* target/i386/kvm: Intel TDX support

* target/i386/emulate: more lflags cleanups
 * meson: remove need for explicit listing of dependencies in hw_common_arch and
   target_common_arch
 * rust: small fixes
 * hpet: Reorganize register decoding to be more similar to Rust code
 * target/i386: fixes for AMD models
 * target/i386: new EPYC-Turin CPU model
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCgAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmg4BxwUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroP67gf+PEP4EDQP0AJUfxXYVsczGf5snGjz
 ro8jYmKG+huBZcrS6uPK5zHYxtOI9bHr4ipTHJyHd61lyzN6Ys9amPbs/CRE2Q4x
 Ky4AojPhCuaL2wHcYNcu41L+hweVQ3myj97vP3hWvkatulXYeMqW3/4JZgr4WZ69
 A9LGLtLabobTz5yLc8x6oHLn/BZ2y7gjd2LzTz8bqxx7C/kamjoDrF2ZHbX9DLQW
 BKWQ3edSO6rorSNHWGZsy9BE20AEkW2LgJdlV9eXglFEuEs6cdPKwGEZepade4bQ
 Rdt2gHTlQdUDTFmAbz8pttPxFGMC9Zpmb3nnicKJpKQAmkT/x4k9ncjyAQ==
 =XmkU
 -----END PGP SIGNATURE-----

Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging

* target/i386/kvm: Intel TDX support
* target/i386/emulate: more lflags cleanups
* meson: remove need for explicit listing of dependencies in hw_common_arch and
  target_common_arch
* rust: small fixes
* hpet: Reorganize register decoding to be more similar to Rust code
* target/i386: fixes for AMD models
* target/i386: new EPYC-Turin CPU model

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCgAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmg4BxwUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroP67gf+PEP4EDQP0AJUfxXYVsczGf5snGjz
# ro8jYmKG+huBZcrS6uPK5zHYxtOI9bHr4ipTHJyHd61lyzN6Ys9amPbs/CRE2Q4x
# Ky4AojPhCuaL2wHcYNcu41L+hweVQ3myj97vP3hWvkatulXYeMqW3/4JZgr4WZ69
# A9LGLtLabobTz5yLc8x6oHLn/BZ2y7gjd2LzTz8bqxx7C/kamjoDrF2ZHbX9DLQW
# BKWQ3edSO6rorSNHWGZsy9BE20AEkW2LgJdlV9eXglFEuEs6cdPKwGEZepade4bQ
# Rdt2gHTlQdUDTFmAbz8pttPxFGMC9Zpmb3nnicKJpKQAmkT/x4k9ncjyAQ==
# =XmkU
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 29 May 2025 03:05:00 EDT
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (77 commits)
  target/i386/tcg/helper-tcg: fix file references in comments
  target/i386: Add support for EPYC-Turin model
  target/i386: Update EPYC-Genoa for Cache property, perfmon-v2, RAS and SVM feature bits
  target/i386: Add couple of feature bits in CPUID_Fn80000021_EAX
  target/i386: Update EPYC-Milan CPU model for Cache property, RAS, SVM feature bits
  target/i386: Update EPYC-Rome CPU model for Cache property, RAS, SVM feature bits
  target/i386: Update EPYC CPU model for Cache property, RAS, SVM feature bits
  rust: make declaration of dependent crates more consistent
  docs: Add TDX documentation
  i386/tdx: Validate phys_bits against host value
  i386/tdx: Make invtsc default on
  i386/tdx: Don't treat SYSCALL as unavailable
  i386/tdx: Fetch and validate CPUID of TD guest
  target/i386: Print CPUID subleaf info for unsupported feature
  i386: Remove unused parameter "uint32_t bit" in feature_word_description()
  i386/cgs: Introduce x86_confidential_guest_check_features()
  i386/tdx: Define supported KVM features for TDX
  i386/tdx: Add XFD to supported bit of TDX
  i386/tdx: Add supported CPUID bits relates to XFAM
  i386/tdx: Add supported CPUID bits related to TD Attributes
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This commit is contained in:
Stefan Hajnoczi 2025-05-30 11:41:07 -04:00
commit 98721058d6
66 changed files with 3231 additions and 346 deletions

View file

@ -10,6 +10,11 @@ config SGX
bool
depends on KVM
config TDX
bool
select X86_FW_OVMF
depends on KVM
config PC
bool
imply APPLESMC
@ -26,6 +31,7 @@ config PC
imply QXL
imply SEV
imply SGX
imply TDX
imply TEST_DEVICES
imply TPM_CRB
imply TPM_TIS_ISA

View file

@ -17,6 +17,7 @@
#include "system/hw_accel.h"
#include "system/kvm.h"
#include "kvm/kvm_i386.h"
#include "kvm/tdx.h"
static inline void kvm_apic_set_reg(struct kvm_lapic_state *kapic,
int reg_id, uint32_t val)
@ -141,6 +142,10 @@ static void kvm_apic_put(CPUState *cs, run_on_cpu_data data)
struct kvm_lapic_state kapic;
int ret;
if (is_tdx_vm()) {
return;
}
kvm_put_apicbase(s->cpu, s->apicbase);
kvm_put_apic_state(s, &kapic);

View file

@ -32,6 +32,7 @@ i386_ss.add(when: 'CONFIG_PC', if_true: files(
'port92.c'))
i386_ss.add(when: 'CONFIG_X86_FW_OVMF', if_true: files('pc_sysfw_ovmf.c'),
if_false: files('pc_sysfw_ovmf-stubs.c'))
i386_ss.add(when: 'CONFIG_TDX', if_true: files('tdvf.c', 'tdvf-hob.c'))
subdir('kvm')
subdir('xen')

View file

@ -44,6 +44,7 @@
#include "system/xen.h"
#include "system/reset.h"
#include "kvm/kvm_i386.h"
#include "kvm/tdx.h"
#include "hw/xen/xen.h"
#include "qobject/qlist.h"
#include "qemu/error-report.h"
@ -976,21 +977,23 @@ void pc_memory_init(PCMachineState *pcms,
/* Initialize PC system firmware */
pc_system_firmware_init(pcms, rom_memory);
option_rom_mr = g_malloc(sizeof(*option_rom_mr));
if (machine_require_guest_memfd(machine)) {
memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom",
PC_ROM_SIZE, &error_fatal);
} else {
memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE,
&error_fatal);
if (pcmc->pci_enabled) {
memory_region_set_readonly(option_rom_mr, true);
if (!is_tdx_vm()) {
option_rom_mr = g_malloc(sizeof(*option_rom_mr));
if (machine_require_guest_memfd(machine)) {
memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom",
PC_ROM_SIZE, &error_fatal);
} else {
memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE,
&error_fatal);
if (pcmc->pci_enabled) {
memory_region_set_readonly(option_rom_mr, true);
}
}
memory_region_add_subregion_overlap(rom_memory,
PC_ROM_MIN_VGA,
option_rom_mr,
1);
}
memory_region_add_subregion_overlap(rom_memory,
PC_ROM_MIN_VGA,
option_rom_mr,
1);
fw_cfg = fw_cfg_arch_create(machine,
x86ms->boot_cpus, x86ms->apic_id_limit);

View file

@ -37,6 +37,7 @@
#include "hw/block/flash.h"
#include "system/kvm.h"
#include "target/i386/sev.h"
#include "kvm/tdx.h"
#define FLASH_SECTOR_SIZE 4096
@ -280,5 +281,11 @@ void x86_firmware_configure(hwaddr gpa, void *ptr, int size)
}
sev_encrypt_flash(gpa, ptr, size, &error_fatal);
} else if (is_tdx_vm()) {
ret = tdx_parse_tdvf(ptr, size);
if (ret) {
error_report("failed to parse TDVF for TDX VM");
exit(1);
}
}
}

