On 14/03/2018 16:54, Christopher Lameter wrote: >>> + pushq %rax /* Support Position Independent Code */ >>> + leaq 1f(%rip), %rax /* RIP */ >>> + xchgq %rax, (%rsp) /* Restore RAX, put 1f */ >>> iretq /* continues at repeat_nmi below */ >>> UNWIND_HINT_IRET_REGS >>> 1: >> Urgh, xchg with a memop has an implicit LOCK prefix. > this_cpu_xchg uses no lock cmpxchg as a replacement to reduce latency. That requires using a second register, since %rax is used as the comparison source. At this point it's easier to just push %rax twice: pushq %rax pushq %rax leaq 1f(%ip), %rax movq %rax, 8(%rsp) popq %rax iretq Paolo _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/virtualization
