Merge branch 'linux-2.6'

8 files changed, 433 insertions, 317 deletions

diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index c0a77fe038b..8d7784122c1 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -7,6 +7,7 @@
  *
  * Copyright (C) 1998, 1999 Ralf Baechle
  * Copyright (C) 1999 Silicon Graphics, Inc.
+ * Copyright (C) 2007  Maciej W. Rozycki
  */
 #include <linux/errno.h>
 #include <asm/asm.h>
@@ -52,9 +53,12 @@
 #define UNIT(unit)  ((unit)*NBYTES)
 
 #define ADDC(sum,reg)						\
+	.set	push;						\
+	.set	noat;						\
 	ADD	sum, reg;					\
 	sltu	v1, sum, reg;					\
-	ADD	sum, v1
+	ADD	sum, v1;					\
+	.set	pop
 
 #define CSUM_BIGCHUNK1(src, offset, sum, _t0, _t1, _t2, _t3)	\
 	LOAD	_t0, (offset + UNIT(0))(src);			\
@@ -92,13 +96,13 @@ LEAF(csum_partial)
 	move	t7, zero
 
 	sltiu	t8, a1, 0x8
-	bnez	t8, small_csumcpy		/* < 8 bytes to copy */
+	bnez	t8, .Lsmall_csumcpy		/* < 8 bytes to copy */
 	 move	t2, a1
 
 	andi	t7, src, 0x1			/* odd buffer? */
 
-hword_align:
-	beqz	t7, word_align
+.Lhword_align:
+	beqz	t7, .Lword_align
 	 andi	t8, src, 0x2
 
 	lbu	t0, (src)
@@ -110,8 +114,8 @@ hword_align:
 	PTR_ADDU	src, src, 0x1
 	andi	t8, src, 0x2
 
-word_align:
-	beqz	t8, dword_align
+.Lword_align:
+	beqz	t8, .Ldword_align
 	 sltiu	t8, a1, 56
 
 	lhu	t0, (src)
@@ -120,12 +124,12 @@ word_align:
 	sltiu	t8, a1, 56
 	PTR_ADDU	src, src, 0x2
 
-dword_align:
-	bnez	t8, do_end_words
+.Ldword_align:
+	bnez	t8, .Ldo_end_words
 	 move	t8, a1
 
 	andi	t8, src, 0x4
-	beqz	t8, qword_align
+	beqz	t8, .Lqword_align
 	 andi	t8, src, 0x8
 
 	lw	t0, 0x00(src)
@@ -134,8 +138,8 @@ dword_align:
 	PTR_ADDU	src, src, 0x4
 	andi	t8, src, 0x8
 
-qword_align:
-	beqz	t8, oword_align
+.Lqword_align:
+	beqz	t8, .Loword_align
 	 andi	t8, src, 0x10
 
 #ifdef USE_DOUBLE
@@ -152,8 +156,8 @@ qword_align:
 	PTR_ADDU	src, src, 0x8
 	andi	t8, src, 0x10
 
-oword_align:
-	beqz	t8, begin_movement
+.Loword_align:
+	beqz	t8, .Lbegin_movement
 	 LONG_SRL	t8, a1, 0x7
 
 #ifdef USE_DOUBLE
@@ -168,51 +172,55 @@ oword_align:
 	PTR_ADDU	src, src, 0x10
 	LONG_SRL	t8, a1, 0x7
 
-begin_movement:
+.Lbegin_movement:
 	beqz	t8, 1f
 	 andi	t2, a1, 0x40
 
-move_128bytes:
+.Lmove_128bytes:
 	CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4)
 	CSUM_BIGCHUNK(src, 0x20, sum, t0, t1, t3, t4)
 	CSUM_BIGCHUNK(src, 0x40, sum, t0, t1, t3, t4)
 	CSUM_BIGCHUNK(src, 0x60, sum, t0, t1, t3, t4)
 	LONG_SUBU	t8, t8, 0x01
-	bnez	t8, move_128bytes
-	 PTR_ADDU	src, src, 0x80
+	.set	reorder				/* DADDI_WAR */
+	PTR_ADDU	src, src, 0x80
+	bnez	t8, .Lmove_128bytes
+	.set	noreorder
 
 1:
 	beqz	t2, 1f
 	 andi	t2, a1, 0x20
 
-move_64bytes:
+.Lmove_64bytes:
 	CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4)
 	CSUM_BIGCHUNK(src, 0x20, sum, t0, t1, t3, t4)
 	PTR_ADDU	src, src, 0x40
 
 1:
-	beqz	t2, do_end_words
+	beqz	t2, .Ldo_end_words
 	 andi	t8, a1, 0x1c
 
-move_32bytes:
+.Lmove_32bytes:
 	CSUM_BIGCHUNK(src, 0x00, sum, t0, t1, t3, t4)
 	andi	t8, a1, 0x1c
 	PTR_ADDU	src, src, 0x20
 
-do_end_words:
-	beqz	t8, small_csumcpy
+.Ldo_end_words:
+	beqz	t8, .Lsmall_csumcpy
 	 andi	t2, a1, 0x3
 	LONG_SRL	t8, t8, 0x2
 
-end_words:
+.Lend_words:
 	lw	t0, (src)
 	LONG_SUBU	t8, t8, 0x1
 	ADDC(sum, t0)
-	bnez	t8, end_words
-	 PTR_ADDU	src, src, 0x4
+	.set	reorder				/* DADDI_WAR */
+	PTR_ADDU	src, src, 0x4
+	bnez	t8, .Lend_words
+	.set	noreorder
 
 /* unknown src alignment and < 8 bytes to go  */
-small_csumcpy:
+.Lsmall_csumcpy:
 	move	a1, t2
 
 	andi	t0, a1, 4
@@ -246,6 +254,8 @@ small_csumcpy:
 1:	ADDC(sum, t1)
 
 	/* fold checksum */
+	.set	push
+	.set	noat
 #ifdef USE_DOUBLE
 	dsll32	v1, sum, 0
 	daddu	sum, v1
@@ -266,6 +276,7 @@ small_csumcpy:
 	srl	sum, sum, 8
 	or	sum, v1
 	andi	sum, 0xffff
+	.set	pop
 1:
 	.set	reorder
 	/* Add the passed partial csum.  */
@@ -373,7 +384,11 @@ small_csumcpy:
 
 #define ADDRMASK (NBYTES-1)
 
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
 	.set	noat
+#else
+	.set	at=v1
+#endif
 
