linux/block/blk-cgroup.c
Linus Torvalds 69234acee5 Merge branch 'for-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup updates from Tejun Heo:
 "The cgroup core saw several significant updates this cycle:

   - percpu_rwsem for threadgroup locking is reinstated.  This was
     temporarily dropped due to down_write latency issues.  Oleg's
     rework of percpu_rwsem which is scheduled to be merged in this
     merge window resolves the issue.

   - On the v2 hierarchy, when controllers are enabled and disabled, all
     operations are atomic and can fail and revert cleanly.  This allows
     ->can_attach() failure which is necessary for cpu RT slices.

   - Tasks now stay associated with the original cgroups after exit
     until released.  This allows tracking resources held by zombies
     (e.g.  pids) and makes it easy to find out where zombies came from
     on the v2 hierarchy.  The pids controller was broken before these
     changes as zombies escaped the limits; unfortunately, updating this
     behavior required too many invasive changes and I don't think it's
     a good idea to backport them, so the pids controller on 4.3, the
     first version which included the pids controller, will stay broken
     at least until I'm sure about the cgroup core changes.

   - Optimization of a couple common tests using static_key"

* 'for-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (38 commits)
  cgroup: fix race condition around termination check in css_task_iter_next()
  blkcg: don't create "io.stat" on the root cgroup
  cgroup: drop cgroup__DEVEL__legacy_files_on_dfl
  cgroup: replace error handling in cgroup_init() with WARN_ON()s
  cgroup: add cgroup_subsys->free() method and use it to fix pids controller
  cgroup: keep zombies associated with their original cgroups
  cgroup: make css_set_rwsem a spinlock and rename it to css_set_lock
  cgroup: don't hold css_set_rwsem across css task iteration
  cgroup: reorganize css_task_iter functions
  cgroup: factor out css_set_move_task()
  cgroup: keep css_set and task lists in chronological order
  cgroup: make cgroup_destroy_locked() test cgroup_is_populated()
  cgroup: make css_sets pin the associated cgroups
  cgroup: relocate cgroup_[try]get/put()
  cgroup: move check_for_release() invocation
  cgroup: replace cgroup_has_tasks() with cgroup_is_populated()
  cgroup: make cgroup->nr_populated count the number of populated css_sets
  cgroup: remove an unused parameter from cgroup_task_migrate()
  cgroup: fix too early usage of static_branch_disable()
  cgroup: make cgroup_update_dfl_csses() migrate all target processes atomically
  ...
2015-11-05 14:51:32 -08:00

1414 lines
36 KiB
C

/*
* Common Block IO controller cgroup interface
*
* Based on ideas and code from CFQ, CFS and BFQ:
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*
* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
* Paolo Valente <paolo.valente@unimore.it>
*
* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
* Nauman Rafique <nauman@google.com>
*
* For policy-specific per-blkcg data:
* Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
* Arianna Avanzini <avanzini.arianna@gmail.com>
*/
#include <linux/ioprio.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/slab.h>
#include <linux/genhd.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/ctype.h>
#include <linux/blk-cgroup.h>
#include "blk.h"
#define MAX_KEY_LEN 100
/*
* blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
* blkcg_pol_register_mutex nests outside of it and synchronizes entire
* policy [un]register operations including cgroup file additions /
* removals. Putting cgroup file registration outside blkcg_pol_mutex
* allows grabbing it from cgroup callbacks.
*/
static DEFINE_MUTEX(blkcg_pol_register_mutex);
static DEFINE_MUTEX(blkcg_pol_mutex);
struct blkcg blkcg_root;
EXPORT_SYMBOL_GPL(blkcg_root);
struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;
static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */
static bool blkcg_policy_enabled(struct request_queue *q,
const struct blkcg_policy *pol)
{
return pol && test_bit(pol->plid, q->blkcg_pols);
}
/**
* blkg_free - free a blkg
* @blkg: blkg to free
*
* Free @blkg which may be partially allocated.
*/
static void blkg_free(struct blkcg_gq *blkg)
{
int i;
if (!blkg)
return;
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (blkg->pd[i])
blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
if (blkg->blkcg != &blkcg_root)
blk_exit_rl(&blkg->rl);
blkg_rwstat_exit(&blkg->stat_ios);
blkg_rwstat_exit(&blkg->stat_bytes);
kfree(blkg);
}
/**
* blkg_alloc - allocate a blkg
* @blkcg: block cgroup the new blkg is associated with
* @q: request_queue the new blkg is associated with
* @gfp_mask: allocation mask to use
*
* Allocate a new blkg assocating @blkcg and @q.