130
hw/i386/tdvf-hob.c Normal file
View file

@ -0,0 +1,130 @@
/*
* Copyright (c) 2025 Intel Corporation
* Author: Isaku Yamahata <isaku.yamahata at gmail.com>
* <isaku.yamahata at intel.com>
* Xiaoyao Li <xiaoyao.li@intel.com>
*
* SPDX-License-Identifier: GPL-2.0-or-later
*/
#include "qemu/osdep.h"
#include "qemu/error-report.h"
#include "standard-headers/uefi/uefi.h"
#include "hw/pci/pcie_host.h"
#include "tdvf-hob.h"
typedef struct TdvfHob {
hwaddr hob_addr;
void *ptr;
int size;
/* working area */
void *current;
void *end;
} TdvfHob;
static uint64_t tdvf_current_guest_addr(const TdvfHob *hob)
{
return hob->hob_addr + (hob->current - hob->ptr);
}
static void tdvf_align(TdvfHob *hob, size_t align)
{
hob->current = QEMU_ALIGN_PTR_UP(hob->current, align);
}
static void *tdvf_get_area(TdvfHob *hob, uint64_t size)
{
void *ret;
if (hob->current + size > hob->end) {
error_report("TD_HOB overrun, size = 0x%" PRIx64, size);
exit(1);
}
ret = hob->current;
hob->current += size;
tdvf_align(hob, 8);
return ret;
}
static void tdvf_hob_add_memory_resources(TdxGuest *tdx, TdvfHob *hob)
{
EFI_HOB_RESOURCE_DESCRIPTOR *region;
EFI_RESOURCE_ATTRIBUTE_TYPE attr;
EFI_RESOURCE_TYPE resource_type;
TdxRamEntry *e;
int i;
for (i = 0; i < tdx->nr_ram_entries; i++) {
e = &tdx->ram_entries[i];
if (e->type == TDX_RAM_UNACCEPTED) {
resource_type = EFI_RESOURCE_MEMORY_UNACCEPTED;
attr = EFI_RESOURCE_ATTRIBUTE_TDVF_UNACCEPTED;
} else if (e->type == TDX_RAM_ADDED) {
resource_type = EFI_RESOURCE_SYSTEM_MEMORY;
attr = EFI_RESOURCE_ATTRIBUTE_TDVF_PRIVATE;
} else {
error_report("unknown TDX_RAM_ENTRY type %d", e->type);
exit(1);
}
region = tdvf_get_area(hob, sizeof(*region));
*region = (EFI_HOB_RESOURCE_DESCRIPTOR) {
.Header = {
.HobType = EFI_HOB_TYPE_RESOURCE_DESCRIPTOR,
.HobLength = cpu_to_le16(sizeof(*region)),
.Reserved = cpu_to_le32(0),
},
.Owner = EFI_HOB_OWNER_ZERO,
.ResourceType = cpu_to_le32(resource_type),
.ResourceAttribute = cpu_to_le32(attr),
.PhysicalStart = cpu_to_le64(e->address),
.ResourceLength = cpu_to_le64(e->length),
};
}
}
void tdvf_hob_create(TdxGuest *tdx, TdxFirmwareEntry *td_hob)
{
TdvfHob hob = {
.hob_addr = td_hob->address,
.size = td_hob->size,
.ptr = td_hob->mem_ptr,
.current = td_hob->mem_ptr,
.end = td_hob->mem_ptr + td_hob->size,
};
EFI_HOB_GENERIC_HEADER *last_hob;
EFI_HOB_HANDOFF_INFO_TABLE *hit;
/* Note, Efi{Free}Memory{Bottom,Top} are ignored, leave 'em zeroed. */
hit = tdvf_get_area(&hob, sizeof(*hit));
*hit = (EFI_HOB_HANDOFF_INFO_TABLE) {
.Header = {
.HobType = EFI_HOB_TYPE_HANDOFF,
.HobLength = cpu_to_le16(sizeof(*hit)),
.Reserved = cpu_to_le32(0),
},
.Version = cpu_to_le32(EFI_HOB_HANDOFF_TABLE_VERSION),
.BootMode = cpu_to_le32(0),
.EfiMemoryTop = cpu_to_le64(0),
.EfiMemoryBottom = cpu_to_le64(0),
.EfiFreeMemoryTop = cpu_to_le64(0),
.EfiFreeMemoryBottom = cpu_to_le64(0),
.EfiEndOfHobList = cpu_to_le64(0), /* initialized later */
};
tdvf_hob_add_memory_resources(tdx, &hob);
last_hob = tdvf_get_area(&hob, sizeof(*last_hob));
*last_hob = (EFI_HOB_GENERIC_HEADER) {
.HobType = EFI_HOB_TYPE_END_OF_HOB_LIST,
.HobLength = cpu_to_le16(sizeof(*last_hob)),
.Reserved = cpu_to_le32(0),
};
hit->EfiEndOfHobList = tdvf_current_guest_addr(&hob);
}

26
hw/i386/tdvf-hob.h Normal file
View file

@ -0,0 +1,26 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef HW_I386_TD_HOB_H
#define HW_I386_TD_HOB_H
#include "hw/i386/tdvf.h"
#include "target/i386/kvm/tdx.h"
void tdvf_hob_create(TdxGuest *tdx, TdxFirmwareEntry *td_hob);
#define EFI_RESOURCE_ATTRIBUTE_TDVF_PRIVATE \
(EFI_RESOURCE_ATTRIBUTE_PRESENT | \
EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \
EFI_RESOURCE_ATTRIBUTE_TESTED)
#define EFI_RESOURCE_ATTRIBUTE_TDVF_UNACCEPTED \
(EFI_RESOURCE_ATTRIBUTE_PRESENT | \
EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \
EFI_RESOURCE_ATTRIBUTE_TESTED)
#define EFI_RESOURCE_ATTRIBUTE_TDVF_MMIO \
(EFI_RESOURCE_ATTRIBUTE_PRESENT | \
EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \
EFI_RESOURCE_ATTRIBUTE_UNCACHEABLE)
#endif

189
hw/i386/tdvf.c Normal file
View file

@ -0,0 +1,189 @@
/*
* Copyright (c) 2025 Intel Corporation
* Author: Isaku Yamahata <isaku.yamahata at gmail.com>
* <isaku.yamahata at intel.com>
* Xiaoyao Li <xiaoyao.li@intel.com>
*
* SPDX-License-Identifier: GPL-2.0-or-later
*/
#include "qemu/osdep.h"
#include "qemu/error-report.h"
#include "hw/i386/pc.h"
#include "hw/i386/tdvf.h"
#include "system/kvm.h"
#define TDX_METADATA_OFFSET_GUID "e47a6535-984a-4798-865e-4685a7bf8ec2"
#define TDX_METADATA_VERSION 1
#define TDVF_SIGNATURE 0x46564454 /* TDVF as little endian */
#define TDVF_ALIGNMENT 4096
/*
* the raw structs read from TDVF keeps the name convention in
* TDVF Design Guide spec.
*/
typedef struct {
uint32_t DataOffset;
uint32_t RawDataSize;
uint64_t MemoryAddress;
uint64_t MemoryDataSize;
uint32_t Type;
uint32_t Attributes;
} TdvfSectionEntry;
typedef struct {
uint32_t Signature;
uint32_t Length;
uint32_t Version;
uint32_t NumberOfSectionEntries;
TdvfSectionEntry SectionEntries[];
} TdvfMetadata;
struct tdx_metadata_offset {
uint32_t offset;
};
static TdvfMetadata *tdvf_get_metadata(void *flash_ptr, int size)
{
TdvfMetadata *metadata;
uint32_t offset = 0;
uint8_t *data;
if ((uint32_t) size != size) {
return NULL;
}
if (pc_system_ovmf_table_find(TDX_METADATA_OFFSET_GUID, &data, NULL)) {
offset = size - le32_to_cpu(((struct tdx_metadata_offset *)data)->offset);
if (offset + sizeof(*metadata) > size) {
return NULL;
}
} else {
error_report("Cannot find TDX_METADATA_OFFSET_GUID");
return NULL;
}
metadata = flash_ptr + offset;
/* Finally, verify the signature to determine if this is a TDVF image. */
metadata->Signature = le32_to_cpu(metadata->Signature);
if (metadata->Signature != TDVF_SIGNATURE) {
error_report("Invalid TDVF signature in metadata!");
return NULL;
}
/* Sanity check that the TDVF doesn't overlap its own metadata. */
metadata->Length = le32_to_cpu(metadata->Length);
if (offset + metadata->Length > size) {
return NULL;
}
/* Only version 1 is supported/defined. */
metadata->Version = le32_to_cpu(metadata->Version);
if (metadata->Version != TDX_METADATA_VERSION) {
return NULL;
}
return metadata;
}
static int tdvf_parse_and_check_section_entry(const TdvfSectionEntry *src,
TdxFirmwareEntry *entry)
{
entry->data_offset = le32_to_cpu(src->DataOffset);
entry->data_len = le32_to_cpu(src->RawDataSize);
