21 files changed, 270 insertions, 69 deletions

diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 68e2b7db9348..b0988fd62fcc 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -52,7 +52,6 @@ obj-$(CONFIG_MIPS_MT_SMP)	+= smp-mt.o
 obj-$(CONFIG_MIPS_CMP)		+= smp-cmp.o
 obj-$(CONFIG_MIPS_CPS)		+= smp-cps.o cps-vec.o
 obj-$(CONFIG_MIPS_CPS_NS16550)	+= cps-vec-ns16550.o
-obj-$(CONFIG_MIPS_GIC_IPI)	+= smp-gic.o
 obj-$(CONFIG_MIPS_SPRAM)	+= spram.o
 
 obj-$(CONFIG_MIPS_VPE_LOADER)	+= vpe.o
diff --git a/arch/mips/kernel/gpio_txx9.c b/arch/mips/kernel/gpio_txx9.c
index 705be43c3533..cbd47f38073b 100644
--- a/arch/mips/kernel/gpio_txx9.c
+++ b/arch/mips/kernel/gpio_txx9.c
@@ -10,7 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/errno.h>
 #include <linux/io.h>
 #include <asm/txx9pio.h>
@@ -85,5 +85,5 @@ int __init txx9_gpio_init(unsigned long baseaddr,
 		return -ENODEV;
 	txx9_gpio_chip.base = base;
 	txx9_gpio_chip.ngpio = num;
-	return gpiochip_add(&txx9_gpio_chip);
+	return gpiochip_add_data(&txx9_gpio_chip, NULL);
 }
diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c
index 1448c1f43d4e..760217bbb2fa 100644
--- a/arch/mips/kernel/mips-cm.c
+++ b/arch/mips/kernel/mips-cm.c
@@ -24,7 +24,7 @@ static char *cm2_tr[8] = {
 	"0x04", "cpc", "0x06", "0x07"
 };
 
-/* CM3 Tag ECC transation type */
+/* CM3 Tag ECC transaction type */
 static char *cm3_tr[16] = {
 	[0x0] = "ReqNoData",
 	[0x1] = "0x1",
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index 1f5aac7f9ec3..3fff89ae760b 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -940,42 +940,42 @@ repeat:
 		switch (rt) {
 		case tgei_op:
 			if ((long)regs->regs[rs] >= MIPSInst_SIMM(inst))
-				do_trap_or_bp(regs, 0, "TGEI");
+				do_trap_or_bp(regs, 0, 0, "TGEI");
 
 			MIPS_R2_STATS(traps);
 
 			break;
 		case tgeiu_op:
 			if (regs->regs[rs] >= MIPSInst_UIMM(inst))
-				do_trap_or_bp(regs, 0, "TGEIU");
+				do_trap_or_bp(regs, 0, 0, "TGEIU");
 
 			MIPS_R2_STATS(traps);
 
 			break;
 		case tlti_op:
 			if ((long)regs->regs[rs] < MIPSInst_SIMM(inst))
-				do_trap_or_bp(regs, 0, "TLTI");
+				do_trap_or_bp(regs, 0, 0, "TLTI");
 
 			MIPS_R2_STATS(traps);
 
 			break;
 		case tltiu_op:
 			if (regs->regs[rs] < MIPSInst_UIMM(inst))
-				do_trap_or_bp(regs, 0, "TLTIU");
+				do_trap_or_bp(regs, 0, 0, "TLTIU");
 
 			MIPS_R2_STATS(traps);
 
 			break;
 		case teqi_op:
 			if (regs->regs[rs] == MIPSInst_SIMM(inst))
-				do_trap_or_bp(regs, 0, "TEQI");
+				do_trap_or_bp(regs, 0, 0, "TEQI");
 
 			MIPS_R2_STATS(traps);
 
 			break;
 		case tnei_op:
 			if (regs->regs[rs] != MIPSInst_SIMM(inst))
-				do_trap_or_bp(regs, 0, "TNEI");
+				do_trap_or_bp(regs, 0, 0, "TNEI");
 
 			MIPS_R2_STATS(traps);
 
diff --git a/arch/mips/kernel/module-rela.c b/arch/mips/kernel/module-rela.c
index 2b70723071c3..9083d63b765c 100644
--- a/arch/mips/kernel/module-rela.c
+++ b/arch/mips/kernel/module-rela.c
@@ -109,9 +109,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		       struct module *me)
 {
 	Elf_Mips_Rela *rel = (void *) sechdrs[relsec].sh_addr;
+	int (*handler)(struct module *me, u32 *location, Elf_Addr v);
 	Elf_Sym *sym;
 	u32 *location;
-	unsigned int i;
+	unsigned int i, type;
 	Elf_Addr v;
 	int res;
 
@@ -134,9 +135,21 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 			return -ENOENT;
 		}
 
-		v = sym->st_value + rel[i].r_addend;
+		type = ELF_MIPS_R_TYPE(rel[i]);
+
+		if (type < ARRAY_SIZE(reloc_handlers_rela))
+			handler = reloc_handlers_rela[type];
+		else
+			handler = NULL;
 
-		res = reloc_handlers_rela[ELF_MIPS_R_TYPE(rel[i])](me, location, v);
+		if (!handler) {
+			pr_err("%s: Unknown relocation type %u\n",
+			       me->name, type);
+			return -EINVAL;
+		}
+
+		v = sym->st_value + rel[i].r_addend;
+		res = handler(me, location, v);
 		if (res)
 			return res;
 	}
diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c
index 1833f5171ccd..f9b2936d598d 100644
--- a/arch/mips/kernel/module.c
+++ b/arch/mips/kernel/module.c
@@ -197,9 +197,10 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab,
 		   struct module *me)
 {
 	Elf_Mips_Rel *rel = (void *) sechdrs[relsec].sh_addr;
+	int (*handler)(struct module *me, u32 *location, Elf_Addr v);
 	Elf_Sym *sym;
 	u32 *location;
-	unsigned int i;
+	unsigned int i, type;
 	Elf_Addr v;
 	int res;
 
@@ -223,9 +224,21 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab,
 			return -ENOENT;
 		}
 
-		v = sym->st_value;
+		type = ELF_MIPS_R_TYPE(rel[i]);
+
+		if (type < ARRAY_SIZE(reloc_handlers_rel))
+			handler = reloc_handlers_rel[type];
+		else
+			handler = NULL;
 
-		res = reloc_handlers_rel[ELF_MIPS_R_TYPE(rel[i])](me, location, v);
+		if (!handler) {
+			pr_err("%s: Unknown relocation type %u\n",
+			       me->name, type);
+			return -EINVAL;
+		}
+
+		v = sym->st_value;
+		res = handler(me, location, v);
 		if (res)
 			return res;
 	}
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index d7b8dd43147a..9bc1191b1ab0 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -530,7 +530,7 @@ static void mipspmu_enable(struct pmu *pmu)
 
