Add access-protected IOMMU mappings
cover Add access-protected IOMMU mappings
This series introduces a new mapping flag to indicate that the mapping should be created with access protection applied. Support for this new flag is then added to the ARM SMMU driver.
Mitchel Humpherys (2):
iommu: add IOMMU_PRIV flag for access-protected mappings iommu/arm-smmu: add support for access-protected mappings
drivers/iommu/arm-smmu.c | 5 +++-- include/linux/iommu.h | 1 + 2 files changed, 4 insertions(+), 2 deletions(-)
Signature · 2 lines
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation
PATCH 1/2 iommu: add IOMMU_PRIV flag for access-protected mappings
Some IOMMUs support access-protected mappings. Add a mapping flag to indicate that the mapping should be created with access protection configured.
--- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+)
include/linux/iommu.h +1 -0
@@ -28,6 +28,7 @@#define IOMMU_WRITE (1 << 1)#define IOMMU_CACHE (1 << 2)/* DMA cache coherency */ #define IOMMU_EXEC (1 << 3) +#define IOMMU_PRIV (1 << 4)struct iommu_ops ;struct iommu_group ;
Signature · 2 lines
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation
PATCH 2/2 iommu/arm-smmu: add support for access-protected mappings
In reply to Mitchel HumpherysARM SMMUs support memory access control via some bits in the translation table descriptor memory attributes. Currently we assume all translations are "unprivileged". Add support for privileged mappings, controlled by the IOMMU_PRIV prot flag.
Also sneak in a whitespace change for consistency with nearby code.
--- drivers/iommu/arm-smmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/iommu/arm-smmu.c +3 -2
@@ -1256,10 +1256,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, }if (stage ==1 ) { - pteval |=ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG; + pteval |= ARM_SMMU_PTE_nG; +if (!(prot &IOMMU_PRIV )) + pteval |=ARM_SMMU_PTE_AP_UNPRIV ;if (!(prot &IOMMU_WRITE ) && (prot &IOMMU_READ )) pteval |=ARM_SMMU_PTE_AP_RDONLY ; -if (prot &IOMMU_CACHE ) pteval |= (MAIR_ATTR_IDX_CACHE <<ARM_SMMU_PTE_ATTRINDX_SHIFT );
Signature · 2 lines
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation
PATCH 2/2 iommu/arm-smmu: add support for access-protected mappings
Quoted 17 lines · Mitchel Humpherys
ARM SMMUs support memory access control via some bits in the translation table descriptor memory attributes. Currently we assume all translations are "unprivileged". Add support for privileged mappings, controlled by the
IOMMU_PRIVprot flag.Also sneak in a whitespace change for consistency with nearby code.
Signed-off-by Mitchel Humpherys <[email protected]>--- drivers/iommu/arm-smmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)drivers/iommu/arm-smmu.c +0
-0
drivers/iommu/arm-smmu.c static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, · line 1261
Quoted 7 lines
drivers/iommu/arm-smmu.c +3
-1@@ -1256,10 +1256,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, }if (stage ==1 ) { - pteval |=ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG; + pteval |= ARM_SMMU_PTE_nG; +if (!(prot &IOMMU_PRIV )) + pteval |=ARM_SMMU_PTE_AP_UNPRIV ;
I think this actually makes more sense if we invert the logic, i.e. have IOMMU_USER as a flag which sets the UNPRIV bit in the pte.
I don't have the spec to hand, but I guess you can't enforce this at stage-2? If so, do we also need a new IOMMU capability so people don't try to use this for stage-2 only SMMUs?
Will
PATCH 2/2 iommu/arm-smmu: add support for access-protected mappings
Quoted 20 lines · Will Deacon
Quoted 19 lines · Mitchel Humpherys
ARM SMMUs support memory access control via some bits in the translation table descriptor memory attributes. Currently we assume all translations are "unprivileged". Add support for privileged mappings, controlled by the
IOMMU_PRIVprot flag.Also sneak in a whitespace change for consistency with nearby code.
Signed-off-by Mitchel Humpherys <[email protected]>--- drivers/iommu/arm-smmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)drivers/iommu/arm-smmu.c +0
-0@@ -1256,10 +1256,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, }
Quoted 8 lines
drivers/iommu/arm-smmu.c static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, · line 1261
Quoted 5 lines
drivers/iommu/arm-smmu.c +3
-1if (stage ==1 ) { - pteval |=ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG; + pteval |= ARM_SMMU_PTE_nG; +if (!(prot &IOMMU_PRIV )) + pteval |=ARM_SMMU_PTE_AP_UNPRIV ;I think this actually makes more sense if we invert the logic, i.e. have
IOMMU_USERas a flag which sets the UNPRIV bit in the pte.
