Skip to contentSkip to conversation

iommu: SVA and IOPF refactoring

PATCH Superseded Lu Baolu 5 participants 50 messages May 19, 2022 – Jun 2, 2022

Subsystems (8)

v7 of 14 Superseded Latest is v14 →

lore
Share & tools
lore

Lu Baolu

author maintainer
#0 lore raw

v7 cover iommu: SVA and IOPF refactoring

Hi folks,

The former part of this series refactors the IOMMU SVA code by assigning an SVA type of iommu_domain to a shared virtual address and replacing sva_bind/unbind iommu ops with attach/detach_dev_pasid domain ops.

The latter part changes the existing I/O page fault handling framework from only serving SVA to a generic one. Any driver or component could handle the I/O page faults for its domain in its own way by installing an I/O page fault handler.

This series has been functionally tested on an x86 machine and compile tested for other architectures.

This series is also available on github:
[2] https://github.com/LuBaolu/intel-iommu/commits/iommu-sva-refactoring-v7

Please review and suggest.

Best regards,
baolu

Change log:
v7:
- Remove duplicate array for sva domain.
- Rename detach_dev_pasid to block_dev_pasid.
- Add raw device driver interfaces for iommufd.
- Other misc refinements and patch reorganization.
- Drop "dmaengine: idxd: Separate user and kernel pasid enabling" which has been picked for dmaengine tree.

v6:
- https://lore.kernel.org/linux-iommu/[email protected]/
- Refine the SVA basic data structures.

- Refine arm smmuv3 sva domain allocation.
- Fix a possible lock issue.

v5:
- https://lore.kernel.org/linux-iommu/[email protected]/
- Address review comments from Jean-Philippe Brucker. Very appreciated!
- Remove redundant pci aliases check in device_group_immutable_singleton().
- Treat all buses exept PCI as static in immutable singleton check.
- As the sva_bind/unbind() have already guaranteed sva domain free only after iopf_queue_flush_dev(), remove the unnecessary domain refcount.
- Move domain get() out of the list iteration in iopf_handle_group().

v4:
- https://lore.kernel.org/linux-iommu/[email protected]/
- Solve the overlap with another series and make this series self-contained.
- No objection to the abstraction of data structure during v3 review. Hence remove the RFC subject prefix.
- Refine the immutable singleton group code according to Kevin's
comments.

v3:
- https://lore.kernel.org/linux-iommu/[email protected]/
- Rework iommu_group_singleton_lockdown() by adding a flag to the group that positively indicates the group can never have more than one member, even after hot plug.
- Abstract the data structs used for iommu sva in a separated patches to make it easier for review.
- I still keep the RFC prefix in this series as above two significant changes need at least another round review to be finalized.
- Several misc refinements.

v2:
- https://lore.kernel.org/linux-iommu/[email protected]/
- Add sva domain life cycle management to avoid race between unbind and page fault handling.
- Use a single domain for each mm.
- Return a single sva handler for the same binding.
- Add a new helper to meet singleton group requirement.
- Rework the SVA domain allocation for arm smmu v3 driver and move the pasid_bit initialization to device probe.
- Drop the patch "iommu: Handle IO page faults directly".
- Add mmget_not_zero(mm) in SVA page fault handler.

v1:
- https://lore.kernel.org/linux-iommu/[email protected]/
- Initial post.

Lu Baolu (10):
iommu: Add pasids field in struct iommu_device
iommu: Remove SVM_FLAG_SUPERVISOR_MODE support iommu/sva: Add iommu_sva_domain support iommu/vt-d: Add SVA domain support arm-smmu-v3/sva: Add SVA domain support iommu/sva: Refactoring iommu_sva_bind/unbind_device()
iommu: Remove SVA related callbacks from iommu ops
iommu: Prepare IOMMU domain for IOPF
iommu: Per-domain I/O page fault handling
iommu: Rename iommu-sva-lib.{c,h}

 include/linux/intel-iommu.h                   |   8 +-
 include/linux/intel-svm.h                     |  13 -
 include/linux/iommu.h                         | 113 +++++--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  21 +-
 .../iommu/{iommu-sva-lib.h => iommu-sva.h}    |  16 +
 drivers/dma/idxd/cdev.c                       |   2 +-
 drivers/dma/idxd/init.c                       |  24 +-
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  89 +++---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   |  12 +-
 drivers/iommu/intel/dmar.c                    |   4 +
 drivers/iommu/intel/iommu.c                   |   9 +-
 drivers/iommu/intel/svm.c                     | 135 +++-----
 drivers/iommu/io-pgfault.c                    |  73 +----
 drivers/iommu/iommu-sva-lib.c                 |  71 -----
 drivers/iommu/iommu-sva.c                     | 297 ++++++++++++++++++
 drivers/iommu/iommu.c                         | 191 +++++------
 drivers/misc/uacce/uacce.c                    |   2 +-
 drivers/iommu/Makefile                        |   2 +-
 18 files changed, 629 insertions(+), 453 deletions(-)
 rename drivers/iommu/{iommu-sva-lib.h => iommu-sva.h} (80%)
 delete mode 100644 drivers/iommu/iommu-sva-lib.c
 create mode 100644 drivers/iommu/iommu-sva.c
Signature · 6 lines
2.25.1

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

PATCH v7 1/10 iommu: Add pasids field in struct iommu_device

Use this field to keep the number of supported PASIDs that an IOMMU hardware is able to support. This is a generic attribute of an IOMMU and lifting it into the per-IOMMU device structure makes it possible to allocate a PASID for device without calls into the IOMMU drivers. Any iommu driver which suports PASID related features should set this field before enabling them on the devices.

---
 include/linux/iommu.h                       | 2 ++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 +
 drivers/iommu/intel/dmar.c                  | 4 ++++
 3 files changed, 7 insertions(+)
include/linux/iommu.h +2 -0
index 5e1afe169549..da423e87f248 100644
@@ -318,12 +318,14 @@ struct iommu_domain_ops {
  * @list: Used by the iommu-core to keep a list of registered iommus
  * @ops: iommu-ops for talking to this iommu
  * @dev: struct device for sysfs handling
+ * @pasids: number of supported PASIDs
  */
 struct iommu_device {
 	struct list_head list;
 	const struct iommu_ops *ops;
 	struct fwnode_handle *fwnode;
 	struct device *dev;
+	u32 pasids;
 };
 
 /**
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +1 -0
index 88817a3376ef..6e2cd082c670 100644
@@ -3546,6 +3546,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	/* SID/SSID sizes */
 	smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
 	smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
+	smmu->iommu.pasids = smmu->ssid_bits;
 
 	/*
 	 * If the SMMU supports fewer bits than would fill a single L2 stream
drivers/iommu/intel/dmar.c +4 -0
index 4de960834a1b..1c3cf267934d 100644
@@ -1126,6 +1126,10 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 	raw_spin_lock_init(&iommu->register_lock);
 
+	/* Supports full 20-bit PASID in scalable mode. */
+	if (ecap_pasid(iommu->ecap))
+		iommu->iommu.pasids = 1UL << 20;
+
 	/*
 	 * This is only for hotplug; at boot time intel_iommu_enabled won't
 	 * be set yet. When intel_iommu_init() runs, it registers the units
Signature · 6 lines
2.25.1

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

PATCH v7 2/10 iommu: Remove SVM_FLAG_SUPERVISOR_MODE support

In reply to Lu Baolu

The current kernel DMA with PASID support is based on the SVA with a flag SVM_FLAG_SUPERVISOR_MODE. The IOMMU driver binds the kernel memory address space to a PASID of the device. The device driver programs the device with kernel virtual address (KVA) for DMA access. There have been security and functional issues with this approach:

- The lack of IOTLB synchronization upon kernel page table updates. (vmalloc, module/BPF loading, CONFIG_DEBUG_PAGEALLOC etc.)
- Other than slight more protection, using kernel virtual address (KVA) has little advantage over physical address. There are also no use cases yet where DMA engines need kernel virtual addresses for in-kernel DMA.

This removes SVM_FLAG_SUPERVISOR_MODE support from the IOMMU interface. The device drivers are suggested to handle kernel DMA with PASID through the kernel DMA APIs.

The drvdata parameter in iommu_sva_bind_device() and all callbacks is not needed anymore. Cleanup them as well.

---
 include/linux/intel-iommu.h                   |  3 +-
 include/linux/intel-svm.h                     | 13 -----
 include/linux/iommu.h                         |  8 +--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  5 +-
 drivers/dma/idxd/cdev.c                       |  2 +-
 drivers/dma/idxd/init.c                       | 24 +-------
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  3 +-
 drivers/iommu/intel/svm.c                     | 57 +++++--------------
 drivers/iommu/iommu.c                         |  5 +-
 drivers/misc/uacce/uacce.c                    |  2 +-
 10 files changed, 26 insertions(+), 96 deletions(-)
include/linux/intel-iommu.h +1 -2
index 4f29139bbfc3..df23300cfa88 100644
@@ -739,8 +739,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
-				 void *drvdata);
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm);
 void intel_svm_unbind(struct iommu_sva *handle);
 u32 intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
include/linux/intel-svm.h +0 -13
index 207ef06ba3e1..f9a0d44f6fdb 100644
@@ -13,17 +13,4 @@
 #define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
 #define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
 
-/*
- * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only
- * for access to kernel addresses. No IOTLB flushes are automatically done
- * for kernel mappings; it is valid only for access to the kernel's static
- * 1:1 mapping of physical memory — not to vmalloc or even module mappings.
- * A future API addition may permit the use of such ranges, by means of an
- * explicit IOTLB flush call (akin to the DMA API's unmap method).
- *
- * It is unlikely that we will ever hook into flush_tlb_kernel_range() to
- * do such IOTLB flushes automatically.
- */
-#define SVM_FLAG_SUPERVISOR_MODE	BIT(0)
-
 #endif /* __INTEL_SVM_H__ */
include/linux/iommu.h +3 -5
index da423e87f248..0c358b7c583b 100644
@@ -243,8 +243,7 @@ struct iommu_ops {
 	int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f);
 	int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f);
 
-	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm,
-				      void *drvdata);
+	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm);
 	void (*sva_unbind)(struct iommu_sva *handle);
 	u32 (*sva_get_pasid)(struct iommu_sva *handle);
 
@@ -667,8 +666,7 @@ int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f);
 bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f);
 
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
-					struct mm_struct *mm,
-					void *drvdata);
+					struct mm_struct *mm);
 void iommu_sva_unbind_device(struct iommu_sva *handle);
 u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 
@@ -1010,7 +1008,7 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 }
 
 static inline struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
 	return NULL;
 }
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +2 -3
index cd48590ada30..d2ba86470c42 100644
@@ -754,8 +754,7 @@ bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
 bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master);
-struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm,
-				    void *drvdata);
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm);
 void arm_smmu_sva_unbind(struct iommu_sva *handle);
 u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);
 void arm_smmu_sva_notifier_synchronize(void);
@@ -791,7 +790,7 @@ static inline bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master
 }
 
 static inline struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 {
 	return ERR_PTR(-ENODEV);
 }
drivers/dma/idxd/cdev.c +1 -1
index b9b2b4a4124e..312ec37ebf91 100644
@@ -100,7 +100,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 	filp->private_data = ctx;
 
 	if (device_pasid_enabled(idxd)) {
-		sva = iommu_sva_bind_device(dev, current->mm, NULL);
+		sva = iommu_sva_bind_device(dev, current->mm);
 		if (IS_ERR(sva)) {
 			rc = PTR_ERR(sva);
 			dev_err(dev, "pasid allocation failed: %d\n", rc);
drivers/dma/idxd/init.c +1 -23
index 993a5dcca24f..1fd80c63248a 100644
@@ -466,29 +466,7 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d
 
 static int idxd_enable_system_pasid(struct idxd_device *idxd)
 {
-	int flags;
-	unsigned int pasid;
-	struct iommu_sva *sva;
-
-	flags = SVM_FLAG_SUPERVISOR_MODE;
-
-	sva = iommu_sva_bind_device(&idxd->pdev->dev, NULL, &flags);
-	if (IS_ERR(sva)) {
-		dev_warn(&idxd->pdev->dev,
-			 "iommu sva bind failed: %ld\n", PTR_ERR(sva));
-		return PTR_ERR(sva);
-	}
-
-	pasid = iommu_sva_get_pasid(sva);
-	if (pasid == IOMMU_PASID_INVALID) {
-		iommu_sva_unbind_device(sva);
-		return -ENODEV;
-	}
-
-	idxd->sva = sva;
-	idxd->pasid = pasid;
-	dev_dbg(&idxd->pdev->dev, "system pasid: %u\n", pasid);
-	return 0;
+	return -EOPNOTSUPP;
 }
 
 static void idxd_disable_system_pasid(struct idxd_device *idxd)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +1 -2
index 1ef7bbb4acf3..f155d406c5d5 100644
@@ -367,8 +367,7 @@ __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 	return ERR_PTR(ret);
 }
 
-struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 {
 	struct iommu_sva *handle;
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
drivers/iommu/intel/svm.c +14 -43

116 lines not on this page · raw message

drivers/iommu/iommu.c +2 -3
index 847ad47a2dfd..9955f58bd08c 100644
@@ -2768,7 +2768,6 @@ EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
  * iommu_sva_bind_device() - Bind a process address space to a device
  * @dev: the device
  * @mm: the mm to bind, caller must hold a reference to it
- * @drvdata: opaque data pointer to pass to bind callback
  *
  * Create a bond between device and address space, allowing the device to access
  * the mm using the returned PASID. If a bond already exists between @device and
@@ -2781,7 +2780,7 @@ EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
  * On error, returns an ERR_PTR value.
  */
 struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
 	struct iommu_group *group;
 	struct iommu_sva *handle = ERR_PTR(-EINVAL);
@@ -2806,7 +2805,7 @@ iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
 	if (iommu_group_device_count(group) != 1)
 		goto out_unlock;
 
-	handle = ops->sva_bind(dev, mm, drvdata);
+	handle = ops->sva_bind(dev, mm);
 
 out_unlock:
 	mutex_unlock(&group->mutex);
drivers/misc/uacce/uacce.c +1 -1
index 281c54003edc..3238a867ea51 100644
@@ -99,7 +99,7 @@ static int uacce_bind_queue(struct uacce_device *uacce, struct uacce_queue *q)
 	if (!(uacce->flags & UACCE_DEV_SVA))
 		return 0;
 
-	handle = iommu_sva_bind_device(uacce->parent, current->mm, NULL);
+	handle = iommu_sva_bind_device(uacce->parent, current->mm);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
Signature · 6 lines
2.25.1

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

PATCH v7 3/10 iommu/sva: Add iommu_sva_domain support

In reply to Lu Baolu

The iommu_sva_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

---
 include/linux/iommu.h         | 51 +++++++++++++++++++++++++
 drivers/iommu/iommu-sva-lib.h | 15 ++++++++
 drivers/iommu/iommu-sva-lib.c | 48 +++++++++++++++++++++++
 drivers/iommu/iommu.c         | 71 +++++++++++++++++++++++++++++++++++
 4 files changed, 185 insertions(+)
include/linux/iommu.h +51 -0
index 0c358b7c583b..e8cf82d46ce1 100644
@@ -64,6 +64,9 @@ struct iommu_domain_geometry {
 #define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
 #define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
 
+#define __IOMMU_DOMAIN_SHARED	(1U << 4)  /* Page table shared from CPU  */
+#define __IOMMU_DOMAIN_HOST_VA	(1U << 5)  /* Host CPU virtual address */
+
 /*
  * This are the possible domain-types
  *
@@ -86,6 +89,8 @@ struct iommu_domain_geometry {
 #define IOMMU_DOMAIN_DMA_FQ	(__IOMMU_DOMAIN_PAGING |	\
 				 __IOMMU_DOMAIN_DMA_API |	\
 				 __IOMMU_DOMAIN_DMA_FQ)
+#define IOMMU_DOMAIN_SVA	(__IOMMU_DOMAIN_SHARED |	\
+				 __IOMMU_DOMAIN_HOST_VA)
 
 struct iommu_domain {
 	unsigned type;
@@ -254,6 +259,7 @@ struct iommu_ops {
 	int (*def_domain_type)(struct device *dev);
 
 	const struct iommu_domain_ops *default_domain_ops;
+	const struct iommu_domain_ops *sva_domain_ops;
 	unsigned long pgsize_bitmap;
 	struct module *owner;
 };
@@ -262,6 +268,8 @@ struct iommu_ops {
  * struct iommu_domain_ops - domain specific operations
  * @attach_dev: attach an iommu domain to a device
  * @detach_dev: detach an iommu domain from a device
+ * @set_dev_pasid: set an iommu domain to a pasid of device
+ * @block_dev_pasid: block pasid of device from using iommu domain
  * @map: map a physically contiguous memory region to an iommu domain
  * @map_pages: map a physically contiguous set of pages of the same size to
  *             an iommu domain.
@@ -282,6 +290,10 @@ struct iommu_ops {
 struct iommu_domain_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
+	int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid);
+	void (*block_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+				ioasid_t pasid);
 
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
@@ -677,6 +689,10 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
 void iommu_group_release_dma_owner(struct iommu_group *group);
 bool iommu_group_dma_owner_claimed(struct iommu_group *group);
 
+int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
+			   ioasid_t pasid);
+void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
+			      ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1050,6 +1066,17 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
 {
 	return false;
 }
+
+static inline int iommu_set_device_pasid(struct iommu_domain *domain,
+					 struct device *dev, ioasid_t pasid)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_block_device_pasid(struct iommu_domain *domain,
+					    struct device *dev, ioasid_t pasid)
+{
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**
@@ -1075,4 +1102,28 @@ void iommu_debugfs_setup(void);
 static inline void iommu_debugfs_setup(void) {}
 #endif
 
+#ifdef CONFIG_IOMMU_SVA
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm);
+void iommu_sva_free_domain(struct iommu_domain *domain);
+int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
+			 ioasid_t pasid);
+#else /* CONFIG_IOMMU_SVA */
+static inline struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline void iommu_sva_free_domain(struct iommu_domain *domain)
+{
+}
+
+static inline int iommu_sva_set_domain(struct iommu_domain *domain,
+				       struct device *dev, ioasid_t pasid)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_IOMMU_SVA */
+
 #endif /* __LINUX_IOMMU_H */
drivers/iommu/iommu-sva-lib.h +15 -0
index 8909ea1094e3..1be21e6b93ec 100644
@@ -7,6 +7,7 @@
 
 #include <linux/ioasid.h>
 #include <linux/mm_types.h>
+#include <linux/iommu.h>
 
 int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
 struct mm_struct *iommu_sva_find(ioasid_t pasid);
@@ -16,6 +17,20 @@ struct device;
 struct iommu_fault;
 struct iopf_queue;
 
+struct iommu_sva_domain {
+	struct iommu_domain	domain;
+	struct mm_struct	*mm;
+};
+
+#define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)
+
+static inline struct mm_struct *domain_to_mm(struct iommu_domain *domain)
+{
+	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
+
+	return sva_domain->mm;
+}
+
 #ifdef CONFIG_IOMMU_SVA
 int iommu_queue_iopf(struct iommu_fault *fault, void *cookie);
 
drivers/iommu/iommu-sva-lib.c +48 -0

51 lines not on this page · raw message

drivers/iommu/iommu.c +71 -0

86 lines not on this page · raw message

Signature · 6 lines
2.25.1

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

PATCH v7 4/10 iommu/vt-d: Add SVA domain support

In reply to Lu Baolu

Add support for domain ops callbacks for an SVA domain.

---
 include/linux/intel-iommu.h |  4 ++++
 drivers/iommu/intel/iommu.c |  4 ++++
 drivers/iommu/intel/svm.c   | 37 ++++++++++++++++++++++++++++++++-----
 3 files changed, 40 insertions(+), 5 deletions(-)
include/linux/intel-iommu.h +4 -0
index df23300cfa88..5e88eaa245aa 100644
@@ -744,6 +744,10 @@ void intel_svm_unbind(struct iommu_sva *handle);
 u32 intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg);
+int intel_svm_attach_dev_pasid(struct iommu_domain *domain,
+			       struct device *dev, ioasid_t pasid);
+void intel_svm_detach_dev_pasid(struct iommu_domain *domain,
+				struct device *dev, ioasid_t pasid);
 
 struct intel_svm_dev {
 	struct list_head list;
drivers/iommu/intel/iommu.c +4 -0
index e56b3a4b6998..2b6a52c87c73 100644
@@ -4923,6 +4923,10 @@ const struct iommu_ops intel_iommu_ops = {
 	.sva_unbind		= intel_svm_unbind,
 	.sva_get_pasid		= intel_svm_get_pasid,
 	.page_response		= intel_svm_page_response,
+	.sva_domain_ops = &(const struct iommu_domain_ops) {
+		.set_dev_pasid		= intel_svm_attach_dev_pasid,
+		.block_dev_pasid	= intel_svm_detach_dev_pasid,
+	},
 #endif
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= intel_iommu_attach_device,
drivers/iommu/intel/svm.c +32 -5
index d04880a291c3..d575792441f3 100644
@@ -323,6 +323,7 @@ static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm)
 
 static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 					   struct device *dev,
+					   ioasid_t pasid,
 					   struct mm_struct *mm)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
@@ -331,13 +332,13 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	struct intel_svm *svm;
 	int ret = 0;
 
-	svm = pasid_private_find(mm->pasid);
+	svm = pasid_private_find(pasid);
 	if (!svm) {
 		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
 		if (!svm)
 			return ERR_PTR(-ENOMEM);
 
-		svm->pasid = mm->pasid;
+		svm->pasid = pasid;
 		svm->mm = mm;
 		INIT_LIST_HEAD_RCU(&svm->devs);
 
@@ -387,7 +388,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
 	spin_lock_irqsave(&iommu->lock, iflags);
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	spin_unlock_irqrestore(&iommu->lock, iflags);
 
@@ -403,7 +404,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 free_svm:
 	if (list_empty(&svm->devs)) {
 		mmu_notifier_unregister(&svm->notifier, mm);
-		pasid_private_remove(mm->pasid);
+		pasid_private_remove(pasid);
 		kfree(svm);
 	}
 
@@ -822,7 +823,7 @@ struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm)
 		return ERR_PTR(ret);
 	}
 
-	sva = intel_svm_bind_mm(iommu, dev, mm);
+	sva = intel_svm_bind_mm(iommu, dev, mm->pasid, mm);
 	mutex_unlock(&pasid_mutex);
 
 	return sva;
@@ -931,3 +932,29 @@ int intel_svm_page_response(struct device *dev,
 	mutex_unlock(&pasid_mutex);
 	return ret;
 }
+
+int intel_svm_attach_dev_pasid(struct iommu_domain *domain,
+			       struct device *dev, ioasid_t pasid)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct mm_struct *mm = domain_to_mm(domain);
+	struct intel_iommu *iommu = info->iommu;
+	struct iommu_sva *sva;
+	int ret = 0;
+
+	mutex_lock(&pasid_mutex);
+	sva = intel_svm_bind_mm(iommu, dev, pasid, mm);
+	if (IS_ERR(sva))
+		ret = PTR_ERR(sva);
+	mutex_unlock(&pasid_mutex);
+
+	return ret;
+}
+
+void intel_svm_detach_dev_pasid(struct iommu_domain *domain,
+				struct device *dev, ioasid_t pasid)
+{
+	mutex_lock(&pasid_mutex);
+	intel_svm_unbind_mm(dev, pasid);
+	mutex_unlock(&pasid_mutex);
+}
Signature · 6 lines
2.25.1

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

PATCH v7 5/10 arm-smmu-v3/sva: Add SVA domain support

In reply to Lu Baolu

Add support for domain ops callbacks for an SVA domain.

---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  4 ++
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   | 46 +++++++++++++++++++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   |  6 +++
 3 files changed, 56 insertions(+)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +4 -0
index d2ba86470c42..ec77f6a51ff9 100644
@@ -758,6 +758,10 @@ struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm);
 void arm_smmu_sva_unbind(struct iommu_sva *handle);
 u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);
 void arm_smmu_sva_notifier_synchronize(void);
+int arm_smmu_sva_attach_dev_pasid(struct iommu_domain *domain,
+				  struct device *dev, ioasid_t id);
+void arm_smmu_sva_detach_dev_pasid(struct iommu_domain *domain,
+				   struct device *dev, ioasid_t id);
 #else /* CONFIG_ARM_SMMU_V3_SVA */
 static inline bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 {
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +46 -0

49 lines not on this page · raw message

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +6 -0
index 6e2cd082c670..4ad3ca70cf89 100644
@@ -2858,6 +2858,12 @@ static struct iommu_ops arm_smmu_ops = {
 	.page_response		= arm_smmu_page_response,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 	.owner			= THIS_MODULE,
+#ifdef CONFIG_ARM_SMMU_V3_SVA
+	.sva_domain_ops = &(const struct iommu_domain_ops) {
+		.set_dev_pasid		= arm_smmu_sva_attach_dev_pasid,
+		.block_dev_pasid	= arm_smmu_sva_detach_dev_pasid,
+	},
+#endif
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= arm_smmu_attach_dev,
 		.map_pages		= arm_smmu_map_pages,
Signature · 6 lines
2.25.1

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

PATCH v7 6/10 iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Lu Baolu

The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need for any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops.

This refactors the IOMMU SVA interfaces implementation by using the set/block_pasid_dev ops and align them with the concept of the SVA iommu domain. Put the new SVA code in the sva related file in order to make it self-contained.

---
 include/linux/iommu.h         |  48 ++++++++------
 drivers/iommu/iommu-sva-lib.h |   1 +
 drivers/iommu/iommu-sva-lib.c | 113 ++++++++++++++++++++++++++++++++
 drivers/iommu/iommu.c         | 119 ++++++++--------------------------
 4 files changed, 170 insertions(+), 111 deletions(-)
include/linux/iommu.h +28 -20
index e8cf82d46ce1..d9ac5ebe5bbb 100644
@@ -635,6 +635,7 @@ struct iommu_fwspec {
  */
 struct iommu_sva {
 	struct device			*dev;
+	refcount_t			users;
 };
 
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
@@ -677,11 +678,6 @@ int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f);
 bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f);
 
-struct iommu_sva *iommu_sva_bind_device(struct device *dev,
-					struct mm_struct *mm);
-void iommu_sva_unbind_device(struct iommu_sva *handle);
-u32 iommu_sva_get_pasid(struct iommu_sva *handle);
-
 int iommu_device_use_default_domain(struct device *dev);
 void iommu_device_unuse_default_domain(struct device *dev);
 
@@ -693,6 +689,8 @@ int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
 			   ioasid_t pasid);
 void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
 			      ioasid_t pasid);
+struct iommu_domain *
+iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1023,21 +1021,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 	return -ENODEV;
 }
 
-static inline struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
-{
-	return NULL;
-}
-
-static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
-{
-}
-
-static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
-{
-	return IOMMU_PASID_INVALID;
-}
-
 static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
 {
 	return NULL;
@@ -1077,6 +1060,12 @@ static inline void iommu_block_device_pasid(struct iommu_domain *domain,
 					    struct device *dev, ioasid_t pasid)
 {
 }
+
+static inline struct iommu_domain *
+iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid)
+{
+	return NULL;
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**
@@ -1108,6 +1097,10 @@ iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm);
 void iommu_sva_free_domain(struct iommu_domain *domain);
 int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
 			 ioasid_t pasid);
+struct iommu_sva *iommu_sva_bind_device(struct device *dev,
+					struct mm_struct *mm);
+void iommu_sva_unbind_device(struct iommu_sva *handle);
+u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 #else /* CONFIG_IOMMU_SVA */
 static inline struct iommu_domain *
 iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
@@ -1124,6 +1117,21 @@ static inline int iommu_sva_set_domain(struct iommu_domain *domain,
 {
 	return -EINVAL;
 }
+
+static inline struct iommu_sva *
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
+{
+	return NULL;
+}
+
+static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
+{
+}
+
+static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
+{
+	return IOMMU_PASID_INVALID;
+}
 #endif /* CONFIG_IOMMU_SVA */
 
 #endif /* __LINUX_IOMMU_H */
drivers/iommu/iommu-sva-lib.h +1 -0
index 1be21e6b93ec..ebab5a8cb126 100644
@@ -20,6 +20,7 @@ struct iopf_queue;
 struct iommu_sva_domain {
 	struct iommu_domain	domain;
 	struct mm_struct	*mm;
+	struct iommu_sva	bond;
 };
 
 #define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)
drivers/iommu/iommu-sva-lib.c +113 -0

122 lines not on this page · raw message

drivers/iommu/iommu.c +28 -91

128 lines not on this page · raw message

Signature · 6 lines
2.25.1

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

PATCH v7 7/10 iommu: Remove SVA related callbacks from iommu ops

In reply to Lu Baolu

These ops'es have been replaced with the dev_attach/detach_pasid domain ops'es. There's no need for them anymore. Remove them to avoid dead code.

---
 include/linux/intel-iommu.h                   |  3 --
 include/linux/iommu.h                         |  7 ---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   | 16 ------
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   | 40 ---------------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   |  3 --
 drivers/iommu/intel/iommu.c                   |  3 --
 drivers/iommu/intel/svm.c                     | 49 -------------------
 7 files changed, 121 deletions(-)
include/linux/intel-iommu.h +0 -3
index 5e88eaa245aa..536f229fd274 100644
@@ -739,9 +739,6 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm);
-void intel_svm_unbind(struct iommu_sva *handle);
-u32 intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg);
 int intel_svm_attach_dev_pasid(struct iommu_domain *domain,
include/linux/iommu.h +0 -7
index d9ac5ebe5bbb..e4ce2fe0e144 100644
@@ -212,9 +212,6 @@ struct iommu_iotlb_gather {
  * @dev_has/enable/disable_feat: per device entries to check/enable/disable
  *                               iommu specific features.
  * @dev_feat_enabled: check enabled feature
- * @sva_bind: Bind process address space to device
- * @sva_unbind: Unbind process address space from device
- * @sva_get_pasid: Get PASID associated to a SVA handle
  * @page_response: handle page request response
  * @def_domain_type: device default domain type, return value:
  *		- IOMMU_DOMAIN_IDENTITY: must use an identity domain
@@ -248,10 +245,6 @@ struct iommu_ops {
 	int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f);
 	int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f);
 
-	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm);
-	void (*sva_unbind)(struct iommu_sva *handle);
-	u32 (*sva_get_pasid)(struct iommu_sva *handle);
-
 	int (*page_response)(struct device *dev,
 			     struct iommu_fault_event *evt,
 			     struct iommu_page_response *msg);
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +0 -16
index ec77f6a51ff9..0f0f5ba26dd5 100644
@@ -754,9 +754,6 @@ bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
 bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master);
-struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm);
-void arm_smmu_sva_unbind(struct iommu_sva *handle);
-u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);
 void arm_smmu_sva_notifier_synchronize(void);
 int arm_smmu_sva_attach_dev_pasid(struct iommu_domain *domain,
 				  struct device *dev, ioasid_t id);
@@ -793,19 +790,6 @@ static inline bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master
 	return false;
 }
 
-static inline struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
-{
-	return ERR_PTR(-ENODEV);
-}
-
-static inline void arm_smmu_sva_unbind(struct iommu_sva *handle) {}
-
-static inline u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
-{
-	return IOMMU_PASID_INVALID;
-}
-
 static inline void arm_smmu_sva_notifier_synchronize(void) {}
 #endif /* CONFIG_ARM_SMMU_V3_SVA */
 #endif /* _ARM_SMMU_V3_H */
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +0 -40
index 6969974ca89e..8290d66569f3 100644
@@ -344,11 +344,6 @@ __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 	if (!bond)
 		return ERR_PTR(-ENOMEM);
 
-	/* Allocate a PASID for this mm if necessary */
-	ret = iommu_sva_alloc_pasid(mm, 1, (1U << master->ssid_bits) - 1);
-	if (ret)
-		goto err_free_bond;
-
 	bond->mm = mm;
 	bond->sva.dev = dev;
 	refcount_set(&bond->refs, 1);
@@ -367,41 +362,6 @@ __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 	return ERR_PTR(ret);
 }
 
-struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
-{
-	struct iommu_sva *handle;
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
-
-	if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1)
-		return ERR_PTR(-EINVAL);
-
-	mutex_lock(&sva_lock);
-	handle = __arm_smmu_sva_bind(dev, mm);
-	mutex_unlock(&sva_lock);
-	return handle;
-}
-
-void arm_smmu_sva_unbind(struct iommu_sva *handle)
-{
-	struct arm_smmu_bond *bond = sva_to_bond(handle);
-
-	mutex_lock(&sva_lock);
-	if (refcount_dec_and_test(&bond->refs)) {
-		list_del(&bond->list);
-		arm_smmu_mmu_notifier_put(bond->smmu_mn);
-		kfree(bond);
-	}
-	mutex_unlock(&sva_lock);
-}
-
-u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
-{
-	struct arm_smmu_bond *bond = sva_to_bond(handle);
-
-	return bond->mm->pasid;
-}
-
 bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 {
 	unsigned long reg, fld;
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +0 -3
index 4ad3ca70cf89..b74f8964cc13 100644
@@ -2852,9 +2852,6 @@ static struct iommu_ops arm_smmu_ops = {
 	.dev_feat_enabled	= arm_smmu_dev_feature_enabled,
 	.dev_enable_feat	= arm_smmu_dev_enable_feature,
 	.dev_disable_feat	= arm_smmu_dev_disable_feature,
-	.sva_bind		= arm_smmu_sva_bind,
-	.sva_unbind		= arm_smmu_sva_unbind,
-	.sva_get_pasid		= arm_smmu_sva_get_pasid,
 	.page_response		= arm_smmu_page_response,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 	.owner			= THIS_MODULE,
drivers/iommu/intel/iommu.c +0 -3
index 2b6a52c87c73..10e07d59d4c8 100644
@@ -4919,9 +4919,6 @@ const struct iommu_ops intel_iommu_ops = {
 	.def_domain_type	= device_def_domain_type,
 	.pgsize_bitmap		= SZ_4K,
 #ifdef CONFIG_INTEL_IOMMU_SVM
-	.sva_bind		= intel_svm_bind,
-	.sva_unbind		= intel_svm_unbind,
-	.sva_get_pasid		= intel_svm_get_pasid,
 	.page_response		= intel_svm_page_response,
 	.sva_domain_ops = &(const struct iommu_domain_ops) {
 		.set_dev_pasid		= intel_svm_attach_dev_pasid,
drivers/iommu/intel/svm.c +0 -49

61 lines not on this page · raw message

Signature · 6 lines
2.25.1

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

PATCH v7 8/10 iommu: Prepare IOMMU domain for IOPF

In reply to Lu Baolu

This adds some mechanisms around the iommu_domain so that the I/O page fault handling framework could route a page fault to the domain and call the fault handler from it.

Add pointers to the page fault handler and its private data in struct iommu_domain. The fault handler will be called with the private data as a parameter once a page fault is routed to the domain. Any kernel component which owns an iommu domain could install handler and its private parameter so that the page fault could be further routed and handled.

This also prepares the SVA implementation to be the first consumer of the per-domain page fault handling model.

---
 include/linux/iommu.h         |  3 ++
 drivers/iommu/io-pgfault.c    |  7 ++++
 drivers/iommu/iommu-sva-lib.c | 65 +++++++++++++++++++++++++++++++++++
 3 files changed, 75 insertions(+)
include/linux/iommu.h +3 -0
index e4ce2fe0e144..45f274b2640d 100644
@@ -100,6 +100,9 @@ struct iommu_domain {
 	void *handler_token;
 	struct iommu_domain_geometry geometry;
 	struct iommu_dma_cookie *iova_cookie;
+	enum iommu_page_response_code (*iopf_handler)(struct iommu_fault *fault,
+						      void *data);
+	void *fault_data;
 };
 
 static inline bool iommu_is_dma_domain(struct iommu_domain *domain)
drivers/iommu/io-pgfault.c +7 -0
index 1df8c1dcae77..aee9e033012f 100644
@@ -181,6 +181,13 @@ static void iopf_handle_group(struct work_struct *work)
  * request completes, outstanding faults will have been dealt with by the time
  * the PASID is freed.
  *
+ * Any valid page fault will be eventually routed to an iommu domain and the
+ * page fault handler installed there will get called. The users of this
+ * handling framework should guarantee that the iommu domain could only be
+ * freed after the device has stopped generating page faults (or the iommu
+ * hardware has been set to block the page faults) and the pending page faults
+ * have been flushed.
+ *
  * Return: 0 on success and <0 on error.
  */
 int iommu_queue_iopf(struct iommu_fault *fault, void *cookie)
drivers/iommu/iommu-sva-lib.c +65 -0

77 lines not on this page · raw message

Signature · 6 lines
2.25.1

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

PATCH v7 9/10 iommu: Per-domain I/O page fault handling

In reply to Lu Baolu

Tweak the I/O page fault handling framework to route the page faults to the domain and call the page fault handler retrieved from the domain. This makes the I/O page fault handling framework possible to serve more usage scenarios as long as they have an IOMMU domain and install a page fault handler in it. Some unused functions are also removed to avoid dead code.

The iommu_get_domain_for_dev_pasid() which retrieves attached domain for a {device, PASID} pair is used. It will be used by the page fault handling framework which knows {device, PASID} reported from the iommu driver. We have a guarantee that the SVA domain doesn't go away during IOPF handling, because unbind() waits for pending faults with iopf_queue_flush_dev() before freeing the domain. Hence, there's no need to synchronize life cycle of the iommu domains between the unbind() and the interrupt threads.

---
 drivers/iommu/io-pgfault.c | 64 +++++---------------------------------
 1 file changed, 7 insertions(+), 57 deletions(-)
drivers/iommu/io-pgfault.c +7 -57
index aee9e033012f..4f24ec703479 100644
@@ -69,69 +69,18 @@ static int iopf_complete_group(struct device *dev, struct iopf_fault *iopf,
 	return iommu_page_response(dev, &resp);
 }
 
-static enum iommu_page_response_code
-iopf_handle_single(struct iopf_fault *iopf)
-{
-	vm_fault_t ret;
-	struct mm_struct *mm;
-	struct vm_area_struct *vma;
-	unsigned int access_flags = 0;
-	unsigned int fault_flags = FAULT_FLAG_REMOTE;
-	struct iommu_fault_page_request *prm = &iopf->fault.prm;
-	enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
-
-	if (!(prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID))
-		return status;
-
-	mm = iommu_sva_find(prm->pasid);
-	if (IS_ERR_OR_NULL(mm))
-		return status;
-
-	mmap_read_lock(mm);
-
-	vma = find_extend_vma(mm, prm->addr);
-	if (!vma)
-		/* Unmapped area */
-		goto out_put_mm;
-
-	if (prm->perm & IOMMU_FAULT_PERM_READ)
-		access_flags |= VM_READ;
-
-	if (prm->perm & IOMMU_FAULT_PERM_WRITE) {
-		access_flags |= VM_WRITE;
-		fault_flags |= FAULT_FLAG_WRITE;
-	}
-
-	if (prm->perm & IOMMU_FAULT_PERM_EXEC) {
-		access_flags |= VM_EXEC;
-		fault_flags |= FAULT_FLAG_INSTRUCTION;
-	}
-
-	if (!(prm->perm & IOMMU_FAULT_PERM_PRIV))
-		fault_flags |= FAULT_FLAG_USER;
-
-	if (access_flags & ~vma->vm_flags)
-		/* Access fault */
-		goto out_put_mm;
-
-	ret = handle_mm_fault(vma, prm->addr, fault_flags, NULL);
-	status = ret & VM_FAULT_ERROR ? IOMMU_PAGE_RESP_INVALID :
-		IOMMU_PAGE_RESP_SUCCESS;
-
-out_put_mm:
-	mmap_read_unlock(mm);
-	mmput(mm);
-
-	return status;
-}
-
 static void iopf_handle_group(struct work_struct *work)
 {
 	struct iopf_group *group;
+	struct iommu_domain *domain;
 	struct iopf_fault *iopf, *next;
 	enum iommu_page_response_code status = IOMMU_PAGE_RESP_SUCCESS;
 
 	group = container_of(work, struct iopf_group, work);
+	domain = iommu_get_domain_for_dev_pasid(group->dev,
+				group->last_fault.fault.prm.pasid);
+	if (!domain || !domain->iopf_handler)
+		status = IOMMU_PAGE_RESP_INVALID;
 
 	list_for_each_entry_safe(iopf, next, &group->faults, list) {
 		/*
@@ -139,7 +88,8 @@ static void iopf_handle_group(struct work_struct *work)
 		 * faults in the group if there is an error.
 		 */
 		if (status == IOMMU_PAGE_RESP_SUCCESS)
-			status = iopf_handle_single(iopf);
+			status = domain->iopf_handler(&iopf->fault,
+						      domain->fault_data);
 
 		if (!(iopf->fault.prm.flags &
 		      IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE))
Signature · 6 lines
2.25.1

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

PATCH v7 10/10 iommu: Rename iommu-sva-lib.{c,h}

In reply to Lu Baolu

Rename iommu-sva-lib.c[h] to iommu-sva.c[h] as it contains all code for SVA implementation in iommu core.

---
 drivers/iommu/{iommu-sva-lib.h => iommu-sva.h}  | 0
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 2 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c     | 2 +-
 drivers/iommu/intel/iommu.c                     | 2 +-
 drivers/iommu/intel/svm.c                       | 2 +-
 drivers/iommu/io-pgfault.c                      | 2 +-
 drivers/iommu/{iommu-sva-lib.c => iommu-sva.c}  | 2 +-
 drivers/iommu/Makefile                          | 2 +-
 8 files changed, 7 insertions(+), 7 deletions(-)
 rename drivers/iommu/{iommu-sva-lib.h => iommu-sva.h} (100%)
 rename drivers/iommu/{iommu-sva-lib.c => iommu-sva.c} (99%)
drivers/iommu/iommu-sva.h renamed from drivers/iommu/iommu-sva-lib.h +0 -0
similarity index 100%
rename from drivers/iommu/iommu-sva-lib.h
rename to drivers/iommu/iommu-sva.h
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +1 -1
index 8290d66569f3..b238b09c4999 100644
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 
 #include "arm-smmu-v3.h"
-#include "../../iommu-sva-lib.h"
+#include "../../iommu-sva.h"
 #include "../../io-pgtable-arm.h"
 
 struct arm_smmu_mmu_notifier {
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +1 -1
index b74f8964cc13..e1b80b7ac858 100644
@@ -31,7 +31,7 @@
 #include <linux/amba/bus.h>
 
 #include "arm-smmu-v3.h"
-#include "../../iommu-sva-lib.h"
+#include "../../iommu-sva.h"
 
 static bool disable_bypass = true;
 module_param(disable_bypass, bool, 0444);
drivers/iommu/intel/iommu.c +1 -1
index 10e07d59d4c8..2289939725a7 100644
@@ -27,7 +27,7 @@
 #include <linux/tboot.h>
 
 #include "../irq_remapping.h"
-#include "../iommu-sva-lib.h"
+#include "../iommu-sva.h"
 #include "pasid.h"
 #include "cap_audit.h"
 
drivers/iommu/intel/svm.c +1 -1
index e412a442d9a4..2c45579e5e81 100644
@@ -25,7 +25,7 @@
 
 #include "pasid.h"
 #include "perf.h"
-#include "../iommu-sva-lib.h"
+#include "../iommu-sva.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
 static void intel_svm_drain_prq(struct device *dev, u32 pasid);
drivers/iommu/io-pgfault.c +1 -1
index 4f24ec703479..91b1c6bd01d4 100644
@@ -11,7 +11,7 @@
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 
-#include "iommu-sva-lib.h"
+#include "iommu-sva.h"
 
 /**
  * struct iopf_queue - IO Page Fault queue
drivers/iommu/iommu-sva.c renamed from drivers/iommu/iommu-sva-lib.c +1 -1
similarity index 99%
rename from drivers/iommu/iommu-sva-lib.c
rename to drivers/iommu/iommu-sva.c
index 317ab8e8c149..0e4f7c889f54 100644
@@ -7,7 +7,7 @@
 #include <linux/pci.h>
 #include <linux/pci-ats.h>
 
-#include "iommu-sva-lib.h"
+#include "iommu-sva.h"
 
 static DEFINE_MUTEX(iommu_sva_lock);
 static DECLARE_IOASID_SET(iommu_sva_pasid);
drivers/iommu/Makefile +1 -1
index 44475a9b3eea..c1763476162b 100644
@@ -27,6 +27,6 @@ obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o
 obj-$(CONFIG_S390_IOMMU) += s390-iommu.o
 obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o
 obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o
-obj-$(CONFIG_IOMMU_SVA) += iommu-sva-lib.o io-pgfault.o
+obj-$(CONFIG_IOMMU_SVA) += iommu-sva.o io-pgfault.o
 obj-$(CONFIG_SPRD_IOMMU) += sprd-iommu.o
 obj-$(CONFIG_APPLE_DART) += apple-dart.o
Signature · 6 lines
2.25.1

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

Re: [PATCH v7 01/10] iommu: Add pasids field in struct iommu_device

In reply to Lu Baolu

Hi Baolu,

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) · line 3549

Quoted 9 lines · Lu Baolu
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +1 -0
index 88817a3376ef..6e2cd082c670 100644
@@ -3546,6 +3546,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	/* SID/SSID sizes */
 	smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
 	smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
+	smmu->iommu.pasids = smmu->ssid_bits;

This should be 1UL << smmu->ssid_bits

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

author maintainer
#3 lore raw

Re: [PATCH v7 01/10] iommu: Add pasids field in struct iommu_device

Hi Jean,

Quoted 11 lines · Jean-Philippe Brucker

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) · line 3549

Quoted 9 lines · Lu Baolu
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +1 -0
index 88817a3376ef..6e2cd082c670 100644
@@ -3546,6 +3546,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
  	/* SID/SSID sizes */
  	smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
  	smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
+	smmu->iommu.pasids = smmu->ssid_bits;

This should be 1UL << smmu->ssid_bits

Done. Thank you for the reminding.

