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
  ...

53 files changed, 2145 insertions, 637 deletions

diff --git a/Documentation/xtensa/atomctl.txt b/Documentation/xtensa/atomctl.txt
index 10a8d1f..1da783a 100644
--- a/Documentation/xtensa/atomctl.txt
+++ b/Documentation/xtensa/atomctl.txt
@@ -40,5 +40,5 @@ See Section 4.3.12.4 of ISA; Bits:
 ---------    ---------------         -----------------     ----------------
     0        Exception               Exception               Exception
     1        RCW Transaction         RCW Transaction         RCW Transaction
-    2        Internal Operation      Exception               Reserved
+    2        Internal Operation      Internal Operation      Reserved
     3        Reserved                Reserved                Reserved
diff --git a/Documentation/xtensa/mmu.txt b/Documentation/xtensa/mmu.txt
index 2b1af76..0312fe6 100644
--- a/Documentation/xtensa/mmu.txt
+++ b/Documentation/xtensa/mmu.txt
@@ -44,3 +44,21 @@ After step 4, we jump to intended (linked) address of this code.
  40..5F -> 40         40..5F -> pc  -> pc  40..5F -> pc
  20..3F -> 20  -> 20  20..3F -> 20
  00..1F -> 00  -> 00  00..1F -> 00
+
+The default location of IO peripherals is above 0xf0000000. This may change
+using a "ranges" property in a device tree simple-bus node. See ePAPR 1.1, §6.5
+for details on the syntax and semantic of simple-bus nodes. The following
+limitations apply:
+
+1. Only top level simple-bus nodes are considered
+
+2. Only one (first) simple-bus node is considered
+
+3. Empty "ranges" properties are not supported
+
+4. Only the first triplet in the "ranges" property is considered
+
+5. The parent-bus-address value is rounded down to the nearest 256MB boundary
+
+6. The IO area covers the entire 256MB segment of parent-bus-address; the
+   "ranges" triplet length field is ignored
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index f8df0cc..ba56e11 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -9,7 +9,6 @@ config XTENSA
 	select GENERIC_CLOCKEVENTS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_SHOW
-	select GENERIC_CPU_DEVICES
 	select GENERIC_SCHED_CLOCK
 	select MODULES_USE_ELF_RELA
 	select GENERIC_PCI_IOMAP
@@ -19,6 +18,8 @@ config XTENSA
 	select IRQ_DOMAIN
 	select HAVE_OPROFILE
 	select HAVE_FUNCTION_TRACER
+	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_PERF_EVENTS
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
 	  primarily for embedded systems.  These processors are both
@@ -67,6 +68,9 @@ config VARIANT_IRQ_SWITCH
 config HAVE_XTENSA_GPIO32
 	def_bool n
 
+config MAY_HAVE_SMP
+	def_bool n
+
 menu "Processor type and features"
 
 choice
@@ -110,6 +114,48 @@ config XTENSA_UNALIGNED_USER
 
 source "kernel/Kconfig.preempt"
 
+config HAVE_SMP
+	bool "System Supports SMP (MX)"
+	depends on MAY_HAVE_SMP
+	select XTENSA_MX
+	help
+	  This option is use to indicate that the system-on-a-chip (SOC)
+	  supports Multiprocessing. Multiprocessor support implemented above
+	  the CPU core definition and currently needs to be selected manually.
+
+	  Multiprocessor support in implemented with external cache and
+	  interrupt controlers.
+
+	  The MX interrupt distributer adds Interprocessor Interrupts
+	  and causes the IRQ numbers to be increased by 4 for devices
+	  like the open cores ethernet driver and the serial interface.
+
+	  You still have to select "Enable SMP" to enable SMP on this SOC.
+
+config SMP
+	bool "Enable Symmetric multi-processing support"
+	depends on HAVE_SMP
+	select USE_GENERIC_SMP_HELPERS
+	select GENERIC_SMP_IDLE_THREAD
+	help
+	  Enabled SMP Software; allows more than one CPU/CORE
+	  to be activated during startup.
+
+config NR_CPUS
+	depends on SMP
+	int "Maximum number of CPUs (2-32)"
+	range 2 32
+	default "4"
+
+config HOTPLUG_CPU
+	bool "Enable CPU hotplug support"
+	depends on SMP
+	help
+	  Say Y here to allow turning CPUs off and on. CPUs can be
+	  controlled through /sys/devices/system/cpu.
+
+	  Say N if you want to disable CPU hotplug.
+
 config MATH_EMULATION
 	bool "Math emulation"
 	help
@@ -156,9 +202,6 @@ config XTENSA_CALIBRATE_CCOUNT
 config SERIAL_CONSOLE
 	def_bool n
 
-config XTENSA_ISS_NETWORK
-	def_bool n
-
 menu "Bus options"
 
 config PCI
@@ -185,7 +228,6 @@ config XTENSA_PLATFORM_ISS
 	depends on TTY
 	select XTENSA_CALIBRATE_CCOUNT
 	select SERIAL_CONSOLE
-	select XTENSA_ISS_NETWORK
 	help
 	  ISS is an acronym for Tensilica's Instruction Set Simulator.
 
diff --git a/arch/xtensa/boot/dts/lx60.dts b/arch/xtensa/boot/dts/lx60.dts
index 2eab365..a0f8b8a 100644
--- a/arch/xtensa/boot/dts/lx60.dts
+++ b/arch/xtensa/boot/dts/lx60.dts
@@ -3,7 +3,7 @@
 /include/ "xtfpga-flash-4m.dtsi"
 
 / {
-	compatible = "xtensa,lx60";
+	compatible = "cdns,xtensa-lx60";
 	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x04000000>;
diff --git a/arch/xtensa/boot/dts/ml605.dts b/arch/xtensa/boot/dts/ml605.dts
index 6ed51d6..905c3a5 100644
--- a/arch/xtensa/boot/dts/ml605.dts
+++ b/arch/xtensa/boot/dts/ml605.dts
@@ -3,7 +3,7 @@
 /include/ "xtfpga-flash-16m.dtsi"
 
 / {
-	compatible = "xtensa,ml605";
+	compatible = "cdns,xtensa-ml605";
 	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;
diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi
index 7eda6ec..46b4f5e 100644
--- a/arch/xtensa/boot/dts/xtfpga.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga.dtsi
@@ -1,5 +1,5 @@
 / {
-	compatible = "xtensa,xtfpga";
+	compatible = "cdns,xtensa-xtfpga";
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&pic>;
@@ -17,7 +17,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		cpu@0 {
-			compatible = "xtensa,cpu";
+			compatible = "cdns,xtensa-cpu";
 			reg = <0>;
 			/* Filled in by platform_setup from FPGA register
 			 * clock-frequency = <100000000>;
@@ -26,7 +26,7 @@
 	};
 
 	pic: pic {
-		compatible = "xtensa,pic";
+		compatible = "cdns,xtensa-pic";
 		/* one cell: internal irq number,
 		 * two cells: second cell == 0: internal irq number
 		 *            second cell == 1: external irq number
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 228d6ae..5851db2 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 e1ee6b5..0a24b04 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 84afe58d..7b6873a 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 127cd48..555a98a 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 3899610c..24304b3 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 73cc3f4..736b9d2 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 0000000..b39531b
--- /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 722553f..600781e 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 700c2e6..2a042d4 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 4c0ccc9..f71f88e 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 8554b2c..71afe41 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 d43525a..d33c71a 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 0000000..73dcc54
--- /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 0000000..5aa4590
--- /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 7e409a5..abb5970 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 81f31bc..598e752 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 83c569e..4e43f56 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 0397590..1d95fa5 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 0000000..7ec5ce1
--- /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 27fa3c1..ca929e6 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 43dd348..fc34274 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 917488a..8c194f6 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 c52b656..5791b45 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
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index f90265e..18d962a 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_KGDB) += xtensa-stub.o
 obj-$(CONFIG_PCI) += pci.o
 obj-$(CONFIG_MODULES) += xtensa_ksyms.o module.o
 obj-$(CONFIG_FUNCTION_TRACER) += mcount.o
+obj-$(CONFIG_SMP) += smp.o mxhead.o
 
 AFLAGS_head.o += -mtext-section-literals
 
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index 7d740eb..aeeb3cc 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -19,6 +19,7 @@
 #include <asm/page.h>
 #include <asm/cacheasm.h>
 #include <asm/initialize_mmu.h>
+#include <asm/mxregs.h>
 
 #include <linux/init.h>
 #include <linux/linkage.h>
@@ -54,7 +55,7 @@ ENTRY(_start)
 
 	/* Preserve the pointer to the boot parameter list in EXCSAVE_1 */
 	wsr     a2, excsave1
-	_j	_SetupMMU
+	_j	_SetupOCD
 
 	.align	4
 	.literal_position
@@ -62,6 +63,23 @@ ENTRY(_start)
 	.word	_startup
 
 	.align	4
+_SetupOCD:
+	/*
+	 * Initialize WB, WS, and clear PS.EXCM (to allow loop instructions).
+	 * Set Interrupt Level just below XCHAL_DEBUGLEVEL to allow
+	 * xt-gdb to single step via DEBUG exceptions received directly
+	 * by ocd.
+	 */
+	movi	a1, 1
+	movi	a0, 0
+	wsr	a1, windowstart
+	wsr	a0, windowbase
+	rsync
+
+	movi	a1, LOCKLEVEL
+	wsr	a1, ps
+	rsync
+
 	.global _SetupMMU
 _SetupMMU:
 	Offset = _SetupMMU - _start
@@ -85,24 +103,11 @@ _SetupMMU:
 
 ENDPROC(_start)
 
-	__INIT
+	__REF
 	.literal_position
 
 ENTRY(_startup)
 
-	/* Disable interrupts and exceptions. */
-
-	movi	a0, LOCKLEVEL
-	wsr	a0, ps
-
-	/* Start with a fresh windowbase and windowstart.  */
-
-	movi	a1, 1
-	movi	a0, 0
-	wsr	a1, windowstart
-	wsr	a0, windowbase
-	rsync
-
 	/* Set a0 to 0 for the remaining initialization. */
 
 	movi	a0, 0
@@ -154,17 +159,6 @@ ENTRY(_startup)
 	wsr	a0, cpenable
 #endif
 
-	/* Set PS.INTLEVEL=LOCKLEVEL, PS.WOE=0, kernel stack, PS.EXCM=0
-	 *
-	 * Note: PS.EXCM must be cleared before using any loop
-	 *	 instructions; otherwise, they are silently disabled, and
-	 * 	 at most one iteration of the loop is executed.
-	 */
-
-	movi	a1, LOCKLEVEL
-	wsr	a1, ps
-	rsync
-
 	/*  Initialize the caches.
 	 *  a2, a3 are just working registers (clobbered).
 	 */
@@ -182,6 +176,37 @@ ENTRY(_startup)
 
 	isync
 
+#ifdef CONFIG_HAVE_SMP
+	movi	a2, CCON	# MX External Register to Configure Cache
+	movi	a3, 1
+	wer	a3, a2
+#endif
+
+	/* Setup stack and enable window exceptions (keep irqs disabled) */
+
+	movi	a1, start_info
+	l32i	a1, a1, 0
+
+	movi	a2, (1 << PS_WOE_BIT) | LOCKLEVEL
+					# WOE=1, INTLEVEL=LOCKLEVEL, UM=0
+	wsr	a2, ps			# (enable reg-windows; progmode stack)
+	rsync
+
+	/* Set up EXCSAVE[DEBUGLEVEL] to point to the Debug Exception Handler.*/
+
+	movi	a2, debug_exception
+	wsr	a2, SREG_EXCSAVE + XCHAL_DEBUGLEVEL
+
+#ifdef CONFIG_SMP
+	/*
+	 * Notice that we assume with SMP that cores have PRID
+	 * supported by the cores.
+	 */
+	rsr	a2, prid
+	bnez	a2, .Lboot_secondary
+
+#endif  /* CONFIG_SMP */
+
 	/* Unpack data sections
 	 *
 	 * The linker script used to build the Linux kernel image
@@ -234,24 +259,7 @@ ENTRY(_startup)
 	___invalidate_icache_all a2 a3
 	isync
 
-	/* Setup stack and enable window exceptions (keep irqs disabled) */
-
-	movi	a1, init_thread_union
-	addi	a1, a1, KERNEL_STACK_SIZE
-
-	movi	a2, (1 << PS_WOE_BIT) | LOCKLEVEL
-					# WOE=1, INTLEVEL=LOCKLEVEL, UM=0
-	wsr	a2, ps			# (enable reg-windows; progmode stack)
-	rsync
-
-	/* Set up EXCSAVE[DEBUGLEVEL] to point to the Debug Exception Handler.*/
-
-	movi	a2, debug_exception
-	wsr	a2, SREG_EXCSAVE + XCHAL_DEBUGLEVEL
-
-	/* Set up EXCSAVE[1] to point to the exc_table. */
-
-	movi	a6, exc_table
+	movi	a6, 0
 	xsr	a6, excsave1
 
 	/* init_arch kick-starts the linux kernel */
@@ -265,8 +273,93 @@ ENTRY(_startup)
 should_never_return:
 	j	should_never_return
 
+#ifdef CONFIG_SMP
+.Lboot_secondary:
+
+	movi	a2, cpu_start_ccount
+1:
+	l32i	a3, a2, 0
+	beqi	a3, 0, 1b
+	movi	a3, 0
+	s32i	a3, a2, 0
+	memw
+1:
+	l32i	a3, a2, 0
+	beqi	a3, 0, 1b
+	wsr	a3, ccount
+	movi	a3, 0
+	s32i	a3, a2, 0
+	memw
+
+	movi	a6, 0
+	wsr	a6, excsave1
+
+	movi	a4, secondary_start_kernel
+	callx4	a4
+	j	should_never_return
+
+#endif  /* CONFIG_SMP */
+
 ENDPROC(_startup)
 
+#ifdef CONFIG_HOTPLUG_CPU
+
+ENTRY(cpu_restart)
+
+#if XCHAL_DCACHE_IS_WRITEBACK
+	___flush_invalidate_dcache_all a2 a3
+#else
+	___invalidate_dcache_all a2 a3
+#endif
+	memw
+	movi	a2, CCON	# MX External Register to Configure Cache
+	movi	a3, 0
+	wer	a3, a2
+	extw
+
+	rsr	a0, prid
+	neg	a2, a0
+	movi	a3, cpu_start_id
+	s32i	a2, a3, 0
+#if XCHAL_DCACHE_IS_WRITEBACK
+	dhwbi	a3, 0
+#endif
+1:
+	l32i	a2, a3, 0
+	dhi	a3, 0
+	bne	a2, a0, 1b
+
+	/*
+	 * Initialize WB, WS, and clear PS.EXCM (to allow loop instructions).
+	 * Set Interrupt Level just below XCHAL_DEBUGLEVEL to allow
+	 * xt-gdb to single step via DEBUG exceptions received directly
+	 * by ocd.
+	 */
+	movi	a1, 1
+	movi	a0, 0
+	wsr	a1, windowstart
+	wsr	a0, windowbase
+	rsync
+
+	movi	a1, LOCKLEVEL
+	wsr	a1, ps
+	rsync
+
+	j	_startup
+
+ENDPROC(cpu_restart)
+
+#endif  /* CONFIG_HOTPLUG_CPU */
+
+/*
+ * DATA section
+ */
+
+        .section ".data.init.refok"
+        .align  4
+ENTRY(start_info)
+        .long   init_thread_union + KERNEL_STACK_SIZE
+
 /*
  * BSS section
  */
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 6f4f974..482868a 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -4,7 +4,7 @@
  * Xtensa built-in interrupt controller and some generic functions copied
  * from i386.
  *
- * Copyright (C) 2002 - 2006 Tensilica, Inc.
+ * Copyright (C) 2002 - 2013 Tensilica, Inc.
  * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
  *
  *
@@ -18,36 +18,27 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kernel_stat.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/xtensa-mx.h>
+#include <linux/irqchip/xtensa-pic.h>
 #include <linux/irqdomain.h>
 #include <linux/of.h>
 
+#include <asm/mxregs.h>
 #include <asm/uaccess.h>
 #include <asm/platform.h>
 
-static unsigned int cached_irq_mask;
-
 atomic_t irq_err_count;
 
-static struct irq_domain *root_domain;
-
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
-
 asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	int irq = irq_find_mapping(root_domain, hwirq);
+	int irq = irq_find_mapping(NULL, hwirq);
 
 	if (hwirq >= NR_IRQS) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
 				__func__, hwirq);
 	}
 
-	irq_enter();
-
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 	/* Debugging check for stack overflow: is there less than 1KB free? */
 	{
@@ -62,95 +53,69 @@ asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
 	}
 #endif
 	generic_handle_irq(irq);
-
-	irq_exit();
-	set_irq_regs(old_regs);
 }
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
+#ifdef CONFIG_SMP
+	show_ipi_list(p, prec);
+#endif
 	seq_printf(p, "%*s: ", prec, "ERR");
 	seq_printf(p, "%10u\n", atomic_read(&irq_err_count));
 	return 0;
 }
 
-static void xtensa_irq_mask(struct irq_data *d)
-{
-	cached_irq_mask &= ~(1 << d->hwirq);
-	set_sr (cached_irq_mask, intenable);
-}
-
-static void xtensa_irq_unmask(struct irq_data *d)
-{
-	cached_irq_mask |= 1 << d->hwirq;
-	set_sr (cached_irq_mask, intenable);
-}
-
-static void xtensa_irq_enable(struct irq_data *d)
-{
-	variant_irq_enable(d->hwirq);
-	xtensa_irq_unmask(d);
-}
-
-static void xtensa_irq_disable(struct irq_data *d)
-{
-	xtensa_irq_mask(d);
-	variant_irq_disable(d->hwirq);
-}
-
-static void xtensa_irq_ack(struct irq_data *d)
-{
-	set_sr(1 << d->hwirq, intclear);
-}
-
-static int xtensa_irq_retrigger(struct irq_data *d)
+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)
 {
-	set_sr(1 << d->hwirq, intset);
-	return 1;
+	if (WARN_ON(intsize < 1 || intsize > 2))
+		return -EINVAL;
+	if (intsize == 2 && intspec[1] == 1) {
+		int_irq = xtensa_map_ext_irq(ext_irq);
+		if (int_irq < XCHAL_NUM_INTERRUPTS)
+			*out_hwirq = int_irq;
+		else
+			return -EINVAL;
+	} else {
+		*out_hwirq = int_irq;
+	}
+	*out_type = IRQ_TYPE_NONE;
+	return 0;
 }
 
-static struct irq_chip xtensa_irq_chip = {
-	.name		= "xtensa",
-	.irq_enable	= xtensa_irq_enable,
-	.irq_disable	= xtensa_irq_disable,
-	.irq_mask	= xtensa_irq_mask,
-	.irq_unmask	= xtensa_irq_unmask,
-	.irq_ack	= xtensa_irq_ack,
-	.irq_retrigger	= xtensa_irq_retrigger,
-};
-
-static int xtensa_irq_map(struct irq_domain *d, unsigned int irq,
+int xtensa_irq_map(struct irq_domain *d, unsigned int irq,
 		irq_hw_number_t hw)
 {
+	struct irq_chip *irq_chip = d->host_data;
 	u32 mask = 1 << hw;
 
 	if (mask & XCHAL_INTTYPE_MASK_SOFTWARE) {
-		irq_set_chip_and_handler_name(irq, &xtensa_irq_chip,
+		irq_set_chip_and_handler_name(irq, irq_chip,
 				handle_simple_irq, "level");
 		irq_set_status_flags(irq, IRQ_LEVEL);
 	} else if (mask & XCHAL_INTTYPE_MASK_EXTERN_EDGE) {
-		irq_set_chip_and_handler_name(irq, &xtensa_irq_chip,
+		irq_set_chip_and_handler_name(irq, irq_chip,
 				handle_edge_irq, "edge");
 		irq_clear_status_flags(irq, IRQ_LEVEL);
 	} else if (mask & XCHAL_INTTYPE_MASK_EXTERN_LEVEL) {
-		irq_set_chip_and_handler_name(irq, &xtensa_irq_chip,
+		irq_set_chip_and_handler_name(irq, irq_chip,
 				handle_level_irq, "level");
 		irq_set_status_flags(irq, IRQ_LEVEL);
 	} else if (mask & XCHAL_INTTYPE_MASK_TIMER) {
-		irq_set_chip_and_handler_name(irq, &xtensa_irq_chip,
-				handle_edge_irq, "edge");
+		irq_set_chip_and_handler_name(irq, irq_chip,
+				handle_percpu_irq, "timer");
 		irq_clear_status_flags(irq, IRQ_LEVEL);
 	} else {/* XCHAL_INTTYPE_MASK_WRITE_ERROR */
 		/* XCHAL_INTTYPE_MASK_NMI */
-
-		irq_set_chip_and_handler_name(irq, &xtensa_irq_chip,
+		irq_set_chip_and_handler_name(irq, irq_chip,
 				handle_level_irq, "level");
 		irq_set_status_flags(irq, IRQ_LEVEL);
 	}
 	return 0;
 }
 
-static unsigned map_ext_irq(unsigned ext_irq)
+unsigned xtensa_map_ext_irq(unsigned ext_irq)
 {
 	unsigned mask = XCHAL_INTTYPE_MASK_EXTERN_EDGE |
 		XCHAL_INTTYPE_MASK_EXTERN_LEVEL;
@@ -163,55 +128,77 @@ static unsigned map_ext_irq(unsigned ext_irq)
 	return XCHAL_NUM_INTERRUPTS;
 }
 
-/*
- * Device Tree IRQ specifier translation function which works with one or
- * two cell bindings. First cell value maps directly to the hwirq number.
- * Second cell if present specifies whether hwirq number is external (1) or
- * internal (0).
- */
-int xtensa_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
-		const u32 *intspec, unsigned int intsize,
-		unsigned long *out_hwirq, unsigned int *out_type)
+unsigned xtensa_get_ext_irq_no(unsigned irq)
 {
-	if (WARN_ON(intsize < 1 || intsize > 2))
-		return -EINVAL;
-	if (intsize == 2 && intspec[1] == 1) {
-		unsigned int_irq = map_ext_irq(intspec[0]);
-		if (int_irq < XCHAL_NUM_INTERRUPTS)
-			*out_hwirq = int_irq;
-		else
-			return -EINVAL;
-	} else {
-		*out_hwirq = intspec[0];
-	}
-	*out_type = IRQ_TYPE_NONE;
-	return 0;
+	unsigned mask = (XCHAL_INTTYPE_MASK_EXTERN_EDGE |
+		XCHAL_INTTYPE_MASK_EXTERN_LEVEL) &
+		((1u << irq) - 1);
+	return hweight32(mask);
 }
 
-static const struct irq_domain_ops xtensa_irq_domain_ops = {
-	.xlate = xtensa_irq_domain_xlate,
-	.map = xtensa_irq_map,
-};
-
 void __init init_IRQ(void)
 {
-	struct device_node *intc = NULL;
-
-	cached_irq_mask = 0;
-	set_sr(~0, intclear);
-
 #ifdef CONFIG_OF
-	/* The interrupt controller device node is mandatory */
-	intc = of_find_compatible_node(NULL, NULL, "xtensa,pic");
-	BUG_ON(!intc);
-
-	root_domain = irq_domain_add_linear(intc, NR_IRQS,
-			&xtensa_irq_domain_ops, NULL);
+	irqchip_init();
+#else
+#ifdef CONFIG_HAVE_SMP
+	xtensa_mx_init_legacy(NULL);
 #else
-	root_domain = irq_domain_add_legacy(intc, NR_IRQS, 0, 0,
-			&xtensa_irq_domain_ops, NULL);
+	xtensa_pic_init_legacy(NULL);
+#endif
 #endif
-	irq_set_default_host(root_domain);
 
+#ifdef CONFIG_SMP
+	ipi_init();
+#endif
 	variant_init_irq();
 }
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void route_irq(struct irq_data *data, unsigned int irq, unsigned int cpu)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	if (chip->irq_set_affinity)
+		chip->irq_set_affinity(data, cpumask_of(cpu), false);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+/*
+ * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
+ * the affinity settings do not allow other CPUs, force them onto any
+ * available CPU.
+ */
+void migrate_irqs(void)
+{
+	unsigned int i, cpu = smp_processor_id();
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_data *data = irq_desc_get_irq_data(desc);
+		unsigned int newcpu;
+
+		if (irqd_is_per_cpu(data))
+			continue;
+
+		if (!cpumask_test_cpu(cpu, data->affinity))
+			continue;
+
+		newcpu = cpumask_any_and(data->affinity, cpu_online_mask);
+
+		if (newcpu >= nr_cpu_ids) {
+			pr_info_ratelimited("IRQ%u no longer affine to CPU%u\n",
+					    i, cpu);
+
+			cpumask_setall(data->affinity);
+			newcpu = cpumask_any_and(data->affinity,
+						 cpu_online_mask);
+		}
+
+		route_irq(data, i, newcpu);
+	}
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/xtensa/kernel/mxhead.S b/arch/xtensa/kernel/mxhead.S
new file mode 100644
index 0000000..77a161a
--- /dev/null
+++ b/arch/xtensa/kernel/mxhead.S
@@ -0,0 +1,85 @@
+/*
+ * Xtensa Secondary Processors startup code.
+ *
+ * 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 - 2013 Tensilica Inc.
+ *
+ * Joe Taylor <joe@tensilica.com>
+ * Chris Zankel <chris@zankel.net>
+ * Marc Gauthier <marc@tensilica.com, marc@alumni.uwaterloo.ca>
+ * Pete Delaney <piet@tensilica.com>
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/cacheasm.h>
+#include <asm/initialize_mmu.h>
+#include <asm/mxregs.h>
+#include <asm/regs.h>
+
+
+	.section .SecondaryResetVector.text, "ax"
+
+
+ENTRY(_SecondaryResetVector)
+	_j _SetupOCD
+
+	.begin  no-absolute-literals
+	.literal_position
+
+_SetupOCD:
+	/*
+	 * Initialize WB, WS, and clear PS.EXCM (to allow loop instructions).
+	 * Set Interrupt Level just below XCHAL_DEBUGLEVEL to allow
+	 * xt-gdb to single step via DEBUG exceptions received directly
+	 * by ocd.
+	 */
+	movi	a1, 1
+	movi	a0, 0
+	wsr	a1, windowstart
+	wsr	a0, windowbase
+	rsync
+
+	movi	a1, LOCKLEVEL
+	wsr	a1, ps
+	rsync
+
+_SetupMMU:
+	Offset = _SetupMMU - _SecondaryResetVector
+
+#ifdef CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX
+	initialize_mmu
+#endif
+
+	/*
+	 * Start Secondary Processors with NULL pointer to boot params.
+	 */
+	movi	a2, 0				#  a2 == NULL
+	movi	a3, _startup
+	jx	a3
+
+	.end    no-absolute-literals
+
+
+	.section 	.SecondaryResetVector.remapped_text, "ax"
+	.global         _RemappedSecondaryResetVector
+
+	.org 0                                  # Need to do org before literals
+
+_RemappedSecondaryResetVector:
+	.begin  no-absolute-literals
+	.literal_position
+
+	_j      _RemappedSetupMMU
+	. = _RemappedSecondaryResetVector + Offset
+
+_RemappedSetupMMU:
+
+#ifdef CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX
+	initialize_mmu
+#endif
+
+	.end    no-absolute-literals
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 6e2b663..7d12af1 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -21,6 +21,8 @@
 #include <linux/screen_info.h>
 #include <linux/bootmem.h>
 #include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 
@@ -37,6 +39,7 @@
 #endif
 
 #include <asm/bootparam.h>
+#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/timex.h>
@@ -45,6 +48,7 @@
 #include <asm/setup.h>
 #include <asm/param.h>
 #include <asm/traps.h>
+#include <asm/smp.h>
 
 #include <platform/hardware.h>
 
@@ -85,12 +89,6 @@ static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
 
 sysmem_info_t __initdata sysmem;
 
-#ifdef CONFIG_MMU
-extern void init_mmu(void);
-#else
-static inline void init_mmu(void) { }
-#endif
-
 extern int mem_reserve(unsigned long, unsigned long, int);
 extern void bootmem_init(void);
 extern void zones_init(void);
@@ -214,6 +212,42 @@ static int __init parse_bootparam(const bp_tag_t* tag)
 #ifdef CONFIG_OF
 bool __initdata dt_memory_scan = false;
 
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY
+unsigned long xtensa_kio_paddr = XCHAL_KIO_DEFAULT_PADDR;
+EXPORT_SYMBOL(xtensa_kio_paddr);
+
+static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
+		int depth, void *data)
+{
+	const __be32 *ranges;
+	unsigned long len;
+
+	if (depth > 1)
+		return 0;
+
+	if (!of_flat_dt_is_compatible(node, "simple-bus"))
+		return 0;
+
+	ranges = of_get_flat_dt_prop(node, "ranges", &len);
+	if (!ranges)
+		return 1;
+	if (len == 0)
+		return 1;
+
+	xtensa_kio_paddr = of_read_ulong(ranges+1, 1);
+	/* round down to nearest 256MB boundary */
+	xtensa_kio_paddr &= 0xf0000000;
+
+	return 1;
+}
+#else
+static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
+		int depth, void *data)
+{
+	return 1;
+}
+#endif
+
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	if (!dt_memory_scan)
@@ -234,6 +268,7 @@ void __init early_init_devtree(void *params)
 		dt_memory_scan = true;
 
 	early_init_dt_scan(params);
+	of_scan_flat_dt(xtensa_dt_io_area, NULL);
 
 	if (!command_line[0])
 		strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
@@ -241,7 +276,7 @@ void __init early_init_devtree(void *params)
 
 static int __init xtensa_device_probe(void)
 {
-	of_platform_populate(NULL, NULL, NULL, NULL);
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
 
@@ -354,7 +389,8 @@ static inline int probed_compare_swap(int *v, int cmp, int set)
 
 /* Handle probed exception */
 
-void __init do_probed_exception(struct pt_regs *regs, unsigned long exccause)
+static void __init do_probed_exception(struct pt_regs *regs,
+		unsigned long exccause)
 {
 	if (regs->pc == rcw_probe_pc) {	/* exception on s32c1i ? */
 		regs->pc += 3;		/* skip the s32c1i instruction */
@@ -366,7 +402,7 @@ void __init do_probed_exception(struct pt_regs *regs, unsigned long exccause)
 
 /* Simple test of S32C1I (soc bringup assist) */
 
-void __init check_s32c1i(void)
+static int __init check_s32c1i(void)
 {
 	int n, cause1, cause2;
 	void *handbus, *handdata, *handaddr; /* temporarily saved handlers */
@@ -421,24 +457,21 @@ void __init check_s32c1i(void)
 	trap_set_handler(EXCCAUSE_LOAD_STORE_ERROR, handbus);
 	trap_set_handler(EXCCAUSE_LOAD_STORE_DATA_ERROR, handdata);
 	trap_set_handler(EXCCAUSE_LOAD_STORE_ADDR_ERROR, handaddr);
+	return 0;
 }
 
 #else /* XCHAL_HAVE_S32C1I */
 
 /* This condition should not occur with a commercially deployed processor.
    Display reminder for early engr test or demo chips / FPGA bitstreams */
-void __init check_s32c1i(void)
+static int __init check_s32c1i(void)
 {
 	pr_warn("Processor configuration lacks atomic compare-and-swap support!\n");
+	return 0;
 }
 
 #endif /* XCHAL_HAVE_S32C1I */
-#else /* CONFIG_S32C1I_SELFTEST */
-
-void __init check_s32c1i(void)
-{
-}
-
+early_initcall(check_s32c1i);
 #endif /* CONFIG_S32C1I_SELFTEST */
 
 
@@ -447,8 +480,6 @@ void __init setup_arch(char **cmdline_p)
 	strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
-	check_s32c1i();
-
 	/* Reserve some memory regions */
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -505,6 +536,10 @@ void __init setup_arch(char **cmdline_p)
 
 	platform_setup(cmdline_p);
 
+#ifdef CONFIG_SMP
+	smp_init_cpus();
+#endif
+
 	paging_init();
 	zones_init();
 
@@ -521,6 +556,22 @@ void __init setup_arch(char **cmdline_p)
 #endif
 }
 
+static DEFINE_PER_CPU(struct cpu, cpu_data);
+
+static int __init topology_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct cpu *cpu = &per_cpu(cpu_data, i);
+		cpu->hotpluggable = !!i;
+		register_cpu(cpu, i);
+	}
+
+	return 0;
+}
+subsys_initcall(topology_init);
+
 void machine_restart(char * cmd)
 {
 	platform_restart();
@@ -546,21 +597,27 @@ void machine_power_off(void)
 static int
 c_show(struct seq_file *f, void *slot)
 {
+	char buf[NR_CPUS * 5];
+
+	cpulist_scnprintf(buf, sizeof(buf), cpu_online_mask);
 	/* high-level stuff */
-	seq_printf(f,"processor\t: 0\n"
-		     "vendor_id\t: Tensilica\n"
-		     "model\t\t: Xtensa " XCHAL_HW_VERSION_NAME "\n"
-		     "core ID\t\t: " XCHAL_CORE_ID "\n"
-		     "build ID\t: 0x%x\n"
-		     "byte order\t: %s\n"
-		     "cpu MHz\t\t: %lu.%02lu\n"
-		     "bogomips\t: %lu.%02lu\n",
-		     XCHAL_BUILD_UNIQUE_ID,
-		     XCHAL_HAVE_BE ?  "big" : "little",
-		     ccount_freq/1000000,
-		     (ccount_freq/10000) % 100,
-		     loops_per_jiffy/(500000/HZ),
-		     (loops_per_jiffy/(5000/HZ)) % 100);
+	seq_printf(f, "CPU count\t: %u\n"
+		      "CPU list\t: %s\n"
+		      "vendor_id\t: Tensilica\n"
+		      "model\t\t: Xtensa " XCHAL_HW_VERSION_NAME "\n"
+		      "core ID\t\t: " XCHAL_CORE_ID "\n"
+		      "build ID\t: 0x%x\n"
+		      "byte order\t: %s\n"
+		      "cpu MHz\t\t: %lu.%02lu\n"
+		      "bogomips\t: %lu.%02lu\n",
+		      num_online_cpus(),
+		      buf,
+		      XCHAL_BUILD_UNIQUE_ID,
+		      XCHAL_HAVE_BE ?  "big" : "little",
+		      ccount_freq/1000000,
+		      (ccount_freq/10000) % 100,
+		      loops_per_jiffy/(500000/HZ),
+		      (loops_per_jiffy/(5000/HZ)) % 100);
 
 	seq_printf(f,"flags\t\t: "
 #if XCHAL_HAVE_NMI
@@ -672,7 +729,7 @@ c_show(struct seq_file *f, void *slot)
 static void *
 c_start(struct seq_file *f, loff_t *pos)
 {
-	return (void *) ((*pos == 0) ? (void *)1 : NULL);
+	return (*pos == 0) ? (void *)1 : NULL;
 }
 
 static void *
@@ -688,10 +745,10 @@ c_stop(struct seq_file *f, void *v)
 
 const struct seq_operations cpuinfo_op =
 {
-	start:  c_start,
-	next:   c_next,
-	stop:   c_stop,
-	show:   c_show
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= c_show,
 };
 
 #endif /* CONFIG_PROC_FS */
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
new file mode 100644
index 0000000..aa8bd87
--- /dev/null
+++ b/arch/xtensa/kernel/smp.c
@@ -0,0 +1,592 @@
+/*
+ * Xtensa SMP support functions.
+ *
+ * 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.
+ *
+ * Chris Zankel <chris@zankel.net>
+ * Joe Taylor <joe@tensilica.com>
+ * Pete Delaney <piet@tensilica.com
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/reboot.h>
+#include <linux/seq_file.h>
+#include <linux/smp.h>
+#include <linux/thread_info.h>
+
+#include <asm/cacheflush.h>
+#include <asm/kdebug.h>
+#include <asm/mmu_context.h>
+#include <asm/mxregs.h>
+#include <asm/platform.h>
+#include <asm/tlbflush.h>
+#include <asm/traps.h>
+
+#ifdef CONFIG_SMP
+# if XCHAL_HAVE_S32C1I == 0
+#  error "The S32C1I option is required for SMP."
+# endif
+#endif
+
+static void system_invalidate_dcache_range(unsigned long start,
+		unsigned long size);
+static void system_flush_invalidate_dcache_range(unsigned long start,
+		unsigned long size);
+
+/* IPI (Inter Process Interrupt) */
+
+#define IPI_IRQ	0
+
+static irqreturn_t ipi_interrupt(int irq, void *dev_id);
+static struct irqaction ipi_irqaction = {
+	.handler =	ipi_interrupt,
+	.flags =	IRQF_PERCPU,
+	.name =		"ipi",
+};
+
+void ipi_init(void)
+{
+	unsigned irq = irq_create_mapping(NULL, IPI_IRQ);
+	setup_irq(irq, &ipi_irqaction);
+}
+
+static inline unsigned int get_core_count(void)
+{
+	/* Bits 18..21 of SYSCFGID contain the core count minus 1. */
+	unsigned int syscfgid = get_er(SYSCFGID);
+	return ((syscfgid >> 18) & 0xf) + 1;
+}
+
+static inline int get_core_id(void)
+{
+	/* Bits 0...18 of SYSCFGID contain the core id  */
+	unsigned int core_id = get_er(SYSCFGID);
+	return core_id & 0x3fff;
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	unsigned i;
+
+	for (i = 0; i < max_cpus; ++i)
+		set_cpu_present(i, true);
+}
+
+void __init smp_init_cpus(void)
+{
+	unsigned i;
+	unsigned int ncpus = get_core_count();
+	unsigned int core_id = get_core_id();
+
+	pr_info("%s: Core Count = %d\n", __func__, ncpus);
+	pr_info("%s: Core Id = %d\n", __func__, core_id);
+
+	for (i = 0; i < ncpus; ++i)
+		set_cpu_possible(i, true);
+}
+
+void __init smp_prepare_boot_cpu(void)
+{
+	unsigned int cpu = smp_processor_id();
+	BUG_ON(cpu != 0);
+	cpu_asid_cache(cpu) = ASID_USER_FIRST;
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+}
+
+static int boot_secondary_processors = 1; /* Set with xt-gdb via .xt-gdb */
+static DECLARE_COMPLETION(cpu_running);
+
+void secondary_start_kernel(void)
+{
+	struct mm_struct *mm = &init_mm;
+	unsigned int cpu = smp_processor_id();
+
+	init_mmu();
+
+#ifdef CONFIG_DEBUG_KERNEL
+	if (boot_secondary_processors == 0) {
+		pr_debug("%s: boot_secondary_processors:%d; Hanging cpu:%d\n",
+			__func__, boot_secondary_processors, cpu);
+		for (;;)
+			__asm__ __volatile__ ("waiti " __stringify(LOCKLEVEL));
+	}
+
+	pr_debug("%s: boot_secondary_processors:%d; Booting cpu:%d\n",
+		__func__, boot_secondary_processors, cpu);
+#endif
+	/* Init EXCSAVE1 */
+
+	secondary_trap_init();
+
+	/* All kernel threads share the same mm context. */
+
+	atomic_inc(&mm->mm_users);
+	atomic_inc(&mm->mm_count);
+	current->active_mm = mm;
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
+	enter_lazy_tlb(mm, current);
+
+	preempt_disable();
+	trace_hardirqs_off();
+
+	calibrate_delay();
+
+	notify_cpu_starting(cpu);
+
+	secondary_init_irq();
+	local_timer_setup(cpu);
+
+	set_cpu_online(cpu, true);
+
+	local_irq_enable();
+
+	complete(&cpu_running);
+
+	cpu_startup_entry(CPUHP_ONLINE);
+}
+
+static void mx_cpu_start(void *p)
+{
+	unsigned cpu = (unsigned)p;
+	unsigned long run_stall_mask = get_er(MPSCORE);
+
+	set_er(run_stall_mask & ~(1u << cpu), MPSCORE);
+	pr_debug("%s: cpu: %d, run_stall_mask: %lx ---> %lx\n",
+			__func__, cpu, run_stall_mask, get_er(MPSCORE));
+}
+
+static void mx_cpu_stop(void *p)
+{
+	unsigned cpu = (unsigned)p;
+	unsigned long run_stall_mask = get_er(MPSCORE);
+
+	set_er(run_stall_mask | (1u << cpu), MPSCORE);
+	pr_debug("%s: cpu: %d, run_stall_mask: %lx ---> %lx\n",
+			__func__, cpu, run_stall_mask, get_er(MPSCORE));
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+unsigned long cpu_start_id __cacheline_aligned;
+#endif
+unsigned long cpu_start_ccount;
+
+static int boot_secondary(unsigned int cpu, struct task_struct *ts)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+	unsigned long ccount;
+	int i;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	cpu_start_id = cpu;
+	system_flush_invalidate_dcache_range(
+			(unsigned long)&cpu_start_id, sizeof(cpu_start_id));
+#endif
+	smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);
+
+	for (i = 0; i < 2; ++i) {
+		do
+			ccount = get_ccount();
+		while (!ccount);
+
+		cpu_start_ccount = ccount;
+
+		while (time_before(jiffies, timeout)) {
+			mb();
+			if (!cpu_start_ccount)
+				break;
+		}
+
+		if (cpu_start_ccount) {
+			smp_call_function_single(0, mx_cpu_stop,
+					(void *)cpu, 1);
+			cpu_start_ccount = 0;
+			return -EIO;
+		}
+	}
+	return 0;
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *idle)
+{
+	int ret = 0;
+
+	if (cpu_asid_cache(cpu) == 0)
+		cpu_asid_cache(cpu) = ASID_USER_FIRST;
+
+	start_info.stack = (unsigned long)task_pt_regs(idle);
+	wmb();
+
+	pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
+			__func__, cpu, idle, start_info.stack);
+
+	ret = boot_secondary(cpu, idle);
+	if (ret == 0) {
+		wait_for_completion_timeout(&cpu_running,
+				msecs_to_jiffies(1000));
+		if (!cpu_online(cpu))
+			ret = -EIO;
+	}
+
+	if (ret)
+		pr_err("CPU %u failed to boot\n", cpu);
+
+	return ret;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	/*
+	 * Take this CPU offline.  Once we clear this, we can't return,
+	 * and we must not schedule until we're ready to give up the cpu.
+	 */
+	set_cpu_online(cpu, false);
+
+	/*
+	 * OK - migrate IRQs away from this CPU
+	 */
+	migrate_irqs();
+
+	/*
+	 * Flush user cache and TLB mappings, and then remove this CPU
+	 * from the vm mask set of all processes.
+	 */
+	local_flush_cache_all();
+	local_flush_tlb_all();
+	invalidate_page_directory();
+
+	clear_tasks_mm_cpumask(cpu);
+
+	return 0;
+}
+
+static void platform_cpu_kill(unsigned int cpu)
+{
+	smp_call_function_single(0, mx_cpu_stop, (void *)cpu, true);
+}
+
+/*
+ * called on the thread which is asking for a CPU to be shutdown -
+ * waits until shutdown has completed, or it is timed out.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+	while (time_before(jiffies, timeout)) {
+		system_invalidate_dcache_range((unsigned long)&cpu_start_id,
+				sizeof(cpu_start_id));
+		if (cpu_start_id == -cpu) {
+			platform_cpu_kill(cpu);
+			return;
+		}
+	}
+	pr_err("CPU%u: unable to kill\n", cpu);
+}
+
+void arch_cpu_idle_dead(void)
+{
+	cpu_die();
+}
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ *
+ * Note that we disable IRQs here, but do not re-enable them
+ * before returning to the caller. This is also the behaviour
+ * of the other hotplug-cpu capable cores, so presumably coming
+ * out of idle fixes this.
+ */
+void __ref cpu_die(void)
+{
+	idle_task_exit();
+	local_irq_disable();
+	__asm__ __volatile__(
+			"	movi	a2, cpu_restart\n"
+			"	jx	a2\n");
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+enum ipi_msg_type {
+	IPI_RESCHEDULE = 0,
+	IPI_CALL_FUNC,
+	IPI_CPU_STOP,
+	IPI_MAX
+};
+
+static const struct {
+	const char *short_text;
+	const char *long_text;
+} ipi_text[] = {
+	{ .short_text = "RES", .long_text = "Rescheduling interrupts" },
+	{ .short_text = "CAL", .long_text = "Function call interrupts" },
+	{ .short_text = "DIE", .long_text = "CPU shutdown interrupts" },
+};
+
+struct ipi_data {
+	unsigned long ipi_count[IPI_MAX];
+};
+
+static DEFINE_PER_CPU(struct ipi_data, ipi_data);
+
+static void send_ipi_message(const struct cpumask *callmask,
+		enum ipi_msg_type msg_id)
+{
+	int index;
+	unsigned long mask = 0;
+
+	for_each_cpu(index, callmask)
+		if (index != smp_processor_id())
+			mask |= 1 << index;
+
+	set_er(mask, MIPISET(msg_id));
+}
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+	send_ipi_message(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
+}
+
+void smp_send_reschedule(int cpu)
+{
+	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
+}
+
+void smp_send_stop(void)
+{
+	struct cpumask targets;
+
+	cpumask_copy(&targets, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &targets);
+	send_ipi_message(&targets, IPI_CPU_STOP);
+}
+
+static void ipi_cpu_stop(unsigned int cpu)
+{
+	set_cpu_online(cpu, false);
+	machine_halt();
+}
+
+irqreturn_t ipi_interrupt(int irq, void *dev_id)
+{
+	unsigned int cpu = smp_processor_id();
+	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
+	unsigned int msg;
+	unsigned i;
+
+	msg = get_er(MIPICAUSE(cpu));
+	for (i = 0; i < IPI_MAX; i++)
+		if (msg & (1 << i)) {
+			set_er(1 << i, MIPICAUSE(cpu));
+			++ipi->ipi_count[i];
+		}
+
+	if (msg & (1 << IPI_RESCHEDULE))
+		scheduler_ipi();
+	if (msg & (1 << IPI_CALL_FUNC))
+		generic_smp_call_function_interrupt();
+	if (msg & (1 << IPI_CPU_STOP))
+		ipi_cpu_stop(cpu);
+
+	return IRQ_HANDLED;
+}
+
+void show_ipi_list(struct seq_file *p, int prec)
+{
+	unsigned int cpu;
+	unsigned i;
+
+	for (i = 0; i < IPI_MAX; ++i) {
+		seq_printf(p, "%*s:", prec, ipi_text[i].short_text);
+		for_each_online_cpu(cpu)
+			seq_printf(p, " %10lu",
+					per_cpu(ipi_data, cpu).ipi_count[i]);
+		seq_printf(p, "   %s\n", ipi_text[i].long_text);
+	}
+}
+
+int setup_profiling_timer(unsigned int multiplier)
+{
+	pr_debug("setup_profiling_timer %d\n", multiplier);
+	return 0;
+}
+
+/* TLB flush functions */
+
+struct flush_data {
+	struct vm_area_struct *vma;
+	unsigned long addr1;
+	unsigned long addr2;
+};
+
+static void ipi_flush_tlb_all(void *arg)
+{
+	local_flush_tlb_all();
+}
+
+void flush_tlb_all(void)
+{
+	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+}
+
+static void ipi_flush_tlb_mm(void *arg)
+{
+	local_flush_tlb_mm(arg);
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	on_each_cpu(ipi_flush_tlb_mm, mm, 1);
+}
+
+static void ipi_flush_tlb_page(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_tlb_page(fd->vma, fd->addr1);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = addr,
+	};
+	on_each_cpu(ipi_flush_tlb_page, &fd, 1);
+}
+
+static void ipi_flush_tlb_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_tlb_range(fd->vma, fd->addr1, fd->addr2);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma,
+		     unsigned long start, unsigned long end)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = start,
+		.addr2 = end,
+	};
+	on_each_cpu(ipi_flush_tlb_range, &fd, 1);
+}
+
+/* Cache flush functions */
+
+static void ipi_flush_cache_all(void *arg)
+{
+	local_flush_cache_all();
+}
+
+void flush_cache_all(void)
+{
+	on_each_cpu(ipi_flush_cache_all, NULL, 1);
+}
+
+static void ipi_flush_cache_page(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_cache_page(fd->vma, fd->addr1, fd->addr2);
+}
+
+void flush_cache_page(struct vm_area_struct *vma,
+		     unsigned long address, unsigned long pfn)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = address,
+		.addr2 = pfn,
+	};
+	on_each_cpu(ipi_flush_cache_page, &fd, 1);
+}
+
+static void ipi_flush_cache_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_cache_range(fd->vma, fd->addr1, fd->addr2);
+}
+
+void flush_cache_range(struct vm_area_struct *vma,
+		     unsigned long start, unsigned long end)
+{
+	struct flush_data fd = {
+		.vma = vma,
+		.addr1 = start,
+		.addr2 = end,
+	};
+	on_each_cpu(ipi_flush_cache_range, &fd, 1);
+}
+
+static void ipi_flush_icache_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	local_flush_icache_range(fd->addr1, fd->addr2);
+}
+
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	struct flush_data fd = {
+		.addr1 = start,
+		.addr2 = end,
+	};
+	on_each_cpu(ipi_flush_icache_range, &fd, 1);
+}
+
+/* ------------------------------------------------------------------------- */
+
+static void ipi_invalidate_dcache_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	__invalidate_dcache_range(fd->addr1, fd->addr2);
+}
+
+static void system_invalidate_dcache_range(unsigned long start,
+		unsigned long size)
+{
+	struct flush_data fd = {
+		.addr1 = start,
+		.addr2 = size,
+	};
+	on_each_cpu(ipi_invalidate_dcache_range, &fd, 1);
+}
+
+static void ipi_flush_invalidate_dcache_range(void *arg)
+{
+	struct flush_data *fd = arg;
+	__flush_invalidate_dcache_range(fd->addr1, fd->addr2);
+}
+
+static void system_flush_invalidate_dcache_range(unsigned long start,
+		unsigned long size)
+{
+	struct flush_data fd = {
+		.addr1 = start,
+		.addr2 = size,
+	};
+	on_each_cpu(ipi_flush_invalidate_dcache_range, &fd, 1);
+}
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 9af3dd8..08b769d 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -36,7 +36,7 @@ static cycle_t ccount_read(struct clocksource *cs)
 	return (cycle_t)get_ccount();
 }
 
-static u32 notrace ccount_sched_clock_read(void)
+static u64 notrace ccount_sched_clock_read(void)
 {
 	return get_ccount();
 }
@@ -46,24 +46,19 @@ static struct clocksource ccount_clocksource = {
 	.rating = 200,
 	.read = ccount_read,
 	.mask = CLOCKSOURCE_MASK(32),
+	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static int ccount_timer_set_next_event(unsigned long delta,
 		struct clock_event_device *dev);
 static void ccount_timer_set_mode(enum clock_event_mode mode,
 		struct clock_event_device *evt);
-static struct ccount_timer_t {
+struct ccount_timer {
 	struct clock_event_device evt;
 	int irq_enabled;
-} ccount_timer = {
-	.evt = {
-		.name		= "ccount_clockevent",
-		.features	= CLOCK_EVT_FEAT_ONESHOT,
-		.rating		= 300,
-		.set_next_event	= ccount_timer_set_next_event,
-		.set_mode	= ccount_timer_set_mode,
-	},
+	char name[24];
 };
+static DEFINE_PER_CPU(struct ccount_timer, ccount_timer);
 
 static int ccount_timer_set_next_event(unsigned long delta,
 		struct clock_event_device *dev)
@@ -84,8 +79,8 @@ static int ccount_timer_set_next_event(unsigned long delta,
 static void ccount_timer_set_mode(enum clock_event_mode mode,
 		struct clock_event_device *evt)
 {
-	struct ccount_timer_t *timer =
-		container_of(evt, struct ccount_timer_t, evt);
+	struct ccount_timer *timer =
+		container_of(evt, struct ccount_timer, evt);
 
 	/*
 	 * There is no way to disable the timer interrupt at the device level,
@@ -117,9 +112,28 @@ static struct irqaction timer_irqaction = {
 	.handler =	timer_interrupt,
 	.flags =	IRQF_TIMER,
 	.name =		"timer",
-	.dev_id =	&ccount_timer,
 };
 
+void local_timer_setup(unsigned cpu)
+{
+	struct ccount_timer *timer = &per_cpu(ccount_timer, cpu);
+	struct clock_event_device *clockevent = &timer->evt;
+
+	timer->irq_enabled = 1;
+	clockevent->name = timer->name;
+	snprintf(timer->name, sizeof(timer->name), "ccount_clockevent_%u", cpu);
+	clockevent->features = CLOCK_EVT_FEAT_ONESHOT;
+	clockevent->rating = 300;
+	clockevent->set_next_event = ccount_timer_set_next_event;
+	clockevent->set_mode = ccount_timer_set_mode;
+	clockevent->cpumask = cpumask_of(cpu);
+	clockevent->irq = irq_create_mapping(NULL, LINUX_TIMER_INT);
+	if (WARN(!clockevent->irq, "error: can't map timer irq"))
+		return;
+	clockevents_config_and_register(clockevent, ccount_freq,
+					0xf, 0xffffffff);
+}
+
 void __init time_init(void)
 {
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
@@ -131,28 +145,21 @@ void __init time_init(void)
 	ccount_freq = CONFIG_XTENSA_CPU_CLOCK*1000000UL;
 #endif
 	clocksource_register_hz(&ccount_clocksource, ccount_freq);
-
-	ccount_timer.evt.cpumask = cpumask_of(0);
-	ccount_timer.evt.irq = irq_create_mapping(NULL, LINUX_TIMER_INT);
-	if (WARN(!ccount_timer.evt.irq, "error: can't map timer irq"))
-		return;
-	clockevents_config_and_register(&ccount_timer.evt, ccount_freq, 0xf,
-			0xffffffff);
-	setup_irq(ccount_timer.evt.irq, &timer_irqaction);
-	ccount_timer.irq_enabled = 1;
-
-	setup_sched_clock(ccount_sched_clock_read, 32, ccount_freq);
+	local_timer_setup(0);
+	setup_irq(this_cpu_ptr(&ccount_timer)->evt.irq, &timer_irqaction);
+	sched_clock_register(ccount_sched_clock_read, 32, ccount_freq);
+	clocksource_of_init();
 }
 
 /*
  * The timer interrupt is called HZ times per second.
  */
 
-irqreturn_t timer_interrupt (int irq, void *dev_id)
+irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
-	struct ccount_timer_t *timer = dev_id;
-	struct clock_event_device *evt = &timer->evt;
+	struct clock_event_device *evt = &this_cpu_ptr(&ccount_timer)->evt;
 
+	set_linux_timer(get_linux_timer());
 	evt->event_handler(evt);
 
 	/* Allow platform to do something useful (Wdog). */
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 3e8a05c..eebbfd8 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -157,7 +157,7 @@ COPROCESSOR(7),
  * 2. it is a temporary memory buffer for the exception handlers.
  */
 
-unsigned long exc_table[EXC_TABLE_SIZE/4];
+DEFINE_PER_CPU(unsigned long, exc_table[EXC_TABLE_SIZE/4]);
 
 void die(const char*, struct pt_regs*, long);
 
@@ -212,6 +212,9 @@ void do_interrupt(struct pt_regs *regs)
 		XCHAL_INTLEVEL6_MASK,
 		XCHAL_INTLEVEL7_MASK,
 	};
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	irq_enter();
 
 	for (;;) {
 		unsigned intread = get_sr(interrupt);
@@ -227,21 +230,13 @@ void do_interrupt(struct pt_regs *regs)
 		}
 
 		if (level == 0)
-			return;
-
-		/*
-		 * Clear the interrupt before processing, in case it's
-		 *  edge-triggered or software-generated
-		 */
-		while (int_at_level) {
-			unsigned i = __ffs(int_at_level);
-			unsigned mask = 1 << i;
-
-			int_at_level ^= mask;
-			set_sr(mask, intclear);
-			do_IRQ(i, regs);
-		}
+			break;
+
+		do_IRQ(__ffs(int_at_level), regs);
 	}
+
+	irq_exit();
+	set_irq_regs(old_regs);
 }
 
 /*
@@ -318,17 +313,31 @@ do_debug(struct pt_regs *regs)
 }
 
 
+static void set_handler(int idx, void *handler)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(exc_table, cpu)[idx] = (unsigned long)handler;
+}
+
 /* Set exception C handler - for temporary use when probing exceptions */
 
 void * __init trap_set_handler(int cause, void *handler)
 {
-	unsigned long *entry = &exc_table[EXC_TABLE_DEFAULT / 4 + cause];
-	void *previous = (void *)*entry;
-	*entry = (unsigned long)handler;
+	void *previous = (void *)per_cpu(exc_table, 0)[
+		EXC_TABLE_DEFAULT / 4 + cause];
+	set_handler(EXC_TABLE_DEFAULT / 4 + cause, handler);
 	return previous;
 }
 
 
+static void trap_init_excsave(void)
+{
+	unsigned long excsave1 = (unsigned long)this_cpu_ptr(exc_table);
+	__asm__ __volatile__("wsr  %0, excsave1\n" : : "a" (excsave1));
+}
+
 /*
  * Initialize dispatch tables.
  *
@@ -342,8 +351,6 @@ void * __init trap_set_handler(int cause, void *handler)
  * See vectors.S for more details.
  */
 
-#define set_handler(idx,handler) (exc_table[idx] = (unsigned long) (handler))
-
 void __init trap_init(void)
 {
 	int i;
@@ -373,10 +380,15 @@ void __init trap_init(void)
 	}
 
 	/* Initialize EXCSAVE_1 to hold the address of the exception table. */
+	trap_init_excsave();
+}
 
-	i = (unsigned long)exc_table;
-	__asm__ __volatile__("wsr  %0, excsave1\n" : : "a" (i));
+#ifdef CONFIG_SMP
+void secondary_trap_init(void)
+{
+	trap_init_excsave();
 }
+#endif
 
 /*
  * This function dumps the current valid window frame and other base registers.
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 21acd11..ee32c00 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -165,6 +165,13 @@ SECTIONS
 		   .DoubleExceptionVector.text);
     RELOCATE_ENTRY(_DebugInterruptVector_text,
 		   .DebugInterruptVector.text);
+#if defined(CONFIG_SMP)
+    RELOCATE_ENTRY(_SecondaryResetVector_literal,
+		   .SecondaryResetVector.literal);
+    RELOCATE_ENTRY(_SecondaryResetVector_text,
+		   .SecondaryResetVector.text);
+#endif
+
   
     __boot_reloc_table_end = ABSOLUTE(.) ;
 
@@ -272,6 +279,25 @@ SECTIONS
 		  .DoubleExceptionVector.literal)
 
   . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;
+
+#if defined(CONFIG_SMP)
+
+  SECTION_VECTOR (_SecondaryResetVector_literal,
+		  .SecondaryResetVector.literal,
+		  RESET_VECTOR1_VADDR - 4,
+		  SIZEOF(.DoubleExceptionVector.text),
+		  .DoubleExceptionVector.text)
+
+  SECTION_VECTOR (_SecondaryResetVector_text,
+		  .SecondaryResetVector.text,
+		  RESET_VECTOR1_VADDR,
+		  4,
+		  .SecondaryResetVector.literal)
+
+  . = LOADADDR(.SecondaryResetVector.text)+SIZEOF(.SecondaryResetVector.text);
+
+#endif
+
   . = ALIGN(PAGE_SIZE);
 
   __init_end = .;
diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c
index 81edeab..ba4c47f 100644
--- a/arch/xtensa/mm/cache.c
+++ b/arch/xtensa/mm/cache.c
@@ -118,7 +118,7 @@ void flush_dcache_page(struct page *page)
  * For now, flush the whole cache. FIXME??
  */
 
-void flush_cache_range(struct vm_area_struct* vma,
+void local_flush_cache_range(struct vm_area_struct *vma,
 		       unsigned long start, unsigned long end)
 {
 	__flush_invalidate_dcache_all();
@@ -132,7 +132,7 @@ void flush_cache_range(struct vm_area_struct* vma,
  * alias versions of the cache flush functions.
  */
 
-void flush_cache_page(struct vm_area_struct* vma, unsigned long address,
+void local_flush_cache_page(struct vm_area_struct *vma, unsigned long address,
 		      unsigned long pfn)
 {
 	/* Note that we have to use the 'alias' address to avoid multi-hit */
@@ -159,8 +159,7 @@ update_mmu_cache(struct vm_area_struct * vma, unsigned long addr, pte_t *ptep)
 
 	/* Invalidate old entry in TLBs */
 
-	invalidate_itlb_mapping(addr);
-	invalidate_dtlb_mapping(addr);
+	flush_tlb_page(vma, addr);
 
 #if (DCACHE_WAY_SIZE > PAGE_SIZE) && XCHAL_DCACHE_IS_WRITEBACK
 
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 70fa7bc..b57c4f9 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -21,7 +21,7 @@
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
-unsigned long asid_cache = ASID_USER_FIRST;
+DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
 void bad_page_fault(struct pt_regs*, unsigned long, int);
 
 #undef DEBUG_PAGE_FAULT
diff --git a/arch/xtensa/mm/misc.S b/arch/xtensa/mm/misc.S
index d97ed1b..1f68558 100644
--- a/arch/xtensa/mm/misc.S
+++ b/arch/xtensa/mm/misc.S
@@ -140,7 +140,7 @@ ENTRY(clear_user_page)
 
 	/* Setup a temporary DTLB with the color of the VPN */
 
-	movi	a4, -PAGE_OFFSET + (PAGE_KERNEL | _PAGE_HW_WRITE)
+	movi	a4, ((PAGE_KERNEL | _PAGE_HW_WRITE) - PAGE_OFFSET) & 0xffffffff
 	movi	a5, TLBTEMP_BASE_1			# virt
 	add	a6, a2, a4				# ppn
 	add	a2, a5, a3				# add 'color'
@@ -194,7 +194,7 @@ ENTRY(copy_user_page)
 	or	a9, a9, a8
 	slli	a4, a4, PAGE_SHIFT
 	s32i	a9, a5, PAGE_FLAGS
-	movi	a5, -PAGE_OFFSET + (PAGE_KERNEL | _PAGE_HW_WRITE)
+	movi	a5, ((PAGE_KERNEL | _PAGE_HW_WRITE) - PAGE_OFFSET) & 0xffffffff
 
 	beqz	a6, 1f
 
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index c43771c..36ec171 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -13,6 +13,8 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
+#include <asm/initialize_mmu.h>
+#include <asm/io.h>
 
 void __init paging_init(void)
 {
@@ -22,7 +24,7 @@ void __init paging_init(void)
 /*
  * Flush the mmu and reset associated register to default values.
  */
-void __init init_mmu(void)
+void init_mmu(void)
 {
 #if !(XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY)
 	/*
@@ -37,7 +39,21 @@ void __init init_mmu(void)
 	set_itlbcfg_register(0);
 	set_dtlbcfg_register(0);
 #endif
-	flush_tlb_all();
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+	/*
+	 * Update the IO area mapping in case xtensa_kio_paddr has changed
+	 */
+	write_dtlb_entry(__pte(xtensa_kio_paddr + CA_WRITEBACK),
+			XCHAL_KIO_CACHED_VADDR + 6);
+	write_itlb_entry(__pte(xtensa_kio_paddr + CA_WRITEBACK),
+			XCHAL_KIO_CACHED_VADDR + 6);
+	write_dtlb_entry(__pte(xtensa_kio_paddr + CA_BYPASS),
+			XCHAL_KIO_BYPASS_VADDR + 6);
+	write_itlb_entry(__pte(xtensa_kio_paddr + CA_BYPASS),
+			XCHAL_KIO_BYPASS_VADDR + 6);
+#endif
+
+	local_flush_tlb_all();
 
 	/* Set rasid register to a known value. */
 
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index ca9d236..ade62382 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -48,7 +48,7 @@ static inline void __flush_dtlb_all (void)
 }
 
 
-void flush_tlb_all (void)
+void local_flush_tlb_all(void)
 {
 	__flush_itlb_all();
 	__flush_dtlb_all();
@@ -60,19 +60,23 @@ void flush_tlb_all (void)
  * a new context will be assigned to it.
  */
 
-void flush_tlb_mm(struct mm_struct *mm)
+void local_flush_tlb_mm(struct mm_struct *mm)
 {
+	int cpu = smp_processor_id();
+
 	if (mm == current->active_mm) {
 		unsigned long flags;
 		local_irq_save(flags);
-		__get_new_mmu_context(mm);
-		__load_mmu_context(mm);
+		mm->context.asid[cpu] = NO_CONTEXT;
+		activate_context(mm, cpu);
 		local_irq_restore(flags);
+	} else {
+		mm->context.asid[cpu] = NO_CONTEXT;
+		mm->context.cpu = -1;
 	}
-	else
-		mm->context = 0;
 }
 
