block: continue ll_rw_blk.c splitup

Adds files for barrier handling, rq execution, io context handling,
mapping data to requests, and queue settings.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

block/Makefile

@@ -2,8 +2,9 @@
 # Makefile for the kernel block layer
 #
 
-obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o ioctl.o \
+obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
-			genhd.o scsi_ioctl.o
+			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
+			blk-exec.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o

block/blk-barrier.c

@@ -0,0 +1,319 @@
+/*
+ * Functions related to barrier IO handling
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+
+#include "blk.h"
+
+/**
+ * blk_queue_ordered - does this queue support ordered writes
+ * @q:        the request queue
+ * @ordered:  one of QUEUE_ORDERED_*
+ * @prepare_flush_fn: rq setup helper for cache flush ordered writes
+ *
+ * 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.
+ *
+ **/
+int blk_queue_ordered(struct request_queue *q, unsigned ordered,
+		      prepare_flush_fn *prepare_flush_fn)
+{
+	if (ordered & (QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH) &&
+	    prepare_flush_fn == NULL) {
+		printk(KERN_ERR "blk_queue_ordered: prepare_flush_fn required\n");
+		return -EINVAL;
+	}
+
+	if (ordered != QUEUE_ORDERED_NONE &&
+	    ordered != QUEUE_ORDERED_DRAIN &&
+	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
+	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
+	    ordered != QUEUE_ORDERED_TAG &&
+	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
+	    ordered != QUEUE_ORDERED_TAG_FUA) {
+		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
+		return -EINVAL;
+	}
+
+	q->ordered = ordered;
+	q->next_ordered = ordered;
+	q->prepare_flush_fn = prepare_flush_fn;
+
+	return 0;
+}
+
+EXPORT_SYMBOL(blk_queue_ordered);
+
+/*
+ * Cache flushing for ordered writes handling
+ */
+inline unsigned blk_ordered_cur_seq(struct request_queue *q)
+{
+	if (!q->ordseq)
+		return 0;
+	return 1 << ffz(q->ordseq);
+}
+
+unsigned blk_ordered_req_seq(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	BUG_ON(q->ordseq == 0);
+
+	if (rq == &q->pre_flush_rq)
+		return QUEUE_ORDSEQ_PREFLUSH;
+	if (rq == &q->bar_rq)
+		return QUEUE_ORDSEQ_BAR;
+	if (rq == &q->post_flush_rq)
+		return QUEUE_ORDSEQ_POSTFLUSH;
+
+	/*
+	 * !fs requests don't need to follow barrier ordering.  Always
+	 * put them at the front.  This fixes the following deadlock.
+	 *
+	 * http://thread.gmane.org/gmane.linux.kernel/537473
+	 */
+	if (!blk_fs_request(rq))
+		return QUEUE_ORDSEQ_DRAIN;
+
+	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
+	    (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
+		return QUEUE_ORDSEQ_DRAIN;
+	else
+		return QUEUE_ORDSEQ_DONE;
+}
+
+void blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
+{
+	struct request *rq;
+
+	if (error && !q->orderr)
+		q->orderr = error;
+
+	BUG_ON(q->ordseq & seq);
+	q->ordseq |= seq;
+
+	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
+		return;
+
+	/*
+	 * Okay, sequence complete.
+	 */
+	q->ordseq = 0;
+	rq = q->orig_bar_rq;
+
+	if (__blk_end_request(rq, q->orderr, blk_rq_bytes(rq)))
+		BUG();
+}
+
+static void pre_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
+}
+
+static void bar_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
+}
+
+static void post_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
+}
+
+static void queue_flush(struct request_queue *q, unsigned which)
+{
+	struct request *rq;
+	rq_end_io_fn *end_io;
+
+	if (which == QUEUE_ORDERED_PREFLUSH) {
+		rq = &q->pre_flush_rq;
+		end_io = pre_flush_end_io;
+	} else {
+		rq = &q->post_flush_rq;
+		end_io = post_flush_end_io;
+	}
+
+	rq->cmd_flags = REQ_HARDBARRIER;
+	rq_init(q, rq);
+	rq->elevator_private = NULL;
+	rq->elevator_private2 = NULL;
+	rq->rq_disk = q->bar_rq.rq_disk;
+	rq->end_io = end_io;
+	q->prepare_flush_fn(q, rq);
+
+	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+}
+
+static inline struct request *start_ordered(struct request_queue *q,
