/*
 * 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
 *
 * Description:
 *   blk_start_queue() will clear the stop flag on the queue, and call
 *   the request_fn for the queue if it was in a stopped state when
 *   entered. Also see blk_stop_queue(). Queue lock must be held.
 **/
void blk_start_queue(struct request_queue *q)
{
	WARN_ON(!irqs_disabled());

	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
	__blk_run_queue(q);
}
EXPORT_SYMBOL(blk_start_queue);

/**
 * blk_stop_queue - stop a queue
 * @q:    The &struct request_queue in question
 *
 * Description:
 *   The Linux block layer assumes that a block driver will consume all
 *   entries on the request queue when the request_fn strategy is called.
 *   Often this will not happen, because of hardware limitations (queue
 *   depth settings). If a device driver gets a 'queue full' response,
 *   or if it simply chooses not to queue more I/O at one point, it can
 *   call this function to prevent the request_fn from being called until
 *   the driver has signalled it's ready to go again. This happens by calling
 *   blk_start_queue() to restart queue operations. Queue lock must be held.
 **/
void blk_stop_queue(struct request_queue *q)
{
	cancel_delayed_work(&q->delay_work);
	queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
EXPORT_SYMBOL(blk_stop_queue);

/**
 * blk_sync_queue - cancel any pending callbacks on a queue
 * @q: the queue
 *
 * Description:
 *     The block layer may perform asynchronous callback activity
 *     on a queue, such as calling the unplug function after a timeout.
 *     A block device may call blk_sync_queue to ensure that any
 *     such activity is cancelled, thus allowing it to release resources
 *     that the callbacks might use. The caller must already have made sure
 *     that its ->make_request_fn will not re-add plugging prior to calling
 *     this function.
 *
 *     This function does not cancel any asynchronous activity arising
 *     out of elevator or throttling code. That would require elevaotor_exit()
 *     and blkcg_exit_queue() to be called with queue lock initialized.
 *
 */
void blk_sync_queue(struct request_queue *q)
{
	del_timer_sync(&q->timeout);
	cancel_delayed_work_sync(&q->delay_work);
}
EXPORT_SYMBOL(blk_sync_queue);

/**
 * __blk_run_queue_uncond - run a queue whether or not it has been stopped
 * @q:	The queue to run
 *
 * Description:
 *    Invoke request handling on a queue if there are any pending requests.
 *    May be used to restart request handling after a request has completed.
 *    This variant runs the queue whether or not the queue has been
 *    stopped. Must be called with the queue lock held and interrupts
 *    disabled. See also @blk_run_queue.
 */
inline void __blk_run_queue_uncond(struct request_queue *q)
{
	if (unlikely(blk_queue_dead(q)))
		return;

	/*
	 * Some request_fn implementations, e.g. scsi_request_fn(), unlock
	 * the queue lock internally. As a result multiple threads may be
	 * running such a request function concurrently. Keep track of the
	 * number of active request_fn invocations such that blk_drain_queue()
	 * can wait until all these request_fn calls have finished.
	 */
	q->request_fn_active++;
	q->request_fn(q);
	q->request_fn_active--;
}

/**
 * __blk_run_queue - run a single device queue
 * @q:	The queue to run
 *
 * Description:
 *    See @blk_run_queue. This variant must be called with the queue lock
 *    held and interrupts disabled.
 */
void __blk_run_queue(struct request_queue *q)
{
	if (unlikely(blk_queue_stopped(q)))
		return;

	__blk_run_queue_uncond(q);
}
EXPORT_SYMBOL(__blk_run_queue);

/**
 * blk_run_queue_async - run a single device queue in workqueue context
 * @q:	The queue to run
 *
 * Description:
 *    Tells kblockd to perform the equivalent of @blk_run_queue on behalf
 *    of us. The caller must hold the queue lock.
 */
void blk_run_queue_async(struct request_queue *q)
{
	if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q)))
		mod_delayed_work(kblockd_workqueue, &q->delay_work, 0);
}
EXPORT_SYMBOL(blk_run_queue_async);

/**
 * blk_run_queue - run a single device queue
 * @q: The queue to run
 *
 * Description:
 *    Invoke request handling on this queue, if it has pending work to do.
 *    May be used to restart queueing when a request has completed.
 */
void blk_run_queue(struct request_queue *q)
{
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	__blk_run_queue(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);

void blk_put_queue(struct request_queue *q)
{
	kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);

/**
 * __blk_drain_queue - drain requests from request_queue
 * @q: queue to drain
 * @drain_all: whether to drain all requests or only the ones w/ ELVPRIV
 *
 * Drain requests from @q.  If @drain_all is set, all requests are drained.
 * If not, only ELVPRIV requests are drained.  The caller is responsible
 * for ensuring that no new requests which need to be drained are queued.
 */
static void __blk_drain_queue(struct request_queue *q, bool drain_all)
	__releases(q->queue_lock)
	__acquires(q->queue_lock)
{
	int i;

	lockdep_assert_held(q->queue_lock);

	while (true) {
		bool drain = false;

		/*
		 * The caller might be trying to drain @q before its
		 * elevator is initialized.
		 */
		if (q->elevator)
			elv_drain_elevator(q);

		blkcg_drain_queue(q);

		/*
		 * This function might be called on a queue which failed
		 * driver init after queue creation or is not yet fully
		 * active yet.  Some drivers (e.g. fd and loop) get unhappy
		 * in such cases.  Kick queue iff dispatch queue has
		 * something on it and @q has request_fn set.
		 */
		if (!list_empty(&q->queue_head) && q->request_fn)
			__blk_run_queue(q);

		drain |= q->nr_rqs_elvpriv;
		drain |= q->request_fn_active;

		/*
		 * Unfortunately, requests are queued at and tracked from
		 * multiple places and there's no single counter which can
		 * be drained.  Check all the queues and counters.
		 */
		if (drain_all) {
			drain |= !list_empty(&q->queue_head);
			for (i = 0; i < 2; i++) {
				drain |= q->nr_rqs[i];
				drain |= q->in_flight[i];
				drain |= !list_empty(&q->flush_queue[i]);
			}
		}

		if (!drain)
			break;

		spin_unlock_irq(q->queue_lock);

		msleep(10);

		spin_lock_irq(q->queue_lock);
	}

	/*
	 * With queue marked dead, any woken up waiter will fail the
	 * allocation path, so the wakeup chaining is lost and we're
	 * left with hung waiters. We need to wake up those waiters.
	 */
	if (q->request_fn) {
		struct request_list *rl;

		blk_queue_for_each_rl(rl, q)
			for (i = 0; i < ARRAY_SIZE(rl->wait); i++)
				wake_up_all(&rl->wait[i]);
	}
}

/**
 * blk_queue_bypass_start - enter queue bypass mode
 * @q: queue of interest
 *
 * In bypass mode, only the dispatch FIFO queue of @q is used.  This
 * function makes @q enter bypass mode and drains all requests which were
 * throttled or issued before.  On return, it's guaranteed that no request
 * is being throttled or has ELVPRIV set and blk_queue_bypass() %true
 * inside queue or RCU read lock.
 */
void blk_queue_bypass_start(struct request_queue *q)
{
	bool drain;

	spin_lock_irq(q->queue_lock);
	drain = !q->bypass_depth++;
	queue_flag_set(QUEUE_FLAG_BYPASS, q);
	spin_unlock_irq(q->queue_lock);

	if (drain) {
		spin_lock_irq(q->queue_lock);
		__blk_drain_queue(q, false);
		spin_unlock_irq(q->queue_lock);

		/* ensure blk_queue_bypass() is %true inside RCU read lock */
		synchronize_rcu();
	}
}
EXPORT_SYMBOL_GPL(blk_queue_bypass_start);

/**
 * blk_queue_bypass_end - leave queue bypass mode
 * @q: queue of interest
 *
 * Leave bypass mode and restore the normal queueing behavior.
 */
void blk_queue_bypass_end(struct request_queue *q)
{
	spin_lock_irq(q->queue_lock);
	if (!--q->bypass_depth)
		queue_flag_clear(QUEUE_FLAG_BYPASS, q);
	WARN_ON_ONCE(q->bypass_depth < 0);
	spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL_GPL(blk_queue_bypass_end);

/**
 * blk_cleanup_queue - shutdown a request queue
 * @q: request queue to shutdown
 *
 * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and
 * put it.  All future requests will be failed immediately with -ENODEV.
 */
void blk_cleanup_queue(struct request_queue *q)
{
	spinlock_t *lock = q->queue_lock;

	/* mark @q DYING, no new request or merges will be allowed afterwards */
	mutex_lock(&q->sysfs_lock);
	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
	spin_lock_irq(lock);

	/*
	 * A dying queue is permanently in bypass mode till released.  Note
	 * that, unlike blk_queue_bypass_start(), we aren't performing
	 * synchronize_rcu() after entering bypass mode to avoid the delay
	 * as some drivers create and destroy a lot of queues while
	 * probing.  This is still safe because blk_release_queue() will be
	 * called only after the queue refcnt drops to zero and nothing,
	 * RCU or not, would be traversing the queue by then.
	 */
	q->bypass_depth++;
	queue_flag_set(QUEUE_FLAG_BYPASS, q);

	queue_flag_set(QUEUE_FLAG_NOMERGES, q);
	queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
	queue_flag_set(QUEUE_FLAG_DYING, q);
	spin_unlock_irq(lock);
	mutex_unlock(&q->sysfs_lock);

	/*
	 * Drain all requests queued before DYING marking. Set DEAD flag to
	 * prevent that q->request_fn() gets invoked after draining finished.
	 */
	spin_lock_irq(lock);
	__blk_drain_queue(q, true);
	queue_flag_set(QUEUE_FLAG_DEAD, q);
	spin_unlock_irq(lock);

	/* @q won't process any more request, flush async actions */
	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
	blk_sync_queue(q);

	spin_lock_irq(lock);
	if (q->queue_lock != &q->__queue_lock)
		q->queue_lock = &q->__queue_lock;
	spin_unlock_irq(lock);

	/* @q is and will stay empty, shutdown and put */
	blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);

int blk_init_rl(struct request_list *rl, struct request_queue *q,
		gfp_t gfp_mask)
{
	if (unlikely(rl->rq_pool))
		return 0;

	rl->q = q;
	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);

	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
					  mempool_free_slab, request_cachep,
					  gfp_mask, q->node);
	if (!rl->rq_pool)
		return -ENOMEM;

	return 0;
}

void blk_exit_rl(struct request_list *rl)
{
	if (rl->rq_pool)
		mempool_destroy(rl->rq_pool);
}

struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
	return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE);
}
EXPORT_SYMBOL(blk_alloc_queue);

struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
	struct request_queue *q;
	int err;

	q = kmem_cache_alloc_node(blk_requestq_cachep,
				gfp_mask | __GFP_ZERO, node_id);
	if (!q)
		return NULL;

	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
	if (q->id < 0)
		goto fail_q;

	q->backing_dev_info.ra_pages =
			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
	q->backing_dev_info.state = 0;
	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
	q->backing_dev_info.name = "block";
	q->node = node_id;

	err = bdi_init(&q->backing_dev_info);
	if (err)
		goto fail_id;

	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
		    laptop_mode_timer_fn, (unsigned long) q);
	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
	INIT_LIST_HEAD(&q->queue_head);
	INIT_LIST_HEAD(&q->timeout_list);
	INIT_LIST_HEAD(&q->icq_list);
#ifdef CONFIG_BLK_CGROUP
	INIT_LIST_HEAD(&q->blkg_list);
#endif
	INIT_LIST_HEAD(&q->flush_queue[0]);
	INIT_LIST_HEAD(&q->flush_queue[1]);
	INIT_LIST_HEAD(&q->flush_data_in_flight);