diff options
64 files changed, 852 insertions, 753 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 798dc538529c..d42970b10a22 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2075,6 +2075,7 @@ M: Jens Axboe <axboe@kernel.dk> T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: block/ +F: kernel/trace/blktrace.c BLOCK2MTD DRIVER M: Joern Engel <joern@lazybastard.org> diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 5cbd5d9ea61d..0436c21db7f2 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -361,7 +361,7 @@ static void bio_integrity_verify_fn(struct work_struct *work) /* Restore original bio completion handler */ bio->bi_end_io = bip->bip_end_io; - bio_endio_nodec(bio, error); + bio_endio(bio, error); } /** @@ -388,7 +388,7 @@ void bio_integrity_endio(struct bio *bio, int error) */ if (error) { bio->bi_end_io = bip->bip_end_io; - bio_endio_nodec(bio, error); + bio_endio(bio, error); return; } diff --git a/block/bio.c b/block/bio.c index f66a4eae16ee..259197d97de1 100644 --- a/block/bio.c +++ b/block/bio.c @@ -270,8 +270,8 @@ void bio_init(struct bio *bio) { memset(bio, 0, sizeof(*bio)); bio->bi_flags = 1 << BIO_UPTODATE; - atomic_set(&bio->bi_remaining, 1); - atomic_set(&bio->bi_cnt, 1); + atomic_set(&bio->__bi_remaining, 1); + atomic_set(&bio->__bi_cnt, 1); } EXPORT_SYMBOL(bio_init); @@ -292,8 +292,8 @@ void bio_reset(struct bio *bio) __bio_free(bio); memset(bio, 0, BIO_RESET_BYTES); - bio->bi_flags = flags|(1 << BIO_UPTODATE); - atomic_set(&bio->bi_remaining, 1); + bio->bi_flags = flags | (1 << BIO_UPTODATE); + atomic_set(&bio->__bi_remaining, 1); } EXPORT_SYMBOL(bio_reset); @@ -303,6 +303,17 @@ static void bio_chain_endio(struct bio *bio, int error) bio_put(bio); } +/* + * Increment chain count for the bio. Make sure the CHAIN flag update + * is visible before the raised count. + */ +static inline void bio_inc_remaining(struct bio *bio) +{ + bio->bi_flags |= (1 << BIO_CHAIN); + smp_mb__before_atomic(); + atomic_inc(&bio->__bi_remaining); +} + /** * bio_chain - chain bio completions * @bio: the target bio @@ -320,7 +331,7 @@ void bio_chain(struct bio *bio, struct bio *parent) bio->bi_private = parent; bio->bi_end_io = bio_chain_endio; - atomic_inc(&parent->bi_remaining); + bio_inc_remaining(parent); } EXPORT_SYMBOL(bio_chain); @@ -524,13 +535,17 @@ EXPORT_SYMBOL(zero_fill_bio); **/ void bio_put(struct bio *bio) { - BIO_BUG_ON(!atomic_read(&bio->bi_cnt)); - - /* - * last put frees it - */ - if (atomic_dec_and_test(&bio->bi_cnt)) + if (!bio_flagged(bio, BIO_REFFED)) bio_free(bio); + else { + BIO_BUG_ON(!atomic_read(&bio->__bi_cnt)); + + /* + * last put frees it + */ + if (atomic_dec_and_test(&bio->__bi_cnt)) + bio_free(bio); + } } EXPORT_SYMBOL(bio_put); @@ -1741,6 +1756,25 @@ void bio_flush_dcache_pages(struct bio *bi) EXPORT_SYMBOL(bio_flush_dcache_pages); #endif +static inline bool bio_remaining_done(struct bio *bio) +{ + /* + * If we're not chaining, then ->__bi_remaining is always 1 and + * we always end io on the first invocation. + */ + if (!bio_flagged(bio, BIO_CHAIN)) + return true; + + BUG_ON(atomic_read(&bio->__bi_remaining) <= 0); + + if (atomic_dec_and_test(&bio->__bi_remaining)) { + clear_bit(BIO_CHAIN, &bio->bi_flags); + return true; + } + + return false; +} + /** * bio_endio - end I/O on a bio * @bio: bio @@ -1758,15 +1792,13 @@ EXPORT_SYMBOL(bio_flush_dcache_pages); void bio_endio(struct bio *bio, int error) { while (bio) { - BUG_ON(atomic_read(&bio->bi_remaining) <= 0); - if (error) clear_bit(BIO_UPTODATE, &bio->bi_flags); else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) error = -EIO; - if (!atomic_dec_and_test(&bio->bi_remaining)) - return; + if (unlikely(!bio_remaining_done(bio))) + break; /* * Need to have a real endio function for chained bios, @@ -1790,21 +1822,6 @@ void bio_endio(struct bio *bio, int error) EXPORT_SYMBOL(bio_endio); /** - * bio_endio_nodec - end I/O on a bio, without decrementing bi_remaining - * @bio: bio - * @error: error, if any - * - * For code that has saved and restored bi_end_io; thing hard before using this - * function, probably you should've cloned the entire bio. - **/ -void bio_endio_nodec(struct bio *bio, int error) -{ - atomic_inc(&bio->bi_remaining); - bio_endio(bio, error); -} -EXPORT_SYMBOL(bio_endio_nodec); - -/** * bio_split - split a bio * @bio: bio to split * @sectors: number of sectors to split from the front of @bio diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 0ac817b750db..6e43fa355e71 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -9,6 +9,10 @@ * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> + * + * For policy-specific per-blkcg data: + * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> + * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> @@ -26,8 +30,7 @@ static DEFINE_MUTEX(blkcg_pol_mutex); -struct blkcg blkcg_root = { .cfq_weight = 2 * CFQ_WEIGHT_DEFAULT, - .cfq_leaf_weight = 2 * CFQ_WEIGHT_DEFAULT, }; +struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; @@ -823,6 +826,8 @@ static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; + struct cgroup_subsys_state *ret; + int i; if (!parent_css) { blkcg = &blkcg_root; @@ -830,17 +835,49 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) } blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); - if (!blkcg) - return ERR_PTR(-ENOMEM); + if (!blkcg) { + ret = ERR_PTR(-ENOMEM); + goto free_blkcg; + } + + for (i = 0; i < BLKCG_MAX_POLS ; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + struct blkcg_policy_data *cpd; + + /* + * If the policy hasn't been attached yet, wait for it + * to be attached before doing anything else. Otherwise, + * check if the policy requires any specific per-cgroup + * data: if it does, allocate and initialize it. + */ + if (!pol || !pol->cpd_size) + continue; + + BUG_ON(blkcg->pd[i]); + cpd = kzalloc(pol->cpd_size, GFP_KERNEL); + if (!cpd) { + ret = ERR_PTR(-ENOMEM); + goto free_pd_blkcg; + } + blkcg->pd[i] = cpd; + cpd->plid = i; + pol->cpd_init_fn(blkcg); + } - blkcg->cfq_weight = CFQ_WEIGHT_DEFAULT; - blkcg->cfq_leaf_weight = CFQ_WEIGHT_DEFAULT; done: spin_lock_init(&blkcg->lock); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&blkcg->blkg_list); return &blkcg->css; + +free_pd_blkcg: + for (i--; i >= 0; i--) + kfree(blkcg->pd[i]); + +free_blkcg: + kfree(blkcg); + return ret; } /** @@ -958,8 +995,10 @@ int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol) { LIST_HEAD(pds); + LIST_HEAD(cpds); struct blkcg_gq *blkg, *new_blkg; - struct blkg_policy_data *pd, *n; + struct blkg_policy_data *pd, *nd; + struct blkcg_policy_data *cpd, *cnd; int cnt = 0, ret; bool preloaded; @@ -1003,7 +1042,10 @@ int blkcg_activate_policy(struct request_queue *q, spin_unlock_irq(q->queue_lock); - /* allocate policy_data for all existing blkgs */ + /* + * Allocate per-blkg and per-blkcg policy data + * for all existing blkgs. + */ while (cnt--) { pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node); if (!pd) { @@ -1011,26 +1053,50 @@ int blkcg_activate_policy(struct request_queue *q, goto out_free; } list_add_tail(&pd->alloc_node, &pds); + + if (!pol->cpd_size) + continue; + cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node); + if (!cpd) { + ret = -ENOMEM; + goto out_free; + } + list_add_tail(&cpd->alloc_node, &cpds); } /* - * Install the allocated pds. With @q bypassing, no new blkg + * Install the allocated pds and cpds. With @q bypassing, no new blkg * should have been created while the queue lock was dropped. */ spin_lock_irq(q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { - if (WARN_ON(list_empty(&pds))) { + if (WARN_ON(list_empty(&pds)) || + WARN_ON(pol->cpd_size && list_empty(&cpds))) { /* umm... this shouldn't happen, just abort */ ret = -ENOMEM; goto out_unlock; } + cpd = list_first_entry(&cpds, struct blkcg_policy_data, + alloc_node); + list_del_init(&cpd->alloc_node); pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node); list_del_init(&pd->alloc_node); /* grab blkcg lock too while installing @pd on @blkg */ spin_lock(&blkg->blkcg->lock); + if (!pol->cpd_size) + goto no_cpd; + if (!blkg->blkcg->pd[pol->plid]) { + /* Per-policy per-blkcg data */ + blkg->blkcg->pd[pol->plid] = cpd; + cpd->plid = pol->plid; + pol->cpd_init_fn(blkg->blkcg); + } else { /* must free it as it has already been extracted */ + kfree(cpd); + } +no_cpd: blkg->pd[pol->plid] = pd; pd->blkg = blkg; pd->plid = pol->plid; @@ -1045,8 +1111,10 @@ out_unlock: spin_unlock_irq(q->queue_lock); out_free: blk_queue_bypass_end(q); - list_for_each_entry_safe(pd, n, &pds, alloc_node) + list_for_each_entry_safe(pd, nd, &pds, alloc_node) kfree(pd); + list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node) + kfree(cpd); return ret; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); @@ -1087,6 +1155,8 @@ void blkcg_deactivate_policy(struct request_queue *q, kfree(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; + kfree(blkg->blkcg->pd[pol->plid]); + blkg->blkcg->pd[pol->plid] = NULL; spin_unlock(&blkg->blkcg->lock); } diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index c567865b5f1d..74296a78bba1 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -23,11 +23,6 @@ /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX -/* CFQ specific, out here for blkcg->cfq_weight */ -#define CFQ_WEIGHT_MIN 10 -#define CFQ_WEIGHT_MAX 1000 -#define CFQ_WEIGHT_DEFAULT 500 - #ifdef CONFIG_BLK_CGROUP enum blkg_rwstat_type { @@ -50,9 +45,7 @@ struct blkcg { struct blkcg_gq *blkg_hint; struct hlist_head blkg_list; - /* TODO: per-policy storage in blkcg */ - unsigned int cfq_weight; /* belongs to cfq */ - unsigned int cfq_leaf_weight; + struct blkcg_policy_data *pd[BLKCG_MAX_POLS]; }; struct blkg_stat { @@ -87,6 +80,24 @@ struct blkg_policy_data { struct list_head alloc_node; }; +/* + * Policies that need to keep per-blkcg data which is independent + * from any request_queue associated to it must specify its size + * with the cpd_size field of the blkcg_policy structure and + * embed a blkcg_policy_data in it. blkcg core allocates + * policy-specific per-blkcg structures lazily the first time + * they are actually needed, so it handles them together with + * blkgs. cpd_init() is invoked to let each policy handle + * per-blkcg data. + */ +struct blkcg_policy_data { + /* the policy id this per-policy data belongs to */ + int plid; + + /* used during policy activation */ + struct list_head alloc_node; +}; + /* association between a blk cgroup and a request queue */ struct blkcg_gq { /* Pointer to the associated request_queue */ @@ -112,6 +123,7 @@ struct blkcg_gq { struct rcu_head rcu_head; }; +typedef void (blkcg_pol_init_cpd_fn)(const struct blkcg *blkcg); typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg); typedef void (blkcg_pol_online_pd_fn)(struct