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

Pull MIPS updates from Ralf Baechle:
 - Support for Imgtec's Aptiv family of MIPS cores.
 - Improved detection of BCM47xx configurations.
 - Fix hiberation for certain configurations.
 - Add support for the Chinese Loongson 3 CPU, a MIPS64 R2 core and
   systems.
 - Detection and support for the MIPS P5600 core.
 - A few more random fixes that didn't make 3.14.
 - Support for the EVA Extended Virtual Addressing
 - Switch Alchemy to the platform PATA driver
 - Complete unification of Alchemy support
 - Allow availability of I/O cache coherency to be runtime detected
 - Improvments to multiprocessing support for Imgtec platforms
 - A few microoptimizations
 - Cleanups of FPU support
 - Paul Gortmaker's fixes for the init stuff
 - Support for seccomp

* 'mips-for-linux-next' of git://git.linux-mips.org/pub/scm/ralf/upstream-sfr: (165 commits)
  MIPS: CPC: Use __raw_ memory access functions
  MIPS: CM: use __raw_ memory access functions
  MIPS: Fix warning when including smp-ops.h with CONFIG_SMP=n
  MIPS: Malta: GIC IPIs may be used without MT
  MIPS: smp-mt: Use common GIC IPI implementation
  MIPS: smp-cmp: Remove incorrect core number probe
  MIPS: Fix gigaton of warning building with microMIPS.
  MIPS: Fix core number detection for MT cores
  MIPS: MT: core_nvpes function to retrieve VPE count
  MIPS: Provide empty mips_mt_set_cpuoptions when CONFIG_MIPS_MT=n
  MIPS: Lasat: Replace del_timer by del_timer_sync
  MIPS: Malta: Setup PM I/O region on boot
  MIPS: Loongson: Add a Loongson-3 default config file
  MIPS: Loongson 3: Add CPU hotplug support
  MIPS: Loongson 3: Add Loongson-3 SMP support
  MIPS: Loongson: Add Loongson-3 Kconfig options
  MIPS: Loongson: Add swiotlb to support All-Memory DMA
  MIPS: Loongson 3: Add serial port support
  MIPS: Loongson 3: Add IRQ init and dispatch support
  MIPS: Loongson 3: Add HT-linked PCI support
  ...

6 files changed, 638 insertions, 318 deletions

diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index a6adffbb4e5f..2e4825e48388 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -8,6 +8,7 @@
  * Copyright (C) 1998, 1999 Ralf Baechle
  * Copyright (C) 1999 Silicon Graphics, Inc.
  * Copyright (C) 2007  Maciej W. Rozycki
+ * Copyright (C) 2014 Imagination Technologies Ltd.
  */
 #include <linux/errno.h>
 #include <asm/asm.h>
@@ -296,7 +297,7 @@ LEAF(csum_partial)
  * checksum and copy routines based on memcpy.S
  *
  *	csum_partial_copy_nocheck(src, dst, len, sum)
- *	__csum_partial_copy_user(src, dst, len, sum, errp)
+ *	__csum_partial_copy_kernel(src, dst, len, sum, errp)
  *
  * See "Spec" in memcpy.S for details.	Unlike __copy_user, all
  * function in this file use the standard calling convention.
@@ -327,20 +328,58 @@ LEAF(csum_partial)
  * These handlers do not need to overwrite any data.
  */
 
-#define EXC(inst_reg,addr,handler)		\
-9:	inst_reg, addr;				\
-	.section __ex_table,"a";		\
-	PTR	9b, handler;			\
-	.previous
+/* Instruction type */
+#define LD_INSN 1
+#define ST_INSN 2
+#define LEGACY_MODE 1
+#define EVA_MODE    2
+#define USEROP   1
+#define KERNELOP 2
+
+/*
+ * Wrapper to add an entry in the exception table
+ * in case the insn causes a memory exception.
+ * Arguments:
+ * insn    : Load/store instruction
+ * type    : Instruction type
+ * reg     : Register
+ * addr    : Address
+ * handler : Exception handler
+ */
+#define EXC(insn, type, reg, addr, handler)	\
+	.if \mode == LEGACY_MODE;		\
+9:		insn reg, addr;			\
+		.section __ex_table,"a";	\
+		PTR	9b, handler;		\
+		.previous;			\
+	/* This is enabled in EVA mode */	\
+	.else;					\
+		/* If loading from user or storing to user */	\
+		.if ((\from == USEROP) && (type == LD_INSN)) || \
+		    ((\to == USEROP) && (type == ST_INSN));	\
+9:			__BUILD_EVA_INSN(insn##e, reg, addr);	\
+			.section __ex_table,"a";		\
+			PTR	9b, handler;			\
+			.previous;				\
+		.else;						\
+			/* EVA without exception */		\
+			insn reg, addr;				\
+		.endif;						\
+	.endif
+
+#undef LOAD
 
 #ifdef USE_DOUBLE
 
-#define LOAD   ld
-#define LOADL  ldl
-#define LOADR  ldr
-#define STOREL sdl
-#define STORER sdr
-#define STORE  sd
+#define LOADK	ld /* No exception */
+#define LOAD(reg, addr, handler)	EXC(ld, LD_INSN, reg, addr, handler)
+#define LOADBU(reg, addr, handler)	EXC(lbu, LD_INSN, reg, addr, handler)
+#define LOADL(reg, addr, handler)	EXC(ldl, LD_INSN, reg, addr, handler)
+#define LOADR(reg, addr, handler)	EXC(ldr, LD_INSN, reg, addr, handler)
+#define STOREB(reg, addr, handler)	EXC(sb, ST_INSN, reg, addr, handler)
+#define STOREL(reg, addr, handler)	EXC(sdl, ST_INSN, reg, addr, handler)
+#define STORER(reg, addr, handler)	EXC(sdr, ST_INSN, reg, addr, handler)
+#define STORE(reg, addr, handler)	EXC(sd, ST_INSN, reg, addr, handler)
 #define ADD    daddu
 #define SUB    dsubu
 #define SRL    dsrl
@@ -352,12 +391,15 @@ LEAF(csum_partial)
 
 #else
 
-#define LOAD   lw
-#define LOADL  lwl
-#define LOADR  lwr
-#define STOREL swl
-#define STORER swr
-#define STORE  sw
+#define LOADK	lw /* No exception */
+#define LOAD(reg, addr, handler)	EXC(lw, LD_INSN, reg, addr, handler)
+#define LOADBU(reg, addr, handler)	EXC(lbu, LD_INSN, reg, addr, handler)
+#define LOADL(reg, addr, handler)	EXC(lwl, LD_INSN, reg, addr, handler)
+#define LOADR(reg, addr, handler)	EXC(lwr, LD_INSN, reg, addr, handler)
+#define STOREB(reg, addr, handler)	EXC(sb, ST_INSN, reg, addr, handler)
+#define STOREL(reg, addr, handler)	EXC(swl, ST_INSN, reg, addr, handler)
+#define STORER(reg, addr, handler)	EXC(swr, ST_INSN, reg, addr, handler)
+#define STORE(reg, addr, handler)	EXC(sw, ST_INSN, reg, addr, handler)
 #define ADD    addu
 #define SUB    subu
 #define SRL    srl
@@ -396,14 +438,20 @@ LEAF(csum_partial)
 	.set	at=v1
 #endif
 
