Skip to contentSkip to conversation

IOMMU user API enhancement

PATCH In review Jacob Pan 3 participants 22 messages Jul 30, 2020 – Aug 31, 2020

Subsystems (3)
lore
Share & tools
lore
author
#7 lore raw

PATCH v7 3/7 iommu/uapi: Introduce enum type for PASID data format

In reply to Jacob Pan

There can be multiple vendor-specific PASID data formats used in UAPI structures. This patch adds enum type with a last entry which makes range checking much easier.

---
 include/uapi/linux/iommu.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
include/uapi/linux/iommu.h +6 -2
index d5e9014f690e..abf4455a3495 100644
@@ -294,11 +294,16 @@ struct iommu_gpasid_bind_data_vtd {
 					 IOMMU_SVA_VTD_GPASID_PCD |  \
 					 IOMMU_SVA_VTD_GPASID_PWT)
 
+enum iommu_pasid_data_format {
+	IOMMU_PASID_FORMAT_INTEL_VTD = 1,
+	IOMMU_PASID_FORMAT_LAST,
+};
+
 /**
  * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
  * @argsz:	User filled size of this data
  * @version:	Version of this data structure
- * @format:	PASID table entry format
+ * @format:	PASID table entry format of enum iommu_pasid_data_format type
  * @flags:	Additional information on guest bind request
  * @gpgd:	Guest page directory base of the guest mm to bind
  * @hpasid:	Process address space ID used for the guest mm in host IOMMU
@@ -317,7 +322,6 @@ struct iommu_gpasid_bind_data {
 	__u32 argsz;
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
-#define IOMMU_PASID_FORMAT_INTEL_VTD	1
 	__u32 format;
 	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
Signature · 1 line
2.7.4

Jacob Pan

author
#0 lore raw

v7 cover IOMMU user API enhancement

IOMMU user API header was introduced to support nested DMA translation and related fault handling. The current UAPI data structures consist of three areas that cover the interactions between host kernel and guest:
- fault handling
- cache invalidation
- bind guest page tables, i.e. guest PASID

Future extensions are likely to support more architectures and vIOMMU features.

In the previous discussion, using user-filled data size and feature flags is made a preferred approach over a unified version number.
https://lkml.org/lkml/2020/1/29/45

In addition to introduce argsz field to data structures, this patchset is also trying to document the UAPI design, usage, and extension rules. VT-d driver changes to utilize the new argsz field is included, VFIO usage is to follow.

This set is available at:
https://github.com/jacobpan/linux.git vsva_v5.8_uapi_v7

Thanks,

Jacob

Changeog:
v7
- Added PASID data format enum for range checking
- Tidy up based on reviews from Alex W.
- Removed doc section for vIOMMU fault handling
v6
- Renamed all UAPI functions with iommu_uapi_ prefix
- Replaced argsz maxsz checking with flag specific size checks
- Documentation improvements based on suggestions by Eric Auger Replaced example code with a pointer to the actual code
- Added more checks for illegal flags combinations
- Added doc file to MAINTAINERS
v5
- Addjusted paddings in UAPI data to be 8 byte aligned
- Do not clobber argsz in IOMMU core before passing on to vendor driver
- Removed pr_warn_ for invalid UAPI data check, just return -EINVAL
- Clarified VFIO responsibility in UAPI data handling
- Use iommu_uapi prefix to differentiate APIs has in-kernel caller
- Added comment for unchecked flags of invalidation granularity
- Added example in doc to show vendor data checking

v4
- Added checks of UAPI data for reserved fields, version, and flags.
- Removed version check from vendor driver (vt-d)
- Relaxed argsz check to match the UAPI struct size instead of variable union size
- Updated documentation

v3:
- Rewrote backward compatibility rule to support existing code re-compiled with newer kernel UAPI header that runs on older kernel. Based on review comment from Alex W.
https://lore.kernel.org/linux-iommu/[email protected]/
- Take user pointer directly in UAPI functions. Perform argsz check and copy_from_user() in IOMMU driver. Eliminate the need for VFIO or other upper layer to parse IOMMU data.
- Create wrapper function for in-kernel users of UAPI functions
v2:
- Removed unified API version and helper
- Introduced argsz for each UAPI data
- Introduced UAPI doc

Jacob Pan (7):
docs: IOMMU user API
iommu/uapi: Add argsz for user filled data iommu/uapi: Introduce enum type for PASID data format iommu/uapi: Use named union for user data iommu/uapi: Rename uapi functions iommu/uapi: Handle data and argsz filled by users iommu/vt-d: Check UAPI data processed by IOMMU core

 Documentation/userspace-api/iommu.rst | 212 ++++++++++++++++++++++++++++++++++
 MAINTAINERS                           |   1 +
 drivers/iommu/intel/iommu.c           |  25 ++--
 drivers/iommu/intel/svm.c             |   9 +-
 drivers/iommu/iommu.c                 | 205 ++++++++++++++++++++++++++++++--
 include/linux/iommu.h                 |  35 ++++--
 include/uapi/linux/iommu.h            |  24 ++--
 7 files changed, 466 insertions(+), 45 deletions(-)
 create mode 100644 Documentation/userspace-api/iommu.rst
Signature · 6 lines
2.7.4

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
author
#19 lore raw

PATCH v7 7/7 iommu/vt-d: Check UAPI data processed by IOMMU core

IOMMU generic layer already does sanity checks UAPI data for version match and argsz range under generic information.
Remove the redundant version check from VT-d driver and check for vendor specific data size.

---
 drivers/iommu/intel/iommu.c | 3 +--
 drivers/iommu/intel/svm.c   | 7 +++++--
 2 files changed, 6 insertions(+), 4 deletions(-)
drivers/iommu/intel/iommu.c +1 -2
index 021f62078f52..7e03cca31a0e 100644
@@ -5391,8 +5391,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 	int ret = 0;
 	u64 size = 0;
 
-	if (!inv_info || !dmar_domain ||
-	    inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+	if (!inv_info || !dmar_domain)
 		return -EINVAL;
 
 	if (!dev || !dev_is_pci(dev))
drivers/iommu/intel/svm.c +5 -2
index 713b3a218483..55ea11e9c0f5 100644
@@ -240,8 +240,11 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	if (WARN_ON(!iommu) || !data)
 		return -EINVAL;
 
-	if (data->version != IOMMU_GPASID_BIND_VERSION_1 ||
-	    data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+	if (data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+		return -EINVAL;
+
+	/* IOMMU core ensures argsz is more than the start of the union */
+	if (data->argsz < offsetofend(struct iommu_gpasid_bind_data, vendor.vtd))
 		return -EINVAL;
 
 	if (!dev_is_pci(dev))
Signature · 6 lines
2.7.4

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
author
#10 lore raw

PATCH v7 5/7 iommu/uapi: Rename uapi functions

In reply to Jacob Pan

User APIs such as iommu_sva_unbind_gpasid() may also be used by the kernel. Since we introduced user pointer to the UAPI functions, in-kernel callers cannot share the same APIs. In-kernel callers are also trusted, there is no need to validate the data.

This patch renames all UAPI functions with iommu_uapi_ prefix such that is clear to the intended callers.

---
 drivers/iommu/iommu.c | 18 +++++++++---------
 include/linux/iommu.h | 31 ++++++++++++++++---------------
 2 files changed, 25 insertions(+), 24 deletions(-)
drivers/iommu/iommu.c +9 -9
index b6858adc4f17..3a913ce94a3d 100644
@@ -1950,35 +1950,35 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
-int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-			   struct iommu_cache_invalidate_info *inv_info)
+int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+				struct iommu_cache_invalidate_info *inv_info)
 {
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
 	return domain->ops->cache_invalidate(domain, dev, inv_info);
 }
-EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-			   struct device *dev, struct iommu_gpasid_bind_data *data)
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+			       struct device *dev, struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_bind_gpasid(domain, dev, data);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-			     ioasid_t pasid)
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 ioasid_t pasid)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_unbind_gpasid(dev, pasid);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
include/linux/iommu.h +16 -15
index 5f0b7859d2eb..2dcc1a33f6dc 100644
@@ -430,13 +430,13 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_cache_invalidate(struct iommu_domain *domain,
-				  struct device *dev,
-				  struct iommu_cache_invalidate_info *inv_info);
-extern int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-		struct device *dev, struct iommu_gpasid_bind_data *data);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-				struct device *dev, ioasid_t pasid);
+extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+				       struct device *dev,
+				       struct iommu_cache_invalidate_info *inv_info);
+extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+				      struct device *dev, struct iommu_gpasid_bind_data *data);
+extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1054,21 +1054,22 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int
-iommu_cache_invalidate(struct iommu_domain *domain,
-		       struct device *dev,
-		       struct iommu_cache_invalidate_info *inv_info)
+static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+					      struct device *dev,
+					      struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
-static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-				struct device *dev, struct iommu_gpasid_bind_data *data)
+
+static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+					     struct device *dev,
+					     struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }
 
-static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-					   struct device *dev, int pasid)
+static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					       struct device *dev, int pasid)
 {
 	return -ENODEV;
 }
Signature · 1 line
2.7.4
author
#1 lore raw

PATCH v7 1/7 docs: IOMMU user API

In reply to Jacob Pan

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 intended to clarify the UAPI design and usage. The mechanics of how future extensions should be achieved are also covered in this documentation.

---
 Documentation/userspace-api/iommu.rst | 212 ++++++++++++++++++++++++++++++++++
 MAINTAINERS                           |   1 +
 2 files changed, 213 insertions(+)
 create mode 100644 Documentation/userspace-api/iommu.rst
Documentation/userspace-api/iommu.rst new file +212 -0
new file mode 100644
index 000000000000..b2f5b3256d85
@@ -0,0 +1,212 @@
+.. 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 baremetal
+usage, the 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), 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)
+4. Invalidate IOMMU caches requested by guests
+5. 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.)
+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 the structure sizes.
+
+No new fields can be added *after* the variable sized union in that it
+will break backward compatibility when offset moves. 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.
+
+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 app to indicate how much data
+it is 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 some structure size increase,
+IOMMU UAPI code 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, the future errors
+can lead to catastrophic failures for the users.
+
+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 kernel header should
+not be an issue in that only existing flags are used.
+
+IOMMU vendor driver should report the below features to IOMMU UAPI
+consumers (e.g. via VFIO).
+
+1. IOMMU_NESTING_FEAT_SYSWIDE_PASID
+2. IOMMU_NESTING_FEAT_BIND_PGTBL
+3. IOMMU_NESTING_FEAT_BIND_PASID_TABLE
+4. IOMMU_NESTING_FEAT_CACHE_INVLD
+5. IOMMU_NESTING_FEAT_PAGE_REQUEST
+
+Take VFIO as example, upon request from VFIO user space (e.g. QEMU),
+VFIO kernel code shall query IOMMU vendor driver for the support of
+the above features. Query result can then be reported back to the
+user-space caller. Details can be found in
+Documentation/driver-api/vfio.rst.
+
+
+Data Passing Example with VFIO
+------------------------------
+As the ubiquitous userspace driver framework, VFIO is already IOMMU
+aware and shares many key concepts such as device model, group, and
+protection domain. Other user driver frameworks can also be extended
+to support IOMMU UAPI but it is outside the scope of this document.
+
+In this tight-knit VFIO-IOMMU interface, the ultimate consumer of the
+IOMMU UAPI data is the host IOMMU driver. VFIO facilitates user-kernel
+transport, capability checking, security, and life cycle management of
+process address space ID (PASID).
+
+Unlike normal user data passed via VFIO UAPI IOTCL, IOMMU driver is the
+ultimate consumer of its UAPI data. At VFIO layer, the IOMMU UAPI data
+is wrapped in a VFIO UAPI data. It follows the
+pattern below::
+
+   struct {
+	__u32 argsz;
+	__u32 flags;
+	__u8  data[];
+   };
+
+Here data[] contains the IOMMU UAPI data structures. VFIO has the
+freedom to bundle the data as well as parse data size based on its own flags.
+
+In order to determine the size and feature set of the user data, argsz
+and flags (or the equivalent) are also embedded in the IOMMU UAPI data
+structures.
+
+A "__u32 argsz" field is *always* at the beginning of each structure.
+
+For example:
+::
+
+   struct iommu_cache_invalidate_info {
+	__u32	argsz;
+	#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
+	__u32	version;
+	/* IOMMU paging structure cache */
+	#define IOMMU_CACHE_INV_TYPE_IOTLB	(1 << 0) /* IOMMU IOTLB */
+	#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB	(1 << 1) /* Device IOTLB */
+	#define IOMMU_CACHE_INV_TYPE_PASID	(1 << 2) /* PASID cache */
+	#define IOMMU_CACHE_INV_TYPE_NR		(3)
+	__u8	cache;
+	__u8	granularity;
+	__u8	padding[6];
+	union {
+		struct iommu_inv_pasid_info pasid_info;
+		struct iommu_inv_addr_info addr_info;
+	} granu;
+   };
+
+VFIO is responsible for checking its own argsz and flags. It then
+invokes appropriate IOMMU UAPI functions. The user pointers are passed
+to the IOMMU layer for further processing. The responsibilities are
+divided as follows:
+
+- Generic IOMMU layer checks argsz range based on UAPI data in the
+  current kernel version
+
+- Generic IOMMU layer checks content of the UAPI data for non-zero
+  reserved bits in flags, padding fields, and unsupported version.
+  This is to ensure not breaking userspace in the future when these
+  fields or flags are used.
+
+- Vendor IOMMU driver checks argsz based on vendor flags, UAPI data
+  is consumed based on flags. Vendor driver has access to
+  unadulterated argsz value in case of vendor specific future
+  extensions. Currently, it does not perform the copy_from_user()
+  itself. A __user pointer can be provided in some future scenarios
+  where there's vendor data outside of the structure definition.
+
+IOMMU code treats UAPI data into two categories:
+
+- structure contains vendor data
+  (Example: iommu_uapi_cache_invalidate())
+
+- structure contains only generic data
+  (Example: iommu_uapi_sva_bind_gpasid())
+
+
+
+Sharing UAPI with in-kernel users
+---------------------------------
+For UAPIs that are shared with in-kernel users, a wrapper function is
+provided to distinguish the callers. For example,
+
+Userspace caller ::
+
+  int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+                                   struct device *dev,
+                                   void __user *udata)
+
+In-kernel caller ::
+
+  int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+                                   struct device *dev,
+                                   struct iommu_gpasid_bind_data *data)
MAINTAINERS +1 -0
index d53db30d1365..11f907b11f12 100644
@@ -9010,6 +9010,7 @@ L:	[email protected]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
 F:	Documentation/devicetree/bindings/iommu/
+F:	Documentation/userspace-api/iommu.rst
 F:	drivers/iommu/
 F:	include/linux/iommu.h
 F:	include/linux/iova.h
Signature · 6 lines
2.7.4

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
author
#4 lore raw

PATCH v7 2/7 iommu/uapi: Add argsz for user filled data

In reply to Jacob Pan

As IOMMU UAPI gets extended, user data size may increase. To support backward compatibiliy, this patch introduces a size field to each UAPI data structures. It is *always* the responsibility for the user to fill in the correct size. Padding fields are adjusted to ensure 8 byte alignment.

Specific scenarios for user data handling are documented in:
Documentation/userspace-api/iommu.rst

---
 include/uapi/linux/iommu.h | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
include/uapi/linux/iommu.h +9 -3
index e907b7091a46..d5e9014f690e 100644
@@ -135,6 +135,7 @@ enum iommu_page_response_code {
 
 /**
  * struct iommu_page_response - Generic page response information
+ * @argsz: User filled size of this data
  * @version: API version of this structure
  * @flags: encodes whether the corresponding fields are valid
  *         (IOMMU_FAULT_PAGE_RESPONSE_* values)
@@ -143,6 +144,7 @@ enum iommu_page_response_code {
  * @code: response code from &enum iommu_page_response_code
  */
 struct iommu_page_response {
+	__u32	argsz;
 #define IOMMU_PAGE_RESP_VERSION_1	1
 	__u32	version;
 #define IOMMU_PAGE_RESP_PASID_VALID	(1 << 0)
@@ -218,6 +220,7 @@ struct iommu_inv_pasid_info {
 /**
  * struct iommu_cache_invalidate_info - First level/stage invalidation
  *     information
+ * @argsz: User filled size of this data
  * @version: API version of this structure
  * @cache: bitfield that allows to select which caches to invalidate
  * @granularity: defines the lowest granularity used for the invalidation:
@@ -246,6 +249,7 @@ struct iommu_inv_pasid_info {
  * must support the used granularity.
  */
 struct iommu_cache_invalidate_info {
+	__u32	argsz;
 #define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
 	__u32	version;
 /* IOMMU paging structure cache */
@@ -255,7 +259,7 @@ struct iommu_cache_invalidate_info {
 #define IOMMU_CACHE_INV_TYPE_NR		(3)
 	__u8	cache;
 	__u8	granularity;
-	__u8	padding[2];
+	__u8	padding[6];
 	union {
 		struct iommu_inv_pasid_info pasid_info;
 		struct iommu_inv_addr_info addr_info;
@@ -292,6 +296,7 @@ struct iommu_gpasid_bind_data_vtd {
 
 /**
  * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
+ * @argsz:	User filled size of this data
  * @version:	Version of this data structure
  * @format:	PASID table entry format
  * @flags:	Additional information on guest bind request
@@ -309,17 +314,18 @@ struct iommu_gpasid_bind_data_vtd {
  * PASID to host PASID based on this bind data.
  */
 struct iommu_gpasid_bind_data {
+	__u32 argsz;
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
 #define IOMMU_PASID_FORMAT_INTEL_VTD	1
 	__u32 format;
+	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
 	__u64 flags;
 	__u64 gpgd;
 	__u64 hpasid;
 	__u64 gpasid;
-	__u32 addr_width;
-	__u8  padding[12];
+	__u8  padding[8];
 	/* Vendor specific data */
 	union {
 		struct iommu_gpasid_bind_data_vtd vtd;
Signature · 1 line
2.7.4
author
#13 lore raw

PATCH v7 6/7 iommu/uapi: Handle data and argsz filled by users

In reply to Jacob Pan

IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality.

IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags.

User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking.

This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst

---
 drivers/iommu/iommu.c | 201 ++++++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/iommu.h |  28 ++++---
 2 files changed, 212 insertions(+), 17 deletions(-)
drivers/iommu/iommu.c +193 -8
index 3a913ce94a3d..1ee55c4b3a3a 100644
@@ -1950,33 +1950,218 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations. We also
+ * make sure no reserved fields or unused flags are set. This is to ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info)
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret = 0;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
-	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (inv_info.argsz < minsz)
+		return -EINVAL;
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.argsz == minsz &&
+	    ((inv_info.granularity == IOMMU_INV_GRANU_PASID) ||
+		    (inv_info.granularity == IOMMU_INV_GRANU_ADDR)))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info))
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data *data)
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
+{
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
 {
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data);
+}
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev,
+			       void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			    struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_unbind_gpasid(dev, pasid);
+	return domain->ops->sva_unbind_gpasid(dev, data->hpasid);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
include/linux/iommu.h +19 -9
index 2dcc1a33f6dc..4a02c9e09048 100644
@@ -432,11 +432,14 @@ extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct iommu_gpasid_bind_data *data);
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, struct iommu_gpasid_bind_data *data);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1054,22 +1057,29 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info *inv_info)
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }
Signature · 6 lines
2.7.4

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
author
#9 lore raw

PATCH v7 4/7 iommu/uapi: Use named union for user data

In reply to Jacob Pan

IOMMU UAPI data size is filled by the user space which must be validated by the kernel. To ensure backward compatibility, user data can only be extended by either re-purpose padding bytes or extend the variable sized union at the end. No size change is allowed before the union. Therefore, the minimum size is the offset of the union.

To use offsetof() on the union, we must make it named.

---
 drivers/iommu/intel/iommu.c | 22 +++++++++++-----------
 drivers/iommu/intel/svm.c   |  2 +-
 include/uapi/linux/iommu.h  |  4 ++--
 3 files changed, 14 insertions(+), 14 deletions(-)
drivers/iommu/intel/iommu.c +11 -11
index 92c7ad66e64c..021f62078f52 100644
@@ -5417,8 +5417,8 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 
 	/* Size is only valid in address selective invalidation */
 	if (inv_info->granularity == IOMMU_INV_GRANU_ADDR)
-		size = to_vtd_size(inv_info->addr_info.granule_size,
-				   inv_info->addr_info.nb_granules);
+		size = to_vtd_size(inv_info->granu.addr_info.granule_size,
+				   inv_info->granu.addr_info.nb_granules);
 
 	for_each_set_bit(cache_type,
 			 (unsigned long *)&inv_info->cache,
@@ -5439,20 +5439,20 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 		 * granularity.
 		 */
 		if (inv_info->granularity == IOMMU_INV_GRANU_PASID &&
-		    (inv_info->pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
-			pasid = inv_info->pasid_info.pasid;
+		    (inv_info->granu.pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
+			pasid = inv_info->granu.pasid_info.pasid;
 		else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
-			 (inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
-			pasid = inv_info->addr_info.pasid;
+			 (inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
+			pasid = inv_info->granu.addr_info.pasid;
 
 		switch (BIT(cache_type)) {
 		case IOMMU_CACHE_INV_TYPE_IOTLB:
 			/* HW will ignore LSB bits based on address mask */
 			if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
 			    size &&
-			    (inv_info->addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
+			    (inv_info->granu.addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
 				pr_err_ratelimited("User address not aligned, 0x%llx, size order %llu\n",
-					  inv_info->addr_info.addr, size);
+						inv_info->granu.addr_info.addr, size);
 			}
 
 			/*
@@ -5460,9 +5460,9 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 			 * We use npages = -1 to indicate that.
 			 */
 			qi_flush_piotlb(iommu, did, pasid,
-					mm_to_dma_pfn(inv_info->addr_info.addr),
+					mm_to_dma_pfn(inv_info->granu.addr_info.addr),
 					(granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size,
-					inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
+					inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
 
 			if (!info->ats_enabled)
 				break;
@@ -5485,7 +5485,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 				size = 64 - VTD_PAGE_SHIFT;
 				addr = 0;
 			} else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR)
-				addr = inv_info->addr_info.addr;
+				addr = inv_info->granu.addr_info.addr;
 
 			if (info->ats_enabled)
 				qi_flush_dev_iotlb_pasid(iommu, sid,
drivers/iommu/intel/svm.c +1 -1
index d386853121a2..713b3a218483 100644
@@ -338,7 +338,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	spin_lock(&iommu->lock);
 	ret = intel_pasid_setup_nested(iommu, dev,
 				       (pgd_t *)(uintptr_t)data->gpgd,
-				       data->hpasid, &data->vtd, dmar_domain,
+				       data->hpasid, &data->vendor.vtd, dmar_domain,
 				       data->addr_width);
 	spin_unlock(&iommu->lock);
 	if (ret) {
include/uapi/linux/iommu.h +2 -2
index abf4455a3495..8c733beb29c7 100644
@@ -263,7 +263,7 @@ struct iommu_cache_invalidate_info {
 	union {
 		struct iommu_inv_pasid_info pasid_info;
 		struct iommu_inv_addr_info addr_info;
-	};
+	} granu;
 };
 
 /**
@@ -333,7 +333,7 @@ struct iommu_gpasid_bind_data {
 	/* Vendor specific data */
 	union {
 		struct iommu_gpasid_bind_data_vtd vtd;
-	};
+	} vendor;
 };
 
 #endif /* _UAPI_IOMMU_H */
Signature · 6 lines
2.7.4

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
Reviewed-by on v7 1/7
#2 lore raw

Re: [PATCH v7 1/7] docs: IOMMU user API

In reply to Jacob Pan

Hi Jacob,

Quoted 38 lines · Jacob Pan

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 intended to clarify the UAPI design and usage. The mechanics of how future extensions should be achieved are also covered in this documentation.

---
 Documentation/userspace-api/iommu.rst | 212 ++++++++++++++++++++++++++++++++++
 MAINTAINERS                           |   1 +
 2 files changed, 213 insertions(+)
 create mode 100644 Documentation/userspace-api/iommu.rst
Documentation/userspace-api/iommu.rst new file +16 -0
new file mode 100644
index 000000000000..b2f5b3256d85
@@ -0,0 +1,212 @@
+.. 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 baremetal
+usage, the 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), wherin the vIOMMU implementation
+relies on the physical IOMMU and for this reason requires interactions
+with the host driver.

Documentation/userspace-api/iommu.rst line 26

Quoted 10 lines
Documentation/userspace-api/iommu.rst new file +10 -0
+
+.. 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)

nit: s/unbind/Unbind to match above Free

Documentation/userspace-api/iommu.rst line 28

Quoted 2 lines
Documentation/userspace-api/iommu.rst new file +2 -0
+3. Bind/unbind guest PASID table (e.g. ARM SMMU)
+4. Invalidate IOMMU caches requested by guests

s/requested by guests/upon guest requests

Quoted 50 lines
Documentation/userspace-api/iommu.rst new file +50 -0
+5. 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.)
+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 the structure sizes.
+
+No new fields can be added *after* the variable sized union in that it
+will break backward compatibility when offset moves. 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.
+
+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 app to indicate how much data
+it is 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 some structure size increase,
+IOMMU UAPI code 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

Documentation/userspace-api/iommu.rst line 88

Quoted 10 lines
Documentation/userspace-api/iommu.rst new file +10 -0
+   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, the future errors
+can lead to catastrophic failures for the users.

I would rather say: it is strongly advised to check the compatibility upfront, as some subsequent errors happening during vIOMMU operation, such as cache invalidation failures cannot be nicely escaladated to the guest due to IOMMU specifications.

Quoted 29 lines
Documentation/userspace-api/iommu.rst new file +29 -0
+
+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 kernel header should
+not be an issue in that only existing flags are used.
+
+IOMMU vendor driver should report the below features to IOMMU UAPI
+consumers (e.g. via VFIO).
+
+1. IOMMU_NESTING_FEAT_SYSWIDE_PASID
+2. IOMMU_NESTING_FEAT_BIND_PGTBL
+3. IOMMU_NESTING_FEAT_BIND_PASID_TABLE
+4. IOMMU_NESTING_FEAT_CACHE_INVLD
+5. IOMMU_NESTING_FEAT_PAGE_REQUEST
+
+Take VFIO as example, upon request from VFIO user space (e.g. QEMU),
+VFIO kernel code shall query IOMMU vendor driver for the support of
+the above features. Query result can then be reported back to the
+user-space caller. Details can be found in
+Documentation/driver-api/vfio.rst.
+
+
+Data Passing Example with VFIO
+------------------------------
+As the ubiquitous userspace driver framework, VFIO is already IOMMU
+aware and shares many key concepts such as device model, group, and

Documentation/userspace-api/iommu.rst

Quoted 10 lines
Documentation/userspace-api/iommu.rst new file +10 -0
+protection domain. Other user driver frameworks can also be extended
+to support IOMMU UAPI but it is outside the scope of this document.
+
+In this tight-knit VFIO-IOMMU interface, the ultimate consumer of the
+IOMMU UAPI data is the host IOMMU driver. VFIO facilitates user-kernel
+transport, capability checking, security, and life cycle management of
+process address space ID (PASID).
+
+Unlike normal user data passed via VFIO UAPI IOTCL, IOMMU driver is the
+ultimate consumer of its UAPI data.

I would remove the above sentence as it sounds like a repetition of the above paragraph 1st sentence. You may simply say that VFIO mostly conveys the data structs downto the IOMMU driver.

At VFIO layer, the IOMMU UAPI data

Quoted 91 lines
Documentation/userspace-api/iommu.rst new file +85 -0
+is wrapped in a VFIO UAPI data. It follows the
+pattern below::
+
+   struct {
+	__u32 argsz;
+	__u32 flags;
+	__u8  data[];
+   };
+
+Here data[] contains the IOMMU UAPI data structures. VFIO has the
+freedom to bundle the data as well as parse data size based on its own flags.
+
+In order to determine the size and feature set of the user data, argsz
+and flags (or the equivalent) are also embedded in the IOMMU UAPI data
+structures.
+
+A "__u32 argsz" field is *always* at the beginning of each structure.
+
+For example:
+::
+
+   struct iommu_cache_invalidate_info {
+	__u32	argsz;
+	#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
+	__u32	version;
+	/* IOMMU paging structure cache */
+	#define IOMMU_CACHE_INV_TYPE_IOTLB	(1 << 0) /* IOMMU IOTLB */
+	#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB	(1 << 1) /* Device IOTLB */
+	#define IOMMU_CACHE_INV_TYPE_PASID	(1 << 2) /* PASID cache */
+	#define IOMMU_CACHE_INV_TYPE_NR		(3)
+	__u8	cache;
+	__u8	granularity;
+	__u8	padding[6];
+	union {
+		struct iommu_inv_pasid_info pasid_info;
+		struct iommu_inv_addr_info addr_info;
+	} granu;
+   };
+
+VFIO is responsible for checking its own argsz and flags. It then
+invokes appropriate IOMMU UAPI functions. The user pointers are passed
+to the IOMMU layer for further processing. The responsibilities are
+divided as follows:
+
+- Generic IOMMU layer checks argsz range based on UAPI data in the
+  current kernel version
+
+- Generic IOMMU layer checks content of the UAPI data for non-zero
+  reserved bits in flags, padding fields, and unsupported version.
+  This is to ensure not breaking userspace in the future when these
+  fields or flags are used.
+
+- Vendor IOMMU driver checks argsz based on vendor flags, UAPI data
+  is consumed based on flags. Vendor driver has access to
+  unadulterated argsz value in case of vendor specific future
+  extensions. Currently, it does not perform the copy_from_user()
+  itself. A __user pointer can be provided in some future scenarios
+  where there's vendor data outside of the structure definition.
+
+IOMMU code treats UAPI data into two categories:
+
+- structure contains vendor data
+  (Example: iommu_uapi_cache_invalidate())
+
+- structure contains only generic data
+  (Example: iommu_uapi_sva_bind_gpasid())
+
+
+
+Sharing UAPI with in-kernel users
+---------------------------------
+For UAPIs that are shared with in-kernel users, a wrapper function is
+provided to distinguish the callers. For example,
+
+Userspace caller ::
+
+  int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+                                   struct device *dev,
+                                   void __user *udata)
+
+In-kernel caller ::
+
+  int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+                                   struct device *dev,
+                                   struct iommu_gpasid_bind_data *data)
MAINTAINERS +0 -0
index d53db30d1365..11f907b11f12 100644

MAINTAINERS L: [email protected] · line 9016

Quoted 7 lines
MAINTAINERS +1 -0
@@ -9010,6 +9010,7 @@ L:	[email protected]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
 F:	Documentation/devicetree/bindings/iommu/
+F:	Documentation/userspace-api/iommu.rst
 F:	drivers/iommu/
 F:	include/linux/iommu.h
 F:	include/linux/iova.h

Besides the above suggestions,

Eric

Reviewed-by on v7 2/7
#5 lore raw

Re: [PATCH v7 2/7] iommu/uapi: Add argsz for user filled data

In reply to Jacob Pan

Hi,

Quoted 2 lines · Jacob Pan

As IOMMU UAPI gets extended, user data size may increase. To support backward compatibiliy, this patch introduces a size field to each UAPI

s/compatibiliy/compatibility

Quoted 5 lines

data structures. It is *always* the responsibility for the user to fill in the correct size. Padding fields are adjusted to ensure 8 byte alignment.

Specific scenarios for user data handling are documented in:
Documentation/userspace-api/iommu.rst

you may mention the struct version does not need to be incremented as no IOCTL uses the structs yet.

Quoted 72 lines
---
 include/uapi/linux/iommu.h | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
include/uapi/linux/iommu.h +8 -1
index e907b7091a46..d5e9014f690e 100644
@@ -135,6 +135,7 @@ enum iommu_page_response_code {
 
 /**
  * struct iommu_page_response - Generic page response information
+ * @argsz: User filled size of this data
  * @version: API version of this structure
  * @flags: encodes whether the corresponding fields are valid
  *         (IOMMU_FAULT_PAGE_RESPONSE_* values)
@@ -143,6 +144,7 @@ enum iommu_page_response_code {
  * @code: response code from &enum iommu_page_response_code
  */
 struct iommu_page_response {
+	__u32	argsz;
 #define IOMMU_PAGE_RESP_VERSION_1	1
 	__u32	version;
 #define IOMMU_PAGE_RESP_PASID_VALID	(1 << 0)
@@ -218,6 +220,7 @@ struct iommu_inv_pasid_info {
 /**
  * struct iommu_cache_invalidate_info - First level/stage invalidation
  *     information
+ * @argsz: User filled size of this data
  * @version: API version of this structure
  * @cache: bitfield that allows to select which caches to invalidate
  * @granularity: defines the lowest granularity used for the invalidation:
@@ -246,6 +249,7 @@ struct iommu_inv_pasid_info {
  * must support the used granularity.
  */
 struct iommu_cache_invalidate_info {
+	__u32	argsz;
 #define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
 	__u32	version;
 /* IOMMU paging structure cache */
@@ -255,7 +259,7 @@ struct iommu_cache_invalidate_info {
 #define IOMMU_CACHE_INV_TYPE_NR		(3)
 	__u8	cache;
 	__u8	granularity;
-	__u8	padding[2];
+	__u8	padding[6];
 	union {
 		struct iommu_inv_pasid_info pasid_info;
 		struct iommu_inv_addr_info addr_info;
@@ -292,6 +296,7 @@ struct iommu_gpasid_bind_data_vtd {
 
 /**
  * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
+ * @argsz:	User filled size of this data
  * @version:	Version of this data structure
  * @format:	PASID table entry format
  * @flags:	Additional information on guest bind request
@@ -309,17 +314,18 @@ struct iommu_gpasid_bind_data_vtd {
  * PASID to host PASID based on this bind data.
  */
 struct iommu_gpasid_bind_data {
+	__u32 argsz;
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
 #define IOMMU_PASID_FORMAT_INTEL_VTD	1
 	__u32 format;
+	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */

include/uapi/linux/iommu.h struct iommu_gpasid_bind_data_vtd { · line 331

Quoted 10 lines
include/uapi/linux/iommu.h +1 -2
 	__u64 flags;
 	__u64 gpgd;
 	__u64 hpasid;
 	__u64 gpasid;
-	__u32 addr_width;
-	__u8  padding[12];
+	__u8  padding[8];
 	/* Vendor specific data */
 	union {
 		struct iommu_gpasid_bind_data_vtd vtd;

Thanks

Eric

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Reviewed-by on v7 5/7
#11 lore raw

Re: [PATCH v7 5/7] iommu/uapi: Rename uapi functions

In reply to Jacob Pan

Hi Jacob,

Quoted 2 lines · Jacob Pan

User APIs such as iommu_sva_unbind_gpasid() may also be used by the kernel. Since we introduced user pointer to the UAPI functions,

Practically this is done in the next patch. What about something like:

We plan to have two flavors of the same API functions, one called through ioctls, carrying a user pointer and one called directly with valid IOMMU UAPI structs. To differentiate both, let's rename existing functions with an iommu_uapi_ prefix.

Besides

Thanks

Eric

Quoted 119 lines

in-kernel callers cannot share the same APIs. In-kernel callers are also trusted, there is no need to validate the data.

This patch renames all UAPI functions with iommu_uapi_ prefix such that is clear to the intended callers.

---
 drivers/iommu/iommu.c | 18 +++++++++---------
 include/linux/iommu.h | 31 ++++++++++++++++---------------
 2 files changed, 25 insertions(+), 24 deletions(-)
drivers/iommu/iommu.c +9 -9
index b6858adc4f17..3a913ce94a3d 100644
@@ -1950,35 +1950,35 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
-int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-			   struct iommu_cache_invalidate_info *inv_info)
+int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+				struct iommu_cache_invalidate_info *inv_info)
 {
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
 	return domain->ops->cache_invalidate(domain, dev, inv_info);
 }
-EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-			   struct device *dev, struct iommu_gpasid_bind_data *data)
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+			       struct device *dev, struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_bind_gpasid(domain, dev, data);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-			     ioasid_t pasid)
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 ioasid_t pasid)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_unbind_gpasid(dev, pasid);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
include/linux/iommu.h +16 -15
index 5f0b7859d2eb..2dcc1a33f6dc 100644
@@ -430,13 +430,13 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_cache_invalidate(struct iommu_domain *domain,
-				  struct device *dev,
-				  struct iommu_cache_invalidate_info *inv_info);
-extern int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-		struct device *dev, struct iommu_gpasid_bind_data *data);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-				struct device *dev, ioasid_t pasid);
+extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+				       struct device *dev,
+				       struct iommu_cache_invalidate_info *inv_info);
+extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+				      struct device *dev, struct iommu_gpasid_bind_data *data);
+extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1054,21 +1054,22 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int
-iommu_cache_invalidate(struct iommu_domain *domain,
-		       struct device *dev,
-		       struct iommu_cache_invalidate_info *inv_info)
+static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+					      struct device *dev,
+					      struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
-static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-				struct device *dev, struct iommu_gpasid_bind_data *data)
+
+static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+					     struct device *dev,
+					     struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }
 
-static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-					   struct device *dev, int pasid)
+static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					       struct device *dev, int pasid)
 {
 	return -ENODEV;
 }
Reviewed-by on v7 6/7
#14 lore raw

Re: [PATCH v7 6/7] iommu/uapi: Handle data and argsz filled by users

In reply to Jacob Pan

Hi Jacob,

Quoted 4 lines · Jacob Pan

IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality.

This is just done for a single function, ie. iommu_sva_unbind_gpasid.

If I am not wrong there is no user of this latter after applying the whole series? If correct you may remove it at this stage?

Quoted 300 lines

IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags.

User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking.

This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst

---
 drivers/iommu/iommu.c | 201 ++++++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/iommu.h |  28 ++++---
 2 files changed, 212 insertions(+), 17 deletions(-)
drivers/iommu/iommu.c +193 -7
index 3a913ce94a3d..1ee55c4b3a3a 100644
@@ -1950,33 +1950,218 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations. We also
+ * make sure no reserved fields or unused flags are set. This is to ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info)
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret = 0;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 > -	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (inv_info.argsz < minsz)
+		return -EINVAL;
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.argsz == minsz &&
+	    ((inv_info.granularity == IOMMU_INV_GRANU_PASID) ||
+		    (inv_info.granularity == IOMMU_INV_GRANU_ADDR)))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info))
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data *data)
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
+{
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
 {
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data);
+}
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev,
+			       void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			    struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_unbind_gpasid(dev, pasid);
+	return domain->ops->sva_unbind_gpasid(dev, data->hpasid);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
include/linux/iommu.h +12 -9
index 2dcc1a33f6dc..4a02c9e09048 100644
@@ -432,11 +432,14 @@ extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct iommu_gpasid_bind_data *data);
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, struct iommu_gpasid_bind_data *data);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1054,22 +1057,29 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info *inv_info)
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle) · line 1085

Quoted 10 lines
include/linux/iommu.h +7 -0
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }

Otherwise looks good to me

Thanks

Eric

#20 lore raw

Re: [PATCH v7 7/7] iommu/vt-d: Check UAPI data processed by IOMMU core

In reply to Jacob Pan

Hi Jacob,

Quoted 32 lines · Jacob Pan

IOMMU generic layer already does sanity checks UAPI data for version match and argsz range under generic information.
Remove the redundant version check from VT-d driver and check for vendor specific data size.

---
 drivers/iommu/intel/iommu.c | 3 +--
 drivers/iommu/intel/svm.c   | 7 +++++--
 2 files changed, 6 insertions(+), 4 deletions(-)
drivers/iommu/intel/iommu.c +1 -2
index 021f62078f52..7e03cca31a0e 100644
@@ -5391,8 +5391,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 	int ret = 0;
 	u64 size = 0;
 
-	if (!inv_info || !dmar_domain ||
-	    inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+	if (!inv_info || !dmar_domain)
 		return -EINVAL;
 
 	if (!dev || !dev_is_pci(dev))
drivers/iommu/intel/svm.c +0 -0
index 713b3a218483..55ea11e9c0f5 100644
@@ -240,8 +240,11 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	if (WARN_ON(!iommu) || !data)

drivers/iommu/intel/svm.c int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, · line 248

Quoted 10 lines
drivers/iommu/intel/svm.c +5 -2
 		return -EINVAL;
 
-	if (data->version != IOMMU_GPASID_BIND_VERSION_1 ||
-	    data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+	if (data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+		return -EINVAL;
+
+	/* IOMMU core ensures argsz is more than the start of the union */
+	if (data->argsz < offsetofend(struct iommu_gpasid_bind_data, vendor.vtd))
 		return -EINVAL;

Shouldn't you test the vendor flags here? intel_pasid_setup_bind_data() only checks valid ones but not ~mask.

Thanks

Eric

Quoted 3 lines
drivers/iommu/intel/svm.c +0 -0
 	if (!dev_is_pci(dev))
 
#15 lore raw

RE: [PATCH v7 6/7] iommu/uapi: Handle data and argsz filled by users

In reply to Auger Eric

Hi Eric,

Quoted 6 lines

From: Auger Eric <[email protected]>
Sent: Thursday, August 13, 2020 5:12 PM

Hi Jacob,

On 7/30/20 2:21 AM, Jacob Pan wrote:

Quoted 8 lines
Quoted 4 lines

IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality.

This is just done for a single function, ie. iommu_sva_unbind_gpasid.

If I am not wrong there is no user of this latter after applying the whole series? If correct you may remove it at this stage?

the user of this function is in vfio. And it is the same with iommu_uapi_sva_bind/unbind_gpasid() and iommu_uapi_cache_invalidate().

https://lore.kernel.org/kvm/[email protected]/
https://lore.kernel.org/kvm/[email protected]/

Regards,
Yi Liu

Quoted 331 lines
Quoted 10 lines

IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags.

User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking.

Quoted 8 lines

This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst

---
 drivers/iommu/iommu.c | 201

++++++++++++++++++++++++++++++++++++++++++++++++--

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain

Quoted 8 lines
 include/linux/iommu.h |  28 ++++---
 2 files changed, 212 insertions(+), 17 deletions(-)
drivers/iommu/iommu.c +0 -0
index 3a913ce94a3d..1ee55c4b3a3a 100644
@@ -1950,33 +1950,218 @@ int iommu_attach_device(struct iommu_domain

*domain, struct device *dev)

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 9 lines
drivers/iommu/iommu.c +6 -0
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations. We also
+ * make sure no reserved fields or unused flags are set. This is to ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info

*info)

Quoted 41 lines
drivers/iommu/iommu.c +41 -0
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +9 -0
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device

*dev,

Quoted 22 lines
drivers/iommu/iommu.c +17 -1
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret = 0;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 > -	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (inv_info.argsz < minsz)

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+		return -EINVAL;
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.argsz == minsz &&
+	    ((inv_info.granularity == IOMMU_INV_GRANU_PASID) ||
+		    (inv_info.granularity == IOMMU_INV_GRANU_ADDR)))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info,

granu.pasid_info))

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 4 lines
drivers/iommu/iommu.c +4 -0
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info,

granu.addr_info))

Quoted 13 lines
drivers/iommu/iommu.c +13 -0
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +5 -2
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data

*data)

Quoted 49 lines
drivers/iommu/iommu.c +48 -0
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
+{
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
 {
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data);
+}
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device

*dev,

Quoted 8 lines
drivers/iommu/iommu.c +5 -0
+			       void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +5 -2
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 13 lines
drivers/iommu/iommu.c +7 -2
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			    struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_unbind_gpasid(dev, pasid);
+	return domain->ops->sva_unbind_gpasid(dev, data->hpasid);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

include/linux/iommu.h extern void iommu_detach_device(struct

Quoted 21 lines
drivers/iommu/iommu.c +13 -0
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
include/linux/iommu.h +0 -0
index 2dcc1a33f6dc..4a02c9e09048 100644
@@ -432,11 +432,14 @@ extern void iommu_detach_device(struct

iommu_domain *domain,

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain,

Quoted 8 lines
include/linux/iommu.h +2 -2
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct

iommu_gpasid_bind_data *data);

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain,

Quoted 6 lines
include/linux/iommu.h +4 -1
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, struct

iommu_gpasid_bind_data *data);

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct

Quoted 4 lines
include/linux/iommu.h +0 -0
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1054,22 +1057,29 @@ static inline int iommu_sva_get_pasid(struct

iommu_sva *handle)

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle)

Quoted 6 lines
include/linux/iommu.h +0 -3
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info

*inv_info)

Quoted 20 lines
include/linux/iommu.h +6 -3
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle) · line 1085

Quoted 10 lines
include/linux/iommu.h +7 -0
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }

Otherwise looks good to me

Thanks

Eric

Reviewed-by on v7 3/7
#8 lore raw

Re: [PATCH v7 3/7] iommu/uapi: Introduce enum type for PASID data format

In reply to Jacob Pan

Hi Jacob,

Quoted 34 lines · Jacob Pan

There can be multiple vendor-specific PASID data formats used in UAPI structures. This patch adds enum type with a last entry which makes range checking much easier.

---
 include/uapi/linux/iommu.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
include/uapi/linux/iommu.h +6 -1
index d5e9014f690e..abf4455a3495 100644
@@ -294,11 +294,16 @@ struct iommu_gpasid_bind_data_vtd {
 					 IOMMU_SVA_VTD_GPASID_PCD |  \
 					 IOMMU_SVA_VTD_GPASID_PWT)
 
+enum iommu_pasid_data_format {
+	IOMMU_PASID_FORMAT_INTEL_VTD = 1,
+	IOMMU_PASID_FORMAT_LAST,
+};
+
 /**
  * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
  * @argsz:	User filled size of this data
  * @version:	Version of this data structure
- * @format:	PASID table entry format
+ * @format:	PASID table entry format of enum iommu_pasid_data_format type
  * @flags:	Additional information on guest bind request
  * @gpgd:	Guest page directory base of the guest mm to bind
  * @hpasid:	Process address space ID used for the guest mm in host IOMMU

include/uapi/linux/iommu.h struct iommu_gpasid_bind_data { · line 327

Quoted 7 lines
include/uapi/linux/iommu.h +0 -1
@@ -317,7 +322,6 @@ struct iommu_gpasid_bind_data {
 	__u32 argsz;
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
-#define IOMMU_PASID_FORMAT_INTEL_VTD	1
 	__u32 format;
 	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */

Eric

#16 lore raw

Re: [PATCH v7 6/7] iommu/uapi: Handle data and argsz filled by users

In reply to Liu, Yi L

Hi Yi,

Quoted 15 lines · Yi L

Hi Eric,

Quoted 12 lines

From: Auger Eric <[email protected]>
Sent: Thursday, August 13, 2020 5:12 PM

Hi Jacob,

Quoted 4 lines · Jacob Pan

IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality.

This is just done for a single function, ie. iommu_sva_unbind_gpasid.

Quoted 8 lines
Quoted 2 lines

If I am not wrong there is no user of this latter after applying the whole series? If correct you may remove it at this stage?

the user of this function is in vfio. And it is the same with iommu_uapi_sva_bind/unbind_gpasid() and iommu_uapi_cache_invalidate().

https://lore.kernel.org/kvm/[email protected]/
https://lore.kernel.org/kvm/[email protected]/

Yep I know ;-) But this series mostly deals with iommu uapi rework. That's not a big deal though.

Thanks

Eric

Quoted 336 lines

Regards,
Yi Liu

Quoted 331 lines
Quoted 10 lines

IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags.

User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking.

Quoted 8 lines

This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst

---
 drivers/iommu/iommu.c | 201

++++++++++++++++++++++++++++++++++++++++++++++++--

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain

Quoted 8 lines
 include/linux/iommu.h |  28 ++++---
 2 files changed, 212 insertions(+), 17 deletions(-)
drivers/iommu/iommu.c +0 -0
index 3a913ce94a3d..1ee55c4b3a3a 100644
@@ -1950,33 +1950,218 @@ int iommu_attach_device(struct iommu_domain

*domain, struct device *dev)

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 9 lines
drivers/iommu/iommu.c +6 -0
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations. We also
+ * make sure no reserved fields or unused flags are set. This is to ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info

*info)

Quoted 41 lines
drivers/iommu/iommu.c +41 -0
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +9 -0
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device

*dev,

Quoted 22 lines
drivers/iommu/iommu.c +17 -1
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret = 0;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 > -	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (inv_info.argsz < minsz)

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+		return -EINVAL;
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.argsz == minsz &&
+	    ((inv_info.granularity == IOMMU_INV_GRANU_PASID) ||
+		    (inv_info.granularity == IOMMU_INV_GRANU_ADDR)))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info,

granu.pasid_info))

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 4 lines
drivers/iommu/iommu.c +4 -0
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info,

granu.addr_info))

Quoted 13 lines
drivers/iommu/iommu.c +13 -0
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +5 -2
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data

*data)

Quoted 49 lines
drivers/iommu/iommu.c +48 -0
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
+{
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
 {
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data);
+}
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device

*dev,

Quoted 8 lines
drivers/iommu/iommu.c +5 -0
+			       void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +5 -2
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 13 lines
drivers/iommu/iommu.c +7 -2
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			    struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_unbind_gpasid(dev, pasid);
+	return domain->ops->sva_unbind_gpasid(dev, data->hpasid);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

include/linux/iommu.h extern void iommu_detach_device(struct

Quoted 21 lines
drivers/iommu/iommu.c +13 -0
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
include/linux/iommu.h +0 -0
index 2dcc1a33f6dc..4a02c9e09048 100644
@@ -432,11 +432,14 @@ extern void iommu_detach_device(struct

iommu_domain *domain,

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain,

Quoted 8 lines
include/linux/iommu.h +2 -2
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct

iommu_gpasid_bind_data *data);

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain,

Quoted 6 lines
include/linux/iommu.h +4 -1
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, struct

iommu_gpasid_bind_data *data);

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct

Quoted 4 lines
include/linux/iommu.h +0 -0
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1054,22 +1057,29 @@ static inline int iommu_sva_get_pasid(struct

iommu_sva *handle)

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle)

Quoted 6 lines
include/linux/iommu.h +0 -3
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info

*inv_info)

Quoted 20 lines
include/linux/iommu.h +6 -3
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle) · line 1085

Quoted 10 lines
include/linux/iommu.h +7 -0
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }

Otherwise looks good to me

Thanks

Eric

#17 lore raw

RE: [PATCH v7 6/7] iommu/uapi: Handle data and argsz filled by users

Quoted 27 lines

From: Auger Eric <[email protected]>
Sent: Thursday, August 13, 2020 5:31 PM

Hi Yi,

Quoted 21 lines · Yi L

Hi Eric,

Quoted 6 lines

From: Auger Eric <[email protected]>
Sent: Thursday, August 13, 2020 5:12 PM

Hi Jacob,

On 7/30/20 2:21 AM, Jacob Pan wrote:

Quoted 8 lines
Quoted 4 lines

IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality.

This is just done for a single function, ie. iommu_sva_unbind_gpasid.

If I am not wrong there is no user of this latter after applying the whole series? If correct you may remove it at this stage?

the user of this function is in vfio. And it is the same with iommu_uapi_sva_bind/unbind_gpasid() and iommu_uapi_cache_invalidate().

Quoted 6 lines
Quoted 4 lines

https://lore.kernel.org/kvm/1595917664-33276-11-git-send-email-yi.l.li
[email protected]/
https://lore.kernel.org/kvm/1595917664-33276-12-git-send-email-yi.l.li
[email protected]/

Yep I know ;-) But this series mostly deals with iommu uapi rework. That's not a big deal though.

I see. btw. it's great if you can take a look on vfio v6 to see if your comments are well addressed. :-)

Regards,
Yi Liu

Quoted 328 lines

Thanks

Eric

Quoted 239 lines

Regards,
Yi Liu

Quoted 235 lines
Quoted 10 lines

IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags.

User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking.

Quoted 8 lines

This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst

---
 drivers/iommu/iommu.c | 201

++++++++++++++++++++++++++++++++++++++++++++++++--

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain

Quoted 8 lines
 include/linux/iommu.h |  28 ++++---
 2 files changed, 212 insertions(+), 17 deletions(-)
drivers/iommu/iommu.c index renamed from drivers/iommu/iommu.c +0 -0

3a913ce94a3d..1ee55c4b3a3a 100644

drivers/iommu/iommu.c +0 -0
@@ -1950,33 +1950,218 @@ int iommu_attach_device(struct iommu_domain

*domain, struct device *dev)

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 12 lines
drivers/iommu/iommu.c +9 -0
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations.
+We also
+ * make sure no reserved fields or unused flags are set. This is to
+ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct
+iommu_cache_invalidate_info

*info)

Quoted 51 lines
drivers/iommu/iommu.c +50 -0
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct
Quoted 1 line

device

*dev,

Quoted 23 lines
drivers/iommu/iommu.c +18 -1
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret = 0;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 > -	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (inv_info.argsz < minsz)
+		return -EINVAL;

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.argsz == minsz &&
+	    ((inv_info.granularity == IOMMU_INV_GRANU_PASID) ||
+		    (inv_info.granularity == IOMMU_INV_GRANU_ADDR)))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct
+iommu_cache_invalidate_info,

granu.pasid_info))

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 5 lines
drivers/iommu/iommu.c +5 -0
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct
+iommu_cache_invalidate_info,

granu.addr_info))

Quoted 13 lines
drivers/iommu/iommu.c +13 -0
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +5 -2
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data

*data)

Quoted 49 lines
drivers/iommu/iommu.c +48 -0
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data
+*data) {
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
 {
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data); }
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct
+device

*dev,

Quoted 17 lines
drivers/iommu/iommu.c +10 -1
+			       void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
Quoted 5 lines
Quoted 5 lines
Quoted 2 lines

-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

drivers/iommu/iommu.c

Quoted 2 lines
drivers/iommu/iommu.c +1 -1
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

Quoted 43 lines
Quoted 43 lines

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 11 lines
drivers/iommu/iommu.c +6 -1
+			    struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_unbind_gpasid(dev, pasid);
+	return domain->ops->sva_unbind_gpasid(dev, data->hpasid); }
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+struct device

*dev,

include/linux/iommu.h extern void iommu_detach_device(struct

Quoted 21 lines
drivers/iommu/iommu.c +13 -0
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
include/linux/iommu.h index renamed from include/linux/iommu.h +0 -0

2dcc1a33f6dc..4a02c9e09048 100644

include/linux/iommu.h +0 -0
@@ -432,11 +432,14 @@ extern void iommu_detach_device(struct

iommu_domain *domain,

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain,

Quoted 8 lines
include/linux/iommu.h +2 -2
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct

iommu_gpasid_bind_data *data);

Quoted 4 lines
Quoted 4 lines

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain, · line 440

Quoted 4 lines
include/linux/iommu.h +2 -1
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);

extern int

Quoted 32 lines
Quoted 32 lines

include/linux/iommu.h extern void iommu_detach_device(struct · line 442

Quoted 2 lines
include/linux/iommu.h +2 -0
+iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, struct

iommu_gpasid_bind_data *data);

Quoted 5 lines
include/linux/iommu.h +0 -0
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device
 *dev);  extern struct iommu_domain *iommu_get_dma_domain(struct
 device *dev);  extern int iommu_map(struct iommu_domain *domain,

unsigned long iova, @@ -1054,22 +1057,29 @@ static inline int iommu_sva_get_pasid(struct

iommu_sva *handle)

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle)

Quoted 6 lines
include/linux/iommu.h +0 -3
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info

*inv_info)

Quoted 16 lines
include/linux/iommu.h +5 -2
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
Quoted 21 lines
Quoted 3 lines
Quoted 3 lines

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle) · line 1075

Quoted 3 lines

static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +1 -1
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)

{

Quoted 17 lines
Quoted 16 lines

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle) · line 1085

Quoted 10 lines
include/linux/iommu.h +6 -0
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }

Otherwise looks good to me

Thanks

Eric

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

#18 lore raw

Re: [PATCH v7 6/7] iommu/uapi: Handle data and argsz filled by users

Hi Yi,

Quoted 31 lines · Yi L
Quoted 31 lines

From: Auger Eric <[email protected]>
Sent: Thursday, August 13, 2020 5:31 PM

Hi Yi,

Quoted 25 lines · Yi L

Hi Eric,

Quoted 6 lines

From: Auger Eric <[email protected]>
Sent: Thursday, August 13, 2020 5:12 PM

Hi Jacob,

On 7/30/20 2:21 AM, Jacob Pan wrote:

Quoted 8 lines
Quoted 4 lines

IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality.

This is just done for a single function, ie. iommu_sva_unbind_gpasid.

If I am not wrong there is no user of this latter after applying the whole series? If correct you may remove it at this stage?

the user of this function is in vfio. And it is the same with iommu_uapi_sva_bind/unbind_gpasid() and iommu_uapi_cache_invalidate().

https://lore.kernel.org/kvm/1595917664-33276-11-git-send-email-yi.l.li
[email protected]/
https://lore.kernel.org/kvm/1595917664-33276-12-git-send-email-yi.l.li
[email protected]/

Quoted 5 lines
Quoted 2 lines

Yep I know ;-) But this series mostly deals with iommu uapi rework. That's not a big deal though.

I see. btw. it's great if you can take a look on vfio v6 to see if your comments are well addressed. :-)

Yep I will do asap

Thanks

Eric

Quoted 354 lines

Regards,
Yi Liu

Quoted 349 lines

Thanks

Eric

Quoted 239 lines

Regards,
Yi Liu

Quoted 235 lines
Quoted 10 lines

IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags.

User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking.

Quoted 8 lines

This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst

---
 drivers/iommu/iommu.c | 201

++++++++++++++++++++++++++++++++++++++++++++++++--

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain

Quoted 8 lines
 include/linux/iommu.h |  28 ++++---
 2 files changed, 212 insertions(+), 17 deletions(-)
drivers/iommu/iommu.c index renamed from drivers/iommu/iommu.c +0 -0

3a913ce94a3d..1ee55c4b3a3a 100644

drivers/iommu/iommu.c +0 -0
@@ -1950,33 +1950,218 @@ int iommu_attach_device(struct iommu_domain

*domain, struct device *dev)

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 12 lines
drivers/iommu/iommu.c +9 -0
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations.
+We also
+ * make sure no reserved fields or unused flags are set. This is to
+ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct
+iommu_cache_invalidate_info

*info)

Quoted 51 lines
drivers/iommu/iommu.c +50 -0
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct
Quoted 1 line

device

*dev,

Quoted 23 lines
drivers/iommu/iommu.c +18 -1
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret = 0;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 > -	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (inv_info.argsz < minsz)
+		return -EINVAL;

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.argsz == minsz &&
+	    ((inv_info.granularity == IOMMU_INV_GRANU_PASID) ||
+		    (inv_info.granularity == IOMMU_INV_GRANU_ADDR)))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct
+iommu_cache_invalidate_info,

granu.pasid_info))

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 5 lines
drivers/iommu/iommu.c +5 -0
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct
+iommu_cache_invalidate_info,

granu.addr_info))

Quoted 13 lines
drivers/iommu/iommu.c +13 -0
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +5 -2
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data

*data)

Quoted 49 lines
drivers/iommu/iommu.c +48 -0
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data
+*data) {
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
 {
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before variable size union is mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data); }
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct
+device

*dev,

Quoted 17 lines
drivers/iommu/iommu.c +10 -1
+			       void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
Quoted 5 lines
Quoted 5 lines
Quoted 2 lines

-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

drivers/iommu/iommu.c

Quoted 2 lines
drivers/iommu/iommu.c +1 -1
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device

*dev,

Quoted 43 lines
Quoted 43 lines

drivers/iommu/iommu.c int iommu_attach_device(struct iommu_domain *domain, struct device *dev)

Quoted 11 lines
drivers/iommu/iommu.c +6 -1
+			    struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_unbind_gpasid(dev, pasid);
+	return domain->ops->sva_unbind_gpasid(dev, data->hpasid); }
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+struct device

*dev,

include/linux/iommu.h extern void iommu_detach_device(struct

Quoted 21 lines
drivers/iommu/iommu.c +13 -0
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
include/linux/iommu.h index renamed from include/linux/iommu.h +0 -0

2dcc1a33f6dc..4a02c9e09048 100644

include/linux/iommu.h +0 -0
@@ -432,11 +432,14 @@ extern void iommu_detach_device(struct

iommu_domain *domain,

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain,

Quoted 8 lines
include/linux/iommu.h +2 -2
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct

iommu_gpasid_bind_data *data);

Quoted 4 lines
Quoted 4 lines

include/linux/iommu.h extern void iommu_detach_device(struct iommu_domain *domain, · line 440

Quoted 4 lines
include/linux/iommu.h +2 -1
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);

extern int

Quoted 32 lines
Quoted 32 lines

include/linux/iommu.h extern void iommu_detach_device(struct · line 442

Quoted 2 lines
include/linux/iommu.h +2 -0
+iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, struct

iommu_gpasid_bind_data *data);

Quoted 5 lines
include/linux/iommu.h +0 -0
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device
 *dev);  extern struct iommu_domain *iommu_get_dma_domain(struct
 device *dev);  extern int iommu_map(struct iommu_domain *domain,

unsigned long iova, @@ -1054,22 +1057,29 @@ static inline int iommu_sva_get_pasid(struct

iommu_sva *handle)

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle)

Quoted 6 lines
include/linux/iommu.h +0 -3
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info

*inv_info)

Quoted 16 lines
include/linux/iommu.h +5 -2
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
Quoted 3 lines
Quoted 3 lines

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle) · line 1075

Quoted 3 lines

static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +1 -1
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)

{

Quoted 17 lines
Quoted 16 lines

include/linux/iommu.h static inline int iommu_sva_get_pasid(struct iommu_sva *handle) · line 1085

Quoted 10 lines
include/linux/iommu.h +6 -0
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }

Otherwise looks good to me

Thanks

Eric

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

author
#3 lore raw

Re: [PATCH v7 1/7] docs: IOMMU user API

In reply to Auger Eric
Quoted 46 lines · On Wed, 12 Aug 2020 18:38:50 +0200 Auger Eric <[email protected]> wrote:

Hi Jacob,

Quoted 43 lines · Jacob Pan

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 intended to clarify the UAPI design and usage. The mechanics of how future extensions should be achieved are also covered in this documentation.

---
 Documentation/userspace-api/iommu.rst | 212

++++++++++++++++++++++++++++++++++
MAINTAINERS | 1 + 2 files changed, 213
insertions(+) create mode 100644
Documentation/userspace-api/iommu.rst

(quoted diff) +0 -0

b/Documentation/userspace-api/iommu.rst new file mode 100644 index 000000000000..b2f5b3256d85

Documentation/userspace-api/iommu.rst new file +8 -0
@@ -0,0 +1,212 @@
+.. 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 baremetal +usage, the IOMMU is a system device which does not need to communicate +with user space directly.

Documentation/userspace-api/iommu.rst new file +4 -0
+
+The primary use cases are guest Shared Virtual Address (SVA) and
+guest IO virtual address (IOVA), wherin the vIOMMU implementation
+relies on the physical IOMMU and for this reason requires

interactions +with the host driver.

Documentation/userspace-api/iommu.rst new file +3 -0
+
+.. contents:: :local:
+
Quoted 8 lines

Documentation/userspace-api/iommu.rst line 26

Quoted 7 lines
Documentation/userspace-api/iommu.rst new file +7 -0
+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)  

nit: s/unbind/Unbind to match above Free

Sounds good, same below.

Quoted 3 lines
Quoted 2 lines

+3. Bind/unbind guest PASID table (e.g. ARM SMMU)
+4. Invalidate IOMMU caches requested by guests

s/requested by guests/upon guest requests

Will do.

Quoted 59 lines
Quoted 59 lines

+5. Report errors to the guest and serve page requests

Documentation/userspace-api/iommu.rst new file +13 -0
+
+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. +

Documentation/userspace-api/iommu.rst new file +6 -0
+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 the structure sizes. +
+No new fields can be added *after* the variable sized union in that it +will break backward compatibility when offset moves. 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.

Documentation/userspace-api/iommu.rst new file +2 -0
+
+Version field is only reserved for the unlikely event of UAPI

upgrade +at its entirety.

Documentation/userspace-api/iommu.rst new file +2 -0
+
+It's *always* the caller's responsibility to indicate the size of

the +structure passed by setting argsz appropriately.

Documentation/userspace-api/iommu.rst new file +2 -0
+Though at the same time, argsz is user provided data which is not
+trusted. The argsz field allows the user app to indicate how much

data +it is providing, it's still the kernel's responsibility to validate +whether it's correct and sufficient for the requested operation. +

Documentation/userspace-api/iommu.rst new file +7 -0
+Compatibility Checking
+----------------------
+When IOMMU UAPI extension results in some structure size increase,
+IOMMU UAPI code 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

Documentation/userspace-api/iommu.rst new file +4 -0
+   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

Documentation/userspace-api/iommu.rst new file +5 -0
+   range. The data may contain garbage.
+
+Feature Checking
+----------------
+While launching a guest with vIOMMU, it is important to ensure
Quoted 9 lines
Quoted 4 lines

that host +can support the UAPI data structures to be used for vIOMMU-pIOMMU +communications. Without upfront compatibility checking, the future errors +can lead to catastrophic failures for the users.

I would rather say: it is strongly advised to check the compatibility upfront, as some subsequent errors happening during vIOMMU operation, such as cache invalidation failures cannot be nicely escaladated to the guest due to IOMMU specifications.

Sounds more fluid, will do. I also wanted to emphasis on the potential catastrophic results.

Quoted 34 lines
Quoted 34 lines
Documentation/userspace-api/iommu.rst new file +4 -0
+
+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 kernel header should +not be an issue in that only existing flags are used. +

Documentation/userspace-api/iommu.rst new file +10 -0
+IOMMU vendor driver should report the below features to IOMMU UAPI
+consumers (e.g. via VFIO).
+
+1. IOMMU_NESTING_FEAT_SYSWIDE_PASID
+2. IOMMU_NESTING_FEAT_BIND_PGTBL
+3. IOMMU_NESTING_FEAT_BIND_PASID_TABLE
+4. IOMMU_NESTING_FEAT_CACHE_INVLD
+5. IOMMU_NESTING_FEAT_PAGE_REQUEST
+
+Take VFIO as example, upon request from VFIO user space (e.g.

QEMU), +VFIO kernel code shall query IOMMU vendor driver for the support of +the above features. Query result can then be reported back to the +user-space caller. Details can be found in

Documentation/userspace-api/iommu.rst new file +8 -0
+Documentation/driver-api/vfio.rst.
+
+
+Data Passing Example with VFIO
+------------------------------
+As the ubiquitous userspace driver framework, VFIO is already IOMMU
+aware and shares many key concepts such as device model, group, and
+protection domain. Other user driver frameworks can also be

extended +to support IOMMU UAPI but it is outside the scope of this document. +
+In this tight-knit VFIO-IOMMU interface, the ultimate consumer of the +IOMMU UAPI data is the host IOMMU driver. VFIO facilitates

Quoted 9 lines
Quoted 5 lines

user-kernel +transport, capability checking, security, and life cycle management of +process address space ID (PASID).

Documentation/userspace-api/iommu.rst new file +2 -0
+
+Unlike normal user data passed via VFIO UAPI IOTCL, IOMMU driver

is the +ultimate consumer of its UAPI data.

I would remove the above sentence as it sounds like a repetition of the above paragraph 1st sentence. You may simply say that VFIO mostly conveys the data structs downto the IOMMU driver.

Right, it is redundant.

Quoted 104 lines

At VFIO layer, the IOMMU UAPI data

Quoted 95 lines
Documentation/userspace-api/iommu.rst new file +11 -0
+is wrapped in a VFIO UAPI data. It follows the
+pattern below::
+
+   struct {
+	__u32 argsz;
+	__u32 flags;
+	__u8  data[];
+   };
+
+Here data[] contains the IOMMU UAPI data structures. VFIO has the
+freedom to bundle the data as well as parse data size based on its

own flags. +
+In order to determine the size and feature set of the user data, argsz +and flags (or the equivalent) are also embedded in the IOMMU UAPI data +structures.

Documentation/userspace-api/iommu.rst new file +2 -0
+
+A "__u32 argsz" field is *always* at the beginning of each

structure. +

Documentation/userspace-api/iommu.rst new file +9 -0
+For example:
+::
+
+   struct iommu_cache_invalidate_info {
+	__u32	argsz;
+	#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
+	__u32	version;
+	/* IOMMU paging structure cache */
+	#define IOMMU_CACHE_INV_TYPE_IOTLB	(1 << 0) /*

IOMMU IOTLB */

Documentation/userspace-api/iommu.rst new file +1 -0
+	#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB	(1 << 1) /*

Device IOTLB */

Documentation/userspace-api/iommu.rst new file +1 -0
+	#define IOMMU_CACHE_INV_TYPE_PASID	(1 << 2) /*

PASID cache */

Documentation/userspace-api/iommu.rst new file +12 -0
+	#define IOMMU_CACHE_INV_TYPE_NR		(3)
+	__u8	cache;
+	__u8	granularity;
+	__u8	padding[6];
+	union {
+		struct iommu_inv_pasid_info pasid_info;
+		struct iommu_inv_addr_info addr_info;
+	} granu;
+   };
+
+VFIO is responsible for checking its own argsz and flags. It then
+invokes appropriate IOMMU UAPI functions. The user pointers are

passed +to the IOMMU layer for further processing. The responsibilities are +divided as follows:

Documentation/userspace-api/iommu.rst new file +29 -0
+
+- Generic IOMMU layer checks argsz range based on UAPI data in the
+  current kernel version
+
+- Generic IOMMU layer checks content of the UAPI data for non-zero
+  reserved bits in flags, padding fields, and unsupported version.
+  This is to ensure not breaking userspace in the future when these
+  fields or flags are used.
+
+- Vendor IOMMU driver checks argsz based on vendor flags, UAPI data
+  is consumed based on flags. Vendor driver has access to
+  unadulterated argsz value in case of vendor specific future
+  extensions. Currently, it does not perform the copy_from_user()
+  itself. A __user pointer can be provided in some future scenarios
+  where there's vendor data outside of the structure definition.
+
+IOMMU code treats UAPI data into two categories:
+
+- structure contains vendor data
+  (Example: iommu_uapi_cache_invalidate())
+
+- structure contains only generic data
+  (Example: iommu_uapi_sva_bind_gpasid())
+
+
+
+Sharing UAPI with in-kernel users
+---------------------------------
+For UAPIs that are shared with in-kernel users, a wrapper function

is +provided to distinguish the callers. For example,

Documentation/userspace-api/iommu.rst new file +12 -0
+
+Userspace caller ::
+
+  int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+                                   struct device *dev,
+                                   void __user *udata)
+
+In-kernel caller ::
+
+  int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+                                   struct device *dev,
+                                   struct iommu_gpasid_bind_data

*data) diff --git a/MAINTAINERS b/MAINTAINERS
index d53db30d1365..11f907b11f12 100644

MAINTAINERS +0 -0
@@ -9010,6 +9010,7 @@ L:	[email protected]
 S:	Maintained
 T:	git
Quoted 6 lines

git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
F: Documentation/devicetree/bindings/iommu/ +F:
Documentation/userspace-api/iommu.rst F: drivers/iommu/
F: include/linux/iommu.h
F: include/linux/iova.h

Besides the above suggestions,

Quoted 4 lines

Eric

Thank you so much, will integrate into version 8.
_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

author
#6 lore raw

Re: [PATCH v7 2/7] iommu/uapi: Add argsz for user filled data

In reply to Auger Eric
Quoted 7 lines · On Wed, 12 Aug 2020 18:59:14 +0200 Auger Eric <[email protected]> wrote:

Hi,

Quoted 3 lines · Jacob Pan

As IOMMU UAPI gets extended, user data size may increase. To support backward compatibiliy, this patch introduces a size field to each UAPI

s/compatibiliy/compatibility

will fix

Quoted 9 lines
Quoted 6 lines

data structures. It is *always* the responsibility for the user to fill in the correct size. Padding fields are adjusted to ensure 8 byte alignment.

