HYPERCALL_r15(%rdi) +.Lout: + /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + pop %rbp + ret + +/* Disable executable stack */ +.section .note.GNU-stack,"",%progbits diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c new file mode 100644 index 0000000000000..c2414523487a7 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "tdx/tdcall.h" +#include "tdx/tdx.h" + +uint64_t tdg_vp_vmcall_instruction_io(uint64_t port, uint64_t size, + uint64_t write, uint64_t *data) +{ + uint64_t ret; + struct tdx_hypercall_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = TDG_VP_VMCALL_INSTRUCTION_IO, + .r12 = size, + .r13 = write, + .r14 = port, + }; + + if (write) + args.r15 = *data; + + ret = __tdx_hypercall(&args, write ? 0 : TDX_HCALL_HAS_OUTPUT); + + if (!write) + *data = args.r11; + + return ret; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c new file mode 100644 index 0000000000000..6905d0ca38774 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <stdbool.h> +#include <stdint.h> +#include <stdlib.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "kvm_util_base.h" +#include "tdx/tdx.h" +#include "tdx/test_util.h" + +void run_in_new_process(void (*func)(void)) +{ + if (fork() == 0) { + func(); + exit(0); + } + wait(NULL); +} + +bool is_tdx_enabled(void) +{ + return !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_TDX_VM)); +} + +void tdx_test_success(void) +{ + uint64_t code = 0; + + tdg_vp_vmcall_instruction_io(TDX_TEST_SUCCESS_PORT, + TDX_TEST_SUCCESS_SIZE, + TDG_VP_VMCALL_INSTRUCTION_IO_WRITE, &code); +} diff --git a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c new file mode 100644 index 0000000000000..a18d1c9d60264 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <signal.h> +#include "kvm_util_base.h" +#include "tdx/tdx_util.h" +#include "tdx/test_util.h" +#include "test_util.h" + +void guest_code_lifecycle(void) +{ + tdx_test_success(); +} + +void verify_td_lifecycle(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + vm = td_create(); + td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); + vcpu = td_vcpu_add(vm, 0, guest_code_lifecycle); + td_finalize(vm); + + printf("Verifying TD lifecycle:\n"); + + vcpu_run(vcpu); + TDX_TEST_ASSERT_SUCCESS(vcpu); + + kvm_vm_free(vm); + printf("\t ... PASSED\n"); +} + +int main(int argc, char **argv) +{ + setbuf(stdout, NULL); + + if (!is_tdx_enabled()) { + print_skip("TDX is not supported by the KVM"); + exit(KSFT_SKIP); + } + + run_in_new_process(&verify_td_lifecycle); + + return 0; +} -- 2.39.0.246.g2a6d74b583-goog

From: Erdem Aktas erdemaktas@google.com

Verifies TDVMCALL<INSTRUCTION.IO> READ and WRITE operations.

Signed-off-by: Erdem Aktas erdemaktas@google.com Signed-off-by: Sagi Shahar sagis@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../kvm/include/x86_64/tdx/test_util.h | 34 ++++++++ .../selftests/kvm/x86_64/tdx_vm_tests.c | 82 +++++++++++++++++++ 2 files changed, 116 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h b/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h index 6d69921136bd2..95a5d5be7f0bf 100644 --- a/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h @@ -9,6 +9,40 @@ #define TDX_TEST_SUCCESS_PORT 0x30 #define TDX_TEST_SUCCESS_SIZE 4

+/** + * Assert that some IO operation involving tdg_vp_vmcall_instruction_io() was + * called in the guest. + */ +#define TDX_TEST_ASSERT_IO(VCPU, PORT, SIZE, DIR) \ + do { \ + TEST_ASSERT((VCPU)->run->exit_reason == KVM_EXIT_IO, \ + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", \ + (VCPU)->run->exit_reason, \ + exit_reason_str((VCPU)->run->exit_reason)); \ + \ + TEST_ASSERT(((VCPU)->run->exit_reason == KVM_EXIT_IO) && \ + ((VCPU)->run->io.port == (PORT)) && \ + ((VCPU)->run->io.size == (SIZE)) && \ + ((VCPU)->run->io.direction == (DIR)), \ + "Got unexpected IO exit values: %u (%s) %d %d %d\n", \ + (VCPU)->run->exit_reason, \ + exit_reason_str((VCPU)->run->exit_reason), \ + (VCPU)->run->io.port, (VCPU)->run->io.size, \ + (VCPU)->run->io.direction); \ + } while (0) + +/** + * Check and report if there was some failure in the guest, either an exception + * like a triple fault, or if a tdx_test_fatal() was hit. + */ +#define TDX_TEST_CHECK_GUEST_FAILURE(VCPU) \ + do { \ + if ((VCPU)->run->exit_reason == KVM_EXIT_SYSTEM_EVENT) \ + TEST_FAIL("Guest reported error. error code: %lld (0x%llx)\n", \ + (VCPU)->run->system_event.data[1], \ + (VCPU)->run->system_event.data[1]); \ + } while (0) + /** * Assert that tdx_test_success() was called in the guest. */ diff --git a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c index 627d60b573bb6..885c2b6bb1b96 100644 --- a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c +++ b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c @@ -2,6 +2,7 @@

#include <signal.h> #include "kvm_util_base.h" +#include "tdx/tdcall.h" #include "tdx/tdx.h" #include "tdx/tdx_util.h" #include "tdx/test_util.h" @@ -73,6 +74,86 @@ void verify_report_fatal_error(void) printf("\t ... PASSED\n"); }

