/*
* This handles all read/write requests to block devices
*/
-#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
-#include <linux/blkdev.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/blktrace_api.h>
/*
* for max sense size
static void drive_stat_acct(struct request *rq, int nr_sectors, 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 struct io_context *current_io_context(gfp_t gfp_flags, int node);
/*
* For the allocated request tables
/*
* Controlling structure to kblockd
*/
-static struct workqueue_struct *kblockd_workqueue;
+static struct workqueue_struct *kblockd_workqueue;
unsigned long blk_max_low_pfn, blk_max_pfn;
EXPORT_SYMBOL(blk_max_low_pfn);
EXPORT_SYMBOL(blk_max_pfn);
+static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+
/* Amount of time in which a process may batch requests */
#define BLK_BATCH_TIME (HZ/50UL)
EXPORT_SYMBOL(blk_queue_merge_bvec);
+void blk_queue_softirq_done(request_queue_t *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
EXPORT_SYMBOL(blk_queue_make_request);
-static inline void rq_init(request_queue_t *q, struct request *rq)
+static void rq_init(request_queue_t *q, struct request *rq)
{
INIT_LIST_HEAD(&rq->queuelist);
+ INIT_LIST_HEAD(&rq->donelist);
rq->errors = 0;
- rq->rq_status = RQ_ACTIVE;
rq->bio = rq->biotail = NULL;
+ INIT_HLIST_NODE(&rq->hash);
+ RB_CLEAR_NODE(&rq->rb_node);
rq->ioprio = 0;
rq->buffer = NULL;
rq->ref_count = 1;
rq->q = q;
- rq->waiting = NULL;
rq->special = NULL;
rq->data_len = 0;
rq->data = NULL;
rq->sense = NULL;
rq->end_io = NULL;
rq->end_io_data = NULL;
+ rq->completion_data = NULL;
}
/**
* blk_queue_ordered - does this queue support ordered writes
- * @q: the request queue
- * @flag: see below
+ * @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
* feature should call this function and indicate so.
*
**/
-void blk_queue_ordered(request_queue_t *q, int flag)
-{
- switch (flag) {
- case QUEUE_ORDERED_NONE:
- if (q->flush_rq)
- kmem_cache_free(request_cachep, q->flush_rq);
- q->flush_rq = NULL;
- q->ordered = flag;
- break;
- case QUEUE_ORDERED_TAG:
- q->ordered = flag;
- break;
- case QUEUE_ORDERED_FLUSH:
- q->ordered = flag;
- if (!q->flush_rq)
- q->flush_rq = kmem_cache_alloc(request_cachep,
- GFP_KERNEL);
- break;
- default:
- printk("blk_queue_ordered: bad value %d\n", flag);
- break;
+int blk_queue_ordered(request_queue_t *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
*/
-static void blk_pre_flush_end_io(struct request *flush_rq, int error)
+inline unsigned blk_ordered_cur_seq(request_queue_t *q)
{
- struct request *rq = flush_rq->end_io_data;
- request_queue_t *q = rq->q;
-
- elv_completed_request(q, flush_rq);
-
- rq->flags |= REQ_BAR_PREFLUSH;
-
- if (!flush_rq->errors)
- elv_requeue_request(q, rq);
- else {
- q->end_flush_fn(q, flush_rq);
- clear_bit(QUEUE_FLAG_FLUSH, &q->queue_flags);
- q->request_fn(q);
- }
+ if (!q->ordseq)
+ return 0;
+ return 1 << ffz(q->ordseq);
}
-static void blk_post_flush_end_io(struct request *flush_rq, int error)
+unsigned blk_ordered_req_seq(struct request *rq)
{
- struct request *rq = flush_rq->end_io_data;
request_queue_t *q = rq->q;
- elv_completed_request(q, flush_rq);
+ BUG_ON(q->ordseq == 0);
- rq->flags |= REQ_BAR_POSTFLUSH;
+ 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;
- q->end_flush_fn(q, flush_rq);
- clear_bit(QUEUE_FLAG_FLUSH, &q->queue_flags);
- q->request_fn(q);
+ 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;
}
-struct request *blk_start_pre_flush(request_queue_t *q, struct request *rq)
+void blk_ordered_complete_seq(request_queue_t *q, unsigned seq, int error)
{
- struct request *flush_rq = q->flush_rq;
+ struct request *rq;
+ int uptodate;
- BUG_ON(!blk_barrier_rq(rq));
+ if (error && !q->orderr)
+ q->orderr = error;
- if (test_and_set_bit(QUEUE_FLAG_FLUSH, &q->queue_flags))
- return NULL;
+ BUG_ON(q->ordseq & seq);
+ q->ordseq |= seq;
- rq_init(q, flush_rq);
- flush_rq->elevator_private = NULL;
- flush_rq->flags = REQ_BAR_FLUSH;
- flush_rq->rq_disk = rq->rq_disk;
- flush_rq->rl = NULL;
-
- /*
- * prepare_flush returns 0 if no flush is needed, just mark both
- * pre and post flush as done in that case
- */
- if (!q->prepare_flush_fn(q, flush_rq)) {
- rq->flags |= REQ_BAR_PREFLUSH | REQ_BAR_POSTFLUSH;
- clear_bit(QUEUE_FLAG_FLUSH, &q->queue_flags);
- return rq;
- }
+ if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
+ return;
/*
- * some drivers dequeue requests right away, some only after io
- * completion. make sure the request is dequeued.
+ * Okay, sequence complete.
