There are callers that read the unmapped bytes even when rc != 0. Thus, do not forget to report it in the error path too.

Fixes: 8d40205f6093 ("iommufd: Add kAPI toward external drivers for kernel access") Cc: stable@vger.kernel.org Reviewed-by: Kevin Tian kevin.tian@intel.com Reviewed-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/io_pagetable.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 13d010f19ed1..22fc3a12109f 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -743,8 +743,10 @@ static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start, iommufd_access_notify_unmap(iopt, area_first, length); /* Something is not responding to unmap requests. */ tries++; - if (WARN_ON(tries > 100)) - return -EDEADLOCK; + if (WARN_ON(tries > 100)) { + rc = -EDEADLOCK; + goto out_unmapped; + } goto again; }

@@ -766,6 +768,7 @@ static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start, out_unlock_iova: up_write(&iopt->iova_rwsem); up_read(&iopt->domains_rwsem); +out_unmapped: if (unmapped) *unmapped = unmapped_bytes; return rc;

The "id" is too genernal to get its meaning easily. Rename it explicitly to "virt_id" and update the kdocs for readability. No functional changes.

Reviewed-by: Kevin Tian kevin.tian@intel.com Reviewed-by: Pranjal Shrivastava praan@google.com Reviewed-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 7 ++++++- drivers/iommu/iommufd/driver.c | 2 +- drivers/iommu/iommufd/viommu.c | 4 ++-- 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 4f5e8cd99c96..320635a177b7 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -634,7 +634,12 @@ struct iommufd_vdevice { struct iommufd_object obj; struct iommufd_viommu *viommu; struct device *dev; - u64 id; /* per-vIOMMU virtual ID */ + + /* + * Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID of + * AMD IOMMU, and vRID of Intel VT-d + */ + u64 virt_id; };

#ifdef CONFIG_IOMMUFD_TEST diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c index 2fee399a148e..887719016804 100644 --- a/drivers/iommu/iommufd/driver.c +++ b/drivers/iommu/iommufd/driver.c @@ -30,7 +30,7 @@ int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu, xa_lock(&viommu->vdevs); xa_for_each(&viommu->vdevs, index, vdev) { if (vdev->dev == dev) { - *vdev_id = vdev->id; + *vdev_id = vdev->virt_id; rc = 0; break; } diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 25ac08fbb52a..bc8796e6684e 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -111,7 +111,7 @@ void iommufd_vdevice_destroy(struct iommufd_object *obj) struct iommufd_viommu *viommu = vdev->viommu;

/* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */ - xa_cmpxchg(&viommu->vdevs, vdev->id, vdev, NULL, GFP_KERNEL); + xa_cmpxchg(&viommu->vdevs, vdev->virt_id, vdev, NULL, GFP_KERNEL); refcount_dec(&viommu->obj.users); put_device(vdev->dev); } @@ -150,7 +150,7 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) goto out_put_idev; }

- vdev->id = virt_id; + vdev->virt_id = virt_id; vdev->dev = idev->dev; get_device(idev->dev); vdev->viommu = viommu;

Replace u32 to make it clear. No functional changes.

Also simplify the kdoc since the type itself is clear enough.

Reviewed-by: Pranjal Shrivastava praan@google.com Reviewed-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 6 +++--- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 3 ++- drivers/iommu/intel/iommu.c | 3 ++- drivers/iommu/iommufd/selftest.c | 3 ++- 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 04548b18df28..b87c2841e6bc 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -563,8 +563,7 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, * @capable: check capability * @hw_info: report iommu hardware information. The data buffer returned by this * op is allocated in the iommu driver and freed by the caller after - * use. The information type is one of enum iommu_hw_info_type defined - * in include/uapi/linux/iommufd.h. + * use. * @domain_alloc: Do not use in new drivers * @domain_alloc_identity: allocate an IDENTITY domain. Drivers should prefer to * use identity_domain instead. This should only be used @@ -623,7 +622,8 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, */ struct iommu_ops { bool (*capable)(struct device *dev, enum iommu_cap); - void *(*hw_info)(struct device *dev, u32 *length, u32 *type); + void *(*hw_info)(struct device *dev, u32 *length, + enum iommu_hw_info_type *type);

/* Domain allocation and freeing by the iommu driver */ #if IS_ENABLED(CONFIG_FSL_PAMU) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 9f59c95a254c..69bbe39e28de 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -7,7 +7,8 @@

#include "arm-smmu-v3.h"

-void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type) +void *arm_smmu_hw_info(struct device *dev, u32 *length, + enum iommu_hw_info_type *type) { struct arm_smmu_master *master = dev_iommu_priv_get(dev); struct iommu_hw_info_arm_smmuv3 *info; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7aa3932251b2..850f1a6f548c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4091,7 +4091,8 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain, return ret; }

-static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type) +static void *intel_iommu_hw_info(struct device *dev, u32 *length, + enum iommu_hw_info_type *type) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 74ca955a766e..7a9abe3f47d5 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -287,7 +287,8 @@ static struct iommu_domain mock_blocking_domain = { .ops = &mock_blocking_ops, };

-static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type) +static void *mock_domain_hw_info(struct device *dev, u32 *length, + enum iommu_hw_info_type *type) { struct iommu_test_hw_info *info;

The new type of vIOMMU for tegra241-cmdqv allows user space VM to use one of its virtual command queue HW resources exclusively. This requires user space to mmap the corresponding MMIO page from kernel space for direct HW control.

To forward the mmap info (offset and length), iommufd should add a driver specific data structure to the IOMMUFD_CMD_VIOMMU_ALLOC ioctl, for driver to output the info during the vIOMMU initialization back to user space.

Similar to the existing ioctls and their IOMMU handlers, add a user_data to viommu_init op to bridge between iommufd and drivers.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Reviewed-by: Pranjal Shrivastava praan@google.com Reviewed-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 3 ++- include/linux/iommu.h | 3 ++- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 3 ++- drivers/iommu/iommufd/selftest.c | 3 ++- drivers/iommu/iommufd/viommu.c | 2 +- 5 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index bb39af84e6b0..7eed5c8c72dd 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -1037,7 +1037,8 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type); size_t arm_smmu_get_viommu_size(struct device *dev, enum iommu_viommu_type viommu_type); int arm_vsmmu_init(struct iommufd_viommu *viommu, - struct iommu_domain *parent_domain); + struct iommu_domain *parent_domain, + const struct iommu_user_data *user_data); int arm_smmu_attach_prepare_vmaster(struct arm_smmu_attach_state *state, struct arm_smmu_nested_domain *nested_domain); void arm_smmu_attach_commit_vmaster(struct arm_smmu_attach_state *state); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index fd7319706684..e06a0fbe4bc7 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -700,7 +700,8 @@ struct iommu_ops { size_t (*get_viommu_size)(struct device *dev, enum iommu_viommu_type viommu_type); int (*viommu_init)(struct iommufd_viommu *viommu, - struct iommu_domain *parent_domain); + struct iommu_domain *parent_domain, + const struct iommu_user_data *user_data);

const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 69bbe39e28de..170d69162848 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -419,7 +419,8 @@ size_t arm_smmu_get_viommu_size(struct device *dev, }

int arm_vsmmu_init(struct iommufd_viommu *viommu, - struct iommu_domain *parent_domain) + struct iommu_domain *parent_domain, + const struct iommu_user_data *user_data) { struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core); struct arm_smmu_device *smmu = diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 7a9abe3f47d5..0d896a89ace7 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -779,7 +779,8 @@ static size_t mock_get_viommu_size(struct device *dev, }

static int mock_viommu_init(struct iommufd_viommu *viommu, - struct iommu_domain *parent_domain) + struct iommu_domain *parent_domain, + const struct iommu_user_data *user_data) { struct mock_iommu_device *mock_iommu = container_of( viommu->iommu_dev, struct mock_iommu_device, iommu_dev); diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index bc8796e6684e..2009a421efae 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -84,7 +84,7 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) */ viommu->iommu_dev = __iommu_get_iommu_dev(idev->dev);

- rc = ops->viommu_init(viommu, hwpt_paging->common.domain); + rc = ops->viommu_init(viommu, hwpt_paging->common.domain, NULL); if (rc) goto out_put_hwpt;

Add a simple user_data for an input-to-output loopback test.

Reviewed-by: Pranjal Shrivastava praan@google.com Reviewed-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_test.h | 13 +++++++++++++ drivers/iommu/iommufd/selftest.c | 15 +++++++++++++++ 2 files changed, 28 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 1cd7e8394129..fbf9ecb35a13 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -227,6 +227,19 @@ struct iommu_hwpt_invalidate_selftest {

#define IOMMU_VIOMMU_TYPE_SELFTEST 0xdeadbeef

+/** + * struct iommu_viommu_selftest - vIOMMU data for Mock driver + * (IOMMU_VIOMMU_TYPE_SELFTEST) + * @in_data: Input random data from user space + * @out_data: Output data (matching @in_data) to user space + * + * Simply set @out_data=@in_data for a loopback test + */ +struct iommu_viommu_selftest { + __u32 in_data; + __u32 out_data; +}; + /* Should not be equal to any defined value in enum iommu_viommu_invalidate_data_type */ #define IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST 0xdeadbeef #define IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 0d896a89ace7..38066dfeb2e7 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -784,6 +784,21 @@ static int mock_viommu_init(struct iommufd_viommu *viommu, { struct mock_iommu_device *mock_iommu = container_of( viommu->iommu_dev, struct mock_iommu_device, iommu_dev); + struct iommu_viommu_selftest data; + int rc; + + if (user_data) { + rc = iommu_copy_struct_from_user( + &data, user_data, IOMMU_VIOMMU_TYPE_SELFTEST, out_data); + if (rc) + return rc; + + data.out_data = data.in_data; + rc = iommu_copy_struct_to_user( + user_data, &data, IOMMU_VIOMMU_TYPE_SELFTEST, out_data); + if (rc) + return rc; + }

refcount_inc(&mock_iommu->users); viommu->ops = &mock_viommu_ops;

The new HW queue object, as an internal iommufd object, wants to reuse the struct iommufd_access to pin some iova range in the iopt.

However, an access generally takes the refcount of an ictx. So, in such an internal case, a deadlock could happen when the release of the ictx has to wait for the release of the access first when releasing a hw_queue object, which could wait for the release of the ictx that is refcounted: ictx --releases--> hw_queue --releases--> access ^ | |_________________releases________________v

To address this, add a set of lightweight internal APIs to unlink the ictx and the access, i.e. no ictx refcounting by the access: ictx --releases--> hw_queue --releases--> access

Then, there's no point in setting the access->ictx. So simply define !ictx as an flag for an internal use and add an inline helper.

Reviewed-by: Kevin Tian kevin.tian@intel.com Reviewed-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 23 ++++++++++ drivers/iommu/iommufd/device.c | 59 +++++++++++++++++++++---- 2 files changed, 73 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 320635a177b7..9fdbf5f21f2e 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -484,6 +484,29 @@ void iopt_remove_access(struct io_pagetable *iopt, struct iommufd_access *access, u32 iopt_access_list_id); void iommufd_access_destroy_object(struct iommufd_object *obj);

+/* iommufd_access for internal use */ +static inline bool iommufd_access_is_internal(struct iommufd_access *access) +{ + return !access->ictx; +} + +struct iommufd_access *iommufd_access_create_internal(struct iommufd_ctx *ictx); + +static inline void +iommufd_access_destroy_internal(struct iommufd_ctx *ictx, + struct iommufd_access *access) +{ + iommufd_object_destroy_user(ictx, &access->obj); +} + +int iommufd_access_attach_internal(struct iommufd_access *access, + struct iommufd_ioas *ioas); + +static inline void iommufd_access_detach_internal(struct iommufd_access *access) +{ + iommufd_access_detach(access); +} + struct iommufd_eventq { struct iommufd_object obj; struct iommufd_ctx *ictx; diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index e9b6ca47095c..07a4ff753c12 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1084,7 +1084,39 @@ void iommufd_access_destroy_object(struct iommufd_object *obj) if (access->ioas) WARN_ON(iommufd_access_change_ioas(access, NULL)); mutex_unlock(&access->ioas_lock); - iommufd_ctx_put(access->ictx); + if (!iommufd_access_is_internal(access)) + iommufd_ctx_put(access->ictx); +} + +static struct iommufd_access *__iommufd_access_create(struct iommufd_ctx *ictx) +{ + struct iommufd_access *access; + + /* + * There is no uAPI for the access object, but to keep things symmetric + * use the object infrastructure anyhow. + */ + access = iommufd_object_alloc(ictx, access, IOMMUFD_OBJ_ACCESS); + if (IS_ERR(access)) + return access; + + /* The calling driver is a user until iommufd_access_destroy() */ + refcount_inc(&access->obj.users); + mutex_init(&access->ioas_lock); + return access; +} + +struct iommufd_access *iommufd_access_create_internal(struct iommufd_ctx *ictx) +{ + struct iommufd_access *access; + + access = __iommufd_access_create(ictx); + if (IS_ERR(access)) + return access; + access->iova_alignment = PAGE_SIZE; + + iommufd_object_finalize(ictx, &access->obj); + return access; }

/** @@ -1106,11 +1138,7 @@ iommufd_access_create(struct iommufd_ctx *ictx, { struct iommufd_access *access;

- /* - * There is no uAPI for the access object, but to keep things symmetric - * use the object infrastructure anyhow. - */ - access = iommufd_object_alloc(ictx, access, IOMMUFD_OBJ_ACCESS); + access = __iommufd_access_create(ictx); if (IS_ERR(access)) return access;

@@ -1122,13 +1150,10 @@ iommufd_access_create(struct iommufd_ctx *ictx, else access->iova_alignment = 1;

- /* The calling driver is a user until iommufd_access_destroy() */ - refcount_inc(&access->obj.users); access->ictx = ictx; iommufd_ctx_get(ictx); iommufd_object_finalize(ictx, &access->obj); *id = access->obj.id; - mutex_init(&access->ioas_lock); return access; } EXPORT_SYMBOL_NS_GPL(iommufd_access_create, "IOMMUFD"); @@ -1173,6 +1198,22 @@ int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id) } EXPORT_SYMBOL_NS_GPL(iommufd_access_attach, "IOMMUFD");

+int iommufd_access_attach_internal(struct iommufd_access *access, + struct iommufd_ioas *ioas) +{ + int rc; + + mutex_lock(&access->ioas_lock); + if (WARN_ON(access->ioas)) { + mutex_unlock(&access->ioas_lock); + return -EINVAL; + } + + rc = iommufd_access_change_ioas(access, ioas); + mutex_unlock(&access->ioas_lock); + return rc; +} + int iommufd_access_replace(struct iommufd_access *access, u32 ioas_id) { int rc;

NVIDIA VCMDQ driver will have a driver-defined vDEVICE structure and do some HW configurations with that.

To allow IOMMU drivers to define their own vDEVICE structures, move the struct iommufd_vdevice to the public header and provide a pair of viommu ops, similar to get_viommu_size and viommu_init.

Doing this, however, creates a new window between the vDEVICE allocation and its driver-level initialization, during which an abort could happen but it can't invoke a driver destroy function from the struct viommu_ops since the driver structure isn't initialized yet. vIOMMU object doesn't have this problem, since its destroy op is set via the viommu_ops by the driver viommu_init function. Thus, vDEVICE should do something similar: add a destroy function pointer inside the struct iommufd_vdevice instead of the struct iommufd_viommu_ops.

Note that there is unlikely a use case for a type dependent vDEVICE, so a static vdevice_size is probably enough for the near term instead of a get_vdevice_size function op.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Kevin Tian kevin.tian@intel.com Reviewed-by: Pranjal Shrivastava praan@google.com Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 12 ---------- include/linux/iommufd.h | 31 +++++++++++++++++++++++++ drivers/iommu/iommufd/viommu.c | 26 ++++++++++++++++++++- 3 files changed, 56 insertions(+), 13 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 9fdbf5f21f2e..06b8c2e2d9e6 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -653,18 +653,6 @@ void iommufd_viommu_destroy(struct iommufd_object *obj); int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd); void iommufd_vdevice_destroy(struct iommufd_object *obj);

-struct iommufd_vdevice { - struct iommufd_object obj; - struct iommufd_viommu *viommu; - struct device *dev; - - /* - * Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID of - * AMD IOMMU, and vRID of Intel VT-d - */ - u64 virt_id; -}; - #ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); void iommufd_selftest_destroy(struct iommufd_object *obj); diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 2d1bf2f97ee3..bdd10a85eeef 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -104,6 +104,21 @@ struct iommufd_viommu { enum iommu_viommu_type type; };

+struct iommufd_vdevice { + struct iommufd_object obj; + struct iommufd_viommu *viommu; + struct device *dev; + + /* + * Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID of + * AMD IOMMU, and vRID of Intel VT-d + */ + u64 virt_id; + + /* Clean up all driver-specific parts of an iommufd_vdevice */ + void (*destroy)(struct iommufd_vdevice *vdev); +}; + /** * struct iommufd_viommu_ops - vIOMMU specific operations * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory @@ -120,6 +135,14 @@ struct iommufd_viommu { * array->entry_num to report the number of handled requests. * The data structure of the array entry must be defined in * include/uapi/linux/iommufd.h + * @vdevice_size: Size of the driver-defined vDEVICE structure per this vIOMMU + * @vdevice_init: Initialize the driver-level structure of a vDEVICE object, or + * related HW procedure. @vdev is already initialized by iommufd + * core: vdev->dev and vdev->viommu pointers; vdev->id carries a + * per-vIOMMU virtual ID (refer to struct iommu_vdevice_alloc in + * include/uapi/linux/iommufd.h) + * If driver has a deinit function to revert what vdevice_init op + * does, it should set it to the @vdev->destroy function pointer */ struct iommufd_viommu_ops { void (*destroy)(struct iommufd_viommu *viommu); @@ -128,6 +151,8 @@ struct iommufd_viommu_ops { const struct iommu_user_data *user_data); int (*cache_invalidate)(struct iommufd_viommu *viommu, struct iommu_user_data_array *array); + const size_t vdevice_size; + int (*vdevice_init)(struct iommufd_vdevice *vdev); };

#if IS_ENABLED(CONFIG_IOMMUFD) @@ -224,4 +249,10 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu, BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) + \ BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_viommu, \ ((drv_struct *)NULL)->member))) + +#define VDEVICE_STRUCT_SIZE(drv_struct, member) \ + (sizeof(drv_struct) + \ + BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) + \ + BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_vdevice, \ + ((drv_struct *)NULL)->member))) #endif diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index c0365849f849..081ee6697a11 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -116,6 +116,8 @@ void iommufd_vdevice_destroy(struct iommufd_object *obj) container_of(obj, struct iommufd_vdevice, obj); struct iommufd_viommu *viommu = vdev->viommu;

+ if (vdev->destroy) + vdev->destroy(vdev); /* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */ xa_cmpxchg(&viommu->vdevs, vdev->virt_id, vdev, NULL, GFP_KERNEL); refcount_dec(&viommu->obj.users); @@ -126,6 +128,7 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) { struct iommu_vdevice_alloc *cmd = ucmd->cmd; struct iommufd_vdevice *vdev, *curr; + size_t vdev_size = sizeof(*vdev); struct iommufd_viommu *viommu; struct iommufd_device *idev; u64 virt_id = cmd->virt_id; @@ -150,7 +153,22 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) goto out_put_idev; }

- vdev = iommufd_object_alloc_ucmd(ucmd, vdev, IOMMUFD_OBJ_VDEVICE); + if (viommu->ops && viommu->ops->vdevice_size) { + /* + * It is a driver bug for: + * - ops->vdevice_size smaller than the core structure size + * - not implementing a pairing ops->vdevice_init op + */ + if (WARN_ON_ONCE(viommu->ops->vdevice_size < vdev_size || + !viommu->ops->vdevice_init)) { + rc = -EOPNOTSUPP; + goto out_put_idev; + } + vdev_size = viommu->ops->vdevice_size; + } + + vdev = (struct iommufd_vdevice *)_iommufd_object_alloc_ucmd( + ucmd, vdev_size, IOMMUFD_OBJ_VDEVICE); if (IS_ERR(vdev)) { rc = PTR_ERR(vdev); goto out_put_idev; @@ -168,6 +186,12 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) goto out_put_idev; }

+ if (viommu->ops && viommu->ops->vdevice_init) { + rc = viommu->ops->vdevice_init(vdev); + if (rc) + goto out_put_idev; + } + cmd->out_vdevice_id = vdev->obj.id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));

Introduce a new IOMMUFD_CMD_HW_QUEUE_ALLOC ioctl for user space to allocate a HW QUEUE object for a vIOMMU specific HW-accelerated queue, e.g.: - NVIDIA's Virtual Command Queue - AMD vIOMMU's Command Buffer, Event Log Buffers, and PPR Log Buffers

Since this is introduced with NVIDIA's VCMDQs that access the guest memory in the physical address space, add an iommufd_hw_queue_alloc_phys() helper that will create an access object to the queue memory in the IOAS, to avoid the mappings of the guest memory from being unmapped, during the life cycle of the HW queue object.

AMD's HW will need an hw_queue_init op that is mutually exclusive with the hw_queue_init_phys op, and their case will bypass the access part, i.e. no iommufd_hw_queue_alloc_phys() call.

Reviewed-by: Pranjal Shrivastava praan@google.com Reviewed-by: Kevin Tian kevin.tian@intel.com Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 2 + include/linux/iommufd.h | 1 + include/uapi/linux/iommufd.h | 33 +++++ drivers/iommu/iommufd/main.c | 6 + drivers/iommu/iommufd/viommu.c | 177 ++++++++++++++++++++++++ 5 files changed, 219 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 06b8c2e2d9e6..dcd609573244 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -652,6 +652,8 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd); void iommufd_viommu_destroy(struct iommufd_object *obj); int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd); void iommufd_vdevice_destroy(struct iommufd_object *obj); +int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd); +void iommufd_hw_queue_destroy(struct iommufd_object *obj);

#ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index f13f3ca6adb5..ce4011a2fc27 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -123,6 +123,7 @@ struct iommufd_vdevice { struct iommufd_hw_queue { struct iommufd_object obj; struct iommufd_viommu *viommu; + struct iommufd_access *access;

u64 base_addr; /* in guest physical address space */ size_t length; diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 640a8b5147c2..55459b9eee31 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -56,6 +56,7 @@ enum { IOMMUFD_CMD_VDEVICE_ALLOC = 0x91, IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92, IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93, + IOMMUFD_CMD_HW_QUEUE_ALLOC = 0x94, };

/** @@ -1156,4 +1157,36 @@ enum iommu_hw_queue_type { IOMMU_HW_QUEUE_TYPE_DEFAULT = 0, };

