Re: Intel CPUs' Kernel Page Table Isolation (KPTI) fix

I wrote:

> However, as Torvalds's interlocutor David Woodhouse then immediately
> pointed out, IBRS does work well enough on Intel Skylake architectures,
> and retpoline on all the other affected Intel architectures, so this is
      ^^^^^^^^^
> not quite the crisis Torvalds's rant would suggest:

In case anyone is wondering, that is a cute neologism for 'return
trampoline', and you can read about the technique here:  
https://stackoverflow.com/questions/48089426/what-is-a-retpoline-and-how-does-it-work

  [A] retpoline is a return trampoline that uses an infinite loop that is
  never executed to prevent the CPU from speculating on the target of an
  indirect jump.