Merge tag 'xtensa-next-20140123' of git://github.com/czankel/xtensa-linux

Pull Xtensa patches from Chris Zankel:
 "The major changes are adding support for SMP for Xtensa, fixing and
  cleaning up the ISS (simulator) network driver, and better support for
  device trees"

* tag 'xtensa-next-20140123' of git://github.com/czankel/xtensa-linux: (40 commits)
  xtensa: implement ndelay
  xtensa: clean up udelay
  xtensa: enable HAVE_PERF_EVENTS
  xtensa: remap io area defined in device tree
  xtensa: support default device tree buses
  xtensa: initialize device tree clock sources
  xtensa: xtfpga: fix definitions of platform devices
  xtensa: standardize devicetree cpu compatible strings
  xtensa: avoid duplicate of IO range definitions
  xtensa: fix ATOMCTL register documentation
  xtensa: Enable irqs after cpu is set online
  xtensa: ISS: raise network polling rate to 10 times/sec
  xtensa: remove unused XTENSA_ISS_NETWORK Kconfig parameter
  xtensa: ISS: avoid simple_strtoul usage
  xtensa: Switch to sched_clock_register()
  xtensa: implement CPU hotplug
  xtensa: add SMP support
  xtensa: add MX irqchip
  xtensa: clear timer IRQ unconditionally in its handler
  xtensa: clean up do_interrupt/do_IRQ
  ...

23 files changed, 503 insertions, 152 deletions

diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 228d6aee3a16..5851db291583 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -8,7 +8,6 @@ generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
 generic-y += fcntl.h
-generic-y += futex.h
 generic-y += hardirq.h
 generic-y += ioctl.h
 generic-y += irq_regs.h
diff --git a/arch/xtensa/include/asm/barrier.h b/arch/xtensa/include/asm/barrier.h
index e1ee6b51dfc5..0a24b04d6b21 100644
--- a/arch/xtensa/include/asm/barrier.h
+++ b/arch/xtensa/include/asm/barrier.h
@@ -13,10 +13,6 @@
 #define rmb() barrier()
 #define wmb() mb()
 
-#ifdef CONFIG_SMP
-#error smp_* not defined
-#endif
-
 #include <asm-generic/barrier.h>
 
 #endif /* _XTENSA_SYSTEM_H */
diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h
index 84afe58d5d37..7b6873ae84c2 100644
--- a/arch/xtensa/include/asm/bitops.h
+++ b/arch/xtensa/include/asm/bitops.h
@@ -22,12 +22,8 @@
 #include <asm/processor.h>
 #include <asm/byteorder.h>
 
-#ifdef CONFIG_SMP
-# error SMP not supported on this architecture
-#endif
-
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
+#define smp_mb__before_clear_bit()	smp_mb()
+#define smp_mb__after_clear_bit()	smp_mb()
 
 #include <asm-generic/bitops/non-atomic.h>
 
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index 127cd48883c4..555a98a18453 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -1,18 +1,14 @@
 /*
- * include/asm-xtensa/cacheflush.h
- *
  * 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.
  *
- * (C) 2001 - 2007 Tensilica Inc.
+ * (C) 2001 - 2013 Tensilica Inc.
  */
 
 #ifndef _XTENSA_CACHEFLUSH_H
 #define _XTENSA_CACHEFLUSH_H
 
-#ifdef __KERNEL__
-
 #include <linux/mm.h>
 #include <asm/processor.h>
 #include <asm/page.h>
@@ -51,7 +47,6 @@ extern void __invalidate_icache_page(unsigned long);
 extern void __invalidate_icache_range(unsigned long, unsigned long);
 extern void __invalidate_dcache_range(unsigned long, unsigned long);
 
-
 #if XCHAL_DCACHE_IS_WRITEBACK
 extern void __flush_invalidate_dcache_all(void);
 extern void __flush_dcache_page(unsigned long);
@@ -87,9 +82,22 @@ static inline void __invalidate_icache_page_alias(unsigned long virt,
  * (see also Documentation/cachetlb.txt)
  */
 
-#if (DCACHE_WAY_SIZE > PAGE_SIZE)
+#if (DCACHE_WAY_SIZE > PAGE_SIZE) || defined(CONFIG_SMP)
+
+#ifdef CONFIG_SMP
+void flush_cache_all(void);
+void flush_cache_range(struct vm_area_struct*, ulong, ulong);
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_cache_page(struct vm_area_struct*,
+			     unsigned long, unsigned long);
+#else
+#define flush_cache_all local_flush_cache_all
+#define flush_cache_range local_flush_cache_range
+#define flush_icache_range local_flush_icache_range
+#define flush_cache_page  local_flush_cache_page
+#endif
 
-#define flush_cache_all()						\
+#define local_flush_cache_all()						\
 	do {								\
 		__flush_invalidate_dcache_all();			\
 		__invalidate_icache_all();				\
@@ -103,9 +111,11 @@ static inline void __invalidate_icache_page_alias(unsigned long virt,
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page*);
-extern void flush_cache_range(struct vm_area_struct*, ulong, ulong);
-extern void flush_cache_page(struct vm_area_struct*,
-			     unsigned long, unsigned long);
+
+void local_flush_cache_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end);
+void local_flush_cache_page(struct vm_area_struct *vma,
+		unsigned long address, unsigned long pfn);
 
 #else
 
@@ -119,13 +129,14 @@ extern void flush_cache_page(struct vm_area_struct*,
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
 #define flush_dcache_page(page)				do { } while (0)
 
-#define flush_cache_page(vma,addr,pfn)			do { } while (0)
-#define flush_cache_range(vma,start,end)		do { } while (0)
+#define flush_icache_range local_flush_icache_range
+#define flush_cache_page(vma, addr, pfn)		do { } while (0)
+#define flush_cache_range(vma, start, end)		do { } while (0)
 
 #endif
 
 /* Ensure consistency between data and instruction cache. */
-#define flush_icache_range(start,end) 					\
+#define local_flush_icache_range(start, end)				\
 	do {								\
 		__flush_dcache_range(start, (end) - (start));		\
 		__invalidate_icache_range(start,(end) - (start));	\
@@ -253,5 +264,4 @@ static inline void flush_invalidate_dcache_unaligned(u32 addr, u32 size)
 	}
 }
 
-#endif /* __KERNEL__ */
 #endif /* _XTENSA_CACHEFLUSH_H */
diff --git a/arch/xtensa/include/asm/delay.h b/arch/xtensa/include/asm/delay.h
index 3899610c1dff..24304b39a5c7 100644
--- a/arch/xtensa/include/asm/delay.h
+++ b/arch/xtensa/include/asm/delay.h
@@ -19,23 +19,57 @@ extern unsigned long loops_per_jiffy;
 
 static inline void __delay(unsigned long loops)
 {
-	/* 2 cycles per loop. */
-	__asm__ __volatile__ ("1: addi %0, %0, -2; bgeui %0, 2, 1b"
-			      : "=r" (loops) : "0" (loops));
+	if (__builtin_constant_p(loops) && loops < 2)
+		__asm__ __volatile__ ("nop");
+	else if (loops >= 2)
+		/* 2 cycles per loop. */
+		__asm__ __volatile__ ("1: addi %0, %0, -2; bgeui %0, 2, 1b"
+				: "+r" (loops));
 }
 
-/* For SMP/NUMA systems, change boot_cpu_data to something like
- * local_cpu_data->... where local_cpu_data points to the current
- * cpu. */
+/* Undefined function to get compile-time error */
+void __bad_udelay(void);
+void __bad_ndelay(void);
 
-static __inline__ void udelay (unsigned long usecs)
+#define __MAX_UDELAY 30000
+#define __MAX_NDELAY 30000
+
+static inline void __udelay(unsigned long usecs)
 {
 	unsigned long start = get_ccount();
-	unsigned long cycles = usecs * (loops_per_jiffy / (1000000UL / HZ));
+	unsigned long cycles = (usecs * (ccount_freq >> 15)) >> 5;
 
 	/* Note: all variables are unsigned (can wrap around)! */
 	while (((unsigned long)get_ccount()) - start < cycles)
-		;
+		cpu_relax();
+}
+
+static inline void udelay(unsigned long usec)
+{
+	if (__builtin_constant_p(usec) && usec >= __MAX_UDELAY)
+		__bad_udelay();
+	else
+		__udelay(usec);
+}
+
+static inline void __ndelay(unsigned long nsec)
+{
+	/*
+	 * Inner shift makes sure multiplication doesn't overflow
+	 * for legitimate nsec values
+	 */
+	unsigned long cycles = (nsec * (ccount_freq >> 15)) >> 15;
+	__delay(cycles);
+}
+
+#define ndelay(n) ndelay(n)
+
+static inline void ndelay(unsigned long nsec)
+{
+	if (__builtin_constant_p(nsec) && nsec >= __MAX_NDELAY)
+		__bad_ndelay();
+	else
+		__ndelay(nsec);
 }
 
 #endif
diff --git a/arch/xtensa/include/asm/ftrace.h b/arch/xtensa/include/asm/ftrace.h
index 73cc3f482304..736b9d214d80 100644
--- a/arch/xtensa/include/asm/ftrace.h
+++ b/arch/xtensa/include/asm/ftrace.h
@@ -18,7 +18,7 @@
 		__asm__ __volatile__ ( \
 			"mov %0, a0\n" \
 			"mov %1, a1\n" \
-			: "=r"(a0), "=r"(a1) : : ); \
+			: "=r"(a0), "=r"(a1)); \
 		MAKE_PC_FROM_RA(a0, a1); })
 #ifdef CONFIG_FRAME_POINTER
 extern unsigned long return_address(unsigned level);
diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h
new file mode 100644
index 000000000000..b39531babec0
--- /dev/null
+++ b/arch/xtensa/include/asm/futex.h
@@ -0,0 +1,147 @@
+/*
+ * Atomic futex routines
+ *
+ * Based on the PowerPC implementataion
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2013 TangoTec Ltd.
+ *
+ * Baruch Siach <baruch@tkos.co.il>
+ */
+
+#ifndef _ASM_XTENSA_FUTEX_H
+#define _ASM_XTENSA_FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <linux/errno.h>
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
+	__asm__ __volatile(				\
+	"1:	l32i	%0, %2, 0\n"			\
+		insn "\n"				\
+	"	wsr	%0, scompare1\n"		\
+	"2:	s32c1i	%1, %2, 0\n"			\
+	"	bne	%1, %0, 1b\n"			\
+	"	movi	%1, 0\n"			\
+	"3:\n"						\
+	"	.section .fixup,\"ax\"\n"		\
+	"	.align 4\n"				\
+	"4:	.long	3b\n"				\
+	"5:	l32r	%0, 4b\n"			\
+	"	movi	%1, %3\n"			\
+	"	jx	%0\n"				\
+	"	.previous\n"				\
+	"	.section __ex_table,\"a\"\n"		\
+	"	.long 1b,5b,2b,5b\n"			\
+	"	.previous\n"				\
+	: "=&r" (oldval), "=&r" (ret)			\
+	: "r" (uaddr), "I" (-EFAULT), "r" (oparg)	\
+	: "memory")
+
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret;
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+#if !XCHAL_HAVE_S32C1I
+	return -ENOSYS;
+#endif
+
+	pagefault_disable();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("mov %1, %4", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("add %1, %0, %4", ret, oldval, uaddr,
+				oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("or %1, %0, %4", ret, oldval, uaddr,
+				oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("and %1, %0, %4", ret, oldval, uaddr,
+				~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("xor %1, %0, %4", ret, oldval, uaddr,
+				oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();
+
+	if (ret)
+		return ret;
+
+	switch (cmp) {
+	case FUTEX_OP_CMP_EQ: return (oldval == cmparg);
+	case FUTEX_OP_CMP_NE: return (oldval != cmparg);
+	case FUTEX_OP_CMP_LT: return (oldval < cmparg);
+	case FUTEX_OP_CMP_GE: return (oldval >= cmparg);
+	case FUTEX_OP_CMP_LE: return (oldval <= cmparg);
+	case FUTEX_OP_CMP_GT: return (oldval > cmparg);
+	}
+
+	return -ENOSYS;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 prev;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+#if !XCHAL_HAVE_S32C1I
+	return -ENOSYS;
+#endif
+
+	__asm__ __volatile__ (
+	"	# futex_atomic_cmpxchg_inatomic\n"
+	"1:	l32i	%1, %3, 0\n"
+	"	mov	%0, %5\n"
+	"	wsr	%1, scompare1\n"
+	"2:	s32c1i	%0, %3, 0\n"
+	"3:\n"
+	"	.section .fixup,\"ax\"\n"
+	"	.align 4\n"
+	"4:	.long	3b\n"
+	"5:	l32r	%1, 4b\n"
+	"	movi	%0, %6\n"
+	"	jx	%1\n"
+	"	.previous\n"
+	"	.section __ex_table,\"a\"\n"
+	"	.long 1b,5b,2b,5b\n"
+	"	.previous\n"
+	: "+r" (ret), "=&r" (prev), "+m" (*uaddr)
+	: "r" (uaddr), "r" (oldval), "r" (newval), "I" (-EFAULT)
+	: "memory");
+
+	*uval = prev;
+	return ret;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_XTENSA_FUTEX_H */
diff --git a/arch/xtensa/include/asm/initialize_mmu.h b/arch/xtensa/include/asm/initialize_mmu.h
index 722553f17db3..600781edc8a3 100644
--- a/arch/xtensa/include/asm/initialize_mmu.h
+++ b/arch/xtensa/include/asm/initialize_mmu.h
@@ -26,6 +26,9 @@
 #include <asm/pgtable.h>
 #include <asm/vectors.h>
 
+#define CA_BYPASS	(_PAGE_CA_BYPASS | _PAGE_HW_WRITE | _PAGE_HW_EXEC)
+#define CA_WRITEBACK	(_PAGE_CA_WB     | _PAGE_HW_WRITE | _PAGE_HW_EXEC)
+
 #ifdef __ASSEMBLY__
 
 #define XTENSA_HWVERSION_RC_2009_0 230000
@@ -80,8 +83,6 @@
 	/* Step 2: map 0x40000000..0x47FFFFFF to paddr containing this code
 	 * and jump to the new mapping.
 	 */
-#define CA_BYPASS	(_PAGE_CA_BYPASS | _PAGE_HW_WRITE | _PAGE_HW_EXEC)
-#define CA_WRITEBACK	(_PAGE_CA_WB     | _PAGE_HW_WRITE | _PAGE_HW_EXEC)
 
 	srli	a3, a0, 27
 	slli	a3, a3, 27
@@ -123,13 +124,13 @@
 	wdtlb	a4, a5
 	witlb	a4, a5
 
-	movi	a5, 0xe0000006
-	movi	a4, 0xf0000000 + CA_WRITEBACK
+	movi	a5, XCHAL_KIO_CACHED_VADDR + 6
+	movi	a4, XCHAL_KIO_DEFAULT_PADDR + CA_WRITEBACK
 	wdtlb	a4, a5
 	witlb	a4, a5
 
-	movi	a5, 0xf0000006
-	movi	a4, 0xf0000000 + CA_BYPASS
+	movi	a5, XCHAL_KIO_BYPASS_VADDR + 6
+	movi	a4, XCHAL_KIO_DEFAULT_PADDR + CA_BYPASS
 	wdtlb	a4, a5
 	witlb	a4, a5
 
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 700c2e6f2d25..2a042d430c25 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -14,20 +14,26 @@
 #ifdef __KERNEL__
 #include <asm/byteorder.h>
 #include <asm/page.h>
+#include <asm/vectors.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
 
 #include <linux/types.h>
 
-#define XCHAL_KIO_CACHED_VADDR	0xe0000000
-#define XCHAL_KIO_BYPASS_VADDR	0xf0000000
-#define XCHAL_KIO_PADDR		0xf0000000
-#define XCHAL_KIO_SIZE		0x10000000
-
 #define IOADDR(x)		(XCHAL_KIO_BYPASS_VADDR + (x))
 #define IO_SPACE_LIMIT ~0
 
 #ifdef CONFIG_MMU
+
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+extern unsigned long xtensa_kio_paddr;
+
+static inline unsigned long xtensa_get_kio_paddr(void)
+{
+	return xtensa_kio_paddr;
+}
+#endif
+
 /*
  * Return the virtual address for the specified bus memory.
  * Note that we currently don't support any address outside the KIO segment.
diff --git a/arch/xtensa/include/asm/irq.h b/arch/xtensa/include/asm/irq.h
index 4c0ccc9c4f4c..f71f88ea7646 100644
--- a/arch/xtensa/include/asm/irq.h
+++ b/arch/xtensa/include/asm/irq.h
@@ -43,5 +43,14 @@ static __inline__ int irq_canonicalize(int irq)
 }
 
 struct irqaction;
+struct irq_domain;
+
+void migrate_irqs(void);
+int xtensa_irq_domain_xlate(const u32 *intspec, unsigned int intsize,
+		unsigned long int_irq, unsigned long ext_irq,
+		unsigned long *out_hwirq, unsigned int *out_type);
+int xtensa_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw);
+unsigned xtensa_map_ext_irq(unsigned ext_irq);
+unsigned xtensa_get_ext_irq_no(unsigned irq);
 
 #endif	/* _XTENSA_IRQ_H */
diff --git a/arch/xtensa/include/asm/mmu.h b/arch/xtensa/include/asm/mmu.h
index 8554b2c8b17a..71afe418d0e5 100644
--- a/arch/xtensa/include/asm/mmu.h
+++ b/arch/xtensa/include/asm/mmu.h
@@ -1,11 +1,9 @@
 /*
- * include/asm-xtensa/mmu.h
- *
  * 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.
  *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
+ * Copyright (C) 2001 - 2013 Tensilica Inc.
  */
 
 #ifndef _XTENSA_MMU_H
@@ -15,8 +13,10 @@
 #include <asm-generic/mmu.h>
 #else
 
-/* Default "unsigned long" context */
-typedef unsigned long mm_context_t;
+typedef struct {
+	unsigned long asid[NR_CPUS];
+	unsigned int cpu;
+} mm_context_t;
 
 #endif /* CONFIG_MMU */
 #endif	/* _XTENSA_MMU_H */
diff --git a/arch/xtensa/include/asm/mmu_context.h b/arch/xtensa/include/asm/mmu_context.h
index d43525a286bb..d33c71a8c9ec 100644
--- a/arch/xtensa/include/asm/mmu_context.h
+++ b/arch/xtensa/include/asm/mmu_context.h
@@ -1,13 +1,11 @@
 /*
- * include/asm-xtensa/mmu_context.h
- *
  * Switch an MMU context.
  *
  * 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.
  *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
+ * Copyright (C) 2001 - 2013 Tensilica Inc.
  */
 
 #ifndef _XTENSA_MMU_CONTEXT_H
@@ -20,22 +18,25 @@
 #include <linux/stringify.h>
 #include <linux/sched.h>
 
-#include <variant/core.h>
+#include <asm/vectors.h>
 
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm-generic/mm_hooks.h>
+#include <asm-generic/percpu.h>
 
 #if (XCHAL_HAVE_TLBS != 1)
 # error "Linux must have an MMU!"
 #endif
 
-extern unsigned long asid_cache;
+DECLARE_PER_CPU(unsigned long, asid_cache);
+#define cpu_asid_cache(cpu) per_cpu(asid_cache, cpu)
 
 /*
  * NO_CONTEXT is the invalid ASID value that we don't ever assign to
- * any user or kernel context.
+ * any user or kernel context.  We use the reserved values in the
+ * ASID_INSERT macro below.
  *
  * 0 invalid
  * 1 kernel
@@ -49,6 +50,12 @@ extern unsigned long asid_cache;
 #define ASID_MASK	((1 << XCHAL_MMU_ASID_BITS) - 1)
 #define ASID_INSERT(x)	(0x03020001 | (((x) & ASID_MASK) << 8))
 
+#ifdef CONFIG_MMU
+void init_mmu(void);
+#else
+static inline void init_mmu(void) { }
+#endif
+
 static inline void set_rasid_register (unsigned long val)
 {
 	__asm__ __volatile__ (" wsr %0, rasid\n\t"
@@ -62,64 +69,77 @@ static inline unsigned long get_rasid_register (void)
 	return tmp;
 }
 
-static inline void
-__get_new_mmu_context(struct mm_struct *mm)
+static inline void get_new_mmu_context(struct mm_struct *mm, unsigned int cpu)
 {
-	extern void flush_tlb_all(void);
-	if (! (++asid_cache & ASID_MASK) ) {
-		flush_tlb_all(); /* start new asid cycle */
-		asid_cache += ASID_USER_FIRST;
+	unsigned long asid = cpu_asid_cache(cpu);
+	if ((++asid & ASID_MASK) == 0) {
+		/*
+		 * Start new asid cycle; continue counting with next
+		 * incarnation bits; skipping over 0, 1, 2, 3.
+		 */
+		local_flush_tlb_all();
+		asid += ASID_USER_FIRST;
 	}
-	mm->context = asid_cache;
+	cpu_asid_cache(cpu) = asid;
+	mm->context.asid[cpu] = asid;
+	mm->context.cpu = cpu;
 }
 
-static inline void
-__load_mmu_context(struct mm_struct *mm)
+static inline void get_mmu_context(struct mm_struct *mm, unsigned int cpu)
 {
-	set_rasid_register(ASID_INSERT(mm->context));
+	/*
+	 * Check if our ASID is of an older version and thus invalid.
+	 */
+
+	if (mm) {
+		unsigned long asid = mm->context.asid[cpu];
+
+		if (asid == NO_CONTEXT ||
+				((asid ^ cpu_asid_cache(cpu)) & ~ASID_MASK))
+			get_new_mmu_context(mm, cpu);
+	}
+}
+
+static inline void activate_context(struct mm_struct *mm, unsigned int cpu)
+{
+	get_mmu_context(mm, cpu);
+	set_rasid_register(ASID_INSERT(mm->context.asid[cpu]));
 	invalidate_page_directory();
 }
 
 /*
  * Initialize the context related info for a new mm_struct
- * instance.
+ * instance.  Valid cpu values are 0..(NR_CPUS-1), so initializing
+ * to -1 says the process has never run on any core.
  */
 
-static inline int
-init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+static inline int init_new_context(struct task_struct *tsk,
+		struct mm_struct *mm)
 {
-	mm->context = NO_CONTEXT;
+	int cpu;
+	for_each_possible_cpu(cpu) {
+		mm->context.asid[cpu] = NO_CONTEXT;
+	}
+	mm->context.cpu = -1;
 	return 0;
 }
 
-/*
- * After we have set current->mm to a new value, this activates
- * the context for the new mm so we see the new mappings.
- */
-static inline void
-activate_mm(struct mm_struct *prev, struct mm_struct *next)
-{
-	/* Unconditionally get a new ASID.  */
-
-	__get_new_mmu_context(next);
-	__load_mmu_context(next);
-}
-
-
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			     struct task_struct *tsk)
 {
-	unsigned long asid = asid_cache;
-
-	/* Check if our ASID is of an older version and thus invalid */
-
-	if (next->context == NO_CONTEXT || ((next->context^asid) & ~ASID_MASK))
-		__get_new_mmu_context(next);
-
-	__load_mmu_context(next);
+	unsigned int cpu = smp_processor_id();
+	int migrated = next->context.cpu != cpu;
+	/* Flush the icache if we migrated to a new core. */
+	if (migrated) {
+		__invalidate_icache_all();
+		next->context.cpu = cpu;
+	}
+	if (migrated || prev != next)
+		activate_context(next, cpu);
 }
 
-#define deactivate_mm(tsk, mm)	do { } while(0)
+#define activate_mm(prev, next)	switch_mm((prev), (next), NULL)
+#define deactivate_mm(tsk, mm)	do { } while (0)
 
 /*
  * Destroy context related info for an mm_struct that is about
diff --git a/arch/xtensa/include/asm/mxregs.h b/arch/xtensa/include/asm/mxregs.h
new file mode 100644
index 000000000000..73dcc5456f68
--- /dev/null
+++ b/arch/xtensa/include/asm/mxregs.h
@@ -0,0 +1,46 @@
+/*
+ * Xtensa MX interrupt distributor
+ *
+ * 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.
+ *
+ * Copyright (C) 2008 - 2013 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_MXREGS_H
+#define _XTENSA_MXREGS_H
+
+/*
+ * RER/WER at, as	Read/write external register
+ *	at: value
+ *	as: address
+ *
+ * Address	Value
+ * 00nn		0...0p..p	Interrupt Routing, route IRQ n to processor p
+ * 01pp		0...0d..d	16 bits (d) 'ored' as single IPI to processor p
+ * 0180		0...0m..m	Clear enable specified by mask (m)
+ * 0184		0...0m..m	Set enable specified by mask (m)
+ * 0190		0...0x..x	8-bit IPI partition register
+ *				VVVVVVVVPPPPUUUUUUUUUUUUUUUUU
+ *				V (10-bit) Release/Version
+ *				P ( 4-bit) Number of cores - 1
+ *				U (18-bit) ID
+ * 01a0		i.......i	32-bit ConfigID
+ * 0200		0...0m..m	RunStall core 'n'
+ * 0220		c		Cache coherency enabled
+ */
+
+#define MIROUT(irq)	(0x000 + (irq))
+#define MIPICAUSE(cpu)	(0x100 + (cpu))
+#define MIPISET(cause)	(0x140 + (cause))
+#define MIENG		0x180
+#define MIENGSET	0x184
+#define MIASG		0x188	/* Read Global Assert Register */
+#define MIASGSET	0x18c	/* Set Global Addert Regiter */
+#define MIPIPART	0x190
+#define SYSCFGID	0x1a0
+#define MPSCORE		0x200
+#define CCON		0x220
+
+#endif /* _XTENSA_MXREGS_H */
diff --git a/arch/xtensa/include/asm/perf_event.h b/arch/xtensa/include/asm/perf_event.h
new file mode 100644
index 000000000000..5aa4590acaae
--- /dev/null
+++ b/arch/xtensa/include/asm/perf_event.h
@@ -0,0 +1,4 @@
+#ifndef __ASM_XTENSA_PERF_EVENT_H
+#define __ASM_XTENSA_PERF_EVENT_H
+
+#endif /* __ASM_XTENSA_PERF_EVENT_H */
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 7e409a5b0ec5..abb59708a3b7 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -191,5 +191,25 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define set_sr(x,sr) ({unsigned int v=(unsigned int)x; WSR(v,sr);})
 #define get_sr(sr) ({unsigned int v; RSR(v,sr); v; })
 
+#ifndef XCHAL_HAVE_EXTERN_REGS
+#define XCHAL_HAVE_EXTERN_REGS 0
+#endif
+
+#if XCHAL_HAVE_EXTERN_REGS
+
+static inline void set_er(unsigned long value, unsigned long addr)
+{
+	asm volatile ("wer %0, %1" : : "a" (value), "a" (addr) : "memory");
+}
+
+static inline unsigned long get_er(unsigned long addr)
+{
+	register unsigned long value;
+	asm volatile ("rer %0, %1" : "=a" (value) : "a" (addr) : "memory");
+	return value;
+}
+
+#endif /* XCHAL_HAVE_EXTERN_REGS */
+
 #endif	/* __ASSEMBLY__ */
 #endif	/* _XTENSA_PROCESSOR_H */
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index 81f31bc9dde0..598e752dcbcd 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -59,9 +59,17 @@ struct pt_regs {
 	(task_stack_page(tsk) + KERNEL_STACK_SIZE - (XCHAL_NUM_AREGS-16)*4) - 1)
 # define user_mode(regs) (((regs)->ps & 0x00000020)!=0)
 # define instruction_pointer(regs) ((regs)->pc)
+# define return_pointer(regs) (MAKE_PC_FROM_RA((regs)->areg[0], \
+					       (regs)->areg[1]))
 
 # ifndef CONFIG_SMP
 #  define profile_pc(regs) instruction_pointer(regs)
+# else
+#  define profile_pc(regs)						\
+	({								\
+		in_lock_functions(instruction_pointer(regs)) ?		\
+		return_pointer(regs) : instruction_pointer(regs);	\
+	})
 # endif
 
 #define user_stack_pointer(regs) ((regs)->areg[1])
diff --git a/arch/xtensa/include/asm/smp.h b/arch/xtensa/include/asm/smp.h
index 83c569e3bdbd..4e43f5643891 100644
--- a/arch/xtensa/include/asm/smp.h
+++ b/arch/xtensa/include/asm/smp.h
@@ -1,27 +1,43 @@
 /*
- * include/asm-xtensa/smp.h
- *
  * 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.
  *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
+ * Copyright (C) 2001 - 2013 Tensilica Inc.
  */
 
 #ifndef _XTENSA_SMP_H
 #define _XTENSA_SMP_H
 
-extern struct xtensa_cpuinfo boot_cpu_data;
+#ifdef CONFIG_SMP
 
-#define cpu_data (&boot_cpu_data)
-#define current_cpu_data boot_cpu_data
+#define raw_smp_processor_id()	(current_thread_info()->cpu)
+#define cpu_logical_map(cpu)	(cpu)
 
-struct xtensa_cpuinfo {
-	unsigned long	*pgd_cache;
-	unsigned long	*pte_cache;
-	unsigned long	pgtable_cache_sz;
+struct start_info {
+	unsigned long stack;
 };
+extern struct start_info start_info;
 
-#define cpu_logical_map(cpu)	(cpu)
+struct cpumask;
+void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+void arch_send_call_function_single_ipi(int cpu);
+
+void smp_init_cpus(void);
+void secondary_init_irq(void);
+void ipi_init(void);
+struct seq_file;
+void show_ipi_list(struct seq_file *p, int prec);
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+void __cpu_die(unsigned int cpu);
+int __cpu_disable(void);
+void cpu_die(void);
+void cpu_restart(void);
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+#endif /* CONFIG_SMP */
 
 #endif	/* _XTENSA_SMP_H */
diff --git a/arch/xtensa/include/asm/spinlock.h b/arch/xtensa/include/asm/spinlock.h
index 03975906b36f..1d95fa5dcd10 100644
--- a/arch/xtensa/include/asm/spinlock.h
+++ b/arch/xtensa/include/asm/spinlock.h
@@ -28,13 +28,13 @@
  *    1         somebody owns the spinlock
  */
 
-#define __raw_spin_is_locked(x) ((x)->slock != 0)
-#define __raw_spin_unlock_wait(lock) \
-	do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0)
+#define arch_spin_is_locked(x) ((x)->slock != 0)
+#define arch_spin_unlock_wait(lock) \
+	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
 
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
-static inline void __raw_spin_lock(raw_spinlock_t *lock)
+static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 
@@ -51,7 +51,7 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock)
 
 /* Returns 1 if the lock is obtained, 0 otherwise. */
 
-static inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 
@@ -67,7 +67,7 @@ static inline int __raw_spin_trylock(raw_spinlock_t *lock)
 	return tmp == 0 ? 1 : 0;
 }
 
-static inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 
@@ -96,9 +96,9 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
  *  0x80000000  one writer owns the rwlock, no other writers, no readers
  */
 
-#define __raw_write_can_lock(x)  ((x)->lock == 0)
+#define arch_write_can_lock(x)  ((x)->lock == 0)
 
-static inline void __raw_write_lock(raw_rwlock_t *rw)
+static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
@@ -116,7 +116,7 @@ static inline void __raw_write_lock(raw_rwlock_t *rw)
 
 /* Returns 1 if the lock is obtained, 0 otherwise. */
 
-static inline int __raw_write_trylock(raw_rwlock_t *rw)
+static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
@@ -133,7 +133,7 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
 	return tmp == 0 ? 1 : 0;
 }
 
-static inline void __raw_write_unlock(raw_rwlock_t *rw)
+static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
@@ -145,7 +145,7 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 			: "memory");
 }
 
-static inline void __raw_read_lock(raw_rwlock_t *rw)
+static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 	unsigned long result;
@@ -164,7 +164,7 @@ static inline void __raw_read_lock(raw_rwlock_t *rw)
 
 /* Returns 1 if the lock is obtained, 0 otherwise. */
 
-static inline int __raw_read_trylock(raw_rwlock_t *rw)
+static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	unsigned long result;
 	unsigned long tmp;
@@ -184,7 +184,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw)
 	return result == 0;
 }
 
-static inline void __raw_read_unlock(raw_rwlock_t *rw)
+static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	unsigned long tmp1, tmp2;
 
@@ -199,4 +199,7 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
 			: "memory");
 }
 
+#define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
+
 #endif	/* _XTENSA_SPINLOCK_H */
diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..7ec5ce10c9e9
--- /dev/null
+++ b/arch/xtensa/include/asm/spinlock_types.h
@@ -0,0 +1,20 @@
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct {
+	volatile unsigned int slock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+
+typedef struct {
+	volatile unsigned int lock;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
+
+#endif
diff --git a/arch/xtensa/include/asm/timex.h b/arch/xtensa/include/asm/timex.h
index 27fa3c170662..ca929e6a38b5 100644
--- a/arch/xtensa/include/asm/timex.h
+++ b/arch/xtensa/include/asm/timex.h
@@ -1,18 +1,14 @@
 /*
- * include/asm-xtensa/timex.h
- *
  * 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.
  *
- * Copyright (C) 2001 - 2008 Tensilica Inc.
+ * Copyright (C) 2001 - 2013 Tensilica Inc.
  */
 
 #ifndef _XTENSA_TIMEX_H
 #define _XTENSA_TIMEX_H
 
-#ifdef __KERNEL__
-
 #include <asm/processor.h>
 #include <linux/stringify.h>
 
@@ -39,14 +35,9 @@ extern unsigned long ccount_freq;
 
 typedef unsigned long long cycles_t;
 
-/*
- * Only used for SMP.
- */
-
-extern cycles_t cacheflush_time;
-
 #define get_cycles()	(0)
 
+void local_timer_setup(unsigned cpu);
 
 /*
  * Register access.
@@ -81,5 +72,4 @@ static inline void set_linux_timer (unsigned long ccompare)
 	WSR_CCOMPARE(LINUX_TIMER, ccompare);
 }
 
-#endif	/* __KERNEL__ */
 #endif	/* _XTENSA_TIMEX_H */
diff --git a/arch/xtensa/include/asm/tlbflush.h b/arch/xtensa/include/asm/tlbflush.h
index 43dd348a5a47..fc34274ce41b 100644
--- a/arch/xtensa/include/asm/tlbflush.h
+++ b/arch/xtensa/include/asm/tlbflush.h
@@ -1,18 +1,14 @@
 /*
- * include/asm-xtensa/tlbflush.h
- *
  * 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.
  *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
+ * Copyright (C) 2001 - 2013 Tensilica Inc.
  */
 
 #ifndef _XTENSA_TLBFLUSH_H
 #define _XTENSA_TLBFLUSH_H
 
-#ifdef __KERNEL__
-
 #include <linux/stringify.h>
 #include <asm/processor.h>
 
@@ -34,12 +30,37 @@
  *  - flush_tlb_range(mm, start, end) flushes a range of pages
  */
 
-extern void flush_tlb_all(void);
-extern void flush_tlb_mm(struct mm_struct*);
-extern void flush_tlb_page(struct vm_area_struct*,unsigned long);
-extern void flush_tlb_range(struct vm_area_struct*,unsigned long,unsigned long);
+void local_flush_tlb_all(void);
+void local_flush_tlb_mm(struct mm_struct *mm);
+void local_flush_tlb_page(struct vm_area_struct *vma,
+		unsigned long page);
+void local_flush_tlb_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end);
+
+#ifdef CONFIG_SMP
+
+void flush_tlb_all(void);
+void flush_tlb_mm(struct mm_struct *);
+void flush_tlb_page(struct vm_area_struct *, unsigned long);
+void flush_tlb_range(struct vm_area_struct *, unsigned long,
+		unsigned long);
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+		unsigned long end)
+{
+	flush_tlb_all();
+}
+
+#else /* !CONFIG_SMP */
+
+#define flush_tlb_all()			   local_flush_tlb_all()
+#define flush_tlb_mm(mm)		   local_flush_tlb_mm(mm)
+#define flush_tlb_page(vma, page)	   local_flush_tlb_page(vma, page)
+#define flush_tlb_range(vma, vmaddr, end)  local_flush_tlb_range(vma, vmaddr, \
+								 end)
+#define flush_tlb_kernel_range(start, end) local_flush_tlb_all()
 
-#define flush_tlb_kernel_range(start,end) flush_tlb_all()
+#endif /* CONFIG_SMP */
 
 /* TLB operations. */
 
@@ -187,5 +208,4 @@ static inline unsigned long read_itlb_translation (int way)
 }
 
 #endif	/* __ASSEMBLY__ */
-#endif	/* __KERNEL__ */
 #endif	/* _XTENSA_TLBFLUSH_H */
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 917488a0ab00..8c194f6af45e 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -19,6 +19,7 @@
  */
 extern void * __init trap_set_handler(int cause, void *handler);
 extern void do_unhandled(struct pt_regs *regs, unsigned long exccause);
+void secondary_trap_init(void);
 
 static inline void spill_registers(void)
 {
diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h
index c52b656d0310..5791b45d5a5d 100644
--- a/arch/xtensa/include/asm/vectors.h
+++ b/arch/xtensa/include/asm/vectors.h
@@ -20,6 +20,17 @@
 
 #include <variant/core.h>
 
+#define XCHAL_KIO_CACHED_VADDR		0xe0000000
+#define XCHAL_KIO_BYPASS_VADDR		0xf0000000
+#define XCHAL_KIO_DEFAULT_PADDR		0xf0000000
+#define XCHAL_KIO_SIZE			0x10000000
+
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#define XCHAL_KIO_PADDR			xtensa_get_kio_paddr()
+#else
+#define XCHAL_KIO_PADDR			XCHAL_KIO_DEFAULT_PADDR
+#endif
+
 #if defined(CONFIG_MMU)
 
 /* Will Become VECBASE */
@@ -30,11 +41,9 @@
 
 #if defined(XCHAL_HAVE_PTP_MMU) && XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY
   /* MMU v3  - XCHAL_HAVE_PTP_MMU  == 1 */
-  #define PHYSICAL_MEMORY_ADDRESS	0x00000000
   #define LOAD_MEMORY_ADDRESS		0x00003000
 #else
   /* MMU V2 -  XCHAL_HAVE_PTP_MMU  == 0 */
-  #define PHYSICAL_MEMORY_ADDRESS	0xD0000000
   #define LOAD_MEMORY_ADDRESS		0xD0003000
 #endif
 
@@ -46,7 +55,6 @@
 
   /* Location of the start of the kernel text, _start */
   #define KERNELOFFSET			0x00003000
-  #define PHYSICAL_MEMORY_ADDRESS	0x00000000
 
   /* Loaded just above possibly live vectors */
   #define LOAD_MEMORY_ADDRESS		0x00003000
@@ -54,7 +62,6 @@
 #endif /* CONFIG_MMU */
 
 #define XC_VADDR(offset)		(VIRTUAL_MEMORY_ADDRESS  + offset)
-#define XC_PADDR(offset)		(PHYSICAL_MEMORY_ADDRESS + offset)
 
 /* Used to set VECBASE register */
 #define VECBASE_RESET_VADDR		VIRTUAL_MEMORY_ADDRESS
@@ -67,7 +74,7 @@
 						VECBASE_RESET_VADDR)
 #define RESET_VECTOR1_VADDR		XC_VADDR(RESET_VECTOR1_VECOFS)
 
-#if XCHAL_HAVE_VECBASE
+#if defined(XCHAL_HAVE_VECBASE) && XCHAL_HAVE_VECBASE
 
 #define USER_VECTOR_VADDR		XC_VADDR(XCHAL_USER_VECOFS)
 #define KERNEL_VECTOR_VADDR		XC_VADDR(XCHAL_KERNEL_VECOFS)
@@ -81,11 +88,9 @@
 
 #define DEBUG_VECTOR_VADDR		XC_VADDR(XCHAL_DEBUG_VECOFS)
 
-#undef  XCHAL_NMI_VECTOR_VADDR
-#define XCHAL_NMI_VECTOR_VADDR		XC_VADDR(XCHAL_NMI_VECOFS)
+#define NMI_VECTOR_VADDR		XC_VADDR(XCHAL_NMI_VECOFS)
 
-#undef  XCHAL_INTLEVEL7_VECTOR_VADDR
-#define XCHAL_INTLEVEL7_VECTOR_VADDR	XC_VADDR(XCHAL_INTLEVEL7_VECOFS)
+#define INTLEVEL7_VECTOR_VADDR		XC_VADDR(XCHAL_INTLEVEL7_VECOFS)
 
 /*
  * These XCHAL_* #defines from varian/core.h