blkcg_gq *blkg); typedef void (blkcg_pol_offline_pd_fn)(struct blkcg_gq *blkg); @@ -122,10 +134,13 @@ struct blkcg_policy { int plid; /* policy specific private data size */ size_t pd_size; + /* policy specific per-blkcg data size */ + size_t cpd_size; /* cgroup files for the policy */ struct cftype *cftypes; /* operations */ + blkcg_pol_init_cpd_fn *cpd_init_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; @@ -218,6 +233,12 @@ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, return blkg ? blkg->pd[pol->plid] : NULL; } +static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, + struct blkcg_policy *pol) +{ + return blkcg ? blkcg->pd[pol->plid] : NULL; +} + /** * pdata_to_blkg - get blkg associated with policy private data * @pd: policy private data of interest @@ -564,6 +585,9 @@ struct blkcg; struct blkg_policy_data { }; +struct blkcg_policy_data { +}; + struct blkcg_gq { }; diff --git a/block/blk-core.c b/block/blk-core.c index 03b5f8d77f37..f6ab750060fe 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -117,7 +117,7 @@ EXPORT_SYMBOL(blk_rq_init); static void req_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, int error) { - if (error) + if (error && !(rq->cmd_flags & REQ_CLONE)) clear_bit(BIO_UPTODATE, &bio->bi_flags); else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) error = -EIO; @@ -128,7 +128,8 @@ static void req_bio_endio(struct request *rq, struct bio *bio, bio_advance(bio, nbytes); /* don't actually finish bio if it's part of flush sequence */ - if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) + if (bio->bi_iter.bi_size == 0 && + !(rq->cmd_flags & (REQ_FLUSH_SEQ|REQ_CLONE))) bio_endio(bio, error); } @@ -285,6 +286,7 @@ inline void __blk_run_queue_uncond(struct request_queue *q) q->request_fn(q); q->request_fn_active--; } +EXPORT_SYMBOL_GPL(__blk_run_queue_uncond); /** * __blk_run_queue - run a single device queue @@ -1525,7 +1527,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req, * Caller must ensure !blk_queue_nomerges(q) beforehand. */ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, - unsigned int *request_count) + unsigned int *request_count, + struct request **same_queue_rq) { struct blk_plug *plug; struct request *rq; @@ -1545,8 +1548,16 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, list_for_each_entry_reverse(rq, plug_list, queuelist) { int el_ret; - if (rq->q == q) + if (rq->q == q) { (*request_count)++; + /* + * Only blk-mq multiple hardware queues case checks the + * rq in the same queue, there should be only one such + * rq in a queue + **/ + if (same_queue_rq) + *same_queue_rq = rq; + } if (rq->q != q || !blk_rq_merge_ok(rq, bio)) continue; @@ -1611,7 +1622,7 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio) * any locks. */ if (!blk_queue_nomerges(q) && - blk_attempt_plug_merge(q, bio, &request_count)) + blk_attempt_plug_merge(q, bio, &request_count, NULL)) return; spin_lock_irq(q->queue_lock); @@ -1718,8 +1729,6 @@ static void handle_bad_sector(struct bio *bio) bio->bi_rw, (unsigned long long)bio_end_sector(bio), (long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9)); - - set_bit(BIO_EOF, &bio->bi_flags); } #ifdef CONFIG_FAIL_MAKE_REQUEST @@ -2904,95 +2913,22 @@ int blk_lld_busy(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_lld_busy); -/** - * blk_rq_unprep_clone - Helper function to free all bios in a cloned request - * @rq: the clone request to be cleaned up - * - * Description: - * Free all bios in @rq for a cloned request. - */ -void blk_rq_unprep_clone(struct request *rq) -{ - struct bio *bio; - - while ((bio = rq->bio) != NULL) { - rq->bio = bio->bi_next; - - bio_put(bio); - } -} -EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); - -/* - * Copy attributes of the original request to the clone request. - * The actual data parts (e.g. ->cmd, ->sense) are not copied. - */ -static void __blk_rq_prep_clone(struct request *dst, struct request *src) +void blk_rq_prep_clone(struct request *dst, struct request *src) { dst->cpu = src->cpu; - dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE; + dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK); + dst->cmd_flags |= REQ_NOMERGE | REQ_CLONE; dst->cmd_type = src->cmd_type; dst->__sector = blk_rq_pos(src); dst->__data_len = blk_rq_bytes(src); dst->nr_phys_segments = src->nr_phys_segments; dst->ioprio = src->ioprio; dst->extra_len = src->extra_len; -} - -/** - * blk_rq_prep_clone - Helper function to setup clone request - * @rq: the request to be setup - * @rq_src: original request to be cloned - * @bs: bio_set that bios for clone are allocated from - * @gfp_mask: memory allocation mask for bio - * @bio_ctr: setup function to be called for each clone bio. - * Returns %0 for success, non %0 for failure. - * @data: private data to be passed to @bio_ctr - * - * Description: - * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. - * The actual data parts of @rq_src (e.g. ->cmd, ->sense) - * are not copied, and copying such parts is the caller's responsibility. - * Also, pages which the original bios are pointing to are not copied - * and the cloned bios just point same pages. - * So cloned bios must be completed before original bios, which means - * the caller must complete @rq before @rq_src. - */ -int blk_rq_prep_clone(struct request *rq, struct request *rq_src, - struct bio_set *bs, gfp_t gfp_mask, - int (*bio_ctr)(struct bio *, struct bio *, void *), - void *data) -{ - struct bio *bio, *bio_src; - - if (!bs) - bs = fs_bio_set; - - __rq_for_each_bio(bio_src, rq_src) { - bio = bio_clone_fast(bio_src, gfp_mask, bs); - if (!bio) - goto free_and_out; - - if (bio_ctr && bio_ctr(bio, bio_src, data)) - goto free_and_out; - - if (rq->bio) { - rq->biotail->bi_next = bio; - rq->biotail = bio; - } else - rq->bio = rq->biotail = bio; - } - - __blk_rq_prep_clone(rq, rq_src); - - return 0; - -free_and_out: - if (bio) - bio_put(bio); - blk_rq_unprep_clone(rq); - - return -ENOMEM; + dst->bio = src->bio; + dst->biotail = src->biotail; + dst->cmd = src->cmd; + dst->cmd_len = src->cmd_len; + dst->sense = src->sense; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); @@ -3034,21 +2970,20 @@ void blk_start_plug(struct blk_plug *plug) { struct task_struct *tsk = current; + /* + * If this is a nested plug, don't actually assign it. + */ + if (tsk->plug) + return; + INIT_LIST_HEAD(&plug->list); INIT_LIST_HEAD(&plug->mq_list); INIT_LIST_HEAD(&plug->cb_list); - /* - * If this is a nested plug, don't actually assign it. It will be - * flushed on its own. + * Store ordering should not be needed here, since a potential + * preempt will imply a full memory barrier */ - if (!tsk->plug) { - /* - * Store ordering should not be needed here, since a potential - * preempt will imply a full memory barrier - */ - tsk->plug = plug; - } + tsk->plug = plug; } EXPORT_SYMBOL(blk_start_plug); @@ -3195,10 +3130,11 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) void blk_finish_plug(struct blk_plug *plug) { + if (plug != current->plug) + return; blk_flush_plug_list(plug, false); - if (plug == current->plug) - current->plug = NULL; + current->plug = NULL; } EXPORT_SYMBOL(blk_finish_plug); |