Merge tag 'vfs-6.17-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc VFS updates from Christian Brauner:
 "This contains the usual selections of misc updates for this cycle.

  Features:

   - Add ext4 IOCB_DONTCACHE support

     This refactors the address_space_operations write_begin() and
     write_end() callbacks to take const struct kiocb * as their first
     argument, allowing IOCB flags such as IOCB_DONTCACHE to propagate
     to the filesystem's buffered I/O path.

     Ext4 is updated to implement handling of the IOCB_DONTCACHE flag
     and advertises support via the FOP_DONTCACHE file operation flag.

     Additionally, the i915 driver's shmem write paths are updated to
     bypass the legacy write_begin/write_end interface in favor of
     directly calling write_iter() with a constructed synchronous kiocb.
     Another i915 change replaces a manual write loop with
     kernel_write() during GEM shmem object creation.

  Cleanups:

   - don't duplicate vfs_open() in kernel_file_open()

   - proc_fd_getattr(): don't bother with S_ISDIR() check

   - fs/ecryptfs: replace snprintf with sysfs_emit in show function

   - vfs: Remove unnecessary list_for_each_entry_safe() from
     evict_inodes()

   - filelock: add new locks_wake_up_waiter() helper

   - fs: Remove three arguments from block_write_end()

   - VFS: change old_dir and new_dir in struct renamedata to dentrys

   - netfs: Remove unused declaration netfs_queue_write_request()

  Fixes:

   - eventpoll: Fix semi-unbounded recursion

   - eventpoll: fix sphinx documentation build warning

   - fs/read_write: Fix spelling typo

   - fs: annotate data race between poll_schedule_timeout() and
     pollwake()

   - fs/pipe: set FMODE_NOWAIT in create_pipe_files()

   - docs/vfs: update references to i_mutex to i_rwsem

   - fs/buffer: remove comment about hard sectorsize

   - fs/buffer: remove the min and max limit checks in __getblk_slow()

   - fs/libfs: don't assume blocksize <= PAGE_SIZE in
     generic_check_addressable

   - fs_context: fix parameter name in infofc() macro

   - fs: Prevent file descriptor table allocations exceeding INT_MAX"

* tag 'vfs-6.17-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (24 commits)
  netfs: Remove unused declaration netfs_queue_write_request()
  eventpoll: fix sphinx documentation build warning
  ext4: support uncached buffered I/O
  mm/pagemap: add write_begin_get_folio() helper function
  fs: change write_begin/write_end interface to take struct kiocb *
  drm/i915: Refactor shmem_pwrite() to use kiocb and write_iter
  drm/i915: Use kernel_write() in shmem object create
  eventpoll: Fix semi-unbounded recursion
  vfs: Remove unnecessary list_for_each_entry_safe() from evict_inodes()
  fs/libfs: don't assume blocksize <= PAGE_SIZE in generic_check_addressable
  fs/buffer: remove the min and max limit checks in __getblk_slow()
  fs: Prevent file descriptor table allocations exceeding INT_MAX
  fs: Remove three arguments from block_write_end()
  fs/ecryptfs: replace snprintf with sysfs_emit in show function
  fs: annotate suspected data race between poll_schedule_timeout() and pollwake()
  docs/vfs: update references to i_mutex to i_rwsem
  fs/buffer: remove comment about hard sectorsize
  fs_context: fix parameter name in infofc() macro
  VFS: change old_dir and new_dir in struct renamedata to dentrys
  proc_fd_getattr(): don't bother with S_ISDIR() check
  ...

9 files changed, 54 insertions, 24 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 0029ff880e27..b16b88bfbc3e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -262,14 +262,12 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		struct folio **foliop, get_block_t *get_block);
 int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block);
-int block_write_end(struct file *, struct address_space *,
-				loff_t, unsigned len, unsigned copied,
-				struct folio *, void *);
-int generic_write_end(struct file *, struct address_space *,
+int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *);
+int generic_write_end(const struct kiocb *, struct address_space *,
 				loff_t, unsigned len, unsigned copied,
 				struct folio *, void *);
 void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
-int cont_write_begin(struct file *, struct address_space *, loff_t,
+int cont_write_begin(const struct kiocb *, struct address_space *, loff_t,
 			unsigned, struct folio **, void **,
 			get_block_t *, loff_t *);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 25c4a5afbd44..cfb0dd1ea49c 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -230,7 +230,7 @@ struct handle_to_path_ctx {
  *    directory.  The name should be stored in the @name (with the
  *    understanding that it is already pointing to a %NAME_MAX+1 sized
  *    buffer.   get_name() should return %0 on success, a negative error code
- *    or error.  @get_name will be called without @parent->i_mutex held.
+ *    or error.  @get_name will be called without @parent->i_rwsem held.
  *
  * get_parent:
  *    @get_parent should find the parent directory for the given @child which
@@ -247,7 +247,7 @@ struct handle_to_path_ctx {
  *    @commit_metadata should commit metadata changes to stable storage.
  *
  * Locking rules:
- *    get_parent is called with child->d_inode->i_mutex down
+ *    get_parent is called with child->d_inode->i_rwsem down
  *    get_name is not (which is possibly inconsistent)
  */
 
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index c412ded9171e..c2ce8ba05d06 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -175,9 +175,14 @@ static inline bool lock_is_write(struct file_lock *fl)
 	return fl->c.flc_type == F_WRLCK;
 }
 
