diff options
74 files changed, 3890 insertions, 1242 deletions
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index cd556b9..68b6a6a 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -387,8 +387,81 @@ groups and put applications in that group which are not driving enough IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle on individual groups and throughput should improve. -What works -========== -- Currently only sync IO queues are support. All the buffered writes are - still system wide and not per group. Hence we will not see service - differentiation between buffered writes between groups. +Writeback +========= + +Page cache is dirtied through buffered writes and shared mmaps and +written asynchronously to the backing filesystem by the writeback +mechanism. Writeback sits between the memory and IO domains and +regulates the proportion of dirty memory by balancing dirtying and +write IOs. + +On traditional cgroup hierarchies, relationships between different +controllers cannot be established making it impossible for writeback +to operate accounting for cgroup resource restrictions and all +writeback IOs are attributed to the root cgroup. + +If both the blkio and memory controllers are used on the v2 hierarchy +and the filesystem supports cgroup writeback, writeback operations +correctly follow the resource restrictions imposed by both memory and +blkio controllers. + +Writeback examines both system-wide and per-cgroup dirty memory status +and enforces the more restrictive of the two. Also, writeback control +parameters which are absolute values - vm.dirty_bytes and +vm.dirty_background_bytes - are distributed across cgroups according +to their current writeback bandwidth. + +There's a peculiarity stemming from the discrepancy in ownership +granularity between memory controller and writeback. While memory +controller tracks ownership per page, writeback operates on inode +basis. cgroup writeback bridges the gap by tracking ownership by +inode but migrating ownership if too many foreign pages, pages which +don't match the current inode ownership, have been encountered while +writing back the inode. + +This is a conscious design choice as writeback operations are +inherently tied to inodes making strictly following page ownership +complicated and inefficient. The only use case which suffers from +this compromise is multiple cgroups concurrently dirtying disjoint +regions of the same inode, which is an unlikely use case and decided +to be unsupported. Note that as memory controller assigns page +ownership on the first use and doesn't update it until the page is +released, even if cgroup writeback strictly follows page ownership, +multiple cgroups dirtying overlapping areas wouldn't work as expected. +In general, write-sharing an inode across multiple cgroups is not well +supported. + +Filesystem support for cgroup writeback +--------------------------------------- + +A filesystem can make writeback IOs cgroup-aware by updating +address_space_operations->writepage[s]() to annotate bio's using the +following two functions. + +* wbc_init_bio(@wbc, @bio) + + Should be called for each bio carrying writeback data and associates + the bio with the inode's owner cgroup. Can be called anytime + between bio allocation and submission. + +* wbc_account_io(@wbc, @page, @bytes) + + Should be called for each data segment being written out. While + this function doesn't care exactly when it's called during the + writeback session, it's the easiest and most natural to call it as + data segments are added to a bio. + +With writeback bio's annotated, cgroup support can be enabled per +super_block by setting MS_CGROUPWB in ->s_flags. This allows for +selective disabling of cgroup writeback support which is helpful when +certain filesystem features, e.g. journaled data mode, are +incompatible. + +wbc_init_bio() binds the specified bio to its cgroup. Depending on +the configuration, the bio may be executed at a lower priority and if +the writeback session is holding shared resources, e.g. a journal +entry, may lead to priority inversion. There is no one easy solution +for the problem. Filesystems can try to work around specific problem +cases by skipping wbc_init_bio() or using bio_associate_blkcg() +directly. diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index f456b43..ff71e16 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -493,6 +493,7 @@ pgpgin - # of charging events to the memory cgroup. The charging pgpgout - # of uncharging events to the memory cgroup. The uncharging event happens each time a page is unaccounted from the cgroup. swap - # of bytes of swap usage +dirty - # of bytes that are waiting to get written back to the disk. writeback - # of bytes of file/anon cache that are queued for syncing to disk. inactive_anon - # of bytes of anonymous and swap cache memory on inactive diff --git a/block/bio.c b/block/bio.c index 259197d..2a00d34 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1988,6 +1988,28 @@ struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_ EXPORT_SYMBOL(bioset_create_nobvec); #ifdef CONFIG_BLK_CGROUP + +/** + * bio_associate_blkcg - associate a bio with the specified blkcg + * @bio: target bio + * @blkcg_css: css of the blkcg to associate + * + * Associate @bio with the blkcg specified by @blkcg_css. Block layer will + * treat @bio as if it were issued by a task which belongs to the blkcg. + * + * This function takes an extra reference of @blkcg_css which will be put + * when @bio is released. The caller must own @bio and is responsible for + * synchronizing calls to this function. + */ +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) +{ + if (unlikely(bio->bi_css)) + return -EBUSY; + css_get(blkcg_css); + bio->bi_css = blkcg_css; + return 0; +} + /** * bio_associate_current - associate a bio with %current * @bio: target bio @@ -2004,26 +2026,17 @@ EXPORT_SYMBOL(bioset_create_nobvec); int bio_associate_current(struct bio *bio) { struct io_context *ioc; - struct cgroup_subsys_state *css; - if (bio->bi_ioc) + if (bio->bi_css) return -EBUSY; ioc = current->io_context; if (!ioc) return -ENOENT; - /* acquire active ref on @ioc and associate */ get_io_context_active(ioc); bio->bi_ioc = ioc; - - /* associate blkcg if exists */ - rcu_read_lock(); - css = task_css(current, blkio_cgrp_id); - if (css && css_tryget_online(css)) - bio->bi_css = css; - rcu_read_unlock(); - + bio->bi_css = task_get_css(current, blkio_cgrp_id); return 0; } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 6e43fa3..9f97da5 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -19,11 +19,12 @@ #include <linux/module.h> #include <linux/err.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/genhd.h> #include <linux/delay.h> #include <linux/atomic.h> -#include "blk-cgroup.h" +#include <linux/blk-cgroup.h> #include "blk.h" #define MAX_KEY_LEN 100 @@ -33,6 +34,8 @@ static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); +struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; + static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static bool blkcg_policy_enabled(struct request_queue *q, @@ -182,6 +185,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; + struct bdi_writeback_congested *wb_congested; int i, ret; WARN_ON_ONCE(!rcu_read_lock_held()); @@ -193,22 +197,30 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, goto err_free_blkg; } + wb_congested = wb_congested_get_create(&q->backing_dev_info, + blkcg->css.id, GFP_ATOMIC); + if (!wb_congested) { + ret = -ENOMEM; + goto err_put_css; + } + /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, q, GFP_ATOMIC); if (unlikely(!new_blkg)) { ret = -ENOMEM; - goto err_put_css; + goto err_put_congested; } } blkg = new_blkg; + blkg->wb_congested = wb_congested; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false); if (WARN_ON_ONCE(!blkg->parent)) { ret = -EINVAL; - goto err_put_css; + goto err_put_congested; } blkg_get(blkg->parent); } @@ -238,18 +250,15 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg->online = true; spin_unlock(&blkcg->lock); - if (!ret) { - if (blkcg == &blkcg_root) { - q->root_blkg = blkg; - q->root_rl.blkg = blkg; - } + if (!ret) return blkg; - } /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); +err_put_congested: + wb_congested_put(wb_congested); err_put_css: css_put(&blkcg->css); err_free_blkg: @@ -343,15 +352,6 @@ static void blkg_destroy(struct blkcg_gq *blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* - * If root blkg is destroyed. Just clear the pointer since root_rl - * does not take reference on root blkg. - */ - if (blkcg == &blkcg_root) { - blkg->q->root_blkg = NULL; - blkg->q->root_rl.blkg = NULL; - } - - /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ @@ -405,6 +405,8 @@ void __blkg_release_rcu(struct rcu_head *rcu_head) if (blkg->parent) blkg_put(blkg->parent); + wb_congested_put(blkg->wb_congested); + blkg_free(blkg); } EXPORT_SYMBOL_GPL(__blkg_release_rcu); @@ -812,6 +814,8 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css) } spin_unlock_irq(&blkcg->lock); + + wb_blkcg_offline(blkcg); } static void blkcg_css_free(struct cgroup_subsys_state *css) @@ -868,7 +872,9 @@ done: spin_lock_init(&blkcg->lock); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&blkcg->blkg_list); - +#ifdef CONFIG_CGROUP_WRITEBACK + INIT_LIST_HEAD(&blkcg->cgwb_list); +#endif return &blkcg->css; free_pd_blkcg: @@ -892,9 +898,45 @@ free_blkcg: */ int blkcg_init_queue(struct request_queue *q) { - might_sleep(); + struct blkcg_gq *new_blkg, *blkg; + bool preloaded; + int ret; + + new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL); + if (!new_blkg) + return -ENOMEM; + + preloaded = !radix_tree_preload(GFP_KERNEL); + + /* + * Make sure the root blkg exists and count the existing blkgs. As + * @q is bypassing at this point, blkg_lookup_create() can't be + * used. Open code insertion. + */ + rcu_read_lock(); + spin_lock_irq(q->queue_lock); + blkg = blkg_create(&blkcg_root, q, new_blkg); + spin_unlock_irq(q->queue_lock); + rcu_read_unlock(); + + if (preloaded) + radix_tree_preload_end(); + + if (IS_ERR(blkg)) { + kfree(new_blkg); + return PTR_ERR(blkg); + } - return blk_throtl_init(q); + q->root_blkg = blkg; + q->root_rl.blkg = blkg; + + ret = blk_throtl_init(q); + if (ret) { + spin_lock_irq(q->queue_lock); + blkg_destroy_all(q); + spin_unlock_irq(q->queue_lock); + } + return ret; } /** @@ -996,50 +1038,19 @@ int blkcg_activate_policy(struct request_queue *q, { LIST_HEAD(pds); LIST_HEAD(cpds); - struct blkcg_gq *blkg, *new_blkg; + struct blkcg_gq *blkg; struct blkg_policy_data *pd, *nd; struct blkcg_policy_data *cpd, *cnd; int cnt = 0, ret; - bool preloaded; if (blkcg_policy_enabled(q, pol)) return 0; - /* preallocations for root blkg */ - new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL); - if (!new_blkg) - return -ENOMEM; - + /* count and allocate policy_data for all existing blkgs */ blk_queue_bypass_start(q); - - preloaded = !radix_tree_preload(GFP_KERNEL); - - /* - * Make sure the root blkg exists and count the existing blkgs. As - * @q is bypassing at this point, blkg_lookup_create() can't be - * used. Open code it. - */ spin_lock_irq(q->queue_lock); - - rcu_read_lock(); - blkg = __blkg_lookup(&blkcg_root, q, false); - if (blkg) - blkg_free(new_blkg); - else - blkg = blkg_create(&blkcg_root, q, new_blkg); - rcu_read_unlock(); - - if (preloaded) - radix_tree_preload_end(); - - if (IS_ERR(blkg)) { - ret = PTR_ERR(blkg); - goto out_unlock; - } - list_for_each_entry(blkg, &q->blkg_list, q_node) cnt++; - spin_unlock_irq(q->queue_lock); /* @@ -1140,10 +1151,6 @@ void blkcg_deactivate_policy(struct request_queue *q, __clear_bit(pol->plid, q->blkcg_pols); - /* if no policy is left, no need for blkgs - shoot them down */ - if (bitmap_empty(q->blkcg_pols, BLKCG_MAX_POLS)) - blkg_destroy_all(q); - list_for_each_entry(blkg, &q->blkg_list, q_node) { /* grab blkcg lock too while removing @pd from @blkg */ spin_lock(&blkg->blkcg->lock); diff --git a/block/blk-core.c b/block/blk-core.c index f6ab750..688ae94 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -32,12 +32,12 @@ #include <linux/delay.h> #include <linux/ratelimit.h> #include <linux/pm_runtime.h> +#include <linux/blk-cgroup.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> #include "blk.h" -#include "blk-cgroup.h" #include "blk-mq.h" EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); @@ -63,6 +63,31 @@ struct kmem_cache *blk_requestq_cachep; */ static struct workqueue_struct *kblockd_workqueue; +static void blk_clear_congested(struct request_list *rl, int sync) +{ +#ifdef CONFIG_CGROUP_WRITEBACK + clear_wb_congested(rl->blkg->wb_congested, sync); +#else + /* + * If !CGROUP_WRITEBACK, all blkg's map to bdi->wb and we shouldn't + * flip its congestion state for events on other blkcgs. + */ + if (rl == &rl->q->root_rl) + clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync); +#endif +} + +static void blk_set_congested(struct request_list *rl, int sync) +{ +#ifdef CONFIG_CGROUP_WRITEBACK + set_wb_congested(rl->blkg->wb_congested, sync); +#else + /* see blk_clear_congested() */ + if (rl == &rl->q->root_rl) + set_wb_congested(rl->q->backing_dev_info.wb.congested, sync); +#endif +} + void blk_queue_congestion_threshold(struct request_queue *q) { int nr; @@ -623,8 +648,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; - q->backing_dev_info.state = 0; - q->backing_dev_info.capabilities = 0; + q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK; q->backing_dev_info.name = "block"; q->node = node_id; @@ -847,13 +871,8 @@ static void __freed_request(struct request_list *rl, int sync) { struct request_queue *q = rl->q; - /* - * bdi isn't aware of blkcg yet. As all async IOs end up root - * blkcg anyway, just use root blkcg state. - */ - if (rl == &q->root_rl && - rl->count[sync] < queue_congestion_off_threshold(q)) - blk_clear_queue_congested(q, sync); + if (rl->count[sync] < queue_congestion_off_threshold(q)) + blk_clear_congested(rl, sync); if (rl->count[sync] + 1 <= q->nr_requests) { if (waitqueue_active(&rl->wait[sync])) @@ -886,25 +905,25 @@ static void freed_request(struct request_list *rl, unsigned int flags) int blk_update_nr_requests(struct request_queue *q, unsigned int nr) { struct request_list *rl; + int on_thresh, off_thresh; spin_lock_irq(q->queue_lock); q->nr_requests = nr; blk_queue_congestion_threshold(q); + on_thresh = queue_congestion_on_threshold(q); + off_thresh = queue_congestion_off_threshold(q); - /* congestion isn't cgroup aware and follows root blkcg for now */ - rl = &q->root_rl; - - if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q)) - blk_set_queue_congested(q, BLK_RW_SYNC); - else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q)) - blk_clear_queue_congested(q, BLK_RW_SYNC); + blk_queue_for_each_rl(rl, q) { + if (rl->count[BLK_RW_SYNC] >= on_thresh) + blk_set_congested(rl, BLK_RW_SYNC); + else if (rl->count[BLK_RW_SYNC] < off_thresh) + blk_clear_congested(rl, BLK_RW_SYNC); - if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q)) - blk_set_queue_congested(q, BLK_RW_ASYNC); - else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q)) - blk_clear_queue_congested(q, BLK_RW_ASYNC); + if (rl->count[BLK_RW_ASYNC] >= on_thresh) + blk_set_congested(rl, BLK_RW_ASYNC); + else if (rl->count[BLK_RW_ASYNC] < off_thresh) + blk_clear_congested(rl, BLK_RW_ASYNC); - blk_queue_for_each_rl(rl, q) { if (rl->count[BLK_RW_SYNC] >= q->nr_requests) { blk_set_rl_full(rl, BLK_RW_SYNC); } else { @@ -1014,12 +1033,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags, } } } - /* - * bdi isn't aware of blkcg yet. As all async IOs end up - * root blkcg anyway, just use root blkcg state. - */ - if (rl == &q->root_rl) - blk_set_queue_congested(q, is_sync); + blk_set_congested(rl, is_sync); } /* diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 79ffb48..f548b64 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -21,6 +21,7 @@ */ #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/mempool.h> #include <linux/bio.h> #include <linux/scatterlist.h> diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 2b8fd30..6264b38 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -6,11 +6,12 @@ #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/blktrace_api.h> #include <linux/blk-mq.h> +#include <linux/blk-cgroup.h> #include "blk.h" -#include "blk-cgroup.h" #include "blk-mq.h" struct queue_sysfs_entry { diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 5b9c6d5..b231935 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -9,7 +9,7 @@ #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/blktrace_api.h> -#include "blk-cgroup.h" +#include <linux/blk-cgroup.h> #include "blk.h" /* Max dispatch from a group in 1 round */ diff --git a/block/bounce.c b/block/bounce.c index 3ab0bce..b173112 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -13,6 +13,7 @@ #include <linux/pagemap.h> #include <linux/mempool.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index d8ad45ccd..c62bb2e 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -14,8 +14,8 @@ #include <linux/rbtree.h> #include <linux/ioprio.h> #include <linux/blktrace_api.h> +#include <linux/blk-cgroup.h> #include "blk.h" -#include "blk-cgroup.h" /* * tunables diff --git a/block/elevator.c b/block/elevator.c index 942579d..84d6394 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -35,11 +35,11 @@ #include <linux/hash.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> +#include <linux/blk-cgroup.h> #include <trace/events/block.h> #include "blk.h" -#include "blk-cgroup.h" static DEFINE_SPINLOCK(elv_list_lock); static LIST_HEAD(elv_list); diff --git a/block/genhd.c b/block/genhd.c index ea982ea..59a1395 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -8,6 +8,7 @@ #include <linux/kdev_t.h> #include <linux/kernel.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/proc_fs.h> diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index b905e98..efd19c2 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -38,6 +38,7 @@ #include <linux/mutex.h> #include <linux/major.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/genhd.h> #include <linux/idr.h> #include <net/tcp.h> diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 81fde9e..a151853 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2359,7 +2359,7 @@ static void drbd_cleanup(void) * @congested_data: User data * @bdi_bits: Bits the BDI flusher thread is currently interested in * - * Returns 1<<BDI_async_congested and/or 1<<BDI_sync_congested if we are congested. + * Returns 1<<WB_async_congested and/or 1<<WB_sync_congested if we are congested. */ static int drbd_congested(void *congested_data, int bdi_bits) { @@ -2376,14 +2376,14 @@ static int drbd_congested(void *congested_data, int bdi_bits) } if (test_bit(CALLBACK_PENDING, &first_peer_device(device)->connection->flags)) { - r |= (1 << BDI_async_congested); + r |= (1 << WB_async_congested); /* Without good local data, we would need to read from remote, * and that would need the worker thread as well, which is * currently blocked waiting for that usermode helper to * finish. */ if (!get_ldev_if_state(device, D_UP_TO_DATE)) - r |= (1 << BDI_sync_congested); + r |= (1 << WB_sync_congested); else put_ldev(device); r &= bdi_bits; @@ -2399,9 +2399,9 @@ static int drbd_congested(void *congested_data, int bdi_bits) reason = 'b'; } - if (bdi_bits & (1 << BDI_async_congested) && + if (bdi_bits & (1 << WB_async_congested) && test_bit(NET_CONGESTED, &first_peer_device(device)->connection->flags)) { - r |= (1 << BDI_async_congested); + r |= (1 << WB_async_congested); reason = reason == 'b' ? 'a' : 'n'; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 09e628da..4c20c22 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -61,6 +61,7 @@ #include <linux/freezer.h> #include <linux/mutex.h> #include <linux/slab.h> +#include <linux/backing-dev.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_ioctl.h> #include <scsi/scsi.h> diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 5fc291c6..60316fb 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -12,6 +12,7 @@ #include <linux/fs.h> #include <linux/major.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/module.h> #include <linux/raw.h> #include <linux/capability.h> diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 1616f66..4afb2d2 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/hash.h> #include <linux/random.h> +#include <linux/backing-dev.h> #include <trace/events/bcache.h> diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4d6f089..d728299 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2080,7 +2080,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits) * the query about congestion status of request_queue */ if (dm_request_based(md)) - r = md->queue->backing_dev_info.state & + r = md->queue->backing_dev_info.wb.state & bdi_bits; else r = dm_table_any_congested(map, bdi_bits); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index e6e66d0..7fff744 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -14,6 +14,7 @@ #include <linux/device-mapper.h> #include <linux/list.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/hdreg.h> #include <linux/completion.h> #include <linux/kobject.h> diff --git a/drivers/md/md.h b/drivers/md/md.h index 4046a6c..7da6e9c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -16,6 +16,7 @@ #define _MD_MD_H #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/kobject.h> #include <linux/list.h> #include <linux/mm.h> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 9157a29..f80f1af 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -745,7 +745,7 @@ static int raid1_congested(struct mddev *mddev, int bits) struct r1conf *conf = mddev->private; int i, ret = 0; - if ((bits & (1 << BDI_async_congested)) && + if ((bits & (1 << WB_async_congested)) && conf->pending_count >= max_queued_requests) return 1; @@ -760,7 +760,7 @@ static int raid1_congested(struct mddev *mddev, int bits) /* Note the '|| 1' - when read_balance prefers * non-congested targets, it can be removed */ - if ((bits & (1<<BDI_async_congested)) || 1) + if ((bits & (1 << WB_async_congested)) || 1) ret |= bdi_congested(&q->backing_dev_info, bits); else ret &= bdi_congested(&q->backing_dev_info, bits); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index f55c3f3..188d8e9 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -914,7 +914,7 @@ static int raid10_congested(struct mddev *mddev, int bits) struct r10conf *conf = mddev->private; int i, ret = 0; - if ((bits & (1 << BDI_async_congested)) && + if ((bits & (1 << WB_async_congested)) && conf->pending_count >= max_queued_requests) return 1; diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index b16f3cd..e2c0057 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/fs.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/pagemap.h> #include <linux/list.h> diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h b/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h index d726058..1456278 100644 --- a/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h +++ b/drivers/staging/lustre/lustre/include/linux/lustre_patchless_compat.h @@ -55,9 +55,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) if (PagePrivate(page)) page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE); - if (TestClearPageDirty(page)) - account_page_cleaned(page, mapping); - + cancel_dirty_page(page); ClearPageMappedToDisk(page); ll_delete_from_page_cache(page); } diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 620d934..8aa56bb 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -320,31 +320,21 @@ fail_option_alloc: struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, const char *dev_name, char *data) { - int retval = -EINVAL; struct p9_fid *fid; - int rc; + int rc = -ENOMEM; v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL); if (!v9ses->uname) - return ERR_PTR(-ENOMEM); + goto err_names; v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL); - if (!v9ses->aname) { - kfree(v9ses->uname); - return ERR_PTR(-ENOMEM); - } + if (!v9ses->aname) + goto err_names; init_rwsem(&v9ses->rename_sem); rc = bdi_setup_and_register(&v9ses->bdi, "9p"); - if (rc) { - kfree(v9ses->aname); - kfree(v9ses->uname); - return ERR_PTR(rc); - } - - spin_lock(&v9fs_sessionlist_lock); - list_add(&v9ses->slist, &v9fs_sessionlist); - spin_unlock(&v9fs_sessionlist_lock); + if (rc) + goto err_names; v9ses->uid = INVALID_UID; v9ses->dfltuid = V9FS_DEFUID; @@ -352,10 +342,9 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, v9ses->clnt = p9_client_create(dev_name, data); if (IS_ERR(v9ses->clnt)) { - retval = PTR_ERR(v9ses->clnt); - v9ses->clnt = NULL; + rc = PTR_ERR(v9ses->clnt); p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n"); - goto error; + goto err_bdi; } v9ses->flags = V9FS_ACCESS_USER; @@ -368,10 +357,8 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, } rc = v9fs_parse_options(v9ses, data); - if (rc < 0) { - retval = rc; - goto error; - } + if (rc < 0) + goto err_clnt; v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ; @@ -405,10 +392,9 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID, v9ses->aname); if (IS_ERR(fid)) { - retval = PTR_ERR(fid); - fid = NULL; + rc = PTR_ERR(fid); p9_debug(P9_DEBUG_ERROR, "cannot attach\n"); - goto error; + goto err_clnt; } if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE) @@ -420,12 +406,20 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, /* register the session for caching */ v9fs_cache_session_get_cookie(v9ses); #endif + spin_lock(&v9fs_sessionlist_lock); + list_add(&v9ses->slist, &v9fs_sessionlist); + spin_unlock(&v9fs_sessionlist_lock); return fid; -error: +err_clnt: + p9_client_destroy(v9ses->clnt); +err_bdi: bdi_destroy(&v9ses->bdi); - return ERR_PTR(retval); +err_names: + kfree(v9ses->uname); + kfree(v9ses->aname); + return ERR_PTR(rc); } /** diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index e99a338..bf495ce 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -130,11 +130,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, fid = v9fs_session_init(v9ses, dev_name, data); if (IS_ERR(fid)) { retval = PTR_ERR(fid); - /* - * we need to call session_close to tear down some - * of the data structure setup by session_init - */ - goto close_session; + goto free_session; } sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses); @@ -195,8 +191,8 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, clunk_fid: p9_client_clunk(fid); -close_session: v9fs_session_close(v9ses); +free_session: kfree(v9ses); return ERR_PTR(retval); diff --git a/fs/block_dev.c b/fs/block_dev.c index c7e4163..f04c873 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -14,6 +14,7 @@ #include <linux/device_cgroup.h> #include <linux/highmem.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/module.h> #include <linux/blkpg.h> #include <linux/magic.h> @@ -546,7 +547,8 @@ static struct file_system_type bd_type = { .kill_sb = kill_anon_super, }; -static struct super_block *blockdev_superblock __read_mostly; +struct super_block *blockdev_superblock __read_mostly; +EXPORT_SYMBOL_GPL(blockdev_superblock); void __init bdev_cache_init(void) { @@ -687,11 +689,6 @@ static struct block_device *bd_acquire(struct inode *inode) return bdev; } -int sb_is_blkdev_sb(struct super_block *sb) -{ - return sb == blockdev_superblock; -} - /* Call when you free inode */ void bd_forget(struct inode *inode) diff --git a/fs/buffer.c b/fs/buffer.c index f96173a..1cf7a53 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -30,6 +30,7 @@ #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> +#include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> @@ -44,6 +45,9 @@ #include <trace/events/block.h> static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); +static int submit_bh_wbc(int rw, struct buffer_head *bh, + unsigned long bio_flags, + struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) @@ -623,21 +627,22 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); * * If warn is true, then emit a warning if the page is not uptodate and has * not been truncated. + * + * The caller must hold mem_cgroup_begin_page_stat() lock. */ -static void __set_page_dirty(struct page *page, - struct address_space *mapping, int warn) +static void __set_page_dirty(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg, int warn) { unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); - account_page_dirtied(page, mapping); + account_page_dirtied(page, mapping, memcg); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } spin_unlock_irqrestore(&mapping->tree_lock, flags); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } /* @@ -668,6 +673,7 @@ static void __set_page_dirty(struct page *page, int __set_page_dirty_buffers(struct page *page) { int newly_dirty; + struct mem_cgroup *memcg; struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) @@ -683,11 +689,22 @@ int __set_page_dirty_buffers(struct page *page) bh = bh->b_this_page; } while (bh != head); } + /* + * Use mem_group_begin_page_stat() to keep PageDirty synchronized with + * per-memcg dirty page counters. + */ + memcg = mem_cgroup_begin_page_stat(page); newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); if (newly_dirty) - __set_page_dirty(page, mapping, 1); + __set_page_dirty(page, mapping, memcg, 1); + + mem_cgroup_end_page_stat(memcg); + + if (newly_dirty) + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + return newly_dirty; } EXPORT_SYMBOL(__set_page_dirty_buffers); @@ -1158,11 +1175,18 @@ void mark_buffer_dirty(struct buffer_head *bh) if (!test_set_buffer_dirty(bh)) { struct page *page = bh->b_page; + struct address_space *mapping = NULL; + struct mem_cgroup *memcg; + + memcg = mem_cgroup_begin_page_stat(page); if (!TestSetPageDirty(page)) { - struct address_space *mapping = page_mapping(page); + mapping = page_mapping(page); if (mapping) - __set_page_dirty(page, mapping, 0); + __set_page_dirty(page, mapping, memcg, 0); } + mem_cgroup_end_page_stat(memcg); + if (mapping) + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); @@ -1684,8 +1708,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, struct buffer_head *bh, *head; unsigned int blocksize, bbits; int nr_underway = 0; - int write_op = (wbc->sync_mode == WB_SYNC_ALL ? - WRITE_SYNC : WRITE); + int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); @@ -1774,7 +1797,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { - submit_bh(write_op, bh); + submit_bh_wbc(write_op, bh, 0, wbc); nr_underway++; } bh = next; @@ -1828,7 +1851,7 @@ recover: struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); - submit_bh(write_op, bh); + submit_bh_wbc(write_op, bh, 0, wbc); nr_underway++; } bh = next; @@ -2993,7 +3016,8 @@ void guard_bio_eod(int rw, struct bio *bio) } } -int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) +static int submit_bh_wbc(int rw, struct buffer_head *bh, + unsigned long bio_flags, struct writeback_control *wbc) { struct bio *bio; @@ -3015,6 +3039,11 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) */ bio = bio_alloc(GFP_NOIO, 1); + if (wbc) { + wbc_init_bio(wbc, bio); + wbc_account_io(wbc, bh->b_page, bh->b_size); + } + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_bdev = bh->b_bdev; bio->bi_io_vec[0].bv_page = bh->b_page; @@ -3039,11 +3068,16 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) submit_bio(rw, bio); return 0; } + +int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags) +{ + return submit_bh_wbc(rw, bh, bio_flags, NULL); +} EXPORT_SYMBOL_GPL(_submit_bh); int submit_bh(int rw, struct buffer_head *bh) { - return _submit_bh(rw, bh, 0); + return submit_bh_wbc(rw, bh, 0, NULL); } EXPORT_SYMBOL(submit_bh); @@ -3232,8 +3266,8 @@ int try_to_free_buffers(struct page *page) * to synchronise against __set_page_dirty_buffers and prevent the * dirty bit from being lost. */ - if (ret && TestClearPageDirty(page)) - account_page_cleaned(page, mapping); + if (ret) + cancel_dirty_page(page); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { diff --git a/fs/ext2/super.c b/fs/ext2/super.c index d0e746e..900e19c 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -882,6 +882,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | ((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); + sb->s_iflags |= SB_I_CGROUPWB; if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV && (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) || diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d86d262..aadb728 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -39,6 +39,7 @@ #include <linux/slab.h> #include <asm/uaccess.h> #include <linux/fiemap.h> +#include <linux/backing-dev.h> #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1c535fa..f6aedf8 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -26,6 +26,7 @@ #include <linux/log2.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/backing-dev.h> #include <trace/events/ext4.h> #ifdef CONFIG_EXT4_DEBUG diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 90ec13f..a7b4b6e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/parser.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index d9c5242..7dd63b7 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -53,7 +53,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) PAGE_CACHE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == DIRTY_DENTS) { - if (sbi->sb->s_bdi->dirty_exceeded) + if (sbi->sb->s_bdi->wb.dirty_exceeded) return false; mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); @@ -70,7 +70,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else { - if (sbi->sb->s_bdi->dirty_exceeded) + if (sbi->sb->s_bdi->wb.dirty_exceeded) return false; } return res; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 8496357..79e7b87 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -9,6 +9,7 @@ * published by the Free Software Foundation. */ #include <linux/blkdev.h> +#include <linux/backing-dev.h> /* constant macro */ #define NULL_SEGNO ((unsigned int)(~0)) @@ -714,7 +715,7 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi) */ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) { - if (sbi->sb->s_bdi->dirty_exceeded) + if (sbi->sb->s_bdi->wb.dirty_exceeded) return 0; if (type == DATA) diff --git a/fs/fat/file.c b/fs/fat/file.c index 442d50a..a08f103 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -11,6 +11,7 @@ #include <linux/compat.h> #include <linux/mount.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/fsnotify.h> #include <linux/security.h> #include "fat.h" diff --git a/fs/fat/inode.c b/fs/fat/inode.c index c067746..509411d 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -18,6 +18,7 @@ #include <linux/parser.h> #include <linux/uio.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <asm/unaligned.h> #include "fat.h" diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 32a8bbd..f0520bc 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -27,6 +27,7 @@ #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> +#include <linux/memcontrol.h> #include "internal.h" /* @@ -34,6 +35,10 @@ */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_CACHE_SHIFT - 10)) +struct wb_completion { + atomic_t cnt; +}; + /* * Passed into wb_writeback(), essentially a subset of writeback_control */ @@ -47,13 +52,29 @@ struct wb_writeback_work { unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + unsigned int auto_free:1; /* free on completion */ + unsigned int single_wait:1; + unsigned int single_done:1; enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ - struct completion *done; /* set if the caller waits */ + struct wb_completion *done; /* set if the caller waits */ }; /* + * If one wants to wait for one or more wb_writeback_works, each work's + * ->done should be set to a wb_completion defined using the following + * macro. Once all work items are issued with wb_queue_work(), the caller + * can wait for the completion of all using wb_wait_for_completion(). Work + * items which are waited upon aren't freed automatically on completion. + */ +#define DEFINE_WB_COMPLETION_ONSTACK(cmpl) \ + struct wb_completion cmpl = { \ + .cnt = ATOMIC_INIT(1), \ + } + + +/* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its @@ -65,35 +86,6 @@ struct wb_writeback_work { */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; -/** - * writeback_in_progress - determine whether there is writeback in progress - * @bdi: the device's backing_dev_info structure. - * - * Determine whether there is writeback waiting to be handled against a - * backing device. - */ -int writeback_in_progress(struct backing_dev_info *bdi) -{ - return test_bit(BDI_writeback_running, &bdi->state); -} -EXPORT_SYMBOL(writeback_in_progress); - -struct backing_dev_info *inode_to_bdi(struct inode *inode) -{ - struct super_block *sb; - - if (!inode) - return &noop_backing_dev_info; - - sb = inode->i_sb; -#ifdef CONFIG_BLOCK - if (sb_is_blkdev_sb(sb)) - return blk_get_backing_dev_info(I_BDEV(inode)); -#endif - return sb->s_bdi; -} -EXPORT_SYMBOL_GPL(inode_to_bdi); - static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_wb_list); @@ -109,45 +101,830 @@ static inline struct inode *wb_inode(struct list_head *head) EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); -static void bdi_wakeup_thread(struct backing_dev_info *bdi) +static bool wb_io_lists_populated(struct bdi_writeback *wb) +{ + if (wb_has_dirty_io(wb)) { + return false; + } else { + set_bit(WB_has_dirty_io, &wb->state); + WARN_ON_ONCE(!wb->avg_write_bandwidth); + atomic_long_add(wb->avg_write_bandwidth, + &wb->bdi->tot_write_bandwidth); + return true; + } +} + +static void wb_io_lists_depopulated(struct bdi_writeback *wb) { - spin_lock_bh(&bdi->wb_lock); - if (test_bit(BDI_registered, &bdi->state)) - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); - spin_unlock_bh(&bdi->wb_lock); + if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && + list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { + clear_bit(WB_has_dirty_io, &wb->state); + WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, + &wb->bdi->tot_write_bandwidth) < 0); + } } -static void bdi_queue_work(struct backing_dev_info *bdi, - struct wb_writeback_work *work) +/** + * inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list + * @inode: inode to be moved + * @wb: target bdi_writeback + * @head: one of @wb->b_{dirty|io|more_io} + * + * Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io. + * Returns %true if @inode is the first occupant of the !dirty_time IO + * lists; otherwise, %false. + */ +static bool inode_wb_list_move_locked(struct inode *inode, + struct bdi_writeback *wb, + struct list_head *head) { - trace_writeback_queue(bdi, work); + assert_spin_locked(&wb->list_lock); + + list_move(&inode->i_wb_list, head); - spin_lock_bh(&bdi->wb_lock); - if (!test_bit(BDI_registered, &bdi->state)) { - if (work->done) - complete(work->done); + /* dirty_time doesn't count as dirty_io until expiration */ + if (head != &wb->b_dirty_time) + return wb_io_lists_populated(wb); + + wb_io_lists_depopulated(wb); + return false; +} + +/** + * inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list + * @inode: inode to be removed + * @wb: bdi_writeback @inode is being removed from + * + * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and + * clear %WB_has_dirty_io if all are empty afterwards. + */ +static void inode_wb_list_del_locked(struct inode *inode, + struct bdi_writeback *wb) +{ + assert_spin_locked(&wb->list_lock); + + list_del_init(&inode->i_wb_list); + wb_io_lists_depopulated(wb); +} + +static void wb_wakeup(struct bdi_writeback *wb) +{ + spin_lock_bh(&wb->work_lock); + if (test_bit(WB_registered, &wb->state)) + mod_delayed_work(bdi_wq, &wb->dwork, 0); + spin_unlock_bh(&wb->work_lock); +} + +static void wb_queue_work(struct bdi_writeback *wb, + struct wb_writeback_work *work) +{ + trace_writeback_queue(wb->bdi, work); + + spin_lock_bh(&wb->work_lock); + if (!test_bit(WB_registered, &wb->state)) { + if (work->single_wait) + work->single_done = 1; goto out_unlock; } - list_add_tail(&work->list, &bdi->work_list); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + if (work->done) + atomic_inc(&work->done->cnt); + list_add_tail(&work->list, &wb->work_list); + mod_delayed_work(bdi_wq, &wb->dwork, 0); out_unlock: - spin_unlock_bh(&bdi->wb_lock); + spin_unlock_bh(&wb->work_lock); +} + +/** + * wb_wait_for_completion - wait for completion of bdi_writeback_works + * @bdi: bdi work items were issued to + * @done: target wb_completion + * + * Wait for one or more work items issued to @bdi with their ->done field + * set to @done, which should have been defined with + * DEFINE_WB_COMPLETION_ONSTACK(). This function returns after all such + * work items are completed. Work items which are waited upon aren't freed + * automatically on completion. + */ +static void wb_wait_for_completion(struct backing_dev_info *bdi, + struct wb_completion *done) +{ + atomic_dec(&done->cnt); /* put down the initial count */ + wait_event(bdi->wb_waitq, !atomic_read(&done->cnt)); +} + +#ifdef CONFIG_CGROUP_WRITEBACK + +/* parameters for foreign inode detection, see wb_detach_inode() */ +#define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ +#define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ +#define WB_FRN_TIME_CUT_DIV 2 /* ignore rounds < avg / 2 */ +#define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ + +#define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ +#define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) + /* each slot's duration is 2s / 16 */ +#define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) + /* if foreign slots >= 8, switch */ +#define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) + /* one round can affect upto 5 slots */ + +void __inode_attach_wb(struct inode *inode, struct page *page) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb = NULL; + + if (inode_cgwb_enabled(inode)) { + struct cgroup_subsys_state *memcg_css; + + if (page) { + memcg_css = mem_cgroup_css_from_page(page); + wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + } else { + /* must pin memcg_css, see wb_get_create() */ + memcg_css = task_get_css(current, memory_cgrp_id); + wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + css_put(memcg_css); + } + } + + if (!wb) + wb = &bdi->wb; + + /* + * There may be multiple instances of this function racing to + * update the same inode. Use cmpxchg() to tell the winner. + */ + if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) + wb_put(wb); +} + +/** + * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it + * @inode: inode of interest with i_lock held + * + * Returns @inode's wb with its list_lock held. @inode->i_lock must be + * held on entry and is released on return. The returned wb is guaranteed + * to stay @inode's associated wb until its list_lock is released. + */ +static struct bdi_writeback * +locked_inode_to_wb_and_lock_list(struct inode *inode) + __releases(&inode->i_lock) + __acquires(&wb->list_lock) +{ + while (true) { + struct bdi_writeback *wb = inode_to_wb(inode); + + /* + * inode_to_wb() association is protected by both + * @inode->i_lock and @wb->list_lock but list_lock nests + * outside i_lock. Drop i_lock and verify that the + * association hasn't changed after acquiring list_lock. + */ + wb_get(wb); + spin_unlock(&inode->i_lock); + spin_lock(&wb->list_lock); + wb_put(wb); /* not gonna deref it anymore */ + + /* i_wb may have changed inbetween, can't use inode_to_wb() */ + if (likely(wb == inode->i_wb)) + return wb; /* @inode already has ref */ + + spin_unlock(&wb->list_lock); + cpu_relax(); + spin_lock(&inode->i_lock); + } +} + +/** + * inode_to_wb_and_lock_list - determine an inode's wb and lock it + * @inode: inode of interest + * + * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held + * on entry. + */ +static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) + __acquires(&wb->list_lock) +{ + spin_lock(&inode->i_lock); + return locked_inode_to_wb_and_lock_list(inode); +} + +struct inode_switch_wbs_context { + struct inode *inode; + struct bdi_writeback *new_wb; + + struct rcu_head rcu_head; + struct work_struct work; +}; + +static void inode_switch_wbs_work_fn(struct work_struct *work) +{ + struct inode_switch_wbs_context *isw = + container_of(work, struct inode_switch_wbs_context, work); + struct inode *inode = isw->inode; + struct address_space *mapping = inode->i_mapping; + struct bdi_writeback *old_wb = inode->i_wb; + struct bdi_writeback *new_wb = isw->new_wb; + struct radix_tree_iter iter; + bool switched = false; + void **slot; + + /* + * By the time control reaches here, RCU grace period has passed + * since I_WB_SWITCH assertion and all wb stat update transactions + * between unlocked_inode_to_wb_begin/end() are guaranteed to be + * synchronizing against mapping->tree_lock. + * + * Grabbing old_wb->list_lock, inode->i_lock and mapping->tree_lock + * gives us exclusion against all wb related operations on @inode + * including IO list manipulations and stat updates. + */ + if (old_wb < new_wb) { + spin_lock(&old_wb->list_lock); + spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&new_wb->list_lock); + spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); + } + spin_lock(&inode->i_lock); + spin_lock_irq(&mapping->tree_lock); + + /* + * Once I_FREEING is visible under i_lock, the eviction path owns + * the inode and we shouldn't modify ->i_wb_list. + */ + if (unlikely(inode->i_state & I_FREEING)) + goto skip_switch; + + /* + * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points + * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to + * pages actually under underwriteback. + */ + radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, 0, + PAGECACHE_TAG_DIRTY) { + struct page *page = radix_tree_deref_slot_protected(slot, + &mapping->tree_lock); + if (likely(page) && PageDirty(page)) { + __dec_wb_stat(old_wb, WB_RECLAIMABLE); + __inc_wb_stat(new_wb, WB_RECLAIMABLE); + } + } + + radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, 0, + PAGECACHE_TAG_WRITEBACK) { + struct page *page = radix_tree_deref_slot_protected(slot, + &mapping->tree_lock); + if (likely(page)) { + WARN_ON_ONCE(!PageWriteback(page)); + __dec_wb_stat(old_wb, WB_WRITEBACK); + __inc_wb_stat(new_wb, WB_WRITEBACK); + } + } + + wb_get(new_wb); + + /* + * Transfer to @new_wb's IO list if necessary. The specific list + * @inode was on is ignored and the inode is put on ->b_dirty which + * is always correct including from ->b_dirty_time. The transfer + * preserves @inode->dirtied_when ordering. + */ + if (!list_empty(&inode->i_wb_list)) { + struct inode *pos; + + inode_wb_list_del_locked(inode, old_wb); + inode->i_wb = new_wb; + list_for_each_entry(pos, &new_wb->b_dirty, i_wb_list) + if (time_after_eq(inode->dirtied_when, + pos->dirtied_when)) + break; + inode_wb_list_move_locked(inode, new_wb, pos->i_wb_list.prev); + } else { + inode->i_wb = new_wb; + } + + /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ + inode->i_wb_frn_winner = 0; + inode->i_wb_frn_avg_time = 0; + inode->i_wb_frn_history = 0; + switched = true; +skip_switch: + /* + * Paired with load_acquire in unlocked_inode_to_wb_begin() and + * ensures that the new wb is visible if they see !I_WB_SWITCH. + */ + smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); + + spin_unlock_irq(&mapping->tree_lock); + spin_unlock(&inode->i_lock); + spin_unlock(&new_wb->list_lock); + spin_unlock(&old_wb->list_lock); + + if (switched) { + wb_wakeup(new_wb); + wb_put(old_wb); + } + wb_put(new_wb); + + iput(inode); + kfree(isw); +} + +static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) +{ + struct inode_switch_wbs_context *isw = container_of(rcu_head, + struct inode_switch_wbs_context, rcu_head); + + /* needs to grab bh-unsafe locks, bounce to work item */ + INIT_WORK(&isw->work, inode_switch_wbs_work_fn); + schedule_work(&isw->work); +} + +/** + * inode_switch_wbs - change the wb association of an inode + * @inode: target inode + * @new_wb_id: ID of the new wb + * + * Switch @inode's wb association to the wb identified by @new_wb_id. The + * switching is performed asynchronously and may fail silently. + */ +static void inode_switch_wbs(struct inode *inode, int new_wb_id) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + struct cgroup_subsys_state *memcg_css; + struct inode_switch_wbs_context *isw; + + /* noop if seems to be already in progress */ + if (inode->i_state & I_WB_SWITCH) + return; + + isw = kzalloc(sizeof(*isw), GFP_ATOMIC); + if (!isw) + return; + + /* find and pin the new wb */ + rcu_read_lock(); + memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); + if (memcg_css) + isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + rcu_read_unlock(); + if (!isw->new_wb) + goto out_free; + + /* while holding I_WB_SWITCH, no one else can update the association */ + spin_lock(&inode->i_lock); + if (inode->i_state & (I_WB_SWITCH | I_FREEING) || + inode_to_wb(inode) == isw->new_wb) { + spin_unlock(&inode->i_lock); + goto out_free; + } + inode->i_state |= I_WB_SWITCH; + spin_unlock(&inode->i_lock); + + ihold(inode); + isw->inode = inode; + + /* + * In addition to synchronizing among switchers, I_WB_SWITCH tells + * the RCU protected stat update paths to grab the mapping's + * tree_lock so that stat transfer can synchronize against them. + * Let's continue after I_WB_SWITCH is guaranteed to be visible. + */ + call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); + return; + +out_free: + if (isw->new_wb) + wb_put(isw->new_wb); + kfree(isw); +} + +/** + * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it + * @wbc: writeback_control of interest + * @inode: target inode + * + * @inode is locked and about to be written back under the control of @wbc. + * Record @inode's writeback context into @wbc and unlock the i_lock. On + * writeback completion, wbc_detach_inode() should be called. This is used + * to track the cgroup writeback context. + */ +void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) +{ + if (!inode_cgwb_enabled(inode)) { + spin_unlock(&inode->i_lock); + return; + } + + wbc->wb = inode_to_wb(inode); + wbc->inode = inode; + + wbc->wb_id = wbc->wb->memcg_css->id; + wbc->wb_lcand_id = inode->i_wb_frn_winner; + wbc->wb_tcand_id = 0; + wbc->wb_bytes = 0; + wbc->wb_lcand_bytes = 0; + wbc->wb_tcand_bytes = 0; + + wb_get(wbc->wb); + spin_unlock(&inode->i_lock); + + /* + * A dying wb indicates that the memcg-blkcg mapping has changed + * and a new wb is already serving the memcg. Switch immediately. + */ + if (unlikely(wb_dying(wbc->wb))) + inode_switch_wbs(inode, wbc->wb_id); +} + +/** + * wbc_detach_inode - disassociate wbc from inode and perform foreign detection + * @wbc: writeback_control of the just finished writeback + * + * To be called after a writeback attempt of an inode finishes and undoes + * wbc_attach_and_unlock_inode(). Can be called under any context. + * + * As concurrent write sharing of an inode is expected to be very rare and + * memcg only tracks page ownership on first-use basis severely confining + * the usefulness of such sharing, cgroup writeback tracks ownership + * per-inode. While the support for concurrent write sharing of an inode + * is deemed unnecessary, an inode being written to by different cgroups at + * different points in time is a lot more common, and, more importantly, + * charging only by first-use can too readily lead to grossly incorrect + * behaviors (single foreign page can lead to gigabytes of writeback to be + * incorrectly attributed). + * + * To resolve this issue, cgroup writeback detects the majority dirtier of + * an inode and transfers the ownership to it. To avoid unnnecessary + * oscillation, the detection mechanism keeps track of history and gives + * out the switch verdict only if the foreign usage pattern is stable over + * a certain amount of time and/or writeback attempts. + * + * On each writeback attempt, @wbc tries to detect the majority writer + * using Boyer-Moore majority vote algorithm. In addition to the byte + * count from the majority voting, it also counts the bytes written for the + * current wb and the last round's winner wb (max of last round's current + * wb, the winner from two rounds ago, and the last round's majority + * candidate). Keeping track of the historical winner helps the algorithm + * to semi-reliably detect the most active writer even when it's not the + * absolute majority. + * + * Once the winner of the round is determined, whether the winner is + * foreign or not and how much IO time the round consumed is recorded in + * inode->i_wb_frn_history. If the amount of recorded foreign IO time is + * over a certain threshold, the switch verdict is given. + */ +void wbc_detach_inode(struct writeback_control *wbc) +{ + struct bdi_writeback *wb = wbc->wb; + struct inode *inode = wbc->inode; + unsigned long avg_time, max_bytes, max_time; + u16 history; + int max_id; + + if (!wb) + return; + + history = inode->i_wb_frn_history; + avg_time = inode->i_wb_frn_avg_time; + + /* pick the winner of this round */ + if (wbc->wb_bytes >= wbc->wb_lcand_bytes && + wbc->wb_bytes >= wbc->wb_tcand_bytes) { + max_id = wbc->wb_id; + max_bytes = wbc->wb_bytes; + } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { + max_id = wbc->wb_lcand_id; + max_bytes = wbc->wb_lcand_bytes; + } else { + max_id = wbc->wb_tcand_id; + max_bytes = wbc->wb_tcand_bytes; + } + + /* + * Calculate the amount of IO time the winner consumed and fold it + * into the running average kept per inode. If the consumed IO + * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for + * deciding whether to switch or not. This is to prevent one-off + * small dirtiers from skewing the verdict. + */ + max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, + wb->avg_write_bandwidth); + if (avg_time) + avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - + (avg_time >> WB_FRN_TIME_AVG_SHIFT); + else + avg_time = max_time; /* immediate catch up on first run */ + + if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { + int slots; + + /* + * The switch verdict is reached if foreign wb's consume + * more than a certain proportion of IO time in a + * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot + * history mask where each bit represents one sixteenth of + * the period. Determine the number of slots to shift into + * history from @max_time. + */ + slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), + (unsigned long)WB_FRN_HIST_MAX_SLOTS); + history <<= slots; + if (wbc->wb_id != max_id) + history |= (1U << slots) - 1; + + /* + * Switch if the current wb isn't the consistent winner. + * If there are multiple closely competing dirtiers, the + * inode may switch across them repeatedly over time, which + * is okay. The main goal is avoiding keeping an inode on + * the wrong wb for an extended period of time. + */ + if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) + inode_switch_wbs(inode, max_id); + } + + /* + * Multiple instances of this function may race to update the + * following fields but we don't mind occassional inaccuracies. + */ + inode->i_wb_frn_winner = max_id; + inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); + inode->i_wb_frn_history = history; + + wb_put(wbc->wb); + wbc->wb = NULL; +} + +/** + * wbc_account_io - account IO issued during writeback + * @wbc: writeback_control of the writeback in progress + * @page: page being written out + * @bytes: number of bytes being written out + * + * @bytes from @page are about to written out during the writeback + * controlled by @wbc. Keep the book for foreign inode detection. See + * wbc_detach_inode(). + */ +void wbc_account_io(struct writeback_control *wbc, struct page *page, + size_t bytes) +{ + int id; + + /* + * pageout() path doesn't attach @wbc to the inode being written + * out. This is intentional as we don't want the function to block + * behind a slow cgroup. Ultimately, we want pageout() to kick off + * regular writeback instead of writing things out itself. + */ + if (!wbc->wb) + return; + + rcu_read_lock(); + id = mem_cgroup_css_from_page(page)->id; + rcu_read_unlock(); + + if (id == wbc->wb_id) { + wbc->wb_bytes += bytes; + return; + } + + if (id == wbc->wb_lcand_id) + wbc->wb_lcand_bytes += bytes; + + /* Boyer-Moore majority vote algorithm */ + if (!wbc->wb_tcand_bytes) + wbc->wb_tcand_id = id; + if (id == wbc->wb_tcand_id) + wbc->wb_tcand_bytes += bytes; + else + wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } -static void -__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - bool range_cyclic, enum wb_reason reason) +/** + * inode_congested - test whether an inode is congested + * @inode: inode to test for congestion + * @cong_bits: mask of WB_[a]sync_congested bits to test + * + * Tests whether @inode is congested. @cong_bits is the mask of congestion + * bits to test and the return value is the mask of set bits. + * + * If cgroup writeback is enabled for @inode, the congestion state is + * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg + * associated with @inode is congested; otherwise, the root wb's congestion + * state is used. + */ +int inode_congested(struct inode *inode, int cong_bits) +{ + /* + * Once set, ->i_wb never becomes NULL while the inode is alive. + * Start transaction iff ->i_wb is visible. + */ + if (inode && inode_to_wb_is_valid(inode)) { + struct bdi_writeback *wb; + bool locked, congested; + + wb = unlocked_inode_to_wb_begin(inode, &locked); + congested = wb_congested(wb, cong_bits); + unlocked_inode_to_wb_end(inode, locked); + return congested; + } + + return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); +} +EXPORT_SYMBOL_GPL(inode_congested); + +/** + * wb_wait_for_single_work - wait for completion of a single bdi_writeback_work + * @bdi: bdi the work item was issued to + * @work: work item to wait for + * + * Wait for the completion of @work which was issued to one of @bdi's + * bdi_writeback's. The caller must have set @work->single_wait before + * issuing it. This wait operates independently fo + * wb_wait_for_completion() and also disables automatic freeing of @work. + */ +static void wb_wait_for_single_work(struct backing_dev_info *bdi, + struct wb_writeback_work *work) +{ + if (WARN_ON_ONCE(!work->single_wait)) + return; + + wait_event(bdi->wb_waitq, work->single_done); + + /* + * Paired with smp_wmb() in wb_do_writeback() and ensures that all + * modifications to @work prior to assertion of ->single_done is + * visible to the caller once this function returns. + */ + smp_rmb(); +} + +/** + * wb_split_bdi_pages - split nr_pages to write according to bandwidth + * @wb: target bdi_writeback to split @nr_pages to + * @nr_pages: number of pages to write for the whole bdi + * + * Split @wb's portion of @nr_pages according to @wb's write bandwidth in + * relation to the total write bandwidth of all wb's w/ dirty inodes on + * @wb->bdi. + */ +static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) +{ + unsigned long this_bw = wb->avg_write_bandwidth; + unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); + + if (nr_pages == LONG_MAX) + return LONG_MAX; + + /* + * This may be called on clean wb's and proportional distribution + * may not make sense, just use the original @nr_pages in those + * cases. In general, we wanna err on the side of writing more. + */ + if (!tot_bw || this_bw >= tot_bw) + return nr_pages; + else + return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); +} + +/** + * wb_clone_and_queue_work - clone a wb_writeback_work and issue it to a wb + * @wb: target bdi_writeback + * @base_work: source wb_writeback_work + * + * Try to make a clone of @base_work and issue it to @wb. If cloning + * succeeds, %true is returned; otherwise, @base_work is issued directly + * and %false is returned. In the latter case, the caller is required to + * wait for @base_work's completion using wb_wait_for_single_work(). + * + * A clone is auto-freed on completion. @base_work never is. + */ +static bool wb_clone_and_queue_work(struct bdi_writeback *wb, + struct wb_writeback_work *base_work) { struct wb_writeback_work *work; + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + *work = *base_work; + work->auto_free = 1; + work->single_wait = 0; + } else { + work = base_work; + work->auto_free = 0; + work->single_wait = 1; + } + work->single_done = 0; + wb_queue_work(wb, work); + return work != base_work; +} + +/** + * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi + * @bdi: target backing_dev_info + * @base_work: wb_writeback_work to issue + * @skip_if_busy: skip wb's which already have writeback in progress + * + * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which + * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's + * distributed to the busy wbs according to each wb's proportion in the + * total active write bandwidth of @bdi. + */ +static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, + struct wb_writeback_work *base_work, + bool skip_if_busy) +{ + long nr_pages = base_work->nr_pages; + int next_blkcg_id = 0; + struct bdi_writeback *wb; + struct wb_iter iter; + + might_sleep(); + + if (!bdi_has_dirty_io(bdi)) + return; +restart: + rcu_read_lock(); + bdi_for_each_wb(wb, bdi, &iter, next_blkcg_id) { + if (!wb_has_dirty_io(wb) || + (skip_if_busy && writeback_in_progress(wb))) + continue; + + base_work->nr_pages = wb_split_bdi_pages(wb, nr_pages); + if (!wb_clone_and_queue_work(wb, base_work)) { + next_blkcg_id = wb->blkcg_css->id + 1; + rcu_read_unlock(); + wb_wait_for_single_work(bdi, base_work); + goto restart; + } + } + rcu_read_unlock(); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static struct bdi_writeback * +locked_inode_to_wb_and_lock_list(struct inode *inode) + __releases(&inode->i_lock) + __acquires(&wb->list_lock) +{ + struct bdi_writeback *wb = inode_to_wb(inode); + + spin_unlock(&inode->i_lock); + spin_lock(&wb->list_lock); + return wb; +} + +static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) + __acquires(&wb->list_lock) +{ + struct bdi_writeback *wb = inode_to_wb(inode); + + spin_lock(&wb->list_lock); + return wb; +} + +static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) +{ + return nr_pages; +} + +static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, + struct wb_writeback_work *base_work, + bool skip_if_busy) +{ + might_sleep(); + + if (bdi_has_dirty_io(bdi) && + (!skip_if_busy || !writeback_in_progress(&bdi->wb))) { + base_work->auto_free = 0; + base_work->single_wait = 0; + base_work->single_done = 0; + wb_queue_work(&bdi->wb, base_work); + } +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, + bool range_cyclic, enum wb_reason reason) +{ + struct wb_writeback_work *work; + + if (!wb_has_dirty_io(wb)) + return; + /* * This is WB_SYNC_NONE writeback, so if allocation fails just * wakeup the thread for old dirty data writeback */ work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) { - trace_writeback_nowork(bdi); - bdi_wakeup_thread(bdi); + trace_writeback_nowork(wb->bdi); + wb_wakeup(wb); return; } @@ -155,46 +932,29 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, work->nr_pages = nr_pages; work->range_cyclic = range_cyclic; work->reason = reason; + work->auto_free = 1; - bdi_queue_work(bdi, work); + wb_queue_work(wb, work); } /** - * bdi_start_writeback - start writeback - * @bdi: the backing device to write from - * @nr_pages: the number of pages to write - * @reason: reason why some writeback work was initiated - * - * Description: - * This does WB_SYNC_NONE opportunistic writeback. The IO is only - * started when this function returns, we make no guarantees on - * completion. Caller need not hold sb s_umount semaphore. - * - */ -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - enum wb_reason reason) -{ - __bdi_start_writeback(bdi, nr_pages, true, reason); -} - -/** - * bdi_start_background_writeback - start background writeback - * @bdi: the backing device to write from + * wb_start_background_writeback - start background writeback + * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When - * this function returns, it is only guaranteed that for given BDI + * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ -void bdi_start_background_writeback(struct backing_dev_info *bdi) +void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ - trace_writeback_wake_background(bdi); - bdi_wakeup_thread(bdi); + trace_writeback_wake_background(wb->bdi); + wb_wakeup(wb); } /* @@ -202,11 +962,11 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi) */ void inode_wb_list_del(struct inode *inode) { - struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb; - spin_lock(&bdi->wb.list_lock); - list_del_init(&inode->i_wb_list); - spin_unlock(&bdi->wb.list_lock); + wb = inode_to_wb_and_lock_list(inode); + inode_wb_list_del_locked(inode, wb); + spin_unlock(&wb->list_lock); } /* @@ -220,7 +980,6 @@ void inode_wb_list_del(struct inode *inode) */ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { - assert_spin_locked(&wb->list_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -228,7 +987,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } - list_move(&inode->i_wb_list, &wb->b_dirty); + inode_wb_list_move_locked(inode, wb, &wb->b_dirty); } /* @@ -236,8 +995,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { - assert_spin_locked(&wb->list_lock); - list_move(&inode->i_wb_list, &wb->b_more_io); + inode_wb_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) @@ -346,6 +1104,8 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work); moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, EXPIRE_DIRTY_ATIME, work); + if (moved) + wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, moved); } @@ -471,10 +1231,10 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, redirty_tail(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; - list_move(&inode->i_wb_list, &wb->b_dirty_time); + inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time); } else { /* The inode is clean. Remove from writeback lists. */ - list_del_init(&inode->i_wb_list); + inode_wb_list_del_locked(inode, wb); } } @@ -605,10 +1365,11 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; - spin_unlock(&inode->i_lock); + wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); + wbc_detach_inode(wbc); spin_lock(&wb->list_lock); spin_lock(&inode->i_lock); /* @@ -616,7 +1377,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, * touch it. See comment above for explanation. */ if (!(inode->i_state & I_DIRTY_ALL)) - list_del_init(&inode->i_wb_list); + inode_wb_list_del_locked(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: @@ -624,7 +1385,7 @@ out: return ret; } -static long writeback_chunk_size(struct backing_dev_info *bdi, +static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; @@ -645,8 +1406,8 @@ static long writeback_chunk_size(struct backing_dev_info *bdi, if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { - pages = min(bdi->avg_write_bandwidth / 2, - global_dirty_limit / DIRTY_SCOPE); + pages = min(wb->avg_write_bandwidth / 2, + global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); @@ -741,9 +1502,9 @@ static long writeback_sb_inodes(struct super_block *sb, continue; } inode->i_state |= I_SYNC; - spin_unlock(&inode->i_lock); + wbc_attach_and_unlock_inode(&wbc, inode); - write_chunk = writeback_chunk_size(wb->bdi, work); + write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; @@ -753,6 +1514,7 @@ static long writeback_sb_inodes(struct super_block *sb, */ __writeback_single_inode(inode, &wbc); + wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote += write_chunk - wbc.nr_to_write; spin_lock(&wb->list_lock); @@ -830,33 +1592,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, return nr_pages - work.nr_pages; } -static bool over_bground_thresh(struct backing_dev_info *bdi) -{ - unsigned long background_thresh, dirty_thresh; - - global_dirty_limits(&background_thresh, &dirty_thresh); - - if (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) > background_thresh) - return true; - - if (bdi_stat(bdi, BDI_RECLAIMABLE) > - bdi_dirty_limit(bdi, background_thresh)) - return true; - - return false; -} - -/* - * Called under wb->list_lock. If there are multiple wb per bdi, - * only the flusher working on the first wb should do it. - */ -static void wb_update_bandwidth(struct bdi_writeback *wb, - unsigned long start_time) -{ - __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time); -} - /* * Explicit flushing or periodic writeback of "old" data. * @@ -899,14 +1634,14 @@ static long wb_writeback(struct bdi_writeback *wb, * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && - !list_empty(&wb->bdi->work_list)) + !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ - if (work->for_background && !over_bground_thresh(wb->bdi)) + if (work->for_background && !wb_over_bg_thresh(wb)) break; /* @@ -970,18 +1705,17 @@ static long wb_writeback(struct bdi_writeback *wb, /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ -static struct wb_writeback_work * -get_next_work_item(struct backing_dev_info *bdi) +static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; - spin_lock_bh(&bdi->wb_lock); - if (!list_empty(&bdi->work_list)) { - work = list_entry(bdi->work_list.next, + spin_lock_bh(&wb->work_lock); + if (!list_empty(&wb->work_list)) { + work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } - spin_unlock_bh(&bdi->wb_lock); + spin_unlock_bh(&wb->work_lock); return work; } @@ -998,7 +1732,7 @@ static unsigned long get_nr_dirty_pages(void) static long wb_check_background_flush(struct bdi_writeback *wb) { - if (over_bground_thresh(wb->bdi)) { + if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, @@ -1053,25 +1787,33 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) */ static long wb_do_writeback(struct bdi_writeback *wb) { - struct backing_dev_info *bdi = wb->bdi; struct wb_writeback_work *work; long wrote = 0; - set_bit(BDI_writeback_running, &wb->bdi->state); - while ((work = get_next_work_item(bdi)) != NULL) { + set_bit(WB_writeback_running, &wb->state); + while ((work = get_next_work_item(wb)) != NULL) { + struct wb_completion *done = work->done; + bool need_wake_up = false; - trace_writeback_exec(bdi, work); + trace_writeback_exec(wb->bdi, work); wrote += wb_writeback(wb, work); - /* - * Notify the caller of completion if this is a synchronous - * work item, otherwise just free it. - */ - if (work->done) - complete(work->done); - else + if (work->single_wait) { + WARN_ON_ONCE(work->auto_free); + /* paired w/ rmb in wb_wait_for_single_work() */ + smp_wmb(); + work->single_done = 1; + need_wake_up = true; + } else if (work->auto_free) { kfree(work); + } + + if (done && atomic_dec_and_test(&done->cnt)) + need_wake_up = true; + + if (need_wake_up) + wake_up_all(&wb->bdi->wb_waitq); } /* @@ -1079,7 +1821,7 @@ static long wb_do_writeback(struct bdi_writeback *wb) */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); - clear_bit(BDI_writeback_running, &wb->bdi->state); + clear_bit(WB_writeback_running, &wb->state); return wrote; } @@ -1088,43 +1830,42 @@ static long wb_do_writeback(struct bdi_writeback *wb) * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ -void bdi_writeback_workfn(struct work_struct *work) +void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); - struct backing_dev_info *bdi = wb->bdi; long pages_written; - set_worker_desc("flush-%s", dev_name(bdi->dev)); + set_worker_desc("flush-%s", dev_name(wb->bdi->dev)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || - !test_bit(BDI_registered, &bdi->state))) { + !test_bit(WB_registered, &wb->state))) { /* - * The normal path. Keep writing back @bdi until its + * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken - * if @bdi is shutting down even when we're running off the + * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); - } while (!list_empty(&bdi->work_list)); + } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ - pages_written = writeback_inodes_wb(&bdi->wb, 1024, + pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } - if (!list_empty(&bdi->work_list)) + if (!list_empty(&wb->work_list)) mod_delayed_work(bdi_wq, &wb->dwork, 0); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) - bdi_wakeup_thread_delayed(bdi); + wb_wakeup_delayed(wb); current->flags &= ~PF_SWAPWRITE; } @@ -1142,9 +1883,15 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { + struct bdi_writeback *wb; + struct wb_iter iter; + if (!bdi_has_dirty_io(bdi)) continue; - __bdi_start_writeback(bdi, nr_pages, false, reason); + + bdi_for_each_wb(wb, bdi, &iter, 0) + wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages), + false, reason); } rcu_read_unlock(); } @@ -1173,9 +1920,12 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { - if (list_empty(&bdi->wb.b_dirty_time)) - continue; - bdi_wakeup_thread(bdi); + struct bdi_writeback *wb; + struct wb_iter iter; + + bdi_for_each_wb(wb, bdi, &iter, 0) + if (!list_empty(&bdi->wb.b_dirty_time)) + wb_wakeup(&bdi->wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); @@ -1249,7 +1999,6 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode) void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; - struct backing_dev_info *bdi = NULL; int dirtytime; trace_writeback_mark_inode_dirty(inode, flags); @@ -1289,6 +2038,8 @@ void __mark_inode_dirty(struct inode *inode, int flags) if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; + inode_attach_wb(inode, NULL); + if (flags & I_DIRTY_INODE) inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags; @@ -1317,38 +2068,39 @@ void __mark_inode_dirty(struct inode *inode, int flags) * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { + struct bdi_writeback *wb; + struct list_head *dirty_list; bool wakeup_bdi = false; - bdi = inode_to_bdi(inode); - spin_unlock(&inode->i_lock); - spin_lock(&bdi->wb.list_lock); - if (bdi_cap_writeback_dirty(bdi)) { - WARN(!test_bit(BDI_registered, &bdi->state), - "bdi-%s not registered\n", bdi->name); + wb = locked_inode_to_wb_and_lock_list(inode); - /* - * If this is the first dirty inode for this - * bdi, we have to wake-up the corresponding - * bdi thread to make sure background - * write-back happens later. - */ - if (!wb_has_dirty_io(&bdi->wb)) - wakeup_bdi = true; - } + WARN(bdi_cap_writeback_dirty(wb->bdi) && + !test_bit(WB_registered, &wb->state), + "bdi-%s not registered\n", wb->bdi->name); inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; + if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES)) - list_move(&inode->i_wb_list, &bdi->wb.b_dirty); + dirty_list = &wb->b_dirty; else - list_move(&inode->i_wb_list, - &bdi->wb.b_dirty_time); - spin_unlock(&bdi->wb.list_lock); + dirty_list = &wb->b_dirty_time; + + wakeup_bdi = inode_wb_list_move_locked(inode, wb, + dirty_list); + + spin_unlock(&wb->list_lock); trace_writeback_dirty_inode_enqueue(inode); - if (wakeup_bdi) - bdi_wakeup_thread_delayed(bdi); + /* + * If this is the first dirty inode for this bdi, + * we have to wake-up the corresponding bdi thread + * to make sure background write-back happens + * later. + */ + if (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi) + wb_wakeup_delayed(wb); return; } } @@ -1411,6 +2163,28 @@ static void wait_sb_inodes(struct super_block *sb) iput(old_inode); } +static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, + enum wb_reason reason, bool skip_if_busy) +{ + DEFINE_WB_COMPLETION_ONSTACK(done); + struct wb_writeback_work work = { + .sb = sb, + .sync_mode = WB_SYNC_NONE, + .tagged_writepages = 1, + .done = &done, + .nr_pages = nr, + .reason = reason, + }; + struct backing_dev_info *bdi = sb->s_bdi; + + if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) + return; + WARN_ON(!rwsem_is_locked(&sb->s_umount)); + + bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); + wb_wait_for_completion(bdi, &done); +} + /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock @@ -1425,21 +2199,7 @@ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { - DECLARE_COMPLETION_ONSTACK(done); - struct wb_writeback_work work = { - .sb = sb, - .sync_mode = WB_SYNC_NONE, - .tagged_writepages = 1, - .done = &done, - .nr_pages = nr, - .reason = reason, - }; - - if (sb->s_bdi == &noop_backing_dev_info) - return; - WARN_ON(!rwsem_is_locked(&sb->s_umount)); - bdi_queue_work(sb->s_bdi, &work); - wait_for_completion(&done); + __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); @@ -1467,19 +2227,15 @@ EXPORT_SYMBOL(writeback_inodes_sb); * Invoke writeback_inodes_sb_nr if no writeback is currently underway. * Returns 1 if writeback was started, 0 if not. */ -int try_to_writeback_inodes_sb_nr(struct super_block *sb, - unsigned long nr, - enum wb_reason reason) +bool try_to_writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, + enum wb_reason reason) { - if (writeback_in_progress(sb->s_bdi)) - return 1; - if (!down_read_trylock(&sb->s_umount)) - return 0; + return false; - writeback_inodes_sb_nr(sb, nr, reason); + __writeback_inodes_sb_nr(sb, nr, reason, true); up_read(&sb->s_umount); - return 1; + return true; } EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr); @@ -1491,7 +2247,7 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr); * Implement by try_to_writeback_inodes_sb_nr() * Returns 1 if writeback was started, 0 if not. */ -int try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) +bool try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } @@ -1506,7 +2262,7 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb); */ void sync_inodes_sb(struct super_block *sb) { - DECLARE_COMPLETION_ONSTACK(done); + DEFINE_WB_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, @@ -1516,14 +2272,15 @@ void sync_inodes_sb(struct super_block *sb) .reason = WB_REASON_SYNC, .for_sync = 1, }; + struct backing_dev_info *bdi = sb->s_bdi; /* Nothing to do? */ - if (sb->s_bdi == &noop_backing_dev_info) + if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); - bdi_queue_work(sb->s_bdi, &work); - wait_for_completion(&done); + bdi_split_work_to_wbs(bdi, &work, false); + wb_wait_for_completion(bdi, &done); wait_sb_inodes(sb); } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5ef05b5..8c5e2fa 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1445,9 +1445,9 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req) list_del(&req->writepages_entry); for (i = 0; i < req->num_pages; i++) { - dec_bdi_stat(bdi, BDI_WRITEBACK); + dec_wb_stat(&bdi->wb, WB_WRITEBACK); dec_zone_page_state(req->pages[i], NR_WRITEBACK_TEMP); - bdi_writeout_inc(bdi); + wb_writeout_inc(&bdi->wb); } wake_up(&fi->page_waitq); } @@ -1634,7 +1634,7 @@ static int fuse_writepage_locked(struct page *page) req->end = fuse_writepage_end; req->inode = inode; - inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK); + inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP); spin_lock(&fc->lock); @@ -1749,9 +1749,9 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, copy_highpage(old_req->pages[0], page); spin_unlock(&fc->lock); - dec_bdi_stat(bdi, BDI_WRITEBACK); + dec_wb_stat(&bdi->wb, WB_WRITEBACK); dec_zone_page_state(page, NR_WRITEBACK_TEMP); - bdi_writeout_inc(bdi); + wb_writeout_inc(&bdi->wb); fuse_writepage_free(fc, new_req); fuse_request_free(new_req); goto out; @@ -1848,7 +1848,7 @@ static int fuse_writepages_fill(struct page *page, req->page_descs[req->num_pages].offset = 0; req->page_descs[req->num_pages].length = PAGE_SIZE; - inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK); + inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK); inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP); err = 0; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 859c6ed..2982445 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -748,7 +748,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc) if (wbc->sync_mode == WB_SYNC_ALL) gfs2_log_flush(GFS2_SB(inode), ip->i_gl, NORMAL_FLUSH); - if (bdi->dirty_exceeded) + if (bdi->wb.dirty_exceeded) gfs2_ail1_flush(sdp, wbc); else filemap_fdatawrite(metamapping); diff --git a/fs/hfs/super.c b/fs/hfs/super.c index eee7206..55c03b9 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/nls.h> diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 593af2f..7302d96 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/pagemap.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/vfs.h> @@ -224,6 +224,7 @@ EXPORT_SYMBOL(free_inode_nonrcu); void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); + inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode->i_flctx); @@ -605,6 +605,8 @@ alloc_new: bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH); if (bio == NULL) goto confused; + + wbc_init_bio(wbc, bio); } /* @@ -612,6 +614,7 @@ alloc_new: * the confused fail path above (OOM) will be very confused when * it finds all bh marked clean (i.e. it will not write anything) */ + wbc_account_io(wbc, page, PAGE_SIZE); length = first_unmapped << blkbits; if (bio_add_page(bio, page, length, 0) < length) { bio = mpage_bio_submit(WRITE, bio); diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index a46bf6d..b34f2e2 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -32,6 +32,7 @@ #include <linux/nfs_fs.h> #include <linux/nfs_page.h> #include <linux/module.h> +#include <linux/backing-dev.h> #include <linux/sunrpc/metrics.h> diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 9e6475b..7e3c460 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -607,7 +607,7 @@ void nfs_mark_page_unstable(struct page *page) struct inode *inode = page_file_mapping(page)->host; inc_zone_page_state(page, NR_UNSTABLE_NFS); - inc_bdi_stat(inode_to_bdi(inode), BDI_RECLAIMABLE); + inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index dfc19f1..e6c2625 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -853,7 +853,8 @@ static void nfs_clear_page_commit(struct page *page) { dec_zone_page_state(page, NR_UNSTABLE_NFS); - dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE); + dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb, + WB_RECLAIMABLE); } /* Called holding inode (/cinfo) lock */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index fbfadb2..719f7f4 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -37,6 +37,7 @@ #include <linux/falloc.h> #include <linux/quotaops.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <cluster/masklog.h> diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 0111ad0..3e0af31 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -21,6 +21,7 @@ #include "xattr.h" #include <linux/init.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/quotaops.h> diff --git a/fs/ufs/super.c b/fs/ufs/super.c index b3bc3e7..098508a 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -80,6 +80,7 @@ #include <linux/stat.h> #include <linux/string.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/init.h> #include <linux/parser.h> #include <linux/buffer_head.h> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 095f94c..e5099f2 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1873,6 +1873,7 @@ xfs_vm_set_page_dirty( loff_t end_offset; loff_t offset; int newly_dirty; + struct mem_cgroup *memcg; if (unlikely(!mapping)) return !TestSetPageDirty(page); @@ -1892,6 +1893,11 @@ xfs_vm_set_page_dirty( offset += 1 << inode->i_blkbits; } while (bh != head); } + /* + * Use mem_group_begin_page_stat() to keep PageDirty synchronized with + * per-memcg dirty page counters. + */ + memcg = mem_cgroup_begin_page_stat(page); newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); @@ -1902,13 +1908,15 @@ xfs_vm_set_page_dirty( spin_lock_irqsave(&mapping->tree_lock, flags); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(!PageUptodate(page)); - account_page_dirtied(page, mapping); + account_page_dirtied(page, mapping, memcg); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } spin_unlock_irqrestore(&mapping->tree_lock, flags); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } + mem_cgroup_end_page_stat(memcg); + if (newly_dirty) + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 3b75912..7c62fca 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -41,6 +41,7 @@ #include <linux/dcache.h> #include <linux/falloc.h> #include <linux/pagevec.h> +#include <linux/backing-dev.h> static const struct vm_operations_struct xfs_file_vm_ops; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h new file mode 100644 index 0000000..a48d90e --- /dev/null +++ b/include/linux/backing-dev-defs.h @@ -0,0 +1,255 @@ +#ifndef __LINUX_BACKING_DEV_DEFS_H +#define __LINUX_BACKING_DEV_DEFS_H + +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/rbtree.h> +#include <linux/spinlock.h> +#include <linux/percpu_counter.h> +#include <linux/percpu-refcount.h> +#include <linux/flex_proportions.h> +#include <linux/timer.h> +#include <linux/workqueue.h> + +struct page; +struct device; +struct dentry; + +/* + * Bits in bdi_writeback.state + */ +enum wb_state { + WB_registered, /* bdi_register() was done */ + WB_writeback_running, /* Writeback is in progress */ + WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ +}; + +enum wb_congested_state { + WB_async_congested, /* The async (write) queue is getting full */ + WB_sync_congested, /* The sync queue is getting full */ +}; + +typedef int (congested_fn)(void *, int); + +enum wb_stat_item { + WB_RECLAIMABLE, + WB_WRITEBACK, + WB_DIRTIED, + WB_WRITTEN, + NR_WB_STAT_ITEMS +}; + +#define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) + +/* + * For cgroup writeback, multiple wb's may map to the same blkcg. Those + * wb's can operate mostly independently but should share the congested + * state. To facilitate such sharing, the congested state is tracked using + * the following struct which is created on demand, indexed by blkcg ID on + * its bdi, and refcounted. + */ +struct bdi_writeback_congested { + unsigned long state; /* WB_[a]sync_congested flags */ + +#ifdef CONFIG_CGROUP_WRITEBACK + struct backing_dev_info *bdi; /* the associated bdi */ + atomic_t refcnt; /* nr of attached wb's and blkg */ + int blkcg_id; /* ID of the associated blkcg */ + struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ +#endif +}; + +/* + * Each wb (bdi_writeback) can perform writeback operations, is measured + * and throttled, independently. Without cgroup writeback, each bdi + * (bdi_writeback) is served by its embedded bdi->wb. + * + * On the default hierarchy, blkcg implicitly enables memcg. This allows + * using memcg's page ownership for attributing writeback IOs, and every + * memcg - blkcg combination can be served by its own wb by assigning a + * dedicated wb to each memcg, which enables isolation across different + * cgroups and propagation of IO back pressure down from the IO layer upto + * the tasks which are generating the dirty pages to be written back. + * + * A cgroup wb is indexed on its bdi by the ID of the associated memcg, + * refcounted with the number of inodes attached to it, and pins the memcg + * and the corresponding blkcg. As the corresponding blkcg for a memcg may + * change as blkcg is disabled and enabled higher up in the hierarchy, a wb + * is tested for blkcg after lookup and removed from index on mismatch so + * that a new wb for the combination can be created. + */ +struct bdi_writeback { + struct backing_dev_info *bdi; /* our parent bdi */ + + unsigned long state; /* Always use atomic bitops on this */ + unsigned long last_old_flush; /* last old data flush */ + + struct list_head b_dirty; /* dirty inodes */ + struct list_head b_io; /* parked for writeback */ + struct list_head b_more_io; /* parked for more writeback */ + struct list_head b_dirty_time; /* time stamps are dirty */ + spinlock_t list_lock; /* protects the b_* lists */ + + struct percpu_counter stat[NR_WB_STAT_ITEMS]; + + struct bdi_writeback_congested *congested; + + unsigned long bw_time_stamp; /* last time write bw is updated */ + unsigned long dirtied_stamp; + unsigned long written_stamp; /* pages written at bw_time_stamp */ + unsigned long write_bandwidth; /* the estimated write bandwidth */ + unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ + + /* + * The base dirty throttle rate, re-calculated on every 200ms. + * All the bdi tasks' dirty rate will be curbed under it. + * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit + * in small steps and is much more smooth/stable than the latter. + */ + unsigned long dirty_ratelimit; + unsigned long balanced_dirty_ratelimit; + + struct fprop_local_percpu completions; + int dirty_exceeded; + + spinlock_t work_lock; /* protects work_list & dwork scheduling */ + struct list_head work_list; + struct delayed_work dwork; /* work item used for writeback */ + +#ifdef CONFIG_CGROUP_WRITEBACK + struct percpu_ref refcnt; /* used only for !root wb's */ + struct fprop_local_percpu memcg_completions; + struct cgroup_subsys_state *memcg_css; /* the associated memcg */ + struct cgroup_subsys_state *blkcg_css; /* and blkcg */ + struct list_head memcg_node; /* anchored at memcg->cgwb_list */ + struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ + + union { + struct work_struct release_work; + struct rcu_head rcu; + }; +#endif +}; + +struct backing_dev_info { + struct list_head bdi_list; + unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ + unsigned int capabilities; /* Device capabilities */ + congested_fn *congested_fn; /* Function pointer if device is md/dm */ + void *congested_data; /* Pointer to aux data for congested func */ + + char *name; + + unsigned int min_ratio; + unsigned int max_ratio, max_prop_frac; + + /* + * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are + * any dirty wbs, which is depended upon by bdi_has_dirty(). + */ + atomic_long_t tot_write_bandwidth; + + struct bdi_writeback wb; /* the root writeback info for this bdi */ + struct bdi_writeback_congested wb_congested; /* its congested state */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ + struct rb_root cgwb_congested_tree; /* their congested states */ + atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */ +#endif + wait_queue_head_t wb_waitq; + + struct device *dev; + + struct timer_list laptop_mode_wb_timer; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debug_dir; + struct dentry *debug_stats; +#endif +}; + +enum { + BLK_RW_ASYNC = 0, + BLK_RW_SYNC = 1, +}; + +void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); +void set_wb_congested(struct bdi_writeback_congested *congested, int sync); + +static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + clear_wb_congested(bdi->wb.congested, sync); +} + +static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) +{ + set_wb_congested(bdi->wb.congested, sync); +} + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * wb_tryget - try to increment a wb's refcount + * @wb: bdi_writeback to get + */ +static inline bool wb_tryget(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + return percpu_ref_tryget(&wb->refcnt); + return true; +} + +/** + * wb_get - increment a wb's refcount + * @wb: bdi_writeback to get + */ +static inline void wb_get(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + percpu_ref_get(&wb->refcnt); +} + +/** + * wb_put - decrement a wb's refcount + * @wb: bdi_writeback to put + */ +static inline void wb_put(struct bdi_writeback *wb) +{ + if (wb != &wb->bdi->wb) + percpu_ref_put(&wb->refcnt); +} + +/** + * wb_dying - is a wb dying? + * @wb: bdi_writeback of interest + * + * Returns whether @wb is unlinked and being drained. + */ +static inline bool wb_dying(struct bdi_writeback *wb) +{ + return percpu_ref_is_dying(&wb->refcnt); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline bool wb_tryget(struct bdi_writeback *wb) +{ + return true; +} + +static inline void wb_get(struct bdi_writeback *wb) +{ +} + +static inline void wb_put(struct bdi_writeback *wb) +{ +} + +static inline bool wb_dying(struct bdi_writeback *wb) +{ + return false; +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +#endif /* __LINUX_BACKING_DEV_DEFS_H */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index d87d8ec..0e6d482 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -8,106 +8,13 @@ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H -#include <linux/percpu_counter.h> -#include <linux/log2.h> -#include <linux/flex_proportions.h> #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> -#include <linux/timer.h> +#include <linux/blkdev.h> #include <linux/writeback.h> -#include <linux/atomic.h> -#include <linux/sysctl.h> -#include <linux/workqueue.h> - -struct page; -struct device; -struct dentry; - -/* - * Bits in backing_dev_info.state - */ -enum bdi_state { - BDI_async_congested, /* The async (write) queue is getting full */ - BDI_sync_congested, /* The sync queue is getting full */ - BDI_registered, /* bdi_register() was done */ - BDI_writeback_running, /* Writeback is in progress */ -}; - -typedef int (congested_fn)(void *, int); - -enum bdi_stat_item { - BDI_RECLAIMABLE, - BDI_WRITEBACK, - BDI_DIRTIED, - BDI_WRITTEN, - NR_BDI_STAT_ITEMS -}; - -#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) - -struct bdi_writeback { - struct backing_dev_info *bdi; /* our parent bdi */ - - unsigned long last_old_flush; /* last old data flush */ - - struct delayed_work dwork; /* work item used for writeback */ - struct list_head b_dirty; /* dirty inodes */ - struct list_head b_io; /* parked for writeback */ - struct list_head b_more_io; /* parked for more writeback */ - struct list_head b_dirty_time; /* time stamps are dirty */ - spinlock_t list_lock; /* protects the b_* lists */ -}; - -struct backing_dev_info { - struct list_head bdi_list; - unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ - unsigned long state; /* Always use atomic bitops on this */ - unsigned int capabilities; /* Device capabilities */ - congested_fn *congested_fn; /* Function pointer if device is md/dm */ - void *congested_data; /* Pointer to aux data for congested func */ - - char *name; - - struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; - - unsigned long bw_time_stamp; /* last time write bw is updated */ - unsigned long dirtied_stamp; - unsigned long written_stamp; /* pages written at bw_time_stamp */ - unsigned long write_bandwidth; /* the estimated write bandwidth */ - unsigned long avg_write_bandwidth; /* further smoothed write bw */ - - /* - * The base dirty throttle rate, re-calculated on every 200ms. - * All the bdi tasks' dirty rate will be curbed under it. - * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit - * in small steps and is much more smooth/stable than the latter. - */ - unsigned long dirty_ratelimit; - unsigned long balanced_dirty_ratelimit; - - struct fprop_local_percpu completions; - int dirty_exceeded; - - unsigned int min_ratio; - unsigned int max_ratio, max_prop_frac; - - struct bdi_writeback wb; /* default writeback info for this bdi */ - spinlock_t wb_lock; /* protects work_list & wb.dwork scheduling */ - - struct list_head work_list; - - struct device *dev; - - struct timer_list laptop_mode_wb_timer; - -#ifdef CONFIG_DEBUG_FS - struct dentry *debug_dir; - struct dentry *debug_stats; -#endif -}; - -struct backing_dev_info *inode_to_bdi(struct inode *inode); +#include <linux/blk-cgroup.h> +#include <linux/backing-dev-defs.h> int __must_check bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); @@ -117,97 +24,99 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - enum wb_reason reason); -void bdi_start_background_writeback(struct backing_dev_info *bdi); -void bdi_writeback_workfn(struct work_struct *work); -int bdi_has_dirty_io(struct backing_dev_info *bdi); -void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); +void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, + bool range_cyclic, enum wb_reason reason); +void wb_start_background_writeback(struct bdi_writeback *wb); +void wb_workfn(struct work_struct *work); +void wb_wakeup_delayed(struct bdi_writeback *wb); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; -static inline int wb_has_dirty_io(struct bdi_writeback *wb) +static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { - return !list_empty(&wb->b_dirty) || - !list_empty(&wb->b_io) || - !list_empty(&wb->b_more_io); + return test_bit(WB_has_dirty_io, &wb->state); +} + +static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) +{ + /* + * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are + * any dirty wbs. See wb_update_write_bandwidth(). + */ + return atomic_long_read(&bdi->tot_write_bandwidth); } -static inline void __add_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item, s64 amount) +static inline void __add_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item, s64 amount) { - __percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH); + __percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH); } -static inline void __inc_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void __inc_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item) { - __add_bdi_stat(bdi, item, 1); + __add_wb_stat(wb, item, 1); } -static inline void inc_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { unsigned long flags; local_irq_save(flags); - __inc_bdi_stat(bdi, item); + __inc_wb_stat(wb, item); local_irq_restore(flags); } -static inline void __dec_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void __dec_wb_stat(struct bdi_writeback *wb, + enum wb_stat_item item) { - __add_bdi_stat(bdi, item, -1); + __add_wb_stat(wb, item, -1); } -static inline void dec_bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { unsigned long flags; local_irq_save(flags); - __dec_bdi_stat(bdi, item); + __dec_wb_stat(wb, item); local_irq_restore(flags); } -static inline s64 bdi_stat(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - return percpu_counter_read_positive(&bdi->bdi_stat[item]); + return percpu_counter_read_positive(&wb->stat[item]); } -static inline s64 __bdi_stat_sum(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 __wb_stat_sum(struct bdi_writeback *wb, + enum wb_stat_item item) { - return percpu_counter_sum_positive(&bdi->bdi_stat[item]); + return percpu_counter_sum_positive(&wb->stat[item]); } -static inline s64 bdi_stat_sum(struct backing_dev_info *bdi, - enum bdi_stat_item item) +static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { s64 sum; unsigned long flags; local_irq_save(flags); - sum = __bdi_stat_sum(bdi, item); + sum = __wb_stat_sum(wb, item); local_irq_restore(flags); return sum; } -extern void bdi_writeout_inc(struct backing_dev_info *bdi); +extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ -static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi) +static inline unsigned long wb_stat_error(struct bdi_writeback *wb) { #ifdef CONFIG_SMP - return nr_cpu_ids * BDI_STAT_BATCH; + return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif @@ -231,50 +140,57 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. + * + * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 #define BDI_CAP_NO_ACCT_WB 0x00000004 #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 +#define BDI_CAP_CGROUP_WRITEBACK 0x00000020 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) extern struct backing_dev_info noop_backing_dev_info; -int writeback_in_progress(struct backing_dev_info *bdi); - -static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits) +/** + * writeback_in_progress - determine whether there is writeback in progress + * @wb: bdi_writeback of interest + * + * Determine whether there is writeback waiting to be handled against a + * bdi_writeback. + */ +static inline bool writeback_in_progress(struct bdi_writeback *wb) { - if (bdi->congested_fn) - return bdi->congested_fn(bdi->congested_data, bdi_bits); - return (bdi->state & bdi_bits); + return test_bit(WB_writeback_running, &wb->state); } -static inline int bdi_read_congested(struct backing_dev_info *bdi) +static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { - return bdi_congested(bdi, 1 << BDI_sync_congested); -} + struct super_block *sb; -static inline int bdi_write_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << BDI_async_congested); + if (!inode) + return &noop_backing_dev_info; + + sb = inode->i_sb; +#ifdef CONFIG_BLOCK + if (sb_is_blkdev_sb(sb)) + return blk_get_backing_dev_info(I_BDEV(inode)); +#endif + return sb->s_bdi; } -static inline int bdi_rw_congested(struct backing_dev_info *bdi) +static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { - return bdi_congested(bdi, (1 << BDI_sync_congested) | - (1 << BDI_async_congested)); -} + struct backing_dev_info *bdi = wb->bdi; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; + if (bdi->congested_fn) + return bdi->congested_fn(bdi->congested_data, cong_bits); + return wb->congested->state & cong_bits; +} -void clear_bdi_congested(struct backing_dev_info *bdi, int sync); -void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); long wait_iff_congested(struct zone *zone, int sync, long timeout); int pdflush_proc_obsolete(struct ctl_table *table, int write, @@ -318,4 +234,333 @@ static inline int bdi_sched_wait(void *word) return 0; } -#endif /* _LINUX_BACKING_DEV_H */ +#ifdef CONFIG_CGROUP_WRITEBACK + +struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); +void wb_congested_put(struct bdi_writeback_congested *congested); +struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, + gfp_t gfp); +void wb_memcg_offline(struct mem_cgroup *memcg); +void wb_blkcg_offline(struct blkcg *blkcg); +int inode_congested(struct inode *inode, int cong_bits); + +/** + * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode + * @inode: inode of interest + * + * cgroup writeback requires support from both the bdi and filesystem. + * Test whether @inode has both. + */ +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + + return bdi_cap_account_dirty(bdi) && + (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && + (inode->i_sb->s_iflags & SB_I_CGROUPWB); +} + +/** + * wb_find_current - find wb for %current on a bdi + * @bdi: bdi of interest + * + * Find the wb of @bdi which matches both the memcg and blkcg of %current. + * Must be called under rcu_read_lock() which protects the returend wb. + * NULL if not found. + */ +static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) +{ + struct cgroup_subsys_state *memcg_css; + struct bdi_writeback *wb; + + memcg_css = task_css(current, memory_cgrp_id); + if (!memcg_css->parent) + return &bdi->wb; + + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + + /* + * %current's blkcg equals the effective blkcg of its memcg. No + * need to use the relatively expensive cgroup_get_e_css(). + */ + if (likely(wb && wb->blkcg_css == task_css(current, blkio_cgrp_id))) + return wb; + return NULL; +} + +/** + * wb_get_create_current - get or create wb for %current on a bdi + * @bdi: bdi of interest + * @gfp: allocation mask + * + * Equivalent to wb_get_create() on %current's memcg. This function is + * called from a relatively hot path and optimizes the common cases using + * wb_find_current(). + */ +static inline struct bdi_writeback * +wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) +{ + struct bdi_writeback *wb; + + rcu_read_lock(); + wb = wb_find_current(bdi); + if (wb && unlikely(!wb_tryget(wb))) + wb = NULL; + rcu_read_unlock(); + + if (unlikely(!wb)) { + struct cgroup_subsys_state *memcg_css; + + memcg_css = task_get_css(current, memory_cgrp_id); + wb = wb_get_create(bdi, memcg_css, gfp); + css_put(memcg_css); + } + return wb; +} + +/** + * inode_to_wb_is_valid - test whether an inode has a wb associated + * @inode: inode of interest + * + * Returns %true if @inode has a wb associated. May be called without any + * locking. + */ +static inline bool inode_to_wb_is_valid(struct inode *inode) +{ + return inode->i_wb; +} + +/** + * inode_to_wb - determine the wb of an inode + * @inode: inode of interest + * + * Returns the wb @inode is currently associated with. The caller must be + * holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the + * associated wb's list_lock. + */ +static inline struct bdi_writeback *inode_to_wb(struct inode *inode) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(debug_locks && + (!lockdep_is_held(&inode->i_lock) && + !lockdep_is_held(&inode->i_mapping->tree_lock) && + !lockdep_is_held(&inode->i_wb->list_lock))); +#endif + return inode->i_wb; +} + +/** + * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction + * @inode: target inode + * @lockedp: temp bool output param, to be passed to the end function + * + * The caller wants to access the wb associated with @inode but isn't + * holding inode->i_lock, mapping->tree_lock or wb->list_lock. This + * function determines the wb associated with @inode and ensures that the + * association doesn't change until the transaction is finished with + * unlocked_inode_to_wb_end(). + * + * The caller must call unlocked_inode_to_wb_end() with *@lockdep + * afterwards and can't sleep during transaction. IRQ may or may not be + * disabled on return. + */ +static inline struct bdi_writeback * +unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +{ + rcu_read_lock(); + + /* + * Paired with store_release in inode_switch_wb_work_fn() and + * ensures that we see the new wb if we see cleared I_WB_SWITCH. + */ + *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + + if (unlikely(*lockedp)) + spin_lock_irq(&inode->i_mapping->tree_lock); + + /* + * Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock. + * inode_to_wb() will bark. Deref directly. + */ + return inode->i_wb; +} + +/** + * unlocked_inode_to_wb_end - end inode wb access transaction + * @inode: target inode + * @locked: *@lockedp from unlocked_inode_to_wb_begin() + */ +static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +{ + if (unlikely(locked)) + spin_unlock_irq(&inode->i_mapping->tree_lock); + + rcu_read_unlock(); +} + +struct wb_iter { + int start_blkcg_id; + struct radix_tree_iter tree_iter; + void **slot; +}; + +static inline struct bdi_writeback *__wb_iter_next(struct wb_iter *iter, + struct backing_dev_info *bdi) +{ + struct radix_tree_iter *titer = &iter->tree_iter; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (iter->start_blkcg_id >= 0) { + iter->slot = radix_tree_iter_init(titer, iter->start_blkcg_id); + iter->start_blkcg_id = -1; + } else { + iter->slot = radix_tree_next_slot(iter->slot, titer, 0); + } + + if (!iter->slot) + iter->slot = radix_tree_next_chunk(&bdi->cgwb_tree, titer, 0); + if (iter->slot) + return *iter->slot; + return NULL; +} + +static inline struct bdi_writeback *__wb_iter_init(struct wb_iter *iter, + struct backing_dev_info *bdi, + int start_blkcg_id) +{ + iter->start_blkcg_id = start_blkcg_id; + + if (start_blkcg_id) + return __wb_iter_next(iter, bdi); + else + return &bdi->wb; +} + +/** + * bdi_for_each_wb - walk all wb's of a bdi in ascending blkcg ID order + * @wb_cur: cursor struct bdi_writeback pointer + * @bdi: bdi to walk wb's of + * @iter: pointer to struct wb_iter to be used as iteration buffer + * @start_blkcg_id: blkcg ID to start iteration from + * + * Iterate @wb_cur through the wb's (bdi_writeback's) of @bdi in ascending + * blkcg ID order starting from @start_blkcg_id. @iter is struct wb_iter + * to be used as temp storage during iteration. rcu_read_lock() must be + * held throughout iteration. + */ +#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \ + for ((wb_cur) = __wb_iter_init(iter, bdi, start_blkcg_id); \ + (wb_cur); (wb_cur) = __wb_iter_next(iter, bdi)) + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + return false; +} + +static inline struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) +{ + return bdi->wb.congested; +} + +static inline void wb_congested_put(struct bdi_writeback_congested *congested) +{ +} + +static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) +{ + return &bdi->wb; +} + +static inline struct bdi_writeback * +wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) +{ + return &bdi->wb; +} + +static inline bool inode_to_wb_is_valid(struct inode *inode) +{ + return true; +} + +static inline struct bdi_writeback *inode_to_wb(struct inode *inode) +{ + return &inode_to_bdi(inode)->wb; +} + +static inline struct bdi_writeback * +unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +{ + return inode_to_wb(inode); +} + +static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +{ +} + +static inline void wb_memcg_offline(struct mem_cgroup *memcg) +{ +} + +static inline void wb_blkcg_offline(struct blkcg *blkcg) +{ +} + +struct wb_iter { + int next_id; +}; + +#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \ + for ((iter)->next_id = (start_blkcg_id); \ + ({ (wb_cur) = !(iter)->next_id++ ? &(bdi)->wb : NULL; }); ) + +static inline int inode_congested(struct inode *inode, int cong_bits) +{ + return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +static inline int inode_read_congested(struct inode *inode) +{ + return inode_congested(inode, 1 << WB_sync_congested); +} + +static inline int inode_write_congested(struct inode *inode) +{ + return inode_congested(inode, 1 << WB_async_congested); +} + +static inline int inode_rw_congested(struct inode *inode) +{ + return inode_congested(inode, (1 << WB_sync_congested) | + (1 << WB_async_congested)); +} + +static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) +{ + return wb_congested(&bdi->wb, cong_bits); +} + +static inline int bdi_read_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, 1 << WB_sync_congested); +} + +static inline int bdi_write_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, 1 << WB_async_congested); +} + +static inline int bdi_rw_congested(struct backing_dev_info *bdi) +{ + return bdi_congested(bdi, (1 << WB_sync_congested) | + (1 << WB_async_congested)); +} + +#endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/bio.h b/include/linux/bio.h index f0291cf..5e963a6 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -482,9 +482,12 @@ extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); void bio_disassociate_task(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } #endif /* CONFIG_BLK_CGROUP */ diff --git a/block/blk-cgroup.h b/include/linux/blk-cgroup.h index 74296a7..58cfab8 100644 --- a/block/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -46,6 +46,10 @@ struct blkcg { struct hlist_head blkg_list; struct blkcg_policy_data *pd[BLKCG_MAX_POLS]; + +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; +#endif }; struct blkg_stat { @@ -106,6 +110,12 @@ struct blkcg_gq { struct hlist_node blkcg_node; struct blkcg *blkcg; + /* + * Each blkg gets congested separately and the congestion state is + * propagated to the matching bdi_writeback_congested. + */ + struct bdi_writeback_congested *wb_congested; + /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; @@ -149,6 +159,7 @@ struct blkcg_policy { }; extern struct blkcg blkcg_root; +extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, @@ -209,6 +220,12 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) return task_blkcg(current); } +static inline struct cgroup_subsys_state * +task_get_blkcg_css(struct task_struct *task) +{ + return task_get_css(task, blkio_cgrp_id); +} + /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest @@ -579,8 +596,8 @@ static inline void blkg_rwstat_merge(struct blkg_rwstat *to, #else /* CONFIG_BLK_CGROUP */ -struct cgroup; -struct blkcg; +struct blkcg { +}; struct blkg_policy_data { }; @@ -594,6 +611,16 @@ struct blkcg_gq { struct blkcg_policy { }; +#define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) + +static inline struct cgroup_subsys_state * +task_get_blkcg_css(struct task_struct *task) +{ + return NULL; +} + +#ifdef CONFIG_BLOCK + static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_drain_queue(struct request_queue *q) { } @@ -623,5 +650,6 @@ static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) +#endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ #endif /* _BLK_CGROUP_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5ced29c..7f2f54b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -12,7 +12,7 @@ #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/pagemap.h> -#include <linux/backing-dev.h> +#include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/bio.h> @@ -787,25 +787,6 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); -/* - * A queue has just exitted congestion. Note this in the global counter of - * congested queues, and wake up anyone who was waiting for requests to be - * put back. - */ -static inline void blk_clear_queue_congested(struct request_queue *q, int sync) -{ - clear_bdi_congested(&q->backing_dev_info, sync); -} - -/* - * A queue has just entered congestion. Flag that in the queue's VM-visible - * state flags and increment the global gounter of congested queues. - */ -static inline void blk_set_queue_congested(struct request_queue *q, int sync) -{ - set_bdi_congested(&q->backing_dev_info, sync); -} - extern void blk_start_queue(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b9cb94c..e7da0aa 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -774,6 +774,31 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, } /** + * task_get_css - find and get the css for (task, subsys) + * @task: the target task + * @subsys_id: the target subsystem ID + * + * Find the css for the (@task, @subsys_id) combination, increment a + * reference on and return it. This function is guaranteed to return a + * valid css. + */ +static inline struct cgroup_subsys_state * +task_get_css(struct task_struct *task, int subsys_id) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + while (true) { + css = task_css(task, subsys_id); + if (likely(css_tryget_online(css))) + break; + cpu_relax(); + } + rcu_read_unlock(); + return css; +} + +/** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID diff --git a/include/linux/fs.h b/include/linux/fs.h index 5db7b13..e351da4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -35,6 +35,7 @@ #include <uapi/linux/fs.h> struct backing_dev_info; +struct bdi_writeback; struct export_operations; struct hd_geometry; struct iovec; @@ -634,6 +635,14 @@ struct inode { struct hlist_node i_hash; struct list_head i_wb_list; /* backing dev IO list */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct bdi_writeback *i_wb; /* the associated cgroup wb */ + + /* foreign inode detection, see wbc_detach_inode() */ + int i_wb_frn_winner; + u16 i_wb_frn_avg_time; + u16 i_wb_frn_history; +#endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; union { @@ -1232,6 +1241,8 @@ struct mm_struct; #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ +/* sb->s_iflags */ +#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ /* Possible states of 'frozen' field */ enum { @@ -1270,6 +1281,7 @@ struct super_block { const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; + unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; @@ -1806,6 +1818,11 @@ struct super_operations { * * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). * + * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to + * synchronize competing switching instances and to tell + * wb stat updates to grab mapping->tree_lock. See + * inode_switch_wb_work_fn() for details. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1825,6 +1842,7 @@ struct super_operations { #define I_DIRTY_TIME (1 << 11) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) +#define I_WB_SWITCH (1 << 13) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) @@ -2241,7 +2259,13 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); -extern int sb_is_blkdev_sb(struct super_block *sb); + +extern struct super_block *blockdev_superblock; + +static inline bool sb_is_blkdev_sb(struct super_block *sb) +{ + return sb == blockdev_superblock; +} #else static inline void bd_forget(struct inode *inode) {} static inline int sync_blockdev(struct block_device *bdev) { return 0; } diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6c89181..73b02b0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -41,6 +41,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ + MEM_CGROUP_STAT_DIRTY, /* # of dirty pages in page cache */ MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */ MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, @@ -67,6 +68,8 @@ enum mem_cgroup_events_index { }; #ifdef CONFIG_MEMCG +extern struct cgroup_subsys_state *mem_cgroup_root_css; + void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, unsigned int nr); @@ -112,6 +115,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, } extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); +extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, @@ -195,6 +199,8 @@ void mem_cgroup_split_huge_fixup(struct page *head); #else /* CONFIG_MEMCG */ struct mem_cgroup; +#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) + static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, unsigned int nr) @@ -382,6 +388,29 @@ enum { OVER_LIMIT, }; +#ifdef CONFIG_CGROUP_WRITEBACK + +struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); +struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail, + unsigned long *pdirty, unsigned long *pwriteback); + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) +{ + return NULL; +} + +static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, + unsigned long *pavail, + unsigned long *pdirty, + unsigned long *pwriteback) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + struct sock; #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) void sock_update_memcg(struct sock *sk); diff --git a/include/linux/mm.h b/include/linux/mm.h index 24ad583..99959a3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -27,6 +27,7 @@ struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; +struct bdi_writeback; #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; @@ -1211,10 +1212,13 @@ int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -void account_page_dirtied(struct page *page, struct address_space *mapping); -void account_page_cleaned(struct page *page, struct address_space *mapping); +void account_page_dirtied(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg); +void account_page_cleaned(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); +void cancel_dirty_page(struct page *page); int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4b3736f..fb0814c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -651,7 +651,8 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow); +extern void __delete_from_page_cache(struct page *page, void *shadow, + struct mem_cgroup *memcg); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); /* diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b2dd371e..b333c94 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -7,6 +7,8 @@ #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/fs.h> +#include <linux/flex_proportions.h> +#include <linux/backing-dev-defs.h> DECLARE_PER_CPU(int, dirty_throttle_leaks); @@ -84,18 +86,95 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct bdi_writeback *wb; /* wb this writeback is issued under */ + struct inode *inode; /* inode being written out */ + + /* foreign inode detection, see wbc_detach_inode() */ + int wb_id; /* current wb id */ + int wb_lcand_id; /* last foreign candidate wb id */ + int wb_tcand_id; /* this foreign candidate wb id */ + size_t wb_bytes; /* bytes written by current wb */ + size_t wb_lcand_bytes; /* bytes written by last candidate */ + size_t wb_tcand_bytes; /* bytes written by this candidate */ +#endif }; /* + * A wb_domain represents a domain that wb's (bdi_writeback's) belong to + * and are measured against each other in. There always is one global + * domain, global_wb_domain, that every wb in the system is a member of. + * This allows measuring the relative bandwidth of each wb to distribute + * dirtyable memory accordingly. + */ +struct wb_domain { + spinlock_t lock; + + /* + * Scale the writeback cache size proportional to the relative + * writeout speed. + * + * We do this by keeping a floating proportion between BDIs, based + * on page writeback completions [end_page_writeback()]. Those + * devices that write out pages fastest will get the larger share, + * while the slower will get a smaller share. + * + * We use page writeout completions because we are interested in + * getting rid of dirty pages. Having them written out is the + * primary goal. + * + * We introduce a concept of time, a period over which we measure + * these events, because demand can/will vary over time. The length + * of this period itself is measured in page writeback completions. + */ + struct fprop_global completions; + struct timer_list period_timer; /* timer for aging of completions */ + unsigned long period_time; + + /* + * The dirtyable memory and dirty threshold could be suddenly + * knocked down by a large amount (eg. on the startup of KVM in a + * swapless system). This may throw the system into deep dirty + * exceeded state and throttle heavy/light dirtiers alike. To + * retain good responsiveness, maintain global_dirty_limit for + * tracking slowly down to the knocked down dirty threshold. + * + * Both fields are protected by ->lock. + */ + unsigned long dirty_limit_tstamp; + unsigned long dirty_limit; +}; + +/** + * wb_domain_size_changed - memory available to a wb_domain has changed + * @dom: wb_domain of interest + * + * This function should be called when the amount of memory available to + * @dom has changed. It resets @dom's dirty limit parameters to prevent + * the past values which don't match the current configuration from skewing + * dirty throttling. Without this, when memory size of a wb_domain is + * greatly reduced, the dirty throttling logic may allow too many pages to + * be dirtied leading to consecutive unnecessary OOMs and may get stuck in + * that situation. + */ +static inline void wb_domain_size_changed(struct wb_domain *dom) +{ + spin_lock(&dom->lock); + dom->dirty_limit_tstamp = jiffies; + dom->dirty_limit = 0; + spin_unlock(&dom->lock); +} + +/* * fs/fs-writeback.c */ struct bdi_writeback; void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); -int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); -int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, - enum wb_reason reason); +bool try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); +bool try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, + enum wb_reason reason); void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); @@ -107,6 +186,123 @@ static inline void wait_on_inode(struct inode *inode) wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } +#ifdef CONFIG_CGROUP_WRITEBACK + +#include <linux/cgroup.h> +#include <linux/bio.h> + +void __inode_attach_wb(struct inode *inode, struct page *page); +void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock); +void wbc_detach_inode(struct writeback_control *wbc); +void wbc_account_io(struct writeback_control *wbc, struct page *page, + size_t bytes); + +/** + * inode_attach_wb - associate an inode with its wb + * @inode: inode of interest + * @page: page being dirtied (may be NULL) + * + * If @inode doesn't have its wb, associate it with the wb matching the + * memcg of @page or, if @page is NULL, %current. May be called w/ or w/o + * @inode->i_lock. + */ +static inline void inode_attach_wb(struct inode *inode, struct page *page) +{ + if (!inode->i_wb) + __inode_attach_wb(inode, page); +} + +/** + * inode_detach_wb - disassociate an inode from its wb + * @inode: inode of interest + * + * @inode is being freed. Detach from its wb. + */ +static inline void inode_detach_wb(struct inode *inode) +{ + if (inode->i_wb) { + wb_put(inode->i_wb); + inode->i_wb = NULL; + } +} + +/** + * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite + * @wbc: writeback_control of interest + * @inode: target inode + * + * This function is to be used by __filemap_fdatawrite_range(), which is an + * alternative entry point into writeback code, and first ensures @inode is + * associated with a bdi_writeback and attaches it to @wbc. + */ +static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode) +{ + spin_lock(&inode->i_lock); + inode_attach_wb(inode, NULL); + wbc_attach_and_unlock_inode(wbc, inode); +} + +/** + * wbc_init_bio - writeback specific initializtion of bio + * @wbc: writeback_control for the writeback in progress + * @bio: bio to be initialized + * + * @bio is a part of the writeback in progress controlled by @wbc. Perform + * writeback specific initialization. This is used to apply the cgroup + * writeback context. + */ +static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) +{ + /* + * pageout() path doesn't attach @wbc to the inode being written + * out. This is intentional as we don't want the function to block + * behind a slow cgroup. Ultimately, we want pageout() to kick off + * regular writeback instead of writing things out itself. + */ + if (wbc->wb) + bio_associate_blkcg(bio, wbc->wb->blkcg_css); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline void inode_attach_wb(struct inode *inode, struct page *page) +{ +} + +static inline void inode_detach_wb(struct inode *inode) +{ +} + +static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock) +{ + spin_unlock(&inode->i_lock); +} + +static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode) +{ +} + +static inline void wbc_detach_inode(struct writeback_control *wbc) +{ +} + +static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) +{ +} + +static inline void wbc_account_io(struct writeback_control *wbc, + struct page *page, size_t bytes) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * mm/page-writeback.c */ @@ -120,8 +316,12 @@ static inline void laptop_sync_completion(void) { } #endif void throttle_vm_writeout(gfp_t gfp_mask); bool zone_dirty_ok(struct zone *zone); +int wb_domain_init(struct wb_domain *dom, gfp_t gfp); +#ifdef CONFIG_CGROUP_WRITEBACK +void wb_domain_exit(struct wb_domain *dom); +#endif -extern unsigned long global_dirty_limit; +extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ extern int dirty_background_ratio; @@ -155,19 +355,12 @@ int dirty_writeback_centisecs_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); -unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, - unsigned long dirty); - -void __bdi_update_bandwidth(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long start_time); +unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); void page_writeback_init(void); void balance_dirty_pages_ratelimited(struct address_space *mapping); +bool wb_over_bg_thresh(struct bdi_writeback *wb); typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, void *data); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index c178d13..a7aa607 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -360,7 +360,7 @@ TRACE_EVENT(global_dirty_state, __entry->nr_written = global_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; - __entry->dirty_limit = global_dirty_limit; + __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu unstable=%lu " @@ -399,13 +399,13 @@ TRACE_EVENT(bdi_dirty_ratelimit, TP_fast_assign( strlcpy(__entry->bdi, dev_name(bdi->dev), 32); - __entry->write_bw = KBps(bdi->write_bandwidth); - __entry->avg_write_bw = KBps(bdi->avg_write_bandwidth); + __entry->write_bw = KBps(bdi->wb.write_bandwidth); + __entry->avg_write_bw = KBps(bdi->wb.avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); - __entry->dirty_ratelimit = KBps(bdi->dirty_ratelimit); + __entry->dirty_ratelimit = KBps(bdi->wb.dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = - KBps(bdi->balanced_dirty_ratelimit); + KBps(bdi->wb.balanced_dirty_ratelimit); ), TP_printk("bdi %s: " @@ -462,8 +462,9 @@ TRACE_EVENT(balance_dirty_pages, unsigned long freerun = (thresh + bg_thresh) / 2; strlcpy(__entry->bdi, dev_name(bdi->dev), 32); - __entry->limit = global_dirty_limit; - __entry->setpoint = (global_dirty_limit + freerun) / 2; + __entry->limit = global_wb_domain.dirty_limit; + __entry->setpoint = (global_wb_domain.dirty_limit + + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); diff --git a/init/Kconfig b/init/Kconfig index b999fa3..7260b27 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1127,6 +1127,11 @@ config DEBUG_BLK_CGROUP Enable some debugging help. Currently it exports additional stat files in a cgroup which can be useful for debugging. +config CGROUP_WRITEBACK + bool + depends on MEMCG && BLK_CGROUP + default y + endif # CGROUPS config CHECKPOINT_RESTORE diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 000e7b3..7756da3 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -18,6 +18,7 @@ struct backing_dev_info noop_backing_dev_info = { .name = "noop", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; +EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; @@ -48,7 +49,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) struct bdi_writeback *wb = &bdi->wb; unsigned long background_thresh; unsigned long dirty_thresh; - unsigned long bdi_thresh; + unsigned long wb_thresh; unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time; struct inode *inode; @@ -66,7 +67,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) spin_unlock(&wb->list_lock); global_dirty_limits(&background_thresh, &dirty_thresh); - bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); + wb_thresh = wb_calc_thresh(wb, dirty_thresh); #define K(x) ((x) << (PAGE_SHIFT - 10)) seq_printf(m, @@ -84,19 +85,19 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", - (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), - (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), - K(bdi_thresh), + (unsigned long) K(wb_stat(wb, WB_WRITEBACK)), + (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)), + K(wb_thresh), K(dirty_thresh), K(background_thresh), - (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)), - (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)), - (unsigned long) K(bdi->write_bandwidth), + (unsigned long) K(wb_stat(wb, WB_DIRTIED)), + (unsigned long) K(wb_stat(wb, WB_WRITTEN)), + (unsigned long) K(wb->write_bandwidth), nr_dirty, nr_io, nr_more_io, nr_dirty_time, - !list_empty(&bdi->bdi_list), bdi->state); + !list_empty(&bdi->bdi_list), bdi->wb.state); #undef K return 0; @@ -255,13 +256,8 @@ static int __init default_bdi_init(void) } subsys_initcall(default_bdi_init); -int bdi_has_dirty_io(struct backing_dev_info *bdi) -{ - return wb_has_dirty_io(&bdi->wb); -} - /* - * This function is used when the first inode for this bdi is marked dirty. It + * This function is used when the first inode for this wb is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just @@ -274,162 +270,550 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) * We have to be careful not to postpone flush work if it is scheduled for * earlier. Thus we use queue_delayed_work(). */ -void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi) +void wb_wakeup_delayed(struct bdi_writeback *wb) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); - spin_lock_bh(&bdi->wb_lock); - if (test_bit(BDI_registered, &bdi->state)) - queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); - spin_unlock_bh(&bdi->wb_lock); + spin_lock_bh(&wb->work_lock); + if (test_bit(WB_registered, &wb->state)) + queue_delayed_work(bdi_wq, &wb->dwork, timeout); + spin_unlock_bh(&wb->work_lock); } /* - * Remove bdi from bdi_list, and ensure that it is no longer visible + * Initial write bandwidth: 100 MB/s */ -static void bdi_remove_from_list(struct backing_dev_info *bdi) -{ - spin_lock_bh(&bdi_lock); - list_del_rcu(&bdi->bdi_list); - spin_unlock_bh(&bdi_lock); - - synchronize_rcu_expedited(); -} +#define INIT_BW (100 << (20 - PAGE_SHIFT)) -int bdi_register(struct backing_dev_info *bdi, struct device *parent, - const char *fmt, ...) +static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, + gfp_t gfp) { - va_list args; - struct device *dev; + int i, err; - if (bdi->dev) /* The driver needs to use separate queues per device */ - return 0; + memset(wb, 0, sizeof(*wb)); - va_start(args, fmt); - dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args); - va_end(args); - if (IS_ERR(dev)) - return PTR_ERR(dev); + wb->bdi = bdi; + wb->last_old_flush = jiffies; + INIT_LIST_HEAD(&wb->b_dirty); + INIT_LIST_HEAD(&wb->b_io); + INIT_LIST_HEAD(&wb->b_more_io); + INIT_LIST_HEAD(&wb->b_dirty_time); + spin_lock_init(&wb->list_lock); - bdi->dev = dev; + wb->bw_time_stamp = jiffies; + wb->balanced_dirty_ratelimit = INIT_BW; + wb->dirty_ratelimit = INIT_BW; + wb->write_bandwidth = INIT_BW; + wb->avg_write_bandwidth = INIT_BW; - bdi_debug_register(bdi, dev_name(dev)); - set_bit(BDI_registered, &bdi->state); + spin_lock_init(&wb->work_lock); + INIT_LIST_HEAD(&wb->work_list); + INIT_DELAYED_WORK(&wb->dwork, wb_workfn); - spin_lock_bh(&bdi_lock); - list_add_tail_rcu(&bdi->bdi_list, &bdi_list); - spin_unlock_bh(&bdi_lock); + err = fprop_local_init_percpu(&wb->completions, gfp); + if (err) + return err; - trace_writeback_bdi_register(bdi); - return 0; -} -EXPORT_SYMBOL(bdi_register); + for (i = 0; i < NR_WB_STAT_ITEMS; i++) { + err = percpu_counter_init(&wb->stat[i], 0, gfp); + if (err) { + while (--i) + percpu_counter_destroy(&wb->stat[i]); + fprop_local_destroy_percpu(&wb->completions); + return err; + } + } -int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) -{ - return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev)); + return 0; } -EXPORT_SYMBOL(bdi_register_dev); /* * Remove bdi from the global list and shutdown any threads we have running */ -static void bdi_wb_shutdown(struct backing_dev_info *bdi) +static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ - spin_lock_bh(&bdi->wb_lock); - if (!test_and_clear_bit(BDI_registered, &bdi->state)) { - spin_unlock_bh(&bdi->wb_lock); + spin_lock_bh(&wb->work_lock); + if (!test_and_clear_bit(WB_registered, &wb->state)) { + spin_unlock_bh(&wb->work_lock); return; } - spin_unlock_bh(&bdi->wb_lock); + spin_unlock_bh(&wb->work_lock); /* - * Make sure nobody finds us on the bdi_list anymore + * Drain work list and shutdown the delayed_work. !WB_registered + * tells wb_workfn() that @wb is dying and its work_list needs to + * be drained no matter what. */ - bdi_remove_from_list(bdi); + mod_delayed_work(bdi_wq, &wb->dwork, 0); + flush_delayed_work(&wb->dwork); + WARN_ON(!list_empty(&wb->work_list)); +} + +static void wb_exit(struct bdi_writeback *wb) +{ + int i; + + WARN_ON(delayed_work_pending(&wb->dwork)); + + for (i = 0; i < NR_WB_STAT_ITEMS; i++) + percpu_counter_destroy(&wb->stat[i]); + + fprop_local_destroy_percpu(&wb->completions); +} + +#ifdef CONFIG_CGROUP_WRITEBACK + +#include <linux/memcontrol.h> + +/* + * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree, + * blkcg->cgwb_list, and memcg->cgwb_list. bdi->cgwb_tree is also RCU + * protected. cgwb_release_wait is used to wait for the completion of cgwb + * releases from bdi destruction path. + */ +static DEFINE_SPINLOCK(cgwb_lock); +static DECLARE_WAIT_QUEUE_HEAD(cgwb_release_wait); + +/** + * wb_congested_get_create - get or create a wb_congested + * @bdi: associated bdi + * @blkcg_id: ID of the associated blkcg + * @gfp: allocation mask + * + * Look up the wb_congested for @blkcg_id on @bdi. If missing, create one. + * The returned wb_congested has its reference count incremented. Returns + * NULL on failure. + */ +struct bdi_writeback_congested * +wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) +{ + struct bdi_writeback_congested *new_congested = NULL, *congested; + struct rb_node **node, *parent; + unsigned long flags; + + if (blkcg_id == 1) + return &bdi->wb_congested; +retry: + spin_lock_irqsave(&cgwb_lock, flags); + + node = &bdi->cgwb_congested_tree.rb_node; + parent = NULL; + + while (*node != NULL) { + parent = *node; + congested = container_of(parent, struct bdi_writeback_congested, + rb_node); + if (congested->blkcg_id < blkcg_id) + node = &parent->rb_left; + else if (congested->blkcg_id > blkcg_id) + node = &parent->rb_right; + else + goto found; + } + + if (new_congested) { + /* !found and storage for new one already allocated, insert */ + congested = new_congested; + new_congested = NULL; + rb_link_node(&congested->rb_node, parent, node); + rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); + atomic_inc(&bdi->usage_cnt); + goto found; + } + + spin_unlock_irqrestore(&cgwb_lock, flags); + + /* allocate storage for new one and retry */ + new_congested = kzalloc(sizeof(*new_congested), gfp); + if (!new_congested) + return NULL; + + atomic_set(&new_congested->refcnt, 0); + new_congested->bdi = bdi; + new_congested->blkcg_id = blkcg_id; + goto retry; + +found: + atomic_inc(&congested->refcnt); + spin_unlock_irqrestore(&cgwb_lock, flags); + kfree(new_congested); + return congested; +} + +/** + * wb_congested_put - put a wb_congested + * @congested: wb_congested to put + * + * Put @congested and destroy it if the refcnt reaches zero. + */ +void wb_congested_put(struct bdi_writeback_congested *congested) +{ + struct backing_dev_info *bdi = congested->bdi; + unsigned long flags; + + if (congested->blkcg_id == 1) + return; + + local_irq_save(flags); + if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) { + local_irq_restore(flags); + return; + } + + rb_erase(&congested->rb_node, &congested->bdi->cgwb_congested_tree); + spin_unlock_irqrestore(&cgwb_lock, flags); + kfree(congested); + + if (atomic_dec_and_test(&bdi->usage_cnt)) + wake_up_all(&cgwb_release_wait); +} + +static void cgwb_release_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb = container_of(work, struct bdi_writeback, + release_work); + struct backing_dev_info *bdi = wb->bdi; + + wb_shutdown(wb); + + css_put(wb->memcg_css); + css_put(wb->blkcg_css); + wb_congested_put(wb->congested); + + fprop_local_destroy_percpu(&wb->memcg_completions); + percpu_ref_exit(&wb->refcnt); + wb_exit(wb); + kfree_rcu(wb, rcu); + + if (atomic_dec_and_test(&bdi->usage_cnt)) + wake_up_all(&cgwb_release_wait); +} + +static void cgwb_release(struct percpu_ref *refcnt) +{ + struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, + refcnt); + schedule_work(&wb->release_work); +} + +static void cgwb_kill(struct bdi_writeback *wb) +{ + lockdep_assert_held(&cgwb_lock); + + WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); + list_del(&wb->memcg_node); + list_del(&wb->blkcg_node); + percpu_ref_kill(&wb->refcnt); +} + +static int cgwb_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, gfp_t gfp) +{ + struct mem_cgroup *memcg; + struct cgroup_subsys_state *blkcg_css; + struct blkcg *blkcg; + struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; + struct bdi_writeback *wb; + unsigned long flags; + int ret = 0; + + memcg = mem_cgroup_from_css(memcg_css); + blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &blkio_cgrp_subsys); + blkcg = css_to_blkcg(blkcg_css); + memcg_cgwb_list = mem_cgroup_cgwb_list(memcg); + blkcg_cgwb_list = &blkcg->cgwb_list; + + /* look up again under lock and discard on blkcg mismatch */ + spin_lock_irqsave(&cgwb_lock, flags); + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + if (wb && wb->blkcg_css != blkcg_css) { + cgwb_kill(wb); + wb = NULL; + } + spin_unlock_irqrestore(&cgwb_lock, flags); + if (wb) + goto out_put; + + /* need to create a new one */ + wb = kmalloc(sizeof(*wb), gfp); + if (!wb) + return -ENOMEM; + + ret = wb_init(wb, bdi, gfp); + if (ret) + goto err_free; + + ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); + if (ret) + goto err_wb_exit; + + ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); + if (ret) + goto err_ref_exit; + + wb->congested = wb_congested_get_create(bdi, blkcg_css->id, gfp); + if (!wb->congested) { + ret = -ENOMEM; + goto err_fprop_exit; + } + + wb->memcg_css = memcg_css; + wb->blkcg_css = blkcg_css; + INIT_WORK(&wb->release_work, cgwb_release_workfn); + set_bit(WB_registered, &wb->state); /* - * Drain work list and shutdown the delayed_work. At this point, - * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi - * is dying and its work_list needs to be drained no matter what. + * The root wb determines the registered state of the whole bdi and + * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate + * whether they're still online. Don't link @wb if any is dead. + * See wb_memcg_offline() and wb_blkcg_offline(). */ - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); - flush_delayed_work(&bdi->wb.dwork); + ret = -ENODEV; + spin_lock_irqsave(&cgwb_lock, flags); + if (test_bit(WB_registered, &bdi->wb.state) && + blkcg_cgwb_list->next && memcg_cgwb_list->next) { + /* we might have raced another instance of this function */ + ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); + if (!ret) { + atomic_inc(&bdi->usage_cnt); + list_add(&wb->memcg_node, memcg_cgwb_list); + list_add(&wb->blkcg_node, blkcg_cgwb_list); + css_get(memcg_css); + css_get(blkcg_css); + } + } + spin_unlock_irqrestore(&cgwb_lock, flags); + if (ret) { + if (ret == -EEXIST) + ret = 0; + goto err_put_congested; + } + goto out_put; + +err_put_congested: + wb_congested_put(wb->congested); +err_fprop_exit: + fprop_local_destroy_percpu(&wb->memcg_completions); +err_ref_exit: + percpu_ref_exit(&wb->refcnt); +err_wb_exit: + wb_exit(wb); +err_free: + kfree(wb); +out_put: + css_put(blkcg_css); + return ret; } -static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) +/** + * wb_get_create - get wb for a given memcg, create if necessary + * @bdi: target bdi + * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) + * @gfp: allocation mask to use + * + * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to + * create one. The returned wb has its refcount incremented. + * + * This function uses css_get() on @memcg_css and thus expects its refcnt + * to be positive on invocation. IOW, rcu_read_lock() protection on + * @memcg_css isn't enough. try_get it before calling this function. + * + * A wb is keyed by its associated memcg. As blkcg implicitly enables + * memcg on the default hierarchy, memcg association is guaranteed to be + * more specific (equal or descendant to the associated blkcg) and thus can + * identify both the memcg and blkcg associations. + * + * Because the blkcg associated with a memcg may change as blkcg is enabled + * and disabled closer to root in the hierarchy, each wb keeps track of + * both the memcg and blkcg associated with it and verifies the blkcg on + * each lookup. On mismatch, the existing wb is discarded and a new one is + * created. + */ +struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css, + gfp_t gfp) { - memset(wb, 0, sizeof(*wb)); + struct bdi_writeback *wb; + + might_sleep_if(gfp & __GFP_WAIT); + + if (!memcg_css->parent) + return &bdi->wb; + + do { + rcu_read_lock(); + wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); + if (wb) { + struct cgroup_subsys_state *blkcg_css; + + /* see whether the blkcg association has changed */ + blkcg_css = cgroup_get_e_css(memcg_css->cgroup, + &blkio_cgrp_subsys); + if (unlikely(wb->blkcg_css != blkcg_css || + !wb_tryget(wb))) + wb = NULL; + css_put(blkcg_css); + } + rcu_read_unlock(); + } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); + + return wb; +} - wb->bdi = bdi; - wb->last_old_flush = jiffies; - INIT_LIST_HEAD(&wb->b_dirty); - INIT_LIST_HEAD(&wb->b_io); - INIT_LIST_HEAD(&wb->b_more_io); - INIT_LIST_HEAD(&wb->b_dirty_time); - spin_lock_init(&wb->list_lock); - INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn); +static void cgwb_bdi_init(struct backing_dev_info *bdi) +{ + bdi->wb.memcg_css = mem_cgroup_root_css; + bdi->wb.blkcg_css = blkcg_root_css; + bdi->wb_congested.blkcg_id = 1; + INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); + bdi->cgwb_congested_tree = RB_ROOT; + atomic_set(&bdi->usage_cnt, 1); } -/* - * Initial write bandwidth: 100 MB/s +static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +{ + struct radix_tree_iter iter; + void **slot; + + WARN_ON(test_bit(WB_registered, &bdi->wb.state)); + + spin_lock_irq(&cgwb_lock); + radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) + cgwb_kill(*slot); + spin_unlock_irq(&cgwb_lock); + + /* + * All cgwb's and their congested states must be shutdown and + * released before returning. Drain the usage counter to wait for + * all cgwb's and cgwb_congested's ever created on @bdi. + */ + atomic_dec(&bdi->usage_cnt); + wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt)); +} + +/** + * wb_memcg_offline - kill all wb's associated with a memcg being offlined + * @memcg: memcg being offlined + * + * Also prevents creation of any new wb's associated with @memcg. */ -#define INIT_BW (100 << (20 - PAGE_SHIFT)) +void wb_memcg_offline(struct mem_cgroup *memcg) +{ + LIST_HEAD(to_destroy); + struct list_head *memcg_cgwb_list = mem_cgroup_cgwb_list(memcg); + struct bdi_writeback *wb, *next; + + spin_lock_irq(&cgwb_lock); + list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) + cgwb_kill(wb); + memcg_cgwb_list->next = NULL; /* prevent new wb's */ + spin_unlock_irq(&cgwb_lock); +} + +/** + * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined + * @blkcg: blkcg being offlined + * + * Also prevents creation of any new wb's associated with @blkcg. + */ +void wb_blkcg_offline(struct blkcg *blkcg) +{ + LIST_HEAD(to_destroy); + struct bdi_writeback *wb, *next; + + spin_lock_irq(&cgwb_lock); + list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node) + cgwb_kill(wb); + blkcg->cgwb_list.next = NULL; /* prevent new wb's */ + spin_unlock_irq(&cgwb_lock); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static void cgwb_bdi_init(struct backing_dev_info *bdi) { } +static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } + +#endif /* CONFIG_CGROUP_WRITEBACK */ int bdi_init(struct backing_dev_info *bdi) { - int i, err; + int err; bdi->dev = NULL; bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = FPROP_FRAC_BASE; - spin_lock_init(&bdi->wb_lock); INIT_LIST_HEAD(&bdi->bdi_list); - INIT_LIST_HEAD(&bdi->work_list); + init_waitqueue_head(&bdi->wb_waitq); - bdi_wb_init(&bdi->wb, bdi); + err = wb_init(&bdi->wb, bdi, GFP_KERNEL); + if (err) + return err; - for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { - err = percpu_counter_init(&bdi->bdi_stat[i], 0, GFP_KERNEL); - if (err) - goto err; - } + bdi->wb_congested.state = 0; + bdi->wb.congested = &bdi->wb_congested; - bdi->dirty_exceeded = 0; + cgwb_bdi_init(bdi); + return 0; +} +EXPORT_SYMBOL(bdi_init); - bdi->bw_time_stamp = jiffies; - bdi->written_stamp = 0; +int bdi_register(struct backing_dev_info *bdi, struct device *parent, + const char *fmt, ...) +{ + va_list args; + struct device *dev; - bdi->balanced_dirty_ratelimit = INIT_BW; - bdi->dirty_ratelimit = INIT_BW; - bdi->write_bandwidth = INIT_BW; - bdi->avg_write_bandwidth = INIT_BW; + if (bdi->dev) /* The driver needs to use separate queues per device */ + return 0; - err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL); + va_start(args, fmt); + dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args); + va_end(args); + if (IS_ERR(dev)) + return PTR_ERR(dev); - if (err) { -err: - while (i--) - percpu_counter_destroy(&bdi->bdi_stat[i]); - } + bdi->dev = dev; - return err; + bdi_debug_register(bdi, dev_name(dev)); + set_bit(WB_registered, &bdi->wb.state); + + spin_lock_bh(&bdi_lock); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); + + trace_writeback_bdi_register(bdi); + return 0; } -EXPORT_SYMBOL(bdi_init); +EXPORT_SYMBOL(bdi_register); -void bdi_destroy(struct backing_dev_info *bdi) +int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) { - int i; + return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev)); +} +EXPORT_SYMBOL(bdi_register_dev); + +/* + * Remove bdi from bdi_list, and ensure that it is no longer visible + */ +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi_lock); + list_del_rcu(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); - bdi_wb_shutdown(bdi); - bdi_set_min_ratio(bdi, 0); + synchronize_rcu_expedited(); +} - WARN_ON(!list_empty(&bdi->work_list)); - WARN_ON(delayed_work_pending(&bdi->wb.dwork)); +void bdi_destroy(struct backing_dev_info *bdi) +{ + /* make sure nobody finds us on the bdi_list anymore */ + bdi_remove_from_list(bdi); + wb_shutdown(&bdi->wb); + cgwb_bdi_destroy(bdi); if (bdi->dev) { bdi_debug_unregister(bdi); @@ -437,9 +821,7 @@ void bdi_destroy(struct backing_dev_info *bdi) bdi->dev = NULL; } - for (i = 0; i < NR_BDI_STAT_ITEMS; i++) - percpu_counter_destroy(&bdi->bdi_stat[i]); - fprop_local_destroy_percpu(&bdi->completions); + wb_exit(&bdi->wb); } EXPORT_SYMBOL(bdi_destroy); @@ -472,31 +854,31 @@ static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; -static atomic_t nr_bdi_congested[2]; +static atomic_t nr_wb_congested[2]; -void clear_bdi_congested(struct backing_dev_info *bdi, int sync) +void clear_wb_congested(struct bdi_writeback_congested *congested, int sync) { - enum bdi_state bit; wait_queue_head_t *wqh = &congestion_wqh[sync]; + enum wb_state bit; - bit = sync ? BDI_sync_congested : BDI_async_congested; - if (test_and_clear_bit(bit, &bdi->state)) - atomic_dec(&nr_bdi_congested[sync]); + bit = sync ? WB_sync_congested : WB_async_congested; + if (test_and_clear_bit(bit, &congested->state)) + atomic_dec(&nr_wb_congested[sync]); smp_mb__after_atomic(); if (waitqueue_active(wqh)) wake_up(wqh); } -EXPORT_SYMBOL(clear_bdi_congested); +EXPORT_SYMBOL(clear_wb_congested); -void set_bdi_congested(struct backing_dev_info *bdi, int sync) +void set_wb_congested(struct bdi_writeback_congested *congested, int sync) { - enum bdi_state bit; + enum wb_state bit; - bit = sync ? BDI_sync_congested : BDI_async_congested; - if (!test_and_set_bit(bit, &bdi->state)) - atomic_inc(&nr_bdi_congested[sync]); + bit = sync ? WB_sync_congested : WB_async_congested; + if (!test_and_set_bit(bit, &congested->state)) + atomic_inc(&nr_wb_congested[sync]); } -EXPORT_SYMBOL(set_bdi_congested); +EXPORT_SYMBOL(set_wb_congested); /** * congestion_wait - wait for a backing_dev to become uncongested @@ -555,7 +937,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) * encountered in the current zone, yield if necessary instead * of sleeping on the congestion queue */ - if (atomic_read(&nr_bdi_congested[sync]) == 0 || + if (atomic_read(&nr_wb_congested[sync]) == 0 || !test_bit(ZONE_CONGESTED, &zone->flags)) { cond_resched(); diff --git a/mm/fadvise.c b/mm/fadvise.c index 4a3907c..b8a5bc6 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -115,7 +115,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) case POSIX_FADV_NOREUSE: break; case POSIX_FADV_DONTNEED: - if (!bdi_write_congested(bdi)) + if (!inode_write_congested(mapping->host)) __filemap_fdatawrite_range(mapping, offset, endbyte, WB_SYNC_NONE); diff --git a/mm/filemap.c b/mm/filemap.c index 8d17cee..11f10ef 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -100,6 +100,7 @@ * ->tree_lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) + * ->memcg->move_lock (page_remove_rmap->mem_cgroup_begin_page_stat) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) @@ -174,9 +175,11 @@ static void page_cache_tree_delete(struct address_space *mapping, /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage - * is safe. The caller must hold the mapping's tree_lock. + * is safe. The caller must hold the mapping's tree_lock and + * mem_cgroup_begin_page_stat(). */ -void __delete_from_page_cache(struct page *page, void *shadow) +void __delete_from_page_cache(struct page *page, void *shadow, + struct mem_cgroup *memcg) { struct address_space *mapping = page->mapping; @@ -212,7 +215,8 @@ void __delete_from_page_cache(struct page *page, void *shadow) * anyway will be cleared before returning page into buddy allocator. */ if (WARN_ON_ONCE(PageDirty(page))) - account_page_cleaned(page, mapping); + account_page_cleaned(page, mapping, memcg, + inode_to_wb(mapping->host)); } /** @@ -226,14 +230,20 @@ void __delete_from_page_cache(struct page *page, void *shadow) void delete_from_page_cache(struct page *page) { struct address_space *mapping = page->mapping; + struct mem_cgroup *memcg; + unsigned long flags; + void (*freepage)(struct page *); BUG_ON(!PageLocked(page)); freepage = mapping->a_ops->freepage; - spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(page, NULL); - spin_unlock_irq(&mapping->tree_lock); + + memcg = mem_cgroup_begin_page_stat(page); + spin_lock_irqsave(&mapping->tree_lock, flags); + __delete_from_page_cache(page, NULL, memcg); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); if (freepage) freepage(page); @@ -283,7 +293,9 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, if (!mapping_cap_writeback_dirty(mapping)) return 0; + wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); + wbc_detach_inode(&wbc); return ret; } @@ -472,6 +484,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) if (!error) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *); + struct mem_cgroup *memcg; + unsigned long flags; pgoff_t offset = old->index; freepage = mapping->a_ops->freepage; @@ -480,8 +494,9 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->mapping = mapping; new->index = offset; - spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(old, NULL); + memcg = mem_cgroup_begin_page_stat(old); + spin_lock_irqsave(&mapping->tree_lock, flags); + __delete_from_page_cache(old, NULL, memcg); error = radix_tree_insert(&mapping->page_tree, offset, new); BUG_ON(error); mapping->nrpages++; @@ -493,7 +508,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) __inc_zone_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(new)) __inc_zone_page_state(new, NR_SHMEM); - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); mem_cgroup_migrate(old, new, true); radix_tree_preload_end(); if (freepage) diff --git a/mm/madvise.c b/mm/madvise.c index d551475..64bb8a2 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> +#include <linux/backing-dev.h> #include <linux/swap.h> #include <linux/swapops.h> diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e65f7b0..acb93c5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -77,6 +77,7 @@ EXPORT_SYMBOL(memory_cgrp_subsys); #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; +struct cgroup_subsys_state *mem_cgroup_root_css __read_mostly; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP @@ -90,6 +91,7 @@ static const char * const mem_cgroup_stat_names[] = { "rss", "rss_huge", "mapped_file", + "dirty", "writeback", "swap", }; @@ -322,11 +324,6 @@ struct mem_cgroup { * percpu counter. */ struct mem_cgroup_stat_cpu __percpu *stat; - /* - * used when a cpu is offlined or other synchronizations - * See mem_cgroup_read_stat(). - */ - struct mem_cgroup_stat_cpu nocpu_base; spinlock_t pcp_counter_lock; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) @@ -346,6 +343,11 @@ struct mem_cgroup { atomic_t numainfo_updating; #endif +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; + struct wb_domain cgwb_domain; +#endif + /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; @@ -596,6 +598,39 @@ struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) return &memcg->css; } +/** + * mem_cgroup_css_from_page - css of the memcg associated with a page + * @page: page of interest + * + * If memcg is bound to the default hierarchy, css of the memcg associated + * with @page is returned. The returned css remains associated with @page + * until it is released. + * + * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup + * is returned. + * + * XXX: The above description of behavior on the default hierarchy isn't + * strictly true yet as replace_page_cache_page() can modify the + * association before @page is released even on the default hierarchy; + * however, the current and planned usages don't mix the the two functions + * and replace_page_cache_page() will soon be updated to make the invariant + * actually true. + */ +struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); + + memcg = page->mem_cgroup; + + if (!memcg || !cgroup_on_dfl(memcg->css.cgroup)) + memcg = root_mem_cgroup; + + rcu_read_unlock(); + return &memcg->css; +} + static struct mem_cgroup_per_zone * mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page) { @@ -795,15 +830,8 @@ static long mem_cgroup_read_stat(struct mem_cgroup *memcg, long val = 0; int cpu; - get_online_cpus(); - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) val += per_cpu(memcg->stat->count[idx], cpu); -#ifdef CONFIG_HOTPLUG_CPU - spin_lock(&memcg->pcp_counter_lock); - val += memcg->nocpu_base.count[idx]; - spin_unlock(&memcg->pcp_counter_lock); -#endif - put_online_cpus(); return val; } @@ -813,15 +841,8 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, unsigned long val = 0; int cpu; - get_online_cpus(); - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) val += per_cpu(memcg->stat->events[idx], cpu); -#ifdef CONFIG_HOTPLUG_CPU - spin_lock(&memcg->pcp_counter_lock); - val += memcg->nocpu_base.events[idx]; - spin_unlock(&memcg->pcp_counter_lock); -#endif - put_online_cpus(); return val; } @@ -2020,6 +2041,7 @@ again: return memcg; } +EXPORT_SYMBOL(mem_cgroup_begin_page_stat); /** * mem_cgroup_end_page_stat - finish a page state statistics transaction @@ -2038,6 +2060,7 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) rcu_read_unlock(); } +EXPORT_SYMBOL(mem_cgroup_end_page_stat); /** * mem_cgroup_update_page_stat - update page state statistics @@ -2178,37 +2201,12 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) mutex_unlock(&percpu_charge_mutex); } -/* - * This function drains percpu counter value from DEAD cpu and - * move it to local cpu. Note that this function can be preempted. - */ -static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu) -{ - int i; - - spin_lock(&memcg->pcp_counter_lock); - for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - long x = per_cpu(memcg->stat->count[i], cpu); - - per_cpu(memcg->stat->count[i], cpu) = 0; - memcg->nocpu_base.count[i] += x; - } - for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) { - unsigned long x = per_cpu(memcg->stat->events[i], cpu); - - per_cpu(memcg->stat->events[i], cpu) = 0; - memcg->nocpu_base.events[i] += x; - } - spin_unlock(&memcg->pcp_counter_lock); -} - static int memcg_cpu_hotplug_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { int cpu = (unsigned long)hcpu; struct memcg_stock_pcp *stock; - struct mem_cgroup *iter; if (action == CPU_ONLINE) return NOTIFY_OK; @@ -2216,9 +2214,6 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) return NOTIFY_OK; - for_each_mem_cgroup(iter) - mem_cgroup_drain_pcp_counter(iter, cpu); - stock = &per_cpu(memcg_stock, cpu); drain_stock(stock); return NOTIFY_OK; @@ -4004,6 +3999,98 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg) } #endif +#ifdef CONFIG_CGROUP_WRITEBACK + +struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg) +{ + return &memcg->cgwb_list; +} + +static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) +{ + return wb_domain_init(&memcg->cgwb_domain, gfp); +} + +static void memcg_wb_domain_exit(struct mem_cgroup *memcg) +{ + wb_domain_exit(&memcg->cgwb_domain); +} + +static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) +{ + wb_domain_size_changed(&memcg->cgwb_domain); +} + +struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + + if (!memcg->css.parent) + return NULL; + + return &memcg->cgwb_domain; +} + +/** + * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg + * @wb: bdi_writeback in question + * @pavail: out parameter for number of available pages + * @pdirty: out parameter for number of dirty pages + * @pwriteback: out parameter for number of pages under writeback + * + * Determine the numbers of available, dirty, and writeback pages in @wb's + * memcg. Dirty and writeback are self-explanatory. Available is a bit + * more involved. + * + * A memcg's headroom is "min(max, high) - used". The available memory is + * calculated as the lowest headroom of itself and the ancestors plus the + * number of pages already being used for file pages. Note that this + * doesn't consider the actual amount of available memory in the system. + * The caller should further cap *@pavail accordingly. + */ +void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail, + unsigned long *pdirty, unsigned long *pwriteback) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); + struct mem_cgroup *parent; + unsigned long head_room = PAGE_COUNTER_MAX; + unsigned long file_pages; + + *pdirty = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_DIRTY); + + /* this should eventually include NR_UNSTABLE_NFS */ + *pwriteback = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_WRITEBACK); + + file_pages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | + (1 << LRU_ACTIVE_FILE)); + while ((parent = parent_mem_cgroup(memcg))) { + unsigned long ceiling = min(memcg->memory.limit, memcg->high); + unsigned long used = page_counter_read(&memcg->memory); + + head_room = min(head_room, ceiling - min(ceiling, used)); + memcg = parent; + } + + *pavail = file_pages + head_room; +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp) +{ + return 0; +} + +static void memcg_wb_domain_exit(struct mem_cgroup *memcg) +{ +} + +static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) +{ +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * DO NOT USE IN NEW FILES. * @@ -4388,9 +4475,15 @@ static struct mem_cgroup *mem_cgroup_alloc(void) memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!memcg->stat) goto out_free; + + if (memcg_wb_domain_init(memcg, GFP_KERNEL)) + goto out_free_stat; + spin_lock_init(&memcg->pcp_counter_lock); return memcg; +out_free_stat: + free_percpu(memcg->stat); out_free: kfree(memcg); return NULL; @@ -4417,6 +4510,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) free_mem_cgroup_per_zone_info(memcg, node); free_percpu(memcg->stat); + memcg_wb_domain_exit(memcg); kfree(memcg); } @@ -4449,6 +4543,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) /* root ? */ if (parent_css == NULL) { root_mem_cgroup = memcg; + mem_cgroup_root_css = &memcg->css; page_counter_init(&memcg->memory, NULL); memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; @@ -4467,7 +4562,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) #ifdef CONFIG_MEMCG_KMEM memcg->kmemcg_id = -1; #endif - +#ifdef CONFIG_CGROUP_WRITEBACK + INIT_LIST_HEAD(&memcg->cgwb_list); +#endif return &memcg->css; free_out: @@ -4555,6 +4652,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) vmpressure_cleanup(&memcg->vmpressure); memcg_deactivate_kmem(memcg); + + wb_memcg_offline(memcg); } static void mem_cgroup_css_free(struct cgroup_subsys_state *css) @@ -4588,6 +4687,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) memcg->low = 0; memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; + memcg_wb_domain_size_changed(memcg); } #ifdef CONFIG_MMU @@ -4757,6 +4857,7 @@ static int mem_cgroup_move_account(struct page *page, { unsigned long flags; int ret; + bool anon; VM_BUG_ON(from == to); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -4782,15 +4883,33 @@ static int mem_cgroup_move_account(struct page *page, if (page->mem_cgroup != from) goto out_unlock; + anon = PageAnon(page); + spin_lock_irqsave(&from->move_lock, flags); - if (!PageAnon(page) && page_mapped(page)) { + if (!anon && page_mapped(page)) { __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], nr_pages); __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], nr_pages); } + /* + * move_lock grabbed above and caller set from->moving_account, so + * mem_cgroup_update_page_stat() will serialize updates to PageDirty. + * So mapping should be stable for dirty pages. + */ + if (!anon && PageDirty(page)) { + struct address_space *mapping = page_mapping(page); + + if (mapping_cap_account_dirty(mapping)) { + __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_DIRTY], + nr_pages); + __this_cpu_add(to->stat->count[MEM_CGROUP_STAT_DIRTY], + nr_pages); + } + } + if (PageWriteback(page)) { __this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_WRITEBACK], nr_pages); @@ -5306,6 +5425,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, memcg->high = high; + memcg_wb_domain_size_changed(memcg); return nbytes; } @@ -5338,6 +5458,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (err) return err; + memcg_wb_domain_size_changed(memcg); return nbytes; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index eb59f7e..22cddd3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -122,31 +122,31 @@ EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ -unsigned long global_dirty_limit; +struct wb_domain global_wb_domain; -/* - * Scale the writeback cache size proportional to the relative writeout speeds. - * - * We do this by keeping a floating proportion between BDIs, based on page - * writeback completions [end_page_writeback()]. Those devices that write out - * pages fastest will get the larger share, while the slower will get a smaller - * share. - * - * We use page writeout completions because we are interested in getting rid of - * dirty pages. Having them written out is the primary goal. - * - * We introduce a concept of time, a period over which we measure these events, - * because demand can/will vary over time. The length of this period itself is - * measured in page writeback completions. - * - */ -static struct fprop_global writeout_completions; +/* consolidated parameters for balance_dirty_pages() and its subroutines */ +struct dirty_throttle_control { +#ifdef CONFIG_CGROUP_WRITEBACK + struct wb_domain *dom; + struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ +#endif + struct bdi_writeback *wb; + struct fprop_local_percpu *wb_completions; -static void writeout_period(unsigned long t); -/* Timer for aging of writeout_completions */ -static struct timer_list writeout_period_timer = - TIMER_DEFERRED_INITIALIZER(writeout_period, 0, 0); -static unsigned long writeout_period_time = 0; + unsigned long avail; /* dirtyable */ + unsigned long dirty; /* file_dirty + write + nfs */ + unsigned long thresh; /* dirty threshold */ + unsigned long bg_thresh; /* dirty background threshold */ + + unsigned long wb_dirty; /* per-wb counterparts */ + unsigned long wb_thresh; + unsigned long wb_bg_thresh; + + unsigned long pos_ratio; +}; + +#define DTC_INIT_COMMON(__wb) .wb = (__wb), \ + .wb_completions = &(__wb)->completions /* * Length of period for aging writeout fractions of bdis. This is an @@ -155,6 +155,97 @@ static unsigned long writeout_period_time = 0; */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) +#ifdef CONFIG_CGROUP_WRITEBACK + +#define GDTC_INIT(__wb) .dom = &global_wb_domain, \ + DTC_INIT_COMMON(__wb) +#define GDTC_INIT_NO_WB .dom = &global_wb_domain +#define MDTC_INIT(__wb, __gdtc) .dom = mem_cgroup_wb_domain(__wb), \ + .gdtc = __gdtc, \ + DTC_INIT_COMMON(__wb) + +static bool mdtc_valid(struct dirty_throttle_control *dtc) +{ + return dtc->dom; +} + +static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) +{ + return dtc->dom; +} + +static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) +{ + return mdtc->gdtc; +} + +static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) +{ + return &wb->memcg_completions; +} + +static void wb_min_max_ratio(struct bdi_writeback *wb, + unsigned long *minp, unsigned long *maxp) +{ + unsigned long this_bw = wb->avg_write_bandwidth; + unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); + unsigned long long min = wb->bdi->min_ratio; + unsigned long long max = wb->bdi->max_ratio; + + /* + * @wb may already be clean by the time control reaches here and + * the total may not include its bw. + */ + if (this_bw < tot_bw) { + if (min) { + min *= this_bw; + do_div(min, tot_bw); + } + if (max < 100) { + max *= this_bw; + do_div(max, tot_bw); + } + } + + *minp = min; + *maxp = max; +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +#define GDTC_INIT(__wb) DTC_INIT_COMMON(__wb) +#define GDTC_INIT_NO_WB +#define MDTC_INIT(__wb, __gdtc) + +static bool mdtc_valid(struct dirty_throttle_control *dtc) +{ + return false; +} + +static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) +{ + return &global_wb_domain; +} + +static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) +{ + return NULL; +} + +static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) +{ + return NULL; +} + +static void wb_min_max_ratio(struct bdi_writeback *wb, + unsigned long *minp, unsigned long *maxp) +{ + *minp = wb->bdi->min_ratio; + *maxp = wb->bdi->max_ratio; +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of @@ -250,42 +341,88 @@ static unsigned long global_dirtyable_memory(void) return x + 1; /* Ensure that we never return 0 */ } -/* - * global_dirty_limits - background-writeback and dirty-throttling thresholds +/** + * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain + * @dtc: dirty_throttle_control of interest * - * Calculate the dirty thresholds based on sysctl parameters - * - vm.dirty_background_ratio or vm.dirty_background_bytes - * - vm.dirty_ratio or vm.dirty_bytes - * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and + * Calculate @dtc->thresh and ->bg_thresh considering + * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller + * must ensure that @dtc->avail is set before calling this function. The + * dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and * real-time tasks. */ -void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) +static void domain_dirty_limits(struct dirty_throttle_control *dtc) { - const unsigned long available_memory = global_dirtyable_memory(); - unsigned long background; - unsigned long dirty; + const unsigned long available_memory = dtc->avail; + struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); + unsigned long bytes = vm_dirty_bytes; + unsigned long bg_bytes = dirty_background_bytes; + unsigned long ratio = vm_dirty_ratio; + unsigned long bg_ratio = dirty_background_ratio; + unsigned long thresh; + unsigned long bg_thresh; struct task_struct *tsk; - if (vm_dirty_bytes) - dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE); + /* gdtc is !NULL iff @dtc is for memcg domain */ + if (gdtc) { + unsigned long global_avail = gdtc->avail; + + /* + * The byte settings can't be applied directly to memcg + * domains. Convert them to ratios by scaling against + * globally available memory. + */ + if (bytes) + ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 / + global_avail, 100UL); + if (bg_bytes) + bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 / + global_avail, 100UL); + bytes = bg_bytes = 0; + } + + if (bytes) + thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else - dirty = (vm_dirty_ratio * available_memory) / 100; + thresh = (ratio * available_memory) / 100; - if (dirty_background_bytes) - background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE); + if (bg_bytes) + bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else - background = (dirty_background_ratio * available_memory) / 100; + bg_thresh = (bg_ratio * available_memory) / 100; - if (background >= dirty) - background = dirty / 2; + if (bg_thresh >= thresh) + bg_thresh = thresh / 2; tsk = current; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) { - background += background / 4; - dirty += dirty / 4; + bg_thresh += bg_thresh / 4; + thresh += thresh / 4; } - *pbackground = background; - *pdirty = dirty; - trace_global_dirty_state(background, dirty); + dtc->thresh = thresh; + dtc->bg_thresh = bg_thresh; + + /* we should eventually report the domain in the TP */ + if (!gdtc) + trace_global_dirty_state(bg_thresh, thresh); +} + +/** + * global_dirty_limits - background-writeback and dirty-throttling thresholds + * @pbackground: out parameter for bg_thresh + * @pdirty: out parameter for thresh + * + * Calculate bg_thresh and thresh for global_wb_domain. See + * domain_dirty_limits() for details. + */ +void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; + + gdtc.avail = global_dirtyable_memory(); + domain_dirty_limits(&gdtc); + + *pbackground = gdtc.bg_thresh; + *pdirty = gdtc.thresh; } /** @@ -392,47 +529,52 @@ static unsigned long wp_next_time(unsigned long cur_time) return cur_time; } -/* - * Increment the BDI's writeout completion count and the global writeout - * completion count. Called from test_clear_page_writeback(). - */ -static inline void __bdi_writeout_inc(struct backing_dev_info *bdi) +static void wb_domain_writeout_inc(struct wb_domain *dom, + struct fprop_local_percpu *completions, + unsigned int max_prop_frac) { - __inc_bdi_stat(bdi, BDI_WRITTEN); - __fprop_inc_percpu_max(&writeout_completions, &bdi->completions, - bdi->max_prop_frac); + __fprop_inc_percpu_max(&dom->completions, completions, + max_prop_frac); /* First event after period switching was turned off? */ - if (!unlikely(writeout_period_time)) { + if (!unlikely(dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ - writeout_period_time = wp_next_time(jiffies); - mod_timer(&writeout_period_timer, writeout_period_time); + dom->period_time = wp_next_time(jiffies); + mod_timer(&dom->period_timer, dom->period_time); } } -void bdi_writeout_inc(struct backing_dev_info *bdi) +/* + * Increment @wb's writeout completion count and the global writeout + * completion count. Called from test_clear_page_writeback(). + */ +static inline void __wb_writeout_inc(struct bdi_writeback *wb) { - unsigned long flags; + struct wb_domain *cgdom; - local_irq_save(flags); - __bdi_writeout_inc(bdi); - local_irq_restore(flags); + __inc_wb_stat(wb, WB_WRITTEN); + wb_domain_writeout_inc(&global_wb_domain, &wb->completions, + wb->bdi->max_prop_frac); + + cgdom = mem_cgroup_wb_domain(wb); + if (cgdom) + wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb), + wb->bdi->max_prop_frac); } -EXPORT_SYMBOL_GPL(bdi_writeout_inc); -/* - * Obtain an accurate fraction of the BDI's portion. - */ -static void bdi_writeout_fraction(struct backing_dev_info *bdi, - long *numerator, long *denominator) +void wb_writeout_inc(struct bdi_writeback *wb) { - fprop_fraction_percpu(&writeout_completions, &bdi->completions, - numerator, denominator); + unsigned long flags; + + local_irq_save(flags); + __wb_writeout_inc(wb); + local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use @@ -440,22 +582,46 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi, */ static void writeout_period(unsigned long t) { - int miss_periods = (jiffies - writeout_period_time) / + struct wb_domain *dom = (void *)t; + int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; - if (fprop_new_period(&writeout_completions, miss_periods + 1)) { - writeout_period_time = wp_next_time(writeout_period_time + + if (fprop_new_period(&dom->completions, miss_periods + 1)) { + dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); - mod_timer(&writeout_period_timer, writeout_period_time); + mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ - writeout_period_time = 0; + dom->period_time = 0; } } +int wb_domain_init(struct wb_domain *dom, gfp_t gfp) +{ + memset(dom, 0, sizeof(*dom)); + + spin_lock_init(&dom->lock); + + init_timer_deferrable(&dom->period_timer); + dom->period_timer.function = writeout_period; + dom->period_timer.data = (unsigned long)dom; + + dom->dirty_limit_tstamp = jiffies; + + return fprop_global_init(&dom->completions, gfp); +} + +#ifdef CONFIG_CGROUP_WRITEBACK +void wb_domain_exit(struct wb_domain *dom) +{ + del_timer_sync(&dom->period_timer); + fprop_global_destroy(&dom->completions); +} +#endif + /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not @@ -510,17 +676,26 @@ static unsigned long dirty_freerun_ceiling(unsigned long thresh, return (thresh + bg_thresh) / 2; } -static unsigned long hard_dirty_limit(unsigned long thresh) +static unsigned long hard_dirty_limit(struct wb_domain *dom, + unsigned long thresh) { - return max(thresh, global_dirty_limit); + return max(thresh, dom->dirty_limit); +} + +/* memory available to a memcg domain is capped by system-wide clean memory */ +static void mdtc_cap_avail(struct dirty_throttle_control *mdtc) +{ + struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); + unsigned long clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); + + mdtc->avail = min(mdtc->avail, clean); } /** - * bdi_dirty_limit - @bdi's share of dirty throttling threshold - * @bdi: the backing_dev_info to query - * @dirty: global dirty limit in pages + * __wb_calc_thresh - @wb's share of dirty throttling threshold + * @dtc: dirty_throttle_context of interest * - * Returns @bdi's dirty limit in pages. The term "dirty" in the context of + * Returns @wb's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages. * * Note that balance_dirty_pages() will only seriously take it as a hard limit @@ -528,34 +703,47 @@ static unsigned long hard_dirty_limit(unsigned long thresh) * control. For example, when the device is completely stalled due to some error * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks - * more (rather than completely block them) when the bdi dirty pages go high. + * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * - * The bdi's share of dirty limit will be adapting to its throughput and + * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. */ -unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty) +static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { - u64 bdi_dirty; + struct wb_domain *dom = dtc_dom(dtc); + unsigned long thresh = dtc->thresh; + u64 wb_thresh; long numerator, denominator; + unsigned long wb_min_ratio, wb_max_ratio; /* - * Calculate this BDI's share of the dirty ratio. + * Calculate this BDI's share of the thresh ratio. */ - bdi_writeout_fraction(bdi, &numerator, &denominator); + fprop_fraction_percpu(&dom->completions, dtc->wb_completions, + &numerator, &denominator); + + wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100; + wb_thresh *= numerator; + do_div(wb_thresh, denominator); - bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100; - bdi_dirty *= numerator; - do_div(bdi_dirty, denominator); + wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); - bdi_dirty += (dirty * bdi->min_ratio) / 100; - if (bdi_dirty > (dirty * bdi->max_ratio) / 100) - bdi_dirty = dirty * bdi->max_ratio / 100; + wb_thresh += (thresh * wb_min_ratio) / 100; + if (wb_thresh > (thresh * wb_max_ratio) / 100) + wb_thresh = thresh * wb_max_ratio / 100; - return bdi_dirty; + return wb_thresh; +} + +unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT(wb), + .thresh = thresh }; + return __wb_calc_thresh(&gdtc); } /* @@ -594,7 +782,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, * * (o) global/bdi setpoints * - * We want the dirty pages be balanced around the global/bdi setpoints. + * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. @@ -604,8 +792,8 @@ static long long pos_ratio_polynom(unsigned long setpoint, * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * - * if (bdi_dirty < bdi_setpoint) scale up pos_ratio - * if (bdi_dirty > bdi_setpoint) scale down pos_ratio + * if (wb_dirty < wb_setpoint) scale up pos_ratio + * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * @@ -630,7 +818,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * - * (o) bdi control line + * (o) wb control line * * ^ pos_ratio * | @@ -656,33 +844,32 @@ static long long pos_ratio_polynom(unsigned long setpoint, * | . . * | . . * 0 +----------------------.-------------------------------.-------------> - * bdi_setpoint^ x_intercept^ + * wb_setpoint^ x_intercept^ * - * The bdi control line won't drop below pos_ratio=1/4, so that bdi_dirty can + * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD - * card's bdi_dirty may rush to many times higher than bdi_setpoint. - * - the bdi dirty thresh drops quickly due to change of JBOD workload + * card's wb_dirty may rush to many times higher than wb_setpoint. + * - the wb dirty thresh drops quickly due to change of JBOD workload */ -static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty) -{ - unsigned long write_bw = bdi->avg_write_bandwidth; - unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh); - unsigned long limit = hard_dirty_limit(thresh); +static void wb_position_ratio(struct dirty_throttle_control *dtc) +{ + struct bdi_writeback *wb = dtc->wb; + unsigned long write_bw = wb->avg_write_bandwidth; + unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); + unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); + unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ - unsigned long bdi_setpoint; + unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; - if (unlikely(dirty >= limit)) - return 0; + dtc->pos_ratio = 0; + + if (unlikely(dtc->dirty >= limit)) + return; /* * global setpoint @@ -690,165 +877,167 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; - pos_ratio = pos_ratio_polynom(setpoint, dirty, limit); + pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For - * such filesystems balance_dirty_pages always checks bdi counters - * against bdi limits. Even if global "nr_dirty" is under "freerun". + * such filesystems balance_dirty_pages always checks wb counters + * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * - * Here, in bdi_position_ratio(), we calculate pos_ratio based on - * two values: bdi_dirty and bdi_thresh. Let's consider an example: + * Here, in wb_position_ratio(), we calculate pos_ratio based on + * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). - * Then bdi_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. - * bdi_dirty_limit(bdi, bg_thresh) is about ~4K pages. bdi_setpoint is - * about ~6K pages (as the average of background and throttle bdi + * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. + * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is + * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if - * bdi_dirty is under bdi_setpoint and vice versa. + * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations - * because we want to throttle process writing to a strictlimit BDI + * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ - if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { - long long bdi_pos_ratio; - unsigned long bdi_bg_thresh; + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + long long wb_pos_ratio; - if (bdi_dirty < 8) - return min_t(long long, pos_ratio * 2, - 2 << RATELIMIT_CALC_SHIFT); + if (dtc->wb_dirty < 8) { + dtc->pos_ratio = min_t(long long, pos_ratio * 2, + 2 << RATELIMIT_CALC_SHIFT); + return; + } - if (bdi_dirty >= bdi_thresh) - return 0; + if (dtc->wb_dirty >= wb_thresh) + return; - bdi_bg_thresh = div_u64((u64)bdi_thresh * bg_thresh, thresh); - bdi_setpoint = dirty_freerun_ceiling(bdi_thresh, - bdi_bg_thresh); + wb_setpoint = dirty_freerun_ceiling(wb_thresh, + dtc->wb_bg_thresh); - if (bdi_setpoint == 0 || bdi_setpoint == bdi_thresh) - return 0; + if (wb_setpoint == 0 || wb_setpoint == wb_thresh) + return; - bdi_pos_ratio = pos_ratio_polynom(bdi_setpoint, bdi_dirty, - bdi_thresh); + wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, + wb_thresh); /* - * Typically, for strictlimit case, bdi_setpoint << setpoint - * and pos_ratio >> bdi_pos_ratio. In the other words global + * Typically, for strictlimit case, wb_setpoint << setpoint + * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to - * make decision based on bdi counters. But there is an + * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other - * BDIs) while given strictlimit BDI is below limit. + * wb's) while given strictlimit wb is below limit. * - * "pos_ratio * bdi_pos_ratio" would work for the case above, + * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all - * activity in the system coming from a single strictlimit BDI + * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 - * (when globally we are at freerun and bdi is well below bdi + * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ - return min(pos_ratio, bdi_pos_ratio); + dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); + return; } /* * We have computed basic pos_ratio above based on global situation. If - * the bdi is over/under its share of dirty pages, we want to scale + * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* - * bdi setpoint + * wb setpoint * - * f(bdi_dirty) := 1.0 + k * (bdi_dirty - bdi_setpoint) + * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * - * x_intercept - bdi_dirty + * x_intercept - wb_dirty * := -------------------------- - * x_intercept - bdi_setpoint + * x_intercept - wb_setpoint * - * The main bdi control line is a linear function that subjects to + * The main wb control line is a linear function that subjects to * - * (1) f(bdi_setpoint) = 1.0 - * (2) k = - 1 / (8 * write_bw) (in single bdi case) - * or equally: x_intercept = bdi_setpoint + 8 * write_bw + * (1) f(wb_setpoint) = 1.0 + * (2) k = - 1 / (8 * write_bw) (in single wb case) + * or equally: x_intercept = wb_setpoint + 8 * write_bw * - * For single bdi case, the dirty pages are observed to fluctuate + * For single wb case, the dirty pages are observed to fluctuate * regularly within range - * [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2] + * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * - * For JBOD case, bdi_thresh (not bdi_dirty!) could fluctuate up to its + * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that - * yields 100% pos_ratio fluctuation on suddenly doubled bdi_thresh. + * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ - if (unlikely(bdi_thresh > thresh)) - bdi_thresh = thresh; + if (unlikely(wb_thresh > dtc->thresh)) + wb_thresh = dtc->thresh; /* - * It's very possible that bdi_thresh is close to 0 not because the + * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ - bdi_thresh = max(bdi_thresh, (limit - dirty) / 8); + wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* - * scale global setpoint to bdi's: - * bdi_setpoint = setpoint * bdi_thresh / thresh + * scale global setpoint to wb's: + * wb_setpoint = setpoint * wb_thresh / thresh */ - x = div_u64((u64)bdi_thresh << 16, thresh | 1); - bdi_setpoint = setpoint * (u64)x >> 16; + x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); + wb_setpoint = setpoint * (u64)x >> 16; /* - * Use span=(8*write_bw) in single bdi case as indicated by - * (thresh - bdi_thresh ~= 0) and transit to bdi_thresh in JBOD case. + * Use span=(8*write_bw) in single wb case as indicated by + * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * - * bdi_thresh thresh - bdi_thresh - * span = ---------- * (8 * write_bw) + ------------------- * bdi_thresh - * thresh thresh + * wb_thresh thresh - wb_thresh + * span = --------- * (8 * write_bw) + ------------------ * wb_thresh + * thresh thresh */ - span = (thresh - bdi_thresh + 8 * write_bw) * (u64)x >> 16; - x_intercept = bdi_setpoint + span; + span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; + x_intercept = wb_setpoint + span; - if (bdi_dirty < x_intercept - span / 4) { - pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty), - (x_intercept - bdi_setpoint) | 1); + if (dtc->wb_dirty < x_intercept - span / 4) { + pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), + (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* - * bdi reserve area, safeguard against dirty pool underrun and disk idle + * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ - x_intercept = bdi_thresh / 2; - if (bdi_dirty < x_intercept) { - if (bdi_dirty > x_intercept / 8) - pos_ratio = div_u64(pos_ratio * x_intercept, bdi_dirty); + x_intercept = wb_thresh / 2; + if (dtc->wb_dirty < x_intercept) { + if (dtc->wb_dirty > x_intercept / 8) + pos_ratio = div_u64(pos_ratio * x_intercept, + dtc->wb_dirty); else pos_ratio *= 8; } - return pos_ratio; + dtc->pos_ratio = pos_ratio; } -static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, - unsigned long elapsed, - unsigned long written) +static void wb_update_write_bandwidth(struct bdi_writeback *wb, + unsigned long elapsed, + unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); - unsigned long avg = bdi->avg_write_bandwidth; - unsigned long old = bdi->write_bandwidth; + unsigned long avg = wb->avg_write_bandwidth; + unsigned long old = wb->write_bandwidth; u64 bw; /* @@ -861,14 +1050,14 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, * @written may have decreased due to account_page_redirty(). * Avoid underflowing @bw calculation. */ - bw = written - min(written, bdi->written_stamp); + bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { do_div(bw, elapsed); avg = bw; goto out; } - bw += (u64)bdi->write_bandwidth * (period - elapsed); + bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* @@ -881,21 +1070,22 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi, avg += (old - avg) >> 3; out: - bdi->write_bandwidth = bw; - bdi->avg_write_bandwidth = avg; + /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ + avg = max(avg, 1LU); + if (wb_has_dirty_io(wb)) { + long delta = avg - wb->avg_write_bandwidth; + WARN_ON_ONCE(atomic_long_add_return(delta, + &wb->bdi->tot_write_bandwidth) <= 0); + } + wb->write_bandwidth = bw; + wb->avg_write_bandwidth = avg; } -/* - * The global dirtyable memory and dirty threshold could be suddenly knocked - * down by a large amount (eg. on the startup of KVM in a swapless system). - * This may throw the system into deep dirty exceeded state and throttle - * heavy/light dirtiers alike. To retain good responsiveness, maintain - * global_dirty_limit for tracking slowly down to the knocked down dirty - * threshold. - */ -static void update_dirty_limit(unsigned long thresh, unsigned long dirty) +static void update_dirty_limit(struct dirty_throttle_control *dtc) { - unsigned long limit = global_dirty_limit; + struct wb_domain *dom = dtc_dom(dtc); + unsigned long thresh = dtc->thresh; + unsigned long limit = dom->dirty_limit; /* * Follow up in one step. @@ -908,63 +1098,57 @@ static void update_dirty_limit(unsigned long thresh, unsigned long dirty) /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce - * global_dirty_limit which is guaranteed to lie above the dirty pages. + * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ - thresh = max(thresh, dirty); + thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: - global_dirty_limit = limit; + dom->dirty_limit = limit; } -static void global_update_bandwidth(unsigned long thresh, - unsigned long dirty, +static void domain_update_bandwidth(struct dirty_throttle_control *dtc, unsigned long now) { - static DEFINE_SPINLOCK(dirty_lock); - static unsigned long update_time = INITIAL_JIFFIES; + struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ - if (time_before(now, update_time + BANDWIDTH_INTERVAL)) + if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; - spin_lock(&dirty_lock); - if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) { - update_dirty_limit(thresh, dirty); - update_time = now; + spin_lock(&dom->lock); + if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { + update_dirty_limit(dtc); + dom->dirty_limit_tstamp = now; } - spin_unlock(&dirty_lock); + spin_unlock(&dom->lock); } /* - * Maintain bdi->dirty_ratelimit, the base dirty throttle rate. + * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * - * Normal bdi tasks will be curbed at or below it in long term. + * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ -static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long dirtied, - unsigned long elapsed) -{ - unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh); - unsigned long limit = hard_dirty_limit(thresh); +static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, + unsigned long dirtied, + unsigned long elapsed) +{ + struct bdi_writeback *wb = dtc->wb; + unsigned long dirty = dtc->dirty; + unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); + unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; - unsigned long write_bw = bdi->avg_write_bandwidth; - unsigned long dirty_ratelimit = bdi->dirty_ratelimit; + unsigned long write_bw = wb->avg_write_bandwidth; + unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; - unsigned long pos_ratio; unsigned long step; unsigned long x; @@ -972,20 +1156,18 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ - dirty_rate = (dirtied - bdi->dirtied_stamp) * HZ / elapsed; + dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; - pos_ratio = bdi_position_ratio(bdi, thresh, bg_thresh, dirty, - bdi_thresh, bdi_dirty); /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * - pos_ratio >> RATELIMIT_CALC_SHIFT; + dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, - * if there are N dd tasks, each throttled at task_ratelimit, the bdi's + * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * @@ -1024,7 +1206,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, /* * We could safely do this and return immediately: * - * bdi->dirty_ratelimit = balanced_dirty_ratelimit; + * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and @@ -1058,32 +1240,31 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, step = 0; /* - * For strictlimit case, calculations above were based on bdi counters - * and limits (starting from pos_ratio = bdi_position_ratio() and up to + * For strictlimit case, calculations above were based on wb counters + * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). - * Hence, to calculate "step" properly, we have to use bdi_dirty as - * "dirty" and bdi_setpoint as "setpoint". + * Hence, to calculate "step" properly, we have to use wb_dirty as + * "dirty" and wb_setpoint as "setpoint". * - * We rampup dirty_ratelimit forcibly if bdi_dirty is low because - * it's possible that bdi_thresh is close to zero due to inactivity - * of backing device (see the implementation of bdi_dirty_limit()). + * We rampup dirty_ratelimit forcibly if wb_dirty is low because + * it's possible that wb_thresh is close to zero due to inactivity + * of backing device. */ - if (unlikely(bdi->capabilities & BDI_CAP_STRICTLIMIT)) { - dirty = bdi_dirty; - if (bdi_dirty < 8) - setpoint = bdi_dirty + 1; + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + dirty = dtc->wb_dirty; + if (dtc->wb_dirty < 8) + setpoint = dtc->wb_dirty + 1; else - setpoint = (bdi_thresh + - bdi_dirty_limit(bdi, bg_thresh)) / 2; + setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { - x = min3(bdi->balanced_dirty_ratelimit, + x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { - x = max3(bdi->balanced_dirty_ratelimit, + x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; @@ -1105,69 +1286,67 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi, else dirty_ratelimit -= step; - bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL); - bdi->balanced_dirty_ratelimit = balanced_dirty_ratelimit; + wb->dirty_ratelimit = max(dirty_ratelimit, 1UL); + wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; - trace_bdi_dirty_ratelimit(bdi, dirty_rate, task_ratelimit); + trace_bdi_dirty_ratelimit(wb->bdi, dirty_rate, task_ratelimit); } -void __bdi_update_bandwidth(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long start_time) +static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, + struct dirty_throttle_control *mdtc, + unsigned long start_time, + bool update_ratelimit) { + struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; - unsigned long elapsed = now - bdi->bw_time_stamp; + unsigned long elapsed = now - wb->bw_time_stamp; unsigned long dirtied; unsigned long written; + lockdep_assert_held(&wb->list_lock); + /* * rate-limit, only update once every 200ms. */ if (elapsed < BANDWIDTH_INTERVAL) return; - dirtied = percpu_counter_read(&bdi->bdi_stat[BDI_DIRTIED]); - written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]); + dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); + written = percpu_counter_read(&wb->stat[WB_WRITTEN]); /* * Skip quiet periods when disk bandwidth is under-utilized. * (at least 1s idle time between two flusher runs) */ - if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time)) + if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time)) goto snapshot; - if (thresh) { - global_update_bandwidth(thresh, dirty, now); - bdi_update_dirty_ratelimit(bdi, thresh, bg_thresh, dirty, - bdi_thresh, bdi_dirty, - dirtied, elapsed); + if (update_ratelimit) { + domain_update_bandwidth(gdtc, now); + wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); + + /* + * @mdtc is always NULL if !CGROUP_WRITEBACK but the + * compiler has no way to figure that out. Help it. + */ + if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { + domain_update_bandwidth(mdtc, now); + wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); + } } - bdi_update_write_bandwidth(bdi, elapsed, written); + wb_update_write_bandwidth(wb, elapsed, written); snapshot: - bdi->dirtied_stamp = dirtied; - bdi->written_stamp = written; - bdi->bw_time_stamp = now; + wb->dirtied_stamp = dirtied; + wb->written_stamp = written; + wb->bw_time_stamp = now; } -static void bdi_update_bandwidth(struct backing_dev_info *bdi, - unsigned long thresh, - unsigned long bg_thresh, - unsigned long dirty, - unsigned long bdi_thresh, - unsigned long bdi_dirty, - unsigned long start_time) +void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) { - if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL)) - return; - spin_lock(&bdi->wb.list_lock); - __bdi_update_bandwidth(bdi, thresh, bg_thresh, dirty, - bdi_thresh, bdi_dirty, start_time); - spin_unlock(&bdi->wb.list_lock); + struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; + + __wb_update_bandwidth(&gdtc, NULL, start_time, false); } /* @@ -1187,10 +1366,10 @@ static unsigned long dirty_poll_interval(unsigned long dirty, return 1; } -static unsigned long bdi_max_pause(struct backing_dev_info *bdi, - unsigned long bdi_dirty) +static unsigned long wb_max_pause(struct bdi_writeback *wb, + unsigned long wb_dirty) { - unsigned long bw = bdi->avg_write_bandwidth; + unsigned long bw = wb->avg_write_bandwidth; unsigned long t; /* @@ -1200,20 +1379,20 @@ static unsigned long bdi_max_pause(struct backing_dev_info *bdi, * * 8 serves as the safety ratio. */ - t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); + t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } -static long bdi_min_pause(struct backing_dev_info *bdi, - long max_pause, - unsigned long task_ratelimit, - unsigned long dirty_ratelimit, - int *nr_dirtied_pause) +static long wb_min_pause(struct bdi_writeback *wb, + long max_pause, + unsigned long task_ratelimit, + unsigned long dirty_ratelimit, + int *nr_dirtied_pause) { - long hi = ilog2(bdi->avg_write_bandwidth); - long lo = ilog2(bdi->dirty_ratelimit); + long hi = ilog2(wb->avg_write_bandwidth); + long lo = ilog2(wb->dirty_ratelimit); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ @@ -1281,34 +1460,27 @@ static long bdi_min_pause(struct backing_dev_info *bdi, return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } -static inline void bdi_dirty_limits(struct backing_dev_info *bdi, - unsigned long dirty_thresh, - unsigned long