arm64/lib: copy_page: avoid x18 register in assembler code

Register x18 will no longer be used as a caller save register in the
future, so stop using it in the copy_page() code.

Link: https://patchwork.kernel.org/patch/9836869/
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
[Sami: changed the offset and bias to be explicit]
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>

diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index bbb8562..290dd3c 100644 (file)
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -34,45 +34,45 @@ alternative_else_nop_endif
        ldp     x14, x15, [x1, #96]
        ldp     x16, x17, [x1, #112]
 
-       mov     x18, #(PAGE_SIZE - 128)
+       add     x0, x0, #256
        add     x1, x1, #128
 1:
-       subs    x18, x18, #128
+       tst     x0, #(PAGE_SIZE - 1)
 
 alternative_if ARM64_HAS_NO_HW_PREFETCH
        prfm    pldl1strm, [x1, #384]
 alternative_else_nop_endif
 
-       stnp    x2, x3, [x0]
+       stnp    x2, x3, [x0, #-256]
        ldp     x2, x3, [x1]
-       stnp    x4, x5, [x0, #16]
+       stnp    x4, x5, [x0, #16 - 256]
        ldp     x4, x5, [x1, #16]
-       stnp    x6, x7, [x0, #32]
+       stnp    x6, x7, [x0, #32 - 256]
        ldp     x6, x7, [x1, #32]
-       stnp    x8, x9, [x0, #48]
+       stnp    x8, x9, [x0, #48 - 256]
        ldp     x8, x9, [x1, #48]
-       stnp    x10, x11, [x0, #64]
+       stnp    x10, x11, [x0, #64 - 256]
        ldp     x10, x11, [x1, #64]
-       stnp    x12, x13, [x0, #80]
+       stnp    x12, x13, [x0, #80 - 256]
        ldp     x12, x13, [x1, #80]
-       stnp    x14, x15, [x0, #96]
+       stnp    x14, x15, [x0, #96 - 256]
        ldp     x14, x15, [x1, #96]
-       stnp    x16, x17, [x0, #112]
+       stnp    x16, x17, [x0, #112 - 256]
        ldp     x16, x17, [x1, #112]
 
        add     x0, x0, #128
        add     x1, x1, #128
 
-       b.gt    1b
+       b.ne    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]
+       stnp    x2, x3, [x0, #-256]
+       stnp    x4, x5, [x0, #16 - 256]
+       stnp    x6, x7, [x0, #32 - 256]
+       stnp    x8, x9, [x0, #48 - 256]
+       stnp    x10, x11, [x0, #64 - 256]
+       stnp    x12, x13, [x0, #80 - 256]
+       stnp    x14, x15, [x0, #96 - 256]
+       stnp    x16, x17, [x0, #112 - 256]
 
        ret
 ENDPROC(copy_page)