/* 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;
* 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).
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
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 *
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
#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)
/* 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;
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);
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 {
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;
};
#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)
{
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);
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)
{
}
/*
+ * 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
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);
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);
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)
__setup("rootfstype=", fs_names_setup);
__setup("rootdelay=", root_delay_setup);
- static void __init get_fs_names(char *page)
+ static int __init split_fs_names(char *page, char *names)
{
- char *s = page;
+ int count = 0;
+ char *p = page;
- if (root_fs_names) {
- strcpy(page, root_fs_names);
- while (*s++) {
- if (s[-1] == ',')
- s[-1] = '\0';
- }
- } else {
- int len = get_filesystem_list(page);
- char *p, *next;
-
- page[len] = '\0';
- for (p = page-1; p; p = next) {
- next = strchr(++p, '\n');
- if (*p++ != '\t')
- continue;
- while ((*s++ = *p++) != '\n')
- ;
- s[-1] = '\0';
- }
+ strcpy(p, root_fs_names);
+ while (*p++) {
+ if (p[-1] == ',')
+ p[-1] = '\0';
}
- *s = '\0';
+ *p = '\0';
+
+ for (p = page; *p; p += strlen(p)+1)
+ count++;
+
+ return count;
}
static int __init do_mount_root(const char *name, const char *fs,
char *fs_names = page_address(page);
char *p;
char b[BDEVNAME_SIZE];
+ int num_fs, i;
scnprintf(b, BDEVNAME_SIZE, "unknown-block(%u,%u)",
MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
- get_fs_names(fs_names);
+ if (root_fs_names)
+ num_fs = split_fs_names(fs_names, root_fs_names);
+ else
+ num_fs = list_bdev_fs_names(fs_names, PAGE_SIZE);
retry:
- for (p = fs_names; *p; p += strlen(p)+1) {
+ for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1) {
int err = do_mount_root(name, p, flags, root_mount_data);
switch (err) {
case 0:
printk("Please append a correct \"root=\" boot option; here are the available partitions:\n");
printk_all_partitions();
-#ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT
- printk("DEBUG_BLOCK_EXT_DEVT is enabled, you need to specify "
- "explicit textual name for \"root=\" boot option.\n");
-#endif
panic("VFS: Unable to mount root fs on %s", b);
}
if (!(flags & SB_RDONLY)) {
printk("List of all partitions:\n");
printk_all_partitions();
printk("No filesystem could mount root, tried: ");
- for (p = fs_names; *p; p += strlen(p)+1)
+ for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1)
printk(" %s", p);
printk("\n");
panic("VFS: Unable to mount root fs on %s", b);
}
#endif
+ static bool __init fs_is_nodev(char *fstype)
+ {
+ struct file_system_type *fs = get_fs_type(fstype);
+ bool ret = false;
+
+ if (fs) {
+ ret = !(fs->fs_flags & FS_REQUIRES_DEV);
+ put_filesystem(fs);
+ }
+
+ return ret;
+ }
+
+ static int __init mount_nodev_root(void)
+ {
+ char *fs_names, *fstype;
+ int err = -EINVAL;
+ int num_fs, i;
+
+ fs_names = (void *)__get_free_page(GFP_KERNEL);
+ if (!fs_names)
+ return -EINVAL;
+ num_fs = split_fs_names(fs_names, root_fs_names);
+
+ for (i = 0, fstype = fs_names; i < num_fs;
+ i++, fstype += strlen(fstype) + 1) {
+ if (!fs_is_nodev(fstype))
+ continue;
+ err = do_mount_root(root_device_name, fstype, root_mountflags,
+ root_mount_data);
+ if (!err)
+ break;
+ if (err != -EACCES && err != -EINVAL)
+ panic("VFS: Unable to mount root \"%s\" (%s), err=%d\n",
+ root_device_name, fstype, err);
+ }
+
+ free_page((unsigned long)fs_names);
+ return err;
+ }
+
void __init mount_root(void)
{
#ifdef CONFIG_ROOT_NFS
return;
}
#endif
+ if (ROOT_DEV == 0 && root_device_name && root_fs_names) {
+ if (mount_nodev_root() == 0)
+ return;
+ }
#ifdef CONFIG_BLOCK
{
int err = create_dev("/dev/root", ROOT_DEV);