[PATCH 0/4 v2] doorbell patches for POWER9

[PATCH 0/4 v2] doorbell patches for POWER9

[Nicholas Piggin]

Since last:
- Ported up to powerpc next (thanks mpe)
- Dropped darn workaround from DD1 for now.
- Dropped the guest doorbell hack. It's not an immediate problem and
  will be tackled in other ways.

Nicholas Piggin (4):
  powerpc: change the doorbell IPI calling convention
  powerpc: Introduce msgsnd/doorbell barrier primitives
  powerpc/64s: avoid branch for ppc_msgsnd
  powerpc/powernv: POWER9 support for msgsnd/doorbell IPI

 arch/powerpc/include/asm/dbell.h          | 40 +++++++++++++++------
 arch/powerpc/include/asm/feature-fixups.h | 20 +++++++++++
 arch/powerpc/include/asm/ppc-opcode.h     |  2 ++
 arch/powerpc/include/asm/ppc_asm.h        |  8 +++++
 arch/powerpc/include/asm/smp.h            |  4 +--
 arch/powerpc/include/asm/xics.h           |  2 +-
 arch/powerpc/kernel/dbell.c               | 58 +++++++++++++++++++++++++++----
 arch/powerpc/kernel/smp.c                 | 27 +++++++-------
 arch/powerpc/platforms/85xx/smp.c         | 11 ++----
 arch/powerpc/platforms/powermac/smp.c     |  2 +-
 arch/powerpc/platforms/powernv/smp.c      | 47 +++++++++++++++++++++----
 arch/powerpc/platforms/pseries/smp.c      | 27 ++++++--------
 arch/powerpc/sysdev/xics/icp-hv.c         |  2 +-
 arch/powerpc/sysdev/xics/icp-native.c     | 12 +------
 arch/powerpc/sysdev/xics/icp-opal.c       |  2 +-
 arch/powerpc/sysdev/xics/xics-common.c    |  3 --
 arch/powerpc/sysdev/xive/common.c         |  6 ++--
 17 files changed, 186 insertions(+), 87 deletions(-)

-- 
2.11.0

[PATCH 1/4] powerpc: change the doorbell IPI calling convention

[Nicholas Piggin]

Change the doorbell callers to know about their msgsnd addressing,
rather than have them set a per-cpu target data tag at boot that gets
sent to the cause_ipi functions. The data is only used for doorbell IPI
functions, no other IPI types, so it makes sense to keep that detail
local to doorbell.

Have the platform code understand doorbell IPIs, rather than the
interrupt controller code understand them. Platform code can look at
capabilities it has available and decide which to use.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/dbell.h       |  9 ++----
 arch/powerpc/include/asm/smp.h         |  3 +-
 arch/powerpc/include/asm/xics.h        |  2 +-
 arch/powerpc/kernel/dbell.c            | 52 ++++++++++++++++++++++++++++++----
 arch/powerpc/kernel/smp.c              | 17 ++++-------
 arch/powerpc/platforms/85xx/smp.c      | 11 ++-----
 arch/powerpc/platforms/powermac/smp.c  |  2 +-
 arch/powerpc/platforms/powernv/smp.c   | 23 ++++++++++-----
 arch/powerpc/platforms/pseries/smp.c   | 27 +++++++-----------
 arch/powerpc/sysdev/xics/icp-hv.c      |  2 +-
 arch/powerpc/sysdev/xics/icp-native.c  | 12 +-------
 arch/powerpc/sysdev/xics/icp-opal.c    |  2 +-
 arch/powerpc/sysdev/xics/xics-common.c |  3 --
 arch/powerpc/sysdev/xive/common.c      |  6 ++--
 14 files changed, 92 insertions(+), 79 deletions(-)

diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 378167377065..a66eb596940c 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -35,8 +35,6 @@ enum ppc_dbell {
 #ifdef CONFIG_PPC_BOOK3S
 
 #define PPC_DBELL_MSGTYPE		PPC_DBELL_SERVER
-#define SPRN_DOORBELL_CPUTAG		SPRN_TIR
-#define PPC_DBELL_TAG_MASK		0x7f
 
 static inline void _ppc_msgsnd(u32 msg)
 {
@@ -49,8 +47,6 @@ static inline void _ppc_msgsnd(u32 msg)
 #else /* CONFIG_PPC_BOOK3S */
 
 #define PPC_DBELL_MSGTYPE		PPC_DBELL
-#define SPRN_DOORBELL_CPUTAG		SPRN_PIR
-#define PPC_DBELL_TAG_MASK		0x3fff
 
 static inline void _ppc_msgsnd(u32 msg)
 {
@@ -59,9 +55,10 @@ static inline void _ppc_msgsnd(u32 msg)
 
 #endif /* CONFIG_PPC_BOOK3S */
 
-extern void doorbell_cause_ipi(int cpu, unsigned long data);
+extern void doorbell_global_ipi(int cpu);
+extern void doorbell_core_ipi(int cpu);
+extern int doorbell_try_core_ipi(int cpu);
 extern void doorbell_exception(struct pt_regs *regs);
-extern void doorbell_setup_this_cpu(void);
 
 static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
 {
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 63fa780b71a0..d9ed3b02615e 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -40,7 +40,7 @@ extern int cpu_to_chip_id(int cpu);
 struct smp_ops_t {
 	void  (*message_pass)(int cpu, int msg);
 #ifdef CONFIG_PPC_SMP_MUXED_IPI
-	void  (*cause_ipi)(int cpu, unsigned long data);
+	void  (*cause_ipi)(int cpu);
 #endif
 	void  (*probe)(void);
 	int   (*kick_cpu)(int nr);
@@ -125,7 +125,6 @@ extern int smp_request_message_ipi(int virq, int message);
 extern const char *smp_ipi_name[];
 
 /* for irq controllers with only a single ipi */
-extern void smp_muxed_ipi_set_data(int cpu, unsigned long data);
 extern void smp_muxed_ipi_message_pass(int cpu, int msg);
 extern void smp_muxed_ipi_set_message(int cpu, int msg);
 extern irqreturn_t smp_ipi_demux(void);
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index e0b9e576905a..7ce2c3ac2964 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -57,7 +57,7 @@ struct icp_ops {
 	void (*teardown_cpu)(void);
 	void (*flush_ipi)(void);
 #ifdef CONFIG_SMP
-	void (*cause_ipi)(int cpu, unsigned long data);
+	void (*cause_ipi)(int cpu);
 	irq_handler_t ipi_action;
 #endif
 };
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 2128f3a96c32..5869c66adfd0 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -20,18 +20,60 @@
 #include <asm/kvm_ppc.h>
 
 #ifdef CONFIG_SMP
-void doorbell_setup_this_cpu(void)
+
+/*
+ * Doorbells must only be used if CPU_FTR_DBELL is available.
+ * msgsnd is used in HV, and msgsndp is used in !HV.
+ *
+ * These should be used by platform code that is aware of restrictions.
+ * Other arch code should use ->cause_ipi.
+ *
+ * doorbell_global_ipi() sends a dbell to any target CPU.
+ * Must be used only by architectures that address msgsnd target
+ * by PIR/get_hard_smp_processor_id.
+ */
+void doorbell_global_ipi(int cpu)
 {
-	unsigned long tag = mfspr(SPRN_DOORBELL_CPUTAG) & PPC_DBELL_TAG_MASK;
+	u32 tag = get_hard_smp_processor_id(cpu);
 
-	smp_muxed_ipi_set_data(smp_processor_id(), tag);
+	kvmppc_set_host_ipi(cpu, 1);
+	/* Order previous accesses vs. msgsnd, which is treated as a store */
+	mb();
+	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
 }
 
-void doorbell_cause_ipi(int cpu, unsigned long data)
+/*
+ * doorbell_core_ipi() sends a dbell to a target CPU in the same core.
+ * Must be used only by architectures that address msgsnd target
+ * by TIR/cpu_thread_in_core.
+ */
+void doorbell_core_ipi(int cpu)
 {
+	u32 tag = cpu_thread_in_core(cpu);
+
+	kvmppc_set_host_ipi(cpu, 1);
 	/* Order previous accesses vs. msgsnd, which is treated as a store */
 	mb();
-	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, data);
+	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
+}
+
+/*
+ * Attempt to cause a core doorbell if destination is on the same core.
+ * Returns 1 on success, 0 on failure.
+ */
+int doorbell_try_core_ipi(int cpu)
+{
+	int this_cpu = get_cpu();
+	int ret = 0;
+
+	if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
+		doorbell_core_ipi(cpu);
+		ret = 1;
+	}
+
+	put_cpu();
+
+	return ret;
 }
 
 void doorbell_exception(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 6e61cdb89194..17de938d41c5 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -39,6 +39,7 @@
 #include <asm/irq.h>
 #include <asm/hw_irq.h>
 #include <asm/kvm_ppc.h>
+#include <asm/dbell.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
@@ -211,17 +212,9 @@ int smp_request_message_ipi(int virq, int msg)
 #ifdef CONFIG_PPC_SMP_MUXED_IPI
 struct cpu_messages {
 	long messages;			/* current messages */
-	unsigned long data;		/* data for cause ipi */
 };
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);
 
-void smp_muxed_ipi_set_data(int cpu, unsigned long data)
-{
-	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
-
-	info->data = data;
-}
-
 void smp_muxed_ipi_set_message(int cpu, int msg)
 {
 	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
@@ -236,14 +229,13 @@ void smp_muxed_ipi_set_message(int cpu, int msg)
 
 void smp_muxed_ipi_message_pass(int cpu, int msg)
 {
-	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
-
 	smp_muxed_ipi_set_message(cpu, msg);
+
 	/*
 	 * cause_ipi functions are required to include a full barrier
 	 * before doing whatever causes the IPI.
 	 */
-	smp_ops->cause_ipi(cpu, info->data);
+	smp_ops->cause_ipi(cpu);
 }
 
 #ifdef __BIG_ENDIAN__
@@ -254,11 +246,12 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 
 irqreturn_t smp_ipi_demux(void)
 {
-	struct cpu_messages *info = this_cpu_ptr(&ipi_message);
+	struct cpu_messages *info;
 	unsigned long all;
 
 	mb();	/* order any irq clear */
 
+	info = this_cpu_ptr(&ipi_message);
 	do {
 		all = xchg(&info->messages, 0);
 #if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 078097a0b09d..0975066f76e8 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -461,16 +461,9 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
 }
 #endif /* CONFIG_KEXEC_CORE */
 
-static void smp_85xx_basic_setup(int cpu_nr)
-{
-	if (cpu_has_feature(CPU_FTR_DBELL))
-		doorbell_setup_this_cpu();
-}
-
 static void smp_85xx_setup_cpu(int cpu_nr)
 {
 	mpic_setup_this_cpu();
-	smp_85xx_basic_setup(cpu_nr);
 }
 
 void __init mpc85xx_smp_init(void)
@@ -484,7 +477,7 @@ void __init mpc85xx_smp_init(void)
 		smp_85xx_ops.setup_cpu = smp_85xx_setup_cpu;
 		smp_85xx_ops.message_pass = smp_mpic_message_pass;
 	} else
-		smp_85xx_ops.setup_cpu = smp_85xx_basic_setup;
+		smp_85xx_ops.setup_cpu = NULL;
 
 	if (cpu_has_feature(CPU_FTR_DBELL)) {
 		/*
@@ -492,7 +485,7 @@ void __init mpc85xx_smp_init(void)
 		 * smp_muxed_ipi_message_pass
 		 */
 		smp_85xx_ops.message_pass = NULL;
-		smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
+		smp_85xx_ops.cause_ipi = doorbell_global_ipi;
 		smp_85xx_ops.probe = NULL;
 	}
 
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 746ca7321b03..a3207cea360e 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -172,7 +172,7 @@ static irqreturn_t psurge_ipi_intr(int irq, void *d)
 	return IRQ_HANDLED;
 }
 
-static void smp_psurge_cause_ipi(int cpu, unsigned long data)
+static void smp_psurge_cause_ipi(int cpu)
 {
 	psurge_set_ipi(cpu);
 }
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 39296bf7009e..33bd4dd2cb41 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -53,11 +53,6 @@ static void pnv_smp_setup_cpu(int cpu)
 		xive_smp_setup_cpu();
 	else if (cpu != boot_cpuid)
 		xics_setup_cpu();
-
-#ifdef CONFIG_PPC_DOORBELL
-	if (cpu_has_feature(CPU_FTR_DBELL))
-		doorbell_setup_this_cpu();
-#endif
 }
 
 static int pnv_smp_kick_cpu(int nr)
@@ -254,17 +249,31 @@ static int pnv_smp_prepare_cpu(int cpu)
 	return 0;
 }
 
+static void pnv_cause_ipi(int cpu)
+{
+	if (doorbell_try_core_ipi(cpu))
+		return;
+
+	icp_ops->cause_ipi(cpu);
+}
+
 static void __init pnv_smp_probe(void)
 {
 	if (xive_enabled())
 		xive_smp_probe();
 	else
 		xics_smp_probe();
+
+	if (cpu_has_feature(CPU_FTR_DBELL) && !cpu_has_feature(CPU_FTR_ARCH_300)) {
+		smp_ops->cause_ipi = pnv_cause_ipi;
+	} else {
+		smp_ops->cause_ipi = icp_ops->cause_ipi;
+	}
 }
 
 static struct smp_ops_t pnv_smp_ops = {
-	.message_pass	= smp_muxed_ipi_message_pass,
-	.cause_ipi	= NULL, /* Filled at runtime by xi{cs,ve}_smp_probe() */
+	.message_pass	= NULL, /* Use smp_muxed_ipi_message_pass */
+	.cause_ipi	= NULL,	/* Filled at runtime by pnv_smp_probe() */
 	.probe		= pnv_smp_probe,
 	.prepare_cpu	= pnv_smp_prepare_cpu,
 	.kick_cpu	= pnv_smp_kick_cpu,
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index f6f83aeccaaa..12ff5bef67fd 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -55,11 +55,6 @@
  */
 static cpumask_var_t of_spin_mask;
 
-/*
- * If we multiplex IPI mechanisms, store the appropriate XICS IPI mechanism here
- */
-static void  (*xics_cause_ipi)(int cpu, unsigned long data);
-
 /* Query where a cpu is now.  Return codes #defined in plpar_wrappers.h */
 int smp_query_cpu_stopped(unsigned int pcpu)
 {
@@ -143,8 +138,6 @@ static void smp_setup_cpu(int cpu)
 {
 	if (cpu != boot_cpuid)
 		xics_setup_cpu();
-	if (cpu_has_feature(CPU_FTR_DBELL))
-		doorbell_setup_this_cpu();
 
 	if (firmware_has_feature(FW_FEATURE_SPLPAR))
 		vpa_init(cpu);
@@ -187,23 +180,23 @@ static int smp_pSeries_kick_cpu(int nr)
 	return 0;
 }
 
-/* Only used on systems that support multiple IPI mechanisms */
-static void pSeries_cause_ipi_mux(int cpu, unsigned long data)
+static void smp_pseries_cause_ipi(int cpu)
 {
-	if (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id())))
-		doorbell_cause_ipi(cpu, data);
-	else
-		xics_cause_ipi(cpu, data);
+	/* POWER9 should not use this handler */
+	if (doorbell_try_core_ipi(cpu))
+		return;
+
+	icp_ops->cause_ipi(cpu);
 }
 
 static __init void pSeries_smp_probe(void)
 {
 	xics_smp_probe();
 
-	if (cpu_has_feature(CPU_FTR_DBELL)) {
-		xics_cause_ipi = smp_ops->cause_ipi;
-		smp_ops->cause_ipi = pSeries_cause_ipi_mux;
-	}
+	if (cpu_has_feature(CPU_FTR_DBELL))
+		smp_ops->cause_ipi = smp_pseries_cause_ipi;
+	else
+		smp_ops->cause_ipi = icp_ops->cause_ipi;
 }
 
 static struct smp_ops_t pseries_smp_ops = {
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index e7fa26c4ff73..bbc839a98c41 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -138,7 +138,7 @@ static void icp_hv_set_cpu_priority(unsigned char cppr)
 
 #ifdef CONFIG_SMP
 
-static void icp_hv_cause_ipi(int cpu, unsigned long data)
+static void icp_hv_cause_ipi(int cpu)
 {
 	icp_hv_set_qirr(cpu, IPI_PRIORITY);
 }
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index f0f3f47a3fc9..2bfb9968d562 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -143,19 +143,9 @@ static unsigned int icp_native_get_irq(void)
 
 #ifdef CONFIG_SMP
 
-static void icp_native_cause_ipi(int cpu, unsigned long data)
+static void icp_native_cause_ipi(int cpu)
 {
 	kvmppc_set_host_ipi(cpu, 1);
-#ifdef CONFIG_PPC_DOORBELL
-	if (cpu_has_feature(CPU_FTR_DBELL)) {
-		if (cpumask_test_cpu(cpu, cpu_sibling_mask(get_cpu()))) {
-			doorbell_cause_ipi(cpu, data);
-			put_cpu();
-			return;
-		}
-		put_cpu();
-	}
-#endif
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index b53f80f0b4d8..c71d2ea42627 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -126,7 +126,7 @@ static void icp_opal_eoi(struct irq_data *d)
 
