#include <linux/cpu.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
+#include <linux/scatterlist.h>
/*
* for max sense size
static void blk_unplug_work(struct work_struct *work);
static void blk_unplug_timeout(unsigned long data);
-static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io);
+static void drive_stat_acct(struct request *rq, int new_io);
static void init_request_from_bio(struct request *req, struct bio *bio);
-static int __make_request(request_queue_t *q, struct bio *bio);
+static int __make_request(struct request_queue *q, struct bio *bio);
static struct io_context *current_io_context(gfp_t gfp_flags, int node);
+static void blk_recalc_rq_segments(struct request *rq);
+static void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
+ struct bio *bio);
/*
* For the allocated request tables
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);
+ struct request_queue *q = bdev_get_queue(bdev);
if (q)
ret = &q->backing_dev_info;
* cdb from the request data for instance.
*
*/
-void blk_queue_prep_rq(request_queue_t *q, prep_rq_fn *pfn)
+void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
{
q->prep_rq_fn = pfn;
}
* 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)
+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(request_queue_t *q, softirq_done_fn *fn)
+void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
{
q->softirq_done_fn = fn;
}
* __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)
+void blk_queue_make_request(struct request_queue * q, make_request_fn * mfn)
{
/*
* set defaults
EXPORT_SYMBOL(blk_queue_make_request);
-static void rq_init(request_queue_t *q, struct request *rq)
+static void rq_init(struct request_queue *q, struct request *rq)
{
INIT_LIST_HEAD(&rq->queuelist);
INIT_LIST_HEAD(&rq->donelist);
rq->end_io = NULL;
rq->end_io_data = NULL;
rq->completion_data = NULL;
+ rq->next_rq = NULL;
}
/**
* feature should call this function and indicate so.
*
**/
-int blk_queue_ordered(request_queue_t *q, unsigned ordered,
+int blk_queue_ordered(struct request_queue *q, unsigned ordered,
prepare_flush_fn *prepare_flush_fn)
{
if (ordered & (QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH) &&
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);
-
/*
* Cache flushing for ordered writes handling
*/
-inline unsigned blk_ordered_cur_seq(request_queue_t *q)
+inline unsigned blk_ordered_cur_seq(struct request_queue *q)
{
if (!q->ordseq)
return 0;
unsigned blk_ordered_req_seq(struct request *rq)
{
- request_queue_t *q = rq->q;
+ struct request_queue *q = rq->q;
BUG_ON(q->ordseq == 0);
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;
return QUEUE_ORDSEQ_DONE;
}
-void blk_ordered_complete_seq(request_queue_t *q, unsigned seq, int error)
+void blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
{
struct request *rq;
int uptodate;
/*
* Okay, sequence complete.
*/
- rq = q->orig_bar_rq;
- uptodate = q->orderr ? q->orderr : 1;
+ uptodate = 1;
+ if (q->orderr)
+ uptodate = q->orderr;
q->ordseq = 0;
+ rq = q->orig_bar_rq;
end_that_request_first(rq, uptodate, rq->hard_nr_sectors);
end_that_request_last(rq, uptodate);
blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
}
-static void queue_flush(request_queue_t *q, unsigned which)
+static void queue_flush(struct request_queue *q, unsigned which)
{
struct request *rq;
rq_end_io_fn *end_io;
elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}
-static inline struct request *start_ordered(request_queue_t *q,
+static inline struct request *start_ordered(struct request_queue *q,
struct request *rq)
{
- q->bi_size = 0;
q->orderr = 0;
q->ordered = q->next_ordered;
q->ordseq |= QUEUE_ORDSEQ_STARTED;
rq_init(q, rq);
if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
rq->cmd_flags |= REQ_RW;
- rq->cmd_flags |= q->ordered & QUEUE_ORDERED_FUA ? REQ_FUA : 0;
+ 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);
* 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.
+ * 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)
+ if ((q->ordered & QUEUE_ORDERED_POSTFLUSH) && !blk_empty_barrier(rq))
queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
else
q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;
return rq;
}
-int blk_do_ordered(request_queue_t *q, struct request **rqp)
+int blk_do_ordered(struct request_queue *q, struct request **rqp)
{
struct request *rq = *rqp;
- int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
+ const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
if (!q->ordseq) {
if (!is_barrier)
return 1;
}
-static int flush_dry_bio_endio(struct bio *bio, unsigned int bytes, int error)
-{
- request_queue_t *q = bio->bi_private;
- struct bio_vec *bvec;
- int i;
-
- /*
- * This is dry run, restore bio_sector and size. We'll finish
- * this request again with the original bi_end_io after an
- * error occurs or post flush is complete.
- */
- q->bi_size += bytes;
-
- if (bio->bi_size)
- return 1;
-
- /* Rewind bvec's */
- bio->bi_idx = 0;
- bio_for_each_segment(bvec, bio, i) {
- bvec->bv_len += bvec->bv_offset;
- bvec->bv_offset = 0;
- }
-
- /* Reset bio */
- set_bit(BIO_UPTODATE, &bio->bi_flags);
- bio->bi_size = q->bi_size;
- bio->bi_sector -= (q->bi_size >> 9);
- q->bi_size = 0;
-
- return 0;
-}
-
-static int ordered_bio_endio(struct request *rq, struct bio *bio,
- unsigned int nbytes, int error)
+static void req_bio_endio(struct request *rq, struct bio *bio,
+ unsigned int nbytes, int error)
{
- request_queue_t *q = rq->q;
- bio_end_io_t *endio;
- void *private;
-
- if (&q->bar_rq != rq)
- return 0;
-
- /*
- * Okay, this is the barrier request in progress, dry finish it.
- */
- if (error && !q->orderr)
- q->orderr = error;
+ struct request_queue *q = rq->q;
- endio = bio->bi_end_io;
- private = bio->bi_private;
- bio->bi_end_io = flush_dry_bio_endio;
- bio->bi_private = q;
+ if (&q->bar_rq != rq) {
+ if (error)
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+ error = -EIO;
- bio_endio(bio, nbytes, error);
+ if (unlikely(nbytes > bio->bi_size)) {
+ printk("%s: want %u bytes done, only %u left\n",
+ __FUNCTION__, nbytes, bio->bi_size);
+ nbytes = bio->bi_size;
+ }
- bio->bi_end_io = endio;
- bio->bi_private = private;
+ bio->bi_size -= nbytes;
+ bio->bi_sector += (nbytes >> 9);
+ if (bio->bi_size == 0)
+ bio_endio(bio, error);
+ } else {
- return 1;
+ /*
+ * Okay, this is the barrier request in progress, just
+ * record the error;
+ */
+ if (error && !q->orderr)
+ q->orderr = error;
+ }
}
/**
* 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(request_queue_t *q, u64 dma_addr)
+void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
{
unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
int dma = 0;
* 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 int max_sectors)
+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);
* 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)
+void blk_queue_max_phys_segments(struct request_queue *q,
+ unsigned short max_segments)
{
if (!max_segments) {
max_segments = 1;
* 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)
+void blk_queue_max_hw_segments(struct request_queue *q,
+ unsigned short max_segments)
{
if (!max_segments) {
max_segments = 1;
* 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)
+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;
* 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)
+void blk_queue_hardsect_size(struct request_queue *q, unsigned short size)
{
q->hardsect_size = size;
}
* @t: the stacking driver (top)
* @b: the underlying device (bottom)
**/
-void blk_queue_stack_limits(request_queue_t *t, request_queue_t *b)
+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);
* @q: the request queue for the device
* @mask: the memory boundary mask
**/
-void blk_queue_segment_boundary(request_queue_t *q, unsigned long mask)
+void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
{
if (mask < PAGE_CACHE_SIZE - 1) {
mask = PAGE_CACHE_SIZE - 1;
* this is used when buiding direct io requests for the queue.
*
**/
-void blk_queue_dma_alignment(request_queue_t *q, int mask)
+void blk_queue_dma_alignment(struct request_queue *q, int mask)
{
q->dma_alignment = mask;
}
*
* no locks need be held.
**/
-struct request *blk_queue_find_tag(request_queue_t *q, int tag)
+struct request *blk_queue_find_tag(struct request_queue *q, int tag)
{
return blk_map_queue_find_tag(q->queue_tags, tag);
}
retval = atomic_dec_and_test(&bqt->refcnt);
if (retval) {
BUG_ON(bqt->busy);
- BUG_ON(!list_empty(&bqt->busy_list));
kfree(bqt->tag_index);
bqt->tag_index = NULL;
* blk_cleanup_queue() will take care of calling this function, if tagging
* has been used. So there's no need to call this directly.
**/
-static void __blk_queue_free_tags(request_queue_t *q)
+static void __blk_queue_free_tags(struct request_queue *q)
{
struct blk_queue_tag *bqt = q->queue_tags;
* This is used to disabled tagged queuing to a device, yet leave
* queue in function.
**/
-void blk_queue_free_tags(request_queue_t *q)
+void blk_queue_free_tags(struct request_queue *q)
{
clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_free_tags);
static int
-init_tag_map(request_queue_t *q, struct blk_queue_tag *tags, int depth)
+init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
{
struct request **tag_index;
unsigned long *tag_map;
if (init_tag_map(q, tags, depth))
goto fail;
- INIT_LIST_HEAD(&tags->busy_list);
tags->busy = 0;
atomic_set(&tags->refcnt, 1);
return tags;
* @depth: the maximum queue depth supported
* @tags: the tag to use
**/
-int blk_queue_init_tags(request_queue_t *q, int depth,
+int blk_queue_init_tags(struct request_queue *q, int depth,
struct blk_queue_tag *tags)
{
int rc;
*/
q->queue_tags = tags;
q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
+ INIT_LIST_HEAD(&q->tag_busy_list);
return 0;
fail:
kfree(tags);
* Notes:
* Must be called with the queue lock held.
**/
-int blk_queue_resize_tags(request_queue_t *q, int new_depth)
+int blk_queue_resize_tags(struct request_queue *q, int new_depth)
{
struct blk_queue_tag *bqt = q->queue_tags;
struct request **tag_index;
* Notes:
* queue lock must be held.
**/
-void blk_queue_end_tag(request_queue_t *q, struct request *rq)
+void blk_queue_end_tag(struct request_queue *q, struct request *rq)
{
struct blk_queue_tag *bqt = q->queue_tags;
int tag = rq->tag;
*/
return;
- if (unlikely(!__test_and_clear_bit(tag, bqt->tag_map))) {
- printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
- __FUNCTION__, tag);
- return;
- }
-
list_del_init(&rq->queuelist);
rq->cmd_flags &= ~REQ_QUEUED;
rq->tag = -1;
__FUNCTION__, tag);
bqt->tag_index[tag] = NULL;
+
+ if (unlikely(!test_bit(tag, bqt->tag_map))) {
+ printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
+ __FUNCTION__, tag);
+ return;
+ }
+ /*
+ * The tag_map bit acts as a lock for tag_index[bit], so we need
+ * unlock memory barrier semantics.
+ */
+ clear_bit_unlock(tag, bqt->tag_map);
bqt->busy--;
}
* Notes:
* queue lock must be held.
**/
-int blk_queue_start_tag(request_queue_t *q, struct request *rq)
+int blk_queue_start_tag(struct request_queue *q, struct request *rq)
{
struct blk_queue_tag *bqt = q->queue_tags;
int tag;
if (tag >= bqt->max_depth)
return 1;
- } while (test_and_set_bit(tag, bqt->tag_map));
+ } while (test_and_set_bit_lock(tag, bqt->tag_map));
+ /*
+ * We need lock ordering semantics given by test_and_set_bit_lock.
+ * See blk_queue_end_tag for details.
+ */
rq->cmd_flags |= REQ_QUEUED;
rq->tag = tag;
bqt->tag_index[tag] = rq;
blkdev_dequeue_request(rq);
- list_add(&rq->queuelist, &bqt->busy_list);
+ list_add(&rq->queuelist, &q->tag_busy_list);
bqt->busy++;
return 0;
}
* Notes:
* queue lock must be held.
**/
-void blk_queue_invalidate_tags(request_queue_t *q)
+void blk_queue_invalidate_tags(struct request_queue *q)
{
- struct blk_queue_tag *bqt = q->queue_tags;
struct list_head *tmp, *n;
struct request *rq;
- list_for_each_safe(tmp, n, &bqt->busy_list) {
+ list_for_each_safe(tmp, n, &q->tag_busy_list) {
rq = list_entry_rq(tmp);
if (rq->tag == -1) {
EXPORT_SYMBOL(blk_dump_rq_flags);
-void blk_recount_segments(request_queue_t *q, struct bio *bio)
+void blk_recount_segments(struct request_queue *q, struct bio *bio)
+{
+ struct request rq;
+ struct bio *nxt = bio->bi_next;
+ rq.q = q;
+ rq.bio = rq.biotail = bio;
+ bio->bi_next = NULL;
+ blk_recalc_rq_segments(&rq);
+ bio->bi_next = nxt;
+ bio->bi_phys_segments = rq.nr_phys_segments;
+ bio->bi_hw_segments = rq.nr_hw_segments;
+ bio->bi_flags |= (1 << BIO_SEG_VALID);
+}
+EXPORT_SYMBOL(blk_recount_segments);
+
+static void blk_recalc_rq_segments(struct request *rq)
{
+ int nr_phys_segs;
+ int nr_hw_segs;
+ unsigned int phys_size;
+ unsigned int hw_size;
struct bio_vec *bv, *bvprv = NULL;
- int i, nr_phys_segs, nr_hw_segs, seg_size, hw_seg_size, cluster;
+ int seg_size;
+ int hw_seg_size;
+ int cluster;
+ struct req_iterator iter;
int high, highprv = 1;
+ struct request_queue *q = rq->q;
- if (unlikely(!bio->bi_io_vec))
+ if (!rq->bio)
return;
cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
- hw_seg_size = seg_size = nr_phys_segs = nr_hw_segs = 0;
- bio_for_each_segment(bv, bio, i) {
+ hw_seg_size = seg_size = 0;
+ phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
+ rq_for_each_segment(bv, rq, iter) {
/*
* the trick here is making sure that a high page is never
* considered part of another segment, since that might
* change with the bounce page.
*/
- high = page_to_pfn(bv->bv_page) >= q->bounce_pfn;
+ high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
if (high || highprv)
goto new_hw_segment;
if (cluster) {
}
new_segment:
if (BIOVEC_VIRT_MERGEABLE(bvprv, bv) &&
- !BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len)) {
+ !BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
hw_seg_size += bv->bv_len;
- } else {
+ else {
new_hw_segment:
- if (hw_seg_size > bio->bi_hw_front_size)
- bio->bi_hw_front_size = hw_seg_size;
+ if (nr_hw_segs == 1 &&
+ hw_seg_size > rq->bio->bi_hw_front_size)
+ rq->bio->bi_hw_front_size = hw_seg_size;
hw_seg_size = BIOVEC_VIRT_START_SIZE(bv) + bv->bv_len;
nr_hw_segs++;
}
seg_size = bv->bv_len;
highprv = high;
}
- if (hw_seg_size > bio->bi_hw_back_size)
- bio->bi_hw_back_size = hw_seg_size;
- if (nr_hw_segs == 1 && hw_seg_size > bio->bi_hw_front_size)
- bio->bi_hw_front_size = hw_seg_size;
- bio->bi_phys_segments = nr_phys_segs;
- bio->bi_hw_segments = nr_hw_segs;
- bio->bi_flags |= (1 << BIO_SEG_VALID);
+
+ if (nr_hw_segs == 1 &&
+ hw_seg_size > rq->bio->bi_hw_front_size)
+ rq->bio->bi_hw_front_size = hw_seg_size;
+ if (hw_seg_size > rq->biotail->bi_hw_back_size)
+ rq->biotail->bi_hw_back_size = hw_seg_size;
+ rq->nr_phys_segments = nr_phys_segs;
+ rq->nr_hw_segments = nr_hw_segs;
}
-EXPORT_SYMBOL(blk_recount_segments);
-static int blk_phys_contig_segment(request_queue_t *q, struct bio *bio,
+static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
struct bio *nxt)
{
if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
return 0;
}
-static int blk_hw_contig_segment(request_queue_t *q, struct bio *bio,
+static int blk_hw_contig_segment(struct request_queue *q, struct bio *bio,
struct bio *nxt)
{
if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
if (unlikely(!bio_flagged(nxt, BIO_SEG_VALID)))
blk_recount_segments(q, nxt);
if (!BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)) ||
- BIOVEC_VIRT_OVERSIZE(bio->bi_hw_front_size + bio->bi_hw_back_size))
+ BIOVEC_VIRT_OVERSIZE(bio->bi_hw_back_size + nxt->bi_hw_front_size))
return 0;
- if (bio->bi_size + nxt->bi_size > q->max_segment_size)
+ if (bio->bi_hw_back_size + nxt->bi_hw_front_size > q->max_segment_size)
return 0;
return 1;
* map a request to scatterlist, return number of sg entries setup. Caller
* must make sure sg can hold rq->nr_phys_segments entries
*/
-int blk_rq_map_sg(request_queue_t *q, struct request *rq, struct scatterlist *sg)
+int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+ struct scatterlist *sglist)
{
struct bio_vec *bvec, *bvprv;
- struct bio *bio;
- int nsegs, i, cluster;
+ struct req_iterator iter;
+ struct scatterlist *sg;
+ int nsegs, cluster;
nsegs = 0;
cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
* for each bio in rq
*/
bvprv = NULL;
- rq_for_each_bio(bio, rq) {
- /*
- * for each segment in bio
- */
- bio_for_each_segment(bvec, bio, i) {
- int nbytes = bvec->bv_len;
+ sg = NULL;
+ rq_for_each_segment(bvec, rq, iter) {
+ int nbytes = bvec->bv_len;
- if (bvprv && cluster) {
- if (sg[nsegs - 1].length + nbytes > q->max_segment_size)
- goto new_segment;
+ if (bvprv && cluster) {
+ if (sg->length + nbytes > q->max_segment_size)
+ goto new_segment;
- if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
- goto new_segment;
- if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
- goto new_segment;
+ if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
+ goto new_segment;
+ if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
+ goto new_segment;
- sg[nsegs - 1].length += nbytes;
- } else {
+ sg->length += nbytes;
+ } else {
new_segment:
- memset(&sg[nsegs],0,sizeof(struct scatterlist));
- sg[nsegs].page = bvec->bv_page;
- sg[nsegs].length = nbytes;
- sg[nsegs].offset = bvec->bv_offset;
-
- nsegs++;
+ if (!sg)
+ sg = sglist;
+ else {
+ /*
+ * If the driver previously mapped a shorter
+ * list, we could see a termination bit
+ * prematurely unless it fully inits the sg
+ * table on each mapping. We KNOW that there
+ * must be more entries here or the driver
+ * would be buggy, so force clear the
+ * termination bit to avoid doing a full
+ * sg_init_table() in drivers for each command.
+ */
+ sg->page_link &= ~0x02;
+ sg = sg_next(sg);
}
- bvprv = bvec;
- } /* segments in bio */
- } /* bios in rq */
+
+ sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
+ nsegs++;
+ }
+ bvprv = bvec;
+ } /* segments in rq */
+
+ if (sg)
+ __sg_mark_end(sg);
return nsegs;
}
* specific ones if so desired
*/
-static inline int ll_new_mergeable(request_queue_t *q,
+static inline int ll_new_mergeable(struct request_queue *q,
struct request *req,
struct bio *bio)
{
return 1;
}
-static inline int ll_new_hw_segment(request_queue_t *q,
+static inline int ll_new_hw_segment(struct request_queue *q,
struct request *req,
struct bio *bio)
{
return 1;
}
-int ll_back_merge_fn(request_queue_t *q, struct request *req, struct bio *bio)
+static int ll_back_merge_fn(struct request_queue *q, struct request *req,
+ struct bio *bio)
{
unsigned short max_sectors;
int len;
return ll_new_hw_segment(q, req, bio);
}
-EXPORT_SYMBOL(ll_back_merge_fn);
-static int ll_front_merge_fn(request_queue_t *q, struct request *req,
+static int ll_front_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio)
{
unsigned short max_sectors;
return ll_new_hw_segment(q, req, bio);
}
-static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
+static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
struct request *next)
{
int total_phys_segments;
* This is called with interrupts off and no requests on the queue and
* with the queue lock held.
