/*
 * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
 *
 * futex-requeue: Block a bunch of threads on futex1 and requeue them
 *                on futex2, N at a time.
 *
 * This program is particularly useful to measure the latency of nthread
 * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
 */

/* For the CLR_() macros */
#include <pthread.h>

#include <signal.h>
#include "../util/stat.h"
#include <subcmd/parse-options.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/time64.h>
#include <errno.h>
#include "bench.h"
#include "futex.h"

#include <err.h>
#include <stdlib.h>
#include <sys/time.h>

static u_int32_t futex1 = 0, futex2 = 0;

/*
 * How many tasks to requeue at a time.
 * Default to 1 in order to make the kernel work more.
 */
static unsigned int nrequeue = 1;

static pthread_t *worker;
static bool done = false, silent = false, fshared = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static struct stats requeuetime_stats, requeued_stats;
static unsigned int ncpus, threads_starting, nthreads = 0;
static int futex_flag = 0;

static const struct option options[] = {
	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
	OPT_BOOLEAN( 'S', "shared",   &fshared,  "Use shared futexes instead of private ones"),
	OPT_END()
};

static const char * const bench_futex_requeue_usage[] = {
	"perf bench futex requeue <options>",
	NULL
};

static void print_summary(void)
{
	double requeuetime_avg = avg_stats(&requeuetime_stats);
	double requeuetime_stddev = stddev_stats(&requeuetime_stats);
	unsigned int requeued_avg = avg_stats(&requeued_stats);

	printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
	       requeued_avg,
	       nthreads,
	       requeuetime_avg / USEC_PER_MSEC,
	       rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
}

static void *workerfn(void *arg __maybe_unused)
{
	pthread_mutex_lock(&thread_lock);
	threads_starting--;
	if (!threads_starting)
		pthread_cond_signal(&thread_parent);
	pthread_cond_wait(&thread_worker, &thread_lock);
	pthread_mutex_unlock(&thread_lock);

	futex_wait(&futex1, 0, NULL, futex_flag);
	return NULL;
}

static void block_threads(pthread_t *w,
			  pthread_attr_t thread_attr)
{
	cpu_set_t cpu;
	unsigned int i;

	threads_starting = nthreads;

	/* create and block all threads */
	for (i = 0; i < nthreads; i++) {
		CPU_ZERO(&cpu);
		CPU_SET(i % ncpus, &cpu);

		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");

		if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
			err(EXIT_FAILURE, "pthread_create");
	}
}

static void toggle_done(int sig __maybe_unused,
			siginfo_t *info __maybe_unused,
			void *uc __maybe_unused)
{
	done = true;
}

int bench_futex_requeue(int argc, const char **argv,
			const char *prefix __maybe_unused)
{
	int ret = 0;
	unsigned int i, j;
	struct sigaction act;
	pthread_attr_t thread_attr;

	argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
	if (argc)
		goto err;

	ncpus = sysconf(_SC_NPROCESSORS_ONLN);

	sigfillset(&act.sa_mask);
	act.sa_sigaction = toggle_done;
	sigaction(SIGINT, &act, NULL);

	if (!nthreads)
		nthreads = ncpus;
	else
		nthreads = futexbench_sanitize_numeric(nthreads);

	worker = calloc(nthreads, sizeof(*worker));
	if (!worker)
		err(EXIT_FAILURE, "calloc");

	if (!fshared)
		futex_flag = FUTEX_PRIVATE_FLAG;

	if (nrequeue > nthreads)
		nrequeue = nthreads;

	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
	       "%d at a time.\n\n",  getpid(), nthreads,
	       fshared ? "shared":"private", &futex1, &futex2, nrequeue);

	init_stats(&requeued_stats);
	init_stats(&requeuetime_stats);
	pthread_attr_init(&thread_attr);
	pthread_mutex_init(&thread_lock, NULL);
	pthread_cond_init(&thread_parent, NULL);
	pthread_cond_init(&thread_worker, NULL);

	for (j = 0; j < bench_repeat && !done; j++) {
		unsigned int nrequeued = 0;
		struct timeval start, end, runtime;

		/* create, launch & block all threads */
		block_threads(worker, thread_attr);

		/* make sure all threads are already blocked */
		pthread_mutex_lock(&thread_lock);
		while (threads_starting)
			pthread_cond_wait(&thread_parent, &thread_lock);
		pthread_cond_broadcast(&thread_worker);
		pthread_mutex_unlock(&thread_lock);

		usleep(100000);

		/* Ok, all threads are patiently blocked, start requeueing */
		gettimeofday(&start, NULL);
		while (nrequeued < nthreads) {
			/*
			 * Do not wakeup any tasks blocked on futex1, allowing
			 * us to really measure futex_wait functionality.
			 */
			nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
						       nrequeue, futex_flag);
		}

		gettimeofday(&end, NULL);
		timersub(&end, &start, &runtime);

		update_stats(&requeued_stats, nrequeued);
		update_stats(&requeuetime_stats, runtime.tv_usec);

		if (!silent) {
			printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
			       j + 1, nrequeued, nthreads, runtime.tv_usec / (double)USEC_PER_MSEC);
		}

		/* everybody should be blocked on futex2, wake'em up */
		nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
		if (nthreads != nrequeued)
			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);

		for (i = 0; i < nthreads; i++) {
			ret = pthread_join(worker[i], NULL);
			if (ret)
				err(EXIT_FAILURE, "pthread_join");
		}
	}

	/* cleanup & report results */
	pthread_cond_destroy(&thread_parent);
	pthread_cond_destroy(&thread_worker);
	pthread_mutex_destroy(&thread_lock);
	pthread_attr_destroy(&thread_attr);

	print_summary();

	free(worker);
	return ret;
err:
	usage_with_options(bench_futex_requeue_usage, options);
	exit(EXIT_FAILURE);
}
2'>tools/perf/perf-archive.sh</a></td></tr>
<tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/tools/perf/perf-archive.sh?h=nds-private-remove&amp;id=3eb86259eca6a363ed7bb13ecea5cda809f7b97d'>3eb86259eca6a363ed7bb13ecea5cda809f7b97d</a> (<a href='/cgit.cgi/linux/net-next.git/diff/tools/perf/perf-archive.sh?h=nds-private-remove&amp;id=ba6d973f78eb62ffebb32f6ef3334fc9a3b33d22&amp;id2=3eb86259eca6a363ed7bb13ecea5cda809f7b97d'>diff</a>)</td></tr><tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/tools/perf/perf-archive.sh?h=nds-private-remove&amp;id=a763f78cea845c91b8d91f93dabf70c407635dc5'>a763f78cea845c91b8d91f93dabf70c407635dc5</a> (<a href='/cgit.cgi/linux/net-next.git/diff/tools/perf/perf-archive.sh?h=nds-private-remove&amp;id=ba6d973f78eb62ffebb32f6ef3334fc9a3b33d22&amp;id2=a763f78cea845c91b8d91f93dabf70c407635dc5'>diff</a>)</td></tr></table>
<div class='commit-subject'>Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net</div><div class='commit-msg'>Pull networking fixes and cleanups from David Miller:

 1) Use rb_entry() instead of hardcoded container_of(), from Geliang
    Tang.

 2) Use correct memory barriers in stammac driver, from Pavel Machek.

 3) Fix assoc bind address handling in SCTP, from Xin Long.

 4) Make the length check for UFO handling consistent between
    __ip_append_data() and ip_finish_output(), from Zheng Li.

 5) HSI driver compatible strings were busted fro hix5hd2, from Dongpo
    Li.

 6) Handle devm_ioremap() errors properly in cavium driver, from Arvind
    Yadav.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (22 commits)
  RDS: use rb_entry()
  net_sched: sch_netem: use rb_entry()
  net_sched: sch_fq: use rb_entry()
  net/mlx5: use rb_entry()
  ethernet: sfc: Add Kconfig entry for vendor Solarflare
  sctp: not copying duplicate addrs to the assoc's bind address list
  sctp: reduce indent level in sctp_copy_local_addr_list
  ARM: dts: hix5hd2: don't change the existing compatible string
  net: hix5hd2_gmac: fix compatible strings name
  openvswitch: Add a missing break statement.
  net: netcp: ethss: fix 10gbe host port tx pri map configuration
  net: netcp: ethss: fix errors in ethtool ops
  fsl/fman: enable compilation on ARM64
  fsl/fman: A007273 only applies to PPC SoCs
  powerpc: fsl/fman: remove fsl,fman from of_device_ids[]
  fsl/fman: fix 1G support for QSGMII interfaces
  dt: bindings: net: use boolean dt properties for eee broken modes
  net: phy: use boolean dt properties for eee broken modes
  net: phy: fix sign type error in genphy_config_eee_advert
  ipv4: Should use consistent conditional judgement for ip fragment in __ip_append_data and ip_finish_output
  ...
</div><div class='diffstat-header'><a href='/cgit.cgi/linux/net-next.git/diff/?h=nds-private-remove&amp;id=ba6d973f78eb62ffebb32f6ef3334fc9a3b33d22'>Diffstat</a> (limited to 'tools/perf/perf-archive.sh')</div><table summary='diffstat' class='diffstat'>