Commit 12ba6c99 authored by Mike Travis's avatar Mike Travis Committed by Ingo Molnar

x86/UV: Add kdump to UV NMI handler

If a system has hung and it no longer responds to external
events, this patch adds the capability of doing a standard kdump
and system reboot then triggered by the system NMI command.

It is enabled when the nmi action is changed to "kdump" and the
kernel is built with CONFIG_KEXEC enabled.
Signed-off-by: default avatarMike Travis <travis@sgi.com>
Reviewed-by: default avatarDimitri Sivanich <sivanich@sgi.com>
Reviewed-by: default avatarHedi Berriche <hedi@sgi.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Jason Wessel <jason.wessel@windriver.com>
Link: http://lkml.kernel.org/r/20130923212500.660567460@asylum.americas.sgi.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 3c121d9a
...@@ -21,6 +21,7 @@ ...@@ -21,6 +21,7 @@
#include <linux/cpu.h> #include <linux/cpu.h>
#include <linux/delay.h> #include <linux/delay.h>
#include <linux/kexec.h>
#include <linux/module.h> #include <linux/module.h>
#include <linux/nmi.h> #include <linux/nmi.h>
#include <linux/sched.h> #include <linux/sched.h>
...@@ -70,6 +71,7 @@ static atomic_t uv_in_nmi; ...@@ -70,6 +71,7 @@ static atomic_t uv_in_nmi;
static atomic_t uv_nmi_cpu = ATOMIC_INIT(-1); static atomic_t uv_nmi_cpu = ATOMIC_INIT(-1);
static atomic_t uv_nmi_cpus_in_nmi = ATOMIC_INIT(-1); static atomic_t uv_nmi_cpus_in_nmi = ATOMIC_INIT(-1);
static atomic_t uv_nmi_slave_continue; static atomic_t uv_nmi_slave_continue;
static atomic_t uv_nmi_kexec_failed;
static cpumask_var_t uv_nmi_cpu_mask; static cpumask_var_t uv_nmi_cpu_mask;
/* Values for uv_nmi_slave_continue */ /* Values for uv_nmi_slave_continue */
...@@ -143,6 +145,7 @@ module_param_named(retry_count, uv_nmi_retry_count, int, 0644); ...@@ -143,6 +145,7 @@ module_param_named(retry_count, uv_nmi_retry_count, int, 0644);
* Valid NMI Actions: * Valid NMI Actions:
* "dump" - dump process stack for each cpu * "dump" - dump process stack for each cpu
* "ips" - dump IP info for each cpu * "ips" - dump IP info for each cpu
* "kdump" - do crash dump
*/ */
static char uv_nmi_action[8] = "dump"; static char uv_nmi_action[8] = "dump";
module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644); module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644);
...@@ -496,6 +499,40 @@ static void uv_nmi_touch_watchdogs(void) ...@@ -496,6 +499,40 @@ static void uv_nmi_touch_watchdogs(void)
touch_nmi_watchdog(); touch_nmi_watchdog();
} }
#if defined(CONFIG_KEXEC)
static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
{
/* Call crash to dump system state */
if (master) {
pr_emerg("UV: NMI executing crash_kexec on CPU%d\n", cpu);
crash_kexec(regs);
pr_emerg("UV: crash_kexec unexpectedly returned, ");
if (!kexec_crash_image) {
pr_cont("crash kernel not loaded\n");
atomic_set(&uv_nmi_kexec_failed, 1);
uv_nmi_sync_exit(1);
return;
}
pr_cont("kexec busy, stalling cpus while waiting\n");
}
/* If crash exec fails the slaves should return, otherwise stall */
while (atomic_read(&uv_nmi_kexec_failed) == 0)
mdelay(10);
/* Crash kernel most likely not loaded, return in an orderly fashion */
uv_nmi_sync_exit(0);
}
#else /* !CONFIG_KEXEC */
static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
{
if (master)
pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n");
}
#endif /* !CONFIG_KEXEC */
/* /*
* UV NMI handler * UV NMI handler
*/ */
...@@ -517,6 +554,10 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) ...@@ -517,6 +554,10 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
/* Indicate we are the first CPU into the NMI handler */ /* Indicate we are the first CPU into the NMI handler */
master = (atomic_read(&uv_nmi_cpu) == cpu); master = (atomic_read(&uv_nmi_cpu) == cpu);
/* If NMI action is "kdump", then attempt to do it */
if (uv_nmi_action_is("kdump"))
uv_nmi_kdump(cpu, master, regs);
/* Pause as all cpus enter the NMI handler */ /* Pause as all cpus enter the NMI handler */
uv_nmi_wait(master); uv_nmi_wait(master);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment