powerpc/powernv: Fixes for hypervisor doorbell handling

Since we can now use hypervisor doorbells for host IPIs, this makes
sure we clear the host IPI flag when taking a doorbell interrupt, and
clears any pending doorbell IPI in pnv_smp_cpu_kill_self() (as we
already do for IPIs sent via the XICS interrupt controller).  Otherwise
if there did happen to be a leftover pending doorbell interrupt for
an offline CPU thread for any reason, it would prevent that thread from
going into a power-saving mode; it would instead keep waking up because
of the interrupt.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 20 insertions, 2 deletions

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 03cd858a401c..4cbe23af400a 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -153,6 +153,7 @@
 #define PPC_INST_MFSPR_PVR_MASK		0xfc1fffff
 #define PPC_INST_MFTMR			0x7c0002dc
 #define PPC_INST_MSGSND			0x7c00019c
+#define PPC_INST_MSGCLR			0x7c0001dc
 #define PPC_INST_MSGSNDP		0x7c00011c
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
@@ -309,6 +310,8 @@
 					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
 					___PPC_RB(b))
+#define PPC_MSGCLR(b)		stringify_in_c(.long PPC_INST_MSGCLR | \
+					___PPC_RB(b))
 #define PPC_MSGSNDP(b)		stringify_in_c(.long PPC_INST_MSGSNDP | \
 					___PPC_RB(b))
 #define PPC_POPCNTB(a, s)	stringify_in_c(.long PPC_INST_POPCNTB | \
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1c874fb533bb..af56b5c6c81a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -608,13 +608,16 @@
 #define   SRR1_ISI_N_OR_G	0x10000000 /* ISI: Access is no-exec or G */
 #define   SRR1_ISI_PROT		0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK		0x00380000 /* reason for wakeup */
+#define   SRR1_WAKEMASK_P8	0x003c0000 /* reason for wakeup on POWER8 */
 #define   SRR1_WAKESYSERR	0x00300000 /* System error */
 #define   SRR1_WAKEEE		0x00200000 /* External interrupt */
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
 #define	  SRR1_WAKEHMI		0x00280000 /* Hypervisor maintenance */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
+#define   SRR1_WAKEDBELL	0x00140000 /* Privileged doorbell on P8 */
 #define   SRR1_WAKETHERM	0x00100000 /* Thermal management interrupt */
 #define	  SRR1_WAKERESET	0x00100000 /* System reset */
+#define   SRR1_WAKEHDBELL	0x000c0000 /* Hypervisor doorbell on P8 */
 #define	  SRR1_WAKESTATE	0x00030000 /* Powersave exit mask [46:47] */
 #define	  SRR1_WS_DEEPEST	0x00030000 /* Some resources not maintained,
 					  * may not be recoverable */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f4217819cc31..2128f3a96c32 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -17,6 +17,7 @@
 
 #include <asm/dbell.h>
 #include <asm/irq_regs.h>
+#include <asm/kvm_ppc.h>
 
 #ifdef CONFIG_SMP
 void doorbell_setup_this_cpu(void)
@@ -41,6 +42,7 @@ void doorbell_exception(struct pt_regs *regs)
 
 	may_hard_irq_enable();
 
+	kvmppc_set_host_ipi(smp_processor_id(), 0);
 	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux();
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fc34025ef822..38a45088f633 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -33,6 +33,8 @@
 #include <asm/runlatch.h>
 #include <asm/code-patching.h>
 #include <asm/dbell.h>
+#include <asm/kvm_ppc.h>
+#include <asm/ppc-opcode.h>
 
 #include "powernv.h"
 
@@ -149,7 +151,7 @@ static int pnv_smp_cpu_disable(void)
 static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
-	unsigned long srr1;
+	unsigned long srr1, wmask;
 	u32 idle_states;
 
 	/* Standard hot unplug procedure */
@@ -161,6 +163,10 @@ static void pnv_smp_cpu_kill_self(void)
 	generic_set_cpu_dead(cpu);
 	smp_wmb();
 
+	wmask = SRR1_WAKEMASK;
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		wmask = SRR1_WAKEMASK_P8;
+
 	idle_states = pnv_get_supported_cpuidle_states();
 	/* We don't want to take decrementer interrupts while we are offline,
 	 * so clear LPCR:PECE1. We keep PECE2 enabled.
@@ -191,10 +197,14 @@ static void pnv_smp_cpu_kill_self(void)
 		 * having finished executing in a KVM guest, then srr1
 		 * contains 0.
 		 */
-		if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) {
+		if ((srr1 & wmask) == SRR1_WAKEEE) {
 			icp_native_flush_interrupt();
 			local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
 			smp_mb();
+		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
+			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
+			kvmppc_set_host_ipi(cpu, 0);
 		}
 
 		if (cpu_core_split_required())