Merge branch 'mipsr6-for-3.20' of git://git.linux-mips.org/pub/scm/mchandras/linux into mips-for-linux-next

65 files changed, 4405 insertions, 415 deletions

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index b1b2de537860..8523db534919 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -377,8 +377,10 @@ config MIPS_MALTA
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_HAS_CPU_MIPS32_R3_5
+	select SYS_HAS_CPU_MIPS32_R6
 	select SYS_HAS_CPU_MIPS64_R1
 	select SYS_HAS_CPU_MIPS64_R2
+	select SYS_HAS_CPU_MIPS64_R6
 	select SYS_HAS_CPU_NEVADA
 	select SYS_HAS_CPU_RM7000
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -1034,6 +1036,9 @@ config MIPS_MACHINE
 config NO_IOPORT_MAP
 	def_bool n
 
+config GENERIC_CSUM
+	bool
+
 config GENERIC_ISA_DMA
 	bool
 	select ZONE_DMA if GENERIC_ISA_DMA_SUPPORT_BROKEN=n
@@ -1147,6 +1152,9 @@ config SOC_PNX8335
 	bool
 	select SOC_PNX833X
 
+config MIPS_SPRAM
+	bool
+
 config SWAP_IO_SPACE
 	bool
 
@@ -1305,6 +1313,22 @@ config CPU_MIPS32_R2
 	  specific type of processor in your system, choose those that one
 	  otherwise CPU_MIPS32_R1 is a safe bet for any MIPS32 system.
 
+config CPU_MIPS32_R6
+	bool "MIPS32 Release 6 (EXPERIMENTAL)"
+	depends on SYS_HAS_CPU_MIPS32_R6
+	select CPU_HAS_PREFETCH
+	select CPU_SUPPORTS_32BIT_KERNEL
+	select CPU_SUPPORTS_HIGHMEM
+	select CPU_SUPPORTS_MSA
+	select GENERIC_CSUM
+	select HAVE_KVM
+	select MIPS_O32_FP64_SUPPORT
+	help
+	  Choose this option to build a kernel for release 6 or later of the
+	  MIPS32 architecture.  New MIPS processors, starting with the Warrior
+	  family, are based on a MIPS32r6 processor. If you own an older
+	  processor, you probably need to select MIPS32r1 or MIPS32r2 instead.
+
 config CPU_MIPS64_R1
 	bool "MIPS64 Release 1"
 	depends on SYS_HAS_CPU_MIPS64_R1
@@ -1340,6 +1364,21 @@ config CPU_MIPS64_R2
 	  specific type of processor in your system, choose those that one
 	  otherwise CPU_MIPS64_R1 is a safe bet for any MIPS64 system.
 
+config CPU_MIPS64_R6
+	bool "MIPS64 Release 6 (EXPERIMENTAL)"
+	depends on SYS_HAS_CPU_MIPS64_R6
+	select CPU_HAS_PREFETCH
+	select CPU_SUPPORTS_32BIT_KERNEL
+	select CPU_SUPPORTS_64BIT_KERNEL
+	select CPU_SUPPORTS_HIGHMEM
+	select CPU_SUPPORTS_MSA
+	select GENERIC_CSUM
+	help
+	  Choose this option to build a kernel for release 6 or later of the
+	  MIPS64 architecture.  New MIPS processors, starting with the Warrior
+	  family, are based on a MIPS64r6 processor. If you own an older
+	  processor, you probably need to select MIPS64r1 or MIPS64r2 instead.
+
 config CPU_R3000
 	bool "R3000"
 	depends on SYS_HAS_CPU_R3000
@@ -1540,7 +1579,7 @@ endchoice
 config CPU_MIPS32_3_5_FEATURES
 	bool "MIPS32 Release 3.5 Features"
 	depends on SYS_HAS_CPU_MIPS32_R3_5
-	depends on CPU_MIPS32_R2
+	depends on CPU_MIPS32_R2 || CPU_MIPS32_R6
 	help
 	  Choose this option to build a kernel for release 2 or later of the
 	  MIPS32 architecture including features from the 3.5 release such as
@@ -1660,12 +1699,18 @@ config SYS_HAS_CPU_MIPS32_R2
 config SYS_HAS_CPU_MIPS32_R3_5
 	bool
 
+config SYS_HAS_CPU_MIPS32_R6
+	bool
+
 config SYS_HAS_CPU_MIPS64_R1
 	bool
 
 config SYS_HAS_CPU_MIPS64_R2
 	bool
 
+config SYS_HAS_CPU_MIPS64_R6
+	bool
+
 config SYS_HAS_CPU_R3000
 	bool
 
@@ -1765,11 +1810,11 @@ endmenu
 #
 config CPU_MIPS32
 	bool
-	default y if CPU_MIPS32_R1 || CPU_MIPS32_R2
+	default y if CPU_MIPS32_R1 || CPU_MIPS32_R2 || CPU_MIPS32_R6
 
 config CPU_MIPS64
 	bool
-	default y if CPU_MIPS64_R1 || CPU_MIPS64_R2
+	default y if CPU_MIPS64_R1 || CPU_MIPS64_R2 || CPU_MIPS64_R6
 
 #
 # These two indicate the revision of the architecture, either Release 1 or Release 2
@@ -1781,6 +1826,12 @@ config CPU_MIPSR1
 config CPU_MIPSR2
 	bool
 	default y if CPU_MIPS32_R2 || CPU_MIPS64_R2 || CPU_CAVIUM_OCTEON
+	select MIPS_SPRAM
+
+config CPU_MIPSR6
+	bool
+	default y if CPU_MIPS32_R6 || CPU_MIPS64_R6
+	select MIPS_SPRAM
 
 config EVA
 	bool
@@ -2014,6 +2065,19 @@ config MIPS_MT_FPAFF
 	default y
 	depends on MIPS_MT_SMP
 
+config MIPSR2_TO_R6_EMULATOR
+	bool "MIPS R2-to-R6 emulator"
+	depends on CPU_MIPSR6 && !SMP
+	default y
+	help
+	  Choose this option if you want to run non-R6 MIPS userland code.
+	  Even if you say 'Y' here, the emulator will still be disabled by
+	  default. You can enable it using the 'mipsr2emul' kernel option.
+	  The only reason this is a build-time option is to save ~14K from the
+	  final kernel image.
+comment "MIPS R2-to-R6 emulator is only available for UP kernels"
+	depends on SMP && CPU_MIPSR6
+
 config MIPS_VPE_LOADER
 	bool "VPE loader support."
 	depends on SYS_SUPPORTS_MULTITHREADING && MODULES
@@ -2149,7 +2213,7 @@ config CPU_HAS_SMARTMIPS
 	  here.
 
 config CPU_MICROMIPS
-	depends on 32BIT && SYS_SUPPORTS_MICROMIPS
+	depends on 32BIT && SYS_SUPPORTS_MICROMIPS && !CPU_MIPSR6
 	bool "microMIPS"
 	help
 	  When this option is enabled the kernel will be built using the
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 88a9f433f6fc..3a2b775e8458 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -122,17 +122,4 @@ config SPINLOCK_TEST
 	help
 	  Add several files to the debugfs to test spinlock speed.
 
-config FP32XX_HYBRID_FPRS
-	bool "Run FP32 & FPXX code with hybrid FPRs"
-	depends on MIPS_O32_FP64_SUPPORT
-	help
-	  The hybrid FPR scheme is normally used only when a program needs to
-	  execute a mix of FP32 & FP64A code, since the trapping & emulation
-	  that it entails is expensive. When enabled, this option will lead
-	  to the kernel running programs which use the FP32 & FPXX FP ABIs
-	  using the hybrid FPR scheme, which can be useful for debugging
-	  purposes.
-
-	  If unsure, say N.
-
 endmenu
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 67109e53ebc0..b3de8ec06e88 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -138,10 +138,12 @@ cflags-$(CONFIG_CPU_MIPS32_R1)	+= $(call cc-option,-march=mips32,-mips32 -U_MIPS
 			-Wa,-mips32 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS32_R2)	+= $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
 			-Wa,-mips32r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R6)	+= -march=mips32r6 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS64_R1)	+= $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
 			-Wa,-mips64 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS64_R2)	+= $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
 			-Wa,-mips64r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R6)	+= -march=mips64r6 -Wa,--trap
 cflags-$(CONFIG_CPU_R5000)	+= -march=r5000 -Wa,--trap
 cflags-$(CONFIG_CPU_R5432)	+= $(call cc-option,-march=r5400,-march=r5000) \
 			-Wa,--trap
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
new file mode 100644
index 000000000000..4bce1f8ebe98
--- /dev/null
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -0,0 +1,193 @@
+CONFIG_MIPS_MALTA=y
+CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_CPU_MIPS32_R6=y
+CONFIG_PAGE_SIZE_16KB=y
+CONFIG_HZ_100=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=15
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_EMBEDDED=y
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PCI=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=m
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_NET_IPIP=m
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_IPCOMP=m
+# CONFIG_INET_LRO is not set
+CONFIG_INET6_AH=m
+CONFIG_INET6_ESP=m
+CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_TUNNEL=m
+CONFIG_BRIDGE=m
+CONFIG_VLAN_8021Q=m
+CONFIG_ATALK=m
+CONFIG_DEV_APPLETALK=m
+CONFIG_IPDDP=m
+CONFIG_IPDDP_ENCAP=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_CBQ=m
+CONFIG_NET_SCH_HTB=m
+CONFIG_NET_SCH_HFSC=m
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NET_SCH_RED=m
+CONFIG_NET_SCH_SFQ=m
+CONFIG_NET_SCH_TEQL=m
+CONFIG_NET_SCH_TBF=m
+CONFIG_NET_SCH_GRED=m
+CONFIG_NET_SCH_DSMARK=m
+CONFIG_NET_SCH_NETEM=m
+CONFIG_NET_SCH_INGRESS=m
+CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_TCINDEX=m
+CONFIG_NET_CLS_ROUTE4=m
+CONFIG_NET_CLS_FW=m
+CONFIG_NET_CLS_U32=m
+CONFIG_NET_CLS_RSVP=m
+CONFIG_NET_CLS_RSVP6=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_ACT_POLICE=y
+CONFIG_NET_CLS_IND=y
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_IDE=y
+# CONFIG_IDE_PROC_FS is not set
+# CONFIG_IDEPCI_PCIBUS_ORDER is not set
+CONFIG_BLK_DEV_GENERIC=y
+CONFIG_BLK_DEV_PIIX=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_SG=y
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_ALTEON is not set
+CONFIG_PCNET32=y
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
+# CONFIG_NET_VENDOR_EMULEX is not set
+# CONFIG_NET_VENDOR_EXAR is not set
+# CONFIG_NET_VENDOR_HP is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MELLANOX is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MYRI is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_PACKET_ENGINE is not set
+# CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_TOSHIBA is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+# CONFIG_VT is not set
+CONFIG_LEGACY_PTY_COUNT=4
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_HW_RANDOM=y
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_MATROX=y
+CONFIG_FB_MATROX_G=y
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_UHCI_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_BACKLIGHT=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_CMOS=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_XFS_FS=y
+CONFIG_XFS_QUOTA=y
+CONFIG_XFS_POSIX_ACL=y
+CONFIG_QUOTA=y
+CONFIG_QFMT_V2=y
+CONFIG_MSDOS_FS=m
+CONFIG_VFAT_FS=m
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
+CONFIG_CIFS=m
+CONFIG_CIFS_WEAK_PW_HASH=y
+CONFIG_CIFS_XATTR=y
+CONFIG_CIFS_POSIX=y
+CONFIG_NLS_CODEPAGE_437=m
+CONFIG_NLS_ISO8859_1=m
+# CONFIG_FTRACE is not set
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+# CONFIG_CRYPTO_HW is not set
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 200efeac4181..526539cbc99f 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,4 +1,5 @@
 # MIPS headers
+generic-(CONFIG_GENERIC_CSUM) += checksum.h
 generic-y += cputime.h
 generic-y += current.h
 generic-y += dma-contiguous.h
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 6caf8766b80f..0cae4595e985 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -19,7 +19,7 @@
 #include <asm/asmmacro-64.h>
 #endif
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	.macro	local_irq_enable reg=t0
 	ei
 	irq_enable_hazard
@@ -104,7 +104,8 @@
 	.endm
 
 	.macro	fpu_save_double thread status tmp
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f
 	fpu_save_16odd \thread
@@ -160,7 +161,8 @@
 	.endm
 
 	.macro	fpu_restore_double thread status tmp
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f				# 16 register mode?
 
@@ -170,16 +172,16 @@
 	fpu_restore_16even \thread \tmp
 	.endm
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	.macro	_EXT	rd, rs, p, s
 	ext	\rd, \rs, \p, \s
 	.endm
-#else /* !CONFIG_CPU_MIPSR2 */
+#else /* !CONFIG_CPU_MIPSR2 || !CONFIG_CPU_MIPSR6 */
 	.macro	_EXT	rd, rs, p, s
 	srl	\rd, \rs, \p
 	andi	\rd, \rd, (1 << \s) - 1
 	.endm
-#endif /* !CONFIG_CPU_MIPSR2 */
+#endif /* !CONFIG_CPU_MIPSR2 || !CONFIG_CPU_MIPSR6 */
 
 /*
  * Temporary until all gas have MT ASE support
@@ -304,7 +306,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -313,7 +315,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 857da84cfc92..26d436336f2e 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -54,19 +54,19 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 		"	sc	%0, %1					\n"   \
 		"	beqzl	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)	      \
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		int temp;						      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	ll	%0, %1		# atomic_" #op "\n"   \
 			"	" #asm_op " %0, %2			\n"   \
 			"	sc	%0, %1				\n"   \
 			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)      \
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
 			: "Ir" (i));					      \
 		} while (unlikely(!temp));				      \
 	} else {							      \
@@ -97,20 +97,20 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF12_ASM() (v->counter)			      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		int temp;						      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	ll	%1, %2	# atomic_" #op "_return	\n"   \
 			"	" #asm_op " %0, %1, %3			\n"   \
 			"	sc	%0, %2				\n"   \
 			"	.set	mips0				\n"   \
 			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF12_ASM() (v->counter)		      \
+			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
 			: "Ir" (i));					      \
 		} while (unlikely(!result));				      \
 									      \
@@ -171,14 +171,14 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF12_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF12_ASM() (v->counter)
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)
+		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		int temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
 		"	subu	%0, %1, %3				\n"
 		"	bltz	%0, 1f					\n"
@@ -190,7 +190,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF12_ASM() (v->counter)
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "Ir" (i));
 	} else {
 		unsigned long flags;
@@ -333,19 +333,19 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 		"	scd	%0, %1					\n"   \
 		"	beqzl	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)	      \
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		long temp;						      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	lld	%0, %1		# atomic64_" #op "\n" \
 			"	" #asm_op " %0, %2			\n"   \
 			"	scd	%0, %1				\n"   \
 			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (v->counter)      \
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
 			: "Ir" (i));					      \
 		} while (unlikely(!temp));				      \
 	} else {							      \
@@ -376,21 +376,21 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
-		  "+" GCC_OFF12_ASM() (v->counter)			      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
 	} else if (kernel_uses_llsc) {					      \
 		long temp;						      \
 									      \
 		do {							      \
 			__asm__ __volatile__(				      \
-			"	.set	arch=r4000			\n"   \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
 			"	lld	%1, %2	# atomic64_" #op "_return\n"  \
 			"	" #asm_op " %0, %1, %3			\n"   \
 			"	scd	%0, %2				\n"   \
 			"	.set	mips0				\n"   \
 			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF12_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF12_ASM() (v->counter)	      \
+			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
 			: "memory");					      \
 		} while (unlikely(!result));				      \
 									      \
@@ -452,14 +452,14 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "=" GCC_OFF12_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF12_ASM() (v->counter)
+		  "=" GCC_OFF_SMALL_ASM() (v->counter)
+		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		long temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
 		"	dsubu	%0, %1, %3				\n"
 		"	bltz	%0, 1f					\n"
@@ -471,7 +471,7 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF12_ASM() (v->counter)
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "Ir" (i));
 	} else {
 		unsigned long flags;
diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index 6663bcca9d0c..9f935f6aa996 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -79,28 +79,28 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC	"%0, %1					\n"
 		"	beqzl	%0, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=" GCC_OFF12_ASM() (*m)
-		: "ir" (1UL << bit), GCC_OFF12_ASM() (*m));
-#ifdef CONFIG_CPU_MIPSR2
+		: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m)
+		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m));
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
 		do {
 			__asm__ __volatile__(
 			"	" __LL "%0, %1		# set_bit	\n"
 			"	" __INS "%0, %3, %2, 1			\n"
 			"	" __SC "%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (bit), "r" (~0));
 		} while (unlikely(!temp));
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1		# set_bit	\n"
 			"	or	%0, %2				\n"
 			"	" __SC	"%0, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (1UL << bit));
 		} while (unlikely(!temp));
 	} else
@@ -131,28 +131,28 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC "%0, %1					\n"
 		"	beqzl	%0, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 		: "ir" (~(1UL << bit)));
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
 		do {
 			__asm__ __volatile__(
 			"	" __LL "%0, %1		# clear_bit	\n"
 			"	" __INS "%0, $0, %2, 1			\n"
 			"	" __SC "%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (bit));
 		} while (unlikely(!temp));
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1		# clear_bit	\n"
 			"	and	%0, %2				\n"
 			"	" __SC "%0, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (~(1UL << bit)));
 		} while (unlikely(!temp));
 	} else
@@ -197,7 +197,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC	"%0, %1				\n"
 		"	beqzl	%0, 1b				\n"
 		"	.set	mips0				\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 		: "ir" (1UL << bit));
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
@@ -205,12 +205,12 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1		# change_bit	\n"
 			"	xor	%0, %2				\n"
 			"	" __SC	"%0, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
 			: "ir" (1UL << bit));
 		} while (unlikely(!temp));
 	} else
@@ -245,7 +245,7 @@ static inline int test_and_set_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
 		: "memory");
 	} else if (kernel_uses_llsc) {
@@ -254,12 +254,12 @@ static inline int test_and_set_bit(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1	# test_and_set_bit	\n"
 			"	or	%2, %0, %3			\n"
 			"	" __SC	"%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
@@ -308,12 +308,12 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL "%0, %1	# test_and_set_bit	\n"
 			"	or	%2, %0, %3			\n"
 			"	" __SC	"%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
@@ -355,10 +355,10 @@ static inline int test_and_clear_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
 		: "memory");
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(nr)) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
@@ -369,7 +369,7 @@ static inline int test_and_clear_bit(unsigned long nr,
 			"	" __EXT "%2, %0, %3, 1			\n"
 			"	" __INS "%0, $0, %3, 1			\n"
 			"	" __SC	"%0, %1				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "ir" (bit)
 			: "memory");
 		} while (unlikely(!temp));
@@ -380,13 +380,13 @@ static inline int test_and_clear_bit(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL	"%0, %1 # test_and_clear_bit	\n"
 			"	or	%2, %0, %3			\n"
 			"	xor	%2, %3				\n"
 			"	" __SC	"%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
@@ -428,7 +428,7 @@ static inline int test_and_change_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 		: "r" (1UL << bit)
 		: "memory");
 	} else if (kernel_uses_llsc) {
@@ -437,12 +437,12 @@ static inline int test_and_change_bit(unsigned long nr,
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	" __LL	"%0, %1 # test_and_change_bit	\n"
 			"	xor	%2, %0, %3			\n"
 			"	" __SC	"\t%2, %1			\n"
 			"	.set	mips0				\n"
-			: "=&r" (temp), "+" GCC_OFF12_ASM() (*m), "=&r" (res)
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
 			: "r" (1UL << bit)
 			: "memory");
 		} while (unlikely(!res));
@@ -485,7 +485,7 @@ static inline unsigned long __fls(unsigned long word)
 	    __builtin_constant_p(cpu_has_clo_clz) && cpu_has_clo_clz) {
 		__asm__(
 		"	.set	push					\n"
-		"	.set	mips32					\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"	clz	%0, %1					\n"
 		"	.set	pop					\n"
 		: "=r" (num)
@@ -498,7 +498,7 @@ static inline unsigned long __fls(unsigned long word)
 	    __builtin_constant_p(cpu_has_mips64) && cpu_has_mips64) {
 		__asm__(
 		"	.set	push					\n"
-		"	.set	mips64					\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"	dclz	%0, %1					\n"
 		"	.set	pop					\n"
 		: "=r" (num)
@@ -562,7 +562,7 @@ static inline int fls(int x)
 	if (__builtin_constant_p(cpu_has_clo_clz) && cpu_has_clo_clz) {
 		__asm__(
 		"	.set	push					\n"
-		"	.set	mips32					\n"
+		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"	clz	%0, %1					\n"
 		"	.set	pop					\n"
 		: "=r" (x)
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 5996252680c6..5c585c5c1c3e 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -12,6 +12,10 @@
 #ifndef _ASM_CHECKSUM_H
 #define _ASM_CHECKSUM_H
 
+#ifdef CONFIG_GENERIC_CSUM
+#include <asm-generic/checksum.h>
+#else
+
 #include <linux/in6.h>
 
 #include <asm/uaccess.h>
@@ -274,5 +278,6 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 }
 
 #include <asm-generic/checksum.h>
+#endif /* CONFIG_GENERIC_CSUM */
 
 #endif /* _ASM_CHECKSUM_H */
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 28b1edf19501..d0a2a68ca600 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -31,24 +31,24 @@ static inline unsigned long __xchg_u32(volatile int * m, unsigned int val)
 		"	sc	%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (retval), "=" GCC_OFF12_ASM() (*m), "=&r" (dummy)
-		: GCC_OFF12_ASM() (*m), "Jr" (val)
+		: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy)
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		unsigned long dummy;
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	ll	%0, %3		# xchg_u32	\n"
 			"	.set	mips0				\n"
 			"	move	%2, %z4				\n"
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	sc	%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (retval), "=" GCC_OFF12_ASM() (*m),
+			: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m),
 			  "=&r" (dummy)
-			: GCC_OFF12_ASM() (*m), "Jr" (val)
+			: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 			: "memory");
 		} while (unlikely(!dummy));
 	} else {
@@ -82,22 +82,22 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val)
 		"	scd	%2, %1					\n"
 		"	beqzl	%2, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (retval), "=" GCC_OFF12_ASM() (*m), "=&r" (dummy)
-		: GCC_OFF12_ASM() (*m), "Jr" (val)
+		: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy)
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		unsigned long dummy;
 
 		do {
 			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
+			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 			"	lld	%0, %3		# xchg_u64	\n"
 			"	move	%2, %z4				\n"
 			"	scd	%2, %1				\n"
 			"	.set	mips0				\n"
-			: "=&r" (retval), "=" GCC_OFF12_ASM() (*m),
+			: "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m),
 			  "=&r" (dummy)
-			: GCC_OFF12_ASM() (*m), "Jr" (val)
+			: GCC_OFF_SMALL_ASM() (*m), "Jr" (val)
 			: "memory");
 		} while (unlikely(!dummy));
 	} else {
@@ -158,25 +158,25 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		"	beqzl	$1, 1b				\n"	\
 		"2:						\n"	\
 		"	.set	pop				\n"	\
-		: "=&r" (__ret), "=" GCC_OFF12_ASM() (*m)		\
-		: GCC_OFF12_ASM() (*m), "Jr" (old), "Jr" (new)		\
+		: "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m)		\
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new)		\
 		: "memory");						\
 	} else if (kernel_uses_llsc) {					\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"1:	" ld "	%0, %2		# __cmpxchg_asm \n"	\
 		"	bne	%0, %z3, 2f			\n"	\
 		"	.set	mips0				\n"	\
 		"	move	$1, %z4				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"	" st "	$1, %1				\n"	\
 		"	beqz	$1, 1b				\n"	\
 		"	.set	pop				\n"	\
 		"2:						\n"	\
-		: "=&r" (__ret), "=" GCC_OFF12_ASM() (*m)		\
-		: GCC_OFF12_ASM() (*m), "Jr" (old), "Jr" (new)		\
+		: "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m)		\
+		: GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new)		\
 		: "memory");						\
 	} else {							\
 		unsigned long __flags;					\
diff --git a/arch/mips/include/asm/compiler.h b/arch/mips/include/asm/compiler.h
index c73815e0123a..e081a265f422 100644
--- a/arch/mips/include/asm/compiler.h
+++ b/arch/mips/include/asm/compiler.h
@@ -16,12 +16,30 @@
 #define GCC_REG_ACCUM "accum"
 #endif
 
+#ifdef CONFIG_CPU_MIPSR6
+/* All MIPS R6 toolchains support the ZC constrain */
+#define GCC_OFF_SMALL_ASM() "ZC"
+#else
 #ifndef CONFIG_CPU_MICROMIPS
-#define GCC_OFF12_ASM() "R"
+#define GCC_OFF_SMALL_ASM() "R"
 #elif __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9)
-#define GCC_OFF12_ASM() "ZC"
+#define GCC_OFF_SMALL_ASM() "ZC"
 #else
 #error "microMIPS compilation unsupported with GCC older than 4.9"
-#endif
+#endif /* CONFIG_CPU_MICROMIPS */
+#endif /* CONFIG_CPU_MIPSR6 */
+
+#ifdef CONFIG_CPU_MIPSR6
+#define MIPS_ISA_LEVEL "mips64r6"
+#define MIPS_ISA_ARCH_LEVEL MIPS_ISA_LEVEL
+#define MIPS_ISA_LEVEL_RAW mips64r6
+#define MIPS_ISA_ARCH_LEVEL_RAW MIPS_ISA_LEVEL_RAW
+#else
+/* MIPS64 is a superset of MIPS32 */
+#define MIPS_ISA_LEVEL "mips64r2"
+#define MIPS_ISA_ARCH_LEVEL "arch=r4000"
+#define MIPS_ISA_LEVEL_RAW mips64r2
+#define MIPS_ISA_ARCH_LEVEL_RAW MIPS_ISA_LEVEL_RAW
+#endif /* CONFIG_CPU_MIPSR6 */
 
 #endif /* _ASM_COMPILER_H */
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 2897cfafcaf0..0d8208de9a3f 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -38,6 +38,9 @@
 #ifndef cpu_has_maar
 #define cpu_has_maar		(cpu_data[0].options & MIPS_CPU_MAAR)
 #endif
+#ifndef cpu_has_rw_llb
+#define cpu_has_rw_llb		(cpu_data[0].options & MIPS_CPU_RW_LLB)
+#endif
 
 /*
  * For the moment we don't consider R6000 and R8000 so we can assume that
@@ -171,6 +174,9 @@
 #endif
 #endif
 
+#ifndef cpu_has_mips_1
+# define cpu_has_mips_1		(!cpu_has_mips_r6)
+#endif
 #ifndef cpu_has_mips_2
 # define cpu_has_mips_2		(cpu_data[0].isa_level & MIPS_CPU_ISA_II)
 #endif
@@ -189,12 +195,18 @@
 #ifndef cpu_has_mips32r2
 # define cpu_has_mips32r2	(cpu_data[0].isa_level & MIPS_CPU_ISA_M32R2)
 #endif
+#ifndef cpu_has_mips32r6
+# define cpu_has_mips32r6	(cpu_data[0].isa_level & MIPS_CPU_ISA_M32R6)
+#endif
 #ifndef cpu_has_mips64r1
 # define cpu_has_mips64r1	(cpu_data[0].isa_level & MIPS_CPU_ISA_M64R1)
 #endif
 #ifndef cpu_has_mips64r2
 # define cpu_has_mips64r2	(cpu_data[0].isa_level & MIPS_CPU_ISA_M64R2)
 #endif
+#ifndef cpu_has_mips64r6
+# define cpu_has_mips64r6	(cpu_data[0].isa_level & MIPS_CPU_ISA_M64R6)
+#endif
 
 /*
  * Shortcuts ...
@@ -208,17 +220,23 @@
 #define cpu_has_mips_4_5_r	(cpu_has_mips_4 | cpu_has_mips_5_r)
 #define cpu_has_mips_5_r	(cpu_has_mips_5 | cpu_has_mips_r)
 
-#define cpu_has_mips_4_5_r2	(cpu_has_mips_4_5 | cpu_has_mips_r2)
+#define cpu_has_mips_4_5_r2_r6	(cpu_has_mips_4_5 | cpu_has_mips_r2 | \
+				 cpu_has_mips_r6)
 
-#define cpu_has_mips32	(cpu_has_mips32r1 | cpu_has_mips32r2)
-#define cpu_has_mips64	(cpu_has_mips64r1 | cpu_has_mips64r2)
+#define cpu_has_mips32	(cpu_has_mips32r1 | cpu_has_mips32r2 | cpu_has_mips32r6)
+#define cpu_has_mips64	(cpu_has_mips64r1 | cpu_has_mips64r2 | cpu_has_mips64r6)
 #define cpu_has_mips_r1 (cpu_has_mips32r1 | cpu_has_mips64r1)
 #define cpu_has_mips_r2 (cpu_has_mips32r2 | cpu_has_mips64r2)
+#define cpu_has_mips_r6	(cpu_has_mips32r6 | cpu_has_mips64r6)
 #define cpu_has_mips_r	(cpu_has_mips32r1 | cpu_has_mips32r2 | \
-			 cpu_has_mips64r1 | cpu_has_mips64r2)
+			 cpu_has_mips32r6 | cpu_has_mips64r1 | \
+			 cpu_has_mips64r2 | cpu_has_mips64r6)
+
+/* MIPSR2 and MIPSR6 have a lot of similarities */
+#define cpu_has_mips_r2_r6	(cpu_has_mips_r2 | cpu_has_mips_r6)
 
 #ifndef cpu_has_mips_r2_exec_hazard
-#define cpu_has_mips_r2_exec_hazard cpu_has_mips_r2
+#define cpu_has_mips_r2_exec_hazard (cpu_has_mips_r2 | cpu_has_mips_r6)
 #endif
 
 /*
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index b4e2bd87df50..8245875f8b33 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -54,6 +54,13 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	case CPU_M5150:
 #endif
 
+#if defined(CONFIG_SYS_HAS_CPU_MIPS32_R2) || \
+    defined(CONFIG_SYS_HAS_CPU_MIPS32_R6) || \
+    defined(CONFIG_SYS_HAS_CPU_MIPS64_R2) || \
+    defined(CONFIG_SYS_HAS_CPU_MIPS64_R6)
+	case CPU_QEMU_GENERIC:
+#endif
+
 #ifdef CONFIG_SYS_HAS_CPU_MIPS64_R1
 	case CPU_5KC:
 	case CPU_5KE:
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 33866fce4d63..15687234d70a 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -93,6 +93,7 @@
  * These are the PRID's for when 23:16 == PRID_COMP_MIPS
  */
 
+#define PRID_IMP_QEMU_GENERIC	0x0000
 #define PRID_IMP_4KC		0x8000
 #define PRID_IMP_5KC		0x8100
 #define PRID_IMP_20KC		0x8200
@@ -312,6 +313,8 @@ enum cpu_type_enum {
 	CPU_LOONGSON3, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS,
 	CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP,
 
+	CPU_QEMU_GENERIC,
+
 	CPU_LAST
 };
 
@@ -329,11 +332,14 @@ enum cpu_type_enum {
 #define MIPS_CPU_ISA_M32R2	0x00000020
 #define MIPS_CPU_ISA_M64R1	0x00000040
 #define MIPS_CPU_ISA_M64R2	0x00000080
+#define MIPS_CPU_ISA_M32R6	0x00000100
+#define MIPS_CPU_ISA_M64R6	0x00000200
 
 #define MIPS_CPU_ISA_32BIT (MIPS_CPU_ISA_II | MIPS_CPU_ISA_M32R1 | \
-	MIPS_CPU_ISA_M32R2)
+	MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M32R6)
 #define MIPS_CPU_ISA_64BIT (MIPS_CPU_ISA_III | MIPS_CPU_ISA_IV | \
-	MIPS_CPU_ISA_V | MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)
+	MIPS_CPU_ISA_V | MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2 | \
+	MIPS_CPU_ISA_M64R6)
 
 /*
  * CPU Option encodings
@@ -370,6 +376,7 @@ enum cpu_type_enum {
 #define MIPS_CPU_RIXIEX		0x200000000ull /* CPU has unique exception codes for {Read, Execute}-Inhibit exceptions */
 #define MIPS_CPU_MAAR		0x400000000ull /* MAAR(I) registers are present */
 #define MIPS_CPU_FRE		0x800000000ull /* FRE & UFE bits implemented */
+#define MIPS_CPU_RW_LLB		0x1000000000ull /* LLADDR/LLB writes are allowed */
 
 /*
  * CPU ASE encodings
diff --git a/arch/mips/include/asm/edac.h b/arch/mips/include/asm/edac.h
index ae6fedcb0060..94105d3f58f4 100644
--- a/arch/mips/include/asm/edac.h
+++ b/arch/mips/include/asm/edac.h
@@ -26,8 +26,8 @@ static inline void atomic_scrub(void *va, u32 size)
 		"	sc	%0, %1					\n"
 		"	beqz	%0, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=" GCC_OFF12_ASM() (*virt_addr)
-		: GCC_OFF12_ASM() (*virt_addr));
+		: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*virt_addr)
+		: GCC_OFF_SMALL_ASM() (*virt_addr));
 
 		virt_addr++;
 	}
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index eb4d95de619c..535f196ffe02 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -417,13 +417,15 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 struct arch_elf_state {
 	int fp_abi;
 	int interp_fp_abi;
-	int overall_abi;
+	int overall_fp_mode;
 };
 
+#define MIPS_ABI_FP_UNKNOWN	(-1)	/* Unknown FP ABI (kernel internal) */
+
 #define INIT_ARCH_ELF_STATE {			\
-	.fp_abi = -1,				\
-	.interp_fp_abi = -1,			\
-	.overall_abi = -1,			\
+	.fp_abi = MIPS_ABI_FP_UNKNOWN,		\
+	.interp_fp_abi = MIPS_ABI_FP_UNKNOWN,	\
+	.overall_fp_mode = -1,			\
 }
 
 extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf,
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 994d21939676..b96d9d327626 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -68,7 +68,8 @@ static inline int __enable_fpu(enum fpu_mode mode)
 		goto fr_common;
 
 	case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_64BIT))
+#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6) \
+      || defined(CONFIG_64BIT))
 		/* we only have a 32-bit FPU */
 		return SIGFPE;
 #endif
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index ef9987a61d88..1de190bdfb9c 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -45,19 +45,19 @@
 		"	"__UA_ADDR "\t2b, 4b			\n"	\
 		"	.previous				\n"	\
 		: "=r" (ret), "=&r" (oldval),				\
-		  "=" GCC_OFF12_ASM() (*uaddr)				\
-		: "0" (0), GCC_OFF12_ASM() (*uaddr), "Jr" (oparg),	\
+		  "=" GCC_OFF_SMALL_ASM() (*uaddr)				\
+		: "0" (0), GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oparg),	\
 		  "i" (-EFAULT)						\
 		: "memory");						\
 	} else if (cpu_has_llsc) {					\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"1:	"user_ll("%1", "%4")" # __futex_atomic_op\n"	\
 		"	.set	mips0				\n"	\
 		"	" insn	"				\n"	\
-		"	.set	arch=r4000			\n"	\
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"	\
 		"2:	"user_sc("$1", "%2")"			\n"	\
 		"	beqz	$1, 1b				\n"	\
 		__WEAK_LLSC_MB						\
@@ -74,8 +74,8 @@
 		"	"__UA_ADDR "\t2b, 4b			\n"	\
 		"	.previous				\n"	\
 		: "=r" (ret), "=&r" (oldval),				\
-		  "=" GCC_OFF12_ASM() (*uaddr)				\
-		: "0" (0), GCC_OFF12_ASM() (*uaddr), "Jr" (oparg),	\
+		  "=" GCC_OFF_SMALL_ASM() (*uaddr)				\
+		: "0" (0), GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oparg),	\
 		  "i" (-EFAULT)						\
 		: "memory");						\
 	} else								\
@@ -174,8 +174,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "+r" (ret), "=&r" (val), "=" GCC_OFF12_ASM() (*uaddr)
-		: GCC_OFF12_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
+		: "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr)
+		: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
 		  "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
@@ -183,12 +183,12 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"# futex_atomic_cmpxchg_inatomic			\n"
 		"	.set	push					\n"
 		"	.set	noat					\n"
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"1:	"user_ll("%1", "%3")"				\n"
 		"	bne	%1, %z4, 3f				\n"
 		"	.set	mips0					\n"
 		"	move	$1, %z5					\n"
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"2:	"user_sc("$1", "%2")"				\n"
 		"	beqz	$1, 1b					\n"
 		__WEAK_LLSC_MB
@@ -203,8 +203,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		"	"__UA_ADDR "\t1b, 4b				\n"
 		"	"__UA_ADDR "\t2b, 4b				\n"
 		"	.previous					\n"
-		: "+r" (ret), "=&r" (val), "=" GCC_OFF12_ASM() (*uaddr)
-		: GCC_OFF12_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
+		: "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr)
+		: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
 		  "i" (-EFAULT)
 		: "memory");
 	} else
diff --git a/arch/mips/include/asm/hazards.h b/arch/mips/include/asm/hazards.h
index e3ee92d4dbe7..4087b47ad1cb 100644
--- a/arch/mips/include/asm/hazards.h
+++ b/arch/mips/include/asm/hazards.h
@@ -11,6 +11,7 @@
 #define _ASM_HAZARDS_H
 
 #include <linux/stringify.h>
+#include <asm/compiler.h>
 
 #define ___ssnop							\
 	sll	$0, $0, 1
@@ -21,7 +22,7 @@
 /*
  * TLB hazards
  */
-#if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_CPU_CAVIUM_OCTEON)
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) && !defined(CONFIG_CPU_CAVIUM_OCTEON)
 
 /*
  * MIPSR2 defines ehb for hazard avoidance
@@ -58,7 +59,7 @@ do {									\
 	unsigned long tmp;						\
 									\
 	__asm__ __volatile__(						\
-	"	.set	mips64r2				\n"	\
+	"	.set "MIPS_ISA_LEVEL"				\n"	\
 	"	dla	%0, 1f					\n"	\
 	"	jr.hb	%0					\n"	\
 	"	.set	mips0					\n"	\
@@ -132,7 +133,7 @@ do {									\
 
 #define instruction_hazard()						\
 do {									\
-	if (cpu_has_mips_r2)						\
+	if (cpu_has_mips_r2_r6)						\
 		__instruction_hazard();					\
 } while (0)
 
@@ -240,7 +241,7 @@ do {									\
 
 #define __disable_fpu_hazard
 
-#elif defined(CONFIG_CPU_MIPSR2)
+#elif defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 
 #define __enable_fpu_hazard						\
 	___ehb
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index 0fa5fdcd1f01..d60cc68fa31e 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -15,9 +15,10 @@
 
 #include <linux/compiler.h>
 #include <linux/stringify.h>
+#include <asm/compiler.h>
 #include <asm/hazards.h>
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined (CONFIG_CPU_MIPSR6)
 
 static inline void arch_local_irq_disable(void)
 {
@@ -118,7 +119,7 @@ void arch_local_irq_disable(void);
 unsigned long arch_local_irq_save(void);
 void arch_local_irq_restore(unsigned long flags);
 void __arch_local_irq_restore(unsigned long flags);
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 
 static inline void arch_local_irq_enable(void)
 {
@@ -126,7 +127,7 @@ static inline void arch_local_irq_enable(void)
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
-#if   defined(CONFIG_CPU_MIPSR2)
+#if   defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	"	ei							\n"
 #else
 	"	mfc0	$1,$12						\n"
diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h
index 46dfc3c1fd49..8feaed62a2ab 100644
--- a/arch/mips/include/asm/local.h
+++ b/arch/mips/include/asm/local.h
@@ -5,6 +5,7 @@
 #include <linux/bitops.h>
 #include <linux/atomic.h>
 #include <asm/cmpxchg.h>
+#include <asm/compiler.h>
 #include <asm/war.h>
 
 typedef struct
@@ -47,7 +48,7 @@ static __inline__ long local_add_return(long i, local_t * l)
 		unsigned long temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"1:"	__LL	"%1, %2		# local_add_return	\n"
 		"	addu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
@@ -92,7 +93,7 @@ static __inline__ long local_sub_return(long i, local_t * l)
 		unsigned long temp;
 
 		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"1:"	__LL	"%1, %2		# local_sub_return	\n"
 		"	subu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
diff --git a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h
index 2e54b4bff5cf..90dbe43c8d27 100644
--- a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h
+++ b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_regops.h
@@ -85,8 +85,8 @@ static inline void set_value_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (~mask), "ir" (value), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (~mask), "ir" (value), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -106,8 +106,8 @@ static inline void set_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (mask), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (mask), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -127,8 +127,8 @@ static inline void clear_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (~mask), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (~mask), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -148,8 +148,8 @@ static inline void toggle_reg32(volatile u32 *const addr,
 	"	"__beqz"%0, 1b				\n"
 	"	nop					\n"
 	"	.set	pop				\n"
-	: "=&r" (temp), "=" GCC_OFF12_ASM() (*addr)
-	: "ir" (mask), GCC_OFF12_ASM() (*addr));
+	: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*addr)
+	: "ir" (mask), GCC_OFF_SMALL_ASM() (*addr));
 }
 
 /*
@@ -220,8 +220,8 @@ static inline u32 blocking_read_reg32(volatile u32 *const addr)
 	"	.set	arch=r4000			\n"	\
 	"1:	ll	%0, %1	#custom_read_reg32	\n"	\
 	"	.set	pop				\n"	\
-	: "=r" (tmp), "=" GCC_OFF12_ASM() (*address)		\
-	: GCC_OFF12_ASM() (*address))
+	: "=r" (tmp), "=" GCC_OFF_SMALL_ASM() (*address)		\
+	: GCC_OFF_SMALL_ASM() (*address))
 
 #define custom_write_reg32(address, tmp)			\
 	__asm__ __volatile__(					\
@@ -231,7 +231,7 @@ static inline u32 blocking_read_reg32(volatile u32 *const addr)
 	"	"__beqz"%0, 1b				\n"	\
 	"	nop					\n"	\
 	"	.set	pop				\n"	\
-	: "=&r" (tmp), "=" GCC_OFF12_ASM() (*address)		\
-	: "0" (tmp), GCC_OFF12_ASM() (*address))
+	: "=&r" (tmp), "=" GCC_OFF_SMALL_ASM() (*address)		\
+	: "0" (tmp), GCC_OFF_SMALL_ASM() (*address))
 
 #endif	/* __ASM_REGOPS_H__ */
diff --git a/arch/mips/include/asm/mips-r2-to-r6-emul.h b/arch/mips/include/asm/mips-r2-to-r6-emul.h
new file mode 100644
index 000000000000..60570f2c3ba2
--- /dev/null
+++ b/arch/mips/include/asm/mips-r2-to-r6-emul.h
@@ -0,0 +1,96 @@
+/*
+ * 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) 2014 Imagination Technologies Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ */
+
+#ifndef __ASM_MIPS_R2_TO_R6_EMUL_H
+#define __ASM_MIPS_R2_TO_R6_EMUL_H
+
+struct mips_r2_emulator_stats {
+	u64 movs;
+	u64 hilo;
+	u64 muls;
+	u64 divs;
+	u64 dsps;
+	u64 bops;
+	u64 traps;
+	u64 fpus;
+	u64 loads;
+	u64 stores;
+	u64 llsc;
+	u64 dsemul;
+};
+
+struct mips_r2br_emulator_stats {
+	u64 jrs;
+	u64 bltzl;
+	u64 bgezl;
+	u64 bltzll;
+	u64 bgezll;
+	u64 bltzall;
+	u64 bgezall;
+	u64 bltzal;
+	u64 bgezal;
+	u64 beql;
+	u64 bnel;
+	u64 blezl;
+	u64 bgtzl;
+};
+
+#ifdef CONFIG_DEBUG_FS
+
+#define MIPS_R2_STATS(M)						\
+do {									\
+	u32 nir;							\
+	int err;							\
+									\
+	preempt_disable();						\
+	__this_cpu_inc(mipsr2emustats.M);				\
+	err = __get_user(nir, (u32 __user *)regs->cp0_epc);		\
+	if (!err) {							\
+		if (nir == BREAK_MATH)					\
+			__this_cpu_inc(mipsr2bdemustats.M);		\
+	}								\
+	preempt_enable();						\
+} while (0)
+
+#define MIPS_R2BR_STATS(M)					\
+do {								\
+	preempt_disable();					\
+	__this_cpu_inc(mipsr2bremustats.M);			\
+	preempt_enable();					\
+} while (0)
+
+#else
+
+#define MIPS_R2_STATS(M)          do { } while (0)
+#define MIPS_R2BR_STATS(M)        do { } while (0)
+
+#endif /* CONFIG_DEBUG_FS */
+
+struct r2_decoder_table {
+	u32     mask;
+	u32     code;
+	int     (*func)(struct pt_regs *regs, u32 inst);
+};
+
+
+extern void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
+			  const char *str);
+
+#ifndef CONFIG_MIPSR2_TO_R6_EMULATOR
+static int mipsr2_emulation;
+static __maybe_unused int mipsr2_decoder(struct pt_regs *regs, u32 inst) { return 0; };
+#else
+/* MIPS R2 Emulator ON/OFF */
+extern int mipsr2_emulation;
+extern int mipsr2_decoder(struct pt_regs *regs, u32 inst);
+#endif /* CONFIG_MIPSR2_TO_R6_EMULATOR */
+
+#define NO_R6EMU	(cpu_has_mips_r6 && !mipsr2_emulation)
+
+#endif /* __ASM_MIPS_R2_TO_R6_EMUL_H */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 5e4aef304b02..06346001ee4d 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -653,6 +653,7 @@
 #define MIPS_CONF5_NF		(_ULCAST_(1) << 0)
 #define MIPS_CONF5_UFR		(_ULCAST_(1) << 2)
 #define MIPS_CONF5_MRP		(_ULCAST_(1) << 3)
+#define MIPS_CONF5_LLB		(_ULCAST_(1) << 4)
 #define MIPS_CONF5_MVH		(_ULCAST_(1) << 5)
 #define MIPS_CONF5_FRE		(_ULCAST_(1) << 8)
 #define MIPS_CONF5_UFE		(_ULCAST_(1) << 9)
@@ -1127,6 +1128,8 @@ do {									\
 #define write_c0_config6(val)	__write_32bit_c0_register($16, 6, val)
 #define write_c0_config7(val)	__write_32bit_c0_register($16, 7, val)
 
+#define read_c0_lladdr()	__read_ulong_c0_register($17, 0)
+#define write_c0_lladdr(val)	__write_ulong_c0_register($17, 0, val)
 #define read_c0_maar()		__read_ulong_c0_register($17, 1)
 #define write_c0_maar(val)	__write_ulong_c0_register($17, 1, val)
 #define read_c0_maari()		__read_32bit_c0_register($17, 2)
diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index 800fe578dc99..0aaf9a01ea50 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -88,10 +88,14 @@ search_module_dbetables(unsigned long addr)
 #define MODULE_PROC_FAMILY "MIPS32_R1 "
 #elif defined CONFIG_CPU_MIPS32_R2
 #define MODULE_PROC_FAMILY "MIPS32_R2 "
+#elif defined CONFIG_CPU_MIPS32_R6
+#define MODULE_PROC_FAMILY "MIPS32_R6 "
 #elif defined CONFIG_CPU_MIPS64_R1
 #define MODULE_PROC_FAMILY "MIPS64_R1 "
 #elif defined CONFIG_CPU_MIPS64_R2
 #define MODULE_PROC_FAMILY "MIPS64_R2 "
+#elif defined CONFIG_CPU_MIPS64_R6
+#define MODULE_PROC_FAMILY "MIPS64_R6 "
 #elif defined CONFIG_CPU_R3000
 #define MODULE_PROC_FAMILY "R3000 "
 #elif defined CONFIG_CPU_TX39XX
diff --git a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
index 75739c83f07e..8d05d9069823 100644
--- a/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
+++ b/arch/mips/include/asm/octeon/cvmx-cmd-queue.h
@@ -275,7 +275,7 @@ static inline void __cvmx_cmd_queue_lock(cvmx_cmd_queue_id_t queue_id,
 		" lbu	%[ticket], %[now_serving]\n"
 		"4:\n"
 		".set pop\n" :
-		[ticket_ptr] "=" GCC_OFF12_ASM()(__cvmx_cmd_queue_state_ptr->ticket[__cvmx_cmd_queue_get_index(queue_id)]),
+		[ticket_ptr] "=" GCC_OFF_SMALL_ASM()(__cvmx_cmd_queue_state_ptr->ticket[__cvmx_cmd_queue_get_index(queue_id)]),
 		[now_serving] "=m"(qptr->now_serving), [ticket] "=r"(tmp),
 		[my_ticket] "=r"(my_ticket)
 	    );
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index e293a8d89a6d..1b22d2da88a1 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -14,6 +14,7 @@
 
