scsi_lib.c

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

	spin_unlock_irqrestore(shost->host_lock, flags);
}

/*
 * Function:	scsi_run_queue()
 *
 * Purpose:	Select a proper request queue to serve next
 *
 * Arguments:	q	- last request's queue
 *
 * Returns:     Nothing
 *
 * Notes:	The previous command was completely finished, start
 *		a new one if possible.
 */
static void scsi_run_queue(struct request_queue *q)
{
	struct scsi_device *sdev = q->queuedata;
	struct Scsi_Host *shost = sdev->host;
	unsigned long flags;

	if (sdev->single_lun)
		scsi_single_lun_run(sdev);

	spin_lock_irqsave(shost->host_lock, flags);
	while (!list_empty(&shost->starved_list) &&
	       !shost->host_blocked && !shost->host_self_blocked &&
		!((shost->can_queue > 0) &&
		  (shost->host_busy >= shost->can_queue))) {
		/*
		 * As long as shost is accepting commands and we have
		 * starved queues, call blk_run_queue. scsi_request_fn
		 * drops the queue_lock and can add us back to the
		 * starved_list.
		 *
		 * host_lock protects the starved_list and starved_entry.
		 * scsi_request_fn must get the host_lock before checking
		 * or modifying starved_list or starved_entry.
		 */
		sdev = list_entry(shost->starved_list.next,
					  struct scsi_device, starved_entry);
		list_del_init(&sdev->starved_entry);
		spin_unlock_irqrestore(shost->host_lock, flags);


		if (test_bit(QUEUE_FLAG_REENTER, &q->queue_flags) &&
		    !test_and_set_bit(QUEUE_FLAG_REENTER,
				      &sdev->request_queue->queue_flags)) {
			blk_run_queue(sdev->request_queue);
			clear_bit(QUEUE_FLAG_REENTER,
				  &sdev->request_queue->queue_flags);
		} else
			blk_run_queue(sdev->request_queue);

		spin_lock_irqsave(shost->host_lock, flags);
		if (unlikely(!list_empty(&sdev->starved_entry)))
			/*
			 * sdev lost a race, and was put back on the
			 * starved list. This is unlikely but without this
			 * in theory we could loop forever.
			 */
			break;
	}
	spin_unlock_irqrestore(shost->host_lock, flags);

	blk_run_queue(q);
}

/*
 * Function:	scsi_requeue_command()
 *
 * Purpose:	Handle post-processing of completed commands.
 *
 * Arguments:	q	- queue to operate on
 *		cmd	- command that may need to be requeued.
 *
 * Returns:	Nothing
 *
 * Notes:	After command completion, there may be blocks left
 *		over which weren't finished by the previous command
 *		this can be for a number of reasons - the main one is
 *		I/O errors in the middle of the request, in which case
 *		we need to request the blocks that come after the bad
 *		sector.
 * Notes:	Upon return, cmd is a stale pointer.
 */
static void scsi_requeue_command(struct request_queue *q, struct scsi_cmnd *cmd)
{
	struct request *req = cmd->request;
	unsigned long flags;

	scsi_unprep_request(req);
	spin_lock_irqsave(q->queue_lock, flags);
	blk_requeue_request(q, req);
	spin_unlock_irqrestore(q->queue_lock, flags);

	scsi_run_queue(q);
}

void scsi_next_command(struct scsi_cmnd *cmd)
{
	struct scsi_device *sdev = cmd->device;
	struct request_queue *q = sdev->request_queue;

	/* need to hold a reference on the device before we let go of the cmd */
	get_device(&sdev->sdev_gendev);

	scsi_put_command(cmd);
	scsi_run_queue(q);