 LEAF(__csum_partial_copy_user)
 	PTR_ADDU	AT, src, len	/* See (1) above. */
@@ -398,95 +413,101 @@ FEXPORT(csum_partial_copy_nocheck)
 	 */
 	sltu	t2, len, NBYTES
 	and	t1, dst, ADDRMASK
-	bnez	t2, copy_bytes_checklen
+	bnez	t2, .Lcopy_bytes_checklen
 	 and	t0, src, ADDRMASK
 	andi	odd, dst, 0x1			/* odd buffer? */
-	bnez	t1, dst_unaligned
+	bnez	t1, .Ldst_unaligned
 	 nop
-	bnez	t0, src_unaligned_dst_aligned
+	bnez	t0, .Lsrc_unaligned_dst_aligned
 	/*
 	 * use delay slot for fall-through
 	 * src and dst are aligned; need to compute rem
 	 */
-both_aligned:
+.Lboth_aligned:
 	 SRL	t0, len, LOG_NBYTES+3    # +3 for 8 units/iter
-	beqz	t0, cleanup_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),	l_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
-EXC(	LOAD	t4, UNIT(4)(src),	l_exc_copy)
-EXC(	LOAD	t5, UNIT(5)(src),	l_exc_copy)
-EXC(	LOAD	t6, UNIT(6)(src),	l_exc_copy)
-EXC(	LOAD	t7, UNIT(7)(src),	l_exc_copy)
+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)
 	SUB	len, len, 8*NBYTES
 	ADD	src, src, 8*NBYTES
-EXC(	STORE	t0, UNIT(0)(dst),	s_exc)
+EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc)
 	ADDC(sum, t0)
-EXC(	STORE	t1, UNIT(1)(dst),	s_exc)
+EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc)
 	ADDC(sum, t1)
-EXC(	STORE	t2, UNIT(2)(dst),	s_exc)
+EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc)
 	ADDC(sum, t2)
-EXC(	STORE	t3, UNIT(3)(dst),	s_exc)
+EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc)
 	ADDC(sum, t3)
-EXC(	STORE	t4, UNIT(4)(dst),	s_exc)
+EXC(	STORE	t4, UNIT(4)(dst),	.Ls_exc)
 	ADDC(sum, t4)
-EXC(	STORE	t5, UNIT(5)(dst),	s_exc)
+EXC(	STORE	t5, UNIT(5)(dst),	.Ls_exc)
 	ADDC(sum, t5)
-EXC(	STORE	t6, UNIT(6)(dst),	s_exc)
+EXC(	STORE	t6, UNIT(6)(dst),	.Ls_exc)
 	ADDC(sum, t6)
-EXC(	STORE	t7, UNIT(7)(dst),	s_exc)
+EXC(	STORE	t7, UNIT(7)(dst),	.Ls_exc)
 	ADDC(sum, t7)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 8*NBYTES
 	bgez	len, 1b
-	 ADD	dst, dst, 8*NBYTES
+	.set	noreorder
 	ADD	len, 8*NBYTES		# revert len (see above)
 
 	/*
 	 * len == the number of bytes left to copy < 8*NBYTES
 	 */
-cleanup_both_aligned:
+.Lcleanup_both_aligned:
 #define rem t7
-	beqz	len, done
+	beqz	len, .Ldone
 	 sltu	t0, len, 4*NBYTES
-	bnez	t0, less_than_4units
+	bnez	t0, .Lless_than_4units
 	 and	rem, len, (NBYTES-1)	# rem = len % NBYTES
 	/*
 	 * len >= 4*NBYTES
 	 */
-EXC(	LOAD	t0, UNIT(0)(src),	l_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
+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)
 	SUB	len, len, 4*NBYTES
 	ADD	src, src, 4*NBYTES
-EXC(	STORE	t0, UNIT(0)(dst),	s_exc)
+EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc)
 	ADDC(sum, t0)
-EXC(	STORE	t1, UNIT(1)(dst),	s_exc)
+EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc)
 	ADDC(sum, t1)
-EXC(	STORE	t2, UNIT(2)(dst),	s_exc)
+EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc)
 	ADDC(sum, t2)
-EXC(	STORE	t3, UNIT(3)(dst),	s_exc)
+EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc)
 	ADDC(sum, t3)
-	beqz	len, done
-	 ADD	dst, dst, 4*NBYTES
-less_than_4units:
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 4*NBYTES
+	beqz	len, .Ldone
+	.set	noreorder
+.Lless_than_4units:
 	/*
 	 * rem = len % NBYTES
 	 */
-	beq	rem, len, copy_bytes
+	beq	rem, len, .Lcopy_bytes
 	 nop
 1:
-EXC(	LOAD	t0, 0(src),		l_exc)
+EXC(	LOAD	t0, 0(src),		.Ll_exc)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		s_exc)
+EXC(	STORE	t0, 0(dst),		.Ls_exc)
 	ADDC(sum, t0)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, NBYTES
 	bne	rem, len, 1b
-	 ADD	dst, dst, NBYTES
+	.set	noreorder
 
 	/*
 	 * src and dst are aligned, need to copy rem bytes (rem < NBYTES)
@@ -500,20 +521,20 @@ EXC(	STORE	t0, 0(dst),		s_exc)
 	 * more instruction-level parallelism.
 	 */
 #define bits t2
-	beqz	len, done
+	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),		l_exc)
+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),		s_exc)
+EXC(	STREST	t0, -1(t1),		.Ls_exc)
 	SHIFT_DISCARD_REVERT t0, t0, bits
 	.set reorder
 	ADDC(sum, t0)
-	b	done
+	b	.Ldone
 	.set noreorder
-dst_unaligned:
+.Ldst_unaligned:
 	/*
 	 * dst is unaligned
 	 * t0 = src & ADDRMASK
@@ -524,25 +545,25 @@ dst_unaligned:
 	 * Set match = (src and dst have same alignment)
 	 */
 #define match rem
-EXC(	LDFIRST	t3, FIRST(0)(src),	l_exc)
+EXC(	LDFIRST	t3, FIRST(0)(src),	.Ll_exc)
 	ADD	t2, zero, NBYTES
-EXC(	LDREST	t3, REST(0)(src),	l_exc_copy)
+EXC(	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),	s_exc)
+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, done
+	beq	len, t2, .Ldone
 	 SUB	len, len, t2
 	ADD	dst, dst, t2
-	beqz	match, both_aligned
+	beqz	match, .Lboth_aligned
 	 ADD	src, src, t2
 
-src_unaligned_dst_aligned:
+.Lsrc_unaligned_dst_aligned:
 	SRL	t0, len, LOG_NBYTES+2    # +2 for 4 units/iter
-	beqz	t0, cleanup_src_unaligned
+	beqz	t0, .Lcleanup_src_unaligned
 	 and	rem, len, (4*NBYTES-1)   # rem = len % 4*NBYTES
 1:
 /*
@@ -551,49 +572,53 @@ src_unaligned_dst_aligned:
  * 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),	l_exc)
-EXC(	LDFIRST	t1, FIRST(1)(src),	l_exc_copy)
+EXC(	LDFIRST	t0, FIRST(0)(src),	.Ll_exc)
+EXC(	LDFIRST	t1, FIRST(1)(src),	.Ll_exc_copy)
 	SUB     len, len, 4*NBYTES
-EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
-EXC(	LDREST	t1, REST(1)(src),	l_exc_copy)
-EXC(	LDFIRST	t2, FIRST(2)(src),	l_exc_copy)
-EXC(	LDFIRST	t3, FIRST(3)(src),	l_exc_copy)
-EXC(	LDREST	t2, REST(2)(src),	l_exc_copy)
-EXC(	LDREST	t3, REST(3)(src),	l_exc_copy)
+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)
 	ADD	src, src, 4*NBYTES
 #ifdef CONFIG_CPU_SB1
 	nop				# improves slotting
 #endif
-EXC(	STORE	t0, UNIT(0)(dst),	s_exc)
+EXC(	STORE	t0, UNIT(0)(dst),	.Ls_exc)
 	ADDC(sum, t0)
-EXC(	STORE	t1, UNIT(1)(dst),	s_exc)
+EXC(	STORE	t1, UNIT(1)(dst),	.Ls_exc)
 	ADDC(sum, t1)
-EXC(	STORE	t2, UNIT(2)(dst),	s_exc)
+EXC(	STORE	t2, UNIT(2)(dst),	.Ls_exc)
 	ADDC(sum, t2)
-EXC(	STORE	t3, UNIT(3)(dst),	s_exc)
+EXC(	STORE	t3, UNIT(3)(dst),	.Ls_exc)
 	ADDC(sum, t3)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 4*NBYTES
 	bne	len, rem, 1b
-	 ADD	dst, dst, 4*NBYTES
+	.set	noreorder
 
-cleanup_src_unaligned:
-	beqz	len, done
+.Lcleanup_src_unaligned:
+	beqz	len, .Ldone
 	 and	rem, len, NBYTES-1  # rem = len % NBYTES
-	beq	rem, len, copy_bytes
+	beq	rem, len, .Lcopy_bytes
 	 nop
 1:
-EXC(	LDFIRST t0, FIRST(0)(src),	l_exc)
-EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
+EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
+EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		s_exc)
+EXC(	STORE	t0, 0(dst),		.Ls_exc)
 	ADDC(sum, t0)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, NBYTES
 	bne	len, rem, 1b
-	 ADD	dst, dst, NBYTES
+	.set	noreorder
 
-copy_bytes_checklen:
-	beqz	len, done
+.Lcopy_bytes_checklen:
+	beqz	len, .Ldone
 	 nop
-copy_bytes:
+.Lcopy_bytes:
 	/* 0 < len < NBYTES  */
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 #define SHIFT_START 0
@@ -604,14 +629,14 @@ copy_bytes:
 #endif
 	move	t2, zero	# partial word
 	li	t3, SHIFT_START	# shift
-/* use l_exc_copy here to return correct sum on fault */
+/* use .Ll_exc_copy here to return correct sum on fault */
 #define COPY_BYTE(N)			\
-EXC(	lbu	t0, N(src), l_exc_copy);	\
+EXC(	lbu	t0, N(src), .Ll_exc_copy);	\
 	SUB	len, len, 1;		\
-EXC(	sb	t0, N(dst), s_exc);	\
+EXC(	sb	t0, N(dst), .Ls_exc);	\
 	SLLV	t0, t0, t3;		\
 	addu	t3, SHIFT_INC;		\
-	beqz	len, copy_bytes_done;	\
+	beqz	len, .Lcopy_bytes_done;	\
 	 or	t2, t0
 
 	COPY_BYTE(0)
@@ -622,15 +647,17 @@ EXC(	sb	t0, N(dst), s_exc);	\
 	COPY_BYTE(4)
 	COPY_BYTE(5)
 #endif
-EXC(	lbu	t0, NBYTES-2(src), l_exc_copy)
+EXC(	lbu	t0, NBYTES-2(src), .Ll_exc_copy)
 	SUB	len, len, 1
-EXC(	sb	t0, NBYTES-2(dst), s_exc)
+EXC(	sb	t0, NBYTES-2(dst), .Ls_exc)
 	SLLV	t0, t0, t3
 	or	t2, t0
-copy_bytes_done:
+.Lcopy_bytes_done:
 	ADDC(sum, t2)
-done:
+.Ldone:
 	/* fold checksum */
+	.set	push
+	.set	noat
 #ifdef USE_DOUBLE
 	dsll32	v1, sum, 0
 	daddu	sum, v1
@@ -651,13 +678,14 @@ done:
 	srl	sum, sum, 8
 	or	sum, v1
 	andi	sum, 0xffff
+	.set	pop
 1:
 	.set reorder
 	ADDC(sum, psum)
 	jr	ra
 	.set noreorder
 
-l_exc_copy:
+.Ll_exc_copy:
 	/*
 	 * Copy bytes from src until faulting load address (or until a
 	 * lb faults)
@@ -672,15 +700,17 @@ l_exc_copy:
 	 li	t2, SHIFT_START
 	LOAD	t0, THREAD_BUADDR(t0)
 1:
-EXC(	lbu	t1, 0(src),	l_exc)
+EXC(	lbu	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
 	addu	t2, SHIFT_INC
 	ADDC(sum, t1)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 1
 	bne	src, t0, 1b
-	 ADD	dst, dst, 1
-l_exc:
+	.set	noreorder
+.Ll_exc:
 	LOAD	t0, TI_TASK($28)
 	 nop
 	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
@@ -697,19 +727,30 @@ l_exc:
 	 * Clear len bytes starting at dst.  Can't call __bzero because it
 	 * might modify len.  An inefficient loop for these rare times...
 	 */
-	beqz	len, done
-	 SUB	src, len, 1
+	.set	reorder				/* DADDI_WAR */
+	SUB	src, len, 1
+	beqz	len, .Ldone
+	.set	noreorder
 1:	sb	zero, 0(dst)
 	ADD	dst, dst, 1
+	.set	push
+	.set	noat
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
 	bnez	src, 1b
 	 SUB	src, src, 1
+#else
+	li	v1, 1
+	bnez	src, 1b
+	 SUB	src, src, v1
+#endif
 	li	v1, -EFAULT
-	b	done
+	b	.Ldone
 	 sw	v1, (errptr)
 
-s_exc:
+.Ls_exc:
 	li	v0, -1 /* invalid checksum */
 	li	v1, -EFAULT
 	jr	ra
 	 sw	v1, (errptr)
+	.set	pop
 	END(__csum_partial_copy_user)
diff --git a/arch/mips/lib/memcpy-inatomic.S b/arch/mips/lib/memcpy-inatomic.S
index 3a534b2baa0..736d0fb56a9 100644
--- a/arch/mips/lib/memcpy-inatomic.S
+++ b/arch/mips/lib/memcpy-inatomic.S
@@ -9,6 +9,7 @@
  * Copyright (C) 1999, 2000, 01, 2002 Silicon Graphics, Inc.
  * Copyright (C) 2002 Broadcom, Inc.
  *   memcpy/copy_user author: Mark Vandevoorde
+ * Copyright (C) 2007  Maciej W. Rozycki
  *
  * Mnemonic names for arguments to memcpy/__copy_user
  */
@@ -175,7 +176,11 @@
 
 	.text
 	.set	noreorder
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
 	.set	noat
+#else
+	.set	at=v1
+#endif
 