+#define TDX_IOEXIT_TEST_PORT 0x50 + +/* + * Verifies IO functionality by writing a |value| to a predefined port. + * Verifies that the read value is |value| + 1 from the same port. + * If all the tests are passed then write a value to port TDX_TEST_PORT + */ +void guest_ioexit(void) +{ + uint64_t data_out, data_in, delta; + uint64_t ret; + + data_out = 0xAB; + ret = tdg_vp_vmcall_instruction_io(TDX_IOEXIT_TEST_PORT, 1, + TDG_VP_VMCALL_INSTRUCTION_IO_WRITE, + &data_out); + if (ret) + tdx_test_fatal(ret); + + ret = tdg_vp_vmcall_instruction_io(TDX_IOEXIT_TEST_PORT, 1, + TDG_VP_VMCALL_INSTRUCTION_IO_READ, + &data_in); + if (ret) + tdx_test_fatal(ret); + + delta = data_in - data_out; + if (delta != 1) + tdx_test_fatal(ret); + + tdx_test_success(); +} + +void verify_td_ioexit(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + uint32_t port_data; + + vm = td_create(); + td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); + vcpu = td_vcpu_add(vm, 0, guest_ioexit); + td_finalize(vm); + + printf("Verifying TD IO Exit:\n"); + + /* Wait for guest to do a IO write */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_IO(vcpu, TDX_IOEXIT_TEST_PORT, 1, + TDG_VP_VMCALL_INSTRUCTION_IO_WRITE); + port_data = *(uint8_t *)((void *)vcpu->run + vcpu->run->io.data_offset); + + printf("\t ... IO WRITE: OK\n"); + + /* + * Wait for the guest to do a IO read. Provide the previous written data + * + 1 back to the guest + */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_IO(vcpu, TDX_IOEXIT_TEST_PORT, 1, + TDG_VP_VMCALL_INSTRUCTION_IO_READ); + *(uint8_t *)((void *)vcpu->run + vcpu->run->io.data_offset) = port_data + 1; + + printf("\t ... IO READ: OK\n"); + + /* + * Wait for the guest to complete execution successfully. The read + * value is checked within the guest. + */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_SUCCESS(vcpu); + + printf("\t ... IO verify read/write values: OK\n"); + kvm_vm_free(vm); + printf("\t ... PASSED\n"); +} + int main(int argc, char **argv) { setbuf(stdout, NULL); @@ -84,6 +165,7 @@ int main(int argc, char **argv)

run_in_new_process(&verify_td_lifecycle); run_in_new_process(&verify_report_fatal_error); + run_in_new_process(&verify_td_ioexit);

return 0; }

From: Sagi Shahar sagis@google.com

The test calls get_td_vmcall_info from the guest and verifies the expected returned values.

Signed-off-by: Sagi Shahar sagis@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/include/x86_64/tdx/tdx.h | 3 + .../kvm/include/x86_64/tdx/test_util.h | 27 +++++++ .../selftests/kvm/lib/x86_64/tdx/tdx.c | 23 ++++++ .../selftests/kvm/lib/x86_64/tdx/test_util.c | 46 +++++++++++ .../selftests/kvm/x86_64/tdx_vm_tests.c | 80 +++++++++++++++++++ 5 files changed, 179 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h index 28959bdb07628..37ad16943e299 100644 --- a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h @@ -4,6 +4,7 @@

#include <stdint.h>

+#define TDG_VP_VMCALL_GET_TD_VM_CALL_INFO 0x10000 #define TDG_VP_VMCALL_REPORT_FATAL_ERROR 0x10003

#define TDG_VP_VMCALL_INSTRUCTION_IO 30 @@ -11,5 +12,7 @@ uint64_t tdg_vp_vmcall_instruction_io(uint64_t port, uint64_t size, uint64_t write, uint64_t *data); void tdg_vp_vmcall_report_fatal_error(uint64_t error_code, uint64_t data_gpa); +uint64_t tdg_vp_vmcall_get_td_vmcall_info(uint64_t *r11, uint64_t *r12, + uint64_t *r13, uint64_t *r14);

#endif // SELFTEST_TDX_TDX_H diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h b/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h index af0ddbfe8d71b..8a9b6a1bec3eb 100644 --- a/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/test_util.h @@ -4,6 +4,7 @@

#include <stdbool.h>

+#include "kvm_util_base.h" #include "tdcall.h"

#define TDX_TEST_SUCCESS_PORT 0x30 @@ -111,4 +112,30 @@ void tdx_test_fatal_with_data(uint64_t error_code, uint64_t data_gpa); */ uint64_t tdx_test_report_to_user_space(uint32_t data);

+/** + * Report a 64 bit value from the guest to user space using TDG.VP.VMCALL + * <Instruction.IO> call. + * + * Data is sent to host in 2 calls. LSB is sent (and needs to be read) first. + */ +uint64_t tdx_test_send_64bit(uint64_t port, uint64_t data); + +/** + * Report a 64 bit value from the guest to user space using TDG.VP.VMCALL + * <Instruction.IO> call. Data is reported on port TDX_TEST_REPORT_PORT. + */ +uint64_t tdx_test_report_64bit_to_user_space(uint64_t data); + +/** + * Read a 64 bit value from the guest in user space, sent using + * tdx_test_send_64bit(). + */ +uint64_t tdx_test_read_64bit(struct kvm_vcpu *vcpu, uint64_t port); + +/** + * Read a 64 bit value from the guest in user space, sent using + * tdx_test_report_64bit_to_user_space. + */ +uint64_t tdx_test_read_64bit_report_from_guest(struct kvm_vcpu *vcpu); + #endif // SELFTEST_TDX_TEST_UTIL_H diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c index e8c399f2277cf..7254d61515db2 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c @@ -43,3 +43,26 @@ void tdg_vp_vmcall_report_fatal_error(uint64_t error_code, uint64_t data_gpa)

__tdx_hypercall(&args, 0); } + +uint64_t tdg_vp_vmcall_get_td_vmcall_info(uint64_t *r11, uint64_t *r12, + uint64_t *r13, uint64_t *r14) +{ + uint64_t ret; + struct tdx_hypercall_args args = { + .r11 = TDG_VP_VMCALL_GET_TD_VM_CALL_INFO, + .r12 = 0, + }; + + ret = __tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT); + + if (r11) + *r11 = args.r11; + if (r12) + *r12 = args.r12; + if (r13) + *r13 = args.r13; + if (r14) + *r14 = args.r14; + + return ret; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c index 55c5a1e634df7..3ae651cd5fac4 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/test_util.c @@ -7,6 +7,7 @@ #include <unistd.h>

#include "kvm_util_base.h" +#include "tdx/tdcall.h" #include "tdx/tdx.h" #include "tdx/test_util.h"

@@ -53,3 +54,48 @@ uint64_t tdx_test_report_to_user_space(uint32_t data) TDG_VP_VMCALL_INSTRUCTION_IO_WRITE, &data_64); } + +uint64_t tdx_test_send_64bit(uint64_t port, uint64_t data) +{ + uint64_t err; + uint64_t data_lo = data & 0xFFFFFFFF; + uint64_t data_hi = (data >> 32) & 0xFFFFFFFF; + + err = tdg_vp_vmcall_instruction_io(port, 4, + TDG_VP_VMCALL_INSTRUCTION_IO_WRITE, + &data_lo); + if (err) + return err; + + return tdg_vp_vmcall_instruction_io(port, 4, + TDG_VP_VMCALL_INSTRUCTION_IO_WRITE, + &data_hi); +} + +uint64_t tdx_test_report_64bit_to_user_space(uint64_t data) +{ + return tdx_test_send_64bit(TDX_TEST_REPORT_PORT, data); +} + +uint64_t tdx_test_read_64bit(struct kvm_vcpu *vcpu, uint64_t port) +{ + uint32_t lo, hi; + uint64_t res; + + TDX_TEST_ASSERT_IO(vcpu, port, 4, TDG_VP_VMCALL_INSTRUCTION_IO_WRITE); + lo = *(uint32_t *)((void *)vcpu->run + vcpu->run->io.data_offset); + + vcpu_run(vcpu); + + TDX_TEST_ASSERT_IO(vcpu, port, 4, TDG_VP_VMCALL_INSTRUCTION_IO_WRITE); + hi = *(uint32_t *)((void *)vcpu->run + vcpu->run->io.data_offset); + + res = hi; + res = (res << 32) | lo; + return res; +} + +uint64_t tdx_test_read_64bit_report_from_guest(struct kvm_vcpu *vcpu) +{ + return tdx_test_read_64bit(vcpu, TDX_TEST_REPORT_PORT); +} diff --git a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c index b6072769967fa..188442a734dca 100644 --- a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c +++ b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c @@ -259,6 +259,85 @@ void verify_td_cpuid(void) printf("\t ... PASSED\n"); }

