#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
+#include <linux/task_io_accounting_ops.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/blktrace_api.h>
+#include <linux/fault-inject.h>
/*
* for max sense size
*/
#include <scsi/scsi_cmnd.h>
-static void blk_unplug_work(void *data);
+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 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
*/
-static kmem_cache_t *request_cachep;
+static struct kmem_cache *request_cachep;
/*
* For queue allocation
*/
-static kmem_cache_t *requestq_cachep;
+static struct kmem_cache *requestq_cachep;
/*
* For io context allocations
*/
-static kmem_cache_t *iocontext_cachep;
-
-static wait_queue_head_t congestion_wqh[2] = {
- __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
- __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
- };
+static struct kmem_cache *iocontext_cachep;
/*
* Controlling structure to kblockd
q->nr_congestion_off = nr;
}
-/*
- * A queue has just exitted congestion. Note this in the global counter of
- * congested queues, and wake up anyone who was waiting for requests to be
- * put back.
- */
-static void clear_queue_congested(request_queue_t *q, int rw)
-{
- enum bdi_state bit;
- wait_queue_head_t *wqh = &congestion_wqh[rw];
-
- bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
- clear_bit(bit, &q->backing_dev_info.state);
- smp_mb__after_clear_bit();
- if (waitqueue_active(wqh))
- wake_up(wqh);
-}
-
-/*
- * A queue has just entered congestion. Flag that in the queue's VM-visible
- * state flags and increment the global gounter of congested queues.
- */
-static void set_queue_congested(request_queue_t *q, int rw)
-{
- enum bdi_state bit;
-
- bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
- set_bit(bit, &q->backing_dev_info.state);
-}
-
/**
* blk_get_backing_dev_info - get the address of a queue's backing_dev_info
* @bdev: device
ret = &q->backing_dev_info;
return ret;
}
-
EXPORT_SYMBOL(blk_get_backing_dev_info);
-void blk_queue_activity_fn(request_queue_t *q, activity_fn *fn, void *data)
-{
- q->activity_fn = fn;
- q->activity_data = data;
-}
-
-EXPORT_SYMBOL(blk_queue_activity_fn);
-
/**
* blk_queue_prep_rq - set a prepare_request function for queue
* @q: queue
if (q->unplug_delay == 0)
q->unplug_delay = 1;
- INIT_WORK(&q->unplug_work, blk_unplug_work, q);
+ INIT_WORK(&q->unplug_work, blk_unplug_work);
q->unplug_timer.function = blk_unplug_timeout;
q->unplug_timer.data = (unsigned long)q;
* by default assume old behaviour and bounce for any highmem page
*/
blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
-
- blk_queue_activity_fn(q, NULL, NULL);
}
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);
- INIT_HLIST_NODE(&rq->hash);
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;
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;
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->rl = NULL;
rq->end_io = end_io;
q->prepare_flush_fn(q, rq);
rq->cmd_flags |= REQ_RW;
rq->cmd_flags |= q->ordered & QUEUE_ORDERED_FUA ? REQ_FUA : 0;
rq->elevator_private = NULL;
- rq->rl = NULL;
+ rq->elevator_private2 = NULL;
init_request_from_bio(rq, q->orig_bar_rq->bio);
rq->end_io = bar_end_io;
return 0;
}
-static inline int ordered_bio_endio(struct request *rq, struct bio *bio,
- unsigned int nbytes, int error)
+static int ordered_bio_endio(struct request *rq, struct bio *bio,
+ unsigned int nbytes, int error)
{
request_queue_t *q = rq->q;
bio_end_io_t *endio;
**/
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);
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->cmd_flags |= REQ_QUEUED;
rq->tag = tag;
* 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) {
bio->bi_hw_segments = nr_hw_segs;
bio->bi_flags |= (1 << BIO_SEG_VALID);
}
-
+EXPORT_SYMBOL(blk_recount_segments);
static int blk_phys_contig_segment(request_queue_t *q, struct bio *bio,
struct bio *nxt)
return 1;
}
-static int ll_back_merge_fn(request_queue_t *q, struct request *req,
- struct bio *bio)
+int ll_back_merge_fn(request_queue_t *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,
struct bio *bio)
}
}
-static void blk_unplug_work(void *data)
+static void blk_unplug_work(struct work_struct *work)
{
- request_queue_t *q = data;
+ request_queue_t *q = container_of(work, request_queue_t, unplug_work);
blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
q->rq.count[READ] + q->rq.count[WRITE]);
* 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();
}
EXPORT_SYMBOL(blk_sync_queue);
}
q->request_fn = rfn;
- q->back_merge_fn = ll_back_merge_fn;
- q->front_merge_fn = ll_front_merge_fn;
- q->merge_requests_fn = ll_merge_requests_fn;
q->prep_rq_fn = NULL;
q->unplug_fn = generic_unplug_device;
q->queue_flags = (1 << QUEUE_FLAG_CLUSTER);
blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
+ q->sg_reserved_size = INT_MAX;
+
/*
* all done
*/
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);
* first three bits are identical in rq->cmd_flags and bio->bi_rw,
* see bio.h and blkdev.h
*/
- rq->cmd_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;
}
struct request_list *rl = &q->rq;
if (rl->count[rw] < queue_congestion_off_threshold(q))
- clear_queue_congested(q, rw);
+ blk_clear_queue_congested(q, rw);
if (rl->count[rw] + 1 <= q->nr_requests) {
if (waitqueue_active(&rl->wait[rw]))
* 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, struct bio *bio,
- gfp_t gfp_mask)
+static struct request *get_request(request_queue_t *q, int rw_flags,
+ struct bio *bio, gfp_t gfp_mask)
{
struct request *rq = NULL;
struct request_list *rl = &q->rq;
struct io_context *ioc = NULL;
+ const int rw = rw_flags & 0x01;
int may_queue, priv;
- may_queue = elv_may_queue(q, rw, bio);
+ may_queue = elv_may_queue(q, rw_flags);
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".
}
}
}
- set_queue_congested(q, rw);
+ blk_set_queue_congested(q, rw);
}
/*
spin_unlock_irq(q->queue_lock);
- rq = blk_alloc_request(q, rw, bio, priv, gfp_mask);
+ rq = blk_alloc_request(q, rw_flags, 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:
*
* Called with q->queue_lock held, and returns with it unlocked.
*/
-static struct request *get_request_wait(request_queue_t *q, int rw,
+static struct request *get_request_wait(request_queue_t *q, int rw_flags,
struct bio *bio)
{
+ const int rw = rw_flags & 0x01;
struct request *rq;
- rq = get_request(q, rw, bio, GFP_NOIO);
+ rq = get_request(q, rw_flags, bio, GFP_NOIO);
while (!rq) {
DEFINE_WAIT(wait);
struct request_list *rl = &q->rq;
prepare_to_wait_exclusive(&rl->wait[rw], &wait,
TASK_UNINTERRUPTIBLE);
- rq = get_request(q, rw, bio, GFP_NOIO);
+ rq = get_request(q, rw_flags, bio, GFP_NOIO);
if (!rq) {
struct io_context *ioc;
* 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
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);
}
EXPORT_SYMBOL(blk_insert_request);
+static int __blk_rq_unmap_user(struct bio *bio)
+{
+ int ret = 0;
+
+ if (bio) {
+ if (bio_flagged(bio, BIO_USER_MAPPED))
+ bio_unmap_user(bio);
+ else
+ ret = bio_uncopy_user(bio);
+ }
+
+ return ret;
+}
+
+static int __blk_rq_map_user(request_queue_t *q, struct request *rq,
+ void __user *ubuf, unsigned int len)
+{
+ unsigned long uaddr;
+ struct bio *bio, *orig_bio;
+ int reading, ret;
+
+ reading = rq_data_dir(rq) == READ;
+
+ /*
+ * if alignment requirement is satisfied, map in user pages for
+ * direct dma. else, set up kernel bounce buffers
+ */
+ uaddr = (unsigned long) ubuf;
+ if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q)))
+ bio = bio_map_user(q, NULL, uaddr, len, reading);
+ else
+ bio = bio_copy_user(q, uaddr, len, reading);
+
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ orig_bio = bio;
+ blk_queue_bounce(q, &bio);
+
+ /*
+ * We link the bounce buffer in and could have to traverse it
+ * later so we have to get a ref to prevent it from being freed
+ */
+ bio_get(bio);
+
+ 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;
+
+unmap_bio:
+ /* if it was boucned we must call the end io function */
+ bio_endio(bio, bio->bi_size, 0);
+ __blk_rq_unmap_user(orig_bio);
+ bio_put(bio);
+ return ret;
+}
+
/**
* blk_rq_map_user - map user data to a request, for REQ_BLOCK_PC usage
* @q: request queue where request should be inserted
* unmapping.
*/
int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
- unsigned int len)
+ unsigned long len)
{
- unsigned long uaddr;
- struct bio *bio;
- int reading;
+ unsigned long bytes_read = 0;
+ struct bio *bio = NULL;
+ int ret;
if (len > (q->max_hw_sectors << 9))
return -EINVAL;
if (!len || !ubuf)
return -EINVAL;
- reading = rq_data_dir(rq) == READ;
-
- /*
- * if alignment requirement is satisfied, map in user pages for
- * direct dma. else, set up kernel bounce buffers
- */
- uaddr = (unsigned long) ubuf;
- if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q)))
- bio = bio_map_user(q, NULL, uaddr, len, reading);
- else
- bio = bio_copy_user(q, uaddr, len, reading);
+ while (bytes_read != len) {
+ unsigned long map_len, end, start;
- if (!IS_ERR(bio)) {
- rq->bio = rq->biotail = bio;
- blk_rq_bio_prep(q, rq, bio);
+ map_len = min_t(unsigned long, len - bytes_read, BIO_MAX_SIZE);
+ end = ((unsigned long)ubuf + map_len + PAGE_SIZE - 1)
+ >> PAGE_SHIFT;
+ start = (unsigned long)ubuf >> PAGE_SHIFT;
- rq->buffer = rq->data = NULL;
- rq->data_len = len;
- return 0;
+ /*
+ * A bad offset could cause us to require BIO_MAX_PAGES + 1
+ * pages. If this happens we just lower the requested
+ * mapping len by a page so that we can fit
+ */
+ if (end - start > BIO_MAX_PAGES)
+ map_len -= PAGE_SIZE;
+
+ ret = __blk_rq_map_user(q, rq, ubuf, map_len);
+ if (ret < 0)
+ goto unmap_rq;
+ if (!bio)
+ bio = rq->bio;
+ bytes_read += ret;
+ ubuf += ret;
}
- /*
- * bio is the err-ptr
- */
- return PTR_ERR(bio);
+ rq->buffer = rq->data = NULL;
+ return 0;
+unmap_rq:
+ blk_rq_unmap_user(bio);
+ return ret;
}
EXPORT_SYMBOL(blk_rq_map_user);
* @rq: request to map data to
* @iov: pointer to the iovec
* @iov_count: number of elements in the iovec
+ * @len: I/O byte count
*
* Description:
* Data will be mapped directly for zero copy io, if possible. Otherwise
* unmapping.
*/
int blk_rq_map_user_iov(request_queue_t *q, struct request *rq,
- struct sg_iovec *iov, int iov_count)
+ struct sg_iovec *iov, int iov_count, unsigned int len)
{
struct bio *bio;
if (IS_ERR(bio))
return PTR_ERR(bio);
- rq->bio = rq->biotail = bio;
+ if (bio->bi_size != len) {
+ bio_endio(bio, bio->bi_size, 0);
+ bio_unmap_user(bio);
+ return -EINVAL;
+ }
+
+ bio_get(bio);
blk_rq_bio_prep(q, rq, bio);
rq->buffer = rq->data = NULL;
- rq->data_len = bio->bi_size;
return 0;
}
/**
* blk_rq_unmap_user - unmap a request with user data
- * @bio: bio to be unmapped
- * @ulen: length of user buffer
+ * @bio: start of bio list
*
* Description:
- * Unmap a bio previously mapped by blk_rq_map_user().
