userfaultfd: selftests: add write-protect test

Add uffd tests for write protection.

Instead of introducing new tests for it, let's simply squashing uffd-wp
tests into existing uffd-missing test cases. Changes are:

(1) Bouncing tests

We do the write-protection in two ways during the bouncing test:

- By using UFFDIO_COPY_MODE_WP when resolving MISSING pages: then
we'll make sure for each bounce process every single page will be
at least fault twice: once for MISSING, once for WP.

- By direct call UFFDIO_WRITEPROTECT on existing faulted memories:
To further torture the explicit page protection procedures of
uffd-wp, we split each bounce procedure into two halves (in the
background thread): the first half will be MISSING+WP for each
page as explained above. After the first half, we write protect
the faulted region in the background thread to make sure at least
half of the pages will be write protected again which is the first
half to test the new UFFDIO_WRITEPROTECT call. Then we continue
with the 2nd half, which will contain both MISSING and WP faulting
tests for the 2nd half and WP-only faults from the 1st half.

(2) Event/Signal test

Mostly previous tests but will do MISSING+WP for each page. For
sigbus-mode test we'll need to provide standalone path to handle the
write protection faults.

For all tests, do statistics as well for uffd-wp pages.

Signed-off-by: Peter Xu <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Cc: Andrea Arcangeli <[e-mail]>
Cc: Bobby Powers <[e-mail]>
Cc: Brian Geffon <[e-mail]>
Cc: David Hildenbrand <[e-mail]>
Cc: Denis Plotnikov <[e-mail]>
Cc: "Dr . David Alan Gilbert" <[e-mail]>
Cc: Hugh Dickins <[e-mail]>
Cc: Jerome Glisse <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: "Kirill A . Shutemov" <[e-mail]>
Cc: Martin Cracauer <[e-mail]>
Cc: Marty McFadden <[e-mail]>
Cc: Maya Gokhale <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Cc: Mike Kravetz <[e-mail]>
Cc: Mike Rapoport <[e-mail]>
Cc: Pavel Emelyanov <[e-mail]>
Cc: Rik van Riel <[e-mail]>
Cc: Shaohua Li <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Linus Torvalds <[e-mail]>

tools/testing/selftests/vm/userfaultfd.c

···
 #include <linux/userfaultfd.h>
 #include <setjmp.h>
 #include <stdbool.h>
+#include <assert.h>
 
 #include "../kselftest.h"
 
···
 #define ALARM_INTERVAL_SECS 10
 static volatile bool test_uffdio_copy_eexist = true;
 static volatile bool test_uffdio_zeropage_eexist = true;
+/* Whether to test uffd write-protection */
+static bool test_uffdio_wp = false;
 
 static bool map_shared;
 static int huge_fd;
···
 struct uffd_stats {
 	int cpu;
 	unsigned long missing_faults;
+	unsigned long wp_faults;
 };
 
 /* pthread_mutex_t starts at page offset 0 */
···
 	for (i = 0; i < n_cpus; i++) {
 		uffd_stats[i].cpu = i;
 		uffd_stats[i].missing_faults = 0;
+		uffd_stats[i].wp_faults = 0;
 	}
+}
+
+static void uffd_stats_report(struct uffd_stats *stats, int n_cpus)
+{
+	int i;
+	unsigned long long miss_total = 0, wp_total = 0;
+
+	for (i = 0; i < n_cpus; i++) {
+		miss_total += stats[i].missing_faults;
+		wp_total += stats[i].wp_faults;
+	}
+
+	printf("userfaults: %llu missing (", miss_total);
+	for (i = 0; i < n_cpus; i++)
+		printf("%lu+", stats[i].missing_faults);
+	printf("\b), %llu wp (", wp_total);
+	for (i = 0; i < n_cpus; i++)
+		printf("%lu+", stats[i].wp_faults);
+	printf("\b)\n");
 }
 
 static int anon_release_pages(char *rel_area)
···
 	void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
 };
 
-#define ANON_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
+#define SHMEM_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
 					 (1 << _UFFDIO_COPY) | \
 					 (1 << _UFFDIO_ZEROPAGE))
+
+#define ANON_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
+					 (1 << _UFFDIO_COPY) | \
+					 (1 << _UFFDIO_ZEROPAGE) | \
+					 (1 << _UFFDIO_WRITEPROTECT))
 
 static struct uffd_test_ops anon_uffd_test_ops = {
 	.expected_ioctls = ANON_EXPECTED_IOCTLS,
···
 };
 
 static struct uffd_test_ops shmem_uffd_test_ops = {
-	.expected_ioctls = ANON_EXPECTED_IOCTLS,
+	.expected_ioctls = SHMEM_EXPECTED_IOCTLS,
 	.allocate_area	= shmem_allocate_area,
 	.release_pages	= shmem_release_pages,
 	.alias_mapping = noop_alias_mapping,
···
 		if (str1[i] != str2[i])
 			return 1;
 	return 0;
+}
+
+static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
+{
+	struct uffdio_writeprotect prms = { 0 };
+
+	/* Write protection page faults */
+	prms.range.start = start;
+	prms.range.len = len;
+	/* Undo write-protect, do wakeup after that */
+	prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0;
+
+	if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms))
+		fprintf(stderr, "clear WP failed for address 0x%Lx\n",
+			start), exit(1);
 }
 
 static void *locking_thread(void *arg)
···
 	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;
+	if (test_uffdio_wp)
+		uffdio_copy.mode = UFFDIO_COPY_MODE_WP;
+	else
+		uffdio_copy.mode = 0;
 	uffdio_copy.copy = 0;
 	if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
 		/* real retval in ufdio_copy.copy */
···
 		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);
+	if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) {
+		wp_range(uffd, msg->arg.pagefault.address, page_size, false);
+		stats->wp_faults++;
+	} else {
+		/* Missing page faults */
+		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);
+		offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+		offset &= ~(page_size-1);
 
