Re: [PATCH v5 1/5] docs: IOMMU user API
On Fri, 17 Jul 2020 13:37:25 -0600 Alex Williamson wrote: > On Thu, 16 Jul 2020 11:45:13 -0700 > Jacob Pan wrote: > > > IOMMU UAPI is newly introduced to support communications between > > guest virtual IOMMU and host IOMMU. There has been lots of > > discussions on how it should work with VFIO UAPI and userspace in > > general. > > > > This document is indended to clarify the UAPI design and usage. The > > mechanics of how future extensions should be achieved are also > > covered in this documentation. > > > > Signed-off-by: Liu Yi L > > Signed-off-by: Jacob Pan > > --- > > Documentation/userspace-api/iommu.rst | 339 > > ++ 1 file changed, 339 insertions(+) > > create mode 100644 Documentation/userspace-api/iommu.rst > > > > diff --git a/Documentation/userspace-api/iommu.rst > > b/Documentation/userspace-api/iommu.rst new file mode 100644 > > index ..efc3e1838235 > > --- /dev/null > > +++ b/Documentation/userspace-api/iommu.rst > > @@ -0,0 +1,339 @@ > > +.. SPDX-License-Identifier: GPL-2.0 > > +.. iommu: > > + > > += > > +IOMMU Userspace API > > += > > + > > +IOMMU UAPI is used for virtualization cases where communications > > are +needed between physical and virtual IOMMU drivers. For native > > +usage, IOMMU is a system device which does not need to communicate > > +with user space directly. > > + > > +The primary use cases are guest Shared Virtual Address (SVA) and > > +guest IO virtual address (IOVA), wherein a virtual IOMMU (vIOMMU) > > is +required to communicate with the physical IOMMU in the host. > > + > > +.. contents:: :local: > > + > > +Functionalities > > +=== > > +Communications of user and kernel involve both directions. The > > +supported user-kernel APIs are as follows: > > + > > +1. Alloc/Free PASID > > +2. Bind/unbind guest PASID (e.g. Intel VT-d) > > +3. Bind/unbind guest PASID table (e.g. ARM sMMU) > > +4. Invalidate IOMMU caches > > +5. Service IO page faults (page request and response) > > + > > +Requirements > > + > > +The IOMMU UAPIs are generic and extensible to meet the following > > +requirements: > > + > > +1. Emulated and para-virtualised vIOMMUs > > +2. Multiple vendors (Intel VT-d, ARM sMMU, etc.) > > +3. Extensions to the UAPI shall not break existing user space > > + > > +Interfaces > > +== > > +Although the data structures defined in IOMMU UAPI are > > self-contained, +there is no user API functions introduced. > > Instead, IOMMU UAPI is +designed to work with existing user driver > > frameworks such as VFIO. + > > +Extension Rules & Precautions > > +- > > +When IOMMU UAPI gets extended, the data structures can *only* be > > +modified in two ways: > > + > > +1. Adding new fields by re-purposing the padding[] field. No size > > change. +2. Adding new union members at the end. May increase in > > size. + > > +No new fields can be added *after* the variable sized union in > > that it +will break backward compatibility when offset moves. In > > both cases, a +new flag must be accompanied with a new field such > > that the IOMMU +driver can process the data based on the new flag. > > Version field is +only reserved for the unlikely event of UAPI > > upgrade at its entirety. + > > +It's *always* the caller's responsibility to indicate the size of > > the +structure passed by setting argsz appropriately. > > +Though at the same time, argsz is user provided data which is not > > +trusted. The argsz field allows the user to indicate how much data > > +they're providing, it's still the kernel's responsibility to > > validate +whether it's correct and sufficient for the requested > > operation. + > > +Compatibility Checking > > +-- > > +When IOMMU UAPI extension results in size increase, IOMMU UAPI core > > +and vendor driver shall handle the following cases: > > + > > +1. User and kernel has exact size match > > +2. An older user with older kernel header (smaller UAPI size) > > running on a > > + newer kernel (larger UAPI size) > > +3. A newer user with newer kernel header (larger UAPI size) running > > + on an older kernel. > > +4. A malicious/misbehaving user pass illegal/invalid size but > > within > > + range. The data may contain garbage. > > + > > +Feature Checking > > + > > +While launching a guest with vIOMMU, it is important to ensure > > that host +can support the UAPI data structures to be used for > > vIOMMU-pIOMMU +communications. Without upfront compatibility > > checking, future faults +are difficult to report even in normal > > conditions. For example, TLB +invalidations should always succeed. > > There is no architectural way to +report back to the vIOMMU if the > > UAPI data is incompatible. If that +happens, in order to protect > > IOMMU iosolation guarantee, we have to +resort to not giving > > completion status in vIOMMU. This may
