From 414b4ff5eecff0097d09c4a7da12e435fd503692 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 25 Jan 2011 12:43:49 +0100 Subject: block: add REQ_FLUSH_SEQ rq == &q->flush_rq was used to determine whether a rq is part of a flush sequence, which worked because all requests in a flush sequence were sequenced using the single dedicated request. This is about to change, so introduce REQ_FLUSH_SEQ flag to distinguish flush sequence requests. This patch doesn't cause any behavior change. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 4ce953f1b390..fc7d8ad76f44 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -136,7 +136,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio, { struct request_queue *q = rq->q; - if (&q->flush_rq != rq) { + if (!(rq->cmd_flags & REQ_FLUSH_SEQ)) { if (error) clear_bit(BIO_UPTODATE, &bio->bi_flags); else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) @@ -1789,7 +1789,7 @@ static void blk_account_io_done(struct request *req) * normal IO on queueing nor completion. Accounting the * containing request is enough. */ - if (blk_do_io_stat(req) && req != &req->q->flush_rq) { + if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) { unsigned long duration = jiffies - req->start_time; const int rw = rq_data_dir(req); struct hd_struct *part; -- cgit v1.2.1 From 143a87f4c9c629067afea5b6703d66ea88c82f8e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 25 Jan 2011 12:43:52 +0100 Subject: block: improve flush bio completion bio's for flush are completed twice - once during the data phase and one more time after the whole sequence is complete. The first completion shouldn't notify completion to the issuer. This was achieved by skipping all bio completion steps in req_bio_endio() for the first completion; however, this has two drawbacks. * Error is not recorded in bio and must be tracked somewhere else. * Partial completion is not supported. Both don't cause problems for the current users; however, they make further improvements difficult. Change req_bio_endio() such that it only skips the actual notification part for the first completion. bio completion is implemented with partial completions on mind anyway so this is as simple as moving the REQ_FLUSH_SEQ conditional such that only calling of bio_endio() is skipped. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 48 +++++++++++++++++++++--------------------------- 1 file changed, 21 insertions(+), 27 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index fc7d8ad76f44..617bb9e40927 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -136,37 +136,31 @@ static void req_bio_endio(struct request *rq, struct bio *bio, { struct request_queue *q = rq->q; - if (!(rq->cmd_flags & REQ_FLUSH_SEQ)) { - if (error) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) - error = -EIO; - - if (unlikely(nbytes > bio->bi_size)) { - printk(KERN_ERR "%s: want %u bytes done, %u left\n", - __func__, nbytes, bio->bi_size); - nbytes = bio->bi_size; - } + if (error) + clear_bit(BIO_UPTODATE, &bio->bi_flags); + else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) + error = -EIO; + + if (unlikely(nbytes > bio->bi_size)) { + printk(KERN_ERR "%s: want %u bytes done, %u left\n", + __func__, nbytes, bio->bi_size); + nbytes = bio->bi_size; + } - if (unlikely(rq->cmd_flags & REQ_QUIET)) - set_bit(BIO_QUIET, &bio->bi_flags); + if (unlikely(rq->cmd_flags & REQ_QUIET)) + set_bit(BIO_QUIET, &bio->bi_flags); - bio->bi_size -= nbytes; - bio->bi_sector += (nbytes >> 9); + bio->bi_size -= nbytes; + bio->bi_sector += (nbytes >> 9); - if (bio_integrity(bio)) - bio_integrity_advance(bio, nbytes); + if (bio_integrity(bio)) + bio_integrity_advance(bio, nbytes); - if (bio->bi_size == 0) - bio_endio(bio, error); - } else { - /* - * Okay, this is the sequenced flush request in - * progress, just record the error; - */ - if (error && !q->flush_err) - q->flush_err = error; - } + /* don't actually finish bio if it's part of flush sequence */ + if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) + bio_endio(bio, error); + else if (error && !q->flush_err) + q->flush_err = error; } void blk_dump_rq_flags(struct request *rq, char *msg) -- cgit v1.2.1 From ae1b1539622fb46e51b4d13b3f9e5f4c713f86ae Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 25 Jan 2011 12:43:54 +0100 Subject: block: reimplement FLUSH/FUA to support merge The current FLUSH/FUA support has evolved from the implementation which had to perform queue draining. As such, sequencing is done queue-wide one flush request after another. However, with the draining requirement gone, there's no reason to keep the queue-wide sequential approach. This patch reimplements FLUSH/FUA support such that each FLUSH/FUA request is sequenced individually. The actual FLUSH execution is double buffered and whenever a request wants to execute one for either PRE or POSTFLUSH, it