Merge patch series "re-enable IOCB_NOWAIT writes to files v6"

Christoph Hellwig <hch@lst.de> says:

Hi all,

commit 66fa3ce ("fs: Add async write file modification handling.")
effectively disabled IOCB_NOWAIT writes as timestamp updates currently
always require blocking, and the modern timestamp resolution means we
always update timestamps.  This leads to a lot of context switches from
applications using io_uring to submit file writes, making it often worse
than using the legacy aio code that is not using IOCB_NOWAIT.

This series allows non-blocking updates for lazytime if the file system
supports it, and adds that support for XFS.

* patches from https://patch.msgid.link/20260108141934.2052404-1-hch@lst.de:
  xfs: enable non-blocking timestamp updates
  xfs: implement ->sync_lazytime
  fs: refactor file_update_time_flags
  fs: add support for non-blocking timestamp updates
  fs: add a ->sync_lazytime method
  fs: factor out a sync_lazytime helper
  fs: refactor ->update_time handling
  fat: cleanup the flags for fat_truncate_time
  nfs: split nfs_update_timestamps
  fs: allow error returns from generic_update_time
  fs: remove inode_update_time

Link: https://patch.msgid.link/20260108141934.2052404-1-hch@lst.de
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: brauner

Documentation/filesystems/locking.rst

@@ -80,7 +80,9 @@ prototypes::
 	int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
-	void (*update_time)(struct inode *, struct timespec *, int);
+	void (*update_time)(struct inode *inode, enum fs_update_time type,
+			    int flags);
+	void (*sync_lazytime)(struct inode *inode);
 	int (*atomic_open)(struct inode *, struct dentry *,
 				struct file *, unsigned open_flag,
 				umode_t create_mode);
@@ -117,6 +119,7 @@ getattr:	no
 listxattr:	no
 fiemap:		no
 update_time:	no
+sync_lazytime:	no
 atomic_open:	shared (exclusive if O_CREAT is set in open flags)
 tmpfile:	no
 fileattr_get:	no or exclusive

Documentation/filesystems/vfs.rst

@@ -485,7 +485,9 @@ As of kernel 2.6.22, the following members are defined:
 		int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
 		int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
 		ssize_t (*listxattr) (struct dentry *, char *, size_t);
-		void (*update_time)(struct inode *, struct timespec *, int);
+		void (*update_time)(struct inode *inode, enum fs_update_time type,
+				    int flags);
+		void (*sync_lazytime)(struct inode *inode);
 		int (*atomic_open)(struct inode *, struct dentry *, struct file *,
 				   unsigned open_flag, umode_t create_mode);
 		int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t);
@@ -642,6 +644,11 @@ otherwise noted.
 	an inode.  If this is not defined the VFS will update the inode
 	itself and call mark_inode_dirty_sync.
 
+``sync_lazytime``:
+	called by the writeback code to update the lazy time stamps to
+	regular time stamp updates that get syncing into the on-disk
+	inode.
+
 ``atomic_open``
 	called on the last component of an open.  Using this optional
 	method the filesystem can look up, possibly create and open the

fs/bad_inode.c

@@ -133,7 +133,8 @@ static int bad_inode_fiemap(struct inode *inode,
 	return -EIO;
 }
 
-static int bad_inode_update_time(struct inode *inode, int flags)
+static int bad_inode_update_time(struct inode *inode, enum fs_update_time type,
+				 unsigned int flags)
 {
 	return -EIO;
 }

fs/btrfs/inode.c

@@ -6345,16 +6345,21 @@ static int btrfs_dirty_inode(struct btrfs_inode *inode)
  * We need our own ->update_time so that we can return error on ENOSPC for
  * updating the inode in the case of file write and mmap writes.
  */
-static int btrfs_update_time(struct inode *inode, int flags)
+static int btrfs_update_time(struct inode *inode, enum fs_update_time type,
+		unsigned int flags)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	bool dirty;
+	int dirty;
 
 	if (btrfs_root_readonly(root))
 		return -EROFS;
+	if (flags & IOCB_NOWAIT)
+		return -EAGAIN;
 
-	dirty = inode_update_timestamps(inode, flags);
-	return dirty ? btrfs_dirty_inode(BTRFS_I(inode)) : 0;
+	dirty = inode_update_time(inode, type, flags);
+	if (dirty <= 0)
+		return dirty;
+	return btrfs_dirty_inode(BTRFS_I(inode));
 }
 
 /*

fs/fat/dir.c

@@ -1080,7 +1080,7 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo)
 		}
 	}
 
