On that Spectre mitigations discussion

By now, almost everybody has probably seen the press coverage of Linus Torvalds's remarks about one of thepatches addressing Spectre variant 2. Less noted, but much moreinformative, is David Woodhouse's responseon why those patches are the way they are. "That's why my initialidea, as implemented in this RFC patchset, was to stick with IBRS onSkylake, and use retpoline everywhere else. I'll give you 'garbagepatches', but they weren't being 'just mindlessly sent around'. If we'regoing to drop IBRS support and accept the caveats, then let's do it as aconscious decision having seen what it would look like, not just drop itquietly because poor Davey is too scared that Linus might shout at himagain."