Merge branch 'mti-next' of git://git.linux-mips.org/pub/scm/sjhill/linux-sjhill into mips-for-linux-next

17 files changed, 2029 insertions, 333 deletions

diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index cdb87b2a423d..cb96ace5c8c5 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -19,15 +19,16 @@ obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
 obj-$(CONFIG_CEVT_R4K)		+= cevt-r4k.o
 obj-$(CONFIG_MIPS_MT_SMTC)	+= cevt-smtc.o
 obj-$(CONFIG_CEVT_DS1287)	+= cevt-ds1287.o
+obj-$(CONFIG_CEVT_GIC)		+= cevt-gic.o
 obj-$(CONFIG_CEVT_GT641XX)	+= cevt-gt641xx.o
 obj-$(CONFIG_CEVT_SB1250)	+= cevt-sb1250.o
 obj-$(CONFIG_CEVT_TXX9)		+= cevt-txx9.o
 obj-$(CONFIG_CSRC_BCM1480)	+= csrc-bcm1480.o
+obj-$(CONFIG_CSRC_GIC)		+= csrc-gic.o
 obj-$(CONFIG_CSRC_IOASIC)	+= csrc-ioasic.o
 obj-$(CONFIG_CSRC_POWERTV)	+= csrc-powertv.o
 obj-$(CONFIG_CSRC_R4K)		+= csrc-r4k.o
 obj-$(CONFIG_CSRC_SB1250)	+= csrc-sb1250.o
-obj-$(CONFIG_CSRC_GIC)		+= csrc-gic.o
 obj-$(CONFIG_SYNC_R4K)		+= sync-r4k.o
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 83ffe950f710..46c2ad0703a0 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -14,10 +14,186 @@
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
 #include <asm/fpu.h>
+#include <asm/fpu_emulator.h>
 #include <asm/inst.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 
+/*
+ * Calculate and return exception PC in case of branch delay slot
+ * for microMIPS and MIPS16e. It does not clear the ISA mode bit.
+ */
+int __isa_exception_epc(struct pt_regs *regs)
+{
+	unsigned short inst;
+	long epc = regs->cp0_epc;
+
+	/* Calculate exception PC in branch delay slot. */
+	if (__get_user(inst, (u16 __user *) msk_isa16_mode(epc))) {
+		/* This should never happen because delay slot was checked. */
+		force_sig(SIGSEGV, current);
+		return epc;
+	}
+	if (cpu_has_mips16) {
+		if (((union mips16e_instruction)inst).ri.opcode
+				== MIPS16e_jal_op)
+			epc += 4;
+		else
+			epc += 2;
+	} else if (mm_insn_16bit(inst))
+		epc += 2;
+	else
+		epc += 4;
+
+	return epc;
+}
+
+/*
+ * Compute return address and emulate branch in microMIPS mode after an
+ * exception only. It does not handle compact branches/jumps and cannot
+ * be used in interrupt context. (Compact branches/jumps do not cause
+ * exceptions.)
+ */
+int __microMIPS_compute_return_epc(struct pt_regs *regs)
+{
+	u16 __user *pc16;
+	u16 halfword;
+	unsigned int word;
+	unsigned long contpc;
+	struct mm_decoded_insn mminsn = { 0 };
+
+	mminsn.micro_mips_mode = 1;
+
+	/* This load never faults. */
+	pc16 = (unsigned short __user *)msk_isa16_mode(regs->cp0_epc);
+	__get_user(halfword, pc16);
+	pc16++;
+	contpc = regs->cp0_epc + 2;
+	word = ((unsigned int)halfword << 16);
+	mminsn.pc_inc = 2;
+
+	if (!mm_insn_16bit(halfword)) {
+		__get_user(halfword, pc16);
+		pc16++;
+		contpc = regs->cp0_epc + 4;
+		mminsn.pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.insn = word;
+
+	if (get_user(halfword, pc16))
+		goto sigsegv;
+	mminsn.next_pc_inc = 2;
+	word = ((unsigned int)halfword << 16);
+
+	if (!mm_insn_16bit(halfword)) {
+		pc16++;
+		if (get_user(halfword, pc16))
+			goto sigsegv;
+		mminsn.next_pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.next_insn = word;
+
+	mm_isBranchInstr(regs, mminsn, &contpc);
+
+	regs->cp0_epc = contpc;
+
+	return 0;
+
+sigsegv:
+	force_sig(SIGSEGV, current);
+	return -EFAULT;
+}
+
+/*
+ * Compute return address and emulate branch in MIPS16e mode after an
+ * exception only. It does not handle compact branches/jumps and cannot
+ * be used in interrupt context. (Compact branches/jumps do not cause
+ * exceptions.)
+ */
+int __MIPS16e_compute_return_epc(struct pt_regs *regs)
+{
+	u16 __user *addr;
+	union mips16e_instruction inst;
+	u16 inst2;
+	u32 fullinst;
+	long epc;
+
+	epc = regs->cp0_epc;
+
+	/* Read the instruction. */
+	addr = (u16 __user *)msk_isa16_mode(epc);
+	if (__get_user(inst.full, addr)) {
+		force_sig(SIGSEGV, current);
+		return -EFAULT;
+	}
+
+	switch (inst.ri.opcode) {
+	case MIPS16e_extend_op:
+		regs->cp0_epc += 4;
+		return 0;
+
+		/*
+		 *  JAL and JALX in MIPS16e mode
+		 */
+	case MIPS16e_jal_op:
+		addr += 1;
+		if (__get_user(inst2, addr)) {
+			force_sig(SIGSEGV, current);
+			return -EFAULT;
+		}
+		fullinst = ((unsigned)inst.full << 16) | inst2;
+		regs->regs[31] = epc + 6;
+		epc += 4;
+		epc >>= 28;
+		epc <<= 28;
+		/*
+		 * JAL:5 X:1 TARGET[20-16]:5 TARGET[25:21]:5 TARGET[15:0]:16
+		 *
+		 * ......TARGET[15:0].................TARGET[20:16]...........
+		 * ......TARGET[25:21]
+		 */
+		epc |=
+		    ((fullinst & 0xffff) << 2) | ((fullinst & 0x3e00000) >> 3) |
+		    ((fullinst & 0x1f0000) << 7);
+		if (!inst.jal.x)
+			set_isa16_mode(epc);	/* Set ISA mode bit. */
+		regs->cp0_epc = epc;
+		return 0;
+
+		/*
+		 *  J(AL)R(C)
+		 */
+	case MIPS16e_rr_op:
+		if (inst.rr.func == MIPS16e_jr_func) {
+
+			if (inst.rr.ra)
+				regs->cp0_epc = regs->regs[31];
+			else
+				regs->cp0_epc =
+				    regs->regs[reg16to32[inst.rr.rx]];
+
+			if (inst.rr.l) {
+				if (inst.rr.nd)
+					regs->regs[31] = epc + 2;
+				else
+					regs->regs[31] = epc + 4;
+			}
+			return 0;
+		}
+		break;
+	}
+
+	/*
+	 * All other cases have no branch delay slot and are 16-bits.
+	 * Branches do not cause an exception.
+	 */
+	regs->cp0_epc += 2;
+
+	return 0;
+}
+
 /**
  * __compute_return_epc_for_insn - Computes the return address and do emulate
  *				    branch simulation, if required.
@@ -129,6 +305,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		epc <<= 28;
 		epc |= (insn.j_format.target << 2);
 		regs->cp0_epc = epc;
+		if (insn.i_format.opcode == jalx_op)
+			set_isa16_mode(regs->cp0_epc);
 		break;
 
 	/*
diff --git a/arch/mips/kernel/cevt-gic.c b/arch/mips/kernel/cevt-gic.c
new file mode 100644
index 000000000000..730eaf92c018
--- /dev/null
+++ b/arch/mips/kernel/cevt-gic.c
@@ -0,0 +1,104 @@
+/*
+ * 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) 2013  Imagination Technologies Ltd.
+ */
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+
+#include <asm/time.h>
+#include <asm/gic.h>
+#include <asm/mips-boards/maltaint.h>
+
+DEFINE_PER_CPU(struct clock_event_device, gic_clockevent_device);
+int gic_timer_irq_installed;
+
+
+static int gic_next_event(unsigned long delta, struct clock_event_device *evt)
+{
+	u64 cnt;
+	int res;
+
+	cnt = gic_read_count();
+	cnt += (u64)delta;
+	gic_write_compare(cnt);
+	res = ((int)(gic_read_count() - cnt) >= 0) ? -ETIME : 0;
+	return res;
+}
+
+void gic_set_clock_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt)
+{
+	/* Nothing to do ...  */
+}
+
+irqreturn_t gic_compare_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *cd;
+	int cpu = smp_processor_id();
+
+	gic_write_compare(gic_read_compare());
+	cd = &per_cpu(gic_clockevent_device, cpu);
+	cd->event_handler(cd);
+	return IRQ_HANDLED;
+}
+
+struct irqaction gic_compare_irqaction = {
+	.handler = gic_compare_interrupt,
+	.flags = IRQF_PERCPU | IRQF_TIMER,
+	.name = "timer",
+};
+
+
+void gic_event_handler(struct clock_event_device *dev)
+{
+}
+
+int __cpuinit gic_clockevent_init(void)
+{
+	unsigned int cpu = smp_processor_id();
+	struct clock_event_device *cd;
+	unsigned int irq;
+
+	if (!cpu_has_counter || !gic_frequency)
+		return -ENXIO;
+
+	irq = MIPS_GIC_IRQ_BASE;
+
+	cd = &per_cpu(gic_clockevent_device, cpu);
+
+	cd->name		= "MIPS GIC";
+	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
+
+	clockevent_set_clock(cd, gic_frequency);
+
+	/* Calculate the min / max delta */
+	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
+	cd->min_delta_ns	= clockevent_delta2ns(0x300, cd);
+
+	cd->rating		= 300;
+	cd->irq			= irq;
+	cd->cpumask		= cpumask_of(cpu);
+	cd->set_next_event	= gic_next_event;
+	cd->set_mode		= gic_set_clock_mode;
+	cd->event_handler	= gic_event_handler;
+
+	clockevents_register_device(cd);
+
+	GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE_MAP), 0x80000002);
+	GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_SMASK), GIC_VPE_SMASK_CMP_MSK);
+
+	if (gic_timer_irq_installed)
+		return 0;
+
+	gic_timer_irq_installed = 1;
+
+	setup_irq(irq, &gic_compare_irqaction);
+	irq_set_handler(irq, handle_percpu_irq);
+	return 0;
+}
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index fd75d7144524..02033eaf8825 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -23,7 +23,6 @@
  */
 
 #ifndef CONFIG_MIPS_MT_SMTC
-
 static int mips_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
 {
@@ -49,7 +48,6 @@ DEFINE_PER_CPU(struct clock_event_device, mips_clockevent_device);
 int cp0_timer_irq_installed;
 
 #ifndef CONFIG_MIPS_MT_SMTC
-
 irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
 {
 	const int r2 = cpu_has_mips_r2;
@@ -74,6 +72,9 @@ irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
 		/* Clear Count/Compare Interrupt */
 		write_c0_compare(read_c0_compare());
 		cd = &per_cpu(mips_clockevent_device, cpu);
+#ifdef CONFIG_CEVT_GIC
+		if (!gic_present)
+#endif
 		cd->event_handler(cd);
 	}
 
@@ -170,7 +171,6 @@ int c0_compare_int_usable(void)
 }
 
 #ifndef CONFIG_MIPS_MT_SMTC
-
 int __cpuinit r4k_clockevent_init(void)
 {
 	unsigned int cpu = smp_processor_id();
@@ -210,6 +210,9 @@ int __cpuinit r4k_clockevent_init(void)
 	cd->set_mode		= mips_set_clock_mode;
 	cd->event_handler	= mips_event_handler;
 
+#ifdef CONFIG_CEVT_GIC
+	if (!gic_present)
+#endif
 	clockevents_register_device(cd);
 
 	if (cp0_timer_irq_installed)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 5fe66a0c3224..4bbffdb9024f 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -470,6 +470,9 @@ static inline unsigned int decode_config3(struct cpuinfo_mips *c)
 		c->options |= MIPS_CPU_ULRI;
 	if (config3 & MIPS_CONF3_ISA)
 		c->options |= MIPS_CPU_MICROMIPS;
+#ifdef CONFIG_CPU_MICROMIPS
+	write_c0_config3(read_c0_config3() | MIPS_CONF3_ISA_OE);
+#endif
 	if (config3 & MIPS_CONF3_VZ)
 		c->ases |= MIPS_ASE_VZ;
 
diff --git a/arch/mips/kernel/csrc-gic.c b/arch/mips/kernel/csrc-gic.c
index 5dca24bce51b..e02620901117 100644
--- a/arch/mips/kernel/csrc-gic.c
+++ b/arch/mips/kernel/csrc-gic.c
@@ -5,23 +5,14 @@
  *
  * Copyright (C) 2012 MIPS Technologies, Inc.  All rights reserved.
  */
-#include <linux/clocksource.h>
 #include <linux/init.h>
+#include <linux/time.h>
 
-#include <asm/time.h>
 #include <asm/gic.h>
 
 static cycle_t gic_hpt_read(struct clocksource *cs)
 {
-	unsigned int hi, hi2, lo;
-
-	do {
-		GICREAD(GIC_REG(SHARED, GIC_SH_COUNTER_63_32), hi);
-		GICREAD(GIC_REG(SHARED, GIC_SH_COUNTER_31_00), lo);
-		GICREAD(GIC_REG(SHARED, GIC_SH_COUNTER_63_32), hi2);
-	} while (hi2 != hi);
-
-	return (((cycle_t) hi) << 32) + lo;
+	return gic_read_count();
 }
 
 static struct clocksource gic_clocksource = {
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index ecb347ce1b3d..5c2ba9f08a80 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -5,8 +5,8 @@
  *
  * Copyright (C) 1994 - 2000, 2001, 2003 Ralf Baechle
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
- * Copyright (C) 2001 MIPS Technologies, Inc.
  * Copyright (C) 2002, 2007  Maciej W. Rozycki
+ * Copyright (C) 2001, 2012 MIPS Technologies, Inc.  All rights reserved.
  */
 #include <linux/init.h>
 
@@ -21,8 +21,10 @@
 #include <asm/war.h>
 #include <asm/thread_info.h>
 
+#ifdef CONFIG_MIPS_MT_SMTC
 #define PANIC_PIC(msg)					\
-		.set push;				\
+		.set	push;				\
+		.set	nomicromips;			\
 		.set	reorder;			\
 		PTR_LA	a0,8f;				\
 		.set	noat;				\
@@ -31,17 +33,10 @@
 9:		b	9b;				\
 		.set	pop;				\
 		TEXT(msg)
+#endif
 
 	__INIT
 
-NESTED(except_vec0_generic, 0, sp)
-	PANIC_PIC("Exception vector 0 called")
-	END(except_vec0_generic)
-
-NESTED(except_vec1_generic, 0, sp)
-	PANIC_PIC("Exception vector 1 called")
-	END(except_vec1_generic)
-
 /*
  * General exception vector for all other CPUs.
  *
@@ -138,12 +133,19 @@ LEAF(r4k_wait)
 	 nop
 	nop
 	nop
+#ifdef CONFIG_CPU_MICROMIPS
+	nop
+	nop
+	nop
+	nop
+#endif
 	.set	mips3
 	wait
 	/* end of rollback region (the region size must be power of two) */
-	.set	pop
 1:
 	jr	ra
+	nop
+	.set	pop
 	END(r4k_wait)
 
 	.macro	BUILD_ROLLBACK_PROLOGUE handler
@@ -201,7 +203,11 @@ NESTED(handle_int, PT_SIZE, sp)
 	LONG_L	s0, TI_REGS($28)
 	LONG_S	sp, TI_REGS($28)
 	PTR_LA	ra, ret_from_irq
-	j	plat_irq_dispatch
+	PTR_LA  v0, plat_irq_dispatch
+	jr	v0
+#ifdef CONFIG_CPU_MICROMIPS
+	nop
+#endif
 	END(handle_int)
 
 	__INIT
@@ -222,11 +228,14 @@ NESTED(except_vec4, 0, sp)
 /*
  * EJTAG debug exception handler.
  * The EJTAG debug exception entry point is 0xbfc00480, which
- * normally is in the boot PROM, so the boot PROM must do a
+ * normally is in the boot PROM, so the boot PROM must do an
  * unconditional jump to this vector.
  */
 NESTED(except_vec_ejtag_debug, 0, sp)
 	j	ejtag_debug_handler
+#ifdef CONFIG_CPU_MICROMIPS
+	 nop
+#endif
 	END(except_vec_ejtag_debug)
 
 	__FINIT
@@ -251,9 +260,10 @@ NESTED(except_vec_vi, 0, sp)
 FEXPORT(except_vec_vi_mori)
 	ori	a0, $0, 0
 #endif /* CONFIG_MIPS_MT_SMTC */
+	PTR_LA	v1, except_vec_vi_handler
 FEXPORT(except_vec_vi_lui)
 	lui	v0, 0		/* Patched */
-	j	except_vec_vi_handler
+	jr	v1
 FEXPORT(except_vec_vi_ori)
 	 ori	v0, 0		/* Patched */
 	.set	pop
@@ -354,6 +364,9 @@ EXPORT(ejtag_debug_buffer)
  */
 NESTED(except_vec_nmi, 0, sp)
 	j	nmi_handler
+#ifdef CONFIG_CPU_MICROMIPS
+	 nop
+#endif
 	END(except_vec_nmi)
 
 	__FINIT
@@ -480,7 +493,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	noreorder
 	/* check if TLB contains a entry for EPC */
 	MFC0	k1, CP0_ENTRYHI
-	andi	k1, 0xff	/* ASID_MASK */
+	andi	k1, 0xff	/* ASID_MASK patched at run-time!! */
 	MFC0	k0, CP0_EPC
 	PTR_SRL k0, _PAGE_SHIFT + 1
 	PTR_SLL k0, _PAGE_SHIFT + 1
@@ -500,13 +513,35 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	push
 	.set	noat
 	.set	noreorder
-	/* 0x7c03e83b: rdhwr v1,$29 */
+	/* MIPS32:    0x7c03e83b: rdhwr v1,$29 */
+	/* microMIPS: 0x007d6b3c: rdhwr v1,$29 */
 	MFC0	k1, CP0_EPC
-	lui	k0, 0x7c03
-	lw	k1, (k1)
-	ori	k0, 0xe83b
-	.set	reorder
+#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS64_R2)
+	and     k0, k1, 1
+	beqz    k0, 1f
+	xor     k1, k0
+	lhu     k0, (k1)
+	lhu     k1, 2(k1)
+	ins     k1, k0, 16, 16
+	lui     k0, 0x007d
+	b       docheck
+	ori     k0, 0x6b3c
+1:
+	lui     k0, 0x7c03
+	lw      k1, (k1)
+	ori     k0, 0xe83b
+#else
+	andi    k0, k1, 1
+	bnez    k0, handle_ri
+	lui     k0, 0x7c03
+	lw      k1, (k1)
+	ori     k0, 0xe83b
+#endif
+	.set    reorder
+docheck:
 	bne	k0, k1, handle_ri	/* if not ours */
+
+isrdhwr:
 	/* The insn is rdhwr.  No need to check CAUSE.BD here. */
 	get_saved_sp	/* k1 := current_thread_info */
 	.set	noreorder
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 485e6a961b31..c01b307317a9 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
+#include <linux/clocksource.h>
 
 #include <asm/io.h>
 #include <asm/gic.h>
@@ -19,6 +20,8 @@
 #include <linux/hardirq.h>
 #include <asm-generic/bitops/find.h>
 
+unsigned int gic_frequency;
+unsigned int gic_present;
 unsigned long _gic_base;
 unsigned int gic_irq_base;
 unsigned int gic_irq_flags[GIC_NUM_INTRS];
@@ -30,6 +33,39 @@ static struct gic_pcpu_mask pcpu_masks[NR_CPUS];
 static struct gic_pending_regs pending_regs[NR_CPUS];
 static struct gic_intrmask_regs intrmask_regs[NR_CPUS];
 
+#if defined(CONFIG_CSRC_GIC) || defined(CONFIG_CEVT_GIC)
+cycle_t gic_read_count(void)
+{
+	unsigned int hi, hi2, lo;
+
+	do {
+		GICREAD(GIC_REG(SHARED, GIC_SH_COUNTER_63_32), hi);
+		GICREAD(GIC_REG(SHARED, GIC_SH_COUNTER_31_00), lo);
+		GICREAD(GIC_REG(SHARED, GIC_SH_COUNTER_63_32), hi2);
+	} while (hi2 != hi);
+
+	return (((cycle_t) hi) << 32) + lo;
+}
+
+void gic_write_compare(cycle_t cnt)
+{
+	GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE_HI),
+				(int)(cnt >> 32));
+	GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE_LO),
+				(int)(cnt & 0xffffffff));
+}
+
+cycle_t gic_read_compare(void)
+{
+	unsigned int hi, lo;
+
+	GICREAD(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE_HI), hi);
+	GICREAD(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE_LO), lo);
+
+	return (((cycle_t) hi) << 32) + lo;
+}
+#endif
+
 unsigned int gic_get_timer_pending(void)
 {
 	unsigned int vpe_pending;
@@ -116,6 +152,17 @@ static void __init vpe_local_setup(unsigned int numvpes)
 	}
 }
 
+unsigned int gic_compare_int(void)
+{
+	unsigned int pending;
+
+	GICREAD(GIC_REG(VPE_LOCAL, GIC_VPE_PEND), pending);
+	if (pending & GIC_VPE_PEND_CMP_MSK)
+		return 1;
+	else
+		return 0;
+}
+
 unsigned int gic_get_int(void)
 {
 	unsigned int i;
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 1dd137bab5c5..a3e461408b7e 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -99,6 +99,10 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (cpu_has_vz)		seq_printf(m, "%s", " vz");
 	seq_printf(m, "\n");
 
+	if (cpu_has_mmips) {
+		seq_printf(m, "micromips kernel\t: %s\n",
+		      (read_c0_config3() & MIPS_CONF3_ISA_OE) ?  "yes" : "no");
+	}
 	seq_printf(m, "shadow register sets\t: %d\n",
 		      cpu_data[n].srsets);
 	seq_printf(m, "kscratch registers\t: %d\n",
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 3be4405c2d14..ef533760d2c8 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2005, 2006 by Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
  * Copyright (C) 2004 Thiemo Seufer
+ * Copyright (C) 2013  Imagination Technologies Ltd.
  */
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -243,34 +244,115 @@ struct mips_frame_info {
 
 static inline int is_ra_save_ins(union mips_instruction *ip)
 {
+#ifdef CONFIG_CPU_MICROMIPS
+	union mips_instruction mmi;
+
+	/*
+	 * swsp ra,offset
+	 * swm16 reglist,offset(sp)
+	 * swm32 reglist,offset(sp)
+	 * sw32 ra,offset(sp)
+	 * jradiussp - NOT SUPPORTED
+	 *
+	 * microMIPS is way more fun...
+	 */
+	if (mm_insn_16bit(ip->halfword[0])) {
+		mmi.word = (ip->halfword[0] << 16);
+		return ((mmi.mm16_r5_format.opcode == mm_swsp16_op &&
+			 mmi.mm16_r5_format.rt == 31) ||
+			(mmi.mm16_m_format.opcode == mm_pool16c_op &&
+			 mmi.mm16_m_format.func == mm_swm16_op));
+	}
+	else {
+		mmi.halfword[0] = ip->halfword[1];
+		mmi.halfword[1] = ip->halfword[0];
+		return ((mmi.mm_m_format.opcode == mm_pool32b_op &&
+			 mmi.mm_m_format.rd > 9 &&
+			 mmi.mm_m_format.base == 29 &&
+			 mmi.mm_m_format.func == mm_swm32_func) ||
+			(mmi.i_format.opcode == mm_sw32_op &&
+			 mmi.i_format.rs == 29 &&
+			 mmi.i_format.rt == 31));
+	}
+#else
 	/* sw / sd $ra, offset($sp) */
 	return (ip->i_format.opcode == sw_op || ip->i_format.opcode == sd_op) &&
 		ip->i_format.rs == 29 &&
 		ip->i_format.rt == 31;
+#endif
 }
 
 static inline int is_jal_jalr_jr_ins(union mips_instruction *ip)
 {
+#ifdef CONFIG_CPU_MICROMIPS
+	/*
+	 * jr16,jrc,jalr16,jalr16
+	 * jal
+	 * jalr/jr,jalr.hb/jr.hb,jalrs,jalrs.hb
+	 * jraddiusp - NOT SUPPORTED
+	 *
+	 * microMIPS is kind of more fun...
+	 */
+	union mips_instruction mmi;
+
+	mmi.word = (ip->halfword[0] << 16);
+
+	if ((mmi.mm16_r5_format.opcode == mm_pool16c_op &&
+	    (mmi.mm16_r5_format.rt & mm_jr16_op) == mm_jr16_op) ||
+	    ip->j_format.opcode == mm_jal32_op)
+		return 1;
+	if (ip->r_format.opcode != mm_pool32a_op ||
+			ip->r_format.func != mm_pool32axf_op)
+		return 0;
+	return (((ip->u_format.uimmediate >> 6) & mm_jalr_op) == mm_jalr_op);
+#else
 	if (ip->j_format.opcode == jal_op)
 		return 1;
 	if (ip->r_format.opcode != spec_op)
 		return 0;
 	return ip->r_format.func == jalr_op || ip->r_format.func == jr_op;
+#endif
 }
 
 static inline int is_sp_move_ins(union mips_instruction *ip)
 {
+#ifdef CONFIG_CPU_MICROMIPS
+	/*
+	 * addiusp -imm
+	 * addius5 sp,-imm
+	 * addiu32 sp,sp,-imm
+	 * jradiussp - NOT SUPPORTED
+	 *
+	 * microMIPS is not more fun...
+	 */
+	if (mm_insn_16bit(ip->halfword[0])) {
+		union mips_instruction mmi;
+
+		mmi.word = (ip->halfword[0] << 16);
+		return ((mmi.mm16_r3_format.opcode == mm_pool16d_op &&
+			 mmi.mm16_r3_format.simmediate && mm_addiusp_func) ||
+			(mmi.mm16_r5_format.opcode == mm_pool16d_op &&
+			 mmi.mm16_r5_format.rt == 29));
+	}
+	return (ip->mm_i_format.opcode == mm_addiu32_op &&
+		 ip->mm_i_format.rt == 29 && ip->mm_i_format.rs == 29);
+#else
 	/* addiu/daddiu sp,sp,-imm */
 	if (ip->i_format.rs != 29 || ip->i_format.rt != 29)
 		return 0;
 	if (ip->i_format.opcode == addiu_op || ip->i_format.opcode == daddiu_op)
 		return 1;
+#endif
 	return 0;
 }
 
 static int get_frame_info(struct mips_frame_info *info)
 {
+#ifdef CONFIG_CPU_MICROMIPS
+	union mips_instruction *ip = (void *) (((char *) info->func) - 1);
+#else
 	union mips_instruction *ip = info->func;
+#endif
 	unsigned max_insns = info->func_size / sizeof(union mips_instruction);
 	unsigned i;
 
@@ -290,7 +372,26 @@ static int get_frame_info(struct mips_frame_info *info)
 			break;
 		if (!info->frame_size) {
 			if (is_sp_move_ins(ip))
+			{
+#ifdef CONFIG_CPU_MICROMIPS
+				if (mm_insn_16bit(ip->halfword[0]))
+				{
+					unsigned short tmp;
+
+					if (ip->halfword[0] & mm_addiusp_func)
+					{
+						tmp = (((ip->halfword[0] >> 1) & 0x1ff) << 2);
+						info->frame_size = -(signed short)(tmp | ((tmp & 0x100) ? 0xfe00 : 0));
+					} else {
+						tmp = (ip->halfword[0] >> 1);
+						info->frame_size = -(signed short)(tmp & 0xf);
+					}
+					ip = (void *) &ip->halfword[1];
+					ip--;
+				} else
+#endif
 				info->frame_size = - ip->i_format.simmediate;
+			}
 			continue;
 		}
 		if (info->pc_offset == -1 && is_ra_save_ins(ip)) {
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 9ea29649fc28..9b36424b03c5 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -138,9 +138,18 @@ stackargs:
 5:	jr	t1
 	 sw	t5, 16(sp)		# argument #5 to ksp
 
+#ifdef CONFIG_CPU_MICROMIPS
 	sw	t8, 28(sp)		# argument #8 to ksp
+	nop
 	sw	t7, 24(sp)		# argument #7 to ksp
+	nop
 	sw	t6, 20(sp)		# argument #6 to ksp
+	nop
+#else
+	sw	t8, 28(sp)		# argument #8 to ksp
+	sw	t7, 24(sp)		# argument #7 to ksp
+	sw	t6, 20(sp)		# argument #6 to ksp
+#endif
 6:	j	stack_done		# go back
 	 nop
 	.set	pop
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index b5e88fd83277..fd3ef2c2afbc 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -35,6 +35,7 @@
 #include <asm/war.h>
 #include <asm/vdso.h>
 #include <asm/dsp.h>
+#include <asm/inst.h>
 
 #include "signal-common.h"
 
@@ -480,7 +481,15 @@ static void handle_signal(unsigned long sig, siginfo_t *info,
 	sigset_t *oldset = sigmask_to_save();
 	int ret;
 	struct mips_abi *abi = current->thread.abi;
+#ifdef CONFIG_CPU_MICROMIPS
+	void *vdso;
+	unsigned int tmp = (unsigned int)current->mm->context.vdso;
+
+	set_isa16_mode(tmp);
+	vdso = (void *)tmp;
+#else
 	void *vdso = current->mm->context.vdso;
+#endif
 
 	if (regs->regs[0]) {
 		switch(regs->regs[2]) {
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index bfede063d96a..3e5164c11cac 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -34,6 +34,7 @@
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
 #include <asm/mips_mt.h>
+#include <asm/gic.h>
 
 static void __init smvp_copy_vpe_config(void)
 {
@@ -151,8 +152,6 @@ static void vsmp_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 static void __cpuinit vsmp_init_secondary(void)
 {
 #ifdef CONFIG_IRQ_GIC
-	extern int gic_present;
-
 	/* This is Malta specific: IPI,performance and timer interrupts */
 	if (gic_present)
 		change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
diff --git a/arch/mips/kernel/smtc-asm.S b/arch/mips/kernel/smtc-asm.S
index 76016ac0a9c8..2866863a39df 100644
--- a/arch/mips/kernel/smtc-asm.S
+++ b/arch/mips/kernel/smtc-asm.S
@@ -49,6 +49,9 @@ CAN WE PROVE THAT WE WON'T DO THIS IF INTS DISABLED??
 	.text
 	.align 5
 FEXPORT(__smtc_ipi_vector)
+#ifdef CONFIG_CPU_MICROMIPS
+	nop
+#endif
 	.set	noat
 	/* Disable thread scheduling to make Status update atomic */
 	DMT	27					# dmt	k1
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 7186222dc5bb..31d22f3121c9 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -111,7 +111,7 @@ static int vpe0limit;
 static int ipibuffers;
 static int nostlb;
 static int asidmask;
-unsigned long smtc_asid_mask = 0xff;
+unsigned int smtc_asid_mask = 0xff;
 
 static int __init vpe0tcs(char *str)
 {
@@ -1395,7 +1395,7 @@ void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
 	asid = asid_cache(cpu);
 
 	do {
-		if (!((asid += ASID_INC) & ASID_MASK) ) {
+		if (!ASID_MASK(ASID_INC(asid))) {
 			if (cpu_has_vtag_icache)
 				flush_icache_all();
 			/* Traverse all online CPUs (hack requires contiguous range) */
@@ -1414,7 +1414,7 @@ void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
 						mips_ihb();
 					}
 					tcstat = read_tc_c0_tcstatus();
-					smtc_live_asid[tlb][(tcstat & ASID_MASK)] |= (asiduse)(0x1 << i);
+					smtc_live_asid[tlb][ASID_MASK(tcstat)] |= (asiduse)(0x1 << i);
 					if (!prevhalt)
 						write_tc_c0_tchalt(0);
 				}
@@ -1423,7 +1423,7 @@ void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
 				asid = ASID_FIRST_VERSION;
 			local_flush_tlb_all();	/* start new asid cycle */
 		}
-	} while (smtc_live_asid[tlb][(asid & ASID_MASK)]);
+	} while (smtc_live_asid[tlb][ASID_MASK(asid)]);
 
 	/*
 	 * SMTC shares the TLB within VPEs and possibly across all VPEs.
@@ -1461,7 +1461,7 @@ void smtc_flush_tlb_asid(unsigned long asid)
 		tlb_read();
 		ehb();
 		ehi = read_c0_entryhi();
-		if ((ehi & ASID_MASK) == asid) {
+		if (ASID_MASK(ehi) == asid) {
 		    /*
 		     * Invalidate only entries with specified ASID,
 		     * makiing sure all entries differ.
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 7a99e60dadbd..3c906e723fd4 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -8,8 +8,8 @@
  * Copyright (C) 1998 Ulf Carlsson
  * Copyright (C) 1999 Silicon Graphics, Inc.
  * Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 2000, 01 MIPS Technologies, Inc.
  * Copyright (C) 2002, 2003, 2004, 2005, 2007  Maciej W. Rozycki
+ * Copyright (C) 2000, 2001, 2012 MIPS Technologies, Inc.  All rights reserved.
  */
 #include <linux/bug.h>
 #include <linux/compiler.h>
@@ -83,10 +83,6 @@ extern asmlinkage void handle_dsp(void);
 extern asmlinkage void handle_mcheck(void);
 extern asmlinkage void handle_reserved(void);
 
