linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: Peter Zijlstra <peterz@infradead.org>,
	"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
	Boqun Feng <boqun.feng@gmail.com>
Cc: linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>,
	Andy Lutomirski <luto@amacapital.net>,
	Dave Watson <davejwatson@fb.com>, Paul Turner <pjt@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Russell King <linux@arm.linux.org.uk>,
	Ingo Molnar <mingo@redhat.com>, "H . Peter Anvin" <hpa@zytor.com>,
	Andi Kleen <andi@firstfloor.org>, Chris Lameter <cl@linux.com>,
	Ben Maurer <bmaurer@fb.com>, Steven Rostedt <rostedt@goodmis.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Michael Kerrisk <mtk.manpages@gmail.com>,
	Joel Fernandes <joelaf@google.com>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Shuah Khan <shuah@kernel.org>,
	linux-kselftest@vger.kernel.org
Subject: [RFC PATCH for 4.21 15/16] cpu-opv/selftests: Provide parametrized tests
Date: Wed, 10 Oct 2018 15:19:35 -0400	[thread overview]
Message-ID: <20181010191936.7495-16-mathieu.desnoyers@efficios.com> (raw)
In-Reply-To: <20181010191936.7495-1-mathieu.desnoyers@efficios.com>

"param_test" is a parametrizable percpu operations test using
both restartable sequences and cpu_opv. See the "--help" output for
usage.

"param_test_benchmark" is the same as "param_test", but it removes
testing book-keeping code to allow accurate benchmarks.

"param_test_compare_twice" is the same as "param_test", but it performs
each comparison within rseq critical section twice, thus validating
invariants. If any of the second comparisons fails, an error message
is printed and the test aborts.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/cpu-opv/param_test.c | 1187 ++++++++++++++++++++++++++
 1 file changed, 1187 insertions(+)
 create mode 100644 tools/testing/selftests/cpu-opv/param_test.c

diff --git a/tools/testing/selftests/cpu-opv/param_test.c b/tools/testing/selftests/cpu-opv/param_test.c
new file mode 100644
index 000000000000..c62e75f07385
--- /dev/null
+++ b/tools/testing/selftests/cpu-opv/param_test.c
@@ -0,0 +1,1187 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <poll.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
+#include <stddef.h>
+
+static inline pid_t gettid(void)
+{
+	return syscall(__NR_gettid);
+}
+
+#define NR_INJECT	9
+static int loop_cnt[NR_INJECT + 1];
+
+static int loop_cnt_1 asm("asm_loop_cnt_1") __attribute__((used));
+static int loop_cnt_2 asm("asm_loop_cnt_2") __attribute__((used));
+static int loop_cnt_3 asm("asm_loop_cnt_3") __attribute__((used));
+static int loop_cnt_4 asm("asm_loop_cnt_4") __attribute__((used));
+static int loop_cnt_5 asm("asm_loop_cnt_5") __attribute__((used));
+static int loop_cnt_6 asm("asm_loop_cnt_6") __attribute__((used));
+
+static int opt_modulo, verbose;
+
+static int opt_yield, opt_signal, opt_sleep,
+		opt_disable_rseq, opt_threads = 200,
+		opt_disable_mod = 0, opt_test = 's', opt_mb = 0;
+
+#ifndef RSEQ_SKIP_FASTPATH
+static long long opt_reps = 5000;
+#else
+static long long opt_reps = 100;
+#endif
+
+static __thread __attribute__((tls_model("initial-exec")))
+unsigned int signals_delivered;
+
+#ifndef BENCHMARK
+
+static __thread __attribute__((tls_model("initial-exec"), unused))
+unsigned int yield_mod_cnt, nr_abort;
+
+#define printf_verbose(fmt, ...)			\
+	do {						\
+		if (verbose)				\
+			printf(fmt, ## __VA_ARGS__);	\
+	} while (0)
+
+#ifdef __i386__
+
+#define INJECT_ASM_REG	"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \
+	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+	"jz 333f\n\t" \
+	"222:\n\t" \