+					    struct request *rq)
+{
+	q->orderr = 0;
+	q->ordered = q->next_ordered;
+	q->ordseq |= QUEUE_ORDSEQ_STARTED;
+
+	/*
+	 * Prep proxy barrier request.
+	 */
+	blkdev_dequeue_request(rq);
+	q->orig_bar_rq = rq;
+	rq = &q->bar_rq;
+	rq->cmd_flags = 0;
+	rq_init(q, rq);
+	if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
+		rq->cmd_flags |= REQ_RW;
+	if (q->ordered & QUEUE_ORDERED_FUA)
+		rq->cmd_flags |= REQ_FUA;
+	rq->elevator_private = NULL;
+	rq->elevator_private2 = NULL;
+	init_request_from_bio(rq, q->orig_bar_rq->bio);
+	rq->end_io = bar_end_io;
+
+	/*
+	 * Queue ordered sequence.  As we stack them at the head, we
+	 * need to queue in reverse order.  Note that we rely on that
+	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
+	 * request gets inbetween ordered sequence. If this request is
+	 * an empty barrier, we don't need to do a postflush ever since
+	 * there will be no data written between the pre and post flush.
+	 * Hence a single flush will suffice.
+	 */
+	if ((q->ordered & QUEUE_ORDERED_POSTFLUSH) && !blk_empty_barrier(rq))
+		queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
+	else
+		q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;
+
+	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+
+	if (q->ordered & QUEUE_ORDERED_PREFLUSH) {
+		queue_flush(q, QUEUE_ORDERED_PREFLUSH);
+		rq = &q->pre_flush_rq;
+	} else
+		q->ordseq |= QUEUE_ORDSEQ_PREFLUSH;
+
+	if ((q->ordered & QUEUE_ORDERED_TAG) || q->in_flight == 0)
+		q->ordseq |= QUEUE_ORDSEQ_DRAIN;
+	else
+		rq = NULL;
+
+	return rq;
+}
+
+int blk_do_ordered(struct request_queue *q, struct request **rqp)
+{
+	struct request *rq = *rqp;
+	const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
+
+	if (!q->ordseq) {
+		if (!is_barrier)
+			return 1;
+
+		if (q->next_ordered != QUEUE_ORDERED_NONE) {
+			*rqp = start_ordered(q, rq);
+			return 1;
+		} else {
+			/*
+			 * This can happen when the queue switches to
+			 * ORDERED_NONE while this request is on it.
+			 */
+			blkdev_dequeue_request(rq);
+			if (__blk_end_request(rq, -EOPNOTSUPP,
+					      blk_rq_bytes(rq)))
+				BUG();
+			*rqp = NULL;
+			return 0;
+		}
+	}
+
+	/*
+	 * Ordered sequence in progress
+	 */
+
+	/* Special requests are not subject to ordering rules. */
+	if (!blk_fs_request(rq) &&
+	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
+		return 1;
+
+	if (q->ordered & QUEUE_ORDERED_TAG) {
+		/* Ordered by tag.  Blocking the next barrier is enough. */
+		if (is_barrier && rq != &q->bar_rq)
+			*rqp = NULL;
+	} else {
+		/* Ordered by draining.  Wait for turn. */
+		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
+		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
+			*rqp = NULL;
+	}
+
+	return 1;
+}
+
+static void bio_end_empty_barrier(struct bio *bio, int err)
+{
+	if (err)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+
+	complete(bio->bi_private);
+}
+
+/**
+ * blkdev_issue_flush - queue a flush
+ * @bdev:	blockdev to issue flush for
+ * @error_sector:	error sector
+ *
+ * Description:
+ *    Issue a flush for the block device in question. Caller can supply
+ *    room for storing the error offset in case of a flush error, if they
+ *    wish to.  Caller must run wait_for_completion() on its own.
+ */
+int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request_queue *q;
+	struct bio *bio;
+	int ret;
+
+	if (bdev->bd_disk == NULL)
+		return -ENXIO;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	bio = bio_alloc(GFP_KERNEL, 0);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_end_io = bio_end_empty_barrier;
+	bio->bi_private = &wait;
+	bio->bi_bdev = bdev;
+	submit_bio(1 << BIO_RW_BARRIER, bio);
+
+	wait_for_completion(&wait);
+
+	/*
+	 * The driver must store the error location in ->bi_sector, if
+	 * it supports it. For non-stacked drivers, this should be copied
+	 * from rq->sector.
+	 */
+	if (error_sector)
+		*error_sector = bio->bi_sector;
+
+	ret = 0;
+	if (!bio_flagged(bio, BIO_UPTODATE))
+		ret = -EIO;
+
+	bio_put(bio);
+	return ret;
+}
+
+EXPORT_SYMBOL(blkdev_issue_flush);