 /*
  * A combined memcpy/__copy_user
@@ -204,36 +209,36 @@ LEAF(__copy_user_inatomic)
 	and	t1, dst, ADDRMASK
 	PREF(	0, 1*32(src) )
 	PREF(	1, 1*32(dst) )
-	bnez	t2, copy_bytes_checklen
+	bnez	t2, .Lcopy_bytes_checklen
 	 and	t0, src, ADDRMASK
 	PREF(	0, 2*32(src) )
 	PREF(	1, 2*32(dst) )
-	bnez	t1, dst_unaligned
+	bnez	t1, .Ldst_unaligned
 	 nop
-	bnez	t0, src_unaligned_dst_aligned
+	bnez	t0, .Lsrc_unaligned_dst_aligned
 	/*
 	 * use delay slot for fall-through
 	 * src and dst are aligned; need to compute rem
 	 */
-both_aligned:
-	 SRL	t0, len, LOG_NBYTES+3    # +3 for 8 units/iter
-	beqz	t0, cleanup_both_aligned # len < 8*NBYTES
-	 and	rem, len, (8*NBYTES-1)	 # rem = len % (8*NBYTES)
+.Lboth_aligned:
+	 SRL	t0, len, LOG_NBYTES+3    	# +3 for 8 units/iter
+	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) )
 	.align	4
 1:
-EXC(	LOAD	t0, UNIT(0)(src),	l_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
+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)
 	SUB	len, len, 8*NBYTES
-EXC(	LOAD	t4, UNIT(4)(src),	l_exc_copy)
-EXC(	LOAD	t7, UNIT(5)(src),	l_exc_copy)
+EXC(	LOAD	t4, UNIT(4)(src),	.Ll_exc_copy)
+EXC(	LOAD	t7, UNIT(5)(src),	.Ll_exc_copy)
 	STORE	t0, UNIT(0)(dst)
 	STORE	t1, UNIT(1)(dst)
-EXC(	LOAD	t0, UNIT(6)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(7)(src),	l_exc_copy)
+EXC(	LOAD	t0, UNIT(6)(src),	.Ll_exc_copy)
+EXC(	LOAD	t1, UNIT(7)(src),	.Ll_exc_copy)
 	ADD	src, src, 8*NBYTES
 	ADD	dst, dst, 8*NBYTES
 	STORE	t2, UNIT(-6)(dst)
@@ -250,39 +255,43 @@ EXC(	LOAD	t1, UNIT(7)(src),	l_exc_copy)
 	/*
 	 * len == rem == the number of bytes left to copy < 8*NBYTES
 	 */
-cleanup_both_aligned:
-	beqz	len, done
+.Lcleanup_both_aligned:
+	beqz	len, .Ldone
 	 sltu	t0, len, 4*NBYTES
-	bnez	t0, less_than_4units
+	bnez	t0, .Lless_than_4units
 	 and	rem, len, (NBYTES-1)	# rem = len % NBYTES
 	/*
 	 * len >= 4*NBYTES
 	 */
-EXC(	LOAD	t0, UNIT(0)(src),	l_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
+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)
 	SUB	len, len, 4*NBYTES
 	ADD	src, src, 4*NBYTES
 	STORE	t0, UNIT(0)(dst)
 	STORE	t1, UNIT(1)(dst)
 	STORE	t2, UNIT(2)(dst)
 	STORE	t3, UNIT(3)(dst)
-	beqz	len, done
-	 ADD	dst, dst, 4*NBYTES
-less_than_4units:
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 4*NBYTES
+	beqz	len, .Ldone
+	.set	noreorder
+.Lless_than_4units:
 	/*
 	 * rem = len % NBYTES
 	 */
-	beq	rem, len, copy_bytes
+	beq	rem, len, .Lcopy_bytes
 	 nop
 1:
-EXC(	LOAD	t0, 0(src),		l_exc)
+EXC(	LOAD	t0, 0(src),		.Ll_exc)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
 	STORE	t0, 0(dst)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, NBYTES
 	bne	rem, len, 1b
-	 ADD	dst, dst, NBYTES
+	.set	noreorder
 
 	/*
 	 * src and dst are aligned, need to copy rem bytes (rem < NBYTES)
@@ -296,17 +305,17 @@ EXC(	LOAD	t0, 0(src),		l_exc)
 	 * more instruction-level parallelism.
 	 */
 #define bits t2
-	beqz	len, done
+	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),		l_exc)
+EXC(	LOAD	t0, 0(src),		.Ll_exc)
 	SUB	bits, bits, rem	# bits = number of bits to discard
 	SHIFT_DISCARD t0, t0, bits
 	STREST	t0, -1(t1)
 	jr	ra
 	 move	len, zero
-dst_unaligned:
+.Ldst_unaligned:
 	/*
 	 * dst is unaligned
 	 * t0 = src & ADDRMASK
@@ -317,22 +326,22 @@ dst_unaligned:
 	 * Set match = (src and dst have same alignment)
 	 */
 #define match rem
-EXC(	LDFIRST	t3, FIRST(0)(src),	l_exc)
+EXC(	LDFIRST	t3, FIRST(0)(src),	.Ll_exc)
 	ADD	t2, zero, NBYTES
-EXC(	LDREST	t3, REST(0)(src),	l_exc_copy)
+EXC(	LDREST	t3, REST(0)(src),	.Ll_exc_copy)
 	SUB	t2, t2, t1	# t2 = number of bytes copied
 	xor	match, t0, t1
 	STFIRST t3, FIRST(0)(dst)
-	beq	len, t2, done
+	beq	len, t2, .Ldone
 	 SUB	len, len, t2
 	ADD	dst, dst, t2
-	beqz	match, both_aligned
+	beqz	match, .Lboth_aligned
 	 ADD	src, src, t2
 
-src_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, cleanup_src_unaligned
+	beqz	t0, .Lcleanup_src_unaligned
 	 and	rem, len, (4*NBYTES-1)   # rem = len % 4*NBYTES
 	PREF(	1, 3*32(dst) )
 1:
@@ -342,15 +351,15 @@ src_unaligned_dst_aligned:
  * 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),	l_exc)
-EXC(	LDFIRST	t1, FIRST(1)(src),	l_exc_copy)
+EXC(	LDFIRST	t0, FIRST(0)(src),	.Ll_exc)
+EXC(	LDFIRST	t1, FIRST(1)(src),	.Ll_exc_copy)
 	SUB     len, len, 4*NBYTES
-EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
-EXC(	LDREST	t1, REST(1)(src),	l_exc_copy)
-EXC(	LDFIRST	t2, FIRST(2)(src),	l_exc_copy)
-EXC(	LDFIRST	t3, FIRST(3)(src),	l_exc_copy)
-EXC(	LDREST	t2, REST(2)(src),	l_exc_copy)
-EXC(	LDREST	t3, REST(3)(src),	l_exc_copy)
+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)
 	ADD	src, src, 4*NBYTES
 #ifdef CONFIG_CPU_SB1
@@ -361,32 +370,36 @@ EXC(	LDREST	t3, REST(3)(src),	l_exc_copy)
 	STORE	t2, UNIT(2)(dst)
 	STORE	t3, UNIT(3)(dst)
 	PREF(	1, 9*32(dst) )     	# 1 is PREF_STORE (not streamed)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 4*NBYTES
 	bne	len, rem, 1b
-	 ADD	dst, dst, 4*NBYTES
+	.set	noreorder
 
