Re: [RFC PATCH v6 01/26] Documentation/x86: Add CET description
From: Ingo Molnar <mingo@kernel.org>
Date: 2018-11-21 07:24:51
Also in:
linux-arch, linux-doc, linux-mm, lkml
From: Ingo Molnar <mingo@kernel.org>
Date: 2018-11-21 07:24:51
Also in:
linux-arch, linux-doc, linux-mm, lkml
* Yu-cheng Yu [off-list ref] wrote:
On Tue, 2018-11-20 at 10:52 +0100, Ingo Molnar wrote:quoted
* Yu-cheng Yu [off-list ref] wrote:quoted
+X86 Documentation [...] + +At run time, /proc/cpuinfo shows the availability of SHSTK and IBT.What is the rough expected performance impact of CET on average function call frequency user applications and the kernel itself?I don't have any conclusive numbers yet; but since currently only user-mode protection is implemented, I suspect any impact would be most likely to the application. The kernel would spend some small amount of time on the setup of CET.
This is horribly vague. Thanks, Ingo