aboutsummaryrefslogtreecommitdiffstats
path: root/lib/diameter/src/base/diameter_watchdog.erl
blob: b615bed860d750dda8e1e58119d4dfc4680f4277 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
%%
%% %CopyrightBegin%
%%
%% Copyright Ericsson AB 2010-2012. All Rights Reserved.
%%
%% The contents of this file are subject to the Erlang Public License,
%% Version 1.1, (the "License"); you may not use this file except in
%% compliance with the License. You should have received a copy of the
%% Erlang Public License along with this software. If not, it can be
%% retrieved online at http://www.erlang.org/.
%%
%% Software distributed under the License is distributed on an "AS IS"
%% basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
%% the License for the specific language governing rights and limitations
%% under the License.
%%
%% %CopyrightEnd%
%%

%%
%% This module implements (as a process) the state machine documented
%% in Appendix A of RFC 3539.
%%

-module(diameter_watchdog).
-behaviour(gen_server).

%% towards diameter_service
-export([start/2]).

%% gen_server callbacks
-export([init/1,
         handle_call/3,
         handle_cast/2,
         handle_info/2,
         terminate/2,
         code_change/3]).

%% diameter_watchdog_sup callback
-export([start_link/1]).

-include_lib("diameter/include/diameter.hrl").
-include("diameter_internal.hrl").

-define(DEFAULT_TW_INIT, 30000). %% RFC 3539 ch 3.4.1

-record(watchdog,
        {%% PCB - Peer Control Block; see RFC 3539, Appendix A
         status = initial :: initial | okay | suspect | down | reopen,
         pending = false  :: boolean(),
         tw :: 6000..16#FFFFFFFF | {module(), atom(), list()},
                                %% {M,F,A} -> integer() >= 0
         num_dwa = 0 :: -1 | non_neg_integer(),
                     %% number of DWAs received during reopen
         %% end PCB
         parent = self() :: pid(),
         transport       :: pid() | undefined,
         tref :: reference(), %% reference for current watchdog timer
         message_data}).   %% term passed into diameter_service with message

%% start/2
%%
%% Start a monitor before the watchdog is allowed to proceed to ensure
%% that a failed capabilities exchange produces the desired exit
%% reason.

-spec start(Type, {RecvData, Opts, SvcName, Svc})
   -> pid()
 when Type :: {connect|accept, reference()},
      RecvData :: term(),
      Opts :: list(),
      SvcName :: term(),
      Svc :: #diameter_service{}.

start({_,_} = Type, T) ->
    Ref = make_ref(),
    {ok, Pid} = diameter_watchdog_sup:start_child({Ref, {Type, self(), T}}),
    try
        {erlang:monitor(process, Pid), Pid}
    after
        Pid ! Ref
    end.

start_link(T) ->
    {ok, _} = proc_lib:start_link(?MODULE,
                                  init,
                                  [T],
                                  infinity,
                                  diameter_lib:spawn_opts(server, [])).

%% ===========================================================================
%% ===========================================================================

%% init/1

init(T) ->
    proc_lib:init_ack({ok, self()}),
    gen_server:enter_loop(?MODULE, [], i(T)).

i({Ref, {_, Pid, _} = T}) ->
    MRef = erlang:monitor(process, Pid),
    receive
        Ref ->
            make_state(T);
        {'DOWN', MRef, process, _, _} = D ->
            exit({shutdown, D})
    end;

i({_, Pid, _} = T) ->  %% from old code
    erlang:monitor(process, Pid),
    make_state(T).

make_state({T, Pid, {RecvData,
                     Opts,
                     SvcName,
                     #diameter_service{applications = Apps,
                                       capabilities = Caps}
                     = Svc}}) ->
    random:seed(now()),
    putr(restart, {T, Opts, Svc}),  %% save seeing it in trace
    putr(dwr, dwr(Caps)),           %%
    #watchdog{parent = Pid,
              transport = monitor(diameter_peer_fsm:start(T, Opts, Svc)),
              tw = proplists:get_value(watchdog_timer,
                                       Opts,
                                       ?DEFAULT_TW_INIT),
              message_data = {RecvData, SvcName, Apps}}.

%% handle_call/3

handle_call(_, _, State) ->
    {reply, nok, State}.

%% handle_cast/2

handle_cast(_, State) ->
    {noreply, State}.

%% handle_info/2

handle_info(T, State) ->
    case transition(T, State) of
        ok ->
            {noreply, State};
        #watchdog{} = S ->
            event(State, S),
            {noreply, S};
        stop ->
            ?LOG(stop, T),
            event(State, State#watchdog{status = down}),
            {stop, {shutdown, T}, State}
    end.

event(#watchdog{status = T}, #watchdog{status = T}) ->
    ok;

event(#watchdog{transport = undefined}, #watchdog{transport = undefined}) ->
    ok;

event(#watchdog{status = From, transport = F, parent = Pid},
      #watchdog{status = To, transport = T}) ->
    E = {tpid(F,T), From, To},
    notify(Pid, E),
    ?LOG(transition, {self(), E}).

tpid(_, Pid)
  when is_pid(Pid) ->
    Pid;
tpid(Pid, _) ->
    Pid.

notify(Pid, E) ->
    Pid ! {watchdog, self(), E}.

%% terminate/2

terminate(_, _) ->
    ok.

%% code_change/3

code_change(_, State, _) ->
    {ok, State}.

%% ===========================================================================
%% ===========================================================================

%% transition/2
%%
%% The state transitions documented here are extracted from RFC 3539,
%% the commentary is ours.

%% Service or watchdog is telling the watchdog of an accepting
%% transport to die after reconnect_timer expiry or reestablished
%% connection (in another transport process) respectively.
transition(close, #watchdog{status = down}) ->
    {{accept, _}, _, _} = getr(restart), %% assert
    stop;
transition(close, #watchdog{}) ->
    ok;

%% Service is asking for the peer to be taken down gracefully.
transition({shutdown, Pid}, #watchdog{parent = Pid,
                                      transport = undefined,
                                      status = S}) ->
    down = S,  %% sanity check
    stop;
transition({shutdown = T, Pid}, #watchdog{parent = Pid,
                                          transport = TPid}) ->
    TPid ! {T, self()},
    ok;

%% Parent process has died,
transition({'DOWN', _, process, Pid, _Reason},
           #watchdog{parent = Pid}) ->
    stop;

%% Transport has accepted a connection.
transition({accepted = T, TPid}, #watchdog{transport = TPid,
                                           parent = Pid}) ->
    Pid ! {T, self(), TPid},
    ok;

%% Transport is telling us that its impending death isn't failure.
transition({close, TPid, _Reason}, #watchdog{transport = TPid}) ->
    stop;

%%   STATE         Event                Actions              New State
%%   =====         ------               -------              ----------
%%   INITIAL       Connection up        SetWatchdog()        OKAY

%% By construction, the watchdog timer isn't set until we move into
%% state okay as the result of the Peer State Machine reaching the
%% Open state.
%%
%% If we're accepting then we may be resuming a connection that went
%% down in another watchdog process, in which case this is the
%% transition below, from down to reopen. That is, it's not until we
%% know the identity of the peer (ie. now) that we know that we're in
%% state down rather than initial.

transition({open, TPid, Hosts, T} = Open,
           #watchdog{transport = TPid,
                     status = initial,
                     parent = Pid}
           = S) ->
    case okay(getr(restart), Hosts) of
        okay ->
            open(Pid, {TPid, T}),
            set_watchdog(S#watchdog{status = okay});
        reopen ->
            transition(Open, S#watchdog{status = down})
    end;

%%   DOWN          Connection up        NumDWA = 0
%%                                      SendWatchdog()
%%                                      SetWatchdog()
%%                                      Pending = TRUE       REOPEN

transition({open = P, TPid, _Hosts, T},
           #watchdog{transport = TPid,
                     status = down}
           = S) ->
    %% Store the info we need to notify the parent to reopen the
    %% connection after the requisite DWA's are received, at which
    %% time we eraser(open).
    putr(P, {TPid, T}),
    set_watchdog(send_watchdog(S#watchdog{status = reopen,
                                          num_dwa = 0}));

%%   OKAY          Connection down      CloseConnection()
%%                                      Failover()
%%                                      SetWatchdog()        DOWN
%%   SUSPECT       Connection down      CloseConnection()
%%                                      SetWatchdog()        DOWN
%%   REOPEN        Connection down      CloseConnection()
%%                                      SetWatchdog()        DOWN

transition({'DOWN', _, process, TPid, _},
           #watchdog{transport = TPid,
                     status = initial}) ->
    stop;

transition({'DOWN', _, process, TPid, _},
           #watchdog{transport = TPid}
           = S) ->
    failover(S),
    close(S),
    set_watchdog(S#watchdog{status = down,
                            pending = false,
                            transport = undefined});
%% Any outstanding pending (or other messages from the transport) will
%% have arrived before 'DOWN' since the message comes from the same
%% process. Note that we could also get this message in the initial
%% state.

%% Incoming message.
transition({recv, TPid, Name, Pkt}, #watchdog{transport = TPid} = S) ->
    recv(Name, Pkt, S);

%% Current watchdog has timed out.
transition({timeout, TRef, tw}, #watchdog{tref = TRef} = S) ->
    set_watchdog(timeout(S));

%% Timer was canceled after message was already sent.
transition({timeout, _, tw}, #watchdog{}) ->
    ok;

%% State query.
transition({state, Pid}, #watchdog{status = S}) ->
    Pid ! {self(), S},
    ok.

%% ===========================================================================

monitor(Pid) ->
    erlang:monitor(process, Pid),
    Pid.

putr(Key, Val) ->
    put({?MODULE, Key}, Val).

getr(Key) ->
    get({?MODULE, Key}).

eraser(Key) ->
    erase({?MODULE, Key}).

%% encode/1

encode(Msg) ->
    #diameter_packet{bin = Bin} = diameter_codec:encode(?BASE, Msg),
    Bin.

%% okay/2

okay({{accept, Ref}, _, _}, Hosts) ->
    T = {?MODULE, connection, Ref, Hosts},
    diameter_reg:add(T),
    okay(diameter_reg:match(T));
%% Register before matching so that at least one of two registering
%% processes will match the other. (Which can't happen as long as
%% diameter_peer_fsm guarantees at most one open connection to the same
%% peer.)

okay({{connect, _}, _, _}, _) ->
    okay.

%% The peer hasn't been connected recently ...
okay([{_,P}]) ->
    P = self(),  %% assert
    okay;

%% ... or it has.
okay(C) ->
    [_|_] = [P ! close || {_,P} <- C, self() /= P],
    reopen.

%% set_watchdog/1

set_watchdog(#watchdog{tw = TwInit,
                       tref = TRef}
             = S) ->
    cancel(TRef),
    S#watchdog{tref = erlang:start_timer(tw(TwInit), self(), tw)}.

cancel(undefined) ->
    ok;
cancel(TRef) ->
    erlang:cancel_timer(TRef).

tw(T)
  when is_integer(T), T >= 6000 ->
    T - 2000 + (random:uniform(4001) - 1); %% RFC3539 jitter of +/- 2 sec.
tw({M,F,A}) ->
    apply(M,F,A).

%% open/2

open(Pid, {_,_} = T) ->
    Pid ! {connection_up, self(), T}.

%% failover/1

failover(#watchdog{status = okay,
                   parent = Pid}) ->
    Pid ! {connection_down, self()};

failover(_) ->
    ok.

%% close/1

close(#watchdog{status = down}) ->
    ok;

close(#watchdog{parent = Pid}) ->
    {{T, _}, _, _} = getr(restart),
    T == accept andalso (Pid ! {close, self()}).

%% send_watchdog/1

send_watchdog(#watchdog{pending = false,
                        transport = TPid}
              = S) ->
    TPid ! {send, encode(getr(dwr))},
    ?LOG(send, 'DWR'),
    S#watchdog{pending = true}.

%% recv/3

recv(Name, Pkt, S) ->
    try rcv(Name, S) of
        #watchdog{} = NS ->
            rcv(Name, Pkt, S),
            NS
    catch
        {?MODULE, throwaway, #watchdog{} = NS} ->
            NS
    end.

%% rcv/3

rcv(N, _, _)
  when N == 'CER';
       N == 'CEA';
       N == 'DWR';
       N == 'DWA';
       N == 'DPR';
       N == 'DPA' ->
    false;

rcv(_, Pkt, #watchdog{transport = TPid,
                      message_data = T}) ->
    diameter_service:receive_message(TPid, Pkt, T).

throwaway(S) ->
    throw({?MODULE, throwaway, S}).

%% rcv/2

%%   INITIAL       Receive DWA          Pending = FALSE
%%                                      Throwaway()          INITIAL
%%   INITIAL       Receive non-DWA      Throwaway()          INITIAL

rcv('DWA', #watchdog{status = initial} = S) ->
    throwaway(S#watchdog{pending = false});

rcv(_, #watchdog{status = initial} = S) ->
    throwaway(S);

%%   DOWN          Receive DWA          Pending = FALSE
%%                                      Throwaway()          DOWN
%%   DOWN          Receive non-DWA      Throwaway()          DOWN

rcv('DWA', #watchdog{status = down} = S) ->
    throwaway(S#watchdog{pending = false});

rcv(_, #watchdog{status = down} = S) ->
    throwaway(S);

%%   OKAY          Receive DWA          Pending = FALSE
%%                                      SetWatchdog()        OKAY
%%   OKAY          Receive non-DWA      SetWatchdog()        OKAY

rcv('DWA', #watchdog{status = okay} = S) ->
    set_watchdog(S#watchdog{pending = false});

rcv(_, #watchdog{status = okay} = S) ->
    set_watchdog(S);

%%   SUSPECT       Receive DWA          Pending = FALSE
%%                                      Failback()
%%                                      SetWatchdog()        OKAY
%%   SUSPECT       Receive non-DWA      Failback()
%%                                      SetWatchdog()        OKAY

rcv('DWA', #watchdog{status = suspect} = S) ->
    failback(S),
    set_watchdog(S#watchdog{status = okay,
                            pending = false});

rcv(_, #watchdog{status = suspect} = S) ->
    failback(S),
    set_watchdog(S#watchdog{status = okay});

