From 7b6d91daee5cac6402186ff224c3af39d79f4a0e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Aug 2010 18:20:39 +0200 Subject: block: unify flags for struct bio and struct request Remove the current bio flags and reuse the request flags for the bio, too. This allows to more easily trace the type of I/O from the filesystem down to the block driver. There were two flags in the bio that were missing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I've renamed two request flags that had a superflous RW in them. Note that the flags are in bio.h despite having the REQ_ name - as blkdev.h includes bio.h that is the only way to go for now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 125 ++++++++++++++++++++++++++++++++-------------------- 1 file changed, 78 insertions(+), 47 deletions(-) (limited to 'include/linux/bio.h') diff --git a/include/linux/bio.h b/include/linux/bio.h index 7fc5606e6ea5..4d379c8250ae 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -138,55 +138,83 @@ struct bio { #define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) /* - * bio bi_rw flags - * - * bit 0 -- data direction - * If not set, bio is a read from device. If set, it's a write to device. - * bit 1 -- fail fast device errors - * bit 2 -- fail fast transport errors - * bit 3 -- fail fast driver errors - * bit 4 -- rw-ahead when set - * bit 5 -- barrier - * Insert a serialization point in the IO queue, forcing previously - * submitted IO to be completed before this one is issued. - * bit 6 -- synchronous I/O hint. - * bit 7 -- Unplug the device immediately after submitting this bio. - * bit 8 -- metadata request - * Used for tracing to differentiate metadata and data IO. May also - * get some preferential treatment in the IO scheduler - * bit 9 -- discard sectors - * Informs the lower level device that this range of sectors is no longer - * used by the file system and may thus be freed by the device. Used - * for flash based storage. - * Don't want driver retries for any fast fail whatever the reason. - * bit 10 -- Tell the IO scheduler not to wait for more requests after this - one has been submitted, even if it is a SYNC request. + * Request flags. For use in the cmd_flags field of struct request, and in + * bi_rw of struct bio. Note that some flags are only valid in either one. */ -enum bio_rw_flags { - BIO_RW, - BIO_RW_FAILFAST_DEV, - BIO_RW_FAILFAST_TRANSPORT, - BIO_RW_FAILFAST_DRIVER, - /* above flags must match REQ_* */ - BIO_RW_AHEAD, - BIO_RW_BARRIER, - BIO_RW_SYNCIO, - BIO_RW_UNPLUG, - BIO_RW_META, - BIO_RW_DISCARD, - BIO_RW_NOIDLE, +enum rq_flag_bits { + /* common flags */ + __REQ_WRITE, /* not set, read. set, write */ + __REQ_FAILFAST_DEV, /* no driver retries of device errors */ + __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ + __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ + + __REQ_HARDBARRIER, /* may not be passed by drive either */ + __REQ_SYNC, /* request is sync (sync write or read) */ + __REQ_META, /* metadata io request */ + __REQ_DISCARD, /* request to discard sectors */ + __REQ_NOIDLE, /* don't anticipate more IO after this one */ + + /* bio only flags */ + __REQ_UNPLUG, /* unplug the immediately after submission */ + __REQ_RAHEAD, /* read ahead, can fail anytime */ + + /* request only flags */ + __REQ_SORTED, /* elevator knows about this request */ + __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ + __REQ_FUA, /* forced unit access */ + __REQ_NOMERGE, /* don't touch this for merging */ + __REQ_STARTED, /* drive already may have started this one */ + __REQ_DONTPREP, /* don't call prep for this one */ + __REQ_QUEUED, /* uses queueing */ + __REQ_ELVPRIV, /* elevator private data attached */ + __REQ_FAILED, /* set if the request failed */ + __REQ_QUIET, /* don't worry about errors */ + __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_ORDERED_COLOR, /* is before or after barrier */ + __REQ_ALLOCED, /* request came from our alloc pool */ + __REQ_COPY_USER, /* contains copies of user pages */ + __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_IO_STAT, /* account I/O stat */ + __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_NR_BITS, /* stops here */ }; -/* - * First four bits must match between bio->bi_rw and rq->cmd_flags, make - * that explicit here. - */ -#define BIO_RW_RQ_MASK 0xf - -static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) -{ - return (bio->bi_rw & (1 << flag)) != 0; -} +#define REQ_WRITE (1 << __REQ_WRITE) +#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) +#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) +#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) +#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) +#define REQ_SYNC (1 << __REQ_SYNC) +#define REQ_META (1 << __REQ_META) +#define REQ_DISCARD (1 << __REQ_DISCARD) +#define REQ_NOIDLE (1 << __REQ_NOIDLE) + +#define REQ_FAILFAST_MASK \ + (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) +#define REQ_COMMON_MASK \ + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ + REQ_META| REQ_DISCARD | REQ_NOIDLE) + +#define REQ_UNPLUG (1 << __REQ_UNPLUG) +#define REQ_RAHEAD (1 << __REQ_RAHEAD) + +#define REQ_SORTED (1 << __REQ_SORTED) +#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) +#define REQ_FUA (1 << __REQ_FUA) +#define REQ_NOMERGE (1 << __REQ_NOMERGE) +#define REQ_STARTED (1 << __REQ_STARTED) +#define REQ_DONTPREP (1 << __REQ_DONTPREP) +#define REQ_QUEUED (1 << __REQ_QUEUED) +#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) +#define REQ_FAILED (1 << __REQ_FAILED) +#define REQ_QUIET (1 << __REQ_QUIET) +#define REQ_PREEMPT (1 << __REQ_PREEMPT) +#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) +#define REQ_ALLOCED (1 << __REQ_ALLOCED) +#define REQ_COPY_USER (1 << __REQ_COPY_USER) +#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_IO_STAT (1 << __REQ_IO_STAT) +#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) /* * upper 16 bits of bi_rw define the io priority of this bio @@ -211,7 +239,10 @@ static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_empty_barrier(bio) (bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD)) +#define bio_empty_barrier(bio) \ + ((bio->bi_rw & REQ_HARDBARRIER) && \ + !bio_has_data(bio) && \ + !(bio->bi_rw & REQ_DISCARD)) static inline unsigned int bio_cur_bytes(struct bio *bio) { -- cgit v1.2.3 From 8749534fe6826596b71bc409c872b047a8e2755b Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sat, 3 Jul 2010 17:45:32 +0900 Subject: block: introduce REQ_FLUSH flag SCSI-ml needs a way to mark a request as flush request in q->prepare_flush_fn because it needs to identify them later (e.g. in q->request_fn or prep_rq_fn). queue_flush sets REQ_HARDBARRIER in rq->cmd_flags however the block layer also sends normal REQ_TYPE_FS requests with REQ_HARDBARRIER. So SCSI-ml can't use REQ_HARDBARRIER to identify flush requests. We could change the block layer to clear REQ_HARDBARRIER bit before sending non flush requests to the lower layers. However, intorudcing the new flag looks cleaner (surely easier). Signed-off-by: FUJITA Tomonori Cc: James Bottomley Cc: David S. Miller Cc: Rusty Russell Cc: Alasdair G Kergon Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 2 +- include/linux/bio.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/bio.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 7c6f4a714687..a3482425c507 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -143,7 +143,7 @@ static void queue_flush(struct request_queue *q, unsigned which) } blk_rq_init(q, rq); - rq->cmd_flags = REQ_HARDBARRIER; + rq->cmd_flags = REQ_HARDBARRIER | REQ_FLUSH; rq->rq_disk = q->bar_rq.rq_disk; rq->end_io = end_io; q->prepare_flush_fn(q, rq); diff --git a/include/linux/bio.h b/include/linux/bio.h index 4d379c8250ae..f655b54c9ef3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -174,6 +174,7 @@ enum rq_flag_bits { __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_FLUSH, /* request for cache flush */ __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ __REQ_NR_BITS, /* stops here */ @@ -213,6 +214,7 @@ enum rq_flag_bits { #define REQ_ALLOCED (1 << __REQ_ALLOCED) #define REQ_COPY_USER (1 << __REQ_COPY_USER) #define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_FLUSH (1 << __REQ_FLUSH) #define REQ_IO_STAT (1 << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) -- cgit v1.2.3 From 7cc015811ef8992dfcce314d0ed9642bc18143d1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Aug 2010 13:14:58 +0200 Subject: bio, fs: separate out bio_types.h and define READ/WRITE constants in terms of BIO_RW_* flags linux/fs.h hard coded READ/WRITE constants which should match BIO_RW_* flags. This is fragile and caused breakage during BIO_RW_* flag rearrangement. The hardcoding is to avoid include dependency hell. Create linux/bio_types.h which contatins definitions for bio data structures and flags and include it from bio.h and fs.h, and make fs.h define all READ/WRITE related constants in terms of BIO_RW_* flags. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 183 +------------------------------------------ include/linux/blk_types.h | 193 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 15 ++-- 3 files changed, 204 insertions(+), 187 deletions(-) create mode 100644 include/linux/blk_types.h (limited to 'include/linux/bio.h') diff --git a/include/linux/bio.h b/include/linux/bio.h index f655b54c9ef3..5274103434ad 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -9,7 +9,7 @@ * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of - + * * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * @@ -28,6 +28,9 @@ #include +/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ +#include + #define BIO_DEBUG #ifdef BIO_DEBUG @@ -40,184 +43,6 @@ #define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_CACHE_SHIFT) #define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9) -/* - * was unsigned short, but we might as well be ready for > 64kB I/O pages - */ -struct bio_vec { - struct page *bv_page; - unsigned int bv_len; - unsigned int bv_offset; -}; - -struct bio_set; -struct bio; -struct bio_integrity_payload; -typedef void (bio_end_io_t) (struct bio *, int); -typedef void (bio_destructor_t) (struct bio *); - -/* - * main unit of I/O for the block layer and lower layers (ie drivers and - * stacking drivers) - */ -struct bio { - sector_t bi_sector; /* device address in 512 byte - sectors */ - struct bio *bi_next; /* request queue link */ - struct block_device *bi_bdev; - unsigned long bi_flags; /* status, command, etc */ - unsigned long bi_rw; /* bottom bits READ/WRITE, - * top bits priority - */ - - unsigned short bi_vcnt; /* how many bio_vec's */ - unsigned short bi_idx; /* current index into bvl_vec */ - - /* Number of segments in this BIO after - * physical address coalescing is performed. - */ - unsigned int bi_phys_segments; - - unsigned int bi_size; /* residual I/O count */ - - /* - * To keep track of the max segment size, we account for the - * sizes of the first and last mergeable segments in this bio. - */ - unsigned int bi_seg_front_size; - unsigned int bi_seg_back_size; - - unsigned int bi_max_vecs; /* max bvl_vecs we can hold */ - - unsigned int bi_comp_cpu; /* completion CPU */ - - atomic_t bi_cnt; /* pin count */ - - struct bio_vec *bi_io_vec; /* the actual vec list */ - - bio_end_io_t *bi_end_io; - - void *bi_private; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - struct bio_integrity_payload *bi_integrity; /* data integrity */ -#endif - - bio_destructor_t *bi_destructor; /* destructor */ - - /* - * We can inline a number of vecs at the end of the bio, to avoid - * double allocations for a small number of bio_vecs. This member - * MUST obviously be kept at the very end of the bio. - */ - struct bio_vec bi_inline_vecs[0]; -}; - -/* - * bio flags - */ -#define BIO_UPTODATE 0 /* ok after I/O completion */ -#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */ -#define BIO_EOF 2 /* out-out-bounds error */ -#define BIO_SEG_VALID 3 /* bi_phys_segments valid */ -#define BIO_CLONED 4 /* doesn't own data */ -#define BIO_BOUNCED 5 /* bio is a bounce bio */ -#define BIO_USER_MAPPED 6 /* contains user pages */ -#define BIO_EOPNOTSUPP 7 /* not supported */ -#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */ -#define BIO_NULL_MAPPED 9 /* contains invalid user pages */ -#define BIO_FS_INTEGRITY 10 /* fs owns integrity data, not block layer */ -#define BIO_QUIET 11 /* Make BIO Quiet */ -#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) - -/* - * top 4 bits of bio flags indicate the pool this bio came from - */ -#define BIO_POOL_BITS (4) -#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1) -#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS) -#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) -#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) - -/* - * Request flags. For use in the cmd_flags field of struct request, and in - * bi_rw of struct bio. Note that some flags are only valid in either one. - */ -enum rq_flag_bits { - /* common flags */ - __REQ_WRITE, /* not set, read. set, write */ - __REQ_FAILFAST_DEV, /* no driver retries of device errors */ - __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ - __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - - __REQ_HARDBARRIER, /* may not be passed by drive either */ - __REQ_SYNC, /* request is sync (sync write or read) */ - __REQ_META, /* metadata io request */ - __REQ_DISCARD, /* request to discard sectors */ - __REQ_NOIDLE, /* don't anticipate more IO after this one */ - - /* bio only flags */ - __REQ_UNPLUG, /* unplug the immediately after submission */ - __REQ_RAHEAD, /* read ahead, can fail anytime */ - - /* request only flags */ - __REQ_SORTED, /* elevator knows about this request */ - __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_FUA, /* forced unit access */ - __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_STARTED, /* drive already may have started this one */ - __REQ_DONTPREP, /* don't call prep for this one */ - __REQ_QUEUED, /* uses queueing */ - __REQ_ELVPRIV, /* elevator private data attached */ - __REQ_FAILED, /* set if the request failed */ - __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ - __REQ_ORDERED_COLOR, /* is before or after barrier */ - __REQ_ALLOCED, /* request came from our alloc pool */ - __REQ_COPY_USER, /* contains copies of user pages */ - __REQ_INTEGRITY, /* integrity metadata has been remapped */ - __REQ_FLUSH, /* request for cache flush */ - __REQ_IO_STAT, /* account I/O stat */ - __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_NR_BITS, /* stops here */ -}; - -#define REQ_WRITE (1 << __REQ_WRITE) -#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) -#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) -#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) -#define REQ_SYNC (1 << __REQ_SYNC) -#define REQ_META (1 << __REQ_META) -#define REQ_DISCARD (1 << __REQ_DISCARD) -#define REQ_NOIDLE (1 << __REQ_NOIDLE) - -#define REQ_FAILFAST_MASK \ - (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) -#define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ - REQ_META| REQ_DISCARD | REQ_NOIDLE) - -#define REQ_UNPLUG (1 << __REQ_UNPLUG) -#define REQ_RAHEAD (1 << __REQ_RAHEAD) - -#define REQ_SORTED (1 << __REQ_SORTED) -#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) -#define REQ_FUA (1 << __REQ_FUA) -#define REQ_NOMERGE (1 << __REQ_NOMERGE) -#define REQ_STARTED (1 << __REQ_STARTED) -#define REQ_DONTPREP (1 << __REQ_DONTPREP) -#define REQ_QUEUED (1 << __REQ_QUEUED) -#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) -#define REQ_FAILED (1 << __REQ_FAILED) -#define REQ_QUIET (1 << __REQ_QUIET) -#define REQ_PREEMPT (1 << __REQ_PREEMPT) -#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) -#define REQ_ALLOCED (1 << __REQ_ALLOCED) -#define REQ_COPY_USER (1 << __REQ_COPY_USER) -#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) -#define REQ_FLUSH (1 << __REQ_FLUSH) -#define REQ_IO_STAT (1 << __REQ_IO_STAT) -#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) - /* * upper 16 bits of bi_rw define the io priority of this bio */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h new file mode 100644 index 000000000000..118523734af0 --- /dev/null +++ b/include/linux/blk_types.h @@ -0,0 +1,193 @@ +/* + * Block data types and constants. Directly include this file only to + * break include dependency loop. + */ +#ifndef __LINUX_BLK_TYPES_H +#define __LINUX_BLK_TYPES_H + +#ifdef CONFIG_BLOCK + +#include + +struct bio_set; +struct bio; +struct bio_integrity_payload; +struct page; +struct block_device; +typedef void (bio_end_io_t) (struct bio *, int); +typedef void (bio_destructor_t) (struct bio *); + +/* + * was unsigned short, but we might as well be ready for > 64kB I/O pages + */ +struct bio_vec { + struct page *bv_page; + unsigned int bv_len; + unsigned int bv_offset; +}; + +/* + * main unit of I/O for the block layer and lower layers (ie drivers and + * stacking drivers) + */ +struct bio { + sector_t bi_sector; /* device address in 512 byte + sectors */ + struct bio *bi_next; /* request queue link */ + struct block_device *bi_bdev; + unsigned long bi_flags; /* status, command, etc */ + unsigned long bi_rw; /* bottom bits READ/WRITE, + * top bits priority + */ + + unsigned short bi_vcnt; /* how many bio_vec's */ + unsigned short bi_idx; /* current index into bvl_vec */ + + /* Number of segments in this BIO after + * physical address coalescing is performed. + */ + unsigned int bi_phys_segments; + + unsigned int bi_size; /* residual I/O count */ + + /* + * To keep track of the max segment size, we account for the + * sizes of the first and last mergeable segments in this bio. + */ + unsigned int bi_seg_front_size; + unsigned int bi_seg_back_size; + + unsigned int bi_max_vecs; /* max bvl_vecs we can hold */ + + unsigned int bi_comp_cpu; /* completion CPU */ + + atomic_t bi_cnt; /* pin count */ + + struct bio_vec *bi_io_vec; /* the actual vec list */ + + bio_end_io_t *bi_end_io; + + void *bi_private; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + struct bio_integrity_payload *bi_integrity; /* data integrity */ +#endif + + bio_destructor_t *bi_destructor; /* destructor */ + + /* + * We can inline a number of vecs at the end of the bio, to avoid + * double allocations for a small number of bio_vecs. This member + * MUST obviously be kept at the very end of the bio. + */ + struct bio_vec bi_inline_vecs[0]; +}; + +/* + * bio flags + */ +#define BIO_UPTODATE 0 /* ok after I/O completion */ +#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */ +#define BIO_EOF 2 /* out-out-bounds error */ +#define BIO_SEG_VALID 3 /* bi_phys_segments valid */ +#define BIO_CLONED 4 /* doesn't own data */ +#define BIO_BOUNCED 5 /* bio is a bounce bio */ +#define BIO_USER_MAPPED 6 /* contains user pages */ +#define BIO_EOPNOTSUPP 7 /* not supported */ +#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */ +#define BIO_NULL_MAPPED 9 /* contains invalid user pages */ +#define BIO_FS_INTEGRITY 10 /* fs owns integrity data, not block layer */ +#define BIO_QUIET 11 /* Make BIO Quiet */ +#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) + +/* + * top 4 bits of bio flags indicate the pool this bio came from + */ +#define BIO_POOL_BITS (4) +#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1) +#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS) +#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) +#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) + +/* + * Request flags. For use in the cmd_flags field of struct request, and in + * bi_rw of struct bio. Note that some flags are only valid in either one. + */ +enum rq_flag_bits { + /* common flags */ + __REQ_WRITE, /* not set, read. set, write */ + __REQ_FAILFAST_DEV, /* no driver retries of device errors */ + __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ + __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ + + __REQ_HARDBARRIER, /* may not be passed by drive either */ + __REQ_SYNC, /* request is sync (sync write or read) */ + __REQ_META, /* metadata io request */ + __REQ_DISCARD, /* request to discard sectors */ + __REQ_NOIDLE, /* don't anticipate more IO after this one */ + + /* bio only flags */ + __REQ_UNPLUG, /* unplug the immediately after submission */ + __REQ_RAHEAD, /* read ahead, can fail anytime */ + + /* request only flags */ + __REQ_SORTED, /* elevator knows about this request */ + __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ + __REQ_FUA, /* forced unit access */ + __REQ_NOMERGE, /* don't touch this for merging */ + __REQ_STARTED, /* drive already may have started this one */ + __REQ_DONTPREP, /* don't call prep for this one */ + __REQ_QUEUED, /* uses queueing */ + __REQ_ELVPRIV, /* elevator private data attached */ + __REQ_FAILED, /* set if the request failed */ + __REQ_QUIET, /* don't worry about errors */ + __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_ORDERED_COLOR, /* is before or after barrier */ + __REQ_ALLOCED, /* request came from our alloc pool */ + __REQ_COPY_USER, /* contains copies of user pages */ + __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_FLUSH, /* request for cache flush */ + __REQ_IO_STAT, /* account I/O stat */ + __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_NR_BITS, /* stops here */ +}; + +#define REQ_WRITE (1 << __REQ_WRITE) +#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) +#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) +#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) +#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) +#define REQ_SYNC (1 << __REQ_SYNC) +#define REQ_META (1 << __REQ_META) +#define REQ_DISCARD (1 << __REQ_DISCARD) +#define REQ_NOIDLE (1 << __REQ_NOIDLE) + +#define REQ_FAILFAST_MASK \ + (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) +#define REQ_COMMON_MASK \ + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ + REQ_META| REQ_DISCARD | REQ_NOIDLE) + +#define REQ_UNPLUG (1 << __REQ_UNPLUG) +#define REQ_RAHEAD (1 << __REQ_RAHEAD) + +#define REQ_SORTED (1 << __REQ_SORTED) +#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) +#define REQ_FUA (1 << __REQ_FUA) +#define REQ_NOMERGE (1 << __REQ_NOMERGE) +#define REQ_STARTED (1 << __REQ_STARTED) +#define REQ_DONTPREP (1 << __REQ_DONTPREP) +#define REQ_QUEUED (1 << __REQ_QUEUED) +#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) +#define REQ_FAILED (1 << __REQ_FAILED) +#define REQ_QUIET (1 << __REQ_QUIET) +#define REQ_PREEMPT (1 << __REQ_PREEMPT) +#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) +#define REQ_ALLOCED (1 << __REQ_ALLOCED) +#define REQ_COPY_USER (1 << __REQ_COPY_USER) +#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_FLUSH (1 << __REQ_FLUSH) +#define REQ_IO_STAT (1 << __REQ_IO_STAT) +#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) + +#endif /* CONFIG_BLOCK */ +#endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 55dad7bca25b..c53911277210 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -8,6 +8,7 @@ #include #include +#include /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -117,7 +118,7 @@ struct inodes_stat_t { * immediately wait on this read without caring about * unplugging. * READA Used for read-ahead operations. Lower priority, and the - * block layer could (in theory) choose to ignore this + * block layer could (in theory) choose to ignore this * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. * SWRITE Like WRITE, but a special case for ll_rw_block() that @@ -144,13 +145,13 @@ struct inodes_stat_t { * of this IO. * */ -#define RW_MASK 1 -#define RWA_MASK 16 +#define RW_MASK REQ_WRITE +#define RWA_MASK REQ_RAHEAD #define READ 0 -#define WRITE 1 -#define READA 16 /* readahead - don't block if no resources */ -#define SWRITE 17 /* for ll_rw_block(), wait for buffer lock */ +#define WRITE RW_MASK +#define READA RWA_MASK +#define SWRITE (WRITE | READA) #define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) #define READ_META (READ | REQ_META) @@ -2200,7 +2201,6 @@ static inline void insert_inode_hash(struct inode *inode) { extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); #ifdef CONFIG_BLOCK -struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); #endif @@ -2267,7 +2267,6 @@ static inline int xip_truncate_page(struct address_space *mapping, loff_t from) #endif #ifdef CONFIG_BLOCK -struct bio; typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); void dio_end_io(struct bio *bio, int error); -- cgit v1.2.3 From 13f05c8d8e98bbdce89158bfdb2e380940695a88 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 10 Sep 2010 20:50:10 +0200 Subject: block/scsi: Provide a limit on the number of integrity segments Some controllers have a hardware limit on the number of protection information scatter-gather list segments they can handle. Introduce a max_integrity_segments limit in the block layer and provide a new scsi_host_template setting that allows HBA drivers to provide a value suitable for the hardware. Add support for honoring the integrity segment limit when merging both bios and requests. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-integrity.c | 93 ++++++++++++++++++++++++++++++++++++----------- block/blk-merge.c | 23 +++++++----- block/blk-settings.c | 3 ++ block/blk-sysfs.c | 11 ++++++ block/blk.h | 8 ---- drivers/scsi/hosts.c | 1 + drivers/scsi/scsi_lib.c | 26 +++++++++---- drivers/scsi/scsi_sysfs.c | 2 + include/linux/bio.h | 4 ++ include/linux/blkdev.h | 33 +++++++++++++++-- include/scsi/scsi.h | 6 +++ include/scsi/scsi_host.h | 7 ++++ 12 files changed, 167 insertions(+), 50 deletions(-) (limited to 'include/linux/bio.h') diff --git a/block/blk-integrity.c b/block/blk-integrity.c index edce1ef7933d..885cbb59967e 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -32,24 +32,37 @@ static struct kmem_cache *integrity_cachep; /** * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements - * @rq: request with integrity metadata attached + * @q: request queue + * @bio: bio with integrity metadata attached * * Description: Returns the number of elements required in a - * scatterlist corresponding to the integrity metadata in a request. + * scatterlist corresponding to the integrity metadata in a bio. */ -int blk_rq_count_integrity_sg(struct request *rq) +int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio) { - struct bio_vec *iv, *ivprv; - struct req_iterator iter; - unsigned int segments; + struct bio_vec *iv, *ivprv = NULL; + unsigned int segments = 0; + unsigned int seg_size = 0; + unsigned int i = 0; - ivprv = NULL; - segments = 0; + bio_for_each_integrity_vec(iv, bio, i) { - rq_for_each_integrity_segment(iv, rq, iter) { + if (ivprv) { + if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv)) + goto new_segment; + + if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv)) + goto new_segment; + + if (seg_size + iv->bv_len > queue_max_segment_size(q)) + goto new_segment; - if (!ivprv || !BIOVEC_PHYS_MERGEABLE(ivprv, iv)) + seg_size += iv->bv_len; + } else { +new_segment: segments++; + seg_size = iv->bv_len; + } ivprv = iv; } @@ -60,30 +73,34 @@ EXPORT_SYMBOL(blk_rq_count_integrity_sg); /** * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist - * @rq: request with integrity metadata attached + * @q: request queue + * @bio: bio with integrity metadata attached * @sglist: target scatterlist * * Description: Map the integrity vectors in request into a * scatterlist. The scatterlist must be big enough to hold all * elements. I.e. sized using blk_rq_count_integrity_sg(). */ -int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist) +int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist) { - struct bio_vec *iv, *ivprv; - struct req_iterator iter; - struct scatterlist *sg; - unsigned int segments; + struct bio_vec *iv, *ivprv = NULL; + struct scatterlist *sg = NULL; + unsigned int segments = 0; + unsigned int i = 0; - ivprv = NULL; - sg = NULL; - segments = 0; - - rq_for_each_integrity_segment(iv, rq, iter) { + bio_for_each_integrity_vec(iv, bio, i) { if (ivprv) { if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv)) goto new_segment; + if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv)) + goto new_segment; + + if (sg->length + iv->bv_len > queue_max_segment_size(q)) + goto new_segment; + sg->length += iv->bv_len; } else { new_segment: @@ -162,6 +179,40 @@ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2) } EXPORT_SYMBOL(blk_integrity_compare); +int blk_integrity_merge_rq(struct request_queue *q, struct request *req, + struct request *next) +{ + if (blk_integrity_rq(req) != blk_integrity_rq(next)) + return -1; + + if (req->nr_integrity_segments + next->nr_integrity_segments > + q->limits.max_integrity_segments) + return -1; + + return 0; +} +EXPORT_SYMBOL(blk_integrity_merge_rq); + +int blk_integrity_merge_bio(struct request_queue *q, struct request *req, + struct bio *bio) +{ + int nr_integrity_segs; + struct bio *next = bio->bi_next; + + bio->bi_next = NULL; + nr_integrity_segs = blk_rq_count_integrity_sg(q, bio); + bio->bi_next = next; + + if (req->nr_integrity_segments + nr_integrity_segs > + q->limits.max_integrity_segments) + return -1; + + req->nr_integrity_segments += nr_integrity_segs; + + return 0; +} +EXPORT_SYMBOL(blk_integrity_merge_bio); + struct integrity_sysfs_entry { struct attribute attr; ssize_t (*show)(struct blk_integrity *, char *); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3b0cd4249671..6a725461654d 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -205,12 +205,11 @@ static inline int ll_new_hw_segment(struct request_queue *q, { int nr_phys_segs = bio_phys_segments(q, bio); - if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) { - req->cmd_flags |= REQ_NOMERGE; - if (req == q->last_merge) - q->last_merge = NULL; - return 0; - } + if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) + goto no_merge; + + if (bio_integrity(bio) && blk_integrity_merge_bio(q, req, bio)) + goto no_merge; /* * This will form the start of a new hw segment. Bump both @@ -218,6 +217,12 @@ static inline int ll_new_hw_segment(struct request_queue *q, */ req->nr_phys_segments += nr_phys_segs; return 1; + +no_merge: + req->cmd_flags |= REQ_NOMERGE; + if (req == q->last_merge) + q->last_merge = NULL; + return 0; } int ll_back_merge_fn(struct request_queue *q, struct request *req, @@ -301,6 +306,9 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, if (total_phys_segments > queue_max_segments(q)) return 0; + if (blk_integrity_rq(req) && blk_integrity_merge_rq(q, req, next)) + return 0; + /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; @@ -372,9 +380,6 @@ static int attempt_merge(struct request_queue *q, struct request *req, || next->special) return 0; - if (blk_integrity_rq(req) != blk_integrity_rq(next)) - return 0; - /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn diff --git a/block/blk-settings.c b/block/blk-settings.c index 8d592b559bd3..f8f2ddf20613 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -111,6 +111,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy); void blk_set_default_limits(struct queue_limits *lim) { lim->max_segments = BLK_MAX_SEGMENTS; + lim->max_integrity_segments = 0; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; @@ -509,6 +510,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, b->seg_boundary_mask); t->max_segments = min_not_zero(t->max_segments, b->max_segments); + t->max_integrity_segments = min_not_zero(t->max_integrity_segments, + b->max_integrity_segments); t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 001ab18078f5..b014f7739e98 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -112,6 +112,11 @@ static ssize_t queue_max_segments_show(struct request_queue *q, char *page) return queue_var_show(queue_max_segments(q), (page)); } +static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) +{ + return queue_var_show(q->limits.max_integrity_segments, (page)); +} + static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags)) @@ -288,6 +293,11 @@ static struct queue_sysfs_entry queue_max_segments_entry = { .show = queue_max_segments_show, }; +static struct queue_sysfs_entry queue_max_integrity_segments_entry = { + .attr = {.name = "max_integrity_segments", .mode = S_IRUGO }, + .show = queue_max_integrity_segments_show, +}; + static struct queue_sysfs_entry queue_max_segment_size_entry = { .attr = {.name = "max_segment_size", .mode = S_IRUGO }, .show = queue_max_segment_size_show, @@ -375,6 +385,7 @@ static struct attribute *default_attrs[] = { &queue_max_hw_sectors_entry.attr, &queue_max_sectors_entry.attr, &queue_max_segments_entry.attr, + &queue_max_integrity_segments_entry.attr, &queue_max_segment_size_entry.attr, &queue_iosched_entry.attr, &queue_hw_sector_size_entry.attr, diff --git a/block/blk.h b/block/blk.h index 6e7dc87141e4..6738831ba447 100644 --- a/block/blk.h +++ b/block/blk.h @@ -132,14 +132,6 @@ static inline int queue_congestion_off_threshold(struct request_queue *q) return q->nr_congestion_off; } -#if defined(CONFIG_BLK_DEV_INTEGRITY) - -#define rq_for_each_integrity_segment(bvl, _rq, _iter) \ - __rq_for_each_bio(_iter.bio, _rq) \ - bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i) - -#endif /* BLK_DEV_INTEGRITY */ - static inline int blk_cpu_to_group(int cpu) { #ifdef CONFIG_SCHED_MC diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 8a8f803439e1..10478153641b 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -376,6 +376,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost->this_id = sht->this_id; shost->can_queue = sht->can_queue; shost->sg_tablesize = sht->sg_tablesize; + shost->sg_prot_tablesize = sht->sg_prot_tablesize; shost->cmd_per_lun = sht->cmd_per_lun; shost->unchecked_isa_dma = sht->unchecked_isa_dma; shost->use_clustering = sht->use_clustering; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9ade720422c6..861c0b937ac9 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -968,11 +968,13 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb, */ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) { - int error = scsi_init_sgtable(cmd->request, &cmd->sdb, gfp_mask); + struct request *rq = cmd->request; + + int error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask); if (error) goto err_exit; - if (blk_bidi_rq(cmd->request)) { + if (blk_bidi_rq(rq)) { struct scsi_data_buffer *bidi_sdb = kmem_cache_zalloc( scsi_sdb_cache, GFP_ATOMIC); if (!bidi_sdb) { @@ -980,28 +982,28 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) goto err_exit; } - cmd->request->next_rq->special = bidi_sdb; - error = scsi_init_sgtable(cmd->request->next_rq, bidi_sdb, - GFP_ATOMIC); + rq->next_rq->special = bidi_sdb; + error = scsi_init_sgtable(rq->next_rq, bidi_sdb, GFP_ATOMIC); if (error) goto err_exit; } - if (blk_integrity_rq(cmd->request)) { + if (blk_integrity_rq(rq)) { struct scsi_data_buffer *prot_sdb = cmd->prot_sdb; int ivecs, count; BUG_ON(prot_sdb == NULL); - ivecs = blk_rq_count_integrity_sg(cmd->request); + ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio); if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask)) { error = BLKPREP_DEFER; goto err_exit; } - count = blk_rq_map_integrity_sg(cmd->request, + count = blk_rq_map_integrity_sg(rq->q, rq->bio, prot_sdb->table.sgl); BUG_ON(unlikely(count > ivecs)); + BUG_ON(unlikely(count > queue_max_integrity_segments(rq->q))); cmd->prot_sdb = prot_sdb; cmd->prot_sdb->table.nents = count; @@ -1625,6 +1627,14 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize, SCSI_MAX_SG_CHAIN_SEGMENTS)); + if (scsi_host_prot_dma(shost)) { + shost->sg_prot_tablesize = + min_not_zero(shost->sg_prot_tablesize, + (unsigned short)SCSI_MAX_PROT_SG_SEGMENTS); + BUG_ON(shost->sg_prot_tablesize < shost->sg_tablesize); + blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize); + } + blk_queue_max_hw_sectors(q, shost->max_sectors); blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost)); blk_queue_segment_boundary(q, shost->dma_boundary); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index c3f67373a4f8..20ad59dff730 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -251,6 +251,7 @@ shost_rd_attr(host_busy, "%hu\n"); shost_rd_attr(cmd_per_lun, "%hd\n"); shost_rd_attr(can_queue, "%hd\n"); shost_rd_attr(sg_tablesize, "%hu\n"); +shost_rd_attr(sg_prot_tablesize, "%hu\n"); shost_rd_attr(unchecked_isa_dma, "%d\n"); shost_rd_attr(prot_capabilities, "%u\n"); shost_rd_attr(prot_guard_type, "%hd\n"); @@ -262,6 +263,7 @@ static struct attribute *scsi_sysfs_shost_attrs[] = { &dev_attr_cmd_per_lun.attr, &dev_attr_can_queue.attr, &dev_attr_sg_tablesize.attr, + &dev_attr_sg_prot_tablesize.attr, &dev_attr_unchecked_isa_dma.attr, &dev_attr_proc_name.attr, &dev_attr_scan.attr, diff --git a/include/linux/bio.h b/include/linux/bio.h index 5274103434ad..2c3fd7421607 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -496,6 +496,10 @@ static inline struct bio *bio_list_get(struct bio_list *bl) #define bip_for_each_vec(bvl, bip, i) \ __bip_for_each_vec(bvl, bip, i, (bip)->bip_idx) +#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ + for_each_bio(_bio) \ + bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) + #define bio_integrity(bio) (bio->bi_integrity != NULL) extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c54906f678f..7e661106270a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -124,6 +124,9 @@ struct request { * physical address coalescing is performed. */ unsigned short nr_phys_segments; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + unsigned short nr_integrity_segments; +#endif unsigned short ioprio; @@ -243,6 +246,7 @@ struct queue_limits { unsigned short logical_block_size; unsigned short max_segments; + unsigned short max_integrity_segments; unsigned char misaligned; unsigned char discard_misaligned; @@ -1213,8 +1217,13 @@ struct blk_integrity { extern int blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); -extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); -extern int blk_rq_count_integrity_sg(struct request *); +extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, + struct scatterlist *); +extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); +extern int blk_integrity_merge_rq(struct request_queue *, struct request *, + struct request *); +extern int blk_integrity_merge_bio(struct request_queue *, struct request *, + struct bio *); static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) @@ -1235,16 +1244,32 @@ static inline int blk_integrity_rq(struct request *rq) return bio_integrity(rq->bio); } +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ + q->limits.max_integrity_segments = segs; +} + +static inline unsigned short +queue_max_integrity_segments(struct request_queue *q) +{ + return q->limits.max_integrity_segments; +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ #define blk_integrity_rq(rq) (0) -#define blk_rq_count_integrity_sg(a) (0) -#define blk_rq_map_integrity_sg(a, b) (0) +#define blk_rq_count_integrity_sg(a, b) (0) +#define blk_rq_map_integrity_sg(a, b, c) (0) #define bdev_get_integrity(a) (0) #define blk_get_integrity(a) (0) #define blk_integrity_compare(a, b) (0) #define blk_integrity_register(a, b) (0) #define blk_integrity_unregister(a) do { } while (0); +#define blk_queue_max_integrity_segments(a, b) do { } while (0); +#define queue_max_integrity_segments(a) (0) +#define blk_integrity_merge_rq(a, b, c) (0) +#define blk_integrity_merge_bio(a, b, c) (0) #endif /* CONFIG_BLK_DEV_INTEGRITY */ diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 8fcb6e0e9e72..d63533a4a59e 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -31,6 +31,12 @@ struct scsi_cmnd; #define SCSI_MAX_SG_CHAIN_SEGMENTS SCSI_MAX_SG_SEGMENTS #endif +/* + * DIX-capable adapters effectively support infinite chaining for the + * protection information scatterlist + */ +#define SCSI_MAX_PROT_SG_SEGMENTS 0xFFFF + /* * Special value for scanning to specify scanning or rescanning of all * possible channels, (target) ids, or luns on a given shost. diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index b7bdecb7b76e..d0a6a845f204 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -388,6 +388,7 @@ struct scsi_host_template { * of scatter-gather. */ unsigned short sg_tablesize; + unsigned short sg_prot_tablesize; /* * Set this if the host adapter has limitations beside segment count. @@ -599,6 +600,7 @@ struct Scsi_Host { int can_queue; short cmd_per_lun; short unsigned int sg_tablesize; + short unsigned int sg_prot_tablesize; short unsigned int max_sectors; unsigned long dma_boundary; /* @@ -823,6 +825,11 @@ static inline unsigned int scsi_host_get_prot(struct Scsi_Host *shost) return shost->prot_capabilities; } +static inline int scsi_host_prot_dma(struct Scsi_Host *shost) +{ + return shost->prot_capabilities >= SHOST_DIX_TYPE0_PROTECTION; +} + static inline unsigned int scsi_host_dif_capable(struct Scsi_Host *shost, unsigned int target_type) { static unsigned char cap[] = { 0, -- cgit v1.2.3 From 11a691bea48887c27425cc40bf291e74c922df25 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 21 Oct 2010 10:32:29 +0200 Subject: block: Turn bvec_k{un,}map_irq() into static inline functions Convert bvec_k{un,}map_irq() from macros to static inline functions if !CONFIG_HIGHMEM, so we can easier detect mistakes like the one fixed in 93055c31045a2d5599ec613a0c6cdcefc481a460 ("ps3disk: passing wrong variable = to bvec_kunmap_irq()") Signed-off-by: Geert Uytterhoeven Signed-off-by: Jens Axboe --- include/linux/bio.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux/bio.h') diff --git a/include/linux/bio.h b/include/linux/bio.h index 2c3fd7421607..ba679992d39b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -346,8 +346,15 @@ static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) } #else -#define bvec_kmap_irq(bvec, flags) (page_address((bvec)->bv_page) + (bvec)->bv_offset) -#define bvec_kunmap_irq(buf, flags) do { *(flags) = 0; } while (0) +static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) +{ + return page_address(bvec->bv_page) + bvec->bv_offset; +} + +static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) +{ + *flags = 0; +} #endif static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx, -- cgit v1.2.3 From 02e031cbc843b010e72fcc05c76113c688b2860f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Nov 2010 14:54:09 +0100 Subject: block: remove REQ_HARDBARRIER REQ_HARDBARRIER is dead now, so remove the leftovers. What's left at this point is: - various checks inside the block layer. - sanity checks in bio based drivers. - now unused bio_empty_barrier helper. - Xen blockfront use of BLKIF_OP_WRITE_BARRIER - it's dead for a while, but Xen really needs to sort out it's barrier situaton. - setting of ordered tags in uas - dead code copied from old scsi drivers. - scsi different retry for barriers - it's dead and should have been removed when flushes were converted to FS requests. - blktrace handling of barriers - removed. Someone who knows blktrace better should add support for REQ_FLUSH and REQ_FUA, though. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 7 ------- block/elevator.c | 4 ++-- drivers/block/aoe/aoeblk.c | 3 --- drivers/block/loop.c | 6 ------ drivers/block/xen-blkfront.c | 2 -- drivers/scsi/scsi_error.c | 18 +++++------------- drivers/usb/storage/uas.c | 5 +---- include/linux/bio.h | 4 ---- include/linux/blk_types.h | 6 ++---- include/linux/blkdev.h | 3 +-- kernel/trace/blktrace.c | 4 ---- 11 files changed, 11 insertions(+), 51 deletions(-) (limited to 'include/linux/bio.h') diff --git a/block/blk-core.c b/block/blk-core.c index 17fcb83670c0..4ce953f1b390 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1194,13 +1194,6 @@ static int __make_request(struct request_queue *q, struct bio *bio) int where = ELEVATOR_INSERT_SORT; int rw_flags; - /* REQ_HARDBARRIER is no more */ - if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER, - "block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) { - bio_endio(bio, -EOPNOTSUPP); - return 0; - } - /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even diff --git a/block/elevator.c b/block/elevator.c index 282e8308f7e2..2569512830d3 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -429,7 +429,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) q->nr_sorted--; boundary = q->end_sector; - stop_flags = REQ_SOFTBARRIER | REQ_HARDBARRIER | REQ_STARTED; + stop_flags = REQ_SOFTBARRIER | REQ_STARTED; list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); @@ -691,7 +691,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) void __elv_add_request(struct request_queue *q, struct request *rq, int where, int plug) { - if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) { + if (rq->cmd_flags & REQ_SOFTBARRIER) { /* barriers are scheduling boundary, update end_sector */ if (rq->cmd_type == REQ_TYPE_FS || (rq->cmd_flags & REQ_DISCARD)) { diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 541e18879965..528f6318ded1 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -180,9 +180,6 @@ aoeblk_make_request(struct request_queue *q, struct bio *bio) BUG(); bio_endio(bio, -ENXIO); return 0; - } else if (bio->bi_rw & REQ_HARDBARRIER) { - bio_endio(bio, -EOPNOTSUPP); - return 0; } else if (bio->bi_io_vec == NULL) { printk(KERN_ERR "aoe: bi_io_vec is NULL\n"); BUG(); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1e5284ef65fa..7ea0bea2f7e3 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -481,12 +481,6 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) if (bio_rw(bio) == WRITE) { struct file *file = lo->lo_backing_file; - /* REQ_HARDBARRIER is deprecated */ - if (bio->bi_rw & REQ_HARDBARRIER) { - ret = -EOPNOTSUPP; - goto out; - } - if (bio->bi_rw & REQ_FLUSH) { ret = vfs_fsync(file, 0); if (unlikely(ret && ret != -EINVAL)) { diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 06e2812ba124..255035cfc88a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -289,8 +289,6 @@ static int blkif_queue_request(struct request *req) ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE : BLKIF_OP_READ; - if (req->cmd_flags & REQ_HARDBARRIER) - ring_req->operation = BLKIF_OP_WRITE_BARRIER; ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg); BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 1de30eb83bb0..f3cf924a2cd9 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -320,19 +320,11 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) "changed. The Linux SCSI layer does not " "automatically adjust these parameters.\n"); - if (scmd->request->cmd_flags & REQ_HARDBARRIER) - /* - * barrier requests should always retry on UA - * otherwise block will get a spurious error - */ - return NEEDS_RETRY; - else - /* - * for normal (non barrier) commands, pass the - * UA upwards for a determination in the - * completion functions - */ - return SUCCESS; + /* + * Pass the UA upwards for a determination in the completion + * functions. + */ + return SUCCESS; /* these three are not supported */ case COPY_ABORTED: diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 2054b1e25a65..d1268191acbd 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -331,10 +331,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp, iu->iu_id = IU_ID_COMMAND; iu->tag = cpu_to_be16(stream_id); - if (sdev->ordered_tags && (cmnd->request->cmd_flags & REQ_HARDBARRIER)) - iu->prio_attr = UAS_ORDERED_TAG; - else - iu->prio_attr = UAS_SIMPLE_TAG; + iu->prio_attr = UAS_SIMPLE_TAG; iu->len = len; int_to_scsilun(sdev->lun, &iu->lun); memcpy(iu->cdb, cmnd->cmnd, cmnd->cmd_len); diff --git a/include/linux/bio.h b/include/linux/bio.h index ba679992d39b..35dcdb3589bc 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -66,10 +66,6 @@ #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_empty_barrier(bio) \ - ((bio->bi_rw & REQ_HARDBARRIER) && \ - !bio_has_data(bio) && \ - !(bio->bi_rw & REQ_DISCARD)) static inline unsigned int bio_cur_bytes(struct bio *bio) { diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 0437ab6bb54c..46ad5197537a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -122,7 +122,6 @@ enum rq_flag_bits { __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - __REQ_HARDBARRIER, /* may not be passed by drive either */ __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_DISCARD, /* request to discard sectors */ @@ -159,7 +158,6 @@ enum rq_flag_bits { #define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) #define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) #define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) #define REQ_SYNC (1 << __REQ_SYNC) #define REQ_META (1 << __REQ_META) #define REQ_DISCARD (1 << __REQ_DISCARD) @@ -168,8 +166,8 @@ enum rq_flag_bits { #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ - REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ + REQ_NOIDLE | REQ_FLUSH | REQ_FUA) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_UNPLUG (1 << __REQ_UNPLUG) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5027a599077d..aae86fd10c4f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -552,8 +552,7 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync) * it already be started by driver. */ #define RQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \ - REQ_FLUSH | REQ_FUA) + (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ (((rq)->cmd_flags & REQ_DISCARD) || \ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index bc251ed66724..7b8ec0281548 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -168,7 +168,6 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; -#define BLK_TC_HARDBARRIER BLK_TC_BARRIER #define BLK_TC_RAHEAD BLK_TC_AHEAD /* The ilog2() calls fall out because they're constant */ @@ -196,7 +195,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, return; what |= ddir_act[rw & WRITE]; - what |= MASK_TC_BIT(rw, HARDBARRIER); what |= MASK_TC_BIT(rw, SYNC); what |= MASK_TC_BIT(rw, RAHEAD); what |= MASK_TC_BIT(rw, META); @@ -1807,8 +1805,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) if (rw & REQ_RAHEAD) rwbs[i++] = 'A'; - if (rw & REQ_HARDBARRIER) - rwbs[i++] = 'B'; if (rw & REQ_SYNC) rwbs[i++] = 'S'; if (rw & REQ_META) -- cgit v1.2.3