From 797476b88bde2a6001f9552f383f147e58c1a330 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 18 Oct 2016 15:40:29 +0900 Subject: block: Add 'zoned' queue limit Add the zoned queue limit to indicate the zoning model of a block device. Defined values are 0 (BLK_ZONED_NONE) for regular block devices, 1 (BLK_ZONED_HA) for host-aware zone block devices and 2 (BLK_ZONED_HM) for host-managed zone block devices. The standards defined drive managed model is not defined here since these block devices do not provide any command for accessing zone information. Drive managed model devices will be reported as BLK_ZONED_NONE. The helper functions blk_queue_zoned_model and bdev_zoned_model return the zoned limit and the functions blk_queue_is_zoned and bdev_is_zoned return a boolean for callers to test if a block device is zoned. The zoned attribute is also exported as a string to applications via sysfs. BLK_ZONED_NONE shows as "none", BLK_ZONED_HA as "host-aware" and BLK_ZONED_HM as "host-managed". Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Shaun Tancheff Tested-by: Shaun Tancheff Signed-off-by: Jens Axboe --- Documentation/ABI/testing/sysfs-block | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index 71d184dbb70d..75a5055a722b 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -235,3 +235,19 @@ Description: write_same_max_bytes is 0, write same is not supported by the device. +What: /sys/block//queue/zoned +Date: September 2016 +Contact: Damien Le Moal +Description: + zoned indicates if the device is a zoned block device + and the zone model of the device if it is indeed zoned. + The possible values indicated by zoned are "none" for + regular block devices and "host-aware" or "host-managed" + for zoned block devices. The characteristics of + host-aware and host-managed zoned block devices are + described in the ZBC (Zoned Block Commands) and ZAC + (Zoned Device ATA Command Set) standards. These standards + also define the "drive-managed" zone model. However, + since drive-managed zoned block devices do not support + zone commands, they will be treated as regular block + devices and zoned will report "none". -- cgit v1.2.3-58-ga151 From 87caf97cf54b5082e56af241b88a2b8a30d17ef3 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 18 Oct 2016 15:40:30 +0900 Subject: blk-sysfs: Add 'chunk_sectors' to sysfs attributes The queue limits already have a 'chunk_sectors' setting, so we should be presenting it via sysfs. Signed-off-by: Hannes Reinecke [Damien: Updated Documentation/ABI/testing/sysfs-block] Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Shaun Tancheff Tested-by: Shaun Tancheff Signed-off-by: Jens Axboe --- Documentation/ABI/testing/sysfs-block | 13 +++++++++++++ block/blk-sysfs.c | 11 +++++++++++ 2 files changed, 24 insertions(+) (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index 75a5055a722b..ee2d5cd26bfe 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -251,3 +251,16 @@ Description: since drive-managed zoned block devices do not support zone commands, they will be treated as regular block devices and zoned will report "none". + +What: /sys/block//queue/chunk_sectors +Date: September 2016 +Contact: Hannes Reinecke +Description: + chunk_sectors has different meaning depending on the type + of the disk. For a RAID device (dm-raid), chunk_sectors + indicates the size in 512B sectors of the RAID volume + stripe segment. For a zoned block device, either + host-aware or host-managed, chunk_sectors indicates the + size of 512B sectors of the zones of the device, with + the eventual exception of the last zone of the device + which may be smaller. diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index ff9cd9cd35a3..488c2e28feb8 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -130,6 +130,11 @@ static ssize_t queue_physical_block_size_show(struct request_queue *q, char *pag return queue_var_show(queue_physical_block_size(q), page); } +static ssize_t queue_chunk_sectors_show(struct request_queue *q, char *page) +{ + return queue_var_show(q->limits.chunk_sectors, page); +} + static ssize_t queue_io_min_show(struct request_queue *q, char *page) { return queue_var_show(queue_io_min(q), page); @@ -455,6 +460,11 @@ static struct queue_sysfs_entry queue_physical_block_size_entry = { .show = queue_physical_block_size_show, }; +static struct queue_sysfs_entry queue_chunk_sectors_entry = { + .attr = {.name = "chunk_sectors", .mode = S_IRUGO }, + .show = queue_chunk_sectors_show, +}; + static struct queue_sysfs_entry queue_io_min_entry = { .attr = {.name = "minimum_io_size", .mode = S_IRUGO }, .show = queue_io_min_show, @@ -555,6 +565,7 @@ static struct attribute *default_attrs[] = { &queue_hw_sector_size_entry.attr, &queue_logical_block_size_entry.attr, &queue_physical_block_size_entry.attr, + &queue_chunk_sectors_entry.attr, &queue_io_min_entry.attr, &queue_io_opt_entry.attr, &queue_discard_granularity_entry.attr, -- cgit v1.2.3-58-ga151 From e806402130c9c494e22c73ae9ead4e79d2a5811c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Oct 2016 15:12:13 +0200 Subject: block: split out request-only flags into a new namespace A lot of the REQ_* flags are only used on struct requests, and only of use to the block layer and a few drivers that dig into struct request internals. This patch adds a new req_flags_t rq_flags field to struct request for them, and thus dramatically shrinks the number of common requests. It also removes the unfortunate situation where we have to fit the fields from the same enum into 32 bits for struct bio and 64 bits for struct request. Signed-off-by: Christoph Hellwig Reviewed-by: Shaun Tancheff Signed-off-by: Jens Axboe --- Documentation/block/biodoc.txt | 2 +- block/blk-core.c | 71 ++++++++++++++------------- block/blk-exec.c | 2 +- block/blk-flush.c | 9 ++-- block/blk-map.c | 4 +- block/blk-merge.c | 8 +-- block/blk-mq.c | 19 ++++---- block/blk-tag.c | 6 +-- block/blk.h | 4 +- block/elevator.c | 32 ++++++------ drivers/block/pktcdvd.c | 2 +- drivers/ide/ide-atapi.c | 6 +-- drivers/ide/ide-cd.c | 46 +++++++++--------- drivers/ide/ide-cd.h | 2 +- drivers/ide/ide-cd_ioctl.c | 6 +-- drivers/ide/ide-io.c | 6 +-- drivers/ide/ide-pm.c | 4 +- drivers/md/dm-rq.c | 12 ++--- drivers/memstick/core/ms_block.c | 2 +- drivers/memstick/core/mspro_block.c | 2 +- drivers/mmc/card/block.c | 4 +- drivers/mmc/card/queue.c | 4 +- drivers/nvme/host/pci.c | 4 +- drivers/scsi/device_handler/scsi_dh_alua.c | 8 +-- drivers/scsi/device_handler/scsi_dh_emc.c | 2 +- drivers/scsi/device_handler/scsi_dh_hp_sw.c | 2 +- drivers/scsi/device_handler/scsi_dh_rdac.c | 2 +- drivers/scsi/osd/osd_initiator.c | 2 +- drivers/scsi/osst.c | 2 +- drivers/scsi/scsi_error.c | 2 +- drivers/scsi/scsi_lib.c | 75 +++++++++++++++++------------ drivers/scsi/sd.c | 6 +-- drivers/scsi/sd_zbc.c | 2 +- drivers/scsi/st.c | 2 +- drivers/scsi/ufs/ufshcd.c | 6 +-- include/linux/blk_types.h | 39 +-------------- include/linux/blkdev.h | 49 ++++++++++++++++++- include/scsi/scsi_device.h | 4 +- 38 files changed, 242 insertions(+), 218 deletions(-) (limited to 'Documentation') diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 918e1e0d0e78..6acea160298c 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -348,7 +348,7 @@ Drivers can now specify a request prepare function (q->prep_rq_fn) that the block layer would invoke to pre-build device commands for a given request, or perform other preparatory processing for the request. This is routine is called by elv_next_request(), i.e. typically just before servicing a request. -(The prepare function would not be called for requests that have REQ_DONTPREP +(The prepare function would not be called for requests that have RQF_DONTPREP enabled) Aside: diff --git a/block/blk-core.c b/block/blk-core.c index e4eda5d2aa56..fd416651a676 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -145,13 +145,13 @@ static void req_bio_endio(struct request *rq, struct bio *bio, if (error) bio->bi_error = error; - if (unlikely(rq->cmd_flags & REQ_QUIET)) + if (unlikely(rq->rq_flags & RQF_QUIET)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, nbytes); /* don't actually finish bio if it's part of flush sequence */ - if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) + if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); } @@ -899,7 +899,7 @@ EXPORT_SYMBOL(blk_get_queue); static inline void blk_free_request(struct request_list *rl, struct request *rq) { - if (rq->cmd_flags & REQ_ELVPRIV) { + if (rq->rq_flags & RQF_ELVPRIV) { elv_put_request(rl->q, rq); if (rq->elv.icq) put_io_context(rq->elv.icq->ioc); @@ -961,14 +961,14 @@ static void __freed_request(struct request_list *rl, int sync) * A request has just been released. Account for it, update the full and * congestion status, wake up any waiters. Called under q->queue_lock. */ -static void freed_request(struct request_list *rl, int op, unsigned int flags) +static void freed_request(struct request_list *rl, bool sync, + req_flags_t rq_flags) { struct request_queue *q = rl->q; - int sync = rw_is_sync(op, flags); q->nr_rqs[sync]--; rl->count[sync]--; - if (flags & REQ_ELVPRIV) + if (rq_flags & RQF_ELVPRIV) q->nr_rqs_elvpriv--; __freed_request(rl, sync); @@ -1079,6 +1079,7 @@ static struct request *__get_request(struct request_list *rl, int op, struct io_cq *icq = NULL; const bool is_sync = rw_is_sync(op, op_flags) != 0; int may_queue; + req_flags_t rq_flags = RQF_ALLOCED; if (unlikely(blk_queue_dying(q))) return ERR_PTR(-ENODEV); @@ -1127,7 +1128,7 @@ static struct request *__get_request(struct request_list *rl, int op, /* * Decide whether the new request will be managed by elevator. If - * so, mark @op_flags and increment elvpriv. Non-zero elvpriv will + * so, mark @rq_flags and increment elvpriv. Non-zero elvpriv will * prevent the current elevator from being destroyed until the new * request is freed. This guarantees icq's won't be destroyed and * makes creating new ones safe. @@ -1136,14 +1137,14 @@ static struct request *__get_request(struct request_list *rl, int op, * it will be created after releasing queue_lock. */ if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) { - op_flags |= REQ_ELVPRIV; + rq_flags |= RQF_ELVPRIV; q->nr_rqs_elvpriv++; if (et->icq_cache && ioc) icq = ioc_lookup_icq(ioc, q); } if (blk_queue_io_stat(q)) - op_flags |= REQ_IO_STAT; + rq_flags |= RQF_IO_STAT; spin_unlock_irq(q->queue_lock); /* allocate and init request */ @@ -1153,10 +1154,11 @@ static struct request *__get_request(struct request_list *rl, int op, blk_rq_init(q, rq); blk_rq_set_rl(rq, rl); - req_set_op_attrs(rq, op, op_flags | REQ_ALLOCED); + req_set_op_attrs(rq, op, op_flags); + rq->rq_flags = rq_flags; /* init elvpriv */ - if (op_flags & REQ_ELVPRIV) { + if (rq_flags & RQF_ELVPRIV) { if (unlikely(et->icq_cache && !icq)) { if (ioc) icq = ioc_create_icq(ioc, q, gfp_mask); @@ -1195,7 +1197,7 @@ fail_elvpriv: printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n", __func__, dev_name(q->backing_dev_info.dev)); - rq->cmd_flags &= ~REQ_ELVPRIV; + rq->rq_flags &= ~RQF_ELVPRIV; rq->elv.icq = NULL; spin_lock_irq(q->queue_lock); @@ -1212,7 +1214,7 @@ fail_alloc: * queue, but this is pretty rare. */ spin_lock_irq(q->queue_lock); - freed_request(rl, op, op_flags); + freed_request(rl, is_sync, rq_flags); /* * in the very unlikely event that allocation failed and no @@ -1347,7 +1349,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) blk_clear_rq_complete(rq); trace_block_rq_requeue(q, rq); - if (rq->cmd_flags & REQ_QUEUED) + if (rq->rq_flags & RQF_QUEUED) blk_queue_end_tag(q, rq); BUG_ON(blk_queued_rq(rq)); @@ -1409,7 +1411,7 @@ EXPORT_SYMBOL_GPL(part_round_stats); #ifdef CONFIG_PM static void blk_pm_put_request(struct request *rq) { - if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending) + if (rq->q->dev && !(rq->rq_flags & RQF_PM) && !--rq->q->nr_pending) pm_runtime_mark_last_busy(rq->q->dev); } #else @@ -1421,6 +1423,8 @@ static inline void blk_pm_put_request(struct request *rq) {} */ void __blk_put_request(struct request_queue *q, struct request *req) { + req_flags_t rq_flags = req->rq_flags; + if (unlikely(!q)) return; @@ -1440,16 +1444,15 @@ void __blk_put_request(struct request_queue *q, struct request *req) * Request may not have originated from ll_rw_blk. if not, * it didn't come out of our reserved rq pools */ - if (req->cmd_flags & REQ_ALLOCED) { - unsigned int flags = req->cmd_flags; - int op = req_op(req); + if (rq_flags & RQF_ALLOCED) { struct request_list *rl = blk_rq_rl(req); + bool sync = rw_is_sync(req_op(req), req->cmd_flags); BUG_ON(!list_empty(&req->queuelist)); BUG_ON(ELV_ON_HASH(req)); blk_free_request(rl, req); - freed_request(rl, op, flags); + freed_request(rl, sync, rq_flags); blk_put_rl(rl); } } @@ -2214,7 +2217,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq) unsigned int bytes = 0; struct bio *bio; - if (!(rq->cmd_flags & REQ_MIXED_MERGE)) + if (!(rq->rq_flags & RQF_MIXED_MERGE)) return blk_rq_bytes(rq); /* @@ -2257,7 +2260,7 @@ void blk_account_io_done(struct request *req) * normal IO on queueing nor completion. Accounting the * containing request is enough. */ - if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) { + if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { unsigned long duration = jiffies - req->start_time; const int rw = rq_data_dir(req); struct hd_struct *part; @@ -2285,7 +2288,7 @@ static struct request *blk_pm_peek_request(struct request_queue *q, struct request *rq) { if (q->dev && (q->rpm_status == RPM_SUSPENDED || - (q->rpm_status != RPM_ACTIVE && !(rq->cmd_flags & REQ_PM)))) + (q->rpm_status != RPM_ACTIVE && !(rq->rq_flags & RQF_PM)))) return NULL; else return rq; @@ -2361,13 +2364,13 @@ struct request *blk_peek_request(struct request_queue *q) if (!rq) break; - if (!(rq->cmd_flags & REQ_STARTED)) { + if (!(rq->rq_flags & RQF_STARTED)) { /* * This is the first time the device driver * sees this request (possibly after * requeueing). Notify IO scheduler. */ - if (rq->cmd_flags & REQ_SORTED) + if (rq->rq_flags & RQF_SORTED) elv_activate_rq(q, rq); /* @@ -2375,7 +2378,7 @@ struct request *blk_peek_request(struct request_queue *q) * it, a request that has been delayed should * not be passed by new incoming requests */ - rq->cmd_flags |= REQ_STARTED; + rq->rq_flags |= RQF_STARTED; trace_block_rq_issue(q, rq); } @@ -2384,7 +2387,7 @@ struct request *blk_peek_request(struct request_queue *q) q->boundary_rq = NULL; } - if (rq->cmd_flags & REQ_DONTPREP) + if (rq->rq_flags & RQF_DONTPREP) break; if (q->dma_drain_size && blk_rq_bytes(rq)) { @@ -2407,11 +2410,11 @@ struct request *blk_peek_request(struct request_queue *q) /* * the request may have been (partially) prepped. * we need to keep this request in the front to - * avoid resource deadlock. REQ_STARTED will + * avoid resource deadlock. RQF_STARTED will * prevent other fs requests from passing this one. */ if (q->dma_drain_size && blk_rq_bytes(rq) && - !(rq->cmd_flags & REQ_DONTPREP)) { + !(rq->rq_flags & RQF_DONTPREP)) { /* * remove the space for the drain we added * so that we don't add it again @@ -2424,7 +2427,7 @@ struct request *blk_peek_request(struct request_queue *q) } else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) { int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO; - rq->cmd_flags |= REQ_QUIET; + rq->rq_flags |= RQF_QUIET; /* * Mark this request as started so we don't trigger * any debug logic in the end I/O path. @@ -2561,7 +2564,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) req->errors = 0; if (error && req->cmd_type == REQ_TYPE_FS && - !(req->cmd_flags & REQ_QUIET)) { + !(req->rq_flags & RQF_QUIET)) { char *error_type; switch (error) { @@ -2634,7 +2637,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ - if (req->cmd_flags & REQ_MIXED_MERGE) { + if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } @@ -2687,7 +2690,7 @@ void blk_unprep_request(struct request *req) { struct request_queue *q = req->q; - req->cmd_flags &= ~REQ_DONTPREP; + req->rq_flags &= ~RQF_DONTPREP; if (q->unprep_rq_fn) q->unprep_rq_fn(q, req); } @@ -2698,7 +2701,7 @@ EXPORT_SYMBOL_GPL(blk_unprep_request); */ void blk_finish_request(struct request *req, int error) { - if (req->cmd_flags & REQ_QUEUED) + if (req->rq_flags & RQF_QUEUED) blk_queue_end_tag(req->q, req); BUG_ON(blk_queued_rq(req)); @@ -2708,7 +2711,7 @@ void blk_finish_request(struct request *req, int error) blk_delete_timer(req); - if (req->cmd_flags & REQ_DONTPREP) + if (req->rq_flags & RQF_DONTPREP) blk_unprep_request(req); blk_account_io_done(req); diff --git a/block/blk-exec.c b/block/blk-exec.c index 7ea04325d02f..3ecb00a6cf45 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -72,7 +72,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, spin_lock_irq(q->queue_lock); if (unlikely(blk_queue_dying(q))) { - rq->cmd_flags |= REQ_QUIET; + rq->rq_flags |= RQF_QUIET; rq->errors = -ENXIO; __blk_end_request_all(rq, rq->errors); spin_unlock_irq(q->queue_lock); diff --git a/block/blk-flush.c b/block/blk-flush.c index 6a14b68b9135..3990b9cfbda5 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -56,7 +56,7 @@ * Once while executing DATA and again after the whole sequence is * complete. The first completion updates the contained bio but doesn't * finish it so that the bio submitter is notified only after the whole - * sequence is complete. This is implemented by testing REQ_FLUSH_SEQ in + * sequence is complete. This is implemented by testing RQF_FLUSH_SEQ in * req_bio_endio(). * * The above peculiarity requires that each FLUSH/FUA request has only one @@ -127,7 +127,7 @@ static void blk_flush_restore_request(struct request *rq) rq->bio = rq->biotail; /* make @rq a normal request */ - rq->cmd_flags &= ~REQ_FLUSH_SEQ; + rq->rq_flags &= ~RQF_FLUSH_SEQ; rq->end_io = rq->flush.saved_end_io; } @@ -330,7 +330,8 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq) } flush_rq->cmd_type = REQ_TYPE_FS; - req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ); + req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH); + flush_rq->rq_flags |= RQF_FLUSH_SEQ; flush_rq->rq_disk = first_rq->rq_disk; flush_rq->end_io = flush_end_io; @@ -433,7 +434,7 @@ void blk_insert_flush(struct request *rq) */ memset(&rq->flush, 0, sizeof(rq->flush)); INIT_LIST_HEAD(&rq->flush.list); - rq->cmd_flags |= REQ_FLUSH_SEQ; + rq->rq_flags |= RQF_FLUSH_SEQ; rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ if (q->mq_ops) { rq->end_io = mq_flush_data_end_io; diff --git a/block/blk-map.c b/block/blk-map.c index b8657fa8dc9a..2c5ae5fef473 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -135,7 +135,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, } while (iov_iter_count(&i)); if (!bio_flagged(bio, BIO_USER_MAPPED)) - rq->cmd_flags |= REQ_COPY_USER; + rq->rq_flags |= RQF_COPY_USER; return 0; unmap_rq: @@ -232,7 +232,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, bio_set_op_attrs(bio, REQ_OP_WRITE, 0); if (do_copy) - rq->cmd_flags |= REQ_COPY_USER; + rq->rq_flags |= RQF_COPY_USER; ret = blk_rq_append_bio(rq, bio); if (unlikely(ret)) { diff --git a/block/blk-merge.c b/block/blk-merge.c index 2642e5fc8b69..fda6a12fc776 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -456,7 +456,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, if (rq->bio) nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg); - if (unlikely(rq->cmd_flags & REQ_COPY_USER) && + if (unlikely(rq->rq_flags & RQF_COPY_USER) && (blk_rq_bytes(rq) & q->dma_pad_mask)) { unsigned int pad_len = (q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1; @@ -634,7 +634,7 @@ void blk_rq_set_mixed_merge(struct request *rq) unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; - if (rq->cmd_flags & REQ_MIXED_MERGE) + if (rq->rq_flags & RQF_MIXED_MERGE) return; /* @@ -647,7 +647,7 @@ void blk_rq_set_mixed_merge(struct request *rq) (bio->bi_opf & REQ_FAILFAST_MASK) != ff); bio->bi_opf |= ff; } - rq->cmd_flags |= REQ_MIXED_MERGE; + rq->rq_flags |= RQF_MIXED_MERGE; } static void blk_account_io_merge(struct request *req) @@ -709,7 +709,7 @@ static int attempt_merge(struct request_queue *q, struct request *req, * makes sure that all involved bios have mixable attributes * set properly. */ - if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE || + if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) || (req->cmd_flags & REQ_FAILFAST_MASK) != (next->cmd_flags & REQ_FAILFAST_MASK)) { blk_rq_set_mixed_merge(req); diff --git a/block/blk-mq.c b/block/blk-mq.c index d74a74a9f9ef..b49c6658eb05 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -142,14 +142,13 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, struct request *rq, int op, unsigned int op_flags) { - if (blk_queue_io_stat(q)) - op_flags |= REQ_IO_STAT; - INIT_LIST_HEAD(&rq->queuelist); /* csd/requeue_work/fifo_time is initialized before use */ rq->q = q; rq->mq_ctx = ctx; req_set_op_attrs(rq, op, op_flags); + if (blk_queue_io_stat(q)) + rq->rq_flags |= RQF_IO_STAT; /* do not touch atomic flags, it needs atomic ops against the timer */ rq->cpu = -1; INIT_HLIST_NODE(&rq->hash); @@ -198,7 +197,7 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags) rq = data->hctx->tags->rqs[tag]; if (blk_mq_tag_busy(data->hctx)) { - rq->cmd_flags = REQ_MQ_INFLIGHT; + rq->rq_flags = RQF_MQ_INFLIGHT; atomic_inc(&data->hctx->nr_active); } @@ -298,9 +297,9 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, const int tag = rq->tag; struct request_queue *q = rq->q; - if (rq->cmd_flags & REQ_MQ_INFLIGHT) + if (rq->rq_flags & RQF_MQ_INFLIGHT) atomic_dec(&hctx->nr_active); - rq->cmd_flags = 0; + rq->rq_flags = 0; clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); blk_mq_put_tag(hctx, ctx, tag); @@ -489,10 +488,10 @@ static void blk_mq_requeue_work(struct work_struct *work) spin_unlock_irqrestore(&q->requeue_lock, flags); list_for_each_entry_safe(rq, next, &rq_list, queuelist) { - if (!(rq->cmd_flags & REQ_SOFTBARRIER)) + if (!(rq->rq_flags & RQF_SOFTBARRIER)) continue; - rq->cmd_flags &= ~REQ_SOFTBARRIER; + rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); blk_mq_insert_request(rq, true, false, false); } @@ -519,11 +518,11 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head) * We abuse this flag that is otherwise used by the I/O scheduler to * request head insertation from the workqueue. */ - BUG_ON(rq->cmd_flags & REQ_SOFTBARRIER); + BUG_ON(rq->rq_flags & RQF_SOFTBARRIER); spin_lock_irqsave(&q->requeue_lock, flags); if (at_head) { - rq->cmd_flags |= REQ_SOFTBARRIER; + rq->rq_flags |= RQF_SOFTBARRIER; list_add(&rq->queuelist, &q->requeue_list); } else { list_add_tail(&rq->queuelist, &q->requeue_list); diff --git a/block/blk-tag.c b/block/blk-tag.c index f0344e6939d5..bae1decb6ec3 100644 --- a/block/blk-tag.c +++ b/block/blk-tag.c @@ -270,7 +270,7 @@ void blk_queue_end_tag(struct request_queue *q, struct request *rq) BUG_ON(tag >= bqt->real_max_depth); list_del_init(&rq->queuelist); - rq->cmd_flags &= ~REQ_QUEUED; + rq->rq_flags &= ~RQF_QUEUED; rq->tag = -1; if (unlikely(bqt->tag_index[tag] == NULL)) @@ -316,7 +316,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq) unsigned max_depth; int tag; - if (unlikely((rq->cmd_flags & REQ_QUEUED))) { + if (unlikely((rq->rq_flags & RQF_QUEUED))) { printk(KERN_ERR "%s: request %p for device [%s] already tagged %d", __func__, rq, @@ -371,7 +371,7 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq) */ bqt->next_tag = (tag + 1) % bqt->max_depth; - rq->cmd_flags |= REQ_QUEUED; + rq->rq_flags |= RQF_QUEUED; rq->tag = tag; bqt->tag_index[tag] = rq; blk_start_request(rq); diff --git a/block/blk.h b/block/blk.h index 74444c49078f..aa132dea598c 100644 --- a/block/blk.h +++ b/block/blk.h @@ -130,7 +130,7 @@ static inline void blk_clear_rq_complete(struct request *rq) /* * Internal elevator interface */ -#define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED) +#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED) void blk_insert_flush(struct request *rq); @@ -247,7 +247,7 @@ extern int blk_update_nr_requests(struct request_queue *, unsigned int); static inline int blk_do_io_stat(struct request *rq) { return rq->rq_disk && - (rq->cmd_flags & REQ_IO_STAT) && + (rq->rq_flags & RQF_IO_STAT) && (rq->cmd_type == REQ_TYPE_FS); } diff --git a/block/elevator.c b/block/elevator.c index f7d973a56fd7..ac80f89a0842 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -245,7 +245,7 @@ EXPORT_SYMBOL(elevator_exit); static inline void __elv_rqhash_del(struct request *rq) { hash_del(&rq->hash); - rq->cmd_flags &= ~REQ_HASHED; + rq->rq_flags &= ~RQF_HASHED; } static void elv_rqhash_del(struct request_queue *q, struct request *rq) @@ -260,7 +260,7 @@ static void elv_rqhash_add(struct request_queue *q, struct request *rq) BUG_ON(ELV_ON_HASH(rq)); hash_add(e->hash, &rq->hash, rq_hash_key(rq)); - rq->cmd_flags |= REQ_HASHED; + rq->rq_flags |= RQF_HASHED; } static void elv_rqhash_reposition(struct request_queue *q, struct request *rq) @@ -352,7 +352,6 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) { sector_t boundary; struct list_head *entry; - int stop_flags; if (q->last_merge == rq) q->last_merge = NULL; @@ -362,7 +361,6 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) q->nr_sorted--; boundary = q->end_sector; - stop_flags = REQ_SOFTBARRIER | REQ_STARTED; list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); @@ -370,7 +368,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; - if (pos->cmd_flags & stop_flags) + if (pos->rq_flags & (RQF_STARTED | RQF_SOFTBARRIER)) break; if (blk_rq_pos(rq) >= boundary) { if (blk_rq_pos(pos) < boundary) @@ -510,7 +508,7 @@ void elv_merge_requests(struct request_queue *q, struct request *rq, struct request *next) { struct elevator_queue *e = q->elevator; - const int next_sorted = next->cmd_flags & REQ_SORTED; + const int next_sorted = next->rq_flags & RQF_SORTED; if (next_sorted && e->type->ops.elevator_merge_req_fn) e->type->ops.elevator_merge_req_fn(q, rq, next); @@ -537,13 +535,13 @@ void elv_bio_merged(struct request_queue *q, struct request *rq, #ifdef CONFIG_PM static void blk_pm_requeue_request(struct request *rq) { - if (rq->q->dev && !(rq->cmd_flags & REQ_PM)) + if (rq->q->dev && !(rq->rq_flags & RQF_PM)) rq->q->nr_pending--; } static void blk_pm_add_request(struct request_queue *q, struct request *rq) { - if (q->dev && !(rq->cmd_flags & REQ_PM) && q->nr_pending++ == 0 && + if (q->dev && !(rq->rq_flags & RQF_PM) && q->nr_pending++ == 0 && (q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING)) pm_request_resume(q->dev); } @@ -563,11 +561,11 @@ void elv_requeue_request(struct request_queue *q, struct request *rq) */ if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]--; - if (rq->cmd_flags & REQ_SORTED) + if (rq->rq_flags & RQF_SORTED) elv_deactivate_rq(q, rq); } - rq->cmd_flags &= ~REQ_STARTED; + rq->rq_flags &= ~RQF_STARTED; blk_pm_requeue_request(rq); @@ -597,13 +595,13 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) rq->q = q; - if (rq->cmd_flags & REQ_SOFTBARRIER) { + if (rq->rq_flags & RQF_SOFTBARRIER) { /* barriers are scheduling boundary, update end_sector */ if (rq->cmd_type == REQ_TYPE_FS) { q->end_sector = rq_end_sector(rq); q->boundary_rq = rq; } - } else if (!(rq->cmd_flags & REQ_ELVPRIV) && + } else if (!(rq->rq_flags & RQF_ELVPRIV) && (where == ELEVATOR_INSERT_SORT || where == ELEVATOR_INSERT_SORT_MERGE)) where = ELEVATOR_INSERT_BACK; @@ -611,12 +609,12 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) switch (where) { case ELEVATOR_INSERT_REQUEUE: case ELEVATOR_INSERT_FRONT: - rq->cmd_flags |= REQ_SOFTBARRIER; + rq->rq_flags |= RQF_SOFTBARRIER; list_add(&rq->queuelist, &q->queue_head); break; case ELEVATOR_INSERT_BACK: - rq->cmd_flags |= REQ_SOFTBARRIER; + rq->rq_flags |= RQF_SOFTBARRIER; elv_drain_elevator(q); list_add_tail(&rq->queuelist, &q->queue_head); /* @@ -642,7 +640,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) break; case ELEVATOR_INSERT_SORT: BUG_ON(rq->cmd_type != REQ_TYPE_FS); - rq->cmd_flags |= REQ_SORTED; + rq->rq_flags |= RQF_SORTED; q->nr_sorted++; if (rq_mergeable(rq)) { elv_rqhash_add(q, rq); @@ -659,7 +657,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) break; case ELEVATOR_INSERT_FLUSH: - rq->cmd_flags |= REQ_SOFTBARRIER; + rq->rq_flags |= RQF_SOFTBARRIER; blk_insert_flush(rq); break; default: @@ -735,7 +733,7 @@ void elv_completed_request(struct request_queue *q, struct request *rq) */ if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]--; - if ((rq->cmd_flags & REQ_SORTED) && + if ((rq->rq_flags & RQF_SORTED) && e->type->ops.elevator_completed_req_fn) e->type->ops.elevator_completed_req_fn(q, rq); } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 90fa4ac149db..7cf795e0fc8d 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -721,7 +721,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * rq->timeout = 60*HZ; if (cgc->quiet) - rq->cmd_flags |= REQ_QUIET; + rq->rq_flags |= RQF_QUIET; blk_execute_rq(rq->q, pd->bdev->bd_disk, rq, 0); if (rq->errors) diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index 05352f490d60..f90ea221f7f2 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -211,7 +211,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) sense_rq->cmd[0] = GPCMD_REQUEST_SENSE; sense_rq->cmd[4] = cmd_len; sense_rq->cmd_type = REQ_TYPE_ATA_SENSE; - sense_rq->cmd_flags |= REQ_PREEMPT; + sense_rq->rq_flags |= RQF_PREEMPT; if (drive->media == ide_tape) sense_rq->cmd[13] = REQ_IDETAPE_PC1; @@ -295,7 +295,7 @@ int ide_cd_expiry(ide_drive_t *drive) wait = ATAPI_WAIT_PC; break; default: - if (!(rq->cmd_flags & REQ_QUIET)) + if (!(rq->rq_flags & RQF_QUIET)) printk(KERN_INFO PFX "cmd 0x%x timed out\n", rq->cmd[0]); wait = 0; @@ -375,7 +375,7 @@ int ide_check_ireason(ide_drive_t *drive, struct request *rq, int len, } if (dev_is_idecd(drive) && rq->cmd_type == REQ_TYPE_ATA_PC) - rq->cmd_flags |= REQ_FAILED; + rq->rq_flags |= RQF_FAILED; return 1; } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index bf9a2ad296ed..9cbd217bc0c9 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -98,7 +98,7 @@ static int cdrom_log_sense(ide_drive_t *drive, struct request *rq) struct request_sense *sense = &drive->sense_data; int log = 0; - if (!sense || !rq || (rq->cmd_flags & REQ_QUIET)) + if (!sense || !rq || (rq->rq_flags & RQF_QUIET)) return 0; ide_debug_log(IDE_DBG_SENSE, "sense_key: 0x%x", sense->sense_key); @@ -291,7 +291,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * (probably while trying to recover from a former error). * Just give up. */ - rq->cmd_flags |= REQ_FAILED; + rq->rq_flags |= RQF_FAILED; return 2; } @@ -311,7 +311,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) cdrom_saw_media_change(drive); if (rq->cmd_type == REQ_TYPE_FS && - !(rq->cmd_flags & REQ_QUIET)) + !(rq->rq_flags & RQF_QUIET)) printk(KERN_ERR PFX "%s: tray open\n", drive->name); } @@ -346,7 +346,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * No point in retrying after an illegal request or data * protect error. */ - if (!(rq->cmd_flags & REQ_QUIET)) + if (!(rq->rq_flags & RQF_QUIET)) ide_dump_status(drive, "command error", stat); do_end_request = 1; break; @@ -355,14 +355,14 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * No point in re-trying a zillion times on a bad sector. * If we got here the error is not correctable. */ - if (!(rq->cmd_flags & REQ_QUIET)) + if (!(rq->rq_flags & RQF_QUIET)) ide_dump_status(drive, "media error " "(bad sector)", stat); do_end_request = 1; break; case BLANK_CHECK: /* disk appears blank? */ - if (!(rq->cmd_flags & REQ_QUIET)) + if (!(rq->rq_flags & RQF_QUIET)) ide_dump_status(drive, "media error (blank)", stat); do_end_request = 1; @@ -380,7 +380,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) } if (rq->cmd_type != REQ_TYPE_FS) { - rq->cmd_flags |= REQ_FAILED; + rq->rq_flags |= RQF_FAILED; do_end_request = 1; } @@ -422,19 +422,19 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd) int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, int write, void *buffer, unsigned *bufflen, struct request_sense *sense, int timeout, - unsigned int cmd_flags) + req_flags_t rq_flags) { struct cdrom_info *info = drive->driver_data; struct request_sense local_sense; int retries = 10; - unsigned int flags = 0; + req_flags_t flags = 0; if (!sense) sense = &local_sense; ide_debug_log(IDE_DBG_PC, "cmd[0]: 0x%x, write: 0x%x, timeout: %d, " - "cmd_flags: 0x%x", - cmd[0], write, timeout, cmd_flags); + "rq_flags: 0x%x", + cmd[0], write, timeout, rq_flags); /* start of retry loop */ do { @@ -446,7 +446,7 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, memcpy(rq->cmd, cmd, BLK_MAX_CDB); rq->cmd_type = REQ_TYPE_ATA_PC; rq->sense = sense; - rq->cmd_flags |= cmd_flags; + rq->rq_flags |= rq_flags; rq->timeout = timeout; if (buffer) { error = blk_rq_map_kern(drive->queue, rq, buffer, @@ -462,14 +462,14 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, if (buffer) *bufflen = rq->resid_len; - flags = rq->cmd_flags; + flags = rq->rq_flags; blk_put_request(rq); /* * FIXME: we should probably abort/retry or something in case of * failure. */ - if (flags & REQ_FAILED) { + if (flags & RQF_FAILED) { /* * The request failed. Retry if it was due to a unit * attention status (usually means media was changed). @@ -494,10 +494,10 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, } /* end of retry loop */ - } while ((flags & REQ_FAILED) && retries >= 0); + } while ((flags & RQF_FAILED) && retries >= 0); /* return an error if the command failed */ - return (flags & REQ_FAILED) ? -EIO : 0; + return (flags & RQF_FAILED) ? -EIO : 0; } /* @@ -589,7 +589,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) "(%u bytes)\n", drive->name, __func__, cmd->nleft); if (!write) - rq->cmd_flags |= REQ_FAILED; + rq->rq_flags |= RQF_FAILED; uptodate = 0; } } else if (rq->cmd_type != REQ_TYPE_BLOCK_PC) { @@ -607,7 +607,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) } if (!uptodate) - rq->cmd_flags |= REQ_FAILED; + rq->rq_flags |= RQF_FAILED; } goto out_end; } @@ -745,9 +745,9 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq) rq->cmd[0], rq->cmd_type); if (rq->cmd_type == REQ_TYPE_BLOCK_PC) - rq->cmd_flags |= REQ_QUIET; + rq->rq_flags |= RQF_QUIET; else - rq->cmd_flags &= ~REQ_FAILED; + rq->rq_flags &= ~RQF_FAILED; drive->dma = 0; @@ -867,7 +867,7 @@ int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense) */ cmd[7] = cdi->sanyo_slot % 3; - return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, REQ_QUIET); + return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, RQF_QUIET); } static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity, @@ -890,7 +890,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity, cmd[0] = GPCMD_READ_CDVD_CAPACITY; stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, sense, 0, - REQ_QUIET); + RQF_QUIET); if (stat) return stat; @@ -943,7 +943,7 @@ static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag, if (msf_flag) cmd[1] = 2; - return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, sense, 0, REQ_QUIET); + return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, sense, 0, RQF_QUIET); } /* Try to read the entire TOC for the disk into our internal buffer. */ diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h index 1efc936f5b66..eea60c986c4f 100644 --- a/drivers/ide/ide-cd.h +++ b/drivers/ide/ide-cd.h @@ -101,7 +101,7 @@ void ide_cd_log_error(const char *, struct request *, struct request_sense *); /* ide-cd.c functions used by ide-cd_ioctl.c */ int ide_cd_queue_pc(ide_drive_t *, const unsigned char *, int, void *, - unsigned *, struct request_sense *, int, unsigned int); + unsigned *, struct request_sense *, int, req_flags_t); int ide_cd_read_toc(ide_drive_t *, struct request_sense *); int ide_cdrom_get_capabilities(ide_drive_t *, u8 *); void ide_cdrom_update_speed(ide_drive_t *, u8 *); diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 5887a7a09e37..f085e3a2e1d6 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -305,7 +305,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi) rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_DRV_PRIV; - rq->cmd_flags = REQ_QUIET; + rq->rq_flags = RQF_QUIET; ret = blk_execute_rq(drive->queue, cd->disk, rq, 0); blk_put_request(rq); /* @@ -449,7 +449,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi, struct packet_command *cgc) { ide_drive_t *drive = cdi->handle; - unsigned int flags = 0; + req_flags_t flags = 0; unsigned len = cgc->buflen; if (cgc->timeout <= 0) @@ -463,7 +463,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi, memset(cgc->sense, 0, sizeof(struct request_sense)); if (cgc->quiet) - flags |= REQ_QUIET; + flags |= RQF_QUIET; cgc->stat = ide_cd_queue_pc(drive, cgc->cmd, cgc->data_direction == CGC_DATA_WRITE, diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 669ea1e45795..6360bbd37efe 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -307,7 +307,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq) { ide_startstop_t startstop; - BUG_ON(!(rq->cmd_flags & REQ_STARTED)); + BUG_ON(!(rq->rq_flags & RQF_STARTED)); #ifdef DEBUG printk("%s: start_request: current=0x%08lx\n", @@ -316,7 +316,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq) /* bail early if we've exceeded max_failures */ if (drive->max_failures && (drive->failures > drive->max_failures)) { - rq->cmd_flags |= REQ_FAILED; + rq->rq_flags |= RQF_FAILED; goto kill_rq; } @@ -539,7 +539,7 @@ repeat: */ if ((drive->dev_flags & IDE_DFLAG_BLOCKED) && ata_pm_request(rq) == 0 && - (rq->cmd_flags & REQ_PREEMPT) == 0) { + (rq->rq_flags & RQF_PREEMPT) == 0) { /* there should be no pending command at this point */ ide_unlock_port(hwif); goto plug_device; diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index e34af488693a..a015acdffb39 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -53,7 +53,7 @@ static int ide_pm_execute_rq(struct request *rq) spin_lock_irq(q->queue_lock); if (unlikely(blk_queue_dying(q))) { - rq->cmd_flags |= REQ_QUIET; + rq->rq_flags |= RQF_QUIET; rq->errors = -ENXIO; __blk_end_request_all(rq, rq->errors); spin_unlock_irq(q->queue_lock); @@ -90,7 +90,7 @@ int generic_ide_resume(struct device *dev) memset(&rqpm, 0, sizeof(rqpm)); rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); rq->cmd_type = REQ_TYPE_ATA_PM_RESUME; - rq->cmd_flags |= REQ_PREEMPT; + rq->rq_flags |= RQF_PREEMPT; rq->special = &rqpm; rqpm.pm_step = IDE_PM_START_RESUME; rqpm.pm_state = PM_EVENT_ON; diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index dc75bea0d541..f76cc36b8546 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -313,7 +313,7 @@ static void dm_unprep_request(struct request *rq) if (!rq->q->mq_ops) { rq->special = NULL; - rq->cmd_flags &= ~REQ_DONTPREP; + rq->rq_flags &= ~RQF_DONTPREP; } if (clone) @@ -431,7 +431,7 @@ static void dm_softirq_done(struct request *rq) return; } - if (rq->cmd_flags & REQ_FAILED) + if (rq->rq_flags & RQF_FAILED) mapped = false; dm_done(clone, tio->error, mapped); @@ -460,7 +460,7 @@ static void dm_complete_request(struct request *rq, int error) */ static void dm_kill_unmapped_request(struct request *rq, int error) { - rq->cmd_flags |= REQ_FAILED; + rq->rq_flags |= RQF_FAILED; dm_complete_request(rq, error); } @@ -476,7 +476,7 @@ static void end_clone_request(struct request *clone, int error) * For just cleaning up the information of the queue in which * the clone was dispatched. * The clone is *NOT* freed actually here because it is alloced - * from dm own mempool (REQ_ALLOCED isn't set). + * from dm own mempool (RQF_ALLOCED isn't set). */ __blk_put_request(clone->q, clone); } @@ -497,7 +497,7 @@ static void dm_dispatch_clone_request(struct request *clone, struct request *rq) int r; if (blk_queue_io_stat(clone->q)) - clone->cmd_flags |= REQ_IO_STAT; + clone->rq_flags |= RQF_IO_STAT; clone->start_time = jiffies; r = blk_insert_cloned_request(clone->q, clone); @@ -633,7 +633,7 @@ static int dm_old_prep_fn(struct request_queue *q, struct request *rq) return BLKPREP_DEFER; rq->special = tio; - rq->cmd_flags |= REQ_DONTPREP; + rq->rq_flags |= RQF_DONTPREP; return BLKPREP_OK; } diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index aacf584f2a42..f3512404bc52 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -2006,7 +2006,7 @@ static int msb_prepare_req(struct request_queue *q, struct request *req) blk_dump_rq_flags(req, "MS unsupported request"); return BLKPREP_KILL; } - req->cmd_flags |= REQ_DONTPREP; + req->rq_flags |= RQF_DONTPREP; return BLKPREP_OK; } diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index c1472275fe57..fa0746d182ff 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -834,7 +834,7 @@ static int mspro_block_prepare_req(struct request_queue *q, struct request *req) return BLKPREP_KILL; } - req->cmd_flags |= REQ_DONTPREP; + req->rq_flags |= RQF_DONTPREP; return BLKPREP_OK; } diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index c3335112e68c..f8190dd4a35c 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -2117,7 +2117,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) mmc_blk_abort_packed_req(mq_rq); } else { if (mmc_card_removed(card)) - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; while (ret) ret = blk_end_request(req, -EIO, blk_rq_cur_bytes(req)); @@ -2126,7 +2126,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) start_new_req: if (rqc) { if (mmc_card_removed(card)) { - rqc->cmd_flags |= REQ_QUIET; + rqc->rq_flags |= RQF_QUIET; blk_end_request_all(rqc, -EIO); } else { /* diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 8037f73a109a..8a67f1c2ce21 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -44,7 +44,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq))) return BLKPREP_KILL; - req->cmd_flags |= REQ_DONTPREP; + req->rq_flags |= RQF_DONTPREP; return BLKPREP_OK; } @@ -120,7 +120,7 @@ static void mmc_request_fn(struct request_queue *q) if (!mq) { while ((req = blk_fetch_request(q)) != NULL) { - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; __blk_end_request_all(req, -EIO); } return; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0fc99f0f2571..0955e9d22020 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -323,9 +323,9 @@ static int nvme_init_iod(struct request *rq, unsigned size, iod->nents = 0; iod->length = size; - if (!(rq->cmd_flags & REQ_DONTPREP)) { + if (!(rq->rq_flags & RQF_DONTPREP)) { rq->retries = 0; - rq->cmd_flags |= REQ_DONTPREP; + rq->rq_flags |= RQF_DONTPREP; } return 0; } diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 241829e59668..05813a420188 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -154,7 +154,8 @@ static int submit_rtpg(struct scsi_device *sdev, unsigned char *buff, return scsi_execute_req_flags(sdev, cdb, DMA_FROM_DEVICE, buff, bufflen, sshdr, ALUA_FAILOVER_TIMEOUT * HZ, - ALUA_FAILOVER_RETRIES, NULL, req_flags); + ALUA_FAILOVER_RETRIES, NULL, + req_flags, 0); } /* @@ -187,7 +188,8 @@ static int submit_stpg(struct scsi_device *sdev, int group_id, return scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE, stpg_data, stpg_len, sshdr, ALUA_FAILOVER_TIMEOUT * HZ, - ALUA_FAILOVER_RETRIES, NULL, req_flags); + ALUA_FAILOVER_RETRIES, NULL, + req_flags, 0); } static struct alua_port_group *alua_find_get_pg(char *id_str, size_t id_size, @@ -1063,7 +1065,7 @@ static int alua_prep_fn(struct scsi_device *sdev, struct request *req) state != SCSI_ACCESS_STATE_ACTIVE && state != SCSI_ACCESS_STATE_LBA) { ret = BLKPREP_KILL; - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; } return ret; diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c index 375d81850f15..5b80746980b8 100644 --- a/drivers/scsi/device_handler/scsi_dh_emc.c +++ b/drivers/scsi/device_handler/scsi_dh_emc.c @@ -452,7 +452,7 @@ static int clariion_prep_fn(struct scsi_device *sdev, struct request *req) if (h->lun_state != CLARIION_LUN_OWNED) { ret = BLKPREP_KILL; - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; } return ret; diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c index 9406d5f4a3d3..308e87195dc1 100644 --- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c +++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c @@ -266,7 +266,7 @@ static int hp_sw_prep_fn(struct scsi_device *sdev, struct request *req) if (h->path_state != HP_SW_PATH_ACTIVE) { ret = BLKPREP_KILL; - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; } return ret; diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 06fbd0b0c68a..00d9c326158e 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -724,7 +724,7 @@ static int rdac_prep_fn(struct scsi_device *sdev, struct request *req) if (h->state != RDAC_STATE_ACTIVE) { ret = BLKPREP_KILL; - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; } return ret; diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index 2f2a9910e30e..ef99f62831fb 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -1595,7 +1595,7 @@ static int _init_blk_request(struct osd_request *or, } or->request = req; - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; req->timeout = or->timeout; req->retries = or->retries; diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c index 5033223f6287..a2960f5d98ec 100644 --- a/drivers/scsi/osst.c +++ b/drivers/scsi/osst.c @@ -368,7 +368,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd, return DRIVER_ERROR << 24; blk_rq_set_block_pc(req); - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; SRpnt->bio = NULL; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 106a6adbd6f1..996e134d79fa 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1988,7 +1988,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev) req->cmd_len = COMMAND_SIZE(req->cmd[0]); - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; req->timeout = 10 * HZ; req->retries = 5; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 2cca9cffc63f..8c52622ac257 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -163,26 +163,11 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason) { __scsi_queue_insert(cmd, reason, 1); } -/** - * scsi_execute - insert request and wait for the result - * @sdev: scsi device - * @cmd: scsi command - * @data_direction: data direction - * @buffer: data buffer - * @bufflen: len of buffer - * @sense: optional sense buffer - * @timeout: request timeout in seconds - * @retries: number of times to retry request - * @flags: or into request flags; - * @resid: optional residual length - * - * returns the req->errors value which is the scsi_cmnd result - * field. - */ -int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, + +static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, unsigned char *sense, int timeout, int retries, u64 flags, - int *resid) + req_flags_t rq_flags, int *resid) { struct request *req; int write = (data_direction == DMA_TO_DEVICE); @@ -203,7 +188,8 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, req->sense_len = 0; req->retries = retries; req->timeout = timeout; - req->cmd_flags |= flags | REQ_QUIET | REQ_PREEMPT; + req->cmd_flags |= flags; + req->rq_flags |= rq_flags | RQF_QUIET | RQF_PREEMPT; /* * head injection *required* here otherwise quiesce won't work @@ -227,12 +213,37 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, return ret; } + +/** + * scsi_execute - insert request and wait for the result + * @sdev: scsi device + * @cmd: scsi command + * @data_direction: data direction + * @buffer: data buffer + * @bufflen: len of buffer + * @sense: optional sense buffer + * @timeout: request timeout in seconds + * @retries: number of times to retry request + * @flags: or into request flags; + * @resid: optional residual length + * + * returns the req->errors value which is the scsi_cmnd result + * field. + */ +int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, + int data_direction, void *buffer, unsigned bufflen, + unsigned char *sense, int timeout, int retries, u64 flags, + int *resid) +{ + return __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense, + timeout, retries, flags, 0, resid); +} EXPORT_SYMBOL(scsi_execute); int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, int retries, - int *resid, u64 flags) + int *resid, u64 flags, req_flags_t rq_flags) { char *sense = NULL; int result; @@ -242,8 +253,8 @@ int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd, if (!sense) return DRIVER_ERROR << 24; } - result = scsi_execute(sdev, cmd, data_direction, buffer, bufflen, - sense, timeout, retries, flags, resid); + result = __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, + sense, timeout, retries, flags, rq_flags, resid); if (sshdr) scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, sshdr); @@ -813,7 +824,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) */ if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d)) ; - else if (!(req->cmd_flags & REQ_QUIET)) + else if (!(req->rq_flags & RQF_QUIET)) scsi_print_sense(cmd); result = 0; /* BLOCK_PC may have set error */ @@ -943,7 +954,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) switch (action) { case ACTION_FAIL: /* Give up and fail the remainder of the request */ - if (!(req->cmd_flags & REQ_QUIET)) { + if (!(req->rq_flags & RQF_QUIET)) { static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -972,7 +983,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * A new command will be prepared and issued. */ if (q->mq_ops) { - cmd->request->cmd_flags &= ~REQ_DONTPREP; + cmd->request->rq_flags &= ~RQF_DONTPREP; scsi_mq_uninit_cmd(cmd); scsi_mq_requeue_cmd(cmd); } else { @@ -1234,7 +1245,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req) /* * If the devices is blocked we defer normal commands. */ - if (!(req->cmd_flags & REQ_PREEMPT)) + if (!(req->rq_flags & RQF_PREEMPT)) ret = BLKPREP_DEFER; break; default: @@ -1243,7 +1254,7 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req) * special commands. In particular any user initiated * command is not allowed. */ - if (!(req->cmd_flags & REQ_PREEMPT)) + if (!(req->rq_flags & RQF_PREEMPT)) ret = BLKPREP_KILL; break; } @@ -1279,7 +1290,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret) blk_delay_queue(q, SCSI_QUEUE_DELAY); break; default: - req->cmd_flags |= REQ_DONTPREP; + req->rq_flags |= RQF_DONTPREP; } return ret; @@ -1736,7 +1747,7 @@ static void scsi_request_fn(struct request_queue *q) * we add the dev to the starved list so it eventually gets * a run when a tag is freed. */ - if (blk_queue_tagged(q) && !(req->cmd_flags & REQ_QUEUED)) { + if (blk_queue_tagged(q) && !(req->rq_flags & RQF_QUEUED)) { spin_lock_irq(shost->host_lock); if (list_empty(&sdev->starved_entry)) list_add_tail(&sdev->starved_entry, @@ -1903,11 +1914,11 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, goto out_dec_target_busy; - if (!(req->cmd_flags & REQ_DONTPREP)) { + if (!