From e686307fdc84f249490e6c9da92fcb2424491f14 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 17 Apr 2009 08:41:21 +0200 Subject: loop: use BIO list management functions Now that the bio list management stuff is generic, convert loop to use bio lists instead of its own private bio list implementation. Cc: Jens Axboe Cc: Christoph Hellwig Signed-off-by: Akinobu Mita Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- include/linux/loop.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 7b214fd672a..f37ca8c726b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -506,7 +506,7 @@ static inline int bio_has_data(struct bio *bio) } /* - * BIO list managment for use by remapping drivers (e.g. DM or MD). + * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * * A bio_list anchors a singly-linked list of bios chained through the bi_next * member of the bio. The bio_list also caches the last list member to allow diff --git a/include/linux/loop.h b/include/linux/loop.h index 40725447f5e..66c194e2d9b 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -56,8 +56,7 @@ struct loop_device { gfp_t old_gfp_mask; spinlock_t lo_lock; - struct bio *lo_bio; - struct bio *lo_biotail; + struct bio_list lo_bio_list; int lo_state; struct mutex lo_ctl_mutex; struct task_struct *lo_thread; -- cgit v1.2.3 From 214ae19104141404f18ad6651752eb38e3dd584e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 19 Apr 2009 07:00:41 +0900 Subject: ide kill unused ide_cmd->special Impact: removal of unused field No one uses ide_cmd->special anymore. Kill it. Signed-off-by: Tejun Heo --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index ff65fffb078..846a1e13240 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -324,7 +324,6 @@ struct ide_cmd { unsigned int cursg_ofs; struct request *rq; /* copy of request */ - void *special; /* valid_t generally */ }; /* ATAPI packet command flags */ -- cgit v1.2.3 From e69d800f7e8797a8e3423380ee9d8ca1cb90c388 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sun, 19 Apr 2009 07:00:42 +0900 Subject: ide: add helpers for preparing sense requests This is in preparation of removing the queueing of a sense request out of the IRQ handler path. Use struct request_sense as a general sense buffer for all ATAPI devices ide-{floppy,tape,cd}. tj: * blk_get_request(__GFP_WAIT) can't be called from do_request() as it can cause deadlock. Converted to use inline struct request and blk_rq_init(). * Added xfer / cdb len selection depending on device type. * All sense prep logics folded into ide_prep_sense() which never fails. * hwif->rq clearing and sense_rq used handling moved into ide_queue_sense_rq(). * blk_rq_map_kern() conversion is moved to later patch. CC: Bartlomiej Zolnierkiewicz CC: FUJITA Tomonori Signed-off-by: Borislav Petkov Signed-off-by: Tejun Heo --- include/linux/ide.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index 846a1e13240..a69ccac5641 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -26,6 +26,9 @@ #include #include +/* for request_sense */ +#include + #if defined(CONFIG_CRIS) || defined(CONFIG_FRV) || defined(CONFIG_MN10300) # define SUPPORT_VLB_SYNC 0 #else @@ -602,6 +605,11 @@ struct ide_drive_s { struct ide_atapi_pc request_sense_pc; struct request request_sense_rq; + + /* current sense rq and buffer */ + bool sense_rq_armed; + struct request sense_rq; + struct request_sense sense_data; }; typedef struct ide_drive_s ide_drive_t; @@ -1175,6 +1183,9 @@ int ide_set_media_lock(ide_drive_t *, struct gendisk *, int); void ide_create_request_sense_cmd(ide_drive_t *, struct ide_atapi_pc *); void ide_retry_pc(ide_drive_t *, struct gendisk *); +void ide_prep_sense(ide_drive_t *drive, struct request *rq); +void ide_queue_sense_rq(ide_drive_t *drive, void *special); + int ide_cd_expiry(ide_drive_t *); int ide_cd_get_xferlen(struct request *); -- cgit v1.2.3 From 068753203e6cd085664a62e0fc0636e19b148a12 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sun, 19 Apr 2009 07:00:42 +0900 Subject: ide-atapi: convert ide-{floppy,tape} to using preallocated sense buffer Since we're issuing REQ_TYPE_SENSE now we need to allow those types of rqs in the ->do_request callbacks. As a future improvement, sense_len assignment might be unified across all ATAPI devices. Borislav to check with specs and test. As a result, get rid of ide_queue_pc_head() and drive->request_sense_rq. tj: * Init request sense ide_atapi_pc from sense request. In the longer timer, it would probably better to fold ide_create_request_sense_cmd() into its only current user - ide_floppy_get_format_progress(). * ide_retry_pc() no longer takes @disk. CC: Bartlomiej Zolnierkiewicz CC: FUJITA Tomonori Signed-off-by: Borislav Petkov Signed-off-by: Tejun Heo --- include/linux/ide.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index a69ccac5641..9e67ccac3c1 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -604,7 +604,6 @@ struct ide_drive_s { unsigned long atapi_flags; struct ide_atapi_pc request_sense_pc; - struct request request_sense_rq; /* current sense rq and buffer */ bool sense_rq_armed; @@ -1181,7 +1180,7 @@ int ide_do_test_unit_ready(ide_drive_t *, struct gendisk *); int ide_do_start_stop(ide_drive_t *, struct gendisk *, int); int ide_set_media_lock(ide_drive_t *, struct gendisk *, int); void ide_create_request_sense_cmd(ide_drive_t *, struct ide_atapi_pc *); -void ide_retry_pc(ide_drive_t *, struct gendisk *); +void ide_retry_pc(ide_drive_t *drive); void ide_prep_sense(ide_drive_t *drive, struct request *rq); void ide_queue_sense_rq(ide_drive_t *drive, void *special); -- cgit v1.2.3 From 02e7cf8f848841ca21864ccd019e480b73c323b7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 19 Apr 2009 07:00:42 +0900 Subject: ide-cd,atapi: use bio for internal commands Impact: unify request data buffer handling rq->data is used mostly to pass kernel buffer through request queue without using bio. There are only a couple of places which still do this in kernel and converting to bio isn't difficult. This patch converts ide-cd and atapi to use bio instead of rq->data for request sense and internal pc commands. With previous change to unify sense request handling, this is relatively easily achieved by adding blk_rq_map_kern() during sense_rq prep and PC issue. If blk_rq_map_kern() fails for sense, the error is deferred till sense issue and aborts the failed command which triggered the sense. Note that this is a slim possibility as sense prep is done on each command issue, so for the above condition to actually trigger, all preps since the last sense issue till the issue of the request which would require a sense should fail. * do_request functions might sleep now. This should be okay as ide request_fn - do_ide_request() - is invoked only from make_request and plug work. Make sure this is the case by adding might_sleep() to do_ide_request(). * Functions which access the read sense data before the sense request is complete now should access bio_data(sense_rq->bio) as the sense buffer might have been copied during blk_rq_map_kern(). * ide-tape updated to map sg. * cdrom_do_block_pc() now doesn't have to deal with REQ_TYPE_ATA_PC special case. Simplified. * tp_ops->output/input_data path dropped from ide_pc_intr(). Signed-off-by: Tejun Heo --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index 9e67ccac3c1..1957461ac76 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1183,7 +1183,7 @@ void ide_create_request_sense_cmd(ide_drive_t *, struct ide_atapi_pc *); void ide_retry_pc(ide_drive_t *drive); void ide_prep_sense(ide_drive_t *drive, struct request *rq); -void ide_queue_sense_rq(ide_drive_t *drive, void *special); +int ide_queue_sense_rq(ide_drive_t *drive, void *special); int ide_cd_expiry(ide_drive_t *); -- cgit v1.2.3 From 29d1a4371035e01b0d079bc5aa88b50f5af7a566 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 19 Apr 2009 08:46:03 +0900 Subject: ide-atapi: kill unused fields and callbacks Impact: remove fields and code paths which are no longer necessary Now that ide-tape uses standard mechanisms to transfer data, special case handling for bh handling can be dropped from ide-atapi. Drop the followings. * pc->cur_pos, b_count, bh and b_data * drive->pc_update_buffers() and pc_io_buffers(). Signed-off-by: Tejun Heo --- include/linux/ide.