Received-SPF: pass (google.com: domain of linux-kernel+bounces-40535-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Date: Fri, 26 Jan 2024 19:56:49 +0100
From: Borislav Petkov <bp@alien8.de>
To: "Luck, Tony" <tony.luck@intel.com>
Cc: Avadhut Naik <avadhut.naik@amd.com>,
	"linux-trace-kernel@vger.kernel.org" <linux-trace-kernel@vger.kernel.org>,
	"linux-edac@vger.kernel.org" <linux-edac@vger.kernel.org>,
	"rostedt@goodmis.org" <rostedt@goodmis.org>,
	"x86@kernel.org" <x86@kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"yazen.ghannam@amd.com" <yazen.ghannam@amd.com>,
	"avadnaik@amd.com" <avadnaik@amd.com>
Subject: Re: [PATCH v2 0/2] Update mce_record tracepoint
Message-ID: <20240126185649.GFZbQAccZphdW_0CkH@fat_crate.local>
References: <20240125184857.851355-1-avadhut.naik@amd.com>
 <20240125185821.GDZbKvTW93APAiY1LP@fat_crate.local>
 <SJ1PR11MB6083DAA7A6EDBBDAF5987A80FC7A2@SJ1PR11MB6083.namprd11.prod.outlook.com>
 <20240126102721.GCZbOJCTqTVmvgOEuM@fat_crate.local>
 <SJ1PR11MB60839509241AA98A59B78D15FC792@SJ1PR11MB6083.namprd11.prod.outlook.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <SJ1PR11MB60839509241AA98A59B78D15FC792@SJ1PR11MB6083.namprd11.prod.outlook.com>

On Fri, Jan 26, 2024 at 05:10:20PM +0000, Luck, Tony wrote:
> 12 extra bytes divided by (say) 64GB (a very small server these days, may laptop has that much)
>    = 0.00000001746%
> 
> We will need 57000 changes like this one before we get to 0.001% :-)

You're forgetting that those 12 bytes repeat per MCE tracepoint logged.
And there's other code which adds more 0.01% here and there, well,
because we can.

> But the key there is keeping the details of the source machine attached to
> the error record. My first contact with machine check debugging is always
> just the raw error record (from mcelog, rasdaemon, or console log).

Yes, that is somewhat sensible reason to have the PPIN together with the
MCE record.

> Knowing which microcode version was loaded on a core *at the time of
> the error* is critical. 

So is the rest of the debug info you're going to need from that machine.
And yet we're not adding that to the tracepoint.

> You've spent enough time with Ashok and Thomas tweaking the Linux
> microcode driver to know that going back to the machine the next day
> to ask about microcode version has a bunch of ways to get a wrong
> answer.

Huh, what does that have to do with this?

IIUC, if someone changes something on the system, whether that is
updating microcode or swapping a harddrive or swapping memory or
whatever, that invalidates the errors reported, pretty much.

You can't put it all in the trace record, you just can't. 

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette