Merge tag 'for-linus' of git://github.com/openrisc/linux

Pull OpenRISC updates from Stafford Horne:
 "The OpenRISC work is a bit more interesting this time, adding SMP
  support and a few general cleanups.

  Small Things:

   - Move OpenRISC docs into Documentation and clean them up

   - Document previously undocumented devicetree bindings

   - Update the or1ksim dts to use stdout-path

  OpenRISC SMP support details:

   - First the "use shadow registers" and "define CPU_BIG_ENDIAN as
     true" get the architecture ready for SMP.

   - The "add 1 and 2 byte cmpxchg support" and "use qspinlocks and
     qrwlocks" add the SMP locking infrastructure as needed. Using the
     qspinlocks and qrwlocks as suggested by Peter Z while reviewing the
     original spinlocks implementation.

   - The "support for ompic" adds a new irqchip device which is used for
     IPI communication to support SMP.

   - The "initial SMP support" adds smp.c and makes changes to all of
     the necessary data-structures to be per-cpu.

  The remaining patches are bug fixes and debug helpers which I wanted
  to keep separate from the "initial SMP support" in order to allow them
  to be reviewed on their own. This includes:

   - add cacheflush support to fix icache aliasing

   - fix initial preempt state for secondary cpu tasks

   - sleep instead of spin on secondary wait

   - support framepointers and STACKTRACE_SUPPORT

   - enable LOCKDEP_SUPPORT and irqflags tracing

   - timer sync: Add tick timer sync logic

   - fix possible deadlock in timer sync, pointed out by mips guys

  Note: the irqchip patch was reviewed with Marc and we agreed to push
  it together with these patches"

* tag 'for-linus' of git://github.com/openrisc/linux:
  openrisc: fix possible deadlock scenario during timer sync
  openrisc: pass endianness info to sparse
  openrisc: add tick timer multi-core sync logic
  openrisc: enable LOCKDEP_SUPPORT and irqflags tracing
  openrisc: support framepointers and STACKTRACE_SUPPORT
  openrisc: add simple_smp dts and defconfig for simulators
  openrisc: add cacheflush support to fix icache aliasing
  openrisc: sleep instead of spin on secondary wait
  openrisc: fix initial preempt state for secondary cpu tasks
  openrisc: initial SMP support
  irqchip: add initial support for ompic
  dt-bindings: add openrisc to vendor prefixes list
  openrisc: use qspinlocks and qrwlocks
  openrisc: add 1 and 2 byte cmpxchg support
  openrisc: use shadow registers to save regs on exception
  dt-bindings: openrisc: Add OpenRISC platform SoC
  Documentation: openrisc: Updates to README
  Documentation: Move OpenRISC docs out of arch/
  MAINTAINERS: Add OpenRISC pic maintainer
  openrisc: dts: or1ksim: Add stdout-path

11 files changed, 1019 insertions, 167 deletions

diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile
index c4ea6cabad46..2d172e79f58d 100644
--- a/arch/openrisc/kernel/Makefile
+++ b/arch/openrisc/kernel/Makefile
@@ -7,8 +7,10 @@ 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-$(CONFIG_SMP)		+= smp.o sync-timer.o
+obj-$(CONFIG_STACKTRACE)	+= stacktrace.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/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 */
 
diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index 1e87913576e3..fb02b2a1d6f2 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)
 
@@ -92,35 +129,67 @@
 #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 ]=== */
 
-
+#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
@@ -163,10 +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 */					;\
@@ -226,7 +292,7 @@
  *
  */
 #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 +321,35 @@
 	/* 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] === */
@@ -487,6 +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
 	 */
@@ -638,6 +710,100 @@ _flush_tlb:
 	l.jr	r9
 	 l.nop
 
+#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
+	LOAD_SYMBOL_2_GPR(r3, 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
@@ -1533,6 +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/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..7d518ee8bddc
--- /dev/null
+++ b/arch/openrisc/kernel/smp.c
@@ -0,0 +1,259 @@
+/*
+ * 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/cacheflush.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_WAKEUP,
+	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;
+	smp_cross_call(cpumask_of(cpu), IPI_WAKEUP);
+
+	/*
+	 * 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 at 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;
+	}
+	synchronise_count_master(cpu);
+
+	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
+	 */
+	complete(&cpu_running);
+
+	synchronise_count_slave(cpu);
+	set_cpu_online(cpu, true);
+
+	local_irq_enable();
+
+	preempt_disable();
+	/*
+	 * 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_WAKEUP:
+		break;
+
+	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);
+}
+
+/* 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/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/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 687c11d048d7..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;
 }
 
@@ -53,13 +64,32 @@ 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 +113,9 @@ 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 +131,12 @@ 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 +152,9 @@ 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/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 */
+