Merge tag 'vfs-6.10.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "This contains the usual miscellaneous features, cleanups, and fixes
  for vfs and individual fses.

  Features:

   - Free up FMODE_* bits. I've freed up bits 6, 7, 8, and 24. That
     means we now have six free FMODE_* bits in total (but bit khadas#6
     already got used for FMODE_WRITE_RESTRICTED)

   - Add FOP_HUGE_PAGES flag (follow-up to FMODE_* cleanup)

   - Add fd_raw cleanup class so we can make use of automatic cleanup
     provided by CLASS(fd_raw, f)(fd) for O_PATH fds as well

   - Optimize seq_puts()

   - Simplify __seq_puts()

   - Add new anon_inode_getfile_fmode() api to allow specifying f_mode
     instead of open-coding it in multiple places

   - Annotate struct file_handle with __counted_by() and use
     struct_size()

   - Warn in get_file() whether f_count resurrection from zero is
     attempted (epoll/drm discussion)

   - Folio-sophize aio

   - Export the subvolume id in statx() for both btrfs and bcachefs

   - Relax linkat(AT_EMPTY_PATH) requirements

   - Add F_DUPFD_QUERY fcntl() allowing to compare two file descriptors
     for dup*() equality replacing kcmp()

  Cleanups:

   - Compile out swapfile inode checks when swap isn't enabled

   - Use (1 << n) notation for FMODE_* bitshifts for clarity

   - Remove redundant variable assignment in fs/direct-io

   - Cleanup uses of strncpy in orangefs

   - Speed up and cleanup writeback

   - Move fsparam_string_empty() helper into header since it's currently
     open-coded in multiple places

   - Add kernel-doc comments to proc_create_net_data_write()

   - Don't needlessly read dentry->d_flags twice

  Fixes:

   - Fix out-of-range warning in nilfs2

   - Fix ecryptfs overflow due to wrong encryption packet size
     calculation

   - Fix overly long line in xfs file_operations (follow-up to FMODE_*
     cleanup)

   - Don't raise FOP_BUFFER_{R,W}ASYNC for directories in xfs (follow-up
     to FMODE_* cleanup)

   - Don't call xfs_file_open from xfs_dir_open (follow-up to FMODE_*
     cleanup)

   - Fix stable offset api to prevent endless loops

   - Fix afs file server rotations

   - Prevent xattr node from overflowing the eraseblock in jffs2

   - Move fdinfo PTRACE_MODE_READ procfs check into the .permission()
     operation instead of .open() operation since this caused userspace
     regressions"

* tag 'vfs-6.10.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (39 commits)
  afs: Fix fileserver rotation getting stuck
  selftests: add F_DUPDFD_QUERY selftests
  fcntl: add F_DUPFD_QUERY fcntl()
  file: add fd_raw cleanup class
  fs: WARN when f_count resurrection is attempted
  seq_file: Simplify __seq_puts()
  seq_file: Optimize seq_puts()
  proc: Move fdinfo PTRACE_MODE_READ check into the inode .permission operation
  fs: Create anon_inode_getfile_fmode()
  xfs: don't call xfs_file_open from xfs_dir_open
  xfs: drop fop_flags for directories
  xfs: fix overly long line in the file_operations
  shmem: Fix shmem_rename2()
  libfs: Add simple_offset_rename() API
  libfs: Fix simple_offset_rename_exchange()
  jffs2: prevent xattr node from overflowing the eraseblock
  vfs, swap: compile out IS_SWAPFILE() on swapless configs
  vfs: relax linkat() AT_EMPTY_PATH - aka flink() - requirements
  fs/direct-io: remove redundant assignment to variable retval
  fs/dcache: Re-use value stored to dentry->d_flags instead of re-reading
  ...

Author: torvalds

block/bdev.c

@@ -912,7 +912,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 		disk_unblock_events(disk);
 
 	bdev_file->f_flags |= O_LARGEFILE;
-	bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
+	bdev_file->f_mode |= FMODE_CAN_ODIRECT;
 	if (bdev_nowait(bdev))
 		bdev_file->f_mode |= FMODE_NOWAIT;
 	if (mode & BLK_OPEN_RESTRICT_WRITES)

block/fops.c

@@ -863,6 +863,7 @@ const struct file_operations def_blk_fops = {
 	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= blkdev_fallocate,
+	.fop_flags	= FOP_BUFFER_RASYNC,
 };
 
 static __init int blkdev_init(void)

drivers/dax/device.c

@@ -377,7 +377,7 @@ static const struct file_operations dax_fops = {
 	.release = dax_release,
 	.get_unmapped_area = dax_get_unmapped_area,
 	.mmap = dax_mmap,
-	.mmap_supported_flags = MAP_SYNC,
+	.fop_flags = FOP_MMAP_SYNC,
 };
 
 static void dev_dax_cdev_del(void *cdev)

fs/afs/rotate.c

@@ -541,11 +541,13 @@ bool afs_select_fileserver(struct afs_operation *op)
 		    test_bit(AFS_SE_EXCLUDED, &se->flags) ||
 		    !test_bit(AFS_SERVER_FL_RESPONDING, &s->flags))
 			continue;
-		es = op->server_states->endpoint_state;
+		es = op->server_states[i].endpoint_state;
 		sal = es->addresses;
 
 		afs_get_address_preferences_rcu(op->net, sal);
 		for (j = 0; j < sal->nr_addrs; j++) {
+			if (es->failed_set & (1 << j))
+				continue;
 			if (!sal->addrs[j].peer)
 				continue;
 			if (sal->addrs[j].prio > best_prio) {
@@ -605,6 +607,8 @@ bool afs_select_fileserver(struct afs_operation *op)
 	best_prio = -1;
 	addr_index = 0;
 	for (i = 0; i < alist->nr_addrs; i++) {
+		if (!(set & (1 << i)))
+			continue;
 		if (alist->addrs[i].prio > best_prio) {
 			addr_index = i;
 			best_prio = alist->addrs[i].prio;
@@ -674,7 +678,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	for (i = 0; i < op->server_list->nr_servers; i++) {
 		struct afs_endpoint_state *estate;
 
-		estate = op->server_states->endpoint_state;
+		estate = op->server_states[i].endpoint_state;
 		error = READ_ONCE(estate->error);
 		if (error < 0)
 			afs_op_accumulate_error(op, error, estate->abort_code);

fs/aio.c

@@ -122,7 +122,7 @@ struct kioctx {
 	unsigned long		mmap_base;
 	unsigned long		mmap_size;
 
-	struct page		**ring_pages;
+	struct folio		**ring_folios;
 	long			nr_pages;
 
 	struct rcu_work		free_rwork;	/* see free_ioctx() */
@@ -160,7 +160,7 @@ struct kioctx {
 		spinlock_t	completion_lock;
 	} ____cacheline_aligned_in_smp;
 
-	struct page		*internal_pages[AIO_RING_PAGES];
+	struct folio		*internal_folios[AIO_RING_PAGES];
 	struct file		*aio_ring_file;
 
 	unsigned		id;
@@ -334,19 +334,20 @@ static void aio_free_ring(struct kioctx *ctx)
 	put_aio_ring_file(ctx);
 
 	for (i = 0; i < ctx->nr_pages; i++) {
-		struct page *page;
-		pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
-				page_count(ctx->ring_pages[i]));
-		page = ctx->ring_pages[i];
-		if (!page)
+		struct folio *folio = ctx->ring_folios[i];
+
+		if (!folio)
 			continue;
-		ctx->ring_pages[i] = NULL;
-		put_page(page);
+
+		pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i,
+			 folio_ref_count(folio));
+		ctx->ring_folios[i] = NULL;
+		folio_put(folio);
 	}
 
-	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) {
-		kfree(ctx->ring_pages);
-		ctx->ring_pages = NULL;
+	if (ctx->ring_folios && ctx->ring_folios != ctx->internal_folios) {
+		kfree(ctx->ring_folios);
+		ctx->ring_folios = NULL;
 	}
 }
 
@@ -441,7 +442,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 	idx = src->index;
 	if (idx < (pgoff_t)ctx->nr_pages) {
 		/* Make sure the old folio hasn't already been changed */
-		if (ctx->ring_pages[idx] != &src->page)
+		if (ctx->ring_folios[idx] != src)
 			rc = -EAGAIN;
 	} else
 		rc = -EINVAL;
@@ -465,8 +466,8 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 	 */
 	spin_lock_irqsave(&ctx->completion_lock, flags);
 	folio_migrate_copy(dst, src);
-	BUG_ON(ctx->ring_pages[idx] != &src->page);
-	ctx->ring_pages[idx] = &dst->page;
+	BUG_ON(ctx->ring_folios[idx] != src);
+	ctx->ring_folios[idx] = dst;
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 	/* The old folio is no longer accessible. */
@@ -516,28 +517,30 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
 			/ sizeof(struct io_event);
 
