diff options
| author |   Mauro Carvalho Chehab <mchehab+samsung@kernel.org> | 2019-02-18 10:12:12 -0500 |
|---|---|---|
| committer | Mauro Carvalho Chehab <mchehab+samsung@kernel.org> | 2019-02-18 10:12:12 -0500 |
| commit | 5f09bc8cc4010a3ea17c5881a62fc45192ebe7b0 (patch) | |
| tree | c8e30ba4eaf357699ef97a786bf56661f4591be8 /arch/arc/lib/memset-archs.S | |
| parent | media: vimc: fill in bus_info in media_device_info (diff) | |
| parent | Linux 5.0-rc7 (diff) | |
| download | linux-dev-5f09bc8cc4010a3ea17c5881a62fc45192ebe7b0.tar.xz linux-dev-5f09bc8cc4010a3ea17c5881a62fc45192ebe7b0.zip | |
Merge tag 'v5.0-rc7' into patchwork
Linux 5.0-rc7
* tag 'v5.0-rc7': (1667 commits)
Linux 5.0-rc7
Input: elan_i2c - add ACPI ID for touchpad in Lenovo V330-15ISK
Input: st-keyscan - fix potential zalloc NULL dereference
Input: apanel - switch to using brightness_set_blocking()
powerpc/64s: Fix possible corruption on big endian due to pgd/pud_present()
efi/arm: Revert "Defer persistent reservations until after paging_init()"
arm64, mm, efi: Account for GICv3 LPI tables in static memblock reserve table
sunrpc: fix 4 more call sites that were using stack memory with a scatterlist
include/linux/module.h: copy __init/__exit attrs to init/cleanup_module
Compiler Attributes: add support for __copy (gcc >= 9)
lib/crc32.c: mark crc32_le_base/__crc32c_le_base aliases as __pure
auxdisplay: ht16k33: fix potential user-after-free on module unload
x86/platform/UV: Use efi_runtime_lock to serialise BIOS calls
i2c: bcm2835: Clear current buffer pointers and counts after a transfer
i2c: cadence: Fix the hold bit setting
drm: Use array_size() when creating lease
dm thin: fix bug where bio that overwrites thin block ignores FUA
Revert "exec: load_script: don't blindly truncate shebang string"
Revert "gfs2: read journal in large chunks to locate the head"
net: ethernet: freescale: set FEC ethtool regs version
...
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Diffstat (limited to 'arch/arc/lib/memset-archs.S')
| -rw-r--r-- | arch/arc/lib/memset-archs.S | 40 |
1 files changed, 32 insertions, 8 deletions
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] |