1 files changed, 174 insertions, 25 deletions

diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 7a6890b23c5f..da94b89cd531 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -86,10 +86,11 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
 	      "Shutdown at end of performance tests.");
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
+torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?");
 
 static char *perf_type = "rcu";
 module_param(perf_type, charp, 0444);
-MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)");
+MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, srcu, ...)");
 
 static int nrealreaders;
 static int nrealwriters;
@@ -105,19 +106,10 @@ static atomic_t n_rcu_perf_writer_finished;
 static wait_queue_head_t shutdown_wq;
 static u64 t_rcu_perf_writer_started;
 static u64 t_rcu_perf_writer_finished;
-static unsigned long b_rcu_perf_writer_started;
-static unsigned long b_rcu_perf_writer_finished;
+static unsigned long b_rcu_gp_test_started;
+static unsigned long b_rcu_gp_test_finished;
 static DEFINE_PER_CPU(atomic_t, n_async_inflight);
 
-static int rcu_perf_writer_state;
-#define RTWS_INIT		0
-#define RTWS_ASYNC		1
-#define RTWS_BARRIER		2
-#define RTWS_EXP_SYNC		3
-#define RTWS_SYNC		4
-#define RTWS_IDLE		5
-#define RTWS_STOPPING		6
-
 #define MAX_MEAS 10000
 #define MIN_MEAS 100
 
@@ -375,14 +367,22 @@ rcu_perf_writer(void *arg)
 	if (holdoff)
 		schedule_timeout_uninterruptible(holdoff * HZ);
 
+	/*
+	 * Wait until rcu_end_inkernel_boot() is called for normal GP tests
+	 * so that RCU is not always expedited for normal GP tests.
+	 * The system_state test is approximate, but works well in practice.
+	 */
+	while (!gp_exp && system_state != SYSTEM_RUNNING)
+		schedule_timeout_uninterruptible(1);
+
 	t = ktime_get_mono_fast_ns();
 	if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
 		t_rcu_perf_writer_started = t;
 		if (gp_exp) {
-			b_rcu_perf_writer_started =
+			b_rcu_gp_test_started =
 				cur_ops->exp_completed() / 2;
 		} else {
-			b_rcu_perf_writer_started = cur_ops->get_gp_seq();
+			b_rcu_gp_test_started = cur_ops->get_gp_seq();
 		}
 	}
 
@@ -396,25 +396,20 @@ retry:
 			if (!rhp)
 				rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
 			if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
-				rcu_perf_writer_state = RTWS_ASYNC;
 				atomic_inc(this_cpu_ptr(&n_async_inflight));
 				cur_ops->async(rhp, rcu_perf_async_cb);
 				rhp = NULL;
 			} else if (!kthread_should_stop()) {
-				rcu_perf_writer_state = RTWS_BARRIER;
 				cur_ops->gp_barrier();
 				goto retry;
 			} else {
 				kfree(rhp); /* Because we are stopping. */
 			}
 		} else if (gp_exp) {
-			rcu_perf_writer_state = RTWS_EXP_SYNC;
 			cur_ops->exp_sync();
 		} else {
-			rcu_perf_writer_state = RTWS_SYNC;
 			cur_ops->sync();
 		}
-		rcu_perf_writer_state = RTWS_IDLE;
 		t = ktime_get_mono_fast_ns();
 		*wdp = t - *wdp;
 		i_max = i;
@@ -435,10 +430,10 @@ retry:
 				PERFOUT_STRING("Test complete");
 				t_rcu_perf_writer_finished = t;
 				if (gp_exp) {
-					b_rcu_perf_writer_finished =
+					b_rcu_gp_test_finished =
 						cur_ops->exp_completed() / 2;
 				} else {
-					b_rcu_perf_writer_finished =
+					b_rcu_gp_test_finished =
 						cur_ops->get_gp_seq();
 				}
 				if (shutdown) {
@@ -455,10 +450,8 @@ retry:
 		rcu_perf_wait_shutdown();
 	} while (!torture_must_stop());
 	if (gp_async) {
-		rcu_perf_writer_state = RTWS_BARRIER;
 		cur_ops->gp_barrier();
 	}
-	rcu_perf_writer_state = RTWS_STOPPING;
 	writer_n_durations[me] = i_max;
 	torture_kthread_stopping("rcu_perf_writer");
 	return 0;
@@ -523,8 +516,8 @@ rcu_perf_cleanup(void)
 			 t_rcu_perf_writer_finished -
 			 t_rcu_perf_writer_started,
 			 ngps,
-			 rcuperf_seq_diff(b_rcu_perf_writer_finished,
-					  b_rcu_perf_writer_started));
+			 rcuperf_seq_diff(b_rcu_gp_test_finished,
+					  b_rcu_gp_test_started));
 		for (i = 0; i < nrealwriters; i++) {
 			if (!writer_durations)
 				break;
@@ -592,6 +585,159 @@ rcu_perf_shutdown(void *arg)
 	return -EINVAL;
 }
 
