summaryrefslogtreecommitdiffstats
path: root/drivers/char/ipmi
diff options
context:
space:
mode:
authorCorey Minyard <cminyard@mvista.com>2011-12-19 17:12:02 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2011-12-20 10:25:04 -0800
commitb75d91f7ca513f0a4d0d1ad0942fb90cf5a2bc88 (patch)
tree3ed9062637e769ab8bd89748baf2b167244bbda8 /drivers/char/ipmi
parentff05b6f7ae762b6eb464183eec994b28ea09f6dd (diff)
downloadop-kernel-dev-b75d91f7ca513f0a4d0d1ad0942fb90cf5a2bc88.zip
op-kernel-dev-b75d91f7ca513f0a4d0d1ad0942fb90cf5a2bc88.tar.gz
ipmi_watchdog: restore settings when BMC reset
If the BMC gets reset, it will return 0x80 response errors. In less than a week # grep "Error 80 on cmd 22" /var/log/kernel |wc -l 378681 In this case, it is probably a good idea to restore the IPMI settings. Signed-off-by: Corey Minyard <cminyard@mvista.com> Tested-by: Arkadiusz Miśkiewicz <a.miskiewicz@gmail.com> Reported-by: Arkadiusz Miśkiewicz <a.miskiewicz@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'drivers/char/ipmi')
-rw-r--r--drivers/char/ipmi/ipmi_watchdog.c41
1 files changed, 38 insertions, 3 deletions
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index c2917ffa..34767a6 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -139,6 +139,8 @@
#define IPMI_WDOG_SET_TIMER 0x24
#define IPMI_WDOG_GET_TIMER 0x25
+#define IPMI_WDOG_TIMER_NOT_INIT_RESP 0x80
+
/* These are here until the real ones get into the watchdog.h interface. */
#ifndef WDIOC_GETTIMEOUT
#define WDIOC_GETTIMEOUT _IOW(WATCHDOG_IOCTL_BASE, 20, int)
@@ -596,6 +598,7 @@ static int ipmi_heartbeat(void)
struct kernel_ipmi_msg msg;
int rv;
struct ipmi_system_interface_addr addr;
+ int timeout_retries = 0;
if (ipmi_ignore_heartbeat)
return 0;
@@ -616,6 +619,7 @@ static int ipmi_heartbeat(void)
mutex_lock(&heartbeat_lock);
+restart:
atomic_set(&heartbeat_tofree, 2);
/*
@@ -653,7 +657,33 @@ static int ipmi_heartbeat(void)
/* Wait for the heartbeat to be sent. */
wait_for_completion(&heartbeat_wait);
- if (heartbeat_recv_msg.msg.data[0] != 0) {
+ if (heartbeat_recv_msg.msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP) {
+ timeout_retries++;
+ if (timeout_retries > 3) {
+ printk(KERN_ERR PFX ": Unable to restore the IPMI"
+ " watchdog's settings, giving up.\n");
+ rv = -EIO;
+ goto out_unlock;
+ }
+
+ /*
+ * The timer was not initialized, that means the BMC was
+ * probably reset and lost the watchdog information. Attempt
+ * to restore the timer's info. Note that we still hold
+ * the heartbeat lock, to keep a heartbeat from happening
+ * in this process, so must say no heartbeat to avoid a
+ * deadlock on this mutex.
+ */
+ rv = ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
+ if (rv) {
+ printk(KERN_ERR PFX ": Unable to send the command to"
+ " set the watchdog's settings, giving up.\n");
+ goto out_unlock;
+ }
+
+ /* We might need a new heartbeat, so do it now */
+ goto restart;
+ } else if (heartbeat_recv_msg.msg.data[0] != 0) {
/*
* Got an error in the heartbeat response. It was already
* reported in ipmi_wdog_msg_handler, but we should return
@@ -662,6 +692,7 @@ static int ipmi_heartbeat(void)
rv = -EINVAL;
}
+out_unlock:
mutex_unlock(&heartbeat_lock);
return rv;
@@ -922,11 +953,15 @@ static struct miscdevice ipmi_wdog_miscdev = {
static void ipmi_wdog_msg_handler(struct ipmi_recv_msg *msg,
void *handler_data)
{
- if (msg->msg.data[0] != 0) {
+ if (msg->msg.cmd == IPMI_WDOG_RESET_TIMER &&
+ msg->msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP)
+ printk(KERN_INFO PFX "response: The IPMI controller appears"
+ " to have been reset, will attempt to reinitialize"
+ " the watchdog timer\n");
+ else if (msg->msg.data[0] != 0)
printk(KERN_ERR PFX "response: Error %x on cmd %x\n",
msg->msg.data[0],
msg->msg.cmd);
- }
ipmi_free_recv_msg(msg);
}
OpenPOWER on IntegriCloud