block/blk-exec.c

@@ -0,0 +1,105 @@
+/*
+ * Functions related to setting various queue properties from drivers
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+
+#include "blk.h"
+
+/*
+ * for max sense size
+ */
+#include <scsi/scsi_cmnd.h>
+
+/**
+ * blk_end_sync_rq - executes a completion event on a request
+ * @rq: request to complete
+ * @error: end io status of the request
+ */
+void blk_end_sync_rq(struct request *rq, int error)
+{
+	struct completion *waiting = rq->end_io_data;
+
+	rq->end_io_data = NULL;
+	__blk_put_request(rq->q, rq);
+
+	/*
+	 * complete last, if this is a stack request the process (and thus
+	 * the rq pointer) could be invalid right after this complete()
+	 */
+	complete(waiting);
+}
+EXPORT_SYMBOL(blk_end_sync_rq);
+
+/**
+ * blk_execute_rq_nowait - insert a request into queue for execution
+ * @q:		queue to insert the request in
+ * @bd_disk:	matching gendisk
+ * @rq:		request to insert
+ * @at_head:    insert request at head or tail of queue
+ * @done:	I/O completion handler
+ *
+ * Description:
+ *    Insert a fully prepared request at the back of the io scheduler queue
+ *    for execution.  Don't wait for completion.
+ */
+void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
+			   struct request *rq, int at_head,
+			   rq_end_io_fn *done)
+{
+	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
+
+	rq->rq_disk = bd_disk;
+	rq->cmd_flags |= REQ_NOMERGE;
+	rq->end_io = done;
+	WARN_ON(irqs_disabled());
+	spin_lock_irq(q->queue_lock);
+	__elv_add_request(q, rq, where, 1);
+	__generic_unplug_device(q);
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
+
+/**
+ * blk_execute_rq - insert a request into queue for execution
+ * @q:		queue to insert the request in
+ * @bd_disk:	matching gendisk
+ * @rq:		request to insert
+ * @at_head:    insert request at head or tail of queue
+ *
+ * Description:
+ *    Insert a fully prepared request at the back of the io scheduler queue
+ *    for execution and wait for completion.
+ */
+int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
+		   struct request *rq, int at_head)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	char sense[SCSI_SENSE_BUFFERSIZE];
+	int err = 0;
+
+	/*
+	 * we need an extra reference to the request, so we can look at
+	 * it after io completion
+	 */
+	rq->ref_count++;
+
+	if (!rq->sense) {
+		memset(sense, 0, sizeof(sense));
+		rq->sense = sense;
+		rq->sense_len = 0;
+	}
+
+	rq->end_io_data = &wait;
+	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
+	wait_for_completion(&wait);
+
+	if (rq->errors)
+		err = -EIO;
+
+	return err;
+}
+
+EXPORT_SYMBOL(blk_execute_rq);

