afs: Don't use probe running state to make decisions outside probe code

Don't use the running state for fileserver probes to make decisions about
which server to use as the state is cleared at the start of a probe and
also intermediate values might be misleading.

Instead, add a separate 'latest known' rtt in the afs_server struct and a
flag to indicate if the server is known to be responding and update these
as and when we know what to change them to.

Signed-off-by: David Howells <dhowells@redhat.com>

Author: dhowells

fs/afs/fs_probe.c

@@ -42,10 +42,13 @@ static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server
 	bool responded = server->probe.responded;
 
 	write_seqlock(&net->fs_lock);
-	if (responded)
+	if (responded) {
 		list_add_tail(&server->probe_link, &net->fs_probe_slow);
-	else
+	} else {
+		server->rtt = UINT_MAX;
+		clear_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
 		list_add_tail(&server->probe_link, &net->fs_probe_fast);
+	}
 	write_sequnlock(&net->fs_lock);
 
 	afs_schedule_fs_probe(net, server, !responded);
@@ -161,12 +164,14 @@ void afs_fileserver_probe_result(struct afs_call *call)
 	rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall);
 	if (rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
+		server->rtt = rtt_us;
 		alist->preferred = index;
 	}
 
 	smp_wmb(); /* Set rtt before responded. */
 	server->probe.responded = true;
 	set_bit(index, &alist->responded);
+	set_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
 out:
 	spin_unlock(&server->probe_lock);
 
@@ -224,7 +229,7 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
 {
 	struct wait_queue_entry *waits;
 	struct afs_server *server;
-	unsigned int rtt = UINT_MAX;
+	unsigned int rtt = UINT_MAX, rtt_s;
 	bool have_responders = false;
 	int pref = -1, i;
 
@@ -280,10 +285,11 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
 	for (i = 0; i < slist->nr_servers; i++) {
 		if (test_bit(i, &untried)) {
 			server = slist->servers[i].server;
-			if (server->probe.responded &&
-			    server->probe.rtt < rtt) {
+			rtt_s = READ_ONCE(server->rtt);
+			if (test_bit(AFS_SERVER_FL_RESPONDING, &server->flags) &&
+			    rtt_s < rtt) {
 				pref = i;
-				rtt = server->probe.rtt;
+				rtt = rtt_s;
 			}
 
 			remove_wait_queue(&server->probe_wq, &waits[i]);

fs/afs/internal.h

@@ -496,6 +496,7 @@ struct afs_server {
 	struct afs_server	*gc_next;	/* Next server in manager's list */
 	time64_t		unuse_time;	/* Time at which last unused */
 	unsigned long		flags;
+#define AFS_SERVER_FL_RESPONDING 0		/* The server is responding */
 #define AFS_SERVER_FL_NOT_READY	1		/* The record is not ready for use */
 #define AFS_SERVER_FL_NOT_FOUND	2		/* VL server says no such server */
 #define AFS_SERVER_FL_VL_FAIL	3		/* Failed to access VL server */
@@ -508,6 +509,7 @@ struct afs_server {
 	atomic_t		ref;		/* Object refcount */
 	atomic_t		active;		/* Active user count */
 	u32			addr_version;	/* Address list version */
+	unsigned int		rtt;		/* Server's current RTT in uS */
 	unsigned int		debug_id;	/* Debugging ID for traces */
 
 	/* file service access */
@@ -522,7 +524,7 @@ struct afs_server {
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT as ktime/64 */
+		unsigned int	rtt;		/* RTT in uS */
 		u32		abort_code;
 		short		error;
 		bool		responded:1;

fs/afs/rotate.c

@@ -341,7 +341,8 @@ bool afs_select_fileserver(struct afs_operation *op)
 	for (i = 0; i < op->server_list->nr_servers; i++) {
 		struct afs_server *s = op->server_list->servers[i].server;
 
-		if (!test_bit(i, &op->untried) || !s->probe.responded)
+		if (!test_bit(i, &op->untried) ||
+		    !test_bit(AFS_SERVER_FL_RESPONDING, &s->flags))
 			continue;
 		if (s->probe.rtt < rtt) {
 			op->index = i;

fs/afs/server.c

@@ -239,6 +239,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
 	INIT_LIST_HEAD(&server->probe_link);
 	spin_lock_init(&server->probe_lock);
 	server->cell = cell;
+	server->rtt = UINT_MAX;
 
 	afs_inc_servers_outstanding(net);
 	trace_afs_server(server, 1, 1, afs_server_trace_alloc);