[MIPS] Unify memset.S

The 32-bit version and 64-bit version are almost equal.  Unify them.
This makes further improvements (for example, supporting CDEX, etc.)
easier.

Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

1 files changed, 166 insertions, 0 deletions

diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
new file mode 100644
index 00000000000..3f8b8b3d0b2
--- /dev/null
+++ b/arch/mips/lib/memset.S
@@ -0,0 +1,166 @@
+/*
+ * 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) 1998, 1999, 2000 by Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ */
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/regdef.h>
+
+#if LONGSIZE == 4
+#define LONG_S_L swl
+#define LONG_S_R swr
+#else
+#define LONG_S_L sdl
+#define LONG_S_R sdr
+#endif
+
+#define EX(insn,reg,addr,handler)			\
+9:	insn	reg, addr;				\
+	.section __ex_table,"a"; 			\
+	PTR	9b, handler; 				\
+	.previous
+
+	.macro	f_fill64 dst, offset, val, fixup
+	EX(LONG_S, \val, (\offset +  0 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  1 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  2 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  3 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  4 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  5 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  6 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  7 * LONGSIZE)(\dst), \fixup)
+#if LONGSIZE == 4
+	EX(LONG_S, \val, (\offset +  8 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset +  9 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset + 10 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset + 11 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset + 12 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset + 13 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset + 14 * LONGSIZE)(\dst), \fixup)
+	EX(LONG_S, \val, (\offset + 15 * LONGSIZE)(\dst), \fixup)
+#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:
+
+FEXPORT(__bzero)
+	sltiu		t0, a2, LONGSIZE	/* very small region? */
+	bnez		t0, small_memset
+	 andi		t0, a0, LONGMASK	/* aligned? */
+
+	beqz		t0, 1f
+	 PTR_SUBU	t0, LONGSIZE		/* alignment in bytes */
+
+#ifdef __MIPSEB__
+	EX(LONG_S_L, a1, (a0), first_fixup)	/* make word/dword aligned */
+#endif
+#ifdef __MIPSEL__
+	EX(LONG_S_R, a1, (a0), first_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 */
+	 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
+	bne		t1, a0, 1b
+	.set		noreorder
+
+memset_partial:
+	PTR_LA		t1, 2f			/* where to start */
+#if LONGSIZE == 4
+	PTR_SUBU	t1, t0
+#else
+	.set		noat
+	LONG_SRL		AT, t0, 1
+	PTR_SUBU	t1, AT
+	.set		noat
+#endif
+	jr		t1
+	 PTR_ADDU	a0, t0			/* dest ptr */
+
+	.set		push
+	.set		noreorder
+	.set		nomacro
+	f_fill64 a0, -64, a1, partial_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 */
+#ifdef __MIPSEB__
+	EX(LONG_S_R, a1, -1(a0), last_fixup)
+#endif
+#ifdef __MIPSEL__
+	EX(LONG_S_L, a1, -1(a0), last_fixup)
+#endif
+1:	jr		ra
+	 move		a2, zero
+
+small_memset:
+	beqz		a2, 2f
+	 PTR_ADDU	t1, a0, a2
+
+1:	PTR_ADDIU	a0, 1			/* fill bytewise */
+	bne		t1, a0, 1b
+	 sb		a1, -1(a0)
+
+2:	jr		ra			/* done */
+	 move		a2, zero
+	END(memset)
+
+first_fixup:
+	jr	ra
+	 nop
+
+fwd_fixup:
+	PTR_L		t0, TI_TASK($28)
+	LONG_L		t0, THREAD_BUADDR(t0)
+	andi		a2, 0x3f
+	LONG_ADDU	a2, t1
+	jr		ra
+	 LONG_SUBU	a2, t0
+
+partial_fixup:
+	PTR_L		t0, TI_TASK($28)
+	LONG_L		t0, THREAD_BUADDR(t0)
+	andi		a2, LONGMASK
+	LONG_ADDU	a2, t1
+	jr		ra
+	 LONG_SUBU	a2, t0
+
+last_fixup:
+	jr		ra
+	 andi		v1, a2, LONGMASK