rpms/qemu-kvm
7
0
Fork 0
Code Issues Pull Requests Releases Activity
c9-beta
qemu-kvm/SOURCES/kvm-i386-kvm-Move-architectural-CPUID-leaf-generation-to.patch

537 lines
18 KiB
Diff
Raw Permalink Blame History

From 5ead79f45e8e90b7a04586c89e70cb9d0b66b730 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Thu, 29 Feb 2024 01:36:43 -0500
Subject: [PATCH 004/100] i386/kvm: Move architectural CPUID leaf generation to
separate helper
RH-Author: Paolo Bonzini <pbonzini@redhat.com>
RH-MergeRequest: 245: SEV-SNP support
RH-Jira: RHEL-39544
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Bandan Das <bdas@redhat.com>
RH-Acked-by: Vitaly Kuznetsov <vkuznets@redhat.com>
RH-Commit: [4/91] 06ecdbcf05ad3d658273980b114f02477d0b0475 (bonzini/rhel-qemu-kvm)
Move the architectural (for lack of a better term) CPUID leaf generation
to a separate helper so that the generation code can be reused by TDX,
which needs to generate a canonical VM-scoped configuration.
For now this is just a cleanup, so keep the function static.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Message-ID: <20240229063726.610065-23-xiaoyao.li@intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit a5acf4f26c208a05d05ef1bde65553ce2ab5e5d0)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
target/i386/kvm/kvm.c | 417 +++++++++++++++++++++---------------------
1 file changed, 211 insertions(+), 206 deletions(-)
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 739f33db47..5f30b649a0 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -1706,195 +1706,22 @@ static void kvm_init_nested_state(CPUX86State *env)
}
}
-int kvm_arch_init_vcpu(CPUState *cs)
+static uint32_t kvm_x86_build_cpuid(CPUX86State *env,
+ struct kvm_cpuid_entry2 *entries,
+ uint32_t cpuid_i)
{
- struct {
- struct kvm_cpuid2 cpuid;
- struct kvm_cpuid_entry2 entries[KVM_MAX_CPUID_ENTRIES];
- } cpuid_data;
- /*
- * The kernel defines these structs with padding fields so there
- * should be no extra padding in our cpuid_data struct.
- */
- QEMU_BUILD_BUG_ON(sizeof(cpuid_data) !=
- sizeof(struct kvm_cpuid2) +
- sizeof(struct kvm_cpuid_entry2) * KVM_MAX_CPUID_ENTRIES);
-
- X86CPU *cpu = X86_CPU(cs);
- CPUX86State *env = &cpu->env;
- uint32_t limit, i, j, cpuid_i;
+ uint32_t limit, i, j;
uint32_t unused;
struct kvm_cpuid_entry2 *c;
- uint32_t signature[3];
- int kvm_base = KVM_CPUID_SIGNATURE;
- int max_nested_state_len;
- int r;
- Error *local_err = NULL;
-
- memset(&cpuid_data, 0, sizeof(cpuid_data));
-
- cpuid_i = 0;
-
- has_xsave2 = kvm_check_extension(cs->kvm_state, KVM_CAP_XSAVE2);
-
- r = kvm_arch_set_tsc_khz(cs);
- if (r < 0) {
- return r;
- }
-
- /* vcpu's TSC frequency is either specified by user, or following
- * the value used by KVM if the former is not present. In the
- * latter case, we query it from KVM and record in env->tsc_khz,
- * so that vcpu's TSC frequency can be migrated later via this field.
- */
- if (!env->tsc_khz) {
- r = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ?
- kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) :
- -ENOTSUP;
- if (r > 0) {
- env->tsc_khz = r;
- }
- }
-
- env->apic_bus_freq = KVM_APIC_BUS_FREQUENCY;
-
- /*
- * kvm_hyperv_expand_features() is called here for the second time in case
- * KVM_CAP_SYS_HYPERV_CPUID is not supported. While we can't possibly handle
- * 'query-cpu-model-expansion' in this case as we don't have a KVM vCPU to
- * check which Hyper-V enlightenments are supported and which are not, we
- * can still proceed and check/expand Hyper-V enlightenments here so legacy
- * behavior is preserved.