Best regards,
baolu

Reviewed-by on v7 2/10
#8 lore raw

Re: [PATCH v7 02/10] iommu: Remove SVM_FLAG_SUPERVISOR_MODE support

In reply to Lu Baolu
Quoted 17 lines · Lu Baolu

The current kernel DMA with PASID support is based on the SVA with a flag SVM_FLAG_SUPERVISOR_MODE. The IOMMU driver binds the kernel memory address space to a PASID of the device. The device driver programs the device with kernel virtual address (KVA) for DMA access. There have been security and functional issues with this approach:

- The lack of IOTLB synchronization upon kernel page table updates. (vmalloc, module/BPF loading, CONFIG_DEBUG_PAGEALLOC etc.)
- Other than slight more protection, using kernel virtual address (KVA) has little advantage over physical address. There are also no use cases yet where DMA engines need kernel virtual addresses for in-kernel DMA.

This removes SVM_FLAG_SUPERVISOR_MODE support from the IOMMU interface. The device drivers are suggested to handle kernel DMA with PASID through the kernel DMA APIs.

Quoted 7 lines

The drvdata parameter in iommu_sva_bind_device() and all callbacks is not needed anymore. Cleanup them as well.

For the SMMU bits

Quoted 341 lines
---
 include/linux/intel-iommu.h                   |  3 +-
 include/linux/intel-svm.h                     | 13 -----
 include/linux/iommu.h                         |  8 +--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  5 +-
 drivers/dma/idxd/cdev.c                       |  2 +-
 drivers/dma/idxd/init.c                       | 24 +-------
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  3 +-
 drivers/iommu/intel/svm.c                     | 57 +++++--------------
 drivers/iommu/iommu.c                         |  5 +-
 drivers/misc/uacce/uacce.c                    |  2 +-
 10 files changed, 26 insertions(+), 96 deletions(-)
include/linux/intel-iommu.h +1 -2
index 4f29139bbfc3..df23300cfa88 100644
@@ -739,8 +739,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
-				 void *drvdata);
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm);
 void intel_svm_unbind(struct iommu_sva *handle);
 u32 intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
include/linux/intel-svm.h +0 -13
index 207ef06ba3e1..f9a0d44f6fdb 100644
@@ -13,17 +13,4 @@
 #define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
 #define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
 
-/*
- * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only
- * for access to kernel addresses. No IOTLB flushes are automatically done
- * for kernel mappings; it is valid only for access to the kernel's static
- * 1:1 mapping of physical memory — not to vmalloc or even module mappings.
- * A future API addition may permit the use of such ranges, by means of an
- * explicit IOTLB flush call (akin to the DMA API's unmap method).
- *
- * It is unlikely that we will ever hook into flush_tlb_kernel_range() to
- * do such IOTLB flushes automatically.
- */
-#define SVM_FLAG_SUPERVISOR_MODE	BIT(0)
-
 #endif /* __INTEL_SVM_H__ */
include/linux/iommu.h +3 -5
index da423e87f248..0c358b7c583b 100644
@@ -243,8 +243,7 @@ struct iommu_ops {
 	int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f);
 	int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f);
 
-	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm,
-				      void *drvdata);
+	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm);
 	void (*sva_unbind)(struct iommu_sva *handle);
 	u32 (*sva_get_pasid)(struct iommu_sva *handle);
 
@@ -667,8 +666,7 @@ int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f);
 bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f);
 
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
-					struct mm_struct *mm,
-					void *drvdata);
+					struct mm_struct *mm);
 void iommu_sva_unbind_device(struct iommu_sva *handle);
 u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 
@@ -1010,7 +1008,7 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 }
 
 static inline struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
 	return NULL;
 }
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +2 -3
index cd48590ada30..d2ba86470c42 100644
@@ -754,8 +754,7 @@ bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
 bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master);
-struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm,
-				    void *drvdata);
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm);
 void arm_smmu_sva_unbind(struct iommu_sva *handle);
 u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);
 void arm_smmu_sva_notifier_synchronize(void);
@@ -791,7 +790,7 @@ static inline bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master
 }
 
 static inline struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 {
 	return ERR_PTR(-ENODEV);
 }
drivers/dma/idxd/cdev.c +1 -1
index b9b2b4a4124e..312ec37ebf91 100644
@@ -100,7 +100,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 	filp->private_data = ctx;
 
 	if (device_pasid_enabled(idxd)) {
-		sva = iommu_sva_bind_device(dev, current->mm, NULL);
+		sva = iommu_sva_bind_device(dev, current->mm);
 		if (IS_ERR(sva)) {
 			rc = PTR_ERR(sva);
 			dev_err(dev, "pasid allocation failed: %d\n", rc);
drivers/dma/idxd/init.c +1 -23
index 993a5dcca24f..1fd80c63248a 100644
@@ -466,29 +466,7 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d
 
 static int idxd_enable_system_pasid(struct idxd_device *idxd)
 {
-	int flags;
-	unsigned int pasid;
-	struct iommu_sva *sva;
-
-	flags = SVM_FLAG_SUPERVISOR_MODE;
-
-	sva = iommu_sva_bind_device(&idxd->pdev->dev, NULL, &flags);
-	if (IS_ERR(sva)) {
-		dev_warn(&idxd->pdev->dev,
-			 "iommu sva bind failed: %ld\n", PTR_ERR(sva));
-		return PTR_ERR(sva);
-	}
-
-	pasid = iommu_sva_get_pasid(sva);
-	if (pasid == IOMMU_PASID_INVALID) {
-		iommu_sva_unbind_device(sva);
-		return -ENODEV;
-	}
-
-	idxd->sva = sva;
-	idxd->pasid = pasid;
-	dev_dbg(&idxd->pdev->dev, "system pasid: %u\n", pasid);
-	return 0;
+	return -EOPNOTSUPP;
 }
 
 static void idxd_disable_system_pasid(struct idxd_device *idxd)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +1 -2
index 1ef7bbb4acf3..f155d406c5d5 100644
@@ -367,8 +367,7 @@ __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 	return ERR_PTR(ret);
 }
 
-struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 {
 	struct iommu_sva *handle;
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
drivers/iommu/intel/svm.c +14 -43
index 7ee37d996e15..d04880a291c3 100644
@@ -313,8 +313,7 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
 	return 0;
 }
 
-static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
-				 unsigned int flags)
+static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm)
 {
 	ioasid_t max_pasid = dev_is_pci(dev) ?
 			pci_max_pasids(to_pci_dev(dev)) : intel_pasid_max_id;
@@ -324,8 +323,7 @@ static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
 
 static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 					   struct device *dev,
-					   struct mm_struct *mm,
-					   unsigned int flags)
+					   struct mm_struct *mm)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	unsigned long iflags, sflags;
@@ -341,22 +339,18 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 
 		svm->pasid = mm->pasid;
 		svm->mm = mm;
-		svm->flags = flags;
 		INIT_LIST_HEAD_RCU(&svm->devs);
 
-		if (!(flags & SVM_FLAG_SUPERVISOR_MODE)) {
-			svm->notifier.ops = &intel_mmuops;
-			ret = mmu_notifier_register(&svm->notifier, mm);
-			if (ret) {
-				kfree(svm);
-				return ERR_PTR(ret);
-			}
+		svm->notifier.ops = &intel_mmuops;
+		ret = mmu_notifier_register(&svm->notifier, mm);
+		if (ret) {
+			kfree(svm);
+			return ERR_PTR(ret);
 		}
 
 		ret = pasid_private_add(svm->pasid, svm);
 		if (ret) {
-			if (svm->notifier.ops)
-				mmu_notifier_unregister(&svm->notifier, mm);
+			mmu_notifier_unregister(&svm->notifier, mm);
 			kfree(svm);
 			return ERR_PTR(ret);
 		}
@@ -391,9 +385,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	}
 
 	/* Setup the pasid table: */
-	sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?
-			PASID_FLAG_SUPERVISOR_MODE : 0;
-	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
+	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
 	spin_lock_irqsave(&iommu->lock, iflags);
 	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
 					    FLPT_DEFAULT_DID, sflags);
@@ -410,8 +402,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	kfree(sdev);
 free_svm:
 	if (list_empty(&svm->devs)) {
-		if (svm->notifier.ops)
-			mmu_notifier_unregister(&svm->notifier, mm);
+		mmu_notifier_unregister(&svm->notifier, mm);
 		pasid_private_remove(mm->pasid);
 		kfree(svm);
 	}
@@ -767,7 +758,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			 * to unbind the mm while any page faults are outstanding.
 			 */
 			svm = pasid_private_find(req->pasid);
-			if (IS_ERR_OR_NULL(svm) || (svm->flags & SVM_FLAG_SUPERVISOR_MODE))
+			if (IS_ERR_OR_NULL(svm))
 				goto bad_req;
 		}
 
@@ -818,40 +809,20 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 	return IRQ_RETVAL(handled);
 }
 
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
-	unsigned int flags = 0;
 	struct iommu_sva *sva;
 	int ret;
 
-	if (drvdata)
-		flags = *(unsigned int *)drvdata;
-
-	if (flags & SVM_FLAG_SUPERVISOR_MODE) {
-		if (!ecap_srs(iommu->ecap)) {
-			dev_err(dev, "%s: Supervisor PASID not supported\n",
-				iommu->name);
-			return ERR_PTR(-EOPNOTSUPP);
-		}
-
-		if (mm) {
-			dev_err(dev, "%s: Supervisor PASID with user provided mm\n",
-				iommu->name);
-			return ERR_PTR(-EINVAL);
-		}
-
-		mm = &init_mm;
-	}
-
 	mutex_lock(&pasid_mutex);
-	ret = intel_svm_alloc_pasid(dev, mm, flags);
+	ret = intel_svm_alloc_pasid(dev, mm);
 	if (ret) {
 		mutex_unlock(&pasid_mutex);
 		return ERR_PTR(ret);
 	}
 
-	sva = intel_svm_bind_mm(iommu, dev, mm, flags);
+	sva = intel_svm_bind_mm(iommu, dev, mm);
 	mutex_unlock(&pasid_mutex);
 
 	return sva;
drivers/iommu/iommu.c +2 -3
index 847ad47a2dfd..9955f58bd08c 100644
@@ -2768,7 +2768,6 @@ EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
  * iommu_sva_bind_device() - Bind a process address space to a device
  * @dev: the device
  * @mm: the mm to bind, caller must hold a reference to it
- * @drvdata: opaque data pointer to pass to bind callback
  *
  * Create a bond between device and address space, allowing the device to access
  * the mm using the returned PASID. If a bond already exists between @device and
@@ -2781,7 +2780,7 @@ EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
  * On error, returns an ERR_PTR value.
  */
 struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
 	struct iommu_group *group;
 	struct iommu_sva *handle = ERR_PTR(-EINVAL);
@@ -2806,7 +2805,7 @@ iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata)
 	if (iommu_group_device_count(group) != 1)
 		goto out_unlock;
 
-	handle = ops->sva_bind(dev, mm, drvdata);
+	handle = ops->sva_bind(dev, mm);
 
 out_unlock:
 	mutex_unlock(&group->mutex);
drivers/misc/uacce/uacce.c +1 -1
index 281c54003edc..3238a867ea51 100644
@@ -99,7 +99,7 @@ static int uacce_bind_queue(struct uacce_device *uacce, struct uacce_queue *q)
 	if (!(uacce->flags & UACCE_DEV_SVA))
 		return 0;
 
-	handle = iommu_sva_bind_device(uacce->parent, current->mm, NULL);
+	handle = iommu_sva_bind_device(uacce->parent, current->mm);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
Signature · 1 line
2.25.1

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

Reviewed-by on v7 3/10
#11 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Lu Baolu
Quoted 155 lines · Lu Baolu

The iommu_sva_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

---
 include/linux/iommu.h         | 51 +++++++++++++++++++++++++
 drivers/iommu/iommu-sva-lib.h | 15 ++++++++
 drivers/iommu/iommu-sva-lib.c | 48 +++++++++++++++++++++++
 drivers/iommu/iommu.c         | 71 +++++++++++++++++++++++++++++++++++
 4 files changed, 185 insertions(+)
include/linux/iommu.h +51 -0
index 0c358b7c583b..e8cf82d46ce1 100644
@@ -64,6 +64,9 @@ struct iommu_domain_geometry {
 #define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
 #define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
 
+#define __IOMMU_DOMAIN_SHARED	(1U << 4)  /* Page table shared from CPU  */
+#define __IOMMU_DOMAIN_HOST_VA	(1U << 5)  /* Host CPU virtual address */
+
 /*
  * This are the possible domain-types
  *
@@ -86,6 +89,8 @@ struct iommu_domain_geometry {
 #define IOMMU_DOMAIN_DMA_FQ	(__IOMMU_DOMAIN_PAGING |	\
 				 __IOMMU_DOMAIN_DMA_API |	\
 				 __IOMMU_DOMAIN_DMA_FQ)
+#define IOMMU_DOMAIN_SVA	(__IOMMU_DOMAIN_SHARED |	\
+				 __IOMMU_DOMAIN_HOST_VA)
 
 struct iommu_domain {
 	unsigned type;
@@ -254,6 +259,7 @@ struct iommu_ops {
 	int (*def_domain_type)(struct device *dev);
 
 	const struct iommu_domain_ops *default_domain_ops;
+	const struct iommu_domain_ops *sva_domain_ops;
 	unsigned long pgsize_bitmap;
 	struct module *owner;
 };
@@ -262,6 +268,8 @@ struct iommu_ops {
  * struct iommu_domain_ops - domain specific operations
  * @attach_dev: attach an iommu domain to a device
  * @detach_dev: detach an iommu domain from a device
+ * @set_dev_pasid: set an iommu domain to a pasid of device
+ * @block_dev_pasid: block pasid of device from using iommu domain
  * @map: map a physically contiguous memory region to an iommu domain
  * @map_pages: map a physically contiguous set of pages of the same size to
  *             an iommu domain.
@@ -282,6 +290,10 @@ struct iommu_ops {
 struct iommu_domain_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
+	int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid);
+	void (*block_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+				ioasid_t pasid);
 
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
@@ -677,6 +689,10 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
 void iommu_group_release_dma_owner(struct iommu_group *group);
 bool iommu_group_dma_owner_claimed(struct iommu_group *group);
 
+int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
+			   ioasid_t pasid);
+void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
+			      ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1050,6 +1066,17 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
 {
 	return false;
 }
+
+static inline int iommu_set_device_pasid(struct iommu_domain *domain,
+					 struct device *dev, ioasid_t pasid)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_block_device_pasid(struct iommu_domain *domain,
+					    struct device *dev, ioasid_t pasid)
+{
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**
@@ -1075,4 +1102,28 @@ void iommu_debugfs_setup(void);
 static inline void iommu_debugfs_setup(void) {}
 #endif
 
+#ifdef CONFIG_IOMMU_SVA
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm);
+void iommu_sva_free_domain(struct iommu_domain *domain);
+int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
+			 ioasid_t pasid);
+#else /* CONFIG_IOMMU_SVA */
+static inline struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline void iommu_sva_free_domain(struct iommu_domain *domain)
+{
+}
+
+static inline int iommu_sva_set_domain(struct iommu_domain *domain,
+				       struct device *dev, ioasid_t pasid)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_IOMMU_SVA */
+
 #endif /* __LINUX_IOMMU_H */
drivers/iommu/iommu-sva-lib.h +1 -0
index 8909ea1094e3..1be21e6b93ec 100644
@@ -7,6 +7,7 @@
 
 #include <linux/ioasid.h>
 #include <linux/mm_types.h>
+#include <linux/iommu.h>
 
 int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
 struct mm_struct *iommu_sva_find(ioasid_t pasid);

drivers/iommu/iommu-sva-lib.h struct device; · line 25

Quoted 9 lines
drivers/iommu/iommu-sva-lib.h +6 -0
@@ -16,6 +17,20 @@ struct device;
 struct iommu_fault;
 struct iopf_queue;
 
+struct iommu_sva_domain {
+	struct iommu_domain	domain;
+	struct mm_struct	*mm;
+};
+
+#define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)

Is there a reason to use the 'safe' version of container_of()? Callers of to_sva_domain() don't check the return value before dereferencing it so they would break anyway if someone passes an error pointer as domain. I think it matters because there is no other user of container_of_safe() in the kernel (the only user, lustre, went away in 2018) so someone will want to remove it.

Apart from that

Quoted 163 lines
drivers/iommu/iommu-sva-lib.h +8 -0
+
+static inline struct mm_struct *domain_to_mm(struct iommu_domain *domain)
+{
+	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
+
+	return sva_domain->mm;
+}
+
 #ifdef CONFIG_IOMMU_SVA
 int iommu_queue_iopf(struct iommu_fault *fault, void *cookie);
 
drivers/iommu/iommu-sva-lib.c +48 -0
index 106506143896..210c376f6043 100644
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
 	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+
+	if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
+		return ERR_PTR(-ENODEV);
+
+	sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
+	if (!sva_domain)
+		return ERR_PTR(-ENOMEM);
+
+	mmgrab(mm);
+	sva_domain->mm = mm;
+
+	domain = &sva_domain->domain;
+	domain->type = IOMMU_DOMAIN_SVA;
+	domain->ops = bus->iommu_ops->sva_domain_ops;
+
+	return domain;
+}
+
+void iommu_sva_free_domain(struct iommu_domain *domain)
+{
+	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
+
+	mmdrop(sva_domain->mm);
+	kfree(sva_domain);
+}
+
+int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
+			 ioasid_t pasid)
+{
+	struct bus_type *bus = dev->bus;
+
+	if (!bus || !bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
+		return -ENODEV;
+
+	if (domain->ops != bus->iommu_ops->sva_domain_ops)
+		return -EINVAL;
+
+	return iommu_set_device_pasid(domain, dev, pasid);
+}
drivers/iommu/iommu.c +71 -0
index 9955f58bd08c..789816e4b9d6 100644
@@ -38,6 +38,7 @@ struct iommu_group {
 	struct kobject kobj;
 	struct kobject *devices_kobj;
 	struct list_head devices;
+	struct xarray pasid_array;
 	struct mutex mutex;
 	void *iommu_data;
 	void (*iommu_data_release)(void *iommu_data);
@@ -640,6 +641,7 @@ struct iommu_group *iommu_group_alloc(void)
 	mutex_init(&group->mutex);
 	INIT_LIST_HEAD(&group->devices);
 	INIT_LIST_HEAD(&group->entry);
+	xa_init(&group->pasid_array);
 
 	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
@@ -3251,3 +3253,72 @@ bool iommu_group_dma_owner_claimed(struct iommu_group *group)
 	return user;
 }
 EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);
+
+static bool device_group_immutable_singleton(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+	int count;
+
+	if (!group)
+		return false;
+
+	mutex_lock(&group->mutex);
+	count = iommu_group_device_count(group);
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	if (count != 1)
+		return false;
+
+	/*
+	 * The PCI device could be considered to be fully isolated if all
+	 * devices on the path from the device to the host-PCI bridge are
+	 * protected from peer-to-peer DMA by ACS.
+	 */
+	if (dev_is_pci(dev))
+		return pci_acs_path_enabled(to_pci_dev(dev), NULL,
+					    REQ_ACS_FLAGS);
+
+	return true;
+}
+
+int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
+			   ioasid_t pasid)
+{
+	struct iommu_group *group;
+	int ret = -EBUSY;
+	void *curr;
+
+	if (!domain->ops->set_dev_pasid)
+		return -EOPNOTSUPP;
+
+	if (!device_group_immutable_singleton(dev))
+		return -EINVAL;
+
+	group = iommu_group_get(dev);
+	mutex_lock(&group->mutex);
+	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
+	if (curr)
+		goto out_unlock;
+	ret = domain->ops->set_dev_pasid(domain, dev, pasid);
+	if (ret)
+		xa_erase(&group->pasid_array, pasid);
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
+			      ioasid_t pasid)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	mutex_lock(&group->mutex);
+	domain->ops->block_dev_pasid(domain, dev, pasid);
+	xa_erase(&group->pasid_array, pasid);
+	mutex_unlock(&group->mutex);
+
+	iommu_group_put(group);
+}
Signature · 1 line
2.25.1
Reviewed-by on v7 5/10
#33 lore raw

Re: [PATCH v7 05/10] arm-smmu-v3/sva: Add SVA domain support

In reply to Lu Baolu
Quoted 3 lines · Lu Baolu

Add support for domain ops callbacks for an SVA domain.

(I'll try to take some time next cycle to clean up the driver following this change)

Quoted 95 lines
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  4 ++
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   | 46 +++++++++++++++++++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   |  6 +++
 3 files changed, 56 insertions(+)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +4 -0
index d2ba86470c42..ec77f6a51ff9 100644
@@ -758,6 +758,10 @@ struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm);
 void arm_smmu_sva_unbind(struct iommu_sva *handle);
 u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);
 void arm_smmu_sva_notifier_synchronize(void);
+int arm_smmu_sva_attach_dev_pasid(struct iommu_domain *domain,
+				  struct device *dev, ioasid_t id);
+void arm_smmu_sva_detach_dev_pasid(struct iommu_domain *domain,
+				   struct device *dev, ioasid_t id);
 #else /* CONFIG_ARM_SMMU_V3_SVA */
 static inline bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 {
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +46 -0
index f155d406c5d5..6969974ca89e 100644
@@ -549,3 +549,49 @@ void arm_smmu_sva_notifier_synchronize(void)
 	 */
 	mmu_notifier_synchronize();
 }
+
+int arm_smmu_sva_attach_dev_pasid(struct iommu_domain *domain,
+				  struct device *dev, ioasid_t id)
+{
+	int ret = 0;
+	struct mm_struct *mm;
+	struct iommu_sva *handle;
+
+	if (domain->type != IOMMU_DOMAIN_SVA)
+		return -EINVAL;
+
+	mm = domain_to_mm(domain);
+	if (WARN_ON(!mm))
+		return -ENODEV;
+
+	mutex_lock(&sva_lock);
+	handle = __arm_smmu_sva_bind(dev, mm);
+	if (IS_ERR(handle))
+		ret = PTR_ERR(handle);
+	mutex_unlock(&sva_lock);
+
+	return ret;
+}
+
+void arm_smmu_sva_detach_dev_pasid(struct iommu_domain *domain,
+				   struct device *dev, ioasid_t id)
+{
+	struct arm_smmu_bond *bond = NULL, *t;
+	struct mm_struct *mm = domain_to_mm(domain);
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+	mutex_lock(&sva_lock);
+	list_for_each_entry(t, &master->bonds, list) {
+		if (t->mm == mm) {
+			bond = t;
+			break;
+		}
+	}
+
+	if (!WARN_ON(!bond) && refcount_dec_and_test(&bond->refs)) {
+		list_del(&bond->list);
+		arm_smmu_mmu_notifier_put(bond->smmu_mn);
+		kfree(bond);
+	}
+	mutex_unlock(&sva_lock);
+}
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +6 -0
index 6e2cd082c670..4ad3ca70cf89 100644
@@ -2858,6 +2858,12 @@ static struct iommu_ops arm_smmu_ops = {
 	.page_response		= arm_smmu_page_response,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 	.owner			= THIS_MODULE,
+#ifdef CONFIG_ARM_SMMU_V3_SVA
+	.sva_domain_ops = &(const struct iommu_domain_ops) {
+		.set_dev_pasid		= arm_smmu_sva_attach_dev_pasid,
+		.block_dev_pasid	= arm_smmu_sva_detach_dev_pasid,
+	},
+#endif
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= arm_smmu_attach_dev,
 		.map_pages		= arm_smmu_map_pages,
Signature · 1 line
2.25.1

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

#35 lore raw

Re: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Lu Baolu
Quoted 176 lines · Lu Baolu

The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need for any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops.

This refactors the IOMMU SVA interfaces implementation by using the set/block_pasid_dev ops and align them with the concept of the SVA iommu domain. Put the new SVA code in the sva related file in order to make it self-contained.

---
 include/linux/iommu.h         |  48 ++++++++------
 drivers/iommu/iommu-sva-lib.h |   1 +
 drivers/iommu/iommu-sva-lib.c | 113 ++++++++++++++++++++++++++++++++
 drivers/iommu/iommu.c         | 119 ++++++++--------------------------
 4 files changed, 170 insertions(+), 111 deletions(-)
include/linux/iommu.h +28 -20
index e8cf82d46ce1..d9ac5ebe5bbb 100644
@@ -635,6 +635,7 @@ struct iommu_fwspec {
  */
 struct iommu_sva {
 	struct device			*dev;
+	refcount_t			users;
 };
 
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
@@ -677,11 +678,6 @@ int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f);
 bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f);
 
-struct iommu_sva *iommu_sva_bind_device(struct device *dev,
-					struct mm_struct *mm);
-void iommu_sva_unbind_device(struct iommu_sva *handle);
-u32 iommu_sva_get_pasid(struct iommu_sva *handle);
-
 int iommu_device_use_default_domain(struct device *dev);
 void iommu_device_unuse_default_domain(struct device *dev);
 
@@ -693,6 +689,8 @@ int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
 			   ioasid_t pasid);
 void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
 			      ioasid_t pasid);
+struct iommu_domain *
+iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1023,21 +1021,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 	return -ENODEV;
 }
 
-static inline struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
-{
-	return NULL;
-}
-
-static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
-{
-}
-
-static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
-{
-	return IOMMU_PASID_INVALID;
-}
-
 static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
 {
 	return NULL;
@@ -1077,6 +1060,12 @@ static inline void iommu_block_device_pasid(struct iommu_domain *domain,
 					    struct device *dev, ioasid_t pasid)
 {
 }
+
+static inline struct iommu_domain *
+iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid)
+{
+	return NULL;
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**
@@ -1108,6 +1097,10 @@ iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm);
 void iommu_sva_free_domain(struct iommu_domain *domain);
 int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
 			 ioasid_t pasid);
+struct iommu_sva *iommu_sva_bind_device(struct device *dev,
+					struct mm_struct *mm);
+void iommu_sva_unbind_device(struct iommu_sva *handle);
+u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 #else /* CONFIG_IOMMU_SVA */
 static inline struct iommu_domain *
 iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
@@ -1124,6 +1117,21 @@ static inline int iommu_sva_set_domain(struct iommu_domain *domain,
 {
 	return -EINVAL;
 }
+
+static inline struct iommu_sva *
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
+{
+	return NULL;
+}
+
+static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
+{
+}
+
+static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
+{
+	return IOMMU_PASID_INVALID;
+}
 #endif /* CONFIG_IOMMU_SVA */
 
 #endif /* __LINUX_IOMMU_H */
drivers/iommu/iommu-sva-lib.h +1 -0
index 1be21e6b93ec..ebab5a8cb126 100644
@@ -20,6 +20,7 @@ struct iopf_queue;
 struct iommu_sva_domain {
 	struct iommu_domain	domain;
 	struct mm_struct	*mm;
+	struct iommu_sva	bond;
 };
 
 #define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)
drivers/iommu/iommu-sva-lib.c +30 -0
index 210c376f6043..568e0f64edac 100644
@@ -4,6 +4,8 @@
  */
 #include <linux/mutex.h>
 #include <linux/sched/mm.h>
+#include <linux/pci.h>
+#include <linux/pci-ats.h>
 
 #include "iommu-sva-lib.h"
 
@@ -117,3 +119,114 @@ int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
 
 	return iommu_set_device_pasid(domain, dev, pasid);
 }
+
+/**
+ * iommu_sva_bind_device() - Bind a process address space to a device
+ * @dev: the device
+ * @mm: the mm to bind, caller must hold a reference to mm_users
+ *
+ * Create a bond between device and address space, allowing the device to access
+ * the mm using the returned PASID. If a bond already exists between @device and
+ * @mm, it is returned and an additional reference is taken. Caller must call
+ * iommu_sva_unbind_device() to release each reference.
+ *
+ * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
+ * initialize the required SVA features.
+ *
+ * On error, returns an ERR_PTR value.
+ */
+struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+	ioasid_t max_pasid = 0;
+	int ret = -EINVAL;
+
+	/* Allocate mm->pasid if necessary. */
+	if (!dev->iommu->iommu_dev->pasids)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (dev_is_pci(dev)) {

drivers/iommu/iommu-sva-lib.c int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev, · line 159

Quoted 10 lines
drivers/iommu/iommu-sva-lib.c +10 -0
+		max_pasid = pci_max_pasids(to_pci_dev(dev));
+		if (max_pasid < 0)
+			return ERR_PTR(max_pasid);
+	} else {
+		ret = device_property_read_u32(dev, "pasid-num-bits",
+					       &max_pasid);
+		if (ret)
+			return ERR_PTR(ret);
+		max_pasid = (1UL << max_pasid);
+	}

The IOMMU driver needs this PASID width information earlier, when creating the PASID table (in .probe_device(), .attach_dev()). Since we're moving it to the IOMMU core to avoid code duplication, it should be done earlier and stored in dev->iommu

Thanks,
Jean

Quoted 210 lines
drivers/iommu/iommu-sva-lib.c +73 -0
+	max_pasid = min_t(u32, max_pasid, dev->iommu->iommu_dev->pasids);
+	ret = iommu_sva_alloc_pasid(mm, 1, max_pasid - 1);
+	if (ret)
+		return ERR_PTR(ret);
+
+	mutex_lock(&iommu_sva_lock);
+	/* Search for an existing domain. */
+	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid);
+	if (domain) {
+		sva_domain = to_sva_domain(domain);
+		refcount_inc(&sva_domain->bond.users);
+		goto out_success;
+	}
+
+	/* Allocate a new domain and set it on device pasid. */
+	domain = iommu_sva_alloc_domain(dev->bus, mm);
+	if (IS_ERR(domain)) {
+		ret = PTR_ERR(domain);
+		goto out_unlock;
+	}
+
+	ret = iommu_sva_set_domain(domain, dev, mm->pasid);
+	if (ret)
+		goto out_free_domain;
+	sva_domain = to_sva_domain(domain);
+	sva_domain->bond.dev = dev;
+	refcount_set(&sva_domain->bond.users, 1);
+
+out_success:
+	mutex_unlock(&iommu_sva_lock);
+	return &sva_domain->bond;
+
+out_free_domain:
+	iommu_sva_free_domain(domain);
+out_unlock:
+	mutex_unlock(&iommu_sva_lock);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
+
+/**
+ * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device
+ * @handle: the handle returned by iommu_sva_bind_device()
+ *
+ * Put reference to a bond between device and address space. The device should
+ * not be issuing any more transaction for this PASID. All outstanding page
+ * requests for this PASID must have been flushed to the IOMMU.
+ */
+void iommu_sva_unbind_device(struct iommu_sva *handle)
+{
+	struct device *dev = handle->dev;
+	struct iommu_sva_domain *sva_domain =
+			container_of(handle, struct iommu_sva_domain, bond);
+	ioasid_t pasid = iommu_sva_get_pasid(handle);
+
+	mutex_lock(&iommu_sva_lock);
+	if (refcount_dec_and_test(&sva_domain->bond.users)) {
+		iommu_block_device_pasid(&sva_domain->domain, dev, pasid);
+		iommu_sva_free_domain(&sva_domain->domain);
+	}
+	mutex_unlock(&iommu_sva_lock);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
+
+u32 iommu_sva_get_pasid(struct iommu_sva *handle)
+{
+	struct iommu_sva_domain *sva_domain =
+			container_of(handle, struct iommu_sva_domain, bond);
+
+	return sva_domain->mm->pasid;
+}
+EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
drivers/iommu/iommu.c +28 -91
index 789816e4b9d6..e49c5a5b8cc1 100644
@@ -2766,97 +2766,6 @@ bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat)
 }
 EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
 
-/**
- * iommu_sva_bind_device() - Bind a process address space to a device
- * @dev: the device
- * @mm: the mm to bind, caller must hold a reference to it
- *
- * Create a bond between device and address space, allowing the device to access
- * the mm using the returned PASID. If a bond already exists between @device and
- * @mm, it is returned and an additional reference is taken. Caller must call
- * iommu_sva_unbind_device() to release each reference.
- *
- * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
- * initialize the required SVA features.
- *
- * On error, returns an ERR_PTR value.
- */
-struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
-{
-	struct iommu_group *group;
-	struct iommu_sva *handle = ERR_PTR(-EINVAL);
-	const struct iommu_ops *ops = dev_iommu_ops(dev);
-
-	if (!ops->sva_bind)
-		return ERR_PTR(-ENODEV);
-
-	group = iommu_group_get(dev);
-	if (!group)
-		return ERR_PTR(-ENODEV);
-
-	/* Ensure device count and domain don't change while we're binding */
-	mutex_lock(&group->mutex);
-
-	/*
-	 * To keep things simple, SVA currently doesn't support IOMMU groups
-	 * with more than one device. Existing SVA-capable systems are not
-	 * affected by the problems that required IOMMU groups (lack of ACS
-	 * isolation, device ID aliasing and other hardware issues).
-	 */
-	if (iommu_group_device_count(group) != 1)
-		goto out_unlock;
-
-	handle = ops->sva_bind(dev, mm);
-
-out_unlock:
-	mutex_unlock(&group->mutex);
-	iommu_group_put(group);
-
-	return handle;
-}
-EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
-
-/**
- * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device
- * @handle: the handle returned by iommu_sva_bind_device()
- *
- * Put reference to a bond between device and address space. The device should
- * not be issuing any more transaction for this PASID. All outstanding page
- * requests for this PASID must have been flushed to the IOMMU.
- */
-void iommu_sva_unbind_device(struct iommu_sva *handle)
-{
-	struct iommu_group *group;
-	struct device *dev = handle->dev;
-	const struct iommu_ops *ops = dev_iommu_ops(dev);
-
-	if (!ops->sva_unbind)
-		return;
-
-	group = iommu_group_get(dev);
-	if (!group)
-		return;
-
-	mutex_lock(&group->mutex);
-	ops->sva_unbind(handle);
-	mutex_unlock(&group->mutex);
-
-	iommu_group_put(group);
-}
-EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
-
-u32 iommu_sva_get_pasid(struct iommu_sva *handle)
-{
-	const struct iommu_ops *ops = dev_iommu_ops(handle->dev);
-
-	if (!ops->sva_get_pasid)
-		return IOMMU_PASID_INVALID;
-
-	return ops->sva_get_pasid(handle);
-}
-EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
-
 /*
  * Changes the default domain of an iommu group that has *only* one device
  *
@@ -3322,3 +3231,31 @@ void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
 
 	iommu_group_put(group);
 }
+
+/*
+ * This is a variant of iommu_get_domain_for_dev(). It returns the existing
+ * domain attached to pasid of a device. It's only for internal use of the
+ * IOMMU subsystem. The caller must take care to avoid any possible
+ * use-after-free case.
+ */
+struct iommu_domain *
+iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid)
+{
+	struct iommu_domain *domain;
+	struct iommu_group *group;
+
+	if (!pasid_valid(pasid))
+		return NULL;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return NULL;
+	/*
+	 * The xarray protects its internal state with RCU. Hence the domain
+	 * obtained is either NULL or fully formed.
+	 */
+	domain = xa_load(&group->pasid_array, pasid);
+	iommu_group_put(group);
+
+	return domain;
+}
Signature · 1 line
2.25.1

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

Reviewed-by on v7 8/10
#47 lore raw

Re: [PATCH v7 08/10] iommu: Prepare IOMMU domain for IOPF

In reply to Lu Baolu
Quoted 59 lines · Lu Baolu

This adds some mechanisms around the iommu_domain so that the I/O page fault handling framework could route a page fault to the domain and call the fault handler from it.

Add pointers to the page fault handler and its private data in struct iommu_domain. The fault handler will be called with the private data as a parameter once a page fault is routed to the domain. Any kernel component which owns an iommu domain could install handler and its private parameter so that the page fault could be further routed and handled.

This also prepares the SVA implementation to be the first consumer of the per-domain page fault handling model.

---
 include/linux/iommu.h         |  3 ++
 drivers/iommu/io-pgfault.c    |  7 ++++
 drivers/iommu/iommu-sva-lib.c | 65 +++++++++++++++++++++++++++++++++++
 3 files changed, 75 insertions(+)
include/linux/iommu.h +3 -0
index e4ce2fe0e144..45f274b2640d 100644
@@ -100,6 +100,9 @@ struct iommu_domain {
 	void *handler_token;
 	struct iommu_domain_geometry geometry;
 	struct iommu_dma_cookie *iova_cookie;
+	enum iommu_page_response_code (*iopf_handler)(struct iommu_fault *fault,
+						      void *data);
+	void *fault_data;
 };
 
 static inline bool iommu_is_dma_domain(struct iommu_domain *domain)
drivers/iommu/io-pgfault.c +7 -0
index 1df8c1dcae77..aee9e033012f 100644
@@ -181,6 +181,13 @@ static void iopf_handle_group(struct work_struct *work)
  * request completes, outstanding faults will have been dealt with by the time
  * the PASID is freed.
  *
+ * Any valid page fault will be eventually routed to an iommu domain and the
+ * page fault handler installed there will get called. The users of this
+ * handling framework should guarantee that the iommu domain could only be
+ * freed after the device has stopped generating page faults (or the iommu
+ * hardware has been set to block the page faults) and the pending page faults
+ * have been flushed.
+ *
  * Return: 0 on success and <0 on error.
  */
 int iommu_queue_iopf(struct iommu_fault *fault, void *cookie)
drivers/iommu/iommu-sva-lib.c +0 -0
index 568e0f64edac..317ab8e8c149 100644

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 79

Quoted 8 lines
drivers/iommu/iommu-sva-lib.c +5 -0
@@ -72,6 +72,69 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
 }
 EXPORT_SYMBOL_GPL(iommu_sva_find);
 
+/*
+ * I/O page fault handler for SVA
+ *
+ * Copied from io-pgfault.c with mmget_not_zero() added before
+ * mmap_read_lock().

Comment doesn't really belong here, maybe better in the commit message. Apart from that

Quoted 73 lines
drivers/iommu/iommu-sva-lib.c +60 -0
+ */
+static enum iommu_page_response_code
+iommu_sva_handle_iopf(struct iommu_fault *fault, void *data)
+{
+	vm_fault_t ret;
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	unsigned int access_flags = 0;
+	struct iommu_domain *domain = data;
+	unsigned int fault_flags = FAULT_FLAG_REMOTE;
+	struct iommu_fault_page_request *prm = &fault->prm;
+	enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
+
+	if (!(prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID))
+		return status;
+
+	mm = domain_to_mm(domain);
+	if (IS_ERR_OR_NULL(mm) || !mmget_not_zero(mm))
+		return status;
+
+	mmap_read_lock(mm);
+
+	vma = find_extend_vma(mm, prm->addr);
+	if (!vma)
+		/* Unmapped area */
+		goto out_put_mm;
+
+	if (prm->perm & IOMMU_FAULT_PERM_READ)
+		access_flags |= VM_READ;
+
+	if (prm->perm & IOMMU_FAULT_PERM_WRITE) {
+		access_flags |= VM_WRITE;
+		fault_flags |= FAULT_FLAG_WRITE;
+	}
+
+	if (prm->perm & IOMMU_FAULT_PERM_EXEC) {
+		access_flags |= VM_EXEC;
+		fault_flags |= FAULT_FLAG_INSTRUCTION;
+	}
+
+	if (!(prm->perm & IOMMU_FAULT_PERM_PRIV))
+		fault_flags |= FAULT_FLAG_USER;
+
+	if (access_flags & ~vma->vm_flags)
+		/* Access fault */
+		goto out_put_mm;
+
+	ret = handle_mm_fault(vma, prm->addr, fault_flags, NULL);
+	status = ret & VM_FAULT_ERROR ? IOMMU_PAGE_RESP_INVALID :
+		IOMMU_PAGE_RESP_SUCCESS;
+
+out_put_mm:
+	mmap_read_unlock(mm);
+	mmput(mm);
+
+	return status;
+}
+
 /*
  * IOMMU SVA driver-oriented interfaces
  */
@@ -94,6 +157,8 @@ iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
 	domain = &sva_domain->domain;
 	domain->type = IOMMU_DOMAIN_SVA;
 	domain->ops = bus->iommu_ops->sva_domain_ops;
+	domain->iopf_handler = iommu_sva_handle_iopf;
+	domain->fault_data = domain;
 
 	return domain;
 }
Signature · 1 line
2.25.1

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

author maintainer
#12 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Jean-Philippe Brucker
Quoted 16 lines · Jean-Philippe Brucker
Quoted 16 lines
drivers/iommu/iommu-sva-lib.h +1 -0
index 8909ea1094e3..1be21e6b93ec 100644
@@ -7,6 +7,7 @@
 
  #include <linux/ioasid.h>
  #include <linux/mm_types.h>
+#include <linux/iommu.h>
 
  int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
  struct mm_struct *iommu_sva_find(ioasid_t pasid);
@@ -16,6 +17,20 @@ struct device;
  struct iommu_fault;
  struct iopf_queue;
 
Quoted 12 lines

drivers/iommu/iommu-sva-lib.h struct device; · line 25

Quoted 6 lines
drivers/iommu/iommu-sva-lib.h +6 -0
+struct iommu_sva_domain {
+	struct iommu_domain	domain;
+	struct mm_struct	*mm;
+};
+
+#define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)

Is there a reason to use the 'safe' version of container_of()? Callers of to_sva_domain() don't check the return value before dereferencing it so they would break anyway if someone passes an error pointer as domain. I think it matters because there is no other user of container_of_safe() in the kernel (the only user, lustre, went away in 2018) so someone will want to remove it.

Fair enough. I wondered why there's no user in the tree. Thanks for the explanation. I will replace it with container_of().

Quoted 5 lines

Apart from that

Thank you!

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

author maintainer
#36 lore raw

Re: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Jean-Philippe Brucker
Quoted 18 lines · Jean-Philippe Brucker
Quoted 18 lines
(quoted diff) +18 -0
+struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+	ioasid_t max_pasid = 0;
+	int ret = -EINVAL;
+
+	/* Allocate mm->pasid if necessary. */
+	if (!dev->iommu->iommu_dev->pasids)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (dev_is_pci(dev)) {
+		max_pasid = pci_max_pasids(to_pci_dev(dev));
+		if (max_pasid < 0)
+			return ERR_PTR(max_pasid);
+	} else {
+		ret = device_property_read_u32(dev, "pasid-num-bits",
+					       &max_pasid);
Quoted 8 lines

Review

Quoted 4 lines
(quoted diff) +4 -0
+		if (ret)
+			return ERR_PTR(ret);
+		max_pasid = (1UL << max_pasid);
+	}

The IOMMU driver needs this PASID width information earlier, when creating the PASID table (in .probe_device(), .attach_dev()). Since we're moving it to the IOMMU core to avoid code duplication, it should be done earlier and stored in dev->iommu

Yes, really. How about below changes?

From f1382579e8a15ca49acdf758d38fd36451ea174d Mon Sep 17 00:00:00 2001
From: Lu Baolu <[email protected]>
Date: Mon, 28 Feb 2022 15:01:35 +0800
Subject: [PATCH 1/1] iommu: Add pasids field in struct dev_iommu

Use this field to save the number of PASIDs that a device is able to consume. It is a generic attribute of a device and lifting it into the per-device dev_iommu struct could help to avoid the boilerplate code in various IOMMU drivers.

---
 drivers/iommu/iommu.c | 15 +++++++++++++++
 include/linux/iommu.h |  2 ++
 2 files changed, 17 insertions(+)
drivers/iommu/iommu.c +15 -0
index e49c5a5b8cc1..6b731171d42f 100644
@@ -20,6 +20,7 @@
 #include <linux/idr.h>
 #include <linux/err.h>
 #include <linux/pci.h>
+#include <linux/pci-ats.h>
 #include <linux/bitops.h>
 #include <linux/property.h>
 #include <linux/fsl/mc.h>
@@ -194,6 +195,8 @@ EXPORT_SYMBOL_GPL(iommu_device_unregister);
 static struct dev_iommu *dev_iommu_get(struct device *dev)
 {
 	struct dev_iommu *param = dev->iommu;
+	u32 max_pasids = 0;
+	int ret;
 
 	if (param)
 		return param;
@@ -202,6 +205,18 @@ static struct dev_iommu *dev_iommu_get(struct device *dev)
 	if (!param)
 		return NULL;
 
+	if (dev_is_pci(dev)) {
+		ret = pci_max_pasids(to_pci_dev(dev));
+		if (ret > 0)
+			max_pasids = ret;
+	} else {
+		ret = device_property_read_u32(dev, "pasid-num-bits",
+					       &max_pasids);
+		if (!ret)
+			max_pasids = (1UL << max_pasids);
+	}
+	param->pasids = max_pasids;
+
 	mutex_init(&param->lock);
 	dev->iommu = param;
 	return param;
include/linux/iommu.h +2 -0
index 45f274b2640d..d4296136ba75 100644
@@ -371,6 +371,7 @@ struct iommu_fault_param {
  * @fwspec:	 IOMMU fwspec data
  * @iommu_dev:	 IOMMU device this device is linked to
  * @priv:	 IOMMU Driver private data
+ * @pasids:	 number of supported PASIDs
  *
  * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
  *	struct iommu_group	*iommu_group;
@@ -382,6 +383,7 @@ struct dev_iommu {
 	struct iommu_fwspec		*fwspec;
 	struct iommu_device		*iommu_dev;
 	void				*priv;
+	u32				pasids;
 };
 
 int iommu_device_register(struct iommu_device *iommu,
Signature · 4 lines
2.25.1

Best regards,
baolu
#37 lore raw

Re: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

Quoted 74 lines · Baolu Lu
Quoted 18 lines · Jean-Philippe Brucker
Quoted 18 lines
(quoted diff) +18 -0
+struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+	ioasid_t max_pasid = 0;
+	int ret = -EINVAL;
+
+	/* Allocate mm->pasid if necessary. */
+	if (!dev->iommu->iommu_dev->pasids)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (dev_is_pci(dev)) {
+		max_pasid = pci_max_pasids(to_pci_dev(dev));
+		if (max_pasid < 0)
+			return ERR_PTR(max_pasid);
+	} else {
+		ret = device_property_read_u32(dev, "pasid-num-bits",
+					       &max_pasid);
Quoted 8 lines

Review

Quoted 4 lines
(quoted diff) +4 -0
+		if (ret)
+			return ERR_PTR(ret);
+		max_pasid = (1UL << max_pasid);
+	}

The IOMMU driver needs this PASID width information earlier, when creating the PASID table (in .probe_device(), .attach_dev()). Since we're moving it to the IOMMU core to avoid code duplication, it should be done earlier and stored in dev->iommu

Yes, really. How about below changes?