+/** + * struct iommu_hw_queue_alloc - ioctl(IOMMU_HW_QUEUE_ALLOC) + * @size: sizeof(struct iommu_hw_queue_alloc) + * @flags: Must be 0 + * @viommu_id: Virtual IOMMU ID to associate the HW queue with + * @type: One of enum iommu_hw_queue_type + * @index: The logical index to the HW queue per virtual IOMMU for a multi-queue + * model + * @out_hw_queue_id: The ID of the new HW queue + * @nesting_parent_iova: Base address of the queue memory in the guest physical + * address space + * @length: Length of the queue memory + * + * Allocate a HW queue object for a vIOMMU-specific HW-accelerated queue, which + * allows HW to access a guest queue memory described using @nesting_parent_iova + * and @length. + * + * A vIOMMU can allocate multiple queues, but it must use a different @index per + * type to separate each allocation, e.g. + * Type1 HW queue0, Type1 HW queue1, Type2 HW queue0, ... + */ +struct iommu_hw_queue_alloc { + __u32 size; + __u32 flags; + __u32 viommu_id; + __u32 type; + __u32 index; + __u32 out_hw_queue_id; + __aligned_u64 nesting_parent_iova; + __aligned_u64 length; +}; +#define IOMMU_HW_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HW_QUEUE_ALLOC) #endif diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 778694d7c207..4e8dbbfac890 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -354,6 +354,7 @@ union ucmd_buffer { struct iommu_destroy destroy; struct iommu_fault_alloc fault; struct iommu_hw_info info; + struct iommu_hw_queue_alloc hw_queue; struct iommu_hwpt_alloc hwpt; struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; struct iommu_hwpt_invalidate cache; @@ -396,6 +397,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { struct iommu_fault_alloc, out_fault_fd), IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info, __reserved), + IOCTL_OP(IOMMU_HW_QUEUE_ALLOC, iommufd_hw_queue_alloc_ioctl, + struct iommu_hw_queue_alloc, length), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, __reserved), IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap, @@ -559,6 +562,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { [IOMMUFD_OBJ_FAULT] = { .destroy = iommufd_fault_destroy, }, + [IOMMUFD_OBJ_HW_QUEUE] = { + .destroy = iommufd_hw_queue_destroy, + }, [IOMMUFD_OBJ_HWPT_PAGING] = { .destroy = iommufd_hwpt_paging_destroy, .abort = iommufd_hwpt_paging_abort, diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 081ee6697a11..00641204efb2 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -201,3 +201,180 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) iommufd_put_object(ucmd->ictx, &viommu->obj); return rc; } + +static void iommufd_hw_queue_destroy_access(struct iommufd_ctx *ictx, + struct iommufd_access *access, + u64 base_iova, size_t length) +{ + iommufd_access_unpin_pages(access, base_iova, length); + iommufd_access_detach_internal(access); + iommufd_access_destroy_internal(ictx, access); +} + +void iommufd_hw_queue_destroy(struct iommufd_object *obj) +{ + struct iommufd_hw_queue *hw_queue = + container_of(obj, struct iommufd_hw_queue, obj); + + if (hw_queue->destroy) + hw_queue->destroy(hw_queue); + if (hw_queue->access) + iommufd_hw_queue_destroy_access(hw_queue->viommu->ictx, + hw_queue->access, + hw_queue->base_addr, + hw_queue->length); + if (hw_queue->viommu) + refcount_dec(&hw_queue->viommu->obj.users); +} + +/* + * When the HW accesses the guest queue via physical addresses, the underlying + * physical pages of the guest queue must be contiguous. Also, for the security + * concern that IOMMUFD_CMD_IOAS_UNMAP could potentially remove the mappings of + * the guest queue from the nesting parent iopt while the HW is still accessing + * the guest queue memory physically, such a HW queue must require an access to + * pin the underlying pages and prevent that from happening. + */ +static struct iommufd_access * +iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd, + struct iommufd_viommu *viommu, phys_addr_t *base_pa) +{ + struct iommufd_access *access; + struct page **pages; + size_t max_npages; + size_t length; + u64 offset; + size_t i; + int rc; + + offset = + cmd->nesting_parent_iova - PAGE_ALIGN(cmd->nesting_parent_iova); + /* DIV_ROUND_UP(offset + cmd->length, PAGE_SIZE) */ + if (check_add_overflow(offset, cmd->length, &length)) + return ERR_PTR(-ERANGE); + if (check_add_overflow(length, PAGE_SIZE - 1, &length)) + return ERR_PTR(-ERANGE); + max_npages = length / PAGE_SIZE; + + /* + * Use kvcalloc() to avoid memory fragmentation for a large page array. + * Set __GFP_NOWARN to avoid syzkaller blowups + */ + pages = kvcalloc(max_npages, sizeof(*pages), GFP_KERNEL | __GFP_NOWARN); + if (!pages) + return ERR_PTR(-ENOMEM); + + access = iommufd_access_create_internal(viommu->ictx); + if (IS_ERR(access)) { + rc = PTR_ERR(access); + goto out_free; + } + + rc = iommufd_access_attach_internal(access, viommu->hwpt->ioas); + if (rc) + goto out_destroy; + + rc = iommufd_access_pin_pages(access, cmd->nesting_parent_iova, + cmd->length, pages, 0); + if (rc) + goto out_detach; + + /* Validate if the underlying physical pages are contiguous */ + for (i = 1; i < max_npages; i++) { + if (page_to_pfn(pages[i]) == page_to_pfn(pages[i - 1]) + 1) + continue; + rc = -EFAULT; + goto out_unpin; + } + + *base_pa = page_to_pfn(pages[0]) << PAGE_SHIFT; + kfree(pages); + return access; + +out_unpin: + iommufd_access_unpin_pages(access, cmd->nesting_parent_iova, + cmd->length); +out_detach: + iommufd_access_detach_internal(access); +out_destroy: + iommufd_access_destroy_internal(viommu->ictx, access); +out_free: + kfree(pages); + return ERR_PTR(rc); +} + +int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd) +{ + struct iommu_hw_queue_alloc *cmd = ucmd->cmd; + struct iommufd_hw_queue *hw_queue; + struct iommufd_viommu *viommu; + struct iommufd_access *access; + size_t hw_queue_size; + phys_addr_t base_pa; + u64 last; + int rc; + + if (cmd->flags || cmd->type == IOMMU_HW_QUEUE_TYPE_DEFAULT) + return -EOPNOTSUPP; + if (!cmd->length) + return -EINVAL; + if (check_add_overflow(cmd->nesting_parent_iova, cmd->length - 1, + &last)) + return -EOVERFLOW; + + viommu = iommufd_get_viommu(ucmd, cmd->viommu_id); + if (IS_ERR(viommu)) + return PTR_ERR(viommu); + + if (!viommu->ops || !viommu->ops->get_hw_queue_size || + !viommu->ops->hw_queue_init_phys) { + rc = -EOPNOTSUPP; + goto out_put_viommu; + } + + hw_queue_size = viommu->ops->get_hw_queue_size(viommu, cmd->type); + if (!hw_queue_size) { + rc = -EOPNOTSUPP; + goto out_put_viommu; + } + + /* + * It is a driver bug for providing a hw_queue_size smaller than the + * core HW queue structure size + */ + if (WARN_ON_ONCE(hw_queue_size < sizeof(*hw_queue))) { + rc = -EOPNOTSUPP; + goto out_put_viommu; + } + + hw_queue = (struct iommufd_hw_queue *)_iommufd_object_alloc_ucmd( + ucmd, hw_queue_size, IOMMUFD_OBJ_HW_QUEUE); + if (IS_ERR(hw_queue)) { + rc = PTR_ERR(hw_queue); + goto out_put_viommu; + } + + access = iommufd_hw_queue_alloc_phys(cmd, viommu, &base_pa); + if (IS_ERR(access)) { + rc = PTR_ERR(access); + goto out_put_viommu; + } + + hw_queue->viommu = viommu; + refcount_inc(&viommu->obj.users); + hw_queue->access = access; + hw_queue->type = cmd->type; + hw_queue->length = cmd->length; + hw_queue->base_addr = cmd->nesting_parent_iova; + + rc = viommu->ops->hw_queue_init_phys(hw_queue, cmd->index, base_pa); + if (rc) + goto out_put_viommu; + + cmd->out_hw_queue_id = hw_queue->obj.id; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + +out_put_viommu: + iommufd_put_object(ucmd->ictx, &viommu->obj); + return rc; +}

Some simple tests for IOMMUFD_CMD_HW_QUEUE_ALLOC infrastructure covering the new iommufd_hw_queue_depend/undepend() helpers.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_test.h | 3 + tools/testing/selftests/iommu/iommufd_utils.h | 31 ++++++ drivers/iommu/iommufd/selftest.c | 97 +++++++++++++++++++ tools/testing/selftests/iommu/iommufd.c | 58 +++++++++++ .../selftests/iommu/iommufd_fail_nth.c | 6 ++ 5 files changed, 195 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index fbf9ecb35a13..51cd744a354f 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -265,4 +265,7 @@ struct iommu_viommu_event_selftest { __u32 virt_id; };

+#define IOMMU_HW_QUEUE_TYPE_SELFTEST 0xdeadbeef +#define IOMMU_TEST_HW_QUEUE_MAX 2 + #endif diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index a5d4cbd089ba..9a556f99d992 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -956,6 +956,37 @@ static int _test_cmd_vdevice_alloc(int fd, __u32 viommu_id, __u32 idev_id, _test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, \ virt_id, vdev_id))

+static int _test_cmd_hw_queue_alloc(int fd, __u32 viommu_id, __u32 type, + __u32 idx, __u64 base_addr, __u64 length, + __u32 *hw_queue_id) +{ + struct iommu_hw_queue_alloc cmd = { + .size = sizeof(cmd), + .viommu_id = viommu_id, + .type = type, + .index = idx, + .nesting_parent_iova = base_addr, + .length = length, + }; + int ret; + + ret = ioctl(fd, IOMMU_HW_QUEUE_ALLOC, &cmd); + if (ret) + return ret; + if (hw_queue_id) + *hw_queue_id = cmd.out_hw_queue_id; + return 0; +} + +#define test_cmd_hw_queue_alloc(viommu_id, type, idx, base_addr, len, out_qid) \ + ASSERT_EQ(0, _test_cmd_hw_queue_alloc(self->fd, viommu_id, type, idx, \ + base_addr, len, out_qid)) +#define test_err_hw_queue_alloc(_errno, viommu_id, type, idx, base_addr, len, \ + out_qid) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_hw_queue_alloc(self->fd, viommu_id, type, idx, \ + base_addr, len, out_qid)) + static int _test_cmd_veventq_alloc(int fd, __u32 viommu_id, __u32 type, __u32 *veventq_id, __u32 *veventq_fd) { diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 38066dfeb2e7..2189e9b119ee 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -150,6 +150,8 @@ to_mock_nested(struct iommu_domain *domain) struct mock_viommu { struct iommufd_viommu core; struct mock_iommu_domain *s2_parent; + struct mock_hw_queue *hw_queue[IOMMU_TEST_HW_QUEUE_MAX]; + struct mutex queue_mutex; };

static inline struct mock_viommu *to_mock_viommu(struct iommufd_viommu *viommu) @@ -157,6 +159,19 @@ static inline struct mock_viommu *to_mock_viommu(struct iommufd_viommu *viommu) return container_of(viommu, struct mock_viommu, core); }

+struct mock_hw_queue { + struct iommufd_hw_queue core; + struct mock_viommu *mock_viommu; + struct mock_hw_queue *prev; + u16 index; +}; + +static inline struct mock_hw_queue * +to_mock_hw_queue(struct iommufd_hw_queue *hw_queue) +{ + return container_of(hw_queue, struct mock_hw_queue, core); +} + enum selftest_obj_type { TYPE_IDEV, }; @@ -670,9 +685,11 @@ static void mock_viommu_destroy(struct iommufd_viommu *viommu) { struct mock_iommu_device *mock_iommu = container_of( viommu->iommu_dev, struct mock_iommu_device, iommu_dev); + struct mock_viommu *mock_viommu = to_mock_viommu(viommu);

if (refcount_dec_and_test(&mock_iommu->users)) complete(&mock_iommu->complete); + mutex_destroy(&mock_viommu->queue_mutex);

/* iommufd core frees mock_viommu and viommu */ } @@ -764,10 +781,86 @@ static int mock_viommu_cache_invalidate(struct iommufd_viommu *viommu, return rc; }

