Release 4.11 tools/testing/selftests/vm/userfaultfd.c

/*
 * Stress userfaultfd syscall.
 *
 *  Copyright (C) 2015  Red Hat, Inc.
 *
 *  This work is licensed under the terms of the GNU GPL, version 2. See
 *  the COPYING file in the top-level directory.
 *
 * This test allocates two virtual areas and bounces the physical
 * memory across the two virtual areas (from area_src to area_dst)
 * using userfaultfd.
 *
 * There are three threads running per CPU:
 *
 * 1) one per-CPU thread takes a per-page pthread_mutex in a random
 *    page of the area_dst (while the physical page may still be in
 *    area_src), and increments a per-page counter in the same page,
 *    and checks its value against a verification region.
 *
 * 2) another per-CPU thread handles the userfaults generated by
 *    thread 1 above. userfaultfd blocking reads or poll() modes are
 *    exercised interleaved.
 *
 * 3) one last per-CPU thread transfers the memory in the background
 *    at maximum bandwidth (if not already transferred by thread
 *    2). Each cpu thread takes cares of transferring a portion of the
 *    area.
 *
 * When all threads of type 3 completed the transfer, one bounce is
 * complete. area_src and area_dst are then swapped. All threads are
 * respawned and so the bounce is immediately restarted in the
 * opposite direction.
 *
 * per-CPU threads 1 by triggering userfaults inside
 * pthread_mutex_lock will also verify the atomicity of the memory
 * transfer (UFFDIO_COPY).
 *
 * The program takes two parameters: the amounts of physical memory in
 * megabytes (MiB) of the area and the number of bounces to execute.
 *
 * # 100MiB 99999 bounces
 * ./userfaultfd 100 99999
 *
 * # 1GiB 99 bounces
 * ./userfaultfd 1000 99
 *
 * # 10MiB-~6GiB 999 bounces, continue forever unless an error triggers
 * while ./userfaultfd $[RANDOM % 6000 + 10] 999; do true; done
 */


#define _GNU_SOURCE
#include <stdio.h>
#include <errno.h>
#include <unistd.h>
#include <stdlib.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <time.h>
#include <signal.h>
#include <poll.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <sys/wait.h>
#include <pthread.h>
#include <linux/userfaultfd.h>

#ifdef __NR_userfaultfd





static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;


#define BOUNCE_RANDOM		(1<<0)

#define BOUNCE_RACINGFAULTS	(1<<1)

#define BOUNCE_VERIFY		(1<<2)

#define BOUNCE_POLL		(1<<3)

static int bounces;

#ifdef HUGETLB_TEST

static int huge_fd;

static char *huge_fd_off0;
#endif

static unsigned long long *count_verify;




static int uffd, uffd_flags, finished, *pipefd;


static char *area_src, *area_dst;

static char *zeropage;

pthread_attr_t attr;

/* pthread_mutex_t starts at page offset 0 */

#define area_mutex(___area, ___nr)					\
	((pthread_mutex_t *) ((___area) + (___nr)*page_size))
/*
 * count is placed in the page after pthread_mutex_t naturally aligned
 * to avoid non alignment faults on non-x86 archs.
 */

#define area_count(___area, ___nr)					\
	((volatile unsigned long long *) ((unsigned long)               \
                                 ((___area) + (___nr)*page_size +       \
                                  sizeof(pthread_mutex_t) +             \
                                  sizeof(unsigned long long) - 1) &     \
                                 ~(unsigned long)(sizeof(unsigned long long) \
                                                  -  1)))

#if !defined(HUGETLB_TEST) && !defined(SHMEM_TEST)

/* Anonymous memory */

#define EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
                                 (1 << _UFFDIO_COPY) | \
                                 (1 << _UFFDIO_ZEROPAGE))



static int release_pages(char *rel_area)
{
	int ret = 0;

	if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) {
		perror("madvise");
		ret = 1;
	}

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Kravetz
42
100.00%
1
100.00%
Total
42
100.00%
1
100.00%



static void allocate_area(void **alloc_area)
{
	if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) {
		fprintf(stderr, "out of memory\n");
		*alloc_area = NULL;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Kravetz
38
100.00%
1
100.00%
Total
38
100.00%
1
100.00%

#else /* HUGETLB_TEST or SHMEM_TEST */


#define EXPECTED_IOCTLS		UFFD_API_RANGE_IOCTLS_BASIC

#ifdef HUGETLB_TEST

/* HugeTLB memory */


static int release_pages(char *rel_area)
{
	int ret = 0;

	if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
				rel_area == huge_fd_off0 ? 0 :
				nr_pages * page_size,
				nr_pages * page_size)) {
		perror("fallocate");
		ret = 1;
	}

	return ret;
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Kravetz
54
100.00%
1
100.00%
Total
54
100.00%
1
100.00%



static void allocate_area(void **alloc_area)
{
	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
				MAP_PRIVATE | MAP_HUGETLB, huge_fd,
				*alloc_area == area_src ? 0 :
				nr_pages * page_size);
	if (*alloc_area == MAP_FAILED) {
		fprintf(stderr, "mmap of hugetlbfs file failed\n");
		*alloc_area = NULL;
	}

	if (*alloc_area == area_src)
		huge_fd_off0 = *alloc_area;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Kravetz
77
100.00%
1
100.00%
Total
77
100.00%
1
100.00%

#elif defined(SHMEM_TEST)

/* Shared memory */


static int release_pages(char *rel_area)
{
	int ret = 0;

	if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) {
		perror("madvise");
		ret = 1;
	}

	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Rapoport
42
100.00%
1
100.00%
Total
42
100.00%
1
100.00%



static void allocate_area(void **alloc_area)
{
	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
			   MAP_ANONYMOUS | MAP_SHARED, -1, 0);
	if (*alloc_area == MAP_FAILED) {
		fprintf(stderr, "shared memory mmap failed\n");
		*alloc_area = NULL;
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Rapoport
57
100.00%
1
100.00%
Total
57
100.00%
1
100.00%

#else /* SHMEM_TEST */
#error "Undefined test type"
#endif /* HUGETLB_TEST */

#endif /* !defined(HUGETLB_TEST) && !defined(SHMEM_TEST) */



static int my_bcmp(char *str1, char *str2, size_t n)
{
	unsigned long i;
	for (i = 0; i < n; i++)
		if (str1[i] != str2[i])
			return 1;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
52
100.00%
1
100.00%
Total
52
100.00%
1
100.00%



static void *locking_thread(void *arg)
{
	unsigned long cpu = (unsigned long) arg;
	struct random_data rand;
	unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */
	int32_t rand_nr;
	unsigned long long count;
	char randstate[64];
	unsigned int seed;
	time_t start;

	if (bounces & BOUNCE_RANDOM) {
		seed = (unsigned int) time(NULL) - bounces;
		if (!(bounces & BOUNCE_RACINGFAULTS))
			seed += cpu;
		bzero(&rand, sizeof(rand));
		bzero(&randstate, sizeof(randstate));
		if (initstate_r(seed, randstate, sizeof(randstate), &rand))
			fprintf(stderr, "srandom_r error\n"), exit(1);
	} else {
		page_nr = -bounces;
		if (!(bounces & BOUNCE_RACINGFAULTS))
			page_nr += cpu * nr_pages_per_cpu;
	}

	while (!finished) {
		if (bounces & BOUNCE_RANDOM) {
			if (random_r(&rand, &rand_nr))
				fprintf(stderr, "random_r 1 error\n"), exit(1);
			page_nr = rand_nr;
			if (sizeof(page_nr) > sizeof(rand_nr)) {
				if (random_r(&rand, &rand_nr))
					fprintf(stderr, "random_r 2 error\n"), exit(1);
				page_nr |= (((unsigned long) rand_nr) << 16) <<
					   16;
			}
		} else
			page_nr += 1;
		page_nr %= nr_pages;

		start = time(NULL);
		if (bounces & BOUNCE_VERIFY) {
			count = *area_count(area_dst, page_nr);
			if (!count)
				fprintf(stderr,
					"page_nr %lu wrong count %Lu %Lu\n",
					page_nr, count,
					count_verify[page_nr]), exit(1);


