Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index eafce1a..e4e321b 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -7,6 +7,9 @@
perf-y += futex-requeue.o
perf-y += futex-lock-pi.o
+perf-y += epoll-wait.o
+perf-y += epoll-ctl.o
+
perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 6c9fcd7..fddb3ce 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -38,6 +38,9 @@
/* pi futexes */
int bench_futex_lock_pi(int argc, const char **argv);
+int bench_epoll_wait(int argc, const char **argv);
+int bench_epoll_ctl(int argc, const char **argv);
+
#define BENCH_FORMAT_DEFAULT_STR "default"
#define BENCH_FORMAT_DEFAULT 0
#define BENCH_FORMAT_SIMPLE_STR "simple"
@@ -48,4 +51,15 @@
extern int bench_format;
extern unsigned int bench_repeat;
+#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
+#include <pthread.h>
+#include <linux/compiler.h>
+static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
+ size_t cpusetsize __maybe_unused,
+ cpu_set_t *cpuset __maybe_unused)
+{
+ return 0;
+}
+#endif
+
#endif
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
new file mode 100644
index 0000000..bb617e5
--- /dev/null
+++ b/tools/perf/bench/epoll-ctl.c
@@ -0,0 +1,415 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Davidlohr Bueso.
+ *
+ * Benchmark the various operations allowed for epoll_ctl(2).
+ * The idea is to concurrently stress a single epoll instance
+ */
+#ifdef HAVE_EVENTFD
+/* For the CLR_() macros */
+#include <string.h>
+#include <pthread.h>
+
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/epoll.h>
+#include <sys/eventfd.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
+
+#include "../util/stat.h"
+#include <subcmd/parse-options.h>
+#include "bench.h"
+
+#include <err.h>
+
+#define printinfo(fmt, arg...) \
+ do { if (__verbose) printf(fmt, ## arg); } while (0)
+
+static unsigned int nthreads = 0;
+static unsigned int nsecs = 8;
+struct timeval start, end, runtime;
+static bool done, __verbose, randomize;
+
+/*
+ * epoll related shared variables.
+ */
+
+/* Maximum number of nesting allowed inside epoll sets */
+#define EPOLL_MAXNESTS 4
+
+enum {
+ OP_EPOLL_ADD,
+ OP_EPOLL_MOD,
+ OP_EPOLL_DEL,
+ EPOLL_NR_OPS,
+};
+
+static int epollfd;
+static int *epollfdp;
+static bool noaffinity;
+static unsigned int nested = 0;
+
+/* amount of fds to monitor, per thread */
+static unsigned int nfds = 64;
+
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats all_stats[EPOLL_NR_OPS];
+static pthread_cond_t thread_parent, thread_worker;
+
+struct worker {
+ int tid;
+ pthread_t thread;
+ unsigned long ops[EPOLL_NR_OPS];
+ int *fdmap;
+};
+
+static const struct option options[] = {
+ OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
+ OPT_UINTEGER('f', "nfds", &nfds, "Specify amount of file descriptors to monitor for each thread"),
+ OPT_BOOLEAN( 'n', "noaffinity", &noaffinity, "Disables CPU affinity"),
+ OPT_UINTEGER( 'N', "nested", &nested, "Nesting level epoll hierarchy (default is 0, no nesting)"),
+ OPT_BOOLEAN( 'R', "randomize", &randomize, "Perform random operations on random fds"),
+ OPT_BOOLEAN( 'v', "verbose", &__verbose, "Verbose mode"),
+ OPT_END()
+};
+
+static const char * const bench_epoll_ctl_usage[] = {
+ "perf bench epoll ctl <options>",
+ NULL
+};
+
+static void toggle_done(int sig __maybe_unused,
+ siginfo_t *info __maybe_unused,
+ void *uc __maybe_unused)
+{
+ /* inform all threads that we're done for the day */
+ done = true;
+ gettimeofday(&end, NULL);
+ timersub(&end, &start, &runtime);
+}
+
+static void nest_epollfd(void)
+{
+ unsigned int i;
+ struct epoll_event ev;
+
+ if (nested > EPOLL_MAXNESTS)
+ nested = EPOLL_MAXNESTS;
+ printinfo("Nesting level(s): %d\n", nested);
+
+ epollfdp = calloc(nested, sizeof(int));
+ if (!epollfd)
+ err(EXIT_FAILURE, "calloc");
+
+ for (i = 0; i < nested; i++) {
+ epollfdp[i] = epoll_create(1);
+ if (epollfd < 0)
+ err(EXIT_FAILURE, "epoll_create");
+ }
+
+ ev.events = EPOLLHUP; /* anything */
+ ev.data.u64 = i; /* any number */
+
+ for (i = nested - 1; i; i--) {
+ if (epoll_ctl(epollfdp[i - 1], EPOLL_CTL_ADD,
+ epollfdp[i], &ev) < 0)
+ err(EXIT_FAILURE, "epoll_ctl");
+ }
+
+ if (epoll_ctl(epollfd, EPOLL_CTL_ADD, *epollfdp, &ev) < 0)
+ err(EXIT_FAILURE, "epoll_ctl");
+}
+
+static inline void do_epoll_op(struct worker *w, int op, int fd)
+{
+ int error;
+ struct epoll_event ev;
+
+ ev.events = EPOLLIN;
+ ev.data.u64 = fd;
+
+ switch (op) {
+ case OP_EPOLL_ADD:
+ error = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev);
+ break;
+ case OP_EPOLL_MOD:
+ ev.events = EPOLLOUT;
+ error = epoll_ctl(epollfd, EPOLL_CTL_MOD, fd, &ev);
+ break;
+ case OP_EPOLL_DEL:
+ error = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, NULL);
+ break;
+ default:
+ error = 1;
+ break;
+ }
+
+ if (!error)
+ w->ops[op]++;
+}
+
+static inline void do_random_epoll_op(struct worker *w)
+{
+ unsigned long rnd1 = random(), rnd2 = random();
+ int op, fd;
+
+ fd = w->fdmap[rnd1 % nfds];
+ op = rnd2 % EPOLL_NR_OPS;
+
+ do_epoll_op(w, op, fd);
+}
+
+static void *workerfn(void *arg)
+{
+ unsigned int i;
+ struct worker *w = (struct worker *) arg;
+ struct timespec ts = { .tv_sec = 0,
+ .tv_nsec = 250 };
+
+ 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);
+
+ /* Let 'em loose */
+ do {
+ /* random */
+ if (randomize) {
+ do_random_epoll_op(w);
+ } else {
+ for (i = 0; i < nfds; i++) {
+ do_epoll_op(w, OP_EPOLL_ADD, w->fdmap[i]);
+ do_epoll_op(w, OP_EPOLL_MOD, w->fdmap[i]);
+ do_epoll_op(w, OP_EPOLL_DEL, w->fdmap[i]);
+ }
+ }
+
+ nanosleep(&ts, NULL);
+ } while (!done);
+
+ return NULL;
+}
+
+static void init_fdmaps(struct worker *w, int pct)
+{
+ unsigned int i;
+ int inc;
+ struct epoll_event ev;
+
+ if (!pct)
+ return;
+
+ inc = 100/pct;
+ for (i = 0; i < nfds; i+=inc) {
+ ev.data.fd = w->fdmap[i];
+ ev.events = EPOLLIN;
+
+ if (epoll_ctl(epollfd, EPOLL_CTL_ADD, w->fdmap[i], &ev) < 0)
+ err(EXIT_FAILURE, "epoll_ct");
+ }
+}
+
+static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
+{
+ pthread_attr_t thread_attr, *attrp = NULL;
+ cpu_set_t cpuset;
+ unsigned int i, j;
+ int ret = 0;
+
+ if (!noaffinity)
+ pthread_attr_init(&thread_attr);
+
+ for (i = 0; i < nthreads; i++) {
+ struct worker *w = &worker[i];
+
+ w->tid = i;
+ w->fdmap = calloc(nfds, sizeof(int));
+ if (!w->fdmap)
+ return 1;
+
+ for (j = 0; j < nfds; j++) {
+ w->fdmap[j] = eventfd(0, EFD_NONBLOCK);
+ if (w->fdmap[j] < 0)
+ err(EXIT_FAILURE, "eventfd");
+ }
+
+ /*
+ * Lets add 50% of the fdmap to the epoll instance, and
+ * do it before any threads are started; otherwise there is
+ * an initial bias of the call failing (mod and del ops).
+ */
+ if (randomize)
+ init_fdmaps(w, 50);
+
+ if (!noaffinity) {
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+
+ ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
+ if (ret)
+ err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+ attrp = &thread_attr;
+ }
+
+ ret = pthread_create(&w->thread, attrp, workerfn,
+ (void *)(struct worker *) w);
+ if (ret)
+ err(EXIT_FAILURE, "pthread_create");
+ }
+
+ if (!noaffinity)
+ pthread_attr_destroy(&thread_attr);
+
+ return ret;
+}
+
+static void print_summary(void)
+{
+ int i;
+ unsigned long avg[EPOLL_NR_OPS];
+ double stddev[EPOLL_NR_OPS];
+
+ for (i = 0; i < EPOLL_NR_OPS; i++) {
+ avg[i] = avg_stats(&all_stats[i]);
+ stddev[i] = stddev_stats(&all_stats[i]);
+ }
+
+ printf("\nAveraged %ld ADD operations (+- %.2f%%)\n",
+ avg[OP_EPOLL_ADD], rel_stddev_stats(stddev[OP_EPOLL_ADD],
+ avg[OP_EPOLL_ADD]));
+ printf("Averaged %ld MOD operations (+- %.2f%%)\n",
+ avg[OP_EPOLL_MOD], rel_stddev_stats(stddev[OP_EPOLL_MOD],
+ avg[OP_EPOLL_MOD]));
+ printf("Averaged %ld DEL operations (+- %.2f%%)\n",
+ avg[OP_EPOLL_DEL], rel_stddev_stats(stddev[OP_EPOLL_DEL],
+ avg[OP_EPOLL_DEL]));
+}
+
+int bench_epoll_ctl(int argc, const char **argv)
+{
+ int j, ret = 0;
+ struct sigaction act;
+ struct worker *worker = NULL;
+ struct perf_cpu_map *cpu;
+ struct rlimit rl, prevrl;
+ unsigned int i;
+
+ argc = parse_options(argc, argv, options, bench_epoll_ctl_usage, 0);
+ if (argc) {
+ usage_with_options(bench_epoll_ctl_usage, options);
+ exit(EXIT_FAILURE);
+ }
+
+ sigfillset(&act.sa_mask);
+ act.sa_sigaction = toggle_done;
+ sigaction(SIGINT, &act, NULL);
+
+ cpu = perf_cpu_map__new(NULL);
+ if (!cpu)
+ goto errmem;
+
+ /* a single, main epoll instance */
+ epollfd = epoll_create(1);
+ if (epollfd < 0)
+ err(EXIT_FAILURE, "epoll_create");
+
+ /*
+ * Deal with nested epolls, if any.
