linux-kernel - [PATCH V2 0/9] x86/intel_rdt: MBA integration fixes

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

Message-Id: <1537048707-76280-1-git-send-email-fenghua.yu@intel.com>
Date:   Sat, 15 Sep 2018 14:58:18 -0700
From:   Fenghua Yu <fenghua.yu@...el.com>
To:     "Thomas Gleixner" <tglx@...utronix.de>,
        "Ingo Molnar" <mingo@...hat.com>, "H Peter Anvin" <hpa@...or.com>,
        "Tony Luck" <tony.luck@...el.com>
Cc:     "Chatre, Reinette" <reinette.chatre@...el.com>,
        "Xiaochen Shen" <xiaochen.shen@...el.com>,
        "Chen Yu" <yu.c.chen@...el.com>,
        "linux-kernel" <linux-kernel@...r.kernel.org>,
        "x86" <x86@...nel.org>, "Fenghua Yu" <fenghua.yu@...el.com>
Subject: [PATCH V2 0/9] x86/intel_rdt: MBA integration fixes

Chen Yu reported an issue where reading the resctrl "size" file results in
a divide-by-zero issue on a system with a MBA resource. Further
investigation revealed more issues where the recent RDT features are not
well integrated with the MBA resource handling.

This series consists out of:
 - One helper function in support of fixes that need to know the number of
   supported CLOSIDs on the system (the minimum of all CLOSIDs of all
   resources).
 - The fix to the issue reported by Chen Yu  - now reading a resource
   group's "size" file will show a MB resource's allocation as its size.
 - A fix from Xiaochen Shen to the MB parsing callback that was never
   changed to accept a new parameter format.
 - Functions that iterate over the number of CLOSIDs need to take care
   whether it is using a particular resource's supported CLOSIDs or the
   number of CLOSIDs supported by the system. This was done incorrectly in
   a few places and fixed here.
 - When a new resource group is created it is intended to be configured
   with sane defaults. This new feature blindly assumed that the resource
   group only consists out of cache resources - make this explicit to not
   cause invalid register writes on a system with MBA resources.
 - The new "exclusive" mode assumes that all resources support a CBM, while
   a MBA resource does not. Since the MBA resource allocations cannot be
   done in a way to specify whether allocations can overlap or not the
   "exclusive" mode of a resource group will only apply to the cache
   resources within the group, if only a MBA resource is present then
   "exclusive" mode will not be allowed.

Changelog
v2:
 - Patch 1: Change 'data' from void pointer to struct rdt_parse_data
   pointer in parsing callbacks based on suggestion from Thomas.
 - Patch 2, 4, 5: Condense backtraces in commit description to minimum
   based on suggestion from Thomas

Reinette Chatre (8):
  x86/intel_rdt: Fix size reporting of MBA resource
  x86/intel_rdt: Global closid helper to support future fixes
  x86/intel_rdt: Fix invalid mode warning when multiple resources are
    managed
  x86/intel_rdt: Fix unchecked MSR access
  x86/intel_rdt: Do not allow pseudo-locking of MBA resource
  x86/intel_rdt: Fix incorrect loop end condition
  x86/intel_rdt: Fix exclusive mode handling of MBA resource
  x86/intel_rdt: Fix incorrect loop end condition

Xiaochen Shen (1):
  x86/intel_rdt: Fix data type in parsing callbacks

 arch/x86/kernel/cpu/intel_rdt.h             | 17 +++++--
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 27 ++++++-----
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 53 +++++++++++++++++----
 3 files changed, 71 insertions(+), 26 deletions(-)

-- 
2.19.0