			/*
                         * We can't use bcmp (or memcmp) because that
                         * returns 0 erroneously if the memory is
                         * changing under it (even if the end of the
                         * page is never changing and always
                         * different).
                         */
#if 1
			if (!my_bcmp(area_dst + page_nr * page_size, zeropage,
				     page_size))
				fprintf(stderr,
					"my_bcmp page_nr %lu wrong count %Lu %Lu\n",
					page_nr, count,
					count_verify[page_nr]), exit(1);
#else
			unsigned long loops;

			loops = 0;
			/* uncomment the below line to test with mutex */
			/* pthread_mutex_lock(area_mutex(area_dst, page_nr)); */
			while (!bcmp(area_dst + page_nr * page_size, zeropage,
				     page_size)) {
				loops += 1;
				if (loops > 10)
					break;
			}
			/* uncomment below line to test with mutex */
			/* pthread_mutex_unlock(area_mutex(area_dst, page_nr)); */
			if (loops) {
				fprintf(stderr,
					"page_nr %lu all zero thread %lu %p %lu\n",
					page_nr, cpu, area_dst + page_nr * page_size,
					loops);
				if (loops > 10)
					exit(1);
			}
#endif
		}

		pthread_mutex_lock(area_mutex(area_dst, page_nr));
		count = *area_count(area_dst, page_nr);
		if (count != count_verify[page_nr]) {
			fprintf(stderr,
				"page_nr %lu memory corruption %Lu %Lu\n",
				page_nr, count,
				count_verify[page_nr]), exit(1);
		}
		count++;
		*area_count(area_dst, page_nr) = count_verify[page_nr] = count;
		pthread_mutex_unlock(area_mutex(area_dst, page_nr));

		if (time(NULL) - start > 1)
			fprintf(stderr,
				"userfault too slow %ld "
				"possible false positive with overcommit\n",
				time(NULL) - start);
	}

	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
548
99.10%
1
50.00%
Geert Uytterhoeven
5
0.90%
1
50.00%
Total
553
100.00%
2
100.00%



static int copy_page(int ufd, unsigned long offset)
{
	struct uffdio_copy uffdio_copy;

	if (offset >= nr_pages * page_size)
		fprintf(stderr, "unexpected offset %lu\n",
			offset), exit(1);
	uffdio_copy.dst = (unsigned long) area_dst + offset;
	uffdio_copy.src = (unsigned long) area_src + offset;
	uffdio_copy.len = page_size;
	uffdio_copy.mode = 0;
	uffdio_copy.copy = 0;
	if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
		/* real retval in ufdio_copy.copy */
		if (uffdio_copy.copy != -EEXIST)
			fprintf(stderr, "UFFDIO_COPY error %Ld\n",
				uffdio_copy.copy), exit(1);
	} else if (uffdio_copy.copy != page_size) {
		fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n",
			uffdio_copy.copy), exit(1);
	} else
		return 1;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
151
97.42%
1
50.00%
Mike Rapoport
4
2.58%
1
50.00%
Total
155
100.00%
2
100.00%



static void *uffd_poll_thread(void *arg)
{
	unsigned long cpu = (unsigned long) arg;
	struct pollfd pollfd[2];
	struct uffd_msg msg;
	struct uffdio_register uffd_reg;
	int ret;
	unsigned long offset;
	char tmp_chr;
	unsigned long userfaults = 0;

	pollfd[0].fd = uffd;
	pollfd[0].events = POLLIN;
	pollfd[1].fd = pipefd[cpu*2];
	pollfd[1].events = POLLIN;

	for (;;) {
		ret = poll(pollfd, 2, -1);
		if (!ret)
			fprintf(stderr, "poll error %d\n", ret), exit(1);
		if (ret < 0)
			perror("poll"), exit(1);
		if (pollfd[1].revents & POLLIN) {
			if (read(pollfd[1].fd, &tmp_chr, 1) != 1)
				fprintf(stderr, "read pipefd error\n"),
					exit(1);
			break;
		}
		if (!(pollfd[0].revents & POLLIN))
			fprintf(stderr, "pollfd[0].revents %d\n",
				pollfd[0].revents), exit(1);
		ret = read(uffd, &msg, sizeof(msg));
		if (ret < 0) {
			if (errno == EAGAIN)
				continue;
			perror("nonblocking read error"), exit(1);
		}
		switch (msg.event) {
		default:
			fprintf(stderr, "unexpected msg event %u\n",
				msg.event), exit(1);
			break;
		case UFFD_EVENT_PAGEFAULT:
			if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
				fprintf(stderr, "unexpected write fault\n"), exit(1);
			offset = (char *)(unsigned long)msg.arg.pagefault.address -
				area_dst;
			offset &= ~(page_size-1);
			if (copy_page(uffd, offset))
				userfaults++;
			break;
		case UFFD_EVENT_FORK:
			uffd = msg.arg.fork.ufd;
			pollfd[0].fd = uffd;
			break;
		case UFFD_EVENT_REMOVE:
			uffd_reg.range.start = msg.arg.remove.start;
			uffd_reg.range.len = msg.arg.remove.end -
				msg.arg.remove.start;
			if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range))
				fprintf(stderr, "remove failure\n"), exit(1);
			break;
		case UFFD_EVENT_REMAP:
			area_dst = (char *)(unsigned long)msg.arg.remap.to;
			break;
		}
	}
	return (void *)userfaults;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
348
72.80%
1
20.00%
Mike Rapoport
126
26.36%
3
60.00%
Geert Uytterhoeven
4
0.84%
1
20.00%
Total
478
100.00%
5
100.00%


pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER;



static void *uffd_read_thread(void *arg)
{
	unsigned long *this_cpu_userfaults;
	struct uffd_msg msg;
	unsigned long offset;
	int ret;

	this_cpu_userfaults = (unsigned long *) arg;
	*this_cpu_userfaults = 0;

	pthread_mutex_unlock(&uffd_read_mutex);
	/* from here cancellation is ok */

	for (;;) {
		ret = read(uffd, &msg, sizeof(msg));
		if (ret != sizeof(msg)) {
			if (ret < 0)
				perror("blocking read error"), exit(1);
			else
				fprintf(stderr, "short read\n"), exit(1);
		}
		if (msg.event != UFFD_EVENT_PAGEFAULT)
			fprintf(stderr, "unexpected msg event %u\n",
				msg.event), exit(1);
		if (bounces & BOUNCE_VERIFY &&
		    msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
			fprintf(stderr, "unexpected write fault\n"), exit(1);
		offset = (char *)(unsigned long)msg.arg.pagefault.address -
			 area_dst;
		offset &= ~(page_size-1);
		if (copy_page(uffd, offset))
			(*this_cpu_userfaults)++;
	}
	return (void *)NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
207
97.18%
1
33.33%
Geert Uytterhoeven
4
1.88%
1
33.33%
Mike Rapoport
2
0.94%
1
33.33%
Total
213
100.00%
3
100.00%



static void *background_thread(void *arg)
{
	unsigned long cpu = (unsigned long) arg;
	unsigned long page_nr;

	for (page_nr = cpu * nr_pages_per_cpu;
	     page_nr < (cpu+1) * nr_pages_per_cpu;
	     page_nr++)
		copy_page(uffd, page_nr * page_size);

	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
56
96.55%
1
50.00%
Mike Rapoport
2
3.45%
1
50.00%
Total
58
100.00%
2
100.00%



static int stress(unsigned long *userfaults)
{
	unsigned long cpu;
	pthread_t locking_threads[nr_cpus];
	pthread_t uffd_threads[nr_cpus];
	pthread_t background_threads[nr_cpus];
	void **_userfaults = (void **) userfaults;

	finished = 0;
	for (cpu = 0; cpu < nr_cpus; cpu++) {
		if (pthread_create(&locking_threads[cpu], &attr,
				   locking_thread, (void *)cpu))
			return 1;
		if (bounces & BOUNCE_POLL) {
			if (pthread_create(&uffd_threads[cpu], &attr,
					   uffd_poll_thread, (void *)cpu))
				return 1;
		} else {
			if (pthread_create(&uffd_threads[cpu], &attr,
					   uffd_read_thread,
					   &_userfaults[cpu]))
				return 1;
			pthread_mutex_lock(&uffd_read_mutex);
		}
		if (pthread_create(&background_threads[cpu], &attr,
				   background_thread, (void *)cpu))
			return 1;
	}
	for (cpu = 0; cpu < nr_cpus; cpu++)
		if (pthread_join(background_threads[cpu], NULL))
			return 1;

