diff options
author | Joerg Roedel <joerg.roedel@amd.com> | 2011-12-01 15:49:45 +0100 |
---|---|---|
committer | Joerg Roedel <joerg.roedel@amd.com> | 2011-12-12 14:54:58 +0100 |
commit | 5abcdba4fa535c29f736455e37229ee97e0e7f5d (patch) | |
tree | 228892cf94773b3215fa588fe8e5fc617afa7591 /drivers/iommu/amd_iommu_types.h | |
parent | 400a28a05f2cc1a311acb4ff6ac64d8402d21678 (diff) | |
download | linux-5abcdba4fa535c29f736455e37229ee97e0e7f5d.tar.bz2 |
iommu/amd: Put IOMMUv2 capable devices in pt_domain
If the device starts to use IOMMUv2 features the dma handles
need to stay valid. The only sane way to do this is to use a
identity mapping for the device and not translate it by the
iommu. This is implemented with this patch. Since this lifts
the device-isolation there is also a new kernel parameter
which allows to disable that feature.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Diffstat (limited to 'drivers/iommu/amd_iommu_types.h')
-rw-r--r-- | drivers/iommu/amd_iommu_types.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 7e81094ab73b..96c652fae0e5 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -330,6 +330,8 @@ struct iommu_dev_data { struct protection_domain *domain; /* Domain the device is bound to */ atomic_t bind; /* Domain attach reverent count */ u16 devid; /* PCI Device ID */ + bool iommu_v2; /* Device can make use of IOMMUv2 */ + bool passthrough; /* Default for device is pt_domain */ struct { bool enabled; int qdep; @@ -575,6 +577,8 @@ extern u32 amd_iommu_max_pasids; extern bool amd_iommu_v2_present; +extern bool amd_iommu_force_isolation; + /* takes bus and device/function and returns the device id * FIXME: should that be in generic PCI code? */ static inline u16 calc_devid(u8 bus, u8 devfn) |