*/
-void blk_plug_device(request_queue_t *q)
+void blk_plug_device(struct request_queue *q)
{
WARN_ON(!irqs_disabled());
* remove the queue from the plugged list, if present. called with
* queue lock held and interrupts disabled.
*/
-int blk_remove_plug(request_queue_t *q)
+int blk_remove_plug(struct request_queue *q)
{
WARN_ON(!irqs_disabled());
/*
* remove the plug and let it rip..
*/
-void __generic_unplug_device(request_queue_t *q)
+void __generic_unplug_device(struct request_queue *q)
{
if (unlikely(blk_queue_stopped(q)))
return;
/**
* generic_unplug_device - fire a request queue
- * @q: The &request_queue_t in question
+ * @q: The &struct request_queue in question
*
* Description:
* Linux uses plugging to build bigger requests queues before letting
* gets unplugged, the request_fn defined for the queue is invoked and
* transfers started.
**/
-void generic_unplug_device(request_queue_t *q)
+void generic_unplug_device(struct request_queue *q)
{
spin_lock_irq(q->queue_lock);
__generic_unplug_device(q);
static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
struct page *page)
{
- request_queue_t *q = bdi->unplug_io_data;
+ struct request_queue *q = bdi->unplug_io_data;
/*
* devices don't necessarily have an ->unplug_fn defined
static void blk_unplug_work(struct work_struct *work)
{
- request_queue_t *q = container_of(work, request_queue_t, unplug_work);
+ struct request_queue *q =
+ container_of(work, struct request_queue, unplug_work);
blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
q->rq.count[READ] + q->rq.count[WRITE]);
static void blk_unplug_timeout(unsigned long data)
{
- request_queue_t *q = (request_queue_t *)data;
+ struct request_queue *q = (struct request_queue *)data;
blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL,
q->rq.count[READ] + q->rq.count[WRITE]);
/**
* blk_start_queue - restart a previously stopped queue
- * @q: The &request_queue_t in question
+ * @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(request_queue_t *q)
+void blk_start_queue(struct request_queue *q)
{
WARN_ON(!irqs_disabled());
/**
* blk_stop_queue - stop a queue
- * @q: The &request_queue_t in question
+ * @q: The &struct request_queue in question
*
* Description:
* The Linux block layer assumes that a block driver will consume all
* 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(request_queue_t *q)
+void blk_stop_queue(struct request_queue *q)
{
blk_remove_plug(q);
set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
* 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
- * the the callbacks might use. The caller must already have made sure
+ * 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.
*
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->unplug_timer);
- kblockd_flush();
+ kblockd_flush_work(&q->unplug_work);
}
EXPORT_SYMBOL(blk_sync_queue);
EXPORT_SYMBOL(blk_run_queue);
/**
- * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
+ * blk_cleanup_queue: - release a &struct request_queue when it is no longer needed
* @kobj: the kobj belonging of the request queue to be released
*
* Description:
**/
static void blk_release_queue(struct kobject *kobj)
{
- request_queue_t *q = container_of(kobj, struct request_queue, kobj);
+ struct request_queue *q =
+ container_of(kobj, struct request_queue, kobj);
struct request_list *rl = &q->rq;
blk_sync_queue(q);
blk_trace_shutdown(q);
+ bdi_destroy(&q->backing_dev_info);
kmem_cache_free(requestq_cachep, q);
}
-void blk_put_queue(request_queue_t *q)
+void blk_put_queue(struct request_queue *q)
{
kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);
-void blk_cleanup_queue(request_queue_t * q)
+void blk_cleanup_queue(struct request_queue * q)
{
mutex_lock(&q->sysfs_lock);
set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
EXPORT_SYMBOL(blk_cleanup_queue);
-static int blk_init_free_list(request_queue_t *q)
+static int blk_init_free_list(struct request_queue *q)
{
struct request_list *rl = &q->rq;
return 0;
}
-request_queue_t *blk_alloc_queue(gfp_t gfp_mask)
+struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
return blk_alloc_queue_node(gfp_mask, -1);
}
static struct kobj_type queue_ktype;
-request_queue_t *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
+struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
- request_queue_t *q;
+ struct request_queue *q;
+ int err;
- q = kmem_cache_alloc_node(requestq_cachep, gfp_mask, node_id);
+ q = kmem_cache_alloc_node(requestq_cachep,
+ gfp_mask | __GFP_ZERO, node_id);
if (!q)
return NULL;
- memset(q, 0, sizeof(*q));
+ q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
+ q->backing_dev_info.unplug_io_data = q;
+ err = bdi_init(&q->backing_dev_info);
+ if (err) {
+ kmem_cache_free(requestq_cachep, q);
+ return NULL;
+ }
+
init_timer(&q->unplug_timer);
- snprintf(q->kobj.name, KOBJ_NAME_LEN, "%s", "queue");
+ kobject_set_name(&q->kobj, "%s", "queue");
q->kobj.ktype = &queue_ktype;
kobject_init(&q->kobj);
- q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
- q->backing_dev_info.unplug_io_data = q;
-
mutex_init(&q->sysfs_lock);
return q;
* when the block device is deactivated (such as at module unload).
**/
-request_queue_t *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
+struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
{
return blk_init_queue_node(rfn, lock, -1);
}
EXPORT_SYMBOL(blk_init_queue);
-request_queue_t *
+struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
- request_queue_t *q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+ struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id);
if (!q)
return NULL;
}
EXPORT_SYMBOL(blk_init_queue_node);
-int blk_get_queue(request_queue_t *q)
+int blk_get_queue(struct request_queue *q)
{
if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
kobject_get(&q->kobj);
EXPORT_SYMBOL(blk_get_queue);
-static inline void blk_free_request(request_queue_t *q, struct request *rq)
+static inline void blk_free_request(struct request_queue *q, struct request *rq)
{
if (rq->cmd_flags & REQ_ELVPRIV)
elv_put_request(q, rq);
}
static struct request *
-blk_alloc_request(request_queue_t *q, int rw, int priv, gfp_t gfp_mask)
+blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
{
struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
* ioc_batching returns true if the ioc is a valid batching request and
* should be given priority access to a request.
*/
-static inline int ioc_batching(request_queue_t *q, struct io_context *ioc)
+static inline int ioc_batching(struct request_queue *q, struct io_context *ioc)
{
if (!ioc)
return 0;
* is the behaviour we want though - once it gets a wakeup it should be given
* a nice run.
*/
-static void ioc_set_batching(request_queue_t *q, struct io_context *ioc)
+static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
{
if (!ioc || ioc_batching(q, ioc))
return;
ioc->last_waited = jiffies;
}
-static void __freed_request(request_queue_t *q, int rw)
+static void __freed_request(struct request_queue *q, int rw)
{
struct request_list *rl = &q->rq;
* A request has just been released. Account for it, update the full and
* congestion status, wake up any waiters. Called under q->queue_lock.
*/
-static void freed_request(request_queue_t *q, int rw, int priv)
+static void freed_request(struct request_queue *q, int rw, int priv)
{
struct request_list *rl = &q->rq;
* Returns NULL on failure, with queue_lock held.
* Returns !NULL on success, with queue_lock *not held*.
*/
-static struct request *get_request(request_queue_t *q, int rw_flags,
+static struct request *get_request(struct request_queue *q, int rw_flags,
struct bio *bio, gfp_t gfp_mask)
{
struct request *rq = NULL;
*
* Called with q->queue_lock held, and returns with it unlocked.
*/
-static struct request *get_request_wait(request_queue_t *q, int rw_flags,
+static struct request *get_request_wait(struct request_queue *q, int rw_flags,
struct bio *bio)
{
const int rw = rw_flags & 0x01;
return rq;
}
-struct request *blk_get_request(request_queue_t *q, int rw, gfp_t gfp_mask)
+struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
{
struct request *rq;
*
* The queue lock must be held with interrupts disabled.
*/
-void blk_start_queueing(request_queue_t *q)
+void blk_start_queueing(struct request_queue *q)
{
if (!blk_queue_plugged(q))
q->request_fn(q);
* more, when that condition happens we need to put the request back
* on the queue. Must be called with queue lock held.
*/
-void blk_requeue_request(request_queue_t *q, struct request *rq)
+void blk_requeue_request(struct request_queue *q, struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
* of the queue for things like a QUEUE_FULL message from a device, or a
* host that is unable to accept a particular command.
*/
-void blk_insert_request(request_queue_t *q, struct request *rq,
+void blk_insert_request(struct request_queue *q, struct request *rq,
int at_head, void *data)
{
int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
if (blk_rq_tagged(rq))
blk_queue_end_tag(q, rq);
- drive_stat_acct(rq, rq->nr_sectors, 1);
+ drive_stat_acct(rq, 1);
__elv_add_request(q, rq, where, 0);
blk_start_queueing(q);
spin_unlock_irqrestore(q->queue_lock, flags);
return ret;
}
-static int __blk_rq_map_user(request_queue_t *q, struct request *rq,
+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_map_user(struct request_queue *q, struct request *rq,
void __user *ubuf, unsigned int len)
{
unsigned long uaddr;
*/
bio_get(bio);
- if (!rq->bio)
- blk_rq_bio_prep(q, rq, bio);
- else if (!ll_back_merge_fn(q, rq, bio)) {
- ret = -EINVAL;
- goto unmap_bio;
- } else {
- rq->biotail->bi_next = bio;
- rq->biotail = bio;
-
- rq->data_len += bio->bi_size;
- }
-
- return bio->bi_size;
+ ret = blk_rq_append_bio(q, rq, bio);
+ if (!ret)
+ return bio->bi_size;
-unmap_bio:
/* if it was boucned we must call the end io function */
- bio_endio(bio, bio->bi_size, 0);
+ bio_endio(bio, 0);
__blk_rq_unmap_user(orig_bio);
bio_put(bio);
return ret;
* original bio must be passed back in to blk_rq_unmap_user() for proper
* unmapping.
*/
-int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
- unsigned long len)
+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;
* original bio must be passed back in to blk_rq_unmap_user() for proper
* unmapping.
*/
-int blk_rq_map_user_iov(request_queue_t *q, struct request *rq,
+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;
return PTR_ERR(bio);
if (bio->bi_size != len) {
- bio_endio(bio, bio->bi_size, 0);
+ bio_endio(bio, 0);
bio_unmap_user(bio);
return -EINVAL;
}
* @len: length of user data
* @gfp_mask: memory allocation flags
*/
-int blk_rq_map_kern(request_queue_t *q, struct request *rq, void *kbuf,
+int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
unsigned int len, gfp_t gfp_mask)
{
struct bio *bio;
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;
}
* 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(request_queue_t *q, struct gendisk *bd_disk,
+void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
struct request *rq, int at_head,
rq_end_io_fn *done)
{
* Insert a fully prepared request at the back of the io scheduler queue
* for execution and wait for completion.
*/
-int blk_execute_rq(request_queue_t *q, struct gendisk *bd_disk,
+int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
struct request *rq, int at_head)
{
DECLARE_COMPLETION_ONSTACK(wait);
EXPORT_SYMBOL(blk_execute_rq);
+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
*/
int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
{
- request_queue_t *q;
+ 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;
- if (!q->issue_flush_fn)
- return -EOPNOTSUPP;
- return q->issue_flush_fn(q, bdev->bd_disk, error_sector);
+ 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);
-static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io)
+static void drive_stat_acct(struct request *rq, int new_io)
{
int rw = rq_data_dir(rq);
* queue lock is held and interrupts disabled, as we muck with the
* request queue list.