*/
- if (!list_empty(&rq->queuelist))
- blkdev_dequeue_request(rq);
+ rq = q->orig_bar_rq;
+ uptodate = q->orderr ? q->orderr : 1;
- flush_rq->end_io_data = rq;
- flush_rq->end_io = blk_pre_flush_end_io;
+ q->ordseq = 0;
- __elv_add_request(q, flush_rq, ELEVATOR_INSERT_FRONT, 0);
- return flush_rq;
+ end_that_request_first(rq, uptodate, rq->hard_nr_sectors);
+ end_that_request_last(rq, uptodate);
}
-static void blk_start_post_flush(request_queue_t *q, struct request *rq)
+static void pre_flush_end_io(struct request *rq, int error)
{
- struct request *flush_rq = q->flush_rq;
+ elv_completed_request(rq->q, rq);
+ blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
+}
- BUG_ON(!blk_barrier_rq(rq));
+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);
+}
- rq_init(q, flush_rq);
- flush_rq->elevator_private = NULL;
- flush_rq->flags = REQ_BAR_FLUSH;
- flush_rq->rq_disk = rq->rq_disk;
- flush_rq->rl = NULL;
+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);
+}
- if (q->prepare_flush_fn(q, flush_rq)) {
- flush_rq->end_io_data = rq;
- flush_rq->end_io = blk_post_flush_end_io;
+static void queue_flush(request_queue_t *q, unsigned which)
+{
+ struct request *rq;
+ rq_end_io_fn *end_io;
- __elv_add_request(q, flush_rq, ELEVATOR_INSERT_FRONT, 0);
- q->request_fn(q);
+ 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 int blk_check_end_barrier(request_queue_t *q, struct request *rq,
- int sectors)
+static inline struct request *start_ordered(request_queue_t *q,
+ struct request *rq)
{
- if (sectors > rq->nr_sectors)
- sectors = rq->nr_sectors;
+ q->bi_size = 0;
+ 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;
+ rq->cmd_flags |= q->ordered & QUEUE_ORDERED_FUA ? REQ_FUA : 0;
+ 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 (q->ordered & QUEUE_ORDERED_POSTFLUSH)
+ queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
+ else
+ q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;
+
+ elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
- rq->nr_sectors -= sectors;
- return rq->nr_sectors;
+ 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;
}
-static int __blk_complete_barrier_rq(request_queue_t *q, struct request *rq,
- int sectors, int queue_locked)
+int blk_do_ordered(request_queue_t *q, struct request **rqp)
{
- if (q->ordered != QUEUE_ORDERED_FLUSH)
- return 0;
- if (!blk_fs_request(rq) || !blk_barrier_rq(rq))
- return 0;
- if (blk_barrier_postflush(rq))
- return 0;
+ struct request *rq = *rqp;
+ int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
- if (!blk_check_end_barrier(q, rq, sectors)) {
- unsigned long flags = 0;
+ if (!q->ordseq) {
+ if (!is_barrier)
+ return 1;
- if (!queue_locked)
- spin_lock_irqsave(q->queue_lock, flags);
+ 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);
+ end_that_request_first(rq, -EOPNOTSUPP,
+ rq->hard_nr_sectors);
+ end_that_request_last(rq, -EOPNOTSUPP);
+ *rqp = NULL;
+ return 0;
+ }
+ }
- blk_start_post_flush(q, rq);
+ /*
+ * 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 (!queue_locked)
- spin_unlock_irqrestore(q->queue_lock, flags);
+ 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;
}
-/**
- * blk_complete_barrier_rq - complete possible barrier request
- * @q: the request queue for the device
- * @rq: the request
- * @sectors: number of sectors to complete
- *
- * Description:
- * Used in driver end_io handling to determine whether to postpone
- * completion of a barrier request until a post flush has been done. This
- * is the unlocked variant, used if the caller doesn't already hold the
- * queue lock.
- **/
-int blk_complete_barrier_rq(request_queue_t *q, struct request *rq, int sectors)
+static int flush_dry_bio_endio(struct bio *bio, unsigned int bytes, int error)
{
- return __blk_complete_barrier_rq(q, rq, sectors, 0);
+ 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;
}
-EXPORT_SYMBOL(blk_complete_barrier_rq);
-/**
- * blk_complete_barrier_rq_locked - complete possible barrier request
- * @q: the request queue for the device
- * @rq: the request
- * @sectors: number of sectors to complete
- *
- * Description:
- * See blk_complete_barrier_rq(). This variant must be used if the caller
- * holds the queue lock.
- **/
-int blk_complete_barrier_rq_locked(request_queue_t *q, struct request *rq,
- int sectors)
+static int ordered_bio_endio(struct request *rq, struct bio *bio,
+ unsigned int nbytes, int error)
{
- return __blk_complete_barrier_rq(q, rq, sectors, 1);
+ 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;
+
+ endio = bio->bi_end_io;
+ private = bio->bi_private;
+ bio->bi_end_io = flush_dry_bio_endio;
+ bio->bi_private = q;
+
+ bio_endio(bio, nbytes, error);
+
+ bio->bi_end_io = endio;
+ bio->bi_private = private;
+
+ return 1;
}
-EXPORT_SYMBOL(blk_complete_barrier_rq_locked);
/**
* blk_queue_bounce_limit - set bounce buffer limit for queue
* Different hardware can have different requirements as to what pages
* it can do I/O directly to. A low level driver can call
* blk_queue_bounce_limit to have lower memory pages allocated as bounce
- * buffers for doing I/O to pages residing above @page. By default
- * the block layer sets this to the highest numbered "low" memory page.
+ * buffers for doing I/O to pages residing above @page.
**/
void blk_queue_bounce_limit(request_queue_t *q, u64 dma_addr)
{
unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
-
- /*
- * set appropriate bounce gfp mask -- unfortunately we don't have a
- * full 4GB zone, so we have to resort to low memory for any bounces.
- * ISA has its own < 16MB zone.
- */
- if (bounce_pfn < blk_max_low_pfn) {
- BUG_ON(dma_addr < BLK_BOUNCE_ISA);
+ 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;
- } else
- q->bounce_gfp = GFP_NOIO;
-
- q->bounce_pfn = bounce_pfn;
+ q->bounce_pfn = bounce_pfn;
+ }
}
EXPORT_SYMBOL(blk_queue_bounce_limit);
* Enables a low level driver to set an upper limit on the size of
* received requests.
**/
-void blk_queue_max_sectors(request_queue_t *q, unsigned short max_sectors)
+void blk_queue_max_sectors(request_queue_t *q, unsigned int max_sectors)
{
if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
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);
**/
struct request *blk_queue_find_tag(request_queue_t *q, int tag)
{
- struct blk_queue_tag *bqt = q->queue_tags;
-
- if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
- return NULL;
-
- return bqt->tag_index[tag];
+ return blk_map_queue_find_tag(q->queue_tags, tag);
}
EXPORT_SYMBOL(blk_queue_find_tag);
/**
- * __blk_queue_free_tags - release tag maintenance info
- * @q: the request queue for the device
+ * __blk_free_tags - release a given set of tag maintenance info
+ * @bqt: the tag map to free
*
- * Notes:
- * 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)
+ * Tries to free the specified @bqt@. Returns true if it was
+ * actually freed and false if there are still references using it
+ */
+static int __blk_free_tags(struct blk_queue_tag *bqt)
{
- struct blk_queue_tag *bqt = q->queue_tags;
+ int retval;
- if (!bqt)
- return;
-
- if (atomic_dec_and_test(&bqt->refcnt)) {
+ retval = atomic_dec_and_test(&bqt->refcnt);
+ if (retval) {
BUG_ON(bqt->busy);
BUG_ON(!list_empty(&bqt->busy_list));
bqt->tag_map = NULL;
kfree(bqt);
+
}
+ return retval;
+}
+
+/**
+ * __blk_queue_free_tags - release tag maintenance info
+ * @q: the request queue for the device
+ *
+ * Notes:
+ * 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)
+{
+ struct blk_queue_tag *bqt = q->queue_tags;
+
+ if (!bqt)
+ return;
+
+ __blk_free_tags(bqt);
+
q->queue_tags = NULL;
q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
}
+
+/**
+ * blk_free_tags - release a given set of tag maintenance info
+ * @bqt: the tag map to free
+ *
+ * For externally managed @bqt@ frees the map. Callers of this
+ * function must guarantee to have released all the queues that
+ * might have been using this tag map.
+ */
+void blk_free_tags(struct blk_queue_tag *bqt)
+{
+ if (unlikely(!__blk_free_tags(bqt)))
+ BUG();
+}
+EXPORT_SYMBOL(blk_free_tags);
+
/**
* blk_queue_free_tags - release tag maintenance info
* @q: the request queue for the device
unsigned long *tag_map;
int nr_ulongs;
- if (depth > q->nr_requests * 2) {
+ if (q && depth > q->nr_requests * 2) {
depth = q->nr_requests * 2;
printk(KERN_ERR "%s: adjusted depth to %d\n",
__FUNCTION__, depth);
}
- tag_index = kmalloc(depth * sizeof(struct request *), GFP_ATOMIC);
+ tag_index = kzalloc(depth * sizeof(struct request *), GFP_ATOMIC);
if (!tag_index)
goto fail;
nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG;
- tag_map = kmalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC);
+ tag_map = kzalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC);
if (!tag_map)
goto fail;
- memset(tag_index, 0, depth * sizeof(struct request *));
- memset(tag_map, 0, nr_ulongs * sizeof(unsigned long));
tags->real_max_depth = depth;
tags->max_depth = depth;
tags->tag_index = tag_index;
return -ENOMEM;
}
+static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
+ int depth)
+{
+ struct blk_queue_tag *tags;
+
+ tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
+ if (!tags)
+ goto fail;
+
+ 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;
+fail:
+ kfree(tags);
+ return NULL;
+}
+
+/**
+ * blk_init_tags - initialize the tag info for an external tag map
+ * @depth: the maximum queue depth supported
+ * @tags: the tag to use
+ **/
+struct blk_queue_tag *blk_init_tags(int depth)
+{
+ return __blk_queue_init_tags(NULL, depth);
+}
+EXPORT_SYMBOL(blk_init_tags);
+
/**
* blk_queue_init_tags - initialize the queue tag info
* @q: the request queue for the device
BUG_ON(tags && q->queue_tags && tags != q->queue_tags);
if (!tags && !q->queue_tags) {
- tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
- if (!tags)
- goto fail;
+ tags = __blk_queue_init_tags(q, depth);
- if (init_tag_map(q, tags, depth))
+ if (!tags)
goto fail;
-
- INIT_LIST_HEAD(&tags->busy_list);
- tags->busy = 0;
- atomic_set(&tags->refcnt, 1);
} else if (q->queue_tags) {
if ((rc = blk_queue_resize_tags(q, depth)))
return rc;
return 0;
}
+ /*
+ * Currently cannot replace a shared tag map with a new
+ * one, so error out if this is the case
+ */
+ if (atomic_read(&bqt->refcnt) != 1)
+ return -EBUSY;
+
/*
* save the old state info, so we can copy it back
*/
}
list_del_init(&rq->queuelist);
- rq->flags &= ~REQ_QUEUED;
+ rq->cmd_flags &= ~REQ_QUEUED;
rq->tag = -1;
if (unlikely(bqt->tag_index[tag] == NULL))
struct blk_queue_tag *bqt = q->queue_tags;
int tag;
- if (unlikely((rq->flags & REQ_QUEUED))) {
+ if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
printk(KERN_ERR
"%s: request %p for device [%s] already tagged %d",
__FUNCTION__, rq,
BUG();
}
- tag = find_first_zero_bit(bqt->tag_map, bqt->max_depth);
- if (tag >= bqt->max_depth)
- return 1;
+ /*
+ * Protect against shared tag maps, as we may not have exclusive
+ * access to the tag map.
+ */
+ do {
+ tag = find_first_zero_bit(bqt->tag_map, bqt->max_depth);
+ if (tag >= bqt->max_depth)
+ return 1;
- __set_bit(tag, bqt->tag_map);
+ } while (test_and_set_bit(tag, bqt->tag_map));
- rq->flags |= REQ_QUEUED;
+ rq->cmd_flags |= REQ_QUEUED;
rq->tag = tag;
bqt->tag_index[tag] = rq;
blkdev_dequeue_request(rq);
printk(KERN_ERR
"%s: bad tag found on list\n", __FUNCTION__);
list_del_init(&rq->queuelist);
- rq->flags &= ~REQ_QUEUED;
+ rq->cmd_flags &= ~REQ_QUEUED;
} else
blk_queue_end_tag(q, rq);
- rq->flags &= ~REQ_STARTED;
+ rq->cmd_flags &= ~REQ_STARTED;
__elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
}
}
EXPORT_SYMBOL(blk_queue_invalidate_tags);
-static const char * const rq_flags[] = {
- "REQ_RW",
- "REQ_FAILFAST",
- "REQ_SORTED",
- "REQ_SOFTBARRIER",
- "REQ_HARDBARRIER",
- "REQ_CMD",
- "REQ_NOMERGE",
- "REQ_STARTED",
- "REQ_DONTPREP",
- "REQ_QUEUED",
- "REQ_ELVPRIV",
- "REQ_PC",
- "REQ_BLOCK_PC",
- "REQ_SENSE",
- "REQ_FAILED",
- "REQ_QUIET",
- "REQ_SPECIAL",
- "REQ_DRIVE_CMD",
- "REQ_DRIVE_TASK",
- "REQ_DRIVE_TASKFILE",
- "REQ_PREEMPT",
- "REQ_PM_SUSPEND",
- "REQ_PM_RESUME",
- "REQ_PM_SHUTDOWN",
-};
-
void blk_dump_rq_flags(struct request *rq, char *msg)
{
int bit;
- printk("%s: dev %s: flags = ", msg,
- rq->rq_disk ? rq->rq_disk->disk_name : "?");
- bit = 0;
- do {
- if (rq->flags & (1 << bit))
- printk("%s ", rq_flags[bit]);
- bit++;
- } while (bit < __REQ_NR_BITS);
+ printk("%s: dev %s: type=%x, flags=%x\n", msg,
+ rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
+ rq->cmd_flags);
printk("\nsector %llu, nr/cnr %lu/%u\n", (unsigned long long)rq->sector,
rq->nr_sectors,
rq->current_nr_sectors);
printk("bio %p, biotail %p, buffer %p, data %p, len %u\n", rq->bio, rq->biotail, rq->buffer, rq->data, rq->data_len);
- if (rq->flags & (REQ_BLOCK_PC | REQ_PC)) {
+ if (blk_pc_request(rq)) {
printk("cdb: ");
for (bit = 0; bit < sizeof(rq->cmd); bit++)
printk("%02x ", rq->cmd[bit]);
int nr_phys_segs = bio_phys_segments(q, bio);
if (req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
- req->flags |= REQ_NOMERGE;
+ req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
return 0;
if (req->nr_hw_segments + nr_hw_segs > q->max_hw_segments
|| req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
- req->flags |= REQ_NOMERGE;
+ req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
return 0;
max_sectors = q->max_sectors;
if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
- req->flags |= REQ_NOMERGE;
+ req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
return 0;
if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
- req->flags |= REQ_NOMERGE;
+ req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
return 0;
* don't plug a stopped queue, it must be paired with blk_start_queue()
* which will restart the queueing
*/
- if (test_bit(QUEUE_FLAG_STOPPED, &q->queue_flags))
+ if (blk_queue_stopped(q))
return;
- if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+ if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
+ blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
+ }
}
EXPORT_SYMBOL(blk_plug_device);
*/
void __generic_unplug_device(request_queue_t *q)
{
- if (unlikely(test_bit(QUEUE_FLAG_STOPPED, &q->queue_flags)))
+ if (unlikely(blk_queue_stopped(q)))
return;
if (!blk_remove_plug(q))
/*
* devices don't necessarily have an ->unplug_fn defined
*/
- if (q->unplug_fn)
+ if (q->unplug_fn) {
+ blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+ q->rq.count[READ] + q->rq.count[WRITE]);
+
q->unplug_fn(q);
+ }
}
static void blk_unplug_work(void *data)
{
request_queue_t *q = data;
+ blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+ q->rq.count[READ] + q->rq.count[WRITE]);
+
q->unplug_fn(q);
}
{
request_queue_t *q = (request_queue_t *)data;
+ blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL,
+ q->rq.count[READ] + q->rq.count[WRITE]);
+
kblockd_schedule_work(&q->unplug_work);
}
**/
void blk_start_queue(request_queue_t *q)
{
+ WARN_ON(!irqs_disabled());
+
clear_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
/*
spin_lock_irqsave(q->queue_lock, flags);
blk_remove_plug(q);
- if (!elv_queue_empty(q))
- q->request_fn(q);
+
+ /*
+ * Only recurse once to avoid overrunning the stack, let the unplug
+ * handling reinvoke the handler shortly if we already got there.
+ */
+ if (!elv_queue_empty(q)) {
+ if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+ q->request_fn(q);
+ clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
+ } else {
+ blk_plug_device(q);
+ kblockd_schedule_work(&q->unplug_work);
+ }
+ }
+
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);
/**
* blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
- * @q: the request queue to be released
+ * @kobj: the kobj belonging of the request queue to be released
*
* Description:
* blk_cleanup_queue is the pair to blk_init_queue() or
* Hopefully the low level driver will have finished any
* outstanding requests first...
**/
-void blk_cleanup_queue(request_queue_t * q)
+static void blk_release_queue(struct kobject *kobj)
{
+ request_queue_t *q = container_of(kobj, struct request_queue, kobj);
struct request_list *rl = &q->rq;
- if (!atomic_dec_and_test(&q->refcnt))
- return;
-
- if (q->elevator)
- elevator_exit(q->elevator);
-
blk_sync_queue(q);
if (rl->rq_pool)
if (q->queue_tags)
__blk_queue_free_tags(q);
- blk_queue_ordered(q, QUEUE_ORDERED_NONE);
+ blk_trace_shutdown(q);
kmem_cache_free(requestq_cachep, q);
}
+void blk_put_queue(request_queue_t *q)
+{
+ kobject_put(&q->kobj);
+}
+EXPORT_SYMBOL(blk_put_queue);
+
+void blk_cleanup_queue(request_queue_t * q)
+{
+ mutex_lock(&q->sysfs_lock);
+ set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
+ mutex_unlock(&q->sysfs_lock);
+
+ if (q->elevator)
+ elevator_exit(q->elevator);
+
+ blk_put_queue(q);
+}
+
EXPORT_SYMBOL(blk_cleanup_queue);
static int blk_init_free_list(request_queue_t *q)
}
EXPORT_SYMBOL(blk_alloc_queue);
+static struct kobj_type queue_ktype;
+
request_queue_t *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
request_queue_t *q;
memset(q, 0, sizeof(*q));
init_timer(&q->unplug_timer);
- atomic_set(&q->refcnt, 1);
+
+ snprintf(q->kobj.name, KOBJ_NAME_LEN, "%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;
}
EXPORT_SYMBOL(blk_alloc_queue_node);
* get dealt with eventually.
*
* The queue spin lock must be held while manipulating the requests on the
- * request queue.
+ * request queue; this lock will be taken also from interrupt context, so irq
+ * disabling is needed for it.
*
* Function returns a pointer to the initialized request queue, or NULL if
* it didn't succeed.
return NULL;
q->node = node_id;
- if (blk_init_free_list(q))
- goto out_init;
+ if (blk_init_free_list(q)) {
+ kmem_cache_free(requestq_cachep, q);
+ return NULL;
+ }
/*
* if caller didn't supply a lock, they get per-queue locking with
return q;
}
- blk_cleanup_queue(q);
-out_init:
- kmem_cache_free(requestq_cachep, q);
+ blk_put_queue(q);
return NULL;
}
EXPORT_SYMBOL(blk_init_queue_node);
int blk_get_queue(request_queue_t *q)
{
if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
- atomic_inc(&q->refcnt);
+ kobject_get(&q->kobj);
return 0;
}
static inline void blk_free_request(request_queue_t *q, struct request *rq)
{
- if (rq->flags & REQ_ELVPRIV)
+ if (rq->cmd_flags & REQ_ELVPRIV)
elv_put_request(q, rq);
mempool_free(rq, q->rq.rq_pool);
}
-static inline struct request *
-blk_alloc_request(request_queue_t *q, int rw, struct bio *bio,
- int priv, gfp_t gfp_mask)
+static struct request *
+blk_alloc_request(request_queue_t *q, int rw, int priv, gfp_t gfp_mask)
{
struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
return NULL;
/*
- * first three bits are identical in rq->flags and bio->bi_rw,
+ * first three bits are identical in rq->cmd_flags and bio->bi_rw,
* see bio.h and blkdev.h
*/
- rq->flags = rw;
+ rq->cmd_flags = rw | REQ_ALLOCED;
if (priv) {
- if (unlikely(elv_set_request(q, rq, bio, gfp_mask))) {
+ if (unlikely(elv_set_request(q, rq, gfp_mask))) {
mempool_free(rq, q->rq.rq_pool);
return NULL;
}
- rq->flags |= REQ_ELVPRIV;
+ rq->cmd_flags |= REQ_ELVPRIV;
}
return rq;
struct io_context *ioc = NULL;
int may_queue, priv;
- may_queue = elv_may_queue(q, rw, bio);
+ may_queue = elv_may_queue(q, rw);
if (may_queue == ELV_MQUEUE_NO)
goto rq_starved;
if (rl->count[rw]+1 >= queue_congestion_on_threshold(q)) {
if (rl->count[rw]+1 >= q->nr_requests) {
- ioc = current_io_context(GFP_ATOMIC);
+ ioc = current_io_context(GFP_ATOMIC, q->node);
/*
* The queue will fill after this allocation, so set
* it as full, and mark this process as "batching".
spin_unlock_irq(q->queue_lock);
- rq = blk_alloc_request(q, rw, bio, priv, gfp_mask);
+ rq = blk_alloc_request(q, rw, priv, gfp_mask);
if (unlikely(!rq)) {
/*
* Allocation failed presumably due to memory. Undo anything
ioc->nr_batch_requests--;
rq_init(q, rq);
- rq->rl = rl;
+
+ blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
out:
return rq;
}
if (!rq) {
struct io_context *ioc;
+ blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);
+
__generic_unplug_device(q);
spin_unlock_irq(q->queue_lock);
io_schedule();
* up to a big batch of them for a small period time.
* See ioc_batching, ioc_set_batching
*/
- ioc = current_io_context(GFP_NOIO);
+ ioc = current_io_context(GFP_NOIO, q->node);
ioc_set_batching(q, ioc);
spin_lock_irq(q->queue_lock);
}
EXPORT_SYMBOL(blk_get_request);
+/**
+ * blk_start_queueing - initiate dispatch of requests to device
+ * @q: request queue to kick into gear
+ *
+ * This is basically a helper to remove the need to know whether a queue
+ * is plugged or not if someone just wants to initiate dispatch of requests
+ * for this queue.
+ *
+ * The queue lock must be held with interrupts disabled.
+ */
+void blk_start_queueing(request_queue_t *q)
+{
+ if (!blk_queue_plugged(q))
+ q->request_fn(q);
+ else
+ __generic_unplug_device(q);
+}
+EXPORT_SYMBOL(blk_start_queueing);
+
/**
* blk_requeue_request - put a request back on queue
* @q: request queue where request should be inserted
*/
void blk_requeue_request(request_queue_t *q, struct request *rq)
{
+ blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+
if (blk_rq_tagged(rq))
blk_queue_end_tag(q, rq);
* must not attempt merges on this) and that it acts as a soft
* barrier
*/
- rq->flags |= REQ_SPECIAL | REQ_SOFTBARRIER;
+ rq->cmd_type = REQ_TYPE_SPECIAL;
+ rq->cmd_flags |= REQ_SOFTBARRIER;
rq->special = data;
drive_stat_acct(rq, rq->nr_sectors, 1);
__elv_add_request(q, rq, where, 0);
-
- if (blk_queue_plugged(q))
- __generic_unplug_device(q);
- else
- q->request_fn(q);
+ blk_start_queueing(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
rq->rq_disk = bd_disk;
- rq->flags |= REQ_NOMERGE;
+ rq->cmd_flags |= REQ_NOMERGE;
rq->end_io = done;
- elv_add_request(q, rq, where, 1);
- generic_unplug_device(q);
+ 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);
/**
int blk_execute_rq(request_queue_t *q, struct gendisk *bd_disk,
struct request *rq, int at_head)
{
- DECLARE_COMPLETION(wait);
+ DECLARE_COMPLETION_ONSTACK(wait);
char sense[SCSI_SENSE_BUFFERSIZE];
int err = 0;
rq->sense_len = 0;
}
- rq->waiting = &wait;
+ rq->end_io_data = &wait;
blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
wait_for_completion(&wait);
- rq->waiting = NULL;
if (rq->errors)
err = -EIO;
disk->stamp = now;
}
+EXPORT_SYMBOL_GPL(disk_round_stats);
+
/*
* queue lock must be held
*/
void __blk_put_request(request_queue_t *q, struct request *req)
{
- struct request_list *rl = req->rl;
-
if (unlikely(!q))
return;
if (unlikely(--req->ref_count))
