diff options
Diffstat (limited to 'Documentation/filesystems')
| -rw-r--r-- | Documentation/filesystems/Locking | 22 | ||||
| -rw-r--r-- | Documentation/filesystems/nilfs2.txt | 3 | ||||
| -rw-r--r-- | Documentation/filesystems/orangefs.txt | 50 | ||||
| -rw-r--r-- | Documentation/filesystems/overlayfs.txt | 8 | ||||
| -rw-r--r-- | Documentation/filesystems/porting | 7 | ||||
| -rw-r--r-- | Documentation/filesystems/tmpfs.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/vfs.txt | 53 |
7 files changed, 101 insertions, 44 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 5a7386e38e2d..d30fb2cb5066 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -12,14 +12,17 @@ prototypes: int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); - int (*d_compare)(const struct dentry *, const struct dentry *, + int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(struct dentry *); + int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); struct vfsmount *(*d_automount)(struct path *path); int (*d_manage)(struct dentry *, bool); + struct dentry *(*d_real)(struct dentry *, const struct inode *, + unsigned int); locking rules: rename_lock ->d_lock may block rcu-walk @@ -28,12 +31,14 @@ d_weak_revalidate:no no yes no d_hash no no no maybe d_compare: yes no no maybe d_delete: no yes no no +d_init: no no yes no d_release: no no yes no d_prune: no yes no no d_iput: no no yes no d_dname: no no no no d_automount: no no yes no d_manage: no no yes (ref-walk) maybe +d_real no no yes no --------------------------- inode_operations --------------------------- prototypes: @@ -66,7 +71,6 @@ prototypes: struct file *, unsigned open_flag, umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); - int (*dentry_open)(struct dentry *, struct file *, const struct cred *); locking rules: all may block @@ -95,7 +99,6 @@ fiemap: no update_time: no atomic_open: yes tmpfile: no -dentry_open: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. @@ -179,7 +182,6 @@ unlocks and drops the reference. prototypes: int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); - int (*sync_page)(struct page *); int (*writepages)(struct address_space *, struct writeback_control *); int (*set_page_dirty)(struct page *page); int (*readpages)(struct file *filp, struct address_space *mapping, @@ -210,7 +212,6 @@ locking rules: PageLocked(page) i_mutex writepage: yes, unlocks (see below) readpage: yes, unlocks -sync_page: maybe writepages: set_page_dirty no readpages: @@ -230,8 +231,8 @@ error_remove_page: yes swap_activate: no swap_deactivate: no - ->write_begin(), ->write_end(), ->sync_page() and ->readpage() -may be called from the request handler (/dev/loop). + ->write_begin(), ->write_end() and ->readpage() may be called from +the request handler (/dev/loop). ->readpage() unlocks the page, either synchronously or via I/O completion. @@ -287,11 +288,6 @@ will leave the page itself marked clean but it will be tagged as dirty in the radix tree. This incoherency can lead to all sorts of hard-to-debug problems in the filesystem like having dirty inodes at umount and losing written data. - ->sync_page() locking rules are not well-defined - usually it is called -with lock on page, but that is not guaranteed. Considering the currently -existing instances of this method ->sync_page() itself doesn't look -well-defined... - ->writepages() is used for periodic writeback and for syscall-initiated sync operations. The address_space should start I/O against at least *nr_to_write pages. *nr_to_write must be decremented for each page which is @@ -399,7 +395,7 @@ prototypes: int (*release) (struct gendisk *, fmode_t); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - int (*direct_access) (struct block_device *, sector_t, void __pmem **, + int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt index 5b21ef76f751..c0727dc36271 100644 --- a/Documentation/filesystems/nilfs2.txt +++ b/Documentation/filesystems/nilfs2.txt @@ -267,7 +267,8 @@ among NILFS2 files can be depicted as follows: `-- file (ino=yy) ( regular file, directory, or symlink ) -For detail on the format of each file, please see include/linux/nilfs2_fs.h. +For detail on the format of each file, please see nilfs2_ondisk.h +located at include/uapi/linux directory. There are no patents or other intellectual property that we protect with regard to the design of NILFS2. It is allowed to replicate the diff --git a/Documentation/filesystems/orangefs.txt b/Documentation/filesystems/orangefs.txt index e1a0056a365f..1dfdec790946 100644 --- a/Documentation/filesystems/orangefs.txt +++ b/Documentation/filesystems/orangefs.txt @@ -281,7 +281,7 @@ on the wait queue and one attempt is made to recycle them. Obviously, if the client-core stays dead too long, the arbitrary userspace processes trying to use Orangefs will be negatively affected. Waiting ops that can't be serviced will be removed from the request list and -have their states set to "given up". In-progress ops that can't +have their states set to "given up". In-progress ops that can't be serviced will be removed from the in_progress hash table and have their states set to "given up". @@ -338,7 +338,7 @@ particular response. PVFS2_VFS_OP_STATFS