-	if (copy_page(uffd, offset))
-		stats->missing_faults++;
+		if (copy_page(uffd, offset))
+			stats->missing_faults++;
+	}
 }
 
 static void *uffd_poll_thread(void *arg)
···
 static void *background_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
-	unsigned long page_nr;
+	unsigned long page_nr, start_nr, mid_nr, end_nr;
 
-	for (page_nr = cpu * nr_pages_per_cpu;
-	     page_nr < (cpu+1) * nr_pages_per_cpu;
-	     page_nr++)
+	start_nr = cpu * nr_pages_per_cpu;
+	end_nr = (cpu+1) * nr_pages_per_cpu;
+	mid_nr = (start_nr + end_nr) / 2;
+
+	/* Copy the first half of the pages */
+	for (page_nr = start_nr; page_nr < mid_nr; page_nr++)
+		copy_page_retry(uffd, page_nr * page_size);
+
+	/*
+	 * If we need to test uffd-wp, set it up now.  Then we'll have
+	 * at least the first half of the pages mapped already which
+	 * can be write-protected for testing
+	 */
+	if (test_uffdio_wp)
+		wp_range(uffd, (unsigned long)area_dst + start_nr * page_size,
+			nr_pages_per_cpu * page_size, true);
+
+	/*
+	 * Continue the 2nd half of the page copying, handling write
+	 * protection faults if any
+	 */
+	for (page_nr = mid_nr; page_nr < end_nr; page_nr++)
 		copy_page_retry(uffd, page_nr * page_size);
 
 	return NULL;
···
 	}
 
 	for (nr = 0; nr < split_nr_pages; nr++) {
+		int steps = 1;
+		unsigned long offset = nr * page_size;
+
 		if (signal_test) {
 			if (sigsetjmp(*sigbuf, 1) != 0) {
-				if (nr == lastnr) {
+				if (steps == 1 && nr == lastnr) {
 					fprintf(stderr, "Signal repeated\n");
 					return 1;
 				}
 
 				lastnr = nr;
 				if (signal_test == 1) {
-					if (copy_page(uffd, nr * page_size))
-						signalled++;
+					if (steps == 1) {
+						/* This is a MISSING request */
+						steps++;
+						if (copy_page(uffd, offset))
+							signalled++;
+					} else {
+						/* This is a WP request */
+						assert(steps == 2);
+						wp_range(uffd,
+							 (__u64)area_dst +
+							 offset,
+							 page_size, false);
+					}
 				} else {
 					signalled++;
 					continue;
···
 			fprintf(stderr,
 				"nr %lu memory corruption %Lu %Lu\n",
 				nr, count,
-				count_verify[nr]), exit(1);
-		}
+				count_verify[nr]);
+	        }
+		/*
+		 * Trigger write protection if there is by writting
+		 * the same value back.
+		 */
+		*area_count(area_dst, nr) = count;
 	}
 
 	if (signal_test)
···
 				nr, count,
 				count_verify[nr]), exit(1);
 		}
+		/*
+		 * Trigger write protection if there is by writting
+		 * the same value back.
+		 */
+		*area_count(area_dst, nr) = count;
 	}
 
 	if (uffd_test_ops->release_pages(area_dst))
···
 	uffdio_register.range.start = (unsigned long) area_dst;
 	uffdio_register.range.len = nr_pages * page_size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+	if (test_uffdio_wp)
+		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		fprintf(stderr, "register failure\n"), exit(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 (test_uffdio_wp)
+		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		fprintf(stderr, "register failure\n"), exit(1);
 
···
 		return 1;
 
 	close(uffd);
-	printf("userfaults: %ld\n", stats.missing_faults);
+
+	uffd_stats_report(&stats, 1);
 
 	return stats.missing_faults != nr_pages;
 }
···
 	uffdio_register.range.start = (unsigned long) area_dst;
 	uffdio_register.range.len = nr_pages * page_size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+	if (test_uffdio_wp)
+		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		fprintf(stderr, "register failure\n"), exit(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 (test_uffdio_wp)
+			uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
 		if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
 			fprintf(stderr, "register failure\n");
 			return 1;
···
 		if (stress(uffd_stats))
 			return 1;
 
+		/* Clear all the write protections if there is any */
+		if (test_uffdio_wp)
+			wp_range(uffd, (unsigned long)area_dst,
+				 nr_pages * page_size, false);
+
 		/* unregister */
 		if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) {
 			fprintf(stderr, "unregister failure\n");
···
 		area_src_alias = area_dst_alias;
 		area_dst_alias = tmp_area;
 
-		printf("userfaults:");
-		for (cpu = 0; cpu < nr_cpus; cpu++)
-			printf(" %lu", uffd_stats[cpu].missing_faults);
-		printf("\n");
+		uffd_stats_report(uffd_stats, nr_cpus);
 	}
 
 	if (err)
···
 	if (!strcmp(type, "anon")) {
 		test_type = TEST_ANON;
 		uffd_test_ops = &anon_uffd_test_ops;
+		/* Only enable write-protect test for anonymous test */
+		test_uffdio_wp = true;
 	} else if (!strcmp(type, "hugetlb")) {
 		test_type = TEST_HUGETLB;
 		uffd_test_ops = &hugetlb_uffd_test_ops;