+/* + * Verifies get_td_vmcall_info functionality. + */ +void guest_code_get_td_vmcall_info(void) +{ + uint64_t err; + uint64_t r11, r12, r13, r14; + + err = tdg_vp_vmcall_get_td_vmcall_info(&r11, &r12, &r13, &r14); + if (err) + tdx_test_fatal(err); + + err = tdx_test_report_64bit_to_user_space(r11); + if (err) + tdx_test_fatal(err); + + err = tdx_test_report_64bit_to_user_space(r12); + if (err) + tdx_test_fatal(err); + + err = tdx_test_report_64bit_to_user_space(r13); + if (err) + tdx_test_fatal(err); + + err = tdx_test_report_64bit_to_user_space(r14); + if (err) + tdx_test_fatal(err); + + tdx_test_success(); +} + +void verify_get_td_vmcall_info(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + uint64_t r11, r12, r13, r14; + + vm = td_create(); + td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); + vcpu = td_vcpu_add(vm, 0, guest_code_get_td_vmcall_info); + td_finalize(vm); + + printf("Verifying TD get vmcall info:\n"); + + /* Wait for guest to report r11 value */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + r11 = tdx_test_read_64bit_report_from_guest(vcpu); + + /* Wait for guest to report r12 value */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + r12 = tdx_test_read_64bit_report_from_guest(vcpu); + + /* Wait for guest to report r13 value */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + r13 = tdx_test_read_64bit_report_from_guest(vcpu); + + /* Wait for guest to report r14 value */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + r14 = tdx_test_read_64bit_report_from_guest(vcpu); + + ASSERT_EQ(r11, 0); + ASSERT_EQ(r12, 0); + ASSERT_EQ(r13, 0); + ASSERT_EQ(r14, 0); + + /* Wait for guest to complete execution */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_SUCCESS(vcpu); + + kvm_vm_free(vm); + printf("\t ... PASSED\n"); +} + int main(int argc, char **argv) { setbuf(stdout, NULL); @@ -272,6 +351,7 @@ int main(int argc, char **argv) run_in_new_process(&verify_report_fatal_error); run_in_new_process(&verify_td_ioexit); run_in_new_process(&verify_td_cpuid); + run_in_new_process(&verify_get_td_vmcall_info);

return 0; }

From: Sagi Shahar sagis@google.com

The test verifies IO reads of various sizes from the host to the guest.

Signed-off-by: Sagi Shahar sagis@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/x86_64/tdx_vm_tests.c | 87 +++++++++++++++++++ 1 file changed, 87 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c index ac23d1ad1e687..71aa4e5907a05 100644 --- a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c +++ b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c @@ -428,6 +428,92 @@ void verify_guest_writes(void) printf("\t ... PASSED\n"); }

+#define TDX_IO_READS_TEST_PORT 0x52 + +/* + * Verifies IO functionality by reading values of different sizes + * from the host. + */ +void guest_io_reads(void) +{ + uint64_t data; + uint64_t ret; + + ret = tdg_vp_vmcall_instruction_io(TDX_IO_READS_TEST_PORT, 1, + TDG_VP_VMCALL_INSTRUCTION_IO_READ, + &data); + if (ret) + tdx_test_fatal(ret); + if (data != 0xAB) + tdx_test_fatal(1); + + ret = tdg_vp_vmcall_instruction_io(TDX_IO_READS_TEST_PORT, 2, + TDG_VP_VMCALL_INSTRUCTION_IO_READ, + &data); + if (ret) + tdx_test_fatal(ret); + if (data != 0xABCD) + tdx_test_fatal(2); + + ret = tdg_vp_vmcall_instruction_io(TDX_IO_READS_TEST_PORT, 4, + TDG_VP_VMCALL_INSTRUCTION_IO_READ, + &data); + if (ret) + tdx_test_fatal(ret); + if (data != 0xFFABCDEF) + tdx_test_fatal(4); + + // Read an invalid number of bytes. + ret = tdg_vp_vmcall_instruction_io(TDX_IO_READS_TEST_PORT, 5, + TDG_VP_VMCALL_INSTRUCTION_IO_READ, + &data); + if (ret) + tdx_test_fatal(ret); + + tdx_test_success(); +} + +void verify_guest_reads(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + vm = td_create(); + td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); + vcpu = td_vcpu_add(vm, 0, guest_io_reads); + td_finalize(vm); + + printf("Verifying guest reads:\n"); + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_IO(vcpu, TDX_IO_READS_TEST_PORT, 1, + TDG_VP_VMCALL_INSTRUCTION_IO_READ); + *(uint8_t *)((void *)vcpu->run + vcpu->run->io.data_offset) = 0xAB; + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_IO(vcpu, TDX_IO_READS_TEST_PORT, 2, + TDG_VP_VMCALL_INSTRUCTION_IO_READ); + *(uint16_t *)((void *)vcpu->run + vcpu->run->io.data_offset) = 0xABCD; + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_IO(vcpu, TDX_IO_READS_TEST_PORT, 4, + TDG_VP_VMCALL_INSTRUCTION_IO_READ); + *(uint32_t *)((void *)vcpu->run + vcpu->run->io.data_offset) = 0xFFABCDEF; + + vcpu_run(vcpu); + ASSERT_EQ(vcpu->run->exit_reason, KVM_EXIT_SYSTEM_EVENT); + ASSERT_EQ(vcpu->run->system_event.data[1], TDG_VP_VMCALL_INVALID_OPERAND); + + vcpu_run(vcpu); + TDX_TEST_ASSERT_SUCCESS(vcpu); + + kvm_vm_free(vm); + printf("\t ... PASSED\n"); +} + int main(int argc, char **argv) { setbuf(stdout, NULL); @@ -443,6 +529,7 @@ int main(int argc, char **argv) run_in_new_process(&verify_td_cpuid); run_in_new_process(&verify_get_td_vmcall_info); run_in_new_process(&verify_guest_writes); + run_in_new_process(&verify_guest_reads);

return 0; }

From: Sagi Shahar sagis@google.com

The test verifies that the guest runs TDVMCALL<INSTRUCTION.HLT> and the guest vCPU enters to the halted state.

