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, 197 insertions, 2 deletions

diff --git a/fs/afs/validation.c b/fs/afs/validation.c
index 18ba2c5e8ead..6aadd5e075e4 100644
--- a/fs/afs/validation.c
+++ b/fs/afs/validation.c
@@ -11,6 +11,201 @@
 #include "internal.h"
 
 /*
+ * See if the server we've just talked to is currently excluded.
+ */
+static bool __afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
+{
+	const struct afs_server_entry *se;
+	const struct afs_server_list *slist;
+	bool is_excluded = true;
+	int i;
+
+	rcu_read_lock();
+
+	slist = rcu_dereference(volume->servers);
+	for (i = 0; i < slist->nr_servers; i++) {
+		se = &slist->servers[i];
+		if (op->server == se->server) {
+			is_excluded = test_bit(AFS_SE_EXCLUDED, &se->flags);
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+	return is_excluded;
+}
+
+/*
+ * Update the volume's server list when the creation time changes and see if
+ * the server we've just talked to is currently excluded.
+ */
+static int afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
+{
+	int ret;
+
+	if (__afs_is_server_excluded(op, volume))
+		return 1;
+
+	set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags);
+	ret = afs_check_volume_status(op->volume, op);
+	if (ret < 0)
+		return ret;
+
+	return __afs_is_server_excluded(op, volume);
+}
+
+/*
+ * Handle a change to the volume creation time in the VolSync record.
+ */
+static int afs_update_volume_creation_time(struct afs_operation *op, struct afs_volume *volume)
+{
+	unsigned int snap;
+	time64_t cur = volume->creation_time;
+	time64_t old = op->pre_volsync.creation;
+	time64_t new = op->volsync.creation;
+	int ret;
+
+	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);
+
+	if (cur == TIME64_MIN) {
+		volume->creation_time = new;
+		return 0;
+	}
+
+	if (new == cur)
+		return 0;
+
+	/* Try to advance the creation timestamp from what we had before the
+	 * operation to what we got back from the server.  This should
+	 * hopefully ensure that in a race between multiple operations only one
+	 * of them will do this.
+	 */
+	if (cur != old)
+		return 0;
+
+	/* If the creation time changes in an unexpected way, we need to scrub
+	 * our caches.  For a RW vol, this will only change if the volume is
+	 * restored from a backup; for a RO/Backup vol, this will advance when
+	 * the volume is updated to a new snapshot (eg. "vos release").
+	 */
+	if (volume->type == AFSVL_RWVOL)
+		goto regressed;
+	if (volume->type == AFSVL_BACKVOL) {
+		if (new < old)
+			goto regressed;
+		goto advance;
+	}
+
+	/* We have an RO volume, we need to query the VL server and look at the
+	 * server flags to see if RW->RO replication is in progress.
+	 */
+	ret = afs_is_server_excluded(op, volume);
+	if (ret < 0)
+		return ret;
+	if (ret > 0) {
+		snap = atomic_read(&volume->cb_ro_snapshot);
+		trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_volume_excluded);
+		return ret;
+	}
+
+advance:
+	snap = atomic_inc_return(&volume->cb_ro_snapshot);
+	trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_for_vos_release);
+	volume->creation_time = new;
+	return 0;
+
+regressed:
+	atomic_inc(&volume->cb_scrub);
+	trace_afs_cb_v_break(volume->vid, 0, afs_cb_break_for_creation_regress);
+	volume->creation_time = new;
+	return 0;
+}
+
+/*
+ * Handle a change to the volume update time in the VolSync record.
+ */
+static void afs_update_volume_update_time(struct afs_operation *op, struct afs_volume *volume)
+{
+	enum afs_cb_break_reason reason = afs_cb_break_no_break;
+	time64_t cur = volume->update_time;
+	time64_t old = op->pre_volsync.update;
+	time64_t new = op->volsync.update;
+
+	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);
+
+	if (cur == TIME64_MIN) {
+		volume->update_time = new;
+		return;
+	}
+
+	if (new == cur)
+		return;
+
+	/* If the volume update time changes in an unexpected way, we need to
+	 * scrub our caches.  For a RW vol, this will advance on every
+	 * modification op; for a RO/Backup vol, this will advance when the
+	 * volume is updated to a new snapshot (eg. "vos release").
+	 */
+	if (new < old)
+		reason = afs_cb_break_for_update_regress;
+
+	/* Try to advance the update timestamp from what we had before the
+	 * operation to what we got back from the server.  This should
+	 * hopefully ensure that in a race between multiple operations only one
+	 * of them will do this.
+	 */
+	if (cur == old) {
+		if (reason == afs_cb_break_for_update_regress) {
+			atomic_inc(&volume->cb_scrub);
+			trace_afs_cb_v_break(volume->vid, 0, reason);
+		}
+		volume->update_time = new;
+	}
+}
+
+static int afs_update_volume_times(struct afs_operation *op, struct afs_volume *volume)
+{
+	int ret = 0;
+
+	if (likely(op->volsync.creation == volume->creation_time &&
+		   op->volsync.update == volume->update_time))
+		return 0;
+
+	mutex_lock(&volume->volsync_lock);
+	if (op->volsync.creation != volume->creation_time) {
+		ret = afs_update_volume_creation_time(op, volume);
+		if (ret < 0)
+			goto out;
+	}
+	if (op->volsync.update != volume->update_time)
+		afs_update_volume_update_time(op, volume);
+out:
+	mutex_unlock(&volume->volsync_lock);
+	return ret;
+}
+
+/*
+ * Update the state of a volume.  Returns 1 to redo the operation from the start.
+ */
+int afs_update_volume_state(struct afs_operation *op)
+{
+	struct afs_volume *volume = op->volume;
+	int ret;
+
+	_enter("%llx", op->volume->vid);
+
+	if (op->volsync.creation != TIME64_MIN || op->volsync.update != TIME64_MIN) {
+		ret = afs_update_volume_times(op, volume);
+		if (ret != 0) {
+			_leave(" = %d", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/*
  * mark the data attached to an inode as obsolete due to a write on the server
  * - might also want to ditch all the outstanding writes and dirty pages
  */
@@ -74,7 +269,7 @@ bool afs_check_validity(struct afs_vnode *vnode)
 		cb_break = vnode->cb_break;
 
 		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
-			if (vnode->cb_v_break != vnode->volume->cb_v_break)
+			if (vnode->cb_v_break != atomic_read(&vnode->volume->cb_v_break))
 				need_clear = afs_cb_break_for_v_break;
 			else if (!afs_check_server_good(vnode))
 				need_clear = afs_cb_break_for_s_reinit;
@@ -95,7 +290,7 @@ bool afs_check_validity(struct afs_vnode *vnode)
 
 	write_seqlock(&vnode->cb_lock);
 	if (need_clear == afs_cb_break_no_promise)
-		vnode->cb_v_break = vnode->volume->cb_v_break;
+		vnode->cb_v_break = atomic_read(&vnode->volume->cb_v_break);
 	else if (cb_break == vnode->cb_break)
 		__afs_break_callback(vnode, need_clear);
 	else