An object allocator needs to call either iommufd_object_finalize() upon a success or iommufd_object_abort_and_destroy() upon an error code.

To reduce duplication, store a new_obj in the struct iommufd_ucmd and call iommufd_object_finalize/iommufd_object_abort_and_destroy() accordingly in the main function.

This will also ease a driver-allocated object so that a driver can simply return with an error code to trigger an iommufd_object_abort_and_destroy() instead of doing an abort itself.

Similar to iommufd_object_alloc() and __iommufd_object_alloc(), add a pair of helpers: __iommufd_object_alloc_ucmd() and iommufd_object_alloc_ucmd().

Suggested-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 1 + include/linux/iommufd.h | 23 +++++++++++++++++++++++ drivers/iommu/iommufd/driver.c | 18 ++++++++++++++++++ drivers/iommu/iommufd/main.c | 7 +++++++ 4 files changed, 49 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 10899e2cd34a..16767c231580 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -135,6 +135,7 @@ struct iommufd_ucmd { void __user *ubuffer; u32 user_size; void *cmd; + struct iommufd_object *new_obj; };

int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 498c9a768506..47f38034f5e7 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -22,6 +22,7 @@ struct iommu_user_data_array; struct iommufd_access; struct iommufd_ctx; struct iommufd_device; +struct iommufd_ucmd; struct iommufd_viommu_ops; struct page;

@@ -51,6 +52,18 @@ struct iommufd_object { unsigned int id; };

+#define __iommufd_object_alloc_ucmd(ucmd, ptr, type, obj) \ + container_of(_iommufd_object_alloc_ucmd( \ + ucmd, \ + sizeof(*(ptr)) + BUILD_BUG_ON_ZERO( \ + offsetof(typeof(*(ptr)), \ + obj) != 0), \ + type), \ + typeof(*(ptr)), obj) + +#define iommufd_object_alloc_ucmd(ucmd, ptr, type) \ + __iommufd_object_alloc_ucmd(ucmd, ptr, type, obj) + struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx, struct device *dev, u32 *id); void iommufd_device_unbind(struct iommufd_device *idev); @@ -193,6 +206,9 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx) struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, enum iommufd_object_type type); +struct iommufd_object * +_iommufd_object_alloc_ucmd(struct iommufd_ucmd *ucmd, size_t size, + enum iommufd_object_type type); struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id); int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu, @@ -208,6 +224,13 @@ _iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, return ERR_PTR(-EOPNOTSUPP); }

+static inline struct iommufd_object * +_iommufd_object_alloc_ucmd(struct iommufd_ucmd *ucmd, size_t size, + enum iommufd_object_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct device * iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) { diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c index 922cd1fe7ec2..28dec9e09720 100644 --- a/drivers/iommu/iommufd/driver.c +++ b/drivers/iommu/iommufd/driver.c @@ -36,6 +36,24 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, } EXPORT_SYMBOL_NS_GPL(_iommufd_object_alloc, "IOMMUFD");

+struct iommufd_object *_iommufd_object_alloc_ucmd(struct iommufd_ucmd *ucmd, + size_t size, + enum iommufd_object_type type) +{ + struct iommufd_object *new_obj; + + if (ucmd->new_obj) + return ERR_PTR(-EBUSY); + + new_obj = _iommufd_object_alloc(ucmd->ictx, size, type); + if (IS_ERR(new_obj)) + return new_obj; + + ucmd->new_obj = new_obj; + return new_obj; +} +EXPORT_SYMBOL_NS_GPL(_iommufd_object_alloc_ucmd, "IOMMUFD"); + /* Caller should xa_lock(&viommu->vdevs) to protect the return value */ struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 347c56ef44d8..c6d0b446e632 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -416,6 +416,13 @@ static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, if (ret) return ret; ret = op->execute(&ucmd); + + if (ucmd.new_obj) { + if (ret) + iommufd_object_abort_and_destroy(ictx, ucmd.new_obj); + else + iommufd_object_finalize(ictx, ucmd.new_obj); + } return ret; }

Similar to the iommu_copy_struct_from_user helper receiving data from the user space, add an iommu_copy_struct_to_user helper to report output data back to the user space data pointer.

