1 files changed, 79 insertions, 107 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 640574294216..f3cfca5edc9a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -48,6 +48,7 @@
 struct backing_dev_info;
 struct bdi_writeback;
 struct bio;
+struct io_comp_batch;
 struct export_operations;
 struct fiemap_extent_info;
 struct hd_geometry;
@@ -319,6 +320,8 @@ enum rw_hint {
 /* iocb->ki_waitq is valid */
 #define IOCB_WAITQ		(1 << 19)
 #define IOCB_NOIO		(1 << 20)
+/* can use bio alloc cache */
+#define IOCB_ALLOC_CACHE	(1 << 21)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -327,16 +330,12 @@ struct kiocb {
 	randomized_struct_fields_start
 
 	loff_t			ki_pos;
-	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
+	void (*ki_complete)(struct kiocb *iocb, long ret);
 	void			*private;
 	int			ki_flags;
 	u16			ki_hint;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	union {
-		unsigned int		ki_cookie; /* for ->iopoll */
-		struct wait_page_queue	*ki_waitq; /* for async buffered IO */
-	};
-
+	struct wait_page_queue	*ki_waitq; /* for async buffered IO */
 	randomized_struct_fields_end
 };
 
@@ -436,6 +435,10 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
  * struct address_space - Contents of a cacheable, mappable object.
  * @host: Owner, either the inode or the block_device.
  * @i_pages: Cached pages.
+ * @invalidate_lock: Guards coherency between page cache contents and
+ *   file offset->disk block mappings in the filesystem during invalidates.
+ *   It is also used to block modification of page cache contents through
+ *   memory mappings.
  * @gfp_mask: Memory allocation flags to use for allocating pages.
  * @i_mmap_writable: Number of VM_SHARED mappings.
  * @nr_thps: Number of THPs in the pagecache (non-shmem only).
@@ -453,6 +456,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
 struct address_space {
 	struct inode		*host;
 	struct xarray		i_pages;
+	struct rw_semaphore	invalidate_lock;
 	gfp_t			gfp_mask;
 	atomic_t		i_mmap_writable;
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
@@ -581,6 +585,11 @@ static inline void mapping_allow_writable(struct address_space *mapping)
 
 struct posix_acl;
 #define ACL_NOT_CACHED ((void *)(-1))
+/*
+ * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to
+ * cache the ACL.  This also means that ->get_acl() can be called in RCU mode
+ * with the LOOKUP_RCU flag.
+ */
 #define ACL_DONT_CACHE ((void *)(-3))
 
 static inline struct posix_acl *
@@ -814,9 +823,42 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla
 	down_read_nested(&inode->i_rwsem, subclass);
 }
 
+static inline void filemap_invalidate_lock(struct address_space *mapping)
+{
+	down_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock(struct address_space *mapping)
+{
+	up_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
+{
+	down_read(&mapping->invalidate_lock);
+}
+
+static inline int filemap_invalidate_trylock_shared(
+					struct address_space *mapping)
+{
+	return down_read_trylock(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock_shared(
+					struct address_space *mapping)
+{
+	up_read(&mapping->invalidate_lock);
+}
+
 void lock_two_nondirectories(struct inode *, struct inode*);
 void unlock_two_nondirectories(struct inode *, struct inode*);
 
+void filemap_invalidate_lock_two(struct address_space *mapping1,
+				 struct address_space *mapping2);
+void filemap_invalidate_unlock_two(struct address_space *mapping1,
+				   struct address_space *mapping2);
+
+
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic
@@ -997,6 +1039,7 @@ static inline struct file *get_file(struct file *f)
 #define FL_UNLOCK_PENDING	512 /* Lease is being broken */
 #define FL_OFDLCK	1024	/* lock is "owned" by struct file */
 #define FL_LAYOUT	2048	/* outstanding pNFS layout */
+#define FL_RECLAIM	4096	/* reclaiming from a reboot server */
 
 #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)
 
@@ -1507,8 +1550,11 @@ struct super_block {
 	/* Number of inodes with nlink == 0 but still referenced */
 	atomic_long_t s_remove_count;
 
-	/* Pending fsnotify inode refs */
-	atomic_long_t s_fsnotify_inode_refs;
+	/*
+	 * Number of inode/mount/sb objects that are being watched, note that
+	 * inodes objects are currently double-accounted.
+	 */
+	atomic_long_t s_fsnotify_connectors;
 
 	/* Being remounted read-only */
 	int s_readonly_remount;
@@ -2026,7 +2072,8 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
-	int (*iopoll)(struct kiocb *kiocb, bool spin);
+	int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
+			unsigned int flags);
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
@@ -2065,7 +2112,7 @@ struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 	int (*permission) (struct user_namespace *, struct inode *, int);
-	struct posix_acl * (*get_acl)(struct inode *, int);
+	struct posix_acl * (*get_acl)(struct inode *, int, bool);
 
 	int (*readlink) (struct dentry *, char __user *,int);
 
@@ -2449,6 +2496,8 @@ 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);
+
 static inline void file_accessed(struct file *file)
 {
 	if (!(file->f_flags & O_NOATIME))
@@ -2457,7 +2506,6 @@ static inline void file_accessed(struct file *file)
 
 extern int file_modified(struct file *file);
 
