/*
* 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>
*/
#include <linux/ioprio.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/genhd.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include "blk-cgroup.h"
#include "blk.h"
#define MAX_KEY_LEN 100
static DEFINE_MUTEX(blkcg_pol_mutex);
struct blkcg blkcg_root = { .cfq_weight = 2 * CFQ_WEIGHT_DEFAULT };
EXPORT_SYMBOL_GPL(blkcg_root);
static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
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++) {
struct blkcg_policy *pol = blkcg_policy[i];
struct blkg_policy_data *pd = blkg->pd[i];
if (!pd)
continue;
if (pol && pol->pd_exit_fn)
pol->pd_exit_fn(blkg);
kfree(pd);
}
blk_exit_rl(&blkg->rl);
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;
blkg->q = q;
INIT_LIST_HEAD(&blkg->q_node);
blkg->blkcg = blkcg;
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 = kzalloc_node(pol->pd_size, gfp_mask, q->node);
if (!pd)
goto err_free;
blkg->pd[i] = pd;
pd->blkg = blkg;
/* invoke per-policy init */
if (blkcg_policy_enabled(blkg->q, pol))
pol->pd_init_fn(blkg);
}
return blkg;
err_free:
blkg_free(blkg);
return NULL;
}
static struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
struct request_queue *q)
{
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 we
* may not be holding queue_lock and thus are not sure whether
* @blkg from blkg_tree has already been removed or not, so we
* can't update hint to the lookup result. Leave it to the caller.
*/
blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
if (blkg && blkg->q == q)
return 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);
}
EXPORT_SYMBOL_GPL(blkg_lookup);
/*
* 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.
*/
static struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
struct request_queue *q,
struct blkcg_gq *new_blkg)
{
struct blkcg_gq *blkg;
int ret;
WARN_ON_ONCE(!rcu_read_lock_held());
lockdep_assert_held(q->queue_lock);
/* lookup and update hint on success, see __blkg_lookup() for details */
blkg = __blkg_lookup(blkcg,