* [PATCH v13 08/22] KVM: selftests: Add TDX boot code
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Erdem Aktas <erdemaktas@google.com>
Add code to boot a TDX test VM. Since TDX registers are inaccessible to
KVM, the boot code loads the relevant values from memory into the
registers before jumping to the guest code.
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Erdem Aktas <erdemaktas@google.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../selftests/kvm/include/x86/tdx/td_boot.h | 5 ++
.../selftests/kvm/include/x86/tdx/td_boot_asm.h | 16 ++++++
tools/testing/selftests/kvm/lib/x86/tdx/td_boot.S | 60 ++++++++++++++++++++++
4 files changed, 82 insertions(+)
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 02fad7b35eac..929965ca4b75 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -31,6 +31,7 @@ LIBKVM_x86 += lib/x86/sev.c
LIBKVM_x86 += lib/x86/svm.c
LIBKVM_x86 += lib/x86/ucall.c
LIBKVM_x86 += lib/x86/vmx.c
+LIBKVM_x86 += lib/x86/tdx/td_boot.S
LIBKVM_arm64 += lib/arm64/gic.c
LIBKVM_arm64 += lib/arm64/gic_v3.c
diff --git a/tools/testing/selftests/kvm/include/x86/tdx/td_boot.h b/tools/testing/selftests/kvm/include/x86/tdx/td_boot.h
index af4474dee387..e5d54a20ed72 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/td_boot.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/td_boot.h
@@ -66,4 +66,9 @@ struct td_boot_parameters {
struct td_per_vcpu_parameters per_vcpu[];
};
+void td_boot(void);
+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/tdx/td_boot_asm.h b/tools/testing/selftests/kvm/include/x86/tdx/td_boot_asm.h
new file mode 100644
index 000000000000..10b4b527595c
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86/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 will be 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/lib/x86/tdx/td_boot.S b/tools/testing/selftests/kvm/lib/x86/tdx/td_boot.S
new file mode 100644
index 000000000000..7aa33caa9a78
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/td_boot.S
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include "tdx/td_boot_asm.h"
+#include "tdx/td_boot_offsets.h"
+#include "processor_asm.h"
+
+.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 use edi 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
+
+ /* Switching to 64bit mode after ljmp and then jump to guest code */
+ ljmp $(KERNEL_CS),$1f
+1:
+ jmp *TD_PER_VCPU_PARAMETERS_GUEST_CODE(%eax)
+
+/* 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
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 07/22] KVM: selftests: Introduce structures for TDX guest boot parameters
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Introduce `td_boot_parameters` and `td_per_vcpu_parameters`, and export
their offsets to assembly via the kbuild infrastructure.
TDX guest registers are private and must be initialized by guest-side
assembly. These structures allow the assembly code to retrieve boot
parameters and index into per-vCPU data based on the vCPU ID, while
keeping host and guest definitions synchronized.
Use kbuild.h to expose the offsets into the structs from c code to
assembly code.
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Co-developed-by: Lisa Wang <wyihan@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/.gitignore | 3 +-
tools/testing/selftests/kvm/Makefile.kvm | 29 ++++++++-
.../selftests/kvm/include/x86/tdx/td_boot.h | 69 ++++++++++++++++++++++
.../selftests/kvm/lib/x86/tdx/td_boot_offsets.c | 21 +++++++
4 files changed, 119 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 1d41a046a7bf..eef6055242b2 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -9,4 +9,5 @@
!config
!settings
!Makefile
-!Makefile.kvm
\ No newline at end of file
+!Makefile.kvm
+include/x86/**/*_offsets.h
\ No newline at end of file
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index e5769268936a..02fad7b35eac 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -19,6 +19,8 @@ LIBKVM += lib/userfaultfd_util.c
LIBKVM_STRING += lib/string_override.c
+LIBKVM_ASM_DEFS += lib/x86/tdx/td_boot_offsets.c
+
LIBKVM_x86 += lib/x86/apic.c
LIBKVM_x86 += lib/x86/handlers.S
LIBKVM_x86 += lib/x86/hyperv.c
@@ -260,6 +262,10 @@ OVERRIDE_TARGETS = 1
include ../lib.mk
include ../cgroup/lib/libcgroup.mk
+# Enable Kbuild tools.
+include $(top_srcdir)/scripts/Kbuild.include
+include $(top_srcdir)/scripts/Makefile.lib
+
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
@@ -272,15 +278,24 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-fno-stack-protector -fno-PIE -fno-strict-aliasing \
-I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \
-I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH) \
- -I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
+ -I ../rseq -I.. -I$(OUTPUT)/include/$(ARCH) $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
ifeq ($(ARCH),s390)
CFLAGS += -march=z10
endif
+
ifeq ($(ARCH),x86)
+
ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0)
CFLAGS += -march=x86-64-v2
endif
+
+KVM_GEN_HDRS := $(patsubst lib/x86/%.c, $(OUTPUT)/include/x86/%.h, $(filter lib/x86/%, $(LIBKVM_ASM_DEFS)))
+$(shell mkdir -p $(sort $(dir $(KVM_GEN_HDRS))))
+$(KVM_GEN_HDRS): GUARD = $(shell echo $(*F) | tr a-z A-Z | tr '.' '_')
+$(KVM_GEN_HDRS): $(OUTPUT)/include/x86/%.h: $(OUTPUT)/lib/x86/%.s FORCE
+ $(call filechk,offsets,__$(GUARD)_H__)
endif
+
ifeq ($(ARCH),arm64)
tools_dir := $(top_srcdir)/tools
arm64_tools_dir := $(tools_dir)/arch/arm64/tools/
@@ -313,6 +328,7 @@ LIBKVM_S := $(filter %.S,$(LIBKVM))
LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
+LIBKVM_ASM_DEFS_OBJ += $(patsubst %.c, $(OUTPUT)/%.s, $(LIBKVM_ASM_DEFS))
LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) $(LIBCGROUP_O)
SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS))
SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH)/%.o, $(SPLIT_TESTS))
@@ -338,7 +354,9 @@ $(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH)/%.o: $(ARCH)/%.c
$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
EXTRA_CLEAN += $(GEN_HDRS) \
+ $(KVM_GEN_HDRS) \
$(LIBKVM_OBJS) \
+ $(LIBKVM_ASM_DEFS_OBJ) \
$(SPLIT_TEST_GEN_OBJ) \
$(TEST_DEP_FILES) \
$(TEST_GEN_OBJ) \
@@ -350,6 +368,9 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS)
$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS)
$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+$(LIBKVM_ASM_DEFS_OBJ): $(OUTPUT)/%.s: %.c FORCE
+ $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -S $< -o $@
+
# Compile the string overrides as freestanding to prevent the compiler from
# generating self-referential code, e.g. without "freestanding" the compiler may
# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion.
@@ -358,11 +379,15 @@ $(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c
$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS)
+$(LIBKVM_OBJS): $(KVM_GEN_HDRS)
$(TEST_GEN_PROGS): $(LIBKVM_OBJS)
$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS)
$(TEST_GEN_OBJ): $(GEN_HDRS)
-cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
+FORCE:
+
+cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib .. \
+ $(wildcard $(sort $(dir $(KVM_GEN_HDRS))))
cscope:
$(RM) cscope.*
(find $(include_paths) -name '*.h' \
diff --git a/tools/testing/selftests/kvm/include/x86/tdx/td_boot.h b/tools/testing/selftests/kvm/include/x86/tdx/td_boot.h
new file mode 100644
index 000000000000..af4474dee387
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86/tdx/td_boot.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_TDX_TD_BOOT_H
+#define SELFTEST_TDX_TD_BOOT_H
+
+#include <stdint.h>
+
+#include <linux/compiler.h>
+#include <linux/sizes.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 (SZ_4G)
+
+/*
+ * The exact memory layout for LGDT or LIDT instructions.
+ */
+struct __packed td_boot_parameters_dtr {
+ u16 limit;
+ u32 base;
+};
+
+/*
+ * Allows each vCPU to be initialized with different rip and esp.
+ */
+struct td_per_vcpu_parameters {
+ u32 esp_gva;
+ u64 guest_code;
+};
+
+/*
+ * Boot parameters for the TD.
+ *
+ * Unlike a regular VM, KVM cannot 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 td_boot_parameters {
+ u32 cr0;
+ u32 cr3;
+ u32 cr4;
+ struct td_boot_parameters_dtr gdtr;
+ struct td_boot_parameters_dtr idtr;
+ struct td_per_vcpu_parameters per_vcpu[];
+};
+
+#endif /* SELFTEST_TDX_TD_BOOT_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/td_boot_offsets.c b/tools/testing/selftests/kvm/lib/x86/tdx/td_boot_offsets.c
new file mode 100644
index 000000000000..7f76a3585b99
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/td_boot_offsets.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#define COMPILE_OFFSETS
+
+#include <linux/kbuild.h>
+
+#include "tdx/td_boot.h"
+
+static void __attribute__((used)) common(void)
+{
+ OFFSET(TD_BOOT_PARAMETERS_CR0, td_boot_parameters, cr0);
+ OFFSET(TD_BOOT_PARAMETERS_CR3, td_boot_parameters, cr3);
+ OFFSET(TD_BOOT_PARAMETERS_CR4, td_boot_parameters, cr4);
+ OFFSET(TD_BOOT_PARAMETERS_GDT, td_boot_parameters, gdtr);
+ OFFSET(TD_BOOT_PARAMETERS_IDT, td_boot_parameters, idtr);
+ OFFSET(TD_BOOT_PARAMETERS_PER_VCPU, td_boot_parameters, per_vcpu);
+ OFFSET(TD_PER_VCPU_PARAMETERS_ESP_GVA, td_per_vcpu_parameters, esp_gva);
+ OFFSET(TD_PER_VCPU_PARAMETERS_GUEST_CODE, td_per_vcpu_parameters,
+ guest_code);
+ DEFINE(SIZEOF_TD_PER_VCPU_PARAMETERS,
+ sizeof(struct td_per_vcpu_parameters));
+}
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 09/22] KVM: selftests: Expose functions to get default sregs values
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
TDX can't set sregs values directly using KVM_SET_SREGS. Expose the
default values of certain sregs used by TDX VMs so they can be set
manually.
