Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224// SPDX-License-Identifier: GPL-2.0-only
#include <linux/blkdev.h>#include <linux/wait.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;EXPORT_SYMBOL_GPL(noop_backing_dev_info);
static const char *bdi_unknown_name = "(unknown)";
/* * 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 */struct workqueue_struct *bdi_wq;
#ifdef CONFIG_DEBUG_FS#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){ bdi_debug_root = debugfs_create_dir("bdi", NULL);}
static void collect_wb_stats(struct wb_stats *stats, struct bdi_writeback *wb){ struct inode *inode;
spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) 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_WRITEBACKstatic 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();}#elsestatic 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);
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" "BdiDirtyThresh: %10lu kB\n" "DirtyThresh: %10lu kB\n" "BackgroundThresh: %10lu kB\n" "BdiDirtied: %10lu kB\n" "BdiWritten: %10lu kB\n" "BdiWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", K(stats.nr_writeback), K(stats.nr_reclaimable), K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), 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);
return 0;}DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats);
static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, struct wb_stats *stats){
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);}
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_recursive(bdi->debug_dir);}#else /* CONFIG_DEBUG_FS */static inline void bdi_debug_init(void){}static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name){}static inline void bdi_debug_unregister(struct backing_dev_info *bdi){}#endif /* CONFIG_DEBUG_FS */
static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count){ struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned long read_ahead_kb; ssize_t ret;
ret = kstrtoul(buf, 10, &read_ahead_kb); if (ret < 0) return ret;
bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);
return count;}
#define BDI_SHOW(name, expr) \static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \{ \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return sysfs_emit(buf, "%lld\n", (long long)expr); \} \static DEVICE_ATTR_RW(name);
BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
static ssize_t min_ratio_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(bdi, ratio); if (!ret) ret = count;
return ret;}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){ 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(bdi, ratio); if (!ret) ret = count;
return ret;}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 *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 sysfs_emit(buf, "%d\n", !!(bdi->capabilities & BDI_CAP_STRICTLIMIT));}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){ int ret;
ret = class_register(&bdi_class); if (ret) return ret;
bdi_debug_init();
return 0;}postcore_initcall(bdi_class_init);
static int __init default_bdi_init(void){ bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; return 0;}subsys_initcall(default_bdi_init);
static void wb_update_bandwidth_workfn(struct work_struct *work){ struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, bw_dwork);
wb_update_bandwidth(wb);}
/* * Initial write bandwidth: 100 MB/s */#define INIT_BW MB_TO_PAGES(100)
static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp){ int err;
memset(wb, 0, sizeof(*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);
atomic_set(&wb->writeback_inodes, 0); 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;
spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
err = fprop_local_init_percpu(&wb->completions, gfp); if (err) return err;
err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); if (err) fprop_local_destroy_percpu(&wb->completions);
return err;}
static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
/* * Remove bdi from the global list and shutdown any threads we have running */static void wb_shutdown(struct bdi_writeback *wb){ /* Make sure nobody queues further work */ spin_lock_irq(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_irq(&wb->work_lock); return; } spin_unlock_irq(&wb->work_lock);
cgwb_remove_from_bdi_list(wb); /* * 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. */ 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){ WARN_ON(delayed_work_pending(&wb->dwork)); percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions);}
#ifdef CONFIG_CGROUP_WRITEBACK
#include <linux/memcontrol.h>
/* * 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;
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);
static void cgwb_free_rcu(struct rcu_head *rcu_head){ struct bdi_writeback *wb = container_of(rcu_head, struct bdi_writeback, rcu);
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 backing_dev_info *bdi = wb->bdi;
mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb);
css_put(wb->memcg_css);
/* triggers blkg destruction if no online users left */ blkcg_unpin_online(wb->blkcg_css);
css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex);
fprop_local_destroy_percpu(&wb->memcg_completions);
spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock);
wb_exit(wb); 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){ struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); queue_work(cgwb_release_wq, &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); list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt);}
