aboutsummaryrefslogtreecommitdiff
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.c112
1 files changed, 63 insertions, 49 deletions
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 320668f4c3a..37b8be7cba9 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
@@ -138,19 +139,10 @@
#define IPMI_WDOG_SET_TIMER 0x24
#define IPMI_WDOG_GET_TIMER 0x25
-/* 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)
-#endif
-#ifndef WDIOC_SET_PRETIMEOUT
-#define WDIOC_SET_PRETIMEOUT _IOW(WATCHDOG_IOCTL_BASE, 21, int)
-#endif
-#ifndef WDIOC_GET_PRETIMEOUT
-#define WDIOC_GET_PRETIMEOUT _IOW(WATCHDOG_IOCTL_BASE, 22, int)
-#endif
+#define IPMI_WDOG_TIMER_NOT_INIT_RESP 0x80
static DEFINE_MUTEX(ipmi_watchdog_mutex);
-static int nowayout = WATCHDOG_NOWAYOUT;
+static bool nowayout = WATCHDOG_NOWAYOUT;
static ipmi_user_t watchdog_user;
static int watchdog_ifnum;
@@ -317,7 +309,7 @@ module_param(start_now, int, 0444);
MODULE_PARM_DESC(start_now, "Set to 1 to start the watchdog as"
"soon as the driver is loaded.");
-module_param(nowayout, int, 0644);
+module_param(nowayout, bool, 0644);
MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
"(default=CONFIG_WATCHDOG_NOWAYOUT)");
@@ -517,6 +509,7 @@ static void panic_halt_ipmi_heartbeat(void)
msg.cmd = IPMI_WDOG_RESET_TIMER;
msg.data = NULL;
msg.data_len = 0;
+ atomic_add(2, &panic_done_count);
rv = ipmi_request_supply_msgs(watchdog_user,
(struct ipmi_addr *) &addr,
0,
@@ -525,8 +518,8 @@ static void panic_halt_ipmi_heartbeat(void)
&panic_halt_heartbeat_smi_msg,
&panic_halt_heartbeat_recv_msg,
1);
- if (!rv)
- atomic_add(2, &panic_done_count);
+ if (rv)
+ atomic_sub(2, &panic_done_count);
}
static struct ipmi_smi_msg panic_halt_smi_msg = {
@@ -550,16 +543,18 @@ static void panic_halt_ipmi_set_timeout(void)
/* Wait for the messages to be free. */
while (atomic_read(&panic_done_count) != 0)
ipmi_poll_interface(watchdog_user);
+ atomic_add(2, &panic_done_count);
rv = i_ipmi_set_timeout(&panic_halt_smi_msg,
&panic_halt_recv_msg,
&send_heartbeat_now);
- if (!rv) {
- atomic_add(2, &panic_done_count);
- if (send_heartbeat_now)
- panic_halt_ipmi_heartbeat();
- } else
+ if (rv) {
+ atomic_sub(2, &panic_done_count);
printk(KERN_WARNING PFX
"Unable to extend the watchdog timeout.");
+ } else {
+ if (send_heartbeat_now)
+ panic_halt_ipmi_heartbeat();
+ }
while (atomic_read(&panic_done_count) != 0)
ipmi_poll_interface(watchdog_user);
}
@@ -595,6 +590,7 @@ 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 +611,7 @@ static int ipmi_heartbeat(void)
mutex_lock(&heartbeat_lock);
+restart:
atomic_set(&heartbeat_tofree, 2);
/*
@@ -652,7 +649,33 @@ 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 +684,7 @@ static int ipmi_heartbeat(void)
rv = -EINVAL;
}
+out_unlock:
mutex_unlock(&heartbeat_lock);
return rv;
@@ -697,7 +721,6 @@ static int ipmi_ioctl(struct file *file,
return -EFAULT;
return 0;
- case WDIOC_SET_PRETIMEOUT:
case WDIOC_SETPRETIMEOUT:
i = copy_from_user(&val, argp, sizeof(int));
if (i)
@@ -705,7 +728,6 @@ static int ipmi_ioctl(struct file *file,
pretimeout = val;
return ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
- case WDIOC_GET_PRETIMEOUT:
case WDIOC_GETPRETIMEOUT:
i = copy_to_user(argp, &pretimeout, sizeof(pretimeout));
if (i)
@@ -921,11 +943,15 @@ 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 +1103,8 @@ 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 +1114,15 @@ 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 +1137,8 @@ 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,
@@ -1141,7 +1154,7 @@ static int wdog_reboot_handler(struct notifier_block *this,
if (code == SYS_POWER_OFF || code == SYS_HALT) {
/* Disable the WDT if we are shutting down. */
ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
- panic_halt_ipmi_set_timeout();
+ ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
} else if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) {
/* Set a long timer to let the reboot happens, but
reboot if it hangs, but only if the watchdog
@@ -1149,7 +1162,7 @@ static int wdog_reboot_handler(struct notifier_block *this,
timeout = 120;
pretimeout = 0;
ipmi_watchdog_state = WDOG_TIMEOUT_RESET;
- panic_halt_ipmi_set_timeout();
+ ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
}
}
return NOTIFY_OK;
@@ -1290,7 +1303,8 @@ 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 +1312,7 @@ 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 +1350,7 @@ 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 +1371,7 @@ 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,
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-13 20:04:53 +0000