+ * Unmap a rq previously mapped by blk_rq_map_user(). The caller must
+ * supply the original rq->bio from the blk_rq_map_user() return, since
+ * the io completion may have changed rq->bio.
*/
-int blk_rq_unmap_user(struct bio *bio, unsigned int ulen)
+int blk_rq_unmap_user(struct bio *bio)
{
- int ret = 0;
+ struct bio *mapped_bio;
+ int ret = 0, ret2;
- if (bio) {
- if (bio_flagged(bio, BIO_USER_MAPPED))
- bio_unmap_user(bio);
- else
- ret = bio_uncopy_user(bio);
+ while (bio) {
+ mapped_bio = bio;
+ if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
+ mapped_bio = bio->bi_private;
+
+ ret2 = __blk_rq_unmap_user(mapped_bio);
+ if (ret2 && !ret)
+ ret = ret2;
+
+ mapped_bio = bio;
+ bio = bio->bi_next;
+ bio_put(mapped_bio);
}
- return 0;
+ return ret;
}
EXPORT_SYMBOL(blk_rq_unmap_user);
if (rq_data_dir(rq) == WRITE)
bio->bi_rw |= (1 << BIO_RW);
- rq->bio = rq->biotail = bio;
blk_rq_bio_prep(q, rq, bio);
-
+ blk_queue_bounce(q, &rq->bio);
rq->buffer = rq->data = NULL;
- rq->data_len = len;
return 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;
{
drive_stat_acct(req, req->nr_sectors, 1);
- if (q->activity_fn)
- q->activity_fn(q->activity_data, rq_data_dir(req));
-
/*
* elevator indicated where it wants this request to be
* inserted at elevator_merge time
*/
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->cmd_flags & REQ_ELVPRIV;
*/
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_end_sync_rq);
-/**
- * blk_congestion_wait - wait for a queue to become uncongested
- * @rw: READ or WRITE
- * @timeout: timeout in jiffies
- *
- * Waits for up to @timeout jiffies for a queue (any queue) to exit congestion.
- * If no queues are congested then just wait for the next request to be
- * returned.
- */
-long blk_congestion_wait(int rw, long timeout)
-{
- long ret;
- DEFINE_WAIT(wait);
- wait_queue_head_t *wqh = &congestion_wqh[rw];
-
- prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
- ret = io_schedule_timeout(timeout);
- finish_wait(wqh, &wait);
- return ret;
-}
-
-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
*/
if (rq_data_dir(req) != rq_data_dir(next)
|| req->rq_disk != next->rq_disk
- || next->waiting || next->special)
+ || next->special)
return 0;
/*
* will have updated segment counts, update sector
* counts here.
*/
- if (!q->merge_requests_fn(q, req, next))
+ if (!ll_merge_requests_fn(q, req, next))
return 0;
/*
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);
+ int rw_flags;
- 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->next_ordered == QUEUE_ORDERED_NONE)) {
err = -EOPNOTSUPP;
case ELEVATOR_BACK_MERGE:
BUG_ON(!rq_mergeable(req));
- if (!q->back_merge_fn(q, req, bio))
+ if (!ll_back_merge_fn(q, req, bio))
break;
blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
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:
BUG_ON(!rq_mergeable(req));
- if (!q->front_merge_fn(q, req, bio))
+ if (!ll_front_merge_fn(q, req, bio))
break;
blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
* 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. */
}
get_rq:
+ /*
+ * This sync check and mask will be re-done in init_request_from_bio(),
+ * but we need to set it earlier to expose the sync flag to the
+ * rq allocator and io schedulers.
