powerpc/64s: make PACA_IRQ_HARD_DIS track MSR[EE] closely

When the masked interrupt handler clears MSR[EE] for an interrupt in
the PACA_IRQ_MUST_HARD_MASK set, it does not set PACA_IRQ_HARD_DIS.
This makes them get out of synch.

With that taken into account, it's only low level irq manipulation
(and interrupt entry before reconcile) where they can be out of synch.
This makes the code less surprising.

It also allows the IRQ replay code to rely on the IRQ_HARD_DIS value
and not have to mtmsrd again in this case (e.g., for an external
interrupt that has been masked). The bigger benefit might just be
that there is not such an element of surprise in these two bits of
state.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

5 files changed, 46 insertions, 12 deletions

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 729e9ef4d3bb..0357f87a013c 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -993,6 +993,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	std	r4,_TRAP(r1)
 
 	/*
+	 * PACA_IRQ_HARD_DIS won't always be set here, so set it now
+	 * to reconcile the IRQ state. Tracing is already accounted for.
+	 */
+	lbz	r4,PACAIRQHAPPENED(r13)
+	ori	r4,r4,PACA_IRQ_HARD_DIS
+	stb	r4,PACAIRQHAPPENED(r13)
+
+	/*
 	 * Then find the right handler and call it. Interrupts are
 	 * still soft-disabled and we keep them that way.
 	*/
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 9b6e653e501a..3325f721e7b2 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -949,7 +949,11 @@ kernel_dbg_exc:
 
 .macro masked_interrupt_book3e paca_irq full_mask
 	lbz	r10,PACAIRQHAPPENED(r13)
+	.if \full_mask == 1
+	ori	r10,r10,\paca_irq | PACA_IRQ_HARD_DIS
+	.else
 	ori	r10,r10,\paca_irq
+	.endif
 	stb	r10,PACAIRQHAPPENED(r13)
 
 	.if \full_mask == 1
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 76a14702cb9c..36aec1f1cb2d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1498,7 +1498,10 @@ masked_##_H##interrupt:					\
 	mfspr	r10,SPRN_##_H##SRR1;			\
 	xori	r10,r10,MSR_EE; /* clear MSR_EE */	\
 	mtspr	SPRN_##_H##SRR1,r10;			\
-2:	mtcrf	0x80,r9;				\
+	ori	r11,r11,PACA_IRQ_HARD_DIS;		\
+	stb	r11,PACAIRQHAPPENED(r13);		\
+2:	/* done */					\
+	mtcrf	0x80,r9;				\
 	std	r1,PACAR1(r13);				\
 	ld	r9,PACA_EXGEN+EX_R9(r13);		\
 	ld	r10,PACA_EXGEN+EX_R10(r13);		\
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 2b269315d377..4e0d94d02030 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -36,7 +36,7 @@ _GLOBAL(\name)
 	 */
 	lbz	r3,PACAIRQHAPPENED(r13)
 	cmpwi	cr0,r3,0
-	bnelr
+	bne	2f
 
 	/* Now we are going to mark ourselves as soft and hard enabled in
 	 * order to be able to take interrupts while asleep. We inform lockdep
@@ -72,6 +72,11 @@ _GLOBAL(\name)
 	wrteei	1
 	\loop
 
+2:
+	lbz	r10,PACAIRQHAPPENED(r13)
+	ori	r10,r10,PACA_IRQ_HARD_DIS
+	stb	r10,PACAIRQHAPPENED(r13)
+	blr
 .endm
 
 .macro BOOK3E_IDLE_LOOP
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0682fef1f385..ca941f1e83a9 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -145,8 +145,20 @@ notrace unsigned int __check_irq_replay(void)
 	trace_hardirqs_on();
 	trace_hardirqs_off();
 
+	/*
+	 * We are always hard disabled here, but PACA_IRQ_HARD_DIS may
+	 * not be set, which means interrupts have only just been hard
+	 * disabled as part of the local_irq_restore or interrupt return
+	 * code. In that case, skip the decrementr check becaus it's
+	 * expensive to read the TB.
+	 *
+	 * HARD_DIS then gets cleared here, but it's reconciled later.
+	 * Either local_irq_disable will replay the interrupt and that
+	 * will reconcile state like other hard interrupts. Or interrupt
+	 * retur will replay the interrupt and in that case it sets
+	 * PACA_IRQ_HARD_DIS by hand (see comments in entry_64.S).
+	 */
 	if (happened & PACA_IRQ_HARD_DIS) {
-		/* Clear bit 0 which we wouldn't clear otherwise */
 		local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
 
 		/*
@@ -248,24 +260,26 @@ notrace void arch_local_irq_restore(unsigned long mask)
 	 * cannot have preempted.
 	 */
 	irq_happened = get_irq_happened();
-	if (!irq_happened)
+	if (!irq_happened) {
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+		WARN_ON(!(mfmsr() & MSR_EE));
+#endif
 		return;
+	}
 
 	/*
 	 * We need to hard disable to get a trusted value from
 	 * __check_irq_replay(). We also need to soft-disable
 	 * again to avoid warnings in there due to the use of
 	 * per-cpu variables.
-	 *
-	 * We know that if the value in irq_happened is exactly 0x01
-	 * then we are already hard disabled (there are other less
-	 * common cases that we'll ignore for now), so we skip the
-	 * (expensive) mtmsrd.
 	 */
-	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
+	if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+		WARN_ON(!(mfmsr() & MSR_EE));
+#endif
 		__hard_irq_disable();
 #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-	else {
+	} else {
 		/*
 		 * We should already be hard disabled here. We had bugs
 		 * where that wasn't the case so let's dbl check it and
@@ -274,8 +288,8 @@ notrace void arch_local_irq_restore(unsigned long mask)
 		 */
 		if (WARN_ON(mfmsr() & MSR_EE))
 			__hard_irq_disable();
-	}
 #endif
+	}
 
 	irq_soft_mask_set(IRQS_ALL_DISABLED);
 	trace_hardirqs_off();