1 /* SPDX-License-Identifier: GPL-2.0 */ 2 /* Copyright 2002 Andi Kleen, SuSE Labs */ 3 4 #include <linux/linkage.h> 5 #include <asm/cpufeatures.h> 6 #include <asm/alternative.h> 7 #include <asm/export.h> 8 9 .section .noinstr.text, "ax" 10 11 /* 12 * ISO C memset - set a memory block to a byte value. This function uses fast 13 * string to get better performance than the original function. The code is 14 * simpler and shorter than the original function as well. 15 * 16 * rdi destination 17 * rsi value (char) 18 * rdx count (bytes) 19 * 20 * rax original destination 21 * 22 * The FSRS alternative should be done inline (avoiding the call and 23 * the disgusting return handling), but that would require some help 24 * from the compiler for better calling conventions. 25 * 26 * The 'rep stosb' itself is small enough to replace the call, but all 27 * the register moves blow up the code. And two of them are "needed" 28 * only for the return value that is the same as the source input, 29 * which the compiler could/should do much better anyway. 30 */ 31 SYM_FUNC_START(__memset) 32 ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS 33 34 movq %rdi,%r9 35 movb %sil,%al 36 movq %rdx,%rcx 37 rep stosb 38 movq %r9,%rax 39 RET 40 SYM_FUNC_END(__memset) 41 EXPORT_SYMBOL(__memset) 42 43 SYM_FUNC_ALIAS_MEMFUNC(memset, __memset) 44 EXPORT_SYMBOL(memset) 45 46 SYM_FUNC_START_LOCAL(memset_orig) 47 movq %rdi,%r10 48 49 /* expand byte value */ 50 movzbl %sil,%ecx 51 movabs $0x0101010101010101,%rax 52 imulq %rcx,%rax 53 54 /* align dst */ 55 movl %edi,%r9d 56 andl $7,%r9d 57 jnz .Lbad_alignment 58 .Lafter_bad_alignment: 59 60 movq %rdx,%rcx 61 shrq $6,%rcx 62 jz .Lhandle_tail 63 64 .p2align 4 65 .Lloop_64: 66 decq %rcx 67 movq %rax,(%rdi) 68 movq %rax,8(%rdi) 69 movq %rax,16(%rdi) 70 movq %rax,24(%rdi) 71 movq %rax,32(%rdi) 72 movq %rax,40(%rdi) 73 movq %rax,48(%rdi) 74 movq %rax,56(%rdi) 75 leaq 64(%rdi),%rdi 76 jnz .Lloop_64 77 78 /* Handle tail in loops. The loops should be faster than hard 79 to predict jump tables. */ 80 .p2align 4 81 .Lhandle_tail: 82 movl %edx,%ecx 83 andl $63&(~7),%ecx 84 jz .Lhandle_7 85 shrl $3,%ecx 86 .p2align 4 87 .Lloop_8: 88 decl %ecx 89 movq %rax,(%rdi) 90 leaq 8(%rdi),%rdi 91 jnz .Lloop_8 92 93 .Lhandle_7: 94 andl $7,%edx 95 jz .Lende 96 .p2align 4 97 .Lloop_1: 98 decl %edx 99 movb %al,(%rdi) 100 leaq 1(%rdi),%rdi 101 jnz .Lloop_1 102 103 .Lende: 104 movq %r10,%rax 105 RET 106 107 .Lbad_alignment: 108 cmpq $7,%rdx 109 jbe .Lhandle_7 110 movq %rax,(%rdi) /* unaligned store */ 111 movq $8,%r8 112 subq %r9,%r8 113 addq %r8,%rdi 114 subq %r8,%rdx 115 jmp .Lafter_bad_alignment 116 .Lfinal: 117 SYM_FUNC_END(memset_orig) 118