[PATCH v2 25/47] mm/userfaultfd: wake waiters when registration modes are removed

["David Hildenbrand (Arm)" <david@kernel.org>]

UFFDIO_REGISTER can replace MISSING or MINOR tracking without waking
faults that are already queued. For example, switching an anonymous
range from MISSING to WP leaves a missing-fault waiter asleep until
userspace explicitly wakes it.

When a registration change removes a UFFD mode, wake waiters in the
affected interval after updating the VMA. The VMA is write-locked at
this point, so no new faults can queue under the old modes and woken
threads cannot retry until mmap_write_unlock(). Waiters for retained
modes in the same interval may also wake and refault.

The hang reproduces for MISSING-to-WP and MINOR-to-MISSING transitions,
with both read and unread fault events.

Fixes: 63b2d4174c4a ("userfaultfd: wp: add the writeprotect API to userfaultfd ioctl")
Cc: stable@vger.kernel.org
Reviewed-by: Gregory Price (Meta) <gourry@gourry.net>
Tested-by: Gregory Price (Meta) <gourry@gourry.net>
Signed-off-by: Gregory Price (Meta) <gourry@gourry.net>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
---
 mm/userfaultfd.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index be630674fda9..03f1b15bfe63 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -2270,6 +2270,9 @@ static struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
 	return ret;
 }
 
+static void wake_userfault_range(struct userfaultfd_ctx *ctx,
+		unsigned long start, unsigned long end);
+
 /* Assumes mmap write lock taken, and mm_struct pinned. */
 static int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 			       struct vm_area_struct *vma,
@@ -2287,6 +2290,8 @@ static int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 		prev = vma;
 
 	for_each_vma_range(vmi, vma, end) {
+		const bool any_mode_removed = vma->vm_flags & __VM_UFFD_FLAGS & ~vm_flags;
+
 		cond_resched();
 
 		VM_WARN_ON_ONCE(!vma_can_userfault(vma, vm_flags, wp_async));
@@ -2332,6 +2337,10 @@ static int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 		 */
 		userfaultfd_set_ctx(vma, ctx, vm_flags);
 
+		/* Retry faults for removed modes while the VMA is write-locked. */
+		if (any_mode_removed)
+			wake_userfault_range(ctx, start, vma_end);
+
 		if (vma_is_hugetlb(vma) && uffd_disable_huge_pmd_share(vma))
 			hugetlb_unshare_all_pmds(vma);
 
@@ -3648,6 +3657,17 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 		__wake_userfault(ctx, range);
 }
 
+static void wake_userfault_range(struct userfaultfd_ctx *ctx,
+		unsigned long start, unsigned long end)
+{
+	struct userfaultfd_wake_range range = {
+		.start = start,
+		.len = end - start,
+	};
+
+	wake_userfault(ctx, &range);
+}
+
 static __always_inline int validate_unaligned_range(
 	struct mm_struct *mm, __u64 start, __u64 len)
 {

-- 
2.43.0