diff options
Diffstat (limited to 'arch/arc/lib')
| -rw-r--r-- | arch/arc/lib/Makefile | 8 | ||||
| -rw-r--r-- | arch/arc/lib/memcpy-archs-unaligned.S | 47 | ||||
| -rw-r--r-- | arch/arc/lib/memcpy-archs.S | 14 |
3 files changed, 54 insertions, 15 deletions
diff --git a/arch/arc/lib/Makefile b/arch/arc/lib/Makefile index b1656d156097..f7537b466b23 100644 --- a/arch/arc/lib/Makefile +++ b/arch/arc/lib/Makefile @@ -8,4 +8,10 @@ lib-y := strchr-700.o strcpy-700.o strlen.o memcmp.o lib-$(CONFIG_ISA_ARCOMPACT) += memcpy-700.o memset.o strcmp.o -lib-$(CONFIG_ISA_ARCV2) += memcpy-archs.o memset-archs.o strcmp-archs.o +lib-$(CONFIG_ISA_ARCV2) += memset-archs.o strcmp-archs.o + +ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS +lib-$(CONFIG_ISA_ARCV2) +=memcpy-archs-unaligned.o +else +lib-$(CONFIG_ISA_ARCV2) +=memcpy-archs.o +endif diff --git a/arch/arc/lib/memcpy-archs-unaligned.S b/arch/arc/lib/memcpy-archs-unaligned.S new file mode 100644 index 000000000000..28993a73fdde --- /dev/null +++ b/arch/arc/lib/memcpy-archs-unaligned.S @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * ARCv2 memcpy implementation optimized for unaligned memory access using. + * + * Copyright (C) 2019 Synopsys + * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com> + */ + +#include <linux/linkage.h> + +#ifdef CONFIG_ARC_HAS_LL64 +# define LOADX(DST,RX) ldd.ab DST, [RX, 8] +# define STOREX(SRC,RX) std.ab SRC, [RX, 8] +# define ZOLSHFT 5 +# define ZOLAND 0x1F +#else +# define LOADX(DST,RX) ld.ab DST, [RX, 4] +# define STOREX(SRC,RX) st.ab SRC, [RX, 4] +# define ZOLSHFT 4 +# define ZOLAND 0xF +#endif + +ENTRY_CFI(memcpy) + mov r3, r0 ; don;t clobber ret val + + lsr.f lp_count, r2, ZOLSHFT + lpnz @.Lcopy32_64bytes + ;; LOOP START + LOADX (r6, r1) + LOADX (r8, r1) + LOADX (r10, r1) + LOADX (r4, r1) + STOREX (r6, r3) + STOREX (r8, r3) + STOREX (r10, r3) + STOREX (r4, r3) +.Lcopy32_64bytes: + + and.f lp_count, r2, ZOLAND ;Last remaining 31 bytes + lpnz @.Lcopyremainingbytes + ;; LOOP START + ldb.ab r5, [r1, 1] + stb.ab r5, [r3, 1] +.Lcopyremainingbytes: + + j [blink] +END_CFI(memcpy) diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S index d61044dd8b58..ea14b0bf3116 100644 --- a/arch/arc/lib/memcpy-archs.S +++ b/arch/arc/lib/memcpy-archs.S @@ -25,15 +25,11 @@ #endif #ifdef CONFIG_ARC_HAS_LL64 -# define PREFETCH_READ(RX) prefetch [RX, 56] -# define PREFETCH_WRITE(RX) prefetchw [RX, 64] # define LOADX(DST,RX) ldd.ab DST, [RX, 8] # define STOREX(SRC,RX) std.ab SRC, [RX, 8] # define ZOLSHFT 5 # define ZOLAND 0x1F #else -# define PREFETCH_READ(RX) prefetch [RX, 28] -# define PREFETCH_WRITE(RX) prefetchw [RX, 32] # define LOADX(DST,RX) ld.ab DST, [RX, 4] # define STOREX(SRC,RX) st.ab SRC, [RX, 4] # define ZOLSHFT 4 @@ -41,8 +37,6 @@ #endif ENTRY_CFI(memcpy) - prefetch [r1] ; Prefetch the read location - prefetchw [r0] ; Prefetch the write location mov.f 0, r2 ;;; if size is zero jz.d [blink] @@ -72,8 +66,6 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy32_64bytes ;; LOOP START LOADX (r6, r1) - PREFETCH_READ (r1) - PREFETCH_WRITE (r3) LOADX (r8, r1) LOADX (r10, r1) LOADX (r4, r1) @@ -117,9 +109,7 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy8bytes_1 ;; LOOP START ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location SHIFT_1 (r7, r6, 24) or r7, r7, r5 @@ -162,9 +152,7 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy8bytes_2 ;; LOOP START ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location SHIFT_1 (r7, r6, 16) or r7, r7, r5 @@ -204,9 +192,7 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy8bytes_3 ;; LOOP START ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location SHIFT_1 (r7, r6, 8) or r7, r7, r5 |
