These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

7 files changed, 1722 insertions, 91 deletions

diff --git a/kernel/tools/testing/selftests/vm/Makefile b/kernel/tools/testing/selftests/vm/Makefile
index a5ce9534e..e4bb1de1d 100644
--- a/kernel/tools/testing/selftests/vm/Makefile
+++ b/kernel/tools/testing/selftests/vm/Makefile
@@ -1,12 +1,24 @@
 # Makefile for vm selftests
 
-CFLAGS = -Wall
-BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest
+CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
+BINARIES = compaction_test
+BINARIES += hugepage-mmap
+BINARIES += hugepage-shm
+BINARIES += map_hugetlb
+BINARIES += mlock2-tests
+BINARIES += on-fault-limit
+BINARIES += thuge-gen
 BINARIES += transhuge-stress
+BINARIES += userfaultfd
 
 all: $(BINARIES)
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^ -lrt
+userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h
+	$(CC) $(CFLAGS) -O2 -o $@ $< -lpthread
+
+../../../../usr/include/linux/kernel.h:
+	make -C ../../../.. headers_install
 
 TEST_PROGS := run_vmtests
 TEST_FILES := $(BINARIES)
diff --git a/kernel/tools/testing/selftests/vm/compaction_test.c b/kernel/tools/testing/selftests/vm/compaction_test.c
new file mode 100644
index 000000000..932ff577f
--- /dev/null
+++ b/kernel/tools/testing/selftests/vm/compaction_test.c
@@ -0,0 +1,225 @@
+/*
+ *
+ * A test for the patch "Allow compaction of unevictable pages".
+ * With this patch we should be able to allocate at least 1/4
+ * of RAM in huge pages. Without the patch much less is
+ * allocated.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+
+#define MAP_SIZE 1048576
+
+struct map_list {
+	void *map;
+	struct map_list *next;
+};
+
+int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize)
+{
+	char  buffer[256] = {0};
+	char *cmd = "cat /proc/meminfo | grep -i memfree | grep -o '[0-9]*'";
+	FILE *cmdfile = popen(cmd, "r");
+
+	if (!(fgets(buffer, sizeof(buffer), cmdfile))) {
+		perror("Failed to read meminfo\n");
+		return -1;
+	}
+
+	pclose(cmdfile);
+
+	*memfree = atoll(buffer);
+	cmd = "cat /proc/meminfo | grep -i hugepagesize | grep -o '[0-9]*'";
+	cmdfile = popen(cmd, "r");
+
+	if (!(fgets(buffer, sizeof(buffer), cmdfile))) {
+		perror("Failed to read meminfo\n");
+		return -1;
+	}
+
+	pclose(cmdfile);
+	*hugepagesize = atoll(buffer);
+
+	return 0;
+}
+
+int prereq(void)
+{
+	char allowed;
+	int fd;
+
+	fd = open("/proc/sys/vm/compact_unevictable_allowed",
+		  O_RDONLY | O_NONBLOCK);
+	if (fd < 0) {
+		perror("Failed to open\n"
+		       "/proc/sys/vm/compact_unevictable_allowed\n");
+		return -1;
+	}
+
+	if (read(fd, &allowed, sizeof(char)) != sizeof(char)) {
+		perror("Failed to read from\n"
+		       "/proc/sys/vm/compact_unevictable_allowed\n");
+		close(fd);
+		return -1;
+	}
+
+	close(fd);
+	if (allowed == '1')
+		return 0;
+
+	return -1;
+}
+
+int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
+{
+	int fd;
+	int compaction_index = 0;
+	char initial_nr_hugepages[10] = {0};
+	char nr_hugepages[10] = {0};
+
+	/* We want to test with 80% of available memory. Else, OOM killer comes
+	   in to play */
+	mem_free = mem_free * 0.8;
+
+	fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK);
+	if (fd < 0) {
+		perror("Failed to open /proc/sys/vm/nr_hugepages");
+		return -1;
+	}
+
+	if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) {
+		perror("Failed to read from /proc/sys/vm/nr_hugepages");
+		goto close_fd;
+	}
+
+	/* Start with the initial condition of 0 huge pages*/
+	if (write(fd, "0", sizeof(char)) != sizeof(char)) {
+		perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
+		goto close_fd;
+	}
+
+	lseek(fd, 0, SEEK_SET);
+
+	/* Request a large number of huge pages. The Kernel will allocate
+	   as much as it can */
+	if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
+		perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
+		goto close_fd;
+	}
+
+	lseek(fd, 0, SEEK_SET);
+
+	if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) {
+		perror("Failed to read from /proc/sys/vm/nr_hugepages\n");
+		goto close_fd;
+	}
+
+	/* We should have been able to request at least 1/3 rd of the memory in
+	   huge pages */
+	compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size);
+
+	if (compaction_index > 3) {
+		printf("No of huge pages allocated = %d\n",
+		       (atoi(nr_hugepages)));
+		fprintf(stderr, "ERROR: Less that 1/%d of memory is available\n"
+			"as huge pages\n", compaction_index);
+		goto close_fd;
+	}
+
+	printf("No of huge pages allocated = %d\n",
+	       (atoi(nr_hugepages)));
+
+	if (write(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages))
+	    != strlen(initial_nr_hugepages)) {
+		perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
+		goto close_fd;
+	}
+
+	close(fd);
+	return 0;
+
+ close_fd:
+	close(fd);
+	printf("Not OK. Compaction test failed.");
+	return -1;
+}
+
+
+int main(int argc, char **argv)
+{
+	struct rlimit lim;
+	struct map_list *list, *entry;
+	size_t page_size, i;
+	void *map = NULL;
+	unsigned long mem_free = 0;
+	unsigned long hugepage_size = 0;
+	unsigned long mem_fragmentable = 0;
+
+	if (prereq() != 0) {
+		printf("Either the sysctl compact_unevictable_allowed is not\n"
+		       "set to 1 or couldn't read the proc file.\n"
+		       "Skipping the test\n");
+		return 0;
+	}
+
+	lim.rlim_cur = RLIM_INFINITY;
+	lim.rlim_max = RLIM_INFINITY;
+	if (setrlimit(RLIMIT_MEMLOCK, &lim)) {
+		perror("Failed to set rlimit:\n");
+		return -1;
+	}
+
+	page_size = getpagesize();
+
+	list = NULL;
+
+	if (read_memory_info(&mem_free, &hugepage_size) != 0) {
+		printf("ERROR: Cannot read meminfo\n");
+		return -1;
+	}
+
+	mem_fragmentable = mem_free * 0.8 / 1024;
+
+	while (mem_fragmentable > 0) {
+		map = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE,
+			   MAP_ANONYMOUS | MAP_PRIVATE | MAP_LOCKED, -1, 0);
+		if (map == MAP_FAILED)
+			break;
+
+		entry = malloc(sizeof(struct map_list));
+		if (!entry) {
+			munmap(map, MAP_SIZE);
+			break;
+		}
+		entry->map = map;
+		entry->next = list;
+		list = entry;
+
+		/* Write something (in this case the address of the map) to
+		 * ensure that KSM can't merge the mapped pages
+		 */
+		for (i = 0; i < MAP_SIZE; i += page_size)
+			*(unsigned long *)(map + i) = (unsigned long)map + i;
+
+		mem_fragmentable--;
+	}
+
+	for (entry = list; entry != NULL; entry = entry->next) {
+		munmap(entry->map, MAP_SIZE);
+		if (!entry->next)
+			break;
+		entry = entry->next;
+	}
+
+	if (check_compaction(mem_free, hugepage_size) == 0)
+		return 0;
+
+	return -1;
+}
diff --git a/kernel/tools/testing/selftests/vm/hugetlbfstest.c b/kernel/tools/testing/selftests/vm/hugetlbfstest.c
deleted file mode 100644
index 02e1072ec..000000000
--- a/kernel/tools/testing/selftests/vm/hugetlbfstest.c
+++ /dev/null
@@ -1,86 +0,0 @@
-#define _GNU_SOURCE
-#include <assert.h>
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/mman.h>
-#include <sys/stat.h>
-#include <sys/types.h>
-#include <unistd.h>
-
-typedef unsigned long long u64;
-
-static size_t length = 1 << 24;
-
-static u64 read_rss(void)
-{
-	char buf[4096], *s = buf;
-	int i, fd;
-	u64 rss;
-
-	fd = open("/proc/self/statm", O_RDONLY);
-	assert(fd > 2);
-	memset(buf, 0, sizeof(buf));
-	read(fd, buf, sizeof(buf) - 1);
-	for (i = 0; i < 1; i++)
-		s = strchr(s, ' ') + 1;
-	rss = strtoull(s, NULL, 10);
-	return rss << 12; /* assumes 4k pagesize */
-}
-
-static void do_mmap(int fd, int extra_flags, int unmap)
-{
-	int *p;
-	int flags = MAP_PRIVATE | MAP_POPULATE | extra_flags;
-	u64 before, after;
-	int ret;
-
-	before = read_rss();
-	p = mmap(NULL, length, PROT_READ | PROT_WRITE, flags, fd, 0);
-	assert(p != MAP_FAILED ||
-			!"mmap returned an unexpected error");
-	after = read_rss();
