diff options
author | Jiri Kosina <jkosina@suse.cz> | 2010-06-16 18:08:13 +0200 |
---|---|---|
committer | Jiri Kosina <jkosina@suse.cz> | 2010-06-16 18:08:13 +0200 |
commit | f1bbbb6912662b9f6070c5bfc4ca9eb1f06a9d5b (patch) | |
tree | c2c130a74be25b0b2dff992e1a195e2728bdaadd /block | |
parent | fd0961ff67727482bb20ca7e8ea97b83e9de2ddb (diff) | |
parent | 7e27d6e778cd87b6f2415515d7127eba53fe5d02 (diff) |
Merge branch 'master' into for-next
Diffstat (limited to 'block')
-rw-r--r-- | block/Kconfig | 23 | ||||
-rw-r--r-- | block/Kconfig.iosched | 16 | ||||
-rw-r--r-- | block/Makefile | 2 | ||||
-rw-r--r-- | block/blk-barrier.c | 147 | ||||
-rw-r--r-- | block/blk-cgroup.c | 791 | ||||
-rw-r--r-- | block/blk-cgroup.h | 178 | ||||
-rw-r--r-- | block/blk-core.c | 49 | ||||
-rw-r--r-- | block/blk-lib.c | 233 | ||||
-rw-r--r-- | block/cfq-iosched.c | 182 | ||||
-rw-r--r-- | block/elevator.c | 19 | ||||
-rw-r--r-- | block/genhd.c | 2 | ||||
-rw-r--r-- | block/ioctl.c | 2 |
12 files changed, 1349 insertions, 295 deletions
diff --git a/block/Kconfig b/block/Kconfig index f9e89f4d94b..9be0b56eaee 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -77,29 +77,6 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. -config BLK_CGROUP - tristate "Block cgroup support" - depends on CGROUPS - depends on CFQ_GROUP_IOSCHED - default n - ---help--- - Generic block IO controller cgroup interface. This is the common - cgroup interface which should be used by various IO controlling - policies. - - Currently, CFQ IO scheduler uses it to recognize task groups and - control disk bandwidth allocation (proportional time slice allocation) - to such task groups. - -config DEBUG_BLK_CGROUP - bool - depends on BLK_CGROUP - default n - ---help--- - Enable some debugging help. Currently it stores the cgroup path - in the blk group which can be used by cfq for tracing various - group related activity. - endif # BLOCK config BLOCK_COMPAT diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index fc71cf071fb..3199b76f795 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -23,7 +23,8 @@ config IOSCHED_DEADLINE config IOSCHED_CFQ tristate "CFQ I/O scheduler" - select BLK_CGROUP if CFQ_GROUP_IOSCHED + # If BLK_CGROUP is a module, CFQ has to be built as module. + depends on (BLK_CGROUP=m && m) || !BLK_CGROUP || BLK_CGROUP=y default y ---help--- The CFQ I/O scheduler tries to distribute bandwidth equally @@ -33,22 +34,15 @@ config IOSCHED_CFQ This is the default I/O scheduler. + Note: If BLK_CGROUP=m, then CFQ can be built only as module. + config CFQ_GROUP_IOSCHED bool "CFQ Group Scheduling support" - depends on IOSCHED_CFQ && CGROUPS + depends on IOSCHED_CFQ && BLK_CGROUP default n ---help--- Enable group IO scheduling in CFQ. -config DEBUG_CFQ_IOSCHED - bool "Debug CFQ Scheduling" - depends on CFQ_GROUP_IOSCHED - select DEBUG_BLK_CGROUP - default n - ---help--- - Enable CFQ IO scheduling debugging in CFQ. Currently it makes - blktrace output more verbose. - choice prompt "Default I/O scheduler" default DEFAULT_CFQ diff --git a/block/Makefile b/block/Makefile index cb2d515ebd6..0bb499a739c 100644 --- a/block/Makefile +++ b/block/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \ blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \ - blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o + blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 6d88544b677..0d710c9d403 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -286,26 +286,31 @@ static void bio_end_empty_barrier(struct bio *bio, int err) set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); clear_bit(BIO_UPTODATE, &bio->bi_flags); } - - complete(bio->bi_private); + if (bio->bi_private) + complete(bio->bi_private); + bio_put(bio); } /** * blkdev_issue_flush - queue a flush * @bdev: blockdev to issue flush for + * @gfp_mask: memory allocation flags (for bio_alloc) * @error_sector: error sector + * @flags: BLKDEV_IFL_* flags to control behaviour * * Description: * Issue a flush for the block device in question. Caller can supply * room for storing the error offset in case of a flush error, if they - * wish to. + * wish to. If WAIT flag is not passed then caller may check only what + * request was pushed in some internal queue for later handling. */ -int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) +int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, + sector_t *error_sector, unsigned long flags) { DECLARE_COMPLETION_ONSTACK(wait); struct request_queue *q; struct bio *bio; - int ret; + int ret = 0; if (bdev->bd_disk == NULL) return -ENXIO; @@ -314,23 +319,25 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) if (!q) return -ENXIO; - bio = bio_alloc(GFP_KERNEL, 0); + bio = bio_alloc(gfp_mask, 0); bio->bi_end_io = bio_end_empty_barrier; - bio->bi_private = &wait; bio->bi_bdev = bdev; - submit_bio(WRITE_BARRIER, bio); - - wait_for_completion(&wait); + if (test_bit(BLKDEV_WAIT, &flags)) + bio->bi_private = &wait; - /* - * The driver must store the error location in ->bi_sector, if - * it supports it. For non-stacked drivers, this should be copied - * from blk_rq_pos(rq). - */ - if (error_sector) - *error_sector = bio->bi_sector; + bio_get(bio); + submit_bio(WRITE_BARRIER, bio); + if (test_bit(BLKDEV_WAIT, &flags)) { + wait_for_completion(&wait); + /* + * The driver must store the error location in ->bi_sector, if + * it supports it. For non-stacked drivers, this should be + * copied from blk_rq_pos(rq). + */ + if (error_sector) + *error_sector = bio->bi_sector; + } - ret = 0; if (bio_flagged(bio, BIO_EOPNOTSUPP)) ret = -EOPNOTSUPP; else if (!bio_flagged(bio, BIO_UPTODATE)) @@ -340,107 +347,3 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) return ret; } EXPORT_SYMBOL(blkdev_issue_flush); - -static void blkdev_discard_end_io(struct bio *bio, int err) -{ - if (err) { - if (err == -EOPNOTSUPP) - set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - clear_bit(BIO_UPTODATE, &bio->bi_flags); - } - - if (bio->bi_private) - complete(bio->bi_private); - __free_page(bio_page(bio)); - - bio_put(bio); -} - -/** - * blkdev_issue_discard - queue a discard - * @bdev: blockdev to issue discard for - * @sector: start sector - * @nr_sects: number of sectors to discard - * @gfp_mask: memory allocation flags (for bio_alloc) - * @flags: DISCARD_FL_* flags to control behaviour - * - * Description: - * Issue a discard request for the sectors in question. - */ -int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags) -{ - DECLARE_COMPLETION_ONSTACK(wait); - struct request_queue *q = bdev_get_queue(bdev); - int type = flags & DISCARD_FL_BARRIER ? - DISCARD_BARRIER : DISCARD_NOBARRIER; - struct bio *bio; - struct page *page; - int ret = 0; - - if (!q) - return -ENXIO; - - if (!blk_queue_discard(q)) - return -EOPNOTSUPP; - - while (nr_sects && !ret) { - unsigned int sector_size = q->limits.logical_block_size; - unsigned int max_discard_sectors = - min(q->limits.max_discard_sectors, UINT_MAX >> 9); - - bio = bio_alloc(gfp_mask, 1); - if (!bio) - goto out; - bio->bi_sector = sector; - bio->bi_end_io = blkdev_discard_end_io; - bio->bi_bdev = bdev; - if (flags & DISCARD_FL_WAIT) - bio->bi_private = &wait; - - /* - * Add a zeroed one-sector payload as that's what - * our current implementations need. If we'll ever need - * more the interface will need revisiting. - */ - page = alloc_page(gfp_mask | __GFP_ZERO); - if (!page) - goto out_free_bio; - if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size) - goto out_free_page; - - /* - * And override the bio size - the way discard works we - * touch many more blocks on disk than the actual payload - * length. - */ - if (nr_sects > max_discard_sectors) { - bio->bi_size = max_discard_sectors << 9; - nr_sects -= max_discard_sectors; - sector += max_discard_sectors; - } else { - bio->bi_size = nr_sects << 9; - nr_sects = 0; - } - - bio_get(bio); - submit_bio(type, bio); - - if (flags & DISCARD_FL_WAIT) - wait_for_completion(&wait); - - if (bio_flagged(bio, BIO_EOPNOTSUPP)) - ret = -EOPNOTSUPP; - else if (!bio_flagged(bio, BIO_UPTODATE)) - ret = -EIO; - bio_put(bio); - } - return ret; -out_free_page: - __free_page(page); -out_free_bio: - bio_put(bio); -out: - return -ENOMEM; -} -EXPORT_SYMBOL(blkdev_issue_discard); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 2cc682b860e..a6809645d21 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -15,8 +15,12 @@ #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/err.h> +#include <linux/blkdev.h> #include <linux/slab.h> #include "blk-cgroup.h" +#include <linux/genhd.h> + +#define MAX_KEY_LEN 100 static DEFINE_SPINLOCK(blkio_list_lock); static LIST_HEAD(blkio_list); @@ -49,6 +53,32 @@ struct cgroup_subsys blkio_subsys = { }; EXPORT_SYMBOL_GPL(blkio_subsys); +static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg, + struct blkio_policy_node *pn) +{ + list_add(&pn->node, &blkcg->policy_list); +} + +/* Must be called with blkcg->lock held */ +static inline void blkio_policy_delete_node(struct blkio_policy_node *pn) +{ + list_del(&pn->node); +} + +/* Must be called with blkcg->lock held */ +static struct blkio_policy_node * +blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev) +{ + struct blkio_policy_node *pn; + + list_for_each_entry(pn, &blkcg->policy_list, node) { + if (pn->dev == dev) + return pn; + } + + return NULL; +} + struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id), @@ -56,13 +86,259 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) } EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup); -void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, - unsigned long time, unsigned long sectors) +/* + * Add to the appropriate stat variable depending on the request type. + * This should be called with the blkg->stats_lock held. + */ +static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction, + bool sync) +{ + if (direction) + stat[BLKIO_STAT_WRITE] += add; + else + stat[BLKIO_STAT_READ] += add; + if (sync) + stat[BLKIO_STAT_SYNC] += add; + else + stat[BLKIO_STAT_ASYNC] += add; +} + +/* + * Decrements the appropriate stat variable if non-zero depending on the + * request type. Panics on value being zero. + * This should be called with the blkg->stats_lock held. + */ +static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync) +{ + if (direction) { + BUG_ON(stat[BLKIO_STAT_WRITE] == 0); + stat[BLKIO_STAT_WRITE]--; + } else { + BUG_ON(stat[BLKIO_STAT_READ] == 0); + stat[BLKIO_STAT_READ]--; + } + if (sync) { + BUG_ON(stat[BLKIO_STAT_SYNC] == 0); + stat[BLKIO_STAT_SYNC]--; + } else { + BUG_ON(stat[BLKIO_STAT_ASYNC] == 0); + stat[BLKIO_STAT_ASYNC]--; + } +} + +#ifdef CONFIG_DEBUG_BLK_CGROUP +/* This should be called with the blkg->stats_lock held. */ +static void blkio_set_start_group_wait_time(struct blkio_group *blkg, + struct blkio_group *curr_blkg) +{ + if (blkio_blkg_waiting(&blkg->stats)) + return; + if (blkg == curr_blkg) + return; + blkg->stats.start_group_wait_time = sched_clock(); + blkio_mark_blkg_waiting(&blkg->stats); +} + +/* This should be called with the blkg->stats_lock held. */ +static void blkio_update_group_wait_time(struct blkio_group_stats *stats) +{ + unsigned long long now; + + if (!blkio_blkg_waiting(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_group_wait_time)) + stats->group_wait_time += now - stats->start_group_wait_time; + blkio_clear_blkg_waiting(stats); +} + +/* This should be called with the blkg->stats_lock held. */ +static void blkio_end_empty_time(struct blkio_group_stats *stats) +{ + unsigned long long now; + + if (!blkio_blkg_empty(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_empty_time)) + stats->empty_time += now - stats->start_empty_time; + blkio_clear_blkg_empty(stats); +} + +void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + BUG_ON(blkio_blkg_idling(&blkg->stats)); + blkg->stats.start_idle_time = sched_clock(); + blkio_mark_blkg_idling(&blkg->stats); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_set_idle_time_stats); + +void blkiocg_update_idle_time_stats(struct blkio_group *blkg) +{ + unsigned long flags; + unsigned long long now; + struct blkio_group_stats *stats; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + if (blkio_blkg_idling(stats)) { + now = sched_clock(); + if (time_after64(now, stats->start_idle_time)) + stats->idle_time += now - stats->start_idle_time; + blkio_clear_blkg_idling(stats); + } + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats); + +void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg) +{ + unsigned long flags; + struct blkio_group_stats *stats; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + stats->avg_queue_size_sum += + stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] + + stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]; + stats->avg_queue_size_samples++; + blkio_update_group_wait_time(stats); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats); + +void blkiocg_set_start_empty_time(struct blkio_group *blkg) +{ + unsigned long flags; + struct blkio_group_stats *stats; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + + if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] || + stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) { + spin_unlock_irqrestore(&blkg->stats_lock, flags); + return; + } + + /* + * group is already marked empty. This can happen if cfqq got new + * request in parent group and moved to this group while being added + * to service tree. Just ignore the event and move on. + */ + if(blkio_blkg_empty(stats)) { + spin_unlock_irqrestore(&blkg->stats_lock, flags); + return; + } + + stats->start_empty_time = sched_clock(); + blkio_mark_blkg_empty(stats); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time); + +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, + unsigned long dequeue) +{ + blkg->stats.dequeue += dequeue; +} +EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats); +#else +static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg, + struct blkio_group *curr_blkg) {} +static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {} +#endif + +void blkiocg_update_io_add_stats(struct blkio_group *blkg, + struct blkio_group *curr_blkg, bool direction, + bool sync) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction, + sync); + blkio_end_empty_time(&blkg->stats); + blkio_set_start_group_wait_time(blkg, curr_blkg); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats); + +void blkiocg_update_io_remove_stats(struct blkio_group *blkg, + bool direction, bool sync) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], + direction, sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats); + +void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkg->stats.time += time; + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used); + +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, + uint64_t bytes, bool direction, bool sync) { - blkg->time += time; - blkg->sectors += sectors; + struct blkio_group_stats *stats; + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + stats->sectors += bytes >> 9; + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction, + sync); + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes, + direction, sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); } -EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_stats); +EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats); + +void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) +{ + struct blkio_group_stats *stats; + unsigned long flags; + unsigned long long now = sched_clock(); + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + if (time_after64(now, io_start_time)) + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME], + now - io_start_time, direction, sync); + if (time_after64(io_start_time, start_time)) + blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME], + io_start_time - start_time, direction, sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats); + +void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction, + bool sync) +{ + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction, + sync); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats); void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev) @@ -70,14 +346,13 @@ void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, unsigned long flags; spin_lock_irqsave(&blkcg->lock, flags); + spin_lock_init(&blkg->stats_lock); rcu_assign_pointer(blkg->key, key); blkg->blkcg_id = css_id(&blkcg->css); hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); spin_unlock_irqrestore(&blkcg->lock, flags); -#ifdef