diff options
Diffstat (limited to 'arch/loongarch/lib')
| -rw-r--r-- | arch/loongarch/lib/Makefile | 3 | ||||
| -rw-r--r-- | arch/loongarch/lib/clear_user.S | 85 | ||||
| -rw-r--r-- | arch/loongarch/lib/copy_user.S | 108 | ||||
| -rw-r--r-- | arch/loongarch/lib/memcpy.S | 95 | ||||
| -rw-r--r-- | arch/loongarch/lib/memmove.S | 121 | ||||
| -rw-r--r-- | arch/loongarch/lib/memset.S | 91 | ||||
| -rw-r--r-- | arch/loongarch/lib/unaligned.S | 84 |
7 files changed, 555 insertions, 32 deletions
diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile index e36635fccb69..40bde632900f 100644 --- a/arch/loongarch/lib/Makefile +++ b/arch/loongarch/lib/Makefile @@ -3,4 +3,5 @@ # Makefile for LoongArch-specific library files. # -lib-y += delay.o clear_user.o copy_user.o dump_tlb.o +lib-y += delay.o memset.o memcpy.o memmove.o \ + clear_user.o copy_user.o dump_tlb.o unaligned.o diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 16ba2b8dd68a..2dc48e61a2c8 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -3,30 +3,37 @@ * 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> -.macro fixup_ex from, to, offset, fix -.if \fix - .section .fixup, "ax" -\to: addi.d a0, a1, \offset +.irp to, 0, 1, 2, 3, 4, 5, 6, 7 +.L_fixup_handle_\to\(): + addi.d a0, a1, (\to) * (-8) jr ra - .previous -.endif - .section __ex_table, "a" - PTR \from\()b, \to\()b - .previous -.endm +.endr + +SYM_FUNC_START(__clear_user) + /* + * Some CPUs support hardware unaligned access + */ + ALTERNATIVE "b __clear_user_generic", \ + "b __clear_user_fast", CPU_FEATURE_UAL +SYM_FUNC_END(__clear_user) + +EXPORT_SYMBOL(__clear_user) /* - * unsigned long __clear_user(void *addr, size_t size) + * unsigned long __clear_user_generic(void *addr, size_t size) * * a0: addr * a1: size */ -SYM_FUNC_START(__clear_user) +SYM_FUNC_START(__clear_user_generic) beqz a1, 2f 1: st.b zero, a0, 0 @@ -37,7 +44,55 @@ SYM_FUNC_START(__clear_user) 2: move a0, a1 jr ra - fixup_ex 1, 3, 0, 1 -SYM_FUNC_END(__clear_user) + _asm_extable 1b, .L_fixup_handle_0 +SYM_FUNC_END(__clear_user_generic) -EXPORT_SYMBOL(__clear_user) +/* + * unsigned long __clear_user_fast(void *addr, unsigned long size) + * + * a0: addr + * a1: size + */ +SYM_FUNC_START(__clear_user_fast) + beqz a1, 10f + + ori a2, zero, 64 + blt a1, a2, 9f + + /* set 64 bytes at a time */ +1: st.d zero, a0, 0 +2: st.d zero, a0, 8 +3: st.d zero, a0, 16 +4: st.d zero, a0, 24 +5: st.d zero, a0, 32 +6: st.d zero, a0, 40 +7: st.d zero, a0, 48 +8: st.d zero, a0, 56 + + addi.d a0, a0, 64 + addi.d a1, a1, -64 + bge a1, a2, 1b + + beqz a1, 10f + + /* set the remaining bytes */ +9: st.b zero, a0, 0 + addi.d a0, a0, 1 + addi.d a1, a1, -1 + bgt a1, zero, 9b + + /* return */ +10: move a0, a1 + 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 +SYM_FUNC_END(__clear_user_fast) diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index 97d20327a69e..55ac6020a1ad 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -3,31 +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> -.macro fixup_ex from, to, offset, fix -.if \fix - .section .fixup, "ax" -\to: addi.d a0, a2, \offset +.irp to, 0, 1, 2, 3, 4, 5, 6, 7 +.L_fixup_handle_\to\(): + addi.d a0, a2, (\to) * (-8) jr ra - .previous -.endif - .section __ex_table, "a" - PTR \from\()b, \to\()b - .previous -.endm +.