userfaultfd: retry copying with locks dropped in mfill_atomic_pte_copy()

Implementation of UFFDIO_COPY for anonymous memory might fail to copy data
from userspace buffer when the destination VMA is locked (either with
mm_lock or with per-VMA lock).

In that case, mfill_atomic() releases the locks, retries copying the data
with locks dropped and then re-locks the destination VMA and
re-establishes PMD.

Since this retry-reget dance is only relevant for UFFDIO_COPY and it never
happens for other UFFDIO_ operations, make it a part of
mfill_atomic_pte_copy() that actually implements UFFDIO_COPY for anonymous
memory.

As a temporal safety measure to avoid breaking biscection
mfill_atomic_pte_copy() makes sure to never return -ENOENT so that the
loop in mfill_atomic() won't retry copiyng outside of mmap_lock.  This is
removed later when shmem implementation will be updated later and the loop
in mfill_atomic() will be adjusted.

[akpm@linux-foundation.org: update mfill_copy_folio_retry()]
  Link: https://lore.kernel.org/20260316173829.1126728-1-avagin@google.com
Link: https://lore.kernel.org/20260306171815.3160826-6-rppt@kernel.org
Link: https://lore.kernel.org/20260402041156.1377214-6-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Harry Yoo (Oracle) <harry@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand (Arm) <david@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nikita Kalyazin <kalyazin@amazon.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Carlier <devnexen@gmail.com>
Cc: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 51 insertions, 24 deletions

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index bcba57dc1aee..4857be5a7fa2 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -405,35 +405,63 @@ static int mfill_copy_folio_locked(struct folio *folio, unsigned long src_addr)
 	return ret;
 }
 
+static int mfill_copy_folio_retry(struct mfill_state *state, struct folio *folio)
+{
+	unsigned long src_addr = state->src_addr;
+	void *kaddr;
+	int err;
+
+	/* retry copying with mm_lock dropped */
+	mfill_put_vma(state);
+
+	kaddr = kmap_local_folio(folio, 0);
+	err = copy_from_user(kaddr, (const void __user *) src_addr, PAGE_SIZE);
+	kunmap_local(kaddr);
+	if (unlikely(err))
+		return -EFAULT;
+
+	flush_dcache_folio(folio);
+
+	/* reget VMA and PMD, they could change underneath us */
+	err = mfill_get_vma(state);
+	if (err)
+		return err;
+
+	err = mfill_establish_pmd(state);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 static int mfill_atomic_pte_copy(struct mfill_state *state)
 {
-	struct vm_area_struct *dst_vma = state->vma;
 	unsigned long dst_addr = state->dst_addr;
 	unsigned long src_addr = state->src_addr;
 	uffd_flags_t flags = state->flags;
-	pmd_t *dst_pmd = state->pmd;
 	struct folio *folio;
 	int ret;
 
-	if (!state->folio) {
-		ret = -ENOMEM;
-		folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, dst_vma,
-					dst_addr);
-		if (!folio)
-			goto out;
+	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, state->vma, dst_addr);
+	if (!folio)
+		return -ENOMEM;
 
-		ret = mfill_copy_folio_locked(folio, src_addr);
+	ret = -ENOMEM;
+	if (mem_cgroup_charge(folio, state->vma->vm_mm, GFP_KERNEL))
+		goto out_release;
 
-		/* fallback to copy_from_user outside mmap_lock */
-		if (unlikely(ret)) {
-			ret = -ENOENT;
-			state->folio = folio;
-			/* don't free the page */
-			goto out;
-		}
-	} else {
-		folio = state->folio;
-		state->folio = NULL;
+	ret = mfill_copy_folio_locked(folio, src_addr);
+	if (unlikely(ret)) {
+		/*
+		 * Fallback to copy_from_user outside mmap_lock.
+		 * If retry is successful, mfill_copy_folio_locked() returns
+		 * with locks retaken by mfill_get_vma().
+		 * If there was an error, we must mfill_put_vma() anyway and it
+		 * will take care of unlocking if needed.
+		 */
+		ret = mfill_copy_folio_retry(state, folio);
+		if (ret)
+			goto out_release;
 	}
 
 	/*
@@ -443,17 +471,16 @@ static int mfill_atomic_pte_copy(struct mfill_state *state)
 	 */
 	__folio_mark_uptodate(folio);
 
-	ret = -ENOMEM;
-	if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL))
-		goto out_release;
-
-	ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr,
+	ret = mfill_atomic_install_pte(state->pmd, state->vma, dst_addr,
 				       &folio->page, true, flags);
 	if (ret)
 		goto out_release;
 out:
 	return ret;
 out_release:
+	/* Don't return -ENOENT so that our caller won't retry */
+	if (ret == -ENOENT)
+		ret = -EFAULT;
 	folio_put(folio);
 	goto out;
 }