Signed-off-by: Erdem Aktas erdemaktas@google.com Signed-off-by: Sagi Shahar sagis@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/include/x86_64/tdx/tdx.h | 3 + .../selftests/kvm/lib/x86_64/tdx/tdx.c | 10 +++ .../selftests/kvm/x86_64/tdx_vm_tests.c | 78 +++++++++++++++++++ 3 files changed, 91 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h index fbac1951cfe35..7eba9d80b3681 100644 --- a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h @@ -7,10 +7,12 @@ #define TDG_VP_VMCALL_GET_TD_VM_CALL_INFO 0x10000 #define TDG_VP_VMCALL_REPORT_FATAL_ERROR 0x10003

+#define TDG_VP_VMCALL_INSTRUCTION_HLT 12 #define TDG_VP_VMCALL_INSTRUCTION_IO 30 #define TDG_VP_VMCALL_INSTRUCTION_RDMSR 31 #define TDG_VP_VMCALL_INSTRUCTION_WRMSR 32

+ uint64_t tdg_vp_vmcall_instruction_io(uint64_t port, uint64_t size, uint64_t write, uint64_t *data); void tdg_vp_vmcall_report_fatal_error(uint64_t error_code, uint64_t data_gpa); @@ -18,5 +20,6 @@ uint64_t tdg_vp_vmcall_get_td_vmcall_info(uint64_t *r11, uint64_t *r12, uint64_t *r13, uint64_t *r14); uint64_t tdg_vp_vmcall_instruction_rdmsr(uint64_t index, uint64_t *ret_value); uint64_t tdg_vp_vmcall_instruction_wrmsr(uint64_t index, uint64_t value); +uint64_t tdg_vp_vmcall_instruction_hlt(uint64_t interrupt_blocked_flag);

#endif // SELFTEST_TDX_TDX_H diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c index 43088d6f40b50..1af0626c2a4ad 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c @@ -93,3 +93,13 @@ uint64_t tdg_vp_vmcall_instruction_wrmsr(uint64_t index, uint64_t value)

return __tdx_hypercall(&args, 0); } + +uint64_t tdg_vp_vmcall_instruction_hlt(uint64_t interrupt_blocked_flag) +{ + struct tdx_hypercall_args args = { + .r11 = TDG_VP_VMCALL_INSTRUCTION_HLT, + .r12 = interrupt_blocked_flag, + }; + + return __tdx_hypercall(&args, 0); +} diff --git a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c index 65ca1ec2a6e82..346c1e07af9c0 100644 --- a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c +++ b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c @@ -728,6 +728,83 @@ void verify_guest_msr_writes(void) printf("\t ... PASSED\n"); }

+/* + * Verifies HLT functionality. + */ +void guest_hlt(void) +{ + uint64_t ret; + uint64_t interrupt_blocked_flag; + + interrupt_blocked_flag = 0; + ret = tdg_vp_vmcall_instruction_hlt(interrupt_blocked_flag); + if (ret) + tdx_test_fatal(ret); + + tdx_test_success(); +} + +void _verify_guest_hlt(int signum); + +void wake_me(int interval) +{ + struct sigaction action; + + action.sa_handler = _verify_guest_hlt; + sigemptyset(&action.sa_mask); + action.sa_flags = 0; + + TEST_ASSERT(sigaction(SIGALRM, &action, NULL) == 0, + "Could not set the alarm handler!"); + + alarm(interval); +} + +void _verify_guest_hlt(int signum) +{ + struct kvm_vm *vm; + static struct kvm_vcpu *vcpu; + + /* + * This function will also be called by SIGALRM handler to check the + * vCPU MP State. If vm has been initialized, then we are in the signal + * handler. Check the MP state and let the guest run again. + */ + if (vcpu != NULL) { + struct kvm_mp_state mp_state; + + vcpu_mp_state_get(vcpu, &mp_state); + ASSERT_EQ(mp_state.mp_state, KVM_MP_STATE_HALTED); + + /* Let the guest to run and finish the test.*/ + mp_state.mp_state = KVM_MP_STATE_RUNNABLE; + vcpu_mp_state_set(vcpu, &mp_state); + return; + } + + vm = td_create(); + td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); + vcpu = td_vcpu_add(vm, 0, guest_hlt); + td_finalize(vm); + + printf("Verifying HLT:\n"); + + printf("\t ... Running guest\n"); + + /* Wait 1 second for guest to execute HLT */ + wake_me(1); + vcpu_run(vcpu); + + TDX_TEST_ASSERT_SUCCESS(vcpu); + + kvm_vm_free(vm); + printf("\t ... PASSED\n"); +} + +void verify_guest_hlt(void) +{ + _verify_guest_hlt(0); +}

int main(int argc, char **argv) { @@ -747,6 +824,7 @@ int main(int argc, char **argv) run_in_new_process(&verify_guest_reads); run_in_new_process(&verify_guest_msr_writes); run_in_new_process(&verify_guest_msr_reads); + run_in_new_process(&verify_guest_hlt);

return 0; }

From: Sagi Shahar sagis@google.com

The test verifies MMIO writes of various sizes from the guest to the host.

Signed-off-by: Sagi Shahar sagis@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/include/x86_64/tdx/tdx.h | 2 + .../selftests/kvm/lib/x86_64/tdx/tdx.c | 14 +++ .../selftests/kvm/x86_64/tdx_vm_tests.c | 85 +++++++++++++++++++ 3 files changed, 101 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h index 8dd6a65485260..f2a90ad8a55c6 100644 --- a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h @@ -24,5 +24,7 @@ uint64_t tdg_vp_vmcall_instruction_wrmsr(uint64_t index, uint64_t value); uint64_t tdg_vp_vmcall_instruction_hlt(uint64_t interrupt_blocked_flag); uint64_t tdg_vp_vmcall_ve_request_mmio_read(uint64_t address, uint64_t size, uint64_t *data_out); +uint64_t tdg_vp_vmcall_ve_request_mmio_write(uint64_t address, uint64_t size, + uint64_t data_in);