-	ctx->ring_pages = ctx->internal_pages;
+	ctx->ring_folios = ctx->internal_folios;
 	if (nr_pages > AIO_RING_PAGES) {
-		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
-					  GFP_KERNEL);
-		if (!ctx->ring_pages) {
+		ctx->ring_folios = kcalloc(nr_pages, sizeof(struct folio *),
+					   GFP_KERNEL);
+		if (!ctx->ring_folios) {
 			put_aio_ring_file(ctx);
 			return -ENOMEM;
 		}
 	}
 
 	for (i = 0; i < nr_pages; i++) {
-		struct page *page;
-		page = find_or_create_page(file->f_mapping,
-					   i, GFP_USER | __GFP_ZERO);
-		if (!page)
+		struct folio *folio;
+
+		folio = __filemap_get_folio(file->f_mapping, i,
+					    FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
+					    GFP_USER | __GFP_ZERO);
+		if (IS_ERR(folio))
 			break;
-		pr_debug("pid(%d) page[%d]->count=%d\n",
-			 current->pid, i, page_count(page));
-		SetPageUptodate(page);
-		unlock_page(page);
 
-		ctx->ring_pages[i] = page;
+		pr_debug("pid(%d) [%d] folio->count=%d\n", current->pid, i,
+			 folio_ref_count(folio));
+		folio_end_read(folio, true);
+
+		ctx->ring_folios[i] = folio;
 	}
 	ctx->nr_pages = i;
 
@@ -570,15 +573,15 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 	ctx->user_id = ctx->mmap_base;
 	ctx->nr_events = nr_events; /* trusted copy */
 
-	ring = page_address(ctx->ring_pages[0]);
+	ring = folio_address(ctx->ring_folios[0]);
 	ring->nr = nr_events;	/* user copy */
 	ring->id = ~0U;
 	ring->head = ring->tail = 0;
 	ring->magic = AIO_RING_MAGIC;
 	ring->compat_features = AIO_RING_COMPAT_FEATURES;
 	ring->incompat_features = AIO_RING_INCOMPAT_FEATURES;
 	ring->header_length = sizeof(struct aio_ring);
-	flush_dcache_page(ctx->ring_pages[0]);
+	flush_dcache_folio(ctx->ring_folios[0]);
 
 	return 0;
 }
@@ -689,9 +692,9 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 
 					/* While kioctx setup is in progress,
 					 * we are protected from page migration
-					 * changes ring_pages by ->ring_lock.
+					 * changes ring_folios by ->ring_lock.
 					 */
-					ring = page_address(ctx->ring_pages[0]);
+					ring = folio_address(ctx->ring_folios[0]);
 					ring->id = ctx->id;
 					return 0;
 				}
@@ -1033,7 +1036,7 @@ static void user_refill_reqs_available(struct kioctx *ctx)
 		 * against ctx->completed_events below will make sure we do the
 		 * safe/right thing.
 		 */
-		ring = page_address(ctx->ring_pages[0]);
+		ring = folio_address(ctx->ring_folios[0]);
 		head = ring->head;
 
 		refill_reqs_available(ctx, head, ctx->tail);
@@ -1145,12 +1148,12 @@ static void aio_complete(struct aio_kiocb *iocb)
 	if (++tail >= ctx->nr_events)
 		tail = 0;
 
-	ev_page = page_address(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
+	ev_page = folio_address(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]);
 	event = ev_page + pos % AIO_EVENTS_PER_PAGE;
 
 	*event = iocb->ki_res;
 
-	flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
+	flush_dcache_folio(ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE]);
 
 	pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb,
 		 (void __user *)(unsigned long)iocb->ki_res.obj,
@@ -1163,10 +1166,10 @@ static void aio_complete(struct aio_kiocb *iocb)
 
 	ctx->tail = tail;
 
-	ring = page_address(ctx->ring_pages[0]);
+	ring = folio_address(ctx->ring_folios[0]);
 	head = ring->head;
 	ring->tail = tail;
-	flush_dcache_page(ctx->ring_pages[0]);
+	flush_dcache_folio(ctx->ring_folios[0]);
 
 	ctx->completed_events++;
 	if (ctx->completed_events > 1)
@@ -1238,8 +1241,8 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	sched_annotate_sleep();
 	mutex_lock(&ctx->ring_lock);
 
-	/* Access to ->ring_pages here is protected by ctx->ring_lock. */
-	ring = page_address(ctx->ring_pages[0]);
+	/* Access to ->ring_folios here is protected by ctx->ring_lock. */
+	ring = folio_address(ctx->ring_folios[0]);
 	head = ring->head;
 	tail = ring->tail;
 
@@ -1260,20 +1263,20 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	while (ret < nr) {
 		long avail;
 		struct io_event *ev;
-		struct page *page;
+		struct folio *folio;
 
 		avail = (head <= tail ?  tail : ctx->nr_events) - head;
 		if (head == tail)
 			break;
 
 		pos = head + AIO_EVENTS_OFFSET;
-		page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
+		folio = ctx->ring_folios[pos / AIO_EVENTS_PER_PAGE];
 		pos %= AIO_EVENTS_PER_PAGE;
 
 		avail = min(avail, nr - ret);
 		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos);
 
