Commit fbbaf700 authored by NeilBrown's avatar NeilBrown Committed by Jens Axboe

block: trace completion of all bios.

Currently only dm and md/raid5 bios trigger
trace_block_bio_complete().  Now that we have bio_chain() and
bio_inc_remaining(), it is not possible, in general, for a driver to
know when the bio is really complete.  Only bio_endio() knows that.

So move the trace_block_bio_complete() call to bio_endio().

Now trace_block_bio_complete() pairs with trace_block_bio_queue().
Any bio for which a 'queue' event is traced, will subsequently
generate a 'complete' event.

There are a few cases where completion tracing is not wanted.
1/ If blk_update_request() has already generated a completion
   trace event at the 'request' level, there is no point generating
   one at the bio level too.  In this case the bi_sector and bi_size
   will have changed, so the bio level event would be wrong

2/ If the bio hasn't actually been queued yet, but is being aborted
   early, then a trace event could be confusing.  Some filesystems
   call bio_endio() but do not want tracing.

3/ The bio_integrity code interposes itself by replacing bi_end_io,
   then restoring it and calling bio_endio() again.  This would produce
   two identical trace events if left like that.

To handle these, we introduce a flag BIO_TRACE_COMPLETION and only
produce the trace event when this is set.
We address point 1 above by clearing the flag in blk_update_request().
We address point 2 above by only setting the flag when
generic_make_request() is called.
We address point 3 above by clearing the flag after generating a
completion event.

When bio_split() is used on a bio, particularly in blk_queue_split(),
there is an extra complication.  A new bio is split off the front, and
may be handle directly without going through generic_make_request().
The old bio, which has been advanced, is passed to
generic_make_request(), so it will trigger a trace event a second
time.
Probably the best result when a split happens is to see a single
'queue' event for the whole bio, then multiple 'complete' events - one
for each component.  To achieve this was can:
- copy the BIO_TRACE_COMPLETION flag to the new bio in bio_split()
- avoid generating a 'queue' event if BIO_TRACE_COMPLETION is already set.
This way, the split-off bio won't create a queue event, the original
won't either even if it re-submitted to generic_make_request(),
but both will produce completion events, each for their own range.

So if generic_make_request() is called (which generates a QUEUED
event), then bi_endio() will create a single COMPLETE event for each
range that the bio is split into, unless the driver has explicitly
requested it not to.
Signed-off-by: default avatarNeilBrown <neilb@suse.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
parent dbde775c
...@@ -1826,6 +1826,11 @@ static inline bool bio_remaining_done(struct bio *bio) ...@@ -1826,6 +1826,11 @@ static inline bool bio_remaining_done(struct bio *bio)
* bio_endio() will end I/O on the whole bio. bio_endio() is the preferred * bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
* way to end I/O on a bio. No one should call bi_end_io() directly on a * way to end I/O on a bio. No one should call bi_end_io() directly on a
* bio unless they own it and thus know that it has an end_io function. * bio unless they own it and thus know that it has an end_io function.
*
* bio_endio() can be called several times on a bio that has been chained
* using bio_chain(). The ->bi_end_io() function will only be called the
* last time. At this point the BLK_TA_COMPLETE tracing event will be
* generated if BIO_TRACE_COMPLETION is set.
**/ **/
void bio_endio(struct bio *bio) void bio_endio(struct bio *bio)
{ {
...@@ -1846,6 +1851,12 @@ void bio_endio(struct bio *bio) ...@@ -1846,6 +1851,12 @@ void bio_endio(struct bio *bio)
goto again; goto again;
} }
if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
trace_block_bio_complete(bdev_get_queue(bio->bi_bdev),
bio, bio->bi_error);
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
}
blk_throtl_bio_endio(bio); blk_throtl_bio_endio(bio);
if (bio->bi_end_io) if (bio->bi_end_io)
bio->bi_end_io(bio); bio->bi_end_io(bio);
...@@ -1885,6 +1896,9 @@ struct bio *bio_split(struct bio *bio, int sectors, ...@@ -1885,6 +1896,9 @@ struct bio *bio_split(struct bio *bio, int sectors,
bio_advance(bio, split->bi_iter.bi_size); bio_advance(bio, split->bi_iter.bi_size);
if (bio_flagged(bio, BIO_TRACE_COMPLETION))
bio_set_flag(bio, BIO_TRACE_COMPLETION);
return split; return split;
} }
EXPORT_SYMBOL(bio_split); EXPORT_SYMBOL(bio_split);
......
...@@ -1957,7 +1957,13 @@ generic_make_request_checks(struct bio *bio) ...@@ -1957,7 +1957,13 @@ generic_make_request_checks(struct bio *bio)
if (!blkcg_bio_issue_check(q, bio)) if (!blkcg_bio_issue_check(q, bio))
return false; return false;
if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
trace_block_bio_queue(q, bio); trace_block_bio_queue(q, bio);
/* Now that enqueuing has been traced, we need to trace
* completion as well.
*/
bio_set_flag(bio, BIO_TRACE_COMPLETION);
}
return true; return true;
not_supported: not_supported:
...@@ -2622,6 +2628,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) ...@@ -2622,6 +2628,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
if (bio_bytes == bio->bi_iter.bi_size) if (bio_bytes == bio->bi_iter.bi_size)
req->bio = bio->bi_next; req->bio = bio->bi_next;
/* Completion has already been traced */
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
req_bio_endio(req, bio, bio_bytes, error); req_bio_endio(req, bio, bio_bytes, error);
total_bytes += bio_bytes; total_bytes += bio_bytes;
......
...@@ -810,7 +810,6 @@ static void dec_pending(struct dm_io *io, int error) ...@@ -810,7 +810,6 @@ static void dec_pending(struct dm_io *io, int error)
queue_io(md, bio); queue_io(md, bio);
} else { } else {
/* done with normal IO or empty flush */ /* done with normal IO or empty flush */
trace_block_bio_complete(md->queue, bio, io_error);
bio->bi_error = io_error; bio->bi_error = io_error;
bio_endio(bio); bio_endio(bio);
} }
......
...@@ -5031,8 +5031,6 @@ static void raid5_align_endio(struct bio *bi) ...@@ -5031,8 +5031,6 @@ static void raid5_align_endio(struct bio *bi)
rdev_dec_pending(rdev, conf->mddev); rdev_dec_pending(rdev, conf->mddev);
if (!error) { if (!error) {
trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
raid_bi, 0);
bio_endio(raid_bi); bio_endio(raid_bi);
if (atomic_dec_and_test(&conf->active_aligned_reads)) if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent); wake_up(&conf->wait_for_quiescent);
......
...@@ -110,6 +110,8 @@ struct bio { ...@@ -110,6 +110,8 @@ struct bio {
#define BIO_REFFED 8 /* bio has elevated ->bi_cnt */ #define BIO_REFFED 8 /* bio has elevated ->bi_cnt */
#define BIO_THROTTLED 9 /* This bio has already been subjected to #define BIO_THROTTLED 9 /* This bio has already been subjected to
* throttling rules. Don't do it again. */ * throttling rules. Don't do it again. */
#define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion
* of this bio. */
/* See BVEC_POOL_OFFSET below before adding new flags */ /* See BVEC_POOL_OFFSET below before adding new flags */
/* /*
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment