From 1ba64edef6051d2ec79bb2fbd3a0c8f0df00ab55 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:37 +0100 Subject: block, sx8: kill blk_insert_request() The only user left for blk_insert_request() is sx8 and it can be trivially switched to use blk_execute_rq_nowait() - special requests aren't included in io stat and sx8 doesn't use block layer tagging. Switch sx8 and kill blk_insert_requeset(). This patch doesn't introduce any functional difference. Only compile tested. Signed-off-by: Tejun Heo Acked-by: Jeff Garzik Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c7a6d3b5bc7b..8a6b51b13a1c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -660,7 +660,6 @@ extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); extern struct request *blk_make_request(struct request_queue *, struct bio *, gfp_t); -extern void blk_insert_request(struct request_queue *, struct request *, int, void *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, unsigned int len); -- cgit v1.2.3 From 34f6055c80285e4efb3f602a9119db75239744dc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:37 +0100 Subject: block: add blk_queue_dead() There are a number of QUEUE_FLAG_DEAD tests. Add blk_queue_dead() macro and use it. This patch doesn't introduce any functional difference. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8a6b51b13a1c..783f97c14d0a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -481,6 +481,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) +#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) -- cgit v1.2.3 From a73f730d013ff2788389fd0c46ad3e5510f124e6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:37 +0100 Subject: block, cfq: move cfqd->cic_index to q->id cfq allocates per-queue id using ida and uses it to index cic radix tree from io_context. Move it to q->id and allocate on queue init and free on queue release. This simplifies cfq a bit and will allow for further improvements of io context life-cycle management. This patch doesn't introduce any functional difference. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 783f97c14d0a..8c8dbc4738ea 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -310,6 +310,12 @@ struct request_queue { */ unsigned long queue_flags; + /* + * ida allocated id for this queue. Used to index queues from + * ioctx. + */ + int id; + /* * queue needs bounce pages for pages above this limit */ -- cgit v1.2.3 From 09ac46c429464c919d04bb737b27edd84d944f02 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:38 +0100 Subject: block: misc updates to blk_get_queue() * blk_get_queue() is peculiar in that it returns 0 on success and 1 on failure instead of 0 / -errno or boolean. Update it such that it returns %true on success and %false on failure. * Make sure the caller checks for the return value. * Separate out __blk_get_queue() which doesn't check whether @q is dead and put it in blk.h. This will be used later. This patch doesn't introduce any functional changes. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8c8dbc4738ea..d1b6f4ed1f96 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -865,7 +865,7 @@ extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatte extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); -int blk_get_queue(struct request_queue *); +bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); -- cgit v1.2.3 From b2efa05265d62bc29f3a64400fad4b44340eedb8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:39 +0100 Subject: block, cfq: unlink cfq_io_context's immediately cic is association between io_context and request_queue. A cic is linked from both ioc and q and should be destroyed when either one goes away. As ioc and q both have their own locks, locking becomes a bit complex - both orders work for removal from one but not from the other. Currently, cfq tries to circumvent this locking order issue with RCU. ioc->lock nests inside queue_lock but the radix tree and cic's are also protected by RCU allowing either side to walk their lists without grabbing lock. This rather unconventional use of RCU quickly devolves into extremely fragile convolution. e.g. The following is from cfqd going away too soon after ioc and q exits raced. general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: [ 88.503444] Pid: 599, comm: hexdump Not tainted 3.1.0-rc10-work+ #158 Bochs Bochs RIP: 0010:[] [] cfq_exit_single_io_context+0x58/0xf0 ... Call Trace: [] call_for_each_cic+0x5a/0x90 [] cfq_exit_io_context+0x15/0x20 [] exit_io_context+0x100/0x140 [] do_exit+0x579/0x850 [] do_group_exit+0x5b/0xd0 [] sys_exit_group+0x17/0x20 [] system_call_fastpath+0x16/0x1b The only real hot path here is cic lookup during request initialization and avoiding extra locking requires very confined use of RCU. This patch makes cic removal from both ioc and request_queue perform double-locking and unlink immediately. * From q side, the change is almost trivial as ioc->lock nests inside queue_lock. It just needs to grab each ioc->lock as it walks cic_list and unlink it. * From ioc side, it's a bit more difficult because of inversed lock order. ioc needs its lock to walk its cic_list but can't grab the matching queue_lock and needs to perform unlock-relock dancing. Unlinking is now wholly done from put_io_context() and fast path is optimized by using the queue_lock the caller already holds, which is by far the most common case. If the ioc accessed multiple devices, it tries with trylock. In unlikely cases of fast path failure, it falls back to full double-locking dance from workqueue. Double-locking isn't the prettiest thing in the world but it's *far* simpler and more understandable than RCU trick without adding any meaningful overhead. This still leaves a lot of now unnecessary RCU logics. Future patches will trim them. -v2: Vivek pointed out that cic->q was being dereferenced after