+static size_t mock_viommu_get_hw_queue_size(struct iommufd_viommu *viommu, + enum iommu_hw_queue_type queue_type) +{ + if (queue_type != IOMMU_HW_QUEUE_TYPE_SELFTEST) + return 0; + return HW_QUEUE_STRUCT_SIZE(struct mock_hw_queue, core); +} + +static void mock_hw_queue_destroy(struct iommufd_hw_queue *hw_queue) +{ + struct mock_hw_queue *mock_hw_queue = to_mock_hw_queue(hw_queue); + struct mock_viommu *mock_viommu = mock_hw_queue->mock_viommu; + + mutex_lock(&mock_viommu->queue_mutex); + mock_viommu->hw_queue[mock_hw_queue->index] = NULL; + if (mock_hw_queue->prev) + iommufd_hw_queue_undepend(mock_hw_queue, mock_hw_queue->prev, + core); + mutex_unlock(&mock_viommu->queue_mutex); +} + +/* Test iommufd_hw_queue_depend/undepend() */ +static int mock_hw_queue_init_phys(struct iommufd_hw_queue *hw_queue, u32 index, + phys_addr_t base_addr_pa) +{ + struct mock_viommu *mock_viommu = to_mock_viommu(hw_queue->viommu); + struct mock_hw_queue *mock_hw_queue = to_mock_hw_queue(hw_queue); + struct mock_hw_queue *prev = NULL; + int rc = 0; + + if (index >= IOMMU_TEST_HW_QUEUE_MAX) + return -EINVAL; + + mutex_lock(&mock_viommu->queue_mutex); + + if (mock_viommu->hw_queue[index]) { + rc = -EEXIST; + goto unlock; + } + + if (index) { + prev = mock_viommu->hw_queue[index - 1]; + if (!prev) { + rc = -EIO; + goto unlock; + } + } + + /* + * Test to catch a kernel bug if the core converted the physical address + * incorrectly. Let mock_domain_iova_to_phys() WARN_ON if it fails. + */ + if (base_addr_pa != iommu_iova_to_phys(&mock_viommu->s2_parent->domain, + hw_queue->base_addr)) { + rc = -EFAULT; + goto unlock; + } + + if (prev) { + rc = iommufd_hw_queue_depend(mock_hw_queue, prev, core); + if (rc) + goto unlock; + } + + mock_hw_queue->prev = prev; + mock_hw_queue->mock_viommu = mock_viommu; + mock_viommu->hw_queue[index] = mock_hw_queue; + + hw_queue->destroy = &mock_hw_queue_destroy; +unlock: + mutex_unlock(&mock_viommu->queue_mutex); + return rc; +} + static struct iommufd_viommu_ops mock_viommu_ops = { .destroy = mock_viommu_destroy, .alloc_domain_nested = mock_viommu_alloc_domain_nested, .cache_invalidate = mock_viommu_cache_invalidate, + .get_hw_queue_size = mock_viommu_get_hw_queue_size, + .hw_queue_init_phys = mock_hw_queue_init_phys, };

static size_t mock_get_viommu_size(struct device *dev, @@ -784,6 +877,7 @@ static int mock_viommu_init(struct iommufd_viommu *viommu, { struct mock_iommu_device *mock_iommu = container_of( viommu->iommu_dev, struct mock_iommu_device, iommu_dev); + struct mock_viommu *mock_viommu = to_mock_viommu(viommu); struct iommu_viommu_selftest data; int rc;

@@ -801,6 +895,9 @@ static int mock_viommu_init(struct iommufd_viommu *viommu, }

refcount_inc(&mock_iommu->users); + mutex_init(&mock_viommu->queue_mutex); + mock_viommu->s2_parent = to_mock_domain(parent_domain); + viommu->ops = &mock_viommu_ops; return 0; } diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index a9dfcce5e1b2..6b88c250b505 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -3032,6 +3032,64 @@ TEST_F(iommufd_viommu, vdevice_cache) } }

+TEST_F(iommufd_viommu, hw_queue) +{ + __u64 iova = MOCK_APERTURE_START, iova2; + uint32_t viommu_id = self->viommu_id; + uint32_t hw_queue_id[2]; + + if (!viommu_id) + SKIP(return, "Skipping test for variant no_viommu"); + + /* Fail IOMMU_HW_QUEUE_TYPE_DEFAULT */ + test_err_hw_queue_alloc(EOPNOTSUPP, viommu_id, + IOMMU_HW_QUEUE_TYPE_DEFAULT, 0, iova, PAGE_SIZE, + &hw_queue_id[0]); + /* Fail queue addr and length */ + test_err_hw_queue_alloc(EINVAL, viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, + 0, iova, 0, &hw_queue_id[0]); + test_err_hw_queue_alloc(EOVERFLOW, viommu_id, + IOMMU_HW_QUEUE_TYPE_SELFTEST, 0, ~(uint64_t)0, + PAGE_SIZE, &hw_queue_id[0]); + /* Fail missing iova */ + test_err_hw_queue_alloc(ENOENT, viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, + 0, iova, PAGE_SIZE, &hw_queue_id[0]); + + /* Map iova */ + test_ioctl_ioas_map(buffer, PAGE_SIZE, &iova); + test_ioctl_ioas_map(buffer + PAGE_SIZE, PAGE_SIZE, &iova2); + + /* Fail index=1 and =MAX; must start from index=0 */ + test_err_hw_queue_alloc(EIO, viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, 1, + iova, PAGE_SIZE, &hw_queue_id[0]); + test_err_hw_queue_alloc(EINVAL, viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, + IOMMU_TEST_HW_QUEUE_MAX, iova, PAGE_SIZE, + &hw_queue_id[0]); + + /* Allocate index=0, declare ownership of the iova */ + test_cmd_hw_queue_alloc(viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, 0, + iova, PAGE_SIZE, &hw_queue_id[0]); + /* Fail duplicate */ + test_err_hw_queue_alloc(EEXIST, viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, + 0, iova, PAGE_SIZE, &hw_queue_id[0]); + /* Fail unmap, due to iova ownership */ + test_err_ioctl_ioas_unmap(EBUSY, iova, PAGE_SIZE); + /* The 2nd page is not pinned, so it can be unmmap */ + test_ioctl_ioas_unmap(iova + PAGE_SIZE, PAGE_SIZE); + + /* Allocate index=1 */ + test_cmd_hw_queue_alloc(viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, 1, + iova, PAGE_SIZE, &hw_queue_id[1]); + /* Fail to destroy, due to dependency */ + EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, hw_queue_id[0])); + + /* Destroy in descending order */ + test_ioctl_destroy(hw_queue_id[1]); + test_ioctl_destroy(hw_queue_id[0]); + /* Now it can unmap the first page */ + test_ioctl_ioas_unmap(iova, PAGE_SIZE); +} + FIXTURE(iommufd_device_pasid) { int fd; diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index f7ccf1822108..41c685bbd252 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -634,6 +634,7 @@ TEST_FAIL_NTH(basic_fail_nth, device) uint32_t idev_id; uint32_t hwpt_id; uint32_t viommu_id; + uint32_t hw_queue_id; uint32_t vdev_id; __u64 iova;

@@ -696,6 +697,11 @@ TEST_FAIL_NTH(basic_fail_nth, device) if (_test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, 0, &vdev_id)) return -1;

+ if (_test_cmd_hw_queue_alloc(self->fd, viommu_id, + IOMMU_HW_QUEUE_TYPE_SELFTEST, 0, iova, + PAGE_SIZE, &hw_queue_id)) + return -1; + if (_test_ioctl_fault_alloc(self->fd, &fault_id, &fault_fd)) return -1; close(fault_fd);

Extend the loopback test to a new mmap page.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_test.h | 4 +++ tools/testing/selftests/iommu/iommufd_utils.h | 4 +++ drivers/iommu/iommufd/selftest.c | 33 ++++++++++++++++++- tools/testing/selftests/iommu/iommufd.c | 19 +++++++++++ 4 files changed, 59 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 51cd744a354f..8fc618b2bcf9 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -232,12 +232,16 @@ struct iommu_hwpt_invalidate_selftest { * (IOMMU_VIOMMU_TYPE_SELFTEST) * @in_data: Input random data from user space * @out_data: Output data (matching @in_data) to user space + * @out_mmap_offset: The offset argument for mmap syscall + * @out_mmap_length: The length argument for mmap syscall * * Simply set @out_data=@in_data for a loopback test */ struct iommu_viommu_selftest { __u32 in_data; __u32 out_data; + __aligned_u64 out_mmap_offset; + __aligned_u64 out_mmap_length; };

/* Should not be equal to any defined value in enum iommu_viommu_invalidate_data_type */ diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 9a556f99d992..4a1b2bade018 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -56,6 +56,10 @@ static unsigned long PAGE_SIZE; #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER))

+#define test_err_mmap(_errno, length, offset) \ + EXPECT_ERRNO(_errno, (long)mmap(NULL, length, PROT_READ | PROT_WRITE, \ + MAP_SHARED, self->fd, offset)) + static inline void *memfd_mmap(size_t length, int prot, int flags, int *mfd_p) { int mfd_flags = (flags & MAP_HUGETLB) ? MFD_HUGETLB : 0; diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 2189e9b119ee..8b2c44b32530 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -152,6 +152,9 @@ struct mock_viommu { struct mock_iommu_domain *s2_parent; struct mock_hw_queue *hw_queue[IOMMU_TEST_HW_QUEUE_MAX]; struct mutex queue_mutex; + + unsigned long mmap_offset; + u32 *page; /* Mmap page to test u32 type of in_data */ };

static inline struct mock_viommu *to_mock_viommu(struct iommufd_viommu *viommu) @@ -689,6 +692,10 @@ static void mock_viommu_destroy(struct iommufd_viommu *viommu)

if (refcount_dec_and_test(&mock_iommu->users)) complete(&mock_iommu->complete); + if (mock_viommu->mmap_offset) + iommufd_viommu_destroy_mmap(&mock_viommu->core, + mock_viommu->mmap_offset); + free_page((unsigned long)mock_viommu->page); mutex_destroy(&mock_viommu->queue_mutex);

/* iommufd core frees mock_viommu and viommu */ @@ -887,11 +894,28 @@ static int mock_viommu_init(struct iommufd_viommu *viommu, if (rc) return rc;

+ /* Allocate two pages */ + mock_viommu->page = + (u32 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + if (!mock_viommu->page) + return -ENOMEM; + + rc = iommufd_viommu_alloc_mmap(&mock_viommu->core, + __pa(mock_viommu->page), + PAGE_SIZE * 2, + &mock_viommu->mmap_offset); + if (rc) + goto err_free_page; + + /* For loopback tests on both the page and out_data */ + *mock_viommu->page = data.in_data; data.out_data = data.in_data; + data.out_mmap_length = PAGE_SIZE * 2; + data.out_mmap_offset = mock_viommu->mmap_offset; rc = iommu_copy_struct_to_user( user_data, &data, IOMMU_VIOMMU_TYPE_SELFTEST, out_data); if (rc) - return rc; + goto err_destroy_mmap; }

refcount_inc(&mock_iommu->users); @@ -900,6 +924,13 @@ static int mock_viommu_init(struct iommufd_viommu *viommu,

viommu->ops = &mock_viommu_ops; return 0; + +err_destroy_mmap: + iommufd_viommu_destroy_mmap(&mock_viommu->core, + mock_viommu->mmap_offset); +err_free_page: + free_page((unsigned long)mock_viommu->page); + return rc; }

static const struct iommu_ops mock_ops = { diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 6b88c250b505..8b85f6fc8cd0 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -2799,6 +2799,7 @@ TEST_F(iommufd_viommu, viommu_alloc_with_data) struct iommu_viommu_selftest data = { .in_data = 0xbeef, }; + uint32_t *test;

if (!self->device_id) SKIP(return, "Skipping test for variant no_viommu"); @@ -2807,6 +2808,24 @@ TEST_F(iommufd_viommu, viommu_alloc_with_data) IOMMU_VIOMMU_TYPE_SELFTEST, &data, sizeof(data), &self->viommu_id); ASSERT_EQ(data.out_data, data.in_data); + + /* Negative mmap tests -- offset and length cannot be changed */ + test_err_mmap(ENXIO, data.out_mmap_length, + data.out_mmap_offset + PAGE_SIZE); + test_err_mmap(ENXIO, data.out_mmap_length, + data.out_mmap_offset + PAGE_SIZE * 2); + test_err_mmap(ENXIO, data.out_mmap_length / 2, data.out_mmap_offset); + test_err_mmap(ENXIO, data.out_mmap_length * 2, data.out_mmap_offset); + + /* Now do a correct mmap for a loopback test */ + test = mmap(NULL, data.out_mmap_length, PROT_READ | PROT_WRITE, + MAP_SHARED, self->fd, data.out_mmap_offset); + ASSERT_NE(MAP_FAILED, test); + ASSERT_EQ(data.in_data, *test); + + /* The owner of the mmap region should be blocked */ + EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, self->viommu_id)); + munmap(test, data.out_mmap_length); }

TEST_F(iommufd_viommu, vdevice_alloc)

The hw_info uAPI will support a bidirectional data_type field that can be used as an input field for user space to request for a specific info data.

To prepare for the uAPI update, change the iommu layer first: - Add a new IOMMU_HW_INFO_TYPE_DEFAULT as an input, for which driver can output its only (or firstly) supported type - Update the kdoc accordingly - Roll out the type validation in the existing drivers

Reviewed-by: Kevin Tian kevin.tian@intel.com Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 3 ++- include/uapi/linux/iommufd.h | 4 +++- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 4 ++++ drivers/iommu/intel/iommu.c | 4 ++++ drivers/iommu/iommufd/device.c | 3 +++ drivers/iommu/iommufd/selftest.c | 4 ++++ 6 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e06a0fbe4bc7..e8b59ef54e48 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -603,7 +603,8 @@ __iommu_copy_struct_to_user(const struct iommu_user_data *dst_data, * @capable: check capability * @hw_info: report iommu hardware information. The data buffer returned by this * op is allocated in the iommu driver and freed by the caller after - * use. + * use. @type can input a requested type and output a supported type. + * Driver should reject an unsupported data @type input * @domain_alloc: Do not use in new drivers * @domain_alloc_identity: allocate an IDENTITY domain. Drivers should prefer to * use identity_domain instead. This should only be used diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 55459b9eee31..fe4b8f9a3403 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -593,13 +593,15 @@ struct iommu_hw_info_arm_smmuv3 {

/** * enum iommu_hw_info_type - IOMMU Hardware Info Types - * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardware + * @IOMMU_HW_INFO_TYPE_NONE: Output by the drivers that do not report hardware * info + * @IOMMU_HW_INFO_TYPE_DEFAULT: Input to request for a default type * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type * @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type */ enum iommu_hw_info_type { IOMMU_HW_INFO_TYPE_NONE = 0, + IOMMU_HW_INFO_TYPE_DEFAULT = 0, IOMMU_HW_INFO_TYPE_INTEL_VTD = 1, IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2, }; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 170d69162848..eb9fe1f6311a 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -15,6 +15,10 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 __iomem *base_idr; unsigned int i;

+ if (*type != IOMMU_HW_INFO_TYPE_DEFAULT && + *type != IOMMU_HW_INFO_TYPE_ARM_SMMUV3) + return ERR_PTR(-EOPNOTSUPP); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 850f1a6f548c..5f75faffca15 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4098,6 +4098,10 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, struct intel_iommu *iommu = info->iommu; struct iommu_hw_info_vtd *vtd;

+ if (*type != IOMMU_HW_INFO_TYPE_DEFAULT && + *type != IOMMU_HW_INFO_TYPE_INTEL_VTD) + return ERR_PTR(-EOPNOTSUPP); + vtd = kzalloc(sizeof(*vtd), GFP_KERNEL); if (!vtd) return ERR_PTR(-ENOMEM); diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 0567faff5680..14955dc43892 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1512,6 +1512,9 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd) cmd->__reserved[2]) return -EOPNOTSUPP;

+ /* Clear the type field since drivers don't support a random input */ + cmd->out_data_type = IOMMU_HW_INFO_TYPE_DEFAULT; + idev = iommufd_get_device(ucmd, cmd->dev_id); if (IS_ERR(idev)) return PTR_ERR(idev); diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 8b2c44b32530..a5dc36219a90 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -310,6 +310,10 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length, { struct iommu_test_hw_info *info;

+ if (*type != IOMMU_HW_INFO_TYPE_DEFAULT && + *type != IOMMU_HW_INFO_TYPE_SELFTEST) + return ERR_PTR(-EOPNOTSUPP); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM);

Test both IOMMU_HW_INFO_TYPE_DEFAULT and IOMMU_HW_INFO_TYPE_SELFTEST, and add a negative test for an unsupported type.

Also drop the unused mask in test_cmd_get_hw_capabilities() as checkpatch is complaining.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- tools/testing/selftests/iommu/iommufd_utils.h | 33 +++++++++++-------- tools/testing/selftests/iommu/iommufd.c | 32 +++++++++++++----- .../selftests/iommu/iommufd_fail_nth.c | 4 +-- 3 files changed, 46 insertions(+), 23 deletions(-)

diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 4a1b2bade018..5384852ce038 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -761,20 +761,24 @@ static void teardown_iommufd(int fd, struct __test_metadata *_metadata) #endif

/* @data can be NULL */ -static int _test_cmd_get_hw_info(int fd, __u32 device_id, void *data, - size_t data_len, uint32_t *capabilities, - uint8_t *max_pasid) +static int _test_cmd_get_hw_info(int fd, __u32 device_id, __u32 data_type, + void *data, size_t data_len, + uint32_t *capabilities, uint8_t *max_pasid) { struct iommu_test_hw_info *info = (struct iommu_test_hw_info *)data; struct iommu_hw_info cmd = { .size = sizeof(cmd), .dev_id = device_id, .data_len = data_len, + .in_data_type = data_type, .data_uptr = (uint64_t)data, .out_capabilities = 0, }; int ret;

+ if (data_type != IOMMU_HW_INFO_TYPE_DEFAULT) + cmd.flags |= IOMMU_HW_INFO_FLAG_INPUT_TYPE; + ret = ioctl(fd, IOMMU_GET_HW_INFO, &cmd); if (ret) return ret; @@ -817,20 +821,23 @@ static int _test_cmd_get_hw_info(int fd, __u32 device_id, void *data, return 0; }

-#define test_cmd_get_hw_info(device_id, data, data_len) \ - ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, data, \ - data_len, NULL, NULL)) +#define test_cmd_get_hw_info(device_id, data_type, data, data_len) \ + ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, data_type, \ + data, data_len, NULL, NULL))

-#define test_err_get_hw_info(_errno, device_id, data, data_len) \ - EXPECT_ERRNO(_errno, _test_cmd_get_hw_info(self->fd, device_id, data, \ - data_len, NULL, NULL)) +#define test_err_get_hw_info(_errno, device_id, data_type, data, data_len) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_get_hw_info(self->fd, device_id, data_type, \ + data, data_len, NULL, NULL))

-#define test_cmd_get_hw_capabilities(device_id, caps, mask) \ - ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, NULL, \ +#define test_cmd_get_hw_capabilities(device_id, caps) \ + ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, \ + IOMMU_HW_INFO_TYPE_DEFAULT, NULL, \ 0, &caps, NULL))

-#define test_cmd_get_hw_info_pasid(device_id, max_pasid) \ - ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, NULL, \ +#define test_cmd_get_hw_info_pasid(device_id, max_pasid) \ + ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, \ + IOMMU_HW_INFO_TYPE_DEFAULT, NULL, \ 0, NULL, max_pasid))

static int _test_ioctl_fault_alloc(int fd, __u32 *fault_id, __u32 *fault_fd) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 8b85f6fc8cd0..9d5b852d5e19 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -764,19 +764,34 @@ TEST_F(iommufd_ioas, get_hw_info) uint8_t max_pasid = 0;

/* Provide a zero-size user_buffer */ - test_cmd_get_hw_info(self->device_id, NULL, 0); + test_cmd_get_hw_info(self->device_id, + IOMMU_HW_INFO_TYPE_DEFAULT, NULL, 0); /* Provide a user_buffer with exact size */ - test_cmd_get_hw_info(self->device_id, &buffer_exact, sizeof(buffer_exact)); + test_cmd_get_hw_info(self->device_id, + IOMMU_HW_INFO_TYPE_DEFAULT, &buffer_exact, + sizeof(buffer_exact)); + + /* Request for a wrong data_type, and a correct one */ + test_err_get_hw_info(EOPNOTSUPP, self->device_id, + IOMMU_HW_INFO_TYPE_SELFTEST + 1, + &buffer_exact, sizeof(buffer_exact)); + test_cmd_get_hw_info(self->device_id, + IOMMU_HW_INFO_TYPE_SELFTEST, &buffer_exact, + sizeof(buffer_exact)); /* * Provide a user_buffer with size larger than the exact size to check if * kernel zero the trailing bytes. */ - test_cmd_get_hw_info(self->device_id, &buffer_larger, sizeof(buffer_larger)); + test_cmd_get_hw_info(self->device_id, + IOMMU_HW_INFO_TYPE_DEFAULT, &buffer_larger, + sizeof(buffer_larger)); /* * Provide a user_buffer with size smaller than the exact size to check if * the fields within the size range still gets updated. */ - test_cmd_get_hw_info(self->device_id, &buffer_smaller, sizeof(buffer_smaller)); + test_cmd_get_hw_info(self->device_id, + IOMMU_HW_INFO_TYPE_DEFAULT, + &buffer_smaller, sizeof(buffer_smaller)); test_cmd_get_hw_info_pasid(self->device_id, &max_pasid); ASSERT_EQ(0, max_pasid); if (variant->pasid_capable) { @@ -786,9 +801,11 @@ TEST_F(iommufd_ioas, get_hw_info) } } else { test_err_get_hw_info(ENOENT, self->device_id, - &buffer_exact, sizeof(buffer_exact)); + IOMMU_HW_INFO_TYPE_DEFAULT, &buffer_exact, + sizeof(buffer_exact)); test_err_get_hw_info(ENOENT, self->device_id, - &buffer_larger, sizeof(buffer_larger)); + IOMMU_HW_INFO_TYPE_DEFAULT, &buffer_larger, + sizeof(buffer_larger)); } }

@@ -2175,8 +2192,7 @@ TEST_F(iommufd_dirty_tracking, device_dirty_capability)

test_cmd_hwpt_alloc(self->idev_id, self->ioas_id, 0, &hwpt_id); test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); - test_cmd_get_hw_capabilities(self->idev_id, caps, - IOMMU_HW_CAP_DIRTY_TRACKING); + test_cmd_get_hw_capabilities(self->idev_id, caps); ASSERT_EQ(IOMMU_HW_CAP_DIRTY_TRACKING, caps & IOMMU_HW_CAP_DIRTY_TRACKING);

diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index 41c685bbd252..651fc9f13c08 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -667,8 +667,8 @@ TEST_FAIL_NTH(basic_fail_nth, device) &self->stdev_id, NULL, &idev_id)) return -1;

- if (_test_cmd_get_hw_info(self->fd, idev_id, &info, - sizeof(info), NULL, NULL)) + if (_test_cmd_get_hw_info(self->fd, idev_id, IOMMU_HW_INFO_TYPE_DEFAULT, + &info, sizeof(info), NULL, NULL)) return -1;

if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0,

This will be used by Tegra241 CMDQV implementation to report a non-default HW info data.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 7 +++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 8 ++++++-- 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 07589350b2a1..836d5556008e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -721,6 +721,13 @@ struct arm_smmu_impl_ops { int (*init_structures)(struct arm_smmu_device *smmu); struct arm_smmu_cmdq *(*get_secondary_cmdq)( struct arm_smmu_device *smmu, struct arm_smmu_cmdq_ent *ent); + /* + * An implementation should define its own type other than the default + * IOMMU_HW_INFO_TYPE_ARM_SMMUV3. And it must validate the input @type + * to return its own structure. + */ + void *(*hw_info)(struct arm_smmu_device *smmu, u32 *length, + enum iommu_hw_info_type *type); const size_t vsmmu_size; const enum iommu_viommu_type vsmmu_type; int (*vsmmu_init)(struct arm_vsmmu *vsmmu, diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 2ab1c6cf4aac..1cf9646e776f 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -11,13 +11,17 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, enum iommu_hw_info_type *type) { struct arm_smmu_master *master = dev_iommu_priv_get(dev); + const struct arm_smmu_impl_ops *impl_ops = master->smmu->impl_ops; struct iommu_hw_info_arm_smmuv3 *info; u32 __iomem *base_idr; unsigned int i;

if (*type != IOMMU_HW_INFO_TYPE_DEFAULT && - *type != IOMMU_HW_INFO_TYPE_ARM_SMMUV3) - return ERR_PTR(-EOPNOTSUPP); + *type != IOMMU_HW_INFO_TYPE_ARM_SMMUV3) { + if (!impl_ops || !impl_ops->hw_info) + return ERR_PTR(-EOPNOTSUPP); + return impl_ops->hw_info(master->smmu, length, type); + }

info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info)

The current flow of tegra241_cmdqv_remove_vintf() is: 1. For each LVCMDQ, tegra241_vintf_remove_lvcmdq(): a. Disable the LVCMDQ HW b. Release the LVCMDQ SW resource 2. For current VINTF, tegra241_vintf_hw_deinit(): c. Disable all LVCMDQ HWs d. Disable VINTF HW

Obviously, the step 1.a and the step 2.c are redundant.

Since tegra241_vintf_hw_deinit() disables all of its LVCMDQ HWs, it could simplify the flow in tegra241_cmdqv_remove_vintf() by calling that first: 1. For current VINTF, tegra241_vintf_hw_deinit(): a. Disable all LVCMDQ HWs b. Disable VINTF HW 2. Release all LVCMDQ SW resources

Drop tegra241_vintf_remove_lvcmdq(), and move tegra241_vintf_free_lvcmdq() as the new step 2.

Acked-by: Pranjal Shrivastava praan@google.com Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index ba029f7d24ce..8d418c131b1b 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -628,24 +628,17 @@ static int tegra241_cmdqv_init_vintf(struct tegra241_cmdqv *cmdqv, u16 max_idx,

/* Remove Helpers */

-static void tegra241_vintf_remove_lvcmdq(struct tegra241_vintf *vintf, u16 lidx) -{ - tegra241_vcmdq_hw_deinit(vintf->lvcmdqs[lidx]); - tegra241_vintf_free_lvcmdq(vintf, lidx); -} - static void tegra241_cmdqv_remove_vintf(struct tegra241_cmdqv *cmdqv, u16 idx) { struct tegra241_vintf *vintf = cmdqv->vintfs[idx]; u16 lidx;

+ tegra241_vintf_hw_deinit(vintf); + /* Remove LVCMDQ resources */ for (lidx = 0; lidx < vintf->cmdqv->num_lvcmdqs_per_vintf; lidx++) if (vintf->lvcmdqs[lidx]) - tegra241_vintf_remove_lvcmdq(vintf, lidx); - - /* Remove VINTF resources */ - tegra241_vintf_hw_deinit(vintf); + tegra241_vintf_free_lvcmdq(vintf, lidx);

dev_dbg(cmdqv->dev, "VINTF%u: deallocated\n", vintf->idx); tegra241_cmdqv_deinit_vintf(cmdqv, idx);

The CMDQV HW supports a user-space use for virtualization cases. It allows the VM to issue guest-level TLBI or ATC_INV commands directly to the queue and executes them without a VMEXIT, as HW will replace the VMID field in a TLBI command and the SID field in an ATC_INV command with the preset VMID and SID.

This is built upon the vIOMMU infrastructure by allowing VMM to allocate a VINTF (as a vIOMMU object) and assign VCMDQs (HW QUEUE objs) to the VINTF.

So firstly, replace the standard vSMMU model with the VINTF implementation but reuse the standard cache_invalidate op (for unsupported commands) and the standard alloc_domain_nested op (for standard nested STE).

Each VINTF has two 64KB MMIO pages (128B per logical VCMDQ): - Page0 (directly accessed by guest) has all the control and status bits. - Page1 (trapped by VMM) has guest-owned queue memory location/size info.

VMM should trap the emulated VINTF0's page1 of the guest VM for the guest- level VCMDQ location/size info and forward that to the kernel to translate to a physical memory location to program the VCMDQ HW during an allocation call. Then, it should mmap the assigned VINTF's page0 to the VINTF0 page0 of the guest VM. This allows the guest OS to read and write the guest-own VINTF's page0 for direct control of the VCMDQ HW.

For ATC invalidation commands that hold an SID, it requires all devices to register their virtual SIDs to the SID_MATCH registers and their physical SIDs to the pairing SID_REPLACE registers, so that HW can use those as a lookup table to replace those virtual SIDs with the correct physical SIDs. Thus, implement the driver-allocated vDEVICE op with a tegra241_vintf_sid structure to allocate SID_REPLACE and to program the SIDs accordingly.

This enables the HW accelerated feature for NVIDIA Grace CPU. Compared to the standard SMMUv3 operating in the nested translation mode trapping CMDQ for TLBI and ATC_INV commands, this gives a huge performance improvement: 70% to 90% reductions of invalidation time were measured by various DMA unmap tests running in a guest OS.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 7 + include/uapi/linux/iommufd.h | 58 +++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 6 +- .../iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 400 +++++++++++++++++- 4 files changed, 465 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 836d5556008e..aa25156e04a3 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -1056,10 +1056,17 @@ int arm_smmu_attach_prepare_vmaster(struct arm_smmu_attach_state *state, void arm_smmu_attach_commit_vmaster(struct arm_smmu_attach_state *state); void arm_smmu_master_clear_vmaster(struct arm_smmu_master *master); int arm_vmaster_report_event(struct arm_smmu_vmaster *vmaster, u64 *evt); +struct iommu_domain * +arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, + const struct iommu_user_data *user_data); +int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array); #else #define arm_smmu_get_viommu_size NULL #define arm_smmu_hw_info NULL #define arm_vsmmu_init NULL +#define arm_vsmmu_alloc_domain_nested NULL +#define arm_vsmmu_cache_invalidate NULL

static inline int arm_smmu_attach_prepare_vmaster(struct arm_smmu_attach_state *state, diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index d6a3376d5608..4e81610390c7 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -591,6 +591,27 @@ struct iommu_hw_info_arm_smmuv3 { __u32 aidr; };

+/** + * iommu_hw_info_tegra241_cmdqv - NVIDIA Tegra241 CMDQV Hardware Information + * (IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV) + * @flags: Must be 0 + * @version: Version number for the CMDQ-V HW for PARAM bits[03:00] + * @log2vcmdqs: Log2 of the total number of VCMDQs for PARAM bits[07:04] + * @log2vsids: Log2 of the total number of SID replacements for PARAM bits[15:12] + * @__reserved: Must be 0 + * + * VMM can use these fields directly in its emulated global PARAM register. Note + * that only one Virtual Interface (VINTF) should be exposed to a VM, i.e. PARAM + * bits[11:08] should be set to 0 for log2 of the total number of VINTFs. + */ +struct iommu_hw_info_tegra241_cmdqv { + __u32 flags; + __u8 version; + __u8 log2vcmdqs; + __u8 log2vsids; + __u8 __reserved; +}; + /** * enum iommu_hw_info_type - IOMMU Hardware Info Types * @IOMMU_HW_INFO_TYPE_NONE: Output by the drivers that do not report hardware @@ -598,12 +619,15 @@ struct iommu_hw_info_arm_smmuv3 { * @IOMMU_HW_INFO_TYPE_DEFAULT: Input to request for a default type * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type * @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type + * @IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM + * SMMUv3) info type */ enum iommu_hw_info_type { IOMMU_HW_INFO_TYPE_NONE = 0, IOMMU_HW_INFO_TYPE_DEFAULT = 0, IOMMU_HW_INFO_TYPE_INTEL_VTD = 1, IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2, + IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV = 3, };

/** @@ -972,10 +996,29 @@ struct iommu_fault_alloc { * enum iommu_viommu_type - Virtual IOMMU Type * @IOMMU_VIOMMU_TYPE_DEFAULT: Reserved for future use * @IOMMU_VIOMMU_TYPE_ARM_SMMUV3: ARM SMMUv3 driver specific type + * @IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM + * SMMUv3) enabled ARM SMMUv3 type */ enum iommu_viommu_type { IOMMU_VIOMMU_TYPE_DEFAULT = 0, IOMMU_VIOMMU_TYPE_ARM_SMMUV3 = 1, + IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV = 2, +}; + +/** + * struct iommu_viommu_tegra241_cmdqv - NVIDIA Tegra241 CMDQV Virtual Interface + * (IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV) + * @out_vintf_mmap_offset: mmap offset argument for VINTF's page0 + * @out_vintf_mmap_length: mmap length argument for VINTF's page0 + * + * Both @out_vintf_mmap_offset and @out_vintf_mmap_length are reported by kernel + * for user space to mmap the VINTF page0 from the host physical address space + * to the guest physical address space so that a guest kernel can directly R/W + * access to the VINTF page0 in order to control its virtual command queues. + */ +struct iommu_viommu_tegra241_cmdqv { + __aligned_u64 out_vintf_mmap_offset; + __aligned_u64 out_vintf_mmap_length; };

/** @@ -1172,9 +1215,24 @@ struct iommu_veventq_alloc { /** * enum iommu_hw_queue_type - HW Queue Type * @IOMMU_HW_QUEUE_TYPE_DEFAULT: Reserved for future use + * @IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV (extension for ARM + * SMMUv3) Virtual Command Queue (VCMDQ) */ enum iommu_hw_queue_type { IOMMU_HW_QUEUE_TYPE_DEFAULT = 0, + /* + * TEGRA241_CMDQV requirements (otherwise, allocation will fail) + * - alloc starts from the lowest @index=0 in ascending order + * - destroy starts from the last allocated @index in descending order + * - @base_addr must be aligned to @length in bytes and mapped in IOAS + * - @length must be a power of 2, with a minimum 32 bytes and a maximum + * 2 ^ idr[1].CMDQS * 16 bytes (use GET_HW_INFO call to read idr[1] + * from struct iommu_hw_info_arm_smmuv3) + * - suggest to back the queue memory with contiguous physical pages or + * a single huge page with alignment of the queue size, and limit the + * emulated vSMMU's IDR1.CMDQS to log2(huge page size / 16 bytes) + */ + IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV = 1, };

/** diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 1cf9646e776f..d9bea8f1f636 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -225,7 +225,7 @@ static int arm_smmu_validate_vste(struct iommu_hwpt_arm_smmuv3 *arg, return 0; }

-static struct iommu_domain * +struct iommu_domain * arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, const struct iommu_user_data *user_data) { @@ -336,8 +336,8 @@ static int arm_vsmmu_convert_user_cmd(struct arm_vsmmu *vsmmu, return 0; }

-static int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, - struct iommu_user_data_array *array) +int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array) { struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core); struct arm_smmu_device *smmu = vsmmu->smmu; diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index 869c90b660c1..3eeb8444fadf 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -8,7 +8,9 @@ #include <linux/dma-mapping.h> #include <linux/interrupt.h> #include <linux/iommu.h> +#include <linux/iommufd.h> #include <linux/iopoll.h> +#include <uapi/linux/iommufd.h>

#include <acpi/acpixf.h>

@@ -26,8 +28,10 @@ #define CMDQV_EN BIT(0)

#define TEGRA241_CMDQV_PARAM 0x0004 +#define CMDQV_NUM_SID_PER_VM_LOG2 GENMASK(15, 12) #define CMDQV_NUM_VINTF_LOG2 GENMASK(11, 8) #define CMDQV_NUM_VCMDQ_LOG2 GENMASK(7, 4) +#define CMDQV_VER GENMASK(3, 0)

#define TEGRA241_CMDQV_STATUS 0x0008 #define CMDQV_ENABLED BIT(0) @@ -53,6 +57,9 @@ #define VINTF_STATUS GENMASK(3, 1) #define VINTF_ENABLED BIT(0)

+#define TEGRA241_VINTF_SID_MATCH(s) (0x0040 + 0x4*(s)) +#define TEGRA241_VINTF_SID_REPLACE(s) (0x0080 + 0x4*(s)) + #define TEGRA241_VINTF_LVCMDQ_ERR_MAP_64(m) \ (0x00C0 + 0x8*(m)) #define LVCMDQ_ERR_MAP_NUM_64 2 @@ -114,16 +121,20 @@ MODULE_PARM_DESC(bypass_vcmdq,

/** * struct tegra241_vcmdq - Virtual Command Queue + * @core: Embedded iommufd_hw_queue structure * @idx: Global index in the CMDQV * @lidx: Local index in the VINTF * @enabled: Enable status * @cmdqv: Parent CMDQV pointer * @vintf: Parent VINTF pointer + * @prev: Previous LVCMDQ to depend on * @cmdq: Command Queue struct * @page0: MMIO Page0 base address * @page1: MMIO Page1 base address */ struct tegra241_vcmdq { + struct iommufd_hw_queue core; + u16 idx; u16 lidx;

@@ -131,22 +142,30 @@ struct tegra241_vcmdq {

struct tegra241_cmdqv *cmdqv; struct tegra241_vintf *vintf; + struct tegra241_vcmdq *prev; struct arm_smmu_cmdq cmdq;

void __iomem *page0; void __iomem *page1; }; +#define hw_queue_to_vcmdq(v) container_of(v, struct tegra241_vcmdq, core)

/** * struct tegra241_vintf - Virtual Interface + * @vsmmu: Embedded arm_vsmmu structure * @idx: Global index in the CMDQV * @enabled: Enable status * @hyp_own: Owned by hypervisor (in-kernel) * @cmdqv: Parent CMDQV pointer * @lvcmdqs: List of logical VCMDQ pointers + * @lvcmdq_mutex: Lock to serialize user-allocated lvcmdqs * @base: MMIO base address + * @mmap_offset: Offset argument for mmap() syscall + * @sids: Stream ID mapping resources */ struct tegra241_vintf { + struct arm_vsmmu vsmmu; + u16 idx;

bool enabled; @@ -154,19 +173,41 @@ struct tegra241_vintf {

struct tegra241_cmdqv *cmdqv; struct tegra241_vcmdq **lvcmdqs; + struct mutex lvcmdq_mutex; /* user space race */

void __iomem *base; + unsigned long mmap_offset; + + struct ida sids; +}; +#define viommu_to_vintf(v) container_of(v, struct tegra241_vintf, vsmmu.core) + +/** + * struct tegra241_vintf_sid - Virtual Interface Stream ID Mapping + * @core: Embedded iommufd_vdevice structure, holding virtual Stream ID + * @vintf: Parent VINTF pointer + * @sid: Physical Stream ID + * @idx: Mapping index in the VINTF + */ +struct tegra241_vintf_sid { + struct iommufd_vdevice core; + struct tegra241_vintf *vintf; + u32 sid; + u8 idx; }; +#define vdev_to_vsid(v) container_of(v, struct tegra241_vintf_sid, core)

/** * struct tegra241_cmdqv - CMDQ-V for SMMUv3 * @smmu: SMMUv3 device * @dev: CMDQV device * @base: MMIO base address + * @base_phys: MMIO physical base address, for mmap * @irq: IRQ number * @num_vintfs: Total number of VINTFs * @num_vcmdqs: Total number of VCMDQs * @num_lvcmdqs_per_vintf: Number of logical VCMDQs per VINTF + * @num_sids_per_vintf: Total number of SID mappings per VINTF * @vintf_ids: VINTF id allocator * @vintfs: List of VINTFs */ @@ -175,12 +216,14 @@ struct tegra241_cmdqv { struct device *dev;

void __iomem *base; + phys_addr_t base_phys; int irq;

/* CMDQV Hardware Params */ u16 num_vintfs; u16 num_vcmdqs; u16 num_lvcmdqs_per_vintf; + u16 num_sids_per_vintf;

struct ida vintf_ids;

@@ -351,6 +394,29 @@ tegra241_cmdqv_get_cmdq(struct arm_smmu_device *smmu,

/* HW Reset Functions */

+/* + * When a guest-owned VCMDQ is disabled, if the guest did not enqueue a CMD_SYNC + * following an ATC_INV command at the end of the guest queue while this ATC_INV + * is timed out, the TIMEOUT will not be reported until this VCMDQ gets assigned + * to the next VM, which will be a false alarm potentially causing some unwanted + * behavior in the new VM. Thus, a guest-owned VCMDQ must flush the TIMEOUT when + * it gets disabled. This can be done by just issuing a CMD_SYNC to SMMU CMDQ. + */ +static void tegra241_vcmdq_hw_flush_timeout(struct tegra241_vcmdq *vcmdq) +{ + struct arm_smmu_device *smmu = &vcmdq->cmdqv->smmu; + u64 cmd_sync[CMDQ_ENT_DWORDS] = {}; + + cmd_sync[0] = FIELD_PREP(CMDQ_0_OP, CMDQ_OP_CMD_SYNC) | + FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_NONE); + + /* + * It does not hurt to insert another CMD_SYNC, taking advantage of the + * arm_smmu_cmdq_issue_cmdlist() that waits for the CMD_SYNC completion. + */ + arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, cmd_sync, 1, true); +} + /* This function is for LVCMDQ, so @vcmdq must not be unmapped yet */ static void tegra241_vcmdq_hw_deinit(struct tegra241_vcmdq *vcmdq) { @@ -364,6 +430,8 @@ static void tegra241_vcmdq_hw_deinit(struct tegra241_vcmdq *vcmdq) readl_relaxed(REG_VCMDQ_PAGE0(vcmdq, GERROR)), readl_relaxed(REG_VCMDQ_PAGE0(vcmdq, CONS))); } + tegra241_vcmdq_hw_flush_timeout(vcmdq); + writel_relaxed(0, REG_VCMDQ_PAGE0(vcmdq, PROD)); writel_relaxed(0, REG_VCMDQ_PAGE0(vcmdq, CONS)); writeq_relaxed(0, REG_VCMDQ_PAGE1(vcmdq, BASE)); @@ -420,6 +488,7 @@ static void tegra241_vcmdq_unmap_lvcmdq(struct tegra241_vcmdq *vcmdq) static void tegra241_vintf_hw_deinit(struct tegra241_vintf *vintf) { u16 lidx = vintf->cmdqv->num_lvcmdqs_per_vintf; + int sidx;

/* HW requires to unmap LVCMDQs in descending order */ while (lidx--) { @@ -429,6 +498,10 @@ static void tegra241_vintf_hw_deinit(struct tegra241_vintf *vintf) } } vintf_write_config(vintf, 0); + for (sidx = 0; sidx < vintf->cmdqv->num_sids_per_vintf; sidx++) { + writel(0, REG_VINTF(vintf, SID_MATCH(sidx))); + writel(0, REG_VINTF(vintf, SID_REPLACE(sidx))); + } }

/* Map a global VCMDQ to the pre-assigned LVCMDQ */ @@ -457,7 +530,8 @@ static int tegra241_vintf_hw_init(struct tegra241_vintf *vintf, bool hyp_own) * whether enabling it here or not, as !HYP_OWN cmdq HWs only support a * restricted set of supported commands. */ - regval = FIELD_PREP(VINTF_HYP_OWN, hyp_own); + regval = FIELD_PREP(VINTF_HYP_OWN, hyp_own) | + FIELD_PREP(VINTF_VMID, vintf->vsmmu.vmid); writel(regval, REG_VINTF(vintf, CONFIG));

ret = vintf_write_config(vintf, regval | VINTF_EN); @@ -584,7 +658,9 @@ static void tegra241_vintf_free_lvcmdq(struct tegra241_vintf *vintf, u16 lidx)

dev_dbg(vintf->cmdqv->dev, "%sdeallocated\n", lvcmdq_error_header(vcmdq, header, 64)); - kfree(vcmdq); + /* Guest-owned VCMDQ is free-ed with hw_queue by iommufd core */ + if (vcmdq->vintf->hyp_own) + kfree(vcmdq); }

static struct tegra241_vcmdq * @@ -671,7 +747,13 @@ static void tegra241_cmdqv_remove_vintf(struct tegra241_cmdqv *cmdqv, u16 idx)

dev_dbg(cmdqv->dev, "VINTF%u: deallocated\n", vintf->idx); tegra241_cmdqv_deinit_vintf(cmdqv, idx); - kfree(vintf); + if (!vintf->hyp_own) { + mutex_destroy(&vintf->lvcmdq_mutex); + ida_destroy(&vintf->sids); + /* Guest-owned VINTF is free-ed with viommu by iommufd core */ + } else { + kfree(vintf); + } }

static void tegra241_cmdqv_remove(struct arm_smmu_device *smmu) @@ -699,10 +781,45 @@ static void tegra241_cmdqv_remove(struct arm_smmu_device *smmu) put_device(cmdqv->dev); /* smmu->impl_dev */ }

+static int +tegra241_cmdqv_init_vintf_user(struct arm_vsmmu *vsmmu, + const struct iommu_user_data *user_data); + +static void *tegra241_cmdqv_hw_info(struct arm_smmu_device *smmu, u32 *length, + enum iommu_hw_info_type *type) +{ + struct tegra241_cmdqv *cmdqv = + container_of(smmu, struct tegra241_cmdqv, smmu); + struct iommu_hw_info_tegra241_cmdqv *info; + u32 regval; + + if (*type != IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV) + return ERR_PTR(-EOPNOTSUPP); + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return ERR_PTR(-ENOMEM); + + regval = readl_relaxed(REG_CMDQV(cmdqv, PARAM)); + info->log2vcmdqs = ilog2(cmdqv->num_lvcmdqs_per_vintf); + info->log2vsids = ilog2(cmdqv->num_sids_per_vintf); + info->version = FIELD_GET(CMDQV_VER, regval); + + *length = sizeof(*info); + *type = IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV; + return info; +} + static struct arm_smmu_impl_ops tegra241_cmdqv_impl_ops = { + /* For in-kernel use */ .get_secondary_cmdq = tegra241_cmdqv_get_cmdq, .device_reset = tegra241_cmdqv_hw_reset, .device_remove = tegra241_cmdqv_remove, + /* For user-space use */ + .hw_info = tegra241_cmdqv_hw_info, + .vsmmu_size = VIOMMU_STRUCT_SIZE(struct tegra241_vintf, vsmmu.core), + .vsmmu_type = IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV, + .vsmmu_init = tegra241_cmdqv_init_vintf_user, };