block/blk-ioc.c

@@ -0,0 +1,194 @@
+/*
+ * Functions related to io context handling
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
+
+#include "blk.h"
+
+/*
+ * For io context allocations
+ */
+static struct kmem_cache *iocontext_cachep;
+
+static void cfq_dtor(struct io_context *ioc)
+{
+	struct cfq_io_context *cic[1];
+	int r;
+
+	/*
+	 * We don't have a specific key to lookup with, so use the gang
+	 * lookup to just retrieve the first item stored. The cfq exit
+	 * function will iterate the full tree, so any member will do.
+	 */
+	r = radix_tree_gang_lookup(&ioc->radix_root, (void **) cic, 0, 1);
+	if (r > 0)
+		cic[0]->dtor(ioc);
+}
+
+/*
+ * IO Context helper functions. put_io_context() returns 1 if there are no
+ * more users of this io context, 0 otherwise.
+ */
+int put_io_context(struct io_context *ioc)
+{
+	if (ioc == NULL)
+		return 1;
+
+	BUG_ON(atomic_read(&ioc->refcount) == 0);
+
+	if (atomic_dec_and_test(&ioc->refcount)) {
+		rcu_read_lock();
+		if (ioc->aic && ioc->aic->dtor)
+			ioc->aic->dtor(ioc->aic);
+		rcu_read_unlock();
+		cfq_dtor(ioc);
+
+		kmem_cache_free(iocontext_cachep, ioc);
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(put_io_context);
+
+static void cfq_exit(struct io_context *ioc)
+{
+	struct cfq_io_context *cic[1];
+	int r;
+
+	rcu_read_lock();
+	/*
+	 * See comment for cfq_dtor()
+	 */
+	r = radix_tree_gang_lookup(&ioc->radix_root, (void **) cic, 0, 1);
+	rcu_read_unlock();
+
+	if (r > 0)
+		cic[0]->exit(ioc);
+}
+
+/* Called by the exitting task */
+void exit_io_context(void)
+{
+	struct io_context *ioc;
+
+	task_lock(current);
+	ioc = current->io_context;
+	current->io_context = NULL;
+	task_unlock(current);
+
+	if (atomic_dec_and_test(&ioc->nr_tasks)) {
+		if (ioc->aic && ioc->aic->exit)
+			ioc->aic->exit(ioc->aic);
+		cfq_exit(ioc);
+
+		put_io_context(ioc);
+	}
+}
+
+struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
+{
+	struct io_context *ret;
+
+	ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node);
+	if (ret) {
+		atomic_set(&ret->refcount, 1);
+		atomic_set(&ret->nr_tasks, 1);
+		spin_lock_init(&ret->lock);
+		ret->ioprio_changed = 0;
+		ret->ioprio = 0;
+		ret->last_waited = jiffies; /* doesn't matter... */
+		ret->nr_batch_requests = 0; /* because this is 0 */
+		ret->aic = NULL;
+		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
+		ret->ioc_data = NULL;
+	}
+
+	return ret;
+}
+
+/*
+ * If the current task has no IO context then create one and initialise it.
+ * Otherwise, return its existing IO context.
+ *
+ * This returned IO context doesn't have a specifically elevated refcount,
+ * but since the current task itself holds a reference, the context can be
+ * used in general code, so long as it stays within `current` context.
+ */
+struct io_context *current_io_context(gfp_t gfp_flags, int node)
+{
+	struct task_struct *tsk = current;
+	struct io_context *ret;
+
+	ret = tsk->io_context;
+	if (likely(ret))
+		return ret;
+
+	ret = alloc_io_context(gfp_flags, node);
+	if (ret) {
+		/* make sure set_task_ioprio() sees the settings above */
+		smp_wmb();
+		tsk->io_context = ret;
+	}
+
+	return ret;
+}
+
+/*
+ * If the current task has no IO context then create one and initialise it.
+ * If it does have a context, take a ref on it.
+ *
+ * This is always called in the context of the task which submitted the I/O.
+ */
+struct io_context *get_io_context(gfp_t gfp_flags, int node)
+{
+	struct io_context *ret = NULL;
+
+	/*
+	 * Check for unlikely race with exiting task. ioc ref count is
+	 * zero when ioc is being detached.
+	 */
+	do {
+		ret = current_io_context(gfp_flags, node);
+		if (unlikely(!ret))
+			break;
+	} while (!atomic_inc_not_zero(&ret->refcount));
+
+	return ret;
+}
+EXPORT_SYMBOL(get_io_context);
+
+void copy_io_context(struct io_context **pdst, struct io_context **psrc)
+{
+	struct io_context *src = *psrc;
+	struct io_context *dst = *pdst;
+
+	if (src) {
+		BUG_ON(atomic_read(&src->refcount) == 0);
+		atomic_inc(&src->refcount);
+		put_io_context(dst);
+		*pdst = src;
+	}
+}
+EXPORT_SYMBOL(copy_io_context);
+
+void swap_io_context(struct io_context **ioc1, struct io_context **ioc2)
+{
+	struct io_context *temp;
+	temp = *ioc1;
+	*ioc1 = *ioc2;
+	*ioc2 = temp;
+}
+EXPORT_SYMBOL(swap_io_context);
+
+int __init blk_ioc_init(void)
+{
+	iocontext_cachep = kmem_cache_create("blkdev_ioc",
+			sizeof(struct io_context), 0, SLAB_PANIC, NULL);
+	return 0;
+}
+subsys_initcall(blk_ioc_init);