-LEAF(__csum_partial_copy_user)
+	.macro __BUILD_CSUM_PARTIAL_COPY_USER mode, from, to, __nocheck
+
 	PTR_ADDU	AT, src, len	/* See (1) above. */
+	/* initialize __nocheck if this the first time we execute this
+	 * macro
+	 */
 #ifdef CONFIG_64BIT
 	move	errptr, a4
 #else
 	lw	errptr, 16(sp)
 #endif
-FEXPORT(csum_partial_copy_nocheck)
+	.if \__nocheck == 1
+	FEXPORT(csum_partial_copy_nocheck)
+	.endif
 	move	sum, zero
 	move	odd, zero
 	/*
@@ -419,48 +467,48 @@ FEXPORT(csum_partial_copy_nocheck)
 	 */
 	sltu	t2, len, NBYTES
 	and	t1, dst, ADDRMASK
-	bnez	t2, .Lcopy_bytes_checklen
+	bnez	t2, .Lcopy_bytes_checklen\@
 	 and	t0, src, ADDRMASK
 	andi	odd, dst, 0x1			/* odd buffer? */
-	bnez	t1, .Ldst_unaligned
+	bnez	t1, .Ldst_unaligned\@
 	 nop
-	bnez	t0, .Lsrc_unaligned_dst_aligned
+	bnez	t0, .Lsrc_unaligned_dst_aligned\@
 	/*
 	 * use delay slot for fall-through
 	 * src and dst are aligned; need to compute rem
 	 */
-.Lboth_aligned:
+.Lboth_aligned\@:
 	 SRL	t0, len, LOG_NBYTES+3	 # +3 for 8 units/iter
-	beqz	t0, .Lcleanup_both_aligned # len < 8*NBYTES
+	beqz	t0, .Lcleanup_both_aligned\@ # len < 8*NBYTES
 	 nop
 	SUB	len, 8*NBYTES		# subtract here for bgez loop
 	.align	4
 1:
-EXC(	LOAD	t0, UNIT(0)(src),	.Ll_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	.Ll_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	.Ll_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	.Ll_exc_copy)
-EXC(	LOAD	t4, UNIT(4)(src),	.Ll_exc_copy)
-EXC(	LOAD	t5, UNIT(5)(src),	.Ll_exc_copy)
-EXC(	LOAD	t6, UNIT(6)(src),	.Ll_exc_copy)
-EXC(	LOAD	t7, UNIT(7)(src),	.Ll_exc_copy)
+	LOAD(t0, UNIT(0)(src), .Ll_exc\@)
+	LOAD(t1, UNIT(1)(src), .Ll_exc_copy\@)
+	LOAD(t2, UNIT(2)(src), .Ll_exc_copy\@)
+	LOAD(t3, UNIT(3)(src), .Ll_exc_copy\@)
+	LOAD(t4, UNIT(4)(src), .Ll_exc_copy\@)
+	LOAD(t5, UNIT(5)(src), .Ll_exc_copy\@)
+	LOAD(t6, UNIT(6)(src), .Ll_exc_copy\@)
+	LOAD(t7, UNIT(7)(src), .Ll_exc_copy\@)
 	SUB	len, len, 8*NBYTES
 	ADD	src, src, 8*NBYTES
-EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc)
+	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
 	ADDC(sum, t0)
-EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc)
+	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
 	ADDC(sum, t1)
-EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc)
+	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
 	ADDC(sum, t2)
-EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc)
+	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
 	ADDC(sum, t3)
-EXC(	STORE	t4, UNIT(4)(dst),	.Ls_exc)
+	STORE(t4, UNIT(4)(dst),	.Ls_exc\@)
 	ADDC(sum, t4)
-EXC(	STORE	t5, UNIT(5)(dst),	.Ls_exc)
+	STORE(t5, UNIT(5)(dst),	.Ls_exc\@)
 	ADDC(sum, t5)
-EXC(	STORE	t6, UNIT(6)(dst),	.Ls_exc)
+	STORE(t6, UNIT(6)(dst),	.Ls_exc\@)
 	ADDC(sum, t6)
-EXC(	STORE	t7, UNIT(7)(dst),	.Ls_exc)
+	STORE(t7, UNIT(7)(dst),	.Ls_exc\@)
 	ADDC(sum, t7)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 8*NBYTES
@@ -471,44 +519,44 @@ EXC(	STORE	t7, UNIT(7)(dst),	.Ls_exc)
 	/*
 	 * len == the number of bytes left to copy < 8*NBYTES
 	 */
-.Lcleanup_both_aligned:
+.Lcleanup_both_aligned\@:
 #define rem t7
-	beqz	len, .Ldone
+	beqz	len, .Ldone\@
 	 sltu	t0, len, 4*NBYTES
-	bnez	t0, .Lless_than_4units
+	bnez	t0, .Lless_than_4units\@
 	 and	rem, len, (NBYTES-1)	# rem = len % NBYTES
 	/*
 	 * len >= 4*NBYTES
 	 */
-EXC(	LOAD	t0, UNIT(0)(src),	.Ll_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	.Ll_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	.Ll_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	.Ll_exc_copy)
+	LOAD(t0, UNIT(0)(src), .Ll_exc\@)
+	LOAD(t1, UNIT(1)(src), .Ll_exc_copy\@)
+	LOAD(t2, UNIT(2)(src), .Ll_exc_copy\@)
+	LOAD(t3, UNIT(3)(src), .Ll_exc_copy\@)
 	SUB	len, len, 4*NBYTES
 	ADD	src, src, 4*NBYTES
-EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc)
+	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
 	ADDC(sum, t0)
-EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc)
+	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
 	ADDC(sum, t1)
-EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc)
+	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
 	ADDC(sum, t2)
-EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc)
+	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
 	ADDC(sum, t3)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
-	beqz	len, .Ldone
+	beqz	len, .Ldone\@
 	.set	noreorder
-.Lless_than_4units:
+.Lless_than_4units\@:
 	/*
 	 * rem = len % NBYTES
 	 */
-	beq	rem, len, .Lcopy_bytes
+	beq	rem, len, .Lcopy_bytes\@
 	 nop
 1:
-EXC(	LOAD	t0, 0(src),		.Ll_exc)
+	LOAD(t0, 0(src), .Ll_exc\@)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		.Ls_exc)
+	STORE(t0, 0(dst), .Ls_exc\@)
 	ADDC(sum, t0)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, NBYTES
@@ -527,20 +575,20 @@ EXC(	STORE	t0, 0(dst),		.Ls_exc)
 	 * more instruction-level parallelism.
 	 */
 #define bits t2
-	beqz	len, .Ldone
+	beqz	len, .Ldone\@
 	 ADD	t1, dst, len	# t1 is just past last byte of dst
 	li	bits, 8*NBYTES
 	SLL	rem, len, 3	# rem = number of bits to keep
-EXC(	LOAD	t0, 0(src),		.Ll_exc)
+	LOAD(t0, 0(src), .Ll_exc\@)
 	SUB	bits, bits, rem # bits = number of bits to discard
 	SHIFT_DISCARD t0, t0, bits
-EXC(	STREST	t0, -1(t1),		.Ls_exc)
+	STREST(t0, -1(t1), .Ls_exc\@)
 	SHIFT_DISCARD_REVERT t0, t0, bits
 	.set reorder
 	ADDC(sum, t0)
-	b	.Ldone
+	b	.Ldone\@
 	.set noreorder
-.Ldst_unaligned:
+.Ldst_unaligned\@:
 	/*
 	 * dst is unaligned
 	 * t0 = src & ADDRMASK
@@ -551,25 +599,25 @@ EXC(	STREST	t0, -1(t1),		.Ls_exc)
 	 * Set match = (src and dst have same alignment)
 	 */
 #define match rem
-EXC(	LDFIRST t3, FIRST(0)(src),	.Ll_exc)
+	LDFIRST(t3, FIRST(0)(src), .Ll_exc\@)
 	ADD	t2, zero, NBYTES
-EXC(	LDREST	t3, REST(0)(src),	.Ll_exc_copy)
+	LDREST(t3, REST(0)(src), .Ll_exc_copy\@)
 	SUB	t2, t2, t1	# t2 = number of bytes copied
 	xor	match, t0, t1
-EXC(	STFIRST t3, FIRST(0)(dst),	.Ls_exc)
+	STFIRST(t3, FIRST(0)(dst), .Ls_exc\@)
 	SLL	t4, t1, 3		# t4 = number of bits to discard
 	SHIFT_DISCARD t3, t3, t4
 	/* no SHIFT_DISCARD_REVERT to handle odd buffer properly */
 	ADDC(sum, t3)
-	beq	len, t2, .Ldone
+	beq	len, t2, .Ldone\@
 	 SUB	len, len, t2
 	ADD	dst, dst, t2
-	beqz	match, .Lboth_aligned
+	beqz	match, .Lboth_aligned\@
 	 ADD	src, src, t2
 
-.Lsrc_unaligned_dst_aligned:
+.Lsrc_unaligned_dst_aligned\@:
 	SRL	t0, len, LOG_NBYTES+2	 # +2 for 4 units/iter
-	beqz	t0, .Lcleanup_src_unaligned
+	beqz	t0, .Lcleanup_src_unaligned\@
 	 and	rem, len, (4*NBYTES-1)	 # rem = len % 4*NBYTES
 1:
 /*
@@ -578,53 +626,53 @@ EXC(	STFIRST t3, FIRST(0)(dst),	.Ls_exc)
  * It's OK to load FIRST(N+1) before REST(N) because the two addresses
  * are to the same unit (unless src is aligned, but it's not).
  */
-EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
-EXC(	LDFIRST t1, FIRST(1)(src),	.Ll_exc_copy)
+	LDFIRST(t0, FIRST(0)(src), .Ll_exc\@)
+	LDFIRST(t1, FIRST(1)(src), .Ll_exc_copy\@)
 	SUB	len, len, 4*NBYTES
-EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
-EXC(	LDREST	t1, REST(1)(src),	.Ll_exc_copy)
-EXC(	LDFIRST t2, FIRST(2)(src),	.Ll_exc_copy)
-EXC(	LDFIRST t3, FIRST(3)(src),	.Ll_exc_copy)
-EXC(	LDREST	t2, REST(2)(src),	.Ll_exc_copy)
-EXC(	LDREST	t3, REST(3)(src),	.Ll_exc_copy)
+	LDREST(t0, REST(0)(src), .Ll_exc_copy\@)
+	LDREST(t1, REST(1)(src), .Ll_exc_copy\@)
+	LDFIRST(t2, FIRST(2)(src), .Ll_exc_copy\@)
+	LDFIRST(t3, FIRST(3)(src), .Ll_exc_copy\@)
+	LDREST(t2, REST(2)(src), .Ll_exc_copy\@)
+	LDREST(t3, REST(3)(src), .Ll_exc_copy\@)
 	ADD	src, src, 4*NBYTES
 #ifdef CONFIG_CPU_SB1
 	nop				# improves slotting
 #endif
-EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc)
+	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
 	ADDC(sum, t0)
-EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc)
+	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
 	ADDC(sum, t1)
-EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc)
+	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
 	ADDC(sum, t2)
-EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc)
+	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
 	ADDC(sum, t3)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
 	bne	len, rem, 1b
 	.set	noreorder
 
-.Lcleanup_src_unaligned:
-	beqz	len, .Ldone
+.Lcleanup_src_unaligned\@:
+	beqz	len, .Ldone\@
 	 and	rem, len, NBYTES-1  # rem = len % NBYTES
-	beq	rem, len, .Lcopy_bytes
+	beq	rem, len, .Lcopy_bytes\@
 	 nop
 1:
-EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
-EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
+	LDFIRST(t0, FIRST(0)(src), .Ll_exc\@)
+	LDREST(t0, REST(0)(src), .Ll_exc_copy\@)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		.Ls_exc)
+	STORE(t0, 0(dst), .Ls_exc\@)
 	ADDC(sum, t0)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, NBYTES
 	bne	len, rem, 1b
 	.set	noreorder
 
-.Lcopy_bytes_checklen:
-	beqz	len, .Ldone
+.Lcopy_bytes_checklen\@:
+	beqz	len, .Ldone\@
 	 nop
-.Lcopy_bytes:
+.Lcopy_bytes\@:
 	/* 0 < len < NBYTES  */
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 #define SHIFT_START 0
@@ -637,12 +685,12 @@ EXC(	STORE	t0, 0(dst),		.Ls_exc)
 	li	t3, SHIFT_START # shift
 /* use .Ll_exc_copy here to return correct sum on fault */
 #define COPY_BYTE(N)			\
-EXC(	lbu	t0, N(src), .Ll_exc_copy);	\
+	LOADBU(t0, N(src), .Ll_exc_copy\@);	\
 	SUB	len, len, 1;		\
-EXC(	sb	t0, N(dst), .Ls_exc);	\
+	STOREB(t0, N(dst), .Ls_exc\@);	\
 	SLLV	t0, t0, t3;		\
 	addu	t3, SHIFT_INC;		\
-	beqz	len, .Lcopy_bytes_done; \
+	beqz	len, .Lcopy_bytes_done\@; \
 	 or	t2, t0
 
 	COPY_BYTE(0)
@@ -653,14 +701,14 @@ EXC(	sb	t0, N(dst), .Ls_exc);	\
 	COPY_BYTE(4)
 	COPY_BYTE(5)
 #endif
-EXC(	lbu	t0, NBYTES-2(src), .Ll_exc_copy)
+	LOADBU(t0, NBYTES-2(src), .Ll_exc_copy\@)
 	SUB	len, len, 1
-EXC(	sb	t0, NBYTES-2(dst), .Ls_exc)
+	STOREB(t0, NBYTES-2(dst), .Ls_exc\@)
 	SLLV	t0, t0, t3
 	or	t2, t0
-.Lcopy_bytes_done:
+.Lcopy_bytes_done\@:
 	ADDC(sum, t2)
-.Ldone:
+.Ldone\@:
 	/* fold checksum */
 #ifdef USE_DOUBLE
 	dsll32	v1, sum, 0
@@ -689,7 +737,7 @@ EXC(	sb	t0, NBYTES-2(dst), .Ls_exc)
 	jr	ra
 	.set noreorder
 
-.Ll_exc_copy:
+.Ll_exc_copy\@:
 	/*
 	 * Copy bytes from src until faulting load address (or until a
 	 * lb faults)
@@ -700,11 +748,11 @@ EXC(	sb	t0, NBYTES-2(dst), .Ls_exc)
 	 *
 	 * Assumes src < THREAD_BUADDR($28)
 	 */
-	LOAD	t0, TI_TASK($28)
+	LOADK	t0, TI_TASK($28)
 	 li	t2, SHIFT_START
-	LOAD	t0, THREAD_BUADDR(t0)
+	LOADK	t0, THREAD_BUADDR(t0)
 1:
-EXC(	lbu	t1, 0(src),	.Ll_exc)
+	LOADBU(t1, 0(src), .Ll_exc\@)
 	ADD	src, src, 1
 	sb	t1, 0(dst)	# can't fault -- we're copy_from_user
 	SLLV	t1, t1, t2
@@ -714,10 +762,10 @@ EXC(	lbu	t1, 0(src),	.Ll_exc)
 	ADD	dst, dst, 1
 	bne	src, t0, 1b
 	.set	noreorder
-.Ll_exc:
-	LOAD	t0, TI_TASK($28)
+.Ll_exc\@:
+	LOADK	t0, TI_TASK($28)
 	 nop
-	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
+	LOADK	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
 	 nop
 	SUB	len, AT, t0		# len number of uncopied bytes
 	/*
@@ -733,7 +781,7 @@ EXC(	lbu	t1, 0(src),	.Ll_exc)
 	 */
 	.set	reorder				/* DADDI_WAR */
 	SUB	src, len, 1
-	beqz	len, .Ldone
+	beqz	len, .Ldone\@
 	.set	noreorder
 1:	sb	zero, 0(dst)
 	ADD	dst, dst, 1
@@ -748,13 +796,31 @@ EXC(	lbu	t1, 0(src),	.Ll_exc)
 	 SUB	src, src, v1
 #endif
 	li	v1, -EFAULT
-	b	.Ldone
+	b	.Ldone\@
 	 sw	v1, (errptr)
 
-.Ls_exc:
+.Ls_exc\@:
 	li	v0, -1 /* invalid checksum */
 	li	v1, -EFAULT
 	jr	ra
 	 sw	v1, (errptr)
 	.set	pop
-	END(__csum_partial_copy_user)
+	.endm
+
+LEAF(__csum_partial_copy_kernel)
+#ifndef CONFIG_EVA
+FEXPORT(__csum_partial_copy_to_user)
+FEXPORT(__csum_partial_copy_from_user)
+#endif
+__BUILD_CSUM_PARTIAL_COPY_USER LEGACY_MODE USEROP USEROP 1
+END(__csum_partial_copy_kernel)
+
+#ifdef CONFIG_EVA
+LEAF(__csum_partial_copy_to_user)
+__BUILD_CSUM_PARTIAL_COPY_USER EVA_MODE KERNELOP USEROP 0
+END(__csum_partial_copy_to_user)
+
+LEAF(__csum_partial_copy_from_user)
+__BUILD_CSUM_PARTIAL_COPY_USER EVA_MODE USEROP KERNELOP 0
+END(__csum_partial_copy_from_user)
+#endif
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index c5c40dad0bbf..c17ef80cf65a 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -10,6 +10,7 @@
  * Copyright (C) 2002 Broadcom, Inc.
  *   memcpy/copy_user author: Mark Vandevoorde
  * Copyright (C) 2007  Maciej W. Rozycki
+ * Copyright (C) 2014 Imagination Technologies Ltd.
  *
  * Mnemonic names for arguments to memcpy/__copy_user
  */
@@ -85,11 +86,51 @@
  * they're not protected.
  */
 
-#define EXC(inst_reg,addr,handler)		\
-9:	inst_reg, addr;				\
-	.section __ex_table,"a";		\
-	PTR	9b, handler;			\
-	.previous
+/* Instruction type */
+#define LD_INSN 1
+#define ST_INSN 2
+/* Pretech type */
+#define SRC_PREFETCH 1
+#define DST_PREFETCH 2
+#define LEGACY_MODE 1
+#define EVA_MODE    2
+#define USEROP   1
+#define KERNELOP 2
+
+/*
+ * Wrapper to add an entry in the exception table
+ * in case the insn causes a memory exception.
+ * Arguments:
+ * insn    : Load/store instruction
+ * type    : Instruction type
+ * reg     : Register
+ * addr    : Address
+ * handler : Exception handler
+ */
+
+#define EXC(insn, type, reg, addr, handler)			\
+	.if \mode == LEGACY_MODE;				\
+9:		insn reg, addr;					\
+		.section __ex_table,"a";			\
+		PTR	9b, handler;				\
+		.previous;					\
+	/* This is assembled in EVA mode */			\
+	.else;							\
+		/* If loading from user or storing to user */	\
+		.if ((\from == USEROP) && (type == LD_INSN)) || \
+		    ((\to == USEROP) && (type == ST_INSN));	\
+9:			__BUILD_EVA_INSN(insn##e, reg, addr);	\
+			.section __ex_table,"a";		\
+			PTR	9b, handler;			\
+			.previous;				\
+		.else;						\
+			/*					\
+			 *  Still in EVA, but no need for	\
+			 * exception handler or EVA insn	\
+			 */					\
+			insn reg, addr;				\
+		.endif;						\
+	.endif
 
 /*
  * Only on the 64-bit kernel we can made use of 64-bit registers.
@@ -100,12 +141,13 @@
 
 #ifdef USE_DOUBLE
 
-#define LOAD   ld
-#define LOADL  ldl
-#define LOADR  ldr
-#define STOREL sdl
-#define STORER sdr
-#define STORE  sd
+#define LOADK ld /* No exception */
+#define LOAD(reg, addr, handler)	EXC(ld, LD_INSN, reg, addr, handler)
+#define LOADL(reg, addr, handler)	EXC(ldl, LD_INSN, reg, addr, handler)
+#define LOADR(reg, addr, handler)	EXC(ldr, LD_INSN, reg, addr, handler)
+#define STOREL(reg, addr, handler)	EXC(sdl, ST_INSN, reg, addr, handler)
+#define STORER(reg, addr, handler)	EXC(sdr, ST_INSN, reg, addr, handler)
+#define STORE(reg, addr, handler)	EXC(sd, ST_INSN, reg, addr, handler)
 #define ADD    daddu
 #define SUB    dsubu
 #define SRL    dsrl
@@ -136,12 +178,13 @@
 
 #else
 
-#define LOAD   lw
-#define LOADL  lwl
-#define LOADR  lwr
-#define STOREL swl
-#define STORER swr
-#define STORE  sw
+#define LOADK lw /* No exception */
+#define LOAD(reg, addr, handler)	EXC(lw, LD_INSN, reg, addr, handler)
+#define LOADL(reg, addr, handler)	EXC(lwl, LD_INSN, reg, addr, handler)
+#define LOADR(reg, addr, handler)	EXC(lwr, LD_INSN, reg, addr, handler)
+#define STOREL(reg, addr, handler)	EXC(swl, ST_INSN, reg, addr, handler)
+#define STORER(reg, addr, handler)	EXC(swr, ST_INSN, reg, addr, handler)
+#define STORE(reg, addr, handler)	EXC(sw, ST_INSN, reg, addr, handler)
 #define ADD    addu
 #define SUB    subu
 #define SRL    srl
@@ -154,6 +197,33 @@
 
 #endif /* USE_DOUBLE */
 
+#define LOADB(reg, addr, handler)	EXC(lb, LD_INSN, reg, addr, handler)
+#define STOREB(reg, addr, handler)	EXC(sb, ST_INSN, reg, addr, handler)
+
+#define _PREF(hint, addr, type)						\
+	.if \mode == LEGACY_MODE;					\
+		PREF(hint, addr);					\
+	.else;								\
+		.if ((\from == USEROP) && (type == SRC_PREFETCH)) ||	\
+		    ((\to == USEROP) && (type == DST_PREFETCH));	\
+			/*						\
+			 * PREFE has only 9 bits for the offset		\
+			 * compared to PREF which has 16, so it may	\
+			 * need to use the $at register but this	\
+			 * register should remain intact because it's	\
+			 * used later on. Therefore use $v1.		\
+			 */						\
+			.set at=v1;					\
+			PREFE(hint, addr);				\
+			.set noat;					\
+		.else;							\
+			PREF(hint, addr);				\
+		.endif;							\
+	.endif
+
+#define PREFS(hint, addr) _PREF(hint, addr, SRC_PREFETCH)
+#define PREFD(hint, addr) _PREF(hint, addr, DST_PREFETCH)
+
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 #define LDFIRST LOADR
 #define LDREST	LOADL
@@ -182,27 +252,23 @@
 	.set	at=v1
 #endif
 
-/*
- * t6 is used as a flag to note inatomic mode.
- */
-LEAF(__copy_user_inatomic)
-	b	__copy_user_common
-	 li	t6, 1
-	END(__copy_user_inatomic)
-
-/*
- * A combined memcpy/__copy_user
- * __copy_user sets len to 0 for success; else to an upper bound of
- * the number of uncopied bytes.
- * memcpy sets v0 to dst.
- */
 	.align	5
-LEAF(memcpy)					/* a0=dst a1=src a2=len */
-	move	v0, dst				/* return value */
-.L__memcpy:
-FEXPORT(__copy_user)
-	li	t6, 0	/* not inatomic */
-__copy_user_common:
+
+	/*
+	 * Macro to build the __copy_user common code
+	 * Arguements:
+	 * mode : LEGACY_MODE or EVA_MODE
+	 * from : Source operand. USEROP or KERNELOP
+	 * to   : Destination operand. USEROP or KERNELOP
+	 */
+	.macro __BUILD_COPY_USER mode, from, to
+
+	/* initialize __memcpy if this the first time we execute this macro */
+	.ifnotdef __memcpy
+	.set __memcpy, 1
+	.hidden __memcpy /* make sure it does not leak */
+	.endif
+
 	/*
 	 * Note: dst & src may be unaligned, len may be 0
 	 * Temps
@@ -217,94 +283,94 @@ __copy_user_common:
 	 *
 	 * If len < NBYTES use byte operations.
 	 */
-	PREF(	0, 0(src) )
-	PREF(	1, 0(dst) )
+	PREFS(	0, 0(src) )
+	PREFD(	1, 0(dst) )
 	sltu	t2, len, NBYTES
 	and	t1, dst, ADDRMASK
-	PREF(	0, 1*32(src) )
-	PREF(	1, 1*32(dst) )
-	bnez	t2, .Lcopy_bytes_checklen
+	PREFS(	0, 1*32(src) )
+	PREFD(	1, 1*32(dst) )
+	bnez	t2, .Lcopy_bytes_checklen\@
 	 and	t0, src, ADDRMASK
-	PREF(	0, 2*32(src) )
-	PREF(	1, 2*32(dst) )
-	bnez	t1, .Ldst_unaligned
+	PREFS(	0, 2*32(src) )
+	PREFD(	1, 2*32(dst) )
+	bnez	t1, .Ldst_unaligned\@
 	 nop
-	bnez	t0, .Lsrc_unaligned_dst_aligned
+	bnez	t0, .Lsrc_unaligned_dst_aligned\@
 	/*
 	 * use delay slot for fall-through
 	 * src and dst are aligned; need to compute rem
 	 */
-.Lboth_aligned:
+.Lboth_aligned\@:
 	 SRL	t0, len, LOG_NBYTES+3	 # +3 for 8 units/iter
-	beqz	t0, .Lcleanup_both_aligned # len < 8*NBYTES
+	beqz	t0, .Lcleanup_both_aligned\@ # len < 8*NBYTES
 	 and	rem, len, (8*NBYTES-1)	 # rem = len % (8*NBYTES)
-	PREF(	0, 3*32(src) )
-	PREF(	1, 3*32(dst) )
+	PREFS(	0, 3*32(src) )
+	PREFD(	1, 3*32(dst) )
 	.align	4
 1:
 	R10KCBARRIER(0(ra))
-EXC(	LOAD	t0, UNIT(0)(src),	.Ll_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	.Ll_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	.Ll_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	.Ll_exc_copy)
+	LOAD(t0, UNIT(0)(src), .Ll_exc\@)
+	LOAD(t1, UNIT(1)(src), .Ll_exc_copy\@)
+	LOAD(t2, UNIT(2)(src), .Ll_exc_copy\@)
+	LOAD(t3, UNIT(3)(src), .Ll_exc_copy\@)
 	SUB	len, len, 8*NBYTES
-EXC(	LOAD	t4, UNIT(4)(src),	.Ll_exc_copy)
-EXC(	LOAD	t7, UNIT(5)(src),	.Ll_exc_copy)
-EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc_p8u)
-EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc_p7u)
-EXC(	LOAD	t0, UNIT(6)(src),	.Ll_exc_copy)
-EXC(	LOAD	t1, UNIT(7)(src),	.Ll_exc_copy)
+	LOAD(t4, UNIT(4)(src), .Ll_exc_copy\@)
+	LOAD(t7, UNIT(5)(src), .Ll_exc_copy\@)
+	STORE(t0, UNIT(0)(dst),	.Ls_exc_p8u\@)
+	STORE(t1, UNIT(1)(dst),	.Ls_exc_p7u\@)
+	LOAD(t0, UNIT(6)(src), .Ll_exc_copy\@)
+	LOAD(t1, UNIT(7)(src), .Ll_exc_copy\@)
 	ADD	src, src, 8*NBYTES
 	ADD	dst, dst, 8*NBYTES
-EXC(	STORE	t2, UNIT(-6)(dst),	.Ls_exc_p6u)
-EXC(	STORE	t3, UNIT(-5)(dst),	.Ls_exc_p5u)
-EXC(	STORE	t4, UNIT(-4)(dst),	.Ls_exc_p4u)
-EXC(	STORE	t7, UNIT(-3)(dst),	.Ls_exc_p3u)
-EXC(	STORE	t0, UNIT(-2)(dst),	.Ls_exc_p2u)
-EXC(	STORE	t1, UNIT(-1)(dst),	.Ls_exc_p1u)
-	PREF(	0, 8*32(src) )
-	PREF(	1, 8*32(dst) )
+	STORE(t2, UNIT(-6)(dst), .Ls_exc_p6u\@)
+	STORE(t3, UNIT(-5)(dst), .Ls_exc_p5u\@)
+	STORE(t4, UNIT(-4)(dst), .Ls_exc_p4u\@)
+	STORE(t7, UNIT(-3)(dst), .Ls_exc_p3u\@)
+	STORE(t0, UNIT(-2)(dst), .Ls_exc_p2u\@)
+	STORE(t1, UNIT(-1)(dst), .Ls_exc_p1u\@)
+	PREFS(	0, 8*32(src) )
+	PREFD(	1, 8*32(dst) )
 	bne	len, rem, 1b
 	 nop
 
 	/*
 	 * len == rem == the number of bytes left to copy < 8*NBYTES
 	 */
-.Lcleanup_both_aligned:
-	beqz	len, .Ldone
+.Lcleanup_both_aligned\@:
+	beqz	len, .Ldone\@
 	 sltu	t0, len, 4*NBYTES
-	bnez	t0, .Lless_than_4units
+	bnez	t0, .Lless_than_4units\@
 	 and	rem, len, (NBYTES-1)	# rem = len % NBYTES
 	/*
 	 * len >= 4*NBYTES
 	 */
-EXC(	LOAD	t0, UNIT(0)(src),	.Ll_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	.Ll_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	.Ll_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	.Ll_exc_copy)
+	LOAD( t0, UNIT(0)(src),	.Ll_exc\@)
+	LOAD( t1, UNIT(1)(src),	.Ll_exc_copy\@)
+	LOAD( t2, UNIT(2)(src),	.Ll_exc_copy\@)
+	LOAD( t3, UNIT(3)(src),	.Ll_exc_copy\@)
 	SUB	len, len, 4*NBYTES
 	ADD	src, src, 4*NBYTES
 	R10KCBARRIER(0(ra))
-EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc_p4u)
-EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc_p3u)
-EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc_p2u)
-EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc_p1u)
+	STORE(t0, UNIT(0)(dst),	.Ls_exc_p4u\@)
+	STORE(t1, UNIT(1)(dst),	.Ls_exc_p3u\@)
+	STORE(t2, UNIT(2)(dst),	.Ls_exc_p2u\@)
+	STORE(t3, UNIT(3)(dst),	.Ls_exc_p1u\@)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
-	beqz	len, .Ldone
+	beqz	len, .Ldone\@
 	.set	noreorder
-.Lless_than_4units:
+.Lless_than_4units\@:
 	/*
 	 * rem = len % NBYTES
 	 */
-	beq	rem, len, .Lcopy_bytes
+	beq	rem, len, .Lcopy_bytes\@
 	 nop
 1:
 	R10KCBARRIER(0(ra))
-EXC(	LOAD	t0, 0(src),		.Ll_exc)
+	LOAD(t0, 0(src), .Ll_exc\@)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		.Ls_exc_p1u)
+	STORE(t0, 0(dst), .Ls_exc_p1u\@)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, NBYTES
 	bne	rem, len, 1b
@@ -322,17 +388,17 @@ EXC(	STORE	t0, 0(dst),		.Ls_exc_p1u)
 	 * more instruction-level parallelism.
 	 */
 #define bits t2
-	beqz	len, .Ldone
+	beqz	len, .Ldone\@
 	 ADD	t1, dst, len	# t1 is just past last byte of dst
 	li	bits, 8*NBYTES
 	SLL	rem, len, 3	# rem = number of bits to keep
-EXC(	LOAD	t0, 0(src),		.Ll_exc)
+	LOAD(t0, 0(src), .Ll_exc\@)
 	SUB	bits, bits, rem # bits = number of bits to discard
 	SHIFT_DISCARD t0, t0, bits
-EXC(	STREST	t0, -1(t1),		.Ls_exc)
+	STREST(t0, -1(t1), .Ls_exc\@)
 	jr	ra
 	 move	len, zero
-.Ldst_unaligned:
+.Ldst_unaligned\@:
 	/*
 	 * dst is unaligned
 	 * t0 = src & ADDRMASK
@@ -343,25 +409,25 @@ EXC(	STREST	t0, -1(t1),		.Ls_exc)
 	 * Set match = (src and dst have same alignment)
 	 */
 #define match rem
-EXC(	LDFIRST t3, FIRST(0)(src),	.Ll_exc)
+	LDFIRST(t3, FIRST(0)(src), .Ll_exc\@)
 	ADD	t2, zero, NBYTES
-EXC(	LDREST	t3, REST(0)(src),	.Ll_exc_copy)
+	LDREST(t3, REST(0)(src), .Ll_exc_copy\@)
 	SUB	t2, t2, t1	# t2 = number of bytes copied
 	xor	match, t0, t1
 	R10KCBARRIER(0(ra))
-EXC(	STFIRST t3, FIRST(0)(dst),	.Ls_exc)
-	beq	len, t2, .Ldone
+	STFIRST(t3, FIRST(0)(dst), .Ls_exc\@)
+	beq	len, t2, .Ldone\@
 	 SUB	len, len, t2
 	ADD	dst, dst, t2
-	beqz	match, .Lboth_aligned
+	beqz	match, .Lboth_aligned\@
 	 ADD	src, src, t2
 