+ */
+ if (nested)
+ nest_epollfd();
+
+ /* default to the number of CPUs */
+ if (!nthreads)
+ nthreads = cpu->nr;
+
+ worker = calloc(nthreads, sizeof(*worker));
+ if (!worker)
+ goto errmem;
+
+ if (getrlimit(RLIMIT_NOFILE, &prevrl))
+ err(EXIT_FAILURE, "getrlimit");
+ rl.rlim_cur = rl.rlim_max = nfds * nthreads * 2 + 50;
+ printinfo("Setting RLIMIT_NOFILE rlimit from %" PRIu64 " to: %" PRIu64 "\n",
+ (uint64_t)prevrl.rlim_max, (uint64_t)rl.rlim_max);
+ if (setrlimit(RLIMIT_NOFILE, &rl) < 0)
+ err(EXIT_FAILURE, "setrlimit");
+
+ printf("Run summary [PID %d]: %d threads doing epoll_ctl ops "
+ "%d file-descriptors for %d secs.\n\n",
+ getpid(), nthreads, nfds, nsecs);
+
+ for (i = 0; i < EPOLL_NR_OPS; i++)
+ init_stats(&all_stats[i]);
+
+ pthread_mutex_init(&thread_lock, NULL);
+ pthread_cond_init(&thread_parent, NULL);
+ pthread_cond_init(&thread_worker, NULL);
+
+ threads_starting = nthreads;
+
+ gettimeofday(&start, NULL);
+
+ do_threads(worker, cpu);
+
+ 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);
+
+ sleep(nsecs);
+ toggle_done(0, NULL, NULL);
+ printinfo("main thread: toggling done\n");
+
+ for (i = 0; i < nthreads; i++) {
+ ret = pthread_join(worker[i].thread, 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);
+
+ for (i = 0; i < nthreads; i++) {
+ unsigned long t[EPOLL_NR_OPS];
+
+ for (j = 0; j < EPOLL_NR_OPS; j++) {
+ t[j] = worker[i].ops[j];
+ update_stats(&all_stats[j], t[j]);
+ }
+
+ if (nfds == 1)
+ printf("[thread %2d] fdmap: %p [ add: %04ld; mod: %04ld; del: %04lds ops ]\n",
+ worker[i].tid, &worker[i].fdmap[0],
+ t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]);
+ else
+ printf("[thread %2d] fdmap: %p ... %p [ add: %04ld ops; mod: %04ld ops; del: %04ld ops ]\n",
+ worker[i].tid, &worker[i].fdmap[0],
+ &worker[i].fdmap[nfds-1],
+ t[OP_EPOLL_ADD], t[OP_EPOLL_MOD], t[OP_EPOLL_DEL]);
+ }
+
+ print_summary();
+
+ close(epollfd);
+ return ret;
+errmem:
+ err(EXIT_FAILURE, "calloc");
+}
+#endif // HAVE_EVENTFD
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
new file mode 100644
index 0000000..7af6944
--- /dev/null
+++ b/tools/perf/bench/epoll-wait.c
@@ -0,0 +1,542 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifdef HAVE_EVENTFD
+/*
+ * Copyright (C) 2018 Davidlohr Bueso.
+ *
+ * This program benchmarks concurrent epoll_wait(2) monitoring multiple
+ * file descriptors under one or two load balancing models. The first,
+ * and default, is the single/combined queueing (which refers to a single
+ * epoll instance for N worker threads):
+ *
+ * |---> [worker A]
+ * |---> [worker B]
+ * [combined queue] .---> [worker C]
+ * |---> [worker D]
+ * |---> [worker E]
+ *
+ * While the second model, enabled via --multiq option, uses multiple
+ * queueing (which refers to one epoll instance per worker). For example,
+ * short lived tcp connections in a high throughput httpd server will
+ * ditribute the accept()'ing connections across CPUs. In this case each
+ * worker does a limited amount of processing.
