From 158dbda0068e63c7cce7bd47c123bd1dfa5a902c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:18 +0900 Subject: block: reorganize request fetching functions Impact: code reorganization elv_next_request() and elv_dequeue_request() are public block layer interface than actual elevator implementation. They mostly deal with how requests interact with block layer and low level drivers at the beginning of rqeuest processing whereas __elv_next_request() is the actual eleveator request fetching interface. Move the two functions to blk-core.c. This prepares for further interface cleanup. Signed-off-by: Tejun Heo --- block/blk.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'block/blk.h') diff --git a/block/blk.h b/block/blk.h index 79c85f7c9ff5..9b2c324e4407 100644 --- a/block/blk.h +++ b/block/blk.h @@ -43,6 +43,43 @@ static inline void blk_clear_rq_complete(struct request *rq) clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags); } +/* + * Internal elevator interface + */ +#define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash)) + +static inline struct request *__elv_next_request(struct request_queue *q) +{ + struct request *rq; + + while (1) { + while (!list_empty(&q->queue_head)) { + rq = list_entry_rq(q->queue_head.next); + if (blk_do_ordered(q, &rq)) + return rq; + } + + if (!q->elevator->ops->elevator_dispatch_fn(q, 0)) + return NULL; + } +} + +static inline void elv_activate_rq(struct request_queue *q, struct request *rq) +{ + struct elevator_queue *e = q->elevator; + + if (e->ops->elevator_activate_req_fn) + e->ops->elevator_activate_req_fn(q, rq); +} + +static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq) +{ + struct elevator_queue *e = q->elevator; + + if (e->ops->elevator_deactivate_req_fn) + e->ops->elevator_deactivate_req_fn(q, rq); +} + #ifdef CONFIG_FAIL_IO_TIMEOUT int blk_should_fake_timeout(struct request_queue *); ssize_t part_timeout_show(struct device *, struct device_attribute *, char *); -- cgit v1.2.3 From c2553b5844b06910435e40cfab9e6f384840cb97 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 24 Apr 2009 08:10:11 +0200 Subject: block: make blk_do_io_stat() do the full "is this rq accountable" checks We currently check for file system requests outside of blk_do_io_stat(rq), but we may as well just include it. Signed-off-by: Jens Axboe --- block/blk.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'block/blk.h') diff --git a/block/blk.h b/block/blk.h index 9b2c324e4407..404c10b25ca1 100644 --- a/block/blk.h +++ b/block/blk.h @@ -149,9 +149,16 @@ static inline int blk_cpu_to_group(int cpu) #endif } +/* + * Contribute to IO statistics IFF: + * + * a) it's attached to a gendisk, and + * b) the queue had IO stats enabled when this request was started, and + * c) it's a file system request + */ static inline int blk_do_io_stat(struct request *rq) { - return rq->rq_disk && blk_rq_io_stat(rq); + return rq->rq_disk && blk_rq_io_stat(rq) && blk_fs_request(rq); } #endif -- cgit v1.2.3 From c69d48540c201394d08cb4d48b905e001313d9b8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 24 Apr 2009 08:12:19 +0200 Subject: block: include discard requests in IO accounting We currently don't do merging on discard requests, but we potentially could. If we do, then we need to include discard requests in the IO accounting, or merging would end up decrementing in_flight IO counters for an IO which never incremented them. So enable accounting for discard requests. Problem found by Nikanth Karthikesan Signed-off-by: Jens Axboe --- block/blk.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'block/blk.h') diff --git a/block/blk.h b/block/blk.h index 404c10b25ca1..51115599df9b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -158,7 +158,8 @@ static inline int blk_cpu_to_group(int cpu) */ static inline int blk_do_io_stat(struct request *rq) { - return rq->rq_disk && blk_rq_io_stat(rq) && blk_fs_request(rq); + return rq->rq_disk && blk_rq_io_stat(rq) && blk_fs_request(rq) && + blk_discard_rq(rq); } #endif -- cgit v1.2.3 From 2e46e8b27aa57c6bd34b3102b40ee4d0144b4fab Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 May 2009 22:24:41 +0900 Subject: block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo Cc: Boaz Harrosh Signed-off-by: Jens Axboe --- block/blk.h | 1 - 1 file changed, 1 deletion(-) (limited to 'block/blk.h') diff --git a/block/blk.h b/block/blk.h index 51115599df9b..ab54529103c0 100644 --- a/block/blk.h +++ b/block/blk.h @@ -101,7 +101,6 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req, int attempt_back_merge(struct request_queue *q, struct request *rq); int attempt_front_merge(struct request_queue *q, struct request *rq); void blk_recalc_rq_segments(struct request *rq); -void blk_recalc_rq_sectors(struct request *rq, int nsect); void blk_queue_congestion_threshold(struct request_queue *q); -- cgit v1.2.3 From 9934c8c04561413609d2bc38c6b9f268cba774a4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 8 May 2009 11:54:16 +0900 Subject: block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo Cc: Rusty Russell Cc: James Bottomley Cc: Mike Miller Cc: unsik Kim Cc: Paul Clements Cc: Tim Waugh Cc: Geert Uytterhoeven Cc: David S. Miller Cc: Laurent Vivier Cc: Jeff Garzik Cc: Jeremy Fitzhardinge Cc: Grant Likely Cc: Adrian McMenamin Cc: Stephen Rothwell Cc: Bartlomiej Zolnierkiewicz Cc: Borislav Petkov Cc: Sergei Shtylyov Cc: Alex Dubov Cc: Pierre Ossman Cc: David Woodhouse Cc: Markus Lidel Cc: Stefan Weinhuber Cc: Martin Schwidefsky Cc: Pete Zaitcev Cc: FUJITA Tomonori Signed-off-by: Jens Axboe --- block/blk.h | 1 + 1 file changed, 1 insertion(+) (limited to 'block/blk.h') diff --git a/block/blk.h b/block/blk.h index ab54529103c0..9e0042ca9495 100644 --- a/block/blk.h +++ b/block/blk.h @@ -13,6 +13,7 @@ extern struct kobj_type blk_queue_ktype; void init_request_from_bio(struct request *req, struct bio *bio); void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio); +void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); void blk_unplug_work(struct work_struct *work); -- cgit v1.2.3 From a411f4bbb89f1f08687b344064d6775bce1e4658 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Sun, 17 May 2009 19:00:01 +0300 Subject: block: Un-export blk_rq_append_bio OSD was the last in-tree user of blk_rq_append_bio(). Now that it is fixed blk_rq_append_bio is un-exported and is only used internally by block layer. Signed-off-by: Boaz Harrosh Signed-off-by: Jens Axboe --- block/blk.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'block/blk.h') diff --git a/block/blk.h b/block/blk.h index 9e0042ca9495..c863ec2281e0 100644 --- a/block/blk.h +++ b/block/blk.h @@ -13,6 +13,8 @@ extern struct kobj_type blk_queue_ktype; void init_request_from_bio(struct request *req, struct bio *bio); void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio); +int blk_rq_append_bio(struct request_queue *q, struct request *rq, + struct bio *bio); void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); -- cgit v1.2.3 From 3c4198e874cde694f5ea1463706873e7907bdb18 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Wed, 27 May 2009 14:50:02 +0200 Subject: block: fix no diskstat problem The commit below in 2.6-block/for-2.6.31 causes no diskstat problem because the blk_discard_rq() check was added with '&&'. It should be 'blk_fs_request() || blk_discard_rq()'. This patch does it and fixes the no diskstat problem. Please review and apply. ------ /proc/diskstat without this patch ------------------------------------- 8 0 sda 0 0 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------ ----- /proc/diskstat with this patch applied --------------------------------- 8 0 sda 4186 303 373621 61600 9578 3859 107468 169479 2 89755 231059 ------------------------------------------------------------------------------ -------------------------------------------------------------------------- commit c69d48540c201394d08cb4d48b905e001313d9b8 Author: Jens Axboe Date: Fri Apr 24 08:12:19 2009 +0200 block: include discard requests in IO accounting We currently don't do merging on discard requests, but we potentially could. If we do, then we need to include discard requests in the IO accounting, or merging would end up decrementing in_flight IO counters for an IO which never incremented them. So enable accounting for discard requests. static inline int blk_do_io_stat(struct request *rq) { - return rq->rq_disk && blk_rq_io_stat(rq) && blk_fs_request(rq); + return rq->rq_disk && blk_rq_io_stat(rq) && blk_fs_request(rq) && + blk_discard_rq(rq); } -------------------------------------------------------------------------- Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Jens Axboe --- block/blk.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'block/blk.h') diff --git a/block/blk.h b/block/blk.h index c863ec2281e0..3fae6add5430 100644 --- a/block/blk.h +++ b/block/blk.h @@ -156,12 +156,12 @@ static inline int blk_cpu_to_group(int cpu) * * a) it's attached to a gendisk, and * b) the queue had IO stats enabled when this request was started, and - * c) it's a file system request + * c) it's a file system request or a discard request */ static inline int blk_do_io_stat(struct request *rq) { - return rq->rq_disk && blk_rq_io_stat(rq) && blk_fs_request(rq) && - blk_discard_rq(rq); + return rq->rq_disk && blk_rq_io_stat(rq) && + (blk_fs_request(rq) || blk_discard_rq(rq)); } #endif -- cgit v1.2.3