	/*
         * Be strict and immediately zap area_src, the whole area has
         * been transferred already by the background treads. The
         * area_src could then be faulted in in a racy way by still
         * running uffdio_threads reading zeropages after we zapped
         * area_src (but they're guaranteed to get -EEXIST from
         * UFFDIO_COPY without writing zero pages into area_dst
         * because the background threads already completed).
         */
	if (release_pages(area_src))
		return 1;

	for (cpu = 0; cpu < nr_cpus; cpu++) {
		char c;
		if (bounces & BOUNCE_POLL) {
			if (write(pipefd[cpu*2+1], &c, 1) != 1) {
				fprintf(stderr, "pipefd write error\n");
				return 1;
			}
			if (pthread_join(uffd_threads[cpu], &_userfaults[cpu]))
				return 1;
		} else {
			if (pthread_cancel(uffd_threads[cpu]))
				return 1;
			if (pthread_join(uffd_threads[cpu], NULL))
				return 1;
		}
	}

	finished = 1;
	for (cpu = 0; cpu < nr_cpus; cpu++)
		if (pthread_join(locking_threads[cpu], NULL))
			return 1;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
363
99.73%
1
50.00%
Mike Kravetz
1
0.27%
1
50.00%
Total
364
100.00%
2
100.00%



static int userfaultfd_open(int features)
{
	struct uffdio_api uffdio_api;

	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
	if (uffd < 0) {
		fprintf(stderr,
			"userfaultfd syscall not available in this kernel\n");
		return 1;
	}
	uffd_flags = fcntl(uffd, F_GETFD, NULL);

	uffdio_api.api = UFFD_API;
	uffdio_api.features = features;
	if (ioctl(uffd, UFFDIO_API, &uffdio_api)) {
		fprintf(stderr, "UFFDIO_API\n");
		return 1;
	}
	if (uffdio_api.api != UFFD_API) {
		fprintf(stderr, "UFFDIO_API error %Lu\n", uffdio_api.api);
		return 1;
	}

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
108
93.10%
1
33.33%
Mike Rapoport
8
6.90%
2
66.67%
Total
116
100.00%
3
100.00%

/*
 * For non-cooperative userfaultfd test we fork() a process that will
 * generate pagefaults, will mremap the area monitored by the
 * userfaultfd and at last this process will release the monitored
 * area.
 * For the anonymous and shared memory the area is divided into two
 * parts, the first part is accessed before mremap, and the second
 * part is accessed after mremap. Since hugetlbfs does not support
 * mremap, the entire monitored area is accessed in a single pass for
 * HUGETLB_TEST.
 * The release of the pages currently generates event for shmem and
 * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked
 * for hugetlb.
 */


static int faulting_process(void)
{
	unsigned long nr;
	unsigned long long count;

#ifndef HUGETLB_TEST
	unsigned long split_nr_pages = (nr_pages + 1) / 2;
#else
	unsigned long split_nr_pages = nr_pages;
#endif

	for (nr = 0; nr < split_nr_pages; nr++) {
		count = *area_count(area_dst, nr);
		if (count != count_verify[nr]) {
			fprintf(stderr,
				"nr %lu memory corruption %Lu %Lu\n",
				nr, count,
				count_verify[nr]), exit(1);
		}
	}

#ifndef HUGETLB_TEST
	area_dst = mremap(area_dst, nr_pages * page_size,  nr_pages * page_size,
			  MREMAP_MAYMOVE | MREMAP_FIXED, area_src);
	if (area_dst == MAP_FAILED)
		perror("mremap"), exit(1);

	for (; nr < nr_pages; nr++) {
		count = *area_count(area_dst, nr);
		if (count != count_verify[nr]) {
			fprintf(stderr,
				"nr %lu memory corruption %Lu %Lu\n",
				nr, count,
				count_verify[nr]), exit(1);
		}
	}

	if (release_pages(area_dst))
		return 1;

	for (nr = 0; nr < nr_pages; nr++) {
		if (my_bcmp(area_dst + nr * page_size, zeropage, page_size))
			fprintf(stderr, "nr %lu is not zero\n", nr), exit(1);
	}

#endif /* HUGETLB_TEST */

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Rapoport
225
88.93%
2
66.67%
Andrea Arcangeli
28
11.07%
1
33.33%
Total
253
100.00%
3
100.00%



static int uffdio_zeropage(int ufd, unsigned long offset)
{
	struct uffdio_zeropage uffdio_zeropage;
	int ret;
	unsigned long has_zeropage = EXPECTED_IOCTLS & (1 << _UFFDIO_ZEROPAGE);

	if (offset >= nr_pages * page_size)
		fprintf(stderr, "unexpected offset %lu\n",
			offset), exit(1);
	uffdio_zeropage.range.start = (unsigned long) area_dst + offset;
	uffdio_zeropage.range.len = page_size;
	uffdio_zeropage.mode = 0;
	ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage);
	if (ret) {
		/* real retval in ufdio_zeropage.zeropage */
		if (has_zeropage) {
			if (uffdio_zeropage.zeropage == -EEXIST)
				fprintf(stderr, "UFFDIO_ZEROPAGE -EEXIST\n"),
					exit(1);
			else
				fprintf(stderr, "UFFDIO_ZEROPAGE error %Ld\n",
					uffdio_zeropage.zeropage), exit(1);
		} else {
			if (uffdio_zeropage.zeropage != -EINVAL)
				fprintf(stderr,
					"UFFDIO_ZEROPAGE not -EINVAL %Ld\n",
					uffdio_zeropage.zeropage), exit(1);
		}
	} else if (has_zeropage) {
		if (uffdio_zeropage.zeropage != page_size) {
			fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
				uffdio_zeropage.zeropage), exit(1);
		} else
			return 1;
	} else {
		fprintf(stderr,
			"UFFDIO_ZEROPAGE succeeded %Ld\n",
			uffdio_zeropage.zeropage), exit(1);
	}

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
232
100.00%
1
100.00%
Total
232
100.00%
1
100.00%

/* exercise UFFDIO_ZEROPAGE */


static int userfaultfd_zeropage_test(void)
{
	struct uffdio_register uffdio_register;
	unsigned long expected_ioctls;

	printf("testing UFFDIO_ZEROPAGE: ");
	fflush(stdout);

	if (release_pages(area_dst))
		return 1;

	if (userfaultfd_open(0) < 0)
		return 1;
	uffdio_register.range.start = (unsigned long) area_dst;
	uffdio_register.range.len = nr_pages * page_size;
	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
		fprintf(stderr, "register failure\n"), exit(1);

	expected_ioctls = EXPECTED_IOCTLS;
	if ((uffdio_register.ioctls & expected_ioctls) !=
	    expected_ioctls)
		fprintf(stderr,
			"unexpected missing ioctl for anon memory\n"),
			exit(1);

	if (uffdio_zeropage(uffd, 0)) {
		if (my_bcmp(area_dst, zeropage, page_size))
			fprintf(stderr, "zeropage is not zero\n"), exit(1);
	}

	close(uffd);
	printf("done.\n");
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
175
100.00%
1
100.00%
Total
175
100.00%
1
100.00%



static int userfaultfd_events_test(void)
{
	struct uffdio_register uffdio_register;
	unsigned long expected_ioctls;
	unsigned long userfaults;
	pthread_t uffd_mon;
	int err, features;
	pid_t pid;
	char c;

	printf("testing events (fork, remap, remove): ");
	fflush(stdout);

	if (release_pages(area_dst))
		return 1;

	features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP |
		UFFD_FEATURE_EVENT_REMOVE;
	if (userfaultfd_open(features) < 0)
		return 1;
	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);

	uffdio_register.range.start = (unsigned long) area_dst;
	uffdio_register.range.len = nr_pages * page_size;
	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
		fprintf(stderr, "register failure\n"), exit(1);

	expected_ioctls = EXPECTED_IOCTLS;
	if ((uffdio_register.ioctls & expected_ioctls) !=
	    expected_ioctls)
		fprintf(stderr,
			"unexpected missing ioctl for anon memory\n"),
			exit(1);

	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL))
		perror("uffd_poll_thread create"), exit(1);

	pid = fork();
	if (pid < 0)
		perror("fork"), exit(1);

	if (!pid)
		return faulting_process();

	waitpid(pid, &err, 0);
	if (err)
		fprintf(stderr, "faulting process failed\n"), exit(1);

	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
		perror("pipe write"), exit(1);
	if (pthread_join(uffd_mon, (void **)&userfaults))
		return 1;

	close(uffd);
	printf("userfaults: %ld\n", userfaults);

	return userfaults != nr_pages;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Rapoport
314
100.00%
2
100.00%
Total
314
100.00%
2
100.00%



static int userfaultfd_stress(void)
{
	void *area;
	char *tmp_area;
	unsigned long nr;
	struct uffdio_register uffdio_register;
	unsigned long cpu;
	int err;
	unsigned long userfaults[nr_cpus];

	allocate_area((void **)&area_src);
	if (!area_src)
		return 1;
	allocate_area((void **)&area_dst);
	if (!area_dst)
		return 1;

	if (userfaultfd_open(0) < 0)
		return 1;

	count_verify = malloc(nr_pages * sizeof(unsigned long long));
	if (!count_verify) {
		perror("count_verify");
		return 1;
	}

	for (nr = 0; nr < nr_pages; nr++) {
		*area_mutex(area_src, nr) = (pthread_mutex_t)
			PTHREAD_MUTEX_INITIALIZER;
		count_verify[nr] = *area_count(area_src, nr) = 1;
		/*
                 * In the transition between 255 to 256, powerpc will
                 * read out of order in my_bcmp and see both bytes as
                 * zero, so leave a placeholder below always non-zero
                 * after the count, to avoid my_bcmp to trigger false
                 * positives.
                 */
		*(area_count(area_src, nr) + 1) = 1;
	}

	pipefd = malloc(sizeof(int) * nr_cpus * 2);
	if (!pipefd) {
		perror("pipefd");
		return 1;
	}
	for (cpu = 0; cpu < nr_cpus; cpu++) {
		if (pipe2(&pipefd[cpu*2], O_CLOEXEC | O_NONBLOCK)) {
			perror("pipe");
			return 1;
		}
	}

	if (posix_memalign(&area, page_size, page_size)) {
		fprintf(stderr, "out of memory\n");
		return 1;
	}
	zeropage = area;
	bzero(zeropage, page_size);

	pthread_mutex_lock(&uffd_read_mutex);

	pthread_attr_init(&attr);
	pthread_attr_setstacksize(&attr, 16*1024*1024);

	err = 0;
	while (bounces--) {
		unsigned long expected_ioctls;

		printf("bounces: %d, mode:", bounces);
		if (bounces & BOUNCE_RANDOM)
			printf(" rnd");
		if (bounces & BOUNCE_RACINGFAULTS)
			printf(" racing");
		if (bounces & BOUNCE_VERIFY)
			printf(" ver");
		if (bounces & BOUNCE_POLL)
			printf(" poll");
		printf(", ");
		fflush(stdout);

		if (bounces & BOUNCE_POLL)
			fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
		else
			fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK);

		/* register */
		uffdio_register.range.start = (unsigned long) area_dst;
		uffdio_register.range.len = nr_pages * page_size;
		uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
		if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
			fprintf(stderr, "register failure\n");
			return 1;
		}
		expected_ioctls = EXPECTED_IOCTLS;
		if ((uffdio_register.ioctls & expected_ioctls) !=
		    expected_ioctls) {
			fprintf(stderr,
				"unexpected missing ioctl for anon memory\n");
			return 1;
		}

		/*
                 * The madvise done previously isn't enough: some
                 * uffd_thread could have read userfaults (one of
                 * those already resolved by the background thread)
                 * and it may be in the process of calling
                 * UFFDIO_COPY. UFFDIO_COPY will read the zapped
                 * area_src and it would map a zero page in it (of
                 * course such a UFFDIO_COPY is perfectly safe as it'd
                 * return -EEXIST). The problem comes at the next
                 * bounce though: that racing UFFDIO_COPY would
                 * generate zeropages in the area_src, so invalidating
                 * the previous MADV_DONTNEED. Without this additional
                 * MADV_DONTNEED those zeropages leftovers in the
                 * area_src would lead to -EEXIST failure during the
                 * next bounce, effectively leaving a zeropage in the
                 * area_dst.
                 *
                 * Try to comment this out madvise to see the memory
                 * corruption being caught pretty quick.
                 *
                 * khugepaged is also inhibited to collapse THP after
                 * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's
                 * required to MADV_DONTNEED here.
                 */
		if (release_pages(area_dst))
			return 1;

		/* bounce pass */
		if (stress(userfaults))
			return 1;

		/* unregister */
		if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) {
			fprintf(stderr, "register failure\n");
			return 1;
		}

		/* verification */
		if (bounces & BOUNCE_VERIFY) {
			for (nr = 0; nr < nr_pages; nr++) {
				if (*area_count(area_dst, nr) != count_verify[nr]) {
					fprintf(stderr,
						"error area_count %Lu %Lu %lu\n",
						*area_count(area_src, nr),
						count_verify[nr],
						nr);
					err = 1;
					bounces = 0;
				}
			}
		}