(req->rq_flags & RQF_DONTPREP)) { ret = prep_to_mq(scsi_mq_prep_fn(req)); if (ret) goto out_dec_host_busy; - req->cmd_flags |= REQ_DONTPREP; + req->rq_flags |= RQF_DONTPREP; } else { blk_mq_start_request(req); } @@ -1952,7 +1963,7 @@ out: * we hit an error, as we will never see this command * again. */ - if (req->cmd_flags & REQ_DONTPREP) + if (req->rq_flags & RQF_DONTPREP) scsi_mq_uninit_cmd(cmd); break; default: diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b9618ffca829..cef1f78031d4 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1520,7 +1520,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp) */ res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, timeout, SD_MAX_RETRIES, - NULL, REQ_PM); + NULL, 0, RQF_PM); if (res == 0) break; } @@ -1879,7 +1879,7 @@ static int sd_done(struct scsi_cmnd *SCpnt) good_bytes = 0; req->__data_len = blk_rq_bytes(req); - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; } } } @@ -3278,7 +3278,7 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) return -ENODEV; res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES, NULL, REQ_PM); + SD_TIMEOUT, SD_MAX_RETRIES, NULL, 0, RQF_PM); if (res) { sd_print_result(sdkp, "Start/Stop Unit failed", res); if (driver_byte(res) & DRIVER_SENSE) diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index d5b3bd915d9e..394ab490919c 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -348,7 +348,7 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, * this case, so be quiet about the error. */ if (req_op(rq) == REQ_OP_ZONE_RESET) - rq->cmd_flags |= REQ_QUIET; + rq->rq_flags |= RQF_QUIET; break; case 0x21: /* diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 7af5226aa55b..3bc46a4abd43 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -546,7 +546,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, return DRIVER_ERROR << 24; blk_rq_set_block_pc(req); - req->cmd_flags |= REQ_QUIET; + req->rq_flags |= RQF_QUIET; mdata->null_mapped = 1; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 05c745663c10..cf549871c1ee 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -5590,7 +5590,7 @@ ufshcd_send_request_sense(struct ufs_hba *hba, struct scsi_device *sdp) ret = scsi_execute_req_flags(sdp, cmd, DMA_FROM_DEVICE, buffer, SCSI_SENSE_BUFFERSIZE, NULL, - msecs_to_jiffies(1000), 3, NULL, REQ_PM); + msecs_to_jiffies(1000), 3, NULL, 0, RQF_PM); if (ret) pr_err("%s: failed with err %d\n", __func__, ret); @@ -5652,11 +5652,11 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, /* * Current function would be generally called from the power management - * callbacks hence set the REQ_PM flag so that it doesn't resume the + * callbacks hence set the RQF_PM flag so that it doesn't resume the * already suspended childs. */ ret = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, - START_STOP_TIMEOUT, 0, NULL, REQ_PM); + START_STOP_TIMEOUT, 0, NULL, 0, RQF_PM); if (ret) { sdev_printk(KERN_WARNING, sdp, "START_STOP failed for power mode: %d, result %x\n", diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6df722de2e22..ec69a8fe3b29 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -167,26 +167,6 @@ enum rq_flag_bits { __REQ_PREFLUSH, /* request for cache flush */ __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_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 and also - for requests for which the SCSI "quiesce" - state must be ignored. */ - __REQ_ALLOCED, /* request came from our alloc pool */ - __REQ_COPY_USER, /* contains copies of user pages */ - __REQ_FLUSH_SEQ, /* request for flush sequence */ - __REQ_IO_STAT, /* account I/O stat */ - __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_PM, /* runtime pm request */ - __REQ_HASHED, /* on IO scheduler merge hash */ - __REQ_MQ_INFLIGHT, /* track inflight for MQ */ __REQ_NR_BITS, /* stops here */ }; @@ -208,29 +188,12 @@ enum rq_flag_bits { /* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_PREFLUSH | REQ_FUA | REQ_FLUSH_SEQ) + (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) -#define REQ_SORTED (1ULL << __REQ_SORTED) -#define REQ_SOFTBARRIER (1ULL << __REQ_SOFTBARRIER) #define REQ_FUA (1ULL << __REQ_FUA) #define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_STARTED (1ULL << __REQ_STARTED) -#define REQ_DONTPREP (1ULL << __REQ_DONTPREP) -#define REQ_QUEUED (1ULL << __REQ_QUEUED) -#define REQ_ELVPRIV (1ULL << __REQ_ELVPRIV) -#define REQ_FAILED (1ULL << __REQ_FAILED) -#define REQ_QUIET (1ULL << __REQ_QUIET) -#define REQ_PREEMPT (1ULL << __REQ_PREEMPT) -#define REQ_ALLOCED (1ULL << __REQ_ALLOCED) -#define REQ_COPY_USER (1ULL << __REQ_COPY_USER) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) -#define REQ_FLUSH_SEQ (1ULL << __REQ_FLUSH_SEQ) -#define REQ_IO_STAT (1ULL << __REQ_IO_STAT) -#define REQ_MIXED_MERGE (1ULL << __REQ_MIXED_MERGE) -#define REQ_PM (1ULL << __REQ_PM) -#define REQ_HASHED (1ULL << __REQ_HASHED) -#define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) enum req_op { REQ_OP_READ, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 90097dd8b8ed..b4415feac679 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -78,6 +78,50 @@ enum rq_cmd_type_bits { REQ_TYPE_DRV_PRIV, /* driver defined types from here */ }; +/* + * request flags */ +typedef __u32 __bitwise req_flags_t; + +/* elevator knows about this request */ +#define RQF_SORTED ((__force req_flags_t)(1 << 0)) +/* drive already may have started this one */ +#define RQF_STARTED ((__force req_flags_t)(1 << 1)) +/* uses tagged queueing */ +#define RQF_QUEUED ((__force req_flags_t)(1 << 2)) +/* may not be passed by ioscheduler */ +#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) +/* request for flush sequence */ +#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) +/* merge of different types, fail separately */ +#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) +/* track inflight for MQ */ +#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) +/* don't call prep for this one */ +#define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) +/* set for "ide_preempt" requests and also for requests for which the SCSI + "quiesce" state must be ignored. */ +#define RQF_PREEMPT ((__force req_flags_t)(1 << 8)) +/* contains copies of user pages */ +#define RQF_COPY_USER ((__force req_flags_t)(1 << 9)) +/* vaguely specified driver internal error. Ignored by the block layer */ +#define RQF_FAILED ((__force req_flags_t)(1 << 10)) +/* don't warn about errors */ +#define RQF_QUIET ((__force req_flags_t)(1 << 11)) +/* elevator private data attached */ +#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) +/* account I/O stat */ +#define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) +/* request came from our alloc pool */ +#define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) +/* runtime pm request */ +#define RQF_PM ((__force req_flags_t)(1 << 15)) +/* on IO scheduler merge hash */ +#define RQF_HASHED ((__force req_flags_t)(1 << 16)) + +/* flags that prevent us from merging requests: */ +#define RQF_NOMERGE_FLAGS \ + (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ) + #define BLK_MAX_CDB 16 /* @@ -99,6 +143,7 @@ struct request { int cpu; unsigned cmd_type; u64 cmd_flags; + req_flags_t rq_flags; unsigned long atomic_flags; /* the following two fields are internal, NEVER access directly */ @@ -648,7 +693,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) REQ_FAILFAST_DRIVER)) #define blk_account_rq(rq) \ - (((rq)->cmd_flags & REQ_STARTED) && \ + (((rq)->rq_flags & RQF_STARTED) && \ ((rq)->cmd_type == REQ_TYPE_FS)) #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) @@ -740,6 +785,8 @@ static inline bool rq_mergeable(struct request *rq) if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; + if (rq->rq_flags & RQF_NOMERGE_FLAGS) + return false; return true; } diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 8a9563144890..8990e580b278 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -414,14 +414,14 @@ extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, extern int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, - int retries, int *resid, u64 flags); + int retries, int *resid, u64 flags, req_flags_t rq_flags); static inline int scsi_execute_req(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, int retries, int *resid) { return scsi_execute_req_flags(sdev, cmd, data_direction, buffer, - bufflen, sshdr, timeout, retries, resid, 0); + bufflen, sshdr, timeout, retries, resid, 0, 0); } extern void sdev_disable_disk_events(struct scsi_device *sdev); extern void sdev_enable_disk_events(struct scsi_device *sdev); -- cgit v1.2.3-58-ga151 From ef295ecf090d3e86e5b742fc6ab34f1122a43773 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 28 Oct 2016 08:48:16 -0600 Subject: block: better op and flags encoding Now that we don't need the common flags to overflow outside the range of a 32-bit type we can encode them the same way for both the bio and request fields. This in addition allows us to place the operation first (and make some room for more ops while we're at it) and to stop having to shift around the operation values. In addition this allows passing around only one value in the block layer instead of two (and eventuall also in the file systems, but we can do that later) and thus clean up a lot of code. Last but not least this allows decreasing the size of the cmd_flags field in struct request to 32-bits. Various functions passing this value could also be updated, but I'd like to avoid the churn for now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- Documentation/block/biodoc.txt | 4 +- block/blk-core.c | 60 ++++++++++-------------------- block/blk-flush.c | 2 +- block/blk-lib.c | 2 +- block/blk-map.c | 2 + block/blk-mq.c | 28 ++++++-------- block/cfq-iosched.c | 66 ++++++++++++++++----------------- block/elevator.c | 4 +- drivers/md/dm-crypt.c | 2 +- drivers/scsi/sd.c | 3 +- fs/btrfs/inode.c | 5 +-- fs/buffer.c | 2 +- fs/f2fs/f2fs.h | 2 +- fs/gfs2/lops.c | 2 +- include/linux/blk-cgroup.h | 11 +++--- include/linux/blk_types.h | 83 +++++++++++++++++++----------------------- include/linux/blkdev.h | 26 +------------ include/linux/blktrace_api.h | 2 +- include/linux/dm-io.h | 2 +- include/linux/elevator.h | 4 +- include/trace/events/bcache.h | 12 ++---- include/trace/events/block.h | 31 ++++++---------- kernel/trace/blktrace.c | 14 +++---- 23 files changed, 148 insertions(+), 221 deletions(-) (limited to 'Documentation') diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 6acea160298c..01ddeaf64b0f 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -553,8 +553,8 @@ struct request { struct request_list *rl; } -See the rq_flag_bits definitions for an explanation of the various flags -available. Some bits are used by the block layer or i/o scheduler. +See the req_ops and req_flag_bits definitions for an explanation of the various +flags available. Some bits are used by the block layer or i/o scheduler. The behaviour of the various sector counts are almost the same as before, except that since we have multi-segment bios, current_nr_sectors refers diff --git a/block/blk-core.c b/block/blk-core.c index fd416651a676..0bfaa54d3e9f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1056,8 +1056,7 @@ static struct io_context *rq_ioc(struct bio *bio) /** * __get_request - get a free request * @rl: request list to allocate from - * @op: REQ_OP_READ/REQ_OP_WRITE - * @op_flags: rq_flag_bits + * @op: operation and flags * @bio: bio to allocate request for (can be %NULL) * @gfp_mask: allocation mask * @@ -1068,23 +1067,22 @@ static struct io_context *rq_ioc(struct bio *bio) * Returns ERR_PTR on failure, with @q->queue_lock held. * Returns request pointer on success, with @q->queue_lock *not held*. */ -static struct request *__get_request(struct request_list *rl, int op, - int op_flags, struct bio *bio, - gfp_t gfp_mask) +static struct request *__get_request(struct request_list *rl, unsigned int op, + struct bio *bio, gfp_t gfp_mask) { struct request_queue *q = rl->q; struct request *rq; struct elevator_type *et = q->elevator->type; struct io_context *ioc = rq_ioc(bio); struct io_cq *icq = NULL; - const bool is_sync = rw_is_sync(op, op_flags) != 0; + const bool is_sync = op_is_sync(op); int may_queue; req_flags_t rq_flags = RQF_ALLOCED; if (unlikely(blk_queue_dying(q))) return ERR_PTR(-ENODEV); - may_queue = elv_may_queue(q, op, op_flags); + may_queue = elv_may_queue(q, op); if (may_queue == ELV_MQUEUE_NO) goto rq_starved; @@ -1154,7 +1152,7 @@ static struct request *__get_request(struct request_list *rl, int op, blk_rq_init(q, rq); blk_rq_set_rl(rq, rl); - req_set_op_attrs(rq, op, op_flags); + rq->cmd_flags = op; rq->rq_flags = rq_flags; /* init elvpriv */ @@ -1232,8 +1230,7 @@ rq_starved: /** * get_request - get a free request * @q: request_queue to allocate request from - * @op: REQ_OP_READ/REQ_OP_WRITE - * @op_flags: rq_flag_bits + * @op: operation and flags * @bio: bio to allocate request for (can be %NULL) * @gfp_mask: allocation mask * @@ -1244,18 +1241,17 @@ rq_starved: * Returns ERR_PTR on failure, with @q->queue_lock held. * Returns request pointer on success, with @q->queue_lock *not held*. */ -static struct request *get_request(struct request_queue *q, int op, - int op_flags, struct bio *bio, - gfp_t gfp_mask) +static struct request *get_request(struct request_queue *q, unsigned int op, + struct bio *bio, gfp_t gfp_mask) { - const bool is_sync = rw_is_sync(op, op_flags) != 0; + const bool is_sync = op_is_sync(op); DEFINE_WAIT(wait); struct request_list *rl; struct request *rq; rl = blk_get_rl(q, bio); /* transferred to @rq on success */ retry: - rq = __get_request(rl, op, op_flags, bio, gfp_mask); + rq = __get_request(rl, op, bio, gfp_mask); if (!IS_ERR(rq)) return rq; @@ -1297,7 +1293,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw, create_io_context(gfp_mask, q->node); spin_lock_irq(q->queue_lock); - rq = get_request(q, rw, 0, NULL, gfp_mask); + rq = get_request(q, rw, NULL, gfp_mask); if (IS_ERR(rq)) { spin_unlock_irq(q->queue_lock); return rq; @@ -1446,7 +1442,7 @@ void __blk_put_request(struct request_queue *q, struct request *req) */ if (rq_flags & RQF_ALLOCED) { struct request_list *rl = blk_rq_rl(req); - bool sync = rw_is_sync(req_op(req), req->cmd_flags); + bool sync = op_is_sync(req->cmd_flags); BUG_ON(!list_empty(&req->queuelist)); BUG_ON(ELV_ON_HASH(req)); @@ -1652,8 +1648,6 @@ out: void init_request_from_bio(struct request *req, struct bio *bio) { req->cmd_type = REQ_TYPE_FS; - - req->cmd_flags |= bio->bi_opf & REQ_COMMON_MASK; if (bio->bi_opf & REQ_RAHEAD) req->cmd_flags |= REQ_FAILFAST_MASK; @@ -1665,9 +1659,8 @@ void init_request_from_bio(struct request *req, struct bio *bio) static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) { - const bool sync = !!(bio->bi_opf & REQ_SYNC); struct blk_plug *plug; - int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT; + int el_ret, where = ELEVATOR_INSERT_SORT; struct request *req; unsigned int request_count = 0; @@ -1722,24 +1715,11 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) } get_rq: - /* - * This sync check and mask will be re-done in init_request_from_bio(), - * but we need to set it earlier to expose the sync flag to the - * rq allocator and io schedulers. - */ - if (sync) - rw_flags |= REQ_SYNC; - - /* - * Add in META/PRIO flags, if set, before we get to the IO scheduler - */ - rw_flags |= (bio->bi_opf & (REQ_META | REQ_PRIO)); - /* * Grab a free request. This is might sleep but can not fail. * Returns with the queue unlocked. */ - req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO); + req = get_request(q, bio->bi_opf, bio, GFP_NOIO); if (IS_ERR(req)) { bio->bi_error = PTR_ERR(req); bio_endio(bio); @@ -2946,8 +2926,6 @@ EXPORT_SYMBOL_GPL(__blk_end_request_err); void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio) { - req_set_op(rq, bio_op(bio)); - if (bio_has_data(bio)) rq->nr_phys_segments = bio_phys_segments(q, bio); @@ -3031,8 +3009,7 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); static void __blk_rq_prep_clone(struct request *dst, struct request *src) { dst->cpu = src->cpu; - req_set_op_attrs(dst, req_op(src), - (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE); + dst->cmd_flags = src->cmd_flags | REQ_NOMERGE; dst->cmd_type = src->cmd_type; dst->__sector = blk_rq_pos(src); dst->__data_len = blk_rq_bytes(src); @@ -3537,8 +3514,11 @@ EXPORT_SYMBOL(blk_set_runtime_active); int __init blk_dev_init(void) { - BUILD_BUG_ON(__REQ_NR_BITS > 8 * + BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); + BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * FIELD_SIZEOF(struct request, cmd_flags)); + BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * + FIELD_SIZEOF(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", diff --git a/block/blk-flush.c b/block/blk-flush.c index 3990b9cfbda5..95f1d4d357df 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -330,7 +330,7 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq) } flush_rq->cmd_type = REQ_TYPE_FS; - req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH); + flush_rq->cmd_flags = REQ_OP_FLUSH | WRITE_FLUSH; flush_rq->rq_flags |= RQF_FLUSH_SEQ; flush_rq->rq_disk = first_rq->rq_disk; flush_rq->end_io = flush_end_io; diff --git a/block/blk-lib.c b/block/blk-lib.c index 46fe9248410d..18abda862915 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -29,7 +29,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct request_queue *q = bdev_get_queue(bdev); struct