diff --git a/daemons/controld/controld_messages.c b/daemons/controld/controld_messages.c
index 875d1e9617..3e472136f8 100644
--- a/daemons/controld/controld_messages.c
+++ b/daemons/controld/controld_messages.c
@@ -1,1358 +1,1358 @@
/*
* Copyright 2004-2024 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU General Public License version 2
* or later (GPLv2+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <sys/param.h>
#include <string.h>
#include <time.h>
#include <crm/crm.h>
#include <crm/common/xml.h>
#include <crm/cluster/internal.h>
#include <crm/cib.h>
#include <crm/common/ipc_internal.h>
#include <pacemaker-controld.h>
static enum crmd_fsa_input handle_message(xmlNode *msg,
enum crmd_fsa_cause cause);
static void handle_response(xmlNode *stored_msg);
static enum crmd_fsa_input handle_request(xmlNode *stored_msg,
enum crmd_fsa_cause cause);
static enum crmd_fsa_input handle_shutdown_request(xmlNode *stored_msg);
static void send_msg_via_ipc(xmlNode * msg, const char *sys);
/* debug only, can wrap all it likes */
static int last_data_id = 0;
void
register_fsa_error_adv(enum crmd_fsa_cause cause, enum crmd_fsa_input input,
fsa_data_t * cur_data, void *new_data, const char *raised_from)
{
/* save the current actions if any */
if (controld_globals.fsa_actions != A_NOTHING) {
register_fsa_input_adv(cur_data ? cur_data->fsa_cause : C_FSA_INTERNAL,
I_NULL, cur_data ? cur_data->data : NULL,
controld_globals.fsa_actions, TRUE, __func__);
}
/* reset the action list */
crm_info("Resetting the current action list");
fsa_dump_actions(controld_globals.fsa_actions, "Drop");
controld_globals.fsa_actions = A_NOTHING;
/* register the error */
register_fsa_input_adv(cause, input, new_data, A_NOTHING, TRUE, raised_from);
}
void
register_fsa_input_adv(enum crmd_fsa_cause cause, enum crmd_fsa_input input,
void *data, uint64_t with_actions,
gboolean prepend, const char *raised_from)
{
unsigned old_len = g_list_length(controld_globals.fsa_message_queue);
fsa_data_t *fsa_data = NULL;
if (raised_from == NULL) {
raised_from = "<unknown>";
}
if (input == I_NULL && with_actions == A_NOTHING /* && data == NULL */ ) {
/* no point doing anything */
crm_err("Cannot add entry to queue: no input and no action");
return;
}
if (input == I_WAIT_FOR_EVENT) {
controld_set_global_flags(controld_fsa_is_stalled);
crm_debug("Stalling the FSA pending further input: source=%s cause=%s data=%p queue=%d",
raised_from, fsa_cause2string(cause), data, old_len);
if (old_len > 0) {
fsa_dump_queue(LOG_TRACE);
prepend = FALSE;
}
if (data == NULL) {
controld_set_fsa_action_flags(with_actions);
fsa_dump_actions(with_actions, "Restored");
return;
}
/* Store everything in the new event and reset
* controld_globals.fsa_actions
*/
with_actions |= controld_globals.fsa_actions;
controld_globals.fsa_actions = A_NOTHING;
}
last_data_id++;
crm_trace("%s %s FSA input %d (%s) due to %s, %s data",
raised_from, (prepend? "prepended" : "appended"), last_data_id,
fsa_input2string(input), fsa_cause2string(cause),
(data? "with" : "without"));
fsa_data = pcmk__assert_alloc(1, sizeof(fsa_data_t));
fsa_data->id = last_data_id;
fsa_data->fsa_input = input;
fsa_data->fsa_cause = cause;
fsa_data->origin = raised_from;
fsa_data->data = NULL;
fsa_data->data_type = fsa_dt_none;
fsa_data->actions = with_actions;
if (with_actions != A_NOTHING) {
crm_trace("Adding actions %.16llx to input",
(unsigned long long) with_actions);
}
if (data != NULL) {
switch (cause) {
case C_FSA_INTERNAL:
case C_CRMD_STATUS_CALLBACK:
case C_IPC_MESSAGE:
case C_HA_MESSAGE:
CRM_CHECK(((ha_msg_input_t *) data)->msg != NULL,
crm_err("Bogus data from %s", raised_from));
crm_trace("Copying %s data from %s as cluster message data",
fsa_cause2string(cause), raised_from);
fsa_data->data = copy_ha_msg_input(data);
fsa_data->data_type = fsa_dt_ha_msg;
break;
case C_LRM_OP_CALLBACK:
crm_trace("Copying %s data from %s as lrmd_event_data_t",
fsa_cause2string(cause), raised_from);
fsa_data->data = lrmd_copy_event((lrmd_event_data_t *) data);
fsa_data->data_type = fsa_dt_lrm;
break;
case C_TIMER_POPPED:
case C_SHUTDOWN:
case C_UNKNOWN:
case C_STARTUP:
crm_crit("Copying %s data (from %s) is not yet implemented",
fsa_cause2string(cause), raised_from);
crmd_exit(CRM_EX_SOFTWARE);
break;
}
}
/* make sure to free it properly later */
if (prepend) {
controld_globals.fsa_message_queue
= g_list_prepend(controld_globals.fsa_message_queue, fsa_data);
} else {
controld_globals.fsa_message_queue
= g_list_append(controld_globals.fsa_message_queue, fsa_data);
}
crm_trace("FSA message queue length is %d",
g_list_length(controld_globals.fsa_message_queue));
/* fsa_dump_queue(LOG_TRACE); */
if (old_len == g_list_length(controld_globals.fsa_message_queue)) {
crm_err("Couldn't add message to the queue");
}
if (input != I_WAIT_FOR_EVENT) {
controld_trigger_fsa();
}
}
void
fsa_dump_queue(int log_level)
{
int offset = 0;
for (GList *iter = controld_globals.fsa_message_queue; iter != NULL;
iter = iter->next) {
fsa_data_t *data = (fsa_data_t *) iter->data;
do_crm_log_unlikely(log_level,
"queue[%d.%d]: input %s raised by %s(%p.%d)\t(cause=%s)",
offset++, data->id, fsa_input2string(data->fsa_input),
data->origin, data->data, data->data_type,
fsa_cause2string(data->fsa_cause));
}
}
ha_msg_input_t *
copy_ha_msg_input(ha_msg_input_t * orig)
{
xmlNode *wrapper = NULL;
ha_msg_input_t *copy = pcmk__assert_alloc(1, sizeof(ha_msg_input_t));
copy->msg = (orig != NULL)? pcmk__xml_copy(NULL, orig->msg) : NULL;
wrapper = pcmk__xe_first_child(copy->msg, PCMK__XE_CRM_XML, NULL, NULL);
copy->xml = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
return copy;
}
void
delete_fsa_input(fsa_data_t * fsa_data)
{
lrmd_event_data_t *op = NULL;
xmlNode *foo = NULL;
if (fsa_data == NULL) {
return;
}
crm_trace("About to free %s data", fsa_cause2string(fsa_data->fsa_cause));
if (fsa_data->data != NULL) {
switch (fsa_data->data_type) {
case fsa_dt_ha_msg:
delete_ha_msg_input(fsa_data->data);
break;
case fsa_dt_xml:
foo = fsa_data->data;
free_xml(foo);
break;
case fsa_dt_lrm:
op = (lrmd_event_data_t *) fsa_data->data;
lrmd_free_event(op);
break;
case fsa_dt_none:
if (fsa_data->data != NULL) {
crm_err("Don't know how to free %s data from %s",
fsa_cause2string(fsa_data->fsa_cause), fsa_data->origin);
crmd_exit(CRM_EX_SOFTWARE);
}
break;
}
crm_trace("%s data freed", fsa_cause2string(fsa_data->fsa_cause));
}
free(fsa_data);
}
/* returns the next message */
fsa_data_t *
get_message(void)
{
fsa_data_t *message
= (fsa_data_t *) controld_globals.fsa_message_queue->data;
controld_globals.fsa_message_queue
= g_list_remove(controld_globals.fsa_message_queue, message);
crm_trace("Processing input %d", message->id);
return message;
}
void *
fsa_typed_data_adv(fsa_data_t * fsa_data, enum fsa_data_type a_type, const char *caller)
{
void *ret_val = NULL;
if (fsa_data == NULL) {
crm_err("%s: No FSA data available", caller);
} else if (fsa_data->data == NULL) {
crm_err("%s: No message data available. Origin: %s", caller, fsa_data->origin);
} else if (fsa_data->data_type != a_type) {
crm_crit("%s: Message data was the wrong type! %d vs. requested=%d. Origin: %s",
caller, fsa_data->data_type, a_type, fsa_data->origin);
CRM_ASSERT(fsa_data->data_type == a_type);
} else {
ret_val = fsa_data->data;
}
return ret_val;
}
/* A_MSG_ROUTE */
void
do_msg_route(long long action,
enum crmd_fsa_cause cause,
enum crmd_fsa_state cur_state,
enum crmd_fsa_input current_input, fsa_data_t * msg_data)
{
ha_msg_input_t *input = fsa_typed_data(fsa_dt_ha_msg);
route_message(msg_data->fsa_cause, input->msg);
}
void
route_message(enum crmd_fsa_cause cause, xmlNode * input)
{
ha_msg_input_t fsa_input;
enum crmd_fsa_input result = I_NULL;
fsa_input.msg = input;
CRM_CHECK(cause == C_IPC_MESSAGE || cause == C_HA_MESSAGE, return);
/* try passing the buck first */
if (relay_message(input, cause == C_IPC_MESSAGE)) {
return;
}
/* handle locally */
result = handle_message(input, cause);
/* done or process later? */
switch (result) {
case I_NULL:
case I_CIB_OP:
case I_ROUTER:
case I_NODE_JOIN:
case I_JOIN_REQUEST:
case I_JOIN_RESULT:
break;
default:
/* Defering local processing of message */
register_fsa_input_later(cause, result, &fsa_input);
return;
}
if (result != I_NULL) {
/* add to the front of the queue */
register_fsa_input(cause, result, &fsa_input);
}
}
gboolean
relay_message(xmlNode * msg, gboolean originated_locally)
{
enum crm_ais_msg_types dest = crm_msg_ais;
bool is_for_dc = false;
bool is_for_dcib = false;
bool is_for_te = false;
bool is_for_crm = false;
bool is_for_cib = false;
bool is_local = false;
bool broadcast = false;
const char *host_to = NULL;
const char *sys_to = NULL;
const char *sys_from = NULL;
const char *type = NULL;
const char *task = NULL;
const char *ref = NULL;
crm_node_t *node_to = NULL;
CRM_CHECK(msg != NULL, return TRUE);
host_to = crm_element_value(msg, PCMK__XA_CRM_HOST_TO);
sys_to = crm_element_value(msg, PCMK__XA_CRM_SYS_TO);
sys_from = crm_element_value(msg, PCMK__XA_CRM_SYS_FROM);
type = crm_element_value(msg, PCMK__XA_T);
task = crm_element_value(msg, PCMK__XA_CRM_TASK);
ref = crm_element_value(msg, PCMK_XA_REFERENCE);
broadcast = pcmk__str_empty(host_to);
if (ref == NULL) {
ref = "without reference ID";
}
if (pcmk__str_eq(task, CRM_OP_HELLO, pcmk__str_casei)) {
crm_trace("Received hello %s from %s (no processing needed)",
ref, pcmk__s(sys_from, "unidentified source"));
crm_log_xml_trace(msg, "hello");
return TRUE;
}
// Require message type (set by create_request())
if (!pcmk__str_eq(type, PCMK__VALUE_CRMD, pcmk__str_none)) {
crm_warn("Ignoring invalid message %s with type '%s' "
"(not '" PCMK__VALUE_CRMD "')",
ref, pcmk__s(type, ""));
crm_log_xml_trace(msg, "ignored");
return TRUE;
}
// Require a destination subsystem (also set by create_request())
if (sys_to == NULL) {
crm_warn("Ignoring invalid message %s with no " PCMK__XA_CRM_SYS_TO,
ref);
crm_log_xml_trace(msg, "ignored");
return TRUE;
}
// Get the message type appropriate to the destination subsystem
if (is_corosync_cluster()) {
dest = text2msg_type(sys_to);
if ((dest < crm_msg_ais) || (dest > crm_msg_stonith_ng)) {
/* Unrecognized value, use a sane default
*
* @TODO Maybe we should bail instead
*/
dest = crm_msg_crmd;
}
}
is_for_dc = (strcasecmp(CRM_SYSTEM_DC, sys_to) == 0);
is_for_dcib = (strcasecmp(CRM_SYSTEM_DCIB, sys_to) == 0);
is_for_te = (strcasecmp(CRM_SYSTEM_TENGINE, sys_to) == 0);
is_for_cib = (strcasecmp(CRM_SYSTEM_CIB, sys_to) == 0);
is_for_crm = (strcasecmp(CRM_SYSTEM_CRMD, sys_to) == 0);
// Check whether message should be processed locally
is_local = false;
if (broadcast) {
if (is_for_dc || is_for_te) {
is_local = false;
} else if (is_for_crm) {
if (pcmk__strcase_any_of(task, CRM_OP_NODE_INFO,
PCMK__CONTROLD_CMD_NODES, NULL)) {
/* Node info requests do not specify a host, which is normally
* treated as "all hosts", because the whole point is that the
* client may not know the local node name. Always handle these
* requests locally.
*/
is_local = true;
} else {
is_local = !originated_locally;
}
} else {
is_local = true;
}
} else if (pcmk__str_eq(controld_globals.our_nodename, host_to,
pcmk__str_casei)) {
is_local = true;
} else if (is_for_crm && pcmk__str_eq(task, CRM_OP_LRM_DELETE, pcmk__str_casei)) {
xmlNode *wrapper = pcmk__xe_first_child(msg, PCMK__XE_CRM_XML, NULL,
NULL);
xmlNode *msg_data = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
const char *mode = crm_element_value(msg_data, PCMK__XA_MODE);
if (pcmk__str_eq(mode, PCMK__VALUE_CIB, pcmk__str_none)) {
// Local delete of an offline node's resource history
is_local = true;
}
}
// Check whether message should be relayed
if (is_for_dc || is_for_dcib || is_for_te) {
if (AM_I_DC) {
if (is_for_te) {
crm_trace("Route message %s locally as transition request",
ref);
crm_log_xml_trace(msg, sys_to);
send_msg_via_ipc(msg, sys_to);
return TRUE; // No further processing of message is needed
}
crm_trace("Route message %s locally as DC request", ref);
return FALSE; // More to be done by caller
}
if (originated_locally
&& !pcmk__strcase_any_of(sys_from, CRM_SYSTEM_PENGINE,
CRM_SYSTEM_TENGINE, NULL)) {
crm_trace("Relay message %s to DC (via %s)",
ref, pcmk__s(host_to, "broadcast"));
crm_log_xml_trace(msg, "relayed");
if (!broadcast) {
node_to = pcmk__get_node(0, host_to, NULL,
pcmk__node_search_cluster);
}
send_cluster_message(node_to, dest, msg, TRUE);
return TRUE;
}
/* Transition engine and scheduler messages are sent only to the DC on
* the same node. If we are no longer the DC, discard this message.
*/
crm_trace("Ignoring message %s because we are no longer DC", ref);
crm_log_xml_trace(msg, "ignored");
return TRUE; // No further processing of message is needed
}
if (is_local) {
if (is_for_crm || is_for_cib) {
crm_trace("Route message %s locally as controller request", ref);
return FALSE; // More to be done by caller
}
crm_trace("Relay message %s locally to %s", ref, sys_to);
crm_log_xml_trace(msg, "IPC-relay");
send_msg_via_ipc(msg, sys_to);
return TRUE;
}
if (!broadcast) {
node_to = pcmk__search_node_caches(0, host_to,
pcmk__node_search_cluster);
if (node_to == NULL) {
crm_warn("Ignoring message %s because node %s is unknown",
ref, host_to);
crm_log_xml_trace(msg, "ignored");
return TRUE;
}
}
crm_trace("Relay message %s to %s",
ref, pcmk__s(host_to, "all peers"));
crm_log_xml_trace(msg, "relayed");
send_cluster_message(node_to, dest, msg, TRUE);
return TRUE;
}
// Return true if field contains a positive integer
static bool
authorize_version(xmlNode *message_data, const char *field,
const char *client_name, const char *ref, const char *uuid)
{
const char *version = crm_element_value(message_data, field);
long long version_num;
if ((pcmk__scan_ll(version, &version_num, -1LL) != pcmk_rc_ok)
|| (version_num < 0LL)) {
crm_warn("Rejected IPC hello from %s: '%s' is not a valid protocol %s "
CRM_XS " ref=%s uuid=%s",
client_name, ((version == NULL)? "" : version),
field, (ref? ref : "none"), uuid);
return false;
}
return true;
}
/*!
* \internal
* \brief Check whether a client IPC message is acceptable
*
* If a given client IPC message is a hello, "authorize" it by ensuring it has
* valid information such as a protocol version, and return false indicating
* that nothing further needs to be done with the message. If the message is not
* a hello, just return true to indicate it needs further processing.
*
* \param[in] client_msg XML of IPC message
* \param[in,out] curr_client If IPC is not proxied, client that sent message
* \param[in] proxy_session If IPC is proxied, the session ID
*
* \return true if message needs further processing, false if it doesn't
*/
bool
controld_authorize_ipc_message(const xmlNode *client_msg, pcmk__client_t *curr_client,
const char *proxy_session)
{
xmlNode *wrapper = NULL;
xmlNode *message_data = NULL;
const char *client_name = NULL;
const char *op = crm_element_value(client_msg, PCMK__XA_CRM_TASK);
const char *ref = crm_element_value(client_msg, PCMK_XA_REFERENCE);
const char *uuid = (curr_client? curr_client->id : proxy_session);
if (uuid == NULL) {
crm_warn("IPC message from client rejected: No client identifier "
CRM_XS " ref=%s", (ref? ref : "none"));
goto rejected;
}
if (!pcmk__str_eq(CRM_OP_HELLO, op, pcmk__str_casei)) {
// Only hello messages need to be authorized
return true;
}
wrapper = pcmk__xe_first_child(client_msg, PCMK__XE_CRM_XML, NULL, NULL);
message_data = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
client_name = crm_element_value(message_data, PCMK__XA_CLIENT_NAME);
if (pcmk__str_empty(client_name)) {
crm_warn("IPC hello from client rejected: No client name",
CRM_XS " ref=%s uuid=%s", (ref? ref : "none"), uuid);
goto rejected;
}
if (!authorize_version(message_data, PCMK__XA_MAJOR_VERSION, client_name,
ref, uuid)) {
goto rejected;
}
if (!authorize_version(message_data, PCMK__XA_MINOR_VERSION, client_name,
ref, uuid)) {
goto rejected;
}
crm_trace("Validated IPC hello from client %s", client_name);
crm_log_xml_trace(client_msg, "hello");
if (curr_client) {
curr_client->userdata = pcmk__str_copy(client_name);
}
controld_trigger_fsa();
return false;
rejected:
crm_log_xml_trace(client_msg, "rejected");
if (curr_client) {
qb_ipcs_disconnect(curr_client->ipcs);
}
return false;
}
static enum crmd_fsa_input
handle_message(xmlNode *msg, enum crmd_fsa_cause cause)
{
const char *type = NULL;
CRM_CHECK(msg != NULL, return I_NULL);
type = crm_element_value(msg, PCMK__XA_SUBT);
if (pcmk__str_eq(type, PCMK__VALUE_REQUEST, pcmk__str_none)) {
return handle_request(msg, cause);
}
if (pcmk__str_eq(type, PCMK__VALUE_RESPONSE, pcmk__str_none)) {
handle_response(msg);
return I_NULL;
}
crm_warn("Ignoring message with unknown " PCMK__XA_SUBT" '%s'",
pcmk__s(type, ""));
crm_log_xml_trace(msg, "bad");
return I_NULL;
}
static enum crmd_fsa_input
handle_failcount_op(xmlNode * stored_msg)
{
const char *rsc = NULL;
const char *uname = NULL;
const char *op = NULL;
char *interval_spec = NULL;
guint interval_ms = 0;
gboolean is_remote_node = FALSE;
xmlNode *wrapper = pcmk__xe_first_child(stored_msg, PCMK__XE_CRM_XML, NULL,
NULL);
xmlNode *xml_op = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
if (xml_op) {
xmlNode *xml_rsc = pcmk__xe_first_child(xml_op, PCMK_XE_PRIMITIVE, NULL,
NULL);
xmlNode *xml_attrs = pcmk__xe_first_child(xml_op, PCMK__XE_ATTRIBUTES,
NULL, NULL);
if (xml_rsc) {
rsc = pcmk__xe_id(xml_rsc);
}
if (xml_attrs) {
op = crm_element_value(xml_attrs,
CRM_META "_" PCMK__META_CLEAR_FAILURE_OP);
crm_element_value_ms(xml_attrs,
CRM_META "_" PCMK__META_CLEAR_FAILURE_INTERVAL,
&interval_ms);
}
}
uname = crm_element_value(xml_op, PCMK__META_ON_NODE);
if ((rsc == NULL) || (uname == NULL)) {
crm_log_xml_warn(stored_msg, "invalid failcount op");
return I_NULL;
}
if (crm_element_value(xml_op, PCMK__XA_ROUTER_NODE)) {
is_remote_node = TRUE;
}
crm_debug("Clearing failures for %s-interval %s on %s "
"from attribute manager, CIB, and executor state",
pcmk__readable_interval(interval_ms), rsc, uname);
if (interval_ms) {
interval_spec = crm_strdup_printf("%ums", interval_ms);
}
update_attrd_clear_failures(uname, rsc, op, interval_spec, is_remote_node);
free(interval_spec);
controld_cib_delete_last_failure(rsc, uname, op, interval_ms);
lrm_clear_last_failure(rsc, uname, op, interval_ms);
return I_NULL;
}
static enum crmd_fsa_input
handle_lrm_delete(xmlNode *stored_msg)
{
const char *mode = NULL;
xmlNode *wrapper = pcmk__xe_first_child(stored_msg, PCMK__XE_CRM_XML, NULL,
NULL);
xmlNode *msg_data = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
CRM_CHECK(msg_data != NULL, return I_NULL);
/* CRM_OP_LRM_DELETE has two distinct modes. The default behavior is to
* relay the operation to the affected node, which will unregister the
* resource from the local executor, clear the resource's history from the
* CIB, and do some bookkeeping in the controller.
*
* However, if the affected node is offline, the client will specify
* mode=PCMK__VALUE_CIB which means the controller receiving the operation
* should clear the resource's history from the CIB and nothing else. This
* is used to clear shutdown locks.
*/
mode = crm_element_value(msg_data, PCMK__XA_MODE);
if (!pcmk__str_eq(mode, PCMK__VALUE_CIB, pcmk__str_none)) {
// Relay to affected node
crm_xml_add(stored_msg, PCMK__XA_CRM_SYS_TO, CRM_SYSTEM_LRMD);
return I_ROUTER;
} else {
// Delete CIB history locally (compare with do_lrm_delete())
const char *from_sys = NULL;
const char *user_name = NULL;
const char *rsc_id = NULL;
const char *node = NULL;
xmlNode *rsc_xml = NULL;
int rc = pcmk_rc_ok;
rsc_xml = pcmk__xe_first_child(msg_data, PCMK_XE_PRIMITIVE, NULL, NULL);
CRM_CHECK(rsc_xml != NULL, return I_NULL);
rsc_id = pcmk__xe_id(rsc_xml);
from_sys = crm_element_value(stored_msg, PCMK__XA_CRM_SYS_FROM);
node = crm_element_value(msg_data, PCMK__META_ON_NODE);
user_name = pcmk__update_acl_user(stored_msg, PCMK__XA_CRM_USER, NULL);
crm_debug("Handling " CRM_OP_LRM_DELETE " for %s on %s locally%s%s "
"(clearing CIB resource history only)", rsc_id, node,
(user_name? " for user " : ""), (user_name? user_name : ""));
rc = controld_delete_resource_history(rsc_id, node, user_name,
cib_dryrun|cib_sync_call);
if (rc == pcmk_rc_ok) {
rc = controld_delete_resource_history(rsc_id, node, user_name,
crmd_cib_smart_opt());
}
/* Notify client. Also notify tengine if mode=PCMK__VALUE_CIB and
* op=CRM_OP_LRM_DELETE.
*/
if (from_sys) {
lrmd_event_data_t *op = NULL;
const char *from_host = crm_element_value(stored_msg, PCMK__XA_SRC);
const char *transition;
if (strcmp(from_sys, CRM_SYSTEM_TENGINE)) {
transition = crm_element_value(msg_data,
PCMK__XA_TRANSITION_KEY);
} else {
transition = crm_element_value(stored_msg,
PCMK__XA_TRANSITION_KEY);
}
crm_info("Notifying %s on %s that %s was%s deleted",
from_sys, (from_host? from_host : "local node"), rsc_id,
((rc == pcmk_rc_ok)? "" : " not"));
op = lrmd_new_event(rsc_id, PCMK_ACTION_DELETE, 0);
op->type = lrmd_event_exec_complete;
op->user_data = pcmk__str_copy(pcmk__s(transition, FAKE_TE_ID));
op->params = pcmk__strkey_table(free, free);
pcmk__insert_dup(op->params, PCMK_XA_CRM_FEATURE_SET,
CRM_FEATURE_SET);
controld_rc2event(op, rc);
controld_ack_event_directly(from_host, from_sys, NULL, op, rsc_id);
lrmd_free_event(op);
controld_trigger_delete_refresh(from_sys, rsc_id);
}
return I_NULL;
}
}
/*!
* \brief Handle a CRM_OP_REMOTE_STATE message by updating remote peer cache
*
* \param[in] msg Message XML
*
* \return Next FSA input
*/
static enum crmd_fsa_input
handle_remote_state(const xmlNode *msg)
{
const char *conn_host = NULL;
const char *remote_uname = pcmk__xe_id(msg);
crm_node_t *remote_peer;
bool remote_is_up = false;
int rc = pcmk_rc_ok;
rc = pcmk__xe_get_bool_attr(msg, PCMK__XA_IN_CCM, &remote_is_up);
CRM_CHECK(remote_uname && rc == pcmk_rc_ok, return I_NULL);
remote_peer = pcmk__cluster_lookup_remote_node(remote_uname);
CRM_CHECK(remote_peer, return I_NULL);
pcmk__update_peer_state(__func__, remote_peer,
remote_is_up ? CRM_NODE_MEMBER : CRM_NODE_LOST,
0);
conn_host = crm_element_value(msg, PCMK__XA_CONNECTION_HOST);
if (conn_host) {
pcmk__str_update(&remote_peer->conn_host, conn_host);
} else if (remote_peer->conn_host) {
free(remote_peer->conn_host);
remote_peer->conn_host = NULL;
}
return I_NULL;
}
/*!
* \brief Handle a CRM_OP_PING message
*
* \param[in] msg Message XML
*
* \return Next FSA input
*/
static enum crmd_fsa_input
handle_ping(const xmlNode *msg)
{
const char *value = NULL;
xmlNode *ping = NULL;
xmlNode *reply = NULL;
// Build reply
ping = pcmk__xe_create(NULL, PCMK__XE_PING_RESPONSE);
value = crm_element_value(msg, PCMK__XA_CRM_SYS_TO);
crm_xml_add(ping, PCMK__XA_CRM_SUBSYSTEM, value);
// Add controller state
value = fsa_state2string(controld_globals.fsa_state);
crm_xml_add(ping, PCMK__XA_CRMD_STATE, value);
crm_notice("Current ping state: %s", value); // CTS needs this
// Add controller health
// @TODO maybe do some checks to determine meaningful status
crm_xml_add(ping, PCMK_XA_RESULT, "ok");
// Send reply
reply = create_reply(msg, ping);
free_xml(ping);
if (reply != NULL) {
(void) relay_message(reply, TRUE);
free_xml(reply);
}
// Nothing further to do
return I_NULL;
}
/*!
* \brief Handle a PCMK__CONTROLD_CMD_NODES message
*
* \param[in] request Message XML
*
* \return Next FSA input
*/
static enum crmd_fsa_input
handle_node_list(const xmlNode *request)
{
GHashTableIter iter;
crm_node_t *node = NULL;
xmlNode *reply = NULL;
xmlNode *reply_data = NULL;
// Create message data for reply
reply_data = pcmk__xe_create(NULL, PCMK_XE_NODES);
g_hash_table_iter_init(&iter, crm_peer_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) & node)) {
xmlNode *xml = pcmk__xe_create(reply_data, PCMK_XE_NODE);
crm_xml_add_ll(xml, PCMK_XA_ID, (long long) node->id); // uint32_t
crm_xml_add(xml, PCMK_XA_UNAME, node->uname);
crm_xml_add(xml, PCMK__XA_IN_CCM, node->state);
}
// Create and send reply
reply = create_reply(request, reply_data);
free_xml(reply_data);
if (reply) {
(void) relay_message(reply, TRUE);
free_xml(reply);
}
// Nothing further to do
return I_NULL;
}
/*!
* \brief Handle a CRM_OP_NODE_INFO request
*
* \param[in] msg Message XML
*
* \return Next FSA input
*/
static enum crmd_fsa_input
handle_node_info_request(const xmlNode *msg)
{
const char *value = NULL;
crm_node_t *node = NULL;
int node_id = 0;
xmlNode *reply = NULL;
xmlNode *reply_data = NULL;
// Build reply
reply_data = pcmk__xe_create(NULL, PCMK_XE_NODE);
crm_xml_add(reply_data, PCMK__XA_CRM_SUBSYSTEM, CRM_SYSTEM_CRMD);
// Add whether current partition has quorum
pcmk__xe_set_bool_attr(reply_data, PCMK_XA_HAVE_QUORUM,
pcmk_is_set(controld_globals.flags,
controld_has_quorum));
// Check whether client requested node info by ID and/or name
crm_element_value_int(msg, PCMK_XA_ID, &node_id);
if (node_id < 0) {
node_id = 0;
}
value = crm_element_value(msg, PCMK_XA_UNAME);
// Default to local node if none given
if ((node_id == 0) && (value == NULL)) {
value = controld_globals.our_nodename;
}
node = pcmk__search_node_caches(node_id, value, pcmk__node_search_any);
if (node) {
crm_xml_add(reply_data, PCMK_XA_ID, node->uuid);
crm_xml_add(reply_data, PCMK_XA_UNAME, node->uname);
crm_xml_add(reply_data, PCMK_XA_CRMD, node->state);
pcmk__xe_set_bool_attr(reply_data, PCMK_XA_REMOTE_NODE,
pcmk_is_set(node->flags, crm_remote_node));
}
// Send reply
reply = create_reply(msg, reply_data);
free_xml(reply_data);
if (reply != NULL) {
(void) relay_message(reply, TRUE);
free_xml(reply);
}
// Nothing further to do
return I_NULL;
}
static void
verify_feature_set(xmlNode *msg)
{
const char *dc_version = crm_element_value(msg, PCMK_XA_CRM_FEATURE_SET);
if (dc_version == NULL) {
/* All we really know is that the DC feature set is older than 3.1.0,
* but that's also all that really matters.
*/
dc_version = "3.0.14";
}
if (feature_set_compatible(dc_version, CRM_FEATURE_SET)) {
crm_trace("Local feature set (%s) is compatible with DC's (%s)",
CRM_FEATURE_SET, dc_version);
} else {
crm_err("Local feature set (%s) is incompatible with DC's (%s)",
CRM_FEATURE_SET, dc_version);
// Nothing is likely to improve without administrator involvement
controld_set_fsa_input_flags(R_STAYDOWN);
crmd_exit(CRM_EX_FATAL);
}
}
// DC gets own shutdown all-clear
static enum crmd_fsa_input
handle_shutdown_self_ack(xmlNode *stored_msg)
{
const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC);
if (pcmk_is_set(controld_globals.fsa_input_register, R_SHUTDOWN)) {
// The expected case -- we initiated own shutdown sequence
crm_info("Shutting down controller");
return I_STOP;
}
if (pcmk__str_eq(host_from, controld_globals.dc_name, pcmk__str_casei)) {
// Must be logic error -- DC confirming its own unrequested shutdown
crm_err("Shutting down controller immediately due to "
"unexpected shutdown confirmation");
return I_TERMINATE;
}
if (controld_globals.fsa_state != S_STOPPING) {
// Shouldn't happen -- non-DC confirming unrequested shutdown
crm_err("Starting new DC election because %s is "
"confirming shutdown we did not request",
(host_from? host_from : "another node"));
return I_ELECTION;
}
// Shouldn't happen, but we are already stopping anyway
crm_debug("Ignoring unexpected shutdown confirmation from %s",
(host_from? host_from : "another node"));
return I_NULL;
}
// Non-DC gets shutdown all-clear from DC
static enum crmd_fsa_input
handle_shutdown_ack(xmlNode *stored_msg)
{
const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC);
if (host_from == NULL) {
crm_warn("Ignoring shutdown request without origin specified");
return I_NULL;
}
if (pcmk__str_eq(host_from, controld_globals.dc_name,
pcmk__str_null_matches|pcmk__str_casei)) {
if (pcmk_is_set(controld_globals.fsa_input_register, R_SHUTDOWN)) {
crm_info("Shutting down controller after confirmation from %s",
host_from);
} else {
crm_err("Shutting down controller after unexpected "
"shutdown request from %s", host_from);
controld_set_fsa_input_flags(R_STAYDOWN);
}
return I_STOP;
}
crm_warn("Ignoring shutdown request from %s because DC is %s",
host_from, controld_globals.dc_name);
return I_NULL;
}
static enum crmd_fsa_input
handle_request(xmlNode *stored_msg, enum crmd_fsa_cause cause)
{
xmlNode *msg = NULL;
const char *op = crm_element_value(stored_msg, PCMK__XA_CRM_TASK);
/* Optimize this for the DC - it has the most to do */
crm_log_xml_trace(stored_msg, "request");
if (op == NULL) {
crm_warn("Ignoring request without " PCMK__XA_CRM_TASK);
return I_NULL;
}
if (strcmp(op, CRM_OP_SHUTDOWN_REQ) == 0) {
const char *from = crm_element_value(stored_msg, PCMK__XA_SRC);
crm_node_t *node = pcmk__search_node_caches(0, from,
pcmk__node_search_cluster);
pcmk__update_peer_expected(__func__, node, CRMD_JOINSTATE_DOWN);
if(AM_I_DC == FALSE) {
return I_NULL; /* Done */
}
}
/*========== DC-Only Actions ==========*/
if (AM_I_DC) {
if (strcmp(op, CRM_OP_JOIN_ANNOUNCE) == 0) {
return I_NODE_JOIN;
} else if (strcmp(op, CRM_OP_JOIN_REQUEST) == 0) {
return I_JOIN_REQUEST;
} else if (strcmp(op, CRM_OP_JOIN_CONFIRM) == 0) {
return I_JOIN_RESULT;
} else if (strcmp(op, CRM_OP_SHUTDOWN) == 0) {
return handle_shutdown_self_ack(stored_msg);
} else if (strcmp(op, CRM_OP_SHUTDOWN_REQ) == 0) {
// Another controller wants to shut down its node
return handle_shutdown_request(stored_msg);
}
}
/*========== common actions ==========*/
if (strcmp(op, CRM_OP_NOVOTE) == 0) {
ha_msg_input_t fsa_input;
fsa_input.msg = stored_msg;
register_fsa_input_adv(C_HA_MESSAGE, I_NULL, &fsa_input,
A_ELECTION_COUNT | A_ELECTION_CHECK, FALSE,
__func__);
} else if (strcmp(op, CRM_OP_REMOTE_STATE) == 0) {
/* a remote connection host is letting us know the node state */
return handle_remote_state(stored_msg);
} else if (strcmp(op, CRM_OP_THROTTLE) == 0) {
throttle_update(stored_msg);
if (AM_I_DC && (controld_globals.transition_graph != NULL)
&& !controld_globals.transition_graph->complete) {
crm_debug("The throttle changed. Trigger a graph.");
trigger_graph();
}
return I_NULL;
} else if (strcmp(op, CRM_OP_CLEAR_FAILCOUNT) == 0) {
return handle_failcount_op(stored_msg);
} else if (strcmp(op, CRM_OP_VOTE) == 0) {
/* count the vote and decide what to do after that */
ha_msg_input_t fsa_input;
fsa_input.msg = stored_msg;
register_fsa_input_adv(C_HA_MESSAGE, I_NULL, &fsa_input,
A_ELECTION_COUNT | A_ELECTION_CHECK, FALSE,
__func__);
/* Sometimes we _must_ go into S_ELECTION */
if (controld_globals.fsa_state == S_HALT) {
crm_debug("Forcing an election from S_HALT");
return I_ELECTION;
}
} else if (strcmp(op, CRM_OP_JOIN_OFFER) == 0) {
verify_feature_set(stored_msg);
crm_debug("Raising I_JOIN_OFFER: join-%s",
crm_element_value(stored_msg, PCMK__XA_JOIN_ID));
return I_JOIN_OFFER;
} else if (strcmp(op, CRM_OP_JOIN_ACKNAK) == 0) {
crm_debug("Raising I_JOIN_RESULT: join-%s",
crm_element_value(stored_msg, PCMK__XA_JOIN_ID));
return I_JOIN_RESULT;
} else if (strcmp(op, CRM_OP_LRM_DELETE) == 0) {
return handle_lrm_delete(stored_msg);
} else if ((strcmp(op, CRM_OP_LRM_FAIL) == 0)
|| (strcmp(op, CRM_OP_LRM_REFRESH) == 0) // @COMPAT
|| (strcmp(op, CRM_OP_REPROBE) == 0)) {
crm_xml_add(stored_msg, PCMK__XA_CRM_SYS_TO, CRM_SYSTEM_LRMD);
return I_ROUTER;
} else if (strcmp(op, CRM_OP_NOOP) == 0) {
return I_NULL;
} else if (strcmp(op, CRM_OP_PING) == 0) {
return handle_ping(stored_msg);
} else if (strcmp(op, CRM_OP_NODE_INFO) == 0) {
return handle_node_info_request(stored_msg);
} else if (strcmp(op, CRM_OP_RM_NODE_CACHE) == 0) {
int id = 0;
const char *name = NULL;
crm_element_value_int(stored_msg, PCMK_XA_ID, &id);
name = crm_element_value(stored_msg, PCMK_XA_UNAME);
if(cause == C_IPC_MESSAGE) {
msg = create_request(CRM_OP_RM_NODE_CACHE, NULL, NULL, CRM_SYSTEM_CRMD, CRM_SYSTEM_CRMD, NULL);
if (send_cluster_message(NULL, crm_msg_crmd, msg, TRUE) == FALSE) {
crm_err("Could not instruct peers to remove references to node %s/%u", name, id);
} else {
crm_notice("Instructing peers to remove references to node %s/%u", name, id);
}
free_xml(msg);
} else {
- reap_crm_member(id, name);
+ pcmk__cluster_forget_cluster_node(id, name);
/* If we're forgetting this node, also forget any failures to fence
* it, so we don't carry that over to any node added later with the
* same name.
*/
st_fail_count_reset(name);
}
} else if (strcmp(op, CRM_OP_MAINTENANCE_NODES) == 0) {
xmlNode *wrapper = pcmk__xe_first_child(stored_msg, PCMK__XE_CRM_XML,
NULL, NULL);
xmlNode *xml = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
remote_ra_process_maintenance_nodes(xml);
} else if (strcmp(op, PCMK__CONTROLD_CMD_NODES) == 0) {
return handle_node_list(stored_msg);
/*========== (NOT_DC)-Only Actions ==========*/
} else if (!AM_I_DC) {
if (strcmp(op, CRM_OP_SHUTDOWN) == 0) {
return handle_shutdown_ack(stored_msg);
}
} else {
crm_err("Unexpected request (%s) sent to %s", op, AM_I_DC ? "the DC" : "non-DC node");
crm_log_xml_err(stored_msg, "Unexpected");
}
return I_NULL;
}
static void
handle_response(xmlNode *stored_msg)
{
const char *op = crm_element_value(stored_msg, PCMK__XA_CRM_TASK);
crm_log_xml_trace(stored_msg, "reply");
if (op == NULL) {
crm_warn("Ignoring reply without " PCMK__XA_CRM_TASK);
} else if (AM_I_DC && strcmp(op, CRM_OP_PECALC) == 0) {
// Check whether scheduler answer been superseded by subsequent request
const char *msg_ref = crm_element_value(stored_msg, PCMK_XA_REFERENCE);
if (msg_ref == NULL) {
crm_err("%s - Ignoring calculation with no reference", op);
} else if (pcmk__str_eq(msg_ref, controld_globals.fsa_pe_ref,
pcmk__str_none)) {
ha_msg_input_t fsa_input;
controld_stop_sched_timer();
fsa_input.msg = stored_msg;
register_fsa_input_later(C_IPC_MESSAGE, I_PE_SUCCESS, &fsa_input);
} else {
crm_info("%s calculation %s is obsolete", op, msg_ref);
}
} else if (strcmp(op, CRM_OP_VOTE) == 0
|| strcmp(op, CRM_OP_SHUTDOWN_REQ) == 0 || strcmp(op, CRM_OP_SHUTDOWN) == 0) {
} else {
const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC);
crm_err("Unexpected response (op=%s, src=%s) sent to the %s",
op, host_from, AM_I_DC ? "DC" : "controller");
}
}
static enum crmd_fsa_input
handle_shutdown_request(xmlNode * stored_msg)
{
/* handle here to avoid potential version issues
* where the shutdown message/procedure may have
* been changed in later versions.
*
* This way the DC is always in control of the shutdown
*/
char *now_s = NULL;
const char *host_from = crm_element_value(stored_msg, PCMK__XA_SRC);
if (host_from == NULL) {
/* we're shutting down and the DC */
host_from = controld_globals.our_nodename;
}
crm_info("Creating shutdown request for %s (state=%s)", host_from,
fsa_state2string(controld_globals.fsa_state));
crm_log_xml_trace(stored_msg, "message");
now_s = pcmk__ttoa(time(NULL));
update_attrd(host_from, PCMK__NODE_ATTR_SHUTDOWN, now_s, NULL, FALSE);
free(now_s);
/* will be picked up by the TE as long as its running */
return I_NULL;
}
static void
send_msg_via_ipc(xmlNode * msg, const char *sys)
{
pcmk__client_t *client_channel = NULL;
CRM_CHECK(sys != NULL, return);
client_channel = pcmk__find_client_by_id(sys);
if (crm_element_value(msg, PCMK__XA_SRC) == NULL) {
crm_xml_add(msg, PCMK__XA_SRC, controld_globals.our_nodename);
}
if (client_channel != NULL) {
/* Transient clients such as crmadmin */
pcmk__ipc_send_xml(client_channel, 0, msg, crm_ipc_server_event);
} else if (pcmk__str_eq(sys, CRM_SYSTEM_TENGINE, pcmk__str_none)) {
xmlNode *wrapper = pcmk__xe_first_child(msg, PCMK__XE_CRM_XML, NULL,
NULL);
xmlNode *data = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
process_te_message(msg, data);
} else if (pcmk__str_eq(sys, CRM_SYSTEM_LRMD, pcmk__str_none)) {
fsa_data_t fsa_data;
ha_msg_input_t fsa_input;
xmlNode *wrapper = NULL;
fsa_input.msg = msg;
wrapper = pcmk__xe_first_child(msg, PCMK__XE_CRM_XML, NULL, NULL);
fsa_input.xml = pcmk__xe_first_child(wrapper, NULL, NULL, NULL);
fsa_data.id = 0;
fsa_data.actions = 0;
fsa_data.data = &fsa_input;
fsa_data.fsa_input = I_MESSAGE;
fsa_data.fsa_cause = C_IPC_MESSAGE;
fsa_data.origin = __func__;
fsa_data.data_type = fsa_dt_ha_msg;
do_lrm_invoke(A_LRM_INVOKE, C_IPC_MESSAGE, controld_globals.fsa_state,
I_MESSAGE, &fsa_data);
} else if (crmd_is_proxy_session(sys)) {
crmd_proxy_send(sys, msg);
} else {
crm_info("Received invalid request: unknown subsystem '%s'", sys);
}
}
void
delete_ha_msg_input(ha_msg_input_t * orig)
{
if (orig == NULL) {
return;
}
free_xml(orig->msg);
free(orig);
}
/*!
* \internal
* \brief Notify the cluster of a remote node state change
*
* \param[in] node_name Node's name
* \param[in] node_up true if node is up, false if down
*/
void
broadcast_remote_state_message(const char *node_name, bool node_up)
{
xmlNode *msg = create_request(CRM_OP_REMOTE_STATE, NULL, NULL,
CRM_SYSTEM_CRMD, CRM_SYSTEM_CRMD, NULL);
crm_info("Notifying cluster of Pacemaker Remote node %s %s",
node_name, node_up? "coming up" : "going down");
crm_xml_add(msg, PCMK_XA_ID, node_name);
pcmk__xe_set_bool_attr(msg, PCMK__XA_IN_CCM, node_up);
if (node_up) {
crm_xml_add(msg, PCMK__XA_CONNECTION_HOST,
controld_globals.our_nodename);
}
send_cluster_message(NULL, crm_msg_crmd, msg, TRUE);
free_xml(msg);
}
diff --git a/daemons/fenced/fenced_commands.c b/daemons/fenced/fenced_commands.c
index 3c035c0930..9e0e647192 100644
--- a/daemons/fenced/fenced_commands.c
+++ b/daemons/fenced/fenced_commands.c
@@ -1,3709 +1,3709 @@
/*
* Copyright 2009-2024 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU General Public License version 2
* or later (GPLv2+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#include <sys/param.h>
#include <stdio.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <sys/stat.h>
#include <unistd.h>
#include <sys/utsname.h>
#include <stdlib.h>
#include <errno.h>
#include <fcntl.h>
#include <ctype.h>
#include <crm/crm.h>
#include <crm/common/ipc.h>
#include <crm/common/ipc_internal.h>
#include <crm/cluster/internal.h>
#include <crm/common/mainloop.h>
#include <crm/stonith-ng.h>
#include <crm/fencing/internal.h>
#include <crm/common/xml.h>
#include <pacemaker-fenced.h>
GHashTable *device_list = NULL;
GHashTable *topology = NULL;
static GList *cmd_list = NULL;
static GHashTable *fenced_handlers = NULL;
struct device_search_s {
/* target of fence action */
char *host;
/* requested fence action */
char *action;
/* timeout to use if a device is queried dynamically for possible targets */
int per_device_timeout;
/* number of registered fencing devices at time of request */
int replies_needed;
/* number of device replies received so far */
int replies_received;
/* whether the target is eligible to perform requested action (or off) */
bool allow_suicide;
/* private data to pass to search callback function */
void *user_data;
/* function to call when all replies have been received */
void (*callback) (GList * devices, void *user_data);
/* devices capable of performing requested action (or off if remapping) */
GList *capable;
/* Whether to perform searches that support the action */
uint32_t support_action_only;
};
static gboolean stonith_device_dispatch(gpointer user_data);
static void st_child_done(int pid, const pcmk__action_result_t *result,
void *user_data);
static void search_devices_record_result(struct device_search_s *search, const char *device,
gboolean can_fence);
static int get_agent_metadata(const char *agent, xmlNode **metadata);
static void read_action_metadata(stonith_device_t *device);
static enum fenced_target_by unpack_level_kind(const xmlNode *level);
typedef struct async_command_s {
int id;
int pid;
int fd_stdout;
int options;
int default_timeout; /* seconds */
int timeout; /* seconds */
int start_delay; // seconds (-1 means disable static/random fencing delays)
int delay_id;
char *op;
char *origin;
char *client;
char *client_name;
char *remote_op_id;
char *target;
uint32_t target_nodeid;
char *action;
char *device;
GList *device_list;
GList *next_device_iter; // device_list entry for next device to execute
void *internal_user_data;
void (*done_cb) (int pid, const pcmk__action_result_t *result,
void *user_data);
guint timer_sigterm;
guint timer_sigkill;
/*! If the operation timed out, this is the last signal
* we sent to the process to get it to terminate */
int last_timeout_signo;
stonith_device_t *active_on;
stonith_device_t *activating_on;
} async_command_t;
static xmlNode *construct_async_reply(const async_command_t *cmd,
const pcmk__action_result_t *result);
static gboolean
is_action_required(const char *action, const stonith_device_t *device)
{
return (device != NULL) && device->automatic_unfencing
&& pcmk__str_eq(action, PCMK_ACTION_ON, pcmk__str_none);
}
static int
get_action_delay_max(const stonith_device_t *device, const char *action)
{
const char *value = NULL;
guint delay_max = 0U;
if (!pcmk__is_fencing_action(action)) {
return 0;
}
value = g_hash_table_lookup(device->params, PCMK_STONITH_DELAY_MAX);
if (value) {
pcmk_parse_interval_spec(value, &delay_max);
delay_max /= 1000;
}
return (int) delay_max;
}
static int
get_action_delay_base(const stonith_device_t *device, const char *action,
const char *target)
{
char *hash_value = NULL;
guint delay_base = 0U;
if (!pcmk__is_fencing_action(action)) {
return 0;
}
hash_value = g_hash_table_lookup(device->params, PCMK_STONITH_DELAY_BASE);
if (hash_value) {
char *value = pcmk__str_copy(hash_value);
char *valptr = value;
if (target != NULL) {
for (char *val = strtok(value, "; \t"); val != NULL; val = strtok(NULL, "; \t")) {
char *mapval = strchr(val, ':');
if (mapval == NULL || mapval[1] == 0) {
crm_err("pcmk_delay_base: empty value in mapping", val);
continue;
}
if (mapval != val && strncasecmp(target, val, (size_t)(mapval - val)) == 0) {
value = mapval + 1;
crm_debug("pcmk_delay_base mapped to %s for %s",
value, target);
break;
}
}
}
if (strchr(value, ':') == 0) {
pcmk_parse_interval_spec(value, &delay_base);
delay_base /= 1000;
}
free(valptr);
}
return (int) delay_base;
}
/*!
* \internal
* \brief Override STONITH timeout with pcmk_*_timeout if available
*
* \param[in] device STONITH device to use
* \param[in] action STONITH action name
* \param[in] default_timeout Timeout to use if device does not have
* a pcmk_*_timeout parameter for action
*
* \return Value of pcmk_(action)_timeout if available, otherwise default_timeout
* \note For consistency, it would be nice if reboot/off/on timeouts could be
* set the same way as start/stop/monitor timeouts, i.e. with an
* <operation> entry in the fencing resource configuration. However that
* is insufficient because fencing devices may be registered directly via
* the fencer's register_device() API instead of going through the CIB
* (e.g. stonith_admin uses it for its -R option, and the executor uses it
* to ensure a device is registered when a command is issued). As device
* properties, pcmk_*_timeout parameters can be grabbed by the fencer when
* the device is registered, whether by CIB change or API call.
*/
static int
get_action_timeout(const stonith_device_t *device, const char *action,
int default_timeout)
{
if (action && device && device->params) {
char buffer[64] = { 0, };
const char *value = NULL;
/* If "reboot" was requested but the device does not support it,
* we will remap to "off", so check timeout for "off" instead
*/
if (pcmk__str_eq(action, PCMK_ACTION_REBOOT, pcmk__str_none)
&& !pcmk_is_set(device->flags, st_device_supports_reboot)) {
crm_trace("%s doesn't support reboot, using timeout for off instead",
device->id);
action = PCMK_ACTION_OFF;
}
/* If the device config specified an action-specific timeout, use it */
snprintf(buffer, sizeof(buffer), "pcmk_%s_timeout", action);
value = g_hash_table_lookup(device->params, buffer);
if (value) {
long long timeout_ms = crm_get_msec(value);
return (int) QB_MIN(timeout_ms / 1000, INT_MAX);
}
}
return default_timeout;
}
/*!
* \internal
* \brief Get the currently executing device for a fencing operation
*
* \param[in] cmd Fencing operation to check
*
* \return Currently executing device for \p cmd if any, otherwise NULL
*/
static stonith_device_t *
cmd_device(const async_command_t *cmd)
{
if ((cmd == NULL) || (cmd->device == NULL) || (device_list == NULL)) {
return NULL;
}
return g_hash_table_lookup(device_list, cmd->device);
}
/*!
* \internal
* \brief Return the configured reboot action for a given device
*
* \param[in] device_id Device ID
*
* \return Configured reboot action for \p device_id
*/
const char *
fenced_device_reboot_action(const char *device_id)
{
const char *action = NULL;
if ((device_list != NULL) && (device_id != NULL)) {
stonith_device_t *device = g_hash_table_lookup(device_list, device_id);
if ((device != NULL) && (device->params != NULL)) {
action = g_hash_table_lookup(device->params, "pcmk_reboot_action");
}
}
return pcmk__s(action, PCMK_ACTION_REBOOT);
}
/*!
* \internal
* \brief Check whether a given device supports the "on" action
*
* \param[in] device_id Device ID
*
* \return true if \p device_id supports "on", otherwise false
*/
bool
fenced_device_supports_on(const char *device_id)
{
if ((device_list != NULL) && (device_id != NULL)) {
stonith_device_t *device = g_hash_table_lookup(device_list, device_id);
if (device != NULL) {
return pcmk_is_set(device->flags, st_device_supports_on);
}
}
return false;
}
static void
free_async_command(async_command_t * cmd)
{
if (!cmd) {
return;
}
if (cmd->delay_id) {
g_source_remove(cmd->delay_id);
}
cmd_list = g_list_remove(cmd_list, cmd);
g_list_free_full(cmd->device_list, free);
free(cmd->device);
free(cmd->action);
free(cmd->target);
free(cmd->remote_op_id);
free(cmd->client);
free(cmd->client_name);
free(cmd->origin);
free(cmd->op);
free(cmd);
}
/*!
* \internal
* \brief Create a new asynchronous fencing operation from request XML
*
* \param[in] msg Fencing request XML (from IPC or CPG)
*
* \return Newly allocated fencing operation on success, otherwise NULL
*
* \note This asserts on memory errors, so a NULL return indicates an
* unparseable message.
*/
static async_command_t *
create_async_command(xmlNode *msg)
{
xmlNode *op = NULL;
async_command_t *cmd = NULL;
if (msg == NULL) {
return NULL;
}
op = get_xpath_object("//@" PCMK__XE_ST_DEVICE_ACTION, msg, LOG_ERR);
if (op == NULL) {
return NULL;
}
cmd = pcmk__assert_alloc(1, sizeof(async_command_t));
// All messages must include these
cmd->action = crm_element_value_copy(op, PCMK__XA_ST_DEVICE_ACTION);
cmd->op = crm_element_value_copy(msg, PCMK__XA_ST_OP);
cmd->client = crm_element_value_copy(msg, PCMK__XA_ST_CLIENTID);
if ((cmd->action == NULL) || (cmd->op == NULL) || (cmd->client == NULL)) {
free_async_command(cmd);
return NULL;
}
crm_element_value_int(msg, PCMK__XA_ST_CALLID, &(cmd->id));
crm_element_value_int(msg, PCMK__XA_ST_CALLOPT, &(cmd->options));
crm_element_value_int(msg, PCMK__XA_ST_DELAY, &(cmd->start_delay));
crm_element_value_int(msg, PCMK__XA_ST_TIMEOUT, &(cmd->default_timeout));
cmd->timeout = cmd->default_timeout;
cmd->origin = crm_element_value_copy(msg, PCMK__XA_SRC);
cmd->remote_op_id = crm_element_value_copy(msg, PCMK__XA_ST_REMOTE_OP);
cmd->client_name = crm_element_value_copy(msg, PCMK__XA_ST_CLIENTNAME);
cmd->target = crm_element_value_copy(op, PCMK__XA_ST_TARGET);
cmd->device = crm_element_value_copy(op, PCMK__XA_ST_DEVICE_ID);
cmd->done_cb = st_child_done;
// Track in global command list
cmd_list = g_list_append(cmd_list, cmd);
return cmd;
}
static int
get_action_limit(stonith_device_t * device)
{
const char *value = NULL;
int action_limit = 1;
value = g_hash_table_lookup(device->params, PCMK_STONITH_ACTION_LIMIT);
if ((value == NULL)
|| (pcmk__scan_min_int(value, &action_limit, INT_MIN) != pcmk_rc_ok)
|| (action_limit == 0)) {
action_limit = 1;
}
return action_limit;
}
static int
get_active_cmds(stonith_device_t * device)
{
int counter = 0;
GList *gIter = NULL;
GList *gIterNext = NULL;
CRM_CHECK(device != NULL, return 0);
for (gIter = cmd_list; gIter != NULL; gIter = gIterNext) {
async_command_t *cmd = gIter->data;
gIterNext = gIter->next;
if (cmd->active_on == device) {
counter++;
}
}
return counter;
}
static void
fork_cb(int pid, void *user_data)
{
async_command_t *cmd = (async_command_t *) user_data;
stonith_device_t * device =
/* in case of a retry we've done the move from
activating_on to active_on already
*/
cmd->activating_on?cmd->activating_on:cmd->active_on;
CRM_ASSERT(device);
crm_debug("Operation '%s' [%d]%s%s using %s now running with %ds timeout",
cmd->action, pid,
((cmd->target == NULL)? "" : " targeting "),
pcmk__s(cmd->target, ""), device->id, cmd->timeout);
cmd->active_on = device;
cmd->activating_on = NULL;
}
static int
get_agent_metadata_cb(gpointer data) {
stonith_device_t *device = data;
guint period_ms;
switch (get_agent_metadata(device->agent, &device->agent_metadata)) {
case pcmk_rc_ok:
if (device->agent_metadata) {
read_action_metadata(device);
stonith__device_parameter_flags(&(device->flags), device->id,
device->agent_metadata);
}
return G_SOURCE_REMOVE;
case EAGAIN:
period_ms = pcmk__mainloop_timer_get_period(device->timer);
if (period_ms < 160 * 1000) {
mainloop_timer_set_period(device->timer, 2 * period_ms);
}
return G_SOURCE_CONTINUE;
default:
return G_SOURCE_REMOVE;
}
}
/*!
* \internal
* \brief Call a command's action callback for an internal (not library) result
*
* \param[in,out] cmd Command to report result for
* \param[in] execution_status Execution status to use for result
* \param[in] exit_status Exit status to use for result
* \param[in] exit_reason Exit reason to use for result
*/
static void
report_internal_result(async_command_t *cmd, int exit_status,
int execution_status, const char *exit_reason)
{
pcmk__action_result_t result = PCMK__UNKNOWN_RESULT;
pcmk__set_result(&result, exit_status, execution_status, exit_reason);
cmd->done_cb(0, &result, cmd);
pcmk__reset_result(&result);
}
static gboolean
stonith_device_execute(stonith_device_t * device)
{
int exec_rc = 0;
const char *action_str = NULL;
const char *host_arg = NULL;
async_command_t *cmd = NULL;
stonith_action_t *action = NULL;
int active_cmds = 0;
int action_limit = 0;
GList *gIter = NULL;
GList *gIterNext = NULL;
CRM_CHECK(device != NULL, return FALSE);
active_cmds = get_active_cmds(device);
action_limit = get_action_limit(device);
if (action_limit > -1 && active_cmds >= action_limit) {
crm_trace("%s is over its action limit of %d (%u active action%s)",
device->id, action_limit, active_cmds,
pcmk__plural_s(active_cmds));
return TRUE;
}
for (gIter = device->pending_ops; gIter != NULL; gIter = gIterNext) {
async_command_t *pending_op = gIter->data;
gIterNext = gIter->next;
if (pending_op && pending_op->delay_id) {
crm_trace("Operation '%s'%s%s using %s was asked to run too early, "
"waiting for start delay of %ds",
pending_op->action,
((pending_op->target == NULL)? "" : " targeting "),
pcmk__s(pending_op->target, ""),
device->id, pending_op->start_delay);
continue;
}
device->pending_ops = g_list_remove_link(device->pending_ops, gIter);
g_list_free_1(gIter);
cmd = pending_op;
break;
}
if (cmd == NULL) {
crm_trace("No actions using %s are needed", device->id);
return TRUE;
}
if (pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT,
STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) {
if (pcmk__is_fencing_action(cmd->action)) {
if (node_does_watchdog_fencing(stonith_our_uname)) {
pcmk__panic(__func__);
goto done;
}
} else {
crm_info("Faking success for %s watchdog operation", cmd->action);
report_internal_result(cmd, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
goto done;
}
}
#if SUPPORT_CIBSECRETS
exec_rc = pcmk__substitute_secrets(device->id, device->params);
if (exec_rc != pcmk_rc_ok) {
if (pcmk__str_eq(cmd->action, PCMK_ACTION_STOP, pcmk__str_none)) {
crm_info("Proceeding with stop operation for %s "
"despite being unable to load CIB secrets (%s)",
device->id, pcmk_rc_str(exec_rc));
} else {
crm_err("Considering %s unconfigured "
"because unable to load CIB secrets: %s",
device->id, pcmk_rc_str(exec_rc));
report_internal_result(cmd, CRM_EX_ERROR, PCMK_EXEC_NO_SECRETS,
"Failed to get CIB secrets");
goto done;
}
}
#endif
action_str = cmd->action;
if (pcmk__str_eq(cmd->action, PCMK_ACTION_REBOOT, pcmk__str_none)
&& !pcmk_is_set(device->flags, st_device_supports_reboot)) {
crm_notice("Remapping 'reboot' action%s%s using %s to 'off' "
"because agent '%s' does not support reboot",
((cmd->target == NULL)? "" : " targeting "),
pcmk__s(cmd->target, ""), device->id, device->agent);
action_str = PCMK_ACTION_OFF;
}
if (pcmk_is_set(device->flags, st_device_supports_parameter_port)) {
host_arg = "port";
} else if (pcmk_is_set(device->flags, st_device_supports_parameter_plug)) {
host_arg = "plug";
}
action = stonith__action_create(device->agent, action_str, cmd->target,
cmd->target_nodeid, cmd->timeout,
device->params, device->aliases, host_arg);
/* for async exec, exec_rc is negative for early error exit
otherwise handling of success/errors is done via callbacks */
cmd->activating_on = device;
exec_rc = stonith__execute_async(action, (void *)cmd, cmd->done_cb,
fork_cb);
if (exec_rc < 0) {
cmd->activating_on = NULL;
cmd->done_cb(0, stonith__action_result(action), cmd);
stonith__destroy_action(action);
}
done:
/* Device might get triggered to work by multiple fencing commands
* simultaneously. Trigger the device again to make sure any
* remaining concurrent commands get executed. */
if (device->pending_ops) {
mainloop_set_trigger(device->work);
}
return TRUE;
}
static gboolean
stonith_device_dispatch(gpointer user_data)
{
return stonith_device_execute(user_data);
}
static gboolean
start_delay_helper(gpointer data)
{
async_command_t *cmd = data;
stonith_device_t *device = cmd_device(cmd);
cmd->delay_id = 0;
if (device) {
mainloop_set_trigger(device->work);
}
return FALSE;
}
static void
schedule_stonith_command(async_command_t * cmd, stonith_device_t * device)
{
int delay_max = 0;
int delay_base = 0;
int requested_delay = cmd->start_delay;
CRM_CHECK(cmd != NULL, return);
CRM_CHECK(device != NULL, return);
if (cmd->device) {
free(cmd->device);
}
if (device->include_nodeid && (cmd->target != NULL)) {
crm_node_t *node = pcmk__get_node(0, cmd->target, NULL,
pcmk__node_search_cluster);
cmd->target_nodeid = node->id;
}
cmd->device = pcmk__str_copy(device->id);
cmd->timeout = get_action_timeout(device, cmd->action, cmd->default_timeout);
if (cmd->remote_op_id) {
crm_debug("Scheduling '%s' action%s%s using %s for remote peer %s "
"with op id %.8s and timeout %ds",
cmd->action,
(cmd->target == NULL)? "" : " targeting ",
pcmk__s(cmd->target, ""),
device->id, cmd->origin, cmd->remote_op_id, cmd->timeout);
} else {
crm_debug("Scheduling '%s' action%s%s using %s for %s with timeout %ds",
cmd->action,
(cmd->target == NULL)? "" : " targeting ",
pcmk__s(cmd->target, ""),
device->id, cmd->client, cmd->timeout);
}
device->pending_ops = g_list_append(device->pending_ops, cmd);
mainloop_set_trigger(device->work);
// Value -1 means disable any static/random fencing delays
if (requested_delay < 0) {
return;
}
delay_max = get_action_delay_max(device, cmd->action);
delay_base = get_action_delay_base(device, cmd->action, cmd->target);
if (delay_max == 0) {
delay_max = delay_base;
}
if (delay_max < delay_base) {
crm_warn(PCMK_STONITH_DELAY_BASE " (%ds) is larger than "
PCMK_STONITH_DELAY_MAX " (%ds) for %s using %s "
"(limiting to maximum delay)",
delay_base, delay_max, cmd->action, device->id);
delay_base = delay_max;
}
if (delay_max > 0) {
// coverity[dontcall] It doesn't matter here if rand() is predictable
cmd->start_delay +=
((delay_max != delay_base)?(rand() % (delay_max - delay_base)):0)
+ delay_base;
}
if (cmd->start_delay > 0) {
crm_notice("Delaying '%s' action%s%s using %s for %ds " CRM_XS
" timeout=%ds requested_delay=%ds base=%ds max=%ds",
cmd->action,
(cmd->target == NULL)? "" : " targeting ",
pcmk__s(cmd->target, ""),
device->id, cmd->start_delay, cmd->timeout,
requested_delay, delay_base, delay_max);
cmd->delay_id =
g_timeout_add_seconds(cmd->start_delay, start_delay_helper, cmd);
}
}
static void
free_device(gpointer data)
{
GList *gIter = NULL;
stonith_device_t *device = data;
g_hash_table_destroy(device->params);
g_hash_table_destroy(device->aliases);
for (gIter = device->pending_ops; gIter != NULL; gIter = gIter->next) {
async_command_t *cmd = gIter->data;
crm_warn("Removal of device '%s' purged operation '%s'", device->id, cmd->action);
report_internal_result(cmd, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE,
"Device was removed before action could be executed");
}
g_list_free(device->pending_ops);
g_list_free_full(device->targets, free);
if (device->timer) {
mainloop_timer_stop(device->timer);
mainloop_timer_del(device->timer);
}
mainloop_destroy_trigger(device->work);
free_xml(device->agent_metadata);
free(device->namespace);
if (device->on_target_actions != NULL) {
g_string_free(device->on_target_actions, TRUE);
}
free(device->agent);
free(device->id);
free(device);
}
void free_device_list(void)
{
if (device_list != NULL) {
g_hash_table_destroy(device_list);
device_list = NULL;
}
}
void
init_device_list(void)
{
if (device_list == NULL) {
device_list = pcmk__strkey_table(NULL, free_device);
}
}
static GHashTable *
build_port_aliases(const char *hostmap, GList ** targets)
{
char *name = NULL;
int last = 0, lpc = 0, max = 0, added = 0;
GHashTable *aliases = pcmk__strikey_table(free, free);
if (hostmap == NULL) {
return aliases;
}
max = strlen(hostmap);
for (; lpc <= max; lpc++) {
switch (hostmap[lpc]) {
/* Skip escaped chars */
case '\\':
lpc++;
break;
/* Assignment chars */
case '=':
case ':':
if (lpc > last) {
free(name);
name = pcmk__assert_alloc(1, 1 + lpc - last);
memcpy(name, hostmap + last, lpc - last);
}
last = lpc + 1;
break;
/* Delimeter chars */
/* case ',': Potentially used to specify multiple ports */
case 0:
case ';':
case ' ':
case '\t':
if (name) {
char *value = NULL;
int k = 0;
value = pcmk__assert_alloc(1, 1 + lpc - last);
memcpy(value, hostmap + last, lpc - last);
for (int i = 0; value[i] != '\0'; i++) {
if (value[i] != '\\') {
value[k++] = value[i];
}
}
value[k] = '\0';
crm_debug("Adding alias '%s'='%s'", name, value);
g_hash_table_replace(aliases, name, value);
if (targets) {
*targets = g_list_append(*targets, pcmk__str_copy(value));
}
value = NULL;
name = NULL;
added++;
} else if (lpc > last) {
crm_debug("Parse error at offset %d near '%s'", lpc - last, hostmap + last);
}
last = lpc + 1;
break;
}
if (hostmap[lpc] == 0) {
break;
}
}
if (added == 0) {
crm_info("No host mappings detected in '%s'", hostmap);
}
free(name);
return aliases;
}
GHashTable *metadata_cache = NULL;
void
free_metadata_cache(void) {
if (metadata_cache != NULL) {
g_hash_table_destroy(metadata_cache);
metadata_cache = NULL;
}
}
static void
init_metadata_cache(void) {
if (metadata_cache == NULL) {
metadata_cache = pcmk__strkey_table(free, free);
}
}
int
get_agent_metadata(const char *agent, xmlNode ** metadata)
{
char *buffer = NULL;
if (metadata == NULL) {
return EINVAL;
}
*metadata = NULL;
if (pcmk__str_eq(agent, STONITH_WATCHDOG_AGENT_INTERNAL, pcmk__str_none)) {
return pcmk_rc_ok;
}
init_metadata_cache();
buffer = g_hash_table_lookup(metadata_cache, agent);
if (buffer == NULL) {
stonith_t *st = stonith_api_new();
int rc;
if (st == NULL) {
crm_warn("Could not get agent meta-data: "
"API memory allocation failed");
return EAGAIN;
}
rc = st->cmds->metadata(st, st_opt_sync_call, agent,
NULL, &buffer, 10);
stonith_api_delete(st);
if (rc || !buffer) {
crm_err("Could not retrieve metadata for fencing agent %s", agent);
return EAGAIN;
}
g_hash_table_replace(metadata_cache, pcmk__str_copy(agent), buffer);
}
*metadata = pcmk__xml_parse(buffer);
return pcmk_rc_ok;
}
static gboolean
is_nodeid_required(xmlNode * xml)
{
xmlXPathObjectPtr xpath = NULL;
if (stand_alone) {
return FALSE;
}
if (!xml) {
return FALSE;
}
xpath = xpath_search(xml,
"//" PCMK_XE_PARAMETER "[@" PCMK_XA_NAME "='nodeid']");
if (numXpathResults(xpath) <= 0) {
freeXpathObject(xpath);
return FALSE;
}
freeXpathObject(xpath);
return TRUE;
}
static void
read_action_metadata(stonith_device_t *device)
{
xmlXPathObjectPtr xpath = NULL;
int max = 0;
int lpc = 0;
if (device->agent_metadata == NULL) {
return;
}
xpath = xpath_search(device->agent_metadata, "//action");
max = numXpathResults(xpath);
if (max <= 0) {
freeXpathObject(xpath);
return;
}
for (lpc = 0; lpc < max; lpc++) {
const char *action = NULL;
xmlNode *match = getXpathResult(xpath, lpc);
CRM_LOG_ASSERT(match != NULL);
if(match == NULL) { continue; };
action = crm_element_value(match, PCMK_XA_NAME);
if (pcmk__str_eq(action, PCMK_ACTION_LIST, pcmk__str_none)) {
stonith__set_device_flags(device->flags, device->id,
st_device_supports_list);
} else if (pcmk__str_eq(action, PCMK_ACTION_STATUS, pcmk__str_none)) {
stonith__set_device_flags(device->flags, device->id,
st_device_supports_status);
} else if (pcmk__str_eq(action, PCMK_ACTION_REBOOT, pcmk__str_none)) {
stonith__set_device_flags(device->flags, device->id,
st_device_supports_reboot);
} else if (pcmk__str_eq(action, PCMK_ACTION_ON, pcmk__str_none)) {
/* PCMK_XA_AUTOMATIC means the cluster will unfence a node when it
* joins.
*
* @COMPAT PCMK__XA_REQUIRED is a deprecated synonym for
* PCMK_XA_AUTOMATIC.
*/
if (pcmk__xe_attr_is_true(match, PCMK_XA_AUTOMATIC)
|| pcmk__xe_attr_is_true(match, PCMK__XA_REQUIRED)) {
device->automatic_unfencing = TRUE;
}
stonith__set_device_flags(device->flags, device->id,
st_device_supports_on);
}
if ((action != NULL)
&& pcmk__xe_attr_is_true(match, PCMK_XA_ON_TARGET)) {
pcmk__add_word(&(device->on_target_actions), 64, action);
}
}
freeXpathObject(xpath);
}
/*!
* \internal
* \brief Set a pcmk_*_action parameter if not already set
*
* \param[in,out] params Device parameters
* \param[in] action Name of action
* \param[in] value Value to use if action is not already set
*/
static void
map_action(GHashTable *params, const char *action, const char *value)
{
char *key = crm_strdup_printf("pcmk_%s_action", action);
if (g_hash_table_lookup(params, key)) {
crm_warn("Ignoring %s='%s', see %s instead",
STONITH_ATTR_ACTION_OP, value, key);
free(key);
} else {
crm_warn("Mapping %s='%s' to %s='%s'",
STONITH_ATTR_ACTION_OP, value, key, value);
g_hash_table_insert(params, key, pcmk__str_copy(value));
}
}
/*!
* \internal
* \brief Create device parameter table from XML
*
* \param[in] name Device name (used for logging only)
* \param[in] dev XML containing device parameters
*/
static GHashTable *
xml2device_params(const char *name, const xmlNode *dev)
{
GHashTable *params = xml2list(dev);
const char *value;
/* Action should never be specified in the device configuration,
* but we support it for users who are familiar with other software
* that worked that way.
*/
value = g_hash_table_lookup(params, STONITH_ATTR_ACTION_OP);
if (value != NULL) {
crm_warn("%s has '%s' parameter, which should never be specified in configuration",
name, STONITH_ATTR_ACTION_OP);
if (*value == '\0') {
crm_warn("Ignoring empty '%s' parameter", STONITH_ATTR_ACTION_OP);
} else if (strcmp(value, PCMK_ACTION_REBOOT) == 0) {
crm_warn("Ignoring %s='reboot' (see " PCMK_OPT_STONITH_ACTION
" cluster property instead)",
STONITH_ATTR_ACTION_OP);
} else if (strcmp(value, PCMK_ACTION_OFF) == 0) {
map_action(params, PCMK_ACTION_REBOOT, value);
} else {
map_action(params, PCMK_ACTION_OFF, value);
map_action(params, PCMK_ACTION_REBOOT, value);
}
g_hash_table_remove(params, STONITH_ATTR_ACTION_OP);
}
return params;
}
static const char *
target_list_type(stonith_device_t * dev)
{
const char *check_type = NULL;
check_type = g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_CHECK);
if (check_type == NULL) {
if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_LIST)) {
check_type = PCMK_VALUE_STATIC_LIST;
} else if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_MAP)) {
check_type = PCMK_VALUE_STATIC_LIST;
} else if (pcmk_is_set(dev->flags, st_device_supports_list)) {
check_type = PCMK_VALUE_DYNAMIC_LIST;
} else if (pcmk_is_set(dev->flags, st_device_supports_status)) {
check_type = PCMK_VALUE_STATUS;
} else {
check_type = PCMK_VALUE_NONE;
}
}
return check_type;
}
static stonith_device_t *
build_device_from_xml(xmlNode *dev)
{
const char *value;
stonith_device_t *device = NULL;
char *agent = crm_element_value_copy(dev, PCMK_XA_AGENT);
CRM_CHECK(agent != NULL, return device);
device = pcmk__assert_alloc(1, sizeof(stonith_device_t));
device->id = crm_element_value_copy(dev, PCMK_XA_ID);
device->agent = agent;
device->namespace = crm_element_value_copy(dev, PCMK__XA_NAMESPACE);
device->params = xml2device_params(device->id, dev);
value = g_hash_table_lookup(device->params, PCMK_STONITH_HOST_LIST);
if (value) {
device->targets = stonith__parse_targets(value);
}
value = g_hash_table_lookup(device->params, PCMK_STONITH_HOST_MAP);
device->aliases = build_port_aliases(value, &(device->targets));
value = target_list_type(device);
if (!pcmk__str_eq(value, PCMK_VALUE_STATIC_LIST, pcmk__str_casei)
&& (device->targets != NULL)) {
// device->targets is necessary only with PCMK_VALUE_STATIC_LIST
g_list_free_full(device->targets, free);
device->targets = NULL;
}
switch (get_agent_metadata(device->agent, &device->agent_metadata)) {
case pcmk_rc_ok:
if (device->agent_metadata) {
read_action_metadata(device);
stonith__device_parameter_flags(&(device->flags), device->id,
device->agent_metadata);
}
break;
case EAGAIN:
if (device->timer == NULL) {
device->timer = mainloop_timer_add("get_agent_metadata", 10 * 1000,
TRUE, get_agent_metadata_cb, device);
}
if (!mainloop_timer_running(device->timer)) {
mainloop_timer_start(device->timer);
}
break;
default:
break;
}
value = g_hash_table_lookup(device->params, "nodeid");
if (!value) {
device->include_nodeid = is_nodeid_required(device->agent_metadata);
}
value = crm_element_value(dev, PCMK__XA_RSC_PROVIDES);
if (pcmk__str_eq(value, PCMK_VALUE_UNFENCING, pcmk__str_casei)) {
device->automatic_unfencing = TRUE;
}
if (is_action_required(PCMK_ACTION_ON, device)) {
crm_info("Fencing device '%s' requires unfencing", device->id);
}
if (device->on_target_actions != NULL) {
crm_info("Fencing device '%s' requires actions (%s) to be executed "
"on target", device->id,
(const char *) device->on_target_actions->str);
}
device->work = mainloop_add_trigger(G_PRIORITY_HIGH, stonith_device_dispatch, device);
/* TODO: Hook up priority */
return device;
}
static void
schedule_internal_command(const char *origin,
stonith_device_t * device,
const char *action,
const char *target,
int timeout,
void *internal_user_data,
void (*done_cb) (int pid,
const pcmk__action_result_t *result,
void *user_data))
{
async_command_t *cmd = NULL;
cmd = pcmk__assert_alloc(1, sizeof(async_command_t));
cmd->id = -1;
cmd->default_timeout = timeout ? timeout : 60;
cmd->timeout = cmd->default_timeout;
cmd->action = pcmk__str_copy(action);
cmd->target = pcmk__str_copy(target);
cmd->device = pcmk__str_copy(device->id);
cmd->origin = pcmk__str_copy(origin);
cmd->client = pcmk__str_copy(crm_system_name);
cmd->client_name = pcmk__str_copy(crm_system_name);
cmd->internal_user_data = internal_user_data;
cmd->done_cb = done_cb; /* cmd, not internal_user_data, is passed to 'done_cb' as the userdata */
schedule_stonith_command(cmd, device);
}
// Fence agent status commands use custom exit status codes
enum fence_status_code {
fence_status_invalid = -1,
fence_status_active = 0,
fence_status_unknown = 1,
fence_status_inactive = 2,
};
static void
status_search_cb(int pid, const pcmk__action_result_t *result, void *user_data)
{
async_command_t *cmd = user_data;
struct device_search_s *search = cmd->internal_user_data;
stonith_device_t *dev = cmd_device(cmd);
gboolean can = FALSE;
free_async_command(cmd);
if (!dev) {
search_devices_record_result(search, NULL, FALSE);
return;
}
mainloop_set_trigger(dev->work);
if (result->execution_status != PCMK_EXEC_DONE) {
crm_warn("Assuming %s cannot fence %s "
"because status could not be executed: %s%s%s%s",
dev->id, search->host,
pcmk_exec_status_str(result->execution_status),
((result->exit_reason == NULL)? "" : " ("),
((result->exit_reason == NULL)? "" : result->exit_reason),
((result->exit_reason == NULL)? "" : ")"));
search_devices_record_result(search, dev->id, FALSE);
return;
}
switch (result->exit_status) {
case fence_status_unknown:
crm_trace("%s reported it cannot fence %s", dev->id, search->host);
break;
case fence_status_active:
case fence_status_inactive:
crm_trace("%s reported it can fence %s", dev->id, search->host);
can = TRUE;
break;
default:
crm_warn("Assuming %s cannot fence %s "
"(status returned unknown code %d)",
dev->id, search->host, result->exit_status);
break;
}
search_devices_record_result(search, dev->id, can);
}
static void
dynamic_list_search_cb(int pid, const pcmk__action_result_t *result,
void *user_data)
{
async_command_t *cmd = user_data;
struct device_search_s *search = cmd->internal_user_data;
stonith_device_t *dev = cmd_device(cmd);
gboolean can_fence = FALSE;
free_async_command(cmd);
/* Host/alias must be in the list output to be eligible to be fenced
*
* Will cause problems if down'd nodes aren't listed or (for virtual nodes)
* if the guest is still listed despite being moved to another machine
*/
if (!dev) {
search_devices_record_result(search, NULL, FALSE);
return;
}
mainloop_set_trigger(dev->work);
if (pcmk__result_ok(result)) {
crm_info("Refreshing target list for %s", dev->id);
g_list_free_full(dev->targets, free);
dev->targets = stonith__parse_targets(result->action_stdout);
dev->targets_age = time(NULL);
} else if (dev->targets != NULL) {
if (result->execution_status == PCMK_EXEC_DONE) {
crm_info("Reusing most recent target list for %s "
"because list returned error code %d",
dev->id, result->exit_status);
} else {
crm_info("Reusing most recent target list for %s "
"because list could not be executed: %s%s%s%s",
dev->id, pcmk_exec_status_str(result->execution_status),
((result->exit_reason == NULL)? "" : " ("),
((result->exit_reason == NULL)? "" : result->exit_reason),
((result->exit_reason == NULL)? "" : ")"));
}
} else { // We have never successfully executed list
if (result->execution_status == PCMK_EXEC_DONE) {
crm_warn("Assuming %s cannot fence %s "
"because list returned error code %d",
dev->id, search->host, result->exit_status);
} else {
crm_warn("Assuming %s cannot fence %s "
"because list could not be executed: %s%s%s%s",
dev->id, search->host,
pcmk_exec_status_str(result->execution_status),
((result->exit_reason == NULL)? "" : " ("),
((result->exit_reason == NULL)? "" : result->exit_reason),
((result->exit_reason == NULL)? "" : ")"));
}
/* Fall back to pcmk_host_check=PCMK_VALUE_STATUS if the user didn't
* explicitly specify PCMK_VALUE_DYNAMIC_LIST
*/
if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_CHECK) == NULL) {
crm_notice("Switching to pcmk_host_check='status' for %s", dev->id);
pcmk__insert_dup(dev->params, PCMK_STONITH_HOST_CHECK,
PCMK_VALUE_STATUS);
}
}
if (dev->targets) {
const char *alias = g_hash_table_lookup(dev->aliases, search->host);
if (!alias) {
alias = search->host;
}
if (pcmk__str_in_list(alias, dev->targets, pcmk__str_casei)) {
can_fence = TRUE;
}
}
search_devices_record_result(search, dev->id, can_fence);
}
/*!
* \internal
* \brief Returns true if any key in first is not in second or second has a different value for key
*/
static int
device_params_diff(GHashTable *first, GHashTable *second) {
char *key = NULL;
char *value = NULL;
GHashTableIter gIter;
g_hash_table_iter_init(&gIter, first);
while (g_hash_table_iter_next(&gIter, (void **)&key, (void **)&value)) {
if(strstr(key, "CRM_meta") == key) {
continue;
} else if (strcmp(key, PCMK_XA_CRM_FEATURE_SET) == 0) {
continue;
} else {
char *other_value = g_hash_table_lookup(second, key);
if (!other_value || !pcmk__str_eq(other_value, value, pcmk__str_casei)) {
crm_trace("Different value for %s: %s != %s", key, other_value, value);
return 1;
}
}
}
return 0;
}
/*!
* \internal
* \brief Checks to see if an identical device already exists in the device_list
*/
static stonith_device_t *
device_has_duplicate(const stonith_device_t *device)
{
stonith_device_t *dup = g_hash_table_lookup(device_list, device->id);
if (!dup) {
crm_trace("No match for %s", device->id);
return NULL;
} else if (!pcmk__str_eq(dup->agent, device->agent, pcmk__str_casei)) {
crm_trace("Different agent: %s != %s", dup->agent, device->agent);
return NULL;
}
/* Use calculate_operation_digest() here? */
if (device_params_diff(device->params, dup->params) ||
device_params_diff(dup->params, device->params)) {
return NULL;
}
crm_trace("Match");
return dup;
}
int
stonith_device_register(xmlNode *dev, gboolean from_cib)
{
stonith_device_t *dup = NULL;
stonith_device_t *device = build_device_from_xml(dev);
guint ndevices = 0;
int rv = pcmk_ok;
CRM_CHECK(device != NULL, return -ENOMEM);
/* do we have a watchdog-device? */
if (pcmk__str_eq(device->id, STONITH_WATCHDOG_ID, pcmk__str_none) ||
pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT,
STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) do {
if (stonith_watchdog_timeout_ms <= 0) {
crm_err("Ignoring watchdog fence device without "
PCMK_OPT_STONITH_WATCHDOG_TIMEOUT " set.");
rv = -ENODEV;
/* fall through to cleanup & return */
} else if (!pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT,
STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) {
crm_err("Ignoring watchdog fence device with unknown "
"agent '%s' unequal '" STONITH_WATCHDOG_AGENT "'.",
device->agent?device->agent:"");
rv = -ENODEV;
/* fall through to cleanup & return */
} else if (!pcmk__str_eq(device->id, STONITH_WATCHDOG_ID,
pcmk__str_none)) {
crm_err("Ignoring watchdog fence device "
"named %s !='"STONITH_WATCHDOG_ID"'.",
device->id?device->id:"");
rv = -ENODEV;
/* fall through to cleanup & return */
} else {
if (pcmk__str_eq(device->agent, STONITH_WATCHDOG_AGENT,
pcmk__str_none)) {
/* this either has an empty list or the targets
configured for watchdog-fencing
*/
g_list_free_full(stonith_watchdog_targets, free);
stonith_watchdog_targets = device->targets;
device->targets = NULL;
}
if (node_does_watchdog_fencing(stonith_our_uname)) {
g_list_free_full(device->targets, free);
device->targets = stonith__parse_targets(stonith_our_uname);
pcmk__insert_dup(device->params,
PCMK_STONITH_HOST_LIST, stonith_our_uname);
/* proceed as with any other stonith-device */
break;
}
crm_debug("Skip registration of watchdog fence device on node not in host-list.");
/* cleanup and fall through to more cleanup and return */
device->targets = NULL;
stonith_device_remove(device->id, from_cib);
}
free_device(device);
return rv;
} while (0);
dup = device_has_duplicate(device);
if (dup) {
ndevices = g_hash_table_size(device_list);
crm_debug("Device '%s' already in device list (%d active device%s)",
device->id, ndevices, pcmk__plural_s(ndevices));
free_device(device);
device = dup;
dup = g_hash_table_lookup(device_list, device->id);
dup->dirty = FALSE;
} else {
stonith_device_t *old = g_hash_table_lookup(device_list, device->id);
if (from_cib && old && old->api_registered) {
/* If the cib is writing over an entry that is shared with a stonith client,
* copy any pending ops that currently exist on the old entry to the new one.
* Otherwise the pending ops will be reported as failures
*/
crm_info("Overwriting existing entry for %s from CIB", device->id);
device->pending_ops = old->pending_ops;
device->api_registered = TRUE;
old->pending_ops = NULL;
if (device->pending_ops) {
mainloop_set_trigger(device->work);
}
}
g_hash_table_replace(device_list, device->id, device);
ndevices = g_hash_table_size(device_list);
crm_notice("Added '%s' to device list (%d active device%s)",
device->id, ndevices, pcmk__plural_s(ndevices));
}
if (from_cib) {
device->cib_registered = TRUE;
} else {
device->api_registered = TRUE;
}
return pcmk_ok;
}
void
stonith_device_remove(const char *id, bool from_cib)
{
stonith_device_t *device = g_hash_table_lookup(device_list, id);
guint ndevices = 0;
if (!device) {
ndevices = g_hash_table_size(device_list);
crm_info("Device '%s' not found (%d active device%s)",
id, ndevices, pcmk__plural_s(ndevices));
return;
}
if (from_cib) {
device->cib_registered = FALSE;
} else {
device->verified = FALSE;
device->api_registered = FALSE;
}
if (!device->cib_registered && !device->api_registered) {
g_hash_table_remove(device_list, id);
ndevices = g_hash_table_size(device_list);
crm_info("Removed '%s' from device list (%d active device%s)",
id, ndevices, pcmk__plural_s(ndevices));
} else {
crm_trace("Not removing '%s' from device list (%d active) because "
"still registered via:%s%s",
id, g_hash_table_size(device_list),
(device->cib_registered? " cib" : ""),
(device->api_registered? " api" : ""));
}
}
/*!
* \internal
* \brief Return the number of stonith levels registered for a node
*
* \param[in] tp Node's topology table entry
*
* \return Number of non-NULL levels in topology entry
* \note This function is used only for log messages.
*/
static int
count_active_levels(const stonith_topology_t *tp)
{
int lpc = 0;
int count = 0;
for (lpc = 0; lpc < ST_LEVEL_MAX; lpc++) {
if (tp->levels[lpc] != NULL) {
count++;
}
}
return count;
}
static void
free_topology_entry(gpointer data)
{
stonith_topology_t *tp = data;
int lpc = 0;
for (lpc = 0; lpc < ST_LEVEL_MAX; lpc++) {
if (tp->levels[lpc] != NULL) {
g_list_free_full(tp->levels[lpc], free);
}
}
free(tp->target);
free(tp->target_value);
free(tp->target_pattern);
free(tp->target_attribute);
free(tp);
}
void
free_topology_list(void)
{
if (topology != NULL) {
g_hash_table_destroy(topology);
topology = NULL;
}
}
void
init_topology_list(void)
{
if (topology == NULL) {
topology = pcmk__strkey_table(NULL, free_topology_entry);
}
}
char *
stonith_level_key(const xmlNode *level, enum fenced_target_by mode)
{
if (mode == fenced_target_by_unknown) {
mode = unpack_level_kind(level);
}
switch (mode) {
case fenced_target_by_name:
return crm_element_value_copy(level, PCMK_XA_TARGET);
case fenced_target_by_pattern:
return crm_element_value_copy(level, PCMK_XA_TARGET_PATTERN);
case fenced_target_by_attribute:
return crm_strdup_printf("%s=%s",
crm_element_value(level, PCMK_XA_TARGET_ATTRIBUTE),
crm_element_value(level, PCMK_XA_TARGET_VALUE));
default:
return crm_strdup_printf("unknown-%s", pcmk__xe_id(level));
}
}
/*!
* \internal
* \brief Parse target identification from topology level XML
*
* \param[in] level Topology level XML to parse
*
* \return How to identify target of \p level
*/
static enum fenced_target_by
unpack_level_kind(const xmlNode *level)
{
if (crm_element_value(level, PCMK_XA_TARGET) != NULL) {
return fenced_target_by_name;
}
if (crm_element_value(level, PCMK_XA_TARGET_PATTERN) != NULL) {
return fenced_target_by_pattern;
}
if (!stand_alone /* if standalone, there's no attribute manager */
&& (crm_element_value(level, PCMK_XA_TARGET_ATTRIBUTE) != NULL)
&& (crm_element_value(level, PCMK_XA_TARGET_VALUE) != NULL)) {
return fenced_target_by_attribute;
}
return fenced_target_by_unknown;
}
static stonith_key_value_t *
parse_device_list(const char *devices)
{
int lpc = 0;
int max = 0;
int last = 0;
stonith_key_value_t *output = NULL;
if (devices == NULL) {
return output;
}
max = strlen(devices);
for (lpc = 0; lpc <= max; lpc++) {
if (devices[lpc] == ',' || devices[lpc] == 0) {
char *line = strndup(devices + last, lpc - last);
output = stonith_key_value_add(output, NULL, line);
free(line);
last = lpc + 1;
}
}
return output;
}
/*!
* \internal
* \brief Unpack essential information from topology request XML
*
* \param[in] xml Request XML to search
* \param[out] mode If not NULL, where to store level kind
* \param[out] target If not NULL, where to store representation of target
* \param[out] id If not NULL, where to store level number
* \param[out] desc If not NULL, where to store log-friendly level description
*
* \return Topology level XML from within \p xml, or NULL if not found
* \note The caller is responsible for freeing \p *target and \p *desc if set.
*/
static xmlNode *
unpack_level_request(xmlNode *xml, enum fenced_target_by *mode, char **target,
int *id, char **desc)
{
enum fenced_target_by local_mode = fenced_target_by_unknown;
char *local_target = NULL;
int local_id = 0;
/* The level element can be the top element or lower. If top level, don't
* search by xpath, because it might give multiple hits if the XML is the
* CIB.
*/
if ((xml != NULL) && !pcmk__xe_is(xml, PCMK_XE_FENCING_LEVEL)) {
xml = get_xpath_object("//" PCMK_XE_FENCING_LEVEL, xml, LOG_WARNING);
}
if (xml == NULL) {
if (desc != NULL) {
*desc = crm_strdup_printf("missing");
}
} else {
local_mode = unpack_level_kind(xml);
local_target = stonith_level_key(xml, local_mode);
crm_element_value_int(xml, PCMK_XA_INDEX, &local_id);
if (desc != NULL) {
*desc = crm_strdup_printf("%s[%d]", local_target, local_id);
}
}
if (mode != NULL) {
*mode = local_mode;
}
if (id != NULL) {
*id = local_id;
}
if (target != NULL) {
*target = local_target;
} else {
free(local_target);
}
return xml;
}
/*!
* \internal
* \brief Register a fencing topology level for a target
*
* Given an XML request specifying the target name, level index, and device IDs
* for the level, this will create an entry for the target in the global topology
* table if one does not already exist, then append the specified device IDs to
* the entry's device list for the specified level.
*
* \param[in] msg XML request for STONITH level registration
* \param[out] desc If not NULL, set to string representation "TARGET[LEVEL]"
* \param[out] result Where to set result of registration
*/
void
fenced_register_level(xmlNode *msg, char **desc, pcmk__action_result_t *result)
{
int id = 0;
xmlNode *level;
enum fenced_target_by mode;
char *target;
stonith_topology_t *tp;
stonith_key_value_t *dIter = NULL;
stonith_key_value_t *devices = NULL;
CRM_CHECK((msg != NULL) && (result != NULL), return);
level = unpack_level_request(msg, &mode, &target, &id, desc);
if (level == NULL) {
fenced_set_protocol_error(result);
return;
}
// Ensure an ID was given (even the client API adds an ID)
if (pcmk__str_empty(pcmk__xe_id(level))) {
crm_warn("Ignoring registration for topology level without ID");
free(target);
crm_log_xml_trace(level, "Bad level");
pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID,
"Topology level is invalid without ID");
return;
}
// Ensure a valid target was specified
if (mode == fenced_target_by_unknown) {
crm_warn("Ignoring registration for topology level '%s' "
"without valid target", pcmk__xe_id(level));
free(target);
crm_log_xml_trace(level, "Bad level");
pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID,
"Invalid target for topology level '%s'",
pcmk__xe_id(level));
return;
}
// Ensure level ID is in allowed range
if ((id <= 0) || (id >= ST_LEVEL_MAX)) {
crm_warn("Ignoring topology registration for %s with invalid level %d",
target, id);
free(target);
crm_log_xml_trace(level, "Bad level");
pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID,
"Invalid level number '%s' for topology level '%s'",
pcmk__s(crm_element_value(level, PCMK_XA_INDEX),
""),
pcmk__xe_id(level));
return;
}
/* Find or create topology table entry */
tp = g_hash_table_lookup(topology, target);
if (tp == NULL) {
tp = pcmk__assert_alloc(1, sizeof(stonith_topology_t));
tp->kind = mode;
tp->target = target;
tp->target_value = crm_element_value_copy(level, PCMK_XA_TARGET_VALUE);
tp->target_pattern = crm_element_value_copy(level,
PCMK_XA_TARGET_PATTERN);
tp->target_attribute = crm_element_value_copy(level,
PCMK_XA_TARGET_ATTRIBUTE);
g_hash_table_replace(topology, tp->target, tp);
crm_trace("Added %s (%d) to the topology (%d active entries)",
target, (int) mode, g_hash_table_size(topology));
} else {
free(target);
}
if (tp->levels[id] != NULL) {
crm_info("Adding to the existing %s[%d] topology entry",
tp->target, id);
}
devices = parse_device_list(crm_element_value(level, PCMK_XA_DEVICES));
for (dIter = devices; dIter; dIter = dIter->next) {
const char *device = dIter->value;
crm_trace("Adding device '%s' for %s[%d]", device, tp->target, id);
tp->levels[id] = g_list_append(tp->levels[id], pcmk__str_copy(device));
}
stonith_key_value_freeall(devices, 1, 1);
{
int nlevels = count_active_levels(tp);
crm_info("Target %s has %d active fencing level%s",
tp->target, nlevels, pcmk__plural_s(nlevels));
}
pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
}
/*!
* \internal
* \brief Unregister a fencing topology level for a target
*
* Given an XML request specifying the target name and level index (or 0 for all
* levels), this will remove any corresponding entry for the target from the
* global topology table.
*
* \param[in] msg XML request for STONITH level registration
* \param[out] desc If not NULL, set to string representation "TARGET[LEVEL]"
* \param[out] result Where to set result of unregistration
*/
void
fenced_unregister_level(xmlNode *msg, char **desc,
pcmk__action_result_t *result)
{
int id = -1;
stonith_topology_t *tp;
char *target;
xmlNode *level = NULL;
CRM_CHECK(result != NULL, return);
level = unpack_level_request(msg, NULL, &target, &id, desc);
if (level == NULL) {
fenced_set_protocol_error(result);
return;
}
// Ensure level ID is in allowed range
if ((id < 0) || (id >= ST_LEVEL_MAX)) {
crm_warn("Ignoring topology unregistration for %s with invalid level %d",
target, id);
free(target);
crm_log_xml_trace(level, "Bad level");
pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID,
"Invalid level number '%s' for topology level %s",
pcmk__s(crm_element_value(level, PCMK_XA_INDEX),
"<null>"),
// Client API doesn't add ID to unregistration XML
pcmk__s(pcmk__xe_id(level), ""));
return;
}
tp = g_hash_table_lookup(topology, target);
if (tp == NULL) {
guint nentries = g_hash_table_size(topology);
crm_info("No fencing topology found for %s (%d active %s)",
target, nentries,
pcmk__plural_alt(nentries, "entry", "entries"));
} else if (id == 0 && g_hash_table_remove(topology, target)) {
guint nentries = g_hash_table_size(topology);
crm_info("Removed all fencing topology entries related to %s "
"(%d active %s remaining)", target, nentries,
pcmk__plural_alt(nentries, "entry", "entries"));
} else if (tp->levels[id] != NULL) {
guint nlevels;
g_list_free_full(tp->levels[id], free);
tp->levels[id] = NULL;
nlevels = count_active_levels(tp);
crm_info("Removed level %d from fencing topology for %s "
"(%d active level%s remaining)",
id, target, nlevels, pcmk__plural_s(nlevels));
}
free(target);
pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
}
static char *
list_to_string(GList *list, const char *delim, gboolean terminate_with_delim)
{
int max = g_list_length(list);
size_t delim_len = delim?strlen(delim):0;
size_t alloc_size = 1 + (max?((max-1+(terminate_with_delim?1:0))*delim_len):0);
char *rv;
GList *gIter;
char *pos = NULL;
const char *lead_delim = "";
for (gIter = list; gIter != NULL; gIter = gIter->next) {
const char *value = (const char *) gIter->data;
alloc_size += strlen(value);
}
rv = pcmk__assert_alloc(alloc_size, sizeof(char));
pos = rv;
for (gIter = list; gIter != NULL; gIter = gIter->next) {
const char *value = (const char *) gIter->data;
pos = &pos[sprintf(pos, "%s%s", lead_delim, value)];
lead_delim = delim;
}
if (max && terminate_with_delim) {
sprintf(pos, "%s", delim);
}
return rv;
}
/*!
* \internal
* \brief Execute a fence agent action directly (and asynchronously)
*
* Handle a STONITH_OP_EXEC API message by scheduling a requested agent action
* directly on a specified device. Only list, monitor, and status actions are
* expected to use this call, though it should work with any agent command.
*
* \param[in] msg Request XML specifying action
* \param[out] result Where to store result of action
*
* \note If the action is monitor, the device must be registered via the API
* (CIB registration is not sufficient), because monitor should not be
* possible unless the device is "started" (API registered).
*/
static void
execute_agent_action(xmlNode *msg, pcmk__action_result_t *result)
{
xmlNode *dev = get_xpath_object("//" PCMK__XE_ST_DEVICE_ID, msg, LOG_ERR);
xmlNode *op = get_xpath_object("//@" PCMK__XE_ST_DEVICE_ACTION, msg,
LOG_ERR);
const char *id = crm_element_value(dev, PCMK__XA_ST_DEVICE_ID);
const char *action = crm_element_value(op, PCMK__XA_ST_DEVICE_ACTION);
async_command_t *cmd = NULL;
stonith_device_t *device = NULL;
if ((id == NULL) || (action == NULL)) {
crm_info("Malformed API action request: device %s, action %s",
(id? id : "not specified"),
(action? action : "not specified"));
fenced_set_protocol_error(result);
return;
}
if (pcmk__str_eq(id, STONITH_WATCHDOG_ID, pcmk__str_none)) {
// Watchdog agent actions are implemented internally
if (stonith_watchdog_timeout_ms <= 0) {
pcmk__set_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE,
"Watchdog fence device not configured");
return;
} else if (pcmk__str_eq(action, PCMK_ACTION_LIST, pcmk__str_none)) {
pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
pcmk__set_result_output(result,
list_to_string(stonith_watchdog_targets,
"\n", TRUE),
NULL);
return;
} else if (pcmk__str_eq(action, PCMK_ACTION_MONITOR, pcmk__str_none)) {
pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
return;
}
}
device = g_hash_table_lookup(device_list, id);
if (device == NULL) {
crm_info("Ignoring API '%s' action request because device %s not found",
action, id);
pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE,
"'%s' not found", id);
return;
} else if (!device->api_registered
&& (strcmp(action, PCMK_ACTION_MONITOR) == 0)) {
// Monitors may run only on "started" (API-registered) devices
crm_info("Ignoring API '%s' action request because device %s not active",
action, id);
pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE,
"'%s' not active", id);
return;
}
cmd = create_async_command(msg);
if (cmd == NULL) {
crm_log_xml_warn(msg, "invalid");
fenced_set_protocol_error(result);
return;
}
schedule_stonith_command(cmd, device);
pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL);
}
static void
search_devices_record_result(struct device_search_s *search, const char *device, gboolean can_fence)
{
search->replies_received++;
if (can_fence && device) {
if (search->support_action_only != st_device_supports_none) {
stonith_device_t *dev = g_hash_table_lookup(device_list, device);
if (dev && !pcmk_is_set(dev->flags, search->support_action_only)) {
return;
}
}
search->capable = g_list_append(search->capable,
pcmk__str_copy(device));
}
if (search->replies_needed == search->replies_received) {
guint ndevices = g_list_length(search->capable);
crm_debug("Search found %d device%s that can perform '%s' targeting %s",
ndevices, pcmk__plural_s(ndevices),
(search->action? search->action : "unknown action"),
(search->host? search->host : "any node"));
search->callback(search->capable, search->user_data);
free(search->host);
free(search->action);
free(search);
}
}
/*!
* \internal
* \brief Check whether the local host is allowed to execute a fencing action
*
* \param[in] device Fence device to check
* \param[in] action Fence action to check
* \param[in] target Hostname of fence target
* \param[in] allow_suicide Whether self-fencing is allowed for this operation
*
* \return TRUE if local host is allowed to execute action, FALSE otherwise
*/
static gboolean
localhost_is_eligible(const stonith_device_t *device, const char *action,
const char *target, gboolean allow_suicide)
{
gboolean localhost_is_target = pcmk__str_eq(target, stonith_our_uname,
pcmk__str_casei);
if ((device != NULL) && (action != NULL)
&& (device->on_target_actions != NULL)
&& (strstr((const char*) device->on_target_actions->str,
action) != NULL)) {
if (!localhost_is_target) {
crm_trace("Operation '%s' using %s can only be executed for local "
"host, not %s", action, device->id, target);
return FALSE;
}
} else if (localhost_is_target && !allow_suicide) {
crm_trace("'%s' operation does not support self-fencing", action);
return FALSE;
}
return TRUE;
}
/*!
* \internal
* \brief Check if local node is allowed to execute (possibly remapped) action
*
* \param[in] device Fence device to check
* \param[in] action Fence action to check
* \param[in] target Node name of fence target
* \param[in] allow_self Whether self-fencing is allowed for this operation
*
* \return true if local node is allowed to execute \p action or any actions it
* might be remapped to, otherwise false
*/
static bool
localhost_is_eligible_with_remap(const stonith_device_t *device,
const char *action, const char *target,
gboolean allow_self)
{
// Check exact action
if (localhost_is_eligible(device, action, target, allow_self)) {
return true;
}
// Check potential remaps
if (pcmk__str_eq(action, PCMK_ACTION_REBOOT, pcmk__str_none)) {
/* "reboot" might get remapped to "off" then "on", so even if reboot is
* disallowed, return true if either of those is allowed. We'll report
* the disallowed actions with the results. We never allow self-fencing
* for remapped "on" actions because the target is off at that point.
*/
if (localhost_is_eligible(device, PCMK_ACTION_OFF, target, allow_self)
|| localhost_is_eligible(device, PCMK_ACTION_ON, target, FALSE)) {
return true;
}
}
return false;
}
static void
can_fence_host_with_device(stonith_device_t *dev,
struct device_search_s *search)
{
gboolean can = FALSE;
const char *check_type = "Internal bug";
const char *target = NULL;
const char *alias = NULL;
const char *dev_id = "Unspecified device";
const char *action = (search == NULL)? NULL : search->action;
CRM_CHECK((dev != NULL) && (action != NULL), goto search_report_results);
if (dev->id != NULL) {
dev_id = dev->id;
}
target = search->host;
if (target == NULL) {
can = TRUE;
check_type = "No target";
goto search_report_results;
}
/* Answer immediately if the device does not support the action
* or the local node is not allowed to perform it
*/
if (pcmk__str_eq(action, PCMK_ACTION_ON, pcmk__str_none)
&& !pcmk_is_set(dev->flags, st_device_supports_on)) {
check_type = "Agent does not support 'on'";
goto search_report_results;
} else if (!localhost_is_eligible_with_remap(dev, action, target,
search->allow_suicide)) {
check_type = "This node is not allowed to execute action";
goto search_report_results;
}
// Check eligibility as specified by pcmk_host_check
check_type = target_list_type(dev);
alias = g_hash_table_lookup(dev->aliases, target);
if (pcmk__str_eq(check_type, PCMK_VALUE_NONE, pcmk__str_casei)) {
can = TRUE;
} else if (pcmk__str_eq(check_type, PCMK_VALUE_STATIC_LIST,
pcmk__str_casei)) {
if (pcmk__str_in_list(target, dev->targets, pcmk__str_casei)) {
can = TRUE;
} else if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_MAP)
&& g_hash_table_lookup(dev->aliases, target)) {
can = TRUE;
}
} else if (pcmk__str_eq(check_type, PCMK_VALUE_DYNAMIC_LIST,
pcmk__str_casei)) {
time_t now = time(NULL);
if (dev->targets == NULL || dev->targets_age + 60 < now) {
int device_timeout = get_action_timeout(dev, PCMK_ACTION_LIST,
search->per_device_timeout);
if (device_timeout > search->per_device_timeout) {
crm_notice("Since the pcmk_list_timeout (%ds) parameter of %s "
"is larger than " PCMK_OPT_STONITH_TIMEOUT
" (%ds), timeout may occur",
device_timeout, dev_id, search->per_device_timeout);
}
crm_trace("Running '%s' to check whether %s is eligible to fence %s (%s)",
check_type, dev_id, target, action);
schedule_internal_command(__func__, dev, PCMK_ACTION_LIST, NULL,
search->per_device_timeout, search, dynamic_list_search_cb);
/* we'll respond to this search request async in the cb */
return;
}
if (pcmk__str_in_list(((alias == NULL)? target : alias), dev->targets,
pcmk__str_casei)) {
can = TRUE;
}
} else if (pcmk__str_eq(check_type, PCMK_VALUE_STATUS, pcmk__str_casei)) {
int device_timeout = get_action_timeout(dev, check_type, search->per_device_timeout);
if (device_timeout > search->per_device_timeout) {
crm_notice("Since the pcmk_status_timeout (%ds) parameter of %s is "
"larger than " PCMK_OPT_STONITH_TIMEOUT " (%ds), "
"timeout may occur",
device_timeout, dev_id, search->per_device_timeout);
}
crm_trace("Running '%s' to check whether %s is eligible to fence %s (%s)",
check_type, dev_id, target, action);
schedule_internal_command(__func__, dev, PCMK_ACTION_STATUS, target,
search->per_device_timeout, search, status_search_cb);
/* we'll respond to this search request async in the cb */
return;
} else {
crm_err("Invalid value for " PCMK_STONITH_HOST_CHECK ": %s", check_type);
check_type = "Invalid " PCMK_STONITH_HOST_CHECK;
}
search_report_results:
crm_info("%s is%s eligible to fence (%s) %s%s%s%s: %s",
dev_id, (can? "" : " not"), pcmk__s(action, "unspecified action"),
pcmk__s(target, "unspecified target"),
(alias == NULL)? "" : " (as '", pcmk__s(alias, ""),
(alias == NULL)? "" : "')", check_type);
search_devices_record_result(search, ((dev == NULL)? NULL : dev_id), can);
}
static void
search_devices(gpointer key, gpointer value, gpointer user_data)
{
stonith_device_t *dev = value;
struct device_search_s *search = user_data;
can_fence_host_with_device(dev, search);
}
#define DEFAULT_QUERY_TIMEOUT 20
static void
get_capable_devices(const char *host, const char *action, int timeout, bool suicide, void *user_data,
void (*callback) (GList * devices, void *user_data), uint32_t support_action_only)
{
struct device_search_s *search;
guint ndevices = g_hash_table_size(device_list);
if (ndevices == 0) {
callback(NULL, user_data);
return;
}
search = pcmk__assert_alloc(1, sizeof(struct device_search_s));
search->host = pcmk__str_copy(host);
search->action = pcmk__str_copy(action);
search->per_device_timeout = timeout;
search->allow_suicide = suicide;
search->callback = callback;
search->user_data = user_data;
search->support_action_only = support_action_only;
/* We are guaranteed this many replies, even if a device is
* unregistered while the search is in progress.
*/
search->replies_needed = ndevices;
crm_debug("Searching %d device%s to see which can execute '%s' targeting %s",
ndevices, pcmk__plural_s(ndevices),
(search->action? search->action : "unknown action"),
(search->host? search->host : "any node"));
g_hash_table_foreach(device_list, search_devices, search);
}
struct st_query_data {
xmlNode *reply;
char *remote_peer;
char *client_id;
char *target;
char *action;
int call_options;
};
/*!
* \internal
* \brief Add action-specific attributes to query reply XML
*
* \param[in,out] xml XML to add attributes to
* \param[in] action Fence action
* \param[in] device Fence device
* \param[in] target Fence target
*/
static void
add_action_specific_attributes(xmlNode *xml, const char *action,
const stonith_device_t *device,
const char *target)
{
int action_specific_timeout;
int delay_max;
int delay_base;
CRM_CHECK(xml && action && device, return);
// PCMK__XA_ST_REQUIRED is currently used only for unfencing
if (is_action_required(action, device)) {
crm_trace("Action '%s' is required using %s", action, device->id);
crm_xml_add_int(xml, PCMK__XA_ST_REQUIRED, 1);
}
// pcmk_<action>_timeout if configured
action_specific_timeout = get_action_timeout(device, action, 0);
if (action_specific_timeout) {
crm_trace("Action '%s' has timeout %ds using %s",
action, action_specific_timeout, device->id);
crm_xml_add_int(xml, PCMK__XA_ST_ACTION_TIMEOUT,
action_specific_timeout);
}
delay_max = get_action_delay_max(device, action);
if (delay_max > 0) {
crm_trace("Action '%s' has maximum random delay %ds using %s",
action, delay_max, device->id);
crm_xml_add_int(xml, PCMK__XA_ST_DELAY_MAX, delay_max);
}
delay_base = get_action_delay_base(device, action, target);
if (delay_base > 0) {
crm_xml_add_int(xml, PCMK__XA_ST_DELAY_BASE, delay_base);
}
if ((delay_max > 0) && (delay_base == 0)) {
crm_trace("Action '%s' has maximum random delay %ds using %s",
action, delay_max, device->id);
} else if ((delay_max == 0) && (delay_base > 0)) {
crm_trace("Action '%s' has a static delay of %ds using %s",
action, delay_base, device->id);
} else if ((delay_max > 0) && (delay_base > 0)) {
crm_trace("Action '%s' has a minimum delay of %ds and a randomly chosen "
"maximum delay of %ds using %s",
action, delay_base, delay_max, device->id);
}
}
/*!
* \internal
* \brief Add "disallowed" attribute to query reply XML if appropriate
*
* \param[in,out] xml XML to add attribute to
* \param[in] action Fence action
* \param[in] device Fence device
* \param[in] target Fence target
* \param[in] allow_suicide Whether self-fencing is allowed
*/
static void
add_disallowed(xmlNode *xml, const char *action, const stonith_device_t *device,
const char *target, gboolean allow_suicide)
{
if (!localhost_is_eligible(device, action, target, allow_suicide)) {
crm_trace("Action '%s' using %s is disallowed for local host",
action, device->id);
pcmk__xe_set_bool_attr(xml, PCMK__XA_ST_ACTION_DISALLOWED, true);
}
}
/*!
* \internal
* \brief Add child element with action-specific values to query reply XML
*
* \param[in,out] xml XML to add attribute to
* \param[in] action Fence action
* \param[in] device Fence device
* \param[in] target Fence target
* \param[in] allow_suicide Whether self-fencing is allowed
*/
static void
add_action_reply(xmlNode *xml, const char *action,
const stonith_device_t *device, const char *target,
gboolean allow_suicide)
{
xmlNode *child = pcmk__xe_create(xml, PCMK__XE_ST_DEVICE_ACTION);
crm_xml_add(child, PCMK_XA_ID, action);
add_action_specific_attributes(child, action, device, target);
add_disallowed(child, action, device, target, allow_suicide);
}
/*!
* \internal
* \brief Send a reply to a CPG peer or IPC client
*
* \param[in] reply XML reply to send
* \param[in] call_options Send synchronously if st_opt_sync_call is set
* \param[in] remote_peer If not NULL, name of peer node to send CPG reply
* \param[in,out] client If not NULL, client to send IPC reply
*/
static void
stonith_send_reply(const xmlNode *reply, int call_options,
const char *remote_peer, pcmk__client_t *client)
{
CRM_CHECK((reply != NULL) && ((remote_peer != NULL) || (client != NULL)),
return);
if (remote_peer == NULL) {
do_local_reply(reply, client, call_options);
} else {
send_cluster_message(pcmk__get_node(0, remote_peer, NULL,
pcmk__node_search_cluster),
crm_msg_stonith_ng, reply, FALSE);
}
}
static void
stonith_query_capable_device_cb(GList * devices, void *user_data)
{
struct st_query_data *query = user_data;
int available_devices = 0;
xmlNode *dev = NULL;
xmlNode *list = NULL;
GList *lpc = NULL;
pcmk__client_t *client = NULL;
if (query->client_id != NULL) {
client = pcmk__find_client_by_id(query->client_id);
if ((client == NULL) && (query->remote_peer == NULL)) {
crm_trace("Skipping reply to %s: no longer a client",
query->client_id);
goto done;
}
}
/* Pack the results into XML */
list = pcmk__xe_create(NULL, __func__);
crm_xml_add(list, PCMK__XA_ST_TARGET, query->target);
for (lpc = devices; lpc != NULL; lpc = lpc->next) {
stonith_device_t *device = g_hash_table_lookup(device_list, lpc->data);
const char *action = query->action;
if (!device) {
/* It is possible the device got unregistered while
* determining who can fence the target */
continue;
}
available_devices++;
dev = pcmk__xe_create(list, PCMK__XE_ST_DEVICE_ID);
crm_xml_add(dev, PCMK_XA_ID, device->id);
crm_xml_add(dev, PCMK__XA_NAMESPACE, device->namespace);
crm_xml_add(dev, PCMK_XA_AGENT, device->agent);
// Has had successful monitor, list, or status on this node
crm_xml_add_int(dev, PCMK__XA_ST_MONITOR_VERIFIED, device->verified);
crm_xml_add_int(dev, PCMK__XA_ST_DEVICE_SUPPORT_FLAGS, device->flags);
/* If the originating fencer wants to reboot the node, and we have a
* capable device that doesn't support "reboot", remap to "off" instead.
*/
if (!pcmk_is_set(device->flags, st_device_supports_reboot)
&& pcmk__str_eq(query->action, PCMK_ACTION_REBOOT,
pcmk__str_none)) {
crm_trace("%s doesn't support reboot, using values for off instead",
device->id);
action = PCMK_ACTION_OFF;
}
/* Add action-specific values if available */
add_action_specific_attributes(dev, action, device, query->target);
if (pcmk__str_eq(query->action, PCMK_ACTION_REBOOT, pcmk__str_none)) {
/* A "reboot" *might* get remapped to "off" then "on", so after
* sending the "reboot"-specific values in the main element, we add
* sub-elements for "off" and "on" values.
*
* We short-circuited earlier if "reboot", "off" and "on" are all
* disallowed for the local host. However if only one or two are
* disallowed, we send back the results and mark which ones are
* disallowed. If "reboot" is disallowed, this might cause problems
* with older fencer versions, which won't check for it. Older
* versions will ignore "off" and "on", so they are not a problem.
*/
add_disallowed(dev, action, device, query->target,
pcmk_is_set(query->call_options, st_opt_allow_suicide));
add_action_reply(dev, PCMK_ACTION_OFF, device, query->target,
pcmk_is_set(query->call_options, st_opt_allow_suicide));
add_action_reply(dev, PCMK_ACTION_ON, device, query->target, FALSE);
}
/* A query without a target wants device parameters */
if (query->target == NULL) {
xmlNode *attrs = pcmk__xe_create(dev, PCMK__XE_ATTRIBUTES);
g_hash_table_foreach(device->params, hash2field, attrs);
}
}
crm_xml_add_int(list, PCMK__XA_ST_AVAILABLE_DEVICES, available_devices);
if (query->target) {
crm_debug("Found %d matching device%s for target '%s'",
available_devices, pcmk__plural_s(available_devices),
query->target);
} else {
crm_debug("%d device%s installed",
available_devices, pcmk__plural_s(available_devices));
}
if (list != NULL) {
xmlNode *wrapper = pcmk__xe_create(query->reply, PCMK__XE_ST_CALLDATA);
crm_log_xml_trace(list, "Add query results");
xmlAddChild(wrapper, list);
}
stonith_send_reply(query->reply, query->call_options, query->remote_peer,
client);
done:
free_xml(query->reply);
free(query->remote_peer);
free(query->client_id);
free(query->target);
free(query->action);
free(query);
g_list_free_full(devices, free);
}
/*!
* \internal
* \brief Log the result of an asynchronous command
*
* \param[in] cmd Command the result is for
* \param[in] result Result of command
* \param[in] pid Process ID of command, if available
* \param[in] next Alternate device that will be tried if command failed
* \param[in] op_merged Whether this command was merged with an earlier one
*/
static void
log_async_result(const async_command_t *cmd,
const pcmk__action_result_t *result,
int pid, const char *next, bool op_merged)
{
int log_level = LOG_ERR;
int output_log_level = LOG_NEVER;
guint devices_remaining = g_list_length(cmd->next_device_iter);
GString *msg = g_string_sized_new(80); // Reasonable starting size
// Choose log levels appropriately if we have a result
if (pcmk__result_ok(result)) {
log_level = (cmd->target == NULL)? LOG_DEBUG : LOG_NOTICE;
if ((result->action_stdout != NULL)
&& !pcmk__str_eq(cmd->action, PCMK_ACTION_METADATA,
pcmk__str_none)) {
output_log_level = LOG_DEBUG;
}
next = NULL;
} else {
log_level = (cmd->target == NULL)? LOG_NOTICE : LOG_ERR;
if ((result->action_stdout != NULL)
&& !pcmk__str_eq(cmd->action, PCMK_ACTION_METADATA,
pcmk__str_none)) {
output_log_level = LOG_WARNING;
}
}
// Build the log message piece by piece
pcmk__g_strcat(msg, "Operation '", cmd->action, "' ", NULL);
if (pid != 0) {
g_string_append_printf(msg, "[%d] ", pid);
}
if (cmd->target != NULL) {
pcmk__g_strcat(msg, "targeting ", cmd->target, " ", NULL);
}
if (cmd->device != NULL) {
pcmk__g_strcat(msg, "using ", cmd->device, " ", NULL);
}
// Add exit status or execution status as appropriate
if (result->execution_status == PCMK_EXEC_DONE) {
g_string_append_printf(msg, "returned %d", result->exit_status);
} else {
pcmk__g_strcat(msg, "could not be executed: ",
pcmk_exec_status_str(result->execution_status), NULL);
}
// Add exit reason and next device if appropriate
if (result->exit_reason != NULL) {
pcmk__g_strcat(msg, " (", result->exit_reason, ")", NULL);
}
if (next != NULL) {
pcmk__g_strcat(msg, ", retrying with ", next, NULL);
}
if (devices_remaining > 0) {
g_string_append_printf(msg, " (%u device%s remaining)",
(unsigned int) devices_remaining,
pcmk__plural_s(devices_remaining));
}
g_string_append_printf(msg, " " CRM_XS " %scall %d from %s",
(op_merged? "merged " : ""), cmd->id,
cmd->client_name);
// Log the result
do_crm_log(log_level, "%s", msg->str);
g_string_free(msg, TRUE);
// Log the output (which may have multiple lines), if appropriate
if (output_log_level != LOG_NEVER) {
char *prefix = crm_strdup_printf("%s[%d]", cmd->device, pid);
crm_log_output(output_log_level, prefix, result->action_stdout);
free(prefix);
}
}
/*!
* \internal
* \brief Reply to requester after asynchronous command completion
*
* \param[in] cmd Command that completed
* \param[in] result Result of command
* \param[in] pid Process ID of command, if available
* \param[in] merged If true, command was merged with another, not executed
*/
static void
send_async_reply(const async_command_t *cmd, const pcmk__action_result_t *result,
int pid, bool merged)
{
xmlNode *reply = NULL;
pcmk__client_t *client = NULL;
CRM_CHECK((cmd != NULL) && (result != NULL), return);
log_async_result(cmd, result, pid, NULL, merged);
if (cmd->client != NULL) {
client = pcmk__find_client_by_id(cmd->client);
if ((client == NULL) && (cmd->origin == NULL)) {
crm_trace("Skipping reply to %s: no longer a client", cmd->client);
return;
}
}
reply = construct_async_reply(cmd, result);
if (merged) {
pcmk__xe_set_bool_attr(reply, PCMK__XA_ST_OP_MERGED, true);
}
if (!stand_alone && pcmk__is_fencing_action(cmd->action)
&& pcmk__str_eq(cmd->origin, cmd->target, pcmk__str_casei)) {
/* The target was also the originator, so broadcast the result on its
* behalf (since it will be unable to).
*/
crm_trace("Broadcast '%s' result for %s (target was also originator)",
cmd->action, cmd->target);
crm_xml_add(reply, PCMK__XA_SUBT, PCMK__VALUE_BROADCAST);
crm_xml_add(reply, PCMK__XA_ST_OP, STONITH_OP_NOTIFY);
send_cluster_message(NULL, crm_msg_stonith_ng, reply, FALSE);
} else {
// Reply only to the originator
stonith_send_reply(reply, cmd->options, cmd->origin, client);
}
crm_log_xml_trace(reply, "Reply");
free_xml(reply);
if (stand_alone) {
/* Do notification with a clean data object */
xmlNode *notify_data = pcmk__xe_create(NULL, PCMK__XE_ST_NOTIFY_FENCE);
stonith__xe_set_result(notify_data, result);
crm_xml_add(notify_data, PCMK__XA_ST_TARGET, cmd->target);
crm_xml_add(notify_data, PCMK__XA_ST_OP, cmd->op);
crm_xml_add(notify_data, PCMK__XA_ST_DELEGATE, "localhost");
crm_xml_add(notify_data, PCMK__XA_ST_DEVICE_ID, cmd->device);
crm_xml_add(notify_data, PCMK__XA_ST_REMOTE_OP, cmd->remote_op_id);
crm_xml_add(notify_data, PCMK__XA_ST_ORIGIN, cmd->client);
fenced_send_notification(PCMK__VALUE_ST_NOTIFY_FENCE, result,
notify_data);
fenced_send_notification(PCMK__VALUE_ST_NOTIFY_HISTORY, NULL, NULL);
}
}
static void
cancel_stonith_command(async_command_t * cmd)
{
stonith_device_t *device = cmd_device(cmd);
if (device) {
crm_trace("Cancel scheduled '%s' action using %s",
cmd->action, device->id);
device->pending_ops = g_list_remove(device->pending_ops, cmd);
}
}
/*!
* \internal
* \brief Cancel and reply to any duplicates of a just-completed operation
*
* Check whether any fencing operations are scheduled to do the same thing as
* one that just succeeded. If so, rather than performing the same operation
* twice, return the result of this operation for all matching pending commands.
*
* \param[in,out] cmd Fencing operation that just succeeded
* \param[in] result Result of \p cmd
* \param[in] pid If nonzero, process ID of agent invocation (for logs)
*
* \note Duplicate merging will do the right thing for either type of remapped
* reboot. If the executing fencer remapped an unsupported reboot to off,
* then cmd->action will be "reboot" and will be merged with any other
* reboot requests. If the originating fencer remapped a topology reboot
* to off then on, we will get here once with cmd->action "off" and once
* with "on", and they will be merged separately with similar requests.
*/
static void
reply_to_duplicates(async_command_t *cmd, const pcmk__action_result_t *result,
int pid)
{
GList *next = NULL;
for (GList *iter = cmd_list; iter != NULL; iter = next) {
async_command_t *cmd_other = iter->data;
next = iter->next; // We might delete this entry, so grab next now
if (cmd == cmd_other) {
continue;
}
/* A pending operation matches if:
* 1. The client connections are different.
* 2. The target is the same.
* 3. The fencing action is the same.
* 4. The device scheduled to execute the action is the same.
*/
if (pcmk__str_eq(cmd->client, cmd_other->client, pcmk__str_casei) ||
!pcmk__str_eq(cmd->target, cmd_other->target, pcmk__str_casei) ||
!pcmk__str_eq(cmd->action, cmd_other->action, pcmk__str_none) ||
!pcmk__str_eq(cmd->device, cmd_other->device, pcmk__str_casei)) {
continue;
}
crm_notice("Merging fencing action '%s'%s%s originating from "
"client %s with identical fencing request from client %s",
cmd_other->action,
(cmd_other->target == NULL)? "" : " targeting ",
pcmk__s(cmd_other->target, ""), cmd_other->client_name,
cmd->client_name);
// Stop tracking the duplicate, send its result, and cancel it
cmd_list = g_list_remove_link(cmd_list, iter);
send_async_reply(cmd_other, result, pid, true);
cancel_stonith_command(cmd_other);
free_async_command(cmd_other);
g_list_free_1(iter);
}
}
/*!
* \internal
* \brief Return the next required device (if any) for an operation
*
* \param[in,out] cmd Fencing operation that just succeeded
*
* \return Next device required for action if any, otherwise NULL
*/
static stonith_device_t *
next_required_device(async_command_t *cmd)
{
for (GList *iter = cmd->next_device_iter; iter != NULL; iter = iter->next) {
stonith_device_t *next_device = g_hash_table_lookup(device_list,
iter->data);
if (is_action_required(cmd->action, next_device)) {
/* This is only called for successful actions, so it's OK to skip
* non-required devices.
*/
cmd->next_device_iter = iter->next;
return next_device;
}
}
return NULL;
}
static void
st_child_done(int pid, const pcmk__action_result_t *result, void *user_data)
{
async_command_t *cmd = user_data;
stonith_device_t *device = NULL;
stonith_device_t *next_device = NULL;
CRM_CHECK(cmd != NULL, return);
device = cmd_device(cmd);
cmd->active_on = NULL;
/* The device is ready to do something else now */
if (device) {
if (!device->verified && pcmk__result_ok(result)
&& pcmk__strcase_any_of(cmd->action, PCMK_ACTION_LIST,
PCMK_ACTION_MONITOR, PCMK_ACTION_STATUS,
NULL)) {
device->verified = TRUE;
}
mainloop_set_trigger(device->work);
}
if (pcmk__result_ok(result)) {
next_device = next_required_device(cmd);
} else if ((cmd->next_device_iter != NULL)
&& !is_action_required(cmd->action, device)) {
/* if this device didn't work out, see if there are any others we can try.
* if the failed device was 'required', we can't pick another device. */
next_device = g_hash_table_lookup(device_list,
cmd->next_device_iter->data);
cmd->next_device_iter = cmd->next_device_iter->next;
}
if (next_device == NULL) {
send_async_reply(cmd, result, pid, false);
if (pcmk__result_ok(result)) {
reply_to_duplicates(cmd, result, pid);
}
free_async_command(cmd);
} else { // This operation requires more fencing
log_async_result(cmd, result, pid, next_device->id, false);
schedule_stonith_command(cmd, next_device);
}
}
static gint
sort_device_priority(gconstpointer a, gconstpointer b)
{
const stonith_device_t *dev_a = a;
const stonith_device_t *dev_b = b;
if (dev_a->priority > dev_b->priority) {
return -1;
} else if (dev_a->priority < dev_b->priority) {
return 1;
}
return 0;
}
static void
stonith_fence_get_devices_cb(GList * devices, void *user_data)
{
async_command_t *cmd = user_data;
stonith_device_t *device = NULL;
guint ndevices = g_list_length(devices);
crm_info("Found %d matching device%s for target '%s'",
ndevices, pcmk__plural_s(ndevices), cmd->target);
if (devices != NULL) {
/* Order based on priority */
devices = g_list_sort(devices, sort_device_priority);
device = g_hash_table_lookup(device_list, devices->data);
}
if (device == NULL) { // No device found
pcmk__action_result_t result = PCMK__UNKNOWN_RESULT;
pcmk__format_result(&result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE,
"No device configured for target '%s'",
cmd->target);
send_async_reply(cmd, &result, 0, false);
pcmk__reset_result(&result);
free_async_command(cmd);
g_list_free_full(devices, free);
} else { // Device found, schedule it for fencing
cmd->device_list = devices;
cmd->next_device_iter = devices->next;
schedule_stonith_command(cmd, device);
}
}
/*!
* \internal
* \brief Execute a fence action via the local node
*
* \param[in] msg Fencing request
* \param[out] result Where to store result of fence action
*/
static void
fence_locally(xmlNode *msg, pcmk__action_result_t *result)
{
const char *device_id = NULL;
stonith_device_t *device = NULL;
async_command_t *cmd = NULL;
xmlNode *dev = NULL;
CRM_CHECK((msg != NULL) && (result != NULL), return);
dev = get_xpath_object("//@" PCMK__XA_ST_TARGET, msg, LOG_ERR);
cmd = create_async_command(msg);
if (cmd == NULL) {
crm_log_xml_warn(msg, "invalid");
fenced_set_protocol_error(result);
return;
}
device_id = crm_element_value(dev, PCMK__XA_ST_DEVICE_ID);
if (device_id != NULL) {
device = g_hash_table_lookup(device_list, device_id);
if (device == NULL) {
crm_err("Requested device '%s' is not available", device_id);
pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE,
"Requested device '%s' not found", device_id);
return;
}
schedule_stonith_command(cmd, device);
} else {
const char *host = crm_element_value(dev, PCMK__XA_ST_TARGET);
if (pcmk_is_set(cmd->options, st_opt_cs_nodeid)) {
int nodeid = 0;
crm_node_t *node = NULL;
pcmk__scan_min_int(host, &nodeid, 0);
node = pcmk__search_node_caches(nodeid, NULL,
pcmk__node_search_any
|pcmk__node_search_known);
if (node != NULL) {
host = node->uname;
}
}
/* If we get to here, then self-fencing is implicitly allowed */
get_capable_devices(host, cmd->action, cmd->default_timeout,
TRUE, cmd, stonith_fence_get_devices_cb,
fenced_support_flag(cmd->action));
}
pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL);
}
/*!
* \internal
* \brief Build an XML reply for a fencing operation
*
* \param[in] request Request that reply is for
* \param[in] data If not NULL, add to reply as call data
* \param[in] result Full result of fencing operation
*
* \return Newly created XML reply
* \note The caller is responsible for freeing the result.
* \note This has some overlap with construct_async_reply(), but that copies
* values from an async_command_t, whereas this one copies them from the
* request.
*/
xmlNode *
fenced_construct_reply(const xmlNode *request, xmlNode *data,
const pcmk__action_result_t *result)
{
xmlNode *reply = NULL;
reply = pcmk__xe_create(NULL, PCMK__XE_ST_REPLY);
crm_xml_add(reply, PCMK__XA_ST_ORIGIN, __func__);
crm_xml_add(reply, PCMK__XA_T, PCMK__VALUE_STONITH_NG);
stonith__xe_set_result(reply, result);
if (request == NULL) {
/* Most likely, this is the result of a stonith operation that was
* initiated before we came up. Unfortunately that means we lack enough
* information to provide clients with a full result.
*
* @TODO Maybe synchronize this information at start-up?
*/
crm_warn("Missing request information for client notifications for "
"operation with result '%s' (initiated before we came up?)",
pcmk_exec_status_str(result->execution_status));
} else {
const char *name = NULL;
const char *value = NULL;
// Attributes to copy from request to reply
const char *names[] = {
PCMK__XA_ST_OP,
PCMK__XA_ST_CALLID,
PCMK__XA_ST_CLIENTID,
PCMK__XA_ST_CLIENTNAME,
PCMK__XA_ST_REMOTE_OP,
PCMK__XA_ST_CALLOPT,
};
for (int lpc = 0; lpc < PCMK__NELEM(names); lpc++) {
name = names[lpc];
value = crm_element_value(request, name);
crm_xml_add(reply, name, value);
}
if (data != NULL) {
xmlNode *wrapper = pcmk__xe_create(reply, PCMK__XE_ST_CALLDATA);
pcmk__xml_copy(wrapper, data);
}
}
return reply;
}
/*!
* \internal
* \brief Build an XML reply to an asynchronous fencing command
*
* \param[in] cmd Fencing command that reply is for
* \param[in] result Command result
*/
static xmlNode *
construct_async_reply(const async_command_t *cmd,
const pcmk__action_result_t *result)
{
xmlNode *reply = pcmk__xe_create(NULL, PCMK__XE_ST_REPLY);
crm_xml_add(reply, PCMK__XA_ST_ORIGIN, __func__);
crm_xml_add(reply, PCMK__XA_T, PCMK__VALUE_STONITH_NG);
crm_xml_add(reply, PCMK__XA_ST_OP, cmd->op);
crm_xml_add(reply, PCMK__XA_ST_DEVICE_ID, cmd->device);
crm_xml_add(reply, PCMK__XA_ST_REMOTE_OP, cmd->remote_op_id);
crm_xml_add(reply, PCMK__XA_ST_CLIENTID, cmd->client);
crm_xml_add(reply, PCMK__XA_ST_CLIENTNAME, cmd->client_name);
crm_xml_add(reply, PCMK__XA_ST_TARGET, cmd->target);
crm_xml_add(reply, PCMK__XA_ST_DEVICE_ACTION, cmd->op);
crm_xml_add(reply, PCMK__XA_ST_ORIGIN, cmd->origin);
crm_xml_add_int(reply, PCMK__XA_ST_CALLID, cmd->id);
crm_xml_add_int(reply, PCMK__XA_ST_CALLOPT, cmd->options);
stonith__xe_set_result(reply, result);
return reply;
}
bool fencing_peer_active(crm_node_t *peer)
{
if (peer == NULL) {
return FALSE;
} else if (peer->uname == NULL) {
return FALSE;
} else if (pcmk_is_set(peer->processes, crm_get_cluster_proc())) {
return TRUE;
}
return FALSE;
}
void
set_fencing_completed(remote_fencing_op_t *op)
{
struct timespec tv;
qb_util_timespec_from_epoch_get(&tv);
op->completed = tv.tv_sec;
op->completed_nsec = tv.tv_nsec;
}
/*!
* \internal
* \brief Look for alternate node needed if local node shouldn't fence target
*
* \param[in] target Node that must be fenced
*
* \return Name of an alternate node that should fence \p target if any,
* or NULL otherwise
*/
static const char *
check_alternate_host(const char *target)
{
if (pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei)) {
GHashTableIter gIter;
crm_node_t *entry = NULL;
g_hash_table_iter_init(&gIter, crm_peer_cache);
while (g_hash_table_iter_next(&gIter, NULL, (void **)&entry)) {
if (fencing_peer_active(entry)
&& !pcmk__str_eq(entry->uname, target, pcmk__str_casei)) {
crm_notice("Forwarding self-fencing request to %s",
entry->uname);
return entry->uname;
}
}
crm_warn("Will handle own fencing because no peer can");
}
return NULL;
}
static void
remove_relay_op(xmlNode * request)
{
xmlNode *dev = get_xpath_object("//@" PCMK__XE_ST_DEVICE_ACTION, request,
LOG_TRACE);
const char *relay_op_id = NULL;
const char *op_id = NULL;
const char *client_name = NULL;
const char *target = NULL;
remote_fencing_op_t *relay_op = NULL;
if (dev) {
target = crm_element_value(dev, PCMK__XA_ST_TARGET);
}
relay_op_id = crm_element_value(request, PCMK__XA_ST_REMOTE_OP_RELAY);
op_id = crm_element_value(request, PCMK__XA_ST_REMOTE_OP);
client_name = crm_element_value(request, PCMK__XA_ST_CLIENTNAME);
/* Delete RELAY operation. */
if (relay_op_id && target && pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei)) {
relay_op = g_hash_table_lookup(stonith_remote_op_list, relay_op_id);
if (relay_op) {
GHashTableIter iter;
remote_fencing_op_t *list_op = NULL;
g_hash_table_iter_init(&iter, stonith_remote_op_list);
/* If the operation to be deleted is registered as a duplicate, delete the registration. */
while (g_hash_table_iter_next(&iter, NULL, (void **)&list_op)) {
GList *dup_iter = NULL;
if (list_op != relay_op) {
for (dup_iter = list_op->duplicates; dup_iter != NULL; dup_iter = dup_iter->next) {
remote_fencing_op_t *other = dup_iter->data;
if (other == relay_op) {
other->duplicates = g_list_remove(other->duplicates, relay_op);
break;
}
}
}
}
crm_debug("Deleting relay op %s ('%s'%s%s for %s), "
"replaced by op %s ('%s'%s%s for %s)",
relay_op->id, relay_op->action,
(relay_op->target == NULL)? "" : " targeting ",
pcmk__s(relay_op->target, ""),
relay_op->client_name, op_id, relay_op->action,
(target == NULL)? "" : " targeting ", pcmk__s(target, ""),
client_name);
g_hash_table_remove(stonith_remote_op_list, relay_op_id);
}
}
}
/*!
* \internal
* \brief Check whether an API request was sent by a privileged user
*
* API commands related to fencing configuration may be done only by privileged
* IPC users (i.e. root or hacluster), because all other users should go through
* the CIB to have ACLs applied. If no client was given, this is a peer request,
* which is always allowed.
*
* \param[in] c IPC client that sent request (or NULL if sent by CPG peer)
* \param[in] op Requested API operation (for logging only)
*
* \return true if sender is peer or privileged client, otherwise false
*/
static inline bool
is_privileged(const pcmk__client_t *c, const char *op)
{
if ((c == NULL) || pcmk_is_set(c->flags, pcmk__client_privileged)) {
return true;
} else {
crm_warn("Rejecting IPC request '%s' from unprivileged client %s",
pcmk__s(op, ""), pcmk__client_name(c));
return false;
}
}
// CRM_OP_REGISTER
static xmlNode *
handle_register_request(pcmk__request_t *request)
{
xmlNode *reply = pcmk__xe_create(NULL, "reply");
CRM_ASSERT(request->ipc_client != NULL);
crm_xml_add(reply, PCMK__XA_ST_OP, CRM_OP_REGISTER);
crm_xml_add(reply, PCMK__XA_ST_CLIENTID, request->ipc_client->id);
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
pcmk__set_request_flags(request, pcmk__request_reuse_options);
return reply;
}
// STONITH_OP_EXEC
static xmlNode *
handle_agent_request(pcmk__request_t *request)
{
execute_agent_action(request->xml, &request->result);
if (request->result.execution_status == PCMK_EXEC_PENDING) {
return NULL;
}
return fenced_construct_reply(request->xml, NULL, &request->result);
}
// STONITH_OP_TIMEOUT_UPDATE
static xmlNode *
handle_update_timeout_request(pcmk__request_t *request)
{
const char *call_id = crm_element_value(request->xml, PCMK__XA_ST_CALLID);
const char *client_id = crm_element_value(request->xml,
PCMK__XA_ST_CLIENTID);
int op_timeout = 0;
crm_element_value_int(request->xml, PCMK__XA_ST_TIMEOUT, &op_timeout);
do_stonith_async_timeout_update(client_id, call_id, op_timeout);
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
return NULL;
}
// STONITH_OP_QUERY
static xmlNode *
handle_query_request(pcmk__request_t *request)
{
int timeout = 0;
xmlNode *dev = NULL;
const char *action = NULL;
const char *target = NULL;
const char *client_id = crm_element_value(request->xml,
PCMK__XA_ST_CLIENTID);
struct st_query_data *query = NULL;
if (request->peer != NULL) {
// Record it for the future notification
create_remote_stonith_op(client_id, request->xml, TRUE);
}
/* Delete the DC node RELAY operation. */
remove_relay_op(request->xml);
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
dev = get_xpath_object("//@" PCMK__XE_ST_DEVICE_ACTION, request->xml,
LOG_NEVER);
if (dev != NULL) {
const char *device = crm_element_value(dev, PCMK__XA_ST_DEVICE_ID);
if (pcmk__str_eq(device, "manual_ack", pcmk__str_casei)) {
return NULL; // No query or reply necessary
}
target = crm_element_value(dev, PCMK__XA_ST_TARGET);
action = crm_element_value(dev, PCMK__XA_ST_DEVICE_ACTION);
}
crm_log_xml_trace(request->xml, "Query");
query = pcmk__assert_alloc(1, sizeof(struct st_query_data));
query->reply = fenced_construct_reply(request->xml, NULL, &request->result);
query->remote_peer = pcmk__str_copy(request->peer);
query->client_id = pcmk__str_copy(client_id);
query->target = pcmk__str_copy(target);
query->action = pcmk__str_copy(action);
query->call_options = request->call_options;
crm_element_value_int(request->xml, PCMK__XA_ST_TIMEOUT, &timeout);
get_capable_devices(target, action, timeout,
pcmk_is_set(query->call_options, st_opt_allow_suicide),
query, stonith_query_capable_device_cb, st_device_supports_none);
return NULL;
}
// STONITH_OP_NOTIFY
static xmlNode *
handle_notify_request(pcmk__request_t *request)
{
const char *flag_name = NULL;
CRM_ASSERT(request->ipc_client != NULL);
flag_name = crm_element_value(request->xml, PCMK__XA_ST_NOTIFY_ACTIVATE);
if (flag_name != NULL) {
crm_debug("Enabling %s callbacks for client %s",
flag_name, pcmk__request_origin(request));
pcmk__set_client_flags(request->ipc_client, get_stonith_flag(flag_name));
}
flag_name = crm_element_value(request->xml, PCMK__XA_ST_NOTIFY_DEACTIVATE);
if (flag_name != NULL) {
crm_debug("Disabling %s callbacks for client %s",
flag_name, pcmk__request_origin(request));
pcmk__clear_client_flags(request->ipc_client,
get_stonith_flag(flag_name));
}
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
pcmk__set_request_flags(request, pcmk__request_reuse_options);
return pcmk__ipc_create_ack(request->ipc_flags, PCMK__XE_ACK, NULL,
CRM_EX_OK);
}
// STONITH_OP_RELAY
static xmlNode *
handle_relay_request(pcmk__request_t *request)
{
xmlNode *dev = get_xpath_object("//@" PCMK__XA_ST_TARGET, request->xml,
LOG_TRACE);
crm_notice("Received forwarded fencing request from "
"%s %s to fence (%s) peer %s",
pcmk__request_origin_type(request),
pcmk__request_origin(request),
crm_element_value(dev, PCMK__XA_ST_DEVICE_ACTION),
crm_element_value(dev, PCMK__XA_ST_TARGET));
if (initiate_remote_stonith_op(NULL, request->xml, FALSE) == NULL) {
fenced_set_protocol_error(&request->result);
return fenced_construct_reply(request->xml, NULL, &request->result);
}
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL);
return NULL;
}
// STONITH_OP_FENCE
static xmlNode *
handle_fence_request(pcmk__request_t *request)
{
if ((request->peer != NULL) || stand_alone) {
fence_locally(request->xml, &request->result);
} else if (pcmk_is_set(request->call_options, st_opt_manual_ack)) {
switch (fenced_handle_manual_confirmation(request->ipc_client,
request->xml)) {
case pcmk_rc_ok:
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE,
NULL);
break;
case EINPROGRESS:
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING,
NULL);
break;
default:
fenced_set_protocol_error(&request->result);
break;
}
} else {
const char *alternate_host = NULL;
xmlNode *dev = get_xpath_object("//@" PCMK__XA_ST_TARGET, request->xml,
LOG_TRACE);
const char *target = crm_element_value(dev, PCMK__XA_ST_TARGET);
const char *action = crm_element_value(dev, PCMK__XA_ST_DEVICE_ACTION);
const char *device = crm_element_value(dev, PCMK__XA_ST_DEVICE_ID);
if (request->ipc_client != NULL) {
int tolerance = 0;
crm_notice("Client %s wants to fence (%s) %s using %s",
pcmk__request_origin(request), action,
target, (device? device : "any device"));
crm_element_value_int(dev, PCMK__XA_ST_TOLERANCE, &tolerance);
if (stonith_check_fence_tolerance(tolerance, target, action)) {
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE,
NULL);
return fenced_construct_reply(request->xml, NULL,
&request->result);
}
alternate_host = check_alternate_host(target);
} else {
crm_notice("Peer %s wants to fence (%s) '%s' with device '%s'",
request->peer, action, target,
(device == NULL)? "(any)" : device);
}
if (alternate_host != NULL) {
const char *client_id = NULL;
remote_fencing_op_t *op = NULL;
if (request->ipc_client->id == 0) {
client_id = crm_element_value(request->xml,
PCMK__XA_ST_CLIENTID);
} else {
client_id = request->ipc_client->id;
}
/* Create a duplicate fencing operation to relay with the client ID.
* When a query response is received, this operation should be
* deleted to avoid keeping the duplicate around.
*/
op = create_remote_stonith_op(client_id, request->xml, FALSE);
crm_xml_add(request->xml, PCMK__XA_ST_OP, STONITH_OP_RELAY);
crm_xml_add(request->xml, PCMK__XA_ST_CLIENTID,
request->ipc_client->id);
crm_xml_add(request->xml, PCMK__XA_ST_REMOTE_OP, op->id);
send_cluster_message(pcmk__get_node(0, alternate_host, NULL,
pcmk__node_search_cluster),
crm_msg_stonith_ng, request->xml, FALSE);
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING,
NULL);
} else if (initiate_remote_stonith_op(request->ipc_client, request->xml,
FALSE) == NULL) {
fenced_set_protocol_error(&request->result);
} else {
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING,
NULL);
}
}
if (request->result.execution_status == PCMK_EXEC_PENDING) {
return NULL;
}
return fenced_construct_reply(request->xml, NULL, &request->result);
}
// STONITH_OP_FENCE_HISTORY
static xmlNode *
handle_history_request(pcmk__request_t *request)
{
xmlNode *reply = NULL;
xmlNode *data = NULL;
stonith_fence_history(request->xml, &data, request->peer,
request->call_options);
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
if (!pcmk_is_set(request->call_options, st_opt_discard_reply)) {
/* When the local node broadcasts its history, it sets
* st_opt_discard_reply and doesn't need a reply.
*/
reply = fenced_construct_reply(request->xml, data, &request->result);
}
free_xml(data);
return reply;
}
// STONITH_OP_DEVICE_ADD
static xmlNode *
handle_device_add_request(pcmk__request_t *request)
{
const char *op = crm_element_value(request->xml, PCMK__XA_ST_OP);
xmlNode *dev = get_xpath_object("//" PCMK__XE_ST_DEVICE_ID, request->xml,
LOG_ERR);
if (is_privileged(request->ipc_client, op)) {
int rc = stonith_device_register(dev, FALSE);
pcmk__set_result(&request->result,
((rc == pcmk_ok)? CRM_EX_OK : CRM_EX_ERROR),
stonith__legacy2status(rc),
((rc == pcmk_ok)? NULL : pcmk_strerror(rc)));
} else {
pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV,
PCMK_EXEC_INVALID,
"Unprivileged users must register device via CIB");
}
fenced_send_config_notification(op, &request->result,
(dev == NULL)? NULL : pcmk__xe_id(dev));
return fenced_construct_reply(request->xml, NULL, &request->result);
}
// STONITH_OP_DEVICE_DEL
static xmlNode *
handle_device_delete_request(pcmk__request_t *request)
{
xmlNode *dev = get_xpath_object("//" PCMK__XE_ST_DEVICE_ID, request->xml,
LOG_ERR);
const char *device_id = crm_element_value(dev, PCMK_XA_ID);
const char *op = crm_element_value(request->xml, PCMK__XA_ST_OP);
if (is_privileged(request->ipc_client, op)) {
stonith_device_remove(device_id, false);
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
} else {
pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV,
PCMK_EXEC_INVALID,
"Unprivileged users must delete device via CIB");
}
fenced_send_config_notification(op, &request->result, device_id);
return fenced_construct_reply(request->xml, NULL, &request->result);
}
// STONITH_OP_LEVEL_ADD
static xmlNode *
handle_level_add_request(pcmk__request_t *request)
{
char *desc = NULL;
const char *op = crm_element_value(request->xml, PCMK__XA_ST_OP);
if (is_privileged(request->ipc_client, op)) {
fenced_register_level(request->xml, &desc, &request->result);
} else {
unpack_level_request(request->xml, NULL, NULL, NULL, &desc);
pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV,
PCMK_EXEC_INVALID,
"Unprivileged users must add level via CIB");
}
fenced_send_config_notification(op, &request->result, desc);
free(desc);
return fenced_construct_reply(request->xml, NULL, &request->result);
}
// STONITH_OP_LEVEL_DEL
static xmlNode *
handle_level_delete_request(pcmk__request_t *request)
{
char *desc = NULL;
const char *op = crm_element_value(request->xml, PCMK__XA_ST_OP);
if (is_privileged(request->ipc_client, op)) {
fenced_unregister_level(request->xml, &desc, &request->result);
} else {
unpack_level_request(request->xml, NULL, NULL, NULL, &desc);
pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV,
PCMK_EXEC_INVALID,
"Unprivileged users must delete level via CIB");
}
fenced_send_config_notification(op, &request->result, desc);
free(desc);
return fenced_construct_reply(request->xml, NULL, &request->result);
}
// CRM_OP_RM_NODE_CACHE
static xmlNode *
handle_cache_request(pcmk__request_t *request)
{
int node_id = 0;
const char *name = NULL;
crm_element_value_int(request->xml, PCMK_XA_ID, &node_id);
name = crm_element_value(request->xml, PCMK_XA_UNAME);
- reap_crm_member(node_id, name);
+ pcmk__cluster_forget_cluster_node(node_id, name);
pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL);
return NULL;
}
static xmlNode *
handle_unknown_request(pcmk__request_t *request)
{
crm_err("Unknown IPC request %s from %s %s",
request->op, pcmk__request_origin_type(request),
pcmk__request_origin(request));
pcmk__format_result(&request->result, CRM_EX_PROTOCOL, PCMK_EXEC_INVALID,
"Unknown IPC request type '%s' (bug?)", request->op);
return fenced_construct_reply(request->xml, NULL, &request->result);
}
static void
fenced_register_handlers(void)
{
pcmk__server_command_t handlers[] = {
{ CRM_OP_REGISTER, handle_register_request },
{ STONITH_OP_EXEC, handle_agent_request },
{ STONITH_OP_TIMEOUT_UPDATE, handle_update_timeout_request },
{ STONITH_OP_QUERY, handle_query_request },
{ STONITH_OP_NOTIFY, handle_notify_request },
{ STONITH_OP_RELAY, handle_relay_request },
{ STONITH_OP_FENCE, handle_fence_request },
{ STONITH_OP_FENCE_HISTORY, handle_history_request },
{ STONITH_OP_DEVICE_ADD, handle_device_add_request },
{ STONITH_OP_DEVICE_DEL, handle_device_delete_request },
{ STONITH_OP_LEVEL_ADD, handle_level_add_request },
{ STONITH_OP_LEVEL_DEL, handle_level_delete_request },
{ CRM_OP_RM_NODE_CACHE, handle_cache_request },
{ NULL, handle_unknown_request },
};
fenced_handlers = pcmk__register_handlers(handlers);
}
void
fenced_unregister_handlers(void)
{
if (fenced_handlers != NULL) {
g_hash_table_destroy(fenced_handlers);
fenced_handlers = NULL;
}
}
static void
handle_request(pcmk__request_t *request)
{
xmlNode *reply = NULL;
const char *reason = NULL;
if (fenced_handlers == NULL) {
fenced_register_handlers();
}
reply = pcmk__process_request(request, fenced_handlers);
if (reply != NULL) {
if (pcmk_is_set(request->flags, pcmk__request_reuse_options)
&& (request->ipc_client != NULL)) {
/* Certain IPC-only commands must reuse the call options from the
* original request rather than the ones set by stonith_send_reply()
* -> do_local_reply().
*/
pcmk__ipc_send_xml(request->ipc_client, request->ipc_id, reply,
request->ipc_flags);
request->ipc_client->request_id = 0;
} else {
stonith_send_reply(reply, request->call_options,
request->peer, request->ipc_client);
}
free_xml(reply);
}
reason = request->result.exit_reason;
crm_debug("Processed %s request from %s %s: %s%s%s%s",
request->op, pcmk__request_origin_type(request),
pcmk__request_origin(request),
pcmk_exec_status_str(request->result.execution_status),
(reason == NULL)? "" : " (",
(reason == NULL)? "" : reason,
(reason == NULL)? "" : ")");
}
static void
handle_reply(pcmk__client_t *client, xmlNode *request, const char *remote_peer)
{
// Copy, because request might be freed before we want to log this
char *op = crm_element_value_copy(request, PCMK__XA_ST_OP);
if (pcmk__str_eq(op, STONITH_OP_QUERY, pcmk__str_none)) {
process_remote_stonith_query(request);
} else if (pcmk__str_any_of(op, STONITH_OP_NOTIFY, STONITH_OP_FENCE,
NULL)) {
fenced_process_fencing_reply(request);
} else {
crm_err("Ignoring unknown %s reply from %s %s",
pcmk__s(op, "untyped"), ((client == NULL)? "peer" : "client"),
((client == NULL)? remote_peer : pcmk__client_name(client)));
crm_log_xml_warn(request, "UnknownOp");
free(op);
return;
}
crm_debug("Processed %s reply from %s %s",
op, ((client == NULL)? "peer" : "client"),
((client == NULL)? remote_peer : pcmk__client_name(client)));
free(op);
}
/*!
