diff options
34 files changed, 1699 insertions, 333 deletions
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 630879cd9a4..48e0b21b005 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -17,6 +17,9 @@ HOWTO You can do a very simple testing of running two dd threads in two different cgroups. Here is what you can do. +- Enable Block IO controller + CONFIG_BLK_CGROUP=y + - Enable group scheduling in CFQ CONFIG_CFQ_GROUP_IOSCHED=y @@ -54,32 +57,52 @@ cgroups. Here is what you can do. Various user visible config options =================================== -CONFIG_CFQ_GROUP_IOSCHED - - Enables group scheduling in CFQ. Currently only 1 level of group - creation is allowed. - -CONFIG_DEBUG_CFQ_IOSCHED - - Enables some debugging messages in blktrace. Also creates extra - cgroup file blkio.dequeue. - -Config options selected automatically -===================================== -These config options are not user visible and are selected/deselected -automatically based on IO scheduler configuration. - CONFIG_BLK_CGROUP - - Block IO controller. Selected by CONFIG_CFQ_GROUP_IOSCHED. + - Block IO controller. CONFIG_DEBUG_BLK_CGROUP - - Debug help. Selected by CONFIG_DEBUG_CFQ_IOSCHED. + - Debug help. Right now some additional stats file show up in cgroup + if this option is enabled. + +CONFIG_CFQ_GROUP_IOSCHED + - Enables group scheduling in CFQ. Currently only 1 level of group + creation is allowed. Details of cgroup files ======================= - blkio.weight - - Specifies per cgroup weight. - + - Specifies per cgroup weight. This is default weight of the group + on all the devices until and unless overridden by per device rule. + (See blkio.weight_device). Currently allowed range of weights is from 100 to 1000. +- blkio.weight_device + - One can specify per cgroup per device rules using this interface. + These rules override the default value of group weight as specified + by blkio.weight. + + Following is the format. + + #echo dev_maj:dev_minor weight > /path/to/cgroup/blkio.weight_device + Configure weight=300 on /dev/sdb (8:16) in this cgroup + # echo 8:16 300 > blkio.weight_device + # cat blkio.weight_device + dev weight + 8:16 300 + + Configure weight=500 on /dev/sda (8:0) in this cgroup + # echo 8:0 500 > blkio.weight_device + # cat blkio.weight_device + dev weight + 8:0 500 + 8:16 300 + + Remove specific weight for /dev/sda in this cgroup + # echo 8:0 0 > blkio.weight_device + # cat blkio.weight_device + dev weight + 8:16 300 + - blkio.time - disk time allocated to cgroup per device in milliseconds. First two fields specify the major and minor number of the device and @@ -92,13 +115,105 @@ Details of cgroup files third field specifies the number of sectors transferred by the group to/from the device. +- blkio.io_service_bytes + - Number of bytes transferred to/from the disk by the group. These + are further divided by the type of operation - read or write, sync + or async. First two fields specify the major and minor number of the + device, third field specifies the operation type and the fourth field + specifies the number of bytes. + +- blkio.io_serviced + - Number of IOs completed to/from the disk by the group. These + are further divided by the type of operation - read or write, sync + or async. First two fields specify the major and minor number of the + device, third field specifies the operation type and the fourth field + specifies the number of IOs. + +- blkio.io_service_time + - Total amount of time between request dispatch and request completion + for the IOs done by this cgroup. This is in nanoseconds to make it + meaningful for flash devices too. For devices with queue depth of 1, + this time represents the actual service time. When queue_depth > 1, + that is no longer true as requests may be served out of order. This + may cause the service time for a given IO to include the service time + of multiple IOs when served out of order which may result in total + io_service_time > actual time elapsed. This time is further divided by + the type of operation - read or write, sync or async. First two fields + specify the major and minor number of the device, third field + specifies the operation type and the fourth field specifies the + io_service_time in ns. + +- blkio.io_wait_time + - Total amount of time the IOs for this cgroup spent waiting in the + scheduler queues for service. This can be greater than the total time + elapsed since it is cumulative io_wait_time for all IOs. It is not a + measure of total time the cgroup spent waiting but rather a measure of + the wait_time for its individual IOs. For devices with queue_depth > 1 + this metric does not include the time spent waiting for service once + the IO is dispatched to the device but till it actually gets serviced + (there might be a time lag here due to re-ordering of requests by the + device). This is in nanoseconds to make it meaningful for flash + devices too. This time is further divided by the type of operation - + read or write, sync or async. First two fields specify the major and + minor number of the device, third field specifies the operation type + and the fourth field specifies the io_wait_time in ns. + +- blkio.io_merged + - Total number of bios/requests merged into requests belonging to this + cgroup. This is further divided by the type of operation - read or + write, sync or async. + +- blkio.io_queued + - Total number of requests queued up at any given instant for this + cgroup. This is further divided by the type of operation - read or + write, sync or async. + +- blkio.avg_queue_size + - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. + The average queue size for this cgroup over the entire time of this + cgroup's existence. Queue size samples are taken each time one of the + queues of this cgroup gets a timeslice. + +- blkio.group_wait_time + - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. + This is the amount of time the cgroup had to wait since it became busy + (i.e., went from 0 to 1 request queued) to get a timeslice for one of + its queues. This is different from the io_wait_time which is the + cumulative total of the amount of time spent by each IO in that cgroup + waiting in the scheduler queue. This is in nanoseconds. If this is + read when the cgroup is in a waiting (for timeslice) state, the stat + will only report the group_wait_time accumulated till the last time it + got a timeslice and will not include the current delta. + +- blkio.empty_time + - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. + This is the amount of time a cgroup spends without any pending + requests when not being served, i.e., it does not include any time + spent idling for one of the queues of the cgroup. This is in + nanoseconds. If this is read when the cgroup is in an empty state, + the stat will only report the empty_time accumulated till the last + time it had a pending request and will not include the current delta. + +- blkio.idle_time + - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. + This is the amount of time spent by the IO scheduler idling for a + given cgroup in anticipation of a better request than the exising ones + from other queues/cgroups. This is in nanoseconds. If this is read + when the cgroup is in an idling state, the stat will only report the + idle_time accumulated till the last idle period and will not include + the current delta. + - blkio.dequeue - - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. This + - Debugging aid only enabled if CONFIG_DEBUG_BLK_CGROUP=y. This gives the statistics about how many a times a group was dequeued from service tree of the device. First two fields specify the major and minor number of the device and third field specifies the number of times a group was dequeued from a particular device. +- blkio.reset_stats + - Writing an int to this file will result in resetting all the stats + for that cgroup. + CFQ sysfs tunable ================= /sys/block/<disk>/queue/iosched/group_isolation 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 5fe03def34b..d02bbf88de1 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) +{ + 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_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) { - blkg->time += time; - blkg->sectors += sectors; + 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_blkio_group_stats); +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); @@ -154,6 +429,7 @@ 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 +438,13 @@ 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 +454,154 @@ 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 +609,295 @@ 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)) + goto out; + + 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); + +out: + 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 }; @@ -246,6 +914,7 @@ 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: @@ -276,7 +945,12 @@ remove_entry: blkiop->ops.blkio_unlink_group_fn(key, blkg); spin_unlock(&blkio_list_lock); goto remove_entry; + done: + list_for_each_entry_safe(pn, pntmp, &blkcg->policy_list, node) { + blkio_policy_delete_node(pn); + kfree(pn); + } free_css_id(&blkio_subsys, &blkcg->css); rcu_read_unlock(); if (blkcg != &blkio_root_cgroup) @@ -307,6 +981,7 @@ 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..e9a5ae25db8 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); @@ -510,6 +512,8 @@ 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); @@ -1198,6 +1202,7 @@ 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 +1236,7 @@ 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 +1861,10 @@ 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 +2106,7 @@ 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 +2525,3 @@ 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 838834be115..0f3eb70f9ce 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; @@ -143,8 +144,6 @@ 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; }; /* @@ -346,7 +345,7 @@ 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', \ @@ -858,7 +857,7 @@ 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 +883,7 @@ 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 +917,8 @@ 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 +959,6 @@ 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 +975,7 @@ 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 +1002,12 @@ 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 +1091,12 @@ 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 +1399,12 @@ 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 +1460,8 @@ 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 +1493,13 @@ 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 +1517,8 @@ 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 +1546,24 @@ 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 +1571,7 @@ 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 +1587,7 @@ __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 +1889,7 @@ 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 +1909,8 @@ 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)); } /* @@ -3185,11 +3219,14 @@ 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 +3251,9 @@ 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 +3339,9 @@ 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 +3482,10 @@ 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); } } @@ -3528,6 +3574,7 @@ new_queue: rq->elevator_private = cic; rq->elevator_private2 = cfqq; + rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg); return 0; queue_fail: @@ -3870,6 +3917,7 @@ 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, diff --git a/block/elevator.c b/block/elevator.c index 76e3702d538..5e734592bb4 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -539,6 +539,15 @@ 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) { /* diff --git a/block/genhd.c b/block/genhd.c index d13ba76a169..154b5f80b3a 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 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) diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index e5e86a78182..d6f1ae342b1 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -2251,7 +2251,8 @@ static inline void drbd_md_flush(struct drbd_conf *mdev) if (test_bit(MD_NO_BARRIER, &mdev->flags)) return; - r = blkdev_issue_flush(mdev->ldev->md_bdev, NULL); + r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); if (r) { set_bit(MD_NO_BARRIER, &mdev->flags); dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 3f096e7959b..c786023001d 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -946,7 +946,8 @@ static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct d int rv; if (mdev->write_ordering >= WO_bdev_flush && get_ldev(mdev)) { - rv = blkdev_issue_flush(mdev->ldev->backing_bdev, NULL); + rv = blkdev_issue_flush(mdev->ldev->backing_bdev, GFP_KERNEL, + NULL, BLKDEV_IFL_WAIT); if (rv) { dev_err(DEV, "local disk flush failed with status %d\n", rv); /* would rather check on EOPNOTSUPP, but that is not reliable. diff --git a/fs/block_dev.c b/fs/block_dev.c index 6dcee88c2e5..55dcb7884f4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -417,7 +417,7 @@ int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync) */ mutex_unlock(&bd_inode->i_mutex); - error = blkdev_issue_flush(bdev, NULL); + error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, BLKDEV_IFL_WAIT); if (error == -EOPNOTSUPP) error = 0; @@ -668,41 +668,209 @@ void bd_forget(struct inode *inode) iput(bdev->bd_inode); } -int bd_claim(struct block_device *bdev, void *holder) +/** + * bd_may_claim - test whether a block device can be claimed + * @bdev: block device of interest + * @whole: whole block device containing @bdev, may equal @bdev + * @holder: holder trying to claim @bdev + * + * Test whther @bdev can be claimed by @holder. + * + * CONTEXT: + * spin_lock(&bdev_lock). + * + * RETURNS: + * %true if @bdev can be claimed, %false otherwise. + */ +static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, + void *holder) { - int res; - spin_lock(&bdev_lock); - - /* first decide result */ if (bdev->bd_holder == holder) - res = 0; /* already a holder */ + return true; /* already a holder */ else if (bdev->bd_holder != NULL) - res = -EBUSY; /* held by someone else */ + return false; /* held by someone else */ else if (bdev->bd_contains == bdev) - res = 0; /* is a whole device which isn't held */ + return true; /* is a whole device which isn't held */ - else if (bdev->bd_contains->bd_holder == bd_claim) - res = 0; /* is a partition of a device that is being partitioned */ - else if (bdev->bd_contains->bd_holder != NULL) - res = -EBUSY; /* is a partition of a held device */ + else if (whole->bd_holder == bd_claim) + return true; /* is a partition of a device that is being partitioned */ + else if (whole->bd_holder != NULL) + return false; /* is a partition of a held device */ else - res = 0; /* is a partition of an un-held device */ + return true; /* is a partition of an un-held device */ +} + +/** + * bd_prepare_to_claim - prepare to claim a block device + * @bdev: block device of interest + * @whole: the whole device containing @bdev, may equal @bdev + * @holder: holder trying to claim @bdev + * + * Prepare to claim @bdev. This function fails if @bdev is already + * claimed by another holder and waits if another claiming is in + * progress. This function doesn't actually claim. On successful + * return, the caller has ownership of bd_claiming and bd_holder[s]. + * + * CONTEXT: + * spin_lock(&bdev_lock). Might release bdev_lock, sleep and regrab + * it multiple times. + * + * RETURNS: + * 0 if @bdev can be claimed, -EBUSY otherwise. + */ +static int bd_prepare_to_claim(struct block_device *bdev, + struct block_device *whole, void *holder) +{ +retry: + /* if someone else claimed, fail */ + if (!bd_may_claim(bdev, whole, holder)) + return -EBUSY; + + /* if someone else is claiming, wait for it to finish */ + if (whole->bd_claiming && whole->bd_claiming != holder) { + wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0); + DEFINE_WAIT(wait); + + prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&bdev_lock); + schedule(); + finish_wait(wq, &wait); + spin_lock(&bdev_lock); + goto retry; + } + + /* yay, all mine */ + return 0; +} + +/** + * bd_start_claiming - start claiming a block device + * @bdev: block device of interest + * @holder: holder trying to claim @bdev + * + * @bdev is about to be opened exclusively. Check @bdev can be opened + * exclusively and mark that an exclusive open is in progress. Each + * successful call to this function must be matched with a call to + * either bd_claim() or bd_abort_claiming(). If this function + * succeeds, the matching bd_claim() is guaranteed to succeed. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * Pointer to the block device containing @bdev on success, ERR_PTR() + * value on failure. + */ +static struct block_device *bd_start_claiming(struct block_device *bdev, + void *holder) +{ + struct gendisk *disk; + struct block_device *whole; + int partno, err; + + might_sleep(); + + /* + * @bdev might not have been initialized properly yet, look up + * and grab the outer block device the hard way. + */ + disk = get_gendisk(bdev->bd_dev, &partno); + if (!disk) + return ERR_PTR(-ENXIO); + + whole = bdget_disk(disk, 0); + put_disk(disk); + if (!whole) + return ERR_PTR(-ENOMEM); + + /* prepare to claim, if successful, mark claiming in progress */ + spin_lock(&bdev_lock); + + err = bd_prepare_to_claim(bdev, whole, holder); + if (err == 0) { + whole->bd_claiming = holder; + spin_unlock(&bdev_lock); + return whole; + } else { + spin_unlock(&bdev_lock); + bdput(whole); + return ERR_PTR(err); + } +} - /* now impose change */ - if (res==0) { +/* releases bdev_lock */ +static void __bd_abort_claiming(struct block_device *whole, void *holder) +{ + BUG_ON(whole->bd_claiming != holder); + whole->bd_claiming = NULL; + wake_up_bit(&whole->bd_claiming, 0); + + spin_unlock(&bdev_lock); + bdput(whole); +} + +/** + * bd_abort_claiming - abort claiming a block device + * @whole: whole block device returned by bd_start_claiming() + * @holder: holder trying to claim @bdev + * + * Abort a claiming block started by bd_start_claiming(). Note that + * @whole is not the block device to be claimed but the whole device + * returned by bd_start_claiming(). + * + * CONTEXT: + * Grabs and releases bdev_lock. + */ +static void bd_abort_claiming(struct block_device *whole, void *holder) +{ + spin_lock(&bdev_lock); + __bd_abort_claiming(whole, holder); /* releases bdev_lock */ +} + +/** + * bd_claim - claim a block device + * @bdev: block device to claim + * @holder: holder trying to claim @bdev + * + * Try to claim @bdev which must have been opened successfully. This + * function may be called with or without preceding + * blk_start_claiming(). In the former case, this function is always + * successful and terminates the claiming block. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * 0 if successful, -EBUSY if @bdev is already claimed. + */ +int bd_claim(struct block_device *bdev, void *holder) +{ + struct block_device *whole = bdev->bd_contains; + int res; + + might_sleep(); + + spin_lock(&bdev_lock); + + res = bd_prepare_to_claim(bdev, whole, holder); + if (res == 0) { /* note that for a whole device bd_holders * will be incremented twice, and bd_holder will * be set to bd_claim before being set to holder */ - bdev->bd_contains->bd_holders ++; - bdev->bd_contains->bd_holder = bd_claim; + whole->bd_holders++; + whole->bd_holder = bd_claim; bdev->bd_holders++; bdev->bd_holder = holder; } - spin_unlock(&bdev_lock); + + if (whole->bd_claiming) + __bd_abort_claiming(whole, holder); /* releases bdev_lock */ + else + spin_unlock(&bdev_lock); + return res; } - EXPORT_SYMBOL(bd_claim); void bd_release(struct block_device *bdev) @@ -1316,6 +1484,7 @@ EXPORT_SYMBOL(blkdev_get); static int blkdev_open(struct inode * inode, struct file * filp) { + struct block_device *whole = NULL; struct block_device *bdev; int res; @@ -1338,22 +1507,25 @@ static int blkdev_open(struct inode * inode, struct file * filp) if (bdev == NULL) return -ENOMEM; + if (filp->f_mode & FMODE_EXCL) { + whole = bd_start_claiming(bdev, filp); + if (IS_ERR(whole)) { + bdput(bdev); + return PTR_ERR(whole); + } + } + filp->f_mapping = bdev->bd_inode->i_mapping; res = blkdev_get(bdev, filp->f_mode); - if (res) - return res; - if (filp->f_mode & FMODE_EXCL) { - res = bd_claim(bdev, filp); - if (res) - goto out_blkdev_put; + if (whole) { + if (res == 0) + BUG_ON(bd_claim(bdev, filp) != 0); + else + bd_abort_claiming(whole, filp); } - return 0; - - out_blkdev_put: - blkdev_put(bdev, filp->f_mode); return res; } @@ -1564,27 +1736,34 @@ EXPORT_SYMBOL(lookup_bdev); */ struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder) { - struct block_device *bdev; - int error = 0; + struct block_device *bdev, *whole; + int error; bdev = lookup_bdev(path); if (IS_ERR(bdev)) return bdev; + whole = bd_start_claiming(bdev, holder); + if (IS_ERR(whole)) { + bdput(bdev); + return whole; + } + error = blkdev_get(bdev, mode); if (error) - return ERR_PTR(error); + goto out_abort_claiming; + error = -EACCES; if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) - goto blkdev_put; - error = bd_claim(bdev, holder); - if (error) - goto blkdev_put; + goto out_blkdev_put; + BUG_ON(bd_claim(bdev, holder) != 0); return bdev; - -blkdev_put: + +out_blkdev_put: blkdev_put(bdev, mode); +out_abort_claiming: + bd_abort_claiming(whole, holder); return ERR_PTR(error); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b34d32fdaae..c6a4f459ad7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1589,7 +1589,7 @@ static void btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len) { blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index 8209f266e9a..9492f6003ef 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -91,7 +91,8 @@ int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync) * storage */ if (test_opt(inode->i_sb, BARRIER)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); out: return ret; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 0d0c3239c1c..ef3d980e67c 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -100,9 +100,11 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) if (ext4_should_writeback_data(inode) && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, + NULL, BLKDEV_IFL_WAIT); jbd2_log_wait_commit(journal, commit_tid); } else if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); return ret; } diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 503b842f3ba..bf011dc6347 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -854,7 +854,8 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, if ((start + nr_sects) != blk) { rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | + BLKDEV_IFL_BARRIER); if (rv) goto fail; nr_sects = 0; @@ -869,7 +870,7 @@ start_new_extent: } if (nr_sects) { rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (rv) goto fail; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 30beb11ef92..076d1cc44f9 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -530,7 +530,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) */ if ((journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); if (!(journal->j_flags & JBD2_ABORT)) jbd2_journal_update_superblock(journal, 1); return 0; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 671da7fb7ff..75716d3d2be 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -717,7 +717,8 @@ start_journal_io: if (commit_transaction->t_flushed_data_blocks && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, @@ -727,7 +728,8 @@ start_journal_io: if (err) __jbd2_journal_abort_hard(journal); if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(journal->j_dev, NULL); + blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); } err = journal_finish_inode_data_buffers(journal, commit_transaction); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 33871f7e4f0..7ffcf2b8b1f 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -670,7 +670,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, start * sects_per_block, nblocks * sects_per_block, GFP_NOFS, - DISCARD_FL_BARRIER); + BLKDEV_IFL_BARRIER); if (ret < 0) return ret; nblocks = 0; @@ -680,7 +680,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, DISCARD_FL_BARRIER); + GFP_NOFS, BLKDEV_IFL_BARRIER); return ret; } diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 1d9c12714c5..9977df9f3a5 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -147,7 +147,8 @@ static int reiserfs_sync_file(struct file *filp, barrier_done = reiserfs_commit_for_inode(inode); reiserfs_write_unlock(inode->i_sb); if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); if (barrier_done < 0) return barrier_done; return (err < 0) ? -EIO : 0; diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 52e06b487ce..2b177c778ba 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -725,7 +725,8 @@ void xfs_blkdev_issue_flush( xfs_buftarg_t *buftarg) { - blkdev_issue_flush(buftarg->bt_bdev, NULL); + blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); } STATIC void diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index bd0e3c6f323..7534979d83b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> +#include <linux/timer.h> #include <linux/writeback.h> #include <asm/atomic.h> @@ -88,6 +89,8 @@ struct backing_dev_info { struct device *dev; + struct timer_list laptop_mode_wb_timer; + #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; struct dentry *debug_stats; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6690e8bae7b..3ac2bd2fc48 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -186,15 +186,19 @@ struct request { }; /* - * two pointers are available for the IO schedulers, if they need + * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. */ void *elevator_private; void *elevator_private2; + void *elevator_private3; struct gendisk *rq_disk; unsigned long start_time; - +#ifdef CONFIG_BLK_CGROUP + unsigned long long start_time_ns; + unsigned long long io_start_time_ns; /* when passed to hardware */ +#endif /* Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ @@ -994,20 +998,25 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return NULL; return bqt->tag_index[tag]; } - -extern int blkdev_issue_flush(struct block_device *, sector_t *); -#define DISCARD_FL_WAIT 0x01 /* wait for completion */ -#define DISCARD_FL_BARRIER 0x02 /* issue DISCARD_BARRIER request */ -extern int blkdev_issue_discard(struct block_device *, sector_t sector, - sector_t nr_sects, gfp_t, int flags); - +enum{ + BLKDEV_WAIT, /* wait for completion */ + BLKDEV_BARRIER, /*issue request with barrier */ +}; +#define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT) +#define BLKDEV_IFL_BARRIER (1 << BLKDEV_BARRIER) +extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, + unsigned long); +extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); +extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks) { block <<= (sb->s_blocksize_bits - 9); nr_blocks <<= (sb->s_blocksize_bits - 9); return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); @@ -1196,6 +1205,39 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +#ifdef CONFIG_BLK_CGROUP +static inline void set_start_time_ns(struct request *req) +{ + req->start_time_ns = sched_clock(); +} + +static inline void set_io_start_time_ns(struct request *req) +{ + req->io_start_time_ns = sched_clock(); +} + +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return req->start_time_ns; +} + +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return req->io_start_time_ns; +} +#else +static inline void set_start_time_ns(struct request *req) {} +static inline void set_io_start_time_ns(struct request *req) {} +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return 0; +} +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return 0; +} +#endif + #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 1cb3372e65d..2c958f4fce1 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -14,6 +14,9 @@ typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *); +typedef void (elevator_bio_merged_fn) (struct request_queue *, + struct request *, struct bio *); + typedef int (elevator_dispatch_fn) (struct request_queue *, int); typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); @@ -36,6 +39,7 @@ struct elevator_ops elevator_merged_fn *elevator_merged_fn; elevator_merge_req_fn *elevator_merge_req_fn; elevator_allow_merge_fn *elevator_allow_merge_fn; + elevator_bio_merged_fn *elevator_bio_merged_fn; elevator_dispatch_fn *elevator_dispatch_fn; elevator_add_req_fn *elevator_add_req_fn; @@ -103,6 +107,8 @@ extern int elv_merge(struct request_queue *, struct request **, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, int); +extern void elv_bio_merged(struct request_queue *q, struct request *, + struct bio *); extern void elv_requeue_request(struct