+
 #define _ITLB_ENTRIES (ITLB_ARF_WAYS << XCHAL_ITLB_ARF_ENTRIES_LOG2)
 #define _DTLB_ENTRIES (DTLB_ARF_WAYS << XCHAL_DTLB_ARF_ENTRIES_LOG2)
 #if _ITLB_ENTRIES > _DTLB_ENTRIES
@@ -81,24 +85,26 @@ void flush_tlb_mm(struct mm_struct *mm)
 # define _TLB_ENTRIES _DTLB_ENTRIES
 #endif
 
-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 cpu = smp_processor_id();
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long flags;
 
-	if (mm->context == NO_CONTEXT)
+	if (mm->context.asid[cpu] == NO_CONTEXT)
 		return;
 
 #if 0
 	printk("[tlbrange<%02lx,%08lx,%08lx>]\n",
-			(unsigned long)mm->context, start, end);
+			(unsigned long)mm->context.asid[cpu], start, end);
 #endif
 	local_irq_save(flags);
 
 	if (end-start + (PAGE_SIZE-1) <= _TLB_ENTRIES << PAGE_SHIFT) {
 		int oldpid = get_rasid_register();
-		set_rasid_register (ASID_INSERT(mm->context));
+
+		set_rasid_register(ASID_INSERT(mm->context.asid[cpu]));
 		start &= PAGE_MASK;
 		if (vma->vm_flags & VM_EXEC)
 			while(start < end) {
@@ -114,24 +120,25 @@ void flush_tlb_range (struct vm_area_struct *vma,
 
 		set_rasid_register(oldpid);
 	} else {
-		flush_tlb_mm(mm);
+		local_flush_tlb_mm(mm);
 	}
 	local_irq_restore(flags);
 }
 
-void flush_tlb_page (struct vm_area_struct *vma, unsigned long page)
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 {
+	int cpu = smp_processor_id();
 	struct mm_struct* mm = vma->vm_mm;
 	unsigned long flags;
 	int oldpid;
 
-	if(mm->context == NO_CONTEXT)
+	if (mm->context.asid[cpu] == NO_CONTEXT)
 		return;
 
 	local_irq_save(flags);
 
 	oldpid = get_rasid_register();
-	set_rasid_register(ASID_INSERT(mm->context));
+	set_rasid_register(ASID_INSERT(mm->context.asid[cpu]));
 
 	if (vma->vm_flags & VM_EXEC)
 		invalidate_itlb_mapping(page);
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index e9e1aad..d05f8fe 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -38,7 +38,7 @@
 #define DRIVER_NAME "iss-netdev"
 #define ETH_MAX_PACKET 1500
 #define ETH_HEADER_OTHER 14
-#define ISS_NET_TIMER_VALUE (2 * HZ)
+#define ISS_NET_TIMER_VALUE (HZ / 10)
 
 
 static DEFINE_SPINLOCK(opened_lock);
@@ -56,8 +56,6 @@ static LIST_HEAD(devices);
 
 struct tuntap_info {
 	char dev_name[IFNAMSIZ];
-	int fixed_config;
-	unsigned char gw[ETH_ALEN];
 	int fd;
 };
 
@@ -67,7 +65,6 @@ struct tuntap_info {
 /* This structure contains out private information for the driver. */
 
 struct iss_net_private {
-
 	struct list_head device_list;
 	struct list_head opened_list;
 
@@ -83,9 +80,6 @@ struct iss_net_private {
 	int index;
 	int mtu;
 
-	unsigned char mac[ETH_ALEN];
-	int have_mac;
-
 	struct {
 		union {
 			struct tuntap_info tuntap;
@@ -118,68 +112,48 @@ static char *split_if_spec(char *str, ...)
 			*arg = str;
 		if (end == NULL)
 			return NULL;
-		*end ++ = '\0';
+		*end++ = '\0';
 		str = end;
 	}
 	va_end(ap);
 	return str;
 }
 
+/* Set Ethernet address of the specified device. */
 
-#if 0
-/* Adjust SKB. */
-
-struct sk_buff *ether_adjust_skb(struct sk_buff *skb, int extra)
+static void setup_etheraddr(struct net_device *dev, char *str)
 {
-	if ((skb != NULL) && (skb_tailroom(skb) < extra)) {
-		struct sk_buff *skb2;
-
-		skb2 = skb_copy_expand(skb, 0, extra, GFP_ATOMIC);
-		dev_kfree_skb(skb);
-		skb = skb2;
-	}
-	if (skb != NULL)
-		skb_put(skb, extra);
-
-	return skb;
-}
-#endif
+	unsigned char *addr = dev->dev_addr;
 
-/* Return the IP address as a string for a given device. */
+	if (str == NULL)
+		goto random;
 
-static void dev_ip_addr(void *d, char *buf, char *bin_buf)
-{
-	struct net_device *dev = d;
-	struct in_device *ip = dev->ip_ptr;
-	struct in_ifaddr *in;
-	__be32 addr;
-
-	if ((ip == NULL) || ((in = ip->ifa_list) == NULL)) {
-		printk(KERN_WARNING "Device not assigned an IP address!\n");
-		return;
+	if (!mac_pton(str, addr)) {
+		pr_err("%s: failed to parse '%s' as an ethernet address\n",
+		       dev->name, str);
+		goto random;
 	}
-
-	addr = in->ifa_address;
-	sprintf(buf, "%d.%d.%d.%d", addr & 0xff, (addr >> 8) & 0xff,
-		(addr >> 16) & 0xff, addr >> 24);
-
-	if (bin_buf) {
-		bin_buf[0] = addr & 0xff;
-		bin_buf[1] = (addr >> 8) & 0xff;
-		bin_buf[2] = (addr >> 16) & 0xff;
-		bin_buf[3] = addr >> 24;
+	if (is_multicast_ether_addr(addr)) {
+		pr_err("%s: attempt to assign a multicast ethernet address\n",
+		       dev->name);
+		goto random;
 	}
+	if (!is_valid_ether_addr(addr)) {
+		pr_err("%s: attempt to assign an invalid ethernet address\n",
+		       dev->name);
+		goto random;
+	}
+	if (!is_local_ether_addr(addr))
+		pr_warn("%s: assigning a globally valid ethernet address\n",
+			dev->name);
+	return;
+
+random:
+	pr_info("%s: choosing a random ethernet address\n",
+		dev->name);
+	eth_hw_addr_random(dev);
 }
 
-/* Set Ethernet address of the specified device. */
-
-static void inline set_ether_mac(void *d, unsigned char *addr)
-{
-	struct net_device *dev = d;
-	memcpy(dev->dev_addr, addr, ETH_ALEN);
-}
-
-
 /* ======================= TUNTAP TRANSPORT INTERFACE ====================== */
 
 static int tuntap_open(struct iss_net_private *lp)
@@ -189,24 +163,21 @@ static int tuntap_open(struct iss_net_private *lp)
 	int err = -EINVAL;
 	int fd;
 
-	/* We currently only support a fixed configuration. */
-
-	if (!lp->tp.info.tuntap.fixed_config)
-		return -EINVAL;
-
-	if ((fd = simc_open("/dev/net/tun", 02, 0)) < 0) {	/* O_RDWR */
-		printk("Failed to open /dev/net/tun, returned %d "
-		       "(errno = %d)\n", fd, errno);
+	fd = simc_open("/dev/net/tun", 02, 0); /* O_RDWR */
+	if (fd < 0) {
+		pr_err("%s: failed to open /dev/net/tun, returned %d (errno = %d)\n",
+		       lp->dev->name, fd, errno);
 		return fd;
 	}
 
-	memset(&ifr, 0, sizeof ifr);
+	memset(&ifr, 0, sizeof(ifr));
 	ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
-	strlcpy(ifr.ifr_name, dev_name, sizeof ifr.ifr_name);
+	strlcpy(ifr.ifr_name, dev_name, sizeof(ifr.ifr_name));
 
-	if ((err = simc_ioctl(fd, TUNSETIFF, (void*) &ifr)) < 0) {
-		printk("Failed to set interface, returned %d "
-		       "(errno = %d)\n", err, errno);
+	err = simc_ioctl(fd, TUNSETIFF, &ifr);
+	if (err < 0) {
+		pr_err("%s: failed to set interface %s, returned %d (errno = %d)\n",
+		       lp->dev->name, dev_name, err, errno);
 		simc_close(fd);
 		return err;
 	}
@@ -217,27 +188,17 @@ static int tuntap_open(struct iss_net_private *lp)
 
 static void tuntap_close(struct iss_net_private *lp)
 {
-#if 0
-	if (lp->tp.info.tuntap.fixed_config)
-		iter_addresses(lp->tp.info.tuntap.dev, close_addr, lp->host.dev_name);
-#endif
 	simc_close(lp->tp.info.tuntap.fd);
 	lp->tp.info.tuntap.fd = -1;
 }
 
-static int tuntap_read (struct iss_net_private *lp, struct sk_buff **skb)
+static int tuntap_read(struct iss_net_private *lp, struct sk_buff **skb)
 {
-#if 0
-	*skb = ether_adjust_skb(*skb, ETH_HEADER_OTHER);
-	if (*skb == NULL)
-		return -ENOMEM;
-#endif
-
 	return simc_read(lp->tp.info.tuntap.fd,
 			(*skb)->data, (*skb)->dev->mtu + ETH_HEADER_OTHER);
 }
 
-static int tuntap_write (struct iss_net_private *lp, struct sk_buff **skb)
+static int tuntap_write(struct iss_net_private *lp, struct sk_buff **skb)
 {
 	return simc_write(lp->tp.info.tuntap.fd, (*skb)->data, (*skb)->len);
 }
@@ -253,45 +214,45 @@ static int tuntap_poll(struct iss_net_private *lp)
 }
 
 /*
- * Currently only a device name is supported.
- * ethX=tuntap[,[mac address][,[device name]]]
+ * ethX=tuntap,[mac address],device name
  */
 
 static int tuntap_probe(struct iss_net_private *lp, int index, char *init)
 {
-	const int len = strlen(TRANSPORT_TUNTAP_NAME);
+	struct net_device *dev = lp->dev;
 	char *dev_name = NULL, *mac_str = NULL, *rem = NULL;
 
 	/* Transport should be 'tuntap': ethX=tuntap,mac,dev_name */
 
-	if (strncmp(init, TRANSPORT_TUNTAP_NAME, len))
+	if (strncmp(init, TRANSPORT_TUNTAP_NAME,
+		    sizeof(TRANSPORT_TUNTAP_NAME) - 1))
 		return 0;
 
-	if (*(init += strlen(TRANSPORT_TUNTAP_NAME)) == ',') {
-		if ((rem=split_if_spec(init+1, &mac_str, &dev_name)) != NULL) {
-			printk("Extra garbage on specification : '%s'\n", rem);
+	init += sizeof(TRANSPORT_TUNTAP_NAME) - 1;
+	if (*init == ',') {
+		rem = split_if_spec(init + 1, &mac_str, &dev_name);
+		if (rem != NULL) {
+			pr_err("%s: extra garbage on specification : '%s'\n",
+			       dev->name, rem);
 			return 0;
 		}
 	} else if (*init != '\0') {
-		printk("Invalid argument: %s. Skipping device!\n", init);
+		pr_err("%s: invalid argument: %s. Skipping device!\n",
+		       dev->name, init);
 		return 0;
 	}
 
-	if (dev_name) {
-		strncpy(lp->tp.info.tuntap.dev_name, dev_name,
-			 sizeof lp->tp.info.tuntap.dev_name);
-		lp->tp.info.tuntap.fixed_config = 1;
-	} else
-		strcpy(lp->tp.info.tuntap.dev_name, TRANSPORT_TUNTAP_NAME);
+	if (!dev_name) {
+		pr_err("%s: missing tuntap device name\n", dev->name);
+		return 0;
+	}
 
+	strlcpy(lp->tp.info.tuntap.dev_name, dev_name,
+		sizeof(lp->tp.info.tuntap.dev_name));
 
-#if 0
-	if (setup_etheraddr(mac_str, lp->mac))
-		lp->have_mac = 1;
-#endif
-	lp->mtu = TRANSPORT_TUNTAP_MTU;
+	setup_etheraddr(dev, mac_str);
 
-	//lp->info.tuntap.gate_addr = gate_addr;
+	lp->mtu = TRANSPORT_TUNTAP_MTU;
 
 	lp->tp.info.tuntap.fd = -1;
 
@@ -302,13 +263,6 @@ static int tuntap_probe(struct iss_net_private *lp, int index, char *init)
 	lp->tp.protocol = tuntap_protocol;
 	lp->tp.poll = tuntap_poll;
 
-	printk("TUN/TAP backend - ");
-#if 0
-	if (lp->host.gate_addr != NULL)
-		printk("IP = %s", lp->host.gate_addr);
-#endif
-	printk("\n");
-
 	return 1;
 }
 
@@ -327,7 +281,8 @@ static int iss_net_rx(struct net_device *dev)
 
 	/* Try to allocate memory, if it fails, try again next round. */
 
-	if ((skb = dev_alloc_skb(dev->mtu + 2 + ETH_HEADER_OTHER)) == NULL) {
+	skb = dev_alloc_skb(dev->mtu + 2 + ETH_HEADER_OTHER);
+	if (skb == NULL) {
 		lp->stats.rx_dropped++;
 		return 0;
 	}
@@ -347,7 +302,6 @@ static int iss_net_rx(struct net_device *dev)
 
 		lp->stats.rx_bytes += skb->len;
 		lp->stats.rx_packets++;
-	//	netif_rx(skb);
 		netif_rx_ni(skb);
 		return pkt_len;
 	}
@@ -378,11 +332,11 @@ static int iss_net_poll(void)
 		spin_unlock(&lp->lock);
 
 		if (err < 0) {
-			printk(KERN_ERR "Device '%s' read returned %d, "
-			       "shutting it down\n", lp->dev->name, err);
+			pr_err("Device '%s' read returned %d, shutting it down\n",
+			       lp->dev->name, err);
 			dev_close(lp->dev);
 		} else {
-			// FIXME reactivate_fd(lp->fd, ISS_ETH_IRQ);
+			/* FIXME reactivate_fd(lp->fd, ISS_ETH_IRQ); */
 		}
 	}
 
@@ -393,14 +347,11 @@ static int iss_net_poll(void)
 
 static void iss_net_timer(unsigned long priv)
 {
-	struct iss_net_private* lp = (struct iss_net_private*) priv;
+	struct iss_net_private *lp = (struct iss_net_private *)priv;
 
 	spin_lock(&lp->lock);
-
 	iss_net_poll();
-
 	mod_timer(&lp->timer, jiffies + lp->timer_val);
-
 	spin_unlock(&lp->lock);
 }
 
@@ -408,19 +359,14 @@ static void iss_net_timer(unsigned long priv)
 static int iss_net_open(struct net_device *dev)
 {
 	struct iss_net_private *lp = netdev_priv(dev);
-	char addr[sizeof "255.255.255.255\0"];
 	int err;
 
 	spin_lock(&lp->lock);
 
-	if ((err = lp->tp.open(lp)) < 0)
+	err = lp->tp.open(lp);
+	if (err < 0)
 		goto out;
 
-	if (!lp->have_mac) {
-		dev_ip_addr(dev, addr, &lp->mac[2]);
-		set_ether_mac(dev, lp->mac);
-	}
-
 	netif_start_queue(dev);
 
 	/* clear buffer - it can happen that the host side of the interface
@@ -448,7 +394,6 @@ out:
 static int iss_net_close(struct net_device *dev)
 {
 	struct iss_net_private *lp = netdev_priv(dev);
-printk("iss_net_close!\n");
 	netif_stop_queue(dev);
 	spin_lock(&lp->lock);
 
@@ -490,7 +435,7 @@ static int iss_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	} else {
 		netif_start_queue(dev);
-		printk(KERN_ERR "iss_net_start_xmit: failed(%d)\n", len);
+		pr_err("%s: %s failed(%d)\n", dev->name, __func__, len);
 	}
 
 	spin_unlock_irqrestore(&lp->lock, flags);
@@ -508,56 +453,27 @@ static struct net_device_stats *iss_net_get_stats(struct net_device *dev)
 
 static void iss_net_set_multicast_list(struct net_device *dev)
 {
-#if 0
-	if (dev->flags & IFF_PROMISC)
-		return;
-	else if (!netdev_mc_empty(dev))
-		dev->flags |= IFF_ALLMULTI;
-	else
-		dev->flags &= ~IFF_ALLMULTI;
-#endif
 }
 
 static void iss_net_tx_timeout(struct net_device *dev)
 {
-#if 0
-	dev->trans_start = jiffies;
-	netif_wake_queue(dev);
-#endif
 }
 
 static int iss_net_set_mac(struct net_device *dev, void *addr)
 {
-#if 0
 	struct iss_net_private *lp = netdev_priv(dev);
 	struct sockaddr *hwaddr = addr;
 
+	if (!is_valid_ether_addr(hwaddr->sa_data))
+		return -EADDRNOTAVAIL;
 	spin_lock(&lp->lock);
 	memcpy(dev->dev_addr, hwaddr->sa_data, ETH_ALEN);
 	spin_unlock(&lp->lock);
-#endif
-
 	return 0;
 }
 
 static int iss_net_change_mtu(struct net_device *dev, int new_mtu)
 {
-#if 0
-	struct iss_net_private *lp = netdev_priv(dev);
-	int err = 0;
-
-	spin_lock(&lp->lock);
-
-	// FIXME not needed new_mtu = transport_set_mtu(new_mtu, &lp->user);
-
-	if (new_mtu < 0)
-		err = new_mtu;
-	else
-		dev->mtu = new_mtu;
-
-	spin_unlock(&lp->lock);
-	return err;
-#endif
 	return -EINVAL;
 }
 
@@ -582,7 +498,6 @@ static const struct net_device_ops iss_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= iss_net_change_mtu,
 	.ndo_set_mac_address	= iss_net_set_mac,
-	//.ndo_do_ioctl		= iss_net_ioctl,
 	.ndo_tx_timeout		= iss_net_tx_timeout,
 	.ndo_set_rx_mode	= iss_net_set_multicast_list,
 };
@@ -593,24 +508,29 @@ static int iss_net_configure(int index, char *init)
 	struct iss_net_private *lp;
 	int err;
 
-	if ((dev = alloc_etherdev(sizeof *lp)) == NULL) {
-		printk(KERN_ERR "eth_configure: failed to allocate device\n");
+	dev = alloc_etherdev(sizeof(*lp));
+	if (dev == NULL) {
+		pr_err("eth_configure: failed to allocate device\n");
 		return 1;
 	}
 
 	/* Initialize private element. */
 
 	lp = netdev_priv(dev);
-	*lp = ((struct iss_net_private) {
+	*lp = (struct iss_net_private) {
 		.device_list		= LIST_HEAD_INIT(lp->device_list),
 		.opened_list		= LIST_HEAD_INIT(lp->opened_list),
 		.lock			= __SPIN_LOCK_UNLOCKED(lp.lock),
 		.dev			= dev,
 		.index			= index,
-		//.fd                   = -1,
-		.mac			= { 0xfe, 0xfd, 0x0, 0x0, 0x0, 0x0 },
-		.have_mac		= 0,
-		});
+		};
+
+	/*
+	 * If this name ends up conflicting with an existing registered
+	 * netdevice, that is OK, register_netdev{,ice}() will notice this
+	 * and fail.
+	 */
+	snprintf(dev->name, sizeof(dev->name), "eth%d", index);
 
 	/*
 	 * Try all transport protocols.
@@ -618,14 +538,12 @@ static int iss_net_configure(int index, char *init)
 	 */
 
 	if (!tuntap_probe(lp, index, init)) {
-		printk("Invalid arguments. Skipping device!\n");
+		pr_err("%s: invalid arguments. Skipping device!\n",
+		       dev->name);
 		goto errout;
 	}
 
-	printk(KERN_INFO "Netdevice %d ", index);
-	if (lp->have_mac)
-		printk("(%pM) ", lp->mac);
-	printk(": ");
+	pr_info("Netdevice %d (%pM)\n", index, dev->dev_addr);
 
 	/* sysfs register */
 
@@ -641,14 +559,7 @@ static int iss_net_configure(int index, char *init)
 	lp->pdev.id = index;
 	lp->pdev.name = DRIVER_NAME;
 	platform_device_register(&lp->pdev);
-	SET_NETDEV_DEV(dev,&lp->pdev.dev);
-
-	/*
-	 * If this name ends up conflicting with an existing registered
-	 * netdevice, that is OK, register_netdev{,ice}() will notice this
-	 * and fail.
-	 */
-	snprintf(dev->name, sizeof dev->name, "eth%d", index);
+	SET_NETDEV_DEV(dev, &lp->pdev.dev);
 
 	dev->netdev_ops = &iss_netdev_ops;
 	dev->mtu = lp->mtu;
@@ -660,7 +571,7 @@ static int iss_net_configure(int index, char *init)
 	rtnl_unlock();
 
 	if (err) {
-		printk("Error registering net device!\n");
+		pr_err("%s: error registering net device!\n", dev->name);
 		/* XXX: should we call ->remove() here? */
 		free_netdev(dev);
 		return 1;
@@ -669,16 +580,11 @@ static int iss_net_configure(int index, char *init)
 	init_timer(&lp->tl);
 	lp->tl.function = iss_net_user_timer_expire;
 
-#if 0
-	if (lp->have_mac)
-		set_ether_mac(dev, lp->mac);
-#endif
 	return 0;
 
 errout:
-	// FIXME: unregister; free, etc..
+	/* FIXME: unregister; free, etc.. */
 	return -EIO;
-
 }
 
 /* ------------------------------------------------------------------------- */
@@ -706,21 +612,22 @@ static int __init iss_net_setup(char *str)
 	struct iss_net_init *new;
 	struct list_head *ele;
 	char *end;
-	int n;
+	int rc;
+	unsigned n;
 
-	n = simple_strtoul(str, &end, 0);
-	if (end == str) {
-		printk(ERR "Failed to parse '%s'\n", str);
-		return 1;
-	}
-	if (n < 0) {
-		printk(ERR "Device %d is negative\n", n);
+	end = strchr(str, '=');
+	if (!end) {
+		printk(ERR "Expected '=' after device number\n");
 		return 1;
 	}
-	if (*(str = end) != '=') {
-		printk(ERR "Expected '=' after device number\n");
+	*end = 0;
+	rc = kstrtouint(str, 0, &n);
+	*end = '=';
+	if (rc < 0) {
+		printk(ERR "Failed to parse '%s'\n", str);
 		return 1;
 	}
+	str = end;
 
 	spin_lock(&devices_lock);
 
@@ -733,13 +640,13 @@ static int __init iss_net_setup(char *str)
 	spin_unlock(&devices_lock);
 
 	if (device && device->index == n) {
-		printk(ERR "Device %d already configured\n", n);
+		printk(ERR "Device %u already configured\n", n);
 		return 1;
 	}
 
 	new = alloc_bootmem(sizeof(*new));
 	if (new == NULL) {
-		printk("Alloc_bootmem failed\n");
+		printk(ERR "Alloc_bootmem failed\n");
 		return 1;
 	}
 
@@ -753,7 +660,7 @@ static int __init iss_net_setup(char *str)
 
 #undef ERR
 
-__setup("eth=", iss_net_setup);
+__setup("eth", iss_net_setup);
 
 /*
  * Initialize all ISS Ethernet devices previously registered in iss_net_setup.
diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
index 4416773..aeb316b 100644
--- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
+++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
@@ -15,10 +15,6 @@
 #ifndef __XTENSA_XTAVNET_HARDWARE_H
 #define __XTENSA_XTAVNET_HARDWARE_H
 
-/* By default NO_IRQ is defined to 0 in Linux, but we use the
-   interrupt 0 for UART... */
-#define NO_IRQ                 -1
-
 /* Memory configuration. */
 
 #define PLATFORM_DEFAULT_MEM_START 0x00000000
@@ -30,7 +26,7 @@
 
 /* Default assignment of LX60 devices to external interrupts. */
 
-#ifdef CONFIG_ARCH_HAS_SMP
+#ifdef CONFIG_XTENSA_MX
 #define DUART16552_INTNUM	XCHAL_EXTINT3_NUM
 #define OETH_IRQ		XCHAL_EXTINT4_NUM
 #else
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 74bb74f..8002278 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -168,7 +168,7 @@ void __init platform_calibrate_ccount(void)
 	long clk_freq = 0;
 #ifdef CONFIG_OF
 	struct device_node *cpu =
-		of_find_compatible_node(NULL, NULL, "xtensa,cpu");
+		of_find_compatible_node(NULL, NULL, "cdns,xtensa-cpu");
 	if (cpu) {
 		u32 freq;
 		update_clock_frequency(cpu);
@@ -194,7 +194,7 @@ void __init platform_calibrate_ccount(void)
  *  Ethernet -- OpenCores Ethernet MAC (ethoc driver)
  */
 
-static struct resource ethoc_res[] __initdata = {
+static struct resource ethoc_res[] = {
 	[0] = { /* register space */
 		.start = OETH_REGS_PADDR,
 		.end   = OETH_REGS_PADDR + OETH_REGS_SIZE - 1,
@@ -212,7 +212,7 @@ static struct resource ethoc_res[] __initdata = {
 	},
 };
 
-static struct ethoc_platform_data ethoc_pdata __initdata = {
+static struct ethoc_platform_data ethoc_pdata = {
 	/*
 	 * The MAC address for these boards is 00:50:c2:13:6f:xx.
 	 * The last byte (here as zero) is read from the DIP switches on the
@@ -222,7 +222,7 @@ static struct ethoc_platform_data ethoc_pdata __initdata = {
 	.phy_id = -1,
 };
 
-static struct platform_device ethoc_device __initdata = {
+static struct platform_device ethoc_device = {
 	.name = "ethoc",
 	.id = -1,
 	.num_resources = ARRAY_SIZE(ethoc_res),
@@ -236,13 +236,13 @@ static struct platform_device ethoc_device __initdata = {
  *  UART
  */
 
-static struct resource serial_resource __initdata = {
+static struct resource serial_resource = {
 	.start	= DUART16552_PADDR,
 	.end	= DUART16552_PADDR + 0x1f,
 	.flags	= IORESOURCE_MEM,
 };
 
-static struct plat_serial8250_port serial_platform_data[] __initdata = {
+static struct plat_serial8250_port serial_platform_data[] = {
 	[0] = {
 		.mapbase	= DUART16552_PADDR,
 		.irq		= DUART16552_INTNUM,
@@ -255,7 +255,7 @@ static struct plat_serial8250_port serial_platform_data[] __initdata = {
 	{ },
 };
 
-static struct platform_device xtavnet_uart __initdata = {
+static struct platform_device xtavnet_uart = {
 	.name		= "serial8250",
 	.id		= PLAT8250_DEV_PLATFORM,
 	.dev		= {
diff --git a/arch/xtensa/variants/s6000/include/variant/irq.h b/arch/xtensa/variants/s6000/include/variant/irq.h
index 97d6fc4..39ca751a 100644
--- a/arch/xtensa/variants/s6000/include/variant/irq.h
+++ b/arch/xtensa/variants/s6000/include/variant/irq.h
@@ -1,7 +1,6 @@
 #ifndef _XTENSA_S6000_IRQ_H
 #define _XTENSA_S6000_IRQ_H
 
-#define NO_IRQ		(-1)
 #define VARIANT_NR_IRQS 8 /* GPIO interrupts */
 
 extern void variant_irq_enable(unsigned int irq);
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 940638d..61ffdca 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -65,3 +65,7 @@ config VERSATILE_FPGA_IRQ_NR
        int
        default 4
        depends on VERSATILE_FPGA_IRQ
+
+config XTENSA_MX
+	bool
+	select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 6427323..86b484c 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -23,3 +23,5 @@ obj-$(CONFIG_RENESAS_IRQC)		+= irq-renesas-irqc.o
 obj-$(CONFIG_VERSATILE_FPGA_IRQ)	+= irq-versatile-fpga.o
 obj-$(CONFIG_ARCH_VT8500)		+= irq-vt8500.o
 obj-$(CONFIG_TB10X_IRQC)		+= irq-tb10x.o
+obj-$(CONFIG_XTENSA)			+= irq-xtensa-pic.o
+obj-$(CONFIG_XTENSA_MX)			+= irq-xtensa-mx.o
diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c
new file mode 100644
index 0000000..f693f1b
--- /dev/null
+++ b/drivers/irqchip/irq-xtensa-mx.c
@@ -0,0 +1,164 @@
+/*
+ * Xtensa MX interrupt distributor
+ *
+ * Copyright (C) 2002 - 2013 Tensilica, Inc.
+ *
+ * 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.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+
+#include <asm/mxregs.h>
+
+#include "irqchip.h"
+
+#define HW_IRQ_IPI_COUNT 2
+#define HW_IRQ_MX_BASE 2
+#define HW_IRQ_EXTERN_BASE 3
+
+static DEFINE_PER_CPU(unsigned int, cached_irq_mask);
+
+static int xtensa_mx_irq_map(struct irq_domain *d, unsigned int irq,
+		irq_hw_number_t hw)
+{
+	if (hw < HW_IRQ_IPI_COUNT) {
+		struct irq_chip *irq_chip = d->host_data;
+		irq_set_chip_and_handler_name(irq, irq_chip,
+				handle_percpu_irq, "ipi");
+		irq_set_status_flags(irq, IRQ_LEVEL);
+		return 0;
+	}
+	return xtensa_irq_map(d, irq, hw);
+}
+
+/*
+ * Device Tree IRQ specifier translation function which works with one or
+ * two cell bindings. First cell value maps directly to the hwirq number.
+ * Second cell if present specifies whether hwirq number is external (1) or
+ * internal (0).
+ */
+static int xtensa_mx_irq_domain_xlate(struct irq_domain *d,
+		struct device_node *ctrlr,
+		const u32 *intspec, unsigned int intsize,
+		unsigned long *out_hwirq, unsigned int *out_type)
+{
+	return xtensa_irq_domain_xlate(intspec, intsize,
+			intspec[0], intspec[0] + HW_IRQ_EXTERN_BASE,
+			out_hwirq, out_type);
+}
+
+static const struct irq_domain_ops xtensa_mx_irq_domain_ops = {
+	.xlate = xtensa_mx_irq_domain_xlate,
+	.map = xtensa_mx_irq_map,
+};
+
+void secondary_init_irq(void)
+{
+	__this_cpu_write(cached_irq_mask,
+			XCHAL_INTTYPE_MASK_EXTERN_EDGE |
+			XCHAL_INTTYPE_MASK_EXTERN_LEVEL);
+	set_sr(XCHAL_INTTYPE_MASK_EXTERN_EDGE |
+			XCHAL_INTTYPE_MASK_EXTERN_LEVEL, intenable);
+}
+
+static void xtensa_mx_irq_mask(struct irq_data *d)
+{
+	unsigned int mask = 1u << d->hwirq;
+
+	if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE |
+				XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) {
+		set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) -
+					HW_IRQ_MX_BASE), MIENG);
+	} else {
+		mask = __this_cpu_read(cached_irq_mask) & ~mask;
+		__this_cpu_write(cached_irq_mask, mask);
+		set_sr(mask, intenable);
+	}
+}
+
+static void xtensa_mx_irq_unmask(struct irq_data *d)
+{
+	unsigned int mask = 1u << d->hwirq;
+
+	if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE |
+				XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) {
+		set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) -
+					HW_IRQ_MX_BASE), MIENGSET);
+	} else {
+		mask |= __this_cpu_read(cached_irq_mask);
+		__this_cpu_write(cached_irq_mask, mask);
+		set_sr(mask, intenable);
+	}
+}
+
+static void xtensa_mx_irq_enable(struct irq_data *d)
+{
+	variant_irq_enable(d->hwirq);
+	xtensa_mx_irq_unmask(d);
+}
+
+static void xtensa_mx_irq_disable(struct irq_data *d)
+{
+	xtensa_mx_irq_mask(d);
+	variant_irq_disable(d->hwirq);
+}
+
+static void xtensa_mx_irq_ack(struct irq_data *d)
+{
+	set_sr(1 << d->hwirq, intclear);
+}
+
+static int xtensa_mx_irq_retrigger(struct irq_data *d)
+{
+	set_sr(1 << d->hwirq, intset);
+	return 1;
+}
+
+static int xtensa_mx_irq_set_affinity(struct irq_data *d,
+		const struct cpumask *dest, bool force)
+{
+	unsigned mask = 1u << cpumask_any(dest);
+
+	set_er(mask, MIROUT(d->hwirq - HW_IRQ_MX_BASE));
+	return 0;
+
+}
+
+static struct irq_chip xtensa_mx_irq_chip = {
+	.name		= "xtensa-mx",
+	.irq_enable	= xtensa_mx_irq_enable,
+	.irq_disable	= xtensa_mx_irq_disable,
+	.irq_mask	= xtensa_mx_irq_mask,
+	.irq_unmask	= xtensa_mx_irq_unmask,
+	.irq_ack	= xtensa_mx_irq_ack,
+	.irq_retrigger	= xtensa_mx_irq_retrigger,
+	.irq_set_affinity = xtensa_mx_irq_set_affinity,
+};
+
+int __init xtensa_mx_init_legacy(struct device_node *interrupt_parent)
+{
+	struct irq_domain *root_domain =
+		irq_domain_add_legacy(NULL, NR_IRQS, 0, 0,
+				&xtensa_mx_irq_domain_ops,
+				&xtensa_mx_irq_chip);
+	irq_set_default_host(root_domain);
+	secondary_init_irq();
+	return 0;
+}
+
+static int __init xtensa_mx_init(struct device_node *np,
+		struct device_node *interrupt_parent)
+{
+	struct irq_domain *root_domain =
+		irq_domain_add_linear(np, NR_IRQS, &xtensa_mx_irq_domain_ops,
+				&xtensa_mx_irq_chip);
+	irq_set_default_host(root_domain);
+	secondary_init_irq();
+	return 0;
+}
+IRQCHIP_DECLARE(xtensa_mx_irq_chip, "cdns,xtensa-mx", xtensa_mx_init);
diff --git a/drivers/irqchip/irq-xtensa-pic.c b/drivers/irqchip/irq-xtensa-pic.c
new file mode 100644
index 0000000..7d71126
--- /dev/null
+++ b/drivers/irqchip/irq-xtensa-pic.c
@@ -0,0 +1,108 @@
+/*
+ * Xtensa built-in interrupt controller
+ *
+ * Copyright (C) 2002 - 2013 Tensilica, Inc.
+ * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
+ *
+ * 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.
+ *
+ * Chris Zankel <chris@zankel.net>
+ * Kevin Chea
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+
+#include "irqchip.h"
+
+unsigned int cached_irq_mask;
+
+/*
+ * Device Tree IRQ specifier translation function which works with one or
+ * two cell bindings. First cell value maps directly to the hwirq number.
+ * Second cell if present specifies whether hwirq number is external (1) or
+ * internal (0).
+ */
+static int xtensa_pic_irq_domain_xlate(struct irq_domain *d,
+		struct device_node *ctrlr,
+		const u32 *intspec, unsigned int intsize,
+		unsigned long *out_hwirq, unsigned int *out_type)
+{
+	return xtensa_irq_domain_xlate(intspec, intsize,
+			intspec[0], intspec[0],
+			out_hwirq, out_type);
+}
+
+static const struct irq_domain_ops xtensa_irq_domain_ops = {
+	.xlate = xtensa_pic_irq_domain_xlate,
+	.map = xtensa_irq_map,
+};
+
+static void xtensa_irq_mask(struct irq_data *d)
+{
+	cached_irq_mask &= ~(1 << d->hwirq);
+	set_sr(cached_irq_mask, intenable);
+}
+
+static void xtensa_irq_unmask(struct irq_data *d)
+{
+	cached_irq_mask |= 1 << d->hwirq;
+	set_sr(cached_irq_mask, intenable);
+}
+
+static void xtensa_irq_enable(struct irq_data *d)
+{
+	variant_irq_enable(d->hwirq);
+	xtensa_irq_unmask(d);
+}
+
+static void xtensa_irq_disable(struct irq_data *d)
+{
+	xtensa_irq_mask(d);
+	variant_irq_disable(d->hwirq);
+}
+
+static void xtensa_irq_ack(struct irq_data *d)
+{
+	set_sr(1 << d->hwirq, intclear);
+}
+
+static int xtensa_irq_retrigger(struct irq_data *d)
+{
+	set_sr(1 << d->hwirq, intset);
+	return 1;
+}
+
+static struct irq_chip xtensa_irq_chip = {
+	.name		= "xtensa",
+	.irq_enable	= xtensa_irq_enable,
+	.irq_disable	= xtensa_irq_disable,
+	.irq_mask	= xtensa_irq_mask,
+	.irq_unmask	= xtensa_irq_unmask,
+	.irq_ack	= xtensa_irq_ack,
+	.irq_retrigger	= xtensa_irq_retrigger,
+};
+
+int __init xtensa_pic_init_legacy(struct device_node *interrupt_parent)
+{
+	struct irq_domain *root_domain =
+		irq_domain_add_legacy(NULL, NR_IRQS, 0, 0,
+				&xtensa_irq_domain_ops, &xtensa_irq_chip);
+	irq_set_default_host(root_domain);
+	return 0;
+}
+
+static int __init xtensa_pic_init(struct device_node *np,
+		struct device_node *interrupt_parent)
+{
+	struct irq_domain *root_domain =
+		irq_domain_add_linear(np, NR_IRQS, &xtensa_irq_domain_ops,
+				&xtensa_irq_chip);
+	irq_set_default_host(root_domain);
+	return 0;
+}
+IRQCHIP_DECLARE(xtensa_irq_chip, "cdns,xtensa-pic", xtensa_pic_init);
diff --git a/include/linux/irqchip/xtensa-mx.h b/include/linux/irqchip/xtensa-mx.h
new file mode 100644
index 0000000..9c3b6ec
--- /dev/null
+++ b/include/linux/irqchip/xtensa-mx.h
@@ -0,0 +1,17 @@
+/*
+ * Xtensa MX interrupt distributor
+ *
+ * Copyright (C) 2002 - 2013 Tensilica, Inc.
+ *
+ * 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 __LINUX_IRQCHIP_XTENSA_MX_H
+#define __LINUX_IRQCHIP_XTENSA_MX_H
+
+struct device_node;
+int xtensa_mx_init_legacy(struct device_node *interrupt_parent);
+
+#endif /* __LINUX_IRQCHIP_XTENSA_MX_H */
diff --git a/include/linux/irqchip/xtensa-pic.h b/include/linux/irqchip/xtensa-pic.h
new file mode 100644
index 0000000..48718ae
--- /dev/null
+++ b/include/linux/irqchip/xtensa-pic.h
@@ -0,0 +1,18 @@
+/*
+ * Xtensa built-in interrupt controller
+ *
+ * Copyright (C) 2002 - 2013 Tensilica, Inc.
+ * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
+ *
+ * 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 __LINUX_IRQCHIP_XTENSA_PIC_H
+#define __LINUX_IRQCHIP_XTENSA_PIC_H
+
+struct device_node;
+int xtensa_pic_init_legacy(struct device_node *interrupt_parent);
+
+#endif /* __LINUX_IRQCHIP_XTENSA_PIC_H */