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
.../testing/selftests/kvm/include/x86/processor.h | 33 ++++++++++++++++++++++
tools/testing/selftests/kvm/lib/x86/processor.c | 18 ++++--------
2 files changed, 38 insertions(+), 13 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 0aa6eecfcbde..1ebf161ec5d0 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -29,6 +29,10 @@ extern u64 guest_tsc_khz;
#define MAX_NR_CPUID_ENTRIES 100
#endif
+#ifndef NUM_INTERRUPTS
+#define NUM_INTERRUPTS 256
+#endif
+
#define NONCANONICAL 0xaaaaaaaaaaaaaaaaull
/* Forced emulation prefix, used to invoke the emulator unconditionally. */
@@ -1562,4 +1566,33 @@ u64 *tdp_get_pte(struct kvm_vm *vm, u64 l2_gpa);
bool sys_clocksource_is_based_on_tsc(void);
+static inline u16 kvm_get_default_idt_limit(void)
+{
+ return NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+}
+
+static inline u16 kvm_get_default_gdt_limit(void)
+{
+ return getpagesize() - 1;
+}
+
+static inline u64 kvm_get_default_cr0(void)
+{
+ return X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
+}
+
+static inline u64 kvm_get_default_cr4(void)
+{
+ u64 cr4 = X86_CR4_PAE | X86_CR4_OSFXSR;
+
+ if (kvm_cpu_has(X86_FEATURE_XSAVE))
+ cr4 |= X86_CR4_OSXSAVE;
+ return cr4;
+}
+
+static inline u64 kvm_get_default_efer(void)
+{
+ return EFER_LME | EFER_LMA | EFER_NX;
+}
+
#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 62abfe27fe3a..5027411665bf 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -15,10 +15,6 @@
#include "tdx/tdx_util.h"
#include "vmx.h"
-#ifndef NUM_INTERRUPTS
-#define NUM_INTERRUPTS 256
-#endif
-
gva_t exception_handlers;
bool host_cpu_is_amd;
bool host_cpu_is_intel;
@@ -647,16 +643,12 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
vcpu_sregs_get(vcpu, &sregs);
sregs.idt.base = vm->arch.idt;
- sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+ sregs.idt.limit = kvm_get_default_idt_limit();
sregs.gdt.base = vm->arch.gdt;
- sregs.gdt.limit = getpagesize() - 1;
-
- sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
- sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
- if (kvm_cpu_has(X86_FEATURE_XSAVE))
- sregs.cr4 |= X86_CR4_OSXSAVE;
- if (vm->mmu.pgtable_levels == 5)
- sregs.cr4 |= X86_CR4_LA57;
+ sregs.gdt.limit = kvm_get_default_gdt_limit();
+
+ sregs.cr0 = kvm_get_default_cr0();
+ sregs.cr4 |= kvm_get_default_cr4();
sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
kvm_seg_set_unusable(&sregs.ldt);
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 10/22] KVM: selftests: Set up TDX boot code region
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Add memory for TDX boot code in a separate memslot.
Use virt_map() to get identity map in this memory region to allow for
seamless transition from paging disabled to paging enabled code.
Copy the boot code into the memory region and set up the reset vector
at this point. While it's possible to separate the memory allocation and
boot code initialization into separate functions, having all the
calculations for memory size and offsets in one place simplifies the
code and avoids duplications.
Handcode the reset vector as suggested by Sean Christopherson.
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Erdem Aktas <erdemaktas@google.com>
Signed-off-by: Erdem Aktas <erdemaktas@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../selftests/kvm/include/x86/tdx/tdx_util.h | 1 +
tools/testing/selftests/kvm/lib/x86/processor.c | 4 +-
tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c | 47 ++++++++++++++++++++++
4 files changed, 52 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 929965ca4b75..a651a876c522 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -31,6 +31,7 @@ LIBKVM_x86 += lib/x86/sev.c
LIBKVM_x86 += lib/x86/svm.c
LIBKVM_x86 += lib/x86/ucall.c
LIBKVM_x86 += lib/x86/vmx.c
+LIBKVM_x86 += lib/x86/tdx/tdx_util.c
LIBKVM_x86 += lib/x86/tdx/td_boot.S
LIBKVM_arm64 += lib/arm64/gic.c
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 48d4bd36c35b..d66ea7bc85f9 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
@@ -40,5 +40,6 @@ static inline bool is_tdx_vm(struct kvm_vm *vm)
})
void tdx_init_vm(struct kvm_vm *vm, u64 attributes);
+void tdx_vm_setup_boot_code_region(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 5027411665bf..dfabdfd17976 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -791,8 +791,10 @@ 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))
+ if (is_tdx_vm(vm)) {
tdx_init_vm(vm, 0);
+ tdx_vm_setup_boot_code_region(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.");
diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
index e5c998874a0d..bbfaa9af9c60 100644
--- a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
@@ -2,8 +2,55 @@
#include "kvm_util.h"
#include "processor.h"
+#include "tdx/td_boot.h"
#include "tdx/tdx_util.h"
+/* Arbitrarily selected to avoid overlaps with anything else */
+#define TD_BOOT_CODE_SLOT 20
+
+#define X86_RESET_VECTOR 0xfffffff0ul
+#define X86_RESET_VECTOR_SIZE 16
+
+void tdx_vm_setup_boot_code_region(struct kvm_vm *vm)
+{
+ size_t total_code_size = TD_BOOT_CODE_SIZE + X86_RESET_VECTOR_SIZE;
+ gpa_t boot_code_gpa = X86_RESET_VECTOR - TD_BOOT_CODE_SIZE;
+ gpa_t alloc_gpa = round_down(boot_code_gpa, PAGE_SIZE);
+ size_t nr_pages = DIV_ROUND_UP(total_code_size, PAGE_SIZE);
+ gpa_t gpa;
+ u8 *hva;
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ alloc_gpa,
+ TD_BOOT_CODE_SLOT, nr_pages,
+ KVM_MEM_GUEST_MEMFD);
+
+ gpa = vm_phy_pages_alloc(vm, nr_pages, alloc_gpa, TD_BOOT_CODE_SLOT);
+ TEST_ASSERT(gpa == alloc_gpa, "Failed vm_phy_pages_alloc\n");
+
+ virt_map(vm, alloc_gpa, alloc_gpa, nr_pages);
+ hva = addr_gpa2hva(vm, boot_code_gpa);
+ memcpy(hva, td_boot, TD_BOOT_CODE_SIZE);
+
+ hva += TD_BOOT_CODE_SIZE;
+ TEST_ASSERT(hva == addr_gpa2hva(vm, X86_RESET_VECTOR),
+ "Expected RESET vector at hva 0x%lx, got %lx",
+ (unsigned long)addr_gpa2hva(vm, X86_RESET_VECTOR), (unsigned long)hva);
+
+ /*
+ * Handcode "JMP rel8" at the RESET vector to jump back to the TD boot
+ * code, as there are only 16 bytes at the RESET vector before RIP will
+ * wrap back to zero. Insert a trailing int3 so that the vCPU crashes
+ * in case the JMP somehow falls through. Note! The target address is
+ * relative to the end of the instruction!
+ */
+ TEST_ASSERT(TD_BOOT_CODE_SIZE + 2 <= 128,
+ "TD boot code not addressable by 'JMP rel8'");
+ hva[0] = 0xeb;
+ hva[1] = 256 - 2 - TD_BOOT_CODE_SIZE;
+ hva[2] = 0xcc;
+}
+
static struct kvm_tdx_capabilities *tdx_read_capabilities(struct kvm_vm *vm)
{
struct kvm_tdx_capabilities *tdx_cap = NULL;
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 11/22] KVM: selftests: Set up TDX boot parameters region
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Allocate memory for TDX boot parameters and define the utility functions
necessary to fill this memory with the boot parameters.
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
.../selftests/kvm/include/x86/tdx/tdx_util.h | 2 +
tools/testing/selftests/kvm/lib/x86/processor.c | 2 +
tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c | 56 ++++++++++++++++++++++
3 files changed, 60 insertions(+)
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 d66ea7bc85f9..9660ea9d2f31 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
@@ -41,5 +41,7 @@ static inline bool is_tdx_vm(struct kvm_vm *vm)
void tdx_init_vm(struct kvm_vm *vm, u64 attributes);
void tdx_vm_setup_boot_code_region(struct kvm_vm *vm);
+void tdx_vm_setup_boot_parameters_region(struct kvm_vm *vm, u32 nr_runnable_vcpus);
+void tdx_vm_load_common_boot_parameters(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 dfabdfd17976..c7c4a37b3170 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -794,6 +794,8 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus)
if (is_tdx_vm(vm)) {
tdx_init_vm(vm, 0);
tdx_vm_setup_boot_code_region(vm);
+ tdx_vm_setup_boot_parameters_region(vm, nr_vcpus);
+ tdx_vm_load_common_boot_parameters(vm);
}
r = __vm_ioctl(vm, KVM_GET_TSC_KHZ, NULL);
diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
index bbfaa9af9c60..b16bf24f3ef1 100644
--- a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
@@ -3,10 +3,12 @@
#include "kvm_util.h"
#include "processor.h"
#include "tdx/td_boot.h"
+#include "tdx/td_boot_asm.h"
#include "tdx/tdx_util.h"
/* Arbitrarily selected to avoid overlaps with anything else */
#define TD_BOOT_CODE_SLOT 20
+#define TD_BOOT_PARAMETERS_SLOT 21
#define X86_RESET_VECTOR 0xfffffff0ul
#define X86_RESET_VECTOR_SIZE 16
@@ -51,6 +53,60 @@ void tdx_vm_setup_boot_code_region(struct kvm_vm *vm)
hva[2] = 0xcc;
}
+void tdx_vm_setup_boot_parameters_region(struct kvm_vm *vm, u32 nr_runnable_vcpus)
+{
+ size_t boot_params_size =
+ sizeof(struct td_boot_parameters) +
+ nr_runnable_vcpus * sizeof(struct td_per_vcpu_parameters);
+ int npages = DIV_ROUND_UP(boot_params_size, PAGE_SIZE);
+ gpa_t gpa;
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ TD_BOOT_PARAMETERS_GPA,
+ TD_BOOT_PARAMETERS_SLOT, npages,
+ KVM_MEM_GUEST_MEMFD);
+ gpa = vm_phy_pages_alloc(vm, npages, TD_BOOT_PARAMETERS_GPA, TD_BOOT_PARAMETERS_SLOT);
+ TEST_ASSERT(gpa == TD_BOOT_PARAMETERS_GPA, "Failed vm_phy_pages_alloc\n");
+
+ virt_map(vm, TD_BOOT_PARAMETERS_GPA, TD_BOOT_PARAMETERS_GPA, npages);
+}
+
+void tdx_vm_load_common_boot_parameters(struct kvm_vm *vm)
+{
+ struct td_boot_parameters *params =
+ addr_gpa2hva(vm, TD_BOOT_PARAMETERS_GPA);
+ u32 cr4;
+
+ TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXVYY_4K);
+
+ cr4 = kvm_get_default_cr4();
+ if (vm->mmu.pgtable_levels == 5)
+ cr4 |= X86_CR4_LA57;
+
+ /* TDX spec 11.6.2: CR4 bit MCE is fixed to 1 */
+ cr4 |= X86_CR4_MCE;
+
+ /* TDX spec 11.6.2: CR4 bit VMXE and SMXE are fixed to 0 */
+ cr4 &= ~(X86_CR4_VMXE | X86_CR4_SMXE);
+
+ /* Set parameters! */
+ params->cr0 = kvm_get_default_cr0();
+ TEST_ASSERT(vm->mmu.pgd < (1ULL << 32),
+ "PGD must be within 32-bit address space for 32-bit boot code");
+ params->cr3 = vm->mmu.pgd;
+ params->cr4 = cr4;
+ params->idtr.base = vm->arch.idt;
+ params->idtr.limit = kvm_get_default_idt_limit();
+ params->gdtr.base = vm->arch.gdt;
+ params->gdtr.limit = kvm_get_default_gdt_limit();
+
+ 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");
+ TEST_ASSERT(params->idtr.base != 0, "idt base address should not be 0");
+}
+
static struct kvm_tdx_capabilities *tdx_read_capabilities(struct kvm_vm *vm)
{
struct kvm_tdx_capabilities *tdx_cap = NULL;
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 12/22] KVM: selftests: Back the first memory region with guest_memfd for TDX
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
Force GUEST_MEMFD for the primary memory region of TDX VMs.