-	fat_truncate_time(dir, NULL, S_ATIME|S_MTIME);
+	fat_truncate_time(dir, NULL, FAT_UPDATE_ATIME | FAT_UPDATE_CMTIME);
 	if (IS_DIRSYNC(dir))
 		(void)fat_sync_inode(dir);
 	else

fs/fat/fat.h

@@ -468,11 +468,12 @@ extern void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec64 *ts,
 			      __le16 *time, __le16 *date, u8 *time_cs);
 extern struct timespec64 fat_truncate_atime(const struct msdos_sb_info *sbi,
 					    const struct timespec64 *ts);
-extern struct timespec64 fat_truncate_mtime(const struct msdos_sb_info *sbi,
-					    const struct timespec64 *ts);
-extern int fat_truncate_time(struct inode *inode, struct timespec64 *now,
-			     int flags);
-extern int fat_update_time(struct inode *inode, int flags);
+#define FAT_UPDATE_ATIME	(1u << 0)
+#define FAT_UPDATE_CMTIME	(1u << 1)
+void fat_truncate_time(struct inode *inode, struct timespec64 *now,
+		unsigned int flags);
+int fat_update_time(struct inode *inode, enum fs_update_time type,
+		unsigned int flags);
 extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs);
 
 int fat_cache_init(void);

fs/fat/file.c

@@ -224,7 +224,7 @@ static int fat_cont_expand(struct inode *inode, loff_t size)
 	if (err)
 		goto out;
 
-	fat_truncate_time(inode, NULL, S_CTIME|S_MTIME);
+	fat_truncate_time(inode, NULL, FAT_UPDATE_CMTIME);
 	mark_inode_dirty(inode);
 	if (IS_SYNC(inode)) {
 		int err2;
@@ -327,7 +327,7 @@ static int fat_free(struct inode *inode, int skip)
 		MSDOS_I(inode)->i_logstart = 0;
 	}
 	MSDOS_I(inode)->i_attrs |= ATTR_ARCH;
-	fat_truncate_time(inode, NULL, S_CTIME|S_MTIME);
+	fat_truncate_time(inode, NULL, FAT_UPDATE_CMTIME);
 	if (wait) {
 		err = fat_sync_inode(inode);
 		if (err) {
@@ -553,15 +553,13 @@ int fat_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	}
 
 	/*
-	 * setattr_copy can't truncate these appropriately, so we'll
-	 * copy them ourselves
+	 * setattr_copy can't truncate these appropriately, so we'll copy them
+	 * ourselves.  See fat_truncate_time for the c/mtime logic on fat.
 	 */
 	if (attr->ia_valid & ATTR_ATIME)
-		fat_truncate_time(inode, &attr->ia_atime, S_ATIME);
-	if (attr->ia_valid & ATTR_CTIME)
-		fat_truncate_time(inode, &attr->ia_ctime, S_CTIME);
+		fat_truncate_time(inode, &attr->ia_atime, FAT_UPDATE_ATIME);
 	if (attr->ia_valid & ATTR_MTIME)
-		fat_truncate_time(inode, &attr->ia_mtime, S_MTIME);
+		fat_truncate_time(inode, &attr->ia_mtime, FAT_UPDATE_CMTIME);
 	attr->ia_valid &= ~(ATTR_ATIME|ATTR_CTIME|ATTR_MTIME);
 
 	setattr_copy(idmap, inode, attr);

fs/fat/inode.c

@@ -246,7 +246,7 @@ static int fat_write_end(const struct kiocb *iocb,
 	if (err < len)
 		fat_write_failed(mapping, pos + len);
 	if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {
-		fat_truncate_time(inode, NULL, S_CTIME|S_MTIME);
+		fat_truncate_time(inode, NULL, FAT_UPDATE_CMTIME);
 		MSDOS_I(inode)->i_attrs |= ATTR_ARCH;
 		mark_inode_dirty(inode);
 	}

fs/fat/misc.c

@@ -299,62 +299,47 @@ struct timespec64 fat_truncate_atime(const struct msdos_sb_info *sbi,
 }
 
 /*
- * truncate mtime to 2 second granularity
- */
-struct timespec64 fat_truncate_mtime(const struct msdos_sb_info *sbi,
-				     const struct timespec64 *ts)
-{
-	return fat_timespec64_trunc_2secs(*ts);
-}
-
-/*
- * truncate the various times with appropriate granularity:
- *   all times in root node are always 0
+ * Update the in-inode atime and/or mtime after truncating the timestamp to the
+ * granularity.  All timestamps in root inode are always 0.
+ *
+ * ctime and mtime share the same on-disk field, and should be identical in
+ * memory.  All mtime updates will be applied to ctime, but ctime updates are
+ * ignored.
  */
-int fat_truncate_time(struct inode *inode, struct timespec64 *now, int flags)
+void fat_truncate_time(struct inode *inode, struct timespec64 *now,
+		unsigned int flags)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
 	struct timespec64 ts;
 
 	if (inode->i_ino == MSDOS_ROOT_INO)
-		return 0;
+		return;
 
 	if (now == NULL) {
 		now = &ts;
 		ts = current_time(inode);
 	}
 
-	if (flags & S_ATIME)
+	if (flags & FAT_UPDATE_ATIME)
 		inode_set_atime_to_ts(inode, fat_truncate_atime(sbi, now));
-	/*
-	 * ctime and mtime share the same on-disk field, and should be
-	 * identical in memory. all mtime updates will be applied to ctime,
-	 * but ctime updates are ignored.
-	 */
-	if (flags & S_MTIME)
-		inode_set_mtime_to_ts(inode,
-				      inode_set_ctime_to_ts(inode, fat_truncate_mtime(sbi, now)));
+	if (flags & FAT_UPDATE_CMTIME) {
+		/* truncate mtime to 2 second granularity */
+		struct timespec64 mtime = fat_timespec64_trunc_2secs(*now);
 
