hardirq/nmi: Allow nested nmi_enter()

Since there are already a number of sites (ARM64, PowerPC) that effectively
nest nmi_enter(), make the primitive support this before adding even more.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Acked-by: Marc Zyngier <[email protected]>
Acked-by: Will Deacon <[email protected]>
Cc: Michael Ellerman <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Peter Zijlstra

arch/arm64/kernel/sdei.c

@@ -251,22 +251,12 @@ asmlinkage __kprobes notrace unsigned long
 __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
 {
 	unsigned long ret;
-	bool do_nmi_exit = false;
 
-	/*
-	 * nmi_enter() deals with printk() re-entrance and use of RCU when
-	 * RCU believed this CPU was idle. Because critical events can
-	 * interrupt normal events, we may already be in_nmi().
-	 */
-	if (!in_nmi()) {
-		nmi_enter();
-		do_nmi_exit = true;
-	}
+	nmi_enter();
 
 	ret = _sdei_handler(regs, arg);
 
-	if (do_nmi_exit)
-		nmi_exit();
+	nmi_exit();
 
 	return ret;
 }

arch/arm64/kernel/traps.c

@@ -906,17 +906,13 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
 
 asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
 {
-	const bool was_in_nmi = in_nmi();
-
-	if (!was_in_nmi)
-		nmi_enter();
+	nmi_enter();
 
 	/* non-RAS errors are not containable */
 	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
 		arm64_serror_panic(regs, esr);
 
-	if (!was_in_nmi)
-		nmi_exit();
+	nmi_exit();
 }
 
 asmlinkage void enter_from_user_mode(void)

arch/powerpc/kernel/traps.c

@@ -441,15 +441,9 @@ void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
 void system_reset_exception(struct pt_regs *regs)
 {
 	unsigned long hsrr0, hsrr1;
-	bool nested = in_nmi();
 	bool saved_hsrrs = false;
 
-	/*
-	 * Avoid crashes in case of nested NMI exceptions. Recoverability
-	 * is determined by RI and in_nmi
-	 */
-	if (!nested)
-		nmi_enter();
+	nmi_enter();
 
 	/*
 	 * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
@@ -521,8 +515,7 @@ void system_reset_exception(struct pt_regs *regs)
 		mtspr(SPRN_HSRR1, hsrr1);
 	}
 
-	if (!nested)
-		nmi_exit();
+	nmi_exit();
 
 	/* What should we do here? We could issue a shutdown or hard reset. */
 }
@@ -823,9 +816,8 @@ int machine_check_generic(struct pt_regs *regs)
 void machine_check_exception(struct pt_regs *regs)
 {
 	int recover = 0;
-	bool nested = in_nmi();
-	if (!nested)
-		nmi_enter();
+
+	nmi_enter();
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
@@ -851,8 +843,7 @@ void machine_check_exception(struct pt_regs *regs)
 	if (check_io_access(regs))
 		goto bail;
 
-	if (!nested)
-		nmi_exit();
+	nmi_exit();
 
 	die("Machine check", regs, SIGBUS);
 
@@ -863,8 +854,7 @@ void machine_check_exception(struct pt_regs *regs)
 	return;
 
 bail:
-	if (!nested)
-		nmi_exit();
+	nmi_exit();
 }
 
 void SMIException(struct pt_regs *regs)

include/linux/hardirq.h

@@ -65,13 +65,16 @@ extern void irq_exit(void);
 #define arch_nmi_exit()		do { } while (0)
 #endif
 
+/*
+ * nmi_enter() can nest up to 15 times; see NMI_BITS.
+ */
 #define nmi_enter()						\
 	do {							\
 		arch_nmi_enter();				\
 		printk_nmi_enter();				\
 		lockdep_off();					\
 		ftrace_nmi_enter();				\
-		BUG_ON(in_nmi());				\
+		BUG_ON(in_nmi() == NMI_MASK);			\
 		preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		rcu_nmi_enter();				\
 		lockdep_hardirq_enter();			\

include/linux/preempt.h

@@ -26,13 +26,13 @@
  *         PREEMPT_MASK:	0x000000ff
  *         SOFTIRQ_MASK:	0x0000ff00
  *         HARDIRQ_MASK:	0x000f0000
- *             NMI_MASK:	0x00100000
+ *             NMI_MASK:	0x00f00000
  * PREEMPT_NEED_RESCHED:	0x80000000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
 #define HARDIRQ_BITS	4
-#define NMI_BITS	1
+#define NMI_BITS	4
 
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)