KVM: selftests: Wait for all vCPU to be created before entering guest mode

Thread creation requires taking the mmap_sem in write mode, which causes
vCPU threads running in guest mode to block while they are populating
memory. Fix this by waiting for all vCPU threads to be created and start
running before entering guest mode on any one vCPU thread.

This substantially improves the "Populate memory time" when using 1GiB
pages since it allows all vCPUs to zero pages in parallel rather than
blocking because a writer is waiting (which is waiting for another vCPU
that is busy zeroing a 1GiB page).

Before:

  $ ./dirty_log_perf_test -v256 -s anonymous_hugetlb_1gb
  ...
  Populate memory time: 52.811184013s

After:

  $ ./dirty_log_perf_test -v256 -s anonymous_hugetlb_1gb
  ...
  Populate memory time: 10.204573342s

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111001257.1446428-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index d646477ed16a31f2213abe6c295e86a81c5018cc..722df3a28791c3b7eb3fd967c9f1ea195f815796 100644 (file)
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -22,6 +22,9 @@ struct vcpu_thread {
 
        /* The pthread backing the vCPU. */
        pthread_t thread;
+
+       /* Set to true once the vCPU thread is up and running. */
+       bool running;
 };
 
 /* The vCPU threads involved in this test. */
@@ -30,6 +33,9 @@ static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
 /* The function run by each vCPU thread, as provided by the test. */
 static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
 
+/* Set to true once all vCPU threads are up and running. */
+static bool all_vcpu_threads_running;
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
@@ -196,6 +202,17 @@ static void *vcpu_thread_main(void *data)
 {
        struct vcpu_thread *vcpu = data;
 
+       WRITE_ONCE(vcpu->running, true);
+
+       /*
+        * Wait for all vCPU threads to be up and running before calling the test-
+        * provided vCPU thread function. This prevents thread creation (which
+        * requires taking the mmap_sem in write mode) from interfering with the
+        * guest faulting in its memory.
+        */
+       while (!READ_ONCE(all_vcpu_threads_running))
+               ;
+
        vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
 
        return NULL;
@@ -206,14 +223,23 @@ void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vc
        int vcpu_id;
 
        vcpu_thread_fn = vcpu_fn;
+       WRITE_ONCE(all_vcpu_threads_running, false);
 
        for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
                struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
 
                vcpu->vcpu_id = vcpu_id;
+               WRITE_ONCE(vcpu->running, false);
 
                pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
        }
+
+       for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+               while (!READ_ONCE(vcpu_threads[vcpu_id].running))
+                       ;
+       }
+
+       WRITE_ONCE(all_vcpu_threads_running, true);
 }
 
 void perf_test_join_vcpu_threads(int vcpus)