linux-kernel - Re: [Patch v2 15/24] perf/x86/intel: Add SSP register support for arch-PEBS

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

Message-ID: <5bbed578-db74-408d-a92e-76d869054738@linux.intel.com>
Date: Wed, 26 Feb 2025 14:56:00 +0800
From: "Mi, Dapeng" <dapeng1.mi@...ux.intel.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...hat.com>, Arnaldo Carvalho de Melo
 <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
 Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>,
 Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
 Kan Liang <kan.liang@...ux.intel.com>, Andi Kleen <ak@...ux.intel.com>,
 Eranian Stephane <eranian@...gle.com>, linux-kernel@...r.kernel.org,
 linux-perf-users@...r.kernel.org, Dapeng Mi <dapeng1.mi@...el.com>
Subject: Re: [Patch v2 15/24] perf/x86/intel: Add SSP register support for
 arch-PEBS


On 2/25/2025 7:52 PM, Peter Zijlstra wrote:
> On Tue, Feb 18, 2025 at 03:28:09PM +0000, Dapeng Mi wrote:
>
>> +	if (unlikely(event->attr.sample_regs_intr & BIT_ULL(PERF_REG_X86_SSP))) {
>> +		/* Only arch-PEBS supports to capture SSP register. */
>> +		if (!x86_pmu.arch_pebs || !event->attr.precise_ip)
>> +			return -EINVAL;
>> +	}
>> @@ -27,9 +27,11 @@ enum perf_event_x86_regs {
>>  	PERF_REG_X86_R13,
>>  	PERF_REG_X86_R14,
>>  	PERF_REG_X86_R15,
>> +	/* Shadow stack pointer (SSP) present on Clearwater Forest and newer models. */
>> +	PERF_REG_X86_SSP,
> The first comment makes more sense. Nobody knows of cares what a
> clearwater forest is, but ARCH-PEBS is something you can check.

Sure. would modify it in next version.


>
> Also, this hard implies that anything exposing ARCH-PEBS exposes
> CET-SS. Does virt complicate this?

Yes, for real HW, I think CET-SS would be always supported as long as
arch-PEBS is supported, but it's not true for virt. So suppose we need to
check CET-SS is supported before reading it.


>