-.Lsrc_unaligned_dst_aligned:
+.Lsrc_unaligned_dst_aligned\@:
 	SRL	t0, len, LOG_NBYTES+2	 # +2 for 4 units/iter
-	PREF(	0, 3*32(src) )
-	beqz	t0, .Lcleanup_src_unaligned
+	PREFS(	0, 3*32(src) )
+	beqz	t0, .Lcleanup_src_unaligned\@
 	 and	rem, len, (4*NBYTES-1)	 # rem = len % 4*NBYTES
-	PREF(	1, 3*32(dst) )
+	PREFD(	1, 3*32(dst) )
 1:
 /*
  * Avoid consecutive LD*'s to the same register since some mips
@@ -370,58 +436,58 @@ EXC(	STFIRST t3, FIRST(0)(dst),	.Ls_exc)
  * are to the same unit (unless src is aligned, but it's not).
  */
 	R10KCBARRIER(0(ra))
-EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
-EXC(	LDFIRST t1, FIRST(1)(src),	.Ll_exc_copy)
+	LDFIRST(t0, FIRST(0)(src), .Ll_exc\@)
+	LDFIRST(t1, FIRST(1)(src), .Ll_exc_copy\@)
 	SUB	len, len, 4*NBYTES
-EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
-EXC(	LDREST	t1, REST(1)(src),	.Ll_exc_copy)
-EXC(	LDFIRST t2, FIRST(2)(src),	.Ll_exc_copy)
-EXC(	LDFIRST t3, FIRST(3)(src),	.Ll_exc_copy)
-EXC(	LDREST	t2, REST(2)(src),	.Ll_exc_copy)
-EXC(	LDREST	t3, REST(3)(src),	.Ll_exc_copy)
-	PREF(	0, 9*32(src) )		# 0 is PREF_LOAD  (not streamed)
+	LDREST(t0, REST(0)(src), .Ll_exc_copy\@)
+	LDREST(t1, REST(1)(src), .Ll_exc_copy\@)
+	LDFIRST(t2, FIRST(2)(src), .Ll_exc_copy\@)
+	LDFIRST(t3, FIRST(3)(src), .Ll_exc_copy\@)
+	LDREST(t2, REST(2)(src), .Ll_exc_copy\@)
+	LDREST(t3, REST(3)(src), .Ll_exc_copy\@)
+	PREFS(	0, 9*32(src) )		# 0 is PREF_LOAD  (not streamed)
 	ADD	src, src, 4*NBYTES
 #ifdef CONFIG_CPU_SB1
 	nop				# improves slotting
 #endif
-EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc_p4u)
-EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc_p3u)
-EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc_p2u)
-EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc_p1u)
-	PREF(	1, 9*32(dst) )		# 1 is PREF_STORE (not streamed)
+	STORE(t0, UNIT(0)(dst),	.Ls_exc_p4u\@)
+	STORE(t1, UNIT(1)(dst),	.Ls_exc_p3u\@)
+	STORE(t2, UNIT(2)(dst),	.Ls_exc_p2u\@)
+	STORE(t3, UNIT(3)(dst),	.Ls_exc_p1u\@)
+	PREFD(	1, 9*32(dst) )		# 1 is PREF_STORE (not streamed)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
 	bne	len, rem, 1b
 	.set	noreorder
 
-.Lcleanup_src_unaligned:
-	beqz	len, .Ldone
+.Lcleanup_src_unaligned\@:
+	beqz	len, .Ldone\@
 	 and	rem, len, NBYTES-1  # rem = len % NBYTES
-	beq	rem, len, .Lcopy_bytes
+	beq	rem, len, .Lcopy_bytes\@
 	 nop
 1:
 	R10KCBARRIER(0(ra))
-EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
-EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
+	LDFIRST(t0, FIRST(0)(src), .Ll_exc\@)
+	LDREST(t0, REST(0)(src), .Ll_exc_copy\@)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		.Ls_exc_p1u)
+	STORE(t0, 0(dst), .Ls_exc_p1u\@)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, NBYTES
 	bne	len, rem, 1b
 	.set	noreorder
 
-.Lcopy_bytes_checklen:
-	beqz	len, .Ldone
+.Lcopy_bytes_checklen\@:
+	beqz	len, .Ldone\@
 	 nop
-.Lcopy_bytes:
+.Lcopy_bytes\@:
 	/* 0 < len < NBYTES  */
 	R10KCBARRIER(0(ra))
 #define COPY_BYTE(N)			\
-EXC(	lb	t0, N(src), .Ll_exc);	\
+	LOADB(t0, N(src), .Ll_exc\@);	\
 	SUB	len, len, 1;		\
-	beqz	len, .Ldone;		\
-EXC(	 sb	t0, N(dst), .Ls_exc_p1)
+	beqz	len, .Ldone\@;		\
+	STOREB(t0, N(dst), .Ls_exc_p1\@)
 
 	COPY_BYTE(0)
 	COPY_BYTE(1)
@@ -431,16 +497,19 @@ EXC(	 sb	t0, N(dst), .Ls_exc_p1)
 	COPY_BYTE(4)
 	COPY_BYTE(5)
 #endif
-EXC(	lb	t0, NBYTES-2(src), .Ll_exc)
+	LOADB(t0, NBYTES-2(src), .Ll_exc\@)
 	SUB	len, len, 1
 	jr	ra
-EXC(	 sb	t0, NBYTES-2(dst), .Ls_exc_p1)
-.Ldone:
+	STOREB(t0, NBYTES-2(dst), .Ls_exc_p1\@)
+.Ldone\@:
 	jr	ra
-	 nop
+	.if __memcpy == 1
 	END(memcpy)
+	.set __memcpy, 0
+	.hidden __memcpy
+	.endif
 
-.Ll_exc_copy:
+.Ll_exc_copy\@:
 	/*
 	 * Copy bytes from src until faulting load address (or until a
 	 * lb faults)
@@ -451,24 +520,24 @@ EXC(	 sb	t0, NBYTES-2(dst), .Ls_exc_p1)
 	 *
 	 * Assumes src < THREAD_BUADDR($28)
 	 */
-	LOAD	t0, TI_TASK($28)
+	LOADK	t0, TI_TASK($28)
 	 nop
-	LOAD	t0, THREAD_BUADDR(t0)
+	LOADK	t0, THREAD_BUADDR(t0)
 1:
-EXC(	lb	t1, 0(src),	.Ll_exc)
+	LOADB(t1, 0(src), .Ll_exc\@)
 	ADD	src, src, 1
 	sb	t1, 0(dst)	# can't fault -- we're copy_from_user
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 1
 	bne	src, t0, 1b
 	.set	noreorder
-.Ll_exc:
-	LOAD	t0, TI_TASK($28)
+.Ll_exc\@:
+	LOADK	t0, TI_TASK($28)
 	 nop
-	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
+	LOADK	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
 	 nop
 	SUB	len, AT, t0		# len number of uncopied bytes
-	bnez	t6, .Ldone	/* Skip the zeroing part if inatomic */
+	bnez	t6, .Ldone\@	/* Skip the zeroing part if inatomic */
 	/*
 	 * Here's where we rely on src and dst being incremented in tandem,
 	 *   See (3) above.
@@ -482,7 +551,7 @@ EXC(	lb	t1, 0(src),	.Ll_exc)
 	 */
 	.set	reorder				/* DADDI_WAR */
 	SUB	src, len, 1
-	beqz	len, .Ldone
+	beqz	len, .Ldone\@
 	.set	noreorder
 1:	sb	zero, 0(dst)
 	ADD	dst, dst, 1
@@ -503,7 +572,7 @@ EXC(	lb	t1, 0(src),	.Ll_exc)
 
 #define SEXC(n)							\
 	.set	reorder;			/* DADDI_WAR */ \
-.Ls_exc_p ## n ## u:						\
+.Ls_exc_p ## n ## u\@:						\
 	ADD	len, len, n*NBYTES;				\
 	jr	ra;						\
 	.set	noreorder
@@ -517,14 +586,15 @@ SEXC(3)
 SEXC(2)
 SEXC(1)
 
-.Ls_exc_p1:
+.Ls_exc_p1\@:
 	.set	reorder				/* DADDI_WAR */
 	ADD	len, len, 1
 	jr	ra
 	.set	noreorder
-.Ls_exc:
+.Ls_exc\@:
 	jr	ra
 	 nop
+	.endm
 
 	.align	5
 LEAF(memmove)
@@ -575,3 +645,71 @@ LEAF(__rmemcpy)					/* a0=dst a1=src a2=len */
 	jr	ra
 	 move	a2, zero
 	END(__rmemcpy)
+
+/*
+ * t6 is used as a flag to note inatomic mode.
+ */
+LEAF(__copy_user_inatomic)
+	b	__copy_user_common
+	li	t6, 1
+	END(__copy_user_inatomic)
+
+/*
+ * A combined memcpy/__copy_user
+ * __copy_user sets len to 0 for success; else to an upper bound of
+ * the number of uncopied bytes.
+ * memcpy sets v0 to dst.
+ */
+	.align	5
+LEAF(memcpy)					/* a0=dst a1=src a2=len */
+	move	v0, dst				/* return value */
+.L__memcpy:
+FEXPORT(__copy_user)
+	li	t6, 0	/* not inatomic */
+__copy_user_common:
+	/* Legacy Mode, user <-> user */
+	__BUILD_COPY_USER LEGACY_MODE USEROP USEROP
+
+#ifdef CONFIG_EVA
+
+/*
+ * For EVA we need distinct symbols for reading and writing to user space.
+ * This is because we need to use specific EVA instructions to perform the
+ * virtual <-> physical translation when a virtual address is actually in user
+ * space
+ */
+
+LEAF(__copy_user_inatomic_eva)
+	b       __copy_from_user_common
+	li	t6, 1
+	END(__copy_user_inatomic_eva)
+
+/*
+ * __copy_from_user (EVA)
+ */
+
+LEAF(__copy_from_user_eva)
+	li	t6, 0	/* not inatomic */
+__copy_from_user_common:
+	__BUILD_COPY_USER EVA_MODE USEROP KERNELOP
+END(__copy_from_user_eva)
+
+
+
+/*
+ * __copy_to_user (EVA)
+ */
+
+LEAF(__copy_to_user_eva)
+__BUILD_COPY_USER EVA_MODE KERNELOP USEROP
+END(__copy_to_user_eva)
+
+/*
+ * __copy_in_user (EVA)
+ */
+
+LEAF(__copy_in_user_eva)
+__BUILD_COPY_USER EVA_MODE USEROP USEROP
+END(__copy_in_user_eva)
+
+#endif
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 0580194e7402..7b0e5462ca51 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -34,13 +34,27 @@
 #define FILLPTRG t0
 #endif
 