- */
- if (!kvm_hyperv_expand_features(cpu, &local_err)) {
- error_report_err(local_err);
- return -ENOSYS;
- }
-
- if (hyperv_enabled(cpu)) {
- r = hyperv_init_vcpu(cpu);
- if (r) {
- return r;
- }
-
- cpuid_i = hyperv_fill_cpuids(cs, cpuid_data.entries);
- kvm_base = KVM_CPUID_SIGNATURE_NEXT;
- has_msr_hv_hypercall = true;
- }
-
- if (cs->kvm_state->xen_version) {
-#ifdef CONFIG_XEN_EMU
- struct kvm_cpuid_entry2 *xen_max_leaf;
-
- memcpy(signature, "XenVMMXenVMM", 12);
-
- xen_max_leaf = c = &cpuid_data.entries[cpuid_i++];
- c->function = kvm_base + XEN_CPUID_SIGNATURE;
- c->eax = kvm_base + XEN_CPUID_TIME;
- c->ebx = signature[0];
- c->ecx = signature[1];
- c->edx = signature[2];
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = kvm_base + XEN_CPUID_VENDOR;
- c->eax = cs->kvm_state->xen_version;
- c->ebx = 0;
- c->ecx = 0;
- c->edx = 0;
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = kvm_base + XEN_CPUID_HVM_MSR;
- /* Number of hypercall-transfer pages */
- c->eax = 1;
- /* Hypercall MSR base address */
- if (hyperv_enabled(cpu)) {
- c->ebx = XEN_HYPERCALL_MSR_HYPERV;
- kvm_xen_init(cs->kvm_state, c->ebx);
- } else {
- c->ebx = XEN_HYPERCALL_MSR;
- }
- c->ecx = 0;
- c->edx = 0;
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = kvm_base + XEN_CPUID_TIME;
- c->eax = ((!!tsc_is_stable_and_known(env) << 1) |
- (!!(env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_RDTSCP) << 2));
- /* default=0 (emulate if necessary) */
- c->ebx = 0;
- /* guest tsc frequency */
- c->ecx = env->user_tsc_khz;
- /* guest tsc incarnation (migration count) */
- c->edx = 0;
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = kvm_base + XEN_CPUID_HVM;
- xen_max_leaf->eax = kvm_base + XEN_CPUID_HVM;
- if (cs->kvm_state->xen_version >= XEN_VERSION(4, 5)) {
- c->function = kvm_base + XEN_CPUID_HVM;
-
- if (cpu->xen_vapic) {
- c->eax |= XEN_HVM_CPUID_APIC_ACCESS_VIRT;
- c->eax |= XEN_HVM_CPUID_X2APIC_VIRT;
- }
-
- c->eax |= XEN_HVM_CPUID_IOMMU_MAPPINGS;
-
- if (cs->kvm_state->xen_version >= XEN_VERSION(4, 6)) {
- c->eax |= XEN_HVM_CPUID_VCPU_ID_PRESENT;
- c->ebx = cs->cpu_index;
- }
-
- if (cs->kvm_state->xen_version >= XEN_VERSION(4, 17)) {
- c->eax |= XEN_HVM_CPUID_UPCALL_VECTOR;
- }
- }
-
- r = kvm_xen_init_vcpu(cs);
- if (r) {
- return r;
- }
-
- kvm_base += 0x100;
-#else /* CONFIG_XEN_EMU */
- /* This should never happen as kvm_arch_init() would have died first. */
- fprintf(stderr, "Cannot enable Xen CPUID without Xen support\n");
- abort();
-#endif
- } else if (cpu->expose_kvm) {
- memcpy(signature, "KVMKVMKVM\0\0\0", 12);
- c = &cpuid_data.entries[cpuid_i++];
- c->function = KVM_CPUID_SIGNATURE | kvm_base;
- c->eax = KVM_CPUID_FEATURES | kvm_base;
- c->ebx = signature[0];
- c->ecx = signature[1];
- c->edx = signature[2];
-
- c = &cpuid_data.entries[cpuid_i++];
- c->function = KVM_CPUID_FEATURES | kvm_base;
- c->eax = env->features[FEAT_KVM];
- c->edx = env->features[FEAT_KVM_HINTS];
- }
cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused);
- if (cpu->kvm_pv_enforce_cpuid) {
- r = kvm_vcpu_enable_cap(cs, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 0, 1);
- if (r < 0) {
- fprintf(stderr,
- "failed to enable KVM_CAP_ENFORCE_PV_FEATURE_CPUID: %s",
- strerror(-r));
- abort();
- }
- }
-
for (i = 0; i <= limit; i++) {
+ j = 0;
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "unsupported level value: 0x%x\n", limit);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
-
+ c = &entries[cpuid_i++];
switch (i) {
case 2: {
/* Keep reading function 2 till all the input is received */
@@ -1908,11 +1735,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
for (j = 1; j < times; ++j) {
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "cpuid_data is full, no space for "
- "cpuid(eax:2):eax & 0xf = 0x%x\n", times);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
+ c = &entries[cpuid_i++];
c->function = i;
c->flags = KVM_CPUID_FLAG_STATEFUL_FUNC;
cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
@@ -1951,11 +1776,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
continue;
}
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "cpuid_data is full, no space for "
- "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
+ c = &entries[cpuid_i++];
}
break;
case 0x12:
@@ -1970,11 +1793,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
}
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "cpuid_data is full, no space for "
- "cpuid(eax:0x12,ecx:0x%x)\n", j);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
+ c = &entries[cpuid_i++];
}
break;
case 0x7:
@@ -1991,11 +1812,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
for (j = 1; j <= times; ++j) {
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "cpuid_data is full, no space for "
- "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
+ c = &entries[cpuid_i++];
c->function = i;
c->index = j;
c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -2048,11 +1867,11 @@ int kvm_arch_init_vcpu(CPUState *cs)
cpu_x86_cpuid(env, 0x80000000, 0, &limit, &unused, &unused, &unused);
for (i = 0x80000000; i <= limit; i++) {
+ j = 0;
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "unsupported xlevel value: 0x%x\n", limit);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
+ c = &entries[cpuid_i++];
switch (i) {
case 0x8000001d:
@@ -2067,11 +1886,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
break;
}
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "cpuid_data is full, no space for "
- "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
+ c = &entries[cpuid_i++];
}
break;
default:
@@ -2094,11 +1911,11 @@ int kvm_arch_init_vcpu(CPUState *cs)
cpu_x86_cpuid(env, 0xC0000000, 0, &limit, &unused, &unused, &unused);
for (i = 0xC0000000; i <= limit; i++) {
+ j = 0;
if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
- fprintf(stderr, "unsupported xlevel2 value: 0x%x\n", limit);
- abort();
+ goto full;
}
- c = &cpuid_data.entries[cpuid_i++];
+ c = &entries[cpuid_i++];
c->function = i;
c->flags = 0;
@@ -2106,6 +1923,194 @@ int kvm_arch_init_vcpu(CPUState *cs)
}
}
+ return cpuid_i;
+
+full:
+ fprintf(stderr, "cpuid_data is full, no space for "
+ "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
+ abort();
+}
+
+int kvm_arch_init_vcpu(CPUState *cs)
+{
+ struct {
+ struct kvm_cpuid2 cpuid;
+ struct kvm_cpuid_entry2 entries[KVM_MAX_CPUID_ENTRIES];
+ } cpuid_data;
+ /*
+ * The kernel defines these structs with padding fields so there
+ * should be no extra padding in our cpuid_data struct.
+ */
+ QEMU_BUILD_BUG_ON(sizeof(cpuid_data) !=
+ sizeof(struct kvm_cpuid2) +
+ sizeof(struct kvm_cpuid_entry2) * KVM_MAX_CPUID_ENTRIES);
+
+ X86CPU *cpu = X86_CPU(cs);
+ CPUX86State *env = &cpu->env;
+ uint32_t cpuid_i;
+ struct kvm_cpuid_entry2 *c;
+ uint32_t signature[3];
+ int kvm_base = KVM_CPUID_SIGNATURE;
+ int max_nested_state_len;
+ int r;
+ Error *local_err = NULL;
+
+ memset(&cpuid_data, 0, sizeof(cpuid_data));
+
+ cpuid_i = 0;
+
+ has_xsave2 = kvm_check_extension(cs->kvm_state, KVM_CAP_XSAVE2);
+
+ r = kvm_arch_set_tsc_khz(cs);
+ if (r < 0) {
+ return r;
+ }
+
+ /* vcpu's TSC frequency is either specified by user, or following
+ * the value used by KVM if the former is not present. In the
+ * latter case, we query it from KVM and record in env->tsc_khz,
+ * so that vcpu's TSC frequency can be migrated later via this field.
+ */
+ if (!env->tsc_khz) {
+ r = kvm_check_extension(cs->kvm_state, KVM_CAP_GET_TSC_KHZ) ?
+ kvm_vcpu_ioctl(cs, KVM_GET_TSC_KHZ) :
+ -ENOTSUP;
+ if (r > 0) {
+ env->tsc_khz = r;
+ }
+ }
+
+ env->apic_bus_freq = KVM_APIC_BUS_FREQUENCY;
+
+ /*
+ * kvm_hyperv_expand_features() is called here for the second time in case
+ * KVM_CAP_SYS_HYPERV_CPUID is not supported. While we can't possibly handle
+ * 'query-cpu-model-expansion' in this case as we don't have a KVM vCPU to
+ * check which Hyper-V enlightenments are supported and which are not, we
+ * can still proceed and check/expand Hyper-V enlightenments here so legacy
+ * behavior is preserved.
+ */
+ if (!kvm_hyperv_expand_features(cpu, &local_err)) {
+ error_report_err(local_err);
+ return -ENOSYS;
+ }
+
+ if (hyperv_enabled(cpu)) {
+ r = hyperv_init_vcpu(cpu);
+ if (r) {
+ return r;
+ }
+
+ cpuid_i = hyperv_fill_cpuids(cs, cpuid_data.entries);
+ kvm_base = KVM_CPUID_SIGNATURE_NEXT;
+ has_msr_hv_hypercall = true;
+ }
+
+ if (cs->kvm_state->xen_version) {
+#ifdef CONFIG_XEN_EMU
+ struct kvm_cpuid_entry2 *xen_max_leaf;
+
+ memcpy(signature, "XenVMMXenVMM", 12);
+
+ xen_max_leaf = c = &cpuid_data.entries[cpuid_i++];
+ c->function = kvm_base + XEN_CPUID_SIGNATURE;
+ c->eax = kvm_base + XEN_CPUID_TIME;
+ c->ebx = signature[0];
+ c->ecx = signature[1];
+ c->edx = signature[2];
+
+ c = &cpuid_data.entries[cpuid_i++];
+ c->function = kvm_base + XEN_CPUID_VENDOR;
+ c->eax = cs->kvm_state->xen_version;
+ c->ebx = 0;
+ c->ecx = 0;
+ c->edx = 0;
+
+ c = &cpuid_data.entries[cpuid_i++];
+ c->function = kvm_base + XEN_CPUID_HVM_MSR;
