bcachefs: Nocow support

This adds support for nocow mode, where we do writes in-place when
possible. Patch components:

 - New boolean filesystem and inode option, nocow: note that when nocow
   is enabled, data checksumming and compression are implicitly disabled

 - To prevent in-place writes from racing with data moves
   (data_update.c) or bucket reuse (i.e. a bucket being reused and
   re-allocated while a nocow write is in flight, we have a new locking
   mechanism.

   Buckets can be locked for either data update or data move, using a
   fixed size hash table of two_state_shared locks. We don't have any
   chaining, meaning updates and moves to different buckets that hash to
   the same lock will wait unnecessarily - we'll want to watch for this
   becoming an issue.

 - The allocator path also needs to check for in-place writes in flight
   to a given bucket before giving it out: thus we add another counter
   to bucket_alloc_state so we can track this.

 - Fsync now may need to issue cache flushes to block devices instead of
   flushing the journal. We add a device bitmask to bch_inode_info,
   ei_devs_need_flush, which tracks devices that need to have flushes
   issued - note that this will lead to unnecessary flushes when other
   codepaths have already issued flushes, we may want to replace this with
   a sequence number.

 - New nocow write path: look up extents, and if they're writable write
   to them - otherwise fall back to the normal COW write path.

XXX: switch to sequence numbers instead of bitmask for devs needing
journal flush

XXX: ei_quota_lock being a mutex means bch2_nocow_write_done() needs to
run in process context - see if we can improve this

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

1 files changed, 4 insertions, 1 deletions

diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index fabee8302afa..24dd2defe7c7 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -543,6 +543,7 @@ DECLARE_EVENT_CLASS(bucket_alloc,
 		__field(u64,			need_journal_commit	)
 		__field(u64,			nouse			)
 		__field(bool,			nonblocking		)
+		__field(u64,			nocow			)
 		__array(char,			err,	32		)
 	),
 
@@ -560,10 +561,11 @@ DECLARE_EVENT_CLASS(bucket_alloc,
 		__entry->need_journal_commit = s->skipped_need_journal_commit;
 		__entry->nouse		= s->skipped_nouse;
 		__entry->nonblocking	= nonblocking;
+		__entry->nocow		= s->skipped_nocow;
 		strscpy(__entry->err, err, sizeof(__entry->err));
 	),
 
-	TP_printk("%d,%d reserve %s user %u bucket %llu free %llu avail %llu copygc_wait %llu/%lli seen %llu open %llu need_journal_commit %llu nouse %llu nonblocking %u err %s",
+	TP_printk("%d,%d reserve %s user %u bucket %llu free %llu avail %llu copygc_wait %llu/%lli seen %llu open %llu need_journal_commit %llu nouse %llu nocow %llu nonblocking %u err %s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->reserve,
 		  __entry->user,
@@ -576,6 +578,7 @@ DECLARE_EVENT_CLASS(bucket_alloc,
 		  __entry->open,
 		  __entry->need_journal_commit,
 		  __entry->nouse,
+		  __entry->nocow,
 		  __entry->nonblocking,
 		  __entry->err)
 );