Subversion Repositories or1k

/*
 * 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 by Ralf Baechle
 */
#include <asm/asm.h>
#include <asm/offset.h>
#include <asm/regdef.h>

#define EX(insn,reg,addr,handler)                       \
9:      insn    reg, addr;                              \
        .section __ex_table,"a";                        \
        PTR     9b, handler;                            \
        .previous

#define F_FILL64(dst, offset, val, fixup)               \
        EX(sw, val, (offset + 0x00)(dst), fixup);       \
        EX(sw, val, (offset + 0x04)(dst), fixup);       \
        EX(sw, val, (offset + 0x08)(dst), fixup);       \
        EX(sw, val, (offset + 0x0c)(dst), fixup);       \
        EX(sw, val, (offset + 0x10)(dst), fixup);       \
        EX(sw, val, (offset + 0x14)(dst), fixup);       \
        EX(sw, val, (offset + 0x18)(dst), fixup);       \
        EX(sw, val, (offset + 0x1c)(dst), fixup);       \
        EX(sw, val, (offset + 0x20)(dst), fixup);       \
        EX(sw, val, (offset + 0x24)(dst), fixup);       \
        EX(sw, val, (offset + 0x28)(dst), fixup);       \
        EX(sw, val, (offset + 0x2c)(dst), fixup);       \
        EX(sw, val, (offset + 0x30)(dst), fixup);       \
        EX(sw, val, (offset + 0x34)(dst), fixup);       \
        EX(sw, val, (offset + 0x38)(dst), fixup);       \
        EX(sw, val, (offset + 0x3c)(dst), fixup)

/*
 * 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 */
        sll     t1, a1, 8
        or      a1, t1
        sll     t1, a1, 16
        or      a1, t1
1:

EXPORT(__bzero)
        sltiu   t0, a2, 4                       /* very small region? */
        bnez    t0, small_memset
         andi   t0, a0, 3                       /* aligned? */

        beqz    t0, 1f
         subu   t0, 4                           /* alignment in bytes */

#ifdef __MIPSEB__
        EX(swl, a1, (a0), first_fixup)          /* make word aligned */
#endif
#ifdef __MIPSEL__
        EX(swr, a1, (a0), first_fixup)          /* make word aligned */
#endif
        subu    a0, t0                          /* word align 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, 0x3c

        addu    t1, a0                          /* end address */
        .set    reorder
1:      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 */
        subu    t1, t0
        jr      t1
         addu   a0, t0                          /* dest ptr */

        .set    push
        .set    noreorder
        .set    nomacro
        F_FILL64(a0, -64, a1, partial_fixup)    /* ... but first do wrds ... */
2:      .set    pop
        andi    a2, 3                           /* 0 <= n <= 3 to go */

        beqz    a2, 1f
         addu   a0, a2                          /* What's left */
#ifdef __MIPSEB__
        EX(swr, a1, -1(a0), last_fixup)
#endif
#ifdef __MIPSEL__
        EX(swl, a1, -1(a0), last_fixup)
#endif
1:      jr      ra
         move   a2, zero

small_memset:
        beqz    a2, 2f
         addu   t1, a0, a2

1:      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:
        lw      t0, THREAD_BUADDR($28)
        andi    a2, 0x3f
        addu    a2, t1
        jr      ra
         subu   a2, t0

partial_fixup:
        lw      t0, THREAD_BUADDR($28)
        andi    a2, 3
        addu    a2, t1
        jr      ra
         subu   a2, t0

last_fixup:
        jr      ra
         andi   v1, a2, 3