diff options
Diffstat (limited to 'Documentation/filesystems')
| -rw-r--r-- | Documentation/filesystems/9p.rst | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/automount-support.rst (renamed from Documentation/filesystems/automount-support.txt) | 23 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/backend-api.rst (renamed from Documentation/filesystems/caching/backend-api.txt) | 165 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/cachefiles.rst (renamed from Documentation/filesystems/caching/cachefiles.txt) | 139 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/fscache.rst | 565 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/fscache.txt | 448 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/index.rst | 14 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/netfs-api.rst (renamed from Documentation/filesystems/caching/netfs-api.txt) | 172 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/object.rst (renamed from Documentation/filesystems/caching/object.txt) | 43 | ||||
| -rw-r--r-- | Documentation/filesystems/caching/operations.rst (renamed from Documentation/filesystems/caching/operations.txt) | 45 | ||||
| -rw-r--r-- | Documentation/filesystems/cifs/cifsroot.rst (renamed from Documentation/filesystems/cifs/cifsroot.txt) | 56 | ||||
| -rw-r--r-- | Documentation/filesystems/coda.rst | 1670 | ||||
| -rw-r--r-- | Documentation/filesystems/coda.txt | 1676 | ||||
| -rw-r--r-- | Documentation/filesystems/configfs.rst (renamed from Documentation/filesystems/configfs/configfs.txt) | 131 | ||||
| -rw-r--r-- | Documentation/filesystems/dax.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/debugfs.rst | 5 | ||||
| -rw-r--r-- | Documentation/filesystems/devpts.rst | 36 | ||||
| -rw-r--r-- | Documentation/filesystems/devpts.txt | 26 | ||||
| -rw-r--r-- | Documentation/filesystems/dnotify.rst (renamed from Documentation/filesystems/dnotify.txt) | 13 | ||||
| -rw-r--r-- | Documentation/filesystems/efivarfs.rst | 17 | ||||
| -rw-r--r-- | Documentation/filesystems/fiemap.rst (renamed from Documentation/filesystems/fiemap.txt) | 135 | ||||
| -rw-r--r-- | Documentation/filesystems/files.rst (renamed from Documentation/filesystems/files.txt) | 15 | ||||
| -rw-r--r-- | Documentation/filesystems/fuse-io.rst (renamed from Documentation/filesystems/fuse-io.txt) | 6 | ||||
| -rw-r--r-- | Documentation/filesystems/index.rst | 23 | ||||
| -rw-r--r-- | Documentation/filesystems/locks.rst (renamed from Documentation/filesystems/locks.txt) | 14 | ||||
| -rw-r--r-- | Documentation/filesystems/mandatory-locking.rst (renamed from Documentation/filesystems/mandatory-locking.txt) | 25 | ||||
| -rw-r--r-- | Documentation/filesystems/mount_api.rst (renamed from Documentation/filesystems/mount_api.txt) | 329 | ||||
| -rw-r--r-- | Documentation/filesystems/orangefs.rst | 4 | ||||
| -rw-r--r-- | Documentation/filesystems/proc.rst | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/quota.rst (renamed from Documentation/filesystems/quota.txt) | 41 | ||||
| -rw-r--r-- | Documentation/filesystems/ramfs-rootfs-initramfs.rst | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/seq_file.rst (renamed from Documentation/filesystems/seq_file.txt) | 61 | ||||
| -rw-r--r-- | Documentation/filesystems/sharedsubtree.rst (renamed from Documentation/filesystems/sharedsubtree.txt) | 398 | ||||
| -rw-r--r-- | Documentation/filesystems/spufs/index.rst | 13 | ||||
| -rw-r--r-- | Documentation/filesystems/spufs/spu_create.rst | 131 | ||||
| -rw-r--r-- | Documentation/filesystems/spufs/spu_run.rst | 138 | ||||
| -rw-r--r-- | Documentation/filesystems/spufs/spufs.rst (renamed from Documentation/filesystems/spufs.txt) | 304 | ||||
| -rw-r--r-- | Documentation/filesystems/sysfs-pci.rst (renamed from Documentation/filesystems/sysfs-pci.txt) | 23 | ||||
| -rw-r--r-- | Documentation/filesystems/sysfs-tagging.rst (renamed from Documentation/filesystems/sysfs-tagging.txt) | 22 | ||||
| -rw-r--r-- | Documentation/filesystems/sysfs.rst | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/xfs-delayed-logging-design.rst (renamed from Documentation/filesystems/xfs-delayed-logging-design.txt) | 65 | ||||
| -rw-r--r-- | Documentation/filesystems/xfs-self-describing-metadata.rst (renamed from Documentation/filesystems/xfs-self-describing-metadata.txt) | 190 |
42 files changed, 3821 insertions, 3370 deletions
diff --git a/Documentation/filesystems/9p.rst b/Documentation/filesystems/9p.rst index 671fef39a802..2995279ddc24 100644 --- a/Documentation/filesystems/9p.rst +++ b/Documentation/filesystems/9p.rst @@ -192,4 +192,4 @@ For more information on the Plan 9 Operating System check out http://plan9.bell-labs.com/plan9 For information on Plan 9 from User Space (Plan 9 applications and libraries -ported to Linux/BSD/OSX/etc) check out http://swtch.com/plan9 +ported to Linux/BSD/OSX/etc) check out https://9fans.github.io/plan9port/ diff --git a/Documentation/filesystems/automount-support.txt b/Documentation/filesystems/automount-support.rst index 7d9f82607562..430f0b40796b 100644 --- a/Documentation/filesystems/automount-support.txt +++ b/Documentation/filesystems/automount-support.rst @@ -1,3 +1,10 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +Automount Support +================= + + Support is available for filesystems that wish to do automounting support (such as kAFS which can be found in fs/afs/ and NFS in fs/nfs/). This facility includes allowing in-kernel mounts to be @@ -5,13 +12,12 @@ performed and mountpoint degradation to be requested. The latter can also be requested by userspace. -====================== -IN-KERNEL AUTOMOUNTING +In-Kernel Automounting ====================== See section "Mount Traps" of Documentation/filesystems/autofs.rst -Then from userspace, you can just do something like: +Then from userspace, you can just do something like:: [root@andromeda root]# mount -t afs \#root.afs. /afs [root@andromeda root]# ls /afs @@ -21,7 +27,7 @@ Then from userspace, you can just do something like: [root@andromeda root]# ls /afs/cambridge/afsdoc/ ChangeLog html LICENSE pdf RELNOTES-1.2.2 -And then if you look in the mountpoint catalogue, you'll see something like: +And then if you look in the mountpoint catalogue, you'll see something like:: [root@andromeda root]# cat /proc/mounts ... @@ -30,8 +36,7 @@ And then if you look in the mountpoint catalogue, you'll see something like: #afsdoc. /afs/cambridge.redhat.com/afsdoc afs rw 0 0 -=========================== -AUTOMATIC MOUNTPOINT EXPIRY +Automatic Mountpoint Expiry =========================== Automatic expiration of mountpoints is easy, provided you've mounted the @@ -43,7 +48,8 @@ To do expiration, you need to follow these steps: hung. (2) When a new mountpoint is created in the ->d_automount method, add - the mnt to the list using mnt_set_expiry() + the mnt to the list using mnt_set_expiry():: + mnt_set_expiry(newmnt, &afs_vfsmounts); (3) When you want mountpoints to be expired, call mark_mounts_for_expiry() @@ -70,8 +76,7 @@ and the copies of those that are on an expiration list will be added to the same expiration list. -======================= -USERSPACE DRIVEN EXPIRY +Userspace Driven Expiry ======================= As an alternative, it is possible for userspace to request expiry of any diff --git a/Documentation/filesystems/caching/backend-api.txt b/Documentation/filesystems/caching/backend-api.rst index c418280c915f..19fbf6b9aa36 100644 --- a/Documentation/filesystems/caching/backend-api.txt +++ b/Documentation/filesystems/caching/backend-api.rst @@ -1,6 +1,8 @@ - ========================== - FS-CACHE CACHE BACKEND API - ========================== +.. SPDX-License-Identifier: GPL-2.0 + +========================== +FS-Cache Cache backend API +========================== The FS-Cache system provides an API by which actual caches can be supplied to FS-Cache for it to then serve out to network filesystems and other interested @@ -9,15 +11,14 @@ parties. This API is declared in <linux/fscache-cache.h>. -==================================== -INITIALISING AND REGISTERING A CACHE +Initialising and Registering a Cache ==================================== To start off, a cache definition must be initialised and registered for each cache the backend wants to make available. For instance, CacheFS does this in the fill_super() operation on mounting. -The cache definition (struct fscache_cache) should be initialised by calling: +The cache definition (struct fscache_cache) should be initialised by calling:: void fscache_init_cache(struct fscache_cache *cache, struct fscache_cache_ops *ops, @@ -26,17 +27,17 @@ The cache definition (struct fscache_cache) should be initialised by calling: Where: - (*) "cache" is a pointer to the cache definition; + * "cache" is a pointer to the cache definition; - (*) "ops" is a pointer to the table of operations that the backend supports on + * "ops" is a pointer to the table of operations that the backend supports on this cache; and - (*) "idfmt" is a format and printf-style arguments for constructing a label + * "idfmt" is a format and printf-style arguments for constructing a label for the cache. The cache should then be registered with FS-Cache by passing a pointer to the -previously initialised cache definition to: +previously initialised cache definition to:: int fscache_add_cache(struct fscache_cache *cache, struct fscache_object *fsdef, @@ -44,12 +45,12 @@ previously initialised cache definition to: Two extra arguments should also be supplied: - (*) "fsdef" which should point to the object representation for the FS-Cache + * "fsdef" which should point to the object representation for the FS-Cache master index in this cache. Netfs primary index entries will be created here. FS-Cache keeps the caller's reference to the index object if successful and will release it upon withdrawal of the cache. - (*) "tagname" which, if given, should be a text string naming this cache. If + * "tagname" which, if given, should be a text string naming this cache. If this is NULL, the identifier will be used instead. For CacheFS, the identifier is set to name the underlying block device and the tag can be supplied by mount. @@ -58,20 +59,18 @@ This function may return -ENOMEM if it ran out of memory or -EEXIST if the tag is already in use. 0 will be returned on success. -===================== -UNREGISTERING A CACHE +Unregistering a Cache ===================== A cache can be withdrawn from the system by calling this function with a -pointer to the cache definition: +pointer to the cache definition:: void fscache_withdraw_cache(struct fscache_cache *cache); In CacheFS's case, this is called by put_super(). -======== -SECURITY +Security ======== The cache methods are executed one of two contexts: @@ -89,8 +88,7 @@ be masqueraded for the duration of the cache driver's access to the cache. This is left to the cache to handle; FS-Cache makes no effort in this regard. -=================================== -CONTROL AND STATISTICS PRESENTATION +Control and Statistics Presentation =================================== The cache may present data to the outside world through FS-Cache's interfaces @@ -101,11 +99,10 @@ is enabled. This is accessible through the kobject struct fscache_cache::kobj and is for use by the cache as it sees fit. -======================== -RELEVANT DATA STRUCTURES +Relevant Data Structures ======================== - (*) Index/Data file FS-Cache representation cookie: + * Index/Data file FS-Cache representation cookie:: struct fscache_cookie { struct fscache_object_def *def; @@ -121,7 +118,7 @@ RELEVANT DATA STRUCTURES cache operations. - (*) In-cache object representation: + * In-cache object representation:: struct fscache_object { int debug_id; @@ -150,7 +147,7 @@ RELEVANT DATA STRUCTURES initialised by calling fscache_object_init(object). - (*) FS-Cache operation record: + * FS-Cache operation record:: struct fscache_operation { atomic_t usage; @@ -173,7 +170,7 @@ RELEVANT DATA STRUCTURES an operation needs more processing time, it should be enqueued again. - (*) FS-Cache retrieval operation record: + * FS-Cache retrieval operation record:: struct fscache_retrieval { struct fscache_operation op; @@ -198,7 +195,7 @@ RELEVANT DATA STRUCTURES it sees fit. - (*) FS-Cache storage operation record: + * FS-Cache storage operation record:: struct fscache_storage { struct fscache_operation op; @@ -212,16 +209,17 @@ RELEVANT DATA STRUCTURES storage. -================ -CACHE OPERATIONS +Cache Operations ================ The cache backend provides FS-Cache with a table of operations that can be performed on the denizens of the cache. These are held in a structure of type: - struct fscache_cache_ops + :: + + struct fscache_cache_ops - (*) Name of cache provider [mandatory]: + * Name of cache provider [mandatory]:: const char *name @@ -229,7 +227,7 @@ performed on the denizens of the cache. These are held in a structure of type: the backend. - (*) Allocate a new object [mandatory]: + * Allocate a new object [mandatory]:: struct fscache_object *(*alloc_object)(struct fscache_cache *cache, struct fscache_cookie *cookie) @@ -244,7 +242,7 @@ performed on the denizens of the cache. These are held in a structure of type: form once lookup is complete or aborted. - (*) Look up and create object [mandatory]: + * Look up and create object [mandatory]:: void (*lookup_object)(struct fscache_object *object) @@ -263,7 +261,7 @@ performed on the denizens of the cache. These are held in a structure of type: to abort the lookup of that object. - (*) Release lookup data [mandatory]: + * Release lookup data [mandatory]:: void (*lookup_complete)(struct fscache_object *object) @@ -271,7 +269,7 @@ performed on the denizens of the cache. These are held in a structure of type: using to perform a lookup. - (*) Increment object refcount [mandatory]: + * Increment object refcount [mandatory]:: struct fscache_object *(*grab_object)(struct fscache_object *object) @@ -280,7 +278,7 @@ performed on the denizens of the cache. These are held in a structure of type: It should return the object pointer if successful. - (*) Lock/Unlock object [mandatory]: + * Lock/Unlock object [mandatory]:: void (*lock_object)(struct fscache_object *object) void (*unlock_object)(struct fscache_object *object) @@ -289,7 +287,7 @@ performed on the denizens of the cache. These are held in a structure of type: to schedule with the lock held, so a spinlock isn't sufficient. - (*) Pin/Unpin object [optional]: + * Pin/Unpin object [optional]:: int (*pin_object)(struct fscache_object *object) void (*unpin_object)(struct fscache_object *object) @@ -299,7 +297,7 @@ performed on the denizens of the cache. These are held in a structure of type: enough space in the cache to permit this. - (*) Check coherency state of an object [mandatory]: + * Check coherency state of an object [mandatory]:: int (*check_consistency)(struct fscache_object *object) @@ -308,7 +306,7 @@ performed on the denizens of the cache. These are held in a structure of type: if they're consistent and -ESTALE otherwise. -ENOMEM and -ERESTARTSYS may also be returned. - (*) Update object [mandatory]: + * Update object [mandatory]:: int (*update_object)(struct fscache_object *object) @@ -317,7 +315,7 @@ performed on the denizens of the cache. These are held in a structure of type: obtained by calling object->cookie->def->get_aux()/get_attr(). - (*) Invalidate data object [mandatory]: + * Invalidate data object [mandatory]:: int (*invalidate_object)(struct fscache_operation *op) @@ -329,7 +327,7 @@ performed on the denizens of the cache. These are held in a structure of type: fscache_op_complete() must be called on op before returning. - (*) Discard object [mandatory]: + * Discard object [mandatory]:: void (*drop_object)(struct fscache_object *object) @@ -341,7 +339,7 @@ performed on the denizens of the cache. These are held in a structure of type: caller. The caller will invoke the put_object() method as appropriate. - (*) Release object reference [mandatory]: + * Release object reference [mandatory]:: void (*put_object)(struct fscache_object *object) @@ -349,7 +347,7 @@ performed on the denizens of the cache. These are held in a structure of type: be freed when all the references to it are released. - (*) Synchronise a cache [mandatory]: + * Synchronise a cache [mandatory]:: void (*sync)(struct fscache_cache *cache) @@ -357,7 +355,7 @@ performed on the denizens of the cache. These are held in a structure of type: device. - (*) Dissociate a cache [mandatory]: + * Dissociate a cache [mandatory]:: void (*dissociate_pages)(struct fscache_cache *cache) @@ -365,7 +363,7 @@ performed on the denizens of the cache. These are held in a structure of type: cache withdrawal. - (*) Notification that the attributes on a netfs file changed [mandatory]: + * Notification that the attributes on a netfs file changed [mandatory]:: int (*attr_changed)(struct fscache_object *object); @@ -386,7 +384,7 @@ performed on the denizens of the cache. These are held in a structure of type: execution of this operation. - (*) Reserve cache space for an object's data [optional]: + * Reserve cache space for an object's data [optional]:: int (*reserve_space)(struct fscache_object *object, loff_t size); @@ -404,7 +402,7 @@ performed on the denizens of the cache. These are held in a structure of type: size if larger than that already. - (*) Request page be read from cache [mandatory]: + * Request page be read from cache [mandatory]:: int (*read_or_alloc_page)(struct fscache_retrieval *op, struct page *page, @@ -446,7 +444,7 @@ performed on the denizens of the cache. These are held in a structure of type: with. This will complete the operation when all pages are dealt with. - (*) Request pages be read from cache [mandatory]: + * Request pages be read from cache [mandatory]:: int (*read_or_alloc_pages)(struct fscache_retrieval *op, struct list_head *pages, @@ -457,7 +455,7 @@ performed on the denizens of the cache. These are held in a structure of type: of pages instead of one page. Any pages on which a read operation is started must be added to the page cache for the specified mapping and also to the LRU. Such pages must also be removed from the pages list and - *nr_pages decremented per page. + ``*nr_pages`` decremented per page. If there was an error such as -ENOMEM, then that should be returned; else if one or more pages couldn't be read or allocated, then -ENOBUFS should @@ -466,7 +464,7 @@ performed on the denizens of the cache. These are held in a structure of type: returned. - (*) Request page be allocated in the cache [mandatory]: + * Request page be allocated in the cache [mandatory]:: int (*allocate_page)(struct fscache_retrieval *op, struct page *page, @@ -482,7 +480,7 @@ performed on the denizens of the cache. These are held in a structure of type: allocated, then the netfs page should be marked and 0 returned. - (*) Request pages be allocated in the cache [mandatory]: + * Request pages be allocated in the cache [mandatory]:: int (*allocate_pages)(struct fscache_retrieval *op, struct list_head *pages, @@ -493,7 +491,7 @@ performed on the denizens of the cache. These are held in a structure of type: nr_pages should be treated as for the read_or_alloc_pages() method. - (*) Request page be written to cache [mandatory]: + * Request page be written to cache [mandatory]:: int (*write_page)(struct fscache_storage *op, struct page *page); @@ -514,7 +512,7 @@ performed on the denizens of the cache. These are held in a structure of type: appropriately. - (*) Discard retained per-page metadata [mandatory]: + * Discard retained per-page metadata [mandatory]:: void (*uncache_page)(struct fscache_object *object, struct page *page) @@ -523,13 +521,12 @@ performed on the denizens of the cache. These are held in a structure of type: maintains for this page. -================== -FS-CACHE UTILITIES +FS-Cache Utilities ================== FS-Cache provides some utilities that a cache backend may make use of: - (*) Note occurrence of an I/O error in a cache: + * Note occurrence of an I/O error in a cache:: void fscache_io_error(struct fscache_cache *cache) @@ -541,7 +538,7 @@ FS-Cache provides some utilities that a cache backend may make use of: This does not actually withdraw the cache. That must be done separately. - (*) Invoke the retrieval I/O completion function: + * Invoke the retrieval I/O completion function:: void fscache_end_io(struct fscache_retrieval *op, struct page *page, int error); @@ -550,8 +547,8 @@ FS-Cache provides some utilities that a cache backend may make use of: error value should be 0 if successful and an error otherwise. - (*) Record that one or more pages being retrieved or allocated have been dealt - with: + * Record that one or more pages being retrieved or allocated have been dealt + with:: void fscache_retrieval_complete(struct fscache_retrieval *op, int n_pages); @@ -562,7 +559,7 @@ FS-Cache provides some utilities that a cache backend may make use of: completed. - (*) Record operation completion: + * Record operation completion:: void fscache_op_complete(struct fscache_operation *op); @@ -571,7 +568,7 @@ FS-Cache provides some utilities that a cache backend may make use of: one or more pending operations to start running. - (*) Set highest store limit: + * Set highest store limit:: void fscache_set_store_limit(struct fscache_object *object, loff_t i_size); @@ -581,7 +578,7 @@ FS-Cache provides some utilities that a cache backend may make use of: rejected by fscache_read_alloc_page() and co with -ENOBUFS. - (*) Mark pages as being cached: + * Mark pages as being cached:: void fscache_mark_pages_cached(struct fscache_retrieval *op, struct pagevec *pagevec); @@ -590,7 +587,7 @@ FS-Cache provides some utilities that a cache backend may make use of: the netfs must call fscache_uncache_page() to unmark the pages. - (*) Perform coherency check on an object: + * Perform coherency check on an object:: enum fscache_checkaux fscache_check_aux(struct fscache_object *object, const void *data, @@ -603,29 +600,26 @@ FS-Cache provides some utilities that a cache backend may make use of: One of three values will be returned: - (*) FSCACHE_CHECKAUX_OKAY - + FSCACHE_CHECKAUX_OKAY The coherency data indicates the object is valid as is. - (*) FSCACHE_CHECKAUX_NEEDS_UPDATE - + FSCACHE_CHECKAUX_NEEDS_UPDATE The coherency data needs updating, but otherwise the object is valid. - (*) FSCACHE_CHECKAUX_OBSOLETE - + FSCACHE_CHECKAUX_OBSOLETE The coherency data indicates that the object is obsolete and should be discarded. - (*) Initialise a freshly allocated object: + * Initialise a freshly allocated object:: void fscache_object_init(struct fscache_object *object); This initialises all the fields in an object representation. - (*) Indicate the destruction of an object: + * Indicate the destruction of an object:: void fscache_object_destroyed(struct fscache_cache *cache); @@ -635,7 +629,7 @@ FS-Cache provides some utilities that a cache backend may make use of: all the objects. - (*) Indicate negative lookup on an object: + * Indicate negative lookup on an object:: void fscache_object_lookup_negative(struct fscache_object *object); @@ -650,7 +644,7 @@ FS-Cache provides some utilities that a cache backend may make use of: significant - all subsequent calls are ignored. - (*) Indicate an object has been obtained: + * Indicate an object has been obtained:: void fscache_obtained_object(struct fscache_object *object); @@ -667,7 +661,7 @@ FS-Cache provides some utilities that a cache backend may make use of: (2) that writes may now proceed against this object. - (*) Indicate that object lookup failed: + * Indicate that object lookup failed:: void fscache_object_lookup_error(struct fscache_object *object); @@ -676,7 +670,7 @@ FS-Cache provides some utilities that a cache backend may make use of: as possible. - (*) Indicate that a stale object was found and discarded: + * Indicate that a stale object was found and discarded:: void fscache_object_retrying_stale(struct fscache_object *object); @@ -685,7 +679,7 @@ FS-Cache provides some utilities that a cache backend may make use of: discarded from the cache and the lookup will be performed again. - (*) Indicate that the caching backend killed an object: + * Indicate that the caching backend killed an object:: void fscache_object_mark_killed(struct fscache_object *object, enum fscache_why_object_killed why); @@ -693,13 +687,20 @@ FS-Cache provides some utilities that a cache backend may make use of: This is called to indicate that the cache backend preemptively killed an object. The why parameter should be set to indicate the reason: - FSCACHE_OBJECT_IS_STALE - the object was stale and needs discarding. - FSCACHE_OBJECT_NO_SPACE - there was insufficient cache space - FSCACHE_OBJECT_WAS_RETIRED - the object was retired when relinquished. - FSCACHE_OBJECT_WAS_CULLED - the object was culled to make space. + FSCACHE_OBJECT_IS_STALE + - the object was stale and needs discarding. + + FSCACHE_OBJECT_NO_SPACE + - there was insufficient cache space + + FSCACHE_OBJECT_WAS_RETIRED + - the object was retired when relinquished. + + FSCACHE_OBJECT_WAS_CULLED + - the object was culled to make space. - (*) Get and release references on a retrieval record: + * Get and release references on a retrieval record:: void fscache_get_retrieval(struct fscache_retrieval *op); void fscache_put_retrieval(struct fscache_retrieval *op); @@ -708,7 +709,7 @@ FS-Cache provides some utilities that a cache backend may make use of: asynchronous data retrieval and block allocation. - (*) Enqueue a retrieval record for processing. + * Enqueue a retrieval record for processing:: void fscache_enqueue_retrieval(struct fscache_retrieval *op); @@ -718,7 +719,7 @@ FS-Cache provides some utilities that a cache backend may make use of: within the callback function. - (*) List of object state names: + * List of object state names:: const char *fscache_object_states[]; diff --git a/Documentation/filesystems/caching/cachefiles.txt b/Documentation/filesystems/caching/cachefiles.rst index 28aefcbb1442..65d3db476765 100644 --- a/Documentation/filesystems/caching/cachefiles.txt +++ b/Documentation/filesystems/caching/cachefiles.rst @@ -1,8 +1,10 @@ - =============================================== - CacheFiles: CACHE ON ALREADY MOUNTED FILESYSTEM - =============================================== +.. SPDX-License-Identifier: GPL-2.0 -Contents: +=============================================== +CacheFiles: CACHE ON ALREADY MOUNTED FILESYSTEM +=============================================== + +.. Contents: (*) Overview. @@ -27,8 +29,8 @@ Contents: (*) Debugging. -======== -OVERVIEW + +Overview ======== CacheFiles is a caching backend that's meant to use as a cache a directory on @@ -58,8 +60,8 @@ spare space and automatically contract when the set of data requires more space. -============ -REQUIREMENTS + +Requirements ============ The use of CacheFiles and its daemon requires the following features to be @@ -79,84 +81,70 @@ It is strongly recommended that the "dir_index" option is enabled on Ext3 filesystems being used as a cache. -============= -CONFIGURATION +Configuration ============= The cache is configured by a script in /etc/cachefilesd.conf. These commands set up cache ready for use. The following script commands are available: - (*) brun <N>% - (*) bcull <N>% - (*) bstop <N>% - (*) frun <N>% - (*) fcull <N>% - (*) fstop <N>% - + brun <N>%, bcull <N>%, bstop <N>%, frun <N>%, fcull <N>%, fstop <N>% Configure the culling limits. Optional. See the section on culling The defaults are 7% (run), 5% (cull) and 1% (stop) respectively. The commands beginning with a 'b' are file space (block) limits, those beginning with an 'f' are file count limits. - (*) dir <path> - + dir <path> Specify the directory containing the root of the cache. Mandatory. - (*) tag <name> - + tag <name> Specify a tag to FS-Cache to use in distinguishing multiple caches. Optional. The default is "CacheFiles". - (*) debug <mask> - + debug <mask> Specify a numeric bitmask to control debugging in the kernel module. Optional. The default is zero (all off). The following values can be OR'd into the mask to collect various information: + == ================================================= 1 Turn on trace of function entry (_enter() macros) 2 Turn on trace of function exit (_leave() macros) 4 Turn on trace of internal debug points (_debug()) + == ================================================= - This mask can also be set through sysfs, eg: + This mask can also be set through sysfs, eg:: echo 5 >/sys/modules/cachefiles/parameters/debug -================== -STARTING THE CACHE +Starting the Cache ================== The cache is started by running the daemon. The daemon opens the cache device, configures the cache and tells it to begin caching. At that point the cache binds to fscache and the cache becomes live. -The daemon is run as follows: +The daemon is run as follows:: /sbin/cachefilesd [-d]* [-s] [-n] [-f <configfile>] The flags are: - (*) -d - + ``-d`` Increase the debugging level. This can be specified multiple times and is cumulative with itself. - (*) -s - + ``-s`` Send messages to stderr instead of syslog. - (*) -n - + ``-n`` Don't daemonise and go into background. - (*) -f <configfile> - + ``-f <configfile>`` Use an alternative configuration file rather than the default one. -=============== -THINGS TO AVOID +Things to Avoid =============== Do not mount other things within the cache as this will cause problems. The @@ -179,8 +167,7 @@ Do not chmod files in the cache. The module creates things with minimal permissions to prevent random users being able to access them directly. -============= -CACHE CULLING +Cache Culling ============= The cache may need culling occasionally to make space. This involves @@ -192,27 +179,21 @@ Cache culling is done on the basis of the percentage of blocks and the percentage of files available in the underlying filesystem. There are six "limits": - (*) brun - (*) frun - + brun, frun If the amount of free space and the number of available files in the cache rises above both these limits, then culling is turned off. - (*) bcull - (*) fcull - + bcull, fcull If the amount of available space or the number of available files in the cache falls below either of these limits, then culling is started. - (*) bstop - (*) fstop - + bstop, fstop If the amount of available space or the number of available files in the cache falls below either of these limits, then no further allocation of disk space or files is permitted until culling has raised things above these limits again. -These must be configured thusly: +These must be configured thusly:: 0 <= bstop < bcull < brun < 100 0 <= fstop < fcull < frun < 100 @@ -226,16 +207,14 @@ started as soon as space is made in the table. Objects will be skipped if their atimes have changed or if the kernel module says it is still using them. -=============== -CACHE STRUCTURE +Cache Structure =============== The CacheFiles module will create two directories in the directory it was given: - (*) cache/ - - (*) graveyard/ + * cache/ + * graveyard/ The active cache objects all reside in the first directory. The CacheFiles kernel module moves any retired or culled objects that it can't simply unlink @@ -261,10 +240,10 @@ If an object has children, then it will be represented as a directory. Immediately in the representative directory are a collection of directories named for hash values of the child object keys with an '@' prepended. Into this directory, if possible, will be placed the representations of the child -objects: +objects:: - INDEX INDEX INDEX DATA FILES - ========= ========== ================================= ================ + /INDEX /INDEX /INDEX /DATA FILES + /=========/==========/=================================/================ cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400 cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...DB1ry cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...N22ry @@ -275,7 +254,7 @@ If the key is so long that it exceeds NAME_MAX with the decorations added on to it, then it will be cut into pieces, the first few of which will be used to make a nest of directories, and the last one of which will be the objects inside the last directory. The names of the intermediate directories will have -'+' prepended: +'+' prepended:: J1223/@23/+xy...z/+kl...m/Epqr @@ -288,11 +267,13 @@ To handle this, CacheFiles will use a suitably printable filename directly and "base-64" encode ones that aren't directly suitable. The two versions of object filenames indicate the encoding: + =============== =============== =============== OBJECT TYPE PRINTABLE ENCODED =============== =============== =============== Index "I..." "J..." Data "D..." "E..." Special "S..." "T..." + =============== =============== =============== Intermediate directories are always "@" or "+" as appropriate. @@ -307,8 +288,7 @@ Note that CacheFiles will erase from the cache any file it doesn't recognise or any file of an incorrect type (such as a FIFO file or a device file). -========================== -SECURITY MODEL AND SELINUX +Security Model and SELinux ========================== CacheFiles is implemented to deal properly with the LSM security features of @@ -331,26 +311,26 @@ When the CacheFiles module is asked to bind to its cache, it: (1) Finds the security label attached to the root cache directory and uses that as the security label with which it will create files. By default, - this is: + this is:: cachefiles_var_t (2) Finds the security label of the process which issued the bind request - (presumed to be the cachefilesd daemon), which by default will be: + (presumed to be the cachefilesd daemon), which by default will be:: cachefilesd_t and asks LSM to supply a security ID as which it should act given the - daemon's label. By default, this will be: + daemon's label. By default, this will be:: cachefiles_kernel_t SELinux transitions the daemon's security ID to the module's security ID - based on a rule of this form in the policy. + based on a rule of this form in the policy:: type_transition <daemon's-ID> kernel_t : process <module's-ID>; - For instance: + For instance:: type_transition cachefilesd_t kernel_t : process cachefiles_kernel_t; @@ -370,7 +350,7 @@ There are policy source files available in: http://people.redhat.com/~dhowells/fscache/cachefilesd-0.8.tar.bz2 -and later versions. In that tarball, see the files: +and later versions. In that tarball, see the files:: cachefilesd.te cachefilesd.fc @@ -379,7 +359,7 @@ and later versions. In that tarball, see the files: They are built and installed directly by the RPM. If a non-RPM based system is being used, then copy the above files to their own -directory and run: +directory and run:: make -f /usr/share/selinux/devel/Makefile semodule -i cachefilesd.pp @@ -394,7 +374,7 @@ an auxiliary policy must be installed to label the alternate location of the cache. For instructions on how to add an auxiliary policy to enable the cache to be -located elsewhere when SELinux is in enforcing mode, please see: +located elsewhere when SELinux is in enforcing mode, please see:: /usr/share/doc/cachefilesd-*/move-cache.txt @@ -402,8 +382,7 @@ When the cachefilesd rpm is installed; alternatively, the document can be found in the sources. -================== -A NOTE ON SECURITY +A Note on Security ================== CacheFiles makes use of the split security in the task_struct. It allocates @@ -445,17 +424,18 @@ for CacheFiles to run in a context of a specific security label, or to create files and directories with another security label. -======================= -STATISTICAL INFORMATION +Statistical Information ======================= -If FS-Cache is compiled with the following option enabled: +If FS-Cache is compiled with the following option enabled:: CONFIG_CACHEFILES_HISTOGRAM=y then it will gather certain statistics and display them through a proc file. - (*) /proc/fs/cachefiles/histogram + /proc/fs/cachefiles/histogram + + :: cat /proc/fs/cachefiles/histogram JIFS SECS LOOKUPS MKDIRS CREATES @@ -465,36 +445,39 @@ then it will gather certain statistics and display them through a proc file. between 0 jiffies and HZ-1 jiffies a variety of tasks took to run. The columns are as follows: + ======= ======================================================= COLUMN TIME MEASUREMENT ======= ======================================================= LOOKUPS Length of time to perform a lookup on the backing fs MKDIRS Length of time to perform a mkdir on the backing fs CREATES Length of time to perform a create on the backing fs + ======= ======================================================= Each row shows the number of events that took a particular range of times. Each step is 1 jiffy in size. The JIFS column indicates the particular jiffy range covered, and the SECS field the equivalent number of seconds. -========= -DEBUGGING +Debugging ========= If CONFIG_CACHEFILES_DEBUG is enabled, the CacheFiles facility can have runtime -debugging enabled by adjusting the value in: +debugging enabled by adjusting the value in:: /sys/module/cachefiles/parameters/debug This is a bitmask of debugging streams to enable: + ======= ======= =============================== ======================= BIT VALUE STREAM POINT ======= ======= =============================== ======================= 0 1 General Function entry trace 1 2 Function exit trace 2 4 General + ======= ======= =============================== ======================= The appropriate set of values should be OR'd together and the result written to -the control file. For example: +the control file. For example:: echo $((1|4|8)) >/sys/module/cachefiles/parameters/debug diff --git a/Documentation/filesystems/caching/fscache.rst b/Documentation/filesystems/caching/fscache.rst new file mode 100644 index 000000000000..70de86922b6a --- /dev/null +++ b/Documentation/filesystems/caching/fscache.rst @@ -0,0 +1,565 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================== +General Filesystem Caching +========================== + +Overview +======== + +This facility is a general purpose cache for network filesystems, though it +could be used for caching other things such as ISO9660 filesystems too. + +FS-Cache mediates between cache backends (such as CacheFS) and network +filesystems:: + + +---------+ + | | +--------------+ + | NFS |--+ | | + | | | +-->| CacheFS | + +---------+ | +----------+ | | /dev/hda5 | + | | | | +--------------+ + +---------+ +-->| | | + | | | |--+ + | AFS |----->| FS-Cache | + | | | |--+ + +---------+ +-->| | | + | | | | +--------------+ + +---------+ | +----------+ | | | + | | | +-->| CacheFiles | + | ISOFS |--+ | /var/cache | + | | +--------------+ + +---------+ + +Or to look at it another way, FS-Cache is a module that provides a caching +facility to a network filesystem such that the cache is transparent to the +user:: + + +---------+ + | | + | Server | + | | + +---------+ + | NETWORK + ~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + | + | +----------+ + V | | + +---------+ | | + | | | | + | NFS |----->| FS-Cache | + | | | |--+ + +---------+ | | | +--------------+ +--------------+ + | | | | | | | | + V +----------+ +-->| CacheFiles |-->| Ext3 | + +---------+ | /var/cache | | /dev/sda6 | + | | +--------------+ +--------------+ + | VFS | ^ ^ + | | | | + +---------+ +--------------+ | + | KERNEL SPACE | | + ~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~|~~~~~~|~~~~ + | USER SPACE | | + V | | + +---------+ +--------------+ + | | | | + | Process | | cachefilesd | + | | | | + +---------+ +--------------+ + + +FS-Cache does not follow the idea of completely loading every netfs file +opened in its entirety into a cache before permitting it to be accessed and +then serving the pages out of that cache rather than the netfs inode because: + + (1) It must be practical to operate without a cache. + + (2) The size of any accessible file must not be limited to the size of the + cache. + + (3) The combined size of all opened files (this includes mapped libraries) + must not be limited to the size of the cache. + + (4) The user should not be forced to download an entire file just to do a + one-off access of a small portion of it (such as might be done with the + "file" program). + +It instead serves the cache out in PAGE_SIZE chunks as and when requested by +the netfs('s) using it. + + +FS-Cache provides the following facilities: + + (1) More than one cache can be used at once. Caches can be selected + explicitly by use of tags. + + (2) Caches can be added / removed at any time. + + (3) The netfs is provided with an interface that allows either party to + withdraw caching facilities from a file (required for (2)). + + (4) The interface to the netfs returns as few errors as possible, preferring + rather to let the netfs remain oblivious. + + (5) Cookies are used to represent indices, files and other objects to the + netfs. The simplest cookie is just a NULL pointer - indicating nothing + cached there. + + (6) The netfs is allowed to propose - dynamically - any index hierarchy it + desires, though it must be aware that the index search function is + recursive, stack space is limited, and indices can only be children of + indices. + + (7) Data I/O is done direct to and from the netfs's pages. The netfs + indicates that page A is at index B of the data-file represented by cookie + C, and that it should be read or written. The cache backend may or may + not start I/O on that page, but if it does, a netfs callback will be + invoked to indicate completion. The I/O may be either synchronous or + asynchronous. + + (8) Cookies can be "retired" upon release. At this point FS-Cache will mark + them as obsolete and the index hierarchy rooted at that point will get + recycled. + + (9) The netfs provides a "match" function for index searches. In addition to + saying