* \internal
* \brief Handle a message from an IPC client or CPG peer
*
* \param[in,out] client If not NULL, IPC client that sent message
* \param[in] id If from IPC client, IPC message ID
* \param[in] flags Message flags
* \param[in,out] message Message XML
* \param[in] remote_peer If not NULL, CPG peer that sent message
*/
void
stonith_command(pcmk__client_t *client, uint32_t id, uint32_t flags,
xmlNode *message, const char *remote_peer)
{
int call_options = st_opt_none;
bool is_reply = false;
CRM_CHECK(message != NULL, return);
if (get_xpath_object("//" PCMK__XE_ST_REPLY, message, LOG_NEVER) != NULL) {
is_reply = true;
}
crm_element_value_int(message, PCMK__XA_ST_CALLOPT, &call_options);
crm_debug("Processing %ssynchronous %s %s %u from %s %s",
pcmk_is_set(call_options, st_opt_sync_call)? "" : "a",
crm_element_value(message, PCMK__XA_ST_OP),
(is_reply? "reply" : "request"), id,
((client == NULL)? "peer" : "client"),
((client == NULL)? remote_peer : pcmk__client_name(client)));
if (pcmk_is_set(call_options, st_opt_sync_call)) {
CRM_ASSERT(client == NULL || client->request_id == id);
}
if (is_reply) {
handle_reply(client, message, remote_peer);
} else {
pcmk__request_t request = {
.ipc_client = client,
.ipc_id = id,
.ipc_flags = flags,
.peer = remote_peer,
.xml = message,
.call_options = call_options,
.result = PCMK__UNKNOWN_RESULT,
};
request.op = crm_element_value_copy(request.xml, PCMK__XA_ST_OP);
CRM_CHECK(request.op != NULL, return);
if (pcmk_is_set(request.call_options, st_opt_sync_call)) {
pcmk__set_request_flags(&request, pcmk__request_sync);
}
handle_request(&request);
pcmk__reset_request(&request);
}
}
diff --git a/include/crm/cluster/internal.h b/include/crm/cluster/internal.h
index abc9afa941..8549db0bb5 100644
--- a/include/crm/cluster/internal.h
+++ b/include/crm/cluster/internal.h
@@ -1,160 +1,162 @@
/*
* Copyright 2004-2024 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU Lesser General Public License
* version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY.
*/
#ifndef PCMK__CRM_CLUSTER_INTERNAL__H
# define PCMK__CRM_CLUSTER_INTERNAL__H
# include <stdint.h> // uint32_t, uint64_t
# include <glib.h> // gboolean
# include <crm/cluster.h>
/* *INDENT-OFF* */
enum crm_proc_flag {
crm_proc_none = 0x00000001,
// Cluster layers
crm_proc_cpg = 0x04000000,
// Daemons
crm_proc_execd = 0x00000010,
crm_proc_based = 0x00000100,
crm_proc_controld = 0x00000200,
crm_proc_attrd = 0x00001000,
crm_proc_schedulerd = 0x00010000,
crm_proc_fenced = 0x00100000,
};
/* *INDENT-ON* */
// Used with node cache search functions
enum pcmk__node_search_flags {
pcmk__node_search_none = 0,
pcmk__node_search_cluster = (1 << 0), // Search for cluster nodes
pcmk__node_search_remote = (1 << 1), // Search for remote nodes
pcmk__node_search_any = pcmk__node_search_cluster
|pcmk__node_search_remote,
/* @COMPAT The values before this must stay the same until we can drop
* support for enum crm_get_peer_flags
*/
pcmk__node_search_known = (1 << 2), // Search previously known nodes
};
/*!
* \internal
* \brief Return the process bit corresponding to the current cluster stack
*
* \return Process flag if detectable, otherwise 0
*/
static inline uint32_t
crm_get_cluster_proc(void)
{
switch (get_cluster_type()) {
case pcmk_cluster_corosync:
return crm_proc_cpg;
default:
break;
}
return crm_proc_none;
}
/*!
* \internal
* \brief Get log-friendly string description of a Corosync return code
*
* \param[in] error Corosync return code
*
* \return Log-friendly string description corresponding to \p error
*/
static inline const char *
pcmk__cs_err_str(int error)
{
# if SUPPORT_COROSYNC
switch (error) {
case CS_OK: return "OK";
case CS_ERR_LIBRARY: return "Library error";
case CS_ERR_VERSION: return "Version error";
case CS_ERR_INIT: return "Initialization error";
case CS_ERR_TIMEOUT: return "Timeout";
case CS_ERR_TRY_AGAIN: return "Try again";
case CS_ERR_INVALID_PARAM: return "Invalid parameter";
case CS_ERR_NO_MEMORY: return "No memory";
case CS_ERR_BAD_HANDLE: return "Bad handle";
case CS_ERR_BUSY: return "Busy";
case CS_ERR_ACCESS: return "Access error";
case CS_ERR_NOT_EXIST: return "Doesn't exist";
case CS_ERR_NAME_TOO_LONG: return "Name too long";
case CS_ERR_EXIST: return "Exists";
case CS_ERR_NO_SPACE: return "No space";
case CS_ERR_INTERRUPT: return "Interrupt";
case CS_ERR_NAME_NOT_FOUND: return "Name not found";
case CS_ERR_NO_RESOURCES: return "No resources";
case CS_ERR_NOT_SUPPORTED: return "Not supported";
case CS_ERR_BAD_OPERATION: return "Bad operation";
case CS_ERR_FAILED_OPERATION: return "Failed operation";
case CS_ERR_MESSAGE_ERROR: return "Message error";
case CS_ERR_QUEUE_FULL: return "Queue full";
case CS_ERR_QUEUE_NOT_AVAILABLE: return "Queue not available";
case CS_ERR_BAD_FLAGS: return "Bad flags";
case CS_ERR_TOO_BIG: return "Too big";
case CS_ERR_NO_SECTIONS: return "No sections";
}
# endif
return "Corosync error";
}
# if SUPPORT_COROSYNC
#if 0
/* This is the new way to do it, but we still support all Corosync 2 versions,
* and this isn't always available. A better alternative here would be to check
* for support in the configure script and enable this conditionally.
*/
#define pcmk__init_cmap(handle) cmap_initialize_map((handle), CMAP_MAP_ICMAP)
#else
#define pcmk__init_cmap(handle) cmap_initialize(handle)
#endif
char *pcmk__corosync_cluster_name(void);
bool pcmk__corosync_add_nodes(xmlNode *xml_parent);
# endif
crm_node_t *crm_update_peer_proc(const char *source, crm_node_t * peer,
uint32_t flag, const char *status);
crm_node_t *pcmk__update_peer_state(const char *source, crm_node_t *node,
const char *state, uint64_t membership);
void pcmk__update_peer_expected(const char *source, crm_node_t *node,
const char *expected);
void pcmk__reap_unseen_nodes(uint64_t ring_id);
void pcmk__corosync_quorum_connect(gboolean (*dispatch)(unsigned long long,
gboolean),
void (*destroy) (gpointer));
bool pcmk__cluster_is_node_active(const crm_node_t *node);
unsigned int pcmk__cluster_num_active_nodes(void);
unsigned int pcmk__cluster_num_remote_nodes(void);
+
crm_node_t *pcmk__cluster_lookup_remote_node(const char *node_name);
+void pcmk__cluster_forget_cluster_node(uint32_t id, const char *node_name);
void pcmk__cluster_forget_remote_node(const char *node_name);
crm_node_t *pcmk__search_node_caches(unsigned int id, const char *uname,
uint32_t flags);
crm_node_t *pcmk__search_cluster_node_cache(unsigned int id, const char *uname,
const char *uuid);
void pcmk__purge_node_from_cache(const char *node_name, uint32_t node_id);
void pcmk__refresh_node_caches_from_cib(xmlNode *cib);
crm_node_t *pcmk__get_node(unsigned int id, const char *uname,
const char *uuid, uint32_t flags);
#endif // PCMK__CRM_CLUSTER_INTERNAL__H
diff --git a/lib/cluster/membership.c b/lib/cluster/membership.c
index 4efc58d56c..7cd8608f66 100644
--- a/lib/cluster/membership.c
+++ b/lib/cluster/membership.c
@@ -1,1485 +1,1549 @@
/*
* Copyright 2004-2024 the Pacemaker project contributors
*
* The version control history for this file may have further details.
*
* This source code is licensed under the GNU Lesser General Public License
* version 2.1 or later (LGPLv2.1+) WITHOUT ANY WARRANTY.
*/
#include <crm_internal.h>
#ifndef _GNU_SOURCE
# define _GNU_SOURCE
#endif
+#include <inttypes.h> // PRIu32
#include <sys/param.h>
#include <sys/types.h>
#include <stdio.h>
#include <unistd.h>
#include <string.h>
#include <glib.h>
#include <crm/common/ipc.h>
#include <crm/common/xml_internal.h>
#include <crm/cluster/internal.h>
#include <crm/common/xml.h>
#include <crm/stonith-ng.h>
#include "crmcluster_private.h"
/* The peer cache remembers cluster nodes that have been seen.
* This is managed mostly automatically by libcluster, based on
* cluster membership events.
*
* Because cluster nodes can have conflicting names or UUIDs,
* the hash table key is a uniquely generated ID.
*/
GHashTable *crm_peer_cache = NULL;
/*
* The remote peer cache tracks pacemaker_remote nodes. While the
* value has the same type as the peer cache's, it is tracked separately for
* three reasons: pacemaker_remote nodes can't have conflicting names or UUIDs,
* so the name (which is also the UUID) is used as the hash table key; there
* is no equivalent of membership events, so management is not automatic; and
* most users of the peer cache need to exclude pacemaker_remote nodes.
*
* That said, using a single cache would be more logical and less error-prone,
* so it would be a good idea to merge them one day.
*
* libcluster provides two avenues for populating the cache:
* pcmk__cluster_lookup_remote_node() and pcmk__cluster_forget_remote_node()
* directly manage it, while refresh_remote_nodes() populates it via the CIB.
*/
GHashTable *crm_remote_peer_cache = NULL;
/*
* The known node cache tracks cluster and remote nodes that have been seen in
* the CIB. It is useful mainly when a caller needs to know about a node that
* may no longer be in the membership, but doesn't want to add the node to the
* main peer cache tables.
*/
static GHashTable *known_node_cache = NULL;
unsigned long long crm_peer_seq = 0;
gboolean crm_have_quorum = FALSE;
static gboolean crm_autoreap = TRUE;
// Flag setting and clearing for crm_node_t:flags
#define set_peer_flags(peer, flags_to_set) do { \
(peer)->flags = pcmk__set_flags_as(__func__, __LINE__, LOG_TRACE, \
"Peer", (peer)->uname, \
(peer)->flags, (flags_to_set), \
#flags_to_set); \
} while (0)
#define clear_peer_flags(peer, flags_to_clear) do { \
(peer)->flags = pcmk__clear_flags_as(__func__, __LINE__, \
LOG_TRACE, \
"Peer", (peer)->uname, \
(peer)->flags, (flags_to_clear), \
#flags_to_clear); \
} while (0)
static void update_peer_uname(crm_node_t *node, const char *uname);
static crm_node_t *find_known_node(const char *id, const char *uname);
/*!
* \internal
* \brief Get the number of Pacemaker Remote nodes that have been seen
*
* \return Number of cached Pacemaker Remote nodes
*/
unsigned int
pcmk__cluster_num_remote_nodes(void)
{
if (crm_remote_peer_cache == NULL) {
return 0U;
}
return g_hash_table_size(crm_remote_peer_cache);
}
/*!
* \internal
* \brief Get a remote node cache entry, creating it if necessary
*
* \param[in] node_name Name of remote node
*
* \return Cache entry for node on success, or \c NULL (and set \c errno)
* otherwise
*
* \note When creating a new entry, this will leave the node state undetermined.
* The caller should also call \c pcmk__update_peer_state() if the state
* is known.
* \note Because this can add and remove cache entries, callers should not
* assume any previously obtained cache entry pointers remain valid.
*/
crm_node_t *
pcmk__cluster_lookup_remote_node(const char *node_name)
{
crm_node_t *node;
char *node_name_copy = NULL;
if (node_name == NULL) {
errno = EINVAL;
return NULL;
}
/* It's theoretically possible that the node was added to the cluster peer
* cache before it was known to be a Pacemaker Remote node. Remove that
* entry unless it has a node ID, which means the name actually is
* associated with a cluster node. (@TODO return an error in that case?)
*/
node = pcmk__search_node_caches(0, node_name, pcmk__node_search_cluster);
if ((node != NULL) && (node->uuid == NULL)) {
/* node_name could be a pointer into the cache entry being removed, so
* reassign it to a copy before the original gets freed
*/
node_name_copy = strdup(node_name);
if (node_name_copy == NULL) {
errno = ENOMEM;
return NULL;
}
node_name = node_name_copy;
- reap_crm_member(0, node_name);
+ pcmk__cluster_forget_cluster_node(0, node_name);
}
/* Return existing cache entry if one exists */
node = g_hash_table_lookup(crm_remote_peer_cache, node_name);
if (node) {
free(node_name_copy);
return node;
}
/* Allocate a new entry */
node = calloc(1, sizeof(crm_node_t));
if (node == NULL) {
free(node_name_copy);
return NULL;
}
/* Populate the essential information */
set_peer_flags(node, crm_remote_node);
node->uuid = strdup(node_name);
if (node->uuid == NULL) {
free(node);
errno = ENOMEM;
free(node_name_copy);
return NULL;
}
/* Add the new entry to the cache */
g_hash_table_replace(crm_remote_peer_cache, node->uuid, node);
crm_trace("added %s to remote cache", node_name);
/* Update the entry's uname, ensuring peer status callbacks are called */
update_peer_uname(node, node_name);
free(node_name_copy);
return node;
}
/*!
* \internal
* \brief Remove a node from the Pacemaker Remote node cache
*
* \param[in] node_name Name of node to remove from cache
*
* \note The caller must be careful not to use \p node_name after calling this
* function if it might be a pointer into the cache entry being removed.
*/
void
pcmk__cluster_forget_remote_node(const char *node_name)
{
/* Do a lookup first, because node_name could be a pointer within the entry
* being removed -- we can't log it *after* removing it.
*/
if (g_hash_table_lookup(crm_remote_peer_cache, node_name) != NULL) {
crm_trace("Removing %s from Pacemaker Remote node cache", node_name);
g_hash_table_remove(crm_remote_peer_cache, node_name);
}
}
/*!
* \internal
* \brief Return node status based on a CIB status entry
*
* \param[in] node_state XML of node state
*
* \return \c CRM_NODE_LOST if \c PCMK__XA_IN_CCM is false in
* \c PCMK__XE_NODE_STATE, \c CRM_NODE_MEMBER otherwise
* \note Unlike most boolean XML attributes, this one defaults to true, for
* backward compatibility with older controllers that don't set it.
*/
static const char *
remote_state_from_cib(const xmlNode *node_state)
{
bool status = false;
if ((pcmk__xe_get_bool_attr(node_state, PCMK__XA_IN_CCM,
&status) == pcmk_rc_ok) && !status) {
return CRM_NODE_LOST;
} else {
return CRM_NODE_MEMBER;
}
}
/* user data for looping through remote node xpath searches */
struct refresh_data {
const char *field; /* XML attribute to check for node name */
gboolean has_state; /* whether to update node state based on XML */
};
/*!
* \internal
* \brief Process one pacemaker_remote node xpath search result
*
* \param[in] result XML search result
* \param[in] user_data what to look for in the XML
*/
static void
remote_cache_refresh_helper(xmlNode *result, void *user_data)
{
const struct refresh_data *data = user_data;
const char *remote = crm_element_value(result, data->field);
const char *state = NULL;
crm_node_t *node;
CRM_CHECK(remote != NULL, return);
/* Determine node's state, if the result has it */
if (data->has_state) {
state = remote_state_from_cib(result);
}
/* Check whether cache already has entry for node */
node = g_hash_table_lookup(crm_remote_peer_cache, remote);
if (node == NULL) {
/* Node is not in cache, so add a new entry for it */
node = pcmk__cluster_lookup_remote_node(remote);
CRM_ASSERT(node);
if (state) {
pcmk__update_peer_state(__func__, node, state, 0);
}
} else if (pcmk_is_set(node->flags, crm_node_dirty)) {
/* Node is in cache and hasn't been updated already, so mark it clean */
clear_peer_flags(node, crm_node_dirty);
if (state) {
pcmk__update_peer_state(__func__, node, state, 0);
}
}
}
static void
mark_dirty(gpointer key, gpointer value, gpointer user_data)
{
set_peer_flags((crm_node_t *) value, crm_node_dirty);
}
static gboolean
is_dirty(gpointer key, gpointer value, gpointer user_data)
{
return pcmk_is_set(((crm_node_t*)value)->flags, crm_node_dirty);
}
/*!
* \internal
* \brief Repopulate the remote node cache based on CIB XML
*
* \param[in] cib CIB XML to parse
*/
static void
refresh_remote_nodes(xmlNode *cib)
{
struct refresh_data data;
crm_peer_init();
/* First, we mark all existing cache entries as dirty,
* so that later we can remove any that weren't in the CIB.
* We don't empty the cache, because we need to detect changes in state.
*/
g_hash_table_foreach(crm_remote_peer_cache, mark_dirty, NULL);
/* Look for guest nodes and remote nodes in the status section */
data.field = PCMK_XA_ID;
data.has_state = TRUE;
crm_foreach_xpath_result(cib, PCMK__XP_REMOTE_NODE_STATUS,
remote_cache_refresh_helper, &data);
/* Look for guest nodes and remote nodes in the configuration section,
* because they may have just been added and not have a status entry yet.
* In that case, the cached node state will be left NULL, so that the
* peer status callback isn't called until we're sure the node started
* successfully.
*/
data.field = PCMK_XA_VALUE;
data.has_state = FALSE;
crm_foreach_xpath_result(cib, PCMK__XP_GUEST_NODE_CONFIG,
remote_cache_refresh_helper, &data);
data.field = PCMK_XA_ID;
data.has_state = FALSE;
crm_foreach_xpath_result(cib, PCMK__XP_REMOTE_NODE_CONFIG,
remote_cache_refresh_helper, &data);
/* Remove all old cache entries that weren't seen in the CIB */
g_hash_table_foreach_remove(crm_remote_peer_cache, is_dirty, NULL);
}
/*!
* \internal
* \brief Check whether a node is an active cluster node
*
* Remote nodes are never considered active. This guarantees that they can never
* become DC.
*
* \param[in] node Node to check
*
* \return \c true if the node is an active cluster node, or \c false otherwise
*/
bool
pcmk__cluster_is_node_active(const crm_node_t *node)
{
const enum cluster_type_e type = get_cluster_type();
if ((node == NULL) || pcmk_is_set(node->flags, crm_remote_node)) {
return false;
}
switch (type) {
case pcmk_cluster_corosync:
#if SUPPORT_COROSYNC
return crm_is_corosync_peer_active(node);
#else
break;
#endif // SUPPORT_COROSYNC
default:
break;
}
crm_err("Unhandled cluster type: %s", name_for_cluster_type(type));
return false;
}
/*!
* \internal
* \brief Check if a node's entry should be removed from the cluster node cache
*
* A node should be removed from the cache if it's inactive and matches another
* \c crm_node_t (the search object). The node is considered a mismatch if any
* of the following are true:
* * The search object is \c NULL.
* * The search object has an ID set and the cached node's ID does not match it.
* * The search object does not have an ID set, and the cached node's name does
* not match the search node's name. (If both names are \c NULL, it's a
* match.)
*
* Otherwise, the node is considered a match.
*
* Note that if the search object has both an ID and a name set, the name is
* ignored for matching purposes.
*
* \param[in] key Ignored
* \param[in] value \c crm_node_t object from cluster node cache
* \param[in] user_data \c crm_node_t object to match against (search object)
*
* \return \c TRUE if the node entry should be removed from \c crm_peer_cache,
* or \c FALSE otherwise
*/
static gboolean
should_forget_cluster_node(gpointer key, gpointer value, gpointer user_data)
{
crm_node_t *node = value;
crm_node_t *search = user_data;
if (search == NULL) {
return FALSE;
}
if ((search->id != 0) && (node->id != search->id)) {
return FALSE;
}
if ((search->id == 0)
&& !pcmk__str_eq(node->uname, search->uname, pcmk__str_casei)) {
// @TODO Consider name even if ID is set?
return FALSE;
}
if (pcmk__cluster_is_node_active(value)) {
return FALSE;
}
crm_info("Removing node with name %s and " PCMK_XA_ID " %u from membership "
"cache",
pcmk__s(node->uname, "(unknown)"), node->id);
return TRUE;
}
+/*!
+ * \internal
+ * \brief Remove one or more inactive nodes from the cluster node cache
+ *
+ * All inactive nodes matching \p id and \p node_name as described in
+ * \c should_forget_cluster_node documentation are removed from the cache.
+ *
+ * If \p id is 0 and \p node_name is \c NULL, all inactive nodes are removed
+ * from the cache regardless of ID and name. This differs from clearing the
+ * cache, in that entries for active nodes are preserved.
+ *
+ * \param[in] id ID of node to remove from cache (0 to ignore)
+ * \param[in] node_name Name of node to remove from cache (ignored if \p id is
+ * nonzero)
+ *
+ * \note \p node_name is not modified directly, but it will be freed if it's a
+ * pointer into a cache entry that is removed.
+ */
+void
+pcmk__cluster_forget_cluster_node(uint32_t id, const char *node_name)
+{
+ crm_node_t search = { 0, };
+ char *criterion = NULL; // For logging
+ guint matches = 0;
+
+ if (crm_peer_cache == NULL) {
+ crm_trace("Membership cache not initialized, ignoring removal request");
+ return;
+ }
+
+ search.id = id;
+ search.uname = pcmk__str_copy(node_name); // May log after original freed
+
+ if (id > 0) {
+ criterion = crm_strdup_printf(PCMK_XA_ID "=%" PRIu32, id);
+
+ } else if (node_name != NULL) {
+ criterion = crm_strdup_printf(PCMK_XA_UNAME "=%s", node_name);
+ }
+
+ matches = g_hash_table_foreach_remove(crm_peer_cache,
+ should_forget_cluster_node, &search);
+ if (matches > 0) {
+ if (criterion != NULL) {
+ crm_notice("Removed %u inactive node%s with %s from the membership "
+ "cache",
+ matches, pcmk__plural_s(matches), criterion);
+ } else {
+ crm_notice("Removed all (%u) inactive cluster nodes from the "
+ "membership cache",
+ matches);
+ }
+
+ } else {
+ crm_info("No inactive cluster nodes%s%s to remove from the membership "
+ "cache",
+ ((criterion != NULL)? " with" : ""), pcmk__s(criterion, ""));
+ }
+
+ free(search.uname);
+ free(criterion);
+}
+
/*!
* \brief Remove all peer cache entries matching a node ID and/or uname
*
* \param[in] id ID of node to remove (or 0 to ignore)
* \param[in] name Uname of node to remove (or NULL to ignore)
*
* \return Number of cache entries removed
*
* \note The caller must be careful not to use \p name after calling this
* function if it might be a pointer into the cache entry being removed.
*/
guint
reap_crm_member(uint32_t id, const char *name)
{
int matches = 0;
crm_node_t search = { 0, };
if (crm_peer_cache == NULL) {
crm_trace("Membership cache not initialized, ignoring purge request");
return 0;
}
search.id = id;
search.uname = pcmk__str_copy(name);
matches = g_hash_table_foreach_remove(crm_peer_cache,
should_forget_cluster_node, &search);
if(matches) {
crm_notice("Purged %d peer%s with " PCMK_XA_ID
"=%u%s%s from the membership cache",
matches, pcmk__plural_s(matches), search.id,
(search.uname? " and/or uname=" : ""),
(search.uname? search.uname : ""));
} else {
crm_info("No peers with " PCMK_XA_ID
"=%u%s%s to purge from the membership cache",
search.id, (search.uname? " and/or uname=" : ""),
(search.uname? search.uname : ""));
}
free(search.uname);
return matches;
}
static void
count_peer(gpointer key, gpointer value, gpointer user_data)
{
unsigned int *count = user_data;
crm_node_t *node = value;
if (pcmk__cluster_is_node_active(node)) {
*count = *count + 1;
}
}
/*!
* \internal
* \brief Get the number of active cluster nodes that have been seen
*
* Remote nodes are never considered active. This guarantees that they can never
* become DC.
*
* \return Number of active nodes in the cluster node cache
*/
unsigned int
pcmk__cluster_num_active_nodes(void)
{
unsigned int count = 0;
if (crm_peer_cache != NULL) {
g_hash_table_foreach(crm_peer_cache, count_peer, &count);
}
return count;
}
static void
destroy_crm_node(gpointer data)
{
crm_node_t *node = data;
crm_trace("Destroying entry for node %u: %s", node->id, node->uname);
free(node->uname);
free(node->state);
free(node->uuid);
free(node->expected);
free(node->conn_host);
free(node);
}
void
crm_peer_init(void)
{
if (crm_peer_cache == NULL) {
crm_peer_cache = pcmk__strikey_table(free, destroy_crm_node);
}
if (crm_remote_peer_cache == NULL) {
crm_remote_peer_cache = pcmk__strikey_table(NULL, destroy_crm_node);
}
if (known_node_cache == NULL) {
known_node_cache = pcmk__strikey_table(free, destroy_crm_node);
}
}
void
crm_peer_destroy(void)
{
if (crm_peer_cache != NULL) {
crm_trace("Destroying peer cache with %d members", g_hash_table_size(crm_peer_cache));
g_hash_table_destroy(crm_peer_cache);
crm_peer_cache = NULL;
}
if (crm_remote_peer_cache != NULL) {
crm_trace("Destroying remote peer cache with %d members",
pcmk__cluster_num_remote_nodes());
g_hash_table_destroy(crm_remote_peer_cache);
crm_remote_peer_cache = NULL;
}
if (known_node_cache != NULL) {
crm_trace("Destroying known node cache with %d members",
g_hash_table_size(known_node_cache));
g_hash_table_destroy(known_node_cache);
known_node_cache = NULL;
}
}
static void (*peer_status_callback)(enum crm_status_type, crm_node_t *,
const void *) = NULL;
/*!
* \brief Set a client function that will be called after peer status changes
*
* \param[in] dispatch Pointer to function to use as callback
*
* \note Previously, client callbacks were responsible for peer cache
* management. This is no longer the case, and client callbacks should do
* only client-specific handling. Callbacks MUST NOT add or remove entries
* in the peer caches.
*/
void
crm_set_status_callback(void (*dispatch) (enum crm_status_type, crm_node_t *, const void *))
{
peer_status_callback = dispatch;
}
/*!
* \brief Tell the library whether to automatically reap lost nodes
*
* If TRUE (the default), calling crm_update_peer_proc() will also update the
* peer state to CRM_NODE_MEMBER or CRM_NODE_LOST, and pcmk__update_peer_state()
* will reap peers whose state changes to anything other than CRM_NODE_MEMBER.
* Callers should leave this enabled unless they plan to manage the cache
* separately on their own.
*
* \param[in] autoreap TRUE to enable automatic reaping, FALSE to disable
*/
void
crm_set_autoreap(gboolean autoreap)
{
crm_autoreap = autoreap;
}
static void
dump_peer_hash(int level, const char *caller)
{
GHashTableIter iter;
const char *id = NULL;
crm_node_t *node = NULL;
g_hash_table_iter_init(&iter, crm_peer_cache);
while (g_hash_table_iter_next(&iter, (gpointer *) &id, (gpointer *) &node)) {
do_crm_log(level, "%s: Node %u/%s = %p - %s", caller, node->id, node->uname, node, id);
}
}
static gboolean
hash_find_by_data(gpointer key, gpointer value, gpointer user_data)
{
return value == user_data;
}
/*!
* \internal
* \brief Search caches for a node (cluster or Pacemaker Remote)
*
* \param[in] id If not 0, cluster node ID to search for
* \param[in] uname If not NULL, node name to search for
* \param[in] flags Group of enum pcmk__node_search_flags
*
* \return Node cache entry if found, otherwise NULL
*/
crm_node_t *
pcmk__search_node_caches(unsigned int id, const char *uname, uint32_t flags)
{
crm_node_t *node = NULL;
CRM_ASSERT(id > 0 || uname != NULL);
crm_peer_init();
if ((uname != NULL) && pcmk_is_set(flags, pcmk__node_search_remote)) {
node = g_hash_table_lookup(crm_remote_peer_cache, uname);
}
if ((node == NULL) && pcmk_is_set(flags, pcmk__node_search_cluster)) {
node = pcmk__search_cluster_node_cache(id, uname, NULL);
}
if ((node == NULL) && pcmk_is_set(flags, pcmk__node_search_known)) {
char *id_str = (id == 0)? NULL : crm_strdup_printf("%u", id);
node = find_known_node(id_str, uname);
free(id_str);
}
return node;
}
/*!
* \internal
* \brief Purge a node from cache (both cluster and Pacemaker Remote)
*
* \param[in] node_name If not NULL, purge only nodes with this name
* \param[in] node_id If not 0, purge cluster nodes only if they have this ID
*
* \note If \p node_name is NULL and \p node_id is 0, no nodes will be purged.
* If \p node_name is not NULL and \p node_id is not 0, Pacemaker Remote
* nodes that match \p node_name will be purged, and cluster nodes that
* match both \p node_name and \p node_id will be purged.
* \note The caller must be careful not to use \p node_name after calling this
* function if it might be a pointer into a cache entry being removed.
*/
void
pcmk__purge_node_from_cache(const char *node_name, uint32_t node_id)
{
char *node_name_copy = NULL;
if ((node_name == NULL) && (node_id == 0U)) {
return;
}
// Purge from Pacemaker Remote node cache
if ((node_name != NULL)
&& (g_hash_table_lookup(crm_remote_peer_cache, node_name) != NULL)) {
/* node_name could be a pointer into the cache entry being purged,
* so reassign it to a copy before the original gets freed
*/
node_name_copy = pcmk__str_copy(node_name);
node_name = node_name_copy;
crm_trace("Purging %s from Pacemaker Remote node cache", node_name);
g_hash_table_remove(crm_remote_peer_cache, node_name);
}
- reap_crm_member(node_id, node_name);
+ pcmk__cluster_forget_cluster_node(node_id, node_name);
free(node_name_copy);
}
/*!
* \internal
* \brief Search cluster node cache
*
* \param[in] id If not 0, cluster node ID to search for
* \param[in] uname If not NULL, node name to search for
* \param[in] uuid If not NULL while id is 0, node UUID instead of cluster
* node ID to search for
*
* \return Cluster node cache entry if found, otherwise NULL
*/
crm_node_t *
pcmk__search_cluster_node_cache(unsigned int id, const char *uname,
const char *uuid)
{
GHashTableIter iter;
crm_node_t *node = NULL;
crm_node_t *by_id = NULL;
crm_node_t *by_name = NULL;
CRM_ASSERT(id > 0 || uname != NULL);
crm_peer_init();
if (uname != NULL) {
g_hash_table_iter_init(&iter, crm_peer_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) &node)) {
if(node->uname && strcasecmp(node->uname, uname) == 0) {
crm_trace("Name match: %s = %p", node->uname, node);
by_name = node;
break;
}
}
}
if (id > 0) {
g_hash_table_iter_init(&iter, crm_peer_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) &node)) {
if(node->id == id) {
crm_trace("ID match: %u = %p", node->id, node);
by_id = node;
break;
}
}
} else if (uuid != NULL) {
g_hash_table_iter_init(&iter, crm_peer_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) &node)) {
if (pcmk__str_eq(node->uuid, uuid, pcmk__str_casei)) {
crm_trace("UUID match: %s = %p", node->uuid, node);
by_id = node;
break;
}
}
}
node = by_id; /* Good default */
if(by_id == by_name) {
/* Nothing to do if they match (both NULL counts) */
crm_trace("Consistent: %p for %u/%s", by_id, id, uname);
} else if(by_id == NULL && by_name) {
crm_trace("Only one: %p for %u/%s", by_name, id, uname);
if(id && by_name->id) {
dump_peer_hash(LOG_WARNING, __func__);
crm_crit("Node %u and %u share the same name '%s'",
id, by_name->id, uname);
node = NULL; /* Create a new one */
} else {
node = by_name;
}
} else if(by_name == NULL && by_id) {
crm_trace("Only one: %p for %u/%s", by_id, id, uname);
if(uname && by_id->uname) {
dump_peer_hash(LOG_WARNING, __func__);
crm_crit("Node '%s' and '%s' share the same cluster nodeid %u: assuming '%s' is correct",
uname, by_id->uname, id, uname);
}
} else if(uname && by_id->uname) {
if(pcmk__str_eq(uname, by_id->uname, pcmk__str_casei)) {
crm_notice("Node '%s' has changed its ID from %u to %u", by_id->uname, by_name->id, by_id->id);
g_hash_table_foreach_remove(crm_peer_cache, hash_find_by_data, by_name);
} else {
crm_warn("Node '%s' and '%s' share the same cluster nodeid: %u %s", by_id->uname, by_name->uname, id, uname);
dump_peer_hash(LOG_INFO, __func__);
crm_abort(__FILE__, __func__, __LINE__, "member weirdness", TRUE,
TRUE);
}
} else if(id && by_name->id) {
crm_warn("Node %u and %u share the same name: '%s'", by_id->id, by_name->id, uname);
} else {
/* Simple merge */
/* Only corosync-based clusters use node IDs. The functions that call
* pcmk__update_peer_state() and crm_update_peer_proc() only know
* nodeid, so 'by_id' is authoritative when merging.
*/
dump_peer_hash(LOG_DEBUG, __func__);
crm_info("Merging %p into %p", by_name, by_id);
g_hash_table_foreach_remove(crm_peer_cache, hash_find_by_data, by_name);
}
return node;
}
#if SUPPORT_COROSYNC
static guint
remove_conflicting_peer(crm_node_t *node)
{
int matches = 0;
GHashTableIter iter;
crm_node_t *existing_node = NULL;
if (node->id == 0 || node->uname == NULL) {
return 0;
}
if (!pcmk__corosync_has_nodelist()) {
return 0;
}
g_hash_table_iter_init(&iter, crm_peer_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) &existing_node)) {
if (existing_node->id > 0
&& existing_node->id != node->id
&& existing_node->uname != NULL
&& strcasecmp(existing_node->uname, node->uname) == 0) {
if (pcmk__cluster_is_node_active(existing_node)) {
continue;
}
crm_warn("Removing cached offline node %u/%s which has conflicting uname with %u",
existing_node->id, existing_node->uname, node->id);
g_hash_table_iter_remove(&iter);
matches++;
}
}
return matches;
}
#endif
/*!
* \brief Get a cluster node cache entry
*
* \param[in] id If not 0, cluster node ID to search for
* \param[in] uname If not NULL, node name to search for
* \param[in] uuid If not NULL while id is 0, node UUID instead of cluster
* node ID to search for
* \param[in] flags Group of enum pcmk__node_search_flags
*
* \return (Possibly newly created) cluster node cache entry
*/
/* coverity[-alloc] Memory is referenced in one or both hashtables */
crm_node_t *
pcmk__get_node(unsigned int id, const char *uname, const char *uuid,
uint32_t flags)
{
crm_node_t *node = NULL;
char *uname_lookup = NULL;
CRM_ASSERT(id > 0 || uname != NULL);
crm_peer_init();
// Check the Pacemaker Remote node cache first
if (pcmk_is_set(flags, pcmk__node_search_remote)) {
node = g_hash_table_lookup(crm_remote_peer_cache, uname);
if (node != NULL) {
return node;
}
}
if (!pcmk_is_set(flags, pcmk__node_search_cluster)) {
return NULL;
}
node = pcmk__search_cluster_node_cache(id, uname, uuid);
/* if uname wasn't provided, and find_peer did not turn up a uname based on id.
* we need to do a lookup of the node name using the id in the cluster membership. */
if ((node == NULL || node->uname == NULL) && (uname == NULL)) {
uname_lookup = get_node_name(id);
}
if (uname_lookup) {
uname = uname_lookup;
crm_trace("Inferred a name of '%s' for node %u", uname, id);
/* try to turn up the node one more time now that we know the uname. */
if (node == NULL) {
node = pcmk__search_cluster_node_cache(id, uname, uuid);
}
}
if (node == NULL) {
char *uniqueid = crm_generate_uuid();
node = pcmk__assert_alloc(1, sizeof(crm_node_t));
crm_info("Created entry %s/%p for node %s/%u (%d total)",
uniqueid, node, uname, id, 1 + g_hash_table_size(crm_peer_cache));
g_hash_table_replace(crm_peer_cache, uniqueid, node);
}
if(id > 0 && uname && (node->id == 0 || node->uname == NULL)) {
crm_info("Node %u is now known as %s", id, uname);
}
if(id > 0 && node->id == 0) {
node->id = id;
}
if (uname && (node->uname == NULL)) {
update_peer_uname(node, uname);
}
if(node->uuid == NULL) {
if (uuid == NULL) {
uuid = crm_peer_uuid(node);
}
if (uuid) {
crm_info("Node %u has uuid %s", id, uuid);
} else {
crm_info("Cannot obtain a UUID for node %u/%s", id, node->uname);
}
}
free(uname_lookup);
return node;
}
/*!
* \internal
* \brief Update a node's uname
*
* \param[in,out] node Node object to update
* \param[in] uname New name to set
*
* \note This function should not be called within a peer cache iteration,
* because in some cases it can remove conflicting cache entries,
* which would invalidate the iterator.
*/
static void
update_peer_uname(crm_node_t *node, const char *uname)
{
CRM_CHECK(uname != NULL,
crm_err("Bug: can't update node name without name"); return);
CRM_CHECK(node != NULL,
crm_err("Bug: can't update node name to %s without node", uname);
return);
if (pcmk__str_eq(uname, node->uname, pcmk__str_casei)) {
crm_debug("Node uname '%s' did not change", uname);
return;
}
for (const char *c = uname; *c; ++c) {
if ((*c >= 'A') && (*c <= 'Z')) {
crm_warn("Node names with capitals are discouraged, consider changing '%s'",
uname);
break;
}
}
pcmk__str_update(&node->uname, uname);
if (peer_status_callback != NULL) {
peer_status_callback(crm_status_uname, node, NULL);
}
#if SUPPORT_COROSYNC
if (is_corosync_cluster() && !pcmk_is_set(node->flags, crm_remote_node)) {
remove_conflicting_peer(node);
}
#endif
}
/*!
* \internal
* \brief Get log-friendly string equivalent of a process flag
*
* \param[in] proc Process flag
*
* \return Log-friendly string equivalent of \p proc
*/
static inline const char *
proc2text(enum crm_proc_flag proc)
{
const char *text = "unknown";
switch (proc) {
case crm_proc_none:
text = "none";
break;
case crm_proc_based:
text = "pacemaker-based";
break;
case crm_proc_controld:
text = "pacemaker-controld";
break;
case crm_proc_schedulerd:
text = "pacemaker-schedulerd";
break;
case crm_proc_execd:
text = "pacemaker-execd";
break;
case crm_proc_attrd:
text = "pacemaker-attrd";
break;
case crm_proc_fenced:
text = "pacemaker-fenced";
break;
case crm_proc_cpg:
text = "corosync-cpg";
break;
}
return text;
}
/*!
* \internal
* \brief Update a node's process information (and potentially state)
*
* \param[in] source Caller's function name (for log messages)
* \param[in,out] node Node object to update
* \param[in] flag Bitmask of new process information
* \param[in] status node status (online, offline, etc.)
*
* \return NULL if any node was reaped from peer caches, value of node otherwise
*
* \note If this function returns NULL, the supplied node object was likely
* freed and should not be used again. This function should not be
* called within a cache iteration if reaping is possible, otherwise
* reaping could invalidate the iterator.
*/
crm_node_t *
crm_update_peer_proc(const char *source, crm_node_t * node, uint32_t flag, const char *status)
{
uint32_t last = 0;
gboolean changed = FALSE;
CRM_CHECK(node != NULL, crm_err("%s: Could not set %s to %s for NULL",
source, proc2text(flag), status);
return NULL);
/* Pacemaker doesn't spawn processes on remote nodes */
if (pcmk_is_set(node->flags, crm_remote_node)) {
return node;
}
last = node->processes;
if (status == NULL) {
node->processes = flag;
if (node->processes != last) {
changed = TRUE;
}
} else if (pcmk__str_eq(status, PCMK_VALUE_ONLINE, pcmk__str_casei)) {
if ((node->processes & flag) != flag) {
node->processes = pcmk__set_flags_as(__func__, __LINE__,
LOG_TRACE, "Peer process",
node->uname, node->processes,
flag, "processes");
changed = TRUE;
}
} else if (node->processes & flag) {
node->processes = pcmk__clear_flags_as(__func__, __LINE__,
LOG_TRACE, "Peer process",
node->uname, node->processes,
flag, "processes");
changed = TRUE;
}
if (changed) {
if (status == NULL && flag <= crm_proc_none) {
crm_info("%s: Node %s[%u] - all processes are now offline", source, node->uname,
node->id);
} else {
crm_info("%s: Node %s[%u] - %s is now %s", source, node->uname, node->id,
proc2text(flag), status);
}
if (pcmk_is_set(node->processes, crm_get_cluster_proc())) {
node->when_online = time(NULL);
} else {
node->when_online = 0;
}
/* Call the client callback first, then update the peer state,
* in case the node will be reaped
*/
if (peer_status_callback != NULL) {
peer_status_callback(crm_status_processes, node, &last);
}
/* The client callback shouldn't touch the peer caches,
* but as a safety net, bail if the peer cache was destroyed.
*/
if (crm_peer_cache == NULL) {
return NULL;
}
if (crm_autoreap) {
const char *peer_state = NULL;
if (pcmk_is_set(node->processes, crm_get_cluster_proc())) {
peer_state = CRM_NODE_MEMBER;
} else {
peer_state = CRM_NODE_LOST;
}
node = pcmk__update_peer_state(__func__, node, peer_state, 0);
}
} else {
crm_trace("%s: Node %s[%u] - %s is unchanged (%s)", source, node->uname, node->id,
proc2text(flag), status);
}
return node;
}
/*!
* \internal
* \brief Update a cluster node cache entry's expected join state
*
* \param[in] source Caller's function name (for logging)
* \param[in,out] node Node to update
* \param[in] expected Node's new join state
*/
void
pcmk__update_peer_expected(const char *source, crm_node_t *node,
const char *expected)
{
char *last = NULL;
gboolean changed = FALSE;
CRM_CHECK(node != NULL, crm_err("%s: Could not set 'expected' to %s", source, expected);
return);
/* Remote nodes don't participate in joins */
if (pcmk_is_set(node->flags, crm_remote_node)) {
return;
}
last = node->expected;
if (expected != NULL && !pcmk__str_eq(node->expected, expected, pcmk__str_casei)) {
node->expected = strdup(expected);
changed = TRUE;
}
if (changed) {
crm_info("%s: Node %s[%u] - expected state is now %s (was %s)", source, node->uname, node->id,
expected, last);
free(last);
} else {
crm_trace("%s: Node %s[%u] - expected state is unchanged (%s)", source, node->uname,
node->id, expected);
}
}
/*!
* \internal
* \brief Update a node's state and membership information
*
* \param[in] source Caller's function name (for log messages)
* \param[in,out] node Node object to update
* \param[in] state Node's new state
* \param[in] membership Node's new membership ID
* \param[in,out] iter If not NULL, pointer to node's peer cache iterator
*
* \return NULL if any node was reaped, value of node otherwise
*
* \note If this function returns NULL, the supplied node object was likely
* freed and should not be used again. This function may be called from
* within a peer cache iteration if the iterator is supplied.
*/
static crm_node_t *
update_peer_state_iter(const char *source, crm_node_t *node, const char *state,
uint64_t membership, GHashTableIter *iter)
{
gboolean is_member;
CRM_CHECK(node != NULL,
crm_err("Could not set state for unknown host to %s"
CRM_XS " source=%s", state, source);
return NULL);
is_member = pcmk__str_eq(state, CRM_NODE_MEMBER, pcmk__str_casei);
if (is_member) {
node->when_lost = 0;
if (membership) {
node->last_seen = membership;
}
}
if (state && !pcmk__str_eq(node->state, state, pcmk__str_casei)) {
char *last = node->state;
if (is_member) {
node->when_member = time(NULL);
} else {
node->when_member = 0;
}
node->state = strdup(state);
crm_notice("Node %s state is now %s " CRM_XS
" nodeid=%u previous=%s source=%s", node->uname, state,
node->id, (last? last : "unknown"), source);
if (peer_status_callback != NULL) {
peer_status_callback(crm_status_nstate, node, last);
}
free(last);
if (crm_autoreap && !is_member
&& !pcmk_is_set(node->flags, crm_remote_node)) {
/* We only autoreap from the peer cache, not the remote peer cache,
* because the latter should be managed only by
* refresh_remote_nodes().
*/
if(iter) {
crm_notice("Purged 1 peer with " PCMK_XA_ID
"=%u and/or uname=%s from the membership cache",
node->id, node->uname);
g_hash_table_iter_remove(iter);
} else {
- reap_crm_member(node->id, node->uname);
+ pcmk__cluster_forget_cluster_node(node->id, node->uname);
}
node = NULL;
}
} else {
crm_trace("Node %s state is unchanged (%s) " CRM_XS
" nodeid=%u source=%s", node->uname, state, node->id, source);
}
return node;
}
/*!
* \brief Update a node's state and membership information
*
* \param[in] source Caller's function name (for log messages)
* \param[in,out] node Node object to update
* \param[in] state Node's new state
* \param[in] membership Node's new membership ID
*
* \return NULL if any node was reaped, value of node otherwise
*
* \note If this function returns NULL, the supplied node object was likely
* freed and should not be used again. This function should not be
* called within a cache iteration if reaping is possible,
* otherwise reaping could invalidate the iterator.
*/
crm_node_t *
pcmk__update_peer_state(const char *source, crm_node_t *node,
const char *state, uint64_t membership)
{
return update_peer_state_iter(source, node, state, membership, NULL);
}
/*!
* \internal
* \brief Reap all nodes from cache whose membership information does not match
*
* \param[in] membership Membership ID of nodes to keep
*/
void
pcmk__reap_unseen_nodes(uint64_t membership)
{
GHashTableIter iter;
crm_node_t *node = NULL;
crm_trace("Reaping unseen nodes...");
g_hash_table_iter_init(&iter, crm_peer_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *)&node)) {
if (node->last_seen != membership) {
if (node->state) {
/*
* Calling update_peer_state_iter() allows us to
* remove the node from crm_peer_cache without
* invalidating our iterator
*/
update_peer_state_iter(__func__, node, CRM_NODE_LOST,
membership, &iter);
} else {
crm_info("State of node %s[%u] is still unknown",
node->uname, node->id);
}
}
}
}
static crm_node_t *
find_known_node(const char *id, const char *uname)
{
GHashTableIter iter;
crm_node_t *node = NULL;
crm_node_t *by_id = NULL;
crm_node_t *by_name = NULL;
if (uname) {
g_hash_table_iter_init(&iter, known_node_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) &node)) {
if (node->uname && strcasecmp(node->uname, uname) == 0) {
crm_trace("Name match: %s = %p", node->uname, node);
by_name = node;
break;
}
}
}
if (id) {
g_hash_table_iter_init(&iter, known_node_cache);
while (g_hash_table_iter_next(&iter, NULL, (gpointer *) &node)) {
if(strcasecmp(node->uuid, id) == 0) {
crm_trace("ID match: %s= %p", id, node);
by_id = node;
break;
}
}
}
node = by_id; /* Good default */
if (by_id == by_name) {
/* Nothing to do if they match (both NULL counts) */
crm_trace("Consistent: %p for %s/%s", by_id, id, uname);
} else if (by_id == NULL && by_name) {
crm_trace("Only one: %p for %s/%s", by_name, id, uname);
if (id) {
node = NULL;
} else {
node = by_name;
}
} else if (by_name == NULL && by_id) {
crm_trace("Only one: %p for %s/%s", by_id, id, uname);
if (uname) {
node = NULL;
}
} else if (uname && by_id->uname
&& pcmk__str_eq(uname, by_id->uname, pcmk__str_casei)) {
/* Multiple nodes have the same uname in the CIB.
* Return by_id. */
} else if (id && by_name->uuid
&& pcmk__str_eq(id, by_name->uuid, pcmk__str_casei)) {
/* Multiple nodes have the same id in the CIB.
* Return by_name. */
node = by_name;
} else {
node = NULL;
}
if (node == NULL) {
crm_debug("Couldn't find node%s%s%s%s",
id? " " : "",
id? id : "",
uname? " with name " : "",
uname? uname : "");
}
return node;
}
static void
known_node_cache_refresh_helper(xmlNode *xml_node, void *user_data)
{
const char *id = crm_element_value(xml_node, PCMK_XA_ID);
const char *uname = crm_element_value(xml_node, PCMK_XA_UNAME);
crm_node_t * node = NULL;
CRM_CHECK(id != NULL && uname !=NULL, return);
node = find_known_node(id, uname);
if (node == NULL) {
char *uniqueid = crm_generate_uuid();
node = pcmk__assert_alloc(1, sizeof(crm_node_t));
node->uname = pcmk__str_copy(uname);
node->uuid = pcmk__str_copy(id);
g_hash_table_replace(known_node_cache, uniqueid, node);
} else if (pcmk_is_set(node->flags, crm_node_dirty)) {
pcmk__str_update(&node->uname, uname);
/* Node is in cache and hasn't been updated already, so mark it clean */
clear_peer_flags(node, crm_node_dirty);
}
}
static void
refresh_known_node_cache(xmlNode *cib)
{
crm_peer_init();
g_hash_table_foreach(known_node_cache, mark_dirty, NULL);
crm_foreach_xpath_result(cib, PCMK__XP_MEMBER_NODE_CONFIG,
known_node_cache_refresh_helper, NULL);
/* Remove all old cache entries that weren't seen in the CIB */
g_hash_table_foreach_remove(known_node_cache, is_dirty, NULL);
}
void
pcmk__refresh_node_caches_from_cib(xmlNode *cib)
{
refresh_remote_nodes(cib);
refresh_known_node_cache(cib);
}
// Deprecated functions kept only for backward API compatibility
// LCOV_EXCL_START
#include <crm/cluster/compat.h>
int
crm_terminate_member(int nodeid, const char *uname, void *unused)
{
return stonith_api_kick(nodeid, uname, 120, TRUE);
}
int
crm_terminate_member_no_mainloop(int nodeid, const char *uname, int *connection)
{
return stonith_api_kick(nodeid, uname, 120, TRUE);
}
crm_node_t *
crm_get_peer(unsigned int id, const char *uname)
{
return pcmk__get_node(id, uname, NULL, pcmk__node_search_cluster);
}
crm_node_t *
crm_get_peer_full(unsigned int id, const char *uname, int flags)
{
return pcmk__get_node(id, uname, NULL, flags);
}
int
crm_remote_peer_cache_size(void)
{
unsigned int count = pcmk__cluster_num_remote_nodes();
return QB_MIN(count, INT_MAX);
}
void
crm_remote_peer_cache_refresh(xmlNode *cib)
{
refresh_remote_nodes(cib);
}
crm_node_t *
crm_remote_peer_get(const char *node_name)
{
return pcmk__cluster_lookup_remote_node(node_name);
}
void
crm_remote_peer_cache_remove(const char *node_name)
{
pcmk__cluster_forget_remote_node(node_name);
}
gboolean
crm_is_peer_active(const crm_node_t * node)
{
return pcmk__cluster_is_node_active(node);
}
guint
crm_active_peers(void)
{
return pcmk__cluster_num_active_nodes();
}
// LCOV_EXCL_STOP
// End deprecated API