 /*
  * MIPS performance counters can be per-TC. The control registers can
- * not be directly accessed accross CPUs. Hence if we want to do global
+ * not be directly accessed across CPUs. Hence if we want to do global
  * control, we need cross CPU calls. on_each_cpu() can help us, but we
  * can not make sure this function is called with interrupts enabled. So
  * here we pause local counters and then grab a rwlock and leave the
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index f63a289977cc..fa3f9ebad8f4 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -472,7 +472,7 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
 	/*
 	 * Disable all but self interventions. The load from COHCTL is defined
 	 * by the interAptiv & proAptiv SUMs as ensuring that the operation
-	 * resulting from the preceeding store is complete.
+	 * resulting from the preceding store is complete.
 	 */
 	uasm_i_addiu(&p, t0, zero, 1 << cpu_data[cpu].core);
 	uasm_i_sw(&p, t0, 0, r_pcohctl);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index eddd5fd6fdfa..92880cee449e 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -615,7 +615,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	 * allows us to only worry about whether an FP mode switch is in
 	 * progress when FP is first used in a tasks time slice. Pretty much all
 	 * of the mode switch overhead can thus be confined to cases where mode
-	 * switches are actually occuring. That is, to here. However for the
+	 * switches are actually occurring. That is, to here. However for the
 	 * thread performing the mode switch it may take a while...
 	 */
 	if (num_online_cpus() > 1) {
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index a56317444bda..d01fe53a6638 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -596,3 +596,5 @@ EXPORT(sys_call_table)
 	PTR	sys_membarrier
 	PTR	sys_mlock2
 	PTR	sys_copy_file_range		/* 4360 */
+	PTR	sys_preadv2
+	PTR	sys_pwritev2
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 2b2dc14610d0..6b73ecc02597 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -434,4 +434,6 @@ EXPORT(sys_call_table)
 	PTR	sys_membarrier
 	PTR	sys_mlock2
 	PTR	sys_copy_file_range		/* 5320 */
+	PTR	sys_preadv2
+	PTR	sys_pwritev2
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 2bf5c8593d91..71f99d5f7a06 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -424,4 +424,6 @@ EXPORT(sysn32_call_table)
 	PTR	sys_membarrier
 	PTR	sys_mlock2
 	PTR	sys_copy_file_range
+	PTR	compat_sys_preadv2		/* 6325 */
+	PTR	compat_sys_pwritev2
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index c5b759e584c7..91b43eea2d5a 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -579,4 +579,6 @@ EXPORT(sys32_call_table)
 	PTR	sys_membarrier
 	PTR	sys_mlock2
 	PTR	sys_copy_file_range		/* 4360 */
+	PTR	compat_sys_preadv2
+	PTR	compat_sys_pwritev2
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 5fdaf8bdcd2e..4f607341a793 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -732,21 +732,23 @@ static void __init resource_init(void)
 			end = HIGHMEM_START - 1;
 
 		res = alloc_bootmem(sizeof(struct resource));
+
+		res->start = start;
+		res->end = end;
+		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
 		switch (boot_mem_map.map[i].type) {
 		case BOOT_MEM_RAM:
 		case BOOT_MEM_INIT_RAM:
 		case BOOT_MEM_ROM_DATA:
 			res->name = "System RAM";
+			res->flags |= IORESOURCE_SYSRAM;
 			break;
 		case BOOT_MEM_RESERVED:
 		default:
 			res->name = "reserved";
 		}
 
-		res->start = start;
-		res->end = end;
-
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 		request_resource(&iomem_resource, res);
 
 		/*
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index d5e0f949dc48..76923349b4fe 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -149,8 +149,8 @@ void __init cmp_prepare_cpus(unsigned int max_cpus)
 }
 
 struct plat_smp_ops cmp_smp_ops = {
-	.send_ipi_single	= gic_send_ipi_single,
-	.send_ipi_mask		= gic_send_ipi_mask,
+	.send_ipi_single	= mips_smp_send_ipi_single,
+	.send_ipi_mask		= mips_smp_send_ipi_mask,
 	.init_secondary		= cmp_init_secondary,
 	.smp_finish		= cmp_smp_finish,
 	.boot_secondary		= cmp_boot_secondary,
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 2ad4e4c96d61..253e1409338c 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -472,8 +472,8 @@ static struct plat_smp_ops cps_smp_ops = {
 	.boot_secondary		= cps_boot_secondary,
 	.init_secondary		= cps_init_secondary,
 	.smp_finish		= cps_smp_finish,
-	.send_ipi_single	= gic_send_ipi_single,
-	.send_ipi_mask		= gic_send_ipi_mask,
+	.send_ipi_single	= mips_smp_send_ipi_single,
+	.send_ipi_mask		= mips_smp_send_ipi_mask,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_disable		= cps_cpu_disable,
 	.cpu_die		= cps_cpu_die,
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 86311a164ef1..4f9570a57e8d 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -121,7 +121,7 @@ static void vsmp_send_ipi_single(int cpu, unsigned int action)
 
 #ifdef CONFIG_MIPS_GIC
 	if (gic_present) {
-		gic_send_ipi_single(cpu, action);
+		mips_smp_send_ipi_single(cpu, action);
 		return;
 	}
 #endif
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 2b521e07b860..27cb638f0824 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -33,12 +33,16 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/ftrace.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
 
 #include <linux/atomic.h>
 #include <asm/cpu.h>
 #include <asm/processor.h>
 #include <asm/idle.h>
 #include <asm/r4k-timer.h>
+#include <asm/mips-cpc.h>
 #include <asm/mmu_context.h>
 #include <asm/time.h>
 #include <asm/setup.h>
@@ -79,6 +83,11 @@ static cpumask_t cpu_core_setup_map;
 
 cpumask_t cpu_coherent_mask;
 
+#ifdef CONFIG_GENERIC_IRQ_IPI
+static struct irq_desc *call_desc;
+static struct irq_desc *sched_desc;
+#endif
+
 static inline void set_cpu_sibling_map(int cpu)
 {
 	int i;
@@ -146,6 +155,145 @@ void register_smp_ops(struct plat_smp_ops *ops)
 	mp_ops = ops;
 }
 
+#ifdef CONFIG_GENERIC_IRQ_IPI
+void mips_smp_send_ipi_single(int cpu, unsigned int action)
+{
+	mips_smp_send_ipi_mask(cpumask_of(cpu), action);
+}
+
+void mips_smp_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+	unsigned long flags;
+	unsigned int core;
+	int cpu;
+
+	local_irq_save(flags);
+
+	switch (action) {
+	case SMP_CALL_FUNCTION:
+		__ipi_send_mask(call_desc, mask);
+		break;
+
+	case SMP_RESCHEDULE_YOURSELF:
+		__ipi_send_mask(sched_desc, mask);
+		break;
+
+	default:
+		BUG();
+	}
+
+	if (mips_cpc_present()) {
+		for_each_cpu(cpu, mask) {
+			core = cpu_data[cpu].core;
+
+			if (core == current_cpu_data.core)
+				continue;
+
+			while (!cpumask_test_cpu(cpu, &cpu_coherent_mask)) {
+				mips_cpc_lock_other(core);
+				write_cpc_co_cmd(CPC_Cx_CMD_PWRUP);
+				mips_cpc_unlock_other();
+			}
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+
+static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
+{
+	scheduler_ipi();
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
+{
+	generic_smp_call_function_interrupt();
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction irq_resched = {
+	.handler	= ipi_resched_interrupt,
+	.flags		= IRQF_PERCPU,
+	.name		= "IPI resched"
+};
+
+static struct irqaction irq_call = {
+	.handler	= ipi_call_interrupt,
+	.flags		= IRQF_PERCPU,
+	.name		= "IPI call"
+};
+
+static __init void smp_ipi_init_one(unsigned int virq,
+				    struct irqaction *action)
+{
+	int ret;
+
+	irq_set_handler(virq, handle_percpu_irq);
+	ret = setup_irq(virq, action);
+	BUG_ON(ret);
+}
+
+static int __init mips_smp_ipi_init(void)
+{
+	unsigned int call_virq, sched_virq;
+	struct irq_domain *ipidomain;
+	struct device_node *node;
+
+	/*
+	 * In some cases like qemu-malta, it is desired to try SMP with
+	 * a single core. Qemu-malta has no GIC, so an attempt to set any IPIs
+	 * would cause a BUG_ON() to be triggered since there's no ipidomain.
+	 *
+	 * Since for a single core system IPIs aren't required really, skip the
+	 * initialisation which should generally keep any such configurations
+	 * happy and only fail hard when trying to truely run SMP.
+	 */
+	if (cpumask_weight(cpu_possible_mask) == 1)
+		return 0;
+
+	node = of_irq_find_parent(of_root);
+	ipidomain = irq_find_matching_host(node, DOMAIN_BUS_IPI);
+
+	/*
+	 * Some platforms have half DT setup. So if we found irq node but
+	 * didn't find an ipidomain, try to search for one that is not in the
+	 * DT.
+	 */
+	if (node && !ipidomain)
+		ipidomain = irq_find_matching_host(NULL, DOMAIN_BUS_IPI);
+
+	BUG_ON(!ipidomain);
+
+	call_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask);
+	BUG_ON(!call_virq);
+
+	sched_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask);
+	BUG_ON(!sched_virq);
+
+	if (irq_domain_is_ipi_per_cpu(ipidomain)) {
+		int cpu;
+
+		for_each_cpu(cpu, cpu_possible_mask) {
+			smp_ipi_init_one(call_virq + cpu, &irq_call);
+			smp_ipi_init_one(sched_virq + cpu, &irq_resched);
+		}
+	} else {
+		smp_ipi_init_one(call_virq, &irq_call);
+		smp_ipi_init_one(sched_virq, &irq_resched);
+	}
+
+	call_desc = irq_to_desc(call_virq);
+	sched_desc = irq_to_desc(sched_virq);
+
+	return 0;
+}
+early_initcall(mips_smp_ipi_init);
+#endif
+
 /*
  * First C code run on the secondary CPUs after being started up by
  * the master.
@@ -192,7 +340,7 @@ asmlinkage void start_secondary(void)
 	WARN_ON_ONCE(!irqs_disabled());
 	mp_ops->smp_finish();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 static void stop_this_cpu(void *dummy)
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index bf14da9f3e33..ae0c89d23ad7 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -56,6 +56,7 @@
 #include <asm/pgtable.h>
 #include <asm/ptrace.h>
 #include <asm/sections.h>
+#include <asm/siginfo.h>
 #include <asm/tlbdebug.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
@@ -871,7 +872,7 @@ out:
 	exception_exit(prev_state);
 }
 
-void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
+void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
 	const char *str)
 {
 	siginfo_t info = { 0 };
@@ -928,7 +929,13 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 	default:
 		scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
 		die_if_kernel(b, regs);
-		force_sig(SIGTRAP, current);
+		if (si_code) {
+			info.si_signo = SIGTRAP;
+			info.si_code = si_code;
+			force_sig_info(SIGTRAP, &info, current);
+		} else {
+			force_sig(SIGTRAP, current);
+		}
 	}
 }
 
@@ -1012,7 +1019,7 @@ asmlinkage void do_bp(struct pt_regs *regs)
 		break;
 	}
 
-	do_trap_or_bp(regs, bcode, "Break");
+	do_trap_or_bp(regs, bcode, TRAP_BRKPT, "Break");
 
 out:
 	set_fs(seg);
@@ -1054,7 +1061,7 @@ asmlinkage void do_tr(struct pt_regs *regs)
 			tcode = (opcode >> 6) & ((1 << 10) - 1);
 	}
 
-	do_trap_or_bp(regs, tcode, "Trap");
+	do_trap_or_bp(regs, tcode, 0, "Trap");
 
 out:
 	set_fs(seg);
@@ -1115,19 +1122,7 @@ no_r2_instr:
 	if (unlikely(compute_return_epc(regs) < 0))
 		goto out;
 
-	if (get_isa16_mode(regs->cp0_epc)) {
-		unsigned short mmop[2] = { 0 };
-
-		if (unlikely(get_user(mmop[0], (u16 __user *)epc + 0) < 0))
-			status = SIGSEGV;
-		if (unlikely(get_user(mmop[1], (u16 __user *)epc + 1) < 0))
-			status = SIGSEGV;
-		opcode = mmop[0];
-		opcode = (opcode << 16) | mmop[1];
-
-		if (status < 0)
-			status = simulate_rdhwr_mm(regs, opcode);
-	} else {
+	if (!get_isa16_mode(regs->cp0_epc)) {
 		if (unlikely(get_user(opcode, epc) < 0))
 			status = SIGSEGV;
 
@@ -1142,6 +1137,18 @@ no_r2_instr:
 
 		if (status < 0)
 			status = simulate_fp(regs, opcode, old_epc, old31);
+	} else if (cpu_has_mmips) {
+		unsigned short mmop[2] = { 0 };
+
+		if (unlikely(get_user(mmop[0], (u16 __user *)epc + 0) < 0))
+			status = SIGSEGV;
+		if (unlikely(get_user(mmop[1], (u16 __user *)epc + 1) < 0))
+			status = SIGSEGV;
+		opcode = mmop[0];
+		opcode = (opcode << 16) | mmop[1];
+
+		if (status < 0)
+			status = simulate_rdhwr_mm(regs, opcode);
 	}
 
 	if (status < 0)
@@ -1492,6 +1499,7 @@ asmlinkage void do_mdmx(struct pt_regs *regs)
  */
 asmlinkage void do_watch(struct pt_regs *regs)
 {
+	siginfo_t info = { .si_signo = SIGTRAP, .si_code = TRAP_HWBKPT };
 	enum ctx_state prev_state;
 	u32 cause;
 
@@ -1512,7 +1520,7 @@ asmlinkage void do_watch(struct pt_regs *regs)
 	if (test_tsk_thread_flag(current, TIF_LOAD_WATCH)) {
 		mips_read_watch_registers();
 		local_irq_enable();
-		force_sig(SIGTRAP, current);
+		force_sig_info(SIGTRAP, &info, current);
 	} else {
 		mips_clear_watch_registers();
 		local_irq_enable();
@@ -2214,7 +2222,7 @@ void __init trap_init(void)
 
 	/*
 	 * Copy the generic exception handlers to their final destination.
-	 * This will be overriden later as suitable for a particular
+	 * This will be overridden later as suitable for a particular
 	 * configuration.
 	 */
 	set_handler(0x180, &except_vec3_generic, 0x80);
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 490cea569d57..5c62065cbf22 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -885,7 +885,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 {
 	union mips_instruction insn;
 	unsigned long value;
-	unsigned int res;
+	unsigned int res, preempted;
 	unsigned long origpc;
 	unsigned long orig31;
 	void __user *fault_addr = NULL;
@@ -1226,27 +1226,36 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			if (!access_ok(VERIFY_READ, addr, sizeof(*fpr)))
 				goto sigbus;
 
-			/*
-			 * Disable preemption to avoid a race between copying
-			 * state from userland, migrating to another CPU and
-			 * updating the hardware vector register below.
-			 */
-			preempt_disable();
-
-			res = __copy_from_user_inatomic(fpr, addr,
-							sizeof(*fpr));
-			if (res)
-				goto fault;
-
-			/*
-			 * Update the hardware register if it is in use by the
-			 * task in this quantum, in order to avoid having to
-			 * save & restore the whole vector context.
-			 */
-			if (test_thread_flag(TIF_USEDMSA))
-				write_msa_wr(wd, fpr, df);
+			do {
+				/*
+				 * If we have live MSA context keep track of
+				 * whether we get preempted in order to avoid
+				 * the register context we load being clobbered
+				 * by the live context as it's saved during
+				 * preemption. If we don't have live context
+				 * then it can't be saved to clobber the value
+				 * we load.
+				 */
+				preempted = test_thread_flag(TIF_USEDMSA);
+
+				res = __copy_from_user_inatomic(fpr, addr,
+								sizeof(*fpr));
+				if (res)
+					goto fault;
 
-			preempt_enable();
+				/*
+				 * Update the hardware register if it is in use
+				 * by the task in this quantum, in order to
+				 * avoid having to save & restore the whole
+				 * vector context.
+				 */
+				preempt_disable();
+				if (test_thread_flag(TIF_USEDMSA)) {
+					write_msa_wr(wd, fpr, df);
+					preempted = 0;
+				}
+				preempt_enable();
+			} while (preempted);
 			break;
 
 		case msa_st_op:
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 0a93e83cd014..54d653ee17e1 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -58,6 +58,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.text.*)
 		*(.fixup)
 		*(.gnu.warning)