fill a pvfs2_statfs_response_t with useless info <g>. It is hard for us to know, in a timely fashion, these statistics about our - distributed network filesystem. + distributed network filesystem. PVFS2_VFS_OP_FS_MOUNT fill a pvfs2_fs_mount_response_t which is just like a PVFS_object_kref @@ -386,7 +386,7 @@ responses: io_array[1].iov_base = address of global variable "pdev_magic" (int32_t) io_array[1].iov_len = sizeof(int32_t) - + io_array[2].iov_base = address of parameter "tag" (PVFS_id_gen_t) io_array[2].iov_len = sizeof(int64_t) @@ -402,5 +402,47 @@ Readdir responses initialize the fifth element io_array like this: io_array[4].iov_len = contents of member trailer_size (PVFS_size) from out_downcall member of global variable vfs_request - + +Orangefs exploits the dcache in order to avoid sending redundant +requests to userspace. We keep object inode attributes up-to-date with +orangefs_inode_getattr. Orangefs_inode_getattr uses two arguments to +help it decide whether or not to update an inode: "new" and "bypass". +Orangefs keeps private data in an object's inode that includes a short +timeout value, getattr_time, which allows any iteration of +orangefs_inode_getattr to know how long it has been since the inode was +updated. When the object is not new (new == 0) and the bypass flag is not +set (bypass == 0) orangefs_inode_getattr returns without updating the inode +if getattr_time has not timed out. Getattr_time is updated each time the +inode is updated. + +Creation of a new object (file, dir, sym-link) includes the evaluation of +its pathname, resulting in a negative directory entry for the object. +A new inode is allocated and associated with the dentry, turning it from +a negative dentry into a "productive full member of society". Orangefs +obtains the new inode from Linux with new_inode() and associates +the inode with the dentry by sending the pair back to Linux with +d_instantiate(). + +The evaluation of a pathname for an object resolves to its corresponding +dentry. If there is no corresponding dentry, one is created for it in +the dcache. Whenever a dentry is modified or verified Orangefs stores a +short timeout value in the dentry's d_time, and the dentry will be trusted +for that amount of time. Orangefs is a network filesystem, and objects +can potentially change out-of-band with any particular Orangefs kernel module +instance, so trusting a dentry is risky. The alternative to trusting +dentries is to always obtain the needed information from userspace - at +least a trip to the client-core, maybe to the servers. Obtaining information +from a dentry is cheap, obtaining it from userspace is relatively expensive, +hence the motivation to use the dentry when possible. + +The timeout values d_time and getattr_time are jiffy based, and the +code is designed to avoid the jiffy-wrap problem: + +"In general, if the clock may have wrapped around more than once, there +is no way to tell how much time has elapsed. However, if the times t1 +and t2 are known to be fairly close, we can reliably compute the +difference in a way that takes into account the possibility that the +clock may have wrapped between times." + + from course notes by instructor Andy Wang diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index d6259c786316..bcbf9710e4af 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -183,12 +183,10 @@ The copy_up operation essentially creates a new, identical file and moves it over to the old name. The new file may be on a different filesystem, so both st_dev and st_ino of the file may change. -Any open files referring to this inode will access the old data and -metadata. Similarly any file locks obtained before copy_up will not -apply to the copied up file. +Any open files referring to this inode will access the old data. -On a file opened with O_RDONLY fchmod(2), fchown(2), futimesat(2) and -fsetxattr(2) will fail with EROFS. +Any file locks (and leases) obtained before copy_up will not apply +to the copied up file. If a file with multiple hard links is copied up, then this will "break" the link. Changes will not be propagated to other names diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index a5fb89cac615..b1bd05ea66b2 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -585,3 +585,10 @@ in your dentry operations instead. in the instances. Rationale: !@#!@# security_d_instantiate() needs to be called before we attach dentry to inode and !@#!@##!@$!$#!@#$!@$!@$ smack ->d_instantiate() uses not just ->getxattr() but ->setxattr() as well. +-- +[mandatory] + ->d_compare() doesn't get parent as a separate argument anymore. If you + used it for finding the struct super_block involved, dentry->d_sb will + work just as well; if it's something more complicated, use dentry->d_parent. + Just be careful not to assume that fetching it more than once will yield + the same value - in RCU mode it could change under you. diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt index d9c11d25bf02..a85355cf85f4 100644 --- a/Documentation/filesystems/tmpfs.txt +++ b/Documentation/filesystems/tmpfs.txt @@ -98,7 +98,7 @@ A memory policy with a valid NodeList will be saved, as specified, for use at file creation time. When a task allocates a file in the file system, the mount option memory policy will be applied with a NodeList, if any, modified by the calling task's cpuset constraints -[See Documentation/cgroups/cpusets.txt] and any optional flags, listed +[See Documentation/cgroup-v1/cpusets.txt] and any optional flags, listed below. If the resulting NodeLists is the empty set, the effective memory policy for the file will revert to "default" policy. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 900360cbcdae..9ace359d6cc5 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -364,7 +364,6 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); - int (*dentry_open)(struct dentry *, struct file *, const struct cred *); }; Again, all methods are called without any locks being held, unless @@ -534,9 +533,7 @@ __sync_single_inode) to check if ->writepages has been successful in writing out the whole address_space. The Writeback tag is used by filemap*wait* and sync_page* functions, -via filemap_fdatawait_range, to wait for all writeback to -complete. While waiting ->sync_page (if defined) will be called on -each page that is found to require writeback. +via filemap_fdatawait_range, to wait for all writeback to complete. An address_space handler may attach extra information to a page, typically using the 'private' field in the 'struct page'. If such @@ -554,8 +551,8 @@ address_space has finer control of write sizes. The read process essentially only requires 'readpage'. The write process is more complicated and uses write_begin/write_end or -set_page_dirty to write data into the address_space, and writepage, -sync_page, and writepages to writeback data to storage. +set_page_dirty to write data into the address_space, and writepage +and writepages to writeback data to storage. Adding and removing pages to/from an address_space is protected by the inode's i_mutex. @@ -701,13 +698,6 @@ struct address_space_operations { but instead uses bmap to find out where the blocks in the file are and uses those addresses directly. - dentry_open: *WARNING: probably going away soon, do not use!* This is an - alternative to f_op->open(), the difference is that this method may open - a file not necessarily originating from the same filesystem as the one - i_op->open() was called on. It may be useful for stacking filesystems - which want to allow native I/O directly on underlying files. - - invalidatepage: If a page has PagePrivate set, then invalidatepage will be called when part or all of the page is to be removed from the address space. This generally corresponds to either a @@ -941,14 +931,17 @@ struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); - int (*d_compare)(const struct dentry *, const struct dentry *, + int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); + int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); + struct dentry *(*d_real)(struct dentry *, const struct inode *, + unsigned int); }; d_revalidate: called when the VFS needs to revalidate a dentry. This @@ -1014,6 +1007,8 @@ struct dentry_operations { always cache a reachable dentry. d_delete must be constant and idempotent. + d_init: called when a dentry is allocated + d_release: called when a dentry is really deallocated d_iput: called when a dentry loses its inode (just prior to its @@ -1033,6 +1028,14 @@ struct dentry_operations { at the end of the buffer, and returns a pointer to the first char. dynamic_dname() helper function is provided to take care of this. + Example : + + static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen) + { + return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]", + dentry->d_inode->i_ino); + } + d_automount: called when an automount dentry is to be traversed (optional). This should create a new VFS mount record and return the record to the caller. The caller is supplied with a path parameter giving the @@ -1071,13 +1074,23 @@ struct dentry_operations { This function is only used if DCACHE_MANAGE_TRANSIT is set on the dentry being transited from. -Example : + d_real: overlay/union type filesystems implement this method to return one of + the underlying dentries hidden by the overlay. It is used in three + different modes: -static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen) -{ - return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]", - dentry->d_inode->i_ino); -} + Called from open it may need to copy-up the file depending on the + supplied open flags. This mode is selected with a non-zero flags + argument. In this mode the d_real method can return an error. + + Called from file_dentry() it returns the real dentry matching the inode + argument. The real dentry may be from a lower layer already copied up, + but still referenced from the file. This mode is selected with a + non-NULL inode argument. This will always succeed. + + With NULL inode and zero flags the topmost real underlying dentry is + returned. This will always succeed. + + This method is never called with both non-NULL inode and non-zero flags. Each dentry has a pointer to its parent dentry, as well as a hash list of child dentries. Child dentries are basically like files in a |