queues on the pending queue. Once certain conditions are met, a flush request is issued and on its completion all pending requests proceed to the next sequence. This allows arbitrary merging of different type of flushes. How they are merged can be primarily controlled and tuned by adjusting the above said 'conditions' used to determine when to issue the next flush. This is inspired by Darrick's patches to merge multiple zero-data flushes which helps workloads with highly concurrent fsync requests. * As flush requests are never put on the IO scheduler, request fields used for flush share space with rq->rb_node. rq->completion_data is moved out of the union. This increases the request size by one pointer. As rq->elevator_private* are used only by the iosched too, it is possible to reduce the request size further. However, to do that, we need to modify request allocation path such that iosched data is not allocated for flush requests. * FLUSH/FUA processing happens on insertion now instead of dispatch. - Comments updated as per Vivek and Mike. Signed-off-by: Tejun Heo Cc: "Darrick J. Wong" Cc: Shaohua Li Cc: Christoph Hellwig Cc: Vivek Goyal Cc: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-core.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 617bb9e40927..05746093b45e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -134,8 +134,6 @@ EXPORT_SYMBOL(blk_rq_init); static void req_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, int error) { - struct request_queue *q = rq->q; - if (error) clear_bit(BIO_UPTODATE, &bio->bi_flags); else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) @@ -159,8 +157,6 @@ static void req_bio_endio(struct request *rq, struct bio *bio, /* don't actually finish bio if it's part of flush sequence */ if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) bio_endio(bio, error); - else if (error && !q->flush_err) - q->flush_err = error; } void blk_dump_rq_flags(struct request *rq, char *msg) @@ -519,7 +515,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); - INIT_LIST_HEAD(&q->pending_flushes); + INIT_LIST_HEAD(&q->flush_queue[0]); + INIT_LIST_HEAD(&q->flush_queue[1]); + INIT_LIST_HEAD(&q->flush_data_in_flight); INIT_WORK(&q->unplug_work, blk_unplug_work); kobject_init(&q->kobj, &blk_queue_ktype); @@ -1198,7 +1196,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) spin_lock_irq(q->queue_lock); if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) { - where = ELEVATOR_INSERT_FRONT; + where = ELEVATOR_INSERT_FLUSH; goto get_rq; } -- cgit v1.2.1 From 9d5a4e946ce5352f19400b6370f4cd8e72806278 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 11 Feb 2011 11:05:46 +0100 Subject: block: skip elevator data initialization for flush requests Skip elevator initialization for flush requests by passing priv=0 to blk_alloc_request() in get_request(). As such elv_set_request() is never called for flush requests. Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-core.c | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 05746093b45e..ab4a7696956d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -737,6 +737,25 @@ static void freed_request(struct request_queue *q, int sync, int priv) __freed_request(q, sync ^ 1); } +/* + * Determine if elevator data should be initialized when allocating the + * request associated with @bio. + */ +static bool blk_rq_should_init_elevator(struct bio *bio) +{ + if (!bio) + return true; + + /* + * Flush requests do not use the elevator so skip initialization. + * This allows a request to share the flush and elevator data. + */ + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) + return false; + + return true; +} + /* * Get a free request, queue_lock must be held. * Returns NULL on failure, with queue_lock held. @@ -749,7 +768,7 @@ static struct request *get_request(struct request_queue *q, int rw_flags, struct request_list *rl = &q->rq; struct io_context *ioc = NULL; const bool is_sync = rw_is_sync(rw_flags) != 0; - int may_queue, priv; + int may_queue, priv = 0; may_queue = elv_may_queue(q, rw_flags); if (may_queue == ELV_MQUEUE_NO) @@ -793,9 +812,11 @@ static struct request *get_request(struct request_queue *q, int rw_flags, rl->count[is_sync]++; rl->starved[is_sync] = 0; - priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags); - if (priv) - rl->elvpriv++; + if (blk_rq_should_init_elevator(bio)) { + priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags); + if (priv) + rl->elvpriv++; + } if (blk_queue_io_stat(q)) rw_flags |= REQ_IO_STAT; -- cgit v1.2.1 From c94a96ac93b4f5b8d1ff8430b1afa1a25610cf53 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 2 Mar 2011 19:04:42 -0500 Subject: block: Initialize ->queue_lock to internal lock at queue allocation time There does not seem to be a clear convention whether q->queue_lock is initialized or not when blk_cleanup_queue() is called. In the past it was not necessary but now blk_throtl_exit() takes up queue lock by default and needs queue lock to be available. In fact elevator_exit() code also has similar requirement just that it is less stringent in the sense that elevator_exit() is called only if elevator is initialized. Two problems have been noticed because of ambiguity about spin lock status. - If a driver calls blk_alloc_queue() and then soon calls blk_cleanup_queue() almost immediately, (because some other driver structure allocation failed or some other error happened) then blk_throtl_exit() will run into issues as queue lock is not initialized. Loop driver ran into this issue recently and I noticed error paths in md driver too. Similar error paths should exist in other drivers too. - If some driver provided external spin lock and zapped the lock before blk_cleanup_queue(), then it can lead to issues. So this patch initializes the default queue lock at queue allocation time. block throttling code is one of the users of queue lock and it is initialized at the queue allocation time, so it makes sense to initialize ->queue_lock also to internal lock. A driver can overide that lock later. This will take care of the issue where a driver does not have to worry about initializing the queue lock to default before calling blk_cleanup_queue() Signed-off-by: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-core.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 3cc17e6064d6..bc2b7c5004e1 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -446,6 +446,11 @@ void blk_put_queue(struct request_queue *q) kobject_put(&q->kobj); } +/* + * Note: If a driver supplied the queue lock, it should not zap that lock + * unexpectedly as some queue cleanup components like elevator_exit() and + * blk_throtl_exit() need queue lock. + */ void blk_cleanup_queue(struct request_queue *q) { /* @@ -540,6 +545,12 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) mutex_init(&q->sysfs_lock); spin_lock_init(&q->__queue_lock); + /* + * By default initialize queue_lock to internal lock and driver can + * override it later if need be. + */ + q->queue_lock = &q->__queue_lock; + return q; } EXPORT_SYMBOL(blk_alloc_queue_node); @@ -624,7 +635,10 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, q->unprep_rq_fn = NULL; q->unplug_fn = generic_unplug_device; q->queue_flags = QUEUE_FLAG_DEFAULT; - q->queue_lock = lock; + + /* Override internal queue lock with supplied lock pointer */ + if (lock) + q->queue_lock = lock; /* * This also sets hw/phys segments, boundary and size -- cgit v1.2.1 From da527770007fce8e4541947d47918248286da875 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 2 Mar 2011 19:05:33 -0500 Subject: block: Move blk_throtl_exit() call to blk_cleanup_queue() Move blk_throtl_exit() in blk_cleanup_queue() as blk_throtl_exit() is written in such a way that it needs queue lock. In blk_release_queue() there is no gurantee that ->queue_lock is still around. Initially blk_throtl_exit() was in blk_cleanup_queue() but Ingo reported one problem. https://lkml.org/lkml/2010/10/23/86 And a quick fix moved blk_throtl_exit() to blk_release_queue(). commit 7ad58c028652753814054f4e3ac58f925e7343f4 Author: Jens Axboe Date: Sat Oct 23 20:40:26 2010 +0200 block: fix use-after-free bug in blk throttle code This patch reverts above change and does not try to shutdown the throtl work in blk_sync_queue(). By avoiding call to throtl_shutdown_timer_wq() from blk_sync_queue(), we should also avoid the problem reported by Ingo. blk_sync_queue() seems to be used only by md driver and it seems to be using it to make sure q->unplug_fn is not called as md registers its own unplug functions and it is about to free up the data structures used by unplug_fn(). Block throttle does not call back into unplug_fn() or into md. So there is no need to cancel blk throttle work. In fact I think cancelling block throttle work is bad because it might happen that some bios are throttled and scheduled to be dispatched later with the help of pending work and if work is cancelled, these bios might never be dispatched. Block layer also uses blk_sync_queue() during blk_cleanup_queue() and blk_release_queue() time. That should be safe as we are also calling blk_throtl_exit() which should make sure all the throttling related data structures are cleaned up. Signed-off-by: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index bc2b7c5004e1..accff29ad674 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -380,13 +380,16 @@ EXPORT_SYMBOL(blk_stop_queue); * that its ->make_request_fn will not re-add plugging prior to calling * this function. * + * This function does not cancel any asynchronous activity arising + * out of elevator or throttling code. That would require elevaotor_exit() + * and blk_throtl_exit() to be called with queue lock initialized. + * */ void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->unplug_timer); del_timer_sync(&q->timeout); cancel_work_sync(&q->unplug_work); - throtl_shutdown_timer_wq(q); } EXPORT_SYMBOL(blk_sync_queue); @@ -469,6 +472,8 @@ void blk_cleanup_queue(struct request_queue *q) if (q->elevator) elevator_exit(q->elevator); + blk_throtl_exit(q); + blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); -- cgit v1.2.1 From 3cca6dc1c81e2407928dc4c6105252146fd3924f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 2 Mar 2011 11:08:00 -0500 Subject: block: add API for delaying work/request_fn a little bit Currently we use plugging for that, but as plugging is going away, we need an alternative mechanism. Signed-off-by: Jens Axboe --- block/blk-core.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 3cc17e6064d6..e958c7a1e462 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -197,6 +197,32 @@ void blk_dump_rq_flags(struct request *rq, char *msg) } EXPORT_SYMBOL(blk_dump_rq_flags); +static void blk_delay_work(struct work_struct *work) +{ + struct request_queue *q; + + q = container_of(work, struct request_queue, delay_work.work); + spin_lock_irq(q->queue_lock); + q->request_fn(q); + spin_unlock_irq(q->queue_lock); +} + +/** + * blk_delay_queue - restart queueing after defined interval + * @q: The &struct request_queue in question + * @msecs: Delay in msecs + * + * Description: + * Sometimes queueing needs to be postponed for a little while, to allow + * resources to come back. This function will make sure that queueing is + * restarted around the specified time. + */ +void blk_delay_queue(struct request_queue *q, unsigned long msecs) +{ + schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs)); +} +EXPORT_SYMBOL(blk_delay_queue); + /* * "plug" the device if there are no outstanding requests: this will * force the transfer to start only after we have put all the requests @@ -363,6 +389,7 @@ EXPORT_SYMBOL(blk_start_queue); void blk_stop_queue(struct request_queue *q) { blk_remove_plug(q); + cancel_delayed_work(&q->delay_work); queue_flag_set(QUEUE_FLAG_STOPPED, q); } EXPORT_SYMBOL(blk_stop_queue); @@ -387,6 +414,7 @@ void blk_sync_queue(struct request_queue *q) del_timer_sync(&q->timeout); cancel_work_sync(&q->unplug_work); throtl_shutdown_timer_wq(q); + cancel_delayed_work_sync(&q->delay_work); } EXPORT_SYMBOL(blk_sync_queue); @@ -534,6 +562,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) INIT_LIST_HEAD(&q->flush_queue[1]); INIT_LIST_HEAD(&q->flush_data_in_flight); INIT_WORK(&q->unplug_work, blk_unplug_work); + INIT_DELAYED_WORK(&q->delay_work, blk_delay_work); kobject_init(&q->kobj, &blk_queue_ktype); -- cgit v1.2.1 From 73c101011926c5832e6e141682180c4debe2cf45 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Mar 2011 13:19:51 +0100 Subject: block: initial patch for on-stack per-task plugging This patch adds support for creating a queuing context outside of the queue itself. This enables us to batch up pieces of IO before grabbing the block device queue lock and submitting them to the IO scheduler. The context is created on the stack of the process and assigned in the task structure, so that we can auto-unplug it if we hit a schedule event. The current queue plugging happens implicitly if IO is submitted to an empty device, yet callers have to remember to unplug that IO when they are going to wait for it. This is an ugly API and has caused bugs in the past. Additionally, it requires hacks in the vm (->sync_page() callback) to handle that logic. By switching to an explicit plugging scheme we make the API a lot nicer and can get rid of the ->sync_page() hack in the vm. Signed-off-by: Jens Axboe --- block/blk-core.c | 369 ++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 271 insertions(+), 98 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index e958c7a1e462..6efb55cc5af0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -27,6 +27,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -203,7 +204,7 @@ static void blk_delay_work(struct work_struct *work) q = container_of(work, struct request_queue, delay_work.work); spin_lock_irq(q->queue_lock); - q->request_fn(q); + __blk_run_queue(q); spin_unlock_irq(q->queue_lock); } @@ -686,6 +687,8 @@ int blk_get_queue(struct request_queue *q) static inline void blk_free_request(struct request_queue *q, struct request *rq) { + BUG_ON(rq->cmd_flags & REQ_ON_PLUG); + if (rq->cmd_flags & REQ_ELVPRIV) elv_put_request(q, rq); mempool_free(rq, q->rq.rq_pool); @@ -1051,6 +1054,13 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) } EXPORT_SYMBOL(blk_requeue_request); +static void add_acct_request(struct request_queue *q, struct request *rq, + int where) +{ + drive_stat_acct(rq, 1); + __elv_add_request(q, rq, where, 0); +} + /** * blk_insert_request - insert a special request into a request queue * @q: request queue where request