1 files changed, 274 insertions, 18 deletions

diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b3d0e2771096..48e8b1539be3 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -1,13 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #define _GNU_SOURCE
-#include "../kselftest_harness.h"
+#include "kselftest_harness.h"
 #include <asm-generic/mman.h> /* Force the import of the tools version. */
 #include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <linux/limits.h>
 #include <linux/userfaultfd.h>
+#include <linux/fs.h>
 #include <setjmp.h>
 #include <signal.h>
 #include <stdbool.h>
@@ -20,6 +21,7 @@
 #include <sys/uio.h>
 #include <unistd.h>
 #include "vm_util.h"
+#include "thp_settings.h"
 
 #include "../pidfd/pidfd.h"
 
@@ -35,13 +37,6 @@ static volatile sig_atomic_t signal_jump_set;
 static sigjmp_buf signal_jmp_buf;
 
 /*
- * Ignore the checkpatch warning, we must read from x but don't want to do
- * anything with it in order to trigger a read page fault. We therefore must use
- * volatile to stop the compiler from optimising this away.
- */
-#define FORCE_READ(x) (*(volatile typeof(x) *)x)
-
-/*
  * How is the test backing the mapping being tested?
  */
 enum backing_type {
@@ -100,6 +95,7 @@ static void *mmap_(FIXTURE_DATA(guard_regions) * self,
 	case ANON_BACKED:
 		flags |= MAP_PRIVATE | MAP_ANON;
 		fd = -1;
+		offset = 0;
 		break;
 	case SHMEM_BACKED:
 	case LOCAL_FILE_BACKED:
@@ -151,7 +147,7 @@ static bool try_access_buf(char *ptr, bool write)
 		if (write)
 			*ptr = 'x';
 		else
-			FORCE_READ(ptr);
+			FORCE_READ(*ptr);
 	}
 
 	signal_jump_set = false;
@@ -266,17 +262,69 @@ static bool is_buf_eq(char *buf, size_t size, char chr)
 	return true;
 }
 
+/*
+ * Some file systems have issues with merging due to changing merge-sensitive
+ * parameters in the .mmap callback, and prior to .mmap_prepare being
+ * implemented everywhere this will now result in an unexpected failure to
+ * merge (e.g. - overlayfs).
+ *
+ * Perform a simple test to see if the local file system suffers from this, if
+ * it does then we can skip test logic that assumes local file system merging is
+ * sane.
+ */
+static bool local_fs_has_sane_mmap(FIXTURE_DATA(guard_regions) * self,
+				   const FIXTURE_VARIANT(guard_regions) * variant)
+{
+	const unsigned long page_size = self->page_size;
+	char *ptr, *ptr2;
+	struct procmap_fd procmap;
+
+	if (variant->backing != LOCAL_FILE_BACKED)
+		return true;
+
+	/* Map 10 pages. */
+	ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0);
+	if (ptr == MAP_FAILED)
+		return false;
+	/* Unmap the middle. */
+	munmap(&ptr[5 * page_size], page_size);
+
+	/* Map again. */
+	ptr2 = mmap_(self, variant, &ptr[5 * page_size], page_size, PROT_READ | PROT_WRITE,
+		     MAP_FIXED, 5 * page_size);
+
+	if (ptr2 == MAP_FAILED)
+		return false;
+
+	/* Now make sure they all merged. */
+	if (open_self_procmap(&procmap) != 0)
+		return false;
+	if (!find_vma_procmap(&procmap, ptr))
+		return false;
+	if (procmap.query.vma_start != (unsigned long)ptr)
+		return false;
+	if (procmap.query.vma_end != (unsigned long)ptr + 10 * page_size)
+		return false;
+	close_procmap(&procmap);
+
+	return true;
+}
+
 FIXTURE_SETUP(guard_regions)
 {
 	self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
 	setup_sighandler();
 
-	if (variant->backing == ANON_BACKED)
+	switch (variant->backing) {
+	case ANON_BACKED:
 		return;
-
-	self->fd = open_file(
-		variant->backing == SHMEM_BACKED ? "/tmp/" : "",
-		self->path);
+	case LOCAL_FILE_BACKED:
+		self->fd = open_file("", self->path);
+		break;
+	case SHMEM_BACKED:
+		self->fd = memfd_create(self->path, 0);
+		break;
+	}
 
 	/* We truncate file to at least 100 pages, tests can modify as needed. */
 	ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
@@ -577,7 +625,7 @@ TEST_F(guard_regions, process_madvise)
 
 	/* OK we don't have permission to do this, skip. */
 	if (count == -1 && errno == EPERM)
-		ksft_exit_skip("No process_madvise() permissions, try running as root.\n");
+		SKIP(return, "No process_madvise() permissions, try running as root.\n");
 
 	/* Returns the number of bytes advised. */
 	ASSERT_EQ(count, 6 * page_size);
@@ -1448,8 +1496,21 @@ TEST_F(guard_regions, uffd)
 
 	/* Set up uffd. */
 	uffd = userfaultfd(0);
-	if (uffd == -1 && errno == EPERM)
-		ksft_exit_skip("No userfaultfd permissions, try running as root.\n");
+	if (uffd == -1) {
+		switch (errno) {
+		case EPERM:
+			SKIP(return, "No userfaultfd permissions, try running as root.");
+			break;
+		case ENOSYS:
+			SKIP(return, "userfaultfd is not supported/not enabled.");
+			break;
+		default:
+			ksft_exit_fail_msg("userfaultfd failed with %s\n",
+					   strerror(errno));
+			break;
+		}
+	}
+
 	ASSERT_NE(uffd, -1);
 
 	ASSERT_EQ(ioctl(uffd, UFFDIO_API, &api), 0);
@@ -1696,7 +1757,7 @@ TEST_F(guard_regions, readonly_file)
 	char *ptr;
 	int i;
 
-	if (variant->backing == ANON_BACKED)
+	if (variant->backing != LOCAL_FILE_BACKED)
 		SKIP(return, "Read-only test specific to file-backed");
 
 	/* Map shared so we can populate with pattern, populate it, unmap. */
@@ -2071,4 +2132,199 @@ TEST_F(guard_regions, pagemap)
 	ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
 }
 
+/*
+ * Assert that PAGEMAP_SCAN correctly reports guard region ranges.
+ */
+TEST_F(guard_regions, pagemap_scan)
+{
+	const unsigned long page_size = self->page_size;
+	struct page_region pm_regs[10];
+	struct pm_scan_arg pm_scan_args = {
+		.size = sizeof(struct pm_scan_arg),
+		.category_anyof_mask = PAGE_IS_GUARD,
+		.return_mask = PAGE_IS_GUARD,
+		.vec = (long)&pm_regs,
+		.vec_len = ARRAY_SIZE(pm_regs),
+	};
+	int proc_fd, i;
+	char *ptr;
+
+	proc_fd = open("/proc/self/pagemap", O_RDONLY);
+	ASSERT_NE(proc_fd, -1);
+
+	ptr = mmap_(self, variant, NULL, 10 * page_size,
+		    PROT_READ | PROT_WRITE, 0, 0);
+	ASSERT_NE(ptr, MAP_FAILED);
+
+	pm_scan_args.start = (long)ptr;
+	pm_scan_args.end = (long)ptr + 10 * page_size;
+	ASSERT_EQ(ioctl(proc_fd, PAGEMAP_SCAN, &pm_scan_args), 0);
+	ASSERT_EQ(pm_scan_args.walk_end, (long)ptr + 10 * page_size);
+
+	/* Install a guard region in every other page. */
+	for (i = 0; i < 10; i += 2) {
+		char *ptr_p = &ptr[i * page_size];
+
+		ASSERT_EQ(syscall(__NR_madvise, ptr_p, page_size, MADV_GUARD_INSTALL), 0);
+	}
+
+	/*
+	 * Assert ioctl() returns the count of located regions, where each
+	 * region spans every other page within the range of 10 pages.
+	 */
+	ASSERT_EQ(ioctl(proc_fd, PAGEMAP_SCAN, &pm_scan_args), 5);
+	ASSERT_EQ(pm_scan_args.walk_end, (long)ptr + 10 * page_size);
+
+	/* Re-read from pagemap, and assert guard regions are detected. */
+	for (i = 0; i < 5; i++) {
+		long ptr_p = (long)&ptr[2 * i * page_size];
+
+		ASSERT_EQ(pm_regs[i].start, ptr_p);
+		ASSERT_EQ(pm_regs[i].end, ptr_p + page_size);
+		ASSERT_EQ(pm_regs[i].categories, PAGE_IS_GUARD);
+	}
+
+	ASSERT_EQ(close(proc_fd), 0);
+	ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+TEST_F(guard_regions, collapse)
+{
+	const unsigned long page_size = self->page_size;
+	const unsigned long size = 2 * HPAGE_SIZE;
+	const unsigned long num_pages = size / page_size;
+	char *ptr;
+	int i;
+
+	if (!thp_available())
+		SKIP(return, "Transparent Hugepages not available\n");
+
+	/* Need file to be correct size for tests for non-anon. */
+	if (variant->backing != ANON_BACKED)
+		ASSERT_EQ(ftruncate(self->fd, size), 0);
+
+	/*
+	 * We must close and re-open local-file backed as read-only for
+	 * CONFIG_READ_ONLY_THP_FOR_FS to work.
+	 */
+	if (variant->backing == LOCAL_FILE_BACKED) {
+		ASSERT_EQ(close(self->fd), 0);
+
+		self->fd = open(self->path, O_RDONLY);
+		ASSERT_GE(self->fd, 0);
+	}
+
+	ptr = mmap_(self, variant, NULL, size, PROT_READ, 0, 0);
+	ASSERT_NE(ptr, MAP_FAILED);
+
+	/* Prevent being faulted-in as huge. */
