shmem, userfaultfd: implement shmem uffd operations using vm_uffd_ops

Add filemap_add() and filemap_remove() methods to vm_uffd_ops and use them
in __mfill_atomic_pte() to add shmem folios to page cache and remove them
in case of error.

Implement these methods in shmem along with vm_uffd_ops->alloc_folio() and
drop shmem_mfill_atomic_pte().

Since userfaultfd now does not reference any functions from shmem, drop
include if linux/shmem_fs.h from mm/userfaultfd.c

mfill_atomic_install_pte() is not used anywhere outside of mm/userfaultfd,
make it static.

Link: https://lore.kernel.org/20260402041156.1377214-11-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: James Houghton <jthoughton@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrei Vagin <avagin@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand (Arm) <david@kernel.org>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: Harry Yoo (Oracle) <harry@kernel.org>
Cc: Hugh Dickins <hughd@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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 39 insertions, 41 deletions

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index dd191703b320..8a023d9326c2 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -14,7 +14,6 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/mmu_notifier.h>
 #include <linux/hugetlb.h>
-#include <linux/shmem_fs.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include "internal.h"
@@ -338,10 +337,10 @@ static bool mfill_file_over_size(struct vm_area_struct *dst_vma,
  * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem
  * and anon, and for both shared and private VMAs.
  */
-int mfill_atomic_install_pte(pmd_t *dst_pmd,
-			     struct vm_area_struct *dst_vma,
-			     unsigned long dst_addr, struct page *page,
-			     bool newly_allocated, uffd_flags_t flags)
+static int mfill_atomic_install_pte(pmd_t *dst_pmd,
+				    struct vm_area_struct *dst_vma,
+				    unsigned long dst_addr, struct page *page,
+				    uffd_flags_t flags)
 {
 	int ret;
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
@@ -385,9 +384,6 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd,
 		goto out_unlock;
 
 	if (page_in_cache) {
-		/* Usually, cache pages are already added to LRU */
-		if (newly_allocated)
-			folio_add_lru(folio);
 		folio_add_file_rmap_pte(folio, page, dst_vma);
 	} else {
 		folio_add_new_anon_rmap(folio, dst_vma, dst_addr, RMAP_EXCLUSIVE);
@@ -402,6 +398,9 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd,
 
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
 
+	if (page_in_cache)
+		folio_unlock(folio);
+
 	/* No need to invalidate - it was non-present before */
 	update_mmu_cache(dst_vma, dst_addr, dst_pte);
 	ret = 0;
@@ -514,13 +513,22 @@ static int __mfill_atomic_pte(struct mfill_state *state,
 	 */
 	__folio_mark_uptodate(folio);
 
+	if (ops->filemap_add) {
+		ret = ops->filemap_add(folio, state->vma, state->dst_addr);
+		if (ret)
+			goto err_folio_put;
+	}
+
 	ret = mfill_atomic_install_pte(state->pmd, state->vma, dst_addr,
-				       &folio->page, true, flags);
+				       &folio->page, flags);
 	if (ret)
-		goto err_folio_put;
+		goto err_filemap_remove;
 
 	return 0;
 
+err_filemap_remove:
+	if (ops->filemap_remove)
+		ops->filemap_remove(folio, state->vma);
 err_folio_put:
 	folio_put(folio);
 	/* Don't return -ENOENT so that our caller won't retry */
@@ -533,6 +541,18 @@ static int mfill_atomic_pte_copy(struct mfill_state *state)
 {
 	const struct vm_uffd_ops *ops = vma_uffd_ops(state->vma);
 
+	/*
+	 * The normal page fault path for a MAP_PRIVATE mapping in a
+	 * file-backed VMA will invoke the fault, fill the hole in the file and
+	 * COW it right away. The result generates plain anonymous memory.
+	 * So when we are asked to fill a hole in a MAP_PRIVATE mapping, we'll
+	 * generate anonymous memory directly without actually filling the
+	 * hole. For the MAP_PRIVATE case the robustness check only happens in
+	 * the pagetable (to verify it's still none) and not in the page cache.
+	 */
+	if (!(state->vma->vm_flags & VM_SHARED))
+		ops = &anon_uffd_ops;
+
 	return __mfill_atomic_pte(state, ops);
 }
 
@@ -552,7 +572,8 @@ static int mfill_atomic_pte_zeropage(struct mfill_state *state)
 	spinlock_t *ptl;
 	int ret;
 
-	if (mm_forbids_zeropage(dst_vma->vm_mm))
+	if (mm_forbids_zeropage(dst_vma->vm_mm) ||
+	    (dst_vma->vm_flags & VM_SHARED))
 		return mfill_atomic_pte_zeroed_folio(state);
 
 	_dst_pte = pte_mkspecial(pfn_pte(zero_pfn(dst_addr),
@@ -609,11 +630,10 @@ static int mfill_atomic_pte_continue(struct mfill_state *state)
 	}
 
 	ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr,
-				       page, false, flags);
+				       page, flags);
 	if (ret)
 		goto out_release;
 
-	folio_unlock(folio);
 	return 0;
 
 out_release:
@@ -836,41 +856,19 @@ extern ssize_t mfill_atomic_hugetlb(struct userfaultfd_ctx *ctx,
 
 static __always_inline ssize_t mfill_atomic_pte(struct mfill_state *state)
 {
-	struct vm_area_struct *dst_vma = state->vma;
-	unsigned long src_addr = state->src_addr;
-	unsigned long dst_addr = state->dst_addr;
-	struct folio **foliop = &state->folio;
 	uffd_flags_t flags = state->flags;
-	pmd_t *dst_pmd = state->pmd;
-	ssize_t err;
 
 	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
 		return mfill_atomic_pte_continue(state);
 	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON))
 		return mfill_atomic_pte_poison(state);
+	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY))
+		return mfill_atomic_pte_copy(state);
+	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE))
+		return mfill_atomic_pte_zeropage(state);
 
-	/*
-	 * The normal page fault path for a shmem will invoke the
-	 * fault, fill the hole in the file and COW it right away. The
-	 * result generates plain anonymous memory. So when we are
-	 * asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll
-	 * generate anonymous memory directly without actually filling
-	 * the hole. For the MAP_PRIVATE case the robustness check
-	 * only happens in the pagetable (to verify it's still none)
-	 * and not in the radix tree.
-	 */
-	if (!(dst_vma->vm_flags & VM_SHARED)) {
-		if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY))
-			err = mfill_atomic_pte_copy(state);
-		else
-			err = mfill_atomic_pte_zeropage(state);
-	} else {
-		err = shmem_mfill_atomic_pte(dst_pmd, dst_vma,
-					     dst_addr, src_addr,
-					     flags, foliop);
-	}
-
-	return err;
+	VM_WARN_ONCE(1, "Unknown UFFDIO operation, flags: %x", flags);
+	return -EOPNOTSUPP;
 }
 
 static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,