qemu-kvm/kvm-i386-tdx-Initialize-TDX-before-creating-TD-vcpus.patch

From 7f2aa231529a03552d642eccae4c4cc209a3ccdb Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 18 Jul 2025 18:03:46 +0200
Subject: [PATCH 037/115] i386/tdx: Initialize TDX before creating TD vcpus

RH-Author: Paolo Bonzini <pbonzini@redhat.com>
RH-MergeRequest: 391: TDX support, including attestation and device assignment
RH-Jira: RHEL-15710 RHEL-20798 RHEL-49728
RH-Acked-by: Yash Mankad <None>
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Commit: [37/115] 1626ea547590c6f25d7d51b66a23820a701398af (bonzini/rhel-qemu-kvm)

Invoke KVM_TDX_INIT_VM in kvm_arch_pre_create_vcpu() that
KVM_TDX_INIT_VM configures global TD configurations, e.g. the canonical
CPUID config, and must be executed prior to creating vCPUs.

Use kvm_x86_arch_cpuid() to setup the CPUID settings for TDX VM.

Note, this doesn't address the fact that QEMU may change the CPUID
configuration when creating vCPUs, i.e. punts on refactoring QEMU to
provide a stable CPUID config prior to kvm_arch_init().

Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Link: https://lore.kernel.org/r/20250508150002.689633-9-xiaoyao.li@intel.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit f15898b0f50609d66465326221aa54b6699da674)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/kvm/kvm.c       |  16 +++---
 target/i386/kvm/kvm_i386.h  |   5 ++
 target/i386/kvm/meson.build |   2 +-
 target/i386/kvm/tdx-stub.c  |  10 ++++
 target/i386/kvm/tdx.c       | 105 ++++++++++++++++++++++++++++++++++++
 target/i386/kvm/tdx.h       |   6 +++
 6 files changed, 137 insertions(+), 7 deletions(-)
 create mode 100644 target/i386/kvm/tdx-stub.c

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 1fddec6b9c..3b71c182ab 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -38,6 +38,7 @@
 #include "kvm_i386.h"
 #include "../confidential-guest.h"
 #include "sev.h"
+#include "tdx.h"
 #include "xen-emu.h"
 #include "hyperv.h"
 #include "hyperv-proto.h"
@@ -406,9 +407,9 @@ static uint32_t cpuid_entry_get_reg(struct kvm_cpuid_entry2 *entry, int reg)
 
 /* Find matching entry for function/index on kvm_cpuid2 struct
  */
-static struct kvm_cpuid_entry2 *cpuid_find_entry(struct kvm_cpuid2 *cpuid,
-                                                 uint32_t function,
-                                                 uint32_t index)
+struct kvm_cpuid_entry2 *cpuid_find_entry(struct kvm_cpuid2 *cpuid,
+                                          uint32_t function,
+                                          uint32_t index)
 {
     int i;
     for (i = 0; i < cpuid->nent; ++i) {
@@ -1813,9 +1814,8 @@ static void kvm_init_nested_state(CPUX86State *env)
     }
 }
 
-static uint32_t kvm_x86_build_cpuid(CPUX86State *env,
-                                    struct kvm_cpuid_entry2 *entries,
-                                    uint32_t cpuid_i)
+uint32_t kvm_x86_build_cpuid(CPUX86State *env, struct kvm_cpuid_entry2 *entries,
+                             uint32_t cpuid_i)
 {
     uint32_t limit, i, j;
     uint32_t unused;
@@ -2041,6 +2041,10 @@ full:
 
 int kvm_arch_pre_create_vcpu(CPUState *cpu, Error **errp)
 {
+    if (is_tdx_vm()) {
+        return tdx_pre_create_vcpu(cpu, errp);
+    }
+
     return 0;
 }
 
diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h
index 499691e8d0..f2fbf3f99f 100644
--- a/target/i386/kvm/kvm_i386.h
+++ b/target/i386/kvm/kvm_i386.h
@@ -59,6 +59,11 @@ uint64_t kvm_swizzle_msi_ext_dest_id(uint64_t address);
 void kvm_update_msi_routes_all(void *private, bool global,
                                uint32_t index, uint32_t mask);
 
+struct kvm_cpuid_entry2 *cpuid_find_entry(struct kvm_cpuid2 *cpuid,
+                                          uint32_t function,
+                                          uint32_t index);
+uint32_t kvm_x86_build_cpuid(CPUX86State *env, struct kvm_cpuid_entry2 *entries,
+                             uint32_t cpuid_i);
 #endif /* CONFIG_KVM */
 
 void kvm_pc_setup_irq_routing(bool pci_enabled);
diff --git a/target/i386/kvm/meson.build b/target/i386/kvm/meson.build
index 466bccb9cb..3f44cdedb7 100644
--- a/target/i386/kvm/meson.build
+++ b/target/i386/kvm/meson.build
@@ -8,7 +8,7 @@ i386_kvm_ss.add(files(
 
 i386_kvm_ss.add(when: 'CONFIG_XEN_EMU', if_true: files('xen-emu.c'))
 
-i386_kvm_ss.add(when: 'CONFIG_TDX', if_true: files('tdx.c'))
+i386_kvm_ss.add(when: 'CONFIG_TDX', if_true: files('tdx.c'), if_false: files('tdx-stub.c'))
 
 i386_system_ss.add(when: 'CONFIG_HYPERV', if_true: files('hyperv.c'), if_false: files('hyperv-stub.c'))
 
diff --git a/target/i386/kvm/tdx-stub.c b/target/i386/kvm/tdx-stub.c
new file mode 100644
index 0000000000..2344433594
--- /dev/null
+++ b/target/i386/kvm/tdx-stub.c
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include "qemu/osdep.h"
+
+#include "tdx.h"
+
+int tdx_pre_create_vcpu(CPUState *cpu, Error **errp)
+{
+    return -EINVAL;
+}
diff --git a/target/i386/kvm/tdx.c b/target/i386/kvm/tdx.c
index 16f67e18ae..8f02c76249 100644
--- a/target/i386/kvm/tdx.c
+++ b/target/i386/kvm/tdx.c
@@ -149,6 +149,109 @@ static int tdx_kvm_type(X86ConfidentialGuest *cg)
     return KVM_X86_TDX_VM;
 }
 
