s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
- if (prealloc_shrinker(&s->s_shrink))
+ if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name))
goto fail;
if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink))
goto fail;
return false;
}
+ /**
+ * retire_super - prevents superblock from being reused
+ * @sb: superblock to retire
+ *
+ * The function marks superblock to be ignored in superblock test, which
+ * prevents it from being reused for any new mounts. If the superblock has
+ * a private bdi, it also unregisters it, but doesn't reduce the refcount
+ * of the superblock to prevent potential races. The refcount is reduced
+ * by generic_shutdown_super(). The function can not be called
+ * concurrently with generic_shutdown_super(). It is safe to call the
+ * function multiple times, subsequent calls have no effect.
+ *
+ * The marker will affect the re-use only for block-device-based
+ * superblocks. Other superblocks will still get marked if this function
+ * is used, but that will not affect their reusability.
+ */
+ void retire_super(struct super_block *sb)
+ {
+ WARN_ON(!sb->s_bdev);
+ down_write(&sb->s_umount);
+ if (sb->s_iflags & SB_I_PERSB_BDI) {
+ bdi_unregister(sb->s_bdi);
+ sb->s_iflags &= ~SB_I_PERSB_BDI;
+ }
+ sb->s_iflags |= SB_I_RETIRED;
+ up_write(&sb->s_umount);
+ }
+ EXPORT_SYMBOL(retire_super);
+
/**
* generic_shutdown_super - common helper for ->kill_sb()
* @sb: superblock to kill
static int test_bdev_super_fc(struct super_block *s, struct fs_context *fc)
{
- return s->s_bdev == fc->sget_key;
+ return !(s->s_iflags & SB_I_RETIRED) && s->s_bdev == fc->sget_key;
}
/**
} else {
s->s_mode = mode;
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
+ shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
+ fc->fs_type->name, s->s_id);
sb_set_blocksize(s, block_size(bdev));
error = fill_super(s, fc);
if (error) {
static int test_bdev_super(struct super_block *s, void *data)
{
- return (void *)s->s_bdev == data;
+ return !(s->s_iflags & SB_I_RETIRED) && (void *)s->s_bdev == data;
}
struct dentry *mount_bdev(struct file_system_type *fs_type,
} else {
s->s_mode = mode;
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
+ shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
+ fs_type->name, s->s_id);
sb_set_blocksize(s, block_size(bdev));
error = fill_super(s, data, flags & SB_SILENT ? 1 : 0);
if (error) {
struct fs_context;
struct fs_parameter_spec;
struct fileattr;
+struct iomap_ops;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
/* File supports async buffered reads */
#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000)
+/* File supports async nowait buffered writes */
+#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000)
+
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
struct iattr {
unsigned int ia_valid;
umode_t ia_mode;
- kuid_t ia_uid;
- kgid_t ia_gid;
+ /*
+ * The two anonymous unions wrap structures with the same member.
+ *
+ * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which
+ * are a dedicated type requiring the filesystem to use the dedicated
+ * helpers. Other filesystem can continue to use ia_{g,u}id until they
+ * have been ported.
+ *
+ * They always contain the same value. In other words FS_ALLOW_IDMAP
+ * pass down the same value on idmapped mounts as they would on regular
+ * mounts.
+ */
+ union {
+ kuid_t ia_uid;
+ vfsuid_t ia_vfsuid;
+ };
+ union {
+ kgid_t ia_gid;
+ vfsgid_t ia_vfsgid;
+ };
loff_t ia_size;
struct timespec64 ia_atime;
struct timespec64 ia_mtime;
void (*free_folio)(struct folio *folio);
ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
/*
- * migrate the contents of a page to the specified target. If
+ * migrate the contents of a folio to the specified target. If
* migrate_mode is MIGRATE_ASYNC, it must not block.
*/
- 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 (*migrate_folio)(struct address_space *, struct folio *dst,
+ struct folio *src, enum migrate_mode);
int (*launder_folio)(struct folio *);
bool (*is_partially_uptodate) (struct folio *, size_t from,
size_t count);
struct file {
union {
- struct llist_node fu_llist;
- struct rcu_head fu_rcuhead;
- } f_u;
+ struct llist_node f_llist;
+ struct rcu_head f_rcuhead;
+ unsigned int f_iocb_flags;
+ };
struct path f_path;
struct inode *f_inode; /* cached value */
const struct file_operations *f_op;
#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */
#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */
#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
+ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */
/* Possible states of 'frozen' field */
enum {
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to map
*
+ * Note, this will eventually be removed completely in favor of the type-safe
+ * i_uid_into_vfsuid().
+ *
* Return: the inode's i_uid mapped down according to @mnt_userns.
* If the inode's i_uid has no mapping INVALID_UID is returned.
*/
static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns,
const struct inode *inode)
{
- return mapped_kuid_fs(mnt_userns, i_user_ns(inode), inode->i_uid);
+ return AS_KUIDT(make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid));
+}
+
+/**
+ * i_uid_into_vfsuid - map an inode's i_uid down into a mnt_userns
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: inode to map
+ *
+ * Return: whe inode's i_uid mapped down according to @mnt_userns.
+ * If the inode's i_uid has no mapping INVALID_VFSUID is returned.
+ */
+static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns,
+ const struct inode *inode)
+{
+ return make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid);
+}
+
+/**
+ * i_uid_needs_update - check whether inode's i_uid needs to be updated
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Check whether the $inode's i_uid field needs to be updated taking idmapped
+ * mounts into account if the filesystem supports it.
+ *
+ * Return: true if @inode's i_uid field needs to be updated, false if not.
+ */
+static inline bool i_uid_needs_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ const struct inode *inode)
+{
+ return ((attr->ia_valid & ATTR_UID) &&
+ !vfsuid_eq(attr->ia_vfsuid,
+ i_uid_into_vfsuid(mnt_userns, inode)));
+}
+
+/**
+ * i_uid_update - update @inode's i_uid field
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Safely update @inode's i_uid field translating the vfsuid of any idmapped
+ * mount into the filesystem kuid.
+ */
+static inline void i_uid_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ struct inode *inode)
+{
+ if (attr->ia_valid & ATTR_UID)
+ inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode),
+ attr->ia_vfsuid);
}
/**
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to map
*
+ * Note, this will eventually be removed completely in favor of the type-safe
+ * i_gid_into_vfsgid().
+ *
* Return: the inode's i_gid mapped down according to @mnt_userns.
* If the inode's i_gid has no mapping INVALID_GID is returned.
*/
static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns,
const struct inode *inode)
{
- return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid);
+ return AS_KGIDT(make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid));
+}
+
+/**
+ * i_gid_into_vfsgid - map an inode's i_gid down into a mnt_userns
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @inode: inode to map
+ *
+ * Return: the inode's i_gid mapped down according to @mnt_userns.
+ * If the inode's i_gid has no mapping INVALID_VFSGID is returned.
+ */
+static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns,
+ const struct inode *inode)
+{
+ return make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid);
+}
+
+/**
+ * i_gid_needs_update - check whether inode's i_gid needs to be updated
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Check whether the $inode's i_gid field needs to be updated taking idmapped
+ * mounts into account if the filesystem supports it.
+ *
+ * Return: true if @inode's i_gid field needs to be updated, false if not.
+ */
+static inline bool i_gid_needs_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ const struct inode *inode)
+{
+ return ((attr->ia_valid & ATTR_GID) &&
+ !vfsgid_eq(attr->ia_vfsgid,
+ i_gid_into_vfsgid(mnt_userns, inode)));
+}
+
+/**
+ * i_gid_update - update @inode's i_gid field
+ * @mnt_userns: user namespace of the mount the inode was found from
+ * @attr: the new attributes of @inode
+ * @inode: the inode to update
+ *
+ * Safely update @inode's i_gid field translating the vfsgid of any idmapped
+ * mount into the filesystem kgid.
+ */
+static inline void i_gid_update(struct user_namespace *mnt_userns,
+ const struct iattr *attr,
+ struct inode *inode)
+{
+ if (attr->ia_valid & ATTR_GID)
+ inode->i_gid = from_vfsgid(mnt_userns, i_user_ns(inode),
+ attr->ia_vfsgid);
}
/**
extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t len, unsigned int flags);
-extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out,
- loff_t *count,
- unsigned int remap_flags);
+int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t *len, unsigned int remap_flags,
+ const struct iomap_ops *dax_read_ops);
+int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t *count, unsigned int remap_flags);
extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns,
struct inode *inode)
{
- return !uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
- !gid_valid(i_gid_into_mnt(mnt_userns, inode));
+ return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) ||
+ !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode));
}
-static inline int iocb_flags(struct file *file);
-
static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
*kiocb = (struct kiocb) {
.ki_filp = filp,
- .ki_flags = iocb_flags(filp),
+ .ki_flags = filp->f_iocb_flags,
.ki_ioprio = get_current_ioprio(),
};
}
}
extern int file_modified(struct file *file);
+int kiocb_modified(struct kiocb *iocb);
int sync_inode_metadata(struct inode *inode, int wait);
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
+ void retire_super(struct super_block *sb);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
unsigned int flags);
+static inline bool iocb_is_dsync(const struct kiocb *iocb)
+{
+ return (iocb->ki_flags & IOCB_DSYNC) ||
+ IS_SYNC(iocb->ki_filp->f_mapping->host);
+}
+
/*
* Sync the bytes written if this was a synchronous write. Expect ki_pos
* to already be updated for the write, and will return either the amount
*/
static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
{
- if (iocb->ki_flags & IOCB_DSYNC) {
+ if (iocb_is_dsync(iocb)) {
int ret = vfs_fsync_range(iocb->ki_filp,
iocb->ki_pos - count, iocb->ki_pos - 1,
(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
-extern loff_t no_llseek(struct file *file, loff_t offset, int whence);
+#define no_llseek NULL
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
-#ifdef CONFIG_MIGRATION
-extern int buffer_migrate_page(struct address_space *,
- struct page *, struct page *,
- enum migrate_mode);
-extern int buffer_migrate_page_norefs(struct address_space *,
- struct page *, struct page *,
- enum migrate_mode);
-#else
-#define buffer_migrate_page NULL
-#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 *);
res |= IOCB_APPEND;
if (file->f_flags & O_DIRECT)
res |= IOCB_DIRECT;
- if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host))
+ if (file->f_flags & O_DSYNC)
res |= IOCB_DSYNC;
if (file->f_flags & __O_SYNC)
res |= IOCB_SYNC;