whether a match was made or not, this can also specify that an + entry should be updated or deleted. + +(10) As much as possible is done asynchronously. + + +FS-Cache maintains a virtual indexing tree in which all indices, files, objects +and pages are kept. Bits of this tree may actually reside in one or more +caches:: + + FSDEF + | + +------------------------------------+ + | | + NFS AFS + | | + +--------------------------+ +-----------+ + | | | | + homedir mirror afs.org redhat.com + | | | + +------------+ +---------------+ +----------+ + | | | | | | + 00001 00002 00007 00125 vol00001 vol00002 + | | | | | + +---+---+ +-----+ +---+ +------+------+ +-----+----+ + | | | | | | | | | | | | | + PG0 PG1 PG2 PG0 XATTR PG0 PG1 DIRENT DIRENT DIRENT R/W R/O Bak + | | + PG0 +-------+ + | | + 00001 00003 + | + +---+---+ + | | | + PG0 PG1 PG2 + +In the example above, you can see two netfs's being backed: NFS and AFS. These +have different index hierarchies: + + * The NFS primary index contains per-server indices. Each server index is + indexed by NFS file handles to get data file objects. Each data file + objects can have an array of pages, but may also have further child + objects, such as extended attributes and directory entries. Extended + attribute objects themselves have page-array contents. + + * The AFS primary index contains per-cell indices. Each cell index contains + per-logical-volume indices. Each of volume index contains up to three + indices for the read-write, read-only and backup mirrors of those volumes. + Each of these contains vnode data file objects, each of which contains an + array of pages. + +The very top index is the FS-Cache master index in which individual netfs's +have entries. + +Any index object may reside in more than one cache, provided it only has index +children. Any index with non-index object children will be assumed to only +reside in one cache. + + +The netfs API to FS-Cache can be found in: + + Documentation/filesystems/caching/netfs-api.rst + +The cache backend API to FS-Cache can be found in: + + Documentation/filesystems/caching/backend-api.rst + +A description of the internal representations and object state machine can be +found in: + + Documentation/filesystems/caching/object.rst + + +Statistical Information +======================= + +If FS-Cache is compiled with the following options enabled:: + + CONFIG_FSCACHE_STATS=y + CONFIG_FSCACHE_HISTOGRAM=y + +then it will gather certain statistics and display them through a number of +proc files. + +/proc/fs/fscache/stats +---------------------- + + This shows counts of a number of events that can happen in FS-Cache: + ++--------------+-------+-------------------------------------------------------+ +|CLASS |EVENT |MEANING | ++==============+=======+=======================================================+ +|Cookies |idx=N |Number of index cookies allocated | ++ +-------+-------------------------------------------------------+ +| |dat=N |Number of data storage cookies allocated | ++ +-------+-------------------------------------------------------+ +| |spc=N |Number of special cookies allocated | ++--------------+-------+-------------------------------------------------------+ +|Objects |alc=N |Number of objects allocated | ++ +-------+-------------------------------------------------------+ +| |nal=N |Number of object allocation failures | ++ +-------+-------------------------------------------------------+ +| |avl=N |Number of objects that reached the available state | ++ +-------+-------------------------------------------------------+ +| |ded=N |Number of objects that reached the dead state | ++--------------+-------+-------------------------------------------------------+ +|ChkAux |non=N |Number of objects that didn't have a coherency check | ++ +-------+-------------------------------------------------------+ +| |ok=N |Number of objects that passed a coherency check | ++ +-------+-------------------------------------------------------+ +| |upd=N |Number of objects that needed a coherency data update | ++ +-------+-------------------------------------------------------+ +| |obs=N |Number of objects that were declared obsolete | ++--------------+-------+-------------------------------------------------------+ +|Pages |mrk=N |Number of pages marked as being cached | +| |unc=N |Number of uncache page requests seen | ++--------------+-------+-------------------------------------------------------+ +|Acquire |n=N |Number of acquire cookie requests seen | ++ +-------+-------------------------------------------------------+ +| |nul=N |Number of acq reqs given a NULL parent | ++ +-------+-------------------------------------------------------+ +| |noc=N |Number of acq reqs rejected due to no cache available | ++ +-------+-------------------------------------------------------+ +| |ok=N |Number of acq reqs succeeded | ++ +-------+-------------------------------------------------------+ +| |nbf=N |Number of acq reqs rejected due to error | ++ +-------+-------------------------------------------------------+ +| |oom=N |Number of acq reqs failed on ENOMEM | ++--------------+-------+-------------------------------------------------------+ +|Lookups |n=N |Number of lookup calls made on cache backends | ++ +-------+-------------------------------------------------------+ +| |neg=N |Number of negative lookups made | ++ +-------+-------------------------------------------------------+ +| |pos=N |Number of positive lookups made | ++ +-------+-------------------------------------------------------+ +| |crt=N |Number of objects created by lookup | ++ +-------+-------------------------------------------------------+ +| |tmo=N |Number of lookups timed out and requeued | ++--------------+-------+-------------------------------------------------------+ +|Updates |n=N |Number of update cookie requests seen | ++ +-------+-------------------------------------------------------+ +| |nul=N |Number of upd reqs given a NULL parent | ++ +-------+-------------------------------------------------------+ +| |run=N |Number of upd reqs granted CPU time | ++--------------+-------+-------------------------------------------------------+ +|Relinqs |n=N |Number of relinquish cookie requests seen | ++ +-------+-------------------------------------------------------+ +| |nul=N |Number of rlq reqs given a NULL parent | ++ +-------+-------------------------------------------------------+ +| |wcr=N |Number of rlq reqs waited on completion of creation | ++--------------+-------+-------------------------------------------------------+ +|AttrChg |n=N |Number of attribute changed requests seen | ++ +-------+-------------------------------------------------------+ +| |ok=N |Number of attr changed requests queued | ++ +-------+-------------------------------------------------------+ +| |nbf=N |Number of attr changed rejected -ENOBUFS | ++ +-------+-------------------------------------------------------+ +| |oom=N |Number of attr changed failed -ENOMEM | ++ +-------+-------------------------------------------------------+ +| |run=N |Number of attr changed ops given CPU time | ++--------------+-------+-------------------------------------------------------+ +|Allocs |n=N |Number of allocation requests seen | ++ +-------+-------------------------------------------------------+ +| |ok=N |Number of successful alloc reqs | ++ +-------+-------------------------------------------------------+ +| |wt=N |Number of alloc reqs that waited on lookup completion | ++ +-------+-------------------------------------------------------+ +| |nbf=N |Number of alloc reqs rejected -ENOBUFS | ++ +-------+-------------------------------------------------------+ +| |int=N |Number of alloc reqs aborted -ERESTARTSYS | ++ +-------+-------------------------------------------------------+ +| |ops=N |Number of alloc reqs submitted | ++ +-------+-------------------------------------------------------+ +| |owt=N |Number of alloc reqs waited for CPU time | ++ +-------+-------------------------------------------------------+ +| |abt=N |Number of alloc reqs aborted due to object death | ++--------------+-------+-------------------------------------------------------+ +|Retrvls |n=N |Number of retrieval (read) requests seen | ++ +-------+-------------------------------------------------------+ +| |ok=N |Number of successful retr reqs | ++ +-------+-------------------------------------------------------+ +| |wt=N |Number of retr reqs that waited on lookup completion | ++ +-------+-------------------------------------------------------+ +| |nod=N |Number of retr reqs returned -ENODATA | ++ +-------+-------------------------------------------------------+ +| |nbf=N |Number of retr reqs rejected -ENOBUFS | ++ +-------+-------------------------------------------------------+ +| |int=N |Number of retr reqs aborted -ERESTARTSYS | ++ +-------+-------------------------------------------------------+ +| |oom=N |Number of retr reqs failed -ENOMEM | ++ +-------+-------------------------------------------------------+ +| |ops=N |Number of retr reqs submitted | ++ +-------+-------------------------------------------------------+ +| |owt=N |Number of retr reqs waited for CPU time | ++ +-------+-------------------------------------------------------+ +| |abt=N |Number of retr reqs aborted due to object death | ++--------------+-------+-------------------------------------------------------+ +|Stores |n=N |Number of storage (write) requests seen | ++ +-------+-------------------------------------------------------+ +| |ok=N |Number of successful store reqs | ++ +-------+-------------------------------------------------------+ +| |agn=N |Number of store reqs on a page already pending storage | ++ +-------+-------------------------------------------------------+ +| |nbf=N |Number of store reqs rejected -ENOBUFS | ++ +-------+-------------------------------------------------------+ +| |oom=N |Number of store reqs failed -ENOMEM | ++ +-------+-------------------------------------------------------+ +| |ops=N |Number of store reqs submitted | ++ +-------+-------------------------------------------------------+ +| |run=N |Number of store reqs granted CPU time | ++ +-------+-------------------------------------------------------+ +| |pgs=N |Number of pages given store req processing time | ++ +-------+-------------------------------------------------------+ +| |rxd=N |Number of store reqs deleted from tracking tree | ++ +-------+-------------------------------------------------------+ +| |olm=N |Number of store reqs over store limit | ++--------------+-------+-------------------------------------------------------+ +|VmScan |nos=N |Number of release reqs against pages with no | +| | |pending store | ++ +-------+-------------------------------------------------------+ +| |gon=N |Number of release reqs against pages stored by | +| | |time lock granted | ++ +-------+-------------------------------------------------------+ +| |bsy=N |Number of release reqs ignored due to in-progress store| ++ +-------+-------------------------------------------------------+ +| |can=N |Number of page stores cancelled due to release req | ++--------------+-------+-------------------------------------------------------+ +|Ops |pend=N |Number of times async ops added to pending queues | ++ +-------+-------------------------------------------------------+ +| |run=N |Number of times async ops given CPU time | ++ +-------+-------------------------------------------------------+ +| |enq=N |Number of times async ops queued for processing | ++ +-------+-------------------------------------------------------+ +| |can=N |Number of async ops cancelled | ++ +-------+-------------------------------------------------------+ +| |rej=N |Number of async ops rejected due to object | +| | |lookup/create failure | ++ +-------+-------------------------------------------------------+ +| |ini=N |Number of async ops initialised | ++ +-------+-------------------------------------------------------+ +| |dfr=N |Number of async ops queued for deferred release | ++ +-------+-------------------------------------------------------+ +| |rel=N |Number of async ops released | +| | |(should equal ini=N when idle) | ++ +-------+-------------------------------------------------------+ +| |gc=N |Number of deferred-release async ops garbage collected | ++--------------+-------+-------------------------------------------------------+ +|CacheOp |alo=N |Number of in-progress alloc_object() cache ops | ++ +-------+-------------------------------------------------------+ +| |luo=N |Number of in-progress lookup_object() cache ops | ++ +-------+-------------------------------------------------------+ +| |luc=N |Number of in-progress lookup_complete() cache ops | ++ +-------+-------------------------------------------------------+ +| |gro=N |Number of in-progress grab_object() cache ops | ++ +-------+-------------------------------------------------------+ +| |upo=N |Number of in-progress update_object() cache ops | ++ +-------+-------------------------------------------------------+ +| |dro=N |Number of in-progress drop_object() cache ops | ++ +-------+-------------------------------------------------------+ +| |pto=N |Number of in-progress put_object() cache ops | ++ +-------+-------------------------------------------------------+ +| |syn=N |Number of in-progress sync_cache() cache ops | ++ +-------+-------------------------------------------------------+ +| |atc=N |Number of in-progress attr_changed() cache ops | ++ +-------+-------------------------------------------------------+ +| |rap=N |Number of in-progress read_or_alloc_page() cache ops | ++ +-------+-------------------------------------------------------+ +| |ras=N |Number of in-progress read_or_alloc_pages() cache ops | ++ +-------+-------------------------------------------------------+ +| |alp=N |Number of in-progress allocate_page() cache ops | ++ +-------+-------------------------------------------------------+ +| |als=N |Number of in-progress allocate_pages() cache ops | ++ +-------+-------------------------------------------------------+ +| |wrp=N |Number of in-progress write_page() cache ops | ++ +-------+-------------------------------------------------------+ +| |ucp=N |Number of in-progress uncache_page() cache ops | ++ +-------+-------------------------------------------------------+ +| |dsp=N |Number of in-progress dissociate_pages() cache ops | ++--------------+-------+-------------------------------------------------------+ +|CacheEv |nsp=N |Number of object lookups/creations rejected due to | +| | |lack of space | ++ +-------+-------------------------------------------------------+ +| |stl=N |Number of stale objects deleted | ++ +-------+-------------------------------------------------------+ +| |rtr=N |Number of objects retired when relinquished | ++ +-------+-------------------------------------------------------+ +| |cul=N |Number of objects culled | ++--------------+-------+-------------------------------------------------------+ + + + +/proc/fs/fscache/histogram +-------------------------- + + :: + + cat /proc/fs/fscache/histogram + JIFS SECS OBJ INST OP RUNS OBJ RUNS RETRV DLY RETRIEVLS + ===== ===== ========= ========= ========= ========= ========= + + This shows the breakdown of the number of times each amount of time + between 0 jiffies and HZ-1 jiffies a variety of tasks took to run. The + columns are as follows: + + ========= ======================================================= + COLUMN TIME MEASUREMENT + ========= ======================================================= + OBJ INST Length of time to instantiate an object + OP RUNS Length of time a call to process an operation took + OBJ RUNS Length of time a call to process an object event took + RETRV DLY Time between an requesting a read and lookup completing + RETRIEVLS Time between beginning and end of a retrieval + ========= ======================================================= + + Each row shows the number of events that took a particular range of times. + Each step is 1 jiffy in size. The JIFS column indicates the particular + jiffy range covered, and the SECS field the equivalent number of seconds. + + + +Object List +=========== + +If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a +list of all the objects currently allocated and allow them to be viewed +through:: + + /proc/fs/fscache/objects + +This will look something like:: + + [root@andromeda ~]# head /proc/fs/fscache/objects + OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA OBJECT_KEY, AUX_DATA + ======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================ + 17e4b 2 ACTV 0 0 0 0 0 0 7b 4 0 0 | NFS.fh DT 0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a + 1693a 2 ACTV 0 0 0 0 0 0 7b 4 0 0 | NFS.fh DT 0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a + +where the first set of columns before the '|' describe the object: + + ======= =============================================================== + COLUMN DESCRIPTION + ======= =============================================================== + OBJECT Object debugging ID (appears as OBJ%x in some debug messages) + PARENT Debugging ID of parent object + STAT Object state + CHLDN Number of child objects of this object + OPS Number of outstanding operations on this object + OOP Number of outstanding child object management operations + IPR + EX Number of outstanding exclusive operations + READS Number of outstanding read operations + EM Object's event mask + EV Events raised on this object + F Object flags + S Object work item busy state mask (1:pending 2:running) + ======= =============================================================== + +and the second set of columns describe the object's cookie, if present: + + ================ ====================================================== + COLUMN DESCRIPTION + ================ ====================================================== + NETFS_COOKIE_DEF Name of netfs cookie definition + TY Cookie type (IX - index, DT - data, hex - special) + FL Cookie flags + NETFS_DATA Netfs private data stored in the cookie + OBJECT_KEY Object key } 1 column, with separating comma + AUX_DATA Object aux data } presence may be configured + ================ ====================================================== + +The data shown may be filtered by attaching the a key to an appropriate keyring +before viewing the file. Something like:: + + keyctl add user fscache:objlist <restrictions> @s + +where <restrictions> are a selection of the following letters: + + == ========================================================= + K Show hexdump of object key (don't show if not given) + A Show hexdump of object aux data (don't show if not given) + == ========================================================= + +and the following paired letters: + + == ========================================================= + C Show objects that have a cookie + c Show objects that don't have a cookie + B Show objects that are busy + b Show objects that aren't busy + W Show objects that have pending writes + w Show objects that don't have pending writes + R Show objects that have outstanding reads + r Show objects that don't have outstanding reads + S Show objects that have work queued + s Show objects that don't have work queued + == ========================================================= + +If neither side of a letter pair is given, then both are implied. For example: + + keyctl add user fscache:objlist KB @s + +shows objects that are busy, and lists their object keys, but does not dump +their auxiliary data. It also implies "CcWwRrSs", but as 'B' is given, 'b' is +not implied. + +By default all objects and all fields will be shown. + + +Debugging +========= + +If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime +debugging enabled by adjusting the value in:: + + /sys/module/fscache/parameters/debug + +This is a bitmask of debugging streams to enable: + + ======= ======= =============================== ======================= + BIT VALUE STREAM POINT + ======= ======= =============================== ======================= + 0 1 Cache management Function entry trace + 1 2 Function exit trace + 2 4 General + 3 8 Cookie management Function entry trace + 4 16 Function exit trace + 5 32 General + 6 64 Page handling Function entry trace + 7 128 Function exit trace + 8 256 General + 9 512 Operation management Function entry trace + 10 1024 Function exit trace + 11 2048 General + ======= ======= =============================== ======================= + +The appropriate set of values should be OR'd together and the result written to +the control file. For example:: + + echo $((1|8|64)) >/sys/module/fscache/parameters/debug + +will turn on all function entry debugging. diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt deleted file mode 100644 index 50f0a5757f48..000000000000 --- a/Documentation/filesystems/caching/fscache.txt +++ /dev/null @@ -1,448 +0,0 @@ - ========================== - General Filesystem Caching - ========================== - -======== -OVERVIEW -======== - -This facility is a general purpose cache for network filesystems, though it -could be used for caching other things such as ISO9660 filesystems too. - -FS-Cache mediates between cache backends (such as CacheFS) and network -filesystems: - - +---------+ - | | +--------------+ - | NFS |--+ | | - | | | +-->| CacheFS | - +---------+ | +----------+ | | /dev/hda5 | - | | | | +--------------+ - +---------+ +-->| | | - | | | |--+ - | AFS |----->| FS-Cache | - | | | |--+ - +---------+ +-->| | | - | | | | +--------------+ - +---------+ | +----------+ | | | - | | | +-->| CacheFiles | - | ISOFS |--+ | /var/cache | - | | +--------------+ - +---------+ - -Or to look at it another way, FS-Cache is a module that provides a caching -facility to a network filesystem such that the cache is transparent to the -user: - - +---------+ - | | - | Server | - | | - +---------+ - | NETWORK - ~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - | - | +----------+ - V | | - +---------+ | | - | | | | - | NFS |----->| FS-Cache | - | | | |--+ - +---------+ | | | +--------------+ +--------------+ - | | | | | | | | - V +----------+ +-->| CacheFiles |-->| Ext3 | - +---------+ | /var/cache | | /dev/sda6 | - | | +--------------+ +--------------+ - | VFS | ^ ^ - | | | | - +---------+ +--------------+ | - | KERNEL SPACE | | - ~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~|~~~~~~|~~~~ - | USER SPACE | | - V | | - +---------+ +--------------+ - | | | | - | Process | | cachefilesd | - | | | | - +---------+ +--------------+ - - -FS-Cache does not follow the idea of completely loading every netfs file -opened in its entirety into a cache before permitting it to be accessed and -then serving the pages out of that cache rather than the netfs inode because: - - (1) It must be practical to operate without a cache. - - (2) The size of any accessible file must not be limited to the size of the - cache. - - (3) The combined size of all opened files (this includes mapped libraries) - must not be limited to the size of the cache. - - (4) The user should not be forced to download an entire file just to do a - one-off access of a small portion of it (such as might be done with the - "file" program). - -It instead serves the cache out in PAGE_SIZE chunks as and when requested by -the netfs('s) using it. - - -FS-Cache provides the following facilities: - - (1) More than one cache can be used at once. Caches can be selected - explicitly by use of tags. - - (2) Caches can be added / removed at any time. - - (3) The netfs is provided with an interface that allows either party to - withdraw caching facilities from a file (required for (2)). - - (4) The interface to the netfs returns as few errors as possible, preferring - rather to let the netfs remain oblivious. - - (5) Cookies are used to represent indices, files and other objects to the - netfs. The simplest cookie is just a NULL pointer - indicating nothing - cached there. - - (6) The netfs is allowed to propose - dynamically - any index hierarchy it - desires, though it must be aware that the index search function is - recursive, stack space is limited, and indices can only be children of - indices. - - (7) Data I/O is done direct to and from the netfs's pages. The netfs - indicates that page A is at index B of the data-file represented by cookie - C, and that it should be read or written. The cache backend may or may - not start I/O on that page, but if it does, a netfs callback will be - invoked to indicate completion. The I/O may be either synchronous or - asynchronous. - - (8) Cookies can be "retired" upon release. At this point FS-Cache will mark - them as obsolete and the index hierarchy rooted at that point will get - recycled. - - (9) The netfs provides a "match" function for index searches. In addition to - saying whether a match was made or not, this can also specify that an - entry should be updated or deleted. - -(10) As much as possible is done asynchronously. - - -FS-Cache maintains a virtual indexing tree in which all indices, files, objects -and pages are kept. Bits of this tree may actually reside in one or more -caches. - - FSDEF - | - +------------------------------------+ - | | - NFS AFS - | | - +--------------------------+ +-----------+ - | | | | - homedir mirror afs.org redhat.com - | | | - +------------+ +---------------+ +----------+ - | | | | | | - 00001 00002 00007 00125 vol00001 vol00002 - | | | | | - +---+---+ +-----+ +---+ +------+------+ +-----+----+ - | | | | | | | | | | | | | -PG0 PG1 PG2 PG0 XATTR PG0 PG1 DIRENT DIRENT DIRENT R/W R/O Bak - | | - PG0 +-------+ - | | - 00001 00003 - | - +---+---+ - | | | - PG0 PG1 PG2 - -In the example above, you can see two netfs's being backed: NFS and AFS. These -have different index hierarchies: - - (*) The NFS primary index contains per-server indices. Each server index is - indexed by NFS file handles to get data file objects. Each data file - objects can have an array of pages, but may also have further child - objects, such as extended attributes and directory entries. Extended - attribute objects themselves have page-array contents. - - (*) The AFS primary index contains per-cell indices. Each cell index contains - per-logical-volume indices. Each of volume index contains up to three - indices for the read-write, read-only and backup mirrors of those volumes. - Each of these contains vnode data file objects, each of which contains an - array of pages. - -The very top index is the FS-Cache master index in which individual netfs's -have entries. - -Any index object may reside in more than one cache, provided it only has index -children. Any index with non-index object children will be assumed to only -reside in one cache. - - -The netfs API to FS-Cache can be found in: - - Documentation/filesystems/caching/netfs-api.txt - -The cache backend API to FS-Cache can be found in: - - Documentation/filesystems/caching/backend-api.txt - -A description of the internal representations and object state machine can be -found in: - - Documentation/filesystems/caching/object.txt - - -======================= -STATISTICAL INFORMATION -======================= - -If FS-Cache is compiled with the following options enabled: - - CONFIG_FSCACHE_STATS=y - CONFIG_FSCACHE_HISTOGRAM=y - -then it will gather certain statistics and display them through a number of -proc files. - - (*) /proc/fs/fscache/stats - - This shows counts of a number of events that can happen in FS-Cache: - - CLASS EVENT MEANING - ======= ======= ======================================================= - Cookies idx=N Number of index cookies allocated - dat=N Number of data storage cookies allocated - spc=N Number of special cookies allocated - Objects alc=N Number of objects allocated - nal=N Number of object allocation failures - avl=N Number of objects that reached the available state - ded=N Number of objects that reached the dead state - ChkAux non=N Number of objects that didn't have a coherency check - ok=N Number of objects that passed a coherency check - upd=N Number of objects that needed a coherency data update - obs=N Number of objects that were declared obsolete - Pages mrk=N Number of pages marked as being cached - unc=N Number of uncache page requests seen - Acquire n=N Number of acquire cookie requests seen - nul=N Number of acq reqs given a NULL parent - noc=N Number of acq reqs rejected due to no cache available - ok=N Number of acq reqs succeeded - nbf=N Number of acq reqs rejected due to error - oom=N Number of acq reqs failed on ENOMEM - Lookups n=N Number of lookup calls made on cache backends - neg=N Number of negative lookups made - pos=N Number of positive lookups made - crt=N Number of objects created by lookup - tmo=N Number of lookups timed out and requeued - Updates n=N Number of update cookie requests seen - nul=N Number of upd reqs given a NULL parent - run=N Number of upd reqs granted CPU time - Relinqs n=N Number of relinquish cookie requests seen - nul=N Number of rlq reqs given a NULL parent - wcr=N Number of rlq reqs waited on completion of creation - AttrChg n=N Number of attribute changed requests seen - ok=N Number of attr changed requests queued - nbf=N Number of attr changed rejected -ENOBUFS - oom=N Number of attr changed failed -ENOMEM - run=N Number of attr changed ops given CPU time - Allocs n=N Number of allocation requests seen - ok=N Number of successful alloc reqs - wt=N Number of alloc reqs that waited on lookup completion - nbf=N Number of alloc reqs rejected -ENOBUFS - int=N Number of alloc reqs aborted -ERESTARTSYS - ops=N Number of alloc reqs submitted - owt=N Number of alloc reqs waited for CPU time - abt=N Number of alloc reqs aborted due to object death - Retrvls n=N Number of retrieval (read) requests seen - ok=N Number of successful retr reqs - wt=N Number of retr reqs that waited on lookup completion - nod=N Number of retr reqs returned -ENODATA - nbf=N Number of retr reqs rejected -ENOBUFS - int=N Number of retr reqs aborted -ERESTARTSYS - oom=N Number of retr reqs failed -ENOMEM - ops=N Number of retr reqs submitted - owt=N Number of retr reqs waited for CPU time - abt=N Number of retr reqs aborted due to object death - Stores n=N Number of storage (write) requests seen - ok=N Number of successful store reqs - agn=N Number of store reqs on a page already pending storage - nbf=N Number of store reqs rejected -ENOBUFS - oom=N Number of store reqs failed -ENOMEM - ops=N Number of store reqs submitted - run=N Number of store reqs granted CPU time - pgs=N Number of pages given store req processing time - rxd=N Number of store reqs deleted from tracking tree - olm=N Number of store reqs over store limit - VmScan nos=N Number of release reqs against pages with no pending store - gon=N Number of release reqs against pages stored by time lock granted - bsy=N Number of release reqs ignored due to in-progress store - can=N Number of page stores cancelled due to release req - Ops pend=N Number of times async ops added to pending queues - run=N Number of times async ops given CPU time - enq=N Number of times async ops queued for processing - can=N Number of async ops cancelled - rej=N Number of async ops rejected due to object lookup/create failure - ini=N Number of async ops initialised - dfr=N Number of async ops queued for deferred release - rel=N Number of async ops released (should equal ini=N when idle) - gc=N Number of deferred-release async ops garbage collected - CacheOp alo=N Number of in-progress alloc_object() cache ops - luo=N Number of in-progress lookup_object() cache ops - luc=N Number of in-progress lookup_complete() cache ops - gro=N Number of in-progress grab_object() cache ops - upo=N Number of in-progress update_object() cache ops - dro=N Number of in-progress drop_object() cache ops - pto=N Number of in-progress put_object() cache ops - syn=N Number of in-progress sync_cache() cache ops - atc=N Number of in-progress attr_changed() cache ops - rap=N Number of in-progress read_or_alloc_page() cache ops - ras=N Number of in-progress read_or_alloc_pages() cache ops - alp=N Number of in-progress allocate_page() cache ops - als=N Number of in-progress allocate_pages() cache ops - wrp=N Number of in-progress write_page() cache ops - ucp=N Number of in-progress uncache_page() cache ops - dsp=N Number of in-progress dissociate_pages() cache ops - CacheEv nsp=N Number of object lookups/creations rejected due to lack of space - stl=N Number of stale objects deleted - rtr=N Number of objects retired when relinquished - cul=N Number of objects culled - - - (*) /proc/fs/fscache/histogram - - cat /proc/fs/fscache/histogram - JIFS SECS OBJ INST OP RUNS OBJ RUNS RETRV DLY RETRIEVLS - ===== ===== ========= ========= ========= ========= ========= - - This shows the breakdown of the number of times each amount of time - between 0 jiffies and HZ-1 jiffies a variety of tasks took to run. The - columns are as follows: - - COLUMN TIME MEASUREMENT - ======= ======================================================= - OBJ INST Length of time to instantiate an object - OP RUNS Length of time a call to process an operation took - OBJ RUNS Length of time a call to process an object event took - RETRV DLY Time between an requesting a read and lookup completing - RETRIEVLS Time between beginning and end of a retrieval - - Each row shows the number of events that took a particular range of times. - Each step is 1 jiffy in size. The JIFS column indicates the particular - jiffy range covered, and the SECS field the equivalent number of seconds. - - -=========== -OBJECT LIST -=========== - -If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a -list of all the objects currently allocated and allow them to be viewed -through: - - /proc/fs/fscache/objects - -This will look something like: - - [root@andromeda ~]# head /proc/fs/fscache/objects - OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA OBJECT_KEY, AUX_DATA - ======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================ - 17e4b 2 ACTV 0 0 0 0 0 0 7b 4 0 0 | NFS.fh DT 0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a - 1693a 2 ACTV 0 0 0 0 0 0 7b 4 0 0 | NFS.fh DT 0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a - -where the first set of columns before the '|' describe the object: - - COLUMN DESCRIPTION - ======= =============================================================== - OBJECT Object debugging ID (appears as OBJ%x in some debug messages) - PARENT Debugging ID of parent object - STAT Object state - CHLDN Number of child objects of this object - OPS Number of outstanding operations on this object - OOP Number of outstanding child object management operations - IPR - EX Number of outstanding exclusive operations - READS Number of outstanding read operations - EM Object's event mask - EV Events raised on this object - F Object flags - S Object work item busy state mask (1:pending 2:running) - -and the second set of columns describe the object's cookie, if present: - - COLUMN DESCRIPTION - =============== ======================================================= - NETFS_COOKIE_DEF Name of netfs cookie definition - TY Cookie type (IX - index, DT - data, hex - special) - FL Cookie flags - NETFS_DATA Netfs private data stored in the cookie - OBJECT_KEY Object key } 1 column, with separating comma - AUX_DATA Object aux data } presence may be configured - -The data shown may be filtered by attaching the a key to an appropriate keyring -before viewing the file. Something like: - - keyctl add user fscache:objlist <restrictions> @s - -where <restrictions> are a selection of the following letters: - - K Show hexdump of object key (don't show if not given) - A Show hexdump of object aux data (don't show if not given) - -and the following paired letters: - - C Show objects that have a cookie - c Show objects that don't have a cookie - B Show objects that are busy - b Show objects that aren't busy - W Show objects that have pending writes - w Show objects that don't have pending writes - R Show objects that have outstanding reads - r Show objects that don't have outstanding reads - S Show objects that have work queued - s Show objects that don't have work queued - -If neither side of a letter pair is given, then both are implied. For example: - - keyctl add user fscache:objlist KB @s - -shows objects that are busy, and lists their object keys, but does not dump -their auxiliary data. It also implies "CcWwRrSs", but as 'B' is given, 'b' is -not implied. - -By default all objects and all fields will be shown. - - -========= -DEBUGGING -========= - -If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime -debugging enabled by adjusting the value in: - - /sys/module/fscache/parameters/debug - -This is a bitmask of debugging streams to enable: - - BIT VALUE STREAM POINT - ======= ======= =============================== ======================= - 0 1 Cache management Function entry trace - 1 2 Function exit trace - 2 4 General - 3 8 Cookie management Function entry trace - 4 16 Function exit trace - 5 32 General - 6 64 Page handling Function entry trace - 7 128 Function exit trace - 8 256 General - 9 512 Operation management Function entry trace - 10 1024 Function exit trace - 11 2048 General - -The appropriate set of values should be OR'd together and the result written to -the control file. For example: - - echo $((1|8|64)) >/sys/module/fscache/parameters/debug - -will turn on all function entry debugging. diff --git a/Documentation/filesystems/caching/index.rst b/Documentation/filesystems/caching/index.rst new file mode 100644 index 000000000000..033da7ac7c6e --- /dev/null +++ b/Documentation/filesystems/caching/index.rst @@ -0,0 +1,14 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Filesystem Caching +================== + +.. toctree:: + :maxdepth: 2 + + fscache + object + backend-api + cachefiles + netfs-api + operations diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.rst index ba968e8f5704..d9f14b8610ba 100644 --- a/Documentation/filesystems/caching/netfs-api.txt +++ b/Documentation/filesystems/caching/netfs-api.rst @@ -1,6 +1,8 @@ - =============================== - FS-CACHE NETWORK FILESYSTEM API - =============================== +.. SPDX-License-Identifier: GPL-2.0 + +=============================== +FS-Cache Network Filesystem API +=============================== There's an API by which a network filesystem can make use of the FS-Cache facilities. This is based around a number of principles: @@ -19,7 +21,7 @@ facilities. This is based around a number of principles: This API is declared in <linux/fscache.h>. -This document contains the following sections: +.. This document contains the following sections: (1) Network filesystem definition (2) Index definition @@ -41,12 +43,11 @@ This document contains the following sections: (18) FS-Cache specific page flags. -============================= -NETWORK FILESYSTEM DEFINITION +Network Filesystem Definition ============================= FS-Cache needs a description of the network filesystem. This is specified -using a record of the following structure: +using a record of the following structure:: struct fscache_netfs { uint32_t version; @@ -71,7 +72,7 @@ The fields are: another parameter passed into the registration function. For example, kAFS (linux/fs/afs/) uses the following definitions to describe -itself: +itself:: struct fscache_netfs afs_cache_netfs = { .version = 0, @@ -79,8 +80,7 @@ itself: }; -================ -INDEX DEFINITION +Index Definition ================ Indices are used for two purposes: @@ -114,11 +114,10 @@ There are some limits on indices: function is recursive. Too many layers will run the kernel out of stack. -================= -OBJECT DEFINITION +Object Definition ================= -To define an object, a structure of the following type should be filled out: +To define an object, a structure of the following type should be filled out:: struct fscache_cookie_def { @@ -149,16 +148,13 @@ This has the following fields: This is one of the following values: - (*) FSCACHE_COOKIE_TYPE_INDEX - + FSCACHE_COOKIE_TYPE_INDEX This defines an index, which is a special FS-Cache type. - (*) FSCACHE_COOKIE_TYPE_DATAFILE - + FSCACHE_COOKIE_TYPE_DATAFILE This defines an ordinary data file. - (*) Any other value between 2 and 255 - + Any other value between 2 and 255 This defines an extraordinary object such as an XATTR. (2) The name of the object type (NUL terminated unless all 16 chars are used) @@ -192,9 +188,14 @@ This has the following fields: If present, the function should return one of the following values: - (*) FSCACHE_CHECKAUX_OKAY - the entry is okay as is - (*) FSCACHE_CHECKAUX_NEEDS_UPDATE - the entry requires update - (*) FSCACHE_CHECKAUX_OBSOLETE - the entry should be deleted + FSCACHE_CHECKAUX_OKAY + - the entry is okay as is + + FSCACHE_CHECKAUX_NEEDS_UPDATE + - the entry requires update + + FSCACHE_CHECKAUX_OBSOLETE + - the entry should be deleted This function can also be used to extract data from the auxiliary data in the cache and copy it into the netfs's structures. @@ -236,32 +237,30 @@ This has the following fields: This function is not required for indices as they're not permitted data. -=================================== -NETWORK FILESYSTEM (UN)REGISTRATION +Network Filesystem (Un)registration =================================== The first step is to declare the network filesystem to the cache. This also involves specifying the layout of the primary index (for AFS, this would be the "cell" level). -The registration function is: +The registration function is:: int fscache_register_netfs(struct fscache_netfs *netfs); It just takes a pointer to the netfs definition. It returns 0 or an error as appropriate. -For kAFS, registration is done as follows: +For kAFS, registration is done as follows:: ret = fscache_register_netfs(&afs_cache_netfs); -The last step is, of course, unregistration: +The last step is, of course, unregistration:: void fscache_unregister_netfs(struct fscache_netfs *netfs); -================ -CACHE TAG LOOKUP +Cache Tag Lookup ================ FS-Cache permits the use of more than one cache. To permit particular index @@ -270,7 +269,7 @@ representation tags. This step is optional; it can be left entirely up to FS-Cache as to which cache should be used. The problem with doing that is that FS-Cache will always pick the first cache that was registered. -To get the representation for a named tag: +To get the representation for a named tag:: struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name); @@ -278,7 +277,7 @@ This takes a text string as the name and returns a representation of a tag. It will never return an error. It may return a dummy tag, however, if it runs out of memory; this will inhibit caching with this tag. -Any representation so obtained must be released by passing it to this function: +Any representation so obtained must be released by passing it to this function:: void fscache_release_cache_tag(struct fscache_cache_tag *tag); @@ -286,13 +285,12 @@ The tag will be retrieved by FS-Cache when it calls the object definition operation select_cache(). -================== -INDEX REGISTRATION +Index Registration ================== The third step is to inform FS-Cache about part of an index hierarchy that can be used to locate files. This is done by requesting a cookie for each index in -the path to the file: +the path to the file:: struct fscache_cookie * fscache_acquire_cookie(struct fscache_cookie *parent, @@ -339,7 +337,7 @@ must be enabled to do anything with it. A disabled cookie can be enabled by calling fscache_enable_cookie() (see below). For example, with AFS, a cell would be added to the primary index. This index -entry would have a dependent inode containing volume mappings within this cell: +entry would have a dependent inode containing volume mappings within this cell:: cell->cache = fscache_acquire_cookie(afs_cache_netfs.primary_index, @@ -349,7 +347,7 @@ entry would have a dependent inode containing volume mappings within this cell: cell, 0, true); And then a particular volume could be added to that index by ID, creating -another index for vnodes (AFS inode equivalents): +another index for vnodes (AFS inode equivalents):: volume->cache = fscache_acquire_cookie(volume->cell->cache, @@ -359,13 +357,12 @@ another index for vnodes (AFS inode equivalents): volume, 0, true); -====================== -DATA FILE REGISTRATION +Data File Registration ====================== The fourth step is to request a data file be created in the cache. This is identical to index cookie acquisition. The only difference is that the type in -the object definition should be something other than index type. +the object definition should be something other than index type:: vnode->cache = fscache_acquire_cookie(volume->cache, @@ -375,15 +372,14 @@ the object definition should be something other than index type. vnode, vnode->status.size, true); -================================= -MISCELLANEOUS OBJECT REGISTRATION +Miscellaneous Object Registration ================================= An optional step is to request an object of miscellaneous type be created in the cache. This is almost identical to index cookie acquisition. The only difference is that the type in the object definition should be something other than index type. While the parent object could be an index, it's more likely -it would be some other type of object such as a data file. +it would be some other type of object such as a data file:: xattr->cache = fscache_acquire_cookie(vnode->cache, @@ -396,13 +392,12 @@ Miscellaneous objects might be used to store extended attributes or directory entries for example. -========================== -SETTING THE DATA FILE SIZE +Setting the Data File Size ========================== The fifth step is to set the physical attributes of the file, such as its size. This doesn't automatically reserve any space in the cache, but permits the -cache to adjust its metadata for data tracking appropriately: +cache to adjust its metadata for data tracking appropriately:: int fscache_attr_changed(struct fscache_cookie *cookie); @@ -417,8 +412,7 @@ some point in the future, and as such, it may happen after the function returns to the caller. The attribute adjustment excludes read and write operations. -===================== -PAGE ALLOC/READ/WRITE +Page alloc/read/write ===================== And the sixth step is to store and retrieve pages in the cache. There are @@ -441,7 +435,7 @@ PAGE READ Firstly, the netfs should ask FS-Cache to examine the caches and read the contents cached for a particular page of a particular file if present, or else -allocate space to store the contents if not: +allocate space to store the contents if not:: typedef void (*fscache_rw_complete_t)(struct page *page, @@ -474,14 +468,14 @@ Else if there's a copy of the page resident in the cache: (4) When the read is complete, end_io_func() will be invoked with: - (*) The netfs data supplied when the cookie was created. + * The netfs data supplied when the cookie was created. - (*) The page descriptor. + * The page descriptor. - (*) The context argument passed to the above function. This will be + * The context argument passed to the above function. This will be maintained with the get_context/put_context functions mentioned above. - (*) An argument that's 0 on success or negative for an error code. + * An argument that's 0 on success or negative for an error code. If an error occurs, it should be assumed that the page contains no usable data. fscache_readpages_cancel() may need to be called. @@ -504,11 +498,11 @@ This function may also return -ENOMEM or -EINTR, in which case it won't have read any data from the cache. -PAGE ALLOCATE +Page Allocate ------------- Alternatively, if there's not expected to be any data in the cache for a page -because the file has been extended, a block can simply be allocated instead: +because the file has been extended, a block can simply be allocated instead:: int fscache_alloc_page(struct fscache_cookie *cookie, struct page *page, @@ -523,12 +517,12 @@ The mark_pages_cached() cookie operation will be called on the page if successful. -PAGE WRITE +Page Write ---------- Secondly, if the netfs changes the contents of the page (either due to an initial download or if a user performs a write), then the page should be -written back to the cache: +written back to the cache:: int fscache_write_page(struct fscache_cookie *cookie, struct page *page, @@ -566,11 +560,11 @@ place if unforeseen circumstances arose (such as a disk error). Writing takes place asynchronously. -MULTIPLE PAGE READ +Multiple Page Read ------------------ A facility is provided to read several pages at once, as requested by the -readpages() address space operation: +readpages() address space operation:: int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, struct address_space *mapping, @@ -598,7 +592,7 @@ This works in a similar way to fscache_read_or_alloc_page(), except: be returned. Otherwise, if all pages had reads dispatched, then 0 will be returned, the - list will be empty and *nr_pages will be 0. + list will be empty and ``*nr_pages`` will be 0. (4) end_io_func will be called once for each page being read as the reads complete. It will be called in process context if error != 0, but it may @@ -609,13 +603,13 @@ some of the pages being read and some being allocated. Those pages will have been marked appropriately and will need uncaching. -CANCELLATION OF UNREAD PAGES +Cancellation of Unread Pages ---------------------------- If one or more pages are passed to fscache_read_or_alloc_pages() but not then read from the cache and also not read from the underlying filesystem then those pages will need to have any marks and reservations removed. This can be -done by calling: +done by calling:: void fscache_readpages_cancel(struct fscache_cookie *cookie, struct list_head *pages); @@ -625,11 +619,10 @@ fscache_read_or_alloc_pages(). Every page in the pages list will be examined and any that have PG_fscache set will be uncached. -============== -PAGE UNCACHING +Page Uncaching ============== -To uncache a page, this function should be called: +To uncache a page, this function should be called:: void fscache_uncache_page(struct fscache_cookie *cookie, struct page *page); @@ -644,12 +637,12 @@ data file must be retired (see the relinquish cookie function below). Furthermore, note that this does not cancel the asynchronous read or write operation started by the read/alloc and write functions, so the page -invalidation functions must use: +invalidation functions must use:: bool fscache_check_page_write(struct fscache_cookie *cookie, struct page *page); -to see if a page is being written to the cache, and: +to see if a page is being written to the cache, and:: void fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page); @@ -660,7 +653,7 @@ to wait for it to finish if it is. When releasepage() is being implemented, a special FS-Cache function exists to manage the heuristics of coping with vmscan trying to eject pages, which may conflict with the cache trying to write pages to the cache (which may itself -need to allocate memory): +need to allocate memory):: bool fscache_maybe_release_page(struct fscache_cookie *cookie, struct page *page, @@ -676,12 +669,12 @@ storage request to complete, or it may attempt to cancel the storage request - in which case the page will not be stored in the cache this time. -BULK INODE PAGE UNCACHE +Bulk Image Page Uncache ----------------------- A convenience routine is provided to perform an uncache on all the pages attached to an inode. This assumes that the pages on the inode correspond on a -1:1 basis with the pages in the cache. +1:1 basis with the pages in the cache:: void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, struct inode *inode); @@ -692,12 +685,11 @@ written to the cache and for the cache to finish with the page generally. No error is returned. -=============================== -INDEX AND DATA FILE CONSISTENCY +Index and Data File consistency =============================== To find out whether auxiliary data for an object is up to data within the -cache, the following function can be called: +cache, the following function can be called:: int fscache_check_consistency(struct fscache_cookie *cookie, const void *aux_data); @@ -708,7 +700,7 @@ data buffer first. It returns 0 if it is and -ESTALE if it isn't; it may also return -ENOMEM and -ERESTARTSYS. To request an update of the index data for an index or other object, the -following function should be called: +following function should be called:: void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data); @@ -721,8 +713,7 @@ Note that partial updates may happen automatically at other times, such as when data blocks are added to a data file object. -================= -COOKIE ENABLEMENT +Cookie Enablement ================= Cookies exist in one of two states: enabled and disabled. If a cookie is @@ -731,7 +722,7 @@ invalidate its state; allocate, read or write backing pages - though it is still possible to uncache pages and relinquish the cookie. The initial enablement state is set by fscache_acquire_cookie(), but the cookie -can be enabled or disabled later. To disable a cookie, call: +can be enabled or disabled later. To disable a cookie, call:: void fscache_disable_cookie(struct fscache_cookie *cookie, const void *aux_data, @@ -746,7 +737,7 @@ All possible failures are handled internally. The caller should consider calling fscache_uncache_all_inode_pages() afterwards to make sure all page markings are cleared up. -Cookies can be enabled or reenabled with: +Cookies can be enabled or reenabled with:: void fscache_enable_cookie(struct fscache_cookie *cookie, const void *aux_data, @@ -771,13 +762,12 @@ In both cases, the cookie's auxiliary data buffer is updated from aux_data if that is non-NULL inside the enablement lock before proceeding. -=============================== -MISCELLANEOUS COOKIE OPERATIONS +Miscellaneous Cookie operations =============================== There are a number of operations that can be used to control cookies: - (*) Cookie pinning: + * Cookie pinning:: int fscache_pin_cookie(struct fscache_cookie *cookie); void fscache_unpin_cookie(struct fscache_cookie *cookie); @@ -790,7 +780,7 @@ There are a number of operations that can be used to control cookies: -ENOSPC if there isn't enough space to honour the operation, -ENOMEM or -EIO if there's any other problem. - (*) Data space reservation: + * Data space reservation:: int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size); @@ -809,11 +799,10 @@ There are a number of operations that can be used to control cookies: make space if it's not in use. -===================== -COOKIE UNREGISTRATION +Cookie Unregistration ===================== -To get rid of a cookie, this function should be called. +To get rid of a cookie, this function should be called:: void fscache_relinquish_cookie(struct fscache_cookie *cookie, const void *aux_data, @@ -835,16 +824,14 @@ the cookies for "child" indices, objects and pages have been relinquished first. -================== -INDEX INVALIDATION +Index Invalidation ================== There is no direct way to invalidate an index subtree. To do this, the caller should relinquish and retire the cookie they have, and then acquire a new one. -====================== -DATA FILE INVALIDATION +Data File Invalidation ====================== Sometimes it will be necessary to invalidate an object that contains data. @@ -853,7 +840,7 @@ change - at which point the netfs has to throw away all the state it had for an inode and reload from the server. To indicate that a cache object should be invalidated, the following function -can be called: +can be called:: void fscache_invalidate(struct fscache_cookie *cookie); @@ -868,13 +855,12 @@ auxiliary data update operation as it is very likely these will have changed. Using the following function, the netfs can wait for the invalidation operation to have reached a point at which it can start submitting ordinary operations -once again: +once again:: void fscache_wait_on_invalidate(struct fscache_cookie *cookie); -=========================== -FS-CACHE SPECIFIC PAGE FLAG +FS-cache Specific Page Flag =========================== FS-Cache makes use of a page flag, PG_private_2, for its own purpose. This is @@ -898,7 +884,7 @@ was given under certain circumstances. This bit does not overlap with such as PG_private. This means that FS-Cache can be used with a filesystem that uses the block buffering code. -There are a number of operations defined on this flag: +There are a number of operations defined on this flag:: int PageFsCache(struct page *page); void SetPageFsCache(struct page *page) diff --git a/Documentation/filesystems/caching/object.txt b/Documentation/filesystems/caching/object.rst index 100ff41127e4..ce0e043ccd33 100644 --- a/Documentation/filesystems/caching/object.txt +++ b/Documentation/filesystems/caching/object.rst @@ -1,10 +1,12 @@ - ==================================================== - IN-KERNEL CACHE OBJECT REPRESENTATION AND MANAGEMENT - ==================================================== +.. SPDX-License-Identifier: GPL-2.0 + +==================================================== +In-Kernel Cache Object Representation and Management +==================================================== By: David Howells <dhowells@redhat.com> -Contents: +.. Contents: (*) Representation @@ -18,8 +20,7 @@ Contents: (*) The set of events. -============== -REPRESENTATION +Representation ============== FS-Cache maintains an in-kernel representation of each object that a netfs is @@ -38,7 +39,7 @@ or even by no objects (it may not be cached). Furthermore, both cookies and objects are hierarchical. The two hierarchies correspond, but the cookies tree is a superset of the union of the object trees -of multiple caches: +of multiple caches:: NETFS INDEX TREE : CACHE 1 : CACHE 2 : : @@ -89,8 +90,7 @@ pointers to the cookies. The cookies themselves and any objects attached to those cookies are hidden from it. -=============================== -OBJECT MANAGEMENT STATE MACHINE +Object Management State Machine =============================== Within FS-Cache, each active object is managed by its own individual state @@ -124,7 +124,7 @@ is not masked, the object will be queued for processing (by calling fscache_enqueue_object()). -PROVISION OF CPU TIME +Provision of CPU Time --------------------- The work to be done by the various states was given CPU time by the threads of @@ -141,7 +141,7 @@ because: workqueues don't necessarily have the right numbers of threads. -LOCKING SIMPLIFICATION +Locking Simplification ---------------------- Because only one worker thread may be operating on any particular object's @@ -151,8 +151,7 @@ from the cache backend's representation (fscache_object) - which may be requested from either end. -================= -THE SET OF STATES +The Set of States ================= The object state machine has a set of states that it can be in. There are @@ -275,19 +274,17 @@ memory and potentially deletes stuff from disk: this state. -THE SET OF EVENTS +The Set of Events ----------------- There are a number of events that can be raised to an object state machine: - (*) FSCACHE_OBJECT_EV_UPDATE - + FSCACHE_OBJECT_EV_UPDATE The netfs requested that an object be updated. The state machine will ask the cache backend to update the object, and the cache backend will ask the netfs for details of the change through its cookie definition ops. - (*) FSCACHE_OBJECT_EV_CLEARED - + FSCACHE_OBJECT_EV_CLEARED This is signalled in two circumstances: (a) when an object's last child object is dropped and @@ -296,20 +293,16 @@ There are a number of events that can be raised to an object state machine: This is used to proceed from the dying state. - (*) FSCACHE_OBJECT_EV_ERROR - + FSCACHE_OBJECT_EV_ERROR This is signalled when an I/O error occurs during the processing of some object. - (*) FSCACHE_OBJECT_EV_RELEASE - (*) FSCACHE_OBJECT_EV_RETIRE - + FSCACHE_OBJECT_EV_RELEASE, FSCACHE_OBJECT_EV_RETIRE These are signalled when the netfs relinquishes a cookie it was using. The event selected depends on whether the netfs asks for the backing object to be retired (deleted) or retained. - (*) FSCACHE_OBJECT_EV_WITHDRAW - + FSCACHE_OBJECT_EV_WITHDRAW This is signalled when the cache backend wants to withdraw an object. This means that the object will have to be detached from the netfs's cookie. diff --git a/Documentation/filesystems/caching/operations.txt b/Documentation/filesystems/caching/operations.rst index d8976c434718..f7ddcc028939 100644 --- a/Documentation/filesystems/caching/operations.txt +++ b/Documentation/filesystems/caching/operations.rst @@ -1,10 +1,12 @@ - ================================ - ASYNCHRONOUS OPERATIONS HANDLING - ================================ +.. SPDX-License-Identifier: GPL-2.0 + +================================ +Asynchronous Operations Handling +================================ By: David Howells <dhowells@redhat.com> -Contents: +.. Contents: (*) Overview. @@ -17,8 +19,7 @@ Contents: (*) Asynchronous callback. -======== -OVERVIEW +Overview ======== FS-Cache has an asynchronous operations handling facility that it uses for its @@ -33,11 +34,10 @@ backend for completion. To make use of this facility, <linux/fscache-cache.h> should be #included. -=============================== -OPERATION RECORD INITIALISATION +Operation Record Initialisation =============================== -An operation is recorded in an fscache_operation struct: +An operation is recorded in an fscache_operation struct:: struct fscache_operation { union { @@ -50,7 +50,7 @@ An operation is recorded in an fscache_operation struct: }; Someone wanting to issue an operation should allocate something with this -struct embedded in it. They should initialise it by calling: +struct embedded in it. They should initialise it by calling:: void fscache_operation_init(struct fscache_operation *op, fscache_operation_release_t release); @@ -67,8 +67,7 @@ FSCACHE_OP_WAITING may be set in op->flags prior to each submission of the operation and waited for afterwards. -========== -PARAMETERS +Parameters ========== There are a number of parameters that can be set in the operation record's flag @@ -87,7 +86,7 @@ operations: If this option is to be used, FSCACHE_OP_WAITING must be set in op->flags before submitting the operation, and the operating thread must wait for it - to be cleared before proceeding: + to be cleared before proceeding:: wait_on_bit(&op->flags, FSCACHE_OP_WAITING, TASK_UNINTERRUPTIBLE); @@ -101,7 +100,7 @@ operations: page to a netfs page after the backing fs has read the page in. If this option is used, op->fast_work and op->processor must be - initialised before submitting the operation: + initialised before submitting the operation:: INIT_WORK(&op->fast_work, do_some_work); @@ -114,7 +113,7 @@ operations: pages that have just been fetched from a remote server. If this option is used, op->slow_work and op->processor must be - initialised before submitting the operation: + initialised before submitting the operation:: fscache_operation_init_slow(op, processor) @@ -132,8 +131,7 @@ Furthermore, operations may be one of two types: operations running at the same time. -========= -PROCEDURE +Procedure ========= Operations are used through the following procedure: @@ -143,7 +141,7 @@ Operations are used through the following procedure: generic op embedded within. (2) The submitting thread must then submit the operation for processing using - one of the following two functions: + one of the following two functions:: int fscache_submit_op(struct fscache_object *object, struct fscache_operation *op); @@ -164,7 +162,7 @@ Operations are used through the following procedure: operation of conflicting exclusivity is in progress on the object. If the operation is asynchronous, the manager will retain a reference to - it, so the caller should put their reference to it by passing it to: + it, so the caller should put their reference to it by passing it to:: void fscache_put_operation(struct fscache_operation *op); @@ -179,12 +177,12 @@ Operations are used through the following procedure: (4) The operation holds an effective lock upon the object, preventing other exclusive ops conflicting until it is released. The operation can be enqueued for further immediate asynchronous processing by adjusting the - CPU time provisioning option if necessary, eg: + CPU time provisioning option if necessary, eg:: op->flags &= ~FSCACHE_OP_TYPE; op->flags |= ~FSCACHE_OP_FAST; - and calling: + and calling:: void fscache_enqueue_operation(struct fscache_operation *op) @@ -192,13 +190,12 @@ Operations are used through the following procedure: pools. -===================== -ASYNCHRONOUS CALLBACK +Asynchronous Callback ===================== When used in asynchronous mode, the worker thread pool will invoke the processor method with a pointer to the operation. This should then get at the -container struct by using container_of(): +container struct by using container_of():: static void fscache_write_op(struct fscache_operation *_op) { diff --git a/Documentation/filesystems/cifs/cifsroot.txt b/Documentation/filesystems/cifs/cifsroot.rst index 947b7ec6ce9e..4930bb443134 100644 --- a/Documentation/filesystems/cifs/cifsroot.txt +++ b/Documentation/filesystems/cifs/cifsroot.rst @@ -1,7 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================================== Mounting root file system via SMB (cifs.ko) =========================================== Written 2019 by Paulo Alcantara <palcantara@suse.de> + Written 2019 by Aurelien Aptel <aaptel@suse.com> The CONFIG_CIFS_ROOT option enables experimental root file system @@ -32,7 +36,7 @@ Server configuration ==================== To enable SMB1+UNIX extensions you will need to set these global -settings in Samba smb.conf: +settings in Samba smb.conf:: [global] server min protocol = NT1 @@ -41,12 +45,16 @@ settings in Samba smb.conf: Kernel command line =================== -root=/dev/cifs +:: + + root=/dev/cifs This is just a virtual device that basically tells the kernel to mount the root file system via SMB protocol. -cifsroot=//<server-ip>/<share>[,options] +:: + + cifsroot=//<server-ip>/<share>[,options] Enables the kernel to mount the root file system via SMB that are located in the <server-ip> and <share> specified in this option. @@ -65,33 +73,33 @@ options Examples ======== -Export root file system as a Samba share in smb.conf file. +Export root file system as a Samba share in smb.conf file:: -... -[linux] - path = /path/to/rootfs - read only = no - guest ok = yes - force user = root - force group = root - browseable = yes - writeable = yes - admin users = root - public = yes - create mask = 0777 - directory mask = 0777 -... + ... + [linux] + path = /path/to/rootfs + read only = no + guest ok = yes + force user = root + force group = root + browseable = yes + writeable = yes + admin users = root + public = yes + create mask = 0777 + directory mask = 0777 + ... -Restart smb service. +Restart smb service:: -# systemctl restart smb + # systemctl restart smb Test it under QEMU on a kernel built with CONFIG_CIFS_ROOT and -CONFIG_IP_PNP options enabled. +CONFIG_IP_PNP options enabled:: -# qemu-system-x86_64 -enable-kvm -cpu host -m 1024 \ - -kernel /path/to/linux/arch/x86/boot/bzImage -nographic \ - -append "root=/dev/cifs rw ip=dhcp cifsroot=//10.0.2.2/linux,username=foo,password=bar console=ttyS0 3" + # qemu-system-x86_64 -enable-kvm -cpu host -m 1024 \ + -kernel /path/to/linux/arch/x86/boot/bzImage -nographic \ + -append "root=/dev/cifs rw ip=dhcp cifsroot=//10.0.2.2/linux,username=foo,password=bar console=ttyS0 3" 1: https://wiki.samba.org/index.php/UNIX_Extensions diff --git a/Documentation/filesystems/coda.rst b/Documentation/filesystems/coda.rst new file mode 100644 index 000000000000..84c860c89887 --- /dev/null +++ b/Documentation/filesystems/coda.rst @@ -0,0 +1,1670 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== +Coda Kernel-Venus Interface +=========================== + +.. Note:: + + This is one of the technical documents describing a component of + Coda -- this document describes the client kernel-Venus interface. + +For more information: + + http://www.coda.cs.cmu.edu + +For user level software needed to run Coda: + + ftp://ftp.coda.cs.cmu.edu + +To run Coda you need to get a user level cache manager for the client, +named Venus, as well as tools to manipulate ACLs, to log in, etc. The +client needs to have the Coda filesystem selected in the kernel +configuration. + +The server needs a user level server and at present does not depend on +kernel support. + + The Venus kernel interface + + Peter J. Braam + + v1.0, Nov 9, 1997 + + This document describes the communication between Venus and kernel + level filesystem code needed for the operation of the Coda file sys- + tem. This document version is meant to describe the current interface + (version 1.0) as well as improvements we envisage. + +.. Table of Contents + + 1. Introduction + + 2. Servicing Coda filesystem calls + + 3. The message layer + + 3.1 Implementation details + + 4. The interface at the call level + + 4.1 Data structures shared by the kernel and Venus + 4.2 The pioctl interface + 4.3 root + 4.4 lookup + 4.5 getattr + 4.6 setattr + 4.7 access + 4.8 create + 4.9 mkdir + 4.10 link + 4.11 symlink + 4.12 remove + 4.13 rmdir + 4.14 readlink + 4.15 open + 4.16 close + 4.17 ioctl + 4.18 rename + 4.19 readdir + 4.20 vget + 4.21 fsync + 4.22 inactive + 4.23 rdwr + 4.24 odymount + 4.25 ody_lookup + 4.26 ody_expand + 4.27 prefetch + 4.28 signal + + 5. The minicache and downcalls + + 5.1 INVALIDATE + 5.2 FLUSH + 5.3 PURGEUSER + 5.4 ZAPFILE + 5.5 ZAPDIR + 5.6 ZAPVNODE + 5.7 PURGEFID + 5.8 REPLACE + + 6. Initialization and cleanup + + 6.1 Requirements + +1. Introduction +=============== + + A key component in the Coda Distributed File System is the cache + manager, Venus. + + When processes on a Coda enabled system access files in the Coda + filesystem, requests are directed at the filesystem layer in the + operating system. The operating system will communicate with Venus to + service the request for the process. Venus manages a persistent + client cache and makes remote procedure calls to Coda file servers and + related servers (such as authentication servers) to service these + requests it receives from the operating system. When Venus has + serviced a request it replies to the operating system with appropriate + return codes, and other data related to the request. Optionally the + kernel support for Coda may maintain a minicache of recently processed + requests to limit the number of interactions with Venus. Venus + possesses the facility to inform the kernel when elements from its + minicache are no longer valid. + + This document describes precisely this communication between the + kernel and Venus. The definitions of so called upcalls and downcalls + will be given with the format of the data they handle. We shall also + describe the semantic invariants resulting from the calls. + + Historically Coda was implemented in a BSD file system in Mach 2.6. + The interface between the kernel and Venus is very similar to the BSD + VFS interface. Similar functionality is provided, and the format of + the parameters and returned data is very similar to the BSD VFS. This + leads to an almost natural environment for implementing a kernel-level + filesystem driver for Coda in a BSD system. However, other operating + systems such as Linux and Windows 95 and NT have virtual filesystem + with different interfaces. + + To implement Coda on these systems some reverse engineering of the + Venus/Kernel protocol is necessary. Also it came to light that other + systems could profit significantly from certain small optimizations + and modifications to the protocol. To facilitate this work as well as + to make future ports easier, communication between Venus and the + kernel should be documented in great detail. This is the aim of this + document. + +2. Servicing Coda filesystem calls +=================================== + + The service of a request for a Coda file system service originates in + a process P which accessing a Coda file. It makes a system call which + traps to the OS kernel. Examples of such calls trapping to the kernel + are ``read``, ``write``, ``open``, ``close``, ``create``, ``mkdir``, + ``rmdir``, ``chmod`` in a Unix ontext. Similar calls exist in the Win32 + environment, and are named ``CreateFile``. + + Generally the operating system handles the request in a virtual + filesystem (VFS) layer, which is named I/O Manager in NT and IFS + manager in Windows 95. The VFS is responsible for partial processing + of the request and for locating the specific filesystem(s) which will + service parts of the request. Usually the information in the path + assists in locating the correct FS drivers. Sometimes after extensive + pre-processing, the VFS starts invoking exported routines in the FS + driver. This is the point where the FS specific processing of the + request starts, and here the Coda specific kernel code comes into + play. + + The FS layer for Coda must expose and implement several interfaces. + First and foremost the VFS must be able to make all necessary calls to + the Coda FS layer, so the Coda FS driver must expose the VFS interface + as applicable in the operating system. These differ very significantly + among operating systems, but share features such as facilities to + read/write and create and remove objects. The Coda FS layer services + such VFS requests by invoking one or more well defined services + offered by the cache manager Venus. When the replies from Venus have + come back to the FS driver, servicing of the VFS call continues and + finishes with a reply to the kernel's VFS. Finally the VFS layer + returns to the process. + + As a result of this design a basic interface exposed by the FS driver + must allow Venus to manage message traffic. In particular Venus must + be able to retrieve and place messages and to be notified of the + arrival of a new message. The notification must be through a mechanism + which does not block Venus since Venus must attend to other tasks even + when no messages are waiting or being processed. + + **Interfaces of the Coda FS Driver** + + Furthermore the FS layer provides for a special path of communication + between a user process and Venus, called the pioctl interface. The + pioctl interface is used for Coda specific services, such as + requesting detailed information about the persistent cache managed by + Venus. Here the involvement of the kernel is minimal. It identifies + the calling process and passes the information on to Venus. When + Venus replies the response is passed back to the caller in unmodified + form. + + Finally Venus allows the kernel FS driver to cache the results from + certain services. This is done to avoid excessive context switches + and results in an efficient system. However, Venus may acquire + information, for example from the network which implies that cached + information must be flushed or replaced. Venus then makes a downcall + to the Coda FS layer to request flushes or updates in the cache. The + kernel FS driver handles such requests synchronously. + + Among these interfaces the VFS interface and the facility to place, + receive and be notified of messages are platform specific. We will + not go into the calls exported to the VFS layer but we will state the + requirements of the message exchange mechanism. + + +3. The message layer +===================== + + At the lowest level the communication between Venus and the FS driver + proceeds through messages. The synchronization between processes + requesting Coda file service and Venus relies on blocking and waking + up processes. The Coda FS driver processes VFS- and pioctl-requests + on behalf of a process P, creates messages for Venus, awaits replies + and finally returns to the caller. The implementation of the exchange + of messages is platform specific, but the semantics have (so far) + appeared to be generally applicable. Data buffers are created by the + FS Driver in kernel memory on behalf of P and copied to user memory in + Venus. + + The FS Driver while servicing P makes upcalls to Venus. Such an + upcall is dispatched to Venus by creating a message structure. The + structure contains the identification of P, the message sequence + number, the size of the request and a pointer to the data in kernel + memory for the request. Since the data buffer is re-used to hold the + reply from Venus, there is a field for the size of the reply. A flags + field is used in the message to precisely record the status of the + message. Additional platform dependent structures involve pointers to + determine the position of the message on queues and pointers to + synchronization objects. In the upcall routine the message structure + is filled in, flags are set to 0, and it is placed on the *pending* + queue. The routine calling upcall is responsible for allocating the + data buffer; its structure will be described in the next section. + + A facility must exist to notify Venus that the message has been + created, and implemented using available synchronization objects in + the OS. This notification is done in the upcall context of the process + P. When the message is on the pending queue, process P cannot proceed + in upcall. The (kernel mode) processing of P in the filesystem + request routine must be suspended until Venus has replied. Therefore + the calling thread in P is blocked in upcall. A pointer in the + message structure will locate the synchronization object on which P is + sleeping. + + Venus detects the notification that a message has arrived, and the FS + driver allow Venus to retrieve the message with a getmsg_from_kernel + call. This action finishes in the kernel by putting the message on the + queue of processing messages and setting flags to READ. Venus is + passed the contents of the data buffer. The getmsg_from_kernel call + now returns and Venus processes the request. + + At some later point the FS driver receives a message from Venus, + namely when Venus calls sendmsg_to_kernel. At this moment the Coda FS + driver looks at the contents of the message and decides if: + + + * the message is a reply for a suspended thread P. If so it removes + the message from the processing queue and marks the message as + WRITTEN. Finally, the FS driver unblocks P (still in the kernel + mode context of Venus) and the sendmsg_to_kernel call returns to + Venus. The process P will be scheduled at some point and continues + processing its upcall with the data buffer replaced with the reply + from Venus. + + * The message is a ``downcall``. A downcall is a request from Venus to + the FS Driver. The FS driver processes the request immediately + (usually a cache eviction or replacement) and when it finishes + sendmsg_to_kernel returns. + + Now P awakes and continues processing upcall. There are some + subtleties to take account of. First P will determine if it was woken + up in upcall by a signal from some other source (for example an + attempt to terminate P) or as is normally the case by Venus in its + sendmsg_to_kernel call. In the normal case, the upcall routine will + deallocate the message structure and return. The FS routine can proceed + with its processing. + + + **Sleeping and IPC arrangements** + + In case P is woken up by a signal and not by Venus, it will first look + at the flags field. If the message is not yet READ, the process P can + handle its signal without notifying Venus. If Venus has READ, and + the request should not be processed, P can send Venus a signal message + to indicate that it should disregard the previous message. Such + signals are put in the queue at the head, and read first by Venus. If + the message is already marked as WRITTEN it is too late to stop the + processing. The VFS routine will now continue. (-- If a VFS request + involves more than one upcall, this can lead to complicated state, an + extra field "handle_signals" could be added in the message structure + to indicate points of no return have been passed.