+#define LEGACY_MODE 1
+#define EVA_MODE    2
+
+/*
+ * No need to protect it with EVA #ifdefery. The generated block of code
+ * will never be assembled if EVA is not enabled.
+ */
+#define __EVAFY(insn, reg, addr) __BUILD_EVA_INSN(insn##e, reg, addr)
+#define ___BUILD_EVA_INSN(insn, reg, addr) __EVAFY(insn, reg, addr)
+
 #define EX(insn,reg,addr,handler)			\
-9:	insn	reg, addr;				\
+	.if \mode == LEGACY_MODE;			\
+9:		insn	reg, addr;			\
+	.else;						\
+9:		___BUILD_EVA_INSN(insn, reg, addr);	\
+	.endif;						\
 	.section __ex_table,"a";			\
 	PTR	9b, handler;				\
 	.previous
 
-	.macro	f_fill64 dst, offset, val, fixup
+	.macro	f_fill64 dst, offset, val, fixup, mode
 	EX(LONG_S, \val, (\offset +  0 * STORSIZE)(\dst), \fixup)
 	EX(LONG_S, \val, (\offset +  1 * STORSIZE)(\dst), \fixup)
 	EX(LONG_S, \val, (\offset +  2 * STORSIZE)(\dst), \fixup)
@@ -63,34 +77,24 @@
 #endif
 	.endm
 
-/*
- * memset(void *s, int c, size_t n)
- *
- * a0: start of area to clear
- * a1: char to fill with
- * a2: size of area to clear
- */
 	.set	noreorder
 	.align	5
-LEAF(memset)
-	beqz		a1, 1f
-	 move		v0, a0			/* result */
 
-	andi		a1, 0xff		/* spread fillword */
-	LONG_SLL		t1, a1, 8
-	or		a1, t1
-	LONG_SLL		t1, a1, 16
-#if LONGSIZE == 8
-	or		a1, t1
-	LONG_SLL		t1, a1, 32
-#endif
-	or		a1, t1
-1:
+	/*
+	 * Macro to generate the __bzero{,_user} symbol
+	 * Arguments:
+	 * mode: LEGACY_MODE or EVA_MODE
+	 */
+	.macro __BUILD_BZERO mode
+	/* Initialize __memset if this is the first time we call this macro */
+	.ifnotdef __memset
+	.set __memset, 1
+	.hidden __memset /* Make sure it does not leak */
+	.endif
 
-FEXPORT(__bzero)
 	sltiu		t0, a2, STORSIZE	/* very small region? */
-	bnez		t0, .Lsmall_memset
-	 andi		t0, a0, STORMASK	/* aligned? */
+	bnez		t0, .Lsmall_memset\@
+	andi		t0, a0, STORMASK	/* aligned? */
 
 #ifdef CONFIG_CPU_MICROMIPS
 	move		t8, a1			/* used by 'swp' instruction */
@@ -98,39 +102,39 @@ FEXPORT(__bzero)
 #endif
 #ifndef CONFIG_CPU_DADDI_WORKAROUNDS
 	beqz		t0, 1f
-	 PTR_SUBU	t0, STORSIZE		/* alignment in bytes */
+	PTR_SUBU	t0, STORSIZE		/* alignment in bytes */
 #else
 	.set		noat
 	li		AT, STORSIZE
 	beqz		t0, 1f
-	 PTR_SUBU	t0, AT			/* alignment in bytes */
+	PTR_SUBU	t0, AT			/* alignment in bytes */
 	.set		at
 #endif
 
 	R10KCBARRIER(0(ra))
 #ifdef __MIPSEB__
-	EX(LONG_S_L, a1, (a0), .Lfirst_fixup)	/* make word/dword aligned */
+	EX(LONG_S_L, a1, (a0), .Lfirst_fixup\@)	/* make word/dword aligned */
 #endif
 #ifdef __MIPSEL__
-	EX(LONG_S_R, a1, (a0), .Lfirst_fixup)	/* make word/dword aligned */
+	EX(LONG_S_R, a1, (a0), .Lfirst_fixup\@)	/* make word/dword aligned */
 #endif
 	PTR_SUBU	a0, t0			/* long align ptr */
 	PTR_ADDU	a2, t0			/* correct size */
 
 1:	ori		t1, a2, 0x3f		/* # of full blocks */
 	xori		t1, 0x3f
-	beqz		t1, .Lmemset_partial	/* no block to fill */
-	 andi		t0, a2, 0x40-STORSIZE
+	beqz		t1, .Lmemset_partial\@	/* no block to fill */
+	andi		t0, a2, 0x40-STORSIZE
 
 	PTR_ADDU	t1, a0			/* end address */
 	.set		reorder
 1:	PTR_ADDIU	a0, 64
 	R10KCBARRIER(0(ra))
-	f_fill64 a0, -64, FILL64RG, .Lfwd_fixup
+	f_fill64 a0, -64, FILL64RG, .Lfwd_fixup\@, \mode
 	bne		t1, a0, 1b
 	.set		noreorder
 
-.Lmemset_partial:
+.Lmemset_partial\@:
 	R10KCBARRIER(0(ra))
 	PTR_LA		t1, 2f			/* where to start */
 #ifdef CONFIG_CPU_MICROMIPS
@@ -145,60 +149,100 @@ FEXPORT(__bzero)
 	.set		at
 #endif
 	jr		t1
-	 PTR_ADDU	a0, t0			/* dest ptr */
+	PTR_ADDU	a0, t0			/* dest ptr */
 
 	.set		push
 	.set		noreorder
 	.set		nomacro
-	f_fill64 a0, -64, FILL64RG, .Lpartial_fixup	/* ... but first do longs ... */
+	/* ... but first do longs ... */
+	f_fill64 a0, -64, FILL64RG, .Lpartial_fixup\@, \mode
 2:	.set		pop
 	andi		a2, STORMASK		/* At most one long to go */
 
 	beqz		a2, 1f
-	 PTR_ADDU	a0, a2			/* What's left */
+	PTR_ADDU	a0, a2			/* What's left */
 	R10KCBARRIER(0(ra))
 #ifdef __MIPSEB__
-	EX(LONG_S_R, a1, -1(a0), .Llast_fixup)
+	EX(LONG_S_R, a1, -1(a0), .Llast_fixup\@)
 #endif
 #ifdef __MIPSEL__
-	EX(LONG_S_L, a1, -1(a0), .Llast_fixup)
+	EX(LONG_S_L, a1, -1(a0), .Llast_fixup\@)
 #endif
 1:	jr		ra
-	 move		a2, zero
+	move		a2, zero
 
-.Lsmall_memset:
+.Lsmall_memset\@:
 	beqz		a2, 2f
-	 PTR_ADDU	t1, a0, a2
+	PTR_ADDU	t1, a0, a2
 
 1:	PTR_ADDIU	a0, 1			/* fill bytewise */
 	R10KCBARRIER(0(ra))
 	bne		t1, a0, 1b
-	 sb		a1, -1(a0)
+	sb		a1, -1(a0)
 
 2:	jr		ra			/* done */
-	 move		a2, zero
+	move		a2, zero
+	.if __memset == 1
 	END(memset)
+	.set __memset, 0
+	.hidden __memset
+	.endif
 
-.Lfirst_fixup:
+.Lfirst_fixup\@:
 	jr	ra
-	 nop
+	nop
 
-.Lfwd_fixup:
+.Lfwd_fixup\@:
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, 0x3f
 	LONG_L		t0, THREAD_BUADDR(t0)
 	LONG_ADDU	a2, t1
 	jr		ra
-	 LONG_SUBU	a2, t0
+	LONG_SUBU	a2, t0
 
-.Lpartial_fixup:
+.Lpartial_fixup\@:
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, STORMASK
 	LONG_L		t0, THREAD_BUADDR(t0)
 	LONG_ADDU	a2, t1
 	jr		ra
-	 LONG_SUBU	a2, t0
+	LONG_SUBU	a2, t0
 
-.Llast_fixup:
+.Llast_fixup\@:
 	jr		ra
-	 andi		v1, a2, STORMASK
+	andi		v1, a2, STORMASK
+
+	.endm
+
+/*
+ * memset(void *s, int c, size_t n)
+ *
+ * a0: start of area to clear
+ * a1: char to fill with
+ * a2: size of area to clear
+ */
+
+LEAF(memset)
+	beqz		a1, 1f
+	move		v0, a0			/* result */
+
+	andi		a1, 0xff		/* spread fillword */
+	LONG_SLL		t1, a1, 8
+	or		a1, t1
+	LONG_SLL		t1, a1, 16
+#if LONGSIZE == 8
+	or		a1, t1
+	LONG_SLL		t1, a1, 32
+#endif
+	or		a1, t1
+1:
+#ifndef CONFIG_EVA
+FEXPORT(__bzero)
+#endif
+	__BUILD_BZERO LEGACY_MODE
+
+#ifdef CONFIG_EVA
+LEAF(__bzero)
+	__BUILD_BZERO EVA_MODE
+END(__bzero)
+#endif
diff --git a/arch/mips/lib/strlen_user.S b/arch/mips/lib/strlen_user.S
index e362dcdc69d1..bef65c98df59 100644
--- a/arch/mips/lib/strlen_user.S
+++ b/arch/mips/lib/strlen_user.S
@@ -22,19 +22,43 @@
  *
  * Return 0 for error
  */
-LEAF(__strlen_user_asm)
+	.macro __BUILD_STRLEN_ASM func
+LEAF(__strlen_\func\()_asm)
 	LONG_L		v0, TI_ADDR_LIMIT($28)	# pointer ok?
 	and		v0, a0
-	bnez		v0, .Lfault
+	bnez		v0, .Lfault\@
 
-FEXPORT(__strlen_user_nocheck_asm)
+FEXPORT(__strlen_\func\()_nocheck_asm)
 	move		v0, a0
-1:	EX(lbu, v1, (v0), .Lfault)
+.ifeqs "\func", "kernel"
+1:	EX(lbu, v1, (v0), .Lfault\@)
+.else
+1:	EX(lbue, v1, (v0), .Lfault\@)
+.endif
 	PTR_ADDIU	v0, 1
 	bnez		v1, 1b
 	PTR_SUBU	v0, a0
 	jr		ra
-	END(__strlen_user_asm)
+	END(__strlen_\func\()_asm)
 
-.Lfault:	move		v0, zero
+.Lfault\@:	move		v0, zero
 	jr		ra
+	.endm
+
+#ifndef CONFIG_EVA
+	/* Set aliases */
+	.global __strlen_user_asm
+	.global __strlen_user_nocheck_asm
+	.set __strlen_user_asm, __strlen_kernel_asm
+	.set __strlen_user_nocheck_asm, __strlen_kernel_nocheck_asm
+#endif
+
+__BUILD_STRLEN_ASM kernel
+
+#ifdef CONFIG_EVA
+
+	.set push
+	.set eva
+__BUILD_STRLEN_ASM user
+	.set pop
+#endif
diff --git a/arch/mips/lib/strncpy_user.S b/arch/mips/lib/strncpy_user.S
index 92870b6b53ea..d3301cd1e9a5 100644
--- a/arch/mips/lib/strncpy_user.S
+++ b/arch/mips/lib/strncpy_user.S
@@ -28,16 +28,21 @@
  * it happens at most some bytes of the exceptions handlers will be copied.
  */
 
-LEAF(__strncpy_from_user_asm)
+	.macro __BUILD_STRNCPY_ASM func
+LEAF(__strncpy_from_\func\()_asm)
 	LONG_L		v0, TI_ADDR_LIMIT($28)	# pointer ok?
 	and		v0, a1
-	bnez		v0, .Lfault
+	bnez		v0, .Lfault\@
 
-FEXPORT(__strncpy_from_user_nocheck_asm)
+FEXPORT(__strncpy_from_\func\()_nocheck_asm)
 	.set		noreorder
 	move		t0, zero
 	move		v1, a1
-1:	EX(lbu, v0, (v1), .Lfault)
+.ifeqs "\func","kernel"
+1:	EX(lbu, v0, (v1), .Lfault\@)
+.else
+1:	EX(lbue, v0, (v1), .Lfault\@)
+.endif
 	PTR_ADDIU	v1, 1
 	R10KCBARRIER(0(ra))
 	beqz		v0, 2f
@@ -47,15 +52,34 @@ FEXPORT(__strncpy_from_user_nocheck_asm)
 	 PTR_ADDIU	a0, 1
 2:	PTR_ADDU	v0, a1, t0
 	xor		v0, a1
-	bltz		v0, .Lfault
+	bltz		v0, .Lfault\@
 	 nop
 	jr		ra			# return n
 	 move		v0, t0
-	END(__strncpy_from_user_asm)
+	END(__strncpy_from_\func\()_asm)
 
-.Lfault: jr		ra
+.Lfault\@: jr		ra
 	  li		v0, -EFAULT
 
 	.section	__ex_table,"a"
-	PTR		1b, .Lfault
+	PTR		1b, .Lfault\@
 	.previous
+
+	.endm
+
+#ifndef CONFIG_EVA
+	/* Set aliases */
+	.global __strncpy_from_user_asm
+	.global __strncpy_from_user_nocheck_asm
+	.set __strncpy_from_user_asm, __strncpy_from_kernel_asm
+	.set __strncpy_from_user_nocheck_asm, __strncpy_from_kernel_nocheck_asm
+#endif
+
+__BUILD_STRNCPY_ASM kernel
+
+#ifdef CONFIG_EVA
+	.set push
+	.set eva
+__BUILD_STRNCPY_ASM user
+	.set pop
+#endif
diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S
index fcacea5e61f1..f3af6995e2a6 100644
--- a/arch/mips/lib/strnlen_user.S
+++ b/arch/mips/lib/strnlen_user.S
@@ -25,22 +25,46 @@
  *	 bytes.	 There's nothing secret there.	On 64-bit accessing beyond
  *	 the maximum is a tad hairier ...
  */
-LEAF(__strnlen_user_asm)
+	.macro __BUILD_STRNLEN_ASM func
+LEAF(__strnlen_\func\()_asm)
 	LONG_L		v0, TI_ADDR_LIMIT($28)	# pointer ok?
 	and		v0, a0
-	bnez		v0, .Lfault
+	bnez		v0, .Lfault\@
 
-FEXPORT(__strnlen_user_nocheck_asm)
+FEXPORT(__strnlen_\func\()_nocheck_asm)
 	move		v0, a0
 	PTR_ADDU	a1, a0			# stop pointer
 1:	beq		v0, a1, 1f		# limit reached?
-	EX(lb, t0, (v0), .Lfault)
+.ifeqs "\func", "kernel"
+	EX(lb, t0, (v0), .Lfault\@)
+.else
+	EX(lbe, t0, (v0), .Lfault\@)
+.endif
 	PTR_ADDIU	v0, 1
 	bnez		t0, 1b
 1:	PTR_SUBU	v0, a0
 	jr		ra
-	END(__strnlen_user_asm)
+	END(__strnlen_\func\()_asm)
 
-.Lfault:
+.Lfault\@:
 	move		v0, zero
 	jr		ra
+	.endm
+
+#ifndef CONFIG_EVA
+	/* Set aliases */
+	.global __strnlen_user_asm
+	.global __strnlen_user_nocheck_asm
+	.set __strnlen_user_asm, __strnlen_kernel_asm
+	.set __strnlen_user_nocheck_asm, __strnlen_kernel_nocheck_asm
+#endif
+
+__BUILD_STRNLEN_ASM kernel
+
+#ifdef CONFIG_EVA
+
+	.set push
+	.set eva
+__BUILD_STRNLEN_ASM user
+	.set pop
+#endif