-int sync_inode(struct inode *inode, struct writeback_control *wbc);
 int sync_inode_metadata(struct inode *inode, int wait);
 
 struct file_system_type {
@@ -2487,6 +2535,7 @@ struct file_system_type {
 
 	struct lock_class_key i_lock_key;
 	struct lock_class_key i_mutex_key;
+	struct lock_class_key invalidate_lock_key;
 	struct lock_class_key i_mutex_dir_key;
 };
 
@@ -2570,90 +2619,6 @@ extern struct kobject *fs_kobj;
 
 #define MAX_RW_COUNT (INT_MAX & PAGE_MASK)
 
-#ifdef CONFIG_MANDATORY_FILE_LOCKING
-extern int locks_mandatory_locked(struct file *);
-extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char);
-
-/*
- * Candidates for mandatory locking have the setgid bit set
- * but no group execute bit -  an otherwise meaningless combination.
- */
-
-static inline int __mandatory_lock(struct inode *ino)
-{
-	return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
-}
-
-/*
- * ... and these candidates should be on SB_MANDLOCK mounted fs,
- * otherwise these will be advisory locks
- */
-
-static inline int mandatory_lock(struct inode *ino)
-{
-	return IS_MANDLOCK(ino) && __mandatory_lock(ino);
-}
-
-static inline int locks_verify_locked(struct file *file)
-{
-	if (mandatory_lock(locks_inode(file)))
-		return locks_mandatory_locked(file);
-	return 0;
-}
-
-static inline int locks_verify_truncate(struct inode *inode,
-				    struct file *f,
-				    loff_t size)
-{
-	if (!inode->i_flctx || !mandatory_lock(inode))
-		return 0;
-
-	if (size < inode->i_size) {
-		return locks_mandatory_area(inode, f, size, inode->i_size - 1,
-				F_WRLCK);
-	} else {
-		return locks_mandatory_area(inode, f, inode->i_size, size - 1,
-				F_WRLCK);
-	}
-}
-
-#else /* !CONFIG_MANDATORY_FILE_LOCKING */
-
-static inline int locks_mandatory_locked(struct file *file)
-{
-	return 0;
-}
-
-static inline int locks_mandatory_area(struct inode *inode, struct file *filp,
-                                       loff_t start, loff_t end, unsigned char type)
-{
-	return 0;
-}
-
-static inline int __mandatory_lock(struct inode *inode)
-{
-	return 0;
-}
-
-static inline int mandatory_lock(struct inode *inode)
-{
-	return 0;
-}
-
-static inline int locks_verify_locked(struct file *file)
-{
-	return 0;
-}
-
-static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
-					size_t size)
-{
-	return 0;
-}
-
-#endif /* CONFIG_MANDATORY_FILE_LOCKING */
-
-
 #ifdef CONFIG_FILE_LOCKING
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
@@ -2786,6 +2751,7 @@ static inline struct file *file_clone_open(struct file *file)
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int, int *);
+extern struct filename *getname_uflags(const char __user *, int);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 extern void putname(struct filename *name);
@@ -2891,6 +2857,8 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,
 				loff_t start, loff_t end);
 extern int filemap_check_errors(struct address_space *mapping);
 extern void __filemap_set_wb_err(struct address_space *mapping, int err);
+int filemap_fdatawrite_wbc(struct address_space *mapping,
+			   struct writeback_control *wbc);
 
 static inline int filemap_write_and_wait(struct address_space *mapping)
 {
@@ -3055,15 +3023,20 @@ static inline void file_end_write(struct file *file)
 }
 
 /*
+ * This is used for regular files where some users -- especially the
+ * currently executed binary in a process, previously handled via
+ * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap
+ * read-write shared) accesses.
+ *
  * get_write_access() gets write permission for a file.
  * put_write_access() releases this write permission.
- * This is used for regular files.
- * We cannot support write (and maybe mmap read-write shared) accesses and
- * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
- * can have the following values:
- * 0: no writers, no VM_DENYWRITE mappings
- * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
- * > 0: (i_writecount) users are writing to the file.
+ * deny_write_access() denies write access to a file.
+ * allow_write_access() re-enables write access to a file.
+ *
+ * The i_writecount field of an inode can have the following values:
+ * 0: no write access, no denied write access
+ * < 0: (-i_writecount) users that denied write access to the file.
+ * > 0: (i_writecount) users that have write access to the file.
  *
  * Normally we operate on that counter with atomic_{inc,dec} and it's safe
  * except for the cases where we don't hold i_writecount yet. Then we need to
@@ -3246,10 +3219,6 @@ ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
 ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
 			    struct iov_iter *iter);
 
-/* fs/block_dev.c */
-extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
-			int datasync);
-
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
@@ -3355,6 +3324,7 @@ 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 user_namespace *, 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);
 void __inode_add_bytes(struct inode *inode, loff_t bytes);
@@ -3469,6 +3439,8 @@ extern int buffer_migrate_page_norefs(struct address_space *,
 #define buffer_migrate_page_norefs NULL
 #endif
 
+int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
+		unsigned int ia_valid);
 int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *);
 extern int inode_newsize_ok(const struct inode *, loff_t offset);
 void setattr_copy(struct user_namespace *, struct inode *inode,
@@ -3622,7 +3594,7 @@ int proc_nr_dentry(struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos);
 int proc_nr_inodes(struct ctl_table *table, int write,
 		   void *buffer, size_t *lenp, loff_t *ppos);
-int __init get_filesystem_list(char *buf);
+int __init list_bdev_fs_names(char *buf, size_t size);
 
 #define __FMODE_EXEC		((__force int) FMODE_EXEC)
 #define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)