#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;
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;
for (i = 0; i < BLKCG_MAX_POLS; i++)
- kfree(blkg->pd[i]);
+ if (blkg->pd[i])
+ blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
- blk_exit_rl(&blkg->rl);
+ if (blkg->blkcg != &blkcg_root)
+ blk_exit_rl(&blkg->rl);
kfree(blkg);
}
continue;
/* alloc per-policy data and attach it to blkg */
- pd = kzalloc_node(pol->pd_size, gfp_mask, q->node);
+ pd = pol->pd_alloc_fn(gfp_mask, q->node);
if (!pd)
goto err_free;
return NULL;
}
-/**
- * __blkg_lookup - internal version of blkg_lookup()
- * @blkcg: blkcg of interest
- * @q: request_queue of interest
- * @update_hint: whether to update lookup hint with the result or not
- *
- * This is internal version and shouldn't be used by policy
- * implementations. Looks up blkgs for the @blkcg - @q pair regardless of
- * @q's bypass state. If @update_hint is %true, the caller should be
- * holding @q->queue_lock and lookup hint is updated on success.
- */
-struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q,
- bool update_hint)
+struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
+ struct request_queue *q, bool update_hint)
{
struct blkcg_gq *blkg;
- blkg = rcu_dereference(blkcg->blkg_hint);
- if (blkg && blkg->q == q)
- return 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
return NULL;
}
-
-/**
- * blkg_lookup - lookup blkg for the specified blkcg - q pair
- * @blkcg: blkcg of interest
- * @q: request_queue of interest
- *
- * Lookup blkg for the @blkcg - @q pair. This function should be called
- * under RCU read lock and is guaranteed to return %NULL if @q is bypassing
- * - see blk_queue_bypass_start() for details.
- */
-struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q)
-{
- WARN_ON_ONCE(!rcu_read_lock_held());
-
- if (unlikely(blk_queue_bypass(q)))
- return NULL;
- return __blkg_lookup(blkcg, q, false);
-}
-EXPORT_SYMBOL_GPL(blkg_lookup);
+EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);
/*
* If @new_blkg is %NULL, this function tries to allocate a new one as
- * necessary using %GFP_ATOMIC. @new_blkg is always consumed on return.
+ * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return.
*/
static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
struct request_queue *q,
}
wb_congested = wb_congested_get_create(&q->backing_dev_info,
- blkcg->css.id, GFP_ATOMIC);
+ 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_ATOMIC);
+ new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT);
if (unlikely(!new_blkg)) {
ret = -ENOMEM;
goto err_put_congested;
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_init_fn)
- pol->pd_init_fn(blkg);
+ pol->pd_init_fn(blkg->pd[i]);
}
/* insert */
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_online_fn)
- pol->pd_online_fn(blkg);
+ pol->pd_online_fn(blkg->pd[i]);
}
}
blkg->online = true;
return blkg;
}
}
-EXPORT_SYMBOL_GPL(blkg_lookup_create);
static void blkg_destroy(struct blkcg_gq *blkg)
{
struct blkcg_policy *pol = blkcg_policy[i];
if (blkg->pd[i] && pol->pd_offline_fn)
- pol->pd_offline_fn(blkg);
+ pol->pd_offline_fn(blkg->pd[i]);
}
blkg->online = false;
void __blkg_release_rcu(struct rcu_head *rcu_head)
{
struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head);
- int i;
-
- /* tell policies that this one is being freed */
- for (i = 0; i < BLKCG_MAX_POLS; i++) {
- struct blkcg_policy *pol = blkcg_policy[i];
-
- if (blkg->pd[i] && pol->pd_exit_fn)
- pol->pd_exit_fn(blkg);
- }
/* release the blkcg and parent blkg refs this blkg has been holding */
css_put(&blkg->blkcg->css);
struct blkcg_gq *blkg;
int i;
- /*
- * XXX: We invoke cgroup_add/rm_cftypes() under blkcg_pol_mutex
- * which ends up putting cgroup's internal cgroup_tree_mutex under
- * it; however, cgroup_tree_mutex is nested above cgroup file
- * active protection and grabbing blkcg_pol_mutex from a cgroup
- * file operation creates a possible circular dependency. cgroup
- * internal locking is planned to go through further simplification
- * and this issue should go away soon. For now, let's trylock
- * blkcg_pol_mutex and restart the write on failure.
