linux-kernel - A Question about the patch "[PATCH v8 3/4] PCI: Introduce disable_acs

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>] [day] [month] [year] [list]

Message-ID: <CAPPcaqPhQ2jJ=wRHf5_hVQAT-9gtn7EZv4y+68dEzgsZv7pTMw@mail.gmail.com>
Date:   Mon, 7 Oct 2019 16:25:49 -0400
From:   Guy Crazy <superymk.adv@...il.com>
To:     linux-kernel@...r.kernel.org
Subject: A Question about the patch "[PATCH v8 3/4] PCI: Introduce
 disable_acs_redir quirk"

Hi,

I have a question about this patch from the web link
(https://lwn.net/ml/linux-kernel/20180730161840.13733-4-logang@deltatee.com/).
According to the PCIe spec (PCIe 3.0), ACS Upstream Forwarding (UF)
seems quite similar with Request Redirect (RR). Why
pci_quirk_disable_intel_spt_pch_acs_redir in this patch seems disable
RR but not UF?

One related question in further: what's the difference between UF and
RR (examples preferred)? Both seems redirect traffics originated from
downstreams. Especially I feel confused about UF in the PCIe spec:
PCIe switches must always route upstream requests towards RC because
they target upstream destinations, why these switches need UF config?

Thanks!