Jorijn van der Graaf
799fd1a802
The keepalive refresh and the resume's re-REGISTER carried an initial registration's first-REGISTER Authorization — an empty nonce and response — in the second REGISTER's frame, with a Security-Client naming the SPIs and ports in use. TS 24.229 5.1.1.4.2 has a reregistration carry the Authorization of the last successful authentication — the last received nonce and the last calculated response — and a Security-Client with the new parameter values for the two SA pairs a re-authentication would set up; TS 33.203 7.4.0 keeps the server ports and changes the client ports. O2 UK refused the refresh of the old shape with 503 on every occasion on record (alyx, 2026-09-24 to 10-08, a stationary phone included) and accepted the fresh registrations that followed; KPN accepted the old shape without a challenge. The fresh registration now records the 401's nonce, our cnonce and the response in the registration state (auth_nonce, auth_cnonce, auth_response in the state file); a reregistration sends them verbatim, mints new SPIs and proposes PortUcNext (45063) as the client port with the server port unchanged. A registration resumed from a state file written before this change has no answer: its reregistrations carry the empty digest, as before, until its next fresh registration, and the resume says so. A 401 to a reregistration asks for re-authentication over temporary SAs on the proposed ports (TS 24.229 5.1.1.5.1), which imsd does not implement: the refresh throws it as a refusal and RegRecovery makes the next step the fresh registration, replacing the in-place answer over the old SAs. Tested with the Messages and Engine suites and on the dev phone (KPN) with a build of this commit's tree: a resume from the previous state file, a fresh registration, a resume that sent the stored answer, three refreshes at a 120-s interval, an outgoing call to a bench line and an incoming call's ring.
836 lines
44 KiB
C++
836 lines
44 KiB
C++
// SPDX-License-Identifier: GPL-3.0-only
|
||
// SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®
|
||
|
||
// lint-disable-file fixed-width-types
|
||
/*
|
||
Imsd:Engine — the daemon's decisions as pure reducers: the call state
|
||
machine (CallMachine) and the registration recovery policy (RegRecovery,
|
||
its own section below).
|
||
|
||
A CallMachine owns one call's SIP dialog, outgoing or incoming. It never
|
||
touches a socket, a clock, or a subprocess: each event (the INVITE's
|
||
responses, an in-dialog request from the network, an accept/hang-up command,
|
||
the media leg exiting, a setup timeout) is a method that mutates the dialog
|
||
state and returns a list of Actions for the daemon shell to carry out — send
|
||
this on the client flow, answer the request on the channel it came in on,
|
||
start/stop the media leg, emit this D-Bus state change, arm this deadline.
|
||
That keeps the whole call FSM — PRACK on reliable 18x, ACK of 2xx vs non-2xx
|
||
finals, CANCEL/answer races, remote BYE, media-plane far-end-hangup, the
|
||
emergency attempt chain (urn:service:sos first for a classified number, one
|
||
fallback to a plain INVITE of the digits; a 380 Alternative Service upgrade
|
||
the other way), and the terminating (UAS) side: 100/180 on an inbound INVITE,
|
||
200-with-answer on Accept, 486 reject, the remote-CANCEL 200+487 pair —
|
||
unit-testable against recorded network dialogs with no I/O (tests/Engine).
|
||
|
||
State/reason strings are the frozen D-Bus vocabulary the dialer maps on
|
||
(dialing/ringing/incoming/active/terminated; outgoing/incoming/accepted/
|
||
local-hangup/remote-hangup/refused-or-busy/error). Pure std C++.
|
||
*/
|
||
|
||
export module Imsd:Engine;
|
||
import std;
|
||
import :Util;
|
||
import :Sip;
|
||
import :Sdp;
|
||
import :Messages;
|
||
|
||
export namespace imsd::engine {
|
||
|
||
enum class CallState { Dialing, Ringing, Incoming, Active, Terminated };
|
||
enum class Direction { Outgoing, Incoming };
|
||
|
||
inline std::string_view StateStr(CallState s) {
|
||
switch (s) {
|
||
case CallState::Dialing: return "dialing";
|
||
case CallState::Ringing: return "ringing";
|
||
case CallState::Incoming: return "incoming";
|
||
case CallState::Active: return "active";
|
||
case CallState::Terminated: return "terminated";
|
||
}
|
||
return "terminated";
|
||
}
|
||
|
||
inline std::string_view DirectionStr(Direction d) {
|
||
return d == Direction::Incoming ? "incoming" : "outgoing";
|
||
}
|
||
|
||
// ---- registration recovery policy ---------------------------------
|
||
//
|
||
// What the daemon does when the registration stops working after
|
||
// bring-up, as a pure reducer: the shell supplies the clock and the
|
||
// network, this decides the next step and how long to wait for it. Two
|
||
// kinds of failure reach it. A REFUSAL: the network answered a refresh
|
||
// with a final other than 200 — a 401, re-authentication, included — or
|
||
// a fresh registration's protected REGISTER with a final other than 200
|
||
// (the unprotected one's 401 is its challenge). SILENCE: the
|
||
// flow died and reconnecting through the SA, or the refresh over it,
|
||
// got no answer. Neither is retried for long on the same registration.
|
||
// TS 24.229 5.1.1.4.1 has the UE perform an initial registration after
|
||
// a 408, 500, 504 or 403 on a re-REGISTER (5.1.1.2.1: not before a
|
||
// Retry-After has passed), and RFC 5626 has it register again when its
|
||
// flow cannot be recovered. imsd does so after any refusal: the 503s
|
||
// below are not in that list. Before this reducer the daemon looped
|
||
// reconnect + re-REGISTER on the same Call-ID and SA forever — O2 UK,
|
||
// 2026-09-24: 21 × 503 over 70 min, then 33 unanswered reconnect
|
||
// cycles over 2 h 39 min, each ended only by a manual restart whose
|
||
// fresh registration the network accepted within two seconds (ims
|
||
// ledger F16).
|
||
//
|
||
// Pacing. Reconnect cycles back off 5 s → 5 min. A refusal without a
|
||
// Retry-After of at least a second (none, 0, unparsable) escalates to
|
||
// a fresh registration after two (one 503 may be a momentary hiccup a
|
||
// retried refresh clears); one with such a Retry-After escalates at
|
||
// once — it is the network's considered answer (O2 2026-10-08: the
|
||
// refresh after the first wait was refused again, 414 s then 772 s) —
|
||
// and so does a 401, the network asking to re-authenticate, which imsd
|
||
// answers with a fresh registration (TS 24.229 5.1.1.5.1's temporary
|
||
// SAs on the proposed client port are not implemented). Silence
|
||
// escalates after two reconnect cycles
|
||
// that end without an answer — a TCP connect series whose last attempt
|
||
// was not a local refusal, a bind() the kernel refused, or a refresh
|
||
// that fails short of a refusal: unanswered, a failed send (the resume
|
||
// at start gives up after two unanswered
|
||
// connects).
|
||
// A fresh registration is the expensive step: an AKA run, a
|
||
// new SA pair, and on KPN a refusal (spi-s=0) while the registration on
|
||
// the address is live, which costs that registration. So a refused or
|
||
// throttled fresh attempt
|
||
// waits on the throttle schedule (21 min, growing ×1.5 to 60) and a
|
||
// silent one backs off 30 s → 10 min. Retry-After (RFC 3261 20.33)
|
||
// always wins over a shorter wait. A 403 is a refusal like the others:
|
||
// never hammered (the schedule), never abandoned (a SIM that is
|
||
// unbarred registers within the hour); once a fresh registration is
|
||
// due it also says the old registration is gone (KPN drops it the
|
||
// moment an initial REGISTER arrives, throttled or not), as does a
|
||
// fresh attempt that got past the SA setup, a binding the network
|
||
// terminated, and a resume that failed at bring-up (OldGone) — no
|
||
// reconnect over the old SA from then on. Every wait
|
||
// is either the self-imposed backoff, which a user's Dial cuts short,
|
||
// or the network's own word (a Retry-After, the schedule after a
|
||
// refused or throttled fresh attempt, a terminated binding's probation
|
||
// or its refusal schedule), which nothing cuts short — a
|
||
// restart of the process neither: the shell keeps the holds (Holds)
|
||
// and hands them to the next one (Restore). The shell supplies the
|
||
// clock and the network; this holds the deadlines and names the next
|
||
// step (Next). Success resets everything.
|
||
struct RegRecovery {
|
||
enum class Failure { Refused, Silent, Throttled };
|
||
enum class Step { Reconnect, Fresh };
|
||
// What comes next: the step, and the earliest time it may run (the
|
||
// shell's clock; at <= now means now).
|
||
struct Plan { Step step; double at; };
|
||
|
||
static constexpr int RefusalsBeforeFresh = 2;
|
||
static constexpr int SilentCyclesBeforeFresh = 2;
|
||
static constexpr double ReconnectDelayMin = 5;
|
||
static constexpr double ReconnectDelayMax = 300;
|
||
static constexpr double FreshDelayMin = 30;
|
||
static constexpr double FreshDelayMax = 600;
|
||
static constexpr int ThrottleMinutesMin = 21;
|
||
static constexpr int ThrottleMinutesMax = 60;
|
||
// The network's word is honoured up to the schedule's own longest
|
||
// wait: a Retry-After beyond an hour is cut to it, and the refusal
|
||
// heard again then — one REGISTER an hour at most, never a day
|
||
// unregistered on one answer.
|
||
static constexpr long RetryAfterMax = ThrottleMinutesMax * 60;
|
||
// A connect refused locally — our own 4-tuple still in TIME_WAIT
|
||
// (up to 60 s after we closed it), no route yet — is not the
|
||
// network's answer: retried soon, never counted, the backoff
|
||
// untouched. Dev phone 2026-09-24: four such refusals in 26 s read
|
||
// as two silent cycles cost a fresh registration into the throttle.
|
||
static constexpr double LocalRetry = 5;
|
||
|
||
int refusals = 0;
|
||
int silentCycles = 0;
|
||
int freshAttempts = 0;
|
||
double reconnectDelay = ReconnectDelayMin;
|
||
double freshDelay = FreshDelayMin;
|
||
int throttleMinutes = ThrottleMinutesMin;
|
||
bool fresh = false; // the next registration attempt is a fresh one
|
||
bool oldGone = false; // the old registration is gone: nothing to reconnect over
|
||
bool terminated = false; // the network terminated our binding, and the policy has counted it
|
||
// the deadlines, on the shell's clock
|
||
double backoffUntil = 0; // self-imposed: no step before this; a Dial clears it
|
||
double holdUntil = 0; // the network's word for any attempt (a Retry-After on a refresh): nothing clears it
|
||
double freshHoldUntil = 0; // no fresh attempt before this (the schedule after a refused or throttled fresh attempt, a fresh Retry-After, probation, rejected/unregistered)
|
||
|
||
bool Fresh() const { return fresh; }
|
||
bool Reconnectable() const { return !oldGone; }
|
||
|
||
// The network's holds as seconds still to run, and where the
|
||
// schedule stands: what a restart of the process must not forget.
|
||
struct Held {
|
||
double hold = 0;
|
||
double freshHold = 0;
|
||
int throttleMinutes = ThrottleMinutesMin;
|
||
bool oldGone = false; // the old registration is gone: the next process has nothing to reconnect over
|
||
// a schedule that has advanced is kept too, until a success resets it, and so is the gone verdict
|
||
bool Any() const { return hold > 0 || freshHold > 0 || throttleMinutes > ThrottleMinutesMin || oldGone; }
|
||
};
|
||
Held Holds(double now) const { return {std::max(0.0, holdUntil - now), std::max(0.0, freshHoldUntil - now), throttleMinutes, oldGone}; }
|
||
// A restarted process takes them over; nothing here shortens a
|
||
// hold it already has, or lengthens one past RetryAfterMax.
|
||
void Restore(double now, const Held& h) {
|
||
if (h.hold > 0) holdUntil = std::max(holdUntil, now + std::min(h.hold, static_cast<double>(RetryAfterMax)));
|
||
if (h.freshHold > 0) freshHoldUntil = std::max(freshHoldUntil, now + std::min(h.freshHold, static_cast<double>(RetryAfterMax)));
|
||
throttleMinutes = std::clamp(std::max(throttleMinutes, h.throttleMinutes), ThrottleMinutesMin, ThrottleMinutesMax);
|
||
if (h.oldGone) OldGone(); // no reconnect over SAs the network has written off
|
||
}
|
||
|
||
// The next step and when. Not escalated: a reconnect after the
|
||
// backoff and any hold. Escalated: the fresh attempt once the
|
||
// backoff, any hold and the fresh hold have passed — and while a
|
||
// fresh hold still runs, a reconnect over the old SA meanwhile, the
|
||
// cheap thing, unless that registration is gone.
|
||
Plan Next(double now) const {
|
||
double any = std::max(backoffUntil, holdUntil);
|
||
double freshAt = std::max(any, freshHoldUntil);
|
||
if (!fresh) return {Step::Reconnect, any};
|
||
if (!oldGone && freshHoldUntil > any && now < freshHoldUntil) return {Step::Reconnect, any};
|
||
return {Step::Fresh, freshAt};
|
||
}
|
||
|
||
void OnLocalRefusal(double now) { backoffUntil = now + LocalRetry; }
|
||
|
||
// A refused keepalive refresh, or a failed reconnect + refresh
|
||
// cycle; `status` is the refusal's. The backoff paces the next step;
|
||
// a Retry-After of at least a second holds every attempt for its own
|
||
// length (up to RetryAfterMax), whichever is longer, and makes the
|
||
// next step the fresh registration, as does a 401. A 403 once a fresh
|
||
// registration is due says the old registration is gone (KPN drops
|
||
// it the moment an initial REGISTER arrives, throttled or not).
|
||
void OnReconnectFailure(double now, Failure f, long retryAfter = 0, int status = 0) {
|
||
if (retryAfter > 0) holdUntil = std::max(holdUntil, now + static_cast<double>(std::min(retryAfter, RetryAfterMax)));
|
||
// A cycle over a registration already known gone — the network
|
||
// terminated the binding while the cycle waited for its final —
|
||
// fails by definition: not a silent cycle, not a refusal, and no
|
||
// backoff before the fresh registration that verdict scheduled.
|
||
if (oldGone) return;
|
||
if (f == Failure::Refused) refusals++;
|
||
else silentCycles++;
|
||
if (refusals >= RefusalsBeforeFresh || silentCycles >= SilentCyclesBeforeFresh) fresh = true;
|
||
if (f == Failure::Refused && (retryAfter > 0 || status == 401)) fresh = true;
|
||
if (status == 403 && fresh) oldGone = true;
|
||
backoffUntil = now + reconnectDelay;
|
||
reconnectDelay = std::min(reconnectDelay * 2, ReconnectDelayMax);
|
||
}
|
||
|
||
// A failed fresh registration; `saReplaced`: it got past the SA
|
||
// setup, so the old registration's SAs went with it. Refusals and
|
||
// throttles hold the next fresh attempt on the schedule (a Retry-After
|
||
// replaces it, never below the short backoff's floor nor above
|
||
// RetryAfterMax); silence backs
|
||
// it off 30 s → 10 min. A reconnect over the old SA meanwhile waits
|
||
// at least the reconnect backoff.
|
||
void OnFreshFailure(double now, Failure f, long retryAfter = 0, bool saReplaced = false) {
|
||
freshAttempts++;
|
||
fresh = true;
|
||
if (saReplaced) oldGone = true;
|
||
backoffUntil = std::max(backoffUntil, now + reconnectDelay);
|
||
if (f == Failure::Silent) {
|
||
backoffUntil = std::max(backoffUntil, now + freshDelay);
|
||
freshDelay = std::min(freshDelay * 2, FreshDelayMax);
|
||
return;
|
||
}
|
||
double wait = throttleMinutes * 60.0;
|
||
throttleMinutes = std::min(throttleMinutes * 3 / 2, ThrottleMinutesMax);
|
||
if (retryAfter > 0) wait = std::max(static_cast<double>(std::min(retryAfter, RetryAfterMax)), FreshDelayMin);
|
||
freshHoldUntil = now + wait;
|
||
}
|
||
|
||
// The network terminated our binding (a reg-event NOTIFY, RFC
|
||
// 3680): the old registration is gone. deactivated and expired
|
||
// mean a fresh registration now; probation after the network's
|
||
// retry-after (up to RetryAfterMax); rejected and unregistered on the
|
||
// refusal schedule —
|
||
// the network's word is neither hammered nor taken as final. One
|
||
// termination counts once, however often it is reported (every
|
||
// reg-event dialog of the account carries it, a NOTIFY may be
|
||
// retransmitted), and never shortens a hold already running.
|
||
void OnBindingTerminated(double now, std::string_view event, long retryAfter = 0) {
|
||
bool reported = terminated;
|
||
terminated = true;
|
||
oldGone = true;
|
||
fresh = true;
|
||
if (event == "probation") {
|
||
freshHoldUntil = std::max(freshHoldUntil, now + static_cast<double>(std::clamp(retryAfter, 1L, RetryAfterMax)));
|
||
} else if (reported) {
|
||
return;
|
||
} else if (event == "rejected" || event == "unregistered") {
|
||
freshHoldUntil = std::max(freshHoldUntil, now + throttleMinutes * 60.0);
|
||
throttleMinutes = std::min(throttleMinutes * 3 / 2, ThrottleMinutesMax);
|
||
} else {
|
||
backoffUntil = 0;
|
||
}
|
||
}
|
||
|
||
// The stored registration is not there to reconnect over (a resume
|
||
// that failed at bring-up found its SAs unusable, or there are none).
|
||
void OldGone() { oldGone = true; fresh = true; }
|
||
|
||
// A user's Dial cuts the backoff short, never the network's word.
|
||
void OnDial() { backoffUntil = 0; }
|
||
|
||
void OnSuccess() { *this = RegRecovery{}; }
|
||
};
|
||
|
||
// Parsed SDP answer needed to bring up the media leg. `codec` is one of
|
||
// imsd-media's: "AMR-WB", "AMR", "PCMA", "PCMU" (empty = none we play).
|
||
struct MediaLeg {
|
||
std::string remoteIp;
|
||
int remotePort = 0;
|
||
int payloadType = -1;
|
||
bool octetAlign = false;
|
||
std::string codec = "AMR-WB";
|
||
bool Valid() const { return !remoteIp.empty() && remotePort > 0 && payloadType >= 0; }
|
||
};
|
||
|
||
struct Action {
|
||
enum class Type {
|
||
SendClient, // send `text` on the client TCP flow
|
||
SendResponse, // answer the just-handled inbound request on its origin channel
|
||
StartMedia, // bring up the media leg described by `media`
|
||
StopMedia, // tear the media leg down
|
||
State, // emit CallStateChanged(uni, `state`, `reason`)
|
||
Deleted, // emit CallDeleted(uni); drop this machine
|
||
SetDeadline, // arm a setup timer for `seconds`; fire calls OnDeadline()
|
||
Log,
|
||
};
|
||
Type type;
|
||
std::string text;
|
||
std::string state;
|
||
std::string reason;
|
||
MediaLeg media;
|
||
double seconds = 0;
|
||
};
|
||
|
||
// ring/answer budget, and how long to wait for a 487 after CANCEL — the
|
||
// imsd.py INVITE_TIMEOUT / CANCEL_487_TIMEOUT constants.
|
||
inline constexpr double InviteTimeout = 90.0;
|
||
inline constexpr double Cancel487Timeout = 10.0;
|
||
// How long an unanswered incoming call may ring before we 480 it — a
|
||
// safety net behind the network's own CANCEL, so generous.
|
||
inline constexpr double IncomingRingTimeout = 120.0;
|
||
|
||
// Constructor tag: this machine is the UAS of the given inbound INVITE.
|
||
struct IncomingInvite {
|
||
std::string_view invite;
|
||
};
|
||
|
||
class CallMachine {
|
||
public:
|
||
// `emergency`: the shell classified the dialled string as an
|
||
// emergency number — the first attempt targets urn:service:sos.
|
||
// `codecs`: the daemon's CODECS override — the codecs offered on an
|
||
// outgoing call and accepted from an inbound offer, in preference
|
||
// order; empty = the sdp module's defaults.
|
||
CallMachine(const imsd::msg::Context& ctx, imsd::util::Rng& rng, std::string uni, std::string number, int rtpPort, bool precond, bool emergency = false,
|
||
std::vector<std::string> codecs = {})
|
||
: ctx_(ctx), rng_(rng), uni_(std::move(uni)), number_(std::move(number)),
|
||
rtpPort_(rtpPort), precond_(precond), codecs_(std::move(codecs)), attemptSos_(emergency) {
|
||
ResetDialog();
|
||
}
|
||
|
||
CallMachine(const imsd::msg::Context& ctx, imsd::util::Rng& rng, std::string uni, IncomingInvite in, int rtpPort,
|
||
std::vector<std::string> codecs = {})
|
||
: ctx_(ctx), rng_(rng), uni_(std::move(uni)), rtpPort_(rtpPort),
|
||
precond_(false), codecs_(std::move(codecs)), direction_(Direction::Incoming),
|
||
state_(CallState::Incoming), reason_("incoming"),
|
||
invite_(in.invite) {
|
||
number_ = imsd::sip::CallerId(invite_);
|
||
d_.callid = std::string(imsd::sip::Header(invite_, "Call-ID").value_or(""));
|
||
d_.itag = rng_.Token(10); // the To tag we mint = our dialog tag
|
||
d_.invBranch = rng_.Token(20); // unused as UAS; kept initialized
|
||
if (auto from = imsd::sip::Header(invite_, "From")) d_.dialogTo = std::string(*from);
|
||
if (auto to = imsd::sip::Header(invite_, "To")) d_.localUri = AngleUri(*to).value_or("");
|
||
if (auto ct = imsd::sip::Header(invite_, "Contact")) d_.remoteTarget = AngleUri(*ct);
|
||
d_.ruri = d_.remoteTarget.value_or("");
|
||
// The UAS route set is the Record-Route in RECEIVED order
|
||
// (RFC 3261 12.1.1); DialogRoute() reverses for the UAC case, so
|
||
// store it reversed here to cancel that out.
|
||
auto rr = imsd::sip::Headers(invite_, "Record-Route");
|
||
for (std::size_t i = rr.size(); i-- > 0;)
|
||
d_.recordRoute.emplace_back(rr[i]);
|
||
answerSdp_ = std::string(Body(invite_)); // the caller's offer
|
||
nextCseq_ = 0; // our first in-dialog request gets CSeq 1
|
||
}
|
||
|
||
const std::string& Uni() const { return uni_; }
|
||
const std::string& Number() const { return number_; }
|
||
const std::string& CallId() const { return d_.callid; }
|
||
CallState State() const { return state_; }
|
||
std::string_view StateStr() const { return engine::StateStr(state_); }
|
||
Direction Dir() const { return direction_; }
|
||
std::string_view DirectionStr() const { return engine::DirectionStr(direction_); }
|
||
const std::string& Reason() const { return reason_; }
|
||
bool Terminated() const { return state_ == CallState::Terminated; }
|
||
|
||
// Build + queue the INVITE for the current attempt and arm the ring
|
||
// timeout.
|
||
std::vector<Action> Start() {
|
||
if (attemptSos_) sosTried_ = true;
|
||
else
|
||
plainTried_ = true;
|
||
imsd::sdp::Offer offer;
|
||
offer.local = ctx_.local;
|
||
offer.rtpPort = rtpPort_;
|
||
offer.sessionId = rng_.UInt(1000000, 9999999);
|
||
offer.precond = precond_;
|
||
offer.codecs = codecs_;
|
||
std::string sdp = imsd::sdp::BuildOffer(offer);
|
||
std::vector<Action> a;
|
||
a.push_back(Send(imsd::msg::BuildInvite(ctx_, d_, sdp, precond_)));
|
||
a.push_back(Deadline(InviteTimeout));
|
||
return a;
|
||
}
|
||
|
||
// UAS: answer the inbound INVITE with 100 Trying + 180 Ringing (made
|
||
// reliable only when the caller Requires 100rel) and arm the ring
|
||
// timeout. An offer we cannot serve — no audio line, or none of the
|
||
// codecs imsd-media plays (AMR-WB, AMR, PCMA, PCMU; the CODECS
|
||
// override narrows that set) — is refused with 488 up front, before
|
||
// the UI ever rings; the log line names
|
||
// what WAS offered, so a field journal answers "which codec did the
|
||
// gateway want" without a raw SIP dump.
|
||
std::vector<Action> OnInvite() {
|
||
std::vector<Action> a;
|
||
if (direction_ != Direction::Incoming || state_ != CallState::Incoming) return a;
|
||
MediaLeg leg = ParseAnswer();
|
||
if (!leg.Valid() || leg.codec.empty()) {
|
||
a.push_back(Respond(imsd::msg::BuildInviteResponse(ctx_, invite_, 488, "Not Acceptable Here", d_.itag)));
|
||
std::string why = !leg.Valid() ? "no usable audio line"
|
||
: std::format("no playable codec, offered: {}", imsd::sdp::OfferedCodecs(answerSdp_));
|
||
Append(a, Finish("error", std::format("incoming offer unusable ({}); 488 sent", why)));
|
||
return a;
|
||
}
|
||
a.push_back(Respond(imsd::msg::BuildInviteResponse(ctx_, invite_, 100, "Trying", d_.itag)));
|
||
std::string require(imsd::sip::Header(invite_, "Require").value_or(""));
|
||
if (require.contains("precondition")) a.push_back(LogAct("caller requires preconditions; answering without them"));
|
||
std::vector<std::string> extra;
|
||
if (require.contains("100rel")) {
|
||
extra.push_back("Require: 100rel");
|
||
extra.push_back("RSeq: 1");
|
||
}
|
||
last180_ = imsd::msg::BuildInviteResponse(ctx_, invite_, 180, "Ringing", d_.itag, std::nullopt, extra);
|
||
a.push_back(Respond(last180_));
|
||
a.push_back(Deadline(IncomingRingTimeout));
|
||
return a;
|
||
}
|
||
|
||
// UAS: the user answered. 200 OK with the SDP answer (the offer's own
|
||
// payload types, RFC 3264), media up, active. The caller's ACK needs
|
||
// no action when it arrives (OnRequest ignores ACK).
|
||
std::vector<Action> OnAccept() {
|
||
std::vector<Action> a;
|
||
if (direction_ != Direction::Incoming || state_ != CallState::Incoming) return a;
|
||
MediaLeg leg = ParseAnswer();
|
||
imsd::sdp::AnswerSpec spec;
|
||
spec.local = ctx_.local;
|
||
spec.rtpPort = rtpPort_;
|
||
spec.sessionId = rng_.UInt(1000000, 9999999);
|
||
spec.payloadType = leg.payloadType;
|
||
spec.octetAlign = leg.octetAlign;
|
||
spec.codec = leg.codec;
|
||
spec.dtmfPt = imsd::sdp::TelephoneEventPt(Body(invite_), imsd::sdp::CodecRate(leg.codec));
|
||
localSdp_ = imsd::sdp::BuildAnswer(spec);
|
||
// session timers: echo the caller's Session-Expires; with no
|
||
// refresher stated, make the caller (uac) the refresher — its
|
||
// re-INVITE/UPDATE refreshes get 200d by OnRequest.
|
||
std::vector<std::string> extra;
|
||
if (auto se = imsd::sip::Header(invite_, "Session-Expires")) {
|
||
std::string v(*se);
|
||
if (!v.contains("refresher=")) v += ";refresher=uac";
|
||
extra.push_back(std::format("Session-Expires: {}", v));
|
||
extra.push_back("Require: timer");
|
||
}
|
||
a.push_back(Respond(imsd::msg::BuildInviteResponse(ctx_, invite_, 200, "OK", d_.itag, localSdp_, extra)));
|
||
a.push_back(StartMediaAct(leg));
|
||
state_ = CallState::Active;
|
||
a.push_back(StateAct("accepted"));
|
||
return a;
|
||
}
|
||
|
||
// A response to our INVITE (the shell already matched Call-ID + CSeq).
|
||
std::vector<Action> OnInviteResponse(std::string_view msg) {
|
||
std::vector<Action> a;
|
||
if (direction_ == Direction::Incoming)
|
||
return a; // a UAS has no INVITE transaction of its own
|
||
AbsorbDialog(msg);
|
||
auto st = imsd::sip::Status(msg);
|
||
if (!st) return a;
|
||
int code = *st;
|
||
if (code > 100 && code < 200) {
|
||
if (state_ == CallState::Dialing) {
|
||
state_ = CallState::Ringing;
|
||
a.push_back(StateAct("outgoing"));
|
||
}
|
||
auto rseq = imsd::sip::Header(msg, "RSeq");
|
||
std::string require = std::string(imsd::sip::Header(msg, "Require").value_or(""));
|
||
if (rseq && require.contains("100rel") && !pracked_.contains(std::string(*rseq))) {
|
||
pracked_.insert(std::string(*rseq));
|
||
std::array<std::string, 1> extra = {
|
||
std::format("RAck: {} 1 INVITE", *rseq)};
|
||
a.push_back(Send(imsd::msg::BuildInDialog(ctx_, d_, "PRACK", nextCseq_, rng_.Token(20), extra)));
|
||
nextCseq_++;
|
||
}
|
||
return a;
|
||
}
|
||
if (code < 200)
|
||
return a; // 1xx other than 100<code<200 (only 100): nothing
|
||
if (code == 200) {
|
||
a.push_back(Send(imsd::msg::BuildAck2xx(ctx_, d_, rng_.Token(20), std::string(imsd::sip::Header(msg, "To").value_or("")))));
|
||
// A 2xx retransmission (RFC 3261 13.3.1.4: the UAS repeats
|
||
// it until our ACK arrives) is ACKed again and nothing else —
|
||
// media is already running, or the call is already over.
