1 /* SPDX-License-Identifier: GPL-2.0-only */ 2 /* 3 * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) 4 */ 5 6 /* If dst and src are 4 byte aligned, copy 8 bytes at a time. 7 If the src is 4, but not 8 byte aligned, we first read 4 bytes to get 8 it 8 byte aligned. Thus, we can do a little read-ahead, without 9 dereferencing a cache line that we should not touch. 10 Note that short and long instructions have been scheduled to avoid 11 branch stalls. 12 The beq_s to r3z could be made unaligned & long to avoid a stall 13 there, but the it is not likely to be taken often, and it 14 would also be likey to cost an unaligned mispredict at the next call. */ 15 16 #include <linux/linkage.h> 17 18 ENTRY_CFI(strcpy) 19 or r2,r0,r1 20 bmsk_s r2,r2,1 21 brne.d r2,0,charloop 22 mov_s r10,r0 23 ld_s r3,[r1,0] 24 mov r8,0x01010101 25 bbit0.d r1,2,loop_start 26 ror r12,r8 27 sub r2,r3,r8 28 bic_s r2,r2,r3 29 tst_s r2,r12 30 bne r3z 31 mov_s r4,r3 32 .balign 4 33 loop: 34 ld.a r3,[r1,4] 35 st.ab r4,[r10,4] 36 loop_start: 37 ld.a r4,[r1,4] 38 sub r2,r3,r8 39 bic_s r2,r2,r3 40 tst_s r2,r12 41 bne_s r3z 42 st.ab r3,[r10,4] 43 sub r2,r4,r8 44 bic r2,r2,r4 45 tst r2,r12 46 beq loop 47 mov_s r3,r4 48 #ifdef __LITTLE_ENDIAN__ 49 r3z: bmsk.f r1,r3,7 50 lsr_s r3,r3,8 51 #else 52 r3z: lsr.f r1,r3,24 53 asl_s r3,r3,8 54 #endif 55 bne.d r3z 56 stb.ab r1,[r10,1] 57 j_s [blink] 58 59 .balign 4 60 charloop: 61 ldb.ab r3,[r1,1] 62 63 64 brne.d r3,0,charloop 65 stb.ab r3,[r10,1] 66 j [blink] 67 END_CFI(strcpy) 68