+/*
+ * kfree_rcu() performance tests: Start a kfree_rcu() loop on all CPUs for number
+ * of iterations and measure total time and number of GP for all iterations to complete.
+ */
+
+torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu().");
+torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration.");
+torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees.");
+
+static struct task_struct **kfree_reader_tasks;
+static int kfree_nrealthreads;
+static atomic_t n_kfree_perf_thread_started;
+static atomic_t n_kfree_perf_thread_ended;
+
+struct kfree_obj {
+	char kfree_obj[8];
+	struct rcu_head rh;
+};
+
+static int
+kfree_perf_thread(void *arg)
+{
+	int i, loop = 0;
+	long me = (long)arg;
+	struct kfree_obj *alloc_ptr;
+	u64 start_time, end_time;
+
+	VERBOSE_PERFOUT_STRING("kfree_perf_thread task started");
+	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+	set_user_nice(current, MAX_NICE);
+
+	start_time = ktime_get_mono_fast_ns();
+
+	if (atomic_inc_return(&n_kfree_perf_thread_started) >= kfree_nrealthreads) {
+		if (gp_exp)
+			b_rcu_gp_test_started = cur_ops->exp_completed() / 2;
+		else
+			b_rcu_gp_test_started = cur_ops->get_gp_seq();
+	}
+
+	do {
+		for (i = 0; i < kfree_alloc_num; i++) {
+			alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL);
+			if (!alloc_ptr)
+				return -ENOMEM;
+
+			kfree_rcu(alloc_ptr, rh);
+		}
+
+		cond_resched();
+	} while (!torture_must_stop() && ++loop < kfree_loops);
+
+	if (atomic_inc_return(&n_kfree_perf_thread_ended) >= kfree_nrealthreads) {
+		end_time = ktime_get_mono_fast_ns();
+
+		if (gp_exp)
+			b_rcu_gp_test_finished = cur_ops->exp_completed() / 2;
+		else
+			b_rcu_gp_test_finished = cur_ops->get_gp_seq();
+
+		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n",
+		       (unsigned long long)(end_time - start_time), kfree_loops,
+		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started));
+		if (shutdown) {
+			smp_mb(); /* Assign before wake. */
+			wake_up(&shutdown_wq);
+		}
+	}
+
+	torture_kthread_stopping("kfree_perf_thread");
+	return 0;
+}
+
+static void
+kfree_perf_cleanup(void)
+{
+	int i;
+
+	if (torture_cleanup_begin())
+		return;
+
+	if (kfree_reader_tasks) {
+		for (i = 0; i < kfree_nrealthreads; i++)
+			torture_stop_kthread(kfree_perf_thread,
+					     kfree_reader_tasks[i]);
+		kfree(kfree_reader_tasks);
+	}
+
+	torture_cleanup_end();
+}
+
+/*
+ * shutdown kthread.  Just waits to be awakened, then shuts down system.
+ */
+static int
+kfree_perf_shutdown(void *arg)
+{
+	do {
+		wait_event(shutdown_wq,
+			   atomic_read(&n_kfree_perf_thread_ended) >=
+			   kfree_nrealthreads);
+	} while (atomic_read(&n_kfree_perf_thread_ended) < kfree_nrealthreads);
+
+	smp_mb(); /* Wake before output. */
+
+	kfree_perf_cleanup();
+	kernel_power_off();
+	return -EINVAL;
+}
+
+static int __init
+kfree_perf_init(void)
+{
+	long i;
+	int firsterr = 0;
+
+	kfree_nrealthreads = compute_real(kfree_nthreads);
+	/* Start up the kthreads. */
+	if (shutdown) {
+		init_waitqueue_head(&shutdown_wq);
+		firsterr = torture_create_kthread(kfree_perf_shutdown, NULL,
+						  shutdown_task);
+		if (firsterr)
+			goto unwind;
+		schedule_timeout_uninterruptible(1);
+	}
+
+	kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
+			       GFP_KERNEL);
+	if (kfree_reader_tasks == NULL) {
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+
+	for (i = 0; i < kfree_nrealthreads; i++) {
+		firsterr = torture_create_kthread(kfree_perf_thread, (void *)i,
+						  kfree_reader_tasks[i]);
+		if (firsterr)
+			goto unwind;
+	}
+
+	while (atomic_read(&n_kfree_perf_thread_started) < kfree_nrealthreads)
+		schedule_timeout_uninterruptible(1);
+
+	torture_init_end();
+	return 0;
+
+unwind:
+	torture_init_end();
+	kfree_perf_cleanup();
+	return firsterr;
+}
+
 static int __init
 rcu_perf_init(void)
 {
@@ -624,6 +770,9 @@ rcu_perf_init(void)
 	if (cur_ops->init)
 		cur_ops->init();
 
+	if (kfree_rcu_test)
+		return kfree_perf_init();
+
 	nrealwriters = compute_real(nwriters);
 	nrealreaders = compute_real(nreaders);
 	atomic_set(&n_rcu_perf_reader_started, 0);