#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
-#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
-#include <trace/block.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/block.h>
#include "blk.h"
-DEFINE_TRACE(block_plug);
-DEFINE_TRACE(block_unplug_io);
-DEFINE_TRACE(block_unplug_timer);
-DEFINE_TRACE(block_getrq);
-DEFINE_TRACE(block_sleeprq);
-DEFINE_TRACE(block_rq_requeue);
-DEFINE_TRACE(block_bio_backmerge);
-DEFINE_TRACE(block_bio_frontmerge);
-DEFINE_TRACE(block_bio_queue);
-DEFINE_TRACE(block_rq_complete);
-DEFINE_TRACE(block_remap); /* Also used in drivers/md/dm.c */
EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
static int __make_request(struct request_queue *q, struct bio *bio);
part_stat_inc(cpu, part, merges[rw]);
else {
part_round_stats(cpu, part);
- part_inc_in_flight(part);
+ part_inc_in_flight(part, rw);
}
part_stat_unlock();
q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
q->backing_dev_info.unplug_io_data = q;
+ q->backing_dev_info.ra_pages =
+ (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+ q->backing_dev_info.state = 0;
+ q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+ q->backing_dev_info.name = "block";
+
err = bdi_init(&q->backing_dev_info);
if (err) {
kmem_cache_free(blk_requestq_cachep, q);
return NULL;
}
- /*
- * if caller didn't supply a lock, they get per-queue locking with
- * our embedded lock
- */
- if (!lock)
- lock = &q->__queue_lock;
-
q->request_fn = rfn;
q->prep_rq_fn = NULL;
q->unplug_fn = generic_unplug_device;
q->sg_reserved_size = INT_MAX;
- blk_set_cmd_filter_defaults(&q->cmd_filter);
-
/*
* all done
*/
/**
* blk_make_request - given a bio, allocate a corresponding struct request.
- *
+ * @q: target request queue
* @bio: The bio describing the memory mappings that will be submitted for IO.
* It may be a chained-bio properly constructed by block/bio layer.
+ * @gfp_mask: gfp flags to be used for memory allocation
*
* blk_make_request is the parallel of generic_make_request for BLOCK_PC
* type commands. Where the struct request needs to be farther initialized by
if (now == part->stamp)
return;
- if (part->in_flight) {
+ if (part_in_flight(part)) {
__part_stat_add(cpu, part, time_in_queue,
- part->in_flight * (now - part->stamp));
+ part_in_flight(part) * (now - part->stamp));
__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
}
part->stamp = now;
req->cmd_type = REQ_TYPE_FS;
/*
- * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
+ * Inherit FAILFAST from bio (for read-ahead, and explicit
+ * FAILFAST). FAILFAST flags are identical for req and bio.
*/
- if (bio_rw_ahead(bio))
- req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
- REQ_FAILFAST_DRIVER);
- if (bio_failfast_dev(bio))
- req->cmd_flags |= REQ_FAILFAST_DEV;
- if (bio_failfast_transport(bio))
- req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
- if (bio_failfast_driver(bio))
- req->cmd_flags |= REQ_FAILFAST_DRIVER;
-
- if (unlikely(bio_discard(bio))) {
+ if (bio_rw_flagged(bio, BIO_RW_AHEAD))
+ 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_barrier(bio))
+ if (bio_rw_flagged(bio, BIO_RW_BARRIER))
req->cmd_flags |= REQ_SOFTBARRIER;
- req->q->prepare_discard_fn(req->q, req);
- } else if (unlikely(bio_barrier(bio)))
+ } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)))
req->cmd_flags |= REQ_HARDBARRIER;
- if (bio_sync(bio))
+ if (bio_rw_flagged(bio, BIO_RW_SYNCIO))
req->cmd_flags |= REQ_RW_SYNC;
- if (bio_rw_meta(bio))
+ if (bio_rw_flagged(bio, BIO_RW_META))
req->cmd_flags |= REQ_RW_META;
- if (bio_noidle(bio))
+ if (bio_rw_flagged(bio, BIO_RW_NOIDLE))
req->cmd_flags |= REQ_NOIDLE;
req->errors = 0;
*/
static inline bool queue_should_plug(struct request_queue *q)
{
- return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
+ return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
}
static int __make_request(struct request_queue *q, struct bio *bio)
int el_ret;
unsigned int bytes = bio->bi_size;
const unsigned short prio = bio_prio(bio);
- const int sync = bio_sync(bio);
- const int unplug = bio_unplug(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;
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_barrier(bio)) || elv_queue_empty(q))
+ if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q))
goto get_rq;
el_ret = elv_merge(q, &req, bio);
trace_block_bio_backmerge(q, bio);
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+ blk_rq_set_mixed_merge(req);
+
req->biotail->bi_next = bio;
req->biotail = bio;
req->__data_len += bytes;
trace_block_bio_frontmerge(q, bio);
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+ blk_rq_set_mixed_merge(req);
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= ff;
+ }
+
bio->bi_next = req->bio;
req->bio = bio;
bio->bi_bdev = bdev->bd_contains;
trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
- bdev->bd_dev, bio->bi_sector,
+ bdev->bd_dev,
bio->bi_sector - p->start_sect);
}
}
goto end_io;
}
- if (unlikely(nr_sectors > queue_max_hw_sectors(q))) {
