scsi_lib.c

来自「linux 内核源代码」· C语言 代码 · 共 2,521 行 · 第 1/5 页

/*
 *  scsi_lib.c Copyright (C) 1999 Eric Youngdale
 *
 *  SCSI queueing library.
 *      Initial versions: Eric Youngdale ([e-mail]).
 *                        Based upon conversations with large numbers
 *                        of people at Linux Expo.
 */

#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/completion.h>
#include <linux/kernel.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/delay.h>
#include <linux/hardirq.h>
#include <linux/scatterlist.h>

#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_dbg.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/scsi_eh.h>
#include <scsi/scsi_host.h>

#include "scsi_priv.h"
#include "scsi_logging.h"


#define SG_MEMPOOL_NR		ARRAY_SIZE(scsi_sg_pools)
#define SG_MEMPOOL_SIZE		2

/*
 * The maximum number of SG segments that we will put inside a scatterlist
 * (unless chaining is used). Should ideally fit inside a single page, to
 * avoid a higher order allocation.
 */
#define SCSI_MAX_SG_SEGMENTS	128

struct scsi_host_sg_pool {
	size_t		size;
	char		*name;
	struct kmem_cache	*slab;
	mempool_t	*pool;
};

#define SP(x) { x, "sgpool-" #x }
static struct scsi_host_sg_pool scsi_sg_pools[] = {
	SP(8),
	SP(16),
#if (SCSI_MAX_SG_SEGMENTS > 16)
	SP(32),
#if (SCSI_MAX_SG_SEGMENTS > 32)
	SP(64),
#if (SCSI_MAX_SG_SEGMENTS > 64)
	SP(128),
#endif
#endif
#endif
};
#undef SP

static void scsi_run_queue(struct request_queue *q);

/*
 * Function:	scsi_unprep_request()
 *
 * Purpose:	Remove all preparation done for a request, including its
 *		associated scsi_cmnd, so that it can be requeued.
 *
 * Arguments:	req	- request to unprepare
 *
 * Lock status:	Assumed that no locks are held upon entry.
 *
 * Returns:	Nothing.
 */
static void scsi_unprep_request(struct request *req)
{
	struct scsi_cmnd *cmd = req->special;

	req->cmd_flags &= ~REQ_DONTPREP;
	req->special = NULL;

	scsi_put_command(cmd);
}

/*
 * Function:    scsi_queue_insert()
 *
 * Purpose:     Insert a command in the midlevel queue.
 *
 * Arguments:   cmd    - command that we are adding to queue.
 *              reason - why we are inserting command to queue.
 *
 * Lock status: Assumed that lock is not held upon entry.
 *
 * Returns:     Nothing.
 *
 * Notes:       We do this for one of two cases.  Either the host is busy
 *              and it cannot accept any more commands for the time being,
 *              or the device returned QUEUE_FULL and can accept no more
 *              commands.
 * Notes:       This could be called either from an interrupt context or a
 *              normal process context.
 */
int scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
{
	struct Scsi_Host *host = cmd->device->host;
	struct scsi_device *device = cmd->device;
	struct request_queue *q = device->request_queue;
	unsigned long flags;

	SCSI_LOG_MLQUEUE(1,
		 printk("Inserting command %p into mlqueue\n", cmd));

	/*
	 * Set the appropriate busy bit for the device/host.
	 *
	 * If the host/device isn't busy, assume that something actually
	 * completed, and that we should be able to queue a command now.
	 *
	 * Note that the prior mid-layer assumption that any host could
	 * always queue at least one command is now broken.  The mid-layer
	 * will implement a user specifiable stall (see
	 * scsi_host.max_host_blocked and scsi_device.max_device_blocked)
	 * if a command is requeued with no other commands outstanding
	 * either for the device or for the host.
	 */
	if (reason == SCSI_MLQUEUE_HOST_BUSY)
		host->host_blocked = host->max_host_blocked;
	else if (reason == SCSI_MLQUEUE_DEVICE_BUSY)
		device->device_blocked = device->max_device_blocked;

