From: Sagi Shahar Add tdx_init_vm() to handle the mandatory VM-level initialization sequence required for Intel TDX. For TDX, the VM's CPUID configuration must be "sealed" during KVM_TDX_INIT_VM before any vCPUs are created. This is necessary because the TDX module does not allow the host to create and initialize any vCPUs before the VM's CPUID configuration is accepted and sealed into the TDCS. Additionally, to satisfy the strict requirements of the TDH.MNG.INIT SEAMCALL, the helper masks the KVM-supported CPUID (kvm_get_supported_cpuid()) against the "directly configurable" bits reported by KVM_TDX_CAPABILITIES. Co-developed-by: Isaku Yamahata Signed-off-by: Isaku Yamahata Co-developed-by: Rick Edgecombe Signed-off-by: Rick Edgecombe Signed-off-by: Sagi Shahar Signed-off-by: Lisa Wang Reviewed-by: Ira Weiny --- tools/testing/selftests/kvm/Makefile.kvm | 1 + .../testing/selftests/kvm/include/x86/processor.h | 2 + .../selftests/kvm/include/x86/tdx/tdx_util.h | 37 +++++++ tools/testing/selftests/kvm/lib/x86/processor.c | 21 +++- tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c | 114 +++++++++++++++++++++ 5 files changed, 171 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 17a4256e9081..e6e81f979bc8 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -27,6 +27,7 @@ LIBKVM_x86 += lib/x86/pmu.c LIBKVM_x86 += lib/x86/processor.c LIBKVM_x86 += lib/x86/sev.c LIBKVM_x86 += lib/x86/svm.c +LIBKVM_x86 += lib/x86/tdx/tdx_util.c LIBKVM_x86 += lib/x86/ucall.c LIBKVM_x86 += lib/x86/vmx.c diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 3e88a413fb1e..e62ca763135e 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -1033,6 +1033,8 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) vcpu_ioctl(vcpu, KVM_SET_XCRS, xcrs); } +const struct kvm_cpuid_entry2 *__get_cpuid_entry(const struct kvm_cpuid2 *cpuid, + u32 function, u32 index); const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, u32 function, u32 index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); diff --git a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h index f647e6ca6b34..f76489ffb48d 100644 --- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h +++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h @@ -2,6 +2,7 @@ #ifndef SELFTESTS_TDX_TDX_UTIL_H #define SELFTESTS_TDX_TDX_UTIL_H +#include #include #include "kvm_util.h" @@ -11,4 +12,40 @@ static inline bool is_tdx_vm(struct kvm_vm *vm) return vm->type == KVM_X86_TDX_VM; } +/* + * TDX ioctls + * Use underscores to avoid collisions with struct member names. + */ +#define __tdx_vm_ioctl(vm, cmd, _flags, arg, hw_err) \ +({ \ + u64 *__hw_err = (hw_err); \ + int r; \ + \ + union { \ + struct kvm_tdx_cmd c; \ + unsigned long raw; \ + } tdx_cmd = { .c = { \ + .id = (cmd), \ + .flags = (u32)(_flags), \ + .data = (u64)(arg), \ + } }; \ + \ + r = __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_OP, &tdx_cmd.raw); \ + if (__hw_err) \ + *__hw_err = tdx_cmd.c.hw_error; \ + r; \ +}) + +#define tdx_vm_ioctl(vm, cmd, flags, arg) \ +({ \ + u64 hw_error; \ + int ret = __tdx_vm_ioctl(vm, cmd, flags, arg, &hw_error); \ + \ + TEST_ASSERT(!ret, \ + "%s failed, rc: %d errno: %i (%s) hw_error: 0x%" PRIx64, \ + #cmd, ret, errno, strerror(errno), hw_error); \ +}) + +void tdx_init_vm(struct kvm_vm *vm); + #endif /* SELFTESTS_TDX_TDX_UTIL_H */ diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index d705e9269a41..7bbc0df49a18 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -836,6 +836,9 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) vm_sev_ioctl(vm, KVM_SEV_INIT2, &init); } + if (is_tdx_vm(vm)) + tdx_init_vm(vm); + r = __vm_ioctl(vm, KVM_GET_TSC_KHZ, NULL); TEST_ASSERT(r > 0, "KVM_GET_TSC_KHZ did not provide a valid TSC frequency."); guest_tsc_khz = r; @@ -1354,8 +1357,8 @@ void kvm_init_vm_address_properties(struct kvm_vm *vm) } } -const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, - u32 function, u32 index) +const struct kvm_cpuid_entry2 *__get_cpuid_entry(const struct kvm_cpuid2 *cpuid, + u32 function, u32 index) { int i; @@ -1365,11 +1368,21 @@ const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, return &cpuid->entries[i]; } - TEST_FAIL("CPUID function 0x%x index 0x%x not found ", function, index); - return NULL; } +const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, + u32 function, u32 index) +{ + const struct kvm_cpuid_entry2 *entry; + + entry = __get_cpuid_entry(cpuid, function, index); + if (!entry) + TEST_FAIL("CPUID function 0x%x index 0x%x not found ", function, index); + + return entry; +} + #define X86_HYPERCALL(inputs...) \ ({ \ u64 r; \ diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c new file mode 100644 index 000000000000..564144c40f0a --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "processor.h" +#include "tdx/tdx_util.h" + +static const struct kvm_tdx_capabilities *tdx_read_capabilities(struct kvm_vm *vm) +{ + static struct kvm_tdx_capabilities *tdx_cap; + int nr_cpuid_configs = 4; + int rc = -1; + int i; + + if (tdx_cap) + return tdx_cap; + + do { + nr_cpuid_configs *= 2; + + tdx_cap = realloc(tdx_cap, sizeof(*tdx_cap) + + (sizeof(struct kvm_cpuid_entry2) * nr_cpuid_configs)); + TEST_ASSERT(tdx_cap, + "Could not allocate memory for tdx capability nr_cpuid_configs %d", + nr_cpuid_configs); + + tdx_cap->cpuid.nent = nr_cpuid_configs; + rc = __tdx_vm_ioctl(vm, KVM_TDX_CAPABILITIES, 0, tdx_cap, NULL); + } while (rc < 0 && errno == E2BIG); + + TEST_ASSERT(rc == 0, "KVM_TDX_CAPABILITIES failed: %d %d", + rc, errno); + + pr_debug("tdx_cap: supported_attrs: 0x%016llx\n" + "tdx_cap: supported_xfam 0x%016llx\n", + tdx_cap->supported_attrs, tdx_cap->supported_xfam); + + for (i = 0; i < tdx_cap->cpuid.nent; i++) { + const struct kvm_cpuid_entry2 *config = &tdx_cap->cpuid.entries[i]; + + pr_debug("cpuid config[%d]: leaf 0x%x sub_leaf 0x%x eax 0x%08x ebx 0x%08x ecx 0x%08x edx 0x%08x\n", + i, config->function, config->index, + config->eax, config->ebx, config->ecx, config->edx); + } + + return tdx_cap; +} + +/* + * For each CPUID leaf in @cpuid_data, filter out unsupported bits based on the + * capabilities reported by KVM. + */ +static void tdx_filter_cpuid(struct kvm_vm *vm, + struct kvm_cpuid2 *cpuid_data) +{ + const struct kvm_tdx_capabilities *tdx_cap; + const struct kvm_cpuid_entry2 *config; + struct kvm_cpuid_entry2 *e; + int i; + + tdx_cap = tdx_read_capabilities(vm); + + i = 0; + while (i < cpuid_data->nent) { + e = cpuid_data->entries + i; + config = __get_cpuid_entry(&tdx_cap->cpuid, e->function, e->index); + + if (!config) { + int left = cpuid_data->nent - i - 1; + + if (left > 0) + memmove(cpuid_data->entries + i, + cpuid_data->entries + i + 1, + sizeof(*cpuid_data->entries) * left); + cpuid_data->nent--; + continue; + } + + e->eax &= config->eax; + e->ebx &= config->ebx; + e->ecx &= config->ecx; + e->edx &= config->edx; + + i++; + } +} + +void tdx_init_vm(struct kvm_vm *vm) +{ + struct kvm_tdx_init_vm *init_vm; + const struct kvm_cpuid2 *tmp; + + tmp = kvm_get_supported_cpuid(); + + init_vm = calloc(1, sizeof(*init_vm) + + sizeof(init_vm->cpuid.entries[0]) * tmp->nent); + TEST_ASSERT(init_vm, "init_vm allocation failed"); + + memcpy(&init_vm->cpuid, tmp, kvm_cpuid2_size(tmp->nent)); + init_vm->cpuid.padding = 0; + tdx_filter_cpuid(vm, &init_vm->cpuid); + + /* + * Set attributes and xfam to 0 to use KVM's baseline config, as KVM + * automatically ORs in the mandatory fixed-1 bits during + * KVM_TDX_INIT_VM. Note, TDX_TD_ATTR_SEPT_VE_DISABLE is not required + * because all initial private memory is pre-mapped before running the + * TD. + */ + init_vm->attributes = 0; + init_vm->xfam = 0; + + tdx_vm_ioctl(vm, KVM_TDX_INIT_VM, 0, init_vm); + + free(init_vm); +} -- 2.56.0.455.g6c5a503b38-goog