Merge pull request torvalds#652 from ojeda/ppc-apply-fix

ppc: apply fix for hard lockup

arch/powerpc/include/asm/hw_irq.h

@@ -345,17 +345,54 @@ static inline bool lazy_irq_pending_nocheck(void)
 bool power_pmu_wants_prompt_pmi(void);
 
 /*
- * This is called by asynchronous interrupts to conditionally
- * re-enable hard interrupts after having cleared the source
- * of the interrupt. They are kept disabled if there is a different
- * soft-masked interrupt pending that requires hard masking.
+ * This is called by asynchronous interrupts to check whether to
+ * conditionally re-enable hard interrupts after having cleared
+ * the source of the interrupt. They are kept disabled if there
+ * is a different soft-masked interrupt pending that requires hard
+ * masking.
  */
-static inline void may_hard_irq_enable(void)
+static inline bool should_hard_irq_enable(void)
 {
-	if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) {
-		get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS;
-		__hard_irq_enable();
-	}
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON(irq_soft_mask_return() == IRQS_ENABLED);
+	WARN_ON(mfmsr() & MSR_EE);
+#endif
+#ifdef CONFIG_PERF_EVENTS
+	/*
+	 * If the PMU is not running, there is not much reason to enable
+	 * MSR[EE] in irq handlers because any interrupts would just be
+	 * soft-masked.
+	 *
+	 * TODO: Add test for 64e
+	 */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !power_pmu_wants_prompt_pmi())
+		return false;
+
+	if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)
+		return false;
+
+	return true;
+#else
+	return false;
+#endif
+}
+
+/*
+ * Do the hard enabling, only call this if should_hard_irq_enable is true.
+ */
+static inline void do_hard_irq_enable(void)
+{
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON(irq_soft_mask_return() == IRQS_ENABLED);
+	WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK);
+	WARN_ON(mfmsr() & MSR_EE);
+#endif
+	/*
+	 * This allows PMI interrupts (and watchdog soft-NMIs) through.
+	 * There is no other reason to enable this way.
+	 */
+	get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	__hard_irq_enable();
 }
 
 static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
@@ -436,7 +473,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 	return !(regs->msr & MSR_EE);
 }
 
-static inline bool may_hard_irq_enable(void)
+static inline bool should_hard_irq_enable(void)
 {
 	return false;
 }

arch/powerpc/kernel/dbell.c

@@ -27,7 +27,8 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
 
 	ppc_msgsync();
 
-	may_hard_irq_enable();
+	if (should_hard_irq_enable())
+		do_hard_irq_enable();
 
 	kvmppc_clear_host_ipi(smp_processor_id());
 	__this_cpu_inc(irq_stat.doorbell_irqs);

arch/powerpc/kernel/irq.c

@@ -745,7 +745,8 @@ void __do_irq(struct pt_regs *regs)
 	irq = ppc_md.get_irq();
 
 	/* We can hard enable interrupts now to allow perf interrupts */
-	may_hard_irq_enable();
+	if (should_hard_irq_enable())
+		do_hard_irq_enable();
 
 	/* And finally process it */
 	if (unlikely(!irq))

arch/powerpc/kernel/time.c

@@ -609,22 +609,23 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 		return;
 	}
 
-	/* Ensure a positive value is written to the decrementer, or else
-	 * some CPUs will continue to take decrementer exceptions. When the
-	 * PPC_WATCHDOG (decrementer based) is configured, keep this at most
-	 * 31 bits, which is about 4 seconds on most systems, which gives
-	 * the watchdog a chance of catching timer interrupt hard lockups.
-	 */
-	if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
-		set_dec(0x7fffffff);
-	else
-		set_dec(decrementer_max);
-
-	/* Conditionally hard-enable interrupts now that the DEC has been
-	 * bumped to its maximum value
-	 */
-	may_hard_irq_enable();
+	/* Conditionally hard-enable interrupts. */
+	if (should_hard_irq_enable()) {
+		/*
+		 * Ensure a positive value is written to the decrementer, or
+		 * else some CPUs will continue to take decrementer exceptions.
+		 * When the PPC_WATCHDOG (decrementer based) is configured,
+		 * keep this at most 31 bits, which is about 4 seconds on most
+		 * systems, which gives the watchdog a chance of catching timer
+		 * interrupt hard lockups.
+		 */
+		if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
+			set_dec(0x7fffffff);
+		else
+			set_dec(decrementer_max);
 
+		do_hard_irq_enable();
+	}
 
 #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
@@ -648,8 +649,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
-		if (now <= decrementer_max)
-			set_dec_or_work(now);
+		if (now > decrementer_max)
+			now = decrementer_max;
+		set_dec_or_work(now);
 		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}