	/* ok to remove device now */
	put_device(&sdev->sdev_gendev);
}

void scsi_run_host_queues(struct Scsi_Host *shost)
{
	struct scsi_device *sdev;

	shost_for_each_device(sdev, shost)
		scsi_run_queue(sdev->request_queue);
}

/*
 * Function:    scsi_end_request()
 *
 * Purpose:     Post-processing of completed commands (usually invoked at end
 *		of upper level post-processing and scsi_io_completion).
 *
 * Arguments:   cmd	 - command that is complete.
 *              uptodate - 1 if I/O indicates success, <= 0 for I/O error.
 *              bytes    - number of bytes of completed I/O
 *		requeue  - indicates whether we should requeue leftovers.
 *
 * Lock status: Assumed that lock is not held upon entry.
 *
 * Returns:     cmd if requeue required, NULL otherwise.
 *
 * Notes:       This is called for block device requests in order to
 *              mark some number of sectors as complete.
 * 
 *		We are guaranteeing that the request queue will be goosed
 *		at some point during this call.
 * Notes:	If cmd was requeued, upon return it will be a stale pointer.
 */
static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int uptodate,
					  int bytes, int requeue)
{
	struct request_queue *q = cmd->device->request_queue;
	struct request *req = cmd->request;
	unsigned long flags;

	/*
	 * If there are blocks left over at the end, set up the command
	 * to queue the remainder of them.
	 */
	if (end_that_request_chunk(req, uptodate, bytes)) {
		int leftover = (req->hard_nr_sectors << 9);

		if (blk_pc_request(req))
			leftover = req->data_len;

		/* kill remainder if no retrys */
		if (!uptodate && blk_noretry_request(req))
			end_that_request_chunk(req, 0, leftover);
		else {
			if (requeue) {
				/*
				 * Bleah.  Leftovers again.  Stick the
				 * leftovers in the front of the
				 * queue, and goose the queue again.
				 */
				scsi_requeue_command(q, cmd);
				cmd = NULL;
			}
			return cmd;
		}
	}

	add_disk_randomness(req->rq_disk);

	spin_lock_irqsave(q->queue_lock, flags);
	if (blk_rq_tagged(req))
		blk_queue_end_tag(q, req);
	end_that_request_last(req, uptodate);
	spin_unlock_irqrestore(q->queue_lock, flags);

	/*
	 * This will goose the queue request function at the end, so we don't
	 * need to worry about launching another command.
	 */
	scsi_next_command(cmd);
	return NULL;
}

/*
 * Like SCSI_MAX_SG_SEGMENTS, but for archs that have sg chaining. This limit
 * is totally arbitrary, a setting of 2048 will get you at least 8mb ios.
 */
#define SCSI_MAX_SG_CHAIN_SEGMENTS	2048

static inline unsigned int scsi_sgtable_index(unsigned short nents)
{
	unsigned int index;

	switch (nents) {
	case 1 ... 8:
		index = 0;
		break;
	case 9 ... 16:
		index = 1;
		break;
#if (SCSI_MAX_SG_SEGMENTS > 16)
	case 17 ... 32:
		index = 2;
		break;
#if (SCSI_MAX_SG_SEGMENTS > 32)
	case 33 ... 64:
		index = 3;
		break;
#if (SCSI_MAX_SG_SEGMENTS > 64)
	case 65 ... 128:
		index = 4;
		break;
#endif
#endif
#endif
	default:
		printk(KERN_ERR "scsi: bad segment count=%d\n", nents);
		BUG();
	}

	return index;
}

struct scatterlist *scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask)
{
	struct scsi_host_sg_pool *sgp;
	struct scatterlist *sgl, *prev, *ret;
	unsigned int index;
	int this, left;

	BUG_ON(!cmd->use_sg);

	left = cmd->use_sg;
	ret = prev = NULL;
	do {
		this = left;
		if (this > SCSI_MAX_SG_SEGMENTS) {
			this = SCSI_MAX_SG_SEGMENTS - 1;
			index = SG_MEMPOOL_NR - 1;
		} else
			index = scsi_sgtable_index(this);

		left -= this;

		sgp = scsi_sg_pools + index;

		sgl = mempool_alloc(sgp->pool, gfp_mask);
		if (unlikely(!sgl))
			goto enomem;

		sg_init_table(sgl, sgp->size);

		/*
		 * first loop through, set initial index and return value
		 */
		if (!ret)
			ret = sgl;

		/*
		 * chain previous sglist, if any. we know the previous
		 * sglist must be the biggest one, or we would not have
		 * ended up doing another loop.
		 */
		if (prev)
			sg_chain(prev, SCSI_MAX_SG_SEGMENTS, sgl);

		/*
		 * if we have nothing left, mark the last segment as
		 * end-of-list
		 */
		if (!left)
			sg_mark_end(&sgl[this - 1]);

		/*
		 * don't allow subsequent mempool allocs to sleep, it would
		 * violate the mempool principle.
		 */
		gfp_mask &= ~__GFP_WAIT;
		gfp_mask |= __GFP_HIGH;
		prev = sgl;
	} while (left);

	/*
	 * ->use_sg may get modified after dma mapping has potentially
	 * shrunk the number of segments, so keep a copy of it for free.
	 */
	cmd->__use_sg = cmd->use_sg;
	return ret;
enomem:
	if (ret) {
		/*
		 * Free entries chained off ret. Since we were trying to
		 * allocate another sglist, we know that all entries are of
		 * the max size.
		 */
		sgp = scsi_sg_pools + SG_MEMPOOL_NR - 1;
		prev = ret;
		ret = &ret[SCSI_MAX_SG_SEGMENTS - 1];

		while ((sgl = sg_chain_ptr(ret)) != NULL) {
			ret = &sgl[SCSI_MAX_SG_SEGMENTS - 1];
			mempool_free(sgl, sgp->pool);
		}

		mempool_free(prev, sgp->pool);
	}
	return NULL;
}

EXPORT_SYMBOL(scsi_alloc_sgtable);

void scsi_free_sgtable(struct scsi_cmnd *cmd)
{
	struct scatterlist *sgl = cmd->request_buffer;
	struct scsi_host_sg_pool *sgp;

	/*
	 * if this is the biggest size sglist, check if we have
	 * chained parts we need to free
	 */
	if (cmd->__use_sg > SCSI_MAX_SG_SEGMENTS) {
		unsigned short this, left;
		struct scatterlist *next;
		unsigned int index;

		left = cmd->__use_sg - (SCSI_MAX_SG_SEGMENTS - 1);
		next = sg_chain_ptr(&sgl[SCSI_MAX_SG_SEGMENTS - 1]);
		while (left && next) {
			sgl = next;
			this = left;
			if (this > SCSI_MAX_SG_SEGMENTS) {
				this = SCSI_MAX_SG_SEGMENTS - 1;
				index = SG_MEMPOOL_NR - 1;
			} else
				index = scsi_sgtable_index(this);

			left -= this;

			sgp = scsi_sg_pools + index;

			if (left)
				next = sg_chain_ptr(&sgl[sgp->size - 1]);

			mempool_free(sgl, sgp->pool);
		}

		/*
		 * Restore original, will be freed below
		 */
		sgl = cmd->request_buffer;
		sgp = scsi_sg_pools + SG_MEMPOOL_NR - 1;
	} else
		sgp = scsi_sg_pools + scsi_sgtable_index(cmd->__use_sg);

	mempool_free(sgl, sgp->pool);
}

EXPORT_SYMBOL(scsi_free_sgtable);

/*
 * Function:    scsi_release_buffers()
 *
 * Purpose:     Completion processing for block device I/O requests.
 *
 * Arguments:   cmd	- command that we are bailing.
 *
 * Lock status: Assumed that no lock is held upon entry.
 *
 * Returns:     Nothing
 *
 * Notes:       In the event that an upper level driver rejects a
 *		command, we must release resources allocated during
 *		the __init_io() function.  Primarily this would involve
 *		the scatter-gather table, and potentially any bounce
 *		buffers.
 */
static void scsi_release_buffers(struct scsi_cmnd *cmd)
{
	if (cmd->use_sg)
		scsi_free_sgtable(cmd);

	/*
	 * Zero these out.  They now point to freed memory, and it is
	 * dangerous to hang onto the pointers.
	 */
	cmd->request_buffer = NULL;
	cmd->request_bufflen = 0;
}

/*
 * Function:    scsi_io_completion()
 *
 * Purpose:     Completion processing for block device I/O requests.
 *
 * Arguments:   cmd   - command that is finished.
 *
 * Lock status: Assumed that no lock is held upon entry.
 *
 * Returns:     Nothing
 *
 * Notes:       This function is matched in terms of capabilities to
 *              the function that created the scatter-gather list.
 *              In other words, if there are no bounce buffers
 *              (the normal case for most drivers), we don't need
 *              the logic to deal with cleaning up afterwards.
 *
 *		We must do one of several things here:
 *
 *		a) Call scsi_end_request.  This will finish off the
 *		   specified number of sectors.  If we are done, the
 *		   command block will be released, and the queue
 *		   function will be goosed.  If we are not done, then
 *		   scsi_end_request will directly goose the queue.
 *
 *		b) We can just use scsi_requeue_command() here.  This would
 *		   be used if we just wanted to retry, for example.
 */
void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
{
	int result = cmd->result;
	int this_count = cmd->request_bufflen;
	struct request_queue *q = cmd->device->request_queue;
	struct request *req = cmd->request;
	int clear_errors = 1;
	struct scsi_sense_hdr sshdr;
	int sense_valid = 0;
	int sense_deferred = 0;

	scsi_release_buffers(cmd);

	if (result) {
		sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
		if (sense_valid)
			sense_deferred = scsi_sense_is_deferred(&sshdr);
	}

	if (blk_pc_request(req)) { /* SG_IO ioctl from block level */
		req->errors = result;
		if (result) {
			clear_errors = 0;
			if (sense_valid && req->sense) {
				/*
				 * SG_IO wants current and deferred errors
				 */
				int len = 8 + cmd->sense_buffer[7];

				if (len > SCSI_SENSE_BUFFERSIZE)
					len = SCSI_SENSE_BUFFERSIZE;
				memcpy(req->sense, cmd->sense_buffer,  len);
				req->sense_len = len;
			}
		}
		req->data_len = cmd->resid;
	}

	/*
	 * Next deal with any sectors which we were able to correctly
	 * handle.
	 */
	SCSI_LOG_HLCOMPLETE(1, printk("%ld sectors total, "
				      "%d bytes done.\n",
				      req->nr_sectors, good_bytes));
	SCSI_LOG_HLCOMPLETE(1, printk("use_sg is %d\n", cmd->use_sg));

	if (clear_errors)
		req->errors = 0;

	/* A number of bytes were successfully read.  If there
	 * are leftovers and there is some kind of error
	 * (result != 0), retry the rest.
	 */
	if (scsi_end_request(cmd, 1, good_bytes, result == 0) == NULL)
		return;

	/* good_bytes = 0, or (inclusive) there were leftovers and
	 * result = 0, so scsi_end_request couldn't retry.
	 */
	if (sense_valid && !sense_deferred) {
		switch (sshdr.sense_key) {
		case UNIT_ATTENTION:
			if (cmd->device->removable) {
				/* Detected disc change.  Set a bit
				 * and quietly refuse further access.
				 */
				cmd->device->changed = 1;
				scsi_end_request(cmd, 0, this_count, 1);
				return;
			} else {
				/* Must have been a power glitch, or a
				 * bus reset.  Could not have been a
				 * media change, so we just retry the
				 * request and see what happens.
				 */
				scsi_requeue_command(q, cmd);