-	assert(llabs(after - before - length) < 0x40000 ||
-			!"rss didn't grow as expected");
-	if (!unmap)
-		return;
-	ret = munmap(p, length);
-	assert(!ret || !"munmap returned an unexpected error");
-	after = read_rss();
-	assert(llabs(after - before) < 0x40000 ||
-			!"rss didn't shrink as expected");
-}
-
-static int open_file(const char *path)
-{
-	int fd, err;
-
-	unlink(path);
-	fd = open(path, O_CREAT | O_RDWR | O_TRUNC | O_EXCL
-			| O_LARGEFILE | O_CLOEXEC, 0600);
-	assert(fd > 2);
-	unlink(path);
-	err = ftruncate(fd, length);
-	assert(!err);
-	return fd;
-}
-
-int main(void)
-{
-	int hugefd, fd;
-
-	fd = open_file("/dev/shm/hugetlbhog");
-	hugefd = open_file("/hugepages/hugetlbhog");
-
-	system("echo 100 > /proc/sys/vm/nr_hugepages");
-	do_mmap(-1, MAP_ANONYMOUS, 1);
-	do_mmap(fd, 0, 1);
-	do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 1);
-	do_mmap(hugefd, 0, 1);
-	do_mmap(hugefd, MAP_HUGETLB, 1);
-	/* Leak the last one to test do_exit() */
-	do_mmap(-1, MAP_ANONYMOUS | MAP_HUGETLB, 0);
-	printf("oll korrekt.\n");
-	return 0;
-}
diff --git a/kernel/tools/testing/selftests/vm/mlock2-tests.c b/kernel/tools/testing/selftests/vm/mlock2-tests.c
new file mode 100644
index 000000000..02ca5e017
--- /dev/null
+++ b/kernel/tools/testing/selftests/vm/mlock2-tests.c
@@ -0,0 +1,737 @@
+#define _GNU_SOURCE
+#include <sys/mman.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <syscall.h>
+#include <errno.h>
+#include <stdbool.h>
+
+#ifndef MLOCK_ONFAULT
+#define MLOCK_ONFAULT 1
+#endif
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int mlock2_(void *start, size_t len, int flags)
+{
+#ifdef __NR_mlock2
+	return syscall(__NR_mlock2, start, len, flags);
+#else
+	errno = ENOSYS;
+	return -1;
+#endif
+}
+
+struct vm_boundaries {
+	unsigned long start;
+	unsigned long end;
+};
+
+static int get_vm_area(unsigned long addr, struct vm_boundaries *area)
+{
+	FILE *file;
+	int ret = 1;
+	char line[1024] = {0};
+	char *end_addr;
+	char *stop;
+	unsigned long start;
+	unsigned long end;
+
+	if (!area)
+		return ret;
+
+	file = fopen("/proc/self/maps", "r");
+	if (!file) {
+		perror("fopen");
+		return ret;
+	}
+
+	memset(area, 0, sizeof(struct vm_boundaries));
+
+	while(fgets(line, 1024, file)) {
+		end_addr = strchr(line, '-');
+		if (!end_addr) {
+			printf("cannot parse /proc/self/maps\n");
+			goto out;
+		}
+		*end_addr = '\0';
+		end_addr++;
+		stop = strchr(end_addr, ' ');
+		if (!stop) {
+			printf("cannot parse /proc/self/maps\n");
+			goto out;
+		}
+		stop = '\0';
+
+		sscanf(line, "%lx", &start);
+		sscanf(end_addr, "%lx", &end);
+
+		if (start <= addr && end > addr) {
+			area->start = start;
+			area->end = end;
+			ret = 0;
+			goto out;
+		}
+	}
+out:
+	fclose(file);
+	return ret;
+}
+
+static uint64_t get_pageflags(unsigned long addr)
+{
+	FILE *file;
+	uint64_t pfn;
+	unsigned long offset;
+
+	file = fopen("/proc/self/pagemap", "r");
+	if (!file) {
+		perror("fopen pagemap");
+		_exit(1);
+	}
+
+	offset = addr / getpagesize() * sizeof(pfn);
+
+	if (fseek(file, offset, SEEK_SET)) {
+		perror("fseek pagemap");
+		_exit(1);
+	}
+
+	if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
+		perror("fread pagemap");
+		_exit(1);
+	}
+
+	fclose(file);
+	return pfn;
+}
+
+static uint64_t get_kpageflags(unsigned long pfn)
+{
+	uint64_t flags;
+	FILE *file;
+
+	file = fopen("/proc/kpageflags", "r");
+	if (!file) {
+		perror("fopen kpageflags");
+		_exit(1);
+	}
+
+	if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
+		perror("fseek kpageflags");
+		_exit(1);
+	}
+
+	if (fread(&flags, sizeof(flags), 1, file) != 1) {
+		perror("fread kpageflags");
+		_exit(1);
+	}
+
+	fclose(file);
+	return flags;
+}
+
+static FILE *seek_to_smaps_entry(unsigned long addr)
+{
+	FILE *file;
+	char *line = NULL;
+	size_t size = 0;
+	unsigned long start, end;
+	char perms[5];
+	unsigned long offset;
