Thread (7 messages) flat view 7 messages, 7 authors, 2017-09-13

Re: [PATCH] POWER9 PMU stops after idle workaround

From: Vaidyanathan Srinivasan <hidden>
Date: 2017-07-20 05:06:50

* Nicholas Piggin [off-list ref] [2017-07-20 11:53:22]:
POWER9 DD2 PMU can stop after a state-loss idle in some conditions.

A solution is to set then clear MMCRA[60] after wake from state-loss
idle.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Vaidyanathan Srinivasan <redacted>

quoted hunk ↗ jump to hunk
---
 arch/powerpc/kernel/idle_book3s.S | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 516ebef905c0..e6252c5a57a4 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -460,11 +460,17 @@ pnv_restore_hyp_resource_arch300:
 	/*
 	 * Workaround for POWER9, if we lost resources, the ERAT
 	 * might have been mixed up and needs flushing. We also need
-	 * to reload MMCR0 (see comment above).
+	 * to reload MMCR0 (see comment above). We also need to set
+	 * then clear bit 60 in MMCRA to ensure the PMU starts running.
 	 */
 	blt	cr3,1f
 	PPC_INVALIDATE_ERAT
 	ld	r1,PACAR1(r13)
+	mfspr	r4,SPRN_MMCRA
+	ori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4
+	xori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4

Timing is ok to resolve the issue?  Does back-to-back bit flip of
MMCRA[60] gets the job done for all cases?  Just asking since this
issue in itself is a corner case ;)

--Vaidy
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help