On Mon, Sep 28, 2020 at 11:17:42AM -0700, Dave Hansen wrote: > On 9/28/20 11:12 AM, Andy Lutomirski wrote: > >> endbr64 > >> /* Check if shadow stack is in use. NB: R11 is the only usable > >> scratch register for function calls. */ > >> xorl %r11d, %r11d > >> rdsspq %r11 > >> testq %r11, %r11 > >> jnz 3f > >> call 2f > >> 1: > >> pause > >> lfence > >> jmp 1b > >> 2: > >> mov %rax, (%rsp) > >> ret > >> 3: > >> /* Shadow stack is in use. Make the indirect call. */ > >> call *%rax > >> ret > > What do we expect user programs to do on CET systems? It would be > > nice if we could instead ALTERNATIVE this out if X86_FEATURE_SHSTK. > > Shouldn't we just be able to use X86_FEATURE_RETPOLINE? > > We probably need a mechanism to force X86_FEATURE_SHSTK and > X86_FEATURE_RETPOLINE to be mutually exclusive if we don't have one already. First of all: lets go with boot time patching instead of dynamic detection. It's both easier to implement and by all other merits makes a lot more sense. It was just a thing that I've not used before. That sorted out, does it matter which direction I look it at? I could use either feature flag as basis (and I do not have a personal preference here). /Jarkko
