diff options
Diffstat (limited to 'block')
-rw-r--r-- | block/Kconfig | 5 | ||||
-rw-r--r-- | block/Makefile | 1 | ||||
-rw-r--r-- | block/bfq-iosched.c | 1 | ||||
-rw-r--r-- | block/bio.c | 2 | ||||
-rw-r--r-- | block/blk-core.c | 5 | ||||
-rw-r--r-- | block/blk-mq-rdma.c | 52 | ||||
-rw-r--r-- | block/blk-softirq.c | 2 | ||||
-rw-r--r-- | block/blk.h | 1 | ||||
-rw-r--r-- | block/bsg-lib.c | 7 | ||||
-rw-r--r-- | block/bsg.c | 7 | ||||
-rw-r--r-- | block/cfq-iosched.c | 81 | ||||
-rw-r--r-- | block/genhd.c | 18 | ||||
-rw-r--r-- | block/mq-deadline.c | 1 |
13 files changed, 110 insertions, 73 deletions
diff --git a/block/Kconfig b/block/Kconfig index 89cd28f8d051..3ab42bbb06d5 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -206,4 +206,9 @@ config BLK_MQ_VIRTIO depends on BLOCK && VIRTIO default y +config BLK_MQ_RDMA + bool + depends on BLOCK && INFINIBAND + default y + source block/Kconfig.iosched diff --git a/block/Makefile b/block/Makefile index 2b281cf258a0..9396ebc85d24 100644 --- a/block/Makefile +++ b/block/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o obj-$(CONFIG_BLK_MQ_VIRTIO) += blk-mq-virtio.o +obj-$(CONFIG_BLK_MQ_RDMA) += blk-mq-rdma.o obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o obj-$(CONFIG_BLK_WBT) += blk-wbt.o obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index fd09d4d4ada7..a4783da90ba8 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5036,6 +5036,7 @@ static struct elevator_type iosched_bfq_mq = { .elevator_name = "bfq", .elevator_owner = THIS_MODULE, }; +MODULE_ALIAS("bfq-iosched"); static int __init bfq_init(void) { diff --git a/block/bio.c b/block/bio.c index 6745759028da..b38e962fa83e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -2089,7 +2089,7 @@ void bio_clone_blkcg_association(struct bio *dst, struct bio *src) if (src->bi_css) WARN_ON(bio_associate_blkcg(dst, src->bi_css)); } - +EXPORT_SYMBOL_GPL(bio_clone_blkcg_association); #endif /* CONFIG_BLK_CGROUP */ static void __init biovec_init_slabs(void) diff --git a/block/blk-core.c b/block/blk-core.c index fc1af9097dff..d709c0e3a2ac 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2615,7 +2615,7 @@ struct request *blk_peek_request(struct request_queue *q) } EXPORT_SYMBOL(blk_peek_request); -void blk_dequeue_request(struct request *rq) +static void blk_dequeue_request(struct request *rq) { struct request_queue *q = rq->q; @@ -2642,9 +2642,6 @@ void blk_dequeue_request(struct request *rq) * Description: * Dequeue @req and start timeout timer on it. This hands off the * request to the driver. - * - * Block internal functions which don't want to start timer should - * call blk_dequeue_request(). */ void blk_start_request(struct request *req) { diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c new file mode 100644 index 000000000000..996167f1de18 --- /dev/null +++ b/block/blk-mq-rdma.c @@ -0,0 +1,52 @@ +/* + * Copyright (c) 2017 Sagi Grimberg. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include <linux/blk-mq.h> +#include <linux/blk-mq-rdma.h> +#include <rdma/ib_verbs.h> + +/** + * blk_mq_rdma_map_queues - provide a default queue mapping for rdma device + * @set: tagset to provide the mapping for + * @dev: rdma device associated with @set. + * @first_vec: first interrupt vectors to use for queues (usually 0) + * + * This function assumes the rdma device @dev has at least as many available + * interrupt vetors as @set has queues. It will then query it's affinity mask + * and built queue mapping that maps a queue to the CPUs that have irq affinity + * for the corresponding vector. + * + * In case either the driver passed a @dev with less vectors than + * @set->nr_hw_queues, or @dev does not provide an affinity mask for a + * vector, we fallback to the naive mapping. + */ +int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set, + struct ib_device *dev, int first_vec) +{ + const struct cpumask *mask; + unsigned int queue, cpu; + + for (queue = 0; queue < set->nr_hw_queues; queue++) { + mask = ib_get_vector_affinity(dev, first_vec + queue); + if (!mask) + goto fallback; + + for_each_cpu(cpu, mask) + set->mq_map[cpu] = queue; + } + + return 0; + +fallback: + return blk_mq_map_queues(set); +} +EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues); diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 87b7df4851bf..07125e7941f4 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -60,7 +60,7 @@ static void trigger_softirq(void *data) static int raise_blk_irq(int cpu, struct request *rq) { if (cpu_online(cpu)) { - struct call_single_data *data = &rq->csd; + call_single_data_t *data = &rq->csd; data->func = trigger_softirq; data->info = rq; diff --git a/block/blk.h b/block/blk.h index fde8b351c166..fcb9775b997d 100644 --- a/block/blk.h +++ b/block/blk.h @@ -64,7 +64,6 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio); void blk_queue_bypass_start(struct request_queue *q); void blk_queue_bypass_end(struct request_queue *q); -void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); void blk_freeze_queue(struct request_queue *q); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index dd56d7460cb9..c82408c7cc3c 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -239,8 +239,9 @@ static void bsg_exit_rq(struct request_queue *q, struct request *req) * @job_fn: bsg job handler * @dd_job_size: size of LLD data needed for each job */ -struct request_queue *bsg_setup_queue(struct device *dev, char *name, - bsg_job_fn *job_fn, int dd_job_size) +struct request_queue *bsg_setup_queue(struct device *dev, const char *name, + bsg_job_fn *job_fn, int dd_job_size, + void (*release)(struct device *)) { struct request_queue *q; int ret; @@ -264,7 +265,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name, blk_queue_softirq_done(q, bsg_softirq_done); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); - ret = bsg_register_queue(q, dev, name, NULL); + ret = bsg_register_queue(q, dev, name, release); if (ret) { printk(KERN_ERR "%s: bsg interface failed to " "initialize - register queue\n", dev->kobj.name); diff --git a/block/bsg.c b/block/bsg.c index 37663b664666..ee1335c68de7 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -932,15 +932,8 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return ret; } - /* - * block device ioctls - */ default: -#if 0 - return ioctl_by_bdev(bd->bdev, cmd, arg); -#else return -ENOTTY; -#endif } } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 9b86e9b352e9..9f342ef1ad42 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -93,13 +93,14 @@ struct cfq_ttime { * move this into the elevator for the rq sorting as well. */ struct cfq_rb_root { - struct rb_root rb; - struct rb_node *left; + struct rb_root_cached rb; + struct rb_node *rb_rightmost; unsigned count; u64 min_vdisktime; struct cfq_ttime ttime; }; -#define CFQ_RB_ROOT (struct cfq_rb_root) { .rb = RB_ROOT, \ +#define CFQ_RB_ROOT (struct cfq_rb_root) { .rb = RB_ROOT_CACHED, \ + .rb_rightmost = NULL, \ .ttime = {.last_end_request = ktime_get_ns(),},} /* @@ -981,10 +982,9 @@ static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime) static void update_min_vdisktime(struct cfq_rb_root *st) { - struct cfq_group *cfqg; + if (!RB_EMPTY_ROOT(&st->rb.rb_root)) { + struct cfq_group *cfqg = rb_entry_cfqg(st->rb.rb_leftmost); - if (st->left) { - cfqg = rb_entry_cfqg(st->left); st->min_vdisktime = max_vdisktime(st->min_vdisktime, cfqg->vdisktime); } @@ -1166,46 +1166,28 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, } } -/* - * The below is leftmost cache rbtree addon - */ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) { /* Service tree is empty */ if (!root->count) return NULL; - if (!root->left) - root->left = rb_first(&root->rb); - - if (root->left) - return rb_entry(root->left, struct cfq_queue, rb_node); - - return NULL; + return rb_entry(rb_first_cached(&root->rb), struct cfq_queue, rb_node); } static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root) { - if (!root->left) - root->left = rb_first(&root->rb); - - if (root->left) - return rb_entry_cfqg(root->left); - - return NULL; + return rb_entry_cfqg(rb_first_cached(&root->rb)); } -static void rb_erase_init(struct rb_node *n, struct rb_root *root) +static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root) { - rb_erase(n, root); + if (root->rb_rightmost == n) + root->rb_rightmost = rb_prev(n); + + rb_erase_cached(n, &root->rb); RB_CLEAR_NODE(n); -} -static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root) -{ - if (root->left == n) - root->left = NULL; - rb_erase_init(n, &root->rb); --root->count; } @@ -1255,29 +1237,30 @@ cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg) static void __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) { - struct rb_node **node = &st->rb.rb_node; + struct rb_node **node = &st->rb.rb_root.rb_node; struct rb_node *parent = NULL; struct cfq_group *__cfqg; s64 key = cfqg_key(st, cfqg); - int left = 1; + bool leftmost = true, rightmost = true; while (*node != NULL) { parent = *node; __cfqg = rb_entry_cfqg(parent); - if (key < cfqg_key(st, __cfqg)) + if (key < cfqg_key(st, __cfqg)) { node = &parent->rb_left; - else { + rightmost = false; + } else { node = &parent->rb_right; - left = 0; + leftmost = false; } } - if (left) - st->left = &cfqg->rb_node; + if (rightmost) + st->rb_rightmost = &cfqg->rb_node; rb_link_node(&cfqg->rb_node, parent, node); - rb_insert_color(&cfqg->rb_node, &st->rb); + rb_insert_color_cached(&cfqg->rb_node, &st->rb, leftmost); } /* @@ -1378,7 +1361,7 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg) * so that groups get lesser vtime based on their weights, so that * if group does not loose all if it was not continuously backlogged. */ - n = rb_last(&st->rb); + n = st->rb_rightmost; if (n) { __cfqg = rb_entry_cfqg(n); cfqg->vdisktime = __cfqg->vdisktime + @@ -2220,14 +2203,14 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_queue *__cfqq; u64 rb_key; struct cfq_rb_root *st; - int left; + bool leftmost = true; int new_cfqq = 1; u64 now = ktime_get_ns(); st = st_for(cfqq->cfqg, cfqq_class(cfqq), cfqq_type(cfqq)); if (cfq_class_idle(cfqq)) { rb_key = CFQ_IDLE_DELAY; - parent = rb_last(&st->rb); + parent = st->rb_rightmost; if (parent && parent != &cfqq->rb_node) { __cfqq = rb_entry(parent, struct cfq_queue, rb_node); rb_key += __cfqq->rb_key; @@ -2261,10 +2244,9 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqq->service_tree = NULL; } - left = 1; parent = NULL; cfqq->service_tree = st; - p = &st->rb.rb_node; + p = &st->rb.rb_root.rb_node; while (*p) { parent = *p; __cfqq = rb_entry(parent, struct cfq_queue, rb_node); @@ -2276,16 +2258,13 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, p = &parent->rb_left; else { p = &parent->rb_right; - left = 0; + leftmost = false; } } - if (left) - st->left = &cfqq->rb_node; - cfqq->rb_key = rb_key; rb_link_node(&cfqq->rb_node, parent, p); - rb_insert_color(&cfqq->rb_node, &st->rb); + rb_insert_color_cached(&cfqq->rb_node, &st->rb, leftmost); st->count++; if (add_front || !new_cfqq) return; @@ -2732,7 +2711,7 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) /* There is nothing to dispatch */ if (!st) return NULL; - if (RB_EMPTY_ROOT(&st->rb)) + if (RB_EMPTY_ROOT(&st->rb.rb_root)) return NULL; return cfq_rb_first(st); } @@ -3219,7 +3198,7 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd) struct cfq_rb_root *st = &cfqd->grp_service_tree; struct cfq_group *cfqg; - if (RB_EMPTY_ROOT(&st->rb)) + if (RB_EMPTY_ROOT(&st->rb.rb_root)) return NULL; cfqg = cfq_rb_first_group(st); update_min_vdisktime(st); diff --git a/block/genhd.c b/block/genhd.c index 713b7d4fe7a1..dd305c65ffb0 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -279,6 +279,7 @@ EXPORT_SYMBOL_GPL(disk_map_sector_rcu); * Can be deleted altogether. Later. * */ +#define BLKDEV_MAJOR_HASH_SIZE 255 static struct blk_major_name { struct blk_major_name *next; int major; @@ -296,12 +297,11 @@ void blkdev_show(struct seq_file *seqf, off_t offset) { struct blk_major_name *dp; - if (offset < BLKDEV_MAJOR_HASH_SIZE) { - mutex_lock(&block_class_lock); - for (dp = major_names[offset]; dp; dp = dp->next) + mutex_lock(&block_class_lock); + for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next) + if (dp->major == offset) seq_printf(seqf, "%3d %s\n", dp->major, dp->name); - mutex_unlock(&block_class_lock); - } + mutex_unlock(&block_class_lock); } #endif /* CONFIG_PROC_FS */ @@ -346,6 +346,14 @@ int register_blkdev(unsigned int major, const char *name) ret = major; } + if (major >= BLKDEV_MAJOR_MAX) { + pr_err("register_blkdev: major requested (%d) is greater than the maximum (%d) for %s\n", + major, BLKDEV_MAJOR_MAX, name); + + ret = -EINVAL; + goto out; + } + p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL); if (p == NULL) { ret = -ENOMEM; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index c8dfddc4ba8b..a1cad4331edd 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -659,6 +659,7 @@ static struct elevator_type mq_deadline = { .elevator_name = "mq-deadline", .elevator_owner = THIS_MODULE, }; +MODULE_ALIAS("mq-deadline-iosched"); static int __init deadline_init(void) { |