#endif // SELFTEST_TDX_TDX_H diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c index dcdacf08bcd60..8b12ac7049572 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c @@ -122,3 +122,17 @@ uint64_t tdg_vp_vmcall_ve_request_mmio_read(uint64_t address, uint64_t size,

return ret; } + +uint64_t tdg_vp_vmcall_ve_request_mmio_write(uint64_t address, uint64_t size, + uint64_t data_in) +{ + struct tdx_hypercall_args args = { + .r11 = TDG_VP_VMCALL_VE_REQUEST_MMIO, + .r12 = size, + .r13 = TDG_VP_VMCALL_VE_REQUEST_MMIO_WRITE, + .r14 = address, + .r15 = data_in, + }; + + return __tdx_hypercall(&args, 0); +} diff --git a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c index 88f0429db0176..dcc0940a74e92 100644 --- a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c +++ b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c @@ -892,6 +892,90 @@ void verify_mmio_reads(void) printf("\t ... PASSED\n"); }

+void guest_mmio_writes(void) +{ + uint64_t ret; + + ret = tdg_vp_vmcall_ve_request_mmio_write(TDX_MMIO_TEST_ADDR, 1, 0x12); + if (ret) + tdx_test_fatal(ret); + + ret = tdg_vp_vmcall_ve_request_mmio_write(TDX_MMIO_TEST_ADDR, 2, 0x1234); + if (ret) + tdx_test_fatal(ret); + + ret = tdg_vp_vmcall_ve_request_mmio_write(TDX_MMIO_TEST_ADDR, 4, 0x12345678); + if (ret) + tdx_test_fatal(ret); + + ret = tdg_vp_vmcall_ve_request_mmio_write(TDX_MMIO_TEST_ADDR, 8, 0x1234567890ABCDEF); + if (ret) + tdx_test_fatal(ret); + + // Write across page boundary. + ret = tdg_vp_vmcall_ve_request_mmio_write(PAGE_SIZE - 1, 8, 0); + if (ret) + tdx_test_fatal(ret); + + tdx_test_success(); +} + +/* + * Varifies guest MMIO writes. + */ +void verify_mmio_writes(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + uint8_t byte_1; + uint16_t byte_2; + uint32_t byte_4; + uint64_t byte_8; + + vm = td_create(); + td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); + vcpu = td_vcpu_add(vm, 0, guest_mmio_writes); + td_finalize(vm); + + printf("Verifying TD MMIO writes:\n"); + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_MMIO(vcpu, TDX_MMIO_TEST_ADDR, 1, TDG_VP_VMCALL_VE_REQUEST_MMIO_WRITE); + byte_1 = *(uint8_t *)(vcpu->run->mmio.data); + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_MMIO(vcpu, TDX_MMIO_TEST_ADDR, 2, TDG_VP_VMCALL_VE_REQUEST_MMIO_WRITE); + byte_2 = *(uint16_t *)(vcpu->run->mmio.data); + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_MMIO(vcpu, TDX_MMIO_TEST_ADDR, 4, TDG_VP_VMCALL_VE_REQUEST_MMIO_WRITE); + byte_4 = *(uint32_t *)(vcpu->run->mmio.data); + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_MMIO(vcpu, TDX_MMIO_TEST_ADDR, 8, TDG_VP_VMCALL_VE_REQUEST_MMIO_WRITE); + byte_8 = *(uint64_t *)(vcpu->run->mmio.data); + + ASSERT_EQ(byte_1, 0x12); + ASSERT_EQ(byte_2, 0x1234); + ASSERT_EQ(byte_4, 0x12345678); + ASSERT_EQ(byte_8, 0x1234567890ABCDEF); + + vcpu_run(vcpu); + ASSERT_EQ(vcpu->run->exit_reason, KVM_EXIT_SYSTEM_EVENT); + ASSERT_EQ(vcpu->run->system_event.data[1], TDG_VP_VMCALL_INVALID_OPERAND); + + vcpu_run(vcpu); + TDX_TEST_ASSERT_SUCCESS(vcpu); + + kvm_vm_free(vm); + printf("\t ... PASSED\n"); +} + int main(int argc, char **argv) { setbuf(stdout, NULL); @@ -912,6 +996,7 @@ int main(int argc, char **argv) run_in_new_process(&verify_guest_msr_reads); run_in_new_process(&verify_guest_hlt); run_in_new_process(&verify_mmio_reads); + run_in_new_process(&verify_mmio_writes);

return 0; }

From: Ryan Afranji afranji@google.com

The test checks that host can only read fixed values when trying to access the guest's private memory.

Signed-off-by: Ryan Afranji afranji@google.com Signed-off-by: Sagi Shahar sagis@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/x86_64/tdx_vm_tests.c | 85 +++++++++++++++++++ 1 file changed, 85 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c index b9d96b5f6521f..4c338206dbaf2 100644 --- a/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c +++ b/tools/testing/selftests/kvm/x86_64/tdx_vm_tests.c @@ -1069,6 +1069,90 @@ void verify_td_cpuid_tdcall(void) printf("\t ... PASSED\n"); }

+/* + * Shared variables between guest and host for host reading private mem test + */ +static uint64_t tdx_test_host_read_private_mem_addr; +#define TDX_HOST_READ_PRIVATE_MEM_PORT_TEST 0x53 + +void guest_host_read_priv_mem(void) +{ + uint64_t ret; + uint64_t placeholder = 0; + + /* Set value */ + *((uint32_t *) tdx_test_host_read_private_mem_addr) = 0xABCD; + + /* Exit so host can read value */ + ret = tdg_vp_vmcall_instruction_io( + TDX_HOST_READ_PRIVATE_MEM_PORT_TEST, 4, + TDG_VP_VMCALL_INSTRUCTION_IO_WRITE, &placeholder); + if (ret) + tdx_test_fatal(ret); + + /* Update guest_var's value and have host reread it. */ + *((uint32_t *) tdx_test_host_read_private_mem_addr) = 0xFEDC; + + tdx_test_success(); +} + +void verify_host_reading_private_mem(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + + vm_vaddr_t test_page; + uint64_t *host_virt; + uint64_t first_host_read; + uint64_t second_host_read; + + vm = td_create(); + td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); + vcpu = td_vcpu_add(vm, 0, guest_host_read_priv_mem); + + test_page = vm_vaddr_alloc_page(vm); + TEST_ASSERT(test_page < BIT_ULL(32), + "Test address should fit in 32 bits so it can be sent to the guest"); + + host_virt = addr_gva2hva(vm, test_page); + TEST_ASSERT(host_virt != NULL, + "Guest address not found in guest memory regions\n"); + + tdx_test_host_read_private_mem_addr = test_page; + sync_global_to_guest(vm, tdx_test_host_read_private_mem_addr); + + td_finalize(vm); + + printf("Verifying host's behavior when reading TD private memory:\n"); + + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + TDX_TEST_ASSERT_IO(vcpu, TDX_HOST_READ_PRIVATE_MEM_PORT_TEST, + 4, TDG_VP_VMCALL_INSTRUCTION_IO_WRITE); + printf("\t ... Guest's variable contains 0xABCD\n"); + + /* Host reads guest's variable. */ + first_host_read = *host_virt; + printf("\t ... Host's read attempt value: %lu\n", first_host_read); + + /* Guest updates variable and host rereads it. */ + vcpu_run(vcpu); + TDX_TEST_CHECK_GUEST_FAILURE(vcpu); + printf("\t ... Guest's variable updated to 0xFEDC\n"); + + second_host_read = *host_virt; + printf("\t ... Host's second read attempt value: %lu\n", + second_host_read); + + TEST_ASSERT(first_host_read == second_host_read, + "Host did not read a fixed pattern\n"); + + printf("\t ... Fixed pattern was returned to the host\n"); + + kvm_vm_free(vm); + printf("\t ... PASSED\n"); +} + int main(int argc, char **argv) { setbuf(stdout, NULL); @@ -1091,6 +1175,7 @@ int main(int argc, char **argv) run_in_new_process(&verify_mmio_reads); run_in_new_process(&verify_mmio_writes); run_in_new_process(&verify_td_cpuid_tdcall); + run_in_new_process(&verify_host_reading_private_mem);