-extern int fpu_emulator_cop1Handler(struct pt_regs *xcp,
-				    struct mips_fpu_struct *ctx, int has_fpu,
-				    void *__user *fault_addr);
-
 void (*board_be_init)(void);
 int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
 void (*board_nmi_handler_setup)(void);
@@ -495,6 +491,12 @@ asmlinkage void do_be(struct pt_regs *regs)
 #define SYNC   0x0000000f
 #define RDHWR  0x0000003b
 
+/*  microMIPS definitions   */
+#define MM_POOL32A_FUNC 0xfc00ffff
+#define MM_RDHWR        0x00006b3c
+#define MM_RS           0x001f0000
+#define MM_RT           0x03e00000
+
 /*
  * The ll_bit is cleared by r*_switch.S
  */
@@ -609,42 +611,62 @@ static int simulate_llsc(struct pt_regs *regs, unsigned int opcode)
  * Simulate trapping 'rdhwr' instructions to provide user accessible
  * registers not implemented in hardware.
  */
-static int simulate_rdhwr(struct pt_regs *regs, unsigned int opcode)
+static int simulate_rdhwr(struct pt_regs *regs, int rd, int rt)
 {
 	struct thread_info *ti = task_thread_info(current);
 
+	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
+			1, regs, 0);
+	switch (rd) {
+	case 0:		/* CPU number */
+		regs->regs[rt] = smp_processor_id();
+		return 0;
+	case 1:		/* SYNCI length */
+		regs->regs[rt] = min(current_cpu_data.dcache.linesz,
+				     current_cpu_data.icache.linesz);
+		return 0;
+	case 2:		/* Read count register */
+		regs->regs[rt] = read_c0_count();
+		return 0;
+	case 3:		/* Count register resolution */
+		switch (current_cpu_data.cputype) {
+		case CPU_20KC:
+		case CPU_25KF:
+			regs->regs[rt] = 1;
+			break;
+		default:
+			regs->regs[rt] = 2;
+		}
+		return 0;
+	case 29:
+		regs->regs[rt] = ti->tp_value;
+		return 0;
+	default:
+		return -1;
+	}
+}
+
+static int simulate_rdhwr_normal(struct pt_regs *regs, unsigned int opcode)
+{
 	if ((opcode & OPCODE) == SPEC3 && (opcode & FUNC) == RDHWR) {
 		int rd = (opcode & RD) >> 11;
 		int rt = (opcode & RT) >> 16;
-		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
-				1, regs, 0);
-		switch (rd) {
-		case 0:		/* CPU number */
-			regs->regs[rt] = smp_processor_id();
-			return 0;
-		case 1:		/* SYNCI length */
-			regs->regs[rt] = min(current_cpu_data.dcache.linesz,
-					     current_cpu_data.icache.linesz);
-			return 0;
-		case 2:		/* Read count register */
-			regs->regs[rt] = read_c0_count();
-			return 0;
-		case 3:		/* Count register resolution */
-			switch (current_cpu_data.cputype) {
-			case CPU_20KC:
-			case CPU_25KF:
-				regs->regs[rt] = 1;
-				break;
-			default:
-				regs->regs[rt] = 2;
-			}
-			return 0;
-		case 29:
-			regs->regs[rt] = ti->tp_value;
-			return 0;
-		default:
-			return -1;
-		}
+
+		simulate_rdhwr(regs, rd, rt);
+		return 0;
+	}
+
+	/* Not ours.  */
+	return -1;
+}
+
+static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned short opcode)
+{
+	if ((opcode & MM_POOL32A_FUNC) == MM_RDHWR) {
+		int rd = (opcode & MM_RS) >> 16;
+		int rt = (opcode & MM_RT) >> 21;
+		simulate_rdhwr(regs, rd, rt);
+		return 0;
 	}
 
 	/* Not ours.  */
@@ -675,7 +697,7 @@ asmlinkage void do_ov(struct pt_regs *regs)
 	force_sig_info(SIGFPE, &info, current);
 }
 
-static int process_fpemu_return(int sig, void __user *fault_addr)
+int process_fpemu_return(int sig, void __user *fault_addr)
 {
 	if (sig == SIGSEGV || sig == SIGBUS) {
 		struct siginfo si = {0};
@@ -826,9 +848,29 @@ static void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 asmlinkage void do_bp(struct pt_regs *regs)
 {
 	unsigned int opcode, bcode;
-
-	if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
-		goto out_sigsegv;
+	unsigned long epc;
+	u16 instr[2];
+
+	if (get_isa16_mode(regs->cp0_epc)) {
+		/* Calculate EPC. */
+		epc = exception_epc(regs);
+		if (cpu_has_mmips) {
+			if ((__get_user(instr[0], (u16 __user *)msk_isa16_mode(epc)) ||
+			    (__get_user(instr[1], (u16 __user *)msk_isa16_mode(epc + 2)))))
+				goto out_sigsegv;
+		    opcode = (instr[0] << 16) | instr[1];
+		} else {
+		    /* MIPS16e mode */
+		    if (__get_user(instr[0], (u16 __user *)msk_isa16_mode(epc)))
+				goto out_sigsegv;
+		    bcode = (instr[0] >> 6) & 0x3f;
+		    do_trap_or_bp(regs, bcode, "Break");
+		    return;
+		}
+	} else {
+		if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
+			goto out_sigsegv;
+	}
 
 	/*
 	 * There is the ancient bug in the MIPS assemblers that the break
@@ -869,13 +911,22 @@ out_sigsegv:
 asmlinkage void do_tr(struct pt_regs *regs)
 {
 	unsigned int opcode, tcode = 0;
+	u16 instr[2];
+	unsigned long epc = exception_epc(regs);
 
-	if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
-		goto out_sigsegv;
+	if ((__get_user(instr[0], (u16 __user *)msk_isa16_mode(epc))) ||
+		(__get_user(instr[1], (u16 __user *)msk_isa16_mode(epc + 2))))
+			goto out_sigsegv;
+	opcode = (instr[0] << 16) | instr[1];
 
 	/* Immediate versions don't provide a code.  */
-	if (!(opcode & OPCODE))
-		tcode = ((opcode >> 6) & ((1 << 10) - 1));
+	if (!(opcode & OPCODE)) {
+		if (get_isa16_mode(regs->cp0_epc))
+			/* microMIPS */
+			tcode = (opcode >> 12) & 0x1f;
+		else
+			tcode = ((opcode >> 6) & ((1 << 10) - 1));
+	}
 
 	do_trap_or_bp(regs, tcode, "Trap");
 	return;
@@ -888,6 +939,7 @@ asmlinkage void do_ri(struct pt_regs *regs)
 {
 	unsigned int __user *epc = (unsigned int __user *)exception_epc(regs);
 	unsigned long old_epc = regs->cp0_epc;
+	unsigned long old31 = regs->regs[31];
 	unsigned int opcode = 0;
 	int status = -1;
 
@@ -900,23 +952,37 @@ asmlinkage void do_ri(struct pt_regs *regs)
 	if (unlikely(compute_return_epc(regs) < 0))
 		return;
 
-	if (unlikely(get_user(opcode, epc) < 0))
-		status = SIGSEGV;
+	if (get_isa16_mode(regs->cp0_epc)) {
+		unsigned short mmop[2] = { 0 };
 
-	if (!cpu_has_llsc && status < 0)
-		status = simulate_llsc(regs, opcode);
+		if (unlikely(get_user(mmop[0], epc) < 0))
+			status = SIGSEGV;
+		if (unlikely(get_user(mmop[1], epc) < 0))
+			status = SIGSEGV;
+		opcode = (mmop[0] << 16) | mmop[1];
 
-	if (status < 0)
-		status = simulate_rdhwr(regs, opcode);
+		if (status < 0)
+			status = simulate_rdhwr_mm(regs, opcode);
+	} else {
+		if (unlikely(get_user(opcode, epc) < 0))
+			status = SIGSEGV;
 
-	if (status < 0)
-		status = simulate_sync(regs, opcode);
+		if (!cpu_has_llsc && status < 0)
+			status = simulate_llsc(regs, opcode);
+
+		if (status < 0)
+			status = simulate_rdhwr_normal(regs, opcode);
+
+		if (status < 0)
+			status = simulate_sync(regs, opcode);
+	}
 
 	if (status < 0)
 		status = SIGILL;
 
 	if (unlikely(status > 0)) {
 		regs->cp0_epc = old_epc;		/* Undo skip-over.  */
+		regs->regs[31] = old31;
 		force_sig(status, current);
 	}
 }
@@ -986,7 +1052,7 @@ static int default_cu2_call(struct notifier_block *nfb, unsigned long action,
 asmlinkage void do_cpu(struct pt_regs *regs)
 {
 	unsigned int __user *epc;
-	unsigned long old_epc;
+	unsigned long old_epc, old31;
 	unsigned int opcode;
 	unsigned int cpid;
 	int status;
@@ -1000,26 +1066,41 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 	case 0:
 		epc = (unsigned int __user *)exception_epc(regs);
 		old_epc = regs->cp0_epc;
+		old31 = regs->regs[31];
 		opcode = 0;
 		status = -1;
 
 		if (unlikely(compute_return_epc(regs) < 0))
 			return;
 
-		if (unlikely(get_user(opcode, epc) < 0))
-			status = SIGSEGV;
+		if (get_isa16_mode(regs->cp0_epc)) {
+			unsigned short mmop[2] = { 0 };
 
-		if (!cpu_has_llsc && status < 0)
-			status = simulate_llsc(regs, opcode);
+			if (unlikely(get_user(mmop[0], epc) < 0))
+				status = SIGSEGV;
+			if (unlikely(get_user(mmop[1], epc) < 0))
+				status = SIGSEGV;
+			opcode = (mmop[0] << 16) | mmop[1];
 
-		if (status < 0)
-			status = simulate_rdhwr(regs, opcode);
+			if (status < 0)
+				status = simulate_rdhwr_mm(regs, opcode);
+		} else {
+			if (unlikely(get_user(opcode, epc) < 0))
+				status = SIGSEGV;
+
+			if (!cpu_has_llsc && status < 0)
+				status = simulate_llsc(regs, opcode);
+
+			if (status < 0)
+				status = simulate_rdhwr_normal(regs, opcode);
+		}
 
 		if (status < 0)
 			status = SIGILL;
 
 		if (unlikely(status > 0)) {
 			regs->cp0_epc = old_epc;	/* Undo skip-over.  */
+			regs->regs[31] = old31;
 			force_sig(status, current);
 		}
 
