From 07fe7cb7c7c179f473fd9c823348fd3eb5dad369 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Create a dynamically sized pool of threads for doing very slow work items Create a dynamically sized pool of threads for doing very slow work items, such as invoking mkdir() or rmdir() - things that may take a long time and may sleep, holding mutexes/semaphores and hogging a thread, and are thus unsuitable for workqueues. The number of threads is always at least a settable minimum, but more are started when there's more work to do, up to a limit. Because of the nature of the load, it's not suitable for a 1-thread-per-CPU type pool. A system with one CPU may well want several threads. This is used by FS-Cache to do slow caching operations in the background, such as looking up, creating or deleting cache objects. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 88 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) create mode 100644 include/linux/slow-work.h (limited to 'include') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h new file mode 100644 index 00000000000..4dd754af393 --- /dev/null +++ b/include/linux/slow-work.h @@ -0,0 +1,88 @@ +/* Worker thread pool for slow items, such as filesystem lookups or mkdirs + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _LINUX_SLOW_WORK_H +#define _LINUX_SLOW_WORK_H + +#ifdef CONFIG_SLOW_WORK + +struct slow_work; + +/* + * The operations used to support slow work items + */ +struct slow_work_ops { + /* get a ref on a work item + * - return 0 if successful, -ve if not + */ + int (*get_ref)(struct slow_work *work); + + /* discard a ref to a work item */ + void (*put_ref)(struct slow_work *work); + + /* execute a work item */ + void (*execute)(struct slow_work *work); +}; + +/* + * A slow work item + * - A reference is held on the parent object by the thread pool when it is + * queued + */ +struct slow_work { + unsigned long flags; +#define SLOW_WORK_PENDING 0 /* item pending (further) execution */ +#define SLOW_WORK_EXECUTING 1 /* item currently executing */ +#define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */ +#define SLOW_WORK_VERY_SLOW 3 /* item is very slow */ + const struct slow_work_ops *ops; /* operations table for this item */ + struct list_head link; /* link in queue */ +}; + +/** + * slow_work_init - Initialise a slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a slow work item. + */ +static inline void slow_work_init(struct slow_work *work, + const struct slow_work_ops *ops) +{ + work->flags = 0; + work->ops = ops; + INIT_LIST_HEAD(&work->link); +} + +/** + * slow_work_init - Initialise a very slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a very slow work item. This item will be restricted such that + * only a certain number of the pool threads will be able to execute items of + * this type. + */ +static inline void vslow_work_init(struct slow_work *work, + const struct slow_work_ops *ops) +{ + work->flags = 1 << SLOW_WORK_VERY_SLOW; + work->ops = ops; + INIT_LIST_HEAD(&work->link); +} + +extern int slow_work_enqueue(struct slow_work *work); +extern int slow_work_register_user(void); +extern void slow_work_unregister_user(void); + + +#endif /* CONFIG_SLOW_WORK */ +#endif /* _LINUX_SLOW_WORK_H */ -- cgit v1.2.3 From 12e22c5e4bc08ab4b05ac079fe40d9891c5e81a0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Make the slow work pool configurable Make the slow work pool configurable through /proc/sys/kernel/slow-work. (*) /proc/sys/kernel/slow-work/min-threads The minimum number of threads that should be in the pool as long as it is in use. This may be anywhere between 2 and max-threads. (*) /proc/sys/kernel/slow-work/max-threads The maximum number of threads that should in the pool. This may be anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater. (*) /proc/sys/kernel/slow-work/vslow-percentage The percentage of active threads in the pool that may be used to execute very slow work items. This may be between 1 and 99. The resultant number is bounded to between 1 and one fewer than the number of active threads. This ensures there is always at least one thread that can process very slow work items, and always at least one thread that won't. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index 4dd754af393..8262809dfa8 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -14,6 +14,8 @@ #ifdef CONFIG_SLOW_WORK +#include + struct slow_work; /* @@ -83,6 +85,9 @@ extern int slow_work_enqueue(struct slow_work *work); extern int slow_work_register_user(void); extern void slow_work_unregister_user(void); +#ifdef CONFIG_SYSCTL +extern ctl_table slow_work_sysctls[]; +#endif #endif /* CONFIG_SLOW_WORK */ #endif /* _LINUX_SLOW_WORK_H */ -- cgit v1.2.3 From 8f0aa2f25b31ba27db84259141e52ee6ec0d2820 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Document the slow work thread pool Document the slow work thread pool. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index 8262809dfa8..85958277f83 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -7,6 +7,8 @@ * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. + * + * See Documentation/slow-work.txt */ #ifndef _LINUX_SLOW_WORK_H -- cgit v1.2.3 From 03fb3d2af96c2783c3a5bc03f3d984cf422f0e69 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: FS-Cache: Release page->private after failed readahead The attached patch causes read_cache_pages() to release page-private data on a page for which add_to_page_cache() fails. If the filler function fails, then the problematic page is left attached to the pagecache (with appropriate flags set, one presumes) and the remaining to-be-attached pages are invalidated and discarded. This permits pages with caching references associated with them to be cleaned up. The invalidatepage() address space op is called (indirectly) to do the honours. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Rik van Riel Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 61df1779b2a..9d99e7471ad 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -182,7 +182,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } struct page; /* forward declaration */ -TESTPAGEFLAG(Locked, locked) +TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked) PAGEFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) -- cgit v1.2.3 From 266cf658efcf6ac33541a46740f74f50c79d2b6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:36 +0100 Subject: FS-Cache: Recruit a page flags for cache management Recruit a page flag to aid in cache management. The following extra flag is defined: (1) PG_fscache (PG_private_2) The marked page is backed by a local cache and is pinning resources in the cache driver. If PG_fscache is set, then things that checked for PG_private will now also check for that. This includes things like truncation and page invalidation. The function page_has_private() had been added to make the checks for both PG_private and PG_private_2 at the same time. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Rik van Riel Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/page-flags.h | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d99e7471ad..62214c7d2d9 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -82,6 +82,7 @@ enum pageflags { PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ + PG_private_2, /* If pagecache, has fs aux data */ PG_writeback, /* Page is under writeback */ #ifdef CONFIG_PAGEFLAGS_EXTENDED PG_head, /* A head page */ @@ -108,6 +109,12 @@ enum pageflags { /* Filesystems */ PG_checked = PG_owner_priv_1, + /* Two page bits are conscripted by FS-Cache to maintain local caching + * state. These bits are set on pages belonging to the netfs's inodes + * when those inodes are being locally cached. + */ + PG_fscache = PG_private_2, /* page backed by cache */ + /* XEN */ PG_pinned = PG_owner_priv_1, PG_savepinned = PG_dirty, @@ -194,8 +201,6 @@ PAGEFLAG(Checked, checked) /* Used by some filesystems */ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) -PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) - __SETPAGEFLAG(Private, private) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobPage, slob_page) @@ -204,6 +209,16 @@ __PAGEFLAG(SlobFree, slob_free) __PAGEFLAG(SlubFrozen, slub_frozen) __PAGEFLAG(SlubDebug, slub_debug) +/* + * Private page markings that may be used by the filesystem that owns the page + * for its own purposes. + * - PG_private and PG_private_2 cause releasepage() and co to be invoked + */ +PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) + __CLEARPAGEFLAG(Private, private) +PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2) +PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) + /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. @@ -384,9 +399,10 @@ static inline void __ClearPageTail(struct page *page) * these flags set. It they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ - (1 << PG_lru | 1 << PG_private | 1 << PG_locked | \ - 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ - 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ + (1 << PG_lru | 1 << PG_locked | \ + 1 << PG_private | 1 << PG_private_2 | \ + 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ + 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ __PG_UNEVICTABLE | __PG_MLOCKED) /* @@ -397,4 +413,16 @@ static inline void __ClearPageTail(struct page *page) #define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1) #endif /* !__GENERATING_BOUNDS_H */ + +/** + * page_has_private - Determine if page has private stuff + * @page: The page to be checked + * + * Determine if a page has private stuff, indicating that release routines + * should be invoked upon it. + */ +#define page_has_private(page) \ + ((page)->flags & ((1 << PG_private) | \ + (1 << PG_private_2))) + #endif /* PAGE_FLAGS_H */ -- cgit v1.2.3 From 2d6fff637037395cc946ef910a880b5fa67b5370 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:36 +0100 Subject: FS-Cache: Add the FS-Cache netfs API and documentation Add the API for a generic facility (FS-Cache) by which filesystems (such as AFS or NFS) may call on local caching capabilities without having to know anything about how the cache works, or even if there is a cache: +---------+ | | +--------------+ | NFS |--+ | | | | | +-->| CacheFS | +---------+ | +----------+ | | /dev/hda5 | | | | | +--------------+ +---------+ +-->| | | | | | |--+ | AFS |----->| FS-Cache | | | | |--+ +---------+ +-->| | | | | | | +--------------+ +---------+ | +----------+ | | | | | | +-->| CacheFiles | | ISOFS |--+ | /var/cache | | | +--------------+ +---------+ General documentation and documentation of the netfs specific API are provided in addition to the header files. As this patch stands, it is possible to build a filesystem against the facility and attempt to use it. All that will happen is that all requests will be immediately denied as if no cache is present. Further patches will implement the core of the facility. The facility will transfer requests from networking filesystems to appropriate caches if possible, or else gracefully deny them. If this facility is disabled in the kernel configuration, then all its operations will trivially reduce to nothing during compilation. WHY NOT I_MAPPING? ================== I have added my own API to implement caching rather than using i_mapping to do this for a number of reasons. These have been discussed a lot on the LKML and CacheFS mailing lists, but to summarise the basics: (1) Most filesystems don't do hole reportage. Holes in files are treated as blocks of zeros and can't be distinguished otherwise, making it difficult to distinguish blocks that have been read from the network and cached from those that haven't. (2) The backing inode must be fully populated before being exposed to userspace through the main inode because the VM/VFS goes directly to the backing inode and does not interrogate the front inode's VM ops. Therefore: (a) The backing inode must fit entirely within the cache. (b) All backed files currently open must fit entirely within the cache at the same time. (c) A working set of files in total larger than the cache may not be cached. (d) A file may not grow larger than the available space in the cache. (e) A file that's open and cached, and remotely grows larger than the cache is potentially stuffed. (3) Writes go to the backing filesystem, and can only be transferred to the network when the file is closed. (4) There's no record of what changes have been made, so the whole file must be written back. (5) The pages belong to the backing filesystem, and all metadata associated with that page are relevant only to the backing filesystem, and not anything stacked atop it. OVERVIEW ======== FS-Cache provides (or will provide) the following facilities: (1) Caches can be added / removed at any time, even whilst in use. (2) Adds a facility by which tags can be used to refer to caches, even if they're not available yet. (3) More than one cache can be used at once. Caches can be selected explicitly by use of tags. (4) The netfs is provided with an interface that allows either party to withdraw caching facilities from a file (required for (1)). (5) A netfs may annotate cache objects that belongs to it. This permits the storage of coherency maintenance data. (6) Cache objects will be pinnable and space reservations will be possible. (7) The interface to the netfs returns as few errors as possible, preferring rather to let the netfs remain oblivious. (8) 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. (9) 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. (10) Indices can be used to group files together to reduce key size and to make group invalidation easier. The use of indices may make lookup quicker, but that's cache dependent. (11) Data I/O is effectively done directly 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. (12) 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. (13) 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. FS-Cache maintains a virtual index 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, two netfs's can be seen to be backed: NFS and AFS. These have different index hierarchies: (*) The NFS primary index will probably contain 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 FS-Cache overview can be found in: Documentation/filesystems/caching/fscache.txt The netfs API to FS-Cache can be found in: Documentation/filesystems/caching/netfs-api.txt Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 548 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 548 insertions(+) create mode 100644 include/linux/fscache.h (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h new file mode 100644 index 00000000000..feb3b0e0af4 --- /dev/null +++ b/include/linux/fscache.h @@ -0,0 +1,548 @@ +/* General filesystem caching interface + * + * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * NOTE!!! See: + * + * Documentation/filesystems/caching/netfs-api.txt + * + * for a description of the network filesystem interface declared here. + */ + +#ifndef _LINUX_FSCACHE_H +#define _LINUX_FSCACHE_H + +#include +#include +#include +#include + +#if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) +#define fscache_available() (1) +#define fscache_cookie_valid(cookie) (cookie) +#else +#define fscache_available() (0) +#define fscache_cookie_valid(cookie) (0) +#endif + + +/* + * overload PG_private_2 to give us PG_fscache - this is used to indicate that + * a page is currently backed by a local disk cache + */ +#define PageFsCache(page) PagePrivate2((page)) +#define SetPageFsCache(page) SetPagePrivate2((page)) +#define ClearPageFsCache(page) ClearPagePrivate2((page)) +#define TestSetPageFsCache(page) TestSetPagePrivate2((page)) +#define TestClearPageFsCache(page) TestClearPagePrivate2((page)) + +/* pattern used to fill dead space in an index entry */ +#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79 + +struct pagevec; +struct fscache_cache_tag; +struct fscache_cookie; +struct fscache_netfs; + +typedef void (*fscache_rw_complete_t)(struct page *page, + void *context, + int error); + +/* result of index entry consultation */ +enum fscache_checkaux { + FSCACHE_CHECKAUX_OKAY, /* entry okay as is */ + FSCACHE_CHECKAUX_NEEDS_UPDATE, /* entry requires update */ + FSCACHE_CHECKAUX_OBSOLETE, /* entry requires deletion */ +}; + +/* + * fscache cookie definition + */ +struct fscache_cookie_def { + /* name of cookie type */ + char name[16]; + + /* cookie type */ + uint8_t type; +#define FSCACHE_COOKIE_TYPE_INDEX 0 +#define FSCACHE_COOKIE_TYPE_DATAFILE 1 + + /* select the cache into which to insert an entry in this index + * - optional + * - should return a cache identifier or NULL to cause the cache to be + * inherited from the parent if possible or the first cache picked + * for a non-index file if not + */ + struct fscache_cache_tag *(*select_cache)( + const void *parent_netfs_data, + const void *cookie_netfs_data); + + /* get an index key + * - should store the key data in the buffer + * - should return the amount of amount stored + * - not permitted to return an error + * - the netfs data from the cookie being used as the source is + * presented + */ + uint16_t (*get_key)(const void *cookie_netfs_data, + void *buffer, + uint16_t bufmax); + + /* get certain file attributes from the netfs data + * - this function can be absent for an index + * - not permitted to return an error + * - the netfs data from the cookie being used as the source is + * presented + */ + void (*get_attr)(const void *cookie_netfs_data, uint64_t *size); + + /* get the auxilliary data from netfs data + * - this function can be absent if the index carries no state data + * - should store the auxilliary data in the buffer + * - should return the amount of amount stored + * - not permitted to return an error + * - the netfs data from the cookie being used as the source is + * presented + */ + uint16_t (*get_aux)(const void *cookie_netfs_data, + void *buffer, + uint16_t bufmax); + + /* consult the netfs about the state of an object + * - this function can be absent if the index carries no state data + * - the netfs data from the cookie being used as the target is + * presented, as is the auxilliary data + */ + enum fscache_checkaux (*check_aux)(void *cookie_netfs_data, + const void *data, + uint16_t datalen); + + /* get an extra reference on a read context + * - this function can be absent if the completion function doesn't + * require a context + */ + void (*get_context)(void *cookie_netfs_data, void *context); + + /* release an extra reference on a read context + * - this function can be absent if the completion function doesn't + * require a context + */ + void (*put_context)(void *cookie_netfs_data, void *context); + + /* indicate pages that now have cache metadata retained + * - this function should mark the specified pages as now being cached + * - the pages will have been marked with PG_fscache before this is + * called, so this is optional + */ + void (*mark_pages_cached)(void *cookie_netfs_data, + struct address_space *mapping, + struct pagevec *cached_pvec); + + /* indicate the cookie is no longer cached + * - this function is called when the backing store currently caching + * a cookie is removed + * - the netfs should use this to clean up any markers indicating + * cached pages + * - this is mandatory for any object that may have data + */ + void (*now_uncached)(void *cookie_netfs_data); +}; + +/* + * fscache cached network filesystem type + * - name, version and ops must be filled in before registration + * - all other fields will be set during registration + */ +struct fscache_netfs { + uint32_t version; /* indexing version */ + const char *name; /* filesystem name */ + struct fscache_cookie *primary_index; + struct list_head link; /* internal link */ +}; + +/* + * slow-path functions for when there is actually caching available, and the + * netfs does actually have a valid token + * - these are not to be called directly + * - these are undefined symbols when FS-Cache is not configured and the + * optimiser takes care of not using them + */ + +/** + * fscache_register_netfs - Register a filesystem as desiring caching services + * @netfs: The description of the filesystem + * + * Register a filesystem as desiring caching services if they're available. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_register_netfs(struct fscache_netfs *netfs) +{ + return 0; +} + +/** + * fscache_unregister_netfs - Indicate that a filesystem no longer desires + * caching services + * @netfs: The description of the filesystem + * + * Indicate that a filesystem no longer desires caching services for the + * moment. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_unregister_netfs(struct fscache_netfs *netfs) +{ +} + +/** + * fscache_lookup_cache_tag - Look up a cache tag + * @name: The name of the tag to search for + * + * Acquire a specific cache referral tag that can be used to select a specific + * cache in which to cache an index. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) +{ + return NULL; +} + +/** + * fscache_release_cache_tag - Release a cache tag + * @tag: The tag to release + * + * Release a reference to a cache referral tag previously looked up. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_release_cache_tag(struct fscache_cache_tag *tag) +{ +} + +/** + * fscache_acquire_cookie - Acquire a cookie to represent a cache object + * @parent: The cookie that's to be the parent of this one + * @def: A description of the cache object, including callback operations + * @netfs_data: An arbitrary piece of data to be kept in the cookie to + * represent the cache object to the netfs + * + * This function is used 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. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +struct fscache_cookie *fscache_acquire_cookie( + struct fscache_cookie *parent, + const struct fscache_cookie_def *def, + void *netfs_data) +{ + return NULL; +} + +/** + * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding + * it + * @cookie: The cookie being returned + * @retire: True if the cache object the cookie represents is to be discarded + * + * This function returns a cookie to the cache, forcibly discarding the + * associated cache object if retire is set to true. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) +{ +} + +/** + * fscache_update_cookie - Request that a cache object be updated + * @cookie: The cookie representing the cache object + * + * Request an update of the index data for the cache object associated with the + * cookie. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_update_cookie(struct fscache_cookie *cookie) +{ +} + +/** + * fscache_pin_cookie - Pin a data-storage cache object in its cache + * @cookie: The cookie representing the cache object + * + * Permit data-storage cache objects to be pinned in the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_pin_cookie(struct fscache_cookie *cookie) +{ + return -ENOBUFS; +} + +/** + * fscache_pin_cookie - Unpin a data-storage cache object in its cache + * @cookie: The cookie representing the cache object + * + * Permit data-storage cache objects to be unpinned from the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_unpin_cookie(struct fscache_cookie *cookie) +{ +} + +/** + * fscache_attr_changed - Notify cache that an object's attributes changed + * @cookie: The cookie representing the cache object + * + * Send a notification to the cache indicating that an object's attributes have + * changed. This includes the data size. These attributes will be obtained + * through the get_attr() cookie definition op. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_attr_changed(struct fscache_cookie *cookie) +{ + return -ENOBUFS; +} + +/** + * fscache_reserve_space - Reserve data space for a cached object + * @cookie: The cookie representing the cache object + * @i_size: The amount of space to be reserved + * + * Reserve an amount of space in the cache for the cache object attached to a + * cookie so that a write to that object within the space can always be + * honoured. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) +{ + return -ENOBUFS; +} + +/** + * fscache_read_or_alloc_page - Read a page from the cache or allocate a block + * in which to store it + * @cookie: The cookie representing the cache object + * @page: The netfs page to fill if possible + * @end_io_func: The callback to invoke when and if the page is filled + * @context: An arbitrary piece of data to pass on to end_io_func() + * @gfp: The conditions under which memory allocation should be made + * + * Read a page from the cache, or if that's not possible make a potential + * one-block reservation in the cache into which the page may be stored once + * fetched from the server. + * + * If the page is not backed by the cache object, or if it there's some reason + * it can't be, -ENOBUFS will be returned and nothing more will be done for + * that page. + * + * Else, if that page is backed by the cache, a read will be initiated directly + * to the netfs's page and 0 will be returned by this function. The + * end_io_func() callback will be invoked when the operation terminates on a + * completion or failure. Note that the callback may be invoked before the + * return. + * + * Else, if the page is unbacked, -ENODATA is returned and a block may have + * been allocated in the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_read_or_alloc_page(struct fscache_cookie *cookie, + struct page *page, + fscache_rw_complete_t end_io_func, + void *context, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate + * blocks in which to store them + * @cookie: The cookie representing the cache object + * @mapping: The netfs inode mapping to which the pages will be attached + * @pages: A list of potential netfs pages to be filled + * @end_io_func: The callback to invoke when and if each page is filled + * @context: An arbitrary piece of data to pass on to end_io_func() + * @gfp: The conditions under which memory allocation should be made + * + * Read a set of pages from the cache, or if that's not possible, attempt to + * make a potential one-block reservation for each page in the cache into which + * that page may be stored once fetched from the server. + * + * If some pages are not backed by the cache object, or if it there's some + * reason they can't be, -ENOBUFS will be returned and nothing more will be + * done for that pages. + * + * Else, if some of the pages are backed by the cache, a read will be initiated + * directly to the netfs's page and 0 will be returned by this function. The + * end_io_func() callback will be invoked when the operation terminates on a + * completion or failure. Note that the callback may be invoked before the + * return. + * + * Else, if a page is unbacked, -ENODATA is returned and a block may have + * been allocated in the cache. + * + * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in + * regard to different pages, the return values are prioritised in that order. + * Any pages submitted for reading are removed from the pages list. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, + struct address_space *mapping, + struct list_head *pages, + unsigned *nr_pages, + fscache_rw_complete_t end_io_func, + void *context, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_alloc_page - Allocate a block in which to store a page + * @cookie: The cookie representing the cache object + * @page: The netfs page to allocate a page for + * @gfp: The conditions under which memory allocation should be made + * + * Request Allocation a block in the cache in which to store a netfs page + * without retrieving any contents from the cache. + * + * If the page is not backed by a file then -ENOBUFS will be returned and + * nothing more will be done, and no reservation will be made. + * + * Else, a block will be allocated if one wasn't already, and 0 will be + * returned + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_alloc_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_write_page - Request storage of a page in the cache + * @cookie: The cookie representing the cache object + * @page: The netfs page to store + * @gfp: The conditions under which memory allocation should be made + * + * Request the contents of the netfs page be written into the cache. This + * request may be ignored if no cache block is currently allocated, in which + * case it will return -ENOBUFS. + * + * If a cache block was already allocated, a write will be initiated and 0 will + * be returned. The PG_fscache_write page bit is set immediately and will then + * be cleared at the completion of the write to indicate the success or failure + * of the operation. Note that the completion may happen before the return. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +int fscache_write_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) +{ + return -ENOBUFS; +} + +/** + * fscache_uncache_page - Indicate that caching is no longer required on a page + * @cookie: The cookie representing the cache object + * @page: The netfs page that was being cached. + * + * Tell the cache that we no longer want a page to be cached and that it should + * remove any knowledge of the netfs page it may have. + * + * Note that this cannot cancel any outstanding I/O operations between this + * page and the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_uncache_page(struct fscache_cookie *cookie, + struct page *page) +{ +} + +/** + * fscache_check_page_write - Ask if a page is being writing to the cache + * @cookie: The cookie representing the cache object + * @page: The netfs page that is being cached. + * + * Ask the cache if a page is being written to the cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +bool fscache_check_page_write(struct fscache_cookie *cookie, + struct page *page) +{ + return false; +} + +/** + * fscache_wait_on_page_write - Wait for a page to complete writing to the cache + * @cookie: The cookie representing the cache object + * @page: The netfs page that is being cached. + * + * Ask the cache to wake us up when a page is no longer being written to the + * cache. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_wait_on_page_write(struct fscache_cookie *cookie, + struct page *page) +{ +} + +#endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 0dfc41d1efcc4180abfd32f68f0ade540e636ff6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:36 +0100 Subject: FS-Cache: Add the FS-Cache cache backend API and documentation Add the API for a generic facility (FS-Cache) by which caches may declare them selves open for business, and may obtain work to be done from network filesystems. The header file is included by: #include Documentation for the API is also added to: Documentation/filesystems/caching/backend-api.txt This API is not usable without the implementation of the utility functions which will be added in further patches. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache-cache.h | 509 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 509 insertions(+) create mode 100644 include/linux/fscache-cache.h (limited to 'include') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h new file mode 100644 index 00000000000..b2a9a484c4c --- /dev/null +++ b/include/linux/fscache-cache.h @@ -0,0 +1,509 @@ +/* General filesystem caching backing cache interface + * + * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * NOTE!!! See: + * + * Documentation/filesystems/caching/backend-api.txt + * + * for a description of the cache backend interface declared here. + */ + +#ifndef _LINUX_FSCACHE_CACHE_H +#define _LINUX_FSCACHE_CACHE_H + +#include +#include +#include + +#define NR_MAXCACHES BITS_PER_LONG + +struct fscache_cache; +struct fscache_cache_ops; +struct fscache_object; +struct fscache_operation; + +#ifdef CONFIG_FSCACHE_PROC +extern struct proc_dir_entry *proc_fscache; +#endif + +/* + * cache tag definition + */ +struct fscache_cache_tag { + struct list_head link; + struct fscache_cache *cache; /* cache referred to by this tag */ + unsigned long flags; +#define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */ + atomic_t usage; + char name[0]; /* tag name */ +}; + +/* + * cache definition + */ +struct fscache_cache { + const struct fscache_cache_ops *ops; + struct fscache_cache_tag *tag; /* tag representing this cache */ + struct kobject *kobj; /* system representation of this cache */ + struct list_head link; /* link in list of caches */ + size_t max_index_size; /* maximum size of index data */ + char identifier[36]; /* cache label */ + + /* node management */ + struct work_struct op_gc; /* operation garbage collector */ + struct list_head object_list; /* list of data/index objects */ + struct list_head op_gc_list; /* list of ops to be deleted */ + spinlock_t object_list_lock; + spinlock_t op_gc_list_lock; + atomic_t object_count; /* no. of live objects in this cache */ + struct fscache_object *fsdef; /* object for the fsdef index */ + unsigned long flags; +#define FSCACHE_IOERROR 0 /* cache stopped on I/O error */ +#define FSCACHE_CACHE_WITHDRAWN 1 /* cache has been withdrawn */ +}; + +extern wait_queue_head_t fscache_cache_cleared_wq; + +/* + * operation to be applied to a cache object + * - retrieval initiation operations are done in the context of the process + * that issued them, and not in an async thread pool + */ +typedef void (*fscache_operation_release_t)(struct fscache_operation *op); +typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); + +struct fscache_operation { + union { + struct work_struct fast_work; /* record for fast ops */ + struct slow_work slow_work; /* record for (very) slow ops */ + }; + struct list_head pend_link; /* link in object->pending_ops */ + struct fscache_object *object; /* object to be operated upon */ + + unsigned long flags; +#define FSCACHE_OP_TYPE 0x000f /* operation type */ +#define FSCACHE_OP_FAST 0x0001 /* - fast op, processor may not sleep for disk */ +#define FSCACHE_OP_SLOW 0x0002 /* - (very) slow op, processor may sleep for disk */ +#define FSCACHE_OP_MYTHREAD 0x0003 /* - processing is done be issuing thread, not pool */ +#define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ +#define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ +#define FSCACHE_OP_DEAD 6 /* op is now dead */ + + atomic_t usage; + unsigned debug_id; /* debugging ID */ + + /* operation processor callback + * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform + * the op in a non-pool thread */ + fscache_operation_processor_t processor; + + /* operation releaser */ + fscache_operation_release_t release; +}; + +extern atomic_t fscache_op_debug_id; +extern const struct slow_work_ops fscache_op_slow_work_ops; + +extern void fscache_enqueue_operation(struct fscache_operation *); +extern void fscache_put_operation(struct fscache_operation *); + +/** + * fscache_operation_init - Do basic initialisation of an operation + * @op: The operation to initialise + * @release: The release function to assign + * + * Do basic initialisation of an operation. The caller must still set flags, + * object, either fast_work or slow_work if necessary, and processor if needed. + */ +static inline void fscache_operation_init(struct fscache_operation *op, + fscache_operation_release_t release) +{ + atomic_set(&op->usage, 1); + op->debug_id = atomic_inc_return(&fscache_op_debug_id); + op->release = release; + INIT_LIST_HEAD(&op->pend_link); +} + +/** + * fscache_operation_init_slow - Do additional initialisation of a slow op + * @op: The operation to initialise + * @processor: The processor function to assign + * + * Do additional initialisation of an operation as required for slow work. + */ +static inline +void fscache_operation_init_slow(struct fscache_operation *op, + fscache_operation_processor_t processor) +{ + op->processor = processor; + slow_work_init(&op->slow_work, &fscache_op_slow_work_ops); +} + +/* + * data read operation + */ +struct fscache_retrieval { + struct fscache_operation op; + struct address_space *mapping; /* netfs pages */ + fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ + void *context; /* netfs read context (pinned) */ + struct list_head to_do; /* list of things to be done by the backend */ + unsigned long start_time; /* time at which retrieval started */ +}; + +typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op, + struct page *page, + gfp_t gfp); + +typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op, + struct list_head *pages, + unsigned *nr_pages, + gfp_t gfp); + +/** + * fscache_get_retrieval - Get an extra reference on a retrieval operation + * @op: The retrieval operation to get a reference on + * + * Get an extra reference on a retrieval operation. + */ +static inline +struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op) +{ + atomic_inc(&op->op.usage); + return op; +} + +/** + * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing + * @op: The retrieval operation affected + * + * Enqueue a retrieval operation for processing by the FS-Cache thread pool. + */ +static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) +{ + fscache_enqueue_operation(&op->op); +} + +/** + * fscache_put_retrieval - Drop a reference to a retrieval operation + * @op: The retrieval operation affected + * + * Drop a reference to a retrieval operation. + */ +static inline void fscache_put_retrieval(struct fscache_retrieval *op) +{ + fscache_put_operation(&op->op); +} + +/* + * cached page storage work item + * - used to do three things: + * - batch writes to the cache + * - do cache writes asynchronously + * - defer writes until cache object lookup completion + */ +struct fscache_storage { + struct fscache_operation op; + pgoff_t store_limit; /* don't write more than this */ +}; + +/* + * cache operations + */ +struct fscache_cache_ops { + /* name of cache provider */ + const char *name; + + /* allocate an object record for a cookie */ + struct fscache_object *(*alloc_object)(struct fscache_cache *cache, + struct fscache_cookie *cookie); + + /* look up the object for a cookie */ + void (*lookup_object)(struct fscache_object *object); + + /* finished looking up */ + void (*lookup_complete)(struct fscache_object *object); + + /* increment the usage count on this object (may fail if unmounting) */ + struct fscache_object *(*grab_object)(struct fscache_object *object); + + /* pin an object in the cache */ + int (*pin_object)(struct fscache_object *object); + + /* unpin an object in the cache */ + void (*unpin_object)(struct fscache_object *object); + + /* store the updated auxilliary data on an object */ + void (*update_object)(struct fscache_object *object); + + /* discard the resources pinned by an object and effect retirement if + * necessary */ + void (*drop_object)(struct fscache_object *object); + + /* dispose of a reference to an object */ + void (*put_object)(struct fscache_object *object); + + /* sync a cache */ + void (*sync_cache)(struct fscache_cache *cache); + + /* notification that the attributes of a non-index object (such as + * i_size) have changed */ + int (*attr_changed)(struct fscache_object *object); + + /* reserve space for an object's data and associated metadata */ + int (*reserve_space)(struct fscache_object *object, loff_t i_size); + + /* request a backing block for a page be read or allocated in the + * cache */ + fscache_page_retrieval_func_t read_or_alloc_page; + + /* request backing blocks for a list of pages be read or allocated in + * the cache */ + fscache_pages_retrieval_func_t read_or_alloc_pages; + + /* request a backing block for a page be allocated in the cache so that + * it can be written directly */ + fscache_page_retrieval_func_t allocate_page; + + /* request backing blocks for pages be allocated in the cache so that + * they can be written directly */ + fscache_pages_retrieval_func_t allocate_pages; + + /* write a page to its backing block in the cache */ + int (*write_page)(struct fscache_storage *op, struct page *page); + + /* detach backing block from a page (optional) + * - must release the cookie lock before returning + * - may sleep + */ + void (*uncache_page)(struct fscache_object *object, + struct page *page); + + /* dissociate a cache from all the pages it was backing */ + void (*dissociate_pages)(struct fscache_cache *cache); +}; + +/* + * data file or index object cookie + * - a file will only appear in one cache + * - a request to cache a file may or may not be honoured, subject to + * constraints such as disk space + * - indices are created on disk just-in-time + */ +struct fscache_cookie { + atomic_t usage; /* number of users of this cookie */ + atomic_t n_children; /* number of children of this cookie */ + spinlock_t lock; + struct hlist_head backing_objects; /* object(s) backing this file/index */ + const struct fscache_cookie_def *def; /* definition */ + struct fscache_cookie *parent; /* parent of this entry */ + void *netfs_data; /* back pointer to netfs */ + struct radix_tree_root stores; /* pages to be stored on this cookie */ +#define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ + + unsigned long flags; +#define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ +#define FSCACHE_COOKIE_CREATING 1 /* T if non-index object being created still */ +#define FSCACHE_COOKIE_NO_DATA_YET 2 /* T if new object with no cached data yet */ +#define FSCACHE_COOKIE_PENDING_FILL 3 /* T if pending initial fill on object */ +#define FSCACHE_COOKIE_FILLING 4 /* T if filling object incrementally */ +#define FSCACHE_COOKIE_UNAVAILABLE 5 /* T if cookie is unavailable (error, etc) */ +}; + +extern struct fscache_cookie fscache_fsdef_index; + +/* + * on-disk cache file or index handle + */ +struct fscache_object { + enum fscache_object_state { + FSCACHE_OBJECT_INIT, /* object in initial unbound state */ + FSCACHE_OBJECT_LOOKING_UP, /* looking up object */ + FSCACHE_OBJECT_CREATING, /* creating object */ + + /* active states */ + FSCACHE_OBJECT_AVAILABLE, /* cleaning up object after creation */ + FSCACHE_OBJECT_ACTIVE, /* object is usable */ + FSCACHE_OBJECT_UPDATING, /* object is updating */ + + /* terminal states */ + FSCACHE_OBJECT_DYING, /* object waiting for accessors to finish */ + FSCACHE_OBJECT_LC_DYING, /* object cleaning up after lookup/create */ + FSCACHE_OBJECT_ABORT_INIT, /* abort the init state */ + FSCACHE_OBJECT_RELEASING, /* releasing object */ + FSCACHE_OBJECT_RECYCLING, /* retiring object */ + FSCACHE_OBJECT_WITHDRAWING, /* withdrawing object */ + FSCACHE_OBJECT_DEAD, /* object is now dead */ + } state; + + int debug_id; /* debugging ID */ + int n_children; /* number of child objects */ + int n_ops; /* number of ops outstanding on object */ + int n_obj_ops; /* number of object ops outstanding on object */ + int n_in_progress; /* number of ops in progress */ + int n_exclusive; /* number of exclusive ops queued */ + spinlock_t lock; /* state and operations lock */ + + unsigned long lookup_jif; /* time at which lookup started */ + unsigned long event_mask; /* events this object is interested in */ + unsigned long events; /* events to be processed by this object + * (order is important - using fls) */ +#define FSCACHE_OBJECT_EV_REQUEUE 0 /* T if object should be requeued */ +#define FSCACHE_OBJECT_EV_UPDATE 1 /* T if object should be updated */ +#define FSCACHE_OBJECT_EV_CLEARED 2 /* T if accessors all gone */ +#define FSCACHE_OBJECT_EV_ERROR 3 /* T if fatal error occurred during processing */ +#define FSCACHE_OBJECT_EV_RELEASE 4 /* T if netfs requested object release */ +#define FSCACHE_OBJECT_EV_RETIRE 5 /* T if netfs requested object retirement */ +#define FSCACHE_OBJECT_EV_WITHDRAW 6 /* T if cache requested object withdrawal */ + + unsigned long flags; +#define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */ +#define FSCACHE_OBJECT_PENDING_WRITE 1 /* T if object has pending write */ +#define FSCACHE_OBJECT_WAITING 2 /* T if object is waiting on its parent */ + + struct list_head cache_link; /* link in cache->object_list */ + struct hlist_node cookie_link; /* link in cookie->backing_objects */ + struct fscache_cache *cache; /* cache that supplied this object */ + struct fscache_cookie *cookie; /* netfs's file/index object */ + struct fscache_object *parent; /* parent object */ + struct slow_work work; /* attention scheduling record */ + struct list_head dependents; /* FIFO of dependent objects */ + struct list_head dep_link; /* link in parent's dependents list */ + struct list_head pending_ops; /* unstarted operations on this object */ + pgoff_t store_limit; /* current storage limit */ +}; + +extern const char *fscache_object_states[]; + +#define fscache_object_is_active(obj) \ + (!test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) && \ + (obj)->state >= FSCACHE_OBJECT_AVAILABLE && \ + (obj)->state < FSCACHE_OBJECT_DYING) + +extern const struct slow_work_ops fscache_object_slow_work_ops; + +/** + * fscache_object_init - Initialise a cache object description + * @object: Object description + * + * Initialise a cache object description to its basic values. + * + * See Documentation/filesystems/caching/backend-api.txt for a complete + * description. + */ +static inline +void fscache_object_init(struct fscache_object *object, + struct fscache_cookie *cookie, + struct fscache_cache *cache) +{ + atomic_inc(&cache->object_count); + + object->state = FSCACHE_OBJECT_INIT; + spin_lock_init(&object->lock); + INIT_LIST_HEAD(&object->cache_link); + INIT_HLIST_NODE(&object->cookie_link); + vslow_work_init(&object->work, &fscache_object_slow_work_ops); + INIT_LIST_HEAD(&object->dependents); + INIT_LIST_HEAD(&object->dep_link); + INIT_LIST_HEAD(&object->pending_ops); + object->n_children = 0; + object->n_ops = object->n_in_progress = object->n_exclusive = 0; + object->events = object->event_mask = 0; + object->flags = 0; + object->store_limit = 0; + object->cache = cache; + object->cookie = cookie; + object->parent = NULL; +} + +extern void fscache_object_lookup_negative(struct fscache_object *object); +extern void fscache_obtained_object(struct fscache_object *object); + +/** + * fscache_object_destroyed - Note destruction of an object in a cache + * @cache: The cache from which the object came + * + * Note the destruction and deallocation of an object record in a cache. + */ +static inline void fscache_object_destroyed(struct fscache_cache *cache) +{ + if (atomic_dec_and_test(&cache->object_count)) + wake_up_all(&fscache_cache_cleared_wq); +} + +/** + * fscache_object_lookup_error - Note an object encountered an error + * @object: The object on which the error was encountered + * + * Note that an object encountered a fatal error (usually an I/O error) and + * that it should be withdrawn as soon as possible. + */ +static inline void fscache_object_lookup_error(struct fscache_object *object) +{ + set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events); +} + +/** + * fscache_set_store_limit - Set the maximum size to be stored in an object + * @object: The object to set the maximum on + * @i_size: The limit to set in bytes + * + * Set the maximum size an object is permitted to reach, implying the highest + * byte that may be written. Intended to be called by the attr_changed() op. + * + * See Documentation/filesystems/caching/backend-api.txt for a complete + * description. + */ +static inline +void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) +{ + object->store_limit = i_size >> PAGE_SHIFT; + if (i_size & ~PAGE_MASK) + object->store_limit++; +} + +/** + * fscache_end_io - End a retrieval operation on a page + * @op: The FS-Cache operation covering the retrieval + * @page: The page that was to be fetched + * @error: The error code (0 if successful) + * + * Note the end of an operation to retrieve a page, as covered by a particular + * operation record. + */ +static inline void fscache_end_io(struct fscache_retrieval *op, + struct page *page, int error) +{ + op->end_io_func(page, op->context, error); +} + +/* + * out-of-line cache backend functions + */ +extern void fscache_init_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + const char *idfmt, + ...) __attribute__ ((format (printf, 3, 4))); + +extern int fscache_add_cache(struct fscache_cache *cache, + struct fscache_object *fsdef, + const char *tagname); +extern void fscache_withdraw_cache(struct fscache_cache *cache); + +extern void fscache_io_error(struct fscache_cache *cache); + +extern void fscache_mark_pages_cached(struct fscache_retrieval *op, + struct pagevec *pagevec); + +extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, + const void *data, + uint16_t datalen); + +#endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From 7394daa8c61dfda4baa687f133748fa0b599b017 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:37 +0100 Subject: FS-Cache: Add use of /proc and presentation of statistics Make FS-Cache create its /proc interface and present various statistical information through it. Also provide the functions for updating this information. These features are enabled by: CONFIG_FSCACHE_PROC CONFIG_FSCACHE_STATS CONFIG_FSCACHE_HISTOGRAM The /proc directory for FS-Cache is also exported so that caching modules can add their own statistics there too. The FS-Cache module is loadable at this point, and the statistics files can be examined by userspace: cat /proc/fs/fscache/stats cat /proc/fs/fscache/histogram Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache-cache.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index b2a9a484c4c..84d3532dd3e 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -29,10 +29,6 @@ struct fscache_cache_ops; struct fscache_object; struct fscache_operation; -#ifdef CONFIG_FSCACHE_PROC -extern struct proc_dir_entry *proc_fscache; -#endif - /* * cache tag definition */ -- cgit v1.2.3 From 0e04d4cefcf4d8fbbdb2c50e93ad541582933fd2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:37 +0100 Subject: FS-Cache: Add cache tag handling Implement two features of FS-Cache: (1) The ability to request and release cache tags - names by which a cache may be known to a netfs, and thus selected for use. (2) An internal function by which a cache is selected by consulting the netfs, if the netfs wishes to be consulted. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index feb3b0e0af4..9584c094d69 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -173,6 +173,8 @@ struct fscache_netfs { * - these are undefined symbols when FS-Cache is not configured and the * optimiser takes care of not using them */ +extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); +extern void __fscache_release_cache_tag(struct fscache_cache_tag *); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -218,7 +220,10 @@ void fscache_unregister_netfs(struct fscache_netfs *netfs) static inline struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) { - return NULL; + if (fscache_available()) + return __fscache_lookup_cache_tag(name); + else + return NULL; } /** @@ -233,6 +238,8 @@ struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) static inline void fscache_release_cache_tag(struct fscache_cache_tag *tag) { + if (fscache_available()) + __fscache_release_cache_tag(tag); } /** -- cgit v1.2.3 From 726dd7ff10c217dd74329c94643dc8ebea27334b Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:38 +0100 Subject: FS-Cache: Add netfs registration Add functions to register and unregister a network filesystem or other client of the FS-Cache service. This allocates and releases the cookie representing the top-level index for a netfs, and makes it available to the netfs. If the FS-Cache facility is disabled, then the calls are optimised away at compile time. Note that whilst this patch may appear to work with FS-Cache enabled and a netfs attempting to use it, it will leak the cookie it allocates for the netfs as fscache_relinquish_cookie() is implemented in a later patch. This will cause the slab code to emit a warning when the module is removed. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 9584c094d69..b195c2e1ef6 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -173,6 +173,8 @@ struct fscache_netfs { * - these are undefined symbols when FS-Cache is not configured and the * optimiser takes care of not using them */ +extern int __fscache_register_netfs(struct fscache_netfs *); +extern void __fscache_unregister_netfs(struct fscache_netfs *); extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); extern void __fscache_release_cache_tag(struct fscache_cache_tag *); @@ -188,7 +190,10 @@ extern void __fscache_release_cache_tag(struct fscache_cache_tag *); static inline int fscache_register_netfs(struct fscache_netfs *netfs) { - return 0; + if (fscache_available()) + return __fscache_register_netfs(netfs); + else + return 0; } /** @@ -205,6 +210,8 @@ int fscache_register_netfs(struct fscache_netfs *netfs) static inline void fscache_unregister_netfs(struct fscache_netfs *netfs) { + if (fscache_available()) + __fscache_unregister_netfs(netfs); } /** -- cgit v1.2.3 From ccc4fc3d11e91477036d1f82bfa2d442f6ce77f0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:38 +0100 Subject: FS-Cache: Implement the cookie management part of the netfs API Implement the cookie management part of the FS-Cache netfs client API. The documentation and API header file were added in a previous patch. This patch implements the following three functions: (1) fscache_acquire_cookie(). Acquire a cookie to represent an object to the netfs. If the object in question is a non-index object, then that object and its parent indices will be created on disk at this point if they don't already exist. Index creation is deferred because an index may reside in multiple caches. (2) fscache_relinquish_cookie(). Retire or release a cookie previously acquired. At this point, the object on disk may be destroyed. (3) fscache_update_cookie(). Update the in-cache representation of a cookie. This is used to update the auxiliary data for coherency management purposes. With this patch it is possible to have a netfs instruct a cache backend to look up, validate and create metadata on disk and to destroy it again. The ability to actually store and retrieve data in the objects so created is added in later patches. Note that these functions will never return an error. _All_ errors are handled internally to FS-Cache. The worst that can happen is that fscache_acquire_cookie() may return a NULL pointer - which is considered a negative cookie pointer and can be passed back to any function that takes a cookie without harm. A negative cookie pointer merely suppresses caching at that level. The stub in linux/fscache.h will detect inline the negative cookie pointer and abort the operation as fast as possible. This means that the compiler doesn't have to set up for a call in that case. See the documentation in Documentation/filesystems/caching/netfs-api.txt for more information. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index b195c2e1ef6..245b48646ef 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -178,6 +178,13 @@ extern void __fscache_unregister_netfs(struct fscache_netfs *); extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); extern void __fscache_release_cache_tag(struct fscache_cache_tag *); +extern struct fscache_cookie *__fscache_acquire_cookie( + struct fscache_cookie *, + const struct fscache_cookie_def *, + void *); +extern void __fscache_relinquish_cookie(struct fscache_cookie *, int); +extern void __fscache_update_cookie(struct fscache_cookie *); + /** * fscache_register_netfs - Register a filesystem as desiring caching services * @netfs: The description of the filesystem @@ -269,7 +276,10 @@ struct fscache_cookie *fscache_acquire_cookie( const struct fscache_cookie_def *def, void *netfs_data) { - return NULL; + if (fscache_cookie_valid(parent)) + return __fscache_acquire_cookie(parent, def, netfs_data); + else + return NULL; } /** @@ -287,6 +297,8 @@ struct fscache_cookie *fscache_acquire_cookie( static inline void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) { + if (fscache_cookie_valid(cookie)) + __fscache_relinquish_cookie(cookie, retire); } /** @@ -302,6 +314,8 @@ void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) static inline void fscache_update_cookie(struct fscache_cookie *cookie) { + if (fscache_cookie_valid(cookie)) + __fscache_update_cookie(cookie); } /** -- cgit v1.2.3 From b510882281d56873e1194021643b7c325336f84f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:39 +0100 Subject: FS-Cache: Implement data I/O part of netfs API Implement the data I/O part of the FS-Cache netfs API. The documentation and API header file were added in a previous patch. This patch implements the following functions for the netfs to call: (*) fscache_attr_changed(). Indicate that the object has changed its attributes. The only attribute currently recorded is the file size. Only pages within the set file size will be stored in the cache. This operation is submitted for asynchronous processing, and will return immediately. It will return -ENOMEM if an out of memory error is encountered, -ENOBUFS if the object is not actually cached, or 0 if the operation is successfully queued. (*) fscache_read_or_alloc_page(). (*) fscache_read_or_alloc_pages(). Request data be fetched from the disk, and allocate internal metadata to track the netfs pages and reserve disk space for unknown pages. These operations perform semi-asynchronous data reads. Upon returning they will indicate which pages they think can be retrieved from disk, and will have set in progress attempts to retrieve those pages. These will return, in order of preference, -ENOMEM on memory allocation error, -ERESTARTSYS if a signal interrupted proceedings, -ENODATA if one or more requested pages are not yet cached, -ENOBUFS if the object is not actually cached or if there isn't space for future pages to be cached on this object, or 0 if successful. In the case of the multipage function, the pages for which reads are set in progress will be removed from the list and the page count decreased appropriately. If any read operations should fail, the completion function will be given an error, and will also be passed contextual information to allow the netfs to fall back to querying the server for the absent pages. For each successful read, the page completion function will also be called. Any pages subsequently tracked by the cache will have PG_fscache set upon them on return. fscache_uncache_page() must be called for such pages. If supplied by the netfs, the mark_pages_cached() cookie op will be invoked for any pages now tracked. (*) fscache_alloc_page(). Allocate internal metadata to track a netfs page and reserve disk space. This will return -ENOMEM on memory allocation error, -ERESTARTSYS on signal, -ENOBUFS if the object isn't cached, or there isn't enough space in the cache, or 0 if successful. Any pages subsequently tracked by the cache will have PG_fscache set upon them on return. fscache_uncache_page() must be called for such pages. If supplied by the netfs, the mark_pages_cached() cookie op will be invoked for any pages now tracked. (*) fscache_write_page(). Request data be stored to disk. This may only be called on pages that have been read or alloc'd by the above three functions and have not yet been uncached. This will return -ENOMEM on memory allocation error, -ERESTARTSYS on signal, -ENOBUFS if the object isn't cached, or there isn't immediately enough space in the cache, or 0 if successful. On a successful return, this operation will have queued the page for asynchronous writing to the cache. The page will be returned with PG_fscache_write set until the write completes one way or another. The caller will not be notified if the write fails due to an I/O error. If that happens, the object will become available and all pending writes will be aborted. Note that the cache may batch up page writes, and so it may take a while to get around to writing them out. The caller must assume that until PG_fscache_write is cleared the page is use by the cache. Any changes made to the page may be reflected on disk. The page may even be under DMA. (*) fscache_uncache_page(). Indicate that the cache should stop tracking a page previously read or alloc'd from the cache. If the page was alloc'd only, but unwritten, it will not appear on disk. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/fscache.h | 52 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 245b48646ef..6d8ee466e0a 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -184,6 +184,24 @@ extern struct fscache_cookie *__fscache_acquire_cookie( void *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, int); extern void __fscache_update_cookie(struct fscache_cookie *); +extern int __fscache_attr_changed(struct fscache_cookie *); +extern int __fscache_read_or_alloc_page(struct fscache_cookie *, + struct page *, + fscache_rw_complete_t, + void *, + gfp_t); +extern int __fscache_read_or_alloc_pages(struct fscache_cookie *, + struct address_space *, + struct list_head *, + unsigned *, + fscache_rw_complete_t, + void *, + gfp_t); +extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t); +extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t); +extern void __fscache_uncache_page(struct fscache_cookie *, struct page *); +extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); +extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -361,7 +379,10 @@ void fscache_unpin_cookie(struct fscache_cookie *cookie) static inline int fscache_attr_changed(struct fscache_cookie *cookie) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_attr_changed(cookie); + else + return -ENOBUFS; } /** @@ -418,7 +439,11 @@ int fscache_read_or_alloc_page(struct fscache_cookie *cookie, void *context, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_read_or_alloc_page(cookie, page, end_io_func, + context, gfp); + else + return -ENOBUFS; } /** @@ -464,7 +489,12 @@ int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, void *context, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_read_or_alloc_pages(cookie, mapping, pages, + nr_pages, end_io_func, + context, gfp); + else + return -ENOBUFS; } /** @@ -490,7 +520,10 @@ int fscache_alloc_page(struct fscache_cookie *cookie, struct page *page, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_alloc_page(cookie, page, gfp); + else + return -ENOBUFS; } /** @@ -516,7 +549,10 @@ int fscache_write_page(struct fscache_cookie *cookie, struct page *page, gfp_t gfp) { - return -ENOBUFS; + if (fscache_cookie_valid(cookie)) + return __fscache_write_page(cookie, page, gfp); + else + return -ENOBUFS; } /** @@ -537,6 +573,8 @@ static inline void fscache_uncache_page(struct fscache_cookie *cookie, struct page *page) { + if (fscache_cookie_valid(cookie)) + __fscache_uncache_page(cookie, page); } /** @@ -553,6 +591,8 @@ static inline bool fscache_check_page_write(struct fscache_cookie *cookie, struct page *page) { + if (fscache_cookie_valid(cookie)) + return __fscache_check_page_write(cookie, page); return false; } @@ -571,6 +611,8 @@ static inline void fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page) { + if (fscache_cookie_valid(cookie)) + __fscache_wait_on_page_write(cookie, page); } #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 385e1ca5f21c4680ad6a46a3aa2ea8af99e99c92 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:39 +0100 Subject: CacheFiles: Permit the page lock state to be monitored Add a function to install a monitor on the page lock waitqueue for a particular page, thus allowing the page being unlocked to be detected. This is used by CacheFiles to detect read completion on a page in the backing filesystem so that it can then copy the data to the waiting netfs page. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Rik van Riel Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/pagemap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 076a7dc67c2..34da5230faa 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -383,6 +383,11 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); +/* + * Add an arbitrary waiter to a page's wait queue + */ +extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter); + /* * Fault a userspace page into pagetables. Return non-zero on a fault. * -- cgit v1.2.3 From c6a6f19e22da0a3d74214ee010224c9a30a794c1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:42 +0100 Subject: NFS: Add FS-Cache option bit and debug bit Add FS-Cache option bit to nfs_server struct. This is set to indicate local on-disk caching is enabled for a particular superblock. Also add debug bit for local caching operations. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs.h | 1 + include/linux/nfs_fs_sb.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bde2557c2a9..fd3e7f9c6fd 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -583,6 +583,7 @@ extern void * nfs_root_data(void); #define NFSDBG_CALLBACK 0x0100 #define NFSDBG_CLIENT 0x0200 #define NFSDBG_MOUNT 0x0400 +#define NFSDBG_FSCACHE 0x0800 #define NFSDBG_ALL 0xFFFF #ifdef __KERNEL__ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 29b1e40dce9..a749f8564aa 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -96,6 +96,8 @@ struct nfs_server { unsigned int acdirmin; unsigned int acdirmax; unsigned int namelen; + unsigned int options; /* extra options enabled by mount */ +#define NFS_OPTION_FSCACHE 0x00000001 /* - local caching enabled */ struct nfs_fsid fsid; __u64 maxfilesize; /* maximum file size */ -- cgit v1.2.3 From 147272813e043fb44bd112527951da70c1e663de Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:42 +0100 Subject: NFS: Define and create server-level objects Define and create server-level cache index objects (as managed by nfs_client structs). Each server object is created in the NFS top-level index object and is itself an index into which superblock-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The server object key is a sequence consisting of: (1) NFS version (2) Server address family (eg: AF_INET or AF_INET6) (3) Server port. (4) Server IP address. The key blob is of variable length, depending on the length of (4). The server object is given no coherency data to carry in the auxiliary data permitted by the cache. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs_sb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a749f8564aa..0a374b9c509 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -64,6 +64,10 @@ struct nfs_client { char cl_ipaddr[48]; unsigned char cl_id_uniquifier; #endif + +#ifdef CONFIG_NFS_FSCACHE + struct fscache_cookie *fscache; /* client index cache cookie */ +#endif }; /* -- cgit v1.2.3 From 08734048b380103f0412f58b84c2f76a2c8b599f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:42 +0100 Subject: NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs_sb.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 0a374b9c509..6ad75948cbf 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -108,6 +108,11 @@ struct nfs_server { unsigned long mount_time; /* when this fs was mounted */ dev_t s_dev; /* superblock dev numbers */ +#ifdef CONFIG_NFS_FSCACHE + struct nfs_fscache_key *fscache_key; /* unique key for superblock */ + struct fscache_cookie *fscache; /* superblock cookie */ +#endif + #ifdef CONFIG_NFS_V4 u32 attr_bitmask[2];/* V4 bitmask representing the set of attributes supported on this -- cgit v1.2.3 From ef79c097bbe9724e13937271b3457df560e00370 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:43 +0100 Subject: NFS: Use local disk inode cache Bind data storage objects in the local cache to NFS inodes. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fd3e7f9c6fd..8a99e79d5ea 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -185,6 +185,9 @@ struct nfs_inode { fmode_t delegation_state; struct rw_semaphore rwsem; #endif /* CONFIG_NFS_V4*/ +#ifdef CONFIG_NFS_FSCACHE + struct fscache_cookie *fscache; +#endif struct inode vfs_inode; }; @@ -207,6 +210,8 @@ struct nfs_inode { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_MOUNTPOINT (3) /* inode is remote mountpoint */ #define NFS_INO_FLUSHING (4) /* inode is flushing out data */ +#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ +#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { @@ -260,6 +265,11 @@ static inline int NFS_STALE(const struct inode *inode) return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } +static inline int NFS_FSCACHE(const struct inode *inode) +{ + return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags); +} + static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; -- cgit v1.2.3 From 6a51091d0775cdc4a923f2172c61925ad416aa32 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:43 +0100 Subject: NFS: Add some new I/O counters for FS-Cache doing things for NFS Add some new NFS I/O counters for FS-Cache doing things for NFS. A new line is emitted into /proc/pid/mountstats if caching is enabled that looks like: fsc: Where is the number of pages read successfully from the cache, is the number of failed page reads against the cache, is the number of successful page writes to the cache, is the number of failed page writes to the cache, and is the number of NFS pages that have been disconnected from the cache. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_iostat.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h index 1cb9a3fed2b..68b10f5f890 100644 --- a/include/linux/nfs_iostat.h +++ b/include/linux/nfs_iostat.h @@ -116,4 +116,16 @@ enum nfs_stat_eventcounters { __NFSIOS_COUNTSMAX, }; +/* + * NFS local caching servicing counters + */ +enum nfs_stat_fscachecounters { + NFSIOS_FSCACHE_PAGES_READ_OK, + NFSIOS_FSCACHE_PAGES_READ_FAIL, + NFSIOS_FSCACHE_PAGES_WRITTEN_OK, + NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, + NFSIOS_FSCACHE_PAGES_UNCACHED, + __NFSIOS_FSCACHEMAX, +}; + #endif /* _LINUX_NFS_IOSTAT */ -- cgit v1.2.3 From f42b293d6d5259043a8944b556eeab427c695d57 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:44 +0100 Subject: NFS: nfs_readpage_async() needs to be accessible as a fallback for local caching nfs_readpage_async() needs to be non-static so that it can be used as a fallback for the local on-disk caching should an EIO crop up when reading the cache. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/nfs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8a99e79d5ea..fdffb413b19 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -516,6 +516,8 @@ extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *); extern void nfs_readdata_release(void *data); +extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, + struct page *); /* * Allocate nfs_read_data structures -- cgit v1.2.3