static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb){ spin_lock_irq(&cgwb_lock); list_del_rcu(&wb->bdi_node); spin_unlock_irq(&cgwb_lock);}
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 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, &io_cgrp_subsys); memcg_cgwb_list = &memcg->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); 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_obj(*wb, gfp); if (!wb) { ret = -ENOMEM; goto out_put; }
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->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 * 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(). */ 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) { 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_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } } spin_unlock_irqrestore(&cgwb_lock, flags); if (ret) { if (ret == -EEXIST) ret = 0; goto err_fprop_exit; } goto out_put;
err_fprop_exit: bdi_put(bdi); 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;}
/** * 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) * * 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 * @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_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_alloc(gfp);
do { wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp));
return wb;}
static int cgwb_bdi_init(struct backing_dev_info *bdi){ int ret;
INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem);
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;}
static void cgwb_bdi_unregister(struct backing_dev_info *bdi){ struct radix_tree_iter iter; void **slot; struct bdi_writeback *wb;
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);
mutex_lock(&bdi->cgwb_release_mutex); spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); 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 * * Also prevents creation of any new wb's associated with @memcg. */void wb_memcg_offline(struct mem_cgroup *memcg){ struct list_head *memcg_cgwb_list = &memcg->cgwb_list; 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);
queue_work(system_dfl_wq, &cleanup_offline_cgwbs_work);}
/** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @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, list, blkcg_node) cgwb_kill(wb); list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock);}
static void cgwb_bdi_register(struct backing_dev_info *bdi){ spin_lock_irq(&cgwb_lock); list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); spin_unlock_irq(&cgwb_lock);}
static int __init cgwb_init(void){ /* * There can be many concurrent release work items overwhelming * system_percpu_wq. Put them in a separate wq and limit concurrency. * There's no point in executing many of these in parallel. */ cgwb_release_wq = alloc_workqueue("cgwb_release", WQ_PERCPU, 1); if (!cgwb_release_wq) return -ENOMEM;
return 0;}subsys_initcall(cgwb_init);
#else /* CONFIG_CGROUP_WRITEBACK */
static int cgwb_bdi_init(struct backing_dev_info *bdi){ return wb_init(&bdi->wb, bdi, GFP_KERNEL);}
static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { }
static void cgwb_bdi_register(struct backing_dev_info *bdi){ list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);}
static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb){ list_del_rcu(&wb->bdi_node);}
#endif /* CONFIG_CGROUP_WRITEBACK */
int bdi_init(struct backing_dev_info *bdi){ bdi->dev = NULL;
kref_init(&bdi->refcnt); bdi->min_ratio = 0; 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;
return cgwb_bdi_init(bdi);}
struct backing_dev_info *bdi_alloc(int node_id){ struct backing_dev_info *bdi;
bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL;
if (bdi_init(bdi)) { kfree(bdi); return NULL; } bdi->capabilities = BDI_CAP_WRITEBACK; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; 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;}
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;
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);
cgwb_bdi_register(bdi); bdi->dev = dev;
bdi_debug_register(bdi, dev_name(dev)); 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;}
int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...){ va_list args; int ret;
va_start(args, fmt); ret = bdi_register_va(bdi, fmt, args); va_end(args); return ret;}EXPORT_SYMBOL(bdi_register);
void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner){ WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner);}
/* * 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); rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock);
synchronize_rcu_expedited();}
void bdi_unregister(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_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); bdi->dev = NULL; }
if (bdi->owner) { put_device(bdi->owner); 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);
WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi);}
void bdi_put(struct backing_dev_info *bdi){ kref_put(&bdi->refcnt, release_bdi);}EXPORT_SYMBOL(bdi_put);
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 I_BDEV(inode)->bd_disk->bdi;#endif return sb->s_bdi;}EXPORT_SYMBOL(inode_to_bdi);
const char *bdi_dev_name(struct backing_dev_info *bdi){ if (!bdi || !bdi->dev) return bdi_unknown_name; return bdi->dev_name;}EXPORT_SYMBOL_GPL(bdi_dev_name);