From 2cee6fbb7f01bcb25f11ef1439e89a29de4c0c1d Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Oct 2021 21:53:44 +0100 Subject: fscache: Remove the contents of the fscache driver, pending rewrite Remove the code that comprises the fscache driver as it's going to be substantially rewritten, with the majority of the code being erased in the rewrite. A small piece of linux/fscache.h is left as that is #included by a bunch of network filesystems. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819578724.215744.18210619052245724238.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906884814.143852.6727245089843862889.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967077097.1823006.1377665951499979089.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021485548.640689.13876080567388696162.stgit@warthog.procyon.org.uk/ # v4 --- include/linux/fscache-cache.h | 548 +-------------------------- include/linux/fscache.h | 851 +----------------------------------------- 2 files changed, 3 insertions(+), 1396 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 8d39491c5f9f..47f21a53ac4b 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching backing cache interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -15,551 +15,5 @@ #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; - -enum fscache_obj_ref_trace { - fscache_obj_get_add_to_deps, - fscache_obj_get_queue, - fscache_obj_put_alloc_fail, - fscache_obj_put_attach_fail, - fscache_obj_put_drop_obj, - fscache_obj_put_enq_dep, - fscache_obj_put_queue, - fscache_obj_put_work, - fscache_obj_ref__nr_traces -}; - -/* - * 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[]; /* 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); -typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op); - -enum fscache_operation_state { - FSCACHE_OP_ST_BLANK, /* Op is not yet submitted */ - FSCACHE_OP_ST_INITIALISED, /* Op is initialised */ - FSCACHE_OP_ST_PENDING, /* Op is blocked from running */ - FSCACHE_OP_ST_IN_PROGRESS, /* Op is in progress */ - FSCACHE_OP_ST_COMPLETE, /* Op is complete */ - FSCACHE_OP_ST_CANCELLED, /* Op has been cancelled */ - FSCACHE_OP_ST_DEAD /* Op is now dead */ -}; - -struct fscache_operation { - struct work_struct work; /* record for async 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_ASYNC 0x0001 /* - async op, processor may sleep for disk */ -#define FSCACHE_OP_MYTHREAD 0x0002 /* - 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_DEC_READ_CNT 6 /* decrement object->n_reads on destruction */ -#define FSCACHE_OP_UNUSE_COOKIE 7 /* call fscache_unuse_cookie() on completion */ -#define FSCACHE_OP_KEEP_FLAGS 0x00f0 /* flags to keep when repurposing an op */ - - enum fscache_operation_state state; - 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 cancellation cleanup (optional) */ - fscache_operation_cancel_t cancel; - - /* operation releaser */ - fscache_operation_release_t release; -}; - -extern atomic_t fscache_op_debug_id; -extern void fscache_op_work_func(struct work_struct *work); - -extern void fscache_enqueue_operation(struct fscache_operation *); -extern void fscache_op_complete(struct fscache_operation *, bool); -extern void fscache_put_operation(struct fscache_operation *); -extern void fscache_operation_init(struct fscache_cookie *, - struct fscache_operation *, - fscache_operation_processor_t, - fscache_operation_cancel_t, - fscache_operation_release_t); - -/* - * data read operation - */ -struct fscache_retrieval { - struct fscache_operation op; - struct fscache_cookie *cookie; /* The netfs cookie */ - 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 */ - atomic_t n_pages; /* number of pages to be retrieved */ -}; - -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_retrieval_complete - Record (partial) completion of a retrieval - * @op: The retrieval operation affected - * @n_pages: The number of pages to account for - */ -static inline void fscache_retrieval_complete(struct fscache_retrieval *op, - int n_pages) -{ - if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) - fscache_op_complete(&op->op, false); -} - -/** - * 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 - * - return -ETIMEDOUT to be requeued - */ - int (*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, - enum fscache_obj_ref_trace why); - - /* 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); - - /* check the consistency between the backing cache and the FS-Cache - * cookie */ - int (*check_consistency)(struct fscache_operation *op); - - /* store the updated auxiliary data on an object */ - void (*update_object)(struct fscache_object *object); - - /* Invalidate an object */ - void (*invalidate_object)(struct fscache_operation *op); - - /* 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, - enum fscache_obj_ref_trace why); - - /* 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); - - /* Begin a read operation for the netfs lib */ - int (*begin_read_operation)(struct netfs_read_request *rreq, - struct fscache_retrieval *op); -}; - -extern struct fscache_cookie fscache_fsdef_index; - -/* - * Event list for fscache_object::{event_mask,events} - */ -enum { - FSCACHE_OBJECT_EV_NEW_CHILD, /* T if object has a new child */ - FSCACHE_OBJECT_EV_PARENT_READY, /* T if object's parent is ready */ - FSCACHE_OBJECT_EV_UPDATE, /* T if object should be updated */ - FSCACHE_OBJECT_EV_INVALIDATE, /* T if cache requested object invalidation */ - FSCACHE_OBJECT_EV_CLEARED, /* T if accessors all gone */ - FSCACHE_OBJECT_EV_ERROR, /* T if fatal error occurred during processing */ - FSCACHE_OBJECT_EV_KILL, /* T if netfs relinquished or cache withdrew object */ - NR_FSCACHE_OBJECT_EVENTS -}; - -#define FSCACHE_OBJECT_EVENTS_MASK ((1UL << NR_FSCACHE_OBJECT_EVENTS) - 1) - -/* - * States for object state machine. - */ -struct fscache_transition { - unsigned long events; - const struct fscache_state *transit_to; -}; - -struct fscache_state { - char name[24]; - char short_name[8]; - const struct fscache_state *(*work)(struct fscache_object *object, - int event); - const struct fscache_transition transitions[]; -}; - -/* - * on-disk cache file or index handle - */ -struct fscache_object { - const struct fscache_state *state; /* Object state machine state */ - const struct fscache_transition *oob_table; /* OOB state transition table */ - int debug_id; /* debugging ID */ - int n_children; /* number of child objects */ - int n_ops; /* number of extant ops 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 or in progress */ - atomic_t n_reads; /* number of read ops in progress */ - spinlock_t lock; /* state and operations lock */ - - unsigned long lookup_jif; /* time at which lookup started */ - unsigned long oob_event_mask; /* OOB events this object is interested in */ - 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) */ - - 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 */ -#define FSCACHE_OBJECT_IS_LIVE 3 /* T if object is not withdrawn or relinquished */ -#define FSCACHE_OBJECT_IS_LOOKED_UP 4 /* T if object has been looked up */ -#define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */ -#define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */ -#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */ -#define FSCACHE_OBJECT_RUN_AFTER_DEAD 8 /* T if object has been dispatched after death */ - - 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 work_struct 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 */ - loff_t store_limit_l; /* current storage limit */ -}; - -extern void fscache_object_init(struct fscache_object *, struct fscache_cookie *, - struct fscache_cache *); -extern void fscache_object_destroy(struct fscache_object *); - -extern void fscache_object_lookup_negative(struct fscache_object *object); -extern void fscache_obtained_object(struct fscache_object *object); - -static inline bool fscache_object_is_live(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); -} - -static inline bool fscache_object_is_dying(struct fscache_object *object) -{ - return !fscache_object_is_live(object); -} - -static inline bool fscache_object_is_available(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); -} - -static inline bool fscache_cache_is_broken(struct fscache_object *object) -{ - return test_bit(FSCACHE_IOERROR, &object->cache->flags); -} - -static inline bool fscache_object_is_active(struct fscache_object *object) -{ - return fscache_object_is_available(object) && - fscache_object_is_live(object) && - !fscache_cache_is_broken(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.rst for a complete - * description. - */ -static inline -void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) -{ - object->store_limit_l = 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); -} - -static inline void __fscache_use_cookie(struct fscache_cookie *cookie) -{ - atomic_inc(&cookie->n_active); -} - -/** - * fscache_use_cookie - Request usage of cookie attached to an object - * @object: Object description - * - * Request usage of the cookie attached to an object. NULL is returned if the - * relinquishment had reduced the cookie usage count to 0. - */ -static inline bool fscache_use_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - return atomic_inc_not_zero(&cookie->n_active) != 0; -} - -static inline bool __fscache_unuse_cookie(struct fscache_cookie *cookie) -{ - return atomic_dec_and_test(&cookie->n_active); -} - -static inline void __fscache_wake_unused_cookie(struct fscache_cookie *cookie) -{ - wake_up_var(&cookie->n_active); -} - -/** - * fscache_unuse_cookie - Cease usage of cookie attached to an object - * @object: Object description - * - * Cease usage of the cookie attached to an object. When the users count - * reaches zero then the cookie relinquishment will be permitted to proceed. - */ -static inline void fscache_unuse_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - if (__fscache_unuse_cookie(cookie)) - __fscache_wake_unused_cookie(cookie); -} - -/* - * out-of-line cache backend functions - */ -extern __printf(3, 4) -void fscache_init_cache(struct fscache_cache *cache, - const struct fscache_cache_ops *ops, - const char *idfmt, ...); - -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_page_cached(struct fscache_retrieval *op, - struct page *page); - -extern void fscache_mark_pages_cached(struct fscache_retrieval *op, - struct pagevec *pagevec); - -extern bool fscache_object_sleep_till_congested(signed long *timeoutp); - -extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, - const void *data, - uint16_t datalen, - loff_t object_size); - -extern void fscache_object_retrying_stale(struct fscache_object *object); - -enum fscache_why_object_killed { - FSCACHE_OBJECT_IS_STALE, - FSCACHE_OBJECT_NO_SPACE, - FSCACHE_OBJECT_WAS_RETIRED, - FSCACHE_OBJECT_WAS_CULLED, -}; -extern void fscache_object_mark_killed(struct fscache_object *object, - enum fscache_why_object_killed why); #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 3b2282c157f7..0364a4ca16f6 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -15,861 +15,14 @@ #define _LINUX_FSCACHE_H #include -#include -#include -#include -#include #include #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) -#define fscache_available() (1) #define fscache_cookie_valid(cookie) (cookie) +#define fscache_cookie_enabled(cookie) (cookie) #else -#define fscache_available() (0) #define fscache_cookie_valid(cookie) (0) +#define fscache_cookie_enabled(cookie) (0) #endif - -/* 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; -struct netfs_read_request; - -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); - - /* 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 auxiliary data and the object size - */ - enum fscache_checkaux (*check_aux)(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size); - - /* 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 page that now have cache metadata retained - * - this function should mark the specified page as now being cached - * - the page will have been marked with PG_fscache before this is - * called, so this is optional - */ - void (*mark_page_cached)(void *cookie_netfs_data, - struct address_space *mapping, - struct page *page); -}; - -/* - * 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; -}; - -/* - * 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 { - refcount_t ref; /* number of users of this cookie */ - atomic_t n_children; /* number of children of this cookie */ - atomic_t n_active; /* number of active users of netfs ptrs */ - unsigned int debug_id; - spinlock_t lock; - spinlock_t stores_lock; /* lock on page store tree */ - 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 */ - struct hlist_bl_node hash_link; /* Link in hash table */ - struct list_head proc_link; /* Link in proc list */ - 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 */ -#define FSCACHE_COOKIE_STORING_TAG 1 /* pages tag: writing to cache */ - - unsigned long flags; -#define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ -#define FSCACHE_COOKIE_NO_DATA_YET 1 /* T if new object with no cached data yet */ -#define FSCACHE_COOKIE_UNAVAILABLE 2 /* T if cookie is unavailable (error, etc) */ -#define FSCACHE_COOKIE_INVALIDATING 3 /* T if cookie is being invalidated */ -#define FSCACHE_COOKIE_RELINQUISHED 4 /* T if cookie has been relinquished */ -#define FSCACHE_COOKIE_ENABLED 5 /* T if cookie is enabled */ -#define FSCACHE_COOKIE_ENABLEMENT_LOCK 6 /* T if cookie is being en/disabled */ -#define FSCACHE_COOKIE_AUX_UPDATED 8 /* T if the auxiliary data was updated */ -#define FSCACHE_COOKIE_ACQUIRED 9 /* T if cookie is in use */ -#define FSCACHE_COOKIE_RELINQUISHING 10 /* T if cookie is being relinquished */ - - u8 type; /* Type of object */ - u8 key_len; /* Length of index key */ - u8 aux_len; /* Length of auxiliary data */ - u32 key_hash; /* Hash of parent, type, key, len */ - union { - void *key; /* Index key */ - u8 inline_key[16]; /* - If the key is short enough */ - }; - union { - void *aux; /* Auxiliary data */ - u8 inline_aux[8]; /* - If the aux data is short enough */ - }; -}; - -static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) -{ - return fscache_cookie_valid(cookie) && test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); -} - -/* - * 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 - */ -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 *); - -extern struct fscache_cookie *__fscache_acquire_cookie( - struct fscache_cookie *, - const struct fscache_cookie_def *, - const void *, size_t, - const void *, size_t, - void *, loff_t, bool); -extern void __fscache_relinquish_cookie(struct fscache_cookie *, const void *, bool); -extern int __fscache_check_consistency(struct fscache_cookie *, const void *); -extern void __fscache_update_cookie(struct fscache_cookie *, const void *); -extern int __fscache_attr_changed(struct fscache_cookie *); -extern void __fscache_invalidate(struct fscache_cookie *); -extern void __fscache_wait_on_invalidate(struct fscache_cookie *); - -#ifdef FSCACHE_USE_NEW_IO_API -extern int __fscache_begin_read_operation(struct netfs_read_request *, struct fscache_cookie *); -#else -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 *, loff_t, 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 *); -extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, - gfp_t); -extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *, - struct inode *); -extern void __fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages); -#endif /* FSCACHE_USE_NEW_IO_API */ - -extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool); -extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t, - bool (*)(void *), void *); - -/** - * 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.rst for a complete - * description. - */ -static inline -int fscache_register_netfs(struct fscache_netfs *netfs) -{ - if (fscache_available()) - return __fscache_register_netfs(netfs); - else - 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.rst for a complete - * description. - */ -static inline -void fscache_unregister_netfs(struct fscache_netfs *netfs) -{ - if (fscache_available()) - __fscache_unregister_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.rst for a complete - * description. - */ -static inline -struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) -{ - if (fscache_available()) - return __fscache_lookup_cache_tag(name); - else - 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.rst for a complete - * description. - */ -static inline -void fscache_release_cache_tag(struct fscache_cache_tag *tag) -{ - if (fscache_available()) - __fscache_release_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 - * @index_key: The index key for this cookie - * @index_key_len: Size of the index key - * @aux_data: The auxiliary data for the cookie (may be NULL) - * @aux_data_len: Size of the auxiliary data buffer - * @netfs_data: An arbitrary piece of data to be kept in the cookie to - * represent the cache object to the netfs - * @object_size: The initial size of object - * @enable: Whether or not to enable a data cookie immediately - * - * 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.rst for a complete - * description. - */ -static inline -struct fscache_cookie *fscache_acquire_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, - const void *index_key, - size_t index_key_len, - const void *aux_data, - size_t aux_data_len, - void *netfs_data, - loff_t object_size, - bool enable) -{ - if (fscache_cookie_valid(parent) && fscache_cookie_enabled(parent)) - return __fscache_acquire_cookie(parent, def, - index_key, index_key_len, - aux_data, aux_data_len, - netfs_data, object_size, enable); - else - return NULL; -} - -/** - * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding - * it - * @cookie: The cookie being returned - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @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. The opportunity is - * provided to update the auxiliary data in the cache before the object is - * disconnected. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_relinquish_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool retire) -{ - if (fscache_cookie_valid(cookie)) - __fscache_relinquish_cookie(cookie, aux_data, retire); -} - -/** - * fscache_check_consistency - Request validation of a cache's auxiliary data - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an consistency check from fscache, which passes the request to the - * backing cache. The auxiliary data on the cookie will be updated first if - * @aux_data is set. - * - * Returns 0 if consistent and -ESTALE if inconsistent. May also - * return -ENOMEM and -ERESTARTSYS. - */ -static inline -int fscache_check_consistency(struct fscache_cookie *cookie, - const void *aux_data) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_check_consistency(cookie, aux_data); - else - return 0; -} - -/** - * fscache_update_cookie - Request that a cache object be updated - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an update of the index data for the cache object associated with the - * cookie. The auxiliary data on the cookie will be updated first if @aux_data - * is set. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_update_cookie(cookie, aux_data); -} - -/** - * 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.rst 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.rst 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.rst for a complete - * description. - */ -static inline -int fscache_attr_changed(struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_attr_changed(cookie); - else - return -ENOBUFS; -} - -/** - * fscache_invalidate - Notify cache that an object needs invalidation - * @cookie: The cookie representing the cache object - * - * Notify the cache that an object is needs to be invalidated and that it - * should abort any retrievals or stores it is doing on the cache. The object - * is then marked non-caching until such time as the invalidation is complete. - * - * This can be called with spinlocks held. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_invalidate(struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_invalidate(cookie); -} - -/** - * fscache_wait_on_invalidate - Wait for invalidation to complete - * @cookie: The cookie representing the cache object - * - * Wait for the invalidation of an object to complete. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_wait_on_invalidate(struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie)) - __fscache_wait_on_invalidate(cookie); -} - -/** - * 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.rst for a complete - * description. - */ -static inline -int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) -{ - return -ENOBUFS; -} - -#ifdef FSCACHE_USE_NEW_IO_API - -/** - * fscache_begin_read_operation - Begin a read operation for the netfs lib - * @rreq: The read request being undertaken - * @cookie: The cookie representing the cache object - * - * Begin a read operation on behalf of the netfs helper library. @rreq - * indicates the read request to which the operation state should be attached; - * @cookie indicates the cache object that will be accessed. - * - * This is intended to be called from the ->begin_cache_operation() netfs lib - * operation as implemented by the network filesystem. - * - * Returns: - * * 0 - Success - * * -ENOBUFS - No caching available - * * Other error code from the cache, such as -ENOMEM. - */ -static inline -int fscache_begin_read_operation(struct netfs_read_request *rreq, - struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_begin_read_operation(rreq, cookie); - return -ENOBUFS; -} - -#else /* FSCACHE_USE_NEW_IO_API */ - -/** - * 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.rst 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) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_page(cookie, page, end_io_func, - context, gfp); - else - 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 - * @nr_pages: Number of pages to be read and/or allocated - * @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.rst 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) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_pages(cookie, mapping, pages, - nr_pages, end_io_func, - context, gfp); - else - 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.rst for a complete - * description. - */ -static inline -int fscache_alloc_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_alloc_page(cookie, page, gfp); - else - return -ENOBUFS; -} - -/** - * fscache_readpages_cancel - Cancel read/alloc on pages - * @cookie: The cookie representing the inode's cache object. - * @pages: The netfs pages that we canceled write on in readpages() - * - * Uncache/unreserve the pages reserved earlier in readpages() via - * fscache_readpages_or_alloc() and similar. In most successful caches in - * readpages() this doesn't do anything. In cases when the underlying netfs's - * readahead failed we need to clean up the pagelist (unmark and uncache). - * - * This function may sleep as it may have to clean up disk state. - */ -static inline -void fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages) -{ - if (fscache_cookie_valid(cookie)) - __fscache_readpages_cancel(cookie, pages); -} - -/** - * fscache_write_page - Request storage of a page in the cache - * @cookie: The cookie representing the cache object - * @page: The netfs page to store - * @object_size: Updated size of object - * @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.rst for a complete - * description. - */ -static inline -int fscache_write_page(struct fscache_cookie *cookie, - struct page *page, - loff_t object_size, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_write_page(cookie, page, object_size, gfp); - else - 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.rst for a complete - * description. - */ -static inline -void fscache_uncache_page(struct fscache_cookie *cookie, - struct page *page) -{ - if (fscache_cookie_valid(cookie)) - __fscache_uncache_page(cookie, 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.rst for a complete - * description. - */ -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; -} - -/** - * 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.rst for a complete - * description. - */ -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); -} - -/** - * fscache_maybe_release_page - Consider releasing a page, cancelling a store - * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * @gfp: The gfp flags passed to releasepage() - * - * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's - * releasepage() call. A storage request on the page may cancelled if it is - * not currently being processed. - * - * The function returns true if the page no longer has a storage request on it, - * and false if a storage request is left in place. If true is returned, the - * page will have been passed to fscache_uncache_page(). If false is returned - * the page cannot be freed yet. - */ -static inline -bool fscache_maybe_release_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && PageFsCache(page)) - return __fscache_maybe_release_page(cookie, page, gfp); - return true; -} - -/** - * fscache_uncache_all_inode_pages - Uncache all an inode's pages - * @cookie: The cookie representing the inode's cache object. - * @inode: The inode to uncache pages from. - * - * Uncache all the pages in an inode that are marked PG_fscache, assuming them - * to be associated with the given cookie. - * - * This function may sleep. It will wait for pages that are being written out - * and will wait whilst the PG_fscache mark is removed by the cache. - */ -static inline -void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, - struct inode *inode) -{ - if (fscache_cookie_valid(cookie)) - __fscache_uncache_all_inode_pages(cookie, inode); -} - -#endif /* FSCACHE_USE_NEW_IO_API */ - -/** - * fscache_disable_cookie - Disable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @invalidate: Invalidate the backing object - * - * Disable a cookie from accepting further alloc, read, write, invalidate, - * update or acquire operations. Outstanding operations can still be waited - * upon and pages can still be uncached and the cookie relinquished. - * - * This will not return until all outstanding operations have completed. - * - * If @invalidate is set, then the backing object will be invalidated and - * detached, otherwise it will just be detached. - * - * If @aux_data is set, then auxiliary data will be updated from that. - */ -static inline -void fscache_disable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool invalidate) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_disable_cookie(cookie, aux_data, invalidate); -} - -/** - * fscache_enable_cookie - Reenable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @object_size: Current size of object - * @can_enable: A function to permit enablement once lock is held - * @data: Data for can_enable() - * - * Reenable a previously disabled cookie, allowing it to accept further alloc, - * read, write, invalidate, update or acquire operations. An attempt will be - * made to immediately reattach the cookie to a backing object. If @aux_data - * is set, the auxiliary data attached to the cookie will be updated. - * - * The can_enable() function is called (if not NULL) once the enablement lock - * is held to rule on whether enablement is still permitted to go ahead. - */ -static inline -void fscache_enable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - loff_t object_size, - bool (*can_enable)(void *data), - void *data) -{ - if (fscache_cookie_valid(cookie) && !fscache_cookie_enabled(cookie)) - __fscache_enable_cookie(cookie, aux_data, object_size, - can_enable, data); -} - #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From a39c41b853ee51f4dcd19f5556f860ae8e2f23d3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:30:37 +0100 Subject: netfs: Pass a flag to ->prepare_write() to say if there's no alloc'd space Pass a flag to ->prepare_write() to indicate if there's definitely no space allocated in the cache yet (for instance if we've already checked as we were asked to do a read). Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819583123.215744.12783808230464471417.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906886835.143852.6689886781122679769.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967079100.1823006.12889542712309574359.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021489334.640689.3131206613015409076.stgit@warthog.procyon.org.uk/ # v4 --- fs/netfs/read_helper.c | 2 +- include/linux/netfs.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 75c76cbb27cc..9dd76b8914f2 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -323,7 +323,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq) } ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - rreq->i_size); + rreq->i_size, true); if (ret < 0) { trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ca0683b9e3d1..1ea22fc48818 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -232,7 +232,8 @@ struct netfs_cache_ops { * actually do. */ int (*prepare_write)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + loff_t *_start, size_t *_len, loff_t i_size, + bool no_space_allocated_yet); }; struct readahead_control; -- cgit v1.2.3 From 1e1236b841166f1d2daf36fdf6bb3e656bc5f5ca Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:34:41 +0100 Subject: fscache: Introduce new driver Introduce basic skeleton of the new, rewritten fscache driver. Changes ======= ver #3: - Use remove_proc_subtree(), not remove_proc_entry() to remove a populated dir. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819584034.215744.4290533472390439030.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906887770.143852.3577888294989185666.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967080039.1823006.5702921801104057922.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021491014.640689.4292699878317589512.stgit@warthog.procyon.org.uk/ # v4 --- fs/Makefile | 1 + fs/fscache/Kconfig | 39 +++++++++ fs/fscache/Makefile | 12 +++ fs/fscache/internal.h | 183 +++++++++++++++++++++++++++++++++++++++++ fs/fscache/main.c | 65 +++++++++++++++ fs/fscache/proc.c | 42 ++++++++++ fs/fscache/stats.c | 22 +++++ include/linux/fscache-cache.h | 2 + include/linux/fscache.h | 6 +- include/trace/events/fscache.h | 49 +++++++++++ 10 files changed, 420 insertions(+), 1 deletion(-) create mode 100644 fs/fscache/Makefile create mode 100644 fs/fscache/internal.h create mode 100644 fs/fscache/main.c create mode 100644 fs/fscache/proc.c create mode 100644 fs/fscache/stats.c create mode 100644 include/trace/events/fscache.h (limited to 'include/linux') diff --git a/fs/Makefile b/fs/Makefile index 23ddd0803d14..290815f3fd31 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -67,6 +67,7 @@ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line obj-$(CONFIG_NETFS_SUPPORT) += netfs/ +obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ obj-$(CONFIG_EXT4_FS) += ext4/ # We place ext4 before ext2 so that clean ext3 root fs's do NOT mount using the diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 6440484d9461..76316c4a3fb7 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -1,4 +1,43 @@ # SPDX-License-Identifier: GPL-2.0-only +config FSCACHE + tristate "General filesystem local caching manager" + select NETFS_SUPPORT + help + This option enables a generic filesystem caching manager that can be + used by various network and other filesystems to cache data locally. + Different sorts of caches can be plugged in, depending on the + resources available. + + See Documentation/filesystems/caching/fscache.rst for more information. + +config FSCACHE_STATS + bool "Gather statistical information on local caching" + depends on FSCACHE && PROC_FS + select NETFS_STATS + help + This option causes statistical information to be gathered on local + caching and exported through file: + + /proc/fs/fscache/stats + + The gathering of statistics adds a certain amount of overhead to + execution as there are a quite a few stats gathered, and on a + multi-CPU system these may be on cachelines that keep bouncing + between CPUs. On the other hand, the stats are very useful for + debugging purposes. Saying 'Y' here is recommended. + + See Documentation/filesystems/caching/fscache.rst for more information. + +config FSCACHE_DEBUG + bool "Debug FS-Cache" + depends on FSCACHE + help + This permits debugging to be dynamically enabled in the local caching + management module. If this is set, the debugging output may be + enabled by setting bits in /sys/modules/fscache/parameter/debug. + + See Documentation/filesystems/caching/fscache.rst for more information. + config FSCACHE_OLD_API bool diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile new file mode 100644 index 000000000000..f9722de32247 --- /dev/null +++ b/fs/fscache/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for general filesystem caching code +# + +fscache-y := \ + main.o + +fscache-$(CONFIG_PROC_FS) += proc.o +fscache-$(CONFIG_FSCACHE_STATS) += stats.o + +obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h new file mode 100644 index 000000000000..ea52f8594a77 --- /dev/null +++ b/fs/fscache/internal.h @@ -0,0 +1,183 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Internal definitions for FS-Cache + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) "FS-Cache: " fmt + +#include +#include +#include +#include +#include + +/* + * main.c + */ +extern unsigned fscache_debug; + +/* + * proc.c + */ +#ifdef CONFIG_PROC_FS +extern int __init fscache_proc_init(void); +extern void fscache_proc_cleanup(void); +#else +#define fscache_proc_init() (0) +#define fscache_proc_cleanup() do {} while (0) +#endif + +/* + * stats.c + */ +#ifdef CONFIG_FSCACHE_STATS + +static inline void fscache_stat(atomic_t *stat) +{ + atomic_inc(stat); +} + +static inline void fscache_stat_d(atomic_t *stat) +{ + atomic_dec(stat); +} + +#define __fscache_stat(stat) (stat) + +int fscache_stats_show(struct seq_file *m, void *v); +#else + +#define __fscache_stat(stat) (NULL) +#define fscache_stat(stat) do {} while (0) +#define fscache_stat_d(stat) do {} while (0) +#endif + + +/*****************************************************************************/ +/* + * debug tracing + */ +#define dbgprintk(FMT, ...) \ + printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) + +#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__) + +#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__) + +#ifdef __KDEBUG +#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__) +#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__) +#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__) + +#elif defined(CONFIG_FSCACHE_DEBUG) +#define _enter(FMT, ...) \ +do { \ + if (__do_kdebug(ENTER)) \ + kenter(FMT, ##__VA_ARGS__); \ +} while (0) + +#define _leave(FMT, ...) \ +do { \ + if (__do_kdebug(LEAVE)) \ + kleave(FMT, ##__VA_ARGS__); \ +} while (0) + +#define _debug(FMT, ...) \ +do { \ + if (__do_kdebug(DEBUG)) \ + kdebug(FMT, ##__VA_ARGS__); \ +} while (0) + +#else +#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__) +#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__) +#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__) +#endif + +/* + * determine whether a particular optional debugging point should be logged + * - we need to go through three steps to persuade cpp to correctly join the + * shorthand in FSCACHE_DEBUG_LEVEL with its prefix + */ +#define ____do_kdebug(LEVEL, POINT) \ + unlikely((fscache_debug & \ + (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3)))) +#define ___do_kdebug(LEVEL, POINT) \ + ____do_kdebug(LEVEL, POINT) +#define __do_kdebug(POINT) \ + ___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT) + +#define FSCACHE_DEBUG_CACHE 0 +#define FSCACHE_DEBUG_COOKIE 1 +#define FSCACHE_DEBUG_OBJECT 2 +#define FSCACHE_DEBUG_OPERATION 3 + +#define FSCACHE_POINT_ENTER 1 +#define FSCACHE_POINT_LEAVE 2 +#define FSCACHE_POINT_DEBUG 4 + +#ifndef FSCACHE_DEBUG_LEVEL +#define FSCACHE_DEBUG_LEVEL CACHE +#endif + +/* + * assertions + */ +#if 1 /* defined(__KDEBUGALL) */ + +#define ASSERT(X) \ +do { \ + if (unlikely(!(X))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTCMP(X, OP, Y) \ +do { \ + if (unlikely(!((X) OP (Y)))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ + (unsigned long)(X), (unsigned long)(Y)); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTIF(C, X) \ +do { \ + if (unlikely((C) && !(X))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTIFCMP(C, X, OP, Y) \ +do { \ + if (unlikely((C) && !((X) OP (Y)))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ + (unsigned long)(X), (unsigned long)(Y)); \ + BUG(); \ + } \ +} while (0) + +#else + +#define ASSERT(X) do {} while (0) +#define ASSERTCMP(X, OP, Y) do {} while (0) +#define ASSERTIF(C, X) do {} while (0) +#define ASSERTIFCMP(C, X, OP, Y) do {} while (0) + +#endif /* assert or not */ diff --git a/fs/fscache/main.c b/fs/fscache/main.c new file mode 100644 index 000000000000..819de2ee1276 --- /dev/null +++ b/fs/fscache/main.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* General filesystem local caching manager + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#define CREATE_TRACE_POINTS +#include "internal.h" + +MODULE_DESCRIPTION("FS Cache Manager"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +unsigned fscache_debug; +module_param_named(debug, fscache_debug, uint, + S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(fscache_debug, + "FS-Cache debugging mask"); + +struct workqueue_struct *fscache_wq; +EXPORT_SYMBOL(fscache_wq); + +/* + * initialise the fs caching module + */ +static int __init fscache_init(void) +{ + int ret = -ENOMEM; + + fscache_wq = alloc_workqueue("fscache", WQ_UNBOUND | WQ_FREEZABLE, 0); + if (!fscache_wq) + goto error_wq; + + ret = fscache_proc_init(); + if (ret < 0) + goto error_proc; + + pr_notice("Loaded\n"); + return 0; + +error_proc: + destroy_workqueue(fscache_wq); +error_wq: + return ret; +} + +fs_initcall(fscache_init); + +/* + * clean up on module removal + */ +static void __exit fscache_exit(void) +{ + _enter(""); + + fscache_proc_cleanup(); + destroy_workqueue(fscache_wq); + pr_notice("Unloaded\n"); +} + +module_exit(fscache_exit); diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c new file mode 100644 index 000000000000..4d866ac41776 --- /dev/null +++ b/fs/fscache/proc.