Re: [PATCH v5 1/5] docs: IOMMU user API
Hi Eric, On Fri, 17 Jul 2020 15:32:58 +0200 Auger Eric wrote: > Hi Jacob, > > On 7/16/20 8:45 PM, Jacob Pan wrote: > > IOMMU UAPI is newly introduced to support communications between > > guest virtual IOMMU and host IOMMU. There has been lots of > > discussions on how it should work with VFIO UAPI and userspace in > > general. > > > > This document is indended to clarify the UAPI design and usage. > > The > intended will fix. > > mechanics of how future extensions should be achieved are also > > covered in this documentation. > > > > Signed-off-by: Liu Yi L > > Signed-off-by: Jacob Pan > > --- > > Documentation/userspace-api/iommu.rst | 339 > > ++ 1 file changed, 339 insertions(+) > > create mode 100644 Documentation/userspace-api/iommu.rst > > > > diff --git a/Documentation/userspace-api/iommu.rst > > b/Documentation/userspace-api/iommu.rst new file mode 100644 > > index ..efc3e1838235 > > --- /dev/null > > +++ b/Documentation/userspace-api/iommu.rst > > @@ -0,0 +1,339 @@ > > +.. SPDX-License-Identifier: GPL-2.0 > > +.. iommu: > > + > > += > > +IOMMU Userspace API > > += > > + > > +IOMMU UAPI is used for virtualization cases where communications > > are +needed between physical and virtual IOMMU drivers. For native > s/native/baremetal? Sounds good. > > +usage, IOMMU is a system device which does not need to > > communicate > the IOMMU? Sounds good. > > +with user space directly. > > + > > +The primary use cases are guest Shared Virtual Address (SVA) and > > +guest IO virtual address (IOVA), wherein a virtual IOMMU (vIOMMU) > > is +required to communicate with the physical IOMMU in the host. > wherin the vIOMMU implementation relies on the physical IOMMU and for > this reason requires interactions with the host driver. > Will do, it is more complete. > > + > > +.. contents:: :local: > > + > > +Functionalities > > +=== > > +Communications of user and kernel involve both directions. The > > +supported user-kernel APIs are as follows: > > + > > +1. Alloc/Free PASID > > +2. Bind/unbind guest PASID (e.g. Intel VT-d) > > +3. Bind/unbind guest PASID table (e.g. ARM sMMU) > s/sMMU/SMMU Sounds good and all below. > > +4. Invalidate IOMMU caches > > +5. Service IO page faults (page request and response) > Report errors to the guest and serve page requests? Yes, the UAPI does cover faults beyond PRS. > > + > > +Requirements > > + > > +The IOMMU UAPIs are generic and extensible to meet the following > > +requirements: > > + > > +1. Emulated and para-virtualised vIOMMUs > > +2. Multiple vendors (Intel VT-d, ARM sMMU, etc.) > SMMU Ditto. > > +3. Extensions to the UAPI shall not break existing user space > > + > > +Interfaces > > +== > > +Although the data structures defined in IOMMU UAPI are > > self-contained, +there is no user API functions introduced. > > Instead, IOMMU UAPI is +designed to work with existing user driver > > frameworks such as VFIO. + > > +Extension Rules & Precautions > > +- > > +When IOMMU UAPI gets extended, the data structures can *only* be > > +modified in two ways: > > + > > +1. Adding new fields by re-purposing the padding[] field. No size > > change. +2. Adding new union members at the end. May increase in > > size. > May increase the structure sizes Sounds good. > > + > > +No new fields can be added *after* the variable sized union in > > that it +will break backward compatibility when offset moves. In > > both cases, a +new flag must be accompanied with a new field such > > that the IOMMU > a new flag must be introduced whenever a change affects the structure > using either method? Yours is more clear, will change to: A new flag must be introduced whenever a change affects the structure using either method. The IOMMU driver processes the data based on flags which ensures backward compatibility. > > +driver can process the data based on the new flag. Version field is > > +only reserved for the unlikely event of UAPI upgrade at its > > entirety. + > > +It's *always* the caller's responsibility to indicate the size of > > the +structure passed by setting argsz appropriately. > > +Though at the same time, argsz is user provided data which is not > > +trusted. The argsz field allows the user to indicate how much data > > +they're providing, it's still the kernel's responsibility to > > validate > he is providing Sounds good. > > +whether it's correct and sufficient for the requested operation. > > + > > +Compatibility Checking > > +-- > > +When IOMMU UAPI extension results in size increase, IOMMU UAPI > > core > in some structure size increase, the IOMMU UAPI code Better > > +and vendor driver shall handle the following cases: > > + > > +1. User and kernel has exact size match > > +2. An older user with older kernel header (smaller UAPI size) > > running
