linux-kernel - Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG is used

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]

Date:	Thu, 13 Sep 2007 12:31:00 -0700
From:	"H. Peter Anvin" <hpa@...or.com>
To:	Yinghai Lu <yhlu.kernel@...il.com>
CC:	Andi Kleen <ak@...e.de>, Greg KH <greg@...ah.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Jeff Garzik <jeff@...zik.org>, Martin Mares <mj@....cz>,
	dean gaudet <dean@...tic.org>,
	Robert Richter <robert.richter@....com>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] x86_64: set cfg_size for AMD Family 10h in case MMCONFIG
 is used

Yinghai Lu wrote:
> On 9/13/07, H. Peter Anvin <hpa@...or.com> wrote:
>> Yinghai Lu wrote:
>>> BIOS guys also said that fam 10h need mmconfig via eax accessing, may
>>> need OS do sth, so it is safe to stay with MCFG entry for SB like
>>> mcp55...
>>>
>>> but latest kernel already have that workaround to make mmconfig via eax...
>>>
>> This is actually a good point.  Since the CPU vendor managed to
>> completely fuck up the operation of MMCONFIG itself on this CPU (it's a
>> *MEMORY REFERENCE*, guys!), it is actually to be expected and prudent
>> that BIOS vendors will drop the MCFG entry.  MMCONFIG doesn't actually
>> work on this CPU for any system software which doesn't already know to
>> work around this particular piece of severe braindamage;
>> standards-complicant MMCONFIG isn't supported at all.
> 
> if other mmconfig device on x86 is sick of accessing via eax, may need
> to provide one fam10h_pci_mmcfg to be assigned to raw_pci_ops instead
> and leave pci_mmcfg to default behavior ( *MEMORY REFERENCE*).
> 

We already have the workaround.  WE do.  However, you could easily see
why a BIOS vendor would want to leave out the MCFG ACPI info, since fam
10h's mmconfig is broken.

	-hpa
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/