+static inline void locks_wake_up_waiter(struct file_lock_core *flc)
+{
+	wake_up(&flc->flc_wait);
+}
+
 static inline void locks_wake_up(struct file_lock *fl)
 {
-	wake_up(&fl->c.flc_wait);
+	locks_wake_up_waiter(&fl->c);
 }
 
 static inline bool locks_can_async_lock(const struct file_operations *fops)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ea5b14fe424d..1b5212de5702 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -446,10 +446,10 @@ struct address_space_operations {
 
 	void (*readahead)(struct readahead_control *);
 
-	int (*write_begin)(struct file *, struct address_space *mapping,
+	int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len,
 				struct folio **foliop, void **fsdata);
-	int (*write_end)(struct file *, struct address_space *mapping,
+	int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct folio *folio, void *fsdata);
 
@@ -839,7 +839,7 @@ static inline void inode_fake_hash(struct inode *inode)
 }
 
 /*
- * inode->i_mutex nesting subclasses for the lock validator:
+ * inode->i_rwsem nesting subclasses for the lock validator:
  *
  * 0: the object of the current VFS operation
  * 1: parent
@@ -991,7 +991,7 @@ static inline loff_t i_size_read(const struct inode *inode)
 
 /*
  * NOTE: unlike i_size_read(), i_size_write() does need locking around it
- * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
+ * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount
  * can be lost, resulting in subsequent i_size_read() calls spinning forever.
  */
 static inline void i_size_write(struct inode *inode, loff_t i_size)
@@ -1924,7 +1924,7 @@ static inline void sb_end_intwrite(struct super_block *sb)
  * freeze protection should be the outermost lock. In particular, we have:
  *
  * sb_start_write
- *   -> i_mutex			(write path, truncate, directory ops, ...)
+ *   -> i_rwsem			(write path, truncate, directory ops, ...)
  *   -> s_umount		(freeze_super, thaw_super)
  */
 static inline void sb_start_write(struct super_block *sb)
@@ -2007,20 +2007,20 @@ int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *,
 /**
  * struct renamedata - contains all information required for renaming
  * @old_mnt_idmap:     idmap of the old mount the inode was found from
- * @old_dir:           parent of source
+ * @old_parent:        parent of source
  * @old_dentry:                source
  * @new_mnt_idmap:     idmap of the new mount the inode was found from
- * @new_dir:           parent of destination
+ * @new_parent:        parent of destination
  * @new_dentry:                destination
  * @delegated_inode:   returns an inode needing a delegation break
  * @flags:             rename flags
  */
 struct renamedata {
 	struct mnt_idmap *old_mnt_idmap;
-	struct inode *old_dir;
+	struct dentry *old_parent;
 	struct dentry *old_dentry;
 	struct mnt_idmap *new_mnt_idmap;
-	struct inode *new_dir;
+	struct dentry *new_parent;
 	struct dentry *new_dentry;
 	struct inode **delegated_inode;
 	unsigned int flags;
@@ -3605,9 +3605,10 @@ extern void locked_recursive_removal(struct dentry *,
 extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int simple_empty(struct dentry *);
-extern int simple_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata);
+extern int simple_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len,
+			      struct folio **foliop, void **fsdata);
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index a19e4bd32e4d..7773eb870039 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -200,7 +200,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt,
  */
 #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__)
 #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__)
-#define infofc(p, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
+#define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
 
 /**
  * warnf - Store supplementary warning message
diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h
index 2b1f74b24070..0cc2fa283305 100644
--- a/include/linux/fs_stack.h
+++ b/include/linux/fs_stack.h
@@ -3,7 +3,7 @@
 #define _LINUX_FS_STACK_H
 
 /* This file defines generic functions used primarily by stackable
- * filesystems; none of these functions require i_mutex to be held.
+ * filesystems; none of these functions require i_rwsem to be held.
  */
 
 #include <linux/fs.h>
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index f43f075852c0..185bd8196503 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -442,7 +442,6 @@ size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
 			size_t max_size, size_t max_segs);
 void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq);
 void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error);
-void netfs_queue_write_request(struct netfs_io_subrequest *subreq);
 
 int netfs_start_io_read(struct inode *inode);
 void netfs_end_io_read(struct inode *inode);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e63fbfbd5b0f..ce2bcdcadb73 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -751,6 +751,33 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
 
 /**
+ * write_begin_get_folio - Get folio for write_begin with flags.
+ * @iocb: The kiocb passed from write_begin (may be NULL).
+ * @mapping: The address space to search.
+ * @index: The page cache index.
+ * @len: Length of data being written.
+ *
+ * This is a helper for filesystem write_begin() implementations.
+ * It wraps __filemap_get_folio(), setting appropriate flags in
+ * the write begin context.
+ *
+ * Return: A folio or an ERR_PTR.
+ */
+static inline struct folio *write_begin_get_folio(const struct kiocb *iocb,
+		  struct address_space *mapping, pgoff_t index, size_t len)
+{
+        fgf_t fgp_flags = FGP_WRITEBEGIN;
+
+        fgp_flags |= fgf_set_order(len);
+
+        if (iocb && iocb->ki_flags & IOCB_DONTCACHE)
+                fgp_flags |= FGP_DONTCACHE;
+
+        return __filemap_get_folio(mapping, index, fgp_flags,
+                                   mapping_gfp_mask(mapping));
+}
+
+/**
  * filemap_get_folio - Find and get a folio.
  * @mapping: The address_space to search.
  * @index: The page index.
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 06cc8888199e..c334f82ed385 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -19,7 +19,7 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb)
 	return &sb->s_dquot;
 }
 
-/* i_mutex must being held */
+/* i_rwsem must being held */
 static inline bool is_quota_modification(struct mnt_idmap *idmap,
 					 struct inode *inode, struct iattr *ia)
 {