diff options
Diffstat (limited to 'mm/backing-dev.c')
| -rw-r--r-- | mm/backing-dev.c | 979 |
1 files changed, 562 insertions, 417 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8a8bb8796c6c..c5740c6d37a2 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,30 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/blkdev.h> #include <linux/wait.h> -#include <linux/backing-dev.h> +#include <linux/rbtree.h> #include <linux/kthread.h> +#include <linux/backing-dev.h> +#include <linux/blk-cgroup.h> #include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mm.h> +#include <linux/sched/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> #include <trace/events/writeback.h> +#include "internal.h" -struct backing_dev_info noop_backing_dev_info = { - .name = "noop", - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; +struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); -static struct class *bdi_class; +static const char *bdi_unknown_name = "(unknown)"; /* - * bdi_lock protects updates to bdi_list. bdi_list has RCU reader side - * locking. + * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU + * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); +static u64 bdi_id_cursor; +static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ @@ -34,6 +39,19 @@ struct workqueue_struct *bdi_wq; #include <linux/debugfs.h> #include <linux/seq_file.h> +struct wb_stats { + unsigned long nr_dirty; + unsigned long nr_io; + unsigned long nr_more_io; + unsigned long nr_dirty_time; + unsigned long nr_writeback; + unsigned long nr_reclaimable; + unsigned long nr_dirtied; + unsigned long nr_written; + unsigned long dirty_thresh; + unsigned long wb_thresh; +}; + static struct dentry *bdi_debug_root; static void bdi_debug_init(void) @@ -41,33 +59,69 @@ static void bdi_debug_init(void) bdi_debug_root = debugfs_create_dir("bdi", NULL); } -static int bdi_debug_stats_show(struct seq_file *m, void *v) +static void collect_wb_stats(struct wb_stats *stats, + struct bdi_writeback *wb) { - struct backing_dev_info *bdi = m->private; - struct bdi_writeback *wb = &bdi->wb; - unsigned long background_thresh; - unsigned long dirty_thresh; - unsigned long wb_thresh; - unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time; struct inode *inode; - nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) - nr_dirty++; + stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) - nr_io++; + stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) - nr_more_io++; + stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) - if (inode->i_state & I_DIRTY_TIME) - nr_dirty_time++; + if (inode_state_read_once(inode) & I_DIRTY_TIME) + stats->nr_dirty_time++; spin_unlock(&wb->list_lock); + stats->nr_writeback += wb_stat(wb, WB_WRITEBACK); + stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE); + stats->nr_dirtied += wb_stat(wb, WB_DIRTIED); + stats->nr_written += wb_stat(wb, WB_WRITTEN); + stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh); +} + +#ifdef CONFIG_CGROUP_WRITEBACK +static void bdi_collect_stats(struct backing_dev_info *bdi, + struct wb_stats *stats) +{ + struct bdi_writeback *wb; + + rcu_read_lock(); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { + if (!wb_tryget(wb)) + continue; + + collect_wb_stats(stats, wb); + wb_put(wb); + } + rcu_read_unlock(); +} +#else +static void bdi_collect_stats(struct backing_dev_info *bdi, + struct wb_stats *stats) +{ + collect_wb_stats(stats, &bdi->wb); +} +#endif + +static int bdi_debug_stats_show(struct seq_file *m, void *v) +{ + struct backing_dev_info *bdi = m->private; + unsigned long background_thresh; + unsigned long dirty_thresh; + struct wb_stats stats; + unsigned long tot_bw; + global_dirty_limits(&background_thresh, &dirty_thresh); - wb_thresh = wb_calc_thresh(wb, dirty_thresh); -#define K(x) ((x) << (PAGE_SHIFT - 10)) + memset(&stats, 0, sizeof(stats)); + stats.dirty_thresh = dirty_thresh; + bdi_collect_stats(bdi, &stats); + tot_bw = atomic_long_read(&bdi->tot_write_bandwidth); + seq_printf(m, "BdiWriteback: %10lu kB\n" "BdiReclaimable: %10lu kB\n" @@ -83,63 +137,125 @@ 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(wb_stat(wb, WB_WRITEBACK)), - (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)), - K(wb_thresh), + K(stats.nr_writeback), + K(stats.nr_reclaimable), + K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), - (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, + K(stats.nr_dirtied), + K(stats.nr_written), + K(tot_bw), + stats.nr_dirty, + stats.nr_io, + stats.nr_more_io, + stats.nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); -#undef K return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); -static int bdi_debug_register(struct backing_dev_info *bdi, const char *name) +static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, + struct wb_stats *stats) { - if (!bdi_debug_root) - return -ENOMEM; - bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); - if (!bdi->debug_dir) - return -ENOMEM; + seq_printf(m, + "WbCgIno: %10lu\n" + "WbWriteback: %10lu kB\n" + "WbReclaimable: %10lu kB\n" + "WbDirtyThresh: %10lu kB\n" + "WbDirtied: %10lu kB\n" + "WbWritten: %10lu kB\n" + "WbWriteBandwidth: %10lu kBps\n" + "b_dirty: %10lu\n" + "b_io: %10lu\n" + "b_more_io: %10lu\n" + "b_dirty_time: %10lu\n" + "state: %10lx\n\n", +#ifdef CONFIG_CGROUP_WRITEBACK + cgroup_ino(wb->memcg_css->cgroup), +#else + 1ul, +#endif + K(stats->nr_writeback), + K(stats->nr_reclaimable), + K(stats->wb_thresh), + K(stats->nr_dirtied), + K(stats->nr_written), + K(wb->avg_write_bandwidth), + stats->nr_dirty, + stats->nr_io, + stats->nr_more_io, + stats->nr_dirty_time, + wb->state); +} - bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir, - bdi, &bdi_debug_stats_fops); - if (!bdi->debug_stats) { - debugfs_remove(bdi->debug_dir); - bdi->debug_dir = NULL; - return -ENOMEM; +static int cgwb_debug_stats_show(struct seq_file *m, void *v) +{ + struct backing_dev_info *bdi = m->private; + unsigned long background_thresh; + unsigned long dirty_thresh; + struct bdi_writeback *wb; + + global_dirty_limits(&background_thresh, &dirty_thresh); + + rcu_read_lock(); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { + struct wb_stats stats = { .dirty_thresh = dirty_thresh }; + + if (!wb_tryget(wb)) + continue; + + collect_wb_stats(&stats, wb); + + /* + * Calculate thresh of wb in writeback cgroup which is min of + * thresh in global domain and thresh in cgroup domain. Drop + * rcu lock because cgwb_calc_thresh may sleep in + * cgroup_rstat_flush. We can do so here because we have a ref. + */ + if (mem_cgroup_wb_domain(wb)) { + rcu_read_unlock(); + stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); + rcu_read_lock(); + } + + wb_stats_show(m, wb, &stats); + + wb_put(wb); } + rcu_read_unlock(); return 0; } +DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); + +static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) +{ + bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); + + debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, + &bdi_debug_stats_fops); + debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, + &cgwb_debug_stats_fops); +} static void bdi_debug_unregister(struct backing_dev_info *bdi) { - debugfs_remove(bdi->debug_stats); - debugfs_remove(bdi->debug_dir); + debugfs_remove_recursive(bdi->debug_dir); } -#else +#else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } -static inline int bdi_debug_register(struct backing_dev_info *bdi, +static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { - return 0; } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } -#endif +#endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, @@ -158,15 +274,13 @@ static ssize_t read_ahead_kb_store(struct device *dev, return count; } -#define K(pages) ((pages) << (PAGE_SHIFT - 10)) - #define BDI_SHOW(name, expr) \ static ssize_t name##_show(struct device *dev, \ - struct device_attribute *attr, char *page) \ + struct device_attribute *attr, char *buf) \ { \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ - return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr); \ + return sysfs_emit(buf, "%lld\n", (long long)expr); \ } \ static DEVICE_ATTR_RW(name); @@ -189,7 +303,26 @@ static ssize_t min_ratio_store(struct device *dev, return ret; } -BDI_SHOW(min_ratio, bdi->min_ratio) +BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE) + +static ssize_t min_ratio_fine_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + unsigned int ratio; + ssize_t ret; + + ret = kstrtouint(buf, 10, &ratio); + if (ret < 0) + return ret; + + ret = bdi_set_min_ratio_no_scale(bdi, ratio); + if (!ret) + ret = count; + + return ret; +} +BDI_SHOW(min_ratio_fine, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -208,97 +341,184 @@ static ssize_t max_ratio_store(struct device *dev, return ret; } -BDI_SHOW(max_ratio, bdi->max_ratio) +BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE) + +static ssize_t max_ratio_fine_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + unsigned int ratio; + ssize_t ret; + + ret = kstrtouint(buf, 10, &ratio); + if (ret < 0) + return ret; + + ret = bdi_set_max_ratio_no_scale(bdi, ratio); + if (!ret) + ret = count; + + return ret; +} +BDI_SHOW(max_ratio_fine, bdi->max_ratio) + +static ssize_t min_bytes_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi)); +} + +static ssize_t min_bytes_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + u64 bytes; + ssize_t ret; + + ret = kstrtoull(buf, 10, &bytes); + if (ret < 0) + return ret; + + ret = bdi_set_min_bytes(bdi, bytes); + if (!ret) + ret = count; + + return ret; +} +static DEVICE_ATTR_RW(min_bytes); + +static ssize_t max_bytes_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi)); +} + +static ssize_t max_bytes_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + u64 bytes; + ssize_t ret; + + ret = kstrtoull(buf, 10, &bytes); + if (ret < 0) + return ret; + + ret = bdi_set_max_bytes(bdi, bytes); + if (!ret) + ret = count; + + return ret; +} +static DEVICE_ATTR_RW(max_bytes); static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, - char *page) + char *buf) +{ + dev_warn_once(dev, + "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); + return sysfs_emit(buf, "%d\n", 0); +} +static DEVICE_ATTR_RO(stable_pages_required); + +static ssize_t strict_limit_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + unsigned int strict_limit; + ssize_t ret; + + ret = kstrtouint(buf, 10, &strict_limit); + if (ret < 0) + return ret; + + ret = bdi_set_strict_limit(bdi, strict_limit); + if (!ret) + ret = count; + + return ret; +} + +static ssize_t strict_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); - return snprintf(page, PAGE_SIZE-1, "%d\n", - bdi_cap_stable_pages_required(bdi) ? 1 : 0); + return sysfs_emit(buf, "%d\n", + !!(bdi->capabilities & BDI_CAP_STRICTLIMIT)); } -static DEVICE_ATTR_RO(stable_pages_required); +static DEVICE_ATTR_RW(strict_limit); static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, + &dev_attr_min_ratio_fine.attr, &dev_attr_max_ratio.attr, + &dev_attr_max_ratio_fine.attr, + &dev_attr_min_bytes.attr, + &dev_attr_max_bytes.attr, &dev_attr_stable_pages_required.attr, + &dev_attr_strict_limit.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); +static const struct class bdi_class = { + .name = "bdi", + .dev_groups = bdi_dev_groups, +}; + static __init int bdi_class_init(void) { - bdi_class = class_create(THIS_MODULE, "bdi"); - if (IS_ERR(bdi_class)) - return PTR_ERR(bdi_class); + int ret; + + ret = class_register(&bdi_class); + if (ret) + return ret; - bdi_class->dev_groups = bdi_dev_groups; bdi_debug_init(); return 0; } postcore_initcall(bdi_class_init); -static int bdi_init(struct backing_dev_info *bdi); - static int __init default_bdi_init(void) { - int err; - - bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE | - WQ_UNBOUND | WQ_SYSFS, 0); + bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | + WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; - - err = bdi_init(&noop_backing_dev_info); - - return err; + return 0; } subsys_initcall(default_bdi_init); -/* - * 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 - * set up a timer which wakes the bdi thread up later. - * - * Note, we wouldn't bother setting up the timer, but this function is on the - * fast-path (used by '__mark_inode_dirty()'), so we save few context switches - * by delaying the wake-up. - * - * We have to be careful not to postpone flush work if it is scheduled for - * earlier. Thus we use queue_delayed_work(). - */ -void wb_wakeup_delayed(struct bdi_writeback *wb) +static void wb_update_bandwidth_workfn(struct work_struct *work) { - unsigned long timeout; + struct bdi_writeback *wb = container_of(to_delayed_work(work), + struct bdi_writeback, bw_dwork); - timeout = msecs_to_jiffies(dirty_writeback_interval * 10); - 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); + wb_update_bandwidth(wb); } /* * Initial write bandwidth: 100 MB/s */ -#define INIT_BW (100 << (20 - PAGE_SHIFT)) +#define INIT_BW MB_TO_PAGES(100) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, - int blkcg_id, gfp_t gfp) + gfp_t gfp) { - int i, err; + int err; memset(wb, 0, sizeof(*wb)); - if (wb != &bdi->wb) - bdi_get(bdi); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); @@ -307,6 +527,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); + atomic_set(&wb->writeback_inodes, 0); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; @@ -316,35 +537,16 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); - wb->dirty_sleep = jiffies; - - wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp); - if (!wb->congested) { - err = -ENOMEM; - goto out_put_bdi; - } + INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); err = fprop_local_init_percpu(&wb->completions, gfp); if (err) - goto out_put_cong; - - for (i = 0; i < NR_WB_STAT_ITEMS; i++) { - err = percpu_counter_init(&wb->stat[i], 0, gfp); - if (err) - goto out_destroy_stat; - } + return err; - return 0; + err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); + if (err) + fprop_local_destroy_percpu(&wb->completions); -out_destroy_stat: - while (i--) - percpu_counter_destroy(&wb->stat[i]); - fprop_local_destroy_percpu(&wb->completions); -out_put_cong: - wb_congested_put(wb->congested); -out_put_bdi: - if (wb != &bdi->wb) - bdi_put(bdi); return err; } @@ -356,12 +558,12 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ - spin_lock_bh(&wb->work_lock); + spin_lock_irq(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); return; } - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); cgwb_remove_from_bdi_list(wb); /* @@ -372,21 +574,14 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); + flush_delayed_work(&wb->bw_dwork); } 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]); - + percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions); - wb_congested_put(wb->congested); - if (wb != &wb->bdi->wb) - bdi_put(wb->bdi); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -394,104 +589,30 @@ static void wb_exit(struct bdi_writeback *wb) #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_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and + * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; -/** - * 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; -retry: - spin_lock_irqsave(&cgwb_lock, flags); - - node = &bdi->cgwb_congested_tree.rb_node; - parent = NULL; - - while (*node != NULL) { - parent = *node; - congested = rb_entry(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; - rb_link_node(&congested->rb_node, parent, node); - rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); - spin_unlock_irqrestore(&cgwb_lock, flags); - return congested; - } - - 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; - - refcount_set(&new_congested->refcnt, 1); - new_congested->__bdi = bdi; - new_congested->blkcg_id = blkcg_id; - goto retry; - -found: - refcount_inc(&congested->refcnt); - spin_unlock_irqrestore(&cgwb_lock, flags); - kfree(new_congested); - return congested; -} +static LIST_HEAD(offline_cgwbs); +static void cleanup_offline_cgwbs_workfn(struct work_struct *work); +static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); -/** - * 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) +static void cgwb_free_rcu(struct rcu_head *rcu_head) { - unsigned long flags; - - if (!refcount_dec_and_lock_irqsave(&congested->refcnt, &cgwb_lock, &flags)) - return; - - /* bdi might already have been destroyed leaving @congested unlinked */ - if (congested->__bdi) { - rb_erase(&congested->rb_node, - &congested->__bdi->cgwb_congested_tree); - congested->__bdi = NULL; - } + struct bdi_writeback *wb = container_of(rcu_head, + struct bdi_writeback, rcu); - spin_unlock_irqrestore(&cgwb_lock, flags); - kfree(congested); + percpu_ref_exit(&wb->refcnt); + kfree(wb); } static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); - struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); + struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); @@ -500,13 +621,20 @@ static void cgwb_release_workfn(struct work_struct *work) css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); - /* triggers blkg destruction if cgwb_refcnt becomes zero */ - blkcg_cgwb_put(blkcg); + /* triggers blkg destruction if no online users left */ + blkcg_unpin_online(wb->blkcg_css); fprop_local_destroy_percpu(&wb->memcg_completions); - percpu_ref_exit(&wb->refcnt); + + spin_lock_irq(&cgwb_lock); + list_del(&wb->offline_node); + spin_unlock_irq(&cgwb_lock); + wb_exit(wb); - kfree_rcu(wb, rcu); + bdi_put(bdi); + WARN_ON_ONCE(!list_empty(&wb->b_attached)); + WARN_ON_ONCE(work_pending(&wb->switch_work)); + call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) @@ -523,6 +651,7 @@ static void cgwb_kill(struct bdi_writeback *wb) WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); + list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } @@ -538,7 +667,6 @@ static int cgwb_create(struct backing_dev_info *bdi, { 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; @@ -546,9 +674,8 @@ static int cgwb_create(struct backing_dev_info *bdi, memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); - blkcg = css_to_blkcg(blkcg_css); memcg_cgwb_list = &memcg->cgwb_list; - blkcg_cgwb_list = &blkcg->cgwb_list; + blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); @@ -568,7 +695,7 @@ static int cgwb_create(struct backing_dev_info *bdi, goto out_put; } - ret = wb_init(wb, bdi, blkcg_css->id, gfp); + ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; @@ -582,8 +709,12 @@ static int cgwb_create(struct backing_dev_info *bdi, wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; + INIT_LIST_HEAD(&wb->b_attached); + INIT_WORK(&wb->switch_work, inode_switch_wbs_work_fn); + init_llist_head(&wb->switch_wbs_ctxs); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); + bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and @@ -601,7 +732,7 @@ static int cgwb_create(struct backing_dev_info *bdi, list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); - blkcg_cgwb_get(blkcg); + blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } @@ -615,6 +746,7 @@ static int cgwb_create(struct backing_dev_info *bdi, goto out_put; err_fprop_exit: + bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); @@ -628,13 +760,12 @@ out_put: } /** - * wb_get_create - get wb for a given memcg, create if necessary + * wb_get_lookup - get wb for a given memcg * @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. + * Try to get the wb for @memcg_css on @bdi. 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 @@ -651,32 +782,49 @@ out_put: * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ +struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, + struct cgroup_subsys_state *memcg_css) +{ + struct bdi_writeback *wb; + + if (!memcg_css->parent) + return &bdi->wb; + + 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, &io_cgrp_subsys); + if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) + wb = NULL; + css_put(blkcg_css); + } + rcu_read_unlock(); + + return wb; +} + +/** + * 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. See wb_get_lookup() for more details. + */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct bdi_writeback *wb; - might_sleep_if(gfpflags_allow_blocking(gfp)); - - if (!memcg_css->parent) - return &bdi->wb; + might_alloc(gfp); 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, - &io_cgrp_subsys); - if (unlikely(wb->blkcg_css != blkcg_css || - !wb_tryget(wb))) - wb = NULL; - css_put(blkcg_css); - } - rcu_read_unlock(); + wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; @@ -687,13 +835,15 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); - bdi->cgwb_congested_tree = RB_ROOT; mutex_init(&bdi->cgwb_release_mutex); + init_rwsem(&bdi->wb_switch_rwsem); - ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); + ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; + INIT_WORK(&bdi->wb.switch_work, inode_switch_wbs_work_fn); + init_llist_head(&bdi->wb.switch_wbs_ctxs); } return ret; } @@ -724,6 +874,54 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) mutex_unlock(&bdi->cgwb_release_mutex); } +/* + * cleanup_offline_cgwbs_workfn - try to release dying cgwbs + * + * Try to release dying cgwbs by switching attached inodes to the nearest + * living ancestor's writeback. Processed wbs are placed at the end + * of the list to guarantee the forward progress. + */ +static void cleanup_offline_cgwbs_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb; + LIST_HEAD(processed); + + spin_lock_irq(&cgwb_lock); + + while (!list_empty(&offline_cgwbs)) { + wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, + offline_node); + list_move(&wb->offline_node, &processed); + + /* + * If wb is dirty, cleaning up the writeback by switching + * attached inodes will result in an effective removal of any + * bandwidth restrictions, which isn't the goal. Instead, + * it can be postponed until the next time, when all io + * will be likely completed. If in the meantime some inodes + * will get re-dirtied, they should be eventually switched to + * a new cgwb. + */ + if (wb_has_dirty_io(wb)) + continue; + + if (!wb_tryget(wb)) + continue; + + spin_unlock_irq(&cgwb_lock); + while (cleanup_offline_cgwb(wb)) + cond_resched(); + spin_lock_irq(&cgwb_lock); + + wb_put(wb); + } + + if (!list_empty(&processed)) + list_splice_tail(&processed, &offline_cgwbs); + + spin_unlock_irq(&cgwb_lock); +} + /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined @@ -740,37 +938,25 @@ void wb_memcg_offline(struct mem_cgroup *memcg) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); + + queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work); } /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined - * @blkcg: blkcg being offlined + * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ -void wb_blkcg_offline(struct blkcg *blkcg) +void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; + struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); - list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node) + list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); - blkcg->cgwb_list.next = NULL; /* prevent new wb's */ - spin_unlock_irq(&cgwb_lock); -} - -static void cgwb_bdi_exit(struct backing_dev_info *bdi) -{ - struct rb_node *rbn; - - spin_lock_irq(&cgwb_lock); - while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { - struct bdi_writeback_congested *congested = - rb_entry(rbn, struct bdi_writeback_congested, rb_node); - - rb_erase(rbn, &bdi->cgwb_congested_tree); - congested->__bdi = NULL; /* mark @congested unlinked */ - } + list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } @@ -800,29 +986,11 @@ subsys_initcall(cgwb_init); static int cgwb_bdi_init(struct backing_dev_info *bdi) { - int err; - - bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL); - if (!bdi->wb_congested) - return -ENOMEM; - - refcount_set(&bdi->wb_congested->refcnt, 1); - - err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); - if (err) { - wb_congested_put(bdi->wb_congested); - return err; - } - return 0; + return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } -static void cgwb_bdi_exit(struct backing_dev_info *bdi) -{ - wb_congested_put(bdi->wb_congested); -} - static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); @@ -835,31 +1003,27 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) #endif /* CONFIG_CGROUP_WRITEBACK */ -static int bdi_init(struct backing_dev_info *bdi) +int bdi_init(struct backing_dev_info *bdi) { - int ret; - bdi->dev = NULL; kref_init(&bdi->refcnt); bdi->min_ratio = 0; - bdi->max_ratio = 100; + bdi->max_ratio = 100 * BDI_RATIO_SCALE; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); + bdi->last_bdp_sleep = jiffies; - ret = cgwb_bdi_init(bdi); - - return ret; + return cgwb_bdi_init(bdi); } -struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) +struct backing_dev_info *bdi_alloc(int node_id) { struct backing_dev_info *bdi; - bdi = kmalloc_node(sizeof(struct backing_dev_info), - gfp_mask | __GFP_ZERO, node_id); + bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL; @@ -867,18 +1031,72 @@ struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id) kfree(bdi); return NULL; } + bdi->capabilities = BDI_CAP_WRITEBACK; + bdi->ra_pages = VM_READAHEAD_PAGES; + bdi->io_pages = VM_READAHEAD_PAGES; + timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); + return bdi; +} +EXPORT_SYMBOL(bdi_alloc); + +static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) +{ + struct rb_node **p = &bdi_tree.rb_node; + struct rb_node *parent = NULL; + struct backing_dev_info *bdi; + + lockdep_assert_held(&bdi_lock); + + while (*p) { + parent = *p; + bdi = rb_entry(parent, struct backing_dev_info, rb_node); + + if (bdi->id > id) + p = &(*p)->rb_left; + else if (bdi->id < id) + p = &(*p)->rb_right; + else + break; + } + + if (parentp) + *parentp = parent; + return p; +} + +/** + * bdi_get_by_id - lookup and get bdi from its id + * @id: bdi id to lookup + * + * Find bdi matching @id and get it. Returns NULL if the matching bdi + * doesn't exist or is already unregistered. + */ +struct backing_dev_info *bdi_get_by_id(u64 id) +{ + struct backing_dev_info *bdi = NULL; + struct rb_node **p; + + spin_lock_bh(&bdi_lock); + p = bdi_lookup_rb_node(id, NULL); + if (*p) { + bdi = rb_entry(*p, struct backing_dev_info, rb_node); + bdi_get(bdi); + } + spin_unlock_bh(&bdi_lock); + return bdi; } -EXPORT_SYMBOL(bdi_alloc_node); int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; + struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); + vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); + dev = device_create(&bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); @@ -889,13 +1107,20 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); + + bdi->id = ++bdi_id_cursor; + + p = bdi_lookup_rb_node(bdi->id, &parent); + rb_link_node(&bdi->rb_node, parent, p); + rb_insert_color(&bdi->rb_node, &bdi_tree); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); return 0; } -EXPORT_SYMBOL(bdi_register_va); int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { @@ -909,20 +1134,12 @@ int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) } EXPORT_SYMBOL(bdi_register); -int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner) +void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) { - int