Merge tag 'vfs-6.16-rc2.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - Fix the AT_HANDLE_CONNECTABLE option so filesystems that don't know
   how to decode a connected non-dir dentry fail the request

 - Use repr(transparent) to ensure identical layout between the C and
   Rust implementation of struct file

 - Add a missing xas_pause() into the dax code employing
   wait_entry_unlocked_exclusive()

 - Fix FOP_DONTCACHE which we disabled for v6.15.

   A folio could get redirtied and/or scheduled for writeback after the
   initial dropbehind test. Change the test accordingly to handle these
   cases so we can re-enable FOP_DONTCACHE again

* tag 'vfs-6.16-rc2.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  exportfs: require ->fh_to_parent() to encode connectable file handles
  rust: file: improve safety comments
  rust: file: mark `LocalFile` as `repr(transparent)`
  fs/dax: Fix "don't skip locked entries when scanning entries"
  iomap: don't lose folio dropbehind state for overwrites
  mm/filemap: unify dropbehind flag testing and clearing
  mm/filemap: unify read/write dropbehind naming
  Revert "Disable FOP_DONTCACHE for now due to bugs"
  mm/filemap: use filemap_end_dropbehind() for read invalidation
  mm/filemap: gate dropbehind invalidate on folio !dirty && !writeback

Author: torvalds

fs/dax.c

@@ -257,7 +257,7 @@ static void *wait_entry_unlocked_exclusive(struct xa_state *xas, void *entry)
 		wq = dax_entry_waitqueue(xas, entry, &ewait.key);
 		prepare_to_wait_exclusive(wq, &ewait.wait,
 					TASK_UNINTERRUPTIBLE);
-		xas_pause(xas);
+		xas_reset(xas);
 		xas_unlock_irq(xas);
 		schedule();
 		finish_wait(wq, &ewait.wait);

fs/iomap/buffered-io.c

@@ -1691,6 +1691,8 @@ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
 		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
 	if (wpc->iomap.flags & IOMAP_F_SHARED)
 		ioend_flags |= IOMAP_IOEND_SHARED;
+	if (folio_test_dropbehind(folio))
+		ioend_flags |= IOMAP_IOEND_DONTCACHE;
 	if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
 		ioend_flags |= IOMAP_IOEND_BOUNDARY;
 

fs/xfs/xfs_aops.c

@@ -436,6 +436,25 @@ xfs_map_blocks(
 	return 0;
 }
 
+static bool
+xfs_ioend_needs_wq_completion(
+	struct iomap_ioend	*ioend)
+{
+	/* Changing inode size requires a transaction. */
+	if (xfs_ioend_is_append(ioend))
+		return true;
+
+	/* Extent manipulation requires a transaction. */
+	if (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED))
+		return true;
+
+	/* Page cache invalidation cannot be done in irq context. */
+	if (ioend->io_flags & IOMAP_IOEND_DONTCACHE)
+		return true;
+
+	return false;
+}
+
 static int
 xfs_submit_ioend(
 	struct iomap_writepage_ctx *wpc,
@@ -460,8 +479,7 @@ xfs_submit_ioend(
 	memalloc_nofs_restore(nofs_flag);
 
 	/* send ioends that might require a transaction to the completion wq */
-	if (xfs_ioend_is_append(ioend) ||
-	    (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED)))
+	if (xfs_ioend_needs_wq_completion(ioend))
 		ioend->io_bio.bi_end_io = xfs_end_bio;
 
 	if (status)

include/linux/exportfs.h

@@ -314,13 +314,23 @@ static inline bool exportfs_can_decode_fh(const struct export_operations *nop)
 static inline bool exportfs_can_encode_fh(const struct export_operations *nop,
 					  int fh_flags)
 {
+	if (!nop)
+		return false;
+
 	/*
 	 * If a non-decodeable file handle was requested, we only need to make
 	 * sure that filesystem did not opt-out of encoding fid.
 	 */
 	if (fh_flags & EXPORT_FH_FID)
 		return exportfs_can_encode_fid(nop);
 
+	/*
+	 * If a connectable file handle was requested, we need to make sure that
+	 * filesystem can also decode connected file handles.
+	 */
+	if ((fh_flags & EXPORT_FH_CONNECTABLE) && !nop->fh_to_parent)
+		return false;
+
 	/*
 	 * If a decodeable file handle was requested, we need to make sure that
 	 * filesystem can also decode file handles.

include/linux/fs.h

@@ -2207,7 +2207,7 @@ struct file_operations {
 /* Supports asynchronous lock callbacks */
 #define FOP_ASYNC_LOCK		((__force fop_flags_t)(1 << 6))
 /* File system supports uncached read/write buffered IO */
-#define FOP_DONTCACHE		0 /* ((__force fop_flags_t)(1 << 7)) */
+#define FOP_DONTCACHE		((__force fop_flags_t)(1 << 7))
 
 /* Wrap a directory iterator that needs exclusive inode access */
 int wrap_directory_iterator(struct file *, struct dir_context *,

include/linux/iomap.h

@@ -377,13 +377,16 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 #define IOMAP_IOEND_BOUNDARY		(1U << 2)
 /* is direct I/O */
 #define IOMAP_IOEND_DIRECT		(1U << 3)
+/* is DONTCACHE I/O */
+#define IOMAP_IOEND_DONTCACHE		(1U << 4)
 
 /*
  * Flags that if set on either ioend prevent the merge of two ioends.
  * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way)
  */
 #define IOMAP_IOEND_NOMERGE_FLAGS \
-	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT)
+	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT | \
+	 IOMAP_IOEND_DONTCACHE)
 
 /*
  * Structure for writeback I/O completions.

mm/filemap.c

@@ -1589,13 +1589,30 @@ int folio_wait_private_2_killable(struct folio *folio)
 }
 EXPORT_SYMBOL(folio_wait_private_2_killable);
 
+static void filemap_end_dropbehind(struct folio *folio)
+{
+	struct address_space *mapping = folio->mapping;
+
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+
+	if (folio_test_writeback(folio) || folio_test_dirty(folio))
+		return;
+	if (!folio_test_clear_dropbehind(folio))
+		return;
+	if (mapping)
+		folio_unmap_invalidate(mapping, folio, 0);
+}
+
 /*
  * If folio was marked as dropbehind, then pages should be dropped when writeback
  * completes. Do that now. If we fail, it's likely because of a big folio -
  * just reset dropbehind for that case and latter completions should invalidate.
  */
-static void folio_end_dropbehind_write(struct folio *folio)
+static void filemap_end_dropbehind_write(struct folio *folio)
 {
+	if (!folio_test_dropbehind(folio))
+		return;
+
 	/*
 	 * Hitting !in_task() should not happen off RWF_DONTCACHE writeback,
 	 * but can happen if normal writeback just happens to find dirty folios
@@ -1604,8 +1621,7 @@ static void folio_end_dropbehind_write(struct folio *folio)
 	 * invalidation in that case.
 	 */
 	if (in_task() && folio_trylock(folio)) {
-		if (folio->mapping)
-			folio_unmap_invalidate(folio->mapping, folio, 0);
+		filemap_end_dropbehind(folio);
 		folio_unlock(folio);
 	}
 }
@@ -1620,8 +1636,6 @@ static void folio_end_dropbehind_write(struct folio *folio)
  */
 void folio_end_writeback(struct folio *folio)
 {
-	bool folio_dropbehind = false;
-
 	VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
 
 	/*
@@ -1643,14 +1657,11 @@ void folio_end_writeback(struct folio *folio)
 	 * reused before the folio_wake_bit().
 	 */
 	folio_get(folio);
-	if (!folio_test_dirty(folio))
-		folio_dropbehind = folio_test_clear_dropbehind(folio);
 	if (__folio_end_writeback(folio))
 		folio_wake_bit(folio, PG_writeback);
-	acct_reclaim_writeback(folio);
 