*/
static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
gfp_t gfp_mask)
{
struct blkcg_gq *blkg;
int i;
/* alloc and init base part */
blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
if (!blkg)
return NULL;
if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) ||
blkg_rwstat_init(&blkg->stat_ios, gfp_mask))
goto err_free;
blkg->q = q;
INIT_LIST_HEAD(&blkg->q_node);
blkg->blkcg = blkcg;
atomic_set(&blkg->refcnt, 1);
/* root blkg uses @q->root_rl, init rl only for !root blkgs */
if (blkcg != &blkcg_root) {
if (blk_init_rl(&blkg->rl, q, gfp_mask))
goto err_free;
blkg->rl.blkg = blkg;
}
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
struct blkg_policy_data *pd;
if (!blkcg_policy_enabled(q, pol))
continue;
/* alloc per-policy data and attach it to blkg */
pd = pol->pd_alloc_fn(gfp_mask, q->node);
if (!pd)
goto err_free;
blkg->pd[i] = pd;
pd->blkg = blkg;
pd->plid = i;
}
return blkg;
err_free:
blkg_free(blkg);
return NULL;
}
struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
struct request_queue *q, bool update_hint)
{
struct blkcg_gq *blkg;
/*
* Hint didn't match. Look up from the radix tree. Note that the
* hint can only be updated under queue_lock as otherwise @blkg
* could have already been removed from blkg_tree. The caller is
* responsible for grabbing queue_lock if @update_hint.
*/
blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
if (blkg && blkg->q == q) {
if (update_hint) {
lockdep_assert_held(q->queue_lock);
rcu_assign_pointer(blkcg->blkg_hint, blkg);
}
return blkg;
}
return NULL;
}
EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);
/*
* If @new_blkg is %NULL, this function tries to allocate a new one as
* necessary using %GFP_NOWAIT. @new_blkg is always consumed on return.
*/
static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
struct request_queue *q,
struct blkcg_gq *new_blkg)
{
struct blkcg_gq *blkg;
struct bdi_writeback_congested *wb_congested;
int i, ret;
WARN_ON_ONCE(!rcu_read_lock_held());
lockdep_assert_held(q->queue_lock);
/* blkg holds a reference to blkcg */
if (!css_tryget_online(&blkcg->css)) {
ret = -ENODEV;
goto err_free_blkg;
}
wb_congested = wb_congested_get_create(&q->backing_dev_info,
blkcg->css.id, GFP_NOWAIT);
if (!wb_congested) {
ret = -ENOMEM;
goto err_put_css;
}
/* allocate */
if (!new_blkg) {
new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT);
if (unlikely(!new_blkg)) {
ret = -ENOMEM;
goto err_put_congested;
}
}
blkg = new_blkg;
blkg->wb_congested = wb_congested;
/* link parent */
if (blkcg_parent(blkcg)) {
blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
if (WARN_ON_ONCE(!blkg->parent)) {
ret = -ENODEV;
goto err_put_congested;
}
blkg_get(blkg->parent);
}
/* invoke per-policy init */
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_init_fn)
pol->pd_init_fn(blkg->pd[i]);
}
/* insert */
spin_lock(&blkcg->lock);
ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg);
if (likely(!ret)) {
hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
list_add(&blkg->q_node, &q->blkg_list);
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_online_fn)
pol->pd_online_fn(blkg->pd[i]);
}
}
blkg->online = true;
spin_unlock(&blkcg->lock);
if (!ret)
return blkg;
/* @blkg failed fully initialized, use the usual release path */
blkg_put(blkg);
return ERR_PTR(ret);
err_put_congested:
wb_congested_put(wb_congested);
err_put_css:
css_put(&blkcg->css);
err_free_blkg:
blkg_free(new_blkg);
return ERR_PTR(ret);
}
/**
* blkg_lookup_create - lookup blkg, try to create one if not there
* @blkcg: blkcg of interest
* @q: request_queue of interest
*
* Lookup blkg for the @blkcg - @q pair. If it doesn't exist, try to
* create one. blkg creation is performed recursively from blkcg_root such
* that all non-root blkg's have access to the parent blkg. This function
* should be called under RCU read lock and @q->queue_lock.
*
* Returns pointer to the looked up or created blkg on success, ERR_PTR()
* value on error. If @q is dead, returns ERR_PTR(-EINVAL). If @q is not
* dead and bypassing, returns ERR_PTR(-EBUSY).
*/
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
struct request_queue *q)
{
struct blkcg_gq *blkg;
WARN_ON_ONCE(!rcu_read_lock_held());
lockdep_assert_held(q->queue_lock);
/*
* This could be the first entry point of blkcg implementation and
* we shouldn't allow anything to go through for a bypassing queue.
*/
if (unlikely(blk_queue_bypass(q)))
return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
blkg = __blkg_lookup(blkcg, q, true);
if (blkg)
return blkg;
/*
* Create blkgs walking down from blkcg_root to @blkcg, so that all
* non-root blkgs have access to their parents.
