[OpenRISC] [PATCH v4 01/13] openrisc: use shadow registers to save regs on exception

[OpenRISC] [PATCH v4 01/13] openrisc: use shadow registers to save regs on exception

[Stafford Horne]

From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>

Previously, the area between 0x0-0x100 have been used as a "scratch"
memory area to temporarily store regs during exception entry. In a
multi-core environment, this will not work.

This change is to use shadow registers for nested context.

Currently only the "critical" temp load/stores are covered, the
EMERGENCY_PRINT ones are left as is (when they are used, it's game over
anyway), they need to be handled as well in the future.

Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Signed-off-by: Stafford Horne <shorne@gmail.com>
---

Changes since v2
 - None

Changes since v1
 - Added SMP checks in Kconfig

 arch/openrisc/Kconfig       | 11 ++++++
 arch/openrisc/kernel/head.S | 95 ++++++++++++++++++++++++++++++++-------------
 2 files changed, 80 insertions(+), 26 deletions(-)

diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index a0f2e4a323c1..356dd67a86ea 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -124,6 +124,17 @@ config OPENRISC_NO_SPR_SR_DSX
 	  Say N here if you know that your OpenRISC processor has
 	  SPR_SR_DSX bit implemented. Say Y if you are unsure.
 
+config OPENRISC_HAVE_SHADOW_GPRS
+	bool "Support for shadow gpr files" if !SMP
+	default y if SMP
+	help
+	  Say Y here if your OpenRISC processor features shadowed
+	  register files. They will in such case be used as a
+	  scratch reg storage on exception entry.
+
+	  On SMP systems, this feature is mandatory.
+	  On a unicore system it's safe to say N here if you are unsure.
+
 config CMDLINE
         string "Default kernel command string"
         default ""
diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index 1e87913576e3..1e49895408f4 100644
--- a/arch/openrisc/kernel/head.S
+++ b/arch/openrisc/kernel/head.S
@@ -49,9 +49,31 @@
 
 /* ============================================[ tmp store locations ]=== */
 
+#define SPR_SHADOW_GPR(x)	((x) + SPR_GPR_BASE + 32)
+
 /*
  * emergency_print temporary stores
  */
+#ifdef CONFIG_OPENRISC_HAVE_SHADOW_GPRS
+#define EMERGENCY_PRINT_STORE_GPR4	l.mtspr r0,r4,SPR_SHADOW_GPR(14)
+#define EMERGENCY_PRINT_LOAD_GPR4	l.mfspr r4,r0,SPR_SHADOW_GPR(14)
+
+#define EMERGENCY_PRINT_STORE_GPR5	l.mtspr r0,r5,SPR_SHADOW_GPR(15)
+#define EMERGENCY_PRINT_LOAD_GPR5	l.mfspr r5,r0,SPR_SHADOW_GPR(15)
+
+#define EMERGENCY_PRINT_STORE_GPR6	l.mtspr r0,r6,SPR_SHADOW_GPR(16)
+#define EMERGENCY_PRINT_LOAD_GPR6	l.mfspr r6,r0,SPR_SHADOW_GPR(16)
+
+#define EMERGENCY_PRINT_STORE_GPR7	l.mtspr r0,r7,SPR_SHADOW_GPR(7)
+#define EMERGENCY_PRINT_LOAD_GPR7	l.mfspr r7,r0,SPR_SHADOW_GPR(7)
+
+#define EMERGENCY_PRINT_STORE_GPR8	l.mtspr r0,r8,SPR_SHADOW_GPR(8)
+#define EMERGENCY_PRINT_LOAD_GPR8	l.mfspr r8,r0,SPR_SHADOW_GPR(8)
+
+#define EMERGENCY_PRINT_STORE_GPR9	l.mtspr r0,r9,SPR_SHADOW_GPR(9)
+#define EMERGENCY_PRINT_LOAD_GPR9	l.mfspr r9,r0,SPR_SHADOW_GPR(9)
+
+#else /* !CONFIG_OPENRISC_HAVE_SHADOW_GPRS */
 #define EMERGENCY_PRINT_STORE_GPR4	l.sw    0x20(r0),r4
 #define EMERGENCY_PRINT_LOAD_GPR4	l.lwz   r4,0x20(r0)
 
@@ -70,13 +92,28 @@
 #define EMERGENCY_PRINT_STORE_GPR9	l.sw    0x34(r0),r9
 #define EMERGENCY_PRINT_LOAD_GPR9	l.lwz   r9,0x34(r0)
 
+#endif
 
 /*
  * TLB miss handlers temorary stores
  */
-#define EXCEPTION_STORE_GPR9		l.sw    0x10(r0),r9
-#define EXCEPTION_LOAD_GPR9		l.lwz   r9,0x10(r0)
+#ifdef CONFIG_OPENRISC_HAVE_SHADOW_GPRS
+#define EXCEPTION_STORE_GPR2		l.mtspr r0,r2,SPR_SHADOW_GPR(2)
+#define EXCEPTION_LOAD_GPR2		l.mfspr r2,r0,SPR_SHADOW_GPR(2)
+
+#define EXCEPTION_STORE_GPR3		l.mtspr r0,r3,SPR_SHADOW_GPR(3)
+#define EXCEPTION_LOAD_GPR3		l.mfspr r3,r0,SPR_SHADOW_GPR(3)
 
+#define EXCEPTION_STORE_GPR4		l.mtspr r0,r4,SPR_SHADOW_GPR(4)
+#define EXCEPTION_LOAD_GPR4		l.mfspr r4,r0,SPR_SHADOW_GPR(4)
+
+#define EXCEPTION_STORE_GPR5		l.mtspr r0,r5,SPR_SHADOW_GPR(5)
+#define EXCEPTION_LOAD_GPR5		l.mfspr r5,r0,SPR_SHADOW_GPR(5)
+
+#define EXCEPTION_STORE_GPR6		l.mtspr r0,r6,SPR_SHADOW_GPR(6)
+#define EXCEPTION_LOAD_GPR6		l.mfspr r6,r0,SPR_SHADOW_GPR(6)
+
+#else /* !CONFIG_OPENRISC_HAVE_SHADOW_GPRS */
 #define EXCEPTION_STORE_GPR2		l.sw    0x64(r0),r2
 #define EXCEPTION_LOAD_GPR2		l.lwz   r2,0x64(r0)
 
@@ -92,26 +129,32 @@
 #define EXCEPTION_STORE_GPR6		l.sw    0x74(r0),r6
 #define EXCEPTION_LOAD_GPR6		l.lwz   r6,0x74(r0)
 
+#endif
 
 /*
  * EXCEPTION_HANDLE temporary stores
  */
 
+#ifdef CONFIG_OPENRISC_HAVE_SHADOW_GPRS
+#define EXCEPTION_T_STORE_GPR30		l.mtspr r0,r30,SPR_SHADOW_GPR(30)
+#define EXCEPTION_T_LOAD_GPR30(reg)	l.mfspr reg,r0,SPR_SHADOW_GPR(30)
+
+#define EXCEPTION_T_STORE_GPR10		l.mtspr r0,r10,SPR_SHADOW_GPR(10)
+#define EXCEPTION_T_LOAD_GPR10(reg)	l.mfspr reg,r0,SPR_SHADOW_GPR(10)
+
+#define EXCEPTION_T_STORE_SP		l.mtspr r0,r1,SPR_SHADOW_GPR(1)
+#define EXCEPTION_T_LOAD_SP(reg)	l.mfspr reg,r0,SPR_SHADOW_GPR(1)
+
+#else /* !CONFIG_OPENRISC_HAVE_SHADOW_GPRS */
 #define EXCEPTION_T_STORE_GPR30		l.sw    0x78(r0),r30
 #define EXCEPTION_T_LOAD_GPR30(reg)	l.lwz   reg,0x78(r0)
 
 #define EXCEPTION_T_STORE_GPR10		l.sw    0x7c(r0),r10
 #define EXCEPTION_T_LOAD_GPR10(reg)	l.lwz   reg,0x7c(r0)
 
-#define EXCEPTION_T_STORE_SP		l.sw	0x80(r0),r1
+#define EXCEPTION_T_STORE_SP		l.sw    0x80(r0),r1
 #define EXCEPTION_T_LOAD_SP(reg)	l.lwz   reg,0x80(r0)
-
-/*
- * For UNHANLDED_EXCEPTION
- */
-
-#define EXCEPTION_T_STORE_GPR31		l.sw    0x84(r0),r31
-#define EXCEPTION_T_LOAD_GPR31(reg)	l.lwz   reg,0x84(r0)
+#endif
 
 /* =========================================================[ macros ]=== */
 
@@ -226,7 +269,7 @@
  *
  */
 #define UNHANDLED_EXCEPTION(handler)				\
-	EXCEPTION_T_STORE_GPR31					;\
+	EXCEPTION_T_STORE_GPR30					;\
 	EXCEPTION_T_STORE_GPR10					;\
 	EXCEPTION_T_STORE_SP					;\
 	/* temporary store r3, r9 into r1, r10 */		;\
@@ -255,35 +298,35 @@
 	/* r1: KSP, r10: current, r31: __pa(KSP) */		;\
 	/* r12:	temp, syscall indicator, r13 temp */		;\
 	l.addi  r1,r1,-(INT_FRAME_SIZE)				;\
-	/* r1 is KSP, r31 is __pa(KSP) */			;\
-	tophys  (r31,r1)					;\
-	l.sw    PT_GPR12(r31),r12					;\
+	/* r1 is KSP, r30 is __pa(KSP) */			;\
+	tophys  (r30,r1)					;\
+	l.sw    PT_GPR12(r30),r12					;\
 	l.mfspr r12,r0,SPR_EPCR_BASE				;\
-	l.sw    PT_PC(r31),r12					;\
+	l.sw    PT_PC(r30),r12					;\
 	l.mfspr r12,r0,SPR_ESR_BASE				;\
-	l.sw    PT_SR(r31),r12					;\
+	l.sw    PT_SR(r30),r12					;\
 	/* save r31 */						;\
-	EXCEPTION_T_LOAD_GPR31(r12)				;\
-	l.sw	PT_GPR31(r31),r12					;\
+	EXCEPTION_T_LOAD_GPR30(r12)				;\
+	l.sw	PT_GPR30(r30),r12					;\
 	/* save r10 as was prior to exception */		;\
 	EXCEPTION_T_LOAD_GPR10(r12)				;\
-	l.sw	PT_GPR10(r31),r12					;\
+	l.sw	PT_GPR10(r30),r12					;\
 	/* save PT_SP as was prior to exception */			;\
 	EXCEPTION_T_LOAD_SP(r12)				;\
-	l.sw	PT_SP(r31),r12					;\
-	l.sw    PT_GPR13(r31),r13					;\
+	l.sw	PT_SP(r30),r12					;\
+	l.sw    PT_GPR13(r30),r13					;\
 	/* --> */						;\
 	/* save exception r4, set r4 = EA */			;\
-	l.sw	PT_GPR4(r31),r4					;\
+	l.sw	PT_GPR4(r30),r4					;\
 	l.mfspr r4,r0,SPR_EEAR_BASE				;\
 	/* r12 == 1 if we come from syscall */			;\
 	CLEAR_GPR(r12)						;\
 	/* ----- play a MMU trick ----- */			;\
-	l.ori	r31,r0,(EXCEPTION_SR)				;\
-	l.mtspr	r0,r31,SPR_ESR_BASE				;\
+	l.ori	r30,r0,(EXCEPTION_SR)				;\
+	l.mtspr	r0,r30,SPR_ESR_BASE				;\
 	/* r31:	EA address of handler */			;\
-	LOAD_SYMBOL_2_GPR(r31,handler)				;\
-	l.mtspr r0,r31,SPR_EPCR_BASE				;\
+	LOAD_SYMBOL_2_GPR(r30,handler)				;\
+	l.mtspr r0,r30,SPR_EPCR_BASE				;\
 	l.rfe
 
 /* =====================================================[ exceptions] === */
-- 
2.13.6

[OpenRISC] [PATCH v4 02/13] openrisc: add 1 and 2 byte cmpxchg support

[Stafford Horne]

OpenRISC only supports hardware instructions that perform 4 byte atomic
operations.  For enabling qrwlocks for upcoming SMP support 1 and 2 byte
implementations are needed.  To do this we leverage the 4 byte atomic
operations and shift/mask the 1 and 2 byte areas as needed.

This heavily borrows ideas and routines from sh and mips, which do
something similar.

Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/include/asm/cmpxchg.h | 147 ++++++++++++++++++++++++++++--------
 1 file changed, 115 insertions(+), 32 deletions(-)

diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index f0a5d8b844d6..d29f7db53906 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -1,32 +1,29 @@
 /*
+ * 1,2 and 4 byte cmpxchg and xchg implementations for OpenRISC.
+ *
  * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
  *
  * This file is licensed under the terms of the GNU General Public License
  * version 2.  This program is licensed "as is" without any warranty of any
  * kind, whether express or implied.
+ *
+ * Note:
+ * The portable implementations of 1 and 2 byte xchg and cmpxchg using a 4
+ * byte cmpxchg is sourced heavily from the sh and mips implementations.
  */
 
 #ifndef __ASM_OPENRISC_CMPXCHG_H
 #define __ASM_OPENRISC_CMPXCHG_H
 
 #include  <linux/types.h>
-
-/*
- * This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid cmpxchg().
- */
-extern void __cmpxchg_called_with_bad_pointer(void);
+#include  <linux/bitops.h>
 
 #define __HAVE_ARCH_CMPXCHG 1
 
-static inline unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
+static inline unsigned long cmpxchg_u32(volatile void *ptr,
+		unsigned long old, unsigned long new)
 {
-	if (size != 4) {
-		__cmpxchg_called_with_bad_pointer();
-		return old;
-	}
-
 	__asm__ __volatile__(
 		"1:	l.lwa %0, 0(%1)		\n"
 		"	l.sfeq %0, %2		\n"
@@ -43,6 +40,97 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 	return old;
 }
 
+static inline unsigned long xchg_u32(volatile void *ptr,
+		unsigned long val)
+{
+	__asm__ __volatile__(
+		"1:	l.lwa %0, 0(%1)		\n"
+		"	l.swa 0(%1), %2		\n"
+		"	l.bnf 1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(val)
+		: "r"(ptr), "r"(val)
+		: "cc", "memory");
+
+	return val;
+}
+
+static inline u32 cmpxchg_small(volatile void *ptr, u32 old, u32 new,
+				int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - size - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 load32, old32, new32;
+	u32 ret;
+
+	load32 = READ_ONCE(*p);
+
+	while (true) {
+		ret = (load32 & bitmask) >> bitoff;
+		if (old != ret)
+			return ret;
+
+		old32 = (load32 & ~bitmask) | (old << bitoff);
+		new32 = (load32 & ~bitmask) | (new << bitoff);
+
+		/* Do 32 bit cmpxchg */
+		load32 = cmpxchg_u32(p, old32, new32);
+		if (load32 == old32)
+			return old;
+	}
+}
+
+/* xchg */
+
+static inline u32 xchg_small(volatile void *ptr, u32 x, int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - size - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 oldv, newv;
+	u32 ret;
+
+	do {
+		oldv = READ_ONCE(*p);
+		ret = (oldv & bitmask) >> bitoff;
+		newv = (oldv & ~bitmask) | (x << bitoff);
+	} while (cmpxchg_u32(p, oldv, newv) != oldv);
+
+	return ret;
+}
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg().
+ */
+extern unsigned long __cmpxchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for cmpxchg");
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+		unsigned long new, int size)
+{
+	switch (size) {
+	case 1:
+	case 2:
+		return cmpxchg_small(ptr, old, new, size);
+	case 4:
+		return cmpxchg_u32(ptr, old, new);
+	default:
+		return __cmpxchg_called_with_bad_pointer();
+	}
+}
+
 #define cmpxchg(ptr, o, n)						\
 	({								\
 		(__typeof__(*(ptr))) __cmpxchg((ptr),			\
@@ -55,32 +143,27 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
  * This function doesn't exist, so you'll get a linker error if
  * something tries to do an invalidly-sized xchg().
  */
-extern void __xchg_called_with_bad_pointer(void);
+extern unsigned long __xchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for xchg");
 
-static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
-				   int size)
+static inline unsigned long __xchg(volatile void *ptr, unsigned long with,
+		int size)
 {
-	if (size != 4) {
-		__xchg_called_with_bad_pointer();
-		return val;
+	switch (size) {
+	case 1:
+	case 2:
+		return xchg_small(ptr, with, size);
+	case 4:
+		return xchg_u32(ptr, with);
+	default:
+		return __xchg_called_with_bad_pointer();
 	}
-
-	__asm__ __volatile__(
-		"1:	l.lwa %0, 0(%1)		\n"
-		"	l.swa 0(%1), %2		\n"
-		"	l.bnf 1b		\n"
-		"	 l.nop			\n"
-		: "=&r"(val)
-		: "r"(ptr), "r"(val)
-		: "cc", "memory");
-
-	return val;
 }
 
 #define xchg(ptr, with) 						\
 	({								\
-		(__typeof__(*(ptr))) __xchg((unsigned long)(with),	\
-					    (ptr),			\
+		(__typeof__(*(ptr))) __xchg((ptr),			\
+					    (unsigned long)(with),	\
 					    sizeof(*(ptr)));		\
 	})
 
-- 
2.13.6

[OpenRISC] [PATCH v4 03/13] openrisc: use qspinlocks and qrwlocks

[Stafford Horne]

Enable OpenRISC to use qspinlocks and qrwlocks for upcoming SMP support.

Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/Kconfig                      |  2 ++
 arch/openrisc/include/asm/Kbuild           |  4 ++++
 arch/openrisc/include/asm/spinlock.h       | 12 +++++++++++-
 arch/openrisc/include/asm/spinlock_types.h |  7 +++++++
 4 files changed, 24 insertions(+), 1 deletion(-)
 create mode 100644 arch/openrisc/include/asm/spinlock_types.h

diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 356dd67a86ea..b49acda5e8f4 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -28,6 +28,8 @@ config OPENRISC
 	select OR1K_PIC
 	select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1
 	select NO_BOOTMEM
+	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_USE_QUEUED_RWLOCKS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 5bea416a7792..5f066780d870 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -28,6 +28,10 @@ generic-y += module.h
 generic-y += pci.h
 generic-y += percpu.h
 generic-y += preempt.h
+generic-y += qspinlock_types.h
+generic-y += qspinlock.h
+generic-y += qrwlock_types.h
+generic-y += qrwlock.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += string.h
diff --git a/arch/openrisc/include/asm/spinlock.h b/arch/openrisc/include/asm/spinlock.h
index fd00a3a24123..9b761e0e22c3 100644
--- a/arch/openrisc/include/asm/spinlock.h
+++ b/arch/openrisc/include/asm/spinlock.h
@@ -19,6 +19,16 @@
 #ifndef __ASM_OPENRISC_SPINLOCK_H
 #define __ASM_OPENRISC_SPINLOCK_H
 
-#error "or32 doesn't do SMP yet"
+#include <asm/qspinlock.h>
+
+#include <asm/qrwlock.h>
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
+
 
 #endif
diff --git a/arch/openrisc/include/asm/spinlock_types.h b/arch/openrisc/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..7c6fb1208c88
--- /dev/null
+++ b/arch/openrisc/include/asm/spinlock_types.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_OPENRISC_SPINLOCK_TYPES_H
+#define _ASM_OPENRISC_SPINLOCK_TYPES_H
+
+#include <asm/qspinlock_types.h>
+#include <asm/qrwlock_types.h>
+
+#endif /* _ASM_OPENRISC_SPINLOCK_TYPES_H */
-- 
2.13.6

[OpenRISC] [PATCH v4 05/13] irqchip: add initial support for ompic

[Stafford Horne]

From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>

IPI driver for the Open Multi-Processor Interrupt Controller (ompic) as
described in the Multi-core support section of the OpenRISC 1.2
architecture specification:

  https://github.com/openrisc/doc/raw/master/openrisc-arch-1.2-rev0.pdf

Each OpenRISC core contains a full interrupt controller which is used in
the SMP architecture for interrupt balancing.  This IPI device, the
ompic, is the only external device required for enabling SMP on
OpenRISC.

Pending ops are stored in a memory bit mask which can allow multiple
pending operations to be set and serviced at a time. This is mostly
borrowed from the alpha IPI implementation.

Cc: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
[shorne at gmail.com: converted ops to bitmask, wrote commit message]
Signed-off-by: Stafford Horne <shorne@gmail.com>
---

Changes since v3
 - Change irq setup to request_irq

Changes since v2
 - Fixed some issues with missing static
 - Fixed spelling issue with multi-core
 - Added back #interrupt-cells

Changes since v1
 - Added openrisc, prefix
 - Clarified 8 bytes per cpu
 - Removed #interrupt-cells as this will not be an irq parent
 - Changed ops to be percpu
 - Added DTS and intialization failure validations

 .../interrupt-controller/openrisc,ompic.txt        |  22 +++
 MAINTAINERS                                        |   1 +
 arch/openrisc/Kconfig                              |   1 +
 drivers/irqchip/Kconfig                            |   3 +
 drivers/irqchip/Makefile                           |   1 +
 drivers/irqchip/irq-ompic.c                        | 202 +++++++++++++++++++++
 6 files changed, 230 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/interrupt-controller/openrisc,ompic.txt
 create mode 100644 drivers/irqchip/irq-ompic.c

diff --git a/Documentation/devicetree/bindings/interrupt-controller/openrisc,ompic.txt b/Documentation/devicetree/bindings/interrupt-controller/openrisc,ompic.txt
new file mode 100644
index 000000000000..caec07cc7149
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/openrisc,ompic.txt
@@ -0,0 +1,22 @@
+Open Multi-Processor Interrupt Controller
+
+Required properties:
+
+- compatible : This should be "openrisc,ompic"
+- reg : Specifies base physical address and size of the register space. The
+  size is based on the number of cores the controller has been configured
+  to handle, this should be set to 8 bytes per cpu core.
+- interrupt-controller : Identifies the node as an interrupt controller.
+- #interrupt-cells : This should be set to 0 as this will not be an irq
+  parent.
+- interrupts : Specifies the interrupt line to which the ompic is wired.
+
+Example:
+
+ompic: interrupt-controller at 98000000 {
+	compatible = "openrisc,ompic";
+	reg = <0x98000000 16>;
+	interrupt-controller;
+	#interrupt-cells = <0>;
+	interrupts = <1>;
+};
diff --git a/MAINTAINERS b/MAINTAINERS
index 2281af4b41b6..4d0255ce6e5f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10009,6 +10009,7 @@ L:	openrisc at lists.librecores.org
 W:	http://openrisc.io
 S:	Maintained
 F:	arch/openrisc/
+F:	drivers/irqchip/irq-ompic.c
 
 OPENVSWITCH
 M:	Pravin Shelar <pshelar@nicira.com>
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index b49acda5e8f4..34eb4e90f56c 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -30,6 +30,7 @@ config OPENRISC
 	select NO_BOOTMEM
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_USE_QUEUED_RWLOCKS
+	select OMPIC if SMP
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 9d8a1dd2e2c2..a2ca82f6c2dd 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -151,6 +151,9 @@ config CLPS711X_IRQCHIP
 	select SPARSE_IRQ
 	default y
 
+config OMPIC
+	bool
+
 config OR1K_PIC
 	bool
 	select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 845abc107ad5..771f8e7f46f8 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_DW_APB_ICTL)		+= irq-dw-apb-ictl.o
 obj-$(CONFIG_METAG)			+= irq-metag-ext.o
 obj-$(CONFIG_METAG_PERFCOUNTER_IRQS)	+= irq-metag.o
 obj-$(CONFIG_CLPS711X_IRQCHIP)		+= irq-clps711x.o
+obj-$(CONFIG_OMPIC)			+= irq-ompic.o
 obj-$(CONFIG_OR1K_PIC)			+= irq-or1k-pic.o
 obj-$(CONFIG_ORION_IRQCHIP)		+= irq-orion.o
 obj-$(CONFIG_OMAP_IRQCHIP)		+= irq-omap-intc.o
diff --git a/drivers/irqchip/irq-ompic.c b/drivers/irqchip/irq-ompic.c
new file mode 100644
index 000000000000..cf6d0c455518
--- /dev/null
+++ b/drivers/irqchip/irq-ompic.c
@@ -0,0 +1,202 @@
+/*
+ * Open Multi-Processor Interrupt Controller driver
+ *
+ * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ * The ompic device handles IPI communication between cores in multi-core
+ * OpenRISC systems.
+ *
+ * Registers
+ *
+ * For each CPU the ompic has 2 registers. The control register for sending
+ * and acking IPIs and the status register for receiving IPIs. The register
+ * layouts are as follows:
+ *
+ *  Control register
+ *  +---------+---------+----------+---------+
+ *  | 31      | 30      | 29 .. 16 | 15 .. 0 |
+ *  ----------+---------+----------+----------
+ *  | IRQ ACK | IRQ GEN | DST CORE | DATA    |
+ *  +---------+---------+----------+---------+
+ *
+ *  Status register
+ *  +----------+-------------+----------+---------+
+ *  | 31       | 30          | 29 .. 16 | 15 .. 0 |
+ *  -----------+-------------+----------+---------+
+ *  | Reserved | IRQ Pending | SRC CORE | DATA    |
+ *  +----------+-------------+----------+---------+
+ *
+ * Architecture
+ *
+ * - The ompic generates a level interrupt to the CPU PIC when a message is
+ *   ready.  Messages are delivered via the memory bus.
+ * - The ompic does not have any interrupt input lines.
+ * - The ompic is wired to the same irq line on each core.
+ * - Devices are wired to the same irq line on each core.
+ *
+ *   +---------+                         +---------+
+ *   | CPU     |                         | CPU     |
+ *   |  Core 0 |<==\ (memory access) /==>|  Core 1 |
+ *   |  [ PIC ]|   |                 |   |  [ PIC ]|
+ *   +----^-^--+   |                 |   +----^-^--+
+ *        | |      v                 v        | |
+ *   <====|=|=================================|=|==> (memory bus)
+ *        | |      ^                  ^       | |
+ *  (ipi  | +------|---------+--------|-------|-+ (device irq)
+ *   irq  |        |         |        |       |
+ *  core0)| +------|---------|--------|-------+ (ipi irq core1)
+ *        | |      |         |        |
+ *   +----o-o-+    |    +--------+    |
+ *   | ompic  |<===/    | Device |<===/
+ *   |  IPI   |         +--------+
+ *   +--------+*
+ *
+ */
+
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+#include <linux/irqchip.h>
+
+#define OMPIC_CPUBYTES		8
+#define OMPIC_CTRL(cpu)		(0x0 + (cpu * OMPIC_CPUBYTES))
+#define OMPIC_STAT(cpu)		(0x4 + (cpu * OMPIC_CPUBYTES))
+
+#define OMPIC_CTRL_IRQ_ACK	(1 << 31)
+#define OMPIC_CTRL_IRQ_GEN	(1 << 30)
+#define OMPIC_CTRL_DST(cpu)	(((cpu) & 0x3fff) << 16)
+
+#define OMPIC_STAT_IRQ_PENDING	(1 << 30)
+
+#define OMPIC_DATA(x)		((x) & 0xffff)
+
+DEFINE_PER_CPU(unsigned long, ops);
+
+static void __iomem *ompic_base;
+
+static inline u32 ompic_readreg(void __iomem *base, loff_t offset)
+{
+	return ioread32be(base + offset);
+}
+
+static void ompic_writereg(void __iomem *base, loff_t offset, u32 data)
+{
+	iowrite32be(data, base + offset);
+}
+
+static void ompic_raise_softirq(const struct cpumask *mask,
+				unsigned int ipi_msg)
+{
+	unsigned int dst_cpu;
+	unsigned int src_cpu = smp_processor_id();
+
+	for_each_cpu(dst_cpu, mask) {
+		set_bit(ipi_msg, &per_cpu(ops, dst_cpu));
+
+		/*
+		 * On OpenRISC the atomic set_bit() call implies a memory
+		 * barrier.  Otherwise we would need: smp_wmb(); paired
+		 * with the read in ompic_ipi_handler.
+		 */
+
+		ompic_writereg(ompic_base, OMPIC_CTRL(src_cpu),
+			       OMPIC_CTRL_IRQ_GEN |
+			       OMPIC_CTRL_DST(dst_cpu) |
+			       OMPIC_DATA(1));
+	}
+}
+
+static irqreturn_t ompic_ipi_handler(int irq, void *dev_id)
+{
+	unsigned int cpu = smp_processor_id();
+	unsigned long *pending_ops = &per_cpu(ops, cpu);
+	unsigned long ops;
+
+	ompic_writereg(ompic_base, OMPIC_CTRL(cpu), OMPIC_CTRL_IRQ_ACK);
+	while ((ops = xchg(pending_ops, 0)) != 0) {
+
+		/*
+		 * On OpenRISC the atomic xchg() call implies a memory
+		 * barrier.  Otherwise we may need an smp_rmb(); paired
+		 * with the write in ompic_raise_softirq.
+		 */
+
+		do {
+			unsigned long ipi_msg;
+
+			ipi_msg = __ffs(ops);
+			ops &= ~(1UL << ipi_msg);
+
+			handle_IPI(ipi_msg);
+		} while (ops);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int __init ompic_of_init(struct device_node *node,
+				struct device_node *parent)
+{
+	struct resource res;
+	int irq;
+	int ret;
+
+	/* Validate the DT */
+	if (ompic_base) {
+		pr_err("ompic: duplicate ompic's are not supported");
+		return -EEXIST;
+	}
+
+	if (of_address_to_resource(node, 0, &res)) {
+		pr_err("ompic: reg property requires an address and size");
+		return -EINVAL;
+	}
+
+	if (resource_size(&res) < (num_possible_cpus() * OMPIC_CPUBYTES)) {
+		pr_err("ompic: reg size, currently %d must be@least %d",
+			resource_size(&res),
+			(num_possible_cpus() * OMPIC_CPUBYTES));
+		return -EINVAL;
+	}
+
+	/* Setup the device */
+	ompic_base = ioremap(res.start, resource_size(&res));
+	if (IS_ERR(ompic_base)) {
+		pr_err("ompic: unable to map registers");
+		return PTR_ERR(ompic_base);
+	}
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq <= 0) {
+		pr_err("ompic: unable to parse device irq");
+		ret = -EINVAL;
+		goto out_unmap;
+	}
+
+	ret = request_irq(irq, ompic_ipi_handler, IRQF_PERCPU,
+				"ompic_ipi", NULL);
+	if (ret)
+		goto out_irq_disp;
+
+	set_smp_cross_call(ompic_raise_softirq);
+
+	return 0;
+
+out_irq_disp:
+	irq_dispose_mapping(irq);
+out_unmap:
+	iounmap(ompic_base);
+	ompic_base = NULL;
+	return ret;
+}
+IRQCHIP_DECLARE(ompic, "openrisc,ompic", ompic_of_init);
-- 
2.13.6

[OpenRISC] [PATCH v4 05/13] irqchip: add initial support for ompic

[Marc Zyngier]

On Mon, Oct 30 2017 at  8:11:15 am GMT, Stafford Horne <shorne@gmail.com> wrote:
> From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
>
> IPI driver for the Open Multi-Processor Interrupt Controller (ompic) as
> described in the Multi-core support section of the OpenRISC 1.2
> architecture specification:
>
>   https://github.com/openrisc/doc/raw/master/openrisc-arch-1.2-rev0.pdf
>
> Each OpenRISC core contains a full interrupt controller which is used in
> the SMP architecture for interrupt balancing.  This IPI device, the
> ompic, is the only external device required for enabling SMP on
> OpenRISC.
>
> Pending ops are stored in a memory bit mask which can allow multiple
> pending operations to be set and serviced at a time. This is mostly
> borrowed from the alpha IPI implementation.
>
> Cc: Marc Zyngier <marc.zyngier@arm.com>
> Acked-by: Rob Herring <robh@kernel.org>
> Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
> [shorne at gmail.com: converted ops to bitmask, wrote commit message]
> Signed-off-by: Stafford Horne <shorne@gmail.com>

Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>

Side question: what is your merge strategy for this? I can take it
through the irqchip tree as it is standalone, but I'm open to other
suggestions.

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny.

[OpenRISC] [PATCH v4 05/13] irqchip: add initial support for ompic

[Stafford Horne]

On Mon, Oct 30, 2017 at 02:29:18AM +0000, Marc Zyngier wrote:
> On Mon, Oct 30 2017 at  8:11:15 am GMT, Stafford Horne <shorne@gmail.com> wrote:
> > From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
> >
> > IPI driver for the Open Multi-Processor Interrupt Controller (ompic) as
> > described in the Multi-core support section of the OpenRISC 1.2
> > architecture specification:
> >
> >   https://github.com/openrisc/doc/raw/master/openrisc-arch-1.2-rev0.pdf
> >
> > Each OpenRISC core contains a full interrupt controller which is used in
> > the SMP architecture for interrupt balancing.  This IPI device, the
> > ompic, is the only external device required for enabling SMP on
> > OpenRISC.
> >
> > Pending ops are stored in a memory bit mask which can allow multiple
> > pending operations to be set and serviced at a time. This is mostly
> > borrowed from the alpha IPI implementation.
> >
> > Cc: Marc Zyngier <marc.zyngier@arm.com>
> > Acked-by: Rob Herring <robh@kernel.org>
> > Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
> > [shorne at gmail.com: converted ops to bitmask, wrote commit message]
> > Signed-off-by: Stafford Horne <shorne@gmail.com>
> 
> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>

Thanks

> Side question: what is your merge strategy for this? I can take it
> through the irqchip tree as it is standalone, but I'm open to other
> suggestions.

For me its easier if I just take it through the openrisc tree, as
there are dependencies between this series and the irqchip driver.
If you are ok with that I can make a note to Linus indicating so in
the pull request.

My plan is to send this series during the 4.15 merge window.

-Stafford

[OpenRISC] [PATCH v4 05/13] irqchip: add initial support for ompic

[Marc Zyngier]

On Mon, Oct 30 2017 at  1:18:06 pm GMT, Stafford Horne <shorne@gmail.com> wrote:
> On Mon, Oct 30, 2017 at 02:29:18AM +0000, Marc Zyngier wrote:
>> On Mon, Oct 30 2017 at  8:11:15 am GMT, Stafford Horne <shorne@gmail.com> wrote:
>> > From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
>> >
>> > IPI driver for the Open Multi-Processor Interrupt Controller (ompic) as
>> > described in the Multi-core support section of the OpenRISC 1.2
>> > architecture specification:
>> >
>> >   https://github.com/openrisc/doc/raw/master/openrisc-arch-1.2-rev0.pdf
>> >
>> > Each OpenRISC core contains a full interrupt controller which is used in
>> > the SMP architecture for interrupt balancing.  This IPI device, the
>> > ompic, is the only external device required for enabling SMP on
>> > OpenRISC.
>> >
>> > Pending ops are stored in a memory bit mask which can allow multiple
>> > pending operations to be set and serviced at a time. This is mostly
>> > borrowed from the alpha IPI implementation.
>> >
>> > Cc: Marc Zyngier <marc.zyngier@arm.com>
>> > Acked-by: Rob Herring <robh@kernel.org>
>> > Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
>> > [shorne at gmail.com: converted ops to bitmask, wrote commit message]
>> > Signed-off-by: Stafford Horne <shorne@gmail.com>
>> 
>> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
>
> Thanks
>
>> Side question: what is your merge strategy for this? I can take it
>> through the irqchip tree as it is standalone, but I'm open to other
>> suggestions.
>
> For me its easier if I just take it through the openrisc tree, as
> there are dependencies between this series and the irqchip driver.
> If you are ok with that I can make a note to Linus indicating so in
> the pull request.

No problem, that's OK with me.

> My plan is to send this series during the 4.15 merge window.

Make sure this is in -next (when it comes back to life...).

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny.

[OpenRISC] [PATCH v4 05/13] irqchip: add initial support for ompic

[Stafford Horne]

On Mon, Oct 30, 2017 at 06:11:40AM +0000, Marc Zyngier wrote:
> On Mon, Oct 30 2017 at  1:18:06 pm GMT, Stafford Horne <shorne@gmail.com> wrote:
> > On Mon, Oct 30, 2017 at 02:29:18AM +0000, Marc Zyngier wrote:
> >> On Mon, Oct 30 2017 at  8:11:15 am GMT, Stafford Horne <shorne@gmail.com> wrote:
> >> > From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
> >> >
> >> > IPI driver for the Open Multi-Processor Interrupt Controller (ompic) as
> >> > described in the Multi-core support section of the OpenRISC 1.2
> >> > architecture specification:
> >> >
> >> >   https://github.com/openrisc/doc/raw/master/openrisc-arch-1.2-rev0.pdf
> >> >
> >> > Each OpenRISC core contains a full interrupt controller which is used in
> >> > the SMP architecture for interrupt balancing.  This IPI device, the
> >> > ompic, is the only external device required for enabling SMP on
> >> > OpenRISC.
> >> >
> >> > Pending ops are stored in a memory bit mask which can allow multiple
> >> > pending operations to be set and serviced at a time. This is mostly
> >> > borrowed from the alpha IPI implementation.
> >> >
> >> > Cc: Marc Zyngier <marc.zyngier@arm.com>
> >> > Acked-by: Rob Herring <robh@kernel.org>
> >> > Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
> >> > [shorne at gmail.com: converted ops to bitmask, wrote commit message]
> >> > Signed-off-by: Stafford Horne <shorne@gmail.com>
> >> 
> >> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
> >
> > Thanks
> >
> >> Side question: what is your merge strategy for this? I can take it
> >> through the irqchip tree as it is standalone, but I'm open to other
> >> suggestions.
> >
> > For me its easier if I just take it through the openrisc tree, as
> > there are dependencies between this series and the irqchip driver.
> > If you are ok with that I can make a note to Linus indicating so in
> > the pull request.
> 
> No problem, that's OK with me.

