afs: Parse the VolSync record in the reply of a number of RPC ops

A number of fileserver RPC operations return a VolSync record as part of
their reply that gives some information about the state of the volume being
accessed, including:

 (1) A volume Creation timestamp.  For an RW volume, this is the time at
     which the volume was created; if it changes, the RW volume was
     presumably restored from a backup and all cached data should be
     scrubbed as Data Version numbers could regress on the files in the
     volume.

     For an RO volume, this is the time it was last snapshotted from the RW
     volume.  It is expected to advance each time this happens; if it
     regresses, cached data should be scrubbed.

 (2) A volume Update timestamp (Auristor only).  For an RW volume, this is
     updated any time any change is made to a volume or its contents.  If
     it regresses, all cached data must be scrubbed.

     For an RO volume, this is a copy of the RW volume's Update timestamp
     at the point of snapshotting.  It can be used as a version number when
     checking to see if a callback on a RO volume was due to a snapshot.
     If it regresses, all cached data must be scrubbed.

but this is currently not made use of by the in-kernel afs filesystem.

Make the afs filesystem use this by:

 (1) Add an update time field to the afs_volsync struct and use a value of
     TIME64_MIN in both that and the creation time to indicate that they
     are unset.

 (2) Add creation and update time fields to the afs_volume struct and use
     this to track the two timestamps.

 (3) Add a volsync_lock mutex to the afs_volume struct to control
     modification access for when we detect a change in these values.

 (3) Add a 'pre-op volsync' struct to the afs_operation struct to record
     the state of the volume tracking before the op.

 (4) Add a new counter, cb_scrub, to the afs_volume struct to count events
     that require all data to be scrubbed.  A copy is placed in the
     afs_vnode struct (inode) and if they no longer match, a scrub takes
     place.

 (5) When the result of an operation is being parsed, parse the VolSync
     data too, if it is provided.  Note that the two timestamps are handled
     separately, since they don't work in quite the same way.

     - If the afs_volume tracking is unset, just set it and do nothing
       else.

     - If the result timestamps are the same as the ones in afs_volume, do
       nothing.

     - If the timestamps regress, increment cb_scrub if not already done
       so.

     - If the creation timestamp on a RW volume changes, increment cb_scrub
       if not already done so.

     - If the creation timestamp on a RO volume advances, update the server
       list and see if the current server has been excluded, if so reissue
       the op.  Once over half of the replication sites have been updated,
       increment cb_ro_snapshot to indicate updates may be required and
       switch over to excluding unupdated replication sites.

     - If the creation timestamp on a Backup volume advances, just
       increment cb_ro_snapshot to trigger updates.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org

1 files changed, 29 insertions, 1 deletions

diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 63ab23876be8..bbe8dcab4b32 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -440,13 +440,17 @@ enum yfs_cm_operation {
 	EM(afs_cb_break_no_break,		"no-break")		\
 	EM(afs_cb_break_no_promise,		"no-promise")		\
 	EM(afs_cb_break_for_callback,		"break-cb")		\
+	EM(afs_cb_break_for_creation_regress,	"creation-regress")	\
 	EM(afs_cb_break_for_deleted,		"break-del")		\
 	EM(afs_cb_break_for_lapsed,		"break-lapsed")		\
 	EM(afs_cb_break_for_s_reinit,		"s-reinit")		\
 	EM(afs_cb_break_for_unlink,		"break-unlink")		\
+	EM(afs_cb_break_for_update_regress,	"update-regress")	\
 	EM(afs_cb_break_for_v_break,		"break-v")		\
 	EM(afs_cb_break_for_volume_callback,	"break-v-cb")		\
-	E_(afs_cb_break_for_zap,		"break-zap")
+	EM(afs_cb_break_for_vos_release,	"break-vos-release")	\
+	EM(afs_cb_break_for_zap,		"break-zap")		\
+	E_(afs_cb_break_volume_excluded,	"vol-excluded")
 
 /*
  * Generate enums for tracing information.
@@ -1249,6 +1253,30 @@ TRACE_EVENT(afs_get_tree,
 		      __entry->cell, __entry->volume, __entry->vid)
 	    );
 
+TRACE_EVENT(afs_cb_v_break,
+	    TP_PROTO(afs_volid_t vid, unsigned int cb_v_break,
+		     enum afs_cb_break_reason reason),
+
+	    TP_ARGS(vid, cb_v_break, reason),
+
+	    TP_STRUCT__entry(
+		    __field(afs_volid_t,		vid)
+		    __field(unsigned int,		cb_v_break)
+		    __field(enum afs_cb_break_reason,	reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->vid	= vid;
+		    __entry->cb_v_break	= cb_v_break;
+		    __entry->reason	= reason;
+			   ),
+
+	    TP_printk("%llx vb=%x %s",
+		      __entry->vid,
+		      __entry->cb_v_break,
+		      __print_symbolic(__entry->reason, afs_cb_break_reasons))
+	    );
+
 TRACE_EVENT(afs_cb_break,
 	    TP_PROTO(struct afs_fid *fid, unsigned int cb_break,
 		     enum afs_cb_break_reason reason, bool skipped),