Merge branch 'for-linus' into for-next

[karo-tx-linux.git] / arch / arm64 / lib / copy_page.S

diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index 512b9a7b980e98bbed9a699107e936e4b1913dca..4c1e700840b6ced5a0b2f868bfb4f37dddc8abc0 100644 (file)
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -18,6 +18,8 @@
 #include <linux/const.h>
 #include <asm/assembler.h>
 #include <asm/page.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
 
 /*
  * Copy a page from src to dest (both are page aligned)
@@ -27,20 +29,65 @@
  *     x1 - src
  */
 ENTRY(copy_page)
-       /* Assume cache line size is 64 bytes. */
-       prfm    pldl1strm, [x1, #64]
-1:     ldp     x2, x3, [x1]
+alternative_if_not ARM64_HAS_NO_HW_PREFETCH
+       nop
+       nop
+alternative_else
+       # Prefetch two cache lines ahead.
+       prfm    pldl1strm, [x1, #128]
+       prfm    pldl1strm, [x1, #256]
+alternative_endif
+
+       ldp     x2, x3, [x1]
        ldp     x4, x5, [x1, #16]
        ldp     x6, x7, [x1, #32]
        ldp     x8, x9, [x1, #48]
-       add     x1, x1, #64
-       prfm    pldl1strm, [x1, #64]
+       ldp     x10, x11, [x1, #64]
+       ldp     x12, x13, [x1, #80]
+       ldp     x14, x15, [x1, #96]
+       ldp     x16, x17, [x1, #112]
+
+       mov     x18, #(PAGE_SIZE - 128)
+       add     x1, x1, #128
+1:
+       subs    x18, x18, #128
+
+alternative_if_not ARM64_HAS_NO_HW_PREFETCH
+       nop
+alternative_else
+       prfm    pldl1strm, [x1, #384]
+alternative_endif
+
        stnp    x2, x3, [x0]
+       ldp     x2, x3, [x1]
        stnp    x4, x5, [x0, #16]
+       ldp     x4, x5, [x1, #16]
        stnp    x6, x7, [x0, #32]
+       ldp     x6, x7, [x1, #32]
        stnp    x8, x9, [x0, #48]
-       add     x0, x0, #64
-       tst     x1, #(PAGE_SIZE - 1)
-       b.ne    1b
+       ldp     x8, x9, [x1, #48]
+       stnp    x10, x11, [x0, #64]
+       ldp     x10, x11, [x1, #64]
+       stnp    x12, x13, [x0, #80]
+       ldp     x12, x13, [x1, #80]
+       stnp    x14, x15, [x0, #96]
+       ldp     x14, x15, [x1, #96]
+       stnp    x16, x17, [x0, #112]
+       ldp     x16, x17, [x1, #112]
+
+       add     x0, x0, #128
+       add     x1, x1, #128
+
+       b.gt    1b
+
+       stnp    x2, x3, [x0]
+       stnp    x4, x5, [x0, #16]
+       stnp    x6, x7, [x0, #32]
+       stnp    x8, x9, [x0, #48]
+       stnp    x10, x11, [x0, #64]
+       stnp    x12, x13, [x0, #80]
+       stnp    x14, x15, [x0, #96]
+       stnp    x16, x17, [x0, #112]
+
        ret
 ENDPROC(copy_page)