diff options
Diffstat (limited to 'arch/loongarch/lib/copy_user.S')
| -rw-r--r-- | arch/loongarch/lib/copy_user.S | 91 |
1 files changed, 86 insertions, 5 deletions
diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index 61933d964da0..55ac6020a1ad 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -3,26 +3,38 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/asm-extable.h> +#include <asm/cpu.h> #include <asm/export.h> #include <asm/regdef.h> -.irp to, 0 +.irp to, 0, 1, 2, 3, 4, 5, 6, 7 .L_fixup_handle_\to\(): addi.d a0, a2, (\to) * (-8) jr ra .endr +SYM_FUNC_START(__copy_user) + /* + * Some CPUs support hardware unaligned access + */ + ALTERNATIVE "b __copy_user_generic", \ + "b __copy_user_fast", CPU_FEATURE_UAL +SYM_FUNC_END(__copy_user) + +EXPORT_SYMBOL(__copy_user) + /* - * unsigned long __copy_user(void *to, const void *from, size_t n) + * unsigned long __copy_user_generic(void *to, const void *from, size_t n) * * a0: to * a1: from * a2: n */ -SYM_FUNC_START(__copy_user) +SYM_FUNC_START(__copy_user_generic) beqz a2, 3f 1: ld.b t0, a1, 0 @@ -37,6 +49,75 @@ SYM_FUNC_START(__copy_user) _asm_extable 1b, .L_fixup_handle_0 _asm_extable 2b, .L_fixup_handle_0 -SYM_FUNC_END(__copy_user) +SYM_FUNC_END(__copy_user_generic) -EXPORT_SYMBOL(__copy_user) +/* + * unsigned long __copy_user_fast(void *to, const void *from, unsigned long n) + * + * a0: to + * a1: from + * a2: n + */ +SYM_FUNC_START(__copy_user_fast) + beqz a2, 19f + + ori a3, zero, 64 + blt a2, a3, 17f + + /* copy 64 bytes at a time */ +1: ld.d t0, a1, 0 +2: ld.d t1, a1, 8 +3: ld.d t2, a1, 16 +4: ld.d t3, a1, 24 +5: ld.d t4, a1, 32 +6: ld.d t5, a1, 40 +7: ld.d t6, a1, 48 +8: ld.d t7, a1, 56 +9: st.d t0, a0, 0 +10: st.d t1, a0, 8 +11: st.d t2, a0, 16 +12: st.d t3, a0, 24 +13: st.d t4, a0, 32 +14: st.d t5, a0, 40 +15: st.d t6, a0, 48 +16: st.d t7, a0, 56 + + addi.d a0, a0, 64 + addi.d a1, a1, 64 + addi.d a2, a2, -64 + bge a2, a3, 1b + + beqz a2, 19f + + /* copy the remaining bytes */ +17: ld.b t0, a1, 0 +18: st.b t0, a0, 0 + addi.d a0, a0, 1 + addi.d a1, a1, 1 + addi.d a2, a2, -1 + bgt a2, zero, 17b + + /* return */ +19: move a0, a2 + jr ra + + /* fixup and ex_table */ + _asm_extable 1b, .L_fixup_handle_0 + _asm_extable 2b, .L_fixup_handle_1 + _asm_extable 3b, .L_fixup_handle_2 + _asm_extable 4b, .L_fixup_handle_3 + _asm_extable 5b, .L_fixup_handle_4 + _asm_extable 6b, .L_fixup_handle_5 + _asm_extable 7b, .L_fixup_handle_6 + _asm_extable 8b, .L_fixup_handle_7 + _asm_extable 9b, .L_fixup_handle_0 + _asm_extable 10b, .L_fixup_handle_1 + _asm_extable 11b, .L_fixup_handle_2 + _asm_extable 12b, .L_fixup_handle_3 + _asm_extable 13b, .L_fixup_handle_4 + _asm_extable 14b, .L_fixup_handle_5 + _asm_extable 15b, .L_fixup_handle_6 + _asm_extable 16b, .L_fixup_handle_7 + _asm_extable 17b, .L_fixup_handle_0 + _asm_extable 18b, .L_fixup_handle_0 +SYM_FUNC_END(__copy_user_fast) |