path: root/block/blk-cgroup.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>
 */
#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,
			    .cfq_leaf_weight = 2 * CFQ_WEIGHT_DEFAULT, };
EXPORT_SYMBOL_GPL(blkcg_root);

static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];

static struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
				      struct request_queue *q, bool update_hint);

/**
 * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
 * @d_blkg: loop cursor pointing to the current descendant
 * @pos_cgrp: used for iteration
 * @p_blkg: target blkg to walk descendants of
 *
 * Walk @c_blkg through the descendants of @p_blkg.  Must be used with RCU
 * read locked.  If called under either blkcg or queue lock, the iteration
 * is guaranteed to include all and only online blkgs.  The caller may
 * update @pos_cgrp by calling cgroup_rightmost_descendant() to skip
 * subtree.
 */
#define blkg_for_each_descendant_pre(d_blkg, pos_cgrp, p_blkg)		\
	cgroup_for_each_descendant_pre((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \
		if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \
					      (p_blkg)->q, false)))

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