return 0; }

Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/include/kvm_util_base.h | 24 ++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 32 +++++++++++++++++++ .../selftests/kvm/lib/x86_64/processor.c | 15 +++++++-- 3 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index cdc204cfeb4c2..30453e2de8396 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -412,6 +412,8 @@ vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);

void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, unsigned int npages); +void virt_map_shared(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + unsigned int npages); void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); @@ -843,6 +845,28 @@ static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr virt_arch_pg_map(vm, vaddr, paddr); }

+/* + * VM Virtual Page Map as Shared + * + * Input Args: + * vm - Virtual Machine + * vaddr - VM Virtual Address + * paddr - VM Physical Address + * memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within @vm, creates a virtual translation for the page starting + * at @vaddr to the page starting at @paddr. + */ +void virt_arch_pg_map_shared(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); + +static inline void virt_pg_map_shared(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + virt_arch_pg_map_shared(vm, vaddr, paddr); +}

/* * Address Guest Virtual to Guest Physical diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 14246f0fd2e78..6673be2f49c31 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1384,6 +1384,38 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, } }

+/* + * Map a range of VM virtual address to the VM's physical address as shared + * + * Input Args: + * vm - Virtual Machine + * vaddr - Virtuall address to map + * paddr - VM Physical Address + * npages - The number of pages to map + * + * Output Args: None + * + * Return: None + * + * Within the VM given by @vm, creates a virtual translation for + * @npages starting at @vaddr to the page range starting at @paddr. + */ +void virt_map_shared(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + unsigned int npages) +{ + size_t page_size = vm->page_size; + size_t size = npages * page_size; + + TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow"); + TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); + + while (npages--) { + virt_pg_map_shared(vm, vaddr, paddr); + vaddr += page_size; + paddr += page_size; + } +} + /* * Address VM Physical to Host Virtual * diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 1ea1019d48c13..b4c18f7335dab 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -176,7 +176,8 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, return pte; }

-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) +static void ___virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + int level, bool protected) { const uint64_t pg_size = PG_LEVEL_SIZE(level); uint64_t *pml4e, *pdpe, *pde; @@ -223,17 +224,27 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);

- if (vm_is_gpa_protected(vm, paddr)) + if (protected) *pte |= vm->arch.c_bit; else *pte |= vm->arch.s_bit; }

+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) +{ + ___virt_pg_map(vm, vaddr, paddr, level, vm_is_gpa_protected(vm, paddr)); +} + void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) { __virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K); }

+void virt_arch_pg_map_shared(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + ___virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K, false); +} + void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, uint64_t nr_bytes, int level) {

With this, vm_userspace_mem_region_add() can use restricted memory to back guest memory.

Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/include/kvm_util_base.h | 7 ++- .../testing/selftests/kvm/include/test_util.h | 2 + tools/testing/selftests/kvm/lib/kvm_util.c | 48 ++++++++++++++++--- tools/testing/selftests/kvm/lib/test_util.c | 7 +++ 4 files changed, 55 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 30453e2de8396..950fd337898e1 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -33,7 +33,10 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */

struct userspace_mem_region { - struct kvm_userspace_memory_region region; + union { + struct kvm_userspace_memory_region region; + struct kvm_userspace_memory_region_ext region_ext; + }; struct sparsebit *unused_phy_pages; struct sparsebit *protected_phy_pages; int fd; @@ -214,7 +217,7 @@ static inline bool kvm_has_cap(long cap)

#define kvm_do_ioctl(fd, cmd, arg) \ ({ \ - static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd), ""); \ + static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) >= _IOC_SIZE(cmd), ""); \ ioctl(fd, cmd, arg); \ })

diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index befc754ce9b3b..01456a78b3a2e 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -94,6 +94,7 @@ enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB, VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB, + VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD, VM_MEM_SRC_SHMEM, VM_MEM_SRC_SHARED_HUGETLB, NUM_SRC_TYPES, @@ -104,6 +105,7 @@ enum vm_mem_backing_src_type { struct vm_mem_backing_src_alias { const char *name; uint32_t flag; + bool need_restricted_memfd; };

#define MIN_RUN_DELAY_NS 200000UL diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 6673be2f49c31..4e5928fa71c44 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -15,7 +15,6 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> -#include <linux/kernel.h>

#define KVM_UTIL_MIN_PFN 2

@@ -799,6 +798,27 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, errno, strerror(errno)); }

+/** + * Initialize memory in restricted_fd with size @memory_region_size and return + * the fd. + * + * Errors out if there's any error + */ +static int initialize_restricted_memfd(uint64_t memory_region_size) +{ + int ret; + int mfd = -1; + + mfd = syscall(__NR_memfd_restricted, 0); + TEST_ASSERT(mfd != -1, "Failed to create private memfd"); + ret = ftruncate(mfd, memory_region_size); + TEST_ASSERT(ret != -1, "Failed to resize memfd %d to %lx", mfd, memory_region_size); + ret = fallocate(mfd, 0, 0, memory_region_size); + TEST_ASSERT(ret != -1, "Failed to allocate %lx bytes in memfd %d", memory_region_size, mfd); + + return mfd; +} + /* * VM Userspace Memory Region Add * @@ -830,6 +850,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, struct userspace_mem_region *region; size_t backing_src_pagesz = get_backing_src_pagesz(src_type); size_t alignment; + int restricted_memfd = -1;

TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages, "Number of guest pages is not compatible with the host. " @@ -927,14 +948,24 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,

/* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || - src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) { - ret = madvise(region->host_mem, npages * vm->page_size, - src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE); + src_type == VM_MEM_SRC_ANONYMOUS_THP || + src_type == VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD) && thp_configured()) { + int advice = src_type == VM_MEM_SRC_ANONYMOUS_THP + ? MADV_HUGEPAGE + : MADV_NOHUGEPAGE; + ret = madvise(region->host_mem, npages * vm->page_size, advice); TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s", region->host_mem, npages * vm->page_size, vm_mem_backing_src_alias(src_type)->name); }

+ if (vm_mem_backing_src_alias(src_type)->need_restricted_memfd) { + restricted_memfd = initialize_restricted_memfd(npages * vm->page_size); + TEST_ASSERT(restricted_memfd != -1, + "Failed to create restricted memfd"); + flags |= KVM_MEM_PRIVATE; + } + region->unused_phy_pages = sparsebit_alloc(); region->protected_phy_pages = sparsebit_alloc(); sparsebit_set_num(region->unused_phy_pages, @@ -944,13 +975,16 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region->region.guest_phys_addr = guest_paddr; region->region.memory_size = npages * vm->page_size; region->region.userspace_addr = (uintptr_t) region->host_mem; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region); + region->region_ext.restricted_fd = restricted_memfd; + region->region_ext.restricted_offset = 0; + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region_ext); TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" - " guest_phys_addr: 0x%lx size: 0x%lx", + " guest_phys_addr: 0x%lx size: 0x%lx restricted_fd: %d", ret, errno, slot, flags, - guest_paddr, (uint64_t) region->region.memory_size); + guest_paddr, (uint64_t) region->region.memory_size, + restricted_memfd);

/* Add to quick lookup data structures */ vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 6d23878bbfe1a..2d53e55d13565 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -8,6 +8,7 @@ #include <assert.h> #include <ctype.h> #include <limits.h> +#include <stdbool.h> #include <stdlib.h> #include <time.h> #include <sys/stat.h> @@ -254,6 +255,11 @@ const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i) */ .flag = MAP_SHARED, }, + [VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD] = { + .name = "anonymous_and_restricted_memfd", + .flag = ANON_FLAGS, + .need_restricted_memfd = true, + }, }; _Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES, "Missing new backing src types?"); @@ -272,6 +278,7 @@ size_t get_backing_src_pagesz(uint32_t i) switch (i) { case VM_MEM_SRC_ANONYMOUS: case VM_MEM_SRC_SHMEM: + case VM_MEM_SRC_ANONYMOUS_AND_RESTRICTED_MEMFD: return getpagesize(); case VM_MEM_SRC_ANONYMOUS_THP: return get_trans_hugepagesz();

vm_vaddr_alloc always allocates memory in memslot 0. This allows users of this function to choose which memslot to allocate virtual memory in.

Signed-off-by: Ackerley Tng ackerleytng@google.com --- tools/testing/selftests/kvm/include/kvm_util_base.h | 3 +++ tools/testing/selftests/kvm/lib/kvm_util.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 950fd337898e1..abeffa5a47e88 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -406,6 +406,9 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +vm_vaddr_t +_vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, + vm_paddr_t paddr_min, uint32_t data_memslot, bool encrypt); vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t vm_vaddr_alloc_1to1(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 4e5928fa71c44..2f1e592d29dfd 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1286,7 +1286,7 @@ static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, * a unique set of pages, with the minimum real allocation being at least * a page. */ -static vm_vaddr_t +vm_vaddr_t _vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, vm_paddr_t paddr_min, uint32_t data_memslot, bool encrypt) {

Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/include/x86_64/tdx/tdx.h | 21 +++++++++++++++++++ .../selftests/kvm/lib/x86_64/tdx/tdx.c | 19 +++++++++++++++++ 2 files changed, 40 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h index c8e4b9ce795ea..2dfb9432c32f9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h +++ b/tools/testing/selftests/kvm/include/x86_64/tdx/tdx.h @@ -5,6 +5,7 @@ #include <stdint.h>

#define TDG_VP_INFO 1 +#define TDG_VP_VEINFO_GET 3 #define TDG_MEM_PAGE_ACCEPT 6

#define TDG_VP_VMCALL_GET_TD_VM_CALL_INFO 0x10000 @@ -41,4 +42,24 @@ uint64_t tdg_vp_info(uint64_t *rcx, uint64_t *rdx, uint64_t tdg_vp_vmcall_map_gpa(uint64_t address, uint64_t size, uint64_t *data_out); uint64_t tdg_mem_page_accept(uint64_t gpa, uint8_t level);

+/* + * Used by the #VE exception handler to gather the #VE exception + * info from the TDX module. This is a software only structure + * and not part of the TDX module/VMM ABI. + * + * Adapted from arch/x86/include/asm/tdx.h + */ +struct ve_info { + uint64_t exit_reason; + uint64_t exit_qual; + /* Guest Linear (virtual) Address */ + uint64_t gla; + /* Guest Physical Address */ + uint64_t gpa; + uint32_t instr_len; + uint32_t instr_info; +}; + +uint64_t tdg_vp_veinfo_get(struct ve_info *ve); + #endif // SELFTEST_TDX_TDX_H diff --git a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c index 2ebc47e268779..11a19832758bb 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/tdx/tdx.c @@ -210,3 +210,22 @@ uint64_t tdg_mem_page_accept(uint64_t gpa, uint8_t level) { return __tdx_module_call(TDG_MEM_PAGE_ACCEPT, gpa | level, 0, 0, 0, NULL); } + +uint64_t tdg_vp_veinfo_get(struct ve_info *ve) +{ + uint64_t ret; + struct tdx_module_output out; + + memset(&out, 0, sizeof(struct tdx_module_output)); + + ret = __tdx_module_call(TDG_VP_VEINFO_GET, 0, 0, 0, 0, &out); + + ve->exit_reason = out.rcx; + ve->exit_qual = out.rdx; + ve->gla = out.r8; + ve->gpa = out.r9; + ve->instr_len = out.r10 & 0xffffffff; + ve->instr_info = out.r10 >> 32; + + return ret; +}

This tests the use of restricted memory without explicit MapGPA calls.