--) + + + +3.1. Implementation details +---------------------------- + + The Unix implementation of this mechanism has been through the + implementation of a character device associated with Coda. Venus + retrieves messages by doing a read on the device, replies are sent + with a write and notification is through the select system call on the + file descriptor for the device. The process P is kept waiting on an + interruptible wait queue object. + + In Windows NT and the DPMI Windows 95 implementation a DeviceIoControl + call is used. The DeviceIoControl call is designed to copy buffers + from user memory to kernel memory with OPCODES. The sendmsg_to_kernel + is issued as a synchronous call, while the getmsg_from_kernel call is + asynchronous. Windows EventObjects are used for notification of + message arrival. The process P is kept waiting on a KernelEvent + object in NT and a semaphore in Windows 95. + + +4. The interface at the call level +=================================== + + + This section describes the upcalls a Coda FS driver can make to Venus. + Each of these upcalls make use of two structures: inputArgs and + outputArgs. In pseudo BNF form the structures take the following + form:: + + + struct inputArgs { + u_long opcode; + u_long unique; /* Keep multiple outstanding msgs distinct */ + u_short pid; /* Common to all */ + u_short pgid; /* Common to all */ + struct CodaCred cred; /* Common to all */ + + <union "in" of call dependent parts of inputArgs> + }; + + struct outputArgs { + u_long opcode; + u_long unique; /* Keep multiple outstanding msgs distinct */ + u_long result; + + <union "out" of call dependent parts of inputArgs> + }; + + + + Before going on let us elucidate the role of the various fields. The + inputArgs start with the opcode which defines the type of service + requested from Venus. There are approximately 30 upcalls at present + which we will discuss. The unique field labels the inputArg with a + unique number which will identify the message uniquely. A process and + process group id are passed. Finally the credentials of the caller + are included. + + Before delving into the specific calls we need to discuss a variety of + data structures shared by the kernel and Venus. + + + + +4.1. Data structures shared by the kernel and Venus +---------------------------------------------------- + + + The CodaCred structure defines a variety of user and group ids as + they are set for the calling process. The vuid_t and vgid_t are 32 bit + unsigned integers. It also defines group membership in an array. On + Unix the CodaCred has proven sufficient to implement good security + semantics for Coda but the structure may have to undergo modification + for the Windows environment when these mature:: + + struct CodaCred { + vuid_t cr_uid, cr_euid, cr_suid, cr_fsuid; /* Real, effective, set, fs uid */ + vgid_t cr_gid, cr_egid, cr_sgid, cr_fsgid; /* same for groups */ + vgid_t cr_groups[NGROUPS]; /* Group membership for caller */ + }; + + + .. Note:: + + It is questionable if we need CodaCreds in Venus. Finally Venus + doesn't know about groups, although it does create files with the + default uid/gid. Perhaps the list of group membership is superfluous. + + + The next item is the fundamental identifier used to identify Coda + files, the ViceFid. A fid of a file uniquely defines a file or + directory in the Coda filesystem within a cell [1]_:: + + typedef struct ViceFid { + VolumeId Volume; + VnodeId Vnode; + Unique_t Unique; + } ViceFid; + + .. [1] A cell is agroup of Coda servers acting under the aegis of a single + system control machine or SCM. See the Coda Administration manual + for a detailed description of the role of the SCM. + + Each of the constituent fields: VolumeId, VnodeId and Unique_t are + unsigned 32 bit integers. We envisage that a further field will need + to be prefixed to identify the Coda cell; this will probably take the + form of a Ipv6 size IP address naming the Coda cell through DNS. + + The next important structure shared between Venus and the kernel is + the attributes of the file. The following structure is used to + exchange information. It has room for future extensions such as + support for device files (currently not present in Coda):: + + + struct coda_timespec { + int64_t tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ + }; + + struct coda_vattr { + enum coda_vtype va_type; /* vnode type (for create) */ + u_short va_mode; /* files access mode and type */ + short va_nlink; /* number of references to file */ + vuid_t va_uid; /* owner user id */ + vgid_t va_gid; /* owner group id */ + long va_fsid; /* file system id (dev for now) */ + long va_fileid; /* file id */ + u_quad_t va_size; /* file size in bytes */ + long va_blocksize; /* blocksize preferred for i/o */ + struct coda_timespec va_atime; /* time of last access */ + struct coda_timespec va_mtime; /* time of last modification */ + struct coda_timespec va_ctime; /* time file changed */ + u_long va_gen; /* generation number of file */ + u_long va_flags; /* flags defined for file */ + dev_t va_rdev; /* device special file represents */ + u_quad_t va_bytes; /* bytes of disk space held by file */ + u_quad_t va_filerev; /* file modification number */ + u_int va_vaflags; /* operations flags, see below */ + long va_spare; /* remain quad aligned */ + }; + + +4.2. The pioctl interface +-------------------------- + + + Coda specific requests can be made by application through the pioctl + interface. The pioctl is implemented as an ordinary ioctl on a + fictitious file /coda/.CONTROL. The pioctl call opens this file, gets + a file handle and makes the ioctl call. Finally it closes the file. + + The kernel involvement in this is limited to providing the facility to + open and close and pass the ioctl message and to verify that a path in + the pioctl data buffers is a file in a Coda filesystem. + + The kernel is handed a data packet of the form:: + + struct { + const char *path; + struct ViceIoctl vidata; + int follow; + } data; + + + + where:: + + + struct ViceIoctl { + caddr_t in, out; /* Data to be transferred in, or out */ + short in_size; /* Size of input buffer <= 2K */ + short out_size; /* Maximum size of output buffer, <= 2K */ + }; + + + + The path must be a Coda file, otherwise the ioctl upcall will not be + made. + + .. Note:: The data structures and code are a mess. We need to clean this up. + + +**We now proceed to document the individual calls**: + + +4.3. root +---------- + + + Arguments + in + + empty + + out:: + + struct cfs_root_out { + ViceFid VFid; + } cfs_root; + + + + Description + This call is made to Venus during the initialization of + the Coda filesystem. If the result is zero, the cfs_root structure + contains the ViceFid of the root of the Coda filesystem. If a non-zero + result is generated, its value is a platform dependent error code + indicating the difficulty Venus encountered in locating the root of + the Coda filesystem. + +4.4. lookup +------------ + + + Summary + Find the ViceFid and type of an object in a directory if it exists. + + Arguments + in:: + + struct cfs_lookup_in { + ViceFid VFid; + char *name; /* Place holder for data. */ + } cfs_lookup; + + + + out:: + + struct cfs_lookup_out { + ViceFid VFid; + int vtype; + } cfs_lookup; + + + + Description + This call is made to determine the ViceFid and filetype of + a directory entry. The directory entry requested carries name name + and Venus will search the directory identified by cfs_lookup_in.VFid. + The result may indicate that the name does not exist, or that + difficulty was encountered in finding it (e.g. due to disconnection). + If the result is zero, the field cfs_lookup_out.VFid contains the + targets ViceFid and cfs_lookup_out.vtype the coda_vtype giving the + type of object the name designates. + + The name of the object is an 8 bit character string of maximum length + CFS_MAXNAMLEN, currently set to 256 (including a 0 terminator.) + + It is extremely important to realize that Venus bitwise ors the field + cfs_lookup.vtype with CFS_NOCACHE to indicate that the object should + not be put in the kernel name cache. + + .. Note:: + + The type of the vtype is currently wrong. It should be + coda_vtype. Linux does not take note of CFS_NOCACHE. It should. + + +4.5. getattr +------------- + + + Summary Get the attributes of a file. + + Arguments + in:: + + struct cfs_getattr_in { + ViceFid VFid; + struct coda_vattr attr; /* XXXXX */ + } cfs_getattr; + + + + out:: + + struct cfs_getattr_out { + struct coda_vattr attr; + } cfs_getattr; + + + + Description + This call returns the attributes of the file identified by fid. + + Errors + Errors can occur if the object with fid does not exist, is + unaccessible or if the caller does not have permission to fetch + attributes. + + .. Note:: + + Many kernel FS drivers (Linux, NT and Windows 95) need to acquire + the attributes as well as the Fid for the instantiation of an internal + "inode" or "FileHandle". A significant improvement in performance on + such systems could be made by combining the lookup and getattr calls + both at the Venus/kernel interaction level and at the RPC level. + + The vattr structure included in the input arguments is superfluous and + should be removed. + + +4.6. setattr +------------- + + + Summary + Set the attributes of a file. + + Arguments + in:: + + struct cfs_setattr_in { + ViceFid VFid; + struct coda_vattr attr; + } cfs_setattr; + + + + + out + + empty + + Description + The structure attr is filled with attributes to be changed + in BSD style. Attributes not to be changed are set to -1, apart from + vtype which is set to VNON. Other are set to the value to be assigned. + The only attributes which the FS driver may request to change are the + mode, owner, groupid, atime, mtime and ctime. The return value + indicates success or failure. + + Errors + A variety of errors can occur. The object may not exist, may + be inaccessible, or permission may not be granted by Venus. + + +4.7. access +------------ + + + Arguments + in:: + + struct cfs_access_in { + ViceFid VFid; + int flags; + } cfs_access; + + + + out + + empty + + Description + Verify if access to the object identified by VFid for + operations described by flags is permitted. The result indicates if + access will be granted. It is important to remember that Coda uses + ACLs to enforce protection and that ultimately the servers, not the + clients enforce the security of the system. The result of this call + will depend on whether a token is held by the user. + + Errors + The object may not exist, or the ACL describing the protection + may not be accessible. + + +4.8. create +------------ + + + Summary + Invoked to create a file + + Arguments + in:: + + struct cfs_create_in { + ViceFid VFid; + struct coda_vattr attr; + int excl; + int mode; + char *name; /* Place holder for data. */ + } cfs_create; + + + + + out:: + + struct cfs_create_out { + ViceFid VFid; + struct coda_vattr attr; + } cfs_create; + + + + Description + This upcall is invoked to request creation of a file. + The file will be created in the directory identified by VFid, its name + will be name, and the mode will be mode. If excl is set an error will + be returned if the file already exists. If the size field in attr is + set to zero the file will be truncated. The uid and gid of the file + are set by converting the CodaCred to a uid using a macro CRTOUID + (this macro is platform dependent). Upon success the VFid and + attributes of the file are returned. The Coda FS Driver will normally + instantiate a vnode, inode or file handle at kernel level for the new + object. + + + Errors + A variety of errors can occur. Permissions may be insufficient. + If the object exists and is not a file the error EISDIR is returned + under Unix. + + .. Note:: + + The packing of parameters is very inefficient and appears to + indicate confusion between the system call creat and the VFS operation + create. The VFS operation create is only called to create new objects. + This create call differs from the Unix one in that it is not invoked + to return a file descriptor. The truncate and exclusive options, + together with the mode, could simply be part of the mode as it is + under Unix. There should be no flags argument; this is used in open + (2) to return a file descriptor for READ or WRITE mode. + + The attributes of the directory should be returned too, since the size + and mtime changed. + + +4.9. mkdir +----------- + + + Summary + Create a new directory. + + Arguments + in:: + + struct cfs_mkdir_in { + ViceFid VFid; + struct coda_vattr attr; + char *name; /* Place holder for data. */ + } cfs_mkdir; + + + + out:: + + struct cfs_mkdir_out { + ViceFid VFid; + struct coda_vattr attr; + } cfs_mkdir; + + + + + Description + This call is similar to create but creates a directory. + Only the mode field in the input parameters is used for creation. + Upon successful creation, the attr returned contains the attributes of + the new directory. + + Errors + As for create. + + .. Note:: + + The input parameter should be changed to mode instead of + attributes. + + The attributes of the parent should be returned since the size and + mtime changes. + + +4.10. link +----------- + + + Summary + Create a link to an existing file. + + Arguments + in:: + + struct cfs_link_in { + ViceFid sourceFid; /* cnode to link *to* */ + ViceFid destFid; /* Directory in which to place link */ + char *tname; /* Place holder for data. */ + } cfs_link; + + + + out + + empty + + Description + This call creates a link to the sourceFid in the directory + identified by destFid with name tname. The source must reside in the + target's parent, i.e. the source must be have parent destFid, i.e. Coda + does not support cross directory hard links. Only the return value is + relevant. It indicates success or the type of failure. + + Errors + The usual errors can occur. + + +4.11. symlink +-------------- + + + Summary + create a symbolic link + + Arguments + in:: + + struct cfs_symlink_in { + ViceFid VFid; /* Directory to put symlink in */ + char *srcname; + struct coda_vattr attr; + char *tname; + } cfs_symlink; + + + + out + + none + + Description + Create a symbolic link. The link is to be placed in the + directory identified by VFid and named tname. It should point to the + pathname srcname. The attributes of the newly created object are to + be set to attr. + + .. Note:: + + The attributes of the target directory should be returned since + its size changed. + + +4.12. remove +------------- + + + Summary + Remove a file + + Arguments + in:: + + struct cfs_remove_in { + ViceFid VFid; + char *name; /* Place holder for data. */ + } cfs_remove; + + + + out + + none + + Description + Remove file named cfs_remove_in.name in directory + identified by VFid. + + + .. Note:: + + The attributes of the directory should be returned since its + mtime and size may change. + + +4.13. rmdir +------------ + + + Summary + Remove a directory + + Arguments + in:: + + struct cfs_rmdir_in { + ViceFid VFid; + char *name; /* Place holder for data. */ + } cfs_rmdir; + + + + out + + none + + Description + Remove the directory with name name from the directory + identified by VFid. + + .. Note:: The attributes of the parent directory should be returned since + its mtime and size may change. + + +4.14. readlink +--------------- + + + Summary + Read the value of a symbolic link. + + Arguments + in:: + + struct cfs_readlink_in { + ViceFid VFid; + } cfs_readlink; + + + + out:: + + struct cfs_readlink_out { + int count; + caddr_t data; /* Place holder for data. */ + } cfs_readlink; + + + + Description + This routine reads the contents of symbolic link + identified by VFid into the buffer data. The buffer data must be able + to hold any name up to CFS_MAXNAMLEN (PATH or NAM??). + + Errors + No unusual errors. + + +4.15. open +----------- + + + Summary + Open a file. + + Arguments + in:: + + struct cfs_open_in { + ViceFid VFid; + int flags; + } cfs_open; + + + + out:: + + struct cfs_open_out { + dev_t dev; + ino_t inode; + } cfs_open; + + + + Description + This request asks Venus to place the file identified by + VFid in its cache and to note that the calling process wishes to open + it with flags as in open(2). The return value to the kernel differs + for Unix and Windows systems. For Unix systems the Coda FS Driver is + informed of the device and inode number of the container file in the + fields dev and inode. For Windows the path of the container file is + returned to the kernel. + + + .. Note:: + + Currently the cfs_open_out structure is not properly adapted to + deal with the Windows case. It might be best to implement two + upcalls, one to open aiming at a container file name, the other at a + container file inode. + + +4.16. close +------------ + + + Summary + Close a file, update it on the servers. + + Arguments + in:: + + struct cfs_close_in { + ViceFid VFid; + int flags; + } cfs_close; + + + + out + + none + + Description + Close the file identified by VFid. + + .. Note:: + + The flags argument is bogus and not used. However, Venus' code + has room to deal with an execp input field, probably this field should + be used to inform Venus that the file was closed but is still memory + mapped for execution. There are comments about fetching versus not + fetching the data in Venus vproc_vfscalls. This seems silly. If a + file is being closed, the data in the container file is to be the new + data. Here again the execp flag might be in play to create confusion: + currently Venus might think a file can be flushed from the cache when + it is still memory mapped. This needs to be understood. + + +4.17. ioctl +------------ + + + Summary + Do an ioctl on a file. This includes the pioctl interface. + + Arguments + in:: + + struct cfs_ioctl_in { + ViceFid VFid; + int cmd; + int len; + int rwflag; + char *data; /* Place holder for data. */ + } cfs_ioctl; + + + + out:: + + + struct cfs_ioctl_out { + int len; + caddr_t data; /* Place holder for data. */ + } cfs_ioctl; + + + + Description + Do an ioctl operation on a file. The command, len and + data arguments are filled as usual. flags is not used by Venus. + + .. Note:: + + Another bogus parameter. flags is not used. What is the + business about PREFETCHING in the Venus code? + + + +4.18. rename +------------- + + + Summary + Rename a fid. + + Arguments + in:: + + struct cfs_rename_in { + ViceFid sourceFid; + char *srcname; + ViceFid destFid; + char *destname; + } cfs_rename; + + + + out + + none + + Description + Rename the object with name srcname in directory + sourceFid to destname in destFid. It is important that the names + srcname and destname are 0 terminated strings. Strings in Unix + kernels are not always null terminated. + + +4.19. readdir +-------------- + + + Summary + Read directory entries. + + Arguments + in:: + + struct cfs_readdir_in { + ViceFid VFid; + int count; + int offset; + } cfs_readdir; + + + + + out:: + + struct cfs_readdir_out { + int size; + caddr_t data; /* Place holder for data. */ + } cfs_readdir; + + + + Description + Read directory entries from VFid starting at offset and + read at most count bytes. Returns the data in data and returns + the size in size. + + + .. Note:: + + This call is not used. Readdir operations exploit container + files. We will re-evaluate this during the directory revamp which is + about to take place. + + +4.20. vget +----------- + + + Summary + instructs Venus to do an FSDB->Get. + + Arguments + in:: + + struct cfs_vget_in { + ViceFid VFid; + } cfs_vget; + + + + out:: + + struct cfs_vget_out { + ViceFid VFid; + int vtype; + } cfs_vget; + + + + Description + This upcall asks Venus to do a get operation on an fsobj + labelled by VFid. + + .. Note:: + + This operation is not used. However, it is extremely useful + since it can be used to deal with read/write memory mapped files. + These can be "pinned" in the Venus cache using vget and released with + inactive. + + +4.21. fsync +------------ + + + Summary + Tell Venus to update the RVM attributes of a file. + + Arguments + in:: + + struct cfs_fsync_in { + ViceFid VFid; + } cfs_fsync; + + + + out + + none + + Description + Ask Venus to update RVM attributes of object VFid. This + should be called as part of kernel level fsync type calls. The + result indicates if the syncing was successful. + + .. Note:: Linux does not implement this call. It should. + + +4.22. inactive +--------------- + + + Summary + Tell Venus a vnode is no longer in use. + + Arguments + in:: + + struct cfs_inactive_in { + ViceFid VFid; + } cfs_inactive; + + + + out + + none + + Description + This operation returns EOPNOTSUPP. + + .. Note:: This should perhaps be removed. + + +4.23. rdwr +----------- + + + Summary + Read or write from a file + + Arguments + in:: + + struct cfs_rdwr_in { + ViceFid VFid; + int rwflag; + int count; + int offset; + int ioflag; + caddr_t data; /* Place holder for data. */ + } cfs_rdwr; + + + + + out:: + + struct cfs_rdwr_out { + int rwflag; + int count; + caddr_t data; /* Place holder for data. */ + } cfs_rdwr; + + + + Description + This upcall asks Venus to read or write from a file. + + + .. Note:: + + It should be removed since it is against the Coda philosophy that + read/write operations never reach Venus. I have been told the + operation does not work. It is not currently used. + + + +4.24. odymount +--------------- + + + Summary + Allows mounting multiple Coda "filesystems" on one Unix mount point. + + Arguments + in:: + + struct ody_mount_in { + char *name; /* Place holder for data. */ + } ody_mount; + + + + out:: + + struct ody_mount_out { + ViceFid VFid; + } ody_mount; + + + + Description + Asks Venus to return the rootfid of a Coda system named + name. The fid is returned in VFid. + + .. Note:: + + This call was used by David for dynamic sets. It should be + removed since it causes a jungle of pointers in the VFS mounting area. + It is not used by Coda proper. Call is not implemented by Venus. + + +4.25. ody_lookup +----------------- + + + Summary + Looks up something. + + Arguments + in + + irrelevant + + + out + + irrelevant + + + .. Note:: Gut it. Call is not implemented by Venus. + + +4.26. ody_expand +----------------- + + + Summary + expands something in a dynamic set. + + Arguments + in + + irrelevant + + out + + irrelevant + + .. Note:: Gut it. Call is not implemented by Venus. + + +4.27. prefetch +--------------- + + + Summary + Prefetch a dynamic set. + + Arguments + + in + + Not documented. + + out + + Not documented. + + Description + Venus worker.cc has support for this call, although it is + noted that it doesn't work. Not surprising, since the kernel does not + have support for it. (ODY_PREFETCH is not a defined operation). + + + .. Note:: Gut it. It isn't working and isn't used by Coda. + + + +4.28. signal +------------- + + + Summary + Send Venus a signal about an upcall. + + Arguments + in + + none + + out + + not applicable. + + Description + This is an out-of-band upcall to Venus to inform Venus + that the calling process received a signal after Venus read the + message from the input queue. Venus is supposed to clean up the + operation. + + Errors + No reply is given. + + .. Note:: + + We need to better understand what Venus needs to clean up and if + it is doing this correctly. Also we need to handle multiple upcall + per system call situations correctly. It would be important to know + what state changes in Venus take place after an upcall for which the + kernel is responsible for notifying Venus to clean up (e.g. open + definitely is such a state change, but many others are maybe not). + + +5. The minicache and downcalls +=============================== + + + The Coda FS Driver can cache results of lookup and access upcalls, to + limit the frequency of upcalls. Upcalls carry a price since a process + context switch needs to take place. The counterpart of caching the + information is that Venus will notify the FS Driver that cached + entries must be flushed or renamed. + + The kernel code generally has to maintain a structure which links the + internal file handles (called vnodes in BSD, inodes in Linux and + FileHandles in Windows) with the ViceFid's which Venus maintains. The + reason is that frequent translations back and forth are needed in + order to make upcalls and use the results of upcalls. Such linking + objects are called cnodes. + + The current minicache implementations have cache entries which record + the following: + + 1. the name of the file + + 2. the cnode of the directory containing the object + + 3. a list of CodaCred's for which the lookup is permitted. + + 4. the cnode of the object + + The lookup call in the Coda FS Driver may request the cnode of the + desired object from the cache, by passing its name, directory and the + CodaCred's of the caller. The cache will return the cnode or indicate + that it cannot be found. The Coda FS Driver must be careful to + invalidate cache entries when it modifies or removes objects. + + When Venus obtains information that indicates that cache entries are + no longer valid, it will make a downcall to the kernel. Downcalls are + intercepted by the Coda FS Driver and lead to cache invalidations of + the kind described below. The Coda FS Driver does not return an error + unless the downcall data could not be read into kernel memory. + + +5.1. INVALIDATE +---------------- + + + No information is available on this call. + + +5.2. FLUSH +----------- + + + + Arguments + None + + Summary + Flush the name cache entirely. + + Description + Venus issues this call upon startup and when it dies. This + is to prevent stale cache information being held. Some operating + systems allow the kernel name cache to be switched off dynamically. + When this is done, this downcall is made. + + +5.3. PURGEUSER +--------------- + + + Arguments + :: + + struct cfs_purgeuser_out {/* CFS_PURGEUSER is a venus->kernel call */ + struct CodaCred cred; + } cfs_purgeuser; + + + + Description + Remove all entries in the cache carrying the Cred. This + call is issued when tokens for a user expire or are flushed. + + +5.4. ZAPFILE +------------- + + + Arguments + :: + + struct cfs_zapfile_out { /* CFS_ZAPFILE is a venus->kernel call */ + ViceFid CodaFid; + } cfs_zapfile; + + + + Description + Remove all entries which have the (dir vnode, name) pair. + This is issued as a result of an invalidation of cached attributes of + a vnode. + + .. Note:: + + Call is not named correctly in NetBSD and Mach. The minicache + zapfile routine takes different arguments. Linux does not implement + the invalidation of attributes correctly. + + + +5.5. ZAPDIR +------------ + + + Arguments + :: + + struct cfs_zapdir_out { /* CFS_ZAPDIR is a venus->kernel call */ + ViceFid CodaFid; + } cfs_zapdir; + + + + Description + Remove all entries in the cache lying in a directory + CodaFid, and all children of this directory. This call is issued when + Venus receives a callback on the directory. + + +5.6. ZAPVNODE +-------------- + + + + Arguments + :: + + struct cfs_zapvnode_out { /* CFS_ZAPVNODE is a venus->kernel call */ + struct CodaCred cred; + ViceFid VFid; + } cfs_zapvnode; + + + + Description + Remove all entries in the cache carrying the cred and VFid + as in the arguments. This downcall is probably never issued. + + +5.7. PURGEFID +-------------- + + + Arguments + :: + + struct cfs_purgefid_out { /* CFS_PURGEFID is a venus->kernel call */ + ViceFid CodaFid; + } cfs_purgefid; + + + + Description + Flush the attribute for the file. If it is a dir (odd + vnode), purge its children from the namecache and remove the file from the + namecache. + + + +5.8. REPLACE +------------- + + + Summary + Replace the Fid's for a collection of names. + + Arguments + :: + + struct cfs_replace_out { /* cfs_replace is a venus->kernel call */ + ViceFid NewFid; + ViceFid OldFid; + } cfs_replace; + + + + Description + This routine replaces a ViceFid in the name cache with + another. It is added to allow Venus during reintegration to replace + locally allocated temp fids while disconnected with global fids even + when the reference counts on those fids are not zero. + + +6. Initialization and cleanup +============================== + + + This section gives brief hints as to desirable features for the Coda + FS Driver at startup and upon shutdown or Venus failures. Before + entering the discussion it is useful to repeat that the Coda FS Driver + maintains the following data: + + + 1. message queues + + 2. cnodes + + 3. name cache entries + + The name cache entries are entirely private to the driver, so they + can easily be manipulated. The message queues will generally have + clear points of initialization and destruction. The cnodes are + much more delicate. User processes hold reference counts in Coda + filesystems and it can be difficult to clean up the cnodes. + + It can expect requests through: + + 1. the message subsystem + + 2. the VFS layer + + 3. pioctl interface + + Currently the pioctl passes through the VFS for Coda so we can + treat these similarly. + + +6.1. Requirements +------------------ + + + The following requirements should be accommodated: + + 1. The message queues should have open and close routines. On Unix + the opening of the character devices are such routines. + + - Before opening, no messages can be placed. + + - Opening will remove any old messages still pending. + + - Close will notify any sleeping processes that their upcall cannot + be completed. + + - Close will free all memory allocated by the message queues. + + + 2. At open the namecache shall be initialized to empty state. + + 3. Before the message queues are open, all VFS operations will fail. + Fortunately this can be achieved by making sure than mounting the + Coda filesystem cannot succeed before opening. + + 4. After closing of the queues, no VFS operations can succeed. Here + one needs to be careful, since a few operations (lookup, + read/write, readdir) can proceed without upcalls. These must be + explicitly blocked. + + 5. Upon closing the namecache shall be flushed and disabled. + + 6. All memory held by cnodes can be freed without relying on upcalls. + + 7. Unmounting the file system can be done without relying on upcalls. + + 8. Mounting the Coda filesystem should fail gracefully if Venus cannot + get the rootfid or the attributes of the rootfid. The latter is + best implemented by Venus fetching these objects before attempting + to mount. + + .. Note:: + + NetBSD in particular but also Linux have not implemented the + above requirements fully. For smooth operation this needs to be + corrected. + + + diff --git a/Documentation/filesystems/coda.txt b/Documentation/filesystems/coda.txt deleted file mode 100644 index 1711ad48e38a..000000000000 --- a/Documentation/filesystems/coda.txt +++ /dev/null @@ -1,1676 +0,0 @@ -NOTE: -This is one of the technical documents describing a component of -Coda -- this document describes the client kernel-Venus interface. - -For more information: - http://www.coda.cs.cmu.edu -For user level software needed to run Coda: - ftp://ftp.coda.cs.cmu.edu - -To run Coda you need to get a user level cache manager for the client, -named Venus, as well as tools to manipulate ACLs, to log in, etc. The -client needs to have the Coda filesystem selected in the kernel -configuration. - -The server needs a user level server and at present does not depend on -kernel support. - - - - - - - - The Venus kernel interface - Peter J. Braam - v1.0, Nov 9, 1997 - - This document describes the communication between Venus and kernel - level filesystem code needed for the operation of the Coda file sys- - tem. This document version is meant to describe the current interface - (version 1.0) as well as improvements we envisage. - ______________________________________________________________________ - - Table of Contents - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 1. Introduction - - 2. Servicing Coda filesystem calls - - 3. The message layer - - 3.1 Implementation details - - 4. The interface at the call level - - 4.1 Data structures shared by the kernel and Venus - 4.2 The pioctl interface - 4.3 root - 4.4 lookup - 4.5 getattr - 4.6 setattr - 4.7 access - 4.8 create - 4.9 mkdir - 4.10 link - 4.11 symlink - 4.12 remove - 4.13 rmdir - 4.14 readlink - 4.15 open - 4.16 close - 4.17 ioctl - 4.18 rename - 4.19 readdir - 4.20 vget - 4.21 fsync - 4.22 inactive - 4.23 rdwr - 4.24 odymount - 4.25 ody_lookup - 4.26 ody_expand - 4.27 prefetch - 4.28 signal - - 5. The minicache and downcalls - - 5.1 INVALIDATE - 5.2 FLUSH - 5.3 PURGEUSER - 5.4 ZAPFILE - 5.5 ZAPDIR - 5.6 ZAPVNODE - 5.7 PURGEFID - 5.8 REPLACE - - 6. Initialization and cleanup - - 6.1 Requirements - - - ______________________________________________________________________ - 0wpage - - 11.. IInnttrroodduuccttiioonn - - - - A key component in the Coda Distributed File System is the cache - manager, _V_e_n_u_s. - - - When processes on a Coda enabled system access files in the Coda - filesystem, requests are directed at the filesystem layer in the - operating system. The operating system will communicate with Venus to - service the request for the process. Venus manages a persistent - client cache and makes remote procedure calls to Coda file servers and - related servers (such as authentication servers) to service these - requests it receives from the operating system. When Venus has - serviced a request it replies to the operating system with appropriate - return codes, and other data related to the request. Optionally the - kernel support for Coda may maintain a minicache of recently processed - requests to limit the number of interactions with Venus. Venus - possesses the facility to inform the kernel when elements from its - minicache are no longer valid. - - This document describes precisely this communication between the - kernel and Venus. The definitions of so called upcalls and downcalls - will be given with the format of the data they handle. We shall also - describe the semantic invariants resulting from the calls. - - Historically Coda was implemented in a BSD file system in Mach 2.6. - The interface between the kernel and Venus is very similar to the BSD - VFS interface. Similar functionality is provided, and the format of - the parameters and returned data is very similar to the BSD VFS. This - leads to an almost natural environment for implementing a kernel-level - filesystem driver for Coda in a BSD system. However, other operating - systems such as Linux and Windows 95 and NT have virtual filesystem - with different interfaces. - - To implement Coda on these systems some reverse engineering of the - Venus/Kernel protocol is necessary. Also it came to light that other - systems could profit significantly from certain small optimizations - and modifications to the protocol. To facilitate this work as well as - to make future ports easier, communication between Venus and the - kernel should be documented in great detail. This is the aim of this - document. - - 0wpage - - 22.. SSeerrvviicciinngg CCooddaa ffiilleessyysstteemm ccaallllss - - The service of a request for a Coda file system service originates in - a process PP which accessing a Coda file. It makes a system call which - traps to the OS kernel. Examples of such calls trapping to the kernel - are _r_e_a_d_, _w_r_i_t_e_, _o_p_e_n_, _c_l_o_s_e_, _c_r_e_a_t_e_, _m_k_d_i_r_, _r_m_d_i_r_, _c_h_m_o_d in a Unix - context. Similar calls exist in the Win32 environment, and are named - _C_r_e_a_t_e_F_i_l_e_, . - - Generally the operating system handles the request in a virtual - filesystem (VFS) layer, which is named I/O Manager in NT and IFS - manager in Windows 95. The VFS is responsible for partial processing - of the request and for locating the specific filesystem(s) which will - service parts of the request. Usually the information in the path - assists in locating the correct FS drivers. Sometimes after extensive - pre-processing, the VFS starts invoking exported routines in the FS - driver. This is the point where the FS specific processing of the - request starts, and here the Coda specific kernel code comes into - play. - - The FS layer for Coda must expose and implement several interfaces. - First and foremost the VFS must be able to make all necessary calls to - the Coda FS layer, so the Coda FS driver must expose the VFS interface - as applicable in the operating system. These differ very significantly - among operating systems, but share features such as facilities to - read/write and create and remove objects. The Coda FS layer services - such VFS requests by invoking one or more well defined services - offered by the cache manager Venus. When the replies from Venus have - come back to the FS driver, servicing of the VFS call continues and - finishes with a reply to the kernel's VFS. Finally the VFS layer - returns to the process. - - As a result of this design a basic interface exposed by the FS driver - must allow Venus to manage message traffic. In particular Venus must - be able to retrieve and place messages and to be notified of the - arrival of a new message. The notification must be through a mechanism - which does not block Venus since Venus must attend to other tasks even - when no messages are waiting or being processed. - - - - - - - Interfaces of the Coda FS Driver - - Furthermore the FS layer provides for a special path of communication - between a user process and Venus, called the pioctl interface. The - pioctl interface is used for Coda specific services, such as - requesting detailed information about the persistent cache managed by - Venus. Here the involvement of the kernel is minimal. It identifies - the calling process and passes the information on to Venus. When - Venus replies the response is passed back to the caller in unmodified - form. - - Finally Venus allows the kernel FS driver to cache the results from - certain services. This is done to avoid excessive context switches - and results in an efficient system. However, Venus may acquire - information, for example from the network which implies that cached - information must be flushed or replaced. Venus then makes a downcall - to the Coda FS layer to request flushes or updates in the cache. The - kernel FS driver handles such requests synchronously. - - Among these interfaces the VFS interface and the facility to place, - receive and be notified of messages are platform specific. We will - not go into the calls exported to the VFS layer but we will state the - requirements of the message exchange mechanism. - - 0wpage - - 33.. TThhee mmeessssaaggee llaayyeerr - - - - At the lowest level the communication between Venus and the FS driver - proceeds through messages. The synchronization between processes - requesting Coda file service and Venus relies on blocking and waking - up processes. The Coda FS driver processes VFS- and pioctl-requests - on behalf of a process P, creates messages for Venus, awaits replies - and finally returns to the caller. The implementation of the exchange - of messages is platform specific, but the semantics have (so far) - appeared to be generally applicable. Data buffers are created by the - FS Driver in kernel memory on behalf of P and copied to user memory in - Venus. - - The FS Driver while servicing P makes upcalls to Venus. Such an - upcall is dispatched to Venus by creating a message structure. The - structure contains the identification of P, the message sequence - number, the size of the request and a pointer to the data in kernel - memory for the request. Since the data buffer is re-used to hold the - reply from Venus, there is a field for the size of the reply. A flags - field is used in the message to precisely record the status of the - message. Additional platform dependent structures involve pointers to - determine the position of the message on queues and pointers to - synchronization objects. In the upcall routine the message structure - is filled in, flags are set to 0, and it is placed on the _p_e_n_d_i_n_g - queue. The routine calling upcall is responsible for allocating the - data buffer; its structure will be described in the next section. - - A facility must exist to notify Venus that the message has been - created, and implemented using available synchronization objects in - the OS. This notification is done in the upcall context of the process - P. When the message is on the pending queue, process P cannot proceed - in upcall. The (kernel mode) processing of P in the filesystem - request routine must be suspended until Venus has replied. Therefore - the calling thread in P is blocked in upcall. A pointer in the - message structure will locate the synchronization object on which P is - sleeping. - - Venus detects the notification that a message has arrived, and the FS - driver allow Venus to retrieve the message with a getmsg_from_kernel - call. This action finishes in the kernel by putting the message on the - queue of processing messages and setting flags to READ. Venus is - passed the contents of the data buffer. The getmsg_from_kernel call - now returns and Venus processes the request. - - At some later point the FS driver receives a message from Venus, - namely when Venus calls sendmsg_to_kernel. At this moment the Coda FS - driver looks at the contents of the message and decides if: - - - +o the message is a reply for a suspended thread P. If so it removes - the message from the processing queue and marks the message as - WRITTEN. Finally, the FS driver unblocks P (still in the kernel - mode context of Venus) and the sendmsg_to_kernel call returns to - Venus. The process P will be scheduled at some point and continues - processing its upcall with the data buffer replaced with the reply - from Venus. - - +o The message is a _d_o_w_n_c_a_l_l. A downcall is a request from Venus to - the FS Driver. The FS driver processes the request immediately - (usually a cache eviction or replacement) and when it finishes - sendmsg_to_kernel returns. - - Now P awakes and continues processing upcall. There are some - subtleties to take account of. First P will determine if it was woken - up in upcall by a signal from some other source (for example an - attempt to terminate P) or as is normally the case by Venus in its - sendmsg_to_kernel call. In the normal case, the upcall routine will - deallocate the message structure and return. The FS routine can proceed - with its processing. - - - - - - - - Sleeping and IPC arrangements - - In case P is woken up by a signal and not by Venus, it will first look - at the flags field. If the message is not yet READ, the process P can - handle its signal without notifying Venus. If Venus has READ, and - the request should not be processed, P can send Venus a signal message - to indicate that it should disregard the previous message. Such - signals are put in the queue at the head, and read first by Venus. If - the message is already marked as WRITTEN it is too late to stop the - processing. The VFS routine will now continue. (-- If a VFS request - involves more than one upcall, this can lead to complicated state, an - extra field "handle_signals" could be added in the message structure - to indicate points of no return have been passed.--) - - - - 33..11.. IImmpplleemmeennttaattiioonn ddeettaaiillss - - The Unix implementation of this mechanism has been through the - implementation of a character device associated with Coda. Venus - retrieves messages by doing a read on the device, replies are sent - with a write and notification is through the select system call on the - file descriptor for the device. The process P is kept waiting on an - interruptible wait queue object. - - In Windows NT and the DPMI Windows 95 implementation a DeviceIoControl - call is used. The DeviceIoControl call is designed to copy buffers - from user memory to kernel memory with OPCODES. The sendmsg_to_kernel - is issued as a synchronous call, while the getmsg_from_kernel call is - asynchronous. Windows EventObjects are used for notification of - message arrival. The process P is kept waiting on a KernelEvent - object in NT and a semaphore in Windows 95. - - 0wpage - - 44.. TThhee iinntteerrffaaccee aatt tthhee ccaallll lleevveell - - - This section describes the upcalls a Coda FS driver can make to Venus. - Each of these upcalls make use of two structures: inputArgs and - outputArgs. In pseudo BNF form the structures take the following - form: - - - struct inputArgs { - u_long opcode; - u_long unique; /* Keep multiple outstanding msgs distinct */ - u_short pid; /* Common to all */ - u_short pgid; /* Common to all */ - struct CodaCred cred; /* Common to all */ - - <union "in" of call dependent parts of inputArgs> - }; - - struct outputArgs { - u_long opcode; - u_long unique; /* Keep multiple outstanding msgs distinct */ - u_long result; - - <union "out" of call dependent parts of inputArgs> - }; - - - - Before going on let us elucidate the role of the various fields. The - inputArgs start with the opcode which defines the type of service - requested from Venus. There are approximately 30 upcalls at present - which we will discuss. The unique field labels the inputArg with a - unique number which will identify the message uniquely. A process and - process group id are passed. Finally the credentials of the caller - are included. - - Before delving into the specific calls we need to discuss a variety of - data structures shared by the kernel and Venus. - - - - - 44..11.. DDaattaa ssttrruuccttuurreess sshhaarreedd bbyy tthhee kkeerrnneell aanndd VVeennuuss - - - The CodaCred structure defines a variety of user and group ids as - they are set for the calling process. The vuid_t and vgid_t are 32 bit - unsigned integers. It also defines group membership in an array. On - Unix the CodaCred has proven sufficient to implement good security - semantics for Coda but the structure may have to undergo modification - for the Windows environment when these mature. - - struct CodaCred { - vuid_t cr_uid, cr_euid, cr_suid, cr_fsuid; /* Real, effective, set, fs uid */ - vgid_t cr_gid, cr_egid, cr_sgid, cr_fsgid; /* same for groups */ - vgid_t cr_groups[NGROUPS]; /* Group membership for caller */ - }; - - - - NNOOTTEE It is questionable if we need CodaCreds in Venus. Finally Venus - doesn't know about groups, although it does create files with the - default uid/gid. Perhaps the list of group membership is superfluous. - - - The next item is the fundamental identifier used to identify Coda - files, the ViceFid. A fid of a file uniquely defines a file or - directory in the Coda filesystem within a _c_e_l_l. (-- A _c_e_l_l is a - group of Coda servers acting under the aegis of a single system - control machine or SCM. See the Coda Administration manual for a - detailed description of the role of the SCM.