[PATCH] x86: Cleanup NMI interrupt path

This patch cleans up the NMI interrupt path.  Instead of being gated by if
the 'nmi callback' is set, the interrupt handler now calls everyone who is
registered on the die_chain and additionally checks the nmi watchdog,
reseting it if enabled.  This allows more subsystems to hook into the NMI if
they need to (without being block by set_nmi_callback).

Signed-off-by:  Don Zickus <dzickus@redhat.com>
Signed-off-by: Andi Kleen <ak@suse.de>

6 files changed, 57 insertions, 29 deletions

diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index d88004343034..bd96ea4f2942 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -781,7 +781,7 @@ EXPORT_SYMBOL(touch_nmi_watchdog);
 
 extern void die_nmi(struct pt_regs *, const char *msg);
 
-void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
+int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
 {
 
 	/*
@@ -794,10 +794,12 @@ void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
 	int cpu = smp_processor_id();
 	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 	u64 dummy;
+	int rc=0;
 
 	/* check for other users first */
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
 			== NOTIFY_STOP) {
+		rc = 1;
 		touched = 1;
 	}
 
@@ -850,10 +852,18 @@ void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
 			}
 			/* start the cycle over again */
 			write_watchdog_counter(wd->perfctr_msr, NULL);
-		}
+			rc = 1;
+		} else if (nmi_watchdog == NMI_IO_APIC) {
+			/* don't know how to accurately check for this.
+			 * just assume it was a watchdog timer interrupt
+			 * This matches the old behaviour.
+			 */
+			rc = 1;
+		} else
+			printk(KERN_WARNING "Unknown enabled NMI hardware?!\n");
 	}
 done:
-	return;
+	return rc;
 }
 
 #ifdef CONFIG_SYSCTL
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 3a07b2677e2a..282f0bd40dfd 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -706,6 +706,13 @@ void die_nmi (struct pt_regs *regs, const char *msg)
 	do_exit(SIGSEGV);
 }
 
+static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
+{
+	return 0;
+}
+
+static nmi_callback_t nmi_callback = dummy_nmi_callback;
+
 static void default_do_nmi(struct pt_regs * regs)
 {
 	unsigned char reason = 0;
@@ -723,12 +730,11 @@ static void default_do_nmi(struct pt_regs * regs)
 		 * Ok, so this is none of the documented NMI sources,
 		 * so it must be the NMI watchdog.
 		 */
-		if (nmi_watchdog) {
-			nmi_watchdog_tick(regs, reason);
+		if (nmi_watchdog_tick(regs, reason))
 			return;
-		}
 #endif
-		unknown_nmi_error(reason, regs);
+		if (!rcu_dereference(nmi_callback)(regs, smp_processor_id()))
+			unknown_nmi_error(reason, regs);
 		return;
 	}
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
@@ -744,13 +750,6 @@ static void default_do_nmi(struct pt_regs * regs)
 	reassert_nmi();
 }
 
-static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
-{
-	return 0;
-}
- 
-static nmi_callback_t nmi_callback = dummy_nmi_callback;
- 
 fastcall void do_nmi(struct pt_regs * regs, long error_code)
 {
 	int cpu;
@@ -761,8 +760,7 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code)
 
 	++nmi_count(cpu);
 
-	if (!rcu_dereference(nmi_callback)(regs, cpu))
-		default_do_nmi(regs);
+	default_do_nmi(regs);
 
 	nmi_exit();
 }
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index d42374a952d7..f6b881b23a70 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -682,16 +682,18 @@ void touch_nmi_watchdog (void)
  	touch_softlockup_watchdog();
 }
 
-void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
+int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 {
 	int sum;
 	int touched = 0;
 	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 	u64 dummy;
+	int rc=0;
 
 	/* check for other users first */
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
 			== NOTIFY_STOP) {
+		rc = 1;
 		touched = 1;
 	}
 
@@ -746,10 +748,18 @@ void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 	 		}
 			/* start the cycle over again */
 			wrmsrl(wd->perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
-		}
+			rc = 1;
+		} else 	if (nmi_watchdog == NMI_IO_APIC) {
+			/* don't know how to accurately check for this.
+			 * just assume it was a watchdog timer interrupt
+			 * This matches the old behaviour.
+			 */
+			rc = 1;
+		} else
+			printk(KERN_WARNING "Unknown enabled NMI hardware?!\n");
 	}
 done:
-	return;
+	return rc;
 }
 
 static __kprobes int dummy_nmi_callback(struct pt_regs * regs, int cpu)
@@ -761,15 +771,17 @@ static nmi_callback_t nmi_callback = dummy_nmi_callback;
  
 asmlinkage __kprobes void do_nmi(struct pt_regs * regs, long error_code)
 {
-	int cpu = safe_smp_processor_id();
-
 	nmi_enter();
 	add_pda(__nmi_count,1);
-	if (!rcu_dereference(nmi_callback)(regs, cpu))
-		default_do_nmi(regs);
+	default_do_nmi(regs);
 	nmi_exit();
 }
 
+int do_nmi_callback(struct pt_regs * regs, int cpu)
+{
+	return rcu_dereference(nmi_callback)(regs, cpu);
+}
+
 void set_nmi_callback(nmi_callback_t callback)
 {
 	vmalloc_sync_all();
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index b1249774d1e8..42bc070fdf11 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -781,12 +781,12 @@ asmlinkage __kprobes void default_do_nmi(struct pt_regs *regs)
 		 * Ok, so this is none of the documented NMI sources,
 		 * so it must be the NMI watchdog.
 		 */
-		if (nmi_watchdog > 0) {
-			nmi_watchdog_tick(regs,reason);
+		if (nmi_watchdog_tick(regs,reason))
 			return;
-		}
+		if (!do_nmi_callback(regs,cpu))
 #endif
-		unknown_nmi_error(reason, regs);
+			unknown_nmi_error(reason, regs);
+
 		return;
 	}
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
diff --git a/include/asm-i386/nmi.h b/include/asm-i386/nmi.h
index 4cda6801ecb8..da0e0b4e9139 100644
--- a/include/asm-i386/nmi.h
+++ b/include/asm-i386/nmi.h
@@ -37,7 +37,7 @@ extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
-extern void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
+extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
 
 extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;
diff --git a/include/asm-x86_64/nmi.h b/include/asm-x86_64/nmi.h
index 5918136fd853..8f02a2a416e6 100644
--- a/include/asm-x86_64/nmi.h
+++ b/include/asm-x86_64/nmi.h
@@ -26,6 +26,14 @@ void set_nmi_callback(nmi_callback_t callback);
  */
 void unset_nmi_callback(void);
 
+/**
+ * do_nmi_callback
+ *
+ * Check to see if a callback exists and execute it.  Return 1
+ * if the handler exists and was handled successfully.
+ */
+int do_nmi_callback(struct pt_regs *regs, int cpu);
+
 #ifdef CONFIG_PM
  
 /** Replace the PM callback routine for NMI. */
@@ -68,7 +76,7 @@ extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
-extern void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
+extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
 
 extern void nmi_watchdog_default(void);
 extern int setup_nmi_watchdog(char *);