{
struct request_queue *q = rq->q;
- if (&q->bar_rq != rq) {
+ if (!(rq->cmd_flags & REQ_FLUSH_SEQ)) {
if (error)
clear_bit(BIO_UPTODATE, &bio->bi_flags);
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
if (bio->bi_size == 0)
bio_endio(bio, error);
} else {
-
/*
- * Okay, this is the barrier request in progress, just
- * record the error;
+ * Okay, this is the sequenced flush request in
+ * progress, just record the error;
*/
- if (error && !q->orderr)
- q->orderr = error;
+ if (error && !q->flush_err)
+ q->flush_err = error;
}
}
printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n",
rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
- if (blk_pc_request(rq)) {
+ if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
printk(KERN_INFO " cdb: ");
for (bit = 0; bit < BLK_MAX_CDB; bit++)
printk("%02x ", rq->cmd[bit]);
del_timer_sync(&q->unplug_timer);
del_timer_sync(&q->timeout);
cancel_work_sync(&q->unplug_work);
+ throtl_shutdown_timer_wq(q);
}
EXPORT_SYMBOL(blk_sync_queue);
{
struct request_list *rl = &q->rq;
+ if (unlikely(rl->rq_pool))
+ return 0;
+
rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
rl->elvpriv = 0;
return NULL;
}
+ if (blk_throtl_init(q)) {
+ kmem_cache_free(blk_requestq_cachep, q);
+ return NULL;
+ }
+
setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
laptop_mode_timer_fn, (unsigned long) q);
init_timer(&q->unplug_timer);
setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
INIT_LIST_HEAD(&q->timeout_list);
+ INIT_LIST_HEAD(&q->pending_flushes);
INIT_WORK(&q->unplug_work, blk_unplug_work);
kobject_init(&q->kobj, &blk_queue_ktype);
q->request_fn = rfn;
q->prep_rq_fn = NULL;
+ q->unprep_rq_fn = NULL;
q->unplug_fn = generic_unplug_device;
q->queue_flags = QUEUE_FLAG_DEFAULT;
q->queue_lock = lock;
}
EXPORT_SYMBOL(blk_insert_request);
-/*
- * add-request adds a request to the linked list.
- * queue lock is held and interrupts disabled, as we muck with the
- * request queue list.
- */
-static inline void add_request(struct request_queue *q, struct request *req)
-{
- drive_stat_acct(req, 1);
-
- /*
- * elevator indicated where it wants this request to be
- * inserted at elevator_merge time
- */
- __elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
-}
-
static void part_round_stats_single(int cpu, struct hd_struct *part,
unsigned long now)
{
}
EXPORT_SYMBOL(blk_put_request);
+/**
+ * blk_add_request_payload - add a payload to a request
+ * @rq: request to update
+ * @page: page backing the payload
+ * @len: length of the payload.
+ *
+ * This allows to later add a payload to an already submitted request by
+ * a block driver. The driver needs to take care of freeing the payload
+ * itself.
+ *
+ * Note that this is a quite horrible hack and nothing but handling of
+ * discard requests should ever use it.
+ */
+void blk_add_request_payload(struct request *rq, struct page *page,
+ unsigned int len)
+{
+ struct bio *bio = rq->bio;
+
+ bio->bi_io_vec->bv_page = page;
+ bio->bi_io_vec->bv_offset = 0;
+ bio->bi_io_vec->bv_len = len;
+
+ bio->bi_size = len;
+ bio->bi_vcnt = 1;
+ bio->bi_phys_segments = 1;
+
+ rq->__data_len = rq->resid_len = len;
+ rq->nr_phys_segments = 1;
+ rq->buffer = bio_data(bio);
+}
+EXPORT_SYMBOL_GPL(blk_add_request_payload);
+
void init_request_from_bio(struct request *req, struct bio *bio)
{
req->cpu = bio->bi_comp_cpu;
req->cmd_type = REQ_TYPE_FS;
- /*
- * Inherit FAILFAST from bio (for read-ahead, and explicit
- * FAILFAST). FAILFAST flags are identical for req and bio.
- */
- if (bio_rw_flagged(bio, BIO_RW_AHEAD))
+ req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
+ if (bio->bi_rw & REQ_RAHEAD)
req->cmd_flags |= REQ_FAILFAST_MASK;
- else
- req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK;
-
- if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) {
- req->cmd_flags |= REQ_DISCARD;
- if (bio_rw_flagged(bio, BIO_RW_BARRIER))
- req->cmd_flags |= REQ_SOFTBARRIER;
- } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
- req->cmd_flags |= REQ_HARDBARRIER;
-
- if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
- req->cmd_flags |= REQ_RW_SYNC;
- if (bio_rw_flagged(bio, BIO_RW_META))
- req->cmd_flags |= REQ_RW_META;
- if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
- req->cmd_flags |= REQ_NOIDLE;
req->errors = 0;
req->__sector = bio->bi_sector;
int el_ret;
unsigned int bytes = bio->bi_size;
const unsigned short prio = bio_prio(bio);
- const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
- const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG);
- const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+ const bool sync = !!(bio->bi_rw & REQ_SYNC);
+ const bool unplug = !!(bio->bi_rw & REQ_UNPLUG);
+ const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
+ int where = ELEVATOR_INSERT_SORT;
int rw_flags;
- if (bio_rw_flagged(bio, BIO_RW_BARRIER) &&
- (q->next_ordered == QUEUE_ORDERED_NONE)) {
- bio_endio(bio, -EOPNOTSUPP);
- return 0;
- }
/*
* low level driver can indicate that it wants pages above a
* certain limit bounced to low memory (ie for highmem, or even
spin_lock_irq(q->queue_lock);
- if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q))
+ if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+ where = ELEVATOR_INSERT_FRONT;
+ goto get_rq;
+ }
+
+ if (elv_queue_empty(q))
goto get_rq;
el_ret = elv_merge(q, &req, bio);
*/
rw_flags = bio_data_dir(bio);
if (sync)
- rw_flags |= REQ_RW_SYNC;
+ rw_flags |= REQ_SYNC;
/*
* Grab a free request. This is might sleep but can not fail.
req->cpu = blk_cpu_to_group(smp_processor_id());
if (queue_should_plug(q) && elv_queue_empty(q))
blk_plug_device(q);
- add_request(q, req);
+
+ /* insert the request into the elevator */
+ drive_stat_acct(req, 1);
+ __elv_add_request(q, req, where, 0);
out:
if (unplug || !queue_should_plug(q))
__generic_unplug_device(q);
bdevname(bio->bi_bdev, b),
bio->bi_rw,
(unsigned long long)bio->bi_sector + bio_sectors(bio),
- (long long)(bio->bi_bdev->bd_inode->i_size >> 9));
+ (long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
set_bit(BIO_EOF, &bio->bi_flags);
}
return 0;
/* Test device or partition size, when known. */
- maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
+ maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
if (maxsector) {
sector_t sector = bio->bi_sector;
goto end_io;
}
- if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+ if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
nr_sectors > queue_max_hw_sectors(q))) {
printk(KERN_ERR "bio too big device %s (%u > %u)\n",
bdevname(bio->bi_bdev, b),
if (bio_check_eod(bio, nr_sectors))
goto end_io;
- if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
- !blk_queue_discard(q)) {
+ /*
+ * Filter flush bio's early so that make_request based
+ * drivers without flush support don't have to worry
+ * about them.
+ */
+ if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
+ bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+ if (!nr_sectors) {
+ err = 0;
+ goto end_io;
+ }
+ }
+
+ if ((bio->bi_rw & REQ_DISCARD) &&
+ (!blk_queue_discard(q) ||
+ ((bio->bi_rw & REQ_SECURE) &&
+ !blk_queue_secdiscard(q)))) {
err = -EOPNOTSUPP;
goto end_io;
}
+ blk_throtl_bio(q, &bio);
+
+ /*
+ * If bio = NULL, bio has been throttled and will be submitted
+ * later.
+ */
+ if (!bio)
+ break;
+
trace_block_bio_queue(q, bio);
ret = q->make_request_fn(q, bio);
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
*/
- if (bio_has_data(bio)) {
+ if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
if (rw & WRITE) {
count_vm_events(PGPGOUT, count);
} else {
if (unlikely(block_dump)) {
char b[BDEVNAME_SIZE];
- printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
+ printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
current->comm, task_pid_nr(current),
(rw & WRITE) ? "WRITE" : "READ",
(unsigned long long)bio->bi_sector,
- bdevname(bio->bi_bdev, b));
+ bdevname(bio->bi_bdev, b),
+ count);
}
}
* the insertion using this generic function.
*
* This function should also be useful for request stacking drivers
- * in some cases below, so export this fuction.
+ * in some cases below, so export this function.
* Request stacking drivers like request-based dm may change the queue
* limits while requests are in the queue (e.g. dm's table swapping).
* Such request stacking drivers should check those requests agaist
*/
int blk_rq_check_limits(struct request_queue *q, struct request *rq)
{
+ if (rq->cmd_flags & REQ_DISCARD)
+ return 0;
+
if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
printk(KERN_ERR "%s: over max size limit.\n", __func__);
static void blk_account_io_done(struct request *req)
{
/*
- * Account IO completion. bar_rq isn't accounted as a normal
- * IO on queueing nor completion. Accounting the containing
- * request is enough.
+ * Account IO completion. flush_rq isn't accounted as a
+ * normal IO on queueing nor completion. Accounting the
+ * containing request is enough.
*/
- if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
+ if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) {
unsigned long duration = jiffies - req->start_time;
const int rw = rq_data_dir(req);
struct hd_struct *part;
* sees this request (possibly after
* requeueing). Notify IO scheduler.
*/
- if (blk_sorted_rq(rq))
+ if (rq->cmd_flags & REQ_SORTED)
elv_activate_rq(q, rq);
/*
* TODO: tj: This is too subtle. It would be better to let
* low level drivers do what they see fit.
*/
- if (blk_fs_request(req))
+ if (req->cmd_type == REQ_TYPE_FS)
req->errors = 0;
- if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) {
+ if (error && req->cmd_type == REQ_TYPE_FS &&
+ !(req->cmd_flags & REQ_QUIET)) {
printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
req->rq_disk ? req->rq_disk->disk_name : "?",
(unsigned long long)blk_rq_pos(req));
req->buffer = bio_data(req->bio);
/* update sector only for requests with clear definition of sector */
- if (blk_fs_request(req) || blk_discard_rq(req))
+ if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
req->__sector += total_bytes >> 9;
/* mixed attributes always follow the first bio */
blk_update_request(rq->next_rq, error, bidi_bytes))
return true;
- add_disk_randomness(rq->rq_disk);
+ if (blk_queue_add_random(rq->q))
+ add_disk_randomness(rq->rq_disk);
return false;
}
+/**
+ * blk_unprep_request - unprepare a request
+ * @req: the request
+ *
+ * This function makes a request ready for complete resubmission (or
+ * completion). It happens only after all error handling is complete,
+ * so represents the appropriate moment to deallocate any resources
+ * that were allocated to the request in the prep_rq_fn. The queue
+ * lock is held when calling this.
+ */
+void blk_unprep_request(struct request *req)
+{
+ struct request_queue *q = req->q;
+
+ req->cmd_flags &= ~REQ_DONTPREP;
+ if (q->unprep_rq_fn)
+ q->unprep_rq_fn(q, req);
+}
+EXPORT_SYMBOL_GPL(blk_unprep_request);
+
/*
* queue lock must be held
*/
BUG_ON(blk_queued_rq(req));
- if (unlikely(laptop_mode) && blk_fs_request(req))
+ if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
laptop_io_completion(&req->q->backing_dev_info);
blk_delete_timer(req);
+ if (req->cmd_flags & REQ_DONTPREP)
+ blk_unprep_request(req);
+
+
blk_account_io_done(req);
if (req->end_io)
struct bio *bio)
{
/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
- rq->cmd_flags |= bio->bi_rw & REQ_RW;
+ rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
if (bio_has_data(bio)) {
rq->nr_phys_segments = bio_phys_segments(q, bio);
static void __blk_rq_prep_clone(struct request *dst, struct request *src)
{
dst->cpu = src->cpu;
- dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
+ dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
dst->cmd_type = src->cmd_type;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
}
EXPORT_SYMBOL(kblockd_schedule_work);
+int kblockd_schedule_delayed_work(struct request_queue *q,
+ struct delayed_work *dwork, unsigned long delay)
+{
+ return queue_delayed_work(kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_schedule_delayed_work);
+
int __init blk_dev_init(void)
{
BUILD_BUG_ON(__REQ_NR_BITS > 8 *
Code Review / linux-2.6.git / blobdiff