block/blk-map.c

@@ -0,0 +1,264 @@
+/*
+ * Functions related to mapping data to requests
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+
+#include "blk.h"
+
+int blk_rq_append_bio(struct request_queue *q, struct request *rq,
+		      struct bio *bio)
+{
+	if (!rq->bio)
+		blk_rq_bio_prep(q, rq, bio);
+	else if (!ll_back_merge_fn(q, rq, bio))
+		return -EINVAL;
+	else {
+		rq->biotail->bi_next = bio;
+		rq->biotail = bio;
+
+		rq->data_len += bio->bi_size;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(blk_rq_append_bio);
+
+static int __blk_rq_unmap_user(struct bio *bio)
+{
+	int ret = 0;
+
+	if (bio) {
+		if (bio_flagged(bio, BIO_USER_MAPPED))
+			bio_unmap_user(bio);
+		else
+			ret = bio_uncopy_user(bio);
+	}
+
+	return ret;
+}
+
+static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
+			     void __user *ubuf, unsigned int len)
+{
+	unsigned long uaddr;
+	struct bio *bio, *orig_bio;
+	int reading, ret;
+
+	reading = rq_data_dir(rq) == READ;
+
+	/*
+	 * if alignment requirement is satisfied, map in user pages for
+	 * direct dma. else, set up kernel bounce buffers
+	 */
+	uaddr = (unsigned long) ubuf;
+	if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q)))
+		bio = bio_map_user(q, NULL, uaddr, len, reading);
+	else
+		bio = bio_copy_user(q, uaddr, len, reading);
+
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	orig_bio = bio;
+	blk_queue_bounce(q, &bio);
+
+	/*
+	 * We link the bounce buffer in and could have to traverse it
+	 * later so we have to get a ref to prevent it from being freed
+	 */
+	bio_get(bio);
+
+	ret = blk_rq_append_bio(q, rq, bio);
+	if (!ret)
+		return bio->bi_size;
+
+	/* if it was boucned we must call the end io function */
+	bio_endio(bio, 0);
+	__blk_rq_unmap_user(orig_bio);
+	bio_put(bio);
+	return ret;
+}
+
+/**
+ * blk_rq_map_user - map user data to a request, for REQ_BLOCK_PC usage
+ * @q:		request queue where request should be inserted
+ * @rq:		request structure to fill
+ * @ubuf:	the user buffer
+ * @len:	length of user data
+ *
+ * Description:
+ *    Data will be mapped directly for zero copy io, if possible. Otherwise
+ *    a kernel bounce buffer is used.
+ *
+ *    A matching blk_rq_unmap_user() must be issued at the end of io, while
+ *    still in process context.
+ *
+ *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
+ *    before being submitted to the device, as pages mapped may be out of
+ *    reach. It's the callers responsibility to make sure this happens. The
+ *    original bio must be passed back in to blk_rq_unmap_user() for proper
+ *    unmapping.
+ */
+int blk_rq_map_user(struct request_queue *q, struct request *rq,
+		    void __user *ubuf, unsigned long len)
+{
+	unsigned long bytes_read = 0;
+	struct bio *bio = NULL;
+	int ret;
+
+	if (len > (q->max_hw_sectors << 9))
+		return -EINVAL;
+	if (!len || !ubuf)
+		return -EINVAL;
+
+	while (bytes_read != len) {
+		unsigned long map_len, end, start;
+
+		map_len = min_t(unsigned long, len - bytes_read, BIO_MAX_SIZE);
+		end = ((unsigned long)ubuf + map_len + PAGE_SIZE - 1)
+								>> PAGE_SHIFT;
+		start = (unsigned long)ubuf >> PAGE_SHIFT;
+
+		/*
+		 * A bad offset could cause us to require BIO_MAX_PAGES + 1
+		 * pages. If this happens we just lower the requested
+		 * mapping len by a page so that we can fit
+		 */
+		if (end - start > BIO_MAX_PAGES)
+			map_len -= PAGE_SIZE;
+
+		ret = __blk_rq_map_user(q, rq, ubuf, map_len);