I'm fine either way but the common case seems to be unprivileged mappings (at least in our system). We have one user of this flag out of a dozen or so users.
Quoted 4 lines
I don't have the spec to hand, but I guess you can't enforce this at stage-2? If so, do we also need a new IOMMU capability so people don't try to use this for stage-2 only SMMUs?
Hmm, actually we do have S2AP although it doesn't make a distinction between accesses from EL0 and EL1. But maybe it would make sense to make the IOMMU_PRIV' mean no access from EL0 or EL1' for stage 2 mappings? Something like:
-- >8 --
Subject: iommu/arm-smmu: add support for access-protected mappings
ARM SMMUs support memory access control via some bits in the translation table descriptor memory attributes. Currently we assume all translations are "unprivileged". Add support for privileged mappings, controlled by the IOMMU_PRIV prot flag.
Also sneak in a whitespace change for consistency with nearby code.
--- drivers/iommu/arm-smmu.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/iommu/arm-smmu.c +5 -4
@@ -1256,18 +1256,19 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, }if (stage ==1 ) { - pteval |=ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG; + pteval |= ARM_SMMU_PTE_nG; +if (!(prot &IOMMU_PRIV )) + pteval |=ARM_SMMU_PTE_AP_UNPRIV ;if (!(prot &IOMMU_WRITE ) && (prot &IOMMU_READ )) pteval |=ARM_SMMU_PTE_AP_RDONLY ; -if (prot &IOMMU_CACHE ) pteval |= (MAIR_ATTR_IDX_CACHE <<ARM_SMMU_PTE_ATTRINDX_SHIFT ); }else { pteval |=ARM_SMMU_PTE_HAP_FAULT ; -if (prot &IOMMU_READ ) +if (prot &IOMMU_READ && !(prot &IOMMU_PRIV )) pteval |=ARM_SMMU_PTE_HAP_READ ; -if (prot &IOMMU_WRITE ) +if (prot &IOMMU_WRITE && !(prot &IOMMU_PRIV )) pteval |=ARM_SMMU_PTE_HAP_WRITE ;if (prot &IOMMU_CACHE ) pteval |=ARM_SMMU_PTE_MEMATTR_OIWB ;
Signature · 2 lines
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation
PATCH 2/2 iommu/arm-smmu: add support for access-protected mappings
Quoted 30 lines · Mitchel Humpherys
Quoted 20 lines · Will Deacon
Quoted 19 lines · Mitchel Humpherys
ARM SMMUs support memory access control via some bits in the translation table descriptor memory attributes. Currently we assume all translations are "unprivileged". Add support for privileged mappings, controlled by the
IOMMU_PRIVprot flag.Also sneak in a whitespace change for consistency with nearby code.
Signed-off-by Mitchel Humpherys <[email protected]>--- drivers/iommu/arm-smmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)drivers/iommu/arm-smmu.c +0
-0@@ -1256,10 +1256,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, }Quoted 8 lines
drivers/iommu/arm-smmu.c static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, · line 1261
Quoted 5 lines
drivers/iommu/arm-smmu.c +3
-1if (stage ==1 ) { - pteval |=ARM_SMMU_PTE_AP_UNPRIV | ARM_SMMU_PTE_nG; + pteval |= ARM_SMMU_PTE_nG; +if (!(prot &IOMMU_PRIV )) + pteval |=ARM_SMMU_PTE_AP_UNPRIV ;I think this actually makes more sense if we invert the logic, i.e. have
IOMMU_USERas a flag which sets the UNPRIV bit in the pte.
Quoted 3 lines
I'm fine either way but the common case seems to be unprivileged mappings (at least in our system). We have one user of this flag out of a dozen or so users.
Well, I think the common case in reality (ie. in upstream) is that we don't care, since there's no page table sharing with the CPU. Given that our DMA buffers are privilege on the kernel side, it's consistent to copy that as the default.
Quoted 9 lines
Quoted 4 lines
I don't have the spec to hand, but I guess you can't enforce this at stage-2? If so, do we also need a new IOMMU capability so people don't try to use this for stage-2 only SMMUs?
Hmm, actually we do have S2AP although it doesn't make a distinction between accesses from EL0 and EL1. But maybe it would make sense to make the
IOMMU_PRIV' meanno access from EL0 or EL1' for stage 2 mappings? Something like:
Hmm, that really doesn't match up with what KVM is doing on the CPU side and would probably break DMA on stage-2 only SMMUs.
A better bet is to add a capability bit to the SMMU, which only advertises support for IOMMU_USER mappings if stage-1 is supported.
Will