	/*
	 * Decrement the counters, since these commands are no longer
	 * active on the host/device.
	 */
	scsi_device_unbusy(device);

	/*
	 * Requeue this command.  It will go before all other commands
	 * that are already in the queue.
	 *
	 * NOTE: there is magic here about the way the queue is plugged if
	 * we have no outstanding commands.
	 * 
	 * Although we *don't* plug the queue, we call the request
	 * function.  The SCSI request function detects the blocked condition
	 * and plugs the queue appropriately.
         */
	spin_lock_irqsave(q->queue_lock, flags);
	blk_requeue_request(q, cmd->request);
	spin_unlock_irqrestore(q->queue_lock, flags);

	scsi_run_queue(q);

	return 0;
}

/**
 * scsi_execute - insert request and wait for the result
 * @sdev:	scsi device
 * @cmd:	scsi command
 * @data_direction: data direction
 * @buffer:	data buffer
 * @bufflen:	len of buffer
 * @sense:	optional sense buffer
 * @timeout:	request timeout in seconds
 * @retries:	number of times to retry request
 * @flags:	or into request flags;
 *
 * returns the req->errors value which is the scsi_cmnd result
 * field.
 **/
int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
		 int data_direction, void *buffer, unsigned bufflen,
		 unsigned char *sense, int timeout, int retries, int flags)
{
	struct request *req;
	int write = (data_direction == DMA_TO_DEVICE);
	int ret = DRIVER_ERROR << 24;

	req = blk_get_request(sdev->request_queue, write, __GFP_WAIT);

	if (bufflen &&	blk_rq_map_kern(sdev->request_queue, req,
					buffer, bufflen, __GFP_WAIT))
		goto out;

	req->cmd_len = COMMAND_SIZE(cmd[0]);
	memcpy(req->cmd, cmd, req->cmd_len);
	req->sense = sense;
	req->sense_len = 0;
	req->retries = retries;
	req->timeout = timeout;
	req->cmd_type = REQ_TYPE_BLOCK_PC;
	req->cmd_flags |= flags | REQ_QUIET | REQ_PREEMPT;

	/*
	 * head injection *required* here otherwise quiesce won't work
	 */
	blk_execute_rq(req->q, NULL, req, 1);

	ret = req->errors;
 out:
	blk_put_request(req);

	return ret;
}
EXPORT_SYMBOL(scsi_execute);


int scsi_execute_req(struct scsi_device *sdev, const unsigned char *cmd,
		     int data_direction, void *buffer, unsigned bufflen,
		     struct scsi_sense_hdr *sshdr, int timeout, int retries)
{
	char *sense = NULL;
	int result;
	
	if (sshdr) {
		sense = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
		if (!sense)
			return DRIVER_ERROR << 24;
	}
	result = scsi_execute(sdev, cmd, data_direction, buffer, bufflen,
			      sense, timeout, retries, 0);
	if (sshdr)
		scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, sshdr);

	kfree(sense);
	return result;
}
EXPORT_SYMBOL(scsi_execute_req);

struct scsi_io_context {
	void *data;
	void (*done)(void *data, char *sense, int result, int resid);
	char sense[SCSI_SENSE_BUFFERSIZE];
};

static struct kmem_cache *scsi_io_context_cache;

static void scsi_end_async(struct request *req, int uptodate)
{
	struct scsi_io_context *sioc = req->end_io_data;

	if (sioc->done)
		sioc->done(sioc->data, sioc->sense, req->errors, req->data_len);

	kmem_cache_free(scsi_io_context_cache, sioc);
	__blk_put_request(req->q, req);
}

static int scsi_merge_bio(struct request *rq, struct bio *bio)
{
	struct request_queue *q = rq->q;

	bio->bi_flags &= ~(1 << BIO_SEG_VALID);
	if (rq_data_dir(rq) == WRITE)
		bio->bi_rw |= (1 << BIO_RW);
	blk_queue_bounce(q, &bio);

	return blk_rq_append_bio(q, rq, bio);
}

static void scsi_bi_endio(struct bio *bio, int error)
{
	bio_put(bio);
}

/**
 * scsi_req_map_sg - map a scatterlist into a request
 * @rq:		request to fill
 * @sg:		scatterlist
 * @nsegs:	number of elements
 * @bufflen:	len of buffer
 * @gfp:	memory allocation flags
 *
 * scsi_req_map_sg maps a scatterlist into a request so that the
 * request can be sent to the block layer. We do not trust the scatterlist
 * sent to use, as some ULDs use that struct to only organize the pages.
 */
static int scsi_req_map_sg(struct request *rq, struct scatterlist *sgl,
			   int nsegs, unsigned bufflen, gfp_t gfp)
{
	struct request_queue *q = rq->q;
	int nr_pages = (bufflen + sgl[0].offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
	unsigned int data_len = bufflen, len, bytes, off;
	struct scatterlist *sg;
	struct page *page;
	struct bio *bio = NULL;
	int i, err, nr_vecs = 0;

	for_each_sg(sgl, sg, nsegs, i) {
		page = sg_page(sg);
		off = sg->offset;
		len = sg->length;
 		data_len += len;

		while (len > 0 && data_len > 0) {
			/*
			 * sg sends a scatterlist that is larger than
			 * the data_len it wants transferred for certain
			 * IO sizes
			 */
			bytes = min_t(unsigned int, len, PAGE_SIZE - off);
			bytes = min(bytes, data_len);

			if (!bio) {
				nr_vecs = min_t(int, BIO_MAX_PAGES, nr_pages);
				nr_pages -= nr_vecs;

				bio = bio_alloc(gfp, nr_vecs);
				if (!bio) {
					err = -ENOMEM;
					goto free_bios;
				}
				bio->bi_end_io = scsi_bi_endio;
			}

			if (bio_add_pc_page(q, bio, page, bytes, off) !=
			    bytes) {
				bio_put(bio);
				err = -EINVAL;
				goto free_bios;
			}

			if (bio->bi_vcnt >= nr_vecs) {
				err = scsi_merge_bio(rq, bio);
				if (err) {
					bio_endio(bio, 0);
					goto free_bios;
				}
				bio = NULL;
			}

			page++;
			len -= bytes;
			data_len -=bytes;
			off = 0;
		}
	}

	rq->buffer = rq->data = NULL;
	rq->data_len = bufflen;
	return 0;

free_bios:
	while ((bio = rq->bio) != NULL) {
		rq->bio = bio->bi_next;
		/*
		 * call endio instead of bio_put incase it was bounced
		 */
		bio_endio(bio, 0);
	}

	return err;
}

/**
 * scsi_execute_async - insert request
 * @sdev:	scsi device
 * @cmd:	scsi command
 * @cmd_len:	length of scsi cdb
 * @data_direction: data direction
 * @buffer:	data buffer (this can be a kernel buffer or scatterlist)
 * @bufflen:	len of buffer
 * @use_sg:	if buffer is a scatterlist this is the number of elements
 * @timeout:	request timeout in seconds
 * @retries:	number of times to retry request
 * @flags:	or into request flags
 **/
int scsi_execute_async(struct scsi_device *sdev, const unsigned char *cmd,
		       int cmd_len, int data_direction, void *buffer, unsigned bufflen,
		       int use_sg, int timeout, int retries, void *privdata,
		       void (*done)(void *, char *, int, int), gfp_t gfp)
{
	struct request *req;
	struct scsi_io_context *sioc;
	int err = 0;
	int write = (data_direction == DMA_TO_DEVICE);

	sioc = kmem_cache_zalloc(scsi_io_context_cache, gfp);
	if (!sioc)
		return DRIVER_ERROR << 24;

	req = blk_get_request(sdev->request_queue, write, gfp);
	if (!req)
		goto free_sense;
	req->cmd_type = REQ_TYPE_BLOCK_PC;
	req->cmd_flags |= REQ_QUIET;

	if (use_sg)
		err = scsi_req_map_sg(req, buffer, use_sg, bufflen, gfp);
	else if (bufflen)
		err = blk_rq_map_kern(req->q, req, buffer, bufflen, gfp);

	if (err)
		goto free_req;

	req->cmd_len = cmd_len;
	memset(req->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
	memcpy(req->cmd, cmd, req->cmd_len);
	req->sense = sioc->sense;
	req->sense_len = 0;
	req->timeout = timeout;
	req->retries = retries;
	req->end_io_data = sioc;

	sioc->data = privdata;
	sioc->done = done;

	blk_execute_rq_nowait(req->q, NULL, req, 1, scsi_end_async);
	return 0;

free_req:
	blk_put_request(req);
free_sense:
	kmem_cache_free(scsi_io_context_cache, sioc);
	return DRIVER_ERROR << 24;
}
EXPORT_SYMBOL_GPL(scsi_execute_async);

/*
 * Function:    scsi_init_cmd_errh()
 *
 * Purpose:     Initialize cmd fields related to error handling.
 *
 * Arguments:   cmd	- command that is ready to be queued.
 *
 * Notes:       This function has the job of initializing a number of
 *              fields related to error handling.   Typically this will
 *              be called once for each command, as required.
 */
static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
{
	cmd->serial_number = 0;
	cmd->resid = 0;
	memset(cmd->sense_buffer, 0, sizeof cmd->sense_buffer);
	if (cmd->cmd_len == 0)
		cmd->cmd_len = COMMAND_SIZE(cmd->cmnd[0]);
}

void scsi_device_unbusy(struct scsi_device *sdev)
{
	struct Scsi_Host *shost = sdev->host;
	unsigned long flags;

	spin_lock_irqsave(shost->host_lock, flags);
	shost->host_busy--;
	if (unlikely(scsi_host_in_recovery(shost) &&
		     (shost->host_failed || shost->host_eh_scheduled)))
		scsi_eh_wakeup(shost);
	spin_unlock(shost->host_lock);
	spin_lock(sdev->request_queue->queue_lock);
	sdev->device_busy--;
	spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags);
}

/*
 * Called for single_lun devices on IO completion. Clear starget_sdev_user,
 * and call blk_run_queue for all the scsi_devices on the target -
 * including current_sdev first.
 *
 * Called with *no* scsi locks held.
 */
static void scsi_single_lun_run(struct scsi_device *current_sdev)
{
	struct Scsi_Host *shost = current_sdev->host;
	struct scsi_device *sdev, *tmp;
	struct scsi_target *starget = scsi_target(current_sdev);
	unsigned long flags;

	spin_lock_irqsave(shost->host_lock, flags);
	starget->starget_sdev_user = NULL;
	spin_unlock_irqrestore(shost->host_lock, flags);

	/*
	 * Call blk_run_queue for all LUNs on the target, starting with
	 * current_sdev. We race with others (to set starget_sdev_user),
	 * but in most cases, we will be first. Ideally, each LU on the
	 * target would get some limited time or requests on the target.
	 */
	blk_run_queue(current_sdev->request_queue);

	spin_lock_irqsave(shost->host_lock, flags);
	if (starget->starget_sdev_user)
		goto out;
	list_for_each_entry_safe(sdev, tmp, &starget->devices,
			same_target_siblings) {
		if (sdev == current_sdev)
			continue;
		if (scsi_device_get(sdev))
			continue;

		spin_unlock_irqrestore(shost->host_lock, flags);
		blk_run_queue(sdev->request_queue);
		spin_lock_irqsave(shost->host_lock, flags);
	
		scsi_device_put(sdev);
	}
 out: