fs/proc/task_mmu: fix PAGEMAP_SCAN written state for unpopulated ptes

PAGEMAP_SCAN reports an unpopulated pte differently depending on which
path serves the request.  The PAGE_IS_WRITTEN fast path in
pagemap_scan_pmd_entry() reports a pte_none as written (and, under
PM_SCAN_WP_MATCHING, arms a marker); pagemap_page_category() returns 0 for
the same pte_none.  A request that cannot take the fast path (an extra
category bit, category_anyof_mask or category_inverted) therefore reports
the pte as clean and skips arming it.

A range that was populated and then MADV_DONTNEED'd reads as written via
one mask and clean via another, and in the latter case is not re-armed for
the next round -- an incremental-dump consumer (e.g.  CRIU) using a richer
mask drops the zapped range and stops tracking writes to it.

Report pte_none as written in pagemap_page_category() too.  A pte_none
carries no uffd-wp marker, i.e.  it is not write-protected -- the same
condition under which the present and swap cases already report
PAGE_IS_WRITTEN.  The fast path applies no VMA test, so neither does this.

The hugetlb and fully-unpopulated-PMD (no page table) scans have no
PAGE_IS_WRITTEN fast path, so they do not exhibit the per-entry divergence
and are left unchanged.

Add a pagemap_ioctl selftest that populates a range, drops it with
MADV_DONTNEED, and checks that the fast path and the generic
(category_anyof_mask) path both report every page written.

Link: https://lore.kernel.org/20260707151349.92143-1-kirill@shutemov.name
Fixes: 12f6b01a0bcb ("fs/proc/task_mmu: add fast paths to get/clear PAGE_IS_WRITTEN flag")
Signed-off-by: Kiryl Shutsemau <kas@kernel.org>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Assisted-by: Claude:claude-fable-5
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 67 insertions, 3 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index d32408f7cd5e..d45c729ab6bb 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -2432,8 +2432,18 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 {
 	unsigned long categories;
 
-	if (pte_none(pte))
-		return 0;
+	if (pte_none(pte)) {
+		/*
+		 * An unpopulated pte carries no uffd-wp marker, i.e. it is not
+		 * write-protected, the same condition under which the present
+		 * and swap cases below report PAGE_IS_WRITTEN. Report it here
+		 * too so this generic path agrees with the PAGE_IS_WRITTEN fast
+		 * path in pagemap_scan_pmd_entry(), which reports pte_none as
+		 * written and, under PM_SCAN_WP_MATCHING, arms a marker. The
+		 * fast path applies no VMA test, so neither does this.
+		 */
+		return PAGE_IS_WRITTEN;
+	}
 
 	if (pte_present(pte)) {
 		struct page *page;
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index 6f8971d5b3ce..f9bcff8e78fa 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -1051,6 +1051,57 @@ static void test_simple(void)
 	ksft_test_result(i == TEST_ITERATIONS, "Test %s\n", __func__);
 }
 
+/*
+ * A range that was populated and then MADV_DONTNEED'd is genuine pte_none
+ * with no uffd-wp marker. Such a pte must read the same regardless of which
+ * PAGEMAP_SCAN path serves the request: both the PAGE_IS_WRITTEN fast path and
+ * the generic path (reached e.g. via category_anyof_mask) must report every
+ * page written.
+ */
+static void unpopulated_scan_test(void)
+{
+	int npages = 16, i;
+	long mem_size = npages * page_size;
+	struct page_region regions[16];
+	long fast = 0, slow = 0, ret;
+	char *mem;
+
+	mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (mem == MAP_FAILED)
+		ksft_exit_fail_msg("%s mmap failed\n", __func__);
+
+	wp_init(mem, mem_size);
+
+	/* Populate, then drop: the ptes become pte_none without a marker. */
+	memset(mem, 1, mem_size);
+	if (madvise(mem, mem_size, MADV_DONTNEED))
+		ksft_exit_fail_msg("%s MADV_DONTNEED failed\n", __func__);
+
+	/* Fast path: category_mask == return_mask == PAGE_IS_WRITTEN. */
+	ret = pagemap_ioctl(mem, mem_size, regions, npages, 0, 0,
+			    PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s fast scan failed\n", __func__);
+	for (i = 0; i < ret; i++)
+		fast += LEN(regions[i]);
+
+	/* Generic path: same query expressed via category_anyof_mask. */
+	ret = pagemap_ioctl(mem, mem_size, regions, npages, 0, 0,
+			    0, PAGE_IS_WRITTEN, 0, PAGE_IS_WRITTEN);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s generic scan failed\n", __func__);
+	for (i = 0; i < ret; i++)
+		slow += LEN(regions[i]);
+
+	ksft_test_result(fast == npages && slow == npages,
+			 "%s unpopulated ptes reported written by both paths (%ld, %ld of %d)\n",
+			 __func__, fast, slow, npages);
+
+	wp_free(mem, mem_size);
+	munmap(mem, mem_size);
+}
+
 int sanity_tests(void)
 {
 	unsigned long long mem_size, vec_size;
@@ -1559,7 +1610,7 @@ int main(int __attribute__((unused)) argc, char *argv[])
 	if (!hugetlb_setup_default(4))
 		ksft_print_msg("HugeTLB test will be skipped\n");
 
-	ksft_set_plan(117);
+	ksft_set_plan(118);
 
 	page_size = getpagesize();
 	hpage_size = read_pmd_pagesize();
@@ -1737,6 +1788,9 @@ int main(int __attribute__((unused)) argc, char *argv[])
 	/* 17. ZEROPFN tests */
 	zeropfn_tests();
 
+	/* 18. Unpopulated pte scan-path consistency */
+	unpopulated_scan_test();
+
 	close(pagemap_fd);
 	ksft_finished();
 }