Specific scenarios for user data handling are documented in:
Documentation/userspace-api/iommu.rst

you may mention the struct version does not need to be incremented as no IOCTL uses the structs yet.

Yes, good point. I also mentioned in the doc that:

"Version field is only reserved for the unlikely event of UAPI upgrade at its entirety."

Quoted 87 lines
Quoted 75 lines
---
 include/uapi/linux/iommu.h | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
include/uapi/linux/iommu.h +2 -0
index e907b7091a46..d5e9014f690e 100644
@@ -135,6 +135,7 @@ enum iommu_page_response_code {
 
 /**
  * struct iommu_page_response - Generic page response information
+ * @argsz: User filled size of this data
  * @version: API version of this structure
  * @flags: encodes whether the corresponding fields are valid
  *         (IOMMU_FAULT_PAGE_RESPONSE_* values)
@@ -143,6 +144,7 @@ enum iommu_page_response_code {
  * @code: response code from &enum iommu_page_response_code
  */
 struct iommu_page_response {
+	__u32	argsz;
 #define IOMMU_PAGE_RESP_VERSION_1	1
 	__u32	version;
 #define IOMMU_PAGE_RESP_PASID_VALID	(1 << 0)
@@ -218,6 +220,7 @@ struct iommu_inv_pasid_info {
 /**
  * struct iommu_cache_invalidate_info - First level/stage

invalidation
* information
+ * @argsz: User filled size of this data
* @version: API version of this structure
* @cache: bitfield that allows to select which caches to
invalidate
* @granularity: defines the lowest granularity used for the
invalidation: @@ -246,6 +249,7 @@ struct iommu_inv_pasid_info {
* must support the used granularity.
*/
struct iommu_cache_invalidate_info {

include/uapi/linux/iommu.h +2 -1
+	__u32	argsz;
 #define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
 	__u32	version;
 /* IOMMU paging structure cache */
@@ -255,7 +259,7 @@ struct iommu_cache_invalidate_info {
 #define IOMMU_CACHE_INV_TYPE_NR		(3)
 	__u8	cache;
 	__u8	granularity;
-	__u8	padding[2];
+	__u8	padding[6];
 	union {
 		struct iommu_inv_pasid_info pasid_info;
 		struct iommu_inv_addr_info addr_info;
@@ -292,6 +296,7 @@ struct iommu_gpasid_bind_data_vtd {
 
 /**
  * struct iommu_gpasid_bind_data - Information about device and

guest PASID binding
+ * @argsz: User filled size of this data
* @version: Version of this data structure
* @format: PASID table entry format
* @flags: Additional information on guest bind request

include/uapi/linux/iommu.h +2 -0
@@ -309,17 +314,18 @@ struct iommu_gpasid_bind_data_vtd {
  * PASID to host PASID based on this bind data.
  */
 struct iommu_gpasid_bind_data {
+	__u32 argsz;
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
 #define IOMMU_PASID_FORMAT_INTEL_VTD	1
 	__u32 format;
+	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid

include/uapi/linux/iommu.h struct iommu_gpasid_bind_data_vtd { · line 331

Quoted 10 lines
include/uapi/linux/iommu.h +1 -2
 */ __u64 flags;
 	__u64 gpgd;
 	__u64 hpasid;
 	__u64 gpasid;
-	__u32 addr_width;
-	__u8  padding[12];
+	__u8  padding[8];
 	/* Vendor specific data */
 	union {
 		struct iommu_gpasid_bind_data_vtd vtd;
Quoted 4 lines

Thanks

Eric

[Jacob Pan]

author
#12 lore raw

Re: [PATCH v7 5/7] iommu/uapi: Rename uapi functions

In reply to Auger Eric
Quoted 12 lines · On Thu, 13 Aug 2020 10:58:53 +0200 Auger Eric <[email protected]> wrote:

Hi Jacob,

Quoted 2 lines · Jacob Pan

User APIs such as iommu_sva_unbind_gpasid() may also be used by the kernel. Since we introduced user pointer to the UAPI functions,

Practically this is done in the next patch. What about something like:

We plan to have two flavors of the same API functions, one called through ioctls, carrying a user pointer and one called directly with valid IOMMU UAPI structs. To differentiate both, let's rename existing functions with an iommu_uapi_ prefix.

will do. Thanks!

Quoted 131 lines

Besides

Thanks

Eric

Quoted 124 lines

in-kernel callers cannot share the same APIs. In-kernel callers are also trusted, there is no need to validate the data.

This patch renames all UAPI functions with iommu_uapi_ prefix such that is clear to the intended callers.

---
 drivers/iommu/iommu.c | 18 +++++++++---------
 include/linux/iommu.h | 31 ++++++++++++++++---------------
 2 files changed, 25 insertions(+), 24 deletions(-)
drivers/iommu/iommu.c +2 -5
index b6858adc4f17..3a913ce94a3d 100644
@@ -1950,35 +1950,35 @@ int iommu_attach_device(struct iommu_domain
 *domain, struct device *dev) }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
-int iommu_cache_invalidate(struct iommu_domain *domain, struct
 device *dev,
-			   struct iommu_cache_invalidate_info
 *inv_info) +int iommu_uapi_cache_invalidate(struct iommu_domain
 *domain, struct device *dev,
+				struct iommu_cache_invalidate_info
 *inv_info) {
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
 	return domain->ops->cache_invalidate(domain, dev,
 inv_info); }
-EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-			   struct device *dev, struct

iommu_gpasid_bind_data *data) +int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,

drivers/iommu/iommu.c +1 -0
+			       struct device *dev, struct

iommu_gpasid_bind_data *data) {

drivers/iommu/iommu.c +1 -2
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_bind_gpasid(domain, dev, data);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct

device *dev,

drivers/iommu/iommu.c +1 -1
-			     ioasid_t pasid)
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,

struct device *dev,

drivers/iommu/iommu.c +2 -1
+				 ioasid_t pasid)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_unbind_gpasid(dev, pasid);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
include/linux/iommu.h +0 -3
index 5f0b7859d2eb..2dcc1a33f6dc 100644
@@ -430,13 +430,13 @@ extern int iommu_attach_device(struct
 iommu_domain *domain, struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_cache_invalidate(struct iommu_domain *domain,
-				  struct device *dev,
-				  struct

iommu_cache_invalidate_info *inv_info); -extern int iommu_sva_bind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +0 -1
-		struct device *dev, struct iommu_gpasid_bind_data

*data); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +0 -1
-				struct device *dev, ioasid_t

pasid); +extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,

include/linux/iommu.h +2 -0
+				       struct device *dev,
+				       struct

iommu_cache_invalidate_info *inv_info); +extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +1 -0
+				      struct device *dev, struct

iommu_gpasid_bind_data *data); +extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +1 -0
+					struct device *dev,

ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1054,21 +1054,22 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; }

include/linux/iommu.h +0 -4
-static inline int
-iommu_cache_invalidate(struct iommu_domain *domain,
-		       struct device *dev,
-		       struct iommu_cache_invalidate_info

*inv_info) +static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,

include/linux/iommu.h +2 -0
+					      struct device *dev,
+					      struct

iommu_cache_invalidate_info *inv_info) {

include/linux/iommu.h +0 -1
 	return -ENODEV;
 }
-static inline int iommu_sva_bind_gpasid(struct iommu_domain

*domain,

include/linux/iommu.h +0 -1
-				struct device *dev, struct

iommu_gpasid_bind_data *data) +
+static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +2 -0
+					     struct device *dev,
+					     struct

iommu_gpasid_bind_data *data) {
return -ENODEV;
}

Quoted 11 lines
Quoted 10 lines

-static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +0 -1
-					   struct device *dev, int

pasid) +static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,

include/linux/iommu.h +1 -0
+					       struct device *dev,

int pasid) {
return -ENODEV;
}

[Jacob Pan]

author
#21 lore raw

Re: [PATCH v7 7/7] iommu/vt-d: Check UAPI data processed by IOMMU core

In reply to Auger Eric
Quoted 38 lines · On Thu, 13 Aug 2020 11:19:46 +0200 Auger Eric <[email protected]> wrote:

Hi Jacob,

Quoted 35 lines · Jacob Pan

IOMMU generic layer already does sanity checks UAPI data for version match and argsz range under generic information.
Remove the redundant version check from VT-d driver and check for vendor specific data size.

---
 drivers/iommu/intel/iommu.c | 3 +--
 drivers/iommu/intel/svm.c   | 7 +++++--
 2 files changed, 6 insertions(+), 4 deletions(-)
(quoted diff) +0 -0

b/drivers/iommu/intel/iommu.c index 021f62078f52..7e03cca31a0e 100644 --- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c

drivers/iommu/intel/iommu.c +1 -2
@@ -5391,8 +5391,7 @@ intel_iommu_sva_invalidate(struct
 iommu_domain *domain, struct device *dev, int ret = 0;
 	u64 size = 0;
 
-	if (!inv_info || !dmar_domain ||
-	    inv_info->version !=
 IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+	if (!inv_info || !dmar_domain)
 		return -EINVAL;
 
drivers/iommu/intel/iommu.c +0 -0
 	if (!dev || !dev_is_pci(dev))
drivers/iommu/intel/svm.c +0 -0
index 713b3a218483..55ea11e9c0f5 100644
@@ -240,8 +240,11 @@ int intel_svm_bind_gpasid(struct iommu_domain
 *domain, struct device *dev, if (WARN_ON(!iommu) || !data)
 		return -EINVAL;
 
Quoted 12 lines
Quoted 9 lines
drivers/iommu/intel/svm.c +4 -2
-	if (data->version != IOMMU_GPASID_BIND_VERSION_1 ||
-	    data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+	if (data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+		return -EINVAL;
+
+	/* IOMMU core ensures argsz is more than the start of the

union */

drivers/iommu/intel/svm.c +1 -0
+	if (data->argsz < offsetofend(struct

iommu_gpasid_bind_data, vendor.vtd)) return -EINVAL;

Shouldn't you test the vendor flags here? intel_pasid_setup_bind_data() only checks valid ones but not ~mask.

Yes, vendor flags should be tested to make sure there is no undefined flags being used.

Thanks!

Quoted 7 lines

Thanks

Eric

Quoted 3 lines

if (!dev_is_pci(dev))

[Jacob Pan]