diff options
Diffstat (limited to 'arch/loongarch/lib')
-rw-r--r-- | arch/loongarch/lib/Makefile | 2 | ||||
-rw-r--r-- | arch/loongarch/lib/clear_user.S | 87 | ||||
-rw-r--r-- | arch/loongarch/lib/copy_user.S | 161 | ||||
-rw-r--r-- | arch/loongarch/lib/memcpy.S | 8 | ||||
-rw-r--r-- | arch/loongarch/lib/memmove.S | 20 | ||||
-rw-r--r-- | arch/loongarch/lib/memset.S | 8 | ||||
-rw-r--r-- | arch/loongarch/lib/xor_simd.c | 93 | ||||
-rw-r--r-- | arch/loongarch/lib/xor_simd.h | 38 | ||||
-rw-r--r-- | arch/loongarch/lib/xor_simd_glue.c | 72 | ||||
-rw-r--r-- | arch/loongarch/lib/xor_template.c | 110 |
10 files changed, 469 insertions, 130 deletions
diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile index d60d4e096cfa..a77bf160bfc4 100644 --- a/arch/loongarch/lib/Makefile +++ b/arch/loongarch/lib/Makefile @@ -6,4 +6,6 @@ lib-y += delay.o memset.o memcpy.o memmove.o \ clear_user.o copy_user.o csum.o dump_tlb.o unaligned.o +obj-$(CONFIG_CPU_HAS_LSX) += xor_simd.o xor_simd_glue.o + obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 0790eadce166..be741544e62b 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -11,19 +11,6 @@ #include <asm/cpu.h> #include <asm/regdef.h> -.irp to, 0, 1, 2, 3, 4, 5, 6, 7 -.L_fixup_handle_\to\(): - sub.d a0, a2, a0 - addi.d a0, a0, (\to) * (-8) - jr ra -.endr - -.irp to, 0, 2, 4 -.L_fixup_handle_s\to\(): - addi.d a0, a1, -\to - jr ra -.endr - SYM_FUNC_START(__clear_user) /* * Some CPUs support hardware unaligned access @@ -51,7 +38,7 @@ SYM_FUNC_START(__clear_user_generic) 2: move a0, a1 jr ra - _asm_extable 1b, .L_fixup_handle_s0 + _asm_extable 1b, 2b SYM_FUNC_END(__clear_user_generic) /* @@ -173,33 +160,47 @@ SYM_FUNC_START(__clear_user_fast) jr ra /* fixup and ex_table */ - _asm_extable 0b, .L_fixup_handle_0 - _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_0 - _asm_extable 14b, .L_fixup_handle_1 - _asm_extable 15b, .L_fixup_handle_0 - _asm_extable 16b, .L_fixup_handle_0 - _asm_extable 17b, .L_fixup_handle_s0 - _asm_extable 18b, .L_fixup_handle_s0 - _asm_extable 19b, .L_fixup_handle_s0 - _asm_extable 20b, .L_fixup_handle_s2 - _asm_extable 21b, .L_fixup_handle_s0 - _asm_extable 22b, .L_fixup_handle_s0 - _asm_extable 23b, .L_fixup_handle_s4 - _asm_extable 24b, .L_fixup_handle_s0 - _asm_extable 25b, .L_fixup_handle_s4 - _asm_extable 26b, .L_fixup_handle_s0 - _asm_extable 27b, .L_fixup_handle_s4 - _asm_extable 28b, .L_fixup_handle_s0 +.Llarge_fixup: + sub.d a1, a2, a0 + +.Lsmall_fixup: +29: st.b zero, a0, 0 + addi.d a0, a0, 1 + addi.d a1, a1, -1 + bgt a1, zero, 29b + +.Lexit: + move a0, a1 + jr ra + + _asm_extable 0b, .Lsmall_fixup + _asm_extable 1b, .Llarge_fixup + _asm_extable 2b, .Llarge_fixup + _asm_extable 3b, .Llarge_fixup + _asm_extable 4b, .Llarge_fixup + _asm_extable 5b, .Llarge_fixup + _asm_extable 6b, .Llarge_fixup + _asm_extable 7b, .Llarge_fixup + _asm_extable 8b, .Llarge_fixup + _asm_extable 9b, .Llarge_fixup + _asm_extable 10b, .Llarge_fixup + _asm_extable 11b, .Llarge_fixup + _asm_extable 12b, .Llarge_fixup + _asm_extable 13b, .Llarge_fixup + _asm_extable 14b, .Llarge_fixup + _asm_extable 15b, .Llarge_fixup + _asm_extable 16b, .Llarge_fixup + _asm_extable 17b, .Lexit + _asm_extable 18b, .Lsmall_fixup + _asm_extable 19b, .Lsmall_fixup + _asm_extable 20b, .Lsmall_fixup + _asm_extable 21b, .Lsmall_fixup + _asm_extable 22b, .Lsmall_fixup + _asm_extable 23b, .Lsmall_fixup + _asm_extable 24b, .Lsmall_fixup + _asm_extable 25b, .Lsmall_fixup + _asm_extable 26b, .Lsmall_fixup + _asm_extable 27b, .Lsmall_fixup + _asm_extable 28b, .Lsmall_fixup + _asm_extable 29b, .Lexit SYM_FUNC_END(__clear_user_fast) diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index bfe3d2793d00..feec3d362803 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -11,19 +11,6 @@ #include <asm/cpu.h> #include <asm/regdef.h> -.irp to, 0, 1, 2, 3, 4, 5, 6, 7 -.L_fixup_handle_\to\(): - sub.d a0, a2, a0 - addi.d a0, a0, (\to) * (-8) - jr ra -.endr - -.irp to, 0, 2, 4 -.L_fixup_handle_s\to\(): - addi.d a0, a2, -\to - jr ra -.endr - SYM_FUNC_START(__copy_user) /* * Some CPUs support hardware unaligned access @@ -54,8 +41,8 @@ SYM_FUNC_START(__copy_user_generic) 3: move a0, a2 jr ra - _asm_extable 1b, .L_fixup_handle_s0 - _asm_extable 2b, .L_fixup_handle_s0 + _asm_extable 1b, 3b + _asm_extable 2b, 3b SYM_FUNC_END(__copy_user_generic) /* @@ -69,10 +56,10 @@ SYM_FUNC_START(__copy_user_fast) sltui t0, a2, 9 bnez t0, .Lsmall - add.d a3, a1, a2 - add.d a2, a0, a2 0: ld.d t0, a1, 0 1: st.d t0, a0, 0 + add.d a3, a1, a2 + add.d a2, a0, a2 /* align up destination address */ andi t1, a0, 7 @@ -94,7 +81,6 @@ SYM_FUNC_START(__copy_user_fast) 7: ld.d t5, a1, 40 8: ld.d t6, a1, 48 9: ld.d t7, a1, 56 - addi.d a1, a1, 64 10: st.d t0, a0, 0 11: st.d t1, a0, 8 12: st.d t2, a0, 16 @@ -103,6 +89,7 @@ SYM_FUNC_START(__copy_user_fast) 15: st.d t5, a0, 40 16: st.d t6, a0, 48 17: st.d t7, a0, 56 + addi.d a1, a1, 64 addi.d a0, a0, 64 bltu a1, a4, .Lloop64 @@ -114,11 +101,11 @@ SYM_FUNC_START(__copy_user_fast) 19: ld.d t1, a1, 8 20: ld.d t2, a1, 16 21: ld.d t3, a1, 24 - addi.d a1, a1, 32 22: st.d t0, a0, 0 23: st.d t1, a0, 8 24: st.d t2, a0, 16 25: st.d t3, a0, 24 + addi.d a1, a1, 32 addi.d a0, a0, 32 .Llt32: @@ -126,9 +113,9 @@ SYM_FUNC_START(__copy_user_fast) bgeu a1, a4, .Llt16 26: ld.d t0, a1, 0 27: ld.d t1, a1, 8 - addi.d a1, a1, 16 28: st.d t0, a0, 0 29: st.d t1, a0, 8 + addi.d a1, a1, 16 addi.d a0, a0, 16 .Llt16: @@ -136,6 +123,7 @@ SYM_FUNC_START(__copy_user_fast) bgeu a1, a4, .Llt8 30: ld.d t0, a1, 0 31: st.d t0, a0, 0 + addi.d a1, a1, 8 addi.d a0, a0, 8 .Llt8: @@ -214,62 +202,79 @@ SYM_FUNC_START(__copy_user_fast) jr ra /* fixup and ex_table */ - _asm_extable 0b, .L_fixup_handle_0 - _asm_extable 1b, .L_fixup_handle_0 - _asm_extable 2b, .L_fixup_handle_0 - _asm_extable 3b, .L_fixup_handle_0 - _asm_extable 4b, .L_fixup_handle_0 - _asm_extable 5b, .L_fixup_handle_0 - _asm_extable 6b, .L_fixup_handle_0 - _asm_extable 7b, .L_fixup_handle_0 - _asm_extable 8b, .L_fixup_handle_0 - _asm_extable 9b, .L_fixup_handle_0 - _asm_extable 10b, .L_fixup_handle_0 - _asm_extable 11b, .L_fixup_handle_1 - _asm_extable 