lkml.org 
[lkml]   [2011]   [Nov]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: ipmi_watchdog: IPMI Watchdog: response: Error 80 on cmd 22
On Sat, Nov 19, 2011 at 02:22:17PM +0100, Arkadiusz Miśkiewicz wrote:
>
> Hello,
>
> I have few machines where ipmi_watchdog (from 3.0.9 kernel currently)
> reports after some time:
>
> IPMI Watchdog: response: Error 80 on cmd 22
>
> In less than a week
> # grep "Error 80 on cmd 22" /var/log/kernel |wc -l
> 378681
>
> #define IPMI_WDOG_RESET_TIMER 0x22
> but no idea what error 80 is.

That error is a command-specific error, and it means: Attempt to start
un-initialized watchdog

I'm guessing that the IPMI controller gets reset somehow and then thinks
it's watchdog timer is not initialized, and thus the reset command causes
an issue.

A fix should be pretty easy, if you get a 0x80 response from a reset,
re-initialize the timer.

Can you try the following patch?

From 4467601416e23740fc940c31b1fffacbcb69b4a0 Mon Sep 17 00:00:00 2001
From: Corey Minyard <cminyard@mvista.com>
Date: Mon, 21 Nov 2011 14:26:20 -0600
Subject: [PATCH] ipmi_watchdog: Restore settings when BMC reset

If the BMC gets reset, it will return 0x80 response errors. In this case,
it is probably a good idea to restore the IPMI settings.
---
drivers/char/ipmi/ipmi_watchdog.c | 41 ++++++++++++++++++++++++++++++++++--
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);
}
--
1.7.4.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2011-11-21 22:39    [W:0.048 / U:0.052 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site