[PATCH v2 00/24] iommu: Refactor DMA domain strictness

[Doug Anderson]

Hi,

On Wed, Jul 28, 2021 at 8:59 AM Robin Murphy <robin.murphy at arm.com> wrote:
>
> Hi all,
>
> Here's v2 where things start to look more realistic, hence the expanded
> CC list. The patches are now based on the current iommu/core branch to
> take John's iommu_set_dma_strict() cleanup into account.
>
> The series remiains in two (or possibly 3) logical parts - for people
> CC'd on cookie cleanup patches, the later parts should not affect you
> since your drivers don't implement non-strict mode anyway; the cleanup
> is all pretty straightforward, but please do yell at me if I've managed
> to let a silly mistake slip through and broken your driver.
>
> This time I have also build-tested x86 as well as arm64 :)
>
> Changes in v2:
>
> - Add iommu_is_dma_domain() helper to abstract flag check (and help
>   avoid silly typos like the one in v1).
> - Tweak a few commit messages for spelling and (hopefully) clarity.
> - Move the iommu_create_device_direct_mappings() update to patch #14
>   where it should have been.
> - Rewrite patch #20 as a conversion of the now-existing option.
> - Clean up the ops->flush_iotlb_all check which is also made redundant
>   by the new domain type
> - Add patch #24, which is arguably tangential, but it was something I
>   spotted during the rebase, so...
>
> Once again, the whole lot is available on a branch here:
>
> https://gitlab.arm.com/linux-arm/linux-rm/-/tree/iommu/fq
>
> Thanks,
> Robin.
>
>
> CC: Marek Szyprowski <m.szyprowski at samsung.com>
> CC: Yoshihiro Shimoda <yoshihiro.shimoda.uh at renesas.com>
> CC: Geert Uytterhoeven <geert+renesas at glider.be>
> CC: Yong Wu <yong.wu at mediatek.com>
> CC: Heiko Stuebner <heiko at sntech.de>
> CC: Chunyan Zhang <chunyan.zhang at unisoc.com>
> CC: Chunyan Zhang <chunyan.zhang at unisoc.com>
> CC: Maxime Ripard <mripard at kernel.org>
> CC: Jean-Philippe Brucker <jean-philippe at linaro.org>
>
> Robin Murphy (24):
>   iommu: Pull IOVA cookie management into the core
>   iommu/amd: Drop IOVA cookie management
>   iommu/arm-smmu: Drop IOVA cookie management
>   iommu/vt-d: Drop IOVA cookie management
>   iommu/exynos: Drop IOVA cookie management
>   iommu/ipmmu-vmsa: Drop IOVA cookie management
>   iommu/mtk: Drop IOVA cookie management
>   iommu/rockchip: Drop IOVA cookie management
>   iommu/sprd: Drop IOVA cookie management
>   iommu/sun50i: Drop IOVA cookie management
>   iommu/virtio: Drop IOVA cookie management
>   iommu/dma: Unexport IOVA cookie management
>   iommu/dma: Remove redundant "!dev" checks
>   iommu: Introduce explicit type for non-strict DMA domains
>   iommu/amd: Prepare for multiple DMA domain types
>   iommu/arm-smmu: Prepare for multiple DMA domain types
>   iommu/vt-d: Prepare for multiple DMA domain types
>   iommu: Express DMA strictness via the domain type
>   iommu: Expose DMA domain strictness via sysfs
>   iommu: Merge strictness and domain type configs
>   iommu/dma: Factor out flush queue init
>   iommu: Allow enabling non-strict mode dynamically
>   iommu/arm-smmu: Allow non-strict in pgtable_quirks interface
>   iommu: Only log strictness for DMA domains
>
>  .../ABI/testing/sysfs-kernel-iommu_groups     |  2 +
>  drivers/iommu/Kconfig                         | 80 +++++++++----------
>  drivers/iommu/amd/iommu.c                     | 21 +----
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 25 ++++--
>  drivers/iommu/arm/arm-smmu/arm-smmu.c         | 29 ++++---
>  drivers/iommu/arm/arm-smmu/qcom_iommu.c       |  8 --
>  drivers/iommu/dma-iommu.c                     | 44 +++++-----
>  drivers/iommu/exynos-iommu.c                  | 18 +----
>  drivers/iommu/intel/iommu.c                   | 23 ++----
>  drivers/iommu/iommu.c                         | 53 +++++++-----
>  drivers/iommu/ipmmu-vmsa.c                    | 27 +------
>  drivers/iommu/mtk_iommu.c                     |  6 --
>  drivers/iommu/rockchip-iommu.c                | 11 +--
>  drivers/iommu/sprd-iommu.c                    |  6 --
>  drivers/iommu/sun50i-iommu.c                  | 12 +--
>  drivers/iommu/virtio-iommu.c                  |  8 --
>  include/linux/dma-iommu.h                     |  9 ++-
>  include/linux/iommu.h                         | 15 +++-
>  18 files changed, 171 insertions(+), 226 deletions(-)

I ran with:

a) mainline Linux (at commit 4010a528219e)
b) pulled iommu/next (at commit 9be9f5580ab6)
c) picked from patchwork your series

...and I ran on sc7180-trogdor-lazor.

Things worked OK and I could transition my eMMC to non-strict mode with:

echo DMA-FQ > /sys/devices/platform/soc at 0/7c4000.sdhci/iommu_group/type

I was definitely getting some inconsistencies in my tests where the
eMMC speeds were getting into a bad state, but I don't believe it's
related to your patch series. I could transition myself back to strict
DMA with this (only got one unrelated warn splat about
dev_pm_opp_put_clkname when unbinding) because I was booted up from
USB for testing:

cd /sys/bus/mmc/drivers/mmcblk
echo mmc1:0001 > unbind
cd /sys/bus/platform/drivers/sdhci_msm/
echo 7c4000.sdhci > unbind
echo DMA > /sys/devices/platform/soc at 0/7c4000.sdhci/iommu_group/type
echo 7c4000.sdhci > bind

...and it was consistently faster with non-strict than with strict so
whatever bad state I sometimes managed to get in it affected both
modes. ;-)

So I guess that's a long-winded way to say this:

Tested-by: Douglas Anderson <dianders at chromium.org>