Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS updates from Ralf Baechle:
 "This is the main pull request for MIPS for 4.8.  Also includes is a
  minor SSB cleanup as SSB code traditionally is merged through the MIPS
  tree:

  ATH25:
    - MIPS: Add default configuration for ath25

  Boot:
    - For zboot, copy appended dtb to the end of the kernel
    - store the appended dtb address in a variable

  BPF:
    - Fix off by one error in offset allocation

  Cobalt code:
    - Fix typos

  Core code:
    - debugfs_create_file returns NULL on error, so don't use IS_ERR for
      testing for errors.
    - Fix double locking issue in RM7000 S-cache code.  This would only
      affect RM7000 ARC systems on reboot.
    - Fix page table corruption on THP permission changes.
    - Use compat_sys_keyctl for 32 bit userspace on 64 bit kernels.
      David says, there are no compatibility issues raised by this fix.
    - Move some signal code around.
    - Rewrite r4k count/compare clockevent device registration such that
      min_delta_ticks/max_delta_ticks files are guaranteed to be
      initialized.
    - Only register r4k count/compare as clockevent device if we can
      assume the clock to be constant.
    - Fix MSA asm warnings in control reg accessors
    - uasm and tlbex fixes and tweaking.
    - Print segment physical address when EU=1.
    - Define AT_VECTOR_SIZE_ARCH for ARCH_DLINFO.
    - CP: Allow booting by VP other than VP 0
    - Cache handling fixes and optimizations for r4k class caches
    - Add hotplug support for R6 processors
    - Cleanup hotplug bits in kconfig
    - traps: return correct si code for accessing nonmapped addresses
    - Remove cpu_has_safe_index_cacheops

  Lantiq:
    - Register IRQ handler for virtual IRQ number
    - Fix EIU interrupt loading code
    - Use the real EXIN count
    - Fix build error.

  Loongson 3:
    - Increase HPET_MIN_PROG_DELTA and decrease HPET_MIN_CYCLES

  Octeon:
    - Delete built-in DTB pruning code for D-Link DSR-1000N.
    - Clean up GPIO definitions in dlink_dsr-1000n.dts.
    - Add more LEDs to the DSR-100n DTS
    - Fix off by one in octeon_irq_gpio_map()
    - Typo fixes
    - Enable SATA by default in cavium_octeon_defconfig
    - Support readq/writeq()
    - Remove forced mappings of USB interrupts.
    - Ensure DMA descriptors are always in the low 4GB
    - Improve USB reset code for OCTEON II.

  Pistachio:
    - Add maintainers entry for pistachio SoC Support
    - Remove plat_setup_iocoherency

  Ralink:
    - Fix pwm UART in spis group pinmux.

  SSB:
    - Change bare unsigned to unsigned int to suit coding style

  Tools:
    - Fix reloc tool compiler warnings.

  Other:
    - Delete use of ARCH_WANT_OPTIONAL_GPIOLIB"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (61 commits)
  MIPS: mm: Fix definition of R6 cache instruction
  MIPS: tools: Fix relocs tool compiler warnings
  MIPS: Cobalt: Fix typo
  MIPS: Octeon: Fix typo
  MIPS: Lantiq: Fix build failure
  MIPS: Use CPHYSADDR to implement mips32 __pa
  MIPS: Octeon: Dlink_dsr-1000n.dts: add more leds.
  MIPS: Octeon: Clean up GPIO definitions in dlink_dsr-1000n.dts.
  MIPS: Octeon: Delete built-in DTB pruning code for D-Link DSR-1000N.
  MIPS: store the appended dtb address in a variable
  MIPS: ZBOOT: copy appended dtb to the end of the kernel
  MIPS: ralink: fix spis group pinmux
  MIPS: Factor o32 specific code into signal_o32.c
  MIPS: non-exec stack & heap when non-exec PT_GNU_STACK is present
  MIPS: Use per-mm page to execute branch delay slot instructions
  MIPS: Modify error handling
  MIPS: c-r4k: Use SMP calls for CM indexed cache ops
  MIPS: c-r4k: Avoid small flush_icache_range SMP calls
  MIPS: c-r4k: Local flush_icache_range cache op override
  MIPS: c-r4k: Split r4k_flush_kernel_vmap_range()
  ...

19 files changed, 437 insertions, 331 deletions

diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index e6053d07072f..4a603a3ea657 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -71,7 +71,7 @@ obj-$(CONFIG_32BIT)		+= scall32-o32.o
 obj-$(CONFIG_64BIT)		+= scall64-64.o
 obj-$(CONFIG_MIPS32_COMPAT)	+= linux32.o ptrace32.o signal32.o
 obj-$(CONFIG_MIPS32_N32)	+= binfmt_elfn32.o scall64-n32.o signal_n32.o
-obj-$(CONFIG_MIPS32_O32)	+= binfmt_elfo32.o scall64-o32.o
+obj-$(CONFIG_MIPS32_O32)	+= binfmt_elfo32.o scall64-o32.o signal_o32.o
 
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_PROC_FS)		+= proc.o
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index e4c21bbf9422..804d2a2a19fe 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -276,12 +276,7 @@ int r4k_clockevent_init(void)
 				  CLOCK_EVT_FEAT_C3STOP |
 				  CLOCK_EVT_FEAT_PERCPU;
 
-	clockevent_set_clock(cd, mips_hpt_frequency);
-
-	/* Calculate the min / max delta */
-	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
 	min_delta		= calculate_min_delta();
-	cd->min_delta_ns	= clockevent_delta2ns(min_delta, cd);
 
 	cd->rating		= 300;
 	cd->irq			= irq;
@@ -289,7 +284,7 @@ int r4k_clockevent_init(void)
 	cd->set_next_event	= mips_next_event;
 	cd->event_handler	= mips_event_handler;
 
-	clockevents_register_device(cd);
+	clockevents_config_and_register(cd, mips_hpt_frequency, min_delta, 0x7fffffff);
 
 	if (cp0_timer_irq_installed)
 		return 0;
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index 1f910563fdf6..d76275da54cb 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static u64 notrace r4k_read_sched_clock(void)
+static u64 __maybe_unused notrace r4k_read_sched_clock(void)
 {
 	return read_c0_count();
 }
@@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void)
 
 	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 
+#ifndef CONFIG_CPU_FREQ
 	sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency);
+#endif
 
 	return 0;
 }
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index e6eb7f1f7723..6430bff21fff 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -8,9 +8,12 @@
  * option) any later version.
  */
 
+#include <linux/binfmts.h>
 #include <linux/elf.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 
+#include <asm/cpu-features.h>
 #include <asm/cpu-info.h>
 
 /* Whether to accept legacy-NaN and 2008-NaN user binaries.  */
@@ -326,3 +329,19 @@ void mips_set_personality_nan(struct arch_elf_state *state)
 		BUG();
 	}
 }
+
+int mips_elf_read_implies_exec(void *elf_ex, int exstack)
+{
+	if (exstack != EXSTACK_DISABLE_X) {
+		/* The binary doesn't request a non-executable stack */
+		return 1;
+	}
+
+	if (!cpu_has_rixi) {
+		/* The CPU doesn't support non-executable memory */
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mips_elf_read_implies_exec);
diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S
index 56e8fede3fd8..cf052204eb0a 100644
--- a/arch/mips/kernel/head.S
+++ b/arch/mips/kernel/head.S
@@ -93,21 +93,24 @@ NESTED(kernel_entry, 16, sp)			# kernel entry point
 	jr	t0
 0:
 
+#ifdef CONFIG_USE_OF
 #ifdef CONFIG_MIPS_RAW_APPENDED_DTB
-	PTR_LA		t0, __appended_dtb
+	PTR_LA		t2, __appended_dtb
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	li		t1, 0xd00dfeed
 #else
 	li		t1, 0xedfe0dd0
 #endif
-	lw		t2, (t0)
-	bne		t1, t2, not_found
-	 nop
+	lw		t0, (t2)
+	beq		t0, t1, dtb_found
+#endif
+	li		t1, -2
+	beq		a0, t1, dtb_found
+	move		t2, a1
 
-	move		a1, t0
-	PTR_LI		a0, -2
-not_found:
+	li		t2, 0
+dtb_found:
 #endif
 	PTR_LA		t0, __bss_start		# clear .bss
 	LONG_S		zero, (t0)
@@ -122,6 +125,10 @@ not_found:
 	LONG_S		a2, fw_arg2
 	LONG_S		a3, fw_arg3
 
+#ifdef CONFIG_USE_OF
+	LONG_S		t2, fw_passed_dtb
+#endif
+
 	MTC0		zero, CP0_CONTEXT	# clear context register
 	PTR_LA		$28, init_thread_union
 	/* Set the SP after an empty pt_regs.  */
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index 43fbadc78d0a..c3372cac6db2 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -283,7 +283,7 @@ static int jr_func(struct pt_regs *regs, u32 ir)
 		err = mipsr6_emul(regs, nir);
 		if (err > 0) {
 			regs->cp0_epc = nepc;
-			err = mips_dsemul(regs, nir, cepc);
+			err = mips_dsemul(regs, nir, epc, cepc);
 			if (err == SIGILL)
 				err = SIGEMT;
 			MIPS_R2_STATS(dsemul);
@@ -1033,7 +1033,7 @@ repeat:
 			if (nir) {
 				err = mipsr6_emul(regs, nir);
 				if (err > 0) {
-					err = mips_dsemul(regs, nir, cpc);
+					err = mips_dsemul(regs, nir, epc, cpc);
 					if (err == SIGILL)
 						err = SIGEMT;
 					MIPS_R2_STATS(dsemul);
@@ -1082,7 +1082,7 @@ repeat:
 			if (nir) {
 				err = mipsr6_emul(regs, nir);
 				if (err > 0) {
-					err = mips_dsemul(regs, nir, cpc);
+					err = mips_dsemul(regs, nir, epc, cpc);
 					if (err == SIGILL)
 						err = SIGEMT;
 					MIPS_R2_STATS(dsemul);
@@ -1149,7 +1149,7 @@ repeat:
 		if (nir) {
 			err = mipsr6_emul(regs, nir);
 			if (err > 0) {
-				err = mips_dsemul(regs, nir, cpc);
+				err = mips_dsemul(regs, nir, epc, cpc);
 				if (err == SIGILL)
 					err = SIGEMT;
 				MIPS_R2_STATS(dsemul);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 813ed7829c61..7429ad09fbe3 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -30,6 +30,7 @@
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
+#include <asm/dsemul.h>
 #include <asm/dsp.h>
 #include <asm/fpu.h>
 #include <asm/msa.h>
@@ -68,11 +69,22 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 	lose_fpu(0);
 	clear_thread_flag(TIF_MSA_CTX_LIVE);
 	clear_used_math();
+	atomic_set(&current->thread.bd_emu_frame, BD_EMUFRAME_NONE);
 	init_dsp();
 	regs->cp0_epc = pc;
 	regs->regs[29] = sp;
 }
 