Signed-off-by: Ackerley Tng ackerleytng@google.com --- .../selftests/kvm/x86_64/tdx_upm_test.c | 88 ++++++++++++++++--- 1 file changed, 78 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/tdx_upm_test.c b/tools/testing/selftests/kvm/x86_64/tdx_upm_test.c index 13914aebd7da7..56ba3d4fb15a5 100644 --- a/tools/testing/selftests/kvm/x86_64/tdx_upm_test.c +++ b/tools/testing/selftests/kvm/x86_64/tdx_upm_test.c @@ -149,11 +149,18 @@ enum { * Does vcpu_run, and also manages memory conversions if requested by the TD. */ void vcpu_run_and_manage_memory_conversions(struct kvm_vm *vm, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, bool handle_conversions) { for (;;) { vcpu_run(vcpu); - if ( + if (handle_conversions && + vcpu->run->exit_reason == KVM_EXIT_MEMORY_FAULT) { + handle_memory_conversion( + vm, vcpu->run->memory.gpa, + vcpu->run->memory.size, + vcpu->run->memory.flags == KVM_MEMORY_EXIT_FLAG_PRIVATE); + continue; + } else if ( vcpu->run->exit_reason == KVM_EXIT_IO && vcpu->run->io.port == TDX_UPM_TEST_ACCEPT_PRINT_PORT) { uint64_t gpa = tdx_test_read_64bit( @@ -233,8 +240,53 @@ static void guest_upm_explicit(void) tdx_test_success(); }

+static void guest_upm_implicit(void) +{ + struct tdx_upm_test_area *test_area_gva_private = + (struct tdx_upm_test_area *)TDX_UPM_TEST_AREA_GVA_PRIVATE; + struct tdx_upm_test_area *test_area_gva_shared = + (struct tdx_upm_test_area *)TDX_UPM_TEST_AREA_GVA_SHARED; + + /* Check: host reading private memory does not modify guest's view */ + fill_test_area(test_area_gva_private, PATTERN_GUEST_GENERAL); + + tdx_test_report_to_user_space(SYNC_CHECK_READ_PRIVATE_MEMORY_FROM_HOST); + + TDX_UPM_TEST_ASSERT( + check_test_area(test_area_gva_private, PATTERN_GUEST_GENERAL)); + + /* Use focus area as shared */ + fill_focus_area(test_area_gva_shared, PATTERN_GUEST_FOCUS); + + /* General areas should not be affected */ + TDX_UPM_TEST_ASSERT( + check_general_areas(test_area_gva_private, PATTERN_GUEST_GENERAL)); + + tdx_test_report_to_user_space(SYNC_CHECK_READ_SHARED_MEMORY_FROM_HOST); + + /* Check that guest has the same view of shared memory */ + TDX_UPM_TEST_ASSERT( + check_focus_area(test_area_gva_shared, PATTERN_HOST_FOCUS)); + + /* Use focus area as private */ + fill_focus_area(test_area_gva_private, PATTERN_GUEST_FOCUS); + + /* General areas should be unaffected by remapping */ + TDX_UPM_TEST_ASSERT( + check_general_areas(test_area_gva_private, PATTERN_GUEST_GENERAL)); + + tdx_test_report_to_user_space(SYNC_CHECK_READ_PRIVATE_MEMORY_FROM_HOST_AGAIN); + + /* Check that guest can use private memory after focus area is remapped as private */ + TDX_UPM_TEST_ASSERT( + fill_and_check(test_area_gva_private, PATTERN_GUEST_GENERAL)); + + tdx_test_success(); +} + static void run_selftest(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - struct tdx_upm_test_area *test_area_base_hva) + struct tdx_upm_test_area *test_area_base_hva, + bool implicit) { vcpu_run(vcpu); TDX_TEST_CHECK_GUEST_FAILURE(vcpu); @@ -253,7 +305,7 @@ static void run_selftest(struct kvm_vm *vm, struct kvm_vcpu *vcpu, TEST_ASSERT(check_test_area(test_area_base_hva, PATTERN_CONFIDENCE_CHECK), "Host should read PATTERN_CONFIDENCE_CHECK from guest's private memory.");

- vcpu_run_and_manage_memory_conversions(vm, vcpu); + vcpu_run_and_manage_memory_conversions(vm, vcpu, implicit); TDX_TEST_CHECK_GUEST_FAILURE(vcpu); TDX_TEST_ASSERT_IO(vcpu, TDX_TEST_REPORT_PORT, TDX_TEST_REPORT_SIZE, TDG_VP_VMCALL_INSTRUCTION_IO_WRITE); @@ -270,7 +322,7 @@ static void run_selftest(struct kvm_vm *vm, struct kvm_vcpu *vcpu, TEST_ASSERT(check_focus_area(test_area_base_hva, PATTERN_HOST_FOCUS), "Host should be able to use shared memory.");

- vcpu_run_and_manage_memory_conversions(vm, vcpu); + vcpu_run_and_manage_memory_conversions(vm, vcpu, implicit); TDX_TEST_CHECK_GUEST_FAILURE(vcpu); TDX_TEST_ASSERT_IO(vcpu, TDX_TEST_REPORT_PORT, TDX_TEST_REPORT_SIZE, TDG_VP_VMCALL_INSTRUCTION_IO_WRITE); @@ -319,18 +371,20 @@ static void guest_ve_handler(struct ex_regs *regs) TDX_UPM_TEST_ASSERT(!ret); }

-static void verify_upm_test(void) +static void verify_upm_test(bool implicit) { struct kvm_vm *vm; struct kvm_vcpu *vcpu;

+ void *guest_code; vm_vaddr_t test_area_gva_private; struct tdx_upm_test_area *test_area_base_hva; uint64_t test_area_npages;

vm = td_create(); td_initialize(vm, VM_MEM_SRC_ANONYMOUS, 0); - vcpu = td_vcpu_add(vm, 0, guest_upm_explicit); + guest_code = implicit ? guest_upm_implicit : guest_upm_explicit; + vcpu = td_vcpu_add(vm, 0, guest_code);

vm_install_exception_handler(vm, VE_VECTOR, guest_ve_handler);

@@ -370,13 +424,26 @@ static void verify_upm_test(void)

td_finalize(vm);

- printf("Verifying UPM functionality: explicit MapGPA\n"); + if (implicit) + printf("Verifying UPM functionality: implicit conversion\n"); + else + printf("Verifying UPM functionality: explicit MapGPA\n");

- run_selftest(vm, vcpu, test_area_base_hva); + run_selftest(vm, vcpu, test_area_base_hva, implicit);

kvm_vm_free(vm); }

+void verify_upm_test_explicit(void) +{ + verify_upm_test(false); +} + +void verify_upm_test_implicit(void) +{ + verify_upm_test(true); +} + int main(int argc, char **argv) { /* Disable stdout buffering */ @@ -388,5 +455,6 @@ int main(int argc, char **argv) return 0; }

- run_in_new_process(&verify_upm_test); + run_in_new_process(&verify_upm_test_explicit); + run_in_new_process(&verify_upm_test_implicit); }