Re: [PATCH v5 1/5] docs: IOMMU user API
On Thu, 16 Jul 2020 11:45:13 -0700 Jacob Pan wrote: > IOMMU UAPI is newly introduced to support communications between guest > virtual IOMMU and host IOMMU. There has been lots of discussions on how > it should work with VFIO UAPI and userspace in general. > > This document is indended to clarify the UAPI design and usage. The > mechanics of how future extensions should be achieved are also covered > in this documentation. > > Signed-off-by: Liu Yi L > Signed-off-by: Jacob Pan > --- > Documentation/userspace-api/iommu.rst | 339 > ++ > 1 file changed, 339 insertions(+) > create mode 100644 Documentation/userspace-api/iommu.rst > > diff --git a/Documentation/userspace-api/iommu.rst > b/Documentation/userspace-api/iommu.rst > new file mode 100644 > index ..efc3e1838235 > --- /dev/null > +++ b/Documentation/userspace-api/iommu.rst > @@ -0,0 +1,339 @@ > +.. SPDX-License-Identifier: GPL-2.0 > +.. iommu: > + > += > +IOMMU Userspace API > += > + > +IOMMU UAPI is used for virtualization cases where communications are > +needed between physical and virtual IOMMU drivers. For native > +usage, IOMMU is a system device which does not need to communicate > +with user space directly. > + > +The primary use cases are guest Shared Virtual Address (SVA) and > +guest IO virtual address (IOVA), wherein a virtual IOMMU (vIOMMU) is > +required to communicate with the physical IOMMU in the host. > + > +.. contents:: :local: > + > +Functionalities > +=== > +Communications of user and kernel involve both directions. The > +supported user-kernel APIs are as follows: > + > +1. Alloc/Free PASID > +2. Bind/unbind guest PASID (e.g. Intel VT-d) > +3. Bind/unbind guest PASID table (e.g. ARM sMMU) > +4. Invalidate IOMMU caches > +5. Service IO page faults (page request and response) > + > +Requirements > + > +The IOMMU UAPIs are generic and extensible to meet the following > +requirements: > + > +1. Emulated and para-virtualised vIOMMUs > +2. Multiple vendors (Intel VT-d, ARM sMMU, etc.) > +3. Extensions to the UAPI shall not break existing user space > + > +Interfaces > +== > +Although the data structures defined in IOMMU UAPI are self-contained, > +there is no user API functions introduced. Instead, IOMMU UAPI is > +designed to work with existing user driver frameworks such as VFIO. > + > +Extension Rules & Precautions > +- > +When IOMMU UAPI gets extended, the data structures can *only* be > +modified in two ways: > + > +1. Adding new fields by re-purposing the padding[] field. No size change. > +2. Adding new union members at the end. May increase in size. > + > +No new fields can be added *after* the variable sized union in that it > +will break backward compatibility when offset moves. In both cases, a > +new flag must be accompanied with a new field such that the IOMMU > +driver can process the data based on the new flag. Version field is > +only reserved for the unlikely event of UAPI upgrade at its entirety. > + > +It's *always* the caller's responsibility to indicate the size of the > +structure passed by setting argsz appropriately. > +Though at the same time, argsz is user provided data which is not > +trusted. The argsz field allows the user to indicate how much data > +they're providing, it's still the kernel's responsibility to validate > +whether it's correct and sufficient for the requested operation. > + > +Compatibility Checking > +-- > +When IOMMU UAPI extension results in size increase, IOMMU UAPI core > +and vendor driver shall handle the following cases: > + > +1. User and kernel has exact size match > +2. An older user with older kernel header (smaller UAPI size) running on a > + newer kernel (larger UAPI size) > +3. A newer user with newer kernel header (larger UAPI size) running > + on an older kernel. > +4. A malicious/misbehaving user pass illegal/invalid size but within > + range. The data may contain garbage. > + > +Feature Checking > + > +While launching a guest with vIOMMU, it is important to ensure that host > +can support the UAPI data structures to be used for vIOMMU-pIOMMU > +communications. Without upfront compatibility checking, future faults > +are difficult to report even in normal conditions. For example, TLB > +invalidations should always succeed. There is no architectural way to > +report back to the vIOMMU if the UAPI data is incompatible. If that > +happens, in order to protect IOMMU iosolation guarantee, we have to > +resort to not giving completion status in vIOMMU. This may result in > +VM hang. > + > +For this reason the following IOMMU UAPIs cannot fail: > + > +1. Free PASID > +2. Unbind guest PASID > +3. Unbind guest PASID table (SMMU) > +4. Cache invalidate > + > +User applications such as QEMU are expected to import kernel UAPI > +headers. Backward
