linux-kernel - [PATCH v2 0/8] Tegra GART driver clean up and optimization

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]

Date:   Sat,  4 Aug 2018 17:29:55 +0300
From:   Dmitry Osipenko <digetx@...il.com>
To:     Joerg Roedel <joro@...tes.org>,
        Robin Murphy <robin.murphy@....com>,
        Thierry Reding <thierry.reding@...il.com>,
        Jonathan Hunter <jonathanh@...dia.com>
Cc:     iommu@...ts.linux-foundation.org, linux-tegra@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: [PATCH v2 0/8] Tegra GART driver clean up and optimization

Hello,

This patch-series makes GART driver one step closer to become actually
usable by addressing the following:

1. Thierry noticed that Memory Controller driver uses registers that belong
   to GART in [0] and for now MC driver only reports the fact of GART's page
   fault. The first two patches of the series are addressing this shortcoming
   by providing integration of the MC driver with the GART.

   [0] https://www.spinics.net/lists/linux-tegra/msg33072.html

2. Currently GART has bee kept disabled by the commit c7e3ca515e784
   ("iommu/tegra: gart: Do not register with bus"). If GART is re-enabled than
   all devices in the system are getting assigned to the GART as it is a global
   systems IOMMU provider. This is wrong simply because GART doesn't handle all
   those devices. This series makes GART to accept only devices that are
   explicitly assigned to GART in device tree using 'iommu' phandle.

3. This series makes a generic clean up of the driver, like removing dead code.

4. This series introduces and utilizes iotlb_sync_map() callback that was
   previously suggested by Joerg Roedel in [1], optimizing mapping / unmapping
   performance.

   [1] https://www.spinics.net/lists/linux-tegra/msg32914.html

Changelog:

v2: Addressed review comments from Robin Murphy to v1 by moving devices
    iommu_fwspec check to gart_iommu_add_device().

    Dropped the "Provide single domain and group for all devices" patch from
    the series for now because after some more considering it became not
    exactly apparent whether that is what we need, that was also suggested
    by Robin Murphy in the review comment. Maybe something like a runtime
    IOMMU usage for devices would be a better solution, allowing to implement
    transparent context switching of virtual IOMMU domains.

    Some very minor code cleanups, reworded commit messages.

Dmitry Osipenko (8):
  memory: tegra: Provide facility for integration with the GART driver
  iommu/tegra: gart: Provide access to Memory Controller driver
  iommu/tegra: gart: Clean up drivers module code
  iommu/tegra: gart: Remove pr_fmt and clean up includes
  iommu/tegra: gart: Clean up driver probe errors handling
  iommu/tegra: gart: Ignore devices without IOMMU phandle in DT
  iommu: Introduce iotlb_sync_map callback
  iommu/tegra: gart: Optimize mapping / unmapping performance

 drivers/iommu/iommu.c      |  8 ++-
 drivers/iommu/tegra-gart.c | 99 +++++++++++++++++++++++---------------
 drivers/memory/tegra/mc.c  | 26 ++++++++--
 include/linux/iommu.h      |  1 +
 include/soc/tegra/mc.h     | 13 +++++
 5 files changed, 103 insertions(+), 44 deletions(-)

-- 
2.18.0