 #include <asm/asm.h>
 #include <asm/cacheops.h>
+#include <asm/compiler.h>
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/mipsmtregs.h>
@@ -39,7 +40,7 @@ extern void (*r4k_blast_icache)(void);
 	__asm__ __volatile__(						\
 	"	.set	push					\n"	\
 	"	.set	noreorder				\n"	\
-	"	.set	arch=r4000				\n"	\
+	"	.set "MIPS_ISA_ARCH_LEVEL"			\n"	\
 	"	cache	%0, %1					\n"	\
 	"	.set	pop					\n"	\
 	:								\
@@ -147,7 +148,7 @@ static inline void flush_scache_line(unsigned long addr)
 	__asm__ __volatile__(					\
 	"	.set	push			\n"		\
 	"	.set	noreorder		\n"		\
-	"	.set	arch=r4000		\n"		\
+	"	.set "MIPS_ISA_ARCH_LEVEL"	\n"		\
 	"1:	cache	%0, (%1)		\n"		\
 	"2:	.set	pop			\n"		\
 	"	.section __ex_table,\"a\"	\n"		\
@@ -218,6 +219,7 @@ static inline void invalidate_tcache_page(unsigned long addr)
 	cache_op(Page_Invalidate_T, addr);
 }
 
+#ifndef CONFIG_CPU_MIPSR6
 #define cache16_unroll32(base,op)					\
 	__asm__ __volatile__(						\
 	"	.set push					\n"	\
@@ -322,6 +324,150 @@ static inline void invalidate_tcache_page(unsigned long addr)
 		: "r" (base),						\
 		  "i" (op));
 
+#else
+/*
+ * MIPS R6 changed the cache opcode and moved to a 8-bit offset field.
+ * This means we now need to increment the base register before we flush
+ * more cache lines
+ */
+#define cache16_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x010(%0)\n"	\
+	"	cache %1, 0x020(%0); cache %1, 0x030(%0)\n"	\
+	"	cache %1, 0x040(%0); cache %1, 0x050(%0)\n"	\
+	"	cache %1, 0x060(%0); cache %1, 0x070(%0)\n"	\
+	"	cache %1, 0x080(%0); cache %1, 0x090(%0)\n"	\
+	"	cache %1, 0x0a0(%0); cache %1, 0x0b0(%0)\n"	\
+	"	cache %1, 0x0c0(%0); cache %1, 0x0d0(%0)\n"	\
+	"	cache %1, 0x0e0(%0); cache %1, 0x0f0(%0)\n"	\
+	"	addiu $1, $0, 0x100			\n"	\
+	"	cache %1, 0x000($1); cache %1, 0x010($1)\n"	\
+	"	cache %1, 0x020($1); cache %1, 0x030($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x050($1)\n"	\
+	"	cache %1, 0x060($1); cache %1, 0x070($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x090($1)\n"	\
+	"	cache %1, 0x0a0($1); cache %1, 0x0b0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0d0($1)\n"	\
+	"	cache %1, 0x0e0($1); cache %1, 0x0f0($1)\n"	\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+
+#define cache32_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x020(%0)\n"	\
+	"	cache %1, 0x040(%0); cache %1, 0x060(%0)\n"	\
+	"	cache %1, 0x080(%0); cache %1, 0x0a0(%0)\n"	\
+	"	cache %1, 0x0c0(%0); cache %1, 0x0e0(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
+	"	addiu $1, $1, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
+	"	addiu $1, $1, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x020($1)\n"	\
+	"	cache %1, 0x040($1); cache %1, 0x060($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0a0($1)\n"	\
+	"	cache %1, 0x0c0($1); cache %1, 0x0e0($1)\n"	\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+
+#define cache64_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x040(%0)\n"	\
+	"	cache %1, 0x080(%0); cache %1, 0x0c0(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000($1); cache %1, 0x040($1)\n"	\
+	"	cache %1, 0x080($1); cache %1, 0x0c0($1)\n"	\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+
+#define cache128_unroll32(base,op)				\
+	__asm__ __volatile__(					\
+	"	.set push\n"					\
+	"	.set noreorder\n"				\
+	"	.set mips64r6\n"				\
+	"	.set noat\n"					\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	cache %1, 0x000(%0); cache %1, 0x080(%0)\n"	\
+	"	addiu $1, %0, 0x100\n"				\
+	"	.set pop\n"					\
+		:						\
+		: "r" (base),					\
+		  "i" (op));
+#endif /* CONFIG_CPU_MIPSR6 */
+
 /*
  * Perform the cache operation specified by op using a user mode virtual
  * address while in kernel mode.
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index c6d06d383ef9..b4548690ade9 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -89,7 +89,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	 subu	%[ticket], %[ticket], 1			\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [serving_now_ptr] "+m" (lock->h.serving_now),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (my_ticket)
@@ -122,7 +122,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	 subu	%[ticket], %[ticket], 1			\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [serving_now_ptr] "+m" (lock->h.serving_now),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (my_ticket)
@@ -164,7 +164,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	 li	%[ticket], 0				\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (tmp2),
 		  [now_serving] "=&r" (tmp3)
@@ -188,7 +188,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	 li	%[ticket], 0				\n"
 		"	.previous					\n"
 		"	.set pop					\n"
-		: [ticket_ptr] "+" GCC_OFF12_ASM() (lock->lock),
+		: [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock),
 		  [ticket] "=&r" (tmp),
 		  [my_ticket] "=&r" (tmp2),
 		  [now_serving] "=&r" (tmp3)
@@ -235,8 +235,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 		"	beqzl	%1, 1b					\n"
 		"	 nop						\n"
 		"	.set	reorder					\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
@@ -245,8 +245,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 			"	bltz	%1, 1b				\n"
 			"	 addu	%1, 1				\n"
 			"2:	sc	%1, %0				\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-			: GCC_OFF12_ASM() (rw->lock)
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 	}
@@ -254,9 +254,6 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 	smp_llsc_mb();
 }
 
-/* Note the use of sub, not subu which will make the kernel die with an
-   overflow exception if we ever try to unlock an rwlock that is already
-   unlocked or is being held by a writer.  */
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	unsigned int tmp;
@@ -266,20 +263,20 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	if (R10000_LLSC_WAR) {
 		__asm__ __volatile__(
 		"1:	ll	%1, %2		# arch_read_unlock	\n"
-		"	sub	%1, 1					\n"
+		"	addiu	%1, 1					\n"
 		"	sc	%1, %0					\n"
 		"	beqzl	%1, 1b					\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
 			__asm__ __volatile__(
 			"1:	ll	%1, %2	# arch_read_unlock	\n"
-			"	sub	%1, 1				\n"
+			"	addiu	%1, -1				\n"
 			"	sc	%1, %0				\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-			: GCC_OFF12_ASM() (rw->lock)
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 	}
@@ -299,8 +296,8 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 		"	beqzl	%1, 1b					\n"
 		"	 nop						\n"
 		"	.set	reorder					\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
@@ -309,8 +306,8 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 			"	bnez	%1, 1b				\n"
 			"	 lui	%1, 0x8000			\n"
 			"2:	sc	%1, %0				\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp)
-			: GCC_OFF12_ASM() (rw->lock)
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 	}
@@ -349,8 +346,8 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
 		"2:							\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		__asm__ __volatile__(
@@ -366,8 +363,8 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
 		"2:							\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	}
 
@@ -393,8 +390,8 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 		"	li	%2, 1					\n"
 		"	.set	reorder					\n"
 		"2:							\n"
-		: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
-		: GCC_OFF12_ASM() (rw->lock)
+		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
+		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
 	} else {
 		do {
@@ -406,9 +403,9 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 			"	sc	%1, %0				\n"
 			"	li	%2, 1				\n"
 			"2:						\n"
-			: "=" GCC_OFF12_ASM() (rw->lock), "=&r" (tmp),
+			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
 			  "=&r" (ret)
-			: GCC_OFF12_ASM() (rw->lock)
+			: GCC_OFF_SMALL_ASM() (rw->lock)
 			: "memory");
 		} while (unlikely(!tmp));
 
diff --git a/arch/mips/include/asm/spram.h b/arch/mips/include/asm/spram.h
index 0b89006e4907..0f90d88e464d 100644
--- a/arch/mips/include/asm/spram.h
+++ b/arch/mips/include/asm/spram.h
@@ -1,10 +1,10 @@
 #ifndef _MIPS_SPRAM_H
 #define _MIPS_SPRAM_H
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_MIPS_SPRAM)
 extern __init void spram_config(void);
 #else
 static inline void spram_config(void) { };
-#endif /* CONFIG_CPU_MIPSR2 */
+#endif /* CONFIG_MIPS_SPRAM */
 
 #endif /* _MIPS_SPRAM_H */
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index b188c797565c..28d6d9364bd1 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -40,7 +40,7 @@
 		LONG_S	v1, PT_HI(sp)
 		mflhxu	v1
 		LONG_S	v1, PT_ACX(sp)
-#else
+#elif !defined(CONFIG_CPU_MIPSR6)
 		mfhi	v1
 #endif
 #ifdef CONFIG_32BIT
@@ -50,7 +50,7 @@
 		LONG_S	$10, PT_R10(sp)
 		LONG_S	$11, PT_R11(sp)
 		LONG_S	$12, PT_R12(sp)
-#ifndef CONFIG_CPU_HAS_SMARTMIPS
+#if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
 		LONG_S	v1, PT_HI(sp)
 		mflo	v1
 #endif
@@ -58,7 +58,7 @@
 		LONG_S	$14, PT_R14(sp)
 		LONG_S	$15, PT_R15(sp)
 		LONG_S	$24, PT_R24(sp)
-#ifndef CONFIG_CPU_HAS_SMARTMIPS
+#if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
 		LONG_S	v1, PT_LO(sp)
 #endif
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
@@ -226,7 +226,7 @@
 		mtlhx	$24
 		LONG_L	$24, PT_LO(sp)
 		mtlhx	$24
-#else
+#elif !defined(CONFIG_CPU_MIPSR6)
 		LONG_L	$24, PT_LO(sp)
 		mtlo	$24
 		LONG_L	$24, PT_HI(sp)
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index b928b6f898cd..e92d6c4b5ed1 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -75,9 +75,12 @@ do {									\
 #endif
 
 #define __clear_software_ll_bit()					\
-do {									\
-	if (!__builtin_constant_p(cpu_has_llsc) || !cpu_has_llsc)	\
-		ll_bit = 0;						\
+do {	if (cpu_has_rw_llb) {						\
+		write_c0_lladdr(0);					\
+	} else {							\
+		if (!__builtin_constant_p(cpu_has_llsc) || !cpu_has_llsc)\
+			ll_bit = 0;					\
+	}								\
 } while (0)
 
 #define switch_to(prev, next, last)					\
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 99eea59604e9..fb68fd2714fb 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -28,7 +28,7 @@ struct thread_info {
 	unsigned long		tp_value;	/* thread pointer */
 	__u32			cpu;		/* current CPU */
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
-
+	int			r2_emul_return; /* 1 => Returning from R2 emulator */
 	mm_segment_t		addr_limit;	/*
 						 * thread address space limit:
 						 * 0x7fffffff for user-thead
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index 89c22433b1c6..fc0cf5ac0cf7 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -21,20 +21,20 @@
 enum major_op {
 	spec_op, bcond_op, j_op, jal_op,
 	beq_op, bne_op, blez_op, bgtz_op,
-	addi_op, addiu_op, slti_op, sltiu_op,
+	addi_op, cbcond0_op = addi_op, addiu_op, slti_op, sltiu_op,
 	andi_op, ori_op, xori_op, lui_op,
 	cop0_op, cop1_op, cop2_op, cop1x_op,
 	beql_op, bnel_op, blezl_op, bgtzl_op,
-	daddi_op, daddiu_op, ldl_op, ldr_op,
+	daddi_op, cbcond1_op = daddi_op, daddiu_op, ldl_op, ldr_op,
 	spec2_op, jalx_op, mdmx_op, spec3_op,
 	lb_op, lh_op, lwl_op, lw_op,
 	lbu_op, lhu_op, lwr_op, lwu_op,
 	sb_op, sh_op, swl_op, sw_op,
 	sdl_op, sdr_op, swr_op, cache_op,
-	ll_op, lwc1_op, lwc2_op, pref_op,
-	lld_op, ldc1_op, ldc2_op, ld_op,
-	sc_op, swc1_op, swc2_op, major_3b_op,
-	scd_op, sdc1_op, sdc2_op, sd_op
+	ll_op, lwc1_op, lwc2_op, bc6_op = lwc2_op, pref_op,
+	lld_op, ldc1_op, ldc2_op, beqzcjic_op = ldc2_op, ld_op,
+	sc_op, swc1_op, swc2_op, balc6_op = swc2_op, major_3b_op,
+	scd_op, sdc1_op, sdc2_op, bnezcjialc_op = sdc2_op, sd_op
 };
 
 /*
@@ -83,9 +83,12 @@ enum spec3_op {
 	swe_op    = 0x1f, bshfl_op  = 0x20,
 	swle_op   = 0x21, swre_op   = 0x22,
 	prefe_op  = 0x23, dbshfl_op = 0x24,
-	lbue_op   = 0x28, lhue_op   = 0x29,
-	lbe_op    = 0x2c, lhe_op    = 0x2d,
-	lle_op    = 0x2e, lwe_op    = 0x2f,
+	cache6_op = 0x25, sc6_op    = 0x26,
+	scd6_op   = 0x27, lbue_op   = 0x28,
+	lhue_op   = 0x29, lbe_op    = 0x2c,
+	lhe_op    = 0x2d, lle_op    = 0x2e,
+	lwe_op    = 0x2f, pref6_op  = 0x35,
+	ll6_op    = 0x36, lld6_op   = 0x37,
 	rdhwr_op  = 0x3b
 };
 
@@ -112,7 +115,8 @@ enum cop_op {
 	mfhc_op       = 0x03, mtc_op	    = 0x04,
 	dmtc_op	      = 0x05, ctc_op	    = 0x06,
 	mthc0_op      = 0x06, mthc_op	    = 0x07,
-	bc_op	      = 0x08, cop_op	    = 0x10,
+	bc_op	      = 0x08, bc1eqz_op     = 0x09,
+	bc1nez_op     = 0x0d, cop_op	    = 0x10,
 	copm_op	      = 0x18
 };
 
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 92987d1bbe5f..d3d2ff2d76dc 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -52,7 +52,7 @@ 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_GIC_IPI)	+= smp-gic.o
-obj-$(CONFIG_CPU_MIPSR2)	+= spram.o
+obj-$(CONFIG_MIPS_SPRAM)	+= spram.o
 
 obj-$(CONFIG_MIPS_VPE_LOADER)	+= vpe.o
 obj-$(CONFIG_MIPS_VPE_LOADER_CMP) += vpe-cmp.o
@@ -90,6 +90,7 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_EARLY_PRINTK_8250)	+= early_printk_8250.o
 obj-$(CONFIG_SPINLOCK_TEST)	+= spinlock_test.o
 obj-$(CONFIG_MIPS_MACHINE)	+= mips_machine.o
+obj-$(CONFIG_MIPSR2_TO_R6_EMULATOR)	+= mips-r2-to-r6-emul.o
 
 CFLAGS_cpu-bugs64.o	= $(shell if $(CC) $(KBUILD_CFLAGS) -Wa,-mdaddi -c -o /dev/null -x c /dev/null >/dev/null 2>&1; then echo "-DHAVE_AS_SET_DADDI"; fi)
 
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index b1d84bd4efb3..7b6c11aa1cae 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -97,6 +97,7 @@ void output_thread_info_defines(void)
 	OFFSET(TI_TP_VALUE, thread_info, tp_value);
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
+	OFFSET(TI_R2_EMUL_RET, thread_info, r2_emul_return);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
 	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 4d7d99d601cc..c2e0f45ddf6c 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -16,6 +16,7 @@
 #include <asm/fpu.h>
 #include <asm/fpu_emulator.h>
 #include <asm/inst.h>
+#include <asm/mips-r2-to-r6-emul.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 
@@ -399,11 +400,21 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs)
  * @returns:	-EFAULT on error and forces SIGBUS, and on success
  *		returns 0 or BRANCH_LIKELY_TAKEN as appropriate after
  *		evaluating the branch.
+ *
+ * MIPS R6 Compact branches and forbidden slots:
+ *	Compact branches do not throw exceptions because they do
+ *	not have delay slots. The forbidden slot instruction ($PC+4)
+ *	is only executed if the branch was not taken. Otherwise the
+ *	forbidden slot is skipped entirely. This means that the
+ *	only possible reason to be here because of a MIPS R6 compact
+ *	branch instruction is that the forbidden slot has thrown one.
+ *	In that case the branch was not taken, so the EPC can be safely
+ *	set to EPC + 8.
  */
 int __compute_return_epc_for_insn(struct pt_regs *regs,
 				   union mips_instruction insn)
 {
-	unsigned int bit, fcr31, dspcontrol;
+	unsigned int bit, fcr31, dspcontrol, reg;
 	long epc = regs->cp0_epc;
 	int ret = 0;
 
@@ -417,6 +428,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 			regs->regs[insn.r_format.rd] = epc + 8;
 			/* Fall through */
 		case jr_op:
+			if (NO_R6EMU && insn.r_format.func == jr_op)
+				goto sigill_r6;
 			regs->cp0_epc = regs->regs[insn.r_format.rs];
 			break;
 		}
@@ -429,8 +442,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	 */
 	case bcond_op:
 		switch (insn.i_format.rt) {
-		case bltz_op:
 		case bltzl_op:
+			if (NO_R6EMU)
+				goto sigill_r6;
+		case bltz_op:
 			if ((long)regs->regs[insn.i_format.rs] < 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
 				if (insn.i_format.rt == bltzl_op)
@@ -440,8 +455,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 			regs->cp0_epc = epc;
 			break;
 
-		case bgez_op:
 		case bgezl_op:
+			if (NO_R6EMU)
+				goto sigill_r6;
+		case bgez_op:
 			if ((long)regs->regs[insn.i_format.rs] >= 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
 				if (insn.i_format.rt == bgezl_op)
@@ -453,7 +470,29 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 		case bltzal_op:
 		case bltzall_op:
+			if (NO_R6EMU && (insn.i_format.rs ||
+			    insn.i_format.rt == bltzall_op)) {
+				ret = -SIGILL;
+				break;
+			}
 			regs->regs[31] = epc + 8;
+			/*
+			 * OK we are here either because we hit a NAL
+			 * instruction or because we are emulating an
+			 * old bltzal{,l} one. Lets figure out what the
+			 * case really is.
+			 */
+			if (!insn.i_format.rs) {
+				/*
+				 * NAL or BLTZAL with rs == 0
+				 * Doesn't matter if we are R6 or not. The
+				 * result is the same
+				 */
+				regs->cp0_epc += 4 +
+					(insn.i_format.simmediate << 2);
+				break;
+			}
+			/* Now do the real thing for non-R6 BLTZAL{,L} */
 			if ((long)regs->regs[insn.i_format.rs] < 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
 				if (insn.i_format.rt == bltzall_op)
@@ -465,7 +504,29 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 		case bgezal_op:
 		case bgezall_op:
+			if (NO_R6EMU && (insn.i_format.rs ||
+			    insn.i_format.rt == bgezall_op)) {
+				ret = -SIGILL;
+				break;
+			}
 			regs->regs[31] = epc + 8;
+			/*
+			 * OK we are here either because we hit a BAL
+			 * instruction or because we are emulating an
+			 * old bgezal{,l} one. Lets figure out what the
+			 * case really is.
+			 */
+			if (!insn.i_format.rs) {
+				/*
+				 * BAL or BGEZAL with rs == 0
+				 * Doesn't matter if we are R6 or not. The
+				 * result is the same
+				 */
+				regs->cp0_epc += 4 +
+					(insn.i_format.simmediate << 2);
+				break;
+			}
+			/* Now do the real thing for non-R6 BGEZAL{,L} */
 			if ((long)regs->regs[insn.i_format.rs] >= 0) {
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
 				if (insn.i_format.rt == bgezall_op)
@@ -477,7 +538,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 
 		case bposge32_op:
 			if (!cpu_has_dsp)
-				goto sigill;
+				goto sigill_dsp;
 
 			dspcontrol = rddsp(0x01);
 
@@ -508,8 +569,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	/*
 	 * These are conditional and in i_format.
 	 */
-	case beq_op:
 	case beql_op:
+		if (NO_R6EMU)
+			goto sigill_r6;
+	case beq_op:
 		if (regs->regs[insn.i_format.rs] ==
 		    regs->regs[insn.i_format.rt]) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
@@ -520,8 +583,10 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		regs->cp0_epc = epc;
 		break;
 
-	case bne_op:
 	case bnel_op:
+		if (NO_R6EMU)
+			goto sigill_r6;
+	case bne_op:
 		if (regs->regs[insn.i_format.rs] !=
 		    regs->regs[insn.i_format.rt]) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
@@ -532,8 +597,31 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		regs->cp0_epc = epc;
 		break;
 
-	case blez_op: /* not really i_format */
-	case blezl_op:
+	case blezl_op: /* not really i_format */
+		if (NO_R6EMU)
+			goto sigill_r6;
+	case blez_op:
+		/*
+		 * Compact branches for R6 for the
+		 * blez and blezl opcodes.
+		 * BLEZ  | rs = 0 | rt != 0  == BLEZALC
+		 * BLEZ  | rs = rt != 0      == BGEZALC
+		 * BLEZ  | rs != 0 | rt != 0 == BGEUC
+		 * BLEZL | rs = 0 | rt != 0  == BLEZC
+		 * BLEZL | rs = rt != 0      == BGEZC
+		 * BLEZL | rs != 0 | rt != 0 == BGEC
+		 *
+		 * For real BLEZ{,L}, rt is always 0.
+		 */
+
+		if (cpu_has_mips_r6 && insn.i_format.rt) {
+			if ((insn.i_format.opcode == blez_op) &&
+			    ((!insn.i_format.rs && insn.i_format.rt) ||
+			     (insn.i_format.rs == insn.i_format.rt)))
+				regs->regs[31] = epc + 4;
+			regs->cp0_epc += 8;
+			break;
+		}
 		/* rt field assumed to be zero */
 		if ((long)regs->regs[insn.i_format.rs] <= 0) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
@@ -544,8 +632,32 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		regs->cp0_epc = epc;
 		break;
 
-	case bgtz_op:
 	case bgtzl_op:
+		if (NO_R6EMU)
+			goto sigill_r6;
+	case bgtz_op:
+		/*
+		 * Compact branches for R6 for the
+		 * bgtz and bgtzl opcodes.
+		 * BGTZ  | rs = 0 | rt != 0  == BGTZALC
+		 * BGTZ  | rs = rt != 0      == BLTZALC
+		 * BGTZ  | rs != 0 | rt != 0 == BLTUC
+		 * BGTZL | rs = 0 | rt != 0  == BGTZC
+		 * BGTZL | rs = rt != 0      == BLTZC
+		 * BGTZL | rs != 0 | rt != 0 == BLTC
+		 *
+		 * *ZALC varint for BGTZ &&& rt != 0
+		 * For real GTZ{,L}, rt is always 0.
+		 */
+		if (cpu_has_mips_r6 && insn.i_format.rt) {
+			if ((insn.i_format.opcode == blez_op) &&
+			    ((!insn.i_format.rs && insn.i_format.rt) ||
+			    (insn.i_format.rs == insn.i_format.rt)))
+				regs->regs[31] = epc + 4;
+			regs->cp0_epc += 8;
+			break;
+		}
+
 		/* rt field assumed to be zero */
 		if ((long)regs->regs[insn.i_format.rs] > 0) {
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
@@ -560,40 +672,83 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	 * And now the FPA/cp1 branch instructions.
 	 */
 	case cop1_op:
-		preempt_disable();
-		if (is_fpu_owner())
-		        fcr31 = read_32bit_cp1_register(CP1_STATUS);
-		else
-			fcr31 = current->thread.fpu.fcr31;
-		preempt_enable();
-
-		bit = (insn.i_format.rt >> 2);
-		bit += (bit != 0);
-		bit += 23;
-		switch (insn.i_format.rt & 3) {
-		case 0: /* bc1f */
-		case 2: /* bc1fl */
-			if (~fcr31 & (1 << bit)) {
-				epc = epc + 4 + (insn.i_format.simmediate << 2);
-				if (insn.i_format.rt == 2)
-					ret = BRANCH_LIKELY_TAKEN;
-			} else
+		if (cpu_has_mips_r6 &&
+		    ((insn.i_format.rs == bc1eqz_op) ||
+		     (insn.i_format.rs == bc1nez_op))) {
+			if (!used_math()) { /* First time FPU user */
+				ret = init_fpu();
+				if (ret && NO_R6EMU) {
+					ret = -ret;
+					break;
+				}
+				ret = 0;
+				set_used_math();
+			}
+			lose_fpu(1);    /* Save FPU state for the emulator. */
+			reg = insn.i_format.rt;
+			bit = 0;
+			switch (insn.i_format.rs) {
+			case bc1eqz_op:
+				/* Test bit 0 */
+				if (get_fpr32(&current->thread.fpu.fpr[reg], 0)
+				    & 0x1)
+					bit = 1;
+				break;
+			case bc1nez_op:
+				/* Test bit 0 */
+				if (!(get_fpr32(&current->thread.fpu.fpr[reg], 0)
+				      & 0x1))
+					bit = 1;
+				break;
+			}
+			own_fpu(1);
+			if (bit)
+				epc = epc + 4 +
+					(insn.i_format.simmediate << 2);
+			else
 				epc += 8;
 			regs->cp0_epc = epc;
+
 			break;
+		} else {
 
-		case 1: /* bc1t */
-		case 3: /* bc1tl */
-			if (fcr31 & (1 << bit)) {
-				epc = epc + 4 + (insn.i_format.simmediate << 2);
-				if (insn.i_format.rt == 3)
-					ret = BRANCH_LIKELY_TAKEN;
-			} else
-				epc += 8;
-			regs->cp0_epc = epc;
+			preempt_disable();
+			if (is_fpu_owner())
+			        fcr31 = read_32bit_cp1_register(CP1_STATUS);
+			else
+				fcr31 = current->thread.fpu.fcr31;
+			preempt_enable();
+
+			bit = (insn.i_format.rt >> 2);
+			bit += (bit != 0);
+			bit += 23;
+			switch (insn.i_format.rt & 3) {
+			case 0: /* bc1f */
+			case 2: /* bc1fl */
+				if (~fcr31 & (1 << bit)) {
+					epc = epc + 4 +
+						(insn.i_format.simmediate << 2);
+					if (insn.i_format.rt == 2)
+						ret = BRANCH_LIKELY_TAKEN;
+				} else
+					epc += 8;
+				regs->cp0_epc = epc;
+				break;
+
+			case 1: /* bc1t */
+			case 3: /* bc1tl */
+				if (fcr31 & (1 << bit)) {
+					epc = epc + 4 +
+						(insn.i_format.simmediate << 2);
+					if (insn.i_format.rt == 3)
+						ret = BRANCH_LIKELY_TAKEN;
+				} else
+					epc += 8;
+				regs->cp0_epc = epc;
+				break;
+			}
 			break;
 		}
-		break;
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	case lwc2_op: /* This is bbit0 on Octeon */
 		if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt))
@@ -626,15 +781,72 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 			epc += 8;
 		regs->cp0_epc = epc;
 		break;
+#else
+	case bc6_op:
+		/* Only valid for MIPS R6 */
+		if (!cpu_has_mips_r6) {
+			ret = -SIGILL;
+			break;
+		}
+		regs->cp0_epc += 8;
+		break;
+	case balc6_op:
+		if (!cpu_has_mips_r6) {
+			ret = -SIGILL;
+			break;
+		}
+		/* Compact branch: BALC */
+		regs->regs[31] = epc + 4;
+		epc += 4 + (insn.i_format.simmediate << 2);
+		regs->cp0_epc = epc;
+		break;
+	case beqzcjic_op:
+		if (!cpu_has_mips_r6) {
+			ret = -SIGILL;
+			break;
+		}
+		/* Compact branch: BEQZC || JIC */
+		regs->cp0_epc += 8;
+		break;
+	case bnezcjialc_op:
+		if (!cpu_has_mips_r6) {
+			ret = -SIGILL;
+			break;
+		}
+		/* Compact branch: BNEZC || JIALC */
+		if (insn.i_format.rs)
+			regs->regs[31] = epc + 4;
+		regs->cp0_epc += 8;
+		break;
 #endif
+	case cbcond0_op:
+	case cbcond1_op:
+		/* Only valid for MIPS R6 */
+		if (!cpu_has_mips_r6) {
+			ret = -SIGILL;
+			break;
+		}
+		/*
+		 * Compact branches:
+		 * bovc, beqc, beqzalc, bnvc, bnec, bnezlac
+		 */
+		if (insn.i_format.rt && !insn.i_format.rs)
+			regs->regs[31] = epc + 4;
+		regs->cp0_epc += 8;
+		break;
 	}
 
 	return ret;
 
-sigill:
+sigill_dsp:
 	printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm);
 	force_sig(SIGBUS, current);
 	return -EFAULT;
+sigill_r6:
+	pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n",
+		current->comm);
+	force_sig(SIGILL, current);
+	return -EFAULT;
 }
 EXPORT_SYMBOL_GPL(__compute_return_epc_for_insn);
 
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 28bfdf2c59a5..82bd2b278a24 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -39,7 +39,7 @@ int cp0_timer_irq_installed;
 
 irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
 {
-	const int r2 = cpu_has_mips_r2;
+	const int r2 = cpu_has_mips_r2_r6;
 	struct clock_event_device *cd;
 	int cpu = smp_processor_id();
 
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 0384b05ab5a0..55b759a0019e 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -99,11 +99,11 @@ not_nmi:
 	xori	t2, t1, 0x7
 	beqz	t2, 1f
 	 li	t3, 32
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 	sllv	t1, t3, t1
 1:	/* At this point t1 == I-cache sets per way */
 	_EXT	t2, v0, MIPS_CONF1_IA_SHF, MIPS_CONF1_IA_SZ
-	addi	t2, t2, 1
+	addiu	t2, t2, 1
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
@@ -126,11 +126,11 @@ icache_done:
 	xori	t2, t1, 0x7
 	beqz	t2, 1f
 	 li	t3, 32
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 	sllv	t1, t3, t1
 1:	/* At this point t1 == D-cache sets per way */
 	_EXT	t2, v0, MIPS_CONF1_DA_SHF, MIPS_CONF1_DA_SZ
-	addi	t2, t2, 1
+	addiu	t2, t2, 1
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
@@ -250,7 +250,7 @@ LEAF(mips_cps_core_init)
 	mfc0	t0, CP0_MVPCONF0
 	srl	t0, t0, MVPCONF0_PVPE_SHIFT
 	andi	t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT)
-	addi	t7, t0, 1
+	addiu	t7, t0, 1
 
 	/* If there's only 1, we're done */
 	beqz	t0, 2f
@@ -280,7 +280,7 @@ LEAF(mips_cps_core_init)
 	mttc0	t0, CP0_TCHALT
 
 	/* Next VPE */
-	addi	t5, t5, 1
+	addiu	t5, t5, 1
 	slt	t0, t5, t7
 	bnez	t0, 1b
 	 nop
@@ -317,7 +317,7 @@ LEAF(mips_cps_boot_vpes)
 	mfc0	t1, CP0_MVPCONF0
 	srl	t1, t1, MVPCONF0_PVPE_SHIFT
 	andi	t1, t1, MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 
 	/* Calculate a mask for the VPE ID from EBase.CPUNum */
 	clz	t1, t1
@@ -424,7 +424,7 @@ LEAF(mips_cps_boot_vpes)
 
 	/* Next VPE */
 2:	srl	t6, t6, 1
-	addi	t5, t5, 1
+	addiu	t5, t5, 1
 	bnez	t6, 1b
 	 nop
 
diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c
index 2d80b5f1aeae..09f4034f239f 100644
--- a/arch/mips/kernel/cpu-bugs64.c
+++ b/arch/mips/kernel/cpu-bugs64.c
@@ -244,7 +244,7 @@ static inline void check_daddi(void)
 	panic(bug64hit, !DADDI_WAR ? daddiwar : nowar);
 }
 
-int daddiu_bug	= -1;
+int daddiu_bug	= config_enabled(CONFIG_CPU_MIPSR6) ? 0 : -1;
 
 static inline void check_daddiu(void)
 {
@@ -314,11 +314,14 @@ static inline void check_daddiu(void)
 
 void __init check_bugs64_early(void)
 {
-	check_mult_sh();
-	check_daddiu();
+	if (!config_enabled(CONFIG_CPU_MIPSR6)) {
+		check_mult_sh();
+		check_daddiu();
+	}
 }
 
 void __init check_bugs64(void)
 {
-	check_daddi();
+	if (!config_enabled(CONFIG_CPU_MIPSR6))
+		check_daddi();
 }
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 228ae864c92e..81f0aedbba0f 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -237,6 +237,13 @@ static void set_isa(struct cpuinfo_mips *c, unsigned int isa)
 		c->isa_level |= MIPS_CPU_ISA_II | MIPS_CPU_ISA_III;
 		break;
 
+	/* R6 incompatible with everything else */
+	case MIPS_CPU_ISA_M64R6:
+		c->isa_level |= MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6;
+	case MIPS_CPU_ISA_M32R6:
+		c->isa_level |= MIPS_CPU_ISA_M32R6;
+		/* Break here so we don't add incompatible ISAs */
+		break;
 	case MIPS_CPU_ISA_M32R2:
 		c->isa_level |= MIPS_CPU_ISA_M32R2;
 	case MIPS_CPU_ISA_M32R1:
@@ -326,6 +333,9 @@ static inline unsigned int decode_config0(struct cpuinfo_mips *c)
 		case 1:
 			set_isa(c, MIPS_CPU_ISA_M32R2);
 			break;
+		case 2:
+			set_isa(c, MIPS_CPU_ISA_M32R6);
+			break;
 		default:
 			goto unknown;
 		}
@@ -338,6 +348,9 @@ static inline unsigned int decode_config0(struct cpuinfo_mips *c)
 		case 1:
 			set_isa(c, MIPS_CPU_ISA_M64R2);
 			break;
+		case 2:
+			set_isa(c, MIPS_CPU_ISA_M64R6);
+			break;
 		default:
 			goto unknown;
 		}
@@ -501,6 +514,8 @@ static inline unsigned int decode_config5(struct cpuinfo_mips *c)
 		c->options |= MIPS_CPU_EVA;
 	if (config5 & MIPS_CONF5_MRP)
 		c->options |= MIPS_CPU_MAAR;
+	if (config5 & MIPS_CONF5_LLB)
+		c->options |= MIPS_CPU_RW_LLB;
 
 	return config5 & MIPS_CONF_M;
 }
@@ -543,7 +558,7 @@ static void decode_configs(struct cpuinfo_mips *c)
 	}
 
 #ifndef CONFIG_MIPS_CPS
-	if (cpu_has_mips_r2) {
+	if (cpu_has_mips_r2_r6) {
 		c->core = get_ebase_cpunum();
 		if (cpu_has_mipsmt)
 			c->core >>= fls(core_nvpes()) - 1;
@@ -898,6 +913,11 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 	switch (c->processor_id & PRID_IMP_MASK) {
+	case PRID_IMP_QEMU_GENERIC:
+		c->writecombine = _CACHE_UNCACHED;
+		c->cputype = CPU_QEMU_GENERIC;
+		__cpu_name[cpu] = "MIPS GENERIC QEMU";
+		break;
 	case PRID_IMP_4KC:
 		c->cputype = CPU_4KC;
 		c->writecombine = _CACHE_UNCACHED;
@@ -1347,8 +1367,7 @@ void cpu_probe(void)
 	if (c->options & MIPS_CPU_FPU) {
 		c->fpu_id = cpu_get_fpu_id();
 
-		if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 |
-				    MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) {
+		if (c->isa_level & cpu_has_mips_r) {
 			if (c->fpu_id & MIPS_FPIR_3D)
 				c->ases |= MIPS_ASE_MIPS3D;
 			if (c->fpu_id & MIPS_FPIR_FREP)
@@ -1356,7 +1375,7 @@ void cpu_probe(void)
 		}
 	}
 
-	if (cpu_has_mips_r2) {
+	if (cpu_has_mips_r2_r6) {
 		c->srsets = ((read_c0_srsctl() >> 26) & 0x0f) + 1;
 		/* R2 has Performance Counter Interrupt indicator */
 		c->options |= MIPS_CPU_PCI;
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index c92b15df6893..d2c09f6475c5 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -11,29 +11,112 @@
 #include <linux/elf.h>
 #include <linux/sched.h>
 
+/* FPU modes */
 enum {
-	FP_ERROR = -1,
-	FP_DOUBLE_64A = -2,
+	FP_FRE,
+	FP_FR0,
+	FP_FR1,
 };
 
+/**
+ * struct mode_req - ABI FPU mode requirements
+ * @single:	The program being loaded needs an FPU but it will only issue
+ *		single precision instructions meaning that it can execute in
+ *		either FR0 or FR1.
+ * @soft:	The soft(-float) requirement means that the program being
+ *		loaded needs has no FPU dependency at all (i.e. it has no
+ *		FPU instructions).
+ * @fr1:	The program being loaded depends on FPU being in FR=1 mode.
+ * @frdefault:	The program being loaded depends on the default FPU mode.
+ *		That is FR0 for O32 and FR1 for N32/N64.
+ * @fre:	The program being loaded depends on FPU with FRE=1. This mode is
+ *		a bridge which uses FR=1 whilst still being able to maintain
+ *		full compatibility with pre-existing code using the O32 FP32
+ *		ABI.
+ *
+ * More information about the FP ABIs can be found here:
+ *
+ * https://dmz-portal.mips.com/wiki/MIPS_O32_ABI_-_FR0_and_FR1_Interlinking#10.4.1._Basic_mode_set-up
+ *
+ */
+
+struct mode_req {
+	bool single;
+	bool soft;
+	bool fr1;
+	bool frdefault;
+	bool fre;
+};
+
+static const struct mode_req fpu_reqs[] = {
+	[MIPS_ABI_FP_ANY]    = { true,  true,  true,  true,  true  },
+	[MIPS_ABI_FP_DOUBLE] = { false, false, false, true,  true  },
+	[MIPS_ABI_FP_SINGLE] = { true,  false, false, false, false },
+	[MIPS_ABI_FP_SOFT]   = { false, true,  false, false, false },
+	[MIPS_ABI_FP_OLD_64] = { false, false, false, false, false },
+	[MIPS_ABI_FP_XX]     = { false, false, true,  true,  true  },
+	[MIPS_ABI_FP_64]     = { false, false, true,  false, false },
+	[MIPS_ABI_FP_64A]    = { false, false, true,  false, true  }
+};
+
+/*
+ * Mode requirements when .MIPS.abiflags is not present in the ELF.
+ * Not present means that everything is acceptable except FR1.
+ */
+static struct mode_req none_req = { true, true, false, true, true };
+
 int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 		     bool is_interp, struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
-	struct elf_phdr *phdr = _phdr;
+	struct elf32_hdr *ehdr32 = _ehdr;
+	struct elf32_phdr *phdr32 = _phdr;
+	struct elf64_phdr *phdr64 = _phdr;
 	struct mips_elf_abiflags_v0 abiflags;
 	int ret;
 
-	if (config_enabled(CONFIG_64BIT) &&
-	    (ehdr->e_ident[EI_CLASS] != ELFCLASS32))
-		return 0;
-	if (phdr->p_type != PT_MIPS_ABIFLAGS)
-		return 0;
-	if (phdr->p_filesz < sizeof(abiflags))
-		return -EINVAL;
+	/* Lets see if this is an O32 ELF */
+	if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) {
+		/* FR = 1 for N32 */
+		if (ehdr32->e_flags & EF_MIPS_ABI2)
+			state->overall_fp_mode = FP_FR1;
+		else
+			/* Set a good default FPU mode for O32 */
+			state->overall_fp_mode = cpu_has_mips_r6 ?
+				FP_FRE : FP_FR0;
+
+		if (ehdr32->e_flags & EF_MIPS_FP64) {
+			/*
+			 * Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it
+			 * later if needed
+			 */
+			if (is_interp)
+				state->interp_fp_abi = MIPS_ABI_FP_OLD_64;
+			else
+				state->fp_abi = MIPS_ABI_FP_OLD_64;
+		}
+		if (phdr32->p_type != PT_MIPS_ABIFLAGS)
+			return 0;
+
+		if (phdr32->p_filesz < sizeof(abiflags))
+			return -EINVAL;
+
+		ret = kernel_read(elf, phdr32->p_offset,
+				  (char *)&abiflags,
+				  sizeof(abiflags));
+	} else {
+		/* FR=1 is really the only option for 64-bit */
+		state->overall_fp_mode = FP_FR1;
+
+		if (phdr64->p_type != PT_MIPS_ABIFLAGS)
+			return 0;
+		if (phdr64->p_filesz < sizeof(abiflags))
+			return -EINVAL;
+
+		ret = kernel_read(elf, phdr64->p_offset,
+				  (char *)&abiflags,
+				  sizeof(abiflags));
+	}
 
-	ret = kernel_read(elf, phdr->p_offset, (char *)&abiflags,
-			  sizeof(abiflags));
 	if (ret < 0)
 		return ret;
 	if (ret != sizeof(abiflags))
@@ -48,35 +131,30 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 	return 0;
 }
 
-static inline unsigned get_fp_abi(struct elfhdr *ehdr, int in_abi)
+static inline unsigned get_fp_abi(int in_abi)
 {
 	/* If the ABI requirement is provided, simply return that */
-	if (in_abi != -1)
+	if (in_abi != MIPS_ABI_FP_UNKNOWN)
 		return in_abi;
 
-	/* If the EF_MIPS_FP64 flag was set, return MIPS_ABI_FP_64 */
-	if (ehdr->e_flags & EF_MIPS_FP64)
-		return MIPS_ABI_FP_64;
-
-	/* Default to MIPS_ABI_FP_DOUBLE */
-	return MIPS_ABI_FP_DOUBLE;
+	/* Unknown ABI */
+	return MIPS_ABI_FP_UNKNOWN;
 }
 
 int arch_check_elf(void *_ehdr, bool has_interpreter,
 		   struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
-	unsigned fp_abi, interp_fp_abi, abi0, abi1;
+	struct elf32_hdr *ehdr = _ehdr;
+	struct mode_req prog_req, interp_req;
+	int fp_abi, interp_fp_abi, abi0, abi1, max_abi;
 
-	/* Ignore non-O32 binaries */
-	if (config_enabled(CONFIG_64BIT) &&
-	    (ehdr->e_ident[EI_CLASS] != ELFCLASS32))
+	if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
 		return 0;
 
-	fp_abi = get_fp_abi(ehdr, state->fp_abi);
+	fp_abi = get_fp_abi(state->fp_abi);
 
 	if (has_interpreter) {
-		interp_fp_abi = get_fp_abi(ehdr, state->interp_fp_abi);
+		interp_fp_abi = get_fp_abi(state->interp_fp_abi);
 
 		abi0 = min(fp_abi, interp_fp_abi);
 		abi1 = max(fp_abi, interp_fp_abi);
@@ -84,108 +162,103 @@ int arch_check_elf(void *_ehdr, bool has_interpreter,
 		abi0 = abi1 = fp_abi;
 	}
 
-	state->overall_abi = FP_ERROR;
-
-	if (abi0 == abi1) {
-		state->overall_abi = abi0;
-	} else if (abi0 == MIPS_ABI_FP_ANY) {
-		state->overall_abi = abi1;
-	} else if (abi0 == MIPS_ABI_FP_DOUBLE) {
-		switch (abi1) {
-		case MIPS_ABI_FP_XX:
-			state->overall_abi = MIPS_ABI_FP_DOUBLE;
-			break;
-
-		case MIPS_ABI_FP_64A:
-			state->overall_abi = FP_DOUBLE_64A;
-			break;
-		}
-	} else if (abi0 == MIPS_ABI_FP_SINGLE ||
-		   abi0 == MIPS_ABI_FP_SOFT) {
-		/* Cannot link with other ABIs */
-	} else if (abi0 == MIPS_ABI_FP_OLD_64) {
-		switch (abi1) {
-		case MIPS_ABI_FP_XX:
-		case MIPS_ABI_FP_64:
-		case MIPS_ABI_FP_64A:
-			state->overall_abi = MIPS_ABI_FP_64;
-			break;
-		}
-	} else if (abi0 == MIPS_ABI_FP_XX ||
-		   abi0 == MIPS_ABI_FP_64 ||
-		   abi0 == MIPS_ABI_FP_64A) {
-		state->overall_abi = MIPS_ABI_FP_64;
-	}
+	/* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */
+	max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) &&
+		   (!(ehdr->e_flags & EF_MIPS_ABI2))) ?
+		MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT;
 
-	switch (state->overall_abi) {
-	case MIPS_ABI_FP_64:
-	case MIPS_ABI_FP_64A:
-	case FP_DOUBLE_64A:
-		if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
-			return -ELIBBAD;
-		break;
+	if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) ||
+	    (abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN))
+		return -ELIBBAD;
+
+	/* It's time to determine the FPU mode requirements */
+	prog_req = (abi0 == MIPS_ABI_FP_UNKNOWN) ? none_req : fpu_reqs[abi0];
+	interp_req = (abi1 == MIPS_ABI_FP_UNKNOWN) ? none_req : fpu_reqs[abi1];
 
-	case FP_ERROR:
+	/*
+	 * Check whether the program's and interp's ABIs have a matching FPU
+	 * mode requirement.
+	 */
+	prog_req.single = interp_req.single && prog_req.single;
+	prog_req.soft = interp_req.soft && prog_req.soft;
+	prog_req.fr1 = interp_req.fr1 && prog_req.fr1;
+	prog_req.frdefault = interp_req.frdefault && prog_req.frdefault;
+	prog_req.fre = interp_req.fre && prog_req.fre;
+
+	/*
+	 * Determine the desired FPU mode
+	 *
+	 * Decision making:
+	 *
+	 * - We want FR_FRE if FRE=1 and both FR=1 and FR=0 are false. This
+	 *   means that we have a combination of program and interpreter
+	 *   that inherently require the hybrid FP mode.
+	 * - If FR1 and FRDEFAULT is true, that means we hit the any-abi or
+	 *   fpxx case. This is because, in any-ABI (or no-ABI) we have no FPU
+	 *   instructions so we don't care about the mode. We will simply use
+	 *   the one preferred by the hardware. In fpxx case, that ABI can
+	 *   handle both FR=1 and FR=0, so, again, we simply choose the one
+	 *   preferred by the hardware. Next, if we only use single-precision
+	 *   FPU instructions, and the default ABI FPU mode is not good
+	 *   (ie single + any ABI combination), we set again the FPU mode to the
+	 *   one is preferred by the hardware. Next, if we know that the code
+	 *   will only use single-precision instructions, shown by single being
+	 *   true but frdefault being false, then we again set the FPU mode to
+	 *   the one that is preferred by the hardware.
+	 * - We want FP_FR1 if that's the only matching mode and the default one
+	 *   is not good.
+	 * - Return with -ELIBADD if we can't find a matching FPU mode.
+	 */
+	if (prog_req.fre && !prog_req.frdefault && !prog_req.fr1)
+		state->overall_fp_mode = FP_FRE;
+	else if ((prog_req.fr1 && prog_req.frdefault) ||
+		 (prog_req.single && !prog_req.frdefault))
+		/* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */
+		state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
+					  cpu_has_mips_r2_r6) ?
+					  FP_FR1 : FP_FR0;
+	else if (prog_req.fr1)
+		state->overall_fp_mode = FP_FR1;
+	else  if (!prog_req.fre && !prog_req.frdefault &&
+		  !prog_req.fr1 && !prog_req.single && !prog_req.soft)
 		return -ELIBBAD;
-	}
 
 	return 0;
 }
 
-void mips_set_personality_fp(struct arch_elf_state *state)
+static inline void set_thread_fp_mode(int hybrid, int regs32)
 {
-	if (config_enabled(CONFIG_FP32XX_HYBRID_FPRS)) {
-		/*
-		 * Use hybrid FPRs for all code which can correctly execute
-		 * with that mode.
-		 */
-		switch (state->overall_abi) {
-		case MIPS_ABI_FP_DOUBLE:
-		case MIPS_ABI_FP_SINGLE:
-		case MIPS_ABI_FP_SOFT:
-		case MIPS_ABI_FP_XX:
-		case MIPS_ABI_FP_ANY:
-			/* FR=1, FRE=1 */
-			clear_thread_flag(TIF_32BIT_FPREGS);
-			set_thread_flag(TIF_HYBRID_FPREGS);
-			return;
-		}
-	}
-
-	switch (state->overall_abi) {
-	case MIPS_ABI_FP_DOUBLE:
-	case MIPS_ABI_FP_SINGLE:
-	case MIPS_ABI_FP_SOFT:
-		/* FR=0 */
-		set_thread_flag(TIF_32BIT_FPREGS);
+	if (hybrid)
+		set_thread_flag(TIF_HYBRID_FPREGS);
+	else
 		clear_thread_flag(TIF_HYBRID_FPREGS);
-		break;
-
-	case FP_DOUBLE_64A:
-		/* FR=1, FRE=1 */
+	if (regs32)
+		set_thread_flag(TIF_32BIT_FPREGS);
+	else
 		clear_thread_flag(TIF_32BIT_FPREGS);
-		set_thread_flag(TIF_HYBRID_FPREGS);
-		break;
+}
 