+	char dev[32];
+	unsigned long inode;
+	char path[BUFSIZ];
+
+	file = fopen("/proc/self/smaps", "r");
+	if (!file) {
+		perror("fopen smaps");
+		_exit(1);
+	}
+
+	while (getline(&line, &size, file) > 0) {
+		if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n",
+			   &start, &end, perms, &offset, dev, &inode, path) < 6)
+			goto next;
+
+		if (start <= addr && addr < end)
+			goto out;
+
+next:
+		free(line);
+		line = NULL;
+		size = 0;
+	}
+
+	fclose(file);
+	file = NULL;
+
+out:
+	free(line);
+	return file;
+}
+
+#define VMFLAGS "VmFlags:"
+
+static bool is_vmflag_set(unsigned long addr, const char *vmflag)
+{
+	char *line = NULL;
+	char *flags;
+	size_t size = 0;
+	bool ret = false;
+	FILE *smaps;
+
+	smaps = seek_to_smaps_entry(addr);
+	if (!smaps) {
+		printf("Unable to parse /proc/self/smaps\n");
+		goto out;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, VMFLAGS)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		flags = line + strlen(VMFLAGS);
+		ret = (strstr(flags, vmflag) != NULL);
+		goto out;
+	}
+
+out:
+	free(line);
+	fclose(smaps);
+	return ret;
+}
+
+#define SIZE "Size:"
+#define RSS  "Rss:"
+#define LOCKED "lo"
+
+static bool is_vma_lock_on_fault(unsigned long addr)
+{
+	bool ret = false;
+	bool locked;
+	FILE *smaps = NULL;
+	unsigned long vma_size, vma_rss;
+	char *line = NULL;
+	char *value;
+	size_t size = 0;
+
+	locked = is_vmflag_set(addr, LOCKED);
+	if (!locked)
+		goto out;
+
+	smaps = seek_to_smaps_entry(addr);
+	if (!smaps) {
+		printf("Unable to parse /proc/self/smaps\n");
+		goto out;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, SIZE)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		value = line + strlen(SIZE);
+		if (sscanf(value, "%lu kB", &vma_size) < 1) {
+			printf("Unable to parse smaps entry for Size\n");
+			goto out;
+		}
+		break;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, RSS)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		value = line + strlen(RSS);
+		if (sscanf(value, "%lu kB", &vma_rss) < 1) {
+			printf("Unable to parse smaps entry for Rss\n");
+			goto out;
+		}
+		break;
+	}
+
+	ret = locked && (vma_rss < vma_size);
+out:
+	free(line);
+	if (smaps)
+		fclose(smaps);
+	return ret;
+}
+
+#define PRESENT_BIT     0x8000000000000000ULL
+#define PFN_MASK        0x007FFFFFFFFFFFFFULL
+#define UNEVICTABLE_BIT (1UL << 18)
+
+static int lock_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Both pages should be present */
+	if (((page1_flags & PRESENT_BIT) == 0) ||
+	    ((page2_flags & PRESENT_BIT) == 0)) {
+		printf("Failed to make both pages present\n");
+		return 1;
+	}
+
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	/* Both pages should be unevictable */
+	if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
+	    ((page2_flags & UNEVICTABLE_BIT) == 0)) {
+		printf("Failed to make both pages unevictable\n");
+		return 1;
+	}
+
+	if (!is_vmflag_set((unsigned long)map, LOCKED)) {
+		printf("VMA flag %s is missing on page 1\n", LOCKED);
+		return 1;
+	}
+
+	if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+		printf("VMA flag %s is missing on page 2\n", LOCKED);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int unlock_lock_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
+		printf("A page is still marked unevictable after unlock\n");
+		return 1;
+	}
+
+	if (is_vmflag_set((unsigned long)map, LOCKED)) {
+		printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
+		return 1;
+	}
+
+	if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+		printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int test_mlock_lock()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	if (mlock2_(map, 2 * page_size, 0)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(0)");
+		goto unmap;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	/* Now unlock and recheck attributes */
+	if (munlock(map, 2 * page_size)) {
+		perror("munlock()");
+		goto unmap;
+	}
+
+	ret = unlock_lock_check(map);
+
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int onfault_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Neither page should be present */
+	if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
+		printf("Pages were made present by MLOCK_ONFAULT\n");
+		return 1;
+	}
+
+	*map = 'a';
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Only page 1 should be present */
+	if ((page1_flags & PRESENT_BIT) == 0) {
+		printf("Page 1 is not present after fault\n");
+		return 1;
+	} else if (page2_flags & PRESENT_BIT) {
+		printf("Page 2 was made present\n");
+		return 1;
+	}
+
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+	/* Page 1 should be unevictable */
+	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+		printf("Failed to make faulted page unevictable\n");
+		return 1;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map)) {
+		printf("VMA is not marked for lock on fault\n");
+		return 1;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA is not marked for lock on fault\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int unlock_onfault_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+	if (page1_flags & UNEVICTABLE_BIT) {
+		printf("Page 1 is still marked unevictable after unlock\n");
+		return 1;
+	}
+
+	if (is_vma_lock_on_fault((unsigned long)map) ||
+	    is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA is still lock on fault after unlock\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int test_mlock_onfault()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(MLOCK_ONFAULT)");
+		goto unmap;
+	}
+
+	if (onfault_check(map))
+		goto unmap;
+
+	/* Now unlock and recheck attributes */
+	if (munlock(map, 2 * page_size)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("munlock()");
+		goto unmap;
+	}
+
+	ret = unlock_onfault_check(map);
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int test_lock_onfault_of_present()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	*map = 'a';
+
+	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(MLOCK_ONFAULT)");
+		goto unmap;
+	}
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	/* Page 1 should be unevictable */
+	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+		printf("Failed to make present page unevictable\n");
+		goto unmap;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map) ||
+	    !is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA with present pages is not marked lock on fault\n");
+		goto unmap;
+	}
+	ret = 0;
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int test_munlockall()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+	if (map == MAP_FAILED) {
+		perror("test_munlockall mmap");
+		goto out;
+	}
+
+	if (mlockall(MCL_CURRENT)) {
+		perror("mlockall(MCL_CURRENT)");
+		goto out;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	if (unlock_lock_check(map))
+		goto unmap;
+
+	munmap(map, 2 * page_size);
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+	if (map == MAP_FAILED) {
+		perror("test_munlockall second mmap");
+		goto out;
+	}
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT)) {
+		perror("mlockall(MCL_CURRENT | MCL_ONFAULT)");
+		goto unmap;
+	}
+
+	if (onfault_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	if (unlock_onfault_check(map))
+		goto unmap;
+
+	if (mlockall(MCL_CURRENT | MCL_FUTURE)) {
+		perror("mlockall(MCL_CURRENT | MCL_FUTURE)");
+		goto out;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	ret = unlock_lock_check(map);
+
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	munlockall();
+	return ret;
+}
+
+static int test_vma_management(bool call_mlock)
+{
+	int ret = 1;
+	void *map;
+	unsigned long page_size = getpagesize();
+	struct vm_boundaries page1;
+	struct vm_boundaries page2;
+	struct vm_boundaries page3;
+
+	map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("mmap()");
+		return ret;
+	}
+
+	if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock(ONFAULT)\n");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/*
+	 * Before we unlock a portion, we need to that all three pages are in
+	 * the same VMA.  If they are not we abort this test (Note that this is
+	 * not a failure)
+	 */
+	if (page1.start != page2.start || page2.start != page3.start) {
+		printf("VMAs are not merged to start, aborting test\n");
+		ret = 0;
+		goto out;
+	}
+
+	if (munlock(map + page_size, page_size)) {
+		perror("munlock()");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/* All three VMAs should be different */
+	if (page1.start == page2.start || page2.start == page3.start) {
+		printf("failed to split VMA for munlock\n");
+		goto out;
+	}
+
+	/* Now unlock the first and third page and check the VMAs again */
+	if (munlock(map, page_size * 3)) {
+		perror("munlock()");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/* Now all three VMAs should be the same */
+	if (page1.start != page2.start || page2.start != page3.start) {
+		printf("failed to merge VMAs after munlock\n");
+		goto out;
+	}
+
+	ret = 0;
+out:
+	munmap(map, 3 * page_size);
+	return ret;
+}
+
+static int test_mlockall(int (test_function)(bool call_mlock))
+{
+	int ret = 1;
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+		perror("mlockall");
+		return ret;
+	}
+
+	ret = test_function(false);
+	munlockall();
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	int ret = 0;
+	ret += test_mlock_lock();
+	ret += test_mlock_onfault();
+	ret += test_munlockall();
+	ret += test_lock_onfault_of_present();
+	ret += test_vma_management(true);
+	ret += test_mlockall(test_vma_management);
+	return ret;
+}
diff --git a/kernel/tools/testing/selftests/vm/on-fault-limit.c b/kernel/tools/testing/selftests/vm/on-fault-limit.c
new file mode 100644
index 000000000..245acccce
--- /dev/null
+++ b/kernel/tools/testing/selftests/vm/on-fault-limit.c
@@ -0,0 +1,47 @@
+#include <sys/mman.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int test_limit(void)
+{
+	int ret = 1;
+	struct rlimit lims;
+	void *map;
+
+	if (getrlimit(RLIMIT_MEMLOCK, &lims)) {
+		perror("getrlimit");
+		return ret;
+	}
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+		perror("mlockall");
+		return ret;
+	}
+
+	map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, 0, 0);
+	if (map != MAP_FAILED)
+		printf("mmap should have failed, but didn't\n");
+	else {
+		ret = 0;
+		munmap(map, 2 * lims.rlim_max);
+	}
+
+	munlockall();
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	int ret = 0;
+
+	ret += test_limit();
+	return ret;
+}
diff --git a/kernel/tools/testing/selftests/vm/run_vmtests b/kernel/tools/testing/selftests/vm/run_vmtests
index c87b68123..e11968b36 100755
--- a/kernel/tools/testing/selftests/vm/run_vmtests
+++ b/kernel/tools/testing/selftests/vm/run_vmtests
@@ -20,13 +20,26 @@ done < /proc/meminfo
 if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
 	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
 	needpgs=`expr $needmem / $pgsize`
-	if [ $freepgs -lt $needpgs ]; then
+	tries=2
+	while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
 		lackpgs=$(( $needpgs - $freepgs ))
+		echo 3 > /proc/sys/vm/drop_caches
 		echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
 		if [ $? -ne 0 ]; then
 			echo "Please run this test as root"
 			exit 1
 		fi
+		while read name size unit; do
+			if [ "$name" = "HugePages_Free:" ]; then
+				freepgs=$size
+			fi
+		done < /proc/meminfo
+		tries=$((tries - 1))
+	done
+	if [ $freepgs -lt $needpgs ]; then
+		printf "Not enough huge pages available (%d < %d)\n" \
+		       $freepgs $needpgs
+		exit 1
 	fi
 else
 	echo "no hugetlbfs support in kernel?"
@@ -75,10 +88,14 @@ else
 	echo "[PASS]"
 fi
 
+echo "NOTE: The above hugetlb tests provide minimal coverage.  Use"
+echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for"
+echo "      hugetlb regression testing."
+
 echo "--------------------"
-echo "running hugetlbfstest"
+echo "running userfaultfd"
 echo "--------------------"
-./hugetlbfstest
+./userfaultfd 128 32
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1
@@ -90,4 +107,38 @@ fi
 umount $mnt
 rm -rf $mnt
 echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
+
+echo "-----------------------"
+echo "running compaction_test"
+echo "-----------------------"
+./compaction_test
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+echo "--------------------"
+echo "running on-fault-limit"
+echo "--------------------"
+sudo -u nobody ./on-fault-limit
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+echo "--------------------"
+echo "running mlock2-tests"
+echo "--------------------"
+./mlock2-tests
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 exit $exitcode
diff --git a/kernel/tools/testing/selftests/vm/userfaultfd.c b/kernel/tools/testing/selftests/vm/userfaultfd.c
new file mode 100644
index 000000000..d77ed41b2
--- /dev/null
+++ b/kernel/tools/testing/selftests/vm/userfaultfd.c
@@ -0,0 +1,645 @@
+/*
+ * 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 <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;
+
+static unsigned long long *count_verify;
+static int uffd, 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)))
+
+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;
+}
+
+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;
+}
+
+static int copy_page(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(uffd, 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;
+}
+
+static void *uffd_poll_thread(void *arg)
+{
+	unsigned long cpu = (unsigned long) arg;
+	struct pollfd pollfd[2];
+	struct uffd_msg msg;
+	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);
+		}
+		if (msg.event != UFFD_EVENT_PAGEFAULT)
+			fprintf(stderr, "unexpected msg event %u\n",
+				msg.event), exit(1);
+		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(offset))
+			userfaults++;
+	}
+	return (void *)userfaults;
+}
+
+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(offset))
+			(*this_cpu_userfaults)++;
+	}
+	return (void *)NULL;
+}
+
+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(page_nr * page_size);
+
+	return NULL;
+}
+
+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 (madvise(area_src, nr_pages * page_size, MADV_DONTNEED)) {
+		perror("madvise");
+		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;
+}
+
+static int userfaultfd_stress(void)
+{
+	void *area;
+	char *tmp_area;
+	unsigned long nr;
+	struct uffdio_register uffdio_register;
+	struct uffdio_api uffdio_api;
+	unsigned long cpu;
+	int uffd_flags, err;
+	unsigned long userfaults[nr_cpus];
+
+	if (posix_memalign(&area, page_size, nr_pages * page_size)) {
+		fprintf(stderr, "out of memory\n");
+		return 1;
+	}
+	area_src = area;
+	if (posix_memalign(&area, page_size, nr_pages * page_size)) {
+		fprintf(stderr, "out of memory\n");
+		return 1;
+	}
+	area_dst = area;
+
+	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 = 0;
+	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;
+	}
+
+	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 = (1 << _UFFDIO_WAKE) |
+				  (1 << _UFFDIO_COPY) |
+				  (1 << _UFFDIO_ZEROPAGE);
+		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 (madvise(area_dst, nr_pages * page_size, MADV_DONTNEED)) {
+			perror("madvise 2");
+			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");
+	}
+
+	return err;
+}
+
+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();
+}
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+	return 0;
+}
+
+#endif /* __NR_userfaultfd */