-cleanup_src_unaligned:
-	beqz	len, done
+.Lcleanup_src_unaligned:
+	beqz	len, .Ldone
 	 and	rem, len, NBYTES-1  # rem = len % NBYTES
-	beq	rem, len, copy_bytes
+	beq	rem, len, .Lcopy_bytes
 	 nop
 1:
-EXC(	LDFIRST t0, FIRST(0)(src),	l_exc)
-EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
+EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
+EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
 	STORE	t0, 0(dst)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, NBYTES
 	bne	len, rem, 1b
-	 ADD	dst, dst, NBYTES
+	.set	noreorder
 
-copy_bytes_checklen:
-	beqz	len, done
+.Lcopy_bytes_checklen:
+	beqz	len, .Ldone
 	 nop
-copy_bytes:
+.Lcopy_bytes:
 	/* 0 < len < NBYTES  */
 #define COPY_BYTE(N)			\
-EXC(	lb	t0, N(src), l_exc);	\
+EXC(	lb	t0, N(src), .Ll_exc);	\
 	SUB	len, len, 1;		\
-	beqz	len, done;		\
+	beqz	len, .Ldone;		\
 	 sb	t0, N(dst)
 
 	COPY_BYTE(0)
@@ -397,16 +410,16 @@ EXC(	lb	t0, N(src), l_exc);	\
 	COPY_BYTE(4)
 	COPY_BYTE(5)
 #endif
-EXC(	lb	t0, NBYTES-2(src), l_exc)
+EXC(	lb	t0, NBYTES-2(src), .Ll_exc)
 	SUB	len, len, 1
 	jr	ra
 	 sb	t0, NBYTES-2(dst)
-done:
+.Ldone:
 	jr	ra
 	 nop
 	END(__copy_user_inatomic)
 
-l_exc_copy:
+.Ll_exc_copy:
 	/*
 	 * Copy bytes from src until faulting load address (or until a
 	 * lb faults)
@@ -421,12 +434,14 @@ l_exc_copy:
 	 nop
 	LOAD	t0, THREAD_BUADDR(t0)
 1:
-EXC(	lb	t1, 0(src),	l_exc)
+EXC(	lb	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
-	 ADD	dst, dst, 1
-l_exc:
+	.set	noreorder
+.Ll_exc:
 	LOAD	t0, TI_TASK($28)
 	 nop
 	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index a526c62cb76..c06cccf60be 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -9,6 +9,7 @@
  * Copyright (C) 1999, 2000, 01, 2002 Silicon Graphics, Inc.
  * Copyright (C) 2002 Broadcom, Inc.
  *   memcpy/copy_user author: Mark Vandevoorde
+ * Copyright (C) 2007  Maciej W. Rozycki
  *
  * Mnemonic names for arguments to memcpy/__copy_user
  */
@@ -175,7 +176,11 @@
 
 	.text
 	.set	noreorder
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
 	.set	noat
+#else
+	.set	at=v1
+#endif
 
 /*
  * A combined memcpy/__copy_user
@@ -186,7 +191,7 @@
 	.align	5
 LEAF(memcpy)					/* a0=dst a1=src a2=len */
 	move	v0, dst				/* return value */
-__memcpy:
+.L__memcpy:
 FEXPORT(__copy_user)
 	/*
 	 * Note: dst & src may be unaligned, len may be 0
@@ -194,6 +199,7 @@ FEXPORT(__copy_user)
 	 */
 #define rem t8
 
+	R10KCBARRIER(0(ra))
 	/*
 	 * The "issue break"s below are very approximate.
 	 * Issue delays for dcache fills will perturb the schedule, as will
@@ -207,44 +213,45 @@ FEXPORT(__copy_user)
 	and	t1, dst, ADDRMASK
 	PREF(	0, 1*32(src) )
 	PREF(	1, 1*32(dst) )
-	bnez	t2, copy_bytes_checklen
+	bnez	t2, .Lcopy_bytes_checklen
 	 and	t0, src, ADDRMASK
 	PREF(	0, 2*32(src) )
 	PREF(	1, 2*32(dst) )
-	bnez	t1, dst_unaligned
+	bnez	t1, .Ldst_unaligned
 	 nop
-	bnez	t0, src_unaligned_dst_aligned
+	bnez	t0, .Lsrc_unaligned_dst_aligned
 	/*
 	 * use delay slot for fall-through
 	 * src and dst are aligned; need to compute rem
 	 */
-both_aligned:
+.Lboth_aligned:
 	 SRL	t0, len, LOG_NBYTES+3    # +3 for 8 units/iter
-	beqz	t0, cleanup_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) )
 	.align	4
 1:
-EXC(	LOAD	t0, UNIT(0)(src),	l_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
+	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)
 	SUB	len, len, 8*NBYTES
-EXC(	LOAD	t4, UNIT(4)(src),	l_exc_copy)
-EXC(	LOAD	t7, UNIT(5)(src),	l_exc_copy)
-EXC(	STORE	t0, UNIT(0)(dst),	s_exc_p8u)
-EXC(	STORE	t1, UNIT(1)(dst),	s_exc_p7u)
-EXC(	LOAD	t0, UNIT(6)(src),	l_exc_copy)
-EXC(	LOAD	t1, UNIT(7)(src),	l_exc_copy)
+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)
 	ADD	src, src, 8*NBYTES
 	ADD	dst, dst, 8*NBYTES
-EXC(	STORE	t2, UNIT(-6)(dst),	s_exc_p6u)
-EXC(	STORE	t3, UNIT(-5)(dst),	s_exc_p5u)
-EXC(	STORE	t4, UNIT(-4)(dst),	s_exc_p4u)
-EXC(	STORE	t7, UNIT(-3)(dst),	s_exc_p3u)
-EXC(	STORE	t0, UNIT(-2)(dst),	s_exc_p2u)
-EXC(	STORE	t1, UNIT(-1)(dst),	s_exc_p1u)
+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) )
 	bne	len, rem, 1b
@@ -253,39 +260,45 @@ EXC(	STORE	t1, UNIT(-1)(dst),	s_exc_p1u)
 	/*
 	 * len == rem == the number of bytes left to copy < 8*NBYTES
 	 */
-cleanup_both_aligned:
-	beqz	len, done
+.Lcleanup_both_aligned:
+	beqz	len, .Ldone
 	 sltu	t0, len, 4*NBYTES
-	bnez	t0, less_than_4units
+	bnez	t0, .Lless_than_4units
 	 and	rem, len, (NBYTES-1)	# rem = len % NBYTES
 	/*
 	 * len >= 4*NBYTES
 	 */
-EXC(	LOAD	t0, UNIT(0)(src),	l_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	l_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	l_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	l_exc_copy)
+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)
 	SUB	len, len, 4*NBYTES
 	ADD	src, src, 4*NBYTES
-EXC(	STORE	t0, UNIT(0)(dst),	s_exc_p4u)
-EXC(	STORE	t1, UNIT(1)(dst),	s_exc_p3u)
-EXC(	STORE	t2, UNIT(2)(dst),	s_exc_p2u)
-EXC(	STORE	t3, UNIT(3)(dst),	s_exc_p1u)
-	beqz	len, done
-	 ADD	dst, dst, 4*NBYTES
-less_than_4units:
+	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)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 4*NBYTES
+	beqz	len, .Ldone
+	.set	noreorder
+.Lless_than_4units:
 	/*
 	 * rem = len % NBYTES
 	 */
-	beq	rem, len, copy_bytes
+	beq	rem, len, .Lcopy_bytes
 	 nop
 1:
-EXC(	LOAD	t0, 0(src),		l_exc)
+	R10KCBARRIER(0(ra))
+EXC(	LOAD	t0, 0(src),		.Ll_exc)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		s_exc_p1u)
+EXC(	STORE	t0, 0(dst),		.Ls_exc_p1u)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, NBYTES
 	bne	rem, len, 1b
-	 ADD	dst, dst, NBYTES
+	.set	noreorder
 
 	/*
 	 * src and dst are aligned, need to copy rem bytes (rem < NBYTES)
@@ -299,17 +312,17 @@ EXC(	STORE	t0, 0(dst),		s_exc_p1u)
 	 * more instruction-level parallelism.
 	 */
 #define bits t2
-	beqz	len, done
+	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),		l_exc)
+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),		s_exc)
+EXC(	STREST	t0, -1(t1),		.Ls_exc)
 	jr	ra
 	 move	len, zero
-dst_unaligned:
+.Ldst_unaligned:
 	/*
 	 * dst is unaligned
 	 * t0 = src & ADDRMASK
@@ -320,22 +333,23 @@ dst_unaligned:
 	 * Set match = (src and dst have same alignment)
 	 */
 #define match rem
-EXC(	LDFIRST	t3, FIRST(0)(src),	l_exc)
+EXC(	LDFIRST	t3, FIRST(0)(src),	.Ll_exc)
 	ADD	t2, zero, NBYTES
-EXC(	LDREST	t3, REST(0)(src),	l_exc_copy)
+EXC(	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),	s_exc)
-	beq	len, t2, done
+	R10KCBARRIER(0(ra))
+EXC(	STFIRST t3, FIRST(0)(dst),	.Ls_exc)
+	beq	len, t2, .Ldone
 	 SUB	len, len, t2
 	ADD	dst, dst, t2
-	beqz	match, both_aligned
+	beqz	match, .Lboth_aligned
 	 ADD	src, src, t2
 
-src_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, cleanup_src_unaligned
+	beqz	t0, .Lcleanup_src_unaligned
 	 and	rem, len, (4*NBYTES-1)   # rem = len % 4*NBYTES
 	PREF(	1, 3*32(dst) )
 1:
@@ -345,52 +359,59 @@ src_unaligned_dst_aligned:
  * 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),	l_exc)
-EXC(	LDFIRST	t1, FIRST(1)(src),	l_exc_copy)
+	R10KCBARRIER(0(ra))
+EXC(	LDFIRST	t0, FIRST(0)(src),	.Ll_exc)
+EXC(	LDFIRST	t1, FIRST(1)(src),	.Ll_exc_copy)
 	SUB     len, len, 4*NBYTES
-EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
-EXC(	LDREST	t1, REST(1)(src),	l_exc_copy)
-EXC(	LDFIRST	t2, FIRST(2)(src),	l_exc_copy)
-EXC(	LDFIRST	t3, FIRST(3)(src),	l_exc_copy)
-EXC(	LDREST	t2, REST(2)(src),	l_exc_copy)
-EXC(	LDREST	t3, REST(3)(src),	l_exc_copy)
+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)
 	ADD	src, src, 4*NBYTES
 #ifdef CONFIG_CPU_SB1
 	nop				# improves slotting
 #endif
-EXC(	STORE	t0, UNIT(0)(dst),	s_exc_p4u)
-EXC(	STORE	t1, UNIT(1)(dst),	s_exc_p3u)
-EXC(	STORE	t2, UNIT(2)(dst),	s_exc_p2u)
-EXC(	STORE	t3, UNIT(3)(dst),	s_exc_p1u)
+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)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, 4*NBYTES
 	bne	len, rem, 1b
-	 ADD	dst, dst, 4*NBYTES
+	.set	noreorder
 
-cleanup_src_unaligned:
-	beqz	len, done
+.Lcleanup_src_unaligned:
+	beqz	len, .Ldone
 	 and	rem, len, NBYTES-1  # rem = len % NBYTES
-	beq	rem, len, copy_bytes
+	beq	rem, len, .Lcopy_bytes
 	 nop
 1:
-EXC(	LDFIRST t0, FIRST(0)(src),	l_exc)
-EXC(	LDREST	t0, REST(0)(src),	l_exc_copy)
+	R10KCBARRIER(0(ra))
+EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
+EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-EXC(	STORE	t0, 0(dst),		s_exc_p1u)
+EXC(	STORE	t0, 0(dst),		.Ls_exc_p1u)
+	.set	reorder				/* DADDI_WAR */
+	ADD	dst, dst, NBYTES
 	bne	len, rem, 1b
-	 ADD	dst, dst, NBYTES
+	.set	noreorder
 
-copy_bytes_checklen:
-	beqz	len, done
+.Lcopy_bytes_checklen:
+	beqz	len, .Ldone
 	 nop
-copy_bytes:
+.Lcopy_bytes:
 	/* 0 < len < NBYTES  */
+	R10KCBARRIER(0(ra))
 #define COPY_BYTE(N)			\
-EXC(	lb	t0, N(src), l_exc);	\
+EXC(	lb	t0, N(src), .Ll_exc);	\
 	SUB	len, len, 1;		\
-	beqz	len, done;		\
-EXC(	 sb	t0, N(dst), s_exc_p1)
+	beqz	len, .Ldone;		\
+EXC(	 sb	t0, N(dst), .Ls_exc_p1)
 
 	COPY_BYTE(0)
 	COPY_BYTE(1)
@@ -400,16 +421,16 @@ EXC(	 sb	t0, N(dst), s_exc_p1)
 	COPY_BYTE(4)
 	COPY_BYTE(5)
 #endif
-EXC(	lb	t0, NBYTES-2(src), l_exc)
+EXC(	lb	t0, NBYTES-2(src), .Ll_exc)
 	SUB	len, len, 1
 	jr	ra
-EXC(	 sb	t0, NBYTES-2(dst), s_exc_p1)
-done:
+EXC(	 sb	t0, NBYTES-2(dst), .Ls_exc_p1)
+.Ldone:
 	jr	ra
 	 nop
 	END(memcpy)
 
