KVM: selftests: Add an option to run vCPUs while disabling dirty logging

Add a command line option to dirty_log_perf_test to run vCPUs for the
entire duration of disabling dirty logging.  By default, the test stops
running runs vCPUs before disabling dirty logging, which is faster but
less interesting as it doesn't stress KVM's handling of contention
between page faults and the zapping of collapsible SPTEs.  Enabling the
flag also lets the user verify that KVM is indeed rebuilding zapped SPTEs
as huge pages by checking KVM's pages_{1g,2m,4k} stats.  Without vCPUs to
fault in the zapped SPTEs, the stats will show that KVM is zapping pages,
but they never show whether or not KVM actually allows huge pages to be
recreated.

Note!  Enabling the flag can _significantly_ increase runtime, especially
if the thread that's disabling dirty logging doesn't have a dedicated
pCPU, e.g. if all pCPUs are used to run vCPUs.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220715232107.3775620-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: sean-jc

tools/testing/selftests/kvm/dirty_log_perf_test.c

@@ -59,6 +59,7 @@ static void arch_cleanup_vm(struct kvm_vm *vm)
 
 static int nr_vcpus = 1;
 static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+static bool run_vcpus_while_disabling_dirty_logging;
 
 /* Host variables */
 static u64 dirty_log_manual_caps;
@@ -109,8 +110,13 @@ static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 				ts_diff.tv_nsec);
 		}
 
+		/*
+		 * Keep running the guest while dirty logging is being disabled
+		 * (iteration is negative) so that vCPUs are accessing memory
+		 * for the entire duration of zapping collapsible SPTEs.
+		 */
 		while (current_iteration == READ_ONCE(iteration) &&
-		       !READ_ONCE(host_quit)) {}
+		       READ_ONCE(iteration) >= 0 && !READ_ONCE(host_quit)) {}
 	}
 
 	avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_idx]);
@@ -302,14 +308,26 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		}
 	}
 
+	/*
+	 * Run vCPUs while dirty logging is being disabled to stress disabling
+	 * in terms of both performance and correctness.  Opt-in via command
+	 * line as this significantly increases time to disable dirty logging.
+	 */
+	if (run_vcpus_while_disabling_dirty_logging)
+		WRITE_ONCE(iteration, -1);
+
 	/* Disable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
 	disable_dirty_logging(vm, p->slots);
 	ts_diff = timespec_elapsed(start);
 	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 
-	/* Tell the vcpu thread to quit */
+	/*
+	 * Tell the vCPU threads to quit.  No need to manually check that vCPUs
+	 * have stopped running after disabling dirty logging, the join will
+	 * wait for them to exit.
+	 */
 	host_quit = true;
 	perf_test_join_vcpu_threads(nr_vcpus);
 
@@ -349,6 +367,9 @@ static void help(char *name)
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
 	guest_modes_help();
 	printf(" -n: Run the vCPUs in nested mode (L2)\n");
+	printf(" -e: Run vCPUs while dirty logging is being disabled.  This\n"
+	       "     can significantly increase runtime, especially if there\n"
+	       "     isn't a dedicated pCPU for the main thread.\n");
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     dirtied by each vCPU. e.g. 10M or 3G.\n"
 	       "     (default: 1G)\n");
@@ -385,8 +406,11 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "ghi:p:m:nb:f:v:os:x:")) != -1) {
+	while ((opt = getopt(argc, argv, "eghi:p:m:nb:f:v:os:x:")) != -1) {
 		switch (opt) {
+		case 'e':
+			/* 'e' is for evil. */
+			run_vcpus_while_disabling_dirty_logging = true;
 		case 'g':
 			dirty_log_manual_caps = 0;
 			break;