*/
-static inline void add_request(request_queue_t * q, struct request * req)
+static inline void add_request(struct request_queue * q, struct request * req)
{
- drive_stat_acct(req, req->nr_sectors, 1);
+ drive_stat_acct(req, 1);
/*
* elevator indicated where it wants this request to be
/*
* queue lock must be held
*/
-void __blk_put_request(request_queue_t *q, struct request *req)
+void __blk_put_request(struct request_queue *q, struct request *req)
{
if (unlikely(!q))
return;
void blk_put_request(struct request *req)
{
unsigned long flags;
- request_queue_t *q = req->q;
+ struct request_queue *q = req->q;
/*
* Gee, IDE calls in w/ NULL q. Fix IDE and remove the
/*
* Has to be called with the request spinlock acquired
*/
-static int attempt_merge(request_queue_t *q, struct request *req,
+static int attempt_merge(struct request_queue *q, struct request *req,
struct request *next)
{
if (!rq_mergeable(req) || !rq_mergeable(next))
return 1;
}
-static inline int attempt_back_merge(request_queue_t *q, struct request *rq)
+static inline int attempt_back_merge(struct request_queue *q,
+ struct request *rq)
{
struct request *next = elv_latter_request(q, rq);
return 0;
}
-static inline int attempt_front_merge(request_queue_t *q, struct request *rq)
+static inline int attempt_front_merge(struct request_queue *q,
+ struct request *rq)
{
struct request *prev = elv_former_request(q, rq);
req->errors = 0;
req->hard_sector = req->sector = bio->bi_sector;
- req->hard_nr_sectors = req->nr_sectors = bio_sectors(bio);
- req->current_nr_sectors = req->hard_cur_sectors = bio_cur_sectors(bio);
- req->nr_phys_segments = bio_phys_segments(req->q, bio);
- req->nr_hw_segments = bio_hw_segments(req->q, bio);
- req->buffer = bio_data(bio); /* see ->buffer comment above */
- req->bio = req->biotail = bio;
req->ioprio = bio_prio(bio);
- req->rq_disk = bio->bi_bdev->bd_disk;
req->start_time = jiffies;
+ blk_rq_bio_prep(req->q, req, bio);
}
-static int __make_request(request_queue_t *q, struct bio *bio)
+static int __make_request(struct request_queue *q, struct bio *bio)
{
struct request *req;
int el_ret, nr_sectors, barrier, err;
req->biotail = bio;
req->nr_sectors = req->hard_nr_sectors += nr_sectors;
req->ioprio = ioprio_best(req->ioprio, prio);
- drive_stat_acct(req, nr_sectors, 0);
+ drive_stat_acct(req, 0);
if (!attempt_back_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out;
req->sector = req->hard_sector = bio->bi_sector;
req->nr_sectors = req->hard_nr_sectors += nr_sectors;
req->ioprio = ioprio_best(req->ioprio, prio);
- drive_stat_acct(req, nr_sectors, 0);
+ drive_stat_acct(req, 0);
if (!attempt_front_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out;
return 0;
end_io:
- bio_endio(bio, nr_sectors << 9, err);
+ bio_endio(bio, err);
return 0;
}
{
struct block_device *bdev = bio->bi_bdev;
- if (bdev != bdev->bd_contains) {
+ if (bio_sectors(bio) && bdev != bdev->bd_contains) {
struct hd_struct *p = bdev->bd_part;
const int rw = bio_data_dir(bio);
bio->bi_sector += p->start_sect;
bio->bi_bdev = bdev->bd_contains;
+
+ blk_add_trace_remap(bdev_get_queue(bio->bi_bdev), bio,
+ bdev->bd_dev, bio->bi_sector,
+ bio->bi_sector - p->start_sect);
}
}
#endif /* CONFIG_FAIL_MAKE_REQUEST */
+/*
+ * Check whether this bio extends beyond the end of the device.
+ */
+static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
+{
+ sector_t maxsector;
+
+ if (!nr_sectors)
+ return 0;
+
+ /* Test device or partition size, when known. */
+ maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
+ if (maxsector) {
+ sector_t sector = bio->bi_sector;
+
+ if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
+ /*
+ * This may well happen - the kernel calls bread()
+ * without checking the size of the device, e.g., when
+ * mounting a device.
+ */
+ handle_bad_sector(bio);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
/**
* generic_make_request: hand a buffer to its device driver for I/O
* @bio: The bio describing the location in memory and on the device.
* bi_sector for remaps as it sees fit. So the values of these fields
* should NOT be depended on after the call to generic_make_request.
*/
-void generic_make_request(struct bio *bio)
+static inline void __generic_make_request(struct bio *bio)
{
- request_queue_t *q;
- sector_t maxsector;
+ struct request_queue *q;
sector_t old_sector;
int ret, nr_sectors = bio_sectors(bio);
dev_t old_dev;
might_sleep();
- /* Test device or partition size, when known. */
- maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
- if (maxsector) {
- sector_t sector = bio->bi_sector;
- if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
- /*
- * This may well happen - the kernel calls bread()
- * without checking the size of the device, e.g., when
- * mounting a device.
- */
- handle_bad_sector(bio);
- goto end_io;
- }
- }
+ if (bio_check_eod(bio, nr_sectors))
+ goto end_io;
/*
* Resolve the mapping until finished. (drivers are
bdevname(bio->bi_bdev, b),
(long long) bio->bi_sector);
end_io:
- bio_endio(bio, bio->bi_size, -EIO);
+ bio_endio(bio, -EIO);
break;
}
- if (unlikely(bio_sectors(bio) > q->max_hw_sectors)) {
+ if (unlikely(nr_sectors > q->max_hw_sectors)) {
printk("bio too big device %s (%u > %u)\n",
bdevname(bio->bi_bdev, b),
bio_sectors(bio),
blk_partition_remap(bio);
if (old_sector != -1)
- blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
+ blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
old_sector);
blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
old_sector = bio->bi_sector;
old_dev = bio->bi_bdev->bd_dev;
- maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
- if (maxsector) {
- sector_t sector = bio->bi_sector;
-
- if (maxsector < nr_sectors ||
- maxsector - nr_sectors < sector) {
- /*
- * This may well happen - partitions are not
- * checked to make sure they are within the size
- * of the whole device.
- */
- handle_bad_sector(bio);
- goto end_io;
- }
- }
+ if (bio_check_eod(bio, nr_sectors))
+ goto end_io;
ret = q->make_request_fn(q, bio);
} while (ret);
}
+/*
+ * We only want one ->make_request_fn to be active at a time,
+ * else stack usage with stacked devices could be a problem.
+ * So use current->bio_{list,tail} to keep a list of requests
+ * submited by a make_request_fn function.
+ * current->bio_tail is also used as a flag to say if
+ * generic_make_request is currently active in this task or not.
+ * If it is NULL, then no make_request is active. If it is non-NULL,
+ * then a make_request is active, and new requests should be added
+ * at the tail
+ */
+void generic_make_request(struct bio *bio)
+{
+ if (current->bio_tail) {
+ /* make_request is active */
+ *(current->bio_tail) = bio;
+ bio->bi_next = NULL;
+ current->bio_tail = &bio->bi_next;
+ return;
+ }
+ /* following loop may be a bit non-obvious, and so deserves some
+ * explanation.
+ * Before entering the loop, bio->bi_next is NULL (as all callers
+ * ensure that) so we have a list with a single bio.
+ * We pretend that we have just taken it off a longer list, so
+ * we assign bio_list to the next (which is NULL) and bio_tail
+ * to &bio_list, thus initialising the bio_list of new bios to be
+ * added. __generic_make_request may indeed add some more bios
+ * through a recursive call to generic_make_request. If it
+ * did, we find a non-NULL value in bio_list and re-enter the loop
+ * from the top. In this case we really did just take the bio
+ * of the top of the list (no pretending) and so fixup bio_list and
+ * bio_tail or bi_next, and call into __generic_make_request again.
+ *
+ * The loop was structured like this to make only one call to
+ * __generic_make_request (which is important as it is large and
+ * inlined) and to keep the structure simple.