cic->release() was called. Updated to use local variable @this_q instead. Signed-off-by: Tejun Heo Cc: Vivek Goyal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d1b6f4ed1f96..65c2f8c70089 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -393,6 +393,9 @@ struct request_queue { /* Throttle data */ struct throtl_data *td; #endif +#ifdef CONFIG_LOCKDEP + int ioc_release_depth; +#endif }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -- cgit v1.2.3 From a612fddf0d8090f2877305c9168b6c1a34fb5d90 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:41 +0100 Subject: block, cfq: move cfqd->icq_list to request_queue and add request->elv.icq Most of icq management is about to be moved out of cfq into blk-ioc. This patch prepares for it. * Move cfqd->icq_list to request_queue->icq_list * Make request explicitly point to icq instead of through elevator private data. ->elevator_private[3] is replaced with sub struct elv which contains icq pointer and priv[2]. cfq is updated accordingly. * Meaningless clearing of ->elevator_private[0] removed from elv_set_request(). At that point in code, the field was guaranteed to be %NULL anyway. This patch doesn't introduce any functional change. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 65c2f8c70089..8bca04873f53 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -111,10 +111,14 @@ struct request { * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. Flush requests are * never put on the IO scheduler. So let the flush fields share - * space with the three elevator_private pointers. + * space with the elevator data. */ union { - void *elevator_private[3]; + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + struct { unsigned int seq; struct list_head list; @@ -357,6 +361,8 @@ struct request_queue { struct timer_list timeout; struct list_head timeout_list; + struct list_head icq_list; + struct queue_limits limits; /* -- cgit v1.2.3 From b1bd055d397e09f99dcef9b138ed104ff1812fcb Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 11 Jan 2012 16:27:11 +0100 Subject: block: Introduce blk_set_stacking_limits function Stacking driver queue limits are typically bounded exclusively by the capabilities of the low level devices, not by the stacking driver itself. This patch introduces blk_set_stacking_limits() which has more liberal metrics than the default queue limits function. This allows us to inherit topology parameters from bottom devices without manually tweaking the default limits in each driver prior to calling the stacking function. Since there is now a clear distinction between stacking and low-level devices, blk_set_default_limits() has been modified to carry the more conservative values that we used to manually set in blk_queue_make_request(). Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8bca04873f53..adc34133a56a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -844,6 +844,7 @@ extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_default_limits(struct queue_limits *lim); +extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev, -- cgit v1.2.3 From fd83240a60ecc59849420df3393e9e6d35c77683 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 12 Jan 2012 09:17:30 +0100 Subject: blockdev: convert some macros to static inlines We prefer to program in C rather than preprocessor and it fixes this warning when CONFIG_BLK_DEV_INTEGRITY is not set: drivers/md/dm-table.c: In function 'dm_table_set_integrity': drivers/md/dm-table.c:1285:3: warning: statement with no effect [-Wunused-value] Signed-off-by: Stephen Rothwell Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 77 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 64 insertions(+), 13 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index adc34133a56a..5cfb9b22627f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1298,19 +1298,70 @@ queue_max_integrity_segments(struct request_queue *q) #else /* CONFIG_BLK_DEV_INTEGRITY */ -#define blk_integrity_rq(rq) (0) -#define blk_rq_count_integrity_sg(a, b) (0) -#define blk_rq_map_integrity_sg(a, b, c) (0) -#define bdev_get_integrity(a) (0) -#define blk_get_integrity(a) (0) -#define blk_integrity_compare(a, b) (0) -#define blk_integrity_register(a, b) (0) -#define blk_integrity_unregister(a) do { } while (0) -#define blk_queue_max_integrity_segments(a, b) do { } while (0) -#define queue_max_integrity_segments(a) (0) -#define blk_integrity_merge_rq(a, b, c) (0) -#define blk_integrity_merge_bio(a, b, c) (0) -#define blk_integrity_is_initialized(a) (0) +struct bio; +struct block_device; +struct gendisk; +struct blk_integrity; + +static inline int blk_integrity_rq(struct request *rq) +{ + return 0; +} +static inline int blk_rq_count_integrity_sg(struct request_queue *q, + struct bio *b) +{ + return 0; +} +static inline int blk_rq_map_integrity_sg(struct request_queue *q, + struct bio *b, + struct scatterlist *s) +{ + return 0; +} +static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) +{ + return 0; +} +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + return NULL; +} +static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) +{ + return 0; +} +static inline int blk_integrity_register(struct gendisk *d, + struct blk_integrity *b) +{ + return 0; +} +static inline void blk_integrity_unregister(struct gendisk *d) +{ +} +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ +} +static inline unsigned short queue_max_integrity_segments(struct request_queue *q) +{ + return 0; +} +static inline int blk_integrity_merge_rq(struct request_queue *rq, + struct request *r1, + struct request *r2) +{ + return 0; +} +static inline int blk_integrity_merge_bio(struct request_queue *rq, + struct request *r, + struct bio *b) +{ + return 0; +} +static inline bool blk_integrity_is_initialized(struct gendisk *g) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3