-		ev = page_address(page);
+		ev = folio_address(folio);
 		copy_ret = copy_to_user(event + ret, ev + pos,
 					sizeof(*ev) * avail);
 
@@ -1287,9 +1290,9 @@ static long aio_read_events_ring(struct kioctx *ctx,
 		head %= ctx->nr_events;
 	}
 
-	ring = page_address(ctx->ring_pages[0]);
+	ring = folio_address(ctx->ring_folios[0]);
 	ring->head = head;
-	flush_dcache_page(ctx->ring_pages[0]);
+	flush_dcache_folio(ctx->ring_folios[0]);
 
 	pr_debug("%li  h%u t%u\n", ret, head, tail);
 out:

fs/anon_inodes.c

@@ -148,6 +148,38 @@ struct file *anon_inode_getfile(const char *name,
 }
 EXPORT_SYMBOL_GPL(anon_inode_getfile);
 
+/**
+ * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an
+ *                      anonymous inode, and a dentry that describe the "class"
+ *                      of the file
+ *
+ * @name:    [in]    name of the "class" of the new file
+ * @fops:    [in]    file operations for the new file
+ * @priv:    [in]    private data for the new file (will be file's private_data)
+ * @flags:   [in]    flags
+ * @f_mode:  [in]    fmode
+ *
+ * Creates a new file by hooking it on a single inode. This is useful for files
+ * that do not need to have a full-fledged inode in order to operate correctly.
+ * All the files created with anon_inode_getfile() will share a single inode,
+ * hence saving memory and avoiding code duplication for the file/inode/dentry
+ * setup. Allows setting the fmode. Returns the newly created file* or an error
+ * pointer.
+ */
+struct file *anon_inode_getfile_fmode(const char *name,
+				const struct file_operations *fops,
+				void *priv, int flags, fmode_t f_mode)
+{
+	struct file *file;
+
+	file = __anon_inode_getfile(name, fops, priv, flags, NULL, false);
+	if (!IS_ERR(file))
+		file->f_mode |= f_mode;
+
+	return file;
+}
+EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode);
+
 /**
  * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new
  *                             !S_PRIVATE anon inode rather than reuse the
@@ -271,6 +303,7 @@ int anon_inode_create_getfd(const char *name, const struct file_operations *fops
 	return __anon_inode_getfd(name, fops, priv, flags, context_inode, true);
 }
 
+
 static int __init anon_inode_init(void)
 {
 	anon_inode_mnt = kern_mount(&anon_inode_fs_type);

fs/bcachefs/fs.c

@@ -844,6 +844,9 @@ static int bch2_getattr(struct mnt_idmap *idmap,
 	stat->blksize	= block_bytes(c);
 	stat->blocks	= inode->v.i_blocks;
 
+	stat->subvol	= inode->ei_subvol;
+	stat->result_mask |= STATX_SUBVOL;
+
 	if (request_mask & STATX_BTIME) {
 		stat->result_mask |= STATX_BTIME;
 		stat->btime = bch2_time_to_timespec(c, inode->ei_inode.bi_otime);

fs/btrfs/file.c

@@ -3719,8 +3719,7 @@ static int btrfs_file_open(struct inode *inode, struct file *filp)
 {
 	int ret;
 
-	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC |
-		        FMODE_CAN_ODIRECT;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
 
 	ret = fsverity_file_open(inode, filp);
 	if (ret)
@@ -3850,6 +3849,7 @@ const struct file_operations btrfs_file_operations = {
 	.compat_ioctl	= btrfs_compat_ioctl,
 #endif
 	.remap_file_range = btrfs_remap_file_range,
+	.fop_flags	= FOP_BUFFER_RASYNC | FOP_BUFFER_WASYNC,
 };
 
 int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end)

fs/btrfs/inode.c

@@ -8789,6 +8789,9 @@ static int btrfs_getattr(struct mnt_idmap *idmap,
 	generic_fillattr(idmap, request_mask, inode, stat);
 	stat->dev = BTRFS_I(inode)->root->anon_dev;
 
+	stat->subvol = BTRFS_I(inode)->root->root_key.objectid;
+	stat->result_mask |= STATX_SUBVOL;
+
 	spin_lock(&BTRFS_I(inode)->lock);
 	delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes;
 	inode_bytes = inode_get_bytes(inode);

fs/dcache.c

@@ -355,7 +355,7 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry)
 	flags &= ~DCACHE_ENTRY_TYPE;
 	WRITE_ONCE(dentry->d_flags, flags);
 	dentry->d_inode = NULL;
-	if (dentry->d_flags & DCACHE_LRU_LIST)
+	if (flags & DCACHE_LRU_LIST)
 		this_cpu_inc(nr_dentry_negative);
 }