[PATCH] powerpc/64: Disable irq restore warning for now

[PATCH] powerpc/64: Disable irq restore warning for now

[Michael Ellerman]

We recently added a warning in arch_local_irq_restore() to check that
the soft masking state matches reality.

Unfortunately it trips in a few places, which are not entirely trivial
to fix. The key problem is if we're doing function_graph tracing of
restore_math(), the warning pops and then seems to recurse. It's not
entirely clear because the system continuously oopses on all CPUs,
with the output interleaved and unreadable.

It's also been observed on a G5 coming out of idle.

Until we can fix those cases disable the warning for now.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/irq.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index ca941f1e83a9..916ddc4aac44 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -261,9 +261,16 @@ notrace void arch_local_irq_restore(unsigned long mask)
 	 */
 	irq_happened = get_irq_happened();
 	if (!irq_happened) {
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-		WARN_ON(!(mfmsr() & MSR_EE));
-#endif
+		/*
+		 * FIXME. Here we'd like to be able to do:
+		 *
+		 * #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+		 *   WARN_ON(!(mfmsr() & MSR_EE));
+		 * #endif
+		 *
+		 * But currently it hits in a few paths, we should fix those and
+		 * enable the warning.
+		 */
 		return;
 	}
 
-- 
2.14.1

Re: powerpc/64: Disable irq restore warning for now

[Michael Ellerman]

On Tue, 2018-08-07 at 11:48:46 UTC, Michael Ellerman wrote:
> We recently added a warning in arch_local_irq_restore() to check that
> the soft masking state matches reality.
> 
> Unfortunately it trips in a few places, which are not entirely trivial
> to fix. The key problem is if we're doing function_graph tracing of
> restore_math(), the warning pops and then seems to recurse. It's not
> entirely clear because the system continuously oopses on all CPUs,
> with the output interleaved and unreadable.
> 
> It's also been observed on a G5 coming out of idle.
> 
> Until we can fix those cases disable the warning for now.
> 
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

Applied to powerpc next.

https://git.kernel.org/powerpc/c/4da1f79227ad42550e3e70e7b4812e

cheers