+ /* Number of hypercall-transfer pages */
+ c->eax = 1;
+ /* Hypercall MSR base address */
+ if (hyperv_enabled(cpu)) {
+ c->ebx = XEN_HYPERCALL_MSR_HYPERV;
+ kvm_xen_init(cs->kvm_state, c->ebx);
+ } else {
+ c->ebx = XEN_HYPERCALL_MSR;
+ }
+ c->ecx = 0;
+ c->edx = 0;
+
+ c = &cpuid_data.entries[cpuid_i++];
+ c->function = kvm_base + XEN_CPUID_TIME;
+ c->eax = ((!!tsc_is_stable_and_known(env) << 1) |
+ (!!(env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_RDTSCP) << 2));
+ /* default=0 (emulate if necessary) */
+ c->ebx = 0;
+ /* guest tsc frequency */
+ c->ecx = env->user_tsc_khz;
+ /* guest tsc incarnation (migration count) */
+ c->edx = 0;
+
+ c = &cpuid_data.entries[cpuid_i++];
+ c->function = kvm_base + XEN_CPUID_HVM;
+ xen_max_leaf->eax = kvm_base + XEN_CPUID_HVM;
+ if (cs->kvm_state->xen_version >= XEN_VERSION(4, 5)) {
+ c->function = kvm_base + XEN_CPUID_HVM;
+
+ if (cpu->xen_vapic) {
+ c->eax |= XEN_HVM_CPUID_APIC_ACCESS_VIRT;
+ c->eax |= XEN_HVM_CPUID_X2APIC_VIRT;
+ }
+
+ c->eax |= XEN_HVM_CPUID_IOMMU_MAPPINGS;
+
+ if (cs->kvm_state->xen_version >= XEN_VERSION(4, 6)) {
+ c->eax |= XEN_HVM_CPUID_VCPU_ID_PRESENT;
+ c->ebx = cs->cpu_index;
+ }
+
+ if (cs->kvm_state->xen_version >= XEN_VERSION(4, 17)) {
+ c->eax |= XEN_HVM_CPUID_UPCALL_VECTOR;
+ }
+ }
+
+ r = kvm_xen_init_vcpu(cs);
+ if (r) {
+ return r;
+ }
+
+ kvm_base += 0x100;
+#else /* CONFIG_XEN_EMU */
+ /* This should never happen as kvm_arch_init() would have died first. */
+ fprintf(stderr, "Cannot enable Xen CPUID without Xen support\n");
+ abort();
+#endif
+ } else if (cpu->expose_kvm) {
+ memcpy(signature, "KVMKVMKVM\0\0\0", 12);
+ c = &cpuid_data.entries[cpuid_i++];
+ c->function = KVM_CPUID_SIGNATURE | kvm_base;
+ c->eax = KVM_CPUID_FEATURES | kvm_base;
+ c->ebx = signature[0];
+ c->ecx = signature[1];
+ c->edx = signature[2];
+
+ c = &cpuid_data.entries[cpuid_i++];
+ c->function = KVM_CPUID_FEATURES | kvm_base;
+ c->eax = env->features[FEAT_KVM];
+ c->edx = env->features[FEAT_KVM_HINTS];
+ }
+
+ if (cpu->kvm_pv_enforce_cpuid) {
+ r = kvm_vcpu_enable_cap(cs, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, 0, 1);
+ if (r < 0) {
+ fprintf(stderr,
+ "failed to enable KVM_CAP_ENFORCE_PV_FEATURE_CPUID: %s",
+ strerror(-r));
+ abort();
+ }
+ }
+
+ cpuid_i = kvm_x86_build_cpuid(env, cpuid_data.entries, cpuid_i);
cpuid_data.cpuid.nent = cpuid_i;
if (((env->cpuid_version >> 8)&0xF) >= 6
--
2.39.3
Reference in New Issue View Git Blame Copy Permalink