linux-kernel - Re: [PATCH] cpufreq: amd_pstate: Fix invalid write to MSR_AMD_CPPC

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <CAJZ5v0gtn4UCEu7tafO7AXfD6TOm7m7keq0RO2CR8QX3vEC30Q@mail.gmail.com>
Date:   Wed, 15 Feb 2023 15:55:33 +0100
From:   "Rafael J. Wysocki" <rafael@...nel.org>
To:     Huang Rui <ray.huang@....com>, "Karny, Wyes" <wyes.karny@....com>
Cc:     Rafael J Wysocki <rafael@...nel.org>,
        Viresh Kumar <viresh.kumar@...aro.org>,
        "Yuan, Perry" <Perry.Yuan@....com>, Arnd Bergmann <arnd@...db.de>,
        "Limonciello, Mario" <Mario.Limonciello@....com>,
        "linux-pm@...r.kernel.org" <linux-pm@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] cpufreq: amd_pstate: Fix invalid write to MSR_AMD_CPPC_REQ

On Wed, Feb 15, 2023 at 1:35 PM Huang Rui <ray.huang@....com> wrote:
>
> On Tue, Feb 14, 2023 at 03:58:11PM +0800, Karny, Wyes wrote:
> > `amd_pstate_set_epp` function uses `cppc_req_cached` and `epp` variable
> > to update the MSR_AMD_CPPC_REQ register for AMD MSR systems. The recent
> > commit 7cca9a9851a5 ("cpufreq: amd-pstate: avoid uninitialized variable
> > use") changed the sequence of updating cppc_req_cached and writing the
> > MSR_AMD_CPPC_REQ. Therefore while switching from powersave to
> > performance governor and vice-versa in active mode MSR_AMD_CPPC_REQ is
> > set with the previous cached value. To fix this: first update the
> > `cppc_req_cached` variable and then call `amd_pstate_set_epp` function.
> >
> > - Before commit 7cca9a9851a5 ("cpufreq: amd-pstate: avoid uninitialized
> > variable use"):
> >
> > With powersave governor:
> > [    1.652743] amd_pstate_epp_init: writing to cppc_req_cached = 0x1eff
> > [    1.652744] amd_pstate_set_epp: writing cppc_req_cached = 0x1eff
> > [    1.652746] amd_pstate_set_epp: writing min_perf = 30, des_perf = 0, max_perf = 255, epp = 0
> >
> > Changing to performance governor:
> > [  300.493842] amd_pstate_epp_init: writing to cppc_req_cached = 0xffff
> > [  300.493846] amd_pstate_set_epp: writing cppc_req_cached = 0xffff
> > [  300.493847] amd_pstate_set_epp: writing min_perf = 255, des_perf = 0, max_perf = 255, epp = 0
> >
> > - After commit 7cca9a9851a5 ("cpufreq: amd-pstate: avoid uninitialized
> > variable use"):
> >
> > With powersave governor:
> > [    1.646037] amd_pstate_set_epp: writing cppc_req_cached = 0xffff
> > [    1.646038] amd_pstate_set_epp: writing min_perf = 255, des_perf = 0, max_perf = 255, epp = 0
> > [    1.646042] amd_pstate_epp_init: writing to cppc_req_cached = 0x1eff
> >
> > Changing to performance governor:
> > [  687.117401] amd_pstate_set_epp: writing cppc_req_cached = 0x1eff
> > [  687.117405] amd_pstate_set_epp: writing min_perf = 30, des_perf = 0, max_perf = 255, epp = 0
> > [  687.117419] amd_pstate_epp_init: writing to cppc_req_cached = 0xffff
> >
> > - After this fix:
> >
> > With powersave governor:
> > [    2.525717] amd_pstate_epp_init: writing to cppc_req_cached = 0x1eff
> > [    2.525720] amd_pstate_set_epp: writing cppc_req_cached = 0x1eff
> > [    2.525722] amd_pstate_set_epp: writing min_perf = 30, des_perf = 0, max_perf = 255, epp = 0
> >
> > Changing to performance governor:
> > [ 3440.152468] amd_pstate_epp_init: writing to cppc_req_cached = 0xffff
> > [ 3440.152473] amd_pstate_set_epp: writing cppc_req_cached = 0xffff
> > [ 3440.152474] amd_pstate_set_epp: writing min_perf = 255, des_perf = 0, max_perf = 255, epp = 0
> >
> > Fixes: 7cca9a9851a5 ("cpufreq: amd-pstate: avoid uninitialized variable use")
> > Signed-off-by: Wyes Karny <wyes.karny@....com>
>
> That's really nice catch! Thanks Wyes.
>
> Acked-by: Huang Rui <ray.huang@....com>

Applied, thanks!