+		if (ret < 0)
+			goto unmap_rq;
+		if (!bio)
+			bio = rq->bio;
+		bytes_read += ret;
+		ubuf += ret;
+	}
+
+	rq->buffer = rq->data = NULL;
+	return 0;
+unmap_rq:
+	blk_rq_unmap_user(bio);
+	return ret;
+}
+
+EXPORT_SYMBOL(blk_rq_map_user);
+
+/**
+ * blk_rq_map_user_iov - map user data to a request, for REQ_BLOCK_PC usage
+ * @q:		request queue where request should be inserted
+ * @rq:		request to map data to
+ * @iov:	pointer to the iovec
+ * @iov_count:	number of elements in the iovec
+ * @len:	I/O byte count
+ *
+ * Description:
+ *    Data will be mapped directly for zero copy io, if possible. Otherwise
+ *    a kernel bounce buffer is used.
+ *
+ *    A matching blk_rq_unmap_user() must be issued at the end of io, while
+ *    still in process context.
+ *
+ *    Note: The mapped bio may need to be bounced through blk_queue_bounce()
+ *    before being submitted to the device, as pages mapped may be out of
+ *    reach. It's the callers responsibility to make sure this happens. The
+ *    original bio must be passed back in to blk_rq_unmap_user() for proper
+ *    unmapping.
+ */
+int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
+			struct sg_iovec *iov, int iov_count, unsigned int len)
+{
+	struct bio *bio;
+
+	if (!iov || iov_count <= 0)
+		return -EINVAL;
+
+	/* we don't allow misaligned data like bio_map_user() does.  If the
+	 * user is using sg, they're expected to know the alignment constraints
+	 * and respect them accordingly */
+	bio = bio_map_user_iov(q, NULL, iov, iov_count, rq_data_dir(rq)== READ);
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	if (bio->bi_size != len) {
+		bio_endio(bio, 0);
+		bio_unmap_user(bio);
+		return -EINVAL;
+	}
+
+	bio_get(bio);
+	blk_rq_bio_prep(q, rq, bio);
+	rq->buffer = rq->data = NULL;
+	return 0;
+}
+
+EXPORT_SYMBOL(blk_rq_map_user_iov);
+
+/**
+ * blk_rq_unmap_user - unmap a request with user data
+ * @bio:	       start of bio list
+ *
+ * Description:
+ *    Unmap a rq previously mapped by blk_rq_map_user(). The caller must
+ *    supply the original rq->bio from the blk_rq_map_user() return, since
+ *    the io completion may have changed rq->bio.
+ */
+int blk_rq_unmap_user(struct bio *bio)
+{
+	struct bio *mapped_bio;
+	int ret = 0, ret2;
+
+	while (bio) {
+		mapped_bio = bio;
+		if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
+			mapped_bio = bio->bi_private;
+
+		ret2 = __blk_rq_unmap_user(mapped_bio);
+		if (ret2 && !ret)
+			ret = ret2;
+
+		mapped_bio = bio;
+		bio = bio->bi_next;
+		bio_put(mapped_bio);
+	}
+
+	return ret;
+}
+
+EXPORT_SYMBOL(blk_rq_unmap_user);
+
+/**
+ * blk_rq_map_kern - map kernel data to a request, for REQ_BLOCK_PC usage
+ * @q:		request queue where request should be inserted
+ * @rq:		request to fill
+ * @kbuf:	the kernel buffer
+ * @len:	length of user data
+ * @gfp_mask:	memory allocation flags
+ */
+int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
+		    unsigned int len, gfp_t gfp_mask)
+{
+	struct bio *bio;
+
+	if (len > (q->max_hw_sectors << 9))
+		return -EINVAL;
+	if (!len || !kbuf)
+		return -EINVAL;
+
+	bio = bio_map_kern(q, kbuf, len, gfp_mask);
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	if (rq_data_dir(rq) == WRITE)
+		bio->bi_rw |= (1 << BIO_RW);
+
+	blk_rq_bio_prep(q, rq, bio);
+	blk_queue_bounce(q, &rq->bio);
+	rq->buffer = rq->data = NULL;
+	return 0;
+}
+
+EXPORT_SYMBOL(blk_rq_map_kern);

