Messages in this thread |  | | Subject | Re: [PATCH v2 5/8] x86/speculation: Add basic support for IBPB | From | David Woodhouse <> | Date | Sun, 21 Jan 2018 20:07:06 +0000 |
| |
On Sun, 2018-01-21 at 20:54 +0100, Borislav Petkov wrote: > On Sun, Jan 21, 2018 at 07:31:39PM +0000, David Woodhouse wrote: > > > if (boot_cpu_has(X86_FEATURE_IBPB)) > > > wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); > > > > > > Problem solved. > > > > Nope. Plenty of patch sets *did* have the bug above though, until it > > was spotted. > > And that bug is...?
That bug is the *reason* we're arguing about static_cpu_has vs. ALTERNATIVE.
A conditional branch that the CPU sees can be speculated over...
Now, Andrew is right that in a number of cases there will be another serialising instruction before we ever hit a problematic indirect branch. But as I just said elsewhere, I'd really like the *primitives* to support unconditional operation.[unhandled content-type:application/x-pkcs7-signature] |  |