/* Probe Functions */ @@ -844,6 +961,7 @@ __tegra241_cmdqv_probe(struct arm_smmu_device *smmu, struct resource *res, cmdqv->irq = irq; cmdqv->base = base; cmdqv->dev = smmu->impl_dev; + cmdqv->base_phys = res->start;

if (cmdqv->irq > 0) { ret = request_threaded_irq(irq, NULL, tegra241_cmdqv_isr, @@ -860,6 +978,8 @@ __tegra241_cmdqv_probe(struct arm_smmu_device *smmu, struct resource *res, cmdqv->num_vintfs = 1 << FIELD_GET(CMDQV_NUM_VINTF_LOG2, regval); cmdqv->num_vcmdqs = 1 << FIELD_GET(CMDQV_NUM_VCMDQ_LOG2, regval); cmdqv->num_lvcmdqs_per_vintf = cmdqv->num_vcmdqs / cmdqv->num_vintfs; + cmdqv->num_sids_per_vintf = + 1 << FIELD_GET(CMDQV_NUM_SID_PER_VM_LOG2, regval);

cmdqv->vintfs = kcalloc(cmdqv->num_vintfs, sizeof(*cmdqv->vintfs), GFP_KERNEL); @@ -913,3 +1033,277 @@ struct arm_smmu_device *tegra241_cmdqv_probe(struct arm_smmu_device *smmu) put_device(smmu->impl_dev); return ERR_PTR(-ENODEV); } + +/* User space VINTF and VCMDQ Functions */ + +static size_t tegra241_vintf_get_vcmdq_size(struct iommufd_viommu *viommu, + enum iommu_hw_queue_type queue_type) +{ + if (queue_type != IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV) + return 0; + return HW_QUEUE_STRUCT_SIZE(struct tegra241_vcmdq, core); +} + +static int tegra241_vcmdq_hw_init_user(struct tegra241_vcmdq *vcmdq) +{ + char header[64]; + + /* Configure the vcmdq only; User space does the enabling */ + writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); + + dev_dbg(vcmdq->cmdqv->dev, "%sinited at host PA 0x%llx size 0x%lx\n", + lvcmdq_error_header(vcmdq, header, 64), + vcmdq->cmdq.q.q_base & VCMDQ_ADDR, + 1UL << (vcmdq->cmdq.q.q_base & VCMDQ_LOG2SIZE)); + return 0; +} + +static void +tegra241_vintf_destroy_lvcmdq_user(struct iommufd_hw_queue *hw_queue) +{ + struct tegra241_vcmdq *vcmdq = hw_queue_to_vcmdq(hw_queue); + + mutex_lock(&vcmdq->vintf->lvcmdq_mutex); + tegra241_vcmdq_hw_deinit(vcmdq); + tegra241_vcmdq_unmap_lvcmdq(vcmdq); + tegra241_vintf_free_lvcmdq(vcmdq->vintf, vcmdq->lidx); + if (vcmdq->prev) + iommufd_hw_queue_undepend(vcmdq, vcmdq->prev, core); + mutex_unlock(&vcmdq->vintf->lvcmdq_mutex); +} + +static int tegra241_vintf_alloc_lvcmdq_user(struct iommufd_hw_queue *hw_queue, + u32 lidx, phys_addr_t base_addr_pa) +{ + struct tegra241_vintf *vintf = viommu_to_vintf(hw_queue->viommu); + struct tegra241_vcmdq *vcmdq = hw_queue_to_vcmdq(hw_queue); + struct tegra241_cmdqv *cmdqv = vintf->cmdqv; + struct arm_smmu_device *smmu = &cmdqv->smmu; + struct tegra241_vcmdq *prev = NULL; + u32 log2size, max_n_shift; + char header[64]; + int ret; + + if (hw_queue->type != IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV) + return -EOPNOTSUPP; + if (lidx >= cmdqv->num_lvcmdqs_per_vintf) + return -EINVAL; + + mutex_lock(&vintf->lvcmdq_mutex); + + if (vintf->lvcmdqs[lidx]) { + ret = -EEXIST; + goto unlock; + } + + /* + * HW requires to map LVCMDQs in ascending order, so reject if the + * previous lvcmdqs is not allocated yet. + */ + if (lidx) { + prev = vintf->lvcmdqs[lidx - 1]; + if (!prev) { + ret = -EIO; + goto unlock; + } + } + + /* + * hw_queue->length must be a power of 2, in range of + * [ 32, 2 ^ (idr[1].CMDQS + CMDQ_ENT_SZ_SHIFT) ] + */ + max_n_shift = FIELD_GET(IDR1_CMDQS, + readl_relaxed(smmu->base + ARM_SMMU_IDR1)); + if (!is_power_of_2(hw_queue->length) || hw_queue->length < 32 || + hw_queue->length > (1 << (max_n_shift + CMDQ_ENT_SZ_SHIFT))) { + ret = -EINVAL; + goto unlock; + } + log2size = ilog2(hw_queue->length) - CMDQ_ENT_SZ_SHIFT; + + /* base_addr_pa must be aligned to hw_queue->length */ + if (base_addr_pa & ~VCMDQ_ADDR || + base_addr_pa & (hw_queue->length - 1)) { + ret = -EINVAL; + goto unlock; + } + + /* + * HW requires to unmap LVCMDQs in descending order, so destroy() must + * follow this rule. Set a dependency on its previous LVCMDQ so iommufd + * core will help enforce it. + */ + if (prev) { + ret = iommufd_hw_queue_depend(vcmdq, prev, core); + if (ret) + goto unlock; + } + vcmdq->prev = prev; + + ret = tegra241_vintf_init_lvcmdq(vintf, lidx, vcmdq); + if (ret) + goto undepend_vcmdq; + + dev_dbg(cmdqv->dev, "%sallocated\n", + lvcmdq_error_header(vcmdq, header, 64)); + + tegra241_vcmdq_map_lvcmdq(vcmdq); + + vcmdq->cmdq.q.q_base = base_addr_pa & VCMDQ_ADDR; + vcmdq->cmdq.q.q_base |= log2size; + + ret = tegra241_vcmdq_hw_init_user(vcmdq); + if (ret) + goto unmap_lvcmdq; + + hw_queue->destroy = &tegra241_vintf_destroy_lvcmdq_user; + mutex_unlock(&vintf->lvcmdq_mutex); + return 0; + +unmap_lvcmdq: + tegra241_vcmdq_unmap_lvcmdq(vcmdq); + tegra241_vintf_deinit_lvcmdq(vintf, lidx); +undepend_vcmdq: + if (vcmdq->prev) + iommufd_hw_queue_undepend(vcmdq, vcmdq->prev, core); +unlock: + mutex_unlock(&vintf->lvcmdq_mutex); + return ret; +} + +static void tegra241_cmdqv_destroy_vintf_user(struct iommufd_viommu *viommu) +{ + struct tegra241_vintf *vintf = viommu_to_vintf(viommu); + + if (vintf->mmap_offset) + iommufd_viommu_destroy_mmap(&vintf->vsmmu.core, + vintf->mmap_offset); + tegra241_cmdqv_remove_vintf(vintf->cmdqv, vintf->idx); +} + +static void tegra241_vintf_destroy_vsid(struct iommufd_vdevice *vdev) +{ + struct tegra241_vintf_sid *vsid = vdev_to_vsid(vdev); + struct tegra241_vintf *vintf = vsid->vintf; + + writel(0, REG_VINTF(vintf, SID_MATCH(vsid->idx))); + writel(0, REG_VINTF(vintf, SID_REPLACE(vsid->idx))); + ida_free(&vintf->sids, vsid->idx); + dev_dbg(vintf->cmdqv->dev, + "VINTF%u: deallocated SID_REPLACE%d for pSID=%x\n", vintf->idx, + vsid->idx, vsid->sid); +} + +static int tegra241_vintf_init_vsid(struct iommufd_vdevice *vdev) +{ + struct arm_smmu_master *master = dev_iommu_priv_get(vdev->dev); + struct tegra241_vintf *vintf = viommu_to_vintf(vdev->viommu); + struct tegra241_vintf_sid *vsid = vdev_to_vsid(vdev); + struct arm_smmu_stream *stream = &master->streams[0]; + u64 virt_sid = vdev->virt_id; + int sidx; + + if (virt_sid > UINT_MAX) + return -EINVAL; + + WARN_ON_ONCE(master->num_streams != 1); + + /* Find an empty pair of SID_REPLACE and SID_MATCH */ + sidx = ida_alloc_max(&vintf->sids, vintf->cmdqv->num_sids_per_vintf - 1, + GFP_KERNEL); + if (sidx < 0) + return sidx; + + writel(stream->id, REG_VINTF(vintf, SID_REPLACE(sidx))); + writel(virt_sid << 1 | 0x1, REG_VINTF(vintf, SID_MATCH(sidx))); + dev_dbg(vintf->cmdqv->dev, + "VINTF%u: allocated SID_REPLACE%d for pSID=%x, vSID=%x\n", + vintf->idx, sidx, stream->id, (u32)virt_sid); + + vsid->idx = sidx; + vsid->vintf = vintf; + vsid->sid = stream->id; + + vdev->destroy = &tegra241_vintf_destroy_vsid; + return 0; +} + +static struct iommufd_viommu_ops tegra241_cmdqv_viommu_ops = { + .destroy = tegra241_cmdqv_destroy_vintf_user, + .alloc_domain_nested = arm_vsmmu_alloc_domain_nested, + /* Non-accelerated commands will be still handled by the kernel */ + .cache_invalidate = arm_vsmmu_cache_invalidate, + .vdevice_size = VDEVICE_STRUCT_SIZE(struct tegra241_vintf_sid, core), + .vdevice_init = tegra241_vintf_init_vsid, + .get_hw_queue_size = tegra241_vintf_get_vcmdq_size, + .hw_queue_init_phys = tegra241_vintf_alloc_lvcmdq_user, +}; + +static int +tegra241_cmdqv_init_vintf_user(struct arm_vsmmu *vsmmu, + const struct iommu_user_data *user_data) +{ + struct tegra241_cmdqv *cmdqv = + container_of(vsmmu->smmu, struct tegra241_cmdqv, smmu); + struct tegra241_vintf *vintf = viommu_to_vintf(&vsmmu->core); + struct iommu_viommu_tegra241_cmdqv data; + phys_addr_t page0_base; + int ret; + + if (!user_data) + return -EINVAL; + + ret = iommu_copy_struct_from_user(&data, user_data, + IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV, + out_vintf_mmap_length); + if (ret) + return ret; + + ret = tegra241_cmdqv_init_vintf(cmdqv, cmdqv->num_vintfs - 1, vintf); + if (ret < 0) { + dev_err(cmdqv->dev, "no more available vintf\n"); + return ret; + } + + /* + * Initialize the user-owned VINTF without a LVCMDQ, as it cannot pre- + * allocate a LVCMDQ until user space wants one, for security reasons. + * It is different than the kernel-owned VINTF0, which had pre-assigned + * and pre-allocated global VCMDQs that would be mapped to the LVCMDQs + * by the tegra241_vintf_hw_init() call. + */ + ret = tegra241_vintf_hw_init(vintf, false); + if (ret) + goto deinit_vintf; + + page0_base = cmdqv->base_phys + TEGRA241_VINTFi_PAGE0(vintf->idx); + ret = iommufd_viommu_alloc_mmap(&vintf->vsmmu.core, page0_base, SZ_64K, + &vintf->mmap_offset); + if (ret) + goto hw_deinit_vintf; + + data.out_vintf_mmap_length = SZ_64K; + data.out_vintf_mmap_offset = vintf->mmap_offset; + ret = iommu_copy_struct_to_user(user_data, &data, + IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV, + out_vintf_mmap_length); + if (ret) + goto free_mmap; + + ida_init(&vintf->sids); + mutex_init(&vintf->lvcmdq_mutex); + + dev_dbg(cmdqv->dev, "VINTF%u: allocated with vmid (%d)\n", vintf->idx, + vintf->vsmmu.vmid); + + vsmmu->core.ops = &tegra241_cmdqv_viommu_ops; + return 0; + +free_mmap: + iommufd_viommu_destroy_mmap(&vintf->vsmmu.core, vintf->mmap_offset); +hw_deinit_vintf: + tegra241_vintf_hw_deinit(vintf); +deinit_vintf: + tegra241_cmdqv_deinit_vintf(cmdqv, vintf->idx); + return ret; +}