+ if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+ nr_sectors > queue_max_hw_sectors(q))) {
printk(KERN_ERR "bio too big device %s (%u > %u)\n",
bdevname(bio->bi_bdev, b),
bio_sectors(bio),
goto end_io;
if (old_sector != -1)
- trace_block_remap(q, bio, old_dev, bio->bi_sector,
- old_sector);
-
- trace_block_bio_queue(q, bio);
+ trace_block_remap(q, bio, old_dev, old_sector);
old_sector = bio->bi_sector;
old_dev = bio->bi_bdev->bd_dev;
if (bio_check_eod(bio, nr_sectors))
goto end_io;
- if (bio_discard(bio) && !q->prepare_discard_fn) {
- err = -EOPNOTSUPP;
- goto end_io;
- }
- if (bio_barrier(bio) && bio_has_data(bio) &&
- (q->next_ordered == QUEUE_ORDERED_NONE)) {
+ if (bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+ !blk_queue_discard(q)) {
err = -EOPNOTSUPP;
goto end_io;
}
+ trace_block_bio_queue(q, bio);
+
ret = q->make_request_fn(q, bio);
} while (ret);
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ * A request could be merge of IOs which require different failure
+ * handling. This function determines the number of bytes which
+ * can be failed from the beginning of the request without
+ * crossing into area which need to be retried further.
+ *
+ * Return:
+ * The number of bytes to fail.
+ *
+ * Context:
+ * queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+ unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+ unsigned int bytes = 0;
+ struct bio *bio;
+
+ if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+ return blk_rq_bytes(rq);
+
+ /*
+ * Currently the only 'mixing' which can happen is between
+ * different fastfail types. We can safely fail portions
+ * which have all the failfast bits that the first one has -
+ * the ones which are at least as eager to fail as the first
+ * one.
+ */
+ for (bio = rq->bio; bio; bio = bio->bi_next) {
+ if ((bio->bi_rw & ff) != ff)
+ break;
+ bytes += bio->bi_size;
+ }
+
+ /* this could lead to infinite loop */
+ BUG_ON(blk_rq_bytes(rq) && !bytes);
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (blk_do_io_stat(req)) {
part_stat_inc(cpu, part, ios[rw]);
part_stat_add(cpu, part, ticks[rw], duration);
part_round_stats(cpu, part);
- part_dec_in_flight(part);
+ part_dec_in_flight(part, rw);
part_stat_unlock();
}
break;
} else if (ret == BLKPREP_KILL) {
rq->cmd_flags |= REQ_QUIET;
+ /*
+ * Mark this request as started so we don't trigger
+ * any debug logic in the end I/O path.
+ */
+ blk_start_request(rq);
__blk_end_request_all(rq, -EIO);
} else {
printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
* and to it is freed is accounted as io that is in progress at
* the driver side.
*/
- if (blk_account_rq(rq))
+ if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]++;
+ /*
+ * Mark this device as supporting hardware queuing, if
+ * we have more IOs in flight than 4.
+ */
+ if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
+ set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
+ }
}
/**
* resid_len to full count and add the timeout handler.
*/
req->resid_len = blk_rq_bytes(req);
+ if (unlikely(blk_bidi_rq(req)))
+ req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
+
blk_add_timer(req);
}
EXPORT_SYMBOL(blk_start_request);
/**
* blk_update_request - Special helper function for request stacking drivers
- * @rq: the request being processed
+ * @req: the request being processed
* @error: %0 for success, < %0 for error
- * @nr_bytes: number of bytes to complete @rq
+ * @nr_bytes: number of bytes to complete @req
*
* Description:
- * Ends I/O on a number of bytes attached to @rq, but doesn't complete
- * the request structure even if @rq doesn't have leftover.
- * If @rq has leftover, sets it up for the next range of segments.
+ * Ends I/O on a number of bytes attached to @req, but doesn't complete
+ * the request structure even if @req doesn't have leftover.
+ * If @req has leftover, sets it up for the next range of segments.
*
* This special helper function is only for request stacking drivers
* (e.g. request-based dm) so that they can handle partial completion.
if (blk_fs_request(req) || blk_discard_rq(req))
req->__sector += total_bytes >> 9;
+ /* mixed attributes always follow the first bio */
+ if (req->cmd_flags & REQ_MIXED_MERGE) {
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+ }
+
/*
* If total number of sectors is less than the first segment
* size, something has gone terribly wrong.
{
return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
-EXPORT_SYMBOL_GPL(blk_end_request);
+EXPORT_SYMBOL(blk_end_request);
/**
* blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
- * @err: %0 for success, < %0 for error
+ * @error: %0 for success, < %0 for error
*
* Description:
* Completely finish @rq.
pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
BUG_ON(pending);
}
-EXPORT_SYMBOL_GPL(blk_end_request_all);
+EXPORT_SYMBOL(blk_end_request_all);
/**
* blk_end_request_cur - Helper function to finish the current request chunk.
* @rq: the request to finish the current chunk for
- * @err: %0 for success, < %0 for error
+ * @error: %0 for success, < %0 for error
*
* Description:
* Complete the current consecutively mapped chunk from @rq.
{
return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
-EXPORT_SYMBOL_GPL(blk_end_request_cur);
+EXPORT_SYMBOL(blk_end_request_cur);
+
+/**
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ * Complete @rq till the next failure boundary.
+ *
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
+{
+ WARN_ON(error >= 0);
+ return blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_err);
/**
* __blk_end_request - Helper function for drivers to complete the request.
{
return __blk_end_bidi_request(rq, error, nr_bytes, 0);
}
-EXPORT_SYMBOL_GPL(__blk_end_request);
+EXPORT_SYMBOL(__blk_end_request);
/**
* __blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
- * @err: %0 for success, < %0 for error
+ * @error: %0 for success, < %0 for error
*
* Description:
* Completely finish @rq. Must be called with queue lock held.
pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
BUG_ON(pending);
}
-EXPORT_SYMBOL_GPL(__blk_end_request_all);
+EXPORT_SYMBOL(__blk_end_request_all);
/**
* __blk_end_request_cur - Helper function to finish the current request chunk.
* @rq: the request to finish the current chunk for
- * @err: %0 for success, < %0 for error
+ * @error: %0 for success, < %0 for error
*
* Description:
* Complete the current consecutively mapped chunk from @rq. Must
{
return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
-EXPORT_SYMBOL_GPL(__blk_end_request_cur);
+EXPORT_SYMBOL(__blk_end_request_cur);
+
+/**
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ * Complete @rq till the next failure boundary. Must be called
+ * with queue lock held.
+ *
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
+{
+ WARN_ON(error >= 0);
+ return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio)
{
- /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and
- we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */
- rq->cmd_flags |= (bio->bi_rw & 3);
+ /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
+ rq->cmd_flags |= bio->bi_rw & REQ_RW;
if (bio_has_data(bio)) {
rq->nr_phys_segments = bio_phys_segments(q, bio);
}
EXPORT_SYMBOL_GPL(blk_lld_busy);
+/**
+ * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
+ * @rq: the clone request to be cleaned up
+ *
+ * Description:
+ * Free all bios in @rq for a cloned request.
+ */
+void blk_rq_unprep_clone(struct request *rq)
+{
+ struct bio *bio;
+
+ while ((bio = rq->bio) != NULL) {
+ rq->bio = bio->bi_next;
+
+ bio_put(bio);
+ }
+}
+EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
+
+/*
+ * Copy attributes of the original request to the clone request.
+ * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
+ */
+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_type = src->cmd_type;
+ dst->__sector = blk_rq_pos(src);
+ dst->__data_len = blk_rq_bytes(src);
+ dst->nr_phys_segments = src->nr_phys_segments;
+ dst->ioprio = src->ioprio;
+ dst->extra_len = src->extra_len;
+}
+
+/**
+ * blk_rq_prep_clone - Helper function to setup clone request
+ * @rq: the request to be setup
+ * @rq_src: original request to be cloned
+ * @bs: bio_set that bios for clone are allocated from
+ * @gfp_mask: memory allocation mask for bio
+ * @bio_ctr: setup function to be called for each clone bio.
+ * Returns %0 for success, non %0 for failure.
+ * @data: private data to be passed to @bio_ctr
+ *
+ * Description:
+ * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
+ * The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
+ * are not copied, and copying such parts is the caller's responsibility.
+ * Also, pages which the original bios are pointing to are not copied
+ * and the cloned bios just point same pages.
+ * So cloned bios must be completed before original bios, which means
+ * the caller must complete @rq before @rq_src.
+ */
+int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+ struct bio_set *bs, gfp_t gfp_mask,
+ int (*bio_ctr)(struct bio *, struct bio *, void *),
+ void *data)
+{
+ struct bio *bio, *bio_src;
+
+ if (!bs)
+ bs = fs_bio_set;
+
+ blk_rq_init(NULL, rq);
+
+ __rq_for_each_bio(bio_src, rq_src) {
+ bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
+ if (!bio)
+ goto free_and_out;
+
+ __bio_clone(bio, bio_src);
+
+ if (bio_integrity(bio_src) &&
+ bio_integrity_clone(bio, bio_src, gfp_mask, bs))
+ goto free_and_out;
+
+ if (bio_ctr && bio_ctr(bio, bio_src, data))
+ goto free_and_out;
+
+ if (rq->bio) {
+ rq->biotail->bi_next = bio;
+ rq->biotail = bio;
+ } else
+ rq->bio = rq->biotail = bio;
+ }
+
+ __blk_rq_prep_clone(rq, rq_src);
+
+ return 0;
+
+free_and_out:
+ if (bio)
+ bio_free(bio, bs);
+ blk_rq_unprep_clone(rq);
+
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
+
int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
{
return queue_work(kblockd_workqueue, work);