+void exit_thread(struct task_struct *tsk)
+{
+	/*
+	 * User threads may have allocated a delay slot emulation frame.
+	 * If so, clean up that allocation.
+	 */
+	if (!(current->flags & PF_KTHREAD))
+		dsemul_thread_cleanup(tsk);
+}
+
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	/*
@@ -159,6 +171,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	clear_tsk_thread_flag(p, TIF_FPUBOUND);
 #endif /* CONFIG_MIPS_MT_FPAFF */
 
+	atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE);
+
 	if (clone_flags & CLONE_SETTLS)
 		ti->tp_value = regs->regs[7];
 
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 9c0b387d6427..51d3988933f8 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -348,7 +348,7 @@ EXPORT(sysn32_call_table)
 	PTR	sys_ni_syscall			/* available, was setaltroot */
 	PTR	sys_add_key
 	PTR	sys_request_key
-	PTR	sys_keyctl			/* 6245 */
+	PTR	compat_sys_keyctl		/* 6245 */
 	PTR	sys_set_thread_area
 	PTR	sys_inotify_init
 	PTR	sys_inotify_add_watch
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f4f28b1580de..6efa7136748f 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -504,7 +504,7 @@ EXPORT(sys32_call_table)
 	PTR	sys_ni_syscall			/* available, was setaltroot */
 	PTR	sys_add_key			/* 4280 */
 	PTR	sys_request_key
-	PTR	sys_keyctl
+	PTR	compat_sys_keyctl
 	PTR	sys_set_thread_area
 	PTR	sys_inotify_init
 	PTR	sys_inotify_add_watch		/* 4285 */
diff --git a/arch/mips/kernel/segment.c b/arch/mips/kernel/segment.c
index 87bc74a5a518..2703f218202e 100644
--- a/arch/mips/kernel/segment.c
+++ b/arch/mips/kernel/segment.c
@@ -26,17 +26,20 @@ static void build_segment_config(char *str, unsigned int cfg)
 
 	/*
 	 * Access modes MK, MSK and MUSK are mapped segments. Therefore
-	 * there is no direct physical address mapping.
+	 * there is no direct physical address mapping unless it becomes
+	 * unmapped uncached at error level due to EU.
 	 */
-	if ((am == 0) || (am > 3)) {
+	if ((am == 0) || (am > 3) || (cfg & MIPS_SEGCFG_EU))
 		str += sprintf(str, "         %03lx",
 			((cfg & MIPS_SEGCFG_PA) >> MIPS_SEGCFG_PA_SHIFT));
+	else
+		str += sprintf(str, "         UND");
+
+	if ((am == 0) || (am > 3))
 		str += sprintf(str, "         %01ld",
 			((cfg & MIPS_SEGCFG_C) >> MIPS_SEGCFG_C_SHIFT));
-	} else {
-		str += sprintf(str, "         UND");
+	else
 		str += sprintf(str, "         U");
-	}
 
 	/* Exception configuration. */
 	str += sprintf(str, "       %01ld\n",
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index ef408a03e818..36cf8d65c47d 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -875,6 +875,10 @@ void __init setup_arch(char **cmdline_p)
 unsigned long kernelsp[NR_CPUS];
 unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3;
 
+#ifdef CONFIG_USE_OF
+unsigned long fw_passed_dtb;
+#endif
+
 #ifdef CONFIG_DEBUG_FS
 struct dentry *mips_debugfs_dir;
 static int __init debugfs_mips(void)
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 1975cd2f7de6..9e224469c788 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -772,6 +772,14 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	struct mips_abi *abi = current->thread.abi;
 	void *vdso = current->mm->context.vdso;
 
+	/*
+	 * If we were emulating a delay slot instruction, exit that frame such
+	 * that addresses in the sigframe are as expected for userland and we
+	 * don't have a problem if we reuse the thread's frame for an
+	 * instruction within the signal handler.
+	 */
+	dsemul_thread_rollback(regs);
+
 	if (regs->regs[0]) {
 		switch(regs->regs[2]) {
 		case ERESTART_RESTARTBLOCK:
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 78c8349d151c..97b7c51b8251 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -6,129 +6,26 @@
  * Copyright (C) 1991, 1992  Linus Torvalds
  * Copyright (C) 1994 - 2000, 2006  Ralf Baechle
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2016, Imagination Technologies Ltd.
  */
-#include <linux/cache.h>
-#include <linux/compat.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/syscalls.h>
-#include <linux/errno.h>
-#include <linux/wait.h>
-#include <linux/ptrace.h>
-#include <linux/suspend.h>
-#include <linux/compiler.h>
-#include <linux/uaccess.h>
 
-#include <asm/abi.h>
-#include <asm/asm.h>
+#include <asm/compat.h>
 #include <asm/compat-signal.h>
-#include <linux/bitops.h>
-#include <asm/cacheflush.h>
-#include <asm/sim.h>
-#include <asm/ucontext.h>
-#include <asm/fpu.h>
-#include <asm/war.h>
-#include <asm/dsp.h>
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
 
 #include "signal-common.h"
 
-/*
- * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
- */
-#define __NR_O32_restart_syscall	4253
-
 /* 32-bit compatibility types */
 
 typedef unsigned int __sighandler32_t;
 typedef void (*vfptr_t)(void);
 
-struct ucontext32 {
-	u32		    uc_flags;
-	s32		    uc_link;
-	compat_stack_t      uc_stack;
-	struct sigcontext32 uc_mcontext;
-	compat_sigset_t	    uc_sigmask;	  /* mask last for extensibility */
-};
-
-struct sigframe32 {
-	u32 sf_ass[4];		/* argument save space for o32 */
-	u32 sf_pad[2];		/* Was: signal trampoline */
-	struct sigcontext32 sf_sc;
-	compat_sigset_t sf_mask;
-};
-
-struct rt_sigframe32 {
-	u32 rs_ass[4];			/* argument save space for o32 */
-	u32 rs_pad[2];			/* Was: signal trampoline */
-	compat_siginfo_t rs_info;
-	struct ucontext32 rs_uc;
-};
-
-static int setup_sigcontext32(struct pt_regs *regs,
-			      struct sigcontext32 __user *sc)
-{
-	int err = 0;
-	int i;
-
-	err |= __put_user(regs->cp0_epc, &sc->sc_pc);
-
-	err |= __put_user(0, &sc->sc_regs[0]);
-	for (i = 1; i < 32; i++)
-		err |= __put_user(regs->regs[i], &sc->sc_regs[i]);
-
-	err |= __put_user(regs->hi, &sc->sc_mdhi);
-	err |= __put_user(regs->lo, &sc->sc_mdlo);
-	if (cpu_has_dsp) {
-		err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp);
-		err |= __put_user(mfhi1(), &sc->sc_hi1);
-		err |= __put_user(mflo1(), &sc->sc_lo1);
-		err |= __put_user(mfhi2(), &sc->sc_hi2);
-		err |= __put_user(mflo2(), &sc->sc_lo2);
-		err |= __put_user(mfhi3(), &sc->sc_hi3);
-		err |= __put_user(mflo3(), &sc->sc_lo3);
-	}
-
-	/*
-	 * Save FPU state to signal context.  Signal handler
-	 * will "inherit" current FPU state.
-	 */
-	err |= protected_save_fp_context(sc);
-
-	return err;
-}
-
-static int restore_sigcontext32(struct pt_regs *regs,
-				struct sigcontext32 __user *sc)
-{
-	int err = 0;
-	s32 treg;
-	int i;
-
-	/* Always make any pending restarted system calls return -EINTR */
-	current->restart_block.fn = do_no_restart_syscall;
-
-	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
-	err |= __get_user(regs->hi, &sc->sc_mdhi);
-	err |= __get_user(regs->lo, &sc->sc_mdlo);
-	if (cpu_has_dsp) {
-		err |= __get_user(treg, &sc->sc_hi1); mthi1(treg);
-		err |= __get_user(treg, &sc->sc_lo1); mtlo1(treg);
-		err |= __get_user(treg, &sc->sc_hi2); mthi2(treg);
-		err |= __get_user(treg, &sc->sc_lo2); mtlo2(treg);
-		err |= __get_user(treg, &sc->sc_hi3); mthi3(treg);
-		err |= __get_user(treg, &sc->sc_lo3); mtlo3(treg);
-		err |= __get_user(treg, &sc->sc_dsp); wrdsp(treg, DSP_MASK);
-	}
-
-	for (i = 1; i < 32; i++)
-		err |= __get_user(regs->regs[i], &sc->sc_regs[i]);
-
-	return err ?: protected_restore_fp_context(sc);
-}
-
 /*
  * Atomically swap in the new signal mask, and wait for a signal.
  */
@@ -247,176 +144,3 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 
 	return 0;
 }
-
-asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
-{
-	struct sigframe32 __user *frame;
-	sigset_t blocked;
-	int sig;
-
-	frame = (struct sigframe32 __user *) regs.regs[29];
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-	if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask))
-		goto badframe;
-
-	set_current_blocked(&blocked);
-
-	sig = restore_sigcontext32(&regs, &frame->sf_sc);
-	if (sig < 0)
-		goto badframe;
-	else if (sig)
-		force_sig(sig, current);
-
-	/*
-	 * Don't let your children do this ...
-	 */
-	__asm__ __volatile__(
-		"move\t$29, %0\n\t"
-		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
-	/* Unreached */
-
-badframe:
-	force_sig(SIGSEGV, current);
-}
-
-asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
-{
-	struct rt_sigframe32 __user *frame;
-	sigset_t set;
-	int sig;
-
-	frame = (struct rt_sigframe32 __user *) regs.regs[29];
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
-		goto badframe;
-
-	set_current_blocked(&set);
-
-	sig = restore_sigcontext32(&regs, &frame->rs_uc.uc_mcontext);
-	if (sig < 0)
-		goto badframe;
-	else if (sig)
-		force_sig(sig, current);
-
-	if (compat_restore_altstack(&frame->rs_uc.uc_stack))
-		goto badframe;
-
-	/*
-	 * Don't let your children do this ...
-	 */
-	__asm__ __volatile__(
-		"move\t$29, %0\n\t"
-		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
-	/* Unreached */
-
-badframe:
-	force_sig(SIGSEGV, current);
-}
-
-static int setup_frame_32(void *sig_return, struct ksignal *ksig,
-			  struct pt_regs *regs, sigset_t *set)
-{
-	struct sigframe32 __user *frame;
-	int err = 0;
-
-	frame = get_sigframe(ksig, regs, sizeof(*frame));
-	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
-		return -EFAULT;
-
-	err |= setup_sigcontext32(regs, &frame->sf_sc);
-	err |= __copy_conv_sigset_to_user(&frame->sf_mask, set);
-
-	if (err)
-		return -EFAULT;
-
-	/*
-	 * Arguments to signal handler:
-	 *
-	 *   a0 = signal number
-	 *   a1 = 0 (should be cause)
-	 *   a2 = pointer to struct sigcontext
-	 *
-	 * $25 and c0_epc point to the signal handler, $29 points to the
-	 * struct sigframe.
-	 */
-	regs->regs[ 4] = ksig->sig;
-	regs->regs[ 5] = 0;
-	regs->regs[ 6] = (unsigned long) &frame->sf_sc;
-	regs->regs[29] = (unsigned long) frame;
-	regs->regs[31] = (unsigned long) sig_return;
-	regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler;