+ */
+ BUG_ON(bio->bi_next);
+ do {
+ current->bio_list = bio->bi_next;
+ if (bio->bi_next == NULL)
+ current->bio_tail = ¤t->bio_list;
+ else
+ bio->bi_next = NULL;
+ __generic_make_request(bio);
+ bio = current->bio_list;
+ } while (bio);
+ current->bio_tail = NULL; /* deactivate */
+}
+
EXPORT_SYMBOL(generic_make_request);
/**
{
int count = bio_sectors(bio);
- BIO_BUG_ON(!bio->bi_size);
- BIO_BUG_ON(!bio->bi_io_vec);
bio->bi_rw |= rw;
- if (rw & WRITE) {
- count_vm_events(PGPGOUT, count);
- } else {
- task_io_account_read(bio->bi_size);
- count_vm_events(PGPGIN, count);
- }
-
- if (unlikely(block_dump)) {
- char b[BDEVNAME_SIZE];
- printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
- current->comm, current->pid,
- (rw & WRITE) ? "WRITE" : "READ",
- (unsigned long long)bio->bi_sector,
- bdevname(bio->bi_bdev,b));
- }
- generic_make_request(bio);
-}
+ /*
+ * If it's a regular read/write or a barrier with data attached,
+ * go through the normal accounting stuff before submission.
+ */
+ if (!bio_empty_barrier(bio)) {
-EXPORT_SYMBOL(submit_bio);
+ BIO_BUG_ON(!bio->bi_size);
+ BIO_BUG_ON(!bio->bi_io_vec);
-static void blk_recalc_rq_segments(struct request *rq)
-{
- struct bio *bio, *prevbio = NULL;
- int nr_phys_segs, nr_hw_segs;
- unsigned int phys_size, hw_size;
- request_queue_t *q = rq->q;
-
- if (!rq->bio)
- return;
+ if (rw & WRITE) {
+ count_vm_events(PGPGOUT, count);
+ } else {
+ task_io_account_read(bio->bi_size);
+ count_vm_events(PGPGIN, count);
+ }
- phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
- rq_for_each_bio(bio, rq) {
- /* Force bio hw/phys segs to be recalculated. */
- bio->bi_flags &= ~(1 << BIO_SEG_VALID);
-
- nr_phys_segs += bio_phys_segments(q, bio);
- nr_hw_segs += bio_hw_segments(q, bio);
- if (prevbio) {
- int pseg = phys_size + prevbio->bi_size + bio->bi_size;
- int hseg = hw_size + prevbio->bi_size + bio->bi_size;
-
- if (blk_phys_contig_segment(q, prevbio, bio) &&
- pseg <= q->max_segment_size) {
- nr_phys_segs--;
- phys_size += prevbio->bi_size + bio->bi_size;
- } else
- phys_size = 0;
-
- if (blk_hw_contig_segment(q, prevbio, bio) &&
- hseg <= q->max_segment_size) {
- nr_hw_segs--;
- hw_size += prevbio->bi_size + bio->bi_size;
- } else
- hw_size = 0;
+ if (unlikely(block_dump)) {
+ char b[BDEVNAME_SIZE];
+ printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
+ current->comm, task_pid_nr(current),
+ (rw & WRITE) ? "WRITE" : "READ",
+ (unsigned long long)bio->bi_sector,
+ bdevname(bio->bi_bdev,b));
}
- prevbio = bio;
}
- rq->nr_phys_segments = nr_phys_segs;
- rq->nr_hw_segments = nr_hw_segs;
+ generic_make_request(bio);
}
+EXPORT_SYMBOL(submit_bio);
+
static void blk_recalc_rq_sectors(struct request *rq, int nsect)
{
if (blk_fs_request(rq)) {
while ((bio = req->bio) != NULL) {
int nbytes;
+ /*
+ * For an empty barrier request, the low level driver must
+ * store a potential error location in ->sector. We pass
+ * that back up in ->bi_sector.
+ */
+ if (blk_empty_barrier(req))
+ bio->bi_sector = req->sector;
+
if (nr_bytes >= bio->bi_size) {
req->bio = bio->bi_next;
nbytes = bio->bi_size;
- if (!ordered_bio_endio(req, bio, nbytes, error))
- bio_endio(bio, nbytes, error);
+ req_bio_endio(req, bio, nbytes, error);
next_idx = 0;
bio_nbytes = 0;
} else {
* if the request wasn't completed, update state
*/
if (bio_nbytes) {
- if (!ordered_bio_endio(req, bio, bio_nbytes, error))
- bio_endio(bio, bio_nbytes, error);
+ req_bio_endio(req, bio, bio_nbytes, error);
bio->bi_idx += next_idx;
bio_iovec(bio)->bv_offset += nr_bytes;
bio_iovec(bio)->bv_len -= nr_bytes;
}
}
-static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
+static int __cpuinit blk_cpu_notify(struct notifier_block *self, unsigned long action,
void *hcpu)
{
/*
* If a CPU goes away, splice its entries to the current CPU
* and trigger a run of the softirq
*/
- if (action == CPU_DEAD) {
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
int cpu = (unsigned long) hcpu;
local_irq_disable();
}
-static struct notifier_block __devinitdata blk_cpu_notifier = {
+static struct notifier_block blk_cpu_notifier __cpuinitdata = {
.notifier_call = blk_cpu_notify,
};
* Description:
* Ends all I/O on a request. It does not handle partial completions,
* unless the driver actually implements this in its completion callback
- * through requeueing. Theh actual completion happens out-of-order,
+ * through requeueing. The actual completion happens out-of-order,
* through a softirq handler. The user must have registered a completion
* callback through blk_queue_softirq_done().
**/
EXPORT_SYMBOL(end_that_request_last);
-void end_request(struct request *req, int uptodate)
+static inline void __end_request(struct request *rq, int uptodate,
+ unsigned int nr_bytes, int dequeue)
{
- if (!end_that_request_first(req, uptodate, req->hard_cur_sectors)) {
- add_disk_randomness(req->rq_disk);
- blkdev_dequeue_request(req);
- end_that_request_last(req, uptodate);
+ if (!end_that_request_chunk(rq, uptodate, nr_bytes)) {
+ if (dequeue)
+ blkdev_dequeue_request(rq);
+ add_disk_randomness(rq->rq_disk);
+ end_that_request_last(rq, uptodate);
}
}
+static unsigned int rq_byte_size(struct request *rq)
+{
+ if (blk_fs_request(rq))
+ return rq->hard_nr_sectors << 9;
+
+ return rq->data_len;
+}
+
+/**
+ * end_queued_request - end all I/O on a queued request
+ * @rq: the request being processed
+ * @uptodate: error value or 0/1 uptodate flag
+ *
+ * Description:
+ * Ends all I/O on a request, and removes it from the block layer queues.
+ * Not suitable for normal IO completion, unless the driver still has
+ * the request attached to the block layer.
