From e6f7f93d58de74700f83dd0547dd4306248a093d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 25 Jan 2017 11:17:11 +0100 Subject: block: fix elevator init check We can't initalize the elevator fields for flushes as flush share space in struct request with the elevator data. But currently we can't communicate that a request is a flush through blk_get_request as we can only pass READ or WRITE, and the low-level code looks at the possible NULL bio to check for a flush. Fix this by allowing to pass any block op and flags, and by checking for the flush flags in __get_request. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-core.c | 26 ++++---------------------- 1 file changed, 4 insertions(+), 22 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 02833ce5664e..4cad535592c3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1022,25 +1022,6 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr) return 0; } -/* - * Determine if elevator data should be initialized when allocating the - * request associated with @bio. - */ -static bool blk_rq_should_init_elevator(struct bio *bio) -{ - if (!bio) - return true; - - /* - * Flush requests do not use the elevator so skip initialization. - * This allows a request to share the flush and elevator data. - */ - if (op_is_flush(bio->bi_opf)) - return false; - - return true; -} - /** * __get_request - get a free request * @rl: request list to allocate from @@ -1119,10 +1100,13 @@ static struct request *__get_request(struct request_list *rl, unsigned int op, * request is freed. This guarantees icq's won't be destroyed and * makes creating new ones safe. * + * Flush requests do not use the elevator so skip initialization. + * This allows a request to share the flush and elevator data. + * * Also, lookup icq while holding queue_lock. If it doesn't exist, * it will be created after releasing queue_lock. */ - if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) { + if (!op_is_flush(op) && !blk_queue_bypass(q)) { rq_flags |= RQF_ELVPRIV; q->nr_rqs_elvpriv++; if (et->icq_cache && ioc) @@ -1276,8 +1260,6 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw, { struct request *rq; - BUG_ON(rw != READ && rw != WRITE); - /* create ioc upfront */ create_io_context(gfp_mask, q->node); -- cgit v1.2.3-59-g8ed1b From 5ea708d15a928f7a479987704203616d3274c03b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Jan 2017 14:52:44 +0300 Subject: block: simplify blk_init_allocated_queue Return an errno value instead of the passed in queue so that the callers don't have to keep track of two queues, and move the assignment of the request_fn and lock to the caller as passing them as argument doesn't simplify anything. While we're at it also remove two pointless NULL assignments, given that the request structure is zeroed on allocation. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-core.c | 38 +++++++++++++++----------------------- drivers/md/dm-rq.c | 3 ++- include/linux/blkdev.h | 3 +-- 3 files changed, 18 insertions(+), 26 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 4cad535592c3..09819d24d385 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -823,15 +823,19 @@ EXPORT_SYMBOL(blk_init_queue); struct request_queue * blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) { - struct request_queue *uninit_q, *q; + struct request_queue *q; - uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id); - if (!uninit_q) + q = blk_alloc_queue_node(GFP_KERNEL, node_id); + if (!q) return NULL; - q = blk_init_allocated_queue(uninit_q, rfn, lock); - if (!q) - blk_cleanup_queue(uninit_q); + q->request_fn = rfn; + if (lock) + q->queue_lock = lock; + if (blk_init_allocated_queue(q) < 0) { + blk_cleanup_queue(q); + return NULL; + } return q; } @@ -839,30 +843,19 @@ EXPORT_SYMBOL(blk_init_queue_node); static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio); -struct request_queue * -blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, - spinlock_t *lock) -{ - if (!q) - return NULL; +int blk_init_allocated_queue(struct request_queue *q) +{ q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0); if (!q->fq) - return NULL; + return -ENOMEM; if (blk_init_rl(&q->root_rl, q, GFP_KERNEL)) goto fail; INIT_WORK(&q->timeout_work, blk_timeout_work); - q->request_fn = rfn; - q->prep_rq_fn = NULL; - q->unprep_rq_fn = NULL; q->queue_flags |= QUEUE_FLAG_DEFAULT; - /* Override internal queue lock with supplied lock pointer */ - if (lock) - q->queue_lock = lock; - /* * This also sets hw/phys segments, boundary and size */ @@ -880,13 +873,12 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, } mutex_unlock(&q->sysfs_lock); - - return q; + return 0; fail: blk_free_flush_queue(q->fq); wbt_exit(q); - return NULL; + return -ENOMEM; } EXPORT_SYMBOL(blk_init_allocated_queue); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 9d7275fb541a..93f6e9f1ebe2 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -823,7 +823,8 @@ static void dm_old_request_fn(struct request_queue *q) int dm_old_init_request_queue(struct mapped_device *md) { /* Fully initialize the queue */ - if (!blk_init_allocated_queue(md->queue, dm_old_request_fn, NULL)) + md->queue->request_fn = dm_old_request_fn; + if (blk_init_allocated_queue(md->queue) < 0) return -EINVAL; /* disable dm_old_request_fn's merge heuristic by default */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 05675b1dfd20..6b1efc5760ea 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1137,8 +1137,7 @@ extern void blk_unprep_request(struct request *); extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id); extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); -extern struct request_queue *blk_init_allocated_queue(struct request_queue *, - request_fn_proc *, spinlock_t *); +extern int blk_init_allocated_queue(struct request_queue *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -- cgit v1.2.3-59-g8ed1b From 6d247d7f71d1fa4b66a5f4da7b1daa21510d529b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Jan 2017 09:51:45 -0700 Subject: block: allow specifying size for extra command data This mirrors the blk-mq capabilities to allocate extra drivers-specific data behind struct request by setting a cmd_size field, as well as having a constructor / destructor for it. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-core.c | 59 ++++++++++++++++++++++++++++++++++++++++---------- block/blk-flush.c | 5 ++--- block/blk-sysfs.c | 7 ++++-- include/linux/blkdev.h | 7 ++++++ 4 files changed, 61 insertions(+), 17 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 09819d24d385..0a485ad802c9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -606,17 +606,41 @@ void blk_cleanup_queue(struct request_queue *q) EXPORT_SYMBOL(blk_cleanup_queue); /* Allocate memory local to the request queue */ -static void *alloc_request_struct(gfp_t gfp_mask, void *data) +static void *alloc_request_simple(gfp_t gfp_mask, void *data) { - int nid = (int)(long)data; - return kmem_cache_alloc_node(request_cachep, gfp_mask, nid); + struct request_queue *q = data; + + return kmem_cache_alloc_node(request_cachep, gfp_mask, q->node); } -static void free_request_struct(void *element, void *unused) +static void free_request_simple(void *element, void *data) { kmem_cache_free(request_cachep, element); } +static void *alloc_request_size(gfp_t gfp_mask, void *data) +{ + struct request_queue *q = data; + struct request *rq; + + rq = kmalloc_node(sizeof(struct request) + q->cmd_size, gfp_mask, + q->node); + if (rq && q->init_rq_fn && q->init_rq_fn(q, rq, gfp_mask) < 0) { + kfree(rq); + rq = NULL; + } + return rq; +} + +static void free_request_size(void *element, void *data) +{ + struct request_queue *q = data; + + if (q->exit_rq_fn) + q->exit_rq_fn(q, element); + kfree(element); +} + int blk_init_rl(struct request_list *rl, struct request_queue *q, gfp_t gfp_mask) { @@ -629,10 +653,15 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q, init_waitqueue_head(&rl->wait[BLK_RW_SYNC]); init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]); - rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, alloc_request_struct, - free_request_struct, - (void *)(long)q->node, gfp_mask, - q->node); + if (q->cmd_size) { + rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, + alloc_request_size, free_request_size, + q, gfp_mask, q->node); + } else { + rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, + alloc_request_simple, free_request_simple, + q, gfp_mask, q->node); + } if (!rl->rq_pool) return -ENOMEM; @@ -846,12 +875,15 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio); int blk_init_allocated_queue(struct request_queue *q) { - q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0); + q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size); if (!q->fq) return -ENOMEM; + if (q->init_rq_fn && q->init_rq_fn(q, q->fq->flush_rq, GFP_KERNEL)) + goto out_free_flush_queue; + if (blk_init_rl(&q->root_rl, q, GFP_KERNEL)) - goto fail; + goto out_exit_flush_rq; INIT_WORK(&q->timeout_work, blk_timeout_work); q->queue_flags |= QUEUE_FLAG_DEFAULT; @@ -869,13 +901,16 @@ int blk_init_allocated_queue(struct request_queue *q) /* init elevator */ if (elevator_init(q, NULL)) { mutex_unlock(&q->sysfs_lock); - goto fail; + goto out_exit_flush_rq; } mutex_unlock(&q->sysfs_lock); return 0; -fail: +out_exit_flush_rq: + if (q->exit_rq_fn) + q->exit_rq_fn(q, q->fq->flush_rq); +out_free_flush_queue: blk_free_flush_queue(q->fq); wbt_exit(q); return -ENOMEM; diff --git a/block/blk-flush.c b/block/blk-flush.c index 4427896641ac..0a0358e48b76 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -547,11 +547,10 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q, if (!fq) goto fail; - if (q->mq_ops) { + if (q->mq_ops) spin_lock_init(&fq->mq_flush_lock); - rq_sz = round_up(rq_sz + cmd_size, cache_line_size()); - } + rq_sz = round_up(rq_sz + cmd_size, cache_line_size()); fq->flush_rq = kzalloc_node(rq_sz, GFP_KERNEL, node); if (!fq->flush_rq) goto fail_rq; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 1dbce057592d..894f77342fd4 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -814,10 +814,13 @@ static void blk_release_queue(struct kobject *kobj) if (q->queue_tags) __blk_queue_free_tags(q); - if (!q->mq_ops) + if (!q->mq_ops) { + if (q->exit_rq_fn) + q->exit_rq_fn(q, q->fq->flush_rq); blk_free_flush_queue(q->fq); - else + } else { blk_mq_release(q); + } blk_trace_shutdown(q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6b1efc5760ea..461b7cf6af1d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -273,6 +273,8 @@ typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); typedef int (bsg_job_fn) (struct bsg_job *); +typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); +typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { BLK_EH_NOT_HANDLED, @@ -408,6 +410,8 @@ struct request_queue { rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; lld_busy_fn *lld_busy_fn; + init_rq_fn *init_rq_fn; + exit_rq_fn *exit_rq_fn; const struct blk_mq_ops *mq_ops; @@ -577,6 +581,9 @@ struct request_queue { #endif bool mq_sysfs_init_done; + + size_t cmd_size; + void *rq_alloc_data; }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -- cgit v1.2.3-59-g8ed1b From 8ae94eb65be9425af4d57a4f4cfebfdf03081e93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Jan 2017 15:25:02 +0300 Subject: block/bsg: move queue creation into bsg_setup_queue Simply the boilerplate code needed for bsg nodes a bit. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- block/bsg-lib.c | 21 +++++++++++---------- drivers/scsi/scsi_transport_fc.c | 36 ++++++++---------------------------- drivers/scsi/scsi_transport_iscsi.c | 15 ++++----------- include/linux/bsg-lib.h | 5 ++--- 4 files changed, 25 insertions(+), 52 deletions(-) (limited to 'block') diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 9d652a992316..c74acf426840 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -177,7 +177,7 @@ failjob_rls_job: * * Drivers/subsys should pass this to the queue init function. */ -void bsg_request_fn(struct request_queue *q) +static void bsg_request_fn(struct request_queue *q) __releases(q->queue_lock) __acquires(q->queue_lock) { @@ -214,24 +214,24 @@ void bsg_request_fn(struct request_queue *q) put_device(dev); spin_lock_irq(q->queue_lock); } -EXPORT_SYMBOL_GPL(bsg_request_fn); /** * bsg_setup_queue - Create and add the bsg hooks so we can receive requests * @dev: device to attach bsg device to - * @q: request queue setup by caller * @name: device to give bsg device * @job_fn: bsg job handler * @dd_job_size: size of LLD data needed for each job - * - * The caller should have setup the reuqest queue with bsg_request_fn - * as the request_fn. */ -int bsg_setup_queue(struct device *dev, struct request_queue *q, - char *name, bsg_job_fn *job_fn, int dd_job_size) +struct request_queue *bsg_setup_queue(struct device *dev, char *name, + bsg_job_fn *job_fn, int dd_job_size) { + struct request_queue *q; int ret; + q = blk_init_queue(bsg_request_fn, NULL); + if (!q) + return ERR_PTR(-ENOMEM); + q->queuedata = dev; q->bsg_job_size = dd_job_size; q->bsg_job_fn = job_fn; @@ -243,9 +243,10 @@ int bsg_setup_queue(struct device *dev, struct request_queue *q, if (ret) { printk(KERN_ERR "%s: bsg interface failed to " "initialize - register queue\n", dev->kobj.name); - return ret; + blk_cleanup_queue(q); + return ERR_PTR(ret); } - return 0; + return q; } EXPORT_SYMBOL_GPL(bsg_setup_queue); diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index afcedec58d17..13dcb9ba823c 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -3765,7 +3765,6 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host) struct device *dev = &shost->shost_gendev; struct fc_internal *i = to_fc_internal(shost->transportt); struct request_queue *q; - int err; char bsg_name[20]; fc_host->rqst_q = NULL; @@ -3776,24 +3775,14 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host) snprintf(bsg_name, sizeof(bsg_name), "fc_host%d", shost->host_no); - q = blk_init_queue(bsg_request_fn, NULL); - if (!q) { - dev_err(dev, - "fc_host%d: bsg interface failed to initialize - no request queue\n", - shost->host_no); - return -ENOMEM; - } - - __scsi_init_queue(shost, q); - err = bsg_setup_queue(dev, q, bsg_name, fc_bsg_dispatch, - i->f->dd_bsg_size); - if (err) { + q = bsg_setup_queue(dev, bsg_name, fc_bsg_dispatch, i->f->dd_bsg_size); + if (IS_ERR(q)) { dev_err(dev, "fc_host%d: bsg interface failed to initialize - setup queue\n", shost->host_no); - blk_cleanup_queue(q); - return err; + return PTR_ERR(q); } + __scsi_init_queue(shost, q); blk_queue_rq_timed_out(q, fc_bsg_job_timeout); blk_queue_rq_timeout(q, FC_DEFAULT_BSG_TIMEOUT); fc_host->rqst_q = q; @@ -3825,27 +3814,18 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport) struct device *dev = &rport->dev; struct fc_internal *i = to_fc_internal(shost->transportt); struct request_queue *q; - int err; rport->rqst_q = NULL; if (!i->f->bsg_request) return -ENOTSUPP; - q = blk_init_queue(bsg_request_fn, NULL); - if (!q) { - dev_err(dev, "bsg interface failed to initialize - no request queue\n"); - return -ENOMEM; - } - - __scsi_init_queue(shost, q); - err = bsg_setup_queue(dev, q, NULL, fc_bsg_dispatch, i->f->dd_bsg_size); - if (err) { + q = bsg_setup_queue(dev, NULL, fc_bsg_dispatch, i->f->dd_bsg_size); + if (IS_ERR(q)) { dev_err(dev, "failed to setup bsg queue\n"); - blk_cleanup_queue(q); - return err; + return PTR_ERR(q); } - + __scsi_init_queue(shost, q); blk_queue_prep_rq(q, fc_bsg_rport_prep); blk_queue_rq_timed_out(q, fc_bsg_job_timeout); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 04ebe6e65b83..568c9f26a561 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -1537,25 +1537,18 @@ iscsi_bsg_host_add(struct Scsi_Host *shost, struct iscsi_cls_host *ihost) struct iscsi_internal *i = to_iscsi_internal(shost->transportt); struct request_queue *q; char bsg_name[20]; - int ret; if (!i->iscsi_transport->bsg_request) return -ENOTSUPP; snprintf(bsg_name, sizeof(bsg_name), "iscsi_host%d", shost->host_no); - - q = blk_init_queue(bsg_request_fn, NULL); - if (!q) - return -ENOMEM; - - __scsi_init_queue(shost, q); - ret = bsg_setup_queue(dev, q, bsg_name, iscsi_bsg_host_dispatch, 0); - if (ret) { + q = bsg_setup_queue(dev, bsg_name, iscsi_bsg_host_dispatch, 0); + if (IS_ERR(q)) { shost_printk(KERN_ERR, shost, "bsg interface failed to " "initialize - no request queue\n"); - blk_cleanup_queue(q); - return ret; + return PTR_ERR(q); } + __scsi_init_queue(shost, q); ihost->bsg_q = q; return 0; diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 657a718c27d2..e34dde2da0ef 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -66,9 +66,8 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); -int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, - bsg_job_fn *job_fn, int dd_job_size); -void bsg_request_fn(struct request_queue *q); +struct request_queue *bsg_setup_queue(struct device *dev, char *name, + bsg_job_fn *job_fn, int dd_job_size); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); -- cgit v1.2.3-59-g8ed1b From 82ed4db499b8598f16f8871261bff088d6b0597f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 Jan 2017 09:46:29 +0100 Subject: block: split scsi_request out of struct request And require all drivers that want to support BLOCK_PC to allocate it as the first thing of their private data. To support this the legacy IDE and BSG code is switched to set cmd_size on their queues to let the block layer allocate the additional space. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 31 ----------- block/blk-exec.c | 17 ------ block/blk-mq.c | 10 ---- block/bsg-lib.c | 34 ++++++++---- block/bsg.c | 47 ++++++++--------- block/scsi_ioctl.c | 76 ++++++++++++++------------ drivers/ata/libata-scsi.c | 2 +- drivers/block/cciss.c | 28 +++++----- drivers/block/pktcdvd.c | 6 +-- drivers/block/virtio_blk.c | 11 ++-- drivers/cdrom/cdrom.c | 32 +++++------ drivers/ide/ide-atapi.c | 43 ++++++++------- drivers/ide/ide-cd.c | 91 +++++++++++++++----------------- drivers/ide/ide-cd_ioctl.c | 1 + drivers/ide/ide-cd_verbose.c | 6 +-- drivers/ide/ide-devsets.c | 9 ++-- drivers/ide/ide-disk.c | 1 + drivers/ide/ide-eh.c | 2 +- drivers/ide/ide-floppy.c | 4 +- drivers/ide/ide-io.c | 3 +- drivers/ide/ide-ioctls.c | 6 ++- drivers/ide/ide-park.c | 12 +++-- drivers/ide/ide-pm.c | 2 + drivers/ide/ide-probe.c | 36 +++++++++++-- drivers/ide/ide-tape.c | 32 +++++------ drivers/ide/ide-taskfile.c | 1 + drivers/ide/sis5513.c | 2 +- drivers/message/fusion/mptsas.c | 8 +-- drivers/scsi/libfc/fc_lport.c | 2 +- drivers/scsi/libsas/sas_expander.c | 8 +-- drivers/scsi/libsas/sas_host_smp.c | 38 ++++++------- drivers/scsi/mpt3sas/mpt3sas_transport.c | 8 +-- drivers/scsi/osd/osd_initiator.c | 19 +++---- drivers/scsi/osst.c | 15 +++--- drivers/scsi/qla2xxx/qla_bsg.c | 2 +- drivers/scsi/qla2xxx/qla_isr.c | 6 ++- drivers/scsi/qla2xxx/qla_mr.c | 2 +- drivers/scsi/scsi_error.c | 22 ++++---- drivers/scsi/scsi_lib.c | 51 ++++++++++-------- drivers/scsi/scsi_transport_sas.c | 5 ++ drivers/scsi/sd.c | 4 +- drivers/scsi/sg.c | 30 ++++++----- drivers/scsi/st.c | 22 ++++---- drivers/target/target_core_pscsi.c | 11 ++-- fs/nfsd/blocklayout.c | 17 +++--- include/linux/blkdev.h | 13 ----- include/linux/ide.h | 8 ++- include/scsi/scsi_cmnd.h | 2 + include/scsi/scsi_request.h | 30 +++++++++++ 49 files changed, 458 insertions(+), 410 deletions(-) create mode 100644 include/scsi/scsi_request.h (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 0a485ad802c9..f3bc083d4c14 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -132,8 +132,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq) rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); - rq->cmd = rq->__cmd; - rq->cmd_len = BLK_MAX_CDB; rq->tag = -1; rq->internal_tag = -1; rq->start_time = jiffies; @@ -160,8 +158,6 @@ static void req_bio_endio(struct request *rq, struct bio *bio, void blk_dump_rq_flags(struct request *rq, char *msg) { - int bit; - printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg, rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type, (unsigned long long) rq->cmd_flags); @@ -171,13 +167,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg) blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); - - if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { - printk(KERN_INFO " cdb: "); - for (bit = 0; bit < BLK_MAX_CDB; bit++) - printk("%02x ", rq->cmd[bit]); - printk("\n"); - } } EXPORT_SYMBOL(blk_dump_rq_flags); @@ -1315,18 +1304,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) } EXPORT_SYMBOL(blk_get_request); -/** - * blk_rq_set_block_pc - initialize a request to type BLOCK_PC - * @rq: request to be initialized - * - */ -void blk_rq_set_block_pc(struct request *rq) -{ - rq->cmd_type = REQ_TYPE_BLOCK_PC; - memset(rq->__cmd, 0, sizeof(rq->__cmd)); -} -EXPORT_SYMBOL(blk_rq_set_block_pc); - /** * blk_requeue_request - put a request back on queue * @q: request queue where request should be inserted @@ -2459,14 +2436,6 @@ void blk_start_request(struct request *req) wbt_issue(req->q->rq_wb, &req->issue_stat); } - /* - * We are now handing the request to the hardware, initialize - * resid_len to full count and add the timeout handler. - */ - req->resid_len = blk_rq_bytes(req); - if (unlikely(blk_bidi_rq(req))) - req->next_rq->resid_len = blk_rq_bytes(req->next_rq); - BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags)); blk_add_timer(req); } diff --git a/block/blk-exec.c b/block/blk-exec.c index ed1f10165268..ed51800f4b44 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -11,11 +11,6 @@ #include "blk.h" #include "blk-mq-sched.h" -/* - * for max sense size - */ -#include - /** * blk_end_sync_rq - executes a completion event on a request * @rq: request to complete @@ -101,16 +96,9 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk, struct request *rq, int at_head) { DECLARE_COMPLETION_ONSTACK(wait); - char sense[SCSI_SENSE_BUFFERSIZE]; int err = 0; unsigned long hang_check; - if (!rq->sense) { - memset(sense, 0, sizeof(sense)); - rq->sense = sense; - rq->sense_len = 0; - } - rq->end_io_data = &wait; blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq); @@ -124,11 +112,6 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk, if (rq->errors) err = -EIO; - if (rq->sense == sense) { - rq->sense = NULL; - rq->sense_len = 0; - } - return err; } EXPORT_SYMBOL(blk_execute_rq); diff --git a/block/blk-mq.c b/block/blk-mq.c index 60dac10228fe..3d76e860f126 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -199,13 +199,7 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, rq->special = NULL; /* tag was already set */ rq->errors = 0; - - rq->cmd = rq->__cmd; - rq->extra_len = 0; - rq->sense_len = 0; - rq->resid_len = 0; - rq->sense = NULL; INIT_LIST_HEAD(&rq->timeout_list); rq->timeout = 0; @@ -487,10 +481,6 @@ void blk_mq_start_request(struct request *rq) trace_block_rq_issue(q, rq); - rq->resid_len = blk_rq_bytes(rq); - if (unlikely(blk_bidi_rq(rq))) - rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq); - if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { blk_stat_set_issue_time(&rq->issue_stat); rq->rq_flags |= RQF_STATS; diff --git a/block/bsg-lib.c b/block/bsg-lib.c index c74acf426840..cd15f9dbb147 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -71,22 +71,24 @@ void bsg_job_done(struct bsg_job *job, int result, { struct request *req = job->req; struct request *rsp = req->next_rq; + struct scsi_request *rq = scsi_req(req); int err; err = job->req->errors = result; if (err < 0) /* we're only returning the result field in the reply */ - job->req->sense_len = sizeof(u32); + rq->sense_len = sizeof(u32); else - job->req->sense_len = job->reply_len; + rq->sense_len = job->reply_len; /* we assume all request payload was transferred, residual == 0 */ - req->resid_len = 0; + rq->resid_len = 0; if (rsp) { - WARN_ON(reply_payload_rcv_len > rsp->resid_len); + WARN_ON(reply_payload_rcv_len > scsi_req(rsp)->resid_len); /* set reply (bidi) residual */ - rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len); + scsi_req(rsp)->resid_len -= + min(reply_payload_rcv_len, scsi_req(rsp)->resid_len); } blk_complete_request(req); } @@ -113,6 +115,7 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req) if (!buf->sg_list) return -ENOMEM; sg_init_table(buf->sg_list, req->nr_phys_segments); + scsi_req(req)->resid_len = blk_rq_bytes(req); buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list); buf->payload_len = blk_rq_bytes(req); return 0; @@ -127,6 +130,7 @@ static int bsg_create_job(struct device *dev, struct request *req) { struct request *rsp = req->next_rq; struct request_queue *q = req->q; + struct scsi_request *rq = scsi_req(req); struct bsg_job *job; int ret; @@ -140,9 +144,9 @@ static int bsg_create_job(struct device *dev, struct request *req) job->req = req; if (q->bsg_job_size) job->dd_data = (void *)&job[1]; - job->request = req->cmd; - job->request_len = req->cmd_len; - job->reply = req->sense; + job->request = rq->cmd; + job->request_len = rq->cmd_len; + job->reply = rq->sense; job->reply_len = SCSI_SENSE_BUFFERSIZE; /* Size of sense buffer * allocated */ if (req->bio) { @@ -228,9 +232,15 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name, struct request_queue *q; int ret; - q = blk_init_queue(bsg_request_fn, NULL); + q = blk_alloc_queue(GFP_KERNEL); if (!q) return ERR_PTR(-ENOMEM); + q->cmd_size = sizeof(struct scsi_request); + q->request_fn = bsg_request_fn; + + ret = blk_init_allocated_queue(q); + if (ret) + goto out_cleanup_queue; q->queuedata = dev; q->bsg_job_size = dd_job_size; @@ -243,10 +253,12 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name, if (ret) { printk(KERN_ERR "%s: bsg interface failed to " "initialize - register queue\n", dev->kobj.name); - blk_cleanup_queue(q); - return ERR_PTR(ret); + goto out_cleanup_queue; } return q; +out_cleanup_queue: + blk_cleanup_queue(q); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(bsg_setup_queue); diff --git a/block/bsg.c b/block/bsg.c index a57046de2f07..e34c3320956c 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -85,7 +85,6 @@ struct bsg_command { struct bio *bidi_bio; int err; struct sg_io_v4 hdr; - char sense[SCSI_SENSE_BUFFERSIZE]; }; static void bsg_free_command(struct bsg_command *bc) @@ -140,18 +139,20 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, struct sg_io_v4 *hdr, struct bsg_device *bd, fmode_t has_write_perm) { + struct scsi_request *req = scsi_req(rq); + if (hdr->request_len > BLK_MAX_CDB) { - rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL); - if (!rq->cmd) + req->cmd = kzalloc(hdr->request_len, GFP_KERNEL); + if (!req->cmd) return -ENOMEM; } - if (copy_from_user(rq->cmd, (void __user *)(unsigned long)hdr->request, + if (copy_from_user(req->cmd, (void __user *)(unsigned long)hdr->request, hdr->request_len)) return -EFAULT; if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) { - if (blk_verify_command(rq->cmd, has_write_perm)) + if (blk_verify_command(req->cmd, has_write_perm)) return -EPERM; } else if (!capable(CAP_SYS_RAWIO)) return -EPERM; @@ -159,7 +160,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, /* * fill in request structure */ - rq->cmd_len = hdr->request_len; + req->cmd_len = hdr->request_len; rq->timeout = msecs_to_jiffies(hdr->timeout); if (!rq->timeout) @@ -205,8 +206,7 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw) * map sg_io_v4 to a request. */ static struct request * -bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm, - u8 *sense) +bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm) { struct request_queue *q = bd->queue; struct request *rq, *next_rq = NULL; @@ -236,7 +236,7 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm, rq = blk_get_request(q, rw, GFP_KERNEL); if (IS_ERR(rq)) return rq; - blk_rq_set_block_pc(rq); + scsi_req_init(rq); ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm); if (ret) @@ -280,13 +280,9 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm, goto out; } - rq->sense = sense; - rq->sense_len = 0; - return rq; out: - if (rq->cmd != rq->__cmd) - kfree(rq->cmd); + scsi_req_free_cmd(scsi_req(rq)); blk_put_request(rq); if (next_rq) { blk_rq_unmap_user(next_rq->bio); @@ -393,6 +389,7 @@ static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd) static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr, struct bio *bio, struct bio *bidi_bio) { + struct scsi_request *req = scsi_req(rq); int ret = 0; dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors); @@ -407,12 +404,12 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr, hdr->info |= SG_INFO_CHECK; hdr->response_len = 0; - if (rq->sense_len && hdr->response) { + if (req->sense_len && hdr->response) { int len = min_t(unsigned int, hdr->max_response_len, - rq->sense_len); + req->sense_len); ret = copy_to_user((void __user *)(unsigned long)hdr->response, - rq->sense, len); + req->sense, len); if (!ret) hdr->response_len = len; else @@ -420,14 +417,14 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr, } if (rq->next_rq) { - hdr->dout_resid = rq->resid_len; - hdr->din_resid = rq->next_rq->resid_len; + hdr->dout_resid = req->resid_len; + hdr->din_resid = scsi_req(rq->next_rq)->resid_len; blk_rq_unmap_user(bidi_bio); blk_put_request(rq->next_rq); } else if (rq_data_dir(rq) == READ) - hdr->din_resid = rq->resid_len; + hdr->din_resid = req->resid_len; else - hdr->dout_resid = rq->resid_len; + hdr->dout_resid = req->resid_len; /* * If the request generated a negative error number, return it @@ -439,8 +436,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr, ret = rq->errors; blk_rq_unmap_user(bio); - if (rq->cmd != rq->__cmd) - kfree(rq->cmd); + scsi_req_free_cmd(req); blk_put_request(rq); return ret; @@ -625,7 +621,7 @@ static int __bsg_write(struct bsg_device *bd, const char __user *buf, /* * get a request, fill in the blanks, and add to request queue */ - rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm, bc->sense); + rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm); if (IS_ERR(rq)) { ret = PTR_ERR(rq); rq = NULL; @@ -911,12 +907,11 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct bio *bio, *bidi_bio = NULL; struct sg_io_v4 hdr; int at_head; - u8 sense[SCSI_SENSE_BUFFERSIZE]; if (copy_from_user(&hdr, uarg, sizeof(hdr))) return -EFAULT; - rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE, sense); + rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE); if (IS_ERR(rq)) return PTR_ERR(rq); diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index c2b64923ab66..7edf44f25e08 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -230,15 +230,17 @@ EXPORT_SYMBOL(blk_verify_command); static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, struct sg_io_hdr *hdr, fmode_t mode) { - if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len)) + struct scsi_request *req = scsi_req(rq); + + if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len)) return -EFAULT; - if (blk_verify_command(rq->cmd, mode & FMODE_WRITE)) + if (blk_verify_command(req->cmd, mode & FMODE_WRITE)) return -EPERM; /* * fill in request structure */ - rq->cmd_len = hdr->cmd_len; + req->cmd_len = hdr->cmd_len; rq->timeout = msecs_to_jiffies(hdr->timeout); if (!rq->timeout) @@ -254,6 +256,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, struct bio *bio) { + struct scsi_request *req = scsi_req(rq); int r, ret = 0; /* @@ -267,13 +270,13 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, hdr->info = 0; if (hdr->masked_status || hdr->host_status || hdr->driver_status) hdr->info |= SG_INFO_CHECK; - hdr->resid = rq->resid_len; + hdr->resid = req->resid_len; hdr->sb_len_wr = 0; - if (rq->sense_len && hdr->sbp) { - int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len); + if (req->sense_len && hdr->sbp) { + int len = min((unsigned int) hdr->mx_sb_len, req->sense_len); - if (!copy_to_user(hdr->sbp, rq->sense, len)) + if (!copy_to_user(hdr->sbp, req->sense, len)) hdr->sb_len_wr = len; else ret = -EFAULT; @@ -294,7 +297,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, int writing = 0; int at_head = 0; struct request *rq; - char sense[SCSI_SENSE_BUFFERSIZE]; + struct scsi_request *req; struct bio *bio; if (hdr->interface_id != 'S') @@ -321,11 +324,12 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL); if (IS_ERR(rq)) return PTR_ERR(rq); - blk_rq_set_block_pc(rq); + req = scsi_req(rq); + scsi_req_init(rq); if (hdr->cmd_len > BLK_MAX_CDB) { - rq->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL); - if (!rq->cmd) + req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL); + if (!req->cmd) goto out_put_request; } @@ -357,9 +361,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, goto out_free_cdb; bio = rq->bio; - memset(sense, 0, sizeof(sense)); - rq->sense = sense; - rq->sense_len = 0; rq->retries = 0; start_time = jiffies; @@ -375,8 +376,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, ret = blk_complete_sghdr_rq(rq, hdr, bio); out_free_cdb: - if (rq->cmd != rq->__cmd) - kfree(rq->cmd); + scsi_req_free_cmd(req); out_put_request: blk_put_request(rq); return ret; @@ -420,9 +420,10 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, struct scsi_ioctl_command __user *sic) { struct request *rq; + struct scsi_request *req; int err; unsigned int in_len, out_len, bytes, opcode, cmdlen; - char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE]; + char *buffer = NULL; if (!sic) return -EINVAL; @@ -452,7 +453,8 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, err = PTR_ERR(rq); goto error_free_buffer; } - blk_rq_set_block_pc(rq); + req = scsi_req(rq); + scsi_req_init(rq); cmdlen = COMMAND_SIZE(opcode); @@ -460,14 +462,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, * get command and data to send to device, if any */ err = -EFAULT; - rq->cmd_len = cmdlen; - if (copy_from_user(rq->cmd, sic->data, cmdlen)) + req->cmd_len = cmdlen; + if (copy_from_user(req->cmd, sic->data, cmdlen)) goto error; if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len)) goto error; - err = blk_verify_command(rq->cmd, mode & FMODE_WRITE); + err = blk_verify_command(req->cmd, mode & FMODE_WRITE); if (err) goto error; @@ -503,18 +505,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, goto error; } - memset(sense, 0, sizeof(sense)); - rq->sense = sense; - rq->sense_len = 0; - blk_execute_rq(q, disk, rq, 0); err = rq->errors & 0xff; /* only 8 bit SCSI status */ if (err) { - if (rq->sense_len && rq->sense) { - bytes = (OMAX_SB_LEN > rq->sense_len) ? - rq->sense_len : OMAX_SB_LEN; - if (copy_to_user(sic->data, rq->sense, bytes)) + if (req->sense_len && req->sense) { + bytes = (OMAX_SB_LEN > req->sense_len) ? + req->sense_len : OMAX_SB_LEN; + if (copy_to_user(sic->data, req->sense, bytes)) err = -EFAULT; } } else { @@ -542,11 +540,11 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, rq = blk_get_request(q, WRITE, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); - blk_rq_set_block_pc(rq); + scsi_req_init(rq); rq->timeout = BLK_DEFAULT_SG_TIMEOUT; - rq->cmd[0] = cmd; - rq->cmd[4] = data; - rq->cmd_len = 6; + scsi_req(rq)->cmd[0] = cmd; + scsi_req(rq)->cmd[4] = data; + scsi_req(rq)->cmd_len = 6; err = blk_execute_rq(q, bd_disk, rq, 0); blk_put_request(rq); @@ -743,6 +741,18 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode, } EXPORT_SYMBOL(scsi_cmd_blk_ioctl); +void scsi_req_init(struct request *rq) +{ + struct scsi_request *req = scsi_req(rq); + + rq->cmd_type = REQ_TYPE_BLOCK_PC; + memset(req->__cmd, 0, sizeof(req->__cmd)); + req->cmd = req->__cmd; + req->cmd_len = BLK_MAX_CDB; + req->sense_len = 0; +} +EXPORT_SYMBOL(scsi_req_init); + static int __init blk_scsi_ioctl_init(void) { blk_set_cmd_filter_defaults(&blk_default_cmd_filter); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 1f863e757ee4..6abd73975f87 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1271,7 +1271,7 @@ static int atapi_drain_needed(struct request *rq) if (!blk_rq_bytes(rq) || op_is_write(req_op(rq))) return 0; - return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC; + return atapi_cmd_type(scsi_req(rq)->cmd[0]) == ATAPI_MISC; } static int ata_scsi_dev_config(struct scsi_device *sdev, diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index e5c5b8eb14a9..b93bb73b49d2 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include #include @@ -1854,7 +1855,7 @@ static void cciss_softirq_done(struct request *rq) /* set the residual count for pc requests */ if (rq->cmd_type == REQ_TYPE_BLOCK_PC) - rq->resid_len = c->err_info->ResidualCnt; + scsi_req(rq)->resid_len = c->err_info->ResidualCnt; blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO); @@ -1941,9 +1942,16 @@ static void cciss_get_serial_no(ctlr_info_t *h, int logvol, static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk, int drv_index) { - disk->queue = blk_init_queue(do_cciss_request, &h->lock); + disk->queue = blk_alloc_queue(GFP_KERNEL); if (!disk->queue) goto init_queue_failure; + + disk->queue->cmd_size = sizeof(struct scsi_request); + disk->queue->request_fn = do_cciss_request; + disk->queue->queue_lock = &h->lock; + if (blk_init_allocated_queue(disk->queue) < 0) + goto cleanup_queue; + sprintf(disk->disk_name, "cciss/c%dd%d", h->ctlr, drv_index); disk->major = h->major; disk->first_minor = drv_index << NWD_SHIFT; @@ -3111,15 +3119,7 @@ static inline int evaluate_target_status(ctlr_info_t *h, return error_value; } - /* SG_IO or similar, copy sense data back */ - if (cmd->rq->sense) { - if (cmd->rq->sense_len > cmd->err_info->SenseLen) - cmd->rq->sense_len = cmd->err_info->SenseLen; - memcpy(cmd->rq->sense, cmd->err_info->SenseInfo, - cmd->rq->sense_len); - } else - cmd->rq->sense_len = 0; - + scsi_req(cmd->rq)->sense_len = cmd->err_info->SenseLen; return error_value; } @@ -3150,7 +3150,6 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, dev_warn(&h->pdev->dev, "cmd %p has" " completed with data underrun " "reported\n", cmd); - cmd->rq->resid_len = cmd->err_info->ResidualCnt; } break; case CMD_DATA_OVERRUN: @@ -3426,8 +3425,9 @@ static void do_cciss_request(struct request_queue *q) c->Request.CDB[14] = c->Request.CDB[15] = 0; } } else if (creq->cmd_type == REQ_TYPE_BLOCK_PC) { - c->Request.CDBLen = creq->cmd_len; - memcpy(c->Request.CDB, creq->cmd, BLK_MAX_CDB); + c->Request.CDBLen = scsi_req(creq)->cmd_len; + memcpy(c->Request.CDB, scsi_req(creq)->cmd, BLK_MAX_CDB); + scsi_req(creq)->sense = c->err_info->SenseInfo; } else { dev_warn(&h->pdev->dev, "bad request type %d\n", creq->cmd_type); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 1b94c1ca5c5f..918a92ccd0c0 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -707,7 +707,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * WRITE : READ, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); - blk_rq_set_block_pc(rq); + scsi_req_init(rq); if (cgc->buflen) { ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen, @@ -716,8 +716,8 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * goto out; } - rq->cmd_len = COMMAND_SIZE(cgc->cmd[0]); - memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE); + scsi_req(rq)->cmd_len = COMMAND_SIZE(cgc->cmd[0]); + memcpy(scsi_req(rq)->cmd, cgc->cmd, CDROM_PACKET_SIZE); rq->timeout = 60*HZ; if (cgc->quiet) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 10332c24f961..3027d2efc5d8 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -52,6 +52,7 @@ struct virtio_blk { }; struct virtblk_req { + struct scsi_request sreq; /* for SCSI passthrough */ struct request *req; struct virtio_blk_outhdr out_hdr; struct virtio_scsi_inhdr in_hdr; @@ -91,7 +92,7 @@ static int __virtblk_add_req(struct virtqueue *vq, * inhdr with additional status information. */ if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) { - sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len); + sg_init_one(&cmd, vbr->sreq.cmd, vbr->sreq.cmd_len); sgs[num_out++] = &cmd; } @@ -103,7 +104,6 @@ static int __virtblk_add_req(struct virtqueue *vq, } if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) { - memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE); sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE); sgs[num_out + num_in++] = &sense; sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr)); @@ -123,8 +123,10 @@ static inline void virtblk_request_done(struct request *req) int error = virtblk_result(vbr); if (req->cmd_type == REQ_TYPE_BLOCK_PC) { - req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual); - req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len); + scsi_req(req)->resid_len = + virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual); + vbr->sreq.sense_len = + virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len); req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors); } else if (req->cmd_type == REQ_TYPE_DRV_PRIV) { req->errors = (error != 0); @@ -538,6 +540,7 @@ static int virtblk_init_request(void *data, struct request *rq, struct virtio_blk *vblk = data; struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq); + vbr->sreq.sense = vbr->sense; sg_init_table(vbr->sg, vblk->sg_elems); return 0; } diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 59cca72647a6..36f5237a8a69 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -281,8 +281,8 @@ #include #include #include - #include +#include /* used to tell the module to turn on full debugging messages */ static bool debug; @@ -2172,6 +2172,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, { struct request_queue *q = cdi->disk->queue; struct request *rq; + struct scsi_request *req; struct bio *bio; unsigned int len; int nr, ret = 0; @@ -2195,7 +2196,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, ret = PTR_ERR(rq); break; } - blk_rq_set_block_pc(rq); + req = scsi_req(rq); + scsi_req_init(rq); ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL); if (ret) { @@ -2203,23 +2205,23 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, break; } - rq->cmd[0] = GPCMD_READ_CD; - rq->cmd[1] = 1 << 2; - rq->cmd[2] = (lba >> 24) & 0xff; - rq->cmd[3] = (lba >> 16) & 0xff; - rq->cmd[4] = (lba >> 8) & 0xff; - rq->cmd[5] = lba & 0xff; - rq->cmd[6] = (nr >> 16) & 0xff; - rq->cmd[7] = (nr >> 8) & 0xff; - rq->cmd[8] = nr & 0xff; - rq->cmd[9] = 0xf8; - - rq->cmd_len = 12; + req->cmd[0] = GPCMD_READ_CD; + req->cmd[1] = 1 << 2; + req->cmd[2] = (lba >> 24) & 0xff; + req->cmd[3] = (lba >> 16) & 0xff; + req->cmd[4] = (lba >> 8) & 0xff; + req->cmd[5] = lba & 0xff; + req->cmd[6] = (nr >> 16) & 0xff; + req->cmd[7] = (nr >> 8) & 0xff; + req->cmd[8] = nr & 0xff; + req->cmd[9] = 0xf8; + + req->cmd_len = 12; rq->timeout = 60 * HZ; bio = rq->bio; if (blk_execute_rq(q, cdi->disk, rq, 0)) { - struct request_sense *s = rq->sense; + struct request_sense *s = req->sense; ret = -EIO; cdi->last_sense = s->sense_key; } diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index f90ea221f7f2..7c826ecbd276 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -93,6 +93,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk, int error; rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->special = (char *)pc; @@ -103,9 +104,9 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk, goto put_req; } - memcpy(rq->cmd, pc->c, 12); + memcpy(scsi_req(rq)->cmd, pc->c, 12); if (drive->media == ide_tape) - rq->cmd[13] = REQ_IDETAPE_PC1; + scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1; error = blk_execute_rq(drive->queue, disk, rq, 0); put_req: blk_put_request(rq); @@ -171,7 +172,8 @@ EXPORT_SYMBOL_GPL(ide_create_request_sense_cmd); void ide_prep_sense(ide_drive_t *drive, struct request *rq) { struct request_sense *sense = &drive->sense_data; - struct request *sense_rq = &drive->sense_rq; + struct request *sense_rq = drive->sense_rq; + struct scsi_request *req = scsi_req(sense_rq); unsigned int cmd_len, sense_len; int err; @@ -197,6 +199,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) memset(sense, 0, sizeof(*sense)); blk_rq_init(rq->q, sense_rq); + scsi_req_init(sense_rq); err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len, GFP_NOIO); @@ -208,13 +211,13 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) } sense_rq->rq_disk = rq->rq_disk; - sense_rq->cmd[0] = GPCMD_REQUEST_SENSE; - sense_rq->cmd[4] = cmd_len; sense_rq->cmd_type = REQ_TYPE_ATA_SENSE; sense_rq->rq_flags |= RQF_PREEMPT; + req->cmd[0] = GPCMD_REQUEST_SENSE; + req->cmd[4] = cmd_len; if (drive->media == ide_tape) - sense_rq->cmd[13] = REQ_IDETAPE_PC1; + req->cmd[13] = REQ_IDETAPE_PC1; drive->sense_rq_armed = true; } @@ -229,12 +232,12 @@ int ide_queue_sense_rq(ide_drive_t *drive, void *special) return -ENOMEM; } - drive->sense_rq.special = special; + drive->sense_rq->special = special; drive->sense_rq_armed = false; drive->hwif->rq = NULL; - elv_add_request(drive->queue, &drive->sense_rq, ELEVATOR_INSERT_FRONT); + elv_add_request(drive->queue, drive->sense_rq, ELEVATOR_INSERT_FRONT); return 0; } EXPORT_SYMBOL_GPL(ide_queue_sense_rq); @@ -247,14 +250,14 @@ EXPORT_SYMBOL_GPL(ide_queue_sense_rq); void ide_retry_pc(ide_drive_t *drive) { struct request *failed_rq = drive->hwif->rq; - struct request *sense_rq = &drive->sense_rq; + struct request *sense_rq = drive->sense_rq; struct ide_atapi_pc *pc = &drive->request_sense_pc; (void)ide_read_error(drive); /* init pc from sense_rq */ ide_init_pc(pc); - memcpy(pc->c, sense_rq->cmd, 12); + memcpy(pc->c, scsi_req(sense_rq)->cmd, 12); if (drive->media == ide_tape) drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC; @@ -286,7 +289,7 @@ int ide_cd_expiry(ide_drive_t *drive) * commands/drives support that. Let ide_timer_expiry keep polling us * for these. */ - switch (rq->cmd[0]) { + switch (scsi_req(rq)->cmd[0]) { case GPCMD_BLANK: case GPCMD_FORMAT_UNIT: case GPCMD_RESERVE_RZONE_TRACK: @@ -297,7 +300,7 @@ int ide_cd_expiry(ide_drive_t *drive) default: if (!(rq->rq_flags & RQF_QUIET)) printk(KERN_INFO PFX "cmd 0x%x timed out\n", - rq->cmd[0]); + scsi_req(rq)->cmd[0]); wait = 0; break; } @@ -420,7 +423,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) ? "write" : "read"); pc->flags |= PC_FLAG_DMA_ERROR; } else - rq->resid_len = 0; + scsi_req(rq)->resid_len = 0; debug_log("%s: DMA finished\n", drive->name); } @@ -436,7 +439,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) local_irq_enable_in_hardirq(); if (drive->media == ide_tape && - (stat & ATA_ERR) && rq->cmd[0] == REQUEST_SENSE) + (stat & ATA_ERR) && scsi_req(rq)->cmd[0] == REQUEST_SENSE) stat &= ~ATA_ERR; if ((stat & ATA_ERR) || (pc->flags & PC_FLAG_DMA_ERROR)) { @@ -446,7 +449,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) if (drive->media != ide_tape) pc->rq->errors++; - if (rq->cmd[0] == REQUEST_SENSE) { + if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) { printk(KERN_ERR PFX "%s: I/O error in request " "sense command\n", drive->name); return ide_do_reset(drive); @@ -512,7 +515,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) ide_pio_bytes(drive, cmd, write, done); /* Update transferred byte count */ - rq->resid_len -= done; + scsi_req(rq)->resid_len -= done; bcount -= done; @@ -520,7 +523,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) ide_pad_transfer(drive, write, bcount); debug_log("[cmd %x] transferred %d bytes, padded %d bytes, resid: %u\n", - rq->cmd[0], done, bcount, rq->resid_len); + rq->cmd[0], done, bcount, scsi_req(rq)->resid_len); /* And set the interrupt handler again */ ide_set_handler(drive, ide_pc_intr, timeout); @@ -603,7 +606,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive) if (dev_is_idecd(drive)) { /* ATAPI commands get padded out to 12 bytes minimum */ - cmd_len = COMMAND_SIZE(rq->cmd[0]); + cmd_len = COMMAND_SIZE(scsi_req(rq)->cmd[0]); if (cmd_len < ATAPI_MIN_CDB_BYTES) cmd_len = ATAPI_MIN_CDB_BYTES; @@ -650,7 +653,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive) /* Send the actual packet */ if ((drive->atapi_flags & IDE_AFLAG_ZIP_DRIVE) == 0) - hwif->tp_ops->output_data(drive, NULL, rq->cmd, cmd_len); + hwif->tp_ops->output_data(drive, NULL, scsi_req(rq)->cmd, cmd_len); /* Begin DMA, if necessary */ if (dev_is_idecd(drive)) { @@ -695,7 +698,7 @@ ide_startstop_t ide_issue_pc(ide_drive_t *drive, struct ide_cmd *cmd) bytes, 63 * 1024)); /* We haven't transferred any data yet */ - rq->resid_len = bcount; + scsi_req(rq)->resid_len = bcount; if (pc->flags & PC_FLAG_DMA_ERROR) { pc->flags &= ~PC_FLAG_DMA_ERROR; diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 9cbd217bc0c9..6eb98725e194 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -121,7 +121,7 @@ static int cdrom_log_sense(ide_drive_t *drive, struct request *rq) * don't log START_STOP unit with LoEj set, since we cannot * reliably check if drive can auto-close */ - if (rq->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24) + if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24) break; log = 1; break; @@ -163,7 +163,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive, * toc has not been recorded yet, it will fail with 05/24/00 (which is a * confusing error) */ - if (failed_command && failed_command->cmd[0] == GPCMD_READ_TOC_PMA_ATIP) + if (failed_command && scsi_req(failed_command)->cmd[0] == GPCMD_READ_TOC_PMA_ATIP) if (sense->sense_key == 0x05 && sense->asc == 0x24) return; @@ -219,15 +219,12 @@ static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq) void *sense = bio_data(rq->bio); if (failed) { - if (failed->sense) { - /* - * Sense is always read into drive->sense_data. - * Copy back if the failed request has its - * sense pointer set. - */ - memcpy(failed->sense, sense, 18); - failed->sense_len = rq->sense_len; - } + /* + * Sense is always read into drive->sense_data, copy back to the + * original request. + */ + memcpy(scsi_req(failed)->sense, sense, 18); + scsi_req(failed)->sense_len = scsi_req(rq)->sense_len; cdrom_analyze_sense_data(drive, failed); if (ide_end_rq(drive, failed, -EIO, blk_rq_bytes(failed))) @@ -338,7 +335,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * * cdrom_log_sense() knows this! */ - if (rq->cmd[0] == GPCMD_START_STOP_UNIT) + if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT) break; /* fall-through */ case DATA_PROTECT: @@ -414,7 +411,7 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd) * Some of the trailing request sense fields are optional, * and some drives don't send them. Sigh. */ - if (rq->cmd[0] == GPCMD_REQUEST_SENSE && + if (scsi_req(rq)->cmd[0] == GPCMD_REQUEST_SENSE && cmd->nleft > 0 && cmd->nleft <= 5) cmd->nleft = 0; } @@ -425,12 +422,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, req_flags_t rq_flags) { struct cdrom_info *info = drive->driver_data; - struct request_sense local_sense; int retries = 10; - req_flags_t flags = 0; - - if (!sense) - sense = &local_sense; + bool failed; ide_debug_log(IDE_DBG_PC, "cmd[0]: 0x%x, write: 0x%x, timeout: %d, " "rq_flags: 0x%x", @@ -440,12 +433,12 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, do { struct request *rq; int error; + bool delay = false; rq = blk_get_request(drive->queue, write, __GFP_RECLAIM); - - memcpy(rq->cmd, cmd, BLK_MAX_CDB); + scsi_req_init(rq); + memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB); rq->cmd_type = REQ_TYPE_ATA_PC; - rq->sense = sense; rq->rq_flags |= rq_flags; rq->timeout = timeout; if (buffer) { @@ -460,21 +453,21 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, error = blk_execute_rq(drive->queue, info->disk, rq, 0); if (buffer) - *bufflen = rq->resid_len; - - flags = rq->rq_flags; - blk_put_request(rq); + *bufflen = scsi_req(rq)->resid_len; + if (sense) + memcpy(sense, scsi_req(rq)->sense, sizeof(*sense)); /* * FIXME: we should probably abort/retry or something in case of * failure. */ - if (flags & RQF_FAILED) { + failed = (rq->rq_flags & RQF_FAILED) != 0; + if (failed) { /* * The request failed. Retry if it was due to a unit * attention status (usually means media was changed). */ - struct request_sense *reqbuf = sense; + struct request_sense *reqbuf = scsi_req(rq)->sense; if (reqbuf->sense_key == UNIT_ATTENTION) cdrom_saw_media_change(drive); @@ -485,19 +478,20 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, * a disk. Retry, but wait a little to give * the drive time to complete the load. */ - ssleep(2); + delay = true; } else { /* otherwise, don't retry */ retries = 0; } --retries; } - - /* end of retry loop */ - } while ((flags & RQF_FAILED) && retries >= 0); + blk_put_request(rq); + if (delay) + ssleep(2); + } while (failed && retries >= 0); /* return an error if the command failed */ - return (flags & RQF_FAILED) ? -EIO : 0; + return failed ? -EIO : 0; } /* @@ -636,7 +630,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) len -= blen; if (sense && write == 0) - rq->sense_len += blen; + scsi_req(rq)->sense_len += blen; } /* pad, if necessary */ @@ -664,7 +658,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) out_end: if (rq->cmd_type == REQ_TYPE_BLOCK_PC && rc == 0) { - rq->resid_len = 0; + scsi_req(rq)->resid_len = 0; blk_end_request_all(rq, 0); hwif->rq = NULL; } else { @@ -685,9 +679,9 @@ out_end: /* make sure it's fully ended */ if (rq->cmd_type != REQ_TYPE_FS) { - rq->resid_len -= cmd->nbytes - cmd->nleft; + scsi_req(rq)->resid_len -= cmd->nbytes - cmd->nleft; if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE)) - rq->resid_len += cmd->last_xfer_len; + scsi_req(rq)->resid_len += cmd->last_xfer_len; } ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq)); @@ -1312,28 +1306,29 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq) int hard_sect = queue_logical_block_size(q); long block = (long)blk_rq_pos(rq) / (hard_sect >> 9); unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9); + struct scsi_request *req = scsi_req(rq); - memset(rq->cmd, 0, BLK_MAX_CDB); + memset(req->cmd, 0, BLK_MAX_CDB); if (rq_data_dir(rq) == READ) - rq->cmd[0] = GPCMD_READ_10; + req->cmd[0] = GPCMD_READ_10; else - rq->cmd[0] = GPCMD_WRITE_10; + req->cmd[0] = GPCMD_WRITE_10; /* * fill in lba */ - rq->cmd[2] = (block >> 24) & 0xff; - rq->cmd[3] = (block >> 16) & 0xff; - rq->cmd[4] = (block >> 8) & 0xff; - rq->cmd[5] = block & 0xff; + req->cmd[2] = (block >> 24) & 0xff; + req->cmd[3] = (block >> 16) & 0xff; + req->cmd[4] = (block >> 8) & 0xff; + req->cmd[5] = block & 0xff; /* * and transfer length */ - rq->cmd[7] = (blocks >> 8) & 0xff; - rq->cmd[8] = blocks & 0xff; - rq->cmd_len = 10; + req->cmd[7] = (blocks >> 8) & 0xff; + req->cmd[8] = blocks & 0xff; + req->cmd_len = 10; return BLKPREP_OK; } @@ -1343,7 +1338,7 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq) */ static int ide_cdrom_prep_pc(struct request *rq) { - u8 *c = rq->cmd; + u8 *c = scsi_req(rq)->cmd; /* transform 6-byte read/write commands to the 10-byte version */ if (c[0] == READ_6 || c[0] == WRITE_6) { @@ -1354,7 +1349,7 @@ static int ide_cdrom_prep_pc(struct request *rq) c[2] = 0; c[1] &= 0xe0; c[0] += (READ_10 - READ_6); - rq->cmd_len = 10; + scsi_req(rq)->cmd_len = 10; return BLKPREP_OK; } diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index f085e3a2e1d6..da0aa0153fb1 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -304,6 +304,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi) int ret; rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->rq_flags = RQF_QUIET; ret = blk_execute_rq(drive->queue, cd->disk, rq, 0); diff --git a/drivers/ide/ide-cd_verbose.c b/drivers/ide/ide-cd_verbose.c index f079ca2f260b..58a6feb74c02 100644 --- a/drivers/ide/ide-cd_verbose.c +++ b/drivers/ide/ide-cd_verbose.c @@ -315,12 +315,12 @@ void ide_cd_log_error(const char *name, struct request *failed_command, while (hi > lo) { mid = (lo + hi) / 2; if (packet_command_texts[mid].packet_command == - failed_command->cmd[0]) { + scsi_req(failed_command)->cmd[0]) { s = packet_command_texts[mid].text; break; } if (packet_command_texts[mid].packet_command > - failed_command->cmd[0]) + scsi_req(failed_command)->cmd[0]) hi = mid; else lo = mid + 1; @@ -329,7 +329,7 @@ void ide_cd_log_error(const char *name, struct request *failed_command, printk(KERN_ERR " The failed \"%s\" packet command " "was: \n \"", s); for (i = 0; i < BLK_MAX_CDB; i++) - printk(KERN_CONT "%02x ", failed_command->cmd[i]); + printk(KERN_CONT "%02x ", scsi_req(failed_command)->cmd[i]); printk(KERN_CONT "\"\n"); } diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c index 0dd43b4fcec6..fd56c9dd9bc7 100644 --- a/drivers/ide/ide-devsets.c +++ b/drivers/ide/ide-devsets.c @@ -166,10 +166,11 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, return setting->set(drive, arg); rq = blk_get_request(q, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_DRV_PRIV; - rq->cmd_len = 5; - rq->cmd[0] = REQ_DEVSET_EXEC; - *(int *)&rq->cmd[1] = arg; + scsi_req(rq)->cmd_len = 5; + scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC; + *(int *)&scsi_req(rq)->cmd[1] = arg; rq->special = setting->set; if (blk_execute_rq(q, NULL, rq, 0)) @@ -183,7 +184,7 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq) { int err, (*setfunc)(ide_drive_t *, int) = rq->special; - err = setfunc(drive, *(int *)&rq->cmd[1]); + err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]); if (err) rq->errors = err; ide_complete_rq(drive, err, blk_rq_bytes(rq)); diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 5ceace542b77..3437c5b28599 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -478,6 +478,7 @@ static int set_multcount(ide_drive_t *drive, int arg) return -EBUSY; rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_ATA_TASKFILE; drive->mult_req = arg; diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c index d6da011299f5..35e5b892f9d7 100644 --- a/drivers/ide/ide-eh.c +++ b/drivers/ide/ide-eh.c @@ -148,7 +148,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err) struct request *rq = drive->hwif->rq; if (rq && rq->cmd_type == REQ_TYPE_DRV_PRIV && - rq->cmd[0] == REQ_DRIVE_RESET) { + scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) { if (err <= 0 && rq->errors == 0) rq->errors = -EIO; ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq)); diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index f079d8d1d856..3bd678ad3519 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -203,7 +203,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive, put_unaligned(cpu_to_be16(blocks), (unsigned short *)&pc->c[7]); put_unaligned(cpu_to_be32(block), (unsigned int *) &pc->c[2]); - memcpy(rq->cmd, pc->c, 12); + memcpy(scsi_req(rq)->cmd, pc->c, 12); pc->rq = rq; if (cmd == WRITE) @@ -216,7 +216,7 @@ static void idefloppy_blockpc_cmd(struct ide_disk_obj *floppy, struct ide_atapi_pc *pc, struct request *rq) { ide_init_pc(pc); - memcpy(pc->c, rq->cmd, sizeof(pc->c)); + memcpy(pc->c, scsi_req(rq)->cmd, sizeof(pc->c)); pc->rq = rq; if (blk_rq_bytes(rq)) { pc->flags |= PC_FLAG_DMA_OK; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 201e43fcbc94..3378503afed4 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -279,7 +279,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive, static ide_startstop_t ide_special_rq(ide_drive_t *drive, struct request *rq) { - u8 cmd = rq->cmd[0]; + u8 cmd = scsi_req(rq)->cmd[0]; switch (cmd) { case REQ_PARK_HEADS: @@ -545,6 +545,7 @@ repeat: goto plug_device; } + scsi_req(rq)->resid_len = blk_rq_bytes(rq); hwif->rq = rq; spin_unlock_irq(&hwif->lock); diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index d05db2469209..a5d22c6e956a 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -126,6 +126,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg) struct request *rq; rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_ATA_TASKFILE; err = blk_execute_rq(drive->queue, NULL, rq, 0); blk_put_request(rq); @@ -222,9 +223,10 @@ static int generic_drive_reset(ide_drive_t *drive) int ret = 0; rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_DRV_PRIV; - rq->cmd_len = 1; - rq->cmd[0] = REQ_DRIVE_RESET; + scsi_req(rq)->cmd_len = 1; + scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET; if (blk_execute_rq(drive->queue, NULL, rq, 1)) ret = rq->errors; blk_put_request(rq); diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index 2d7dca56dd24..c37604a75097 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -32,8 +32,9 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) spin_unlock_irq(&hwif->lock); rq = blk_get_request(q, READ, __GFP_RECLAIM); - rq->cmd[0] = REQ_PARK_HEADS; - rq->cmd_len = 1; + scsi_req_init(rq); + scsi_req(rq)->cmd[0] = REQ_PARK_HEADS; + scsi_req(rq)->cmd_len = 1; rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->special = &timeout; rc = blk_execute_rq(q, NULL, rq, 1); @@ -46,11 +47,12 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) * timeout has expired, so power management will be reenabled. */ rq = blk_get_request(q, READ, GFP_NOWAIT); + scsi_req_init(rq); if (IS_ERR(rq)) goto out; - rq->cmd[0] = REQ_UNPARK_HEADS; - rq->cmd_len = 1; + scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS; + scsi_req(rq)->cmd_len = 1; rq->cmd_type = REQ_TYPE_DRV_PRIV; elv_add_request(q, rq, ELEVATOR_INSERT_FRONT); @@ -64,7 +66,7 @@ ide_startstop_t ide_do_park_unpark(ide_drive_t *drive, struct request *rq) struct ide_taskfile *tf = &cmd.tf; memset(&cmd, 0, sizeof(cmd)); - if (rq->cmd[0] == REQ_PARK_HEADS) { + if (scsi_req(rq)->cmd[0] == REQ_PARK_HEADS) { drive->sleep = *(unsigned long *)rq->special; drive->dev_flags |= IDE_DFLAG_SLEEPING; tf->command = ATA_CMD_IDLEIMMEDIATE; diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index a015acdffb39..f6767aba7cfb 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -19,6 +19,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) memset(&rqpm, 0, sizeof(rqpm)); rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND; rq->special = &rqpm; rqpm.pm_step = IDE_PM_START_SUSPEND; @@ -89,6 +90,7 @@ int generic_ide_resume(struct device *dev) memset(&rqpm, 0, sizeof(rqpm)); rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_ATA_PM_RESUME; rq->rq_flags |= RQF_PREEMPT; rq->special = &rqpm; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 330e319419e6..a74ae8df4bb8 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -741,6 +741,14 @@ static void ide_port_tune_devices(ide_hwif_t *hwif) } } +static int ide_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp) +{ + struct ide_request *req = blk_mq_rq_to_pdu(rq); + + req->sreq.sense = req->sense; + return 0; +} + /* * init request queue */ @@ -758,11 +766,18 @@ static int ide_init_queue(ide_drive_t *drive) * limits and LBA48 we could raise it but as yet * do not. */ - - q = blk_init_queue_node(do_ide_request, NULL, hwif_to_node(hwif)); + q = blk_alloc_queue_node(GFP_KERNEL, hwif_to_node(hwif)); if (!q) return 1; + q->request_fn = do_ide_request; + q->init_rq_fn = ide_init_rq; + q->cmd_size = sizeof(struct ide_request); + if (blk_init_allocated_queue(q) < 0) { + blk_cleanup_queue(q); + return 1; + } + q->queuedata = drive; blk_queue_segment_boundary(q, 0xffff); @@ -1131,10 +1146,12 @@ static void ide_port_init_devices_data(ide_hwif_t *hwif) ide_port_for_each_dev(i, drive, hwif) { u8 j = (hwif->index * MAX_DRIVES) + i; u16 *saved_id = drive->id; + struct request *saved_sense_rq = drive->sense_rq; memset(drive, 0, sizeof(*drive)); memset(saved_id, 0, SECTOR_SIZE); drive->id = saved_id; + drive->sense_rq = saved_sense_rq; drive->media = ide_disk; drive->select = (i << 4) | ATA_DEVICE_OBS; @@ -1241,6 +1258,7 @@ static void ide_port_free_devices(ide_hwif_t *hwif) int i; ide_port_for_each_dev(i, drive, hwif) { + kfree(drive->sense_rq); kfree(drive->id); kfree(drive); } @@ -1248,11 +1266,10 @@ static void ide_port_free_devices(ide_hwif_t *hwif) static int ide_port_alloc_devices(ide_hwif_t *hwif, int node) { + ide_drive_t *drive; int i; for (i = 0; i < MAX_DRIVES; i++) { - ide_drive_t *drive; - drive = kzalloc_node(sizeof(*drive), GFP_KERNEL, node); if (drive == NULL) goto out_nomem; @@ -1267,12 +1284,21 @@ static int ide_port_alloc_devices(ide_hwif_t *hwif, int node) */ drive->id = kzalloc_node(SECTOR_SIZE, GFP_KERNEL, node); if (drive->id == NULL) - goto out_nomem; + goto out_free_drive; + + drive->sense_rq = kmalloc(sizeof(struct request) + + sizeof(struct ide_request), GFP_KERNEL); + if (!drive->sense_rq) + goto out_free_id; hwif->devices[i] = drive; } return 0; +out_free_id: + kfree(drive->id); +out_free_drive: + kfree(drive); out_nomem: ide_port_free_devices(hwif); return -ENOMEM; diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index 9ecf4e35adcd..f6bc1e2bb035 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -282,7 +282,7 @@ static void idetape_analyze_error(ide_drive_t *drive) /* correct remaining bytes to transfer */ if (pc->flags & PC_FLAG_DMA_ERROR) - rq->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]); + scsi_req(rq)->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]); /* * If error was the result of a zero-length read or write command, @@ -316,7 +316,7 @@ static void idetape_analyze_error(ide_drive_t *drive) pc->flags |= PC_FLAG_ABORT; } if (!(pc->flags & PC_FLAG_ABORT) && - (blk_rq_bytes(rq) - rq->resid_len)) + (blk_rq_bytes(rq) - scsi_req(rq)->resid_len)) pc->retries = IDETAPE_MAX_PC_RETRIES + 1; } } @@ -348,7 +348,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc) "itself - Aborting request!\n"); } else if (pc->c[0] == READ_6 || pc->c[0] == WRITE_6) { unsigned int blocks = - (blk_rq_bytes(rq) - rq->resid_len) / tape->blk_size; + (blk_rq_bytes(rq) - scsi_req(rq)->resid_len) / tape->blk_size; tape->avg_size += blocks * tape->blk_size; @@ -560,7 +560,7 @@ static void ide_tape_create_rw_cmd(idetape_tape_t *tape, pc->flags |= PC_FLAG_WRITING; } - memcpy(rq->cmd, pc->c, 12); + memcpy(scsi_req(rq)->cmd, pc->c, 12); } static ide_startstop_t idetape_do_request(ide_drive_t *drive, @@ -570,10 +570,11 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive, idetape_tape_t *tape = drive->driver_data; struct ide_atapi_pc *pc = NULL; struct ide_cmd cmd; + struct scsi_request *req = scsi_req(rq); u8 stat; ide_debug_log(IDE_DBG_RQ, "cmd: 0x%x, sector: %llu, nr_sectors: %u", - rq->cmd[0], (unsigned long long)blk_rq_pos(rq), + req->cmd[0], (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq)); BUG_ON(!(rq->cmd_type == REQ_TYPE_DRV_PRIV || @@ -592,7 +593,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive, stat = hwif->tp_ops->read_status(hwif); if ((drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) == 0 && - (rq->cmd[13] & REQ_IDETAPE_PC2) == 0) + (req->cmd[13] & REQ_IDETAPE_PC2) == 0) drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC; if (drive->dev_flags & IDE_DFLAG_POST_RESET) { @@ -609,7 +610,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive, } else if (time_after(jiffies, tape->dsc_timeout)) { printk(KERN_ERR "ide-tape: %s: DSC timeout\n", tape->name); - if (rq->cmd[13] & REQ_IDETAPE_PC2) { + if (req->cmd[13] & REQ_IDETAPE_PC2) { idetape_media_access_finished(drive); return ide_stopped; } else { @@ -626,23 +627,23 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive, tape->postponed_rq = false; } - if (rq->cmd[13] & REQ_IDETAPE_READ) { + if (req->cmd[13] & REQ_IDETAPE_READ) { pc = &tape->queued_pc; ide_tape_create_rw_cmd(tape, pc, rq, READ_6); goto out; } - if (rq->cmd[13] & REQ_IDETAPE_WRITE) { + if (req->cmd[13] & REQ_IDETAPE_WRITE) { pc = &tape->queued_pc; ide_tape_create_rw_cmd(tape, pc, rq, WRITE_6); goto out; } - if (rq->cmd[13] & REQ_IDETAPE_PC1) { + if (req->cmd[13] & REQ_IDETAPE_PC1) { pc = (struct ide_atapi_pc *)rq->special; - rq->cmd[13] &= ~(REQ_IDETAPE_PC1); - rq->cmd[13] |= REQ_IDETAPE_PC2; + req->cmd[13] &= ~(REQ_IDETAPE_PC1); + req->cmd[13] |= REQ_IDETAPE_PC2; goto out; } - if (rq->cmd[13] & REQ_IDETAPE_PC2) { + if (req->cmd[13] & REQ_IDETAPE_PC2) { idetape_media_access_finished(drive); return ide_stopped; } @@ -853,8 +854,9 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size) BUG_ON(size < 0 || size % tape->blk_size); rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_DRV_PRIV; - rq->cmd[13] = cmd; + scsi_req(rq)->cmd[13] = cmd; rq->rq_disk = tape->disk; rq->__sector = tape->first_frame; @@ -868,7 +870,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size) blk_execute_rq(drive->queue, tape->disk, rq, 0); /* calculate the number of transferred bytes and update buffer state */ - size -= rq->resid_len; + size -= scsi_req(rq)->resid_len; tape->cur = tape->buf; if (cmd == REQ_IDETAPE_READ) tape->valid = size; diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c index a716693417a3..a393e13b8007 100644 --- a/drivers/ide/ide-taskfile.c +++ b/drivers/ide/ide-taskfile.c @@ -431,6 +431,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf, int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE; rq = blk_get_request(drive->queue, rw, __GFP_RECLAIM); + scsi_req_init(rq); rq->cmd_type = REQ_TYPE_ATA_TASKFILE; /* diff --git a/drivers/ide/sis5513.c b/drivers/ide/sis5513.c index 247853ea1368..c3062b53056f 100644 --- a/drivers/ide/sis5513.c +++ b/drivers/ide/sis5513.c @@ -54,7 +54,7 @@ #define DRV_NAME "sis5513" /* registers layout and init values are chipset family dependent */ - +#undef ATA_16 #define ATA_16 0x01 #define ATA_33 0x02 #define ATA_66 0x03 diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c index 7ee1667acde4..b8c4b2ba7519 100644 --- a/drivers/message/fusion/mptsas.c +++ b/drivers/message/fusion/mptsas.c @@ -2320,10 +2320,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy, SmpPassthroughReply_t *smprep; smprep = (SmpPassthroughReply_t *)ioc->sas_mgmt.reply; - memcpy(req->sense, smprep, sizeof(*smprep)); - req->sense_len = sizeof(*smprep); - req->resid_len = 0; - rsp->resid_len -= smprep->ResponseDataLength; + memcpy(scsi_req(req)->sense, smprep, sizeof(*smprep)); + scsi_req(req)->sense_len = sizeof(*smprep); + scsi_req(req)->resid_len = 0; + scsi_req(rsp)->resid_len -= smprep->ResponseDataLength; } else { printk(MYIOC_s_ERR_FMT "%s: smp passthru reply failed to be returned\n", diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index 919736a74ffa..aa76f36abe03 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -2095,7 +2095,7 @@ int fc_lport_bsg_request(struct bsg_job *job) bsg_reply->reply_payload_rcv_len = 0; if (rsp) - rsp->resid_len = job->reply_payload.payload_len; + scsi_req(rsp)->resid_len = job->reply_payload.payload_len; mutex_lock(&lport->lp_mutex); diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 022bb6e10d98..570b2cb2da43 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -2174,12 +2174,12 @@ int sas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy, bio_data(rsp->bio), blk_rq_bytes(rsp)); if (ret > 0) { /* positive number is the untransferred residual */ - rsp->resid_len = ret; - req->resid_len = 0; + scsi_req(rsp)->resid_len = ret; + scsi_req(req)->resid_len = 0; ret = 0; } else if (ret == 0) { - rsp->resid_len = 0; - req->resid_len = 0; + scsi_req(rsp)->resid_len = 0; + scsi_req(req)->resid_len = 0; } return ret; diff --git a/drivers/scsi/libsas/sas_host_smp.c b/drivers/scsi/libsas/sas_host_smp.c index d24792575169..45cbbc44f4d7 100644 --- a/drivers/scsi/libsas/sas_host_smp.c +++ b/drivers/scsi/libsas/sas_host_smp.c @@ -274,15 +274,15 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req, switch (req_data[1]) { case SMP_REPORT_GENERAL: - req->resid_len -= 8; - rsp->resid_len -= 32; + scsi_req(req)->resid_len -= 8; + scsi_req(rsp)->resid_len -= 32; resp_data[2] = SMP_RESP_FUNC_ACC; resp_data[9] = sas_ha->num_phys; break; case SMP_REPORT_MANUF_INFO: - req->resid_len -= 8; - rsp->resid_len -= 64; + scsi_req(req)->resid_len -= 8; + scsi_req(rsp)->resid_len -= 64; resp_data[2] = SMP_RESP_FUNC_ACC; memcpy(resp_data + 12, shost->hostt->name, SAS_EXPANDER_VENDOR_ID_LEN); @@ -295,13 +295,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req, break; case SMP_DISCOVER: - req->resid_len -= 16; - if ((int)req->resid_len < 0) { - req->resid_len = 0; + scsi_req(req)->resid_len -= 16; + if ((int)scsi_req(req)->resid_len < 0) { + scsi_req(req)->resid_len = 0; error = -EINVAL; goto out; } - rsp->resid_len -= 56; + scsi_req(rsp)->resid_len -= 56; sas_host_smp_discover(sas_ha, resp_data, req_data[9]); break; @@ -311,13 +311,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req, break; case SMP_REPORT_PHY_SATA: - req->resid_len -= 16; - if ((int)req->resid_len < 0) { - req->resid_len = 0; + scsi_req(req)->resid_len -= 16; + if ((int)scsi_req(req)->resid_len < 0) { + scsi_req(req)->resid_len = 0; error = -EINVAL; goto out; } - rsp->resid_len -= 60; + scsi_req(rsp)->resid_len -= 60; sas_report_phy_sata(sas_ha, resp_data, req_data[9]); break; @@ -331,15 +331,15 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req, int to_write = req_data[4]; if (blk_rq_bytes(req) < base_frame_size + to_write * 4 || - req->resid_len < base_frame_size + to_write * 4) { + scsi_req(req)->resid_len < base_frame_size + to_write * 4) { resp_data[2] = SMP_RESP_INV_FRM_LEN; break; } to_write = sas_host_smp_write_gpio(sas_ha, resp_data, req_data[2], req_data[3], to_write, &req_data[8]); - req->resid_len -= base_frame_size + to_write * 4; - rsp->resid_len -= 8; + scsi_req(req)->resid_len -= base_frame_size + to_write * 4; + scsi_req(rsp)->resid_len -= 8; break; } @@ -348,13 +348,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req, break; case SMP_PHY_CONTROL: - req->resid_len -= 44; - if ((int)req->resid_len < 0) { - req->resid_len = 0; + scsi_req(req)->resid_len -= 44; + if ((int)scsi_req(req)->resid_len < 0) { + scsi_req(req)->resid_len = 0; error = -EINVAL; goto out; } - rsp->resid_len -= 8; + scsi_req(rsp)->resid_len -= 8; sas_phy_control(sas_ha, req_data[9], req_data[10], req_data[32] >> 4, req_data[33] >> 4, resp_data); diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c index 7f1d5785bc30..e7a7a704a315 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_transport.c +++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c @@ -2057,10 +2057,10 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy, ioc->name, __func__, le16_to_cpu(mpi_reply->ResponseDataLength))); - memcpy(req->sense, mpi_reply, sizeof(*mpi_reply)); - req->sense_len = sizeof(*mpi_reply); - req->resid_len = 0; - rsp->resid_len -= + memcpy(scsi_req(req)->sense, mpi_reply, sizeof(*mpi_reply)); + scsi_req(req)->sense_len = sizeof(*mpi_reply); + scsi_req(req)->resid_len = 0; + scsi_req(rsp)->resid_len -= le16_to_cpu(mpi_reply->ResponseDataLength); /* check if the resp needs to be copied from the allocated diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index ef99f62831fb..fcb040eebf47 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -48,6 +48,7 @@ #include #include +#include #include "osd_debug.h" @@ -477,11 +478,13 @@ static void _set_error_resid(struct osd_request *or, struct request *req, { or->async_error = error; or->req_errors = req->errors ? : error; - or->sense_len = req->sense_len; + or->sense_len = scsi_req(req)->sense_len; + if (or->sense_len) + memcpy(or->sense, scsi_req(req)->sense, or->sense_len); if (or->out.req) - or->out.residual = or->out.req->resid_len; + or->out.residual = scsi_req(or->out.req)->resid_len; if (or->in.req) - or->in.residual = or->in.req->resid_len; + or->in.residual = scsi_req(or->in.req)->resid_len; } int osd_execute_request(struct osd_request *or) @@ -1565,7 +1568,7 @@ static struct request *_make_request(struct request_queue *q, bool has_write, req = blk_get_request(q, has_write ? WRITE : READ, flags); if (IS_ERR(req)) return req; - blk_rq_set_block_pc(req); + scsi_req_init(req); for_each_bio(bio) { struct bio *bounce_bio = bio; @@ -1599,8 +1602,6 @@ static int _init_blk_request(struct osd_request *or, req->timeout = or->timeout; req->retries = or->retries; - req->sense = or->sense; - req->sense_len = 0; if (has_out) { or->out.req = req; @@ -1612,7 +1613,7 @@ static int _init_blk_request(struct osd_request *or, ret = PTR_ERR(req); goto out; } - blk_rq_set_block_pc(req); + scsi_req_init(req); or->in.req = or->request->next_rq = req; } } else if (has_in) @@ -1699,8 +1700,8 @@ int osd_finalize_request(struct osd_request *or, osd_sec_sign_cdb(&or->cdb, cap_key); - or->request->cmd = or->cdb.buff; - or->request->cmd_len = _osd_req_cdb_len(or); + scsi_req(or->request)->cmd = or->cdb.buff; + scsi_req(or->request)->cmd_len = _osd_req_cdb_len(or); return 0; } diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c index e8196c55b633..d314aa5c71cf 100644 --- a/drivers/scsi/osst.c +++ b/drivers/scsi/osst.c @@ -322,6 +322,7 @@ static int osst_chk_result(struct osst_tape * STp, struct osst_request * SRpnt) /* Wakeup from interrupt */ static void osst_end_async(struct request *req, int update) { + struct scsi_request *rq = scsi_req(req); struct osst_request *SRpnt = req->end_io_data; struct osst_tape *STp = SRpnt->stp; struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data; @@ -330,6 +331,8 @@ static void osst_end_async(struct request *req, int update) #if DEBUG STp->write_pending = 0; #endif + if (rq->sense_len) + memcpy(SRpnt->sense, rq->sense, SCSI_SENSE_BUFFERSIZE); if (SRpnt->waiting) complete(SRpnt->waiting); @@ -357,6 +360,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd, int use_sg, int timeout, int retries) { struct request *req; + struct scsi_request *rq; struct page **pages = NULL; struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data; @@ -367,7 +371,8 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd, if (IS_ERR(req)) return DRIVER_ERROR << 24; - blk_rq_set_block_pc(req); + rq = scsi_req(req); + scsi_req_init(req); req->rq_flags |= RQF_QUIET; SRpnt->bio = NULL; @@ -404,11 +409,9 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd, goto free_req; } - req->cmd_len = cmd_len; - memset(req->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */ - memcpy(req->cmd, cmd, req->cmd_len); - req->sense = SRpnt->sense; - req->sense_len = 0; + rq->cmd_len = cmd_len; + memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */ + memcpy(rq->cmd, cmd, rq->cmd_len); req->timeout = timeout; req->retries = retries; req->end_io_data = SRpnt; diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 1bf8061ff803..40ca75bbcb9d 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -921,7 +921,7 @@ qla2x00_process_loopback(struct bsg_job *bsg_job) bsg_job->reply_len = sizeof(struct fc_bsg_reply) + sizeof(response) + sizeof(uint8_t); - fw_sts_ptr = ((uint8_t *)bsg_job->req->sense) + + fw_sts_ptr = ((uint8_t *)scsi_req(bsg_job->req)->sense) + sizeof(struct fc_bsg_reply); memcpy(fw_sts_ptr, response, sizeof(response)); fw_sts_ptr += sizeof(response); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index dc88a09f9043..67e157d81da8 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1468,7 +1468,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, type, sp->handle, comp_status, fw_status[1], fw_status[2], le16_to_cpu(((struct els_sts_entry_24xx *) pkt)->total_byte_count)); - fw_sts_ptr = ((uint8_t*)bsg_job->req->sense) + sizeof(struct fc_bsg_reply); + fw_sts_ptr = ((uint8_t*)scsi_req(bsg_job->req)->sense) + + sizeof(struct fc_bsg_reply); memcpy( fw_sts_ptr, fw_status, sizeof(fw_status)); } else { @@ -1482,7 +1483,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, pkt)->error_subcode_2)); res = DID_ERROR << 16; bsg_reply->reply_payload_rcv_len = 0; - fw_sts_ptr = ((uint8_t*)bsg_job->req->sense) + sizeof(struct fc_bsg_reply); + fw_sts_ptr = ((uint8_t*)scsi_req(bsg_job->req)->sense) + + sizeof(struct fc_bsg_reply); memcpy( fw_sts_ptr, fw_status, sizeof(fw_status)); } ql_dump_buffer(ql_dbg_user + ql_dbg_buffer, vha, 0x5056, diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c index 02f1de18bc2b..96c33e292eba 100644 --- a/drivers/scsi/qla2xxx/qla_mr.c +++ b/drivers/scsi/qla2xxx/qla_mr.c @@ -2244,7 +2244,7 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req, memcpy(fstatus.reserved_3, pkt->reserved_2, 20 * sizeof(uint8_t)); - fw_sts_ptr = ((uint8_t *)bsg_job->req->sense) + + fw_sts_ptr = ((uint8_t *)scsi_req(bsg_job->req)->sense) + sizeof(struct fc_bsg_reply); memcpy(fw_sts_ptr, (uint8_t *)&fstatus, diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 7c084600827b..4b40f746d534 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1968,6 +1968,7 @@ static void eh_lock_door_done(struct request *req, int uptodate) static void scsi_eh_lock_door(struct scsi_device *sdev) { struct request *req; + struct scsi_request *rq; /* * blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a @@ -1976,17 +1977,16 @@ static void scsi_eh_lock_door(struct scsi_device *sdev) req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL); if (IS_ERR(req)) return; + rq = scsi_req(req); + scsi_req_init(req); - blk_rq_set_block_pc(req); - - req->cmd[0] = ALLOW_MEDIUM_REMOVAL; - req->cmd[1] = 0; - req->cmd[2] = 0; - req->cmd[3] = 0; - req->cmd[4] = SCSI_REMOVAL_PREVENT; - req->cmd[5] = 0; - - req->cmd_len = COMMAND_SIZE(req->cmd[0]); + rq->cmd[0] = ALLOW_MEDIUM_REMOVAL; + rq->cmd[1] = 0; + rq->cmd[2] = 0; + rq->cmd[3] = 0; + rq->cmd[4] = SCSI_REMOVAL_PREVENT; + rq->cmd[5] = 0; + rq->cmd_len = COMMAND_SIZE(rq->cmd[0]); req->rq_flags |= RQF_QUIET; req->timeout = 10 * HZ; @@ -2355,7 +2355,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) scmd = (struct scsi_cmnd *)(rq + 1); scsi_init_command(dev, scmd); scmd->request = rq; - scmd->cmnd = rq->cmd; + scmd->cmnd = scsi_req(rq)->cmd; scmd->scsi_done = scsi_reset_provider_done_command; memset(&scmd->sdb, 0, sizeof(scmd->sdb)); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 81ff5ad23b83..8188e5c71f75 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -220,21 +220,21 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, { struct request *req; int write = (data_direction == DMA_TO_DEVICE); + struct scsi_request *rq; int ret = DRIVER_ERROR << 24; req = blk_get_request(sdev->request_queue, write, __GFP_RECLAIM); if (IS_ERR(req)) return ret; - blk_rq_set_block_pc(req); + rq = scsi_req(req); + scsi_req_init(req); if (bufflen && blk_rq_map_kern(sdev->request_queue, req, buffer, bufflen, __GFP_RECLAIM)) goto out; - req->cmd_len = COMMAND_SIZE(cmd[0]); - memcpy(req->cmd, cmd, req->cmd_len); - req->sense = sense; - req->sense_len = 0; + rq->cmd_len = COMMAND_SIZE(cmd[0]); + memcpy(rq->cmd, cmd, rq->cmd_len); req->retries = retries; req->timeout = timeout; req->cmd_flags |= flags; @@ -251,11 +251,13 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, * is invalid. Prevent the garbage from being misinterpreted * and prevent security leaks by zeroing out the excess data. */ - if (unlikely(req->resid_len > 0 && req->resid_len <= bufflen)) - memset(buffer + (bufflen - req->resid_len), 0, req->resid_len); + if (unlikely(rq->resid_len > 0 && rq->resid_len <= bufflen)) + memset(buffer + (bufflen - rq->resid_len), 0, rq->resid_len); if (resid) - *resid = req->resid_len; + *resid = rq->resid_len; + if (sense && rq->sense_len) + memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE); ret = req->errors; out: blk_put_request(req); @@ -806,16 +808,13 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */ if (result) { - if (sense_valid && req->sense) { + if (sense_valid) { /* * SG_IO wants current and deferred errors */ - int len = 8 + cmd->sense_buffer[7]; - - if (len > SCSI_SENSE_BUFFERSIZE) - len = SCSI_SENSE_BUFFERSIZE; - memcpy(req->sense, cmd->sense_buffer, len); - req->sense_len = len; + scsi_req(req)->sense_len = + min(8 + cmd->sense_buffer[7], + SCSI_SENSE_BUFFERSIZE); } if (!sense_deferred) error = __scsi_error_from_host_byte(cmd, result); @@ -825,14 +824,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) */ req->errors = cmd->result; - req->resid_len = scsi_get_resid(cmd); + scsi_req(req)->resid_len = scsi_get_resid(cmd); if (scsi_bidi_cmnd(cmd)) { /* * Bidi commands Must be complete as a whole, * both sides at once. */ - req->next_rq->resid_len = scsi_in(cmd)->resid; + scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid; if (scsi_end_request(req, 0, blk_rq_bytes(req), blk_rq_bytes(req->next_rq))) BUG(); @@ -1165,7 +1164,10 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) void *prot = cmd->prot_sdb; unsigned long flags; - memset(cmd, 0, sizeof(*cmd)); + /* zero out the cmd, except for the embedded scsi_request */ + memset((char *)cmd + sizeof(cmd->req), 0, + sizeof(*cmd) - sizeof(cmd->req)); + cmd->device = dev; cmd->sense_buffer = buf; cmd->prot_sdb = prot; @@ -1197,7 +1199,8 @@ static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) memset(&cmd->sdb, 0, sizeof(cmd->sdb)); } - cmd->cmd_len = req->cmd_len; + cmd->cmd_len = scsi_req(req)->cmd_len; + cmd->cmnd = scsi_req(req)->cmd; cmd->transfersize = blk_rq_bytes(req); cmd->allowed = req->retries; return BLKPREP_OK; @@ -1217,6 +1220,7 @@ static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req) return ret; } + cmd->cmnd = scsi_req(req)->cmd = scsi_req(req)->__cmd; memset(cmd->cmnd, 0, BLK_MAX_CDB); return scsi_cmd_to_driver(cmd)->init_command(cmd); } @@ -1355,7 +1359,6 @@ static int scsi_prep_fn(struct request_queue *q, struct request *req) cmd->tag = req->tag; cmd->request = req; - cmd->cmnd = req->cmd; cmd->prot_op = SCSI_PROT_NORMAL; ret = scsi_setup_cmnd(sdev, req); @@ -1874,7 +1877,9 @@ static int scsi_mq_prep_fn(struct request *req) unsigned char *sense_buf = cmd->sense_buffer; struct scatterlist *sg; - memset(cmd, 0, sizeof(struct scsi_cmnd)); + /* zero out the cmd, except for the embedded scsi_request */ + memset((char *)cmd + sizeof(cmd->req), 0, + sizeof(*cmd) - sizeof(cmd->req)); req->special = cmd; @@ -1884,7 +1889,6 @@ static int scsi_mq_prep_fn(struct request *req) cmd->tag = req->tag; - cmd->cmnd = req->cmd; cmd->prot_op = SCSI_PROT_NORMAL; INIT_LIST_HEAD(&cmd->list); @@ -1959,7 +1963,6 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, if (!scsi_host_queue_ready(q, shost, sdev)) goto out_dec_target_busy; - if (!(req->rq_flags & RQF_DONTPREP)) { ret = prep_to_mq(scsi_mq_prep_fn(req)); if (ret != BLK_MQ_RQ_QUEUE_OK) @@ -2036,6 +2039,7 @@ static int scsi_init_request(void *data, struct request *rq, scsi_alloc_sense_buffer(shost, GFP_KERNEL, numa_node); if (!cmd->sense_buffer) return -ENOMEM; + cmd->req.sense = cmd->sense_buffer; return 0; } @@ -2125,6 +2129,7 @@ static int scsi_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp) cmd->sense_buffer = scsi_alloc_sense_buffer(shost, gfp, NUMA_NO_NODE); if (!cmd->sense_buffer) goto fail; + cmd->req.sense = cmd->sense_buffer; if (scsi_host_get_prot(shost) >= SHOST_DIX_TYPE0_PROTECTION) { cmd->prot_sdb = kmem_cache_zalloc(scsi_sdb_cache, gfp); diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 60b651bfaa01..126a5ee00987 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -33,6 +33,7 @@ #include #include +#include #include #include #include @@ -177,6 +178,10 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost, while ((req = blk_fetch_request(q)) != NULL) { spin_unlock_irq(q->queue_lock); + scsi_req(req)->resid_len = blk_rq_bytes(req); + if (req->next_rq) + scsi_req(req->next_rq)->resid_len = + blk_rq_bytes(req->next_rq); handler = to_sas_internal(shost->transportt)->f->smp_handler; ret = handler(shost, rphy, req); req->errors = ret; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 0b09638fa39b..c779986edb43 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -781,7 +781,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd) rq->special_vec.bv_len = len; rq->rq_flags |= RQF_SPECIAL_PAYLOAD; - rq->resid_len = len; + scsi_req(rq)->resid_len = len; ret = scsi_init_io(cmd); out: @@ -1164,7 +1164,7 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt) if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) __free_page(rq->special_vec.bv_page); - if (SCpnt->cmnd != rq->cmd) { + if (SCpnt->cmnd != scsi_req(rq)->cmd) { mempool_free(SCpnt->cmnd, sd_cdb_pool); SCpnt->cmnd = NULL; SCpnt->cmd_len = 0; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index dbe5b4b95df0..226a8def7a8b 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -781,9 +781,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, } if (atomic_read(&sdp->detaching)) { if (srp->bio) { - if (srp->rq->cmd != srp->rq->__cmd) - kfree(srp->rq->cmd); - + scsi_req_free_cmd(scsi_req(srp->rq)); blk_end_request_all(srp->rq, -EIO); srp->rq = NULL; } @@ -1279,6 +1277,7 @@ static void sg_rq_end_io(struct request *rq, int uptodate) { struct sg_request *srp = rq->end_io_data; + struct scsi_request *req = scsi_req(rq); Sg_device *sdp; Sg_fd *sfp; unsigned long iflags; @@ -1297,9 +1296,9 @@ sg_rq_end_io(struct request *rq, int uptodate) if (unlikely(atomic_read(&sdp->detaching))) pr_info("%s: device detaching\n", __func__); - sense = rq->sense; + sense = req->sense; result = rq->errors; - resid = rq->resid_len; + resid = req->resid_len; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp, "sg_cmd_done: pack_id=%d, res=0x%x\n", @@ -1333,6 +1332,10 @@ sg_rq_end_io(struct request *rq, int uptodate) sdp->device->changed = 1; } } + + if (req->sense_len) + memcpy(srp->sense_b, req->sense, SCSI_SENSE_BUFFERSIZE); + /* Rely on write phase to clean out srp status values, so no "else" */ /* @@ -1342,8 +1345,7 @@ sg_rq_end_io(struct request *rq, int uptodate) * blk_rq_unmap_user() can be called from user context. */ srp->rq = NULL; - if (rq->cmd != rq->__cmd) - kfree(rq->cmd); + scsi_req_free_cmd(scsi_req(rq)); __blk_put_request(rq->q, rq); write_lock_irqsave(&sfp->rq_list_lock, iflags); @@ -1658,6 +1660,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) { int res; struct request *rq; + struct scsi_request *req; Sg_fd *sfp = srp->parentfp; sg_io_hdr_t *hp = &srp->header; int dxfer_len = (int) hp->dxfer_len; @@ -1700,17 +1703,17 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) kfree(long_cmdp); return PTR_ERR(rq); } + req = scsi_req(rq); - blk_rq_set_block_pc(rq); + scsi_req_init(rq); if (hp->cmd_len > BLK_MAX_CDB) - rq->cmd = long_cmdp; - memcpy(rq->cmd, cmd, hp->cmd_len); - rq->cmd_len = hp->cmd_len; + req->cmd = long_cmdp; + memcpy(req->cmd, cmd, hp->cmd_len); + req->cmd_len = hp->cmd_len; srp->rq = rq; rq->end_io_data = srp; - rq->sense = srp->sense_b; rq->retries = SG_DEFAULT_RETRIES; if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE)) @@ -1786,8 +1789,7 @@ sg_finish_rem_req(Sg_request *srp) ret = blk_rq_unmap_user(srp->bio); if (srp->rq) { - if (srp->rq->cmd != srp->rq->__cmd) - kfree(srp->rq->cmd); + scsi_req_free_cmd(scsi_req(srp->rq)); blk_put_request(srp->rq); } diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 5f35b863e1a7..4af900100a24 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -475,7 +475,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req) ktime_t now; now = ktime_get(); - if (req->cmd[0] == WRITE_6) { + if (scsi_req(req)->cmd[0] == WRITE_6) { now = ktime_sub(now, STp->stats->write_time); atomic64_add(ktime_to_ns(now), &STp->stats->tot_write_time); atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time); @@ -489,7 +489,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req) } else atomic64_add(atomic_read(&STp->stats->last_write_size), &STp->stats->write_byte_cnt); - } else if (req->cmd[0] == READ_6) { + } else if (scsi_req(req)->cmd[0] == READ_6) { now = ktime_sub(now, STp->stats->read_time); atomic64_add(ktime_to_ns(now), &STp->stats->tot_read_time); atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time); @@ -514,15 +514,18 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req) static void st_scsi_execute_end(struct request *req, int uptodate) { struct st_request *SRpnt = req->end_io_data; + struct scsi_request *rq = scsi_req(req); struct scsi_tape *STp = SRpnt->stp; struct bio *tmp; STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors; - STp->buffer->cmdstat.residual = req->resid_len; + STp->buffer->cmdstat.residual = rq->resid_len; st_do_stats(STp, req); tmp = SRpnt->bio; + if (rq->sense_len) + memcpy(SRpnt->sense, rq->sense, SCSI_SENSE_BUFFERSIZE); if (SRpnt->waiting) complete(SRpnt->waiting); @@ -535,6 +538,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, int timeout, int retries) { struct request *req; + struct scsi_request *rq; struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data; int err = 0; int write = (data_direction == DMA_TO_DEVICE); @@ -544,8 +548,8 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, GFP_KERNEL); if (IS_ERR(req)) return DRIVER_ERROR << 24; - - blk_rq_set_block_pc(req); + rq = scsi_req(req); + scsi_req_init(req); req->rq_flags |= RQF_QUIET; mdata->null_mapped = 1; @@ -571,11 +575,9 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, } SRpnt->bio = req->bio; - req->cmd_len = COMMAND_SIZE(cmd[0]); - memset(req->cmd, 0, BLK_MAX_CDB); - memcpy(req->cmd, cmd, req->cmd_len); - req->sense = SRpnt->sense; - req->sense_len = 0; + rq->cmd_len = COMMAND_SIZE(cmd[0]); + memset(rq->cmd, 0, BLK_MAX_CDB); + memcpy(rq->cmd, cmd, rq->cmd_len); req->timeout = timeout; req->retries = retries; req->end_io_data = SRpnt; diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 04d7aa7390d0..e52f4e1a4675 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1013,7 +1013,7 @@ pscsi_execute_cmd(struct se_cmd *cmd) goto fail; } - blk_rq_set_block_pc(req); + scsi_req_init(req); if (sgl) { ret = pscsi_map_sg(cmd, sgl, sgl_nents, req); @@ -1023,10 +1023,8 @@ pscsi_execute_cmd(struct se_cmd *cmd) req->end_io = pscsi_req_done; req->end_io_data = cmd; - req->cmd_len = scsi_command_size(pt->pscsi_cdb); - req->cmd = &pt->pscsi_cdb[0]; - req->sense = &pt->pscsi_sense[0]; - req->sense_len = 0; + scsi_req(req)->cmd_len = scsi_command_size(pt->pscsi_cdb); + scsi_req(req)->cmd = &pt->pscsi_cdb[0]; if (pdv->pdv_sd->type == TYPE_DISK) req->timeout = PS_TIMEOUT_DISK; else @@ -1075,7 +1073,7 @@ static void pscsi_req_done(struct request *req, int uptodate) struct pscsi_plugin_task *pt = cmd->priv; pt->pscsi_result = req->errors; - pt->pscsi_resid = req->resid_len; + pt->pscsi_resid = scsi_req(req)->resid_len; cmd->scsi_status = status_byte(pt->pscsi_result) << 1; if (cmd->scsi_status) { @@ -1096,6 +1094,7 @@ static void pscsi_req_done(struct request *req, int uptodate) break; } + memcpy(pt->pscsi_sense, scsi_req(req)->sense, TRANSPORT_SENSE_BUFFER); __blk_put_request(req->q, req); kfree(pt); } diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 0780ff864539..930d98caab5b 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "blocklayoutxdr.h" #include "pnfs.h" @@ -213,6 +214,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, { struct request_queue *q = bdev->bd_disk->queue; struct request *rq; + struct scsi_request *req; size_t bufflen = 252, len, id_len; u8 *buf, *d, type, assoc; int error; @@ -226,18 +228,19 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, error = -ENOMEM; goto out_free_buf; } - blk_rq_set_block_pc(rq); + req = scsi_req(rq); + scsi_req_init(rq); error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL); if (error) goto out_put_request; - rq->cmd[0] = INQUIRY; - rq->cmd[1] = 1; - rq->cmd[2] = 0x83; - rq->cmd[3] = bufflen >> 8; - rq->cmd[4] = bufflen & 0xff; - rq->cmd_len = COMMAND_SIZE(INQUIRY); + req->cmd[0] = INQUIRY; + req->cmd[1] = 1; + req->cmd[2] = 0x83; + req->cmd[3] = bufflen >> 8; + req->cmd[4] = bufflen & 0xff; + req->cmd_len = COMMAND_SIZE(INQUIRY); error = blk_execute_rq(rq->q, NULL, rq, 1); if (error) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 461b7cf6af1d..e4c5f284fe2d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -128,8 +128,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) -#define BLK_MAX_CDB 16 - /* * Try to put the fields that are referenced together in the same cacheline. * @@ -227,17 +225,7 @@ struct request { int errors; - /* - * when request is used as a packet command carrier - */ - unsigned char __cmd[BLK_MAX_CDB]; - unsigned char *cmd; - unsigned short cmd_len; - unsigned int extra_len; /* length of alignment and padding */ - unsigned int sense_len; - unsigned int resid_len; /* residual count */ - void *sense; unsigned long deadline; struct list_head timeout_list; @@ -925,7 +913,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); -extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, diff --git a/include/linux/ide.h b/include/linux/ide.h index a633898f36ac..086fbe172817 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -20,6 +20,7 @@ #include /* for request_sense */ #include +#include #include #include @@ -52,6 +53,11 @@ enum ata_cmd_type_bits { ((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \ (rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME) +struct ide_request { + struct scsi_request sreq; + u8 sense[SCSI_SENSE_BUFFERSIZE]; +}; + /* Error codes returned in rq->errors to the higher part of the driver. */ enum { IDE_DRV_ERROR_GENERAL = 101, @@ -579,7 +585,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; - struct request sense_rq; + struct request *sense_rq; struct request_sense sense_data; }; diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 9fc1aecfc813..f708f1acfc50 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -8,6 +8,7 @@ #include #include #include +#include struct Scsi_Host; struct scsi_driver; @@ -57,6 +58,7 @@ struct scsi_pointer { #define SCMD_TAGGED (1 << 0) struct scsi_cmnd { + struct scsi_request req; struct scsi_device *device; struct list_head list; /* scsi_cmnd participates in queue lists */ struct list_head eh_entry; /* entry for the host eh_cmd_q */ diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h new file mode 100644 index 000000000000..ba0aeb980f7e --- /dev/null +++ b/include/scsi/scsi_request.h @@ -0,0 +1,30 @@ +#ifndef _SCSI_SCSI_REQUEST_H +#define _SCSI_SCSI_REQUEST_H + +#include + +#define BLK_MAX_CDB 16 + +struct scsi_request { + unsigned char __cmd[BLK_MAX_CDB]; + unsigned char *cmd; + unsigned short cmd_len; + unsigned int sense_len; + unsigned int resid_len; /* residual count */ + void *sense; +}; + +static inline struct scsi_request *scsi_req(struct request *rq) +{ + return blk_mq_rq_to_pdu(rq); +} + +static inline void scsi_req_free_cmd(struct scsi_request *req) +{ + if (req->cmd != req->__cmd) + kfree(req->cmd); +} + +void scsi_req_init(struct request *); + +#endif /* _SCSI_SCSI_REQUEST_H */ -- cgit v1.2.3-59-g8ed1b From fb045ca25cc7b6d46368ab8221774489c2a81648 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 23 Jan 2017 14:31:09 +0100 Subject: block: don't assign cmd_flags in __blk_rq_prep_clone These days we have the proper flags set since request allocation time. Signed-off-by: Christoph Hellwig Acked-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-core.c | 1 - 1 file changed, 1 deletion(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index f3bc083d4c14..95829523cded 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2983,7 +2983,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); static void __blk_rq_prep_clone(struct request *dst, struct request *src) { dst->cpu = src->cpu; - 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); -- cgit v1.2.3-59-g8ed1b From 72148aecf4fd9218e2db1333534e8403fdd66eb9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 28 Jan 2017 09:32:51 +0100 Subject: block: make scsi_request and scsi ioctl support optional We only need this code to support scsi, ide, cciss and virtio. And at least for virtio it's a deprecated feature to start with. This should shrink the kernel size for embedded device that only use, say eMMC a bit. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/Kconfig | 5 +++++ block/Makefile | 5 +++-- drivers/block/Kconfig | 4 ++++ drivers/block/paride/Kconfig | 1 + drivers/ide/Kconfig | 1 + drivers/scsi/Kconfig | 1 + drivers/target/Kconfig | 1 + fs/nfsd/Kconfig | 1 + 8 files changed, 17 insertions(+), 2 deletions(-) (limited to 'block') diff --git a/block/Kconfig b/block/Kconfig index 7f659b23850c..b97d7f6fd622 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -49,9 +49,13 @@ config LBDAF If unsure, say Y. +config BLK_SCSI_REQUEST + bool + config BLK_DEV_BSG bool "Block layer SG support v4" default y + select BLK_SCSI_REQUEST help Saying Y here will enable generic SG (SCSI generic) v4 support for any block device. @@ -71,6 +75,7 @@ config BLK_DEV_BSGLIB bool "Block layer SG support v4 helper lib" default n select BLK_DEV_BSG + select BLK_SCSI_REQUEST help Subsystems will normally enable this if needed. Users will not normally need to manually enable this. diff --git a/block/Makefile b/block/Makefile index 317165f8708c..38f26cae4303 100644 --- a/block/Makefile +++ b/block/Makefile @@ -7,10 +7,11 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ - genhd.o scsi_ioctl.o partition-generic.o ioprio.o \ + genhd.o partition-generic.o ioprio.o \ badblocks.o partitions/ -obj-$(CONFIG_BOUNCE) += bounce.o +obj-$(CONFIG_BOUNCE) += bounce.o +obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 223ff2fcae7e..7a4c787a5edf 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -69,6 +69,7 @@ config AMIGA_Z2RAM config GDROM tristate "SEGA Dreamcast GD-ROM drive" depends on SH_DREAMCAST + select BLK_SCSI_REQUEST # only for the generic cdrom code help A standard SEGA Dreamcast comes with a modified CD ROM drive called a "GD-ROM" by SEGA to signify it is capable of reading special disks @@ -114,6 +115,7 @@ config BLK_CPQ_CISS_DA tristate "Compaq Smart Array 5xxx support" depends on PCI select CHECK_SIGNATURE + select BLK_SCSI_REQUEST help This is the driver for Compaq Smart Array 5xxx controllers. Everyone using these boards should say Y here. @@ -386,6 +388,7 @@ config BLK_DEV_RAM_DAX config CDROM_PKTCDVD tristate "Packet writing on CD/DVD media (DEPRECATED)" depends on !UML + select BLK_SCSI_REQUEST help Note: This driver is deprecated and will be removed from the kernel in the near future! @@ -497,6 +500,7 @@ config XEN_BLKDEV_BACKEND config VIRTIO_BLK tristate "Virtio block driver" depends on VIRTIO + select BLK_SCSI_REQUEST ---help--- This is the virtual block driver for virtio. It can be used with lguest or QEMU based VMMs (like KVM or Xen). Say Y or M. diff --git a/drivers/block/paride/Kconfig b/drivers/block/paride/Kconfig index efefb5ac3004..3a15247942e4 100644 --- a/drivers/block/paride/Kconfig +++ b/drivers/block/paride/Kconfig @@ -25,6 +25,7 @@ config PARIDE_PD config PARIDE_PCD tristate "Parallel port ATAPI CD-ROMs" depends on PARIDE + select BLK_SCSI_REQUEST # only for the generic cdrom code ---help--- This option enables the high-level driver for ATAPI CD-ROM devices connected through a parallel port. If you chose to build PARIDE diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig index 39ea67f9b066..c99a25c075bc 100644 --- a/drivers/ide/Kconfig +++ b/drivers/ide/Kconfig @@ -10,6 +10,7 @@ menuconfig IDE tristate "ATA/ATAPI/MFM/RLL support (DEPRECATED)" depends on HAVE_IDE depends on BLOCK + select BLK_SCSI_REQUEST ---help--- If you say Y here, your kernel will be able to manage ATA/(E)IDE and ATAPI units. The most common cases are IDE hard drives and ATAPI diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index a4f6b0d95515..d4023bf1e739 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -18,6 +18,7 @@ config SCSI depends on BLOCK select SCSI_DMA if HAS_DMA select SG_POOL + select BLK_SCSI_REQUEST ---help--- If you want to use a SCSI hard disk, SCSI tape drive, SCSI CD-ROM or any other SCSI device under Linux, say Y and make sure that you know diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig index 257361280510..e2bc99980f75 100644 --- a/drivers/target/Kconfig +++ b/drivers/target/Kconfig @@ -4,6 +4,7 @@ menuconfig TARGET_CORE depends on SCSI && BLOCK select CONFIGFS_FS select CRC_T10DIF + select BLK_SCSI_REQUEST # only for scsi_command_size_tbl.. default n help Say Y or M here to enable the TCM Storage Engine and ConfigFS enabled diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 47febcf99185..20b1c17320d5 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -104,6 +104,7 @@ config NFSD_SCSILAYOUT depends on NFSD_V4 && BLOCK select NFSD_PNFS select EXPORTFS_BLOCK_OPS + select BLK_SCSI_REQUEST help This option enables support for the exporting pNFS SCSI layouts in the kernel's NFS server. The pNFS SCSI layout enables NFS -- cgit v1.2.3-59-g8ed1b From 57292b58ddb58689e8c3b4c6eadbef10d9ca44dd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 31 Jan 2017 16:57:29 +0100 Subject: block: introduce blk_rq_is_passthrough This can be used to check for fs vs non-fs requests and basically removes all knowledge of BLOCK_PC specific from the block layer, as well as preparing for removing the cmd_type field in struct request. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 8 ++++---- block/blk-exec.c | 2 +- block/blk.h | 2 +- block/elevator.c | 4 ++-- block/mq-deadline.c | 2 +- drivers/ata/libata-scsi.c | 2 +- drivers/block/cciss.c | 36 +++++++++++++++++------------------ drivers/nvme/host/fc.c | 2 +- drivers/nvme/host/pci.c | 4 ++-- drivers/nvme/host/rdma.c | 4 ++-- drivers/nvme/target/loop.c | 2 +- drivers/scsi/hpsa.c | 4 ++-- drivers/scsi/scsi.c | 2 +- drivers/scsi/scsi_error.c | 4 ++-- drivers/scsi/scsi_lib.c | 6 +++--- drivers/scsi/smartpqi/smartpqi_init.c | 2 +- drivers/scsi/sun3_scsi.c | 2 +- include/linux/blkdev.h | 16 +++++++++++----- include/linux/blktrace_api.h | 4 ++-- include/scsi/scsi_cmnd.h | 2 +- kernel/trace/blktrace.c | 2 +- 21 files changed, 59 insertions(+), 53 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 95829523cded..44431086e4e7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2506,10 +2506,10 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) * TODO: tj: This is too subtle. It would be better to let * low level drivers do what they see fit. */ - if (req->cmd_type == REQ_TYPE_FS) + if (!blk_rq_is_passthrough(req)) req->errors = 0; - if (error && req->cmd_type == REQ_TYPE_FS && + if (error && !blk_rq_is_passthrough(req) && !(req->rq_flags & RQF_QUIET)) { char *error_type; @@ -2581,7 +2581,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ - if (req->cmd_type == REQ_TYPE_FS) + if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ @@ -2659,7 +2659,7 @@ void blk_finish_request(struct request *req, int error) BUG_ON(blk_queued_rq(req)); - if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS) + if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req)) laptop_io_completion(&req->q->backing_dev_info); blk_delete_timer(req); diff --git a/block/blk-exec.c b/block/blk-exec.c index ed51800f4b44..8cd0e9bc8dc8 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -51,7 +51,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK; WARN_ON(irqs_disabled()); - WARN_ON(rq->cmd_type == REQ_TYPE_FS); + WARN_ON(!blk_rq_is_passthrough(rq)); rq->rq_disk = bd_disk; rq->end_io = done; diff --git a/block/blk.h b/block/blk.h index 9a716b5925a4..c1bd4bf9e645 100644 --- a/block/blk.h +++ b/block/blk.h @@ -249,7 +249,7 @@ static inline int blk_do_io_stat(struct request *rq) { return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT) && - (rq->cmd_type == REQ_TYPE_FS); + !blk_rq_is_passthrough(rq); } /* diff --git a/block/elevator.c b/block/elevator.c index ef7f59469acc..dba9be891a6b 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -634,7 +634,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) if (rq->rq_flags & RQF_SOFTBARRIER) { /* barriers are scheduling boundary, update end_sector */ - if (rq->cmd_type == REQ_TYPE_FS) { + if (!blk_rq_is_passthrough(rq)) { q->end_sector = rq_end_sector(rq); q->boundary_rq = rq; } @@ -676,7 +676,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) if (elv_attempt_insert_merge(q, rq)) break; case ELEVATOR_INSERT_SORT: - BUG_ON(rq->cmd_type != REQ_TYPE_FS); + BUG_ON(blk_rq_is_passthrough(rq)); rq->rq_flags |= RQF_SORTED; q->nr_sorted++; if (rq_mergeable(rq)) { diff --git a/block/mq-deadline.c b/block/mq-deadline.c index d93ec713fa62..49583536698c 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -398,7 +398,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, if (blk_mq_sched_bypass_insert(hctx, rq)) return; - if (at_head || rq->cmd_type != REQ_TYPE_FS) { + if (at_head || blk_rq_is_passthrough(rq)) { if (at_head) list_add(&rq->queuelist, &dd->dispatch); else diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 6abd73975f87..c771d4c341ea 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1265,7 +1265,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev) */ static int atapi_drain_needed(struct request *rq) { - if (likely(rq->cmd_type != REQ_TYPE_BLOCK_PC)) + if (likely(!blk_rq_is_passthrough(rq))) return 0; if (!blk_rq_bytes(rq) || op_is_write(req_op(rq))) diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index b93bb73b49d2..53dc2971a3ba 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1854,7 +1854,7 @@ static void cciss_softirq_done(struct request *rq) dev_dbg(&h->pdev->dev, "Done with %p\n", rq); /* set the residual count for pc requests */ - if (rq->cmd_type == REQ_TYPE_BLOCK_PC) + if (blk_rq_is_passthrough(rq)) scsi_req(rq)->resid_len = c->err_info->ResidualCnt; blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO); @@ -3083,7 +3083,7 @@ static inline int evaluate_target_status(ctlr_info_t *h, driver_byte = DRIVER_OK; msg_byte = cmd->err_info->CommandStatus; /* correct? seems too device specific */ - if (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) + if (blk_rq_is_passthrough(cmd->rq)) host_byte = DID_PASSTHROUGH; else host_byte = DID_OK; @@ -3092,7 +3092,7 @@ static inline int evaluate_target_status(ctlr_info_t *h, host_byte, driver_byte); if (cmd->err_info->ScsiStatus != SAM_STAT_CHECK_CONDITION) { - if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) + if (!blk_rq_is_passthrough(cmd->rq)) dev_warn(&h->pdev->dev, "cmd %p " "has SCSI Status 0x%x\n", cmd, cmd->err_info->ScsiStatus); @@ -3103,16 +3103,16 @@ static inline int evaluate_target_status(ctlr_info_t *h, sense_key = 0xf & cmd->err_info->SenseInfo[2]; /* no status or recovered error */ if (((sense_key == 0x0) || (sense_key == 0x1)) && - (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC)) + !blk_rq_is_passthrough(cmd->rq)) error_value = 0; if (check_for_unit_attention(h, cmd)) { - *retry_cmd = !(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC); + *retry_cmd = !blk_rq_is_passthrough(cmd->rq); return 0; } /* Not SG_IO or similar? */ - if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) { + if (!blk_rq_is_passthrough(cmd->rq)) { if (error_value != 0) dev_warn(&h->pdev->dev, "cmd %p has CHECK CONDITION" " sense key = 0x%x\n", cmd, sense_key); @@ -3146,14 +3146,14 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, rq->errors = evaluate_target_status(h, cmd, &retry_cmd); break; case CMD_DATA_UNDERRUN: - if (cmd->rq->cmd_type == REQ_TYPE_FS) { + if (!blk_rq_is_passthrough(cmd->rq)) { dev_warn(&h->pdev->dev, "cmd %p has" " completed with data underrun " "reported\n", cmd); } break; case CMD_DATA_OVERRUN: - if (cmd->rq->cmd_type == REQ_TYPE_FS) + if (!blk_rq_is_passthrough(cmd->rq)) dev_warn(&h->pdev->dev, "cciss: cmd %p has" " completed with data overrun " "reported\n", cmd); @@ -3163,7 +3163,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "reported invalid\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); break; case CMD_PROTOCOL_ERR: @@ -3171,7 +3171,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "protocol error\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); break; case CMD_HARDWARE_ERR: @@ -3179,7 +3179,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, " hardware error\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); break; case CMD_CONNECTION_LOST: @@ -3187,7 +3187,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "connection lost\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); break; case CMD_ABORTED: @@ -3195,7 +3195,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "aborted\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ABORT); break; case CMD_ABORT_FAILED: @@ -3203,7 +3203,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "abort failed\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); break; case CMD_UNSOLICITED_ABORT: @@ -3218,21 +3218,21 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "%p retried too many times\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ABORT); break; case CMD_TIMEOUT: dev_warn(&h->pdev->dev, "cmd %p timedout\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); break; case CMD_UNABORTABLE: dev_warn(&h->pdev->dev, "cmd %p unabortable\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); break; default: @@ -3241,7 +3241,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, cmd->err_info->CommandStatus); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_is_passthrough(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index fcc9dcfdf675..40c979b777b8 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1937,7 +1937,7 @@ nvme_fc_complete_rq(struct request *rq) return; } - if (rq->cmd_type == REQ_TYPE_DRV_PRIV) + if (blk_rq_is_passthrough(rq)) error = rq->errors; else error = nvme_error_status(rq->errors); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 7103bce4ba4f..f29365b8c9be 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -588,7 +588,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, */ if (ns && ns->ms && !blk_integrity_rq(req)) { if (!(ns->pi_type && ns->ms == 8) && - req->cmd_type != REQ_TYPE_DRV_PRIV) { + !blk_rq_is_passthrough(req)) { blk_mq_end_request(req, -EFAULT); return BLK_MQ_RQ_QUEUE_OK; } @@ -645,7 +645,7 @@ static void nvme_complete_rq(struct request *req) return; } - if (req->cmd_type == REQ_TYPE_DRV_PRIV) + if (blk_rq_is_passthrough(req)) error = req->errors; else error = nvme_error_status(req->errors); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 557f29b1f1bb..ecc79b2fcfaf 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1423,7 +1423,7 @@ static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) { struct nvme_command *cmd = nvme_req(rq)->cmd; - if (rq->cmd_type != REQ_TYPE_DRV_PRIV || + if (!blk_rq_is_passthrough(rq) || cmd->common.opcode != nvme_fabrics_command || cmd->fabrics.fctype != nvme_fabrics_type_connect) return false; @@ -1522,7 +1522,7 @@ static void nvme_rdma_complete_rq(struct request *rq) return; } - if (rq->cmd_type == REQ_TYPE_DRV_PRIV) + if (blk_rq_is_passthrough(rq)) error = rq->errors; else error = nvme_error_status(rq->errors); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 9aaa70071ae5..f3862e38f574 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -104,7 +104,7 @@ static void nvme_loop_complete_rq(struct request *req) return; } - if (req->cmd_type == REQ_TYPE_DRV_PRIV) + if (blk_rq_is_passthrough(req)) error = req->errors; else error = nvme_error_status(req->errors); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index cbc0c5fe5a60..c611412a8de9 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -5539,8 +5539,8 @@ static int hpsa_scsi_queue_command(struct Scsi_Host *sh, struct scsi_cmnd *cmd) * Retries always go down the normal I/O path. */ if (likely(cmd->retries == 0 && - cmd->request->cmd_type == REQ_TYPE_FS && - h->acciopath_status)) { + !blk_rq_is_passthrough(cmd->request) && + h->acciopath_status)) { rc = hpsa_ioaccel_submit(h, c, cmd, scsi3addr); if (rc == 0) return 0; diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 3d8d2153b448..7bfbcfa7af40 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -238,7 +238,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd) "(result %x)\n", cmd->result)); good_bytes = scsi_bufflen(cmd); - if (cmd->request->cmd_type != REQ_TYPE_BLOCK_PC) { + if (!blk_rq_is_passthrough(cmd->request)) { int old_good_bytes = good_bytes; drv = scsi_cmd_to_driver(cmd); if (drv->done) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 4b40f746d534..b4ce7bb5d2a9 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1106,7 +1106,7 @@ static int scsi_request_sense(struct scsi_cmnd *scmd) static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn) { - if (scmd->request->cmd_type != REQ_TYPE_BLOCK_PC) { + if (!blk_rq_is_passthrough(scmd->request)) { struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); if (sdrv->eh_action) rtn = sdrv->eh_action(scmd, rtn); @@ -1746,7 +1746,7 @@ check_type: * the check condition was retryable. */ if (scmd->request->cmd_flags & REQ_FAILFAST_DEV || - scmd->request->cmd_type == REQ_TYPE_BLOCK_PC) + blk_rq_is_passthrough(scmd->request)) return 1; else return 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 8188e5c71f75..31629a7b728d 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -582,7 +582,7 @@ void scsi_run_host_queues(struct Scsi_Host *shost) static void scsi_uninit_cmd(struct scsi_cmnd *cmd) { - if (cmd->request->cmd_type == REQ_TYPE_FS) { + if (!blk_rq_is_passthrough(cmd->request)) { struct scsi_driver *drv = scsi_cmd_to_driver(cmd); if (drv->uninit_command) @@ -806,7 +806,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) sense_deferred = scsi_sense_is_deferred(&sshdr); } - if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */ + if (blk_rq_is_passthrough(req)) { if (result) { if (sense_valid) { /* @@ -847,7 +847,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) error = __scsi_error_from_host_byte(cmd, result); } - /* no bidi support for !REQ_TYPE_BLOCK_PC yet */ + /* no bidi support for !blk_rq_is_passthrough yet */ BUG_ON(blk_bidi_rq(req)); /* diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 8702d9cf8040..11c0dfb3dfa3 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -4499,7 +4499,7 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost, if (pqi_is_logical_device(device)) { raid_bypassed = false; if (device->offload_enabled && - scmd->request->cmd_type == REQ_TYPE_FS) { + !blk_rq_is_passthrough(scmd->request)) { rc = pqi_raid_bypass_submit_scsi_cmd(ctrl_info, device, scmd, queue_group); if (rc == 0 || diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c index 88db6992420e..bcf7d05d1aab 100644 --- a/drivers/scsi/sun3_scsi.c +++ b/drivers/scsi/sun3_scsi.c @@ -260,7 +260,7 @@ static int sun3scsi_dma_xfer_len(struct NCR5380_hostdata *hostdata, { int wanted_len = cmd->SCp.this_residual; - if (wanted_len < DMA_MIN_SIZE || cmd->request->cmd_type != REQ_TYPE_FS) + if (wanted_len < DMA_MIN_SIZE || blk_rq_is_passthrough(cmd->request)) return 0; return wanted_len; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e4c5f284fe2d..7121be081517 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -242,6 +242,11 @@ struct request { struct request *next_rq; }; +static inline bool blk_rq_is_passthrough(struct request *rq) +{ + return rq->cmd_type != REQ_TYPE_FS; +} + static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; @@ -698,9 +703,10 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) -#define blk_account_rq(rq) \ - (((rq)->rq_flags & RQF_STARTED) && \ - ((rq)->cmd_type == REQ_TYPE_FS)) +static inline bool blk_account_rq(struct request *rq) +{ + return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); +} #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) @@ -775,7 +781,7 @@ static inline void blk_clear_rl_full(struct request_list *rl, bool sync) static inline bool rq_mergeable(struct request *rq) { - if (rq->cmd_type != REQ_TYPE_FS) + if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) @@ -1049,7 +1055,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, { struct request_queue *q = rq->q; - if (unlikely(rq->cmd_type != REQ_TYPE_FS)) + if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index a143a67a6f33..341f9418bd68 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -114,12 +114,12 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); static inline sector_t blk_rq_trace_sector(struct request *rq) { - return (rq->cmd_type != REQ_TYPE_FS) ? 0 : blk_rq_pos(rq); + return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) { - return (rq->cmd_type != REQ_TYPE_FS) ? 0 : blk_rq_sectors(rq); + return blk_rq_is_passthrough(rq) ? 0 : blk_rq_sectors(rq); } #endif diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index f708f1acfc50..b379f93a2c48 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -151,7 +151,7 @@ static inline void *scsi_cmd_priv(struct scsi_cmnd *cmd) return cmd + 1; } -/* make sure not to use it with REQ_TYPE_BLOCK_PC commands */ +/* make sure not to use it with passthrough commands */ static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd) { return *(struct scsi_driver **)cmd->request->rq_disk->private_data; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 512b34703ac3..e33050e3ea1c 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -712,7 +712,7 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (likely(!bt)) return; - if (rq->cmd_type != REQ_TYPE_FS) + if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); else what |= BLK_TC_ACT(BLK_TC_FS); -- cgit v1.2.3-59-g8ed1b From aebf526b53aea164508730427597d45f3e06b376 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 31 Jan 2017 16:57:31 +0100 Subject: block: fold cmd_type into the REQ_OP_ space Instead of keeping two levels of indirection for requests types, fold it all into the operations. The little caveat here is that previously cmd_type only applied to struct request, while the request and bio op fields were set to plain REQ_OP_READ/WRITE even for passthrough operations. Instead this patch adds new REQ_OP_* for SCSI passthrough and driver private requests, althought it has to add two for each so that we can communicate the data in/out nature of the request. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/bio.c | 10 ----- block/blk-core.c | 6 +-- block/blk-flush.c | 1 - block/blk-map.c | 13 ++++--- block/blk-mq-debugfs.c | 4 +- block/bsg.c | 17 ++++----- block/scsi_ioctl.c | 9 +++-- drivers/block/cciss.c | 13 +++++-- drivers/block/floppy.c | 4 +- drivers/block/hd.c | 45 +++++++++++----------- drivers/block/mg_disk.c | 31 +++++++++------- drivers/block/nbd.c | 19 ++++++---- drivers/block/null_blk.c | 4 +- drivers/block/osdblk.c | 6 --- drivers/block/paride/pd.c | 15 +++----- drivers/block/pktcdvd.c | 2 +- drivers/block/ps3disk.c | 15 +++++--- drivers/block/rbd.c | 22 ++++++----- drivers/block/sx8.c | 4 +- drivers/block/virtio_blk.c | 61 +++++++++++++++--------------- drivers/block/xen-blkfront.c | 2 +- drivers/block/xsysace.c | 2 +- drivers/cdrom/cdrom.c | 2 +- drivers/cdrom/gdrom.c | 29 ++++++++------- drivers/ide/ide-atapi.c | 21 ++++++----- drivers/ide/ide-cd.c | 76 ++++++++++++++++++++++---------------- drivers/ide/ide-cd_ioctl.c | 3 +- drivers/ide/ide-devsets.c | 3 +- drivers/ide/ide-disk.c | 9 ++--- drivers/ide/ide-eh.c | 2 +- drivers/ide/ide-floppy.c | 19 +++++----- drivers/ide/ide-io.c | 2 +- drivers/ide/ide-ioctls.c | 6 +-- drivers/ide/ide-park.c | 6 +-- drivers/ide/ide-pm.c | 10 ++--- drivers/ide/ide-tape.c | 5 +-- drivers/ide/ide-taskfile.c | 6 +-- drivers/mtd/mtd_blkdevs.c | 13 +++---- drivers/mtd/ubi/block.c | 15 ++++---- drivers/nvme/host/core.c | 26 +++++++++---- drivers/nvme/host/rdma.c | 2 +- drivers/scsi/osd/osd_initiator.c | 3 +- drivers/scsi/osst.c | 3 +- drivers/scsi/scsi_error.c | 2 +- drivers/scsi/scsi_lib.c | 30 +++++++-------- drivers/scsi/sg.c | 3 +- drivers/scsi/sr.c | 9 +++-- drivers/scsi/st.c | 6 +-- drivers/target/target_core_pscsi.c | 3 +- fs/nfsd/blocklayout.c | 2 +- include/linux/blk_types.h | 7 ++++ include/linux/blkdev.h | 22 +++++------ include/linux/ide.h | 14 +++---- 53 files changed, 338 insertions(+), 326 deletions(-) (limited to 'block') diff --git a/block/bio.c b/block/bio.c index 2b375020fc49..9a2dd7145e83 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1227,9 +1227,6 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (!bio) goto out_bmd; - if (iter->type & WRITE) - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - ret = 0; if (map_data) { @@ -1394,12 +1391,6 @@ struct bio *bio_map_user_iov(struct request_queue *q, kfree(pages); - /* - * set data direction, and check if mapped pages need bouncing - */ - if (iter->type & WRITE) - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - bio_set_flag(bio, BIO_USER_MAPPED); /* @@ -1590,7 +1581,6 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len, bio->bi_private = data; } else { bio->bi_end_io = bio_copy_kern_endio; - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); } return bio; diff --git a/block/blk-core.c b/block/blk-core.c index 44431086e4e7..3266daaa343f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -158,8 +158,8 @@ static void req_bio_endio(struct request *rq, struct bio *bio, void blk_dump_rq_flags(struct request *rq, char *msg) { - printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg, - rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type, + printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, + rq->rq_disk ? rq->rq_disk->disk_name : "?", (unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", @@ -1593,7 +1593,6 @@ out: void init_request_from_bio(struct request *req, struct bio *bio) { - req->cmd_type = REQ_TYPE_FS; if (bio->bi_opf & REQ_RAHEAD) req->cmd_flags |= REQ_FAILFAST_MASK; @@ -2983,7 +2982,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); static void __blk_rq_prep_clone(struct request *dst, struct request *src) { dst->cpu = src->cpu; - dst->cmd_type = src->cmd_type; dst->__sector = blk_rq_pos(src); dst->__data_len = blk_rq_bytes(src); dst->nr_phys_segments = src->nr_phys_segments; diff --git a/block/blk-flush.c b/block/blk-flush.c index 0a0358e48b76..968162579234 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -327,7 +327,6 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq) blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq); } - flush_rq->cmd_type = REQ_TYPE_FS; flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH; flush_rq->rq_flags |= RQF_FLUSH_SEQ; flush_rq->rq_disk = first_rq->rq_disk; diff --git a/block/blk-map.c b/block/blk-map.c index 0acb6640ead7..2f18c2a0be1b 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -16,8 +16,6 @@ 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)) @@ -62,6 +60,9 @@ static int __blk_rq_map_user_iov(struct request *rq, if (IS_ERR(bio)) return PTR_ERR(bio); + bio->bi_opf &= ~REQ_OP_MASK; + bio->bi_opf |= req_op(rq); + if (map_data && map_data->null_mapped) bio_set_flag(bio, BIO_NULL_MAPPED); @@ -90,7 +91,7 @@ static int __blk_rq_map_user_iov(struct request *rq, } /** - * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage + * blk_rq_map_user_iov - map user data to a request, for passthrough requests * @q: request queue where request should be inserted * @rq: request to map data to * @map_data: pointer to the rq_map_data holding pages (if necessary) @@ -199,7 +200,7 @@ int blk_rq_unmap_user(struct bio *bio) EXPORT_SYMBOL(blk_rq_unmap_user); /** - * blk_rq_map_kern - map kernel data to a request, for REQ_TYPE_BLOCK_PC usage + * blk_rq_map_kern - map kernel data to a request, for passthrough requests * @q: request queue where request should be inserted * @rq: request to fill * @kbuf: the kernel buffer @@ -234,8 +235,8 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, if (IS_ERR(bio)) return PTR_ERR(bio); - if (!reading) - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + bio->bi_opf &= ~REQ_OP_MASK; + bio->bi_opf |= req_op(rq); if (do_copy) rq->rq_flags |= RQF_COPY_USER; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 5cd2b435a9f5..1e2a4a2ff623 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -88,8 +88,8 @@ static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v) { struct request *rq = list_entry_rq(v); - seq_printf(m, "%p {.cmd_type=%u, .cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n", - rq, rq->cmd_type, rq->cmd_flags, (unsigned int)rq->rq_flags, + seq_printf(m, "%p {.cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n", + rq, rq->cmd_flags, (unsigned int)rq->rq_flags, rq->tag, rq->internal_tag); return 0; } diff --git a/block/bsg.c b/block/bsg.c index e34c3320956c..a9a8b8e0446f 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -177,7 +177,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, * Check if sg_io_v4 from user is allowed and valid */ static int -bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw) +bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *op) { int ret = 0; @@ -198,7 +198,7 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw) ret = -EINVAL; } - *rw = hdr->dout_xfer_len ? WRITE : READ; + *op = hdr->dout_xfer_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN; return ret; } @@ -210,8 +210,8 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm) { struct request_queue *q = bd->queue; struct request *rq, *next_rq = NULL; - int ret, rw; - unsigned int dxfer_len; + int ret; + unsigned int op, dxfer_len; void __user *dxferp = NULL; struct bsg_class_device *bcd = &q->bsg_dev; @@ -226,14 +226,14 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm) hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp, hdr->din_xfer_len); - ret = bsg_validate_sgv4_hdr(hdr, &rw); + ret = bsg_validate_sgv4_hdr(hdr, &op); if (ret) return ERR_PTR(ret); /* * map scatter-gather elements separately and string them to request */ - rq = blk_get_request(q, rw, GFP_KERNEL); + rq = blk_get_request(q, op, GFP_KERNEL); if (IS_ERR(rq)) return rq; scsi_req_init(rq); @@ -242,20 +242,19 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm) if (ret) goto out; - if (rw == WRITE && hdr->din_xfer_len) { + if (op == REQ_OP_SCSI_OUT && hdr->din_xfer_len) { if (!test_bit(QUEUE_FLAG_BIDI, &q->queue_flags)) { ret = -EOPNOTSUPP; goto out; } - next_rq = blk_get_request(q, READ, GFP_KERNEL); + next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(next_rq)) { ret = PTR_ERR(next_rq); next_rq = NULL; goto out; } rq->next_rq = next_rq; - next_rq->cmd_type = rq->cmd_type; dxferp = (void __user *)(unsigned long)hdr->din_xferp; ret = blk_rq_map_user(q, next_rq, NULL, dxferp, diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 7edf44f25e08..2a2fc768b27a 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -321,7 +321,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, at_head = 1; ret = -ENOMEM; - rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL); + rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, + GFP_KERNEL); if (IS_ERR(rq)) return PTR_ERR(rq); req = scsi_req(rq); @@ -448,7 +449,8 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, } - rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM); + rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, + __GFP_RECLAIM); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto error_free_buffer; @@ -537,7 +539,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, struct request *rq; int err; - rq = blk_get_request(q, WRITE, __GFP_RECLAIM); + rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); scsi_req_init(rq); @@ -745,7 +747,6 @@ void scsi_req_init(struct request *rq) { struct scsi_request *req = scsi_req(rq); - rq->cmd_type = REQ_TYPE_BLOCK_PC; memset(req->__cmd, 0, sizeof(req->__cmd)); req->cmd = req->__cmd; req->cmd_len = BLK_MAX_CDB; diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 53dc2971a3ba..f21c2f0c5ccd 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -3394,7 +3394,9 @@ static void do_cciss_request(struct request_queue *q) c->Header.SGList = h->max_cmd_sgentries; set_performant_mode(h, c); - if (likely(creq->cmd_type == REQ_TYPE_FS)) { + switch (req_op(creq)) { + case REQ_OP_READ: + case REQ_OP_WRITE: if(h->cciss_read == CCISS_READ_10) { c->Request.CDB[1] = 0; c->Request.CDB[2] = (start_blk >> 24) & 0xff; /* MSB */ @@ -3424,13 +3426,16 @@ static void do_cciss_request(struct request_queue *q) c->Request.CDB[13]= blk_rq_sectors(creq) & 0xff; c->Request.CDB[14] = c->Request.CDB[15] = 0; } - } else if (creq->cmd_type == REQ_TYPE_BLOCK_PC) { + break; + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: c->Request.CDBLen = scsi_req(creq)->cmd_len; memcpy(c->Request.CDB, scsi_req(creq)->cmd, BLK_MAX_CDB); scsi_req(creq)->sense = c->err_info->SenseInfo; - } else { + break; + default: dev_warn(&h->pdev->dev, "bad request type %d\n", - creq->cmd_type); + creq->cmd_flags); BUG(); } diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 184887af4b9f..45b4384f650c 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2900,8 +2900,8 @@ static void do_fd_request(struct request_queue *q) return; if (WARN(atomic_read(&usage_count) == 0, - "warning: usage count=0, current_req=%p sect=%ld type=%x flags=%llx\n", - current_req, (long)blk_rq_pos(current_req), current_req->cmd_type, + "warning: usage count=0, current_req=%p sect=%ld flags=%llx\n", + current_req, (long)blk_rq_pos(current_req), (unsigned long long) current_req->cmd_flags)) return; diff --git a/drivers/block/hd.c b/drivers/block/hd.c index a9b48ed7a3cd..6043648da1e8 100644 --- a/drivers/block/hd.c +++ b/drivers/block/hd.c @@ -626,30 +626,29 @@ repeat: req_data_dir(req) == READ ? "read" : "writ", cyl, head, sec, nsect, bio_data(req->bio)); #endif - if (req->cmd_type == REQ_TYPE_FS) { - switch (rq_data_dir(req)) { - case READ: - hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ, - &read_intr); - if (reset) - goto repeat; - break; - case WRITE: - hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE, - &write_intr); - if (reset) - goto repeat; - if (wait_DRQ()) { - bad_rw_intr(); - goto repeat; - } - outsw(HD_DATA, bio_data(req->bio), 256); - break; - default: - printk("unknown hd-command\n"); - hd_end_request_cur(-EIO); - break; + + switch (req_op(req)) { + case REQ_OP_READ: + hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ, + &read_intr); + if (reset) + goto repeat; + break; + case REQ_OP_WRITE: + hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE, + &write_intr); + if (reset) + goto repeat; + if (wait_DRQ()) { + bad_rw_intr(); + goto repeat; } + outsw(HD_DATA, bio_data(req->bio), 256); + break; + default: + printk("unknown hd-command\n"); + hd_end_request_cur(-EIO); + break; } } diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c index e937fcf71769..286f276f586e 100644 --- a/drivers/block/mg_disk.c +++ b/drivers/block/mg_disk.c @@ -670,15 +670,17 @@ static void mg_request_poll(struct request_queue *q) break; } - if (unlikely(host->req->cmd_type != REQ_TYPE_FS)) { - mg_end_request_cur(host, -EIO); - continue; - } - - if (rq_data_dir(host->req) == READ) + switch (req_op(host->req)) { + case REQ_OP_READ: mg_read(host->req); - else + break; + case REQ_OP_WRITE: mg_write(host->req); + break; + default: + mg_end_request_cur(host, -EIO); + break; + } } } @@ -687,13 +689,15 @@ static unsigned int mg_issue_req(struct request *req, unsigned int sect_num, unsigned int sect_cnt) { - if (rq_data_dir(req) == READ) { + switch (req_op(host->req)) { + case REQ_OP_READ: if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr) != MG_ERR_NONE) { mg_bad_rw_intr(host); return host->error; } - } else { + break; + case REQ_OP_WRITE: /* TODO : handler */ outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL); if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr) @@ -712,6 +716,10 @@ static unsigned int mg_issue_req(struct request *req, mod_timer(&host->timer, jiffies + 3 * HZ); outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND); + break; + default: + mg_end_request_cur(host, -EIO); + break; } return MG_ERR_NONE; } @@ -753,11 +761,6 @@ static void mg_request(struct request_queue *q) continue; } - if (unlikely(req->cmd_type != REQ_TYPE_FS)) { - mg_end_request_cur(host, -EIO); - continue; - } - if (!mg_issue_req(req, host, sect_num, sect_cnt)) return; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 8bce1c7c18d5..58296e4427b0 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -271,17 +271,22 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) u32 type; u32 tag = blk_mq_unique_tag(req); - if (req->cmd_type != REQ_TYPE_FS) - return -EIO; - - if (req_op(req) == REQ_OP_DISCARD) + switch (req_op(req)) { + case REQ_OP_DISCARD: type = NBD_CMD_TRIM; - else if (req_op(req) == REQ_OP_FLUSH) + break; + case REQ_OP_FLUSH: type = NBD_CMD_FLUSH; - else if (rq_data_dir(req) == WRITE) + break; + case REQ_OP_WRITE: type = NBD_CMD_WRITE; - else + break; + case REQ_OP_READ: type = NBD_CMD_READ; + break; + default: + return -EIO; + } if (rq_data_dir(req) == WRITE && (nbd->flags & NBD_FLAG_READ_ONLY)) { diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index c0e14e54909b..4335b84a565b 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -431,11 +431,11 @@ static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) struct request *rq; struct bio *bio = rqd->bio; - rq = blk_mq_alloc_request(q, bio_data_dir(bio), 0); + rq = blk_mq_alloc_request(q, + op_is_write(bio_op(bio)) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return -ENOMEM; - rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->__sector = bio->bi_iter.bi_sector; rq->ioprio = bio_prio(bio); diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index 92900f5f0b47..8127b8201a01 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -308,12 +308,6 @@ static void osdblk_rq_fn(struct request_queue *q) if (!rq) break; - /* filter out block requests we don't understand */ - if (rq->cmd_type != REQ_TYPE_FS) { - blk_end_request_all(rq, 0); - continue; - } - /* deduce our operation (read, write, flush) */ /* I wish the block layer simplified cmd_type/cmd_flags/cmd[] * into a clearly defined set of RPC commands: diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index c3ed2fc72daa..644ba0888bd4 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -439,18 +439,16 @@ static int pd_retries = 0; /* i/o error retry count */ static int pd_block; /* address of next requested block */ static int pd_count; /* number of blocks still to do */ static int pd_run; /* sectors in current cluster */ -static int pd_cmd; /* current command READ/WRITE */ static char *pd_buf; /* buffer for request in progress */ static enum action do_pd_io_start(void) { - if (pd_req->cmd_type == REQ_TYPE_DRV_PRIV) { + switch (req_op(pd_req)) { + case REQ_OP_DRV_IN: phase = pd_special; return pd_special(); - } - - pd_cmd = rq_data_dir(pd_req); - if (pd_cmd == READ || pd_cmd == WRITE) { + case REQ_OP_READ: + case REQ_OP_WRITE: pd_block = blk_rq_pos(pd_req); pd_count = blk_rq_cur_sectors(pd_req); if (pd_block + pd_count > get_capacity(pd_req->rq_disk)) @@ -458,7 +456,7 @@ static enum action do_pd_io_start(void) pd_run = blk_rq_sectors(pd_req); pd_buf = bio_data(pd_req->bio); pd_retries = 0; - if (pd_cmd == READ) + if (req_op(pd_req) == REQ_OP_READ) return do_pd_read_start(); else return do_pd_write_start(); @@ -723,11 +721,10 @@ static int pd_special_command(struct pd_unit *disk, struct request *rq; int err = 0; - rq = blk_get_request(disk->gd->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; rq->special = func; err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 918a92ccd0c0..f4bd95943dc2 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -704,7 +704,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * int ret = 0; rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ? - WRITE : READ, __GFP_RECLAIM); + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM); if (IS_ERR(rq)) return PTR_ERR(rq); scsi_req_init(rq); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 76f33c84ce3d..a809e3e9feb8 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -196,16 +196,19 @@ static void ps3disk_do_request(struct ps3_storage_device *dev, dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__); while ((req = blk_fetch_request(q))) { - if (req_op(req) == REQ_OP_FLUSH) { + switch (req_op(req)) { + case REQ_OP_FLUSH: if (ps3disk_submit_flush_request(dev, req)) - break; - } else if (req->cmd_type == REQ_TYPE_FS) { + return; + break; + case REQ_OP_READ: + case REQ_OP_WRITE: if (ps3disk_submit_request_sg(dev, req)) - break; - } else { + return; + break; + default: blk_dump_rq_flags(req, DEVICE_NAME " bad request"); __blk_end_request_all(req, -EIO); - continue; } } } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 36d2b9f4e836..4d78cf605b21 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4099,19 +4099,21 @@ static void rbd_queue_workfn(struct work_struct *work) bool must_be_locked; int result; - if (rq->cmd_type != REQ_TYPE_FS) { - dout("%s: non-fs request type %d\n", __func__, - (int) rq->cmd_type); - result = -EIO; - goto err; - } - - if (req_op(rq) == REQ_OP_DISCARD) + switch (req_op(rq)) { + case REQ_OP_DISCARD: op_type = OBJ_OP_DISCARD; - else if (req_op(rq) == REQ_OP_WRITE) + break; + case REQ_OP_WRITE: op_type = OBJ_OP_WRITE; - else + break; + case REQ_OP_READ: op_type = OBJ_OP_READ; + break; + default: + dout("%s: non-fs request type %d\n", __func__, req_op(rq)); + result = -EIO; + goto err; + } /* Ignore/skip any zero-length requests */ diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 0e93ad7b8511..c8e072caf56f 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -567,7 +567,7 @@ static struct carm_request *carm_get_special(struct carm_host *host) if (!crq) return NULL; - rq = blk_get_request(host->oob_q, WRITE /* bogus */, GFP_KERNEL); + rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, GFP_KERNEL); if (IS_ERR(rq)) { spin_lock_irqsave(&host->lock, flags); carm_put_request(host, crq); @@ -620,7 +620,6 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx) spin_unlock_irq(&host->lock); DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx); - crq->rq->cmd_type = REQ_TYPE_DRV_PRIV; crq->rq->special = crq; blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL); @@ -661,7 +660,6 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func) crq->msg_bucket = (u32) rc; DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx); - crq->rq->cmd_type = REQ_TYPE_DRV_PRIV; crq->rq->special = crq; blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index d9491bdd3ad3..a363170e45b1 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -175,11 +175,12 @@ static inline void virtblk_request_done(struct request *req) struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); int error = virtblk_result(vbr); - switch (req->cmd_type) { - case REQ_TYPE_BLOCK_PC: + switch (req_op(req)) { + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: virtblk_scsi_reques_done(req); break; - case REQ_TYPE_DRV_PRIV: + case REQ_OP_DRV_IN: req->errors = (error != 0); break; } @@ -226,36 +227,35 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, int qid = hctx->queue_num; int err; bool notify = false; + u32 type; BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); - if (req_op(req) == REQ_OP_FLUSH) { - vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH); - vbr->out_hdr.sector = 0; - vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req)); - } else { - switch (req->cmd_type) { - case REQ_TYPE_FS: - vbr->out_hdr.type = 0; - vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(req)); - vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req)); - break; - case REQ_TYPE_BLOCK_PC: - vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD); - vbr->out_hdr.sector = 0; - vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req)); - break; - case REQ_TYPE_DRV_PRIV: - vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID); - vbr->out_hdr.sector = 0; - vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req)); - break; - default: - /* We don't put anything else in the queue. */ - BUG(); - } + switch (req_op(req)) { + case REQ_OP_READ: + case REQ_OP_WRITE: + type = 0; + break; + case REQ_OP_FLUSH: + type = VIRTIO_BLK_T_FLUSH; + break; + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: + type = VIRTIO_BLK_T_SCSI_CMD; + break; + case REQ_OP_DRV_IN: + type = VIRTIO_BLK_T_GET_ID; + break; + default: + WARN_ON_ONCE(1); + return BLK_MQ_RQ_QUEUE_ERROR; } + vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type); + vbr->out_hdr.sector = type ? + 0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req)); + vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req)); + blk_mq_start_request(req); num = blk_rq_map_sg(hctx->queue, req, vbr->sg); @@ -267,7 +267,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, } spin_lock_irqsave(&vblk->vqs[qid].lock, flags); - if (req->cmd_type == REQ_TYPE_BLOCK_PC) + if (req_op(req) == REQ_OP_SCSI_IN || req_op(req) == REQ_OP_SCSI_OUT) err = virtblk_add_req_scsi(vblk->vqs[qid].vq, vbr, vbr->sg, num); else err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num); @@ -300,10 +300,9 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) struct request *req; int err; - req = blk_get_request(q, READ, GFP_KERNEL); + req = blk_get_request(q, REQ_OP_DRV_IN, GFP_KERNEL); if (IS_ERR(req)) return PTR_ERR(req); - req->cmd_type = REQ_TYPE_DRV_PRIV; err = blk_rq_map_kern(q, req, id_str, VIRTIO_BLK_ID_BYTES, GFP_KERNEL); if (err) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index b2bdfa81f929..9a8cb226cb3a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -865,7 +865,7 @@ static inline void flush_requests(struct blkfront_ring_info *rinfo) static inline bool blkif_request_flush_invalid(struct request *req, struct blkfront_info *info) { - return ((req->cmd_type != REQ_TYPE_FS) || + return (blk_rq_is_passthrough(req) || ((req_op(req) == REQ_OP_FLUSH) && !info->feature_flush) || ((req->cmd_flags & REQ_FUA) && diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index c4328d9d9981..757dce2147e0 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -468,7 +468,7 @@ static struct request *ace_get_next_request(struct request_queue *q) struct request *req; while ((req = blk_peek_request(q)) != NULL) { - if (req->cmd_type == REQ_TYPE_FS) + if (!blk_rq_is_passthrough(req)) break; blk_start_request(req); __blk_end_request_all(req, -EIO); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 36f5237a8a69..8f496b4f3dd1 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2191,7 +2191,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf, len = nr * CD_FRAMESIZE_RAW; - rq = blk_get_request(q, READ, GFP_KERNEL); + rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(rq)) { ret = PTR_ERR(rq); break; diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 584bc3126403..b6f1a5d95bc5 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -659,23 +659,24 @@ static void gdrom_request(struct request_queue *rq) struct request *req; while ((req = blk_fetch_request(rq)) != NULL) { - if (req->cmd_type != REQ_TYPE_FS) { - printk(KERN_DEBUG "gdrom: Non-fs request ignored\n"); - __blk_end_request_all(req, -EIO); - continue; - } - if (rq_data_dir(req) != READ) { + switch (req_op(req)) { + case REQ_OP_READ: + /* + * Add to list of deferred work and then schedule + * workqueue. + */ + list_add_tail(&req->queuelist, &gdrom_deferred); + schedule_work(&work); + break; + case REQ_OP_WRITE: pr_notice("Read only device - write request ignored\n"); __blk_end_request_all(req, -EIO); - continue; + break; + default: + printk(KERN_DEBUG "gdrom: Non-fs request ignored\n"); + __blk_end_request_all(req, -EIO); + break; } - - /* - * Add to list of deferred work and then schedule - * workqueue. - */ - list_add_tail(&req->queuelist, &gdrom_deferred); - schedule_work(&work); } } diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index a8c650e8c92e..feb30061123b 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -92,9 +92,8 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk, struct request *rq; int error; - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_MISC; rq->special = (char *)pc; @@ -212,7 +211,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) } sense_rq->rq_disk = rq->rq_disk; - sense_rq->cmd_type = REQ_TYPE_DRV_PRIV; + sense_rq->cmd_flags = REQ_OP_DRV_IN; ide_req(sense_rq)->type = ATA_PRIV_SENSE; sense_rq->rq_flags |= RQF_PREEMPT; @@ -312,19 +311,21 @@ EXPORT_SYMBOL_GPL(ide_cd_expiry); int ide_cd_get_xferlen(struct request *rq) { - switch (rq->cmd_type) { - case REQ_TYPE_FS: + switch (req_op(rq)) { + default: return 32768; - case REQ_TYPE_BLOCK_PC: + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: return blk_rq_bytes(rq); - case REQ_TYPE_DRV_PRIV: + case REQ_OP_DRV_IN: + case REQ_OP_DRV_OUT: switch (ide_req(rq)->type) { case ATA_PRIV_PC: case ATA_PRIV_SENSE: return blk_rq_bytes(rq); + default: + return 0; } - default: - return 0; } } EXPORT_SYMBOL_GPL(ide_cd_get_xferlen); @@ -491,7 +492,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) error = 0; } else { - if (rq->cmd_type != REQ_TYPE_FS && uptodate <= 0) { + if (blk_rq_is_passthrough(rq) && uptodate <= 0) { if (rq->errors == 0) rq->errors = -EIO; } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 207af7816544..dc039d150357 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -176,7 +176,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive, if (!sense->valid) break; if (failed_command == NULL || - failed_command->cmd_type != REQ_TYPE_FS) + blk_rq_is_passthrough(failed_command)) break; sector = (sense->information[0] << 24) | (sense->information[1] << 16) | @@ -293,7 +293,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) } /* if we have an error, pass CHECK_CONDITION as the SCSI status byte */ - if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !rq->errors) + if (blk_rq_is_scsi(rq) && !rq->errors) rq->errors = SAM_STAT_CHECK_CONDITION; if (blk_noretry_request(rq)) @@ -301,13 +301,13 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) switch (sense_key) { case NOT_READY: - if (rq->cmd_type == REQ_TYPE_FS && rq_data_dir(rq) == WRITE) { + if (req_op(rq) == REQ_OP_WRITE) { if (ide_cd_breathe(drive, rq)) return 1; } else { cdrom_saw_media_change(drive); - if (rq->cmd_type == REQ_TYPE_FS && + if (!blk_rq_is_passthrough(rq) && !(rq->rq_flags & RQF_QUIET)) printk(KERN_ERR PFX "%s: tray open\n", drive->name); @@ -317,7 +317,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) case UNIT_ATTENTION: cdrom_saw_media_change(drive); - if (rq->cmd_type != REQ_TYPE_FS) + if (blk_rq_is_passthrough(rq)) return 0; /* @@ -365,7 +365,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) do_end_request = 1; break; default: - if (rq->cmd_type != REQ_TYPE_FS) + if (blk_rq_is_passthrough(rq)) break; if (err & ~ATA_ABORTED) { /* go to the default handler for other errors */ @@ -376,7 +376,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) do_end_request = 1; } - if (rq->cmd_type != REQ_TYPE_FS) { + if (blk_rq_is_passthrough(rq)) { rq->rq_flags |= RQF_FAILED; do_end_request = 1; } @@ -435,10 +435,10 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd, int error; bool delay = false; - rq = blk_get_request(drive->queue, write, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, + write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_PC; rq->rq_flags |= rq_flags; rq->timeout = timeout; @@ -564,7 +564,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) ide_read_bcount_and_ireason(drive, &len, &ireason); - thislen = (rq->cmd_type == REQ_TYPE_FS) ? len : cmd->nleft; + thislen = !blk_rq_is_passthrough(rq) ? len : cmd->nleft; if (thislen > len) thislen = len; @@ -573,7 +573,8 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) /* If DRQ is clear, the command has completed. */ if ((stat & ATA_DRQ) == 0) { - if (rq->cmd_type == REQ_TYPE_FS) { + switch (req_op(rq)) { + default: /* * If we're not done reading/writing, complain. * Otherwise, complete the command normally. @@ -587,7 +588,9 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) rq->rq_flags |= RQF_FAILED; uptodate = 0; } - } else if (rq->cmd_type != REQ_TYPE_BLOCK_PC) { + goto out_end; + case REQ_OP_DRV_IN: + case REQ_OP_DRV_OUT: ide_cd_request_sense_fixup(drive, cmd); uptodate = cmd->nleft ? 0 : 1; @@ -603,8 +606,11 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) if (!uptodate) rq->rq_flags |= RQF_FAILED; + goto out_end; + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: + goto out_end; } - goto out_end; } rc = ide_check_ireason(drive, rq, len, ireason, write); @@ -636,7 +642,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) /* pad, if necessary */ if (len > 0) { - if (rq->cmd_type != REQ_TYPE_FS || write == 0) + if (blk_rq_is_passthrough(rq) || write == 0) ide_pad_transfer(drive, write, len); else { printk(KERN_ERR PFX "%s: confused, missing data\n", @@ -645,12 +651,18 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) } } - if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { + switch (req_op(rq)) { + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: timeout = rq->timeout; - } else { + break; + case REQ_OP_DRV_IN: + case REQ_OP_DRV_OUT: + expiry = ide_cd_expiry; + /*FALLTHRU*/ + default: timeout = ATAPI_WAIT_PC; - if (rq->cmd_type != REQ_TYPE_FS) - expiry = ide_cd_expiry; + break; } hwif->expiry = expiry; @@ -658,7 +670,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) return ide_started; out_end: - if (rq->cmd_type == REQ_TYPE_BLOCK_PC && rc == 0) { + if (blk_rq_is_scsi(rq) && rc == 0) { scsi_req(rq)->resid_len = 0; blk_end_request_all(rq, 0); hwif->rq = NULL; @@ -666,7 +678,7 @@ out_end: if (sense && uptodate) ide_cd_complete_failed_rq(drive, rq); - if (rq->cmd_type == REQ_TYPE_FS) { + if (!blk_rq_is_passthrough(rq)) { if (cmd->nleft == 0) uptodate = 1; } else { @@ -679,7 +691,7 @@ out_end: return ide_stopped; /* make sure it's fully ended */ - if (rq->cmd_type != REQ_TYPE_FS) { + if (blk_rq_is_passthrough(rq)) { scsi_req(rq)->resid_len -= cmd->nbytes - cmd->nleft; if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE)) scsi_req(rq)->resid_len += cmd->last_xfer_len; @@ -739,7 +751,7 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq) ide_debug_log(IDE_DBG_PC, "rq->cmd[0]: 0x%x, rq->cmd_type: 0x%x", rq->cmd[0], rq->cmd_type); - if (rq->cmd_type == REQ_TYPE_BLOCK_PC) + if (blk_rq_is_scsi(rq)) rq->rq_flags |= RQF_QUIET; else rq->rq_flags &= ~RQF_FAILED; @@ -781,18 +793,20 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq, if (drive->debug_mask & IDE_DBG_RQ) blk_dump_rq_flags(rq, "ide_cd_do_request"); - switch (rq->cmd_type) { - case REQ_TYPE_FS: + switch (req_op(rq)) { + default: if (cdrom_start_rw(drive, rq) == ide_stopped) goto out_end; break; - case REQ_TYPE_BLOCK_PC: + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: handle_pc: if (!rq->timeout) rq->timeout = ATAPI_WAIT_PC; cdrom_do_block_pc(drive, rq); break; - case REQ_TYPE_DRV_PRIV: + case REQ_OP_DRV_IN: + case REQ_OP_DRV_OUT: switch (ide_req(rq)->type) { case ATA_PRIV_MISC: /* right now this can only be a reset... */ @@ -801,9 +815,9 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq, case ATA_PRIV_SENSE: case ATA_PRIV_PC: goto handle_pc; + default: + BUG(); } - default: - BUG(); } /* prepare sense request for this command */ @@ -816,7 +830,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq, cmd.rq = rq; - if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) { + if (!blk_rq_is_passthrough(rq) || blk_rq_bytes(rq)) { ide_init_sg_cmd(&cmd, blk_rq_bytes(rq)); ide_map_sg(drive, &cmd); } @@ -1373,9 +1387,9 @@ static int ide_cdrom_prep_pc(struct request *rq) static int ide_cdrom_prep_fn(struct request_queue *q, struct request *rq) { - if (rq->cmd_type == REQ_TYPE_FS) + if (!blk_rq_is_passthrough(rq)) return ide_cdrom_prep_fs(q, rq); - else if (rq->cmd_type == REQ_TYPE_BLOCK_PC) + else if (blk_rq_is_scsi(rq)) return ide_cdrom_prep_pc(rq); return 0; diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 3f03eed0ff78..9fcefbc8425e 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -303,9 +303,8 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi) struct request *rq; int ret; - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_MISC; rq->rq_flags = RQF_QUIET; ret = blk_execute_rq(drive->queue, cd->disk, rq, 0); diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c index c040b9de2b4e..a45dda5386e4 100644 --- a/drivers/ide/ide-devsets.c +++ b/drivers/ide/ide-devsets.c @@ -165,9 +165,8 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting, if (!(setting->flags & DS_SYNC)) return setting->set(drive, arg); - rq = blk_get_request(q, READ, __GFP_RECLAIM); + rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_MISC; scsi_req(rq)->cmd_len = 5; scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC; diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 69cf71729841..186159715b71 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -184,7 +184,7 @@ static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq, ide_hwif_t *hwif = drive->hwif; BUG_ON(drive->dev_flags & IDE_DFLAG_BLOCKED); - BUG_ON(rq->cmd_type != REQ_TYPE_FS); + BUG_ON(blk_rq_is_passthrough(rq)); ledtrig_disk_activity(); @@ -452,8 +452,8 @@ static int idedisk_prep_fn(struct request_queue *q, struct request *rq) cmd->valid.out.tf = IDE_VALID_OUT_TF | IDE_VALID_DEVICE; cmd->tf_flags = IDE_TFLAG_DYN; cmd->protocol = ATA_PROT_NODATA; - - rq->cmd_type = REQ_TYPE_DRV_PRIV; + rq->cmd_flags &= ~REQ_OP_MASK; + rq->cmd_flags |= REQ_OP_DRV_OUT; ide_req(rq)->type = ATA_PRIV_TASKFILE; rq->special = cmd; cmd->rq = rq; @@ -478,9 +478,8 @@ static int set_multcount(ide_drive_t *drive, int arg) if (drive->special_flags & IDE_SFLAG_SET_MULTMODE) return -EBUSY; - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_TASKFILE; drive->mult_req = arg; diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c index 1e4b1476e559..cf3af6840368 100644 --- a/drivers/ide/ide-eh.c +++ b/drivers/ide/ide-eh.c @@ -123,7 +123,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat) return ide_stopped; /* retry only "normal" I/O: */ - if (rq->cmd_type != REQ_TYPE_FS) { + if (blk_rq_is_passthrough(rq)) { if (ata_taskfile_request(rq)) { struct ide_cmd *cmd = rq->special; diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index 24c6d363b3a4..a69e8013f1df 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -72,7 +72,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc) drive->failed_pc = NULL; if (pc->c[0] == GPCMD_READ_10 || pc->c[0] == GPCMD_WRITE_10 || - rq->cmd_type == REQ_TYPE_BLOCK_PC) + (req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT)) uptodate = 1; /* FIXME */ else if (pc->c[0] == GPCMD_REQUEST_SENSE) { @@ -254,8 +254,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, goto out_end; } - switch (rq->cmd_type) { - case REQ_TYPE_FS: + switch (req_op(rq)) { + default: if (((long)blk_rq_pos(rq) % floppy->bs_factor) || (blk_rq_sectors(rq) % floppy->bs_factor)) { printk(KERN_ERR PFX "%s: unsupported r/w rq size\n", @@ -265,11 +265,13 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, pc = &floppy->queued_pc; idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block); break; - case REQ_TYPE_BLOCK_PC: + case REQ_OP_SCSI_IN: + case REQ_OP_SCSI_OUT: pc = &floppy->queued_pc; idefloppy_blockpc_cmd(floppy, pc, rq); break; - case REQ_TYPE_DRV_PRIV: + case REQ_OP_DRV_IN: + case REQ_OP_DRV_OUT: switch (ide_req(rq)->type) { case ATA_PRIV_MISC: case ATA_PRIV_SENSE: @@ -278,9 +280,6 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, default: BUG(); } - break; - default: - BUG(); } ide_prep_sense(drive, rq); @@ -292,7 +291,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, cmd.rq = rq; - if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) { + if (!blk_rq_is_passthrough(rq) || blk_rq_bytes(rq)) { ide_init_sg_cmd(&cmd, blk_rq_bytes(rq)); ide_map_sg(drive, &cmd); } @@ -302,7 +301,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, return ide_floppy_issue_pc(drive, &cmd, pc); out_end: drive->failed_pc = NULL; - if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0) + if (blk_rq_is_passthrough(rq) && rq->errors == 0) rq->errors = -EIO; ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); return ide_stopped; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 6735c92b8da7..043b1fb963cb 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -145,7 +145,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq) } else { if (media == ide_tape) rq->errors = IDE_DRV_ERROR_GENERAL; - else if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0) + else if (blk_rq_is_passthrough(rq) && rq->errors == 0) rq->errors = -EIO; } diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index fc19e842deef..248a3e0ceb46 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -125,9 +125,8 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg) if (NULL == (void *) arg) { struct request *rq; - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_TASKFILE; err = blk_execute_rq(drive->queue, NULL, rq, 0); blk_put_request(rq); @@ -223,9 +222,8 @@ static int generic_drive_reset(ide_drive_t *drive) struct request *rq; int ret = 0; - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_MISC; scsi_req(rq)->cmd_len = 1; scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET; diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index fc3c944ca4be..101aed9a61ca 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -31,11 +31,10 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) } spin_unlock_irq(&hwif->lock); - rq = blk_get_request(q, READ, __GFP_RECLAIM); + rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); scsi_req(rq)->cmd[0] = REQ_PARK_HEADS; scsi_req(rq)->cmd_len = 1; - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_MISC; rq->special = &timeout; rc = blk_execute_rq(q, NULL, rq, 1); @@ -47,14 +46,13 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) * Make sure that *some* command is sent to the drive after the * timeout has expired, so power management will be reenabled. */ - rq = blk_get_request(q, READ, GFP_NOWAIT); + rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT); scsi_req_init(rq); if (IS_ERR(rq)) goto out; scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS; scsi_req(rq)->cmd_len = 1; - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_MISC; elv_add_request(q, rq, ELEVATOR_INSERT_FRONT); diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index 0c1296815dfa..ec951be4b0c8 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -18,9 +18,8 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) } memset(&rqpm, 0, sizeof(rqpm)); - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_PM_SUSPEND; rq->special = &rqpm; rqpm.pm_step = IDE_PM_START_SUSPEND; @@ -90,9 +89,8 @@ int generic_ide_resume(struct device *dev) } memset(&rqpm, 0, sizeof(rqpm)); - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_PM_RESUME; rq->rq_flags |= RQF_PREEMPT; rq->special = &rqpm; @@ -244,12 +242,12 @@ void ide_check_pm_state(ide_drive_t *drive, struct request *rq) { struct ide_pm_state *pm = rq->special; - if (rq->cmd_type == REQ_TYPE_DRV_PRIV && + if (blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_PM_SUSPEND && pm->pm_step == IDE_PM_START_SUSPEND) /* Mark drive blocked when starting the suspend sequence. */ drive->dev_flags |= IDE_DFLAG_BLOCKED; - else if (rq->cmd_type == REQ_TYPE_DRV_PRIV && + else if (blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_PM_RESUME && pm->pm_step == IDE_PM_START_RESUME) { /* diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index 37c7beabaacc..3c1b7974d66d 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -577,7 +577,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive, req->cmd[0], (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq)); - BUG_ON(rq->cmd_type != REQ_TYPE_DRV_PRIV); + BUG_ON(!blk_rq_is_private(rq)); BUG_ON(ide_req(rq)->type != ATA_PRIV_MISC && ide_req(rq)->type != ATA_PRIV_SENSE); @@ -854,9 +854,8 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size) BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE); BUG_ON(size < 0 || size % tape->blk_size); - rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_MISC; scsi_req(rq)->cmd[13] = cmd; rq->rq_disk = tape->disk; diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c index 9ccc1d573393..247b9faccce1 100644 --- a/drivers/ide/ide-taskfile.c +++ b/drivers/ide/ide-taskfile.c @@ -428,11 +428,11 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf, { struct request *rq; int error; - int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE; - rq = blk_get_request(drive->queue, rw, __GFP_RECLAIM); + rq = blk_get_request(drive->queue, + (cmd->tf_flags & IDE_TFLAG_WRITE) ? + REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM); scsi_req_init(rq); - rq->cmd_type = REQ_TYPE_DRV_PRIV; ide_req(rq)->type = ATA_PRIV_TASKFILE; /* diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index df8a5ef334c0..6b8d5cd7dbf6 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -84,9 +84,6 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, nsect = blk_rq_cur_bytes(req) >> tr->blkshift; buf = bio_data(req->bio); - if (req->cmd_type != REQ_TYPE_FS) - return -EIO; - if (req_op(req) == REQ_OP_FLUSH) return tr->flush(dev); @@ -94,16 +91,16 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, get_capacity(req->rq_disk)) return -EIO; - if (req_op(req) == REQ_OP_DISCARD) + switch (req_op(req)) { + case REQ_OP_DISCARD: return tr->discard(dev, block, nsect); - - if (rq_data_dir(req) == READ) { + case REQ_OP_READ: for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->readsect(dev, block, buf)) return -EIO; rq_flush_dcache_pages(req); return 0; - } else { + case REQ_OP_WRITE: if (!tr->writesect) return -EIO; @@ -112,6 +109,8 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, if (tr->writesect(dev, block, buf)) return -EIO; return 0; + default: + return -EIO; } } diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index d1e6931c132f..c80869e60909 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -323,16 +323,15 @@ static int ubiblock_queue_rq(struct blk_mq_hw_ctx *hctx, struct ubiblock *dev = hctx->queue->queuedata; struct ubiblock_pdu *pdu = blk_mq_rq_to_pdu(req); - if (req->cmd_type != REQ_TYPE_FS) + switch (req_op(req)) { + case REQ_OP_READ: + ubi_sgl_init(&pdu->usgl); + queue_work(dev->wq, &pdu->work); + return BLK_MQ_RQ_QUEUE_OK; + default: return BLK_MQ_RQ_QUEUE_ERROR; + } - if (rq_data_dir(req) != READ) - return BLK_MQ_RQ_QUEUE_ERROR; /* Write not implemented */ - - ubi_sgl_init(&pdu->usgl); - queue_work(dev->wq, &pdu->work); - - return BLK_MQ_RQ_QUEUE_OK; } static int ubiblock_init_request(void *data, struct request *req, diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8a3c3e32a704..1640a5c8abbb 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -208,18 +208,18 @@ EXPORT_SYMBOL_GPL(nvme_requeue_req); struct request *nvme_alloc_request(struct request_queue *q, struct nvme_command *cmd, unsigned int flags, int qid) { + unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN; struct request *req; if (qid == NVME_QID_ANY) { - req = blk_mq_alloc_request(q, nvme_is_write(cmd), flags); + req = blk_mq_alloc_request(q, op, flags); } else { - req = blk_mq_alloc_request_hctx(q, nvme_is_write(cmd), flags, + req = blk_mq_alloc_request_hctx(q, op, flags, qid ? qid - 1 : 0); } if (IS_ERR(req)) return req; - req->cmd_type = REQ_TYPE_DRV_PRIV; req->cmd_flags |= REQ_FAILFAST_DRIVER; nvme_req(req)->cmd = cmd; @@ -309,17 +309,27 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req, { int ret = BLK_MQ_RQ_QUEUE_OK; - if (req->cmd_type == REQ_TYPE_DRV_PRIV) + switch (req_op(req)) { + case REQ_OP_DRV_IN: + case REQ_OP_DRV_OUT: memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd)); - else if (req_op(req) == REQ_OP_FLUSH) + break; + case REQ_OP_FLUSH: nvme_setup_flush(ns, cmd); - else if (req_op(req) == REQ_OP_DISCARD) + break; + case REQ_OP_DISCARD: ret = nvme_setup_discard(ns, req, cmd); - else + break; + case REQ_OP_READ: + case REQ_OP_WRITE: nvme_setup_rw(ns, req, cmd); + break; + default: + WARN_ON_ONCE(1); + return BLK_MQ_RQ_QUEUE_ERROR; + } cmd->common.command_id = req->tag; - return ret; } EXPORT_SYMBOL_GPL(nvme_setup_cmd); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index ecc79b2fcfaf..a75e95d42b3f 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1471,7 +1471,7 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(struct nvme_command), DMA_TO_DEVICE); - if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH) + if (req_op(rq) == REQ_OP_FLUSH) flush = true; ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, req->mr->need_inval ? &req->reg_wr.wr : NULL, flush); diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index fcb040eebf47..30b905080c61 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -1565,7 +1565,8 @@ static struct request *_make_request(struct request_queue *q, bool has_write, struct bio *bio = oii->bio; int ret; - req = blk_get_request(q, has_write ? WRITE : READ, flags); + req = blk_get_request(q, has_write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, + flags); if (IS_ERR(req)) return req; scsi_req_init(req); diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c index d314aa5c71cf..451de6c5e3c9 100644 --- a/drivers/scsi/osst.c +++ b/drivers/scsi/osst.c @@ -367,7 +367,8 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd, int err = 0; int write = (data_direction == DMA_TO_DEVICE); - req = blk_get_request(SRpnt->stp->device->request_queue, write, GFP_KERNEL); + req = blk_get_request(SRpnt->stp->device->request_queue, + write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(req)) return DRIVER_ERROR << 24; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index b4ce7bb5d2a9..9e82fa5715bc 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1974,7 +1974,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev) * blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a * request becomes available */ - req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL); + req = blk_get_request(sdev->request_queue, REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(req)) return; rq = scsi_req(req); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 31629a7b728d..90f65c8f487a 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -219,11 +219,12 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, req_flags_t rq_flags, int *resid) { struct request *req; - int write = (data_direction == DMA_TO_DEVICE); struct scsi_request *rq; int ret = DRIVER_ERROR << 24; - req = blk_get_request(sdev->request_queue, write, __GFP_RECLAIM); + req = blk_get_request(sdev->request_queue, + data_direction == DMA_TO_DEVICE ? + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM); if (IS_ERR(req)) return ret; rq = scsi_req(req); @@ -839,8 +840,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) } } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) { /* - * Certain non BLOCK_PC requests are commands that don't - * actually transfer anything (FLUSH), so cannot use + * Flush commands do not transfers any data, and thus cannot use * good_bytes != blk_rq_bytes(req) as the signal for an error. * This sets the error explicitly for the problem case. */ @@ -859,8 +859,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) blk_rq_sectors(req), good_bytes)); /* - * Recovered errors need reporting, but they're always treated - * as success, so fiddle the result code here. For BLOCK_PC + * Recovered errors need reporting, but they're always treated as + * success, so fiddle the result code here. For passthrough requests * we already took a copy of the original into rq->errors which * is what gets returned to the user */ @@ -874,7 +874,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) else if (!(req->rq_flags & RQF_QUIET)) scsi_print_sense(cmd); result = 0; - /* BLOCK_PC may have set error */ + /* for passthrough error may be set */ error = 0; } @@ -1179,12 +1179,12 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) spin_unlock_irqrestore(&dev->list_lock, flags); } -static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) +static int scsi_setup_scsi_cmnd(struct scsi_device *sdev, struct request *req) { struct scsi_cmnd *cmd = req->special; /* - * BLOCK_PC requests may transfer data, in which case they must + * Passthrough requests may transfer data, in which case they must * a bio attached to them. Or they might contain a SCSI command * that does not transfer data, in which case they may optionally * submit a request without an attached bio. @@ -1207,7 +1207,7 @@ static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) } /* - * Setup a REQ_TYPE_FS command. These are simple request from filesystems + * Setup a normal block command. These are simple request from filesystems * that still need to be translated to SCSI CDBs from the ULD. */ static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req) @@ -1236,14 +1236,10 @@ static int scsi_setup_cmnd(struct scsi_device *sdev, struct request *req) else cmd->sc_data_direction = DMA_FROM_DEVICE; - switch (req->cmd_type) { - case REQ_TYPE_FS: + if (blk_rq_is_scsi(req)) + return scsi_setup_scsi_cmnd(sdev, req); + else return scsi_setup_fs_cmnd(sdev, req); - case REQ_TYPE_BLOCK_PC: - return scsi_setup_blk_pc_cmnd(sdev, req); - default: - return BLKPREP_KILL; - } } static int diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 226a8def7a8b..e0e308b7e01a 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1698,7 +1698,8 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually * does not sleep except under memory pressure. */ - rq = blk_get_request(q, rw, GFP_KERNEL); + rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ? + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(rq)) { kfree(long_cmdp); return PTR_ERR(rq); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 94352e4df831..2e1d910092d8 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -437,14 +437,17 @@ static int sr_init_command(struct scsi_cmnd *SCpnt) goto out; } - if (rq_data_dir(rq) == WRITE) { + switch (req_op(rq)) { + case REQ_OP_WRITE: if (!cd->writeable) goto out; SCpnt->cmnd[0] = WRITE_10; cd->cdi.media_written = 1; - } else if (rq_data_dir(rq) == READ) { + break; + case REQ_OP_READ: SCpnt->cmnd[0] = READ_10; - } else { + break; + default: blk_dump_rq_flags(rq, "Unknown sr command"); goto out; } diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 4af900100a24..81212d4bd9bf 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -541,11 +541,11 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, struct scsi_request *rq; struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data; int err = 0; - int write = (data_direction == DMA_TO_DEVICE); struct scsi_tape *STp = SRpnt->stp; - req = blk_get_request(SRpnt->stp->device->request_queue, write, - GFP_KERNEL); + req = blk_get_request(SRpnt->stp->device->request_queue, + data_direction == DMA_TO_DEVICE ? + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(req)) return DRIVER_ERROR << 24; rq = scsi_req(req); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index e52f4e1a4675..a8f8e53f2f57 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1005,7 +1005,8 @@ pscsi_execute_cmd(struct se_cmd *cmd) scsi_command_size(cmd->t_task_cdb)); req = blk_get_request(pdv->pdv_sd->request_queue, - (cmd->data_direction == DMA_TO_DEVICE), + cmd->data_direction == DMA_TO_DEVICE ? + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(req)) { pr_err("PSCSI: blk_get_request() failed\n"); diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 930d98caab5b..a06115e31612 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -223,7 +223,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, if (!buf) return -ENOMEM; - rq = blk_get_request(q, READ, GFP_KERNEL); + rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(rq)) { error = -ENOMEM; goto out_free_buf; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 37c9a43c5e78..d703acb55d0f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -162,6 +162,13 @@ enum req_opf { /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 8, + /* SCSI passthrough using struct scsi_request */ + REQ_OP_SCSI_IN = 32, + REQ_OP_SCSI_OUT = 33, + /* Driver private requests */ + REQ_OP_DRV_IN = 34, + REQ_OP_DRV_OUT = 35, + REQ_OP_LAST, }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7121be081517..1e947e725528 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -70,15 +70,6 @@ struct request_list { unsigned int flags; }; -/* - * request command types - */ -enum rq_cmd_type_bits { - REQ_TYPE_FS = 1, /* fs request */ - REQ_TYPE_BLOCK_PC, /* scsi command */ - REQ_TYPE_DRV_PRIV, /* driver defined types from here */ -}; - /* * request flags */ typedef __u32 __bitwise req_flags_t; @@ -145,7 +136,6 @@ struct request { struct blk_mq_ctx *mq_ctx; int cpu; - unsigned cmd_type; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; unsigned long atomic_flags; @@ -242,9 +232,19 @@ struct request { struct request *next_rq; }; +static inline bool blk_rq_is_scsi(struct request *rq) +{ + return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT; +} + +static inline bool blk_rq_is_private(struct request *rq) +{ + return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT; +} + static inline bool blk_rq_is_passthrough(struct request *rq) { - return rq->cmd_type != REQ_TYPE_FS; + return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); } static inline unsigned short req_get_ioprio(struct request *req) diff --git a/include/linux/ide.h b/include/linux/ide.h index 5cc6caa94cac..2f51c1724b5a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -63,31 +63,27 @@ static inline struct ide_request *ide_req(struct request *rq) static inline bool ata_misc_request(struct request *rq) { - return rq->cmd_type == REQ_TYPE_DRV_PRIV && - ide_req(rq)->type == ATA_PRIV_MISC; + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_MISC; } static inline bool ata_taskfile_request(struct request *rq) { - return rq->cmd_type == REQ_TYPE_DRV_PRIV && - ide_req(rq)->type == ATA_PRIV_TASKFILE; + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_TASKFILE; } static inline bool ata_pc_request(struct request *rq) { - return rq->cmd_type == REQ_TYPE_DRV_PRIV && - ide_req(rq)->type == ATA_PRIV_PC; + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_PC; } static inline bool ata_sense_request(struct request *rq) { - return rq->cmd_type == REQ_TYPE_DRV_PRIV && - ide_req(rq)->type == ATA_PRIV_SENSE; + return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_SENSE; } static inline bool ata_pm_request(struct request *rq) { - return rq->cmd_type == REQ_TYPE_DRV_PRIV && + return blk_rq_is_private(rq) && (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND || ide_req(rq)->type == ATA_PRIV_PM_RESUME); } -- cgit v1.2.3-59-g8ed1b From f3bcb0e60685acfc258a20caa0607e084271c482 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 1 Feb 2017 10:20:56 -0800 Subject: blk-mq-debugfs: Add missing __acquires() / __releases() annotations This patch avoids that sparse complains about lock imbalances. Signed-off-by: Bart Van Assche Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'block') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 1e2a4a2ff623..3a914e78ac11 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -95,6 +95,7 @@ static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v) } static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos) + __acquires(&hctx->lock) { struct blk_mq_hw_ctx *hctx = m->private; @@ -110,6 +111,7 @@ static void *hctx_dispatch_next(struct seq_file *m, void *v, loff_t *pos) } static void hctx_dispatch_stop(struct seq_file *m, void *v) + __releases(&hctx->lock) { struct blk_mq_hw_ctx *hctx = m->private; @@ -482,6 +484,7 @@ static const struct file_operations hctx_active_fops = { }; static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos) + __acquires(&ctx->lock) { struct blk_mq_ctx *ctx = m->private; @@ -497,6 +500,7 @@ static void *ctx_rq_list_next(struct seq_file *m, void *v, loff_t *pos) } static void ctx_rq_list_stop(struct seq_file *m, void *v) + __releases(&ctx->lock) { struct blk_mq_ctx *ctx = m->private; -- cgit v1.2.3-59-g8ed1b From a1ae0f74a73fbd113647321c49032a561b3f3781 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 1 Feb 2017 12:22:23 -0700 Subject: blk-mq-debug: Avoid that sparse complains about req_flags_t usage Avoid that sparse reports the following complaints: block/elevator.c:541:29: warning: incorrect type in assignment (different base types) block/elevator.c:541:29: expected bool [unsigned] [usertype] next_sorted block/elevator.c:541:29: got restricted req_flags_t block/blk-mq-debugfs.c:92:54: warning: cast from restricted req_flags_t Signed-off-by: Bart Van Assche Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 2 +- block/elevator.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'block') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 3a914e78ac11..0119ec533824 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -89,7 +89,7 @@ static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v) struct request *rq = list_entry_rq(v); seq_printf(m, "%p {.cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n", - rq, rq->cmd_flags, (unsigned int)rq->rq_flags, + rq, rq->cmd_flags, (__force unsigned int)rq->rq_flags, rq->tag, rq->internal_tag); return 0; } diff --git a/block/elevator.c b/block/elevator.c index dba9be891a6b..7e4f5880dd64 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -538,7 +538,7 @@ void elv_merge_requests(struct request_queue *q, struct request *rq, if (e->uses_mq && e->type->ops.mq.requests_merged) e->type->ops.mq.requests_merged(q, rq, next); else if (e->type->ops.sq.elevator_merge_req_fn) { - next_sorted = next->rq_flags & RQF_SORTED; + next_sorted = (__force bool)(next->rq_flags & RQF_SORTED); if (next_sorted) e->type->ops.sq.elevator_merge_req_fn(q, rq, next); } -- cgit v1.2.3-59-g8ed1b From 8c0f14eab8f138689e68b3498c0c5fd6ff20a948 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 1 Feb 2017 10:20:58 -0800 Subject: blk-mq-debug: Make show() operations interruptible Allow users to interrupt show operations instead of making a user space process unkillable if ownership of q->sysfs_lock cannot be obtained. Signed-off-by: Bart Van Assche Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'block') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 0119ec533824..54b2f484eab4 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -178,13 +178,17 @@ static int hctx_tags_show(struct seq_file *m, void *v) { struct blk_mq_hw_ctx *hctx = m->private; struct request_queue *q = hctx->queue; + int res; - mutex_lock(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->sysfs_lock); + if (res) + goto out; if (hctx->tags) blk_mq_debugfs_tags_show(m, hctx->tags); mutex_unlock(&q->sysfs_lock); - return 0; +out: + return res; } static int hctx_tags_open(struct inode *inode, struct file *file) @@ -203,12 +207,17 @@ static int hctx_tags_bitmap_show(struct seq_file *m, void *v) { struct blk_mq_hw_ctx *hctx = m->private; struct request_queue *q = hctx->queue; + int res; - mutex_lock(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->sysfs_lock); + if (res) + goto out; if (hctx->tags) sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m); mutex_unlock(&q->sysfs_lock); - return 0; + +out: + return res; } static int hctx_tags_bitmap_open(struct inode *inode, struct file *file) @@ -227,13 +236,17 @@ static int hctx_sched_tags_show(struct seq_file *m, void *v) { struct blk_mq_hw_ctx *hctx = m->private; struct request_queue *q = hctx->queue; + int res; - mutex_lock(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->sysfs_lock); + if (res) + goto out; if (hctx->sched_tags) blk_mq_debugfs_tags_show(m, hctx->sched_tags); mutex_unlock(&q->sysfs_lock); - return 0; +out: + return res; } static int hctx_sched_tags_open(struct inode *inode, struct file *file) @@ -252,12 +265,17 @@ static int hctx_sched_tags_bitmap_show(struct seq_file *m, void *v) { struct blk_mq_hw_ctx *hctx = m->private; struct request_queue *q = hctx->queue; + int res; - mutex_lock(&q->sysfs_lock); + res = mutex_lock_interruptible(&q->sysfs_lock); + if (res) + goto out; if (hctx->sched_tags) sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m); mutex_unlock(&q->sysfs_lock); - return 0; + +out: + return res; } static int hctx_sched_tags_bitmap_open(struct inode *inode, struct file *file) -- cgit v1.2.3-59-g8ed1b From 72f2f8f6929cf680d42ca44f87b7d370aff94d85 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 1 Feb 2017 10:20:59 -0800 Subject: blk-mq-debug: Introduce debugfs_create_files() Replace the two debugfs_create_file() loops by a call to the new debugfs_create_files() function. Add an empty element at the end of the two attribute arrays such that the array size does not have to be passed to debugfs_create_files(). Signed-off-by: Bart Van Assche Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'block') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 54b2f484eab4..1077008690b2 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -652,6 +652,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = { {"queued", 0600, &hctx_queued_fops}, {"run", 0600, &hctx_run_fops}, {"active", 0400, &hctx_active_fops}, + {}, }; static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { @@ -659,6 +660,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { {"dispatched", 0600, &ctx_dispatched_fops}, {"merged", 0600, &ctx_merged_fops}, {"completed", 0600, &ctx_completed_fops}, + {}, }; int blk_mq_debugfs_register(struct request_queue *q, const char *name) @@ -687,27 +689,31 @@ void blk_mq_debugfs_unregister(struct request_queue *q) q->debugfs_dir = NULL; } +static bool debugfs_create_files(struct dentry *parent, void *data, + const struct blk_mq_debugfs_attr *attr) +{ + for (; attr->name; attr++) { + if (!debugfs_create_file(attr->name, attr->mode, parent, + data, attr->fops)) + return false; + } + return true; +} + static int blk_mq_debugfs_register_ctx(struct request_queue *q, struct blk_mq_ctx *ctx, struct dentry *hctx_dir) { struct dentry *ctx_dir; char name[20]; - int i; snprintf(name, sizeof(name), "cpu%u", ctx->cpu); ctx_dir = debugfs_create_dir(name, hctx_dir); if (!ctx_dir) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_ctx_attrs); i++) { - const struct blk_mq_debugfs_attr *attr; - - attr = &blk_mq_debugfs_ctx_attrs[i]; - if (!debugfs_create_file(attr->name, attr->mode, ctx_dir, ctx, - attr->fops)) - return -ENOMEM; - } + if (!debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs)) + return -ENOMEM; return 0; } @@ -725,14 +731,8 @@ static int blk_mq_debugfs_register_hctx(struct request_queue *q, if (!hctx_dir) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_hctx_attrs); i++) { - const struct blk_mq_debugfs_attr *attr; - - attr = &blk_mq_debugfs_hctx_attrs[i]; - if (!debugfs_create_file(attr->name, attr->mode, hctx_dir, hctx, - attr->fops)) - return -ENOMEM; - } + if (!debugfs_create_files(hctx_dir, hctx, blk_mq_debugfs_hctx_attrs)) + return -ENOMEM; hctx_for_each_ctx(hctx, ctx, i) { if (blk_mq_debugfs_register_ctx(q, ctx, hctx_dir)) -- cgit v1.2.3-59-g8ed1b From f44f1ab5a2dcd4e16eab850fd08e40ff2d0c28d4 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:49 +0100 Subject: block: Unhash block device inodes on gendisk destruction Currently, block device inodes stay around after corresponding gendisk hash died until memory reclaim finds them and frees them. Since we will make block device inode pin the bdi, we want to free the block device inode as soon as the device goes away so that bdi does not stay around unnecessarily. Furthermore we need to avoid issues when new device with the same major,minor pair gets created since reusing the bdi structure would be rather difficult in this case. Unhashing block device inode on gendisk destruction nicely deals with these problems. Once last block device inode reference is dropped (which may be directly in del_gendisk()), the inode gets evicted. Furthermore if the major,minor pair gets reallocated, we are guaranteed to get new block device inode even if old block device inode is not yet evicted and thus we avoid issues with possible reuse of bdi. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- block/genhd.c | 2 ++ fs/block_dev.c | 15 +++++++++++++++ include/linux/fs.h | 1 + 3 files changed, 18 insertions(+) (limited to 'block') diff --git a/block/genhd.c b/block/genhd.c index fcd6d4fae657..f2f22d0e8e14 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -648,6 +648,8 @@ void del_gendisk(struct gendisk *disk) disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE); while ((part = disk_part_iter_next(&piter))) { + bdev_unhash_inode(MKDEV(disk->major, + disk->first_minor + part->partno)); invalidate_partition(disk, part->partno); delete_partition(disk, part->partno); } diff --git a/fs/block_dev.c b/fs/block_dev.c index 5db5d1340d69..ed6a34be7a1e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -954,6 +954,21 @@ static int bdev_set(struct inode *inode, void *data) static LIST_HEAD(all_bdevs); +/* + * If there is a bdev inode for this device, unhash it so that it gets evicted + * as soon as last inode reference is dropped. + */ +void bdev_unhash_inode(dev_t dev) +{ + struct inode *inode; + + inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev); + if (inode) { + remove_inode_hash(inode); + iput(inode); + } +} + struct block_device *bdget(dev_t dev) { struct block_device *bdev; diff --git a/include/linux/fs.h b/include/linux/fs.h index 2ba074328894..702cb6c50194 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2342,6 +2342,7 @@ extern struct kmem_cache *names_cachep; #ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); extern void unregister_blkdev(unsigned int, const char *); +extern void bdev_unhash_inode(dev_t dev); extern struct block_device *bdget(dev_t); extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); -- cgit v1.2.3-59-g8ed1b From dc3b17cc8bf21307c7e076e7c778d5db756f7871 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:50 +0100 Subject: block: Use pointer to backing_dev_info from request_queue We will want to have struct backing_dev_info allocated separately from struct request_queue. As the first step add pointer to backing_dev_info to request_queue and convert all users touching it. No functional changes in this patch. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 6 +++--- block/blk-core.c | 27 ++++++++++++++------------- block/blk-integrity.c | 4 ++-- block/blk-settings.c | 2 +- block/blk-sysfs.c | 8 ++++---- block/blk-wbt.c | 8 ++++---- block/genhd.c | 2 +- drivers/block/aoe/aoeblk.c | 4 ++-- drivers/block/drbd/drbd_main.c | 6 +++--- drivers/block/drbd/drbd_nl.c | 12 +++++++----- drivers/block/drbd/drbd_proc.c | 2 +- drivers/block/drbd/drbd_req.c | 2 +- drivers/block/pktcdvd.c | 4 ++-- drivers/block/rbd.c | 2 +- drivers/md/bcache/request.c | 10 +++++----- drivers/md/bcache/super.c | 8 ++++---- drivers/md/dm-cache-target.c | 2 +- drivers/md/dm-era-target.c | 2 +- drivers/md/dm-table.c | 2 +- drivers/md/dm-thin.c | 2 +- drivers/md/dm.c | 6 +++--- drivers/md/linear.c | 2 +- drivers/md/md.c | 6 +++--- drivers/md/multipath.c | 2 +- drivers/md/raid0.c | 6 +++--- drivers/md/raid1.c | 4 ++-- drivers/md/raid10.c | 10 +++++----- drivers/md/raid5.c | 12 ++++++------ fs/gfs2/ops_fstype.c | 2 +- fs/nilfs2/super.c | 2 +- fs/super.c | 2 +- include/linux/blkdev.h | 3 ++- mm/page-writeback.c | 4 ++-- 33 files changed, 90 insertions(+), 86 deletions(-) (limited to 'block') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index fb59a3edc778..37fe595cfd70 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -184,7 +184,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, goto err_free_blkg; } - wb_congested = wb_congested_get_create(&q->backing_dev_info, + wb_congested = wb_congested_get_create(q->backing_dev_info, blkcg->css.id, GFP_NOWAIT | __GFP_NOWARN); if (!wb_congested) { @@ -469,8 +469,8 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, const char *blkg_dev_name(struct blkcg_gq *blkg) { /* some drivers (floppy) instantiate a queue w/o disk registered */ - if (blkg->q->backing_dev_info.dev) - return dev_name(blkg->q->backing_dev_info.dev); + if (blkg->q->backing_dev_info->dev) + return dev_name(blkg->q->backing_dev_info->dev); return NULL; } EXPORT_SYMBOL_GPL(blkg_dev_name); diff --git a/block/blk-core.c b/block/blk-core.c index 3266daaa343f..dcac0352c14c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -75,7 +75,7 @@ static void blk_clear_congested(struct request_list *rl, int sync) * flip its congestion state for events on other blkcgs. */ if (rl == &rl->q->root_rl) - clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync); + clear_wb_congested(rl->q->backing_dev_info->wb.congested, sync); #endif } @@ -86,7 +86,7 @@ static void blk_set_congested(struct request_list *rl, int sync) #else /* see blk_clear_congested() */ if (rl == &rl->q->root_rl) - set_wb_congested(rl->q->backing_dev_info.wb.congested, sync); + set_wb_congested(rl->q->backing_dev_info->wb.congested, sync); #endif } @@ -117,7 +117,7 @@ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - return &q->backing_dev_info; + return q->backing_dev_info; } EXPORT_SYMBOL(blk_get_backing_dev_info); @@ -575,7 +575,7 @@ void blk_cleanup_queue(struct request_queue *q) blk_flush_integrity(); /* @q won't process any more request, flush async actions */ - del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer); + del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer); blk_sync_queue(q); if (q->mq_ops) @@ -587,7 +587,7 @@ void blk_cleanup_queue(struct request_queue *q) q->queue_lock = &q->__queue_lock; spin_unlock_irq(lock); - bdi_unregister(&q->backing_dev_info); + bdi_unregister(q->backing_dev_info); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); @@ -728,17 +728,18 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) if (!q->bio_split) goto fail_id; - q->backing_dev_info.ra_pages = + q->backing_dev_info = &q->_backing_dev_info; + q->backing_dev_info->ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE; - q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK; - q->backing_dev_info.name = "block"; + q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; + q->backing_dev_info->name = "block"; q->node = node_id; - err = bdi_init(&q->backing_dev_info); + err = bdi_init(q->backing_dev_info); if (err) goto fail_split; - setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, + setup_timer(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, (unsigned long) q); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->queue_head); @@ -788,7 +789,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) fail_ref: percpu_ref_exit(&q->q_usage_counter); fail_bdi: - bdi_destroy(&q->backing_dev_info); + bdi_destroy(q->backing_dev_info); fail_split: bioset_free(q->bio_split); fail_id: @@ -1182,7 +1183,7 @@ fail_elvpriv: * disturb iosched and blkcg but weird is bettern than dead. */ 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)); + __func__, dev_name(q->backing_dev_info->dev)); rq->rq_flags &= ~RQF_ELVPRIV; rq->elv.icq = NULL; @@ -2659,7 +2660,7 @@ void blk_finish_request(struct request *req, int error) BUG_ON(blk_queued_rq(req)); if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req)) - laptop_io_completion(&req->q->backing_dev_info); + laptop_io_completion(req->q->backing_dev_info); blk_delete_timer(req); diff --git a/block/blk-integrity.c b/block/blk-integrity.c index d69c5c79f98e..9f0ff5ba4f84 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -443,10 +443,10 @@ void blk_integrity_revalidate(struct gendisk *disk) return; if (bi->profile) - disk->queue->backing_dev_info.capabilities |= + disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; else - disk->queue->backing_dev_info.capabilities &= + disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; } diff --git a/block/blk-settings.c b/block/blk-settings.c index 529e55f52a03..6eb19bcbf3cb 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -253,7 +253,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors); max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS); limits->max_sectors = max_sectors; - q->backing_dev_info.io_pages = max_sectors >> (PAGE_SHIFT - 9); + q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 894f77342fd4..05841be1f30f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -89,7 +89,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) static ssize_t queue_ra_show(struct request_queue *q, char *page) { - unsigned long ra_kb = q->backing_dev_info.ra_pages << + unsigned long ra_kb = q->backing_dev_info->ra_pages << (PAGE_SHIFT - 10); return queue_var_show(ra_kb, (page)); @@ -104,7 +104,7 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count) if (ret < 0) return ret; - q->backing_dev_info.ra_pages = ra_kb >> (PAGE_SHIFT - 10); + q->backing_dev_info->ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } @@ -236,7 +236,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) spin_lock_irq(q->queue_lock); q->limits.max_sectors = max_sectors_kb << 1; - q->backing_dev_info.io_pages = max_sectors_kb >> (PAGE_SHIFT - 10); + q->backing_dev_info->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10); spin_unlock_irq(q->queue_lock); return ret; @@ -799,7 +799,7 @@ static void blk_release_queue(struct kobject *kobj) container_of(kobj, struct request_queue, kobj); wbt_exit(q); - bdi_exit(&q->backing_dev_info); + bdi_exit(q->backing_dev_info); blkcg_exit_queue(q); if (q->elevator) { diff --git a/block/blk-wbt.c b/block/blk-wbt.c index f0a9c07b4c7a..1aedb1f7ee0c 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -96,7 +96,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) */ static bool wb_recent_wait(struct rq_wb *rwb) { - struct bdi_writeback *wb = &rwb->queue->backing_dev_info.wb; + struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb; return time_before(jiffies, wb->dirty_sleep + HZ); } @@ -279,7 +279,7 @@ enum { static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat) { - struct backing_dev_info *bdi = &rwb->queue->backing_dev_info; + struct backing_dev_info *bdi = rwb->queue->backing_dev_info; u64 thislat; /* @@ -339,7 +339,7 @@ static int latency_exceeded(struct rq_wb *rwb) static void rwb_trace_step(struct rq_wb *rwb, const char *msg) { - struct backing_dev_info *bdi = &rwb->queue->backing_dev_info; + struct backing_dev_info *bdi = rwb->queue->backing_dev_info; trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec, rwb->wb_background, rwb->wb_normal, rwb->wb_max); @@ -423,7 +423,7 @@ static void wb_timer_fn(unsigned long data) status = latency_exceeded(rwb); - trace_wbt_timer(&rwb->queue->backing_dev_info, status, rwb->scale_step, + trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step, inflight); /* diff --git a/block/genhd.c b/block/genhd.c index f2f22d0e8e14..d9ccd42f3675 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -613,7 +613,7 @@ void device_add_disk(struct device *parent, struct gendisk *disk) disk_alloc_events(disk); /* Register BDI before referencing it from bdev */ - bdi = &disk->queue->backing_dev_info; + bdi = disk->queue->backing_dev_info; bdi_register_owner(bdi, disk_to_dev(disk)); blk_register_region(disk_devt(disk), disk->minors, NULL, diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index ec9d8610b25f..027b876370bc 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -396,8 +396,8 @@ aoeblk_gdalloc(void *vp) WARN_ON(d->gd); WARN_ON(d->flags & DEVFL_UP); blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS); - q->backing_dev_info.name = "aoe"; - q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_SIZE; + q->backing_dev_info->name = "aoe"; + q->backing_dev_info->ra_pages = READ_AHEAD / PAGE_SIZE; d->bufpool = mp; d->blkq = gd->queue = q; q->queuedata = d; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 83482721bc01..d305f05be648 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2462,7 +2462,7 @@ static int drbd_congested(void *congested_data, int bdi_bits) if (get_ldev(device)) { q = bdev_get_queue(device->ldev->backing_bdev); - r = bdi_congested(&q->backing_dev_info, bdi_bits); + r = bdi_congested(q->backing_dev_info, bdi_bits); put_ldev(device); if (r) reason = 'b'; @@ -2834,8 +2834,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig /* we have no partitions. we contain only ourselves. */ device->this_bdev->bd_contains = device->this_bdev; - q->backing_dev_info.congested_fn = drbd_congested; - q->backing_dev_info.congested_data = device; + q->backing_dev_info->congested_fn = drbd_congested; + q->backing_dev_info->congested_data = device; blk_queue_make_request(q, drbd_make_request); blk_queue_write_cache(q, true, true); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index f35db29cac76..908c704e20aa 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1328,11 +1328,13 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi if (b) { blk_queue_stack_limits(q, b); - if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) { + if (q->backing_dev_info->ra_pages != + b->backing_dev_info->ra_pages) { drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n", - q->backing_dev_info.ra_pages, - b->backing_dev_info.ra_pages); - q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages; + q->backing_dev_info->ra_pages, + b->backing_dev_info->ra_pages); + q->backing_dev_info->ra_pages = + b->backing_dev_info->ra_pages; } } fixup_discard_if_not_supported(q); @@ -3345,7 +3347,7 @@ static void device_to_statistics(struct device_statistics *s, s->dev_disk_flags = md->flags; q = bdev_get_queue(device->ldev->backing_bdev); s->dev_lower_blocked = - bdi_congested(&q->backing_dev_info, + bdi_congested(q->backing_dev_info, (1 << WB_async_congested) | (1 << WB_sync_congested)); put_ldev(device); diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index be2b93fd2c11..8378142f7a55 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -288,7 +288,7 @@ static int drbd_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2d: cs:Unconfigured\n", i); } else { /* reset device->congestion_reason */ - bdi_rw_congested(&device->rq_queue->backing_dev_info); + bdi_rw_congested(device->rq_queue->backing_dev_info); nc = rcu_dereference(first_peer_device(device)->connection->net_conf); wp = nc ? nc->wire_protocol - DRBD_PROT_A + 'A' : ' '; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index de279fe4e4fd..cb6bdb75d52d 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -938,7 +938,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se switch (rbm) { case RB_CONGESTED_REMOTE: - bdi = &device->ldev->backing_bdev->bd_disk->queue->backing_dev_info; + bdi = device->ldev->backing_bdev->bd_disk->queue->backing_dev_info; return bdi_read_congested(bdi); case RB_LEAST_PENDING: return atomic_read(&device->local_cnt) > diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index f4bd95943dc2..66d846ba85a9 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1243,7 +1243,7 @@ try_next_bio: && pd->bio_queue_size <= pd->write_congestion_off); spin_unlock(&pd->lock); if (wakeup) { - clear_bdi_congested(&pd->disk->queue->backing_dev_info, + clear_bdi_congested(pd->disk->queue->backing_dev_info, BLK_RW_ASYNC); } @@ -2370,7 +2370,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) spin_lock(&pd->lock); if (pd->write_congestion_on > 0 && pd->bio_queue_size >= pd->write_congestion_on) { - set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC); + set_bdi_congested(q->backing_dev_info, BLK_RW_ASYNC); do { spin_unlock(&pd->lock); congestion_wait(BLK_RW_ASYNC, HZ); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 4d78cf605b21..588721f30a22 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4526,7 +4526,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) q->limits.discard_zeroes_data = 1; if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) - q->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES; + q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; disk->queue = q; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 01035e718c1c..709c9cc34369 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1009,7 +1009,7 @@ static int cached_dev_congested(void *data, int bits) struct request_queue *q = bdev_get_queue(dc->bdev); int ret = 0; - if (bdi_congested(&q->backing_dev_info, bits)) + if (bdi_congested(q->backing_dev_info, bits)) return 1; if (cached_dev_get(dc)) { @@ -1018,7 +1018,7 @@ static int cached_dev_congested(void *data, int bits) for_each_cache(ca, d->c, i) { q = bdev_get_queue(ca->bdev); - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); } cached_dev_put(dc); @@ -1032,7 +1032,7 @@ void bch_cached_dev_request_init(struct cached_dev *dc) struct gendisk *g = dc->disk.disk; g->queue->make_request_fn = cached_dev_make_request; - g->queue->backing_dev_info.congested_fn = cached_dev_congested; + g->queue->backing_dev_info->congested_fn = cached_dev_congested; dc->disk.cache_miss = cached_dev_cache_miss; dc->disk.ioctl = cached_dev_ioctl; } @@ -1125,7 +1125,7 @@ static int flash_dev_congested(void *data, int bits) for_each_cache(ca, d->c, i) { q = bdev_get_queue(ca->bdev); - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); } return ret; @@ -1136,7 +1136,7 @@ void bch_flash_dev_request_init(struct bcache_device *d) struct gendisk *g = d->disk; g->queue->make_request_fn = flash_dev_make_request; - g->queue->backing_dev_info.congested_fn = flash_dev_congested; + g->queue->backing_dev_info->congested_fn = flash_dev_congested; d->cache_miss = flash_dev_cache_miss; d->ioctl = flash_dev_ioctl; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 3a19cbc8b230..85e3f21c2514 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -807,7 +807,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, blk_queue_make_request(q, NULL); d->disk->queue = q; q->queuedata = d; - q->backing_dev_info.congested_data = d; + q->backing_dev_info->congested_data = d; q->limits.max_hw_sectors = UINT_MAX; q->limits.max_sectors = UINT_MAX; q->limits.max_segment_size = UINT_MAX; @@ -1132,9 +1132,9 @@ static int cached_dev_init(struct cached_dev *dc, unsigned block_size) set_capacity(dc->disk.disk, dc->bdev->bd_part->nr_sects - dc->sb.data_offset); - dc->disk.disk->queue->backing_dev_info.ra_pages = - max(dc->disk.disk->queue->backing_dev_info.ra_pages, - q->backing_dev_info.ra_pages); + dc->disk.disk->queue->backing_dev_info->ra_pages = + max(dc->disk.disk->queue->backing_dev_info->ra_pages, + q->backing_dev_info->ra_pages); bch_cached_dev_request_init(dc); bch_cached_dev_writeback_init(dc); diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 5b9cf56de8ef..894bc14469c8 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2284,7 +2284,7 @@ static void do_waker(struct work_struct *ws) static int is_congested(struct dm_dev *dev, int bdi_bits) { struct request_queue *q = bdev_get_queue(dev->bdev); - return bdi_congested(&q->backing_dev_info, bdi_bits); + return bdi_congested(q->backing_dev_info, bdi_bits); } static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits) diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index bf2b2676cb8a..9fab33b113c4 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1379,7 +1379,7 @@ static void stop_worker(struct era *era) static int dev_is_congested(struct dm_dev *dev, int bdi_bits) { struct request_queue *q = bdev_get_queue(dev->bdev); - return bdi_congested(&q->backing_dev_info, bdi_bits); + return bdi_congested(q->backing_dev_info, bdi_bits); } static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 0a427de23ed2..3ad16d9c9d5a 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1750,7 +1750,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits) char b[BDEVNAME_SIZE]; if (likely(q)) - r |= bdi_congested(&q->backing_dev_info, bdi_bits); + r |= bdi_congested(q->backing_dev_info, bdi_bits); else DMWARN_LIMIT("%s: any_congested: nonexistent device %s", dm_device_name(t->md), diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 110982db4b48..2b266a2b5035 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2711,7 +2711,7 @@ static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits) return 1; q = bdev_get_queue(pt->data_dev->bdev); - return bdi_congested(&q->backing_dev_info, bdi_bits); + return bdi_congested(q->backing_dev_info, bdi_bits); } static void requeue_bios(struct pool *pool) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ff4a29a97ad3..9e958bc94fed 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1313,7 +1313,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits) * With request-based DM we only need to check the * top-level queue for congestion. */ - r = md->queue->backing_dev_info.wb.state & bdi_bits; + r = md->queue->backing_dev_info->wb.state & bdi_bits; } else { map = dm_get_live_table_fast(md); if (map) @@ -1396,7 +1396,7 @@ void dm_init_md_queue(struct mapped_device *md) * - must do so here (in alloc_dev callchain) before queue is used */ md->queue->queuedata = md; - md->queue->backing_dev_info.congested_data = md; + md->queue->backing_dev_info->congested_data = md; } void dm_init_normal_md_queue(struct mapped_device *md) @@ -1407,7 +1407,7 @@ void dm_init_normal_md_queue(struct mapped_device *md) /* * Initialize aspects of queue that aren't relevant for blk-mq */ - md->queue->backing_dev_info.congested_fn = dm_any_congested; + md->queue->backing_dev_info->congested_fn = dm_any_congested; blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); } diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 5975c9915684..f1c7bbac31a5 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -62,7 +62,7 @@ static int linear_congested(struct mddev *mddev, int bits) for (i = 0; i < mddev->raid_disks && !ret ; i++) { struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev); - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); } return ret; diff --git a/drivers/md/md.c b/drivers/md/md.c index 82821ee0d57f..ede3b2ad45db 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5341,8 +5341,8 @@ int md_run(struct mddev *mddev) queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mddev->queue); else queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, mddev->queue); - mddev->queue->backing_dev_info.congested_data = mddev; - mddev->queue->backing_dev_info.congested_fn = md_congested; + mddev->queue->backing_dev_info->congested_data = mddev; + mddev->queue->backing_dev_info->congested_fn = md_congested; } if (pers->sync_request) { if (mddev->kobj.sd && @@ -5699,7 +5699,7 @@ static int do_md_stop(struct mddev *mddev, int mode, __md_stop_writes(mddev); __md_stop(mddev); - mddev->queue->backing_dev_info.congested_fn = NULL; + mddev->queue->backing_dev_info->congested_fn = NULL; /* tell userspace to handle 'inactive' */ sysfs_notify_dirent_safe(mddev->sysfs_state); diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index aa8c4e5c1ee2..d457afa672d5 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -169,7 +169,7 @@ static int multipath_congested(struct mddev *mddev, int bits) if (rdev && !test_bit(Faulty, &rdev->flags)) { struct request_queue *q = bdev_get_queue(rdev->bdev); - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); /* Just like multipath_map, we just check the * first available device */ diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 848365d474f3..d6585239bff2 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -41,7 +41,7 @@ static int raid0_congested(struct mddev *mddev, int bits) for (i = 0; i < raid_disks && !ret ; i++) { struct request_queue *q = bdev_get_queue(devlist[i]->bdev); - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); } return ret; } @@ -420,8 +420,8 @@ static int raid0_run(struct mddev *mddev) */ int stripe = mddev->raid_disks * (mddev->chunk_sectors << 9) / PAGE_SIZE; - if (mddev->queue->backing_dev_info.ra_pages < 2* stripe) - mddev->queue->backing_dev_info.ra_pages = 2* stripe; + if (mddev->queue->backing_dev_info->ra_pages < 2* stripe) + mddev->queue->backing_dev_info->ra_pages = 2* stripe; } dump_zones(mddev); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 67b0365d49b5..830ff2b20346 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -744,9 +744,9 @@ static int raid1_congested(struct mddev *mddev, int bits) * non-congested targets, it can be removed */ if ((bits & (1 << WB_async_congested)) || 1) - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); else - ret &= bdi_congested(&q->backing_dev_info, bits); + ret &= bdi_congested(q->backing_dev_info, bits); } } rcu_read_unlock(); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 1920756828df..6bc5c2a85160 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -860,7 +860,7 @@ static int raid10_congested(struct mddev *mddev, int bits) if (rdev && !test_bit(Faulty, &rdev->flags)) { struct request_queue *q = bdev_get_queue(rdev->bdev); - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); } } rcu_read_unlock(); @@ -3841,8 +3841,8 @@ static int raid10_run(struct mddev *mddev) * maybe... */ stripe /= conf->geo.near_copies; - if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe) - mddev->queue->backing_dev_info.ra_pages = 2 * stripe; + if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe) + mddev->queue->backing_dev_info->ra_pages = 2 * stripe; } if (md_integrity_register(mddev)) @@ -4643,8 +4643,8 @@ static void end_reshape(struct r10conf *conf) int stripe = conf->geo.raid_disks * ((conf->mddev->chunk_sectors << 9) / PAGE_SIZE); stripe /= conf->geo.near_copies; - if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe) - conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe; + if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe) + conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe; } conf->fullsync = 0; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 36c13e4be9c9..c0312d3f516a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6264,10 +6264,10 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len) mddev_suspend(mddev); conf->skip_copy = new; if (new) - mddev->queue->backing_dev_info.capabilities |= + mddev->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; else - mddev->queue->backing_dev_info.capabilities &= + mddev->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; mddev_resume(mddev); } @@ -7086,8 +7086,8 @@ static int raid5_run(struct mddev *mddev) int data_disks = conf->previous_raid_disks - conf->max_degraded; int stripe = data_disks * ((mddev->chunk_sectors << 9) / PAGE_SIZE); - if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe) - mddev->queue->backing_dev_info.ra_pages = 2 * stripe; + if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe) + mddev->queue->backing_dev_info->ra_pages = 2 * stripe; chunk_size = mddev->chunk_sectors << 9; blk_queue_io_min(mddev->queue, chunk_size); @@ -7696,8 +7696,8 @@ static void end_reshape(struct r5conf *conf) int data_disks = conf->raid_disks - conf->max_degraded; int stripe = data_disks * ((conf->chunk_sectors << 9) / PAGE_SIZE); - if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe) - conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe; + if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe) + conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe; } } } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index a34308df927f..c0e5b9a8bf5f 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1226,7 +1226,7 @@ static int set_gfs2_super(struct super_block *s, void *data) * We set the bdi here to the queue backing, file systems can * overwrite this in ->fill_super() */ - s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info; + s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info; return 0; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 12eeae62a2b1..e1872f36147f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1068,7 +1068,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; sb->s_max_links = NILFS_LINK_MAX; - sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info; + sb->s_bdi = bdev_get_queue(sb->s_bdev)->backing_dev_info; err = load_nilfs(nilfs, sb); if (err) diff --git a/fs/super.c b/fs/super.c index 1709ed029a2c..ea662b0e5e78 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1047,7 +1047,7 @@ static int set_bdev_super(struct super_block *s, void *data) * We set the bdi here to the queue backing, file systems can * overwrite this in ->fill_super() */ - s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info; + s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info; return 0; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 11f7a8e86a89..a75e42de34ab 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -432,7 +432,8 @@ struct request_queue { */ struct delayed_work delay_work; - struct backing_dev_info backing_dev_info; + struct backing_dev_info *backing_dev_info; + struct backing_dev_info _backing_dev_info; /* * The queue owner gets to use this for whatever they like. diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 290e8b7d3181..216449825859 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1988,11 +1988,11 @@ void laptop_mode_timer_fn(unsigned long data) * We want to write everything out, not just down to the dirty * threshold */ - if (!bdi_has_dirty_io(&q->backing_dev_info)) + if (!bdi_has_dirty_io(q->backing_dev_info)) return; rcu_read_lock(); - list_for_each_entry_rcu(wb, &q->backing_dev_info.wb_list, bdi_node) + list_for_each_entry_rcu(wb, &q->backing_dev_info->wb_list, bdi_node) if (wb_has_dirty_io(wb)) wb_start_writeback(wb, nr_pages, true, WB_REASON_LAPTOP_TIMER); -- cgit v1.2.3-59-g8ed1b From d03f6cdc1fc422accb734c7c07a661a0018d8631 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:51 +0100 Subject: block: Dynamically allocate and refcount backing_dev_info Instead of storing backing_dev_info inside struct request_queue, allocate it dynamically, reference count it, and free it when the last reference is dropped. Currently only request_queue holds the reference but in the following patch we add other users referencing backing_dev_info. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- block/blk-core.c | 12 +++++------- block/blk-sysfs.c | 2 +- include/linux/backing-dev-defs.h | 2 ++ include/linux/backing-dev.h | 10 +++++++++- include/linux/blkdev.h | 1 - mm/backing-dev.c | 34 +++++++++++++++++++++++++++++++++- 6 files changed, 50 insertions(+), 11 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index dcac0352c14c..d2bba4700e65 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -713,7 +713,6 @@ static void blk_rq_timed_out_timer(unsigned long data) struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) { struct request_queue *q; - int err; q = kmem_cache_alloc_node(blk_requestq_cachep, gfp_mask | __GFP_ZERO, node_id); @@ -728,17 +727,16 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) if (!q->bio_split) goto fail_id; - q->backing_dev_info = &q->_backing_dev_info; + q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id); + if (!q->backing_dev_info) + goto fail_split; + q->backing_dev_info->ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE; q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; q->backing_dev_info->name = "block"; q->node = node_id; - err = bdi_init(q->backing_dev_info); - if (err) - goto fail_split; - setup_timer(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, (unsigned long) q); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); @@ -789,7 +787,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) fail_ref: percpu_ref_exit(&q->q_usage_counter); fail_bdi: - bdi_destroy(q->backing_dev_info); + bdi_put(q->backing_dev_info); fail_split: bioset_free(q->bio_split); fail_id: diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 05841be1f30f..3e204789b8d3 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -799,7 +799,7 @@ static void blk_release_queue(struct kobject *kobj) container_of(kobj, struct request_queue, kobj); wbt_exit(q); - bdi_exit(q->backing_dev_info); + bdi_put(q->backing_dev_info); blkcg_exit_queue(q); if (q->elevator) { diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index e850e76acaaf..ad955817916d 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -10,6 +10,7 @@ #include #include #include +#include struct page; struct device; @@ -144,6 +145,7 @@ struct backing_dev_info { char *name; + struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 43b93a947e61..efb6ca992d05 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -18,7 +18,14 @@ #include int __must_check bdi_init(struct backing_dev_info *bdi); -void bdi_exit(struct backing_dev_info *bdi); + +static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) +{ + kref_get(&bdi->refcnt); + return bdi; +} + +void bdi_put(struct backing_dev_info *bdi); __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, @@ -29,6 +36,7 @@ void bdi_unregister(struct backing_dev_info *bdi); int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); void bdi_destroy(struct backing_dev_info *bdi); +struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id); void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, bool range_cyclic, enum wb_reason reason); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a75e42de34ab..e77c1039fd0e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -433,7 +433,6 @@ struct request_queue { struct delayed_work delay_work; struct backing_dev_info *backing_dev_info; - struct backing_dev_info _backing_dev_info; /* * The queue owner gets to use this for whatever they like. diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 3bfed5ab2475..28ce6cf7b2ff 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -237,6 +237,7 @@ static __init int bdi_class_init(void) bdi_class->dev_groups = bdi_dev_groups; bdi_debug_init(); + return 0; } postcore_initcall(bdi_class_init); @@ -776,6 +777,7 @@ int bdi_init(struct backing_dev_info *bdi) bdi->dev = NULL; + kref_init(&bdi->refcnt); bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = FPROP_FRAC_BASE; @@ -791,6 +793,22 @@ int bdi_init(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_init); +struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) +{ + struct backing_dev_info *bdi; + + bdi = kmalloc_node(sizeof(struct backing_dev_info), + gfp_mask | __GFP_ZERO, node_id); + if (!bdi) + return NULL; + + if (bdi_init(bdi)) { + kfree(bdi); + return NULL; + } + return bdi; +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -871,12 +889,26 @@ void bdi_unregister(struct backing_dev_info *bdi) } } -void bdi_exit(struct backing_dev_info *bdi) +static void bdi_exit(struct backing_dev_info *bdi) { WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); } +static void release_bdi(struct kref *ref) +{ + struct backing_dev_info *bdi = + container_of(ref, struct backing_dev_info, refcnt); + + bdi_exit(bdi); + kfree(bdi); +} + +void bdi_put(struct backing_dev_info *bdi) +{ + kref_put(&bdi->refcnt, release_bdi); +} + void bdi_destroy(struct backing_dev_info *bdi) { bdi_unregister(bdi); -- cgit v1.2.3-59-g8ed1b From b1d2dc5659b41741f5a29b2ade76ffb4e5bb13d8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:52 +0100 Subject: block: Make blk_get_backing_dev_info() safe without open bdev Currenly blk_get_backing_dev_info() is not safe to be called when the block device is not open as bdev->bd_disk is NULL in that case. However inode_to_bdi() uses this function and may be call called from flusher worker or other writeback related functions without bdev being open which leads to crashes such as: [113031.075540] Unable to handle kernel paging request for data at address 0x00000000 [113031.075614] Faulting instruction address: 0xc0000000003692e0 0:mon> t [c0000000fb65f900] c00000000036cb6c writeback_sb_inodes+0x30c/0x590 [c0000000fb65fa10] c00000000036ced4 __writeback_inodes_wb+0xe4/0x150 [c0000000fb65fa70] c00000000036d33c wb_writeback+0x30c/0x450 [c0000000fb65fb40] c00000000036e198 wb_workfn+0x268/0x580 [c0000000fb65fc50] c0000000000f3470 process_one_work+0x1e0/0x590 [c0000000fb65fce0] c0000000000f38c8 worker_thread+0xa8/0x660 [c0000000fb65fd80] c0000000000fc4b0 kthread+0x110/0x130 [c0000000fb65fe30] c0000000000098f0 ret_from_kernel_thread+0x5c/0x6c Signed-off-by: Jens Axboe --- block/blk-core.c | 8 +++----- fs/block_dev.c | 7 +++++++ include/linux/fs.h | 1 + 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index d2bba4700e65..6375674e719b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -110,14 +110,12 @@ void blk_queue_congestion_threshold(struct request_queue *q) * @bdev: device * * Locates the passed device's request queue and returns the address of its - * backing_dev_info. This function can only be called if @bdev is opened - * and the return value is never NULL. + * backing_dev_info. The return value is never NULL however we may return + * &noop_backing_dev_info if the bdev is not currently open. */ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - return q->backing_dev_info; + return bdev->bd_bdi; } EXPORT_SYMBOL(blk_get_backing_dev_info); diff --git a/fs/block_dev.c b/fs/block_dev.c index ed6a34be7a1e..601b71b76d7f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -884,6 +884,8 @@ static void bdev_evict_inode(struct inode *inode) spin_lock(&bdev_lock); list_del_init(&bdev->bd_list); spin_unlock(&bdev_lock); + if (bdev->bd_bdi != &noop_backing_dev_info) + bdi_put(bdev->bd_bdi); } static const struct super_operations bdev_sops = { @@ -986,6 +988,7 @@ struct block_device *bdget(dev_t dev) bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; + bdev->bd_bdi = &noop_backing_dev_info; bdev->bd_block_size = (1 << inode->i_blkbits); bdev->bd_part_count = 0; bdev->bd_invalidated = 0; @@ -1542,6 +1545,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; + if (bdev->bd_bdi == &noop_backing_dev_info) + bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); if (!partno) { ret = -ENXIO; @@ -1637,6 +1642,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = NULL; bdev->bd_part = NULL; bdev->bd_queue = NULL; + bdi_put(bdev->bd_bdi); + bdev->bd_bdi = &noop_backing_dev_info; if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; diff --git a/include/linux/fs.h b/include/linux/fs.h index 702cb6c50194..c930cbc19342 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -423,6 +423,7 @@ struct block_device { int bd_invalidated; struct gendisk * bd_disk; struct request_queue * bd_queue; + struct backing_dev_info *bd_bdi; struct list_head bd_list; /* * Private data. You must have bd_claim'ed the block_device -- cgit v1.2.3-59-g8ed1b From efa7c9f97e3ef624e9a398bf69c15f58eea9f0e8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 2 Feb 2017 15:56:53 +0100 Subject: block: Get rid of blk_get_backing_dev_info() blk_get_backing_dev_info() is now a simple dereference. Remove that function and simplify some code around that. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- block/blk-core.c | 14 -------------- block/compat_ioctl.c | 7 ++----- block/ioctl.c | 7 ++----- fs/btrfs/disk-io.c | 2 +- fs/btrfs/volumes.c | 2 +- fs/xfs/xfs_buf.c | 3 +-- fs/xfs/xfs_buf.h | 1 - include/linux/backing-dev.h | 2 +- include/linux/blkdev.h | 1 - 9 files changed, 8 insertions(+), 31 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 6375674e719b..a3c29270807e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -105,20 +105,6 @@ void blk_queue_congestion_threshold(struct request_queue *q) q->nr_congestion_off = nr; } -/** - * blk_get_backing_dev_info - get the address of a queue's backing_dev_info - * @bdev: device - * - * Locates the passed device's request queue and returns the address of its - * backing_dev_info. The return value is never NULL however we may return - * &noop_backing_dev_info if the bdev is not currently open. - */ -struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev) -{ - return bdev->bd_bdi; -} -EXPORT_SYMBOL(blk_get_backing_dev_info); - void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 556826ac7cb4..570021a0dc1c 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -661,7 +661,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) struct block_device *bdev = inode->i_bdev; struct gendisk *disk = bdev->bd_disk; fmode_t mode = file->f_mode; - struct backing_dev_info *bdi; loff_t size; unsigned int max_sectors; @@ -708,9 +707,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKFRAGET: if (!arg) return -EINVAL; - bdi = blk_get_backing_dev_info(bdev); return compat_put_long(arg, - (bdi->ra_pages * PAGE_SIZE) / 512); + (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512); case BLKROGET: /* compatible */ return compat_put_int(arg, bdev_read_only(bdev) != 0); case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */ @@ -728,8 +726,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKFRASET: if (!capable(CAP_SYS_ADMIN)) return -EACCES; - bdi = blk_get_backing_dev_info(bdev); - bdi->ra_pages = (arg * 512) / PAGE_SIZE; + bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKGETSIZE: size = i_size_read(bdev->bd_inode); diff --git a/block/ioctl.c b/block/ioctl.c index be7f4de3eb3c..7b88820b93d9 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -505,7 +505,6 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode, int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { - struct backing_dev_info *bdi; void __user *argp = (void __user *)arg; loff_t size; unsigned int max_sectors; @@ -532,8 +531,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKFRAGET: if (!arg) return -EINVAL; - bdi = blk_get_backing_dev_info(bdev); - return put_long(arg, (bdi->ra_pages * PAGE_SIZE) / 512); + return put_long(arg, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512); case BLKROGET: return put_int(arg, bdev_read_only(bdev) != 0); case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ @@ -560,8 +558,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) return -EACCES; - bdi = blk_get_backing_dev_info(bdev); - bdi->ra_pages = (arg * 512) / PAGE_SIZE; + bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKBSZSET: return blkdev_bszset(bdev, mode, argp); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 18004169552c..37a31b12bb0c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1800,7 +1800,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits) list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { if (!device->bdev) continue; - bdi = blk_get_backing_dev_info(device->bdev); + bdi = device->bdev->bd_bdi; if (bdi_congested(bdi, bdi_bits)) { ret = 1; break; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3c3c69c0eee4..b2e70073a10d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -366,7 +366,7 @@ static noinline void run_scheduled_bios(struct btrfs_device *device) */ blk_start_plug(&plug); - bdi = blk_get_backing_dev_info(device->bdev); + bdi = device->bdev->bd_bdi; limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 7f0a01f7b592..8bbec20aa138 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -757,7 +757,7 @@ xfs_buf_readahead_map( int nmaps, const struct xfs_buf_ops *ops) { - if (bdi_read_congested(target->bt_bdi)) + if (bdi_read_congested(target->bt_bdev->bd_bdi)) return; xfs_buf_read_map(target, map, nmaps, @@ -1790,7 +1790,6 @@ xfs_alloc_buftarg( btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_bdi = blk_get_backing_dev_info(bdev); if (xfs_setsize_buftarg_early(btp, bdev)) goto error; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 8a9d3a9599f0..3c867e5a63e1 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -109,7 +109,6 @@ typedef unsigned int xfs_buf_flags_t; typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; - struct backing_dev_info *bt_bdi; struct xfs_mount *bt_mount; unsigned int bt_meta_sectorsize; size_t bt_meta_sectormask; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index efb6ca992d05..c52a48cb9a66 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -191,7 +191,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) - return blk_get_backing_dev_info(I_BDEV(inode)); + return I_BDEV(inode)->bd_bdi; #endif return sb->s_bdi; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e77c1039fd0e..b31137e2afd0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1187,7 +1187,6 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); -extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { -- cgit v1.2.3-59-g8ed1b From 0dba1314d4f81115dce711292ec7981d17231064 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 1 Feb 2017 14:05:23 -0800 Subject: scsi, block: fix duplicate bdi name registration crashes Warnings of the following form occur because scsi reuses a devt number while the block layer still has it referenced as the name of the bdi [1]: WARNING: CPU: 1 PID: 93 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x62/0x80 sysfs: cannot create duplicate filename '/devices/virtual/bdi/8:192' [..] Call Trace: dump_stack+0x86/0xc3 __warn+0xcb/0xf0 warn_slowpath_fmt+0x5f/0x80 ? kernfs_path_from_node+0x4f/0x60 sysfs_warn_dup+0x62/0x80 sysfs_create_dir_ns+0x77/0x90 kobject_add_internal+0xb2/0x350 kobject_add+0x75/0xd0 device_add+0x15a/0x650 device_create_groups_vargs+0xe0/0xf0 device_create_vargs+0x1c/0x20 bdi_register+0x90/0x240 ? lockdep_init_map+0x57/0x200 bdi_register_owner+0x36/0x60 device_add_disk+0x1bb/0x4e0 ? __pm_runtime_use_autosuspend+0x5c/0x70 sd_probe_async+0x10d/0x1c0 async_run_entry_fn+0x39/0x170 This is a brute-force fix to pass the devt release information from sd_probe() to the locations where we register the bdi, device_add_disk(), and unregister the bdi, blk_cleanup_queue(). Thanks to Omar for the quick reproducer script [2]. This patch survives where an unmodified kernel fails in a few seconds. [1]: https://marc.info/?l=linux-scsi&m=147116857810716&w=4 [2]: http://marc.info/?l=linux-block&m=148554717109098&w=2 Cc: James Bottomley Cc: Bart Van Assche Cc: "Martin K. Petersen" Cc: Jan Kara Reported-by: Omar Sandoval Tested-by: Omar Sandoval Signed-off-by: Dan Williams Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + block/genhd.c | 21 +++++++++++++++++++++ drivers/scsi/sd.c | 41 +++++++++++++++++++++++++++++++++-------- include/linux/blkdev.h | 1 + include/linux/genhd.h | 8 ++++++++ 5 files changed, 64 insertions(+), 8 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index a3c29270807e..a5726e01f839 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -572,6 +572,7 @@ void blk_cleanup_queue(struct request_queue *q) spin_unlock_irq(lock); bdi_unregister(q->backing_dev_info); + put_disk_devt(q->disk_devt); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); diff --git a/block/genhd.c b/block/genhd.c index d9ccd42f3675..3631cd480295 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -572,6 +572,20 @@ exit: disk_part_iter_exit(&piter); } +void put_disk_devt(struct disk_devt *disk_devt) +{ + if (disk_devt && atomic_dec_and_test(&disk_devt->count)) + disk_devt->release(disk_devt); +} +EXPORT_SYMBOL(put_disk_devt); + +void get_disk_devt(struct disk_devt *disk_devt) +{ + if (disk_devt) + atomic_inc(&disk_devt->count); +} +EXPORT_SYMBOL(get_disk_devt); + /** * device_add_disk - add partitioning information to kernel list * @parent: parent device for the disk @@ -612,6 +626,13 @@ void device_add_disk(struct device *parent, struct gendisk *disk) disk_alloc_events(disk); + /* + * Take a reference on the devt and assign it to queue since it + * must not be reallocated while the bdi is registered + */ + disk->queue->disk_devt = disk->disk_devt; + get_disk_devt(disk->disk_devt); + /* Register BDI before referencing it from bdev */ bdi = disk->queue->backing_dev_info; bdi_register_owner(bdi, disk_to_dev(disk)); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index bd2fb4d52efa..dff709e22370 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3064,6 +3064,23 @@ static void sd_probe_async(void *data, async_cookie_t cookie) put_device(&sdkp->dev); } +struct sd_devt { + int idx; + struct disk_devt disk_devt; +}; + +void sd_devt_release(struct disk_devt *disk_devt) +{ + struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt, + disk_devt); + + spin_lock(&sd_index_lock); + ida_remove(&sd_index_ida, sd_devt->idx); + spin_unlock(&sd_index_lock); + + kfree(sd_devt); +} + /** * sd_probe - called during driver initialization and whenever a * new scsi device is attached to the system. It is called once @@ -3085,6 +3102,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie) static int sd_probe(struct device *dev) { struct scsi_device *sdp = to_scsi_device(dev); + struct sd_devt *sd_devt; struct scsi_disk *sdkp; struct gendisk *gd; int index; @@ -3110,9 +3128,13 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; + sd_devt = kzalloc(sizeof(*sd_devt), GFP_KERNEL); + if (!sd_devt) + goto out_free; + gd = alloc_disk(SD_MINORS); if (!gd) - goto out_free; + goto out_free_devt; do { if (!ida_pre_get(&sd_index_ida, GFP_KERNEL)) @@ -3128,6 +3150,11 @@ static int sd_probe(struct device *dev) goto out_put; } + atomic_set(&sd_devt->disk_devt.count, 1); + sd_devt->disk_devt.release = sd_devt_release; + sd_devt->idx = index; + gd->disk_devt = &sd_devt->disk_devt; + error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN); if (error) { sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n"); @@ -3167,13 +3194,14 @@ static int sd_probe(struct device *dev) return 0; out_free_index: - spin_lock(&sd_index_lock); - ida_remove(&sd_index_ida, index); - spin_unlock(&sd_index_lock); + put_disk_devt(&sd_devt->disk_devt); + sd_devt = NULL; out_put: put_disk(gd); out_free: kfree(sdkp); + out_free_devt: + kfree(sd_devt); out: scsi_autopm_put_device(sdp); return error; @@ -3232,10 +3260,7 @@ static void scsi_disk_release(struct device *dev) struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; - spin_lock(&sd_index_lock); - ida_remove(&sd_index_ida, sdkp->index); - spin_unlock(&sd_index_lock); - + put_disk_devt(disk->disk_devt); disk->private_data = NULL; put_disk(disk); put_device(&sdkp->device->sdev_gendev); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b31137e2afd0..f84fbe55d3b3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -433,6 +433,7 @@ struct request_queue { struct delayed_work delay_work; struct backing_dev_info *backing_dev_info; + struct disk_devt *disk_devt; /* * The queue owner gets to use this for whatever they like. diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 76f39754e7b0..a999d281a2f1 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -167,6 +167,13 @@ struct blk_integrity { }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ +struct disk_devt { + atomic_t count; + void (*release)(struct disk_devt *disk_devt); +}; + +void put_disk_devt(struct disk_devt *disk_devt); +void get_disk_devt(struct disk_devt *disk_devt); struct gendisk { /* major, first_minor and minors are input parameters only, @@ -176,6 +183,7 @@ struct gendisk { int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ + struct disk_devt *disk_devt; char disk_name[DISK_NAME_LEN]; /* name of major driver */ char *(*devnode)(struct gendisk *gd, umode_t *mode); -- cgit v1.2.3-59-g8ed1b From 18fbda91c6370d520278db9ee1e768b59ef5c4ab Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 31 Jan 2017 14:53:20 -0800 Subject: block: use same block debugfs directory for blk-mq and blktrace When I added the blk-mq debugging information to debugfs, I didn't notice that blktrace also creates a "block" directory in debugfs. Make them use the same dentry, now created in the core block code. Based on a patch from Jens. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-core.c | 9 +++++++++ block/blk-mq-debugfs.c | 12 +++--------- block/blk-mq.c | 2 -- block/blk-mq.h | 5 ----- block/blk.h | 4 ++++ kernel/trace/blktrace.c | 18 +++++------------- 6 files changed, 21 insertions(+), 29 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index a5726e01f839..76c42f559df8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -33,6 +33,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -42,6 +43,10 @@ #include "blk-mq-sched.h" #include "blk-wbt.h" +#ifdef CONFIG_DEBUG_FS +struct dentry *blk_debugfs_root; +#endif + EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); @@ -3441,5 +3446,9 @@ int __init blk_dev_init(void) blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); +#ifdef CONFIG_DEBUG_FS + blk_debugfs_root = debugfs_create_dir("block", NULL); +#endif + return 0; } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 1077008690b2..f6d917977b33 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -19,6 +19,7 @@ #include #include +#include "blk.h" #include "blk-mq.h" #include "blk-mq-tag.h" @@ -28,8 +29,6 @@ struct blk_mq_debugfs_attr { const struct file_operations *fops; }; -static struct dentry *block_debugfs_root; - static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file, const struct seq_operations *ops) { @@ -665,10 +664,10 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { int blk_mq_debugfs_register(struct request_queue *q, const char *name) { - if (!block_debugfs_root) + if (!blk_debugfs_root) return -ENOENT; - q->debugfs_dir = debugfs_create_dir(name, block_debugfs_root); + q->debugfs_dir = debugfs_create_dir(name, blk_debugfs_root); if (!q->debugfs_dir) goto err; @@ -771,8 +770,3 @@ void blk_mq_debugfs_unregister_hctxs(struct request_queue *q) debugfs_remove_recursive(q->mq_debugfs_dir); q->mq_debugfs_dir = NULL; } - -void blk_mq_debugfs_init(void) -{ - block_debugfs_root = debugfs_create_dir("block", NULL); -} diff --git a/block/blk-mq.c b/block/blk-mq.c index 3d76e860f126..e9957df05700 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2817,8 +2817,6 @@ void blk_mq_enable_hotplug(void) static int __init blk_mq_init(void) { - blk_mq_debugfs_init(); - cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); diff --git a/block/blk-mq.h b/block/blk-mq.h index b52abd62b1b0..24b2256186f3 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -85,16 +85,11 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); * debugfs helpers */ #ifdef CONFIG_BLK_DEBUG_FS -void blk_mq_debugfs_init(void); int blk_mq_debugfs_register(struct request_queue *q, const char *name); void blk_mq_debugfs_unregister(struct request_queue *q); int blk_mq_debugfs_register_hctxs(struct request_queue *q); void blk_mq_debugfs_unregister_hctxs(struct request_queue *q); #else -static inline void blk_mq_debugfs_init(void) -{ -} - static inline int blk_mq_debugfs_register(struct request_queue *q, const char *name) { diff --git a/block/blk.h b/block/blk.h index c1bd4bf9e645..6aa53a4aad88 100644 --- a/block/blk.h +++ b/block/blk.h @@ -14,6 +14,10 @@ /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) +#ifdef CONFIG_DEBUG_FS +extern struct dentry *blk_debugfs_root; +#endif + struct blk_flush_queue { unsigned int flush_queue_delayed:1; unsigned int flush_pending_idx:1; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 84763e0c83cf..8cea91d248d9 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -28,6 +28,8 @@ #include #include +#include "../../block/blk.h" + #include #include "trace_output.h" @@ -292,9 +294,6 @@ record_it: local_irq_restore(flags); } -static struct dentry *blk_tree_root; -static DEFINE_MUTEX(blk_tree_mutex); - static void blk_trace_free(struct blk_trace *bt) { debugfs_remove(bt->msg_file); @@ -468,17 +467,10 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = -ENOENT; - mutex_lock(&blk_tree_mutex); - if (!blk_tree_root) { - blk_tree_root = debugfs_create_dir("block", NULL); - if (!blk_tree_root) { - mutex_unlock(&blk_tree_mutex); - goto err; - } - } - mutex_unlock(&blk_tree_mutex); + if (!blk_debugfs_root) + goto err; - dir = debugfs_create_dir(buts->name, blk_tree_root); + dir = debugfs_create_dir(buts->name, blk_debugfs_root); if (!dir) goto err; -- cgit v1.2.3-59-g8ed1b From 62ebce16c0ac2ffac44e32f931a2d8f6e749be4c Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 31 Jan 2017 14:53:21 -0800 Subject: blk-mq: move debugfs_remove() of disk dir to blk_release_queue() This needs to happen after we tear down blktrace. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq-sysfs.c | 2 +- block/blk-sysfs.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 308b3f4fc310..295e69670c39 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -254,7 +254,7 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q) kobject_put(&hctx->kobj); } - blk_mq_debugfs_unregister(q); + blk_mq_debugfs_unregister_hctxs(q); kobject_uevent(&q->mq_kobj, KOBJ_REMOVE); kobject_del(&q->mq_kobj); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 3e204789b8d3..3ce1217778f4 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -824,6 +824,9 @@ static void blk_release_queue(struct kobject *kobj) blk_trace_shutdown(q); + if (q->mq_ops) + blk_mq_debugfs_unregister(q); + if (q->bio_split) bioset_free(q->bio_split); -- cgit v1.2.3-59-g8ed1b From 0cacba6cf8252438f8166bd3fa1c3370dd28a769 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 2 Feb 2017 15:42:39 -0800 Subject: blk-mq-sched: bypass the scheduler for flushes entirely There's a weird inconsistency that flushes are mostly hidden from the scheduler, but it needs to be aware of them in ->insert_requests(). Instead of having every scheduler call blk_mq_sched_bypass_insert(), let's do it in the common framework. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 25 +++++++++++++++++++++++-- block/blk-mq-sched.h | 1 - block/mq-deadline.c | 3 --- 3 files changed, 23 insertions(+), 6 deletions(-) (limited to 'block') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 114814ec3d49..3ec52f494094 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -289,7 +289,8 @@ void blk_mq_sched_request_inserted(struct request *rq) } EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted); -bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq) +static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, + struct request *rq) { if (rq->tag == -1) { rq->rq_flags |= RQF_SORTED; @@ -305,7 +306,6 @@ bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq) spin_unlock(&hctx->lock); return true; } -EXPORT_SYMBOL_GPL(blk_mq_sched_bypass_insert); static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) { @@ -363,6 +363,9 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, return; } + if (e && blk_mq_sched_bypass_insert(hctx, rq)) + goto run; + if (e && e->type->ops.mq.insert_requests) { LIST_HEAD(list); @@ -374,6 +377,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, spin_unlock(&ctx->lock); } +run: if (run_queue) blk_mq_run_hw_queue(hctx, async); } @@ -385,6 +389,23 @@ void blk_mq_sched_insert_requests(struct request_queue *q, struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); struct elevator_queue *e = hctx->queue->elevator; + if (e) { + struct request *rq, *next; + + /* + * We bypass requests that already have a driver tag assigned, + * which should only be flushes. Flushes are only ever inserted + * as single requests, so we shouldn't ever hit the + * WARN_ON_ONCE() below (but let's handle it just in case). + */ + list_for_each_entry_safe(rq, next, list, queuelist) { + if (WARN_ON_ONCE(rq->tag != -1)) { + list_del_init(&rq->queuelist); + blk_mq_sched_bypass_insert(hctx, rq); + } + } + } + if (e && e->type->ops.mq.insert_requests) e->type->ops.mq.insert_requests(hctx, list, false); else diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 9478aaeb48c5..add5f090a8cd 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -15,7 +15,6 @@ struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bi void blk_mq_sched_put_request(struct request *rq); void blk_mq_sched_request_inserted(struct request *rq); -bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio); bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio); bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 49583536698c..8f91f21e8663 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -395,9 +395,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_mq_sched_request_inserted(rq); - if (blk_mq_sched_bypass_insert(hctx, rq)) - return; - if (at_head || blk_rq_is_passthrough(rq)) { if (at_head) list_add(&rq->queuelist, &dd->dispatch); -- cgit v1.2.3-59-g8ed1b From 9b54d816e00425c3a517514e0d677bb3cec49258 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 3 Feb 2017 17:19:07 +0800 Subject: blkcg: fix double free of new_blkg in blkcg_init_queue If blkg_create fails, new_blkg passed as an argument will be freed by blkg_create, so there is no need to free it again. Signed-off-by: Hou Tao Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'block') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 37fe595cfd70..295e98c2c8cc 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1079,10 +1079,8 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); - if (IS_ERR(blkg)) { - blkg_free(new_blkg); + if (IS_ERR(blkg)) return PTR_ERR(blkg); - } q->root_blkg = blkg; q->root_rl.blkg = blkg; -- cgit v1.2.3-59-g8ed1b From b973cb7e89fe3dcc2bc72c5b3aa7a3bfd9d0e6d5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 2 Feb 2017 08:54:40 -0700 Subject: blk-merge: return the merged request When we attempt to merge request-to-request, we return a 0/1 if we ended up merging or not. Change that to return the pointer to the request that we freed. We will use this to move the freeing of that request out of the merge logic, so that callers can drop locks before freeing the request. There should be no functional changes in this patch. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-merge.c | 31 ++++++++++++++++--------------- block/blk.h | 4 ++-- 2 files changed, 18 insertions(+), 17 deletions(-) (limited to 'block') diff --git a/block/blk-merge.c b/block/blk-merge.c index 6aa43dec5af4..3826fc32b72c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -659,31 +659,32 @@ static void blk_account_io_merge(struct request *req) } /* - * Has to be called with the request spinlock acquired + * For non-mq, this has to be called with the request spinlock acquired. + * For mq with scheduling, the appropriate queue wide lock should be held. */ -static int attempt_merge(struct request_queue *q, struct request *req, - struct request *next) +static struct request *attempt_merge(struct request_queue *q, + struct request *req, struct request *next) { if (!rq_mergeable(req) || !rq_mergeable(next)) - return 0; + return NULL; if (req_op(req) != req_op(next)) - return 0; + return NULL; /* * not contiguous */ if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next)) - return 0; + return NULL; if (rq_data_dir(req) != rq_data_dir(next) || req->rq_disk != next->rq_disk || req_no_special_merge(next)) - return 0; + return NULL; if (req_op(req) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(req->bio, next->bio)) - return 0; + return NULL; /* * If we are allowed to merge, then append bio list @@ -692,7 +693,7 @@ static int attempt_merge(struct request_queue *q, struct request *req, * counts here. */ if (!ll_merge_requests_fn(q, req, next)) - return 0; + return NULL; /* * If failfast settings disagree or any of the two is already @@ -735,27 +736,27 @@ static int attempt_merge(struct request_queue *q, struct request *req, /* owner-ship of bio passed from next to req */ next->bio = NULL; __blk_put_request(q, next); - return 1; + return next; } -int attempt_back_merge(struct request_queue *q, struct request *rq) +struct request *attempt_back_merge(struct request_queue *q, struct request *rq) { struct request *next = elv_latter_request(q, rq); if (next) return attempt_merge(q, rq, next); - return 0; + return NULL; } -int attempt_front_merge(struct request_queue *q, struct request *rq) +struct request *attempt_front_merge(struct request_queue *q, struct request *rq) { struct request *prev = elv_former_request(q, rq); if (prev) return attempt_merge(q, prev, rq); - return 0; + return NULL; } int blk_attempt_req_merge(struct request_queue *q, struct request *rq, @@ -767,7 +768,7 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq, if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next)) return 0; - return attempt_merge(q, rq, next); + return attempt_merge(q, rq, next) != NULL; } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) diff --git a/block/blk.h b/block/blk.h index 6aa53a4aad88..4972b98d47e1 100644 --- a/block/blk.h +++ b/block/blk.h @@ -208,8 +208,8 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req, struct bio *bio); int ll_front_merge_fn(struct request_queue *q, struct request *req, struct bio *bio); -int attempt_back_merge(struct request_queue *q, struct request *rq); -int attempt_front_merge(struct request_queue *q, struct request *rq); +struct request *attempt_back_merge(struct request_queue *q, struct request *rq); +struct request *attempt_front_merge(struct request_queue *q, struct request *rq); int blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next); void blk_recalc_rq_segments(struct request *rq); -- cgit v1.2.3-59-g8ed1b From e4d750c97794ea2bab793d4c518b1f4006364588 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Feb 2017 09:48:28 -0700 Subject: block: free merged request in the caller If we end up doing a request-to-request merge when we have completed a bio-to-request merge, we free the request from deep down in that path. For blk-mq-sched, the merge path has to hold the appropriate lock, but we don't need it for freeing the request. And in fact holding the lock is problematic, since we are now calling the mq sched put_rq_private() hook with the lock held. Other call paths do not hold this lock. Fix this inconsistency by ensuring that the caller frees a merged request. Then we can do it outside of the lock, making it both more efficient and fixing the blk-mq-sched problem of invoking parts of the scheduler with an unknown lock state. Reported-by: Paolo Valente Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-core.c | 12 +++++++++--- block/blk-merge.c | 15 ++++++++++++--- block/blk-mq-sched.c | 9 ++++++--- block/blk-mq-sched.h | 3 ++- block/mq-deadline.c | 8 ++++++-- 5 files changed, 35 insertions(+), 12 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 76c42f559df8..1d263311353a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1596,7 +1596,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) { struct blk_plug *plug; int el_ret, where = ELEVATOR_INSERT_SORT; - struct request *req; + struct request *req, *free; unsigned int request_count = 0; unsigned int wb_acct; @@ -1637,15 +1637,21 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) if (el_ret == ELEVATOR_BACK_MERGE) { if (bio_attempt_back_merge(q, req, bio)) { elv_bio_merged(q, req, bio); - if (!attempt_back_merge(q, req)) + free = attempt_back_merge(q, req); + if (!free) elv_merged_request(q, req, el_ret); + else + __blk_put_request(q, free); goto out_unlock; } } else if (el_ret == ELEVATOR_FRONT_MERGE) { if (bio_attempt_front_merge(q, req, bio)) { elv_bio_merged(q, req, bio); - if (!attempt_front_merge(q, req)) + free = attempt_front_merge(q, req); + if (!free) elv_merged_request(q, req, el_ret); + else + __blk_put_request(q, free); goto out_unlock; } } diff --git a/block/blk-merge.c b/block/blk-merge.c index 3826fc32b72c..a373416dbc9a 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -733,9 +733,11 @@ static struct request *attempt_merge(struct request_queue *q, if (blk_rq_cpu_valid(next)) req->cpu = next->cpu; - /* owner-ship of bio passed from next to req */ + /* + * ownership of bio passed from next to req, return 'next' for + * the caller to free + */ next->bio = NULL; - __blk_put_request(q, next); return next; } @@ -763,12 +765,19 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next) { struct elevator_queue *e = q->elevator; + struct request *free; if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn) if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next)) return 0; - return attempt_merge(q, rq, next) != NULL; + free = attempt_merge(q, rq, next); + if (free) { + __blk_put_request(q, free); + return 1; + } + + return 0; } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 3ec52f494094..ee455e7cf9d8 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -234,7 +234,8 @@ void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx, } EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch); -bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio) +bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, + struct request **merged_request) { struct request *rq; int ret; @@ -244,7 +245,8 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio) if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_back_merge(q, rq, bio)) { - if (!attempt_back_merge(q, rq)) + *merged_request = attempt_back_merge(q, rq); + if (!*merged_request) elv_merged_request(q, rq, ret); return true; } @@ -252,7 +254,8 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio) if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_front_merge(q, rq, bio)) { - if (!attempt_front_merge(q, rq)) + *merged_request = attempt_front_merge(q, rq); + if (!*merged_request) elv_merged_request(q, rq, ret); return true; } diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index add5f090a8cd..5954859c8670 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -15,7 +15,8 @@ struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bi void blk_mq_sched_put_request(struct request *rq); void blk_mq_sched_request_inserted(struct request *rq); -bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio); +bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, + struct request **merged_request); bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio); bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq); void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 8f91f21e8663..d68d9c273a66 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -371,12 +371,16 @@ static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio) { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; - int ret; + struct request *free = NULL; + bool ret; spin_lock(&dd->lock); - ret = blk_mq_sched_try_merge(q, bio); + ret = blk_mq_sched_try_merge(q, bio, &free); spin_unlock(&dd->lock); + if (free) + blk_mq_free_request(free); + return ret; } -- cgit v1.2.3-59-g8ed1b From 80c6b15732f0d8830032149cbcbc8d67e074b5e8 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 6 Feb 2017 12:52:24 -0800 Subject: blk-mq-sched: (un)register elevator when (un)registering queue I noticed that when booting with a default blk-mq I/O scheduler, the /sys/block/*/queue/iosched directory was missing. However, switching after boot did create the directory. This is because we skip the initial elevator register/unregister when we don't have a ->request_fn(), but we should still do it for the ->mq_ops case. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'block') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 3ce1217778f4..48032c4759a7 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -903,16 +903,15 @@ int blk_register_queue(struct gendisk *disk) blk_wb_init(q); - if (!q->request_fn) - return 0; - - ret = elv_register_queue(q); - if (ret) { - kobject_uevent(&q->kobj, KOBJ_REMOVE); - kobject_del(&q->kobj); - blk_trace_remove_sysfs(dev); - kobject_put(&dev->kobj); - return ret; + if (q->request_fn || (q->mq_ops && q->elevator)) { + ret = elv_register_queue(q); + if (ret) { + kobject_uevent(&q->kobj, KOBJ_REMOVE); + kobject_del(&q->kobj); + blk_trace_remove_sysfs(dev); + kobject_put(&dev->kobj); + return ret; + } } return 0; @@ -928,7 +927,7 @@ void blk_unregister_queue(struct gendisk *disk) if (q->mq_ops) blk_mq_unregister_dev(disk_to_dev(disk), q); - if (q->request_fn) + if (q->request_fn || (q->mq_ops && q->elevator)) elv_unregister_queue(q); kobject_uevent(&q->kobj, KOBJ_REMOVE); -- cgit v1.2.3-59-g8ed1b From 6cf7677f1a94546e472658290b3b8bdbb16cc045 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Feb 2017 14:46:47 +0100 Subject: block: move req_set_nomerge to blk.h This makes it available outside of blk-merge.c, and inlining such a trivial helper seems pretty useful to start with. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-merge.c | 7 ------- block/blk.h | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'block') diff --git a/block/blk-merge.c b/block/blk-merge.c index a373416dbc9a..c956d9e7aafd 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -482,13 +482,6 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, } EXPORT_SYMBOL(blk_rq_map_sg); -static void req_set_nomerge(struct request_queue *q, struct request *req) -{ - req->cmd_flags |= REQ_NOMERGE; - if (req == q->last_merge) - q->last_merge = NULL; -} - static inline int ll_new_hw_segment(struct request_queue *q, struct request *req, struct bio *bio) diff --git a/block/blk.h b/block/blk.h index 4972b98d47e1..3e08703902a9 100644 --- a/block/blk.h +++ b/block/blk.h @@ -256,6 +256,13 @@ static inline int blk_do_io_stat(struct request *rq) !blk_rq_is_passthrough(rq); } +static inline void req_set_nomerge(struct request_queue *q, struct request *req) +{ + req->cmd_flags |= REQ_NOMERGE; + if (req == q->last_merge) + q->last_merge = NULL; +} + /* * Internal io_context interface */ -- cgit v1.2.3-59-g8ed1b From 34fe7c05400663e01e23cddd1fea68bb7a2b3d29 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Feb 2017 14:46:48 +0100 Subject: block: enumify ELEVATOR_*_MERGE Switch these constants to an enum, and make let the compiler ensure that all callers of blk_try_merge and elv_merge handle all potential values. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 76 +++++++++++++++++++++++++----------------------- block/blk-merge.c | 2 +- block/blk-mq-sched.c | 35 +++++++++++----------- block/blk-mq.c | 32 +++++++++----------- block/blk.h | 2 +- block/cfq-iosched.c | 4 +-- block/deadline-iosched.c | 12 +++----- block/elevator.c | 10 ++++--- block/mq-deadline.c | 2 +- include/linux/elevator.h | 28 ++++++++++-------- 10 files changed, 102 insertions(+), 101 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 1d263311353a..00e053c704a1 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1511,12 +1511,11 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, { struct blk_plug *plug; struct request *rq; - bool ret = false; struct list_head *plug_list; plug = current->plug; if (!plug) - goto out; + return false; *request_count = 0; if (q->mq_ops) @@ -1525,7 +1524,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, plug_list = &plug->list; list_for_each_entry_reverse(rq, plug_list, queuelist) { - int el_ret; + bool merged = false; if (rq->q == q) { (*request_count)++; @@ -1541,19 +1540,22 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, if (rq->q != q || !blk_rq_merge_ok(rq, bio)) continue; - el_ret = blk_try_merge(rq, bio); - if (el_ret == ELEVATOR_BACK_MERGE) { - ret = bio_attempt_back_merge(q, rq, bio); - if (ret) - break; - } else if (el_ret == ELEVATOR_FRONT_MERGE) { - ret = bio_attempt_front_merge(q, rq, bio); - if (ret) - break; + switch (blk_try_merge(rq, bio)) { + case ELEVATOR_BACK_MERGE: + merged = bio_attempt_back_merge(q, rq, bio); + break; + case ELEVATOR_FRONT_MERGE: + merged = bio_attempt_front_merge(q, rq, bio); + break; + default: + break; } + + if (merged) + return true; } -out: - return ret; + + return false; } unsigned int blk_plug_queued_count(struct request_queue *q) @@ -1595,7 +1597,7 @@ 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) { struct blk_plug *plug; - int el_ret, where = ELEVATOR_INSERT_SORT; + int where = ELEVATOR_INSERT_SORT; struct request *req, *free; unsigned int request_count = 0; unsigned int wb_acct; @@ -1633,27 +1635,29 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) spin_lock_irq(q->queue_lock); - el_ret = elv_merge(q, &req, bio); - if (el_ret == ELEVATOR_BACK_MERGE) { - if (bio_attempt_back_merge(q, req, bio)) { - elv_bio_merged(q, req, bio); - free = attempt_back_merge(q, req); - if (!free) - elv_merged_request(q, req, el_ret); - else - __blk_put_request(q, free); - goto out_unlock; - } - } else if (el_ret == ELEVATOR_FRONT_MERGE) { - if (bio_attempt_front_merge(q, req, bio)) { - elv_bio_merged(q, req, bio); - free = attempt_front_merge(q, req); - if (!free) - elv_merged_request(q, req, el_ret); - else - __blk_put_request(q, free); - goto out_unlock; - } + switch (elv_merge(q, &req, bio)) { + case ELEVATOR_BACK_MERGE: + if (!bio_attempt_back_merge(q, req, bio)) + break; + elv_bio_merged(q, req, bio); + free = attempt_back_merge(q, req); + if (free) + __blk_put_request(q, free); + else + elv_merged_request(q, req, ELEVATOR_BACK_MERGE); + goto out_unlock; + case ELEVATOR_FRONT_MERGE: + if (!bio_attempt_front_merge(q, req, bio)) + break; + elv_bio_merged(q, req, bio); + free = attempt_front_merge(q, req); + if (free) + __blk_put_request(q, free); + else + elv_merged_request(q, req, ELEVATOR_FRONT_MERGE); + goto out_unlock; + default: + break; } get_rq: diff --git a/block/blk-merge.c b/block/blk-merge.c index c956d9e7aafd..6cbd90ad5f90 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -801,7 +801,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) return true; } -int blk_try_merge(struct request *rq, struct bio *bio) +enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index ee455e7cf9d8..72d0d8361175 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -238,30 +238,29 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, struct request **merged_request) { struct request *rq; - int ret; - ret = elv_merge(q, &rq, bio); - if (ret == ELEVATOR_BACK_MERGE) { + switch (elv_merge(q, &rq, bio)) { + case ELEVATOR_BACK_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; - if (bio_attempt_back_merge(q, rq, bio)) { - *merged_request = attempt_back_merge(q, rq); - if (!*merged_request) - elv_merged_request(q, rq, ret); - return true; - } - } else if (ret == ELEVATOR_FRONT_MERGE) { + if (!bio_attempt_back_merge(q, rq, bio)) + return false; + *merged_request = attempt_back_merge(q, rq); + if (!*merged_request) + elv_merged_request(q, rq, ELEVATOR_BACK_MERGE); + return true; + case ELEVATOR_FRONT_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; - if (bio_attempt_front_merge(q, rq, bio)) { - *merged_request = attempt_front_merge(q, rq); - if (!*merged_request) - elv_merged_request(q, rq, ret); - return true; - } + if (!bio_attempt_front_merge(q, rq, bio)) + return false; + *merged_request = attempt_front_merge(q, rq); + if (!*merged_request) + elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE); + return true; + default: + return false; } - - return false; } EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); diff --git a/block/blk-mq.c b/block/blk-mq.c index e9957df05700..dd9722df4afe 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -763,7 +763,7 @@ static bool blk_mq_attempt_merge(struct request_queue *q, int checked = 8; list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) { - int el_ret; + bool merged = false; if (!checked--) break; @@ -771,26 +771,22 @@ static bool blk_mq_attempt_merge(struct request_queue *q, if (!blk_rq_merge_ok(rq, bio)) continue; - el_ret = blk_try_merge(rq, bio); - if (el_ret == ELEVATOR_NO_MERGE) - continue; - - if (!blk_mq_sched_allow_merge(q, rq, bio)) + switch (blk_try_merge(rq, bio)) { + case ELEVATOR_BACK_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_back_merge(q, rq, bio); break; - - if (el_ret == ELEVATOR_BACK_MERGE) { - if (bio_attempt_back_merge(q, rq, bio)) { - ctx->rq_merged++; - return true; - } - break; - } else if (el_ret == ELEVATOR_FRONT_MERGE) { - if (bio_attempt_front_merge(q, rq, bio)) { - ctx->rq_merged++; - return true; - } + case ELEVATOR_FRONT_MERGE: + if (blk_mq_sched_allow_merge(q, rq, bio)) + merged = bio_attempt_front_merge(q, rq, bio); break; + default: + continue; } + + if (merged) + ctx->rq_merged++; + return merged; } return false; diff --git a/block/blk.h b/block/blk.h index 3e08703902a9..ae82f2ac4019 100644 --- a/block/blk.h +++ b/block/blk.h @@ -215,7 +215,7 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq, void blk_recalc_rq_segments(struct request *rq); void blk_rq_set_mixed_merge(struct request *rq); bool blk_rq_merge_ok(struct request *rq, struct bio *bio); -int blk_try_merge(struct request *rq, struct bio *bio); +enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); void blk_queue_congestion_threshold(struct request_queue *q); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index f0f29ee731e1..921262770636 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -2528,7 +2528,7 @@ static void cfq_remove_request(struct request *rq) } } -static int cfq_merge(struct request_queue *q, struct request **req, +static enum elv_merge cfq_merge(struct request_queue *q, struct request **req, struct bio *bio) { struct cfq_data *cfqd = q->elevator->elevator_data; @@ -2544,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req, } static void cfq_merged_request(struct request_queue *q, struct request *req, - int type) + enum elv_merge type) { if (type == ELEVATOR_FRONT_MERGE) { struct cfq_queue *cfqq = RQ_CFQQ(req); diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c index 05fc0ea25a98..c68f6bbc0dcd 100644 --- a/block/deadline-iosched.c +++ b/block/deadline-iosched.c @@ -120,12 +120,11 @@ static void deadline_remove_request(struct request_queue *q, struct request *rq) deadline_del_rq_rb(dd, rq); } -static int +static enum elv_merge deadline_merge(struct request_queue *q, struct request **req, struct bio *bio) { struct deadline_data *dd = q->elevator->elevator_data; struct request *__rq; - int ret; /* * check for front merge @@ -138,20 +137,17 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio) BUG_ON(sector != blk_rq_pos(__rq)); if (elv_bio_merge_ok(__rq, bio)) { - ret = ELEVATOR_FRONT_MERGE; - goto out; + *req = __rq; + return ELEVATOR_FRONT_MERGE; } } } return ELEVATOR_NO_MERGE; -out: - *req = __rq; - return ret; } static void deadline_merged_request(struct request_queue *q, - struct request *req, int type) + struct request *req, enum elv_merge type) { struct deadline_data *dd = q->elevator->elevator_data; diff --git a/block/elevator.c b/block/elevator.c index 7e4f5880dd64..27ff1ed5a6fa 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -427,11 +427,11 @@ void elv_dispatch_add_tail(struct request_queue *q, struct request *rq) } EXPORT_SYMBOL(elv_dispatch_add_tail); -int elv_merge(struct request_queue *q, struct request **req, struct bio *bio) +enum elv_merge elv_merge(struct request_queue *q, struct request **req, + struct bio *bio) { struct elevator_queue *e = q->elevator; struct request *__rq; - int ret; /* * Levels of merges: @@ -446,7 +446,8 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio) * First try one-hit cache. */ if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) { - ret = blk_try_merge(q->last_merge, bio); + enum elv_merge ret = blk_try_merge(q->last_merge, bio); + if (ret != ELEVATOR_NO_MERGE) { *req = q->last_merge; return ret; @@ -514,7 +515,8 @@ bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq) return ret; } -void elv_merged_request(struct request_queue *q, struct request *rq, int type) +void elv_merged_request(struct request_queue *q, struct request *rq, + enum elv_merge type) { struct elevator_queue *e = q->elevator; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index d68d9c273a66..236121633ca0 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -121,7 +121,7 @@ static void deadline_remove_request(struct request_queue *q, struct request *rq) } static void dd_request_merged(struct request_queue *q, struct request *req, - int type) + enum elv_merge type) { struct deadline_data *dd = q->elevator->elevator_data; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index b5825c4f06f7..b38b4e651ea6 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -9,12 +9,21 @@ struct io_cq; struct elevator_type; -typedef int (elevator_merge_fn) (struct request_queue *, struct request **, +/* + * Return values from elevator merger + */ +enum elv_merge { + ELEVATOR_NO_MERGE = 0, + ELEVATOR_FRONT_MERGE = 1, + ELEVATOR_BACK_MERGE = 2, +}; + +typedef enum elv_merge (elevator_merge_fn) (struct request_queue *, struct request **, struct bio *); typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, struct request *); -typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int); +typedef void (elevator_merged_fn) (struct request_queue *, struct request *, enum elv_merge); typedef int (elevator_allow_bio_merge_fn) (struct request_queue *, struct request *, struct bio *); @@ -87,7 +96,7 @@ struct elevator_mq_ops { bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *); int (*request_merge)(struct request_queue *q, struct request **, struct bio *); - void (*request_merged)(struct request_queue *, struct request *, int); + void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *); void (*put_request)(struct request *); @@ -166,10 +175,12 @@ extern void elv_dispatch_sort(struct request_queue *, struct request *); extern void elv_dispatch_add_tail(struct request_queue *, struct request *); extern void elv_add_request(struct request_queue *, struct request *, int); extern void __elv_add_request(struct request_queue *, struct request *, int); -extern int elv_merge(struct request_queue *, struct request **, struct bio *); +extern enum elv_merge elv_merge(struct request_queue *, struct request **, + struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); -extern void elv_merged_request(struct request_queue *, struct request *, int); +extern void elv_merged_request(struct request_queue *, struct request *, + enum elv_merge); extern void elv_bio_merged(struct request_queue *q, struct request *, struct bio *); extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); @@ -218,13 +229,6 @@ extern void elv_rb_add(struct rb_root *, struct request *); extern void elv_rb_del(struct rb_root *, struct request *); extern struct request *elv_rb_find(struct rb_root *, sector_t); -/* - * Return values from elevator merger - */ -#define ELEVATOR_NO_MERGE 0 -#define ELEVATOR_FRONT_MERGE 1 -#define ELEVATOR_BACK_MERGE 2 - /* * Insertion selection */ -- cgit v1.2.3-59-g8ed1b From 1e739730c5b9ea80a2f25e9cf6e1025d47e3d8ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Feb 2017 14:46:49 +0100 Subject: block: optionally merge discontiguous discard bios into a single request Add a new merge strategy that merges discard bios into a request until the maximum number of discard ranges (or the maximum discard size) is reached from the plug merging code. I/O scheduler merging is not wired up yet but might also be useful, although not for fast devices like NVMe which are the only user for now. Note that for now we don't support limiting the size of each discard range, but if needed that can be added later. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 27 +++++++++++++++++++++++++++ block/blk-merge.c | 5 ++++- block/blk-mq.c | 3 +++ block/blk-settings.c | 20 ++++++++++++++++++++ block/blk-sysfs.c | 12 ++++++++++++ block/blk.h | 2 ++ include/linux/blkdev.h | 26 ++++++++++++++++++++++++++ include/linux/elevator.h | 1 + 8 files changed, 95 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 00e053c704a1..c0e4d41d3d33 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1483,6 +1483,30 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req, return true; } +bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, + struct bio *bio) +{ + unsigned short segments = blk_rq_nr_discard_segments(req); + + if (segments >= queue_max_discard_segments(q)) + goto no_merge; + if (blk_rq_sectors(req) + bio_sectors(bio) > + blk_rq_get_max_sectors(req, blk_rq_pos(req))) + goto no_merge; + + req->biotail->bi_next = bio; + req->biotail = bio; + req->__data_len += bio->bi_iter.bi_size; + req->ioprio = ioprio_best(req->ioprio, bio_prio(bio)); + req->nr_phys_segments = segments + 1; + + blk_account_io_start(req, false); + return true; +no_merge: + req_set_nomerge(q, req); + return false; +} + /** * blk_attempt_plug_merge - try to merge with %current's plugged list * @q: request_queue new bio is being queued at @@ -1547,6 +1571,9 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, case ELEVATOR_FRONT_MERGE: merged = bio_attempt_front_merge(q, rq, bio); break; + case ELEVATOR_DISCARD_MERGE: + merged = bio_attempt_discard_merge(q, rq, bio); + break; default: break; } diff --git a/block/blk-merge.c b/block/blk-merge.c index 6cbd90ad5f90..2afa262425d1 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -803,7 +803,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { - if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) + if (req_op(rq) == REQ_OP_DISCARD && + queue_max_discard_segments(rq->q) > 1) + return ELEVATOR_DISCARD_MERGE; + else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector) return ELEVATOR_FRONT_MERGE; diff --git a/block/blk-mq.c b/block/blk-mq.c index dd9722df4afe..7412191aee57 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -780,6 +780,9 @@ static bool blk_mq_attempt_merge(struct request_queue *q, if (blk_mq_sched_allow_merge(q, rq, bio)) merged = bio_attempt_front_merge(q, rq, bio); break; + case ELEVATOR_DISCARD_MERGE: + merged = bio_attempt_discard_merge(q, rq, bio); + break; default: continue; } diff --git a/block/blk-settings.c b/block/blk-settings.c index 6eb19bcbf3cb..1e7174ffc9d4 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -88,6 +88,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy); void blk_set_default_limits(struct queue_limits *lim) { lim->max_segments = BLK_MAX_SEGMENTS; + lim->max_discard_segments = 1; lim->max_integrity_segments = 0; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->virt_boundary_mask = 0; @@ -128,6 +129,7 @@ void blk_set_stacking_limits(struct queue_limits *lim) /* Inherit limits from component devices */ lim->discard_zeroes_data = 1; lim->max_segments = USHRT_MAX; + lim->max_discard_segments = 1; lim->max_hw_sectors = UINT_MAX; lim->max_segment_size = UINT_MAX; lim->max_sectors = UINT_MAX; @@ -336,6 +338,22 @@ void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments } EXPORT_SYMBOL(blk_queue_max_segments); +/** + * blk_queue_max_discard_segments - set max segments for discard requests + * @q: the request queue for the device + * @max_segments: max number of segments + * + * Description: + * Enables a low level driver to set an upper limit on the number of + * segments in a discard request. + **/ +void blk_queue_max_discard_segments(struct request_queue *q, + unsigned short max_segments) +{ + q->limits.max_discard_segments = max_segments; +} +EXPORT_SYMBOL_GPL(blk_queue_max_discard_segments); + /** * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg * @q: the request queue for the device @@ -553,6 +571,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, b->virt_boundary_mask); t->max_segments = min_not_zero(t->max_segments, b->max_segments); + t->max_discard_segments = min_not_zero(t->max_discard_segments, + b->max_discard_segments); t->max_integrity_segments = min_not_zero(t->max_integrity_segments, b->max_integrity_segments); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 48032c4759a7..070d81bae1d5 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -121,6 +121,12 @@ static ssize_t queue_max_segments_show(struct request_queue *q, char *page) return queue_var_show(queue_max_segments(q), (page)); } +static ssize_t queue_max_discard_segments_show(struct request_queue *q, + char *page) +{ + return queue_var_show(queue_max_discard_segments(q), (page)); +} + static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) { return queue_var_show(q->limits.max_integrity_segments, (page)); @@ -545,6 +551,11 @@ static struct queue_sysfs_entry queue_max_segments_entry = { .show = queue_max_segments_show, }; +static struct queue_sysfs_entry queue_max_discard_segments_entry = { + .attr = {.name = "max_discard_segments", .mode = S_IRUGO }, + .show = queue_max_discard_segments_show, +}; + static struct queue_sysfs_entry queue_max_integrity_segments_entry = { .attr = {.name = "max_integrity_segments", .mode = S_IRUGO }, .show = queue_max_integrity_segments_show, @@ -697,6 +708,7 @@ static struct attribute *default_attrs[] = { &queue_max_hw_sectors_entry.attr, &queue_max_sectors_entry.attr, &queue_max_segments_entry.attr, + &queue_max_discard_segments_entry.attr, &queue_max_integrity_segments_entry.attr, &queue_max_segment_size_entry.attr, &queue_iosched_entry.attr, diff --git a/block/blk.h b/block/blk.h index ae82f2ac4019..d1ea4bd9b9a3 100644 --- a/block/blk.h +++ b/block/blk.h @@ -100,6 +100,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req, struct bio *bio); bool bio_attempt_back_merge(struct request_queue *q, struct request *req, struct bio *bio); +bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, + struct bio *bio); bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int *request_count, struct request **same_queue_rq); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e0bac14347e6..aecca0e7d9ca 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -331,6 +331,7 @@ struct queue_limits { unsigned short logical_block_size; unsigned short max_segments; unsigned short max_integrity_segments; + unsigned short max_discard_segments; unsigned char misaligned; unsigned char discard_misaligned; @@ -1146,6 +1147,8 @@ extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); +extern void blk_queue_max_discard_segments(struct request_queue *, + unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1189,6 +1192,15 @@ extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); +/* + * Number of physical segments as sent to the device. + * + * Normally this is the number of discontiguous data segments sent by the + * submitter. But for data-less command like discard we might have no + * actual data segments submitted, but the driver might have to add it's + * own special payload. In that case we still return 1 here so that this + * special payload will be mapped. + */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) @@ -1196,6 +1208,15 @@ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) return rq->nr_phys_segments; } +/* + * Number of discard segments (or ranges) the driver needs to fill in. + * Each discard bio merged into a request is counted as one segment. + */ +static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) +{ + return max_t(unsigned short, rq->nr_phys_segments, 1); +} + extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); @@ -1384,6 +1405,11 @@ static inline unsigned short queue_max_segments(struct request_queue *q) return q->limits.max_segments; } +static inline unsigned short queue_max_discard_segments(struct request_queue *q) +{ + return q->limits.max_discard_segments; +} + static inline unsigned int queue_max_segment_size(struct request_queue *q) { return q->limits.max_segment_size; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index b38b4e651ea6..8265b6330cc2 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -16,6 +16,7 @@ enum elv_merge { ELEVATOR_NO_MERGE = 0, ELEVATOR_FRONT_MERGE = 1, ELEVATOR_BACK_MERGE = 2, + ELEVATOR_DISCARD_MERGE = 3, }; typedef enum elv_merge (elevator_merge_fn) (struct request_queue *, struct request **, -- cgit v1.2.3-59-g8ed1b From f1ba82616c3368e1ae9e64ef29cf3edc1be0860d Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Tue, 7 Feb 2017 18:24:43 +0100 Subject: blk-mq: pass bio to blk_mq_sched_get_rq_priv bio is used in bfq-mq's get_rq_priv, to get the request group. We could pass directly the group here, but I thought that passing the bio was more general, giving the possibility to get other pieces of information if needed. Signed-off-by: Paolo Valente Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 8 +++++--- block/blk-mq-sched.h | 5 +++-- include/linux/elevator.h | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'block') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 72d0d8361175..97fe904f0a04 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -68,7 +68,9 @@ error: EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data); static void __blk_mq_sched_assign_ioc(struct request_queue *q, - struct request *rq, struct io_context *ioc) + struct request *rq, + struct bio *bio, + struct io_context *ioc) { struct io_cq *icq; @@ -83,7 +85,7 @@ static void __blk_mq_sched_assign_ioc(struct request_queue *q, } rq->elv.icq = icq; - if (!blk_mq_sched_get_rq_priv(q, rq)) { + if (!blk_mq_sched_get_rq_priv(q, rq, bio)) { rq->rq_flags |= RQF_ELVPRIV; get_io_context(icq->ioc); return; @@ -99,7 +101,7 @@ static void blk_mq_sched_assign_ioc(struct request_queue *q, ioc = rq_ioc(bio); if (ioc) - __blk_mq_sched_assign_ioc(q, rq, ioc); + __blk_mq_sched_assign_ioc(q, rq, bio, ioc); } struct request *blk_mq_sched_get_request(struct request_queue *q, diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 5954859c8670..7b5f3b95c78e 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -49,12 +49,13 @@ blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio) } static inline int blk_mq_sched_get_rq_priv(struct request_queue *q, - struct request *rq) + struct request *rq, + struct bio *bio) { struct elevator_queue *e = q->elevator; if (e && e->type->ops.mq.get_rq_priv) - return e->type->ops.mq.get_rq_priv(q, rq); + return e->type->ops.mq.get_rq_priv(q, rq, bio); return 0; } diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 8265b6330cc2..aebecc4ed088 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -109,7 +109,7 @@ struct elevator_mq_ops { void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); struct request *(*next_request)(struct request_queue *, struct request *); - int (*get_rq_priv)(struct request_queue *, struct request *); + int (*get_rq_priv)(struct request_queue *, struct request *, struct bio *); void (*put_rq_priv)(struct request_queue *, struct request *); void (*init_icq)(struct io_cq *); void (*exit_icq)(struct io_cq *); -- cgit v1.2.3-59-g8ed1b From f6f94300cda0f85180a0dd8838d1cc855661e239 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 10 Feb 2017 13:03:33 -0500 Subject: block: set make_request_fn manually in blk_mq_update_nr_hw_queues Calling blk_queue_make_request resets a bunch of settings on the request_queue, but all we really want is to update the make_request_fn, so do this directly so we don't lose things like the logical and physical block sizes. Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- block/blk-mq.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index 7412191aee57..ade89197a4f1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2629,10 +2629,14 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); + /* + * Manually set the make_request_fn as blk_queue_make_request + * resets a lot of the queue settings. + */ if (q->nr_hw_queues > 1) - blk_queue_make_request(q, blk_mq_make_request); + q->make_request_fn = blk_mq_make_request; else - blk_queue_make_request(q, blk_sq_make_request); + q->make_request_fn = blk_sq_make_request; blk_mq_queue_reinit(q, cpu_online_mask); } -- cgit v1.2.3-59-g8ed1b From 3d492c2e0146ccaad08c7cbe16e2e229328b5e79 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 10 Feb 2017 10:32:34 -0800 Subject: blk-mq-sched: don't hold queue_lock when calling exit_icq None of the other blk-mq elevator hooks are called with this lock held. Additionally, it can lead to circular locking dependencies between queue_lock and the private scheduler lock. Reported-by: Paolo Valente Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-ioc.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'block') diff --git a/block/blk-ioc.c b/block/blk-ioc.c index fe186a9eade9..b12f9c87b4c3 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -35,7 +35,10 @@ static void icq_free_icq_rcu(struct rcu_head *head) kmem_cache_free(icq->__rcu_icq_cache, icq); } -/* Exit an icq. Called with both ioc and q locked. */ +/* + * Exit an icq. Called with both ioc and q locked for sq, only ioc locked for + * mq. + */ static void ioc_exit_icq(struct io_cq *icq) { struct elevator_type *et = icq->q->elevator->type; @@ -166,6 +169,7 @@ EXPORT_SYMBOL(put_io_context); */ void put_io_context_active(struct io_context *ioc) { + struct elevator_type *et; unsigned long flags; struct io_cq *icq; @@ -184,13 +188,19 @@ retry: hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) { if (icq->flags & ICQ_EXITED) continue; - if (spin_trylock(icq->q->queue_lock)) { + + et = icq->q->elevator->type; + if (et->uses_mq) { ioc_exit_icq(icq); - spin_unlock(icq->q->queue_lock); } else { - spin_unlock_irqrestore(&ioc->lock, flags); - cpu_relax(); - goto retry; + if (spin_trylock(icq->q->queue_lock)) { + ioc_exit_icq(icq); + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); + cpu_relax(); + goto retry; + } } } spin_unlock_irqrestore(&ioc->lock, flags); -- cgit v1.2.3-59-g8ed1b From b410aff2bd9f101bc096069612391aecce204cd1 Mon Sep 17 00:00:00 2001 From: Tahsin Erdogan Date: Tue, 14 Feb 2017 19:27:38 -0800 Subject: block: do not allow updates through sysfs until registration completes When a new disk shows up, sysfs queue directory is created before elevator is registered. This allows a user to attempt a scheduler switch even though the initial registration hasn't completed yet. In one scenario, blk_register_queue() calls elv_register_queue() and right before cfq_registered_queue() is called, another process executes elevator_switch() and replaces q->elevator with deadline scheduler. When cfq_registered_queue() executes it interprets e->elevator_data as struct cfq_data even though it is actually struct deadline_data. Grab q->sysfs_lock in blk_register_queue() to synchronize with sysfs callers. Signed-off-by: Tahsin Erdogan Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'block') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 070d81bae1d5..002af836aa87 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -902,17 +902,20 @@ int blk_register_queue(struct gendisk *disk) if (ret) return ret; + if (q->mq_ops) + blk_mq_register_dev(dev, q); + + /* Prevent changes through sysfs until registration is completed. */ + mutex_lock(&q->sysfs_lock); + ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue"); if (ret < 0) { blk_trace_remove_sysfs(dev); - return ret; + goto unlock; } kobject_uevent(&q->kobj, KOBJ_ADD); - if (q->mq_ops) - blk_mq_register_dev(dev, q); - blk_wb_init(q); if (q->request_fn || (q->mq_ops && q->elevator)) { @@ -922,11 +925,13 @@ int blk_register_queue(struct gendisk *disk) kobject_del(&q->kobj); blk_trace_remove_sysfs(dev); kobject_put(&dev->kobj); - return ret; + goto unlock; } } - - return 0; + ret = 0; +unlock: + mutex_unlock(&q->sysfs_lock); + return ret; } void blk_unregister_queue(struct gendisk *disk) -- cgit v1.2.3-59-g8ed1b From 2aa0f21d5491976729087104553b7bdaef047b9d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Feb 2017 11:35:35 -0700 Subject: blk-mq: have blk_mq_dispatch_rq_list() return if we queued IO or not Currently we're almost there, but if we dispatch nothing, then we still return success. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-mq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index ade89197a4f1..6baa0c9fc06d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1005,7 +1005,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list) blk_mq_run_hw_queue(hctx, true); } - return ret != BLK_MQ_RQ_QUEUE_BUSY; + return queued != 0; } static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) -- cgit v1.2.3-59-g8ed1b From c7a571b45055dba740156013fef4a7fdbe3262d9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Feb 2017 11:37:14 -0700 Subject: blk-mq-sched: don't add flushes to the head of requeue queue If we are currently out of driver tags, we don't want to add a new flush (without a tag) to the head of the requeue list. We want to add it to the back, behind the others that are potentially also waiting for a tag. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-mq-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 97fe904f0a04..4ee7cb043812 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -351,7 +351,7 @@ static void blk_mq_sched_insert_flush(struct blk_mq_hw_ctx *hctx, blk_insert_flush(rq); blk_mq_run_hw_queue(hctx, true); } else - blk_mq_add_to_requeue_list(rq, true, true); + blk_mq_add_to_requeue_list(rq, false, true); } void blk_mq_sched_insert_request(struct request *rq, bool at_head, -- cgit v1.2.3-59-g8ed1b From 0c2a6fe4dc3e8c24bc67cd5d0a36092834027cf0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Feb 2017 11:38:36 -0700 Subject: blk-mq: don't special case flush inserts for blk-mq-sched The current request insertion machinery works just fine for directly inserting flushes, so no need to special case this anymore. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-mq.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index 6baa0c9fc06d..ee8c6f9f1d4d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1434,12 +1434,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) cookie = request_to_qc_t(data.hctx, rq); if (unlikely(is_flush_fua)) { - blk_mq_put_ctx(data.ctx); + if (q->elevator) + goto elv_insert; blk_mq_bio_to_request(rq, bio); - blk_mq_get_driver_tag(rq, NULL, true); blk_insert_flush(rq); - blk_mq_run_hw_queue(data.hctx, true); - goto done; + goto run_queue; } plug = current->plug; @@ -1489,6 +1488,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) } if (q->elevator) { +elv_insert: blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); blk_mq_sched_insert_request(rq, false, true, @@ -1502,6 +1502,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) * latter allows for merging opportunities and more efficient * dispatching. */ +run_queue: blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua); } blk_mq_put_ctx(data.ctx); @@ -1557,12 +1558,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) cookie = request_to_qc_t(data.hctx, rq); if (unlikely(is_flush_fua)) { - blk_mq_put_ctx(data.ctx); + if (q->elevator) + goto elv_insert; blk_mq_bio_to_request(rq, bio); - blk_mq_get_driver_tag(rq, NULL, true); blk_insert_flush(rq); - blk_mq_run_hw_queue(data.hctx, true); - goto done; + goto run_queue; } /* @@ -1600,6 +1600,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) } if (q->elevator) { +elv_insert: blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); blk_mq_sched_insert_request(rq, false, true, @@ -1613,6 +1614,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) * latter allows for merging opportunities and more efficient * dispatching. */ +run_queue: blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua); } -- cgit v1.2.3-59-g8ed1b From 64765a75ef258c802f795558d00a5a1864c531fc Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Feb 2017 11:39:26 -0700 Subject: blk-mq-sched: ask scheduler for work, if we failed dispatching leftovers Usually we don't ask the scheduler for work, if we already have leftovers on the dispatch list. This is done to leave work on the scheduler side for as long as possible, for proper merging. But if we do have work leftover but didn't dispatch anything, then we should ask the scheduler since we could potentially issue requests from that. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-mq-sched.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'block') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 4ee7cb043812..9e8d6795a8c1 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -175,6 +175,8 @@ void blk_mq_sched_put_request(struct request *rq) void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct elevator_queue *e = hctx->queue->elevator; + const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request; + bool did_work = false; LIST_HEAD(rq_list); if (unlikely(blk_mq_hctx_stopped(hctx))) @@ -204,11 +206,18 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) */ if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart(hctx); - blk_mq_dispatch_rq_list(hctx, &rq_list); - } else if (!e || !e->type->ops.mq.dispatch_request) { + did_work = blk_mq_dispatch_rq_list(hctx, &rq_list); + } else if (!has_sched_dispatch) { blk_mq_flush_busy_ctxs(hctx, &rq_list); blk_mq_dispatch_rq_list(hctx, &rq_list); - } else { + } + + /* + * We want to dispatch from the scheduler if we had no work left + * on the dispatch list, OR if we did have work but weren't able + * to make progress. + */ + if (!did_work && has_sched_dispatch) { do { struct request *rq; -- cgit v1.2.3-59-g8ed1b From 7520872c0cf4d3df6d74242c6edfb9e70a47df4d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Feb 2017 11:40:44 -0700 Subject: block: don't defer flushes on blk-mq + scheduling For blk-mq with scheduling, we can potentially end up with ALL driver tags assigned and sitting on the flush queues. If we defer because of an inlfight data request, then we can deadlock if that data request doesn't already have a tag assigned. This fixes a deadlock with running the xfs/297 xfstest, where thousands of syncs can cause the drive queue to stall. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-flush.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-flush.c b/block/blk-flush.c index 968162579234..0d5a9c1da1fc 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -297,8 +297,14 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq) if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending)) return false; - /* C2 and C3 */ + /* C2 and C3 + * + * For blk-mq + scheduling, we can risk having all driver tags + * assigned to empty flushes, and we deadlock if we are expecting + * other requests to make progress. Don't defer for that case. + */ if (!list_empty(&fq->flush_data_in_flight) && + !(q->mq_ops && q->elevator) && time_before(jiffies, fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) return false; -- cgit v1.2.3-59-g8ed1b