fs/proc/task_mmu: fix uffd-wp confusion in pagemap_scan_pmd_entry()

pagemap_scan_pmd_entry() checks if uffd-wp is set on each pte to avoid
unnecessary if set.  However it was previously checking with
`pte_uffd_wp(ptep_get(pte))` without first confirming that the pte was
present.  It is only valid to call pte_uffd_wp() for present ptes.  For
swap ptes, pte_swp_uffd_wp() must be called because the uffd-wp bit may be
kept in a different position, depending on the arch.

This was leading to test failures in the pagemap_ioctl mm selftest, when
bringing up uffd-wp support on arm64 due to incorrectly interpretting the
uffd-wp status of migration entries.

Let's fix this by using the correct check based on pte_present().  While
we are at it, let's pass the pte to make_uffd_wp_pte() to avoid the
pointless extra ptep_get() which can't be optimized out due to READ_ONCE()
on many arches.

Link: https://lkml.kernel.org/r/20240429114104.182890-1-ryan.roberts@arm.com
Fixes: 12f6b01a0bcb ("fs/proc/task_mmu: add fast paths to get/clear PAGE_IS_WRITTEN flag")
Closes: https://lore.kernel.org/linux-arm-kernel/ZiuyGXt0XWwRgFh9@x1n/
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Tested-by: Muhammad Usama Anjum <usama.anjum@collabora.com> 
Cc: Peter Xu <peterx@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 13 insertions, 9 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index af4bc1da0c01..102f48668c35 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1817,10 +1817,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 }
 
 static void make_uffd_wp_pte(struct vm_area_struct *vma,
-			     unsigned long addr, pte_t *pte)
+			     unsigned long addr, pte_t *pte, pte_t ptent)
 {
-	pte_t ptent = ptep_get(pte);
-
 	if (pte_present(ptent)) {
 		pte_t old_pte;
 
@@ -2175,9 +2173,12 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 	if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) {
 		/* Fast path for performing exclusive WP */
 		for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
-			if (pte_uffd_wp(ptep_get(pte)))
+			pte_t ptent = ptep_get(pte);
+
+			if ((pte_present(ptent) && pte_uffd_wp(ptent)) ||
+			    pte_swp_uffd_wp_any(ptent))
 				continue;
-			make_uffd_wp_pte(vma, addr, pte);
+			make_uffd_wp_pte(vma, addr, pte, ptent);
 			if (!flush_end)
 				start = addr;
 			flush_end = addr + PAGE_SIZE;
@@ -2190,8 +2191,10 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 	    p->arg.return_mask == PAGE_IS_WRITTEN) {
 		for (addr = start; addr < end; pte++, addr += PAGE_SIZE) {
 			unsigned long next = addr + PAGE_SIZE;
+			pte_t ptent = ptep_get(pte);
 
-			if (pte_uffd_wp(ptep_get(pte)))
+			if ((pte_present(ptent) && pte_uffd_wp(ptent)) ||
+			    pte_swp_uffd_wp_any(ptent))
 				continue;
 			ret = pagemap_scan_output(p->cur_vma_category | PAGE_IS_WRITTEN,
 						  p, addr, &next);
@@ -2199,7 +2202,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 				break;
 			if (~p->arg.flags & PM_SCAN_WP_MATCHING)
 				continue;
-			make_uffd_wp_pte(vma, addr, pte);
+			make_uffd_wp_pte(vma, addr, pte, ptent);
 			if (!flush_end)
 				start = addr;
 			flush_end = next;
@@ -2208,8 +2211,9 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 	}
 
 	for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
+		pte_t ptent = ptep_get(pte);
 		unsigned long categories = p->cur_vma_category |
-					   pagemap_page_category(p, vma, addr, ptep_get(pte));
+					   pagemap_page_category(p, vma, addr, ptent);
 		unsigned long next = addr + PAGE_SIZE;
 
 		if (!pagemap_scan_is_interesting_page(categories, p))
@@ -2224,7 +2228,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 		if (~categories & PAGE_IS_WRITTEN)
 			continue;
 
-		make_uffd_wp_pte(vma, addr, pte);
+		make_uffd_wp_pte(vma, addr, pte, ptent);
 		if (!flush_end)
 			start = addr;
 		flush_end = next;