-
-	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
-	       current->comm, current->pid,
-	       frame, regs->cp0_epc, regs->regs[31]);
-
-	return 0;
-}
-
-static int setup_rt_frame_32(void *sig_return, struct ksignal *ksig,
-			     struct pt_regs *regs, sigset_t *set)
-{
-	struct rt_sigframe32 __user *frame;
-	int err = 0;
-
-	frame = get_sigframe(ksig, regs, sizeof(*frame));
-	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
-		return -EFAULT;
-
-	/* Convert (siginfo_t -> compat_siginfo_t) and copy to user. */
-	err |= copy_siginfo_to_user32(&frame->rs_info, &ksig->info);
-
-	/* Create the ucontext.	 */
-	err |= __put_user(0, &frame->rs_uc.uc_flags);
-	err |= __put_user(0, &frame->rs_uc.uc_link);
-	err |= __compat_save_altstack(&frame->rs_uc.uc_stack, regs->regs[29]);
-	err |= setup_sigcontext32(regs, &frame->rs_uc.uc_mcontext);
-	err |= __copy_conv_sigset_to_user(&frame->rs_uc.uc_sigmask, set);
-
-	if (err)
-		return -EFAULT;
-
-	/*
-	 * Arguments to signal handler:
-	 *
-	 *   a0 = signal number
-	 *   a1 = 0 (should be cause)
-	 *   a2 = pointer to ucontext
-	 *
-	 * $25 and c0_epc point to the signal handler, $29 points to
-	 * the struct rt_sigframe32.
-	 */
-	regs->regs[ 4] = ksig->sig;
-	regs->regs[ 5] = (unsigned long) &frame->rs_info;
-	regs->regs[ 6] = (unsigned long) &frame->rs_uc;
-	regs->regs[29] = (unsigned long) frame;
-	regs->regs[31] = (unsigned long) sig_return;
-	regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler;
-
-	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
-	       current->comm, current->pid,
-	       frame, regs->cp0_epc, regs->regs[31]);
-
-	return 0;
-}
-
-/*
- * o32 compatibility on 64-bit kernels, without DSP ASE
- */
-struct mips_abi mips_abi_32 = {
-	.setup_frame	= setup_frame_32,
-	.setup_rt_frame = setup_rt_frame_32,
-	.restart	= __NR_O32_restart_syscall,
-
-	.off_sc_fpregs = offsetof(struct sigcontext32, sc_fpregs),
-	.off_sc_fpc_csr = offsetof(struct sigcontext32, sc_fpc_csr),
-	.off_sc_used_math = offsetof(struct sigcontext32, sc_used_math),
-
-	.vdso		= &vdso_image_o32,
-};
diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c
new file mode 100644
index 000000000000..5e169fc5ca5c
--- /dev/null
+++ b/arch/mips/kernel/signal_o32.c
@@ -0,0 +1,285 @@
+/*
+ * 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) 1991, 1992  Linus Torvalds
+ * Copyright (C) 1994 - 2000, 2006  Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2016, Imagination Technologies Ltd.
+ */
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+
+#include <asm/abi.h>
+#include <asm/compat-signal.h>
+#include <asm/dsp.h>
+#include <asm/sim.h>
+#include <asm/unistd.h>
+
+#include "signal-common.h"
+
+/*
+ * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
+ */
+#define __NR_O32_restart_syscall	4253
+
+struct sigframe32 {
+	u32 sf_ass[4];		/* argument save space for o32 */
+	u32 sf_pad[2];		/* Was: signal trampoline */
+	struct sigcontext32 sf_sc;
+	compat_sigset_t sf_mask;
+};
+
+struct ucontext32 {
+	u32		    uc_flags;
+	s32		    uc_link;
+	compat_stack_t      uc_stack;
+	struct sigcontext32 uc_mcontext;
+	compat_sigset_t	    uc_sigmask;	  /* mask last for extensibility */
+};
+
+struct rt_sigframe32 {
+	u32 rs_ass[4];			/* argument save space for o32 */
+	u32 rs_pad[2];			/* Was: signal trampoline */
+	compat_siginfo_t rs_info;
+	struct ucontext32 rs_uc;
+};
+
+static int setup_sigcontext32(struct pt_regs *regs,
+			      struct sigcontext32 __user *sc)
+{
+	int err = 0;
+	int i;
+
+	err |= __put_user(regs->cp0_epc, &sc->sc_pc);
+
+	err |= __put_user(0, &sc->sc_regs[0]);
+	for (i = 1; i < 32; i++)
+		err |= __put_user(regs->regs[i], &sc->sc_regs[i]);
+
+	err |= __put_user(regs->hi, &sc->sc_mdhi);
+	err |= __put_user(regs->lo, &sc->sc_mdlo);
+	if (cpu_has_dsp) {
+		err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp);
+		err |= __put_user(mfhi1(), &sc->sc_hi1);
+		err |= __put_user(mflo1(), &sc->sc_lo1);
+		err |= __put_user(mfhi2(), &sc->sc_hi2);
+		err |= __put_user(mflo2(), &sc->sc_lo2);
+		err |= __put_user(mfhi3(), &sc->sc_hi3);
+		err |= __put_user(mflo3(), &sc->sc_lo3);
+	}
+
+	/*
+	 * Save FPU state to signal context.  Signal handler
+	 * will "inherit" current FPU state.
+	 */
+	err |= protected_save_fp_context(sc);
+
+	return err;
+}
+
+static int restore_sigcontext32(struct pt_regs *regs,
+				struct sigcontext32 __user *sc)
+{
+	int err = 0;
+	s32 treg;
+	int i;
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current->restart_block.fn = do_no_restart_syscall;
+
+	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
+	err |= __get_user(regs->hi, &sc->sc_mdhi);
+	err |= __get_user(regs->lo, &sc->sc_mdlo);
+	if (cpu_has_dsp) {
+		err |= __get_user(treg, &sc->sc_hi1); mthi1(treg);
+		err |= __get_user(treg, &sc->sc_lo1); mtlo1(treg);
+		err |= __get_user(treg, &sc->sc_hi2); mthi2(treg);
+		err |= __get_user(treg, &sc->sc_lo2); mtlo2(treg);
+		err |= __get_user(treg, &sc->sc_hi3); mthi3(treg);
+		err |= __get_user(treg, &sc->sc_lo3); mtlo3(treg);
+		err |= __get_user(treg, &sc->sc_dsp); wrdsp(treg, DSP_MASK);
+	}
+
+	for (i = 1; i < 32; i++)
+		err |= __get_user(regs->regs[i], &sc->sc_regs[i]);
+
+	return err ?: protected_restore_fp_context(sc);
+}
+
+static int setup_frame_32(void *sig_return, struct ksignal *ksig,
+			  struct pt_regs *regs, sigset_t *set)
+{
+	struct sigframe32 __user *frame;
+	int err = 0;
+
+	frame = get_sigframe(ksig, regs, sizeof(*frame));
+	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
+		return -EFAULT;
+
+	err |= setup_sigcontext32(regs, &frame->sf_sc);
+	err |= __copy_conv_sigset_to_user(&frame->sf_mask, set);
+
+	if (err)
+		return -EFAULT;
+
+	/*
+	 * Arguments to signal handler:
+	 *
+	 *   a0 = signal number
+	 *   a1 = 0 (should be cause)
+	 *   a2 = pointer to struct sigcontext
+	 *
+	 * $25 and c0_epc point to the signal handler, $29 points to the
+	 * struct sigframe.
+	 */
+	regs->regs[ 4] = ksig->sig;
+	regs->regs[ 5] = 0;
+	regs->regs[ 6] = (unsigned long) &frame->sf_sc;
+	regs->regs[29] = (unsigned long) frame;
+	regs->regs[31] = (unsigned long) sig_return;
+	regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler;
+
+	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
+	       current->comm, current->pid,
+	       frame, regs->cp0_epc, regs->regs[31]);
+
+	return 0;
+}
+
+asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+{
+	struct rt_sigframe32 __user *frame;
+	sigset_t set;
+	int sig;
+
+	frame = (struct rt_sigframe32 __user *) regs.regs[29];
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
+		goto badframe;
+
+	set_current_blocked(&set);
+
+	sig = restore_sigcontext32(&regs, &frame->rs_uc.uc_mcontext);
+	if (sig < 0)
+		goto badframe;
+	else if (sig)
+		force_sig(sig, current);
+
+	if (compat_restore_altstack(&frame->rs_uc.uc_stack))
+		goto badframe;
+
+	/*
+	 * Don't let your children do this ...
+	 */
+	__asm__ __volatile__(
+		"move\t$29, %0\n\t"
+		"j\tsyscall_exit"
+		:/* no outputs */
+		:"r" (&regs));
+	/* Unreached */
+
+badframe:
+	force_sig(SIGSEGV, current);
+}
+
+static int setup_rt_frame_32(void *sig_return, struct ksignal *ksig,
+			     struct pt_regs *regs, sigset_t *set)
+{
+	struct rt_sigframe32 __user *frame;
+	int err = 0;
+
+	frame = get_sigframe(ksig, regs, sizeof(*frame));
+	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
+		return -EFAULT;
+
+	/* Convert (siginfo_t -> compat_siginfo_t) and copy to user. */
+	err |= copy_siginfo_to_user32(&frame->rs_info, &ksig->info);
+
+	/* Create the ucontext.	 */
+	err |= __put_user(0, &frame->rs_uc.uc_flags);
+	err |= __put_user(0, &frame->rs_uc.uc_link);
+	err |= __compat_save_altstack(&frame->rs_uc.uc_stack, regs->regs[29]);
+	err |= setup_sigcontext32(regs, &frame->rs_uc.uc_mcontext);
+	err |= __copy_conv_sigset_to_user(&frame->rs_uc.uc_sigmask, set);
+
+	if (err)
+		return -EFAULT;
+
+	/*
+	 * Arguments to signal handler:
+	 *
+	 *   a0 = signal number
+	 *   a1 = 0 (should be cause)
+	 *   a2 = pointer to ucontext
+	 *
+	 * $25 and c0_epc point to the signal handler, $29 points to
+	 * the struct rt_sigframe32.
+	 */
+	regs->regs[ 4] = ksig->sig;
+	regs->regs[ 5] = (unsigned long) &frame->rs_info;
+	regs->regs[ 6] = (unsigned long) &frame->rs_uc;
+	regs->regs[29] = (unsigned long) frame;
+	regs->regs[31] = (unsigned long) sig_return;
+	regs->cp0_epc = regs->regs[25] = (unsigned long) ksig->ka.sa.sa_handler;
+
+	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
+	       current->comm, current->pid,
+	       frame, regs->cp0_epc, regs->regs[31]);
+
+	return 0;
+}
+
+/*
+ * o32 compatibility on 64-bit kernels, without DSP ASE
+ */
+struct mips_abi mips_abi_32 = {
+	.setup_frame	= setup_frame_32,
+	.setup_rt_frame = setup_rt_frame_32,
+	.restart	= __NR_O32_restart_syscall,
+
+	.off_sc_fpregs = offsetof(struct sigcontext32, sc_fpregs),
+	.off_sc_fpc_csr = offsetof(struct sigcontext32, sc_fpc_csr),
+	.off_sc_used_math = offsetof(struct sigcontext32, sc_used_math),
+
+	.vdso		= &vdso_image_o32,
+};
+
+
+asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
+{
+	struct sigframe32 __user *frame;
+	sigset_t blocked;
+	int sig;
+
+	frame = (struct sigframe32 __user *) regs.regs[29];
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask))
+		goto badframe;
+
+	set_current_blocked(&blocked);
+
+	sig = restore_sigcontext32(&regs, &frame->sf_sc);
+	if (sig < 0)
+		goto badframe;
+	else if (sig)
+		force_sig(sig, current);
+
+	/*
+	 * Don't let your children do this ...
+	 */
+	__asm__ __volatile__(
+		"move\t$29, %0\n\t"
+		"j\tsyscall_exit"
+		:/* no outputs */
+		:"r" (&regs));
+	/* Unreached */
+
+badframe:
+	force_sig(SIGSEGV, current);
+}
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index e02addc0307f..6d0f1321e084 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -363,6 +363,7 @@ static int bmips_cpu_disable(void)
 	pr_info("SMP: CPU%d is offline\n", cpu);
 
 	set_cpu_online(cpu, false);
+	calculate_cpu_foreign_map();
 	cpumask_clear_cpu(cpu, &cpu_callin_map);
 	clear_c0_status(IE_IRQ5);
 
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 05b3201271b4..e9d9fc6c754c 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -206,7 +206,7 @@ err_out:
 	}
 }
 
-static void boot_core(unsigned core)
+static void boot_core(unsigned int core, unsigned int vpe_id)
 {
 	u32 access, stat, seq_state;
 	unsigned timeout;
@@ -233,8 +233,9 @@ static void boot_core(unsigned core)
 		mips_cpc_lock_other(core);
 
 		if (mips_cm_revision() >= CM_REV_CM3) {
-			/* Run VP0 following the reset */
-			write_cpc_co_vp_run(0x1);
+			/* Run only the requested VP following the reset */
+			write_cpc_co_vp_stop(0xf);
+			write_cpc_co_vp_run(1 << vpe_id);
 
 			/*
 			 * Ensure that the VP_RUN register is written before the
@@ -306,7 +307,7 @@ static void cps_boot_secondary(int cpu, struct task_struct *idle)
 
 	if (!test_bit(core, core_power)) {
 		/* Boot a VPE on a powered down core */
-		boot_core(core);
+		boot_core(core, vpe_id);
 		goto out;
 	}
 
@@ -397,6 +398,7 @@ static int cps_cpu_disable(void)
 	atomic_sub(1 << cpu_vpe_id(&current_cpu_data), &core_cfg->vpe_mask);
 	smp_mb__after_atomic();
 	set_cpu_online(cpu, false);
+	calculate_cpu_foreign_map();
 	cpumask_clear_cpu(cpu, &cpu_callin_map);
 
 	return 0;
@@ -411,14 +413,16 @@ static enum {
 
 void play_dead(void)
 {
-	unsigned cpu, core;
+	unsigned int cpu, core, vpe_id;
 
 	local_irq_disable();
 	idle_task_exit();
 	cpu = smp_processor_id();
 	cpu_death = CPU_DEATH_POWER;
 
-	if (cpu_has_mipsmt) {
+	pr_debug("CPU%d going offline\n", cpu);
+
+	if (cpu_has_mipsmt || cpu_has_vp) {
 		core = cpu_data[cpu].core;
 
 		/* Look for another online VPE within the core */
@@ -439,10 +443,21 @@ void play_dead(void)
 	complete(&cpu_death_chosen);
 
 	if (cpu_death == CPU_DEATH_HALT) {
-		/* Halt this TC */
-		write_c0_tchalt(TCHALT_H);
-		instruction_hazard();
+		vpe_id = cpu_vpe_id(&cpu_data[cpu]);
+
+		pr_debug("Halting core %d VP%d\n", core, vpe_id);
+		if (cpu_has_mipsmt) {
+			/* Halt this TC */
+			write_c0_tchalt(TCHALT_H);
+			instruction_hazard();
+		} else if (cpu_has_vp) {
+			write_cpc_cl_vp_stop(1 << vpe_id);
+
+			/* Ensure that the VP_STOP register is written */
+			wmb();
+		}
 	} else {
+		pr_debug("Gating power to core %d\n", core);
 		/* Power down the core */
 		cps_pm_enter_state(CPS_PM_POWER_GATED);
 	}
@@ -469,6 +484,7 @@ static void wait_for_sibling_halt(void *ptr_cpu)
 static void cps_cpu_die(unsigned int cpu)
 {
 	unsigned core = cpu_data[cpu].core;
+	unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]);
 	unsigned stat;
 	int err;
 