+	"dec %%" INJECT_ASM_REG "\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__x86_64__)
+
+#define INJECT_ASM_REG_P	"rax"
+#define INJECT_ASM_REG		"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG_P \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \
+	"mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \
+	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
+	"jz 333f\n\t" \
+	"222:\n\t" \
+	"dec %%" INJECT_ASM_REG "\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
+#elif defined(__ARMEL__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"r4"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"ldr " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"cmp " INJECT_ASM_REG ", #0\n\t" \
+	"beq 333f\n\t" \
+	"222:\n\t" \
+	"subs " INJECT_ASM_REG ", #1\n\t" \
+	"bne 222b\n\t" \
+	"333:\n\t"
+
+#elif __PPC__
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"r18"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"lwz %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"cmpwi %%" INJECT_ASM_REG ", 0\n\t" \
+	"beq 333f\n\t" \
+	"222:\n\t" \
+	"subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \
+	"bne 222b\n\t" \
+	"333:\n\t"
+#else
+#error unsupported target
+#endif
+
+#define RSEQ_INJECT_FAILED \
+	nr_abort++;
+
+#define RSEQ_INJECT_C(n) \
+{ \
+	int loc_i, loc_nr_loops = loop_cnt[n]; \
+	\
+	for (loc_i = 0; loc_i < loc_nr_loops; loc_i++) { \
+		rseq_barrier(); \
+	} \
+	if (loc_nr_loops == -1 && opt_modulo) { \
+		if (yield_mod_cnt == opt_modulo - 1) { \
+			if (opt_sleep > 0) \
+				poll(NULL, 0, opt_sleep); \
+			if (opt_yield) \
+				sched_yield(); \
+			if (opt_signal) \
+				raise(SIGUSR1); \
+			yield_mod_cnt = 0; \
+		} else { \
+			yield_mod_cnt++; \
+		} \
+	} \
+}
+
+#else
+
+#define printf_verbose(fmt, ...)
+
+#endif /* BENCHMARK */
+
+#include "percpu-op.h"
+
+struct percpu_lock_entry {
+	intptr_t v;
+} __attribute__((aligned(128)));
+
+struct percpu_lock {
+	struct percpu_lock_entry c[CPU_SETSIZE];
+};
+
+struct test_data_entry {
+	intptr_t count;
+} __attribute__((aligned(128)));
+
+struct spinlock_test_data {
+	struct percpu_lock lock;
+	struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct spinlock_thread_test_data {
+	struct spinlock_test_data *data;
+	long long reps;
+	int reg;
+};
+
+struct inc_test_data {
+	struct test_data_entry c[CPU_SETSIZE];
+};
+
+struct inc_thread_test_data {
+	struct inc_test_data *data;
+	long long reps;
+	int reg;
+};
+
+struct percpu_list_node {
+	intptr_t data;
+	struct percpu_list_node *next;
+};
+
+struct percpu_list_entry {
+	struct percpu_list_node *head;
+} __attribute__((aligned(128)));
+
+struct percpu_list {
+	struct percpu_list_entry c[CPU_SETSIZE];
+};
+
+#define BUFFER_ITEM_PER_CPU	100
+
+struct percpu_buffer_node {
+	intptr_t data;
+};
+
+struct percpu_buffer_entry {
+	intptr_t offset;
+	intptr_t buflen;
+	struct percpu_buffer_node **array;
+} __attribute__((aligned(128)));
+
+struct percpu_buffer {
+	struct percpu_buffer_entry c[CPU_SETSIZE];
+};
+
+#define MEMCPY_BUFFER_ITEM_PER_CPU	100
+
+struct percpu_memcpy_buffer_node {
+	intptr_t data1;
+	uint64_t data2;
+};
+
+struct percpu_memcpy_buffer_entry {
+	intptr_t offset;
+	intptr_t buflen;
+	struct percpu_memcpy_buffer_node *array;
+} __attribute__((aligned(128)));
+
+struct percpu_memcpy_buffer {
+	struct percpu_memcpy_buffer_entry c[CPU_SETSIZE];
+};
+
+/* A simple percpu spinlock. */
+static void rseq_percpu_lock(struct percpu_lock *lock, int cpu)
+{
+	for (;;) {
+		int ret;
+
+		ret = percpu_cmpeqv_storev(&lock->c[cpu].v,
+					   0, 1, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	/*
+	 * Acquire semantic when taking lock after control dependency.
+	 * Matches rseq_smp_store_release().
+	 */
+	rseq_smp_acquire__after_ctrl_dep();
+}
+
+static void rseq_percpu_unlock(struct percpu_lock *lock, int cpu)
+{
+	assert(lock->c[cpu].v == 1);
+	/*
+	 * Release lock, with release semantic. Matches
+	 * rseq_smp_acquire__after_ctrl_dep().
+	 */
+	rseq_smp_store_release(&lock->c[cpu].v, 0);
+}
+
+void *test_percpu_spinlock_thread(void *arg)
+{
+	struct spinlock_thread_test_data *thread_data = arg;
+	struct spinlock_test_data *data = thread_data->data;
+	long long i, reps;
+
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_register_current_thread())
+		abort();
+	reps = thread_data->reps;
+	for (i = 0; i < reps; i++) {
+		int cpu = rseq_cpu_start();
+
+		rseq_percpu_lock(&data->lock, cpu);
+		data->c[cpu].count++;
+		rseq_percpu_unlock(&data->lock, cpu);
+#ifndef BENCHMARK
+		if (i != 0 && !(i % (reps / 10)))
+			printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+#endif
+	}
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_unregister_current_thread())
+		abort();
+	return NULL;
+}
+
+/*
+ * A simple test which implements a sharded counter using a per-cpu
+ * lock.  Obviously real applications might prefer to simply use a
+ * per-cpu increment; however, this is reasonable for a test and the
+ * lock can be extended to synchronize more complicated operations.
+ */
+void test_percpu_spinlock(void)
+{
+	const int num_threads = opt_threads;
+	int i, ret;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct spinlock_test_data data;
+	struct spinlock_thread_test_data thread_data[num_threads];
+
+	memset(&data, 0, sizeof(data));
+	for (i = 0; i < num_threads; i++) {
+		thread_data[i].reps = opt_reps;
+		if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+			thread_data[i].reg = 1;
+		else
+			thread_data[i].reg = 0;
+		thread_data[i].data = &data;
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_spinlock_thread,
+				     &thread_data[i]);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void *test_percpu_inc_thread(void *arg)
+{
+	struct inc_thread_test_data *thread_data = arg;
+	struct inc_test_data *data = thread_data->data;
+	long long i, reps;
+
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_register_current_thread())
+		abort();
+	reps = thread_data->reps;
+	for (i = 0; i < reps; i++) {
+		int cpu, ret;
+
+		cpu = rseq_cpu_start();
+		ret = percpu_addv(&data->c[cpu].count, 1, cpu);
+		if (rseq_unlikely(ret)) {
+			perror("cpu_opv");
+			abort();
+		}
+#ifndef BENCHMARK
+		if (i != 0 && !(i % (reps / 10)))
+			printf_verbose("tid %d: count %lld\n", (int) gettid(), i);
+#endif
+	}
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && thread_data->reg &&
+	    rseq_unregister_current_thread())
+		abort();
+	return NULL;
+}
+
+void test_percpu_inc(void)
+{
+	const int num_threads = opt_threads;
+	int i, ret;
+	uint64_t sum;
+	pthread_t test_threads[num_threads];
+	struct inc_test_data data;
+	struct inc_thread_test_data thread_data[num_threads];
+
+	memset(&data, 0, sizeof(data));
+	for (i = 0; i < num_threads; i++) {
+		thread_data[i].reps = opt_reps;
+		if (opt_disable_mod <= 0 || (i % opt_disable_mod))
+			thread_data[i].reg = 1;
+		else
+			thread_data[i].reg = 0;
+		thread_data[i].data = &data;
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_inc_thread,
+				     &thread_data[i]);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	sum = 0;
+	for (i = 0; i < CPU_SETSIZE; i++)
+		sum += data.c[i].count;
+
+	assert(sum == (uint64_t)opt_reps * num_threads);
+}
+
+void percpu_list_push(struct percpu_list *list,
+		      struct percpu_list_node *node,
+		      int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr, newval, expect;
+		int ret;
+
+		/* Load list->c[cpu].head with single-copy atomicity. */
+		expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head);
+		newval = (intptr_t)node;
+		targetptr = (intptr_t *)&list->c[cpu].head;
+		node->next = (struct percpu_list_node *)expect;
+		ret = percpu_cmpeqv_storev(targetptr, expect, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+}
+
+/*
+ * Unlike a traditional lock-less linked list; the availability of a
+ * rseq primitive allows us to implement pop without concerns over
+ * ABA-type races.
+ */
+struct percpu_list_node *percpu_list_pop(struct percpu_list *list,
+					 int cpu)
+{
+	struct percpu_list_node *head;
+	intptr_t *targetptr, expectnot, *load;
+	off_t offset;
+	int ret;
+
+	targetptr = (intptr_t *)&list->c[cpu].head;
+	expectnot = (intptr_t)NULL;
+	offset = offsetof(struct percpu_list_node, next);
+	load = (intptr_t *)&head;
+	ret = percpu_cmpnev_storeoffp_load(targetptr, expectnot,
+					   offset, load, cpu);
+	if (rseq_unlikely(ret < 0)) {
+		perror("cpu_opv");
+		abort();
+	}
+	if (ret > 0)
+		return NULL;
+	return head;
+}
+
+void *test_percpu_list_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_list *list = (struct percpu_list *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_list_node *node;
+
+		node = percpu_list_pop(list, rseq_cpu_start());
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (node)
+			percpu_list_push(list, node, rseq_cpu_start());
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu linked list from many threads.  */
+void test_percpu_list(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_list list;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&list, 0, sizeof(list));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		for (j = 1; j <= 100; j++) {
+			struct percpu_list_node *node;
+
+			expected_sum += j;
+
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			node->next = list.c[i].head;
+			list.c[i].head = node;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_list_thread, &list);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = percpu_list_pop(&list, i))) {
+			sum += node->data;
+			free(node);
+		}
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+bool percpu_buffer_push(struct percpu_buffer *buffer,
+			struct percpu_buffer_node *node,
+			int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr_spec, newval_spec;
+		intptr_t *targetptr_final, newval_final;
+		intptr_t offset;
+		int ret;
+
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == buffer->c[cpu].buflen)
+			return false;
+		newval_spec = (intptr_t)node;
+		targetptr_spec = (intptr_t *)&buffer->c[cpu].array[offset];
+		newval_final = offset + 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		if (opt_mb)
+			ret = percpu_cmpeqv_storev_storev_release(
+				targetptr_final, offset, targetptr_spec,
+				newval_spec, newval_final, cpu);
+		else
+			ret = percpu_cmpeqv_storev_storev(targetptr_final,
+				offset, targetptr_spec, newval_spec,
+				newval_final, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return true;
+}
+
+struct percpu_buffer_node *percpu_buffer_pop(struct percpu_buffer *buffer,
+					     int cpu)
+{
+	struct percpu_buffer_node *head;
+
+	for (;;) {
+		intptr_t *targetptr, newval;
+		intptr_t offset;
+		int ret;
+
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == 0)
+			return NULL;
+		head = RSEQ_READ_ONCE(buffer->c[cpu].array[offset - 1]);
+		newval = offset - 1;
+		targetptr = (intptr_t *)&buffer->c[cpu].offset;
+		ret = percpu_cmpeqv_cmpeqv_storev(targetptr, offset,
+			(intptr_t *)&buffer->c[cpu].array[offset - 1],
+			(intptr_t)head, newval, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return head;
+}
+
+void *test_percpu_buffer_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_buffer *buffer = (struct percpu_buffer *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_buffer_node *node;
+
+		node = percpu_buffer_pop(buffer, rseq_cpu_start());
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (node) {
+			if (!percpu_buffer_push(buffer, node,
+						rseq_cpu_start())) {
+				/* Should increase buffer size. */
+				abort();
+			}
+		}
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads.  */
+void test_percpu_buffer(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_buffer buffer;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&buffer, 0, sizeof(buffer));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		/* Worse-case is every item in same CPU. */
+		buffer.c[i].array =
+			malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+			       BUFFER_ITEM_PER_CPU);
+		assert(buffer.c[i].array);
+		buffer.c[i].buflen = CPU_SETSIZE * BUFFER_ITEM_PER_CPU;
+		for (j = 1; j <= BUFFER_ITEM_PER_CPU; j++) {
+			struct percpu_buffer_node *node;
+
+			expected_sum += j;
+
+			/*
+			 * We could theoretically put the word-sized
+			 * "data" directly in the buffer. However, we
+			 * want to model objects that would not fit
+			 * within a single word, so allocate an object
+			 * for each node.
+			 */
+			node = malloc(sizeof(*node));
+			assert(node);
+			node->data = j;
+			buffer.c[i].array[j - 1] = node;
+			buffer.c[i].offset++;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_buffer_thread, &buffer);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_buffer_node *node;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while ((node = percpu_buffer_pop(&buffer, i))) {
+			sum += node->data;
+			free(node);
+		}
+		free(buffer.c[i].array);
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+bool percpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer,
+			       struct percpu_memcpy_buffer_node item, int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr_final, newval_final, offset;
+		char *destptr, *srcptr;
+		size_t copylen;
+		int ret;
+
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == buffer->c[cpu].buflen)
+			return false;
+		destptr = (char *)&buffer->c[cpu].array[offset];
+		srcptr = (char *)&item;
+		/* copylen must be <= 4kB. */
+		copylen = sizeof(item);
+		newval_final = offset + 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		if (opt_mb)
+			ret = percpu_cmpeqv_memcpy_storev_release(
+				targetptr_final, offset,
+				destptr, srcptr, copylen,
+				newval_final, cpu);
+		else
+			ret = percpu_cmpeqv_memcpy_storev(targetptr_final,
+				offset, destptr, srcptr, copylen,
+				newval_final, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return true;
+}
+
+bool percpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer,
+		struct percpu_memcpy_buffer_node *item, int cpu)
+{
+	for (;;) {
+		intptr_t *targetptr_final, newval_final, offset;
+		char *destptr, *srcptr;
+		size_t copylen;
+		int ret;
+
+		/* Load offset with single-copy atomicity. */
+		offset = RSEQ_READ_ONCE(buffer->c[cpu].offset);
+		if (offset == 0)
+			return false;
+		destptr = (char *)item;
+		srcptr = (char *)&buffer->c[cpu].array[offset - 1];
+		/* copylen must be <= 4kB. */
+		copylen = sizeof(*item);
+		newval_final = offset - 1;
+		targetptr_final = &buffer->c[cpu].offset;
+		ret = percpu_cmpeqv_memcpy_storev(targetptr_final,
+			offset, destptr, srcptr, copylen,
+			newval_final, cpu);
+		if (rseq_likely(!ret))
+			break;
+		if (rseq_unlikely(ret < 0)) {
+			perror("cpu_opv");
+			abort();
+		}
+		/* Retry if comparison fails. */
+	}
+	return true;
+}
+
+void *test_percpu_memcpy_buffer_thread(void *arg)
+{
+	long long i, reps;
+	struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		abort();
+
+	reps = opt_reps;
+	for (i = 0; i < reps; i++) {
+		struct percpu_memcpy_buffer_node item;
+		bool result;
+
+		result = percpu_memcpy_buffer_pop(buffer, &item,
+						  rseq_cpu_start());
+		if (opt_yield)
+			sched_yield();  /* encourage shuffling */
+		if (result) {
+			if (!percpu_memcpy_buffer_push(buffer, item,
+						       rseq_cpu_start())) {
+				/* Should increase buffer size. */
+				abort();
+			}
+		}
+	}
+
+	printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n",
+		       (int) gettid(), nr_abort, signals_delivered);
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+
+	return NULL;
+}
+
+/* Simultaneous modification to a per-cpu buffer from many threads.  */
+void test_percpu_memcpy_buffer(void)
+{
+	const int num_threads = opt_threads;
+	int i, j, ret;
+	uint64_t sum = 0, expected_sum = 0;
+	struct percpu_memcpy_buffer buffer;
+	pthread_t test_threads[num_threads];
+	cpu_set_t allowed_cpus;
+
+	memset(&buffer, 0, sizeof(buffer));
+
+	/* Generate list entries for every usable cpu. */
+	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+		/* Worse-case is every item in same CPU. */
+		buffer.c[i].array =
+			malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE *
+			       MEMCPY_BUFFER_ITEM_PER_CPU);
+		assert(buffer.c[i].array);
+		buffer.c[i].buflen = CPU_SETSIZE * MEMCPY_BUFFER_ITEM_PER_CPU;
+		for (j = 1; j <= MEMCPY_BUFFER_ITEM_PER_CPU; j++) {
+			expected_sum += 2 * j + 1;
+
+			/*
+			 * We could theoretically put the word-sized
+			 * "data" directly in the buffer. However, we
+			 * want to model objects that would not fit
+			 * within a single word, so allocate an object
+			 * for each node.
+			 */
+			buffer.c[i].array[j - 1].data1 = j;
+			buffer.c[i].array[j - 1].data2 = j + 1;
+			buffer.c[i].offset++;
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&test_threads[i], NULL,
+				     test_percpu_memcpy_buffer_thread,
+				     &buffer);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(test_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_memcpy_buffer_node item;
+
+		if (!CPU_ISSET(i, &allowed_cpus))
+			continue;
+
+		while (percpu_memcpy_buffer_pop(&buffer, &item, i)) {
+			sum += item.data1;
+			sum += item.data2;
+		}
+		free(buffer.c[i].array);
+	}
+
+	/*
+	 * All entries should now be accounted for (unless some external
+	 * actor is interfering with our allowed affinity while this
+	 * test is running).
+	 */
+	assert(sum == expected_sum);
+}
+
+static void test_signal_interrupt_handler(int signo)
+{
+	signals_delivered++;
+}
+
+static int set_signal_handler(void)
+{
+	int ret = 0;
+	struct sigaction sa;
+	sigset_t sigset;
+
+	ret = sigemptyset(&sigset);
+	if (ret < 0) {
+		perror("sigemptyset");
+		return ret;
+	}
+
+	sa.sa_handler = test_signal_interrupt_handler;
+	sa.sa_mask = sigset;
+	sa.sa_flags = 0;
+	ret = sigaction(SIGUSR1, &sa, NULL);
+	if (ret < 0) {
+		perror("sigaction");
+		return ret;
+	}
+
+	printf_verbose("Signal handler set for SIGUSR1\n");
+
+	return ret;
+}
+
+static void show_usage(int argc, char **argv)
+{
+	printf("Usage : %s <OPTIONS>\n",
+		argv[0]);
+	printf("OPTIONS:\n");
+	printf("	[-1 loops] Number of loops for delay injection 1\n");
+	printf("	[-2 loops] Number of loops for delay injection 2\n");
+	printf("	[-3 loops] Number of loops for delay injection 3\n");
+	printf("	[-4 loops] Number of loops for delay injection 4\n");
+	printf("	[-5 loops] Number of loops for delay injection 5\n");
+	printf("	[-6 loops] Number of loops for delay injection 6\n");
+	printf("	[-7 loops] Number of loops for delay injection 7 (-1 to enable -m)\n");
+	printf("	[-8 loops] Number of loops for delay injection 8 (-1 to enable -m)\n");
+	printf("	[-9 loops] Number of loops for delay injection 9 (-1 to enable -m)\n");
+	printf("	[-m N] Yield/sleep/kill every modulo N (default 0: disabled) (>= 0)\n");
+	printf("	[-y] Yield\n");
+	printf("	[-k] Kill thread with signal\n");
+	printf("	[-s S] S: =0: disabled (default), >0: sleep time (ms)\n");
+	printf("	[-t N] Number of threads (default 200)\n");
+	printf("	[-r N] Number of repetitions per thread (default 5000)\n");
+	printf("	[-d] Disable rseq system call (no initialization)\n");
+	printf("	[-D M] Disable rseq for each M threads\n");
+	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement\n");
+	printf("	[-M] Push into buffer and memcpy buffer with memory barriers.\n");
+	printf("	[-v] Verbose output.\n");
+	printf("	[-h] Show this help.\n");
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		if (argv[i][0] != '-')
+			continue;
+		switch (argv[i][1]) {
+		case '1':
+		case '2':
+		case '3':
+		case '4':
+		case '5':
+		case '6':
+		case '7':
+		case '8':
+		case '9':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			loop_cnt[argv[i][1] - '0'] = atol(argv[i + 1]);
+			i++;
+			break;
+		case 'm':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_modulo = atol(argv[i + 1]);
+			if (opt_modulo < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 's':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_sleep = atol(argv[i + 1]);
+			if (opt_sleep < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'y':
+			opt_yield = 1;
+			break;
+		case 'k':
+			opt_signal = 1;
+			break;
+		case 'd':
+			opt_disable_rseq = 1;
+			break;
+		case 'D':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_disable_mod = atol(argv[i + 1]);
+			if (opt_disable_mod < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 't':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_threads = atol(argv[i + 1]);
+			if (opt_threads < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'r':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_reps = atoll(argv[i + 1]);
+			if (opt_reps < 0) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'h':
+			show_usage(argc, argv);
+			goto end;
+		case 'T':
+			if (argc < i + 2) {
+				show_usage(argc, argv);
+				goto error;
+			}
+			opt_test = *argv[i + 1];
+			switch (opt_test) {
+			case 's':
+			case 'l':
+			case 'i':
+			case 'b':
+			case 'm':
+				break;
+			default:
+				show_usage(argc, argv);
+				goto error;
+			}
+			i++;
+			break;
+		case 'v':
+			verbose = 1;
+			break;
+		case 'M':
+			opt_mb = 1;
+			break;
+		default:
+			show_usage(argc, argv);
+			goto error;
+		}
+	}
+
+	loop_cnt_1 = loop_cnt[1];
+	loop_cnt_2 = loop_cnt[2];
+	loop_cnt_3 = loop_cnt[3];
+	loop_cnt_4 = loop_cnt[4];
+	loop_cnt_5 = loop_cnt[5];
+	loop_cnt_6 = loop_cnt[6];
+
+	if (set_signal_handler())
+		goto error;
+
+	if (!opt_disable_rseq && rseq_register_current_thread())
+		goto error;
+	switch (opt_test) {
+	case 's':
+		printf_verbose("spinlock\n");
+		test_percpu_spinlock();
+		break;
+	case 'l':
+		printf_verbose("linked list\n");
+		test_percpu_list();
+		break;
+	case 'b':
+		printf_verbose("buffer\n");
+		test_percpu_buffer();
+		break;
+	case 'm':
+		printf_verbose("memcpy buffer\n");
+		test_percpu_memcpy_buffer();
+		break;
+	case 'i':
+		printf_verbose("counter increment\n");
+		test_percpu_inc();
+		break;
+	}
+	if (!opt_disable_rseq && rseq_unregister_current_thread())
+		abort();
+end:
+	return 0;
+
+error:
+	return -1;
+}
-- 
2.11.0


  parent reply	other threads:[~2018-10-10 19:20 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-10 19:19 [RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 01/16] rseq/selftests: Add reference counter to coexist with glibc Mathieu Desnoyers
2018-10-11 10:37   ` Szabolcs Nagy
2018-10-11 15:13     ` Mathieu Desnoyers
2018-10-11 16:20       ` Szabolcs Nagy
2018-10-11 16:37         ` Mathieu Desnoyers
2018-10-11 17:04           ` Szabolcs Nagy
2018-10-11 19:42             ` Mathieu Desnoyers
2018-10-12  9:59               ` Szabolcs Nagy
2018-10-23 14:59                 ` Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 02/16] rseq/selftests: Adapt number of threads to the number of detected cpus Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 03/16] sched: Implement push_task_to_cpu (v2) Mathieu Desnoyers
2018-10-17  6:51   ` Srikar Dronamraju
2018-10-17 15:09     ` Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 04/16] mm: Introduce vm_map_user_ram, vm_unmap_user_ram Mathieu Desnoyers
2018-10-16 18:30   ` Steven Rostedt
2018-10-16 19:21     ` Mathieu Desnoyers
2018-10-16 19:40       ` Steven Rostedt
2018-10-17  0:27     ` Sergey Senozhatsky
2018-10-17 15:00       ` Mathieu Desnoyers
2018-10-17 15:04         ` Mathieu Desnoyers
2018-10-17 15:34           ` Sergey Senozhatsky
2018-10-10 19:19 ` [RFC PATCH for 4.21 05/16] mm: Provide is_vma_noncached Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 06/16] cpu_opv: Provide cpu_opv system call (v8) Mathieu Desnoyers
2018-10-16  8:10   ` Sergey Senozhatsky
2018-10-16 19:17     ` Mathieu Desnoyers
2018-10-17  1:46       ` Sergey Senozhatsky
2018-10-17  7:19   ` Srikar Dronamraju
2018-10-17 15:11     ` Mathieu Desnoyers
2018-10-17 16:09       ` Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 07/16] cpu_opv: limit amount of virtual address space used by cpu_opv Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 08/16] x86: Wire up cpu_opv system call Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 09/16] powerpc: " Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 10/16] arm: " Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 11/16] cpu-opv/selftests: Provide cpu-op library Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 12/16] cpu-opv/selftests: Provide basic test Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 13/16] cpu-opv/selftests: Provide percpu_op API Mathieu Desnoyers
2018-10-10 19:19 ` [RFC PATCH for 4.21 14/16] cpu-opv/selftests: Provide basic percpu ops test Mathieu Desnoyers
2018-10-10 19:19 ` Mathieu Desnoyers [this message]
2018-10-10 19:19 ` [RFC PATCH for 4.21 16/16] cpu-opv/selftests: Provide Makefile, scripts, gitignore Mathieu Desnoyers
2018-11-01  9:58 [RFC PATCH for 4.21 00/16] rseq updates, new cpu_opv system call (v2) Mathieu Desnoyers
2018-11-01  9:58 ` [RFC PATCH for 4.21 15/16] cpu-opv/selftests: Provide parametrized tests Mathieu Desnoyers

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20181010191936.7495-16-mathieu.desnoyers@efficios.com \
    --to=mathieu.desnoyers@efficios.com \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=bmaurer@fb.com \
    --cc=boqun.feng@gmail.com \
    --cc=catalin.marinas@arm.com \
    --cc=cl@linux.com \
    --cc=davejwatson@fb.com \
    --cc=hpa@zytor.com \
    --cc=joelaf@google.com \
    --cc=josh@joshtriplett.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux@arm.linux.org.uk \
    --cc=luto@amacapital.net \
    --cc=mingo@redhat.com \
    --cc=mtk.manpages@gmail.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=rostedt@goodmis.org \
    --cc=shuah@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).