@@ -1333,7 +1414,7 @@ asmlinkage void cache_parity_error(void)
 void ejtag_exception_handler(struct pt_regs *regs)
 {
 	const int field = 2 * sizeof(unsigned long);
-	unsigned long depc, old_epc;
+	unsigned long depc, old_epc, old_ra;
 	unsigned int debug;
 
 	printk(KERN_DEBUG "SDBBP EJTAG debug exception - not handled yet, just ignored!\n");
@@ -1348,10 +1429,12 @@ void ejtag_exception_handler(struct pt_regs *regs)
 		 * calculation.
 		 */
 		old_epc = regs->cp0_epc;
+		old_ra = regs->regs[31];
 		regs->cp0_epc = depc;
-		__compute_return_epc(regs);
+		compute_return_epc(regs);
 		depc = regs->cp0_epc;
 		regs->cp0_epc = old_epc;
+		regs->regs[31] = old_ra;
 	} else
 		depc += 4;
 	write_c0_depc(depc);
@@ -1390,10 +1473,27 @@ unsigned long vi_handlers[64];
 void __init *set_except_vector(int n, void *addr)
 {
 	unsigned long handler = (unsigned long) addr;
-	unsigned long old_handler = xchg(&exception_handlers[n], handler);
+	unsigned long old_handler;
+
+#ifdef CONFIG_CPU_MICROMIPS
+	/*
+	 * Only the TLB handlers are cache aligned with an even
+	 * address. All other handlers are on an odd address and
+	 * require no modification. Otherwise, MIPS32 mode will
+	 * be entered when handling any TLB exceptions. That
+	 * would be bad...since we must stay in microMIPS mode.
+	 */
+	if (!(handler & 0x1))
+		handler |= 1;
+#endif
+	old_handler = xchg(&exception_handlers[n], handler);
 
 	if (n == 0 && cpu_has_divec) {
+#ifdef CONFIG_CPU_MICROMIPS
+		unsigned long jump_mask = ~((1 << 27) - 1);
+#else
 		unsigned long jump_mask = ~((1 << 28) - 1);
+#endif
 		u32 *buf = (u32 *)(ebase + 0x200);
 		unsigned int k0 = 26;
 		if ((handler & jump_mask) == ((ebase + 0x200) & jump_mask)) {
@@ -1420,17 +1520,18 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 	unsigned long handler;
 	unsigned long old_handler = vi_handlers[n];
 	int srssets = current_cpu_data.srsets;
-	u32 *w;
+	u16 *h;
 	unsigned char *b;
 
 	BUG_ON(!cpu_has_veic && !cpu_has_vint);
+	BUG_ON((n < 0) && (n > 9));
 
 	if (addr == NULL) {
 		handler = (unsigned long) do_default_vi;
 		srs = 0;
 	} else
 		handler = (unsigned long) addr;
-	vi_handlers[n] = (unsigned long) addr;
+	vi_handlers[n] = handler;
 
 	b = (unsigned char *)(ebase + 0x200 + n*VECTORSPACING);
 
@@ -1449,9 +1550,8 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 	if (srs == 0) {
 		/*
 		 * If no shadow set is selected then use the default handler
-		 * that does normal register saving and a standard interrupt exit
+		 * that does normal register saving and standard interrupt exit
 		 */
-
 		extern char except_vec_vi, except_vec_vi_lui;
 		extern char except_vec_vi_ori, except_vec_vi_end;
 		extern char rollback_except_vec_vi;
@@ -1464,11 +1564,20 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 		 * Status.IM bit to be masked before going there.
 		 */
 		extern char except_vec_vi_mori;
+#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
+		const int mori_offset = &except_vec_vi_mori - vec_start + 2;
+#else
 		const int mori_offset = &except_vec_vi_mori - vec_start;
+#endif
 #endif /* CONFIG_MIPS_MT_SMTC */
-		const int handler_len = &except_vec_vi_end - vec_start;
+#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
+		const int lui_offset = &except_vec_vi_lui - vec_start + 2;
+		const int ori_offset = &except_vec_vi_ori - vec_start + 2;
+#else
 		const int lui_offset = &except_vec_vi_lui - vec_start;
 		const int ori_offset = &except_vec_vi_ori - vec_start;
+#endif
+		const int handler_len = &except_vec_vi_end - vec_start;
 
 		if (handler_len > VECTORSPACING) {
 			/*
@@ -1478,30 +1587,44 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 			panic("VECTORSPACING too small");
 		}
 
-		memcpy(b, vec_start, handler_len);
+		set_handler(((unsigned long)b - ebase), vec_start,
+#ifdef CONFIG_CPU_MICROMIPS
+				(handler_len - 1));
+#else
+				handler_len);
+#endif
 #ifdef CONFIG_MIPS_MT_SMTC
 		BUG_ON(n > 7);	/* Vector index %d exceeds SMTC maximum. */
 
-		w = (u32 *)(b + mori_offset);
-		*w = (*w & 0xffff0000) | (0x100 << n);
+		h = (u16 *)(b + mori_offset);
+		*h = (0x100 << n);
 #endif /* CONFIG_MIPS_MT_SMTC */
-		w = (u32 *)(b + lui_offset);
-		*w = (*w & 0xffff0000) | (((u32)handler >> 16) & 0xffff);
-		w = (u32 *)(b + ori_offset);
-		*w = (*w & 0xffff0000) | ((u32)handler & 0xffff);
+		h = (u16 *)(b + lui_offset);
+		*h = (handler >> 16) & 0xffff;
+		h = (u16 *)(b + ori_offset);
+		*h = (handler & 0xffff);
 		local_flush_icache_range((unsigned long)b,
 					 (unsigned long)(b+handler_len));
 	}
 	else {
 		/*
-		 * In other cases jump directly to the interrupt handler
-		 *
-		 * It is the handlers responsibility to save registers if required
-		 * (eg hi/lo) and return from the exception using "eret"
+		 * In other cases jump directly to the interrupt handler. It
+		 * is the handler's responsibility to save registers if required
+		 * (eg hi/lo) and return from the exception using "eret".
 		 */
-		w = (u32 *)b;
-		*w++ = 0x08000000 | (((u32)handler >> 2) & 0x03fffff); /* j handler */
-		*w = 0;
+		u32 insn;
+
+		h = (u16 *)b;
+		/* j handler */
+#ifdef CONFIG_CPU_MICROMIPS
+		insn = 0xd4000000 | (((u32)handler & 0x07ffffff) >> 1);
+#else
+		insn = 0x08000000 | (((u32)handler & 0x0fffffff) >> 2);
+#endif
+		h[0] = (insn >> 16) & 0xffff;
+		h[1] = insn & 0xffff;
+		h[2] = 0;
+		h[3] = 0;
 		local_flush_icache_range((unsigned long)b,
 					 (unsigned long)(b+8));
 	}
@@ -1546,6 +1669,7 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu)
 	unsigned int cpu = smp_processor_id();
 	unsigned int status_set = ST0_CU0;
 	unsigned int hwrena = cpu_hwrena_impl_bits;
+	unsigned long asid = 0;
 #ifdef CONFIG_MIPS_MT_SMTC
 	int secondaryTC = 0;
 	int bootTC = (cpu == 0);
@@ -1629,8 +1753,9 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu)
 	}
 #endif /* CONFIG_MIPS_MT_SMTC */
 
-	if (!cpu_data[cpu].asid_cache)
-		cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
+	asid = ASID_FIRST_VERSION;
+	cpu_data[cpu].asid_cache = asid;
+	TLBMISS_HANDLER_SETUP();
 
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
@@ -1660,7 +1785,11 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu)
 /* Install CPU exception handler */
 void __cpuinit set_handler(unsigned long offset, void *addr, unsigned long size)
 {
+#ifdef CONFIG_CPU_MICROMIPS
+	memcpy((void *)(ebase + offset), ((unsigned char *)addr - 1), size);
+#else
 	memcpy((void *)(ebase + offset), addr, size);
+#endif
 	local_flush_icache_range(ebase + offset, ebase + offset + size);
 }
 
@@ -1694,8 +1823,9 @@ __setup("rdhwr_noopt", set_rdhwr_noopt);
 
 void __init trap_init(void)
 {
-	extern char except_vec3_generic, except_vec3_r4000;
+	extern char except_vec3_generic;
 	extern char except_vec4;
+	extern char except_vec3_r4000;
 	unsigned long i;
 	int rollback;
 
@@ -1833,11 +1963,11 @@ void __init trap_init(void)
 
 	if (cpu_has_vce)
 		/* Special exception: R4[04]00 uses also the divec space. */
-		memcpy((void *)(ebase + 0x180), &except_vec3_r4000, 0x100);
+		set_handler(0x180, &except_vec3_r4000, 0x100);
 	else if (cpu_has_4kex)
-		memcpy((void *)(ebase + 0x180), &except_vec3_generic, 0x80);
+		set_handler(0x180, &except_vec3_generic, 0x80);
 	else
-		memcpy((void *)(ebase + 0x080), &except_vec3_generic, 0x80);
+		set_handler(0x080, &except_vec3_generic, 0x80);
 
 	local_flush_icache_range(ebase, ebase + 0x400);
 	flush_tlb_handlers();
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 6087a54c86a0..203d8857070d 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -83,8 +83,12 @@
 #include <asm/branch.h>
 #include <asm/byteorder.h>
 #include <asm/cop2.h>
+#include <asm/fpu.h>
+#include <asm/fpu_emulator.h>
 #include <asm/inst.h>
 #include <asm/uaccess.h>
+#include <asm/fpu.h>
+#include <asm/fpu_emulator.h>
 
 #define STR(x)	__STR(x)
 #define __STR(x)  #x
@@ -102,12 +106,332 @@ static u32 unaligned_action;
 #endif
 extern void show_registers(struct pt_regs *regs);
 
+#ifdef __BIG_ENDIAN
+#define     LoadHW(addr, value, res)  \
+		__asm__ __volatile__ (".set\tnoat\n"        \
+			"1:\tlb\t%0, 0(%2)\n"               \
+			"2:\tlbu\t$1, 1(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\t.set\tat\n\t"                  \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadW(addr, value, res)   \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, (%2)\n"               \
+			"2:\tlwr\t%0, 3(%2)\n\t"            \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadHWU(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tlbu\t%0, 0(%2)\n"              \
+			"2:\tlbu\t$1, 1(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".set\tat\n\t"                      \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadWU(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, (%2)\n"               \
+			"2:\tlwr\t%0, 3(%2)\n\t"            \
+			"dsll\t%0, %0, 32\n\t"              \
+			"dsrl\t%0, %0, 32\n\t"              \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadDW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tldl\t%0, (%2)\n"               \
+			"2:\tldr\t%0, 7(%2)\n\t"            \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     StoreHW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tsb\t%1, 1(%2)\n\t"             \
+			"srl\t$1, %1, 0x8\n"                \
+			"2:\tsb\t$1, 0(%2)\n\t"             \
+			".set\tat\n\t"                      \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=r" (res)                        \
+			: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tswl\t%1,(%2)\n"                \
+			"2:\tswr\t%1, 3(%2)\n\t"            \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreDW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			"1:\tsdl\t%1,(%2)\n"                \
+			"2:\tsdr\t%1, 7(%2)\n\t"            \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+#endif
+
+#ifdef __LITTLE_ENDIAN
+#define     LoadHW(addr, value, res)  \
+		__asm__ __volatile__ (".set\tnoat\n"        \
+			"1:\tlb\t%0, 1(%2)\n"               \
+			"2:\tlbu\t$1, 0(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\t.set\tat\n\t"                  \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadW(addr, value, res)   \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, 3(%2)\n"              \
+			"2:\tlwr\t%0, (%2)\n\t"             \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadHWU(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tlbu\t%0, 1(%2)\n"              \
+			"2:\tlbu\t$1, 0(%2)\n\t"            \
+			"sll\t%0, 0x8\n\t"                  \
+			"or\t%0, $1\n\t"                    \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".set\tat\n\t"                      \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadWU(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tlwl\t%0, 3(%2)\n"              \
+			"2:\tlwr\t%0, (%2)\n\t"             \
+			"dsll\t%0, %0, 32\n\t"              \
+			"dsrl\t%0, %0, 32\n\t"              \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadDW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tldl\t%0, 7(%2)\n"              \
+			"2:\tldr\t%0, (%2)\n\t"             \
+			"li\t%1, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			"\t.section\t.fixup,\"ax\"\n\t"     \
+			"4:\tli\t%1, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=&r" (value), "=r" (res)         \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     StoreHW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tnoat\n"                      \
+			"1:\tsb\t%1, 0(%2)\n\t"             \
+			"srl\t$1,%1, 0x8\n"                 \
+			"2:\tsb\t$1, 1(%2)\n\t"             \
+			".set\tat\n\t"                      \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+			: "=r" (res)                        \
+			: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			"1:\tswl\t%1, 3(%2)\n"              \
+			"2:\tswr\t%1, (%2)\n\t"             \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+
+#define     StoreDW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			"1:\tsdl\t%1, 7(%2)\n"              \
+			"2:\tsdr\t%1, (%2)\n\t"             \
+			"li\t%0, 0\n"                       \
+			"3:\n\t"                            \
+			".insn\n\t"                         \
+			".section\t.fixup,\"ax\"\n\t"       \
+			"4:\tli\t%0, %3\n\t"                \
+			"j\t3b\n\t"                         \
+			".previous\n\t"                     \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 4b\n\t"              \
+			STR(PTR)"\t2b, 4b\n\t"              \
+			".previous"                         \
+		: "=r" (res)                                \
+		: "r" (value), "r" (addr), "i" (-EFAULT));
+#endif
+
 static void emulate_load_store_insn(struct pt_regs *regs,
 	void __user *addr, unsigned int __user *pc)
 {
 	union mips_instruction insn;
 	unsigned long value;
 	unsigned int res;
+	unsigned long origpc;
+	unsigned long orig31;
+	void __user *fault_addr = NULL;
+
+	origpc = (unsigned long)pc;
+	orig31 = regs->regs[31];
 
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
@@ -117,22 +441,22 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	__get_user(insn.word, pc);
 
 	switch (insn.i_format.opcode) {
-	/*
-	 * These are instructions that a compiler doesn't generate.  We
-	 * can assume therefore that the code is MIPS-aware and
-	 * really buggy.  Emulating these instructions would break the
-	 * semantics anyway.
-	 */
+		/*
+		 * These are instructions that a compiler doesn't generate.  We
+		 * can assume therefore that the code is MIPS-aware and
+		 * really buggy.  Emulating these instructions would break the
+		 * semantics anyway.
+		 */
 	case ll_op:
 	case lld_op:
 	case sc_op:
 	case scd_op:
 
-	/*
-	 * For these instructions the only way to create an address
-	 * error is an attempted access to kernel/supervisor address
-	 * space.
-	 */
+		/*
+		 * For these instructions the only way to create an address
+		 * error is an attempted access to kernel/supervisor address
+		 * space.
+		 */
 	case ldl_op:
 	case ldr_op:
 	case lwl_op:
@@ -146,36 +470,15 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	case sb_op:
 		goto sigbus;
 
-	/*
-	 * The remaining opcodes are the ones that are really of interest.
-	 */
+		/*
+		 * The remaining opcodes are the ones that are really of
+		 * interest.
+		 */
 	case lh_op:
 		if (!access_ok(VERIFY_READ, addr, 2))
 			goto sigbus;
 
-		__asm__ __volatile__ (".set\tnoat\n"
-#ifdef __BIG_ENDIAN
-			"1:\tlb\t%0, 0(%2)\n"
-			"2:\tlbu\t$1, 1(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlb\t%0, 1(%2)\n"
-			"2:\tlbu\t$1, 0(%2)\n\t"
-#endif
-			"sll\t%0, 0x8\n\t"
-			"or\t%0, $1\n\t"
-			"li\t%1, 0\n"
-			"3:\t.set\tat\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadHW(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -186,26 +489,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 4))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tlwl\t%0, (%2)\n"
-			"2:\tlwr\t%0, 3(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlwl\t%0, 3(%2)\n"
-			"2:\tlwr\t%0, (%2)\n\t"
-#endif
-			"li\t%1, 0\n"
-			"3:\t.section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadW(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -216,30 +500,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 2))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-			".set\tnoat\n"
-#ifdef __BIG_ENDIAN
-			"1:\tlbu\t%0, 0(%2)\n"
-			"2:\tlbu\t$1, 1(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlbu\t%0, 1(%2)\n"
-			"2:\tlbu\t$1, 0(%2)\n\t"
-#endif
-			"sll\t%0, 0x8\n\t"
-			"or\t%0, $1\n\t"
-			"li\t%1, 0\n"
-			"3:\t.set\tat\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadHWU(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -258,28 +519,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 4))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tlwl\t%0, (%2)\n"
-			"2:\tlwr\t%0, 3(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tlwl\t%0, 3(%2)\n"
-			"2:\tlwr\t%0, (%2)\n\t"
-#endif
-			"dsll\t%0, %0, 32\n\t"
-			"dsrl\t%0, %0, 32\n\t"
-			"li\t%1, 0\n"
-			"3:\t.section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadWU(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -302,26 +542,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_READ, addr, 8))
 			goto sigbus;
 
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tldl\t%0, (%2)\n"
-			"2:\tldr\t%0, 7(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tldl\t%0, 7(%2)\n"
-			"2:\tldr\t%0, (%2)\n\t"
-#endif
-			"li\t%1, 0\n"
-			"3:\t.section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%1, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=&r" (value), "=r" (res)
-			: "r" (addr), "i" (-EFAULT));
+		LoadDW(addr, value, res);
 		if (res)
 			goto fault;
 		compute_return_epc(regs);
@@ -336,68 +557,22 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_WRITE, addr, 2))
 			goto sigbus;
 
+		compute_return_epc(regs);
 		value = regs->regs[insn.i_format.rt];
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			".set\tnoat\n"
-			"1:\tsb\t%1, 1(%2)\n\t"
-			"srl\t$1, %1, 0x8\n"
-			"2:\tsb\t$1, 0(%2)\n\t"
-			".set\tat\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			".set\tnoat\n"
-			"1:\tsb\t%1, 0(%2)\n\t"
-			"srl\t$1,%1, 0x8\n"
-			"2:\tsb\t$1, 1(%2)\n\t"
-			".set\tat\n\t"
-#endif
-			"li\t%0, 0\n"
-			"3:\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%0, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-			: "=r" (res)
-			: "r" (value), "r" (addr), "i" (-EFAULT));
+		StoreHW(addr, value, res);
 		if (res)
 			goto fault;
-		compute_return_epc(regs);
 		break;
 
 	case sw_op:
 		if (!access_ok(VERIFY_WRITE, addr, 4))
 			goto sigbus;
 
+		compute_return_epc(regs);
 		value = regs->regs[insn.i_format.rt];
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tswl\t%1,(%2)\n"
-			"2:\tswr\t%1, 3(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tswl\t%1, 3(%2)\n"
-			"2:\tswr\t%1, (%2)\n\t"
-#endif
-			"li\t%0, 0\n"
-			"3:\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%0, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-		: "=r" (res)
-		: "r" (value), "r" (addr), "i" (-EFAULT));
+		StoreW(addr, value, res);
 		if (res)
 			goto fault;
-		compute_return_epc(regs);
 		break;
 
 	case sd_op:
@@ -412,31 +587,11 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		if (!access_ok(VERIFY_WRITE, addr, 8))
 			goto sigbus;
 
+		compute_return_epc(regs);
 		value = regs->regs[insn.i_format.rt];
-		__asm__ __volatile__ (
-#ifdef __BIG_ENDIAN
-			"1:\tsdl\t%1,(%2)\n"
-			"2:\tsdr\t%1, 7(%2)\n\t"
-#endif
-#ifdef __LITTLE_ENDIAN
-			"1:\tsdl\t%1, 7(%2)\n"
-			"2:\tsdr\t%1, (%2)\n\t"
-#endif
-			"li\t%0, 0\n"
-			"3:\n\t"
-			".section\t.fixup,\"ax\"\n\t"
-			"4:\tli\t%0, %3\n\t"
-			"j\t3b\n\t"
-			".previous\n\t"
-			".section\t__ex_table,\"a\"\n\t"
-			STR(PTR)"\t1b, 4b\n\t"
-			STR(PTR)"\t2b, 4b\n\t"
-			".previous"
-		: "=r" (res)
-		: "r" (value), "r" (addr), "i" (-EFAULT));
+		StoreDW(addr, value, res);
 		if (res)
 			goto fault;
-		compute_return_epc(regs);
 		break;
 #endif /* CONFIG_64BIT */
 
@@ -447,10 +602,21 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	case ldc1_op:
 	case swc1_op:
 	case sdc1_op:
-		/*
-		 * I herewith declare: this does not happen.  So send SIGBUS.
-		 */
-		goto sigbus;
+		die_if_kernel("Unaligned FP access in kernel code", regs);
+		BUG_ON(!used_math());
+		BUG_ON(!is_fpu_owner());
+
+		lose_fpu(1);	/* Save FPU state for the emulator. */
+		res = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
+					       &fault_addr);
+		own_fpu(1);	/* Restore FPU state. */
+
+		/* Signal if something went wrong. */
+		process_fpemu_return(res, fault_addr);
+
+		if (res == 0)
+			break;
+		return;
 
 	/*
 	 * COP2 is available to implementor for application specific use.
@@ -488,6 +654,9 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	return;
 
 fault:
+	/* roll back jump/branch */
+	regs->cp0_epc = origpc;
+	regs->regs[31] = orig31;
 	/* Did we have an exception handler installed? */
 	if (fixup_exception(regs))
 		return;
@@ -504,10 +673,881 @@ sigbus:
 	return;
 
 sigill:
-	die_if_kernel("Unhandled kernel unaligned access or invalid instruction", regs);
+	die_if_kernel
+	    ("Unhandled kernel unaligned access or invalid instruction", regs);
 	force_sig(SIGILL, current);
 }
 
+/* Recode table from 16-bit register notation to 32-bit GPR. */
+const int reg16to32[] = { 16, 17, 2, 3, 4, 5, 6, 7 };
+
+/* Recode table from 16-bit STORE register notation to 32-bit GPR. */
+const int reg16to32st[] = { 0, 17, 2, 3, 4, 5, 6, 7 };
+
+void emulate_load_store_microMIPS(struct pt_regs *regs, void __user * addr)
+{
+	unsigned long value;
+	unsigned int res;
+	int i;
+	unsigned int reg = 0, rvar;
+	unsigned long orig31;
+	u16 __user *pc16;
+	u16 halfword;
+	unsigned int word;
+	unsigned long origpc, contpc;
+	union mips_instruction insn;
+	struct mm_decoded_insn mminsn;
+	void __user *fault_addr = NULL;
+
+	origpc = regs->cp0_epc;
+	orig31 = regs->regs[31];
+
+	mminsn.micro_mips_mode = 1;
+
+	/*
+	 * This load never faults.
+	 */
+	pc16 = (unsigned short __user *)msk_isa16_mode(regs->cp0_epc);
+	__get_user(halfword, pc16);
+	pc16++;
+	contpc = regs->cp0_epc + 2;
+	word = ((unsigned int)halfword << 16);
+	mminsn.pc_inc = 2;
+
+	if (!mm_insn_16bit(halfword)) {
+		__get_user(halfword, pc16);
+		pc16++;
+		contpc = regs->cp0_epc + 4;
+		mminsn.pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.insn = word;
+
+	if (get_user(halfword, pc16))
+		goto fault;
+	mminsn.next_pc_inc = 2;
+	word = ((unsigned int)halfword << 16);
+
+	if (!mm_insn_16bit(halfword)) {
+		pc16++;
+		if (get_user(halfword, pc16))
+			goto fault;
+		mminsn.next_pc_inc = 4;
+		word |= halfword;
+	}
+	mminsn.next_insn = word;
+
+	insn = (union mips_instruction)(mminsn.insn);
+	if (mm_isBranchInstr(regs, mminsn, &contpc))
+		insn = (union mips_instruction)(mminsn.next_insn);
+
+	/*  Parse instruction to find what to do */
+
+	switch (insn.mm_i_format.opcode) {
+
+	case mm_pool32a_op:
+		switch (insn.mm_x_format.func) {
+		case mm_lwxs_op:
+			reg = insn.mm_x_format.rd;
+			goto loadW;
+		}
+
+		goto sigbus;
+
+	case mm_pool32b_op:
+		switch (insn.mm_m_format.func) {
+		case mm_lwp_func:
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_READ, addr, 8))
+				goto sigbus;
+
+			LoadW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg] = value;
+			addr += 4;
+			LoadW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg + 1] = value;
+			goto success;
+
+		case mm_swp_func:
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_WRITE, addr, 8))
+				goto sigbus;
+
+			value = regs->regs[reg];
+			StoreW(addr, value, res);
+			if (res)
+				goto fault;
+			addr += 4;
+			value = regs->regs[reg + 1];
+			StoreW(addr, value, res);
+			if (res)
+				goto fault;
+			goto success;
+
+		case mm_ldp_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_READ, addr, 16))
+				goto sigbus;
+
+			LoadDW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg] = value;
+			addr += 8;
+			LoadDW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[reg + 1] = value;
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+		case mm_sdp_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			if (reg == 31)
+				goto sigbus;
+
+			if (!access_ok(VERIFY_WRITE, addr, 16))
+				goto sigbus;
+
+			value = regs->regs[reg];
+			StoreDW(addr, value, res);
+			if (res)
+				goto fault;
+			addr += 8;
+			value = regs->regs[reg + 1];
+			StoreDW(addr, value, res);
+			if (res)
+				goto fault;
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+		case mm_lwm32_func:
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_READ, addr, 4 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_READ, addr, 4 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+			for (i = 16; rvar; rvar--, i++) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[i] = value;
+			}
+			if ((reg & 0xf) == 9) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[30] = value;
+			}
+			if (reg & 0x10) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				regs->regs[31] = value;
+			}
+			goto success;
+
+		case mm_swm32_func:
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_WRITE, addr, 4 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_WRITE, addr, 4 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+			for (i = 16; rvar; rvar--, i++) {
+				value = regs->regs[i];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+			}
+			if ((reg & 0xf) == 9) {
+				value = regs->regs[30];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+			}
+			if (reg & 0x10) {
+				value = regs->regs[31];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+			}
+			goto success;
+
+		case mm_ldm_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_READ, addr, 8 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_READ, addr, 8 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+
+			for (i = 16; rvar; rvar--, i++) {
+				LoadDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[i] = value;
+			}
+			if ((reg & 0xf) == 9) {
+				LoadDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 8;
+				regs->regs[30] = value;
+			}
+			if (reg & 0x10) {
+				LoadDW(addr, value, res);
+				if (res)
+					goto fault;
+				regs->regs[31] = value;
+			}
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+		case mm_sdm_func:
+#ifdef CONFIG_64BIT
+			reg = insn.mm_m_format.rd;
+			rvar = reg & 0xf;
+			if ((rvar > 9) || !reg)
+				goto sigill;
+			if (reg & 0x10) {
+				if (!access_ok
+				    (VERIFY_WRITE, addr, 8 * (rvar + 1)))
+					goto sigbus;
+			} else {
+				if (!access_ok(VERIFY_WRITE, addr, 8 * rvar))
+					goto sigbus;
+			}
+			if (rvar == 9)
+				rvar = 8;
+
+			for (i = 16; rvar; rvar--, i++) {
+				value = regs->regs[i];
+				StoreDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 8;
+			}
+			if ((reg & 0xf) == 9) {
+				value = regs->regs[30];
+				StoreDW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 8;
+			}
+			if (reg & 0x10) {
+				value = regs->regs[31];
+				StoreDW(addr, value, res);
+				if (res)
+					goto fault;
+			}
+			goto success;
+#endif /* CONFIG_64BIT */
+
+			goto sigill;
+
+			/*  LWC2, SWC2, LDC2, SDC2 are not serviced */
+		}
+
+		goto sigbus;
+
+	case mm_pool32c_op:
+		switch (insn.mm_m_format.func) {
+		case mm_lwu_func:
+			reg = insn.mm_m_format.rd;
+			goto loadWU;
+		}
+
+		/*  LL,SC,LLD,SCD are not serviced */
+		goto sigbus;
+
+	case mm_pool32f_op:
+		switch (insn.mm_x_format.func) {
+		case mm_lwxc1_func:
+		case mm_swxc1_func:
+		case mm_ldxc1_func:
+		case mm_sdxc1_func:
+			goto fpu_emul;
+		}
+
+		goto sigbus;
+
+	case mm_ldc132_op:
+	case mm_sdc132_op:
+	case mm_lwc132_op:
+	case mm_swc132_op:
+fpu_emul:
+		/* roll back jump/branch */
+		regs->cp0_epc = origpc;
+		regs->regs[31] = orig31;
+
+		die_if_kernel("Unaligned FP access in kernel code", regs);
+		BUG_ON(!used_math());
+		BUG_ON(!is_fpu_owner());
+
+		lose_fpu(1);	/* save the FPU state for the emulator */
+		res = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
+					       &fault_addr);
+		own_fpu(1);	/* restore FPU state */
+
+		/* If something went wrong, signal */
+		process_fpemu_return(res, fault_addr);
+
+		if (res == 0)
+			goto success;
+		return;
+
+	case mm_lh32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadHW;
+
+	case mm_lhu32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadHWU;
+
+	case mm_lw32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadW;
+
+	case mm_sh32_op:
+		reg = insn.mm_i_format.rt;
+		goto storeHW;
+
+	case mm_sw32_op:
+		reg = insn.mm_i_format.rt;
+		goto storeW;
+
+	case mm_ld32_op:
+		reg = insn.mm_i_format.rt;
+		goto loadDW;
+
+	case mm_sd32_op:
+		reg = insn.mm_i_format.rt;
+		goto storeDW;
+
+	case mm_pool16c_op:
+		switch (insn.mm16_m_format.func) {
+		case mm_lwm16_op:
+			reg = insn.mm16_m_format.rlist;
+			rvar = reg + 1;
+			if (!access_ok(VERIFY_READ, addr, 4 * rvar))
+				goto sigbus;
+
+			for (i = 16; rvar; rvar--, i++) {
+				LoadW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+				regs->regs[i] = value;
+			}
+			LoadW(addr, value, res);
+			if (res)
+				goto fault;
+			regs->regs[31] = value;
+
+			goto success;
+
+		case mm_swm16_op:
+			reg = insn.mm16_m_format.rlist;
+			rvar = reg + 1;
+			if (!access_ok(VERIFY_WRITE, addr, 4 * rvar))
+				goto sigbus;
+
+			for (i = 16; rvar; rvar--, i++) {
+				value = regs->regs[i];
+				StoreW(addr, value, res);
+				if (res)
+					goto fault;
+				addr += 4;
+			}
+			value = regs->regs[31];
+			StoreW(addr, value, res);
+			if (res)
+				goto fault;
+
+			goto success;
+
+		}
+
+		goto sigbus;
+
+	case mm_lhu16_op:
+		reg = reg16to32[insn.mm16_rb_format.rt];
+		goto loadHWU;
+
+	case mm_lw16_op:
+		reg = reg16to32[insn.mm16_rb_format.rt];
+		goto loadW;
+
+	case mm_sh16_op:
+		reg = reg16to32st[insn.mm16_rb_format.rt];
+		goto storeHW;
+
+	case mm_sw16_op:
+		reg = reg16to32st[insn.mm16_rb_format.rt];
+		goto storeW;
+
+	case mm_lwsp16_op:
+		reg = insn.mm16_r5_format.rt;
+		goto loadW;
+
+	case mm_swsp16_op:
+		reg = insn.mm16_r5_format.rt;
+		goto storeW;
+
+	case mm_lwgp16_op:
+		reg = reg16to32[insn.mm16_r3_format.rt];
+		goto loadW;
+
+	default:
+		goto sigill;
+	}
+
+loadHW:
+	if (!access_ok(VERIFY_READ, addr, 2))
+		goto sigbus;
+
+	LoadHW(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+
+loadHWU:
+	if (!access_ok(VERIFY_READ, addr, 2))
+		goto sigbus;
+
+	LoadHWU(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+
+loadW:
+	if (!access_ok(VERIFY_READ, addr, 4))
+		goto sigbus;
+
+	LoadW(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+
+loadWU:
+#ifdef CONFIG_64BIT
+	/*
+	 * A 32-bit kernel might be running on a 64-bit processor.  But
+	 * if we're on a 32-bit processor and an i-cache incoherency
+	 * or race makes us see a 64-bit instruction here the sdl/sdr
+	 * would blow up, so for now we don't handle unaligned 64-bit
+	 * instructions on 32-bit kernels.
+	 */
+	if (!access_ok(VERIFY_READ, addr, 4))
+		goto sigbus;
+
+	LoadWU(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+#endif /* CONFIG_64BIT */
+
+	/* Cannot handle 64-bit instructions in 32-bit kernel */
+	goto sigill;
+
+loadDW:
+#ifdef CONFIG_64BIT
+	/*
+	 * A 32-bit kernel might be running on a 64-bit processor.  But
+	 * if we're on a 32-bit processor and an i-cache incoherency
+	 * or race makes us see a 64-bit instruction here the sdl/sdr
+	 * would blow up, so for now we don't handle unaligned 64-bit
+	 * instructions on 32-bit kernels.
+	 */
+	if (!access_ok(VERIFY_READ, addr, 8))
+		goto sigbus;
+
+	LoadDW(addr, value, res);
+	if (res)
+		goto fault;
+	regs->regs[reg] = value;
+	goto success;
+#endif /* CONFIG_64BIT */
+
+	/* Cannot handle 64-bit instructions in 32-bit kernel */
+	goto sigill;
+
+storeHW:
+	if (!access_ok(VERIFY_WRITE, addr, 2))
+		goto sigbus;
+
+	value = regs->regs[reg];
+	StoreHW(addr, value, res);
+	if (res)
+		goto fault;
+	goto success;
+
+storeW:
+	if (!access_ok(VERIFY_WRITE, addr, 4))
+		goto sigbus;
+
+	value = regs->regs[reg];
+	StoreW(addr, value, res);
+	if (res)
+		goto fault;
+	goto success;
+
+storeDW:
+#ifdef CONFIG_64BIT
+	/*
+	 * A 32-bit kernel might be running on a 64-bit processor.  But
+	 * if we're on a 32-bit processor and an i-cache incoherency
+	 * or race makes us see a 64-bit instruction here the sdl/sdr
+	 * would blow up, so for now we don't handle unaligned 64-bit
+	 * instructions on 32-bit kernels.
+	 */
+	if (!access_ok(VERIFY_WRITE, addr, 8))
+		goto sigbus;
+
+	value = regs->regs[reg];
+	StoreDW(addr, value, res);
+	if (res)
+		goto fault;
+	goto success;
+#endif /* CONFIG_64BIT */
+
+	/* Cannot handle 64-bit instructions in 32-bit kernel */
+	goto sigill;
+
+success:
+	regs->cp0_epc = contpc;	/* advance or branch */
+
+#ifdef CONFIG_DEBUG_FS
+	unaligned_instructions++;
+#endif
+	return;
+
+fault:
+	/* roll back jump/branch */
+	regs->cp0_epc = origpc;
+	regs->regs[31] = orig31;
+	/* Did we have an exception handler installed? */
+	if (fixup_exception(regs))
+		return;
+
+	die_if_kernel("Unhandled kernel unaligned access", regs);
+	force_sig(SIGSEGV, current);
+
+	return;
+
+sigbus:
+	die_if_kernel("Unhandled kernel unaligned access", regs);
+	force_sig(SIGBUS, current);
+
+	return;
+
+sigill:
+	die_if_kernel
+	    ("Unhandled kernel unaligned access or invalid instruction", regs);
+	force_sig(SIGILL, current);
+}
+
+static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr)
+{
+	unsigned long value;
+	unsigned int res;
+	int reg;
+	unsigned long orig31;
+	u16 __user *pc16;
+	unsigned long origpc;
+	union mips16e_instruction mips16inst, oldinst;
+
+	origpc = regs->cp0_epc;
+	orig31 = regs->regs[31];
+	pc16 = (unsigned short __user *)msk_isa16_mode(origpc);
+	/*
+	 * This load never faults.
+	 */
+	__get_user(mips16inst.full, pc16);
+	oldinst = mips16inst;
+
+	/* skip EXTEND instruction */
+	if (mips16inst.ri.opcode == MIPS16e_extend_op) {
+		pc16++;
+		__get_user(mips16inst.full, pc16);
+	} else if (delay_slot(regs)) {
+		/*  skip jump instructions */
+		/*  JAL/JALX are 32 bits but have OPCODE in first short int */
+		if (mips16inst.ri.opcode == MIPS16e_jal_op)
+			pc16++;
+		pc16++;
+		if (get_user(mips16inst.full, pc16))
+			goto sigbus;
+	}
+
+	switch (mips16inst.ri.opcode) {
+	case MIPS16e_i64_op:	/* I64 or RI64 instruction */
+		switch (mips16inst.i64.func) {	/* I64/RI64 func field check */
+		case MIPS16e_ldpc_func:
+		case MIPS16e_ldsp_func:
+			reg = reg16to32[mips16inst.ri64.ry];
+			goto loadDW;
+
+		case MIPS16e_sdsp_func:
+			reg = reg16to32[mips16inst.ri64.ry];
+			goto writeDW;
+
+		case MIPS16e_sdrasp_func:
+			reg = 29;	/* GPRSP */
+			goto writeDW;
+		}
+
+		goto sigbus;
+
+	case MIPS16e_swsp_op:
+	case MIPS16e_lwpc_op:
+	case MIPS16e_lwsp_op:
+		reg = reg16to32[mips16inst.ri.rx];
+		break;
+
+	case MIPS16e_i8_op:
+		if (mips16inst.i8.func != MIPS16e_swrasp_func)
+			goto sigbus;
+		reg = 29;	/* GPRSP */
+		break;
+
+	default:
+		reg = reg16to32[mips16inst.rri.ry];
+		break;
+	}
+
+	switch (mips16inst.ri.opcode) {
+
+	case MIPS16e_lb_op:
+	case MIPS16e_lbu_op:
+	case MIPS16e_sb_op:
+		goto sigbus;
+
+	case MIPS16e_lh_op:
+		if (!access_ok(VERIFY_READ, addr, 2))
+			goto sigbus;
+
+		LoadHW(addr, value, res);
+		if (res)
+			goto fault;
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		regs->regs[reg] = value;
+		break;
+
+	case MIPS16e_lhu_op:
+		if (!access_ok(VERIFY_READ, addr, 2))
+			goto sigbus;
+
+		LoadHWU(addr, value, res);
+		if (res)
+			goto fault;
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		regs->regs[reg] = value;
+		break;
+
+	case MIPS16e_lw_op:
+	case MIPS16e_lwpc_op:
+	case MIPS16e_lwsp_op:
+		if (!access_ok(VERIFY_READ, addr, 4))
+			goto sigbus;
+
+		LoadW(addr, value, res);
+		if (res)
+			goto fault;
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		regs->regs[reg] = value;
+		break;
+
+	case MIPS16e_lwu_op:
+#ifdef CONFIG_64BIT
+		/*
+		 * A 32-bit kernel might be running on a 64-bit processor.  But
+		 * if we're on a 32-bit processor and an i-cache incoherency
+		 * or race makes us see a 64-bit instruction here the sdl/sdr
+		 * would blow up, so for now we don't handle unaligned 64-bit
+		 * instructions on 32-bit kernels.
+		 */
+		if (!access_ok(VERIFY_READ, addr, 4))
+			goto sigbus;
+
+		LoadWU(addr, value, res);
+		if (res)
+			goto fault;
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		regs->regs[reg] = value;
+		break;
+#endif /* CONFIG_64BIT */
+
+		/* Cannot handle 64-bit instructions in 32-bit kernel */
+		goto sigill;
+
+	case MIPS16e_ld_op:
+loadDW:
+#ifdef CONFIG_64BIT
+		/*
+		 * A 32-bit kernel might be running on a 64-bit processor.  But
+		 * if we're on a 32-bit processor and an i-cache incoherency
+		 * or race makes us see a 64-bit instruction here the sdl/sdr
+		 * would blow up, so for now we don't handle unaligned 64-bit
+		 * instructions on 32-bit kernels.
+		 */
+		if (!access_ok(VERIFY_READ, addr, 8))
+			goto sigbus;
+
+		LoadDW(addr, value, res);
+		if (res)
+			goto fault;
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		regs->regs[reg] = value;
+		break;
+#endif /* CONFIG_64BIT */
+
+		/* Cannot handle 64-bit instructions in 32-bit kernel */
+		goto sigill;
+
+	case MIPS16e_sh_op:
+		if (!access_ok(VERIFY_WRITE, addr, 2))
+			goto sigbus;
+
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		value = regs->regs[reg];
+		StoreHW(addr, value, res);
+		if (res)
+			goto fault;
+		break;
+
+	case MIPS16e_sw_op:
+	case MIPS16e_swsp_op:
+	case MIPS16e_i8_op:	/* actually - MIPS16e_swrasp_func */
+		if (!access_ok(VERIFY_WRITE, addr, 4))
+			goto sigbus;
+
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		value = regs->regs[reg];
+		StoreW(addr, value, res);
+		if (res)
+			goto fault;
+		break;
+
+	case MIPS16e_sd_op:
+writeDW:
+#ifdef CONFIG_64BIT
+		/*
+		 * A 32-bit kernel might be running on a 64-bit processor.  But
+		 * if we're on a 32-bit processor and an i-cache incoherency
+		 * or race makes us see a 64-bit instruction here the sdl/sdr
+		 * would blow up, so for now we don't handle unaligned 64-bit
+		 * instructions on 32-bit kernels.
+		 */
+		if (!access_ok(VERIFY_WRITE, addr, 8))
+			goto sigbus;
+
+		MIPS16e_compute_return_epc(regs, &oldinst);
+		value = regs->regs[reg];
+		StoreDW(addr, value, res);
+		if (res)
+			goto fault;
+		break;
+#endif /* CONFIG_64BIT */
+
+		/* Cannot handle 64-bit instructions in 32-bit kernel */
+		goto sigill;
+
+	default:
+		/*
+		 * Pheeee...  We encountered an yet unknown instruction or
+		 * cache coherence problem.  Die sucker, die ...
+		 */
+		goto sigill;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	unaligned_instructions++;
+#endif
+
+	return;
+
+fault:
+	/* roll back jump/branch */
+	regs->cp0_epc = origpc;
+	regs->regs[31] = orig31;
+	/* Did we have an exception handler installed? */
+	if (fixup_exception(regs))
+		return;
+
+	die_if_kernel("Unhandled kernel unaligned access", regs);
+	force_sig(SIGSEGV, current);
+
+	return;
+
+sigbus:
+	die_if_kernel("Unhandled kernel unaligned access", regs);
+	force_sig(SIGBUS, current);
+
+	return;
+
+sigill:
+	die_if_kernel
+	    ("Unhandled kernel unaligned access or invalid instruction", regs);
+	force_sig(SIGILL, current);
+}
 asmlinkage void do_ade(struct pt_regs *regs)
 {
 	unsigned int __user *pc;
@@ -517,23 +1557,62 @@ asmlinkage void do_ade(struct pt_regs *regs)
 			1, regs, regs->cp0_badvaddr);
 	/*
 	 * Did we catch a fault trying to load an instruction?
-	 * Or are we running in MIPS16 mode?
 	 */
-	if ((regs->cp0_badvaddr == regs->cp0_epc) || (regs->cp0_epc & 0x1))
+	if (regs->cp0_badvaddr == regs->cp0_epc)
 		goto sigbus;
 