-	return 0;
+		inode_set_mtime_to_ts(inode, mtime);
+		inode_set_ctime_to_ts(inode, mtime);
+	}
 }
 EXPORT_SYMBOL_GPL(fat_truncate_time);
 
-int fat_update_time(struct inode *inode, int flags)
+int fat_update_time(struct inode *inode, enum fs_update_time type,
+		unsigned int flags)
 {
-	int dirty_flags = 0;
-
-	if (inode->i_ino == MSDOS_ROOT_INO)
-		return 0;
-
-	if (flags & (S_ATIME | S_CTIME | S_MTIME)) {
-		fat_truncate_time(inode, NULL, flags);
-		if (inode->i_sb->s_flags & SB_LAZYTIME)
-			dirty_flags |= I_DIRTY_TIME;
-		else
-			dirty_flags |= I_DIRTY_SYNC;
+	if (inode->i_ino != MSDOS_ROOT_INO) {
+		fat_truncate_time(inode, NULL, type == FS_UPD_ATIME ?
+				FAT_UPDATE_ATIME : FAT_UPDATE_CMTIME);
+		__mark_inode_dirty(inode, inode_time_dirty_flag(inode));
 	}
-
-	__mark_inode_dirty(inode, dirty_flags);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fat_update_time);

fs/fat/namei_msdos.c

@@ -251,7 +251,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
 	if (err)
 		return err;
 
-	fat_truncate_time(dir, ts, S_CTIME|S_MTIME);
+	fat_truncate_time(dir, ts, FAT_UPDATE_CMTIME);
 	if (IS_DIRSYNC(dir))
 		(void)fat_sync_inode(dir);
 	else
@@ -295,7 +295,7 @@ static int msdos_create(struct mnt_idmap *idmap, struct inode *dir,
 		err = PTR_ERR(inode);
 		goto out;
 	}
-	fat_truncate_time(inode, &ts, S_ATIME|S_CTIME|S_MTIME);
+	fat_truncate_time(inode, &ts, FAT_UPDATE_ATIME | FAT_UPDATE_CMTIME);
 	/* timestamp is already written, so mark_inode_dirty() is unneeded. */
 
 	d_instantiate(dentry, inode);
@@ -328,7 +328,6 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
 	drop_nlink(dir);
 
 	clear_nlink(inode);
-	fat_truncate_time(inode, NULL, S_CTIME);
 	fat_detach(inode);
 out:
 	mutex_unlock(&MSDOS_SB(sb)->s_lock);
@@ -382,7 +381,7 @@ static struct dentry *msdos_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 	set_nlink(inode, 2);
-	fat_truncate_time(inode, &ts, S_ATIME|S_CTIME|S_MTIME);
+	fat_truncate_time(inode, &ts, FAT_UPDATE_ATIME | FAT_UPDATE_CMTIME);
 	/* timestamp is already written, so mark_inode_dirty() is unneeded. */
 
 	d_instantiate(dentry, inode);
@@ -415,7 +414,6 @@ static int msdos_unlink(struct inode *dir, struct dentry *dentry)
 	if (err)
 		goto out;
 	clear_nlink(inode);
-	fat_truncate_time(inode, NULL, S_CTIME);
 	fat_detach(inode);
 out:
 	mutex_unlock(&MSDOS_SB(sb)->s_lock);
@@ -480,7 +478,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 				mark_inode_dirty(old_inode);
 
 			inode_inc_iversion(old_dir);
-			fat_truncate_time(old_dir, NULL, S_CTIME|S_MTIME);
+			fat_truncate_time(old_dir, NULL, FAT_UPDATE_CMTIME);
 			if (IS_DIRSYNC(old_dir))
 				(void)fat_sync_inode(old_dir);
 			else
@@ -540,7 +538,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 	if (err)
 		goto error_dotdot;
 	inode_inc_iversion(old_dir);
-	fat_truncate_time(old_dir, &ts, S_CTIME|S_MTIME);
+	fat_truncate_time(old_dir, &ts, FAT_UPDATE_CMTIME);
 	if (IS_DIRSYNC(old_dir))
 		(void)fat_sync_inode(old_dir);
 	else
@@ -550,7 +548,6 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 		drop_nlink(new_inode);
 		if (is_dir)
 			drop_nlink(new_inode);
-		fat_truncate_time(new_inode, &ts, S_CTIME);
 	}
 out:
 	brelse(sinfo.bh);