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/ide.h b/include/linux/ide.h index 1957461ac76..34c128f0a33 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -362,11 +362,7 @@ struct ide_atapi_pc { /* data buffer */ u8 *buf; - /* current buffer position */ - u8 *cur_pos; int buf_size; - /* missing/available data on the current buffer */ - int b_count; /* the corresponding request */ struct request *rq; @@ -379,10 +375,6 @@ struct ide_atapi_pc { */ u8 pc_buf[IDE_PC_BUFFER_SIZE]; - /* idetape only */ - struct idetape_bh *bh; - char *b_data; - unsigned long timeout; }; @@ -595,10 +587,6 @@ struct ide_drive_s { /* callback for packet commands */ int (*pc_callback)(struct ide_drive_s *, int); - void (*pc_update_buffers)(struct ide_drive_s *, struct ide_atapi_pc *); - int (*pc_io_buffers)(struct ide_drive_s *, struct ide_atapi_pc *, - unsigned int, int); - ide_startstop_t (*irq_handler)(struct ide_drive_s *); unsigned long atapi_flags; -- cgit v1.2.3 From a7f557923441186a3cdbabc54f1bcacf42b63bf5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:17 +0900 Subject: block: kill blk_start_queueing() blk_start_queueing() is identical to __blk_run_queue() except that it doesn't check for recursion. None of the current users depends on blk_start_queueing() running request_fn directly. Replace usages of blk_start_queueing() with [__]blk_run_queue() and kill it. [ Impact: removal of mostly duplicate interface function ] Signed-off-by: Tejun Heo --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2755d5c6da2..12e20de44b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -797,7 +797,6 @@ extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); extern void __blk_run_queue(struct request_queue *); extern void blk_run_queue(struct request_queue *); -extern void blk_start_queueing(struct request_queue *); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); -- cgit v1.2.3 From 5efccd17ceb0fc43837a331297c2c407969d7201 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:18 +0900 Subject: block: reorder request completion functions Reorder request completion functions such that * All request completion functions are located together. * Functions which are used by only one caller is put right above the caller. * end_request() is put after other completion functions but before blk_update_request(). This change is for completion function cleanup which will follow. [ Impact: cleanup, code reorganization ] Signed-off-by: Tejun Heo --- include/linux/blkdev.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 12e20de44b6..156ffd9de96 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -831,6 +831,14 @@ static inline void blk_run_address_space(struct address_space *mapping) extern void blkdev_dequeue_request(struct request *req); +/* + * blk_end_request() takes bytes instead of sectors as a complete size. + * blk_rq_bytes() returns bytes left to complete in the entire request. + * blk_rq_cur_bytes() returns bytes left to complete in the current segment. + */ +extern unsigned int blk_rq_bytes(struct request *rq); +extern unsigned int blk_rq_cur_bytes(struct request *rq); + /* * blk_end_request() and friends. * __blk_end_request() and end_request() must be called with @@ -857,14 +865,6 @@ extern void blk_abort_queue(struct request_queue *); extern void blk_update_request(struct request *rq, int error, unsigned int nr_bytes); -/* - * blk_end_request() takes bytes instead of sectors as a complete size. - * blk_rq_bytes() returns bytes left to complete in the entire request. - * blk_rq_cur_bytes() returns bytes left to complete in the current segment. - */ -extern unsigned int blk_rq_bytes(struct request *rq); -extern unsigned int blk_rq_cur_bytes(struct request *rq); - /* * Access functions for manipulating queue properties */ -- cgit v1.2.3 From 0b302d5aa7975006fa2ec3d66386610b9b36c669 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:18 +0900 Subject: block: kill blk_end_request_callback() With recent IDE updates, blk_end_request_callback() doesn't have any user now. Kill it. [ Impact: removal of unused convoluted interface ] Signed-off-by: Tejun Heo --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 156ffd9de96..1fa9dcf9aa6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -855,9 +855,6 @@ extern int __blk_end_request(struct request *rq, int error, extern int blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes, unsigned int bidi_bytes); extern void end_request(struct request *, int); -extern int blk_end_request_callback(struct request *rq, int error, - unsigned int nr_bytes, - int (drv_callback)(struct request *)); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); -- cgit v1.2.3 From 2e60e02297cf54e367567f2d85b2ca56b1c4a906 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:18 +0900 Subject: block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo Reviewed-by: Boaz Harrosh Cc: Christoph Hellwig --- include/linux/blkdev.h | 94 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 82 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1fa9dcf9aa6..501f6845cc7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -840,27 +840,97 @@ extern unsigned int blk_rq_bytes(struct request *rq); extern unsigned int blk_rq_cur_bytes(struct request *rq); /* - * blk_end_request() and friends. - * __blk_end_request() and end_request() must be called with - * the request queue spinlock acquired. + * Request completion related functions. + * + * blk_update_request() completes given number of bytes and updates + * the request without completing it. + * + * blk_end_request() and friends. __blk_end_request() and + * end_request() must be called with the request queue spinlock + * acquired. * * Several drivers define their own end_request and call * blk_end_request() for parts of the original function. * This prevents code duplication in drivers. */ -extern int blk_end_request(struct request *rq, int error, - unsigned int nr_bytes); -extern int __blk_end_request(struct request *rq, int error, - unsigned int nr_bytes); -extern int blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, unsigned int bidi_bytes); -extern void end_request(struct request *, int); +extern bool blk_update_request(struct request *rq, int error, + unsigned int nr_bytes); +extern bool blk_end_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, + unsigned int bidi_bytes); +extern bool __blk_end_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, + unsigned int bidi_bytes); + +/** + * blk_end_request - Helper function for drivers to complete the request. + * @rq: the request being processed + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete + * + * Description: + * Ends I/O on a number of bytes attached to @rq. + * If @rq has leftover, sets it up for the next range of segments. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + **/ +static inline bool blk_end_request(struct request *rq, int error, + unsigned int nr_bytes) +{ + return blk_end_bidi_request(rq, error, nr_bytes, 0); +} + +/** + * __blk_end_request - Helper function for drivers to complete the request. + * @rq: the request being processed + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete + * + * Description: + * Must be called with queue lock held unlike blk_end_request(). + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + **/ +static inline bool __blk_end_request(struct request *rq, int error, + unsigned int nr_bytes) +{ + return __blk_end_bidi_request(rq, error, nr_bytes, 0); +} + +/** + * end_request - end I/O on the current segment of the request + * @rq: the request being processed + * @uptodate: error value or %0/%1 uptodate flag + * + * Description: + * Ends I/O on the current segment of a request. If that is the only + * remaining segment, the request is also completed and freed. + * + * This is a remnant of how older block drivers handled I/O completions. + * Modern drivers typically end I/O on the full request in one go, unless + * they have a residual value to account for. For that case this function + * isn't really useful, unless the residual just happens to be the + * full current segment. In other words, don't use this function in new + * code. Use blk_end_request() or __blk_end_request() to end a request. + **/ +static inline void end_request(struct request *rq, int uptodate) +{ + int error = 0; + + if (uptodate <= 0) + error = uptodate ? uptodate : -EIO; + + __blk_end_bidi_request(rq, error, rq->hard_cur_sectors << 9, 0); +} + extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); extern void blk_abort_queue(struct request_queue *); -extern void blk_update_request(struct request *rq, int error, - unsigned int nr_bytes); /* * Access functions for manipulating queue properties -- cgit v1.2.3 From 40cbbb781d3eba5d6ac0860db078af490e5c7c6b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:19 +0900 Subject: block: implement and use [__]blk_end_request_all() There are many [__]blk_end_request() call sites which call it with full request length and expect full completion. Many of them ensure that the request actually completes by doing BUG_ON() the return value, which is awkward and error-prone. This patch adds [__]blk_end_request_all() which takes @rq and @error and fully completes the request. BUG_ON() is added to to ensure that this actually happens. Most conversions are simple but there are a few noteworthy ones. * cdrom/viocd: viocd_end_request() replaced with direct calls to __blk_end_request_all(). * s390/block/dasd: dasd_end_request() replaced with direct calls to __blk_end_request_all(). * s390/char/tape_block: tapeblock_end_request() replaced with direct calls to blk_end_request_all(). [ Impact: cleanup ] Signed-off-by: Tejun Heo Cc: Russell King Cc: Stephen Rothwell Cc: Mike Miller Cc: Martin Schwidefsky Cc: Jeff Garzik Cc: Rusty Russell Cc: Jeremy Fitzhardinge Cc: Alex Dubov Cc: James Bottomley --- include/linux/blkdev.