-	case MIPS_ABI_FP_64:
-	case MIPS_ABI_FP_64A:
-		/* FR=1, FRE=0 */
-		clear_thread_flag(TIF_32BIT_FPREGS);
-		clear_thread_flag(TIF_HYBRID_FPREGS);
-		break;
+void mips_set_personality_fp(struct arch_elf_state *state)
+{
+	/*
+	 * This function is only ever called for O32 ELFs so we should
+	 * not be worried about N32/N64 binaries.
+	 */
 
-	case MIPS_ABI_FP_XX:
-	case MIPS_ABI_FP_ANY:
-		if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
-			set_thread_flag(TIF_32BIT_FPREGS);
-		else
-			clear_thread_flag(TIF_32BIT_FPREGS);
+	if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
+		return;
 
-		clear_thread_flag(TIF_HYBRID_FPREGS);
+	switch (state->overall_fp_mode) {
+	case FP_FRE:
+		set_thread_fp_mode(1, 0);
+		break;
+	case FP_FR0:
+		set_thread_fp_mode(0, 1);
+		break;
+	case FP_FR1:
+		set_thread_fp_mode(0, 0);
 		break;
-
 	default:
-	case FP_ERROR:
 		BUG();
 	}
 }
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 4353d323f017..af41ba6db960 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -46,6 +46,11 @@ resume_userspace:
 	local_irq_disable		# make sure we dont miss an
 					# interrupt setting need_resched
 					# between sampling and return
+#ifdef CONFIG_MIPSR2_TO_R6_EMULATOR
+	lw	k0, TI_R2_EMUL_RET($28)
+	bnez	k0, restore_all_from_r2_emul
+#endif
+
 	LONG_L	a2, TI_FLAGS($28)	# current->work
 	andi	t0, a2, _TIF_WORK_MASK	# (ignoring syscall_trace)
 	bnez	t0, work_pending
@@ -114,6 +119,19 @@ restore_partial:		# restore partial frame
 	RESTORE_SP_AND_RET
 	.set	at
 
+#ifdef CONFIG_MIPSR2_TO_R6_EMULATOR
+restore_all_from_r2_emul:			# restore full frame
+	.set	noat
+	sw	zero, TI_R2_EMUL_RET($28)	# reset it
+	RESTORE_TEMP
+	RESTORE_AT
+	RESTORE_STATIC
+	RESTORE_SOME
+	LONG_L	sp, PT_R29(sp)
+	eretnc
+	.set	at
+#endif
+
 work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
@@ -158,7 +176,8 @@ syscall_exit_work:
 	jal	syscall_trace_leave
 	b	resume_userspace
 
-#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT)
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) || \
+    defined(CONFIG_MIPS_MT)
 
 /*
  * MIPS32R2 Instruction Hazard Barrier - must be called
@@ -171,4 +190,4 @@ LEAF(mips_ihb)
 	nop
 	END(mips_ihb)
 
-#endif /* CONFIG_CPU_MIPSR2 or CONFIG_MIPS_MT */
+#endif /* CONFIG_CPU_MIPSR2 or CONFIG_CPU_MIPSR6 or CONFIG_MIPS_MT */
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index a5e26dd90592..2ebaabe3af15 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -125,7 +125,7 @@ LEAF(__r4k_wait)
 	nop
 	nop
 #endif
-	.set	arch=r4000
+	.set	MIPS_ISA_ARCH_LEVEL_RAW
 	wait
 	/* end of rollback region (the region size must be power of two) */
 1:
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 0b9082b6b683..368c88b7eb6c 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -186,6 +186,7 @@ void __init check_wait(void)
 	case CPU_PROAPTIV:
 	case CPU_P5600:
 	case CPU_M5150:
+	case CPU_QEMU_GENERIC:
 		cpu_wait = r4k_wait;
 		if (read_c0_config7() & MIPS_CONF7_WII)
 			cpu_wait = r4k_wait_irqoff;
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
new file mode 100644
index 000000000000..64d17e41093b
--- /dev/null
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -0,0 +1,2378 @@
+/*
+ * 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) 2014 Imagination Technologies Ltd.
+ * Author: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *      MIPS R2 user space instruction emulator for MIPS R6
+ *
+ */
+#include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/seq_file.h>
+
+#include <asm/asm.h>
+#include <asm/branch.h>
+#include <asm/break.h>
+#include <asm/fpu.h>
+#include <asm/fpu_emulator.h>
+#include <asm/inst.h>
+#include <asm/mips-r2-to-r6-emul.h>
+#include <asm/local.h>
+#include <asm/ptrace.h>
+#include <asm/uaccess.h>
+
+#ifdef CONFIG_64BIT
+#define ADDIU	"daddiu "
+#define INS	"dins "
+#define EXT	"dext "
+#else
+#define ADDIU	"addiu "
+#define INS	"ins "
+#define EXT	"ext "
+#endif /* CONFIG_64BIT */
+
+#define SB	"sb "
+#define LB	"lb "
+#define LL	"ll "
+#define SC	"sc "
+
+DEFINE_PER_CPU(struct mips_r2_emulator_stats, mipsr2emustats);
+DEFINE_PER_CPU(struct mips_r2_emulator_stats, mipsr2bdemustats);
+DEFINE_PER_CPU(struct mips_r2br_emulator_stats, mipsr2bremustats);
+
+extern const unsigned int fpucondbit[8];
+
+#define MIPS_R2_EMUL_TOTAL_PASS	10
+
+int mipsr2_emulation = 0;
+
+static int __init mipsr2emu_enable(char *s)
+{
+	mipsr2_emulation = 1;
+
+	pr_info("MIPS R2-to-R6 Emulator Enabled!");
+
+	return 1;
+}
+__setup("mipsr2emu", mipsr2emu_enable);
+
+/**
+ * mipsr6_emul - Emulate some frequent R2/R5/R6 instructions in delay slot
+ * for performance instead of the traditional way of using a stack trampoline
+ * which is rather slow.
+ * @regs: Process register set
+ * @ir: Instruction
+ */
+static inline int mipsr6_emul(struct pt_regs *regs, u32 ir)
+{
+	switch (MIPSInst_OPCODE(ir)) {
+	case addiu_op:
+		if (MIPSInst_RT(ir))
+			regs->regs[MIPSInst_RT(ir)] =
+				(s32)regs->regs[MIPSInst_RS(ir)] +
+				(s32)MIPSInst_SIMM(ir);
+		return 0;
+	case daddiu_op:
+		if (config_enabled(CONFIG_32BIT))
+			break;
+
+		if (MIPSInst_RT(ir))
+			regs->regs[MIPSInst_RT(ir)] =
+				(s64)regs->regs[MIPSInst_RS(ir)] +
+				(s64)MIPSInst_SIMM(ir);
+		return 0;
+	case lwc1_op:
+	case swc1_op:
+	case cop1_op:
+	case cop1x_op:
+		/* FPU instructions in delay slot */
+		return -SIGFPE;
+	case spec_op:
+		switch (MIPSInst_FUNC(ir)) {
+		case or_op:
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					regs->regs[MIPSInst_RS(ir)] |
+					regs->regs[MIPSInst_RT(ir)];
+			return 0;
+		case sll_op:
+			if (MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)(((u32)regs->regs[MIPSInst_RT(ir)]) <<
+						MIPSInst_FD(ir));
+			return 0;
+		case srl_op:
+			if (MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)(((u32)regs->regs[MIPSInst_RT(ir)]) >>
+						MIPSInst_FD(ir));
+			return 0;
+		case addu_op:
+			if (MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)((u32)regs->regs[MIPSInst_RS(ir)] +
+					      (u32)regs->regs[MIPSInst_RT(ir)]);
+			return 0;
+		case subu_op:
+			if (MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s32)((u32)regs->regs[MIPSInst_RS(ir)] -
+					      (u32)regs->regs[MIPSInst_RT(ir)]);
+			return 0;
+		case dsll_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s64)(((u64)regs->regs[MIPSInst_RT(ir)]) <<
+						MIPSInst_FD(ir));
+			return 0;
+		case dsrl_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_RS(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s64)(((u64)regs->regs[MIPSInst_RT(ir)]) >>
+						MIPSInst_FD(ir));
+			return 0;
+		case daddu_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(u64)regs->regs[MIPSInst_RS(ir)] +
+					(u64)regs->regs[MIPSInst_RT(ir)];
+			return 0;
+		case dsubu_op:
+			if (config_enabled(CONFIG_32BIT) || MIPSInst_FD(ir))
+				break;
+
+			if (MIPSInst_RD(ir))
+				regs->regs[MIPSInst_RD(ir)] =
+					(s64)((u64)regs->regs[MIPSInst_RS(ir)] -
+					      (u64)regs->regs[MIPSInst_RT(ir)]);
+			return 0;
+		}
+		break;
+	default:
+		pr_debug("No fastpath BD emulation for instruction 0x%08x (op: %02x)\n",
+			 ir, MIPSInst_OPCODE(ir));
+	}
+
+	return SIGILL;
+}
+
+/**
+ * movt_func - Emulate a MOVT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movf_func(struct pt_regs *regs, u32 ir)
+{
+	u32 csr;
+	u32 cond;
+
+	csr = current->thread.fpu.fcr31;
+	cond = fpucondbit[MIPSInst_RT(ir) >> 2];
+	if (((csr & cond) == 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+	MIPS_R2_STATS(movs);
+	return 0;
+}
+
+/**
+ * movt_func - Emulate a MOVT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movt_func(struct pt_regs *regs, u32 ir)
+{
+	u32 csr;
+	u32 cond;
+
+	csr = current->thread.fpu.fcr31;
+	cond = fpucondbit[MIPSInst_RT(ir) >> 2];
+
+	if (((csr & cond) != 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+
+	MIPS_R2_STATS(movs);
+
+	return 0;
+}
+
+/**
+ * jr_func - Emulate a JR instruction.
+ * @pt_regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns SIGILL if JR was in delay slot, SIGEMT if we
+ * can't compute the EPC, SIGSEGV if we can't access the
+ * userland instruction or 0 on success.
+ */
+static int jr_func(struct pt_regs *regs, u32 ir)
+{
+	int err;
+	unsigned long cepc, epc, nepc;
+	u32 nir;
+
+	if (delay_slot(regs))
+		return SIGILL;
+
+	/* EPC after the RI/JR instruction */
+	nepc = regs->cp0_epc;
+	/* Roll back to the reserved R2 JR instruction */
+	regs->cp0_epc -= 4;
+	epc = regs->cp0_epc;
+	err = __compute_return_epc(regs);
+
+	if (err < 0)
+		return SIGEMT;
+
+
+	/* Computed EPC */
+	cepc = regs->cp0_epc;
+
+	/* Get DS instruction */
+	err = __get_user(nir, (u32 __user *)nepc);
+	if (err)
+		return SIGSEGV;
+
+	MIPS_R2BR_STATS(jrs);
+
+	/* If nir == 0(NOP), then nothing else to do */
+	if (nir) {
+		/*
+		 * Negative err means FPU instruction in BD-slot,
+		 * Zero err means 'BD-slot emulation done'
+		 * For anything else we go back to trampoline emulation.
+		 */
+		err = mipsr6_emul(regs, nir);
+		if (err > 0) {
+			regs->cp0_epc = nepc;
+			err = mips_dsemul(regs, nir, cepc);
+			if (err == SIGILL)
+				err = SIGEMT;
+			MIPS_R2_STATS(dsemul);
+		}
+	}
+
+	return err;
+}
+
+/**
+ * movz_func - Emulate a MOVZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movz_func(struct pt_regs *regs, u32 ir)
+{
+	if (((regs->regs[MIPSInst_RT(ir)]) == 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+	MIPS_R2_STATS(movs);
+
+	return 0;
+}
+
+/**
+ * movn_func - Emulate a MOVZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int movn_func(struct pt_regs *regs, u32 ir)
+{
+	if (((regs->regs[MIPSInst_RT(ir)]) != 0) && MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->regs[MIPSInst_RS(ir)];
+	MIPS_R2_STATS(movs);
+
+	return 0;
+}
+
+/**
+ * mfhi_func - Emulate a MFHI instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mfhi_func(struct pt_regs *regs, u32 ir)
+{
+	if (MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->hi;
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mthi_func - Emulate a MTHI instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mthi_func(struct pt_regs *regs, u32 ir)
+{
+	regs->hi = regs->regs[MIPSInst_RS(ir)];
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mflo_func - Emulate a MFLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mflo_func(struct pt_regs *regs, u32 ir)
+{
+	if (MIPSInst_RD(ir))
+		regs->regs[MIPSInst_RD(ir)] = regs->lo;
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mtlo_func - Emulate a MTLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mtlo_func(struct pt_regs *regs, u32 ir)
+{
+	regs->lo = regs->regs[MIPSInst_RS(ir)];
+
+	MIPS_R2_STATS(hilo);
+
+	return 0;
+}
+
+/**
+ * mult_func - Emulate a MULT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mult_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+
+	rs = res;
+	regs->lo = (s64)rs;
+	rt = res >> 32;
+	res = (s64)rt;
+	regs->hi = res;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * multu_func - Emulate a MULTU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int multu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (u64)rt * (u64)rs;
+	rt = res;
+	regs->lo = (s64)rt;
+	regs->hi = (s64)(res >> 32);
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * div_func - Emulate a DIV instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int div_func(struct pt_regs *regs, u32 ir)
+{
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = (s64)(rs / rt);
+	regs->hi = (s64)(rs % rt);
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/**
+ * divu_func - Emulate a DIVU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int divu_func(struct pt_regs *regs, u32 ir)
+{
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = (s64)(rs / rt);
+	regs->hi = (s64)(rs % rt);
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/**
+ * dmult_func - Emulate a DMULT instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int dmult_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = rt * rs;
+
+	regs->lo = res;
+	__asm__ __volatile__(
+		"dmuh %0, %1, %2\t\n"
+		: "=r"(res)
+		: "r"(rt), "r"(rs));
+
+	regs->hi = res;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * dmultu_func - Emulate a DMULTU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int dmultu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = rt * rs;
+
+	regs->lo = res;
+	__asm__ __volatile__(
+		"dmuhu %0, %1, %2\t\n"
+		: "=r"(res)
+		: "r"(rt), "r"(rs));
+
+	regs->hi = res;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * ddiv_func - Emulate a DDIV instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int ddiv_func(struct pt_regs *regs, u32 ir)
+{
+	s64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = rs / rt;
+	regs->hi = rs % rt;
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/**
+ * ddivu_func - Emulate a DDIVU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 on success or SIGILL for 32-bit kernels.
+ */
+static int ddivu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 rt, rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+
+	regs->lo = rs / rt;
+	regs->hi = rs % rt;
+
+	MIPS_R2_STATS(divs);
+
+	return 0;
+}
+
+/* R6 removed instructions for the SPECIAL opcode */
+static struct r2_decoder_table spec_op_table[] = {
+	{ 0xfc1ff83f, 0x00000008, jr_func },
+	{ 0xfc00ffff, 0x00000018, mult_func },
+	{ 0xfc00ffff, 0x00000019, multu_func },
+	{ 0xfc00ffff, 0x0000001c, dmult_func },
+	{ 0xfc00ffff, 0x0000001d, dmultu_func },
+	{ 0xffff07ff, 0x00000010, mfhi_func },
+	{ 0xfc1fffff, 0x00000011, mthi_func },
+	{ 0xffff07ff, 0x00000012, mflo_func },
+	{ 0xfc1fffff, 0x00000013, mtlo_func },
+	{ 0xfc0307ff, 0x00000001, movf_func },
+	{ 0xfc0307ff, 0x00010001, movt_func },
+	{ 0xfc0007ff, 0x0000000a, movz_func },
+	{ 0xfc0007ff, 0x0000000b, movn_func },
+	{ 0xfc00ffff, 0x0000001a, div_func },
+	{ 0xfc00ffff, 0x0000001b, divu_func },
+	{ 0xfc00ffff, 0x0000001e, ddiv_func },
+	{ 0xfc00ffff, 0x0000001f, ddivu_func },
+	{}
+};
+
+/**
+ * madd_func - Emulate a MADD instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int madd_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res += ((((s64)rt) << 32) | (u32)rs);
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * maddu_func - Emulate a MADDU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int maddu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (u64)rt * (u64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res += ((((s64)rt) << 32) | (u32)rs);
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * msub_func - Emulate a MSUB instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int msub_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res = ((((s64)rt) << 32) | (u32)rs) - res;
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * msubu_func - Emulate a MSUBU instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int msubu_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u32 rt, rs;
+
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (u64)rt * (u64)rs;
+	rt = regs->hi;
+	rs = regs->lo;
+	res = ((((s64)rt) << 32) | (u32)rs) - res;
+
+	rt = res;
+	regs->lo = (s64)rt;
+	rs = res >> 32;
+	regs->hi = (s64)rs;
+
+	MIPS_R2_STATS(dsps);
+
+	return 0;
+}
+
+/**
+ * mul_func - Emulate a MUL instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int mul_func(struct pt_regs *regs, u32 ir)
+{
+	s64 res;
+	s32 rt, rs;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+	rt = regs->regs[MIPSInst_RT(ir)];
+	rs = regs->regs[MIPSInst_RS(ir)];
+	res = (s64)rt * (s64)rs;
+
+	rs = res;
+	regs->regs[MIPSInst_RD(ir)] = (s64)rs;
+
+	MIPS_R2_STATS(muls);
+
+	return 0;
+}
+
+/**
+ * clz_func - Emulate a CLZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int clz_func(struct pt_regs *regs, u32 ir)
+{
+	u32 res;
+	u32 rs;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("clz %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/**
+ * clo_func - Emulate a CLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+
+static int clo_func(struct pt_regs *regs, u32 ir)
+{
+	u32 res;
+	u32 rs;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("clo %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/**
+ * dclz_func - Emulate a DCLZ instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int dclz_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u64 rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("dclz %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/**
+ * dclo_func - Emulate a DCLO instruction
+ * @regs: Process register set
+ * @ir: Instruction
+ *
+ * Returns 0 since it always succeeds.
+ */
+static int dclo_func(struct pt_regs *regs, u32 ir)
+{
+	u64 res;
+	u64 rs;
+
+	if (config_enabled(CONFIG_32BIT))
+		return SIGILL;
+
+	if (!MIPSInst_RD(ir))
+		return 0;
+
+	rs = regs->regs[MIPSInst_RS(ir)];
+	__asm__ __volatile__("dclo %0, %1" : "=r"(res) : "r"(rs));
+	regs->regs[MIPSInst_RD(ir)] = res;
+
+	MIPS_R2_STATS(bops);
+
+	return 0;
+}
+
+/* R6 removed instructions for the SPECIAL2 opcode */
+static struct r2_decoder_table spec2_op_table[] = {
+	{ 0xfc00ffff, 0x70000000, madd_func },
+	{ 0xfc00ffff, 0x70000001, maddu_func },
+	{ 0xfc0007ff, 0x70000002, mul_func },
+	{ 0xfc00ffff, 0x70000004, msub_func },
+	{ 0xfc00ffff, 0x70000005, msubu_func },
+	{ 0xfc0007ff, 0x70000020, clz_func },
+	{ 0xfc0007ff, 0x70000021, clo_func },
+	{ 0xfc0007ff, 0x70000024, dclz_func },
+	{ 0xfc0007ff, 0x70000025, dclo_func },
+	{ }
+};
+
+static inline int mipsr2_find_op_func(struct pt_regs *regs, u32 inst,
+				      struct r2_decoder_table *table)
+{
+	struct r2_decoder_table *p;
+	int err;
+
+	for (p = table; p->func; p++) {
+		if ((inst & p->mask) == p->code) {
+			err = (p->func)(regs, inst);
+			return err;
+		}
+	}
+	return SIGILL;
+}
+
+/**
+ * mipsr2_decoder: Decode and emulate a MIPS R2 instruction
+ * @regs: Process register set
+ * @inst: Instruction to decode and emulate
+ */
+int mipsr2_decoder(struct pt_regs *regs, u32 inst)
+{
+	int err = 0;
+	unsigned long vaddr;
+	u32 nir;
+	unsigned long cpc, epc, nepc, r31, res, rs, rt;
+
+	void __user *fault_addr = NULL;
+	int pass = 0;
+
+repeat:
+	r31 = regs->regs[31];
+	epc = regs->cp0_epc;
+	err = compute_return_epc(regs);
+	if (err < 0) {
+		BUG();
+		return SIGEMT;
+	}
+	pr_debug("Emulating the 0x%08x R2 instruction @ 0x%08lx (pass=%d))\n",
+		 inst, epc, pass);
+
+	switch (MIPSInst_OPCODE(inst)) {
+	case spec_op:
+		err = mipsr2_find_op_func(regs, inst, spec_op_table);
+		if (err < 0) {
+			/* FPU instruction under JR */
+			regs->cp0_cause |= CAUSEF_BD;
+			goto fpu_emul;
+		}
+		break;
+	case spec2_op:
+		err = mipsr2_find_op_func(regs, inst, spec2_op_table);
+		break;
+	case bcond_op:
+		rt = MIPSInst_RT(inst);
+		rs = MIPSInst_RS(inst);
+		switch (rt) {
+		case tgei_op:
+			if ((long)regs->regs[rs] >= MIPSInst_SIMM(inst))
+				do_trap_or_bp(regs, 0, "TGEI");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case tgeiu_op:
+			if (regs->regs[rs] >= MIPSInst_UIMM(inst))
+				do_trap_or_bp(regs, 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");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case tltiu_op:
+			if (regs->regs[rs] < MIPSInst_UIMM(inst))
+				do_trap_or_bp(regs, 0, "TLTIU");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case teqi_op:
+			if (regs->regs[rs] == MIPSInst_SIMM(inst))
+				do_trap_or_bp(regs, 0, "TEQI");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case tnei_op:
+			if (regs->regs[rs] != MIPSInst_SIMM(inst))
+				do_trap_or_bp(regs, 0, "TNEI");
+
+			MIPS_R2_STATS(traps);
+
+			break;
+		case bltzl_op:
+		case bgezl_op:
+		case bltzall_op:
+		case bgezall_op:
+			if (delay_slot(regs)) {
+				err = SIGILL;
+				break;
+			}
+			regs->regs[31] = r31;
+			regs->cp0_epc = epc;
+			err = __compute_return_epc(regs);
+			if (err < 0)
+				return SIGEMT;
+			if (err != BRANCH_LIKELY_TAKEN)
+				break;
+			cpc = regs->cp0_epc;
+			nepc = epc + 4;
+			err = __get_user(nir, (u32 __user *)nepc);
+			if (err) {
+				err = SIGSEGV;
+				break;
+			}
+			/*
+			 * This will probably be optimized away when
+			 * CONFIG_DEBUG_FS is not enabled
+			 */
+			switch (rt) {
+			case bltzl_op:
+				MIPS_R2BR_STATS(bltzl);
+				break;
+			case bgezl_op:
+				MIPS_R2BR_STATS(bgezl);
+				break;
+			case bltzall_op:
+				MIPS_R2BR_STATS(bltzall);
+				break;
+			case bgezall_op:
+				MIPS_R2BR_STATS(bgezall);
+				break;
+			}
+
+			switch (MIPSInst_OPCODE(nir)) {
+			case cop1_op:
+			case cop1x_op:
+			case lwc1_op:
+			case swc1_op:
+				regs->cp0_cause |= CAUSEF_BD;
+				goto fpu_emul;
+			}
+			if (nir) {
+				err = mipsr6_emul(regs, nir);
+				if (err > 0) {
+					err = mips_dsemul(regs, nir, cpc);
+					if (err == SIGILL)
+						err = SIGEMT;
+					MIPS_R2_STATS(dsemul);
+				}
+			}
+			break;
+		case bltzal_op:
+		case bgezal_op:
+			if (delay_slot(regs)) {
+				err = SIGILL;
+				break;
+			}
+			regs->regs[31] = r31;
+			regs->cp0_epc = epc;
+			err = __compute_return_epc(regs);
+			if (err < 0)
+				return SIGEMT;
+			cpc = regs->cp0_epc;
+			nepc = epc + 4;
+			err = __get_user(nir, (u32 __user *)nepc);
+			if (err) {
+				err = SIGSEGV;
+				break;
+			}
+			/*
+			 * This will probably be optimized away when
+			 * CONFIG_DEBUG_FS is not enabled
+			 */
+			switch (rt) {
+			case bltzal_op:
+				MIPS_R2BR_STATS(bltzal);
+				break;
+			case bgezal_op:
+				MIPS_R2BR_STATS(bgezal);
+				break;
+			}
+
+			switch (MIPSInst_OPCODE(nir)) {
+			case cop1_op:
+			case cop1x_op:
+			case lwc1_op:
+			case swc1_op:
+				regs->cp0_cause |= CAUSEF_BD;
+				goto fpu_emul;
+			}
+			if (nir) {
+				err = mipsr6_emul(regs, nir);
+				if (err > 0) {
+					err = mips_dsemul(regs, nir, cpc);
+					if (err == SIGILL)
+						err = SIGEMT;
+					MIPS_R2_STATS(dsemul);
+				}
+			}
+			break;
+		default:
+			regs->regs[31] = r31;
+			regs->cp0_epc = epc;
+			err = SIGILL;
+			break;
+		}
+		break;
+
+	case beql_op:
+	case bnel_op:
+	case blezl_op:
+	case bgtzl_op:
+		if (delay_slot(regs)) {
+			err = SIGILL;
+			break;
+		}
+		regs->regs[31] = r31;
+		regs->cp0_epc = epc;
+		err = __compute_return_epc(regs);
+		if (err < 0)
+			return SIGEMT;
+		if (err != BRANCH_LIKELY_TAKEN)
+			break;
+		cpc = regs->cp0_epc;
+		nepc = epc + 4;
+		err = __get_user(nir, (u32 __user *)nepc);
+		if (err) {
+			err = SIGSEGV;
+			break;
+		}
+		/*
+		 * This will probably be optimized away when
+		 * CONFIG_DEBUG_FS is not enabled
+		 */
+		switch (MIPSInst_OPCODE(inst)) {
+		case beql_op:
+			MIPS_R2BR_STATS(beql);
+			break;
+		case bnel_op:
+			MIPS_R2BR_STATS(bnel);
+			break;
+		case blezl_op:
+			MIPS_R2BR_STATS(blezl);
+			break;
+		case bgtzl_op:
+			MIPS_R2BR_STATS(bgtzl);
+			break;
+		}
+
+		switch (MIPSInst_OPCODE(nir)) {
+		case cop1_op:
+		case cop1x_op:
+		case lwc1_op:
+		case swc1_op:
+			regs->cp0_cause |= CAUSEF_BD;
+			goto fpu_emul;
+		}
+		if (nir) {
+			err = mipsr6_emul(regs, nir);
+			if (err > 0) {
+				err = mips_dsemul(regs, nir, cpc);
+				if (err == SIGILL)
+					err = SIGEMT;
+				MIPS_R2_STATS(dsemul);
+			}
+		}
+		break;
+	case lwc1_op:
+	case swc1_op:
+	case cop1_op:
+	case cop1x_op:
+fpu_emul:
+		regs->regs[31] = r31;
+		regs->cp0_epc = epc;
+		if (!used_math()) {     /* First time FPU user.  */
+			err = init_fpu();
+			set_used_math();
+		}
+		lose_fpu(1);    /* Save FPU state for the emulator. */
+
+		err = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 0,
+					       &fault_addr);
+
+		/*
+		 * this is a tricky issue - lose_fpu() uses LL/SC atomics
+		 * if FPU is owned and effectively cancels user level LL/SC.
+		 * So, it could be logical to don't restore FPU ownership here.
+		 * But the sequence of multiple FPU instructions is much much
+		 * more often than LL-FPU-SC and I prefer loop here until
+		 * next scheduler cycle cancels FPU ownership
+		 */
+		own_fpu(1);	/* Restore FPU state. */
+
+		if (err)
+			current->thread.cp0_baduaddr = (unsigned long)fault_addr;
+
+		MIPS_R2_STATS(fpus);
+
+		break;
+
+	case lwl_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"2:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"3:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"4:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+			"2:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+			"3:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+			"4:"	LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:	sll	%0, %0, 0\n"
+			"10:\n"
+			"	.insn\n"
+			"	.section	.fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	10b\n"
+			"	.previous\n"
+			"	.section	__ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+
+		break;
+
+	case lwr_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"       .set	push\n"
+			"       .set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+			"2:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+			"3:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+				ADDIU	"%2, %2, 1\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+			"4:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+			"       sll	%0, %0, 0\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 0, 8\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"2:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 8, 8\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"3:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 16, 8\n"
+			"       andi	%1, %2, 0x3\n"
+			"       beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+			"4:"    LB	"%1, 0(%2)\n"
+				INS	"%0, %1, 24, 8\n"
+			"       sll	%0, %0, 0\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"10:\n"
+			"	.insn\n"
+			"	.section	.fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	10b\n"
+			"       .previous\n"
+			"	.section	__ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+
+		break;
+
+	case swl_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+				EXT	"%1, %0, 24, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 16, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 8, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 0, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+				EXT	"%1, %0, 24, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 16, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 8, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 0, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"       .section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+
+		break;
+
+	case swr_op:
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+				EXT	"%1, %0, 0, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 8, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 16, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+				ADDIU	"%2, %2, 1\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				EXT	"%1, %0, 24, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+				EXT	"%1, %0, 0, 8\n"
+			"1:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 8, 8\n"
+			"2:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 16, 8\n"
+			"3:"	SB	"%1, 0(%2)\n"
+			"	andi	%1, %2, 0x3\n"
+			"	beq	$0, %1, 9f\n"
+				ADDIU	"%2, %2, -1\n"
+				EXT	"%1, %0, 24, 8\n"
+			"4:"	SB	"%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+
+		break;
+
+	case ldl_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set    push\n"
+			"	.set    reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 56, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"2:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 48, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"3:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 40, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"4:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 32, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"5:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 24, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"6:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 16, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"7:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 8, 8\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"0:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 0, 8\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 56, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"2:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 48, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"3:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 40, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"4:	lb	%1, 0(%2)\n"
+			"	dinsu	%0, %1, 32, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"5:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 24, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"6:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 16, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"7:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 8, 8\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"0:	lb	%1, 0(%2)\n"
+			"	dins	%0, %1, 0, 8\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.word	5b,8b\n"
+			"	.word	6b,8b\n"
+			"	.word	7b,8b\n"
+			"	.word	0b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+		break;
+
+	case ldr_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set    push\n"
+			"	.set    reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"1:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 0, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"2:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 8, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"3:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 16, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"4:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 24, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"5:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 32, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"6:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 40, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"7:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 48, 8\n"
+			"	daddiu  %2, %2, 1\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"0:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 56, 8\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"1:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 0, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"2:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 8, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"3:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 16, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"4:	lb      %1, 0(%2)\n"
+			"	dins   %0, %1, 24, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"5:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 32, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"6:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 40, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"7:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 48, 8\n"
+			"	andi    %1, %2, 0x7\n"
+			"	beq     $0, %1, 9f\n"
+			"	daddiu  %2, %2, -1\n"
+			"0:	lb      %1, 0(%2)\n"
+			"	dinsu    %0, %1, 56, 8\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li     %3,%4\n"
+			"	j      9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word  1b,8b\n"
+			"	.word  2b,8b\n"
+			"	.word  3b,8b\n"
+			"	.word  4b,8b\n"
+			"	.word  5b,8b\n"
+			"	.word  6b,8b\n"
+			"	.word  7b,8b\n"
+			"	.word  0b,8b\n"
+			"	.previous\n"
+			"	.set    pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV));
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = rt;
+
+		MIPS_R2_STATS(loads);
+		break;
+
+	case sdl_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"	.set	push\n"
+			"	.set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"	dextu	%1, %0, 56, 8\n"
+			"1:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dextu	%1, %0, 48, 8\n"
+			"2:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dextu	%1, %0, 40, 8\n"
+			"3:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dextu	%1, %0, 32, 8\n"
+			"4:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 24, 8\n"
+			"5:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 16, 8\n"
+			"6:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 8, 8\n"
+			"7:	sb	%1, 0(%2)\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	daddiu	%2, %2, -1\n"
+			"	dext	%1, %0, 0, 8\n"
+			"0:	sb	%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"	dextu	%1, %0, 56, 8\n"
+			"1:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dextu	%1, %0, 48, 8\n"
+			"2:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dextu	%1, %0, 40, 8\n"
+			"3:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dextu	%1, %0, 32, 8\n"
+			"4:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 24, 8\n"
+			"5:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 16, 8\n"
+			"6:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 8, 8\n"
+			"7:	sb	%1, 0(%2)\n"
+			"	daddiu	%2, %2, 1\n"
+			"	andi	%1, %2, 0x7\n"
+			"	beq	$0, %1, 9f\n"
+			"	dext	%1, %0, 0, 8\n"
+			"0:	sb	%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"	.insn\n"
+			"	.section        .fixup,\"ax\"\n"
+			"8:	li	%3,%4\n"
+			"	j	9b\n"
+			"	.previous\n"
+			"	.section        __ex_table,\"a\"\n"
+			"	.word	1b,8b\n"
+			"	.word	2b,8b\n"
+			"	.word	3b,8b\n"
+			"	.word	4b,8b\n"
+			"	.word	5b,8b\n"
+			"	.word	6b,8b\n"
+			"	.word	7b,8b\n"
+			"	.word	0b,8b\n"
+			"	.previous\n"
+			"	.set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+		break;
+
+	case sdr_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		rt = regs->regs[MIPSInst_RT(inst)];
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGSEGV;
+			break;
+		}
+		__asm__ __volatile__(
+			"       .set	push\n"
+			"       .set	reorder\n"
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			"       dext	%1, %0, 0, 8\n"
+			"1:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dext	%1, %0, 8, 8\n"
+			"2:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dext	%1, %0, 16, 8\n"
+			"3:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dext	%1, %0, 24, 8\n"
+			"4:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 32, 8\n"
+			"5:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 40, 8\n"
+			"6:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 48, 8\n"
+			"7:     sb	%1, 0(%2)\n"
+			"       daddiu	%2, %2, 1\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       dextu	%1, %0, 56, 8\n"
+			"0:     sb	%1, 0(%2)\n"
+#else /* !CONFIG_CPU_LITTLE_ENDIAN */
+			"       dext	%1, %0, 0, 8\n"
+			"1:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dext	%1, %0, 8, 8\n"
+			"2:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dext	%1, %0, 16, 8\n"
+			"3:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dext	%1, %0, 24, 8\n"
+			"4:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 32, 8\n"
+			"5:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 40, 8\n"
+			"6:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 48, 8\n"
+			"7:     sb	%1, 0(%2)\n"
+			"       andi	%1, %2, 0x7\n"
+			"       beq	$0, %1, 9f\n"
+			"       daddiu	%2, %2, -1\n"
+			"       dextu	%1, %0, 56, 8\n"
+			"0:     sb	%1, 0(%2)\n"
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+			"9:\n"
+			"       .insn\n"
+			"       .section        .fixup,\"ax\"\n"
+			"8:     li	%3,%4\n"
+			"       j	9b\n"
+			"       .previous\n"
+			"       .section        __ex_table,\"a\"\n"
+			"       .word	1b,8b\n"
+			"       .word	2b,8b\n"
+			"       .word	3b,8b\n"
+			"       .word	4b,8b\n"
+			"       .word	5b,8b\n"
+			"       .word	6b,8b\n"
+			"       .word	7b,8b\n"
+			"       .word	0b,8b\n"
+			"       .previous\n"
+			"       .set	pop\n"
+			: "+&r"(rt), "=&r"(rs),
+			  "+&r"(vaddr), "+&r"(err)
+			: "i"(SIGSEGV)
+			: "memory");
+
+		MIPS_R2_STATS(stores);
+
+		break;
+	case ll_op:
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x3) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_READ, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		__asm__ __volatile__(
+			"1:\n"
+			"ll	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word  1b, 3b\n"
+			".previous\n"
+			: "=&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV)
+			: "memory");
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+		MIPS_R2_STATS(llsc);
+
+		break;
+
+	case sc_op:
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x3) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		res = regs->regs[MIPSInst_RT(inst)];
+
+		__asm__ __volatile__(
+			"1:\n"
+			"sc	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word	1b, 3b\n"
+			".previous\n"
+			: "+&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV));
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+
+		MIPS_R2_STATS(llsc);
+
+		break;
+
+	case lld_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x7) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_READ, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		__asm__ __volatile__(
+			"1:\n"
+			"lld	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word  1b, 3b\n"
+			".previous\n"
+			: "=&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV)
+			: "memory");
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+
+		MIPS_R2_STATS(llsc);
+
+		break;
+
+	case scd_op:
+		if (config_enabled(CONFIG_32BIT)) {
+		    err = SIGILL;
+		    break;
+		}
+
+		vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
+		if (vaddr & 0x7) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+		if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+			current->thread.cp0_baduaddr = vaddr;
+			err = SIGBUS;
+			break;
+		}
+
+		if (!cpu_has_rw_llb) {
+			/*
+			 * An LL/SC block can't be safely emulated without
+			 * a Config5/LLB availability. So it's probably time to
+			 * kill our process before things get any worse. This is
+			 * because Config5/LLB allows us to use ERETNC so that
+			 * the LLAddr/LLB bit is not cleared when we return from
+			 * an exception. MIPS R2 LL/SC instructions trap with an
+			 * RI exception so once we emulate them here, we return
+			 * back to userland with ERETNC. That preserves the
+			 * LLAddr/LLB so the subsequent SC instruction will
+			 * succeed preserving the atomic semantics of the LL/SC
+			 * block. Without that, there is no safe way to emulate
+			 * an LL/SC block in MIPSR2 userland.
+			 */
+			pr_err("Can't emulate MIPSR2 LL/SC without Config5/LLB\n");
+			err = SIGKILL;
+			break;
+		}
+
+		res = regs->regs[MIPSInst_RT(inst)];
+
+		__asm__ __volatile__(
+			"1:\n"
+			"scd	%0, 0(%2)\n"
+			"2:\n"
+			".insn\n"
+			".section        .fixup,\"ax\"\n"
+			"3:\n"
+			"li	%1, %3\n"
+			"j	2b\n"
+			".previous\n"
+			".section        __ex_table,\"a\"\n"
+			".word	1b, 3b\n"
+			".previous\n"
+			: "+&r"(res), "+&r"(err)
+			: "r"(vaddr), "i"(SIGSEGV));
+
+		if (MIPSInst_RT(inst) && !err)
+			regs->regs[MIPSInst_RT(inst)] = res;
+
+		MIPS_R2_STATS(llsc);
+
+		break;
+	case pref_op:
+		/* skip it */
+		break;
+	default:
+		err = SIGILL;
+	}
+
+	/*
+	 * Lets not return to userland just yet. It's constly and
+	 * it's likely we have more R2 instructions to emulate
+	 */
+	if (!err && (pass++ < MIPS_R2_EMUL_TOTAL_PASS)) {
+		regs->cp0_cause &= ~CAUSEF_BD;
+		err = get_user(inst, (u32 __user *)regs->cp0_epc);
+		if (!err)
+			goto repeat;
+
+		if (err < 0)
+			err = SIGSEGV;
+	}
+
+	if (err && (err != SIGEMT)) {
+		regs->regs[31] = r31;
+		regs->cp0_epc = epc;
+	}
+
+	/* Likely a MIPS R6 compatible instruction */
+	if (pass && (err == SIGILL))
+		err = 0;
+
+	return err;
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static int mipsr2_stats_show(struct seq_file *s, void *unused)
+{
+
+	seq_printf(s, "Instruction\tTotal\tBDslot\n------------------------------\n");
+	seq_printf(s, "movs\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.movs),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.movs));
+	seq_printf(s, "hilo\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.hilo),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.hilo));
+	seq_printf(s, "muls\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.muls),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.muls));
+	seq_printf(s, "divs\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.divs),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.divs));
+	seq_printf(s, "dsps\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.dsps),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.dsps));
+	seq_printf(s, "bops\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.bops),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.bops));
+	seq_printf(s, "traps\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.traps),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.traps));
+	seq_printf(s, "fpus\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.fpus),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.fpus));
+	seq_printf(s, "loads\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.loads),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.loads));
+	seq_printf(s, "stores\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.stores),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.stores));
+	seq_printf(s, "llsc\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.llsc),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.llsc));
+	seq_printf(s, "dsemul\t\t%ld\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2emustats.dsemul),
+		   (unsigned long)__this_cpu_read(mipsr2bdemustats.dsemul));
+	seq_printf(s, "jr\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.jrs));
+	seq_printf(s, "bltzl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bltzl));
+	seq_printf(s, "bgezl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgezl));
+	seq_printf(s, "bltzll\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bltzll));
+	seq_printf(s, "bgezll\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgezll));
+	seq_printf(s, "bltzal\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bltzal));
+	seq_printf(s, "bgezal\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgezal));
+	seq_printf(s, "beql\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.beql));
+	seq_printf(s, "bnel\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bnel));
+	seq_printf(s, "blezl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.blezl));
+	seq_printf(s, "bgtzl\t\t%ld\n",
+		   (unsigned long)__this_cpu_read(mipsr2bremustats.bgtzl));
+
+	return 0;
+}
+
+static int mipsr2_stats_clear_show(struct seq_file *s, void *unused)
+{
+	mipsr2_stats_show(s, unused);
+
+	__this_cpu_write((mipsr2emustats).movs, 0);
+	__this_cpu_write((mipsr2bdemustats).movs, 0);
+	__this_cpu_write((mipsr2emustats).hilo, 0);
+	__this_cpu_write((mipsr2bdemustats).hilo, 0);
+	__this_cpu_write((mipsr2emustats).muls, 0);
+	__this_cpu_write((mipsr2bdemustats).muls, 0);
+	__this_cpu_write((mipsr2emustats).divs, 0);
+	__this_cpu_write((mipsr2bdemustats).divs, 0);
+	__this_cpu_write((mipsr2emustats).dsps, 0);
+	__this_cpu_write((mipsr2bdemustats).dsps, 0);
+	__this_cpu_write((mipsr2emustats).bops, 0);
+	__this_cpu_write((mipsr2bdemustats).bops, 0);
+	__this_cpu_write((mipsr2emustats).traps, 0);
+	__this_cpu_write((mipsr2bdemustats).traps, 0);
+	__this_cpu_write((mipsr2emustats).fpus, 0);
+	__this_cpu_write((mipsr2bdemustats).fpus, 0);
+	__this_cpu_write((mipsr2emustats).loads, 0);
+	__this_cpu_write((mipsr2bdemustats).loads, 0);
+	__this_cpu_write((mipsr2emustats).stores, 0);
+	__this_cpu_write((mipsr2bdemustats).stores, 0);
+	__this_cpu_write((mipsr2emustats).llsc, 0);
+	__this_cpu_write((mipsr2bdemustats).llsc, 0);
+	__this_cpu_write((mipsr2emustats).dsemul, 0);
+	__this_cpu_write((mipsr2bdemustats).dsemul, 0);
+	__this_cpu_write((mipsr2bremustats).jrs, 0);
+	__this_cpu_write((mipsr2bremustats).bltzl, 0);
+	__this_cpu_write((mipsr2bremustats).bgezl, 0);
+	__this_cpu_write((mipsr2bremustats).bltzll, 0);
+	__this_cpu_write((mipsr2bremustats).bgezll, 0);
+	__this_cpu_write((mipsr2bremustats).bltzal, 0);
+	__this_cpu_write((mipsr2bremustats).bgezal, 0);
+	__this_cpu_write((mipsr2bremustats).beql, 0);
+	__this_cpu_write((mipsr2bremustats).bnel, 0);
+	__this_cpu_write((mipsr2bremustats).blezl, 0);
+	__this_cpu_write((mipsr2bremustats).bgtzl, 0);
+
+	return 0;
+}
+
+static int mipsr2_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mipsr2_stats_show, inode->i_private);
+}
+
+static int mipsr2_stats_clear_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mipsr2_stats_clear_show, inode->i_private);
+}
+
+static const struct file_operations mipsr2_emul_fops = {
+	.open                   = mipsr2_stats_open,
+	.read			= seq_read,
+	.llseek			= seq_lseek,
+	.release		= single_release,
+};
+
+static const struct file_operations mipsr2_clear_fops = {
+	.open                   = mipsr2_stats_clear_open,
+	.read			= seq_read,
+	.llseek			= seq_lseek,
+	.release		= single_release,
+};
+
+
+static int __init mipsr2_init_debugfs(void)
+{
+	extern struct dentry	*mips_debugfs_dir;
+	struct dentry		*mipsr2_emul;
+
+	if (!mips_debugfs_dir)
+		return -ENODEV;
+
+	mipsr2_emul = debugfs_create_file("r2_emul_stats", S_IRUGO,
+					  mips_debugfs_dir, NULL,
+					  &mipsr2_emul_fops);
+	if (!mipsr2_emul)
+		return -ENOMEM;
+
+	mipsr2_emul = debugfs_create_file("r2_emul_stats_clear", S_IRUGO,
+					  mips_debugfs_dir, NULL,
+					  &mipsr2_clear_fops);
+	if (!mipsr2_emul)
+		return -ENOMEM;
+
+	return 0;
+}
+
+device_initcall(mipsr2_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 1a73c6c9e4b7..291af0b5c482 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -77,11 +77,13 @@ EXPORT_SYMBOL(__strnlen_kernel_asm);
 EXPORT_SYMBOL(__strnlen_user_nocheck_asm);
 EXPORT_SYMBOL(__strnlen_user_asm);
 
+#ifndef CONFIG_CPU_MIPSR6
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(csum_partial_copy_nocheck);
 EXPORT_SYMBOL(__csum_partial_copy_kernel);
 EXPORT_SYMBOL(__csum_partial_copy_to_user);
 EXPORT_SYMBOL(__csum_partial_copy_from_user);
+#endif
 
 EXPORT_SYMBOL(invalid_pte_table);
 #ifdef CONFIG_FUNCTION_TRACER
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 097fc8d14e42..130af7d26a9c 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -82,7 +82,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "]\n");
 	}
 
-	seq_printf(m, "isa\t\t\t: mips1");
+	seq_printf(m, "isa\t\t\t:"); 
+	if (cpu_has_mips_r1)
+		seq_printf(m, " mips1");
 	if (cpu_has_mips_2)
 		seq_printf(m, "%s", " mips2");
 	if (cpu_has_mips_3)
@@ -95,10 +97,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "%s", " mips32r1");
 	if (cpu_has_mips32r2)
 		seq_printf(m, "%s", " mips32r2");
+	if (cpu_has_mips32r6)
+		seq_printf(m, "%s", " mips32r6");
 	if (cpu_has_mips64r1)
 		seq_printf(m, "%s", " mips64r1");
 	if (cpu_has_mips64r2)
 		seq_printf(m, "%s", " mips64r2");
+	if (cpu_has_mips64r6)
+		seq_printf(m, "%s", " mips64r6");
 	seq_printf(m, "\n");
 
 	seq_printf(m, "ASEs implemented\t:");
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 4677b4c67da6..696d59e40fa4 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -581,6 +581,10 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	if ((value & PR_FP_MODE_FRE) && cpu_has_fpu && !cpu_has_fre)
 		return -EOPNOTSUPP;
 
+	/* FR = 0 not supported in MIPS R6 */
+	if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6)
+		return -EOPNOTSUPP;
+
 	/* Save FP & vector context, then disable FPU & MSA */
 	if (task->signal == current->signal)
 		lose_fpu(1);
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 6c160c67984c..676c5030a953 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -34,7 +34,7 @@
 	.endm
 
 	.set	noreorder
-	.set	arch=r4000
+	.set	MIPS_ISA_ARCH_LEVEL_RAW
 
 LEAF(_save_fp_context)
 	.set	push
@@ -42,7 +42,8 @@ LEAF(_save_fp_context)
 	cfc1	t1, fcr31
 	.set	pop
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	.set	push
 	SET_HARDFLOAT
 #ifdef CONFIG_CPU_MIPS32_R2
@@ -105,10 +106,12 @@ LEAF(_save_fp_context32)
 	SET_HARDFLOAT
 	cfc1	t1, fcr31
 
+#ifndef CONFIG_CPU_MIPS64_R6
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
 	bgez	t0, 1f			# skip storing odd if FR=0
 	 nop
+#endif
 
 	/* Store the 16 odd double precision registers */
 	EX      sdc1 $f1, SC32_FPREGS+8(a0)
@@ -163,7 +166,8 @@ LEAF(_save_fp_context32)
 LEAF(_restore_fp_context)
 	EX	lw t1, SC_FPC_CSR(a0)
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)  || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	.set	push
 	SET_HARDFLOAT
 #ifdef CONFIG_CPU_MIPS32_R2
@@ -223,10 +227,12 @@ LEAF(_restore_fp_context32)
 	SET_HARDFLOAT
 	EX	lw t1, SC32_FPC_CSR(a0)
 
+#ifndef CONFIG_CPU_MIPS64_R6
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
 	bgez	t0, 1f			# skip loading odd if FR=0
 	 nop
+#endif
 
 	EX      ldc1 $f1, SC32_FPREGS+8(a0)
 	EX      ldc1 $f3, SC32_FPREGS+24(a0)
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index 64591e671878..3b1a36f13a7d 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -115,7 +115,8 @@
  * Save a thread's fp context.
  */
 LEAF(_save_fp)
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	mfc0	t0, CP0_STATUS
 #endif
 	fpu_save_double a0 t0 t1		# clobbers t1
@@ -126,7 +127,8 @@ LEAF(_save_fp)
  * Restore a thread's fp context.
  */
 LEAF(_restore_fp)
-#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \
+		defined(CONFIG_CPU_MIPS32_R6)
 	mfc0	t0, CP0_STATUS
 #endif
 	fpu_restore_double a0 t0 t1		# clobbers t1
@@ -240,9 +242,9 @@ LEAF(_init_fpu)
 	mtc1	t1, $f30
 	mtc1	t1, $f31
 
-#ifdef CONFIG_CPU_MIPS32_R2
+#if defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6)
 	.set    push
-	.set    mips32r2
+	.set    MIPS_ISA_LEVEL_RAW
 	.set	fp=64
 	sll     t0, t0, 5			# is Status.FR set?
 	bgez    t0, 1f				# no: skip setting upper 32b
@@ -280,9 +282,9 @@ LEAF(_init_fpu)
 	mthc1   t1, $f30
 	mthc1   t1, $f31
 1:	.set    pop
-#endif /* CONFIG_CPU_MIPS32_R2 */
+#endif /* CONFIG_CPU_MIPS32_R2 || CONFIG_CPU_MIPS32_R6 */
 #else
-	.set	arch=r4000
+	.set	MIPS_ISA_ARCH_LEVEL_RAW
 	dmtc1	t1, $f0
 	dmtc1	t1, $f2
 	dmtc1	t1, $f4
diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c
index 67f2495def1c..d1168d7c31e8 100644
--- a/arch/mips/kernel/spram.c
+++ b/arch/mips/kernel/spram.c
@@ -208,6 +208,7 @@ void spram_config(void)
 	case CPU_INTERAPTIV:
 	case CPU_PROAPTIV:
 	case CPU_P5600:
+	case CPU_QEMU_GENERIC:
 		config0 = read_c0_config();
 		/* FIXME: addresses are Malta specific */
 		if (config0 & (1<<24)) {
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 604b558809c4..53a7ef9a8f32 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -136,7 +136,7 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new)
 		: "memory");
 	} else if (cpu_has_llsc) {
 		__asm__ __volatile__ (
-		"	.set	arch=r4000				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"	li	%[err], 0				\n"
 		"1:	ll	%[old], (%[addr])			\n"
 		"	move	%[tmp], %[new]				\n"
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d5fbfb51b9da..afa447e5e97f 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -46,6 +46,7 @@
 #include <asm/fpu.h>
 #include <asm/fpu_emulator.h>
 #include <asm/idle.h>
+#include <asm/mips-r2-to-r6-emul.h>
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
 #include <asm/module.h>
@@ -837,7 +838,7 @@ out:
 	exception_exit(prev_state);
 }
 
-static void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
+void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 	const char *str)
 {
 	siginfo_t info;
@@ -1027,7 +1028,34 @@ asmlinkage void do_ri(struct pt_regs *regs)
 	unsigned int opcode = 0;
 	int status = -1;
 
+	/*
+	 * Avoid any kernel code. Just emulate the R2 instruction
+	 * as quickly as possible.
+	 */
+	if (mipsr2_emulation && cpu_has_mips_r6 &&
+	    likely(user_mode(regs))) {
+		if (likely(get_user(opcode, epc) >= 0)) {
+			status = mipsr2_decoder(regs, opcode);
+			switch (status) {
+			case 0:
+			case SIGEMT:
+				task_thread_info(current)->r2_emul_return = 1;
+				return;
+			case SIGILL:
+				goto no_r2_instr;
+			default:
+				process_fpemu_return(status,
+						     &current->thread.cp0_baduaddr);
+				task_thread_info(current)->r2_emul_return = 1;
+				return;
+			}
+		}
+	}
+
+no_r2_instr:
+
 	prev_state = exception_enter();
+
 	if (notify_die(DIE_RI, "RI Fault", regs, 0, regs_to_trapnr(regs),
 		       SIGILL) == NOTIFY_STOP)
 		goto out;
@@ -1559,6 +1587,7 @@ static inline void parity_protection_init(void)
 	case CPU_INTERAPTIV:
 	case CPU_PROAPTIV:
 	case CPU_P5600:
+	case CPU_QEMU_GENERIC:
 		{
 #define ERRCTL_PE	0x80000000
 #define ERRCTL_L2P	0x00800000
@@ -1648,7 +1677,7 @@ asmlinkage void cache_parity_error(void)
 	printk("Decoded c0_cacheerr: %s cache fault in %s reference.\n",
 	       reg_val & (1<<30) ? "secondary" : "primary",
 	       reg_val & (1<<31) ? "data" : "insn");
-	if (cpu_has_mips_r2 &&
+	if ((cpu_has_mips_r2_r6) &&
 	    ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) {
 		pr_err("Error bits: %s%s%s%s%s%s%s%s\n",
 			reg_val & (1<<29) ? "ED " : "",
@@ -1688,7 +1717,7 @@ asmlinkage void do_ftlb(void)
 	unsigned int reg_val;
 
 	/* For the moment, report the problem and hang. */
-	if (cpu_has_mips_r2 &&
+	if ((cpu_has_mips_r2_r6) &&
 	    ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) {
 		pr_err("FTLB error exception, cp0_ecc=0x%08x:\n",
 		       read_c0_ecc());
@@ -1977,7 +2006,7 @@ static void configure_hwrena(void)
 {
 	unsigned int hwrena = cpu_hwrena_impl_bits;
 
-	if (cpu_has_mips_r2)
+	if (cpu_has_mips_r2_r6)
 		hwrena |= 0x0000000f;
 
 	if (!noulri && cpu_has_userlocal)
@@ -2021,7 +2050,7 @@ void per_cpu_trap_init(bool is_boot_cpu)
 	 *  o read IntCtl.IPTI to determine the timer interrupt
 	 *  o read IntCtl.IPPCI to determine the performance counter interrupt
 	 */
-	if (cpu_has_mips_r2) {
+	if (cpu_has_mips_r2_r6) {
 		cp0_compare_irq_shift = CAUSEB_TI - CAUSEB_IP;
 		cp0_compare_irq = (read_c0_intctl() >> INTCTLB_IPTI) & 7;
 		cp0_perfcount_irq = (read_c0_intctl() >> INTCTLB_IPPCI) & 7;
@@ -2112,7 +2141,7 @@ void __init trap_init(void)
 #else
         ebase = CKSEG0;
 #endif
-		if (cpu_has_mips_r2)
+		if (cpu_has_mips_r2_r6)
 			ebase += (read_c0_ebase() & 0x3ffff000);
 	}
 
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index e11906dff885..bbb69695a0a1 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -129,6 +129,7 @@ extern void show_registers(struct pt_regs *regs);
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
 
+#ifndef CONFIG_CPU_MIPSR6
 #define     LoadW(addr, value, res)   \
 		__asm__ __volatile__ (                      \
 			"1:\t"user_lwl("%0", "(%2)")"\n"    \
@@ -146,6 +147,39 @@ extern void show_registers(struct pt_regs *regs);
 			".previous"                         \
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
+#else
+/* MIPSR6 has no lwl instruction */
+#define     LoadW(addr, value, res) \
+		__asm__ __volatile__ (			    \
+			".set\tpush\n"			    \
+			".set\tnoat\n\t"		    \
+			"1:"user_lb("%0", "0(%2)")"\n\t"    \
+			"2:"user_lbu("$1", "1(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"3:"user_lbu("$1", "2(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"4:"user_lbu("$1", "3(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"li\t%1, 0\n"			    \
+			".set\tpop\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%1, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			".previous"			    \
+			: "=&r" (value), "=r" (res)	    \
+			: "r" (addr), "i" (-EFAULT));
+#endif /* CONFIG_CPU_MIPSR6 */
 
 #define     LoadHWU(addr, value, res) \
 		__asm__ __volatile__ (                      \
@@ -169,6 +203,7 @@ extern void show_registers(struct pt_regs *regs);
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
 
+#ifndef CONFIG_CPU_MIPSR6
 #define     LoadWU(addr, value, res)  \
 		__asm__ __volatile__ (                      \
 			"1:\t"user_lwl("%0", "(%2)")"\n"    \
@@ -206,6 +241,87 @@ extern void show_registers(struct pt_regs *regs);
 			".previous"                         \
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
+#else
+/* MIPSR6 has not lwl and ldl instructions */
+#define	    LoadWU(addr, value, res) \
+		__asm__ __volatile__ (			    \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:"user_lbu("%0", "0(%2)")"\n\t"   \
+			"2:"user_lbu("$1", "1(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"3:"user_lbu("$1", "2(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"4:"user_lbu("$1", "3(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"li\t%1, 0\n"			    \
+			".set\tpop\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%1, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			".previous"			    \
+			: "=&r" (value), "=r" (res)	    \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadDW(addr, value, res)  \
+		__asm__ __volatile__ (			    \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:lb\t%0, 0(%2)\n\t"    	    \
+			"2:lbu\t $1, 1(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"3:lbu\t$1, 2(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"4:lbu\t$1, 3(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"5:lbu\t$1, 4(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"6:lbu\t$1, 5(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"7:lbu\t$1, 6(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"8:lbu\t$1, 7(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"li\t%1, 0\n"			    \
+			".set\tpop\n\t"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%1, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			STR(PTR)"\t5b, 11b\n\t"		    \
+			STR(PTR)"\t6b, 11b\n\t"		    \
+			STR(PTR)"\t7b, 11b\n\t"		    \
+			STR(PTR)"\t8b, 11b\n\t"		    \
+			".previous"			    \
+			: "=&r" (value), "=r" (res)	    \
+			: "r" (addr), "i" (-EFAULT));
+#endif /* CONFIG_CPU_MIPSR6 */
+
 
 #define     StoreHW(addr, value, res) \
 		__asm__ __volatile__ (                      \
@@ -228,6 +344,7 @@ extern void show_registers(struct pt_regs *regs);
 			: "=r" (res)                        \
 			: "r" (value), "r" (addr), "i" (-EFAULT));
 
+#ifndef CONFIG_CPU_MIPSR6
 #define     StoreW(addr, value, res)  \
 		__asm__ __volatile__ (                      \
 			"1:\t"user_swl("%1", "(%2)")"\n"    \
@@ -263,9 +380,82 @@ extern void show_registers(struct pt_regs *regs);
 			".previous"                         \
 		: "=r" (res)                                \
 		: "r" (value), "r" (addr), "i" (-EFAULT));
-#endif
+#else
+/* MIPSR6 has no swl and sdl instructions */
+#define     StoreW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:"user_sb("%1", "3(%2)")"\n\t"    \
+			"srl\t$1, %1, 0x8\n\t"		    \
+			"2:"user_sb("$1", "2(%2)")"\n\t"    \
+			"srl\t$1, $1,  0x8\n\t"		    \
+			"3:"user_sb("$1", "1(%2)")"\n\t"    \
+			"srl\t$1, $1, 0x8\n\t"		    \
+			"4:"user_sb("$1", "0(%2)")"\n\t"    \
+			".set\tpop\n\t"			    \
+			"li\t%0, 0\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%0, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			".previous"			    \
+		: "=&r" (res)			    	    \
+		: "r" (value), "r" (addr), "i" (-EFAULT)    \
+		: "memory");
+
+#define     StoreDW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:sb\t%1, 7(%2)\n\t"    	    \
+			"dsrl\t$1, %1, 0x8\n\t"		    \
+			"2:sb\t$1, 6(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"3:sb\t$1, 5(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"4:sb\t$1, 4(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"5:sb\t$1, 3(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"6:sb\t$1, 2(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"7:sb\t$1, 1(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"8:sb\t$1, 0(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			".set\tpop\n\t"			    \
+			"li\t%0, 0\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%0, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			STR(PTR)"\t5b, 11b\n\t"		    \
+			STR(PTR)"\t6b, 11b\n\t"		    \
+			STR(PTR)"\t7b, 11b\n\t"		    \
+			STR(PTR)"\t8b, 11b\n\t"		    \
+			".previous"			    \
+		: "=&r" (res)			    	    \
+		: "r" (value), "r" (addr), "i" (-EFAULT)    \
+		: "memory");
+#endif /* CONFIG_CPU_MIPSR6 */
+
+#else /* __BIG_ENDIAN */
 
-#ifdef __LITTLE_ENDIAN
 #define     LoadHW(addr, value, res)  \
 		__asm__ __volatile__ (".set\tnoat\n"        \
 			"1:\t"user_lb("%0", "1(%2)")"\n"    \
@@ -286,6 +476,7 @@ extern void show_registers(struct pt_regs *regs);
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
 
+#ifndef CONFIG_CPU_MIPSR6
 #define     LoadW(addr, value, res)   \
 		__asm__ __volatile__ (                      \
 			"1:\t"user_lwl("%0", "3(%2)")"\n"   \
@@ -303,6 +494,40 @@ extern void show_registers(struct pt_regs *regs);
 			".previous"                         \
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
+#else
+/* MIPSR6 has no lwl instruction */
+#define     LoadW(addr, value, res) \
+		__asm__ __volatile__ (			    \
+			".set\tpush\n"			    \
+			".set\tnoat\n\t"		    \
+			"1:"user_lb("%0", "3(%2)")"\n\t"    \
+			"2:"user_lbu("$1", "2(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"3:"user_lbu("$1", "1(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"4:"user_lbu("$1", "0(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"li\t%1, 0\n"			    \
+			".set\tpop\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%1, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			".previous"			    \
+			: "=&r" (value), "=r" (res)	    \
+			: "r" (addr), "i" (-EFAULT));
+#endif /* CONFIG_CPU_MIPSR6 */
+
 
 #define     LoadHWU(addr, value, res) \
 		__asm__ __volatile__ (                      \
@@ -326,6 +551,7 @@ extern void show_registers(struct pt_regs *regs);
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
 
+#ifndef CONFIG_CPU_MIPSR6
 #define     LoadWU(addr, value, res)  \
 		__asm__ __volatile__ (                      \
 			"1:\t"user_lwl("%0", "3(%2)")"\n"   \
@@ -363,6 +589,86 @@ extern void show_registers(struct pt_regs *regs);
 			".previous"                         \
 			: "=&r" (value), "=r" (res)         \
 			: "r" (addr), "i" (-EFAULT));
+#else
+/* MIPSR6 has not lwl and ldl instructions */
+#define	    LoadWU(addr, value, res) \
+		__asm__ __volatile__ (			    \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:"user_lbu("%0", "3(%2)")"\n\t"   \
+			"2:"user_lbu("$1", "2(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"3:"user_lbu("$1", "1(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"4:"user_lbu("$1", "0(%2)")"\n\t"   \
+			"sll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"li\t%1, 0\n"			    \
+			".set\tpop\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%1, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			".previous"			    \
+			: "=&r" (value), "=r" (res)	    \
+			: "r" (addr), "i" (-EFAULT));
+
+#define     LoadDW(addr, value, res)  \
+		__asm__ __volatile__ (			    \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:lb\t%0, 7(%2)\n\t"    	    \
+			"2:lbu\t$1, 6(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"3:lbu\t$1, 5(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"4:lbu\t$1, 4(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"5:lbu\t$1, 3(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"6:lbu\t$1, 2(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"7:lbu\t$1, 1(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"8:lbu\t$1, 0(%2)\n\t"   	    \
+			"dsll\t%0, 0x8\n\t"		    \
+			"or\t%0, $1\n\t"		    \
+			"li\t%1, 0\n"			    \
+			".set\tpop\n\t"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%1, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			STR(PTR)"\t5b, 11b\n\t"		    \
+			STR(PTR)"\t6b, 11b\n\t"		    \
+			STR(PTR)"\t7b, 11b\n\t"		    \
+			STR(PTR)"\t8b, 11b\n\t"		    \
+			".previous"			    \
+			: "=&r" (value), "=r" (res)	    \
+			: "r" (addr), "i" (-EFAULT));
+#endif /* CONFIG_CPU_MIPSR6 */
 
 #define     StoreHW(addr, value, res) \
 		__asm__ __volatile__ (                      \
@@ -384,7 +690,7 @@ extern void show_registers(struct pt_regs *regs);
 			".previous"                         \
 			: "=r" (res)                        \
 			: "r" (value), "r" (addr), "i" (-EFAULT));
-
+#ifndef CONFIG_CPU_MIPSR6
 #define     StoreW(addr, value, res)  \
 		__asm__ __volatile__ (                      \
 			"1:\t"user_swl("%1", "3(%2)")"\n"   \
@@ -420,6 +726,79 @@ extern void show_registers(struct pt_regs *regs);
 			".previous"                         \
 		: "=r" (res)                                \
 		: "r" (value), "r" (addr), "i" (-EFAULT));
+#else
+/* MIPSR6 has no swl and sdl instructions */
+#define     StoreW(addr, value, res)  \
+		__asm__ __volatile__ (                      \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:"user_sb("%1", "0(%2)")"\n\t"    \
+			"srl\t$1, %1, 0x8\n\t"		    \
+			"2:"user_sb("$1", "1(%2)")"\n\t"    \
+			"srl\t$1, $1,  0x8\n\t"		    \
+			"3:"user_sb("$1", "2(%2)")"\n\t"    \
+			"srl\t$1, $1, 0x8\n\t"		    \
+			"4:"user_sb("$1", "3(%2)")"\n\t"    \
+			".set\tpop\n\t"			    \
+			"li\t%0, 0\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%0, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			".previous"			    \
+		: "=&r" (res)			    	    \
+		: "r" (value), "r" (addr), "i" (-EFAULT)    \
+		: "memory");
+
+#define     StoreDW(addr, value, res) \
+		__asm__ __volatile__ (                      \
+			".set\tpush\n\t"		    \
+			".set\tnoat\n\t"		    \
+			"1:sb\t%1, 0(%2)\n\t"    	    \
+			"dsrl\t$1, %1, 0x8\n\t"		    \
+			"2:sb\t$1, 1(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"3:sb\t$1, 2(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"4:sb\t$1, 3(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"5:sb\t$1, 4(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"6:sb\t$1, 5(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"7:sb\t$1, 6(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			"8:sb\t$1, 7(%2)\n\t"    	    \
+			"dsrl\t$1, $1, 0x8\n\t"		    \
+			".set\tpop\n\t"			    \
+			"li\t%0, 0\n"			    \
+			"10:\n\t"			    \
+			".insn\n\t"			    \
+			".section\t.fixup,\"ax\"\n\t"	    \
+			"11:\tli\t%0, %3\n\t"		    \
+			"j\t10b\n\t"			    \
+			".previous\n\t"			    \
+			".section\t__ex_table,\"a\"\n\t"    \
+			STR(PTR)"\t1b, 11b\n\t"		    \
+			STR(PTR)"\t2b, 11b\n\t"		    \
+			STR(PTR)"\t3b, 11b\n\t"		    \
+			STR(PTR)"\t4b, 11b\n\t"		    \
+			STR(PTR)"\t5b, 11b\n\t"		    \
+			STR(PTR)"\t6b, 11b\n\t"		    \
+			STR(PTR)"\t7b, 11b\n\t"		    \
+			STR(PTR)"\t8b, 11b\n\t"		    \
+			".previous"			    \
+		: "=&r" (res)			    	    \
+		: "r" (value), "r" (addr), "i" (-EFAULT)    \
+		: "memory");
+#endif /* CONFIG_CPU_MIPSR6 */
 #endif
 
 static void emulate_load_store_insn(struct pt_regs *regs,
@@ -703,10 +1082,13 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 			break;
 		return;
 
+#ifndef CONFIG_CPU_MIPSR6
 	/*
 	 * COP2 is available to implementor for application specific use.
 	 * It's up to applications to register a notifier chain and do
 	 * whatever they have to do, including possible sending of signals.
+	 *
+	 * This instruction has been reallocated in Release 6
 	 */
 	case lwc2_op:
 		cu2_notifier_call_chain(CU2_LWC2_OP, regs);
@@ -723,7 +1105,7 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	case sdc2_op:
 		cu2_notifier_call_chain(CU2_SDC2_OP, regs);
 		break;
-
+#endif
 	default:
 		/*
 		 * Pheeee...  We encountered an yet unknown instruction or
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index eeddc58802e1..1e9e900cd3c3 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -8,6 +8,7 @@ lib-y	+= bitops.o csum_partial.o delay.o memcpy.o memset.o \
 
 obj-y			+= iomap.o
 obj-$(CONFIG_PCI)	+= iomap-pci.o
+lib-$(CONFIG_GENERIC_CSUM)	:= $(filter-out csum_partial.o, $(lib-y))
 
 obj-$(CONFIG_CPU_GENERIC_DUMP_TLB) += dump_tlb.o
 obj-$(CONFIG_CPU_R3000)		+= r3k_dump_tlb.o
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index 5d3238af9b5c..9245e1705e69 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -293,9 +293,14 @@
 	 and	t0, src, ADDRMASK
 	PREFS(	0, 2*32(src) )
 	PREFD(	1, 2*32(dst) )
+#ifndef CONFIG_CPU_MIPSR6
 	bnez	t1, .Ldst_unaligned\@
 	 nop
 	bnez	t0, .Lsrc_unaligned_dst_aligned\@
+#else
+	or	t0, t0, t1
+	bnez	t0, .Lcopy_unaligned_bytes\@
+#endif
 	/*
 	 * use delay slot for fall-through
 	 * src and dst are aligned; need to compute rem
@@ -376,6 +381,7 @@
 	bne	rem, len, 1b
 	.set	noreorder
 
+#ifndef CONFIG_CPU_MIPSR6
 	/*
 	 * src and dst are aligned, need to copy rem bytes (rem < NBYTES)
 	 * A loop would do only a byte at a time with possible branch
@@ -477,6 +483,7 @@
 	bne	len, rem, 1b
 	.set	noreorder
 
+#endif /* !CONFIG_CPU_MIPSR6 */
 .Lcopy_bytes_checklen\@:
 	beqz	len, .Ldone\@
 	 nop
@@ -504,6 +511,22 @@
 .Ldone\@:
 	jr	ra
 	 nop
+
+#ifdef CONFIG_CPU_MIPSR6
+.Lcopy_unaligned_bytes\@:
+1:
+	COPY_BYTE(0)
+	COPY_BYTE(1)
+	COPY_BYTE(2)
+	COPY_BYTE(3)
+	COPY_BYTE(4)
+	COPY_BYTE(5)
+	COPY_BYTE(6)
+	COPY_BYTE(7)
+	ADD	src, src, 8
+	b	1b
+	 ADD	dst, dst, 8
+#endif /* CONFIG_CPU_MIPSR6 */
 	.if __memcpy == 1
 	END(memcpy)
 	.set __memcpy, 0
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index c8fe6b1968fb..b8e63fd00375 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -111,6 +111,7 @@
 	.set		at
 #endif
 
+#ifndef CONFIG_CPU_MIPSR6
 	R10KCBARRIER(0(ra))
 #ifdef __MIPSEB__
 	EX(LONG_S_L, a1, (a0), .Lfirst_fixup\@)	/* make word/dword aligned */
@@ -120,6 +121,30 @@
 	PTR_SUBU	a0, t0			/* long align ptr */
 	PTR_ADDU	a2, t0			/* correct size */
 
+#else /* CONFIG_CPU_MIPSR6 */
+#define STORE_BYTE(N)				\
+	EX(sb, a1, N(a0), .Lbyte_fixup\@);	\
+	beqz		t0, 0f;			\
+	PTR_ADDU	t0, 1;
+
+	PTR_ADDU	a2, t0			/* correct size */
+	PTR_ADDU	t0, 1
+	STORE_BYTE(0)
+	STORE_BYTE(1)
+#if LONGSIZE == 4
+	EX(sb, a1, 2(a0), .Lbyte_fixup\@)
+#else
+	STORE_BYTE(2)
+	STORE_BYTE(3)
+	STORE_BYTE(4)
+	STORE_BYTE(5)
+	EX(sb, a1, 6(a0), .Lbyte_fixup\@)
+#endif
+0:
+	ori		a0, STORMASK
+	xori		a0, STORMASK
+	PTR_ADDIU	a0, STORSIZE
+#endif /* CONFIG_CPU_MIPSR6 */
 1:	ori		t1, a2, 0x3f		/* # of full blocks */
 	xori		t1, 0x3f
 	beqz		t1, .Lmemset_partial\@	/* no block to fill */
@@ -159,6 +184,7 @@
 	andi		a2, STORMASK		/* At most one long to go */
 
 	beqz		a2, 1f
+#ifndef CONFIG_CPU_MIPSR6
 	PTR_ADDU	a0, a2			/* What's left */
 	R10KCBARRIER(0(ra))
 #ifdef __MIPSEB__
@@ -166,6 +192,22 @@
 #else
 	EX(LONG_S_L, a1, -1(a0), .Llast_fixup\@)
 #endif
+#else
+	PTR_SUBU	t0, $0, a2
+	PTR_ADDIU	t0, 1
+	STORE_BYTE(0)
+	STORE_BYTE(1)
+#if LONGSIZE == 4
+	EX(sb, a1, 2(a0), .Lbyte_fixup\@)
+#else
+	STORE_BYTE(2)
+	STORE_BYTE(3)
+	STORE_BYTE(4)
+	STORE_BYTE(5)
+	EX(sb, a1, 6(a0), .Lbyte_fixup\@)
+#endif
+0:
+#endif
 1:	jr		ra
 	move		a2, zero
 
@@ -186,6 +228,11 @@
 	.hidden __memset
 	.endif
 
+.Lbyte_fixup\@:
+	PTR_SUBU	a2, $0, t0
+	jr		ra
+	 PTR_ADDIU	a2, 1
+
 .Lfirst_fixup\@:
 	jr	ra
 	nop
diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c
index be777d9a3f85..272af8ac2425 100644
--- a/arch/mips/lib/mips-atomic.c
+++ b/arch/mips/lib/mips-atomic.c
@@ -15,7 +15,7 @@
 #include <linux/export.h>
 #include <linux/stringify.h>
 
-#ifndef CONFIG_CPU_MIPSR2
+#if !defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_CPU_MIPSR6)
 
 /*
  * For cli() we have to insert nops to make sure that the new value
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 9dfcd7fc1bc3..b30bf65c7d7d 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -48,6 +48,7 @@
 #include <asm/processor.h>
 #include <asm/fpu_emulator.h>
 #include <asm/fpu.h>
+#include <asm/mips-r2-to-r6-emul.h>
 
 #include "ieee754.h"
 
@@ -68,7 +69,7 @@ static int fpux_emu(struct pt_regs *,
 #define modeindex(v) ((v) & FPU_CSR_RM)
 
 /* convert condition code register number to csr bit */
-static const unsigned int fpucondbit[8] = {
+const unsigned int fpucondbit[8] = {
 	FPU_CSR_COND0,
 	FPU_CSR_COND1,
 	FPU_CSR_COND2,
@@ -448,6 +449,9 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.next_pc_inc;
 			/* Fall through */
 		case jr_op:
+			/* For R6, JR already emulated in jalr_op */
+			if (NO_R6EMU && insn.r_format.opcode == jr_op)
+				break;
 			*contpc = regs->regs[insn.r_format.rs];
 			return 1;
 		}
@@ -456,12 +460,18 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		switch (insn.i_format.rt) {
 		case bltzal_op:
 		case bltzall_op:
+			if (NO_R6EMU && (insn.i_format.rs ||
+			    insn.i_format.rt == bltzall_op))
+				break;
+
 			regs->regs[31] = regs->cp0_epc +
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 			/* Fall through */
-		case bltz_op:
 		case bltzl_op:
+			if (NO_R6EMU)
+				break;
+		case bltz_op:
 			if ((long)regs->regs[insn.i_format.rs] < 0)
 				*contpc = regs->cp0_epc +
 					dec_insn.pc_inc +
@@ -473,12 +483,18 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 			return 1;
 		case bgezal_op:
 		case bgezall_op:
+			if (NO_R6EMU && (insn.i_format.rs ||
+			    insn.i_format.rt == bgezall_op))
+				break;
+
 			regs->regs[31] = regs->cp0_epc +
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 			/* Fall through */
-		case bgez_op:
 		case bgezl_op:
+			if (NO_R6EMU)
+				break;
+		case bgez_op:
 			if ((long)regs->regs[insn.i_format.rs] >= 0)
 				*contpc = regs->cp0_epc +
 					dec_insn.pc_inc +
@@ -505,8 +521,10 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		/* Set microMIPS mode bit: XOR for jalx. */
 		*contpc ^= bit;
 		return 1;
-	case beq_op:
 	case beql_op:
+		if (NO_R6EMU)
+			break;
+	case beq_op:
 		if (regs->regs[insn.i_format.rs] ==
 		    regs->regs[insn.i_format.rt])
 			*contpc = regs->cp0_epc +
@@ -517,8 +535,10 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-	case bne_op:
 	case bnel_op:
+		if (NO_R6EMU)
+			break;
+	case bne_op:
 		if (regs->regs[insn.i_format.rs] !=
 		    regs->regs[insn.i_format.rt])
 			*contpc = regs->cp0_epc +
@@ -529,8 +549,34 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-	case blez_op:
 	case blezl_op:
+		if (NO_R6EMU)
+			break;
+	case blez_op:
+
+		/*
+		 * Compact branches for R6 for the
+		 * blez and blezl opcodes.
+		 * BLEZ  | rs = 0 | rt != 0  == BLEZALC
+		 * BLEZ  | rs = rt != 0      == BGEZALC
+		 * BLEZ  | rs != 0 | rt != 0 == BGEUC
+		 * BLEZL | rs = 0 | rt != 0  == BLEZC
+		 * BLEZL | rs = rt != 0      == BGEZC
+		 * BLEZL | rs != 0 | rt != 0 == BGEC
+		 *
+		 * For real BLEZ{,L}, rt is always 0.
+		 */
+		if (cpu_has_mips_r6 && insn.i_format.rt) {
+			if ((insn.i_format.opcode == blez_op) &&
+			    ((!insn.i_format.rs && insn.i_format.rt) ||
+			     (insn.i_format.rs == insn.i_format.rt)))
+				regs->regs[31] = regs->cp0_epc +
+					dec_insn.pc_inc;
+			*contpc = regs->cp0_epc + dec_insn.pc_inc +
+				dec_insn.next_pc_inc;
+
+			return 1;
+		}
 		if ((long)regs->regs[insn.i_format.rs] <= 0)
 			*contpc = regs->cp0_epc +
 				dec_insn.pc_inc +
@@ -540,8 +586,35 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-	case bgtz_op:
 	case bgtzl_op:
+		if (NO_R6EMU)
+			break;
+	case bgtz_op:
+		/*
+		 * Compact branches for R6 for the
+		 * bgtz and bgtzl opcodes.
+		 * BGTZ  | rs = 0 | rt != 0  == BGTZALC
+		 * BGTZ  | rs = rt != 0      == BLTZALC
+		 * BGTZ  | rs != 0 | rt != 0 == BLTUC
+		 * BGTZL | rs = 0 | rt != 0  == BGTZC
+		 * BGTZL | rs = rt != 0      == BLTZC
+		 * BGTZL | rs != 0 | rt != 0 == BLTC
+		 *
+		 * *ZALC varint for BGTZ &&& rt != 0
+		 * For real GTZ{,L}, rt is always 0.
+		 */
+		if (cpu_has_mips_r6 && insn.i_format.rt) {
+			if ((insn.i_format.opcode == blez_op) &&
+			    ((!insn.i_format.rs && insn.i_format.rt) ||
+			     (insn.i_format.rs == insn.i_format.rt)))
+				regs->regs[31] = regs->cp0_epc +
+					dec_insn.pc_inc;
+			*contpc = regs->cp0_epc + dec_insn.pc_inc +
+				dec_insn.next_pc_inc;
+
+			return 1;
+		}
+
 		if ((long)regs->regs[insn.i_format.rs] > 0)
 			*contpc = regs->cp0_epc +
 				dec_insn.pc_inc +
@@ -551,6 +624,16 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
+	case cbcond0_op:
+	case cbcond1_op:
+		if (!cpu_has_mips_r6)
+			break;
+		if (insn.i_format.rt && !insn.i_format.rs)
+			regs->regs[31] = regs->cp0_epc + 4;
+		*contpc = regs->cp0_epc + dec_insn.pc_inc +
+			dec_insn.next_pc_inc;
+
+		return 1;
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	case lwc2_op: /* This is bbit0 on Octeon */
 		if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0)
@@ -576,9 +659,73 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		else
 			*contpc = regs->cp0_epc + 8;
 		return 1;
+#else
+	case bc6_op:
+		/*
+		 * Only valid for MIPS R6 but we can still end up
+		 * here from a broken userland so just tell emulator
+		 * this is not a branch and let it break later on.
+		 */
+		if  (!cpu_has_mips_r6)
+			break;
+		*contpc = regs->cp0_epc + dec_insn.pc_inc +
+			dec_insn.next_pc_inc;
+
+		return 1;
+	case balc6_op:
+		if (!cpu_has_mips_r6)
+			break;
+		regs->regs[31] = regs->cp0_epc + 4;
+		*contpc = regs->cp0_epc + dec_insn.pc_inc +
+			dec_insn.next_pc_inc;
+
+		return 1;
+	case beqzcjic_op:
+		if (!cpu_has_mips_r6)
+			break;
+		*contpc = regs->cp0_epc + dec_insn.pc_inc +
+			dec_insn.next_pc_inc;
+
+		return 1;
+	case bnezcjialc_op:
+		if (!cpu_has_mips_r6)
+			break;
+		if (!insn.i_format.rs)
+			regs->regs[31] = regs->cp0_epc + 4;
+		*contpc = regs->cp0_epc + dec_insn.pc_inc +
+			dec_insn.next_pc_inc;
+
+		return 1;
 #endif
 	case cop0_op:
 	case cop1_op:
+		/* Need to check for R6 bc1nez and bc1eqz branches */
+		if (cpu_has_mips_r6 &&
+		    ((insn.i_format.rs == bc1eqz_op) ||
+		     (insn.i_format.rs == bc1nez_op))) {
+			bit = 0;
+			switch (insn.i_format.rs) {
+			case bc1eqz_op:
+				if (get_fpr32(&current->thread.fpu.fpr[insn.i_format.rt], 0) & 0x1)
+				    bit = 1;
+				break;
+			case bc1nez_op:
+				if (!(get_fpr32(&current->thread.fpu.fpr[insn.i_format.rt], 0) & 0x1))
+				    bit = 1;
+				break;
+			}
+			if (bit)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.i_format.simmediate << 2);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+
+			return 1;
+		}
+		/* R2/R6 compatible cop1 instruction. Fall through */
 	case cop2_op:
 	case cop1x_op:
 		if (insn.i_format.rs == bc_op) {
@@ -1414,14 +1561,14 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		 * achieve full IEEE-754 accuracy - however this emulator does.
 		 */
 		case frsqrt_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_sp_rsqrt;
 			goto scopuop;
 
 		case frecip_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_sp_recip;
@@ -1616,13 +1763,13 @@ copcsr:
 		 * achieve full IEEE-754 accuracy - however this emulator does.
 		 */
 		case frsqrt_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_dp_rsqrt;
 			goto dcopuop;
 		case frecip_op:
-			if (!cpu_has_mips_4_5_r2)
+			if (!cpu_has_mips_4_5_r2_r6)
 				return SIGILL;
 
 			handler.u = fpemu_dp_recip;
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index dd261df005c2..3f8059602765 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -794,7 +794,7 @@ static void local_r4k_flush_cache_sigtramp(void * arg)
 		__asm__ __volatile__ (
 			".set push\n\t"
 			".set noat\n\t"
-			".set mips3\n\t"
+			".set "MIPS_ISA_LEVEL"\n\t"
 #ifdef CONFIG_32BIT
 			"la	$at,1f\n\t"
 #endif
@@ -1255,6 +1255,7 @@ static void probe_pcache(void)
 	case CPU_P5600:
 	case CPU_PROAPTIV:
 	case CPU_M5150:
+	case CPU_QEMU_GENERIC:
 		if (!(read_c0_config7() & MIPS_CONF7_IAR) &&
 		    (c->icache.waysize > PAGE_SIZE))
 			c->icache.flags |= MIPS_CACHE_ALIASES;
@@ -1472,7 +1473,8 @@ static void setup_scache(void)
 
 	default:
 		if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 |
-				    MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)) {
+				    MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R1 |
+				    MIPS_CPU_ISA_M64R2 | MIPS_CPU_ISA_M64R6)) {
 #ifdef CONFIG_MIPS_CPU_SCACHE
 			if (mips_sc_init ()) {
 				scache_size = c->scache.ways * c->scache.sets * c->scache.linesz;
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index b611102e23b5..3f85f921801b 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -72,6 +72,20 @@ static struct uasm_reloc relocs[5];
 #define cpu_is_r4600_v1_x()	((read_c0_prid() & 0xfffffff0) == 0x00002010)
 #define cpu_is_r4600_v2_x()	((read_c0_prid() & 0xfffffff0) == 0x00002020)
 
+/*
+ * R6 has a limited offset of the pref instruction.
+ * Skip it if the offset is more than 9 bits.
+ */
+#define _uasm_i_pref(a, b, c, d)		\
+do {						\
+	if (cpu_has_mips_r6) {			\
+		if (c <= 0xff && c >= -0x100)	\
+			uasm_i_pref(a, b, c, d);\
+	} else {				\
+		uasm_i_pref(a, b, c, d);	\
+	}					\
+} while(0)
+
 static int pref_bias_clear_store;
 static int pref_bias_copy_load;
 static int pref_bias_copy_store;
@@ -178,7 +192,15 @@ static void set_prefetch_parameters(void)
 			pref_bias_copy_load = 256;
 			pref_bias_copy_store = 128;
 			pref_src_mode = Pref_LoadStreamed;
-			pref_dst_mode = Pref_PrepareForStore;
+			if (cpu_has_mips_r6)
+				/*
+				 * Bit 30 (Pref_PrepareForStore) has been
+				 * removed from MIPS R6. Use bit 5
+				 * (Pref_StoreStreamed).
+				 */
+				pref_dst_mode = Pref_StoreStreamed;
+			else
+				pref_dst_mode = Pref_PrepareForStore;
 			break;
 		}
 	} else {
@@ -214,7 +236,7 @@ static inline void build_clear_pref(u32 **buf, int off)
 		return;
 
 	if (pref_bias_clear_store) {
-		uasm_i_pref(buf, pref_dst_mode, pref_bias_clear_store + off,
+		_uasm_i_pref(buf, pref_dst_mode, pref_bias_clear_store + off,
 			    A0);
 	} else if (cache_line_size == (half_clear_loop_size << 1)) {
 		if (cpu_has_cache_cdex_s) {
@@ -357,7 +379,7 @@ static inline void build_copy_load_pref(u32 **buf, int off)
 		return;
 
 	if (pref_bias_copy_load)
-		uasm_i_pref(buf, pref_src_mode, pref_bias_copy_load + off, A1);
+		_uasm_i_pref(buf, pref_src_mode, pref_bias_copy_load + off, A1);
 }
 
 static inline void build_copy_store_pref(u32 **buf, int off)
@@ -366,7 +388,7 @@ static inline void build_copy_store_pref(u32 **buf, int off)
 		return;
 
 	if (pref_bias_copy_store) {
-		uasm_i_pref(buf, pref_dst_mode, pref_bias_copy_store + off,
+		_uasm_i_pref(buf, pref_dst_mode, pref_bias_copy_store + off,
 			    A0);
 	} else if (cache_line_size == (half_copy_loop_size << 1)) {
 		if (cpu_has_cache_cdex_s) {
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 99eb8fabab60..4ceafd13870c 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -81,6 +81,7 @@ static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 	case CPU_PROAPTIV:
 	case CPU_P5600:
 	case CPU_BMIPS5000:
+	case CPU_QEMU_GENERIC:
 		if (config2 & (1 << 12))
 			return 0;
 	}
@@ -104,7 +105,8 @@ static inline int __init mips_sc_probe(void)
 
 	/* Ignore anything but MIPSxx processors */
 	if (!(c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 |
-			      MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2)))
+			      MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R1 |
+			      MIPS_CPU_ISA_M64R2 | MIPS_CPU_ISA_M64R6)))
 		return 0;
 
 	/* Does this MIPS32/MIPS64 CPU have a config2 register? */
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 3978a3d81366..d75ff73a2012 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -501,7 +501,7 @@ static void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 	case tlb_indexed: tlbw = uasm_i_tlbwi; break;
 	}
 
-	if (cpu_has_mips_r2) {
+	if (cpu_has_mips_r2_exec_hazard) {
 		/*
 		 * The architecture spec says an ehb is required here,
 		 * but a number of cores do not have the hazard and
@@ -514,6 +514,7 @@ static void build_tlb_write_entry(u32 **p, struct uasm_label **l,
 		case CPU_PROAPTIV:
 		case CPU_P5600:
 		case CPU_M5150:
+		case CPU_QEMU_GENERIC:
 			break;
 
 		default:
@@ -1952,7 +1953,7 @@ static void build_r4000_tlb_load_handler(void)
 
 		switch (current_cpu_type()) {
 		default:
-			if (cpu_has_mips_r2) {
+			if (cpu_has_mips_r2_exec_hazard) {
 				uasm_i_ehb(&p);
 
 		case CPU_CAVIUM_OCTEON:
@@ -2019,7 +2020,7 @@ static void build_r4000_tlb_load_handler(void)
 
 		switch (current_cpu_type()) {
 		default:
-			if (cpu_has_mips_r2) {
+			if (cpu_has_mips_r2_exec_hazard) {
 				uasm_i_ehb(&p);
 
 		case CPU_CAVIUM_OCTEON:
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 8e02291cfc0c..855fc8a6a3c5 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -38,6 +38,14 @@
 	 | (e) << RE_SH						\
 	 | (f) << FUNC_SH)
 
+/* This macro sets the non-variable bits of an R6 instruction. */
+#define M6(a, b, c, d, e)					\
+	((a) << OP_SH						\
+	 | (b) << RS_SH						\
+	 | (c) << RT_SH						\
+	 | (d) << SIMM9_SH					\
+	 | (e) << FUNC_SH)
+
 /* Define these when we are not the ISA the kernel is being compiled with. */
 #ifdef CONFIG_CPU_MICROMIPS
 #define CL_uasm_i_b(buf, off) ISAOPC(_beq)(buf, 0, 0, off)
@@ -62,7 +70,11 @@ static struct insn insn_table[] = {
 	{ insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM },
 	{ insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM },
 	{ insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
+#ifndef CONFIG_CPU_MIPSR6
 	{ insn_cache,  M(cache_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+#else
+	{ insn_cache,  M6(cache_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
+#endif
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
 	{ insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE },
@@ -85,13 +97,22 @@ static struct insn insn_table[] = {
 	{ insn_jal,  M(jal_op, 0, 0, 0, 0, 0),	JIMM },
 	{ insn_jalr,  M(spec_op, 0, 0, 0, 0, jalr_op), RS | RD },
 	{ insn_j,  M(j_op, 0, 0, 0, 0, 0),  JIMM },
+#ifndef CONFIG_CPU_MIPSR6
 	{ insn_jr,  M(spec_op, 0, 0, 0, 0, jr_op),  RS },
+#else
+	{ insn_jr,  M(spec_op, 0, 0, 0, 0, jalr_op),  RS },
+#endif
 	{ insn_lb, M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_ld,  M(ld_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD },
 	{ insn_lh,  M(lh_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+#ifndef CONFIG_CPU_MIPSR6
 	{ insn_lld,  M(lld_op, 0, 0, 0, 0, 0),	RS | RT | SIMM },
 	{ insn_ll,  M(ll_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+#else
+	{ insn_lld,  M6(spec3_op, 0, 0, 0, lld6_op),  RS | RT | SIMM9 },
+	{ insn_ll,  M6(spec3_op, 0, 0, 0, ll6_op),  RS | RT | SIMM9 },
+#endif
 	{ insn_lui,  M(lui_op, 0, 0, 0, 0, 0),	RT | SIMM },
 	{ insn_lw,  M(lw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD },
@@ -104,11 +125,20 @@ static struct insn insn_table[] = {
 	{ insn_mul, M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD},
 	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),	RS | RT | UIMM },
 	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
+#ifndef CONFIG_CPU_MIPSR6
 	{ insn_pref,  M(pref_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+#else
+	{ insn_pref,  M6(spec3_op, 0, 0, 0, pref6_op),  RS | RT | SIMM9 },
+#endif
 	{ insn_rfe,  M(cop0_op, cop_op, 0, 0, 0, rfe_op),  0 },
 	{ insn_rotr,  M(spec_op, 1, 0, 0, 0, srl_op),  RT | RD | RE },
+#ifndef CONFIG_CPU_MIPSR6
 	{ insn_scd,  M(scd_op, 0, 0, 0, 0, 0),	RS | RT | SIMM },
 	{ insn_sc,  M(sc_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+#else
+	{ insn_scd,  M6(spec3_op, 0, 0, 0, scd6_op),  RS | RT | SIMM9 },
+	{ insn_sc,  M6(spec3_op, 0, 0, 0, sc6_op),  RS | RT | SIMM9 },
+#endif
 	{ insn_sd,  M(sd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_sll,  M(spec_op, 0, 0, 0, 0, sll_op),  RT | RD | RE },
 	{ insn_sllv,  M(spec_op, 0, 0, 0, 0, sllv_op),  RS | RT | RD },
@@ -198,6 +228,8 @@ static void build_insn(u32 **buf, enum opcode opc, ...)
 		op |= build_set(va_arg(ap, u32));
 	if (ip->fields & SCIMM)
 		op |= build_scimm(va_arg(ap, u32));
+	if (ip->fields & SIMM9)
+		op |= build_scimm9(va_arg(ap, u32));
 	va_end(ap);
 
 	**buf = op;
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index 4adf30284813..f86d293463a6 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -24,7 +24,8 @@ enum fields {
 	JIMM = 0x080,
 	FUNC = 0x100,
 	SET = 0x200,
-	SCIMM = 0x400
+	SCIMM = 0x400,
+	SIMM9 = 0x800,
 };
 
 #define OP_MASK		0x3f
@@ -41,6 +42,8 @@ enum fields {
 #define FUNC_SH		0
 #define SET_MASK	0x7
 #define SET_SH		0
+#define SIMM9_SH	7
+#define SIMM9_MASK	0x1ff
 
 enum opcode {
 	insn_invalid,
@@ -116,6 +119,14 @@ static inline u32 build_scimm(u32 arg)
 	return (arg & SCIMM_MASK) << SCIMM_SH;
 }
 
+static inline u32 build_scimm9(s32 arg)
+{
+	WARN((arg > 0xff || arg < -0x100),
+	       KERN_WARNING "Micro-assembler field overflow\n");
+
+	return (arg & SIMM9_MASK) << SIMM9_SH;
+}
+
 static inline u32 build_func(u32 arg)
 {
 	WARN(arg & ~FUNC_MASK, KERN_WARNING "Micro-assembler field overflow\n");