-	pc = (unsigned int __user *) exception_epc(regs);
 	if (user_mode(regs) && !test_thread_flag(TIF_FIXADE))
 		goto sigbus;
 	if (unaligned_action == UNALIGNED_ACTION_SIGNAL)
 		goto sigbus;
-	else if (unaligned_action == UNALIGNED_ACTION_SHOW)
-		show_registers(regs);
 
 	/*
 	 * Do branch emulation only if we didn't forward the exception.
 	 * This is all so but ugly ...
 	 */
+
+	/*
+	 * Are we running in microMIPS mode?
+	 */
+	if (get_isa16_mode(regs->cp0_epc)) {
+		/*
+		 * Did we catch a fault trying to load an instruction in
+		 * 16-bit mode?
+		 */
+		if (regs->cp0_badvaddr == msk_isa16_mode(regs->cp0_epc))
+			goto sigbus;
+		if (unaligned_action == UNALIGNED_ACTION_SHOW)
+			show_registers(regs);
+
+		if (cpu_has_mmips) {
+			seg = get_fs();
+			if (!user_mode(regs))
+				set_fs(KERNEL_DS);
+			emulate_load_store_microMIPS(regs,
+				(void __user *)regs->cp0_badvaddr);
+			set_fs(seg);
+
+			return;
+		}
+
+		if (cpu_has_mips16) {
+			seg = get_fs();
+			if (!user_mode(regs))
+				set_fs(KERNEL_DS);
+			emulate_load_store_MIPS16e(regs,
+				(void __user *)regs->cp0_badvaddr);
+			set_fs(seg);
+
+			return;
+	}
+
+		goto sigbus;
+	}
+
+	if (unaligned_action == UNALIGNED_ACTION_SHOW)
+		show_registers(regs);
+	pc = (unsigned int __user *)exception_epc(regs);
+
 	seg = get_fs();
 	if (!user_mode(regs))
 		set_fs(KERNEL_DS);