On Wed, 2026-07-22 at 23:13 +0000, Lisa Wang wrote: > From: Sagi Shahar <[email protected]> > > Add tdx_init_vm() to handle the mandatory VM-level initialization > sequence required for Intel TDX. > > For TDX, the guest's CPUID configuration must be "sealed" during > KVM_TDX_INIT_VM before any vCPUs are created. This is necessary because > the TDX hardware directly virtualizes CPUID and includes the > configuration in the guest's initial security measurement.
"TDX hardware" should be TDX module. But I'm not sure what it is trying to say about directly virtualizes. Also, it is not accurate to say that the CPUID configuration is included in the measurement? Is that right Peter? It's not in the report, but is it in the measurement? Or maybe it doesn't really need to be in the log anyway. > > The helper calculates the required CPUID values by filtering the host- > supported bits (kvm_get_supported_cpuid) against the "directly > configurable" bits reported by KVM_TDX_CAPABILITIES, ensuring > compliance with the strict requirements of the TDH.MNG.INIT SEAMCALL. > > Co-developed-by: Isaku Yamahata <[email protected]> > Signed-off-by: Isaku Yamahata <[email protected]> > Co-developed-by: Rick Edgecombe <[email protected]> > Signed-off-by: Rick Edgecombe <[email protected]> > Signed-off-by: Sagi Shahar <[email protected]> > Reviewed-by: Ira Weiny <[email protected]> > Signed-off-by: Lisa Wang <[email protected]> > --- > tools/testing/selftests/kvm/Makefile.kvm | 1 + > .../testing/selftests/kvm/include/x86/processor.h | 2 + > .../selftests/kvm/include/x86/tdx/tdx_util.h | 35 ++++++ > tools/testing/selftests/kvm/lib/x86/processor.c | 21 +++- > tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c | 120 > +++++++++++++++++++++ > 5 files changed, 175 insertions(+), 4 deletions(-) > > diff --git a/tools/testing/selftests/kvm/Makefile.kvm > b/tools/testing/selftests/kvm/Makefile.kvm > index e5769268936a..3f98d1c6488c 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 0aa6eecfcbde..76180dfaffea 100644 > --- a/tools/testing/selftests/kvm/include/x86/processor.h > +++ b/tools/testing/selftests/kvm/include/x86/processor.h > @@ -956,6 +956,8 @@ 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..eb8602dce0bc 100644 > --- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h > +++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h > @@ -11,4 +11,39 @@ 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) \ > +({ \ > + u64 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); \ > + r ?: tdx_cmd.c.hw_error; \ > +}) > + > +#define tdx_vm_ioctl(vm, cmd, flags, arg) \ > +({ \ > + u64 ret = __tdx_vm_ioctl(vm, cmd, flags, arg); \ > + \ > + if (ret) { \ > + TEST_ASSERT(!ret, \ > + "%s failed, rc: 0x%llx errno: %i (%s)", \ > + #cmd, (unsigned long long)ret, \ > + errno, strerror(errno)); \ > + } \ > +}) > + > +void tdx_init_vm(struct kvm_vm *vm, u64 attributes); > + > #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 b68ad1dc7e02..7d23344854cc 100644 > --- a/tools/testing/selftests/kvm/lib/x86/processor.c > +++ b/tools/testing/selftests/kvm/lib/x86/processor.c > @@ -802,6 +802,9 @@ 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, 0); In this series tdx_init_vm() is only called with 0 for attributes. Do we need the arg or could we just set it to 0 internally like xfam? > + > 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; > @@ -1328,8 +1331,8 @@ 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; > > @@ -1339,11 +1342,21 @@ 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..e1ffb67a106c > --- /dev/null > +++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c > @@ -0,0 +1,120 @@ > +// SPDX-License-Identifier: GPL-2.0-only > + > +#include "processor.h" > +#include "tdx/tdx_util.h" > + > +static 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\n", > + nr_cpuid_configs); > + > + tdx_cap->cpuid.nent = nr_cpuid_configs; > + rc = __tdx_vm_ioctl(vm, KVM_TDX_CAPABILITIES, 0, tdx_cap); > + } 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; > +} > + > +/* > + * Filter CPUID based on TDX supported capabilities > + * > + * Input Args: > + * vm - Virtual Machine > + * cpuid_data - CPUID fields to filter > + * > + * Output Args: None > + * > + * Return: None > + * > + * For each CPUID leaf, filter out unsupported bits based on the capabilities > + * reported by the TDX module > + */ > +static void tdx_filter_cpuid(struct kvm_vm *vm, > + struct kvm_cpuid2 *cpuid_data) > +{ > + 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, u64 attributes) > +{ > + struct kvm_tdx_init_vm *init_vm; > + const struct kvm_cpuid2 *tmp; > + struct kvm_cpuid2 *cpuid; > + > + tmp = kvm_get_supported_cpuid(); > + > + cpuid = allocate_kvm_cpuid2(tmp->nent); > + memcpy(cpuid, tmp, kvm_cpuid2_size(tmp->nent)); > + tdx_filter_cpuid(vm, cpuid); > + > + init_vm = calloc(1, sizeof(*init_vm) + > + sizeof(init_vm->cpuid.entries[0]) * cpuid->nent); > + TEST_ASSERT(init_vm, "init_vm allocation failed"); > + > + memcpy(&init_vm->cpuid, cpuid, kvm_cpuid2_size(cpuid->nent)); > + free(cpuid); > + > + init_vm->attributes = attributes; > + > + tdx_vm_ioctl(vm, KVM_TDX_INIT_VM, 0, init_vm); > + > + free(init_vm); > +} >