- *
- * http://lkml.kernel.org/g/5363C04B.4010400@oracle.com
- */
- if (!mutex_trylock(&blkcg_pol_mutex))
- return restart_syscall();
+ mutex_lock(&blkcg_pol_mutex);
spin_lock_irq(&blkcg->lock);
/*
for (i = 0; i < BLKCG_MAX_POLS; i++) {
struct blkcg_policy *pol = blkcg_policy[i];
- if (blkcg_policy_enabled(blkg->q, pol) &&
- pol->pd_reset_stats_fn)
- pol->pd_reset_stats_fn(blkg);
+ if (blkg->pd[i] && pol->pd_reset_stats_fn)
+ pol->pd_reset_stats_fn(blkg->pd[i]);
}
}
for (i = 0; i < BLKG_RWSTAT_NR; i++)
seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
- (unsigned long long)rwstat->cnt[i]);
+ (unsigned long long)atomic64_read(&rwstat->aux_cnt[i]));
- v = rwstat->cnt[BLKG_RWSTAT_READ] + rwstat->cnt[BLKG_RWSTAT_WRITE];
+ 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;
}
/**
* blkg_stat_recursive_sum - collect hierarchical blkg_stat
- * @pd: policy private data of interest
- * @off: offset to the blkg_stat in @pd
+ * @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.
*
- * Collect the blkg_stat specified by @off from @pd and all its online
- * descendants and return the sum. 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 blkg_policy_data *pd, int off)
+u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg,
+ struct blkcg_policy *pol, int off)
{
- struct blkcg_policy *pol = blkcg_policy[pd->plid];
struct blkcg_gq *pos_blkg;
struct cgroup_subsys_state *pos_css;
u64 sum = 0;
- lockdep_assert_held(pd->blkg->q->queue_lock);
+ lockdep_assert_held(blkg->q->queue_lock);
rcu_read_lock();
- blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
- struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
- struct blkg_stat *stat = (void *)pos_pd + off;
+ blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
+ struct blkg_stat *stat;
+
+ if (!pos_blkg->online)
+ continue;
- if (pos_blkg->online)
- sum += blkg_stat_read(stat);
+ 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();
/**
* blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
- * @pd: policy private data of interest
- * @off: offset to the blkg_stat in @pd
+ * @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.
*
- * Collect the blkg_rwstat specified by @off from @pd and all its online
- * descendants and return the sum. 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 blkg_policy_data *pd,
- int off)
+struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg,
+ struct blkcg_policy *pol, int off)
{
- struct blkcg_policy *pol = blkcg_policy[pd->plid];
struct blkcg_gq *pos_blkg;
struct cgroup_subsys_state *pos_css;
struct blkg_rwstat sum = { };
int i;
- lockdep_assert_held(pd->blkg->q->queue_lock);
+ lockdep_assert_held(blkg->q->queue_lock);
rcu_read_lock();
- blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
- struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
- struct blkg_rwstat *rwstat = (void *)pos_pd + off;
- struct blkg_rwstat tmp;
+ blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
+ struct blkg_rwstat *rwstat, tmp;
if (!pos_blkg->online)
continue;
+ if (pol)
+ rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
+ else
+ rwstat = (void *)pos_blkg + off;
+
tmp = blkg_rwstat_read(rwstat);
for (i = 0; i < BLKG_RWSTAT_NR; i++)
- sum.cnt[i] += tmp.cnt[i];
+ atomic64_add(atomic64_read(&tmp.aux_cnt[i]) +
+ atomic64_read(&rwstat->aux_cnt[i]),
+ &sum.aux_cnt[i]);
}
rcu_read_unlock();
return -EINVAL;
disk = get_gendisk(MKDEV(major, minor), &part);
- if (!disk || part)
+ if (!disk)
return -EINVAL;
+ if (part) {
+ put_disk(disk);
+ return -EINVAL;
+ }
rcu_read_lock();
spin_lock_irq(disk->queue->queue_lock);
static void blkcg_css_free(struct cgroup_subsys_state *css)
{
struct blkcg *blkcg = css_to_blkcg(css);
+ int i;
- if (blkcg != &blkcg_root)
- kfree(blkcg);
+ 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 *
struct cgroup_subsys_state *ret;
int i;
+ mutex_lock(&blkcg_pol_mutex);
+
if (!parent_css) {
blkcg = &blkcg_root;
- goto done;
- }
-
- blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
- if (!blkcg) {
- ret = ERR_PTR(-ENOMEM);
- goto free_blkcg;
+ } else {
+ blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
+ if (!blkcg) {
+ ret = ERR_PTR(-ENOMEM);
+ goto free_blkcg;
+ }
}
for (i = 0; i < BLKCG_MAX_POLS ; i++) {
* check if the policy requires any specific per-cgroup
* data: if it does, allocate and initialize it.
*/
- if (!pol || !pol->cpd_size)
+ if (!pol || !pol->cpd_alloc_fn)
continue;
- BUG_ON(blkcg->pd[i]);
- cpd = kzalloc(pol->cpd_size, GFP_KERNEL);
+ cpd = pol->cpd_alloc_fn(GFP_KERNEL);
if (!cpd) {
ret = ERR_PTR(-ENOMEM);
goto free_pd_blkcg;
}
- blkcg->pd[i] = cpd;
+ blkcg->cpd[i] = cpd;
+ cpd->blkcg = blkcg;
cpd->plid = i;
- pol->cpd_init_fn(blkcg);
+ if (pol->cpd_init_fn)
+ pol->cpd_init_fn(cpd);
}
-done:
spin_lock_init(&blkcg->lock);
- INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC);
+ 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--)
- kfree(blkcg->pd[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;
}
radix_tree_preload_end();
if (IS_ERR(blkg)) {
- kfree(new_blkg);
+ blkg_free(new_blkg);
return PTR_ERR(blkg);
}
int blkcg_activate_policy(struct request_queue *q,
const struct blkcg_policy *pol)
{
- LIST_HEAD(pds);
- LIST_HEAD(cpds);
+ struct blkg_policy_data *pd_prealloc = NULL;
struct blkcg_gq *blkg;
- struct blkg_policy_data *pd, *nd;
- struct blkcg_policy_data *cpd, *cnd;
- int cnt = 0, ret;
+ int ret;
if (blkcg_policy_enabled(q, pol))
return 0;
- /* count and allocate policy_data for all existing blkgs */
blk_queue_bypass_start(q);
- spin_lock_irq(q->queue_lock);
- list_for_each_entry(blkg, &q->blkg_list, q_node)
- cnt++;
- spin_unlock_irq(q->queue_lock);
-
- /*
- * Allocate per-blkg and per-blkcg policy data
- * for all existing blkgs.
- */
- while (cnt--) {
- pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
- if (!pd) {
- ret = -ENOMEM;
- goto out_free;
- }
- list_add_tail(&pd->alloc_node, &pds);
-
- if (!pol->cpd_size)
- continue;
- cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node);
- if (!cpd) {
+pd_prealloc:
+ if (!pd_prealloc) {
+ pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
+ if (!pd_prealloc) {
ret = -ENOMEM;
- goto out_free;
+ goto out_bypass_end;
}
- list_add_tail(&cpd->alloc_node, &cpds);
}
- /*
- * Install the allocated pds and cpds. With @q bypassing, no new blkg
- * should have been created while the queue lock was dropped.
- */
spin_lock_irq(q->queue_lock);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
- if (WARN_ON(list_empty(&pds)) ||
- WARN_ON(pol->cpd_size && list_empty(&cpds))) {
- /* umm... this shouldn't happen, just abort */
- ret = -ENOMEM;
- goto out_unlock;
- }
- cpd = list_first_entry(&cpds, struct blkcg_policy_data,
- alloc_node);
- list_del_init(&cpd->alloc_node);
- pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node);
- list_del_init(&pd->alloc_node);
+ struct blkg_policy_data *pd;
- /* grab blkcg lock too while installing @pd on @blkg */
- spin_lock(&blkg->blkcg->lock);
+ if (blkg->pd[pol->plid])
+ continue;
- if (!pol->cpd_size)
- goto no_cpd;
- if (!blkg->blkcg->pd[pol->plid]) {
- /* Per-policy per-blkcg data */
- blkg->blkcg->pd[pol->plid] = cpd;
- cpd->plid = pol->plid;
- pol->cpd_init_fn(blkg->blkcg);
- } else { /* must free it as it has already been extracted */
- kfree(cpd);
+ 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;
}
-no_cpd:
+
blkg->pd[pol->plid] = pd;
pd->blkg = blkg;
pd->plid = pol->plid;
- pol->pd_init_fn(blkg);
-
- spin_unlock(&blkg->blkcg->lock);
+ if (pol->pd_init_fn)
+ pol->pd_init_fn(pd);
}
__set_bit(pol->plid, q->blkcg_pols);
ret = 0;
-out_unlock:
+
spin_unlock_irq(q->queue_lock);
-out_free:
+out_bypass_end:
blk_queue_bypass_end(q);
- list_for_each_entry_safe(pd, nd, &pds, alloc_node)
- kfree(pd);
- list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node)
- kfree(cpd);
+ if (pd_prealloc)
+ pol->pd_free_fn(pd_prealloc);
return ret;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);
/* grab blkcg lock too while removing @pd from @blkg */
spin_lock(&blkg->blkcg->lock);
- if (pol->pd_offline_fn)
- pol->pd_offline_fn(blkg);
- if (pol->pd_exit_fn)
- pol->pd_exit_fn(blkg);
-
- kfree(blkg->pd[pol->plid]);
- blkg->pd[pol->plid] = NULL;
- kfree(blkg->blkcg->pd[pol->plid]);
- blkg->blkcg->pd[pol->plid] = NULL;
+ 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);
}
*/
int blkcg_policy_register(struct blkcg_policy *pol)
{
+ struct blkcg *blkcg;
int i, ret;
- if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data)))
- return -EINVAL;
-
+ mutex_lock(&blkcg_pol_register_mutex);
mutex_lock(&blkcg_pol_mutex);
/* find an empty slot */
if (!blkcg_policy[i])
break;
if (i >= BLKCG_MAX_POLS)
- goto out_unlock;
+ goto err_unlock;
- /* register and update blkgs */
+ /* register @pol */
pol->plid = i;
- blkcg_policy[i] = pol;
+ 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->cftypes)
WARN_ON(cgroup_add_legacy_cftypes(&blkio_cgrp_subsys,
pol->cftypes));
- ret = 0;
-out_unlock:
+ 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);
*/
void blkcg_policy_unregister(struct blkcg_policy *pol)
{
- mutex_lock(&blkcg_pol_mutex);
+ struct blkcg *blkcg;
+
+ mutex_lock(&blkcg_pol_register_mutex);
if (WARN_ON(blkcg_policy[pol->plid] != pol))
goto out_unlock;
if (pol->cftypes)
cgroup_rm_cftypes(pol->cftypes);
- /* unregister and update blkgs */
+ /* 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;
-out_unlock:
+
mutex_unlock(&blkcg_pol_mutex);
+out_unlock:
+ mutex_unlock(&blkcg_pol_register_mutex);
}
EXPORT_SYMBOL_GPL(blkcg_policy_unregister);