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 @@ -40,8 +47,77 @@ SYM_FUNC_START(__copy_user) 3: move a0, a2 jr ra - fixup_ex 1, 4, 0, 1 - fixup_ex 2, 4, 0, 0 -SYM_FUNC_END(__copy_user) + _asm_extable 1b, .L_fixup_handle_0 + _asm_extable 2b, .L_fixup_handle_0 +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) diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S new file mode 100644 index 000000000000..7c07d595ee89 --- /dev/null +++ b/arch/loongarch/lib/memcpy.S @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#include <asm/alternative-asm.h> +#include <asm/asm.h> +#include <asm/asmmacro.h> +#include <asm/cpu.h> +#include <asm/export.h> +#include <asm/regdef.h> + +SYM_FUNC_START(memcpy) + /* + * Some CPUs support hardware unaligned access + */ + ALTERNATIVE "b __memcpy_generic", \ + "b __memcpy_fast", CPU_FEATURE_UAL +SYM_FUNC_END(memcpy) + +EXPORT_SYMBOL(memcpy) + +/* + * void *__memcpy_generic(void *dst, const void *src, size_t n) + * + * a0: dst + * a1: src + * a2: n + */ +SYM_FUNC_START(__memcpy_generic) + move a3, a0 + beqz a2, 2f + +1: ld.b t0, a1, 0 + st.b t0, a0, 0 + addi.d a0, a0, 1 + addi.d a1, a1, 1 + addi.d a2, a2, -1 + bgt a2, zero, 1b + +2: move a0, a3 + jr ra +SYM_FUNC_END(__memcpy_generic) + +/* + * void *__memcpy_fast(void *dst, const void *src, size_t n) + * + * a0: dst + * a1: src + * a2: n + */ +SYM_FUNC_START(__memcpy_fast) + move a3, a0 + beqz a2, 3f + + ori a4, zero, 64 + blt a2, a4, 2f + + /* copy 64 bytes at a time */ +1: ld.d t0, a1, 0 + ld.d t1, a1, 8 + ld.d t2, a1, 16 + ld.d t3, a1, 24 + ld.d t4, a1, 32 + ld.d t5, a1, 40 + ld.d t6, a1, 48 + ld.d t7, a1, 56 + st.d t0, a0, 0 + st.d t1, a0, 8 + st.d t2, a0, 16 + st.d t3, a0, 24 + st.d t4, a0, 32 + st.d t5, a0, 40 + st.d t6, a0, 48 + st.d t7, a0, 56 + + addi.d a0, a0, 64 + addi.d a1, a1, 64 + addi.d a2, a2, -64 + bge a2, a4, 1b + + beqz a2, 3f + + /* copy the remaining bytes */ +2: ld.b t0, a1, 0 + st.b t0, a0, 0 + addi.d a0, a0, 1 + addi.d a1, a1, 1 + addi.d a2, a2, -1 + bgt a2, zero, 2b + + /* return */ +3: move a0, a3 + jr ra +SYM_FUNC_END(__memcpy_fast) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S new file mode 100644 index 000000000000..6ffdb46da78f --- /dev/null +++ b/arch/loongarch/lib/memmove.S @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#include <asm/alternative-asm.h> +#include <asm/asm.h> +#include <asm/asmmacro.h> +#include <asm/cpu.h> +#include <asm/export.h> +#include <asm/regdef.h> + +SYM_FUNC_START(memmove) + blt a0, a1, 1f /* dst < src, memcpy */ + blt a1, a0, 3f /* src < dst, rmemcpy */ + jr ra /* dst == src, return */ + + /* if (src - dst) < 64, copy 1 byte at a time */ +1: ori a3, zero, 64 + sub.d t0, a1, a0 + blt t0, a3, 2f + b memcpy +2: b __memcpy_generic + + /* if (dst - src) < 64, copy 1 byte at a time */ +3: ori a3, zero, 64 + sub.d t0, a0, a1 + blt t0, a3, 4f + b rmemcpy +4: b __rmemcpy_generic +SYM_FUNC_END(memmove) + +EXPORT_SYMBOL(memmove) + +SYM_FUNC_START(rmemcpy) + /* + * Some CPUs support hardware unaligned access + */ + ALTERNATIVE "b __rmemcpy_generic", \ + "b __rmemcpy_fast", CPU_FEATURE_UAL +SYM_FUNC_END(rmemcpy) + +/* + * void *__rmemcpy_generic(void *dst, const void *src, size_t n) + * + * a0: dst + * a1: src + * a2: n + */ +SYM_FUNC_START(__rmemcpy_generic) + move a3, a0 + beqz a2, 2f + + add.d a0, a0, a2 + add.d a1, a1, a2 + +1: ld.b t0, a1, -1 + st.b t0, a0, -1 + addi.d a0, a0, -1 + addi.d a1, a1, -1 + addi.d a2, a2, -1 + bgt a2, zero, 1b + +2: move a0, a3 + jr ra +SYM_FUNC_END(__rmemcpy_generic) + +/* + * void *__rmemcpy_fast(void *dst, const void *src, size_t n) + * + * a0: dst + * a1: src + * a2: n + */ +SYM_FUNC_START(__rmemcpy_fast) + move a3, a0 + beqz a2, 3f + + add.d a0, a0, a2 + add.d a1, a1, a2 + + ori a4, zero, 64 + blt a2, a4, 2f + + /* copy 64 bytes at a time */ +1: ld.d t0, a1, -8 + ld.d t1, a1, -16 + ld.d t2, a1, -24 + ld.d t3, a1, -32 + ld.d t4, a1, -40 + ld.d t5, a1, -48 + ld.d t6, a1, -56 + ld.d t7, a1, -64 + st.d t0, a0, -8 + st.d t1, a0, -16 + st.d t2, a0, -24 + st.d t3, a0, -32 + st.d t4, a0, -40 + st.d t5, a0, -48 + st.d t6, a0, -56 + st.d t7, a0, -64 + + addi.d a0, a0, -64 + addi.d a1, a1, -64 + addi.d a2, a2, -64 + bge a2, a4, 1b + + beqz a2, 3f + + /* copy the remaining bytes */ +2: ld.b t0, a1, -1 + st.b t0, a0, -1 + addi.d a0, a0, -1 + addi.d a1, a1, -1 + addi.d a2, a2, -1 + bgt a2, zero, 2b + + /* return */ +3: move a0, a3 + jr ra +SYM_FUNC_END(__rmemcpy_fast) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S new file mode 100644 index 000000000000..e7cb4ea3747d --- /dev/null +++ b/arch/loongarch/lib/memset.S @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#include <asm/alternative-asm.h> +#include <asm/asm.h> +#include <asm/asmmacro.h> +#include <asm/cpu.h> +#include <asm/export.h> +#include <asm/regdef.h> + +.macro fill_to_64 r0 + bstrins.d \r0, \r0, 15, 8 + bstrins.d \r0, \r0, 31, 16 + bstrins.d \r0, \r0, 63, 32 +.endm + +SYM_FUNC_START(memset) + /* + * Some CPUs support hardware unaligned access + */ + ALTERNATIVE "b __memset_generic", \ + "b __memset_fast", CPU_FEATURE_UAL +SYM_FUNC_END(memset) + +EXPORT_SYMBOL(memset) + +/* + * void *__memset_generic(void *s, int c, size_t n) + * + * a0: s + * a1: c + * a2: n + */ +SYM_FUNC_START(__memset_generic) + move a3, a0 + beqz a2, 2f + +1: st.b a1, a0, 0 + addi.d a0, a0, 1 + addi.d a2, a2, -1 + bgt a2, zero, 1b + +2: move a0, a3 + jr ra +SYM_FUNC_END(__memset_generic) + +/* + * void *__memset_fast(void *s, int c, size_t n) + * + * a0: s + * a1: c + * a2: n + */ +SYM_FUNC_START(__memset_fast) + move a3, a0 + beqz a2, 3f + + ori a4, zero, 64 + blt a2, a4, 2f + + /* fill a1 to 64 bits */ + fill_to_64 a1 + + /* set 64 bytes at a time */ +1: st.d a1, a0, 0 + st.d a1, a0, 8 + st.d a1, a0, 16 + st.d a1, a0, 24 + st.d a1, a0, 32 + st.d a1, a0, 40 + st.d a1, a0, 48 + st.d a1, a0, 56 + + addi.d a0, a0, 64 + addi.d a2, a2, -64 + bge a2, a4, 1b + + beqz a2, 3f + + /* set the remaining bytes */ +2: st.b a1, a0, 0 + addi.d a0, a0, 1 + addi.d a2, a2, -1 + bgt a2, zero, 2b + + /* return */ +3: move a0, a3 + jr ra +SYM_FUNC_END(__memset_fast) diff --git a/arch/loongarch/lib/unaligned.S b/arch/loongarch/lib/unaligned.S new file mode 100644 index 000000000000..9177fd638f07 --- /dev/null +++ b/arch/loongarch/lib/unaligned.S @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#include <linux/linkage.h> + +#include <asm/asm.h> +#include <asm/asmmacro.h> +#include <asm/asm-extable.h> +#include <asm/errno.h> +#include <asm/export.h> +#include <asm/regdef.h> + +.L_fixup_handle_unaligned: + li.w a0, -EFAULT + jr ra + +/* + * unsigned long unaligned_read(void *addr, void *value, unsigned long n, bool sign) + * + * a0: addr + * a1: value + * a2: n + * a3: sign + */ +SYM_FUNC_START(unaligned_read) + beqz a2, 5f + + li.w t2, 0 + addi.d t0, a2, -1 + slli.d t1, t0, 3 + add.d a0, a0, t0 + + beqz a3, 2f +1: ld.b t3, a0, 0 + b 3f + +2: ld.bu t3, a0, 0 +3: sll.d t3, t3, t1 + or t2, t2, t3 + addi.d t1, t1, -8 + addi.d a0, a0, -1 + addi.d a2, a2, -1 + bgtz a2, 2b +4: st.d t2, a1, 0 + + move a0, a2 + jr ra + +5: li.w a0, -EFAULT + jr ra + + _asm_extable 1b, .L_fixup_handle_unaligned + _asm_extable 2b, .L_fixup_handle_unaligned + _asm_extable 4b, .L_fixup_handle_unaligned +SYM_FUNC_END(unaligned_read) + +/* + * unsigned long unaligned_write(void *addr, unsigned long value, unsigned long n) + * + * a0: addr + * a1: value + * a2: n + */ +SYM_FUNC_START(unaligned_write) + beqz a2, 3f + + li.w t0, 0 +1: srl.d t1, a1, t0 +2: st.b t1, a0, 0 + addi.d t0, t0, 8 + addi.d a2, a2, -1 + addi.d a0, a0, 1 + bgtz a2, 1b + + move a0, a2 + jr ra + +3: li.w a0, -EFAULT + jr ra + + _asm_extable 2b, .L_fixup_handle_unaligned +SYM_FUNC_END(unaligned_write) |