From f1382579e8a15ca49acdf758d38fd36451ea174d Mon Sep 17 00:00:00 2001
From: Lu Baolu <[email protected]>
Date: Mon, 28 Feb 2022 15:01:35 +0800
Subject: [PATCH 1/1] iommu: Add pasids field in struct dev_iommu

Use this field to save the number of PASIDs that a device is able to consume. It is a generic attribute of a device and lifting it into the per-device dev_iommu struct could help to avoid the boilerplate code in various IOMMU drivers.

---
 drivers/iommu/iommu.c | 15 +++++++++++++++
 include/linux/iommu.h |  2 ++
 2 files changed, 17 insertions(+)
drivers/iommu/iommu.c +5 -0
index e49c5a5b8cc1..6b731171d42f 100644
@@ -20,6 +20,7 @@
 #include <linux/idr.h>
 #include <linux/err.h>
 #include <linux/pci.h>
+#include <linux/pci-ats.h>
 #include <linux/bitops.h>
 #include <linux/property.h>
 #include <linux/fsl/mc.h>
@@ -194,6 +195,8 @@ EXPORT_SYMBOL_GPL(iommu_device_unregister);
 static struct dev_iommu *dev_iommu_get(struct device *dev)
 {
 	struct dev_iommu *param = dev->iommu;
+	u32 max_pasids = 0;
+	int ret;
 
 	if (param)
 		return param;
@@ -202,6 +205,18 @@ static struct dev_iommu *dev_iommu_get(struct device
 *dev)
 	if (!param)
 		return NULL;
 
+	if (dev_is_pci(dev)) {
+		ret = pci_max_pasids(to_pci_dev(dev));

drivers/iommu/iommu.c static struct dev_iommu *dev_iommu_get(struct device · line 220

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+		if (ret > 0)
+			max_pasids = ret;
+	} else {
+		ret = device_property_read_u32(dev, "pasid-num-bits",
+					       &max_pasids);
+		if (!ret)
+			max_pasids = (1UL << max_pasids);
+	}
+	param->pasids = max_pasids;
+

we could also do a min() with the IOMMU PASID size here

include/linux/iommu.h struct iommu_fault_param { · line 374

Quoted 12 lines
drivers/iommu/iommu.c +0 -0
 	mutex_init(&param->lock);
 	dev->iommu = param;
drivers/iommu/iommu.c +0 -0
 	return param;
include/linux/iommu.h +1 -0
index 45f274b2640d..d4296136ba75 100644
@@ -371,6 +371,7 @@ struct iommu_fault_param {
  * @fwspec:	 IOMMU fwspec data
  * @iommu_dev:	 IOMMU device this device is linked to
  * @priv:	 IOMMU Driver private data
+ * @pasids:	 number of supported PASIDs

'max_pasids' to stay consistent?

Thanks,
Jean

Quoted 16 lines
include/linux/iommu.h +1 -0
  *
  * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
  *	struct iommu_group	*iommu_group;
@@ -382,6 +383,7 @@ struct dev_iommu {
 	struct iommu_fwspec		*fwspec;
 	struct iommu_device		*iommu_dev;
 	void				*priv;
+	u32				pasids;
 };
 
 int iommu_device_register(struct iommu_device *iommu,
Signature · 4 lines
2.25.1

Best regards,
baolu

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

author maintainer
#38 lore raw

Re: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

Quoted 86 lines · Jean-Philippe Brucker
Quoted 73 lines · Baolu Lu
Quoted 18 lines · Jean-Philippe Brucker
Quoted 18 lines
(quoted diff) +18 -0
+struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+	ioasid_t max_pasid = 0;
+	int ret = -EINVAL;
+
+	/* Allocate mm->pasid if necessary. */
+	if (!dev->iommu->iommu_dev->pasids)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (dev_is_pci(dev)) {
+		max_pasid = pci_max_pasids(to_pci_dev(dev));
+		if (max_pasid < 0)
+			return ERR_PTR(max_pasid);
+	} else {
+		ret = device_property_read_u32(dev, "pasid-num-bits",
+					       &max_pasid);
Quoted 8 lines

Review

Quoted 4 lines
(quoted diff) +4 -0
+		if (ret)
+			return ERR_PTR(ret);
+		max_pasid = (1UL << max_pasid);
+	}

The IOMMU driver needs this PASID width information earlier, when creating the PASID table (in .probe_device(), .attach_dev()). Since we're moving it to the IOMMU core to avoid code duplication, it should be done earlier and stored in dev->iommu

Yes, really. How about below changes?

From f1382579e8a15ca49acdf758d38fd36451ea174d Mon Sep 17 00:00:00 2001
From: Lu Baolu<[email protected]>
Date: Mon, 28 Feb 2022 15:01:35 +0800
Subject: [PATCH 1/1] iommu: Add pasids field in struct dev_iommu

Use this field to save the number of PASIDs that a device is able to consume. It is a generic attribute of a device and lifting it into the per-device dev_iommu struct could help to avoid the boilerplate code in various IOMMU drivers.

---
  drivers/iommu/iommu.c | 15 +++++++++++++++
  include/linux/iommu.h |  2 ++
  2 files changed, 17 insertions(+)
drivers/iommu/iommu.c +5 -0
index e49c5a5b8cc1..6b731171d42f 100644
@@ -20,6 +20,7 @@
  #include <linux/idr.h>
  #include <linux/err.h>
  #include <linux/pci.h>
+#include <linux/pci-ats.h>
  #include <linux/bitops.h>
  #include <linux/property.h>
  #include <linux/fsl/mc.h>
@@ -194,6 +195,8 @@ EXPORT_SYMBOL_GPL(iommu_device_unregister);
  static struct dev_iommu *dev_iommu_get(struct device *dev)
  {
  	struct dev_iommu *param = dev->iommu;
+	u32 max_pasids = 0;
+	int ret;
 
  	if (param)
  		return param;
@@ -202,6 +205,18 @@ static struct dev_iommu *dev_iommu_get(struct device
 *dev)
  	if (!param)
  		return NULL;
 
+	if (dev_is_pci(dev)) {
+		ret = pci_max_pasids(to_pci_dev(dev));

drivers/iommu/iommu.c static struct dev_iommu *dev_iommu_get(struct device · line 220

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+		if (ret > 0)
+			max_pasids = ret;
+	} else {
+		ret = device_property_read_u32(dev, "pasid-num-bits",
+					       &max_pasids);
+		if (!ret)
+			max_pasids = (1UL << max_pasids);
+	}
+	param->pasids = max_pasids;
+

we could also do a min() with the IOMMU PASID size here

Quoted 13 lines

include/linux/iommu.h struct iommu_fault_param { · line 374

Quoted 12 lines
drivers/iommu/iommu.c +0 -0
  	mutex_init(&param->lock);
  	dev->iommu = param;

return param;

include/linux/iommu.h +1 -0
index 45f274b2640d..d4296136ba75 100644
@@ -371,6 +371,7 @@ struct iommu_fault_param {
   * @fwspec:	 IOMMU fwspec data
   * @iommu_dev:	 IOMMU device this device is linked to
   * @priv:	 IOMMU Driver private data
+ * @pasids:	 number of supported PASIDs

'max_pasids' to stay consistent?

Both done. How about below changes?

From 008c73b9c0ad51a4a70a18d60361a76c28a63342 Mon Sep 17 00:00:00 2001
From: Lu Baolu <[email protected]>
Date: Mon, 28 Feb 2022 15:01:35 +0800
Subject: [PATCH 1/1] iommu: Add max_pasids field in struct dev_iommu

Use this field to save the number of PASIDs that a device is able to consume. It is a generic attribute of a device and lifting it into the per-device dev_iommu struct could help to avoid the boilerplate code in various IOMMU drivers.

---
 drivers/iommu/iommu.c | 26 ++++++++++++++++++++++++++
 include/linux/iommu.h |  2 ++
 2 files changed, 28 insertions(+)
drivers/iommu/iommu.c +25 -0
index 847ad47a2dfd..365d0f2b7f55 100644
@@ -20,6 +20,7 @@
 #include <linux/idr.h>
 #include <linux/err.h>
 #include <linux/pci.h>
+#include <linux/pci-ats.h>
 #include <linux/bitops.h>
 #include <linux/property.h>
 #include <linux/fsl/mc.h>
@@ -218,6 +219,30 @@ static void dev_iommu_free(struct device *dev)
 	kfree(param);
 }
 
+static u32 dev_iommu_get_max_pasids(struct device *dev)
+{
+	u32 max_pasids = dev->iommu->iommu_dev->max_pasids;
+	u32 num_bits;
+	int ret;
+
+	if (!max_pasids)
+		return 0;
+
+	if (dev_is_pci(dev)) {
+		ret = pci_max_pasids(to_pci_dev(dev));
+		if (ret < 0)
+			return 0;
+
+		return min_t(u32, max_pasids, ret);
+	}
+
+	ret = device_property_read_u32(dev, "pasid-num-bits", &num_bits);
+	if (ret)
+		return 0;
+
+	return min_t(u32, max_pasids, 1UL << num_bits);
+}
+
 static int __iommu_probe_device(struct device *dev, struct list_head 

*group_list)
{
const struct iommu_ops *ops = dev->bus->iommu_ops;
@@ -242,6 +267,7 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
goto out_module_put;
}

+ iommu_dev->max_pasids = dev_iommu_get_max_pasids(dev);
dev->iommu->iommu_dev = iommu_dev;

group = iommu_group_get_for_dev(dev);

include/linux/iommu.h +2 -0
index 03fbb1b71536..d50afb2c9a09 100644
@@ -364,6 +364,7 @@ struct iommu_fault_param {
  * @fwspec:	 IOMMU fwspec data
  * @iommu_dev:	 IOMMU device this device is linked to
  * @priv:	 IOMMU Driver private data
+ * @max_pasids:  number of PASIDs device can consume
  *
  * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
  *	struct iommu_group	*iommu_group;
@@ -375,6 +376,7 @@ struct dev_iommu {
 	struct iommu_fwspec		*fwspec;
 	struct iommu_device		*iommu_dev;
 	void				*priv;
+	u32				max_pasids;
 };
 
 int iommu_device_register(struct iommu_device *iommu,

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

author maintainer
#13 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Lu Baolu
Quoted 57 lines · Lu Baolu

The iommu_sva_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

---
  include/linux/iommu.h         | 51 +++++++++++++++++++++++++
  drivers/iommu/iommu-sva-lib.h | 15 ++++++++
  drivers/iommu/iommu-sva-lib.c | 48 +++++++++++++++++++++++
  drivers/iommu/iommu.c         | 71 +++++++++++++++++++++++++++++++++++
  4 files changed, 185 insertions(+)
include/linux/iommu.h +5 -0
index 0c358b7c583b..e8cf82d46ce1 100644
@@ -64,6 +64,9 @@ struct iommu_domain_geometry {
  #define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
  #define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
 
+#define __IOMMU_DOMAIN_SHARED	(1U << 4)  /* Page table shared from CPU  */
+#define __IOMMU_DOMAIN_HOST_VA	(1U << 5)  /* Host CPU virtual address */
+
  /*
   * This are the possible domain-types
   *
@@ -86,6 +89,8 @@ struct iommu_domain_geometry {
  #define IOMMU_DOMAIN_DMA_FQ	(__IOMMU_DOMAIN_PAGING |	\
  				 __IOMMU_DOMAIN_DMA_API |	\
  				 __IOMMU_DOMAIN_DMA_FQ)
+#define IOMMU_DOMAIN_SVA	(__IOMMU_DOMAIN_SHARED |	\
+				 __IOMMU_DOMAIN_HOST_VA)
 
  struct iommu_domain {
  	unsigned type;

include/linux/iommu.h struct iommu_ops { · line 262

Quoted 4 lines
include/linux/iommu.h +1 -0
@@ -254,6 +259,7 @@ struct iommu_ops {
  	int (*def_domain_type)(struct device *dev);
 
  	const struct iommu_domain_ops *default_domain_ops;
+	const struct iommu_domain_ops *sva_domain_ops;

Per Joerg's comment in anther thread,

https://lore.kernel.org/linux-iommu/[email protected]/

adding a sva_domain_ops here is not the right way to go.

If no objection, I will make the sva domain go through the generic domain_alloc/free() callbacks in the next version.

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

#4 lore raw

RE: [PATCH v7 01/10] iommu: Add pasids field in struct iommu_device

In reply to Lu Baolu
Quoted 24 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

Use this field to keep the number of supported PASIDs that an IOMMU hardware is able to support. This is a generic attribute of an IOMMU and lifting it into the per-IOMMU device structure makes it possible to allocate a PASID for device without calls into the IOMMU drivers. Any iommu driver which suports PASID related features should set this field before enabling them on the devices.

---
 include/linux/iommu.h                       | 2 ++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 +
 drivers/iommu/intel/dmar.c                  | 4 ++++
 3 files changed, 7 insertions(+)
include/linux/iommu.h +0 -0
index 5e1afe169549..da423e87f248 100644
@@ -318,12 +318,14 @@ struct iommu_domain_ops {
  * @list: Used by the iommu-core to keep a list of registered iommus

include/linux/iommu.h struct iommu_domain_ops { · line 328

Quoted 10 lines
include/linux/iommu.h +2 -0
  * @ops: iommu-ops for talking to this iommu
  * @dev: struct device for sysfs handling
+ * @pasids: number of supported PASIDs
  */
 struct iommu_device {
 	struct list_head list;
 	const struct iommu_ops *ops;
 	struct fwnode_handle *fwnode;
 	struct device *dev;
+	u32 pasids;

max_pasid or nr_pasids?

Quoted 22 lines
include/linux/iommu.h +0 -0
 };
 
 /**
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +1 -0
index 88817a3376ef..6e2cd082c670 100644
@@ -3546,6 +3546,7 @@ static int arm_smmu_device_hw_probe(struct
 arm_smmu_device *smmu)
 	/* SID/SSID sizes */
 	smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
 	smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
+	smmu->iommu.pasids = smmu->ssid_bits;
 
 	/*
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +0 -0
 	 * If the SMMU supports fewer bits than would fill a single L2 stream
drivers/iommu/intel/dmar.c +0 -0
index 4de960834a1b..1c3cf267934d 100644

drivers/iommu/intel/dmar.c static int alloc_iommu(struct dmar_drhd_unit · line 1133

Quoted 8 lines
drivers/iommu/intel/dmar.c +4 -0
@@ -1126,6 +1126,10 @@ static int alloc_iommu(struct dmar_drhd_unit
 *drhd)
 
 	raw_spin_lock_init(&iommu->register_lock);
 
+	/* Supports full 20-bit PASID in scalable mode. */
+	if (ecap_pasid(iommu->ecap))
+		iommu->iommu.pasids = 1UL << 20;
+

supported pasid bits is reported by ecap_pss(). I don't think we should assume 20bits here.

Quoted 5 lines
drivers/iommu/intel/dmar.c +0 -0
 	/*
 	 * This is only for hotplug; at boot time intel_iommu_enabled won't

* be set yet. When intel_iommu_init() runs, it registers the units
--
2.25.1

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

Reviewed-by on v7 2/10
#9 lore raw

RE: [PATCH v7 02/10] iommu: Remove SVM_FLAG_SUPERVISOR_MODE support

In reply to Lu Baolu
Quoted 22 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The current kernel DMA with PASID support is based on the SVA with a flag SVM_FLAG_SUPERVISOR_MODE. The IOMMU driver binds the kernel memory address
space to a PASID of the device. The device driver programs the device with kernel virtual address (KVA) for DMA access. There have been security and functional issues with this approach:

- The lack of IOTLB synchronization upon kernel page table updates. (vmalloc, module/BPF loading, CONFIG_DEBUG_PAGEALLOC etc.)
- Other than slight more protection, using kernel virtual address (KVA) has little advantage over physical address. There are also no use cases yet where DMA engines need kernel virtual addresses for in-kernel DMA.

This removes SVM_FLAG_SUPERVISOR_MODE support from the IOMMU interface.
The device drivers are suggested to handle kernel DMA with PASID through the kernel DMA APIs.

Quoted 8 lines

The drvdata parameter in iommu_sva_bind_device() and all callbacks is not needed anymore. Cleanup them as well.

iommu/[email protected]/

Quoted 387 lines
---
 include/linux/intel-iommu.h                   |  3 +-
 include/linux/intel-svm.h                     | 13 -----
 include/linux/iommu.h                         |  8 +--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  5 +-
 drivers/dma/idxd/cdev.c                       |  2 +-
 drivers/dma/idxd/init.c                       | 24 +-------
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  3 +-
 drivers/iommu/intel/svm.c                     | 57 +++++--------------
 drivers/iommu/iommu.c                         |  5 +-
 drivers/misc/uacce/uacce.c                    |  2 +-
 10 files changed, 26 insertions(+), 96 deletions(-)
include/linux/intel-iommu.h +1 -2
index 4f29139bbfc3..df23300cfa88 100644
@@ -739,8 +739,7 @@ struct intel_iommu *device_to_iommu(struct device
 *dev, u8 *bus, u8 *devfn);
 extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct
 *mm,
-				 void *drvdata);
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct
 *mm);

void intel_svm_unbind(struct iommu_sva *handle);
u32 intel_svm_get_pasid(struct iommu_sva *handle);
int intel_svm_page_response(struct device *dev, struct iommu_fault_event
*evt,

include/linux/intel-svm.h +0 -2
index 207ef06ba3e1..f9a0d44f6fdb 100644
@@ -13,17 +13,4 @@
 #define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
 #define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
 
-/*
- * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be

used only
- * for access to kernel addresses. No IOTLB flushes are automatically done
- * for kernel mappings; it is valid only for access to the kernel's static
- * 1:1 mapping of physical memory — not to vmalloc or even module mappings.
- * A future API addition may permit the use of such ranges, by means of an
- * explicit IOTLB flush call (akin to the DMA API's unmap method).
- *
- * It is unlikely that we will ever hook into flush_tlb_kernel_range() to
- * do such IOTLB flushes automatically.
- */

include/linux/intel-svm.h +0 -2
-#define SVM_FLAG_SUPERVISOR_MODE	BIT(0)
-
 #endif /* __INTEL_SVM_H__ */
include/linux/iommu.h +1 -2
index da423e87f248..0c358b7c583b 100644
@@ -243,8 +243,7 @@ struct iommu_ops {
 	int (*dev_enable_feat)(struct device *dev, enum
 iommu_dev_features f);
 	int (*dev_disable_feat)(struct device *dev, enum
 iommu_dev_features f);
 
-	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct
 *mm,
-				      void *drvdata);
+	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct

*mm);

include/linux/iommu.h +1 -2
 	void (*sva_unbind)(struct iommu_sva *handle);
 	u32 (*sva_get_pasid)(struct iommu_sva *handle);
@@ -667,8 +666,7 @@ int iommu_dev_disable_feature(struct device *dev,
 enum iommu_dev_features f);
 bool iommu_dev_feature_enabled(struct device *dev, enum
 iommu_dev_features f);
 
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
-					struct mm_struct *mm,
-					void *drvdata);
+					struct mm_struct *mm);
 void iommu_sva_unbind_device(struct iommu_sva *handle);

u32 iommu_sva_get_pasid(struct iommu_sva *handle);

include/linux/iommu.h +1 -1
@@ -1010,7 +1008,7 @@ iommu_dev_disable_feature(struct device *dev,
 enum iommu_dev_features feat)
 }
 
 static inline struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void
 *drvdata)
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
include/linux/iommu.h +0 -0
 	return NULL;
 }
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +1 -2
index cd48590ada30..d2ba86470c42 100644
@@ -754,8 +754,7 @@ bool arm_smmu_master_sva_enabled(struct
 arm_smmu_master *master);
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
 bool arm_smmu_master_iopf_supported(struct arm_smmu_master
 *master);
-struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct
 mm_struct *mm,
-				    void *drvdata);
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct

mm_struct *mm);
void arm_smmu_sva_unbind(struct iommu_sva *handle); u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle); void arm_smmu_sva_notifier_synchronize(void);

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +0 -0
@@ -791,7 +790,7 @@ static inline bool

arm_smmu_master_iopf_supported(struct arm_smmu_master *master
}

static inline struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +1 -0
+arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 {
 	return ERR_PTR(-ENODEV);
 }
drivers/dma/idxd/cdev.c +1 -1
index b9b2b4a4124e..312ec37ebf91 100644
@@ -100,7 +100,7 @@ static int idxd_cdev_open(struct inode *inode, struct
 file *filp)
 	filp->private_data = ctx;
 
 	if (device_pasid_enabled(idxd)) {
-		sva = iommu_sva_bind_device(dev, current->mm, NULL);
+		sva = iommu_sva_bind_device(dev, current->mm);
 		if (IS_ERR(sva)) {
 			rc = PTR_ERR(sva);
drivers/dma/idxd/cdev.c +0 -0
 			dev_err(dev, "pasid allocation failed: %d\n", rc);
drivers/dma/idxd/init.c +1 -23
index 993a5dcca24f..1fd80c63248a 100644
@@ -466,29 +466,7 @@ static struct idxd_device *idxd_alloc(struct pci_dev
 *pdev, struct idxd_driver_d
 
 static int idxd_enable_system_pasid(struct idxd_device *idxd)
 {
-	int flags;
-	unsigned int pasid;
-	struct iommu_sva *sva;
-
-	flags = SVM_FLAG_SUPERVISOR_MODE;
-
-	sva = iommu_sva_bind_device(&idxd->pdev->dev, NULL, &flags);
-	if (IS_ERR(sva)) {
-		dev_warn(&idxd->pdev->dev,
-			 "iommu sva bind failed: %ld\n", PTR_ERR(sva));
-		return PTR_ERR(sva);
-	}
-
-	pasid = iommu_sva_get_pasid(sva);
-	if (pasid == IOMMU_PASID_INVALID) {
-		iommu_sva_unbind_device(sva);
-		return -ENODEV;
-	}
-
-	idxd->sva = sva;
-	idxd->pasid = pasid;
-	dev_dbg(&idxd->pdev->dev, "system pasid: %u\n", pasid);
-	return 0;
+	return -EOPNOTSUPP;
 }
 

static void idxd_disable_system_pasid(struct idxd_device *idxd)

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +1 -2
index 1ef7bbb4acf3..f155d406c5d5 100644
@@ -367,8 +367,7 @@ __arm_smmu_sva_bind(struct device *dev, struct
 mm_struct *mm)
 	return ERR_PTR(ret);
 }
 
-struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void
 *drvdata)
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct
 mm_struct *mm)

{

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +0 -0
 	struct iommu_sva *handle;
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
drivers/iommu/intel/svm.c +1 -2
index 7ee37d996e15..d04880a291c3 100644
@@ -313,8 +313,7 @@ static int pasid_to_svm_sdev(struct device *dev,
 unsigned int pasid,
 	return 0;
 }
 
-static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
-				 unsigned int flags)
+static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm)
 {
 	ioasid_t max_pasid = dev_is_pci(dev) ?

pci_max_pasids(to_pci_dev(dev)) :
intel_pasid_max_id;

drivers/iommu/intel/svm.c +1 -2
@@ -324,8 +323,7 @@ static int intel_svm_alloc_pasid(struct device *dev,
 struct mm_struct *mm,
 
 static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 					   struct device *dev,
-					   struct mm_struct *mm,
-					   unsigned int flags)
+					   struct mm_struct *mm)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
drivers/iommu/intel/svm.c +6 -10
 	unsigned long iflags, sflags;
@@ -341,22 +339,18 @@ static struct iommu_sva
 *intel_svm_bind_mm(struct intel_iommu *iommu,
 
 		svm->pasid = mm->pasid;
 		svm->mm = mm;
-		svm->flags = flags;
 		INIT_LIST_HEAD_RCU(&svm->devs);
 
-		if (!(flags & SVM_FLAG_SUPERVISOR_MODE)) {
-			svm->notifier.ops = &intel_mmuops;
-			ret = mmu_notifier_register(&svm->notifier, mm);
-			if (ret) {
-				kfree(svm);
-				return ERR_PTR(ret);
-			}
+		svm->notifier.ops = &intel_mmuops;
+		ret = mmu_notifier_register(&svm->notifier, mm);
+		if (ret) {
+			kfree(svm);
+			return ERR_PTR(ret);
 		}
 
 		ret = pasid_private_add(svm->pasid, svm);
 		if (ret) {
-			if (svm->notifier.ops)
-				mmu_notifier_unregister(&svm->notifier,
 mm);
+			mmu_notifier_unregister(&svm->notifier, mm);
 			kfree(svm);
drivers/iommu/intel/svm.c +1 -3
 			return ERR_PTR(ret);
 		}
@@ -391,9 +385,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct
 intel_iommu *iommu,
 	}
 
 	/* Setup the pasid table: */
-	sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?
-			PASID_FLAG_SUPERVISOR_MODE : 0;
-	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ?
 PASID_FLAG_FL5LP : 0;
+	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ?
 PASID_FLAG_FL5LP : 0;
drivers/iommu/intel/svm.c +0 -0
 	spin_lock_irqsave(&iommu->lock, iflags);
 	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm-
Quoted 1 line

pasid,

drivers/iommu/intel/svm.c +1 -2
 					    FLPT_DEFAULT_DID, sflags);
@@ -410,8 +402,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct
 intel_iommu *iommu,
 	kfree(sdev);
 free_svm:
 	if (list_empty(&svm->devs)) {
-		if (svm->notifier.ops)
-			mmu_notifier_unregister(&svm->notifier, mm);
+		mmu_notifier_unregister(&svm->notifier, mm);
 		pasid_private_remove(mm->pasid);
 		kfree(svm);
drivers/iommu/intel/svm.c +0 -0
 	}
@@ -767,7 +758,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			 * to unbind the mm while any page faults are

outstanding.

drivers/iommu/intel/svm.c +0 -1
 			 */
 			svm = pasid_private_find(req->pasid);
-			if (IS_ERR_OR_NULL(svm) || (svm->flags &

SVM_FLAG_SUPERVISOR_MODE))

drivers/iommu/intel/svm.c +4 -23
+			if (IS_ERR_OR_NULL(svm))
 				goto bad_req;
 		}
@@ -818,40 +809,20 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 	return IRQ_RETVAL(handled);
 }
 
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct
 *mm, void *drvdata)
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct
 *mm)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
-	unsigned int flags = 0;
 	struct iommu_sva *sva;
 	int ret;
 
-	if (drvdata)
-		flags = *(unsigned int *)drvdata;
-
-	if (flags & SVM_FLAG_SUPERVISOR_MODE) {
-		if (!ecap_srs(iommu->ecap)) {
-			dev_err(dev, "%s: Supervisor PASID not supported\n",
-				iommu->name);
-			return ERR_PTR(-EOPNOTSUPP);
-		}
-
-		if (mm) {
-			dev_err(dev, "%s: Supervisor PASID with user
 provided mm\n",
-				iommu->name);
-			return ERR_PTR(-EINVAL);
-		}
-
-		mm = &init_mm;
-	}
-
 	mutex_lock(&pasid_mutex);
-	ret = intel_svm_alloc_pasid(dev, mm, flags);
+	ret = intel_svm_alloc_pasid(dev, mm);
 	if (ret) {
 		mutex_unlock(&pasid_mutex);
 		return ERR_PTR(ret);
 	}
 
-	sva = intel_svm_bind_mm(iommu, dev, mm, flags);
+	sva = intel_svm_bind_mm(iommu, dev, mm);
drivers/iommu/intel/svm.c +0 -0
 	mutex_unlock(&pasid_mutex);
 
 	return sva;
drivers/iommu/iommu.c +0 -1
index 847ad47a2dfd..9955f58bd08c 100644
@@ -2768,7 +2768,6 @@
 EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
  * iommu_sva_bind_device() - Bind a process address space to a device
  * @dev: the device
  * @mm: the mm to bind, caller must hold a reference to it
- * @drvdata: opaque data pointer to pass to bind callback
  *
  * Create a bond between device and address space, allowing the device to

access
* the mm using the returned PASID. If a bond already exists between
@device and

drivers/iommu/iommu.c +1 -1
@@ -2781,7 +2780,7 @@
 EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled);
  * On error, returns an ERR_PTR value.
  */
 struct iommu_sva *
-iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void
 *drvdata)
+iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
drivers/iommu/iommu.c +1 -1
 	struct iommu_group *group;
 	struct iommu_sva *handle = ERR_PTR(-EINVAL);
@@ -2806,7 +2805,7 @@ iommu_sva_bind_device(struct device *dev, struct
 mm_struct *mm, void *drvdata)
 	if (iommu_group_device_count(group) != 1)
 		goto out_unlock;
 
-	handle = ops->sva_bind(dev, mm, drvdata);
+	handle = ops->sva_bind(dev, mm);
 
 out_unlock:
drivers/iommu/iommu.c +0 -0
 	mutex_unlock(&group->mutex);
drivers/misc/uacce/uacce.c +1 -1
index 281c54003edc..3238a867ea51 100644
@@ -99,7 +99,7 @@ static int uacce_bind_queue(struct uacce_device *uacce,
 struct uacce_queue *q)
 	if (!(uacce->flags & UACCE_DEV_SVA))
 		return 0;
 
-	handle = iommu_sva_bind_device(uacce->parent, current->mm,
 NULL);
+	handle = iommu_sva_bind_device(uacce->parent, current->mm);
 	if (IS_ERR(handle))

return PTR_ERR(handle);

Quoted 2 lines

--
2.25.1

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

#16 lore raw

RE: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Lu Baolu
Quoted 23 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The iommu_sva_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain
type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

Quoted 3 lines

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

usually we have 'set/clear' pair or 'allow/block'. Having 'set' paired with 'block' doesn't read very clearly.

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3259

Quoted 3 lines
drivers/iommu/iommu.c +3 -0
+static bool device_group_immutable_singleton(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);

what about passing group as the parameter since the caller will get the group again right after calling this function? In that case the function could be renamed as:

iommu_group_immutable_singleton()

or be shorter:

iommu_group_fixed_singleton()

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3271

Quoted 12 lines
drivers/iommu/iommu.c +12 -0
+	int count;
+
+	if (!group)
+		return false;
+
+	mutex_lock(&group->mutex);
+	count = iommu_group_device_count(group);
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	if (count != 1)
+		return false;

For non-pci devices above doesn't check anything against immutable. Please add some comment to explain why doing so is correct.

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3284

Quoted 13 lines
drivers/iommu/iommu.c +13 -0
+
+	/*
+	 * The PCI device could be considered to be fully isolated if all
+	 * devices on the path from the device to the host-PCI bridge are
+	 * protected from peer-to-peer DMA by ACS.
+	 */
+	if (dev_is_pci(dev))
+		return pci_acs_path_enabled(to_pci_dev(dev), NULL,
+					    REQ_ACS_FLAGS);
+
+	return true;
+}
+

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

#14 lore raw

RE: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Baolu Lu
Quoted 10 lines

From: Baolu Lu <[email protected]>
Sent: Monday, May 23, 2022 3:13 PM

include/linux/iommu.h struct iommu_ops { · line 262

Quoted 5 lines
include/linux/iommu.h +1 -0
@@ -254,6 +259,7 @@ struct iommu_ops {
  	int (*def_domain_type)(struct device *dev);
 
  	const struct iommu_domain_ops *default_domain_ops;
+	const struct iommu_domain_ops *sva_domain_ops;

Per Joerg's comment in anther thread,

Quoted 7 lines

https://lore.kernel.org/linux-iommu/[email protected]/

adding a sva_domain_ops here is not the right way to go.

If no objection, I will make the sva domain go through the generic domain_alloc/free() callbacks in the next version.

suppose it's just back to what v1-v6 did which all registered the ops in domain_alloc() callback?
_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

#39 lore raw

RE: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Lu Baolu
Quoted 7 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need for any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops.

set/block_pasid_dev, to be consistent.

drivers/iommu/iommu-sva-lib.c int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev, · line 173

Quoted 10 lines
drivers/iommu/iommu-sva-lib.c +10 -0
+
+	mutex_lock(&iommu_sva_lock);
+	/* Search for an existing domain. */
+	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid);
+	if (domain) {
+		sva_domain = to_sva_domain(domain);
+		refcount_inc(&sva_domain->bond.users);
+		goto out_success;
+	}
+

why would one device/pasid be bound to a mm more than once?
_______________________________________________
iommu mailing list [email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Reviewed-by on v7 7/10
#45 lore raw

RE: [PATCH v7 07/10] iommu: Remove SVA related callbacks from iommu ops

In reply to Lu Baolu
Quoted 9 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

These ops'es have been replaced with the dev_attach/detach_pasid domain ops'es. There's no need for them anymore. Remove them to avoid dead code.

Quoted 256 lines
---
 include/linux/intel-iommu.h                   |  3 --
 include/linux/iommu.h                         |  7 ---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   | 16 ------
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   | 40 ---------------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   |  3 --
 drivers/iommu/intel/iommu.c                   |  3 --
 drivers/iommu/intel/svm.c                     | 49 -------------------
 7 files changed, 121 deletions(-)
include/linux/intel-iommu.h +0 -3
index 5e88eaa245aa..536f229fd274 100644
@@ -739,9 +739,6 @@ struct intel_iommu *device_to_iommu(struct device
 *dev, u8 *bus, u8 *devfn);
 extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct
 *mm);
-void intel_svm_unbind(struct iommu_sva *handle);
-u32 intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event

*evt,

include/linux/intel-iommu.h +0 -0
 			    struct iommu_page_response *msg);
 int intel_svm_attach_dev_pasid(struct iommu_domain *domain,
include/linux/iommu.h +0 -0
index d9ac5ebe5bbb..e4ce2fe0e144 100644
@@ -212,9 +212,6 @@ struct iommu_iotlb_gather {
  * @dev_has/enable/disable_feat: per device entries to

check/enable/disable
* iommu specific features.
* @dev_feat_enabled: check enabled feature
- * @sva_bind: Bind process address space to device
- * @sva_unbind: Unbind process address space from device
- * @sva_get_pasid: Get PASID associated to a SVA handle
* @page_response: handle page request response
* @def_domain_type: device default domain type, return value:
* - IOMMU_DOMAIN_IDENTITY: must use an identity domain

include/linux/iommu.h +0 -4
@@ -248,10 +245,6 @@ struct iommu_ops {
 	int (*dev_enable_feat)(struct device *dev, enum
 iommu_dev_features f);
 	int (*dev_disable_feat)(struct device *dev, enum
 iommu_dev_features f);
 
-	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct
 *mm);
-	void (*sva_unbind)(struct iommu_sva *handle);
-	u32 (*sva_get_pasid)(struct iommu_sva *handle);
-
include/linux/iommu.h +0 -0
 	int (*page_response)(struct device *dev,
 			     struct iommu_fault_event *evt,
 			     struct iommu_page_response *msg);
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +0 -3
index ec77f6a51ff9..0f0f5ba26dd5 100644
@@ -754,9 +754,6 @@ bool arm_smmu_master_sva_enabled(struct
 arm_smmu_master *master);
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
 bool arm_smmu_master_iopf_supported(struct arm_smmu_master
 *master);
-struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct
 mm_struct *mm);
-void arm_smmu_sva_unbind(struct iommu_sva *handle);
-u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);

void arm_smmu_sva_notifier_synchronize(void);
int arm_smmu_sva_attach_dev_pasid(struct iommu_domain *domain,

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +0 -0
 				  struct device *dev, ioasid_t id);
@@ -793,19 +790,6 @@ static inline bool

arm_smmu_master_iopf_supported(struct arm_smmu_master *master

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +0 -13
 	return false;
 }
 
-static inline struct iommu_sva *
-arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
-{
-	return ERR_PTR(-ENODEV);
-}
-
-static inline void arm_smmu_sva_unbind(struct iommu_sva *handle) {}
-
-static inline u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
-{
-	return IOMMU_PASID_INVALID;
-}
-
 static inline void arm_smmu_sva_notifier_synchronize(void) {}
 #endif /* CONFIG_ARM_SMMU_V3_SVA */
 #endif /* _ARM_SMMU_V3_H */
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +0 -5
index 6969974ca89e..8290d66569f3 100644
@@ -344,11 +344,6 @@ __arm_smmu_sva_bind(struct device *dev, struct
 mm_struct *mm)
 	if (!bond)
 		return ERR_PTR(-ENOMEM);
 
-	/* Allocate a PASID for this mm if necessary */
-	ret = iommu_sva_alloc_pasid(mm, 1, (1U << master->ssid_bits) - 1);
-	if (ret)
-		goto err_free_bond;
-
 	bond->mm = mm;
 	bond->sva.dev = dev;
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +0 -35
 	refcount_set(&bond->refs, 1);
@@ -367,41 +362,6 @@ __arm_smmu_sva_bind(struct device *dev, struct
 mm_struct *mm)
 	return ERR_PTR(ret);
 }
 
-struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct
 mm_struct *mm)
-{
-	struct iommu_sva *handle;
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	struct arm_smmu_domain *smmu_domain =
 to_smmu_domain(domain);
-
-	if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1)
-		return ERR_PTR(-EINVAL);
-
-	mutex_lock(&sva_lock);
-	handle = __arm_smmu_sva_bind(dev, mm);
-	mutex_unlock(&sva_lock);
-	return handle;
-}
-
-void arm_smmu_sva_unbind(struct iommu_sva *handle)
-{
-	struct arm_smmu_bond *bond = sva_to_bond(handle);
-
-	mutex_lock(&sva_lock);
-	if (refcount_dec_and_test(&bond->refs)) {
-		list_del(&bond->list);
-		arm_smmu_mmu_notifier_put(bond->smmu_mn);
-		kfree(bond);
-	}
-	mutex_unlock(&sva_lock);
-}
-
-u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
-{
-	struct arm_smmu_bond *bond = sva_to_bond(handle);
-
-	return bond->mm->pasid;
-}
-

bool arm_smmu_sva_supported(struct arm_smmu_device *smmu) {

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +0 -0
 	unsigned long reg, fld;
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +0 -3
index 4ad3ca70cf89..b74f8964cc13 100644
@@ -2852,9 +2852,6 @@ static struct iommu_ops arm_smmu_ops = {
 	.dev_feat_enabled	= arm_smmu_dev_feature_enabled,
 	.dev_enable_feat	= arm_smmu_dev_enable_feature,
 	.dev_disable_feat	= arm_smmu_dev_disable_feature,
-	.sva_bind		= arm_smmu_sva_bind,
-	.sva_unbind		= arm_smmu_sva_unbind,
-	.sva_get_pasid		= arm_smmu_sva_get_pasid,
 	.page_response		= arm_smmu_page_response,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 	.owner			= THIS_MODULE,
drivers/iommu/intel/iommu.c +0 -3
index 2b6a52c87c73..10e07d59d4c8 100644
@@ -4919,9 +4919,6 @@ const struct iommu_ops intel_iommu_ops = {
 	.def_domain_type	= device_def_domain_type,
 	.pgsize_bitmap		= SZ_4K,
 #ifdef CONFIG_INTEL_IOMMU_SVM
-	.sva_bind		= intel_svm_bind,
-	.sva_unbind		= intel_svm_unbind,
-	.sva_get_pasid		= intel_svm_get_pasid,
 	.page_response		= intel_svm_page_response,
 	.sva_domain_ops = &(const struct iommu_domain_ops) {
 		.set_dev_pasid		= intel_svm_attach_dev_pasid,
drivers/iommu/intel/svm.c +0 -8
index d575792441f3..e412a442d9a4 100644
@@ -313,14 +313,6 @@ static int pasid_to_svm_sdev(struct device *dev,
 unsigned int pasid,
 	return 0;
 }
 
-static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm)
-{
-	ioasid_t max_pasid = dev_is_pci(dev) ?
-			pci_max_pasids(to_pci_dev(dev)) :
 intel_pasid_max_id;
-
-	return iommu_sva_alloc_pasid(mm, PASID_MIN, max_pasid - 1);
-}
-
 static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
drivers/iommu/intel/svm.c +0 -41
 					   struct device *dev,
 					   ioasid_t pasid,
@@ -810,47 +802,6 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 	return IRQ_RETVAL(handled);
 }
 
-struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct
 *mm)
-{
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
-	struct iommu_sva *sva;
-	int ret;
-
-	mutex_lock(&pasid_mutex);
-	ret = intel_svm_alloc_pasid(dev, mm);
-	if (ret) {
-		mutex_unlock(&pasid_mutex);
-		return ERR_PTR(ret);
-	}
-
-	sva = intel_svm_bind_mm(iommu, dev, mm->pasid, mm);
-	mutex_unlock(&pasid_mutex);
-
-	return sva;
-}
-
-void intel_svm_unbind(struct iommu_sva *sva)
-{
-	struct intel_svm_dev *sdev = to_intel_svm_dev(sva);
-
-	mutex_lock(&pasid_mutex);
-	intel_svm_unbind_mm(sdev->dev, sdev->pasid);
-	mutex_unlock(&pasid_mutex);
-}
-
-u32 intel_svm_get_pasid(struct iommu_sva *sva)
-{
-	struct intel_svm_dev *sdev;
-	u32 pasid;
-
-	mutex_lock(&pasid_mutex);
-	sdev = to_intel_svm_dev(sva);
-	pasid = sdev->pasid;
-	mutex_unlock(&pasid_mutex);
-
-	return pasid;
-}
-
 int intel_svm_page_response(struct device *dev,
 			    struct iommu_fault_event *evt,
Quoted 3 lines

struct iommu_page_response *msg)
--
2.25.1

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

#40 lore raw

Re: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Tian, Kevin
Quoted 10 lines · Kevin
Quoted 7 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need for any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops.

set/block_pasid_dev, to be consistent.

Quoted 12 lines

drivers/iommu/iommu-sva-lib.c int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev, · line 173

Quoted 10 lines
drivers/iommu/iommu-sva-lib.c +10 -0
+
+	mutex_lock(&iommu_sva_lock);
+	/* Search for an existing domain. */
+	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid);
+	if (domain) {
+		sva_domain = to_sva_domain(domain);
+		refcount_inc(&sva_domain->bond.users);
+		goto out_success;
+	}
+

why would one device/pasid be bound to a mm more than once?

Device drivers can call bind() multiple times for the same device and mm, for example if one process wants to open multiple accelerator queues.

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

#17 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Tian, Kevin
Quoted 23 lines · Kevin
Quoted 23 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The iommu_sva_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain
type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

Quoted 6 lines
Quoted 3 lines

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

usually we have 'set/clear' pair or 'allow/block'. Having 'set' paired with 'block' doesn't read very clearly.

I thought we agreed we'd use the blocking domain for this? Why did it go back to an op?