		/* prepare next bounce */
		tmp_area = area_src;
		area_src = area_dst;
		area_dst = tmp_area;

		printf("userfaults:");
		for (cpu = 0; cpu < nr_cpus; cpu++)
			printf(" %lu", userfaults[cpu]);
		printf("\n");
	}

	if (err)
		return err;

	close(uffd);
	return userfaultfd_zeropage_test() || userfaultfd_events_test();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
502
74.15%
4
66.67%
Mike Rapoport
173
25.55%
1
16.67%
Mike Kravetz
2
0.30%
1
16.67%
Total
677
100.00%
6
100.00%

#ifndef HUGETLB_TEST



int main(int argc, char **argv)
{
	if (argc < 3)
		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
	page_size = sysconf(_SC_PAGE_SIZE);
	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
	    > page_size)
		fprintf(stderr, "Impossible to run this test\n"), exit(2);
	nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size /
		nr_cpus;
	if (!nr_pages_per_cpu) {
		fprintf(stderr, "invalid MiB\n");
		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
	}
	bounces = atoi(argv[2]);
	if (bounces <= 0) {
		fprintf(stderr, "invalid bounces\n");
		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
	}
	nr_pages = nr_pages_per_cpu * nr_cpus;
	printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n",
	       nr_pages, nr_pages_per_cpu);
	return userfaultfd_stress();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
181
100.00%
2
100.00%
Total
181
100.00%
2
100.00%

#else /* HUGETLB_TEST */

/*
 * Copied from mlock2-tests.c
 */


unsigned long default_huge_page_size(void)
{
	unsigned long hps = 0;
	char *line = NULL;
	size_t linelen = 0;
	FILE *f = fopen("/proc/meminfo", "r");

	if (!f)
		return 0;
	while (getline(&line, &linelen, f) > 0) {
		if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
			hps <<= 10;
			break;
		}
	}

	free(line);
	fclose(f);
	return hps;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Kravetz
95
100.00%
1
100.00%
Total
95
100.00%
1
100.00%



int main(int argc, char **argv)
{
	if (argc < 4)
		fprintf(stderr, "Usage: <MiB> <bounces> <hugetlbfs_file>\n"),
				exit(1);
	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
	page_size = default_huge_page_size();
	if (!page_size)
		fprintf(stderr, "Unable to determine huge page size\n"),
				exit(2);
	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
	    > page_size)
		fprintf(stderr, "Impossible to run this test\n"), exit(2);
	nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size /
		nr_cpus;
	if (!nr_pages_per_cpu) {
		fprintf(stderr, "invalid MiB\n");
		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
	}
	bounces = atoi(argv[2]);
	if (bounces <= 0) {
		fprintf(stderr, "invalid bounces\n");
		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
	}
	nr_pages = nr_pages_per_cpu * nr_cpus;
	huge_fd = open(argv[3], O_CREAT | O_RDWR, 0755);
	if (huge_fd < 0) {
		fprintf(stderr, "Open of %s failed", argv[3]);
		perror("open");
		exit(1);
	}
	if (ftruncate(huge_fd, 0)) {
		fprintf(stderr, "ftruncate %s to size 0 failed", argv[3]);
		perror("ftruncate");
		exit(1);
	}
	printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n",
	       nr_pages, nr_pages_per_cpu);
	return userfaultfd_stress();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Mike Kravetz
275
100.00%
1
100.00%
Total
275
100.00%
1
100.00%

#endif
#else /* __NR_userfaultfd */

#warning "missing __NR_userfaultfd definition"



int main(void)
{
	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Michael Ellerman
15
100.00%
1
100.00%
Total
15
100.00%
1
100.00%

#endif /* __NR_userfaultfd */
Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrea Arcangeli
3093
65.14%
4
26.67%
Mike Rapoport
994
20.94%
7
46.67%
Mike Kravetz
620
13.06%
1
6.67%
Michael Ellerman
26
0.55%
1
6.67%
Geert Uytterhoeven
13
0.27%
1
6.67%
Thierry Reding
2
0.04%
1
6.67%
Total
4748
100.00%
15
100.00%
Directory: tools/testing/selftests/vm

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.