btrfs: add trace event for submitted RAID56 bio

Add tracepoint for better insight to how the RAID56 data are submitted.

The output looks like this: (trace event header and UUID skipped)

   raid56_read_partial: full_stripe=389152768 devid=3 type=DATA1 offset=32768 opf=0x0 physical=323059712 len=32768
   raid56_read_partial: full_stripe=389152768 devid=1 type=DATA2 offset=0 opf=0x0 physical=67174400 len=65536
   raid56_write_stripe: full_stripe=389152768 devid=3 type=DATA1 offset=0 opf=0x1 physical=323026944 len=32768
   raid56_write_stripe: full_stripe=389152768 devid=2 type=PQ1 offset=0 opf=0x1 physical=323026944 len=32768

The above debug output is from a 32K data write into an empty RAID56
data chunk.

Some explanation on the event output:

  full_stripe:	the logical bytenr of the full stripe
  devid:	btrfs devid
  type:		raid stripe type.
         	DATA1:	the first data stripe
         	DATA2:	the second data stripe
         	PQ1:	the P stripe
         	PQ2:	the Q stripe
  offset:	the offset inside the stripe.
  opf:		the bio op type
  physical:	the physical offset the bio is for
  len:		the length of the bio

The first two lines are from partial RMW read, which is reading the
remaining data stripes from disks.

The last two lines are for full stripe RMW write, which is writing the
involved two 16K stripes (one for DATA1 stripe, one for P stripe).
The stripe for DATA2 doesn't need to be written.

There are 5 types of trace events:

- raid56_read_partial
  Read remaining data for regular read/write path.

- raid56_write_stripe
  Write the modified stripes for regular read/write path.

- raid56_scrub_read_recover
  Read remaining data for scrub recovery path.

- raid56_scrub_write_stripe
  Write the modified stripes for scrub path.

- raid56_scrub_read
  Read remaining data for scrub path.

Also, since the trace events are included at super.c, we have to export
needed structure definitions to 'raid56.h' and include the header in
super.c, or we're unable to access those members.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ reformat comments ]
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 94 insertions, 0 deletions

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 9ae94ef3e270..29fa8ea2cc0f 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -30,6 +30,8 @@ struct btrfs_qgroup;
 struct extent_io_tree;
 struct prelim_ref;
 struct btrfs_space_info;
+struct btrfs_raid_bio;
+struct raid56_bio_trace_info;
 
 #define show_ref_type(type)						\
 	__print_symbolic(type,						\
@@ -2258,6 +2260,98 @@ DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned,
 	TP_ARGS(fs_info, sinfo, old, diff)
 );
 
+DECLARE_EVENT_CLASS(btrfs_raid56_bio,
+
+	TP_PROTO(const struct btrfs_raid_bio *rbio,
+		 const struct bio *bio,
+		 const struct raid56_bio_trace_info *trace_info),
+
+	TP_ARGS(rbio, bio, trace_info),
+
+	TP_STRUCT__entry_btrfs(
+		__field(	u64,	full_stripe	)
+		__field(	u64,	physical	)
+		__field(	u64,	devid		)
+		__field(	u32,	offset		)
+		__field(	u32,	len		)
+		__field(	u8,	opf		)
+		__field(	u8,	total_stripes	)
+		__field(	u8,	real_stripes	)
+		__field(	u8,	nr_data		)
+		__field(	u8,	stripe_nr	)
+	),
+
+	TP_fast_assign_btrfs(rbio->bioc->fs_info,
+		__entry->full_stripe	= rbio->bioc->raid_map[0];
+		__entry->physical	= bio->bi_iter.bi_sector << SECTOR_SHIFT;
+		__entry->len		= bio->bi_iter.bi_size;
+		__entry->opf		= bio_op(bio);
+		__entry->devid		= trace_info->devid;
+		__entry->offset		= trace_info->offset;
+		__entry->stripe_nr	= trace_info->stripe_nr;
+		__entry->total_stripes	= rbio->bioc->num_stripes;
+		__entry->real_stripes	= rbio->real_stripes;
+		__entry->nr_data	= rbio->nr_data;
+	),
+	/*
+	 * For type output, we need to output things like "DATA1"
+	 * (the first data stripe), "DATA2" (the second data stripe),
+	 * "PQ1" (P stripe),"PQ2" (Q stripe), "REPLACE0" (replace target device).
+	 */
+	TP_printk_btrfs(
+"full_stripe=%llu devid=%lld type=%s%d offset=%d opf=0x%x physical=%llu len=%u",
+		__entry->full_stripe, __entry->devid,
+		(__entry->stripe_nr < __entry->nr_data) ? "DATA" :
+			((__entry->stripe_nr < __entry->real_stripes) ? "PQ" :
+			 "REPLACE"),
+		(__entry->stripe_nr < __entry->nr_data) ?
+			(__entry->stripe_nr + 1) :
+			((__entry->stripe_nr < __entry->real_stripes) ?
+			 (__entry->stripe_nr - __entry->nr_data + 1) : 0),
+		__entry->offset, __entry->opf, __entry->physical, __entry->len)
+);
+
+DEFINE_EVENT(btrfs_raid56_bio, raid56_read_partial,
+	TP_PROTO(const struct btrfs_raid_bio *rbio,
+		 const struct bio *bio,
+		 const struct raid56_bio_trace_info *trace_info),
+
+	TP_ARGS(rbio, bio, trace_info)
+);
+
+DEFINE_EVENT(btrfs_raid56_bio, raid56_write_stripe,
+	TP_PROTO(const struct btrfs_raid_bio *rbio,
+		 const struct bio *bio,
+		 const struct raid56_bio_trace_info *trace_info),
+
+	TP_ARGS(rbio, bio, trace_info)
+);
+
+
+DEFINE_EVENT(btrfs_raid56_bio, raid56_scrub_write_stripe,
+	TP_PROTO(const struct btrfs_raid_bio *rbio,
+		 const struct bio *bio,
+		 const struct raid56_bio_trace_info *trace_info),
+
+	TP_ARGS(rbio, bio, trace_info)
+);
+
+DEFINE_EVENT(btrfs_raid56_bio, raid56_scrub_read,
+	TP_PROTO(const struct btrfs_raid_bio *rbio,
+		 const struct bio *bio,
+		 const struct raid56_bio_trace_info *trace_info),
+
+	TP_ARGS(rbio, bio, trace_info)
+);
+
+DEFINE_EVENT(btrfs_raid56_bio, raid56_scrub_read_recover,
+	TP_PROTO(const struct btrfs_raid_bio *rbio,
+		 const struct bio *bio,
+		 const struct raid56_bio_trace_info *trace_info),
+
+	TP_ARGS(rbio, bio, trace_info)
+);
+
 #endif /* _TRACE_BTRFS_H */
 
 /* This part must be outside protection */