From bf6f27388d33c7fd8df97d42b2cb6996a525ec63 Mon Sep 17 00:00:00 2001
From: Kevin Harwell <kharwell@digium.com>
Date: Wed, 9 Oct 2019 15:17:59 -0500
Subject: [PATCH] pbx: deadlock when outgoing dialed channel hangs up too
quickly
Here's the basic scenario that occurred when executing an AMI fast originate
while at the same time something else locks the channels container, and also
wants a lock on the dialed channel:
1. pbx_outgoing_attempt obtains a lock on a dialed channel
2. concurrently another thread obtains a lock on the channels container, and
subsequently requests a lock on the dialed channel. It waits on #1. For
instance, "core show channel <dialed channel"
3. the outgoing call does not fail, but ends before the pbx_outgoing_attempt
function exits
4. pbx_outgoing_attempt function exits, the outgoing structure destructs, and
attempts to hang up the dialed channel
5. hang up tries to obtain the channels container lock, but can't due to #2.
6. Asterisk is deadlocked.
The solution was to allow the pbx_outgoing_exec function to "steal" ownership
of the dialed channel, and handle hanging it up. The channel now is either hung
up prior to it being potentially locked by the initiating thread, or if locked
the hang up takes place in a different thread, thus alleviating the deadlock.
ASTERISK-28561
patches:
iliketrains.diff submitted by Joshua Colp (license 5000)
Change-Id: I51b42b92dde8f2215b69bb509e28667ee3a3853a
---
main/pbx.c | 26 ++++++++++++++------------
1 file changed, 14 insertions(+), 12 deletions(-)
diff --git a/main/pbx.c b/main/pbx.c
index 8b869f162c..872d67413d 100644
--- a/main/pbx.c
+++ b/main/pbx.c
@@ -7604,6 +7604,7 @@ static void *pbx_outgoing_exec(void *data)
{
RAII_VAR(struct pbx_outgoing *, outgoing, data, ao2_cleanup);
enum ast_dial_result res;
+ struct ast_channel *chan;
res = ast_dial_run(outgoing->dial, NULL, 0);
@@ -7624,36 +7625,37 @@ static void *pbx_outgoing_exec(void *data)
return NULL;
}
+ /* We steal the channel so we get ownership of when it is hung up */
+ chan = ast_dial_answered_steal(outgoing->dial);
+
if (!ast_strlen_zero(outgoing->app)) {
struct ast_app *app = pbx_findapp(outgoing->app);
if (app) {
ast_verb(4, "Launching %s(%s) on %s\n", outgoing->app, S_OR(outgoing->appdata, ""),
- ast_channel_name(ast_dial_answered(outgoing->dial)));
- pbx_exec(ast_dial_answered(outgoing->dial), app, outgoing->appdata);
+ ast_channel_name(chan));
+ pbx_exec(chan, app, outgoing->appdata);
} else {
ast_log(LOG_WARNING, "No such application '%s'\n", outgoing->app);
}
- } else {
- struct ast_channel *answered = ast_dial_answered(outgoing->dial);
+ ast_hangup(chan);
+ } else {
if (!ast_strlen_zero(outgoing->context)) {
- ast_channel_context_set(answered, outgoing->context);
+ ast_channel_context_set(chan, outgoing->context);
}
if (!ast_strlen_zero(outgoing->exten)) {
- ast_channel_exten_set(answered, outgoing->exten);
+ ast_channel_exten_set(chan, outgoing->exten);
}
if (outgoing->priority > 0) {
- ast_channel_priority_set(answered, outgoing->priority);
+ ast_channel_priority_set(chan, outgoing->priority);
}
- if (ast_pbx_run(answered)) {
- ast_log(LOG_ERROR, "Failed to start PBX on %s\n", ast_channel_name(answered));
- } else {
- /* PBX will have taken care of hanging up, so we steal the answered channel so dial doesn't do it */
- ast_dial_answered_steal(outgoing->dial);
+ if (ast_pbx_run(chan)) {
+ ast_log(LOG_ERROR, "Failed to start PBX on %s\n", ast_channel_name(chan));
+ ast_hangup(chan);
}
}
--
GitLab