From 9aeab4aced35f668149aa083a96928766f645f23 Mon Sep 17 00:00:00 2001
From: Jan Friesse <jfriesse@redhat.com>
Date: Thu, 30 Mar 2017 16:33:51 +0200
Subject: [PATCH] res_corosync: Change thread stack size

In Corosync 2.x libraries were changed to use LibQB IPC.
Sadly LibQB IPC doesn't support copy-free access to received buffer, so
Corosync libraries were rewritten to use stack as buffer. Mostly the
needed stack size is quite small, but for all *_dispatch functions, 1MiB
is needed.

Asterisk function ast_pthread_create_background set stack size for new
thread to much smaller AST_BACKGROUND_STACKSIZE (~500KiB).

This results in Asterisk crash when running with Corosync 2.x.

Patch solves this issue by creating it's own version of
ast_pthread_create_background which sets stack size to much higher value
(actually it's AST_BACKGROUND_STACKSIZE + 3MiB).

Another problem may appear when "corosync show members" netconsole
command is executed. It is also executed in thread and also has only
500KiB stack size. Sadly it calls corosync_cfg_get_node_addrs which
again needs at least 1MiB stack.

Solution is to use HAVE_COROSYNC_CFG_STATE_TRACK as a discriminator
between Corosync 1.x and 2.x. If 1.x is found, nothing changes. If 2.x
is found, NodeID is displayed instead of IP address.

ASTERISK-25370 #close
Reported by: mdu113

Change-Id: Id95b0d21ab6e708e7d74ad8786c587211676fa08
---
 res/res_corosync.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/res/res_corosync.c b/res/res_corosync.c
index 79cd810cef..0d91b1860a 100644
--- a/res/res_corosync.c
+++ b/res/res_corosync.c
@@ -77,6 +77,15 @@ struct corosync_node {
 	struct ast_sockaddr addr;
 };
 
+/*! \brief Corosync ipc dispatch/request and reply size */
+#define COROSYNC_IPC_BUFFER_SIZE				(8192 * 128)
+
+/*! \brief Version of pthread_create to ensure stack is large enough */
+#define corosync_pthread_create_background(a, b, c, d)				\
+	ast_pthread_create_stack(a, b, c, d,					\
+		(AST_BACKGROUND_STACKSIZE + (3 * COROSYNC_IPC_BUFFER_SIZE)),	\
+		__FILE__, __FUNCTION__, __LINE__, #c)
+
 static struct corosync_node *corosync_node_alloc(struct ast_event *event)
 {
 	struct corosync_node *node;
@@ -808,10 +817,21 @@ static char *corosync_show_members(struct ast_cli_entry *e, int cmd, struct ast_
 	for (i = 1, cs_err = cpg_iteration_next(cpg_iter, &cpg_desc);
 			cs_err == CS_OK;
 			cs_err = cpg_iteration_next(cpg_iter, &cpg_desc), i++) {
+#ifdef HAVE_COROSYNC_CFG_STATE_TRACK
 		corosync_cfg_node_address_t addrs[8];
 		int num_addrs = 0;
 		unsigned int j;
+#endif
 
+		ast_cli(a->fd, "=== Node %u\n", i);
+		ast_cli(a->fd, "=== --> Group: %s\n", cpg_desc.group.value);
+
+#ifdef HAVE_COROSYNC_CFG_STATE_TRACK
+		/*
+		 * Corosync 2.x cfg lib needs to allocate 1M on stack after calling
+		 * corosync_cfg_get_node_addrs. netconsole thread has allocated only 0.5M
+		 * resulting in crash.
+		 */
 		cs_err = corosync_cfg_get_node_addrs(cfg_handle, cpg_desc.nodeid,
 				ARRAY_LEN(addrs), &num_addrs, addrs);
 		if (cs_err != CS_OK) {
@@ -819,9 +839,6 @@ static char *corosync_show_members(struct ast_cli_entry *e, int cmd, struct ast_
 			continue;
 		}
 
-		ast_cli(a->fd, "=== Node %u\n", i);
-		ast_cli(a->fd, "=== --> Group: %s\n", cpg_desc.group.value);
-
 		for (j = 0; j < num_addrs; j++) {
 			struct sockaddr *sa = (struct sockaddr *) addrs[j].address;
 			size_t sa_len = (size_t) addrs[j].address_length;
@@ -831,7 +848,9 @@ static char *corosync_show_members(struct ast_cli_entry *e, int cmd, struct ast_
 
 			ast_cli(a->fd, "=== --> Address %u: %s\n", j + 1, buf);
 		}
-
+#else
+		ast_cli(a->fd, "=== --> Nodeid: %"PRIu32"\n", cpg_desc.nodeid);
+#endif
 	}
 
 	ast_cli(a->fd, "===\n"
@@ -1157,7 +1176,7 @@ static int load_module(void)
 		goto failed;
 	}
 
-	if (ast_pthread_create_background(&dispatch_thread.id, NULL,
+	if (corosync_pthread_create_background(&dispatch_thread.id, NULL,
 			dispatch_thread_handler, NULL)) {
 		ast_log(LOG_ERROR, "Error starting CPG dispatch thread.\n");
 		goto failed;