TDX must use guest_memfd for private pages as there is no alternative
mechanism supported by the TDX architecture.
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/lib/kvm_util.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index d1befa3f4b30..9a29540fff40 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -472,7 +472,7 @@ void kvm_set_files_rlimit(u32 nr_vcpus)
static bool is_guest_memfd_required(struct vm_shape shape)
{
#ifdef __x86_64__
- return shape.type == KVM_X86_SNP_VM;
+ return (shape.type == KVM_X86_SNP_VM || shape.type == KVM_X86_TDX_VM);
#else
return false;
#endif
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 13/22] KVM: selftests: Set first memory region as shared if guest_memfd
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
Set the initial state of the first memory region as shared if it is
backed by guest_memfd, so that the KVM selftest framework functions can
populate mmap()-ed guest_memfd memory the same way memory from other
memory providers are populated.
For CoCo VMs, pages that need to be private are explicitly set to
private before executing the VM.
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/lib/kvm_util.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 9a29540fff40..1bab7d76a59c 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -484,8 +484,10 @@ struct kvm_vm *__vm_create(struct vm_shape shape, u32 nr_runnable_vcpus,
u64 nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus,
nr_extra_pages);
struct userspace_mem_region *slot0;
+ u64 gmem_flags = 0;
struct kvm_vm *vm;
- int i, flags;
+ int flags = 0;
+ int i;
kvm_set_files_rlimit(nr_runnable_vcpus);
@@ -495,14 +497,16 @@ struct kvm_vm *__vm_create(struct vm_shape shape, u32 nr_runnable_vcpus,
vm = ____vm_create(shape);
/*
- * Force GUEST_MEMFD for the primary memory region if necessary, e.g.
- * for CoCo VMs that require GUEST_MEMFD backed private memory.
+ * Force GUEST_MEMFD for the primary memory region if necessary, and
+ * initialize it as shared so the selftest framework can populate it
+ * exactly like other memory providers.
*/
- flags = 0;
- if (is_guest_memfd_required(shape))
+ if (is_guest_memfd_required(shape)) {
flags |= KVM_MEM_GUEST_MEMFD;
+ gmem_flags |= GUEST_MEMFD_FLAG_INIT_SHARED;
+ }
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, flags);
+ vm_mem_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, flags, -1, 0, gmem_flags);
for (i = 0; i < NR_MEM_REGIONS; i++)
vm->memslots[i] = 0;
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 14/22] KVM: selftests: Expose function to allocate vCPU stack
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Introduce kvm_allocate_vcpu_stack() to allocate a vCPU's stack
in preparation for TDX to allocate a vCPU's stack and initialize
its stack pointer.
TDX VMs' registers are protected state and cannot be initialized
using the KVM_SET_REGS ioctl() that is used for normal VMs. A TDX
vCPU's stack address will be a property of the TDX specific boot code
that initializes the vCPUs' stack pointers at boot.
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/include/x86/processor.h | 2 ++
tools/testing/selftests/kvm/lib/x86/processor.c | 16 +++++++++++-----
2 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 1ebf161ec5d0..ed9c031b77b8 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -1142,6 +1142,8 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu,
vcpu_set_or_clear_cpuid_feature(vcpu, feature, false);
}
+gva_t kvm_allocate_vcpu_stack(struct kvm_vm *vm);
+
u64 vcpu_get_msr(struct kvm_vcpu *vcpu, u64 msr_index);
int _vcpu_set_msr(struct kvm_vcpu *vcpu, u64 msr_index, u64 msr_value);
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index c7c4a37b3170..8b0aa64384a1 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -813,12 +813,9 @@ void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
vcpu_regs_set(vcpu, ®s);
}
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
+gva_t kvm_allocate_vcpu_stack(struct kvm_vm *vm)
{
- struct kvm_mp_state mp_state;
- struct kvm_regs regs;
gva_t stack_gva;
- struct kvm_vcpu *vcpu;
stack_gva = __vm_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
DEFAULT_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA);
@@ -838,6 +835,15 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
"__vm_alloc() did not provide a page-aligned address");
stack_gva -= 8;
+ return stack_gva;
+}
+
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
+{
+ struct kvm_mp_state mp_state;
+ struct kvm_vcpu *vcpu;
+ struct kvm_regs regs;
+
vcpu = __vm_vcpu_add(vm, vcpu_id);
vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
vcpu_init_sregs(vm, vcpu);
@@ -846,7 +852,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
/* Setup guest general purpose registers */
vcpu_regs_get(vcpu, ®s);
regs.rflags = regs.rflags | 0x2;
- regs.rsp = stack_gva;
+ regs.rsp = kvm_allocate_vcpu_stack(vm);
vcpu_regs_set(vcpu, ®s);
/* Setup the MP state */
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 15/22] KVM: selftests: Call KVM_TDX_INIT_VCPU when creating a new TDX vcpu
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
TDX VMs need to issue the KVM_TDX_INIT_VCPU ioctl for each vcpu after
vcpu creation.
Since the cpuids for TD are managed by the TDX module, read the values
virtualized for the TD using KVM_TDX_GET_CPUID and set them in kvm using
KVM_SET_CPUID2 so that kvm has an accurate view of the VM cpuid values.
Signed-off-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
.../selftests/kvm/include/x86/tdx/tdx_util.h | 24 ++++++++++++++++
tools/testing/selftests/kvm/lib/x86/processor.c | 33 ++++++++++++++++------
2 files changed, 49 insertions(+), 8 deletions(-)
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 9660ea9d2f31..4d01f806b37d 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
@@ -39,6 +39,30 @@ static inline bool is_tdx_vm(struct kvm_vm *vm)
__TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \
})
+#define __tdx_vcpu_ioctl(vcpu, cmd, _flags, arg) \
+({ \
+ int r; \
+ \
+ union { \
+ struct kvm_tdx_cmd c; \
+ unsigned long raw; \
+ } tdx_cmd = { .c = { \
+ .id = (cmd), \
+ .flags = (u32)(_flags), \
+ .data = (u64)(arg), \
+ } }; \
+ \
+ r = __vcpu_ioctl(vcpu, KVM_MEMORY_ENCRYPT_OP, &tdx_cmd.raw); \
+ r ?: tdx_cmd.c.hw_error; \
+})
+
+#define tdx_vcpu_ioctl(vcpu, cmd, flags, arg) \
+({ \
+ int ret = __tdx_vcpu_ioctl(vcpu, cmd, flags, arg); \
+ \
+ __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \
+})
+
void tdx_init_vm(struct kvm_vm *vm, u64 attributes);
void tdx_vm_setup_boot_code_region(struct kvm_vm *vm);
void tdx_vm_setup_boot_parameters_region(struct kvm_vm *vm, u32 nr_runnable_vcpus);
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 8b0aa64384a1..757da2295ba0 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -838,6 +838,17 @@ gva_t kvm_allocate_vcpu_stack(struct kvm_vm *vm)
return stack_gva;
}
+static void tdx_vcpu_init(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid2 *cpuid;
+
+ cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES);
+ tdx_vcpu_ioctl(vcpu, KVM_TDX_GET_CPUID, 0, cpuid);
+ vcpu_init_cpuid(vcpu, cpuid);
+ free(cpuid);
+ tdx_vcpu_ioctl(vcpu, KVM_TDX_INIT_VCPU, 0, NULL);
+}
+
struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
{
struct kvm_mp_state mp_state;
@@ -845,15 +856,21 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
struct kvm_regs regs;
vcpu = __vm_vcpu_add(vm, vcpu_id);
- vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
- vcpu_init_sregs(vm, vcpu);
- vcpu_init_xcrs(vm, vcpu);
- /* Setup guest general purpose registers */
- vcpu_regs_get(vcpu, ®s);
- regs.rflags = regs.rflags | 0x2;
- regs.rsp = kvm_allocate_vcpu_stack(vm);
- vcpu_regs_set(vcpu, ®s);
+ if (is_tdx_vm(vm)) {
+ tdx_vcpu_init(vm, vcpu);
+ } else {
+ vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
+
+ vcpu_init_sregs(vm, vcpu);
+ vcpu_init_xcrs(vm, vcpu);
+
+ /* Setup guest general purpose registers */
+ vcpu_regs_get(vcpu, ®s);
+ regs.rflags = regs.rflags | 0x2;
+ regs.rsp = kvm_allocate_vcpu_stack(vm);
+ vcpu_regs_set(vcpu, ®s);
+ }
/* Setup the MP state */
mp_state.mp_state = 0;
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 16/22] KVM: selftests: Load per-vCPU guest stack in TDX boot parameters
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Allocate a guest stack for each vCPU and record the GVA in the TDX boot
parameters region to allow proper vCPU initialization.
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h | 1 +
tools/testing/selftests/kvm/lib/x86/processor.c | 2 ++
tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c | 11 +++++++++++
3 files changed, 14 insertions(+)
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 4d01f806b37d..644de6bbec17 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
@@ -67,5 +67,6 @@ void tdx_init_vm(struct kvm_vm *vm, u64 attributes);
void tdx_vm_setup_boot_code_region(struct kvm_vm *vm);
void tdx_vm_setup_boot_parameters_region(struct kvm_vm *vm, u32 nr_runnable_vcpus);
void tdx_vm_load_common_boot_parameters(struct kvm_vm *vm);
+void tdx_vcpu_load_boot_parameters(struct kvm_vm *vm, struct kvm_vcpu *vcpu);
#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 757da2295ba0..ba332f279f03 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -847,6 +847,8 @@ static void tdx_vcpu_init(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
vcpu_init_cpuid(vcpu, cpuid);
free(cpuid);
tdx_vcpu_ioctl(vcpu, KVM_TDX_INIT_VCPU, 0, NULL);
+
+ tdx_vcpu_load_boot_parameters(vm, vcpu);
}
struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, u32 vcpu_id)
diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
index b16bf24f3ef1..f26d602501b8 100644
--- a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
@@ -107,6 +107,17 @@ void tdx_vm_load_common_boot_parameters(struct kvm_vm *vm)
TEST_ASSERT(params->idtr.base != 0, "idt base address should not be 0");
}
+void tdx_vcpu_load_boot_parameters(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
+{
+ struct td_boot_parameters *params =
+ addr_gpa2hva(vm, TD_BOOT_PARAMETERS_GPA);
+ struct td_per_vcpu_parameters *vcpu_params =
+ ¶ms->per_vcpu[vcpu->id];
+
+ vcpu_params->esp_gva = kvm_allocate_vcpu_stack(vm);
+}
+
+
static struct kvm_tdx_capabilities *tdx_read_capabilities(struct kvm_vm *vm)
{
struct kvm_tdx_capabilities *tdx_cap = NULL;
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 17/22] KVM: selftests: Set entry point for TDX guest code
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Since the rip register is inaccessible for TDX VMs, we need a different
way to set the guest entry point for TDX VMs. This is done by writing
the guest code address to a predefined location in the guest memory and
loading it into rip as part of the TDX boot code.
Signed-off-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h | 1 +
tools/testing/selftests/kvm/lib/x86/processor.c | 10 +++++++---
tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c | 10 ++++++++++
3 files changed, 18 insertions(+), 3 deletions(-)
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 644de6bbec17..efa4c7f7b1c1 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
@@ -68,5 +68,6 @@ void tdx_vm_setup_boot_code_region(struct kvm_vm *vm);
void tdx_vm_setup_boot_parameters_region(struct kvm_vm *vm, u32 nr_runnable_vcpus);
void tdx_vm_load_common_boot_parameters(struct kvm_vm *vm);
void tdx_vcpu_load_boot_parameters(struct kvm_vm *vm, struct kvm_vcpu *vcpu);
+void tdx_vcpu_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code);
#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 ba332f279f03..d84c629a1945 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -808,9 +808,13 @@ void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
{
struct kvm_regs regs;
- vcpu_regs_get(vcpu, ®s);
- regs.rip = (unsigned long) guest_code;
- vcpu_regs_set(vcpu, ®s);
+ if (is_tdx_vm(vcpu->vm)) {
+ tdx_vcpu_set_entry_point(vcpu, guest_code);
+ } else {
+ vcpu_regs_get(vcpu, ®s);
+ regs.rip = (unsigned long)guest_code;
+ vcpu_regs_set(vcpu, ®s);
+ }
}
gva_t kvm_allocate_vcpu_stack(struct kvm_vm *vm)
diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
index f26d602501b8..158cba1b95e3 100644
--- a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
@@ -117,6 +117,16 @@ void tdx_vcpu_load_boot_parameters(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
vcpu_params->esp_gva = kvm_allocate_vcpu_stack(vm);
}
+void tdx_vcpu_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+ struct td_boot_parameters *params =
+ addr_gpa2hva(vcpu->vm, TD_BOOT_PARAMETERS_GPA);
+ struct td_per_vcpu_parameters *vcpu_params =
+ ¶ms->per_vcpu[vcpu->id];
+
+ vcpu_params->guest_code = (u64)guest_code;
+}
+
static struct kvm_tdx_capabilities *tdx_read_capabilities(struct kvm_vm *vm)
{
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 18/22] KVM: selftests: Add helpers to init TDX memory and finalize VM
From: Lisa Wang @ 2026-05-21 23:16 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Ackerley Tng <ackerleytng@google.com>
TDX protected memory needs to be measured and encrypted before it can be
used by the guest. Traverse the VM's memory regions and initialize all
the protected ranges by calling KVM_TDX_INIT_MEM_REGION.
Once all the memory is initialized, the VM can be finalized by calling
KVM_TDX_FINALIZE_VM.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Erdem Aktas <erdemaktas@google.com>
Signed-off-by: Erdem Aktas <erdemaktas@google.com>
Co-developed-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
.../selftests/kvm/include/x86/tdx/tdx_util.h | 2 +
tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c | 59 ++++++++++++++++++++++
2 files changed, 61 insertions(+)
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 efa4c7f7b1c1..8276622c50d2 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
@@ -70,4 +70,6 @@ void tdx_vm_load_common_boot_parameters(struct kvm_vm *vm);
void tdx_vcpu_load_boot_parameters(struct kvm_vm *vm, struct kvm_vcpu *vcpu);
void tdx_vcpu_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code);
+void tdx_vm_finalize(struct kvm_vm *vm);
+
#endif /* SELFTESTS_TDX_TDX_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
index 158cba1b95e3..584e6600b588 100644
--- a/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c
@@ -1,5 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/align.h>
+
#include "kvm_util.h"
#include "processor.h"
#include "tdx/td_boot.h"
@@ -273,3 +275,60 @@ void tdx_init_vm(struct kvm_vm *vm, u64 attributes)
free(init_vm);
}
+
+static void tdx_init_mem_region(struct kvm_vm *vm, void *source_pages,
+ u64 gpa, u64 size)
+{
+ u32 flags = KVM_TDX_MEASURE_MEMORY_REGION;
+ struct kvm_tdx_init_mem_region mem_region = {
+ .source_addr = (u64)source_pages,
+ .gpa = gpa,
+ .nr_pages = size / PAGE_SIZE,
+ };
+ struct kvm_vcpu *vcpu;
+
+ vcpu = list_first_entry_or_null(&vm->vcpus, struct kvm_vcpu, list);
+
+ TEST_ASSERT(size && IS_ALIGNED(size, PAGE_SIZE),
+ "Cannot add partial pages to the guest memory.\n");
+ TEST_ASSERT(IS_ALIGNED((u64)source_pages, PAGE_SIZE),
+ "Source memory buffer is not page aligned\n");
+ tdx_vcpu_ioctl(vcpu, KVM_TDX_INIT_MEM_REGION, flags, &mem_region);
+}
+
+static void tdx_load_private_memory(struct kvm_vm *vm)
+{
+ struct userspace_mem_region *region;
+ int ctr;
+
+ hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) {
+ const struct sparsebit *protected_pages = region->protected_phy_pages;
+ const gpa_t gpa_base = region->region.guest_phys_addr;
+ const u64 hva_base = region->region.userspace_addr;
+ const sparsebit_idx_t lowest_page_in_region = gpa_base >> vm->page_shift;
+ sparsebit_idx_t i, j;
+
+ if (!sparsebit_any_set(protected_pages))
+ continue;
+
+ TEST_ASSERT(region->region.guest_memfd != -1,
+ "TD private memory must be backed by guest_memfd");
+
+ sparsebit_for_each_set_range(protected_pages, i, j) {
+ const u64 size_to_load = (j - i + 1) * vm->page_size;
+ const u64 offset =
+ (i - lowest_page_in_region) * vm->page_size;
+ const u64 hva = hva_base + offset;
+ const u64 gpa = gpa_base + offset;
+
+ vm_mem_set_private(vm, gpa, size_to_load);
+ tdx_init_mem_region(vm, (void *)hva, gpa, size_to_load);
+ }
+ }
+}
+
+void tdx_vm_finalize(struct kvm_vm *vm)
+{
+ tdx_load_private_memory(vm);
+ tdx_vm_ioctl(vm, KVM_TDX_FINALIZE_VM, 0, NULL);
+}
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 19/22] KVM: selftests: Finalize TD memory as part of kvm_arch_vm_finalize_vcpus
From: Lisa Wang @ 2026-05-21 23:17 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Finalize TDX VM after creation to make it runnable.
Signed-off-by: Sagi Shahar <sagis@google.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/lib/x86/processor.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index d84c629a1945..842cac168e99 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -1479,6 +1479,12 @@ bool kvm_arch_has_default_irqchip(void)
return true;
}
+void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm)
+{
+ if (is_tdx_vm(vm))
+ tdx_vm_finalize(vm);
+}
+
void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu, u64 smram_gpa,
const void *smi_handler, size_t handler_size)
{
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 20/22] KVM: selftests: Implement MMIO WRITE for the TDX VM
From: Lisa Wang @ 2026-05-21 23:17 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Erdem Aktas <erdemaktas@google.com>
Implement the tdx_mmio_write() to allow TDX VMs to request MMIO
emulation.
Follow the Intel Guest-Hypervisor Communication Interface (GHCI) spec
to the minimum extent that a spec-abiding TDX module will pass the
request to KVM. Skip implementing the #VE handler as described in the
GHCI spec so selftests will not take a dependency on having a working
To perform emulated I/O, VMs use the TDG.VP.VMCALL instruction to
request MMIO.
Signed-off-by: Erdem Aktas <erdemaktas@google.com>
Co-developed-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Co-developed-by: Lisa Wang <wyihan@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
tools/testing/selftests/kvm/include/x86/tdx/tdx.h | 16 ++++++++++++
tools/testing/selftests/kvm/lib/x86/tdx/tdx.c | 30 +++++++++++++++++++++++
3 files changed, 47 insertions(+)
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index a651a876c522..489324cecf83 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -33,6 +33,7 @@ LIBKVM_x86 += lib/x86/ucall.c
LIBKVM_x86 += lib/x86/vmx.c
LIBKVM_x86 += lib/x86/tdx/tdx_util.c
LIBKVM_x86 += lib/x86/tdx/td_boot.S
+LIBKVM_x86 += lib/x86/tdx/tdx.c
LIBKVM_arm64 += lib/arm64/gic.c
LIBKVM_arm64 += lib/arm64/gic_v3.c
diff --git a/tools/testing/selftests/kvm/include/x86/tdx/tdx.h b/tools/testing/selftests/kvm/include/x86/tdx/tdx.h
new file mode 100644
index 000000000000..810ca7423c84
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTESTS_TDX_TDX_H
+#define SELFTESTS_TDX_TDX_H
+
+#include <linux/types.h>
+
+enum mmio_size {
+ MMIO_SIZE_1B = 1,
+ MMIO_SIZE_2B = 2,
+ MMIO_SIZE_4B = 4,
+ MMIO_SIZE_8B = 8
+};
+
+u64 tdx_mmio_write(u64 address, enum mmio_size size, u64 data_in);
+
+#endif // SELFTESTS_TDX_TDX_H
diff --git a/tools/testing/selftests/kvm/lib/x86/tdx/tdx.c b/tools/testing/selftests/kvm/lib/x86/tdx/tdx.c
new file mode 100644
index 000000000000..f19be79fe11f
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86/tdx/tdx.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "tdx/tdx.h"
+
+#define TDG_VP_VMCALL 0
+#define TDG_VP_VMCALL_VE_REQUEST_MMIO 48
+#define TDVMCALL_MMIO_WRITE 1
+#define TDVMCALL_EXPOSE_REGS_MASK 0xFC00
+
+u64 tdx_mmio_write(u64 address, enum mmio_size size, u64 data_in)
+{
+ register u64 r10_reg asm("r10") = TDG_VP_VMCALL;
+ register u64 r11_reg asm("r11") = TDG_VP_VMCALL_VE_REQUEST_MMIO;
+ register u64 r12_reg asm("r12") = size;
+ register u64 r13_reg asm("r13") = TDVMCALL_MMIO_WRITE;
+ register u64 r14_reg asm("r14") = address;
+ register u64 r15_reg asm("r15") = data_in;
+ register u64 rax_reg asm("rax") = TDG_VP_VMCALL;
+ register u64 rcx_reg asm("rcx") = TDVMCALL_EXPOSE_REGS_MASK;
+
+ asm volatile(
+ ".byte 0x66,0x0f,0x01,0xcc" /* tdcall */
+ : "+r" (r10_reg), "+r" (r11_reg)
+ : "r" (r12_reg), "r" (r13_reg), "r" (r14_reg), "r" (r15_reg),
+ "r" (rax_reg), "r" (rcx_reg)
+ : "cc", "memory"
+ );
+
+ return r10_reg;
+}
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 21/22] KVM: selftests: Add ucall support for TDX
From: Lisa Wang @ 2026-05-21 23:17 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Ackerley Tng <ackerleytng@google.com>
Implement TDX ucall using TDCALL-based MMIO to pass the ucall address
from the VM to the host.