should be inserted @@ -1093,8 +1103,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq, if (blk_rq_tagged(rq)) blk_queue_end_tag(q, rq); - drive_stat_acct(rq, 1); - __elv_add_request(q, rq, where, 0); + add_acct_request(q, rq, where); __blk_run_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); } @@ -1215,6 +1224,113 @@ void blk_add_request_payload(struct request *rq, struct page *page, } EXPORT_SYMBOL_GPL(blk_add_request_payload); +static bool bio_attempt_back_merge(struct request_queue *q, struct request *req, + struct bio *bio) +{ + const int ff = bio->bi_rw & REQ_FAILFAST_MASK; + + /* + * Debug stuff, kill later + */ + if (!rq_mergeable(req)) { + blk_dump_rq_flags(req, "back"); + return false; + } + + if (!ll_back_merge_fn(q, req, bio)) + return false; + + trace_block_bio_backmerge(q, bio); + + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) + blk_rq_set_mixed_merge(req); + + req->biotail->bi_next = bio; + req->biotail = bio; + req->__data_len += bio->bi_size; + req->ioprio = ioprio_best(req->ioprio, bio_prio(bio)); + + drive_stat_acct(req, 0); + return true; +} + +static bool bio_attempt_front_merge(struct request_queue *q, + struct request *req, struct bio *bio) +{ + const int ff = bio->bi_rw & REQ_FAILFAST_MASK; + sector_t sector; + + /* + * Debug stuff, kill later + */ + if (!rq_mergeable(req)) { + blk_dump_rq_flags(req, "front"); + return false; + } + + if (!ll_front_merge_fn(q, req, bio)) + return false; + + trace_block_bio_frontmerge(q, bio); + + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) + blk_rq_set_mixed_merge(req); + + sector = bio->bi_sector; + + bio->bi_next = req->bio; + req->bio = bio; + + /* + * may not be valid. if the low level driver said + * it didn't need a bounce buffer then it better + * not touch req->buffer either... + */ + req->buffer = bio_data(bio); + req->__sector = bio->bi_sector; + req->__data_len += bio->bi_size; + req->ioprio = ioprio_best(req->ioprio, bio_prio(bio)); + + drive_stat_acct(req, 0); + return true; +} + +/* + * Attempts to merge with the plugged list in the current process. Returns + * true if merge was succesful, otherwise false. + */ +static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q, + struct bio *bio) +{ + struct blk_plug *plug; + struct request *rq; + bool ret = false; + + plug = tsk->plug; + if (!plug) + goto out; + + list_for_each_entry_reverse(rq, &plug->list, queuelist) { + int el_ret; + + if (rq->q != q) + continue; + + el_ret = elv_try_merge(rq, bio); + if (el_ret == ELEVATOR_BACK_MERGE) { + ret = bio_attempt_back_merge(q, rq, bio); + if (ret) + break; + } else if (el_ret == ELEVATOR_FRONT_MERGE) { + ret = bio_attempt_front_merge(q, rq, bio); + if (ret) + break; + } + } +out: + return ret; +} + void init_request_from_bio(struct request *req, struct bio *bio) { req->cpu = bio->bi_comp_cpu; @@ -1230,26 +1346,12 @@ void init_request_from_bio(struct request *req, struct bio *bio) blk_rq_bio_prep(req->q, req, bio); } -/* - * Only disabling plugging for non-rotational devices if it does tagging - * as well, otherwise we do need the proper merging - */ -static inline bool queue_should_plug(struct request_queue *q) -{ - return !(blk_queue_nonrot(q) && blk_queue_tagged(q)); -} - static int __make_request(struct request_queue *q, struct bio *bio) { - struct request *req; - int el_ret; - unsigned int bytes = bio->bi_size; - const unsigned short prio = bio_prio(bio); const bool sync = !!(bio->bi_rw & REQ_SYNC); - const bool unplug = !!(bio->bi_rw & REQ_UNPLUG); - const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK; - int where = ELEVATOR_INSERT_SORT; - int rw_flags; + struct blk_plug *plug; + int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT; + struct request *req; /* * low level driver can indicate that it wants pages above a @@ -1258,78 +1360,36 @@ static int __make_request(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); - spin_lock_irq(q->queue_lock); - if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) { + spin_lock_irq(q->queue_lock); where = ELEVATOR_INSERT_FLUSH; goto get_rq; } - if (elv_queue_empty(q)) - goto get_rq; - - el_ret = elv_merge(q, &req, bio); - switch (el_ret) { - case ELEVATOR_BACK_MERGE: - BUG_ON(!rq_mergeable(req)); - - if (!ll_back_merge_fn(q, req, bio)) - break; - - trace_block_bio_backmerge(q, bio); - - if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) - blk_rq_set_mixed_merge(req); - - req->biotail->bi_next = bio; - req->biotail = bio; - req->__data_len += bytes; - req->ioprio = ioprio_best(req->ioprio, prio); - if (!blk_rq_cpu_valid(req)) - req->cpu = bio->bi_comp_cpu; - drive_stat_acct(req, 0); - elv_bio_merged(q, req, bio); - if (!attempt_back_merge(q, req)) - elv_merged_request(q, req, el_ret); + /* + * Check if we can merge with the plugged list before grabbing + * any locks. + */ + if (attempt_plug_merge(current, q, bio)) goto