ll_rw_blk.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 2,525 行 · 第 1/5 页

/*
 *  linux/drivers/block/ll_rw_blk.c
 *
 * Copyright (C) 1991, 1992 Linus Torvalds
 * Copyright (C) 1994,      Karl Keyte: Added support for disk statistics
 * Elevator latency, (C) 2000  Andrea Arcangeli <[e-mail]> SuSE
 * Queue request tables / lock, selectable elevator, Jens Axboe <[e-mail]>
 * kernel-doc documentation started by NeilBrown <[e-mail]> -  July2000
 * bio rewrite, highmem i/o, etc, Jens Axboe <[e-mail]> - may 2001
 */

/*
 * This handles all read/write requests to block devices
 */
#include <linux/config.h>
#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/bootmem.h>	/* for max_pfn/max_low_pfn */
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>

/*
 * for max sense size
 */
#include <scsi/scsi_cmnd.h>

static void blk_unplug_work(void *data);
static void blk_unplug_timeout(unsigned long data);

/*
 * For the allocated request tables
 */
static kmem_cache_t *request_cachep;

/*
 * For queue allocation
 */
static kmem_cache_t *requestq_cachep;

/*
 * For io context allocations
 */
static kmem_cache_t *iocontext_cachep;

static wait_queue_head_t congestion_wqh[2] = {
		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
	};

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

unsigned long blk_max_low_pfn, blk_max_pfn;

EXPORT_SYMBOL(blk_max_low_pfn);
EXPORT_SYMBOL(blk_max_pfn);

/* Amount of time in which a process may batch requests */
#define BLK_BATCH_TIME	(HZ/50UL)

/* Number of requests a "batching" process may submit */
#define BLK_BATCH_REQ	32

/*
 * Return the threshold (number of used requests) at which the queue is
 * considered to be congested.  It include a little hysteresis to keep the
 * context switch rate down.
 */
static inline int queue_congestion_on_threshold(struct request_queue *q)
{
	return q->nr_congestion_on;
}

/*
 * The threshold at which a queue is considered to be uncongested
 */
static inline int queue_congestion_off_threshold(struct request_queue *q)
{
	return q->nr_congestion_off;
}

static 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) - 1;
	if (nr < 1)
		nr = 1;
	q->nr_congestion_off = nr;
}

/*
 * A queue has just exitted congestion.  Note this in the global counter of
 * congested queues, and wake up anyone who was waiting for requests to be
 * put back.
 */
static void clear_queue_congested(request_queue_t *q, int rw)
{
	enum bdi_state bit;
	wait_queue_head_t *wqh = &congestion_wqh[rw];

	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
	clear_bit(bit, &q->backing_dev_info.state);
	smp_mb__after_clear_bit();
	if (waitqueue_active(wqh))
		wake_up(wqh);
}

/*
 * A queue has just entered congestion.  Flag that in the queue's VM-visible
 * state flags and increment the global gounter of congested queues.
 */
static void set_queue_congested(request_queue_t *q, int rw)
{
	enum bdi_state bit;

	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
	set_bit(bit, &q->backing_dev_info.state);
}

/**
 * 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;
	request_queue_t *q = bdev_get_queue(bdev);

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

EXPORT_SYMBOL(blk_get_backing_dev_info);

void blk_queue_activity_fn(request_queue_t *q, activity_fn *fn, void *data)
{
	q->activity_fn = fn;
	q->activity_data = data;
}

EXPORT_SYMBOL(blk_queue_activity_fn);

/**
 * blk_queue_prep_rq - set a prepare_request function for queue
 * @q:		queue
 * @pfn:	prepare_request function
 *
 * It's possible for a queue to register a prepare_request callback which
 * is invoked before the request is handed to the request_fn. The goal of
 * the function is to prepare a request for I/O, it can be used to build a
 * cdb from the request data for instance.
 *
 */
void blk_queue_prep_rq(request_queue_t *q, prep_rq_fn *pfn)
{
	q->prep_rq_fn = pfn;
}

EXPORT_SYMBOL(blk_queue_prep_rq);

/**
 * blk_queue_merge_bvec - set a merge_bvec function for queue
 * @q:		queue
 * @mbfn:	merge_bvec_fn
 *
 * Usually queues have static limitations on the max sectors or segments that
 * we can put in a request. Stacking drivers may have some settings that
 * are dynamic, and thus we have to query the queue whether it is ok to
 * add a new bio_vec to a bio at a given offset or not. If the block device
 * has such limitations, it needs to register a merge_bvec_fn to control
 * the size of bio's sent to it. Note that a block device *must* allow a
 * single page to be added to an empty bio. The block device driver may want
 * to use the bio_split() function to deal with these bio's. By default
 * no merge_bvec_fn is defined for a queue, and only the fixed limits are
 * honored.
 */
void blk_queue_merge_bvec(request_queue_t *q, merge_bvec_fn *mbfn)
{
	q->merge_bvec_fn = mbfn;
}

EXPORT_SYMBOL(blk_queue_merge_bvec);

/**
 * blk_queue_make_request - define an alternate make_request function for a device
 * @q:  the request queue for the device to be affected
 * @mfn: the alternate make_request function
 *
 * Description:
 *    The normal way for &struct bios to be passed to a device
 *    driver is for them to be collected into requests on a request
 *    queue, and then to allow the device driver to select requests
 *    off that queue when it is ready.  This works well for many block
 *    devices. However some block devices (typically virtual devices
 *    such as md or lvm) do not benefit from the processing on the
 *    request queue, and are served best by having the requests passed
 *    directly to them.  This can be achieved by providing a function
 *    to blk_queue_make_request().
 *
 * Caveat:
 *    The driver that does this *must* be able to deal appropriately
 *    with buffers in "highmemory". This can be accomplished by either calling
 *    __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
 *    blk_queue_bounce() to create a buffer in normal memory.
 **/
void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
{
	/*
	 * set defaults
	 */
	q->nr_requests = BLKDEV_MAX_RQ;
	q->max_phys_segments = MAX_PHYS_SEGMENTS;
	q->max_hw_segments = MAX_HW_SEGMENTS;
	q->make_request_fn = mfn;
	q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
	q->backing_dev_info.state = 0;
	q->backing_dev_info.memory_backed = 0;
	blk_queue_max_sectors(q, MAX_SECTORS);
	blk_queue_hardsect_size(q, 512);
	blk_queue_dma_alignment(q, 511);
	blk_queue_congestion_threshold(q);

	q->unplug_thresh = 4;		/* hmm */
	q->unplug_delay = (3 * HZ) / 1000;	/* 3 milliseconds */
	if (q->unplug_delay == 0)
		q->unplug_delay = 1;

	INIT_WORK(&q->unplug_work, blk_unplug_work, q);

	q->unplug_timer.function = blk_unplug_timeout;
	q->unplug_timer.data = (unsigned long)q;

	/*
	 * by default assume old behaviour and bounce for any highmem page
	 */
	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);

	blk_queue_activity_fn(q, NULL, NULL);
}

EXPORT_SYMBOL(blk_queue_make_request);

/**
 * blk_queue_ordered - does this queue support ordered writes
 * @q:     the request queue
 * @flag:  see below
 *
 * Description:
 *   For journalled file systems, doing ordered writes on a commit
 *   block instead of explicitly doing wait_on_buffer (which is bad
 *   for performance) can be a big win. Block drivers supporting this
 *   feature should call this function and indicate so.
 *
 **/
void blk_queue_ordered(request_queue_t *q, int flag)
{
	if (flag)
		set_bit(QUEUE_FLAG_ORDERED, &q->queue_flags);
	else
		clear_bit(QUEUE_FLAG_ORDERED, &q->queue_flags);
}

EXPORT_SYMBOL(blk_queue_ordered);

/**
 * blk_queue_issue_flush_fn - set function for issuing a flush
 * @q:     the request queue
 * @iff:   the function to be called issuing the flush
 *
 * Description:
 *   If a driver supports issuing a flush command, the support is notified
 *   to the block layer by defining it through this call.
 *
 **/
void blk_queue_issue_flush_fn(request_queue_t *q, issue_flush_fn *iff)
{
	q->issue_flush_fn = iff;
}

EXPORT_SYMBOL(blk_queue_issue_flush_fn);

/**
 * blk_queue_bounce_limit - set bounce buffer limit for queue
 * @q:  the request queue for the device
 * @dma_addr:   bus address limit
 *
 * Description:
 *    Different hardware can have different requirements as to what pages
 *    it can do I/O directly to. A low level driver can call
 *    blk_queue_bounce_limit to have lower memory pages allocated as bounce
 *    buffers for doing I/O to pages residing above @page. By default
 *    the block layer sets this to the highest numbered "low" memory page.
 **/
void blk_queue_bounce_limit(request_queue_t *q, u64 dma_addr)
{
	unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;

	/*
	 * set appropriate bounce gfp mask -- unfortunately we don't have a
	 * full 4GB zone, so we have to resort to low memory for any bounces.
	 * ISA has its own < 16MB zone.
	 */
	if (bounce_pfn < blk_max_low_pfn) {
		BUG_ON(dma_addr < BLK_BOUNCE_ISA);
		init_emergency_isa_pool();
		q->bounce_gfp = GFP_NOIO | GFP_DMA;
	} else
		q->bounce_gfp = GFP_NOIO;

	q->bounce_pfn = bounce_pfn;
}

EXPORT_SYMBOL(blk_queue_bounce_limit);