Re: [PATCH v5 1/5] docs: IOMMU user API
Hi Jacob, On 7/16/20 8:45 PM, Jacob Pan wrote: > IOMMU UAPI is newly introduced to support communications between guest > virtual IOMMU and host IOMMU. There has been lots of discussions on how > it should work with VFIO UAPI and userspace in general. > > This document is indended to clarify the UAPI design and usage. The intended > mechanics of how future extensions should be achieved are also covered > in this documentation. > > Signed-off-by: Liu Yi L > Signed-off-by: Jacob Pan > --- > Documentation/userspace-api/iommu.rst | 339 > ++ > 1 file changed, 339 insertions(+) > create mode 100644 Documentation/userspace-api/iommu.rst > > diff --git a/Documentation/userspace-api/iommu.rst > b/Documentation/userspace-api/iommu.rst > new file mode 100644 > index ..efc3e1838235 > --- /dev/null > +++ b/Documentation/userspace-api/iommu.rst > @@ -0,0 +1,339 @@ > +.. SPDX-License-Identifier: GPL-2.0 > +.. iommu: > + > += > +IOMMU Userspace API > += > + > +IOMMU UAPI is used for virtualization cases where communications are > +needed between physical and virtual IOMMU drivers. For native s/native/baremetal? > +usage, IOMMU is a system device which does not need to communicate the IOMMU? > +with user space directly. > + > +The primary use cases are guest Shared Virtual Address (SVA) and > +guest IO virtual address (IOVA), wherein a virtual IOMMU (vIOMMU) is > +required to communicate with the physical IOMMU in the host. wherin the vIOMMU implementation relies on the physical IOMMU and for this reason requires interactions with the host driver. > + > +.. contents:: :local: > + > +Functionalities > +=== > +Communications of user and kernel involve both directions. The > +supported user-kernel APIs are as follows: > + > +1. Alloc/Free PASID > +2. Bind/unbind guest PASID (e.g. Intel VT-d) > +3. Bind/unbind guest PASID table (e.g. ARM sMMU) s/sMMU/SMMU > +4. Invalidate IOMMU caches > +5. Service IO page faults (page request and response) Report errors to the guest and serve page requests? > + > +Requirements > + > +The IOMMU UAPIs are generic and extensible to meet the following > +requirements: > + > +1. Emulated and para-virtualised vIOMMUs > +2. Multiple vendors (Intel VT-d, ARM sMMU, etc.) SMMU > +3. Extensions to the UAPI shall not break existing user space > + > +Interfaces > +== > +Although the data structures defined in IOMMU UAPI are self-contained, > +there is no user API functions introduced. Instead, IOMMU UAPI is > +designed to work with existing user driver frameworks such as VFIO. > + > +Extension Rules & Precautions > +- > +When IOMMU UAPI gets extended, the data structures can *only* be > +modified in two ways: > + > +1. Adding new fields by re-purposing the padding[] field. No size change. > +2. Adding new union members at the end. May increase in size. May increase the structure sizes > + > +No new fields can be added *after* the variable sized union in that it > +will break backward compatibility when offset moves. In both cases, a > +new flag must be accompanied with a new field such that the IOMMU a new flag must be introduced whenever a change affects the structure using either method? > +driver can process the data based on the new flag. Version field is > +only reserved for the unlikely event of UAPI upgrade at its entirety. > + > +It's *always* the caller's responsibility to indicate the size of the > +structure passed by setting argsz appropriately. > +Though at the same time, argsz is user provided data which is not > +trusted. The argsz field allows the user to indicate how much data > +they're providing, it's still the kernel's responsibility to validate he is providing > +whether it's correct and sufficient for the requested operation. > + > +Compatibility Checking > +-- > +When IOMMU UAPI extension results in size increase, IOMMU UAPI core in some structure size increase, the IOMMU UAPI code > +and vendor driver shall handle the following cases: > + > +1. User and kernel has exact size match > +2. An older user with older kernel header (smaller UAPI size) running on a > + newer kernel (larger UAPI size) > +3. A newer user with newer kernel header (larger UAPI size) running > + on an older kernel. > +4. A malicious/misbehaving user pass illegal/invalid size but within > + range. The data may contain garbage.> + > +Feature Checking > + > +While launching a guest with vIOMMU, it is important to ensure that host > +can support the UAPI data structures to be used for vIOMMU-pIOMMU > +communications. Without upfront compatibility checking, future faults s/faults/failures? > +are difficult to report even in normal conditions. For example, TLB > +invalidations should always succeed. There is no architectural way to > +report back to the vIOMMU if the UAPI data is
[PATCH v5 1/5] docs: IOMMU user API
IOMMU UAPI is newly introduced to support communications between guest virtual IOMMU and host IOMMU. There has been lots of discussions on how it should work with VFIO UAPI and userspace in general. This document is indended to clarify the UAPI design and usage. The mechanics of how future extensions should be achieved are also covered in this documentation. Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan --- Documentation/userspace-api/iommu.rst | 339 ++ 1 file changed, 339 insertions(+) create mode 100644 Documentation/userspace-api/iommu.rst diff --git a/Documentation/userspace-api/iommu.rst b/Documentation/userspace-api/iommu.rst new file mode 100644 index ..efc3e1838235 --- /dev/null +++ b/Documentation/userspace-api/iommu.rst @@ -0,0 +1,339 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. iommu: + += +IOMMU Userspace API += + +IOMMU UAPI is used for virtualization cases where communications are +needed between physical and virtual IOMMU drivers. For native +usage, IOMMU is a system device which does not need to communicate +with user space directly. + +The primary use cases are guest Shared Virtual Address (SVA) and +guest IO virtual address (IOVA), wherein a virtual IOMMU (vIOMMU) is +required to communicate with the physical IOMMU in the host. + +.. contents:: :local: + +Functionalities +=== +Communications of user and kernel involve both directions. The +supported user-kernel APIs are as follows: + +1. Alloc/Free PASID +2. Bind/unbind guest PASID (e.g. Intel VT-d) +3. Bind/unbind guest PASID table (e.g. ARM sMMU) +4. Invalidate IOMMU caches +5. Service IO page faults (page request and response) + +Requirements + +The IOMMU UAPIs are generic and extensible to meet the following +requirements: + +1. Emulated and para-virtualised vIOMMUs +2. Multiple vendors (Intel VT-d, ARM sMMU, etc.) +3. Extensions to the UAPI shall not break existing user space + +Interfaces +== +Although the data structures defined in IOMMU UAPI are self-contained, +there is no user API functions introduced. Instead, IOMMU UAPI is +designed to work with existing user driver frameworks such as VFIO. + +Extension Rules & Precautions +- +When IOMMU UAPI gets extended, the data structures can *only* be +modified in two ways: + +1. Adding new fields by re-purposing the padding[] field. No size change. +2. Adding new union members at the end. May increase in size. + +No new fields can be added *after* the variable sized union in that it +will break backward compatibility when offset moves. In both cases, a +new flag must be accompanied with a new field such that the IOMMU +driver can process the data based on the new flag. Version field is +only reserved for the unlikely event of UAPI upgrade at its entirety. + +It's *always* the caller's responsibility to indicate the size of the +structure passed by setting argsz appropriately. +Though at the same time, argsz is user provided data which is not +trusted. The argsz field allows the user to indicate how much data +they're providing, it's still the kernel's responsibility to validate +whether it's correct and sufficient for the requested operation. + +Compatibility Checking +-- +When IOMMU UAPI extension results in size increase, IOMMU UAPI core +and vendor driver shall handle the following cases: + +1. User and kernel has exact size match +2. An older user with older kernel header (smaller UAPI size) running on a + newer kernel (larger UAPI size) +3. A newer user with newer kernel header (larger UAPI size) running + on an older kernel. +4. A malicious/misbehaving user pass illegal/invalid size but within + range. The data may contain garbage. + +Feature Checking + +While launching a guest with vIOMMU, it is important to ensure that host +can support the UAPI data structures to be used for vIOMMU-pIOMMU +communications. Without upfront compatibility checking, future faults +are difficult to report even in normal conditions. For example, TLB +invalidations should always succeed. There is no architectural way to +report back to the vIOMMU if the UAPI data is incompatible. If that +happens, in order to protect IOMMU iosolation guarantee, we have to +resort to not giving completion status in vIOMMU. This may result in +VM hang. + +For this reason the following IOMMU UAPIs cannot fail: + +1. Free PASID +2. Unbind guest PASID +3. Unbind guest PASID table (SMMU) +4. Cache invalidate + +User applications such as QEMU are expected to import kernel UAPI +headers. Backward compatibility is supported per feature flags. +For example, an older QEMU (with older kernel header) can run on newer +kernel. Newer QEMU (with new kernel header) may refuse to initialize +on an older kernel if new feature flags are not supported by older +kernel. Simply recompiling existing code with newer
