From 182d919b84902eece162c63ed3d476c8016b4197 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 19 Feb 2015 23:47:31 +0000 Subject: FS-Cache: Count culled objects and objects rejected due to lack of space Count the number of objects that get culled by the cache backend and the number of objects that the cache backend declines to instantiate due to lack of space in the cache. These numbers are made available through /proc/fs/fscache/stats Signed-off-by: David Howells Reviewed-by: Steve Dickson Acked-by: Jeff Layton --- fs/fscache/object.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'fs/fscache/object.c') diff --git a/fs/fscache/object.c b/fs/fscache/object.c index da032daf0e0d..12bb468bf0ae 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -1016,3 +1016,50 @@ static const struct fscache_state *fscache_update_object(struct fscache_object * _leave(""); return transit_to(WAIT_FOR_CMD); } + +/** + * fscache_object_retrying_stale - Note retrying stale object + * @object: The object that will be retried + * + * Note that an object lookup found an on-disk object that was adjudged to be + * stale and has been deleted. The lookup will be retried. + */ +void fscache_object_retrying_stale(struct fscache_object *object) +{ + fscache_stat(&fscache_n_cache_no_space_reject); +} +EXPORT_SYMBOL(fscache_object_retrying_stale); + +/** + * fscache_object_mark_killed - Note that an object was killed + * @object: The object that was culled + * @why: The reason the object was killed. + * + * Note that an object was killed. Returns true if the object was + * already marked killed, false if it wasn't. + */ +void fscache_object_mark_killed(struct fscache_object *object, + enum fscache_why_object_killed why) +{ + if (test_and_set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags)) { + pr_err("Error: Object already killed by cache [%s]\n", + object->cache->identifier); + return; + } + + switch (why) { + case FSCACHE_OBJECT_NO_SPACE: + fscache_stat(&fscache_n_cache_no_space_reject); + break; + case FSCACHE_OBJECT_IS_STALE: + fscache_stat(&fscache_n_cache_stale_objects); + break; + case FSCACHE_OBJECT_WAS_RETIRED: + fscache_stat(&fscache_n_cache_retired_objects); + break; + case FSCACHE_OBJECT_WAS_CULLED: + fscache_stat(&fscache_n_cache_culled_objects); + break; + } +} +EXPORT_SYMBOL(fscache_object_mark_killed); -- cgit v1.2.3 From 6515d1dbf424c5c3b94d44e9c7f581026e7fc0d3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 25 Feb 2015 11:53:57 +0000 Subject: FS-Cache: Handle a new operation submitted against a killed object Reject new operations that are being submitted against an object if that object has failed its lookup or creation states or has been killed by the cache backend for some other reason, such as having been culled. Signed-off-by: David Howells Reviewed-by: Steve Dickson Acked-by: Jeff Layton --- fs/fscache/object.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/fscache/object.c') diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 12bb468bf0ae..9b79fc9a1464 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -610,6 +610,8 @@ static const struct fscache_state *fscache_lookup_failure(struct fscache_object object->cache->ops->lookup_complete(object); fscache_stat_d(&fscache_n_cop_lookup_complete); + set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags); + cookie = object->cookie; set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) -- cgit v1.2.3 From f09b443d0e09f37121c55d7f83056f6ebff6ab4f Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Feb 2015 10:05:28 +0000 Subject: FS-Cache: Synchronise object death state change vs operation submission When an object is being marked as no longer live, do this under the object spinlock to prevent a race with operation submission targeted on that object. The problem occurs due to the following pair of intertwined sequences when the cache tries to create an object that would take it over the hard available space limit: NETFS INTERFACE =============== (A) The netfs calls fscache_acquire_cookie(). object creation is deferred to the object state machine and the netfs is allowed to continue. OBJECT STATE MACHINE KTHREAD ============================ (1) The object is looked up on disk by fscache_look_up_object() calling cachefiles_walk_to_object(). The latter finds that the object is not yet represented on disk and calls fscache_object_lookup_negative(). (2) fscache_object_lookup_negative() sets FSCACHE_COOKIE_NO_DATA_YET and clears FSCACHE_COOKIE_LOOKING_UP, thus allowing the netfs to start queuing read operations. (B) The netfs calls fscache_read_or_alloc_pages(). This calls fscache_wait_for_deferred_lookup() which sees FSCACHE_COOKIE_LOOKING_UP become clear, allowing the read to begin. (C) A read operation is set up and passed to fscache_submit_op() to deal with. (3) cachefiles_walk_to_object() calls cachefiles_has_space(), which fails (or one of the file operations to create stuff fails). cachefiles returns an error to fscache. (4) fscache_look_up_object() transits to the LOOKUP_FAILURE state, (5) fscache_lookup_failure() sets FSCACHE_OBJECT_LOOKED_UP and FSCACHE_COOKIE_UNAVAILABLE and clears FSCACHE_COOKIE_LOOKING_UP then transits to the KILL_OBJECT state. (6) fscache_kill_object() clears FSCACHE_OBJECT_IS_LIVE in an attempt to reject any further requests from the netfs. (7) object->n_ops is examined and found to be 0. fscache_kill_object() transits to the DROP_OBJECT state. (D) fscache_submit_op() locks the object spinlock, sees if it can dispatch the op immediately by calling fscache_object_is_active() - which fails since FSCACHE_OBJECT_IS_AVAILABLE has not yet been set. (E) fscache_submit_op() then tests FSCACHE_OBJECT_LOOKED_UP - which