| /* |
| * Copyright (C) 2013 Regents of the University of California |
| * |
| * This program is free software; you can redistribute it and/or |
| * modify it under the terms of the GNU General Public License |
| * as published by the Free Software Foundation, version 2. |
| * |
| * This program is distributed in the hope that it will be useful, |
| * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| * GNU General Public License for more details. |
| */ |
| |
| #include <linux/linkage.h> |
| #include <asm/asm.h> |
| |
| /* void *memcpy(void *, const void *, size_t) */ |
| ENTRY(memcpy) |
| move t6, a0 /* Preserve return value */ |
| |
| /* Defer to byte-oriented copy for small sizes */ |
| sltiu a3, a2, 128 |
| bnez a3, 4f |
| /* Use word-oriented copy only if low-order bits match */ |
| andi a3, t6, SZREG-1 |
| andi a4, a1, SZREG-1 |
| bne a3, a4, 4f |
| |
| beqz a3, 2f /* Skip if already aligned */ |
| /* |
| * Round to nearest double word-aligned address |
| * greater than or equal to start address |
| */ |
| andi a3, a1, ~(SZREG-1) |
| addi a3, a3, SZREG |
| /* Handle initial misalignment */ |
| sub a4, a3, a1 |
| 1: |
| lb a5, 0(a1) |
| addi a1, a1, 1 |
| sb a5, 0(t6) |
| addi t6, t6, 1 |
| bltu a1, a3, 1b |
| sub a2, a2, a4 /* Update count */ |
| |
| 2: |
| andi a4, a2, ~((16*SZREG)-1) |
| beqz a4, 4f |
| add a3, a1, a4 |
| 3: |
| REG_L a4, 0(a1) |
| REG_L a5, SZREG(a1) |
| REG_L a6, 2*SZREG(a1) |
| REG_L a7, 3*SZREG(a1) |
| REG_L t0, 4*SZREG(a1) |
| REG_L t1, 5*SZREG(a1) |
| REG_L t2, 6*SZREG(a1) |
| REG_L t3, 7*SZREG(a1) |
| REG_L t4, 8*SZREG(a1) |
| REG_L t5, 9*SZREG(a1) |
| REG_S a4, 0(t6) |
| REG_S a5, SZREG(t6) |
| REG_S a6, 2*SZREG(t6) |
| REG_S a7, 3*SZREG(t6) |
| REG_S t0, 4*SZREG(t6) |
| REG_S t1, 5*SZREG(t6) |
| REG_S t2, 6*SZREG(t6) |
| REG_S t3, 7*SZREG(t6) |
| REG_S t4, 8*SZREG(t6) |
| REG_S t5, 9*SZREG(t6) |
| REG_L a4, 10*SZREG(a1) |
| REG_L a5, 11*SZREG(a1) |
| REG_L a6, 12*SZREG(a1) |
| REG_L a7, 13*SZREG(a1) |
| REG_L t0, 14*SZREG(a1) |
| REG_L t1, 15*SZREG(a1) |
| addi a1, a1, 16*SZREG |
| REG_S a4, 10*SZREG(t6) |
| REG_S a5, 11*SZREG(t6) |
| REG_S a6, 12*SZREG(t6) |
| REG_S a7, 13*SZREG(t6) |
| REG_S t0, 14*SZREG(t6) |
| REG_S t1, 15*SZREG(t6) |
| addi t6, t6, 16*SZREG |
| bltu a1, a3, 3b |
| andi a2, a2, (16*SZREG)-1 /* Update count */ |
| |
| 4: |
| /* Handle trailing misalignment */ |
| beqz a2, 6f |
| add a3, a1, a2 |
| |
| /* Use word-oriented copy if co-aligned to word boundary */ |
| or a5, a1, t6 |
| or a5, a5, a3 |
| andi a5, a5, 3 |
| bnez a5, 5f |
| 7: |
| lw a4, 0(a1) |
| addi a1, a1, 4 |
| sw a4, 0(t6) |
| addi t6, t6, 4 |
| bltu a1, a3, 7b |
| |
| ret |
| |
| 5: |
| lb a4, 0(a1) |
| addi a1, a1, 1 |
| sb a4, 0(t6) |
| addi t6, t6, 1 |
| bltu a1, a3, 5b |
| 6: |
| ret |
| END(memcpy) |