#define CHECK_IOVEC_ONLY -1
/*
- * The below are the various read and write types that we support. Some of
+ * The below are the various read and write flags that we support. Some of
* them include behavioral modifiers that send information down to the
- * block layer and IO scheduler. Terminology:
+ * block layer and IO scheduler. They should be used along with a req_op.
+ * Terminology:
*
* The block layer uses device plugging to defer IO a little bit, in
* the hope that we will see more IO very shortly. This increases
* READ_SYNC A synchronous read. Device is not plugged, caller can
* immediately wait on this read without caring about
* unplugging.
- * READA Used for read-ahead operations. Lower priority, and the
- * block layer could (in theory) choose to ignore this
- * request if it runs into resource problems.
* WRITE A normal async write. Device will be plugged.
* WRITE_SYNC Synchronous write. Identical to WRITE, but passes down
* the hint that someone will be waiting on this IO
* non-volatile media on completion.
*
*/
-#define RW_MASK REQ_WRITE
-#define RWA_MASK REQ_RAHEAD
+#define RW_MASK REQ_OP_WRITE
-#define READ 0
-#define WRITE RW_MASK
-#define READA RWA_MASK
+#define READ REQ_OP_READ
+#define WRITE REQ_OP_WRITE
-#define READ_SYNC (READ | REQ_SYNC)
-#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
-#define WRITE_ODIRECT (WRITE | REQ_SYNC)
-#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
-#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
-#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
+#define READ_SYNC REQ_SYNC
+#define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT REQ_SYNC
+#define WRITE_FLUSH (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH)
+#define WRITE_FUA (REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA)
/*
* Attribute flags. These should be or-ed together to figure out what
*/
int (*migratepage) (struct address_space *,
struct page *, struct page *, enum migrate_mode);
+ bool (*isolate_page)(struct page *, isolate_mode_t);
+ void (*putback_page)(struct page *);
int (*launder_page) (struct page *);
int (*is_partially_uptodate) (struct page *, unsigned long,
unsigned long);
struct inode * bd_inode; /* will die */
struct super_block * bd_super;
struct mutex bd_mutex; /* open/close mutex */
- struct list_head bd_inodes;
void * bd_claiming;
void * bd_holder;
int bd_holders;
#endif
struct list_head i_lru; /* inode LRU list */
struct list_head i_sb_list;
+ struct list_head i_wb_list; /* backing dev writeback list */
union {
struct hlist_head i_dentry;
struct rcu_head i_rcu;
#endif
}
-/* Helper functions so that in most cases filesystems will
- * not need to deal directly with kuid_t and kgid_t and can
- * instead deal with the raw numeric values that are stored
- * in the filesystem.
- */
-static inline uid_t i_uid_read(const struct inode *inode)
-{
- return from_kuid(&init_user_ns, inode->i_uid);
-}
-
-static inline gid_t i_gid_read(const struct inode *inode)
-{
- return from_kgid(&init_user_ns, inode->i_gid);
-}
-
-static inline void i_uid_write(struct inode *inode, uid_t uid)
-{
- inode->i_uid = make_kuid(&init_user_ns, uid);
-}
-
-static inline void i_gid_write(struct inode *inode, gid_t gid)
-{
- inode->i_gid = make_kgid(&init_user_ns, gid);
-}
-
static inline unsigned iminor(const struct inode *inode)
{
return MINOR(inode->i_rdev);
static inline struct dentry *file_dentry(const struct file *file)
{
- struct dentry *dentry = file->f_path.dentry;
-
- if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
- return dentry->d_op->d_real(dentry, file_inode(file));
- else
- return dentry;
+ return d_real(file->f_path.dentry, file_inode(file), 0);
}
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
/* sb->s_iflags */
#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */
#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */
+#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */
+
+/* sb->s_iflags to limit user namespace mounts */
+#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */
/* Possible states of 'frozen' field */
enum {
struct workqueue_struct *s_dio_done_wq;
struct hlist_head s_pins;
+ /*
+ * Owning user namespace and default context in which to
+ * interpret filesystem uids, gids, quotas, device nodes,
+ * xattrs and security labels.
+ */
+ struct user_namespace *s_user_ns;
+
/*
* Keep the lru lists last in the structure so they always sit on their
* own individual cachelines.
/* s_inode_list_lock protects s_inodes */
spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp;
struct list_head s_inodes; /* all inodes */
+
+ spinlock_t s_inode_wblist_lock;
+ struct list_head s_inodes_wb; /* writeback inodes */
};
+/* Helper functions so that in most cases filesystems will
+ * not need to deal directly with kuid_t and kgid_t and can
+ * instead deal with the raw numeric values that are stored
+ * in the filesystem.
+ */
+static inline uid_t i_uid_read(const struct inode *inode)
+{
+ return from_kuid(inode->i_sb->s_user_ns, inode->i_uid);
+}
+
+static inline gid_t i_gid_read(const struct inode *inode)
+{
+ return from_kgid(inode->i_sb->s_user_ns, inode->i_gid);
+}
+
+static inline void i_uid_write(struct inode *inode, uid_t uid)
+{
+ inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid);
+}
+
+static inline void i_gid_write(struct inode *inode, gid_t gid)
+{
+ inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid);
+}
+
extern struct timespec current_fs_time(struct super_block *sb);
/*
*/
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
umode_t mode);
+extern bool may_open_dev(const struct path *path);
/*
* VFS FS_IOC_FIEMAP helper definitions.
*/
#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \
(inode)->i_rdev == WHITEOUT_DEV)
+static inline bool HAS_UNMAPPED_ID(struct inode *inode)
+{
+ return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid);
+}
+
/*
* Inode state bits. Protected by inode->i_lock
*
#define FS_BINARY_MOUNTDATA 2
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
-#define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */
-#define FS_USERNS_VISIBLE 32 /* FS must already be visible */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
-extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
- void *data, int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_ns(struct file_system_type *fs_type,
+ int flags, void *data, void *ns, struct user_namespace *user_ns,
+ int (*fill_super)(struct super_block *, void *, int));
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));
int set_anon_super(struct super_block *s, void *data);
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
+struct super_block *sget_userns(struct file_system_type *type,
+ int (*test)(struct super_block *,void *),
+ int (*set)(struct super_block *,void *),
+ int flags, struct user_namespace *user_ns,
+ void *data);
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
extern bool is_bad_inode(struct inode *);
#ifdef CONFIG_BLOCK
-/*
- * return READ, READA, or WRITE
- */
-#define bio_rw(bio) ((bio)->bi_rw & (RW_MASK | RWA_MASK))
+static inline bool op_is_write(unsigned int op)
+{
+ return op == REQ_OP_READ ? false : true;
+}
/*
* return data direction, READ or WRITE
*/
-#define bio_data_dir(bio) ((bio)->bi_rw & 1)
+static inline int bio_data_dir(struct bio *bio)
+{
+ return op_is_write(bio_op(bio)) ? WRITE : READ;
+}
extern void check_disk_size_change(struct gendisk *disk,
struct block_device *bdev);
extern void inode_sb_list_add(struct inode *inode);
#ifdef CONFIG_BLOCK
-extern blk_qc_t submit_bio(int, struct bio *);
+extern blk_qc_t submit_bio(struct bio *);
extern int bdev_read_only(struct block_device *);
#endif
extern int set_blocksize(struct block_device *, int);
extern int nonseekable_open(struct inode * inode, struct file * filp);
#ifdef CONFIG_BLOCK
-typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
+typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
loff_t file_offset);
enum {