+ *
+ **/
+void end_queued_request(struct request *rq, int uptodate)
+{
+ __end_request(rq, uptodate, rq_byte_size(rq), 1);
+}
+EXPORT_SYMBOL(end_queued_request);
+
+/**
+ * end_dequeued_request - end all I/O on a dequeued request
+ * @rq: the request being processed
+ * @uptodate: error value or 0/1 uptodate flag
+ *
+ * Description:
+ * Ends all I/O on a request. The request must already have been
+ * dequeued using blkdev_dequeue_request(), as is normally the case
+ * for most drivers.
+ *
+ **/
+void end_dequeued_request(struct request *rq, int uptodate)
+{
+ __end_request(rq, uptodate, rq_byte_size(rq), 0);
+}
+EXPORT_SYMBOL(end_dequeued_request);
+
+
+/**
+ * end_request - end I/O on the current segment of the request
+ * @req: the request being processed
+ * @uptodate: error value or 0/1 uptodate flag
+ *
+ * Description:
+ * Ends I/O on the current segment of a request. If that is the only
+ * remaining segment, the request is also completed and freed.
+ *
+ * This is a remnant of how older block drivers handled IO completions.
+ * Modern drivers typically end IO on the full request in one go, unless
+ * they have a residual value to account for. For that case this function
+ * isn't really useful, unless the residual just happens to be the
+ * full current segment. In other words, don't use this function in new
+ * code. Either use end_request_completely(), or the
+ * end_that_request_chunk() (along with end_that_request_last()) for
+ * partial completions.
+ *
+ **/
+void end_request(struct request *req, int uptodate)
+{
+ __end_request(req, uptodate, req->hard_cur_sectors << 9, 1);
+}
EXPORT_SYMBOL(end_request);
-void blk_rq_bio_prep(request_queue_t *q, struct request *rq, struct bio *bio)
+static void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
+ struct bio *bio)
{
/* first two bits are identical in rq->cmd_flags and bio->bi_rw */
rq->cmd_flags |= (bio->bi_rw & 3);
rq->data_len = bio->bi_size;
rq->bio = rq->biotail = bio;
-}
-EXPORT_SYMBOL(blk_rq_bio_prep);
+ if (bio->bi_bdev)
+ rq->rq_disk = bio->bi_bdev->bd_disk;
+}
int kblockd_schedule_work(struct work_struct *work)
{
EXPORT_SYMBOL(kblockd_schedule_work);
-void kblockd_flush(void)
+void kblockd_flush_work(struct work_struct *work)
{
- flush_workqueue(kblockd_workqueue);
+ cancel_work_sync(work);
}
-EXPORT_SYMBOL(kblockd_flush);
+EXPORT_SYMBOL(kblockd_flush_work);
int __init blk_dev_init(void)
{
panic("Failed to create kblockd\n");
request_cachep = kmem_cache_create("blkdev_requests",
- sizeof(struct request), 0, SLAB_PANIC, NULL, NULL);
+ sizeof(struct request), 0, SLAB_PANIC, NULL);
requestq_cachep = kmem_cache_create("blkdev_queue",
- sizeof(request_queue_t), 0, SLAB_PANIC, NULL, NULL);
+ sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
iocontext_cachep = kmem_cache_create("blkdev_ioc",
- sizeof(struct io_context), 0, SLAB_PANIC, NULL, NULL);
+ sizeof(struct io_context), 0, SLAB_PANIC, NULL);
for_each_possible_cpu(i)
INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
open_softirq(BLOCK_SOFTIRQ, blk_done_softirq, NULL);
register_hotcpu_notifier(&blk_cpu_notifier);
- blk_max_low_pfn = max_low_pfn;
- blk_max_pfn = max_pfn;
+ blk_max_low_pfn = max_low_pfn - 1;
+ blk_max_pfn = max_pfn - 1;
return 0;
}
ret->nr_batch_requests = 0; /* because this is 0 */
ret->aic = NULL;
ret->cic_root.rb_node = NULL;
+ ret->ioc_data = NULL;
/* make sure set_task_ioprio() sees the settings above */
smp_wmb();
tsk->io_context = ret;
return ret;
}
-EXPORT_SYMBOL(current_io_context);
/*
* If the current task has no IO context then create one and initialise it.
max_hw_sectors_kb = q->max_hw_sectors >> 1,
page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
- int ra_kb;
if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
return -EINVAL;
* values synchronously:
*/
spin_lock_irq(q->queue_lock);
- /*
- * Trim readahead window as well, if necessary:
- */
- ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
- if (ra_kb > max_sectors_kb)
- q->backing_dev_info.ra_pages =
- max_sectors_kb >> (PAGE_CACHE_SHIFT - 10);
-
q->max_sectors = max_sectors_kb << 1;
spin_unlock_irq(q->queue_lock);
return queue_var_show(max_hw_sectors_kb, (page));
}
+static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
+{
+ return queue_var_show(q->max_phys_segments, page);
+}
+
+static ssize_t queue_max_segments_store(struct request_queue *q,
+ const char *page, size_t count)
+{
+ unsigned long segments;
+ ssize_t ret = queue_var_store(&segments, page, count);
+
+ spin_lock_irq(q->queue_lock);
+ q->max_phys_segments = segments;
+ spin_unlock_irq(q->queue_lock);
+ return ret;
+}
static struct queue_sysfs_entry queue_requests_entry = {
.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
.show = queue_requests_show,
.show = queue_max_hw_sectors_show,
};
+static struct queue_sysfs_entry queue_max_segments_entry = {
+ .attr = {.name = "max_segments", .mode = S_IRUGO | S_IWUSR },
+ .show = queue_max_segments_show,
+ .store = queue_max_segments_store,
+};
+
static struct queue_sysfs_entry queue_iosched_entry = {
.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
.show = elv_iosched_show,
&queue_ra_entry.attr,
&queue_max_hw_sectors_entry.attr,
&queue_max_sectors_entry.attr,
+ &queue_max_segments_entry.attr,
&queue_iosched_entry.attr,
NULL,
};
queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
struct queue_sysfs_entry *entry = to_queue(attr);
- request_queue_t *q = container_of(kobj, struct request_queue, kobj);
+ struct request_queue *q =
+ container_of(kobj, struct request_queue, kobj);
ssize_t res;
if (!entry->show)
const char *page, size_t length)
{
struct queue_sysfs_entry *entry = to_queue(attr);
- request_queue_t *q = container_of(kobj, struct request_queue, kobj);
+ struct request_queue *q = container_of(kobj, struct request_queue, kobj);
ssize_t res;
{
int ret;
- request_queue_t *q = disk->queue;
+ struct request_queue *q = disk->queue;
if (!q || !q->request_fn)
return -ENXIO;
void blk_unregister_queue(struct gendisk *disk)
{
- request_queue_t *q = disk->queue;
+ struct request_queue *q = disk->queue;
if (q && q->request_fn) {
elv_unregister_queue(q);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff