From 7b24fc4d7eb611da367dea3aad45473050aacd6c Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Sun, 4 Jan 2009 02:43:38 -0500 Subject: block: Don't verify integrity metadata on read error If we get an I/O error on a read request there is no point in doing a verify pass on the integrity buffer. Adjust the completion path accordingly. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 18462c5b8fff..18fc4a281a7b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -312,7 +312,6 @@ struct bio_integrity_payload { void *bip_buf; /* generated integrity data */ bio_end_io_t *bip_end_io; /* saved I/O completion fn */ - int bip_error; /* saved I/O error */ unsigned int bip_size; unsigned short bip_pool; /* pool the ivec came from */ -- cgit v1.2.3 From 16642eb68216d8e0e136a99e514e9166e7125838 Mon Sep 17 00:00:00 2001 From: Alberto Bertogli Date: Mon, 5 Jan 2009 10:18:53 +0100 Subject: Fix small typo in bio.h's documentation Signed-off-by: Alberto Bertogli Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 18fc4a281a7b..5175aa3103c6 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -144,7 +144,7 @@ struct bio { * bit 1 -- rw-ahead when set * bit 2 -- barrier * Insert a serialization point in the IO queue, forcing previously - * submitted IO to be completed before this oen is issued. + * submitted IO to be completed before this one is issued. * bit 3 -- synchronous I/O hint: the block layer will unplug immediately * Note that this does NOT indicate that the IO itself is sync, just * that the block layer will not postpone issue of this IO by plugging. -- cgit v1.2.3 From 213d9417fec62ef4c3675621b9364a667954d4dd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 6 Jan 2009 09:16:05 +0100 Subject: block: seperate bio/request unplug and sync bits Signed-off-by: Jens Axboe --- block/blk-core.c | 5 ++++- include/linux/bio.h | 18 +++++++++++------- include/linux/blkdev.h | 2 ++ 3 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index a824e49c0d0a..9e2e86fb78b8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1125,6 +1125,8 @@ void init_request_from_bio(struct request *req, struct bio *bio) if (bio_sync(bio)) req->cmd_flags |= REQ_RW_SYNC; + if (bio_unplug(bio)) + req->cmd_flags |= REQ_UNPLUG; if (bio_rw_meta(bio)) req->cmd_flags |= REQ_RW_META; @@ -1141,6 +1143,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) int el_ret, nr_sectors; const unsigned short prio = bio_prio(bio); const int sync = bio_sync(bio); + const int unplug = bio_unplug(bio); int rw_flags; nr_sectors = bio_sectors(bio); @@ -1244,7 +1247,7 @@ get_rq: blk_plug_device(q); add_request(q, req); out: - if (sync || blk_queue_nonrot(q)) + if (unplug || blk_queue_nonrot(q)) __generic_unplug_device(q); spin_unlock_irq(q->queue_lock); return 0; diff --git a/include/linux/bio.h b/include/linux/bio.h index 5175aa3103c6..f53568c5852e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -163,12 +163,15 @@ struct bio { #define BIO_RW 0 /* Must match RW in req flags (blkdev.h) */ #define BIO_RW_AHEAD 1 /* Must match FAILFAST in req flags */ #define BIO_RW_BARRIER 2 -#define BIO_RW_SYNC 3 -#define BIO_RW_META 4 -#define BIO_RW_DISCARD 5 -#define BIO_RW_FAILFAST_DEV 6 -#define BIO_RW_FAILFAST_TRANSPORT 7 -#define BIO_RW_FAILFAST_DRIVER 8 +#define BIO_RW_SYNCIO 3 +#define BIO_RW_UNPLUG 4 +#define BIO_RW_META 5 +#define BIO_RW_DISCARD 6 +#define BIO_RW_FAILFAST_DEV 7 +#define BIO_RW_FAILFAST_TRANSPORT 8 +#define BIO_RW_FAILFAST_DRIVER 9 + +#define BIO_RW_SYNC (BIO_RW_SYNCIO | BIO_RW_UNPLUG) /* * upper 16 bits of bi_rw define the io priority of this bio @@ -194,7 +197,8 @@ struct bio { #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) #define bio_barrier(bio) ((bio)->bi_rw & (1 << BIO_RW_BARRIER)) -#define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNC)) +#define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNCIO)) +#define bio_unplug(bio) ((bio)->bi_rw & (1 << BIO_RW_UNPLUG)) #define bio_failfast_dev(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_DEV)) #define bio_failfast_transport(bio) \ ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_TRANSPORT)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 044467ef7b11..75426e4b8cdf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -108,6 +108,7 @@ enum rq_flag_bits { __REQ_RW_META, /* metadata io request */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_UNPLUG, /* unplug queue on submission */ __REQ_NR_BITS, /* stops here */ }; @@ -134,6 +135,7 @@ enum rq_flag_bits { #define REQ_RW_META (1 << __REQ_RW_META) #define REQ_COPY_USER (1 << __REQ_COPY_USER) #define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_UNPLUG (1 << __REQ_UNPLUG) #define BLK_MAX_CDB 16 -- cgit v1.2.3 From 1dfa17f4ab8543d82caf4d36636b93916a18f456 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 6 Jan 2009 09:21:49 +0100 Subject: block: add bio_rw_flagged() for testing bio->bi_rw The existing functions for checking bio->bi_rw are badly named. So lets mirror what we do for bio->bi_flags testing, use a properly named function so that it's immediately obvious what is being tested. Maintain compatability names for the old macros, eventually we'll get rid of these. Signed-off-by: Jens Axboe --- include/linux/bio.h | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index f53568c5852e..0942765cf8c0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -173,6 +173,24 @@ struct bio { #define BIO_RW_SYNC (BIO_RW_SYNCIO | BIO_RW_UNPLUG) +#define bio_rw_flagged(bio, flag) ((bio)->bi_rw & (1 << (flag))) + +/* + * Old defines, these should eventually be replaced by direct usage of + * bio_rw_flagged() + */ +#define bio_barrier(bio) bio_rw_flagged(bio, BIO_RW_BARRIER) +#define bio_sync(bio) bio_rw_flagged(bio, BIO_RW_SYNCIO) +#define bio_unplug(bio) bio_rw_flagged(bio, BIO_RW_UNPLUG) +#define bio_failfast_dev(bio) bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV) +#define bio_failfast_transport(bio) \ + bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT) +#define bio_failfast_driver(bio) \ + bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER) +#define bio_rw_ahead(bio) bio_rw_flagged(bio, BIO_RW_AHEAD) +#define bio_rw_meta(bio) bio_rw_flagged(bio, BIO_RW_META) +#define bio_discard(bio) bio_rw_flagged(bio, BIO_RW_DISCARD) + /* * upper 16 bits of bi_rw define the io priority of this bio */ @@ -196,16 +214,6 @@ struct bio { #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_barrier(bio) ((bio)->bi_rw & (1 << BIO_RW_BARRIER)) -#define bio_sync(bio) ((bio)->bi_rw & (1 << BIO_RW_SYNCIO)) -#define bio_unplug(bio) ((bio)->bi_rw & (1 << BIO_RW_UNPLUG)) -#define bio_failfast_dev(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_DEV)) -#define bio_failfast_transport(bio) \ - ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_TRANSPORT)) -#define bio_failfast_driver(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_DRIVER)) -#define bio_rw_ahead(bio) ((bio)->bi_rw & (1 << BIO_RW_AHEAD)) -#define bio_rw_meta(bio) ((bio)->bi_rw & (1 << BIO_RW_META)) -#define bio_discard(bio) ((bio)->bi_rw & (1 << BIO_RW_DISCARD)) #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) -- cgit v1.2.3 From a229fc61ef0ee3c30fd193beee0eeb87410227f1 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Mon, 19 Jan 2009 10:37:38 +0100 Subject: include/linux: Add bsg.h to the Kernel exported headers bsg.h in current form is perfectly suitable for user-mode consumption. It is needed together with scsi/sg.h for applications that want to interface with the bsg driver. Currently the few projects that use it would copy it over into the projects. But that is not acceptable for projects that need to provide source and devel packages for distros. This should also be submitted to stable 2.6.28 and 2.6.27 since bsg had a stable API since these Kernels and distro users will need the header for these kernels a swell Signed-off-by: Boaz Harrosh Acked-by: FUJITA Tomonori CC: stable@kernel.org Signed-off-by: Jens Axboe --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 12e9a2957caf..2124c063a7ef 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -41,6 +41,7 @@ header-y += baycom.h header-y += bfs_fs.h header-y += blkpg.h header-y += bpqether.h +header-y += bsg.h header-y += can.h header-y += cdk.h header-y += chio.h -- cgit v1.2.3 From bc58ba9468d94d62c56ab9b47173583ec140b165 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Jan 2009 10:54:44 +0100 Subject: block: add sysfs file for controlling io stats accounting This allows us to turn off disk stat accounting completely, for the cases where the 0.5-1% reduction in system time is important. Signed-off-by: Jens Axboe --- block/blk-core.c | 90 ++++++++++++++++++++++++++++++-------------------- block/blk-sysfs.c | 28 ++++++++++++++++ include/linux/blkdev.h | 6 ++++ 3 files changed, 88 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index ae75c047f45d..ca69f3d94100 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -64,11 +64,12 @@ static struct workqueue_struct *kblockd_workqueue; static void drive_stat_acct(struct request *rq, int new_io) { + struct gendisk *disk = rq->rq_disk; struct hd_struct *part; int rw = rq_data_dir(rq); int cpu; - if (!blk_fs_request(rq) || !rq->rq_disk) + if (!blk_fs_request(rq) || !disk || !blk_queue_io_stat(disk->queue)) return; cpu = part_stat_lock(); @@ -599,8 +600,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) q->request_fn = rfn; q->prep_rq_fn = NULL; q->unplug_fn = generic_unplug_device; - q->queue_flags = (1 << QUEUE_FLAG_CLUSTER | - 1 << QUEUE_FLAG_STACKABLE); + q->queue_flags = QUEUE_FLAG_DEFAULT; q->queue_lock = lock; blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK); @@ -1663,6 +1663,55 @@ void blkdev_dequeue_request(struct request *req) } EXPORT_SYMBOL(blkdev_dequeue_request); +static void blk_account_io_completion(struct request *req, unsigned int bytes) +{ + struct gendisk *disk = req->rq_disk; + + if (!disk || !blk_queue_io_stat(disk->queue)) + return; + + if (blk_fs_request(req)) { + const int rw = rq_data_dir(req); + struct hd_struct *part; + int cpu; + + cpu = part_stat_lock(); + part = disk_map_sector_rcu(req->rq_disk, req->sector); + part_stat_add(cpu, part, sectors[rw], bytes >> 9); + part_stat_unlock(); + } +} + +static void blk_account_io_done(struct request *req) +{ + struct gendisk *disk = req->rq_disk; + + if (!disk || !blk_queue_io_stat(disk->queue)) + return; + + /* + * Account IO completion. bar_rq isn't accounted as a normal + * IO on queueing nor completion. Accounting the containing + * request is enough. + */ + if (blk_fs_request(req) && req != &req->q->bar_rq) { + unsigned long duration = jiffies - req->start_time; + const int rw = rq_data_dir(req); + struct hd_struct *part; + int cpu; + + cpu = part_stat_lock(); + part = disk_map_sector_rcu(disk, req->sector); + + part_stat_inc(cpu, part, ios[rw]); + part_stat_add(cpu, part, ticks[rw], duration); + part_round_stats(cpu, part); + part_dec_in_flight(part); + + part_stat_unlock(); + } +} + /** * __end_that_request_first - end I/O on a request * @req: the request being processed @@ -1698,16 +1747,7 @@ static int __end_that_request_first(struct request *req, int error, (unsigned long long)req->sector); } - if (blk_fs_request(req) && req->rq_disk) { - const int rw = rq_data_dir(req); - struct hd_struct *part; - int cpu; - - cpu = part_stat_lock(); - part = disk_map_sector_rcu(req->rq_disk, req->sector); - part_stat_add(cpu, part, sectors[rw], nr_bytes >> 9); - part_stat_unlock(); - } + blk_account_io_completion(req, nr_bytes); total_bytes = bio_nbytes = 0; while ((bio = req->bio) != NULL) { @@ -1787,8 +1827,6 @@ static int __end_that_request_first(struct request *req, int error, */ static void end_that_request_last(struct request *req, int error) { - struct gendisk *disk = req->rq_disk; - if (blk_rq_tagged(req)) blk_queue_end_tag(req->q, req); @@ -1800,27 +1838,7 @@ static void end_that_request_last(struct request *req, int error) blk_delete_timer(req); - /* - * Account IO completion. bar_rq isn't accounted as a normal - * IO on queueing nor completion. Accounting the containing - * request is enough. - */ - if (disk && blk_fs_request(req) && req != &req->q->bar_rq) { - unsigned long duration = jiffies - req->start_time; - const int rw = rq_data_dir(req); - struct hd_struct *part; - int cpu; - - cpu = part_stat_lock(); - part = disk_map_sector_rcu(disk, req->sector); - - part_stat_inc(cpu, part, ios[rw]); - part_stat_add(cpu, part, ticks[rw], duration); - part_round_stats(cpu, part); - part_dec_in_flight(part); - - part_stat_unlock(); - } + blk_account_io_done(req); if (req->end_io) req->end_io(req, error); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b538ab8dbbd1..e29ddfc73cf4 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -197,6 +197,27 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count) return ret; } +static ssize_t queue_iostats_show(struct request_queue *q, char *page) +{ + return queue_var_show(blk_queue_io_stat(q), page); +} + +static ssize_t queue_iostats_store(struct request_queue *q, const char *page, + size_t count) +{ + unsigned long stats; + ssize_t ret = queue_var_store(&stats, page, count); + + spin_lock_irq(q->queue_lock); + if (stats) + queue_flag_set(QUEUE_FLAG_IO_STAT, q); + else + queue_flag_clear(QUEUE_FLAG_IO_STAT, q); + spin_unlock_irq(q->queue_lock); + + return ret; +} + static struct queue_sysfs_entry queue_requests_entry = { .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR }, .show = queue_requests_show, @@ -249,6 +270,12 @@ static struct queue_sysfs_entry queue_rq_affinity_entry = { .store = queue_rq_affinity_store, }; +static struct queue_sysfs_entry queue_iostats_entry = { + .attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR }, + .show = queue_iostats_show, + .store = queue_iostats_store, +}; + static struct attribute *default_attrs[] = { &queue_requests_entry.attr, &queue_ra_entry.attr, @@ -259,6 +286,7 @@ static struct attribute *default_attrs[] = { &queue_nonrot_entry.attr, &queue_nomerges_entry.attr, &queue_rq_affinity_entry.attr, + &queue_iostats_entry.attr, NULL, }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 75426e4b8cdf..d08c4b8219a6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -451,6 +451,11 @@ struct request_queue #define QUEUE_FLAG_STACKABLE 13 /* supports request stacking */ #define QUEUE_FLAG_NONROT 14 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ +#define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ + +#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ + (1 << QUEUE_FLAG_CLUSTER) | \ + 1 << QUEUE_FLAG_STACKABLE) static inline int queue_is_locked(struct request_queue *q) { @@ -567,6 +572,7 @@ enum { #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) +#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) -- cgit v1.2.3