KVM: x86: Do not return host topology information from KVM_GET_SUPPORTED_CPUID

commit 45e966fcca03ecdcccac7cb236e16eea38cc18af upstream.

Passing the host topology to the guest is almost certainly wrong
and will confuse the scheduler.  In addition, several fields of
these CPUID leaves vary on each processor; it is simply impossible to
return the right values from KVM_GET_SUPPORTED_CPUID in such a way that
they can be passed to KVM_SET_CPUID2.

The values that will most likely prevent confusion are all zeroes.
Userspace will have to override it anyway if it wishes to present a
specific topology to the guest.

Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 896914e..b8ec88e 100644 (file)
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8248,6 +8248,20 @@ CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``
 It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
 has enabled in-kernel emulation of the local APIC.
 
+CPU topology
+~~~~~~~~~~~~
+
+Several CPUID values include topology information for the host CPU:
+0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems.  Different
+versions of KVM return different values for this information and userspace
+should not rely on it.  Currently they return all zeroes.
+
+If userspace wishes to set up a guest topology, it should be careful that
+the values of these three leaves differ for each CPU.  In particular,
+the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX
+for 0x8000001e; the latter also encodes the core id and node id in bits
+7:0 of EBX and ECX respectively.
+
 Obsolete ioctls and capabilities
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 62bc7a0..6047dbe 100644 (file)
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -759,16 +759,22 @@ struct kvm_cpuid_array {
        int nent;
 };
 
+static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array)
+{
+       if (array->nent >= array->maxnent)
+               return NULL;
+
+       return &array->entries[array->nent++];
+}
+
 static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
                                              u32 function, u32 index)
 {
-       struct kvm_cpuid_entry2 *entry;
+       struct kvm_cpuid_entry2 *entry = get_next_cpuid(array);
 
-       if (array->nent >= array->maxnent)
+       if (!entry)
                return NULL;
 
-       entry = &array->entries[array->nent++];
-
        memset(entry, 0, sizeof(*entry));
        entry->function = function;
        entry->index = index;
@@ -945,22 +951,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
                entry->edx = edx.full;
                break;
        }
-       /*
-        * Per Intel's SDM, the 0x1f is a superset of 0xb,
-        * thus they can be handled by common code.
-        */
        case 0x1f:
        case 0xb:
                /*
-                * Populate entries until the level type (ECX[15:8]) of the
-                * previous entry is zero.  Note, CPUID EAX.{0x1f,0xb}.0 is
-                * the starting entry, filled by the primary do_host_cpuid().
+                * No topology; a valid topology is indicated by the presence
+                * of subleaf 1.
                 */
-               for (i = 1; entry->ecx & 0xff00; ++i) {
-                       entry = do_host_cpuid(array, function, i);
-                       if (!entry)
-                               goto out;
-               }
+               entry->eax = entry->ebx = entry->ecx = 0;
                break;
        case 0xd: {
                u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
@@ -1193,6 +1190,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
                entry->ebx = entry->ecx = entry->edx = 0;
                break;
        case 0x8000001e:
+               /* Do not return host topology information.  */
+               entry->eax = entry->ebx = entry->ecx = 0;
+               entry->edx = 0; /* reserved */
                break;
        case 0x8000001F:
                if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {