[PATCH v3 7/7] selftests/mm: check that unauthorized MADV_PAGEOUT skips large file folios

[Gregory Price (Meta)]

A caller that neither owns nor may write a file may page out the COW
pages of a private mapping of it, but not its file pages. When the
advised range only partly covers a large file folio, the folio must be
filtered out before it is split, on separate paths for PMD- and
PTE-mapped folios.

Splitting a file folio unmaps all of it, and a partly covered folio can
only be reclaimed after a split, so a split is the failure to look for.

Check that partial MADV_PAGEOUT by such a caller leaves every mapped page
of a PMD-sized shmem folio mapped, both when a PMD maps it and when a
mapping of half of it maps it with PTEs. Since this checks for a split
rather than for reclaim, it needs no swap.

Signed-off-by: Gregory Price (Meta) <gourry@xxxxxxxxxx>
Reviewed-by: Sarthak Sharma <sarthak.sharma@xxxxxxx>
---
 .../testing/selftests/mm/madv_cold_pageout.c  | 114 ++++++++++++++++++
 1 file changed, 114 insertions(+)

diff --git a/tools/testing/selftests/mm/madv_cold_pageout.c b/tools/testing/selftests/mm/madv_cold_pageout.c
index f5a81d7bd08b..5a226ccbacb2 100644
--- a/tools/testing/selftests/mm/madv_cold_pageout.c
+++ b/tools/testing/selftests/mm/madv_cold_pageout.c
@@ -195,6 +195,33 @@ static void pte_map_thp(struct __test_metadata *_metadata, char *mapping,
 	ASSERT_TRUE(flags & KPF_COMPOUND_HEAD);
 }
 
+static char *map_aligned_file(struct __test_metadata *_metadata, int fd,
+			      size_t size, int flags)
+{
+	char *mapping = reserve_aligned(_metadata, size);
+
+	ASSERT_EQ(mmap(mapping, size, PROT_READ | PROT_WRITE, flags | MAP_FIXED,
+		       fd, 0), mapping);
+
+	return mapping;
+}
+
+/* Create a PMD-sized shmem file filled with 1s. */
+static int create_shmem_file(struct __test_metadata *_metadata)
+{
+	char *shared;
+	int fd;
+
+	fd = memfd_create("madv_cold_pageout", 0);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(ftruncate(fd, pmd_size), 0);
+	shared = map_aligned_file(_metadata, fd, pmd_size, MAP_SHARED);
+	memset(shared, 1, pmd_size);
+	ASSERT_EQ(munmap(shared, pmd_size), 0);
+
+	return fd;
+}
+
 static void assert_filled(struct __test_metadata *_metadata,
 			  const char *mapping, size_t size)
 {
@@ -792,6 +819,93 @@ TEST_F(madv_cold_pageout, pageout_private_file_reclaims_only_cow)
 	ASSERT_EQ(munmap(mapping, 2 * page_size), 0);
 }
 
+/*
+ * An unauthorized caller must leave a large file folio of a private mapping
+ * alone, even when the advised range only partly covers it. Splitting the
+ * folio would unmap all of it, so every page must stay mapped, which needs
+ * no swap to check. See pageout_stays_within_range about other unmapping.
+ */
+TEST_F(madv_cold_pageout, pageout_private_file_skips_large_file_folio)
+{
+	char *mapping;
+	size_t offset;
+	int fd;
+
+	if (!pmd_size)
+		SKIP(return, "PMD-sized THPs are not supported");
+	if (geteuid())
+		SKIP(return, "requires root to change credentials");
+	fd = create_shmem_file(_metadata);
+	mapping = map_aligned_file(_metadata, fd, pmd_size, MAP_PRIVATE);
+	if (!collapse(mapping, pmd_size, check_huge_file))
+		SKIP(return, "could not allocate a PMD-sized shmem THP");
+	ASSERT_EQ(fchmod(fd, 0400), 0);
+	if (!drop_privileges())
+		SKIP(return, "could not drop privileges");
+
+	ASSERT_EQ(madvise(mapping, pmd_size / 2, MADV_PAGEOUT), 0);
+	for (offset = 0; offset < pmd_size; offset += page_size) {
+		ASSERT_TRUE(page_is_present(self->pagemap_fd,
+					    mapping + offset))
+			TH_LOG("page at offset %zu was unmapped", offset);
+	}
+	assert_filled(_metadata, mapping, pmd_size);
+
+	ASSERT_EQ(munmap(mapping, pmd_size), 0);
+	close(fd);
+}
+
+/*
+ * The same holds for a large file folio that a private mapping maps with
+ * PTEs: every page the mapping maps must stay mapped. See
+ * pageout_stays_within_range about other unmapping.
+ */
+TEST_F(madv_cold_pageout, pageout_private_file_skips_pte_mapped_file_folio)
+{
+	const size_t size = pmd_size / 2;
+	char *mapping, *shared;
+	unsigned long pfn;
+	uint64_t flags;
+	size_t offset;
+	int fd;
+
+	if (!pmd_size)
+		SKIP(return, "PMD-sized THPs are not supported");
+	if (geteuid())
+		SKIP(return, "requires root to change credentials");
+	if (self->kpageflags_fd < 0)
+		SKIP(return, "cannot read page flags");
+	fd = create_shmem_file(_metadata);
+	shared = map_aligned_file(_metadata, fd, pmd_size, MAP_SHARED);
+	if (!collapse(shared, pmd_size, check_huge_file))
+		SKIP(return, "could not allocate a PMD-sized shmem THP");
+	ASSERT_EQ(munmap(shared, pmd_size), 0);
+
+	/* Mapping half of the folio leaves it mapped by PTEs. */
+	mapping = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+	ASSERT_NE(mapping, MAP_FAILED);
+	assert_filled(_metadata, mapping, size);
+	pfn = pagemap_get_pfn(self->pagemap_fd, mapping);
+	ASSERT_NE(pfn, -1UL);
+	ASSERT_EQ(pageflags_get(pfn, self->kpageflags_fd, &flags), 0);
+	if (!(flags & KPF_COMPOUND_HEAD))
+		SKIP(return, "the shmem THP was split");
+	ASSERT_EQ(fchmod(fd, 0400), 0);
+	if (!drop_privileges())
+		SKIP(return, "could not drop privileges");
+
+	ASSERT_EQ(madvise(mapping, size / 2, MADV_PAGEOUT), 0);
+	for (offset = 0; offset < size; offset += page_size) {
+		ASSERT_TRUE(page_is_present(self->pagemap_fd,
+					    mapping + offset))
+			TH_LOG("page at offset %zu was unmapped", offset);
+	}
+	assert_filled(_metadata, mapping, size);
+
+	ASSERT_EQ(munmap(mapping, size), 0);
+	close(fd);
+}
+
 /* Swap out an anonymous page, to see whether swap works at all. */
 static bool probe_swap(int pagemap_fd)
 {
-- 
2.56.0