@@ -94,14 +94,42 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int
 }
 
 struct interrupt_nmi_state {
+#ifdef CONFIG_PPC64
+	u8 ftrace_enabled;
+#endif
 };
 
 static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
 {
+#ifdef CONFIG_PPC64
+	/* Allow DEC and PMI to be traced when they are soft-NMI */
+	if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260) {
+		state->ftrace_enabled = this_cpu_get_ftrace_enabled();
+		this_cpu_set_ftrace_enabled(0);
+	}
+#endif
+
+	/*
+	 * Do not use nmi_enter() for pseries hash guest taking a real-mode
+	 * NMI because not everything it touches is within the RMA limit.
+	 */
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+			!firmware_has_feature(FW_FEATURE_LPAR) ||
+			radix_enabled() || (mfmsr() & MSR_DR))
+		nmi_enter();
 }
 
 static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
 {
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) ||
+			!firmware_has_feature(FW_FEATURE_LPAR) ||
+			radix_enabled() || (mfmsr() & MSR_DR))
+		nmi_exit();
+
+#ifdef CONFIG_PPC64
+	if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260)
+		this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+#endif
 }
 
 /**

@@ -592,12 +592,6 @@ EXPORT_SYMBOL_GPL(machine_check_print_event_info);
 DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
 {
 	long handled = 0;
-	u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
-
-	this_cpu_set_ftrace_enabled(0);
-	/* Do not use nmi_enter/exit for pseries hpte guest */
-	if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
-		nmi_enter();
 
 	hv_nmi_check_nonrecoverable(regs);
 

@@ -607,11 +601,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
 	if (ppc_md.machine_check_early)
 		handled = ppc_md.machine_check_early(regs);
 
-	if (radix_enabled() || !firmware_has_feature(FW_FEATURE_LPAR))
-		nmi_exit();
-
-	this_cpu_set_ftrace_enabled(ftrace_enabled);
-
 	return handled;
 }
 

@@ -435,11 +435,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
 {
 	unsigned long hsrr0, hsrr1;
 	bool saved_hsrrs = false;
-	u8 ftrace_enabled = this_cpu_get_ftrace_enabled();
-
-	this_cpu_set_ftrace_enabled(0);
-
-	nmi_enter();
 
 	/*
 	 * System reset can interrupt code where HSRRs are live and MSR[RI]=1.

@@ -514,10 +509,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
 		mtspr(SPRN_HSRR1, hsrr1);
 	}
 
-	nmi_exit();
-
-	this_cpu_set_ftrace_enabled(ftrace_enabled);
-
 	/* What should we do here? We could issue a shutdown or hard reset. */
 
 	return 0;

@@ -809,6 +800,12 @@ void die_mce(const char *str, struct pt_regs *regs, long err)
 }
 NOKPROBE_SYMBOL(die_mce);
 
+/*
+ * BOOK3S_64 does not call this handler as a non-maskable interrupt
+ * (it uses its own early real-mode handler to handle the MCE proper
+ * and then raises irq_work to call this handler when interrupts are
+ * enabled).
+ */
 #ifdef CONFIG_PPC_BOOK3S_64
 DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception)
 #else

@@ -817,20 +814,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
 {
 	int recover = 0;
 
-	/*
-	 * BOOK3S_64 does not call this handler as a non-maskable interrupt
-	 * (it uses its own early real-mode handler to handle the MCE proper
-	 * and then raises irq_work to call this handler when interrupts are
-	 * enabled).
-	 *
-	 * This is silly. The BOOK3S_64 should just call a different function
-	 * rather than expecting semantics to magically change. Something
-	 * like 'non_nmi_machine_check_exception()', perhaps?
-	 */
-	const bool nmi = !IS_ENABLED(CONFIG_PPC_BOOK3S_64);
-
-	if (nmi) nmi_enter();
-
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);

@@ -862,8 +845,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
 	if (!(regs->msr & MSR_RI))
 		die_mce("Unrecoverable Machine check", regs, SIGBUS);
 
-	if (nmi) nmi_exit();
-
 #ifdef CONFIG_PPC_BOOK3S_64
 	return;
 #else

@@ -1886,14 +1867,10 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
 DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
 DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
 {
-	nmi_enter();
-
 	__this_cpu_inc(irq_stat.pmu_irqs);
 
 	perf_irq(regs);
 
-	nmi_exit();
-
 	return 0;
 }
 #endif

@@ -254,11 +254,12 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 	int cpu = raw_smp_processor_id();
 	u64 tb;
 
+	/* should only arrive from kernel, with irqs disabled */
+	WARN_ON_ONCE(!arch_irq_disabled_regs(regs));
+
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
 		return 0;
 
-	nmi_enter();
-
 	__this_cpu_inc(irq_stat.soft_nmi_irqs);
 
 	tb = get_tb();

@@ -266,7 +267,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 		wd_smp_lock(&flags);
 		if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) {
 			wd_smp_unlock(&flags);
-			goto out;
+			return 0;
 		}
 		set_cpu_stuck(cpu, tb);
 

@@ -290,9 +291,6 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 	if (wd_panic_timeout_tb < 0x7fffffff)
 		mtspr(SPRN_DEC, wd_panic_timeout_tb);
 
-out:
-	nmi_exit();
-
 	return 0;
 }