17 files changed, 1050 insertions, 350 deletions

diff --git a/fs/afs/Makefile b/fs/afs/Makefile
index cc942b790cff..0738e2bf5193 100644
--- a/fs/afs/Makefile
+++ b/fs/afs/Makefile
@@ -17,6 +17,7 @@ kafs-y := \
         file.o \
         flock.o \
         fsclient.o \
+        fs_probe.o \
         inode.o \
         main.o \
         misc.o \
@@ -29,8 +30,9 @@ kafs-y := \
         super.o \
         netdevices.o \
         vlclient.o \
-        vl_rotate.o \
         vl_list.o \
+        vl_probe.o \
+        vl_rotate.o \
         volume.o \
         write.o \
         xattr.o \
diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index 1536d1d21c33..967db336d11a 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -303,6 +303,8 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
                         sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
 
         srx = &alist->addrs[i];
+        srx->srx_family = AF_RXRPC;
+        srx->transport_type = SOCK_DGRAM;
         srx->transport_len = sizeof(srx->transport.sin);
         srx->transport.sin.sin_family = AF_INET;
         srx->transport.sin.sin_port = htons(port);
@@ -341,6 +343,8 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
                         sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
 
         srx = &alist->addrs[i];
+        srx->srx_family = AF_RXRPC;
+        srx->transport_type = SOCK_DGRAM;
         srx->transport_len = sizeof(srx->transport.sin6);
         srx->transport.sin6.sin6_family = AF_INET6;
         srx->transport.sin6.sin6_port = htons(port);
@@ -353,23 +357,32 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
  */
 bool afs_iterate_addresses(struct afs_addr_cursor *ac)
 {
-        _enter("%hu+%hd", ac->start, (short)ac->index);
+        unsigned long set, failed;
+        int index;
 
         if (!ac->alist)
                 return false;
 
+        set = ac->alist->responded;
+        failed = ac->alist->failed;
+        _enter("%lx-%lx-%lx,%d", set, failed, ac->tried, ac->index);
+
         ac->nr_iterations++;
 
-        if (ac->begun) {
-                ac->index++;
-                if (ac->index == ac->alist->nr_addrs)
-                        ac->index = 0;
+        set &= ~(failed | ac->tried);
 
-                if (ac->index == ac->start)
-                        return false;
-        }
+        if (!set)
+                return false;
+
+        index = READ_ONCE(ac->alist->preferred);
+        if (test_bit(index, &set))
+                goto selected;
+
+        index = __ffs(set);
 
-        ac->begun = true;
+selected:
+        ac->index = index;
+        set_bit(index, &ac->tried);
         ac->responded = false;
         return true;
 }
@@ -383,12 +396,13 @@ int afs_end_cursor(struct afs_addr_cursor *ac)
 
         alist = ac->alist;
         if (alist) {
-                if (ac->responded && ac->index != ac->start)
-                        WRITE_ONCE(alist->index, ac->index);
+                if (ac->responded &&
+                    ac->index != alist->preferred &&
+                    test_bit(ac->alist->preferred, &ac->tried))
+                        WRITE_ONCE(alist->preferred, ac->index);
                 afs_put_addrlist(alist);
+                ac->alist = NULL;
         }
 
-        ac->alist = NULL;
-        ac->begun = false;
         return ac->error;
 }
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 8cf8d10daa6c..8ee5972893ed 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -122,6 +122,8 @@ bool afs_cm_incoming_call(struct afs_call *call)
 {
         _enter("{%u, CB.OP %u}", call->service_id, call->operation_ID);
 
+        call->epoch = rxrpc_kernel_get_epoch(call->net->socket, call->rxcall);
+
         switch (call->operation_ID) {
         case CBCallBack:
                 call->type = &afs_SRXCBCallBack;
@@ -152,6 +154,91 @@ bool afs_cm_incoming_call(struct afs_call *call)
 }
 
 /*
+ * Record a probe to the cache manager from a server.
+ */
+static int afs_record_cm_probe(struct afs_call *call, struct afs_server *server)
+{
+        _enter("");
+
+        if (test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags) &&
+            !test_bit(AFS_SERVER_FL_PROBING, &server->flags)) {
+                if (server->cm_epoch == call->epoch)
+                        return 0;
+
+                if (!server->probe.said_rebooted) {
+                        pr_notice("kAFS: FS rebooted %pU\n", &server->uuid);
+                        server->probe.said_rebooted = true;
+                }
+        }
+
+        spin_lock(&server->probe_lock);
+
+        if (!test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) {
+                server->cm_epoch = call->epoch;
+                server->probe.cm_epoch = call->epoch;
+                goto out;
+        }
+
+        if (server->probe.cm_probed &&
+            call->epoch != server->probe.cm_epoch &&
+            !server->probe.said_inconsistent) {
+                pr_notice("kAFS: FS endpoints inconsistent %pU\n",
+                          &server->uuid);
+                server->probe.said_inconsistent = true;
+        }
+
+        if (!server->probe.cm_probed || call->epoch == server->cm_epoch)
+                server->probe.cm_epoch = server->cm_epoch;
+
+out:
+        server->probe.cm_probed = true;
+        spin_unlock(&server->probe_lock);
+        return 0;
+}
+
+/*
+ * Find the server record by peer address and record a probe to the cache
+ * manager from a server.
+ */
+static int afs_find_cm_server_by_peer(struct afs_call *call)
+{
+        struct sockaddr_rxrpc srx;
+        struct afs_server *server;
+
+        rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
+
+        server = afs_find_server(call->net, &srx);
+        if (!server) {
+                trace_afs_cm_no_server(call, &srx);
+                return 0;
+        }
+
+        call->cm_server = server;
+        return afs_record_cm_probe(call, server);
+}
+