Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2013-2021, Arm Limited. * * Adapted from the original at: * https://github.com/ARM-software/optimized-routines/blob/e823e3abf5f89ecb/string/aarch64/memcmp.S */ #include <linux/linkage.h> #include <asm/assembler.h> /* Assumptions: * * ARMv8-a, AArch64, unaligned accesses. */ #define L(label) .L ## label /* Parameters and result. */ #define src1 x0 #define src2 x1 #define limit x2 #define result w0 /* Internal variables. */ #define data1 x3 #define data1w w3 #define data1h x4 #define data2 x5 #define data2w w5 #define data2h x6 #define tmp1 x7 #define tmp2 x8 SYM_FUNC_START(__pi_memcmp) subs limit, limit, 8 b.lo L(less8) ldr data1, [src1], 8 ldr data2, [src2], 8 cmp data1, data2 b.ne L(return) subs limit, limit, 8 b.gt L(more16) ldr data1, [src1, limit] ldr data2, [src2, limit] b L(return) L(more16): ldr data1, [src1], 8 ldr data2, [src2], 8 cmp data1, data2 bne L(return) /* Jump directly to comparing the last 16 bytes for 32 byte (or less) strings. */ subs limit, limit, 16 b.ls L(last_bytes) /* We overlap loads between 0-32 bytes at either side of SRC1 when we try to align, so limit it only to strings larger than 128 bytes. */ cmp limit, 96 b.ls L(loop16) /* Align src1 and adjust src2 with bytes not yet done. */ and tmp1, src1, 15 add limit, limit, tmp1 sub src1, src1, tmp1 sub src2, src2, tmp1 /* Loop performing 16 bytes per iteration using aligned src1. Limit is pre-decremented by 16 and must be larger than zero. Exit if <= 16 bytes left to do or if the data is not equal. */ .p2align 4 L(loop16): ldp data1, data1h, [src1], 16 ldp data2, data2h, [src2], 16 subs limit, limit, 16 ccmp data1, data2, 0, hi ccmp data1h, data2h, 0, eq b.eq L(loop16) cmp data1, data2 bne L(return) mov data1, data1h mov data2, data2h cmp data1, data2 bne L(return) /* Compare last 1-16 bytes using unaligned access. */ L(last_bytes): add src1, src1, limit add src2, src2, limit ldp data1, data1h, [src1] ldp data2, data2h, [src2] cmp data1, data2 bne L(return) mov data1, data1h mov data2, data2h cmp data1, data2 /* Compare data bytes and set return value to 0, -1 or 1. */ L(return): #ifndef __AARCH64EB__ rev data1, data1 rev data2, data2 #endif cmp data1, data2 L(ret_eq): cset result, ne cneg result, result, lo ret .p2align 4 /* Compare up to 8 bytes. Limit is [-8..-1]. */ L(less8): adds limit, limit, 4 b.lo L(less4) ldr data1w, [src1], 4 ldr data2w, [src2], 4 cmp data1w, data2w b.ne L(return) sub limit, limit, 4 L(less4): adds limit, limit, 4 beq L(ret_eq) L(byte_loop): ldrb data1w, [src1], 1 ldrb data2w, [src2], 1 subs limit, limit, 1 ccmp data1w, data2w, 0, ne /* NZCV = 0b0000. */ b.eq L(byte_loop) sub result, data1w, data2w ret SYM_FUNC_END(__pi_memcmp) SYM_FUNC_ALIAS_WEAK(memcmp, __pi_memcmp) EXPORT_SYMBOL_NOKASAN(memcmp) |