linux-kernel - Re: [PATCH 3/5] cxl: Separate coherence from target type

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: <67118ed29b418_3f14294a1@dwillia2-xfh.jf.intel.com.notmuch>
Date: Thu, 17 Oct 2024 15:25:22 -0700
From: Dan Williams <dan.j.williams@...el.com>
To: Huang Ying <ying.huang@...el.com>, Dan Williams
	<dan.j.williams@...el.com>, Dave Jiang <dave.jiang@...el.com>
CC: <linux-cxl@...r.kernel.org>, <linux-kernel@...r.kernel.org>, Huang Ying
	<ying.huang@...el.com>, Gregory Price <gourry@...rry.net>, Davidlohr Bueso
	<dave@...olabs.net>, Jonathan Cameron <jonathan.cameron@...wei.com>, "Alison
 Schofield" <alison.schofield@...el.com>, Vishal Verma
	<vishal.l.verma@...el.com>, Ira Weiny <ira.weiny@...el.com>, Alejandro Lucero
	<alucerop@....com>, Ben Cheatham <benjamin.cheatham@....com>
Subject: Re: [PATCH 3/5] cxl: Separate coherence from target type

Huang Ying wrote:
> Previously, target type (expander or accelerator) and
> coherence (HOSTONLY (HDM-H) or DEV (HDM-D/DB)) are synonym.  So
> current kernel uses target type to designate coherence too.  However,
> it's possible for expanders to use HDM-DB now.  So, the patch
> separates coherence from target type.
> 
> Accordingly, the patch sets the HOSTONLY field of decoder ctrl
> register (CXL_HDM_DECODER0_CTRL_HOSTONLY) according to the coherence
> instead of the target type.
> 
> Because we cannot determine the coherence of decoders via target type,
> the patch lets accelerator/expander device drivers specify coherence
> explicitly via newly added coherence field in struct cxl_dev_state.
> 
> The coherence of each end points in a region needs to be same.  So,
> the patch records the coherence of the first added end point in struct
> region.  Then, it checks whether the coherence of all other end points
> is same.

The target type is the coherence type, I am not sure what is motivating
this separation?

The decoder must match the mode of window it is joining because both
HDM-D and HDM-DB speak a different protocol than HDM.