aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/char/ipmi/ipmi_watchdog.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/char/ipmi/ipmi_watchdog.c')
-rw-r--r--drivers/char/ipmi/ipmi_watchdog.c76
1 files changed, 50 insertions, 26 deletions
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 320668f..34767a6 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -52,7 +52,7 @@
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/delay.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#ifdef CONFIG_X86
/*
@@ -65,6 +65,7 @@
* mechanism for it at that time.
*/
#include <asm/kdebug.h>
+#include <asm/nmi.h>
#define HAVE_DIE_NMI
#endif
@@ -138,6 +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)
@@ -595,6 +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;
@@ -615,6 +619,7 @@ static int ipmi_heartbeat(void)
mutex_lock(&heartbeat_lock);
+restart:
atomic_set(&heartbeat_tofree, 2);
/*
@@ -652,7 +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
@@ -661,6 +692,7 @@ static int ipmi_heartbeat(void)
rv = -EINVAL;
}
+out_unlock:
mutex_unlock(&heartbeat_lock);
return rv;
@@ -921,11 +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);
}
@@ -1077,17 +1113,8 @@ static void ipmi_unregister_watchdog(int ipmi_intf)
#ifdef HAVE_DIE_NMI
static int
-ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
+ipmi_nmi(unsigned int val, struct pt_regs *regs)
{
- struct die_args *args = data;
-
- if (val != DIE_NMIUNKNOWN)
- return NOTIFY_OK;
-
- /* Hack, if it's a memory or I/O error, ignore it. */
- if (args->err & 0xc0)
- return NOTIFY_OK;
-
/*
* If we get here, it's an NMI that's not a memory or I/O
* error. We can't truly tell if it's from IPMI or not
@@ -1097,15 +1124,15 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
if (testing_nmi) {
testing_nmi = 2;
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
/* If we are not expecting a timeout, ignore it. */
if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE)
- return NOTIFY_OK;
+ return NMI_DONE;
if (preaction_val != WDOG_PRETIMEOUT_NMI)
- return NOTIFY_OK;
+ return NMI_DONE;
/*
* If no one else handled the NMI, we assume it was the IPMI
@@ -1120,12 +1147,8 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
panic(PFX "pre-timeout");
}
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
-
-static struct notifier_block ipmi_nmi_handler = {
- .notifier_call = ipmi_nmi
-};
#endif
static int wdog_reboot_handler(struct notifier_block *this,
@@ -1290,7 +1313,8 @@ static void check_parms(void)
}
}
if (do_nmi && !nmi_handler_registered) {
- rv = register_die_notifier(&ipmi_nmi_handler);
+ rv = register_nmi_handler(NMI_UNKNOWN, ipmi_nmi, 0,
+ "ipmi");
if (rv) {
printk(KERN_WARNING PFX
"Can't register nmi handler\n");
@@ -1298,7 +1322,7 @@ static void check_parms(void)
} else
nmi_handler_registered = 1;
} else if (!do_nmi && nmi_handler_registered) {
- unregister_die_notifier(&ipmi_nmi_handler);
+ unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
nmi_handler_registered = 0;
}
#endif
@@ -1336,7 +1360,7 @@ static int __init ipmi_wdog_init(void)
if (rv) {
#ifdef HAVE_DIE_NMI
if (nmi_handler_registered)
- unregister_die_notifier(&ipmi_nmi_handler);
+ unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
#endif
atomic_notifier_chain_unregister(&panic_notifier_list,
&wdog_panic_notifier);
@@ -1357,7 +1381,7 @@ static void __exit ipmi_wdog_exit(void)
#ifdef HAVE_DIE_NMI
if (nmi_handler_registered)
- unregister_die_notifier(&ipmi_nmi_handler);
+ unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
#endif
atomic_notifier_chain_unregister(&panic_notifier_list,