In standard KVM selftests, ucall uses a PIO instruction as a trigger
to exit to the host, which then retrieves the ucall address by reading
the guest's RDI register. This approach is incompatible with TDX
because the host cannot access guest registers.
Furthermore, PIO exits only expose 4 bytes of immediate data, which
is insufficient for a 8-byte ucall address. By using TDCALL-based MMIO,
the VM can share the full 8-byte address in a single exit without
refactoring the common ucall framework and other non-x86 architectures.
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Sagi Shahar <sagis@google.com>
Co-developed-by: Lisa Wang <wyihan@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/include/x86/ucall.h | 6 -----
tools/testing/selftests/kvm/lib/x86/ucall.c | 30 +++++++++++++++++++++++++
2 files changed, 30 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/x86/ucall.h b/tools/testing/selftests/kvm/include/x86/ucall.h
index 0e4950041e3e..7e54ec2c1a45 100644
--- a/tools/testing/selftests/kvm/include/x86/ucall.h
+++ b/tools/testing/selftests/kvm/include/x86/ucall.h
@@ -2,12 +2,6 @@
#ifndef SELFTEST_KVM_UCALL_H
#define SELFTEST_KVM_UCALL_H
-#include "kvm_util.h"
-
#define UCALL_EXIT_REASON KVM_EXIT_IO
-static inline void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa)
-{
-}
-
#endif
diff --git a/tools/testing/selftests/kvm/lib/x86/ucall.c b/tools/testing/selftests/kvm/lib/x86/ucall.c
index e7dd5791959b..c8e3418d53af 100644
--- a/tools/testing/selftests/kvm/lib/x86/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86/ucall.c
@@ -5,11 +5,34 @@
* Copyright (C) 2018, Red Hat, Inc.
*/
#include "kvm_util.h"
+#include "tdx/tdx.h"
+#include "tdx/tdx_util.h"
#define UCALL_PIO_PORT ((u16)0x1000)
+static u8 vm_type;
+static gpa_t host_ucall_mmio_gpa;
+static gpa_t ucall_mmio_gpa;
+
+void ucall_arch_init(struct kvm_vm *vm, gpa_t mmio_gpa)
+{
+ vm_type = vm->type;
+ sync_global_to_guest(vm, vm_type);
+
+ if (is_tdx_vm(vm)) {
+ host_ucall_mmio_gpa = ucall_mmio_gpa = mmio_gpa;
+ ucall_mmio_gpa |= vm->arch.s_bit;
+ sync_global_to_guest(vm, ucall_mmio_gpa);
+ }
+}
+
void ucall_arch_do_ucall(gva_t uc)
{
+ if (vm_type == KVM_X86_TDX_VM) {
+ tdx_mmio_write(ucall_mmio_gpa, MMIO_SIZE_8B, uc);
+ return;
+ }
+
/*
* FIXME: Revert this hack (the entire commit that added it) once nVMX
* preserves L2 GPRs across a nested VM-Exit. If a ucall from L2, e.g.
@@ -46,6 +69,13 @@ void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
+ if (vm_type == KVM_X86_TDX_VM) {
+ if (run->exit_reason == KVM_EXIT_MMIO &&
+ run->mmio.phys_addr == host_ucall_mmio_gpa &&
+ run->mmio.len == MMIO_SIZE_8B && run->mmio.is_write)
+ return (void *)(*((u64 *)run->mmio.data));
+ }
+
if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
struct kvm_regs regs;
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH v13 22/22] KVM: selftests: Add TDX lifecycle test
From: Lisa Wang @ 2026-05-21 23:17 UTC (permalink / raw)
To: Andrew Jones, Ackerley Tng, Binbin Wu, Chao Gao, Chenyi Qiang,
Dave Hansen, Erdem Aktas, Ira Weiny, Isaku Yamahata,
Kiryl Shutsemau, linux-kselftest, Paolo Bonzini, Pratik R. Sampat,
Reinette Chatre, Rick Edgecombe, Roger Wang, Ryan Afranji,
Sagi Shahar, Sean Christopherson, Shuah Khan, Oliver Upton
Cc: Jeremiah McReynolds, kvm, linux-coco, linux-kernel, x86,
Lisa Wang
In-Reply-To: <20260521-tdx-selftests-v13-v13-0-6983ae4c3a4d@google.com>
From: Sagi Shahar <sagis@google.com>
Adding a test to verify TDX lifecycle by creating a simple TDX VM.
Signed-off-by: Sagi Shahar <sagis@google.com>
Signed-off-by: Lisa Wang <wyihan@google.com>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../testing/selftests/kvm/include/x86/processor.h | 1 +
.../selftests/kvm/include/x86/tdx/tdx_util.h | 5 ++++
tools/testing/selftests/kvm/x86/tdx_vm_test.c | 33 ++++++++++++++++++++++
4 files changed, 40 insertions(+)
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 489324cecf83..14db8eb2bf0d 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -167,6 +167,7 @@ TEST_GEN_PROGS_x86 += rseq_test
TEST_GEN_PROGS_x86 += steal_time
TEST_GEN_PROGS_x86 += system_counter_offset_test
TEST_GEN_PROGS_x86 += pre_fault_memory_test
+TEST_GEN_PROGS_x86 += x86/tdx_vm_test
# Compiled outputs used by test targets
TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index ed9c031b77b8..f65755482a97 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -372,6 +372,7 @@ static inline unsigned int x86_model(unsigned int eax)
#define VM_SHAPE_SEV VM_TYPE(KVM_X86_SEV_VM)
#define VM_SHAPE_SEV_ES VM_TYPE(KVM_X86_SEV_ES_VM)
#define VM_SHAPE_SNP VM_TYPE(KVM_X86_SNP_VM)
+#define VM_SHAPE_TDX VM_TYPE(KVM_X86_TDX_VM)
#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12)
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 8276622c50d2..56538b1286f3 100644
--- a/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
+++ b/tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h
@@ -11,6 +11,11 @@ static inline bool is_tdx_vm(struct kvm_vm *vm)
return vm->type == KVM_X86_TDX_VM;
}
+static inline bool is_tdx_supported(void)
+{
+ return !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_TDX_VM));
+}
+
/*
* TDX ioctls
* Use underscores to avoid collisions with struct member names.
diff --git a/tools/testing/selftests/kvm/x86/tdx_vm_test.c b/tools/testing/selftests/kvm/x86/tdx_vm_test.c
new file mode 100644
index 000000000000..7cdcaf33b585
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/tdx_vm_test.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "processor.h"
+#include "kvm_util.h"
+#include "tdx/tdx_util.h"
+#include "ucall_common.h"
+#include "kselftest_harness.h"
+
+static void guest_code_lifecycle(void)
+{
+ GUEST_DONE();
+}
+
+TEST(verify_td_lifecycle)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ struct ucall uc;
+
+ vm = vm_create_shape_with_one_vcpu(VM_SHAPE_TDX, &vcpu,
+ guest_code_lifecycle);
+
+ vcpu_run(vcpu);
+ TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_DONE);
+
+ kvm_vm_free(vm);
+}
+
+int main(int argc, char **argv)
+{
+ TEST_REQUIRE(is_tdx_supported());
+ return test_harness_run(argc, argv);
+}
--
2.54.0.746.g67dd491aae-goog
^ permalink raw reply related
* [PATCH 00/15] Enable TDX Module Extensions and DICE-based TDX Quoting
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
This posting is just to collect initial review.
Sean, Paolo, Dave please feel free to ignore for now. Sean, especially
the x86 KVM stuff is only here as an example for the init code, and not
ready for review.
Kiryl and Dan, we are trying to get acks for the first 4 patches of the
series so they can be serve as a settled base for all the other work
that uses Extensions. Please review the first 4 patches and treat the
later ones as an example for the Extensions initialization.
== Why it's being posted ==
The TDX Module is introducing a new concept called "TDX Module
Extensions", and several upcoming features depend on them. The
Extensions need some extra setup at TDX module init time, and the code
to do this is expected to be somewhat generic.
We want to get the basics of this TDX module extensions piece sorted so
that all of the extension-based work can build on it. This series
includes those basics, and an example usage called DICE-based TDX
Quoting. Only the first 4 patches are about initializing the TDX module
Extensions. I'd like some review on them. The later DICE patches are
just included to serve as a usage example for the TDX module extension
code.
The first 4 patches will eventually need an ack by an x86 maintainer, so
please review with that in mind.
== Overview ==
TDX Module introduces the "TDX Module Extensions" to support long
running / hard-irq preemptible flows inside. This makes TDX Module
capable of handling complex tasks through "Extension SEAMCALLs".
TDX Module allows some add-on features to use the Extension. The first
feature to use Extensions is DICE-based TDX Quoting [1]. DICE is an
industry-standard, certificate-backed attestation framework that layers
evidence through a chain of certificates.
This series adds infrastructure to enable the Extensions and then
implement DICE-based TDX Quoting.
The Extensions consumes relatively large amount of memory (~50MB). So it
is designed to be off by default. It must be enabled after basic TDX
Module initialization and when add-on features require it. To enable
the Extensions, host first adds extra memory to TDX Module via a
SEAMCALL (TDH.EXT.MEM.ADD), then uses another SEAMCALL (TDH.EXT.INIT) to
initialize Extensions, and then some add-on features, e.g. DICE, could
use Extension SEAMCALLs for work. Note that host can never get the added
memory back.
Theoretically, the Extensions doesn't need to be enabled right after
basic TDX initialization. It could be enabled right before the first
Extension SEAMCALL is issued. That would save or postpone memory usage.
But it isn't worth the complexity, the needs for the Extensions are vast
but the savings are little for a typical TDX capable system (about
0.001% of memory). So the Linux decision is to just enable it along with
the basic TDX.
This series has 2 distinct parts:
Patches 1-4: TDX Module Extensions enabling
Patches 5-15: DICE-based TDX Quoting, primarily Peter's work.
== Some history ==
The TDX Module Extensions part was first posted along with TDX
Connect [2]. Now this part is remarkably smaller because we've removed
the generic tdx_page_array abstraction for HPA_LIST_INFO. TDX Module
Extensions is the first user of HPA_LIST_INFO, and doesn't use it in a
typical way (HPA_LIST_INFO can only hold at most 2MB memory). There
isn't enough justification to make the abstraction in this series. A
possible plan is to rebuild tdx_page_array iteratively when more use
cases arise.
== Misc ==
This series is based on tip/x86/tdx [3], because we need a small
being-merged patch [4] before our work.
Link: https://cdrdv2.intel.com/v1/dl/getContent/874303 # [1]
Link: https://lore.kernel.org/all/20260327160132.2946114-1-yilun.xu@linux.intel.com/ # [2]
Link: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/log/?h=x86/tdx # [3]
Link: https://patch.msgid.link/20260402-fuller_tdx_kexec_support-v3-1-34438d7094bf@intel.com # [4]
Peter Fang (10):
x86/virt/tdx: Move tdx_tdr_pa() up in the file
x86/virt/tdx: Initialize Quoting extension during bringup
x86/virt/tdx: Prepare Quote buffer during extension bringup
x86/virt/tdx: Add interface to check Quoting availability
x86/virt/tdx: Add interface to generate a Quote
x86/tdx: Move and rename Quote request structure
KVM: TDX: Factor out userspace return path from tdx_get_quote()
KVM: TDX: Add in-kernel Quote generation
KVM: TDX: Support event-notify interrupts only with userspace quoting
x86/virt/tdx: Enable TDX Quoting extension
Xu Yilun (5):
x86/virt/tdx: Read global metadata for TDX Module Extensions
x86/virt/tdx: Add extra memory to TDX Module for Extensions
x86/virt/tdx: Make TDX Module initialize Extensions
x86/virt/tdx: Enable the Extensions right after basic TDX Module init
x86/virt/tdx: Embed version info in SEAMCALL leaf function definitions
Documentation/virt/kvm/api.rst | 8 +-
arch/x86/include/asm/tdx.h | 34 ++
arch/x86/include/asm/tdx_global_metadata.h | 11 +
arch/x86/kvm/vmx/tdx.h | 6 +
arch/x86/virt/vmx/tdx/tdx.h | 32 +-
arch/x86/kvm/vmx/tdx.c | 176 ++++++++-
arch/x86/virt/vmx/tdx/tdx.c | 387 +++++++++++++++++++-
arch/x86/virt/vmx/tdx/tdx_global_metadata.c | 27 ++
drivers/virt/coco/tdx-guest/tdx-guest.c | 25 +-
virt/kvm/kvm_main.c | 1 +
10 files changed, 655 insertions(+), 52 deletions(-)
base-commit: 5209e5bfe5cab593476c3e7754e42c5e47ce36de
--
2.25.1
^ permalink raw reply
* [PATCH 01/15] x86/virt/tdx: Read global metadata for TDX Module Extensions
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
Add reading of the global metadata for TDX Module Extensions.
TDX Module Extensions is an add-on feature enumerated by TDX_FEATURES0.
But for the Module's integrity, Linux requires that all features that a
Module advertises must have a complete, valid set of metadata, and the
validation must succeed at core TDX initialization time.
Check TDX_FEATURES0 before reading these metadata. If a feature is
advertised, a failure in reading associated metadata causes the entire
TDX initialization to fail, otherwise skip.
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/include/asm/tdx_global_metadata.h | 6 ++++++
arch/x86/virt/vmx/tdx/tdx.h | 1 +
arch/x86/virt/vmx/tdx/tdx_global_metadata.c | 16 ++++++++++++++++
3 files changed, 23 insertions(+)
diff --git a/arch/x86/include/asm/tdx_global_metadata.h b/arch/x86/include/asm/tdx_global_metadata.h
index 40689c8dc67e..533afe50a3f1 100644
--- a/arch/x86/include/asm/tdx_global_metadata.h
+++ b/arch/x86/include/asm/tdx_global_metadata.h
@@ -40,12 +40,18 @@ struct tdx_sys_info_td_conf {
u64 cpuid_config_values[128][2];
};
+struct tdx_sys_info_ext {
+ u16 memory_pool_required_pages;
+ u8 ext_required;
+};
+
struct tdx_sys_info {
struct tdx_sys_info_version version;
struct tdx_sys_info_features features;
struct tdx_sys_info_tdmr tdmr;
struct tdx_sys_info_td_ctrl td_ctrl;
struct tdx_sys_info_td_conf td_conf;
+ struct tdx_sys_info_ext ext;
};
#endif
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index e2cf2dd48755..a5eec8e3cc71 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -87,6 +87,7 @@ struct tdmr_info {
/* Bit definitions of TDX_FEATURES0 metadata field */
#define TDX_FEATURES0_NO_RBP_MOD BIT(18)
+#define TDX_FEATURES0_EXT BIT_ULL(39)
/*
* Do not put any hardware-defined TDX structure representations below
diff --git a/arch/x86/virt/vmx/tdx/tdx_global_metadata.c b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
index c7db393a9cfb..3d3b56ef3d2f 100644
--- a/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
+++ b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
@@ -100,6 +100,19 @@ static __init int get_tdx_sys_info_td_conf(struct tdx_sys_info_td_conf *sysinfo_
return ret;
}
+static __init int get_tdx_sys_info_ext(struct tdx_sys_info_ext *sysinfo_ext)
+{
+ int ret = 0;
+ u64 val;
+
+ if (!ret && !(ret = read_sys_metadata_field(0x3100000100000000, &val)))
+ sysinfo_ext->memory_pool_required_pages = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x3100000000000001, &val)))
+ sysinfo_ext->ext_required = val;
+
+ return ret;
+}
+
static __init int get_tdx_sys_info(struct tdx_sys_info *sysinfo)
{
int ret = 0;
@@ -116,5 +129,8 @@ static __init int get_tdx_sys_info(struct tdx_sys_info *sysinfo)
ret = ret ?: get_tdx_sys_info_td_ctrl(&sysinfo->td_ctrl);
ret = ret ?: get_tdx_sys_info_td_conf(&sysinfo->td_conf);
+ if (sysinfo->features.tdx_features0 & TDX_FEATURES0_EXT)
+ ret = ret ?: get_tdx_sys_info_ext(&sysinfo->ext);
+
return ret;
}
--
2.25.1
^ permalink raw reply related
* [PATCH 02/15] x86/virt/tdx: Add extra memory to TDX Module for Extensions
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
TDX Module introduces a new concept called "TDX Module Extensions" to
support long running / hard-irq preemptible flows inside. This makes TDX
Module capable of handling complex tasks through "Extension SEAMCALLs".
Adding more memory to TDX Module is the first step to enable Extensions.
Currently, TDX Module memory use is relatively static. But, the
Extensions need to use memory more dynamically. While 'static' here
means the kernel provides necessary amount of memory to TDX Module for
its basic functionalities, 'dynamic' means extra memory is needed only
if new add-on features are to be enabled. So add a new memory feeding
process backed by a new SEAMCALL TDH.EXT.MEM.ADD.
The process is mostly the same as adding PAMT. The kernel queries TDX
Module how much memory needed, allocates it, hands it over, and never
gets it back.
TDH.EXT.MEM.ADD uses a new parameter type HPA_LIST_INFO to provide
control (private) pages to TDX Module. This type represents a list of
pages for TDX Module to access. It needs a 'root page' which contains
the list of HPAs of the pages. It collapses the HPA of the root page
and the number of valid HPAs into a 64 bit raw value for SEAMCALL
parameters. The root page is always a medium, TDX Module never keeps
the root page.
Introduce a tdx_clflush_hpa_list() helper to flush shared cache before
SEAMCALL, to avoid shared cache writeback damaging these private pages.
For now, TDX Module Extensions consumes relatively large amount of
memory (~50MB). Use contiguous page allocation to avoid permanently
fragment too much memory. Print the allocation amount on TDX Module
Extensions initialization for visibility.
Co-developed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/virt/vmx/tdx/tdx.h | 1 +
arch/x86/virt/vmx/tdx/tdx.c | 118 ++++++++++++++++++++++++++++++++++++
2 files changed, 119 insertions(+)
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index a5eec8e3cc71..2335f88bbb10 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -46,6 +46,7 @@
#define TDH_PHYMEM_PAGE_WBINVD 41
#define TDH_VP_WR 43
#define TDH_SYS_CONFIG 45
+#define TDH_EXT_MEM_ADD 61
#define TDH_SYS_DISABLE 69
/*
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index c0c6281b08a5..622399d8da68 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -31,6 +31,7 @@
#include <linux/syscore_ops.h>
#include <linux/idr.h>
#include <linux/kvm_types.h>
+#include <linux/bitfield.h>
#include <asm/page.h>
#include <asm/special_insns.h>
#include <asm/msr-index.h>
@@ -1179,6 +1180,123 @@ static __init int init_tdmrs(struct tdmr_info_list *tdmr_list)
return 0;
}
+static void tdx_clflush_hpa_list(struct page *root, unsigned int nr_pages)
+{
+ u64 *entries = page_to_virt(root);
+ int i;
+
+ for (i = 0; i < nr_pages; i++)
+ clflush_cache_range(__va(entries[i]), PAGE_SIZE);
+}
+
+#define HPA_LIST_INFO_FIRST_ENTRY GENMASK_U64(11, 3)
+#define HPA_LIST_INFO_PFN GENMASK_U64(51, 12)
+#define HPA_LIST_INFO_LAST_ENTRY GENMASK_U64(63, 55)
+
+static u64 to_hpa_list_info(struct page *root, unsigned int nr_pages)
+{
+ return FIELD_PREP(HPA_LIST_INFO_FIRST_ENTRY, 0) |
+ FIELD_PREP(HPA_LIST_INFO_PFN, page_to_pfn(root)) |
+ FIELD_PREP(HPA_LIST_INFO_LAST_ENTRY, nr_pages - 1);
+}
+
+static int tdx_ext_mem_add(struct page *root, unsigned int nr_pages)
+{
+ struct tdx_module_args args = {
+ .rcx = to_hpa_list_info(root, nr_pages),
+ };
+ u64 r;
+
+ tdx_clflush_hpa_list(root, nr_pages);
+
+ do {
+ /*
+ * TDH_EXT_MEM_ADD is designed to use output parameter RCX to
+ * override/update input parameter RCX, so the caller doesn't
+ * have to do manual parameter update on retry call.