+	ASSERT_EQ(madvise(ptr, size, MADV_NOHUGEPAGE), 0);
+	/* Fault in. */
+	ASSERT_EQ(madvise(ptr, size, MADV_POPULATE_READ), 0);
+
+	/* Install guard regions in ever other page. */
+	for (i = 0; i < num_pages; i += 2) {
+		char *ptr_page = &ptr[i * page_size];
+
+		ASSERT_EQ(madvise(ptr_page, page_size, MADV_GUARD_INSTALL), 0);
+		/* Accesses should now fail. */
+		ASSERT_FALSE(try_read_buf(ptr_page));
+	}
+
+	/* Allow huge page throughout region. */
+	ASSERT_EQ(madvise(ptr, size, MADV_HUGEPAGE), 0);
+
+	/*
+	 * Now collapse the entire region. This should fail in all cases.
+	 *
+	 * The madvise() call will also fail if CONFIG_READ_ONLY_THP_FOR_FS is
+	 * not set for the local file case, but we can't differentiate whether
+	 * this occurred or if the collapse was rightly rejected.
+	 */
+	EXPECT_NE(madvise(ptr, size, MADV_COLLAPSE), 0);
+
+	/*
+	 * If we introduce a bug that causes the collapse to succeed, gather
+	 * data on whether guard regions are at least preserved. The test will
+	 * fail at this point in any case.
+	 */
+	for (i = 0; i < num_pages; i += 2) {
+		char *ptr_page = &ptr[i * page_size];
+
+		/* Accesses should still fail. */
+		ASSERT_FALSE(try_read_buf(ptr_page));
+	}
+}
+
+TEST_F(guard_regions, smaps)
+{
+	const unsigned long page_size = self->page_size;
+	struct procmap_fd procmap;
+	char *ptr, *ptr2;
+	int i;
+
+	/* Map a region. */
+	ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0);
+	ASSERT_NE(ptr, MAP_FAILED);
+
+	/* We shouldn't yet see a guard flag. */
+	ASSERT_FALSE(check_vmflag_guard(ptr));
+
+	/* Install a single guard region. */
+	ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+
+	/* Now we should see a guard flag. */
+	ASSERT_TRUE(check_vmflag_guard(ptr));
+
+	/*
+	 * Removing the guard region should not change things because we simply
+	 * cannot accurately track whether a given VMA has had all of its guard
+	 * regions removed.
+	 */
+	ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_REMOVE), 0);
+	ASSERT_TRUE(check_vmflag_guard(ptr));
+
+	/* Install guard regions throughout. */
+	for (i = 0; i < 10; i++) {
+		ASSERT_EQ(madvise(&ptr[i * page_size], page_size, MADV_GUARD_INSTALL), 0);
+		/* We should always see the guard region flag. */
+		ASSERT_TRUE(check_vmflag_guard(ptr));
+	}
+
+	/* Split into two VMAs. */
+	ASSERT_EQ(munmap(&ptr[4 * page_size], page_size), 0);
+
+	/* Both VMAs should have the guard flag set. */
+	ASSERT_TRUE(check_vmflag_guard(ptr));
+	ASSERT_TRUE(check_vmflag_guard(&ptr[5 * page_size]));
+
+	/*
+	 * If the local file system is unable to merge VMAs due to having
+	 * unusual characteristics, there is no point in asserting merge
+	 * behaviour.
+	 */
+	if (!local_fs_has_sane_mmap(self, variant)) {
+		TH_LOG("local filesystem does not support sane merging skipping merge test");
+		return;
+	}
+
+	/* Map a fresh VMA between the two split VMAs. */
+	ptr2 = mmap_(self, variant, &ptr[4 * page_size], page_size,
+		     PROT_READ | PROT_WRITE, MAP_FIXED, 4 * page_size);
+	ASSERT_NE(ptr2, MAP_FAILED);
+
+	/*
+	 * Check the procmap to ensure that this VMA merged with the adjacent
+	 * two. The guard region flag is 'sticky' so should not preclude
+	 * merging.
+	 */
+	ASSERT_EQ(open_self_procmap(&procmap), 0);
+	ASSERT_TRUE(find_vma_procmap(&procmap, ptr));
+	ASSERT_EQ(procmap.query.vma_start, (unsigned long)ptr);
+	ASSERT_EQ(procmap.query.vma_end, (unsigned long)ptr + 10 * page_size);
+	ASSERT_EQ(close_procmap(&procmap), 0);
+	/* And, of course, this VMA should have the guard flag set. */
+	ASSERT_TRUE(check_vmflag_guard(ptr));
+}
+
 TEST_HARNESS_MAIN