elv_completed_request(q, req);
- req->rq_status = RQ_INACTIVE;
- req->rl = NULL;
-
/*
* Request may not have originated from ll_rw_blk. if not,
* it didn't come out of our reserved rq pools
*/
- if (rl) {
+ if (req->cmd_flags & REQ_ALLOCED) {
int rw = rq_data_dir(req);
- int priv = req->flags & REQ_ELVPRIV;
+ int priv = req->cmd_flags & REQ_ELVPRIV;
BUG_ON(!list_empty(&req->queuelist));
+ BUG_ON(!hlist_unhashed(&req->hash));
blk_free_request(q, req);
freed_request(q, rw, priv);
/**
* 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->waiting;
+ struct completion *waiting = rq->end_io_data;
- rq->waiting = NULL;
+ rq->end_io_data = NULL;
__blk_put_request(rq->q, rq);
/*
EXPORT_SYMBOL(blk_congestion_wait);
+/**
+ * blk_congestion_end - wake up sleepers on a congestion queue
+ * @rw: READ or WRITE
+ */
+void blk_congestion_end(int rw)
+{
+ wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+ if (waitqueue_active(wqh))
+ wake_up(wqh);
+}
+
/*
* Has to be called with the request spinlock acquired
*/
return 0;
/*
- * not contigious
+ * not contiguous
*/
if (req->sector + req->nr_sectors != next->sector)
return 0;
if (rq_data_dir(req) != rq_data_dir(next)
|| req->rq_disk != next->rq_disk
- || next->waiting || next->special)
+ || next->special)
return 0;
/*
return 0;
}
-/**
- * blk_attempt_remerge - attempt to remerge active head with next request
- * @q: The &request_queue_t belonging to the device
- * @rq: The head request (usually)
- *
- * Description:
- * For head-active devices, the queue can easily be unplugged so quickly
- * that proper merging is not done on the front request. This may hurt
- * performance greatly for some devices. The block layer cannot safely
- * do merging on that first request for these queues, but the driver can
- * call this function and make it happen any way. Only the driver knows
- * when it is safe to do so.
- **/
-void blk_attempt_remerge(request_queue_t *q, struct request *rq)
-{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- attempt_back_merge(q, rq);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
-EXPORT_SYMBOL(blk_attempt_remerge);
-
static void init_request_from_bio(struct request *req, struct bio *bio)
{
- req->flags |= REQ_CMD;
+ req->cmd_type = REQ_TYPE_FS;
/*
* inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
*/
if (bio_rw_ahead(bio) || bio_failfast(bio))
- req->flags |= REQ_FAILFAST;
+ req->cmd_flags |= REQ_FAILFAST;
/*
* REQ_BARRIER implies no merging, but lets make it explicit
*/
if (unlikely(bio_barrier(bio)))
- req->flags |= (REQ_HARDBARRIER | REQ_NOMERGE);
+ req->cmd_flags |= (REQ_HARDBARRIER | REQ_NOMERGE);
+
+ if (bio_sync(bio))
+ req->cmd_flags |= REQ_RW_SYNC;
+ if (bio_rw_meta(bio))
+ req->cmd_flags |= REQ_RW_META;
req->errors = 0;
req->hard_sector = req->sector = bio->bi_sector;
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->waiting = NULL;
req->bio = req->biotail = bio;
req->ioprio = bio_prio(bio);
req->rq_disk = bio->bi_bdev->bd_disk;
static int __make_request(request_queue_t *q, struct bio *bio)
{
struct request *req;
- int el_ret, rw, nr_sectors, cur_nr_sectors, barrier, err, sync;
- unsigned short prio;
- sector_t sector;
+ int el_ret, nr_sectors, barrier, err;
+ const unsigned short prio = bio_prio(bio);
+ const int sync = bio_sync(bio);
- sector = bio->bi_sector;
nr_sectors = bio_sectors(bio);
- cur_nr_sectors = bio_cur_sectors(bio);
- prio = bio_prio(bio);
-
- rw = bio_data_dir(bio);
- sync = bio_sync(bio);
/*
* low level driver can indicate that it wants pages above a
*/
blk_queue_bounce(q, &bio);
- spin_lock_prefetch(q->queue_lock);
-
barrier = bio_barrier(bio);
- if (unlikely(barrier) && (q->ordered == QUEUE_ORDERED_NONE)) {
+ if (unlikely(barrier) && (q->next_ordered == QUEUE_ORDERED_NONE)) {
err = -EOPNOTSUPP;
goto end_io;
}
if (!q->back_merge_fn(q, req, bio))
break;
+ blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+
req->biotail->bi_next = bio;
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);
if (!attempt_back_merge(q, req))
- elv_merged_request(q, req);
+ elv_merged_request(q, req, el_ret);
goto out;
case ELEVATOR_FRONT_MERGE:
if (!q->front_merge_fn(q, req, bio))
break;
+ blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+
bio->bi_next = req->bio;
req->bio = bio;
* not touch req->buffer either...
*/
req->buffer = bio_data(bio);
- req->current_nr_sectors = cur_nr_sectors;
- req->hard_cur_sectors = cur_nr_sectors;
- req->sector = req->hard_sector = sector;
+ req->current_nr_sectors = bio_cur_sectors(bio);
+ req->hard_cur_sectors = req->current_nr_sectors;
+ 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);
if (!attempt_front_merge(q, req))
- elv_merged_request(q, req);
+ elv_merged_request(q, req, el_ret);
goto out;
/* ELV_NO_MERGE: elevator says don't/can't merge. */
* Grab a free request. This is might sleep but can not fail.
* Returns with the queue unlocked.
*/
- req = get_request_wait(q, rw, bio);
+ req = get_request_wait(q, bio_data_dir(bio), bio);
/*
* After dropping the lock and possibly sleeping here, our request
request_queue_t *q;
sector_t maxsector;
int ret, nr_sectors = bio_sectors(bio);
+ dev_t old_dev;
might_sleep();
/* Test device or partition size, when known. */
* NOTE: we don't repeat the blk_size check for each new device.
