[PATCH] mm/ksm: fix userfaultfd protection during merge and unmerge

[Lance Yang <lance.yang@linux.dev>]

KSM loses userfaultfd protection when replace_page() builds a new PTE
from vma->vm_page_prot. Dropping its uffd bit lets a subsequent write go
through ordinary COW instead of userfaultfd write protection handling. For
RWP, a merged page also becomes readable without faulting.

Keeping the uffd bit and restoring PAGE_NONE fixes merging, but we also
have to handle unmerging. An existing KSM page can be protected with RWP
before MADV_UNMERGEABLE, so unmerging already needs fixing independently
of preserving RWP during merging.

Unsharing replaces a shared page with a private one and should leave
userfaultfd protection in place, as do_wp_page() already does for write
protection. Currently, an unshare fault reaches do_uffd_rwp() before it
can proceed to do_wp_page().

- With synchronous RWP, handle_userfault() returns VM_FAULT_SIGBUS.
  break_ksm() then reports success with a KSM page still merged.

- With asynchronous RWP, protection is cleared before unsharing.

Preserve the uffd bit when merging, and restore PAGE_NONE for RWP. Let
FAULT_FLAG_UNSHARE skip RWP fault handling and keep PAGE_NONE on each
private copy as well. Unsharing can then complete with RWP still armed
for a subsequent access.

Fixes: 63b2d4174c4a ("userfaultfd: wp: add the writeprotect API to userfaultfd ioctl")
Fixes: 2d427bb01639 ("mm/userfaultfd: add RWP fault delivery and expose UFFDIO_REGISTER_MODE_RWP")
Link: https://lore.kernel.org/all/20261019010934.697895-1-samarth.colleges@gmail.com/
Link: https://lore.kernel.org/all/20261020055518.36087-1-lance.yang@linux.dev/
Cc: stable@vger.kernel.org
Co-developed-by: Samarth Narang <samarth.colleges@gmail.com>
Signed-off-by: Samarth Narang <samarth.colleges@gmail.com>
Signed-off-by: Lance Yang <lance.yang@linux.dev>
---
 mm/ksm.c    |  8 +++++++-
 mm/memory.c | 14 ++++++++++----
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c
index 910a1307ac9f..d6f736a1aa2f 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -34,6 +34,7 @@
 #include <linux/memory.h>
 #include <linux/mmu_notifier.h>
 #include <linux/swap.h>
+#include <linux/userfaultfd_k.h>
 #include <linux/ksm.h>
 #include <linux/hashtable.h>
 #include <linux/freezer.h>
@@ -1463,9 +1464,14 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 		dec_mm_counter(mm, MM_ANONPAGES);
 	}
 
-	/* Preserve soft-dirty when replacing the page. */
+	/* Preserve soft-dirty and uffd protection when replacing the page. */
 	if (pte_soft_dirty(orig_pte))
 		newpte = pte_mksoft_dirty(newpte);
+	if (pte_uffd(orig_pte)) {
+		newpte = pte_mkuffd(newpte);
+		if (userfaultfd_rwp(vma))
+			newpte = pte_modify(newpte, PAGE_NONE);
+	}
 
 	flush_cache_page(vma, addr, pte_pfn(ptep_get(ptep)));
 	/*
diff --git a/mm/memory.c b/mm/memory.c
index 6a93b7fa48b2..99439a7afa63 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4122,8 +4122,11 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		if (unlikely(unshare)) {
 			if (pte_soft_dirty(vmf->orig_pte))
 				entry = pte_mksoft_dirty(entry);
-			if (pte_uffd(vmf->orig_pte))
+			if (pte_uffd(vmf->orig_pte)) {
 				entry = pte_mkuffd(entry);
+				if (userfaultfd_rwp(vma))
+					entry = pte_modify(entry, PAGE_NONE);
+			}
 		} else {
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		}
@@ -6659,9 +6662,12 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 		 * VM_UFFD_RWP VMA, a protnone PTE without the uffd bit is
 		 * NUMA hinting and must still fall through to do_numa_page().
 		 */
-		if (userfaultfd_pte_rwp(vmf->vma, vmf->orig_pte))
-			return do_uffd_rwp(vmf);
-		return do_numa_page(vmf);
+		if (userfaultfd_pte_rwp(vmf->vma, vmf->orig_pte)) {
+			if (!(vmf->flags & FAULT_FLAG_UNSHARE))
+				return do_uffd_rwp(vmf);
+		} else {
+			return do_numa_page(vmf);
+		}
 	}
 
 	spin_lock(vmf->ptl);
-- 
2.49.0