From mboxrd@z Thu Jan 1 00:00:00 1970 From: Konrad Rzeszutek Wilk Subject: Re: [RFC 09/10] x86/enter: Create macros to restrict/unrestrict Indirect Branch Speculation Date: Fri, 26 Jan 2018 14:02:57 -0500 Message-ID: <20180126190257.GS14668@char.us.oracle.com> References: <7c0b0879-3448-43e4-8380-4708fc787113@default> <50c5d627-8975-184b-b50f-4cc02c5816c5@intel.com> <1516957886.30244.161.camel@infradead.org> <20180126175901.GL26209@tassilo.jf.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Linus Torvalds , David Woodhouse , Dave Hansen , Liran Alon , Laura Abbott , Andrew Lutomirski , Janakarajan Natarajan , Borislav Petkov , "Mallick, Asit K" , Radim =?utf-8?B?S3LEjW3DocWZ?= , KarimAllah Ahmed , Peter Anvin , Jun Nakajima , Ingo Molnar , the arch/x86 maintainers , Ashok Raj , "Van De Ven, Arjan" , Tim Chen , Paolo Bonzini Return-path: Content-Disposition: inline In-Reply-To: <20180126175901.GL26209@tassilo.jf.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Fri, Jan 26, 2018 at 09:59:01AM -0800, Andi Kleen wrote: > On Fri, Jan 26, 2018 at 09:19:09AM -0800, Linus Torvalds wrote: > > On Fri, Jan 26, 2018 at 1:11 AM, David Woodhouse wrote: > > > > > > Do we need to look again at the fact that we've disabled the RSB- > > > stuffing for SMEP? > > > > Absolutely. SMEP helps make people a lot less worried about things, > > but it doesn't fix the "BTB only contains partial addresses" case. > > > > But did we do that "disable stuffing with SMEP"? I'm not seeing it. In > > my tree, it's only conditional on X86_FEATURE_RETPOLINE. > > For Skylake we need RSB stuffing even with SMEP to avoid falling back to the > BTB on underflow. > > It's also always needed with virtualization. -ECONFUSED, see ==> Is this incorrect then? I see: 241 * Skylake era CPUs have a separate issue with *underflow* of the 242 * RSB, when they will predict 'ret' targets from the generic BTB. 243 * The proper mitigation for this is IBRS. If IBRS is not supported 244 * or deactivated in favour of retpolines the RSB fill on context 245 * switch is required. 246 */ which came from this: commit c995efd5a740d9cbafbf58bde4973e8b50b4d761 Author: David Woodhouse Date: Fri Jan 12 17:49:25 2018 +0000 x86/retpoline: Fill RSB on context switch for affected CPUs On context switch from a shallow call stack to a deeper one, as the CPU does 'ret' up the deeper side it may encounter RSB entries (predictions for where the 'ret' goes to) which were populated in userspace. This is problematic if neither SMEP nor KPTI (the latter of which marks userspace pages as NX for the kernel) are active, as malicious code in userspace may then be executed speculatively. Overwrite the CPU's return prediction stack with calls which are predicted to return to an infinite loop, to "capture" speculation if this happens. This is required both for retpoline, and also in conjunction with IBRS for !SMEP && !KPTI. On Skylake+ the problem is slightly different, and an *underflow* of the RSB may cause errant branch predictions to occur. So there it's not so much overwrite, as *filling* the RSB to attempt to prevent it getting empty. This is only a partial solution for Skylake+ since there are many ==>other conditions which may result in the RSB becoming empty. The full <== ==>solution on Skylake+ is to use IBRS, which will prevent the problem even <== when the RSB becomes empty. With IBRS, the RSB-stuffing will not be required on context switch. Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Acked-by: Arjan van de Ven The "full solution" is what is making me confused. > > -Andi