request_queue *, struct request *); extern int elv_queue_empty(struct request_queue *); extern struct request *elv_former_request(struct request_queue *, struct request *); diff --git a/include/linux/fs.h b/include/linux/fs.h index 44f35aea2f1..f30970c97ac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -651,6 +651,7 @@ struct block_device { int bd_openers; struct mutex bd_mutex; /* open/close mutex */ struct list_head bd_inodes; + void * bd_claiming; void * bd_holder; int bd_holders; #ifdef CONFIG_SYSFS diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 36520ded3e0..eb38a2c645f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -96,8 +96,10 @@ static inline void inode_sync_wait(struct inode *inode) /* * mm/page-writeback.c */ -void laptop_io_completion(void); +void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); +void laptop_mode_sync(struct work_struct *work); +void laptop_mode_timer_fn(unsigned long data); void throttle_vm_writeout(gfp_t gfp_mask); /* These are exported to sysctl. */ diff --git a/init/Kconfig b/init/Kconfig index eb77e8ccde1..087c14f3c59 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -612,6 +612,33 @@ config RT_GROUP_SCHED endif #CGROUP_SCHED +config BLK_CGROUP + tristate "Block IO controller" + depends on CGROUPS && BLOCK + 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. + + This option only enables generic Block IO controller infrastructure. + One needs to also enable actual IO controlling logic in CFQ for it + to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y). + + See Documentation/cgroups/blkio-controller.txt for more information. + +config DEBUG_BLK_CGROUP + bool "Enable Block IO controller debugging" + depends on BLK_CGROUP + default n + ---help--- + Enable some debugging help. Currently it exports additional stat + files in a cgroup which can be useful for debugging. + endif # CGROUPS config MM_OWNER diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 5b496132c28..906a0f718cb 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -41,6 +41,7 @@ unsigned long long __attribute__((weak)) sched_clock(void) return (unsigned long long)(jiffies - INITIAL_JIFFIES) * (NSEC_PER_SEC / HZ); } +EXPORT_SYMBOL_GPL(sched_clock); static __read_mostly int sched_clock_running; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b19943ecf8..d0f2b3765f8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -683,10 +683,6 @@ void throttle_vm_writeout(gfp_t gfp_mask) } } -static void laptop_timer_fn(unsigned long unused); - -static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); - /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ @@ -697,21 +693,19 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, return 0; } -static void do_laptop_sync(struct work_struct *work) +void laptop_mode_timer_fn(unsigned long data) { - wakeup_flusher_threads(0); - kfree(work); -} + struct request_queue *q = (struct request_queue *)data; + int nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); -static void laptop_timer_fn(unsigned long unused) -{ - struct work_struct *work; + /* + * We want to write everything out, not just down to the dirty + * threshold + */ - work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (work) { - INIT_WORK(work, do_laptop_sync); - schedule_work(work); - } + if (bdi_has_dirty_io(&q->backing_dev_info)) + bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages); } /* @@ -719,9 +713,9 @@ static void laptop_timer_fn(unsigned long unused) * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ -void laptop_io_completion(void) +void laptop_io_completion(struct backing_dev_info *info) { - mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode); + mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* @@ -731,7 +725,14 @@ void laptop_io_completion(void) */ void laptop_sync_completion(void) { - del_timer(&laptop_mode_wb_timer); + struct backing_dev_info *bdi; + + rcu_read_lock(); + + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) + del_timer(&bdi->laptop_mode_wb_timer); + + rcu_read_unlock(); } /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 6cd0a8f90dc..eb086e0f4dc 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -139,7 +139,8 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, DISCARD_FL_BARRIER); + nr_blocks, GFP_KERNEL, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (err) return err; cond_resched(); @@ -150,7 +151,8 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, DISCARD_FL_BARRIER); + nr_blocks, GFP_KERNEL, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (err) break; @@ -189,7 +191,8 @@ static void discard_swap_cluster(struct swap_info_struct *si, start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO, DISCARD_FL_BARRIER)) + nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT | + BLKDEV_IFL_BARRIER)) break; } |