Acknowledged

> > My plan is to send this series during the 4.15 merge window.
> 
> Make sure this is in -next (when it comes back to life...).

Its there now, and it looks like -next is almost back to life.

-Stafford

[OpenRISC] [PATCH v4 06/13] openrisc: initial SMP support

[Stafford Horne]

From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>

This patch introduces the SMP support for the OpenRISC architecture.
The SMP architecture requires cores which have multi-core features which
have been introduced a few years back including:

 - New SPRS SPR_COREID SPR_NUMCORES
 - Shadow SPRs
 - Atomic Instructions
 - Cache Coherency
 - A wired in IPI controller

This patch adds all of the SMP specific changes to core infrastructure,
it looks big but it needs to go all together as its hard to split this
one up.

Boot loader spinning of second cpu is not supported yet, it's assumed
that Linux is booted straight after cpu reset.

The bulk of these changes are trivial changes to refactor to use per cpu
data structures throughout.  The addition of the smp.c and changes in
time.c are the changes.  Some specific notes:

MM changes
----------
The reason why this is created as an array, and not with DEFINE_PER_CPU
is that doing it this way, we'll save a load in the tlb-miss handler
(the load from __per_cpu_offset).

TLB Flush
---------
The SMP implementation of flush_tlb_* works by sending out a
function-call IPI to all the non-local cpus by using the generic
on_each_cpu() function.

Currently, all flush_tlb_* functions will result in a flush_tlb_all(),
which has always been the behaviour in the UP case.

CPU INFO
--------
This creates a per cpu cpuinfo struct and fills it out accordingly for
each activated cpu.  show_cpuinfo is also updated to reflect new version
information in later versions of the spec.

SMP API
-------
This imitates the arm64 implementation by having a smp_cross_call
callback that can be set by set_smp_cross_call to initiate an IPI and a
handle_IPI function that is expected to be called from an IPI irqchip
driver.

Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
[shorne at gmail.com: added cpu stop, checkpatch fixes, wrote commit message]
Signed-off-by: Stafford Horne <shorne@gmail.com>
---

Changes since v2
 - none

Changes since v1
 - Added time.h for timer initialization
 - Don't crash on boot if IPI initialization fails
 - Removed volatile on secondary_release flag (checkpatch report)
 - Change ipi variable name from ipi_msg from

 arch/openrisc/Kconfig                   |  17 ++-
 arch/openrisc/include/asm/cpuinfo.h     |   7 +-
 arch/openrisc/include/asm/mmu_context.h |   2 +-
 arch/openrisc/include/asm/pgtable.h     |   2 +-
 arch/openrisc/include/asm/serial.h      |   2 +-
 arch/openrisc/include/asm/smp.h         |  26 ++++
 arch/openrisc/include/asm/spr_defs.h    |  14 ++
 arch/openrisc/include/asm/time.h        |  15 ++
 arch/openrisc/include/asm/tlbflush.h    |  25 +++-
 arch/openrisc/kernel/Makefile           |   1 +
 arch/openrisc/kernel/dma.c              |  14 +-
 arch/openrisc/kernel/head.S             |  97 ++++++++++++-
 arch/openrisc/kernel/setup.c            | 165 ++++++++++++++--------
 arch/openrisc/kernel/smp.c              | 235 ++++++++++++++++++++++++++++++++
 arch/openrisc/kernel/time.c             |  51 ++++---
 arch/openrisc/lib/delay.c               |   2 +-
 arch/openrisc/mm/fault.c                |   4 +-
 arch/openrisc/mm/init.c                 |   2 +-
 arch/openrisc/mm/tlb.c                  |  16 +--
 19 files changed, 584 insertions(+), 113 deletions(-)
 create mode 100644 arch/openrisc/include/asm/smp.h
 create mode 100644 arch/openrisc/include/asm/time.h
 create mode 100644 arch/openrisc/kernel/smp.c

diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 34eb4e90f56c..2b3898ede888 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -21,8 +21,10 @@ config OPENRISC
 	select HAVE_UID16
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select GENERIC_SMP_IDLE_THREAD
 	select MODULES_USE_ELF_RELA
 	select HAVE_DEBUG_STACKOVERFLOW
 	select OR1K_PIC
@@ -107,8 +109,19 @@ config OPENRISC_HAVE_INST_DIV
 endmenu
 
 config NR_CPUS
-	int
-	default "1"
+	int "Maximum number of CPUs (2-32)"
+	range 2 32
+	depends on SMP
+	default "2"
+
+config SMP
+	bool "Symmetric Multi-Processing support"
+	help
+	  This enables support for systems with more than one CPU. If you have
+	  a system with only one CPU, say N. If you have a system with more
+	  than one CPU, say Y.
+
+	  If you don't know what to do here, say N.
 
 source kernel/Kconfig.hz
 source kernel/Kconfig.preempt
diff --git a/arch/openrisc/include/asm/cpuinfo.h b/arch/openrisc/include/asm/cpuinfo.h
index ec10679d6429..4ea0a33eba6c 100644
--- a/arch/openrisc/include/asm/cpuinfo.h
+++ b/arch/openrisc/include/asm/cpuinfo.h
@@ -19,7 +19,7 @@
 #ifndef __ASM_OPENRISC_CPUINFO_H
 #define __ASM_OPENRISC_CPUINFO_H
 
-struct cpuinfo {
+struct cpuinfo_or1k {
 	u32 clock_frequency;
 
 	u32 icache_size;
@@ -29,8 +29,11 @@ struct cpuinfo {
 	u32 dcache_size;
 	u32 dcache_block_size;
 	u32 dcache_ways;
+
+	u16 coreid;
 };
 
-extern struct cpuinfo cpuinfo;
+extern struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
+extern void setup_cpuinfo(void);
 
 #endif /* __ASM_OPENRISC_CPUINFO_H */
diff --git a/arch/openrisc/include/asm/mmu_context.h b/arch/openrisc/include/asm/mmu_context.h
index e94b814d2e3c..c380d8caf84f 100644
--- a/arch/openrisc/include/asm/mmu_context.h
+++ b/arch/openrisc/include/asm/mmu_context.h
@@ -34,7 +34,7 @@ extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
  * registers like cr3 on the i386
  */
 
-extern volatile pgd_t *current_pgd;   /* defined in arch/openrisc/mm/fault.c */
+extern volatile pgd_t *current_pgd[]; /* defined in arch/openrisc/mm/fault.c */
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index 71a6f08de8f2..eff5ba2a5af2 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -94,7 +94,7 @@ extern void paging_init(void);
  * 64 MB of vmalloc area is comparable to what's available on other arches.
  */
 
-#define VMALLOC_START	(PAGE_OFFSET-0x04000000)
+#define VMALLOC_START	(PAGE_OFFSET-0x04000000UL)
 #define VMALLOC_END	(PAGE_OFFSET)
 #define VMALLOC_VMADDR(x) ((unsigned long)(x))
 
diff --git a/arch/openrisc/include/asm/serial.h b/arch/openrisc/include/asm/serial.h
index 270a45241639..cb5932f5447a 100644
--- a/arch/openrisc/include/asm/serial.h
+++ b/arch/openrisc/include/asm/serial.h
@@ -29,7 +29,7 @@
  * it needs to be correct to get the early console working.
  */
 
-#define BASE_BAUD (cpuinfo.clock_frequency/16)
+#define BASE_BAUD (cpuinfo_or1k[smp_processor_id()].clock_frequency/16)
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/openrisc/include/asm/smp.h b/arch/openrisc/include/asm/smp.h
new file mode 100644
index 000000000000..e21d2f12b5b6
--- /dev/null
+++ b/arch/openrisc/include/asm/smp.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ASM_OPENRISC_SMP_H
+#define __ASM_OPENRISC_SMP_H
+
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+#define raw_smp_processor_id()	(current_thread_info()->cpu)
+#define hard_smp_processor_id()	mfspr(SPR_COREID)
+
+extern void smp_init_cpus(void);
+
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+
+extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
+extern void handle_IPI(unsigned int ipi_msg);
+
+#endif /* __ASM_OPENRISC_SMP_H */
diff --git a/arch/openrisc/include/asm/spr_defs.h b/arch/openrisc/include/asm/spr_defs.h
index 367dac70326a..154b5a1ee579 100644
--- a/arch/openrisc/include/asm/spr_defs.h
+++ b/arch/openrisc/include/asm/spr_defs.h
@@ -51,6 +51,11 @@
 #define SPR_ICCFGR	(SPRGROUP_SYS + 6)
 #define SPR_DCFGR	(SPRGROUP_SYS + 7)
 #define SPR_PCCFGR	(SPRGROUP_SYS + 8)
+#define SPR_VR2		(SPRGROUP_SYS + 9)
+#define SPR_AVR		(SPRGROUP_SYS + 10)
+#define SPR_EVBAR	(SPRGROUP_SYS + 11)
+#define SPR_AECR	(SPRGROUP_SYS + 12)
+#define SPR_AESR	(SPRGROUP_SYS + 13)
 #define SPR_NPC         (SPRGROUP_SYS + 16)  /* CZ 21/06/01 */
 #define SPR_SR		(SPRGROUP_SYS + 17)  /* CZ 21/06/01 */
 #define SPR_PPC         (SPRGROUP_SYS + 18)  /* CZ 21/06/01 */
@@ -61,6 +66,8 @@
 #define SPR_EEAR_LAST	(SPRGROUP_SYS + 63)
 #define SPR_ESR_BASE	(SPRGROUP_SYS + 64)
 #define SPR_ESR_LAST	(SPRGROUP_SYS + 79)
+#define SPR_COREID	(SPRGROUP_SYS + 128)
+#define SPR_NUMCORES	(SPRGROUP_SYS + 129)
 #define SPR_GPR_BASE	(SPRGROUP_SYS + 1024)
 
 /* Data MMU group */
@@ -135,12 +142,19 @@
 #define SPR_VR_CFG	0x00ff0000  /* Processor configuration */
 #define SPR_VR_RES	0x0000ffc0  /* Reserved */
 #define SPR_VR_REV	0x0000003f  /* Processor revision */
+#define SPR_VR_UVRP	0x00000040  /* Updated Version Registers Present */
 
 #define SPR_VR_VER_OFF	24
 #define SPR_VR_CFG_OFF	16
 #define SPR_VR_REV_OFF	0
 
 /*
+ * Bit definitions for the Version Register 2
+ */
+#define SPR_VR2_CPUID	0xff000000  /* Processor ID */
+#define SPR_VR2_VER	0x00ffffff  /* Processor version */
+
+/*
  * Bit definitions for the Unit Present Register
  *
  */
diff --git a/arch/openrisc/include/asm/time.h b/arch/openrisc/include/asm/time.h
new file mode 100644
index 000000000000..fe83a34a7d68
--- /dev/null
+++ b/arch/openrisc/include/asm/time.h
@@ -0,0 +1,15 @@
+/*
+ * OpenRISC timer API
+ *
+ * Copyright (C) 2017 by Stafford Horne (shorne at gmail.com)
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_OR1K_TIME_H
+#define __ASM_OR1K_TIME_H
+
+extern void openrisc_clockevent_init(void);
+
+#endif /* __ASM_OR1K_TIME_H */
diff --git a/arch/openrisc/include/asm/tlbflush.h b/arch/openrisc/include/asm/tlbflush.h
index 6a2accd6cb67..94227f0eaf6d 100644
--- a/arch/openrisc/include/asm/tlbflush.h
+++ b/arch/openrisc/include/asm/tlbflush.h
@@ -33,13 +33,26 @@
  *  - flush_tlb_page(vma, vmaddr) flushes one page
  *  - flush_tlb_range(mm, start, end) flushes a range of pages
  */
+extern void local_flush_tlb_all(void);
+extern void local_flush_tlb_mm(struct mm_struct *mm);
+extern void local_flush_tlb_page(struct vm_area_struct *vma,
+				 unsigned long addr);
+extern void local_flush_tlb_range(struct vm_area_struct *vma,
+				  unsigned long start,
+				  unsigned long end);
 
-void flush_tlb_all(void);
-void flush_tlb_mm(struct mm_struct *mm);
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
-void flush_tlb_range(struct vm_area_struct *vma,
-		     unsigned long start,
-		     unsigned long end);
+#ifndef CONFIG_SMP
+#define flush_tlb_all	local_flush_tlb_all
+#define flush_tlb_mm	local_flush_tlb_mm
+#define flush_tlb_page	local_flush_tlb_page
+#define flush_tlb_range	local_flush_tlb_range
+#else
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end);
+#endif
 
 static inline void flush_tlb(void)
 {
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index ec6d9d37cefd..7d94643c878d 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -8,6 +8,7 @@ obj-y	:= setup.o or32_ksyms.o process.o dma.o \
 	   traps.o time.o irq.o entry.o ptrace.o signal.o \
 	   sys_call_table.o
 
+obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_OF)		+= prom.o
 
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index b10369b7e31b..a945f00011b4 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -32,6 +32,7 @@ page_set_nocache(pte_t *pte, unsigned long addr,
 		 unsigned long next, struct mm_walk *walk)
 {
 	unsigned long cl;
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
 
 	pte_val(*pte) |= _PAGE_CI;
 
@@ -42,7 +43,7 @@ page_set_nocache(pte_t *pte, unsigned long addr,
 	flush_tlb_page(NULL, addr);
 
 	/* Flush page out of dcache */
-	for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo.dcache_block_size)
+	for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
 		mtspr(SPR_DCBFR, cl);
 
 	return 0;
@@ -140,6 +141,7 @@ or1k_map_page(struct device *dev, struct page *page,
 {
 	unsigned long cl;
 	dma_addr_t addr = page_to_phys(page) + offset;
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
 
 	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
 		return addr;
@@ -148,13 +150,13 @@ or1k_map_page(struct device *dev, struct page *page,
 	case DMA_TO_DEVICE:
 		/* Flush the dcache for the requested range */
 		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo.dcache_block_size)
+		     cl += cpuinfo->dcache_block_size)
 			mtspr(SPR_DCBFR, cl);
 		break;
 	case DMA_FROM_DEVICE:
 		/* Invalidate the dcache for the requested range */
 		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo.dcache_block_size)
+		     cl += cpuinfo->dcache_block_size)
 			mtspr(SPR_DCBIR, cl);
 		break;
 	default:
@@ -213,9 +215,10 @@ or1k_sync_single_for_cpu(struct device *dev,
 {
 	unsigned long cl;
 	dma_addr_t addr = dma_handle;
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
 
 	/* Invalidate the dcache for the requested range */
-	for (cl = addr; cl < addr + size; cl += cpuinfo.dcache_block_size)
+	for (cl = addr; cl < addr + size; cl += cpuinfo->dcache_block_size)
 		mtspr(SPR_DCBIR, cl);
 }
 
@@ -226,9 +229,10 @@ or1k_sync_single_for_device(struct device *dev,
 {
 	unsigned long cl;
 	dma_addr_t addr = dma_handle;
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
 
 	/* Flush the dcache for the requested range */
-	for (cl = addr; cl < addr + size; cl += cpuinfo.dcache_block_size)
+	for (cl = addr; cl < addr + size; cl += cpuinfo->dcache_block_size)
 		mtspr(SPR_DCBFR, cl);
 }
 
diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index 1e49895408f4..a9972dc103f8 100644
--- a/arch/openrisc/kernel/head.S
+++ b/arch/openrisc/kernel/head.S
@@ -158,12 +158,38 @@
 
 /* =========================================================[ macros ]=== */
 
-
+#ifdef CONFIG_SMP
 #define GET_CURRENT_PGD(reg,t1)					\
 	LOAD_SYMBOL_2_GPR(reg,current_pgd)			;\
+	l.mfspr	t1,r0,SPR_COREID				;\
+	l.slli	t1,t1,2						;\
+	l.add	reg,reg,t1					;\
 	tophys  (t1,reg)					;\
 	l.lwz   reg,0(t1)
+#else
+#define GET_CURRENT_PGD(reg,t1)					\
+	LOAD_SYMBOL_2_GPR(reg,current_pgd)			;\
+	tophys  (t1,reg)					;\
+	l.lwz   reg,0(t1)
+#endif
 
+/* Load r10 from current_thread_info_set - clobbers r1 and r30 */
+#ifdef CONFIG_SMP
+#define GET_CURRENT_THREAD_INFO					\
+	LOAD_SYMBOL_2_GPR(r1,current_thread_info_set)		;\
+	tophys  (r30,r1)					;\
+	l.mfspr	r10,r0,SPR_COREID				;\
+	l.slli	r10,r10,2					;\
+	l.add	r30,r30,r10					;\
+	/* r10: current_thread_info  */				;\
+	l.lwz   r10,0(r30)
+#else
+#define GET_CURRENT_THREAD_INFO					\
+	LOAD_SYMBOL_2_GPR(r1,current_thread_info_set)		;\
+	tophys  (r30,r1)					;\
+	/* r10: current_thread_info  */				;\
+	l.lwz   r10,0(r30)
+#endif
 
 /*
  * DSCR: this is a common hook for handling exceptions. it will save
@@ -206,10 +232,7 @@
 	l.bnf   2f                            /* kernel_mode */	;\
 	 EXCEPTION_T_STORE_SP                 /* delay slot */	;\
 1: /* user_mode:   */						;\
-	LOAD_SYMBOL_2_GPR(r1,current_thread_info_set)		;\
-	tophys  (r30,r1)					;\
-	/* r10: current_thread_info  */				;\
-	l.lwz   r10,0(r30)					;\
+	GET_CURRENT_THREAD_INFO	 				;\
 	tophys  (r30,r10)					;\
 	l.lwz   r1,(TI_KSP)(r30)				;\
 	/* fall through */					;\
@@ -530,6 +553,12 @@ _start:
 	CLEAR_GPR(r30)
 	CLEAR_GPR(r31)
 
+#ifdef CONFIG_SMP
+	l.mfspr	r26,r0,SPR_COREID
+	l.sfeq	r26,r0
+	l.bnf	secondary_wait
+	 l.nop
+#endif
 	/*
 	 * set up initial ksp and current
 	 */
@@ -681,6 +710,64 @@ _flush_tlb:
 	l.jr	r9
 	 l.nop
 
+#ifdef CONFIG_SMP
+secondary_wait:
+	l.mfspr	r25,r0,SPR_COREID
+	l.movhi	r3,hi(secondary_release)
+	l.ori	r3,r3,lo(secondary_release)
+	tophys(r4, r3)
+	l.lwz	r3,0(r4)
+	l.sfeq	r25,r3
+	l.bnf	secondary_wait
+	 l.nop
+	/* fall through to secondary_init */
+
+secondary_init:
+	/*
+	 * set up initial ksp and current
+	 */
+	LOAD_SYMBOL_2_GPR(r10, secondary_thread_info)
+	tophys	(r30,r10)
+	l.lwz	r10,0(r30)
+	l.addi	r1,r10,THREAD_SIZE
+	tophys	(r30,r10)
+	l.sw	TI_KSP(r30),r1
+
+	l.jal	_ic_enable
+	 l.nop
+
+	l.jal	_dc_enable
+	 l.nop
+
+	l.jal	_flush_tlb
+	 l.nop
+
+	/*
+	 * enable dmmu & immu
+	 */
+	l.mfspr	r30,r0,SPR_SR
+	l.movhi	r28,hi(SPR_SR_DME | SPR_SR_IME)
+	l.ori	r28,r28,lo(SPR_SR_DME | SPR_SR_IME)
+	l.or	r30,r30,r28
+	/*
+	 * This is a bit tricky, we need to switch over from physical addresses
+	 * to virtual addresses on the fly.
+	 * To do that, we first set up ESR with the IME and DME bits set.
+	 * Then EPCR is set to secondary_start and then a l.rfe is issued to
+	 * "jump" to that.
+	 */
+	l.mtspr	r0,r30,SPR_ESR_BASE
+	LOAD_SYMBOL_2_GPR(r30, secondary_start)
+	l.mtspr	r0,r30,SPR_EPCR_BASE
+	l.rfe
+
+secondary_start:
+	LOAD_SYMBOL_2_GPR(r30, secondary_start_kernel)
+	l.jr    r30
+	 l.nop
+
+#endif
+
 /* ========================================[ cache ]=== */
 
 	/* alignment here so we don't change memory offsets with
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index dbf5ee95a0d5..9d28ab14d139 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -93,7 +93,7 @@ static void __init setup_memory(void)
 	memblock_dump_all();
 }
 
-struct cpuinfo cpuinfo;
+struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
 
 static void print_cpuinfo(void)
 {
@@ -101,12 +101,13 @@ static void print_cpuinfo(void)
 	unsigned long vr = mfspr(SPR_VR);
 	unsigned int version;
 	unsigned int revision;
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
 
 	version = (vr & SPR_VR_VER) >> 24;
 	revision = (vr & SPR_VR_REV);
 
 	printk(KERN_INFO "CPU: OpenRISC-%x (revision %d) @%d MHz\n",
-	       version, revision, cpuinfo.clock_frequency / 1000000);
+	       version, revision, cpuinfo->clock_frequency / 1000000);
 
 	if (!(upr & SPR_UPR_UP)) {
 		printk(KERN_INFO
@@ -117,15 +118,15 @@ static void print_cpuinfo(void)
 	if (upr & SPR_UPR_DCP)
 		printk(KERN_INFO
 		       "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo.dcache_size, cpuinfo.dcache_block_size,
-		       cpuinfo.dcache_ways);
+		       cpuinfo->dcache_size, cpuinfo->dcache_block_size,
+		       cpuinfo->dcache_ways);
 	else
 		printk(KERN_INFO "-- dcache disabled\n");
 	if (upr & SPR_UPR_ICP)
 		printk(KERN_INFO
 		       "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo.icache_size, cpuinfo.icache_block_size,
-		       cpuinfo.icache_ways);
+		       cpuinfo->icache_size, cpuinfo->icache_block_size,
+		       cpuinfo->icache_ways);
 	else
 		printk(KERN_INFO "-- icache disabled\n");
 
@@ -153,38 +154,58 @@ static void print_cpuinfo(void)
 		printk(KERN_INFO "-- custom unit(s)\n");
 }
 
+static struct device_node *setup_find_cpu_node(int cpu)
+{
+	u32 hwid;
+	struct device_node *cpun;
+	struct device_node *cpus = of_find_node_by_path("/cpus");
+
+	for_each_available_child_of_node(cpus, cpun) {
+		if (of_property_read_u32(cpun, "reg", &hwid))
+			continue;
+		if (hwid == cpu)
+			return cpun;
+	}
+
+	return NULL;
+}
+
 void __init setup_cpuinfo(void)
 {
 	struct device_node *cpu;
 	unsigned long iccfgr, dccfgr;
 	unsigned long cache_set_size;
+	int cpu_id = smp_processor_id();
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id];
 
-	cpu = of_find_compatible_node(NULL, NULL, "opencores,or1200-rtlsvn481");
+	cpu = setup_find_cpu_node(cpu_id);
 	if (!cpu)
-		panic("No compatible CPU found in device tree...\n");
+		panic("Couldn't find CPU%d in device tree...\n", cpu_id);
 
 	iccfgr = mfspr(SPR_ICCFGR);
-	cpuinfo.icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
+	cpuinfo->icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
 	cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
-	cpuinfo.icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
-	cpuinfo.icache_size =
-	    cache_set_size * cpuinfo.icache_ways * cpuinfo.icache_block_size;
+	cpuinfo->icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
+	cpuinfo->icache_size =
+	    cache_set_size * cpuinfo->icache_ways * cpuinfo->icache_block_size;
 
 	dccfgr = mfspr(SPR_DCCFGR);
-	cpuinfo.dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
+	cpuinfo->dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
 	cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
-	cpuinfo.dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
-	cpuinfo.dcache_size =
-	    cache_set_size * cpuinfo.dcache_ways * cpuinfo.dcache_block_size;
+	cpuinfo->dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
+	cpuinfo->dcache_size =
+	    cache_set_size * cpuinfo->dcache_ways * cpuinfo->dcache_block_size;
 
 	if (of_property_read_u32(cpu, "clock-frequency",
-				 &cpuinfo.clock_frequency)) {
+				 &cpuinfo->clock_frequency)) {
 		printk(KERN_WARNING
 		       "Device tree missing CPU 'clock-frequency' parameter."
 		       "Assuming frequency 25MHZ"
 		       "This is probably not what you want.");
 	}
 
+	cpuinfo->coreid = mfspr(SPR_COREID);
+
 	of_node_put(cpu);
 
 	print_cpuinfo();
@@ -251,8 +272,8 @@ void __init detect_unit_config(unsigned long upr, unsigned long mask,
 void calibrate_delay(void)
 {
 	const int *val;
-	struct device_node *cpu = NULL;
-	cpu = of_find_compatible_node(NULL, NULL, "opencores,or1200-rtlsvn481");
+	struct device_node *cpu = setup_find_cpu_node(smp_processor_id());
+
 	val = of_get_property(cpu, "clock-frequency", NULL);
 	if (!val)
 		panic("no cpu 'clock-frequency' parameter in device tree");
@@ -268,6 +289,10 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_cpuinfo();
 
+#ifdef CONFIG_SMP
+	smp_init_cpus();
+#endif
+
 	/* process 1's initial memory region is the kernel code/data */
 	init_mm.start_code = (unsigned long)_stext;
 	init_mm.end_code = (unsigned long)_etext;
@@ -302,54 +327,78 @@ void __init setup_arch(char **cmdline_p)
 
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
-	unsigned long vr;
-	int version, revision;
+	unsigned int vr, cpucfgr;
+	unsigned int avr;
+	unsigned int version;
+	struct cpuinfo_or1k *cpuinfo = v;
 
 	vr = mfspr(SPR_VR);
-	version = (vr & SPR_VR_VER) >> 24;
-	revision = vr & SPR_VR_REV;
-
-	seq_printf(m,
-		  "cpu\t\t: OpenRISC-%x\n"
-		  "revision\t: %d\n"
-		  "frequency\t: %ld\n"
-		  "dcache size\t: %d bytes\n"
-		  "dcache block size\t: %d bytes\n"
-		  "dcache ways\t: %d\n"
-		  "icache size\t: %d bytes\n"
-		  "icache block size\t: %d bytes\n"
-		  "icache ways\t: %d\n"
-		  "immu\t\t: %d entries, %lu ways\n"
-		  "dmmu\t\t: %d entries, %lu ways\n"
-		  "bogomips\t: %lu.%02lu\n",
-		  version,
-		  revision,
-		  loops_per_jiffy * HZ,
-		  cpuinfo.dcache_size,
-		  cpuinfo.dcache_block_size,
-		  cpuinfo.dcache_ways,
-		  cpuinfo.icache_size,
-		  cpuinfo.icache_block_size,
-		  cpuinfo.icache_ways,
-		  1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
-		  1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW),
-		  1 << ((mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTS) >> 2),
-		  1 + (mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTW),
-		  (loops_per_jiffy * HZ) / 500000,
-		  ((loops_per_jiffy * HZ) / 5000) % 100);
+	cpucfgr = mfspr(SPR_CPUCFGR);
+
+#ifdef CONFIG_SMP
+	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
+#endif
+	if (vr & SPR_VR_UVRP) {
+		vr = mfspr(SPR_VR2);
+		version = vr & SPR_VR2_VER;
+		avr = mfspr(SPR_AVR);
+		seq_printf(m, "cpu architecture\t: "
+			   "OpenRISC 1000 (%d.%d-rev%d)\n",
+			   (avr >> 24) & 0xff,
+			   (avr >> 16) & 0xff,
+			   (avr >> 8) & 0xff);
+		seq_printf(m, "cpu implementation id\t: 0x%x\n",
+			   (vr & SPR_VR2_CPUID) >> 24);
+		seq_printf(m, "cpu version\t\t: 0x%x\n", version);
+	} else {
+		version = (vr & SPR_VR_VER) >> 24;
+		seq_printf(m, "cpu\t\t\t: OpenRISC-%x\n", version);
+		seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV);
+	}
+	seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ);
+	seq_printf(m, "dcache size\t\t: %d bytes\n", cpuinfo->dcache_size);
+	seq_printf(m, "dcache block size\t: %d bytes\n",
+		   cpuinfo->dcache_block_size);
+	seq_printf(m, "dcache ways\t\t: %d\n", cpuinfo->dcache_ways);
+	seq_printf(m, "icache size\t\t: %d bytes\n", cpuinfo->icache_size);
+	seq_printf(m, "icache block size\t: %d bytes\n",
+		   cpuinfo->icache_block_size);
+	seq_printf(m, "icache ways\t\t: %d\n", cpuinfo->icache_ways);
+	seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n",
+		   1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
+		   1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW));
+	seq_printf(m, "dmmu\t\t\t: %d entries, %lu ways\n",
+		   1 << ((mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTS) >> 2),
+		   1 + (mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTW));
+	seq_printf(m, "bogomips\t\t: %lu.%02lu\n",
+		   (loops_per_jiffy * HZ) / 500000,
+		   ((loops_per_jiffy * HZ) / 5000) % 100);
+
+	seq_puts(m, "features\t\t: ");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OB32S ? "orbis32" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OB64S ? "orbis64" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OF32S ? "orfpx32" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OF64S ? "orfpx64" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OV64S ? "orvdx64" : "");
+	seq_puts(m, "\n");
+
+	seq_puts(m, "\n");
+
 	return 0;
 }
 
-static void *c_start(struct seq_file *m, loff_t * pos)
+static void *c_start(struct seq_file *m, loff_t *pos)
 {
-	/* We only have one CPU... */
-	return *pos < 1 ? (void *)1 : NULL;
+	*pos = cpumask_next(*pos - 1, cpu_online_mask);
+	if ((*pos) < nr_cpu_ids)
+		return &cpuinfo_or1k[*pos];
+	return NULL;
 }
 
-static void *c_next(struct seq_file *m, void *v, loff_t * pos)
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	++*pos;
-	return NULL;
+	(*pos)++;
+	return c_start(m, pos);
 }
 
 static void c_stop(struct seq_file *m, void *v)
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
new file mode 100644
index 000000000000..fd724123229a
--- /dev/null
+++ b/arch/openrisc/kernel/smp.c
@@ -0,0 +1,235 @@
+/*
+ * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
+ *
+ * Based on arm64 and arc implementations
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <linux/smp.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/irq.h>
+#include <asm/cpuinfo.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/time.h>
+
+static void (*smp_cross_call)(const struct cpumask *, unsigned int);
+
+unsigned long secondary_release = -1;
+struct thread_info *secondary_thread_info;
+
+enum ipi_msg_type {
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
+};
+
+static DEFINE_SPINLOCK(boot_lock);
+
+static void boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	/*
+	 * set synchronisation state between this boot processor
+	 * and the secondary one
+	 */
+	spin_lock(&boot_lock);
+
+	secondary_release = cpu;
+
+	/*
+	 * now the secondary core is starting up let it run its
+	 * calibrations, then wait for it to finish
+	 */
+	spin_unlock(&boot_lock);
+}
+
+void __init smp_prepare_boot_cpu(void)
+{
+}
+
+void __init smp_init_cpus(void)
+{
+	int i;
+
+	for (i = 0; i < NR_CPUS; i++)
+		set_cpu_possible(i, true);
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	int i;
+
+	/*
+	 * Initialise the present map, which describes the set of CPUs
+	 * actually populated@the present time.
+	 */
+	for (i = 0; i < max_cpus; i++)
+		set_cpu_present(i, true);
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+static DECLARE_COMPLETION(cpu_running);
+
+int __cpu_up(unsigned int cpu, struct task_struct *idle)
+{
+	if (smp_cross_call == NULL) {
+		pr_warn("CPU%u: failed to start, IPI controller missing",
+			cpu);
+		return -EIO;
+	}
+
+	secondary_thread_info = task_thread_info(idle);
+	current_pgd[cpu] = init_mm.pgd;
+
+	boot_secondary(cpu, idle);
+	if (!wait_for_completion_timeout(&cpu_running,
+					msecs_to_jiffies(1000))) {
+		pr_crit("CPU%u: failed to start\n", cpu);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+asmlinkage __init void secondary_start_kernel(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+	/*
+	 * All kernel threads share the same mm context; grab a
+	 * reference and switch to it.
+	 */
+	atomic_inc(&mm->mm_count);
+	current->active_mm = mm;
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
+
+	pr_info("CPU%u: Booted secondary processor\n", cpu);
+
+	setup_cpuinfo();
+	openrisc_clockevent_init();
+
+	notify_cpu_starting(cpu);
+
+	/*
+	 * OK, now it's safe to let the boot CPU continue
+	 */
+	set_cpu_online(cpu, true);
+	complete(&cpu_running);
+
+	local_irq_enable();
+
+	/*
+	 * OK, it's off to the idle thread for us
+	 */
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
+
+void handle_IPI(unsigned int ipi_msg)
+{
+	unsigned int cpu = smp_processor_id();
+
+	switch (ipi_msg) {
+	case IPI_RESCHEDULE:
+		scheduler_ipi();
+		break;
+
+	case IPI_CALL_FUNC:
+		generic_smp_call_function_interrupt();
+		break;
+
+	case IPI_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
+
+	default:
+		WARN(1, "CPU%u: Unknown IPI message 0x%x\n", cpu, ipi_msg);
+		break;
+	}
+}
+
+void smp_send_reschedule(int cpu)
+{
+	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
+}
+
+static void stop_this_cpu(void *dummy)
+{
+	/* Remove this CPU */
+	set_cpu_online(smp_processor_id(), false);
+
+	local_irq_disable();
+	/* CPU Doze */
+	if (mfspr(SPR_UPR) & SPR_UPR_PMP)
+		mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME);
+	/* If that didn't work, infinite loop */
+	while (1)
+		;
+}
+
+void smp_send_stop(void)
+{
+	smp_call_function(stop_this_cpu, NULL, 0);
+}
+
+/* not supported, yet */
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return -EINVAL;
+}
+
+void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
+{
+	smp_cross_call = fn;
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+}
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+	smp_cross_call(mask, IPI_CALL_FUNC);
+}
+
+/* TLB flush operations - Performed on each CPU*/
+static inline void ipi_flush_tlb_all(void *ignored)
+{
+	local_flush_tlb_all();
+}
+
+void flush_tlb_all(void)
+{
+	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+}
+
+/*
+ * FIXME: implement proper functionality instead of flush_tlb_all.
+ * *But*, as things currently stands, the local_tlb_flush_* functions will
+ * all boil down to local_tlb_flush_all anyway.
+ */
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma,
+		     unsigned long start, unsigned long end)
+{
+	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+}
diff --git a/arch/openrisc/kernel/time.c b/arch/openrisc/kernel/time.c
index 687c11d048d7..ab04eaedbf8d 100644
--- a/arch/openrisc/kernel/time.c
+++ b/arch/openrisc/kernel/time.c
@@ -53,13 +53,32 @@ static int openrisc_timer_set_next_event(unsigned long delta,
  * timers) we cannot enable the PERIODIC feature.  The tick timer can run using
  * one-shot events, so no problem.
  */
+DEFINE_PER_CPU(struct clock_event_device, clockevent_openrisc_timer);
 
-static struct clock_event_device clockevent_openrisc_timer = {
-	.name = "openrisc_timer_clockevent",
-	.features = CLOCK_EVT_FEAT_ONESHOT,
-	.rating = 300,
-	.set_next_event = openrisc_timer_set_next_event,
-};
+void openrisc_clockevent_init(void)
+{
+	unsigned int cpu = smp_processor_id();
+	struct clock_event_device *evt =
+		&per_cpu(clockevent_openrisc_timer, cpu);
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu];
+
+	mtspr(SPR_TTMR, SPR_TTMR_CR);
+
+#ifdef CONFIG_SMP
+	evt->broadcast = tick_broadcast;
+#endif
+	evt->name = "openrisc_timer_clockevent",
+	evt->features = CLOCK_EVT_FEAT_ONESHOT,
+	evt->rating = 300,
+	evt->set_next_event = openrisc_timer_set_next_event,
+
+	evt->cpumask = cpumask_of(cpu);
+
+	/* We only have 28 bits */
+	clockevents_config_and_register(evt, cpuinfo->clock_frequency,
+					100, 0x0fffffff);
+
+}
 
 static inline void timer_ack(void)
 {
@@ -83,7 +102,9 @@ static inline void timer_ack(void)
 irqreturn_t __irq_entry timer_interrupt(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct clock_event_device *evt = &clockevent_openrisc_timer;
+	unsigned int cpu = smp_processor_id();
+	struct clock_event_device *evt =
+		&per_cpu(clockevent_openrisc_timer, cpu);
 
 	timer_ack();
 
