1 files changed, 211 insertions, 20 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 562f2623c9c9..dda08d973639 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -338,6 +338,20 @@ enum rw_hint {
 #define IOCB_NOIO		(1 << 20)
 /* can use bio alloc cache */
 #define IOCB_ALLOC_CACHE	(1 << 21)
+/*
+ * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the
+ * iocb completion can be passed back to the owner for execution from a safe
+ * context rather than needing to be punted through a workqueue. If this
+ * flag is set, the bio completion handling may set iocb->dio_complete to a
+ * handler function and iocb->private to context information for that handler.
+ * The issuer should call the handler with that context information from task
+ * context to complete the processing of the iocb. Note that while this
+ * provides a task context for the dio_complete() callback, it should only be
+ * used on the completion side for non-IO generating completions. It's fine to
+ * call blocking functions from this callback, but they should not wait for
+ * unrelated IO (like cache flushing, new IO generation, etc).
+ */
+#define IOCB_DIO_CALLER_COMP	(1 << 22)
 
 /* for use in trace events */
 #define TRACE_IOCB_STRINGS \
@@ -351,7 +365,8 @@ enum rw_hint {
 	{ IOCB_WRITE,		"WRITE" }, \
 	{ IOCB_WAITQ,		"WAITQ" }, \
 	{ IOCB_NOIO,		"NOIO" }, \
-	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }
+	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }, \
+	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -360,7 +375,23 @@ struct kiocb {
 	void			*private;
 	int			ki_flags;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	struct wait_page_queue	*ki_waitq; /* for async buffered IO */
+	union {
+		/*
+		 * Only used for async buffered reads, where it denotes the
+		 * page waitqueue associated with completing the read. Valid
+		 * IFF IOCB_WAITQ is set.
+		 */
+		struct wait_page_queue	*ki_waitq;
+		/*
+		 * Can be used for O_DIRECT IO, where the completion handling
+		 * is punted back to the issuer of the IO. May only be set
+		 * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer
+		 * must then check for presence of this handler when ki_complete
+		 * is invoked. The data passed in to this handler must be
+		 * assigned to ->private when dio_complete is assigned.
+		 */
+		ssize_t (*dio_complete)(void *data);
+	};
 };
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -642,7 +673,7 @@ struct inode {
 	loff_t			i_size;
 	struct timespec64	i_atime;
 	struct timespec64	i_mtime;
-	struct timespec64	i_ctime;
+	struct timespec64	__i_ctime; /* use inode_*_ctime accessors! */
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
 	u8			i_blkbits;
@@ -1069,7 +1100,7 @@ extern void fasync_free(struct fasync_struct *);
 extern void kill_fasync(struct fasync_struct **, int, int);
 
 extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
-extern int f_setown(struct file *filp, unsigned long arg, int force);
+extern int f_setown(struct file *filp, int who, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
@@ -1095,6 +1126,8 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_LAZYTIME     BIT(25)	/* Update the on-disk [acm]times lazily */
 
 /* These sb flags are internal to the kernel */
+#define SB_DEAD         BIT(21)
+#define SB_DYING        BIT(24)
 #define SB_SUBMOUNT     BIT(26)
 #define SB_FORCE        BIT(27)
 #define SB_NOSEC        BIT(28)
@@ -1147,7 +1180,8 @@ enum {
 #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
 
 struct sb_writers {
-	int				frozen;		/* Is sb frozen? */
+	unsigned short			frozen;		/* Is sb frozen? */
+	unsigned short			freeze_holders;	/* Who froze fs? */
 	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
 };
 
@@ -1474,7 +1508,79 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb,
 	       kgid_has_mapping(fs_userns, kgid);
 }
 
-extern struct timespec64 current_time(struct inode *inode);
+struct timespec64 current_mgtime(struct inode *inode);
+struct timespec64 current_time(struct inode *inode);
+struct timespec64 inode_set_ctime_current(struct inode *inode);
+
+/*
+ * Multigrain timestamps
+ *
+ * Conditionally use fine-grained ctime and mtime timestamps when there
+ * are users actively observing them via getattr. The primary use-case
+ * for this is NFS clients that use the ctime to distinguish between
+ * different states of the file, and that are often fooled by multiple
+ * operations that occur in the same coarse-grained timer tick.
+ *
+ * The kernel always keeps normalized struct timespec64 values in the ctime,
+ * which means that only the first 30 bits of the value are used. Use the
+ * 31st bit of the ctime's tv_nsec field as a flag to indicate that the value
+ * has been queried since it was last updated.
+ */
+#define I_CTIME_QUERIED		(1L<<30)
+
+/**
+ * inode_get_ctime - fetch the current ctime from the inode
+ * @inode: inode from which to fetch ctime
+ *
+ * Grab the current ctime tv_nsec field from the inode, mask off the
+ * I_CTIME_QUERIED flag and return it. This is mostly intended for use by
+ * internal consumers of the ctime that aren't concerned with ensuring a
+ * fine-grained update on the next change (e.g. when preparing to store
+ * the value in the backing store for later retrieval).
+ *
+ * This is safe to call regardless of whether the underlying filesystem
+ * is using multigrain timestamps.
+ */
+static inline struct timespec64 inode_get_ctime(const struct inode *inode)
+{
+	struct timespec64 ctime;
+
+	ctime.tv_sec = inode->__i_ctime.tv_sec;
+	ctime.tv_nsec = inode->__i_ctime.tv_nsec & ~I_CTIME_QUERIED;
+
+	return ctime;
+}
+
+/**
+ * inode_set_ctime_to_ts - set the ctime in the inode
+ * @inode: inode in which to set the ctime
+ * @ts: value to set in the ctime field
+ *
+ * Set the ctime in @inode to @ts
+ */
+static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode,
+						      struct timespec64 ts)
+{
+	inode->__i_ctime = ts;
+	return ts;
+}
+
+/**
+ * inode_set_ctime - set the ctime in the inode
+ * @inode: inode in which to set the ctime
+ * @sec: tv_sec value to set
+ * @nsec: tv_nsec value to set
+ *
+ * Set the ctime in @inode to { @sec, @nsec }
+ */
+static inline struct timespec64 inode_set_ctime(struct inode *inode,
+						time64_t sec, long nsec)
+{
+	struct timespec64 ts = { .tv_sec  = sec,
+				 .tv_nsec = nsec };
+
+	return inode_set_ctime_to_ts(inode, ts);
+}
 
 /*
  * Snapshotting support.
@@ -1770,6 +1876,7 @@ struct dir_context {
 
 struct iov_iter;
 struct io_uring_cmd;
+struct offset_ctx;
 
 struct file_operations {
 	struct module *owner;
@@ -1798,7 +1905,7 @@ struct file_operations {
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
 	void (*splice_eof)(struct file *file);
-	int (*setlease)(struct file *, long, struct file_lock **, void **);
+	int (*setlease)(struct file *, int, struct file_lock **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	void (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -1850,7 +1957,7 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
-	int (*update_time)(struct inode *, struct timespec64 *, int);
+	int (*update_time)(struct inode *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 			   struct file *, unsigned open_flag,
 			   umode_t create_mode);
@@ -1863,6 +1970,7 @@ struct inode_operations {
 	int (*fileattr_set)(struct mnt_idmap *idmap,
 			    struct dentry *dentry, struct fileattr *fa);
 	int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
+	struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
 } ____cacheline_aligned;
 
 static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
@@ -1908,6 +2016,10 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 					struct file *dst_file, loff_t dst_pos,
 					loff_t len, unsigned int remap_flags);
 
+enum freeze_holder {
+	FREEZE_HOLDER_KERNEL	= (1U << 0),
+	FREEZE_HOLDER_USERSPACE	= (1U << 1),
+};
 
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
@@ -1920,9 +2032,9 @@ struct super_operations {
 	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
-	int (*freeze_super) (struct super_block *);
+	int (*freeze_super) (struct super_block *, enum freeze_holder who);
 	int (*freeze_fs) (struct super_block *);
-	int (*thaw_super) (struct super_block *);
+	int (*thaw_super) (struct super_block *, enum freeze_holder who);
 	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
@@ -2200,7 +2312,7 @@ enum file_time_flags {
 
 extern bool atime_needs_update(const struct path *, struct inode *);
 extern void touch_atime(const struct path *);
-int inode_update_time(struct inode *inode, struct timespec64 *time, int flags);
+int inode_update_time(struct inode *inode, int flags);
 
 static inline void file_accessed(struct file *file)
 {
@@ -2222,6 +2334,7 @@ struct file_system_type {
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_DISALLOW_NOTIFY_PERM	16	/* Disable fanotify permission events */
 #define FS_ALLOW_IDMAP         32      /* FS has been updated to handle vfs idmappings. */
+#define FS_MGTIME		64	/* FS uses multigrain timestamps */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
@@ -2245,6 +2358,17 @@ struct file_system_type {
 
 #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
 
+/**
+ * is_mgtime: is this inode using multigrain timestamps
+ * @inode: inode to test for multigrain timestamps
+ *
+ * Return true if the inode uses multigrain timestamps, false otherwise.
+ */
+static inline bool is_mgtime(const struct inode *inode)
+{
+	return inode->i_sb->s_type->fs_flags & FS_MGTIME;
+}
+
 extern struct dentry *mount_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
@@ -2296,8 +2420,8 @@ extern int unregister_filesystem(struct file_system_type *);
 extern int vfs_statfs(const struct path *, struct kstatfs *);
 extern int user_statfs(const char __user *, struct kstatfs *);
 extern int fd_statfs(int, struct kstatfs *);
-extern int freeze_super(struct super_block *super);
-extern int thaw_super(struct super_block *super);
+int freeze_super(struct super_block *super, enum freeze_holder who);
+int thaw_super(struct super_block *super, enum freeze_holder who);
 extern __printf(2, 3)
 int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
 extern int super_setup_bdi(struct super_block *sb);
@@ -2306,7 +2430,8 @@ extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
-extern int generic_update_time(struct inode *, struct timespec64 *, int);
+int inode_update_timestamps(struct inode *inode, int flags);
+int generic_update_time(struct inode *, int);
 