--) - - - typedef struct ViceFid { - VolumeId Volume; - VnodeId Vnode; - Unique_t Unique; - } ViceFid; - - - - Each of the constituent fields: VolumeId, VnodeId and Unique_t are - unsigned 32 bit integers. We envisage that a further field will need - to be prefixed to identify the Coda cell; this will probably take the - form of a Ipv6 size IP address naming the Coda cell through DNS. - - The next important structure shared between Venus and the kernel is - the attributes of the file. The following structure is used to - exchange information. It has room for future extensions such as - support for device files (currently not present in Coda). - - - - - - - - - - - - - - - - - struct coda_timespec { - int64_t tv_sec; /* seconds */ - long tv_nsec; /* nanoseconds */ - }; - - struct coda_vattr { - enum coda_vtype va_type; /* vnode type (for create) */ - u_short va_mode; /* files access mode and type */ - short va_nlink; /* number of references to file */ - vuid_t va_uid; /* owner user id */ - vgid_t va_gid; /* owner group id */ - long va_fsid; /* file system id (dev for now) */ - long va_fileid; /* file id */ - u_quad_t va_size; /* file size in bytes */ - long va_blocksize; /* blocksize preferred for i/o */ - struct coda_timespec va_atime; /* time of last access */ - struct coda_timespec va_mtime; /* time of last modification */ - struct coda_timespec va_ctime; /* time file changed */ - u_long va_gen; /* generation number of file */ - u_long va_flags; /* flags defined for file */ - dev_t va_rdev; /* device special file represents */ - u_quad_t va_bytes; /* bytes of disk space held by file */ - u_quad_t va_filerev; /* file modification number */ - u_int va_vaflags; /* operations flags, see below */ - long va_spare; /* remain quad aligned */ - }; - - - - - 44..22.. TThhee ppiiooccttll iinntteerrffaaccee - - - Coda specific requests can be made by application through the pioctl - interface. The pioctl is implemented as an ordinary ioctl on a - fictitious file /coda/.CONTROL. The pioctl call opens this file, gets - a file handle and makes the ioctl call. Finally it closes the file. - - The kernel involvement in this is limited to providing the facility to - open and close and pass the ioctl message _a_n_d to verify that a path in - the pioctl data buffers is a file in a Coda filesystem. - - The kernel is handed a data packet of the form: - - struct { - const char *path; - struct ViceIoctl vidata; - int follow; - } data; - - - - where - - - struct ViceIoctl { - caddr_t in, out; /* Data to be transferred in, or out */ - short in_size; /* Size of input buffer <= 2K */ - short out_size; /* Maximum size of output buffer, <= 2K */ - }; - - - - The path must be a Coda file, otherwise the ioctl upcall will not be - made. - - NNOOTTEE The data structures and code are a mess. We need to clean this - up. - - We now proceed to document the individual calls: - - 0wpage - - 44..33.. rroooott - - - AArrgguummeennttss - - iinn empty - - oouutt - - struct cfs_root_out { - ViceFid VFid; - } cfs_root; - - - - DDeessccrriippttiioonn This call is made to Venus during the initialization of - the Coda filesystem. If the result is zero, the cfs_root structure - contains the ViceFid of the root of the Coda filesystem. If a non-zero - result is generated, its value is a platform dependent error code - indicating the difficulty Venus encountered in locating the root of - the Coda filesystem. - - 0wpage - - 44..44.. llooookkuupp - - - SSuummmmaarryy Find the ViceFid and type of an object in a directory if it - exists. - - AArrgguummeennttss - - iinn - - struct cfs_lookup_in { - ViceFid VFid; - char *name; /* Place holder for data. */ - } cfs_lookup; - - - - oouutt - - struct cfs_lookup_out { - ViceFid VFid; - int vtype; - } cfs_lookup; - - - - DDeessccrriippttiioonn This call is made to determine the ViceFid and filetype of - a directory entry. The directory entry requested carries name name - and Venus will search the directory identified by cfs_lookup_in.VFid. - The result may indicate that the name does not exist, or that - difficulty was encountered in finding it (e.g. due to disconnection). - If the result is zero, the field cfs_lookup_out.VFid contains the - targets ViceFid and cfs_lookup_out.vtype the coda_vtype giving the - type of object the name designates. - - The name of the object is an 8 bit character string of maximum length - CFS_MAXNAMLEN, currently set to 256 (including a 0 terminator.) - - It is extremely important to realize that Venus bitwise ors the field - cfs_lookup.vtype with CFS_NOCACHE to indicate that the object should - not be put in the kernel name cache. - - NNOOTTEE The type of the vtype is currently wrong. It should be - coda_vtype. Linux does not take note of CFS_NOCACHE. It should. - - 0wpage - - 44..55.. ggeettaattttrr - - - SSuummmmaarryy Get the attributes of a file. - - AArrgguummeennttss - - iinn - - struct cfs_getattr_in { - ViceFid VFid; - struct coda_vattr attr; /* XXXXX */ - } cfs_getattr; - - - - oouutt - - struct cfs_getattr_out { - struct coda_vattr attr; - } cfs_getattr; - - - - DDeessccrriippttiioonn This call returns the attributes of the file identified by - fid. - - EErrrroorrss Errors can occur if the object with fid does not exist, is - unaccessible or if the caller does not have permission to fetch - attributes. - - NNoottee Many kernel FS drivers (Linux, NT and Windows 95) need to acquire - the attributes as well as the Fid for the instantiation of an internal - "inode" or "FileHandle". A significant improvement in performance on - such systems could be made by combining the _l_o_o_k_u_p and _g_e_t_a_t_t_r calls - both at the Venus/kernel interaction level and at the RPC level. - - The vattr structure included in the input arguments is superfluous and - should be removed. - - 0wpage - - 44..66.. sseettaattttrr - - - SSuummmmaarryy Set the attributes of a file. - - AArrgguummeennttss - - iinn - - struct cfs_setattr_in { - ViceFid VFid; - struct coda_vattr attr; - } cfs_setattr; - - - - - oouutt - empty - - DDeessccrriippttiioonn The structure attr is filled with attributes to be changed - in BSD style. Attributes not to be changed are set to -1, apart from - vtype which is set to VNON. Other are set to the value to be assigned. - The only attributes which the FS driver may request to change are the - mode, owner, groupid, atime, mtime and ctime. The return value - indicates success or failure. - - EErrrroorrss A variety of errors can occur. The object may not exist, may - be inaccessible, or permission may not be granted by Venus. - - 0wpage - - 44..77.. aacccceessss - - - SSuummmmaarryy - - AArrgguummeennttss - - iinn - - struct cfs_access_in { - ViceFid VFid; - int flags; - } cfs_access; - - - - oouutt - empty - - DDeessccrriippttiioonn Verify if access to the object identified by VFid for - operations described by flags is permitted. The result indicates if - access will be granted. It is important to remember that Coda uses - ACLs to enforce protection and that ultimately the servers, not the - clients enforce the security of the system. The result of this call - will depend on whether a _t_o_k_e_n is held by the user. - - EErrrroorrss The object may not exist, or the ACL describing the protection - may not be accessible. - - 0wpage - - 44..88.. ccrreeaattee - - - SSuummmmaarryy Invoked to create a file - - AArrgguummeennttss - - iinn - - struct cfs_create_in { - ViceFid VFid; - struct coda_vattr attr; - int excl; - int mode; - char *name; /* Place holder for data. */ - } cfs_create; - - - - - oouutt - - struct cfs_create_out { - ViceFid VFid; - struct coda_vattr attr; - } cfs_create; - - - - DDeessccrriippttiioonn This upcall is invoked to request creation of a file. - The file will be created in the directory identified by VFid, its name - will be name, and the mode will be mode. If excl is set an error will - be returned if the file already exists. If the size field in attr is - set to zero the file will be truncated. The uid and gid of the file - are set by converting the CodaCred to a uid using a macro CRTOUID - (this macro is platform dependent). Upon success the VFid and - attributes of the file are returned. The Coda FS Driver will normally - instantiate a vnode, inode or file handle at kernel level for the new - object. - - - EErrrroorrss A variety of errors can occur. Permissions may be insufficient. - If the object exists and is not a file the error EISDIR is returned - under Unix. - - NNOOTTEE The packing of parameters is very inefficient and appears to - indicate confusion between the system call creat and the VFS operation - create. The VFS operation create is only called to create new objects. - This create call differs from the Unix one in that it is not invoked - to return a file descriptor. The truncate and exclusive options, - together with the mode, could simply be part of the mode as it is - under Unix. There should be no flags argument; this is used in open - (2) to return a file descriptor for READ or WRITE mode. - - The attributes of the directory should be returned too, since the size - and mtime changed. - - 0wpage - - 44..99.. mmkkddiirr - - - SSuummmmaarryy Create a new directory. - - AArrgguummeennttss - - iinn - - struct cfs_mkdir_in { - ViceFid VFid; - struct coda_vattr attr; - char *name; /* Place holder for data. */ - } cfs_mkdir; - - - - oouutt - - struct cfs_mkdir_out { - ViceFid VFid; - struct coda_vattr attr; - } cfs_mkdir; - - - - - DDeessccrriippttiioonn This call is similar to create but creates a directory. - Only the mode field in the input parameters is used for creation. - Upon successful creation, the attr returned contains the attributes of - the new directory. - - EErrrroorrss As for create. - - NNOOTTEE The input parameter should be changed to mode instead of - attributes. - - The attributes of the parent should be returned since the size and - mtime changes. - - 0wpage - - 44..1100.. lliinnkk - - - SSuummmmaarryy Create a link to an existing file. - - AArrgguummeennttss - - iinn - - struct cfs_link_in { - ViceFid sourceFid; /* cnode to link *to* */ - ViceFid destFid; /* Directory in which to place link */ - char *tname; /* Place holder for data. */ - } cfs_link; - - - - oouutt - empty - - DDeessccrriippttiioonn This call creates a link to the sourceFid in the directory - identified by destFid with name tname. The source must reside in the - target's parent, i.e. the source must be have parent destFid, i.e. Coda - does not support cross directory hard links. Only the return value is - relevant. It indicates success or the type of failure. - - EErrrroorrss The usual errors can occur.0wpage - - 44..1111.. ssyymmlliinnkk - - - SSuummmmaarryy create a symbolic link - - AArrgguummeennttss - - iinn - - struct cfs_symlink_in { - ViceFid VFid; /* Directory to put symlink in */ - char *srcname; - struct coda_vattr attr; - char *tname; - } cfs_symlink; - - - - oouutt - none - - DDeessccrriippttiioonn Create a symbolic link. The link is to be placed in the - directory identified by VFid and named tname. It should point to the - pathname srcname. The attributes of the newly created object are to - be set to attr. - - EErrrroorrss - - NNOOTTEE The attributes of the target directory should be returned since - its size changed. - - 0wpage - - 44..1122.. rreemmoovvee - - - SSuummmmaarryy Remove a file - - AArrgguummeennttss - - iinn - - struct cfs_remove_in { - ViceFid VFid; - char *name; /* Place holder for data. */ - } cfs_remove; - - - - oouutt - none - - DDeessccrriippttiioonn Remove file named cfs_remove_in.name in directory - identified by VFid. - - EErrrroorrss - - NNOOTTEE The attributes of the directory should be returned since its - mtime and size may change. - - 0wpage - - 44..1133.. rrmmddiirr - - - SSuummmmaarryy Remove a directory - - AArrgguummeennttss - - iinn - - struct cfs_rmdir_in { - ViceFid VFid; - char *name; /* Place holder for data. */ - } cfs_rmdir; - - - - oouutt - none - - DDeessccrriippttiioonn Remove the directory with name name from the directory - identified by VFid. - - EErrrroorrss - - NNOOTTEE The attributes of the parent directory should be returned since - its mtime and size may change. - - 0wpage - - 44..1144.. rreeaaddlliinnkk - - - SSuummmmaarryy Read the value of a symbolic link. - - AArrgguummeennttss - - iinn - - struct cfs_readlink_in { - ViceFid VFid; - } cfs_readlink; - - - - oouutt - - struct cfs_readlink_out { - int count; - caddr_t data; /* Place holder for data. */ - } cfs_readlink; - - - - DDeessccrriippttiioonn This routine reads the contents of symbolic link - identified by VFid into the buffer data. The buffer data must be able - to hold any name up to CFS_MAXNAMLEN (PATH or NAM??). - - EErrrroorrss No unusual errors. - - 0wpage - - 44..1155.. ooppeenn - - - SSuummmmaarryy Open a file. - - AArrgguummeennttss - - iinn - - struct cfs_open_in { - ViceFid VFid; - int flags; - } cfs_open; - - - - oouutt - - struct cfs_open_out { - dev_t dev; - ino_t inode; - } cfs_open; - - - - DDeessccrriippttiioonn This request asks Venus to place the file identified by - VFid in its cache and to note that the calling process wishes to open - it with flags as in open(2). The return value to the kernel differs - for Unix and Windows systems. For Unix systems the Coda FS Driver is - informed of the device and inode number of the container file in the - fields dev and inode. For Windows the path of the container file is - returned to the kernel. - EErrrroorrss - - NNOOTTEE Currently the cfs_open_out structure is not properly adapted to - deal with the Windows case. It might be best to implement two - upcalls, one to open aiming at a container file name, the other at a - container file inode. - - 0wpage - - 44..1166.. cclloossee - - - SSuummmmaarryy Close a file, update it on the servers. - - AArrgguummeennttss - - iinn - - struct cfs_close_in { - ViceFid VFid; - int flags; - } cfs_close; - - - - oouutt - none - - DDeessccrriippttiioonn Close the file identified by VFid. - - EErrrroorrss - - NNOOTTEE The flags argument is bogus and not used. However, Venus' code - has room to deal with an execp input field, probably this field should - be used to inform Venus that the file was closed but is still memory - mapped for execution. There are comments about fetching versus not - fetching the data in Venus vproc_vfscalls. This seems silly. If a - file is being closed, the data in the container file is to be the new - data. Here again the execp flag might be in play to create confusion: - currently Venus might think a file can be flushed from the cache when - it is still memory mapped. This needs to be understood. - - 0wpage - - 44..1177.. iiooccttll - - - SSuummmmaarryy Do an ioctl on a file. This includes the pioctl interface. - - AArrgguummeennttss - - iinn - - struct cfs_ioctl_in { - ViceFid VFid; - int cmd; - int len; - int rwflag; - char *data; /* Place holder for data. */ - } cfs_ioctl; - - - - oouutt - - - struct cfs_ioctl_out { - int len; - caddr_t data; /* Place holder for data. */ - } cfs_ioctl; - - - - DDeessccrriippttiioonn Do an ioctl operation on a file. The command, len and - data arguments are filled as usual. flags is not used by Venus. - - EErrrroorrss - - NNOOTTEE Another bogus parameter. flags is not used. What is the - business about PREFETCHING in the Venus code? - - - 0wpage - - 44..1188.. rreennaammee - - - SSuummmmaarryy Rename a fid. - - AArrgguummeennttss - - iinn - - struct cfs_rename_in { - ViceFid sourceFid; - char *srcname; - ViceFid destFid; - char *destname; - } cfs_rename; - - - - oouutt - none - - DDeessccrriippttiioonn Rename the object with name srcname in directory - sourceFid to destname in destFid. It is important that the names - srcname and destname are 0 terminated strings. Strings in Unix - kernels are not always null terminated. - - EErrrroorrss - - 0wpage - - 44..1199.. rreeaaddddiirr - - - SSuummmmaarryy Read directory entries. - - AArrgguummeennttss - - iinn - - struct cfs_readdir_in { - ViceFid VFid; - int count; - int offset; - } cfs_readdir; - - - - - oouutt - - struct cfs_readdir_out { - int size; - caddr_t data; /* Place holder for data. */ - } cfs_readdir; - - - - DDeessccrriippttiioonn Read directory entries from VFid starting at offset and - read at most count bytes. Returns the data in data and returns - the size in size. - - EErrrroorrss - - NNOOTTEE This call is not used. Readdir operations exploit container - files. We will re-evaluate this during the directory revamp which is - about to take place. - - 0wpage - - 44..2200.. vvggeett - - - SSuummmmaarryy instructs Venus to do an FSDB->Get. - - AArrgguummeennttss - - iinn - - struct cfs_vget_in { - ViceFid VFid; - } cfs_vget; - - - - oouutt - - struct cfs_vget_out { - ViceFid VFid; - int vtype; - } cfs_vget; - - - - DDeessccrriippttiioonn This upcall asks Venus to do a get operation on an fsobj - labelled by VFid. - - EErrrroorrss - - NNOOTTEE This operation is not used. However, it is extremely useful - since it can be used to deal with read/write memory mapped files. - These can be "pinned" in the Venus cache using vget and released with - inactive. - - 0wpage - - 44..2211.. ffssyynncc - - - SSuummmmaarryy Tell Venus to update the RVM attributes of a file. - - AArrgguummeennttss - - iinn - - struct cfs_fsync_in { - ViceFid VFid; - } cfs_fsync; - - - - oouutt - none - - DDeessccrriippttiioonn Ask Venus to update RVM attributes of object VFid. This - should be called as part of kernel level fsync type calls. The - result indicates if the syncing was successful. - - EErrrroorrss - - NNOOTTEE Linux does not implement this call. It should. - - 0wpage - - 44..2222.. iinnaaccttiivvee - - - SSuummmmaarryy Tell Venus a vnode is no longer in use. - - AArrgguummeennttss - - iinn - - struct cfs_inactive_in { - ViceFid VFid; - } cfs_inactive; - - - - oouutt - none - - DDeessccrriippttiioonn This operation returns EOPNOTSUPP. - - EErrrroorrss - - NNOOTTEE This should perhaps be removed. - - 0wpage - - 44..2233.. rrddwwrr - - - SSuummmmaarryy Read or write from a file - - AArrgguummeennttss - - iinn - - struct cfs_rdwr_in { - ViceFid VFid; - int rwflag; - int count; - int offset; - int ioflag; - caddr_t data; /* Place holder for data. */ - } cfs_rdwr; - - - - - oouutt - - struct cfs_rdwr_out { - int rwflag; - int count; - caddr_t data; /* Place holder for data. */ - } cfs_rdwr; - - - - DDeessccrriippttiioonn This upcall asks Venus to read or write from a file. - - EErrrroorrss - - NNOOTTEE It should be removed since it is against the Coda philosophy that - read/write operations never reach Venus. I have been told the - operation does not work. It is not currently used. - - - 0wpage - - 44..2244.. ooddyymmoouunntt - - - SSuummmmaarryy Allows mounting multiple Coda "filesystems" on one Unix mount - point. - - AArrgguummeennttss - - iinn - - struct ody_mount_in { - char *name; /* Place holder for data. */ - } ody_mount; - - - - oouutt - - struct ody_mount_out { - ViceFid VFid; - } ody_mount; - - - - DDeessccrriippttiioonn Asks Venus to return the rootfid of a Coda system named - name. The fid is returned in VFid. - - EErrrroorrss - - NNOOTTEE This call was used by David for dynamic sets. It should be - removed since it causes a jungle of pointers in the VFS mounting area. - It is not used by Coda proper. Call is not implemented by Venus. - - 0wpage - - 44..2255.. ooddyy__llooookkuupp - - - SSuummmmaarryy Looks up something. - - AArrgguummeennttss - - iinn irrelevant - - - oouutt - irrelevant - - DDeessccrriippttiioonn - - EErrrroorrss - - NNOOTTEE Gut it. Call is not implemented by Venus. - - 0wpage - - 44..2266.. ooddyy__eexxppaanndd - - - SSuummmmaarryy expands something in a dynamic set. - - AArrgguummeennttss - - iinn irrelevant - - oouutt - irrelevant - - DDeessccrriippttiioonn - - EErrrroorrss - - NNOOTTEE Gut it. Call is not implemented by Venus. - - 0wpage - - 44..2277.. pprreeffeettcchh - - - SSuummmmaarryy Prefetch a dynamic set. - - AArrgguummeennttss - - iinn Not documented. - - oouutt - Not documented. - - DDeessccrriippttiioonn Venus worker.cc has support for this call, although it is - noted that it doesn't work. Not surprising, since the kernel does not - have support for it. (ODY_PREFETCH is not a defined operation). - - EErrrroorrss - - NNOOTTEE Gut it. It isn't working and isn't used by Coda. - - - 0wpage - - 44..2288.. ssiiggnnaall - - - SSuummmmaarryy Send Venus a signal about an upcall. - - AArrgguummeennttss - - iinn none - - oouutt - not applicable. - - DDeessccrriippttiioonn This is an out-of-band upcall to Venus to inform Venus - that the calling process received a signal after Venus read the - message from the input queue. Venus is supposed to clean up the - operation. - - EErrrroorrss No reply is given. - - NNOOTTEE We need to better understand what Venus needs to clean up and if - it is doing this correctly. Also we need to handle multiple upcall - per system call situations correctly. It would be important to know - what state changes in Venus take place after an upcall for which the - kernel is responsible for notifying Venus to clean up (e.g. open - definitely is such a state change, but many others are maybe not). - - 0wpage - - 55.. TThhee mmiinniiccaacchhee aanndd ddoowwnnccaallllss - - - The Coda FS Driver can cache results of lookup and access upcalls, to - limit the frequency of upcalls. Upcalls carry a price since a process - context switch needs to take place. The counterpart of caching the - information is that Venus will notify the FS Driver that cached - entries must be flushed or renamed. - - The kernel code generally has to maintain a structure which links the - internal file handles (called vnodes in BSD, inodes in Linux and - FileHandles in Windows) with the ViceFid's which Venus maintains. The - reason is that frequent translations back and forth are needed in - order to make upcalls and use the results of upcalls. Such linking - objects are called ccnnooddeess. - - The current minicache implementations have cache entries which record - the following: - - 1. the name of the file - - 2. the cnode of the directory containing the object - - 3. a list of CodaCred's for which the lookup is permitted. - - 4. the cnode of the object - - The lookup call in the Coda FS Driver may request the cnode of the - desired object from the cache, by passing its name, directory and the - CodaCred's of the caller. The cache will return the cnode or indicate - that it cannot be found. The Coda FS Driver must be careful to - invalidate cache entries when it modifies or removes objects. - - When Venus obtains information that indicates that cache entries are - no longer valid, it will make a downcall to the kernel. Downcalls are - intercepted by the Coda FS Driver and lead to cache invalidations of - the kind described below. The Coda FS Driver does not return an error - unless the downcall data could not be read into kernel memory. - - - 55..11.. IINNVVAALLIIDDAATTEE - - - No information is available on this call. - - - 55..22.. FFLLUUSSHH - - - - AArrgguummeennttss None - - SSuummmmaarryy Flush the name cache entirely. - - DDeessccrriippttiioonn Venus issues this call upon startup and when it dies. This - is to prevent stale cache information being held. Some operating - systems allow the kernel name cache to be switched off dynamically. - When this is done, this downcall is made. - - - 55..33.. PPUURRGGEEUUSSEERR - - - AArrgguummeennttss - - struct cfs_purgeuser_out {/* CFS_PURGEUSER is a venus->kernel call */ - struct CodaCred cred; - } cfs_purgeuser; - - - - DDeessccrriippttiioonn Remove all entries in the cache carrying the Cred. This - call is issued when tokens for a user expire or are flushed. - - - 55..44.. ZZAAPPFFIILLEE - - - AArrgguummeennttss - - struct cfs_zapfile_out { /* CFS_ZAPFILE is a venus->kernel call */ - ViceFid CodaFid; - } cfs_zapfile; - - - - DDeessccrriippttiioonn Remove all entries which have the (dir vnode, name) pair. - This is issued as a result of an invalidation of cached attributes of - a vnode. - - NNOOTTEE Call is not named correctly in NetBSD and Mach. The minicache - zapfile routine takes different arguments. Linux does not implement - the invalidation of attributes correctly. - - - - 55..55.. ZZAAPPDDIIRR - - - AArrgguummeennttss - - struct cfs_zapdir_out { /* CFS_ZAPDIR is a venus->kernel call */ - ViceFid CodaFid; - } cfs_zapdir; - - - - DDeessccrriippttiioonn Remove all entries in the cache lying in a directory - CodaFid, and all children of this directory. This call is issued when - Venus receives a callback on the directory. - - - 55..66.. ZZAAPPVVNNOODDEE - - - - AArrgguummeennttss - - struct cfs_zapvnode_out { /* CFS_ZAPVNODE is a venus->kernel call */ - struct CodaCred cred; - ViceFid VFid; - } cfs_zapvnode; - - - - DDeessccrriippttiioonn Remove all entries in the cache carrying the cred and VFid - as in the arguments. This downcall is probably never issued. - - - 55..77.. PPUURRGGEEFFIIDD - - - SSuummmmaarryy - - AArrgguummeennttss - - struct cfs_purgefid_out { /* CFS_PURGEFID is a venus->kernel call */ - ViceFid CodaFid; - } cfs_purgefid; - - - - DDeessccrriippttiioonn Flush the attribute for the file. If it is a dir (odd - vnode), purge its children from the namecache and remove the file from the - namecache. - - - - 55..88.. RREEPPLLAACCEE - - - SSuummmmaarryy Replace the Fid's for a collection of names. - - AArrgguummeennttss - - struct cfs_replace_out { /* cfs_replace is a venus->kernel call */ - ViceFid NewFid; - ViceFid OldFid; - } cfs_replace; - - - - DDeessccrriippttiioonn This routine replaces a ViceFid in the name cache with - another. It is added to allow Venus during reintegration to replace - locally allocated temp fids while disconnected with global fids even - when the reference counts on those fids are not zero. - - 0wpage - - 66.. IInniittiiaalliizzaattiioonn aanndd cclleeaannuupp - - - This section gives brief hints as to desirable features for the Coda - FS Driver at startup and upon shutdown or Venus failures. Before - entering the discussion it is useful to repeat that the Coda FS Driver - maintains the following data: - - - 1. message queues - - 2. cnodes - - 3. name cache entries - - The name cache entries are entirely private to the driver, so they - can easily be manipulated. The message queues will generally have - clear points of initialization and destruction. The cnodes are - much more delicate. User processes hold reference counts in Coda - filesystems and it can be difficult to clean up the cnodes. - - It can expect requests through: - - 1. the message subsystem - - 2. the VFS layer - - 3. pioctl interface - - Currently the _p_i_o_c_t_l passes through the VFS for Coda so we can - treat these similarly. - - - 66..11.. RReeqquuiirreemmeennttss - - - The following requirements should be accommodated: - - 1. The message queues should have open and close routines. On Unix - the opening of the character devices are such routines. - - +o Before opening, no messages can be placed. - - +o Opening will remove any old messages still pending. - - +o Close will notify any sleeping processes that their upcall cannot - be completed. - - +o Close will free all memory allocated by the message queues. - - - 2. At open the namecache shall be initialized to empty state. - - 3. Before the message queues are open, all VFS operations will fail. - Fortunately this can be achieved by making sure than mounting the - Coda filesystem cannot succeed before opening. - - 4. After closing of the queues, no VFS operations can succeed. Here - one needs to be careful, since a few operations (lookup, - read/write, readdir) can proceed without upcalls. These must be - explicitly blocked. - - 5. Upon closing the namecache shall be flushed and disabled. - - 6. All memory held by cnodes can be freed without relying on upcalls. - - 7. Unmounting the file system can be done without relying on upcalls. - - 8. Mounting the Coda filesystem should fail gracefully if Venus cannot - get the rootfid or the attributes of the rootfid. The latter is - best implemented by Venus fetching these objects before attempting - to mount. - - NNOOTTEE NetBSD in particular but also Linux have not implemented the - above requirements fully. For smooth operation this needs to be - corrected. - - - diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs.rst index 16e606c11f40..f8941954c667 100644 --- a/Documentation/filesystems/configfs/configfs.txt +++ b/Documentation/filesystems/configfs.rst @@ -1,5 +1,6 @@ - -configfs - Userspace-driven kernel object configuration. +======================================================= +Configfs - Userspace-driven Kernel Object Configuration +======================================================= Joel Becker <joel.becker@oracle.com> @@ -9,7 +10,8 @@ Copyright (c) 2005 Oracle Corporation, Joel Becker <joel.becker@oracle.com> -[What is configfs?] +What is configfs? +================= configfs is a ram-based filesystem that provides the converse of sysfs's functionality. Where sysfs is a filesystem-based view of @@ -35,10 +37,11 @@ kernel modules backing the items must respond to this. Both sysfs and configfs can and should exist together on the same system. One is not a replacement for the other. -[Using configfs] +Using configfs +============== configfs can be compiled as a module or into the kernel. You can access -it by doing +it by doing:: mount -t configfs none /config @@ -56,28 +59,29 @@ values. Don't mix more than one attribute in one attribute file. There are two types of configfs attributes: * Normal attributes, which similar to sysfs attributes, are small ASCII text -files, with a maximum size of one page (PAGE_SIZE, 4096 on i386). Preferably -only one value per file should be used, and the same caveats from sysfs apply. -Configfs expects write(2) to store the entire buffer at once. When writing to -normal configfs attributes, userspace processes should first read the entire -file, modify the portions they wish to change, and then write the entire -buffer back. + files, with a maximum size of one page (PAGE_SIZE, 4096 on i386). Preferably + only one value per file should be used, and the same caveats from sysfs apply. + Configfs expects write(2) to store the entire buffer at once. When writing to + normal configfs attributes, userspace processes should first read the entire + file, modify the portions they wish to change, and then write the entire + buffer back. * Binary attributes, which are somewhat similar to sysfs binary attributes, -but with a few slight changes to semantics. The PAGE_SIZE limitation does not -apply, but the whole binary item must fit in single kernel vmalloc'ed buffer. -The write(2) calls from user space are buffered, and the attributes' -write_bin_attribute method will be invoked on the final close, therefore it is -imperative for user-space to check the return code of close(2) in order to -verify that the operation finished successfully. -To avoid a malicious user OOMing the kernel, there's a per-binary attribute -maximum buffer value. + but with a few slight changes to semantics. The PAGE_SIZE limitation does not + apply, but the whole binary item must fit in single kernel vmalloc'ed buffer. + The write(2) calls from user space are buffered, and the attributes' + write_bin_attribute method will be invoked on the final close, therefore it is + imperative for user-space to check the return code of close(2) in order to + verify that the operation finished successfully. + To avoid a malicious user OOMing the kernel, there's a per-binary attribute + maximum buffer value. When an item needs to be destroyed, remove it with rmdir(2). An item cannot be destroyed if any other item has a link to it (via symlink(2)). Links can be removed via unlink(2). -[Configuring FakeNBD: an Example] +Configuring FakeNBD: an Example +=============================== Imagine there's a Network Block Device (NBD) driver that allows you to access remote block devices. Call it FakeNBD. FakeNBD uses configfs @@ -86,14 +90,14 @@ sysadmins use to configure FakeNBD, but somehow that program has to tell the driver about it. Here's where configfs comes in. When the FakeNBD driver is loaded, it registers itself with configfs. -readdir(3) sees this just fine: +readdir(3) sees this just fine:: # ls /config fakenbd A fakenbd connection can be created with mkdir(2). The name is arbitrary, but likely the tool will make some use of the name. Perhaps -it is a uuid or a disk name: +it is a uuid or a disk name:: # mkdir /config/fakenbd/disk1 # ls /config/fakenbd/disk1 @@ -102,7 +106,7 @@ it is a uuid or a disk name: The target attribute contains the IP address of the server FakeNBD will connect to. The device attribute is the device on the server. Predictably, the rw attribute determines whether the connection is -read-only or read-write. +read-only or read-write:: # echo 10.0.0.1 > /config/fakenbd/disk1/target # echo /dev/sda1 > /config/fakenbd/disk1/device @@ -111,7 +115,8 @@ read-only or read-write. That's it. That's all there is. Now the device is configured, via the shell no less. -[Coding With configfs] +Coding With configfs +==================== Every object in configfs is a config_item. A config_item reflects an object in the subsystem. It has attributes that match values on that @@ -130,7 +135,10 @@ appears as a directory at the top of the configfs filesystem. A subsystem is also a config_group, and can do everything a config_group can. -[struct config_item] +struct config_item +================== + +:: struct config_item { char *ci_name; @@ -168,7 +176,10 @@ By itself, a config_item cannot do much more than appear in configfs. Usually a subsystem wants the item to display and/or store attributes, among other things. For that, it needs a type. -[struct config_item_type] +struct config_item_type +======================= + +:: struct configfs_item_operations { void (*release)(struct config_item *); @@ -192,7 +203,10 @@ allocated dynamically will need to provide the ct_item_ops->release() method. This method is called when the config_item's reference count reaches zero. -[struct configfs_attribute] +struct configfs_attribute +========================= + +:: struct configfs_attribute { char *ca_name; @@ -214,7 +228,10 @@ be called whenever userspace asks for a read(2) on the attribute. If an attribute is writable and provides a ->store method, that method will be be called whenever userspace asks for a write(2) on the attribute. -[struct configfs_bin_attribute] +struct configfs_bin_attribute +============================= + +:: struct configfs_bin_attribute { struct configfs_attribute cb_attr; @@ -240,11 +257,12 @@ will happen for write(2). The reads/writes are bufferred so only a single read/write will occur; the attributes' need not concern itself with it. -[struct config_group] +struct config_group +=================== A config_item cannot live in a vacuum. The only way one can be created is via mkdir(2) on a config_group. This will trigger creation of a -child item. +child item:: struct config_group { struct config_item cg_item; @@ -264,7 +282,7 @@ The config_group structure contains a config_item. Properly configuring that item means that a group can behave as an item in its own right. However, it can do more: it can create child items or groups. This is accomplished via the group operations specified on the group's -config_item_type. +config_item_type:: struct configfs_group_operations { struct config_item *(*make_item)(struct config_group *group, @@ -279,7 +297,8 @@ config_item_type. }; A group creates child items by providing the -ct_group_ops->make_item() method. If provided, this method is called from mkdir(2) in the group's directory. The subsystem allocates a new +ct_group_ops->make_item() method. If provided, this method is called from +mkdir(2) in the group's directory. The subsystem allocates a new config_item (or more likely, its container structure), initializes it, and returns it to configfs. Configfs will then populate the filesystem tree to reflect the new item. @@ -296,13 +315,14 @@ upon item allocation. If a subsystem has no work to do, it may omit the ct_group_ops->drop_item() method, and configfs will call config_item_put() on the item on behalf of the subsystem. -IMPORTANT: drop_item() is void, and as such cannot fail. When rmdir(2) -is called, configfs WILL remove the item from the filesystem tree -(assuming that it has no children to keep it busy). The subsystem is -responsible for responding to this. If the subsystem has references to -the item in other threads, the memory is safe. It may take some time -for the item to actually disappear from the subsystem's usage. But it -is gone from configfs. +Important: + drop_item() is void, and as such cannot fail. When rmdir(2) + is called, configfs WILL remove the item from the filesystem tree + (assuming that it has no children to keep it busy). The subsystem is + responsible for responding to this. If the subsystem has references to + the item in other threads, the memory is safe. It may take some time + for the item to actually disappear from the subsystem's usage. But it + is gone from configfs. When drop_item() is called, the item's linkage has already been torn down. It no longer has a reference on its parent and has no place in @@ -319,10 +339,11 @@ is implemented in the configfs rmdir(2) code. ->drop_item() will not be called, as the item has not been dropped. rmdir(2) will fail, as the directory is not empty. -[struct configfs_subsystem] +struct configfs_subsystem +========================= A subsystem must register itself, usually at module_init time. This -tells configfs to make the subsystem appear in the file tree. +tells configfs to make the subsystem appear in the file tree:: struct configfs_subsystem { struct config_group su_group; @@ -332,17 +353,19 @@ tells configfs to make the subsystem appear in the file tree. int configfs_register_subsystem(struct configfs_subsystem *subsys); void configfs_unregister_subsystem(struct configfs_subsystem *subsys); - A subsystem consists of a toplevel config_group and a mutex. +A subsystem consists of a toplevel config_group and a mutex. The group is where child config_items are created. For a subsystem, this group is usually defined statically. Before calling configfs_register_subsystem(), the subsystem must have initialized the group via the usual group _init() functions, and it must also have initialized the mutex. - When the register call returns, the subsystem is live, and it + +When the register call returns, the subsystem is live, and it will be visible via configfs. At that point, mkdir(2) can be called and the subsystem must be ready for it. -[An Example] +An Example +========== The best example of these basic concepts is the simple_children subsystem/group and the simple_child item in @@ -350,7 +373,8 @@ samples/configfs/configfs_sample.c. It shows a trivial object displaying and storing an attribute, and a simple group creating and destroying these children. -[Hierarchy Navigation and the Subsystem Mutex] +Hierarchy Navigation and the Subsystem Mutex +============================================ There is an extra bonus that configfs provides. The config_groups and config_items are arranged in a hierarchy due to the fact that they @@ -375,7 +399,8 @@ be in its parent's cg_children list for the same duration. This allows a subsystem to trust ci_parent and cg_children while they hold the mutex. -[Item Aggregation Via symlink(2)] +Item Aggregation Via symlink(2) +=============================== configfs provides a simple group via the group->item parent/child relationship. Often, however, a larger environment requires aggregation @@ -403,7 +428,8 @@ A config_item cannot be removed while it links to any other item, nor can it be removed while an item links to it. Dangling symlinks are not allowed in configfs. -[Automatically Created Subgroups] +Automatically Created Subgroups +=============================== A new config_group may want to have two types of child config_items. While this could be codified by magic names in ->make_item(), it is much @@ -433,7 +459,8 @@ As a consequence of this, default groups cannot be removed directly via rmdir(2). They also are not considered when rmdir(2) on the parent group is checking for children. -[Dependent Subsystems] +Dependent