+ */
+ r = seamcall_ret(TDH_EXT_MEM_ADD, &args);
+ } while (r == TDX_INTERRUPTED_RESUMABLE);
+
+ if (r != TDX_SUCCESS)
+ return -EFAULT;
+
+ return 0;
+}
+
+static int tdx_ext_mem_setup(void)
+{
+ unsigned int nr_pages;
+ struct page *page;
+ u64 *root;
+ unsigned int i;
+ int ret;
+
+ nr_pages = tdx_sysinfo.ext.memory_pool_required_pages;
+ /*
+ * memory_pool_required_pages == 0 means no need to add pages,
+ * skip the memory setup.
+ */
+ if (!nr_pages)
+ return 0;
+
+ root = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!root)
+ return -ENOMEM;
+
+ page = alloc_contig_pages(nr_pages, GFP_KERNEL, numa_mem_id(),
+ &node_online_map);
+ if (!page) {
+ ret = -ENOMEM;
+ goto out_free_root;
+ }
+
+ for (i = 0; i < nr_pages;) {
+ unsigned int nents = min(nr_pages - i,
+ PAGE_SIZE / sizeof(*root));
+ int j;
+
+ for (j = 0; j < nents; j++)
+ root[j] = page_to_phys(page + i + j);
+
+ ret = tdx_ext_mem_add(virt_to_page(root), nents);
+ /*
+ * No SEAMCALLs to reclaim the added pages. For simple error
+ * handling, leak all pages.
+ */
+ WARN_ON_ONCE(ret);
+ if (ret)
+ break;
+
+ i += nents;
+ }
+
+ /*
+ * Extensions memory can't be reclaimed once added, print out the
+ * amount, stop tracking it and free the root page, no matter success
+ * or failure.
+ */
+ pr_info("%lu KB allocated for TDX Module Extensions\n",
+ nr_pages * PAGE_SIZE / 1024);
+
+out_free_root:
+ kfree(root);
+
+ return ret;
+}
+
+static int __maybe_unused init_tdx_ext(void)
+{
+ if (!(tdx_sysinfo.features.tdx_features0 & TDX_FEATURES0_EXT))
+ return 0;
+
+ /* No feature requires TDX Module Extensions. */
+ if (!tdx_sysinfo.ext.ext_required)
+ return 0;
+
+ return tdx_ext_mem_setup();
+}
+
static __init int init_tdx_module(void)
{
int ret;
--
2.25.1
^ permalink raw reply related
* [PATCH 03/15] x86/virt/tdx: Make TDX Module initialize Extensions
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
After providing all required memory to TDX Module, initialize TDX
Module Extensions via TDH.EXT.INIT, so Extension-SEAMCALLs can be used.
Co-developed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/virt/vmx/tdx/tdx.h | 1 +
arch/x86/virt/vmx/tdx/tdx.c | 24 +++++++++++++++++++++++-
2 files changed, 24 insertions(+), 1 deletion(-)
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index 2335f88bbb10..c5bffd118145 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -46,6 +46,7 @@
#define TDH_PHYMEM_PAGE_WBINVD 41
#define TDH_VP_WR 43
#define TDH_SYS_CONFIG 45
+#define TDH_EXT_INIT 60
#define TDH_EXT_MEM_ADD 61
#define TDH_SYS_DISABLE 69
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 622399d8da68..ff2b96c20d2b 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1200,6 +1200,22 @@ static u64 to_hpa_list_info(struct page *root, unsigned int nr_pages)
FIELD_PREP(HPA_LIST_INFO_LAST_ENTRY, nr_pages - 1);
}
+/* Initialize the TDX Module Extensions then Extension-SEAMCALLs can be used */
+static int tdx_ext_init(void)
+{
+ struct tdx_module_args args = {};
+ u64 r;
+
+ do {
+ r = seamcall(TDH_EXT_INIT, &args);
+ } while (r == TDX_INTERRUPTED_RESUMABLE);
+
+ if (r != TDX_SUCCESS)
+ return -EFAULT;
+
+ return 0;
+}
+
static int tdx_ext_mem_add(struct page *root, unsigned int nr_pages)
{
struct tdx_module_args args = {
@@ -1287,6 +1303,8 @@ static int tdx_ext_mem_setup(void)
static int __maybe_unused init_tdx_ext(void)
{
+ int ret;
+
if (!(tdx_sysinfo.features.tdx_features0 & TDX_FEATURES0_EXT))
return 0;
@@ -1294,7 +1312,11 @@ static int __maybe_unused init_tdx_ext(void)
if (!tdx_sysinfo.ext.ext_required)
return 0;
- return tdx_ext_mem_setup();
+ ret = tdx_ext_mem_setup();
+ if (ret)
+ return ret;
+
+ return tdx_ext_init();
}
static __init int init_tdx_module(void)
--
2.25.1
^ permalink raw reply related
* [PATCH 04/15] x86/virt/tdx: Enable the Extensions right after basic TDX Module init
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
The detailed initialization flow for TDX Module Extensions has been
fully implemented. Enable the flow after basic TDX Module
initialization.
Theoretically, the Extensions doesn't need to be enabled right after
basic TDX initialization. It could be enabled right before the first
Extension SEAMCALL is issued. That would save or postpone memory usage.
But it isn't worth the complexity, the needs for the Extensions are vast
but the savings are little for a typical TDX capable system (about
0.001% of memory). So the Linux decision is to just enable it along with
the basic TDX.
Note that the Extensions initialization flow will still not start if no
add-on features require Extensions. The enabling of add-on features will
be in later patches. Until then, the system hasn't consumed extra memory.
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/virt/vmx/tdx/tdx.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index ff2b96c20d2b..dad5ec642723 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1180,7 +1180,7 @@ static __init int init_tdmrs(struct tdmr_info_list *tdmr_list)
return 0;
}
-static void tdx_clflush_hpa_list(struct page *root, unsigned int nr_pages)
+static __init void tdx_clflush_hpa_list(struct page *root, unsigned int nr_pages)
{
u64 *entries = page_to_virt(root);
int i;
@@ -1193,7 +1193,7 @@ static void tdx_clflush_hpa_list(struct page *root, unsigned int nr_pages)
#define HPA_LIST_INFO_PFN GENMASK_U64(51, 12)
#define HPA_LIST_INFO_LAST_ENTRY GENMASK_U64(63, 55)
-static u64 to_hpa_list_info(struct page *root, unsigned int nr_pages)
+static __init u64 to_hpa_list_info(struct page *root, unsigned int nr_pages)
{
return FIELD_PREP(HPA_LIST_INFO_FIRST_ENTRY, 0) |
FIELD_PREP(HPA_LIST_INFO_PFN, page_to_pfn(root)) |
@@ -1201,7 +1201,7 @@ static u64 to_hpa_list_info(struct page *root, unsigned int nr_pages)
}
/* Initialize the TDX Module Extensions then Extension-SEAMCALLs can be used */
-static int tdx_ext_init(void)
+static __init int tdx_ext_init(void)
{
struct tdx_module_args args = {};
u64 r;
@@ -1216,7 +1216,7 @@ static int tdx_ext_init(void)
return 0;
}
-static int tdx_ext_mem_add(struct page *root, unsigned int nr_pages)
+static __init int tdx_ext_mem_add(struct page *root, unsigned int nr_pages)
{
struct tdx_module_args args = {
.rcx = to_hpa_list_info(root, nr_pages),
@@ -1240,7 +1240,7 @@ static int tdx_ext_mem_add(struct page *root, unsigned int nr_pages)
return 0;
}
-static int tdx_ext_mem_setup(void)
+static __init int tdx_ext_mem_setup(void)
{
unsigned int nr_pages;
struct page *page;
@@ -1301,7 +1301,7 @@ static int tdx_ext_mem_setup(void)
return ret;
}
-static int __maybe_unused init_tdx_ext(void)
+static __init int init_tdx_ext(void)
{
int ret;
@@ -1373,6 +1373,10 @@ static __init int init_tdx_module(void)
if (ret)
goto err_reset_pamts;
+ ret = init_tdx_ext();
+ if (ret)
+ goto err_reset_pamts;
+
pr_info("%lu KB allocated for PAMT\n", tdmrs_count_pamt_kb(&tdx_tdmr_list));
out_put_tdxmem:
--
2.25.1
^ permalink raw reply related
* [RFC PATCH 05/15] x86/virt/tdx: Move tdx_tdr_pa() up in the file
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
From: Peter Fang <peter.fang@intel.com>
Move the tdx_tdr_pa() in preparation for upcoming changes to use them
during TDX bringup.
No functional change intended.
Signed-off-by: Peter Fang <peter.fang@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/virt/vmx/tdx/tdx.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index dad5ec642723..67758adefb4a 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1200,6 +1200,11 @@ static __init u64 to_hpa_list_info(struct page *root, unsigned int nr_pages)
FIELD_PREP(HPA_LIST_INFO_LAST_ENTRY, nr_pages - 1);
}
+static inline u64 tdx_tdr_pa(struct tdx_td *td)
+{
+ return page_to_phys(td->tdr_page);
+}
+
/* Initialize the TDX Module Extensions then Extension-SEAMCALLs can be used */
static __init int tdx_ext_init(void)
{
@@ -1725,11 +1730,6 @@ void tdx_guest_keyid_free(unsigned int keyid)
}
EXPORT_SYMBOL_FOR_KVM(tdx_guest_keyid_free);
-static inline u64 tdx_tdr_pa(struct tdx_td *td)
-{
- return page_to_phys(td->tdr_page);
-}
-
/*
* The TDX module exposes a CLFLUSH_BEFORE_ALLOC bit to specify whether
* a CLFLUSH of pages is required before handing them to the TDX module.
--
2.25.1
^ permalink raw reply related
* [RFC PATCH 06/15] x86/virt/tdx: Initialize Quoting extension during bringup
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
From: Peter Fang <peter.fang@intel.com>
Initialize the Quoting extension and fetch its metadata during TDX
bringup.
Because Quoting is an optional TDX feature, do not let its
initialization failures cause TDX bringup to fail.
This patch does not include the opt-in portion of the initialization.