block/blk-settings.c

@@ -0,0 +1,402 @@
+/*
+ * Functions related to setting various queue properties from drivers
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
+
+#include "blk.h"
+
+unsigned long blk_max_low_pfn, blk_max_pfn;
+EXPORT_SYMBOL(blk_max_low_pfn);
+EXPORT_SYMBOL(blk_max_pfn);
+
+/**
+ * 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(struct request_queue *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(struct request_queue *q, merge_bvec_fn *mbfn)
+{
+	q->merge_bvec_fn = mbfn;
+}
+
+EXPORT_SYMBOL(blk_queue_merge_bvec);
+
+void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
+{
+	q->softirq_done_fn = fn;
+}
+
+EXPORT_SYMBOL(blk_queue_softirq_done);
+
+/**
+ * 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(struct request_queue * q, make_request_fn * mfn)
+{
+	/*
+	 * set defaults
+	 */
+	q->nr_requests = BLKDEV_MAX_RQ;
+	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
+	blk_queue_max_hw_segments(q, 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.capabilities = BDI_CAP_MAP_COPY;
+	blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
+	blk_queue_hardsect_size(q, 512);
+	blk_queue_dma_alignment(q, 511);
+	blk_queue_congestion_threshold(q);
+	q->nr_batching = BLK_BATCH_REQ;
+
+	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->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);
+}
+
+EXPORT_SYMBOL(blk_queue_make_request);
+
+/**
+ * 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.
+ **/
+void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
+{
+	unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
+	int dma = 0;
+
+	q->bounce_gfp = GFP_NOIO;
+#if BITS_PER_LONG == 64
+	/* Assume anything <= 4GB can be handled by IOMMU.
+	   Actually some IOMMUs can handle everything, but I don't
+	   know of a way to test this here. */
+	if (bounce_pfn < (min_t(u64,0xffffffff,BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
+		dma = 1;
+	q->bounce_pfn = max_low_pfn;
+#else
+	if (bounce_pfn < blk_max_low_pfn)
+		dma = 1;
+	q->bounce_pfn = bounce_pfn;
+#endif
+	if (dma) {
+		init_emergency_isa_pool();
+		q->bounce_gfp = GFP_NOIO | GFP_DMA;
+		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(struct request_queue *q, unsigned int 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);
+	}
+
+	if (BLK_DEF_MAX_SECTORS > max_sectors)
+		q->max_hw_sectors = q->max_sectors = max_sectors;
+	else {
+		q->max_sectors = BLK_DEF_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(struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *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(struct request_queue *t, struct request_queue *b)
+{
+	/* zero is "infinity" */
+	t->max_sectors = min_not_zero(t->max_sectors,b->max_sectors);
+	t->max_hw_sectors = min_not_zero(t->max_hw_sectors,b->max_hw_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);
+	if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
+		clear_bit(QUEUE_FLAG_CLUSTER, &t->queue_flags);
+}
+
+EXPORT_SYMBOL(blk_queue_stack_limits);
+
+/**
+ * blk_queue_dma_drain - Set up a drain buffer for excess dma.
+ *
+ * @q:  the request queue for the device
+ * @buf:	physically contiguous buffer
+ * @size:	size of the buffer in bytes
+ *
+ * Some devices have excess DMA problems and can't simply discard (or