Subsystems +==================== Sometimes other drivers depend on particular configfs items. For example, ocfs2 mounts depend on a heartbeat region item. If that @@ -460,9 +487,11 @@ succeeds, then heartbeat knows the region is safe to give to ocfs2. If it fails, it was being torn down anyway, and heartbeat can gracefully pass up an error. -[Committable Items] +Committable Items +================= -NOTE: Committable items are currently unimplemented. +Note: + Committable items are currently unimplemented. Some config_items cannot have a valid initial state. That is, no default values can be specified for the item's attributes such that the @@ -504,5 +533,3 @@ As rmdir(2) does not work in the "live" directory, an item must be shutdown, or "uncommitted". Again, this is done via rename(2), this time from the "live" directory back to the "pending" one. The subsystem is notified by the ct_group_ops->uncommit_object() method. - - diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt index 679729442fd2..735f3859b19f 100644 --- a/Documentation/filesystems/dax.txt +++ b/Documentation/filesystems/dax.txt @@ -74,7 +74,7 @@ are zeroed out and converted to written extents before being returned to avoid exposure of uninitialized data through mmap. These filesystems may be used for inspiration: -- ext2: see Documentation/filesystems/ext2.txt +- ext2: see Documentation/filesystems/ext2.rst - ext4: see Documentation/filesystems/ext4/ - xfs: see Documentation/admin-guide/xfs.rst diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst index 6c032db235a5..1da7a4b7383d 100644 --- a/Documentation/filesystems/debugfs.rst +++ b/Documentation/filesystems/debugfs.rst @@ -166,16 +166,17 @@ file:: }; struct debugfs_regset32 { - struct debugfs_reg32 *regs; + const struct debugfs_reg32 *regs; int nregs; void __iomem *base; + struct device *dev; /* Optional device for Runtime PM */ }; debugfs_create_regset32(const char *name, umode_t mode, struct dentry *parent, struct debugfs_regset32 *regset); - void debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs, + void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); The "base" argument may be 0, but you may want to build the reg32 array diff --git a/Documentation/filesystems/devpts.rst b/Documentation/filesystems/devpts.rst new file mode 100644 index 000000000000..a03248ddfb4c --- /dev/null +++ b/Documentation/filesystems/devpts.rst @@ -0,0 +1,36 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================== +The Devpts Filesystem +===================== + +Each mount of the devpts filesystem is now distinct such that ptys +and their indicies allocated in one mount are independent from ptys +and their indicies in all other mounts. + +All mounts of the devpts filesystem now create a ``/dev/pts/ptmx`` node +with permissions ``0000``. + +To retain backwards compatibility the a ptmx device node (aka any node +created with ``mknod name c 5 2``) when opened will look for an instance +of devpts under the name ``pts`` in the same directory as the ptmx device +node. + +As an option instead of placing a ``/dev/ptmx`` device node at ``/dev/ptmx`` +it is possible to place a symlink to ``/dev/pts/ptmx`` at ``/dev/ptmx`` or +to bind mount ``/dev/ptx/ptmx`` to ``/dev/ptmx``. If you opt for using +the devpts filesystem in this manner devpts should be mounted with +the ``ptmxmode=0666``, or ``chmod 0666 /dev/pts/ptmx`` should be called. + +Total count of pty pairs in all instances is limited by sysctls:: + + kernel.pty.max = 4096 - global limit + kernel.pty.reserve = 1024 - reserved for filesystems mounted from the initial mount namespace + kernel.pty.nr - current count of ptys + +Per-instance limit could be set by adding mount option ``max=<count>``. + +This feature was added in kernel 3.4 together with +``sysctl kernel.pty.reserve``. + +In kernels older than 3.4 sysctl ``kernel.pty.max`` works as per-instance limit. diff --git a/Documentation/filesystems/devpts.txt b/Documentation/filesystems/devpts.txt deleted file mode 100644 index 9f94fe276dea..000000000000 --- a/Documentation/filesystems/devpts.txt +++ /dev/null @@ -1,26 +0,0 @@ -Each mount of the devpts filesystem is now distinct such that ptys -and their indicies allocated in one mount are independent from ptys -and their indicies in all other mounts. - -All mounts of the devpts filesystem now create a /dev/pts/ptmx node -with permissions 0000. - -To retain backwards compatibility the a ptmx device node (aka any node -created with "mknod name c 5 2") when opened will look for an instance -of devpts under the name "pts" in the same directory as the ptmx device -node. - -As an option instead of placing a /dev/ptmx device node at /dev/ptmx -it is possible to place a symlink to /dev/pts/ptmx at /dev/ptmx or -to bind mount /dev/ptx/ptmx to /dev/ptmx. If you opt for using -the devpts filesystem in this manner devpts should be mounted with -the ptmxmode=0666, or chmod 0666 /dev/pts/ptmx should be called. - -Total count of pty pairs in all instances is limited by sysctls: -kernel.pty.max = 4096 - global limit -kernel.pty.reserve = 1024 - reserved for filesystems mounted from the initial mount namespace -kernel.pty.nr - current count of ptys - -Per-instance limit could be set by adding mount option "max=<count>". -This feature was added in kernel 3.4 together with sysctl kernel.pty.reserve. -In kernels older than 3.4 sysctl kernel.pty.max works as per-instance limit. diff --git a/Documentation/filesystems/dnotify.txt b/Documentation/filesystems/dnotify.rst index 15156883d321..a28a1f9ef79c 100644 --- a/Documentation/filesystems/dnotify.txt +++ b/Documentation/filesystems/dnotify.rst @@ -1,5 +1,8 @@ - Linux Directory Notification - ============================ +.. SPDX-License-Identifier: GPL-2.0 + +============================ +Linux Directory Notification +============================ Stephen Rothwell <sfr@canb.auug.org.au> @@ -12,6 +15,7 @@ being delivered using signals. The application decides which "events" it wants to be notified about. The currently defined events are: + ========= ===================================================== DN_ACCESS A file in the directory was accessed (read) DN_MODIFY A file in the directory was modified (write,truncate) DN_CREATE A file was created in the directory @@ -19,6 +23,7 @@ The currently defined events are: DN_RENAME A file in the directory was renamed DN_ATTRIB A file in the directory had its attributes changed (chmod,chown) + ========= ===================================================== Usually, the application must reregister after each notification, but if DN_MULTISHOT is or'ed with the event mask, then the registration will @@ -36,7 +41,7 @@ especially important if DN_MULTISHOT is specified. Note that SIGRTMIN is often blocked, so it is better to use (at least) SIGRTMIN + 1. Implementation expectations (features and bugs :-)) ---------------------------- +--------------------------------------------------- The notification should work for any local access to files even if the actual file system is on a remote server. This implies that remote @@ -67,4 +72,4 @@ See tools/testing/selftests/filesystems/dnotify_test.c for an example. NOTE ---- Beginning with Linux 2.6.13, dnotify has been replaced by inotify. -See Documentation/filesystems/inotify.txt for more information on it. +See Documentation/filesystems/inotify.rst for more information on it. diff --git a/Documentation/filesystems/efivarfs.rst b/Documentation/filesystems/efivarfs.rst index 90ac65683e7e..0551985821b8 100644 --- a/Documentation/filesystems/efivarfs.rst +++ b/Documentation/filesystems/efivarfs.rst @@ -24,3 +24,20 @@ files that are not well-known standardized variables are created as immutable files. This doesn't prevent removal - "chattr -i" will work - but it does prevent this kind of failure from being accomplished accidentally. + +.. warning :: + When a content of an UEFI variable in /sys/firmware/efi/efivars is + displayed, for example using "hexdump", pay attention that the first + 4 bytes of the output represent the UEFI variable attributes, + in little-endian format. + + Practically the output of each efivar is composed of: + + +-----------------------------------+ + |4_bytes_of_attributes + efivar_data| + +-----------------------------------+ + +*See also:* + +- Documentation/admin-guide/acpi/ssdt-overlays.rst +- Documentation/ABI/stable/sysfs-firmware-efi-vars diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.rst index ac87e6fda842..2a572e7edc08 100644 --- a/Documentation/filesystems/fiemap.txt +++ b/Documentation/filesystems/fiemap.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ============ Fiemap Ioctl ============ @@ -10,9 +12,9 @@ returns a list of extents. Request Basics -------------- -A fiemap request is encoded within struct fiemap: +A fiemap request is encoded within struct fiemap:: -struct fiemap { + struct fiemap { __u64 fm_start; /* logical offset (inclusive) at * which to start mapping (in) */ __u64 fm_length; /* logical length of mapping which @@ -23,7 +25,7 @@ struct fiemap { __u32 fm_extent_count; /* size of fm_extents array (in) */ __u32 fm_reserved; struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ -}; + }; fm_start, and fm_length specify the logical range within the file @@ -51,12 +53,12 @@ nothing to prevent the file from changing between calls to FIEMAP. The following flags can be set in fm_flags: -* FIEMAP_FLAG_SYNC -If this flag is set, the kernel will sync the file before mapping extents. +FIEMAP_FLAG_SYNC + If this flag is set, the kernel will sync the file before mapping extents. -* FIEMAP_FLAG_XATTR -If this flag is set, the extents returned will describe the inodes -extended attribute lookup tree, instead of its data tree. +FIEMAP_FLAG_XATTR + If this flag is set, the extents returned will describe the inodes + extended attribute lookup tree, instead of its data tree. Extent Mapping @@ -75,18 +77,18 @@ complete the requested range and will not have the FIEMAP_EXTENT_LAST flag set (see the next section on extent flags). Each extent is described by a single fiemap_extent structure as -returned in fm_extents. - -struct fiemap_extent { - __u64 fe_logical; /* logical offset in bytes for the start of - * the extent */ - __u64 fe_physical; /* physical offset in bytes for the start - * of the extent */ - __u64 fe_length; /* length in bytes for the extent */ - __u64 fe_reserved64[2]; - __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ - __u32 fe_reserved[3]; -}; +returned in fm_extents:: + + struct fiemap_extent { + __u64 fe_logical; /* logical offset in bytes for the start of + * the extent */ + __u64 fe_physical; /* physical offset in bytes for the start + * of the extent */ + __u64 fe_length; /* length in bytes for the extent */ + __u64 fe_reserved64[2]; + __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ + __u32 fe_reserved[3]; + }; All offsets and lengths are in bytes and mirror those on disk. It is valid for an extents logical offset to start before the request or its logical @@ -114,26 +116,27 @@ worry about all present and future flags which might imply unaligned data. Note that the opposite is not true - it would be valid for FIEMAP_EXTENT_NOT_ALIGNED to appear alone. -* FIEMAP_EXTENT_LAST -This is generally the last extent in the file. A mapping attempt past -this extent may return nothing. Some implementations set this flag to -indicate this extent is the last one in the range queried by the user -(via fiemap->fm_length). +FIEMAP_EXTENT_LAST + This is generally the last extent in the file. A mapping attempt past + this extent may return nothing. Some implementations set this flag to + indicate this extent is the last one in the range queried by the user + (via fiemap->fm_length). + +FIEMAP_EXTENT_UNKNOWN + The location of this extent is currently unknown. This may indicate + the data is stored on an inaccessible volume or that no storage has + been allocated for the file yet. -* FIEMAP_EXTENT_UNKNOWN -The location of this extent is currently unknown. This may indicate -the data is stored on an inaccessible volume or that no storage has -been allocated for the file yet. +FIEMAP_EXTENT_DELALLOC + This will also set FIEMAP_EXTENT_UNKNOWN. -* FIEMAP_EXTENT_DELALLOC - - This will also set FIEMAP_EXTENT_UNKNOWN. -Delayed allocation - while there is data for this extent, its -physical location has not been allocated yet. + Delayed allocation - while there is data for this extent, its + physical location has not been allocated yet. -* FIEMAP_EXTENT_ENCODED -This extent does not consist of plain filesystem blocks but is -encoded (e.g. encrypted or compressed). Reading the data in this -extent via I/O to the block device will have undefined results. +FIEMAP_EXTENT_ENCODED + This extent does not consist of plain filesystem blocks but is + encoded (e.g. encrypted or compressed). Reading the data in this + extent via I/O to the block device will have undefined results. Note that it is *always* undefined to try to update the data in-place by writing to the indicated location without the @@ -145,32 +148,32 @@ unmounted, and then only if the FIEMAP_EXTENT_ENCODED flag is clear; user applications must not try reading or writing to the filesystem via the block device under any other circumstances. -* FIEMAP_EXTENT_DATA_ENCRYPTED - - This will also set FIEMAP_EXTENT_ENCODED -The data in this extent has been encrypted by the file system. +FIEMAP_EXTENT_DATA_ENCRYPTED + This will also set FIEMAP_EXTENT_ENCODED + The data in this extent has been encrypted by the file system. -* FIEMAP_EXTENT_NOT_ALIGNED -Extent offsets and length are not guaranteed to be block aligned. +FIEMAP_EXTENT_NOT_ALIGNED + Extent offsets and length are not guaranteed to be block aligned. -* FIEMAP_EXTENT_DATA_INLINE +FIEMAP_EXTENT_DATA_INLINE This will also set FIEMAP_EXTENT_NOT_ALIGNED -Data is located within a meta data block. + Data is located within a meta data block. -* FIEMAP_EXTENT_DATA_TAIL +FIEMAP_EXTENT_DATA_TAIL This will also set FIEMAP_EXTENT_NOT_ALIGNED -Data is packed into a block with data from other files. + Data is packed into a block with data from other files. -* FIEMAP_EXTENT_UNWRITTEN -Unwritten extent - the extent is allocated but its data has not been -initialized. This indicates the extent's data will be all zero if read -through the filesystem but the contents are undefined if read directly from -the device. +FIEMAP_EXTENT_UNWRITTEN + Unwritten extent - the extent is allocated but its data has not been + initialized. This indicates the extent's data will be all zero if read + through the filesystem but the contents are undefined if read directly from + the device. -* FIEMAP_EXTENT_MERGED -This will be set when a file does not support extents, i.e., it uses a block -based addressing scheme. Since returning an extent for each block back to -userspace would be highly inefficient, the kernel will try to merge most -adjacent blocks into 'extents'. +FIEMAP_EXTENT_MERGED + This will be set when a file does not support extents, i.e., it uses a block + based addressing scheme. Since returning an extent for each block back to + userspace would be highly inefficient, the kernel will try to merge most + adjacent blocks into 'extents'. VFS -> File System Implementation @@ -179,23 +182,23 @@ VFS -> File System Implementation File systems wishing to support fiemap must implement a ->fiemap callback on their inode_operations structure. The fs ->fiemap call is responsible for defining its set of supported fiemap flags, and calling a helper function on -each discovered extent: +each discovered extent:: -struct inode_operations { + struct inode_operations { ... int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); ->fiemap is passed struct fiemap_extent_info which describes the -fiemap request: +fiemap request:: -struct fiemap_extent_info { + struct fiemap_extent_info { unsigned int fi_flags; /* Flags as passed from user */ unsigned int fi_extents_mapped; /* Number of mapped extents */ unsigned int fi_extents_max; /* Size of fiemap_extent array */ struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */ -}; + }; It is intended that the file system should not need to access any of this structure directly. Filesystem handlers should be tolerant to signals and return @@ -203,9 +206,9 @@ EINTR once fatal signal received. Flag checking should be done at the beginning of the ->fiemap callback via the -fiemap_check_flags() helper: +fiemap_check_flags() helper:: -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); + int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); The struct fieinfo should be passed in as received from ioctl_fiemap(). The set of fiemap flags which the fs understands should be passed via fs_flags. If @@ -216,10 +219,10 @@ ioctl_fiemap(). For each extent in the request range, the file system should call -the helper function, fiemap_fill_next_extent(): +the helper function, fiemap_fill_next_extent():: -int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, - u64 phys, u64 len, u32 flags, u32 dev); + int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags, u32 dev); fiemap_fill_next_extent() will use the passed values to populate the next free extent in the fm_extents array. 'General' extent flags will diff --git a/Documentation/filesystems/files.txt b/Documentation/filesystems/files.rst index 46dfc6b038c3..cbf8e57376bf 100644 --- a/Documentation/filesystems/files.txt +++ b/Documentation/filesystems/files.rst @@ -1,5 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================================== File management in the Linux kernel ------------------------------------ +=================================== This document describes how locking for files (struct file) and file descriptor table (struct files) works. @@ -34,7 +37,7 @@ appear atomic. Here are the locking rules for the fdtable structure - 1. All references to the fdtable must be done through - the files_fdtable() macro : + the files_fdtable() macro:: struct fdtable *fdt; @@ -61,7 +64,8 @@ the fdtable structure - 4. To look up the file structure given an fd, a reader must use either fcheck() or fcheck_files() APIs. These take care of barrier requirements due to lock-free lookup. - An example : + + An example:: struct file *file; @@ -77,7 +81,7 @@ the fdtable structure - of the fd (fget()/fget_light()) are lock-free, it is possible that look-up may race with the last put() operation on the file structure. This is avoided using atomic_long_inc_not_zero() - on ->f_count : + on ->f_count:: rcu_read_lock(); file = fcheck_files(files, fd); @@ -106,7 +110,8 @@ the fdtable structure - holding files->file_lock. If ->file_lock is dropped, then another thread expand the files thereby creating a new fdtable and making the earlier fdtable pointer stale. - For example : + + For example:: spin_lock(&files->file_lock); fd = locate_fd(files, file, start); diff --git a/Documentation/filesystems/fuse-io.txt b/Documentation/filesystems/fuse-io.rst index 07b8f73f100f..255a368fe534 100644 --- a/Documentation/filesystems/fuse-io.txt +++ b/Documentation/filesystems/fuse-io.rst @@ -1,3 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============== +Fuse I/O Modes +============== + Fuse supports the following I/O modes: - direct-io diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index e7b46dac7079..17795341e0a3 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -24,6 +24,22 @@ algorithms work. splice locking directory-locking + devpts + dnotify + fiemap + files + locks + mandatory-locking + mount_api + quota + seq_file + sharedsubtree + sysfs-pci + sysfs-tagging + + automount-support + + caching/index porting @@ -57,7 +73,10 @@ Documentation for filesystem implementations. befs bfs btrfs + cifs/cifsroot ceph + coda + configfs cramfs debugfs dlmfs @@ -73,6 +92,7 @@ Documentation for filesystem implementations. hfsplus hpfs fuse + fuse-io inotify isofs nilfs2 @@ -88,6 +108,7 @@ Documentation for filesystem implementations. ramfs-rootfs-initramfs relay romfs + spufs/index squashfs sysfs sysv-fs @@ -97,4 +118,6 @@ Documentation for filesystem implementations. udf virtiofs vfat + xfs-delayed-logging-design + xfs-self-describing-metadata zonefs diff --git a/Documentation/filesystems/locks.txt b/Documentation/filesystems/locks.rst index 5368690f412e..c5ae858b1aac 100644 --- a/Documentation/filesystems/locks.txt +++ b/Documentation/filesystems/locks.rst @@ -1,4 +1,8 @@ - File Locking Release Notes +.. SPDX-License-Identifier: GPL-2.0 + +========================== +File Locking Release Notes +========================== Andy Walker <andy@lysaker.kvaerner.no> @@ -6,7 +10,7 @@ 1. What's New? --------------- +============== 1.1 Broken Flock Emulation -------------------------- @@ -25,7 +29,7 @@ anyway (see the file "Documentation/process/changes.rst".) --------------------------- 1.2.1 Typical Problems - Sendmail ---------------------------------- +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Because sendmail was unable to use the old flock() emulation, many sendmail installations use fcntl() instead of flock(). This is true of Slackware 3.0 for example. This gave rise to some other subtle problems if sendmail was @@ -37,7 +41,7 @@ to lock solid with deadlocked processes. 1.2.2 The Solution ------------------- +^^^^^^^^^^^^^^^^^^ The solution I have chosen, after much experimentation and discussion, is to make flock() and fcntl() locks oblivious to each other. Both can exists, and neither will have any effect on the other. @@ -54,7 +58,7 @@ fcntl(), with all the problems that implies. --------------------------------------- Mandatory locking, as described in -'Documentation/filesystems/mandatory-locking.txt' was prior to this release a +'Documentation/filesystems/mandatory-locking.rst' was prior to this release a general configuration option that was valid for all mounted filesystems. This had a number of inherent dangers, not the least of which was the ability to freeze an NFS server by asking it to read a file for which a mandatory lock diff --git a/Documentation/filesystems/mandatory-locking.txt b/Documentation/filesystems/mandatory-locking.rst index a251ca33164a..9ce73544a8f0 100644 --- a/Documentation/filesystems/mandatory-locking.txt +++ b/Documentation/filesystems/mandatory-locking.rst @@ -1,8 +1,13 @@ - Mandatory File Locking For The Linux Operating System +.. SPDX-License-Identifier: GPL-2.0 + +===================================================== +Mandatory File Locking For The Linux Operating System +===================================================== Andy Walker <andy@lysaker.kvaerner.no> 15 April 1996 + (Updated September 2007) 0. Why you should avoid mandatory locking @@ -53,15 +58,17 @@ possible on existing user code. The scheme is based on marking individual files as candidates for mandatory locking, and using the existing fcntl()/lockf() interface for applying locks just as if they were normal, advisory locks. -Note 1: In saying "file" in the paragraphs above I am actually not telling -the whole truth. System V locking is based on fcntl(). The granularity of -fcntl() is such that it allows the locking of byte ranges in files, in addition -to entire files, so the mandatory locking rules also have byte level -granularity. +.. Note:: + + 1. In saying "file" in the paragraphs above I am actually not telling + the whole truth. System V locking is based on fcntl(). The granularity of + fcntl() is such that it allows the locking of byte ranges in files, in + addition to entire files, so the mandatory locking rules also have byte + level granularity. -Note 2: POSIX.1 does not specify any scheme for mandatory locking, despite -borrowing the fcntl() locking scheme from System V. The mandatory locking -scheme is defined by the System V Interface Definition (SVID) Version 3. + 2. POSIX.1 does not specify any scheme for mandatory locking, despite + borrowing the fcntl() locking scheme from System V. The mandatory locking + scheme is defined by the System V Interface Definition (SVID) Version 3. 2. Marking a file for mandatory locking --------------------------------------- diff --git a/Documentation/filesystems/mount_api.txt b/Documentation/filesystems/mount_api.rst index 87c14bbb2b35..dea22d64f060 100644 --- a/Documentation/filesystems/mount_api.txt +++ b/Documentation/filesystems/mount_api.rst @@ -1,8 +1,10 @@ - ==================== - FILESYSTEM MOUNT API - ==================== +.. SPDX-License-Identifier: GPL-2.0 -CONTENTS +==================== +fILESYSTEM Mount API +==================== + +.. CONTENTS (1) Overview. @@ -21,8 +23,7 @@ CONTENTS (8) Parameter helper functions. -======== -OVERVIEW +Overview ======== The creation of new mounts is now to be done in a multistep process: @@ -43,7 +44,7 @@ The creation of new mounts is now to be done in a multistep process: (7) Destroy the context. -To support this, the file_system_type struct gains two new fields: +To support this, the file_system_type struct gains two new fields:: int (*init_fs_context)(struct fs_context *fc); const struct fs_parameter_description *parameters; @@ -57,12 +58,11 @@ Note that security initialisation is done *after* the filesystem is called so that the namespaces may be adjusted first. -====================== -THE FILESYSTEM CONTEXT +The Filesystem context ====================== The creation and reconfiguration of a superblock is governed by a filesystem -context. This is represented by the fs_context structure: +context. This is represented by the fs_context structure:: struct fs_context { const struct fs_context_operations *ops; @@ -86,78 +86,106 @@ context. This is represented by the fs_context structure: The fs_context fields are as follows: - (*) const struct fs_context_operations *ops + * :: + + const struct fs_context_operations *ops These are operations that can be done on a filesystem context (see below). This must be set by the ->init_fs_context() file_system_type operation. - (*) struct file_system_type *fs_type + * :: + + struct file_system_type *fs_type A pointer to the file_system_type of the filesystem that is being constructed or reconfigured. This retains a reference on the type owner. - (*) void *fs_private + * :: + + void *fs_private A pointer to the file system's private data. This is where the filesystem will need to store any options it parses. - (*) struct dentry *root + * :: + + struct dentry *root A pointer to the root of the mountable tree (and indirectly, the superblock thereof). This is filled in by the ->get_tree() op. If this is set, an active reference on root->d_sb must also be held. - (*) struct user_namespace *user_ns - (*) struct net *net_ns + * :: + + struct user_namespace *user_ns + struct net *net_ns There are a subset of the namespaces in use by the invoking process. They retain references on each namespace. The subscribed namespaces may be replaced by the filesystem to reflect other sources, such as the parent mount superblock on an automount. - (*) const struct cred *cred + * :: + + const struct cred *cred The mounter's credentials. This retains a reference on the credentials. - (*) char *source + * :: + + char *source This specifies the source. It may be a block device (e.g. /dev/sda1) or something more exotic, such as the "host:/path" that NFS desires. - (*) char *subtype + * :: + + char *subtype This is a string to be added to the type displayed in /proc/mounts to qualify it (used by FUSE). This is available for the filesystem to set if desired. - (*) void *security + * :: + + void *security A place for the LSMs to hang their security data for the superblock. The relevant security operations are described below. - (*) void *s_fs_info + * :: + + void *s_fs_info The proposed s_fs_info for a new superblock, set in the superblock by sget_fc(). This can be used to distinguish superblocks. - (*) unsigned int sb_flags - (*) unsigned int sb_flags_mask + * :: + + unsigned int sb_flags + unsigned int sb_flags_mask Which bits SB_* flags are to be set/cleared in super_block::s_flags. - (*) unsigned int s_iflags + * :: + + unsigned int s_iflags These will be bitwise-OR'd with s->s_iflags when a superblock is created. - (*) enum fs_context_purpose + * :: + + enum fs_context_purpose This indicates the purpose for which the context is intended. The available values are: - FS_CONTEXT_FOR_MOUNT, -- New superblock for explicit mount - FS_CONTEXT_FOR_SUBMOUNT -- New automatic submount of extant mount - FS_CONTEXT_FOR_RECONFIGURE -- Change an existing mount + ========================== ====================================== + FS_CONTEXT_FOR_MOUNT, New superblock for explicit mount + FS_CONTEXT_FOR_SUBMOUNT New automatic submount of extant mount + FS_CONTEXT_FOR_RECONFIGURE Change an existing mount + ========================== ====================================== The mount context is created by calling vfs_new_fs_context() or vfs_dup_fs_context() and is destroyed with put_fs_context(). Note that the @@ -176,11 +204,10 @@ mount context. For instance, NFS might pin the appropriate protocol version module. -================================= -THE FILESYSTEM CONTEXT OPERATIONS +The Filesystem Context Operations ================================= -The filesystem context points to a table of operations: +The filesystem context points to a table of operations:: struct fs_context_operations { void (*free)(struct fs_context *fc); @@ -195,24 +222,32 @@ The filesystem context points to a table of operations: These operations are invoked by the various stages of the mount procedure to manage the filesystem context. They are as follows: - (*) void (*free)(struct fs_context *fc); + * :: + + void (*free)(struct fs_context *fc); Called to clean up the filesystem-specific part of the filesystem context when the context is destroyed. It should be aware that parts of the context may have been removed and NULL'd out by ->get_tree(). - (*) int (*dup)(struct fs_context *fc, struct fs_context *src_fc); + * :: + + int (*dup)(struct fs_context *fc, struct fs_context *src_fc); Called when a filesystem context has been duplicated to duplicate the filesystem-private data. An error may be returned to indicate failure to do this. - [!] Note that even if this fails, put_fs_context() will be called + .. Warning:: + + Note that even if this fails, put_fs_context() will be called immediately thereafter, so ->dup() *must* make the filesystem-private data safe for ->free(). - (*) int (*parse_param)(struct fs_context *fc, - struct struct fs_parameter *param); + * :: + + int (*parse_param)(struct fs_context *fc, + struct struct fs_parameter *param); Called when a parameter is being added to the filesystem context. param points to the key name and maybe a value object. VFS-specific options @@ -224,7 +259,9 @@ manage the filesystem context. They are as follows: If successful, 0 should be returned or a negative error code otherwise. - (*) int (*parse_monolithic)(struct fs_context *fc, void *data); + * :: + + int (*parse_monolithic)(struct fs_context *fc, void *data); Called when the mount(2) system call is invoked to pass the entire data page in one go. If this is expected to be just a list of "key[=val]" @@ -236,7 +273,9 @@ manage the filesystem context. They are as follows: finds it's the standard key-val list then it may pass it off to generic_parse_monolithic(). - (*) int (*get_tree)(struct fs_context *fc); + * :: + + int (*get_tree)(struct fs_context *fc); Called to get or create the mountable root and superblock, using the information stored in the filesystem context (reconfiguration goes via a @@ -249,7 +288,9 @@ manage the filesystem context. They are as follows: The phase on a userspace-driven context will be set to only allow this to be called once on any particular context. - (*) int (*reconfigure)(struct fs_context *fc); + * :: + + int (*reconfigure)(struct fs_context *fc); Called to effect reconfiguration of a superblock using information stored in the filesystem context. It may detach any resources it desires from @@ -259,19 +300,20 @@ manage the filesystem context. They are as follows: On success it should return 0. In the case of an error, it should return a negative error code. - [NOTE] reconfigure is intended as a replacement for remount_fs. + .. Note:: reconfigure is intended as a replacement for remount_fs. -=========================== -FILESYSTEM CONTEXT SECURITY +Filesystem context Security =========================== The filesystem context contains a security pointer that the LSMs can use for building up a security context for the superblock to be mounted. There are a number of operations used by the new mount code for this purpose: - (*) int security_fs_context_alloc(struct fs_context *fc, - struct dentry *reference); + * :: + + int security_fs_context_alloc(struct fs_context *fc, + struct dentry *reference); Called to initialise fc->security (which is preset to NULL) and allocate any resources needed. It should return 0 on success or a negative error @@ -283,22 +325,28 @@ number of operations used by the new mount code for this purpose: non-NULL in the case of a submount (FS_CONTEXT_FOR_SUBMOUNT) in which case it indicates the automount point. - (*) int security_fs_context_dup(struct fs_context *fc, - struct fs_context *src_fc); + * :: + + int security_fs_context_dup(struct fs_context *fc, + struct fs_context *src_fc); Called to initialise fc->security (which is preset to NULL) and allocate any resources needed. The original filesystem context is pointed to by src_fc and may be used for reference. It should return 0 on success or a negative error code on failure. - (*) void security_fs_context_free(struct fs_context *fc); + * :: + + void security_fs_context_free(struct fs_context *fc); Called to clean up anything attached to fc->security. Note that the contents may have been transferred to a superblock and the pointer cleared during get_tree. - (*) int security_fs_context_parse_param(struct fs_context *fc, - struct fs_parameter *param); + * :: + + int security_fs_context_parse_param(struct fs_context *fc, + struct fs_parameter *param); Called for each mount parameter, including the source. The arguments are as for the ->parse_param() method. It should return 0 to indicate that @@ -310,7 +358,9 @@ number of operations used by the new mount code for this purpose: (provided the value pointer is NULL'd out). If it is stolen, 1 must be returned to prevent it being passed to the filesystem. - (*) int security_fs_context_validate(struct fs_context *fc); + * :: + + int security_fs_context_validate(struct fs_context *fc); Called after all the options have been parsed to validate the collection as a whole and to do any necessary allocation so that @@ -320,36 +370,43 @@ number of operations used by the new mount code for this purpose: In the case of reconfiguration, the target superblock will be accessible via fc->root. - (*) int security_sb_get_tree(struct fs_context *fc); + * :: + + int security_sb_get_tree(struct fs_context *fc); Called during the mount procedure to verify that the specified superblock is allowed to be mounted and to transfer the security data there. It should return 0 or a negative error code. - (*) void security_sb_reconfigure(struct fs_context *fc); + * :: + + void security_sb_reconfigure(struct fs_context *fc); Called to apply any reconfiguration to an LSM's context. It must not fail. Error checking and resource allocation must be done in advance by the parameter parsing and validation hooks. - (*) int security_sb_mountpoint(struct fs_context *fc, struct path *mountpoint, - unsigned int mnt_flags); + * :: + + int security_sb_mountpoint(struct fs_context *fc, + struct path *mountpoint, + unsigned int mnt_flags); Called during the mount procedure to verify that the root dentry attached to the context is permitted to be attached to the specified mountpoint. It should return 0 on success or a negative error code on failure. -========================== -VFS FILESYSTEM CONTEXT API +VFS Filesystem context API ========================== There are four operations for creating a filesystem context and one for destroying a context: - (*) struct fs_context *fs_context_for_mount( - struct file_system_type *fs_type, - unsigned int sb_flags); + * :: + + struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, + unsigned int sb_flags); Allocate a filesystem context for the purpose of setting up a new mount, whether that be with a new superblock or sharing an existing one. This @@ -359,7 +416,9 @@ destroying a context: fs_type specifies the filesystem type that will manage the context and sb_flags presets the superblock flags stored therein. - (*) struct fs_context *fs_context_for_reconfigure( + * :: + + struct fs_context *fs_context_for_reconfigure( struct dentry *dentry, unsigned int sb_flags, unsigned int sb_flags_mask); @@ -369,7 +428,9 @@ destroying a context: configured. sb_flags and sb_flags_mask indicate which superblock flags need changing and to what. - (*) struct fs_context *fs_context_for_submount( + * :: + + struct fs_context *fs_context_for_submount( struct file_system_type *fs_type, struct dentry *reference); @@ -382,7 +443,9 @@ destroying a context: Note that it's not a requirement that the reference dentry be of the same filesystem type as fs_type. - (*) struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc); + * :: + + struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc); Duplicate a filesystem context, copying any options noted and duplicating or additionally referencing any resources held therein. This is available @@ -392,14 +455,18 @@ destroying a context: The purpose in the new context is inherited from the old one. - (*) void put_fs_context(struct fs_context *fc); + * :: + + void put_fs_context(struct fs_context *fc); Destroy a filesystem context, releasing any resources it holds. This calls the ->free() operation. This is intended to be called by anyone who created a filesystem context. - [!] filesystem contexts are not refcounted, so this causes unconditional - destruction. + .. Warning:: + + filesystem contexts are not refcounted, so this causes unconditional + destruction. In all the above operations, apart from the put op, the return is a mount context pointer or a negative error code. @@ -407,8 +474,10 @@ context pointer or a negative error code. For the remaining operations, if an error occurs, a negative error code will be returned. - (*) int vfs_parse_fs_param(struct fs_context *fc, - struct fs_parameter *param); + * :: + + int vfs_parse_fs_param(struct fs_context *fc, + struct fs_parameter *param); Supply a single mount parameter to the filesystem context. This include the specification of the source/device which is specified as the "source" @@ -423,53 +492,64 @@ returned. The parameter value is typed and can be one of: - fs_value_is_flag, Parameter not given a value. - fs_value_is_string, Value is a string - fs_value_is_blob, Value is a binary blob - fs_value_is_filename, Value is a filename* + dirfd - fs_value_is_file, Value is an open file (file*) + ==================== ============================= + fs_value_is_flag Parameter not given a value + fs_value_is_string Value is a string + fs_value_is_blob Value is a binary blob + fs_value_is_filename Value is a filename* + dirfd + fs_value_is_file Value is an open file (file*) + ==================== ============================= If there is a value, that value is stored in a union in the struct in one of param->{string,blob,name,file}. Note that the function may steal and clear the pointer, but then becomes responsible for disposing of the object. - (*) int vfs_parse_fs_string(struct fs_context *fc, const char *key, - const char *value, size_t v_size); + * :: + + int vfs_parse_fs_string(struct fs_context *fc, const char *key, + const char *value, size_t v_size); A wrapper around vfs_parse_fs_param() that copies the value string it is passed. - (*) int generic_parse_monolithic(struct fs_context *fc, void *data); + * :: + + int generic_parse_monolithic(struct fs_context *fc, void *data); Parse a sys_mount() data page, assuming the form to be a text list consisting of key[=val] options separated by commas. Each item in the list is passed to vfs_mount_option(). This is the default when the ->parse_monolithic() method is NULL. - (*) int vfs_get_tree(struct fs_context *fc); + * :: + + int vfs_get_tree(struct fs_context *fc); Get or create the mountable root and superblock, using the parameters in the filesystem context to select/configure the superblock. This invokes the ->get_tree() method. - (*) struct vfsmount *vfs_create_mount(struct fs_context *fc); + * :: + + struct vfsmount *vfs_create_mount(struct fs_context *fc); Create a mount given the parameters in the specified filesystem context. Note that this does not attach the mount to anything. -=========================== -SUPERBLOCK CREATION HELPERS +Superblock Creation Helpers =========================== A number of VFS helpers are available for use by filesystems for the creation or looking up of superblocks. - (*) struct super_block * - sget_fc(struct fs_context *fc, - int (*test)(struct super_block *sb, struct fs_context *fc), - int (*set)(struct super_block *sb, struct fs_context *fc)); + * :: + + struct super_block * + sget_fc(struct fs_context *fc, + int (*test)(struct super_block *sb, struct fs_context *fc), + int (*set)(struct super_block *sb, struct fs_context *fc)); This is the core routine. If test is non-NULL, it searches for an existing superblock matching the criteria held in the fs_context, using @@ -482,10 +562,12 @@ or looking up of superblocks. The following helpers all wrap sget_fc(): - (*) int vfs_get_super(struct fs_context *fc, - enum vfs_get_super_keying keying, - int (*fill_super)(struct super_block *sb, - struct fs_context *fc)) + * :: + + int vfs_get_super(struct fs_context *fc, + enum vfs_get_super_keying keying, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc)) This creates/looks up a deviceless superblock. The