* Stacking drivers are expected to know what they are doing.
*/
+ maxsector = -1;
+ old_dev = 0;
do {
char b[BDEVNAME_SIZE];
*/
blk_partition_remap(bio);
+ if (maxsector != -1)
+ blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
+ maxsector);
+
+ blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+
+ maxsector = bio->bi_sector;
+ old_dev = bio->bi_bdev->bd_dev;
+
ret = q->make_request_fn(q, bio);
} while (ret);
}
BIO_BUG_ON(!bio->bi_io_vec);
bio->bi_rw |= rw;
if (rw & WRITE)
- mod_page_state(pgpgout, count);
+ count_vm_events(PGPGOUT, count);
else
- mod_page_state(pgpgin, count);
+ count_vm_events(PGPGIN, count);
if (unlikely(block_dump)) {
char b[BDEVNAME_SIZE];
int total_bytes, bio_nbytes, error, next_idx = 0;
struct bio *bio;
+ blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE);
+
/*
* extend uptodate bool to allow < 0 value to be direct io error
*/
req->errors = 0;
if (!uptodate) {
- if (blk_fs_request(req) && !(req->flags & REQ_QUIET))
+ if (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))
printk("end_request: I/O error, dev %s, sector %llu\n",
req->rq_disk ? req->rq_disk->disk_name : "?",
(unsigned long long)req->sector);
if (blk_fs_request(req) && req->rq_disk) {
const int rw = rq_data_dir(req);
- __disk_stat_add(req->rq_disk, sectors[rw], nr_bytes >> 9);
+ disk_stat_add(req->rq_disk, sectors[rw], nr_bytes >> 9);
}
total_bytes = bio_nbytes = 0;
if (nr_bytes >= bio->bi_size) {
req->bio = bio->bi_next;
nbytes = bio->bi_size;
- bio_endio(bio, nbytes, error);
+ if (!ordered_bio_endio(req, bio, nbytes, error))
+ bio_endio(bio, nbytes, error);
next_idx = 0;
bio_nbytes = 0;
} else {
* if the request wasn't completed, update state
*/
if (bio_nbytes) {
- bio_endio(bio, bio_nbytes, error);
+ if (!ordered_bio_endio(req, bio, bio_nbytes, error))
+ bio_endio(bio, bio_nbytes, error);
bio->bi_idx += next_idx;
bio_iovec(bio)->bv_offset += nr_bytes;
bio_iovec(bio)->bv_len -= nr_bytes;
EXPORT_SYMBOL(end_that_request_chunk);
+/*
+ * splice the completion data to a local structure and hand off to
+ * process_completion_queue() to complete the requests
+ */
+static void blk_done_softirq(struct softirq_action *h)
+{
+ struct list_head *cpu_list, local_list;
+
+ local_irq_disable();
+ cpu_list = &__get_cpu_var(blk_cpu_done);
+ list_replace_init(cpu_list, &local_list);
+ local_irq_enable();
+
+ while (!list_empty(&local_list)) {
+ struct request *rq = list_entry(local_list.next, struct request, donelist);
+
+ list_del_init(&rq->donelist);
+ rq->q->softirq_done_fn(rq);
+ }
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int 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) {
+ int cpu = (unsigned long) hcpu;
+
+ local_irq_disable();
+ list_splice_init(&per_cpu(blk_cpu_done, cpu),
+ &__get_cpu_var(blk_cpu_done));
+ raise_softirq_irqoff(BLOCK_SOFTIRQ);
+ local_irq_enable();
+ }
+
+ return NOTIFY_OK;
+}
+
+
+static struct notifier_block __devinitdata blk_cpu_notifier = {
+ .notifier_call = blk_cpu_notify,
+};
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+/**
+ * blk_complete_request - end I/O on a request
+ * @req: the request being processed
+ *
+ * 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 a softirq handler. The user must have registered a completion
+ * callback through blk_queue_softirq_done().
+ **/
+
+void blk_complete_request(struct request *req)
+{
+ struct list_head *cpu_list;
+ unsigned long flags;
+
+ BUG_ON(!req->q->softirq_done_fn);
+
+ local_irq_save(flags);
+
+ cpu_list = &__get_cpu_var(blk_cpu_done);
+ list_add_tail(&req->donelist, cpu_list);
+ raise_softirq_irqoff(BLOCK_SOFTIRQ);
+
+ local_irq_restore(flags);
+}
+
+EXPORT_SYMBOL(blk_complete_request);
+
/*
* queue lock must be held
*/
if (unlikely(laptop_mode) && blk_fs_request(req))
laptop_io_completion();
- if (disk && blk_fs_request(req)) {
+ /*
+ * Account IO completion. bar_rq isn't accounted as a normal
+ * IO on queueing nor completion. Accounting the containing
+ * request is enough.