-l_exc_copy:
+.Ll_exc_copy:
 	/*
 	 * Copy bytes from src until faulting load address (or until a
 	 * lb faults)
@@ -424,12 +445,14 @@ l_exc_copy:
 	 nop
 	LOAD	t0, THREAD_BUADDR(t0)
 1:
-EXC(	lb	t1, 0(src),	l_exc)
+EXC(	lb	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
-	 ADD	dst, dst, 1
-l_exc:
+	.set	noreorder
+.Ll_exc:
 	LOAD	t0, TI_TASK($28)
 	 nop
 	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
@@ -446,20 +469,33 @@ l_exc:
 	 * Clear len bytes starting at dst.  Can't call __bzero because it
 	 * might modify len.  An inefficient loop for these rare times...
 	 */
-	beqz	len, done
-	 SUB	src, len, 1
+	.set	reorder				/* DADDI_WAR */
+	SUB	src, len, 1
+	beqz	len, .Ldone
+	.set	noreorder
 1:	sb	zero, 0(dst)
 	ADD	dst, dst, 1
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
 	bnez	src, 1b
 	 SUB	src, src, 1
+#else
+	.set	push
+	.set	noat
+	li	v1, 1
+	bnez	src, 1b
+	 SUB	src, src, v1
+	.set	pop
+#endif
 	jr	ra
 	 nop
 
 
-#define SEXC(n)				\
-s_exc_p ## n ## u:			\
-	jr	ra;			\
-	 ADD	len, len, n*NBYTES
+#define SEXC(n)							\
+	.set	reorder;			/* DADDI_WAR */	\
+.Ls_exc_p ## n ## u:						\
+	ADD	len, len, n*NBYTES;				\
+	jr	ra;						\
+	.set	noreorder
 
 SEXC(8)
 SEXC(7)
@@ -470,10 +506,12 @@ SEXC(3)
 SEXC(2)
 SEXC(1)
 
-s_exc_p1:
+.Ls_exc_p1:
+	.set	reorder				/* DADDI_WAR */
+	ADD	len, len, 1
 	jr	ra
-	 ADD	len, len, 1
-s_exc:
+	.set	noreorder
+.Ls_exc:
 	jr	ra
 	 nop
 
@@ -484,38 +522,44 @@ LEAF(memmove)
 	sltu	t0, a1, t0			# dst + len <= src -> memcpy
 	sltu	t1, a0, t1			# dst >= src + len -> memcpy
 	and	t0, t1
-	beqz	t0, __memcpy
+	beqz	t0, .L__memcpy
 	 move	v0, a0				/* return value */
-	beqz	a2, r_out
+	beqz	a2, .Lr_out
 	END(memmove)
 
 	/* fall through to __rmemcpy */
 LEAF(__rmemcpy)					/* a0=dst a1=src a2=len */
 	 sltu	t0, a1, a0
-	beqz	t0, r_end_bytes_up		# src >= dst
+	beqz	t0, .Lr_end_bytes_up		# src >= dst
 	 nop
 	ADD	a0, a2				# dst = dst + len
 	ADD	a1, a2				# src = src + len
 
-r_end_bytes:
+.Lr_end_bytes:
+	R10KCBARRIER(0(ra))
 	lb	t0, -1(a1)
 	SUB	a2, a2, 0x1
 	sb	t0, -1(a0)
 	SUB	a1, a1, 0x1
-	bnez	a2, r_end_bytes
-	 SUB	a0, a0, 0x1
+	.set	reorder				/* DADDI_WAR */
+	SUB	a0, a0, 0x1
+	bnez	a2, .Lr_end_bytes
+	.set	noreorder
 
-r_out:
+.Lr_out:
 	jr	ra
 	 move	a2, zero
 
-r_end_bytes_up:
+.Lr_end_bytes_up:
+	R10KCBARRIER(0(ra))
 	lb	t0, (a1)
 	SUB	a2, a2, 0x1
 	sb	t0, (a0)
 	ADD	a1, a1, 0x1
-	bnez	a2, r_end_bytes_up
-	 ADD	a0, a0, 0x1
+	.set	reorder				/* DADDI_WAR */
+	ADD	a0, a0, 0x1
+	bnez	a2, .Lr_end_bytes_up
+	.set	noreorder
 
 	jr	ra
 	 move	a2, zero
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 3f8b8b3d0b2..77dc3b20110 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 1998, 1999, 2000 by Ralf Baechle
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2007  Maciej W. Rozycki
  */
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
@@ -71,34 +72,45 @@ LEAF(memset)
 
 FEXPORT(__bzero)
 	sltiu		t0, a2, LONGSIZE	/* very small region? */
-	bnez		t0, small_memset
+	bnez		t0, .Lsmall_memset
 	 andi		t0, a0, LONGMASK	/* aligned? */
 
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
 	beqz		t0, 1f
 	 PTR_SUBU	t0, LONGSIZE		/* alignment in bytes */
+#else
+	.set		noat
+	li		AT, LONGSIZE
+	beqz		t0, 1f
+	 PTR_SUBU	t0, AT			/* alignment in bytes */
+	.set		at
+#endif
 
+	R10KCBARRIER(0(ra))
 #ifdef __MIPSEB__
-	EX(LONG_S_L, a1, (a0), first_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), first_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, memset_partial	/* no block to fill */
+	beqz		t1, .Lmemset_partial	/* no block to fill */
 	 andi		t0, a2, 0x40-LONGSIZE
 
 	PTR_ADDU	t1, a0			/* end address */
 	.set		reorder
 1:	PTR_ADDIU	a0, 64
-	f_fill64 a0, -64, a1, fwd_fixup
+	R10KCBARRIER(0(ra))
+	f_fill64 a0, -64, a1, .Lfwd_fixup
 	bne		t1, a0, 1b
 	.set		noreorder
 
-memset_partial:
+.Lmemset_partial:
+	R10KCBARRIER(0(ra))
 	PTR_LA		t1, 2f			/* where to start */
 #if LONGSIZE == 4
 	PTR_SUBU	t1, t0
@@ -106,7 +118,7 @@ memset_partial:
 	.set		noat
 	LONG_SRL		AT, t0, 1
 	PTR_SUBU	t1, AT
-	.set		noat
+	.set		at
 #endif
 	jr		t1
 	 PTR_ADDU	a0, t0			/* dest ptr */
@@ -114,26 +126,28 @@ memset_partial:
 	.set		push
 	.set		noreorder
 	.set		nomacro
-	f_fill64 a0, -64, a1, partial_fixup	/* ... but first do longs ... */
+	f_fill64 a0, -64, a1, .Lpartial_fixup	/* ... but first do longs ... */
 2:	.set		pop
 	andi		a2, LONGMASK		/* At most one long to go */
 
 	beqz		a2, 1f
 	 PTR_ADDU	a0, a2			/* What's left */
+	R10KCBARRIER(0(ra))
 #ifdef __MIPSEB__
-	EX(LONG_S_R, a1, -1(a0), last_fixup)
+	EX(LONG_S_R, a1, -1(a0), .Llast_fixup)
 #endif
 #ifdef __MIPSEL__
-	EX(LONG_S_L, a1, -1(a0), last_fixup)
+	EX(LONG_S_L, a1, -1(a0), .Llast_fixup)
 #endif
 1:	jr		ra
 	 move		a2, zero
 
-small_memset:
+.Lsmall_memset:
 	beqz		a2, 2f
 	 PTR_ADDU	t1, a0, a2
 
 1:	PTR_ADDIU	a0, 1			/* fill bytewise */
+	R10KCBARRIER(0(ra))
 	bne		t1, a0, 1b
 	 sb		a1, -1(a0)
 
@@ -141,11 +155,11 @@ small_memset:
 	 move		a2, zero
 	END(memset)
 
-first_fixup:
+.Lfirst_fixup:
 	jr	ra
 	 nop
 
-fwd_fixup:
+.Lfwd_fixup:
 	PTR_L		t0, TI_TASK($28)
 	LONG_L		t0, THREAD_BUADDR(t0)
 	andi		a2, 0x3f
@@ -153,7 +167,7 @@ fwd_fixup:
 	jr		ra
 	 LONG_SUBU	a2, t0
 
-partial_fixup:
+.Lpartial_fixup:
 	PTR_L		t0, TI_TASK($28)
 	LONG_L		t0, THREAD_BUADDR(t0)
 	andi		a2, LONGMASK
@@ -161,6 +175,6 @@ partial_fixup:
 	jr		ra
 	 LONG_SUBU	a2, t0
 
-last_fixup:
+.Llast_fixup:
 	jr		ra
 	 andi		v1, a2, LONGMASK
diff --git a/arch/mips/lib/strlen_user.S b/arch/mips/lib/strlen_user.S
index eca558d83a3..fdbb970f670 100644
--- a/arch/mips/lib/strlen_user.S
+++ b/arch/mips/lib/strlen_user.S
@@ -24,16 +24,16 @@
 LEAF(__strlen_user_asm)
 	LONG_L		v0, TI_ADDR_LIMIT($28)	# pointer ok?
 	and		v0, a0
-	bnez		v0, fault
+	bnez		v0, .Lfault
 
 FEXPORT(__strlen_user_nocheck_asm)
 	move		v0, a0
-1:	EX(lb, t0, (v0), fault)
+1:	EX(lb, t0, (v0), .Lfault)
 	PTR_ADDIU	v0, 1
 	bnez		t0, 1b
 	PTR_SUBU	v0, a0
 	jr		ra
 	END(__strlen_user_asm)
 
-fault:	move		v0, zero
+.Lfault:	move		v0, zero
 	jr		ra
diff --git a/arch/mips/lib/strncpy_user.S b/arch/mips/lib/strncpy_user.S
index d16c76fbfac..7201b2ff08c 100644
--- a/arch/mips/lib/strncpy_user.S
+++ b/arch/mips/lib/strncpy_user.S
@@ -30,29 +30,30 @@
 LEAF(__strncpy_from_user_asm)
 	LONG_L		v0, TI_ADDR_LIMIT($28)	# pointer ok?
 	and		v0, a1
-	bnez		v0, fault
+	bnez		v0, .Lfault
 
 FEXPORT(__strncpy_from_user_nocheck_asm)
 	move		v0, zero
 	move		v1, a1
 	.set		noreorder
-1:	EX(lbu, t0, (v1), fault)
+1:	EX(lbu, t0, (v1), .Lfault)
 	PTR_ADDIU	v1, 1
+	R10KCBARRIER(0(ra))
 	beqz		t0, 2f
 	 sb		t0, (a0)
 	PTR_ADDIU	v0, 1
-	bne		v0, a2, 1b
-	 PTR_ADDIU	a0, 1
 	.set		reorder
+	PTR_ADDIU	a0, 1
+	bne		v0, a2, 1b
 2:	PTR_ADDU	t0, a1, v0
 	xor		t0, a1
-	bltz		t0, fault
+	bltz		t0, .Lfault
 	jr		ra			# return n
 	END(__strncpy_from_user_asm)
 
-fault:	li		v0, -EFAULT
+.Lfault:	li		v0, -EFAULT
 	jr		ra
 
 	.section	__ex_table,"a"
-	PTR		1b, fault
+	PTR		1b, .Lfault
 	.previous
diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S
index c0ea15194a0..c768e300061 100644
--- a/arch/mips/lib/strnlen_user.S
+++ b/arch/mips/lib/strnlen_user.S
@@ -28,18 +28,19 @@
 LEAF(__strnlen_user_asm)
 	LONG_L		v0, TI_ADDR_LIMIT($28)	# pointer ok?
 	and		v0, a0
-	bnez		v0, fault
+	bnez		v0, .Lfault
 
 FEXPORT(__strnlen_user_nocheck_asm)
 	move		v0, a0
 	PTR_ADDU	a1, a0			# stop pointer
 1:	beq		v0, a1, 1f		# limit reached?
-	EX(lb, t0, (v0), fault)
+	EX(lb, t0, (v0), .Lfault)
 	PTR_ADDU	v0, 1
 	bnez		t0, 1b
 1:	PTR_SUBU	v0, a0
 	jr		ra
 	END(__strnlen_user_asm)
 
-fault:	move		v0, zero
+.Lfault:
+	move		v0, zero
 	jr		ra
diff --git a/arch/mips/lib/uncached.c b/arch/mips/lib/uncached.c
index 58d14f4d934..27b012d4341 100644
--- a/arch/mips/lib/uncached.c
+++ b/arch/mips/lib/uncached.c
@@ -46,9 +46,9 @@ unsigned long __init run_uncached(void *func)
 	if (sp >= (long)CKSEG0 && sp < (long)CKSEG2)
 		usp = CKSEG1ADDR(sp);
 #ifdef CONFIG_64BIT
-	else if ((long long)sp >= (long long)PHYS_TO_XKPHYS(0LL, 0) &&
-		 (long long)sp < (long long)PHYS_TO_XKPHYS(8LL, 0))
-		usp = PHYS_TO_XKPHYS((long long)K_CALG_UNCACHED,
+	else if ((long long)sp >= (long long)PHYS_TO_XKPHYS(0, 0) &&
+		 (long long)sp < (long long)PHYS_TO_XKPHYS(8, 0))
+		usp = PHYS_TO_XKPHYS(K_CALG_UNCACHED,
 				     XKPHYS_TO_PHYS((long long)sp));
 #endif
 	else {
@@ -58,9 +58,9 @@ unsigned long __init run_uncached(void *func)
 	if (lfunc >= (long)CKSEG0 && lfunc < (long)CKSEG2)
 		ufunc = CKSEG1ADDR(lfunc);
 #ifdef CONFIG_64BIT
-	else if ((long long)lfunc >= (long long)PHYS_TO_XKPHYS(0LL, 0) &&
-		 (long long)lfunc < (long long)PHYS_TO_XKPHYS(8LL, 0))
-		ufunc = PHYS_TO_XKPHYS((long long)K_CALG_UNCACHED,
+	else if ((long long)lfunc >= (long long)PHYS_TO_XKPHYS(0, 0) &&
+		 (long long)lfunc < (long long)PHYS_TO_XKPHYS(8, 0))
+		ufunc = PHYS_TO_XKPHYS(K_CALG_UNCACHED,
 				       XKPHYS_TO_PHYS((long long)lfunc));
 #endif
 	else {