@@ -99,24 +120,12 @@ irqreturn_t __irq_entry timer_interrupt(struct pt_regs *regs)
 	return IRQ_HANDLED;
 }
 
-static __init void openrisc_clockevent_init(void)
-{
-	clockevent_openrisc_timer.cpumask = cpumask_of(0);
-
-	/* We only have 28 bits */
-	clockevents_config_and_register(&clockevent_openrisc_timer,
-					cpuinfo.clock_frequency,
-					100, 0x0fffffff);
-
-}
-
 /**
  * Clocksource: Based on OpenRISC timer/counter
  *
  * This sets up the OpenRISC Tick Timer as a clock source.  The tick timer
  * is 32 bits wide and runs at the CPU clock frequency.
  */
-
 static u64 openrisc_timer_read(struct clocksource *cs)
 {
 	return (u64) mfspr(SPR_TTCR);
@@ -132,7 +141,9 @@ static struct clocksource openrisc_timer = {
 
 static int __init openrisc_timer_init(void)
 {
-	if (clocksource_register_hz(&openrisc_timer, cpuinfo.clock_frequency))
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+
+	if (clocksource_register_hz(&openrisc_timer, cpuinfo->clock_frequency))
 		panic("failed to register clocksource");
 
 	/* Enable the incrementer: 'continuous' mode with interrupt disabled */
diff --git a/arch/openrisc/lib/delay.c b/arch/openrisc/lib/delay.c
index 8b13fdf43ec6..a92bd621aa1f 100644
--- a/arch/openrisc/lib/delay.c
+++ b/arch/openrisc/lib/delay.c
@@ -25,7 +25,7 @@
 
 int read_current_timer(unsigned long *timer_value)
 {
-	*timer_value = mfspr(SPR_TTCR);
+	*timer_value = get_cycles();
 	return 0;
 }
 
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index e310ab499385..d0021dfae20a 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -33,7 +33,7 @@ unsigned long pte_errors;	/* updated by do_page_fault() */
 /* __PHX__ :: - check the vmalloc_fault in do_page_fault()
  *            - also look into include/asm-or32/mmu_context.h
  */
-volatile pgd_t *current_pgd;
+volatile pgd_t *current_pgd[NR_CPUS];
 
 extern void die(char *, struct pt_regs *, long);
 
@@ -319,7 +319,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 
 		phx_mmu("vmalloc_fault");
 */
-		pgd = (pgd_t *)current_pgd + offset;
+		pgd = (pgd_t *)current_pgd[smp_processor_id()] + offset;
 		pgd_k = init_mm.pgd + offset;
 
 		/* Since we're two-level, we don't need to do both
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index f67d82b9d22f..6972d5d6f23f 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -147,7 +147,7 @@ void __init paging_init(void)
 	 * (even if it is most probably not used until the next
 	 *  switch_mm)
 	 */
-	current_pgd = init_mm.pgd;
+	current_pgd[smp_processor_id()] = init_mm.pgd;
 
 	end = (unsigned long)__va(max_low_pfn * PAGE_SIZE);
 
diff --git a/arch/openrisc/mm/tlb.c b/arch/openrisc/mm/tlb.c
index 683bd4d31c7c..6c253a2e86bc 100644
--- a/arch/openrisc/mm/tlb.c
+++ b/arch/openrisc/mm/tlb.c
@@ -49,7 +49,7 @@
  *
  */
 
-void flush_tlb_all(void)
+void local_flush_tlb_all(void)
 {
 	int i;
 	unsigned long num_tlb_sets;
@@ -86,7 +86,7 @@ void flush_tlb_all(void)
 #define flush_itlb_page_no_eir(addr) \
 	mtspr_off(SPR_ITLBMR_BASE(0), ITLB_OFFSET(addr), 0);
 
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	if (have_dtlbeir)
 		flush_dtlb_page_eir(addr);
@@ -99,8 +99,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 		flush_itlb_page_no_eir(addr);
 }
 
-void flush_tlb_range(struct vm_area_struct *vma,
-		     unsigned long start, unsigned long end)
+void local_flush_tlb_range(struct vm_area_struct *vma,
+			   unsigned long start, unsigned long end)
 {
 	int addr;
 	bool dtlbeir;
@@ -129,13 +129,13 @@ void flush_tlb_range(struct vm_area_struct *vma,
  * This should be changed to loop over over mm and call flush_tlb_range.
  */
 
-void flush_tlb_mm(struct mm_struct *mm)
+void local_flush_tlb_mm(struct mm_struct *mm)
 {
 
 	/* Was seeing bugs with the mm struct passed to us. Scrapped most of
 	   this function. */
 	/* Several architctures do this */
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
 /* called in schedule() just before actually doing the switch_to */
@@ -149,14 +149,14 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 * might be invalid at points where we still need to derefer
 	 * the pgd.
 	 */
-	current_pgd = next->pgd;
+	current_pgd[smp_processor_id()] = next->pgd;
 
 	/* We don't have context support implemented, so flush all
 	 * entries belonging to previous map
 	 */
 
 	if (prev != next)
-		flush_tlb_mm(prev);
+		local_flush_tlb_mm(prev);
 
 }
 
-- 
2.13.6

[OpenRISC] [PATCH v4 07/13] openrisc: fix initial preempt state for secondary cpu tasks

[Stafford Horne]

During SMP testing we were getting the below warning after booting the
secondary cpu:

[    0.060000] BUG: scheduling while atomic: swapper/1/0/0x00000000

This change follows similar patterns from other architectures to start
the schduler with preempt disabled.

Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/include/asm/thread_info.h | 2 +-
 arch/openrisc/kernel/smp.c              | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h
index 6e619a79a401..c229aa6bb502 100644
--- a/arch/openrisc/include/asm/thread_info.h
+++ b/arch/openrisc/include/asm/thread_info.h
@@ -74,7 +74,7 @@ struct thread_info {
 	.task		= &tsk,				\
 	.flags		= 0,				\
 	.cpu		= 0,				\
-	.preempt_count	= 1,				\
+	.preempt_count	= INIT_PREEMPT_COUNT,		\
 	.addr_limit	= KERNEL_DS,			\
 	.ksp            = 0,                            \
 }
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index fd724123229a..154c94a0cfbc 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -128,6 +128,7 @@ asmlinkage __init void secondary_start_kernel(void)
 
 	local_irq_enable();
 
+	preempt_disable();
 	/*
 	 * OK, it's off to the idle thread for us
 	 */
-- 
2.13.6

[OpenRISC] [PATCH v4 08/13] openrisc: sleep instead of spin on secondary wait

[Stafford Horne]

Currently we do a spin on secondary cpus when waiting to boot.  This
theoretically causes issues with power consumption and does cause issues
with qemu cycle burning (it starves cpu 0 from actually being able to
boot.)

This change puts each secondary cpu to sleep if they have a power
management unit, then signals them to wake via IPI when its time to boot.
If the cpus have no power management unit they will loop as before.

Note: The wakeup IPI requires a special interrupt handler as on secondary
cpu's the interrupt infrastructure is not yet established.  This
interrupt handler is set and reset by updating SPR_EVBAR.

Signed-off-by: Stafford Horne <shorne@gmail.com>
---

Changes since v2
 - none

Changes since v1
 - Check if power management exists before sleeping

 arch/openrisc/kernel/head.S | 51 +++++++++++++++++++++++++++++++++++++++++++--
 arch/openrisc/kernel/smp.c  |  5 +++++
 2 files changed, 54 insertions(+), 2 deletions(-)

diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index a9972dc103f8..fb02b2a1d6f2 100644
--- a/arch/openrisc/kernel/head.S
+++ b/arch/openrisc/kernel/head.S
@@ -712,9 +712,45 @@ _flush_tlb:
 
 #ifdef CONFIG_SMP
 secondary_wait:
+	/* Doze the cpu until we are asked to run */
+	/* If we dont have power management skip doze */
+	l.mfspr r25,r0,SPR_UPR
+	l.andi  r25,r25,SPR_UPR_PMP
+	l.sfeq  r25,r0
+	l.bf	secondary_check_release
+	 l.nop
+
+	/* Setup special secondary exception handler */
+	LOAD_SYMBOL_2_GPR(r3, _secondary_evbar)
+	tophys(r25,r3)
+	l.mtspr	r0,r25,SPR_EVBAR
+
+	/* Enable Interrupts */
+	l.mfspr	r25,r0,SPR_SR
+	l.ori	r25,r25,SPR_SR_IEE
+	l.mtspr	r0,r25,SPR_SR
+
+	/* Unmask interrupts interrupts */
+	l.mfspr r25,r0,SPR_PICMR
+	l.ori   r25,r25,0xffff
+	l.mtspr	r0,r25,SPR_PICMR
+
+	/* Doze */
+	l.mfspr r25,r0,SPR_PMR
+	LOAD_SYMBOL_2_GPR(r3, SPR_PMR_DME)
+	l.or    r25,r25,r3
+	l.mtspr r0,r25,SPR_PMR
+
+	/* Wakeup - Restore exception handler */
+	l.mtspr	r0,r0,SPR_EVBAR
+
+secondary_check_release:
+	/*
+	 * Check if we actually got the release signal, if not go-back to
+	 * sleep.
+	 */
 	l.mfspr	r25,r0,SPR_COREID
-	l.movhi	r3,hi(secondary_release)
-	l.ori	r3,r3,lo(secondary_release)
+	LOAD_SYMBOL_2_GPR(r3, secondary_release)
 	tophys(r4, r3)
 	l.lwz	r3,0(r4)
 	l.sfeq	r25,r3
@@ -1663,6 +1699,17 @@ ENTRY(_early_uart_init)
 	l.jr	r9
 	l.nop
 
+	.align	0x1000
+	.global _secondary_evbar
+_secondary_evbar:
+
+	.space 0x800
+	/* Just disable interrupts and Return */
+	l.ori	r3,r0,SPR_SR_SM
+	l.mtspr	r0,r3,SPR_ESR_BASE
+	l.rfe
+
+
 	.section .rodata
 _string_unhandled_exception:
 	.string "\n\rRunarunaround: Unhandled exception 0x\0"
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index 154c94a0cfbc..685b4934fa39 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -26,6 +26,7 @@ unsigned long secondary_release = -1;
 struct thread_info *secondary_thread_info;
 
 enum ipi_msg_type {
+	IPI_WAKEUP,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
@@ -42,6 +43,7 @@ static void boot_secondary(unsigned int cpu, struct task_struct *idle)
 	spin_lock(&boot_lock);
 
 	secondary_release = cpu;
+	smp_cross_call(cpumask_of(cpu), IPI_WAKEUP);
 
 	/*
 	 * now the secondary core is starting up let it run its
@@ -140,6 +142,9 @@ void handle_IPI(unsigned int ipi_msg)
 	unsigned int cpu = smp_processor_id();
 
 	switch (ipi_msg) {
+	case IPI_WAKEUP:
+		break;
+
 	case IPI_RESCHEDULE:
 		scheduler_ipi();
 		break;
-- 
2.13.6

[OpenRISC] [PATCH v4 09/13] openrisc: add cacheflush support to fix icache aliasing

[Stafford Horne]

From: Jan Henrik Weinstock <jan.weinstock@ice.rwth-aachen.de>

On OpenRISC the icache does not snoop data stores.  This can cause
aliasing as reported by Jan. This patch fixes the issue to ensure icache
is properly synchronized when code is written to memory.  It supports both
SMP and UP flushing.

This supports dcache flush as well for architectures that do not support
write-through caches; most OpenRISC implementations do implement
write-through cache however. Dcache flushes are done only on a single
core as OpenRISC dcaches all support snooping of bus stores.

Signed-off-by: Jan Henrik Weinstock <jan.weinstock@ice.rwth-aachen.de>
[shorne at gmail.com: Squashed patches and wrote commit message]
Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/Kconfig                  | 11 ++++
 arch/openrisc/include/asm/Kbuild       |  1 -
 arch/openrisc/include/asm/cacheflush.h | 96 ++++++++++++++++++++++++++++++++++
 arch/openrisc/include/asm/pgtable.h    | 16 +++---
 arch/openrisc/kernel/smp.c             | 15 ++++++
 arch/openrisc/mm/Makefile              |  2 +-
 arch/openrisc/mm/cache.c               | 61 +++++++++++++++++++++
 7 files changed, 194 insertions(+), 8 deletions(-)
 create mode 100644 arch/openrisc/include/asm/cacheflush.h
 create mode 100644 arch/openrisc/mm/cache.c

diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 2b3898ede888..bfff04ae7f7d 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -77,6 +77,17 @@ config OR1K_1200
 
 endchoice
 
+config DCACHE_WRITETHROUGH
+	bool "Have write through data caches"
+	default n
+	help
+	  Select this if your implementation features write through data caches.
+	  Selecting 'N' here will allow the kernel to force flushing of data
+	  caches at relevant times. Most OpenRISC implementations support write-
+	  through data caches.
+
+	  If unsure say N here
+
 config OPENRISC_BUILTIN_DTB
         string "Builtin DTB"
         default ""
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 5f066780d870..6eb16719549e 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -1,7 +1,6 @@
 generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
-generic-y += cacheflush.h
 generic-y += checksum.h
 generic-y += clkdev.h
 generic-y += current.h
diff --git a/arch/openrisc/include/asm/cacheflush.h b/arch/openrisc/include/asm/cacheflush.h
new file mode 100644
index 000000000000..70f46fd7a074
--- /dev/null
+++ b/arch/openrisc/include/asm/cacheflush.h
@@ -0,0 +1,96 @@
+/*
+ * OpenRISC Linux
+ *
+ * Linux architectural port borrowing liberally from similar works of
+ * others.  All original copyrights apply as per the original source
+ * declaration.
+ *
+ * OpenRISC implementation:
+ * Copyright (C) Jan Henrik Weinstock <jan.weinstock@rwth-aachen.de>
+ * et al.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __ASM_CACHEFLUSH_H
+#define __ASM_CACHEFLUSH_H
+
+#include <linux/mm.h>
+
+/*
+ * Helper function for flushing or invalidating entire pages from data
+ * and instruction caches. SMP needs a little extra work, since we need
+ * to flush the pages on all cpus.
+ */
+extern void local_dcache_page_flush(struct page *page);
+extern void local_icache_page_inv(struct page *page);
+
+/*
+ * Data cache flushing always happen on the local cpu. Instruction cache
+ * invalidations need to be broadcasted to all other cpu in the system in
+ * case of SMP configurations.
+ */
+#ifndef CONFIG_SMP
+#define dcache_page_flush(page)      local_dcache_page_flush(page)
+#define icache_page_inv(page)        local_icache_page_inv(page)
+#else  /* CONFIG_SMP */
+#define dcache_page_flush(page)      local_dcache_page_flush(page)
+#define icache_page_inv(page)        smp_icache_page_inv(page)
+extern void smp_icache_page_inv(struct page *page);
+#endif /* CONFIG_SMP */
+
+/*
+ * Synchronizes caches. Whenever a cpu writes executable code to memory, this
+ * should be called to make sure the processor sees the newly written code.
+ */
+static inline void sync_icache_dcache(struct page *page)
+{
+	if (!IS_ENABLED(CONFIG_DCACHE_WRITETHROUGH))
+		dcache_page_flush(page);
+	icache_page_inv(page);
+}
+
+/*
+ * Pages with this bit set need not be flushed/invalidated, since
+ * they have not changed since last flush. New pages start with
+ * PG_arch_1 not set and are therefore dirty by default.
+ */
+#define PG_dc_clean                  PG_arch_1
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+static inline void flush_dcache_page(struct page *page)
+{
+	clear_bit(PG_dc_clean, &page->flags);
+}
+
+/*
+ * Other interfaces are not required since we do not have virtually
+ * indexed or tagged caches. So we can use the default here.
+ */
+#define flush_cache_all()				do { } while (0)
+#define flush_cache_mm(mm)				do { } while (0)
+#define flush_cache_dup_mm(mm)				do { } while (0)
+#define flush_cache_range(vma, start, end)		do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)		do { } while (0)
+#define flush_dcache_mmap_lock(mapping)			do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)		do { } while (0)
+#define flush_icache_range(start, end)			do { } while (0)
+#define flush_icache_page(vma, pg)			do { } while (0)
+#define flush_icache_user_range(vma, pg, adr, len)	do { } while (0)
+#define flush_cache_vmap(start, end)			do { } while (0)
+#define flush_cache_vunmap(start, end)			do { } while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len)           \
+	do {                                                         \
+		memcpy(dst, src, len);                               \
+		if (vma->vm_flags & VM_EXEC)                         \
+			sync_icache_dcache(page);                    \
+	} while (0)
+
+#define copy_from_user_page(vma, page, vaddr, dst, src, len)         \
+	memcpy(dst, src, len)
+
+#endif /* __ASM_CACHEFLUSH_H */
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index eff5ba2a5af2..21c71303012f 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -416,15 +416,19 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; /* defined in head.S */
 
 struct vm_area_struct;
 
-/*
- * or32 doesn't have any external MMU info: the kernel page
- * tables contain all the necessary information.
- *
- * Actually I am not sure on what this could be used for.
- */
+static inline void update_tlb(struct vm_area_struct *vma,
+	unsigned long address, pte_t *pte)
+{
+}
+
+extern void update_cache(struct vm_area_struct *vma,
+	unsigned long address, pte_t *pte);
+
 static inline void update_mmu_cache(struct vm_area_struct *vma,
 	unsigned long address, pte_t *pte)
 {
+	update_tlb(vma, address, pte);
+	update_cache(vma, address, pte);
 }
 
 /* __PHX__ FIXME, SWAP, this probably doesn't work */
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index 685b4934fa39..4763b8b9161e 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -18,6 +18,7 @@
 #include <asm/cpuinfo.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 #include <asm/time.h>
 
 static void (*smp_cross_call)(const struct cpumask *, unsigned int);
@@ -239,3 +240,17 @@ void flush_tlb_range(struct vm_area_struct *vma,
 {
 	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
 }
+
+/* Instruction cache invalidate - performed on each cpu */
+static void ipi_icache_page_inv(void *arg)
+{
+	struct page *page = arg;
+
+	local_icache_page_inv(page);
+}
+
+void smp_icache_page_inv(struct page *page)
+{
+	on_each_cpu(ipi_icache_page_inv, page, 1);
+}
+EXPORT_SYMBOL(smp_icache_page_inv);
diff --git a/arch/openrisc/mm/Makefile b/arch/openrisc/mm/Makefile
index 324ba2634529..a31b2a42e966 100644
--- a/arch/openrisc/mm/Makefile
+++ b/arch/openrisc/mm/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the linux openrisc-specific parts of the memory manager.
 #
 
-obj-y	:= fault.o tlb.o init.o ioremap.o
+obj-y	:= fault.o cache.o tlb.o init.o ioremap.o
diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c
new file mode 100644
index 000000000000..b747bf1fc1b6
--- /dev/null
+++ b/arch/openrisc/mm/cache.c
@@ -0,0 +1,61 @@
+/*
+ * OpenRISC cache.c
+ *
+ * Linux architectural port borrowing liberally from similar works of
+ * others.  All original copyrights apply as per the original source
+ * declaration.
+ *
+ * Modifications for the OpenRISC architecture:
+ * Copyright (C) 2015 Jan Henrik Weinstock <jan.weinstock@rwth-aachen.de>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+#include <asm/cache.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+static void cache_loop(struct page *page, const unsigned int reg)
+{
+	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
+	unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
+
+	while (line < paddr + PAGE_SIZE) {
+		mtspr(reg, line);
+		line += L1_CACHE_BYTES;
+	}
+}
+
+void local_dcache_page_flush(struct page *page)
+{
+	cache_loop(page, SPR_DCBFR);
+}
+EXPORT_SYMBOL(local_dcache_page_flush);
+
+void local_icache_page_inv(struct page *page)
+{
+	cache_loop(page, SPR_ICBIR);
+}
+EXPORT_SYMBOL(local_icache_page_inv);
+
+void update_cache(struct vm_area_struct *vma, unsigned long address,
+	pte_t *pte)
+{
+	unsigned long pfn = pte_val(*pte) >> PAGE_SHIFT;
+	struct page *page = pfn_to_page(pfn);
+	int dirty = !test_and_set_bit(PG_dc_clean, &page->flags);
+
+	/*
+	 * Since icaches do not snoop for updated data on OpenRISC, we
+	 * must write back and invalidate any dirty pages manually. We
+	 * can skip data pages, since they will not end up in icaches.
+	 */
+	if ((vma->vm_flags & VM_EXEC) && dirty)
+		sync_icache_dcache(page);
+}
+
-- 
2.13.6

[OpenRISC] [PATCH v4 10/13] openrisc: add simple_smp dts and defconfig for simulators

[Stafford Horne]

From: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>

Simple enough to be compatible with simulation environments,
such as verilated systems, QEMU and other targets supporting OpenRISC
SMP.  This also supports our base FPGA SoC's if the cpu frequency is
upped to 50Mhz.

Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
[shorne at gmail.com: Added defconfig]
Signed-off-by: Stafford Horne <shorne@gmail.com>
---

Changes since v3
 - none

Changes since v2
 - Fix stdout-path

Changes since v1
 - Use openrisc, prefix for ompic
 - Add stdout-path
 - Remove @interrupt cells

 arch/openrisc/boot/dts/simple_smp.dts      | 63 ++++++++++++++++++++++++++++
 arch/openrisc/configs/simple_smp_defconfig | 66 ++++++++++++++++++++++++++++++
 2 files changed, 129 insertions(+)
 create mode 100644 arch/openrisc/boot/dts/simple_smp.dts
 create mode 100644 arch/openrisc/configs/simple_smp_defconfig

diff --git a/arch/openrisc/boot/dts/simple_smp.dts b/arch/openrisc/boot/dts/simple_smp.dts
new file mode 100644
index 000000000000..defbb92714ec
--- /dev/null
+++ b/arch/openrisc/boot/dts/simple_smp.dts
@@ -0,0 +1,63 @@
+/dts-v1/;
+/ {
+	compatible = "opencores,or1ksim";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&pic>;
+
+	aliases {
+		uart0 = &serial0;
+	};
+
+	chosen {
+		bootargs = "earlycon";
+		stdout-path = "uart0:115200";
+	};
+
+	memory at 0 {
+		device_type = "memory";
+		reg = <0x00000000 0x02000000>;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu at 0 {
+			compatible = "opencores,or1200-rtlsvn481";
+			reg = <0>;
+			clock-frequency = <20000000>;
+		};
+		cpu at 1 {
+			compatible = "opencores,or1200-rtlsvn481";
+			reg = <1>;
+			clock-frequency = <20000000>;
+		};
+	};
+
+	ompic: ompic at 98000000 {
+		compatible = "openrisc,ompic";
+		reg = <0x98000000 16>;
+		interrupt-controller;
+		#interrupt-cells = <0>;
+		interrupts = <1>;
+	};
+
+	/*
+	 * OR1K PIC is built into CPU and accessed via special purpose
+	 * registers.  It is not addressable and, hence, has no 'reg'
+	 * property.
+	 */
+	pic: pic {
+		compatible = "opencores,or1k-pic-level";
+		#interrupt-cells = <1>;
+		interrupt-controller;
+	};
+
+	serial0: serial at 90000000 {
+		compatible = "opencores,uart16550-rtlsvn105", "ns16550a";
+		reg = <0x90000000 0x100>;
+		interrupts = <2>;
+		clock-frequency = <20000000>;
+	};
+
+};
diff --git a/arch/openrisc/configs/simple_smp_defconfig b/arch/openrisc/configs/simple_smp_defconfig
new file mode 100644
index 000000000000..b6e3c7e158e7
--- /dev/null
+++ b/arch/openrisc/configs/simple_smp_defconfig
@@ -0,0 +1,66 @@
+CONFIG_CROSS_COMPILE="or1k-linux-"
+CONFIG_LOCALVERSION="-simple-smp"
+CONFIG_NO_HZ=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_RD_GZIP is not set
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+# CONFIG_RD_XZ is not set
+# CONFIG_RD_LZO is not set
+# CONFIG_RD_LZ4 is not set
+CONFIG_EXPERT=y
+# CONFIG_KALLSYMS is not set
+# CONFIG_EPOLL is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+CONFIG_MODULES=y
+# CONFIG_BLOCK is not set
+CONFIG_OPENRISC_BUILTIN_DTB="simple_smp"
+CONFIG_SMP=y
+CONFIG_HZ_100=y
+CONFIG_OPENRISC_HAVE_SHADOW_GPRS=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
+# CONFIG_TCP_CONG_CUBIC is not set
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+CONFIG_NETDEVICES=y
+CONFIG_ETHOC=y
+CONFIG_MICREL_PHY=y
+# CONFIG_WLAN is not set
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+CONFIG_TMPFS=y
+CONFIG_NFS_FS=y
+CONFIG_XZ_DEC=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+# CONFIG_RCU_TRACE is not set
-- 
2.13.6

[OpenRISC] [PATCH v4 11/13] openrisc: support framepointers and STACKTRACE_SUPPORT

[Stafford Horne]

For lockdep support a reliable stack trace mechanism is needed.  This
patch adds support in OpenRISC for the stacktrace framework, implemented
by a simple unwinder api.  The unwinder api supports both framepointer
and basic stack tracing.

The unwinder is now used to replace the stack_dump() implementation as
well. The new traces are inline with other architectures trace format:

 Call trace:
 [<c0004448>] show_stack+0x3c/0x58
 [<c031c940>] dump_stack+0xa8/0xe4
 [<c0008104>] __cpu_up+0x64/0x130
 [<c000d268>] bringup_cpu+0x3c/0x178
 [<c000d038>] cpuhp_invoke_callback+0xa8/0x1fc
 [<c000d680>] cpuhp_up_callbacks+0x44/0x14c
 [<c000e400>] cpu_up+0x14c/0x1bc
 [<c041da60>] smp_init+0x104/0x15c
 [<c033843c>] ? kernel_init+0x0/0x140
 [<c0415e04>] kernel_init_freeable+0xbc/0x25c
 [<c033843c>] ? kernel_init+0x0/0x140
 [<c0338458>] kernel_init+0x1c/0x140
 [<c003a174>] ? schedule_tail+0x18/0xa0
 [<c0006b80>] ret_from_fork+0x1c/0x9c

Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/Kconfig                |   4 ++
 arch/openrisc/include/asm/unwinder.h |  20 +++++++
 arch/openrisc/kernel/Makefile        |   3 +-
 arch/openrisc/kernel/stacktrace.c    |  86 ++++++++++++++++++++++++++++
 arch/openrisc/kernel/traps.c         |  54 +++---------------
 arch/openrisc/kernel/unwinder.c      | 105 +++++++++++++++++++++++++++++++++++
 6 files changed, 224 insertions(+), 48 deletions(-)
 create mode 100644 arch/openrisc/include/asm/unwinder.h
 create mode 100644 arch/openrisc/kernel/stacktrace.c
 create mode 100644 arch/openrisc/kernel/unwinder.c

diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index bfff04ae7f7d..399f55e82dcb 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -33,6 +33,7 @@ config OPENRISC
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_USE_QUEUED_RWLOCKS
 	select OMPIC if SMP
+	select ARCH_WANT_FRAME_POINTERS
 
 config CPU_BIG_ENDIAN
 	def_bool y
@@ -60,6 +61,9 @@ config TRACE_IRQFLAGS_SUPPORT
 config GENERIC_CSUM
         def_bool y
 
+config STACKTRACE_SUPPORT
+	def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/openrisc/include/asm/unwinder.h b/arch/openrisc/include/asm/unwinder.h
new file mode 100644
index 000000000000..165ec6f02ab8
--- /dev/null
+++ b/arch/openrisc/include/asm/unwinder.h
@@ -0,0 +1,20 @@
+/*
+ * OpenRISC unwinder.h
+ *
+ * Architecture API for unwinding stacks.
+ *
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ASM_OPENRISC_UNWINDER_H
+#define __ASM_OPENRISC_UNWINDER_H
+
+void unwind_stack(void *data, unsigned long *stack,
+		  void (*trace)(void *data, unsigned long addr,
+				int reliable));
+
+#endif /* __ASM_OPENRISC_UNWINDER_H */
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index 7d94643c878d..b4b51a07016a 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -6,9 +6,10 @@ extra-y	:= head.o vmlinux.lds
 
 obj-y	:= setup.o or32_ksyms.o process.o dma.o \
 	   traps.o time.o irq.o entry.o ptrace.o signal.o \
-	   sys_call_table.o
+	   sys_call_table.o unwinder.o
 
 obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_OF)		+= prom.o
 
diff --git a/arch/openrisc/kernel/stacktrace.c b/arch/openrisc/kernel/stacktrace.c
new file mode 100644
index 000000000000..43f140a28bc7
--- /dev/null
+++ b/arch/openrisc/kernel/stacktrace.c
@@ -0,0 +1,86 @@
+/*
+ * Stack trace utility for OpenRISC
+ *
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ * Losely based on work from sh and powerpc.
+ */
+
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/stacktrace.h>
+
+#include <asm/processor.h>
+#include <asm/unwinder.h>
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+static void
+save_stack_address(void *data, unsigned long addr, int reliable)
+{
+	struct stack_trace *trace = data;
+
+	if (!reliable)
+		return;
+
+	if (trace->skip > 0) {
+		trace->skip--;
+		return;
+	}
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = addr;
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	unwind_stack(trace, (unsigned long *) &trace, save_stack_address);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+static void
+save_stack_address_nosched(void *data, unsigned long addr, int reliable)
+{
+	struct stack_trace *trace = (struct stack_trace *)data;
+
+	if (!reliable)
+		return;
+
+	if (in_sched_functions(addr))
+		return;
+
+	if (trace->skip > 0) {
+		trace->skip--;
+		return;
+	}
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = addr;
+}
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	unsigned long *sp = NULL;
+
+	if (tsk == current)
+		sp = (unsigned long *) &sp;
+	else
+		sp = (unsigned long *) KSTK_ESP(tsk);
+
+	unwind_stack(trace, sp, save_stack_address_nosched);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void
+save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+	unwind_stack(trace, (unsigned long *) regs->sp,
+		     save_stack_address_nosched);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_regs);
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 803e9e756f77..4085d72fa5ae 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -38,6 +38,7 @@
 #include <asm/segment.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
+#include <asm/unwinder.h>
 
 extern char _etext, _stext;
 
@@ -45,61 +46,20 @@ int kstack_depth_to_print = 0x180;
 int lwa_flag;
 unsigned long __user *lwa_addr;
 
-static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
+void print_trace(void *data, unsigned long addr, int reliable)
 {
-	return p > (void *)tinfo && p < (void *)tinfo + THREAD_SIZE - 3;
-}
-
-void show_trace(struct task_struct *task, unsigned long *stack)
-{
-	struct thread_info *context;
-	unsigned long addr;
-
-	context = (struct thread_info *)
-	    ((unsigned long)stack & (~(THREAD_SIZE - 1)));
-
-	while (valid_stack_ptr(context, stack)) {
-		addr = *stack++;
-		if (__kernel_text_address(addr)) {
-			printk(" [<%08lx>]", addr);
-			print_symbol(" %s", addr);
-			printk("\n");
-		}
-	}
-	printk(" =======================\n");
+	pr_emerg("[<%p>] %s%pS\n", (void *) addr, reliable ? "" : "? ",
+	       (void *) addr);
 }
 
 /* displays a short stack trace */
 void show_stack(struct task_struct *task, unsigned long *esp)
 {
-	unsigned long addr, *stack;
-	int i;
-
 	if (esp == NULL)
 		esp = (unsigned long *)&esp;
 
-	stack = esp;
-
-	printk("Stack dump [0x%08lx]:\n", (unsigned long)esp);
-	for (i = 0; i < kstack_depth_to_print; i++) {
-		if (kstack_end(stack))
-			break;
-		if (__get_user(addr, stack)) {
-			/* This message matches "failing address" marked
-			   s390 in ksymoops, so lines containing it will
-			   not be filtered out by ksymoops.  */
-			printk("Failing address 0x%lx\n", (unsigned long)stack);
-			break;
-		}
-		stack++;
-
-		printk("sp + %02d: 0x%08lx\n", i * 4, addr);
-	}
-	printk("\n");
-
-	show_trace(task, esp);
-
-	return;
+	pr_emerg("Call trace:\n");
+	unwind_stack(NULL, esp, print_trace);
 }
 
 void show_trace_task(struct task_struct *tsk)
@@ -115,7 +75,7 @@ void show_registers(struct pt_regs *regs)
 	int in_kernel = 1;
 	unsigned long esp;
 
-	esp = (unsigned long)(&regs->sp);
+	esp = (unsigned long)(regs->sp);
 	if (user_mode(regs))
 		in_kernel = 0;
 
diff --git a/arch/openrisc/kernel/unwinder.c b/arch/openrisc/kernel/unwinder.c
new file mode 100644
index 000000000000..8ae15c2c1845
--- /dev/null
+++ b/arch/openrisc/kernel/unwinder.c
@@ -0,0 +1,105 @@
+/*
+ * OpenRISC unwinder.c
+ *
+ * Reusable arch specific api for unwinding stacks.
+ *
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <linux/sched/task_stack.h>
+#include <linux/kernel.h>
+
+#include <asm/unwinder.h>
+
+#ifdef CONFIG_FRAME_POINTER
+struct or1k_frameinfo {
+	unsigned long *fp;
+	unsigned long ra;
+	unsigned long top;
+};
+
+/*
+ * Verify a frameinfo structure.  The return address should be a valid text
+ * address.  The frame pointer may be null if its the last frame, otherwise
+ * the frame pointer should point to a location in the stack after the the
+ * top of the next frame up.
+ */
+static inline int or1k_frameinfo_valid(struct or1k_frameinfo *frameinfo)
+{
+	return (frameinfo->fp == NULL ||
+		(!kstack_end(frameinfo->fp) &&
+		 frameinfo->fp > &frameinfo->top)) &&
+	       __kernel_text_address(frameinfo->ra);
+}
+
+/*
+ * Create a stack trace doing scanning which is frame pointer aware. We can
+ * get reliable stack traces by matching the previously found frame
+ * pointer with the top of the stack address every time we find a valid
+ * or1k_frameinfo.
+ *
+ * Ideally the stack parameter will be passed as FP, but it can not be
+ * guaranteed.  Therefore we scan each address looking for the first sign
+ * of a return address.
+ *
+ * The OpenRISC stack frame looks something like the following.  The
+ * location SP is held in r1 and location FP is held in r2 when frame pointers
+ * enabled.
+ *
+ * SP   -> (top of stack)
+ *      -  (callee saved registers)
+ *      -  (local variables)
+ * FP-8 -> previous FP             \
+ * FP-4 -> return address          |- or1k_frameinfo
+ * FP   -> (previous top of stack) /
+ */
+void unwind_stack(void *data, unsigned long *stack,
+		  void (*trace)(void *data, unsigned long addr, int reliable))
+{
+	unsigned long *next_fp = NULL;
+	struct or1k_frameinfo *frameinfo = NULL;
+	int reliable = 0;
+
+	while (!kstack_end(stack)) {
+		frameinfo = container_of(stack,
+					 struct or1k_frameinfo,
+					 top);
+
+		if (__kernel_text_address(frameinfo->ra)) {
+			if (or1k_frameinfo_valid(frameinfo) &&
+			    (next_fp == NULL ||
+			     next_fp == &frameinfo->top)) {
+				reliable = 1;
+				next_fp = frameinfo->fp;
+			} else
+				reliable = 0;
+
+			trace(data, frameinfo->ra, reliable);
+		}
+		stack++;
+	}
+}
+
+#else /* CONFIG_FRAME_POINTER */
+
+/*
+ * Create a stack trace by doing a simple scan treating all text addresses
+ * as return addresses.
+ */
+void unwind_stack(void *data, unsigned long *stack,
+		   void (*trace)(void *data, unsigned long addr, int reliable))
+{
+	unsigned long addr;
+
+	while (!kstack_end(stack)) {
+		addr = *stack++;
+		if (__kernel_text_address(addr))
+			trace(data, addr, 0);
+	}
+}
+#endif /* CONFIG_FRAME_POINTER */
+
-- 
2.13.6

[OpenRISC] [PATCH v4 12/13] openrisc: enable LOCKDEP_SUPPORT and irqflags tracing

[Stafford Horne]

Lockdep is needed for proving the spinlocks and rwlocks work fine on our
platform.  It also requires calling the trace_hardirqs_off() and
trace_hardirqs_on() pair of routines when entering and exiting an
interrupt.

For OpenRISC the interrupt stack frame does not support frame pointers,
so to call trace_hardirqs_on() and trace_hardirqs_off() here the macro's
build up a stack frame each time.

There is one necessary small change in _sys_call_handler to move
interrupt enabling later so they can get re-enabled during syscall
restart. This was done to fix lockdep warnings that are now possible due
to this
patch.

Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/Kconfig        |  3 ++
 arch/openrisc/kernel/entry.S | 74 ++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 74 insertions(+), 3 deletions(-)

diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 399f55e82dcb..f8cfb3ba9e89 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -64,6 +64,9 @@ config GENERIC_CSUM
 config STACKTRACE_SUPPORT
 	def_bool y
 
+config LOCKDEP_SUPPORT
+	def_bool  y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index 1b7160c79646..690d55272ba6 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -42,6 +42,61 @@
 
 /* =========================================================[ macros ]=== */
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * Trace irq on/off creating a stack frame.
+ */
+#define TRACE_IRQS_OP(trace_op)					\
+	l.sw 	-8(r1),r2	/* store frame pointer */		;\
+	l.sw	-4(r1),r9	/* store return address */		;\
+	l.addi	r2,r1,0		/* move sp to fp */			;\
+	l.jal	trace_op						;\
+	 l.addi	r1,r1,-8						;\
+	l.ori	r1,r2,0		/* restore sp */			;\
+	l.lwz	r9,-4(r1)	/* restore return address */		;\
+	l.lwz	r2,-8(r1)	/* restore fp */			;\
+/*
+ * Trace irq on/off and save registers we need that would otherwise be
+ * clobbered.
+ */
+#define TRACE_IRQS_SAVE(t1,trace_op)					\
+	l.sw	-12(r1),t1	/* save extra reg */			;\
+	l.sw 	-8(r1),r2	/* store frame pointer */		;\
+	l.sw	-4(r1),r9	/* store return address */		;\
+	l.addi	r2,r1,0		/* move sp to fp */			;\
+	l.jal	trace_op						;\
+	 l.addi	r1,r1,-12						;\
+	l.ori	r1,r2,0		/* restore sp */			;\
+	l.lwz	r9,-4(r1)	/* restore return address */		;\
+	l.lwz	r2,-8(r1)	/* restore fp */			;\
+	l.lwz	t1,-12(r1)	/* restore extra reg */
+
+#define TRACE_IRQS_OFF	TRACE_IRQS_OP(trace_hardirqs_off)
+#define TRACE_IRQS_ON	TRACE_IRQS_OP(trace_hardirqs_on)
+#define TRACE_IRQS_ON_SYSCALL						\
+	TRACE_IRQS_SAVE(r10,trace_hardirqs_on)				;\
+	l.lwz	r3,PT_GPR3(r1)						;\
+	l.lwz	r4,PT_GPR4(r1)						;\
+	l.lwz	r5,PT_GPR5(r1)						;\
+	l.lwz	r6,PT_GPR6(r1)						;\
+	l.lwz	r7,PT_GPR7(r1)						;\
+	l.lwz	r8,PT_GPR8(r1)						;\
+	l.lwz	r11,PT_GPR11(r1)
+#define TRACE_IRQS_OFF_ENTRY						\
+	l.lwz	r5,PT_SR(r1)						;\
+	l.andi	r3,r5,(SPR_SR_IEE|SPR_SR_TEE)				;\
+	l.sfeq	r5,r0		/* skip trace if irqs were already off */;\
+	l.bf	1f							;\
+	 l.nop								;\
+	TRACE_IRQS_SAVE(r4,trace_hardirqs_off)				;\
+1:
+#else
+#define TRACE_IRQS_OFF
+#define TRACE_IRQS_ON
+#define TRACE_IRQS_OFF_ENTRY
+#define TRACE_IRQS_ON_SYSCALL
+#endif
+
 /*
  * We need to disable interrupts at beginning of RESTORE_ALL
  * since interrupt might come in after we've loaded EPC return address
@@ -124,6 +179,7 @@ handler:							;\
 	/* r30 already save */					;\
 /*        l.sw    PT_GPR30(r1),r30*/					;\
 	l.sw    PT_GPR31(r1),r31					;\
+	TRACE_IRQS_OFF_ENTRY						;\
 	/* Store -1 in orig_gpr11 for non-syscall exceptions */	;\
 	l.addi	r30,r0,-1					;\
 	l.sw	PT_ORIG_GPR11(r1),r30
@@ -557,9 +613,6 @@ _string_syscall_return:
 	.align 4
 
 ENTRY(_sys_call_handler)
-	/* syscalls run with interrupts enabled */
-	ENABLE_INTERRUPTS(r29)		// enable interrupts, r29 is temp
-
 	/* r1, EPCR, ESR a already saved */
 	l.sw	PT_GPR2(r1),r2
 	/* r3-r8 must be saved because syscall restart relies
@@ -597,6 +650,10 @@ ENTRY(_sys_call_handler)
 /*	l.sw    PT_GPR30(r1),r30 */
 
 _syscall_check_trace_enter:
+	/* syscalls run with interrupts enabled */
+	TRACE_IRQS_ON_SYSCALL
+	ENABLE_INTERRUPTS(r29)		// enable interrupts, r29 is temp
+
 	/* If TIF_SYSCALL_TRACE is set, then we want to do syscall tracing */
 	l.lwz	r30,TI_FLAGS(r10)
 	l.andi	r30,r30,_TIF_SYSCALL_TRACE
@@ -657,6 +714,7 @@ _syscall_check_trace_leave:
 _syscall_check_work:
 	/* Here we need to disable interrupts */
 	DISABLE_INTERRUPTS(r27,r29)
+	TRACE_IRQS_OFF
 	l.lwz	r30,TI_FLAGS(r10)
 	l.andi	r30,r30,_TIF_WORK_MASK
 	l.sfne	r30,r0
@@ -871,6 +929,7 @@ UNHANDLED_EXCEPTION(_vector_0x1f00,0x1f00)
 
 _resume_userspace:
 	DISABLE_INTERRUPTS(r3,r4)
+	TRACE_IRQS_OFF
 	l.lwz	r4,TI_FLAGS(r10)
 	l.andi	r13,r4,_TIF_WORK_MASK
 	l.sfeqi	r13,0
@@ -909,6 +968,15 @@ _work_pending:
 	 l.lwz	r8,PT_GPR8(r1)
 
 _restore_all:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	l.lwz	r4,PT_SR(r1)
+	l.andi	r3,r4,(SPR_SR_IEE|SPR_SR_TEE)
+	l.sfeq	r3,r0		/* skip trace if irqs were off */
+	l.bf	skip_hardirqs_on
+	 l.nop
+	TRACE_IRQS_ON
+skip_hardirqs_on:
+#endif
 	RESTORE_ALL
 	/* This returns to userspace code */
 
-- 
2.13.6

[OpenRISC] [PATCH v4 13/13] openrisc: add tick timer multi-core sync logic

[Stafford Horne]

In case timers are not in sync when cpus start (i.e. hot plug / offset
resets) we need to synchronize the secondary cpus internal timer with
the main cpu.  This is needed as in OpenRISC SMP there is only one
clocksource registered which reads from the same ttcr register on each
cpu.

This synchronization routine heavily borrows from mips implementation that
does something similar.

Signed-off-by: Stafford Horne <shorne@gmail.com>
---

Changes since v2
 - none

Changes since v1
 - change from timer-sync.h header to just time.h

 arch/openrisc/include/asm/time.h  |   8 +++
 arch/openrisc/kernel/Makefile     |   2 +-
 arch/openrisc/kernel/smp.c        |   3 +
 arch/openrisc/kernel/sync-timer.c | 120 ++++++++++++++++++++++++++++++++++++++
 arch/openrisc/kernel/time.c       |  15 ++++-
 5 files changed, 145 insertions(+), 3 deletions(-)
 create mode 100644 arch/openrisc/kernel/sync-timer.c

diff --git a/arch/openrisc/include/asm/time.h b/arch/openrisc/include/asm/time.h
index fe83a34a7d68..313ee975774b 100644
--- a/arch/openrisc/include/asm/time.h
+++ b/arch/openrisc/include/asm/time.h
@@ -12,4 +12,12 @@
 
 extern void openrisc_clockevent_init(void);
 
+extern void openrisc_timer_set(unsigned long count);
+extern void openrisc_timer_set_next(unsigned long delta);
+
+#ifdef CONFIG_SMP
+extern void synchronise_count_master(int cpu);
+extern void synchronise_count_slave(int cpu);
+#endif
+
 #endif /* __ASM_OR1K_TIME_H */
diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index b4b51a07016a..9028e5a1fdd7 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -8,7 +8,7 @@ obj-y	:= setup.o or32_ksyms.o process.o dma.o \
 	   traps.o time.o irq.o entry.o ptrace.o signal.o \
 	   sys_call_table.o unwinder.o
 
-obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_SMP)		+= smp.o sync-timer.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_OF)		+= prom.o
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index 4763b8b9161e..4d80ce6fa045 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -100,6 +100,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		pr_crit("CPU%u: failed to start\n", cpu);
 		return -EIO;
 	}
+	synchronise_count_master(cpu);
 
 	return 0;
 }
@@ -129,6 +130,8 @@ asmlinkage __init void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
+	synchronise_count_slave(cpu);
+
 	local_irq_enable();
 
 	preempt_disable();
diff --git a/arch/openrisc/kernel/sync-timer.c b/arch/openrisc/kernel/sync-timer.c
new file mode 100644
index 000000000000..ed8d835caca1
--- /dev/null
+++ b/arch/openrisc/kernel/sync-timer.c
@@ -0,0 +1,120 @@
+/*
+ * OR1K timer synchronisation
+ *
+ * Based on work from MIPS implementation.
+ *
+ * All CPUs will have their count registers synchronised to the CPU0 next time
+ * value. This can cause a small timewarp for CPU0. All other CPU's should
+ * not have done anything significant (but they may have had interrupts
+ * enabled briefly - prom_smp_finish() should not be responsible for enabling
+ * interrupts...)
+ */
+
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+#include <linux/cpumask.h>
+
+#include <asm/time.h>
+#include <asm/timex.h>
+#include <linux/atomic.h>
+#include <asm/barrier.h>
+
+#include <asm/spr.h>
+
+static unsigned int initcount;
+static atomic_t count_count_start = ATOMIC_INIT(0);
+static atomic_t count_count_stop = ATOMIC_INIT(0);
+
+#define COUNTON 100
+#define NR_LOOPS 3
+
+void synchronise_count_master(int cpu)
+{
+	int i;
+	unsigned long flags;
+
+	pr_info("Synchronize counters for CPU %u: ", cpu);
+
+	local_irq_save(flags);
+
+	/*
+	 * We loop a few times to get a primed instruction cache,
+	 * then the last pass is more or less synchronised and
+	 * the master and slaves each set their cycle counters to a known
+	 * value all at once. This reduces the chance of having random offsets
+	 * between the processors, and guarantees that the maximum
+	 * delay between the cycle counters is never bigger than
+	 * the latency of information-passing (cachelines) between
+	 * two CPUs.
+	 */
+
+	for (i = 0; i < NR_LOOPS; i++) {
+		/* slaves loop on '!= 2' */
+		while (atomic_read(&count_count_start) != 1)
+			mb();
+		atomic_set(&count_count_stop, 0);
+		smp_wmb();
+
+		/* Let the slave writes its count register */
+		atomic_inc(&count_count_start);
+
+		/* Count will be initialised to current timer */
+		if (i == 1)
+			initcount = get_cycles();
+
+		/*
+		 * Everyone initialises count in the last loop:
+		 */
+		if (i == NR_LOOPS-1)
+			openrisc_timer_set(initcount);
+
+		/*
+		 * Wait for slave to leave the synchronization point:
+		 */
+		while (atomic_read(&count_count_stop) != 1)
+			mb();
+		atomic_set(&count_count_start, 0);
+		smp_wmb();
+		atomic_inc(&count_count_stop);
+	}
+	/* Arrange for an interrupt in a short while */
+	openrisc_timer_set_next(COUNTON);
+
+	local_irq_restore(flags);
+
+	/*
+	 * i386 code reported the skew here, but the
+	 * count registers were almost certainly out of sync
+	 * so no point in alarming people
+	 */
+	pr_cont("done.\n");
+}
+
+void synchronise_count_slave(int cpu)
+{
+	int i;
+
+	/*
+	 * Not every cpu is online@the time this gets called,
+	 * so we first wait for the master to say everyone is ready
+	 */
+
+	for (i = 0; i < NR_LOOPS; i++) {
+		atomic_inc(&count_count_start);
+		while (atomic_read(&count_count_start) != 2)
+			mb();
+
+		/*
+		 * Everyone initialises count in the last loop:
+		 */
+		if (i == NR_LOOPS-1)
+			openrisc_timer_set(initcount);
+
+		atomic_inc(&count_count_stop);
+		while (atomic_read(&count_count_stop) != 2)
+			mb();
+	}
+	/* Arrange for an interrupt in a short while */
+	openrisc_timer_set_next(COUNTON);
+}
+#undef NR_LOOPS
diff --git a/arch/openrisc/kernel/time.c b/arch/openrisc/kernel/time.c
index ab04eaedbf8d..6baecea27080 100644
--- a/arch/openrisc/kernel/time.c
+++ b/arch/openrisc/kernel/time.c
@@ -27,8 +27,14 @@
 
 #include <asm/cpuinfo.h>
 
-static int openrisc_timer_set_next_event(unsigned long delta,
-					 struct clock_event_device *dev)
+/* Test the timer ticks to count, used in sync routine */
+inline void openrisc_timer_set(unsigned long count)
+{
+	mtspr(SPR_TTCR, count);
+}
+
+/* Set the timer to trigger in delta cycles */
+inline void openrisc_timer_set_next(unsigned long delta)
 {
 	u32 c;
 
@@ -44,7 +50,12 @@ static int openrisc_timer_set_next_event(unsigned long delta,
 	 * Keep timer in continuous mode always.
 	 */
 	mtspr(SPR_TTMR, SPR_TTMR_CR | SPR_TTMR_IE | c);
+}
 
+static int openrisc_timer_set_next_event(unsigned long delta,
+					 struct clock_event_device *dev)
+{
+	openrisc_timer_set_next(delta);
 	return 0;
 }
 
-- 
2.13.6

[OpenRISC] [PATCH v4 13/13] openrisc: add tick timer multi-core sync logic

[Matt Redfearn]

Hi,


On 29/10/17 23:11, Stafford Horne wrote:
> In case timers are not in sync when cpus start (i.e. hot plug / offset
> resets) we need to synchronize the secondary cpus internal timer with
> the main cpu.  This is needed as in OpenRISC SMP there is only one
> clocksource registered which reads from the same ttcr register on each
> cpu.
>
> This synchronization routine heavily borrows from mips implementation that
> does something similar.
> Signed-off-by: Stafford Horne <shorne@gmail.com>
> ---
>
> Changes since v2
>   - none
>
> Changes since v1
>   - change from timer-sync.h header to just time.h
>
>   arch/openrisc/include/asm/time.h  |   8 +++
>   arch/openrisc/kernel/Makefile     |   2 +-
>   arch/openrisc/kernel/smp.c        |   3 +
>   arch/openrisc/kernel/sync-timer.c | 120 ++++++++++++++++++++++++++++++++++++++
>   arch/openrisc/kernel/time.c       |  15 ++++-
>   5 files changed, 145 insertions(+), 3 deletions(-)
>   create mode 100644 arch/openrisc/kernel/sync-timer.c
>
> diff --git a/arch/openrisc/include/asm/time.h b/arch/openrisc/include/asm/time.h
> index fe83a34a7d68..313ee975774b 100644
> --- a/arch/openrisc/include/asm/time.h
> +++ b/arch/openrisc/include/asm/time.h
> @@ -12,4 +12,12 @@
>   
>   extern void openrisc_clockevent_init(void);
>   
> +extern void openrisc_timer_set(unsigned long count);
> +extern void openrisc_timer_set_next(unsigned long delta);
> +
> +#ifdef CONFIG_SMP
> +extern void synchronise_count_master(int cpu);
> +extern void synchronise_count_slave(int cpu);
> +#endif
> +
>   #endif /* __ASM_OR1K_TIME_H */
> diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
> index b4b51a07016a..9028e5a1fdd7 100644
> --- a/arch/openrisc/kernel/Makefile
> +++ b/arch/openrisc/kernel/Makefile
> @@ -8,7 +8,7 @@ obj-y	:= setup.o or32_ksyms.o process.o dma.o \
>   	   traps.o time.o irq.o entry.o ptrace.o signal.o \
>   	   sys_call_table.o unwinder.o
>   
> -obj-$(CONFIG_SMP)		+= smp.o
> +obj-$(CONFIG_SMP)		+= smp.o sync-timer.o
>   obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
>   obj-$(CONFIG_MODULES)		+= module.o
>   obj-$(CONFIG_OF)		+= prom.o
> diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
> index 4763b8b9161e..4d80ce6fa045 100644
> --- a/arch/openrisc/kernel/smp.c
> +++ b/arch/openrisc/kernel/smp.c
> @@ -100,6 +100,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
>   		pr_crit("CPU%u: failed to start\n", cpu);
>   		return -EIO;
>   	}
> +	synchronise_count_master(cpu);
>   
>   	return 0;
>   }
> @@ -129,6 +130,8 @@ asmlinkage __init void secondary_start_kernel(void)
>   	set_cpu_online(cpu, true);
>   	complete(&cpu_running);
>   
> +	synchronise_count_slave(cpu);
> +


Note that until 8f46cca1e6c06a058374816887059bcc017b382f, the MIPS timer 
synchronization code contained the possibility of deadlock. If you mark 
a CPU online before it goes into the synchronize loop, then the boot CPU 
can schedule a different thread and send IPIs to all "online" CPUs. It 
gets stuck waiting for the secondary to ack it's IPI, since this 
secondary CPU has not enabled IRQs yet, and is stuck waiting for the 
master to synchronise with it. The system then deadlocks.
Commit 8f46cca1e6c06a058374816887059bcc017b382f fixed this for MIPS and 
you might want to similarly move the

set_cpu_online(cpu, true);

after counters are synchronized.

Thanks,
Matt

>   	local_irq_enable();
>   
>   	preempt_disable();
> diff --git a/arch/openrisc/kernel/sync-timer.c b/arch/openrisc/kernel/sync-timer.c
> new file mode 100644
> index 000000000000..ed8d835caca1
> --- /dev/null
> +++ b/arch/openrisc/kernel/sync-timer.c
> @@ -0,0 +1,120 @@
> +/*
> + * OR1K timer synchronisation
> + *
> + * Based on work from MIPS implementation.
> + *
> + * All CPUs will have their count registers synchronised to the CPU0 next time
> + * value. This can cause a small timewarp for CPU0. All other CPU's should
> + * not have done anything significant (but they may have had interrupts
> + * enabled briefly - prom_smp_finish() should not be responsible for enabling
> + * interrupts...)
> + */
> +
> +#include <linux/kernel.h>
> +#include <linux/irqflags.h>
> +#include <linux/cpumask.h>
> +
> +#include <asm/time.h>
> +#include <asm/timex.h>
> +#include <linux/atomic.h>
> +#include <asm/barrier.h>
> +
> +#include <asm/spr.h>
> +
> +static unsigned int initcount;
> +static atomic_t count_count_start = ATOMIC_INIT(0);
> +static atomic_t count_count_stop = ATOMIC_INIT(0);
> +
> +#define COUNTON 100
> +#define NR_LOOPS 3
> +
> +void synchronise_count_master(int cpu)
> +{
> +	int i;
> +	unsigned long flags;
> +
> +	pr_info("Synchronize counters for CPU %u: ", cpu);
> +
> +	local_irq_save(flags);
> +
> +	/*
> +	 * We loop a few times to get a primed instruction cache,
> +	 * then the last pass is more or less synchronised and
> +	 * the master and slaves each set their cycle counters to a known
> +	 * value all at once. This reduces the chance of having random offsets
> +	 * between the processors, and guarantees that the maximum
> +	 * delay between the cycle counters is never bigger than
> +	 * the latency of information-passing (cachelines) between
> +	 * two CPUs.
> +	 */
> +
> +	for (i = 0; i < NR_LOOPS; i++) {
> +		/* slaves loop on '!= 2' */
> +		while (atomic_read(&count_count_start) != 1)
> +			mb();
> +		atomic_set(&count_count_stop, 0);
> +		smp_wmb();
> +
> +		/* Let the slave writes its count register */
> +		atomic_inc(&count_count_start);
> +
> +		/* Count will be initialised to current timer */
> +		if (i == 1)
> +			initcount = get_cycles();
> +
> +		/*
> +		 * Everyone initialises count in the last loop:
> +		 */
> +		if (i == NR_LOOPS-1)
> +			openrisc_timer_set(initcount);
> +
> +		/*
> +		 * Wait for slave to leave the synchronization point:
> +		 */
> +		while (atomic_read(&count_count_stop) != 1)
> +			mb();
> +		atomic_set(&count_count_start, 0);
> +		smp_wmb();
> +		atomic_inc(&count_count_stop);
> +	}
> +	/* Arrange for an interrupt in a short while */
> +	openrisc_timer_set_next(COUNTON);
> +
> +	local_irq_restore(flags);
> +
> +	/*
> +	 * i386 code reported the skew here, but the
> +	 * count registers were almost certainly out of sync
> +	 * so no point in alarming people
> +	 */
> +	pr_cont("done.\n");
> +}
> +
> +void synchronise_count_slave(int cpu)
> +{
> +	int i;
> +
> +	/*
> +	 * Not every cpu is online at the time this gets called,
> +	 * so we first wait for the master to say everyone is ready
> +	 */
> +
> +	for (i = 0; i < NR_LOOPS; i++) {
> +		atomic_inc(&count_count_start);
> +		while (atomic_read(&count_count_start) != 2)
> +			mb();
> +
> +		/*
> +		 * Everyone initialises count in the last loop:
> +		 */
> +		if (i == NR_LOOPS-1)
> +			openrisc_timer_set(initcount);
> +
> +		atomic_inc(&count_count_stop);
> +		while (atomic_read(&count_count_stop) != 2)
> +			mb();
> +	}
> +	/* Arrange for an interrupt in a short while */
> +	openrisc_timer_set_next(COUNTON);
> +}
> +#undef NR_LOOPS
> diff --git a/arch/openrisc/kernel/time.c b/arch/openrisc/kernel/time.c
> index ab04eaedbf8d..6baecea27080 100644
> --- a/arch/openrisc/kernel/time.c
> +++ b/arch/openrisc/kernel/time.c
> @@ -27,8 +27,14 @@
>   
>   #include <asm/cpuinfo.h>
>   
> -static int openrisc_timer_set_next_event(unsigned long delta,
> -					 struct clock_event_device *dev)
> +/* Test the timer ticks to count, used in sync routine */
> +inline void openrisc_timer_set(unsigned long count)
> +{
> +	mtspr(SPR_TTCR, count);
> +}
> +
> +/* Set the timer to trigger in delta cycles */
> +inline void openrisc_timer_set_next(unsigned long delta)
>   {
>   	u32 c;
>   
> @@ -44,7 +50,12 @@ static int openrisc_timer_set_next_event(unsigned long delta,
>   	 * Keep timer in continuous mode always.
>   	 */
>   	mtspr(SPR_TTMR, SPR_TTMR_CR | SPR_TTMR_IE | c);
> +}
>   
> +static int openrisc_timer_set_next_event(unsigned long delta,
> +					 struct clock_event_device *dev)
> +{
> +	openrisc_timer_set_next(delta);
>   	return 0;
>   }
>   

[OpenRISC] [PATCH v4 13/13] openrisc: add tick timer multi-core sync logic

[Stafford Horne]

On Tue, Oct 31, 2017 at 02:06:21PM +0000, Matt Redfearn wrote:
> Hi,
> 
> 
> On 29/10/17 23:11, Stafford Horne wrote:
> > In case timers are not in sync when cpus start (i.e. hot plug / offset
> > resets) we need to synchronize the secondary cpus internal timer with
> > the main cpu.  This is needed as in OpenRISC SMP there is only one
> > clocksource registered which reads from the same ttcr register on each
> > cpu.
> > 
> > This synchronization routine heavily borrows from mips implementation that
> > does something similar.
[..]
> > diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
> > index 4763b8b9161e..4d80ce6fa045 100644
> > --- a/arch/openrisc/kernel/smp.c
> > +++ b/arch/openrisc/kernel/smp.c
> > @@ -100,6 +100,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
> >   		pr_crit("CPU%u: failed to start\n", cpu);
> >   		return -EIO;
> >   	}
> > +	synchronise_count_master(cpu);
> >   	return 0;
> >   }
> > @@ -129,6 +130,8 @@ asmlinkage __init void secondary_start_kernel(void)
> >   	set_cpu_online(cpu, true);
> >   	complete(&cpu_running);
> > +	synchronise_count_slave(cpu);
> > +
> 
> 
> Note that until 8f46cca1e6c06a058374816887059bcc017b382f, the MIPS timer
> synchronization code contained the possibility of deadlock. If you mark a
> CPU online before it goes into the synchronize loop, then the boot CPU can
> schedule a different thread and send IPIs to all "online" CPUs. It gets
> stuck waiting for the secondary to ack it's IPI, since this secondary CPU
> has not enabled IRQs yet, and is stuck waiting for the master to synchronise
> with it. The system then deadlocks.
> Commit 8f46cca1e6c06a058374816887059bcc017b382f fixed this for MIPS and you
> might want to similarly move the
> 
> set_cpu_online(cpu, true);
> 
> after counters are synchronized.

Thank you for the heads up.  I do remember having interim issues with the timer
syncing but I havent seen it for a while.  I think I fixed it by also moving
synchronise_count_slave.

Let me double check.  Also, I see your patch 8f46cca1e6c06a0583748168 was merged
last year?

-Stafford

[OpenRISC] [PATCH v4 13/13] openrisc: add tick timer multi-core sync logic

[Stafford Horne]

On Wed, Nov 01, 2017 at 08:17:59AM +0900, Stafford Horne wrote:
> On Tue, Oct 31, 2017 at 02:06:21PM +0000, Matt Redfearn wrote:
> > Hi,
> > 
> > 
> > On 29/10/17 23:11, Stafford Horne wrote:
> > > In case timers are not in sync when cpus start (i.e. hot plug / offset
> > > resets) we need to synchronize the secondary cpus internal timer with
> > > the main cpu.  This is needed as in OpenRISC SMP there is only one
> > > clocksource registered which reads from the same ttcr register on each
> > > cpu.
> > > 
> > > This synchronization routine heavily borrows from mips implementation that
> > > does something similar.
> [..]
> > > diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
> > > index 4763b8b9161e..4d80ce6fa045 100644
> > > --- a/arch/openrisc/kernel/smp.c
> > > +++ b/arch/openrisc/kernel/smp.c
> > > @@ -100,6 +100,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
> > >   		pr_crit("CPU%u: failed to start\n", cpu);
> > >   		return -EIO;
> > >   	}
> > > +	synchronise_count_master(cpu);
> > >   	return 0;
> > >   }
> > > @@ -129,6 +130,8 @@ asmlinkage __init void secondary_start_kernel(void)
> > >   	set_cpu_online(cpu, true);
> > >   	complete(&cpu_running);
> > > +	synchronise_count_slave(cpu);
> > > +
> > 
> > 
> > Note that until 8f46cca1e6c06a058374816887059bcc017b382f, the MIPS timer
> > synchronization code contained the possibility of deadlock. If you mark a
> > CPU online before it goes into the synchronize loop, then the boot CPU can
> > schedule a different thread and send IPIs to all "online" CPUs. It gets
> > stuck waiting for the secondary to ack it's IPI, since this secondary CPU
> > has not enabled IRQs yet, and is stuck waiting for the master to synchronise
> > with it. The system then deadlocks.
> > Commit 8f46cca1e6c06a058374816887059bcc017b382f fixed this for MIPS and you
> > might want to similarly move the
> > 
> > set_cpu_online(cpu, true);
> > 
> > after counters are synchronized.
> 
> Thank you for the heads up.  I do remember having interim issues with the timer
> syncing but I havent seen it for a while.  I think I fixed it by also moving
> synchronise_count_slave.
> 
> Let me double check.  Also, I see your patch 8f46cca1e6c06a0583748168 was merged
> last year?

Hello,

I should have read a bit more closely, definitely this could be an issue if the
boot cpu has other things running.

However, looking at mainline I can see the clock sync comes after set_cpu_online
again after this patch in mips.

  6f542ebeaee0 MIPS: Fix race on setting and getting cpu_online_mask
  Author: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com>

Is this deadlock an issue in mips again?

-Stafford

[OpenRISC] [PATCH v4 13/13] openrisc: add tick timer multi-core sync logic

[Matt Redfearn]

On 01/11/17 00:34, Stafford Horne wrote:
> On Wed, Nov 01, 2017 at 08:17:59AM +0900, Stafford Horne wrote:
>> On Tue, Oct 31, 2017 at 02:06:21PM +0000, Matt Redfearn wrote:
>>> Hi,
>>>
>>>
>>> On 29/10/17 23:11, Stafford Horne wrote:
>>>> In case timers are not in sync when cpus start (i.e. hot plug / offset
>>>> resets) we need to synchronize the secondary cpus internal timer with
>>>> the main cpu.  This is needed as in OpenRISC SMP there is only one
>>>> clocksource registered which reads from the same ttcr register on each
>>>> cpu.
>>>>
>>>> This synchronization routine heavily borrows from mips implementation that
>>>> does something similar.
>> [..]
>>>> diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
>>>> index 4763b8b9161e..4d80ce6fa045 100644
>>>> --- a/arch/openrisc/kernel/smp.c
>>>> +++ b/arch/openrisc/kernel/smp.c
>>>> @@ -100,6 +100,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
>>>>    		pr_crit("CPU%u: failed to start\n", cpu);
>>>>    		return -EIO;
>>>>    	}
>>>> +	synchronise_count_master(cpu);
>>>>    	return 0;
>>>>    }
>>>> @@ -129,6 +130,8 @@ asmlinkage __init void secondary_start_kernel(void)
>>>>    	set_cpu_online(cpu, true);
>>>>    	complete(&cpu_running);
>>>> +	synchronise_count_slave(cpu);
>>>> +
>>>
>>> Note that until 8f46cca1e6c06a058374816887059bcc017b382f, the MIPS timer
>>> synchronization code contained the possibility of deadlock. If you mark a
>>> CPU online before it goes into the synchronize loop, then the boot CPU can
>>> schedule a different thread and send IPIs to all "online" CPUs. It gets
>>> stuck waiting for the secondary to ack it's IPI, since this secondary CPU
>>> has not enabled IRQs yet, and is stuck waiting for the master to synchronise
>>> with it. The system then deadlocks.
>>> Commit 8f46cca1e6c06a058374816887059bcc017b382f fixed this for MIPS and you
>>> might want to similarly move the
>>>
>>> set_cpu_online(cpu, true);
>>>
>>> after counters are synchronized.
>> Thank you for the heads up.  I do remember having interim issues with the timer
>> syncing but I havent seen it for a while.  I think I fixed it by also moving
>> synchronise_count_slave.
>>
>> Let me double check.  Also, I see your patch 8f46cca1e6c06a0583748168 was merged
>> last year?
> Hello,
>
> I should have read a bit more closely, definitely this could be an issue if the
> boot cpu has other things running.
>
> However, looking at mainline I can see the clock sync comes after set_cpu_online
> again after this patch in mips.
>
>    6f542ebeaee0 MIPS: Fix race on setting and getting cpu_online_mask
>    Author: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com>
>
> Is this deadlock an issue in mips again?
>
> -Stafford

Hi Stafford,

Yes - the deadlock is an issue again, it was re-introduced by 
6f542ebeaee0. That patch was based on testing with 4.4, where the core 
CPU hotplug code did not contain it's own completion event. Since commit 
8df3e07e7f21f ("cpu/hotplug: Let upcoming cpu bring itself fully up"), 
which was added in 4.6, this is no longer the case and there is no race 
condition. I have https://patchwork.linux-mips.org/patch/17376/ pending 
which fixes this race in pre-4.6 stable kernels, and guards against the 
deadlock as well. Unfortunately because of the backport to stable this 
gets a little more complex.

Unless your patches to add SMP are going to be applied to pre-4.6 
kernels, then you will not suffer the race condition. The potential 
deadlock is the only pitfall you need to guard against - which will be 
OK if you put the clock sync before marking the CPU online.

Thanks,
Matt

[OpenRISC] [PATCH v4 13/13] openrisc: add tick timer multi-core sync logic

[Stafford Horne]

On Wed, Nov 01, 2017 at 09:26:43AM +0000, Matt Redfearn wrote:
> 
> 
> On 01/11/17 00:34, Stafford Horne wrote:
> > On Wed, Nov 01, 2017 at 08:17:59AM +0900, Stafford Horne wrote:
> > > On Tue, Oct 31, 2017 at 02:06:21PM +0000, Matt Redfearn wrote:
> > > > Hi,
> > > > 
> > > > 
> > > > On 29/10/17 23:11, Stafford Horne wrote:
> > > > > In case timers are not in sync when cpus start (i.e. hot plug / offset
> > > > > resets) we need to synchronize the secondary cpus internal timer with
> > > > > the main cpu.  This is needed as in OpenRISC SMP there is only one
> > > > > clocksource registered which reads from the same ttcr register on each
> > > > > cpu.
> > > > > 
> > > > > This synchronization routine heavily borrows from mips implementation that
> > > > > does something similar.
> > > [..]
> > > > > diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
> > > > > index 4763b8b9161e..4d80ce6fa045 100644
> > > > > --- a/arch/openrisc/kernel/smp.c
> > > > > +++ b/arch/openrisc/kernel/smp.c
> > > > > @@ -100,6 +100,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
> > > > >    		pr_crit("CPU%u: failed to start\n", cpu);
> > > > >    		return -EIO;
> > > > >    	}
> > > > > +	synchronise_count_master(cpu);
> > > > >    	return 0;
> > > > >    }
> > > > > @@ -129,6 +130,8 @@ asmlinkage __init void secondary_start_kernel(void)
> > > > >    	set_cpu_online(cpu, true);
> > > > >    	complete(&cpu_running);
> > > > > +	synchronise_count_slave(cpu);
> > > > > +
> > > > 
> > > > Note that until 8f46cca1e6c06a058374816887059bcc017b382f, the MIPS timer
> > > > synchronization code contained the possibility of deadlock. If you mark a
> > > > CPU online before it goes into the synchronize loop, then the boot CPU can
> > > > schedule a different thread and send IPIs to all "online" CPUs. It gets
> > > > stuck waiting for the secondary to ack it's IPI, since this secondary CPU
> > > > has not enabled IRQs yet, and is stuck waiting for the master to synchronise
> > > > with it. The system then deadlocks.
> > > > Commit 8f46cca1e6c06a058374816887059bcc017b382f fixed this for MIPS and you
> > > > might want to similarly move the
> > > > 
> > > > set_cpu_online(cpu, true);
> > > > 
> > > > after counters are synchronized.
> > > Thank you for the heads up.  I do remember having interim issues with the timer
> > > syncing but I havent seen it for a while.  I think I fixed it by also moving
> > > synchronise_count_slave.
> > > 
> > > Let me double check.  Also, I see your patch 8f46cca1e6c06a0583748168 was merged
> > > last year?
> > Hello,
> > 
> > I should have read a bit more closely, definitely this could be an issue if the
> > boot cpu has other things running.
> > 
> > However, looking at mainline I can see the clock sync comes after set_cpu_online
> > again after this patch in mips.
> > 
> >    6f542ebeaee0 MIPS: Fix race on setting and getting cpu_online_mask
> >    Author: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com>
> > 
> > Is this deadlock an issue in mips again?
> > 
> > -Stafford
> 
> Hi Stafford,
> 
> Yes - the deadlock is an issue again, it was re-introduced by 6f542ebeaee0.
> That patch was based on testing with 4.4, where the core CPU hotplug code
> did not contain it's own completion event. Since commit 8df3e07e7f21f
> ("cpu/hotplug: Let upcoming cpu bring itself fully up"), which was added in
> 4.6, this is no longer the case and there is no race condition. I have
> https://patchwork.linux-mips.org/patch/17376/ pending which fixes this race
> in pre-4.6 stable kernels, and guards against the deadlock as well.
> Unfortunately because of the backport to stable this gets a little more
> complex.
> 
> Unless your patches to add SMP are going to be applied to pre-4.6 kernels,
> then you will not suffer the race condition. The potential deadlock is the
> only pitfall you need to guard against - which will be OK if you put the
> clock sync before marking the CPU online.
> 
> Thanks,
> Matt

Hi Matt,

Thanks for the details.  I will make the patch and test it out.

On a side note, I was thinking to pull the sync code out into asm-generic in
case any other architectures want to use it, it seems generic enough to work for
other architectures.  Any thoughts?

-Stafford