It mainly lays the groundwork for TDX Quoting support. Opt-in will be
added in a follow-up patch once the feature can be properly used by the
system.
Signed-off-by: Peter Fang <peter.fang@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/include/asm/tdx_global_metadata.h | 5 ++++
arch/x86/virt/vmx/tdx/tdx.h | 1 +
arch/x86/virt/vmx/tdx/tdx.c | 29 ++++++++++++++++++++-
arch/x86/virt/vmx/tdx/tdx_global_metadata.c | 11 ++++++++
4 files changed, 45 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/tdx_global_metadata.h b/arch/x86/include/asm/tdx_global_metadata.h
index 533afe50a3f1..04f515cd4c1d 100644
--- a/arch/x86/include/asm/tdx_global_metadata.h
+++ b/arch/x86/include/asm/tdx_global_metadata.h
@@ -45,6 +45,10 @@ struct tdx_sys_info_ext {
u8 ext_required;
};
+struct tdx_sys_info_quote {
+ u32 max_quote_size;
+};
+
struct tdx_sys_info {
struct tdx_sys_info_version version;
struct tdx_sys_info_features features;
@@ -52,6 +56,7 @@ struct tdx_sys_info {
struct tdx_sys_info_td_ctrl td_ctrl;
struct tdx_sys_info_td_conf td_conf;
struct tdx_sys_info_ext ext;
+ struct tdx_sys_info_quote quote;
};
#endif
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index c5bffd118145..3849f4f9cc78 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -49,6 +49,7 @@
#define TDH_EXT_INIT 60
#define TDH_EXT_MEM_ADD 61
#define TDH_SYS_DISABLE 69
+#define TDH_QUOTE_INIT 100
/*
* SEAMCALL leaf:
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 67758adefb4a..fb84fb6d952b 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1205,6 +1205,22 @@ static inline u64 tdx_tdr_pa(struct tdx_td *td)
return page_to_phys(td->tdr_page);
}
+static void tdx_quote_init(void)
+{
+ struct tdx_module_args args = {};
+ u64 r;
+
+ do {
+ r = seamcall(TDH_QUOTE_INIT, &args);
+ } while (r == TDX_INTERRUPTED_RESUMABLE);
+
+ if (r)
+ return;
+
+ /* Quoting metadata is valid only after initialization */
+ get_tdx_sys_info_quote(&tdx_sysinfo.quote);
+}
+
/* Initialize the TDX Module Extensions then Extension-SEAMCALLs can be used */
static __init int tdx_ext_init(void)
{
@@ -1306,6 +1322,13 @@ static __init int tdx_ext_mem_setup(void)
return ret;
}
+static int init_tdx_ext_features(void)
+{
+ tdx_quote_init();
+
+ return 0;
+}
+
static __init int init_tdx_ext(void)
{
int ret;
@@ -1321,7 +1344,11 @@ static __init int init_tdx_ext(void)
if (ret)
return ret;
- return tdx_ext_init();
+ ret = tdx_ext_init();
+ if (ret)
+ return ret;
+
+ return init_tdx_ext_features();
}
static __init int init_tdx_module(void)
diff --git a/arch/x86/virt/vmx/tdx/tdx_global_metadata.c b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
index 3d3b56ef3d2f..f9cc2dd02caf 100644
--- a/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
+++ b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
@@ -113,6 +113,17 @@ static __init int get_tdx_sys_info_ext(struct tdx_sys_info_ext *sysinfo_ext)
return ret;
}
+static int get_tdx_sys_info_quote(struct tdx_sys_info_quote *sysinfo_quote)
+{
+ int ret = 0;
+ u64 val;
+
+ if (!ret && !(ret = read_sys_metadata_field(0x2300000200000002, &val)))
+ sysinfo_quote->max_quote_size = val;
+
+ return ret;
+}
+
static __init int get_tdx_sys_info(struct tdx_sys_info *sysinfo)
{
int ret = 0;
--
2.25.1
^ permalink raw reply related
* [RFC PATCH 07/15] x86/virt/tdx: Prepare Quote buffer during extension bringup
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
From: Peter Fang <peter.fang@intel.com>
The host uses a Quote buffer to communicate with the TDX module when
generating Quotes. Because the Quote buffer is shared with TDX guests,
prepare the required metadata during Quoting extension bringup.
This mostly involves determining the physical addresses of the Quote
buffer pages and arranging them in the HPA_LINKED_LIST format defined by
the Intel TDX Module ABI specification.
Signed-off-by: Peter Fang <peter.fang@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/virt/vmx/tdx/tdx.c | 85 ++++++++++++++++++++++++++++++++++++-
1 file changed, 84 insertions(+), 1 deletion(-)
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index fb84fb6d952b..9d04293394d7 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -32,6 +32,7 @@
#include <linux/idr.h>
#include <linux/kvm_types.h>
#include <linux/bitfield.h>
+#include <linux/vmalloc.h>
#include <asm/page.h>
#include <asm/special_insns.h>
#include <asm/msr-index.h>
@@ -61,6 +62,13 @@ static LIST_HEAD(tdx_memlist);
static struct tdx_sys_info tdx_sysinfo __ro_after_init;
static bool tdx_module_initialized __ro_after_init;
+static struct quote_data {
+ void *buf;
+ u64 buf_len;
+ u64 *hpa_list;
+ phys_addr_t hpa_list_pa;
+} quote_data;
+
typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args);
static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args)
@@ -1205,9 +1213,78 @@ static inline u64 tdx_tdr_pa(struct tdx_td *td)
return page_to_phys(td->tdr_page);
}
+#define HPAS_PER_PAGE (PAGE_SIZE / sizeof(u64))
+
+static int tdx_quote_create_buf(unsigned int nr_pages, struct quote_data *qdata)
+{
+ unsigned long pfn;
+ u64 qlist_npages;
+ int err, i, j;
+ u64 *qlist;
+ void *qbuf;
+
+ if (!nr_pages)
+ return -EINVAL;
+
+ /* The last entry of a linked list page points to the next page */
+ qlist_npages = (u64)DIV_ROUND_UP(nr_pages, HPAS_PER_PAGE - 1);
+
+ qlist = vmalloc_array(qlist_npages, PAGE_SIZE);
+ if (!qlist) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+
+ /*
+ * Make sure unfilled entries are always -1, which means NULL in TDX.
+ * Only the last page needs to be filled. All the other pages will be
+ * fully populated.
+ */
+ memset((u8 *)qlist + (qlist_npages - 1) * PAGE_SIZE, 0xff, PAGE_SIZE);
+
+ qbuf = vcalloc(nr_pages, PAGE_SIZE);
+ if (!qbuf) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+
+ /* Populate HPA_LINKED_LIST as per TDX ABI spec */
+ for (i = 0, j = 0; j < nr_pages; i++) {
+ if ((i % HPAS_PER_PAGE) == HPAS_PER_PAGE - 1) {
+ /*
+ * The last entry always points to the next page. The
+ * address of the following entry must be on next page's
+ * boundary.
+ */
+ pfn = vmalloc_to_pfn(&qlist[i + 1]);
+ qlist[i] = PFN_PHYS(pfn);
+ continue;
+ }
+
+ pfn = vmalloc_to_pfn((u8 *)qbuf + j * PAGE_SIZE);
+ qlist[i] = PFN_PHYS(pfn);
+ j++;
+ }
+
+ qdata->buf = qbuf;
+ qdata->buf_len = (u64)nr_pages * PAGE_SIZE;
+ qdata->hpa_list = qlist;
+
+ pfn = vmalloc_to_pfn(qlist);
+ qdata->hpa_list_pa = PFN_PHYS(pfn);
+
+ return 0;
+
+out_err:
+ vfree(qlist);
+
+ return err;
+}
+
static void tdx_quote_init(void)
{
struct tdx_module_args args = {};
+ unsigned int nr_quote_pages;
u64 r;
do {
@@ -1218,7 +1295,13 @@ static void tdx_quote_init(void)
return;
/* Quoting metadata is valid only after initialization */
- get_tdx_sys_info_quote(&tdx_sysinfo.quote);
+ if (get_tdx_sys_info_quote(&tdx_sysinfo.quote))
+ return;
+
+ nr_quote_pages = PAGE_ALIGN(tdx_sysinfo.quote.max_quote_size) /
+ PAGE_SIZE;
+ if (tdx_quote_create_buf(nr_quote_pages, "e_data))
+ pr_err("Failed to create quote buffer\n");
}
/* Initialize the TDX Module Extensions then Extension-SEAMCALLs can be used */
--
2.25.1
^ permalink raw reply related
* [RFC PATCH 08/15] x86/virt/tdx: Add interface to check Quoting availability
From: Xu Yilun @ 2026-05-22 3:41 UTC (permalink / raw)
To: kas, djbw, rick.p.edgecombe, x86, peter.fang
Cc: linux-coco, linux-kernel, kvm, sohil.mehta, yilun.xu, yilun.xu,
baolu.lu, zhenzhong.duan, xiaoyao.li
In-Reply-To: <20260522034128.3144354-1-yilun.xu@linux.intel.com>
From: Peter Fang <peter.fang@intel.com>
KVM needs to know if the Quoting extension is available to determine
whether userspace must be involved in Quote generation.
Since the Quote buffer is always created during Quoting extension
bringup, checking whether the buffer exists is sufficient.
Signed-off-by: Peter Fang <peter.fang@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
---
arch/x86/include/asm/tdx.h | 2 ++
arch/x86/virt/vmx/tdx/tdx.c | 15 +++++++++++++++
2 files changed, 17 insertions(+)
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 15eac89b0afb..7b257088aa1e 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -176,6 +176,8 @@ struct tdx_vp {
struct page **tdcx_pages;
};
+bool tdx_quote_enabled(void);
+
static inline u64 mk_keyed_paddr(u16 hkid, struct page *page)
{
u64 ret;
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 9d04293394d7..b305fa5aab5c 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1213,6 +1213,21 @@ static inline u64 tdx_tdr_pa(struct tdx_td *td)
return page_to_phys(td->tdr_page);
}
+/**
+ * tdx_quote_enabled() - Check whether TDX Quoting extension is available
+ *
+ * Return: %true if the Quoting extension is available, otherwise %false.
+ */
+bool tdx_quote_enabled(void)
+{
+ /*
+ * No need for locking here. The quote buffer is initialized as part of
+ * core TDX bringup, which comes before KVM is ready for userspace.
+ */
+ return !!quote_data.buf;
+}
+EXPORT_SYMBOL_FOR_KVM(tdx_quote_enabled);
+
#define HPAS_PER_PAGE (PAGE_SIZE / sizeof(u64))
static int tdx_quote_create_buf(unsigned int nr_pages, struct quote_data *qdata)
--
2.25.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox