diff options
Diffstat (limited to 'Documentation/filesystems/Locking')
| -rw-r--r-- | Documentation/filesystems/Locking | 57 |
1 files changed, 18 insertions, 39 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 18b9d0ca063..2db4283efa8 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -92,8 +92,8 @@ prototypes: void (*destroy_inode)(struct inode *); void (*dirty_inode) (struct inode *); int (*write_inode) (struct inode *, int); - void (*drop_inode) (struct inode *); - void (*delete_inode) (struct inode *); + int (*drop_inode) (struct inode *); + void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); @@ -101,14 +101,13 @@ prototypes: int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); - void (*clear_inode) (struct inode *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct vfsmount *); ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); locking rules: - All may block. + All may block [not true, see below] None have BKL s_umount alloc_inode: @@ -116,22 +115,25 @@ destroy_inode: dirty_inode: (must not sleep) write_inode: drop_inode: !!!inode_lock!!! -delete_inode: +evict_inode: put_super: write write_super: read sync_fs: read freeze_fs: read unfreeze_fs: read -statfs: no -remount_fs: maybe (see below) -clear_inode: +statfs: maybe(read) (see below) +remount_fs: write umount_begin: no show_options: no (namespace_sem) quota_read: no (see below) quota_write: no (see below) -->remount_fs() will have the s_umount exclusive lock if it's already mounted. -When called from get_sb_single, it does NOT have the s_umount lock. +->statfs() has s_umount (shared) when called by ustat(2) (native or +compat), but that's an accident of bad API; s_umount is used to pin +the superblock down when we only have dev_t given us by userland to +identify the superblock. Everything else (statfs(), fstatfs(), etc.) +doesn't hold it when calling ->statfs() - superblock is pinned down +by resolving the pathname passed to syscall. ->quota_read() and ->quota_write() functions are both guaranteed to be the only ones operating on the quota file by the quota code (via dqio_sem) (unless an admin really wants to screw up something and @@ -178,7 +180,7 @@ prototypes: locking rules: All except set_page_dirty may block - BKL PageLocked(page) i_sem + BKL PageLocked(page) i_mutex writepage: no yes, unlocks (see below) readpage: no yes, unlocks sync_page: no maybe @@ -372,15 +374,13 @@ prototypes: ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); - int (*ioctl) (struct inode *, struct file *, unsigned int, - unsigned long); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, struct dentry *, int datasync); + int (*fsync) (struct file *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); @@ -407,8 +407,7 @@ write: no aio_write: no readdir: no poll: no -ioctl: yes (see below) -unlocked_ioctl: no (see below) +unlocked_ioctl: no compat_ioctl: no mmap: no open: no @@ -429,8 +428,9 @@ check_flags: no implementations. If your fs is not using generic_file_llseek, you need to acquire and release the appropriate locks in your ->llseek(). For many filesystems, it is probably safe to acquire the inode -semaphore. Note some filesystems (i.e. remote ones) provide no -protection for i_size so you will need to use the BKL. +mutex or just to use i_size_read() instead. +Note: this does not protect the file->f_pos against concurrent modifications +since this is something the userspace has to take care about. Note: ext2_release() was *the* source of contention on fs-intensive loads and dropping BKL on ->release() helps to get rid of that (we still @@ -450,9 +450,6 @@ move ->readdir() to inode_operations and use a separate method for directory anything that resembles union-mount we won't have a struct file for all components. And there are other reasons why the current interface is a mess... -->ioctl() on regular files is superceded by the ->unlocked_ioctl() that -doesn't take the BKL. - ->read on directories probably must go away - we should just enforce -EISDIR in sys_read() and friends. @@ -460,13 +457,6 @@ in sys_read() and friends. --------------------------- dquot_operations ------------------------------- prototypes: - int (*initialize) (struct inode *, int); - int (*drop) (struct inode *); - int (*alloc_space) (struct inode *, qsize_t, int); - int (*alloc_inode) (const struct inode *, unsigned long); - int (*free_space) (struct inode *, qsize_t); - int (*free_inode) (const struct inode *, unsigned long); - int (*transfer) (struct inode *, struct iattr *); int (*write_dquot) (struct dquot *); int (*acquire_dquot) (struct dquot *); int (*release_dquot) (struct dquot *); @@ -479,13 +469,6 @@ a proper locking wrt the filesystem and call the generic quota operations. What filesystem should expect from the generic quota functions: FS recursion Held locks when called -initialize: yes maybe dqonoff_sem -drop: yes - -alloc_space: ->mark_dirty() - -alloc_inode: ->mark_dirty() - -free_space: ->mark_dirty() - -free_inode: ->mark_dirty() - -transfer: yes - write_dquot: yes dqonoff_sem or dqptr_sem acquire_dquot: yes dqonoff_sem or dqptr_sem release_dquot: yes dqonoff_sem or dqptr_sem @@ -495,10 +478,6 @@ write_info: yes dqonoff_sem FS recursion means calling ->quota_read() and ->quota_write() from superblock operations. -->alloc_space(), ->alloc_inode(), ->free_space(), ->free_inode() are called -only directly by the filesystem and do not call any fs functions only -the ->mark_dirty() operation. - More details about quota locking can be found in fs/dquot.c. --------------------------- vm_operations_struct ----------------------------- |