+ *
+ * [queue A] ---> [worker]
+ * [queue B] ---> [worker]
+ * [queue C] ---> [worker]
+ * [queue D] ---> [worker]
+ * [queue E] ---> [worker]
+ *
+ * Naturally, the single queue will enforce more concurrency on the epoll
+ * instance, and can therefore scale poorly compared to multiple queues.
+ * However, this is a benchmark raw data and must be taken with a grain of
+ * salt when choosing how to make use of sys_epoll.
+
+ * Each thread has a number of private, nonblocking file descriptors,
+ * referred to as fdmap. A writer thread will constantly be writing to
+ * the fdmaps of all threads, minimizing each threads's chances of
+ * epoll_wait not finding any ready read events and blocking as this
+ * is not what we want to stress. The size of the fdmap can be adjusted
+ * by the user; enlarging the value will increase the chances of
+ * epoll_wait(2) blocking as the lineal writer thread will take "longer",
+ * at least at a high level.
+ *
+ * Note that because fds are private to each thread, this workload does
+ * not stress scenarios where multiple tasks are awoken per ready IO; ie:
+ * EPOLLEXCLUSIVE semantics.
+ *
+ * The end result/metric is throughput: number of ops/second where an
+ * operation consists of:
+ *
+ * epoll_wait(2) + [others]
+ *
+ * ... where [others] is the cost of re-adding the fd (EPOLLET),
+ * or rearming it (EPOLLONESHOT).
+ *
+ *
+ * The purpose of this is program is that it be useful for measuring
+ * kernel related changes to the sys_epoll, and not comparing different
+ * IO polling methods, for example. Hence everything is very adhoc and
+ * outputs raw microbenchmark numbers. Also this uses eventfd, similar
+ * tools tend to use pipes or sockets, but the result is the same.
+ */
+
+/* For the CLR_() macros */
+#include <string.h>
+#include <pthread.h>
+#include <unistd.h>
+
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/epoll.h>
+#include <sys/eventfd.h>
+#include <sys/types.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
+
+#include "../util/stat.h"
+#include <subcmd/parse-options.h>
+#include "bench.h"
+
+#include <err.h>
+
+#define printinfo(fmt, arg...) \
+ do { if (__verbose) { printf(fmt, ## arg); fflush(stdout); } } while (0)
+
+static unsigned int nthreads = 0;
+static unsigned int nsecs = 8;
+struct timeval start, end, runtime;
+static bool wdone, done, __verbose, randomize, nonblocking;
+
+/*
+ * epoll related shared variables.
+ */
+
+/* Maximum number of nesting allowed inside epoll sets */
+#define EPOLL_MAXNESTS 4
+
+static int epollfd;
+static int *epollfdp;
+static bool noaffinity;
+static unsigned int nested = 0;
+static bool et; /* edge-trigger */
+static bool oneshot;
+static bool multiq; /* use an epoll instance per thread */
+
+/* amount of fds to monitor, per thread */
+static unsigned int nfds = 64;
+
+static pthread_mutex_t thread_lock;
+static unsigned int threads_starting;
+static struct stats throughput_stats;
+static pthread_cond_t thread_parent, thread_worker;
+
+struct worker {
+ int tid;
+ int epollfd; /* for --multiq */
+ pthread_t thread;
+ unsigned long ops;
+ int *fdmap;
+};
+
+static const struct option options[] = {
+ /* general benchmark options */
+ OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
+ OPT_UINTEGER('f', "nfds", &nfds, "Specify amount of file descriptors to monitor for each thread"),
+ OPT_BOOLEAN( 'n', "noaffinity", &noaffinity, "Disables CPU affinity"),
+ OPT_BOOLEAN('R', "randomize", &randomize, "Enable random write behaviour (default is lineal)"),
+ OPT_BOOLEAN( 'v', "verbose", &__verbose, "Verbose mode"),
+
+ /* epoll specific options */
+ OPT_BOOLEAN( 'm', "multiq", &multiq, "Use multiple epoll instances (one per thread)"),
+ OPT_BOOLEAN( 'B', "nonblocking", &nonblocking, "Nonblocking epoll_wait(2) behaviour"),
+ OPT_UINTEGER( 'N', "nested", &nested, "Nesting level epoll hierarchy (default is 0, no nesting)"),
+ OPT_BOOLEAN( 'S', "oneshot", &oneshot, "Use EPOLLONESHOT semantics"),
+ OPT_BOOLEAN( 'E', "edge", &et, "Use Edge-triggered interface (default is LT)"),
+
+ OPT_END()
+};
+
+static const char * const bench_epoll_wait_usage[] = {
+ "perf bench epoll wait <options>",
+ NULL
+};
+
+
+/*
+ * Arrange the N elements of ARRAY in random order.