12b, .L_fixup_handle_2 - _asm_extable 13b, .L_fixup_handle_3 - _asm_extable 14b, .L_fixup_handle_4 - _asm_extable 15b, .L_fixup_handle_5 - _asm_extable 16b, .L_fixup_handle_6 - _asm_extable 17b, .L_fixup_handle_7 - _asm_extable 18b, .L_fixup_handle_0 - _asm_extable 19b, .L_fixup_handle_0 - _asm_extable 20b, .L_fixup_handle_0 - _asm_extable 21b, .L_fixup_handle_0 - _asm_extable 22b, .L_fixup_handle_0 - _asm_extable 23b, .L_fixup_handle_1 - _asm_extable 24b, .L_fixup_handle_2 - _asm_extable 25b, .L_fixup_handle_3 - _asm_extable 26b, .L_fixup_handle_0 - _asm_extable 27b, .L_fixup_handle_0 - _asm_extable 28b, .L_fixup_handle_0 - _asm_extable 29b, .L_fixup_handle_1 - _asm_extable 30b, .L_fixup_handle_0 - _asm_extable 31b, .L_fixup_handle_0 - _asm_extable 32b, .L_fixup_handle_0 - _asm_extable 33b, .L_fixup_handle_0 - _asm_extable 34b, .L_fixup_handle_s0 - _asm_extable 35b, .L_fixup_handle_s0 - _asm_extable 36b, .L_fixup_handle_s0 - _asm_extable 37b, .L_fixup_handle_s0 - _asm_extable 38b, .L_fixup_handle_s0 - _asm_extable 39b, .L_fixup_handle_s0 - _asm_extable 40b, .L_fixup_handle_s0 - _asm_extable 41b, .L_fixup_handle_s2 - _asm_extable 42b, .L_fixup_handle_s0 - _asm_extable 43b, .L_fixup_handle_s0 - _asm_extable 44b, .L_fixup_handle_s0 - _asm_extable 45b, .L_fixup_handle_s0 - _asm_extable 46b, .L_fixup_handle_s0 - _asm_extable 47b, .L_fixup_handle_s4 - _asm_extable 48b, .L_fixup_handle_s0 - _asm_extable 49b, .L_fixup_handle_s0 - _asm_extable 50b, .L_fixup_handle_s0 - _asm_extable 51b, .L_fixup_handle_s4 - _asm_extable 52b, .L_fixup_handle_s0 - _asm_extable 53b, .L_fixup_handle_s0 - _asm_extable 54b, .L_fixup_handle_s0 - _asm_extable 55b, .L_fixup_handle_s4 - _asm_extable 56b, .L_fixup_handle_s0 - _asm_extable 57b, .L_fixup_handle_s0 +.Llarge_fixup: + sub.d a2, a2, a0 + +.Lsmall_fixup: +58: ld.b t0, a1, 0 +59: st.b t0, a0, 0 + addi.d a0, a0, 1 + addi.d a1, a1, 1 + addi.d a2, a2, -1 + bgt a2, zero, 58b + +.Lexit: + move a0, a2 + jr ra + + _asm_extable 0b, .Lsmall_fixup + _asm_extable 1b, .Lsmall_fixup + _asm_extable 2b, .Llarge_fixup + _asm_extable 3b, .Llarge_fixup + _asm_extable 4b, .Llarge_fixup + _asm_extable 5b, .Llarge_fixup + _asm_extable 6b, .Llarge_fixup + _asm_extable 7b, .Llarge_fixup + _asm_extable 8b, .Llarge_fixup + _asm_extable 9b, .Llarge_fixup + _asm_extable 10b, .Llarge_fixup + _asm_extable 11b, .Llarge_fixup + _asm_extable 12b, .Llarge_fixup + _asm_extable 13b, .Llarge_fixup + _asm_extable 14b, .Llarge_fixup + _asm_extable 15b, .Llarge_fixup + _asm_extable 16b, .Llarge_fixup + _asm_extable 17b, .Llarge_fixup + _asm_extable 18b, .Llarge_fixup + _asm_extable 19b, .Llarge_fixup + _asm_extable 20b, .Llarge_fixup + _asm_extable 21b, .Llarge_fixup + _asm_extable 22b, .Llarge_fixup + _asm_extable 23b, .Llarge_fixup + _asm_extable 24b, .Llarge_fixup + _asm_extable 25b, .Llarge_fixup + _asm_extable 26b, .Llarge_fixup + _asm_extable 27b, .Llarge_fixup + _asm_extable 28b, .Llarge_fixup + _asm_extable 29b, .Llarge_fixup + _asm_extable 30b, .Llarge_fixup + _asm_extable 31b, .Llarge_fixup + _asm_extable 32b, .Llarge_fixup + _asm_extable 33b, .Llarge_fixup + _asm_extable 34b, .Lexit + _asm_extable 35b, .Lexit + _asm_extable 36b, .Lsmall_fixup + _asm_extable 37b, .Lsmall_fixup + _asm_extable 38b, .Lsmall_fixup + _asm_extable 39b, .Lsmall_fixup + _asm_extable 40b, .Lsmall_fixup + _asm_extable 41b, .Lsmall_fixup + _asm_extable 42b, .Lsmall_fixup + _asm_extable 43b, .Lsmall_fixup + _asm_extable 44b, .Lsmall_fixup + _asm_extable 45b, .Lsmall_fixup + _asm_extable 46b, .Lsmall_fixup + _asm_extable 47b, .Lsmall_fixup + _asm_extable 48b, .Lsmall_fixup + _asm_extable 49b, .Lsmall_fixup + _asm_extable 50b, .Lsmall_fixup + _asm_extable 51b, .Lsmall_fixup + _asm_extable 52b, .Lsmall_fixup + _asm_extable 53b, .Lsmall_fixup + _asm_extable 54b, .Lsmall_fixup + _asm_extable 55b, .Lsmall_fixup + _asm_extable 56b, .Lsmall_fixup + _asm_extable 57b, .Lsmall_fixup + _asm_extable 58b, .Lexit + _asm_extable 59b, .Lexit SYM_FUNC_END(__copy_user_fast) diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index cc30b3b6252f..fa1148878d2b 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -10,6 +10,8 @@ #include <asm/cpu.h> #include <asm/regdef.h> +.section .noinstr.text, "ax" + SYM_FUNC_START(memcpy) /* * Some CPUs support hardware unaligned access @@ -17,9 +19,13 @@ SYM_FUNC_START(memcpy) ALTERNATIVE "b __memcpy_generic", \ "b __memcpy_fast", CPU_FEATURE_UAL SYM_FUNC_END(memcpy) -_ASM_NOKPROBE(memcpy) +SYM_FUNC_ALIAS(__memcpy, memcpy) EXPORT_SYMBOL(memcpy) +EXPORT_SYMBOL(__memcpy) + +_ASM_NOKPROBE(memcpy) +_ASM_NOKPROBE(__memcpy) /* * void *__memcpy_generic(void *dst, const void *src, size_t n) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S index 7dc76d1484b6..82dae062fec8 100644 --- a/arch/loongarch/lib/memmove.S +++ b/arch/loongarch/lib/memmove.S @@ -10,23 +10,29 @@ #include <asm/cpu.h> #include <asm/regdef.h> +.section .noinstr.text, "ax" + SYM_FUNC_START(memmove) - blt a0, a1, memcpy /* dst < src, memcpy */ - blt a1, a0, rmemcpy /* src < dst, rmemcpy */ - jr ra /* dst == src, return */ + blt a0, a1, __memcpy /* dst < src, memcpy */ + blt a1, a0, __rmemcpy /* src < dst, rmemcpy */ + jr ra /* dst == src, return */ SYM_FUNC_END(memmove) -_ASM_NOKPROBE(memmove) +SYM_FUNC_ALIAS(__memmove, memmove) EXPORT_SYMBOL(memmove) +EXPORT_SYMBOL(__memmove) + +_ASM_NOKPROBE(memmove) +_ASM_NOKPROBE(__memmove) -SYM_FUNC_START(rmemcpy) +SYM_FUNC_START(__rmemcpy) /* * Some CPUs support hardware unaligned access */ ALTERNATIVE "b __rmemcpy_generic", \ "b __rmemcpy_fast", CPU_FEATURE_UAL -SYM_FUNC_END(rmemcpy) -_ASM_NOKPROBE(rmemcpy) +SYM_FUNC_END(__rmemcpy) +_ASM_NOKPROBE(__rmemcpy) /* * void *__rmemcpy_generic(void *dst, const void *src, size_t n) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index 3f20f7996e8e..06d3ca54cbfe 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -16,6 +16,8 @@ bstrins.d \r0, \r0, 63, 32 .endm +.section .noinstr.text, "ax" + SYM_FUNC_START(memset) /* * Some CPUs support hardware unaligned access @@ -23,9 +25,13 @@ SYM_FUNC_START(memset) ALTERNATIVE "b __memset_generic", \ "b __memset_fast", CPU_FEATURE_UAL SYM_FUNC_END(memset) -_ASM_NOKPROBE(memset) +SYM_FUNC_ALIAS(__memset, memset) EXPORT_SYMBOL(memset) +EXPORT_SYMBOL(__memset) + +_ASM_NOKPROBE(memset) +_ASM_NOKPROBE(__memset) /* * void *__memset_generic(void *s, int c, size_t n) diff --git a/arch/loongarch/lib/xor_simd.c b/arch/loongarch/lib/xor_simd.c new file mode 100644 index 000000000000..84cd24b728c4 --- /dev/null +++ b/arch/loongarch/lib/xor_simd.