The patch titled
Subject: ipmi_watchdog: restore settings when BMC reset
has been added to the -mm tree. Its filename is
ipmi_watchdog-restore-settings-when-bmc-reset.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
From: Corey Minyard <cminyard@xxxxxxxxxx>
Subject: 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@xxxxxxxxxx>
Tested-by: Arkadiusz MiÅ?kiewicz <a.miskiewicz@xxxxxxxxx>
Reported-by: Arkadiusz MiÅ?kiewicz <a.miskiewicz@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/char/ipmi/ipmi_watchdog.c | 41 +++++++++++++++++++++++++---
1 file changed, 38 insertions(+), 3 deletions(-)
diff -puN drivers/char/ipmi/ipmi_watchdog.c~ipmi_watchdog-restore-settings-when-bmc-reset drivers/char/ipmi/ipmi_watchdog.c
--- a/drivers/char/ipmi/ipmi_watchdog.c~ipmi_watchdog-restore-settings-when-bmc-reset
+++ a/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_miscd
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);
}
_
Subject: Subject: ipmi_watchdog: restore settings when BMC reset
Patches currently in -mm which might be from cminyard@xxxxxxxxxx are
ipmi_watchdog-restore-settings-when-bmc-reset.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