%%   REOPEN        Receive DWA &        Pending = FALSE
%%                 NumDWA == 2          NumDWA++
%%                                      Failback()           OKAY

rcv('DWA', #watchdog{status = reopen,
                     num_dwa = 2 = N,
                     parent = Pid}
           = S) ->
    open(Pid, eraser(open)),
    S#watchdog{status = okay,
               num_dwa = N+1,
               pending = false};

%%   REOPEN        Receive DWA &        Pending = FALSE
%%                 NumDWA < 2           NumDWA++             REOPEN

rcv('DWA', #watchdog{status = reopen,
                     num_dwa = N}
           = S) ->
    S#watchdog{num_dwa = N+1,
               pending = false};

%%   REOPEN        Receive non-DWA      Throwaway()          REOPEN

rcv(_, #watchdog{status = reopen} = S) ->
    throwaway(S).

%% failback/1

failback(#watchdog{parent = Pid}) ->
    Pid ! {connection_up, self()}.

%% timeout/1
%%
%% The caller sets the watchdog on the return value.

%%   OKAY          Timer expires &      SendWatchdog()
%%                 !Pending             SetWatchdog()
%%                                      Pending = TRUE       OKAY
%%   REOPEN        Timer expires &      SendWatchdog()
%%                 !Pending             SetWatchdog()
%%                                      Pending = TRUE       REOPEN

timeout(#watchdog{status = T,
                  pending = false}
        = S)
  when T == okay;
       T == reopen ->
    send_watchdog(S);

%%   OKAY          Timer expires &      Failover()
%%                 Pending              SetWatchdog()        SUSPECT

timeout(#watchdog{status = okay,
                  pending = true}
  = S) ->
    failover(S),
    S#watchdog{status = suspect};

%%   SUSPECT       Timer expires        CloseConnection()
%%                                      SetWatchdog()        DOWN
%%   REOPEN        Timer expires &      CloseConnection()
%%                 Pending &            SetWatchdog()
%%                 NumDWA < 0                                DOWN

timeout(#watchdog{status = T,
                  pending = P,
                  num_dwa = N,
                  transport = TPid}
        = S)
  when T == suspect;
       T == reopen, P, N < 0 ->
    exit(TPid, shutdown),
    close(S),
    S#watchdog{status = down};

%%   REOPEN        Timer expires &      NumDWA = -1
%%                 Pending &            SetWatchdog()
%%                 NumDWA >= 0                               REOPEN

timeout(#watchdog{status = reopen,
                  pending = true,
                  num_dwa = N}
        = S)
  when 0 =< N ->
    S#watchdog{num_dwa = -1};

%%   DOWN          Timer expires        AttemptOpen()
%%                                      SetWatchdog()        DOWN
%%   INITIAL       Timer expires        AttemptOpen()
%%                                      SetWatchdog()        INITIAL

%% RFC 3539, 3.4.1:
%%
%%   [5] While the connection is in the closed state, the AAA client MUST
%%       NOT attempt to send further watchdog messages on the connection.
%%       However, after the connection is closed, the AAA client continues
%%       to periodically attempt to reopen the connection.
%%
%%       The AAA client SHOULD wait for the transport layer to report
%%       connection failure before attempting again, but MAY choose to
%%       bound this wait time by the watchdog interval, Tw.

%% Don't bound, restarting the peer process only when the previous
%% process has died. We only need to handle state down since we start
%% the first watchdog when transitioning out of initial.

timeout(#watchdog{status = down} = S) ->
    restart(S).

%% restart/1

restart(#watchdog{transport = undefined} = S) ->
    restart(getr(restart), S);
restart(S) ->
    S.

%% Only restart the transport in the connecting case. For an accepting
%% transport, we've registered the peer connection when leaving state
%% initial and this is used by a new accepting process to realize that
%% it's actually in state down rather then initial when receiving
%% notification of an open connection.

restart({{connect, _} = T, Opts, Svc}, #watchdog{parent = Pid} = S) ->
    Pid ! {reconnect, self()},
    S#watchdog{transport = monitor(diameter_peer_fsm:start(T, Opts, Svc))};
restart({{accept, _}, _, _}, S) ->
    S.
%% Don't currently use Opts/Svc in the accept case but having them in
%% the process dictionary is helpful if the process dies unexpectedly.

%% dwr/1

dwr(#diameter_caps{origin_host = OH,
                   origin_realm = OR,
                   origin_state_id = OSI}) ->
    ['DWR', {'Origin-Host', OH},
            {'Origin-Realm', OR},
            {'Origin-State-Id', OSI}].