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 501f6845cc7..e33c8356b3d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -882,6 +882,22 @@ static inline bool blk_end_request(struct request *rq, int error, return blk_end_bidi_request(rq, error, nr_bytes, 0); } +/** + * blk_end_request_all - Helper function for drives to finish the request. + * @rq: the request to finish + * @err: %0 for success, < %0 for error + * + * Description: + * Completely finish @rq. + */ +static inline void blk_end_request_all(struct request *rq, int error) +{ + bool pending; + + pending = blk_end_request(rq, error, blk_rq_bytes(rq)); + BUG_ON(pending); +} + /** * __blk_end_request - Helper function for drivers to complete the request. * @rq: the request being processed @@ -901,6 +917,22 @@ static inline bool __blk_end_request(struct request *rq, int error, return __blk_end_bidi_request(rq, error, nr_bytes, 0); } +/** + * __blk_end_request_all - Helper function for drives to finish the request. + * @rq: the request to finish + * @err: %0 for success, < %0 for error + * + * Description: + * Completely finish @rq. Must be called with queue lock held. + */ +static inline void __blk_end_request_all(struct request *rq, int error) +{ + bool pending; + + pending = __blk_end_request(rq, error, blk_rq_bytes(rq)); + BUG_ON(pending); +} + /** * end_request - end I/O on the current segment of the request * @rq: the request being processed -- cgit v1.2.3 From f06d9a2b52e246a66b606130cea3f0d7b7be17a7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:19 +0900 Subject: block: replace end_request() with [__]blk_end_request_cur() end_request() has been kept around for backward compatibility; however, it's about time for it to go away. * There aren't too many users left. * Its use of @updtodate is pretty confusing. * In some cases, newer code ends up using mixture of end_request() and [__]blk_end_request[_all](), which is way too confusing. So, add [__]blk_end_request_cur() and replace end_request() with it. Most conversions are straightforward. Noteworthy ones are... * paride/pcd: next_request() updated to take 0/-errno instead of 1/0. * paride/pf: pf_end_request() and next_request() updated to take 0/-errno instead of 1/0. * xd: xd_readwrite() updated to return 0/-errno instead of 1/0. * mtd/mtd_blkdevs: blktrans_discard_request() updated to return 0/-errno instead of 1/0. Unnecessary local variable res initialization removed from mtd_blktrans_thread(). [ Impact: cleanup ] Signed-off-by: Tejun Heo Acked-by: Joerg Dorchain Acked-by: Geert Uytterhoeven Acked-by: Grant Likely Acked-by: Laurent Vivier Cc: Tim Waugh Cc: Stephen Rothwell Cc: Paul Mackerras Cc: Jeremy Fitzhardinge Cc: Markus Lidel Cc: David Woodhouse Cc: Pete Zaitcev Cc: unsik Kim --- include/linux/blkdev.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e33c8356b3d..cfeb3c2feb2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -845,9 +845,8 @@ extern unsigned int blk_rq_cur_bytes(struct request *rq); * blk_update_request() completes given number of bytes and updates * the request without completing it. * - * blk_end_request() and friends. __blk_end_request() and - * end_request() must be called with the request queue spinlock - * acquired. + * blk_end_request() and friends. __blk_end_request() must be called + * with the request queue spinlock acquired. * * Several drivers define their own end_request and call * blk_end_request() for parts of the original function. @@ -898,6 +897,19 @@ static inline void blk_end_request_all(struct request *rq, int error) BUG_ON(pending); } +/** + * blk_end_request_cur - Helper function to finish the current request chunk. + * @rq: the request to finish the current chunk for + * @err: %0 for success, < %0 for error + * + * Description: + * Complete the current consecutively mapped chunk from @rq. + */ +static inline void blk_end_request_cur(struct request *rq, int error) +{ + blk_end_request(rq, error, rq->hard_cur_sectors << 9); +} + /** * __blk_end_request - Helper function for drivers to complete the request. * @rq: the request being processed @@ -934,29 +946,17 @@ static inline void __blk_end_request_all(struct request *rq, int error) } /** - * end_request - end I/O on the current segment of the request - * @rq: the request being processed - * @uptodate: error value or %0/%1 uptodate flag + * __blk_end_request_cur - Helper function to finish the current request chunk. + * @rq: the request to finish the current chunk for + * @err: %0 for success, < %0 for error * * Description: - * Ends I/O on the current segment of a request. If that is the only - * remaining segment, the request is also completed and freed. - * - * This is a remnant of how older block drivers handled I/O completions. - * Modern drivers typically end I/O on the full request in one go, unless - * they have a residual value to account for. For that case this function - * isn't really useful, unless the residual just happens to be the - * full current segment. In other words, don't use this function in new - * code. Use blk_end_request() or __blk_end_request() to end a request. - **/ -static inline void end_request(struct request *rq, int uptodate) + * Complete the current consecutively mapped chunk from @rq. Must + * be called with queue lock held. + */ +static inline void __blk_end_request_cur(struct request *rq, int error) { - int error = 0; - - if (uptodate <= 0) - error = uptodate ? uptodate : -EIO; - - __blk_end_bidi_request(rq, error, rq->hard_cur_sectors << 9, 0); + __blk_end_request(rq, error, rq->hard_cur_sectors << 9); } extern void blk_complete_request(struct request *); -- cgit v1.2.3 From 731ec497e5888c6792ad62613ae9be97eebcd7ca Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 23 Apr 2009 11:05:20 +0900 Subject: block: kill rq->data Now that all block request data transfer is done via bio, rq->data isn't used. Kill it. While at it, make the roles of rq->special and buffer clear. [ Impact: drop now unncessary field from struct request ] Signed-off-by: Tejun Heo Cc: Boaz Harrosh --- include/linux/blkdev.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cfeb3c2feb2..12c545e2737 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -211,8 +211,8 @@ struct request { unsigned short ioprio; - void *special; - char *buffer; + void *special; /* opaque pointer available for LLD use */ + char *buffer; /* kaddr of the current segment if available */ int tag; int errors; @@ -229,7 +229,6 @@ struct request { unsigned int data_len; unsigned int extra_len; /* length of alignment and padding */ unsigned int sense_len; - void *data; void *sense; unsigned long deadline; -- cgit v1.2.3 From 9fd8d0e1bcb848257968d9a7d73ca4d890ea8bd1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 28 Apr 2009 13:06:04 +0900 Subject: block: make blk_end_request_cur() return bool In the process of mindlessly copying [__]blk_end_request_all(), [__]blk_end_request_cur() ended up returning void even though they're partial completion functions. Fix it. [ Impact: fix braindead API ] Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 12c545e2737..3a5b1bd6582 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -903,10 +903,14 @@ static inline void blk_end_request_all(struct request *rq, int error) * * Description: * Complete the current consecutively mapped chunk from @rq. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request */ -static inline void blk_end_request_cur(struct request *rq, int error) +static inline bool blk_end_request_cur(struct request *rq, int error) { - blk_end_request(rq, error, rq->hard_cur_sectors << 9); + return blk_end_request(rq, error, rq->hard_cur_sectors << 9); } /** @@ -952,10 +956,14 @@ static inline void __blk_end_request_all(struct request *rq, int error) * Description: * Complete the current consecutively mapped chunk from @rq. Must * be called with queue lock held. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request */ -static inline void __blk_end_request_cur(struct request *rq, int error) +static inline bool __blk_end_request_cur(struct request *rq, int error) { - __blk_end_request(rq, error, rq->hard_cur_sectors << 9); + return __blk_end_request(rq, error, rq->hard_cur_sectors << 9); } extern void blk_complete_request(struct request *); -- cgit v1.2.3 From eec9462088a26c046d4db3100796a340a50890b8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 28 Apr 2009 13:06:14 +0900 Subject: mg_disk: fold mg_disk.h into mg_disk.c include/linux/mg_disk.h is used only by drivers/block/mg_disk.c. No reason to put it in a separate header. Fold it into mg_disk.c. [ Impact: cleanup ] Signed-off-by: Tejun Heo Cc: unsik Kim Signed-off-by: Jens Axboe --- include/linux/mg_disk.h | 206 ------------------------------------------------ 1 file changed, 206 deletions(-) delete mode 100644 include/linux/mg_disk.h (limited to 'include') diff --git a/include/linux/mg_disk.h b/include/linux/mg_disk.h deleted file mode 100644 index 1f76b1ebf62..00000000000 --- a/include/linux/mg_disk.h +++ /dev/null @@ -1,206 +0,0 @@ -/* - * include/linux/mg_disk.c - * - * Support for the mGine m[g]flash IO mode. - * Based on legacy hd.c - * - * (c) 2008 mGine Co.,LTD - * (c) 2008 unsik Kim - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __MG_DISK_H__ -#define __MG_DISK_H__ - -#include -#include - -/* name for block device */ -#define MG_DISK_NAME "mgd" -/* name for platform device */ -#define MG_DEV_NAME "mg_disk" - -#define MG_DISK_MAJ 0 -#define MG_DISK_MAX_PART 16 -#define MG_SECTOR_SIZE 512 -#define MG_MAX_SECTS 256 - -/* Register offsets */ -#define MG_BUFF_OFFSET 0x8000 -#define MG_STORAGE_BUFFER_SIZE 0x200 -#define MG_REG_OFFSET 0xC000 -#define MG_REG_FEATURE (MG_REG_OFFSET + 2) /* write case */ -#define MG_REG_ERROR (MG_REG_OFFSET + 2) /* read case */ -#define MG_REG_SECT_CNT (MG_REG_OFFSET + 4) -#define MG_REG_SECT_NUM (MG_REG_OFFSET + 6) -#define MG_REG_CYL_LOW (MG_REG_OFFSET + 8) -#define MG_REG_CYL_HIGH (MG_REG_OFFSET + 0xA) -#define MG_REG_DRV_HEAD (MG_REG_OFFSET + 0xC) -#define MG_REG_COMMAND (MG_REG_OFFSET + 0xE) /* write case */ -#define MG_REG_STATUS (MG_REG_OFFSET + 0xE) /* read case */ -#define MG_REG_DRV_CTRL (MG_REG_OFFSET + 0x10) -#define MG_REG_BURST_CTRL (MG_REG_OFFSET + 0x12) - -/* "Drive