This patch introduces a new sysctl:
/proc/sys/kernel/panic_on_io_nmi
which defaults to 0 (off).
When enabled, the kernel panics when the kernel receives an NMI
caused by an IO error.
The IO error triggered NMI indicates a serious system
condition, which could result in IO data corruption. Rather
than contiuing, panicing and dumping might be a better choice,
so one can figure out what's causing the IO error.
This could be especially important to companies running IO
intensive applications where corruption must be avoided, e.g. a
bank's databases.
[ SuSE has been shipping it for a while, it was done at the
request of a large database vendor, for their users. ]
Signed-off-by: Kurt Garloff <garloff@suse.de>
Signed-off-by: Roberto Angelino <robertangelino@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
LKML-Reference: <
20090624213211.GA11291@kroah.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
#include "dumpstack.h"
int panic_on_unrecovered_nmi;
+int panic_on_io_nmi;
unsigned int code_bytes = 64;
int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
static int die_counter;
printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
show_registers(regs);
+ if (panic_on_io_nmi)
+ panic("NMI IOCK error: Not continuing");
+
/* Re-enable the IOCK line, wait for a few seconds */
reason = (reason & 0xf) | 8;
outb(reason, 0x61);
extern int panic_timeout;
extern int panic_on_oops;
extern int panic_on_unrecovered_nmi;
+extern int panic_on_io_nmi;
extern const char *print_tainted(void);
extern void add_taint(unsigned flag);
extern int test_taint(unsigned flag);
.proc_handler = &proc_dointvec,
},
{
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "panic_on_io_nmi",
+ .data = &panic_on_io_nmi,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ {
.ctl_name = KERN_BOOTLOADER_TYPE,
.procname = "bootloader_type",
.data = &bootloader_type,