4 files changed, 72 insertions, 1 deletions

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