keying indicates how many superblocks of this type may exist and in what manner they may be @@ -515,14 +597,14 @@ PARAMETER DESCRIPTION ===================== Parameters are described using structures defined in linux/fs_parser.h. -There's a core description struct that links everything together: +There's a core description struct that links everything together:: struct fs_parameter_description { const struct fs_parameter_spec *specs; const struct fs_parameter_enum *enums; }; -For example: +For example:: enum { Opt_autocell, @@ -539,10 +621,12 @@ For example: The members are as follows: - (1) const struct fs_parameter_specification *specs; + (1) :: + + const struct fs_parameter_specification *specs; Table of parameter specifications, terminated with a null entry, where the - entries are of type: + entries are of type:: struct fs_parameter_spec { const char *name; @@ -558,6 +642,7 @@ The members are as follows: The 'type' field indicates the desired value type and must be one of: + ======================= ======================= ===================== TYPE NAME EXPECTED VALUE RESULT IN ======================= ======================= ===================== fs_param_is_flag No value n/a @@ -573,19 +658,23 @@ The members are as follows: fs_param_is_blockdev Blockdev path * Needs lookup fs_param_is_path Path * Needs lookup fs_param_is_fd File descriptor result->int_32 + ======================= ======================= ===================== Note that if the value is of fs_param_is_bool type, fs_parse() will try to match any string value against "0", "1", "no", "yes", "false", "true". Each parameter can also be qualified with 'flags': + ======================= ================================================ fs_param_v_optional The value is optional fs_param_neg_with_no result->negated set if key is prefixed with "no" fs_param_neg_with_empty result->negated set if value is "" fs_param_deprecated The parameter is deprecated. + ======================= ================================================ These are wrapped with a number of convenience wrappers: + ======================= =============================================== MACRO SPECIFIES ======================= =============================================== fsparam_flag() fs_param_is_flag @@ -602,9 +691,10 @@ The members are as follows: fsparam_bdev() fs_param_is_blockdev fsparam_path() fs_param_is_path fsparam_fd() fs_param_is_fd + ======================= =============================================== all of which take two arguments, name string and option number - for - example: + example:: static const struct fs_parameter_spec afs_param_specs[] = { fsparam_flag ("autocell", Opt_autocell), @@ -618,10 +708,12 @@ The members are as follows: of arguments to specify the type and the flags for anything that doesn't match one of the above macros. - (2) const struct fs_parameter_enum *enums; + (2) :: + + const struct fs_parameter_enum *enums; Table of enum value names to integer mappings, terminated with a null - entry. This is of type: + entry. This is of type:: struct fs_parameter_enum { u8 opt; @@ -630,7 +722,7 @@ The members are as follows: }; Where the array is an unsorted list of { parameter ID, name }-keyed - elements that indicate the value to map to, e.g.: + elements that indicate the value to map to, e.g.:: static const struct fs_parameter_enum afs_param_enums[] = { { Opt_bar, "x", 1}, @@ -648,18 +740,19 @@ CONFIG_VALIDATE_FS_PARSER=y) and will allow the description to be queried from userspace using the fsinfo() syscall. -========================== -PARAMETER HELPER FUNCTIONS +Parameter Helper Functions ========================== A number of helper functions are provided to help a filesystem or an LSM process the parameters it is given. - (*) int lookup_constant(const struct constant_table tbl[], - const char *name, int not_found); + * :: + + int lookup_constant(const struct constant_table tbl[], + const char *name, int not_found); Look up a constant by name in a table of name -> integer mappings. The - table is an array of elements of the following type: + table is an array of elements of the following type:: struct constant_table { const char *name; @@ -669,9 +762,11 @@ process the parameters it is given. If a match is found, the corresponding value is returned. If a match isn't found, the not_found value is returned instead. - (*) bool validate_constant_table(const struct constant_table *tbl, - size_t tbl_size, - int low, int high, int special); + * :: + + bool validate_constant_table(const struct constant_table *tbl, + size_t tbl_size, + int low, int high, int special); Validate a constant table. Checks that all the elements are appropriately ordered, that there are no duplicates and that the values are between low @@ -682,16 +777,20 @@ process the parameters it is given. If all is good, true is returned. If the table is invalid, errors are logged to dmesg and false is returned. - (*) bool fs_validate_description(const struct fs_parameter_description *desc); + * :: + + bool fs_validate_description(const struct fs_parameter_description *desc); This performs some validation checks on a parameter description. It returns true if the description is good and false if it is not. It will log errors to dmesg if validation fails. - (*) int fs_parse(struct fs_context *fc, - const struct fs_parameter_description *desc, - struct fs_parameter *param, - struct fs_parse_result *result); + * :: + + int fs_parse(struct fs_context *fc, + const struct fs_parameter_description *desc, + struct fs_parameter *param, + struct fs_parse_result *result); This is the main interpreter of parameters. It uses the parameter description to look up a parameter by key name and to convert that to an @@ -711,14 +810,16 @@ process the parameters it is given. parameter is matched, but the value is erroneous, -EINVAL will be returned; otherwise the parameter's option number will be returned. - (*) int fs_lookup_param(struct fs_context *fc, - struct fs_parameter *value, - bool want_bdev, - struct path *_path); + * :: + + int fs_lookup_param(struct fs_context *fc, + struct fs_parameter *value, + bool want_bdev, + struct path *_path); This takes a parameter that carries a string or filename type and attempts to do a path lookup on it. If the parameter expects a blockdev, a check is made that the inode actually represents one. - Returns 0 if successful and *_path will be set; returns a negative error - code if not. + Returns 0 if successful and ``*_path`` will be set; returns a negative + error code if not. diff --git a/Documentation/filesystems/orangefs.rst b/Documentation/filesystems/orangefs.rst index e41369709c5b..463e37694250 100644 --- a/Documentation/filesystems/orangefs.rst +++ b/Documentation/filesystems/orangefs.rst @@ -119,9 +119,7 @@ it comes to that question:: /opt/ofs/bin/pvfs2-genconfig /etc/pvfs2.conf -Create an /etc/pvfs2tab file:: - -Localhost is fine for your pvfs2tab file: +Create an /etc/pvfs2tab file (localhost is fine):: echo tcp://localhost:3334/orangefs /pvfsmnt pvfs2 defaults,noauto 0 0 > \ /etc/pvfs2tab diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 9969bf4c0c44..06d41c0b91cc 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -1871,7 +1871,7 @@ unbindable mount is unbindable For more information on mount propagation see: - Documentation/filesystems/sharedsubtree.txt + Documentation/filesystems/sharedsubtree.rst 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm diff --git a/Documentation/filesystems/quota.txt b/Documentation/filesystems/quota.rst index 32874b06ebe9..a30cdd47c652 100644 --- a/Documentation/filesystems/quota.txt +++ b/Documentation/filesystems/quota.rst @@ -1,4 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 +=============== Quota subsystem =============== @@ -39,6 +41,7 @@ Currently, the interface supports only one message type QUOTA_NL_C_WARNING. This command is used to send a notification about any of the above mentioned events. Each message has six attributes. These are (type of the argument is in parentheses): + QUOTA_NL_A_QTYPE (u32) - type of quota being exceeded (one of USRQUOTA, GRPQUOTA) QUOTA_NL_A_EXCESS_ID (u64) @@ -48,20 +51,34 @@ in parentheses): - UID of a user who caused the event QUOTA_NL_A_WARNING (u32) - what kind of limit is exceeded: - QUOTA_NL_IHARDWARN - inode hardlimit - QUOTA_NL_ISOFTLONGWARN - inode softlimit is exceeded longer - than given grace period - QUOTA_NL_ISOFTWARN - inode softlimit - QUOTA_NL_BHARDWARN - space (block) hardlimit - QUOTA_NL_BSOFTLONGWARN - space (block) softlimit is exceeded - longer than given grace period. - QUOTA_NL_BSOFTWARN - space (block) softlimit + + QUOTA_NL_IHARDWARN + inode hardlimit + QUOTA_NL_ISOFTLONGWARN + inode softlimit is exceeded longer + than given grace period + QUOTA_NL_ISOFTWARN + inode softlimit + QUOTA_NL_BHARDWARN + space (block) hardlimit + QUOTA_NL_BSOFTLONGWARN + space (block) softlimit is exceeded + longer than given grace period. + QUOTA_NL_BSOFTWARN + space (block) softlimit + - four warnings are also defined for the event when user stops exceeding some limit: - QUOTA_NL_IHARDBELOW - inode hardlimit - QUOTA_NL_ISOFTBELOW - inode softlimit - QUOTA_NL_BHARDBELOW - space (block) hardlimit - QUOTA_NL_BSOFTBELOW - space (block) softlimit + + QUOTA_NL_IHARDBELOW + inode hardlimit + QUOTA_NL_ISOFTBELOW + inode softlimit + QUOTA_NL_BHARDBELOW + space (block) hardlimit + QUOTA_NL_BSOFTBELOW + space (block) softlimit + QUOTA_NL_A_DEV_MAJOR (u32) - major number of a device with the affected filesystem QUOTA_NL_A_DEV_MINOR (u32) diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 6c576e241d86..3fddacc6bf14 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -71,7 +71,7 @@ be allowed write access to a ramfs mount. A ramfs derivative called tmpfs was created to add size limits, and the ability to write the data to swap space. Normal users can be allowed write access to -tmpfs mounts. See Documentation/filesystems/tmpfs.txt for more information. +tmpfs mounts. See Documentation/filesystems/tmpfs.rst for more information. What is rootfs? --------------- diff --git a/Documentation/filesystems/seq_file.txt b/Documentation/filesystems/seq_file.rst index d412b236a9d6..fab302046b13 100644 --- a/Documentation/filesystems/seq_file.txt +++ b/Documentation/filesystems/seq_file.rst @@ -1,6 +1,11 @@ -The seq_file interface +.. SPDX-License-Identifier: GPL-2.0 + +====================== +The seq_file Interface +====================== Copyright 2003 Jonathan Corbet <corbet@lwn.net> + This file is originally from the LWN.net Driver Porting series at http://lwn.net/Articles/driver-porting/ @@ -43,7 +48,7 @@ loadable module which creates a file called /proc/sequence. The file, when read, simply produces a set of increasing integer values, one per line. The sequence will continue until the user loses patience and finds something better to do. The file is seekable, in that one can do something like the -following: +following:: dd if=/proc/sequence of=out1 count=1 dd if=/proc/sequence skip=1 of=out2 count=1 @@ -55,16 +60,18 @@ wanting to see the full source for this module can find it at http://lwn.net/Articles/22359/). Deprecated create_proc_entry +============================ Note that the above article uses create_proc_entry which was removed in -kernel 3.10. Current versions require the following update +kernel 3.10. Current versions require the following update:: -- entry = create_proc_entry("sequence", 0, NULL); -- if (entry) -- entry->proc_fops = &ct_file_ops; -+ entry = proc_create("sequence", 0, NULL, &ct_file_ops); + - entry = create_proc_entry("sequence", 0, NULL); + - if (entry) + - entry->proc_fops = &ct_file_ops; + + entry = proc_create("sequence", 0, NULL, &ct_file_ops); The iterator interface +====================== Modules implementing a virtual file with seq_file must implement an iterator object that allows stepping through the data of interest @@ -99,7 +106,7 @@ position. The pos passed to start() will always be either zero, or the most recent pos used in the previous session. For our simple sequence example, -the start() function looks like: +the start() function looks like:: static void *ct_seq_start(struct seq_file *s, loff_t *pos) { @@ -129,7 +136,7 @@ move the iterator forward to the next position in the sequence. The example module can simply increment the position by one; more useful modules will do what is needed to step through some data structure. The next() function returns a new iterator, or NULL if the sequence is -complete. Here's the example version: +complete. Here's the example version:: static void *ct_seq_next(struct seq_file *s, void *v, loff_t *pos) { @@ -141,10 +148,10 @@ complete. Here's the example version: The stop() function closes a session; its job, of course, is to clean up. If dynamic memory is allocated for the iterator, stop() is the place to free it; if a lock was taken by start(), stop() must release -that lock. The value that *pos was set to by the last next() call +that lock. The value that ``*pos`` was set to by the last next() call before stop() is remembered, and used for the first start() call of the next session unless lseek() has been called on the file; in that -case next start() will be asked to start at position zero. +case next start() will be asked to start at position zero:: static void ct_seq_stop(struct seq_file *s, void *v) { @@ -152,7 +159,7 @@ case next start() will be asked to start at position zero. } Finally, the show() function should format the object currently pointed to -by the iterator for output. The example module's show() function is: +by the iterator for output. The example module's show() function is:: static int ct_seq_show(struct seq_file *s, void *v) { @@ -169,7 +176,7 @@ generated output before returning SEQ_SKIP, that output will be dropped. We will look at seq_printf() in a moment. But first, the definition of the seq_file iterator is finished by creating a seq_operations structure with -the four functions we have just defined: +the four functions we have just defined:: static const struct seq_operations ct_seq_ops = { .start = ct_seq_start, @@ -194,6 +201,7 @@ other locks while the iterator is active. Formatted output +================ The seq_file code manages positioning within the output created by the iterator and getting it into the user's buffer. But, for that to work, that @@ -203,7 +211,7 @@ been defined which make this task easy. Most code will simply use seq_printf(), which works pretty much like printk(), but which requires the seq_file pointer as an argument. -For straight character output, the following functions may be used: +For straight character output, the following functions may be used:: seq_putc(struct seq_file *m, char c); seq_puts(struct seq_file *m, const char *s); @@ -213,7 +221,7 @@ The first two output a single character and a string, just like one would expect. seq_escape() is like seq_puts(), except that any character in s which is in the string esc will be represented in octal form in the output. -There are also a pair of functions for printing filenames: +There are also a pair of functions for printing filenames:: int seq_path(struct seq_file *m, const struct path *path, const char *esc); @@ -226,8 +234,10 @@ the path relative to the current process's filesystem root. If a different root is desired, it can be used with seq_path_root(). If it turns out that path cannot be reached from root, seq_path_root() returns SEQ_SKIP. -A function producing complicated output may want to check +A function producing complicated output may want to check:: + bool seq_has_overflowed(struct seq_file *m); + and avoid further seq_<output> calls if true is returned. A true return from seq_has_overflowed means that the seq_file buffer will @@ -236,6 +246,7 @@ buffer and retry printing. Making it all work +================== So far, we have a nice set of functions which can produce output within the seq_file system, but we have not yet turned them into a file that a user @@ -244,7 +255,7 @@ creation of a set of file_operations which implement the operations on that file. The seq_file interface provides a set of canned operations which do most of the work. The virtual file author still must implement the open() method, however, to hook everything up. The open function is often a single -line, as in the example module: +line, as in the example module:: static int ct_open(struct inode *inode, struct file *file) { @@ -263,7 +274,7 @@ by the iterator functions. There is also a wrapper function to seq_open() called seq_open_private(). It kmallocs a zero filled block of memory and stores a pointer to it in the private field of the seq_file structure, returning 0 on success. The -block size is specified in a third parameter to the function, e.g.: +block size is specified in a third parameter to the function, e.g.:: static int ct_open(struct inode *inode, struct file *file) { @@ -273,7 +284,7 @@ block size is specified in a third parameter to the function, e.g.: There is also a variant function, __seq_open_private(), which is functionally identical except that, if successful, it returns the pointer to the allocated -memory block, allowing further initialisation e.g.: +memory block, allowing further initialisation e.g.:: static int ct_open(struct inode *inode, struct file *file) { @@ -295,7 +306,7 @@ frees the memory allocated in the corresponding open. The other operations of interest - read(), llseek(), and release() - are all implemented by the seq_file code itself. So a virtual file's -file_operations structure will look like: +file_operations structure will look like:: static const struct file_operations ct_file_ops = { .owner = THIS_MODULE, @@ -309,7 +320,7 @@ There is also a seq_release_private() which passes the contents of the seq_file private field to kfree() before releasing the structure. The final step is the creation of the /proc file itself. In the example -code, that is done in the initialization code in the usual way: +code, that is done in the initialization code in the usual way:: static int ct_init(void) { @@ -325,9 +336,10 @@ And that is pretty much it. seq_list +======== If your file will be iterating through a linked list, you may find these -routines useful: +routines useful:: struct list_head *seq_list_start(struct list_head *head, loff_t pos); @@ -338,15 +350,16 @@ routines useful: These helpers will interpret pos as a position within the list and iterate accordingly. Your start() and next() functions need only invoke the -seq_list_* helpers with a pointer to the appropriate list_head structure. +``seq_list_*`` helpers with a pointer to the appropriate list_head structure. The extra-simple version +======================== For extremely simple virtual files, there is an even easier interface. A module can define only the show() function, which should create all the output that the virtual file will contain. The file's open() method then -calls: +calls:: int single_open(struct file *file, int (*show)(struct seq_file *m, void *p), diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.rst index 8ccfbd55244b..d83395354250 100644 --- a/Documentation/filesystems/sharedsubtree.txt +++ b/Documentation/filesystems/sharedsubtree.rst @@ -1,7 +1,10 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============== Shared Subtrees ---------------- +=============== -Contents: +.. Contents: 1) Overview 2) Features 3) Setting mount states @@ -41,31 +44,38 @@ replicas continue to be exactly same. Here is an example: - Let's say /mnt has a mount that is shared. - mount --make-shared /mnt + Let's say /mnt has a mount that is shared:: + + mount --make-shared /mnt Note: mount(8) command now supports the --make-shared flag, so the sample 'smount' program is no longer needed and has been removed. - # mount --bind /mnt /tmp + :: + + # mount --bind /mnt /tmp + The above command replicates the mount at /mnt to the mountpoint /tmp and the contents of both the mounts remain identical. - #ls /mnt - a b c + :: - #ls /tmp - a b c + #ls /mnt + a b c - Now let's say we mount a device at /tmp/a - # mount /dev/sd0 /tmp/a + #ls /tmp + a b c - #ls /tmp/a - t1 t2 t3 + Now let's say we mount a device at /tmp/a:: - #ls /mnt/a - t1 t2 t3 + # mount /dev/sd0 /tmp/a + + #ls /tmp/a + t1 t2 t3 + + #ls /mnt/a + t1 t2 t3 Note that the mount has propagated to the mount at /mnt as well. @@ -123,14 +133,15 @@ replicas continue to be exactly same. 2d) A unbindable mount is a unbindable private mount - let's say we have a mount at /mnt and we make it unbindable + let's say we have a mount at /mnt and we make it unbindable:: + + # mount --make-unbindable /mnt - # mount --make-unbindable /mnt + Let's try to bind mount this mount somewhere else:: - Let's try to bind mount this mount somewhere else. - # mount --bind /mnt /tmp - mount: wrong fs type, bad option, bad superblock on /mnt, - or too many mounted file systems + # mount --bind /mnt /tmp + mount: wrong fs type, bad option, bad superblock on /mnt, + or too many mounted file systems Binding a unbindable mount is a invalid operation. @@ -138,12 +149,12 @@ replicas continue to be exactly same. 3) Setting mount states The mount command (util-linux package) can be used to set mount - states: + states:: - mount --make-shared mountpoint - mount --make-slave mountpoint - mount --make-private mountpoint - mount --make-unbindable mountpoint + mount --make-shared mountpoint + mount --make-slave mountpoint + mount --make-private mountpoint + mount --make-unbindable mountpoint 4) Use cases @@ -154,9 +165,10 @@ replicas continue to be exactly same. Solution: - The system administrator can make the mount at /cdrom shared - mount --bind /cdrom /cdrom - mount --make-shared /cdrom + The system administrator can make the mount at /cdrom shared:: + + mount --bind /cdrom /cdrom + mount --make-shared /cdrom Now any process that clones off a new namespace will have a mount at /cdrom which is a replica of the same mount in the @@ -172,14 +184,14 @@ replicas continue to be exactly same. Solution: To begin with, the administrator can mark the entire mount tree - as shareable. + as shareable:: - mount --make-rshared / + mount --make-rshared / A new process can clone off a new namespace. And mark some part - of its namespace as slave + of its namespace as slave:: - mount --make-rslave /myprivatetree + mount --make-rslave /myprivatetree Hence forth any mounts within the /myprivatetree done by the process will not show up in any other namespace. However mounts @@ -206,13 +218,13 @@ replicas continue to be exactly same. versions of the file depending on the path used to access that file. - An example is: + An example is:: - mount --make-shared / - mount --rbind / /view/v1 - mount --rbind / /view/v2 - mount --rbind / /view/v3 - mount --rbind / /view/v4 + mount --make-shared / + mount --rbind / /view/v1 + mount --rbind / /view/v2 + mount --rbind / /view/v3 + mount --rbind / /view/v4 and if /usr has a versioning filesystem mounted, then that mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and @@ -224,8 +236,8 @@ replicas continue to be exactly same. filesystem is being requested and return the corresponding inode. -5) Detailed semantics: -------------------- +5) Detailed semantics +--------------------- The section below explains the detailed semantics of bind, rbind, move, mount, umount and clone-namespace operations. @@ -235,6 +247,7 @@ replicas continue to be exactly same. 5a) Mount states A given mount can be in one of the following states + 1) shared 2) slave 3) shared and slave @@ -252,7 +265,8 @@ replicas continue to be exactly same. A 'shared mount' is defined as a vfsmount that belongs to a 'peer group'. - For example: + For example:: + mount --make-shared /mnt mount --bind /mnt /tmp @@ -270,7 +284,7 @@ replicas continue to be exactly same. A slave mount as the name implies has a master mount from which mount/unmount events are received. Events do not propagate from the slave mount to the master. Only a shared mount can be made - a slave by executing the following command + a slave by executing the following command:: mount --make-slave mount @@ -290,8 +304,10 @@ replicas continue to be exactly same. peer group. Only a slave vfsmount can be made as 'shared and slave' by - either executing the following command + either executing the following command:: + mount --make-shared mount + or by moving the slave vfsmount under a shared vfsmount. (4) Private mount @@ -307,30 +323,32 @@ replicas continue to be exactly same. State diagram: + The state diagram below explains the state transition of a mount, - in response to various commands. - ------------------------------------------------------------------------ - | |make-shared | make-slave | make-private |make-unbindab| - --------------|------------|--------------|--------------|-------------| - |shared |shared |*slave/private| private | unbindable | - | | | | | | - |-------------|------------|--------------|--------------|-------------| - |slave |shared | **slave | private | unbindable | - | |and slave | | | | - |-------------|------------|--------------|--------------|-------------| - |shared |shared | slave | private | unbindable | - |and slave |and slave | | | | - |-------------|------------|--------------|--------------|-------------| - |private |shared | **private | private | unbindable | - |-------------|------------|--------------|--------------|-------------| - |unbindable |shared |**unbindable | private | unbindable | - ------------------------------------------------------------------------ - - * if the shared mount is the only mount in its peer group, making it - slave, makes it private automatically. Note that there is no master to - which it can be slaved to. - - ** slaving a non-shared mount has no effect on the mount. + in response to various commands:: + + ----------------------------------------------------------------------- + | |make-shared | make-slave | make-private |make-unbindab| + --------------|------------|--------------|--------------|-------------| + |shared |shared |*slave/private| private | unbindable | + | | | | | | + |-------------|------------|--------------|--------------|-------------| + |slave |shared | **slave | private | unbindable | + | |and slave | | | | + |-------------|------------|--------------|--------------|-------------| + |shared |shared | slave | private | unbindable | + |and slave |and slave | | | | + |-------------|------------|--------------|--------------|-------------| + |private |shared | **private | private | unbindable | + |-------------|------------|--------------|--------------|-------------| + |unbindable |shared |**unbindable | private | unbindable | + ------------------------------------------------------------------------ + + * if the shared mount is the only mount in its peer group, making it + slave, makes it private automatically. Note that there is no master to + which it can be slaved to. + + ** slaving a non-shared mount has no effect on the mount. Apart from the commands listed below, the 'move' operation also changes the state of a mount depending on type of the destination mount. Its @@ -338,31 +356,32 @@ replicas continue to be exactly same. 5b) Bind semantics - Consider the following command + Consider the following command:: - mount --bind A/a B/b + mount --bind A/a B/b where 'A' is the source mount, 'a' is the dentry in the mount 'A', 'B' is the destination mount and 'b' is the dentry in the destination mount. The outcome depends on the type of mount of 'A' and 'B'. The table - below contains quick reference. - --------------------------------------------------------------------------- - | BIND MOUNT OPERATION | - |************************************************************************** - |source(A)->| shared | private | slave | unbindable | - | dest(B) | | | | | - | | | | | | | - | v | | | | | - |************************************************************************** - | shared | shared | shared | shared & slave | invalid | - | | | | | | - |non-shared| shared | private | slave | invalid | - *************************************************************************** + below contains quick reference:: + + -------------------------------------------------------------------------- + | BIND MOUNT OPERATION | + |************************************************************************| + |source(A)->| shared | private | slave | unbindable | + | dest(B) | | | | | + | | | | | | | + | v | | | | | + |************************************************************************| + | shared | shared | shared | shared & slave | invalid | + | | | | | | + |non-shared| shared | private | slave | invalid | + ************************************************************************** Details: - 1. 'A' is a shared mount and 'B' is a shared mount. A new mount 'C' + 1. 'A' is a shared mount and 'B' is a shared mount. A new mount 'C' which is clone of 'A', is created. Its root dentry is 'a' . 'C' is mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ... are created and mounted at the dentry 'b' on all mounts where 'B' @@ -371,7 +390,7 @@ replicas continue to be exactly same. 'B'. And finally the peer-group of 'C' is merged with the peer group of 'A'. - 2. 'A' is a private mount and 'B' is a shared mount. A new mount 'C' + 2. 'A' is a private mount and 'B' is a shared mount. A new mount 'C' which is clone of 'A', is created. Its root dentry is 'a'. 'C' is mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ... are created and mounted at the dentry 'b' on all mounts where 'B' @@ -379,7 +398,7 @@ replicas continue to be exactly same. 'C', 'C1', .., 'Cn' with exactly the same configuration as the propagation tree for 'B'. - 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. A new + 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. A new mount 'C' which is clone of 'A', is created. Its root dentry is 'a' . 'C' is mounted on mount 'B' at dentry 'b'. Also new mounts 'C1', 'C2', 'C3' ... are created and mounted at the dentry 'b' on all mounts where @@ -389,19 +408,19 @@ replicas continue to be exactly same. is made the slave of mount 'Z'. In other words, mount 'C' is in the state 'slave and shared'. - 4. 'A' is a unbindable mount and 'B' is a shared mount. This is a + 4. 'A' is a unbindable mount and 'B' is a shared mount. This is a invalid operation. - 5. 'A' is a private mount and 'B' is a non-shared(private or slave or + 5. 'A' is a private mount and 'B' is a non-shared(private or slave or unbindable) mount. A new mount 'C' which is clone of 'A', is created. Its root dentry is 'a'. 'C' is mounted on mount 'B' at dentry 'b'. - 6. 'A' is a shared mount and 'B' is a non-shared mount. A new mount 'C' + 6. 'A' is a shared mount and 'B' is a non-shared mount. A new mount 'C' which is a clone of 'A' is created. Its root dentry is 'a'. 'C' is mounted on mount 'B' at dentry 'b'. 'C' is made a member of the peer-group of 'A'. - 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. A + 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. A new mount 'C' which is a clone of 'A' is created. Its root dentry is 'a'. 'C' is mounted on mount 'B' at dentry 'b'. Also 'C' is set as a slave mount of 'Z'. In other words 'A' and 'C' are both slave mounts of @@ -409,7 +428,7 @@ replicas continue to be exactly same. mount/unmount on 'A' do not propagate anywhere else. Similarly mount/unmount on 'C' do not propagate anywhere else. - 8. 'A' is a unbindable mount and 'B' is a non-shared mount. This is a + 8. 'A' is a unbindable mount and 'B' is a non-shared mount. This is a invalid operation. A unbindable mount cannot be bind mounted. 5c) Rbind semantics @@ -422,7 +441,9 @@ replicas continue to be exactly same. then the subtree under the unbindable mount is pruned in the new location. - eg: let's say we have the following mount tree. + eg: + + let's say we have the following mount tree:: A / \ @@ -430,12 +451,12 @@ replicas continue to be exactly same. / \ / \ D E F G - Let's say all the mount except the mount C in the tree are - of a type other than unbindable. + Let's say all the mount except the mount C in the tree are + of a type other than unbindable. - If this tree is rbound to say Z + If this tree is rbound to say Z - We will have the following tree at the new location. + We will have the following tree at the new location:: Z | @@ -457,24 +478,26 @@ replicas continue to be exactly same. the dentry in the destination mount. The outcome depends on the type of the mount of 'A' and 'B'. The table - below is a quick reference. - --------------------------------------------------------------------------- - | MOVE MOUNT OPERATION | - |************************************************************************** - | source(A)->| shared | private | slave | unbindable | - | dest(B) | | | | | - | | | | | | | - | v | | | | | - |************************************************************************** - | shared | shared | shared |shared and slave| invalid | - | | | | | | - |non-shared| shared | private | slave | unbindable | - *************************************************************************** - NOTE: moving a mount residing under a shared mount is invalid. + below is a quick reference:: + + --------------------------------------------------------------------------- + | MOVE MOUNT OPERATION | + |************************************************************************** + | source(A)->| shared | private | slave | unbindable | + | dest(B) | | | | | + | | | | | | | + | v | | | | | + |************************************************************************** + | shared | shared | shared |shared and slave| invalid | + | | | | | | + |non-shared| shared | private | slave | unbindable | + *************************************************************************** + + .. Note:: moving a mount residing under a shared mount is invalid. Details follow: - 1. 'A' is a shared mount and 'B' is a shared mount. The mount 'A' is + 1. 'A' is a shared mount and 'B' is a shared mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. Also new mounts 'A1', 'A2'...'An' are created and mounted at dentry 'b' on all mounts that receive propagation from mount 'B'. A new propagation tree is created in the @@ -483,7 +506,7 @@ replicas continue to be exactly same. propagation tree is appended to the already existing propagation tree of 'A'. - 2. 'A' is a private mount and 'B' is a shared mount. The mount 'A' is + 2. 'A' is a private mount and 'B' is a shared mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. Also new mount 'A1', 'A2'... 'An' are created and mounted at dentry 'b' on all mounts that receive propagation from mount 'B'. The mount 'A' becomes a shared mount and a @@ -491,7 +514,7 @@ replicas continue to be exactly same. 'B'. This new propagation tree contains all the new mounts 'A1', 'A2'... 'An'. - 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. The + 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. Also new mounts 'A1', 'A2'... 'An' are created and mounted at dentry 'b' on all mounts that receive propagation from mount 'B'. A new propagation tree is created @@ -501,32 +524,32 @@ replicas continue to be exactly same. 'A'. Mount 'A' continues to be the slave mount of 'Z' but it also becomes 'shared'. - 4. 'A' is a unbindable mount and 'B' is a shared mount. The operation + 4. 'A' is a unbindable mount and 'B' is a shared mount. The operation is invalid. Because mounting anything on the shared mount 'B' can create new mounts that get mounted on the mounts that receive propagation from 'B'. And since the mount 'A' is unbindable, cloning it to mount at other mountpoints is not possible. - 5. 'A' is a private mount and 'B' is a non-shared(private or slave or + 5. 'A' is a private mount and 'B' is a non-shared(private or slave or unbindable) mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. - 6. 'A' is a shared mount and 'B' is a non-shared mount. The mount 'A' + 6. 'A' is a shared mount and 'B' is a non-shared mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a shared mount. - 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. + 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a slave mount of mount 'Z'. - 8. 'A' is a unbindable mount and 'B' is a non-shared mount. The mount + 8. 'A' is a unbindable mount and 'B' is a non-shared mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a unbindable mount. 