out; - case ELEVATOR_FRONT_MERGE: - BUG_ON(!rq_mergeable(req)); - - if (!ll_front_merge_fn(q, req, bio)) - break; - - trace_block_bio_frontmerge(q, bio); + spin_lock_irq(q->queue_lock); - if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) { - blk_rq_set_mixed_merge(req); - req->cmd_flags &= ~REQ_FAILFAST_MASK; - req->cmd_flags |= ff; + el_ret = elv_merge(q, &req, bio); + if (el_ret == ELEVATOR_BACK_MERGE) { + BUG_ON(req->cmd_flags & REQ_ON_PLUG); + if (bio_attempt_back_merge(q, req, bio)) { + if (!attempt_back_merge(q, req)) + elv_merged_request(q, req, el_ret); + goto out_unlock; + } + } else if (el_ret == ELEVATOR_FRONT_MERGE) { + BUG_ON(req->cmd_flags & REQ_ON_PLUG); + if (bio_attempt_front_merge(q, req, bio)) { + if (!attempt_front_merge(q, req)) + elv_merged_request(q, req, el_ret); + goto out_unlock; } - - bio->bi_next = req->bio; - req->bio = bio; - - /* - * may not be valid. if the low level driver said - * it didn't need a bounce buffer then it better - * not touch req->buffer either... - */ - req->buffer = bio_data(bio); - req->__sector = bio->bi_sector; - req->__data_len += bytes; - req->ioprio = ioprio_best(req->ioprio, prio); - if (!blk_rq_cpu_valid(req)) - req->cpu = bio->bi_comp_cpu; - drive_stat_acct(req, 0); - elv_bio_merged(q, req, bio); - if (!attempt_front_merge(q, req)) - elv_merged_request(q, req, el_ret); - goto out; - - /* ELV_NO_MERGE: elevator says don't/can't merge. */ - default: - ; } get_rq: @@ -1356,20 +1416,35 @@ get_rq: */ init_request_from_bio(req, bio); - spin_lock_irq(q->queue_lock); if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) || - bio_flagged(bio, BIO_CPU_AFFINE)) - req->cpu = blk_cpu_to_group(smp_processor_id()); - if (queue_should_plug(q) && elv_queue_empty(q)) - blk_plug_device(q); - - /* insert the request into the elevator */ - drive_stat_acct(req, 1); - __elv_add_request(q, req, where, 0); + bio_flagged(bio, BIO_CPU_AFFINE)) { + req->cpu = blk_cpu_to_group(get_cpu()); + put_cpu(); + } + + plug = current->plug; + if (plug && !sync) { + if (!plug->should_sort && !list_empty(&plug->list)) { + struct request *__rq; + + __rq = list_entry_rq(plug->list.prev); + if (__rq->q != q) + plug->should_sort = 1; + } + /* + * Debug flag, kill later + */ + req->cmd_flags |= REQ_ON_PLUG; + list_add_tail(&req->queuelist, &plug->list); + drive_stat_acct(req, 1); + } else { + spin_lock_irq(q->queue_lock); + add_acct_request(q, req, where); + __blk_run_queue(q); +out_unlock: + spin_unlock_irq(q->queue_lock); + } out: - if (unplug || !queue_should_plug(q)) - __generic_unplug_device(q); - spin_unlock_irq(q->queue_lock); return 0; } @@ -1772,9 +1847,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) */ BUG_ON(blk_queued_rq(rq)); - drive_stat_acct(rq, 1); - __elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0); - + add_acct_request(q, rq, ELEVATOR_INSERT_BACK); spin_unlock_irqrestore(q->queue_lock, flags); return 0; @@ -2659,6 +2732,106 @@ int kblockd_schedule_delayed_work(struct request_queue *q, } EXPORT_SYMBOL(kblockd_schedule_delayed_work); +#define PLUG_MAGIC 0x91827364 + +void blk_start_plug(struct blk_plug *plug) +{ + struct task_struct *tsk = current; + + plug->magic = PLUG_MAGIC; + INIT_LIST_HEAD(&plug->list); + plug->should_sort = 0; + + /* + * If this is a nested plug, don't actually assign it. It will be + * flushed on its own. + */ + if (!tsk->plug) { + /* + * Store ordering should not be needed here, since a potential + * preempt will imply a full memory barrier + */ + tsk->plug = plug; + } +} +EXPORT_SYMBOL(blk_start_plug); + +static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b) +{ + struct request *rqa = container_of(a, struct request, queuelist); + struct request *rqb = container_of(b, struct request, queuelist); + + return !(rqa->q == rqb->q); +} + +static void flush_plug_list(struct blk_plug *plug) +{ + struct request_queue *q; + unsigned long flags; + struct request *rq; + + BUG_ON(plug->magic != PLUG_MAGIC); + + if (list_empty(&plug->list)) + return; + + if (plug->should_sort) + list_sort(NULL, &plug->list, plug_rq_cmp); + + q = NULL; + local_irq_save(flags); + while (!list_empty(&plug->list)) { + rq = list_entry_rq(plug->list.next); + list_del_init(&rq->queuelist); + BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG)); + BUG_ON(!rq->q); + if (rq->q != q) { + if (q) { + __blk_run_queue(q); + spin_unlock(q->queue_lock); + } + q = rq->q; + spin_lock(q->queue_lock); + } + rq->cmd_flags &= ~REQ_ON_PLUG; + + /* + * rq is already accounted, so use raw insert + */ + __elv_add_request(q, rq, ELEVATOR_INSERT_SORT, 0); + } + + if (q) { + __blk_run_queue(q); + spin_unlock(q->queue_lock); + } + + BUG_ON(!list_empty(&plug->list)); + local_irq_restore(flags); +} + +static void __blk_finish_plug(struct task_struct *tsk, struct blk_plug *plug) +{ + flush_plug_list(plug); + + if (plug == tsk->plug) + tsk->plug = NULL; +} + +void blk_finish_plug(struct blk_plug *plug) +{ + if (plug) + __blk_finish_plug(current, plug); +} +EXPORT_SYMBOL(blk_finish_plug); + +void __blk_flush_plug(struct task_struct *tsk, struct blk_plug *plug) +{ + __blk_finish_plug(tsk, plug); + tsk->plug = plug; +} +EXPORT_SYMBOL(__blk_flush_plug); + int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * -- cgit v1.2.1 From 7eaceaccab5f40bbfda044629a6298616aeaed50 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2011 08:52:07 +0100 Subject: block: remove per-queue plugging Code has been converted over to the new explicit on-stack plugging, and delay users have been converted to use the new API for that. So lets kill off the old plugging along with aops->sync_page(). Signed-off-by: Jens Axboe --- block/blk-core.c | 173 +++++++------------------------------------------------ 1 file changed, 20 insertions(+), 153 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 6efb55cc5af0..82a45898ba76 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -198,6 +198,19 @@ void blk_dump_rq_flags(struct request *rq, char *msg) } EXPORT_SYMBOL(blk_dump_rq_flags); +/* + * Make sure that plugs that were pending when this function was entered, + * are now complete and requests pushed to the queue. +*/ +static inline void queue_sync_plugs(struct request_queue *q) +{ + /* + * If the current process is plugged and has barriers submitted, + * we will livelock if we don't unplug first. + */ + blk_flush_plug(current); +} + static void blk_delay_work(struct work_struct *work) { struct request_queue *q; @@ -224,137 +237,6 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs) } EXPORT_SYMBOL(blk_delay_queue); -/* - * "plug" the device if there are no outstanding requests: this will - * force the transfer to start only after we have put all the requests - * on the list. - * - * This is called with interrupts off and no requests on the queue and - * with the queue lock held. - */ -void blk_plug_device(struct request_queue *q) -{ - WARN_ON(!irqs_disabled()); - - /* - * don't plug a stopped queue, it must be paired with blk_start_queue() - * which will restart the queueing - */ - if (blk_queue_stopped(q)) - return; - - if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) { - mod_timer(&q->unplug_timer, jiffies + q->unplug_delay); - trace_block_plug(q); - } -} -EXPORT_SYMBOL(blk_plug_device); - -/** - * blk_plug_device_unlocked - plug a device without queue lock held - * @q: The &struct request_queue to plug - * - * Description: - * Like @blk_plug_device(), but grabs the queue lock and disables - * interrupts. - **/ -void blk_plug_device_unlocked(struct request_queue *q) -{ - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - blk_plug_device(q); - spin_unlock_irqrestore(q->queue_lock, flags); -} -EXPORT_SYMBOL(blk_plug_device_unlocked); - -/* - * remove the queue from the plugged list, if present. called with - * queue lock held and interrupts disabled. - */ -int blk_remove_plug(struct request_queue *q) -{ - WARN_ON(!irqs_disabled()); - - if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q)) - return 0; - - del_timer(&q->unplug_timer); - return 1; -} -EXPORT_SYMBOL(blk_remove_plug); - -/* - * remove the plug and let it rip.. - */ -void __generic_unplug_device(struct request_queue *q) -{ - if (unlikely(blk_queue_stopped(q))) - return; - if (!blk_remove_plug(q) && !blk_queue_nonrot(q)) - return; - - q->request_fn(q); -} - -/** - * generic_unplug_device - fire a request queue - * @q: The &struct request_queue in question - * - * Description: - * Linux uses plugging to build bigger requests queues before letting - * the device have at them. If a queue is plugged, the I/O scheduler - * is still adding and merging requests on the queue. Once the queue - * gets unplugged, the request_fn defined for the queue is invoked and - * transfers started. - **/ -void generic_unplug_device(struct request_queue *q) -{ - if (blk_queue_plugged(q)) { - spin_lock_irq(q->queue_lock); - __generic_unplug_device(q); - spin_unlock_irq(q->queue_lock); - } -} -EXPORT_SYMBOL(generic_unplug_device); - -static void blk_backing_dev_unplug(struct backing_dev_info *bdi, - struct page *page) -{ - struct request_queue *q = bdi->unplug_io_data; - - blk_unplug(q); -} - -void blk_unplug_work(struct work_struct *work) -{ - struct request_queue *q = - container_of(work, struct request_queue, unplug_work); - - trace_block_unplug_io(q); - q->unplug_fn(q); -} - -void blk_unplug_timeout(unsigned long data) -{ - struct request_queue *q = (struct request_queue *)data; - - trace_block_unplug_timer(q); - kblockd_schedule_work(q, &q->unplug_work); -} - -void blk_unplug(struct request_queue *q) -{ - /* - * devices don't necessarily have an ->unplug_fn defined - */ - if (q->unplug_fn) { - trace_block_unplug_io(q); - q->unplug_fn(q); - } -} -EXPORT_SYMBOL(blk_unplug); - /** * blk_start_queue - restart a previously stopped queue * @q: The &struct request_queue in question @@ -389,7 +271,6 @@ EXPORT_SYMBOL(blk_start_queue); **/ void blk_stop_queue(struct request_queue *q) { - blk_remove_plug(q); cancel_delayed_work(&q->delay_work); queue_flag_set(QUEUE_FLAG_STOPPED, q); } @@ -411,11 +292,10 @@ EXPORT_SYMBOL(blk_stop_queue); */ void blk_sync_queue(struct request_queue *q) { - del_timer_sync(&q->unplug_timer); del_timer_sync(&q->timeout); - cancel_work_sync(&q->unplug_work); throtl_shutdown_timer_wq(q); cancel_delayed_work_sync(&q->delay_work); + queue_sync_plugs(q); } EXPORT_SYMBOL(blk_sync_queue); @@ -430,14 +310,9 @@ EXPORT_SYMBOL(blk_sync_queue); */ void __blk_run_queue(struct request_queue *q) { - blk_remove_plug(q); - if (unlikely(blk_queue_stopped(q))) return; - if (elv_queue_empty(q)) - return; - /* * Only recurse once to avoid overrunning the stack, let the unplug * handling reinvoke the handler shortly if we already got there. @@ -445,10 +320,8 @@ void __blk_run_queue(struct request_queue *q) if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { q->request_fn(q); queue_flag_clear(QUEUE_FLAG_REENTER, q); - } else { - queue_flag_set(QUEUE_FLAG_PLUGGED, q); - kblockd_schedule_work(q, &q->unplug_work); - } + } else + queue_delayed_work(kblockd_workqueue, &q->delay_work, 0); } EXPORT_SYMBOL(__blk_run_queue); @@ -535,8 +408,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) if (!q) return NULL; - q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug; - q->backing_dev_info.unplug_io_data = q; q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; q->backing_dev_info.state = 0; @@ -556,13 +427,11 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, laptop_mode_timer_fn, (unsigned long) q); - init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); INIT_LIST_HEAD(&q->flush_queue[0]); INIT_LIST_HEAD(&q->flush_queue[1]); INIT_LIST_HEAD(&q->flush_data_in_flight); - INIT_WORK(&q->unplug_work, blk_unplug_work); INIT_DELAYED_WORK(&q->delay_work, blk_delay_work); kobject_init(&q->kobj, &blk_queue_ktype); @@ -652,7 +521,6 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, q->request_fn = rfn; q->prep_rq_fn = NULL; q->unprep_rq_fn = NULL; - q->unplug_fn = generic_unplug_device; q->queue_flags = QUEUE_FLAG_DEFAULT; q->queue_lock = lock; @@ -910,8 +778,8 @@ out: } /* - * No available requests for this queue, unplug the device and wait for some - * requests to become available. + * No available requests for this queue, wait for some requests to become + * available. * * Called with q->queue_lock held, and returns with it unlocked. */ @@ -932,7 +800,6 @@ static struct request *get_request_wait(struct request_queue *q, int rw_flags, trace_block_sleeprq(q, bio, rw_flags & 1); - __generic_unplug_device(q); spin_unlock_irq(q->queue_lock); io_schedule(); @@ -1058,7 +925,7 @@ static void add_acct_request(struct request_queue *q, struct request *rq, int where) { drive_stat_acct(rq, 1); - __elv_add_request(q, rq, where, 0); + __elv_add_request(q, rq, where); } /** @@ -2798,7 +2665,7 @@ static void flush_plug_list(struct blk_plug *plug) /* * rq is already accounted, so use raw insert */ - __elv_add_request(q, rq, ELEVATOR_INSERT_SORT, 0); + __elv_add_request(q, rq, ELEVATOR_INSERT_SORT); } if (q) { -- cgit v1.2.1 From 721a9602e6607417c6bc15b18e97a2f35266c690 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Mar 2011 11:56:30 +0100 Subject: block: kill off REQ_UNPLUG With the plugging now being explicitly controlled by the submitter, callers need not pass down unplugging hints to the block layer. If they want to unplug, it's because they manually plugged on their own - in which case, they should just unplug at will. Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 82a45898ba76..7e9715ae18c8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1290,7 +1290,7 @@ get_rq: } plug = current->plug; - if (plug && !sync) { + if (plug) { if (!plug->should_sort && !list_empty(&plug->list)) { struct request *__rq; -- cgit v1.2.1 From 5e84ea3a9c662dc2d7a48703a4468fad954a3b7f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 21 Mar 2011 10:14:27 +0100 Subject: block: attempt to merge with existing requests on plug flush One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized. Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging). This fixes a regression with multiple processes issuing IO that can be merged. Thanks to Shaohua Li for testing and fixing an accounting bug. Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index e1fcf7a24668..525693237a4a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2685,7 +2685,7 @@ static void flush_plug_list(struct blk_plug *plug) /* * rq is already accounted, so use raw insert */ - __elv_add_request(q, rq, ELEVATOR_INSERT_SORT); + __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE); } if (q) { -- cgit v1.2.1