bio *bio = *biop; unsigned int granularity; - enum req_op op; + unsigned int op; int alignment; sector_t bs_mask; diff --git a/block/blk-map.c b/block/blk-map.c index 2c5ae5fef473..0173a72a8aa9 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -16,6 +16,8 @@ int blk_rq_append_bio(struct request *rq, struct bio *bio) { if (!rq->bio) { + rq->cmd_flags &= REQ_OP_MASK; + rq->cmd_flags |= (bio->bi_opf & REQ_OP_MASK); blk_rq_bio_prep(rq->q, rq, bio); } else { if (!ll_back_merge_fn(rq->q, rq, bio)) diff --git a/block/blk-mq.c b/block/blk-mq.c index b49c6658eb05..2da1a0ee3318 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -139,14 +139,13 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) EXPORT_SYMBOL(blk_mq_can_queue); static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, - struct request *rq, int op, - unsigned int op_flags) + struct request *rq, unsigned int op) { INIT_LIST_HEAD(&rq->queuelist); /* csd/requeue_work/fifo_time is initialized before use */ rq->q = q; rq->mq_ctx = ctx; - req_set_op_attrs(rq, op, op_flags); + rq->cmd_flags = op; if (blk_queue_io_stat(q)) rq->rq_flags |= RQF_IO_STAT; /* do not touch atomic flags, it needs atomic ops against the timer */ @@ -183,11 +182,11 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, rq->end_io_data = NULL; rq->next_rq = NULL; - ctx->rq_dispatched[rw_is_sync(op, op_flags)]++; + ctx->rq_dispatched[op_is_sync(op)]++; } static struct request * -__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags) +__blk_mq_alloc_request(struct blk_mq_alloc_data *data, unsigned int op) { struct request *rq; unsigned int tag; @@ -202,7 +201,7 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags) } rq->tag = tag; - blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags); + blk_mq_rq_ctx_init(data->q, data->ctx, rq, op); return rq; } @@ -225,7 +224,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, ctx = blk_mq_get_ctx(q); hctx = blk_mq_map_queue(q, ctx->cpu); blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); - rq = __blk_mq_alloc_request(&alloc_data, rw, 0); + rq = __blk_mq_alloc_request(&alloc_data, rw); blk_mq_put_ctx(ctx); if (!rq) { @@ -277,7 +276,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw, ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask)); blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); - rq = __blk_mq_alloc_request(&alloc_data, rw, 0); + rq = __blk_mq_alloc_request(&alloc_data, rw); if (!rq) { ret = -EWOULDBLOCK; goto out_queue_exit; @@ -1196,19 +1195,14 @@ static struct request *blk_mq_map_request(struct request_queue *q, struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct request *rq; - int op = bio_data_dir(bio); - int op_flags = 0; blk_queue_enter_live(q); ctx = blk_mq_get_ctx(q); hctx = blk_mq_map_queue(q, ctx->cpu); - if (rw_is_sync(bio_op(bio), bio->bi_opf)) - op_flags |= REQ_SYNC; - - trace_block_getrq(q, bio, op); + trace_block_getrq(q, bio, bio->bi_opf); blk_mq_set_alloc_data(data, q, 0, ctx, hctx); - rq = __blk_mq_alloc_request(data, op, op_flags); + rq = __blk_mq_alloc_request(data, bio->bi_opf); data->hctx->queued++; return rq; @@ -1256,7 +1250,7 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie) */ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { - const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf); + const int is_sync = op_is_sync(bio->bi_opf); const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); struct blk_mq_alloc_data data; struct request *rq; @@ -1350,7 +1344,7 @@ done: */ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) { - const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf); + const int is_sync = op_is_sync(bio->bi_opf); const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); struct blk_plug *plug; unsigned int request_count = 0; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 5e24d880306c..c96186adaa66 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -667,10 +667,10 @@ static inline void cfqg_put(struct cfq_group *cfqg) } while (0) static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg, - struct cfq_group *curr_cfqg, int op, - int op_flags) + struct cfq_group *curr_cfqg, + unsigned int op) { - blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, 1); + blkg_rwstat_add(&cfqg->stats.queued, op, 1); cfqg_stats_end_empty_time(&cfqg->stats); cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg); } @@ -684,30 +684,29 @@ static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg, #endif } -static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op, - int op_flags) +static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, + unsigned int op) { - blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, -1); + blkg_rwstat_add(&cfqg->stats.queued, op, -1); } -static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op, - int op_flags) +static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, + unsigned int op) { - blkg_rwstat_add(&cfqg->stats.merged, op, op_flags, 1); + blkg_rwstat_add(&cfqg->stats.merged, op, 1); } static inline void cfqg_stats_update_completion(struct cfq_group *cfqg, - uint64_t start_time, uint64_t io_start_time, int op, - int op_flags) + uint64_t start_time, uint64_t io_start_time, + unsigned int op) { struct cfqg_stats *stats = &cfqg->stats; unsigned long long now = sched_clock(); if (time_after64(now, io_start_time)) - blkg_rwstat_add(&stats->service_time, op, op_flags, - now - io_start_time); + blkg_rwstat_add(&stats->service_time, op, now - io_start_time); if (time_after64(io_start_time, start_time)) - blkg_rwstat_add(&stats->wait_time, op, op_flags, + blkg_rwstat_add(&stats->wait_time, op, io_start_time - start_time); } @@ -786,16 +785,16 @@ static inline void cfqg_put(struct cfq_group *cfqg) { } #define cfq_log_cfqg(cfqd, cfqg, fmt, args...) do {} while (0) static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg, - struct cfq_group *curr_cfqg, int op, int op_flags) { } + struct cfq_group *curr_cfqg, unsigned int op) { } static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg, uint64_t time, unsigned long unaccounted_time) { } -static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op, - int op_flags) { } -static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op, - int op_flags) { } +static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, + unsigned int op) { } +static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, + unsigned int op) { } static inline void cfqg_stats_update_completion(struct cfq_group *cfqg, - uint64_t start_time, uint64_t io_start_time, int op, - int op_flags) { } + uint64_t start_time, uint64_t io_start_time, + unsigned int op) { } #endif /* CONFIG_CFQ_GROUP_IOSCHED */ @@ -2474,10 +2473,10 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq) { elv_rb_del(&cfqq->sort_list, rq); cfqq->queued[rq_is_sync(rq)]--; - cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags); + cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags); cfq_add_rq_rb(rq); cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group, - req_op(rq), rq->cmd_flags); + rq->cmd_flags); } static struct request * @@ -2530,7 +2529,7 @@ static void cfq_remove_request(struct request *rq) cfq_del_rq_rb(rq); cfqq->cfqd->rq_queued--; - cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags); + cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags); if (rq->cmd_flags & REQ_PRIO) { WARN_ON(!cfqq->prio_pending); cfqq->prio_pending--; @@ -2565,7 +2564,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req, static void cfq_bio_merged(struct request_queue *q, struct request *req, struct bio *bio) { - cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_opf); + cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_opf); } static void @@ -2588,7 +2587,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, if (cfqq->next_rq == next) cfqq->next_rq = rq; cfq_remove_request(next); - cfqg_stats_update_io_merged(RQ_CFQG(rq), req_op(next), next->cmd_flags); + cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags); cfqq = RQ_CFQQ(next); /* @@ -4142,7 +4141,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) rq->fifo_time = ktime_get_ns() + cfqd->cfq_fifo_expire[rq_is_sync(rq)]; list_add_tail(&rq->queuelist, &cfqq->fifo); cfq_add_rq_rb(rq); - cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq), + cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, rq->cmd_flags); cfq_rq_enqueued(cfqd, cfqq, rq); } @@ -4240,8 +4239,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfqq->dispatched--; (RQ_CFQG(rq))->dispatched--; cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq), - rq_io_start_time_ns(rq), req_op(rq), - rq->cmd_flags); + rq_io_start_time_ns(rq), rq->cmd_flags); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; @@ -4319,14 +4317,14 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfq_schedule_dispatch(cfqd); } -static void cfqq_boost_on_prio(struct cfq_queue *cfqq, int op_flags) +static void cfqq_boost_on_prio(struct cfq_queue *cfqq, unsigned int op) { /* * If REQ_PRIO is set, boost class and prio level, if it's below * BE/NORM. If prio is not set, restore the potentially boosted * class/prio level. */ - if (!(op_flags & REQ_PRIO)) { + if (!(op & REQ_PRIO)) { cfqq->ioprio_class = cfqq->org_ioprio_class; cfqq->ioprio = cfqq->org_ioprio; } else { @@ -4347,7 +4345,7 @@ static inline int __cfq_may_queue(struct cfq_queue *cfqq) return ELV_MQUEUE_MAY; } -static int cfq_may_queue(struct request_queue *q, int op, int op_flags) +static int cfq_may_queue(struct request_queue *q, unsigned int op) { struct cfq_data *cfqd = q->elevator->elevator_data; struct task_struct *tsk = current; @@ -4364,10 +4362,10 @@ static int cfq_may_queue(struct request_queue *q, int op, int op_flags) if (!cic) return ELV_MQUEUE_MAY; - cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags)); + cfqq = cic_to_cfqq(cic, op_is_sync(op)); if (cfqq) { cfq_init_prio_data(cfqq, cic); - cfqq_boost_on_prio(cfqq, op_flags); + cfqq_boost_on_prio(cfqq, op); return __cfq_may_queue(cfqq); } diff --git a/block/elevator.c b/block/elevator.c index ac80f89a0842..a18a5db274e4 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -714,12 +714,12 @@ void elv_put_request(struct request_queue *q, struct request *rq) e->type->ops.elevator_put_req_fn(rq); } -int elv_may_queue(struct request_queue *q, int op, int op_flags) +int elv_may_queue(struct request_queue *q, unsigned int op) { struct elevator_queue *e = q->elevator; if (e->type->ops.elevator_may_queue_fn) - return e->type->ops.elevator_may_queue_fn(q, op, op_flags); + return e->type->ops.elevator_may_queue_fn(q, op); return ELV_MQUEUE_MAY; } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index a2768835d394..68a9eb4f3f36 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1135,7 +1135,7 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone) clone->bi_private = io; clone->bi_end_io = crypt_endio; clone->bi_bdev = cc->dev->bdev; - bio_set_op_attrs(clone, bio_op(io->base_bio), bio_flags(io->base_bio)); + clone->bi_opf = io->base_bio->bi_opf; } static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index cef1f78031d4..65738b0aad36 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1031,8 +1031,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt) } else if (rq_data_dir(rq) == READ) { SCpnt->cmnd[0] = READ_6; } else { - scmd_printk(KERN_ERR, SCpnt, "Unknown command %llu,%llx\n", - req_op(rq), (unsigned long long) rq->cmd_flags); + scmd_printk(KERN_ERR, SCpnt, "Unknown command %d\n", req_op(rq)); goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2b790bda7998..9a377079af26 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8427,7 +8427,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip, if (!bio) return -ENOMEM; - bio_set_op_attrs(bio, bio_op(orig_bio), bio_flags(orig_bio)); + bio->bi_opf = orig_bio->bi_opf; bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; @@ -8465,8 +8465,7 @@ next_block: start_sector, GFP_NOFS); if (!bio) goto out_err; - bio_set_op_attrs(bio, bio_op(orig_bio), - bio_flags(orig_bio)); + bio->bi_opf = orig_bio->bi_opf; bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; diff --git a/fs/buffer.c b/fs/buffer.c index b205a629001d..a29335867e30 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3118,7 +3118,7 @@ EXPORT_SYMBOL(submit_bh); /** * ll_rw_block: low-level access to block devices (DEPRECATED) * @op: whether to %READ or %WRITE - * @op_flags: rq_flag_bits + * @op_flags: req_flag_bits * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9e8de18a168a..2cf4f7f09e32 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -688,7 +688,7 @@ struct f2fs_io_info { struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ int op; /* contains REQ_OP_ */ - int op_flags; /* rq_flag_bits */ + int op_flags; /* req_flag_bits */ block_t new_blkaddr; /* new block address to be written */ block_t old_blkaddr; /* old block address before Cow */ struct page *page; /* page to be written */ diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 49d5a1b61b06..b1f9144b42c7 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -231,7 +231,7 @@ static void gfs2_end_log_write(struct bio *bio) * gfs2_log_flush_bio - Submit any pending log bio * @sdp: The superblock * @op: REQ_OP - * @op_flags: rq_flag_bits + * @op_flags: req_flag_bits * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 3bf5d33800ab..ddaf28d0988f 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -581,15 +581,14 @@ static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) /** * blkg_rwstat_add - add a value to a blkg_rwstat * @rwstat: target blkg_rwstat - * @op: REQ_OP - * @op_flags: rq_flag_bits + * @op: REQ_OP and flags * @val: value to add * * Add @val to @rwstat. The counters are chosen according to @rw. The * caller is responsible for synchronizing calls to this function. */ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, - int op, int op_flags, uint64_t val) + unsigned int op, uint64_t val) { struct percpu_counter *cnt; @@ -600,7 +599,7 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); - if (op_flags & REQ_SYNC) + if (op & REQ_SYNC) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; @@ -705,9 +704,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_opf, + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_opf, 1); + blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } rcu_read_unlock(); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ec69a8fe3b29..dca972d67548 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -88,24 +88,6 @@ struct bio { struct bio_vec bi_inline_vecs[0]; }; -#define BIO_OP_SHIFT (8 * FIELD_SIZEOF(struct bio, bi_opf) - REQ_OP_BITS) -#define bio_flags(bio) ((bio)->bi_opf & ((1 << BIO_OP_SHIFT) - 1)) -#define bio_op(bio) ((bio)->bi_opf >> BIO_OP_SHIFT) - -#define bio_set_op_attrs(bio, op, op_flags) do { \ - if (__builtin_constant_p(op)) \ - BUILD_BUG_ON((op) + 0U >= (1U << REQ_OP_BITS)); \ - else \ - WARN_ON_ONCE((op) + 0U >= (1U << REQ_OP_BITS)); \ - if (__builtin_constant_p(op_flags)) \ - BUILD_BUG_ON((op_flags) + 0U >= (1U << BIO_OP_SHIFT)); \ - else \ - WARN_ON_ONCE((op_flags) + 0U >= (1U << BIO_OP_SHIFT)); \ - (bio)->bi_opf = bio_flags(bio); \ - (bio)->bi_opf |= (((op) + 0U) << BIO_OP_SHIFT); \ - (bio)->bi_opf |= (op_flags); \ -} while (0) - #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) /* @@ -147,26 +129,40 @@ struct bio { #endif /* CONFIG_BLOCK */ /* - * Request flags. For use in the cmd_flags field of struct request, and in - * bi_opf of struct bio. Note that some flags are only valid in either one. + * Operations and flags common to the bio and request structures. + * We use 8 bits for encoding the operation, and the remaining 24 for flags. */ -enum rq_flag_bits { - /* common flags */ - __REQ_FAILFAST_DEV, /* no driver retries of device errors */ +#define REQ_OP_BITS 8 +#define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) +#define REQ_FLAG_BITS 24 + +enum req_opf { + REQ_OP_READ, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ + REQ_OP_ZONE_REPORT, /* Get zone information */ + REQ_OP_ZONE_RESET, /* Reset a zone write pointer */ + + REQ_OP_LAST, +}; + +enum req_flag_bits { + __REQ_FAILFAST_DEV = /* no driver retries of device errors */ + REQ_OP_BITS, __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ - __REQ_NOMERGE, /* don't touch this for merging */ __REQ_NOIDLE, /* don't anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ - __REQ_NR_BITS, /* stops here */ }; @@ -176,37 +172,32 @@ enum rq_flag_bits { #define REQ_SYNC (1ULL << __REQ_SYNC) #define REQ_META (1ULL << __REQ_META) #define REQ_PRIO (1ULL << __REQ_PRIO) +#define REQ_NOMERGE (1ULL << __REQ_NOMERGE) #define REQ_NOIDLE (1ULL << __REQ_NOIDLE) #define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) +#define REQ_FUA (1ULL << __REQ_FUA) +#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) +#define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) -#define REQ_COMMON_MASK \ - (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ - REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE | REQ_RAHEAD) -#define