KVM: selftests: Restore assert for non-nested VMs in access tracking test

Restore the assert (on x86-64) that <10% of pages are still idle when NOT
running as a nested VM in the access tracking test.  The original assert
was converted to a "warning" to avoid false failures when running the
test in a VM, but the non-nested case does not suffer from the same
"infinite TLB size" issue.

Using the HYPERVISOR flag isn't infallible as VMMs aren't strictly
required to enumerate the "feature" in CPUID, but practically speaking
anyone that is running KVM selftests in VMs is going to be using a VMM
and hypervisor that sets the HYPERVISOR flag.

Cc: David Matlack <dmatlack@google.com>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20221129175300.4052283-3-seanjc@google.com

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index d45ef319a68f3ff066b2281500c50b0dce50eab4..9f9503e40ca56aa92bf53597e2bd3815c5d3de10 100644 (file)
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -46,6 +46,7 @@
 #include "test_util.h"
 #include "memstress.h"
 #include "guest_modes.h"
+#include "processor.h"
 
 /* Global variable used to synchronize all of the vCPU threads. */
 static int iteration;
@@ -180,15 +181,21 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm,
         * access tracking but low enough as to not make the test too brittle
         * over time and across architectures.
         *
-        * Note that when run in nested virtualization, this check will trigger
-        * much more frequently because TLB size is unlimited and since no flush
-        * happens, much more pages are cached there and guest won't see the
-        * "idle" bit cleared.
+        * When running the guest as a nested VM, "warn" instead of asserting
+        * as the TLB size is effectively unlimited and the KVM doesn't
+        * explicitly flush the TLB when aging SPTEs.  As a result, more pages
+        * are cached and the guest won't see the "idle" bit cleared.
         */
-       if (still_idle >= pages / 10)
+       if (still_idle >= pages / 10) {
+#ifdef __x86_64__
+               TEST_ASSERT(this_cpu_has(X86_FEATURE_HYPERVISOR),
+                           "vCPU%d: Too many pages still idle (%lu out of %lu)",
+                           vcpu_idx, still_idle, pages);
+#endif
                printf("WARNING: vCPU%d: Too many pages still idle (%lu out of %lu), "
                       "this will affect performance results.\n",
                       vcpu_idx, still_idle, pages);
+       }
 
        close(page_idle_fd);
        close(pagemap_fd);

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 5d310abe6c3f4671b56c4cfbb8454ca84c16243e..22852bd32d7b7842d01626d7d0d09d4a4eef35e2 100644 (file)
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -94,6 +94,7 @@ struct kvm_x86_cpu_feature {
 #define        X86_FEATURE_XSAVE               KVM_X86_CPU_FEATURE(0x1, 0, ECX, 26)
 #define        X86_FEATURE_OSXSAVE             KVM_X86_CPU_FEATURE(0x1, 0, ECX, 27)
 #define        X86_FEATURE_RDRAND              KVM_X86_CPU_FEATURE(0x1, 0, ECX, 30)
+#define        X86_FEATURE_HYPERVISOR          KVM_X86_CPU_FEATURE(0x1, 0, ECX, 31)
 #define X86_FEATURE_PAE                        KVM_X86_CPU_FEATURE(0x1, 0, EDX, 6)
 #define        X86_FEATURE_MCE                 KVM_X86_CPU_FEATURE(0x1, 0, EDX, 7)
 #define        X86_FEATURE_APIC                KVM_X86_CPU_FEATURE(0x1, 0, EDX, 9)