-	if (folio_dropbehind)
-		folio_end_dropbehind_write(folio);
+	filemap_end_dropbehind_write(folio);
+	acct_reclaim_writeback(folio);
 	folio_put(folio);
 }
 EXPORT_SYMBOL(folio_end_writeback);
@@ -2635,16 +2646,14 @@ static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio)
 	return (pos1 >> shift == pos2 >> shift);
 }
 
-static void filemap_end_dropbehind_read(struct address_space *mapping,
-					struct folio *folio)
+static void filemap_end_dropbehind_read(struct folio *folio)
 {
 	if (!folio_test_dropbehind(folio))
 		return;
 	if (folio_test_writeback(folio) || folio_test_dirty(folio))
 		return;
 	if (folio_trylock(folio)) {
-		if (folio_test_clear_dropbehind(folio))
-			folio_unmap_invalidate(mapping, folio, 0);
+		filemap_end_dropbehind(folio);
 		folio_unlock(folio);
 	}
 }
@@ -2765,7 +2774,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 		for (i = 0; i < folio_batch_count(&fbatch); i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			filemap_end_dropbehind_read(mapping, folio);
+			filemap_end_dropbehind_read(folio);
 			folio_put(folio);
 		}
 		folio_batch_init(&fbatch);

rust/kernel/fs/file.rs

@@ -219,12 +219,13 @@ unsafe impl AlwaysRefCounted for File {
 ///   must be on the same thread as this file.
 ///
 /// [`assume_no_fdget_pos`]: LocalFile::assume_no_fdget_pos
+#[repr(transparent)]
 pub struct LocalFile {
     inner: Opaque<bindings::file>,
 }
 
 // SAFETY: The type invariants guarantee that `LocalFile` is always ref-counted. This implementation
-// makes `ARef<File>` own a normal refcount.
+// makes `ARef<LocalFile>` own a normal refcount.
 unsafe impl AlwaysRefCounted for LocalFile {
     #[inline]
     fn inc_ref(&self) {
@@ -235,7 +236,8 @@ unsafe impl AlwaysRefCounted for LocalFile {
     #[inline]
     unsafe fn dec_ref(obj: ptr::NonNull<LocalFile>) {
         // SAFETY: To call this method, the caller passes us ownership of a normal refcount, so we
-        // may drop it. The cast is okay since `File` has the same representation as `struct file`.
+        // may drop it. The cast is okay since `LocalFile` has the same representation as
+        // `struct file`.
         unsafe { bindings::fput(obj.cast().as_ptr()) }
     }
 }
@@ -273,7 +275,7 @@ impl LocalFile {
     #[inline]
     pub unsafe fn from_raw_file<'a>(ptr: *const bindings::file) -> &'a LocalFile {
         // SAFETY: The caller guarantees that the pointer is not dangling and stays valid for the
-        // duration of 'a. The cast is okay because `File` is `repr(transparent)`.
+        // duration of `'a`. The cast is okay because `LocalFile` is `repr(transparent)`.
         //
         // INVARIANT: The caller guarantees that there are no problematic `fdget_pos` calls.
         unsafe { &*ptr.cast() }
@@ -347,7 +349,7 @@ impl File {
     #[inline]
     pub unsafe fn from_raw_file<'a>(ptr: *const bindings::file) -> &'a File {
         // SAFETY: The caller guarantees that the pointer is not dangling and stays valid for the
-        // duration of 'a. The cast is okay because `File` is `repr(transparent)`.
+        // duration of `'a`. The cast is okay because `File` is `repr(transparent)`.
         //
         // INVARIANT: The caller guarantees that there are no problematic `fdget_pos` calls.
         unsafe { &*ptr.cast() }