 /* /sys/fs */
 extern struct kobject *fs_kobj;
@@ -2545,6 +2670,13 @@ static inline bool inode_wrong_type(const struct inode *inode, umode_t mode)
 	return (inode->i_mode ^ mode) & S_IFMT;
 }
 
+/**
+ * file_start_write - get write access to a superblock for regular file io
+ * @file: the file we want to write to
+ *
+ * This is a variant of sb_start_write() which is a noop on non-regualr file.
+ * Should be matched with a call to file_end_write().
+ */
 static inline void file_start_write(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
@@ -2559,11 +2691,53 @@ static inline bool file_start_write_trylock(struct file *file)
 	return sb_start_write_trylock(file_inode(file)->i_sb);
 }
 
+/**
+ * file_end_write - drop write access to a superblock of a regular file
+ * @file: the file we wrote to
+ *
+ * Should be matched with a call to file_start_write().
+ */
 static inline void file_end_write(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return;
-	__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+	sb_end_write(file_inode(file)->i_sb);
+}
+
+/**
+ * kiocb_start_write - get write access to a superblock for async file io
+ * @iocb: the io context we want to submit the write with
+ *
+ * This is a variant of sb_start_write() for async io submission.
+ * Should be matched with a call to kiocb_end_write().
+ */
+static inline void kiocb_start_write(struct kiocb *iocb)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	sb_start_write(inode->i_sb);
+	/*
+	 * Fool lockdep by telling it the lock got released so that it
+	 * doesn't complain about the held lock when we return to userspace.
+	 */
+	__sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * kiocb_end_write - drop write access to a superblock after async file io
+ * @iocb: the io context we sumbitted the write with
+ *
+ * Should be matched with a call to kiocb_start_write().
+ */
+static inline void kiocb_end_write(struct kiocb *iocb)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	/*
+	 * Tell lockdep we inherited freeze protection from submission thread.
+	 */
+	__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+	sb_end_write(inode->i_sb);
 }
 
 /*
@@ -2613,8 +2787,7 @@ static inline bool inode_is_open_for_write(const struct inode *inode)
 #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
 static inline void i_readcount_dec(struct inode *inode)
 {
-	BUG_ON(!atomic_read(&inode->i_readcount));
-	atomic_dec(&inode->i_readcount);
+	BUG_ON(atomic_dec_return(&inode->i_readcount) < 0);
 }
 static inline void i_readcount_inc(struct inode *inode)
 {
@@ -2880,7 +3053,8 @@ extern void page_put_link(void *);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
-void generic_fillattr(struct mnt_idmap *, struct inode *, struct kstat *);
+void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode);
+void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
 void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
 extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
 extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
@@ -2919,7 +3093,6 @@ extern int vfs_readlink(struct dentry *, char __user *, int);
 extern struct file_system_type *get_filesystem(struct file_system_type *fs);
 extern void put_filesystem(struct file_system_type *fs);
 extern struct file_system_type *get_fs_type(const char *name);
-extern struct super_block *get_super(struct block_device *);
 extern struct super_block *get_active_super(struct block_device *bdev);
 extern void drop_super(struct super_block *sb);
 extern void drop_super_exclusive(struct super_block *sb);
@@ -2940,6 +3113,8 @@ extern int simple_open(struct inode *inode, struct file *file);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
 extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
+void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry,
+			     struct inode *new_dir, struct dentry *new_dentry);
 extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
 				  struct inode *new_dir, struct dentry *new_dentry);
 extern int simple_rename(struct mnt_idmap *, struct inode *,
@@ -2956,7 +3131,7 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
 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 *);
-extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
+extern int simple_nosetlease(struct file *, int, struct file_lock **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
@@ -2977,6 +3152,22 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
 extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
 		const void __user *from, size_t count);
 
+struct offset_ctx {
+	struct xarray		xa;
+	u32			next_offset;
+};
+
+void simple_offset_init(struct offset_ctx *octx);
+int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry);
+void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry);
+int simple_offset_rename_exchange(struct inode *old_dir,
+				  struct dentry *old_dentry,
+				  struct inode *new_dir,
+				  struct dentry *new_dentry);
+void simple_offset_destroy(struct offset_ctx *octx);
+
+extern const struct file_operations simple_offset_dir_operations;
+
 extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
 extern int generic_file_fsync(struct file *, loff_t, loff_t, int);