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

#21 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Lu Baolu
Quoted 176 lines · Lu Baolu

The iommu_sva_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

 include/linux/iommu.h         | 51 +++++++++++++++++++++++++
 drivers/iommu/iommu-sva-lib.h | 15 ++++++++
 drivers/iommu/iommu-sva-lib.c | 48 +++++++++++++++++++++++
 drivers/iommu/iommu.c         | 71 +++++++++++++++++++++++++++++++++++
 4 files changed, 185 insertions(+)
include/linux/iommu.h +52 -0
index 0c358b7c583b..e8cf82d46ce1 100644
+++ b/include/linux/iommu.h
@@ -64,6 +64,9 @@ struct iommu_domain_geometry {
 #define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
 #define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
 
+#define __IOMMU_DOMAIN_SHARED	(1U << 4)  /* Page table shared from CPU  */
+#define __IOMMU_DOMAIN_HOST_VA	(1U << 5)  /* Host CPU virtual address */
+
 /*
  * This are the possible domain-types
  *
@@ -86,6 +89,8 @@ struct iommu_domain_geometry {
 #define IOMMU_DOMAIN_DMA_FQ	(__IOMMU_DOMAIN_PAGING |	\
 				 __IOMMU_DOMAIN_DMA_API |	\
 				 __IOMMU_DOMAIN_DMA_FQ)
+#define IOMMU_DOMAIN_SVA	(__IOMMU_DOMAIN_SHARED |	\
+				 __IOMMU_DOMAIN_HOST_VA)
 
 struct iommu_domain {
 	unsigned type;
@@ -254,6 +259,7 @@ struct iommu_ops {
 	int (*def_domain_type)(struct device *dev);
 
 	const struct iommu_domain_ops *default_domain_ops;
+	const struct iommu_domain_ops *sva_domain_ops;
 	unsigned long pgsize_bitmap;
 	struct module *owner;
 };
@@ -262,6 +268,8 @@ struct iommu_ops {
  * struct iommu_domain_ops - domain specific operations
  * @attach_dev: attach an iommu domain to a device
  * @detach_dev: detach an iommu domain from a device
+ * @set_dev_pasid: set an iommu domain to a pasid of device
+ * @block_dev_pasid: block pasid of device from using iommu domain
  * @map: map a physically contiguous memory region to an iommu domain
  * @map_pages: map a physically contiguous set of pages of the same size to
  *             an iommu domain.
@@ -282,6 +290,10 @@ struct iommu_ops {
 struct iommu_domain_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
+	int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid);
+	void (*block_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+				ioasid_t pasid);
 
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
@@ -677,6 +689,10 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
 void iommu_group_release_dma_owner(struct iommu_group *group);
 bool iommu_group_dma_owner_claimed(struct iommu_group *group);
 
+int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
+			   ioasid_t pasid);
+void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
+			      ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1050,6 +1066,17 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
 {
 	return false;
 }
+
+static inline int iommu_set_device_pasid(struct iommu_domain *domain,
+					 struct device *dev, ioasid_t pasid)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_block_device_pasid(struct iommu_domain *domain,
+					    struct device *dev, ioasid_t pasid)
+{
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**
@@ -1075,4 +1102,28 @@ void iommu_debugfs_setup(void);
 static inline void iommu_debugfs_setup(void) {}
 #endif
 
+#ifdef CONFIG_IOMMU_SVA
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm);
+void iommu_sva_free_domain(struct iommu_domain *domain);
+int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
+			 ioasid_t pasid);
+#else /* CONFIG_IOMMU_SVA */
+static inline struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline void iommu_sva_free_domain(struct iommu_domain *domain)
+{
+}
+
+static inline int iommu_sva_set_domain(struct iommu_domain *domain,
+				       struct device *dev, ioasid_t pasid)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_IOMMU_SVA */
+
 #endif /* __LINUX_IOMMU_H */
drivers/iommu/iommu-sva-lib.h +16 -0
index 8909ea1094e3..1be21e6b93ec 100644
+++ b/drivers/iommu/iommu-sva-lib.h
@@ -7,6 +7,7 @@
 
 #include <linux/ioasid.h>
 #include <linux/mm_types.h>
+#include <linux/iommu.h>
 
 int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max);
 struct mm_struct *iommu_sva_find(ioasid_t pasid);
@@ -16,6 +17,20 @@ struct device;
 struct iommu_fault;
 struct iopf_queue;
 
+struct iommu_sva_domain {
+	struct iommu_domain	domain;
+	struct mm_struct	*mm;
+};
+
+#define to_sva_domain(d) container_of_safe(d, struct iommu_sva_domain, domain)
+
+static inline struct mm_struct *domain_to_mm(struct iommu_domain *domain)
+{
+	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
+
+	return sva_domain->mm;
+}
+
 #ifdef CONFIG_IOMMU_SVA
 int iommu_queue_iopf(struct iommu_fault *fault, void *cookie);
 
drivers/iommu/iommu-sva-lib.c +1 -0
index 106506143896..210c376f6043 100644
+++ b/drivers/iommu/iommu-sva-lib.c

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 77

Quoted 9 lines
drivers/iommu/iommu-sva-lib.c +6 -0
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
 	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

This should return the proper type

Quoted 18 lines
drivers/iommu/iommu-sva-lib.c +18 -0
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+
+	if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
+		return ERR_PTR(-ENODEV);
+
+	sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
+	if (!sva_domain)
+		return ERR_PTR(-ENOMEM);
+
+	mmgrab(mm);
+	sva_domain->mm = mm;
+
+	domain = &sva_domain->domain;
+	domain->type = IOMMU_DOMAIN_SVA;
+	domain->ops = bus->iommu_ops->sva_domain_ops;
+

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 105

Quoted 10 lines
drivers/iommu/iommu-sva-lib.c +10 -0
+	return domain;
+}
+
+void iommu_sva_free_domain(struct iommu_domain *domain)
+{
+	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
+
+	mmdrop(sva_domain->mm);
+	kfree(sva_domain);
+}

No callback to the driver?

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 109

Quoted 3 lines
drivers/iommu/iommu-sva-lib.c +3 -0
+int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
+			 ioasid_t pasid)
+{

Why does this function exist? Just call iommu_set_device_pasid()

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 111

Quoted 3 lines
drivers/iommu/iommu-sva-lib.c +3 -0
+int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
+			   ioasid_t pasid)
+{

Here you can continue to use attach/detach language as at this API level we expect strict pairing..

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid)

Quoted 9 lines
drivers/iommu/iommu-sva-lib.c +9 -0
+void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
+			      ioasid_t pasid)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	mutex_lock(&group->mutex);
+	domain->ops->block_dev_pasid(domain, dev, pasid);
+	xa_erase(&group->pasid_array, pasid);
+	mutex_unlock(&group->mutex);

Should be the blocking domain.

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

reviewer
#26 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Lu Baolu

On 2022-05-19 08:20, Lu Baolu wrote:
[...]

Quoted 5 lines
drivers/iommu/iommu-sva-lib.c +0 -0
index 106506143896..210c376f6043 100644

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 77

Quoted 9 lines
drivers/iommu/iommu-sva-lib.c +6 -0
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
  	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
  }
  EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

Argh, please no new bus-based external interfaces! Domain allocation needs to resolve to the right IOMMU instance to solve a number of issues, and cleaning up existing users of iommu_domain_alloc() to prepare for that is already hard enough. This is arguably even more relevant here than for other domain types, since SVA support is more likely to depend on specific features that can vary between IOMMU instances even with the same driver. Please make the external interface take a struct device, then resolve the ops through dev->iommu.

Further nit: the naming inconsistency bugs me a bit - iommu_sva_domain_alloc() seems more natural. Also I'd question the symmetry vs. usability dichotomy of whether we *really* want two different free functions for a struct iommu_domain pointer, where any caller which might mix SVA and non-SVA usage then has to remember how they allocated any particular domain :/

Quoted 7 lines
drivers/iommu/iommu-sva-lib.c +7 -0
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+
+	if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
+		return ERR_PTR(-ENODEV);
+

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 94

Quoted 10 lines
drivers/iommu/iommu-sva-lib.c +10 -0
+	sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
+	if (!sva_domain)
+		return ERR_PTR(-ENOMEM);
+
+	mmgrab(mm);
+	sva_domain->mm = mm;
+
+	domain = &sva_domain->domain;
+	domain->type = IOMMU_DOMAIN_SVA;
+	domain->ops = bus->iommu_ops->sva_domain_ops;

I'd have thought it would be logical to pass IOMMU_DOMAIN_SVA to the normal domain_alloc call, so that driver-internal stuff like context descriptors can be still be hung off the domain as usual (rather than all drivers having to implement some extra internal lookup mechanism to handle all the SVA domain ops), but that's something we're free to come back and change later. FWIW I'd just stick the mm pointer in struct iommu_domain, in a union with the fault handler stuff and/or iova_cookie - those are mutually exclusive with SVA, right?

Cheers,
Robin.

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 106

Quoted 12 lines
drivers/iommu/iommu-sva-lib.c +12 -0
+
+	return domain;
+}
+
+void iommu_sva_free_domain(struct iommu_domain *domain)
+{
+	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
+
+	mmdrop(sva_domain->mm);
+	kfree(sva_domain);
+}
+

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

#18 lore raw

RE: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Jason Gunthorpe
Quoted 32 lines

From: Jason Gunthorpe <[email protected]>
Sent: Tuesday, May 24, 2022 9:39 PM

Quoted 4 lines · Kevin
Quoted 4 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The iommu_sva_domain represents a hardware pagetable that the

IOMMU

Quoted 23 lines
Quoted 22 lines

hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain
type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

Quoted 6 lines
Quoted 2 lines

usually we have 'set/clear' pair or 'allow/block'. Having 'set' paired with 'block' doesn't read very clearly.

I thought we agreed we'd use the blocking domain for this? Why did it go back to an op?

Probably it's based on following discussion:

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

--

Quoted 2 lines

FWIW from my point of view I'm happy with having a .detach_dev_pasid op meaning implicitly-blocked access for now.

If this is the path then lets not call it attach/detach please. 'set_dev_pasid' and 'set_dev_blocking_pasid' are clearer names.
--

Looks Baolu chooses this path and plans to use the blocking domain later.

Thanks
Kevin

author maintainer
#5 lore raw

Re: [PATCH v7 01/10] iommu: Add pasids field in struct iommu_device

In reply to Tian, Kevin

Hi Kevin,

Thank you for reviewing my patches.

Quoted 28 lines · Kevin
Quoted 28 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

Use this field to keep the number of supported PASIDs that an IOMMU hardware is able to support. This is a generic attribute of an IOMMU and lifting it into the per-IOMMU device structure makes it possible to allocate a PASID for device without calls into the IOMMU drivers. Any iommu driver which suports PASID related features should set this field before enabling them on the devices.

---
  include/linux/iommu.h                       | 2 ++
  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 +
  drivers/iommu/intel/dmar.c                  | 4 ++++
  3 files changed, 7 insertions(+)
include/linux/iommu.h +1 -0
index 5e1afe169549..da423e87f248 100644
@@ -318,12 +318,14 @@ struct iommu_domain_ops {
   * @list: Used by the iommu-core to keep a list of registered iommus
   * @ops: iommu-ops for talking to this iommu
   * @dev: struct device for sysfs handling
+ * @pasids: number of supported PASIDs
   */
Quoted 8 lines

include/linux/iommu.h struct iommu_domain_ops { · line 328

Quoted 6 lines
include/linux/iommu.h +1 -0
  struct iommu_device {
  	struct list_head list;
  	const struct iommu_ops *ops;
  	struct fwnode_handle *fwnode;
  	struct device *dev;
+	u32 pasids;

max_pasid or nr_pasids?

max_pasid looks better.

Quoted 27 lines
Quoted 27 lines
include/linux/iommu.h +0 -0
  };
 
  /**
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +1 -0
index 88817a3376ef..6e2cd082c670 100644
@@ -3546,6 +3546,7 @@ static int arm_smmu_device_hw_probe(struct
 arm_smmu_device *smmu)
  	/* SID/SSID sizes */
  	smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg);
  	smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg);
+	smmu->iommu.pasids = smmu->ssid_bits;
 
  	/*

* If the SMMU supports fewer bits than would fill a single L2 stream

drivers/iommu/intel/dmar.c +0 -0
index 4de960834a1b..1c3cf267934d 100644
@@ -1126,6 +1126,10 @@ static int alloc_iommu(struct dmar_drhd_unit
 *drhd)
 
  	raw_spin_lock_init(&iommu->register_lock);
 
Quoted 7 lines

drivers/iommu/intel/dmar.c static int alloc_iommu(struct dmar_drhd_unit *drhd) · line 1132

Quoted 4 lines
drivers/iommu/intel/dmar.c +4 -0
+	/* Supports full 20-bit PASID in scalable mode. */
+	if (ecap_pasid(iommu->ecap))
+		iommu->iommu.pasids = 1UL << 20;
+

supported pasid bits is reported by ecap_pss(). I don't think we should assume 20bits here.

Yes. I overlooked this. Thanks for reminding.

Another thing I need to improve is that scalable mode could be disabled. This field should be 0 in that case.

Quoted 7 lines
Quoted 6 lines
drivers/iommu/intel/dmar.c +0 -0
  	/*
  	 * This is only for hotplug; at boot time intel_iommu_enabled won't

* be set yet. When intel_iommu_init() runs, it registers the units
--
2.25.1

Best regards,
baolu

#41 lore raw

RE: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Jean-Philippe Brucker
Quoted 27 lines

From: Jean-Philippe Brucker <[email protected]>
Sent: Tuesday, May 24, 2022 6:58 PM

Quoted 10 lines · Kevin
Quoted 7 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need for any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops.

set/block_pasid_dev, to be consistent.

Quoted 12 lines

drivers/iommu/iommu-sva-lib.c int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev, · line 173

Quoted 10 lines
drivers/iommu/iommu-sva-lib.c +10 -0
+
+	mutex_lock(&iommu_sva_lock);
+	/* Search for an existing domain. */
+	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid);
+	if (domain) {
+		sva_domain = to_sva_domain(domain);
+		refcount_inc(&sva_domain->bond.users);
+		goto out_success;
+	}
+

why would one device/pasid be bound to a mm more than once?

Quoted 3 lines

Device drivers can call bind() multiple times for the same device and mm, for example if one process wants to open multiple accelerator queues.

Is it clearer to have a sva_bond_get/put() pair instead of calling bind() multiple times here?
_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

author maintainer
#6 lore raw

Re: [PATCH v7 01/10] iommu: Add pasids field in struct iommu_device

In reply to Baolu Lu
Quoted 17 lines · Baolu Lu
Quoted 9 lines
Quoted 9 lines
drivers/iommu/intel/dmar.c +0 -0
index 4de960834a1b..1c3cf267934d 100644
@@ -1126,6 +1126,10 @@ static int alloc_iommu(struct dmar_drhd_unit
 *drhd)
 
       raw_spin_lock_init(&iommu->register_lock);
 
Quoted 7 lines

drivers/iommu/intel/dmar.c static int alloc_iommu(struct dmar_drhd_unit *drhd) · line 1132

Quoted 4 lines
drivers/iommu/intel/dmar.c +4 -0
+    /* Supports full 20-bit PASID in scalable mode. */
+    if (ecap_pasid(iommu->ecap))
+        iommu->iommu.pasids = 1UL << 20;
+

supported pasid bits is reported by ecap_pss(). I don't think we should assume 20bits here.

Quoted 4 lines

Yes. I overlooked this. Thanks for reminding.

Another thing I need to improve is that scalable mode could be disabled. This field should be 0 in that case.

I will change above to:

+ /*

+         * A value of N in PSS field of eCap register indicates hardware
+         * supports PASID field of N+1 bits.
+         */

+ if (pasid_supported(iommu))
+ iommu->iommu.max_pasids = 2UL << ecap_pss(iommu->ecap);

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

author maintainer
#15 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Tian, Kevin
Quoted 12 lines · Kevin
Quoted 12 lines

From: Baolu Lu <[email protected]>
Sent: Monday, May 23, 2022 3:13 PM

include/linux/iommu.h struct iommu_ops { · line 262

Quoted 5 lines
include/linux/iommu.h +1 -0
@@ -254,6 +259,7 @@ struct iommu_ops {
   	int (*def_domain_type)(struct device *dev);
 
   	const struct iommu_domain_ops *default_domain_ops;
+	const struct iommu_domain_ops *sva_domain_ops;

Per Joerg's comment in anther thread,

https://lore.kernel.org/linux-iommu/[email protected]/

Quoted 8 lines
Quoted 5 lines

adding a sva_domain_ops here is not the right way to go.

If no objection, I will make the sva domain go through the generic domain_alloc/free() callbacks in the next version.

suppose it's just back to what v1-v6 did which all registered the ops in domain_alloc() callback?

Yes.

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

author maintainer
#19 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Tian, Kevin
Quoted 43 lines · Kevin
Quoted 32 lines

From: Jason Gunthorpe <[email protected]>
Sent: Tuesday, May 24, 2022 9:39 PM

Quoted 4 lines · Kevin
Quoted 4 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The iommu_sva_domain represents a hardware pagetable that the

IOMMU

Quoted 23 lines
Quoted 22 lines

hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain
type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

Quoted 6 lines
Quoted 2 lines

usually we have 'set/clear' pair or 'allow/block'. Having 'set' paired with 'block' doesn't read very clearly.

I thought we agreed we'd use the blocking domain for this? Why did it go back to an op?

Probably it's based on following discussion:

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

Quoted 7 lines

--

Quoted 2 lines

FWIW from my point of view I'm happy with having a .detach_dev_pasid op meaning implicitly-blocked access for now.

If this is the path then lets not call it attach/detach please. 'set_dev_pasid' and 'set_dev_blocking_pasid' are clearer names.

Yes. Learning from above discussion, we are about to implement the set_dev_pasid and blocking domain in parallel. We will convert all the callback names to set_dev and set_dev_pasid after blocking domain support is merged.

Quoted 4 lines

--

Looks Baolu chooses this path and plans to use the blocking domain later.

Yes. I have already started to implement the blocking domain in Intel driver. With it as an example, we can extend it to other possible IOMMU drivers.

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

author maintainer
#20 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Tian, Kevin
Quoted 23 lines · Kevin
Quoted 23 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The iommu_sva_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Add a new struct iommu_sva_domain and new IOMMU_DOMAIN_SVA domain
type.
- Add a new domain ops pointer in iommu_ops. The IOMMU drivers that support SVA should provide the callbacks.
- Add helpers to allocate and free an SVA domain.
- Add helpers to set an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

Quoted 6 lines
Quoted 3 lines

The iommu_set/block_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc. Hence, it is put in the iommu.c.

usually we have 'set/clear' pair or 'allow/block'. Having 'set' paired with 'block' doesn't read very clearly.

Yes. Let's still use the attach/detach semantics.

Quoted 9 lines

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3259

Quoted 4 lines
drivers/iommu/iommu.c +3 -0
+static bool device_group_immutable_singleton(struct device *dev)
+{
+	struct iommu_group *group = iommu_group_get(dev);

what about passing group as the parameter since the caller will get the group again right after calling this function? In that case the function could be renamed as:

Quoted 5 lines

iommu_group_immutable_singleton()

or be shorter:

iommu_group_fixed_singleton()

Fair enough. I will tune it as below:

+static bool iommu_group_immutable_singleton(struct iommu_group *group) +{
+ int count;
+

+       mutex_lock(&group->mutex);
+       count = iommu_group_device_count(group);
+       mutex_unlock(&group->mutex);

+
+ if (count != 1)
+ return false;
+
+ /*

+        * The PCI device could be considered to be fully isolated if all
+        * devices on the path from the device to the host-PCI bridge are
+        * protected from peer-to-peer DMA by ACS.
+        */

+ if (dev_is_pci(dev))
+ return pci_acs_path_enabled(to_pci_dev(dev), NULL,
+ REQ_ACS_FLAGS);
+
+ /*

+        * Otherwise, the device came from DT/ACPI, assume it is static and
+        * then singleton can know from the device count in the group.
+        */

+ return true;
+}

Quoted 16 lines

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3271

Quoted 13 lines
drivers/iommu/iommu.c +12 -0
+	int count;
+
+	if (!group)
+		return false;
+
+	mutex_lock(&group->mutex);
+	count = iommu_group_device_count(group);
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	if (count != 1)
+		return false;

For non-pci devices above doesn't check anything against immutable. Please add some comment to explain why doing so is correct.

Yes, as above code shows.

Quoted 14 lines
Quoted 4 lines
drivers/iommu/iommu.c +3 -0
+
+	/*
+	 * The PCI device could be considered to be fully isolated if all

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3284

Quoted 10 lines
drivers/iommu/iommu.c +10 -0
+	 * devices on the path from the device to the host-PCI bridge are
+	 * protected from peer-to-peer DMA by ACS.
+	 */
+	if (dev_is_pci(dev))
+		return pci_acs_path_enabled(to_pci_dev(dev), NULL,
+					    REQ_ACS_FLAGS);
+
+	return true;
+}
+

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

author maintainer
#22 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Jason Gunthorpe

Hi Jason,

Quoted 6 lines · Jason Gunthorpe
Quoted 6 lines
drivers/iommu/iommu-sva-lib.c +1 -0
index 106506143896..210c376f6043 100644
+++ b/drivers/iommu/iommu-sva-lib.c
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
  	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
  }
Quoted 9 lines

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 77

Quoted 7 lines
drivers/iommu/iommu-sva-lib.c +6 -0
  EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

This should return the proper type

Can you please elaborate a bit on "return the proper type"? Did you mean return iommu_sva_domain instead? That's a wrapper of iommu_domain and only for iommu internal usage.

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

author maintainer
#25 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Jason Gunthorpe
Quoted 21 lines · Jason Gunthorpe
Quoted 21 lines
drivers/iommu/iommu-sva-lib.c +21 -0
+{
+	struct iommu_sva_domain *sva_domain;
+	struct iommu_domain *domain;
+
+	if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
+		return ERR_PTR(-ENODEV);
+
+	sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
+	if (!sva_domain)
+		return ERR_PTR(-ENOMEM);
+
+	mmgrab(mm);
+	sva_domain->mm = mm;
+
+	domain = &sva_domain->domain;
+	domain->type = IOMMU_DOMAIN_SVA;
+	domain->ops = bus->iommu_ops->sva_domain_ops;
+
+	return domain;
+}
+
Quoted 8 lines

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 105

Quoted 7 lines
drivers/iommu/iommu-sva-lib.c +7 -0
+void iommu_sva_free_domain(struct iommu_domain *domain)
+{
+	struct iommu_sva_domain *sva_domain = to_sva_domain(domain);
+
+	mmdrop(sva_domain->mm);
+	kfree(sva_domain);
+}

No callback to the driver?

Should do this in the next version. This version added an sva-specific iommu_domain_ops pointer in iommu_ops. This is not the right way to go.

Quoted 5 lines

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 109

Quoted 4 lines
drivers/iommu/iommu-sva-lib.c +3 -0
+int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,
+			 ioasid_t pasid)
+{

Why does this function exist? Just call iommu_set_device_pasid()

Yes, agreed.

Quoted 6 lines

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3287

Quoted 4 lines
drivers/iommu/iommu.c +3 -0
+int iommu_set_device_pasid(struct iommu_domain *domain, struct device *dev,
+			   ioasid_t pasid)
+{

Here you can continue to use attach/detach language as at this API level we expect strict pairing..

Sure.

Quoted 12 lines

drivers/iommu/iommu.c bool iommu_group_dma_owner_claimed(struct iommu_group *group) · line 3321

Quoted 11 lines
drivers/iommu/iommu.c +9 -0
+void iommu_block_device_pasid(struct iommu_domain *domain, struct device *dev,
+			      ioasid_t pasid)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	mutex_lock(&group->mutex);
+	domain->ops->block_dev_pasid(domain, dev, pasid);
+	xa_erase(&group->pasid_array, pasid);
+	mutex_unlock(&group->mutex);

Should be the blocking domain.

As we discussed, we should change above to blocking domain when the blocking domain is supported on at least Intel and arm-smmu-v3 drivers. I have started the work for Intel driver support.

Best regards,
baolu

author maintainer
#27 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Robin Murphy

Hi Robin,

Quoted 32 lines · Robin Murphy

On 2022-05-19 08:20, Lu Baolu wrote:
[...]