+static int setup_td_xfam(X86CPU *x86cpu, Error **errp)
+{
+    CPUX86State *env = &x86cpu->env;
+    uint64_t xfam;
+
+    xfam = env->features[FEAT_XSAVE_XCR0_LO] |
+           env->features[FEAT_XSAVE_XCR0_HI] |
+           env->features[FEAT_XSAVE_XSS_LO] |
+           env->features[FEAT_XSAVE_XSS_HI];
+
+    if (xfam & ~tdx_caps->supported_xfam) {
+        error_setg(errp, "Invalid XFAM 0x%lx for TDX VM (supported: 0x%llx))",
+                   xfam, tdx_caps->supported_xfam);
+        return -1;
+    }
+
+    tdx_guest->xfam = xfam;
+    return 0;
+}
+
+static void tdx_filter_cpuid(struct kvm_cpuid2 *cpuids)
+{
+    int i, dest_cnt = 0;
+    struct kvm_cpuid_entry2 *src, *dest, *conf;
+
+    for (i = 0; i < cpuids->nent; i++) {
+        src = cpuids->entries + i;
+        conf = cpuid_find_entry(&tdx_caps->cpuid, src->function, src->index);
+        if (!conf) {
+            continue;
+        }
+        dest = cpuids->entries + dest_cnt;
+
+        dest->function = src->function;
+        dest->index = src->index;
+        dest->flags = src->flags;
+        dest->eax = src->eax & conf->eax;
+        dest->ebx = src->ebx & conf->ebx;
+        dest->ecx = src->ecx & conf->ecx;
+        dest->edx = src->edx & conf->edx;
+
+        dest_cnt++;
+    }
+    cpuids->nent = dest_cnt++;
+}
+
+int tdx_pre_create_vcpu(CPUState *cpu, Error **errp)
+{
+    X86CPU *x86cpu = X86_CPU(cpu);
+    CPUX86State *env = &x86cpu->env;
+    g_autofree struct kvm_tdx_init_vm *init_vm = NULL;
+    Error *local_err = NULL;
+    int retry = 10000;
+    int r = 0;
+
+    QEMU_LOCK_GUARD(&tdx_guest->lock);
+    if (tdx_guest->initialized) {
+        return r;
+    }
+
+    init_vm = g_malloc0(sizeof(struct kvm_tdx_init_vm) +
+                        sizeof(struct kvm_cpuid_entry2) * KVM_MAX_CPUID_ENTRIES);
+
+    r = setup_td_xfam(x86cpu, errp);
+    if (r) {
+        return r;
+    }
+
+    init_vm->cpuid.nent = kvm_x86_build_cpuid(env, init_vm->cpuid.entries, 0);
+    tdx_filter_cpuid(&init_vm->cpuid);
+
+    init_vm->attributes = tdx_guest->attributes;
+    init_vm->xfam = tdx_guest->xfam;
+
+    /*
+     * KVM_TDX_INIT_VM gets -EAGAIN when KVM side SEAMCALL(TDH_MNG_CREATE)
+     * gets TDX_RND_NO_ENTROPY due to Random number generation (e.g., RDRAND or
+     * RDSEED) is busy.
+     *
+     * Retry for the case.
+     */
+    do {
+        error_free(local_err);
+        local_err = NULL;
+        r = tdx_vm_ioctl(KVM_TDX_INIT_VM, 0, init_vm, &local_err);
+    } while (r == -EAGAIN && --retry);
+
+    if (r < 0) {
+        if (!retry) {
+            error_append_hint(&local_err, "Hardware RNG (Random Number "
+            "Generator) is busy occupied by someone (via RDRAND/RDSEED) "
+            "maliciously, which leads to KVM_TDX_INIT_VM keeping failure "
+            "due to lack of entropy.\n");
+        }
+        error_propagate(errp, local_err);
+        return r;
+    }
+
+    tdx_guest->initialized = true;
+
+    return 0;
+}
+
 /* tdx guest */
 OBJECT_DEFINE_TYPE_WITH_INTERFACES(TdxGuest,
                                    tdx_guest,
@@ -162,6 +265,8 @@ static void tdx_guest_init(Object *obj)
     ConfidentialGuestSupport *cgs = CONFIDENTIAL_GUEST_SUPPORT(obj);
     TdxGuest *tdx = TDX_GUEST(obj);
 
+    qemu_mutex_init(&tdx->lock);
+
     cgs->require_guest_memfd = true;
     tdx->attributes = 0;
 
diff --git a/target/i386/kvm/tdx.h b/target/i386/kvm/tdx.h
index de8ae91961..4e2b5c61ff 100644
--- a/target/i386/kvm/tdx.h
+++ b/target/i386/kvm/tdx.h
@@ -19,7 +19,11 @@ typedef struct TdxGuestClass {
 typedef struct TdxGuest {
     X86ConfidentialGuest parent_obj;
 
+    QemuMutex lock;
+
+    bool initialized;
     uint64_t attributes;    /* TD attributes */
+    uint64_t xfam;
 } TdxGuest;
 
 #ifdef CONFIG_TDX
@@ -28,4 +32,6 @@ bool is_tdx_vm(void);
 #define is_tdx_vm() 0
 #endif /* CONFIG_TDX */
 
+int tdx_pre_create_vcpu(CPUState *cpu, Error **errp);
+
 #endif /* QEMU_I386_TDX_H */
-- 
2.50.1