 #ifdef CONFIG_SMP
 
-static void icp_opal_cause_ipi(int cpu, unsigned long data)
+static void icp_opal_cause_ipi(int cpu)
 {
 	int hw_cpu = get_hard_smp_processor_id(cpu);
 
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 23efe4e42172..2eb53c12ee6e 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -143,9 +143,6 @@ static void xics_request_ipi(void)
 
 void __init xics_smp_probe(void)
 {
-	/* Setup cause_ipi callback  based on which ICP is used */
-	smp_ops->cause_ipi = icp_ops->cause_ipi;
-
 	/* Register all the IPIs */
 	xics_request_ipi();
 }
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index d9cd7f705f21..6a98efb14264 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -834,15 +834,15 @@ static void xive_irq_free_data(unsigned int virq)
 
 #ifdef CONFIG_SMP
 
-static void xive_cause_ipi(int cpu, unsigned long msg)
+static void xive_cause_ipi(int cpu)
 {
 	struct xive_cpu *xc;
 	struct xive_irq_data *xd;
 
 	xc = per_cpu(xive_cpu, cpu);
 
-	DBG_VERBOSE("IPI msg#%ld CPU %d -> %d (HW IRQ 0x%x)\n",
-		    msg, smp_processor_id(), cpu, xc->hw_ipi);
+	DBG_VERBOSE("IPI CPU %d -> %d (HW IRQ 0x%x)\n",
+		    smp_processor_id(), cpu, xc->hw_ipi);
 
 	xd = &xc->ipi_data;
 	if (WARN_ON(!xd->trig_mmio))
-- 
2.11.0

[PATCH 2/4] powerpc: Introduce msgsnd/doorbell barrier primitives

[Nicholas Piggin]

POWER9 changes requirements and adds new instructions for
synchronization.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/dbell.h | 22 ++++++++++++++++++++++
 arch/powerpc/include/asm/smp.h   |  1 +
 arch/powerpc/kernel/dbell.c      |  8 +++++---
 arch/powerpc/kernel/smp.c        | 10 ++++++++--
 4 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index a66eb596940c..350694a1a6e5 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -44,6 +44,17 @@ static inline void _ppc_msgsnd(u32 msg)
 		__asm__ __volatile__ (PPC_MSGSNDP(%0) : : "r" (msg));
 }
 
+/* sync before sending message */
+static inline void ppc_msgsnd_sync(void)
+{
+	__asm__ __volatile__ ("sync" : : : "memory");
+}
+
+/* sync after taking message interrupt */
+static inline void ppc_msgsync(void)
+{
+}
+
 #else /* CONFIG_PPC_BOOK3S */
 
 #define PPC_DBELL_MSGTYPE		PPC_DBELL
@@ -53,6 +64,17 @@ static inline void _ppc_msgsnd(u32 msg)
 	__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
 }
 
+/* sync before sending message */
+static inline void ppc_msgsnd_sync(void)
+{
+	__asm__ __volatile__ ("sync" : : : "memory");
+}
+
+/* sync after taking message interrupt */
+static inline void ppc_msgsync(void)
+{
+}
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 extern void doorbell_global_ipi(int cpu);
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index d9ed3b02615e..751b2bd944fc 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -128,6 +128,7 @@ extern const char *smp_ipi_name[];
 extern void smp_muxed_ipi_message_pass(int cpu, int msg);
 extern void smp_muxed_ipi_set_message(int cpu, int msg);
 extern irqreturn_t smp_ipi_demux(void);
+extern irqreturn_t smp_ipi_demux_relaxed(void);
 
 void smp_init_pSeries(void);
 void smp_init_cell(void);
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 5869c66adfd0..b6fe883b1016 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -38,7 +38,7 @@ void doorbell_global_ipi(int cpu)
 
 	kvmppc_set_host_ipi(cpu, 1);
 	/* Order previous accesses vs. msgsnd, which is treated as a store */
-	mb();
+	ppc_msgsnd_sync();
 	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
 }
 
@@ -53,7 +53,7 @@ void doorbell_core_ipi(int cpu)
 
 	kvmppc_set_host_ipi(cpu, 1);
 	/* Order previous accesses vs. msgsnd, which is treated as a store */
-	mb();
+	ppc_msgsnd_sync();
 	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
 }
 
@@ -82,12 +82,14 @@ void doorbell_exception(struct pt_regs *regs)
 
 	irq_enter();
 
+	ppc_msgsync();
+
 	may_hard_irq_enable();
 
 	kvmppc_set_host_ipi(smp_processor_id(), 0);
 	__this_cpu_inc(irq_stat.doorbell_irqs);
 
-	smp_ipi_demux();
+	smp_ipi_demux_relaxed(); /* already performed the barrier */
 
 	irq_exit();
 	set_irq_regs(old_regs);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 17de938d41c5..2eca1e491e2b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -246,11 +246,17 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 
 irqreturn_t smp_ipi_demux(void)
 {
+	mb();	/* order any irq clear */
+
+	return smp_ipi_demux_relaxed();
+}
+
+/* sync-free variant. Callers should ensure synchronization */
+irqreturn_t smp_ipi_demux_relaxed(void)
+{
 	struct cpu_messages *info;
 	unsigned long all;
 
-	mb();	/* order any irq clear */
-
 	info = this_cpu_ptr(&ipi_message);
 	do {
 		all = xchg(&info->messages, 0);
-- 
2.11.0

[PATCH 3/4] powerpc/64s: avoid branch for ppc_msgsnd

[Nicholas Piggin]

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/dbell.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 350694a1a6e5..040944659a20 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -38,10 +38,8 @@ enum ppc_dbell {
 
 static inline void _ppc_msgsnd(u32 msg)
 {
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
-	else
-		__asm__ __volatile__ (PPC_MSGSNDP(%0) : : "r" (msg));
+	__asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSND(%1), PPC_MSGSNDP(%1), %0)
+				: : "i" (CPU_FTR_HVMODE), "r" (msg));
 }
 
 /* sync before sending message */
-- 
2.11.0

[PATCH 4/4] powerpc/powernv: POWER9 support for msgsnd/doorbell IPI

[Nicholas Piggin]

POWER9 requires msgsync for receiver-side synchronization, and a DD1
workaround restricts IPIs to core-local.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/dbell.h          |  3 +++
 arch/powerpc/include/asm/feature-fixups.h | 20 ++++++++++++++++++++
 arch/powerpc/include/asm/ppc-opcode.h     |  2 ++
 arch/powerpc/include/asm/ppc_asm.h        |  8 ++++++++
 arch/powerpc/platforms/powernv/smp.c      | 28 ++++++++++++++++++++++++++--
 5 files changed, 59 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 040944659a20..f70cbfe0ec04 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -51,6 +51,9 @@ static inline void ppc_msgsnd_sync(void)
 /* sync after taking message interrupt */
 static inline void ppc_msgsync(void)
 {
+	/* sync is not required when taking messages from the same core */
+	__asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSYNC " ; lwsync", "", %0)
+				: : "i" (CPU_FTR_HVMODE|CPU_FTR_ARCH_300));
 }
 
 #else /* CONFIG_PPC_BOOK3S */
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index ddf54f5bbdd1..d6b8c9a20496 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -66,7 +66,14 @@ label##5:							\
 #define END_FTR_SECTION(msk, val)		\
 	END_FTR_SECTION_NESTED(msk, val, 97)
 
+#define END_FTR_SECTION_NESTED_IFSET(msk, label) \
+	END_FTR_SECTION_NESTED((msk), (msk), label)
+
 #define END_FTR_SECTION_IFSET(msk)	END_FTR_SECTION((msk), (msk))
+
+#define END_FTR_SECTION_NESTED_IFCLR(msk, label) \
+	END_FTR_SECTION_NESTED((msk), 0, label)
+
 #define END_FTR_SECTION_IFCLR(msk)	END_FTR_SECTION((msk), 0)
 
 /* CPU feature sections with alternatives, use BEGIN_FTR_SECTION to start */
@@ -153,12 +160,25 @@ label##5:							\
 	section_else "; "					\
 	stringify_in_c(ALT_FTR_SECTION_END((msk), (val)))
 
+#define ASM_FTR_IF_NESTED(section_if, section_else, msk, val, label)	\
+	stringify_in_c(BEGIN_FTR_SECTION_NESTED(label))		\
+	section_if "; "						\
+	stringify_in_c(FTR_SECTION_ELSE_NESTED(label))		\
+	section_else "; "					\
+	stringify_in_c(ALT_FTR_SECTION_END_NESTED((msk), (val), label))
+
 #define ASM_FTR_IFSET(section_if, section_else, msk)	\
 	ASM_FTR_IF(section_if, section_else, (msk), (msk))
 
+#define ASM_FTR_IFSET_NESTED(section_if, section_else, msk, label)	\
+	ASM_FTR_IF(section_if, section_else, (msk), (msk), label)
+
 #define ASM_FTR_IFCLR(section_if, section_else, msk)	\
 	ASM_FTR_IF(section_if, section_else, (msk), 0)
 
+#define ASM_FTR_IFCLR_NESTED(section_if, section_else, msk, label)	\
+	ASM_FTR_IF(section_if, section_else, (msk), 0, label)
+
 #define ASM_MMU_FTR_IF(section_if, section_else, msk, val)	\
 	stringify_in_c(BEGIN_MMU_FTR_SECTION)			\
 	section_if "; "						\
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index e7d6d86563ee..142d78d645f4 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -161,6 +161,7 @@
 #define PPC_INST_MFTMR			0x7c0002dc
 #define PPC_INST_MSGSND			0x7c00019c
 #define PPC_INST_MSGCLR			0x7c0001dc
+#define PPC_INST_MSGSYNC		0x7c0006ec
 #define PPC_INST_MSGSNDP		0x7c00011c
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
@@ -345,6 +346,7 @@
 					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
 					___PPC_RB(b))
+#define PPC_MSGSYNC		stringify_in_c(.long PPC_INST_MSGSYNC)
 #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 | \
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 359c44341761..4d9cac8b1066 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -402,6 +402,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 	FTR_SECTION_ELSE_NESTED(848);	\
 	mtocrf (FXM), RS;		\
 	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_NOEXECUTE, 848)
+
+#if defined(CONFIG_BOOKS)
+#define MSGSYNC(reg)			\
+	BEGIN_FTR_SECTION_NESTED(849);	\
+	PPC_MSGSYNC;			\
+	lwsync;				\
+	END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE|CPU_FTR_ARCH_300, 849)
+#endif
 #endif
 
 /*
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 33bd4dd2cb41..951a2e230cfa 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -257,6 +257,23 @@ static void pnv_cause_ipi(int cpu)
 	icp_ops->cause_ipi(cpu);
 }
 
+static void pnv_p9_dd1_cause_ipi(int cpu)
+{
+	int this_cpu = get_cpu();
+
+	/*
+	 * POWER9 DD1 has a global addressed msgsnd, but for now we restrict
+	 * IPIs to same core, because it requires additional synchronization
+	 * for inter-core doorbells which we do not implement.
+	 */
+	if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu)))
+		doorbell_global_ipi(cpu);
+	else
+		icp_ops->cause_ipi(cpu);
+
+	put_cpu();
+}
+
 static void __init pnv_smp_probe(void)
 {
 	if (xive_enabled())
@@ -264,8 +281,15 @@ static void __init pnv_smp_probe(void)
 	else
 		xics_smp_probe();
 
-	if (cpu_has_feature(CPU_FTR_DBELL) && !cpu_has_feature(CPU_FTR_ARCH_300)) {
-		smp_ops->cause_ipi = pnv_cause_ipi;
+	if (cpu_has_feature(CPU_FTR_DBELL)) {
+		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+			if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+				smp_ops->cause_ipi = pnv_p9_dd1_cause_ipi;
+			else
+				smp_ops->cause_ipi = doorbell_global_ipi;
+		} else {
+			smp_ops->cause_ipi = pnv_cause_ipi;
+		}
 	} else {
 		smp_ops->cause_ipi = icp_ops->cause_ipi;
 	}
-- 
2.11.0

Re: [1/4] powerpc: change the doorbell IPI calling convention

[Michael Ellerman]

On Thu, 2017-04-13 at 10:16:21 UTC, Nicholas Piggin wrote:
> Change the doorbell callers to know about their msgsnd addressing,
> rather than have them set a per-cpu target data tag at boot that gets
> sent to the cause_ipi functions. The data is only used for doorbell IPI
> functions, no other IPI types, so it makes sense to keep that detail
> local to doorbell.
> 
> Have the platform code understand doorbell IPIs, rather than the
> interrupt controller code understand them. Platform code can look at
> capabilities it has available and decide which to use.
> 
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

Series applied to powerpc next, thanks.

https://git.kernel.org/powerpc/c/b866cc2199d6a6cdcefe4acfe4cfca

cheers