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * LoongArch SIMD XOR operations + * + * Copyright (C) 2023 WANG Xuerui <git@xen0n.name> + */ + +#include "xor_simd.h" + +/* + * Process one cache line (64 bytes) per loop. This is assuming all future + * popular LoongArch cores are similar performance-characteristics-wise to the + * current models. + */ +#define LINE_WIDTH 64 + +#ifdef CONFIG_CPU_HAS_LSX + +#define LD(reg, base, offset) \ + "vld $vr" #reg ", %[" #base "], " #offset "\n\t" +#define ST(reg, base, offset) \ + "vst $vr" #reg ", %[" #base "], " #offset "\n\t" +#define XOR(dj, k) "vxor.v $vr" #dj ", $vr" #dj ", $vr" #k "\n\t" + +#define LD_INOUT_LINE(base) \ + LD(0, base, 0) \ + LD(1, base, 16) \ + LD(2, base, 32) \ + LD(3, base, 48) + +#define LD_AND_XOR_LINE(base) \ + LD(4, base, 0) \ + LD(5, base, 16) \ + LD(6, base, 32) \ + LD(7, base, 48) \ + XOR(0, 4) \ + XOR(1, 5) \ + XOR(2, 6) \ + XOR(3, 7) + +#define ST_LINE(base) \ + ST(0, base, 0) \ + ST(1, base, 16) \ + ST(2, base, 32) \ + ST(3, base, 48) + +#define XOR_FUNC_NAME(nr) __xor_lsx_##nr +#include "xor_template.c" + +#undef LD +#undef ST +#undef XOR +#undef LD_INOUT_LINE +#undef LD_AND_XOR_LINE +#undef ST_LINE +#undef XOR_FUNC_NAME + +#endif /* CONFIG_CPU_HAS_LSX */ + +#ifdef CONFIG_CPU_HAS_LASX + +#define LD(reg, base, offset) \ + "xvld $xr" #reg ", %[" #base "], " #offset "\n\t" +#define ST(reg, base, offset) \ + "xvst $xr" #reg ", %[" #base "], " #offset "\n\t" +#define XOR(dj, k) "xvxor.v $xr" #dj ", $xr" #dj ", $xr" #k "\n\t" + +#define LD_INOUT_LINE(base) \ + LD(0, base, 0) \ + LD(1, base, 32) + +#define LD_AND_XOR_LINE(base) \ + LD(2, base, 0) \ + LD(3, base, 32) \ + XOR(0, 2) \ + XOR(1, 3) + +#define ST_LINE(base) \ + ST(0, base, 0) \ + ST(1, base, 32) + +#define XOR_FUNC_NAME(nr) __xor_lasx_##nr +#include "xor_template.c" + +#undef LD +#undef ST +#undef XOR +#undef LD_INOUT_LINE +#undef LD_AND_XOR_LINE +#undef ST_LINE +#undef XOR_FUNC_NAME + +#endif /* CONFIG_CPU_HAS_LASX */ diff --git a/arch/loongarch/lib/xor_simd.h b/arch/loongarch/lib/xor_simd.h new file mode 100644 index 000000000000..f50f32514d80 --- /dev/null +++ b/arch/loongarch/lib/xor_simd.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Simple interface to link xor_simd.c and xor_simd_glue.c + * + * Separating these files ensures that no SIMD instructions are run outside of + * the kfpu critical section. + */ + +#ifndef __LOONGARCH_LIB_XOR_SIMD_H +#define __LOONGARCH_LIB_XOR_SIMD_H + +#ifdef CONFIG_CPU_HAS_LSX +void __xor_lsx_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2); +void __xor_lsx_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, const unsigned long * __restrict p3); +void __xor_lsx_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, const unsigned long * __restrict p3, + const unsigned long * __restrict p4); +void __xor_lsx_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, const unsigned long * __restrict p3, + const unsigned long * __restrict p4, const unsigned long * __restrict p5); +#endif /* CONFIG_CPU_HAS_LSX */ + +#ifdef CONFIG_CPU_HAS_LASX +void __xor_lasx_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2); +void __xor_lasx_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, const unsigned long * __restrict p3); +void __xor_lasx_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, const unsigned long * __restrict p3, + const unsigned long * __restrict p4); +void __xor_lasx_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, const unsigned long * __restrict p3, + const unsigned long * __restrict p4, const unsigned long * __restrict p5); +#endif /* CONFIG_CPU_HAS_LASX */ + +#endif /* __LOONGARCH_LIB_XOR_SIMD_H */ diff --git a/arch/loongarch/lib/xor_simd_glue.c b/arch/loongarch/lib/xor_simd_glue.c new file mode 100644 index 000000000000..393f689dbcf6 --- /dev/null +++ b/arch/loongarch/lib/xor_simd_glue.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * LoongArch SIMD XOR operations + * + * Copyright (C) 2023 WANG Xuerui <git@xen0n.name> + */ + +#include <linux/export.h> +#include <linux/sched.h> +#include <asm/fpu.h> +#include <asm/xor_simd.h> +#include "xor_simd.h" + +#define MAKE_XOR_GLUE_2(flavor) \ +void xor_##flavor##_2(unsigned long bytes, unsigned long * __restrict p1, \ + const unsigned long * __restrict p2) \ +{ \ + kernel_fpu_begin(); \ + __xor_##flavor##_2(bytes, p1, p2); \ + kernel_fpu_end(); \ +} \ +EXPORT_SYMBOL_GPL(xor_##flavor##_2) + +#define MAKE_XOR_GLUE_3(flavor) \ +void xor_##flavor##_3(unsigned long bytes, unsigned long * __restrict p1, \ + const unsigned long * __restrict p2, \ + const unsigned long * __restrict p3) \ +{ \ + kernel_fpu_begin(); \ + __xor_##flavor##_3(bytes, p1, p2, p3); \ + kernel_fpu_end(); \ +} \ +EXPORT_SYMBOL_GPL(xor_##flavor##_3) + +#define MAKE_XOR_GLUE_4(flavor) \ +void xor_##flavor##_4(unsigned long bytes, unsigned long * __restrict p1, \ + const unsigned long * __restrict p2, \ + const unsigned long * __restrict p3, \ + const unsigned long * __restrict p4) \ +{ \ + kernel_fpu_begin(); \ + __xor_##flavor##_4(bytes, p1, p2, p3, p4); \ + kernel_fpu_end(); \ +} \ +EXPORT_SYMBOL_GPL(xor_##flavor##_4) + +#define MAKE_XOR_GLUE_5(flavor) \ +void xor_##flavor##_5(unsigned long bytes, unsigned long * __restrict p1, \ + const unsigned long * __restrict p2, \ + const unsigned long * __restrict p3, \ + const unsigned long * __restrict p4, \ + const unsigned long * __restrict p5) \ +{ \ + kernel_fpu_begin(); \ + __xor_##flavor##_5(bytes, p1, p2, p3, p4, p5); \ + kernel_fpu_end(); \ +} \ +EXPORT_SYMBOL_GPL(xor_##flavor##_5) + +#define MAKE_XOR_GLUES(flavor) \ + MAKE_XOR_GLUE_2(flavor); \ + MAKE_XOR_GLUE_3(flavor); \ + MAKE_XOR_GLUE_4(flavor); \ + MAKE_XOR_GLUE_5(flavor) + +#ifdef CONFIG_CPU_HAS_LSX +MAKE_XOR_GLUES(lsx); +#endif + +#ifdef CONFIG_CPU_HAS_LASX +MAKE_XOR_GLUES(lasx); +#endif diff --git a/arch/loongarch/lib/xor_template.c b/arch/loongarch/lib/xor_template.c new file mode 100644 index 000000000000..0358ced7fe33 --- /dev/null +++ b/arch/loongarch/lib/xor_template.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 WANG Xuerui <git@xen0n.name> + * + * Template for XOR operations, instantiated in xor_simd.c. + * + * Expected preprocessor definitions: + * + * - LINE_WIDTH + * - XOR_FUNC_NAME(nr) + * - LD_INOUT_LINE(buf) + * - LD_AND_XOR_LINE(buf) + * - ST_LINE(buf) + */ + +void XOR_FUNC_NAME(2)(unsigned long bytes, + unsigned long * __restrict v1, + const unsigned long * __restrict v2) +{ + unsigned long lines = bytes / LINE_WIDTH; + + do { + __asm__ __volatile__ ( + LD_INOUT_LINE(v1) + LD_AND_XOR_LINE(v2) + ST_LINE(v1) + : : [v1] "r"(v1), [v2] "r"(v2) : "memory" + ); + + v1 += LINE_WIDTH / sizeof(unsigned long); + v2 += LINE_WIDTH / sizeof(unsigned long); + } while (--lines > 0); +} + +void XOR_FUNC_NAME(3)(unsigned long bytes, + unsigned long * __restrict v1, + const unsigned long * __restrict v2, + const unsigned long * __restrict v3) +{ + unsigned long lines = bytes / LINE_WIDTH; + + do { + __asm__ __volatile__ ( + LD_INOUT_LINE(v1) + LD_AND_XOR_LINE(v2) + LD_AND_XOR_LINE(v3) + ST_LINE(v1) + : : [v1] "r"(v1), [v2] "r"(v2), [v3] "r"(v3) : "memory" + ); + + v1 += LINE_WIDTH / sizeof(unsigned long); + v2 += LINE_WIDTH / sizeof(unsigned long); + v3 += LINE_WIDTH / sizeof(unsigned long); + } while (--lines > 0); +} + +void XOR_FUNC_NAME(4)(unsigned long bytes, + unsigned long * __restrict v1, + const unsigned long * __restrict v2, + const unsigned long * __restrict v3, + const unsigned long * __restrict v4) +{ + unsigned long lines = bytes / LINE_WIDTH; + + do { + __asm__ __volatile__ ( + LD_INOUT_LINE(v1) + LD_AND_XOR_LINE(v2) + LD_AND_XOR_LINE(v3) + LD_AND_XOR_LINE(v4) + ST_LINE(v1) + : : [v1] "r"(v1), [v2] "r"(v2), [v3] "r"(v3), [v4] "r"(v4) + : "memory" + ); + + v1 += LINE_WIDTH / sizeof(unsigned long); + v2 += LINE_WIDTH / sizeof(unsigned long); + v3 += LINE_WIDTH / sizeof(unsigned long); + v4 += LINE_WIDTH / sizeof(unsigned long); + } while (--lines > 0); +} + +void XOR_FUNC_NAME(5)(unsigned long bytes, + unsigned long * __restrict v1, + const unsigned long * __restrict v2, + const unsigned long * __restrict v3, + const unsigned long * __restrict v4, + const unsigned long * __restrict v5) +{ + unsigned long lines = bytes / LINE_WIDTH; + + do { + __asm__ __volatile__ ( + LD_INOUT_LINE(v1) + LD_AND_XOR_LINE(v2) + LD_AND_XOR_LINE(v3) + LD_AND_XOR_LINE(v4) + LD_AND_XOR_LINE(v5) + ST_LINE(v1) + : : [v1] "r"(v1), [v2] "r"(v2), [v3] "r"(v3), [v4] "r"(v4), + [v5] "r"(v5) : "memory" + ); + + v1 += LINE_WIDTH / sizeof(unsigned long); + v2 += LINE_WIDTH / sizeof(unsigned long); + v3 += LINE_WIDTH / sizeof(unsigned long); + v4 += LINE_WIDTH / sizeof(unsigned long); + v5 += LINE_WIDTH / sizeof(unsigned long); + } while (--lines > 0); +} |