>>> On 05.06.15 at 15:31, wrote:
> Both the trampoline copy and BSS initialise can be performed more efficiently
> by using 4-byte varients of the string operations.
On second thought I'm actually not convinced of this: With
X86_FEATURE_ERMS using byte MOVS/STOS is supposedly
preferred.
> --- a/
Both the trampoline copy and BSS initialise can be performed more efficiently
by using 4-byte varients of the string operations.
The ALIGN(STACK_SIZE) actually belongs with .bss.stack_aligned, but __init_end
still needs page alignment because of the init sections being freed and
returned to the do