+ * Only effective if N is much smaller than RAND_MAX;
+ * if this may not be the case, use a better random
+ * number generator. -- Ben Pfaff.
+ */
+static void shuffle(void *array, size_t n, size_t size)
+{
+ char *carray = array;
+ void *aux;
+ size_t i;
+
+ if (n <= 1)
+ return;
+
+ aux = calloc(1, size);
+ if (!aux)
+ err(EXIT_FAILURE, "calloc");
+
+ for (i = 1; i < n; ++i) {
+ size_t j = i + rand() / (RAND_MAX / (n - i) + 1);
+ j *= size;
+
+ memcpy(aux, &carray[j], size);
+ memcpy(&carray[j], &carray[i*size], size);
+ memcpy(&carray[i*size], aux, size);
+ }
+
+ free(aux);
+}
+
+
+static void *workerfn(void *arg)
+{
+ int fd, ret, r;
+ struct worker *w = (struct worker *) arg;
+ unsigned long ops = w->ops;
+ struct epoll_event ev;
+ uint64_t val;
+ int to = nonblocking? 0 : -1;
+ int efd = multiq ? w->epollfd : epollfd;
+
+ 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);
+
+ do {
+ /*
+ * Block undefinitely waiting for the IN event.
+ * In order to stress the epoll_wait(2) syscall,
+ * call it event per event, instead of a larger
+ * batch (max)limit.
+ */
+ do {
+ ret = epoll_wait(efd, &ev, 1, to);
+ } while (ret < 0 && errno == EINTR);
+ if (ret < 0)
+ err(EXIT_FAILURE, "epoll_wait");
+
+ fd = ev.data.fd;
+
+ do {
+ r = read(fd, &val, sizeof(val));
+ } while (!done && (r < 0 && errno == EAGAIN));
+
+ if (et) {
+ ev.events = EPOLLIN | EPOLLET;
+ ret = epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev);
+ }
+
+ if (oneshot) {
+ /* rearm the file descriptor with a new event mask */
+ ev.events |= EPOLLIN | EPOLLONESHOT;
+ ret = epoll_ctl(efd, EPOLL_CTL_MOD, fd, &ev);
+ }
+
+ ops++;
+ } while (!done);
+
+ if (multiq)
+ close(w->epollfd);
+
+ w->ops = ops;
+ return NULL;
+}
+
+static void nest_epollfd(struct worker *w)
+{
+ unsigned int i;
+ struct epoll_event ev;
+ int efd = multiq ? w->epollfd : epollfd;
+
+ if (nested > EPOLL_MAXNESTS)
+ nested = EPOLL_MAXNESTS;
+
+ epollfdp = calloc(nested, sizeof(*epollfdp));
+ if (!epollfdp)
+ err(EXIT_FAILURE, "calloc");
+
+ for (i = 0; i < nested; i++) {
+ epollfdp[i] = epoll_create(1);
+ if (epollfdp[i] < 0)
+ err(EXIT_FAILURE, "epoll_create");
+ }
+
+ ev.events = EPOLLHUP; /* anything */
+ ev.data.u64 = i; /* any number */
+
+ for (i = nested - 1; i; i--) {
+ if (epoll_ctl(epollfdp[i - 1], EPOLL_CTL_ADD,
+ epollfdp[i], &ev) < 0)
+ err(EXIT_FAILURE, "epoll_ctl");
+ }
+
+ if (epoll_ctl(efd, EPOLL_CTL_ADD, *epollfdp, &ev) < 0)
+ err(EXIT_FAILURE, "epoll_ctl");
+}
+
+static void toggle_done(int sig __maybe_unused,
+ siginfo_t *info __maybe_unused,
+ void *uc __maybe_unused)
+{
+ /* inform all threads that we're done for the day */
+ done = true;
+ gettimeofday(&end, NULL);
+ timersub(&end, &start, &runtime);
+}
+
+static void print_summary(void)
+{
+ unsigned long avg = avg_stats(&throughput_stats);
+ double stddev = stddev_stats(&throughput_stats);
+
+ printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
+ avg, rel_stddev_stats(stddev, avg),
+ (int) runtime.tv_sec);
+}
+
+static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
+{
+ pthread_attr_t thread_attr, *attrp = NULL;
+ cpu_set_t cpuset;
+ unsigned int i, j;
+ int ret = 0, events = EPOLLIN;
+
+ if (oneshot)
+ events |= EPOLLONESHOT;
+ if (et)
+ events |= EPOLLET;
+
+ printinfo("starting worker/consumer %sthreads%s\n",
+ noaffinity ? "":"CPU affinity ",
+ nonblocking ? " (nonblocking)":"");
+ if (!noaffinity)
+ pthread_attr_init(&thread_attr);
+
+ for (i = 0; i < nthreads; i++) {
+ struct worker *w = &worker[i];
+
+ if (multiq) {
+ w->epollfd = epoll_create(1);
+ if (w->epollfd < 0)
+ err(EXIT_FAILURE, "epoll_create");
+
+ if (nested)
+ nest_epollfd(w);
+ }
+
+ w->tid = i;
+ w->fdmap = calloc(nfds, sizeof(int));
+ if (!w->fdmap)
+ return 1;
+
+ for (j = 0; j < nfds; j++) {
+ int efd = multiq ? w->epollfd : epollfd;
+ struct epoll_event ev;
+
+ w->fdmap[j] = eventfd(0, EFD_NONBLOCK);
+ if (w->fdmap[j] < 0)
+ err(EXIT_FAILURE, "eventfd");
+
+ ev.data.fd = w->fdmap[j];
+ ev.events = events;
+
+ ret = epoll_ctl(efd, EPOLL_CTL_ADD,
+ w->fdmap[j], &ev);
+ if (ret < 0)
+ err(EXIT_FAILURE, "epoll_ctl");
+ }
+
+ if (!noaffinity) {
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+
+ ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
+ if (ret)
+ err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+ attrp = &thread_attr;
+ }
+
+ ret = pthread_create(&w->thread, attrp, workerfn,
+ (void *)(struct worker *) w);
+ if (ret)
+ err(EXIT_FAILURE, "pthread_create");
+ }
+
+ if (!noaffinity)
+ pthread_attr_destroy(&thread_attr);
+
+ return ret;
+}
+
+static void *writerfn(void *p)
+{
+ struct worker *worker = p;
+ size_t i, j, iter;
+ const uint64_t val = 1;
+ ssize_t sz;
+ struct timespec ts = { .tv_sec = 0,
+ .tv_nsec = 500 };
+
+ printinfo("starting writer-thread: doing %s writes ...\n",
+ randomize? "random":"lineal");
+
+ for (iter = 0; !wdone; iter++) {
+ if (randomize) {
+ shuffle((void *)worker, nthreads, sizeof(*worker));
+ }
+
+ for (i = 0; i < nthreads; i++) {
+ struct worker *w = &worker[i];
+
+ if (randomize) {
+ shuffle((void *)w->fdmap, nfds, sizeof(int));
+ }
+
+ for (j = 0; j < nfds; j++) {
+ do {
+ sz = write(w->fdmap[j], &val, sizeof(val));
+ } while (!wdone && (sz < 0 && errno == EAGAIN));
+ }
+ }
+
+ nanosleep(&ts, NULL);
+ }
+
+ printinfo("exiting writer-thread (total full-loops: %zd)\n", iter);
+ return NULL;
+}
+
+static int cmpworker(const void *p1, const void *p2)
+{
+
+ struct worker *w1 = (struct worker *) p1;
+ struct worker *w2 = (struct worker *) p2;
+ return w1->tid > w2->tid;
+}
+
+int bench_epoll_wait(int argc, const char **argv)
+{
+ int ret = 0;
+ struct sigaction act;
+ unsigned int i;
+ struct worker *worker = NULL;
+ struct perf_cpu_map *cpu;
+ pthread_t wthread;
+ struct rlimit rl, prevrl;
+
+ argc = parse_options(argc, argv, options, bench_epoll_wait_usage, 0);
+ if (argc) {
+ usage_with_options(bench_epoll_wait_usage, options);
+ exit(EXIT_FAILURE);
+ }
+
+ sigfillset(&act.sa_mask);
+ act.sa_sigaction = toggle_done;
+ sigaction(SIGINT, &act, NULL);
+
+ cpu = perf_cpu_map__new(NULL);
+ if (!cpu)
+ goto errmem;
+
+ /* a single, main epoll instance */
+ if (!multiq) {
+ epollfd = epoll_create(1);
+ if (epollfd < 0)
+ err(EXIT_FAILURE, "epoll_create");
+
+ /*
+ * Deal with nested epolls, if any.
+ */
+ if (nested)
+ nest_epollfd(NULL);
+ }
+
+ printinfo("Using %s queue model\n", multiq ? "multi" : "single");
+ printinfo("Nesting level(s): %d\n", nested);
+
+ /* default to the number of CPUs and leave one for the writer pthread */
+ if (!nthreads)
+ nthreads = cpu->nr - 1;
+
+ worker = calloc(nthreads, sizeof(*worker));
+ if (!worker) {
+ goto errmem;
+ }
+
+ if (getrlimit(RLIMIT_NOFILE, &prevrl))
+ err(EXIT_FAILURE, "getrlimit");
+ rl.rlim_cur = rl.rlim_max = nfds * nthreads * 2 + 50;
+ printinfo("Setting RLIMIT_NOFILE rlimit from %" PRIu64 " to: %" PRIu64 "\n",
+ (uint64_t)prevrl.rlim_max, (uint64_t)rl.rlim_max);
+ if (setrlimit(RLIMIT_NOFILE, &rl) < 0)
+ err(EXIT_FAILURE, "setrlimit");
+
+ printf("Run summary [PID %d]: %d threads monitoring%s on "
+ "%d file-descriptors for %d secs.\n\n",
+ getpid(), nthreads, oneshot ? " (EPOLLONESHOT semantics)": "", nfds, nsecs);
+
+ init_stats(&throughput_stats);
+ pthread_mutex_init(&thread_lock, NULL);
+ pthread_cond_init(&thread_parent, NULL);
+ pthread_cond_init(&thread_worker, NULL);
+
+ threads_starting = nthreads;
+
+ gettimeofday(&start, NULL);
+
+ do_threads(worker, cpu);
+
+ 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);
+
+ /*
+ * At this point the workers should be blocked waiting for read events
+ * to become ready. Launch the writer which will constantly be writing
+ * to each thread's fdmap.
+ */
+ ret = pthread_create(&wthread, NULL, writerfn,
+ (void *)(struct worker *) worker);
+ if (ret)
+ err(EXIT_FAILURE, "pthread_create");
+
+ sleep(nsecs);
+ toggle_done(0, NULL, NULL);
+ printinfo("main thread: toggling done\n");
+
+ sleep(1); /* meh */
+ wdone = true;
+ ret = pthread_join(wthread, 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);
+
+ /* sort the array back before reporting */
+ if (randomize)
+ qsort(worker, nthreads, sizeof(struct worker), cmpworker);
+
+ for (i = 0; i < nthreads; i++) {
+ unsigned long t = worker[i].ops/runtime.tv_sec;
+
+ update_stats(&throughput_stats, t);
+
+ if (nfds == 1)
+ printf("[thread %2d] fdmap: %p [ %04ld ops/sec ]\n",
+ worker[i].tid, &worker[i].fdmap[0], t);
+ else
+ printf("[thread %2d] fdmap: %p ... %p [ %04ld ops/sec ]\n",
+ worker[i].tid, &worker[i].fdmap[0],
+ &worker[i].fdmap[nfds-1], t);
+ }
+
+ print_summary();
+
+ close(epollfd);
+ return ret;
+errmem:
+ err(EXIT_FAILURE, "calloc");
+}
+#endif // HAVE_EVENTFD
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 9aa3a67..8ba0c33 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -18,13 +18,15 @@
#include <stdlib.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
+#include <linux/zalloc.h>
#include <sys/time.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
#include "../util/stat.h"
#include <subcmd/parse-options.h>
#include "bench.h"
#include "futex.h"
-#include "cpumap.h"
#include <err.h>
@@ -123,7 +125,7 @@
unsigned int i;
pthread_attr_t thread_attr;
struct worker *worker = NULL;
- struct cpu_map *cpu;
+ struct perf_cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
if (argc) {
@@ -131,7 +133,7 @@
exit(EXIT_FAILURE);
}
- cpu = cpu_map__new(NULL);
+ cpu = perf_cpu_map__new(NULL);
if (!cpu)
goto errmem;
@@ -214,7 +216,7 @@
&worker[i].futex[nfutexes-1], t);
}
- free(worker[i].futex);
+ zfree(&worker[i].futex);
}
print_summary();
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 8e9c475..d0cae81 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -12,10 +12,12 @@
#include <subcmd/parse-options.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
+#include <linux/zalloc.h>
#include <errno.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
#include "bench.h"
#include "futex.h"
-#include "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -115,7 +117,7 @@
}
static void create_threads(struct worker *w, pthread_attr_t thread_attr,
- struct cpu_map *cpu)
+ struct perf_cpu_map *cpu)
{
cpu_set_t cpuset;
unsigned int i;
@@ -149,13 +151,13 @@
unsigned int i;
struct sigaction act;
pthread_attr_t thread_attr;
- struct cpu_map *cpu;
+ struct perf_cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0);
if (argc)
goto err;
- cpu = cpu_map__new(NULL);
+ cpu = perf_cpu_map__new(NULL);
if (!cpu)
err(EXIT_FAILURE, "calloc");
@@ -217,7 +219,7 @@
worker[i].tid, worker[i].futex, t);
if (multi)
- free(worker[i].futex);
+ zfree(&worker[i].futex);
}
print_summary();
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index fc692ef..a00a689 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -20,9 +20,10 @@
#include <linux/kernel.h>
#include <linux/time64.h>
#include <errno.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
#include "bench.h"
#include "futex.h"
-#include "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -84,7 +85,7 @@
}
static void block_threads(pthread_t *w,
- pthread_attr_t thread_attr, struct cpu_map *cpu)
+ pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
{
cpu_set_t cpuset;
unsigned int i;
@@ -117,13 +118,13 @@
unsigned int i, j;
struct sigaction act;
pthread_attr_t thread_attr;
- struct cpu_map *cpu;
+ struct perf_cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
if (argc)
goto err;
- cpu = cpu_map__new(NULL);
+ cpu = perf_cpu_map__new(NULL);
if (!cpu)
err(EXIT_FAILURE, "cpu_map__new");
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 69d8fdc..a053cf2 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -29,7 +29,8 @@
#include <linux/time64.h>
#include <errno.h>
#include "futex.h"
-#include "cpumap.h"
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
#include <err.h>
#include <stdlib.h>
@@ -138,7 +139,7 @@
}
static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
- struct cpu_map *cpu)
+ struct perf_cpu_map *cpu)
{
cpu_set_t cpuset;
unsigned int i;
@@ -224,7 +225,7 @@
struct sigaction act;
pthread_attr_t thread_attr;
struct thread_data *waking_worker;
- struct cpu_map *cpu;
+ struct perf_cpu_map *cpu;
argc = parse_options(argc, argv, options,
bench_futex_wake_parallel_usage, 0);
@@ -237,7 +238,7 @@
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
- cpu = cpu_map__new(NULL);
+ cpu = perf_cpu_map__new(NULL);
if (!cpu)
err(EXIT_FAILURE, "calloc");
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index e8181ad..df81009 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -20,9 +20,10 @@
#include <linux/kernel.h>
#include <linux/time64.h>
#include <errno.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
#include "bench.h"
#include "futex.h"
-#include "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -90,7 +91,7 @@
}
static void block_threads(pthread_t *w,
- pthread_attr_t thread_attr, struct cpu_map *cpu)
+ pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
{
cpu_set_t cpuset;
unsigned int i;
@@ -123,7 +124,7 @@
unsigned int i, j;
struct sigaction act;
pthread_attr_t thread_attr;
- struct cpu_map *cpu;
+ struct perf_cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
if (argc) {
@@ -131,7 +132,7 @@
exit(EXIT_FAILURE);
}
- cpu = cpu_map__new(NULL);
+ cpu = perf_cpu_map__new(NULL);
if (!cpu)
err(EXIT_FAILURE, "calloc");
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index db4853f..31b53cc 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -86,16 +86,4 @@
return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
val, opflags);
}
-
-#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
-#include <pthread.h>
-#include <linux/compiler.h>
-static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
- size_t cpusetsize __maybe_unused,
- cpu_set_t *cpuset __maybe_unused)
-{
- return 0;
-}
-#endif
-
#endif /* _FUTEX_H */
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 0251dd3..9235b76 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -8,8 +8,7 @@
*/
#include "debug.h"
-#include "../perf.h"
-#include "../util/util.h"
+#include "../perf-sys.h"
#include <subcmd/parse-options.h>
#include "../util/header.h"
#include "../util/cloexec.h"
@@ -21,9 +20,11 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <unistd.h>
#include <sys/time.h>
#include <errno.h>
#include <linux/time64.h>
+#include <linux/zalloc.h>
#define K 1024
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 4419551..5797253 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -9,9 +9,6 @@
/* For the CLR_() macros */
#include <pthread.h>
-#include "../perf.h"
-#include "../builtin.h"
-#include "../util/util.h"
#include <subcmd/parse-options.h>
#include "../util/cloexec.h"
@@ -34,10 +31,16 @@
#include <sys/types.h>
#include <linux/kernel.h>
#include <linux/time64.h>
+#include <linux/numa.h>
+#include <linux/zalloc.h>
#include <numa.h>
#include <numaif.h>
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
/*
* Regular printout to the terminal, supressed if -q is specified:
*/
@@ -298,7 +301,7 @@
CPU_ZERO(&mask);
- if (target_node == -1) {
+ if (target_node == NUMA_NO_NODE) {
for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
CPU_SET(cpu, &mask);
} else {
@@ -339,7 +342,7 @@
unsigned long nodemask;
int ret;
- if (node == -1)
+ if (node == NUMA_NO_NODE)
return;
BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8);
@@ -374,8 +377,10 @@
/* Allocate and initialize all memory on CPU#0: */
if (init_cpu0) {
- orig_mask = bind_to_node(0);
- bind_to_memnode(0);
+ int node = numa_node_of_cpu(0);
+
+ orig_mask = bind_to_node(node);
+ bind_to_memnode(node);
}
bytes = bytes0 + HPSIZE;
@@ -1363,7 +1368,7 @@
int cpu;
/* Allow all nodes by default: */
- td->bind_node = -1;
+ td->bind_node = NUMA_NO_NODE;
/* Allow all CPUs by default: */
CPU_ZERO(&td->bind_cpumask);
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index f9d7641..97e4a4f 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -10,10 +10,7 @@
*
*/
-#include "../perf.h"
-#include "../util/util.h"
#include <subcmd/parse-options.h>
-#include "../builtin.h"
#include "bench.h"
/* Test groups of 20 processes spraying to 20 receivers */
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 0591be0..3c88d1f 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -9,10 +9,7 @@
* http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
* Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
*/
-#include "../perf.h"
-#include "../util/util.h"
#include <subcmd/parse-options.h>
-#include "../builtin.h"
#include "bench.h"
#include <unistd.h>