#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)";
DEFINE_SPINLOCK(bdi_lock);
static u64 bdi_id_cursor;
static struct rb_root bdi_tree = RB_ROOT;
LIST_HEAD(bdi_list);
struct workqueue_struct *bdi_wq;
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#include <linux/seq_file.h>
static struct dentry *bdi_debug_root;
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)
{
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++;
list_for_each_entry(inode, &wb->b_io, i_io_list)
nr_io++;
list_for_each_entry(inode, &wb->b_more_io, i_io_list)
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++;
spin_unlock(&wb->list_lock);
global_dirty_limits(&background_thresh, &dirty_thresh);
wb_thresh = wb_calc_thresh(wb, dirty_thresh);
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",
(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(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->wb.state);
return 0;
}
DEFINE_SHOW_ATTRIBUTE(bdi_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);
}
static void bdi_debug_unregister(struct backing_dev_info *bdi)
{
debugfs_remove_recursive(bdi->debug_dir);
}
#else
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
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);
void wb_wakeup_delayed(struct bdi_writeback *wb)
{
unsigned long timeout;
timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
spin_lock_irq(&wb->work_lock);
if (test_bit(WB_registered, &wb->state))
queue_delayed_work(bdi_wq, &wb->dwork, timeout);
spin_unlock_irq(&wb->work_lock);
}
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);
}
#define INIT_BW (100 << (20 - PAGE_SHIFT))
static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
gfp_t gfp)
{
int i, 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);
wb->dirty_sleep = jiffies;
err = fprop_local_init_percpu(&wb->completions, gfp);
if (err)
return err;
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 0;
out_destroy_stat:
while (i--)
percpu_counter_destroy(&wb->stat[i]);
fprop_local_destroy_percpu(&wb->completions);
return err;
}
static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
static void wb_shutdown(struct bdi_writeback *wb)
{
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);
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]);
fprop_local_destroy_percpu(&wb->completions);
}
#ifdef CONFIG_CGROUP_WRITEBACK
#include <linux/memcontrol.h>
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);
css_put(wb->blkcg_css);
mutex_unlock(&wb->bdi->cgwb_release_mutex);
blkcg_unpin_online(wb->blkcg_css);
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));
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);
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;
wb = kmalloc(sizeof(*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->release_work, cgwb_release_workfn);
set_bit(WB_registered, &wb->state);
bdi_get(bdi);
ret = -ENODEV;
spin_lock_irqsave(&cgwb_lock, flags);
if (test_bit(WB_registered, &bdi->wb.state) &&
blkcg_cgwb_list->next && memcg_cgwb_list->next) {
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;
}
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;
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;
}
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;
}
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);
}
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_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);
}
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;
spin_unlock_irq(&cgwb_lock);
queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work);
}
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;
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)
{
cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 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);
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_CAP_WRITEBACK_ACCT;
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;
}
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)
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);
}
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)
{
del_timer_sync(&bdi->laptop_mode_wb_timer);
bdi_remove_from_list(bdi);
wb_shutdown(&bdi->wb);
cgwb_bdi_unregister(bdi);
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