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* FS-Cache statistics viewing interface + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#include +#include "internal.h" + +/* + * initialise the /proc/fs/fscache/ directory + */ +int __init fscache_proc_init(void) +{ + if (!proc_mkdir("fs/fscache", NULL)) + goto error_dir; + +#ifdef CONFIG_FSCACHE_STATS + if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, + fscache_stats_show)) + goto error; +#endif + + return 0; + +error: + remove_proc_entry("fs/fscache", NULL); +error_dir: + return -ENOMEM; +} + +/* + * clean up the /proc/fs/fscache/ directory + */ +void fscache_proc_cleanup(void) +{ + remove_proc_subtree("fs/fscache", NULL); +} diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c new file mode 100644 index 000000000000..bd92f93e1680 --- /dev/null +++ b/fs/fscache/stats.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* FS-Cache statistics + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#include "internal.h" + +/* + * display the general statistics + */ +int fscache_stats_show(struct seq_file *m, void *v) +{ + seq_puts(m, "FS-Cache statistics\n"); + + netfs_stats_show(m); + return 0; +} diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 47f21a53ac4b..d6910a913918 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -16,4 +16,6 @@ #include +extern struct workqueue_struct *fscache_wq; + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 0364a4ca16f6..1cf90c252aac 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -18,9 +18,13 @@ #include #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) +#define __fscache_available (1) +#define fscache_available() (1) #define fscache_cookie_valid(cookie) (cookie) #define fscache_cookie_enabled(cookie) (cookie) #else +#define __fscache_available (0) +#define fscache_available() (0) #define fscache_cookie_valid(cookie) (0) #define fscache_cookie_enabled(cookie) (0) #endif diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h new file mode 100644 index 000000000000..fe214c5cc87f --- /dev/null +++ b/include/trace/events/fscache.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* FS-Cache tracepoints + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM fscache + +#if !defined(_TRACE_FSCACHE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_FSCACHE_H + +#include +#include + +/* + * Define enums for tracing information. + */ +#ifndef __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#endif + +/* + * Declare tracing information enums and their string mappings for display. + */ + +/* + * Export enum symbols via userspace. + */ +#undef EM +#undef E_ +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define E_(a, b) TRACE_DEFINE_ENUM(a); + +/* + * Now redefine the EM() and E_() macros to map the enums to the strings that + * will be printed in the output. + */ +#undef EM +#undef E_ +#define EM(a, b) { a, b }, +#define E_(a, b) { a, b } + + +#endif /* _TRACE_FSCACHE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 9549332df4ed4e761a1d41c83f2c25d28bb22431 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:00:26 +0100 Subject: fscache: Implement cache registration Implement a register of caches and provide functions to manage it. Two functions are provided for the cache backend to use: (1) Acquire a cache cookie: struct fscache_cache *fscache_acquire_cache(const char *name) This gets the cache cookie for a cache of the specified name and moves it to the preparation state. If a nameless cache cookie exists, that will be given this name and used. (2) Relinquish a cache cookie: void fscache_relinquish_cache(struct fscache_cache *cache); This relinquishes a cache cookie, cleans it and makes it available if it's still referenced by a network filesystem. Note that network filesystems don't deal with cache cookies directly, but rather go straight to the volume registration. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819587157.215744.13523139317322503286.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906889665.143852.10378009165231294456.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967085081.1823006.2218944206363626210.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021494847.640689.10109692261640524343.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 1 + fs/fscache/cache.c | 274 +++++++++++++++++++++++++++++++++++++++++ fs/fscache/internal.h | 33 +++++ fs/fscache/proc.c | 4 + include/linux/fscache-cache.h | 34 +++++ include/trace/events/fscache.h | 43 +++++++ 6 files changed, 389 insertions(+) create mode 100644 fs/fscache/cache.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index f9722de32247..d9fc22c18090 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -4,6 +4,7 @@ # fscache-y := \ + cache.o \ main.o fscache-$(CONFIG_PROC_FS) += proc.o diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c new file mode 100644 index 000000000000..8db77bb9f8e2 --- /dev/null +++ b/fs/fscache/cache.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* FS-Cache cache handling + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#include "internal.h" + +static LIST_HEAD(fscache_caches); +DECLARE_RWSEM(fscache_addremove_sem); +EXPORT_SYMBOL(fscache_addremove_sem); + +static atomic_t fscache_cache_debug_id; + +/* + * Allocate a cache cookie. + */ +static struct fscache_cache *fscache_alloc_cache(const char *name) +{ + struct fscache_cache *cache; + + cache = kzalloc(sizeof(*cache), GFP_KERNEL); + if (cache) { + if (name) { + cache->name = kstrdup(name, GFP_KERNEL); + if (!cache->name) { + kfree(cache); + return NULL; + } + } + refcount_set(&cache->ref, 1); + INIT_LIST_HEAD(&cache->cache_link); + cache->debug_id = atomic_inc_return(&fscache_cache_debug_id); + } + return cache; +} + +static bool fscache_get_cache_maybe(struct fscache_cache *cache, + enum fscache_cache_trace where) +{ + bool success; + int ref; + + success = __refcount_inc_not_zero(&cache->ref, &ref); + if (success) + trace_fscache_cache(cache->debug_id, ref + 1, where); + return success; +} + +/* + * Look up a cache cookie. + */ +struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache) +{ + struct fscache_cache *candidate, *cache, *unnamed = NULL; + + /* firstly check for the existence of the cache under read lock */ + down_read(&fscache_addremove_sem); + + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && name && strcmp(cache->name, name) == 0 && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + if (!cache->name && !name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + } + + if (!name) { + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + } + } + + up_read(&fscache_addremove_sem); + + /* the cache does not exist - create a candidate */ + candidate = fscache_alloc_cache(name); + if (!candidate) + return ERR_PTR(-ENOMEM); + + /* write lock, search again and add if still not present */ + down_write(&fscache_addremove_sem); + + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && name && strcmp(cache->name, name) == 0 && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + if (!cache->name) { + unnamed = cache; + if (!name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + } + } + + if (unnamed && is_cache && + fscache_get_cache_maybe(unnamed, fscache_cache_get_acquire)) + goto use_unnamed_cache; + + if (!name) { + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + } + } + + list_add_tail(&candidate->cache_link, &fscache_caches); + trace_fscache_cache(candidate->debug_id, + refcount_read(&candidate->ref), + fscache_cache_new_acquire); + up_write(&fscache_addremove_sem); + return candidate; + +got_cache_r: + up_read(&fscache_addremove_sem); + return cache; +use_unnamed_cache: + cache = unnamed; + cache->name = candidate->name; + candidate->name = NULL; +got_cache_w: + up_write(&fscache_addremove_sem); + kfree(candidate->name); + kfree(candidate); + return cache; +} + +/** + * fscache_acquire_cache - Acquire a cache-level cookie. + * @name: The name of the cache. + * + * Get a cookie to represent an actual cache. If a name is given and there is + * a nameless cache record available, this will acquire that and set its name, + * directing all the volumes using it to this cache. + * + * The cache will be switched over to the preparing state if not currently in + * use, otherwise -EBUSY will be returned. + */ +struct fscache_cache *fscache_acquire_cache(const char *name) +{ + struct fscache_cache *cache; + + ASSERT(name); + cache = fscache_lookup_cache(name, true); + if (IS_ERR(cache)) + return cache; + + if (!fscache_set_cache_state_maybe(cache, + FSCACHE_CACHE_IS_NOT_PRESENT, + FSCACHE_CACHE_IS_PREPARING)) { + pr_warn("Cache tag %s in use\n", name); + fscache_put_cache(cache, fscache_cache_put_cache); + return ERR_PTR(-EBUSY); + } + + return cache; +} +EXPORT_SYMBOL(fscache_acquire_cache); + +/** + * fscache_put_cache - Release a cache-level cookie. + * @cache: The cache cookie to be released + * @where: An indication of where the release happened + * + * Release the caller's reference on a cache-level cookie. The @where + * indication should give information about the circumstances in which the call + * occurs and will be logged through a tracepoint. + */ +void fscache_put_cache(struct fscache_cache *cache, + enum fscache_cache_trace where) +{ + unsigned int debug_id = cache->debug_id; + bool zero; + int ref; + + if (IS_ERR_OR_NULL(cache)) + return; + + zero = __refcount_dec_and_test(&cache->ref, &ref); + trace_fscache_cache(debug_id, ref - 1, where); + + if (zero) { + down_write(&fscache_addremove_sem); + list_del_init(&cache->cache_link); + up_write(&fscache_addremove_sem); + kfree(cache->name); + kfree(cache); + } +} + +/** + * fscache_relinquish_cache - Reset cache state and release cookie + * @cache: The cache cookie to be released + * + * Reset the state of a cache and release the caller's reference on a cache + * cookie. + */ +void fscache_relinquish_cache(struct fscache_cache *cache) +{ + enum fscache_cache_trace where = + (cache->state == FSCACHE_CACHE_IS_PREPARING) ? + fscache_cache_put_prep_failed : + fscache_cache_put_relinquish; + + cache->cache_priv = NULL; + smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); + fscache_put_cache(cache, where); +} +EXPORT_SYMBOL(fscache_relinquish_cache); + +#ifdef CONFIG_PROC_FS +static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW"; + +/* + * Generate a list of caches in /proc/fs/fscache/caches + */ +static int fscache_caches_seq_show(struct seq_file *m, void *v) +{ + struct fscache_cache *cache; + + if (v == &fscache_caches) { + seq_puts(m, + "CACHE REF VOLS OBJS ACCES S NAME\n" + "======== ===== ===== ===== ===== = ===============\n" + ); + return 0; + } + + cache = list_entry(v, struct fscache_cache, cache_link); + seq_printf(m, + "%08x %5d %5d %5d %5d %c %s\n", + cache->debug_id, + refcount_read(&cache->ref), + atomic_read(&cache->n_volumes), + atomic_read(&cache->object_count), + atomic_read(&cache->n_accesses), + fscache_cache_states[cache->state], + cache->name ?: "-"); + return 0; +} + +static void *fscache_caches_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(fscache_addremove_sem) +{ + down_read(&fscache_addremove_sem); + return seq_list_start_head(&fscache_caches, *_pos); +} + +static void *fscache_caches_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_caches, _pos); +} + +static void fscache_caches_seq_stop(struct seq_file *m, void *v) + __releases(fscache_addremove_sem) +{ + up_read(&fscache_addremove_sem); +} + +const struct seq_operations fscache_caches_seq_ops = { + .start = fscache_caches_seq_start, + .next = fscache_caches_seq_next, + .stop = fscache_caches_seq_stop, + .show = fscache_caches_seq_show, +}; +#endif /* CONFIG_PROC_FS */ diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index f345bdb018ba..8fd39e7735fc 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -17,6 +17,39 @@ #include #include +/* + * cache.c + */ +#ifdef CONFIG_PROC_FS +extern const struct seq_operations fscache_caches_seq_ops; +#endif +struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache); +void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where); + +static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache) +{ + return smp_load_acquire(&cache->state); +} + +static inline bool fscache_cache_is_live(const struct fscache_cache *cache) +{ + return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE; +} + +static inline void fscache_set_cache_state(struct fscache_cache *cache, + enum fscache_cache_state new_state) +{ + smp_store_release(&cache->state, new_state); + +} + +static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, + enum fscache_cache_state old_state, + enum fscache_cache_state new_state) +{ + return try_cmpxchg_release(&cache->state, &old_state, new_state); +} + /* * main.c */ diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 4d866ac41776..93b925709e09 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -19,6 +19,10 @@ int __init fscache_proc_init(void) if (!proc_mkdir("fs/fscache", NULL)) goto error_dir; + if (!proc_create_seq("fs/fscache/caches", S_IFREG | 0444, NULL, + &fscache_caches_seq_ops)) + goto error; + #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, fscache_stats_show)) diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index d6910a913918..18cd5c9877bb 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -16,6 +16,40 @@ #include +enum fscache_cache_trace; +enum fscache_access_trace; + +enum fscache_cache_state { + FSCACHE_CACHE_IS_NOT_PRESENT, /* No cache is present for this name */ + FSCACHE_CACHE_IS_PREPARING, /* A cache is preparing to come live */ + FSCACHE_CACHE_IS_ACTIVE, /* Attached cache is active and can be used */ + FSCACHE_CACHE_GOT_IOERROR, /* Attached cache stopped on I/O error */ + FSCACHE_CACHE_IS_WITHDRAWN, /* Attached cache is being withdrawn */ +#define NR__FSCACHE_CACHE_STATE (FSCACHE_CACHE_IS_WITHDRAWN + 1) +}; + +/* + * Cache cookie. + */ +struct fscache_cache { + struct list_head cache_link; /* Link in cache list */ + void *cache_priv; /* Private cache data (or NULL) */ + refcount_t ref; + atomic_t n_volumes; /* Number of active volumes; */ + atomic_t n_accesses; /* Number of in-progress accesses on the cache */ + atomic_t object_count; /* no. of live objects in this cache */ + unsigned int debug_id; + enum fscache_cache_state state; + char *name; +}; + extern struct workqueue_struct *fscache_wq; +/* + * out-of-line cache backend functions + */ +extern struct rw_semaphore fscache_addremove_sem; +extern struct fscache_cache *fscache_acquire_cache(const char *name); +extern void fscache_relinquish_cache(struct fscache_cache *cache); + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index fe214c5cc87f..3b8e0597b2c1 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -19,11 +19,27 @@ #ifndef __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY +enum fscache_cache_trace { + fscache_cache_collision, + fscache_cache_get_acquire, + fscache_cache_new_acquire, + fscache_cache_put_cache, + fscache_cache_put_prep_failed, + fscache_cache_put_relinquish, +}; + #endif /* * Declare tracing information enums and their string mappings for display. */ +#define fscache_cache_traces \ + EM(fscache_cache_collision, "*COLLIDE*") \ + EM(fscache_cache_get_acquire, "GET acq ") \ + EM(fscache_cache_new_acquire, "NEW acq ") \ + EM(fscache_cache_put_cache, "PUT cache") \ + EM(fscache_cache_put_prep_failed, "PUT pfail") \ + E_(fscache_cache_put_relinquish, "PUT relnq") /* * Export enum symbols via userspace. @@ -33,6 +49,8 @@ #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); +fscache_cache_traces; + /* * Now redefine the EM() and E_() macros to map the enums to the strings that * will be printed in the output. @@ -43,6 +61,31 @@ #define E_(a, b) { a, b } +TRACE_EVENT(fscache_cache, + TP_PROTO(unsigned int cache_debug_id, + int usage, + enum fscache_cache_trace where), + + TP_ARGS(cache_debug_id, usage, where), + + TP_STRUCT__entry( + __field(unsigned int, cache ) + __field(int, usage ) + __field(enum fscache_cache_trace, where ) + ), + + TP_fast_assign( + __entry->cache = cache_debug_id; + __entry->usage = usage; + __entry->where = where; + ), + + TP_printk("C=%08x %s r=%d", + __entry->cache, + __print_symbolic(__entry->where, fscache_cache_traces), + __entry->usage) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 62ab63352350e881ae693a8236b35d7d0516c78b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:26:17 +0100 Subject: fscache: Implement volume registration Add functions to the fscache API to allow volumes to be acquired and relinquished by the network filesystem. A volume is an index of data storage cache objects. A volume is represented by a volume cookie in the API. A filesystem would typically create a volume for a superblock and then create per-inode cookies within it. To request a volume, the filesystem calls: struct fscache_volume * fscache_acquire_volume(const char *volume_key, const char *cache_name, const void *coherency_data, size_t coherency_len) The volume_key is a printable string used to match the volume in the cache. It should not contain any '/' characters. For AFS, for example, this would be "afs,,", e.g. "afs,example.com,523001". The cache_name can be NULL, but if not it should be a string indicating the name of the cache to use if there's more than one available. The coherency data, if given, is an arbitrarily-sized blob that's attached to the volume and is compared when the volume is looked up. If it doesn't match, the old volume is judged to be out of date and it and everything within it is discarded. Acquiring a volume twice concurrently is disallowed, though the function will wait if an old volume cookie is being relinquishing. When a network filesystem has finished with a volume, it should return the volume cookie by calling: void fscache_relinquish_volume(struct fscache_volume *volume, const void *coherency_data, bool invalidate) If invalidate is true, the entire volume will be discarded; if false, the volume will be synced and the coherency data will be updated. Changes ======= ver #4: - Removed an extraneous param from kdoc on fscache_relinquish_volume()[3]. ver #3: - fscache_hash()'s size parameter is now in bytes. Use __le32 as the unit to round up to. - When comparing cookies, simply see if the attributes are the same rather than subtracting them to produce a strcmp-style return[2]. - Make the coherency data an arbitrary blob rather than a u64, but don't store it for the moment. ver #2: - Fix error check[1]. - Make a fscache_acquire_volume() return errors, including EBUSY if a conflicting volume cookie already exists. No error is printed now - that's left to the netfs. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203095608.GC2480@kili/ [1] Link: https://lore.kernel.org/r/CAHk-=whtkzB446+hX0zdLsdcUJsJ=8_-0S1mE_R+YurThfUbLA@mail.gmail.com/ [2] Link: https://lore.kernel.org/r/20211220224646.30e8205c@canb.auug.org.au/ [3] Link: https://lore.kernel.org/r/163819588944.215744.1629085755564865996.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906890630.143852.13972180614535611154.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967086836.1823006.8191672796841981763.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021495816.640689.4403156093668590217.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 3 +- fs/fscache/internal.h | 14 ++ fs/fscache/proc.c | 4 + fs/fscache/stats.c | 12 ++ fs/fscache/volume.c | 340 +++++++++++++++++++++++++++++++++++++++++ include/linux/fscache.h | 84 ++++++++++ include/trace/events/fscache.h | 61 +++++++- 7 files changed, 516 insertions(+), 2 deletions(-) create mode 100644 fs/fscache/volume.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index d9fc22c18090..bb5282ae682f 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -5,7 +5,8 @@ fscache-y := \ cache.o \ - main.o + main.o \ + volume.o fscache-$(CONFIG_PROC_FS) += proc.o fscache-$(CONFIG_FSCACHE_STATS) += stats.o diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 8fd39e7735fc..07dc9cbc2280 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -72,6 +72,9 @@ extern void fscache_proc_cleanup(void); * stats.c */ #ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_volumes; +extern atomic_t fscache_n_volumes_collision; +extern atomic_t fscache_n_volumes_nomem; static inline void fscache_stat(atomic_t *stat) { @@ -93,6 +96,17 @@ int fscache_stats_show(struct seq_file *m, void *v); #define fscache_stat_d(stat) do {} while (0) #endif +/* + * volume.c + */ +extern const struct seq_operations fscache_volumes_seq_ops; + +struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +void fscache_create_volume(struct fscache_volume *volume, bool wait); + /*****************************************************************************/ /* diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 93b925709e09..bc6ecbdd065d 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -23,6 +23,10 @@ int __init fscache_proc_init(void) &fscache_caches_seq_ops)) goto error; + if (!proc_create_seq("fs/fscache/volumes", S_IFREG | 0444, NULL, + &fscache_volumes_seq_ops)) + goto error; + #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, fscache_stats_show)) diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index bd92f93e1680..b811a4d03585 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -10,12 +10,24 @@ #include #include "internal.h" +/* + * operation counters + */ +atomic_t fscache_n_volumes; +atomic_t fscache_n_volumes_collision; +atomic_t fscache_n_volumes_nomem; + /* * display the general statistics */ int fscache_stats_show(struct seq_file *m, void *v) { seq_puts(m, "FS-Cache statistics\n"); + seq_printf(m, "Cookies: v=%d vcol=%u voom=%u\n", + atomic_read(&fscache_n_volumes), + atomic_read(&fscache_n_volumes_collision), + atomic_read(&fscache_n_volumes_nomem) + ); netfs_stats_show(m); return 0; diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c new file mode 100644 index 000000000000..630894fefd02 --- /dev/null +++ b/fs/fscache/volume.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Volume-level cache cookie handling. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL COOKIE +#include +#include +#include "internal.h" + +#define fscache_volume_hash_shift 10 +static struct hlist_bl_head fscache_volume_hash[1 << fscache_volume_hash_shift]; +static atomic_t fscache_volume_debug_id; +static LIST_HEAD(fscache_volumes); + +struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + int ref; + + __refcount_inc(&volume->ref, &ref); + trace_fscache_volume(volume->debug_id, ref + 1, where); + return volume; +} + +static void fscache_see_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + int ref = refcount_read(&volume->ref); + + trace_fscache_volume(volume->debug_id, ref, where); +} + +static bool fscache_volume_same(const struct fscache_volume *a, + const struct fscache_volume *b) +{ + size_t klen; + + if (a->key_hash != b->key_hash || + a->cache != b->cache || + a->key[0] != b->key[0]) + return false; + + klen = round_up(a->key[0] + 1, sizeof(__le32)); + return memcmp(a->key, b->key, klen) == 0; +} + +static bool fscache_is_acquire_pending(struct fscache_volume *volume) +{ + return test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &volume->flags); +} + +static void fscache_wait_on_volume_collision(struct fscache_volume *candidate, + unsigned int collidee_debug_id) +{ + wait_var_event_timeout(&candidate->flags, + fscache_is_acquire_pending(candidate), 20 * HZ); + if (!fscache_is_acquire_pending(candidate)) { + pr_notice("Potential volume collision new=%08x old=%08x", + candidate->debug_id, collidee_debug_id); + fscache_stat(&fscache_n_volumes_collision); + wait_var_event(&candidate->flags, fscache_is_acquire_pending(candidate)); + } +} + +/* + * Attempt to insert the new volume into the hash. If there's a collision, we + * wait for the old volume to complete if it's being relinquished and an error + * otherwise. + */ +static bool fscache_hash_volume(struct fscache_volume *candidate) +{ + struct fscache_volume *cursor; + struct hlist_bl_head *h; + struct hlist_bl_node *p; + unsigned int bucket, collidee_debug_id = 0; + + bucket = candidate->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); + h = &fscache_volume_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_volume_same(candidate, cursor)) { + if (!test_bit(FSCACHE_VOLUME_RELINQUISHED, &cursor->flags)) + goto collision; + fscache_see_volume(cursor, fscache_volume_get_hash_collision); + set_bit(FSCACHE_VOLUME_COLLIDED_WITH, &cursor->flags); + set_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags); + collidee_debug_id = cursor->debug_id; + break; + } + } + + hlist_bl_add_head(&candidate->hash_link, h); + hlist_bl_unlock(h); + + if (test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags)) + fscache_wait_on_volume_collision(candidate, collidee_debug_id); + return true; + +collision: + fscache_see_volume(cursor, fscache_volume_collision); + hlist_bl_unlock(h); + return false; +} + +/* + * Allocate and initialise a volume representation cookie. + */ +static struct fscache_volume *fscache_alloc_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + struct fscache_volume *volume; + struct fscache_cache *cache; + size_t klen, hlen; + char *key; + + cache = fscache_lookup_cache(cache_name, false); + if (IS_ERR(cache)) + return NULL; + + volume = kzalloc(sizeof(*volume), GFP_KERNEL); + if (!volume) + goto err_cache; + + volume->cache = cache; + INIT_LIST_HEAD(&volume->proc_link); + INIT_WORK(&volume->work, NULL /* PLACEHOLDER */); + refcount_set(&volume->ref, 1); + spin_lock_init(&volume->lock); + + /* Stick the length on the front of the key and pad it out to make + * hashing easier. + */ + klen = strlen(volume_key); + hlen = round_up(1 + klen + 1, sizeof(__le32)); + key = kzalloc(hlen, GFP_KERNEL); + if (!key) + goto err_vol; + key[0] = klen; + memcpy(key + 1, volume_key, klen); + + volume->key = key; + volume->key_hash = fscache_hash(0, key, hlen); + + volume->debug_id = atomic_inc_return(&fscache_volume_debug_id); + down_write(&fscache_addremove_sem); + atomic_inc(&cache->n_volumes); + list_add_tail(&volume->proc_link, &fscache_volumes); + fscache_see_volume(volume, fscache_volume_new_acquire); + fscache_stat(&fscache_n_volumes); + up_write(&fscache_addremove_sem); + _leave(" = v=%x", volume->debug_id); + return volume; + +err_vol: + kfree(volume); +err_cache: + fscache_put_cache(cache, fscache_cache_put_alloc_volume); + fscache_stat(&fscache_n_volumes_nomem); + return NULL; +} + +/* + * Acquire a volume representation cookie and link it to a (proposed) cache. + */ +struct fscache_volume *__fscache_acquire_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + struct fscache_volume *volume; + + volume = fscache_alloc_volume(volume_key, cache_name, + coherency_data, coherency_len); + if (!volume) + return ERR_PTR(-ENOMEM); + + if (!fscache_hash_volume(volume)) { + fscache_put_volume(volume, fscache_volume_put_hash_collision); + return ERR_PTR(-EBUSY); + } + + // PLACEHOLDER: Create the volume if we have a cache available + return volume; +} +EXPORT_SYMBOL(__fscache_acquire_volume); + +static void fscache_wake_pending_volume(struct fscache_volume *volume, + struct hlist_bl_head *h) +{ + struct fscache_volume *cursor; + struct hlist_bl_node *p; + + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_volume_same(cursor, volume)) { + fscache_see_volume(cursor, fscache_volume_see_hash_wake); + clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags); + wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING); + return; + } + } +} + +/* + * Remove a volume cookie from the hash table. + */ +static void fscache_unhash_volume(struct fscache_volume *volume) +{ + struct hlist_bl_head *h; + unsigned int bucket; + + bucket = volume->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); + h = &fscache_volume_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_del(&volume->hash_link); + if (test_bit(FSCACHE_VOLUME_COLLIDED_WITH, &volume->flags)) + fscache_wake_pending_volume(volume, h); + hlist_bl_unlock(h); +} + +/* + * Drop a cache's volume attachments. + */ +static void fscache_free_volume(struct fscache_volume *volume) +{ + struct fscache_cache *cache = volume->cache; + + if (volume->cache_priv) { + // PLACEHOLDER: Detach any attached cache + } + + down_write(&fscache_addremove_sem); + list_del_init(&volume->proc_link); + atomic_dec(&volume->cache->n_volumes); + up_write(&fscache_addremove_sem); + + if (!hlist_bl_unhashed(&volume->hash_link)) + fscache_unhash_volume(volume); + + trace_fscache_volume(volume->debug_id, 0, fscache_volume_free); + kfree(volume->key); + kfree(volume); + fscache_stat_d(&fscache_n_volumes); + fscache_put_cache(cache, fscache_cache_put_volume); +} + +/* + * Drop a reference to a volume cookie. + */ +void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + if (volume) { + unsigned int debug_id = volume->debug_id; + bool zero; + int ref; + + zero = __refcount_dec_and_test(&volume->ref, &ref); + trace_fscache_volume(debug_id, ref - 1, where); + if (zero) + fscache_free_volume(volume); + } +} + +/* + * Relinquish a volume representation cookie. + */ +void __fscache_relinquish_volume(struct fscache_volume *volume, + const void *coherency_data, + bool invalidate) +{ + if (WARN_ON(test_and_set_bit(FSCACHE_VOLUME_RELINQUISHED, &volume->flags))) + return; + + if (invalidate) + set_bit(FSCACHE_VOLUME_INVALIDATE, &volume->flags); + + fscache_put_volume(volume, fscache_volume_put_relinquish); +} +EXPORT_SYMBOL(__fscache_relinquish_volume); + +#ifdef CONFIG_PROC_FS +/* + * Generate a list of volumes in /proc/fs/fscache/volumes + */ +static int fscache_volumes_seq_show(struct seq_file *m, void *v) +{ + struct fscache_volume *volume; + + if (v == &fscache_volumes) { + seq_puts(m, + "VOLUME REF nCOOK ACC FL CACHE KEY\n" + "======== ===== ===== === == =============== ================\n"); + return 0; + } + + volume = list_entry(v, struct fscache_volume, proc_link); + seq_printf(m, + "%08x %5d %5d %3d %02lx %-15.15s %s\n", + volume->debug_id, + refcount_read(&volume->ref), + atomic_read(&volume->n_cookies), + atomic_read(&volume->n_accesses), + volume->flags, + volume->cache->name ?: "-", + volume->key + 1); + return 0; +} + +static void *fscache_volumes_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(&fscache_addremove_sem) +{ + down_read(&fscache_addremove_sem); + return seq_list_start_head(&fscache_volumes, *_pos); +} + +static void *fscache_volumes_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_volumes, _pos); +} + +static void fscache_volumes_seq_stop(struct seq_file *m, void *v) + __releases(&fscache_addremove_sem) +{ + up_read(&fscache_addremove_sem); +} + +const struct seq_operations fscache_volumes_seq_ops = { + .start = fscache_volumes_seq_start, + .next = fscache_volumes_seq_next, + .stop = fscache_volumes_seq_stop, + .show = fscache_volumes_seq_show, +}; +#endif /* CONFIG_PROC_FS */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 1cf90c252aac..131a741a6652 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -20,13 +20,97 @@ #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) #define __fscache_available (1) #define fscache_available() (1) +#define fscache_volume_valid(volume) (volume) #define fscache_cookie_valid(cookie) (cookie) #define fscache_cookie_enabled(cookie) (cookie) #else #define __fscache_available (0) #define fscache_available() (0) +#define fscache_volume_valid(volume) (0) #define fscache_cookie_valid(cookie) (0) #define fscache_cookie_enabled(cookie) (0) #endif +/* + * Volume representation cookie. + */ +struct fscache_volume { + refcount_t ref; + atomic_t n_cookies; /* Number of data cookies in volume */ + atomic_t n_accesses; /* Number of cache accesses in progress */ + unsigned int debug_id; + unsigned int key_hash; /* Hash of key string */ + char *key; /* Volume ID, eg. "afs@example.com@1234" */ + struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ + struct hlist_bl_node hash_link; /* Link in hash table */ + struct work_struct work; + struct fscache_cache *cache; /* The cache in which this resides */ + void *cache_priv; /* Cache private data */ + spinlock_t lock; + unsigned long flags; +#define FSCACHE_VOLUME_RELINQUISHED 0 /* Volume is being cleaned up */ +#define FSCACHE_VOLUME_INVALIDATE 1 /* Volume was invalidated */ +#define FSCACHE_VOLUME_COLLIDED_WITH 2 /* Volume was collided with */ +#define FSCACHE_VOLUME_ACQUIRE_PENDING 3 /* Volume is waiting to complete acquisition */ +#define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ +}; + +/* + * 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 + */ +extern struct fscache_volume *__fscache_acquire_volume(const char *, const char *, + const void *, size_t); +extern void __fscache_relinquish_volume(struct fscache_volume *, const void *, bool); + +/** + * fscache_acquire_volume - Register a volume as desiring caching services + * @volume_key: An identification string for the volume + * @cache_name: The name of the cache to use (or NULL for the default) + * @coherency_data: Piece of arbitrary coherency data to check (or NULL) + * @coherency_len: The size of the coherency data + * + * Register a volume as desiring caching services if they're available. The + * caller must provide an identifier for the volume and may also indicate which + * cache it should be in. If a preexisting volume entry is found in the cache, + * the coherency data must match otherwise the entry will be invalidated. + * + * Returns a cookie pointer on success, -ENOMEM if out of memory or -EBUSY if a + * cache volume of that name is already acquired. Note that "NULL" is a valid + * cookie pointer and can be returned if caching is refused. + */ +static inline +struct fscache_volume *fscache_acquire_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + if (!fscache_available()) + return NULL; + return __fscache_acquire_volume(volume_key, cache_name, + coherency_data, coherency_len); +} + +/** + * fscache_relinquish_volume - Cease caching a volume + * @volume: The volume cookie + * @coherency_data: Piece of arbitrary coherency data to set (or NULL) + * @invalidate: True if the volume should be invalidated + * + * Indicate that a filesystem no longer desires caching services for a volume. + * The caller must have relinquished all file cookies prior to calling this. + * The stored coherency data is updated. + */ +static inline +void fscache_relinquish_volume(struct fscache_volume *volume, + const void *coherency_data, + bool invalidate) +{ + if (fscache_volume_valid(volume)) + __fscache_relinquish_volume(volume, coherency_data, invalidate); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 3b8e0597b2c1..eeb3e7d88e20 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -23,9 +23,26 @@ enum fscache_cache_trace { fscache_cache_collision, fscache_cache_get_acquire, fscache_cache_new_acquire, + fscache_cache_put_alloc_volume, fscache_cache_put_cache, fscache_cache_put_prep_failed, fscache_cache_put_relinquish, + fscache_cache_put_volume, +}; + +enum fscache_volume_trace { + fscache_volume_collision, + fscache_volume_get_cookie, + fscache_volume_get_create_work, + fscache_volume_get_hash_collision, + fscache_volume_free, + fscache_volume_new_acquire, + fscache_volume_put_cookie, + fscache_volume_put_create_work, + fscache_volume_put_hash_collision, + fscache_volume_put_relinquish, + fscache_volume_see_create_work, + fscache_volume_see_hash_wake, }; #endif @@ -37,9 +54,25 @@ enum fscache_cache_trace { EM(fscache_cache_collision, "*COLLIDE*") \ EM(fscache_cache_get_acquire, "GET acq ") \ EM(fscache_cache_new_acquire, "NEW acq ") \ + EM(fscache_cache_put_alloc_volume, "PUT alvol") \ EM(fscache_cache_put_cache, "PUT cache") \ EM(fscache_cache_put_prep_failed, "PUT pfail") \ - E_(fscache_cache_put_relinquish, "PUT relnq") + EM(fscache_cache_put_relinquish, "PUT relnq") \ + E_(fscache_cache_put_volume, "PUT vol ") + +#define fscache_volume_traces \ + EM(fscache_volume_collision, "*COLLIDE*") \ + EM(fscache_volume_get_cookie, "GET cook ") \ + EM(fscache_volume_get_create_work, "GET creat") \ + EM(fscache_volume_get_hash_collision, "GET hcoll") \ + EM(fscache_volume_free, "FREE ") \ + EM(fscache_volume_new_acquire, "NEW acq ") \ + EM(fscache_volume_put_cookie, "PUT cook ") \ + EM(fscache_volume_put_create_work, "PUT creat") \ + EM(fscache_volume_put_hash_collision, "PUT hcoll") \ + EM(fscache_volume_put_relinquish, "PUT relnq") \ + EM(fscache_volume_see_create_work, "SEE creat") \ + E_(fscache_volume_see_hash_wake, "SEE hwake") /* * Export enum symbols via userspace. @@ -50,6 +83,7 @@ enum fscache_cache_trace { #define E_(a, b) TRACE_DEFINE_ENUM(a); fscache_cache_traces; +fscache_volume_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -86,6 +120,31 @@ TRACE_EVENT(fscache_cache, __entry->usage) ); +TRACE_EVENT(fscache_volume, + TP_PROTO(unsigned int volume_debug_id, + int usage, + enum fscache_volume_trace where), + + TP_ARGS(volume_debug_id, usage, where), + + TP_STRUCT__entry( + __field(unsigned int, volume ) + __field(int, usage ) + __field(enum fscache_volume_trace, where ) + ), + + TP_fast_assign( + __entry->volume = volume_debug_id; + __entry->usage = usage; + __entry->where = where; + ), + + TP_printk("V=%08x %s u=%d", + __entry->volume, + __print_symbolic(__entry->where, fscache_volume_traces), + __entry->usage) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7f3283aba39a0f395700c3b5defa4ec49d9914b3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie registration Add functions to the fscache API to allow data file cookies to be acquired and relinquished by the network filesystem. It is intended that the filesystem will create such cookies per-inode under a volume. To request a cookie, the filesystem should call: struct fscache_cookie * fscache_acquire_cookie(struct fscache_volume *volume, u8 advice, const void *index_key, size_t index_key_len, const void *aux_data, size_t aux_data_len, loff_t object_size) The filesystem must first have created a volume cookie, which is passed in here. If it passes in NULL then the function will just return a NULL cookie. A binary key should be passed in index_key and is of size index_key_len. This is saved in the cookie and is used to locate the associated data in the cache. A coherency data buffer of size aux_data_len will be allocated and initialised from the buffer pointed to by aux_data. This is used to validate cache objects when they're opened and is stored on disk with them when they're committed. The data is stored in the cookie and will be updateable by various functions in later patches. The object_size must also be given. This is also used to perform a coherency check and to size the backing storage appropriately. This function disallows a cookie from being acquired twice in parallel, though it will cause the second user to wait if the first is busy relinquishing its cookie. When a network filesystem has finished with a cookie, it should call: void fscache_relinquish_cookie(struct fscache_volume *volume, bool retire) If retire is true, any backing data will be discarded immediately. Changes ======= ver #3: - fscache_hash()'s size parameter is now in bytes. Use __le32 as the unit to round up to. - When comparing cookies, simply see if the attributes are the same rather than subtracting them to produce a strcmp-style return[1]. - Add a check to see if the cookie is still hashed at the point of freeing. ver #2: - Don't hold n_accesses elevated whilst cache is bound to a cookie, but rather add a flag that prevents the state machine from being queued when n_accesses reaches 0. - Remove the unused cookie pointer field from the fscache_acquire tracepoint. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/CAHk-=whtkzB446+hX0zdLsdcUJsJ=8_-0S1mE_R+YurThfUbLA@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/163819590658.215744.14934902514281054323.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906891983.143852.6219772337558577395.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967088507.1823006.12659006350221417165.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021498432.640689.12743483856927722772.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 1 + fs/fscache/cookie.c | 497 +++++++++++++++++++++++++++++++++++++++++ fs/fscache/internal.h | 23 ++ fs/fscache/main.c | 12 + fs/fscache/proc.c | 4 + fs/fscache/stats.c | 28 ++- include/linux/fscache-cache.h | 22 ++ include/linux/fscache.h | 134 +++++++++++ include/trace/events/fscache.h | 111 +++++++++ 9 files changed, 831 insertions(+), 1 deletion(-) create mode 100644 fs/fscache/cookie.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index bb5282ae682f..bcc79615f93a 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -5,6 +5,7 @@ fscache-y := \ cache.o \ + cookie.o \ main.o \ volume.o diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c new file mode 100644 index 000000000000..438b0098aa73 --- /dev/null +++ b/fs/fscache/cookie.c @@ -0,0 +1,497 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* netfs cookie management + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * See Documentation/filesystems/caching/netfs-api.rst for more information on + * the netfs API. + */ + +#define FSCACHE_DEBUG_LEVEL COOKIE +#include +#include +#include "internal.h" + +struct kmem_cache *fscache_cookie_jar; + +static void fscache_drop_cookie(struct fscache_cookie *cookie); + +#define fscache_cookie_hash_shift 15 +static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; +static LIST_HEAD(fscache_cookies); +static DEFINE_RWLOCK(fscache_cookies_lock); +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFWRD"; + +void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) +{ + const u8 *k; + + pr_err("%c-cookie c=%08x [fl=%lx na=%u nA=%u s=%c]\n", + prefix, + cookie->debug_id, + cookie->flags, + atomic_read(&cookie->n_active), + atomic_read(&cookie->n_accesses), + fscache_cookie_states[cookie->state]); + pr_err("%c-cookie V=%08x [%s]\n", + prefix, + cookie->volume->debug_id, + cookie->volume->key); + + k = (cookie->key_len <= sizeof(cookie->inline_key)) ? + cookie->inline_key : cookie->key; + pr_err("%c-key=[%u] '%*phN'\n", prefix, cookie->key_len, cookie->key_len, k); +} + +static void fscache_free_cookie(struct fscache_cookie *cookie) +{ + if (WARN_ON_ONCE(test_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags))) { + fscache_print_cookie(cookie, 'F'); + return; + } + + write_lock(&fscache_cookies_lock); + list_del(&cookie->proc_link); + write_unlock(&fscache_cookies_lock); + if (cookie->aux_len > sizeof(cookie->inline_aux)) + kfree(cookie->aux); + if (cookie->key_len > sizeof(cookie->inline_key)) + kfree(cookie->key); + fscache_stat_d(&fscache_n_cookies); + kmem_cache_free(fscache_cookie_jar, cookie); +} + +static inline void wake_up_cookie_state(struct fscache_cookie *cookie) +{ + /* Use a barrier to ensure that waiters see the state variable + * change, as spin_unlock doesn't guarantee a barrier. + * + * See comments over wake_up_bit() and waitqueue_active(). + */ + smp_mb(); + wake_up_var(&cookie->state); +} + +static void __fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) +{ + cookie->state = state; +} + +/* + * Change the state a cookie is at and wake up anyone waiting for that - but + * only if the cookie isn't already marked as being in a cleanup state. + */ +void fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) +{ + bool changed = false; + + spin_lock(&cookie->lock); + switch (cookie->state) { + case FSCACHE_COOKIE_STATE_RELINQUISHING: + break; + default: + __fscache_set_cookie_state(cookie, state); + changed = true; + break; + } + spin_unlock(&cookie->lock); + if (changed) + wake_up_cookie_state(cookie); +} +EXPORT_SYMBOL(fscache_set_cookie_state); + +/* + * Set the index key in a cookie. The cookie struct has space for a 16-byte + * key plus length and hash, but if that's not big enough, it's instead a + * pointer to a buffer containing 3 bytes of hash, 1 byte of length and then + * the key data. + */ +static int fscache_set_key(struct fscache_cookie *cookie, + const void *index_key, size_t index_key_len) +{ + void *buf; + size_t buf_size; + + buf_size = round_up(index_key_len, sizeof(__le32)); + + if (index_key_len > sizeof(cookie->inline_key)) { + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + cookie->key = buf; + } else { + buf = cookie->inline_key; + } + + memcpy(buf, index_key, index_key_len); + cookie->key_hash = fscache_hash(cookie->volume->key_hash, + buf, buf_size); + return 0; +} + +static bool fscache_cookie_same(const struct fscache_cookie *a, + const struct fscache_cookie *b) +{ + const void *ka, *kb; + + if (a->key_hash != b->key_hash || + a->volume != b->volume || + a->key_len != b->key_len) + return false; + + if (a->key_len <= sizeof(a->inline_key)) { + ka = &a->inline_key; + kb = &b->inline_key; + } else { + ka = a->key; + kb = b->key; + } + return memcmp(ka, kb, a->key_len) == 0; +} + +static atomic_t fscache_cookie_debug_id = ATOMIC_INIT(1); + +/* + * Allocate a cookie. + */ +static struct fscache_cookie *fscache_alloc_cookie( + struct fscache_volume *volume, + u8 advice, + const void *index_key, size_t index_key_len, + const void *aux_data, size_t aux_data_len, + loff_t object_size) +{ + struct fscache_cookie *cookie; + + /* allocate and initialise a cookie */ + cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); + if (!cookie) + return NULL; + fscache_stat(&fscache_n_cookies); + + cookie->volume = volume; + cookie->advice = advice; + cookie->key_len = index_key_len; + cookie->aux_len = aux_data_len; + cookie->object_size = object_size; + if (object_size == 0) + __set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + + if (fscache_set_key(cookie, index_key, index_key_len) < 0) + goto nomem; + + if (cookie->aux_len <= sizeof(cookie->inline_aux)) { + memcpy(cookie->inline_aux, aux_data, cookie->aux_len); + } else { + cookie->aux = kmemdup(aux_data, cookie->aux_len, GFP_KERNEL); + if (!cookie->aux) + goto nomem; + } + + refcount_set(&cookie->ref, 1); + cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); + cookie->state = FSCACHE_COOKIE_STATE_QUIESCENT; + spin_lock_init(&cookie->lock); + INIT_LIST_HEAD(&cookie->commit_link); + INIT_WORK(&cookie->work, NULL /* PLACEHOLDER */); + + write_lock(&fscache_cookies_lock); + list_add_tail(&cookie->proc_link, &fscache_cookies); + write_unlock(&fscache_cookies_lock); + fscache_see_cookie(cookie, fscache_cookie_new_acquire); + return cookie; + +nomem: + fscache_free_cookie(cookie); + return NULL; +} + +static void fscache_wait_on_collision(struct fscache_cookie *candidate, + struct fscache_cookie *wait_for) +{ + enum fscache_cookie_state *statep = &wait_for->state; + + wait_var_event_timeout(statep, READ_ONCE(*statep) == FSCACHE_COOKIE_STATE_DROPPED, + 20 * HZ); + if (READ_ONCE(*statep) != FSCACHE_COOKIE_STATE_DROPPED) { + pr_notice("Potential collision c=%08x old: c=%08x", + candidate->debug_id, wait_for->debug_id); + wait_var_event(statep, READ_ONCE(*statep) == FSCACHE_COOKIE_STATE_DROPPED); + } +} + +/* + * Attempt to insert the new cookie into the hash. If there's a collision, we + * wait for the old cookie to complete if it's being relinquished and an error + * otherwise. + */ +static bool fscache_hash_cookie(struct fscache_cookie *candidate) +{ + struct fscache_cookie *cursor, *wait_for = NULL; + struct hlist_bl_head *h; + struct hlist_bl_node *p; + unsigned int bucket; + + bucket = candidate->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1); + h = &fscache_cookie_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_cookie_same(candidate, cursor)) { + if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cursor->flags)) + goto collision; + wait_for = fscache_get_cookie(cursor, + fscache_cookie_get_hash_collision); + break; + } + } + + fscache_get_volume(candidate->volume, fscache_volume_get_cookie); + atomic_inc(&candidate->volume->n_cookies); + hlist_bl_add_head(&candidate->hash_link, h); + set_bit(FSCACHE_COOKIE_IS_HASHED, &candidate->flags); + hlist_bl_unlock(h); + + if (wait_for) { + fscache_wait_on_collision(candidate, wait_for); + fscache_put_cookie(wait_for, fscache_cookie_put_hash_collision); + } + return true; + +collision: + trace_fscache_cookie(cursor->debug_id, refcount_read(&cursor->ref), + fscache_cookie_collision); + pr_err("Duplicate cookie detected\n"); + fscache_print_cookie(cursor, 'O'); + fscache_print_cookie(candidate, 'N'); + hlist_bl_unlock(h); + return false; +} + +/* + * Request a cookie to represent a data storage object within a volume. + * + * We never let on to the netfs about errors. We may set a negative cookie + * pointer, but that's okay + */ +struct fscache_cookie *__fscache_acquire_cookie( + struct fscache_volume *volume, + u8 advice, + const void *index_key, size_t index_key_len, + const void *aux_data, size_t aux_data_len, + loff_t object_size) +{ + struct fscache_cookie *cookie; + + _enter("V=%x", volume->debug_id); + + if (!index_key || !index_key_len || index_key_len > 255 || aux_data_len > 255) + return NULL; + if (!aux_data || !aux_data_len) { + aux_data = NULL; + aux_data_len = 0; + } + + fscache_stat(&fscache_n_acquires); + + cookie = fscache_alloc_cookie(volume, advice, + index_key, index_key_len, + aux_data, aux_data_len, + object_size); + if (!cookie) { + fscache_stat(&fscache_n_acquires_oom); + return NULL; + } + + if (!fscache_hash_cookie(cookie)) { + fscache_see_cookie(cookie, fscache_cookie_discard); + fscache_free_cookie(cookie); + return NULL; + } + + trace_fscache_acquire(cookie); + fscache_stat(&fscache_n_acquires_ok); + _leave(" = c=%08x", cookie->debug_id); + return cookie; +} +EXPORT_SYMBOL(__fscache_acquire_cookie); + +/* + * Remove a cookie from the hash table. + */ +static void fscache_unhash_cookie(struct fscache_cookie *cookie) +{ + struct hlist_bl_head *h; + unsigned int bucket; + + bucket = cookie->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1); + h = &fscache_cookie_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_del(&cookie->hash_link); + clear_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags); + hlist_bl_unlock(h); +} + +/* + * Finalise a cookie after all its resources have been disposed of. + */ +static void fscache_drop_cookie(struct fscache_cookie *cookie) +{ + spin_lock(&cookie->lock); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_DROPPED); + spin_unlock(&cookie->lock); + wake_up_cookie_state(cookie); + + fscache_unhash_cookie(cookie); + fscache_stat(&fscache_n_relinquishes_dropped); +} + +/* + * Allow the netfs to release a cookie back to the cache. + * - the object will be marked as recyclable on disk if retire is true + */ +void __fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) +{ + fscache_stat(&fscache_n_relinquishes); + if (retire) + fscache_stat(&fscache_n_relinquishes_retire); + + _enter("c=%08x{%d},%d", + cookie->debug_id, atomic_read(&cookie->n_active), retire); + + if (WARN(test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Cookie c=%x already relinquished\n", cookie->debug_id)) + return; + + if (retire) + set_bit(FSCACHE_COOKIE_RETIRED, &cookie->flags); + trace_fscache_relinquish(cookie, retire); + + ASSERTCMP(atomic_read(&cookie->n_active), ==, 0); + ASSERTCMP(atomic_read(&cookie->volume->n_cookies), >, 0); + atomic_dec(&cookie->volume->n_cookies); + + set_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags); + + if (test_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags)) + ; // PLACEHOLDER: Do something here if the cookie was cached + else + fscache_drop_cookie(cookie); + fscache_put_cookie(cookie, fscache_cookie_put_relinquish); +} +EXPORT_SYMBOL(__fscache_relinquish_cookie); + +/* + * Drop a reference to a cookie. + */ +void fscache_put_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + struct fscache_volume *volume = cookie->volume; + unsigned int cookie_debug_id = cookie->debug_id; + bool zero; + int ref; + + zero = __refcount_dec_and_test(&cookie->ref, &ref); + trace_fscache_cookie(cookie_debug_id, ref - 1, where); + if (zero) { + fscache_free_cookie(cookie); + fscache_put_volume(volume, fscache_volume_put_cookie); + } +} +EXPORT_SYMBOL(fscache_put_cookie); + +/* + * Get a reference to a cookie. + */ +struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + int ref; + + __refcount_inc(&cookie->ref, &ref); + trace_fscache_cookie(cookie->debug_id, ref + 1, where); + return cookie; +} +EXPORT_SYMBOL(fscache_get_cookie); + +/* + * Generate a list of extant cookies in /proc/fs/fscache/cookies + */ +static int fscache_cookies_seq_show(struct seq_file *m, void *v) +{ + struct fscache_cookie *cookie; + unsigned int keylen = 0, auxlen = 0; + u8 *p; + + if (v == &fscache_cookies) { + seq_puts(m, + "COOKIE VOLUME REF ACT ACC S FL DEF \n" + "======== ======== === === === = == ================\n" + ); + return 0; + } + + cookie = list_entry(v, struct fscache_cookie, proc_link); + + seq_printf(m, + "%08x %08x %3d %3d %3d %c %02lx", + cookie->debug_id, + cookie->volume->debug_id, + refcount_read(&cookie->ref), + atomic_read(&cookie->n_active), + atomic_read(&cookie->n_accesses), + fscache_cookie_states[cookie->state], + cookie->flags); + + keylen = cookie->key_len; + auxlen = cookie->aux_len; + + if (keylen > 0 || auxlen > 0) { + seq_puts(m, " "); + p = keylen <= sizeof(cookie->inline_key) ? + cookie->inline_key : cookie->key; + for (; keylen > 0; keylen--) + seq_printf(m, "%02x", *p++); + if (auxlen > 0) { + seq_puts(m, ", "); + p = auxlen <= sizeof(cookie->inline_aux) ? + cookie->inline_aux : cookie->aux; + for (; auxlen > 0; auxlen--) + seq_printf(m, "%02x", *p++); + } + } + + seq_puts(m, "\n"); + return 0; +} + +static void *fscache_cookies_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(fscache_cookies_lock) +{ + read_lock(&fscache_cookies_lock); + return seq_list_start_head(&fscache_cookies, *_pos); +} + +static void *fscache_cookies_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_cookies, _pos); +} + +static void fscache_cookies_seq_stop(struct seq_file *m, void *v) + __releases(rcu) +{ + read_unlock(&fscache_cookies_lock); +} + + +const struct seq_operations fscache_cookies_seq_ops = { + .start = fscache_cookies_seq_start, + .next = fscache_cookies_seq_next, + .stop = fscache_cookies_seq_stop, + .show = fscache_cookies_seq_show, +}; diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 07dc9cbc2280..71c897757d44 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -50,6 +50,20 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, return try_cmpxchg_release(&cache->state, &old_state, new_state); } +/* + * cookie.c + */ +extern struct kmem_cache *fscache_cookie_jar; +extern const struct seq_operations fscache_cookies_seq_ops; + +extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); +static inline void fscache_see_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), + where); +} + /* * main.c */ @@ -75,6 +89,15 @@ extern void fscache_proc_cleanup(void); extern atomic_t fscache_n_volumes; extern atomic_t fscache_n_volumes_collision; extern atomic_t fscache_n_volumes_nomem; +extern atomic_t fscache_n_cookies; + +extern atomic_t fscache_n_acquires; +extern atomic_t fscache_n_acquires_ok; +extern atomic_t fscache_n_acquires_oom; + +extern atomic_t fscache_n_relinquishes; +extern atomic_t fscache_n_relinquishes_retire; +extern atomic_t fscache_n_relinquishes_dropped; static inline void fscache_stat(atomic_t *stat) { diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 687b34903d5b..ae493e9ca1c9 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -79,9 +79,20 @@ static int __init fscache_init(void) if (ret < 0) goto error_proc; + fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar", + sizeof(struct fscache_cookie), + 0, 0, NULL); + if (!fscache_cookie_jar) { + pr_notice("Failed to allocate a cookie jar\n"); + ret = -ENOMEM; + goto error_cookie_jar; + } + pr_notice("Loaded\n"); return 0; +error_cookie_jar: + fscache_proc_cleanup(); error_proc: destroy_workqueue(fscache_wq); error_wq: @@ -97,6 +108,7 @@ static void __exit fscache_exit(void) { _enter(""); + kmem_cache_destroy(fscache_cookie_jar); fscache_proc_cleanup(); destroy_workqueue(fscache_wq); pr_notice("Unloaded\n"); diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index bc6ecbdd065d..dc3b0e9c8cce 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -27,6 +27,10 @@ int __init fscache_proc_init(void) &fscache_volumes_seq_ops)) goto error; + if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL, + &fscache_cookies_seq_ops)) + goto error; + #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, fscache_stats_show)) diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index b811a4d03585..252e883ae148 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -16,6 +16,18 @@ atomic_t fscache_n_volumes; atomic_t fscache_n_volumes_collision; atomic_t fscache_n_volumes_nomem; +atomic_t fscache_n_cookies; + +atomic_t fscache_n_acquires; +atomic_t fscache_n_acquires_ok; +atomic_t fscache_n_acquires_oom; + +atomic_t fscache_n_updates; +EXPORT_SYMBOL(fscache_n_updates); + +atomic_t fscache_n_relinquishes; +atomic_t fscache_n_relinquishes_retire; +atomic_t fscache_n_relinquishes_dropped; /* * display the general statistics @@ -23,12 +35,26 @@ atomic_t fscache_n_volumes_nomem; int fscache_stats_show(struct seq_file *m, void *v) { seq_puts(m, "FS-Cache statistics\n"); - seq_printf(m, "Cookies: v=%d vcol=%u voom=%u\n", + seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n", + atomic_read(&fscache_n_cookies), atomic_read(&fscache_n_volumes), atomic_read(&fscache_n_volumes_collision), atomic_read(&fscache_n_volumes_nomem) ); + seq_printf(m, "Acquire: n=%u ok=%u oom=%u\n", + atomic_read(&fscache_n_acquires), + atomic_read(&fscache_n_acquires_ok), + atomic_read(&fscache_n_acquires_oom)); + + seq_printf(m, "Updates: n=%u\n", + atomic_read(&fscache_n_updates)); + + seq_printf(m, "Relinqs: n=%u rtr=%u drop=%u\n", + atomic_read(&fscache_n_relinquishes), + atomic_read(&fscache_n_relinquishes_retire), + atomic_read(&fscache_n_relinquishes_dropped)); + netfs_stats_show(m); return 0; } diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 18cd5c9877bb..c4355b888c91 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -17,6 +17,7 @@ #include enum fscache_cache_trace; +enum fscache_cookie_trace; enum fscache_access_trace; enum fscache_cache_state { @@ -52,4 +53,25 @@ extern struct rw_semaphore fscache_addremove_sem; extern struct fscache_cache *fscache_acquire_cache(const char *name); extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_put_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state); + +/** + * fscache_get_key - Get a pointer to the cookie key + * @cookie: The cookie to query + * + * Return a pointer to the where a cookie's key is stored. + */ +static inline void *fscache_get_key(struct fscache_cookie *cookie) +{ + if (cookie->key_len <= sizeof(cookie->inline_key)) + return cookie->inline_key; + else + return cookie->key; +} + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 131a741a6652..4450d17c11e8 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -31,6 +31,27 @@ #define fscache_cookie_enabled(cookie) (0) #endif +struct fscache_cookie; + +#define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ +#define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ +#define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ + +/* + * Data object state. + */ +enum fscache_cookie_state { + FSCACHE_COOKIE_STATE_QUIESCENT, /* The cookie is uncached */ + FSCACHE_COOKIE_STATE_LOOKING_UP, /* The cache object is being looked up */ + FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ + FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ + FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ + FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ + FSCACHE_COOKIE_STATE_RELINQUISHING, /* The cookie is being relinquished */ + FSCACHE_COOKIE_STATE_DROPPED, /* The cookie has been dropped */ +#define FSCACHE_COOKIE_STATE__NR (FSCACHE_COOKIE_STATE_DROPPED + 1) +} __attribute__((mode(byte))); + /* * Volume representation cookie. */ @@ -55,6 +76,60 @@ struct fscache_volume { #define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ }; +/* + * Data file representation 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 { + refcount_t ref; + atomic_t n_active; /* number of active users of cookie */ + atomic_t n_accesses; /* Number of cache accesses in progress */ + unsigned int debug_id; + unsigned int inval_counter; /* Number of invalidations made */ + spinlock_t lock; + struct fscache_volume *volume; /* Parent volume of this file. */ + void *cache_priv; /* Cache-side representation */ + struct hlist_bl_node hash_link; /* Link in hash table */ + struct list_head proc_link; /* Link in proc list */ + struct list_head commit_link; /* Link in commit queue */ + struct work_struct work; /* Commit/relinq/withdraw work */ + loff_t object_size; /* Size of the netfs object */ + unsigned long unused_at; /* Time at which unused (jiffies) */ + unsigned long flags; +#define FSCACHE_COOKIE_RELINQUISHED 0 /* T if cookie has been relinquished */ +#define FSCACHE_COOKIE_RETIRED 1 /* T if this cookie has retired on relinq */ +#define FSCACHE_COOKIE_IS_CACHING 2 /* T if this cookie is cached */ +#define FSCACHE_COOKIE_NO_DATA_TO_READ 3 /* T if this cookie has nothing to read */ +#define FSCACHE_COOKIE_NEEDS_UPDATE 4 /* T if attrs have been updated */ +#define FSCACHE_COOKIE_HAS_BEEN_CACHED 5 /* T if cookie needs withdraw-on-relinq */ +#define FSCACHE_COOKIE_DISABLED 6 /* T if cookie has been disabled */ +#define FSCACHE_COOKIE_LOCAL_WRITE 7 /* T if cookie has been modified locally */ +#define FSCACHE_COOKIE_NO_ACCESS_WAKE 8 /* T if no wake when n_accesses goes 0 */ +#define FSCACHE_COOKIE_DO_RELINQUISH 9 /* T if this cookie needs relinquishment */ +#define FSCACHE_COOKIE_DO_WITHDRAW 10 /* T if this cookie needs withdrawing */ +#define FSCACHE_COOKIE_DO_LRU_DISCARD 11 /* T if this cookie needs LRU discard */ +#define FSCACHE_COOKIE_DO_PREP_TO_WRITE 12 /* T if cookie needs write preparation */ +#define FSCACHE_COOKIE_HAVE_DATA 13 /* T if this cookie has data stored */ +#define FSCACHE_COOKIE_IS_HASHED 14 /* T if this cookie is hashed */ + + enum fscache_cookie_state state; + u8 advice; /* FSCACHE_ADV_* */ + u8 key_len; /* Length of index key */ + u8 aux_len; /* Length of auxiliary data */ + u32 key_hash; /* Hash of volume, key, len */ + union { + void *key; /* Index key */ + u8 inline_key[16]; /* - If the key is short enough */ + }; + union { + void *aux; /* Auxiliary data */ + u8 inline_aux[8]; /* - If the aux data is short enough */ + }; +}; + /* * slow-path functions for when there is actually caching available, and the * netfs does actually have a valid token @@ -66,6 +141,14 @@ extern struct fscache_volume *__fscache_acquire_volume(const char *, const char const void *, size_t); extern void __fscache_relinquish_volume(struct fscache_volume *, const void *, bool); +extern struct fscache_cookie *__fscache_acquire_cookie( + struct fscache_volume *, + u8, + const void *, size_t, + const void *, size_t, + loff_t); +extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); + /** * fscache_acquire_volume - Register a volume as desiring caching services * @volume_key: An identification string for the volume @@ -113,4 +196,55 @@ void fscache_relinquish_volume(struct fscache_volume *volume, __fscache_relinquish_volume(volume, coherency_data, invalidate); } +/** + * fscache_acquire_cookie - Acquire a cookie to represent a cache object + * @volume: The volume in which to locate/create this cookie + * @advice: Advice flags (FSCACHE_COOKIE_ADV_*) + * @index_key: The index key for this cookie + * @index_key_len: Size of the index key + * @aux_data: The auxiliary data for the cookie (may be NULL) + * @aux_data_len: Size of the auxiliary data buffer + * @object_size: The initial size of object + * + * Acquire a cookie to represent a data file within the given cache volume. + * + * See Documentation/filesystems/caching/netfs-api.rst for a complete + * description. + */ +static inline +struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume, + u8 advice, + const void *index_key, + size_t index_key_len, + const void *aux_data, + size_t aux_data_len, + loff_t object_size) +{ + if (!fscache_volume_valid(volume)) + return NULL; + return __fscache_acquire_cookie(volume, advice, + index_key, index_key_len, + aux_data, aux_data_len, + object_size); +} + +/** + * 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.rst for a complete + * description. + */ +static inline +void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) +{ + if (fscache_cookie_valid(cookie)) + __fscache_relinquish_cookie(cookie, retire); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index eeb3e7d88e20..9286e1c4b2ac 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -45,6 +45,23 @@ enum fscache_volume_trace { fscache_volume_see_hash_wake, }; +enum fscache_cookie_trace { + fscache_cookie_collision, + fscache_cookie_discard, + fscache_cookie_get_end_access, + fscache_cookie_get_hash_collision, + fscache_cookie_new_acquire, + fscache_cookie_put_hash_collision, + fscache_cookie_put_over_queued, + fscache_cookie_put_relinquish, + fscache_cookie_put_withdrawn, + fscache_cookie_put_work, + fscache_cookie_see_active, + fscache_cookie_see_relinquish, + fscache_cookie_see_withdraw, + fscache_cookie_see_work, +}; + #endif /* @@ -74,6 +91,22 @@ enum fscache_volume_trace { EM(fscache_volume_see_create_work, "SEE creat") \ E_(fscache_volume_see_hash_wake, "SEE hwake") +#define fscache_cookie_traces \ + EM(fscache_cookie_collision, "*COLLIDE*") \ + EM(fscache_cookie_discard, "DISCARD ") \ + EM(fscache_cookie_get_hash_collision, "GET hcoll") \ + EM(fscache_cookie_get_end_access, "GQ endac") \ + EM(fscache_cookie_new_acquire, "NEW acq ") \ + EM(fscache_cookie_put_hash_collision, "PUT hcoll") \ + EM(fscache_cookie_put_over_queued, "PQ overq") \ + EM(fscache_cookie_put_relinquish, "PUT relnq") \ + EM(fscache_cookie_put_withdrawn, "PUT wthdn") \ + EM(fscache_cookie_put_work, "PQ work ") \ + EM(fscache_cookie_see_active, "- activ") \ + EM(fscache_cookie_see_relinquish, "- x-rlq") \ + EM(fscache_cookie_see_withdraw, "- x-wth") \ + E_(fscache_cookie_see_work, "- work ") + /* * Export enum symbols via userspace. */ @@ -84,6 +117,7 @@ enum fscache_volume_trace { fscache_cache_traces; fscache_volume_traces; +fscache_cookie_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -145,6 +179,83 @@ TRACE_EVENT(fscache_volume, __entry->usage) ); +TRACE_EVENT(fscache_cookie, + TP_PROTO(unsigned int cookie_debug_id, + int ref, + enum fscache_cookie_trace where), + + TP_ARGS(cookie_debug_id, ref, where), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(int, ref ) + __field(enum fscache_cookie_trace, where ) + ), + + TP_fast_assign( + __entry->cookie = cookie_debug_id; + __entry->ref = ref; + __entry->where = where; + ), + + TP_printk("c=%08x %s r=%d", + __entry->cookie, + __print_symbolic(__entry->where, fscache_cookie_traces), + __entry->ref) + ); + +TRACE_EVENT(fscache_acquire, + TP_PROTO(struct fscache_cookie *cookie), + + TP_ARGS(cookie), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(unsigned int, volume ) + __field(int, v_ref ) + __field(int, v_n_cookies ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->volume = cookie->volume->debug_id; + __entry->v_ref = refcount_read(&cookie->volume->ref); + __entry->v_n_cookies = atomic_read(&cookie->volume->n_cookies); + ), + + TP_printk("c=%08x V=%08x vr=%d vc=%d", + __entry->cookie, + __entry->volume, __entry->v_ref, __entry->v_n_cookies) + ); + +TRACE_EVENT(fscache_relinquish, + TP_PROTO(struct fscache_cookie *cookie, bool retire), + + TP_ARGS(cookie, retire), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(unsigned int, volume ) + __field(int, ref ) + __field(int, n_active ) + __field(u8, flags ) + __field(bool, retire ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->volume = cookie->volume->debug_id; + __entry->ref = refcount_read(&cookie->ref); + __entry->n_active = atomic_read(&cookie->n_active); + __entry->flags = cookie->flags; + __entry->retire = retire; + ), + + TP_printk("c=%08x V=%08x r=%d U=%d f=%02x rt=%u", + __entry->cookie, __entry->volume, __entry->ref, + __entry->n_active, __entry->flags, __entry->retire) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From e6acd3299badbfb5fb0231d42481d4f5dedf5599 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:26:17 +0100 Subject: fscache: Implement volume-level access helpers Add a pair of helper functions to manage access to a volume, pinning the volume in place for the duration to prevent cache withdrawal from removing it: bool fscache_begin_volume_access(struct fscache_volume *volume, enum fscache_access_trace why); void fscache_end_volume_access(struct fscache_volume *volume, enum fscache_access_trace why); The way the access gate on the volume works/will work is: (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), then we return false to indicate access was not permitted. (2) If the cache tests as live, then we increment the volume's n_accesses count and then recheck the cache liveness, ending the access if it ceased to be live. (3) When we end the access, we decrement the volume's n_accesses and wake up the any waiters if it reaches 0. (4) Whilst the cache is caching, the volume's n_accesses is kept artificially incremented to prevent wakeups from happening. (5) When the cache is taken offline, the state is changed to prevent new accesses, the volume's n_accesses is decremented and we wait for it to become 0. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819594158.215744.8285859817391683254.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906894315.143852.5454793807544710479.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967095028.1823006.9173132503876627466.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021501546.640689.9631510472149608443.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/internal.h | 3 ++ fs/fscache/main.c | 1 + fs/fscache/volume.c | 84 ++++++++++++++++++++++++++++++++++++++++++ include/linux/fscache-cache.h | 4 ++ include/trace/events/fscache.h | 34 +++++++++++++++++ 5 files changed, 126 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index be29816b37ef..91a4ea08ec0b 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -130,6 +130,9 @@ struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where); void fscache_put_volume(struct fscache_volume *volume, enum fscache_volume_trace where); +bool fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); void fscache_create_volume(struct fscache_volume *volume, bool wait); diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 876f4bee5840..6cab5d99ba4c 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -22,6 +22,7 @@ MODULE_PARM_DESC(fscache_debug, "FS-Cache debugging mask"); EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache); +EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume); struct workqueue_struct *fscache_wq; EXPORT_SYMBOL(fscache_wq); diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index 630894fefd02..20497f0f10bb 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -33,6 +33,90 @@ static void fscache_see_volume(struct fscache_volume *volume, trace_fscache_volume(volume->debug_id, ref, where); } +/* + * Pin the cache behind a volume so that we can access it. + */ +static void __fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + n_accesses = atomic_inc_return(&volume->n_accesses); + smp_mb__after_atomic(); + trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, + refcount_read(&volume->ref), + n_accesses, why); +} + +/** + * fscache_begin_volume_access - Pin a cache so a volume can be accessed + * @volume: The volume cookie + * @cookie: A datafile cookie for a tracing reference (or NULL) + * @why: An indication of the circumstances of the access for tracing + * + * Attempt to pin the cache to prevent it from going away whilst we're + * accessing a volume and returns true if successful. This works as follows: + * + * (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), + * then we return false to indicate access was not permitted. + * + * (2) If the cache tests as live, then we increment the volume's n_accesses + * count and then recheck the cache liveness, ending the access if it + * ceased to be live. + * + * (3) When we end the access, we decrement the volume's n_accesses and wake + * up the any waiters if it reaches 0. + * + * (4) Whilst the cache is caching, the volume's n_accesses is kept + * artificially incremented to prevent wakeups from happening. + * + * (5) When the cache is taken offline, the state is changed to prevent new + * accesses, the volume's n_accesses is decremented and we wait for it to + * become 0. + * + * The datafile @cookie and the @why indicator are merely provided for tracing + * purposes. + */ +bool fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + if (!fscache_cache_is_live(volume->cache)) + return false; + __fscache_begin_volume_access(volume, cookie, why); + if (!fscache_cache_is_live(volume->cache)) { + fscache_end_volume_access(volume, cookie, fscache_access_unlive); + return false; + } + return true; +} + +/** + * fscache_end_volume_access - Unpin a cache at the end of an access. + * @volume: The volume cookie + * @cookie: A datafile cookie for a tracing reference (or NULL) + * @why: An indication of the circumstances of the access for tracing + * + * Unpin a cache volume after we've accessed it. The datafile @cookie and the + * @why indicator are merely provided for tracing purposes. + */ +void fscache_end_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + smp_mb__before_atomic(); + n_accesses = atomic_dec_return(&volume->n_accesses); + trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, + refcount_read(&volume->ref), + n_accesses, why); + if (n_accesses == 0) + wake_up_var(&volume->n_accesses); +} +EXPORT_SYMBOL(fscache_end_volume_access); + static bool fscache_volume_same(const struct fscache_volume *a, const struct fscache_volume *b) { diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index c4355b888c91..fbbd8a2afe12 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -53,6 +53,10 @@ extern struct rw_semaphore fscache_addremove_sem; extern struct fscache_cache *fscache_acquire_cache(const char *name); extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern void fscache_end_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); + extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); extern void fscache_put_cookie(struct fscache_cookie *cookie, diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 734966bc49e1..4f40cfa52469 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -43,6 +43,7 @@ enum fscache_volume_trace { fscache_volume_put_relinquish, fscache_volume_see_create_work, fscache_volume_see_hash_wake, + fscache_volume_wait_create_work, }; enum fscache_cookie_trace { @@ -245,6 +246,39 @@ TRACE_EVENT(fscache_access_cache, __entry->n_accesses) ); +TRACE_EVENT(fscache_access_volume, + TP_PROTO(unsigned int volume_debug_id, + unsigned int cookie_debug_id, + int ref, + int n_accesses, + enum fscache_access_trace why), + + TP_ARGS(volume_debug_id, cookie_debug_id, ref, n_accesses, why), + + TP_STRUCT__entry( + __field(unsigned int, volume ) + __field(unsigned int, cookie ) + __field(int, ref ) + __field(int, n_accesses ) + __field(enum fscache_access_trace, why ) + ), + + TP_fast_assign( + __entry->volume = volume_debug_id; + __entry->cookie = cookie_debug_id; + __entry->ref = ref; + __entry->n_accesses = n_accesses; + __entry->why = why; + ), + + TP_printk("V=%08x c=%08x %s r=%d a=%d", + __entry->volume, + __entry->cookie, + __print_symbolic(__entry->why, fscache_access_traces), + __entry->ref, + __entry->n_accesses) + ); + TRACE_EVENT(fscache_acquire, TP_PROTO(struct fscache_cookie *cookie), -- cgit v1.2.3 From a7733fb632722a2f085f9324f14783effe268ed3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie-level access helpers Add a number of helper functions to manage access to a cookie, pinning the cache object in place for the duration to prevent cache withdrawal from removing it: (1) void fscache_init_access_gate(struct fscache_cookie *cookie); This function initialises the access count when a cache binds to a cookie. An extra ref is taken on the access count to prevent wakeups while the cache is active. We're only interested in the wakeup when a cookie is being withdrawn and we're waiting for it to quiesce - at which point the counter will be decremented before the wait. The FSCACHE_COOKIE_NACC_ELEVATED flag is set on the cookie to keep track of the extra ref in order to handle a race between relinquishment and withdrawal both trying to drop the extra ref. (2) bool fscache_begin_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); This function attempts to begin access upon a cookie, pinning it in place if it's cached. If successful, it returns true and leaves a the access count incremented. (3) void fscache_end_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); This function drops the access count obtained by (2), permitting object withdrawal to take place when it reaches zero. A tracepoint is provided to track changes to the access counter on a cookie. Changes ======= ver #2: - Don't hold n_accesses elevated whilst cache is bound to a cookie, but rather add a flag that prevents the state machine from being queued when n_accesses reaches 0. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819595085.215744.1706073049250505427.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906895313.143852.10141619544149102193.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967095980.1823006.1133648159424418877.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021503063.640689.8870918985269528670.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 98 ++++++++++++++++++++++++++++++++++++++++++ fs/fscache/internal.h | 3 ++ fs/fscache/main.c | 1 + include/linux/fscache-cache.h | 2 + include/trace/events/fscache.h | 29 +++++++++++++ 5 files changed, 133 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 438b0098aa73..04d2127bd354 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -62,6 +62,104 @@ static void fscache_free_cookie(struct fscache_cookie *cookie) kmem_cache_free(fscache_cookie_jar, cookie); } +/* + * Initialise the access gate on a cookie by setting a flag to prevent the + * state machine from being queued when the access counter transitions to 0. + * We're only interested in this when we withdraw caching services from the + * cookie. + */ +static void fscache_init_access_gate(struct fscache_cookie *cookie) +{ + int n_accesses; + + n_accesses = atomic_read(&cookie->n_accesses); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, fscache_access_cache_pin); + set_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags); +} + +/** + * fscache_end_cookie_access - Unpin a cache at the end of an access. + * @cookie: A data file cookie + * @why: An indication of the circumstances of the access for tracing + * + * Unpin a cache cookie after we've accessed it and bring a deferred + * relinquishment or withdrawal state into effect. + * + * The @why indicator is provided for tracing purposes. + */ +void fscache_end_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + smp_mb__before_atomic(); + n_accesses = atomic_dec_return(&cookie->n_accesses); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, why); + if (n_accesses == 0 && + !test_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags)) { + // PLACEHOLDER: Need to poke the state machine + } +} +EXPORT_SYMBOL(fscache_end_cookie_access); + +/* + * Pin the cache behind a cookie so that we can access it. + */ +static void __fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + n_accesses = atomic_inc_return(&cookie->n_accesses); + smp_mb__after_atomic(); /* (Future) read state after is-caching. + * Reread n_accesses after is-caching + */ + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, why); +} + +/** + * fscache_begin_cookie_access - Pin a cache so data can be accessed + * @cookie: A data file cookie + * @why: An indication of the circumstances of the access for tracing + * + * Attempt to pin the cache to prevent it from going away whilst we're + * accessing data and returns true if successful. This works as follows: + * + * (1) If the cookie is not being cached (ie. FSCACHE_COOKIE_IS_CACHING is not + * set), we return false to indicate access was not permitted. + * + * (2) If the cookie is being cached, we increment its n_accesses count and + * then recheck the IS_CACHING flag, ending the access if it got cleared. + * + * (3) When we end the access, we decrement the cookie's n_accesses and wake + * up the any waiters if it reaches 0. + * + * (4) Whilst the cookie is actively being cached, its n_accesses is kept + * artificially incremented to prevent wakeups from happening. + * + * (5) When the cache is taken offline or if the cookie is culled, the flag is + * cleared to prevent new accesses, the cookie's n_accesses is decremented + * and we wait for it to become 0. + * + * The @why indicator are merely provided for tracing purposes. + */ +bool fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) + return false; + __fscache_begin_cookie_access(cookie, why); + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags) || + !fscache_cache_is_live(cookie->volume->cache)) { + fscache_end_cookie_access(cookie, fscache_access_unlive); + return false; + } + return true; +} + static inline void wake_up_cookie_state(struct fscache_cookie *cookie) { /* Use a barrier to ensure that waiters see the state variable diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 91a4ea08ec0b..e0d8ef212e82 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -59,6 +59,9 @@ extern struct kmem_cache *fscache_cookie_jar; extern const struct seq_operations fscache_cookies_seq_ops; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); +extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); + static inline void fscache_see_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where) { diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 6cab5d99ba4c..dad85fd84f6f 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -23,6 +23,7 @@ MODULE_PARM_DESC(fscache_debug, EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache); EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume); +EXPORT_TRACEPOINT_SYMBOL(fscache_access); struct workqueue_struct *fscache_wq; EXPORT_SYMBOL(fscache_wq); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index fbbd8a2afe12..66624407ba84 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -61,6 +61,8 @@ extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); extern void fscache_put_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); +extern void fscache_end_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); extern void fscache_set_cookie_state(struct fscache_cookie *cookie, enum fscache_cookie_state state); diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 4f40cfa52469..b1a962adfd16 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -279,6 +279,35 @@ TRACE_EVENT(fscache_access_volume, __entry->n_accesses) ); +TRACE_EVENT(fscache_access, + TP_PROTO(unsigned int cookie_debug_id, + int ref, + int n_accesses, + enum fscache_access_trace why), + + TP_ARGS(cookie_debug_id, ref, n_accesses, why), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(int, ref ) + __field(int, n_accesses ) + __field(enum fscache_access_trace, why ) + ), + + TP_fast_assign( + __entry->cookie = cookie_debug_id; + __entry->ref = ref; + __entry->n_accesses = n_accesses; + __entry->why = why; + ), + + TP_printk("c=%08x %s r=%d a=%d", + __entry->cookie, + __print_symbolic(__entry->why, fscache_access_traces), + __entry->ref, + __entry->n_accesses) + ); + TRACE_EVENT(fscache_acquire, TP_PROTO(struct fscache_cookie *cookie), -- cgit v1.2.3 From 2e0c76aee25f33c482abda6224bd87732359354d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:00:26 +0100 Subject: fscache: Implement functions add/remove a cache Implement functions to allow the cache backend to add or remove a cache: (1) Declare a cache to be live: int fscache_add_cache(struct fscache_cache *cache, const struct fscache_cache_ops *ops, void *cache_priv); Take a previously acquired cache cookie, set the operations table and private data and mark the cache open for access. (2) Withdraw a cache from service: void fscache_withdraw_cache(struct fscache_cache *cache); This marks the cache as withdrawn and thus prevents further cache-level and volume-level accesses. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819596022.215744.8799712491432238827.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906896599.143852.17049208999019262884.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967097870.1823006.3470041000971522030.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021505541.640689.1819714759326331054.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cache.c | 70 +++++++++++++++++++++++++++++++++++++++++++ include/linux/fscache-cache.h | 13 ++++++++ 2 files changed, 83 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index e867cff53a70..bbd102be91c4 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -210,12 +210,55 @@ void fscache_relinquish_cache(struct fscache_cache *cache) fscache_cache_put_prep_failed : fscache_cache_put_relinquish; + cache->ops = NULL; cache->cache_priv = NULL; smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); fscache_put_cache(cache, where); } EXPORT_SYMBOL(fscache_relinquish_cache); +/** + * fscache_add_cache - Declare a cache as being open for business + * @cache: The cache-level cookie representing the cache + * @ops: Table of cache operations to use + * @cache_priv: Private data for the cache record + * + * Add a cache to the system, making it available for netfs's to use. + * + * See Documentation/filesystems/caching/backend-api.rst for a complete + * description. + */ +int fscache_add_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + void *cache_priv) +{ + int n_accesses; + + _enter("{%s,%s}", ops->name, cache->name); + + BUG_ON(fscache_cache_state(cache) != FSCACHE_CACHE_IS_PREPARING); + + /* Get a ref on the cache cookie and keep its n_accesses counter raised + * by 1 to prevent wakeups from transitioning it to 0 until we're + * withdrawing caching services from it. + */ + n_accesses = atomic_inc_return(&cache->n_accesses); + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, fscache_access_cache_pin); + + down_write(&fscache_addremove_sem); + + cache->ops = ops; + cache->cache_priv = cache_priv; + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_ACTIVE); + + up_write(&fscache_addremove_sem); + pr_notice("Cache \"%s\" added (type %s)\n", cache->name, ops->name); + _leave(" = 0 [%s]", cache->name); + return 0; +} +EXPORT_SYMBOL(fscache_add_cache); + /** * fscache_begin_cache_access - Pin a cache so it can be accessed * @cache: The cache-level cookie @@ -278,6 +321,33 @@ void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_t wake_up_var(&cache->n_accesses); } +/** + * fscache_withdraw_cache - Withdraw a cache from the active service + * @cache: The cache cookie + * + * Begin the process of withdrawing a cache from service. This stops new + * cache-level and volume-level accesses from taking place and waits for + * currently ongoing cache-level accesses to end. + */ +void fscache_withdraw_cache(struct fscache_cache *cache) +{ + int n_accesses; + + pr_notice("Withdrawing cache \"%s\" (%u objs)\n", + cache->name, atomic_read(&cache->object_count)); + + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_WITHDRAWN); + + /* Allow wakeups on dec-to-0 */ + n_accesses = atomic_dec_return(&cache->n_accesses); + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, fscache_access_cache_unpin); + + wait_var_event(&cache->n_accesses, + atomic_read(&cache->n_accesses) == 0); +} +EXPORT_SYMBOL(fscache_withdraw_cache); + #ifdef CONFIG_PROC_FS static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW"; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 66624407ba84..f78add6e7823 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -33,6 +33,7 @@ enum fscache_cache_state { * Cache cookie. */ struct fscache_cache { + const struct fscache_cache_ops *ops; struct list_head cache_link; /* Link in cache list */ void *cache_priv; /* Private cache data (or NULL) */ refcount_t ref; @@ -44,6 +45,14 @@ struct fscache_cache { char *name; }; +/* + * cache operations + */ +struct fscache_cache_ops { + /* name of cache provider */ + const char *name; +}; + extern struct workqueue_struct *fscache_wq; /* @@ -52,6 +61,10 @@ extern struct workqueue_struct *fscache_wq; extern struct rw_semaphore fscache_addremove_sem; extern struct fscache_cache *fscache_acquire_cache(const char *name); extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern int fscache_add_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + void *cache_priv); +extern void fscache_withdraw_cache(struct fscache_cache *cache); extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, -- cgit v1.2.3 From bfa22da3ed652aa15acd4246fa13a0de6dbe4a59 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:26:17 +0100 Subject: fscache: Provide and use cache methods to lookup/create/free a volume Add cache methods to lookup, create and remove a volume. Looking up or creating the volume requires the cache pinning for access; freeing the volume requires the volume pinning for access. The ->acquire_volume() method is used to ask the cache backend to lookup and, if necessary, create a volume; the ->free_volume() method is used to free the resources for a volume. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819597821.215744.5225318658134989949.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906898645.143852.8537799955945956818.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967099771.1823006.1455197910571061835.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021507345.640689.4073511598838843040.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/volume.c | 89 ++++++++++++++++++++++++++++++++++++++++-- include/linux/fscache-cache.h | 7 ++++ include/trace/events/fscache.h | 11 +++++- 3 files changed, 103 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index 20497f0f10bb..e1a8e92a6adb 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -15,6 +15,8 @@ static struct hlist_bl_head fscache_volume_hash[1 << fscache_volume_hash_shift]; static atomic_t fscache_volume_debug_id; static LIST_HEAD(fscache_volumes); +static void fscache_create_volume_work(struct work_struct *work); + struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where) { @@ -213,7 +215,7 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, volume->cache = cache; INIT_LIST_HEAD(&volume->proc_link); - INIT_WORK(&volume->work, NULL /* PLACEHOLDER */); + INIT_WORK(&volume->work, fscache_create_volume_work); refcount_set(&volume->ref, 1); spin_lock_init(&volume->lock); @@ -249,6 +251,58 @@ err_cache: return NULL; } +/* + * Create a volume's representation on disk. Have a volume ref and a cache + * access we have to release. + */ +static void fscache_create_volume_work(struct work_struct *work) +{ + const struct fscache_cache_ops *ops; + struct fscache_volume *volume = + container_of(work, struct fscache_volume, work); + + fscache_see_volume(volume, fscache_volume_see_create_work); + + ops = volume->cache->ops; + if (ops->acquire_volume) + ops->acquire_volume(volume); + fscache_end_cache_access(volume->cache, + fscache_access_acquire_volume_end); + + clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); + wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); + fscache_put_volume(volume, fscache_volume_put_create_work); +} + +/* + * Dispatch a worker thread to create a volume's representation on disk. + */ +void fscache_create_volume(struct fscache_volume *volume, bool wait) +{ + if (test_and_set_bit(FSCACHE_VOLUME_CREATING, &volume->flags)) + goto maybe_wait; + if (volume->cache_priv) + goto no_wait; /* We raced */ + if (!fscache_begin_cache_access(volume->cache, + fscache_access_acquire_volume)) + goto no_wait; + + fscache_get_volume(volume, fscache_volume_get_create_work); + if (!schedule_work(&volume->work)) + fscache_put_volume(volume, fscache_volume_put_create_work); + +maybe_wait: + if (wait) { + fscache_see_volume(volume, fscache_volume_wait_create_work); + wait_on_bit(&volume->flags, FSCACHE_VOLUME_CREATING, + TASK_UNINTERRUPTIBLE); + } + return; +no_wait: + clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); + wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); +} + /* * Acquire a volume representation cookie and link it to a (proposed) cache. */ @@ -269,7 +323,7 @@ struct fscache_volume *__fscache_acquire_volume(const char *volume_key, return ERR_PTR(-EBUSY); } - // PLACEHOLDER: Create the volume if we have a cache available + fscache_create_volume(volume, false); return volume; } EXPORT_SYMBOL(__fscache_acquire_volume); @@ -316,7 +370,12 @@ static void fscache_free_volume(struct fscache_volume *volume) struct fscache_cache *cache = volume->cache; if (volume->cache_priv) { - // PLACEHOLDER: Detach any attached cache + __fscache_begin_volume_access(volume, NULL, + fscache_access_relinquish_volume); + if (volume->cache_priv) + cache->ops->free_volume(volume); + fscache_end_volume_access(volume, NULL, + fscache_access_relinquish_volume_end); } down_write(&fscache_addremove_sem); @@ -369,6 +428,30 @@ void __fscache_relinquish_volume(struct fscache_volume *volume, } EXPORT_SYMBOL(__fscache_relinquish_volume); +/** + * fscache_withdraw_volume - Withdraw a volume from being cached + * @volume: Volume cookie + * + * Withdraw a cache volume from service, waiting for all accesses to complete + * before returning. + */ +void fscache_withdraw_volume(struct fscache_volume *volume) +{ + int n_accesses; + + _debug("withdraw V=%x", volume->debug_id); + + /* Allow wakeups on dec-to-0 */ + n_accesses = atomic_dec_return(&volume->n_accesses); + trace_fscache_access_volume(volume->debug_id, 0, + refcount_read(&volume->ref), + n_accesses, fscache_access_cache_unpin); + + wait_var_event(&volume->n_accesses, + atomic_read(&volume->n_accesses) == 0); +} +EXPORT_SYMBOL(fscache_withdraw_volume); + #ifdef CONFIG_PROC_FS /* * Generate a list of volumes in /proc/fs/fscache/volumes diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index f78add6e7823..a10b66ca3544 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -51,6 +51,12 @@ struct fscache_cache { struct fscache_cache_ops { /* name of cache provider */ const char *name; + + /* Acquire a volume */ + void (*acquire_volume)(struct fscache_volume *volume); + + /* Free the cache's data attached to a volume */ + void (*free_volume)(struct fscache_volume *volume); }; extern struct workqueue_struct *fscache_wq; @@ -65,6 +71,7 @@ extern int fscache_add_cache(struct fscache_cache *cache, const struct fscache_cache_ops *ops, void *cache_priv); extern void fscache_withdraw_cache(struct fscache_cache *cache); +extern void fscache_withdraw_volume(struct fscache_volume *volume); extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index b1a962adfd16..1d576bd8112e 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -64,8 +64,12 @@ enum fscache_cookie_trace { }; enum fscache_access_trace { + fscache_access_acquire_volume, + fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_relinquish_volume, + fscache_access_relinquish_volume_end, fscache_access_unlive, }; @@ -96,7 +100,8 @@ enum fscache_access_trace { EM(fscache_volume_put_hash_collision, "PUT hcoll") \ EM(fscache_volume_put_relinquish, "PUT relnq") \ EM(fscache_volume_see_create_work, "SEE creat") \ - E_(fscache_volume_see_hash_wake, "SEE hwake") + EM(fscache_volume_see_hash_wake, "SEE hwake") \ + E_(fscache_volume_wait_create_work, "WAIT crea") #define fscache_cookie_traces \ EM(fscache_cookie_collision, "*COLLIDE*") \ @@ -115,8 +120,12 @@ enum fscache_access_trace { E_(fscache_cookie_see_work, "- work ") #define fscache_access_traces \ + EM(fscache_access_acquire_volume, "BEGIN acq_vol") \ + EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_relinquish_volume, "BEGIN rlq_vol") \ + EM(fscache_access_relinquish_volume_end,"END rlq_vol") \ E_(fscache_access_unlive, "END unlive ") /* -- cgit v1.2.3 From 29f18e79fe7c5f8011befeda9be6b220a350f947 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:00:26 +0100 Subject: fscache: Add a function for a cache backend to note an I/O error Add a function to the backend API to note an I/O error in a cache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819598741.215744.891281275151382095.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906901316.143852.15225412215771586528.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967100721.1823006.16435671567428949398.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021508840.640689.11902836226570620424.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cache.c | 20 ++++++++++++++++++++ include/linux/fscache-cache.h | 2 ++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index bbd102be91c4..25eac61f1c29 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -321,6 +321,26 @@ void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_t wake_up_var(&cache->n_accesses); } +/** + * fscache_io_error - Note a cache I/O error + * @cache: The record describing the cache + * + * Note that an I/O error occurred in a cache and that it should no longer be + * used for anything. This also reports the error into the kernel log. + * + * See Documentation/filesystems/caching/backend-api.rst for a complete + * description. + */ +void fscache_io_error(struct fscache_cache *cache) +{ + if (fscache_set_cache_state_maybe(cache, + FSCACHE_CACHE_IS_ACTIVE, + FSCACHE_CACHE_GOT_IOERROR)) + pr_err("Cache '%s' stopped due to I/O error\n", + cache->name); +} +EXPORT_SYMBOL(fscache_io_error); + /** * fscache_withdraw_cache - Withdraw a cache from the active service * @cache: The cache cookie diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index a10b66ca3544..936ef731bbc7 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -73,6 +73,8 @@ extern int fscache_add_cache(struct fscache_cache *cache, extern void fscache_withdraw_cache(struct fscache_cache *cache); extern void fscache_withdraw_volume(struct fscache_volume *volume); +extern void fscache_io_error(struct fscache_cache *cache); + extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, enum fscache_access_trace why); -- cgit v1.2.3 From 5d00e426f95e7ea036fec2a0aceb3f71d6dbdf92 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement simple cookie state machine Implement a very simple cookie state machine to handle lookup, invalidation, withdrawal, relinquishment and, to be added later, commit on LRU discard. Three cache methods are provided: ->lookup_cookie() to look up and, if necessary, create a data storage object; ->withdraw_cookie() to free the resources associated with that object and potentially delete it; and ->prepare_to_write(), to do prepare for changes to the cached data to be modified locally. Changes ======= ver #3: - Fix a race between LRU discard and relinquishment whereby the former would override the latter and thus the latter would never happen[1]. ver #2: - Don't hold n_accesses elevated whilst cache is bound to a cookie, but rather add a flag that prevents the state machine from being queued when n_accesses reaches 0. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/599331.1639410068@warthog.procyon.org.uk/ [1] Link: https://lore.kernel.org/r/163819599657.215744.15799615296912341745.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906903925.143852.1805855338154353867.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967105456.1823006.14730395299835841776.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021510706.640689.7961423370243272583.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 313 +++++++++++++++++++++++++++++++++++------ include/linux/fscache-cache.h | 27 +++- include/trace/events/fscache.h | 4 + 3 files changed, 300 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 04d2127bd354..336046de08ee 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -15,7 +15,8 @@ struct kmem_cache *fscache_cookie_jar; -static void fscache_drop_cookie(struct fscache_cookie *cookie); +static void fscache_cookie_worker(struct work_struct *work); +static void fscache_unhash_cookie(struct fscache_cookie *cookie); #define fscache_cookie_hash_shift 15 static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; @@ -62,6 +63,19 @@ static void fscache_free_cookie(struct fscache_cookie *cookie) kmem_cache_free(fscache_cookie_jar, cookie); } +static void __fscache_queue_cookie(struct fscache_cookie *cookie) +{ + if (!queue_work(fscache_wq, &cookie->work)) + fscache_put_cookie(cookie, fscache_cookie_put_over_queued); +} + +static void fscache_queue_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + fscache_get_cookie(cookie, where); + __fscache_queue_cookie(cookie); +} + /* * Initialise the access gate on a cookie by setting a flag to prevent the * state machine from being queued when the access counter transitions to 0. @@ -98,9 +112,8 @@ void fscache_end_cookie_access(struct fscache_cookie *cookie, trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), n_accesses, why); if (n_accesses == 0 && - !test_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags)) { - // PLACEHOLDER: Need to poke the state machine - } + !test_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags)) + fscache_queue_cookie(cookie, fscache_cookie_get_end_access); } EXPORT_SYMBOL(fscache_end_cookie_access); @@ -171,35 +184,58 @@ static inline void wake_up_cookie_state(struct fscache_cookie *cookie) wake_up_var(&cookie->state); } +/* + * Change the state a cookie is at and wake up anyone waiting for that. Impose + * an ordering between the stuff stored in the cookie and the state member. + * Paired with fscache_cookie_state(). + */ static void __fscache_set_cookie_state(struct fscache_cookie *cookie, enum fscache_cookie_state state) { - cookie->state = state; + smp_store_release(&cookie->state, state); } -/* - * Change the state a cookie is at and wake up anyone waiting for that - but - * only if the cookie isn't already marked as being in a cleanup state. - */ -void fscache_set_cookie_state(struct fscache_cookie *cookie, - enum fscache_cookie_state state) +static void fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) { - bool changed = false; - spin_lock(&cookie->lock); - switch (cookie->state) { - case FSCACHE_COOKIE_STATE_RELINQUISHING: - break; - default: - __fscache_set_cookie_state(cookie, state); - changed = true; - break; - } + __fscache_set_cookie_state(cookie, state); spin_unlock(&cookie->lock); - if (changed) - wake_up_cookie_state(cookie); + wake_up_cookie_state(cookie); +} + +/** + * fscache_cookie_lookup_negative - Note negative lookup + * @cookie: The cookie that was being looked up + * + * Note that some part of the metadata path in the cache doesn't exist and so + * we can release any waiting readers in the certain knowledge that there's + * nothing for them to actually read. + * + * This function uses no locking and must only be called from the state machine. + */ +void fscache_cookie_lookup_negative(struct fscache_cookie *cookie) +{ + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_CREATING); +} +EXPORT_SYMBOL(fscache_cookie_lookup_negative); + +/** + * fscache_caching_failed - Report that a failure stopped caching on a cookie + * @cookie: The cookie that was affected + * + * Tell fscache that caching on a cookie needs to be stopped due to some sort + * of failure. + * + * This function uses no locking and must only be called from the state machine. + */ +void fscache_caching_failed(struct fscache_cookie *cookie) +{ + clear_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_FAILED); } -EXPORT_SYMBOL(fscache_set_cookie_state); +EXPORT_SYMBOL(fscache_caching_failed); /* * Set the index key in a cookie. The cookie struct has space for a 16-byte @@ -291,10 +327,10 @@ static struct fscache_cookie *fscache_alloc_cookie( refcount_set(&cookie->ref, 1); cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); - cookie->state = FSCACHE_COOKIE_STATE_QUIESCENT; spin_lock_init(&cookie->lock); INIT_LIST_HEAD(&cookie->commit_link); - INIT_WORK(&cookie->work, NULL /* PLACEHOLDER */); + INIT_WORK(&cookie->work, fscache_cookie_worker); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); write_lock(&fscache_cookies_lock); list_add_tail(&cookie->proc_link, &fscache_cookies); @@ -417,6 +453,192 @@ struct fscache_cookie *__fscache_acquire_cookie( } EXPORT_SYMBOL(__fscache_acquire_cookie); +/* + * Prepare a cache object to be written to. + */ +static void fscache_prepare_to_write(struct fscache_cookie *cookie) +{ + cookie->volume->cache->ops->prepare_to_write(cookie); +} + +/* + * Look up a cookie in the cache. + */ +static void fscache_perform_lookup(struct fscache_cookie *cookie) +{ + enum fscache_access_trace trace = fscache_access_lookup_cookie_end_failed; + bool need_withdraw = false; + + _enter(""); + + if (!cookie->volume->cache_priv) { + fscache_create_volume(cookie->volume, true); + if (!cookie->volume->cache_priv) { + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + goto out; + } + } + + if (!cookie->volume->cache->ops->lookup_cookie(cookie)) { + if (cookie->state != FSCACHE_COOKIE_STATE_FAILED) + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + need_withdraw = true; + _leave(" [fail]"); + goto out; + } + + fscache_see_cookie(cookie, fscache_cookie_see_active); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); + trace = fscache_access_lookup_cookie_end; + +out: + fscache_end_cookie_access(cookie, trace); + if (need_withdraw) + fscache_withdraw_cookie(cookie); + fscache_end_volume_access(cookie->volume, cookie, trace); +} + +/* + * Perform work upon the cookie, such as committing its cache state, + * relinquishing it or withdrawing the backing cache. We're protected from the + * cache going away under us as object withdrawal must come through this + * non-reentrant work item. + */ +static void fscache_cookie_state_machine(struct fscache_cookie *cookie) +{ + enum fscache_cookie_state state; + bool wake = false; + + _enter("c=%x", cookie->debug_id); + +again: + spin_lock(&cookie->lock); +again_locked: + state = cookie->state; + switch (state) { + case FSCACHE_COOKIE_STATE_QUIESCENT: + /* The QUIESCENT state is jumped to the LOOKING_UP state by + * fscache_use_cookie(). + */ + + if (atomic_read(&cookie->n_accesses) == 0 && + test_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_RELINQUISHING); + wake = true; + goto again_locked; + } + break; + + case FSCACHE_COOKIE_STATE_LOOKING_UP: + spin_unlock(&cookie->lock); + fscache_init_access_gate(cookie); + fscache_perform_lookup(cookie); + goto again; + + case FSCACHE_COOKIE_STATE_ACTIVE: + if (test_and_clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags)) { + spin_unlock(&cookie->lock); + fscache_prepare_to_write(cookie); + spin_lock(&cookie->lock); + } + fallthrough; + + case FSCACHE_COOKIE_STATE_FAILED: + if (atomic_read(&cookie->n_accesses) != 0) + break; + if (test_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_RELINQUISHING); + wake = true; + goto again_locked; + } + if (test_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_WITHDRAWING); + wake = true; + goto again_locked; + } + break; + + case FSCACHE_COOKIE_STATE_RELINQUISHING: + case FSCACHE_COOKIE_STATE_WITHDRAWING: + if (cookie->cache_priv) { + spin_unlock(&cookie->lock); + cookie->volume->cache->ops->withdraw_cookie(cookie); + spin_lock(&cookie->lock); + } + + switch (state) { + case FSCACHE_COOKIE_STATE_RELINQUISHING: + fscache_see_cookie(cookie, fscache_cookie_see_relinquish); + fscache_unhash_cookie(cookie); + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_DROPPED); + wake = true; + goto out; + case FSCACHE_COOKIE_STATE_WITHDRAWING: + fscache_see_cookie(cookie, fscache_cookie_see_withdraw); + break; + default: + BUG(); + } + + clear_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + wake = true; + goto again_locked; + + case FSCACHE_COOKIE_STATE_DROPPED: + break; + + default: + WARN_ONCE(1, "Cookie %x in unexpected state %u\n", + cookie->debug_id, state); + break; + } + +out: + spin_unlock(&cookie->lock); + if (wake) + wake_up_cookie_state(cookie); + _leave(""); +} + +static void fscache_cookie_worker(struct work_struct *work) +{ + struct fscache_cookie *cookie = container_of(work, struct fscache_cookie, work); + + fscache_see_cookie(cookie, fscache_cookie_see_work); + fscache_cookie_state_machine(cookie); + fscache_put_cookie(cookie, fscache_cookie_put_work); +} + +/* + * Wait for the object to become inactive. The cookie's work item will be + * scheduled when someone transitions n_accesses to 0 - but if someone's + * already done that, schedule it anyway. + */ +static void __fscache_withdraw_cookie(struct fscache_cookie *cookie) +{ + int n_accesses; + bool unpinned; + + unpinned = test_and_clear_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags); + + /* Need to read the access count after unpinning */ + n_accesses = atomic_read(&cookie->n_accesses); + if (unpinned) + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, fscache_access_cache_unpin); + if (n_accesses == 0) + fscache_queue_cookie(cookie, fscache_cookie_get_end_access); +} + /* * Remove a cookie from the hash table. */ @@ -432,21 +654,27 @@ static void fscache_unhash_cookie(struct fscache_cookie *cookie) hlist_bl_del(&cookie->hash_link); clear_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags); hlist_bl_unlock(h); + fscache_stat(&fscache_n_relinquishes_dropped); } -/* - * Finalise a cookie after all its resources have been disposed of. - */ -static void fscache_drop_cookie(struct fscache_cookie *cookie) +static void fscache_drop_withdraw_cookie(struct fscache_cookie *cookie) { - spin_lock(&cookie->lock); - __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_DROPPED); - spin_unlock(&cookie->lock); - wake_up_cookie_state(cookie); + __fscache_withdraw_cookie(cookie); +} - fscache_unhash_cookie(cookie); - fscache_stat(&fscache_n_relinquishes_dropped); +/** + * fscache_withdraw_cookie - Mark a cookie for withdrawal + * @cookie: The cookie to be withdrawn. + * + * Allow the cache backend to withdraw the backing for a cookie for its own + * reasons, even if that cookie is in active use. + */ +void fscache_withdraw_cookie(struct fscache_cookie *cookie) +{ + set_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags); + fscache_drop_withdraw_cookie(cookie); } +EXPORT_SYMBOL(fscache_withdraw_cookie); /* * Allow the netfs to release a cookie back to the cache. @@ -473,12 +701,13 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) ASSERTCMP(atomic_read(&cookie->volume->n_cookies), >, 0); atomic_dec(&cookie->volume->n_cookies); - set_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags); - - if (test_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags)) - ; // PLACEHOLDER: Do something here if the cookie was cached - else - fscache_drop_cookie(cookie); + if (test_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags)) { + set_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags); + fscache_drop_withdraw_cookie(cookie); + } else { + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_DROPPED); + fscache_unhash_cookie(cookie); + } fscache_put_cookie(cookie, fscache_cookie_put_relinquish); } EXPORT_SYMBOL(__fscache_relinquish_cookie); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 936ef731bbc7..ae6a75976450 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -57,6 +57,15 @@ struct fscache_cache_ops { /* Free the cache's data attached to a volume */ void (*free_volume)(struct fscache_volume *volume); + + /* Look up a cookie in the cache */ + bool (*lookup_cookie)(struct fscache_cookie *cookie); + + /* Withdraw an object without any cookie access counts held */ + void (*withdraw_cookie)(struct fscache_cookie *cookie); + + /* Prepare to write to a live cache object */ + void (*prepare_to_write)(struct fscache_cookie *cookie); }; extern struct workqueue_struct *fscache_wq; @@ -72,6 +81,7 @@ extern int fscache_add_cache(struct fscache_cache *cache, void *cache_priv); extern void fscache_withdraw_cache(struct fscache_cache *cache); extern void fscache_withdraw_volume(struct fscache_volume *volume); +extern void fscache_withdraw_cookie(struct fscache_cookie *cookie); extern void fscache_io_error(struct fscache_cache *cache); @@ -85,8 +95,21 @@ extern void fscache_put_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); extern void fscache_end_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); -extern void fscache_set_cookie_state(struct fscache_cookie *cookie, - enum fscache_cookie_state state); +extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); +extern void fscache_caching_failed(struct fscache_cookie *cookie); + +/** + * fscache_cookie_state - Read the state of a cookie + * @cookie: The cookie to query + * + * Get the state of a cookie, imposing an ordering between the cookie contents + * and the state value. Paired with fscache_set_cookie_state(). + */ +static inline +enum fscache_cookie_state fscache_cookie_state(struct fscache_cookie *cookie) +{ + return smp_load_acquire(&cookie->state); +} /** * fscache_get_key - Get a pointer to the cookie key diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 1d576bd8112e..030c97bb9c8b 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -68,6 +68,8 @@ enum fscache_access_trace { fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_lookup_cookie_end, + fscache_access_lookup_cookie_end_failed, fscache_access_relinquish_volume, fscache_access_relinquish_volume_end, fscache_access_unlive, @@ -124,6 +126,8 @@ enum fscache_access_trace { EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_lookup_cookie_end, "END lookup ") \ + EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ EM(fscache_access_relinquish_volume, "BEGIN rlq_vol") \ EM(fscache_access_relinquish_volume_end,"END rlq_vol") \ E_(fscache_access_unlive, "END unlive ") -- cgit v1.2.3 From 12bb21a29c19aae50cfad4e2bb5c943108f34a7d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie user counting and resource pinning Provide a pair of functions to count the number of users of a cookie (open files, writeback, invalidation, resizing, reads, writes), to obtain and pin resources for the cookie and to prevent culling for the whilst there are users. The first function marks a cookie as being in use: void fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify); The caller should indicate the cookie to use and whether or not the caller is in a context that may modify the cookie (e.g. a file open O_RDWR). If the cookie is not already resourced, fscache will ask the cache backend in the background to do whatever it needs to look up, create or otherwise obtain the resources necessary to access data. This is pinned to the cookie and may not be culled, though it may be withdrawn if the cache as a whole is withdrawn. The second function removes the in-use mark from a cookie and, optionally, updates the coherency data: void fscache_unuse_cookie(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size); If non-NULL, the aux_data buffer and/or the object_size will be saved into the cookie and will be set on the backing store when the object is committed. If this removes the last usage on a cookie, the cookie is placed onto an LRU list from which it will be removed and closed after a couple of seconds if it doesn't get reused. This prevents resource overload in the cache - in particular it prevents it from holding too many files open. Changes ======= ver #2: - Fix fscache_unuse_cookie() to use atomic_dec_and_lock() to avoid a potential race if the cookie gets reused before it completes the unusement. - Added missing transition to LRU_DISCARDING state. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819600612.215744.13678350304176542741.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906907567.143852.16979631199380722019.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967106467.1823006.6790864931048582667.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021511674.640689.10084988363699111860.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 218 ++++++++++++++++++++++++++++++++++++++++- fs/fscache/internal.h | 5 + fs/fscache/stats.c | 12 +++ include/linux/fscache.h | 82 +++++++++++++++- include/trace/events/fscache.h | 12 +++ 5 files changed, 327 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 336046de08ee..2f5ee717f2bb 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -15,6 +15,8 @@ struct kmem_cache *fscache_cookie_jar; +static void fscache_cookie_lru_timed_out(struct timer_list *timer); +static void fscache_cookie_lru_worker(struct work_struct *work); static void fscache_cookie_worker(struct work_struct *work); static void fscache_unhash_cookie(struct fscache_cookie *cookie); @@ -22,7 +24,12 @@ static void fscache_unhash_cookie(struct fscache_cookie *cookie); static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; static LIST_HEAD(fscache_cookies); static DEFINE_RWLOCK(fscache_cookies_lock); -static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFWRD"; +static LIST_HEAD(fscache_cookie_lru); +static DEFINE_SPINLOCK(fscache_cookie_lru_lock); +DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); +static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFUWRD"; +unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { @@ -47,6 +54,14 @@ void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) static void fscache_free_cookie(struct fscache_cookie *cookie) { + if (WARN_ON_ONCE(!list_empty(&cookie->commit_link))) { + spin_lock(&fscache_cookie_lru_lock); + list_del_init(&cookie->commit_link); + spin_unlock(&fscache_cookie_lru_lock); + fscache_stat_d(&fscache_n_cookies_lru); + fscache_stat(&fscache_n_cookies_lru_removed); + } + if (WARN_ON_ONCE(test_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags))) { fscache_print_cookie(cookie, 'F'); return; @@ -498,6 +513,126 @@ out: fscache_end_volume_access(cookie->volume, cookie, trace); } +/* + * Begin the process of looking up a cookie. We offload the actual process to + * a worker thread. + */ +static bool fscache_begin_lookup(struct fscache_cookie *cookie, bool will_modify) +{ + if (will_modify) { + set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); + set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + } + if (!fscache_begin_volume_access(cookie->volume, cookie, + fscache_access_lookup_cookie)) + return false; + + __fscache_begin_cookie_access(cookie, fscache_access_lookup_cookie); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_LOOKING_UP); + set_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); + set_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags); + return true; +} + +/* + * Start using the cookie for I/O. This prevents the backing object from being + * reaped by VM pressure. + */ +void __fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify) +{ + enum fscache_cookie_state state; + bool queue = false; + + _enter("c=%08x", cookie->debug_id); + + if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Trying to use relinquished cookie\n")) + return; + + spin_lock(&cookie->lock); + + atomic_inc(&cookie->n_active); + +again: + state = fscache_cookie_state(cookie); + switch (state) { + case FSCACHE_COOKIE_STATE_QUIESCENT: + queue = fscache_begin_lookup(cookie, will_modify); + break; + + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_CREATING: + if (will_modify) + set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); + break; + case FSCACHE_COOKIE_STATE_ACTIVE: + if (will_modify && + !test_and_set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags)) { + set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + queue = true; + } + break; + + case FSCACHE_COOKIE_STATE_FAILED: + case FSCACHE_COOKIE_STATE_WITHDRAWING: + break; + + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + spin_unlock(&cookie->lock); + wait_var_event(&cookie->state, + fscache_cookie_state(cookie) != + FSCACHE_COOKIE_STATE_LRU_DISCARDING); + spin_lock(&cookie->lock); + goto again; + + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + WARN(1, "Can't use cookie in state %u\n", state); + break; + } + + spin_unlock(&cookie->lock); + if (queue) + fscache_queue_cookie(cookie, fscache_cookie_get_use_work); + _leave(""); +} +EXPORT_SYMBOL(__fscache_use_cookie); + +static void fscache_unuse_cookie_locked(struct fscache_cookie *cookie) +{ + clear_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags); + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) + return; + + cookie->unused_at = jiffies; + spin_lock(&fscache_cookie_lru_lock); + if (list_empty(&cookie->commit_link)) { + fscache_get_cookie(cookie, fscache_cookie_get_lru); + fscache_stat(&fscache_n_cookies_lru); + } + list_move_tail(&cookie->commit_link, &fscache_cookie_lru); + + spin_unlock(&fscache_cookie_lru_lock); + timer_reduce(&fscache_cookie_lru_timer, + jiffies + fscache_lru_cookie_timeout); +} + +/* + * Stop using the cookie for I/O. + */ +void __fscache_unuse_cookie(struct fscache_cookie *cookie, + const void *aux_data, const loff_t *object_size) +{ + if (aux_data || object_size) + __fscache_update_cookie(cookie, aux_data, object_size); + + if (atomic_dec_and_lock(&cookie->n_active, &cookie->lock)) { + fscache_unuse_cookie_locked(cookie); + spin_unlock(&cookie->lock); + } +} +EXPORT_SYMBOL(__fscache_unuse_cookie); + /* * Perform work upon the cookie, such as committing its cache state, * relinquishing it or withdrawing the backing cache. We're protected from the @@ -542,6 +677,12 @@ again_locked: fscache_prepare_to_write(cookie); spin_lock(&cookie->lock); } + if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_LRU_DISCARDING); + wake = true; + goto again_locked; + } fallthrough; case FSCACHE_COOKIE_STATE_FAILED: @@ -561,6 +702,7 @@ again_locked: } break; + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: case FSCACHE_COOKIE_STATE_RELINQUISHING: case FSCACHE_COOKIE_STATE_WITHDRAWING: if (cookie->cache_priv) { @@ -577,6 +719,9 @@ again_locked: FSCACHE_COOKIE_STATE_DROPPED); wake = true; goto out; + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + fscache_see_cookie(cookie, fscache_cookie_see_lru_discard); + break; case FSCACHE_COOKIE_STATE_WITHDRAWING: fscache_see_cookie(cookie, fscache_cookie_see_withdraw); break; @@ -639,6 +784,76 @@ static void __fscache_withdraw_cookie(struct fscache_cookie *cookie) fscache_queue_cookie(cookie, fscache_cookie_get_end_access); } +static void fscache_cookie_lru_do_one(struct fscache_cookie *cookie) +{ + fscache_see_cookie(cookie, fscache_cookie_see_lru_do_one); + + spin_lock(&cookie->lock); + if (cookie->state != FSCACHE_COOKIE_STATE_ACTIVE || + time_before(jiffies, cookie->unused_at + fscache_lru_cookie_timeout) || + atomic_read(&cookie->n_active) > 0) { + spin_unlock(&cookie->lock); + fscache_stat(&fscache_n_cookies_lru_removed); + } else { + set_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags); + spin_unlock(&cookie->lock); + fscache_stat(&fscache_n_cookies_lru_expired); + _debug("lru c=%x", cookie->debug_id); + __fscache_withdraw_cookie(cookie); + } + + fscache_put_cookie(cookie, fscache_cookie_put_lru); +} + +static void fscache_cookie_lru_worker(struct work_struct *work) +{ + struct fscache_cookie *cookie; + unsigned long unused_at; + + spin_lock(&fscache_cookie_lru_lock); + + while (!list_empty(&fscache_cookie_lru)) { + cookie = list_first_entry(&fscache_cookie_lru, + struct fscache_cookie, commit_link); + unused_at = cookie->unused_at + fscache_lru_cookie_timeout; + if (time_before(jiffies, unused_at)) { + timer_reduce(&fscache_cookie_lru_timer, unused_at); + break; + } + + list_del_init(&cookie->commit_link); + fscache_stat_d(&fscache_n_cookies_lru); + spin_unlock(&fscache_cookie_lru_lock); + fscache_cookie_lru_do_one(cookie); + spin_lock(&fscache_cookie_lru_lock); + } + + spin_unlock(&fscache_cookie_lru_lock); +} + +static void fscache_cookie_lru_timed_out(struct timer_list *timer) +{ + queue_work(fscache_wq, &fscache_cookie_lru_work); +} + +static void fscache_cookie_drop_from_lru(struct fscache_cookie *cookie) +{ + bool need_put = false; + + if (!list_empty(&cookie->commit_link)) { + spin_lock(&fscache_cookie_lru_lock); + if (!list_empty(&cookie->commit_link)) { + list_del_init(&cookie->commit_link); + fscache_stat_d(&fscache_n_cookies_lru); + fscache_stat(&fscache_n_cookies_lru_dropped); + need_put = true; + } + spin_unlock(&fscache_cookie_lru_lock); + if (need_put) + fscache_put_cookie(cookie, fscache_cookie_put_lru); + } +} + /* * Remove a cookie from the hash table. */ @@ -659,6 +874,7 @@ static void fscache_unhash_cookie(struct fscache_cookie *cookie) static void fscache_drop_withdraw_cookie(struct fscache_cookie *cookie) { + fscache_cookie_drop_from_lru(cookie); __fscache_withdraw_cookie(cookie); } diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index e0d8ef212e82..ca938e00eaa0 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -57,6 +57,7 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, */ extern struct kmem_cache *fscache_cookie_jar; extern const struct seq_operations fscache_cookies_seq_ops; +extern struct timer_list fscache_cookie_lru_timer; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie, @@ -95,6 +96,10 @@ extern atomic_t fscache_n_volumes; extern atomic_t fscache_n_volumes_collision; extern atomic_t fscache_n_volumes_nomem; extern atomic_t fscache_n_cookies; +extern atomic_t fscache_n_cookies_lru; +extern atomic_t fscache_n_cookies_lru_expired; +extern atomic_t fscache_n_cookies_lru_removed; +extern atomic_t fscache_n_cookies_lru_dropped; extern atomic_t fscache_n_acquires; extern atomic_t fscache_n_acquires_ok; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 252e883ae148..5aa4bd9fe207 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -17,6 +17,10 @@ atomic_t fscache_n_volumes; atomic_t fscache_n_volumes_collision; atomic_t fscache_n_volumes_nomem; atomic_t fscache_n_cookies; +atomic_t fscache_n_cookies_lru; +atomic_t fscache_n_cookies_lru_expired; +atomic_t fscache_n_cookies_lru_removed; +atomic_t fscache_n_cookies_lru_dropped; atomic_t fscache_n_acquires; atomic_t fscache_n_acquires_ok; @@ -47,6 +51,14 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_acquires_ok), atomic_read(&fscache_n_acquires_oom)); + seq_printf(m, "LRU : n=%u exp=%u rmv=%u drp=%u at=%ld\n", + atomic_read(&fscache_n_cookies_lru), + atomic_read(&fscache_n_cookies_lru_expired), + atomic_read(&fscache_n_cookies_lru_removed), + atomic_read(&fscache_n_cookies_lru_dropped), + timer_pending(&fscache_cookie_lru_timer) ? + fscache_cookie_lru_timer.expires - jiffies : 0); + seq_printf(m, "Updates: n=%u\n", atomic_read(&fscache_n_updates)); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 4450d17c11e8..e6c321e5bf73 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -22,12 +22,14 @@ #define fscache_available() (1) #define fscache_volume_valid(volume) (volume) #define fscache_cookie_valid(cookie) (cookie) -#define fscache_cookie_enabled(cookie) (cookie) +#define fscache_resources_valid(cres) ((cres)->cache_priv) +#define fscache_cookie_enabled(cookie) (cookie && !test_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) #else #define __fscache_available (0) #define fscache_available() (0) #define fscache_volume_valid(volume) (0) #define fscache_cookie_valid(cookie) (0) +#define fscache_resources_valid(cres) (false) #define fscache_cookie_enabled(cookie) (0) #endif @@ -46,6 +48,7 @@ enum fscache_cookie_state { FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ + FSCACHE_COOKIE_STATE_LRU_DISCARDING, /* The cookie is being discarded by the LRU */ FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ FSCACHE_COOKIE_STATE_RELINQUISHING, /* The cookie is being relinquished */ FSCACHE_COOKIE_STATE_DROPPED, /* The cookie has been dropped */ @@ -147,6 +150,8 @@ extern struct fscache_cookie *__fscache_acquire_cookie( const void *, size_t, const void *, size_t, loff_t); +extern void __fscache_use_cookie(struct fscache_cookie *, bool); +extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); /** @@ -228,6 +233,39 @@ struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume, object_size); } +/** + * fscache_use_cookie - Request usage of cookie attached to an object + * @object: Object description + * @will_modify: If cache is expected to be modified locally + * + * Request usage of the cookie attached to an object. The caller should tell + * the cache if the object's contents are about to be modified locally and then + * the cache can apply the policy that has been set to handle this case. + */ +static inline void fscache_use_cookie(struct fscache_cookie *cookie, + bool will_modify) +{ + if (fscache_cookie_valid(cookie)) + __fscache_use_cookie(cookie, will_modify); +} + +/** + * fscache_unuse_cookie - Cease usage of cookie attached to an object + * @object: Object description + * @aux_data: Updated auxiliary data (or NULL) + * @object_size: Revised size of the object (or NULL) + * + * Cease usage of the cookie attached to an object. When the users count + * reaches zero then the cookie relinquishment will be permitted to proceed. + */ +static inline void fscache_unuse_cookie(struct fscache_cookie *cookie, + const void *aux_data, + const loff_t *object_size) +{ + if (fscache_cookie_valid(cookie)) + __fscache_unuse_cookie(cookie, aux_data, object_size); +} + /** * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding * it @@ -247,4 +285,46 @@ void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) __fscache_relinquish_cookie(cookie, retire); } +/* + * Find the auxiliary data on a cookie. + */ +static inline void *fscache_get_aux(struct fscache_cookie *cookie) +{ + if (cookie->aux_len <= sizeof(cookie->inline_aux)) + return cookie->inline_aux; + else + return cookie->aux; +} + +/* + * Update the auxiliary data on a cookie. + */ +static inline +void fscache_update_aux(struct fscache_cookie *cookie, + const void *aux_data, const loff_t *object_size) +{ + void *p = fscache_get_aux(cookie); + + if (aux_data && p) + memcpy(p, aux_data, cookie->aux_len); + if (object_size) + cookie->object_size = *object_size; +} + +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_updates; +#endif + +static inline +void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) +{ +#ifdef CONFIG_FSCACHE_STATS + atomic_inc(&fscache_n_updates); +#endif + fscache_update_aux(cookie, aux_data, object_size); + smp_wmb(); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 030c97bb9c8b..b0409b1fad23 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -51,13 +51,18 @@ enum fscache_cookie_trace { fscache_cookie_discard, fscache_cookie_get_end_access, fscache_cookie_get_hash_collision, + fscache_cookie_get_lru, + fscache_cookie_get_use_work, fscache_cookie_new_acquire, fscache_cookie_put_hash_collision, + fscache_cookie_put_lru, fscache_cookie_put_over_queued, fscache_cookie_put_relinquish, fscache_cookie_put_withdrawn, fscache_cookie_put_work, fscache_cookie_see_active, + fscache_cookie_see_lru_discard, + fscache_cookie_see_lru_do_one, fscache_cookie_see_relinquish, fscache_cookie_see_withdraw, fscache_cookie_see_work, @@ -68,6 +73,7 @@ enum fscache_access_trace { fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, fscache_access_relinquish_volume, @@ -110,13 +116,18 @@ enum fscache_access_trace { EM(fscache_cookie_discard, "DISCARD ") \ EM(fscache_cookie_get_hash_collision, "GET hcoll") \ EM(fscache_cookie_get_end_access, "GQ endac") \ + EM(fscache_cookie_get_lru, "GET lru ") \ + EM(fscache_cookie_get_use_work, "GQ use ") \ EM(fscache_cookie_new_acquire, "NEW acq ") \ EM(fscache_cookie_put_hash_collision, "PUT hcoll") \ + EM(fscache_cookie_put_lru, "PUT lru ") \ EM(fscache_cookie_put_over_queued, "PQ overq") \ EM(fscache_cookie_put_relinquish, "PUT relnq") \ EM(fscache_cookie_put_withdrawn, "PUT wthdn") \ EM(fscache_cookie_put_work, "PQ work ") \ EM(fscache_cookie_see_active, "- activ") \ + EM(fscache_cookie_see_lru_discard, "- x-lru") \ + EM(fscache_cookie_see_lru_do_one, "- lrudo") \ EM(fscache_cookie_see_relinquish, "- x-rlq") \ EM(fscache_cookie_see_withdraw, "- x-wth") \ E_(fscache_cookie_see_work, "- work ") @@ -126,6 +137,7 @@ enum fscache_access_trace { EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ EM(fscache_access_relinquish_volume, "BEGIN rlq_vol") \ -- cgit v1.2.3 From d24af13e2e2358a602740c7817ea90da43d3e740 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie invalidation Add a function to invalidate the cache behind a cookie: void fscache_invalidate(struct fscache_cookie *cookie, const void *aux_data, loff_t size, unsigned int flags) This causes any cached data for the specified cookie to be discarded. If the cookie is marked as being in use, a new cache object will be created if possible and future I/O will use that instead. In-flight I/O should be abandoned (writes) or reconsidered (reads). Each time it is called cookie->inval_counter is incremented and this can be used to detect invalidation at the end of an I/O operation. The coherency data attached to the cookie can be updated and the cookie size should be reset. One flag is available, FSCACHE_INVAL_DIO_WRITE, which should be used to indicate invalidation due to a DIO write on a file. This will temporarily disable caching for this cookie. Changes ======= ver #2: - Should only change to inval state if can get access to cache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819602231.215744.11206598147269491575.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906909707.143852.18056070560477964891.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967107447.1823006.5945029409592119962.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021512640.640689.11418616313147754172.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 88 +++++++++++++++++++++++++++++++++++++++++- fs/fscache/internal.h | 2 + fs/fscache/stats.c | 5 +++ include/linux/fscache-cache.h | 4 ++ include/linux/fscache.h | 31 +++++++++++++++ include/linux/netfs.h | 1 + include/trace/events/fscache.h | 25 ++++++++++++ 7 files changed, 155 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 2f5ee717f2bb..a7ea7d1db032 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -19,6 +19,7 @@ static void fscache_cookie_lru_timed_out(struct timer_list *timer); static void fscache_cookie_lru_worker(struct work_struct *work); static void fscache_cookie_worker(struct work_struct *work); static void fscache_unhash_cookie(struct fscache_cookie *cookie); +static void fscache_perform_invalidation(struct fscache_cookie *cookie); #define fscache_cookie_hash_shift 15 static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; @@ -28,7 +29,7 @@ static LIST_HEAD(fscache_cookie_lru); static DEFINE_SPINLOCK(fscache_cookie_lru_lock); DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); -static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFUWRD"; +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) @@ -236,6 +237,19 @@ void fscache_cookie_lookup_negative(struct fscache_cookie *cookie) } EXPORT_SYMBOL(fscache_cookie_lookup_negative); +/** + * fscache_resume_after_invalidation - Allow I/O to resume after invalidation + * @cookie: The cookie that was invalidated + * + * Tell fscache that invalidation is sufficiently complete that I/O can be + * allowed again. + */ +void fscache_resume_after_invalidation(struct fscache_cookie *cookie) +{ + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); +} +EXPORT_SYMBOL(fscache_resume_after_invalidation); + /** * fscache_caching_failed - Report that a failure stopped caching on a cookie * @cookie: The cookie that was affected @@ -566,6 +580,7 @@ again: set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); break; case FSCACHE_COOKIE_STATE_ACTIVE: + case FSCACHE_COOKIE_STATE_INVALIDATING: if (will_modify && !test_and_set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags)) { set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); @@ -671,6 +686,11 @@ again_locked: fscache_perform_lookup(cookie); goto again; + case FSCACHE_COOKIE_STATE_INVALIDATING: + spin_unlock(&cookie->lock); + fscache_perform_invalidation(cookie); + goto again; + case FSCACHE_COOKIE_STATE_ACTIVE: if (test_and_clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags)) { spin_unlock(&cookie->lock); @@ -962,6 +982,72 @@ struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, } EXPORT_SYMBOL(fscache_get_cookie); +/* + * Ask the cache to effect invalidation of a cookie. + */ +static void fscache_perform_invalidation(struct fscache_cookie *cookie) +{ + if (!cookie->volume->cache->ops->invalidate_cookie(cookie)) + fscache_caching_failed(cookie); + fscache_end_cookie_access(cookie, fscache_access_invalidate_cookie_end); +} + +/* + * Invalidate an object. + */ +void __fscache_invalidate(struct fscache_cookie *cookie, + const void *aux_data, loff_t new_size, + unsigned int flags) +{ + bool is_caching; + + _enter("c=%x", cookie->debug_id); + + fscache_stat(&fscache_n_invalidates); + + if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Trying to invalidate relinquished cookie\n")) + return; + + if ((flags & FSCACHE_INVAL_DIO_WRITE) && + test_and_set_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) + return; + + spin_lock(&cookie->lock); + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + fscache_update_aux(cookie, aux_data, &new_size); + cookie->inval_counter++; + trace_fscache_invalidate(cookie, new_size); + + switch (cookie->state) { + case FSCACHE_COOKIE_STATE_INVALIDATING: /* is_still_valid will catch it */ + default: + spin_unlock(&cookie->lock); + _leave(" [no %u]", cookie->state); + return; + + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_CREATING: + spin_unlock(&cookie->lock); + _leave(" [look %x]", cookie->inval_counter); + return; + + case FSCACHE_COOKIE_STATE_ACTIVE: + is_caching = fscache_begin_cookie_access( + cookie, fscache_access_invalidate_cookie); + if (is_caching) + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_INVALIDATING); + spin_unlock(&cookie->lock); + wake_up_cookie_state(cookie); + + if (is_caching) + fscache_queue_cookie(cookie, fscache_cookie_get_inval_work); + _leave(" [inv]"); + return; + } +} +EXPORT_SYMBOL(__fscache_invalidate); + /* * Generate a list of extant cookies in /proc/fs/fscache/cookies */ diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index ca938e00eaa0..7fb83d216360 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -105,6 +105,8 @@ extern atomic_t fscache_n_acquires; extern atomic_t fscache_n_acquires_ok; extern atomic_t fscache_n_acquires_oom; +extern atomic_t fscache_n_invalidates; + extern atomic_t fscache_n_relinquishes; extern atomic_t fscache_n_relinquishes_retire; extern atomic_t fscache_n_relinquishes_dropped; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 5aa4bd9fe207..cdbb672a274f 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -26,6 +26,8 @@ atomic_t fscache_n_acquires; atomic_t fscache_n_acquires_ok; atomic_t fscache_n_acquires_oom; +atomic_t fscache_n_invalidates; + atomic_t fscache_n_updates; EXPORT_SYMBOL(fscache_n_updates); @@ -59,6 +61,9 @@ int fscache_stats_show(struct seq_file *m, void *v) timer_pending(&fscache_cookie_lru_timer) ? fscache_cookie_lru_timer.expires - jiffies : 0); + seq_printf(m, "Invals : n=%u\n", + atomic_read(&fscache_n_invalidates)); + seq_printf(m, "Updates: n=%u\n", atomic_read(&fscache_n_updates)); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index ae6a75976450..1ad56bfd9d72 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -64,6 +64,9 @@ struct fscache_cache_ops { /* Withdraw an object without any cookie access counts held */ void (*withdraw_cookie)(struct fscache_cookie *cookie); + /* Invalidate an object */ + bool (*invalidate_cookie)(struct fscache_cookie *cookie); + /* Prepare to write to a live cache object */ void (*prepare_to_write)(struct fscache_cookie *cookie); }; @@ -96,6 +99,7 @@ extern void fscache_put_cookie(struct fscache_cookie *cookie, extern void fscache_end_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); +extern void fscache_resume_after_invalidation(struct fscache_cookie *cookie); extern void fscache_caching_failed(struct fscache_cookie *cookie); /** diff --git a/include/linux/fscache.h b/include/linux/fscache.h index e6c321e5bf73..0f36d1fac237 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -39,6 +39,8 @@ struct fscache_cookie; #define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ #define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ +#define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ + /* * Data object state. */ @@ -47,6 +49,7 @@ enum fscache_cookie_state { FSCACHE_COOKIE_STATE_LOOKING_UP, /* The cache object is being looked up */ FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ + FSCACHE_COOKIE_STATE_INVALIDATING, /* The cache is being invalidated */ FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ FSCACHE_COOKIE_STATE_LRU_DISCARDING, /* The cookie is being discarded by the LRU */ FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ @@ -153,6 +156,7 @@ extern struct fscache_cookie *__fscache_acquire_cookie( extern void __fscache_use_cookie(struct fscache_cookie *, bool); extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); +extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); /** * fscache_acquire_volume - Register a volume as desiring caching services @@ -327,4 +331,31 @@ void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); } +/** + * fscache_invalidate - Notify cache that an object needs invalidation + * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @size: The revised size of the object. + * @flags: Invalidation flags (FSCACHE_INVAL_*) + * + * Notify the cache that an object is needs to be invalidated and that it + * should abort any retrievals or stores it is doing on the cache. This + * increments inval_counter on the cookie which can be used by the caller to + * reconsider I/O requests as they complete. + * + * If @flags has FSCACHE_INVAL_DIO_WRITE set, this indicates that this is due + * to a direct I/O write and will cause caching to be disabled on this cookie + * until it is completely unused. + * + * See Documentation/filesystems/caching/netfs-api.rst for a complete + * description. + */ +static inline +void fscache_invalidate(struct fscache_cookie *cookie, + const void *aux_data, loff_t size, unsigned int flags) +{ + if (fscache_cookie_enabled(cookie)) + __fscache_invalidate(cookie, aux_data, size, flags); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 1ea22fc48818..5a46fde65759 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -124,6 +124,7 @@ struct netfs_cache_resources { void *cache_priv; void *cache_priv2; unsigned int debug_id; /* Cookie debug ID */ + unsigned int inval_counter; /* object->inval_counter at begin_op */ }; /* diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index b0409b1fad23..294792881434 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -51,6 +51,7 @@ enum fscache_cookie_trace { fscache_cookie_discard, fscache_cookie_get_end_access, fscache_cookie_get_hash_collision, + fscache_cookie_get_inval_work, fscache_cookie_get_lru, fscache_cookie_get_use_work, fscache_cookie_new_acquire, @@ -73,6 +74,8 @@ enum fscache_access_trace { fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_invalidate_cookie, + fscache_access_invalidate_cookie_end, fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, @@ -116,6 +119,7 @@ enum fscache_access_trace { EM(fscache_cookie_discard, "DISCARD ") \ EM(fscache_cookie_get_hash_collision, "GET hcoll") \ EM(fscache_cookie_get_end_access, "GQ endac") \ + EM(fscache_cookie_get_inval_work, "GQ inval") \ EM(fscache_cookie_get_lru, "GET lru ") \ EM(fscache_cookie_get_use_work, "GQ use ") \ EM(fscache_cookie_new_acquire, "NEW acq ") \ @@ -137,6 +141,8 @@ enum fscache_access_trace { EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_invalidate_cookie, "BEGIN inval ") \ + EM(fscache_access_invalidate_cookie_end,"END inval ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ @@ -385,6 +391,25 @@ TRACE_EVENT(fscache_relinquish, __entry->n_active, __entry->flags, __entry->retire) ); +TRACE_EVENT(fscache_invalidate, + TP_PROTO(struct fscache_cookie *cookie, loff_t new_size), + + TP_ARGS(cookie, new_size), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(loff_t, new_size ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->new_size = new_size; + ), + + TP_printk("c=%08x sz=%llx", + __entry->cookie, __entry->new_size) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From d64f4554dd177c5891c02424a8d9e80590b55b35 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Provide a means to begin an operation Provide a function to begin a read operation: int fscache_begin_read_operation( struct netfs_cache_resources *cres, struct fscache_cookie *cookie) This is primarily intended to be called by network filesystems on behalf of netfslib, but may also be called to use the I/O access functions directly. It attaches the resources required by the cache to cres struct from the supplied cookie. This holds access to the cache behind the cookie for the duration of the operation and forces cache withdrawal and cookie invalidation to perform synchronisation on the operation. cres->inval_counter is set from the cookie at this point so that it can be compared at the end of the operation. Note that this does not guarantee that the cache state is fully set up and able to perform I/O immediately; looking up and creation may be left in progress in the background. The operations intended to be called by the network filesystem, such as reading and writing, are expected to wait for the cookie to move to the correct state. This will, however, potentially sleep, waiting for a certain minimum state to be set or for operations such as invalidate to advance far enough that I/O can resume. Also provide a function for the cache to call to wait for the cache object to get to a state where it can be used for certain things: bool fscache_wait_for_operation(struct netfs_cache_resources *cres, enum fscache_want_stage stage); This looks at the cache resources provided by the begin function and waits for them to get to an appropriate stage. There's a choice of wanting just some parameters (FSCACHE_WANT_PARAM) or the ability to do I/O (FSCACHE_WANT_READ or FSCACHE_WANT_WRITE). Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819603692.215744.146724961588817028.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906910672.143852.13856103384424986357.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967110245.1823006.2239170567540431836.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021513617.640689.16627329360866150606.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 1 + fs/fscache/internal.h | 11 +++ fs/fscache/io.c | 151 +++++++++++++++++++++++++++++++++++++++++ include/linux/fscache-cache.h | 11 +++ include/linux/fscache.h | 49 +++++++++++++ include/trace/events/fscache.h | 6 ++ 6 files changed, 229 insertions(+) create mode 100644 fs/fscache/io.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index bcc79615f93a..afb090ea16c4 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -6,6 +6,7 @@ fscache-y := \ cache.o \ cookie.o \ + io.o \ main.o \ volume.o diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 7fb83d216360..017bf3d346a4 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -70,6 +70,17 @@ static inline void fscache_see_cookie(struct fscache_cookie *cookie, where); } +/* + * io.c + */ +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + /* * main.c */ diff --git a/fs/fscache/io.c b/fs/fscache/io.c new file mode 100644 index 000000000000..460a43473019 --- /dev/null +++ b/fs/fscache/io.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Cache data I/O routines + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ +#define FSCACHE_DEBUG_LEVEL OPERATION +#include +#include +#include +#include +#include +#include "internal.h" + +/** + * fscache_wait_for_operation - Wait for an object become accessible + * @cres: The cache resources for the operation being performed + * @want_state: The minimum state the object must be at + * + * See if the target cache object is at the specified minimum state of + * accessibility yet, and if not, wait for it. + */ +bool fscache_wait_for_operation(struct netfs_cache_resources *cres, + enum fscache_want_state want_state) +{ + struct fscache_cookie *cookie = fscache_cres_cookie(cres); + enum fscache_cookie_state state; + +again: + if (!fscache_cache_is_live(cookie->volume->cache)) { + _leave(" [broken]"); + return false; + } + + state = fscache_cookie_state(cookie); + _enter("c=%08x{%u},%x", cookie->debug_id, state, want_state); + + switch (state) { + case FSCACHE_COOKIE_STATE_CREATING: + case FSCACHE_COOKIE_STATE_INVALIDATING: + if (want_state == FSCACHE_WANT_PARAMS) + goto ready; /* There can be no content */ + fallthrough; + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + wait_var_event(&cookie->state, + fscache_cookie_state(cookie) != state); + goto again; + + case FSCACHE_COOKIE_STATE_ACTIVE: + goto ready; + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + default: + _leave(" [not live]"); + return false; + } + +ready: + if (!cres->cache_priv2) + return cookie->volume->cache->ops->begin_operation(cres, want_state); + return true; +} +EXPORT_SYMBOL(fscache_wait_for_operation); + +/* + * Begin an I/O operation on the cache, waiting till we reach the right state. + * + * Attaches the resources required to the operation resources record. + */ +static int fscache_begin_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie, + enum fscache_want_state want_state, + enum fscache_access_trace why) +{ + enum fscache_cookie_state state; + long timeo; + bool once_only = false; + + cres->ops = NULL; + cres->cache_priv = cookie; + cres->cache_priv2 = NULL; + cres->debug_id = cookie->debug_id; + cres->inval_counter = cookie->inval_counter; + + if (!fscache_begin_cookie_access(cookie, why)) + return -ENOBUFS; + +again: + spin_lock(&cookie->lock); + + state = fscache_cookie_state(cookie); + _enter("c=%08x{%u},%x", cookie->debug_id, state, want_state); + + switch (state) { + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + case FSCACHE_COOKIE_STATE_INVALIDATING: + goto wait_for_file_wrangling; + case FSCACHE_COOKIE_STATE_CREATING: + if (want_state == FSCACHE_WANT_PARAMS) + goto ready; /* There can be no content */ + goto wait_for_file_wrangling; + case FSCACHE_COOKIE_STATE_ACTIVE: + goto ready; + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + WARN(1, "Can't use cookie in state %u\n", cookie->state); + goto not_live; + default: + goto not_live; + } + +ready: + spin_unlock(&cookie->lock); + if (!cookie->volume->cache->ops->begin_operation(cres, want_state)) + goto failed; + return 0; + +wait_for_file_wrangling: + spin_unlock(&cookie->lock); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + atomic_read(&cookie->n_accesses), + fscache_access_io_wait); + timeo = wait_var_event_timeout(&cookie->state, + fscache_cookie_state(cookie) != state, 20 * HZ); + if (timeo <= 1 && !once_only) { + pr_warn("%s: cookie state change wait timed out: cookie->state=%u state=%u", + __func__, fscache_cookie_state(cookie), state); + fscache_print_cookie(cookie, 'O'); + once_only = true; + } + goto again; + +not_live: + spin_unlock(&cookie->lock); +failed: + cres->cache_priv = NULL; + cres->ops = NULL; + fscache_end_cookie_access(cookie, fscache_access_io_not_live); + _leave(" = -ENOBUFS"); + return -ENOBUFS; +} + +int __fscache_begin_read_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + return fscache_begin_operation(cres, cookie, FSCACHE_WANT_PARAMS, + fscache_access_io_read); +} +EXPORT_SYMBOL(__fscache_begin_read_operation); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 1ad56bfd9d72..566497cf5f13 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -67,6 +67,10 @@ struct fscache_cache_ops { /* Invalidate an object */ bool (*invalidate_cookie)(struct fscache_cookie *cookie); + /* Begin an operation for the netfs lib */ + bool (*begin_operation)(struct netfs_cache_resources *cres, + enum fscache_want_state want_state); + /* Prepare to write to a live cache object */ void (*prepare_to_write)(struct fscache_cookie *cookie); }; @@ -101,6 +105,8 @@ extern void fscache_end_cookie_access(struct fscache_cookie *cookie, extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); extern void fscache_resume_after_invalidation(struct fscache_cookie *cookie); extern void fscache_caching_failed(struct fscache_cookie *cookie); +extern bool fscache_wait_for_operation(struct netfs_cache_resources *cred, + enum fscache_want_state state); /** * fscache_cookie_state - Read the state of a cookie @@ -129,4 +135,9 @@ static inline void *fscache_get_key(struct fscache_cookie *cookie) return cookie->key; } +static inline struct fscache_cookie *fscache_cres_cookie(struct netfs_cache_resources *cres) +{ + return cres->cache_priv; +} + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 0f36d1fac237..7cdc63c4fe35 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -41,6 +41,12 @@ struct fscache_cookie; #define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ +enum fscache_want_state { + FSCACHE_WANT_PARAMS, + FSCACHE_WANT_WRITE, + FSCACHE_WANT_READ, +}; + /* * Data object state. */ @@ -157,6 +163,7 @@ extern void __fscache_use_cookie(struct fscache_cookie *, bool); extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); +extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); /** * fscache_acquire_volume - Register a volume as desiring caching services @@ -358,4 +365,46 @@ void fscache_invalidate(struct fscache_cookie *cookie, __fscache_invalidate(cookie, aux_data, size, flags); } +/** + * fscache_operation_valid - Return true if operations resources are usable + * @cres: The resources to check. + * + * Returns a pointer to the operations table if usable or NULL if not. + */ +static inline +const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_resources *cres) +{ + return fscache_resources_valid(cres) ? cres->ops : NULL; +} + +/** + * fscache_begin_read_operation - Begin a read operation for the netfs lib + * @cres: The cache resources for the read being performed + * @cookie: The cookie representing the cache object + * + * Begin a read operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. + * + * This is intended to be called from the ->begin_cache_operation() netfs lib + * operation as implemented by the network filesystem. + * + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. + * + * Returns: + * * 0 - Success + * * -ENOBUFS - No caching available + * * Other error code from the cache, such as -ENOMEM. + */ +static inline +int fscache_begin_read_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_read_operation(cres, cookie); + return -ENOBUFS; +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 294792881434..9f78c903b00a 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -76,6 +76,9 @@ enum fscache_access_trace { fscache_access_cache_unpin, fscache_access_invalidate_cookie, fscache_access_invalidate_cookie_end, + fscache_access_io_not_live, + fscache_access_io_read, + fscache_access_io_wait, fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, @@ -143,6 +146,9 @@ enum fscache_access_trace { EM(fscache_access_cache_unpin, "UNPIN cache ") \ EM(fscache_access_invalidate_cookie, "BEGIN inval ") \ EM(fscache_access_invalidate_cookie_end,"END inval ") \ + EM(fscache_access_io_not_live, "END io_notl") \ + EM(fscache_access_io_read, "BEGIN io_read") \ + EM(fscache_access_io_wait, "WAIT io ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ -- cgit v1.2.3 From cdf262f29488e6c3432911ec487ea41918fcbcd7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 11 Nov 2021 23:14:29 +0000 Subject: fscache: Count data storage objects in a cache Count the data storage objects that are currently allocated in a cache. This is used to pin certain cache structures until cache withdrawal is complete. Three helpers are provided to manage and make use of the count: (1) void fscache_count_object(struct fscache_cache *cache); This should be called by the cache backend to note that an object has been allocated and attached to the cache. (2) void fscache_uncount_object(struct fscache_cache *cache); This should be called by the backend to note that an object has been destroyed. This sends a wakeup event that allows cache withdrawal to proceed if it was waiting for that object. (3) void fscache_wait_for_objects(struct fscache_cache *cache); This can be used by the backend to wait for all outstanding cache object to be destroyed. Each cache's counter is displayed as part of /proc/fs/fscache/caches. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819608594.215744.1812706538117388252.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906911646.143852.168184059935530127.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967111846.1823006.9868154941573671255.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021516219.640689.4934796654308958158.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cache.c | 2 ++ include/linux/fscache-cache.h | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index 25eac61f1c29..2749933852a9 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -13,6 +13,8 @@ static LIST_HEAD(fscache_caches); DECLARE_RWSEM(fscache_addremove_sem); EXPORT_SYMBOL(fscache_addremove_sem); +DECLARE_WAIT_QUEUE_HEAD(fscache_clearance_waiters); +EXPORT_SYMBOL(fscache_clearance_waiters); static atomic_t fscache_cache_debug_id; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 566497cf5f13..337335d7a5e2 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -76,6 +76,7 @@ struct fscache_cache_ops { }; extern struct workqueue_struct *fscache_wq; +extern wait_queue_head_t fscache_clearance_waiters; /* * out-of-line cache backend functions @@ -140,4 +141,42 @@ static inline struct fscache_cookie *fscache_cres_cookie(struct netfs_cache_reso return cres->cache_priv; } +/** + * fscache_count_object - Tell fscache that an object has been added + * @cache: The cache to account to + * + * Tell fscache that an object has been added to the cache. This prevents the + * cache from tearing down the cache structure until the object is uncounted. + */ +static inline void fscache_count_object(struct fscache_cache *cache) +{ + atomic_inc(&cache->object_count); +} + +/** + * fscache_uncount_object - Tell fscache that an object has been removed + * @cache: The cache to account to + * + * Tell fscache that an object has been removed from the cache and will no + * longer be accessed. After this point, the cache cookie may be destroyed. + */ +static inline void fscache_uncount_object(struct fscache_cache *cache) +{ + if (atomic_dec_and_test(&cache->object_count)) + wake_up_all(&fscache_clearance_waiters); +} + +/** + * fscache_wait_for_objects - Wait for all objects to be withdrawn + * @cache: The cache to query + * + * Wait for all extant objects in a cache to finish being withdrawn + * and go away. + */ +static inline void fscache_wait_for_objects(struct fscache_cache *cache) +{ + wait_event(fscache_clearance_waiters, + atomic_read(&cache->object_count) == 0); +} + #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From 8e7a867bb7309fbf47e8c2a68798b919fc02523f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 23:06:16 +0100 Subject: fscache: Provide read/write stat counters for the cache Provide read/write stat counters for the cache backend to use. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819609532.215744.10821082637727410554.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906912598.143852.12960327989649429069.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967113830.1823006.3222957649202368162.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021517502.640689.6077928311710357342.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/stats.c | 9 +++++++++ include/linux/fscache-cache.h | 10 ++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index cdbb672a274f..db42beb1ba3f 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -35,6 +35,11 @@ atomic_t fscache_n_relinquishes; atomic_t fscache_n_relinquishes_retire; atomic_t fscache_n_relinquishes_dropped; +atomic_t fscache_n_read; +EXPORT_SYMBOL(fscache_n_read); +atomic_t fscache_n_write; +EXPORT_SYMBOL(fscache_n_write); + /* * display the general statistics */ @@ -72,6 +77,10 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_relinquishes_retire), atomic_read(&fscache_n_relinquishes_dropped)); + seq_printf(m, "IO : rd=%u wr=%u\n", + atomic_read(&fscache_n_read), + atomic_read(&fscache_n_write)); + netfs_stats_show(m); return 0; } diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 337335d7a5e2..796c8b5c5305 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -179,4 +179,14 @@ static inline void fscache_wait_for_objects(struct fscache_cache *cache) atomic_read(&cache->object_count) == 0); } +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_read; +extern atomic_t fscache_n_write; +#define fscache_count_read() atomic_inc(&fscache_n_read) +#define fscache_count_write() atomic_inc(&fscache_n_write) +#else +#define fscache_count_read() do {} while(0) +#define fscache_count_write() do {} while(0) +#endif + #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From ed1235eb78a7421cd0ac2ad09e931f8f07ccdc7c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 23:10:46 +0100 Subject: fscache: Provide a function to let the netfs update its coherency data Provide a function to let the netfs update its coherency data: void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size); This will update the auxiliary data and/or the size of the object attached to a cookie if either pointer is not-NULL and flag that the disk needs to be updated. Note that fscache_unuse_cookie() also allows this to be done. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819610438.215744.4223265964131424954.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906913530.143852.18150303220217653820.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967117795.1823006.7493373142653442595.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021518440.640689.6369952464473039268.stgit@warthog.procyon.org.uk/ # v4 --- include/linux/fscache.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 7cdc63c4fe35..fc77648c8af6 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -338,6 +338,28 @@ void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); } +/** + * fscache_update_cookie - Request that a cache object be updated + * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @object_size: The current size of the object (may be NULL) + * + * Request an update of the index data for the cache object associated with the + * cookie. The auxiliary data on the cookie will be updated first if @aux_data + * is set and the object size will be updated and the object possibly trimmed + * if @object_size is set. + * + * See Documentation/filesystems/caching/netfs-api.rst for a complete + * description. + */ +static inline +void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) +{ + if (fscache_cookie_enabled(cookie)) + __fscache_update_cookie(cookie, aux_data, object_size); +} + /** * fscache_invalidate - Notify cache that an object needs invalidation * @cookie: The cookie representing the cache object -- cgit v1.2.3 From 3a11b3a86366ccbf0818b088ffecadf8b2d61177 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Sep 2021 09:47:45 +0100 Subject: netfs: Pass more information on how to deal with a hole in the cache Pass more information to the cache on how to deal with a hole if it encounters one when trying to read from the cache. Three options are provided: (1) NETFS_READ_HOLE_IGNORE. Read the hole along with the data, assuming it to be a punched-out extent by the backing filesystem. (2) NETFS_READ_HOLE_CLEAR. If there's a hole, erase the requested region of the cache and clear the read buffer. (3) NETFS_READ_HOLE_FAIL. Fail the read if a hole is detected. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819612321.215744.9738308885948264476.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906914460.143852.6284247083607910189.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967119923.1823006.15637375885194297582.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021519762.640689.16994364383313159319.stgit@warthog.procyon.org.uk/ # v4 --- fs/netfs/read_helper.c | 8 ++++---- include/linux/netfs.h | 11 ++++++++++- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 9dd76b8914f2..6169659857b3 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -170,7 +170,7 @@ static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error */ static void netfs_read_from_cache(struct netfs_read_request *rreq, struct netfs_read_subrequest *subreq, - bool seek_data) + enum netfs_read_from_hole read_hole) { struct netfs_cache_resources *cres = &rreq->cache_resources; struct iov_iter iter; @@ -180,7 +180,7 @@ static void netfs_read_from_cache(struct netfs_read_request *rreq, subreq->start + subreq->transferred, subreq->len - subreq->transferred); - cres->ops->read(cres, subreq->start, &iter, seek_data, + cres->ops->read(cres, subreq->start, &iter, read_hole, netfs_cache_read_terminated, subreq); } @@ -461,7 +461,7 @@ static void netfs_rreq_short_read(struct netfs_read_request *rreq, netfs_get_read_subrequest(subreq); atomic_inc(&rreq->nr_rd_ops); if (subreq->source == NETFS_READ_FROM_CACHE) - netfs_read_from_cache(rreq, subreq, true); + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); else netfs_read_from_server(rreq, subreq); } @@ -789,7 +789,7 @@ static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq, netfs_read_from_server(rreq, subreq); break; case NETFS_READ_FROM_CACHE: - netfs_read_from_cache(rreq, subreq, false); + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); break; default: BUG(); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5a46fde65759..b46c39d98bbd 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -196,6 +196,15 @@ struct netfs_read_request_ops { void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; +/* + * How to handle reading from a hole. + */ +enum netfs_read_from_hole { + NETFS_READ_HOLE_IGNORE, + NETFS_READ_HOLE_CLEAR, + NETFS_READ_HOLE_FAIL, +}; + /* * Table of operations for access to a cache. This is obtained by * rreq->ops->begin_cache_operation(). @@ -208,7 +217,7 @@ struct netfs_cache_ops { int (*read)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, - bool seek_data, + enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv); -- cgit v1.2.3 From 9af1c6c3089b294ffa240e0fbba356666698b6d0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Implement raw I/O interface Provide a pair of functions to perform raw I/O on the cache. The first function allows an arbitrary asynchronous direct-IO read to be made against a cache object, though the read should be aligned and sized appropriately for the backing device: int fscache_read(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv); The cache resources must have been previously initialised by fscache_begin_read_operation(). A read operation is sent to the backing filesystem, starting at start_pos within the file. The size of the read is specified by the iterator, as is the location of the output buffer. If there is a hole in the data it can be ignored and left to the backing filesystem to deal with (NETFS_READ_HOLE_IGNORE), a hole at the beginning can be skipped over and the buffer padded with zeros (NETFS_READ_HOLE_CLEAR) or -ENODATA can be given (NETFS_READ_HOLE_FAIL). If term_func is not NULL, the operation may be performed asynchronously. Upon completion, successful or otherwise, (*term_func)() will be called and passed term_func_priv, along with an error or the amount of data transferred. If the op is run asynchronously, fscache_read() will return -EIOCBQUEUED. The second function allows an arbitrary asynchronous direct-IO write to be made against a cache object, though the write should be aligned and sized appropriately for the backing device: int fscache_write(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, netfs_io_terminated_t term_func, void *term_func_priv); This works in very similar way to fscache_read(), except that there's no need to deal with holes (they're just overwritten). The caller is responsible for preventing concurrent overlapping writes. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819613224.215744.7877577215582621254.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906915386.143852.16936177636106480724.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967122632.1823006.7487049517698562172.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021521420.640689.12747258780542678309.stgit@warthog.procyon.org.uk/ # v4 --- include/linux/fscache.h | 74 ++++++++++++++++++++++++++++++++++++++++++ include/trace/events/fscache.h | 2 ++ 2 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index fc77648c8af6..ae753cae0fdd 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -429,4 +429,78 @@ int fscache_begin_read_operation(struct netfs_cache_resources *cres, return -ENOBUFS; } +/** + * fscache_read - Start a read from the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The buffer to fill - and also the length + * @read_hole: How to handle a hole in the data. + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * + * Start a read from the cache. @cres indicates the cache object to read from + * and must be obtained by a call to fscache_begin_operation() beforehand. + * + * The data is read into the iterator, @iter, and that also indicates the size + * of the operation. @start_pos is the start position in the file, though if + * @seek_data is set appropriately, the cache can use SEEK_DATA to find the + * next piece of data, writing zeros for the hole into the iterator. + * + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. + * + * @read_hole indicates how a partially populated region in the cache should be + * handled. It can be one of a number of settings: + * + * NETFS_READ_HOLE_IGNORE - Just try to read (may return a short read). + * + * NETFS_READ_HOLE_CLEAR - Seek for data, clearing the part of the buffer + * skipped over, then do as for IGNORE. + * + * NETFS_READ_HOLE_FAIL - Give ENODATA if we encounter a hole. + */ +static inline +int fscache_read(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + enum netfs_read_from_hole read_hole, + netfs_io_terminated_t term_func, + void *term_func_priv) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->read(cres, start_pos, iter, read_hole, + term_func, term_func_priv); +} + +/** + * fscache_write - Start a write to the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The data to write - and also the length + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * + * Start a write to the cache. @cres indicates the cache object to write to and + * must be obtained by a call to fscache_begin_operation() beforehand. + * + * The data to be written is obtained from the iterator, @iter, and that also + * indicates the size of the operation. @start_pos is the start position in + * the file. + * + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. + */ +static inline +int fscache_write(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->write(cres, start_pos, iter, term_func, term_func_priv); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 9f78c903b00a..2459d75659cf 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -79,6 +79,7 @@ enum fscache_access_trace { fscache_access_io_not_live, fscache_access_io_read, fscache_access_io_wait, + fscache_access_io_write, fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, @@ -149,6 +150,7 @@ enum fscache_access_trace { EM(fscache_access_io_not_live, "END io_notl") \ EM(fscache_access_io_read, "BEGIN io_read") \ EM(fscache_access_io_wait, "WAIT io ") \ + EM(fscache_access_io_write, "BEGIN io_writ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ -- cgit v1.2.3 From b6e16652d6c0e4f9e9b120f66966ec153f0623fc Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Implement higher-level write I/O interface Provide a higher-level function than fscache_write() to perform a write from an inode's pagecache to the cache, whilst fending off concurrent writes by means of the PG_fscache mark on a page: void fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, bool caching); If caching is false, this function does nothing except call (*term_func)() if given. It assumes that, in such a case, PG_fscache will not have been set on the pages. Otherwise, if caching is true, this function requires the source pages to have had PG_fscache set on them before calling. start and len define the region of the file to be modified and i_size indicates the new file size. The source pages are extracted from the mapping. term_func and term_func_priv work as for fscache_write(). The PG_fscache marks will be cleared at the end of the operation, before term_func is called or the function otherwise returns. There is an additonal helper function to clear the PG_fscache bits from a range of pages: void fscache_clear_page_bits(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, bool caching); If caching is true, the pages to be managed are expected to be located on mapping in the range defined by start and len. If caching is false, it does nothing. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819614155.215744.5528123235123721230.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906916346.143852.15632773570362489926.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967123599.1823006.12946816026724657428.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021522672.640689.4381958316198807813.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/io.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fscache.h | 63 +++++++++++++++++++++++++++++ 2 files changed, 167 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/io.c b/fs/fscache/io.c index 460a43473019..74cde7acf434 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -149,3 +149,107 @@ int __fscache_begin_read_operation(struct netfs_cache_resources *cres, fscache_access_io_read); } EXPORT_SYMBOL(__fscache_begin_read_operation); + +struct fscache_write_request { + struct netfs_cache_resources cache_resources; + struct address_space *mapping; + loff_t start; + size_t len; + bool set_bits; + netfs_io_terminated_t term_func; + void *term_func_priv; +}; + +void __fscache_clear_page_bits(struct address_space *mapping, + loff_t start, size_t len) +{ + pgoff_t first = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE; + struct page *page; + + if (len) { + XA_STATE(xas, &mapping->i_pages, first); + + rcu_read_lock(); + xas_for_each(&xas, page, last) { + end_page_fscache(page); + } + rcu_read_unlock(); + } +} +EXPORT_SYMBOL(__fscache_clear_page_bits); + +/* + * Deal with the completion of writing the data to the cache. + */ +static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct fscache_write_request *wreq = priv; + + fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), + wreq->mapping, wreq->start, wreq->len, + wreq->set_bits); + + if (wreq->term_func) + wreq->term_func(wreq->term_func_priv, transferred_or_error, + was_async); + fscache_end_operation(&wreq->cache_resources); + kfree(wreq); +} + +void __fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool cond) +{ + struct fscache_write_request *wreq; + struct netfs_cache_resources *cres; + struct iov_iter iter; + int ret = -ENOBUFS; + + if (len == 0) + goto abandon; + + _enter("%llx,%zx", start, len); + + wreq = kzalloc(sizeof(struct fscache_write_request), GFP_NOFS); + if (!wreq) + goto abandon; + wreq->mapping = mapping; + wreq->start = start; + wreq->len = len; + wreq->set_bits = cond; + wreq->term_func = term_func; + wreq->term_func_priv = term_func_priv; + + cres = &wreq->cache_resources; + if (fscache_begin_operation(cres, cookie, FSCACHE_WANT_WRITE, + fscache_access_io_write) < 0) + goto abandon_free; + + ret = cres->ops->prepare_write(cres, &start, &len, i_size, false); + if (ret < 0) + goto abandon_end; + + /* TODO: Consider clearing page bits now for space the write isn't + * covering. This is more complicated than it appears when THPs are + * taken into account. + */ + + iov_iter_xarray(&iter, WRITE, &mapping->i_pages, start, len); + fscache_write(cres, start, &iter, fscache_wreq_done, wreq); + return; + +abandon_end: + return fscache_wreq_done(wreq, ret, false); +abandon_free: + kfree(wreq); +abandon: + fscache_clear_page_bits(cookie, mapping, start, len, cond); + if (term_func) + term_func(term_func_priv, ret, false); +} +EXPORT_SYMBOL(__fscache_write_to_cache); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index ae753cae0fdd..9d469613e16c 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -165,6 +165,11 @@ extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); +extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, + loff_t, size_t, loff_t, netfs_io_terminated_t, void *, + bool); +extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); + /** * fscache_acquire_volume - Register a volume as desiring caching services * @volume_key: An identification string for the volume @@ -503,4 +508,62 @@ int fscache_write(struct netfs_cache_resources *cres, return ops->write(cres, start_pos, iter, term_func, term_func_priv); } +/** + * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages + * @cookie: The cookie representing the cache object + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to unlock + * @caching: If PG_fscache has been set + * + * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's + * waiting. + */ +static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, + bool caching) +{ + if (caching) + __fscache_clear_page_bits(mapping, start, len); +} + +/** + * fscache_write_to_cache - Save a write to the cache and clear PG_fscache + * @cookie: The cookie representing the cache object + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to write back + * @i_size: The new size of the inode + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * @caching: If PG_fscache has been set + * + * Helper function for a netfs to write dirty data from an inode into the cache + * object that's backing it. + * + * @start and @len describe the range of the data. This does not need to be + * page-aligned, but to satisfy DIO requirements, the cache may expand it up to + * the page boundaries on either end. All the pages covering the range must be + * marked with PG_fscache. + * + * If given, @term_func will be called upon completion and supplied with + * @term_func_priv. Note that the PG_fscache flags will have been cleared by + * this point, so the netfs must retain its own pin on the mapping. + */ +static inline void fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool caching) +{ + if (caching) + __fscache_write_to_cache(cookie, mapping, start, len, i_size, + term_func, term_func_priv, caching); + else if (term_func) + term_func(term_func_priv, -ENOBUFS, false); + +} + #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 08276bdae68b022a7726edf7416b6748e3df5395 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 23:50:01 +0100 Subject: vfs, fscache: Implement pinning of cache usage for writeback Cachefiles has a problem in that it needs to keep the backing file for a cookie open whilst there are local modifications pending that need to be written to it. However, we don't want to keep the file open indefinitely, as that causes EMFILE/ENFILE/ENOMEM problems. Reopening the cache file, however, is a problem if this is being done due to writeback triggered by exit(). Some filesystems will oops if we try to open a file in that context because they want to access current->fs or other resources that have already been dismantled. To get around this, I added the following: (1) An inode flag, I_PINNING_FSCACHE_WB, to be set on a network filesystem inode to indicate that we have a usage count on the cookie caching that inode. (2) A flag in struct writeback_control, unpinned_fscache_wb, that is set when __writeback_single_inode() clears the last dirty page from i_pages - at which point it clears I_PINNING_FSCACHE_WB and sets this flag. This has to be done here so that clearing I_PINNING_FSCACHE_WB can be done atomically with the check of PAGECACHE_TAG_DIRTY that clears I_DIRTY_PAGES. (3) A function, fscache_set_page_dirty(), which if it is not set, sets I_PINNING_FSCACHE_WB and calls fscache_use_cookie() to pin the cache resources. (4) A function, fscache_unpin_writeback(), to be called by ->write_inode() to unuse the cookie. (5) A function, fscache_clear_inode_writeback(), to be called when the inode is evicted, before clear_inode() is called. This cleans up any lingering I_PINNING_FSCACHE_WB. The network filesystem can then use these tools to make sure that fscache_write_to_cache() can write locally modified data to the cache as well as to the server. For the future, I'm working on write helpers for netfs lib that should allow this facility to be removed by keeping track of the dirty regions separately - but that's incomplete at the moment and is also going to be affected by folios, one way or another, since it deals with pages Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819615157.215744.17623791756928043114.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906917856.143852.8224898306177154573.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967124567.1823006.14188359004568060298.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021524705.640689.17824932021727663017.stgit@warthog.procyon.org.uk/ # v4 --- fs/fs-writeback.c | 8 ++++++++ fs/fscache/io.c | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 3 +++ include/linux/fscache.h | 41 +++++++++++++++++++++++++++++++++++++++++ include/linux/writeback.h | 1 + 5 files changed, 91 insertions(+) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 67f0e88eed01..8294a60ce323 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1666,6 +1666,13 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; + else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) { + if (!(inode->i_state & I_DIRTY_PAGES)) { + inode->i_state &= ~I_PINNING_FSCACHE_WB; + wbc->unpinned_fscache_wb = true; + dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */ + } + } spin_unlock(&inode->i_lock); @@ -1675,6 +1682,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (ret == 0) ret = err; } + wbc->unpinned_fscache_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } diff --git a/fs/fscache/io.c b/fs/fscache/io.c index 74cde7acf434..e9e5d6758ea8 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -150,6 +150,44 @@ int __fscache_begin_read_operation(struct netfs_cache_resources *cres, } EXPORT_SYMBOL(__fscache_begin_read_operation); +/** + * fscache_set_page_dirty - Mark page dirty and pin a cache object for writeback + * @page: The page being dirtied + * @cookie: The cookie referring to the cache object + * + * Set the dirty flag on a page and pin an in-use cache object in memory when + * dirtying a page so that writeback can later write to it. This is intended + * to be called from the filesystem's ->set_page_dirty() method. + * + * Returns 1 if PG_dirty was set on the page, 0 otherwise. + */ +int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cookie) +{ + struct inode *inode = page->mapping->host; + bool need_use = false; + + _enter(""); + + if (!__set_page_dirty_nobuffers(page)) + return 0; + if (!fscache_cookie_valid(cookie)) + return 1; + + if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { + inode->i_state |= I_PINNING_FSCACHE_WB; + need_use = true; + } + spin_unlock(&inode->i_lock); + + if (need_use) + fscache_use_cookie(cookie, true); + } + return 1; +} +EXPORT_SYMBOL(fscache_set_page_dirty); + struct fscache_write_request { struct netfs_cache_resources cache_resources; struct address_space *mapping; diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..2c0b8e77d9ab 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2418,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2440,6 +2442,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) +#define I_PINNING_FSCACHE_WB (1 << 18) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 9d469613e16c..18e725671594 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -16,6 +16,7 @@ #include #include +#include #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) #define __fscache_available (1) @@ -566,4 +567,44 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, } +#if __fscache_available +extern int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cookie); +#else +#define fscache_set_page_dirty(PAGE, COOKIE) (__set_page_dirty_nobuffers((PAGE))) +#endif + +/** + * fscache_unpin_writeback - Unpin writeback resources + * @wbc: The writeback control + * @cookie: The cookie referring to the cache object + * + * Unpin the writeback resources pinned by fscache_set_page_dirty(). This is + * intended to be called by the netfs's ->write_inode() method. + */ +static inline void fscache_unpin_writeback(struct writeback_control *wbc, + struct fscache_cookie *cookie) +{ + if (wbc->unpinned_fscache_wb) + fscache_unuse_cookie(cookie, NULL, NULL); +} + +/** + * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode + * @cookie: The cookie referring to the cache object + * @inode: The inode to clean up + * @aux: Auxiliary data to apply to the inode + * + * Clear any writeback resources held by an inode when the inode is evicted. + * This must be called before clear_inode() is called. + */ +static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, + struct inode *inode, + const void *aux) +{ + if (inode->i_state & I_PINNING_FSCACHE_WB) { + loff_t i_size = i_size_read(inode); + fscache_unuse_cookie(cookie, aux, &i_size); + } +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3bfd487d1dd2..fec248ab1fec 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,6 +68,7 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + unsigned unpinned_fscache_wb:1; /* Cleared I_PINNING_FSCACHE_WB */ /* * When writeback IOs are bounced through async layers, only the -- cgit v1.2.3 From 1f67e6d0b18853c641d861a671f46a4964a88510 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Provide a function to note the release of a page Provide a function to be called from a network filesystem's releasepage method to indicate that a page has been released that might have been a reflection of data upon the server - and now that data must be reloaded from the server or the cache. This is used to end an optimisation for empty files, in particular files that have just been created locally, whereby we know there cannot yet be any data that we would need to read from the server or the cache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819617128.215744.4725572296135656508.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906920354.143852.7511819614661372008.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967128061.1823006.611781655060034988.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021525963.640689.9264556596205140044.stgit@warthog.procyon.org.uk/ # v4 --- include/linux/fscache.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 18e725671594..28ce258c1f87 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -607,4 +607,20 @@ static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, } } +/** + * fscache_note_page_release - Note that a netfs page got released + * @cookie: The cookie corresponding to the file + * + * Note that a page that has been copied to the cache has been released. This + * means that future reads will need to look in the cache to see if it's there. + */ +static inline +void fscache_note_page_release(struct fscache_cookie *cookie) +{ + if (cookie && + test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && + test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); +} + #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 16a96bdf92d5af06f9fa6a01a4b08e2fdfed2e5b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Provide a function to resize a cookie Provide a function to change the size of the storage attached to a cookie, to match the size of the file being cached when it's changed by truncate or fallocate: void fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size); This acts synchronously and is expected to run under the inode lock of the caller. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819621839.215744.7895597119803515402.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906922387.143852.16394459879816147793.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967128998.1823006.10740669081985775576.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021527861.640689.3466382085497236267.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/internal.h | 3 +++ fs/fscache/io.c | 25 +++++++++++++++++++++++++ fs/fscache/stats.c | 9 +++++++-- include/linux/fscache-cache.h | 4 ++++ include/linux/fscache.h | 18 ++++++++++++++++++ include/trace/events/fscache.h | 25 +++++++++++++++++++++++++ 6 files changed, 82 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 017bf3d346a4..f121c21590dc 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -122,6 +122,9 @@ extern atomic_t fscache_n_relinquishes; extern atomic_t fscache_n_relinquishes_retire; extern atomic_t fscache_n_relinquishes_dropped; +extern atomic_t fscache_n_resizes; +extern atomic_t fscache_n_resizes_null; + static inline void fscache_stat(atomic_t *stat) { atomic_inc(stat); diff --git a/fs/fscache/io.c b/fs/fscache/io.c index e9e5d6758ea8..bed7628a5a9d 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -291,3 +291,28 @@ abandon: term_func(term_func_priv, ret, false); } EXPORT_SYMBOL(__fscache_write_to_cache); + +/* + * Change the size of a backing object. + */ +void __fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) +{ + struct netfs_cache_resources cres; + + trace_fscache_resize(cookie, new_size); + if (fscache_begin_operation(&cres, cookie, FSCACHE_WANT_WRITE, + fscache_access_io_resize) == 0) { + fscache_stat(&fscache_n_resizes); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); + + /* We cannot defer a resize as we need to do it inside the + * netfs's inode lock so that we're serialised with respect to + * writes. + */ + cookie->volume->cache->ops->resize_cookie(&cres, new_size); + fscache_end_operation(&cres); + } else { + fscache_stat(&fscache_n_resizes_null); + } +} +EXPORT_SYMBOL(__fscache_resize_cookie); diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index db42beb1ba3f..798ee68b3e9d 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -35,6 +35,9 @@ atomic_t fscache_n_relinquishes; atomic_t fscache_n_relinquishes_retire; atomic_t fscache_n_relinquishes_dropped; +atomic_t fscache_n_resizes; +atomic_t fscache_n_resizes_null; + atomic_t fscache_n_read; EXPORT_SYMBOL(fscache_n_read); atomic_t fscache_n_write; @@ -69,8 +72,10 @@ int fscache_stats_show(struct seq_file *m, void *v) seq_printf(m, "Invals : n=%u\n", atomic_read(&fscache_n_invalidates)); - seq_printf(m, "Updates: n=%u\n", - atomic_read(&fscache_n_updates)); + seq_printf(m, "Updates: n=%u rsz=%u rsn=%u\n", + atomic_read(&fscache_n_updates), + atomic_read(&fscache_n_resizes), + atomic_read(&fscache_n_resizes_null)); seq_printf(m, "Relinqs: n=%u rtr=%u drop=%u\n", atomic_read(&fscache_n_relinquishes), diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 796c8b5c5305..3fa4902dc87c 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -64,6 +64,10 @@ struct fscache_cache_ops { /* Withdraw an object without any cookie access counts held */ void (*withdraw_cookie)(struct fscache_cookie *cookie); + /* Change the size of a data object */ + void (*resize_cookie)(struct netfs_cache_resources *cres, + loff_t new_size); + /* Invalidate an object */ bool (*invalidate_cookie)(struct fscache_cookie *cookie); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 28ce258c1f87..86b1c0db1de5 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -163,6 +163,7 @@ extern struct fscache_cookie *__fscache_acquire_cookie( extern void __fscache_use_cookie(struct fscache_cookie *, bool); extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); +extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); @@ -366,6 +367,23 @@ void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, __fscache_update_cookie(cookie, aux_data, object_size); } +/** + * fscache_resize_cookie - Request that a cache object be resized + * @cookie: The cookie representing the cache object + * @new_size: The new size of the object (may be NULL) + * + * Request that the size of an object be changed. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) +{ + if (fscache_cookie_enabled(cookie)) + __fscache_resize_cookie(cookie, new_size); +} + /** * fscache_invalidate - Notify cache that an object needs invalidation * @cookie: The cookie representing the cache object diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 2459d75659cf..5fa37a8b4ec7 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -78,6 +78,7 @@ enum fscache_access_trace { fscache_access_invalidate_cookie_end, fscache_access_io_not_live, fscache_access_io_read, + fscache_access_io_resize, fscache_access_io_wait, fscache_access_io_write, fscache_access_lookup_cookie, @@ -149,6 +150,7 @@ enum fscache_access_trace { EM(fscache_access_invalidate_cookie_end,"END inval ") \ EM(fscache_access_io_not_live, "END io_notl") \ EM(fscache_access_io_read, "BEGIN io_read") \ + EM(fscache_access_io_resize, "BEGIN io_resz") \ EM(fscache_access_io_wait, "WAIT io ") \ EM(fscache_access_io_write, "BEGIN io_writ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ @@ -418,6 +420,29 @@ TRACE_EVENT(fscache_invalidate, __entry->cookie, __entry->new_size) ); +TRACE_EVENT(fscache_resize, + TP_PROTO(struct fscache_cookie *cookie, loff_t new_size), + + TP_ARGS(cookie, new_size), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(loff_t, old_size ) + __field(loff_t, new_size ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->old_size = cookie->object_size; + __entry->new_size = new_size; + ), + + TP_printk("c=%08x os=%08llx sz=%08llx", + __entry->cookie, + __entry->old_size, + __entry->new_size) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 1bd9c4e4f0494915b2391f373d25096579f835ff Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 18 Nov 2021 08:58:08 +0000 Subject: vfs, cachefiles: Mark a backing file in use with an inode flag Use an inode flag, S_KERNEL_FILE, to mark that a backing file is in use by the kernel to prevent cachefiles or other kernel services from interfering with that file. Alter rmdir to reject attempts to remove a directory marked with this flag. This is used by cachefiles to prevent cachefilesd from removing them. Using S_SWAPFILE instead isn't really viable as that has other effects in the I/O paths. Changes ======= ver #3: - Check for the object pointer being NULL in the tracepoints rather than the caller. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819630256.215744.4815885535039369574.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906931596.143852.8642051223094013028.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967141000.1823006.12920680657559677789.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021541207.640689.564689725898537127.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/Makefile | 1 + fs/cachefiles/namei.c | 43 +++++++++++++++++++++++++++++++++++++++ fs/namei.c | 3 ++- include/linux/fs.h | 1 + include/trace/events/cachefiles.h | 42 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 89 insertions(+), 1 deletion(-) create mode 100644 fs/cachefiles/namei.c (limited to 'include/linux') diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile index 463e3d608b75..e0b092ca077f 100644 --- a/fs/cachefiles/Makefile +++ b/fs/cachefiles/Makefile @@ -7,6 +7,7 @@ cachefiles-y := \ cache.o \ daemon.o \ main.o \ + namei.o \ security.o cachefiles-$(CONFIG_CACHEFILES_ERROR_INJECTION) += error_inject.o diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c new file mode 100644 index 000000000000..913f83f1c900 --- /dev/null +++ b/fs/cachefiles/namei.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* CacheFiles path walking and related routines + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include "internal.h" + +/* + * Mark the backing file as being a cache file if it's not already in use. The + * mark tells the culling request command that it's not allowed to cull the + * file or directory. The caller must hold the inode lock. + */ +static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + bool can_use = false; + + if (!(inode->i_flags & S_KERNEL_FILE)) { + inode->i_flags |= S_KERNEL_FILE; + trace_cachefiles_mark_active(object, inode); + can_use = true; + } else { + pr_notice("cachefiles: Inode already in use: %pd\n", dentry); + } + + return can_use; +} + +/* + * Unmark a backing inode. The caller must hold the inode lock. + */ +static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + + inode->i_flags &= ~S_KERNEL_FILE; + trace_cachefiles_mark_inactive(object, inode); +} diff --git a/fs/namei.c b/fs/namei.c index 1f9d2187c765..d81f04f8d818 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3958,7 +3958,8 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, inode_lock(dentry->d_inode); error = -EBUSY; - if (is_local_mountpoint(dentry)) + if (is_local_mountpoint(dentry) || + (dentry->d_inode->i_flags & S_KERNEL_FILE)) goto out; error = security_inode_rmdir(dir, dentry); diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c0b8e77d9ab..bcf1ca430139 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2249,6 +2249,7 @@ struct super_operations { #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ +#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 9bd5a8a60801..6331cd29880d 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -83,6 +83,48 @@ cachefiles_error_traces; #define E_(a, b) { a, b } +TRACE_EVENT(cachefiles_mark_active, + TP_PROTO(struct cachefiles_object *obj, + struct inode *inode), + + TP_ARGS(obj, inode), + + /* Note that obj may be NULL */ + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(ino_t, inode ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->inode = inode->i_ino; + ), + + TP_printk("o=%08x i=%lx", + __entry->obj, __entry->inode) + ); + +TRACE_EVENT(cachefiles_mark_inactive, + TP_PROTO(struct cachefiles_object *obj, + struct inode *inode), + + TP_ARGS(obj, inode), + + /* Note that obj may be NULL */ + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(ino_t, inode ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->inode = inode->i_ino; + ), + + TP_printk("o=%08x i=%lx", + __entry->obj, __entry->inode) + ); + TRACE_EVENT(cachefiles_vfs_error, TP_PROTO(struct cachefiles_object *obj, struct inode *backer, int error, enum cachefiles_error_trace where), -- cgit v1.2.3 From 32e150037dce368d129996ffe5f98217b1974d9e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Dec 2021 09:51:43 +0000 Subject: fscache, cachefiles: Store the volume coherency data Store the volume coherency data in an xattr and check it when we rebind the volume. If it doesn't match the cache volume is moved to the graveyard and rebuilt anew. Changes ======= ver #4: - Remove a couple of debugging prints. Signed-off-by: David Howells Reviewed-by: Jeff Layton Link: https://lore.kernel.org/r/163967164397.1823006.2950539849831291830.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021563138.640689.15851092065380543119.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/internal.h | 2 + fs/cachefiles/volume.c | 25 ++++++++++++- fs/cachefiles/xattr.c | 78 +++++++++++++++++++++++++++++++++++++++ fs/fscache/volume.c | 14 ++++++- include/linux/fscache.h | 2 + include/trace/events/cachefiles.h | 42 ++++++++++++++++++++- 6 files changed, 157 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index d5868f5514d3..abdd1b66f6b9 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -270,6 +270,8 @@ extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, struct cachefiles_object *object, struct dentry *dentry); extern void cachefiles_prepare_to_write(struct fscache_cookie *cookie); +extern bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume); +extern int cachefiles_check_volume_xattr(struct cachefiles_volume *volume); /* * Error handling diff --git a/fs/cachefiles/volume.c b/fs/cachefiles/volume.c index 4a14f5e72764..89df0ba8ba5e 100644 --- a/fs/cachefiles/volume.c +++ b/fs/cachefiles/volume.c @@ -22,7 +22,8 @@ void cachefiles_acquire_volume(struct fscache_volume *vcookie) struct dentry *vdentry, *fan; size_t len; char *name; - int n_accesses, i; + bool is_new = false; + int ret, n_accesses, i; _enter(""); @@ -43,11 +44,29 @@ void cachefiles_acquire_volume(struct fscache_volume *vcookie) memcpy(name + 1, vcookie->key + 1, len); name[len + 1] = 0; - vdentry = cachefiles_get_directory(cache, cache->store, name, NULL); +retry: + vdentry = cachefiles_get_directory(cache, cache->store, name, &is_new); if (IS_ERR(vdentry)) goto error_name; volume->dentry = vdentry; + if (is_new) { + if (!cachefiles_set_volume_xattr(volume)) + goto error_dir; + } else { + ret = cachefiles_check_volume_xattr(volume); + if (ret < 0) { + if (ret != -ESTALE) + goto error_dir; + inode_lock_nested(d_inode(cache->store), I_MUTEX_PARENT); + cachefiles_bury_object(cache, NULL, cache->store, vdentry, + FSCACHE_VOLUME_IS_WEIRD); + cachefiles_put_directory(volume->dentry); + cond_resched(); + goto retry; + } + } + for (i = 0; i < 256; i++) { sprintf(name, "@%02x", i); fan = cachefiles_get_directory(cache, vdentry, name, NULL); @@ -74,6 +93,7 @@ void cachefiles_acquire_volume(struct fscache_volume *vcookie) error_fan: for (i = 0; i < 256; i++) cachefiles_put_directory(volume->fanout[i]); +error_dir: cachefiles_put_directory(volume->dentry); error_name: kfree(name); @@ -114,5 +134,6 @@ void cachefiles_free_volume(struct fscache_volume *vcookie) void cachefiles_withdraw_volume(struct cachefiles_volume *volume) { fscache_withdraw_volume(volume->vcookie); + cachefiles_set_volume_xattr(volume); __cachefiles_free_volume(volume); } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 0601c46a22ef..83f41bd0c3a9 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -179,3 +179,81 @@ void cachefiles_prepare_to_write(struct fscache_cookie *cookie) cachefiles_end_secure(cache, saved_cred); } } + +/* + * Set the state xattr on a volume directory. + */ +bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) +{ + unsigned int len = volume->vcookie->coherency_len; + const void *p = volume->vcookie->coherency; + struct dentry *dentry = volume->dentry; + int ret; + + _enter("%x,#%d", volume->vcookie->debug_id, len); + + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + p, len, 0); + if (ret < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret, + cachefiles_trace_setxattr_error); + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, + cachefiles_coherency_vol_set_fail); + if (ret != -ENOMEM) + cachefiles_io_error( + volume->cache, "Failed to set xattr with error %d", ret); + } else { + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, + cachefiles_coherency_vol_set_ok); + } + + _leave(" = %d", ret); + return ret == 0; +} + +/* + * Check the consistency between the backing cache and the volume cookie. + */ +int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) +{ + struct cachefiles_xattr *buf; + struct dentry *dentry = volume->dentry; + unsigned int len = volume->vcookie->coherency_len; + const void *p = volume->vcookie->coherency; + enum cachefiles_coherency_trace why; + ssize_t xlen; + int ret = -ESTALE; + + _enter(""); + + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + xlen = cachefiles_inject_read_error(); + if (xlen == 0) + xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, buf, len); + if (xlen != len) { + if (xlen < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(dentry), xlen, + cachefiles_trace_getxattr_error); + if (xlen == -EIO) + cachefiles_io_error( + volume->cache, + "Failed to read xattr with error %zd", xlen); + } + why = cachefiles_coherency_vol_check_xattr; + } else if (memcmp(buf->data, p, len) != 0) { + why = cachefiles_coherency_vol_check_cmp; + } else { + why = cachefiles_coherency_vol_check_ok; + ret = 0; + } + + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, why); + kfree(buf); + _leave(" = %d", ret); + return ret; +} diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index e1a8e92a6adb..a57c6cbee858 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -205,15 +205,22 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, size_t klen, hlen; char *key; + if (!coherency_data) + coherency_len = 0; + cache = fscache_lookup_cache(cache_name, false); if (IS_ERR(cache)) return NULL; - volume = kzalloc(sizeof(*volume), GFP_KERNEL); + volume = kzalloc(struct_size(volume, coherency, coherency_len), + GFP_KERNEL); if (!volume) goto err_cache; volume->cache = cache; + volume->coherency_len = coherency_len; + if (coherency_data) + memcpy(volume->coherency, coherency_data, coherency_len); INIT_LIST_HEAD(&volume->proc_link); INIT_WORK(&volume->work, fscache_create_volume_work); refcount_set(&volume->ref, 1); @@ -421,8 +428,11 @@ void __fscache_relinquish_volume(struct fscache_volume *volume, if (WARN_ON(test_and_set_bit(FSCACHE_VOLUME_RELINQUISHED, &volume->flags))) return; - if (invalidate) + if (invalidate) { set_bit(FSCACHE_VOLUME_INVALIDATE, &volume->flags); + } else if (coherency_data) { + memcpy(volume->coherency, coherency_data, volume->coherency_len); + } fscache_put_volume(volume, fscache_volume_put_relinquish); } diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 86b1c0db1de5..7bd35f60d19a 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -87,6 +87,8 @@ struct fscache_volume { #define FSCACHE_VOLUME_COLLIDED_WITH 2 /* Volume was collided with */ #define FSCACHE_VOLUME_ACQUIRE_PENDING 3 /* Volume is waiting to complete acquisition */ #define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ + u8 coherency_len; /* Length of the coherency data */ + u8 coherency[]; /* Coherency data */ }; /* diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index ab1376ebc3ab..1172529b5b49 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -40,6 +40,7 @@ enum fscache_why_object_killed { FSCACHE_OBJECT_NO_SPACE, FSCACHE_OBJECT_WAS_RETIRED, FSCACHE_OBJECT_WAS_CULLED, + FSCACHE_VOLUME_IS_WEIRD, }; enum cachefiles_coherency_trace { @@ -53,6 +54,11 @@ enum cachefiles_coherency_trace { cachefiles_coherency_check_xattr, cachefiles_coherency_set_fail, cachefiles_coherency_set_ok, + cachefiles_coherency_vol_check_cmp, + cachefiles_coherency_vol_check_ok, + cachefiles_coherency_vol_check_xattr, + cachefiles_coherency_vol_set_fail, + cachefiles_coherency_vol_set_ok, }; enum cachefiles_trunc_trace { @@ -103,7 +109,8 @@ enum cachefiles_error_trace { EM(FSCACHE_OBJECT_INVALIDATED, "inval") \ EM(FSCACHE_OBJECT_NO_SPACE, "no_space") \ EM(FSCACHE_OBJECT_WAS_RETIRED, "was_retired") \ - E_(FSCACHE_OBJECT_WAS_CULLED, "was_culled") + EM(FSCACHE_OBJECT_WAS_CULLED, "was_culled") \ + E_(FSCACHE_VOLUME_IS_WEIRD, "volume_weird") #define cachefiles_obj_ref_traces \ EM(cachefiles_obj_get_ioreq, "GET ioreq") \ @@ -129,7 +136,12 @@ enum cachefiles_error_trace { EM(cachefiles_coherency_check_type, "BAD type") \ EM(cachefiles_coherency_check_xattr, "BAD xatt") \ EM(cachefiles_coherency_set_fail, "SET fail") \ - E_(cachefiles_coherency_set_ok, "SET ok ") + EM(cachefiles_coherency_set_ok, "SET ok ") \ + EM(cachefiles_coherency_vol_check_cmp, "VOL BAD cmp ") \ + EM(cachefiles_coherency_vol_check_ok, "VOL OK ") \ + EM(cachefiles_coherency_vol_check_xattr,"VOL BAD xatt") \ + EM(cachefiles_coherency_vol_set_fail, "VOL SET fail") \ + E_(cachefiles_coherency_vol_set_ok, "VOL SET ok ") #define cachefiles_trunc_traces \ EM(cachefiles_trunc_dio_adjust, "DIOADJ") \ @@ -365,6 +377,32 @@ TRACE_EVENT(cachefiles_coherency, __entry->content) ); +TRACE_EVENT(cachefiles_vol_coherency, + TP_PROTO(struct cachefiles_volume *volume, + ino_t ino, + enum cachefiles_coherency_trace why), + + TP_ARGS(volume, ino, why), + + /* Note that obj may be NULL */ + TP_STRUCT__entry( + __field(unsigned int, vol ) + __field(enum cachefiles_coherency_trace, why ) + __field(u64, ino ) + ), + + TP_fast_assign( + __entry->vol = volume->vcookie->debug_id; + __entry->why = why; + __entry->ino = ino; + ), + + TP_printk("V=%08x %s i=%llx", + __entry->vol, + __print_symbolic(__entry->why, cachefiles_coherency_traces), + __entry->ino) + ); + TRACE_EVENT(cachefiles_prep_read, TP_PROTO(struct netfs_read_subrequest *sreq, enum netfs_read_source source, -- cgit v1.2.3 From 3929eca769b5a231010b4978acc61c0735da198f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 21 Oct 2021 21:58:29 +0100 Subject: fscache, cachefiles: Display stats of no-space events Add stat counters of no-space events that caused caching not to happen and display in /proc/fs/fscache/stats. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819653216.215744.17210522251617386509.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906958369.143852.7257100711818401748.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967166917.1823006.14842444049198947892.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021566184.640689.4417328329632709265.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/cache.c | 18 +++++++++++++++--- fs/cachefiles/daemon.c | 2 +- fs/cachefiles/internal.h | 11 +++++++++-- fs/cachefiles/io.c | 7 +++++-- fs/cachefiles/namei.c | 6 ++++-- fs/fscache/stats.c | 8 ++++++++ include/linux/fscache-cache.h | 6 ++++++ 7 files changed, 48 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index e2cbbc08bad9..809519286335 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -147,7 +147,7 @@ int cachefiles_add_cache(struct cachefiles_cache *cache) pr_info("File cache on %s registered\n", cache_cookie->name); /* check how much space the cache has */ - cachefiles_has_space(cache, 0, 0); + cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); cachefiles_end_secure(cache, saved_cred); _leave(" = 0 [%px]", cache->cache); return 0; @@ -175,7 +175,8 @@ error_getsec: * cache */ int cachefiles_has_space(struct cachefiles_cache *cache, - unsigned fnr, unsigned bnr) + unsigned fnr, unsigned bnr, + enum cachefiles_has_space_for reason) { struct kstatfs stats; u64 b_avail, b_writing; @@ -233,7 +234,7 @@ int cachefiles_has_space(struct cachefiles_cache *cache, ret = -ENOBUFS; if (stats.f_ffree < cache->fstop || b_avail < cache->bstop) - goto begin_cull; + goto stop_and_begin_cull; ret = 0; if (stats.f_ffree < cache->fcull || @@ -252,6 +253,17 @@ int cachefiles_has_space(struct cachefiles_cache *cache, //_leave(" = 0"); return 0; +stop_and_begin_cull: + switch (reason) { + case cachefiles_has_space_for_write: + fscache_count_no_write_space(); + break; + case cachefiles_has_space_for_create: + fscache_count_no_create_space(); + break; + default: + break; + } begin_cull: if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) { _debug("### CULL CACHE ###"); diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 45af558a696e..40a792421fc1 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -170,7 +170,7 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, return 0; /* check how much space the cache has */ - cachefiles_has_space(cache, 0, 0); + cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); /* summarise */ f_released = atomic_xchg(&cache->f_released, 0); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index abdd1b66f6b9..8dd54d9375b6 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -130,10 +130,17 @@ static inline void cachefiles_state_changed(struct cachefiles_cache *cache) * cache.c */ extern int cachefiles_add_cache(struct cachefiles_cache *cache); -extern int cachefiles_has_space(struct cachefiles_cache *cache, - unsigned fnr, unsigned bnr); extern void cachefiles_withdraw_cache(struct cachefiles_cache *cache); +enum cachefiles_has_space_for { + cachefiles_has_space_check, + cachefiles_has_space_for_write, + cachefiles_has_space_for_create, +}; +extern int cachefiles_has_space(struct cachefiles_cache *cache, + unsigned fnr, unsigned bnr, + enum cachefiles_has_space_for reason); + /* * daemon.c */ diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 6f4dce0cfc36..60b1eac2ce78 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -468,7 +468,8 @@ static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, * space, we need to see if it's fully allocated. If it's not, we may * want to cull it. */ - if (cachefiles_has_space(cache, 0, *_len / PAGE_SIZE) == 0) + if (cachefiles_has_space(cache, 0, *_len / PAGE_SIZE, + cachefiles_has_space_check) == 0) return 0; /* Enough space to simply overwrite the whole block */ pos = cachefiles_inject_read_error(); @@ -483,6 +484,7 @@ static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, return 0; /* Fully allocated */ /* Partially allocated, but insufficient space: cull. */ + fscache_count_no_write_space(); ret = cachefiles_inject_remove_error(); if (ret == 0) ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, @@ -498,7 +500,8 @@ static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, return ret; check_space: - return cachefiles_has_space(cache, 0, *_len / PAGE_SIZE); + return cachefiles_has_space(cache, 0, *_len / PAGE_SIZE, + cachefiles_has_space_for_write); } static int cachefiles_prepare_write(struct netfs_cache_resources *cres, diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index b549e9f79c01..ab3ca598acac 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -115,7 +115,8 @@ retry: /* we need to create the subdir if it doesn't exist yet */ if (d_is_negative(subdir)) { - ret = cachefiles_has_space(cache, 1, 0); + ret = cachefiles_has_space(cache, 1, 0, + cachefiles_has_space_for_create); if (ret < 0) goto mkdir_error; @@ -513,7 +514,8 @@ static bool cachefiles_create_file(struct cachefiles_object *object) struct file *file; int ret; - ret = cachefiles_has_space(object->volume->cache, 1, 0); + ret = cachefiles_has_space(object->volume->cache, 1, 0, + cachefiles_has_space_for_create); if (ret < 0) return false; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 798ee68b3e9d..db2f4e225dd9 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -42,6 +42,10 @@ atomic_t fscache_n_read; EXPORT_SYMBOL(fscache_n_read); atomic_t fscache_n_write; EXPORT_SYMBOL(fscache_n_write); +atomic_t fscache_n_no_write_space; +EXPORT_SYMBOL(fscache_n_no_write_space); +atomic_t fscache_n_no_create_space; +EXPORT_SYMBOL(fscache_n_no_create_space); /* * display the general statistics @@ -82,6 +86,10 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_relinquishes_retire), atomic_read(&fscache_n_relinquishes_dropped)); + seq_printf(m, "NoSpace: nwr=%u ncr=%u\n", + atomic_read(&fscache_n_no_write_space), + atomic_read(&fscache_n_no_create_space)); + seq_printf(m, "IO : rd=%u wr=%u\n", atomic_read(&fscache_n_read), atomic_read(&fscache_n_write)); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 3fa4902dc87c..007e47f38610 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -186,11 +186,17 @@ static inline void fscache_wait_for_objects(struct fscache_cache *cache) #ifdef CONFIG_FSCACHE_STATS extern atomic_t fscache_n_read; extern atomic_t fscache_n_write; +extern atomic_t fscache_n_no_write_space; +extern atomic_t fscache_n_no_create_space; #define fscache_count_read() atomic_inc(&fscache_n_read) #define fscache_count_write() atomic_inc(&fscache_n_write) +#define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) +#define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) #else #define fscache_count_read() do {} while(0) #define fscache_count_write() do {} while(0) +#define fscache_count_no_write_space() do {} while(0) +#define fscache_count_no_create_space() do {} while(0) #endif #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From 9f08ebc3438baaaefcc79654b330209b83397f17 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 22 Oct 2021 09:17:58 +0100 Subject: fscache, cachefiles: Display stat of culling events Add a stat counter of culling events whereby the cache backend culls a file to make space (when asked by cachefilesd in this case) and display in /proc/fs/fscache/stats. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819654165.215744.3797804661644212436.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906961387.143852.9291157239960289090.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967168266.1823006.14436200166581605746.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021567619.640689.4339228906248763197.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/namei.c | 1 + fs/fscache/stats.c | 7 +++++-- include/linux/fscache-cache.h | 3 +++ 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ab3ca598acac..9bd692870617 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -805,6 +805,7 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, if (ret < 0) goto error; + fscache_count_culled(); dput(victim); _leave(" = 0"); return 0; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index db2f4e225dd9..fc94e5e79f1c 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -46,6 +46,8 @@ atomic_t fscache_n_no_write_space; EXPORT_SYMBOL(fscache_n_no_write_space); atomic_t fscache_n_no_create_space; EXPORT_SYMBOL(fscache_n_no_create_space); +atomic_t fscache_n_culled; +EXPORT_SYMBOL(fscache_n_culled); /* * display the general statistics @@ -86,9 +88,10 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_relinquishes_retire), atomic_read(&fscache_n_relinquishes_dropped)); - seq_printf(m, "NoSpace: nwr=%u ncr=%u\n", + seq_printf(m, "NoSpace: nwr=%u ncr=%u cull=%u\n", atomic_read(&fscache_n_no_write_space), - atomic_read(&fscache_n_no_create_space)); + atomic_read(&fscache_n_no_create_space), + atomic_read(&fscache_n_culled)); seq_printf(m, "IO : rd=%u wr=%u\n", atomic_read(&fscache_n_read), diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 007e47f38610..a174cedf4d90 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -188,15 +188,18 @@ extern atomic_t fscache_n_read; extern atomic_t fscache_n_write; extern atomic_t fscache_n_no_write_space; extern atomic_t fscache_n_no_create_space; +extern atomic_t fscache_n_culled; #define fscache_count_read() atomic_inc(&fscache_n_read) #define fscache_count_write() atomic_inc(&fscache_n_write) #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) +#define fscache_count_culled() atomic_inc(&fscache_n_culled) #else #define fscache_count_read() do {} while(0) #define fscache_count_write() do {} while(0) #define fscache_count_no_write_space() do {} while(0) #define fscache_count_no_create_space() do {} while(0) +#define fscache_count_culled() do {} while(0) #endif #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From a6b5a28eb56c3f4988f7ff5290b954ba296e309a Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Sat, 14 Nov 2020 13:43:54 -0500 Subject: nfs: Convert to new fscache volume/cookie API Change the nfs filesystem to support fscache's indexing rewrite and reenable caching in nfs. The following changes have been made: (1) The fscache_netfs struct is no more, and there's no need to register the filesystem as a whole. (2) The session cookie is now an fscache_volume cookie, allocated with fscache_acquire_volume(). That takes three parameters: a string representing the "volume" in the index, a string naming the cache to use (or NULL) and a u64 that conveys coherency metadata for the volume. For nfs, I've made it render the volume name string as: "nfs,,,
,,,*<,param>[,]" (3) The fscache_cookie_def is no more and needed information is passed directly to fscache_acquire_cookie(). The cache no longer calls back into the filesystem, but rather metadata changes are indicated at other times. fscache_acquire_cookie() is passed the same keying and coherency information as before. (4) fscache_enable/disable_cookie() have been removed. Call fscache_use_cookie() and fscache_unuse_cookie() when a file is opened or closed to prevent a cache file from being culled and to keep resources to hand that are needed to do I/O. If a file is opened for writing, we invalidate it with FSCACHE_INVAL_DIO_WRITE in lieu of doing writeback to the cache, thereby making it cease caching until all currently open files are closed. This should give the same behaviour as the uptream code. Making the cache store local modifications isn't straightforward for NFS, so that's left for future patches. (5) fscache_invalidate() now needs to be given uptodate auxiliary data and a file size. It also takes a flag to indicate if this was due to a DIO write. (6) Call nfs_fscache_invalidate() with FSCACHE_INVAL_DIO_WRITE on a file to which a DIO write is made. (7) Call fscache_note_page_release() from nfs_release_page(). (8) Use a killable wait in nfs_vm_page_mkwrite() when waiting for PG_fscache to be cleared. (9) The functions to read and write data to/from the cache are stubbed out pending a conversion to use netfslib. Changes ======= ver #3: - Added missing =n fallback for nfs_fscache_release_file()[1][2]. ver #2: - Use gfpflags_allow_blocking() rather than using flag directly. - fscache_acquire_volume() now returns errors. - Remove NFS_INO_FSCACHE as it's no longer used. - Need to unuse a cookie on file-release, not inode-clear. Signed-off-by: Dave Wysochanski Co-developed-by: David Howells Signed-off-by: David Howells Tested-by: Dave Wysochanski Acked-by: Jeff Layton cc: Trond Myklebust cc: Anna Schumaker cc: linux-nfs@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/202112100804.nksO8K4u-lkp@intel.com/ [1] Link: https://lore.kernel.org/r/202112100957.2oEDT20W-lkp@intel.com/ [2] Link: https://lore.kernel.org/r/163819668938.215744.14448852181937731615.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906979003.143852.2601189243864854724.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967182112.1823006.7791504655391213379.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021575950.640689.12069642327533368467.stgit@warthog.procyon.org.uk/ # v4 --- fs/nfs/Kconfig | 2 +- fs/nfs/Makefile | 2 +- fs/nfs/client.c | 4 - fs/nfs/direct.c | 2 + fs/nfs/file.c | 13 +- fs/nfs/fscache-index.c | 140 --------------- fs/nfs/fscache.c | 434 +++++++++++----------------------------------- fs/nfs/fscache.h | 127 ++++---------- fs/nfs/inode.c | 11 +- fs/nfs/nfstrace.h | 1 - fs/nfs/super.c | 28 +-- fs/nfs/write.c | 1 + include/linux/nfs_fs.h | 1 - include/linux/nfs_fs_sb.h | 9 +- 14 files changed, 172 insertions(+), 603 deletions(-) delete mode 100644 fs/nfs/fscache-index.c (limited to 'include/linux') diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index bdc11b89eac5..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -170,7 +170,7 @@ config ROOT_NFS config NFS_FSCACHE bool "Provide NFS client caching support" - depends on NFS_FS=m && FSCACHE_OLD_API || NFS_FS=y && FSCACHE_OLD_API=y + depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y help Say Y here if you want NFS data to be cached locally on disc through the general filesystem cache manager diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 22d11fdc6deb..5f6db37f461e 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -12,7 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ export.o sysfs.o fs_context.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o -nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o +nfs-$(CONFIG_NFS_FSCACHE) += fscache.o obj-$(CONFIG_NFS_V2) += nfsv2.o nfsv2-y := nfs2super.o proc.o nfs2xdr.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 1e4dc1ab9312..8d8b85b5a641 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -183,8 +183,6 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_net = get_net(cl_init->net); clp->cl_principal = "*"; - nfs_fscache_get_client_cookie(clp); - return clp; error_cleanup: @@ -238,8 +236,6 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { - nfs_fscache_release_client_cookie(clp); - /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) rpc_shutdown_client(clp->cl_rpcclient); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 9cff8709c80a..eabfdab543c8 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -59,6 +59,7 @@ #include "internal.h" #include "iostat.h" #include "pnfs.h" +#include "fscache.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -959,6 +960,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) } else { result = requested; } + nfs_fscache_invalidate(inode, FSCACHE_INVAL_DIO_WRITE); out_release: nfs_direct_req_release(dreq); out: diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 24e7dccce355..76d76acbc594 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -84,6 +84,7 @@ nfs_file_release(struct inode *inode, struct file *filp) nfs_inc_stats(inode, NFSIOS_VFSRELEASE); nfs_file_clear_open_context(filp); + nfs_fscache_release_file(inode, filp); return 0; } EXPORT_SYMBOL_GPL(nfs_file_release); @@ -415,8 +416,7 @@ static void nfs_invalidate_page(struct page *page, unsigned int offset, return; /* Cancel any unstarted writes on this page */ nfs_wb_page_cancel(page_file_mapping(page)->host, page); - - nfs_fscache_invalidate_page(page, page->mapping->host); + wait_on_page_fscache(page); } /* @@ -475,12 +475,11 @@ static void nfs_check_dirty_writeback(struct page *page, static int nfs_launder_page(struct page *page) { struct inode *inode = page_file_mapping(page)->host; - struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n", inode->i_ino, (long long)page_offset(page)); - nfs_fscache_wait_on_page_write(nfsi, page); + wait_on_page_fscache(page); return nfs_wb_page(inode, page); } @@ -555,7 +554,11 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); /* make sure the cache has finished storing the page */ - nfs_fscache_wait_on_page_write(NFS_I(inode), page); + if (PageFsCache(page) && + wait_on_page_fscache_killable(vmf->page) < 0) { + ret = VM_FAULT_RETRY; + goto out; + } wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING, nfs_wait_bit_killable, TASK_KILLABLE); diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c deleted file mode 100644 index 573b1da9342c..000000000000 --- a/fs/nfs/fscache-index.c +++ /dev/null @@ -1,140 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* NFS FS-Cache index structure definition - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" -#include "fscache.h" - -#define NFSDBG_FACILITY NFSDBG_FSCACHE - -/* - * Define the NFS filesystem for FS-Cache. Upon registration FS-Cache sticks - * the cookie for the top-level index object for NFS into here. The top-level - * index can than have other cache objects inserted into it. - */ -struct fscache_netfs nfs_fscache_netfs = { - .name = "nfs", - .version = 0, -}; - -/* - * Register NFS for caching - */ -int nfs_fscache_register(void) -{ - return fscache_register_netfs(&nfs_fscache_netfs); -} - -/* - * Unregister NFS for caching - */ -void nfs_fscache_unregister(void) -{ - fscache_unregister_netfs(&nfs_fscache_netfs); -} - -/* - * Define the server object for FS-Cache. This is used to describe a server - * object to fscache_acquire_cookie(). It is keyed by the NFS protocol and - * server address parameters. - */ -const struct fscache_cookie_def nfs_fscache_server_index_def = { - .name = "NFS.server", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * Define the superblock object for FS-Cache. This is used to describe a - * superblock object to fscache_acquire_cookie(). It is keyed by all the NFS - * parameters that might cause a separate superblock. - */ -const struct fscache_cookie_def nfs_fscache_super_index_def = { - .name = "NFS.super", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * 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 auxiliary data - */ -static -enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size) -{ - struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = cookie_netfs_data; - - if (datalen != sizeof(auxdata)) - return FSCACHE_CHECKAUX_OBSOLETE; - - memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); - - if (memcmp(data, &auxdata, datalen) != 0) - return FSCACHE_CHECKAUX_OBSOLETE; - - return FSCACHE_CHECKAUX_OKAY; -} - -/* - * Get an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - * - The read context is passed back to NFS in the event that a data read on the - * cache fails with EIO - in which case the server must be contacted to - * retrieve the data, which requires the read context for security. - */ -static void nfs_fh_get_context(void *cookie_netfs_data, void *context) -{ - get_nfs_open_context(context); -} - -/* - * Release an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - */ -static void nfs_fh_put_context(void *cookie_netfs_data, void *context) -{ - if (context) - put_nfs_open_context(context); -} - -/* - * Define the inode object for FS-Cache. This is used to describe an inode - * object to fscache_acquire_cookie(). It is keyed by the NFS file handle for - * an inode. - * - * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime - * held in the cache auxiliary data for the data storage object with those in - * the inode struct in memory. - */ -const struct fscache_cookie_def nfs_fscache_inode_object_def = { - .name = "NFS.fh", - .type = FSCACHE_COOKIE_TYPE_DATAFILE, - .check_aux = nfs_fscache_inode_check_aux, - .get_context = nfs_fh_get_context, - .put_context = nfs_fh_put_context, -}; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index d743629e05e1..fac6438477a0 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -22,24 +22,18 @@ #define NFSDBG_FACILITY NFSDBG_FSCACHE -static struct rb_root nfs_fscache_keys = RB_ROOT; -static DEFINE_SPINLOCK(nfs_fscache_keys_lock); +#define NFS_MAX_KEY_LEN 1000 -/* - * Layout of the key for an NFS server cache object. - */ -struct nfs_server_key { - struct { - uint16_t nfsversion; /* NFS protocol version */ - uint32_t minorversion; /* NFSv4 minor version */ - uint16_t family; /* address family */ - __be16 port; /* IP port */ - } hdr; - union { - struct in_addr ipv4_addr; /* IPv4 address */ - struct in6_addr ipv6_addr; /* IPv6 address */ - }; -} __packed; +static bool nfs_append_int(char *key, int *_len, unsigned long long x) +{ + if (*_len > NFS_MAX_KEY_LEN) + return false; + if (x == 0) + key[(*_len)++] = ','; + else + *_len += sprintf(key + *_len, ",%llx", x); + return true; +} /* * Get the per-client index cookie for an NFS client if the appropriate mount @@ -47,160 +41,108 @@ struct nfs_server_key { * - We always try and get an index cookie for the client, but get filehandle * cookies on a per-superblock basis, depending on the mount flags */ -void nfs_fscache_get_client_cookie(struct nfs_client *clp) +static bool nfs_fscache_get_client_key(struct nfs_client *clp, + char *key, int *_len) { const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr; const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr; - struct nfs_server_key key; - uint16_t len = sizeof(key.hdr); - memset(&key, 0, sizeof(key)); - key.hdr.nfsversion = clp->rpc_ops->version; - key.hdr.minorversion = clp->cl_minorversion; - key.hdr.family = clp->cl_addr.ss_family; + *_len += snprintf(key + *_len, NFS_MAX_KEY_LEN - *_len, + ",%u.%u,%x", + clp->rpc_ops->version, + clp->cl_minorversion, + clp->cl_addr.ss_family); switch (clp->cl_addr.ss_family) { case AF_INET: - key.hdr.port = sin->sin_port; - key.ipv4_addr = sin->sin_addr; - len += sizeof(key.ipv4_addr); - break; + if (!nfs_append_int(key, _len, sin->sin_port) || + !nfs_append_int(key, _len, sin->sin_addr.s_addr)) + return false; + return true; case AF_INET6: - key.hdr.port = sin6->sin6_port; - key.ipv6_addr = sin6->sin6_addr; - len += sizeof(key.ipv6_addr); - break; + if (!nfs_append_int(key, _len, sin6->sin6_port) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[0]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[1]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[2]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[3])) + return false; + return true; default: printk(KERN_WARNING "NFS: Unknown network family '%d'\n", clp->cl_addr.ss_family); - clp->fscache = NULL; - return; + return false; } - - /* create a cache index for looking up filehandles */ - clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index, - &nfs_fscache_server_index_def, - &key, len, - NULL, 0, - clp, 0, true); - dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n", - clp, clp->fscache); -} - -/* - * Dispose of a per-client cookie - */ -void nfs_fscache_release_client_cookie(struct nfs_client *clp) -{ - dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n", - clp, clp->fscache); - - fscache_relinquish_cookie(clp->fscache, NULL, false); - clp->fscache = NULL; } /* - * Get the cache cookie for an NFS superblock. We have to handle - * uniquification here because the cache doesn't do it for us. + * Get the cache cookie for an NFS superblock. * * The default uniquifier is just an empty string, but it may be overridden * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent * superblock across an automount point of some nature. */ -void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) +int nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) { - struct nfs_fscache_key *key, *xkey; + struct fscache_volume *vcookie; struct nfs_server *nfss = NFS_SB(sb); - struct rb_node **p, *parent; - int diff; + unsigned int len = 3; + char *key; - nfss->fscache_key = NULL; - nfss->fscache = NULL; - if (!uniq) { - uniq = ""; - ulen = 1; + if (uniq) { + nfss->fscache_uniq = kmemdup_nul(uniq, ulen, GFP_KERNEL); + if (!nfss->fscache_uniq) + return -ENOMEM; } - key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL); + key = kmalloc(NFS_MAX_KEY_LEN + 24, GFP_KERNEL); if (!key) - return; - - key->nfs_client = nfss->nfs_client; - key->key.super.s_flags = sb->s_flags & NFS_SB_MASK; - key->key.nfs_server.flags = nfss->flags; - key->key.nfs_server.rsize = nfss->rsize; - key->key.nfs_server.wsize = nfss->wsize; - key->key.nfs_server.acregmin = nfss->acregmin; - key->key.nfs_server.acregmax = nfss->acregmax; - key->key.nfs_server.acdirmin = nfss->acdirmin; - key->key.nfs_server.acdirmax = nfss->acdirmax; - key->key.nfs_server.fsid = nfss->fsid; - key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor; - - key->key.uniq_len = ulen; - memcpy(key->key.uniquifier, uniq, ulen); - - spin_lock(&nfs_fscache_keys_lock); - p = &nfs_fscache_keys.rb_node; - parent = NULL; - while (*p) { - parent = *p; - xkey = rb_entry(parent, struct nfs_fscache_key, node); - - if (key->nfs_client < xkey->nfs_client) - goto go_left; - if (key->nfs_client > xkey->nfs_client) - goto go_right; - - diff = memcmp(&key->key, &xkey->key, sizeof(key->key)); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - - if (key->key.uniq_len == 0) - goto non_unique; - diff = memcmp(key->key.uniquifier, - xkey->key.uniquifier, - key->key.uniq_len); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - goto non_unique; - - go_left: - p = &(*p)->rb_left; - continue; - go_right: - p = &(*p)->rb_right; + return -ENOMEM; + + memcpy(key, "nfs", 3); + if (!nfs_fscache_get_client_key(nfss->nfs_client, key, &len) || + !nfs_append_int(key, &len, nfss->fsid.major) || + !nfs_append_int(key, &len, nfss->fsid.minor) || + !nfs_append_int(key, &len, sb->s_flags & NFS_SB_MASK) || + !nfs_append_int(key, &len, nfss->flags) || + !nfs_append_int(key, &len, nfss->rsize) || + !nfs_append_int(key, &len, nfss->wsize) || + !nfs_append_int(key, &len, nfss->acregmin) || + !nfs_append_int(key, &len, nfss->acregmax) || + !nfs_append_int(key, &len, nfss->acdirmin) || + !nfs_append_int(key, &len, nfss->acdirmax) || + !nfs_append_int(key, &len, nfss->client->cl_auth->au_flavor)) + goto out; + + if (ulen > 0) { + if (ulen > NFS_MAX_KEY_LEN - len) + goto out; + key[len++] = ','; + memcpy(key + len, uniq, ulen); + len += ulen; } - - rb_link_node(&key->node, parent, p); - rb_insert_color(&key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - nfss->fscache_key = key; + key[len] = 0; /* create a cache index for looking up filehandles */ - nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache, - &nfs_fscache_super_index_def, - &key->key, - sizeof(key->key) + ulen, - NULL, 0, - nfss, 0, true); + vcookie = fscache_acquire_volume(key, + NULL, /* preferred_cache */ + NULL, 0 /* coherency_data */); dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n", - nfss, nfss->fscache); - return; + nfss, vcookie); + if (IS_ERR(vcookie)) { + if (vcookie != ERR_PTR(-EBUSY)) { + kfree(key); + return PTR_ERR(vcookie); + } + pr_err("NFS: Cache volume key already in use (%s)\n", key); + vcookie = NULL; + } + nfss->fscache = vcookie; -non_unique: - spin_unlock(&nfs_fscache_keys_lock); +out: kfree(key); - nfss->fscache_key = NULL; - nfss->fscache = NULL; - printk(KERN_WARNING "NFS:" - " Cache request denied due to non-unique superblock keys\n"); + return 0; } /* @@ -213,29 +155,9 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n", nfss, nfss->fscache); - fscache_relinquish_cookie(nfss->fscache, NULL, false); + fscache_relinquish_volume(nfss->fscache, NULL, false); nfss->fscache = NULL; - - if (nfss->fscache_key) { - spin_lock(&nfs_fscache_keys_lock); - rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - kfree(nfss->fscache_key); - nfss->fscache_key = NULL; - } -} - -static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, - struct nfs_inode *nfsi) -{ - memset(auxdata, 0, sizeof(*auxdata)); - auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); + kfree(nfss->fscache_uniq); } /* @@ -254,10 +176,12 @@ void nfs_fscache_init_inode(struct inode *inode) nfs_fscache_update_auxdata(&auxdata, nfsi); nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, - &nfs_fscache_inode_object_def, - nfsi->fh.data, nfsi->fh.size, - &auxdata, sizeof(auxdata), - nfsi, nfsi->vfs_inode.i_size, false); + 0, + nfsi->fh.data, /* index_key */ + nfsi->fh.size, + &auxdata, /* aux_data */ + sizeof(auxdata), + i_size_read(&nfsi->vfs_inode)); } /* @@ -265,24 +189,15 @@ void nfs_fscache_init_inode(struct inode *inode) */ void nfs_fscache_clear_inode(struct inode *inode) { - struct nfs_fscache_inode_auxdata auxdata; struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); - nfs_fscache_update_auxdata(&auxdata, nfsi); - fscache_relinquish_cookie(cookie, &auxdata, false); + fscache_relinquish_cookie(cookie, false); nfsi->fscache = NULL; } -static bool nfs_fscache_can_enable(void *data) -{ - struct inode *inode = data; - - return !inode_is_open_for_write(inode); -} - /* * Enable or disable caching for a file that is being opened as appropriate. * The cookie is allocated when the inode is initialised, but is not enabled at @@ -307,93 +222,31 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp) struct nfs_fscache_inode_auxdata auxdata; struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); + bool open_for_write = inode_is_open_for_write(inode); if (!fscache_cookie_valid(cookie)) return; - nfs_fscache_update_auxdata(&auxdata, nfsi); - - if (inode_is_open_for_write(inode)) { + fscache_use_cookie(cookie, open_for_write); + if (open_for_write) { dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); - clear_bit(NFS_INO_FSCACHE, &nfsi->flags); - fscache_disable_cookie(cookie, &auxdata, true); - fscache_uncache_all_inode_pages(cookie, inode); - } else { - dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi); - fscache_enable_cookie(cookie, &auxdata, nfsi->vfs_inode.i_size, - nfs_fscache_can_enable, inode); - if (fscache_cookie_enabled(cookie)) - set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags); + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_invalidate(cookie, &auxdata, i_size_read(inode), + FSCACHE_INVAL_DIO_WRITE); } } EXPORT_SYMBOL_GPL(nfs_fscache_open_file); -/* - * Release the caching state associated with a page, if the page isn't busy - * interacting with the cache. - * - Returns true (can release page) or false (page busy). - */ -int nfs_fscache_release_page(struct page *page, gfp_t gfp) -{ - if (PageFsCache(page)) { - struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host); - - BUG_ON(!cookie); - dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(page->mapping->host)); - - if (!fscache_maybe_release_page(cookie, page, gfp)) - return 0; - - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); - } - - return 1; -} - -/* - * Release the caching state associated with a page if undergoing complete page - * invalidation. - */ -void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode) +void nfs_fscache_release_file(struct inode *inode, struct file *filp) { + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); - BUG_ON(!cookie); - - dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(inode)); - - fscache_wait_on_page_write(cookie, page); - - BUG_ON(!PageLocked(page)); - fscache_uncache_page(cookie, page); - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); -} - -/* - * Handle completion of a page being read from the cache. - * - Called in process (keventd) context. - */ -static void nfs_readpage_from_fscache_complete(struct page *page, - void *context, - int error) -{ - dfprintk(FSCACHE, - "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n", - page, context, error); - - /* - * If the read completes with an error, mark the page with PG_checked, - * unlock the page, and let the VM reissue the readpage. - */ - if (!error) - SetPageUptodate(page); - else - SetPageChecked(page); - unlock_page(page); + if (fscache_cookie_valid(cookie)) { + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_unuse_cookie(cookie, &auxdata, NULL); + } } /* @@ -402,8 +255,6 @@ static void nfs_readpage_from_fscache_complete(struct page *page, int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, struct inode *inode, struct page *page) { - int ret; - dfprintk(FSCACHE, "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n", nfs_i_fscache(inode), page, page->index, page->flags, inode); @@ -413,31 +264,7 @@ int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, return 1; } - ret = fscache_read_or_alloc_page(nfs_i_fscache(inode), - page, - nfs_readpage_from_fscache_complete, - ctx, - GFP_KERNEL); - - switch (ret) { - case 0: /* read BIO submitted (page in fscache) */ - dfprintk(FSCACHE, - "NFS: readpage_from_fscache: BIO submitted\n"); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); - return ret; - - case -ENOBUFS: /* inode not in cache */ - case -ENODATA: /* page not in cache */ - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - dfprintk(FSCACHE, - "NFS: readpage_from_fscache %d\n", ret); - return 1; - - default: - dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - } - return ret; + return -ENOBUFS; // TODO: Use netfslib } /* @@ -449,45 +276,10 @@ int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, struct list_head *pages, unsigned *nr_pages) { - unsigned npages = *nr_pages; - int ret; - dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n", - nfs_i_fscache(inode), npages, inode); - - ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode), - mapping, pages, nr_pages, - nfs_readpage_from_fscache_complete, - ctx, - mapping_gfp_mask(mapping)); - if (*nr_pages < npages) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, - npages); - if (*nr_pages > 0) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, - *nr_pages); - - switch (ret) { - case 0: /* read submitted to the cache for all pages */ - BUG_ON(!list_empty(pages)); - BUG_ON(*nr_pages != 0); - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: submitted\n"); - - return ret; - - case -ENOBUFS: /* some pages aren't cached and can't be */ - case -ENODATA: /* some pages aren't cached */ - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: no page: %d\n", ret); - return 1; + nfs_i_fscache(inode), *nr_pages, inode); - default: - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: ret %d\n", ret); - } - - return ret; + return -ENOBUFS; // TODO: Use netfslib } /* @@ -496,25 +288,9 @@ int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, */ void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) { - int ret; - dfprintk(FSCACHE, "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n", nfs_i_fscache(inode), page, page->index, page->flags, sync); - ret = fscache_write_page(nfs_i_fscache(inode), page, - inode->i_size, GFP_KERNEL); - dfprintk(FSCACHE, - "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", - page, page->index, page->flags, ret); - - if (ret != 0) { - fscache_uncache_page(nfs_i_fscache(inode), page); - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); - } else { - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK); - } + return; // TODO: Use netfslib } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 6754c8607230..0fa267243d26 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -12,46 +12,10 @@ #include #include #include +#include #ifdef CONFIG_NFS_FSCACHE -/* - * set of NFS FS-Cache objects that form a superblock key - */ -struct nfs_fscache_key { - struct rb_node node; - struct nfs_client *nfs_client; /* the server */ - - /* the elements of the unique key - as used by nfs_compare_super() and - * nfs_compare_mount_options() to distinguish superblocks */ - struct { - struct { - unsigned long s_flags; /* various flags - * (& NFS_MS_MASK) */ - } super; - - struct { - struct nfs_fsid fsid; - int flags; - unsigned int rsize; /* read size */ - unsigned int wsize; /* write size */ - unsigned int acregmin; /* attr cache timeouts */ - unsigned int acregmax; - unsigned int acdirmin; - unsigned int acdirmax; - } nfs_server; - - struct { - rpc_authflavor_t au_flavor; - } rpc_auth; - - /* uniquifier - can be used if nfs_server.flags includes - * NFS_MOUNT_UNSHARED */ - u8 uniq_len; - char uniquifier[0]; - } key; -}; - /* * Definition of the auxiliary data attached to NFS inode storage objects * within the cache. @@ -69,32 +33,18 @@ struct nfs_fscache_inode_auxdata { u64 change_attr; }; -/* - * fscache-index.c - */ -extern struct fscache_netfs nfs_fscache_netfs; -extern const struct fscache_cookie_def nfs_fscache_server_index_def; -extern const struct fscache_cookie_def nfs_fscache_super_index_def; -extern const struct fscache_cookie_def nfs_fscache_inode_object_def; - -extern int nfs_fscache_register(void); -extern void nfs_fscache_unregister(void); - /* * fscache.c */ -extern void nfs_fscache_get_client_cookie(struct nfs_client *); -extern void nfs_fscache_release_client_cookie(struct nfs_client *); - -extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int); +extern int nfs_fscache_get_super_cookie(struct super_block *, const char *, int); extern void nfs_fscache_release_super_cookie(struct super_block *); extern void nfs_fscache_init_inode(struct inode *); extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); +extern void nfs_fscache_release_file(struct inode *, struct file *); extern void __nfs_fscache_invalidate_page(struct page *, struct inode *); -extern int nfs_fscache_release_page(struct page *, gfp_t); extern int __nfs_readpage_from_fscache(struct nfs_open_context *, struct inode *, struct page *); @@ -103,25 +53,17 @@ extern int __nfs_readpages_from_fscache(struct nfs_open_context *, struct list_head *, unsigned *); extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int); -/* - * wait for a page to complete writing to the cache - */ -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) -{ - if (PageFsCache(page)) - fscache_wait_on_page_write(nfsi->fscache, page); -} - -/* - * release the caching state associated with a page if undergoing complete page - * invalidation - */ -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) +static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { - if (PageFsCache(page)) - __nfs_fscache_invalidate_page(page, inode); + if (PageFsCache(page)) { + if (!gfpflags_allow_blocking(gfp) || !(gfp & __GFP_FS)) + return false; + wait_on_page_fscache(page); + fscache_note_page_release(nfs_i_fscache(page->mapping->host)); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); + } + return true; } /* @@ -163,20 +105,32 @@ static inline void nfs_readpage_to_fscache(struct inode *inode, __nfs_readpage_to_fscache(inode, page, sync); } -/* - * Invalidate the contents of fscache for this inode. This will not sleep. - */ -static inline void nfs_fscache_invalidate(struct inode *inode) +static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, + struct nfs_inode *nfsi) { - fscache_invalidate(NFS_I(inode)->fscache); + memset(auxdata, 0, sizeof(*auxdata)); + auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; + auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; + auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; + auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; + + if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) + auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); } /* - * Wait for an object to finish being invalidated. + * Invalidate the contents of fscache for this inode. This will not sleep. */ -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) { - fscache_wait_on_invalidate(NFS_I(inode)->fscache); + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = NFS_I(inode); + + if (nfsi->fscache) { + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_invalidate(nfsi->fscache, &auxdata, + i_size_read(&nfsi->vfs_inode), flags); + } } /* @@ -190,28 +144,18 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server) } #else /* CONFIG_NFS_FSCACHE */ -static inline int nfs_fscache_register(void) { return 0; } -static inline void nfs_fscache_unregister(void) {} - -static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {} -static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {} - static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {} static inline void nfs_fscache_init_inode(struct inode *inode) {} static inline void nfs_fscache_clear_inode(struct inode *inode) {} static inline void nfs_fscache_open_file(struct inode *inode, struct file *filp) {} +static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {} static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { return 1; /* True: may release page */ } -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) {} -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) {} - static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, struct inode *inode, struct page *page) @@ -230,8 +174,7 @@ static inline void nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) {} -static inline void nfs_fscache_invalidate(struct inode *inode) {} -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) {} +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} static inline const char *nfs_server_fscache_state(struct nfs_server *server) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index fda530d5e764..a918c3a834b6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -209,7 +209,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) - nfs_fscache_invalidate(inode); + nfs_fscache_invalidate(inode, 0); flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); nfsi->cache_validity |= flags; @@ -1289,6 +1289,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map { int ret; + nfs_fscache_invalidate(inode, 0); if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); @@ -1300,7 +1301,6 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); - nfs_fscache_wait_on_invalidate(inode); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, @@ -2374,10 +2374,6 @@ static int __init init_nfs_fs(void) if (err < 0) goto out9; - err = nfs_fscache_register(); - if (err < 0) - goto out8; - err = nfsiod_start(); if (err) goto out7; @@ -2429,8 +2425,6 @@ out5: out6: nfsiod_stop(); out7: - nfs_fscache_unregister(); -out8: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); @@ -2445,7 +2439,6 @@ static void __exit exit_nfs_fs(void) nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); - nfs_fscache_unregister(); unregister_pernet_subsys(&nfs_net_ops); rpc_proc_unregister(&init_net, "nfs"); unregister_nfs_fs(); diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index b3aee261801e..317ce27bdc4b 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -42,7 +42,6 @@ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ { BIT(NFS_INO_FSCACHE), "FSCACHE" }, \ - { BIT(NFS_INO_FSCACHE_LOCK), "FSCACHE_LOCK" }, \ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \ diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3aced401735c..6ab5eeb000dc 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1204,42 +1204,42 @@ static int nfs_compare_super(struct super_block *sb, struct fs_context *fc) } #ifdef CONFIG_NFS_FSCACHE -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { struct nfs_server *nfss = NFS_SB(sb); char *uniq = NULL; int ulen = 0; - nfss->fscache_key = NULL; nfss->fscache = NULL; if (!ctx) - return; + return 0; if (ctx->clone_data.sb) { struct nfs_server *mnt_s = NFS_SB(ctx->clone_data.sb); if (!(mnt_s->options & NFS_OPTION_FSCACHE)) - return; - if (mnt_s->fscache_key) { - uniq = mnt_s->fscache_key->key.uniquifier; - ulen = mnt_s->fscache_key->key.uniq_len; + return 0; + if (mnt_s->fscache_uniq) { + uniq = mnt_s->fscache_uniq; + ulen = strlen(uniq); } } else { if (!(ctx->options & NFS_OPTION_FSCACHE)) - return; + return 0; if (ctx->fscache_uniq) { uniq = ctx->fscache_uniq; ulen = strlen(ctx->fscache_uniq); } } - nfs_fscache_get_super_cookie(sb, uniq, ulen); + return nfs_fscache_get_super_cookie(sb, uniq, ulen); } #else -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { + return 0; } #endif @@ -1299,7 +1299,9 @@ int nfs_get_tree_common(struct fs_context *fc) s->s_blocksize_bits = bsize; s->s_blocksize = 1U << bsize; } - nfs_get_cache_cookie(s, ctx); + error = nfs_get_cache_cookie(s, ctx); + if (error < 0) + goto error_splat_super; } error = nfs_get_root(s, fc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9b7619ce17a7..2b322170372a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -294,6 +294,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); out: spin_unlock(&inode->i_lock); + nfs_fscache_invalidate(inode, 0); } /* A writeback failed: mark the page as bad, and invalidate the page cache */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 05f249f20f55..00835bacd236 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -275,7 +275,6 @@ struct nfs4_copy_state { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ #define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2a9acbfe00f0..77b2dba27bbb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -120,11 +120,6 @@ struct nfs_client { * This is used to generate the mv0 callback address. */ char cl_ipaddr[48]; - -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; /* client index cache cookie */ -#endif - struct net *cl_net; struct list_head pending_cb_stateids; }; @@ -194,8 +189,8 @@ struct nfs_server { struct nfs_auth_info auth_info; /* parsed auth flavors */ #ifdef CONFIG_NFS_FSCACHE - struct nfs_fscache_key *fscache_key; /* unique key for superblock */ - struct fscache_cookie *fscache; /* superblock cookie */ + struct fscache_volume *fscache; /* superblock cookie */ + char *fscache_uniq; /* Uniquifier (or NULL) */ #endif u32 pnfs_blksize; /* layout_blksize attr */ -- cgit v1.2.3 From 16f2f4e679cfdaa9552574484f104014908a76c6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 27 Aug 2021 15:19:34 +0100 Subject: nfs: Implement cache I/O by accessing the cache directly Move NFS to using fscache DIO API instead of the old upstream I/O API as that has been removed. This is a stopgap solution as the intention is that at sometime in the future, the cache will move to using larger blocks and won't be able to store individual pages in order to deal with the potential for data corruption due to the backing filesystem being able insert/remove bridging blocks of zeros into its extent list[1]. NFS then reads and writes cache pages synchronously and one page at a time. The preferred change would be to use the netfs lib, but the new I/O API can be used directly. It's just that as the cache now needs to track data for itself, caching blocks may exceed page size... This code is somewhat borrowed from my "fallback I/O" patchset[2]. Changes ======= ver #3: - Restore lost =n fallback for nfs_fscache_release_page()[2]. Signed-off-by: David Howells Tested-by: Dave Wysochanski Acked-by: Jeff Layton cc: Trond Myklebust cc: Anna Schumaker cc: linux-nfs@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YO17ZNOcq+9PajfQ@mit.edu [1] Link: https://lore.kernel.org/r/202112100957.2oEDT20W-lkp@intel.com/ [2] Link: https://lore.kernel.org/r/163189108292.2509237.12615909591150927232.stgit@warthog.procyon.org.uk/ [2] Link: https://lore.kernel.org/r/163906981318.143852.17220018647843475985.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967184451.1823006.6450645559828329590.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021577632.640689.11069627070150063812.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/io.c | 8 +++ fs/nfs/fscache.c | 126 +++++++++++++++++++++++++++++++++++++++--------- fs/nfs/fscache.h | 52 +++++--------------- fs/nfs/read.c | 25 +++------- fs/nfs/write.c | 7 ++- include/linux/fscache.h | 28 +++++++++++ 6 files changed, 163 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/io.c b/fs/fscache/io.c index bed7628a5a9d..7a769ea57720 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -150,6 +150,14 @@ int __fscache_begin_read_operation(struct netfs_cache_resources *cres, } EXPORT_SYMBOL(__fscache_begin_read_operation); +int __fscache_begin_write_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + return fscache_begin_operation(cres, cookie, FSCACHE_WANT_PARAMS, + fscache_access_io_write); +} +EXPORT_SYMBOL(__fscache_begin_write_operation); + /** * fscache_set_page_dirty - Mark page dirty and pin a cache object for writeback * @page: The page being dirtied diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index fac6438477a0..cfe901650ab0 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -249,48 +249,128 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp) } } +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + +/* + * Fallback page reading interface. + */ +static int fscache_fallback_read_page(struct inode *inode, struct page *page) +{ + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + int ret; + + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + + ret = fscache_begin_read_operation(&cres, cookie); + if (ret < 0) + return ret; + + ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL, + NULL, NULL); + fscache_end_operation(&cres); + return ret; +} + +/* + * Fallback page writing interface. + */ +static int fscache_fallback_write_page(struct inode *inode, struct page *page, + bool no_space_allocated_yet) +{ + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + loff_t start = page_offset(page); + size_t len = PAGE_SIZE; + int ret; + + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + + ret = fscache_begin_write_operation(&cres, cookie); + if (ret < 0) + return ret; + + ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode), + no_space_allocated_yet); + if (ret == 0) + ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL); + fscache_end_operation(&cres); + return ret; +} + /* * Retrieve a page from fscache */ -int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, struct page *page) +int __nfs_readpage_from_fscache(struct inode *inode, struct page *page) { + int ret; + dfprintk(FSCACHE, "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n", nfs_i_fscache(inode), page, page->index, page->flags, inode); if (PageChecked(page)) { + dfprintk(FSCACHE, "NFS: readpage_from_fscache: PageChecked\n"); ClearPageChecked(page); return 1; } - return -ENOBUFS; // TODO: Use netfslib -} - -/* - * Retrieve a set of pages from fscache - */ -int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n", - nfs_i_fscache(inode), *nr_pages, inode); + ret = fscache_fallback_read_page(inode, page); + if (ret < 0) { + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); + dfprintk(FSCACHE, + "NFS: readpage_from_fscache failed %d\n", ret); + SetPageChecked(page); + return ret; + } - return -ENOBUFS; // TODO: Use netfslib + /* Read completed synchronously */ + dfprintk(FSCACHE, "NFS: readpage_from_fscache: read successful\n"); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); + SetPageUptodate(page); + return 0; } /* - * Store a newly fetched page in fscache - * - PG_fscache must be set on the page + * Store a newly fetched page in fscache. We can be certain there's no page + * stored in the cache as yet otherwise we would've read it from there. */ -void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) +void __nfs_readpage_to_fscache(struct inode *inode, struct page *page) { + int ret; + dfprintk(FSCACHE, - "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n", - nfs_i_fscache(inode), page, page->index, page->flags, sync); + "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx))\n", + nfs_i_fscache(inode), page, page->index, page->flags); - return; // TODO: Use netfslib + ret = fscache_fallback_write_page(inode, page, true); + + dfprintk(FSCACHE, + "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", + page, page->index, page->flags, ret); + + if (ret != 0) { + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); + } else { + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK); + } } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 0fa267243d26..e0220fc40366 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -44,14 +44,10 @@ extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); extern void nfs_fscache_release_file(struct inode *, struct file *); -extern void __nfs_fscache_invalidate_page(struct page *, struct inode *); - -extern int __nfs_readpage_from_fscache(struct nfs_open_context *, - struct inode *, struct page *); -extern int __nfs_readpages_from_fscache(struct nfs_open_context *, - struct inode *, struct address_space *, - struct list_head *, unsigned *); -extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int); +extern int __nfs_readpage_from_fscache(struct inode *, struct page *); +extern void __nfs_read_completion_to_fscache(struct nfs_pgio_header *hdr, + unsigned long bytes); +extern void __nfs_readpage_to_fscache(struct inode *, struct page *); static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { @@ -69,27 +65,11 @@ static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) /* * Retrieve a page from an inode data storage object. */ -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, +static inline int nfs_readpage_from_fscache(struct inode *inode, struct page *page) { if (NFS_I(inode)->fscache) - return __nfs_readpage_from_fscache(ctx, inode, page); - return -ENOBUFS; -} - -/* - * Retrieve a set of pages from an inode data storage object. - */ -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - if (NFS_I(inode)->fscache) - return __nfs_readpages_from_fscache(ctx, inode, mapping, pages, - nr_pages); + return __nfs_readpage_from_fscache(inode, page); return -ENOBUFS; } @@ -98,11 +78,10 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, * in the cache. */ static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, - int sync) + struct page *page) { - if (PageFsCache(page)) - __nfs_readpage_to_fscache(inode, page, sync); + if (NFS_I(inode)->fscache) + __nfs_readpage_to_fscache(inode, page); } static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, @@ -156,22 +135,13 @@ static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { return 1; /* True: may release page */ } -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, +static inline int nfs_readpage_from_fscache(struct inode *inode, struct page *page) { return -ENOBUFS; } -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - return -ENOBUFS; -} static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, int sync) {} + struct page *page) {} static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} diff --git a/fs/nfs/read.c b/fs/nfs/read.c index d11af2a9299c..eb00229c1a50 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -123,7 +123,7 @@ static void nfs_readpage_release(struct nfs_page *req, int error) struct address_space *mapping = page_file_mapping(page); if (PageUptodate(page)) - nfs_readpage_to_fscache(inode, page, 0); + nfs_readpage_to_fscache(inode, page); else if (!PageError(page) && !PagePrivate(page)) generic_error_remove_page(mapping, page); unlock_page(page); @@ -305,6 +305,12 @@ readpage_async_filler(void *data, struct page *page) aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE); + if (!IS_SYNC(page->mapping->host)) { + error = nfs_readpage_from_fscache(page->mapping->host, page); + if (error == 0) + goto out_unlock; + } + new = nfs_create_request(desc->ctx, page, 0, aligned_len); if (IS_ERR(new)) goto out_error; @@ -320,6 +326,7 @@ readpage_async_filler(void *data, struct page *page) return 0; out_error: error = PTR_ERR(new); +out_unlock: unlock_page(page); out: return error; @@ -366,12 +373,6 @@ int nfs_readpage(struct file *file, struct page *page) desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); xchg(&desc.ctx->error, 0); - if (!IS_SYNC(inode)) { - ret = nfs_readpage_from_fscache(desc.ctx, inode, page); - if (ret == 0) - goto out_wait; - } - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); @@ -381,7 +382,6 @@ int nfs_readpage(struct file *file, struct page *page) nfs_pageio_complete_read(&desc.pgio); ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; -out_wait: if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) @@ -419,14 +419,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping, } else desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); - /* attempt to read as many of the pages as possible from the cache - * - this returns -ENOBUFS immediately if the cookie is negative - */ - ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping, - pages, &nr_pages); - if (ret == 0) - goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); @@ -434,7 +426,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping, nfs_pageio_complete_read(&desc.pgio); -read_complete: put_nfs_open_context(desc.ctx); out: trace_nfs_aop_readahead_done(inode, nr_pages, ret); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2b322170372a..987a187bd39a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2126,8 +2126,11 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, if (PagePrivate(page)) return -EBUSY; - if (!nfs_fscache_release_page(page, GFP_KERNEL)) - return -EBUSY; + if (PageFsCache(page)) { + if (mode == MIGRATE_ASYNC) + return -EBUSY; + wait_on_page_fscache(page); + } return migrate_page(mapping, newpage, page, mode); } diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 7bd35f60d19a..ede50406bcb0 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -168,6 +168,7 @@ extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); +extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, loff_t, size_t, loff_t, netfs_io_terminated_t, void *, @@ -499,6 +500,33 @@ int fscache_read(struct netfs_cache_resources *cres, term_func, term_func_priv); } +/** + * fscache_begin_write_operation - Begin a write operation for the netfs lib + * @cres: The cache resources for the write being performed + * @cookie: The cookie representing the cache object + * + * Begin a write operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. + * + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. + * + * Returns: + * * 0 - Success + * * -ENOBUFS - No caching available + * * Other error code from the cache, such as -ENOMEM. + */ +static inline +int fscache_begin_write_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_write_operation(cres, cookie); + return -ENOBUFS; +} + /** * fscache_write - Start a write to the cache. * @cres: The cache resources to use -- cgit v1.2.3