/*
 * 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, q);
	if (blkg) {
		rcu_assign_pointer(blkcg->blkg_hint, blkg);
		goto out_free;
	}

	/* blkg holds a reference to blkcg */
	if (!css_tryget(&blkcg->css)) {
		blkg = ERR_PTR(-EINVAL);
		goto out_free;
	}

	/* allocate */
	if (!new_blkg) {
		new_blkg = blkg_alloc(blkcg, q, GFP_ATOMIC);
		if (unlikely(!new_blkg)) {
			blkg = ERR_PTR(-ENOMEM);
			goto out_put;
		}
	}
	blkg = new_blkg;

	/* 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);
	}
	spin_unlock(&blkcg->lock);

	if (!ret)
		return blkg;

	blkg = ERR_PTR(ret);
out_put:
	css_put(&blkcg->css);
out_free:
	blkg_free(new_blkg);
	return blkg;
}

struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
				    struct request_queue *q)
{
	/*
	 * 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) ? -EINVAL : -EBUSY);
	return __blkg_lookup_create(blkcg, q, NULL);
}
EXPORT_SYMBOL_GPL(blkg_lookup_create);

static void blkg_destroy(struct blkcg_gq *blkg)
{
	struct blkcg *blkcg = blkg->blkcg;

	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));

	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_dereference_raw(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);
	}

	/*
	 * root blkg is destroyed.  Just clear the pointer since
	 * root_rl does not take reference on root blkg.
	 */
	q->root_blkg = NULL;
	q->root_rl.blkg = NULL;
}

static void blkg_rcu_free(struct rcu_head *rcu_head)
{
	blkg_free(container_of(rcu_head, struct blkcg_gq, rcu_head));
}

void __blkg_release(struct blkcg_gq *blkg)
{
	/* release the extra blkcg reference this blkg has been holding */
	css_put(&blkg->blkcg->css);

	/*
	 * A group is freed in rcu manner. 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 acess to only
	 * values local to groups like group stats and group rate limits
	 */
	call_rcu(&blkg->rcu_head, blkg_rcu_free);
}
EXPORT_SYMBOL_GPL(__blkg_release);

/*
 * 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 *cgroup, struct cftype *cftype,
			     u64 val)
{
	struct blkcg *blkcg = cgroup_to_blkcg(cgroup);
	struct blkcg_gq *blkg;
	struct hlist_node *n;
	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, n, &blkcg->blkg_list, blkcg_node) {
		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);
		}
	}

	spin_unlock_irq(&blkcg->lock);
	mutex_unlock(&blkcg_pol_mutex);
	return 0;
}

static 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;
}

/**
 * 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.  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;
	struct hlist_node *n;
	u64 total = 0;

	spin_lock_irq(&blkcg->lock);
	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node)
		if (blkcg_policy_enabled(blkg->q, pol))
			total += prfill(sf, blkg->pd[pol->plid], data);
	spin_unlock_irq(&blkcg->lock);

	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)rwstat->cnt[i]);

	v = rwstat->cnt[BLKG_RWSTAT_READ] + rwstat->cnt[BLKG_RWSTAT_WRITE];
	seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
	return v;
}

/**
 * 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);