+ */
+ if (disk && blk_fs_request(req) && req != &req->q->bar_rq) {
unsigned long duration = jiffies - req->start_time;
const int rw = rq_data_dir(req);
void blk_rq_bio_prep(request_queue_t *q, struct request *rq, struct bio *bio)
{
- /* first three bits are identical in rq->flags and bio->bi_rw */
- rq->flags |= (bio->bi_rw & 7);
+ /* first two bits are identical in rq->cmd_flags and bio->bi_rw */
+ rq->cmd_flags |= (bio->bi_rw & 3);
rq->nr_phys_segments = bio_phys_segments(q, bio);
rq->nr_hw_segments = bio_hw_segments(q, bio);
int __init blk_dev_init(void)
{
+ int i;
+
kblockd_workqueue = create_workqueue("kblockd");
if (!kblockd_workqueue)
panic("Failed to create kblockd\n");
iocontext_cachep = kmem_cache_create("blkdev_ioc",
sizeof(struct io_context), 0, SLAB_PANIC, NULL, 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;
BUG_ON(atomic_read(&ioc->refcount) == 0);
if (atomic_dec_and_test(&ioc->refcount)) {
+ struct cfq_io_context *cic;
+
+ rcu_read_lock();
if (ioc->aic && ioc->aic->dtor)
ioc->aic->dtor(ioc->aic);
- if (ioc->cic && ioc->cic->dtor)
- ioc->cic->dtor(ioc->cic);
+ if (ioc->cic_root.rb_node != NULL) {
+ struct rb_node *n = rb_first(&ioc->cic_root);
+
+ cic = rb_entry(n, struct cfq_io_context, rb_node);
+ cic->dtor(ioc);
+ }
+ rcu_read_unlock();
kmem_cache_free(iocontext_cachep, ioc);
}
/* Called by the exitting task */
void exit_io_context(void)
{
- unsigned long flags;
struct io_context *ioc;
+ struct cfq_io_context *cic;
- local_irq_save(flags);
task_lock(current);
ioc = current->io_context;
current->io_context = NULL;
- ioc->task = NULL;
task_unlock(current);
- local_irq_restore(flags);
+ ioc->task = NULL;
if (ioc->aic && ioc->aic->exit)
ioc->aic->exit(ioc->aic);
- if (ioc->cic && ioc->cic->exit)
- ioc->cic->exit(ioc->cic);
+ if (ioc->cic_root.rb_node != NULL) {
+ cic = rb_entry(rb_first(&ioc->cic_root), struct cfq_io_context, rb_node);
+ cic->exit(ioc);
+ }
put_io_context(ioc);
}
* 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)
+static struct io_context *current_io_context(gfp_t gfp_flags, int node)
{
struct task_struct *tsk = current;
struct io_context *ret;
if (likely(ret))
return ret;
- ret = kmem_cache_alloc(iocontext_cachep, gfp_flags);
+ ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node);
if (ret) {
atomic_set(&ret->refcount, 1);
ret->task = current;
- ret->set_ioprio = NULL;
+ ret->ioprio_changed = 0;
ret->last_waited = jiffies; /* doesn't matter... */
ret->nr_batch_requests = 0; /* because this is 0 */
ret->aic = NULL;
- ret->cic = NULL;
+ ret->cic_root.rb_node = NULL;
+ /* make sure set_task_ioprio() sees the settings above */
+ smp_wmb();
tsk->io_context = ret;
}
*
* 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)
+struct io_context *get_io_context(gfp_t gfp_flags, int node)
{
struct io_context *ret;
- ret = current_io_context(gfp_flags);
+ ret = current_io_context(gfp_flags, node);
if (likely(ret))
atomic_inc(&ret->refcount);
return ret;
queue_requests_store(struct request_queue *q, const char *page, size_t count)
{
struct request_list *rl = &q->rq;
+ unsigned long nr;
+ int ret = queue_var_store(&nr, page, count);
+ if (nr < BLKDEV_MIN_RQ)
+ nr = BLKDEV_MIN_RQ;
- int ret = queue_var_store(&q->nr_requests, page, count);
- if (q->nr_requests < BLKDEV_MIN_RQ)
- q->nr_requests = BLKDEV_MIN_RQ;
+ spin_lock_irq(q->queue_lock);
+ q->nr_requests = nr;
blk_queue_congestion_threshold(q);
if (rl->count[READ] >= queue_congestion_on_threshold(q))
blk_clear_queue_full(q, WRITE);
wake_up(&rl->wait[WRITE]);
}
+ spin_unlock_irq(q->queue_lock);
return ret;
}
ssize_t ret = queue_var_store(&ra_kb, page, count);
spin_lock_irq(q->queue_lock);
- if (ra_kb > (q->max_sectors >> 1))
- ra_kb = (q->max_sectors >> 1);
-
q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10);
spin_unlock_irq(q->queue_lock);
queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
struct queue_sysfs_entry *entry = to_queue(attr);
- struct request_queue *q;
+ request_queue_t *q = container_of(kobj, struct request_queue, kobj);
+ ssize_t res;
- q = container_of(kobj, struct request_queue, kobj);
if (!entry->show)
return -EIO;
-
- return entry->show(q, page);
+ mutex_lock(&q->sysfs_lock);
+ if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
+ mutex_unlock(&q->sysfs_lock);
+ return -ENOENT;
+ }
+ res = entry->show(q, page);
+ mutex_unlock(&q->sysfs_lock);
+ return res;
}
static ssize_t
const char *page, size_t length)
{
struct queue_sysfs_entry *entry = to_queue(attr);
- struct request_queue *q;
+ request_queue_t *q = container_of(kobj, struct request_queue, kobj);
+
+ ssize_t res;
- q = container_of(kobj, struct request_queue, kobj);
if (!entry->store)
return -EIO;
-
- return entry->store(q, page, length);
+ mutex_lock(&q->sysfs_lock);
+ if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)) {
+ mutex_unlock(&q->sysfs_lock);
+ return -ENOENT;
+ }
+ res = entry->store(q, page, length);
+ mutex_unlock(&q->sysfs_lock);
+ return res;
}
static struct sysfs_ops queue_sysfs_ops = {
static struct kobj_type queue_ktype = {
.sysfs_ops = &queue_sysfs_ops,
.default_attrs = default_attrs,
+ .release = blk_release_queue,
};
int blk_register_queue(struct gendisk *disk)
return -ENXIO;
q->kobj.parent = kobject_get(&disk->kobj);
- if (!q->kobj.parent)
- return -EBUSY;
- snprintf(q->kobj.name, KOBJ_NAME_LEN, "%s", "queue");
- q->kobj.ktype = &queue_ktype;
-
- ret = kobject_register(&q->kobj);
+ ret = kobject_add(&q->kobj);
if (ret < 0)
return ret;
+ kobject_uevent(&q->kobj, KOBJ_ADD);
+
ret = elv_register_queue(q);
if (ret) {
- kobject_unregister(&q->kobj);
+ kobject_uevent(&q->kobj, KOBJ_REMOVE);
+ kobject_del(&q->kobj);
return ret;
}
if (q && q->request_fn) {
elv_unregister_queue(q);
- kobject_unregister(&q->kobj);
+ kobject_uevent(&q->kobj, KOBJ_REMOVE);
+ kobject_del(&q->kobj);
kobject_put(&disk->kobj);
}
}
Code Review / linux-2.6.git / blobdiff