background_thresh, - unsigned long *bdi_dirty, - unsigned long *bdi_thresh, - unsigned long *bdi_bg_thresh) +static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { - unsigned long bdi_reclaimable; + struct bdi_writeback *wb = dtc->wb; + unsigned long wb_reclaimable; /* - * bdi_thresh is not treated as some limiting factor as + * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons - * - in JBOD setup, bdi_thresh can fluctuate a lot + * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow - * go into state (bdi_dirty >> bdi_thresh) either because - * bdi_dirty starts high, or because bdi_thresh drops low. + * go into state (wb_dirty >> wb_thresh) either because + * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key - * dirtiers for 100 seconds until bdi_dirty drops under - * bdi_thresh. Instead the auxiliary bdi control line in - * bdi_position_ratio() will let the dirtier task progress - * at some rate <= (write_bw / 2) for bringing down bdi_dirty. + * dirtiers for 100 seconds until wb_dirty drops under + * wb_thresh. Instead the auxiliary wb control line in + * wb_position_ratio() will let the dirtier task progress + * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ - *bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); - - if (bdi_bg_thresh) - *bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh * - background_thresh, - dirty_thresh) : 0; + dtc->wb_thresh = __wb_calc_thresh(dtc); + dtc->wb_bg_thresh = dtc->thresh ? + div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need @@ -1320,14 +1492,12 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, * actually dirty; with m+n sitting in the percpu * deltas. */ - if (*bdi_thresh < 2 * bdi_stat_error(bdi)) { - bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); - *bdi_dirty = bdi_reclaimable + - bdi_stat_sum(bdi, BDI_WRITEBACK); + if (dtc->wb_thresh < 2 * wb_stat_error(wb)) { + wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); + dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { - bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); - *bdi_dirty = bdi_reclaimable + - bdi_stat(bdi, BDI_WRITEBACK); + wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); + dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } @@ -1339,12 +1509,16 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi, * perform some writeout. */ static void balance_dirty_pages(struct address_space *mapping, + struct bdi_writeback *wb, unsigned long pages_dirtied) { + struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; + struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; + struct dirty_throttle_control * const gdtc = &gdtc_stor; + struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? + &mdtc_stor : NULL; + struct dirty_throttle_control *sdtc; unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */ - unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */ - unsigned long background_thresh; - unsigned long dirty_thresh; long period; long pause; long max_pause; @@ -1353,18 +1527,14 @@ static void balance_dirty_pages(struct address_space *mapping, bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; - unsigned long pos_ratio; - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; for (;;) { unsigned long now = jiffies; - unsigned long uninitialized_var(bdi_thresh); - unsigned long thresh; - unsigned long uninitialized_var(bdi_dirty); - unsigned long dirty; - unsigned long bg_thresh; + unsigned long dirty, thresh, bg_thresh; + unsigned long m_dirty, m_thresh, m_bg_thresh; /* * Unstable writes are a feature of certain networked @@ -1374,65 +1544,127 @@ static void balance_dirty_pages(struct address_space *mapping, */ nr_reclaimable = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); - nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); + gdtc->avail = global_dirtyable_memory(); + gdtc->dirty = nr_reclaimable + global_page_state(NR_WRITEBACK); - global_dirty_limits(&background_thresh, &dirty_thresh); + domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { - bdi_dirty_limits(bdi, dirty_thresh, background_thresh, - &bdi_dirty, &bdi_thresh, &bg_thresh); + wb_dirty_limits(gdtc); - dirty = bdi_dirty; - thresh = bdi_thresh; + dirty = gdtc->wb_dirty; + thresh = gdtc->wb_thresh; + bg_thresh = gdtc->wb_bg_thresh; } else { - dirty = nr_dirty; - thresh = dirty_thresh; - bg_thresh = background_thresh; + dirty = gdtc->dirty; + thresh = gdtc->thresh; + bg_thresh = gdtc->bg_thresh; + } + + if (mdtc) { + unsigned long writeback; + + /* + * If @wb belongs to !root memcg, repeat the same + * basic calculations for the memcg domain. + */ + mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, + &writeback); + mdtc_cap_avail(mdtc); + mdtc->dirty += writeback; + + domain_dirty_limits(mdtc); + + if (unlikely(strictlimit)) { + wb_dirty_limits(mdtc); + m_dirty = mdtc->wb_dirty; + m_thresh = mdtc->wb_thresh; + m_bg_thresh = mdtc->wb_bg_thresh; + } else { + m_dirty = mdtc->dirty; + m_thresh = mdtc->thresh; + m_bg_thresh = mdtc->bg_thresh; + } } /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts - * when the bdi limits are ramping up in case of !strictlimit. + * when the wb limits are ramping up in case of !strictlimit. * - * In strictlimit case make decision based on the bdi counters - * and limits. Small writeouts when the bdi limits are ramping + * In strictlimit case make decision based on the wb counters + * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. + * + * If memcg domain is in effect, @dirty should be under + * both global and memcg freerun ceilings. */ - if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh)) { + if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && + (!mdtc || + m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { + unsigned long intv = dirty_poll_interval(dirty, thresh); + unsigned long m_intv = ULONG_MAX; + current->dirty_paused_when = now; current->nr_dirtied = 0; - current->nr_dirtied_pause = - dirty_poll_interval(dirty, thresh); + if (mdtc) + m_intv = dirty_poll_interval(m_dirty, m_thresh); + current->nr_dirtied_pause = min(intv, m_intv); break; } - if (unlikely(!writeback_in_progress(bdi))) - bdi_start_background_writeback(bdi); + if (unlikely(!writeback_in_progress(wb))) + wb_start_background_writeback(wb); + /* + * Calculate global domain's pos_ratio and select the + * global dtc by default. + */ if (!strictlimit) - bdi_dirty_limits(bdi, dirty_thresh, background_thresh, - &bdi_dirty, &bdi_thresh, NULL); - - dirty_exceeded = (bdi_dirty > bdi_thresh) && - ((nr_dirty > dirty_thresh) || strictlimit); - if (dirty_exceeded && !bdi->dirty_exceeded) - bdi->dirty_exceeded = 1; - - bdi_update_bandwidth(bdi, dirty_thresh, background_thresh, - nr_dirty, bdi_thresh, bdi_dirty, - start_time); - - dirty_ratelimit = bdi->dirty_ratelimit; - pos_ratio = bdi_position_ratio(bdi, dirty_thresh, - background_thresh, nr_dirty, - bdi_thresh, bdi_dirty); - task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >> + wb_dirty_limits(gdtc); + + dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && + ((gdtc->dirty > gdtc->thresh) || strictlimit); + + wb_position_ratio(gdtc); + sdtc = gdtc; + + if (mdtc) { + /* + * If memcg domain is in effect, calculate its + * pos_ratio. @wb should satisfy constraints from + * both global and memcg domains. Choose the one + * w/ lower pos_ratio. + */ + if (!strictlimit) + wb_dirty_limits(mdtc); + + dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && + ((mdtc->dirty > mdtc->thresh) || strictlimit); + + wb_position_ratio(mdtc); + if (mdtc->pos_ratio < gdtc->pos_ratio) + sdtc = mdtc; + } + + if (dirty_exceeded && !wb->dirty_exceeded) + wb->dirty_exceeded = 1; + + if (time_is_before_jiffies(wb->bw_time_stamp + + BANDWIDTH_INTERVAL)) { + spin_lock(&wb->list_lock); + __wb_update_bandwidth(gdtc, mdtc, start_time, true); + spin_unlock(&wb->list_lock); + } + + /* throttle according to the chosen dtc */ + dirty_ratelimit = wb->dirty_ratelimit; + task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; - max_pause = bdi_max_pause(bdi, bdi_dirty); - min_pause = bdi_min_pause(bdi, max_pause, - task_ratelimit, dirty_ratelimit, - &nr_dirtied_pause); + max_pause = wb_max_pause(wb, sdtc->wb_dirty); + min_pause = wb_min_pause(wb, max_pause, + task_ratelimit, dirty_ratelimit, + &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; @@ -1452,11 +1684,11 @@ static void balance_dirty_pages(struct address_space *mapping, */ if (pause < min_pause) { trace_balance_dirty_pages(bdi, - dirty_thresh, - background_thresh, - nr_dirty, - bdi_thresh, - bdi_dirty, + sdtc->thresh, + sdtc->bg_thresh, + sdtc->dirty, + sdtc->wb_thresh, + sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, @@ -1481,11 +1713,11 @@ static void balance_dirty_pages(struct address_space *mapping, pause: trace_balance_dirty_pages(bdi, - dirty_thresh, - background_thresh, - nr_dirty, - bdi_thresh, - bdi_dirty, + sdtc->thresh, + sdtc->bg_thresh, + sdtc->dirty, + sdtc->wb_thresh, + sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, @@ -1500,33 +1732,33 @@ pause: current->nr_dirtied_pause = nr_dirtied_pause; /* - * This is typically equal to (nr_dirty < dirty_thresh) and can - * also keep "1000+ dd on a slow USB stick" under control. + * This is typically equal to (dirty < thresh) and can also + * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponding NFS server and the NFS dirty - * pages exceeds dirty_thresh, give the other good bdi's a pipe + * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the comsumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 - * more page. However bdi_dirty has accounting errors. So use - * the larger and more IO friendly bdi_stat_error. + * more page. However wb_dirty has accounting errors. So use + * the larger and more IO friendly wb_stat_error. */ - if (bdi_dirty <= bdi_stat_error(bdi)) + if (sdtc->wb_dirty <= wb_stat_error(wb)) break; if (fatal_signal_pending(current)) break; } - if (!dirty_exceeded && bdi->dirty_exceeded) - bdi->dirty_exceeded = 0; + if (!dirty_exceeded && wb->dirty_exceeded) + wb->dirty_exceeded = 0; - if (writeback_in_progress(bdi)) + if (writeback_in_progress(wb)) return; /* @@ -1540,8 +1772,8 @@ pause: if (laptop_mode) return; - if (nr_reclaimable > background_thresh) - bdi_start_background_writeback(bdi); + if (nr_reclaimable > gdtc->bg_thresh) + wb_start_background_writeback(wb); } static DEFINE_PER_CPU(int, bdp_ratelimits); @@ -1577,15 +1809,22 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb = NULL; int ratelimit; int *p; if (!bdi_cap_account_dirty(bdi)) return; + if (inode_cgwb_enabled(inode)) + wb = wb_get_create_current(bdi, GFP_KERNEL); + if (!wb) + wb = &bdi->wb; + ratelimit = current->nr_dirtied_pause; - if (bdi->dirty_exceeded) + if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); @@ -1617,10 +1856,59 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping) preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) - balance_dirty_pages(mapping, current->nr_dirtied); + balance_dirty_pages(mapping, wb, current->nr_dirtied); + + wb_put(wb); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); +/** + * wb_over_bg_thresh - does @wb need to be written back? + * @wb: bdi_writeback of interest + * + * Determines whether background writeback should keep writing @wb or it's + * clean enough. Returns %true if writeback should continue. + */ +bool wb_over_bg_thresh(struct bdi_writeback *wb) +{ + struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; + struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; + struct dirty_throttle_control * const gdtc = &gdtc_stor; + struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? + &mdtc_stor : NULL; + + /* + * Similar to balance_dirty_pages() but ignores pages being written + * as we're trying to decide whether to put more under writeback. + */ + gdtc->avail = global_dirtyable_memory(); + gdtc->dirty = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); + domain_dirty_limits(gdtc); + + if (gdtc->dirty > gdtc->bg_thresh) + return true; + + if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc)) + return true; + + if (mdtc) { + unsigned long writeback; + + mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, &writeback); + mdtc_cap_avail(mdtc); + domain_dirty_limits(mdtc); /* ditto, ignore writeback */ + + if (mdtc->dirty > mdtc->bg_thresh) + return true; + + if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc)) + return true; + } + + return false; +} + void throttle_vm_writeout(gfp_t gfp_mask) { unsigned long background_thresh; @@ -1628,7 +1916,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) for ( ; ; ) { global_dirty_limits(&background_thresh, &dirty_thresh); - dirty_thresh = hard_dirty_limit(dirty_thresh); + dirty_thresh = hard_dirty_limit(&global_wb_domain, dirty_thresh); /* * Boost the allowable dirty threshold a bit for page @@ -1667,14 +1955,20 @@ void laptop_mode_timer_fn(unsigned long data) struct request_queue *q = (struct request_queue *)data; int nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); + struct bdi_writeback *wb; + struct wb_iter iter; /* * We want to write everything out, not just down to the dirty * threshold */ - if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, nr_pages, - WB_REASON_LAPTOP_TIMER); + if (!bdi_has_dirty_io(&q->backing_dev_info)) + return; + + bdi_for_each_wb(wb, &q->backing_dev_info, &iter, 0) + if (wb_has_dirty_io(wb)) + wb_start_writeback(wb, nr_pages, true, + WB_REASON_LAPTOP_TIMER); } /* @@ -1718,10 +2012,12 @@ void laptop_sync_completion(void) void writeback_set_ratelimit(void) { + struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; + global_dirty_limits(&background_thresh, &dirty_thresh); - global_dirty_limit = dirty_thresh; + dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; @@ -1770,7 +2066,7 @@ void __init page_writeback_init(void) writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); - fprop_global_init(&writeout_completions, GFP_KERNEL); + BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); } /** @@ -2090,19 +2386,29 @@ int __set_page_dirty_no_writeback(struct page *page) /* * Helper function for set_page_dirty family. + * + * Caller must hold mem_cgroup_begin_page_stat(). + * * NOTE: This relies on being atomic wrt interrupts. */ -void account_page_dirtied(struct page *page, struct address_space *mapping) +void account_page_dirtied(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg) { + struct inode *inode = mapping->host; + trace_writeback_dirty_page(page, mapping); if (mapping_cap_account_dirty(mapping)) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct bdi_writeback *wb; + inode_attach_wb(inode, page); + wb = inode_to_wb(inode); + + mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_DIRTY); __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); - __inc_bdi_stat(bdi, BDI_RECLAIMABLE); - __inc_bdi_stat(bdi, BDI_DIRTIED); + __inc_wb_stat(wb, WB_RECLAIMABLE); + __inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_CACHE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); @@ -2113,21 +2419,18 @@ EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for deaccounting dirty page without writeback. * - * Doing this should *normally* only ever be done when a page - * is truncated, and is not actually mapped anywhere at all. However, - * fs/buffer.c does this when it notices that somebody has cleaned - * out all the buffers on a page without actually doing it through - * the VM. Can you say "ext3 is horribly ugly"? Thought you could. + * Caller must hold mem_cgroup_begin_page_stat(). */ -void account_page_cleaned(struct page *page, struct address_space *mapping) +void account_page_cleaned(struct page *page, struct address_space *mapping, + struct mem_cgroup *memcg, struct bdi_writeback *wb) { if (mapping_cap_account_dirty(mapping)) { + mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY); dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); + dec_wb_stat(wb, WB_RECLAIMABLE); task_io_account_cancelled_write(PAGE_CACHE_SIZE); } } -EXPORT_SYMBOL(account_page_cleaned); /* * For address_spaces which do not use buffers. Just tag the page as dirty in @@ -2143,26 +2446,34 @@ EXPORT_SYMBOL(account_page_cleaned); */ int __set_page_dirty_nobuffers(struct page *page) { + struct mem_cgroup *memcg; + + memcg = mem_cgroup_begin_page_stat(page); if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); unsigned long flags; - if (!mapping) + if (!mapping) { + mem_cgroup_end_page_stat(memcg); return 1; + } spin_lock_irqsave(&mapping->tree_lock, flags); BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - account_page_dirtied(page, mapping); + account_page_dirtied(page, mapping, memcg); radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); + if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return 1; } + mem_cgroup_end_page_stat(memcg); return 0; } EXPORT_SYMBOL(__set_page_dirty_nobuffers); @@ -2177,10 +2488,17 @@ EXPORT_SYMBOL(__set_page_dirty_nobuffers); void account_page_redirty(struct page *page) { struct address_space *mapping = page->mapping; + if (mapping && mapping_cap_account_dirty(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + bool locked; + + wb = unlocked_inode_to_wb_begin(inode, &locked); current->nr_dirtied--; dec_zone_page_state(page, NR_DIRTIED); - dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED); + dec_wb_stat(wb, WB_DIRTIED); + unlocked_inode_to_wb_end(inode, locked); } } EXPORT_SYMBOL(account_page_redirty); @@ -2266,6 +2584,43 @@ int set_page_dirty_lock(struct page *page) EXPORT_SYMBOL(set_page_dirty_lock); /* + * This cancels just the dirty bit on the kernel page itself, it does NOT + * actually remove dirty bits on any mmap's that may be around. It also + * leaves the page tagged dirty, so any sync activity will still find it on + * the dirty lists, and in particular, clear_page_dirty_for_io() will still + * look at the dirty bits in the VM. + * + * Doing this should *normally* only ever be done when a page is truncated, + * and is not actually mapped anywhere at all. However, fs/buffer.c does + * this when it notices that somebody has cleaned out all the buffers on a + * page without actually doing it through the VM. Can you say "ext3 is + * horribly ugly"? Thought you could. + */ +void cancel_dirty_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + + if (mapping_cap_account_dirty(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + struct mem_cgroup *memcg; + bool locked; + + memcg = mem_cgroup_begin_page_stat(page); + wb = unlocked_inode_to_wb_begin(inode, &locked); + + if (TestClearPageDirty(page)) + account_page_cleaned(page, mapping, memcg, wb); + + unlocked_inode_to_wb_end(inode, locked); + mem_cgroup_end_page_stat(memcg); + } else { + ClearPageDirty(page); + } +} +EXPORT_SYMBOL(cancel_dirty_page); + +/* * Clear a page's dirty flag, while caring for dirty memory accounting. * Returns true if the page was previously dirty. * @@ -2282,10 +2637,16 @@ EXPORT_SYMBOL(set_page_dirty_lock); int clear_page_dirty_for_io(struct page *page) { struct address_space *mapping = page_mapping(page); + int ret = 0; BUG_ON(!PageLocked(page)); if (mapping && mapping_cap_account_dirty(mapping)) { + struct inode *inode = mapping->host; + struct bdi_writeback *wb; + struct mem_cgroup *memcg; + bool locked; + /* * Yes, Virginia, this is indeed insane. * @@ -2321,13 +2682,17 @@ int clear_page_dirty_for_io(struct page *page) * always locked coming in here, so we get the desired * exclusion. */ + memcg = mem_cgroup_begin_page_stat(page); + wb = unlocked_inode_to_wb_begin(inode, &locked); if (TestClearPageDirty(page)) { + mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY); dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(inode_to_bdi(mapping->host), - BDI_RECLAIMABLE); - return 1; + dec_wb_stat(wb, WB_RECLAIMABLE); + ret = 1; } - return 0; + unlocked_inode_to_wb_end(inode, locked); + mem_cgroup_end_page_stat(memcg); + return ret; } return TestClearPageDirty(page); } @@ -2341,7 +2706,8 @@ int test_clear_page_writeback(struct page *page) memcg = mem_cgroup_begin_page_stat(page); if (mapping) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2351,8 +2717,10 @@ int test_clear_page_writeback(struct page *page) page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) { - __dec_bdi_stat(bdi, BDI_WRITEBACK); - __bdi_writeout_inc(bdi); + struct bdi_writeback *wb = inode_to_wb(inode); + + __dec_wb_stat(wb, WB_WRITEBACK); + __wb_writeout_inc(wb); } } spin_unlock_irqrestore(&mapping->tree_lock, flags); @@ -2376,7 +2744,8 @@ int __test_set_page_writeback(struct page *page, bool keep_write) memcg = mem_cgroup_begin_page_stat(page); if (mapping) { - struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + struct inode *inode = mapping->host; + struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2386,7 +2755,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) - __inc_bdi_stat(bdi, BDI_WRITEBACK); + __inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); } if (!PageDirty(page)) radix_tree_tag_clear(&mapping->page_tree, diff --git a/mm/readahead.c b/mm/readahead.c index 9356758..60cd846 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping, /* * Defer asynchronous read-ahead on IO congestion. */ - if (bdi_read_congested(inode_to_bdi(mapping->host))) + if (inode_read_congested(mapping->host)) return; /* do read-ahead */ @@ -30,6 +30,8 @@ * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) + * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) + * mapping->tree_lock (widely used) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) diff --git a/mm/truncate.c b/mm/truncate.c index 66af903..76e35ad 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -116,9 +116,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ - if (TestClearPageDirty(page)) - account_page_cleaned(page, mapping); - + cancel_dirty_page(page); ClearPageMappedToDisk(page); delete_from_page_cache(page); return 0; @@ -512,19 +510,24 @@ EXPORT_SYMBOL(invalidate_mapping_pages); static int invalidate_complete_page2(struct address_space *mapping, struct page *page) { + struct mem_cgroup *memcg; + unsigned long flags; + if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; - spin_lock_irq(&mapping->tree_lock); + memcg = mem_cgroup_begin_page_stat(page); + spin_lock_irqsave(&mapping->tree_lock, flags); if (PageDirty(page)) goto failed; BUG_ON(page_has_private(page)); - __delete_from_page_cache(page, NULL); - spin_unlock_irq(&mapping->tree_lock); + __delete_from_page_cache(page, NULL, memcg); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); @@ -532,7 +535,8 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) page_cache_release(page); /* pagecache ref */ return 1; failed: - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 19ef01e..e61445d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -154,11 +154,42 @@ static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; } + +/** + * sane_reclaim - is the usual dirty throttling mechanism operational? + * @sc: scan_control in question + * + * The normal page dirty throttling mechanism in balance_dirty_pages() is + * completely broken with the legacy memcg and direct stalling in + * shrink_page_list() is used for throttling instead, which lacks all the + * niceties such as fairness, adaptive pausing, bandwidth proportional + * allocation and configurability. + * + * This function tests whether the vmscan currently in progress can assume + * that the normal dirty throttling mechanism is operational. + */ +static bool sane_reclaim(struct scan_control *sc) +{ + struct mem_cgroup *memcg = sc->target_mem_cgroup; + + if (!memcg) + return true; +#ifdef CONFIG_CGROUP_WRITEBACK + if (cgroup_on_dfl(mem_cgroup_css(memcg)->cgroup)) + return true; +#endif + return false; +} #else static bool global_reclaim(struct scan_control *sc) { return true; } + +static bool sane_reclaim(struct scan_control *sc) +{ + return true; +} #endif static unsigned long zone_reclaimable_pages(struct zone *zone) @@ -452,14 +483,13 @@ static inline int is_page_cache_freeable(struct page *page) return page_count(page) - page_has_private(page) == 2; } -static int may_write_to_queue(struct backing_dev_info *bdi, - struct scan_control *sc) +static int may_write_to_inode(struct inode *inode, struct scan_control *sc) { if (current->flags & PF_SWAPWRITE) return 1; - if (!bdi_write_congested(bdi)) + if (!inode_write_congested(inode)) return 1; - if (bdi == current->backing_dev_info) + if (inode_to_bdi(inode) == current->backing_dev_info) return 1; return 0; } @@ -538,7 +568,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_queue(inode_to_bdi(mapping->host), sc)) + if (!may_write_to_inode(mapping->host, sc)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { @@ -579,10 +609,14 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, static int __remove_mapping(struct address_space *mapping, struct page *page, bool reclaimed) { + unsigned long flags; + struct mem_cgroup *memcg; + BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); - spin_lock_irq(&mapping->tree_lock); + memcg = mem_cgroup_begin_page_stat(page); + spin_lock_irqsave(&mapping->tree_lock, flags); /* * The non racy check for a busy page. * @@ -620,7 +654,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); __delete_from_swap_cache(page); - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); swapcache_free(swap); } else { void (*freepage)(struct page *); @@ -640,8 +675,9 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, if (reclaimed && page_is_file_cache(page) && !mapping_exiting(mapping)) shadow = workingset_eviction(mapping, page); - __delete_from_page_cache(page, shadow); - spin_unlock_irq(&mapping->tree_lock); + __delete_from_page_cache(page, shadow, memcg); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); if (freepage != NULL) freepage(page); @@ -650,7 +686,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, return 1; cannot_free: - spin_unlock_irq(&mapping->tree_lock); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + mem_cgroup_end_page_stat(memcg); return 0; } @@ -917,7 +954,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ mapping = page_mapping(page); if (((dirty || writeback) && mapping && - bdi_write_congested(inode_to_bdi(mapping->host))) || + inode_write_congested(mapping->host)) || (writeback && PageReclaim(page))) nr_congested++; @@ -935,10 +972,10 @@ static unsigned long shrink_page_list(struct list_head *page_list, * note that the LRU is being scanned too quickly and the * caller can stall after page list has been processed. * - * 2) Global reclaim encounters a page, memcg encounters a - * page that is not marked for immediate reclaim or - * the caller does not have __GFP_IO. In this case mark - * the page for immediate reclaim and continue scanning. + * 2) Global or new memcg reclaim encounters a page that is + * not marked for immediate reclaim or the caller does not + * have __GFP_IO. In this case mark the page for immediate + * reclaim and continue scanning. * * __GFP_IO is checked because a loop driver thread might * enter reclaim, and deadlock if it waits on a page for @@ -952,7 +989,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing * may_enter_fs here is liable to OOM on them. * - * 3) memcg encounters a page that is not already marked + * 3) Legacy memcg encounters a page that is not already marked * PageReclaim. memcg does not have any dirty pages * throttling so we could easily OOM just because too many * pages are in writeback and there is nothing else to @@ -967,7 +1004,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep_locked; /* Case 2 above */ - } else if (global_reclaim(sc) || + } else if (sane_reclaim(sc) || !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) { /* * This is slightly racy - end_page_writeback() @@ -1416,7 +1453,7 @@ static int too_many_isolated(struct zone *zone, int file, if (current_is_kswapd()) return 0; - if (!global_reclaim(sc)) + if (!sane_reclaim(sc)) return 0; if (file) { @@ -1608,10 +1645,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, set_bit(ZONE_WRITEBACK, &zone->flags); /* - * memcg will stall in page writeback so only consider forcibly - * stalling for global reclaim + * Legacy memcg will stall in page writeback so avoid forcibly + * stalling here. */ - if (global_reclaim(sc)) { + if (sane_reclaim(sc)) { /* * Tag a zone as congested if all the dirty pages scanned were * backed by a congested BDI and wait_iff_congested will stall. |