|
||
if (state_ != CallState::Ringing && state_ != CallState::Dialing) return a;
|
||
if (cancelled_ && userCancelled_) {
|
||
// answered in the user's CANCEL race — we no longer want it
|
||
nextCseq_++;
|
||
a.push_back(Send(imsd::msg::BuildInDialog(ctx_, d_, "BYE", nextCseq_, rng_.Token(20))));
|
||
Append(a, Finish("local-hangup", "answered during our CANCEL; BYE sent"));
|
||
return a;
|
||
}
|
||
// An answer racing a DEADLINE-initiated CANCEL is still
|
||
// wanted — the user never hung up. Matters most when the sos
|
||
// attempt is answered at the wire just as the timeout fires:
|
||
// BYEing an answering PSAP is the worst possible outcome.
|
||
MediaLeg leg = ParseAnswer();
|
||
a.push_back(StartMediaAct(leg));
|
||
state_ = CallState::Active;
|
||
a.push_back(StateAct("accepted"));
|
||
return a;
|
||
}
|
||
// non-2xx final
|
||
a.push_back(Send(imsd::msg::BuildAckNon2xx(ctx_, d_, std::string(imsd::sip::Header(msg, "To").value_or("")))));
|
||
std::string fin = WithReason(std::format("INVITE final {}", code), msg);
|
||
if (auto sos = FallbackTo(code, msg)) {
|
||
Append(a, Retry(*sos, fin));
|
||
return a;
|
||
}
|
||
if (cancelled_ || code == 487) Append(a, Finish("local-hangup", fin));
|
||
else if (code == 486 || code == 480 || code == 603) Append(a, Finish("refused-or-busy", fin));
|
||
else
|
||
Append(a, Finish("error", fin));
|
||
return a;
|
||
}
|
||
|
||
// An in-dialog request from the network (the shell matched Call-ID).
|
||
std::vector<Action> OnRequest(std::string_view msg) {
|
||
std::vector<Action> a;
|
||
std::string_view method = Method(msg);
|
||
if (method == "ACK")
|
||
return a; // ACK is never responded to (RFC 3261 17.1.1.2)
|
||
std::string_view body = Body(msg);
|
||
if (body.contains("m=audio")) answerSdp_ = std::string(body);
|
||
if (direction_ == Direction::Incoming && state_ == CallState::Incoming) {
|
||
if (method == "CANCEL") {
|
||
// the caller gave up: 200 the CANCEL transaction, 487 the
|
||
// INVITE transaction (RFC 3261 9.2), done.
|
||
a.push_back(Respond(imsd::msg::BuildResponse200(ctx_, msg)));
|
||
a.push_back(Respond(imsd::msg::BuildInviteResponse(ctx_, invite_, 487, "Request Terminated", d_.itag)));
|
||
Append(a, Finish("remote-hangup", WithReason("CANCEL before answer", msg)));
|
||
} else if (method == "INVITE") {
|
||
// retransmitted INVITE (our provisional got lost): repeat it
|
||
a.push_back(Respond(last180_));
|
||
} else {
|
||
// PRACK of our reliable 180, or anything else: 200 echo
|
||
a.push_back(Respond(imsd::msg::BuildResponse200(ctx_, msg)));
|
||
}
|
||
return a;
|
||
}
|
||
if (method == "UPDATE" || method == "INVITE") {
|
||
std::optional<std::string> ans;
|
||
if (direction_ == Direction::Incoming) {
|
||
// session-refresh: re-state the answer we gave if the
|
||
// refresh carries an offer; a bodyless refresh gets a
|
||
// bodyless 200 (RFC 3311/4028)
|
||
if (body.contains("m=audio")) ans = localSdp_;
|
||
} else {
|
||
imsd::sdp::Offer offer;
|
||
offer.local = ctx_.local;
|
||
offer.rtpPort = rtpPort_;
|
||
offer.sessionId = rng_.UInt(1000000, 9999999);
|
||
offer.precond = precond_;
|
||
offer.currRemote = "sendrecv";
|
||
offer.codecs = codecs_;
|
||
ans = imsd::sdp::BuildOffer(offer);
|
||
}
|
||
// RFC 4028 §9: a 2xx to a refresh MUST echo Session-Expires,
|
||
// or the refresher treats the session as unrefreshed. KPN's
|
||
// B2BUA audits ~55 s into every call with such an UPDATE and
|
||
// releases ("PT: Session timer expired") on a bare 200.
|
||
std::vector<std::string> extra;
|
||
if (auto se = imsd::sip::Header(msg, "Session-Expires")) {
|
||
std::string v(*se);
|
||
if (!v.contains("refresher=")) v += ";refresher=uac";
|
||
extra.push_back(std::format("Session-Expires: {}", v));
|
||
extra.push_back("Require: timer");
|
||
}
|
||
a.push_back(Respond(imsd::msg::BuildResponse200(ctx_, msg, ans ? std::optional<std::string_view>(*ans) : std::nullopt, extra)));
|
||
} else if (method == "BYE") {
|
||
a.push_back(Respond(imsd::msg::BuildResponse200(ctx_, msg)));
|
||
Append(a, Finish("remote-hangup", WithReason("remote BYE", msg)));
|
||
} else if (method == "CANCEL") {
|
||
a.push_back(Respond(imsd::msg::BuildResponse200(ctx_, msg)));
|
||
Append(a, Finish("remote-hangup", WithReason("remote CANCEL", msg)));
|
||
} else {
|
||
a.push_back(Respond(imsd::msg::BuildResponse200(ctx_, msg)));
|
||
}
|
||
return a;
|
||
}
|
||
|
||
std::vector<Action> OnHangup() {
|
||
std::vector<Action> a;
|
||
if (direction_ == Direction::Incoming && state_ == CallState::Incoming) {
|
||
// reject the unanswered call
|
||
a.push_back(Respond(imsd::msg::BuildInviteResponse(ctx_, invite_, 486, "Busy Here", d_.itag)));
|
||
Append(a, Finish("local-hangup", "rejected (486 sent)"));
|
||
return a;
|
||
}
|
||
if (state_ == CallState::Active) {
|
||
nextCseq_++;
|
||
a.push_back(Send(imsd::msg::BuildInDialog(ctx_, d_, "BYE", nextCseq_, rng_.Token(20))));
|
||
Append(a, Finish("local-hangup", "HangUp; BYE sent"));
|
||
} else if (state_ == CallState::Dialing || state_ == CallState::Ringing) {
|
||
// even when a deadline already CANCELled: the user's intent
|
||
// also kills the emergency fallback chain
|
||
userCancelled_ = true;
|
||
if (!cancelled_) {
|
||
a.push_back(Send(imsd::msg::BuildCancel(ctx_, d_)));
|
||
cancelled_ = true;
|
||
a.push_back(Deadline(Cancel487Timeout));
|
||
}
|
||
}
|
||
return a;
|
||
}
|
||
|
||
// The shell is abandoning this machine (an emergency dial preempts
|
||
// it while it waits on a CANCEL's 487): terminate bookkeeping only —
|
||
// the CANCEL already sent stands, and the late final for this
|
||
// Call-ID is ignored by dispatch.
|
||
std::vector<Action> Abandon(std::string_view detail) {
|
||
return Finish("local-hangup", detail);
|
||
}
|
||
|
||
// The media subprocess exited. code 3 = the downlink RTP dried up
|
||
// (far-end hangup); anything else = the leg died. Either way, if the
|
||
// call was up we release it network-side and tear down.
|
||
std::vector<Action> OnMediaExit(int code) {
|
||
std::vector<Action> a;
|
||
if (state_ != CallState::Active) return a;
|
||
nextCseq_++;
|
||
a.push_back(Send(imsd::msg::BuildInDialog(ctx_, d_, "BYE", nextCseq_, rng_.Token(20))));
|
||
Append(a, Finish("remote-hangup", code == 3 ? "far-end hangup (downlink RTP stopped); BYE sent" : std::format("media leg died (code {}); BYE sent", code)));
|
||
return a;
|
||
}
|
||
|
||
// A setup deadline fired (never armed once Active).
|
||
std::vector<Action> OnDeadline() {
|
||
std::vector<Action> a;
|
||
if (state_ == CallState::Active) return a;
|
||
if (direction_ == Direction::Incoming) {
|
||
if (state_ == CallState::Incoming) {
|
||
// rang unanswered past the safety net; the missed call
|
||
// reads as remote-hangup, like a network CANCEL would
|
||
a.push_back(Respond(imsd::msg::BuildInviteResponse(ctx_, invite_, 480, "Temporarily Unavailable", d_.itag)));
|
||
Append(a, Finish("remote-hangup", "rang unanswered past the deadline (480 sent)"));
|
||
}
|
||
return a;
|
||
}
|
||
if (!cancelled_ && (state_ == CallState::Dialing || state_ == CallState::Ringing)) {
|
||
a.push_back(Send(imsd::msg::BuildCancel(ctx_, d_)));
|
||
cancelled_ = true;
|
||
a.push_back(Deadline(Cancel487Timeout));
|
||
} else if (auto sos = FallbackTo(0, {})) {
|
||
// the 487 never came; an abandoned sos attempt still gets
|
||
// its digits fallback rather than dying silently
|
||
Append(a, Retry(*sos, "no final after CANCEL"));
|
||
} else {
|
||
Append(a, Finish("error", "setup deadline expired"));
|
||
}
|
||
return a;
|
||
}
|
||
|
||
// The shell couldn't send (socket error) — collapse the call.
|
||
std::vector<Action> Fail(std::string_view reason) {
|
||
std::vector<Action> a;
|
||
Append(a, Finish(reason, "client-flow send failed"));
|
||
return a;
|
||
}
|
||
|
||
private:
|
||
const imsd::msg::Context& ctx_;
|
||
imsd::util::Rng& rng_;
|
||
std::string uni_, number_;
|
||
int rtpPort_;
|
||
bool precond_;
|
||
std::vector<std::string> codecs_; // CODECS override; empty = defaults
|
||
Direction direction_ = Direction::Outgoing;
|
||
CallState state_ = CallState::Dialing;
|
||
std::string reason_ = "outgoing";
|
||
std::string invite_; // incoming only: the inbound INVITE verbatim
|
||
std::string last180_; // incoming only: our provisional, for retransmits
|
||
std::string localSdp_; // incoming only: the SDP answer we sent
|
||
imsd::msg::Dialog d_;
|
||
int nextCseq_ = 2;
|
||
bool cancelled_ = false;
|
||
// The emergency attempt chain (outgoing only). attemptSos_ is what
|
||
// the CURRENT attempt targets; the tried flags bound the chain to
|
||
// one step in each direction, never a loop.
|
||
bool attemptSos_ = false;
|
||
bool sosTried_ = false;
|
||
bool plainTried_ = false;
|
||
bool userCancelled_ = false; // CANCEL came from OnHangup, not a deadline
|
||
std::set<std::string> pracked_;
|
||
std::string answerSdp_;
|
||
|
||
// Fresh dialog identity for the current attempt. A fallback INVITE
|
||
// after a final response is a new transaction AND a clean new dialog
|
||
// attempt (fresh Call-ID) — the shell's dispatch then ignores late
|
||
// responses to the abandoned attempt by Call-ID mismatch.
|
||
void ResetDialog() {
|
||
d_ = {};
|
||
d_.ruri = attemptSos_ ? std::string(imsd::msg::SosUrn)
|
||
: imsd::msg::RuriFor(number_, ctx_.id.domain);
|
||
d_.callid = std::format("{}@{}", rng_.Token(20), ctx_.local);
|
||
d_.itag = rng_.Token(10);
|
||
d_.invBranch = rng_.Token(20);
|
||
nextCseq_ = 2;
|
||
pracked_.clear();
|
||
answerSdp_.clear();
|
||
cancelled_ = false;
|
||
userCancelled_ = false;
|
||
}
|
||
|
||
// The emergency fallback chain — where the next attempt (if any)
|
||
// points. `msg` may be empty (deadline paths).
|
||
// - a sos INVITE that fails for any reason other than the user
|
||
// hanging up is re-attempted as a plain INVITE of the dialled
|
||
// digits: the pre-emergency-support behavior, so classification
|
||
// can only improve on the status quo, never block a call the old
|
||
// code would have placed.
|
||
// - a plain INVITE answered 380 Alternative Service whose body
|
||
// names emergency (TS 24.229 5.1.6: the network classified a
|
||
// number we didn't) is re-attempted as urn:service:sos. A 380
|
||
// without that indication terminates as an error: promoting an
|
||
// arbitrary redirect would put a non-emergency call through to a
|
||
// PSAP.
|
||
std::optional<bool> FallbackTo(int code, std::string_view msg) const {
|
||
if (userCancelled_) return std::nullopt;
|
||
if (attemptSos_) return plainTried_ ? std::nullopt : std::optional(false);
|
||
if (code == 380 && !sosTried_ && Body(msg).contains("emergency")) return true;
|
||
return std::nullopt;
|
||
}
|
||
|
||
// Switch the attempt and send its INVITE. Same uni: the dialer keeps
|
||
// seeing one continuous call, back in "dialing".
|
||
std::vector<Action> Retry(bool sos, std::string_view why) {
|
||
attemptSos_ = sos;
|
||
ResetDialog();
|
||
state_ = CallState::Dialing;
|
||
std::vector<Action> a;
|
||
a.push_back(LogAct(std::format("call {}: {} — retrying as {}", uni_, why, sos ? "emergency (urn:service:sos)" : "plain INVITE of the digits")));
|
||
a.push_back(StateAct("outgoing"));
|
||
Append(a, Start());
|
||
return a;
|
||
}
|
||
|
||
static std::string_view Body(std::string_view msg) {
|
||
std::size_t at = msg.find("\r\n\r\n");
|
||
return at == std::string_view::npos ? std::string_view{}
|
||
: msg.substr(at + 4);
|
||
}
|
||
static std::string_view Method(std::string_view msg) {
|
||
std::size_t sp = msg.find(' ');
|
||
return sp == std::string_view::npos ? msg : msg.substr(0, sp);
|
||
}
|
||
static std::optional<std::string> AngleUri(std::string_view v) {
|
||
std::size_t lt = v.find('<');
|
||
if (lt == std::string_view::npos) return std::string(v);
|
||
std::size_t gt = v.find('>', lt);
|
||
if (gt == std::string_view::npos) return std::string(v);
|
||
return std::string(v.substr(lt + 1, gt - lt - 1));
|
||
}
|
||
|
||
// Fold a response's dialog-establishing headers into the dialog.
|
||
void AbsorbDialog(std::string_view msg) {
|
||
if (auto to = imsd::sip::Header(msg, "To"))
|
||
if (to->contains("tag=")) d_.dialogTo = std::string(*to);
|
||
auto rr = imsd::sip::Headers(msg, "Record-Route");
|
||
if (!rr.empty()) {
|
||
d_.recordRoute.clear();
|
||
for (auto v : rr)
|
||
d_.recordRoute.emplace_back(v);
|
||
}
|
||
if (auto ct = imsd::sip::Header(msg, "Contact")) d_.remoteTarget = AngleUri(*ct);
|
||
std::string_view body = Body(msg);
|
||
if (body.contains("m=audio")) answerSdp_ = std::string(body);
|
||
}
|
||
|
||
MediaLeg ParseAnswer() const {
|
||
imsd::sdp::Answer ans = imsd::sdp::ParseAnswer(answerSdp_, codecs_);
|
||
MediaLeg leg;
|
||
leg.remoteIp = ans.ip;
|
||
leg.remotePort = ans.port < 0 ? 0 : ans.port;
|
||
leg.payloadType = ans.payloadType;
|
||
leg.octetAlign = ans.octetAlign;
|
||
leg.codec = ans.codec;
|
||
return leg;
|
||
}
|
||
|
||
// Terminate: state change, media teardown, deletion — in that order,
|
||
// so the UI leaves the call page before the (slow) media teardown.
|
||
// One journald line per teardown — who ended the call and why
|
||
// (the s59 60-second-drop hunt ran blind for lack of exactly
|
||
// this; the network's Reason header named the cause all along).
|
||
// `detail` carries the SIP-level cause when the caller knows it.
|
||
std::vector<Action> Finish(std::string_view reason, std::string_view detail = "") {
|
||
state_ = CallState::Terminated;
|
||
reason_ = std::string(reason);
|
||
std::vector<Action> a;
|
||
a.push_back(LogAct(detail.empty() ? std::format("call {} ended: {}", uni_, reason) : std::format("call {} ended: {} — {}", uni_, reason, detail)));
|
||
a.push_back(StateAct(reason));
|
||
a.push_back(Action{Action::Type::StopMedia});
|
||
a.push_back(Action{Action::Type::Deleted});
|
||
return a;
|
||
}
|
||
|
||
// "remote BYE, Reason: SIP;cause=503;text=..." — the peer's own
|
||
// stated cause, when it sent one.
|
||
static std::string WithReason(std::string_view what, std::string_view msg) {
|
||
auto r = imsd::sip::Header(msg, "Reason");
|
||
return r ? std::format("{}, Reason: {}", what, *r) : std::string(what);
|
||
}
|
||
|
||
Action Send(std::string text) {
|
||
return Action{Action::Type::SendClient, std::move(text)};
|
||
}
|
||
Action Respond(std::string text) {
|
||
return Action{Action::Type::SendResponse, std::move(text)};
|
||
}
|
||
Action StateAct(std::string_view reason) {
|
||
reason_ = std::string(reason);
|
||
Action a{Action::Type::State};
|
||
a.state = std::string(engine::StateStr(state_));
|
||
a.reason = reason_;
|
||
return a;
|
||
}
|
||
Action StartMediaAct(const MediaLeg& leg) {
|
||
Action a{Action::Type::StartMedia};
|
||
a.media = leg;
|
||
return a;
|
||
}
|
||
Action Deadline(double s) {
|
||
Action a{Action::Type::SetDeadline};
|
||
a.seconds = s;
|
||
return a;
|
||
}
|
||
Action LogAct(std::string text) {
|
||
return Action{Action::Type::Log, std::move(text)};
|
||
}
|
||
static void Append(std::vector<Action>& into, std::vector<Action> more) {
|
||
for (auto& m : more)
|
||
into.push_back(std::move(m));
|
||
}
|
||
};
|
||
}
|