REQ_CLONE_MASK REQ_COMMON_MASK -/* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA) -#define REQ_RAHEAD (1ULL << __REQ_RAHEAD) -#define REQ_FUA (1ULL << __REQ_FUA) -#define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) +#define bio_op(bio) \ + ((bio)->bi_opf & REQ_OP_MASK) +#define req_op(req) \ + ((req)->cmd_flags & REQ_OP_MASK) -enum req_op { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ - REQ_OP_ZONE_REPORT, /* Get zone information */ - REQ_OP_ZONE_RESET, /* Reset a zone write pointer */ -}; +/* obsolete, don't use in new code */ +#define bio_set_op_attrs(bio, op, op_flags) \ + ((bio)->bi_opf |= (op | op_flags)) -#define REQ_OP_BITS 3 +static inline bool op_is_sync(unsigned int op) +{ + return (op & REQ_OP_MASK) == REQ_OP_READ || (op & REQ_SYNC); +} typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b4415feac679..8396da2bb698 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -142,7 +142,7 @@ struct request { int cpu; unsigned cmd_type; - u64 cmd_flags; + unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; unsigned long atomic_flags; @@ -244,20 +244,6 @@ struct request { struct request *next_rq; }; -#define REQ_OP_SHIFT (8 * sizeof(u64) - REQ_OP_BITS) -#define req_op(req) ((req)->cmd_flags >> REQ_OP_SHIFT) - -#define req_set_op(req, op) do { \ - WARN_ON(op >= (1 << REQ_OP_BITS)); \ - (req)->cmd_flags &= ((1ULL << REQ_OP_SHIFT) - 1); \ - (req)->cmd_flags |= ((u64) (op) << REQ_OP_SHIFT); \ -} while (0) - -#define req_set_op_attrs(req, op, flags) do { \ - req_set_op(req, op); \ - (req)->cmd_flags |= flags; \ -} while (0) - static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; @@ -741,17 +727,9 @@ static inline unsigned int blk_queue_zone_size(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } -/* - * We regard a request as sync, if either a read or a sync write - */ -static inline bool rw_is_sync(int op, unsigned int rw_flags) -{ - return op == REQ_OP_READ || (rw_flags & REQ_SYNC); -} - static inline bool rq_is_sync(struct request *rq) { - return rw_is_sync(req_op(rq), rq->cmd_flags); + return op_is_sync(rq->cmd_flags); } static inline bool blk_rl_full(struct request_list *rl, bool sync) diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index cceb72f9e29f..e417f080219a 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -118,7 +118,7 @@ static inline int blk_cmd_buf_len(struct request *rq) } extern void blk_dump_cmd(char *buf, struct request *rq); -extern void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes); +extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); #endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */ diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index b91b023deffb..a52c6580cc9a 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -58,7 +58,7 @@ struct dm_io_notify { struct dm_io_client; struct dm_io_request { int bi_op; /* REQ_OP */ - int bi_op_flags; /* rq_flag_bits */ + int bi_op_flags; /* req_flag_bits */ struct dm_io_memory mem; /* Memory to use for io */ struct dm_io_notify notify; /* Synchronous if notify.fn is NULL */ struct dm_io_client *client; /* Client memory handler */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index e7f358d2e5fc..f219c9aed360 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -30,7 +30,7 @@ typedef int (elevator_dispatch_fn) (struct request_queue *, int); typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *); typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *); -typedef int (elevator_may_queue_fn) (struct request_queue *, int, int); +typedef int (elevator_may_queue_fn) (struct request_queue *, unsigned int); typedef void (elevator_init_icq_fn) (struct io_cq *); typedef void (elevator_exit_icq_fn) (struct io_cq *); @@ -139,7 +139,7 @@ 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); extern void elv_unregister_queue(struct request_queue *q); -extern int elv_may_queue(struct request_queue *, int, int); +extern int elv_may_queue(struct request_queue *, unsigned int); extern void elv_completed_request(struct request_queue *, struct request *); extern int elv_set_request(struct request_queue *q, struct request *rq, struct bio *bio, gfp_t gfp_mask); diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index d336b890e31f..df3e9ae5ad8d 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -27,8 +27,7 @@ DECLARE_EVENT_CLASS(bcache_request, __entry->sector = bio->bi_iter.bi_sector; __entry->orig_sector = bio->bi_iter.bi_sector - 16; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u (from %d,%d @ %llu)", @@ -102,8 +101,7 @@ DECLARE_EVENT_CLASS(bcache_bio, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u", @@ -138,8 +136,7 @@ TRACE_EVENT(bcache_read, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); __entry->cache_hit = hit; __entry->bypass = bypass; ), @@ -170,8 +167,7 @@ TRACE_EVENT(bcache_write, __entry->inode = inode; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); __entry->writeback = writeback; __entry->bypass = bypass; ), diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 8f3a163b8166..3e02e3a25413 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -84,8 +84,7 @@ DECLARE_EVENT_CLASS(block_rq_with_error, 0 : blk_rq_sectors(rq); __entry->errors = rq->errors; - blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, - blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); blk_dump_cmd(__get_str(cmd), rq); ), @@ -163,7 +162,7 @@ TRACE_EVENT(block_rq_complete, __entry->nr_sector = nr_bytes >> 9; __entry->errors = rq->errors; - blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, nr_bytes); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes); blk_dump_cmd(__get_str(cmd), rq); ), @@ -199,8 +198,7 @@ DECLARE_EVENT_CLASS(block_rq, __entry->bytes = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? blk_rq_bytes(rq) : 0; - blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, - blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); blk_dump_cmd(__get_str(cmd), rq); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -274,8 +272,7 @@ TRACE_EVENT(block_bio_bounce, bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -313,8 +310,7 @@ TRACE_EVENT(block_bio_complete, __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); __entry->error = error; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u [%d]", @@ -341,8 +337,7 @@ DECLARE_EVENT_CLASS(block_bio_merge, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -409,8 +404,7 @@ TRACE_EVENT(block_bio_queue, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -438,7 +432,7 @@ DECLARE_EVENT_CLASS(block_get_rq, __entry->dev = bio ? bio->bi_bdev->bd_dev : 0; __entry->sector = bio ? bio->bi_iter.bi_sector : 0; __entry->nr_sector = bio ? bio_sectors(bio) : 0; - blk_fill_rwbs(__entry->rwbs, bio ? bio_op(bio) : 0, + blk_fill_rwbs(__entry->rwbs, bio ? bio->bi_opf : 0, __entry->nr_sector); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -573,8 +567,7 @@ TRACE_EVENT(block_split, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->new_sector = new_sector; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -617,8 +610,7 @@ TRACE_EVENT(block_bio_remap, __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, - bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", @@ -664,8 +656,7 @@ TRACE_EVENT(block_rq_remap, __entry->old_dev = dev; __entry->old_sector = from; __entry->nr_bios = blk_rq_count_bios(rq); - blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, - blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u", diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index dbafc5df03f3..95cecbf67f5c 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1777,14 +1777,14 @@ void blk_dump_cmd(char *buf, struct request *rq) } } -void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes) +void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes) { int i = 0; - if (rw & REQ_PREFLUSH) + if (op & REQ_PREFLUSH) rwbs[i++] = 'F'; - switch (op) { + switch (op & REQ_OP_MASK) { case REQ_OP_WRITE: case REQ_OP_WRITE_SAME: rwbs[i++] = 'W'; @@ -1806,13 +1806,13 @@ void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes) rwbs[i++] = 'N'; } - if (rw & REQ_FUA) + if (op & REQ_FUA) rwbs[i++] = 'F'; - if (rw & REQ_RAHEAD) + if (op & REQ_RAHEAD) rwbs[i++] = 'A'; - if (rw & REQ_SYNC) + if (op & REQ_SYNC) rwbs[i++] = 'S'; - if (rw & REQ_META) + if (op & REQ_META) rwbs[i++] = 'M'; rwbs[i] = '\0'; -- cgit v1.2.3-58-ga151 From a2b809672ee6fcb4d5756ea815725b3dbaea654e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 1 Nov 2016 07:40:09 -0600 Subject: block: replace REQ_NOIDLE with REQ_IDLE Noidle should be the default for writes as seen by all the compounds definitions in fs.h using it. In fact only direct I/O really should be using NODILE, so turn the whole flag around to get the defaults right, which will make our life much easier especially onces the WRITE_* defines go away. This assumes all the existing "raw" users of REQ_SYNC for writes want noidle behavior, which seems to be spot on from a quick audit. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- Documentation/block/cfq-iosched.txt | 32 ++++++++++++++++---------------- block/cfq-iosched.c | 11 ++++++++--- drivers/block/drbd/drbd_actlog.c | 2 +- include/linux/blk_types.h | 4 ++-- include/linux/fs.h | 10 +++++----- include/trace/events/f2fs.h | 2 +- 6 files changed, 33 insertions(+), 28 deletions(-) (limited to 'Documentation') diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt index 1e4f835a659d..895bd3813115 100644 --- a/Documentation/block/cfq-iosched.txt +++ b/Documentation/block/cfq-iosched.txt @@ -240,11 +240,11 @@ All cfq queues doing synchronous sequential IO go on to sync-idle tree. On this tree we idle on each queue individually. All synchronous non-sequential queues go on sync-noidle tree. Also any -request which are marked with REQ_NOIDLE go on this service tree. On this -tree we do not idle on individual queues instead idle on the whole group -of queues or the tree. So if there are 4 queues waiting for IO to dispatch -we will idle only once last queue has dispatched the IO and there is -no more IO on this service tree. +synchronous write request which is not marked with REQ_IDLE goes on this +service tree. On this tree we do not idle on individual queues instead idle +on the whole group of queues or the tree. So if there are 4 queues waiting +for IO to dispatch we will idle only once last queue has dispatched the IO +and there is no more IO on this service tree. All async writes go on async service tree. There is no idling on async queues. @@ -257,17 +257,17 @@ tree idling provides isolation with buffered write queues on async tree. FAQ === -Q1. Why to idle at all on queues marked with REQ_NOIDLE. +Q1. Why to idle at all on queues not marked with REQ_IDLE. -A1. We only do tree idle (all queues on sync-noidle tree) on queues marked - with REQ_NOIDLE. This helps in providing isolation with all the sync-idle +A1. We only do tree idle (all queues on sync-noidle tree) on queues not marked + with REQ_IDLE. This helps in providing isolation with all the sync-idle queues. Otherwise in presence of many sequential readers, other synchronous IO might not get fair share of disk. For example, if there are 10 sequential readers doing IO and they get - 100ms each. If a REQ_NOIDLE request comes in, it will be scheduled - roughly after 1 second. If after completion of REQ_NOIDLE request we - do not idle, and after a couple of milli seconds a another REQ_NOIDLE + 100ms each. If a !REQ_IDLE request comes in, it will be scheduled + roughly after 1 second. If after completion of !REQ_IDLE request we + do not idle, and after a couple of milli seconds a another !REQ_IDLE request comes in, again it will be scheduled after 1second. Repeat it and notice how a workload can lose its disk share and suffer due to multiple sequential readers. @@ -276,16 +276,16 @@ A1. We only do tree idle (all queues on sync-noidle tree) on queues marked context of fsync, and later some journaling data is written. Journaling data comes in only after fsync has finished its IO (atleast for ext4 that seemed to be the case). Now if one decides not to idle on fsync - thread due to REQ_NOIDLE, then next journaling write will not get + thread due to !REQ_IDLE, then next journaling write will not get scheduled for another second. A process doing small fsync, will suffer badly in presence of multiple sequential readers. - Hence doing tree idling on threads using REQ_NOIDLE flag on requests + Hence doing tree idling on threads using !REQ_IDLE flag on requests provides isolation from multiple sequential readers and at the same time we do not idle on individual threads. -Q2. When to specify REQ_NOIDLE -A2. I would think whenever one is doing synchronous write and not expecting +Q2. When to specify REQ_IDLE +A2. I would think whenever one is doing synchronous write and expecting more writes to be dispatched from same context soon, should be able - to specify REQ_NOIDLE on writes and that probably should work well for + to specify REQ_IDLE on writes and that probably should work well for most of the cases. diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index f28db97c3fe0..dcbed8c9c82c 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3914,6 +3914,12 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqq->seek_history |= (sdist > CFQQ_SEEK_THR); } +static inline bool req_noidle(struct request *req) +{ + return req_op(req) == REQ_OP_WRITE && + (req->cmd_flags & (REQ_SYNC | REQ_IDLE)) == REQ_SYNC; +} + /* * Disable idle window if the process thinks too long or seeks so much that * it doesn't matter @@ -3935,7 +3941,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (cfqq->queued[0] + cfqq->queued[1] >= 4) cfq_mark_cfqq_deep(cfqq); - if (cfqq->next_rq && (cfqq->next_rq->cmd_flags & REQ_NOIDLE)) + if (cfqq->next_rq && req_noidle(cfqq->next_rq)) enable_idle = 0; else if (!atomic_read(&cic->icq.ioc->active_ref) || !cfqd->cfq_slice_idle || @@ -4220,8 +4226,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) const int sync = rq_is_sync(rq); u64 now = ktime_get_ns(); - cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", - !!(rq->cmd_flags & REQ_NOIDLE)); + cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", req_noidle(rq)); cfq_update_hw_tag(cfqd); diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index 2d3d50ab74bf..8d7bcfa49c12 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -148,7 +148,7 @@ static int _drbd_md_sync_page_io(struct drbd_device *device, if ((op == REQ_OP_WRITE) && !test_bit(MD_NO_FUA, &device->flags)) op_flags |= REQ_FUA | REQ_PREFLUSH; - op_flags |= REQ_SYNC | REQ_NOIDLE; + op_flags |= REQ_SYNC; bio = bio_alloc_drbd(GFP_NOIO); bio->bi_bdev = bdev->md_bdev; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 107d23d18096..63b750a3b165 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -175,7 +175,7 @@ enum req_flag_bits { __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_NOIDLE, /* don't anticipate more IO after this one */ + __REQ_IDLE, /* anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ __REQ_PREFLUSH, /* request for cache flush */ @@ -190,7 +190,7 @@ enum req_flag_bits { #define REQ_META (1ULL << __REQ_META) #define REQ_PRIO (1ULL << __REQ_PRIO) #define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_NOIDLE (1ULL << __REQ_NOIDLE) +#define REQ_IDLE (1ULL << __REQ_IDLE) #define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) #define REQ_FUA (1ULL << __REQ_FUA) #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) diff --git a/include/linux/fs.h b/include/linux/fs.h index ccedccb28ec8..46a74209917f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -197,11 +197,11 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define WRITE REQ_OP_WRITE #define READ_SYNC 0 -#define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) -#define WRITE_ODIRECT REQ_SYNC -#define WRITE_FLUSH (REQ_NOIDLE | REQ_PREFLUSH) -#define WRITE_FUA (REQ_NOIDLE | REQ_FUA) -#define WRITE_FLUSH_FUA (REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA) +#define WRITE_SYNC REQ_SYNC +#define WRITE_ODIRECT (REQ_SYNC | REQ_IDLE) +#define WRITE_FLUSH REQ_PREFLUSH +#define WRITE_FUA REQ_FUA +#define WRITE_FLUSH_FUA (REQ_PREFLUSH | REQ_FUA) /* * Attribute flags. These should be or-ed together to figure out what diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 903a09165bb1..a9d34424450d 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -32,7 +32,7 @@ TRACE_DEFINE_ENUM(LFS); TRACE_DEFINE_ENUM(SSR); TRACE_DEFINE_ENUM(__REQ_RAHEAD); TRACE_DEFINE_ENUM(__REQ_SYNC); -TRACE_DEFINE_ENUM(__REQ_NOIDLE); +TRACE_DEFINE_ENUM(__REQ_IDLE); TRACE_DEFINE_ENUM(__REQ_PREFLUSH); TRACE_DEFINE_ENUM(__REQ_FUA); TRACE_DEFINE_ENUM(__REQ_PRIO); -- cgit v1.2.3-58-ga151 From 87760e5eef359788047d6fd54fc12eec74ce0d27 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Nov 2016 12:38:14 -0700 Subject: block: hook up writeback throttling Enable throttling of buffered writeback to make it a lot more smooth, and has way less impact on other system activity. Background writeback should be, by definition, background activity. The fact that we flush huge bundles of it at the time means that it potentially has heavy impacts on foreground workloads, which isn't ideal. We can't easily limit the sizes of writes that we do, since that would impact file system layout in the presence of delayed allocation. So just throttle back buffered writeback, unless someone is waiting for it. The algorithm for when to throttle takes its inspiration in the CoDel networking scheduling algorithm. Like CoDel, blk-wb monitors the minimum latencies of requests over a window of time. In that window of time, if the minimum latency of any request exceeds a given target, then a scale count is incremented and the queue depth is shrunk. The next monitoring window is shrunk accordingly. Unlike CoDel, if we hit a window that exhibits good behavior, then we simply increment the scale count and re-calculate the limits for that scale value. This prevents us from oscillating between a close-to-ideal value and max all the time, instead remaining in the windows where we get good behavior. Unlike CoDel, blk-wb allows the scale count to to negative. This happens if we primarily have writes going on. Unlike positive scale counts, this doesn't change the size of the monitoring window. When the heavy writers finish, blk-bw quickly snaps back to it's stable state of a zero scale count. The patch registers a sysfs entry, 'wb_lat_usec'. This sets the latency target to me met. It defaults to 2 msec for non-rotational storage, and 75 msec for rotational storage. Setting this value to '0' disables blk-wb. Generally, a user would not have to touch this setting. We don't enable WBT on devices that are managed with CFQ, and have a non-root block cgroup attached. If we have a proportional share setup on this particular disk, then the wbt throttling will interfere with that. We don't have a strong need for wbt for that case, since we will rely on CFQ doing that for us. Signed-off-by: Jens Axboe --- Documentation/block/queue-sysfs.txt | 7 +++ block/Kconfig | 26 +++++++++++ block/blk-core.c | 17 ++++++- block/blk-mq.c | 26 ++++++++++- block/blk-settings.c | 4 ++ block/blk-sysfs.c | 88 +++++++++++++++++++++++++++++++++++++ block/cfq-iosched.c | 14 ++++++ include/linux/blkdev.h | 3 ++ 8 files changed, 181 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index 2a3904030dea..87abf1ac2939 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -169,5 +169,12 @@ This is the number of bytes the device can write in a single write-same command. A value of '0' means write-same is not supported by this device. +wb_lat_usec (RW) +---------------- +If the device is registered for writeback throttling, then this file shows +the target minimum read latency. If this latency is exceeded in a given +window of time (see wb_window_usec), then the writeback throttling will start +scaling back writes. + Jens Axboe , February 2009 diff --git a/block/Kconfig b/block/Kconfig index 3a024440a669..8bf114a3858a 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -121,6 +121,32 @@ config BLK_CMDLINE_PARSER See Documentation/block/cmdline-partition.txt for more information. +config BLK_WBT + bool "Enable support for block device writeback throttling" + default n + ---help--- + Enabling this option enables the block layer to throttle buffered + background writeback from the VM, making it more smooth and having + less impact on foreground operations. The throttling is done + dynamically on an algorithm loosely based on CoDel, factoring in + the realtime performance of the disk. + +config BLK_WBT_SQ + bool "Single queue writeback throttling" + default n + depends on BLK_WBT + ---help--- + Enable writeback throttling by default on legacy single queue devices + +config BLK_WBT_MQ + bool "Multiqueue writeback throttling" + default y + depends on BLK_WBT + ---help--- + Enable writeback throttling by default on multiqueue devices. + Multiqueue currently doesn't have support for IO scheduling, + enabling this option is recommended. + menu "Partition Types" source "block/partitions/Kconfig" diff --git a/block/blk-core.c b/block/blk-core.c index 216372b01624..59f8129a4295 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -39,6 +39,7 @@ #include "blk.h" #include "blk-mq.h" +#include "blk-wbt.h" EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); @@ -882,6 +883,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, fail: blk_free_flush_queue(q->fq); + wbt_exit(q); return NULL; } EXPORT_SYMBOL(blk_init_allocated_queue); @@ -1344,6 +1346,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) blk_delete_timer(rq); blk_clear_rq_complete(rq); trace_block_rq_requeue(q, rq); + wbt_requeue(q->rq_wb, &rq->issue_stat); if (rq->rq_flags & RQF_QUEUED) blk_queue_end_tag(q, rq); @@ -1436,6 +1439,8 @@ void __blk_put_request(struct request_queue *q, struct request *req) /* this is a bio leak */ WARN_ON(req->bio != NULL); + wbt_done(q->rq_wb, &req->issue_stat); + /* * Request may not have originated from ll_rw_blk. if not, * it didn't come out of our reserved rq pools @@ -1663,6 +1668,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) int el_ret, where = ELEVATOR_INSERT_SORT; struct request *req; unsigned int request_count = 0; + unsigned int wb_acct; /* * low level driver can indicate that it wants pages above a @@ -1715,17 +1721,22 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) } get_rq: + wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock); + /* * Grab a free request. This is might sleep but can not fail. * Returns with the queue unlocked. */ req = get_request(q, bio->bi_opf, bio, GFP_NOIO); if (IS_ERR(req)) { + __wbt_done(q->rq_wb, wb_acct); bio->bi_error = PTR_ERR(req); bio_endio(bio); goto out_unlock; } + wbt_track(&req->issue_stat, wb_acct); + /* * After dropping the lock and possibly sleeping here, our request * may now be mergeable after it had proven unmergeable (above). @@ -2467,6 +2478,7 @@ void blk_start_request(struct request *req) if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) { blk_stat_set_issue_time(&req->issue_stat); req->rq_flags |= RQF_STATS; + wbt_issue(req->q->rq_wb, &req->issue_stat); } /* @@ -2708,9 +2720,10 @@ void blk_finish_request(struct request *req, int error) blk_account_io_done(req); - if (req->end_io) + if (req->end_io) { + wbt_done(req->q->rq_wb, &req->issue_stat); req->end_io(req, error); - else { + } else { if (blk_bidi_rq(req)) __blk_put_request(req->next_rq->q, req->next_rq); diff --git a/block/blk-mq.c b/block/blk-mq.c index 19795886d46e..d180c989a0e5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -31,6 +31,7 @@ #include "blk-mq.h" #include "blk-mq-tag.h" #include "blk-stat.h" +#include "blk-wbt.h" static DEFINE_MUTEX(all_q_mutex); static LIST_HEAD(all_q_list); @@ -326,6 +327,8 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, if (rq->rq_flags & RQF_MQ_INFLIGHT) atomic_dec(&hctx->nr_active); + + wbt_done(q->rq_wb, &rq->issue_stat); rq->rq_flags = 0; clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); @@ -354,6 +357,7 @@ inline void __blk_mq_end_request(struct request *rq, int error) blk_account_io_done(rq); if (rq->end_io) { + wbt_done(rq->q->rq_wb, &rq->issue_stat); rq->end_io(rq, error); } else { if (unlikely(blk_bidi_rq(rq))) @@ -471,6 +475,7 @@ void blk_mq_start_request(struct request *rq) if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { blk_stat_set_issue_time(&rq->issue_stat); rq->rq_flags |= RQF_STATS; + wbt_issue(q->rq_wb, &rq->issue_stat); } blk_add_timer(rq); @@ -508,6 +513,7 @@ static void __blk_mq_requeue_request(struct request *rq) struct request_queue *q = rq->q; trace_block_rq_requeue(q, rq); + wbt_requeue(q->rq_wb, &rq->issue_stat); if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) { if (q->dma_drain_size && blk_rq_bytes(rq)) @@ -1339,6 +1345,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) struct blk_plug *plug; struct request *same_queue_rq = NULL; blk_qc_t cookie; + unsigned int wb_acct; blk_queue_bounce(q, &bio); @@ -1353,9 +1360,15 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) return BLK_QC_T_NONE; + wb_acct = wbt_wait(q->rq_wb, bio, NULL); + rq = blk_mq_map_request(q, bio, &data); - if (unlikely(!rq)) + if (unlikely(!rq)) { + __wbt_done(q->rq_wb, wb_acct); return BLK_QC_T_NONE; + } + + wbt_track(&rq->issue_stat, wb_acct); cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num); @@ -1439,6 +1452,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) struct blk_mq_alloc_data data; struct request *rq; blk_qc_t cookie; + unsigned int wb_acct; blk_queue_bounce(q, &bio); @@ -1455,9 +1469,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) } else request_count = blk_plug_queued_count(q); + wb_acct = wbt_wait(q->rq_wb, bio, NULL); + rq = blk_mq_map_request(q, bio, &data); - if (unlikely(!rq)) + if (unlikely(!rq)) { + __wbt_done(q->rq_wb, wb_acct); return BLK_QC_T_NONE; + } + + wbt_track(&rq->issue_stat, wb_acct); cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num); @@ -2139,6 +2159,8 @@ void blk_mq_free_queue(struct request_queue *q) list_del_init(&q->all_q_node); mutex_unlock(&all_q_mutex); + wbt_exit(q); + blk_mq_del_queue_tag_set(q); blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); diff --git a/block/blk-settings.c b/block/blk-settings.c index 9cf053759363..c7ccabc0ec3e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -13,6 +13,7 @@ #include #include "blk.h" +#include "blk-wbt.h" unsigned long blk_max_low_pfn; EXPORT_SYMBOL(blk_max_low_pfn); @@ -845,6 +846,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); void blk_set_queue_depth(struct request_queue *q, unsigned int depth) { q->queue_depth = depth; + wbt_set_queue_depth(q->rq_wb, depth); } EXPORT_SYMBOL(blk_set_queue_depth); @@ -868,6 +870,8 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) else queue_flag_clear(QUEUE_FLAG_FUA, q); spin_unlock_irq(q->queue_lock); + + wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); } EXPORT_SYMBOL_GPL(blk_queue_write_cache); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 9cdb7247727a..9262d2d60a09 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -13,6 +13,7 @@ #include "blk.h" #include "blk-mq.h" +#include "blk-wbt.h" struct queue_sysfs_entry { struct attribute attr; @@ -41,6 +42,19 @@ queue_var_store(unsigned long *var, const char *page, size_t count) return count; } +static ssize_t queue_var_store64(u64 *var, const char *page) +{ + int err; + u64 v; + + err = kstrtou64(page, 10, &v); + if (err < 0) + return err; + + *var = v; + return 0; +} + static ssize_t queue_requests_show(struct request_queue *q, char *page) { return queue_var_show(q->nr_requests, (page)); @@ -364,6 +378,32 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page, return ret; } +static ssize_t queue_wb_lat_show(struct request_queue *q, char *page) +{ + if (!q->rq_wb) + return -EINVAL; + + return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000)); +} + +static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, + size_t count) +{ + ssize_t ret; + u64 val; + + if (!q->rq_wb) + return -EINVAL; + + ret = queue_var_store64(&val, page); + if (ret < 0) + return ret; + + q->rq_wb->min_lat_nsec = val * 1000ULL; + wbt_update_limits(q->rq_wb); + return count; +} + static ssize_t queue_wc_show(struct request_queue *q, char *page) { if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) @@ -578,6 +618,12 @@ static struct queue_sysfs_entry queue_stats_entry = { .show = queue_stats_show, }; +static struct queue_sysfs_entry queue_wb_lat_entry = { + .attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR }, + .show = queue_wb_lat_show, + .store = queue_wb_lat_store, +}; + static struct attribute *default_attrs[] = { &queue_requests_entry.attr, &queue_ra_entry.attr, @@ -608,6 +654,7 @@ static struct attribute *default_attrs[] = { &queue_wc_entry.attr, &queue_dax_entry.attr, &queue_stats_entry.attr, + &queue_wb_lat_entry.attr, NULL, }; @@ -682,6 +729,7 @@ static void blk_release_queue(struct kobject *kobj) struct request_queue *q = container_of(kobj, struct request_queue, kobj); + wbt_exit(q); bdi_exit(&q->backing_dev_info); blkcg_exit_queue(q); @@ -722,6 +770,44 @@ struct kobj_type blk_queue_ktype = { .release = blk_release_queue, }; +static void blk_wb_stat_get(void *data, struct blk_rq_stat *stat) +{ + blk_queue_stat_get(data, stat); +} + +static void blk_wb_stat_clear(void *data) +{ + blk_stat_clear(data); +} + +static bool blk_wb_stat_is_current(struct blk_rq_stat *stat) +{ + return blk_stat_is_current(stat); +} + +static struct wb_stat_ops wb_stat_ops = { + .get = blk_wb_stat_get, + .is_current = blk_wb_stat_is_current, + .clear = blk_wb_stat_clear, +}; + +static void blk_wb_init(struct request_queue *q) +{ +#ifndef CONFIG_BLK_WBT_MQ + if (q->mq_ops) + return; +#endif +#ifndef CONFIG_BLK_WBT_SQ + if (q->request_fn) + return; +#endif + + /* + * If this fails, we don't get throttling + */ + wbt_init(q, &wb_stat_ops); +} + int blk_register_queue(struct gendisk *disk) { int ret; @@ -761,6 +847,8 @@ int blk_register_queue(struct gendisk *disk) if (q->mq_ops) blk_mq_register_dev(dev, q); + blk_wb_init(q); + if (!q->request_fn) return 0; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 61010511c5a0..e280d08ef6d7 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -16,6 +16,7 @@ #include #include #include "blk.h" +#include "blk-wbt.h" /* * tunables @@ -3762,9 +3763,11 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) struct cfq_data *cfqd = cic_to_cfqd(cic); struct cfq_queue *cfqq; uint64_t serial_nr; + bool nonroot_cg; rcu_read_lock(); serial_nr = bio_blkcg(bio)->css.serial_nr; + nonroot_cg = bio_blkcg(bio) != &blkcg_root; rcu_read_unlock(); /* @@ -3774,6 +3777,17 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr)) return; + /* + * If we have a non-root cgroup, we can depend on that to + * do proper throttling of writes. Turn off wbt for that + * case. + */ + if (nonroot_cg) { + struct request_queue *q = cfqd->queue; + + wbt_disable(q->rq_wb); + } + /* * Drop reference to queues. New queues will be assigned in new * group upon arrival of fresh requests. diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 303723a2e5b8..15da9e430f90 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -38,6 +38,7 @@ struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; +struct rq_wb; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -383,6 +384,8 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ + struct rq_wb *rq_wb; + /* * If blkcg is not used, @q->root_rl serves all requests. If blkcg * is used, root blkg allocates from @q->root_rl and all other -- cgit v1.2.3-58-ga151 From 92153d30c7c8863022cad684926d71ffaed6a56d Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Wed, 16 Nov 2016 08:26:11 -0700 Subject: null_blk: add usage hints for NVM If CONFIG_NVM is disabled, loading null_block module with use_lightnvm=1 fails. But there are no messages and documents related to the failure. Add the appropriate error message. Signed-off-by: Yasuaki Ishimatsu Massaged the text a bit. Signed-off-by: Jens Axboe --- Documentation/block/null_blk.txt | 2 +- drivers/block/null_blk.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt index d8880ca30af4..3140dbd860d8 100644 --- a/Documentation/block/null_blk.txt +++ b/Documentation/block/null_blk.txt @@ -72,4 +72,4 @@ use_per_node_hctx=[0/1]: Default: 0 queue for each CPU node in the system. use_lightnvm=[0/1]: Default: 0 - Register device with LightNVM. Requires blk-mq to be used. + Register device with LightNVM. Requires blk-mq and CONFIG_NVM to be enabled. diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index ba6f4a2e73db..4943ee22716e 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -577,6 +577,7 @@ static void null_nvm_unregister(struct nullb *nullb) #else static int null_nvm_register(struct nullb *nullb) { + pr_err("null_blk: CONFIG_NVM needs to be enabled for LightNVM\n"); return -EINVAL; } static void null_nvm_unregister(struct nullb *nullb) {} -- cgit v1.2.3-58-ga151 From 10e6246e2275865ab917494e418f44b8c25ddd34 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Nov 2016 22:23:02 -0700 Subject: block: document the 'io_poll_delay' queue sysfs file This was documented in the original commit, 64f1c21e86f7, but it never made it into the proper location for queue sysfs files. Signed-off-by: Jens Axboe --- Documentation/block/queue-sysfs.