*/
while (true) {
struct blkcg *pos = blkcg;
struct blkcg *parent = blkcg_parent(blkcg);
while (parent && !__blkg_lookup(parent, q, false)) {
pos = parent;
parent = blkcg_parent(parent);
}
blkg = blkg_create(pos, q, NULL);
if (pos == blkcg || IS_ERR(blkg))
return blkg;
}
}
static void blkg_destroy(struct blkcg_gq *blkg)
{
struct blkcg *blkcg = blkg->blkcg;
struct blkcg_gq *parent = blkg->parent;
int i;
lockdep_assert_held(blkg->q->queue_lock);
lockdep_assert_held(&blkcg->lock);
/* Something wrong if we are trying to remove same group twice */
WARN_ON_ONCE(list_empty(&blkg->q_node));
WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_offline_fn)
pol->pd_offline_fn(blkg->pd[i]);
}
if (parent) {
blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
}
blkg->online = false;
radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
list_del_init(&blkg->q_node);
hlist_del_init_rcu(&blkg->blkcg_node);
/*
* Both setting lookup hint to and clearing it from @blkg are done
* under queue_lock. If it's not pointing to @blkg now, it never
* will. Hint assignment itself can race safely.
*/
if (rcu_access_pointer(blkcg->blkg_hint) == blkg)
rcu_assign_pointer(blkcg->blkg_hint, NULL);
/*
* Put the reference taken at the time of creation so that when all
* queues are gone, group can be destroyed.
*/
blkg_put(blkg);
}
/**
* blkg_destroy_all - destroy all blkgs associated with a request_queue
* @q: request_queue of interest
*
* Destroy all blkgs associated with @q.
*/
static void blkg_destroy_all(struct request_queue *q)
{
struct blkcg_gq *blkg, *n;
lockdep_assert_held(q->queue_lock);
list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
struct blkcg *blkcg = blkg->blkcg;
spin_lock(&blkcg->lock);
blkg_destroy(blkg);
spin_unlock(&blkcg->lock);
}
q->root_blkg = NULL;
q->root_rl.blkg = NULL;
}
/*
* A group is RCU protected, but having an rcu lock does not mean that one
* can access all the fields of blkg and assume these are valid. For
* example, don't try to follow throtl_data and request queue links.
*
* Having a reference to blkg under an rcu allows accesses to only values
* local to groups like group stats and group rate limits.
*/
void __blkg_release_rcu(struct rcu_head *rcu_head)
{
struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head);
/* release the blkcg and parent blkg refs this blkg has been holding */
css_put(&blkg->blkcg->css);
if (blkg->parent)
blkg_put(blkg->parent);
wb_congested_put(blkg->wb_congested);
blkg_free(blkg);
}
EXPORT_SYMBOL_GPL(__blkg_release_rcu);
/*
* The next function used by blk_queue_for_each_rl(). It's a bit tricky
* because the root blkg uses @q->root_rl instead of its own rl.
*/
struct request_list *__blk_queue_next_rl(struct request_list *rl,
struct request_queue *q)
{
struct list_head *ent;
struct blkcg_gq *blkg;
/*
* Determine the current blkg list_head. The first entry is
* root_rl which is off @q->blkg_list and mapped to the head.
*/
if (rl == &q->root_rl) {
ent = &q->blkg_list;
/* There are no more block groups, hence no request lists */
if (list_empty(ent))
return NULL;
} else {
blkg = container_of(rl, struct blkcg_gq, rl);
ent = &blkg->q_node;
}
/* walk to the next list_head, skip root blkcg */
ent = ent->next;
if (ent == &q->root_blkg->q_node)
ent = ent->next;
if (ent == &q->blkg_list)
return NULL;
blkg = container_of(ent, struct blkcg_gq, q_node);
return &blkg->rl;
}
static int blkcg_reset_stats(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 val)
{
struct blkcg *blkcg = css_to_blkcg(css);
struct blkcg_gq *blkg;
int i;
mutex_lock(&blkcg_pol_mutex);
spin_lock_irq(&blkcg->lock);
/*
* Note that stat reset is racy - it doesn't synchronize against
* stat updates. This is a debug feature which shouldn't exist
* anyway. If you get hit by a race, retry.
*/
hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
blkg_rwstat_reset(&blkg->stat_bytes);
blkg_rwstat_reset(&blkg->stat_ios);
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_reset_stats_fn)
pol->pd_reset_stats_fn(blkg->pd[i]);
}
}
spin_unlock_irq(&blkcg->lock);
mutex_unlock(&blkcg_pol_mutex);
return 0;
}
const char *blkg_dev_name(struct blkcg_gq *blkg)
{
/* some drivers (floppy) instantiate a queue w/o disk registered */
if (blkg->q->backing_dev_info.dev)
return dev_name(blkg->q->backing_dev_info.dev);
return NULL;
}
EXPORT_SYMBOL_GPL(blkg_dev_name);
/**
* blkcg_print_blkgs - helper for printing per-blkg data
* @sf: seq_file to print to
* @blkcg: blkcg of interest
* @prfill: fill function to print out a blkg
* @pol: policy in question
* @data: data to be passed to @prfill
* @show_total: to print out sum of prfill return values or not
*
* This function invokes @prfill on each blkg of @blkcg if pd for the
* policy specified by @pol exists. @prfill is invoked with @sf, the
* policy data and @data and the matching queue lock held. If @show_total
* is %true, the sum of the return values from @prfill is printed with
* "Total" label at the end.
*
* This is to be used to construct print functions for
* cftype->read_seq_string method.
*/
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
u64 (*prfill)(struct seq_file *,
struct blkg_policy_data *, int),
const struct blkcg_policy *pol, int data,
bool show_total)
{
struct blkcg_gq *blkg;
u64 total = 0;
rcu_read_lock();
hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
spin_lock_irq(blkg->q->queue_lock);
if (blkcg_policy_enabled(blkg->q, pol))
total += prfill(sf, blkg->pd[pol->plid], data);
spin_unlock_irq(blkg->q->queue_lock);
}
rcu_read_unlock();
if (show_total)
seq_printf(sf, "Total %llu\n", (unsigned long long)total);
}
EXPORT_SYMBOL_GPL(blkcg_print_blkgs);
/**
* __blkg_prfill_u64 - prfill helper for a single u64 value
* @sf: seq_file to print to
* @pd: policy private data of interest
* @v: value to print
*
* Print @v to @sf for the device assocaited with @pd.
*/
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
{
const char *dname = blkg_dev_name(pd->blkg);
if (!dname)
return 0;
seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v);
return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
/**
* __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
* @sf: seq_file to print to
* @pd: policy private data of interest
* @rwstat: rwstat to print
*
* Print @rwstat to @sf for the device assocaited with @pd.
*/
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
const struct blkg_rwstat *rwstat)
{
static const char *rwstr[] = {
[BLKG_RWSTAT_READ] = "Read",
[BLKG_RWSTAT_WRITE] = "Write",
[BLKG_RWSTAT_SYNC] = "Sync",
[BLKG_RWSTAT_ASYNC] = "Async",
};
const char *dname = blkg_dev_name(pd->blkg);
u64 v;
int i;
if (!dname)
return 0;
for (i = 0; i < BLKG_RWSTAT_NR; i++)
seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
(unsigned long long)atomic64_read(&rwstat->aux_cnt[i]));
v = atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_READ]) +
atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]);
seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
/**
* blkg_prfill_stat - prfill callback for blkg_stat
* @sf: seq_file to print to
* @pd: policy private data of interest
* @off: offset to the blkg_stat in @pd
*
* prfill callback for printing a blkg_stat.
*/
u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off)
{
return __blkg_prfill_u64(sf, pd, blkg_stat_read((void *)pd + off));
}
EXPORT_SYMBOL_GPL(blkg_prfill_stat);
/**
* blkg_prfill_rwstat - prfill callback for blkg_rwstat
* @sf: seq_file to print to
* @pd: policy private data of interest
* @off: offset to the blkg_rwstat in @pd
*
* prfill callback for printing a blkg_rwstat.
*/
u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
int off)
{
struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd + off);
return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
static u64 blkg_prfill_rwstat_field(struct seq_file *sf,
struct blkg_policy_data *pd, int off)
{
struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd->blkg + off);
return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
/**
* blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes
* @sf: seq_file to print to
* @v: unused
*
* To be used as cftype->seq_show to print blkg->stat_bytes.
* cftype->private must be set to the blkcg_policy.
*/
int blkg_print_stat_bytes(struct seq_file *sf, void *v)
{
blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
offsetof(struct blkcg_gq, stat_bytes), true);
return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_bytes);
/**
* blkg_print_stat_bytes - seq_show callback for blkg->stat_ios
* @sf: seq_file to print to
* @v: unused
*
* To be used as cftype->seq_show to print blkg->stat_ios. cftype->private
* must be set to the blkcg_policy.
*/
int blkg_print_stat_ios(struct seq_file *sf, void *v)
{
blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
offsetof(struct blkcg_gq, stat_ios), true);
return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_ios);
static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf,
struct blkg_policy_data *pd,
int off)
{
struct blkg_rwstat rwstat = blkg_rwstat_recursive_sum(pd->blkg,
NULL, off);
return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
/**
* blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes
* @sf: seq_file to print to
* @v: unused
*/
int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v)
{
blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
blkg_prfill_rwstat_field_recursive,
(void *)seq_cft(sf)->private,
offsetof(struct blkcg_gq, stat_bytes), true);
return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive);
/**
* blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios
* @sf: seq_file to print to
* @v: unused
*/
int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v)
{
blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
blkg_prfill_rwstat_field_recursive,
(void *)seq_cft(sf)->private,
offsetof(struct blkcg_gq, stat_ios), true);
return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive);
/**
* blkg_stat_recursive_sum - collect hierarchical blkg_stat
* @blkg: blkg of interest
* @pol: blkcg_policy which contains the blkg_stat
* @off: offset to the blkg_stat in blkg_policy_data or @blkg
*
* Collect the blkg_stat specified by @blkg, @pol and @off and all its
* online descendants and their aux counts. The caller must be holding the
* queue lock for online tests.
*
* If @pol is NULL, blkg_stat is at @off bytes into @blkg; otherwise, it is
* at @off bytes into @blkg's blkg_policy_data of the policy.
*/
u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg,
struct blkcg_policy *pol, int off)
{
struct blkcg_gq *pos_blkg;
struct cgroup_subsys_state *pos_css;
u64 sum = 0;
lockdep_assert_held(blkg->q->queue_lock);
rcu_read_lock();
blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
struct blkg_stat *stat;
if (!pos_blkg->online)
continue;
if (pol)
stat = (void *)blkg_to_pd(pos_blkg, pol) + off;
else
stat = (void *)blkg + off;
sum += blkg_stat_read(stat) + atomic64_read(&stat->aux_cnt);
}
rcu_read_unlock();
return sum;
}
EXPORT_SYMBOL_GPL(blkg_stat_recursive_sum);
/**
* blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
* @blkg: blkg of interest
* @pol: blkcg_policy which contains the blkg_rwstat
* @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
*
* Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
* online descendants and their aux counts. The caller must be holding the
* queue lock for online tests.
*
* If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
* is at @off bytes into @blkg's blkg_policy_data of the policy.
*/
struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg,
struct blkcg_policy *pol, int off)
{
struct blkcg_gq *pos_blkg;
struct cgroup_subsys_state *pos_css;
struct blkg_rwstat sum = { };
int i;
lockdep_assert_held(blkg->q->queue_lock);
rcu_read_lock();
blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
struct blkg_rwstat *rwstat;
if (!pos_blkg->online)
continue;
if (pol)
rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
else
rwstat = (void *)pos_blkg + off;
for (i = 0; i < BLKG_RWSTAT_NR; i++)
atomic64_add(atomic64_read(&rwstat->aux_cnt[i]) +
percpu_counter_sum_positive(&rwstat->cpu_cnt[i]),
&sum.aux_cnt[i]);
}
rcu_read_unlock();
return sum;
}
EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
/**
* blkg_conf_prep - parse and prepare for per-blkg config update
* @blkcg: target block cgroup
* @pol: target policy
* @input: input string
* @ctx: blkg_conf_ctx to be filled
*
* Parse per-blkg config update from @input and initialize @ctx with the
* result. @ctx->blkg points to the blkg to be updated and @ctx->body the
* part of @input following MAJ:MIN. This function returns with RCU read
* lock and queue lock held and must be paired with blkg_conf_finish().
*/
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
char *input, struct blkg_conf_ctx *ctx)
__acquires(rcu) __acquires(disk->queue->queue_lock)
{
struct gendisk *disk;
struct blkcg_gq *blkg;
unsigned int major, minor;
int key_len, part, ret;
char *body;
if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
return -EINVAL;
body = input + key_len;
if (!isspace(*body))
return -EINVAL;
body = skip_spaces(body);
disk = get_gendisk(MKDEV(major, minor), &part);
if (!disk)
return -ENODEV;
if (part) {
put_disk(disk);
return -ENODEV;
}
rcu_read_lock();
spin_lock_irq(disk->queue->queue_lock);
if (blkcg_policy_enabled(disk->queue, pol))
blkg = blkg_lookup_create(blkcg, disk->queue);
else
blkg = ERR_PTR(-EOPNOTSUPP);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
rcu_read_unlock();
spin_unlock_irq(disk->queue->queue_lock);
put_disk(disk);
/*
* If queue was bypassing, we should retry. Do so after a
* short msleep(). It isn't strictly necessary but queue
* can be bypassing for some time and it's always nice to
* avoid busy looping.
*/
if (ret == -EBUSY) {
msleep(10);
ret = restart_syscall();
}
return ret;
}
ctx->disk = disk;
ctx->blkg = blkg;
ctx->body = body;
return 0;
}
EXPORT_SYMBOL_GPL(blkg_conf_prep);
/**
* blkg_conf_finish - finish up per-blkg config update
* @ctx: blkg_conf_ctx intiailized by blkg_conf_prep()
*
* Finish up after per-blkg config update. This function must be paired
* with blkg_conf_prep().
*/
void blkg_conf_finish(struct blkg_conf_ctx *ctx)
__releases(ctx->disk->queue->queue_lock) __releases(rcu)
{
spin_unlock_irq(ctx->disk->queue->queue_lock);
rcu_read_unlock();
put_disk(ctx->disk);
}
EXPORT_SYMBOL_GPL(blkg_conf_finish);
static int blkcg_print_stat(struct seq_file *sf, void *v)
{
struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
struct blkcg_gq *blkg;
rcu_read_lock();
hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
const char *dname;
struct blkg_rwstat rwstat;
u64 rbytes, wbytes, rios, wios;
dname = blkg_dev_name(blkg);
if (!dname)
continue;
spin_lock_irq(blkg->q->queue_lock);
rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
offsetof(struct blkcg_gq, stat_bytes));
rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
offsetof(struct blkcg_gq, stat_ios));
rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
spin_unlock_irq(blkg->q->queue_lock);
if (rbytes || wbytes || rios || wios)
seq_printf(sf, "%s rbytes=%llu wbytes=%llu rios=%llu wios=%llu\n",
dname, rbytes, wbytes, rios, wios);
}
rcu_read_unlock();
return 0;
}
struct cftype blkcg_files[] = {
{
.name = "stat",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = blkcg_print_stat,
},
{ } /* terminate */
};
struct cftype blkcg_legacy_files[] = {
{
.name = "reset_stats",
.write_u64 = blkcg_reset_stats,
},
{ } /* terminate */
};
/**
* blkcg_css_offline - cgroup css_offline callback
* @css: css of interest
*
* This function is called when @css is about to go away and responsible
* for shooting down all blkgs associated with @css. blkgs should be
* removed while holding both q and blkcg locks. As blkcg lock is nested
* inside q lock, this function performs reverse double lock dancing.
*
* This is the blkcg counterpart of ioc_release_fn().
*/
static void blkcg_css_offline(struct cgroup_subsys_state *css)
{
struct blkcg *blkcg = css_to_blkcg(css);
spin_lock_irq(&blkcg->lock);
while (!hlist_empty(&blkcg->blkg_list)) {
struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
struct blkcg_gq, blkcg_node);
struct request_queue *q = blkg->q;
if (spin_trylock(q->queue_lock)) {
blkg_destroy(blkg);
spin_unlock(q->queue_lock);
} else {
spin_unlock_irq(&blkcg->lock);
cpu_relax();
spin_lock_irq(&blkcg->lock);
}
}
spin_unlock_irq(&blkcg->lock);
wb_blkcg_offline(blkcg);
}
static void blkcg_css_free(struct cgroup_subsys_state *css)
{
struct blkcg *blkcg = css_to_blkcg(css);
int i;
mutex_lock(&blkcg_pol_mutex);
list_del(&blkcg->all_blkcgs_node);
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (blkcg->cpd[i])
blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);
mutex_unlock(&blkcg_pol_mutex);
kfree(blkcg);
}
static struct cgroup_subsys_state *
blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct blkcg *blkcg;
struct cgroup_subsys_state *ret;
int i;
mutex_lock(&blkcg_pol_mutex);
if (!parent_css) {
blkcg = &blkcg_root;
} else {
blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
if (!blkcg) {
ret = ERR_PTR(-ENOMEM);
goto free_blkcg;
}
}
for (i = 0; i < BLKCG_MAX_POLS ; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
struct blkcg_policy_data *cpd;
/*
* If the policy hasn't been attached yet, wait for it
* to be attached before doing anything else. Otherwise,
* check if the policy requires any specific per-cgroup
* data: if it does, allocate and initialize it.
*/
if (!pol || !pol->cpd_alloc_fn)
continue;
cpd = pol->cpd_alloc_fn(GFP_KERNEL);
if (!cpd) {
ret = ERR_PTR(-ENOMEM);
goto free_pd_blkcg;
}
blkcg->cpd[i] = cpd;
cpd->blkcg = blkcg;
cpd->plid = i;
if (pol->cpd_init_fn)
pol->cpd_init_fn(cpd);
}
spin_lock_init(&blkcg->lock);
INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT);
INIT_HLIST_HEAD(&blkcg->blkg_list);
#ifdef CONFIG_CGROUP_WRITEBACK
INIT_LIST_HEAD(&blkcg->cgwb_list);
#endif
list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
mutex_unlock(&blkcg_pol_mutex);
return &blkcg->css;
free_pd_blkcg:
for (i--; i >= 0; i--)
if (blkcg->cpd[i])
blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);
free_blkcg:
kfree(blkcg);
mutex_unlock(&blkcg_pol_mutex);
return ret;
}
/**
* blkcg_init_queue - initialize blkcg part of request queue
* @q: request_queue to initialize
*
* Called from blk_alloc_queue_node(). Responsible for initializing blkcg
* part of new request_queue @q.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int blkcg_init_queue(struct request_queue *q)
{
struct blkcg_gq *new_blkg, *blkg;
bool preloaded;
int ret;
new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
if (!new_blkg)
return -ENOMEM;
preloaded = !radix_tree_preload(GFP_KERNEL);
/*
* Make sure the root blkg exists and count the existing blkgs. As
* @q is bypassing at this point, blkg_lookup_create() can't be
* used. Open code insertion.