+ * zero fill) the unwanted piece of the transfer.  They have to have a
+ * real area of memory to transfer it into.  The use case for this is
+ * ATAPI devices in DMA mode.  If the packet command causes a transfer
+ * bigger than the transfer size some HBAs will lock up if there
+ * aren't DMA elements to contain the excess transfer.  What this API
+ * does is adjust the queue so that the buf is always appended
+ * silently to the scatterlist.
+ *
+ * Note: This routine adjusts max_hw_segments to make room for
+ * appending the drain buffer.  If you call
+ * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
+ * calling this routine, you must set the limit to one fewer than your
+ * device can support otherwise there won't be room for the drain
+ * buffer.
+ */
+int blk_queue_dma_drain(struct request_queue *q, void *buf,
+				unsigned int size)
+{
+	if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
+		return -EINVAL;
+	/* make room for appending the drain */
+	--q->max_hw_segments;
+	--q->max_phys_segments;
+	q->dma_drain_buffer = buf;
+	q->dma_drain_size = size;
+
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(blk_queue_dma_drain);
+
+/**
+ * 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(struct request_queue *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(struct request_queue *q, int mask)
+{
+	q->dma_alignment = mask;
+}
+
+EXPORT_SYMBOL(blk_queue_dma_alignment);
+
+/**
+ * blk_queue_update_dma_alignment - update dma length and memory alignment
+ * @q:     the request queue for the device
+ * @mask:  alignment mask
+ *
+ * description:
+ *    update required memory and length aligment for direct dma transactions.
+ *    If the requested alignment is larger than the current alignment, then
+ *    the current queue alignment is updated to the new value, otherwise it
+ *    is left alone.  The design of this is to allow multiple objects
+ *    (driver, device, transport etc) to set their respective
+ *    alignments without having them interfere.
+ *
+ **/
+void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
+{
+	BUG_ON(mask > PAGE_SIZE);
+
+	if (mask > q->dma_alignment)
+		q->dma_alignment = mask;
+}
+
+EXPORT_SYMBOL(blk_queue_update_dma_alignment);
+
+int __init blk_settings_init(void)
+{
+	blk_max_low_pfn = max_low_pfn - 1;
+	blk_max_pfn = max_pfn - 1;
+	return 0;
+}
+subsys_initcall(blk_settings_init);

block/blk.h

@@ -1,11 +1,28 @@
 #ifndef BLK_INTERNAL_H
 #define BLK_INTERNAL_H
 
+/* 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
+
 extern struct kmem_cache *blk_requestq_cachep;
 extern struct kobj_type blk_queue_ktype;
 
+void rq_init(struct request_queue *q, struct request *rq);
+void init_request_from_bio(struct request *req, struct bio *bio);
+void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
+			struct bio *bio);
+int ll_back_merge_fn(struct request_queue *q, struct request *req,
+		     struct bio *bio);
 void __blk_queue_free_tags(struct request_queue *q);
 
+void blk_unplug_work(struct work_struct *work);
+void blk_unplug_timeout(unsigned long data);
+
+struct io_context *current_io_context(gfp_t gfp_flags, int node);
+
 void blk_queue_congestion_threshold(struct request_queue *q);
 
 /*