/*
 * Copyright (C) 1991, 1992 Linus Torvalds
 * Copyright (C) 1994,      Karl Keyte: Added support for disk statistics
 * Elevator latency, (C) 2000  Andrea Arcangeli <andrea@suse.de> SuSE
 * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
 * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au>
 *	-  July2000
 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001
 */

/*
 * This handles all read/write requests to block devices
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/fault-inject.h>
#include <linux/list_sort.h>
#include <linux/delay.h>
#include <linux/ratelimit.h>

#define CREATE_TRACE_POINTS
#include <trace/events/block.h>

#include "blk.h"
#include "blk-cgroup.h"

EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);

DEFINE_IDA(blk_queue_ida);

/*
 * For the allocated request tables
 */
static struct kmem_cache *request_cachep;

/*
 * For queue allocation
 */
struct kmem_cache *blk_requestq_cachep;

/*
 * Controlling structure to kblockd
 */
static struct workqueue_struct *kblockd_workqueue;

static void drive_stat_acct(struct request *rq, int new_io)
{
	struct hd_struct *part;
	int rw = rq_data_dir(rq);
	int cpu;

	if (!blk_do_io_stat(rq))
		return;

	cpu = part_stat_lock();

	if (!new_io) {
		part = rq->part;
		part_stat_inc(cpu, part, merges[rw]);
	} else {
		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
		if (!hd_struct_try_get(part)) {
			/*
			 * The partition is already being removed,
			 * the request will be accounted on the disk only
			 *
			 * We take a reference on disk->part0 although that
			 * partition will never be deleted, so we can treat
			 * it as any other partition.
			 */
			part = &rq->rq_disk->part0;
			hd_struct_get(part);
		}
		part_round_stats(cpu, part);
		part_inc_in_flight(part, rw);
		rq->part = part;
	}

	part_stat_unlock();
}

void blk_queue_congestion_threshold(struct request_queue *q)
{
	int nr;

	nr = q->nr_requests - (q->nr_requests / 8) + 1;
	if (nr > q->nr_requests)
		nr = q->nr_requests;
	q->nr_congestion_on = nr;

	nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
	if (nr < 1)
		nr = 1;
	q->nr_congestion_off = nr;
}

/**
 * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
 * @bdev:	device
 *
 * Locates the passed device's request queue and returns the address of its
 * backing_dev_info
 *
 * Will return NULL if the request queue cannot be located.
 */
struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
	struct backing_dev_info *ret = NULL;
	struct request_queue *q = bdev_get_queue(bdev);

	if (q)
		ret = &q->backing_dev_info;
	return ret;
}
EXPORT_SYMBOL(blk_get_backing_dev_info);

void blk_rq_init(struct request_queue *q, struct request *rq)
{
	memset(rq, 0, sizeof(*rq));

	INIT_LIST_HEAD(&rq->queuelist);
	INIT_LIST_HEAD(&rq->timeout_list);
	rq->cpu = -1;
	rq->q = q;
	rq->__sector = (sector_t) -1;
	INIT_HLIST_NODE(&rq->hash);
	RB_CLEAR_NODE(&rq->rb_node);
	rq->cmd = rq->__cmd;
	rq->cmd_len = BLK_MAX_CDB;
	rq->tag = -1;
	rq->ref_count = 1;
	rq->start_time = jiffies;
	set_start_time_ns(rq);
	rq->part = NULL;
}
EXPORT_SYMBOL(blk_rq_init);

static void req_bio_endio(struct request *rq, struct bio *bio,
			  unsigned int nbytes, int error)
{
	if (error)
		clear_bit(BIO_UPTODATE, &bio->bi_flags);
	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
		error = -EIO;

	if (unlikely(nbytes > bio->bi_size)) {
		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
		       __func__, nbytes, bio->bi_size);
		nbytes = bio->bi_size;
	}

	if (unlikely(rq->cmd_flags & REQ_QUIET))
		set_bit(BIO_QUIET, &bio->bi_flags);

	bio->bi_size -= nbytes;
	bio->bi_sector += (nbytes >> 9);

	if (bio_integrity(bio))
		bio_integrity_advance(bio, nbytes);

	/* don't actually finish bio if it's part of flush sequence */
	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
		bio_endio(bio, error);
}

void blk_dump_rq_flags(struct request *rq, char *msg)
{
	int bit;

	printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
		rq->cmd_flags);

	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
	       (unsigned long long)blk_rq_pos(rq),
	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));

	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
		printk(KERN_INFO "  cdb: ");
		for (bit = 0; bit < BLK_MAX_CDB; bit++)
			printk("%02x ", rq->cmd[bit]);
		printk("\n");
	}
}
EXPORT_SYMBOL(blk_dump_rq_flags);

static void blk_delay_work(struct work_struct *work)
{
	struct request_queue *q;

	q = container_of(work, struct request_queue, delay_work.work);
	spin_lock_irq(q->queue_lock);
	__blk_run_queue(q);
	spin_unlock_irq(q->queue_lock);
}

/**
 * blk_delay_queue - restart queueing after defined interval
 * @q:		The &struct request_queue in question
 * @msecs:	Delay in msecs
 *
 * Description:
 *   Sometimes queueing needs to be postponed for a little while, to allow
 *   resources to come back. This function will make sure that queueing is
 *   restarted around the specified time. Queue lock must be held.
 */
void blk_delay_queue(struct request_queue *q, unsigned long msecs)
{
	if (likely(!blk_queue_dead(q)))
		queue_delayed_work(kblockd_workqueue, &q->delay_work,
				   msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_delay_queue);

/**
 * blk_start_queue - restart a previously stopped queue
 * @q:    The &struct request_queue in question