CONFIG_DEBUG_BLK_CGROUP /* Need to take css reference ? */ cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path)); -#endif blkg->dev = dev; } EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group); @@ -101,17 +376,16 @@ int blkiocg_del_blkio_group(struct blkio_group *blkg) rcu_read_lock(); css = css_lookup(&blkio_subsys, blkg->blkcg_id); - if (!css) - goto out; - - blkcg = container_of(css, struct blkio_cgroup, css); - spin_lock_irqsave(&blkcg->lock, flags); - if (!hlist_unhashed(&blkg->blkcg_node)) { - __blkiocg_del_blkio_group(blkg); - ret = 0; + if (css) { + blkcg = container_of(css, struct blkio_cgroup, css); + spin_lock_irqsave(&blkcg->lock, flags); + if (!hlist_unhashed(&blkg->blkcg_node)) { + __blkiocg_del_blkio_group(blkg); + ret = 0; + } + spin_unlock_irqrestore(&blkcg->lock, flags); } - spin_unlock_irqrestore(&blkcg->lock, flags); -out: + rcu_read_unlock(); return ret; } @@ -154,6 +428,7 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) struct blkio_group *blkg; struct hlist_node *n; struct blkio_policy_type *blkiop; + struct blkio_policy_node *pn; if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX) return -EINVAL; @@ -162,7 +437,13 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) spin_lock(&blkio_list_lock); spin_lock_irq(&blkcg->lock); blkcg->weight = (unsigned int)val; + hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + pn = blkio_policy_search_node(blkcg, blkg->dev); + + if (pn) + continue; + list_for_each_entry(blkiop, &blkio_list, list) blkiop->ops.blkio_update_group_weight_fn(blkg, blkcg->weight); @@ -172,13 +453,154 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) return 0; } -#define SHOW_FUNCTION_PER_GROUP(__VAR) \ +static int +blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val) +{ + struct blkio_cgroup *blkcg; + struct blkio_group *blkg; + struct blkio_group_stats *stats; + struct hlist_node *n; + uint64_t queued[BLKIO_STAT_TOTAL]; + int i; +#ifdef CONFIG_DEBUG_BLK_CGROUP + bool idling, waiting, empty; + unsigned long long now = sched_clock(); +#endif + + blkcg = cgroup_to_blkio_cgroup(cgroup); + spin_lock_irq(&blkcg->lock); + hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + spin_lock(&blkg->stats_lock); + stats = &blkg->stats; +#ifdef CONFIG_DEBUG_BLK_CGROUP + idling = blkio_blkg_idling(stats); + waiting = blkio_blkg_waiting(stats); + empty = blkio_blkg_empty(stats); +#endif + for (i = 0; i < BLKIO_STAT_TOTAL; i++) + queued[i] = stats->stat_arr[BLKIO_STAT_QUEUED][i]; + memset(stats, 0, sizeof(struct blkio_group_stats)); + for (i = 0; i < BLKIO_STAT_TOTAL; i++) + stats->stat_arr[BLKIO_STAT_QUEUED][i] = queued[i]; +#ifdef CONFIG_DEBUG_BLK_CGROUP + if (idling) { + blkio_mark_blkg_idling(stats); + stats->start_idle_time = now; + } + if (waiting) { + blkio_mark_blkg_waiting(stats); + stats->start_group_wait_time = now; + } + if (empty) { + blkio_mark_blkg_empty(stats); + stats->start_empty_time = now; + } +#endif + spin_unlock(&blkg->stats_lock); + } + spin_unlock_irq(&blkcg->lock); + return 0; +} + +static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str, + int chars_left, bool diskname_only) +{ + snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev)); + chars_left -= strlen(str); + if (chars_left <= 0) { + printk(KERN_WARNING + "Possibly incorrect cgroup stat display format"); + return; + } + if (diskname_only) + return; + switch (type) { + case BLKIO_STAT_READ: + strlcat(str, " Read", chars_left); + break; + case BLKIO_STAT_WRITE: + strlcat(str, " Write", chars_left); + break; + case BLKIO_STAT_SYNC: + strlcat(str, " Sync", chars_left); + break; + case BLKIO_STAT_ASYNC: + strlcat(str, " Async", chars_left); + break; + case BLKIO_STAT_TOTAL: + strlcat(str, " Total", chars_left); + break; + default: + strlcat(str, " Invalid", chars_left); + } +} + +static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val, + struct cgroup_map_cb *cb, dev_t dev) +{ + blkio_get_key_name(0, dev, str, chars_left, true); + cb->fill(cb, str, val); + return val; +} + +/* This should be called with blkg->stats_lock held */ +static uint64_t blkio_get_stat(struct blkio_group *blkg, + struct cgroup_map_cb *cb, dev_t dev, enum stat_type type) +{ + uint64_t disk_total; + char key_str[MAX_KEY_LEN]; + enum stat_sub_type sub_type; + + if (type == BLKIO_STAT_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.time, cb, dev); + if (type == BLKIO_STAT_SECTORS) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.sectors, cb, dev); +#ifdef CONFIG_DEBUG_BLK_CGROUP + if (type == BLKIO_STAT_AVG_QUEUE_SIZE) { + uint64_t sum = blkg->stats.avg_queue_size_sum; + uint64_t samples = blkg->stats.avg_queue_size_samples; + if (samples) + do_div(sum, samples); + else + sum = 0; + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev); + } + if (type == BLKIO_STAT_GROUP_WAIT_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.group_wait_time, cb, dev); + if (type == BLKIO_STAT_IDLE_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.idle_time, cb, dev); + if (type == BLKIO_STAT_EMPTY_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.empty_time, cb, dev); + if (type == BLKIO_STAT_DEQUEUE) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.dequeue, cb, dev); +#endif + + for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL; + sub_type++) { + blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false); + cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]); + } + disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] + + blkg->stats.stat_arr[type][BLKIO_STAT_WRITE]; + blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false); + cb->fill(cb, key_str, disk_total); + return disk_total; +} + +#define SHOW_FUNCTION_PER_GROUP(__VAR, type, show_total) \ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ - struct cftype *cftype, struct seq_file *m) \ + struct cftype *cftype, struct cgroup_map_cb *cb) \ { \ struct blkio_cgroup *blkcg; \ struct blkio_group *blkg; \ struct hlist_node *n; \ + uint64_t cgroup_total = 0; \ \ if (!cgroup_lock_live_group(cgroup)) \ return -ENODEV; \ @@ -186,50 +608,293 @@ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ blkcg = cgroup_to_blkio_cgroup(cgroup); \ rcu_read_lock(); \ hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\ - if (blkg->dev) \ - seq_printf(m, "%u:%u %lu\n", MAJOR(blkg->dev), \ - MINOR(blkg->dev), blkg->__VAR); \ + if (blkg->dev) { \ + spin_lock_irq(&blkg->stats_lock); \ + cgroup_total += blkio_get_stat(blkg, cb, \ + blkg->dev, type); \ + spin_unlock_irq(&blkg->stats_lock); \ + } \ } \ + if (show_total) \ + cb->fill(cb, "Total", cgroup_total); \ rcu_read_unlock(); \ cgroup_unlock(); \ return 0; \ } -SHOW_FUNCTION_PER_GROUP(time); -SHOW_FUNCTION_PER_GROUP(sectors); +SHOW_FUNCTION_PER_GROUP(time, BLKIO_STAT_TIME, 0); +SHOW_FUNCTION_PER_GROUP(sectors, BLKIO_STAT_SECTORS, 0); +SHOW_FUNCTION_PER_GROUP(io_service_bytes, BLKIO_STAT_SERVICE_BYTES, 1); +SHOW_FUNCTION_PER_GROUP(io_serviced, BLKIO_STAT_SERVICED, 1); +SHOW_FUNCTION_PER_GROUP(io_service_time, BLKIO_STAT_SERVICE_TIME, 1); +SHOW_FUNCTION_PER_GROUP(io_wait_time, BLKIO_STAT_WAIT_TIME, 1); +SHOW_FUNCTION_PER_GROUP(io_merged, BLKIO_STAT_MERGED, 1); +SHOW_FUNCTION_PER_GROUP(io_queued, BLKIO_STAT_QUEUED, 1); #ifdef CONFIG_DEBUG_BLK_CGROUP -SHOW_FUNCTION_PER_GROUP(dequeue); +SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0); +SHOW_FUNCTION_PER_GROUP(avg_queue_size, BLKIO_STAT_AVG_QUEUE_SIZE, 0); +SHOW_FUNCTION_PER_GROUP(group_wait_time, BLKIO_STAT_GROUP_WAIT_TIME, 0); +SHOW_FUNCTION_PER_GROUP(idle_time, BLKIO_STAT_IDLE_TIME, 0); +SHOW_FUNCTION_PER_GROUP(empty_time, BLKIO_STAT_EMPTY_TIME, 0); #endif #undef SHOW_FUNCTION_PER_GROUP -#ifdef CONFIG_DEBUG_BLK_CGROUP -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, - unsigned long dequeue) +static int blkio_check_dev_num(dev_t dev) { - blkg->dequeue += dequeue; + int part = 0; + struct gendisk *disk; + + disk = get_gendisk(dev, &part); + if (!disk || part) + return -ENODEV; + + return 0; +} + +static int blkio_policy_parse_and_set(char *buf, + struct blkio_policy_node *newpn) +{ + char *s[4], *p, *major_s = NULL, *minor_s = NULL; + int ret; + unsigned long major, minor, temp; + int i = 0; + dev_t dev; + + memset(s, 0, sizeof(s)); + + while ((p = strsep(&buf, " ")) != NULL) { + if (!*p) + continue; + + s[i++] = p; + + /* Prevent from inputing too many things */ + if (i == 3) + break; + } + + if (i != 2) + return -EINVAL; + + p = strsep(&s[0], ":"); + if (p != NULL) + major_s = p; + else + return -EINVAL; + + minor_s = s[0]; + if (!minor_s) + return -EINVAL; + + ret = strict_strtoul(major_s, 10, &major); + if (ret) + return -EINVAL; + + ret = strict_strtoul(minor_s, 10, &minor); + if (ret) + return -EINVAL; + + dev = MKDEV(major, minor); + + ret = blkio_check_dev_num(dev); + if (ret) + return ret; + + newpn->dev = dev; + + if (s[1] == NULL) + return -EINVAL; + + ret = strict_strtoul(s[1], 10, &temp); + if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) || + temp > BLKIO_WEIGHT_MAX) + return -EINVAL; + + newpn->weight = temp; + + return 0; +} + +unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg, + dev_t dev) +{ + struct blkio_policy_node *pn; + + pn = blkio_policy_search_node(blkcg, dev); + if (pn) + return pn->weight; + else + return blkcg->weight; +} +EXPORT_SYMBOL_GPL(blkcg_get_weight); + + +static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft, + const char *buffer) +{ + int ret = 0; + char *buf; + struct blkio_policy_node *newpn, *pn; + struct blkio_cgroup *blkcg; + struct blkio_group *blkg; + int keep_newpn = 0; + struct hlist_node *n; + struct blkio_policy_type *blkiop; + + buf = kstrdup(buffer, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + newpn = kzalloc(sizeof(*newpn), GFP_KERNEL); + if (!newpn) { + ret = -ENOMEM; + goto free_buf; + } + + ret = blkio_policy_parse_and_set(buf, newpn); + if (ret) + goto free_newpn; + + blkcg = cgroup_to_blkio_cgroup(cgrp); + + spin_lock_irq(&blkcg->lock); + + pn = blkio_policy_search_node(blkcg, newpn->dev); + if (!pn) { + if (newpn->weight != 0) { + blkio_policy_insert_node(blkcg, newpn); + keep_newpn = 1; + } + spin_unlock_irq(&blkcg->lock); + goto update_io_group; + } + + if (newpn->weight == 0) { + /* weight == 0 means deleteing a specific weight */ + blkio_policy_delete_node(pn); + spin_unlock_irq(&blkcg->lock); + goto update_io_group; + } + spin_unlock_irq(&blkcg->lock); + + pn->weight = newpn->weight; + +update_io_group: + /* update weight for each cfqg */ + spin_lock(&blkio_list_lock); + spin_lock_irq(&blkcg->lock); + + hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + if (newpn->dev == blkg->dev) { + list_for_each_entry(blkiop, &blkio_list, list) + blkiop->ops.blkio_update_group_weight_fn(blkg, + newpn->weight ? + newpn->weight : + blkcg->weight); + } + } + + spin_unlock_irq(&blkcg->lock); + spin_unlock(&blkio_list_lock); + +free_newpn: + if (!keep_newpn) + kfree(newpn); +free_buf: + kfree(buf); + return ret; +} + +static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft, + struct seq_file *m) +{ + struct blkio_cgroup *blkcg; + struct blkio_policy_node *pn; + + seq_printf(m, "dev\tweight\n"); + + blkcg = cgroup_to_blkio_cgroup(cgrp); + if (!list_empty(&blkcg->policy_list)) { + spin_lock_irq(&blkcg->lock); + list_for_each_entry(pn, &blkcg->policy_list, node) { + seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev), + MINOR(pn->dev), pn->weight); + } + spin_unlock_irq(&blkcg->lock); + } + + return 0; } -EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats); -#endif struct cftype blkio_files[] = { { + .name = "weight_device", + .read_seq_string = blkiocg_weight_device_read, + .write_string = blkiocg_weight_device_write, + .max_write_len = 256, + }, + { .name = "weight", .read_u64 = blkiocg_weight_read, .write_u64 = blkiocg_weight_write, }, { .name = "time", - .read_seq_string = blkiocg_time_read, + .read_map = blkiocg_time_read, }, { .name = "sectors", - .read_seq_string = blkiocg_sectors_read, + .read_map = blkiocg_sectors_read, + }, + { + .name = "io_service_bytes", + .read_map = blkiocg_io_service_bytes_read, + }, + { + .name = "io_serviced", + .read_map = blkiocg_io_serviced_read, + }, + { + .name = "io_service_time", + .read_map = blkiocg_io_service_time_read, + }, + { + .name = "io_wait_time", + .read_map = blkiocg_io_wait_time_read, + }, + { + .name = "io_merged", + .read_map = blkiocg_io_merged_read, + }, + { + .name = "io_queued", + .read_map = blkiocg_io_queued_read, + }, + { + .name = "reset_stats", + .write_u64 = blkiocg_reset_stats, }, #ifdef CONFIG_DEBUG_BLK_CGROUP - { + { + .name = "avg_queue_size", + .read_map = blkiocg_avg_queue_size_read, + }, + { + .name = "group_wait_time", + .read_map = blkiocg_group_wait_time_read, + }, + { + .name = "idle_time", + .read_map = blkiocg_idle_time_read, + }, + { + .name = "empty_time", + .read_map = blkiocg_empty_time_read, + }, + { .name = "dequeue", - .read_seq_string = blkiocg_dequeue_read, - }, + .read_map = blkiocg_dequeue_read, + }, #endif }; @@ -246,37 +911,42 @@ static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup) struct blkio_group *blkg; void *key; struct blkio_policy_type *blkiop; + struct blkio_policy_node *pn, *pntmp; rcu_read_lock(); -remove_entry: - spin_lock_irqsave(&blkcg->lock, flags); + do { + spin_lock_irqsave(&blkcg->lock, flags); + + if (hlist_empty(&blkcg->blkg_list)) { + spin_unlock_irqrestore(&blkcg->lock, flags); + break; + } + + blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group, + blkcg_node); + key = rcu_dereference(blkg->key); + __blkiocg_del_blkio_group(blkg); - if (hlist_empty(&blkcg->blkg_list)) { spin_unlock_irqrestore(&blkcg->lock, flags); - goto done; - } - blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group, - blkcg_node); - key = rcu_dereference(blkg->key); - __blkiocg_del_blkio_group(blkg); + /* + * This blkio_group is being unlinked as associated cgroup is + * going away. Let all the IO controlling policies know about + * this event. Currently this is static call to one io + * controlling policy. Once we have more policies in place, we + * need some dynamic registration of callback function. + */ + spin_lock(&blkio_list_lock); + list_for_each_entry(blkiop, &blkio_list, list) + blkiop->ops.blkio_unlink_group_fn(key, blkg); + spin_unlock(&blkio_list_lock); + } while (1); - spin_unlock_irqrestore(&blkcg->lock, flags); + list_for_each_entry_safe(pn, pntmp, &blkcg->policy_list, node) { + blkio_policy_delete_node(pn); + kfree(pn); + } - /* - * This blkio_group is being unlinked as associated cgroup is going - * away. Let all the IO controlling policies know about this event. - * - * Currently this is static call to one io controlling policy. Once - * we have more policies in place, we need some dynamic registration - * of callback function. - */ - spin_lock(&blkio_list_lock); - list_for_each_entry(blkiop, &blkio_list, list) - blkiop->ops.blkio_unlink_group_fn(key, blkg); - spin_unlock(&blkio_list_lock); - goto remove_entry; -done: free_css_id(&blkio_subsys, &blkcg->css); rcu_read_unlock(); if (blkcg != &blkio_root_cgroup) @@ -307,6 +977,7 @@ done: spin_lock_init(&blkcg->lock); INIT_HLIST_HEAD(&blkcg->blkg_list); + INIT_LIST_HEAD(&blkcg->policy_list); return &blkcg->css; } diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 8ccc20464da..2b866ec1dce 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -23,11 +23,84 @@ extern struct cgroup_subsys blkio_subsys; #define blkio_subsys_id blkio_subsys.subsys_id #endif +enum stat_type { + /* Total time spent (in ns) between request dispatch to the driver and + * request completion for IOs doen by this cgroup. This may not be + * accurate when NCQ is turned on. */ + BLKIO_STAT_SERVICE_TIME = 0, + /* Total bytes transferred */ + BLKIO_STAT_SERVICE_BYTES, + /* Total IOs serviced, post merge */ + BLKIO_STAT_SERVICED, + /* Total time spent waiting in scheduler queue in ns */ + BLKIO_STAT_WAIT_TIME, + /* Number of IOs merged */ + BLKIO_STAT_MERGED, + /* Number of IOs queued up */ + BLKIO_STAT_QUEUED, + /* All the single valued stats go below this */ + BLKIO_STAT_TIME, + BLKIO_STAT_SECTORS, +#ifdef CONFIG_DEBUG_BLK_CGROUP + BLKIO_STAT_AVG_QUEUE_SIZE, + BLKIO_STAT_IDLE_TIME, + BLKIO_STAT_EMPTY_TIME, + BLKIO_STAT_GROUP_WAIT_TIME, + BLKIO_STAT_DEQUEUE +#endif +}; + +enum stat_sub_type { + BLKIO_STAT_READ = 0, + BLKIO_STAT_WRITE, + BLKIO_STAT_SYNC, + BLKIO_STAT_ASYNC, + BLKIO_STAT_TOTAL +}; + +/* blkg state flags */ +enum blkg_state_flags { + BLKG_waiting = 0, + BLKG_idling, + BLKG_empty, +}; + struct blkio_cgroup { struct cgroup_subsys_state css; unsigned int weight; spinlock_t lock; struct hlist_head blkg_list; + struct list_head policy_list; /* list of blkio_policy_node */ +}; + +struct blkio_group_stats { + /* total disk time and nr sectors dispatched by this group */ + uint64_t time; + uint64_t sectors; + uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL]; +#ifdef CONFIG_DEBUG_BLK_CGROUP + /* Sum of number of IOs queued across all samples */ + uint64_t avg_queue_size_sum; + /* Count of samples taken for average */ + uint64_t avg_queue_size_samples; + /* How many times this group has been removed from service tree */ + unsigned long dequeue; + + /* Total time spent waiting for it to be assigned a timeslice. */ + uint64_t group_wait_time; + uint64_t start_group_wait_time; + + /* Time spent idling for this blkio_group */ + uint64_t idle_time; + uint64_t start_idle_time; + /* + * Total time when we have requests queued and do not contain the + * current active queue. + */ + uint64_t empty_time; + uint64_t start_empty_time; + uint16_t flags; +#endif }; struct blkio_group { @@ -35,20 +108,25 @@ struct blkio_group { void *key; struct hlist_node blkcg_node; unsigned short blkcg_id; -#ifdef CONFIG_DEBUG_BLK_CGROUP /* Store cgroup path */ char path[128]; - /* How many times this group has been removed from service tree */ - unsigned long dequeue; -#endif /* The device MKDEV(major, minor), this group has been created for */ - dev_t dev; + dev_t dev; - /* total disk time and nr sectors dispatched by this group */ - unsigned long time; - unsigned long sectors; + /* Need to serialize the stats in the case of reset/update */ + spinlock_t stats_lock; + struct blkio_group_stats stats; }; +struct blkio_policy_node { + struct list_head node; + dev_t dev; + unsigned int weight; +}; + +extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg, + dev_t dev); + typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg); typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg, unsigned int weight); @@ -67,6 +145,11 @@ struct blkio_policy_type { extern void blkio_policy_register(struct blkio_policy_type *); extern void blkio_policy_unregister(struct blkio_policy_type *); +static inline char *blkg_path(struct blkio_group *blkg) +{ + return blkg->path; +} + #else struct blkio_group { @@ -78,6 +161,8 @@ struct blkio_policy_type { static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { } static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { } +static inline char *blkg_path(struct blkio_group *blkg) { return NULL; } + #endif #define BLKIO_WEIGHT_MIN 100 @@ -85,16 +170,42 @@ static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { } #define BLKIO_WEIGHT_DEFAULT 500 #ifdef CONFIG_DEBUG_BLK_CGROUP -static inline char *blkg_path(struct blkio_group *blkg) -{ - return blkg->path; -} -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, +void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg); +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, unsigned long dequeue); +void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg); +void blkiocg_update_idle_time_stats(struct blkio_group *blkg); +void blkiocg_set_start_empty_time(struct blkio_group *blkg); + +#define BLKG_FLAG_FNS(name) \ +static inline void blkio_mark_blkg_##name( \ + struct blkio_group_stats *stats) \ +{ \ + stats->flags |= (1 << BLKG_##name); \ +} \ +static inline void blkio_clear_blkg_##name( \ + struct blkio_group_stats *stats) \ +{ \ + stats->flags &= ~(1 << BLKG_##name); \ +} \ +static inline int blkio_blkg_##name(struct blkio_group_stats *stats) \ +{ \ + return (stats->flags & (1 << BLKG_##name)) != 0; \ +} \ + +BLKG_FLAG_FNS(waiting) +BLKG_FLAG_FNS(idling) +BLKG_FLAG_FNS(empty) +#undef BLKG_FLAG_FNS #else -static inline char *blkg_path(struct blkio_group *blkg) { return NULL; } -static inline void blkiocg_update_blkio_group_dequeue_stats( - struct blkio_group *blkg, unsigned long dequeue) {} +static inline void blkiocg_update_avg_queue_size_stats( + struct blkio_group *blkg) {} +static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg, + unsigned long dequeue) {} +static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg) +{} +static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg) {} +static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {} #endif #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) @@ -105,26 +216,43 @@ extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, extern int blkiocg_del_blkio_group(struct blkio_group *blkg); extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key); -void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, - unsigned long time, unsigned long sectors); +void blkiocg_update_timeslice_used(struct blkio_group *blkg, + unsigned long time); +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes, + bool direction, bool sync); +void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync); +void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction, + bool sync); +void blkiocg_update_io_add_stats(struct blkio_group *blkg, + struct blkio_group *curr_blkg, bool direction, bool sync); +void blkiocg_update_io_remove_stats(struct blkio_group *blkg, + bool direction, bool sync); #else struct cgroup; static inline struct blkio_cgroup * cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; } static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, - struct blkio_group *blkg, void *key, dev_t dev) -{ -} + struct blkio_group *blkg, void *key, dev_t dev) {} static inline int blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; } static inline struct blkio_group * blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; } -static inline void blkiocg_update_blkio_group_stats(struct blkio_group *blkg, - unsigned long time, unsigned long sectors) -{ -} +static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg, + unsigned long time) {} +static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg, + uint64_t bytes, bool direction, bool sync) {} +static inline void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, + bool sync) {} +static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg, + bool direction, bool sync) {} +static inline void blkiocg_update_io_add_stats(struct blkio_group *blkg, + struct blkio_group *curr_blkg, bool direction, bool sync) {} +static inline void blkiocg_update_io_remove_stats(struct blkio_group *blkg, + bool direction, bool sync) {} #endif #endif /* _BLK_CGROUP_H */ diff --git a/block/blk-core.c b/block/blk-core.c index 9fe174dc74d..f84cce42fc5 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -127,6 +127,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq) rq->tag = -1; rq->ref_count = 1; rq->start_time = jiffies; + set_start_time_ns(rq); } EXPORT_SYMBOL(blk_rq_init); @@ -450,6 +451,7 @@ void blk_cleanup_queue(struct request_queue *q) */ blk_sync_queue(q); + del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer); mutex_lock(&q->sysfs_lock); queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q); mutex_unlock(&q->sysfs_lock); @@ -465,6 +467,9 @@ static int blk_init_free_list(struct request_queue *q) { struct request_list *rl = &q->rq; + if (unlikely(rl->rq_pool)) + return 0; + rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0; rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0; rl->elvpriv = 0; @@ -510,6 +515,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) return NULL; } + setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, + laptop_mode_timer_fn, (unsigned long) q); init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); @@ -566,16 +573,38 @@ 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 *q = blk_alloc_queue_node(GFP_KERNEL, node_id); + struct request_queue *uninit_q, *q; + + uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id); + if (!uninit_q) + return NULL; + + q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id); + if (!q) + blk_cleanup_queue(uninit_q); + + return q; +} +EXPORT_SYMBOL(blk_init_queue_node); + +struct request_queue * +blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, + spinlock_t *lock) +{ + return blk_init_allocated_queue_node(q, rfn, lock, -1); +} +EXPORT_SYMBOL(blk_init_allocated_queue); +struct request_queue * +blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, + spinlock_t *lock, int node_id) +{ if (!q) return NULL; q->node = node_id; - if (blk_init_free_list(q)) { - kmem_cache_free(blk_requestq_cachep, q); + if (blk_init_free_list(q)) return NULL; - } q->request_fn = rfn; q->prep_rq_fn = NULL; @@ -598,10 +627,9 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) return q; } - blk_put_queue(q); return NULL; } -EXPORT_SYMBOL(blk_init_queue_node); +EXPORT_SYMBOL(blk_init_allocated_queue_node); int blk_get_queue(struct request_queue *q) { @@ -1198,6 +1226,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) if (!blk_rq_cpu_valid(req)) req->cpu = bio->bi_comp_cpu; drive_stat_acct(req, 0); + elv_bio_merged(q, req, bio); if (!attempt_back_merge(q, req)) elv_merged_request(q, req, el_ret); goto out; @@ -1231,6 +1260,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) if (!blk_rq_cpu_valid(req)) req->cpu = bio->bi_comp_cpu; drive_stat_acct(req, 0); + elv_bio_merged(q, req, bio); if (!attempt_front_merge(q, req)) elv_merged_request(q, req, el_ret); goto out; @@ -1855,8 +1885,10 @@ void blk_dequeue_request(struct request *rq) * and to it is freed is accounted as io that is in progress at * the driver side. */ - if (blk_account_rq(rq)) + if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]++; + set_io_start_time_ns(rq); + } } /** @@ -2098,7 +2130,7 @@ static void blk_finish_request(struct request *req, int error) BUG_ON(blk_queued_rq(req)); if (unlikely(laptop_mode) && blk_fs_request(req)) - laptop_io_completion(); + laptop_io_completion(&req->q->backing_dev_info); blk_delete_timer(req); @@ -2517,4 +2549,3 @@ int __init blk_dev_init(void) return 0; } - diff --git a/block/blk-lib.c b/block/blk-lib.c new file mode 100644 index 00000000000..d0216b9f22d --- /dev/null +++ b/block/blk-lib.c @@ -0,0 +1,233 @@ +/* + * Functions related to generic helpers functions + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/bio.h> +#include <linux/blkdev.h> +#include <linux/scatterlist.h> + +#include "blk.h" + +static void blkdev_discard_end_io(struct bio *bio, int err) +{ + if (err) { + if (err == -EOPNOTSUPP) + set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); + clear_bit(BIO_UPTODATE, &bio->bi_flags); + } + + if (bio->bi_private) + complete(bio->bi_private); + __free_page(bio_page(bio)); + + bio_put(bio); +} + +/** + * blkdev_issue_discard - queue a discard + * @bdev: blockdev to issue discard for + * @sector: start sector + * @nr_sects: number of sectors to discard + * @gfp_mask: memory allocation flags (for bio_alloc) + * @flags: BLKDEV_IFL_* flags to control behaviour + * + * Description: + * Issue a discard request for the sectors in question. + */ +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) +{ + DECLARE_COMPLETION_ONSTACK(wait); + struct request_queue *q = bdev_get_queue(bdev); + int type = flags & BLKDEV_IFL_BARRIER ? + DISCARD_BARRIER : DISCARD_NOBARRIER; + struct bio *bio; + struct page *page; + int ret = 0; + + if (!q) + return -ENXIO; + + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + + while (nr_sects && !ret) { + unsigned int sector_size = q->limits.logical_block_size; + unsigned int max_discard_sectors = + min(q->limits.max_discard_sectors, UINT_MAX >> 9); + + bio = bio_alloc(gfp_mask, 1); + if (!bio) + goto out; + bio->bi_sector = sector; + bio->bi_end_io = blkdev_discard_end_io; + bio->bi_bdev = bdev; + if (flags & BLKDEV_IFL_WAIT) + bio->bi_private = &wait; + + /* + * Add a zeroed one-sector payload as that's what + * our current implementations need. If we'll ever need + * more the interface will need revisiting. + */ + page = alloc_page(gfp_mask | __GFP_ZERO); + if (!page) + goto out_free_bio; + if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size) + goto out_free_page; + + /* + * And override the bio size - the way discard works we + * touch many more blocks on disk than the actual payload + * length. + */ + if (nr_sects > max_discard_sectors) { + bio->bi_size = max_discard_sectors << 9; + nr_sects -= max_discard_sectors; + sector += max_discard_sectors; + } else { + bio->bi_size = nr_sects << 9; + nr_sects = 0; + } + + bio_get(bio); + submit_bio(type, bio); + + if (flags & BLKDEV_IFL_WAIT) + wait_for_completion(&wait); + + if (bio_flagged(bio, BIO_EOPNOTSUPP)) + ret = -EOPNOTSUPP; + else if (!bio_flagged(bio, BIO_UPTODATE)) + ret = -EIO; + bio_put(bio); + } + return ret; +out_free_page: + __free_page(page); +out_free_bio: + bio_put(bio); +out: + return -ENOMEM; +} +EXPORT_SYMBOL(blkdev_issue_discard); + +struct bio_batch +{ + atomic_t done; + unsigned long flags; + struct completion *wait; + bio_end_io_t *end_io; +}; + +static void bio_batch_end_io(struct bio *bio, int err) +{ + struct bio_batch *bb = bio->bi_private; + + if (err) { + if (err == -EOPNOTSUPP) + set_bit(BIO_EOPNOTSUPP, &bb->flags); + else + clear_bit(BIO_UPTODATE, &bb->flags); + } + if (bb) { + if (bb->end_io) + bb->end_io(bio, err); + atomic_inc(&bb->done); + complete(bb->wait); + } + bio_put(bio); +} + +/** + * blkdev_issue_zeroout generate number of zero filed write bios + * @bdev: blockdev to issue + * @sector: start sector + * @nr_sects: number of sectors to write + * @gfp_mask: memory allocation flags (for bio_alloc) + * @flags: BLKDEV_IFL_* flags to control behaviour + * + * Description: + * Generate and issue number of bios with zerofiled pages. + * Send barrier at the beginning and at the end if requested. This guarantie + * correct request ordering. Empty barrier allow us to avoid post queue flush. + */ + +int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) +{ + int ret = 0; + struct bio *bio; + struct bio_batch bb; + unsigned int sz, issued = 0; + DECLARE_COMPLETION_ONSTACK(wait); + + atomic_set(&bb.done, 0); + bb.flags = 1 << BIO_UPTODATE; + bb.wait = &wait; + bb.end_io = NULL; + + if (flags & BLKDEV_IFL_BARRIER) { + /* issue async barrier before the data */ + ret = blkdev_issue_flush(bdev, gfp_mask, NULL, 0); + if (ret) + return ret; + } +submit: + while (nr_sects != 0) { + bio = bio_alloc(gfp_mask, + min(nr_sects, (sector_t)BIO_MAX_PAGES)); + if (!bio) + break; + + bio->bi_sector = sector; + bio->bi_bdev = bdev; + bio->bi_end_io = bio_batch_end_io; + if (flags & BLKDEV_IFL_WAIT) + bio->bi_private = &bb; + + while (nr_sects != 0) { + sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects); + if (sz == 0) + /* bio has maximum size possible */ + break; + ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0); + nr_sects -= ret >> 9; + sector += ret >> 9; + if (ret < (sz << 9)) + break; + } + issued++; + submit_bio(WRITE, bio); + } + /* + * When all data bios are in flight. Send final barrier if requeted. + */ + if (nr_sects == 0 && flags & BLKDEV_IFL_BARRIER) + ret = blkdev_issue_flush(bdev, gfp_mask, NULL, + flags & BLKDEV_IFL_WAIT); + + + if (flags & BLKDEV_IFL_WAIT) + /* Wait for bios in-flight */ + while ( issued != atomic_read(&bb.done)) + wait_for_completion(&wait); + + if (!test_bit(BIO_UPTODATE, &bb.flags)) + /* One of bios in the batch was completed with error.*/ + ret = -EIO; + + if (ret) + goto out; + + if (test_bit(BIO_EOPNOTSUPP, &bb.flags)) { + ret = -EOPNOTSUPP; + goto out; + } + if (nr_sects != 0) + goto submit; +out: + return ret; +} +EXPORT_SYMBOL(blkdev_issue_zeroout); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 5f127cfb2e9..5ff4f4850e7 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -55,6 +55,7 @@ static const int cfq_hist_divisor = 4; #define RQ_CIC(rq) \ ((struct cfq_io_context *) (rq)->elevator_private) #define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2) +#define RQ_CFQG(rq) (struct cfq_group *) ((rq)->elevator_private3) static struct kmem_cache *cfq_pool; static struct kmem_cache *cfq_ioc_pool; @@ -63,6 +64,9 @@ static DEFINE_PER_CPU(unsigned long, cfq_ioc_count); static struct completion *ioc_gone; static DEFINE_SPINLOCK(ioc_gone_lock); +static DEFINE_SPINLOCK(cic_index_lock); +static DEFINE_IDA(cic_index_ida); + #define CFQ_PRIO_LISTS IOPRIO_BE_NR #define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE) #define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT) @@ -143,8 +147,6 @@ struct cfq_queue { struct cfq_queue *new_cfqq; struct cfq_group *cfqg; struct cfq_group *orig_cfqg; - /* Sectors dispatched in current dispatch round */ - unsigned long nr_sectors; }; /* @@ -272,6 +274,7 @@ struct cfq_data { unsigned int cfq_latency; unsigned int cfq_group_isolation; + unsigned int cic_index; struct list_head cic_list; /* @@ -346,7 +349,7 @@ CFQ_CFQQ_FNS(deep); CFQ_CFQQ_FNS(wait_busy); #undef CFQ_CFQQ_FNS -#ifdef CONFIG_DEBUG_CFQ_IOSCHED +#ifdef CONFIG_CFQ_GROUP_IOSCHED #define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \ cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \ @@ -431,6 +434,24 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic, cic->cfqq[is_sync] = cfqq; } +#define CIC_DEAD_KEY 1ul +#define CIC_DEAD_INDEX_SHIFT 1 + +static inline void *cfqd_dead_key(struct cfq_data *cfqd) +{ + return (void *)(cfqd->cic_index << CIC_DEAD_INDEX_SHIFT | CIC_DEAD_KEY); +} + +static inline struct cfq_data *cic_to_cfqd(struct cfq_io_context *cic) +{ + struct cfq_data *cfqd = cic->key; + + if (unlikely((unsigned long) cfqd & CIC_DEAD_KEY)) + return NULL; + + return cfqd; +} + /* * We regard a request as SYNC, if it's either a read or has the SYNC bit * set (in which case it could also be direct WRITE). @@ -858,7 +879,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg) if (!RB_EMPTY_NODE(&cfqg->rb_node)) cfq_rb_erase(&cfqg->rb_node, st); cfqg->saved_workload_slice = 0; - blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1); + blkiocg_update_dequeue_stats(&cfqg->blkg, 1); } static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) @@ -884,8 +905,7 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) slice_used = cfqq->allocated_slice; } - cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used, - cfqq->nr_sectors); + cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used); return slice_used; } @@ -919,8 +939,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime, st->min_vdisktime); - blkiocg_update_blkio_group_stats(&cfqg->blkg, used_sl, - cfqq->nr_sectors); + blkiocg_update_timeslice_used(&cfqg->blkg, used_sl); + blkiocg_set_start_empty_time(&cfqg->blkg); } #ifdef CONFIG_CFQ_GROUP_IOSCHED @@ -961,7 +981,6 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) if (!cfqg) goto done; - cfqg->weight = blkcg->weight; for_each_cfqg_st(cfqg, i, j, st) *st = CFQ_RB_ROOT; RB_CLEAR_NODE(&cfqg->rb_node); @@ -978,6 +997,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd, MKDEV(major, minor)); + cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev); /* Add group on cfqd list */ hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list); @@ -1004,6 +1024,12 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create) return cfqg; } +static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg) +{ + atomic_inc(&cfqg->ref); + return cfqg; +} + static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { /* Currently, all async queues are mapped to root group */ @@ -1087,6 +1113,12 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create) { return &cfqd->root_group; } + +static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg) +{ + return cfqg; +} + static inline void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { cfqq->cfqg = cfqg; @@ -1389,7 +1421,12 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq) { elv_rb_del(&cfqq->sort_list, rq); cfqq->queued[rq_is_sync(rq)]--; + blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), + rq_is_sync(rq)); cfq_add_rq_rb(rq); + blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg, + &cfqq->cfqd->serving_group->blkg, rq_data_dir(rq), + rq_is_sync(rq)); } static struct request * @@ -1445,6 +1482,8 @@ static void cfq_remove_request(struct request *rq) cfq_del_rq_rb(rq); cfqq->cfqd->rq_queued--; + blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), + rq_is_sync(rq)); if (rq_is_meta(rq)) { WARN_ON(!cfqq->meta_pending); cfqq->meta_pending--; @@ -1476,6 +1515,13 @@ static void cfq_merged_request(struct request_queue *q, struct request *req, } } +static void cfq_bio_merged(struct request_queue *q, struct request *req, + struct bio *bio) +{ + blkiocg_update_io_merged_stats(&(RQ_CFQG(req))->blkg, bio_data_dir(bio), + cfq_bio_sync(bio)); +} + static void cfq_merged_requests(struct request_queue *q, struct request *rq, struct request *next) @@ -1493,6 +1539,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, if (cfqq->next_rq == next) cfqq->next_rq = rq; cfq_remove_request(next); + blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(next), + rq_is_sync(next)); } static int cfq_allow_merge(struct request_queue *q, struct request *rq, @@ -1520,18 +1568,24 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq, return cfqq == RQ_CFQQ(rq); } +static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + del_timer(&cfqd->idle_slice_timer); + blkiocg_update_idle_time_stats(&cfqq->cfqg->blkg); +} + static void __cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (cfqq) { cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d", cfqd->serving_prio, cfqd->serving_type); + blkiocg_update_avg_queue_size_stats(&cfqq->cfqg->blkg); cfqq->slice_start = 0; cfqq->dispatch_start = jiffies; cfqq->allocated_slice = 0; cfqq->slice_end = 0; cfqq->slice_dispatch = 0; - cfqq->nr_sectors = 0; cfq_clear_cfqq_wait_request(cfqq); cfq_clear_cfqq_must_dispatch(cfqq); @@ -1539,7 +1593,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, cfq_clear_cfqq_fifo_expire(cfqq); cfq_mark_cfqq_slice_new(cfqq); - del_timer(&cfqd->idle_slice_timer); + cfq_del_timer(cfqd, cfqq); } cfqd->active_queue = cfqq; @@ -1555,7 +1609,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out); if (cfq_cfqq_wait_request(cfqq)) - del_timer(&cfqd->idle_slice_timer); + cfq_del_timer(cfqd, cfqq); cfq_clear_cfqq_wait_request(cfqq); cfq_clear_cfqq_wait_busy(cfqq); @@ -1857,6 +1911,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) sl = cfqd->cfq_slice_idle; mod_timer(&cfqd->idle_slice_timer, jiffies + sl); + blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg); cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl); } @@ -1876,7 +1931,8 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) elv_dispatch_sort(q, rq); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; - cfqq->nr_sectors += blk_rq_sectors(rq); + blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq), + rq_data_dir(rq), rq_is_sync(rq)); } /* @@ -2476,11 +2532,12 @@ static void cfq_cic_free(struct cfq_io_context *cic) static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic) { unsigned long flags; + unsigned long dead_key = (unsigned long) cic->key; - BUG_ON(!cic->dead_key); + BUG_ON(!(dead_key & CIC_DEAD_KEY)); spin_lock_irqsave(&ioc->lock, flags); - radix_tree_delete(&ioc->radix_root, cic->dead_key); + radix_tree_delete(&ioc->radix_root, dead_key >> CIC_DEAD_INDEX_SHIFT); hlist_del_rcu(&cic->cic_list); spin_unlock_irqrestore(&ioc->lock, flags); @@ -2503,15 +2560,10 @@ static void cfq_free_io_context(struct io_context *ioc) __call_for_each_cic(ioc, cic_free_func); } -static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) +static void cfq_put_cooperator(struct cfq_queue *cfqq) { struct cfq_queue *__cfqq, *next; - if (unlikely(cfqq == cfqd->active_queue)) { - __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); - } - /* * If this queue was scheduled to merge with another queue, be * sure to drop the reference taken on that queue (and others in @@ -2527,6 +2579,16 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) cfq_put_queue(__cfqq); __cfqq = next; } +} + +static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + if (unlikely(cfqq == cfqd->active_queue)) { + __cfq_slice_expired(cfqd, cfqq, 0); + cfq_schedule_dispatch(cfqd); + } + + cfq_put_cooperator(cfqq); cfq_put_queue(cfqq); } @@ -2539,11 +2601,10 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd, list_del_init(&cic->queue_list); /* - * Make sure key == NULL is seen for dead queues + * Make sure dead mark is seen for dead queues */ smp_wmb(); - cic->dead_key = (unsigned long) cic->key; - cic->key = NULL; + cic->key = cfqd_dead_key(cfqd); if (ioc->ioc_data == cic) rcu_assign_pointer(ioc->ioc_data, NULL); @@ -2562,7 +2623,7 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd, static void cfq_exit_single_io_context(struct io_context *ioc, struct cfq_io_context *cic) { - struct cfq_data *cfqd = cic->key; + struct cfq_data *cfqd = cic_to_cfqd(cic); if (cfqd) { struct request_queue *q = cfqd->queue; @@ -2575,7 +2636,7 @@ static void cfq_exit_single_io_context(struct io_context *ioc, * race between exiting task and queue */ smp_read_barrier_depends(); - if (cic->key) + if (cic->key == cfqd) __cfq_exit_single_io_context(cfqd, cic); spin_unlock_irqrestore(q->queue_lock, flags); @@ -2655,7 +2716,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic) { - struct cfq_data *cfqd = cic->key; + struct cfq_data *cfqd = cic_to_cfqd(cic); struct cfq_queue *cfqq; unsigned long flags; @@ -2712,7 +2773,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic) { struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1); - struct cfq_data *cfqd = cic->key; + struct cfq_data *cfqd = cic_to_cfqd(cic); unsigned long flags; struct request_queue *q; @@ -2849,12 +2910,13 @@ cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc, unsigned long flags; WARN_ON(!list_empty(&cic->queue_list)); + BUG_ON(cic->key != cfqd_dead_key(cfqd)); spin_lock_irqsave(&ioc->lock, flags); BUG_ON(ioc->ioc_data == cic); - radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd); + radix_tree_delete(&ioc->radix_root, cfqd->cic_index); hlist_del_rcu(&cic->cic_list); spin_unlock_irqrestore(&ioc->lock, flags); @@ -2866,7 +2928,6 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc) { struct cfq_io_context *cic; unsigned long flags; - void *k; if (unlikely(!ioc)) return NULL; @@ -2883,13 +2944,11 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc) } do { - cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd); + cic = radix_tree_lookup(&ioc->radix_root, cfqd->cic_index); rcu_read_unlock(); if (!cic) break; - /* ->key must be copied to avoid race with cfq_exit_queue() */ - k = cic->key; - if (unlikely(!k)) { + if (unlikely(cic->key != cfqd)) { cfq_drop_dead_cic(cfqd, ioc, cic); rcu_read_lock(); continue; @@ -2922,7 +2981,7 @@ static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc, spin_lock_irqsave(&ioc->lock, flags); ret = radix_tree_insert(&ioc->radix_root, - (unsigned long) cfqd, cic); + cfqd->cic_index, cic); if (!ret) hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list); spin_unlock_irqrestore(&ioc->lock, flags); @@ -3185,11 +3244,14 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (cfq_cfqq_wait_request(cfqq)) { if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || cfqd->busy_queues > 1) { - del_timer(&cfqd->idle_slice_timer); + cfq_del_timer(cfqd, cfqq); cfq_clear_cfqq_wait_request(cfqq); __blk_run_queue(cfqd->queue); - } else + } else { + blkiocg_update_idle_time_stats( + &cfqq->cfqg->blkg); cfq_mark_cfqq_must_dispatch(cfqq); + } } } else if (cfq_should_preempt(cfqd, cfqq, rq)) { /* @@ -3214,7 +3276,9 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]); list_add_tail(&rq->queuelist, &cfqq->fifo); cfq_add_rq_rb(rq); - + blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg, + &cfqd->serving_group->blkg, rq_data_dir(rq), + rq_is_sync(rq)); cfq_rq_enqueued(cfqd, cfqq, rq); } @@ -3300,6 +3364,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) WARN_ON(!cfqq->dispatched); cfqd->rq_in_driver--; cfqq->dispatched--; + blkiocg_update_completion_stats(&cfqq->cfqg->blkg, rq_start_time_ns(rq), + rq_io_start_time_ns(rq), rq_data_dir(rq), + rq_is_sync(rq)); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; @@ -3440,6 +3507,10 @@ static void cfq_put_request(struct request *rq) rq->elevator_private = NULL; rq->elevator_private2 = NULL; + /* Put down rq reference on cfqg */ + cfq_put_cfqg(RQ_CFQG(rq)); + rq->elevator_private3 = NULL; + cfq_put_queue(cfqq); } } @@ -3470,6 +3541,9 @@ split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq) } cic_set_cfqq(cic, NULL, 1); + + cfq_put_cooperator(cfqq); + cfq_put_queue(cfqq); return NULL; } @@ -3528,6 +3602,7 @@ new_queue: rq->elevator_private = cic; rq->elevator_private2 = cfqq; + rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg); return 0; queue_fail: @@ -3661,10 +3736,32 @@ static void cfq_exit_queue(struct elevator_queue *e) cfq_shutdown_timer_wq(cfqd); + spin_lock(&cic_index_lock); + ida_remove(&cic_index_ida, cfqd->cic_index); + spin_unlock(&cic_index_lock); + /* Wait for cfqg->blkg->key accessors to exit their grace periods. */ call_rcu(&cfqd->rcu, cfq_cfqd_free); } +static int cfq_alloc_cic_index(void) +{ + int index, error; + + do { + if (!ida_pre_get(&cic_index_ida, GFP_KERNEL)) + return -ENOMEM; + + spin_lock(&cic_index_lock); + error = ida_get_new(&cic_index_ida, &index); + spin_unlock(&cic_index_lock); + if (error && error != -EAGAIN) + return error; + } while (error); + + return index; +} + static void *cfq_init_queue(struct request_queue *q) { struct cfq_data *cfqd; @@ -3672,10 +3769,16 @@ static void *cfq_init_queue(struct request_queue *q) struct cfq_group *cfqg; struct cfq_rb_root *st; + i = cfq_alloc_cic_index(); + if (i < 0) + return NULL; + cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node); if (!cfqd) return NULL; + cfqd->cic_index = i; + /* Init root service tree */ cfqd->grp_service_tree = CFQ_RB_ROOT; @@ -3743,7 +3846,6 @@ static void *cfq_init_queue(struct request_queue *q) * second, in order to have larger depth for async operations. */ cfqd->last_delayed_sync = jiffies - HZ; - INIT_RCU_HEAD(&cfqd->rcu); return cfqd; } @@ -3872,6 +3974,7 @@ static struct elevator_type iosched_cfq = { .elevator_merged_fn = cfq_merged_request, .elevator_merge_req_fn = cfq_merged_requests, .elevator_allow_merge_fn = cfq_allow_merge, + .elevator_bio_merged_fn = cfq_bio_merged, .elevator_dispatch_fn = cfq_dispatch_requests, .elevator_add_req_fn = cfq_insert_request, .elevator_activate_req_fn = cfq_activate_request, @@ -3937,6 +4040,7 @@ static void __exit cfq_exit(void) */ if (elv_ioc_count_read(cfq_ioc_count)) wait_for_completion(&all_gone); + ida_destroy(&cic_index_ida); cfq_slab_kill(); } diff --git a/block/elevator.c b/block/elevator.c index 76e3702d538..923a9139106 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -242,9 +242,11 @@ int elevator_init(struct request_queue *q, char *name) { struct elevator_type *e = NULL; struct elevator_queue *eq; - int ret = 0; void *data; + if (unlikely(q->elevator)) + return 0; + INIT_LIST_HEAD(&q->queue_head); q->last_merge = NULL; q->end_sector = 0; @@ -284,7 +286,7 @@ int elevator_init(struct request_queue *q, char *name) } elevator_attach(q, eq, data); - return ret; + return 0; } EXPORT_SYMBOL(elevator_init); @@ -539,6 +541,15 @@ void elv_merge_requests(struct request_queue *q, struct request *rq, q->last_merge = rq; } +void elv_bio_merged(struct request_queue *q, struct request *rq, + struct bio *bio) +{ + struct elevator_queue *e = q->elevator; + + if (e->ops->elevator_bio_merged_fn) + e->ops->elevator_bio_merged_fn(q, rq, bio); +} + void elv_requeue_request(struct request_queue *q, struct request *rq) { /* @@ -921,6 +932,7 @@ int elv_register_queue(struct request_queue *q) } return error; } +EXPORT_SYMBOL(elv_register_queue); static void __elv_unregister_queue(struct elevator_queue *e) { @@ -933,6 +945,7 @@ void elv_unregister_queue(struct request_queue *q) if (q) __elv_unregister_queue(q->elevator); } +EXPORT_SYMBOL(elv_unregister_queue); void elv_register(struct elevator_type *e) { @@ -1086,7 +1099,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) struct elevator_type *__e; int len = 0; - if (!q->elevator) + if (!q->elevator || !blk_queue_stackable(q)) return sprintf(name, "none\n"); elv = e->elevator_type; diff --git a/block/genhd.c b/block/genhd.c index d13ba76a169..59a2db6fece 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -596,6 +596,7 @@ struct gendisk *get_gendisk(dev_t devt, int *partno) return disk; } +EXPORT_SYMBOL(get_gendisk); /** * bdget_disk - do bdget() by gendisk and partition number @@ -987,7 +988,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno) if (!new_ptbl) return -ENOMEM; - INIT_RCU_HEAD(&new_ptbl->rcu_head); new_ptbl->len = target; for (i = 0; i < len; i++) diff --git a/block/ioctl.c b/block/ioctl.c index 8905d2a2a71..e8eb679f2f9 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -126,7 +126,7 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, if (start + len > (bdev->bd_inode->i_size >> 9)) return -EINVAL; return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, - DISCARD_FL_WAIT); + BLKDEV_IFL_WAIT); } static int put_ushort(unsigned long arg, unsigned short val) |