diff options
Diffstat (limited to 'arch/arc/lib')
| -rw-r--r-- | arch/arc/lib/memcpy-archs.S | 14 | ||||
| -rw-r--r-- | arch/arc/lib/memset-archs.S | 40 |
2 files changed, 32 insertions, 22 deletions
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 diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S index 62ad4bcb841a..f230bb7092fd 100644 --- a/arch/arc/lib/memset-archs.S +++ b/arch/arc/lib/memset-archs.S @@ -7,11 +7,39 @@ */ #include <linux/linkage.h> +#include <asm/cache.h> -#undef PREALLOC_NOT_AVAIL +/* + * The memset implementation below is optimized to use prefetchw and prealloc + * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6) + * If you want to implement optimized memset for other possible L1 data cache + * line lengths (32B and 128B) you should rewrite code carefully checking + * we don't call any prefetchw/prealloc instruction for L1 cache lines which + * don't belongs to memset area. + */ + +#if L1_CACHE_SHIFT == 6 + +.macro PREALLOC_INSTR reg, off + prealloc [\reg, \off] +.endm + +.macro PREFETCHW_INSTR reg, off + prefetchw [\reg, \off] +.endm + +#else + +.macro PREALLOC_INSTR +.endm + +.macro PREFETCHW_INSTR +.endm + +#endif ENTRY_CFI(memset) - prefetchw [r0] ; Prefetch the write location + PREFETCHW_INSTR r0, 0 ; Prefetch the first write location mov.f 0, r2 ;;; if size is zero jz.d [blink] @@ -48,11 +76,8 @@ ENTRY_CFI(memset) lpnz @.Lset64bytes ;; LOOP START -#ifdef PREALLOC_NOT_AVAIL - prefetchw [r3, 64] ;Prefetch the next write location -#else - prealloc [r3, 64] -#endif + PREALLOC_INSTR r3, 64 ; alloc next line w/o fetching + #ifdef CONFIG_ARC_HAS_LL64 std.ab r4, [r3, 8] std.ab r4, [r3, 8] @@ -85,7 +110,6 @@ ENTRY_CFI(memset) lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes lpnz .Lset32bytes ;; LOOP START - prefetchw [r3, 32] ;Prefetch the next write location #ifdef CONFIG_ARC_HAS_LL64 std.ab r4, [r3, 8] std.ab r4, [r3, 8] |