iommu/iova: Make dma_32bit_pfn implicit
authorZhen Lei <thunder.leizhen@huawei.com>
Thu, 21 Sep 2017 15:52:45 +0000 (16:52 +0100)
committerJoerg Roedel <jroedel@suse.de>
Wed, 27 Sep 2017 15:09:57 +0000 (17:09 +0200)
commitaa3ac9469c1850ed00741955b975c3a19029763a
tree998e22c451f149ef7c2cd5284d1539cc9b33496f
parente60aa7b53845a261dd419652f12ab9f89e668843
iommu/iova: Make dma_32bit_pfn implicit

Now that the cached node optimisation can apply to all allocations, the
couple of users which were playing tricks with dma_32bit_pfn in order to
benefit from it can stop doing so. Conversely, there is also no need for
all the other users to explicitly calculate a 'real' 32-bit PFN, when
init_iova_domain() can happily do that itself from the page granularity.

CC: Thierry Reding <thierry.reding@gmail.com>
CC: Jonathan Hunter <jonathanh@nvidia.com>
CC: David Airlie <airlied@linux.ie>
CC: Sudeep Dutt <sudeep.dutt@intel.com>
CC: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Nate Watterson <nwatters@codeaurora.org>
[rm: use iova_shift(), rewrote commit message]
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
drivers/gpu/drm/tegra/drm.c
drivers/gpu/host1x/dev.c
drivers/iommu/amd_iommu.c
drivers/iommu/dma-iommu.c
drivers/iommu/intel-iommu.c
drivers/iommu/iova.c
drivers/misc/mic/scif/scif_rma.c
include/linux/iova.h