Select/Head Register" bit values */ -#define MG_REG_HEAD_MUST_BE_ON 0xA0 /* These 2 bits are always on */ -#define MG_REG_HEAD_DRIVE_MASTER (0x00 | MG_REG_HEAD_MUST_BE_ON) -#define MG_REG_HEAD_DRIVE_SLAVE (0x10 | MG_REG_HEAD_MUST_BE_ON) -#define MG_REG_HEAD_LBA_MODE (0x40 | MG_REG_HEAD_MUST_BE_ON) - - -/* "Device Control Register" bit values */ -#define MG_REG_CTRL_INTR_ENABLE 0x0 -#define MG_REG_CTRL_INTR_DISABLE (0x1<<1) -#define MG_REG_CTRL_RESET (0x1<<2) -#define MG_REG_CTRL_INTR_POLA_ACTIVE_HIGH 0x0 -#define MG_REG_CTRL_INTR_POLA_ACTIVE_LOW (0x1<<4) -#define MG_REG_CTRL_DPD_POLA_ACTIVE_LOW 0x0 -#define MG_REG_CTRL_DPD_POLA_ACTIVE_HIGH (0x1<<5) -#define MG_REG_CTRL_DPD_DISABLE 0x0 -#define MG_REG_CTRL_DPD_ENABLE (0x1<<6) - -/* Status register bit */ -/* error bit in status register */ -#define MG_REG_STATUS_BIT_ERROR 0x01 -/* corrected error in status register */ -#define MG_REG_STATUS_BIT_CORRECTED_ERROR 0x04 -/* data request bit in status register */ -#define MG_REG_STATUS_BIT_DATA_REQ 0x08 -/* DSC - Drive Seek Complete */ -#define MG_REG_STATUS_BIT_SEEK_DONE 0x10 -/* DWF - Drive Write Fault */ -#define MG_REG_STATUS_BIT_WRITE_FAULT 0x20 -#define MG_REG_STATUS_BIT_READY 0x40 -#define MG_REG_STATUS_BIT_BUSY 0x80 - -/* handy status */ -#define MG_STAT_READY (MG_REG_STATUS_BIT_READY | MG_REG_STATUS_BIT_SEEK_DONE) -#define MG_READY_OK(s) (((s) & (MG_STAT_READY | \ - (MG_REG_STATUS_BIT_BUSY | \ - MG_REG_STATUS_BIT_WRITE_FAULT | \ - MG_REG_STATUS_BIT_ERROR))) == MG_STAT_READY) - -/* Error register */ -#define MG_REG_ERR_AMNF 0x01 -#define MG_REG_ERR_ABRT 0x04 -#define MG_REG_ERR_IDNF 0x10 -#define MG_REG_ERR_UNC 0x40 -#define MG_REG_ERR_BBK 0x80 - -/* error code for others */ -#define MG_ERR_NONE 0 -#define MG_ERR_TIMEOUT 0x100 -#define MG_ERR_INIT_STAT 0x101 -#define MG_ERR_TRANSLATION 0x102 -#define MG_ERR_CTRL_RST 0x103 -#define MG_ERR_INV_STAT 0x104 -#define MG_ERR_RSTOUT 0x105 - -#define MG_MAX_ERRORS 6 /* Max read/write errors */ - -/* command */ -#define MG_CMD_RD 0x20 -#define MG_CMD_WR 0x30 -#define MG_CMD_SLEEP 0x99 -#define MG_CMD_WAKEUP 0xC3 -#define MG_CMD_ID 0xEC -#define MG_CMD_WR_CONF 0x3C -#define MG_CMD_RD_CONF 0x40 - -/* operation mode */ -#define MG_OP_CASCADE (1 << 0) -#define MG_OP_CASCADE_SYNC_RD (1 << 1) -#define MG_OP_CASCADE_SYNC_WR (1 << 2) -#define MG_OP_INTERLEAVE (1 << 3) - -/* synchronous */ -#define MG_BURST_LAT_4 (3 << 4) -#define MG_BURST_LAT_5 (4 << 4) -#define MG_BURST_LAT_6 (5 << 4) -#define MG_BURST_LAT_7 (6 << 4) -#define MG_BURST_LAT_8 (7 << 4) -#define MG_BURST_LEN_4 (1 << 1) -#define MG_BURST_LEN_8 (2 << 1) -#define MG_BURST_LEN_16 (3 << 1) -#define MG_BURST_LEN_32 (4 << 1) -#define MG_BURST_LEN_CONT (0 << 1) - -/* timeout value (unit: ms) */ -#define MG_TMAX_CONF_TO_CMD 1 -#define MG_TMAX_WAIT_RD_DRQ 10 -#define MG_TMAX_WAIT_WR_DRQ 500 -#define MG_TMAX_RST_TO_BUSY 10 -#define MG_TMAX_HDRST_TO_RDY 500 -#define MG_TMAX_SWRST_TO_RDY 500 -#define MG_TMAX_RSTOUT 3000 - -/* device attribution */ -/* use mflash as boot device */ -#define MG_BOOT_DEV (1 << 0) -/* use mflash as storage device */ -#define MG_STORAGE_DEV (1 << 1) -/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */ -#define MG_STORAGE_DEV_SKIP_RST (1 << 2) - -#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST) - -/* names of GPIO resource */ -#define MG_RST_PIN "mg_rst" -/* except MG_BOOT_DEV, reset-out pin should be assigned */ -#define MG_RSTOUT_PIN "mg_rstout" - -/* private driver data */ -struct mg_drv_data { - /* disk resource */ - u32 use_polling; - - /* device attribution */ - u32 dev_attr; - - /* internally used */ - struct mg_host *host; -}; - -/* main structure for mflash driver */ -struct mg_host { - struct device *dev; - - struct request_queue *breq; - spinlock_t lock; - struct gendisk *gd; - - struct timer_list timer; - void (*mg_do_intr) (struct mg_host *); - - u16 id[ATA_ID_WORDS]; - - u16 cyls; - u16 heads; - u16 sectors; - u32 n_sectors; - u32 nres_sectors; - - void __iomem *dev_base; - unsigned int irq; - unsigned int rst; - unsigned int rstout; - - u32 major; - u32 error; -}; - -/* - * Debugging macro and defines - */ -#undef DO_MG_DEBUG -#ifdef DO_MG_DEBUG -# define MG_DBG(fmt, args...) \ - printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args) -#else /* CONFIG_MG_DEBUG */ -# define MG_DBG(fmt, args...) do { } while (0) -#endif /* CONFIG_MG_DEBUG */ - -#endif -- cgit v1.2.3 From c3a4d78c580de4edc9ef0f7c59812fb02ceb037f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 May 2009 22:24:37 +0900 Subject: block: add rq->resid_len rq->data_len served two purposes - the length of data buffer on issue and the residual count on completion. This duality creates some headaches. First of all, block layer and low level drivers can't really determine what rq->data_len contains while a request is executing. It could be the total request length or it coulde be anything else one of the lower layers is using to keep track of residual count. This complicates things because blk_rq_bytes() and thus [__]blk_end_request_all() relies on rq->data_len for PC commands. Drivers which want to report residual count should first cache the total request length, update rq->data_len and then complete the request with the cached data length. Secondly, it makes requests default to reporting full residual count, ie. reporting that no data transfer occurred. The residual count is an exception not the norm; however, the driver should clear rq->data_len to zero to signify the normal cases while leaving it alone means no data transfer occurred at all. This reverse default behavior complicates code unnecessarily and renders block PC on some drivers (ide-tape/floppy) unuseable. This patch adds rq->resid_len which is used only for residual count. While at it, remove now unnecessasry blk_rq_bytes() caching in ide_pc_intr() as rq->data_len is not changed anymore. Boaz : spotted missing conversion in osd Sergei : spotted too early conversion to blk_rq_bytes() in ide-tape [ Impact: cleanup residual count handling, report 0 resid by default ] Signed-off-by: Tejun Heo Cc: James Bottomley Cc: Bartlomiej Zolnierkiewicz Cc: Borislav Petkov Cc: Sergei Shtylyov Cc: Mike Miller Cc: Eric Moore Cc: Alan Stern Cc: FUJITA Tomonori Cc: Doug Gilbert Cc: Mike Miller Cc: Eric Moore Cc: Darrick J. Wong Cc: Pete Zaitcev Cc: Boaz Harrosh Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3a5b1bd6582..6a967cad89f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -229,6 +229,7 @@ struct request { unsigned int data_len; unsigned int extra_len; /* length of alignment and padding */ unsigned int sense_len; + unsigned int resid_len; /* residual count */ void *sense; unsigned long deadline; -- cgit v1.2.3 From 5b93629b4509c03ffa87a9316412fedf6f58cb37 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 May 2009 22:24:38 +0900 Subject: block: implement blk_rq_pos/[cur_]sectors() and convert obvious ones Implement accessors - blk_rq_pos(), blk_rq_sectors() and blk_rq_cur_sectors() which return rq->hard_sector, rq->hard_nr_sectors and rq->hard_cur_sectors respectively and convert direct references of the said fields to the accessors. This is in preparation of request data length handling cleanup. Geert : suggested adding const to struct request * parameter to accessors Sergei : spotted error in patch description [ Impact: cleanup ] Signed-off-by: Tejun Heo Acked-by: Geert Uytterhoeven Acked-by: Stephen Rothwell Tested-by: Grant Likely Acked-by: Grant Likely Ackec-by: Sergei Shtylyov Cc: Bartlomiej Zolnierkiewicz Cc: Borislav Petkov Cc: James Bottomley Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6a967cad89f..4e5f8559872 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -832,13 +832,30 @@ static inline void blk_run_address_space(struct address_space *mapping) extern void blkdev_dequeue_request(struct request *req); /* - * blk_end_request() takes bytes instead of sectors as a complete size. - * blk_rq_bytes() returns bytes left to complete in the entire request. - * blk_rq_cur_bytes() returns bytes left to complete in the current segment. + * blk_rq_pos() : the current sector + * blk_rq_bytes() : bytes left in the entire request + * blk_rq_cur_bytes() : bytes left in the current segment + * blk_rq_sectors() : sectors left in the entire request + * blk_rq_cur_sectors() : sectors left in the current segment */ +static inline sector_t blk_rq_pos(const struct request *rq) +{ + return rq->hard_sector; +} + extern unsigned int blk_rq_bytes(struct request *rq); extern unsigned int blk_rq_cur_bytes(struct request *rq); +static inline unsigned int blk_rq_sectors(const struct request *rq) +{ + return rq->hard_nr_sectors; +} + +static inline unsigned int blk_rq_cur_sectors(const struct request *rq) +{ + return rq->hard_cur_sectors; +} + /* * Request completion related functions. * -- cgit v1.2.3 From 83096ebf1263b2c1ee5e653ba37d993d02e3eb7b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 May 2009 22:24:39 +0900 Subject: block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo Acked-by: Geert Uytterhoeven Tested-by: Grant Likely Acked-by: Grant Likely Tested-by: Adrian McMenamin Acked-by: Adrian McMenamin Acked-by: Mike Miller Cc: James Bottomley Cc: Bartlomiej Zolnierkiewicz Cc: Borislav Petkov Cc: Sergei Shtylyov Cc: Eric Moore Cc: Alan Stern Cc: FUJITA Tomonori Cc: Pete Zaitcev Cc: Stephen Rothwell Cc: Paul Clements Cc: Tim Waugh Cc: Jeff Garzik Cc: Jeremy Fitzhardinge Cc: Alex Dubov Cc: David Woodhouse Cc: Martin Schwidefsky Cc: Dario Ballabio Cc: David S. Miller Cc: Rusty Russell Cc: unsik Kim Cc: Laurent Vivier Signed-off-by: Jens Axboe --- include/scsi/scsi_cmnd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 43b50d36925..3878d1dc7f5 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -270,7 +270,7 @@ static inline unsigned char scsi_get_prot_type(struct scsi_cmnd *scmd) static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd) { - return scmd->request->sector; + return blk_rq_pos(scmd->request); } static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd) -- 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 --- include/linux/bio.h | 6 +++--- include/linux/blkdev.h | 37 ++++++++++++++++--------------------- include/linux/elevator.h | 2 +- 3 files changed, 20 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index f37ca8c726b..d30ec6f30dd 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -218,12 +218,12 @@ struct bio { #define bio_sectors(bio) ((bio)->bi_size >> 9) #define bio_empty_barrier(bio) (bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio)) -static inline unsigned int bio_cur_sectors(struct bio *bio) +static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio->bi_vcnt) - return bio_iovec(bio)->bv_len >> 9; + return bio_iovec(bio)->bv_len; else /* dataless requests such as discard */ - return bio->bi_size >> 9; + return bio->bi_size; } static inline void *bio_data(struct bio *bio) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4e5f8559872..ce2bf5efa9b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -166,19 +166,8 @@ struct request { enum rq_cmd_type_bits cmd_type; unsigned long atomic_flags; - /* Maintain bio traversal state for part by part I/O submission. - * hard_* are block layer internals, no driver should touch them! - */ - - sector_t sector; /* next sector to submit */ - sector_t hard_sector; /* next sector to complete */ - unsigned long nr_sectors; /* no. of sectors left to submit */ - unsigned long hard_nr_sectors; /* no. of sectors left to complete */ - /* no. of sectors left to submit in the current segment */ - unsigned int current_nr_sectors; - - /* no. of sectors left to complete in the current segment */ - unsigned int hard_cur_sectors; + sector_t sector; /* sector cursor */ + unsigned int data_len; /* total data len, don't access directly */ struct bio *bio; struct bio *biotail; @@ -226,7 +215,6 @@ struct request { unsigned char __cmd[BLK_MAX_CDB]; unsigned char *cmd; - unsigned int data_len; unsigned int extra_len; /* length of alignment and padding */ unsigned int sense_len; unsigned int resid_len; /* residual count */ @@ -840,20 +828,27 @@ extern void blkdev_dequeue_request(struct request *req); */ static inline sector_t blk_rq_pos(const struct request *rq) { - return rq->hard_sector; + return rq->sector; +} + +static inline unsigned int blk_rq_bytes(const struct request *rq) +{ + return rq->data_len; } -extern unsigned int blk_rq_bytes(struct request *rq); -extern unsigned int blk_rq_cur_bytes(struct request *rq); +static inline int blk_rq_cur_bytes(const struct request *rq) +{ + return rq->bio ? bio_cur_bytes(rq->bio) : 0; +} static inline unsigned int blk_rq_sectors(const struct request *rq) { - return rq->hard_nr_sectors; + return blk_rq_bytes(rq) >> 9; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { - return rq->hard_cur_sectors; + return blk_rq_cur_bytes(rq) >> 9; } /* @@ -928,7 +923,7 @@ static inline void blk_end_request_all(struct request *rq, int error) */ static inline bool blk_end_request_cur(struct request *rq, int error) { - return blk_end_request(rq, error, rq->hard_cur_sectors << 9); + return blk_end_request(rq, error, blk_rq_cur_bytes(rq)); } /** @@ -981,7 +976,7 @@ static inline void __blk_end_request_all(struct request *rq, int error) */ static inline bool __blk_end_request_cur(struct request *rq, int error) { - return __blk_end_request(rq, error, rq->hard_cur_sectors << 9); + return __blk_end_request(rq, error, blk_rq_cur_bytes(rq)); } extern void blk_complete_request(struct request *); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index c59b769f62b..4e462878c9c 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -171,7 +171,7 @@ enum { ELV_MQUEUE_MUST, }; -#define rq_end_sector(rq) ((rq)->sector + (rq)->nr_sectors) +#define rq_end_sector(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq)) #define rb_entry_rq(node) rb_entry((node), struct request, rb_node) /* -- cgit v1.2.3 From a2dec7b36364a5cc564c4d76cf16d2e7d33f5c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 May 2009 22:24:44 +0900 Subject: block: hide request sector and data_len Block low level drivers for some reason have been pretty good at abusing block layer API. Especially struct request's fields tend to get violated in all possible ways. Make it clear that low level drivers MUST NOT access or manipulate rq->sector and rq->data_len directly by prefixing them with double underscores. This change is also necessary to break build of out-of-tree codes which assume the previous block API where internal fields can be manipulated and rq->data_len carries residual count on completion. [ Impact: hide internal fields, block API change ] Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ce2bf5efa9b..c7558034570 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -166,8 +166,9 @@ struct request { enum rq_cmd_type_bits cmd_type; unsigned long atomic_flags; - sector_t sector; /* sector cursor */ - unsigned int data_len; /* total data len, don't access directly */ + /* the following two fields are internal, NEVER access directly */ + sector_t __sector; /* sector cursor */ + unsigned int __data_len; /* total data len */ struct bio *bio; struct bio *biotail; @@ -828,12 +829,12 @@ extern void blkdev_dequeue_request(struct request *req); */ static inline sector_t blk_rq_pos(const struct request *rq) { - return rq->sector; + return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { - return rq->data_len; + return rq->__data_len; } static inline int blk_rq_cur_bytes(const struct request *rq) -- 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 --- include/linux/blkdev.h | 9 +++++++-- include/linux/elevator.h | 2 -- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c7558034570..6e59d3b92ff 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -818,8 +818,6 @@ static inline void blk_run_address_space(struct address_space *mapping) blk_run_backing_dev(mapping->backing_dev_info, NULL); } -extern void blkdev_dequeue_request(struct request *req); - /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request @@ -852,6 +850,13 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } +/* + * Request issue related functions. + */ +extern struct request *blk_peek_request(struct request_queue *q); +extern void blk_start_request(struct request *rq); +extern struct request *blk_fetch_request(struct request_queue *q); + /* * Request completion related functions. * diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 4e462878c9c..1cb3372e65d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -103,10 +103,8 @@ extern int elv_merge(struct request_queue *, struct request **, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, int); -extern void elv_dequeue_request(struct request_queue *, struct request *); extern void elv_requeue_request(struct request_queue *, struct request *); extern int elv_queue_empty(struct request_queue *); -extern struct request *elv_next_request(struct request_queue *q); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); extern int elv_register_queue(struct request_queue *q); -- cgit v1.2.3 From 1822952ba2b9f22f79019d07ebbeca31dc14b718 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 11 May 2009 17:56:07 +0900 Subject: block: let blk_end_request_all handle bidi requests blk_end_request_all() and __blk_end_request_all() should finish all bytes including bidi, by definition. That's what all bidi users need , bidi requests must be complete as a whole (partial completion is impossible). Signed-off-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6e59d3b92ff..1069f4483c6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -910,8 +910,12 @@ static inline bool blk_end_request(struct request *rq, int error, static inline void blk_end_request_all(struct request *rq, int error) { bool pending; + unsigned int bidi_bytes = 0; - pending = blk_end_request(rq, error, blk_rq_bytes(rq)); + if (unlikely(blk_bidi_rq(rq))) + bidi_bytes = blk_rq_bytes(rq->next_rq); + + pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); BUG_ON(pending); } @@ -962,8 +966,12 @@ static inline bool __blk_end_request(struct request *rq, int error, static inline void __blk_end_request_all(struct request *rq, int error) { bool pending; + unsigned int bidi_bytes = 0; + + if (unlikely(blk_bidi_rq(rq))) + bidi_bytes = blk_rq_bytes(rq->next_rq); - pending = __blk_end_request(rq, error, blk_rq_bytes(rq)); + pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); BUG_ON(pending); } -- cgit v1.2.3 From b1f744937f1be3e6d3009382a755679133cf782d Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 11 May 2009 17:56:09 +0900 Subject: block: move completion related functions back to blk-core.c Let's put the completion related functions back to block/blk-core.c where they have lived. We can also unexport blk_end_bidi_request() and __blk_end_bidi_request(), which nobody uses. Signed-off-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 128 ++++--------------------------------------------- 1 file changed, 8 insertions(+), 120 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1069f4483c6..f9d60a78c08 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -872,126 +872,14 @@ extern struct request *blk_fetch_request(struct request_queue *q); */ extern bool blk_update_request(struct request *rq, int error, unsigned int nr_bytes); -extern bool blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, - unsigned int bidi_bytes); -extern bool __blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, - unsigned int bidi_bytes); - -/** - * blk_end_request - Helper function for drivers to complete the request. - * @rq: the request being processed - * @error: %0 for success, < %0 for error - * @nr_bytes: number of bytes to complete - * - * Description: - * Ends I/O on a number of bytes attached to @rq. - * If @rq has leftover, sets it up for the next range of segments. - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - **/ -static inline bool blk_end_request(struct request *rq, int error, - unsigned int nr_bytes) -{ - return blk_end_bidi_request(rq, error, nr_bytes, 0); -} - -/** - * blk_end_request_all - Helper function for drives to finish the request. - * @rq: the request to finish - * @err: %0 for success, < %0 for error - * - * Description: - * Completely finish @rq. - */ -static inline void blk_end_request_all(struct request *rq, int error) -{ - bool pending; - unsigned int bidi_bytes = 0; - - if (unlikely(blk_bidi_rq(rq))) - bidi_bytes = blk_rq_bytes(rq->next_rq); - - pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); - BUG_ON(pending); -} - -/** - * blk_end_request_cur - Helper function to finish the current request chunk. - * @rq: the request to finish the current chunk for - * @err: %0 for success, < %0 for error - * - * Description: - * Complete the current consecutively mapped chunk from @rq. - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - */ -static inline bool blk_end_request_cur(struct request *rq, int error) -{ - return blk_end_request(rq, error, blk_rq_cur_bytes(rq)); -} - -/** - * __blk_end_request - Helper function for drivers to complete the request. - * @rq: the request being processed - * @error: %0 for success, < %0 for error - * @nr_bytes: number of bytes to complete - * - * Description: - * Must be called with queue lock held unlike blk_end_request(). - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - **/ -static inline bool __blk_end_request(struct request *rq, int error, - unsigned int nr_bytes) -{ - return __blk_end_bidi_request(rq, error, nr_bytes, 0); -} - -/** - * __blk_end_request_all - Helper function for drives to finish the request. - * @rq: the request to finish - * @err: %0 for success, < %0 for error - * - * Description: - * Completely finish @rq. Must be called with queue lock held. - */ -static inline void __blk_end_request_all(struct request *rq, int error) -{ - bool pending; - unsigned int bidi_bytes = 0; - - if (unlikely(blk_bidi_rq(rq))) - bidi_bytes = blk_rq_bytes(rq->next_rq); - - pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); - BUG_ON(pending); -} - -/** - * __blk_end_request_cur - Helper function to finish the current request chunk. - * @rq: the request to finish the current chunk for - * @err: %0 for success, < %0 for error - * - * Description: - * Complete the current consecutively mapped chunk from @rq. Must - * be called with queue lock held. - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - */ -static inline bool __blk_end_request_cur(struct request *rq, int error) -{ - return __blk_end_request(rq, error, blk_rq_cur_bytes(rq)); -} +extern bool blk_end_request(struct request *rq, int error, + unsigned int nr_bytes); +extern void blk_end_request_all(struct request *rq, int error); +extern bool blk_end_request_cur(struct request *rq, int error); +extern bool __blk_end_request(struct request *rq, int error, + unsigned int nr_bytes); +extern void __blk_end_request_all(struct request *rq, int error); +extern bool __blk_end_request_cur(struct request *rq, int error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); -- cgit v1.2.3 From 6818173bd658439b83896a2a7586f64ab51bf29c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 7 May 2009 15:37:36 +0200 Subject: splice: implement default splice_read method If f_op->splice_read() is not implemented, fall back to a plain read. Use vfs_readv() to read into previously allocated pages. This will allow splice and functions using splice, such as the loop device, to work on all filesystems. This includes "direct_io" files in fuse which bypass the page cache. Signed-off-by: Miklos Szeredi Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 ++ include/linux/pipe_fs_i.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5bed436f435..d926c2bea16 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2204,6 +2204,8 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); +extern ssize_t default_file_splice_read(struct file *, loff_t *, + struct pipe_inode_info *, size_t, unsigned int); extern ssize_t generic_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index c8f038554e8..b43a9e03905 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -152,5 +152,6 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *, struct pipe_buffer *, void void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); +void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); #endif -- cgit v1.2.3 From 2b1ccc0ee918a653d0483fdad9dd6112ce8e9043 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 May 2009 11:11:48 +0200 Subject: splice: fix misleading comment Splice is tied to pipes by design, it'll not change. And now that the splice stuff is in splice.h (and note pipe.h), the rest of the comment is out-of-date as well. Signed-off-by: Jens Axboe --- include/linux/splice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/splice.h b/include/linux/splice.h index 5f3faa9d15a..18e7c7c0cae 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -11,8 +11,7 @@ #include /* - * splice is tied to pipes as a transport (at least for now), so we'll just - * add the splice flags here. + * Flags passed in from splice/tee/vmsplice */ #define SPLICE_F_MOVE (0x01) /* move pages instead of copying */ #define SPLICE_F_NONBLOCK (0x02) /* don't block on the pipe splicing (but */ -- cgit v1.2.3 From 1cde26f928863d90e9e7c1217880c8450464d305 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 18 May 2009 14:41:30 +0200 Subject: virtio_blk: SG_IO passthru support Add support for SG_IO passthru to virtio_blk. We add the scsi command block after the normal outhdr, and the scsi inhdr with full status information aswell as the sense buffer before the regular inhdr. [hch: forward ported, added the VIRTIO_BLK_F_SCSI flags, some comments and tested the whole beast] [axboe: updated to use ->resid and not dual-path the byte count] Signed-off-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Rusty Russell (+ checkpatch.pl tweak) Signed-off-by: Jens Axboe --- include/linux/virtio_blk.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index 94c56d29869..4dbcbc1c348 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -15,6 +15,7 @@ #define VIRTIO_BLK_F_GEOMETRY 4 /* Legacy geometry available */ #define VIRTIO_BLK_F_RO 5 /* Disk is read-only */ #define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/ +#define VIRTIO_BLK_F_SCSI 7 /* Supports scsi command passthru */ struct virtio_blk_config { @@ -55,6 +56,13 @@ struct virtio_blk_outhdr __u64 sector; }; +struct virtio_scsi_inhdr { + __u32 errors; + __u32 data_len; + __u32 sense_len; + __u32 residual; +}; + /* And this is the final byte of the write scatter-gather list. */ #define VIRTIO_BLK_S_OK 0 #define VIRTIO_BLK_S_IOERR 1 -- cgit v1.2.3 From 79eb63e9e5875b84341a3a05f8e6ae9cdb4bb6f6 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Sun, 17 May 2009 18:57:15 +0300 Subject: block: Add blk_make_request(), takes bio, returns a request New block API: given a struct bio allocates a new request. This is the parallel of generic_make_request for BLOCK_PC commands users. The passed bio may be a chained-bio. The bio is bounced if needed inside the call to this member. This is in the effort of un-exporting blk_rq_append_bio(). Signed-off-by: Boaz Harrosh CC: Jeff Garzik Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f9d60a78c08..88a83e112c9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -740,6 +740,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); 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 int blk_rq_check_limits(struct request_queue *q, struct request *rq); -- 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 --- include/linux/blkdev.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 88a83e112c9..564445be7a6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -757,12 +757,6 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); -/* - * Temporary export, until SCSI gets fixed up. - */ -extern int blk_rq_append_bio(struct request_queue *q, struct request *rq, - struct bio *bio); - /* * A queue has just exitted congestion. Note this in the global counter of * congested queues, and wake up anyone who was waiting for requests to be -- cgit v1.2.3 From 0a7ae2ff0d29bb3b327edff4c8ab67b3834fa811 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 20 May 2009 08:54:31 +0200 Subject: block: change the tag sync vs async restriction logic Make them fully share the tag space, but disallow async requests using the last any two slots. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 564445be7a6..a967dd775db 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -404,7 +404,7 @@ struct request_queue struct list_head tag_busy_list; unsigned int nr_sorted; - unsigned int in_flight; + unsigned int in_flight[2]; unsigned int rq_timeout; struct timer_list timeout; @@ -511,6 +511,11 @@ static inline void queue_flag_clear_unlocked(unsigned int flag, __clear_bit(flag, &q->queue_flags); } +static inline int queue_in_flight(struct request_queue *q) +{ + return q->in_flight[0] + q->in_flight[1]; +} + static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) { WARN_ON_ONCE(!queue_is_locked(q)); -- cgit v1.2.3 From e1defc4ff0cf57aca6c5e3ff99fa503f5943c1f1 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 22 May 2009 17:17:49 -0400 Subject: block: Do away with the notion of hardsect_size Until now we have had a 1:1 mapping between storage device physical block size and the logical block sized used when addressing the device. With SATA 4KB drives coming out that will no longer be the case. The sector size will be 4KB but the logical block size will remain 512-bytes. Hence we need to distinguish between the physical block size and the logical ditto. This patch renames hardsect_size to logical_block_size. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 +++++++------- include/linux/device-mapper.h | 2 +- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 56ce53fce72..872b78b7a10 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -391,7 +391,7 @@ struct request_queue unsigned int max_hw_sectors; unsigned short max_phys_segments; unsigned short max_hw_segments; - unsigned short hardsect_size; + unsigned short logical_block_size; unsigned int max_segment_size; unsigned long seg_boundary_mask; @@ -901,7 +901,7 @@ extern void blk_queue_max_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -extern void blk_queue_hardsect_size(struct request_queue *, unsigned short); +extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); extern void blk_queue_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); @@ -988,19 +988,19 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) -static inline int queue_hardsect_size(struct request_queue *q) +static inline unsigned short queue_logical_block_size(struct request_queue *q) { int retval = 512; - if (q && q->hardsect_size) - retval = q->hardsect_size; + if (q && q->logical_block_size) + retval = q->logical_block_size; return retval; } -static inline int bdev_hardsect_size(struct block_device *bdev) +static inline unsigned short bdev_logical_block_size(struct block_device *bdev) { - return queue_hardsect_size(bdev_get_queue(bdev)); + return queue_logical_block_size(bdev_get_queue(bdev)); } static inline int queue_dma_alignment(struct request_queue *q) diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ded2d7c4266..49c2362977f 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -149,7 +149,7 @@ struct io_restrictions { unsigned max_hw_sectors; unsigned max_sectors; unsigned max_segment_size; - unsigned short hardsect_size; + unsigned short logical_block_size; unsigned short max_hw_segments; unsigned short max_phys_segments; unsigned char no_cluster; /* inverted so that 0 is default */ -- cgit v1.2.3 From ae03bf639a5027d27270123f5f6e3ee6a412781d Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 22 May 2009 17:17:50 -0400 Subject: block: Use accessor functions for queue limits Convert all external users of queue limits to using wrapper functions instead of poking the request queue variables directly. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- include/linux/blkdev.h | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index d30ec6f30dd..12737be5860 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -279,7 +279,7 @@ static inline int bio_has_allocated_vec(struct bio *bio) #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \ (((addr1) | (mask)) == (((addr2) - 1) | (mask))) #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ - __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, (q)->seg_boundary_mask) + __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q))) #define BIO_SEG_BOUNDARY(q, b1, b2) \ BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2))) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 872b78b7a10..29b48f7b4ba 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -898,6 +898,7 @@ extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_sectors(struct request_queue *, unsigned int); +extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); @@ -988,6 +989,41 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) +static inline unsigned long queue_bounce_pfn(struct request_queue *q) +{ + return q->bounce_pfn; +} + +static inline unsigned long queue_segment_boundary(struct request_queue *q) +{ + return q->seg_boundary_mask; +} + +static inline unsigned int queue_max_sectors(struct request_queue *q) +{ + return q->max_sectors; +} + +static inline unsigned int queue_max_hw_sectors(struct request_queue *q) +{ + return q->max_hw_sectors; +} + +static inline unsigned short queue_max_hw_segments(struct request_queue *q) +{ + return q->max_hw_segments; +} + +static inline unsigned short queue_max_phys_segments(struct request_queue *q) +{ + return q->max_phys_segments; +} + +static inline unsigned int queue_max_segment_size(struct request_queue *q) +{ + return q->max_segment_size; +} + static inline unsigned short queue_logical_block_size(struct request_queue *q) { int retval = 512; -- cgit v1.2.3 From 025146e13b63483add912706c101fb0fb6f015cc Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 22 May 2009 17:17:51 -0400 Subject: block: Move queue limits to an embedded struct To accommodate stacking drivers that do not have an associated request queue we're moving the limits to a separate, embedded structure. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 44 ++++++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 29b48f7b4ba..b7bb6fdba12 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -307,6 +307,21 @@ struct blk_cmd_filter { struct kobject kobj; }; +struct queue_limits { + unsigned long bounce_pfn; + unsigned long seg_boundary_mask; + + unsigned int max_hw_sectors; + unsigned int max_sectors; + unsigned int max_segment_size; + + unsigned short logical_block_size; + unsigned short max_hw_segments; + unsigned short max_phys_segments; + + unsigned char no_cluster; +}; + struct request_queue { /* @@ -358,7 +373,6 @@ struct request_queue /* * queue needs bounce pages for pages above this limit */ - unsigned long bounce_pfn; gfp_t bounce_gfp; /* @@ -387,14 +401,6 @@ struct request_queue unsigned int nr_congestion_off; unsigned int nr_batching; - unsigned int max_sectors; - unsigned int max_hw_sectors; - unsigned short max_phys_segments; - unsigned short max_hw_segments; - unsigned short logical_block_size; - unsigned int max_segment_size; - - unsigned long seg_boundary_mask; void *dma_drain_buffer; unsigned int dma_drain_size; unsigned int dma_pad_mask; @@ -410,6 +416,8 @@ struct request_queue struct timer_list timeout; struct list_head timeout_list; + struct queue_limits limits; + /* * sg stuff */ @@ -991,45 +999,45 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); static inline unsigned long queue_bounce_pfn(struct request_queue *q) { - return q->bounce_pfn; + return q->limits.bounce_pfn; } static inline unsigned long queue_segment_boundary(struct request_queue *q) { - return q->seg_boundary_mask; + return q->limits.seg_boundary_mask; } static inline unsigned int queue_max_sectors(struct request_queue *q) { - return q->max_sectors; + return q->limits.max_sectors; } static inline unsigned int queue_max_hw_sectors(struct request_queue *q) { - return q->max_hw_sectors; + return q->limits.max_hw_sectors; } static inline unsigned short queue_max_hw_segments(struct request_queue *q) { - return q->max_hw_segments; + return q->limits.max_hw_segments; } static inline unsigned short queue_max_phys_segments(struct request_queue *q) { - return q->max_phys_segments; + return q->limits.max_phys_segments; } static inline unsigned int queue_max_segment_size(struct request_queue *q) { - return q->max_segment_size; + return q->limits.max_segment_size; } static inline unsigned short queue_logical_block_size(struct request_queue *q) { int retval = 512; - if (q && q->logical_block_size) - retval = q->logical_block_size; + if (q && q->limits.logical_block_size) + retval = q->limits.logical_block_size; return retval; } -- cgit v1.2.3 From c72758f33784e5e2a1a4bb9421ef3e6de8f9fcf3 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 22 May 2009 17:17:53 -0400 Subject: block: Export I/O topology for block devices and partitions To support devices with physical block sizes bigger than 512 bytes we need to ensure proper alignment. This patch adds support for exposing I/O topology characteristics as devices are stacked. logical_block_size is the smallest unit the device can address. physical_block_size indicates the smallest I/O the device can write without incurring a read-modify-write penalty. The io_min parameter is the smallest preferred I/O size reported by the device. In many cases this is the same as the physical block size. However, the io_min parameter can be scaled up when stacking (RAID5 chunk size > physical block size). The io_opt characteristic indicates the optimal I/O size reported by the device. This is usually the stripe width for arrays. The alignment_offset parameter indicates the number of bytes the start of the device/partition is offset from the device's natural alignment. Partition tools and MD/DM utilities can use this to pad their offsets so filesystems start on proper boundaries. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/genhd.h | 1 + 2 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b7bb6fdba12..5e740a135e7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -314,11 +314,16 @@ struct queue_limits { unsigned int max_hw_sectors; unsigned int max_sectors; unsigned int max_segment_size; + unsigned int physical_block_size; + unsigned int alignment_offset; + unsigned int io_min; + unsigned int io_opt; unsigned short logical_block_size; unsigned short max_hw_segments; unsigned short max_phys_segments; + unsigned char misaligned; unsigned char no_cluster; }; @@ -911,6 +916,15 @@ extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); +extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); +extern void blk_queue_alignment_offset(struct request_queue *q, + unsigned int alignment); +extern void blk_queue_io_min(struct request_queue *q, unsigned int min); +extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); +extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, + sector_t offset); +extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, + sector_t offset); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); extern void blk_queue_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); @@ -1047,6 +1061,39 @@ static inline unsigned short bdev_logical_block_size(struct block_device *bdev) return queue_logical_block_size(bdev_get_queue(bdev)); } +static inline unsigned int queue_physical_block_size(struct request_queue *q) +{ + return q->limits.physical_block_size; +} + +static inline unsigned int queue_io_min(struct request_queue *q) +{ + return q->limits.io_min; +} + +static inline unsigned int queue_io_opt(struct request_queue *q) +{ + return q->limits.io_opt; +} + +static inline int queue_alignment_offset(struct request_queue *q) +{ + if (q && q->limits.misaligned) + return -1; + + if (q && q->limits.alignment_offset) + return q->limits.alignment_offset; + + return 0; +} + +static inline int queue_sector_alignment_offset(struct request_queue *q, + sector_t sector) +{ + return ((sector << 9) - q->limits.alignment_offset) + & (q->limits.io_min - 1); +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a1a28caed23..149fda264c8 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -90,6 +90,7 @@ struct disk_stats { struct hd_struct { sector_t start_sect; sector_t nr_sects; + sector_t alignment_offset; struct device __dev; struct kobject *holder_dir; int policy, partno; -- cgit v1.2.3 From a05c0205ba031c01bba33a21bf0a35920eb64833 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 3 Jun 2009 09:33:18 +0200 Subject: block: Fix bounce limit setting in DM blk_queue_bounce_limit() is more than a wrapper about the request queue limits.bounce_pfn variable. Introduce blk_queue_bounce_pfn() which can be called by stacking drivers that wish to set the bounce limit explicitly. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5e740a135e7..989aa1790f4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -910,6 +910,7 @@ extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); +extern void blk_queue_bounce_pfn(struct request_queue *, u64); extern void blk_queue_max_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); -- cgit v1.2.3 From 9df1bb9b516daeece159ab7fb262d01a0359247c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 9 Jun 2009 06:22:57 +0200 Subject: Revert "block: Fix bounce limit setting in DM" This reverts commit a05c0205ba031c01bba33a21bf0a35920eb64833. DM doesn't need to access the bounce_pfn directly. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 989aa1790f4..5e740a135e7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -910,7 +910,6 @@ extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -extern void blk_queue_bounce_pfn(struct request_queue *, u64); extern void blk_queue_max_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); -- cgit v1.2.3 From 1d589bb16b825b3a7b4edd34d997f1f1f953033d Mon Sep 17 00:00:00 2001 From: john cooper Date: Tue, 9 Jun 2009 14:41:40 +0200 Subject: Add serial number support for virtio_blk, V4a This patch extracts the opaque data from pci i/o region 0 via the added VIRTIO_BLK_F_IDENTIFY field. By convention this data takes the form of that returned by an ATA IDENTIFY DEVICE command, however the driver (except for structure size) makes no interpretation of the data. The structure data is copied wholesale to userspace via a HDIO_GET_IDENTITY ioctl command (eg: hdparm -i ). Signed-off-by: john cooper Signed-off-by: Rusty Russell Signed-off-by: Jens Axboe --- include/linux/virtio_blk.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h index 4dbcbc1c348..be7d255fc7c 100644 --- a/include/linux/virtio_blk.h +++ b/include/linux/virtio_blk.h @@ -16,6 +16,9 @@ #define VIRTIO_BLK_F_RO 5 /* Disk is read-only */ #define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/ #define VIRTIO_BLK_F_SCSI 7 /* Supports scsi command passthru */ +#define VIRTIO_BLK_F_IDENTIFY 8 /* ATA IDENTIFY supported */ + +#define VIRTIO_BLK_ID_BYTES (sizeof(__u16[256])) /* IDENTIFY DATA */ struct virtio_blk_config { @@ -33,6 +36,7 @@ struct virtio_blk_config } geometry; /* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */ __u32 blk_size; + __u8 identify[VIRTIO_BLK_ID_BYTES]; } __attribute__((packed)); /* These two define direction. */ -- cgit v1.2.3 From d9c7d394a8ebacb60097b192939ae9f15235225e Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Wed, 10 Jun 2009 12:57:06 -0700 Subject: block: prevent possible io_context->refcount overflow Currently io_context has an atomic_t(32-bit) as refcount. In the case of cfq, for each device against whcih a task does I/O, a reference to the io_context would be taken. And when there are multiple process sharing io_contexts(CLONE_IO) would also have a reference to the same io_context. Theoretically the possible maximum number of processes sharing the same io_context + the number of disks/cfq_data referring to the same io_context can overflow the 32-bit counter on a very high-end machine. Even though it is an improbable case, let us make it atomic_long_t. Signed-off-by: Nikanth Karthikesan Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/iocontext.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 08b987bccf8..dd05434fa45 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -64,7 +64,7 @@ struct cfq_io_context { * and kmalloc'ed. These could be shared between processes. */ struct io_context { - atomic_t refcount; + atomic_long_t refcount; atomic_t nr_tasks; /* all the fields below are protected by this lock */ @@ -91,8 +91,8 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc) * if ref count is zero, don't allow sharing (ioc is going away, it's * a race). */ - if (ioc && atomic_inc_not_zero(&ioc->refcount)) { - atomic_inc(&ioc->nr_tasks); + if (ioc && atomic_long_inc_not_zero(&ioc->refcount)) { + atomic_long_inc(&ioc->refcount); return ioc; } -- cgit v1.2.3 From b0fd271d5fba0b2d00888363f3869e3f9b26caa9 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Thu, 11 Jun 2009 13:10:16 +0200 Subject: block: add request clone interface (v2) This patch adds the following 2 interfaces for request-stacking drivers: - blk_rq_prep_clone(struct request *clone, struct request *orig, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio*, void *), void *data) * Clones bios in the original request to the clone request (bio_ctr is called for each cloned bios.) * Copies attributes of the original request to the clone request. The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied. - blk_rq_unprep_clone(struct request *clone) * Frees cloned bios from the clone request. Request stacking drivers (e.g. request-based dm) need to make a clone request for a submitted request and dispatch it to other devices. To allocate request for the clone, request stacking drivers may not be able to use blk_get_request() because the allocation may be done in an irq-disabled context. So blk_rq_prep_clone() takes a request allocated by the caller as an argument. For each clone bio in the clone request, request stacking drivers should be able to set up their own completion handler. So blk_rq_prep_clone() takes a callback function which is called for each clone bio, and a pointer for private data which is passed to the callback. NOTE: blk_rq_prep_clone() doesn't copy any actual data of the original request. Pages are shared between original bios and cloned bios. So caller must not complete the original request before the clone request. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Cc: Boaz Harrosh Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5e740a135e7..ebdfde8fe55 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -765,6 +765,11 @@ extern void blk_insert_request(struct request_queue *, struct request *, int, vo extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_rq_check_limits(struct request_queue *q, struct request *rq); extern int blk_lld_busy(struct request_queue *q); +extern 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); +extern void blk_rq_unprep_clone(struct request *rq); extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern void blk_plug_device(struct request_queue *); -- cgit v1.2.3