[PATCH] x86 NMI: better support for debuggers

This patch adds a notify to the die_nmi notify that the system is about to
be taken down.  If the notify is handled with a NOTIFY_STOP return, the
system is given a new lease on life.

We also change the nmi watchdog to carry on if die_nmi returns.

This give debug code a chance to a) catch watchdog timeouts and b) possibly
allow the system to continue, realizing that the time out may be due to
debugger activities such as single stepping which is usually done with
"other" cpus held.

Signed-off-by: George Anzinger<george@mvista.com>
Cc: Keith Owens <kaos@ocs.com.au>
Signed-off-by: NGeorge Anzinger <george@mvista.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

arch/i386/kernel/nmi.c

@@ -501,8 +501,11 @@ void nmi_watchdog_tick (struct pt_regs * regs)
 		 */
 		alert_counter[cpu]++;
 		if (alert_counter[cpu] == 5*nmi_hz)
+			/*
+			 * die_nmi will return ONLY if NOTIFY_STOP happens..
+			 */
 			die_nmi(regs, "NMI Watchdog detected LOCKUP");
-	} else {
+
 		last_irq_sums[cpu] = sum;
 		alert_counter[cpu] = 0;
 	}

arch/i386/kernel/traps.c

@@ -565,6 +565,10 @@ static DEFINE_SPINLOCK(nmi_print_lock);
 
 void die_nmi (struct pt_regs *regs, const char *msg)
 {
+	if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 0, SIGINT) ==
+	    NOTIFY_STOP)
+		return;
+
 	spin_lock(&nmi_print_lock);
 	/*
 	* We are in trouble anyway, lets at least try

include/asm-i386/kdebug.h

@@ -41,9 +41,16 @@ enum die_val {
 	DIE_PAGE_FAULT,
 };
 
-static inline int notify_die(enum die_val val,char *str,struct pt_regs *regs,long err,int trap, int sig)
+static inline int notify_die(enum die_val val, const char *str,
+			struct pt_regs *regs, long err, int trap, int sig)
 {
-	struct die_args args = { .regs=regs, .str=str, .err=err, .trapnr=trap,.signr=sig };
+	struct die_args args = {
+		.regs = regs,
+		.str = str,
+		.err = err,
+		.trapnr = trap,
+		.signr = sig
+	};
 	return notifier_call_chain(&i386die_chain, val, &args);
 }