/**
 * blk_queue_max_sectors - set max sectors for a request for this queue
 * @q:  the request queue for the device
 * @max_sectors:  max sectors in the usual 512b unit
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of
 *    received requests.
 **/
void blk_queue_max_sectors(request_queue_t *q, unsigned short max_sectors)
{
	if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
		max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
		printk("%s: set to minimum %d\n", __FUNCTION__, max_sectors);
	}

	q->max_sectors = q->max_hw_sectors = max_sectors;
}

EXPORT_SYMBOL(blk_queue_max_sectors);

/**
 * blk_queue_max_phys_segments - set max phys segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    physical data segments in a request.  This would be the largest sized
 *    scatter list the driver could handle.
 **/
void blk_queue_max_phys_segments(request_queue_t *q, unsigned short max_segments)
{
	if (!max_segments) {
		max_segments = 1;
		printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
	}

	q->max_phys_segments = max_segments;
}

EXPORT_SYMBOL(blk_queue_max_phys_segments);

/**
 * blk_queue_max_hw_segments - set max hw segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    hw data segments in a request.  This would be the largest number of
 *    address/length pairs the host adapter can actually give as once
 *    to the device.
 **/
void blk_queue_max_hw_segments(request_queue_t *q, unsigned short max_segments)
{
	if (!max_segments) {
		max_segments = 1;
		printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
	}

	q->max_hw_segments = max_segments;
}

EXPORT_SYMBOL(blk_queue_max_hw_segments);

/**
 * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
 * @q:  the request queue for the device
 * @max_size:  max size of segment in bytes
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of a
 *    coalesced segment
 **/
void blk_queue_max_segment_size(request_queue_t *q, unsigned int max_size)
{
	if (max_size < PAGE_CACHE_SIZE) {
		max_size = PAGE_CACHE_SIZE;
		printk("%s: set to minimum %d\n", __FUNCTION__, max_size);
	}

	q->max_segment_size = max_size;
}

EXPORT_SYMBOL(blk_queue_max_segment_size);

/**
 * blk_queue_hardsect_size - set hardware sector size for the queue
 * @q:  the request queue for the device
 * @size:  the hardware sector size, in bytes
 *
 * Description:
 *   This should typically be set to the lowest possible sector size
 *   that the hardware can operate on (possible without reverting to
 *   even internal read-modify-write operations). Usually the default
 *   of 512 covers most hardware.
 **/
void blk_queue_hardsect_size(request_queue_t *q, unsigned short size)
{
	q->hardsect_size = size;
}

EXPORT_SYMBOL(blk_queue_hardsect_size);

/*
 * Returns the minimum that is _not_ zero, unless both are zero.
 */
#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))

/**
 * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
 * @t:	the stacking driver (top)
 * @b:  the underlying device (bottom)
 **/
void blk_queue_stack_limits(request_queue_t *t, request_queue_t *b)
{
	/* zero is "infinity" */
	t->max_sectors = t->max_hw_sectors =
		min_not_zero(t->max_sectors,b->max_sectors);

	t->max_phys_segments = min(t->max_phys_segments,b->max_phys_segments);
	t->max_hw_segments = min(t->max_hw_segments,b->max_hw_segments);
	t->max_segment_size = min(t->max_segment_size,b->max_segment_size);
	t->hardsect_size = max(t->hardsect_size,b->hardsect_size);
}

EXPORT_SYMBOL(blk_queue_stack_limits);

/**
 * blk_queue_segment_boundary - set boundary rules for segment merging
 * @q:  the request queue for the device
 * @mask:  the memory boundary mask
 **/
void blk_queue_segment_boundary(request_queue_t *q, unsigned long mask)
{
	if (mask < PAGE_CACHE_SIZE - 1) {
		mask = PAGE_CACHE_SIZE - 1;
		printk("%s: set to minimum %lx\n", __FUNCTION__, mask);
	}

	q->seg_boundary_mask = mask;
}

EXPORT_SYMBOL(blk_queue_segment_boundary);

/**
 * blk_queue_dma_alignment - set dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    set required memory and length aligment for direct dma transactions.
 *    this is used when buiding direct io requests for the queue.
 *
 **/
void blk_queue_dma_alignment(request_queue_t *q, int mask)
{
	q->dma_alignment = mask;
}

EXPORT_SYMBOL(blk_queue_dma_alignment);

/**
 * blk_queue_find_tag - find a request by its tag and queue
 *
 * @q:	 The request queue for the device