*/
rcu_read_lock();
spin_lock_irq(q->queue_lock);
blkg = blkg_create(&blkcg_root, q, new_blkg);
spin_unlock_irq(q->queue_lock);
rcu_read_unlock();
if (preloaded)
radix_tree_preload_end();
if (IS_ERR(blkg)) {
blkg_free(new_blkg);
return PTR_ERR(blkg);
}
q->root_blkg = blkg;
q->root_rl.blkg = blkg;
ret = blk_throtl_init(q);
if (ret) {
spin_lock_irq(q->queue_lock);
blkg_destroy_all(q);
spin_unlock_irq(q->queue_lock);
}
return ret;
}
/**
* blkcg_drain_queue - drain blkcg part of request_queue
* @q: request_queue to drain
*
* Called from blk_drain_queue(). Responsible for draining blkcg part.
*/
void blkcg_drain_queue(struct request_queue *q)
{
lockdep_assert_held(q->queue_lock);
/*
* @q could be exiting and already have destroyed all blkgs as
* indicated by NULL root_blkg. If so, don't confuse policies.
*/
if (!q->root_blkg)
return;
blk_throtl_drain(q);
}
/**
* blkcg_exit_queue - exit and release blkcg part of request_queue
* @q: request_queue being released
*
* Called from blk_release_queue(). Responsible for exiting blkcg part.
*/
void blkcg_exit_queue(struct request_queue *q)
{
spin_lock_irq(q->queue_lock);
blkg_destroy_all(q);
spin_unlock_irq(q->queue_lock);
blk_throtl_exit(q);
}
/*
* We cannot support shared io contexts, as we have no mean to support
* two tasks with the same ioc in two different groups without major rework
* of the main cic data structures. For now we allow a task to change
* its cgroup only if it's the only owner of its ioc.
*/
static int blkcg_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *task;
struct io_context *ioc;
int ret = 0;
/* task_lock() is needed to avoid races with exit_io_context() */
cgroup_taskset_for_each(task, tset) {
task_lock(task);
ioc = task->io_context;
if (ioc && atomic_read(&ioc->nr_tasks) > 1)
ret = -EINVAL;
task_unlock(task);
if (ret)
break;
}
return ret;
}
static void blkcg_bind(struct cgroup_subsys_state *root_css)
{
int i;
mutex_lock(&blkcg_pol_mutex);
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
struct blkcg *blkcg;
if (!pol || !pol->cpd_bind_fn)
continue;
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node)
if (blkcg->cpd[pol->plid])
pol->cpd_bind_fn(blkcg->cpd[pol->plid]);
}
mutex_unlock(&blkcg_pol_mutex);
}
struct cgroup_subsys io_cgrp_subsys = {
.css_alloc = blkcg_css_alloc,
.css_offline = blkcg_css_offline,
.css_free = blkcg_css_free,
.can_attach = blkcg_can_attach,
.bind = blkcg_bind,
.dfl_cftypes = blkcg_files,
.legacy_cftypes = blkcg_legacy_files,
.legacy_name = "blkio",
#ifdef CONFIG_MEMCG
/*
* This ensures that, if available, memcg is automatically enabled
* together on the default hierarchy so that the owner cgroup can
* be retrieved from writeback pages.
*/
.depends_on = 1 << memory_cgrp_id,
#endif
};
EXPORT_SYMBOL_GPL(io_cgrp_subsys);
/**
* blkcg_activate_policy - activate a blkcg policy on a request_queue
* @q: request_queue of interest
* @pol: blkcg policy to activate
*
* Activate @pol on @q. Requires %GFP_KERNEL context. @q goes through
* bypass mode to populate its blkgs with policy_data for @pol.
*
* Activation happens with @q bypassed, so nobody would be accessing blkgs
* from IO path. Update of each blkg is protected by both queue and blkcg
* locks so that holding either lock and testing blkcg_policy_enabled() is
* always enough for dereferencing policy data.
*
* The caller is responsible for synchronizing [de]activations and policy
* [un]registerations. Returns 0 on success, -errno on failure.
*/
int blkcg_activate_policy(struct request_queue *q,
const struct blkcg_policy *pol)
{
struct blkg_policy_data *pd_prealloc = NULL;
struct blkcg_gq *blkg;
int ret;
if (blkcg_policy_enabled(q, pol))
return 0;
blk_queue_bypass_start(q);
pd_prealloc:
if (!pd_prealloc) {
pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
if (!pd_prealloc) {
ret = -ENOMEM;
goto out_bypass_end;
}
}
spin_lock_irq(q->queue_lock);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
struct blkg_policy_data *pd;
if (blkg->pd[pol->plid])
continue;
pd = pol->pd_alloc_fn(GFP_NOWAIT, q->node);
if (!pd)
swap(pd, pd_prealloc);
if (!pd) {
spin_unlock_irq(q->queue_lock);
goto pd_prealloc;
}
blkg->pd[pol->plid] = pd;
pd->blkg = blkg;
pd->plid = pol->plid;
if (pol->pd_init_fn)
pol->pd_init_fn(pd);
}
__set_bit(pol->plid, q->blkcg_pols);
ret = 0;
spin_unlock_irq(q->queue_lock);
out_bypass_end:
blk_queue_bypass_end(q);
if (pd_prealloc)
pol->pd_free_fn(pd_prealloc);
return ret;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);
/**
* blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue
* @q: request_queue of interest
* @pol: blkcg policy to deactivate
*
* Deactivate @pol on @q. Follows the same synchronization rules as
* blkcg_activate_policy().
