[RFC PATCH 04/16] mm: userfaultfd: let UFFDIO_MOVE move memcomp entries
From: nakixii
Date: Mon Nov 16 2026 - 06:04:05 EST
UFFDIO_MOVE rejects memcomp entries as unsupported non-swap entries.
Support moving them without requiring the memory-cgroup, shmem,
writeback or asynchronous-compression paths.
Move nonresident tokens like swap entries while keeping a lookup
reference across PTE revalidation. The reference prevents token reuse
from changing the backing whose resident state was checked. Return
-EAGAIN for a busy entry or a stale token rather than moving it without
a stable handle. Keep zero-token movement neutral to zero ownership.
A resident pending token still names a folio whose anonymous rmap points
to the source address. Restore that folio there, then retry through the
present-PTE move path instead of moving the resident token directly.
Drop both RCU PTE mappings before the token-lock lookup and preserve the
existing PTE and exclusivity checks.
Rollback of memcomp entries makes partially unmapped large folios more
common. The per-page exclusivity check also covers that state without
treating the first page's flag as the flag of every mapped subpage.
Signed-off-by: nakixii <nakixii@xxxxxxxxx>
---
mm/userfaultfd.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 77 insertions(+)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index d8a699981d097ae393a981a33cede5f5ce6e2725..0ed91fdd2e80a89073ce2f165e0d557a55218e55 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -15,6 +15,7 @@
#include <linux/mmu_notifier.h>
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
+#include <linux/memcomp.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include "internal.h"
@@ -1150,6 +1151,9 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
struct anon_vma *src_anon_vma = NULL;
struct mmu_notifier_range range;
int err = 0;
+ swp_entry_t memcomp_checked_entry = { };
+ bool memcomp_token_checked = false;
+ struct memcomp_ref memcomp_checked_ref = { };
flush_cache_range(src_vma, src_addr, src_addr + PAGE_SIZE);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
@@ -1338,6 +1342,77 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
struct folio *folio = NULL;
entry = pte_to_swp_entry(orig_src_pte);
+ if (is_memcomp_entry(entry)) {
+ int resident;
+
+ if (!pte_swp_exclusive(orig_src_pte)) {
+ err = -EBUSY;
+ goto out;
+ }
+ /*
+ * A resident token must be faulted back where its
+ * folio's rmap expects it; the present-pte path then
+ * moves the folio. Any other token carries no
+ * address and moves like a swap entry.
+ *
+ * pte_offset_map_nolock() leaves us in an RCU read-side
+ * section. Drop both mappings before querying the token:
+ * memcomp_entry_resident_get() may take the token mutex when
+ * it wins its trylock, and lockdep quite correctly rejects
+ * even that conditional mutex acquisition in this context.
+ * The PTEs are revalidated by retry before either move path.
+ */
+ /* Zero is a pure value: MOVE keeps its logical owner count. */
+ if (!swp_offset(entry)) {
+ err = move_swap_pte(mm, dst_vma, dst_addr, src_addr,
+ dst_pte, src_pte, orig_dst_pte,
+ orig_src_pte, dst_ptl, src_ptl, NULL);
+ goto out;
+ }
+ if (!memcomp_token_checked ||
+ memcomp_checked_entry.val != entry.val) {
+ if (memcomp_checked_ref.slot)
+ memcomp_entry_resident_put(&memcomp_checked_ref);
+ pte_unmap(src_pte);
+ pte_unmap(dst_pte);
+ dst_pte = NULL;
+ src_pte = NULL;
+ resident = memcomp_entry_resident_get(swp_offset(entry),
+ &memcomp_checked_ref);
+ if (resident < 0) {
+ err = resident;
+ goto out;
+ }
+ if (resident) {
+ struct vm_fault vmf = {
+ .vma = src_vma,
+ .address = src_addr,
+ .pgoff = linear_page_index(src_vma, src_addr),
+ .pmd = src_pmd,
+ .orig_pte = orig_src_pte,
+ };
+
+ err = memcomp_restore_resident(&vmf,
+ &memcomp_checked_ref);
+ memcomp_token_checked = false;
+ if (!err)
+ goto retry;
+ goto out;
+ }
+ if (!memcomp_checked_ref.slot) {
+ /* Do not move a stale token without a stable entry. */
+ err = -EAGAIN;
+ goto out;
+ }
+ memcomp_checked_entry = entry;
+ memcomp_token_checked = true;
+ goto retry;
+ }
+ err = move_swap_pte(mm, dst_vma, dst_addr, src_addr,
+ dst_pte, src_pte, orig_dst_pte,
+ orig_src_pte, dst_ptl, src_ptl, NULL);
+ goto out;
+ }
if (non_swap_entry(entry)) {
if (is_migration_entry(entry)) {
pte_unmap(src_pte);
@@ -1400,6 +1475,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
}
out:
+ if (memcomp_checked_ref.slot)
+ memcomp_entry_resident_put(&memcomp_checked_ref);
if (src_anon_vma) {
anon_vma_unlock_write(src_anon_vma);
put_anon_vma(src_anon_vma);