Quoted 5 lines
drivers/iommu/iommu-sva-lib.c +0 -0
index 106506143896..210c376f6043 100644

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 77

Quoted 9 lines
drivers/iommu/iommu-sva-lib.c +6 -0
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
       return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
   }
   EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

Argh, please no new bus-based external interfaces! Domain allocation needs to resolve to the right IOMMU instance to solve a number of issues, and cleaning up existing users of iommu_domain_alloc() to prepare for that is already hard enough. This is arguably even more relevant here than for other domain types, since SVA support is more likely to depend on specific features that can vary between IOMMU instances even with the same driver. Please make the external interface take a struct device, then resolve the ops through dev->iommu.

Further nit: the naming inconsistency bugs me a bit - iommu_sva_domain_alloc() seems more natural. Also I'd question the symmetry vs. usability dichotomy of whether we *really* want two different free functions for a struct iommu_domain pointer, where any caller which might mix SVA and non-SVA usage then has to remember how they allocated any particular domain :/

Quoted 11 lines
drivers/iommu/iommu-sva-lib.c +11 -0
+{
+    struct iommu_sva_domain *sva_domain;
+    struct iommu_domain *domain;
+
+    if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
+        return ERR_PTR(-ENODEV);
+
+    sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
+    if (!sva_domain)
+        return ERR_PTR(-ENOMEM);
+
Quoted 8 lines

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 94

Quoted 6 lines
drivers/iommu/iommu-sva-lib.c +6 -0
+    mmgrab(mm);
+    sva_domain->mm = mm;
+
+    domain = &sva_domain->domain;
+    domain->type = IOMMU_DOMAIN_SVA;
+    domain->ops = bus->iommu_ops->sva_domain_ops;

I'd have thought it would be logical to pass IOMMU_DOMAIN_SVA to the normal domain_alloc call, so that driver-internal stuff like context descriptors can be still be hung off the domain as usual (rather than all drivers having to implement some extra internal lookup mechanism to handle all the SVA domain ops), but that's something we're free to come

Agreed with above comments. Thanks! I will post an additional patch for review later.

Quoted 2 lines

back and change later. FWIW I'd just stick the mm pointer in struct iommu_domain, in a union with the fault handler stuff and/or iova_cookie
- those are mutually exclusive with SVA, right?

"iova_cookie" is mutually exclusive with SVA, but I am not sure about the fault handler stuff.

Did you mean @handler and @handler_token staffs below?

struct iommu_domain {
        unsigned type;
        const struct iommu_domain_ops *ops;
        unsigned long pgsize_bitmap;    /* Bitmap of page sizes in use */
        iommu_fault_handler_t handler;
        void *handler_token;
        struct iommu_domain_geometry geometry;
        struct iommu_dma_cookie *iova_cookie;
};

Is it only for DMA domains? From the point view of IOMMU faults, it seems to be generic.

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

#42 lore raw

Re: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Tian, Kevin
Quoted 27 lines · Kevin
Quoted 27 lines

From: Jean-Philippe Brucker <[email protected]>
Sent: Tuesday, May 24, 2022 6:58 PM

Quoted 22 lines · Kevin
Quoted 7 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need for any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops.

set/block_pasid_dev, to be consistent.

drivers/iommu/iommu-sva-lib.c int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev, · line 173

Quoted 10 lines
drivers/iommu/iommu-sva-lib.c +10 -0
+
+	mutex_lock(&iommu_sva_lock);
+	/* Search for an existing domain. */
+	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid);
+	if (domain) {
+		sva_domain = to_sva_domain(domain);
+		refcount_inc(&sva_domain->bond.users);
+		goto out_success;
+	}
+

why would one device/pasid be bound to a mm more than once?

Quoted 6 lines
Quoted 3 lines

Device drivers can call bind() multiple times for the same device and mm, for example if one process wants to open multiple accelerator queues.

Is it clearer to have a sva_bond_get/put() pair instead of calling bind() multiple times here?

I don't think it's clearer, and it would force device drivers to keep track of {dev, mm} pairs, when the IOMMU subsystem already does that. At the moment a device driver calls

bond = iommu_sva_bind_device(dev, mm)

for each ADI that it wants to assign to userspace. If a process happens to want multiple ADIs on one device, then the {dev, mm} parameters are the same and bind() returns the same bond. Since the IOMMU driver needs to track these anyway, it might as well refcount them.

Thanks,
Jean

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

reviewer
#28 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Baolu Lu
Quoted 44 lines · Baolu Lu

Hi Robin,

Quoted 32 lines · Robin Murphy

On 2022-05-19 08:20, Lu Baolu wrote:
[...]

Quoted 5 lines
drivers/iommu/iommu-sva-lib.c +0 -0
index 106506143896..210c376f6043 100644

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 77

Quoted 9 lines
drivers/iommu/iommu-sva-lib.c +6 -0
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
       return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
   }
   EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

Argh, please no new bus-based external interfaces! Domain allocation needs to resolve to the right IOMMU instance to solve a number of issues, and cleaning up existing users of iommu_domain_alloc() to prepare for that is already hard enough. This is arguably even more relevant here than for other domain types, since SVA support is more likely to depend on specific features that can vary between IOMMU instances even with the same driver. Please make the external interface take a struct device, then resolve the ops through dev->iommu.

Further nit: the naming inconsistency bugs me a bit - iommu_sva_domain_alloc() seems more natural. Also I'd question the symmetry vs. usability dichotomy of whether we *really* want two different free functions for a struct iommu_domain pointer, where any caller which might mix SVA and non-SVA usage then has to remember how they allocated any particular domain :/

Quoted 11 lines
drivers/iommu/iommu-sva-lib.c +11 -0
+{
+    struct iommu_sva_domain *sva_domain;
+    struct iommu_domain *domain;
+
+    if (!bus->iommu_ops || !bus->iommu_ops->sva_domain_ops)
+        return ERR_PTR(-ENODEV);
+
+    sva_domain = kzalloc(sizeof(*sva_domain), GFP_KERNEL);
+    if (!sva_domain)
+        return ERR_PTR(-ENOMEM);
+
Quoted 8 lines

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 94

Quoted 6 lines
drivers/iommu/iommu-sva-lib.c +6 -0
+    mmgrab(mm);
+    sva_domain->mm = mm;
+
+    domain = &sva_domain->domain;
+    domain->type = IOMMU_DOMAIN_SVA;
+    domain->ops = bus->iommu_ops->sva_domain_ops;

I'd have thought it would be logical to pass IOMMU_DOMAIN_SVA to the normal domain_alloc call, so that driver-internal stuff like context descriptors can be still be hung off the domain as usual (rather than all drivers having to implement some extra internal lookup mechanism to handle all the SVA domain ops), but that's something we're free to come

Quoted 7 lines

Agreed with above comments. Thanks! I will post an additional patch for review later.

Quoted 1 line

back and change later. FWIW I'd just stick the mm pointer in struct iommu_domain, in a union with the fault handler stuff and/or iova_cookie - those are mutually exclusive with SVA, right?

"iova_cookie" is mutually exclusive with SVA, but I am not sure about the fault handler stuff.

To correct myself, the IOVA cookie should be irrelevant to *current* SVA, but if we ever get as far as whole-device-SVA without PASIDs then we might need an MSI cookie (modulo the additional problem of stealing some procvess address space for it).

Quoted 12 lines

Did you mean @handler and @handler_token staffs below?

struct iommu_domain {
        unsigned type;
        const struct iommu_domain_ops *ops;
        unsigned long pgsize_bitmap;    /* Bitmap of page sizes in use */ iommu_fault_handler_t handler;
        void *handler_token;
        struct iommu_domain_geometry geometry;
        struct iommu_dma_cookie *iova_cookie;
};

Quoted 2 lines

Is it only for DMA domains? From the point view of IOMMU faults, it seems to be generic.

Yes, it's the old common iommu_set_fault_handler() stuff (which arguably is more of a "notifier" than a "handler"), but I assume that that's irrelevant if SVA is using IOPF instead?

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

#29 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

Quoted 12 lines · Robin Murphy
Quoted 12 lines

Did you mean @handler and @handler_token staffs below?

struct iommu_domain {
        unsigned type;
        const struct iommu_domain_ops *ops;
        unsigned long pgsize_bitmap;    /* Bitmap of page sizes in use */ iommu_fault_handler_t handler;
        void *handler_token;
        struct iommu_domain_geometry geometry;
        struct iommu_dma_cookie *iova_cookie;
};

Quoted 6 lines
Quoted 2 lines

Is it only for DMA domains? From the point view of IOMMU faults, it seems to be generic.

Yes, it's the old common iommu_set_fault_handler() stuff (which arguably is more of a "notifier" than a "handler"), but I assume that that's irrelevant if SVA is using IOPF instead?

Yes IOMMU drivers call either the newer iommu_report_device_fault() or the old report_iommu_fault(), and only the former can support IOPF/SVA. I've tried to merge them before but never completed it. I think the main issue was with finding the endpoint that caused the fault from the fault handler. Some IOMMU drivers just pass the IOMMU device to report_iommu_fault(). I'll probably pick that up at some point.

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

author maintainer Reviewed-by Jean-Philippe Brucker
#30 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

Quoted 18 lines · Jean-Philippe Brucker
Quoted 12 lines · Robin Murphy
Quoted 12 lines

Did you mean @handler and @handler_token staffs below?

struct iommu_domain {
        unsigned type;
        const struct iommu_domain_ops *ops;
        unsigned long pgsize_bitmap;    /* Bitmap of page sizes in use */ iommu_fault_handler_t handler;
        void *handler_token;
        struct iommu_domain_geometry geometry;
        struct iommu_dma_cookie *iova_cookie;
};

Quoted 5 lines
Quoted 2 lines

Is it only for DMA domains? From the point view of IOMMU faults, it seems to be generic.

Yes, it's the old common iommu_set_fault_handler() stuff (which arguably is more of a "notifier" than a "handler"), but I assume that that's irrelevant if SVA is using IOPF instead?

Quoted 6 lines

Yes IOMMU drivers call either the newer iommu_report_device_fault() or the old report_iommu_fault(), and only the former can support IOPF/SVA. I've tried to merge them before but never completed it. I think the main issue was with finding the endpoint that caused the fault from the fault handler. Some IOMMU drivers just pass the IOMMU device to report_iommu_fault(). I'll probably pick that up at some point.

Thank you all for the comments and suggestions. Below is the refreshed patch. Hope that I didn't miss anything.

From 463c04cada8e8640598f981d8d16157781b9de6f Mon Sep 17 00:00:00 2001
From: Lu Baolu <[email protected]>
Date: Wed, 11 May 2022 20:59:24 +0800
Subject: [PATCH 04/11] iommu: Add sva iommu_domain support

The sva iommu_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructure to support SVA domain in the iommu common layer. It includes:

- Extend the iommu_domain to support a new IOMMU_DOMAIN_SVA domain type. The IOMMU drivers that support SVA should provide the sva domain specific iommu_domain_ops.
- Add a helper to allocate an SVA domain. The iommu_domain_free() is still used to free an SVA domain.
- Add helpers to attach an SVA domain to a device and the reverse operation.

Some buses, like PCI, route packets without considering the PASID value. Thus a DMA target address with PASID might be treated as P2P if the address falls into the MMIO BAR of other devices in the group. To make things simple, the attach/detach interfaces only apply to devices belonging to the singleton groups, and the singleton is immutable in fabric i.e. not affected by hotplug.

The iommu_attach/detach_device_pasid() can be used for other purposes, such as kernel DMA with pasid, mediation device, etc.

---
 drivers/iommu/iommu.c | 93 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/iommu.h | 45 ++++++++++++++++++++-
 2 files changed, 136 insertions(+), 2 deletions(-)
drivers/iommu/iommu.c +93 -0
index 63b64b4e8a38..b1a2ad64a413 100644
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/cc_platform.h>
 #include <trace/events/iommu.h>
+#include <linux/sched/mm.h>
 
 static struct kset *iommu_group_kset;
 static DEFINE_IDA(iommu_group_ida);
@@ -39,6 +40,7 @@ struct iommu_group {
 	struct kobject kobj;
 	struct kobject *devices_kobj;
 	struct list_head devices;
+	struct xarray pasid_array;
 	struct mutex mutex;
 	void *iommu_data;
 	void (*iommu_data_release)(void *iommu_data);
@@ -666,6 +668,7 @@ struct iommu_group *iommu_group_alloc(void)
 	mutex_init(&group->mutex);
 	INIT_LIST_HEAD(&group->devices);
 	INIT_LIST_HEAD(&group->entry);
+	xa_init(&group->pasid_array);
 
 	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
@@ -1961,6 +1964,8 @@ EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 
 void iommu_domain_free(struct iommu_domain *domain)
 {
+	if (domain->type == IOMMU_DOMAIN_SVA)
+		mmdrop(domain->mm);
 	iommu_put_dma_cookie(domain);
 	domain->ops->free(domain);
 }
@@ -3277,3 +3282,91 @@ bool iommu_group_dma_owner_claimed(struct iommu_group *group)
 	return user;
 }
 EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);
+
+struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
+					    struct mm_struct *mm)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+	struct iommu_domain *domain;
+
+	domain = ops->domain_alloc(IOMMU_DOMAIN_SVA);
+	if (!domain)
+		return NULL;
+
+	domain->type = IOMMU_DOMAIN_SVA;
+	mmgrab(mm);
+	domain->mm = mm;
+
+	return domain;
+}
+
+static bool iommu_group_immutable_singleton(struct iommu_group *group,
+					    struct device *dev)
+{
+	int count;
+
+	mutex_lock(&group->mutex);
+	count = iommu_group_device_count(group);
+	mutex_unlock(&group->mutex);
+
+	if (count != 1)
+		return false;
+
+	/*
+	 * The PCI device could be considered to be fully isolated if all
+	 * devices on the path from the device to the host-PCI bridge are
+	 * protected from peer-to-peer DMA by ACS.
+	 */
+	if (dev_is_pci(dev))
+		return pci_acs_path_enabled(to_pci_dev(dev), NULL,
+					    REQ_ACS_FLAGS);
+
+	/*
+	 * Otherwise, the device came from DT/ACPI, assume it is static and
+	 * then singleton can know from the device count in the group.
+	 */
+	return true;
+}
+
+int iommu_attach_device_pasid(struct iommu_domain *domain, struct device *dev,
+			      ioasid_t pasid)
+{
+	struct iommu_group *group;
+	int ret = -EBUSY;
+	void *curr;
+
+	if (!domain->ops->set_dev_pasid)
+		return -EOPNOTSUPP;
+
+	group = iommu_group_get(dev);
+	if (!group || !iommu_group_immutable_singleton(group, dev)) {
+		iommu_group_put(group);
+		return -EINVAL;
+	}
+
+	mutex_lock(&group->mutex);
+	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
+	if (curr)
+		goto out_unlock;
+	ret = domain->ops->set_dev_pasid(domain, dev, pasid);
+	if (ret)
+		xa_erase(&group->pasid_array, pasid);
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+
+void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
+			       ioasid_t pasid)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	mutex_lock(&group->mutex);
+	domain->ops->block_dev_pasid(domain, dev, pasid);
+	xa_erase(&group->pasid_array, pasid);
+	mutex_unlock(&group->mutex);
+
+	iommu_group_put(group);
+}
include/linux/iommu.h +16 -2
index 3fbad42c0bf8..9173c5741447 100644
@@ -64,6 +64,9 @@ struct iommu_domain_geometry {
 #define __IOMMU_DOMAIN_PT	(1U << 2)  /* Domain is identity mapped   */
 #define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
 
+#define __IOMMU_DOMAIN_SHARED	(1U << 4)  /* Page table shared from CPU  */
+#define __IOMMU_DOMAIN_HOST_VA	(1U << 5)  /* Host CPU virtual address */
+
 /*
  * This are the possible domain-types
  *
@@ -86,15 +89,24 @@ struct iommu_domain_geometry {
 #define IOMMU_DOMAIN_DMA_FQ	(__IOMMU_DOMAIN_PAGING |	\
 				 __IOMMU_DOMAIN_DMA_API |	\
 				 __IOMMU_DOMAIN_DMA_FQ)
+#define IOMMU_DOMAIN_SVA	(__IOMMU_DOMAIN_SHARED |	\
+				 __IOMMU_DOMAIN_HOST_VA)
 
 struct iommu_domain {
 	unsigned type;
 	const struct iommu_domain_ops *ops;
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
-	iommu_fault_handler_t handler;
-	void *handler_token;
 	struct iommu_domain_geometry geometry;
 	struct iommu_dma_cookie *iova_cookie;
+	union {
+		struct {	/* IOMMU_DOMAIN_DMA */
+			iommu_fault_handler_t handler;
+			void *handler_token;
+		};
+		struct {	/* IOMMU_DOMAIN_SVA */
+			struct mm_struct *mm;
+		};
+	};
 };
 
 static inline bool iommu_is_dma_domain(struct iommu_domain *domain)
@@ -262,6 +274,8 @@ struct iommu_ops {
  * struct iommu_domain_ops - domain specific operations
  * @attach_dev: attach an iommu domain to a device
  * @detach_dev: detach an iommu domain from a device
+ * @set_dev_pasid: set an iommu domain to a pasid of device
+ * @block_dev_pasid: block pasid of device from using iommu domain
  * @map: map a physically contiguous memory region to an iommu domain
  * @map_pages: map a physically contiguous set of pages of the same 

size to
* an iommu domain.
@@ -282,6 +296,10 @@ struct iommu_ops {
struct iommu_domain_ops {
int (*attach_dev)(struct iommu_domain *domain, struct device *dev); void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
+ int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+ ioasid_t pasid);
+ void (*block_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+ ioasid_t pasid);

int (*map)(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
@@ -679,6 +697,12 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
void iommu_group_release_dma_owner(struct iommu_group *group);
bool iommu_group_dma_owner_claimed(struct iommu_group *group);

+struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
+ struct mm_struct *mm);
+int iommu_attach_device_pasid(struct iommu_domain *domain, struct device *dev,
+ ioasid_t pasid);
+void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
+ ioasid_t pasid);
#else /* CONFIG_IOMMU_API */

struct iommu_ops {};
@@ -1052,6 +1076,23 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
{
return false;
}
+
+static inline struct iommu_domain *
+iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm)
+{
+ return NULL;
+}
+
+static inline int iommu_attach_device_pasid(struct iommu_domain *domain,
+ struct device *dev, ioasid_t pasid)
+{
+ return -ENODEV;
+}
+
+static inline void iommu_detach_device_pasid(struct iommu_domain *domain,
+ struct device *dev, ioasid_t pasid)
+{
+}
#endif /* CONFIG_IOMMU_API */

/**

Signature · 8 lines
2.25.1

Best regards,
baolu
_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
#23 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

In reply to Baolu Lu
Quoted 19 lines · Baolu Lu

Hi Jason,

Quoted 6 lines · Jason Gunthorpe
Quoted 6 lines
drivers/iommu/iommu-sva-lib.c +1 -0
index 106506143896..210c376f6043 100644
+++ b/drivers/iommu/iommu-sva-lib.c
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
  	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
  }
Quoted 9 lines

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 77

Quoted 7 lines
drivers/iommu/iommu-sva-lib.c +6 -0
  EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

This should return the proper type

Quoted 3 lines

Can you please elaborate a bit on "return the proper type"? Did you mean return iommu_sva_domain instead? That's a wrapper of iommu_domain and only for iommu internal usage.

If you are exposing special SVA APIs then it is not internal usage only anymore, so expose the type.

Jason

author maintainer
#24 lore raw

Re: [PATCH v7 03/10] iommu/sva: Add iommu_sva_domain support

Quoted 20 lines · Jason Gunthorpe
Quoted 19 lines · Baolu Lu

Hi Jason,

Quoted 15 lines · Jason Gunthorpe

drivers/iommu/iommu-sva-lib.c struct mm_struct *iommu_sva_find(ioasid_t pasid) · line 77

Quoted 13 lines
drivers/iommu/iommu-sva-lib.c +7 -0
index 106506143896..210c376f6043 100644
+++ b/drivers/iommu/iommu-sva-lib.c
@@ -69,3 +69,51 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid)
   	return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero);
   }
   EXPORT_SYMBOL_GPL(iommu_sva_find);
+
+/*
+ * IOMMU SVA driver-oriented interfaces
+ */
+struct iommu_domain *
+iommu_sva_alloc_domain(struct bus_type *bus, struct mm_struct *mm)

This should return the proper type

Quoted 6 lines
Quoted 3 lines

Can you please elaborate a bit on "return the proper type"? Did you mean return iommu_sva_domain instead? That's a wrapper of iommu_domain and only for iommu internal usage.

If you are exposing special SVA APIs then it is not internal usage only anymore, so expose the type.

Ah, got you. Thanks for the explanation.

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

#43 lore raw

RE: [PATCH v7 06/10] iommu/sva: Refactoring iommu_sva_bind/unbind_device()

In reply to Jean-Philippe Brucker
Quoted 44 lines

From: Jean-Philippe Brucker <[email protected]>
Sent: Wednesday, May 25, 2022 3:30 PM

Quoted 9 lines · Kevin
Quoted 9 lines

From: Jean-Philippe Brucker <[email protected]>
Sent: Tuesday, May 24, 2022 6:58 PM

Quoted 5 lines · Kevin
Quoted 5 lines

From: Lu Baolu <[email protected]>
Sent: Thursday, May 19, 2022 3:21 PM

The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need

for

Quoted 19 lines
Quoted 9 lines
Quoted 9 lines
Quoted 2 lines

any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops.

set/block_pasid_dev, to be consistent.

drivers/iommu/iommu-sva-lib.c int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev,

Quoted 4 lines
drivers/iommu/iommu-sva-lib.c +4 -0
+
+	mutex_lock(&iommu_sva_lock);
+	/* Search for an existing domain. */
+	domain = iommu_get_domain_for_dev_pasid(dev, mm-

pasid);

Quoted 9 lines
Quoted 8 lines

drivers/iommu/iommu-sva-lib.c int iommu_sva_set_domain(struct iommu_domain *domain, struct device *dev, · line 173

Quoted 6 lines
drivers/iommu/iommu-sva-lib.c +6 -0
+	if (domain) {
+		sva_domain = to_sva_domain(domain);
+		refcount_inc(&sva_domain->bond.users);
+		goto out_success;
+	}
+

why would one device/pasid be bound to a mm more than once?

Quoted 6 lines
Quoted 3 lines

Device drivers can call bind() multiple times for the same device and mm, for example if one process wants to open multiple accelerator queues.

Is it clearer to have a sva_bond_get/put() pair instead of calling bind() multiple times here?

I don't think it's clearer, and it would force device drivers to keep track of {dev, mm} pairs, when the IOMMU subsystem already does that. At the moment a device driver calls

Quoted 7 lines

bond = iommu_sva_bind_device(dev, mm)

for each ADI that it wants to assign to userspace. If a process happens to want multiple ADIs on one device, then the {dev, mm} parameters are the same and bind() returns the same bond. Since the IOMMU driver needs to track these anyway, it might as well refcount them.

My impression was that when an interface returns an object then further reference to this object is usually directly acquired on the object hence requires the caller to track it. But not a strong opinion here if others all agree to favor simplicity for the caller side.

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