@@ -497,10 +513,12 @@ static void cps_cpu_die(unsigned int cpu)
 		 * in which case the CPC will refuse to power down the core.
 		 */
 		do {
+			mips_cm_lock_other(core, vpe_id);
 			mips_cpc_lock_other(core);
 			stat = read_cpc_co_stat_conf();
 			stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK;
 			mips_cpc_unlock_other();
+			mips_cm_unlock_other();
 		} while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 &&
 			 stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 &&
 			 stat != CPC_Cx_STAT_CONF_SEQSTATE_U2);
@@ -517,6 +535,12 @@ static void cps_cpu_die(unsigned int cpu)
 					       (void *)(unsigned long)cpu, 1);
 		if (err)
 			panic("Failed to call remote sibling CPU\n");
+	} else if (cpu_has_vp) {
+		do {
+			mips_cm_lock_other(core, vpe_id);
+			stat = read_cpc_co_vp_running();
+			mips_cm_unlock_other();
+		} while (stat & (1 << vpe_id));
 	}
 }
 
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index f9d01e953acb..f95f094f36e4 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -72,7 +72,7 @@ EXPORT_SYMBOL(cpu_core_map);
  * A logcal cpu mask containing only one VPE per core to
  * reduce the number of IPIs on large MT systems.
  */
-cpumask_t cpu_foreign_map __read_mostly;
+cpumask_t cpu_foreign_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_foreign_map);
 
 /* representing cpus for which sibling maps can be computed */
@@ -124,7 +124,7 @@ static inline void set_cpu_core_map(int cpu)
  * Calculate a new cpu_foreign_map mask whenever a
  * new cpu appears or disappears.
  */
-static inline void calculate_cpu_foreign_map(void)
+void calculate_cpu_foreign_map(void)
 {
 	int i, k, core_present;
 	cpumask_t temp_foreign_map;
@@ -141,7 +141,9 @@ static inline void calculate_cpu_foreign_map(void)
 			cpumask_set_cpu(i, &temp_foreign_map);
 	}
 
-	cpumask_copy(&cpu_foreign_map, &temp_foreign_map);
+	for_each_online_cpu(i)
+		cpumask_andnot(&cpu_foreign_map[i],
+			       &temp_foreign_map, &cpu_sibling_map[i]);
 }
 
 struct plat_smp_ops *mp_ops;
@@ -344,16 +346,9 @@ asmlinkage void start_secondary(void)
 static void stop_this_cpu(void *dummy)
 {
 	/*
-	 * Remove this CPU. Be a bit slow here and
-	 * set the bits for every online CPU so we don't miss
-	 * any IPI whilst taking this VPE down.
+	 * Remove this CPU:
 	 */
 
-	cpumask_copy(&cpu_foreign_map, cpu_online_mask);
-
-	/* Make it visible to every other CPU */
-	smp_mb();
-
 	set_cpu_online(smp_processor_id(), false);
 	calculate_cpu_foreign_map();
 	local_irq_disable();
@@ -512,10 +507,17 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned l
 		smp_on_other_tlbs(flush_tlb_range_ipi, &fd);
 	} else {
 		unsigned int cpu;
+		int exec = vma->vm_flags & VM_EXEC;
 
 		for_each_online_cpu(cpu) {
+			/*
+			 * flush_cache_range() will only fully flush icache if
+			 * the VMA is executable, otherwise we must invalidate
+			 * ASID without it appearing to has_valid_asid() as if
+			 * mm has been completely unused by that CPU.
+			 */
 			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
-				cpu_context(cpu, mm) = 0;
+				cpu_context(cpu, mm) = !exec;
 		}
 	}
 	local_flush_tlb_range(vma, start, end);
@@ -560,8 +562,14 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 		unsigned int cpu;
 
 		for_each_online_cpu(cpu) {
+			/*
+			 * flush_cache_page() only does partial flushes, so
+			 * invalidate ASID without it appearing to
+			 * has_valid_asid() as if mm has been completely unused
+			 * by that CPU.
+			 */
 			if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm))
-				cpu_context(cpu, vma->vm_mm) = 0;
+				cpu_context(cpu, vma->vm_mm) = 1;
 		}
 	}
 	local_flush_tlb_page(vma, page);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 6fb4704bd156..3de85be2486a 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -704,6 +704,7 @@ asmlinkage void do_ov(struct pt_regs *regs)
 int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 {
 	struct siginfo si = { 0 };
+	struct vm_area_struct *vma;
 
 	switch (sig) {
 	case 0:
@@ -744,7 +745,8 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 		si.si_addr = fault_addr;
 		si.si_signo = sig;
 		down_read(&current->mm->mmap_sem);
-		if (find_vma(current->mm, (unsigned long)fault_addr))
+		vma = find_vma(current->mm, (unsigned long)fault_addr);
+		if (vma && (vma->vm_start <= (unsigned long)fault_addr))
 			si.si_code = SEGV_ACCERR;
 		else
 			si.si_code = SEGV_MAPERR;
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 54e1663ce639..9abe447a4b48 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -107,6 +107,16 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
+	/* Map delay slot emulation page */
+	base = mmap_region(NULL, STACK_TOP, PAGE_SIZE,
+			   VM_READ|VM_WRITE|VM_EXEC|
+			   VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+			   0);
+	if (IS_ERR_VALUE(base)) {
+		ret = base;
+		goto out;
+	}
+
 	/*
 	 * Determine total area size. This includes the VDSO data itself, the
 	 * data page, and the GIC user page if present. Always create a mapping