From 422765c2638924da10ff363b5eed77924911bdc7 Mon Sep 17 00:00:00 2001 From: Jianpeng Ma Date: Fri, 11 Jan 2013 14:46:09 +0100 Subject: block: Remove should_sort judgement when flush blk_plug In commit 975927b942c932,it add blk_rq_pos to sort rq when flushing. Although this commit was used for the situation which blk_plug handled multi devices on the same time like md device. I think there must be some situations like this but only single device. So remove the should_sort judgement. Because the parameter should_sort is only for this purpose,it can delete should_sort from blk_plug. CC: Shaohua Li Signed-off-by: Jianpeng Ma Signed-off-by: Jens Axboe --- block/blk-core.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index c973249d68cd..aca5d82ff13c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1548,13 +1548,6 @@ get_rq: if (list_empty(&plug->list)) trace_block_plug(q); else { - if (!plug->should_sort) { - struct request *__rq; - - __rq = list_entry_rq(plug->list.prev); - if (__rq->q != q) - plug->should_sort = 1; - } if (request_count >= BLK_MAX_REQUEST_COUNT) { blk_flush_plug_list(plug, false); trace_block_plug(q); @@ -2888,7 +2881,6 @@ void blk_start_plug(struct blk_plug *plug) plug->magic = PLUG_MAGIC; INIT_LIST_HEAD(&plug->list); INIT_LIST_HEAD(&plug->cb_list); - plug->should_sort = 0; /* * If this is a nested plug, don't actually assign it. It will be @@ -2990,10 +2982,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) list_splice_init(&plug->list, &list); - if (plug->should_sort) { - list_sort(NULL, &list, plug_rq_cmp); - plug->should_sort = 0; - } + list_sort(NULL, &list, plug_rq_cmp); q = NULL; depth = 0; -- cgit v1.2.3-59-g8ed1b From 3a366e614d0837d9fc23f78cdb1a1186ebc3387f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:33 -0800 Subject: block: add missing block_bio_complete() tracepoint bio completion didn't kick block_bio_complete TP. Only dm was explicitly triggering the TP on IO completion. This makes block_bio_complete TP useless for tracers which want to know about bios, and all other bio based drivers skip generating blktrace completion events. This patch makes all bio completions via bio_endio() generate block_bio_complete TP. * Explicit trace_block_bio_complete() invocation removed from dm and the trace point is unexported. * @rq dropped from trace_block_bio_complete(). bios may fly around w/o queue associated. Verifying and accessing the assocaited queue belongs to TP probes. * blktrace now gets both request and bio completions. Make it ignore bio completions if request completion path is happening. This makes all bio based drivers generate blktrace completion events properly and makes the block_bio_complete TP actually useful. v2: With this change, block_bio_complete TP could be invoked on sg commands which have bio's with %NULL bi_bdev. Update TP assignment code to check whether bio->bi_bdev is %NULL before dereferencing. Signed-off-by: Tejun Heo Original-patch-by: Namhyung Kim Cc: Tejun Heo Cc: Steven Rostedt Cc: Alasdair Kergon Cc: dm-devel@redhat.com Cc: Neil Brown Signed-off-by: Jens Axboe --- block/blk-core.c | 1 - drivers/md/dm.c | 1 - drivers/md/raid5.c | 11 +---------- fs/bio.c | 2 ++ include/linux/blktrace_api.h | 1 + include/trace/events/block.h | 8 ++++---- kernel/trace/blktrace.c | 26 +++++++++++++++++++++++--- 7 files changed, 31 insertions(+), 19 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index aca5d82ff13c..4f5aec708be6 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -39,7 +39,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); -EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); DEFINE_IDA(blk_queue_ida); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c72e4d5a9617..650ec2866e34 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -627,7 +627,6 @@ static void dec_pending(struct dm_io *io, int error) queue_io(md, bio); } else { /* done with normal IO or empty flush */ - trace_block_bio_complete(md->queue, bio, io_error); bio_endio(bio, io_error); } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 19d77a026639..9ab506df42da 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -184,8 +184,6 @@ static void return_io(struct bio *return_bi) return_bi = bi->bi_next; bi->bi_next = NULL; bi->bi_size = 0; - trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), - bi, 0); bio_endio(bi, 0); bi = return_bi; } @@ -3917,8 +3915,6 @@ static void raid5_align_endio(struct bio *bi, int error) rdev_dec_pending(rdev, conf->mddev); if (!error && uptodate) { - trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev), - raid_bi, 0); bio_endio(raid_bi, 0); if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); @@ -4377,8 +4373,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) if ( rw == WRITE ) md_write_end(mddev); - trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), - bi, 0); bio_endio(bi, 0); } } @@ -4755,11 +4749,8 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) handled++; } remaining = raid5_dec_bi_active_stripes(raid_bio); - if (remaining == 0) { - trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev), - raid_bio, 0); + if (remaining == 0) bio_endio(raid_bio, 0); - } if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); return handled; diff --git a/fs/bio.c b/fs/bio.c index b96fc6ce4855..bb5768f59b32 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1428,6 +1428,8 @@ void bio_endio(struct bio *bio, int error) else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) error = -EIO; + trace_block_bio_complete(bio, error); + if (bio->bi_end_io) bio->bi_end_io(bio, error); } diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7c2e030e72f1..0ea61e07a91c 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -12,6 +12,7 @@ struct blk_trace { int trace_state; + bool rq_based; struct rchan *rchan; unsigned long __percpu *sequence; unsigned char __percpu *msg_data; diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 05c5e61f0a7c..8a168db9a645 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -206,7 +206,6 @@ TRACE_EVENT(block_bio_bounce, /** * block_bio_complete - completed all work on the block operation - * @q: queue holding the block operation * @bio: block operation completed * @error: io error value * @@ -215,9 +214,9 @@ TRACE_EVENT(block_bio_bounce, */ TRACE_EVENT(block_bio_complete, - TP_PROTO(struct request_queue *q, struct bio *bio, int error), + TP_PROTO(struct bio *bio, int error), - TP_ARGS(q, bio, error), + TP_ARGS(bio, error), TP_STRUCT__entry( __field( dev_t, dev ) @@ -228,7 +227,8 @@ TRACE_EVENT(block_bio_complete, ), TP_fast_assign( - __entry->dev = bio->bi_bdev->bd_dev; + __entry->dev = bio->bi_bdev ? + bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_sector; __entry->nr_sector = bio->bi_size >> 9; __entry->error = error; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index c0bd0308741c..190d98fbed27 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -739,6 +739,12 @@ static void blk_add_trace_rq_complete(void *ignore, struct request_queue *q, struct request *rq) { + struct blk_trace *bt = q->blk_trace; + + /* if control ever passes through here, it's a request based driver */ + if (unlikely(bt && !bt->rq_based)) + bt->rq_based = true; + blk_add_trace_rq(q, rq, BLK_TA_COMPLETE); } @@ -774,10 +780,24 @@ static void blk_add_trace_bio_bounce(void *ignore, blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0); } -static void blk_add_trace_bio_complete(void *ignore, - struct request_queue *q, struct bio *bio, - int error) +static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error) { + struct request_queue *q; + struct blk_trace *bt; + + if (!bio->bi_bdev) + return; + + q = bdev_get_queue(bio->bi_bdev); + bt = q->blk_trace; + + /* + * Request based drivers will generate both rq and bio completions. + * Ignore bio ones. + */ + if (likely(!bt) || bt->rq_based) + return; + blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error); } -- cgit v1.2.3-59-g8ed1b From 8c1cf6bb02fda79b0a4b9bd121f6be6d4ce7a15a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:34 -0800 Subject: block: add @req to bio_{front|back}_merge tracepoints bio_{front|back}_merge tracepoints report a bio merging into an existing request but didn't specify which request the bio is being merged into. Add @req to it. This makes it impossible to share the event template with block_bio_queue - split it out. @req isn't used or exported to userland at this point and there is no userland visible behavior change. Later changes will make use of the extra parameter. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 4 ++-- include/trace/events/block.h | 45 +++++++++++++++++++++++++++++++++----------- kernel/trace/blktrace.c | 2 ++ 3 files changed, 38 insertions(+), 13 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 4f5aec708be6..66d31687cf6b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1347,7 +1347,7 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req, if (!ll_back_merge_fn(q, req, bio)) return false; - trace_block_bio_backmerge(q, bio); + trace_block_bio_backmerge(q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); @@ -1369,7 +1369,7 @@ static bool bio_attempt_front_merge(struct request_queue *q, if (!ll_front_merge_fn(q, req, bio)) return false; - trace_block_bio_frontmerge(q, bio); + trace_block_bio_frontmerge(q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 8a168db9a645..b408f518a819 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -241,11 +241,11 @@ TRACE_EVENT(block_bio_complete, __entry->nr_sector, __entry->error) ); -DECLARE_EVENT_CLASS(block_bio, +DECLARE_EVENT_CLASS(block_bio_merge, - TP_PROTO(struct request_queue *q, struct bio *bio), + TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), - TP_ARGS(q, bio), + TP_ARGS(q, rq, bio), TP_STRUCT__entry( __field( dev_t, dev ) @@ -272,31 +272,33 @@ DECLARE_EVENT_CLASS(block_bio, /** * block_bio_backmerge - merging block operation to the end of an existing operation * @q: queue holding operation + * @rq: request bio is being merged into * @bio: new block operation to merge * * Merging block request @bio to the end of an existing block request * in queue @q. */ -DEFINE_EVENT(block_bio, block_bio_backmerge, +DEFINE_EVENT(block_bio_merge, block_bio_backmerge, - TP_PROTO(struct request_queue *q, struct bio *bio), + TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), - TP_ARGS(q, bio) + TP_ARGS(q, rq, bio) ); /** * block_bio_frontmerge - merging block operation to the beginning of an existing operation * @q: queue holding operation + * @rq: request bio is being merged into * @bio: new block operation to merge * * Merging block IO operation @bio to the beginning of an existing block * operation in queue @q. */ -DEFINE_EVENT(block_bio, block_bio_frontmerge, +DEFINE_EVENT(block_bio_merge, block_bio_frontmerge, - TP_PROTO(struct request_queue *q, struct bio *bio), + TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), - TP_ARGS(q, bio) + TP_ARGS(q, rq, bio) ); /** @@ -306,11 +308,32 @@ DEFINE_EVENT(block_bio, block_bio_frontmerge, * * About to place the block IO operation @bio into queue @q. */ -DEFINE_EVENT(block_bio, block_bio_queue, +TRACE_EVENT(block_bio_queue, TP_PROTO(struct request_queue *q, struct bio *bio), - TP_ARGS(q, bio) + TP_ARGS(q, bio), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( unsigned int, nr_sector ) + __array( char, rwbs, RWBS_LEN ) + __array( char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->sector = bio->bi_sector; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s]", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm) ); DECLARE_EVENT_CLASS(block_get_rq, diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 190d98fbed27..fb593f6a687e 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -803,6 +803,7 @@ static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error) static void blk_add_trace_bio_backmerge(void *ignore, struct request_queue *q, + struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); @@ -810,6 +811,7 @@ static void blk_add_trace_bio_backmerge(void *ignore, static void blk_add_trace_bio_frontmerge(void *ignore, struct request_queue *q, + struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); -- cgit v1.2.3-59-g8ed1b