is set. It then queues the object and increments object->n_ops. (8) fscache_drop_object() releases the object and eventually fscache_put_object() calls cachefiles_put_object() which suffers an assertion failure here: ASSERTCMP(object->fscache.n_ops, ==, 0); Locking the object spinlock in step (6) around the clearance of FSCACHE_OBJECT_IS_LIVE ensures that the the decision trees in fscache_submit_op() and fscache_submit_exclusive_op() don't see the IS_LIVE flag being cleared mid-decision: either the op is queued before step (7) - in which case fscache_kill_object() will see n_ops>0 and will deal with the op - or the op will be rejected. This, combined with rejecting op submission if the target object is dying, fix the problem. The problem shows up as the following oops: CacheFiles: Assertion failed CacheFiles: 1 == 0 is false ------------[ cut here ]------------ kernel BUG at ../fs/cachefiles/interface.c:339! ... RIP: 0010:[] [] cachefiles_put_object+0x2a4/0x301 [cachefiles] ... Call Trace: [] fscache_put_object+0x18/0x21 [fscache] [] fscache_object_work_func+0x3ba/0x3c9 [fscache] [] process_one_work+0x226/0x441 [] worker_thread+0x273/0x36b [] ? rescuer_thread+0x2e1/0x2e1 [] kthread+0x10e/0x116 [] ? kthread_create_on_node+0x1bb/0x1bb [] ret_from_fork+0x7c/0xb0 [] ? kthread_create_on_node+0x1bb/0x1bb Signed-off-by: David Howells Reviewed-by: Steve Dickson Acked-by: Jeff Layton --- fs/fscache/object.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'fs/fscache/object.c') diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 9b79fc9a1464..40049f7505f0 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -327,6 +327,17 @@ void fscache_object_init(struct fscache_object *object, } EXPORT_SYMBOL(fscache_object_init); +/* + * Mark the object as no longer being live, making sure that we synchronise + * against op submission. + */ +static inline void fscache_mark_object_dead(struct fscache_object *object) +{ + spin_lock(&object->lock); + clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); + spin_unlock(&object->lock); +} + /* * Abort object initialisation before we start it. */ @@ -631,7 +642,7 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob _enter("{OBJ%x,%d,%d},%d", object->debug_id, object->n_ops, object->n_children, event); - clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); + fscache_mark_object_dead(object); object->oob_event_mask = 0; if (list_empty(&object->dependents) && @@ -976,13 +987,13 @@ static const struct fscache_state *_fscache_invalidate_object(struct fscache_obj return transit_to(UPDATE_OBJECT); nomem: - clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); + fscache_mark_object_dead(object); fscache_unuse_cookie(object); _leave(" [ENOMEM]"); return transit_to(KILL_OBJECT); submit_op_failed: - clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); + fscache_mark_object_dead(object); spin_unlock(&cookie->lock); fscache_unuse_cookie(object); kfree(op); -- cgit v1.2.3 From d3b97ca4a99e4e6c78f5a21c968eadf5c8ba9971 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Feb 2015 10:05:29 +0000 Subject: FS-Cache: The operation cancellation method needs calling in more places Any time an incomplete operation is cancelled, the operation cancellation function needs to be called to clean up. This is currently being passed directly to some of the functions that might want to call it, but not all. Instead, pass the cancellation method pointer to the fscache_operation_init() and have that cache it in the operation struct. Further, plug in a dummy cancellation handler if the caller declines to set one as this allows us to call the function unconditionally (the extra overhead isn't worth bothering about as we don't expect to be calling this typically). The cancellation method must thence be called everywhere the CANCELLED state is set. Note that we call it *before* setting the CANCELLED state such that the method can use the old state value to guide its operation. fscache_do_cancel_retrieval() needs moving higher up in the sources so that the init function can use it now. Without this, the following oops may be seen: FS-Cache: Assertion failed FS-Cache: 3 == 0 is false ------------[ cut here ]------------ kernel BUG at ../fs/fscache/page.c:261! ... RIP: 0010:[] fscache_release_retrieval_op+0x77/0x100 [] fscache_put_operation+0x114/0x2da [] __fscache_read_or_alloc_pages+0x358/0x3b3 [] __nfs_readpages_from_fscache+0x59/0xbf [nfs] [] nfs_readpages+0x10c/0x185 [nfs] [] ? alloc_pages_current+0x119/0x13e [] ? __page_cache_alloc+0xfb/0x10a [] __do_page_cache_readahead+0x188/0x22c [] ondemand_readahead+0x29e/0x2af [] page_cache_sync_readahead+0x38/0x3a [] generic_file_read_iter+0x1a2/0x55a [] ? nfs_revalidate_mapping+0xd6/0x288 [nfs] [] nfs_file_read+0x49/0x70 [nfs] [] new_sync_read+0x78/0x9c [] __vfs_read+0x13/0x38 [] vfs_read+0x95/0x121 [] SyS_read+0x4c/0x8a [] system_call_fastpath+0x12/0x17 The assertion is showing that the remaining number of pages (n_pages) is not 0 when the operation is being released. Signed-off-by: David Howells Reviewed-by: Steve Dickson Acked-by: Jeff Layton --- fs/fscache/object.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/fscache/object.c') diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 40049f7505f0..9e792e30f4db 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -961,7 +961,8 @@ static const struct fscache_state *_fscache_invalidate_object(struct fscache_obj if (!op) goto nomem; - fscache_operation_init(op, object->cache->ops->invalidate_object, NULL); + fscache_operation_init(op, object->cache->ops->invalidate_object, + NULL, NULL); op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE) | (1 << FSCACHE_OP_UNUSE_COOKIE); -- cgit v1.2.3