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'Documentation') diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index 87abf1ac2939..14235e72a702 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -58,6 +58,20 @@ When read, this file shows the total number of block IO polls and how many returned success. Writing '0' to this file will disable polling for this device. Writing any non-zero value will enable this feature. +io_poll_delay (RW) +------------------ +If polling is enabled, this controls what kind of polling will be +performed. It defaults to -1, which is classic polling. In this mode, +the CPU will repeatedly ask for completions without giving up any time. +If set to 0, a hybrid polling mode is used, where the kernel will attempt +to make an educated guess at when the IO will complete. Based on this +guess, the kernel will put the process issuing IO to sleep for an amount +of time, before entering a classic poll loop. This mode might be a +little slower than pure classic polling, but it will be more efficient. +If set to a value larger than 0, the kernel will put the process issuing +IO to sleep for this amont of microseconds before entering classic +polling. + iostats (RW) ------------- This file is used to control (on/off) the iostats accounting of the -- cgit v1.2.3-58-ga151 From 80e091d10e8bf7b801d634ea8870b9e907314424 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 28 Nov 2016 09:22:47 -0700 Subject: blk-wbt: allow reset of default latency through sysfs Allow a write of '-1' to reset the default latency target for a given device. This removes knowledge of the different default settings for rotational vs non-rotational from user space. Signed-off-by: Jens Axboe --- Documentation/block/queue-sysfs.txt | 4 +++- block/blk-sysfs.c | 22 +++++++++++++++------- block/blk-wbt.c | 17 +++++++++++++---- block/blk-wbt.h | 6 ++++++ 4 files changed, 37 insertions(+), 12 deletions(-) (limited to 'Documentation') diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index 14235e72a702..51642159aedb 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -188,7 +188,9 @@ wb_lat_usec (RW) If the device is registered for writeback throttling, then this file shows the target minimum read latency. If this latency is exceeded in a given window of time (see wb_window_usec), then the writeback throttling will start -scaling back writes. +scaling back writes. Writing a value of '0' to this file disables the +feature. Writing a value of '-1' to this file resets the value to the +default setting. Jens Axboe , February 2009 diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 1855c6770045..f0ca569e276b 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -42,12 +42,12 @@ queue_var_store(unsigned long *var, const char *page, size_t count) return count; } -static ssize_t queue_var_store64(u64 *var, const char *page) +static ssize_t queue_var_store64(s64 *var, const char *page) { int err; - u64 v; + s64 v; - err = kstrtou64(page, 10, &v); + err = kstrtos64(page, 10, &v); if (err < 0) return err; @@ -421,18 +421,26 @@ static ssize_t queue_wb_lat_show(struct request_queue *q, char *page) static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, size_t count) { + struct rq_wb *rwb; ssize_t ret; - u64 val; + s64 val; - if (!q->rq_wb) + rwb = q->rq_wb; + if (!rwb) return -EINVAL; ret = queue_var_store64(&val, page); if (ret < 0) return ret; - q->rq_wb->min_lat_nsec = val * 1000ULL; - wbt_update_limits(q->rq_wb); + if (val == -1) + rwb->min_lat_nsec = wbt_default_latency_nsec(q); + else if (val >= 0) + rwb->min_lat_nsec = val * 1000ULL; + else + return -EINVAL; + + wbt_update_limits(rwb); return count; } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 9f97594e68ce..92df2f7c5af1 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -675,6 +675,18 @@ void wbt_disable(struct rq_wb *rwb) } EXPORT_SYMBOL_GPL(wbt_disable); +u64 wbt_default_latency_nsec(struct request_queue *q) +{ + /* + * We default to 2msec for non-rotational storage, and 75msec + * for rotational storage. + */ + if (blk_queue_nonrot(q)) + return 2000000ULL; + else + return 75000000ULL; +} + int wbt_init(struct request_queue *q) { struct rq_wb *rwb; @@ -711,10 +723,7 @@ int wbt_init(struct request_queue *q) q->rq_wb = rwb; blk_stat_enable(q); - if (blk_queue_nonrot(q)) - rwb->min_lat_nsec = 2000000ULL; - else - rwb->min_lat_nsec = 75000000ULL; + rwb->min_lat_nsec = wbt_default_latency_nsec(q); wbt_set_queue_depth(rwb, blk_queue_depth(q)); wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); diff --git a/block/blk-wbt.h b/block/blk-wbt.h index 44dc2173dc1f..9dfc88ad7f30 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -110,6 +110,8 @@ void wbt_disable(struct rq_wb *); void wbt_set_queue_depth(struct rq_wb *, unsigned int); void wbt_set_write_cache(struct rq_wb *, bool); +u64 wbt_default_latency_nsec(struct request_queue *); + #else static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags) @@ -148,6 +150,10 @@ static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth) static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc) { } +static inline u64 wbt_default_latency_nsec(struct request_queue *q) +{ + return 0; +} #endif /* CONFIG_BLK_WBT */ -- cgit v1.2.3-58-ga151 From a6f0788ec2881ac14e97ff7fa6a78a807f87b5ba Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 30 Nov 2016 12:28:59 -0800 Subject: block: add support for REQ_OP_WRITE_ZEROES This adds a new block layer operation to zero out a range of LBAs. This allows to implement zeroing for devices that don't use either discard with a predictable zero pattern or WRITE SAME of zeroes. The prominent example of that is NVMe with the Write Zeroes command, but in the future, this should also help with improving the way zeroing discards work. For this operation, suitable entry is exported in sysfs which indicate the number of maximum bytes allowed in one write zeroes operation by the device. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- Documentation/ABI/testing/sysfs-block | 13 ++++++++ block/bio.c | 1 + block/blk-core.c | 4 +++ block/blk-lib.c | 58 +++++++++++++++++++++++++++++++++-- block/blk-merge.c | 17 +++++++--- block/blk-settings.c | 17 ++++++++++ block/blk-sysfs.c | 11 +++++++ block/blk-wbt.c | 5 +-- include/linux/bio.h | 25 ++++++++------- include/linux/blk_types.h | 2 ++ include/linux/blkdev.h | 19 ++++++++++++ 11 files changed, 153 insertions(+), 19 deletions(-) (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index ee2d5cd26bfe..2da04ce6aeef 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -235,6 +235,19 @@ Description: write_same_max_bytes is 0, write same is not supported by the device. +What: /sys/block//queue/write_zeroes_max_bytes +Date: November 2016 +Contact: Chaitanya Kulkarni +Description: + Devices that support write zeroes operation in which a + single request can be issued to zero out the range of + contiguous blocks on storage without having any payload + in the request. This can be used to optimize writing zeroes + to the devices. write_zeroes_max_bytes indicates how many + bytes can be written in a single write zeroes command. If + write_zeroes_max_bytes is 0, write zeroes is not supported + by the device. + What: /sys/block//queue/zoned Date: September 2016 Contact: Damien Le Moal diff --git a/block/bio.c b/block/bio.c index de257ced69b1..83db1f37fd0b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -674,6 +674,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: + case REQ_OP_WRITE_ZEROES: break; case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; diff --git a/block/blk-core.c b/block/blk-core.c index 6c4a425690fc..3f2eb8d80189 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1950,6 +1950,10 @@ generic_make_request_checks(struct bio *bio) if (!bdev_is_zoned(bio->bi_bdev)) goto not_supported; break; + case REQ_OP_WRITE_ZEROES: + if (!bdev_write_zeroes_sectors(bio->bi_bdev)) + goto not_supported; + break; default: break; } diff --git a/block/blk-lib.c b/block/blk-lib.c index bfb28b03765e..510a6fb15318 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -226,6 +226,55 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, } EXPORT_SYMBOL(blkdev_issue_write_same); +/** + * __blkdev_issue_write_zeroes - generate number of bios with WRITE ZEROES + * @bdev: blockdev to issue + * @sector: start sector + * @nr_sects: number of sectors to write + * @gfp_mask: memory allocation flags (for bio_alloc) + * @biop: pointer to anchor bio + * + * Description: + * Generate and issue number of bios(REQ_OP_WRITE_ZEROES) with zerofiled pages. + */ +static int __blkdev_issue_write_zeroes(struct block_device *bdev, + sector_t sector, sector_t nr_sects, gfp_t gfp_mask, + struct bio **biop) +{ + struct bio *bio = *biop; + unsigned int max_write_zeroes_sectors; + struct request_queue *q = bdev_get_queue(bdev); + + if (!q) + return -ENXIO; + + /* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */ + max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev); + + if (max_write_zeroes_sectors == 0) + return -EOPNOTSUPP; + + while (nr_sects) { + bio = next_bio(bio, 0, gfp_mask); + bio->bi_iter.bi_sector = sector; + bio->bi_bdev = bdev; + bio_set_op_attrs(bio, REQ_OP_WRITE_ZEROES, 0); + + if (nr_sects > max_write_zeroes_sectors) { + bio->bi_iter.bi_size = max_write_zeroes_sectors << 9; + nr_sects -= max_write_zeroes_sectors; + sector += max_write_zeroes_sectors; + } else { + bio->bi_iter.bi_size = nr_sects << 9; + nr_sects = 0; + } + cond_resched(); + } + + *biop = bio; + return 0; +} + /** * __blkdev_issue_zeroout - generate number of zero filed write bios * @bdev: blockdev to issue @@ -259,6 +308,11 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, goto out; } + ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, + biop); + if (ret == 0 || (ret && ret != -EOPNOTSUPP)) + goto out; + ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask, ZERO_PAGE(0), biop); if (ret == 0 || (ret && ret != -EOPNOTSUPP)) @@ -304,8 +358,8 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout); * the discard request fail, if the discard flag is not set, or if * discard_zeroes_data is not supported, this function will resort to * zeroing the blocks manually, thus provisioning (allocating, - * anchoring) them. If the block device supports the WRITE SAME command - * blkdev_issue_zeroout() will use it to optimize the process of + * anchoring) them. If the block device supports WRITE ZEROES or WRITE SAME + * command(s), blkdev_issue_zeroout() will use it to optimize the process of * clearing the block range. Otherwise the zeroing will be performed * using regular WRITE calls. */ diff --git a/block/blk-merge.c b/block/blk-merge.c index fda6a12fc776..cf2848cb91d8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -199,6 +199,10 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); break; + case REQ_OP_WRITE_ZEROES: + split = NULL; + nsegs = (*bio)->bi_phys_segments; + break; case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); break; @@ -241,11 +245,15 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) - return 1; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE_ZEROES: return 1; + default: + break; + } fbio = bio; cluster = blk_queue_cluster(q); @@ -416,6 +424,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: + case REQ_OP_WRITE_ZEROES: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of diff --git a/block/blk-settings.c b/block/blk-settings.c index c7ccabc0ec3e..8a2bc124a684 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -96,6 +96,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_dev_sectors = 0; lim->chunk_sectors = 0; lim->max_write_same_sectors = 0; + lim->max_write_zeroes_sectors = 0; lim->max_discard_sectors = 0; lim->max_hw_discard_sectors = 0; lim->discard_granularity = 0; @@ -132,6 +133,7 @@ void blk_set_stacking_limits(struct queue_limits *lim) lim->max_sectors = UINT_MAX; lim->max_dev_sectors = UINT_MAX; lim->max_write_same_sectors = UINT_MAX; + lim->max_write_zeroes_sectors = UINT_MAX; } EXPORT_SYMBOL(blk_set_stacking_limits); @@ -299,6 +301,19 @@ void blk_queue_max_write_same_sectors(struct request_queue *q, } EXPORT_SYMBOL(blk_queue_max_write_same_sectors); +/** + * blk_queue_max_write_zeroes_sectors - set max sectors for a single + * write zeroes + * @q: the request queue for the device + * @max_write_zeroes_sectors: maximum number of sectors to write per command + **/ +void blk_queue_max_write_zeroes_sectors(struct request_queue *q, + unsigned int max_write_zeroes_sectors) +{ + q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors; +} +EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors); + /** * blk_queue_max_segments - set max hw segments for a request for this queue * @q: the request queue for the device @@ -527,6 +542,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors); t->max_write_same_sectors = min(t->max_write_same_sectors, b->max_write_same_sectors); + t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors, + b->max_write_zeroes_sectors); t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn); t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index a97841491769..706b27bd73a1 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -211,6 +211,11 @@ static ssize_t queue_write_same_max_show(struct request_queue *q, char *page) (unsigned long long)q->limits.max_write_same_sectors << 9); } +static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page) +{ + return sprintf(page, "%llu\n", + (unsigned long long)q->limits.max_write_zeroes_sectors << 9); +} static ssize_t queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) @@ -611,6 +616,11 @@ static struct queue_sysfs_entry queue_write_same_max_entry = { .show = queue_write_same_max_show, }; +static struct queue_sysfs_entry queue_write_zeroes_max_entry = { + .attr = {.name = "write_zeroes_max_bytes", .mode = S_IRUGO }, + .show = queue_write_zeroes_max_show, +}; + static struct queue_sysfs_entry queue_nonrot_entry = { .attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR }, .show = queue_show_nonrot, @@ -700,6 +710,7 @@ static struct attribute *default_attrs[] = { &queue_discard_max_hw_entry.attr, &queue_discard_zeroes_data_entry.attr, &queue_write_same_max_entry.attr, + &queue_write_zeroes_max_entry.attr, &queue_nonrot_entry.attr, &queue_zoned_entry.attr, &queue_nomerges_entry.attr, diff --git a/block/blk-wbt.c b/block/blk-wbt.c index b8647343141f..d500e43da5d9 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -575,9 +575,10 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio) const int op = bio_op(bio); /* - * If not a WRITE (or a discard), do nothing + * If not a WRITE (or a discard or write zeroes), do nothing */ - if (!(op == REQ_OP_WRITE || op == REQ_OP_DISCARD)) + if (!(op == REQ_OP_WRITE || op == REQ_OP_DISCARD || + op == REQ_OP_WRITE_ZEROES)) return false; /* diff --git a/include/linux/bio.h b/include/linux/bio.h index 70a7244f08a7..b15323934a29 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -76,7 +76,8 @@ static inline bool bio_has_data(struct bio *bio) if (bio && bio->bi_iter.bi_size && bio_op(bio) != REQ_OP_DISCARD && - bio_op(bio) != REQ_OP_SECURE_ERASE) + bio_op(bio) != REQ_OP_SECURE_ERASE && + bio_op(bio) != REQ_OP_WRITE_ZEROES) return true; return false; @@ -86,7 +87,8 @@ static inline bool bio_no_advance_iter(struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || - bio_op(bio) == REQ_OP_WRITE_SAME; + bio_op(bio) == REQ_OP_WRITE_SAME || + bio_op(bio) == REQ_OP_WRITE_ZEROES; } static inline bool bio_mergeable(struct bio *bio) @@ -188,18 +190,19 @@ static inline unsigned bio_segments(struct bio *bio) struct bvec_iter iter; /* - * We special case discard/write same, because they interpret bi_size - * differently: + * We special case discard/write same/write zeroes, because they + * interpret bi_size differently: */ - if (bio_op(bio) == REQ_OP_DISCARD) - return 1; - - if (bio_op(bio) == REQ_OP_SECURE_ERASE) - return 1; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE_ZEROES: return 1; + default: + break; + } bio_for_each_segment(bv, bio, iter) segs++; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f57458a6a93b..519ea2c9df61 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -159,6 +159,8 @@ enum req_opf { REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, + /* write the zero filled sector many times */ + REQ_OP_WRITE_ZEROES = 8, REQ_OP_LAST, }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7e9d8a0895be..ebeef2b79c5a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -323,6 +323,7 @@ struct queue_limits { unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; + unsigned int max_write_zeroes_sectors; unsigned int discard_granularity; unsigned int discard_alignment; @@ -774,6 +775,9 @@ static inline bool rq_mergeable(struct request *rq) if (req_op(rq) == REQ_OP_FLUSH) return false; + if (req_op(rq) == REQ_OP_WRITE_ZEROES) + return false; + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) @@ -1004,6 +1008,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, if (unlikely(op == REQ_OP_WRITE_SAME)) return q->limits.max_write_same_sectors; + if (unlikely(op == REQ_OP_WRITE_ZEROES)) + return q->limits.max_write_zeroes_sectors; + return q->limits.max_sectors; } @@ -1107,6 +1114,8 @@ extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); +extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, + unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, @@ -1475,6 +1484,16 @@ static inline unsigned int bdev_write_same(struct block_device *bdev) return 0; } +static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return q->limits.max_write_zeroes_sectors; + + return 0; +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3-58-ga151