entry->address = le64_to_cpu(src->MemoryAddress);
entry->size = le64_to_cpu(src->MemoryDataSize);
entry->type = le32_to_cpu(src->Type);
entry->attributes = le32_to_cpu(src->Attributes);
/* sanity check */
if (entry->size < entry->data_len) {
error_report("Broken metadata RawDataSize 0x%x MemoryDataSize 0x%lx",
entry->data_len, entry->size);
return -1;
}
if (!QEMU_IS_ALIGNED(entry->address, TDVF_ALIGNMENT)) {
error_report("MemoryAddress 0x%lx not page aligned", entry->address);
return -1;
}
if (!QEMU_IS_ALIGNED(entry->size, TDVF_ALIGNMENT)) {
error_report("MemoryDataSize 0x%lx not page aligned", entry->size);
return -1;
}
switch (entry->type) {
case TDVF_SECTION_TYPE_BFV:
case TDVF_SECTION_TYPE_CFV:
/* The sections that must be copied from firmware image to TD memory */
if (entry->data_len == 0) {
error_report("%d section with RawDataSize == 0", entry->type);
return -1;
}
break;
case TDVF_SECTION_TYPE_TD_HOB:
case TDVF_SECTION_TYPE_TEMP_MEM:
/* The sections that no need to be copied from firmware image */
if (entry->data_len != 0) {
error_report("%d section with RawDataSize 0x%x != 0",
entry->type, entry->data_len);
return -1;
}
break;
default:
error_report("TDVF contains unsupported section type %d", entry->type);
return -1;
}
return 0;
}
int tdvf_parse_metadata(TdxFirmware *fw, void *flash_ptr, int size)
{
g_autofree TdvfSectionEntry *sections = NULL;
TdvfMetadata *metadata;
ssize_t entries_size;
int i;
metadata = tdvf_get_metadata(flash_ptr, size);
if (!metadata) {
return -EINVAL;
}
/* load and parse metadata entries */
fw->nr_entries = le32_to_cpu(metadata->NumberOfSectionEntries);
if (fw->nr_entries < 2) {
error_report("Invalid number of fw entries (%u) in TDVF Metadata",
fw->nr_entries);
return -EINVAL;
}
entries_size = fw->nr_entries * sizeof(TdvfSectionEntry);
if (metadata->Length != sizeof(*metadata) + entries_size) {
error_report("TDVF metadata len (0x%x) mismatch, expected (0x%x)",
metadata->Length,
(uint32_t)(sizeof(*metadata) + entries_size));
return -EINVAL;
}
fw->entries = g_new(TdxFirmwareEntry, fw->nr_entries);
sections = g_new(TdvfSectionEntry, fw->nr_entries);
memcpy(sections, (void *)metadata + sizeof(*metadata), entries_size);
for (i = 0; i < fw->nr_entries; i++) {
if (tdvf_parse_and_check_section_entry(&sections[i], &fw->entries[i])) {
goto err;
}
}
fw->mem_ptr = flash_ptr;
return 0;
err:
fw->entries = 0;
g_free(fw->entries);
return -EINVAL;
}

View file

@ -44,6 +44,7 @@
#include "standard-headers/asm-x86/bootparam.h"
#include CONFIG_DEVICES
#include "kvm/kvm_i386.h"
#include "kvm/tdx.h"
#ifdef CONFIG_XEN_EMU
#include "hw/xen/xen.h"
@ -1035,11 +1036,14 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware,
if (machine_require_guest_memfd(MACHINE(x86ms))) {
memory_region_init_ram_guest_memfd(&x86ms->bios, NULL, "pc.bios",
bios_size, &error_fatal);
if (is_tdx_vm()) {
tdx_set_tdvf_region(&x86ms->bios);
}
} else {
memory_region_init_ram(&x86ms->bios, NULL, "pc.bios",
bios_size, &error_fatal);
}
if (sev_enabled()) {
if (sev_enabled() || is_tdx_vm()) {
/*
* The concept of a "reset" simply doesn't exist for
* confidential computing guests, we have to destroy and