[PATCH v2] powerpc/powernv: Tell OPAL about our MMU mode on POWER9

[Michael Neuling]

From: Benjamin Herrenschmidt <benh at kernel.crashing.org>

That will allow OPAL to configure the CPU in an optimal way.

Signed-off-by: Benjamin Herrenschmidt <benh at kernel.crashing.org>
Signed-off-by: Michael Neuling <mikey at neuling.org>
---
v2:
  - Always set the hash bit since we always need hash for KVM guests.
  - Gate with ARCH_300 since this can break P8.
---
 arch/powerpc/include/asm/opal-api.h    |  9 +++++++++
 arch/powerpc/platforms/powernv/opal.c  | 19 +++++++++++++++++--
 arch/powerpc/platforms/powernv/setup.c | 11 ++++++++++-
 3 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 0b543f0f54..b3111c14f8 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -876,6 +876,15 @@ struct OpalIoPhb4ErrorData {
 enum {
 	OPAL_REINIT_CPUS_HILE_BE	= (1 << 0),
 	OPAL_REINIT_CPUS_HILE_LE	= (1 << 1),
+
+	/* These two define the base MMU mode of the host on P9
+	 *
+	 * On P9 Nimbus DD2.0 and Cumlus (and later), KVM can still
+	 * create hash guests in "radix" mode with care (full core
+	 * switch only).
+	 */
+	OPAL_REINIT_CPUS_MMU_HASH	= (1 << 2),
+	OPAL_REINIT_CPUS_MMU_RADIX	= (1 << 3),
 };
 
 typedef struct oppanel_line {
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 59684b4af4..eaefae10bd 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -59,6 +59,8 @@ static struct task_struct *kopald_tsk;
 
 void opal_configure_cores(void)
 {
+	uint64_t reinit_flags = 0;
+
 	/* Do the actual re-init, This will clobber all FPRs, VRs, etc...
 	 *
 	 * It will preserve non volatile GPRs and HSPRG0/1. It will
@@ -66,11 +68,24 @@ void opal_configure_cores(void)
 	 * but it might clobber a bunch.
 	 */
 #ifdef __BIG_ENDIAN__
-	opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE);
+	reinit_flags |= OPAL_REINIT_CPUS_HILE_BE;
 #else
-	opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE);
+	reinit_flags |= OPAL_REINIT_CPUS_HILE_LE;
 #endif
 
+	/*
+	 * POWER9 always support running hash:
+	 *  ie. Host hash  supports  hash guests
+	 *      Host radix supports  hash/radix guests
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		reinit_flags |= OPAL_REINIT_CPUS_MMU_HASH;
+		if (early_radix_enabled())
+			reinit_flags |= OPAL_REINIT_CPUS_MMU_RADIX;
+	}
+
+	opal_reinit_cpus(reinit_flags);
+
 	/* Restore some bits */
 	if (cur_cpu_spec->cpu_restore)
 		cur_cpu_spec->cpu_restore();
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 2dc7e5fb86..7d2723429d 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -225,6 +225,8 @@ static void pnv_kexec_wait_secondaries_down(void)
 
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
+	uint64_t reinit_flags;
+
 	if (xive_enabled())
 		xive_kexec_teardown_cpu(secondary);
 	else
@@ -254,8 +256,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 		 * We might be running as little-endian - now that interrupts
 		 * are disabled, reset the HILE bit to big-endian so we don't
 		 * take interrupts in the wrong endian later
+		 *
+		 * We reinit to enable both radix and hash on P9 to ensure
+		 * the mode used by the next kernel is always supported.
 		 */
-		opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE);
+		reinit_flags = OPAL_REINIT_CPUS_HILE_BE;
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			reinit_flags |= OPAL_REINIT_CPUS_MMU_RADIX |
+				OPAL_REINIT_CPUS_MMU_HASH;
+		opal_reinit_cpus(reinit_flags);
 	}
 }
 #endif /* CONFIG_KEXEC_CORE */
-- 
2.11.0