After allocating 32MB or more contiguous memory, huge pages
would seem to be ideal.
Signed-off-by: Richard Henderson <[email protected]>
Signed-off-by: Blue Swirl <[email protected]>
exit(1);
}
+ qemu_madvise(code_gen_buffer, code_gen_buffer_size, QEMU_MADV_HUGEPAGE);
+
/* Steal room for the prologue at the end of the buffer. This ensures
(via the MAX_CODE_GEN_BUFFER_SIZE limits above) that direct branches
from TB's to the prologue are going to be in range. It also means