rc; - - rc = bdi_register(bdi, "%u:%u", MAJOR(owner->devt), MINOR(owner->devt)); - if (rc) - return rc; - /* Leaking owner reference... */ - WARN_ON(bdi->owner); + WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner); - return 0; } -EXPORT_SYMBOL(bdi_register_owner); /* * Remove bdi from bdi_list, and ensure that it is no longer visible @@ -930,6 +1147,7 @@ EXPORT_SYMBOL(bdi_register_owner); static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); + rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); @@ -938,11 +1156,20 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi) void bdi_unregister(struct backing_dev_info *bdi) { + timer_delete_sync(&bdi->laptop_mode_wb_timer); + /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); + /* + * If this BDI's min ratio has been set, use bdi_set_min_ratio() to + * update the global bdi_min_ratio. + */ + if (bdi->min_ratio) + bdi_set_min_ratio(bdi, 0); + if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); @@ -954,17 +1181,16 @@ void bdi_unregister(struct backing_dev_info *bdi) bdi->owner = NULL; } } +EXPORT_SYMBOL(bdi_unregister); static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); - if (test_bit(WB_registered, &bdi->wb.state)) - bdi_unregister(bdi); + WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); - cgwb_bdi_exit(bdi); kfree(bdi); } @@ -974,107 +1200,26 @@ void bdi_put(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_put); -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_wb_congested[2]; - -void clear_wb_congested(struct bdi_writeback_congested *congested, int sync) +struct backing_dev_info *inode_to_bdi(struct inode *inode) { - wait_queue_head_t *wqh = &congestion_wqh[sync]; - enum wb_congested_state bit; - - 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_wb_congested); + struct super_block *sb; -void set_wb_congested(struct bdi_writeback_congested *congested, int sync) -{ - enum wb_congested_state bit; + if (!inode) + return &noop_backing_dev_info; - 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_wb_congested); - -/** - * congestion_wait - wait for a backing_dev to become uncongested - * @sync: SYNC or ASYNC IO - * @timeout: timeout in jiffies - * - * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit - * write congestion. If no backing_devs are congested then just wait for the - * next write to be completed. - */ -long congestion_wait(int sync, long timeout) -{ - long ret; - unsigned long start = jiffies; - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[sync]; - - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - ret = io_schedule_timeout(timeout); - finish_wait(wqh, &wait); - - trace_writeback_congestion_wait(jiffies_to_usecs(timeout), - jiffies_to_usecs(jiffies - start)); - - return ret; + sb = inode->i_sb; +#ifdef CONFIG_BLOCK + if (sb_is_blkdev_sb(sb)) + return I_BDEV(inode)->bd_disk->bdi; +#endif + return sb->s_bdi; } -EXPORT_SYMBOL(congestion_wait); +EXPORT_SYMBOL(inode_to_bdi); -/** - * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes - * @sync: SYNC or ASYNC IO - * @timeout: timeout in jiffies - * - * In the event of a congested backing_dev (any backing_dev) this waits - * for up to @timeout jiffies for either a BDI to exit congestion of the - * given @sync queue or a write to complete. - * - * The return value is 0 if the sleep is for the full timeout. Otherwise, - * it is the number of jiffies that were still remaining when the function - * returned. return_value == timeout implies the function did not sleep. - */ -long wait_iff_congested(int sync, long timeout) +const char *bdi_dev_name(struct backing_dev_info *bdi) { - long ret; - unsigned long start = jiffies; - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[sync]; - - /* - * If there is no congestion, yield if necessary instead - * of sleeping on the congestion queue - */ - if (atomic_read(&nr_wb_congested[sync]) == 0) { - cond_resched(); - - /* In case we scheduled, work out time remaining */ - ret = timeout - (jiffies - start); - if (ret < 0) - ret = 0; - - goto out; - } - - /* Sleep until uncongested or a write happens */ - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - ret = io_schedule_timeout(timeout); - finish_wait(wqh, &wait); - -out: - trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), - jiffies_to_usecs(jiffies - start)); - - return ret; + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return bdi->dev_name; } -EXPORT_SYMBOL(wait_iff_congested); +EXPORT_SYMBOL_GPL(bdi_dev_name); |