+ */
+ rw_flags = bio_data_dir(bio);
+ if (sync)
+ rw_flags |= REQ_RW_SYNC;
+
/*
* 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, rw_flags, bio);
/*
* After dropping the lock and possibly sleeping here, our request
set_bit(BIO_EOF, &bio->bi_flags);
}
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+
+static DECLARE_FAULT_ATTR(fail_make_request);
+
+static int __init setup_fail_make_request(char *str)
+{
+ return setup_fault_attr(&fail_make_request, str);
+}
+__setup("fail_make_request=", setup_fail_make_request);
+
+static int should_fail_request(struct bio *bio)
+{
+ if ((bio->bi_bdev->bd_disk->flags & GENHD_FL_FAIL) ||
+ (bio->bi_bdev->bd_part && bio->bi_bdev->bd_part->make_it_fail))
+ return should_fail(&fail_make_request, bio->bi_size);
+
+ return 0;
+}
+
+static int __init fail_make_request_debugfs(void)
+{
+ return init_fault_attr_dentries(&fail_make_request,
+ "fail_make_request");
+}
+
+late_initcall(fail_make_request_debugfs);
+
+#else /* CONFIG_FAIL_MAKE_REQUEST */
+
+static inline int should_fail_request(struct bio *bio)
+{
+ return 0;
+}
+
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
/**
* 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;
+ sector_t old_sector;
int ret, nr_sectors = bio_sectors(bio);
dev_t old_dev;
* 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_sector = -1;
old_dev = 0;
do {
char b[BDEVNAME_SIZE];
if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
goto end_io;
+ if (should_fail_request(bio))
+ goto end_io;
+
/*
* If this device has partitions, remap block n
* of partition p to block n+start(p) of the disk.
*/
blk_partition_remap(bio);
- if (maxsector != -1)
+ if (old_sector != -1)
blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
- maxsector);
+ old_sector);
blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
- maxsector = bio->bi_sector;
+ 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;
+ }
+ }
+
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);
/**
BIO_BUG_ON(!bio->bi_size);
BIO_BUG_ON(!bio->bi_io_vec);
bio->bi_rw |= rw;
- if (rw & WRITE)
+ if (rw & WRITE) {
count_vm_events(PGPGOUT, count);
- else
+ } else {
+ task_io_account_read(bio->bi_size);
count_vm_events(PGPGIN, count);
+ }
if (unlikely(block_dump)) {
char b[BDEVNAME_SIZE];
}
}
-#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) {
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
int cpu = (unsigned long) hcpu;
local_irq_disable();
.notifier_call = blk_cpu_notify,
};
-#endif /* CONFIG_HOTPLUG_CPU */
-
/**
* blk_complete_request - end I/O on a request
* @req: the request being processed
rq->hard_cur_sectors = rq->current_nr_sectors;
rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
rq->buffer = bio_data(bio);
+ rq->data_len = bio->bi_size;
rq->bio = rq->biotail = bio;
}
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)
{
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;
}
/* 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_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_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.
*
* 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;
blk_queue_congestion_threshold(q);
if (rl->count[READ] >= queue_congestion_on_threshold(q))
- set_queue_congested(q, READ);
+ blk_set_queue_congested(q, READ);
else if (rl->count[READ] < queue_congestion_off_threshold(q))
- clear_queue_congested(q, READ);
+ blk_clear_queue_congested(q, READ);
if (rl->count[WRITE] >= queue_congestion_on_threshold(q))
- set_queue_congested(q, WRITE);
+ blk_set_queue_congested(q, WRITE);
else if (rl->count[WRITE] < queue_congestion_off_threshold(q))
- clear_queue_congested(q, WRITE);
+ blk_clear_queue_congested(q, WRITE);
if (rl->count[READ] >= q->nr_requests) {
blk_set_queue_full(q, READ);
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);
Code Review / linux-2.6.git / blobdiff