Re: [kernel-hardening] Re: [PATCH 1/2] security, perf: allow further restriction of perf_event_open

[Daniel Micay]

On Thu, 2016-08-04 at 11:28 +0100, Mark Rutland wrote:
> On Wed, Aug 03, 2016 at 03:36:16PM -0400, Daniel Micay wrote:
> > 
> > There's a lot of architecture and vendor specific perf events code
> > and
> > lots of bleeding edge features. On Android, a lot of the perf events
> > vulnerabilities have been specific to the Qualcomm SoC platform.
> > Other
> > platforms are likely just receiving a lot less attention.
> 
> Are the relevant perf drivers for those platforms upstream? I've seen
> no
> patches addressing security issues in the ARMv7 krait+Scorpion PMU
> driver since it was added, and there's no ARMv8 QCOM PMU driver.
> 
> If there are outstanding issues, please report them upstream.
> 
> FWIW, I've used Vince Weaver's perf fuzzer to test the ARM PMU code
> (both the framework and drivers), so other platforms are seeing some
> attention. That said, I haven't done that recently.

Qualcomm's perf driver is out-of-tree along with most of their other
drivers. Their drivers add up to a LOT of code shared across over a
billion mobile devices, leading to the focus on them. It also helps that
there are bounties for Nexus devices, so there are multi thousand dollar
rewards for bugs in the Qualcomm drivers compared to nothing for other
platforms / drivers. Now that perf is only available via ADB debugging,
further perf bugs no longer technically qualify for their bounties (but
they might still pay, I don't know).

Attachment: signature.asc
Description: This is a digitally signed message part