5e) Mount semantics - Consider the following command + Consider the following command:: - mount device B/b + mount device B/b 'B' is the destination mount and 'b' is the dentry in the destination mount. @@ -537,9 +560,9 @@ replicas continue to be exactly same. 5f) Unmount semantics - Consider the following command + Consider the following command:: - umount A + umount A where 'A' is a mount mounted on mount 'B' at dentry 'b'. @@ -592,10 +615,12 @@ replicas continue to be exactly same. A. What is the result of the following command sequence? - mount --bind /mnt /mnt - mount --make-shared /mnt - mount --bind /mnt /tmp - mount --move /tmp /mnt/1 + :: + + mount --bind /mnt /mnt + mount --make-shared /mnt + mount --bind /mnt /tmp + mount --move /tmp /mnt/1 what should be the contents of /mnt /mnt/1 /mnt/1/1 should be? Should they all be identical? or should /mnt and /mnt/1 be @@ -604,23 +629,27 @@ replicas continue to be exactly same. B. What is the result of the following command sequence? - mount --make-rshared / - mkdir -p /v/1 - mount --rbind / /v/1 + :: + + mount --make-rshared / + mkdir -p /v/1 + mount --rbind / /v/1 what should be the content of /v/1/v/1 be? C. What is the result of the following command sequence? - mount --bind /mnt /mnt - mount --make-shared /mnt - mkdir -p /mnt/1/2/3 /mnt/1/test - mount --bind /mnt/1 /tmp - mount --make-slave /mnt - mount --make-shared /mnt - mount --bind /mnt/1/2 /tmp1 - mount --make-slave /mnt + :: + + mount --bind /mnt /mnt + mount --make-shared /mnt + mkdir -p /mnt/1/2/3 /mnt/1/test + mount --bind /mnt/1 /tmp + mount --make-slave /mnt + mount --make-shared /mnt + mount --bind /mnt/1/2 /tmp1 + mount --make-slave /mnt At this point we have the first mount at /tmp and its root dentry is 1. Let's call this mount 'A' @@ -668,7 +697,8 @@ replicas continue to be exactly same. step 1: let's say the root tree has just two directories with - one vfsmount. + one vfsmount:: + root / \ tmp usr @@ -676,14 +706,17 @@ replicas continue to be exactly same. And we want to replicate the tree at multiple mountpoints under /root/tmp - step2: - mount --make-shared /root + step 2: + :: - mkdir -p /tmp/m1 - mount --rbind /root /tmp/m1 + mount --make-shared /root - the new tree now looks like this: + mkdir -p /tmp/m1 + + mount --rbind /root /tmp/m1 + + the new tree now looks like this:: root / \ @@ -697,11 +730,13 @@ replicas continue to be exactly same. it has two vfsmounts - step3: + step 3: + :: + mkdir -p /tmp/m2 mount --rbind /root /tmp/m2 - the new tree now looks like this: + the new tree now looks like this:: root / \ @@ -724,6 +759,7 @@ replicas continue to be exactly same. it has 6 vfsmounts step 4: + :: mkdir -p /tmp/m3 mount --rbind /root /tmp/m3 @@ -740,7 +776,8 @@ replicas continue to be exactly same. step 1: let's say the root tree has just two directories with - one vfsmount. + one vfsmount:: + root / \ tmp usr @@ -748,17 +785,20 @@ replicas continue to be exactly same. How do we set up the same tree at multiple locations under /root/tmp - step2: - mount --bind /root/tmp /root/tmp + step 2: + :: - mount --make-rshared /root - mount --make-unbindable /root/tmp - mkdir -p /tmp/m1 + mount --bind /root/tmp /root/tmp - mount --rbind /root /tmp/m1 + mount --make-rshared /root + mount --make-unbindable /root/tmp - the new tree now looks like this: + mkdir -p /tmp/m1 + + mount --rbind /root /tmp/m1 + + the new tree now looks like this:: root / \ @@ -768,11 +808,13 @@ replicas continue to be exactly same. / \ tmp usr - step3: + step 3: + :: + mkdir -p /tmp/m2 mount --rbind /root /tmp/m2 - the new tree now looks like this: + the new tree now looks like this:: root / \ @@ -782,12 +824,13 @@ replicas continue to be exactly same. / \ / \ tmp usr tmp usr - step4: + step 4: + :: mkdir -p /tmp/m3 mount --rbind /root /tmp/m3 - the new tree now looks like this: + the new tree now looks like this:: root / \ @@ -801,25 +844,31 @@ replicas continue to be exactly same. 8A) Datastructure - 4 new fields are introduced to struct vfsmount - ->mnt_share - ->mnt_slave_list - ->mnt_slave - ->mnt_master + 4 new fields are introduced to struct vfsmount: + + * ->mnt_share + * ->mnt_slave_list + * ->mnt_slave + * ->mnt_master - ->mnt_share links together all the mount to/from which this vfsmount + ->mnt_share + links together all the mount to/from which this vfsmount send/receives propagation events. - ->mnt_slave_list links all the mounts to which this vfsmount propagates + ->mnt_slave_list + links all the mounts to which this vfsmount propagates to. - ->mnt_slave links together all the slaves that its master vfsmount + ->mnt_slave + links together all the slaves that its master vfsmount propagates to. - ->mnt_master points to the master vfsmount from which this vfsmount + ->mnt_master + points to the master vfsmount from which this vfsmount receives propagation. - ->mnt_flags takes two more flags to indicate the propagation status of + ->mnt_flags + takes two more flags to indicate the propagation status of the vfsmount. MNT_SHARE indicates that the vfsmount is a shared vfsmount. MNT_UNCLONABLE indicates that the vfsmount cannot be replicated. @@ -842,7 +891,7 @@ replicas continue to be exactly same. A example propagation tree looks as shown in the figure below. [ NOTE: Though it looks like a forest, if we consider all the shared - mounts as a conceptual entity called 'pnode', it becomes a tree] + mounts as a conceptual entity called 'pnode', it becomes a tree]:: A <--> B <--> C <---> D @@ -864,14 +913,19 @@ replicas continue to be exactly same. A's ->mnt_slave_list links with ->mnt_slave of 'E', 'K', 'F' and 'G' E's ->mnt_share links with ->mnt_share of K - 'E', 'K', 'F', 'G' have their ->mnt_master point to struct - vfsmount of 'A' + + 'E', 'K', 'F', 'G' have their ->mnt_master point to struct vfsmount of 'A' + 'M', 'L', 'N' have their ->mnt_master point to struct vfsmount of 'K' + K's ->mnt_slave_list links with ->mnt_slave of 'M', 'L' and 'N' C's ->mnt_slave_list links with ->mnt_slave of 'J' and 'K' + J and K's ->mnt_master points to struct vfsmount of C + and finally D's ->mnt_slave_list links with ->mnt_slave of 'H' and 'I' + 'H' and 'I' have their ->mnt_master pointing to struct vfsmount of 'D'. @@ -903,6 +957,7 @@ replicas continue to be exactly same. Prepare phase: for each mount in the source tree: + a) Create the necessary number of mount trees to be attached to each of the mounts that receive propagation from the destination mount. @@ -929,11 +984,12 @@ replicas continue to be exactly same. Abort phase delete all the newly created trees. - NOTE: all the propagation related functionality resides in the file - pnode.c + .. Note:: + all the propagation related functionality resides in the file pnode.c ------------------------------------------------------------------------ version 0.1 (created the initial document, Ram Pai linuxram@us.ibm.com) + version 0.2 (Incorporated comments from Al Viro) diff --git a/Documentation/filesystems/spufs/index.rst b/Documentation/filesystems/spufs/index.rst new file mode 100644 index 000000000000..5ed4a8494967 --- /dev/null +++ b/Documentation/filesystems/spufs/index.rst @@ -0,0 +1,13 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============== +SPU Filesystem +============== + + +.. toctree:: + :maxdepth: 1 + + spufs + spu_create + spu_run diff --git a/Documentation/filesystems/spufs/spu_create.rst b/Documentation/filesystems/spufs/spu_create.rst new file mode 100644 index 000000000000..83108c099696 --- /dev/null +++ b/Documentation/filesystems/spufs/spu_create.rst @@ -0,0 +1,131 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========== +spu_create +========== + +Name +==== + spu_create - create a new spu context + + +Synopsis +======== + + :: + + #include <sys/types.h> + #include <sys/spu.h> + + int spu_create(const char *pathname, int flags, mode_t mode); + +Description +=========== + The spu_create system call is used on PowerPC machines that implement + the Cell Broadband Engine Architecture in order to access Synergistic + Processor Units (SPUs). It creates a new logical context for an SPU in + pathname and returns a handle to associated with it. pathname must + point to a non-existing directory in the mount point of the SPU file + system (spufs). When spu_create is successful, a directory gets cre- + ated on pathname and it is populated with files. + + The returned file handle can only be passed to spu_run(2) or closed, + other operations are not defined on it. When it is closed, all associ- + ated directory entries in spufs are removed. When the last file handle + pointing either inside of the context directory or to this file + descriptor is closed, the logical SPU context is destroyed. + + The parameter flags can be zero or any bitwise or'd combination of the + following constants: + + SPU_RAWIO + Allow mapping of some of the hardware registers of the SPU into + user space. This flag requires the CAP_SYS_RAWIO capability, see + capabilities(7). + + The mode parameter specifies the permissions used for creating the new + directory in spufs. mode is modified with the user's umask(2) value + and then used for both the directory and the files contained in it. The + file permissions mask out some more bits of mode because they typically + support only read or write access. See stat(2) for a full list of the + possible mode values. + + +Return Value +============ + spu_create returns a new file descriptor. It may return -1 to indicate + an error condition and set errno to one of the error codes listed + below. + + +Errors +====== + EACCES + The current user does not have write access on the spufs mount + point. + + EEXIST An SPU context already exists at the given path name. + + EFAULT pathname is not a valid string pointer in the current address + space. + + EINVAL pathname is not a directory in the spufs mount point. + + ELOOP Too many symlinks were found while resolving pathname. + + EMFILE The process has reached its maximum open file limit. + + ENAMETOOLONG + pathname was too long. + + ENFILE The system has reached the global open file limit. + + ENOENT Part of pathname could not be resolved. + + ENOMEM The kernel could not allocate all resources required. + + ENOSPC There are not enough SPU resources available to create a new + context or the user specific limit for the number of SPU con- + texts has been reached. + + ENOSYS the functionality is not provided by the current system, because + either the hardware does not provide SPUs or the spufs module is + not loaded. + + ENOTDIR + A part of pathname is not a directory. + + + +Notes +===== + spu_create is meant to be used from libraries that implement a more + abstract interface to SPUs, not to be used from regular applications. + See http://www.bsc.es/projects/deepcomputing/linuxoncell/ for the rec- + ommended libraries. + + +Files +===== + pathname must point to a location beneath the mount point of spufs. By + convention, it gets mounted in /spu. + + +Conforming to +============= + This call is Linux specific and only implemented by the ppc64 architec- + ture. Programs using this system call are not portable. + + +Bugs +==== + The code does not yet fully implement all features lined out here. + + +Author +====== + Arnd Bergmann <arndb@de.ibm.com> + +See Also +======== + capabilities(7), close(2), spu_run(2), spufs(7) diff --git a/Documentation/filesystems/spufs/spu_run.rst b/Documentation/filesystems/spufs/spu_run.rst new file mode 100644 index 000000000000..7fdb1c31cb91 --- /dev/null +++ b/Documentation/filesystems/spufs/spu_run.rst @@ -0,0 +1,138 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======= +spu_run +======= + + +Name +==== + spu_run - execute an spu context + + +Synopsis +======== + + :: + + #include <sys/spu.h> + + int spu_run(int fd, unsigned int *npc, unsigned int *event); + +Description +=========== + The spu_run system call is used on PowerPC machines that implement the + Cell Broadband Engine Architecture in order to access Synergistic Pro- + cessor Units (SPUs). It uses the fd that was returned from spu_cre- + ate(2) to address a specific SPU context. When the context gets sched- + uled to a physical SPU, it starts execution at the instruction pointer + passed in npc. + + Execution of SPU code happens synchronously, meaning that spu_run does + not return while the SPU is still running. If there is a need to exe- + cute SPU code in parallel with other code on either the main CPU or + other SPUs, you need to create a new thread of execution first, e.g. + using the pthread_create(3) call. + + When spu_run returns, the current value of the SPU instruction pointer + is written back to npc, so you can call spu_run again without updating + the pointers. + + event can be a NULL pointer or point to an extended status code that + gets filled when spu_run returns. It can be one of the following con- + stants: + + SPE_EVENT_DMA_ALIGNMENT + A DMA alignment error + + SPE_EVENT_SPE_DATA_SEGMENT + A DMA segmentation error + + SPE_EVENT_SPE_DATA_STORAGE + A DMA storage error + + If NULL is passed as the event argument, these errors will result in a + signal delivered to the calling process. + +Return Value +============ + spu_run returns the value of the spu_status register or -1 to indicate + an error and set errno to one of the error codes listed below. The + spu_status register value contains a bit mask of status codes and + optionally a 14 bit code returned from the stop-and-signal instruction + on the SPU. The bit masks for the status codes are: + + 0x02 + SPU was stopped by stop-and-signal. + + 0x04 + SPU was stopped by halt. + + 0x08 + SPU is waiting for a channel. + + 0x10 + SPU is in single-step mode. + + 0x20 + SPU has tried to execute an invalid instruction. + + 0x40 + SPU has tried to access an invalid channel. + + 0x3fff0000 + The bits masked with this value contain the code returned from + stop-and-signal. + + There are always one or more of the lower eight bits set or an error + code is returned from spu_run. + +Errors +====== + EAGAIN or EWOULDBLOCK + fd is in non-blocking mode and spu_run would block. + + EBADF fd is not a valid file descriptor. + + EFAULT npc is not a valid pointer or status is neither NULL nor a valid + pointer. + + EINTR A signal occurred while spu_run was in progress. The npc value + has been updated to the new program counter value if necessary. + + EINVAL fd is not a file descriptor returned from spu_create(2). + + ENOMEM Insufficient memory was available to handle a page fault result- + ing from an MFC direct memory access. + + ENOSYS the functionality is not provided by the current system, because + either the hardware does not provide SPUs or the spufs module is + not loaded. + + +Notes +===== + spu_run is meant to be used from libraries that implement a more + abstract interface to SPUs, not to be used from regular applications. + See http://www.bsc.es/projects/deepcomputing/linuxoncell/ for the rec- + ommended libraries. + + +Conforming to +============= + This call is Linux specific and only implemented by the ppc64 architec- + ture. Programs using this system call are not portable. + + +Bugs +==== + The code does not yet fully implement all features lined out here. + + +Author +====== + Arnd Bergmann <arndb@de.ibm.com> + +See Also +======== + capabilities(7), close(2), spu_create(2), spufs(7) diff --git a/Documentation/filesystems/spufs.txt b/Documentation/filesystems/spufs/spufs.rst index eb9e3aa63026..8a42859bb100 100644 --- a/Documentation/filesystems/spufs.txt +++ b/Documentation/filesystems/spufs/spufs.rst @@ -1,12 +1,18 @@ -SPUFS(2) Linux Programmer's Manual SPUFS(2) +.. SPDX-License-Identifier: GPL-2.0 +===== +spufs +===== +Name +==== -NAME spufs - the SPU file system -DESCRIPTION +Description +=========== + The SPU file system is used on PowerPC machines that implement the Cell Broadband Engine Architecture in order to access Synergistic Processor Units (SPUs). @@ -21,7 +27,9 @@ DESCRIPTION ally add or remove files. -MOUNT OPTIONS +Mount Options +============= + uid=<uid> set the user owning the mount point, the default is 0 (root). @@ -29,7 +37,9 @@ MOUNT OPTIONS set the group owning the mount point, the default is 0 (root). -FILES +Files +===== + The files in spufs mostly follow the standard behavior for regular sys- tem calls like read(2) or write(2), but often support only a subset of the operations supported on regular file systems. This list details the @@ -125,14 +135,12 @@ FILES space is available for writing. - /mbox_stat - /ibox_stat - /wbox_stat + /mbox_stat, /ibox_stat, /wbox_stat Read-only files that contain the length of the current queue, i.e. how many words can be read from mbox or ibox or how many words can be written to wbox without blocking. The files can be read only in 4-byte units and return a big-endian binary integer number. The possible - operations on an open *box_stat file are: + operations on an open ``*box_stat`` file are: read(2) If a count smaller than four is requested, read returns -1 and @@ -143,12 +151,7 @@ FILES in EAGAIN. - /npc - /decr - /decr_status - /spu_tag_mask - /event_mask - /srr0 + /npc, /decr, /decr_status, /spu_tag_mask, /event_mask, /srr0 Internal registers of the SPU. The representation is an ASCII string with the numeric value of the next instruction to be executed. These can be used in read/write mode for debugging, but normal operation of @@ -157,17 +160,14 @@ FILES The contents of these files are: + =================== =================================== npc Next Program Counter - decr SPU Decrementer - decr_status Decrementer Status - spu_tag_mask MFC tag mask for SPU DMA - event_mask Event mask for SPU interrupts - srr0 Interrupt Return address register + =================== =================================== The possible operations on an open npc, decr, decr_status, @@ -206,8 +206,7 @@ FILES from the data buffer, updating the value of the fpcr register. - /signal1 - /signal2 + /signal1, /signal2 The two signal notification channels of an SPU. These are read-write files that operate on a 32 bit word. Writing to one of these files triggers an interrupt on the SPU. The value written to the signal @@ -233,8 +232,7 @@ FILES file. - /signal1_type - /signal2_type + /signal1_type, /signal2_type These two files change the behavior of the signal1 and signal2 notifi- cation files. The contain a numerical ASCII string which is read as either "1" or "0". In mode 0 (overwrite), the hardware replaces the @@ -259,263 +257,17 @@ FILES the previous setting. -EXAMPLES +Examples +======== /etc/fstab entry none /spu spufs gid=spu 0 0 -AUTHORS +Authors +======= Arnd Bergmann <arndb@de.ibm.com>, Mark Nutter <mnutter@us.ibm.com>, Ulrich Weigand <Ulrich.Weigand@de.ibm.com> -SEE ALSO +See Also +======== capabilities(7), close(2), spu_create(2), spu_run(2), spufs(7) - - - -Linux 2005-09-28 SPUFS(2) - ------------------------------------------------------------------------------- - -SPU_RUN(2) Linux Programmer's Manual SPU_RUN(2) - - - -NAME - spu_run - execute an spu context - - -SYNOPSIS - #include <sys/spu.h> - - int spu_run(int fd, unsigned int *npc, unsigned int *event); - -DESCRIPTION - The spu_run system call is used on PowerPC machines that implement the - Cell Broadband Engine Architecture in order to access Synergistic Pro- - cessor Units (SPUs). It uses the fd that was returned from spu_cre- - ate(2) to address a specific SPU context. When the context gets sched- - uled to a physical SPU, it starts execution at the instruction pointer - passed in npc. - - Execution of SPU code happens synchronously, meaning that spu_run does - not return while the SPU is still running. If there is a need to exe- - cute SPU code in parallel with other code on either the main CPU or - other SPUs, you need to create a new thread of execution first, e.g. - using the pthread_create(3) call. - - When spu_run returns, the current value of the SPU instruction pointer - is written back to npc, so you can call spu_run again without updating - the pointers. - - event can be a NULL pointer or point to an extended status code that - gets filled when spu_run returns. It can be one of the following con- - stants: - - SPE_EVENT_DMA_ALIGNMENT - A DMA alignment error - - SPE_EVENT_SPE_DATA_SEGMENT - A DMA segmentation error - - SPE_EVENT_SPE_DATA_STORAGE - A DMA storage error - - If NULL is passed as the event argument, these errors will result in a - signal delivered to the calling process. - -RETURN VALUE - spu_run returns the value of the spu_status register or -1 to indicate - an error and set errno to one of the error codes listed below. The - spu_status register value contains a bit mask of status codes and - optionally a 14 bit code returned from the stop-and-signal instruction - on the SPU. The bit masks for the status codes are: - - 0x02 SPU was stopped by stop-and-signal. - - 0x04 SPU was stopped by halt. - - 0x08 SPU is waiting for a channel. - - 0x10 SPU is in single-step mode. - - 0x20 SPU has tried to execute an invalid instruction. - - 0x40 SPU has tried to access an invalid channel. - - 0x3fff0000 - The bits masked with this value contain the code returned from - stop-and-signal. - - There are always one or more of the lower eight bits set or an error - code is returned from spu_run. - -ERRORS - EAGAIN or EWOULDBLOCK - fd is in non-blocking mode and spu_run would block. - - EBADF fd is not a valid file descriptor. - - EFAULT npc is not a valid pointer or status is neither NULL nor a valid - pointer. - - EINTR A signal occurred while spu_run was in progress. The npc value - has been updated to the new program counter value if necessary. - - EINVAL fd is not a file descriptor returned from spu_create(2). - - ENOMEM Insufficient memory was available to handle a page fault result- - ing from an MFC direct memory access. - - ENOSYS the functionality is not provided by the current system, because - either the hardware does not provide SPUs or the spufs module is - not loaded. - - -NOTES - spu_run is meant to be used from libraries that implement a more - abstract interface to SPUs, not to be used from regular applications. - See http://www.bsc.es/projects/deepcomputing/linuxoncell/ for the rec- - ommended libraries. - - -CONFORMING TO - This call is Linux specific and only implemented by the ppc64 architec- - ture. Programs using this system call are not portable. - - -BUGS - The code does not yet fully implement all features lined out here. - - -AUTHOR - Arnd Bergmann <arndb@de.ibm.com> - -SEE ALSO - capabilities(7), close(2), spu_create(2), spufs(7) - - - -Linux 2005-09-28 SPU_RUN(2) - ------------------------------------------------------------------------------- - -SPU_CREATE(2) Linux Programmer's Manual SPU_CREATE(2) - - - -NAME - spu_create - create a new spu context - - -SYNOPSIS - #include <sys/types.h> - #include <sys/spu.h> - - int spu_create(const char *pathname, int flags, mode_t mode); - -DESCRIPTION - The spu_create system call is used on PowerPC machines that implement - the Cell Broadband Engine Architecture in order to access Synergistic - Processor Units (SPUs). It creates a new logical context for an SPU in - pathname and returns a handle to associated with it. pathname must - point to a non-existing directory in the mount point of the SPU file - system (spufs). When spu_create is successful, a directory gets cre- - ated on pathname and it is populated with files. - - The returned file handle can only be passed to spu_run(2) or closed, - other operations are not defined on it. When it is closed, all associ- - ated directory entries in spufs are removed. When the last file handle - pointing either inside of the context directory or to this file - descriptor is closed, the logical SPU context is destroyed. - - The parameter flags can be zero or any bitwise or'd combination of the - following constants: - - SPU_RAWIO - Allow mapping of some of the hardware registers of the SPU into - user space. This flag requires the CAP_SYS_RAWIO capability, see - capabilities(7). - - The mode parameter specifies the permissions used for creating the new - directory in spufs. mode is modified with the user's umask(2) value - and then used for both the directory and the files contained in it. The - file permissions mask out some more bits of mode because they typically - support only read or write access. See stat(2) for a full list of the - possible mode values. - - -RETURN VALUE - spu_create returns a new file descriptor. It may return -1 to indicate - an error condition and set errno to one of the error codes listed - below. - - -ERRORS - EACCES - The current user does not have write access on the spufs mount - point. - - EEXIST An SPU context already exists at the given path name. - - EFAULT pathname is not a valid string pointer in the current address - space. - - EINVAL pathname is not a directory in the spufs mount point. - - ELOOP Too many symlinks were found while resolving pathname. - - EMFILE The process has reached its maximum open file limit. - - ENAMETOOLONG - pathname was too long. - - ENFILE The system has reached the global open file limit. - - ENOENT Part of pathname could not be resolved. - - ENOMEM The kernel could not allocate all resources required. - - ENOSPC There are not enough SPU resources available to create a new - context or the user specific limit for the number of SPU con- - texts has been reached. - - ENOSYS the functionality is not provided by the current system, because - either the hardware does not provide SPUs or the spufs module is - not loaded. - - ENOTDIR - A part of pathname is not a directory. - - - -NOTES - spu_create is meant to be used from libraries that implement a more - abstract interface to SPUs, not to be used from regular applications. - See http://www.bsc.es/projects/deepcomputing/linuxoncell/ for the rec- - ommended libraries. - - -FILES - pathname must point to a location beneath the mount point of spufs. By - convention, it gets mounted in /spu. - - -CONFORMING TO - This call is Linux specific and only implemented by the ppc64 architec- - ture. Programs using this system call are not portable. - - -BUGS - The code does not yet fully implement all features lined out here. - - -AUTHOR - Arnd Bergmann <arndb@de.ibm.com> - -SEE ALSO - capabilities(7), close(2), spu_run(2), spufs(7) - - - -Linux 2005-09-28 SPU_CREATE(2) diff --git a/Documentation/filesystems/sysfs-pci.txt b/Documentation/filesystems/sysfs-pci.rst index 06f1d64c6f70..a265f3e2cc80 100644 --- a/Documentation/filesystems/sysfs-pci.txt +++ b/Documentation/filesystems/sysfs-pci.rst @@ -1,8 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================================ Accessing PCI device resources through sysfs --------------------------------------------- +============================================ sysfs, usually mounted at /sys, provides access to PCI resources on platforms -that support it. For example, a given bus might look like this: +that support it. For example, a given bus might look like this:: /sys/devices/pci0000:17 |-- 0000:17:00.0 @@ -30,8 +33,9 @@ This bus contains a single function device in slot 0. The domain and bus numbers are reproduced for convenience. Under the device directory are several files, each with their own function. + =================== ===================================================== file function - ---- -------- + =================== ===================================================== class PCI class (ascii, ro) config PCI config space (binary, rw) device PCI device (ascii, ro) @@ -40,13 +44,16 @@ files, each with their own function. local_cpus nearby CPU mask (cpumask, ro) remove remove device from kernel's list (ascii, wo) resource PCI resource host addresses (ascii, ro) - resource0..N PCI resource N, if present (binary, mmap, rw[1]) + resource0..N PCI resource N, if present (binary, mmap, rw\ [1]_) resource0_wc..N_wc PCI WC map resource N, if prefetchable (binary, mmap) revision PCI revision (ascii, ro) rom PCI ROM resource, if present (binary, ro) subsystem_device PCI subsystem device (ascii, ro) subsystem_vendor PCI subsystem vendor (ascii, ro) vendor PCI vendor (ascii, ro) + =================== ===================================================== + +:: ro - read only file rw - file is readable and writable @@ -56,7 +63,7 @@ files, each with their own function. binary - file contains binary data cpumask - file contains a cpumask type -[1] rw for RESOURCE_IO (I/O port) regions only +.. [1] rw for RESOURCE_IO (I/O port) regions only The read only files are informational, writes to them will be ignored, with the exception of the 'rom' file. Writable files can be used to perform @@ -67,11 +74,11 @@ don't support mmapping of certain resources, so be sure to check the return value from any attempted mmap. The most notable of these are I/O port resources, which also provide read/write access. -The 'enable' file provides a counter that indicates how many times the device +The 'enable' file provides a counter that indicates how many times the device has been enabled. If the 'enable' file currently returns '4', and a '1' is echoed into it, it will then return '5'. Echoing a '0' into it will decrease the count. Even when it returns to 0, though, some of the initialisation -may not be reversed. +may not be reversed. The 'rom' file is special in that it provides read-only access to the device's ROM file, if available. It's disabled by default, however, so applications @@ -93,7 +100,7 @@ Accessing legacy resources through sysfs Legacy I/O port and ISA memory resources are also provided in sysfs if the underlying platform supports them. They're located in the PCI class hierarchy, -e.g. +e.g.:: /sys/class/pci_bus/0000:17/ |-- bridge -> ../../../devices/pci0000:17 diff --git a/Documentation/filesystems/sysfs-tagging.txt b/Documentation/filesystems/sysfs-tagging.rst index c7c8e6438958..8888a05c398e 100644 --- a/Documentation/filesystems/sysfs-tagging.txt +++ b/Documentation/filesystems/sysfs-tagging.rst @@ -1,5 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============= Sysfs tagging -------------- +============= (Taken almost verbatim from Eric Biederman's netns tagging patch commit msg) @@ -18,25 +21,28 @@ in the directories and applications only see a limited set of the network devices. Each sysfs directory entry may be tagged with a namespace via the -void *ns member of its kernfs_node. If a directory entry is tagged, -then kernfs_node->flags will have a flag between KOBJ_NS_TYPE_NONE +``void *ns member`` of its ``kernfs_node``. If a directory entry is tagged, +then ``kernfs_node->flags`` will have a flag between KOBJ_NS_TYPE_NONE and KOBJ_NS_TYPES, and ns will point to the namespace to which it belongs. -Each sysfs superblock's kernfs_super_info contains an array void -*ns[KOBJ_NS_TYPES]. When a task in a tagging namespace +Each sysfs superblock's kernfs_super_info contains an array +``void *ns[KOBJ_NS_TYPES]``. When a task in a tagging namespace kobj_nstype first mounts sysfs, a new superblock is created. It will be differentiated from other sysfs mounts by having its -s_fs_info->ns[kobj_nstype] set to the new namespace. Note that +``s_fs_info->ns[kobj_nstype]`` set to the new namespace. Note that through bind mounting and mounts propagation, a task can easily view the contents of other namespaces' sysfs mounts. Therefore, when a namespace exits, it will call kobj_ns_exit() to invalidate any kernfs_node->ns pointers pointing to it. Users of this interface: -- define a type in the kobj_ns_type enumeration. -- call kobj_ns_type_register() with its kobj_ns_type_operations which has + +- define a type in the ``kobj_ns_type`` enumeration. +- call kobj_ns_type_register() with its ``kobj_ns_type_operations`` which has + - current_ns() which returns current's namespace - netlink_ns() which returns a socket's namespace - initial_ns() which returns the initial namesapce + - call kobj_ns_exit() when an individual tag is no longer valid diff --git a/Documentation/filesystems/sysfs.rst b/Documentation/filesystems/sysfs.rst index 290891c3fecb..ab0f7795792b 100644 --- a/Documentation/filesystems/sysfs.rst +++ b/Documentation/filesystems/sysfs.rst @@ -20,7 +20,7 @@ a means to export kernel data structures, their attributes, and the linkages between them to userspace. sysfs is tied inherently to the kobject infrastructure. Please read -Documentation/kobject.txt for more information concerning the kobject +Documentation/core-api/kobject.rst for more information concerning the kobject interface. diff --git a/Documentation/filesystems/xfs-delayed-logging-design.txt b/Documentation/filesystems/xfs-delayed-logging-design.rst index 9a6dd289b17b..464405d2801e 100644 --- a/Documentation/filesystems/xfs-delayed-logging-design.txt +++ b/Documentation/filesystems/xfs-delayed-logging-design.rst @@ -1,8 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================== XFS Delayed Logging Design --------------------------- +========================== Introduction to Re-logging in XFS ---------------------------------- +================================= XFS logging is a combination of logical and physical logging. Some objects, such as inodes and dquots, are logged in logical format where the details @@ -25,7 +28,7 @@ changes in the new transaction that is written to the log. That is, if we have a sequence of changes A through to F, and the object was written to disk after change D, we would see in the log the following series of transactions, their contents and the log sequence number (LSN) of the -transaction: +transaction:: Transaction Contents LSN A A X @@ -85,7 +88,7 @@ IO permanently. Hence the XFS journalling subsystem can be considered to be IO bound. Delayed Logging: Concepts -------------------------- +========================= The key thing to note about the asynchronous logging combined with the relogging technique XFS uses is that we can be relogging changed objects @@ -154,9 +157,10 @@ The fundamental requirements for delayed logging in XFS are simple: 6. No performance regressions for synchronous transaction workloads. Delayed Logging: Design ------------------------ +======================= Storing Changes +--------------- The problem with accumulating changes at a logical level (i.e. just using the existing log item dirty region tracking) is that when it comes to writing the @@ -194,30 +198,30 @@ asynchronous transactions to the log. The differences between the existing formatting method and the delayed logging formatting can be seen in the diagram below. -Current format log vector: +Current format log vector:: -Object +---------------------------------------------+ -Vector 1 +----+ -Vector 2 +----+ -Vector 3 +----------+ + Object +---------------------------------------------+ + Vector 1 +----+ + Vector 2 +----+ + Vector 3 +----------+ -After formatting: +After formatting:: -Log Buffer +-V1-+-V2-+----V3----+ + Log Buffer +-V1-+-V2-+----V3----+ -Delayed logging vector: +Delayed logging vector:: -Object +---------------------------------------------+ -Vector 1 +----+ -Vector 2 +----+ -Vector 3 +----------+ + Object +---------------------------------------------+ + Vector 1 +----+ + Vector 2 +----+ + Vector 3 +----------+ -After formatting: +After formatting:: -Memory Buffer +-V1-+-V2-+----V3----+ -Vector 1 +----+ -Vector 2 +----+ -Vector 3 +----------+ + Memory Buffer +-V1-+-V2-+----V3----+ + Vector 1 +----+ + Vector 2 +----+ + Vector 3 +----------+ The memory buffer and associated vector need to be passed as a single object, but still need to be associated with the parent object so if the object is @@ -242,6 +246,7 @@ relogged in memory. Tracking Changes +---------------- Now that we can record transactional changes in memory in a form that allows them to be used without limitations, we need to be able to track and accumulate @@ -278,6 +283,7 @@ done for convenience/sanity of the developers. Delayed Logging: Checkpoints +---------------------------- When we have a log synchronisation event, commonly known as a "log force", all the items in the CIL must be written into the log via the log buffers. @@ -341,7 +347,7 @@ Hence log vectors need to be able to be chained together to allow them to be detached from the log items. That is, when the CIL is flushed the memory buffer and log vector attached to each log item needs to be attached to the checkpoint context so that the log item can be released. In diagrammatic form, -the CIL would look like this before the flush: +the CIL would look like this before the flush:: CIL Head | @@ -362,7 +368,7 @@ the CIL would look like this before the flush: -> vector array And after the flush the CIL head is empty, and the checkpoint context log -vector list would look like: +vector list would look like:: Checkpoint Context | @@ -411,6 +417,7 @@ compare" situation that can be done after a working and reviewed implementation is in the dev tree.... Delayed Logging: Checkpoint Sequencing +-------------------------------------- One of the key aspects of the XFS transaction subsystem is that it tags committed transactions with the log sequence number of the transaction commit. @@ -474,6 +481,7 @@ force the log at the LSN of that transaction) and so the higher level code behaves the same regardless of whether delayed logging is being used or not. Delayed Logging: Checkpoint Log Space Accounting +------------------------------------------------ The big issue for a checkpoint transaction is the log space reservation for the transaction. We don't know how big a checkpoint transaction is going to be @@ -491,7 +499,7 @@ the size of the transaction and the number of regions being logged (the number of log vectors in the transaction). An example of the differences would be logging directory changes versus logging -inode changes. If you modify lots of inode cores (e.g. chmod -R g+w *), then +inode changes. If you modify lots of inode cores (e.g. ``chmod -R g+w *``), then there are lots of transactions that only contain an inode core and an inode log format structure. That is, two vectors totaling roughly 150 bytes. If we modify 10,000 inodes, we have about 1.5MB of metadata to write in 20,000 vectors. Each @@ -565,6 +573,7 @@ which is once every 30s. Delayed Logging: Log Item Pinning +--------------------------------- Currently log items are pinned during transaction commit while the items are still locked. This happens just after the items are formatted, though it could @@ -605,6 +614,7 @@ object, we have a race with CIL being flushed between the check and the pin lock to guarantee that we pin the items correctly. Delayed Logging: Concurrent Scalability +--------------------------------------- A fundamental requirement for the CIL is that accesses through transaction commits must scale to many concurrent commits. The current transaction commit @@ -683,8 +693,9 @@ woken by the wrong event. Lifecycle Changes +----------------- -The existing log item life cycle is as follows: +The existing log item life cycle is as follows:: 1. Transaction allocate 2. Transaction reserve @@ -729,7 +740,7 @@ at the same time. If the log item is in the AIL or between steps 6 and 7 and steps 1-6 are re-entered, then the item is relogged. Only when steps 8-9 are entered and completed is the object considered clean. -With delayed logging, there are new steps inserted into the life cycle: +With delayed logging, there are new steps inserted into the life cycle:: 1. Transaction allocate 2. Transaction reserve diff --git a/Documentation/filesystems/xfs-self-describing-metadata.txt b/Documentation/filesystems/xfs-self-describing-metadata.rst index 8db0121d0980..51cdafe01ab1 100644 --- a/Documentation/filesystems/xfs-self-describing-metadata.txt +++ b/Documentation/filesystems/xfs-self-describing-metadata.rst @@ -1,8 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================ XFS Self Describing Metadata ----------------------------- +============================ Introduction ------------- +============ The largest scalability problem facing XFS is not one of algorithmic scalability, but of verification of the filesystem structure. Scalabilty of the @@ -34,7 +37,7 @@ required for basic forensic analysis of the filesystem structure. Self Describing Metadata ------------------------- +======================== One of the problems with the current metadata format is that apart from the magic number in the metadata block, we have no other way of identifying what it @@ -142,7 +145,7 @@ modification occurred between the corruption being written and when it was detected. Runtime Validation ------------------- +================== Validation of self-describing metadata takes place at runtime in two places: @@ -183,18 +186,18 @@ error occurs during this process, the buffer is again marked with a EFSCORRUPTED error for the higher layers to catch. Structures ----------- +========== -A typical on-disk structure needs to contain the following information: +A typical on-disk structure needs to contain the following information:: -struct xfs_ondisk_hdr { - __be32 magic; /* magic number */ - __be32 crc; /* CRC, not logged */ - uuid_t uuid; /* filesystem identifier */ - __be64 owner; /* parent object */ - __be64 blkno; /* location on disk */ - __be64 lsn; /* last modification in log, not logged */ -}; + struct xfs_ondisk_hdr { + __be32 magic; /* magic number */ + __be32 crc; /* CRC, not logged */ + uuid_t uuid; /* filesystem identifier */ + __be64 owner; /* parent object */ + __be64 blkno; /* location on disk */ + __be64 lsn; /* last modification in log, not logged */ + }; Depending on the metadata, this information may be part of a header structure separate to the metadata contents, or may be distributed through an existing @@ -214,24 +217,24 @@ level of information is generally provided. For example: well. hence the additional metadata headers change the overall format of the metadata. -A typical buffer read verifier is structured as follows: +A typical buffer read verifier is structured as follows:: -#define XFS_FOO_CRC_OFF offsetof(struct xfs_ondisk_hdr, crc) + #define XFS_FOO_CRC_OFF offsetof(struct xfs_ondisk_hdr, crc) -static void -xfs_foo_read_verify( - struct xfs_buf *bp) -{ - struct xfs_mount *mp = bp->b_mount; + static void + xfs_foo_read_verify( + struct xfs_buf *bp) + { + struct xfs_mount *mp = bp->b_mount; - if ((xfs_sb_version_hascrc(&mp->m_sb) && - !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length), - XFS_FOO_CRC_OFF)) || - !xfs_foo_verify(bp)) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); - xfs_buf_ioerror(bp, EFSCORRUPTED); - } -} + if ((xfs_sb_version_hascrc(&mp->m_sb) && + !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length), + XFS_FOO_CRC_OFF)) || + !xfs_foo_verify(bp)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); + xfs_buf_ioerror(bp, EFSCORRUPTED); + } + } The code ensures that the CRC is only checked if the filesystem has CRCs enabled by checking the superblock of the feature bit, and then if the CRC verifies OK @@ -239,83 +242,83 @@ by checking the superblock of the feature bit, and then if the CRC verifies OK The verifier function will take a couple of different forms, depending on whether the magic number can be used to determine the format of the block. In -the case it can't, the code is structured as follows: +the case it can't, the code is structured as follows:: -static bool -xfs_foo_verify( - struct xfs_buf *bp) -{ - struct xfs_mount *mp = bp->b_mount; - struct xfs_ondisk_hdr *hdr = bp->b_addr; + static bool + xfs_foo_verify( + struct xfs_buf *bp) + { + struct xfs_mount *mp = bp->b_mount; + struct xfs_ondisk_hdr *hdr = bp->b_addr; - if (hdr->magic != cpu_to_be32(XFS_FOO_MAGIC)) - return false; + if (hdr->magic != cpu_to_be32(XFS_FOO_MAGIC)) + return false; - if (!xfs_sb_version_hascrc(&mp->m_sb)) { - if (!uuid_equal(&hdr->uuid, &mp->m_sb.sb_uuid)) - return false; - if (bp->b_bn != be64_to_cpu(hdr->blkno)) - return false; - if (hdr->owner == 0) - return false; - } + if (!xfs_sb_version_hascrc(&mp->m_sb)) { + if (!uuid_equal(&hdr->uuid, &mp->m_sb.sb_uuid)) + return false; + if (bp->b_bn != be64_to_cpu(hdr->blkno)) + return false; + if (hdr->owner == 0) + return false; + } - /* object specific verification checks here */ + /* object specific verification checks here */ - return true; -} + return true; + } If there are different magic numbers for the different formats, the verifier -will look like: - -static bool -xfs_foo_verify( - struct xfs_buf *bp) -{ - struct xfs_mount *mp = bp->b_mount; - struct xfs_ondisk_hdr *hdr = bp->b_addr; - - if (hdr->magic == cpu_to_be32(XFS_FOO_CRC_MAGIC)) { - if (!uuid_equal(&hdr->uuid, &mp->m_sb.sb_uuid)) - return false; - if (bp->b_bn != be64_to_cpu(hdr->blkno)) - return false; - if (hdr->owner == 0) - return false; - } else if (hdr->magic != cpu_to_be32(XFS_FOO_MAGIC)) - return false; - - /* object specific verification checks here */ - - return true; -} +will look like:: + + static bool + xfs_foo_verify( + struct xfs_buf *bp) + { + struct xfs_mount *mp = bp->b_mount; + struct xfs_ondisk_hdr *hdr = bp->b_addr; + + if (hdr->magic == cpu_to_be32(XFS_FOO_CRC_MAGIC)) { + if (!uuid_equal(&hdr->uuid, &mp->m_sb.sb_uuid)) + return false; + if (bp->b_bn != be64_to_cpu(hdr->blkno)) + return false; + if (hdr->owner == 0) + return false; + } else if (hdr->magic != cpu_to_be32(XFS_FOO_MAGIC)) + return false; + + /* object specific verification checks here */ + + return true; + } Write verifiers are very similar to the read verifiers, they just do things in -the opposite order to the read verifiers. A typical write verifier: +the opposite order to the read verifiers. A typical write verifier:: -static void -xfs_foo_write_verify( - struct xfs_buf *bp) -{ - struct xfs_mount *mp = bp->b_mount; - struct xfs_buf_log_item *bip = bp->b_fspriv; + static void + xfs_foo_write_verify( + struct xfs_buf *bp) + { + struct xfs_mount *mp = bp->b_mount; + struct xfs_buf_log_item *bip = bp->b_fspriv; - if (!xfs_foo_verify(bp)) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); - xfs_buf_ioerror(bp, EFSCORRUPTED); - return; - } + if (!xfs_foo_verify(bp)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); + xfs_buf_ioerror(bp, EFSCORRUPTED); + return; + } - if (!xfs_sb_version_hascrc(&mp->m_sb)) - return; + if (!xfs_sb_version_hascrc(&mp->m_sb)) + return; - if (bip) { - struct xfs_ondisk_hdr *hdr = bp->b_addr; - hdr->lsn = cpu_to_be64(bip->bli_item.li_lsn); - } - xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_FOO_CRC_OFF); -} + if (bip) { + struct xfs_ondisk_hdr *hdr = bp->b_addr; + hdr->lsn = cpu_to_be64(bip->bli_item.li_lsn); + } + xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_FOO_CRC_OFF); + } This will verify the internal structure of the metadata before we go any further, detecting corruptions that have occurred as the metadata has been @@ -324,7 +327,7 @@ update the LSN field (when it was last modified) and calculate the CRC on the metadata. Once this is done, we can issue the IO. Inodes and Dquots ------------------ +================= Inodes and dquots are special snowflakes. They have per-object CRC and self-identifiers, but they are packed so that there are multiple objects per @@ -347,4 +350,3 @@ XXX: inode unlinked list modification doesn't recalculate the inode CRC! None of the unlinked list modifications check or update CRCs, neither during unlink nor log recovery. So, it's gone unnoticed until now. This won't matter immediately - repair will probably complain about it - but it needs to be fixed. - |