*/
void blkcg_deactivate_policy(struct request_queue *q,
const struct blkcg_policy *pol)
{
struct blkcg_gq *blkg;
if (!blkcg_policy_enabled(q, pol))
return;
blk_queue_bypass_start(q);
spin_lock_irq(q->queue_lock);
__clear_bit(pol->plid, q->blkcg_pols);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
/* grab blkcg lock too while removing @pd from @blkg */
spin_lock(&blkg->blkcg->lock);
if (blkg->pd[pol->plid]) {
if (pol->pd_offline_fn)
pol->pd_offline_fn(blkg->pd[pol->plid]);
pol->pd_free_fn(blkg->pd[pol->plid]);
blkg->pd[pol->plid] = NULL;
}
spin_unlock(&blkg->blkcg->lock);
}
spin_unlock_irq(q->queue_lock);
blk_queue_bypass_end(q);
}
EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
/**
* blkcg_policy_register - register a blkcg policy
* @pol: blkcg policy to register
*
* Register @pol with blkcg core. Might sleep and @pol may be modified on
* successful registration. Returns 0 on success and -errno on failure.
*/
int blkcg_policy_register(struct blkcg_policy *pol)
{
struct blkcg *blkcg;
int i, ret;
mutex_lock(&blkcg_pol_register_mutex);
mutex_lock(&blkcg_pol_mutex);
/* find an empty slot */
ret = -ENOSPC;
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (!blkcg_policy[i])
break;
if (i >= BLKCG_MAX_POLS)
goto err_unlock;
/* register @pol */
pol->plid = i;
blkcg_policy[pol->plid] = pol;
/* allocate and install cpd's */
if (pol->cpd_alloc_fn) {
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
struct blkcg_policy_data *cpd;
cpd = pol->cpd_alloc_fn(GFP_KERNEL);
if (!cpd) {
mutex_unlock(&blkcg_pol_mutex);
goto err_free_cpds;
}
blkcg->cpd[pol->plid] = cpd;
cpd->blkcg = blkcg;
cpd->plid = pol->plid;
pol->cpd_init_fn(cpd);
}
}
mutex_unlock(&blkcg_pol_mutex);
/* everything is in place, add intf files for the new policy */
if (pol->dfl_cftypes)
WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys,
pol->dfl_cftypes));
if (pol->legacy_cftypes)
WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys,
pol->legacy_cftypes));
mutex_unlock(&blkcg_pol_register_mutex);
return 0;
err_free_cpds:
if (pol->cpd_alloc_fn) {
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
if (blkcg->cpd[pol->plid]) {
pol->cpd_free_fn(blkcg->cpd[pol->plid]);
blkcg->cpd[pol->plid] = NULL;
}
}
}
blkcg_policy[pol->plid] = NULL;
err_unlock:
mutex_unlock(&blkcg_pol_mutex);
mutex_unlock(&blkcg_pol_register_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(blkcg_policy_register);
/**
* blkcg_policy_unregister - unregister a blkcg policy
* @pol: blkcg policy to unregister
*
* Undo blkcg_policy_register(@pol). Might sleep.
*/
void blkcg_policy_unregister(struct blkcg_policy *pol)
{
struct blkcg *blkcg;
mutex_lock(&blkcg_pol_register_mutex);
if (WARN_ON(blkcg_policy[pol->plid] != pol))
goto out_unlock;
/* kill the intf files first */
if (pol->dfl_cftypes)
cgroup_rm_cftypes(pol->dfl_cftypes);
if (pol->legacy_cftypes)
cgroup_rm_cftypes(pol->legacy_cftypes);
/* remove cpds and unregister */
mutex_lock(&blkcg_pol_mutex);
if (pol->cpd_alloc_fn) {
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
if (blkcg->cpd[pol->plid]) {
pol->cpd_free_fn(blkcg->cpd[pol->plid]);
blkcg->cpd[pol->plid] = NULL;
}
}
}
blkcg_policy[pol->plid] = NULL;
mutex_unlock(&blkcg_pol_mutex);
out_unlock:
mutex_unlock(&blkcg_pol_register_mutex);
}
EXPORT_SYMBOL_GPL(blkcg_policy_unregister);