diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-01 10:39:57 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-01 10:39:57 -0700 |
commit | 694752922b12bd318aa80191bd9d8c3dcfb39055 (patch) | |
tree | 5afe83fd99100bea546dd5a1c1f778c58f41e5c0 /block/blk-sysfs.c | |
parent | Linux 4.11 (diff) | |
parent | block: hide badblocks attribute by default (diff) | |
download | linux-dev-694752922b12bd318aa80191bd9d8c3dcfb39055.tar.xz linux-dev-694752922b12bd318aa80191bd9d8c3dcfb39055.zip |
Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe:
- Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
was initially a fork of CFQ, but subsequently changed to implement
fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
to be used on desktop type single drives, providing good fairness.
From Paolo.
- Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
using a scalable token based algorithm that throttles IO based on
live completion IO stats, similary to blk-wbt. From Omar.
- A series from Jan, moving users to separately allocated backing
devices. This continues the work of separating backing device life
times, solving various problems with hot removal.
- A series of updates for lightnvm, mostly from Javier. Includes a
'pblk' target that exposes an open channel SSD as a physical block
device.
- A series of fixes and improvements for nbd from Josef.
- A series from Omar, removing queue sharing between devices on mostly
legacy drivers. This helps us clean up other bits, if we know that a
queue only has a single device backing. This has been overdue for
more than a decade.
- Fixes for the blk-stats, and improvements to unify the stats and user
windows. This both improves blk-wbt, and enables other users to
register a need to receive IO stats for a device. From Omar.
- blk-throttle improvements from Shaohua. This provides a scalable
framework for implementing scalable priotization - particularly for
blk-mq, but applicable to any type of block device. The interface is
marked experimental for now.
- Bucketized IO stats for IO polling from Stephen Bates. This improves
efficiency of polled workloads in the presence of mixed block size
IO.
- A few fixes for opal, from Scott.
- A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
From a variety of folks, mostly Sagi and James Smart.
- A series from Bart, improving our exposed info and capabilities from
the blk-mq debugfs support.
- A series from Christoph, cleaning up how handle WRITE_ZEROES.
- A series from Christoph, cleaning up the block layer handling of how
we track errors in a request. On top of being a nice cleanup, it also
shrinks the size of struct request a bit.
- Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
never used by platforms, and the latter has outlived it's usefulness.
- Various little bug fixes and cleanups from a wide variety of folks.
* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
block: hide badblocks attribute by default
blk-mq: unify hctx delay_work and run_work
block: add kblock_mod_delayed_work_on()
blk-mq: unify hctx delayed_run_work and run_work
nbd: fix use after free on module unload
MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
blk-mq-sched: alloate reserved tags out of normal pool
mtip32xx: use runtime tag to initialize command header
scsi: Implement blk_mq_ops.show_rq()
blk-mq: Add blk_mq_ops.show_rq()
blk-mq: Show operation, cmd_flags and rq_flags names
blk-mq: Make blk_flags_show() callers append a newline character
blk-mq: Move the "state" debugfs attribute one level down
blk-mq: Unregister debugfs attributes earlier
blk-mq: Only unregister hctxs for which registration succeeded
blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
blk-mq: Let blk_mq_debugfs_register() look up the queue name
blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
ide-pm: always pass 0 error to __blk_end_request_all
..
Diffstat (limited to 'block/blk-sysfs.c')
-rw-r--r-- | block/blk-sysfs.c | 82 |
1 files changed, 33 insertions, 49 deletions
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 37f0b3ad635e..3f37813ccbaf 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -208,7 +208,7 @@ static ssize_t queue_discard_max_store(struct request_queue *q, static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page) { - return queue_var_show(queue_discard_zeroes_data(q), page); + return queue_var_show(0, page); } static ssize_t queue_write_same_max_show(struct request_queue *q, char *page) @@ -503,26 +503,6 @@ static ssize_t queue_dax_show(struct request_queue *q, char *page) return queue_var_show(blk_queue_dax(q), page); } -static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre) -{ - return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n", - pre, (long long) stat->nr_samples, - (long long) stat->mean, (long long) stat->min, - (long long) stat->max); -} - -static ssize_t queue_stats_show(struct request_queue *q, char *page) -{ - struct blk_rq_stat stat[2]; - ssize_t ret; - - blk_queue_stat_get(q, stat); - - ret = print_stat(page, &stat[BLK_STAT_READ], "read :"); - ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:"); - return ret; -} - static struct queue_sysfs_entry queue_requests_entry = { .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR }, .show = queue_requests_show, @@ -691,17 +671,20 @@ static struct queue_sysfs_entry queue_dax_entry = { .show = queue_dax_show, }; -static struct queue_sysfs_entry queue_stats_entry = { - .attr = {.name = "stats", .mode = S_IRUGO }, - .show = queue_stats_show, -}; - static struct queue_sysfs_entry queue_wb_lat_entry = { .attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR }, .show = queue_wb_lat_show, .store = queue_wb_lat_store, }; +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW +static struct queue_sysfs_entry throtl_sample_time_entry = { + .attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR }, + .show = blk_throtl_sample_time_show, + .store = blk_throtl_sample_time_store, +}; +#endif + static struct attribute *default_attrs[] = { &queue_requests_entry.attr, &queue_ra_entry.attr, @@ -733,9 +716,11 @@ static struct attribute *default_attrs[] = { &queue_poll_entry.attr, &queue_wc_entry.attr, &queue_dax_entry.attr, - &queue_stats_entry.attr, &queue_wb_lat_entry.attr, &queue_poll_delay_entry.attr, +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + &throtl_sample_time_entry.attr, +#endif NULL, }; @@ -810,7 +795,9 @@ static void blk_release_queue(struct kobject *kobj) struct request_queue *q = container_of(kobj, struct request_queue, kobj); - wbt_exit(q); + if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags)) + blk_stat_remove_callback(q, q->poll_cb); + blk_stat_free_callback(q->poll_cb); bdi_put(q->backing_dev_info); blkcg_exit_queue(q); @@ -819,6 +806,8 @@ static void blk_release_queue(struct kobject *kobj) elevator_exit(q, q->elevator); } + blk_free_queue_stats(q->stats); + blk_exit_rl(&q->root_rl); if (q->queue_tags) @@ -855,23 +844,6 @@ struct kobj_type blk_queue_ktype = { .release = blk_release_queue, }; -static void blk_wb_init(struct request_queue *q) -{ -#ifndef CONFIG_BLK_WBT_MQ - if (q->mq_ops) - return; -#endif -#ifndef CONFIG_BLK_WBT_SQ - if (q->request_fn) - return; -#endif - - /* - * If this fails, we don't get throttling - */ - wbt_init(q); -} - int blk_register_queue(struct gendisk *disk) { int ret; @@ -881,6 +853,11 @@ int blk_register_queue(struct gendisk *disk) if (WARN_ON(!q)) return -ENXIO; + WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags), + "%s is registering an already registered queue\n", + kobject_name(&dev->kobj)); + queue_flag_set_unlocked(QUEUE_FLAG_REGISTERED, q); + /* * SCSI probing may synchronously create and destroy a lot of * request_queues for non-existent devices. Shutting down a fully @@ -900,9 +877,6 @@ 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); @@ -912,9 +886,14 @@ int blk_register_queue(struct gendisk *disk) goto unlock; } + if (q->mq_ops) + __blk_mq_register_dev(dev, q); + kobject_uevent(&q->kobj, KOBJ_ADD); - blk_wb_init(q); + wbt_enable_default(q); + + blk_throtl_register_queue(q); if (q->request_fn || (q->mq_ops && q->elevator)) { ret = elv_register_queue(q); @@ -939,6 +918,11 @@ void blk_unregister_queue(struct gendisk *disk) if (WARN_ON(!q)) return; + queue_flag_clear_unlocked(QUEUE_FLAG_REGISTERED, q); + + wbt_exit(q); + + if (q->mq_ops) blk_mq_unregister_dev(disk_to_dev(disk), q); |