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 --- include/linux/iommu.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0db39f922775..5f9c4eaaaaff 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -562,6 +562,46 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, return 0; }

+/** + * __iommu_copy_struct_to_user - Report iommu driver specific user space data + * @dst_data: Pointer to a struct iommu_user_data for user space data location + * @src_data: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @data_type: The data type of the @src_data. Must match with @dst_data.type + * @data_len: Length of current user data structure, i.e. sizeof(struct _src) + * @min_len: Initial length of user data structure for backward compatibility. + * This should be offsetofend using the last member in the user data + * struct that was initially added to include/uapi/linux/iommufd.h + */ +static inline int +__iommu_copy_struct_to_user(const struct iommu_user_data *dst_data, + void *src_data, unsigned int data_type, + size_t data_len, size_t min_len) +{ + if (WARN_ON(!dst_data || !src_data)) + return -EINVAL; + if (dst_data->type != data_type) + return -EINVAL; + if (dst_data->len < min_len || data_len < dst_data->len) + return -EINVAL; + return copy_struct_to_user(dst_data->uptr, dst_data->len, src_data, + data_len, NULL); +} + +/** + * iommu_copy_struct_to_user - Report iommu driver specific user space data + * @user_data: Pointer to a struct iommu_user_data for user space data location + * @ksrc: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @data_type: The data type of the @ksrc. Must match with @user_data->type + * @min_last: The last member of the data structure @ksrc points in the initial + * version. + * Return 0 for success, otherwise -error. + */ +#define iommu_copy_struct_to_user(user_data, ksrc, data_type, min_last) \ + __iommu_copy_struct_to_user(user_data, ksrc, data_type, sizeof(*ksrc), \ + offsetofend(typeof(*ksrc), min_last)) + /** * struct iommu_ops - iommu ops and capabilities * @capable: check capability

The new type of vIOMMU for tegra241-cmdqv driver needs a driver-specific user data. So, add data_len/uptr to the iommu_viommu_alloc uAPI and pass it in via the viommu_alloc iommu op.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Acked-by: Pranjal Shrivastava praan@google.com Acked-by: Alok Tiwari alok.a.tiwari@oracle.com Reviewed-by: Vasant Hegde vasant.hegde@amd.com Reviewed-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/uapi/linux/iommufd.h | 6 ++++++ drivers/iommu/iommufd/viommu.c | 8 +++++++- 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index f29b6c44655e..272da7324a2b 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -965,6 +965,9 @@ enum iommu_viommu_type { * @dev_id: The device's physical IOMMU will be used to back the virtual IOMMU * @hwpt_id: ID of a nesting parent HWPT to associate to * @out_viommu_id: Output virtual IOMMU ID for the allocated object + * @data_len: Length of the type specific data + * @__reserved: Must be 0 + * @data_uptr: User pointer to a driver-specific virtual IOMMU data * * Allocate a virtual IOMMU object, representing the underlying physical IOMMU's * virtualization support that is a security-isolated slice of the real IOMMU HW @@ -985,6 +988,9 @@ struct iommu_viommu_alloc { __u32 dev_id; __u32 hwpt_id; __u32 out_viommu_id; + __u32 data_len; + __u32 __reserved; + __aligned_u64 data_uptr; }; #define IOMMU_VIOMMU_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VIOMMU_ALLOC)

diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index b50b50ec87da..2b30627d1d8e 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -17,6 +17,11 @@ void iommufd_viommu_destroy(struct iommufd_object *obj) int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) { struct iommu_viommu_alloc *cmd = ucmd->cmd; + const struct iommu_user_data user_data = { + .type = cmd->type, + .uptr = u64_to_user_ptr(cmd->data_uptr), + .len = cmd->data_len, + }; struct iommufd_hwpt_paging *hwpt_paging; struct iommufd_viommu *viommu; struct iommufd_device *idev; @@ -48,7 +53,8 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) }

viommu = ops->viommu_alloc(idev->dev, hwpt_paging->common.domain, ucmd, - cmd->type, NULL); + cmd->type, + user_data.len ? &user_data : NULL); if (IS_ERR(viommu)) { rc = PTR_ERR(viommu); goto out_put_hwpt;

Extend the existing test_cmd/err_viommu_alloc helpers to accept optional user data. And add a TEST_F for a 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 --- tools/testing/selftests/iommu/iommufd_utils.h | 21 ++++++++----- tools/testing/selftests/iommu/iommufd.c | 30 ++++++++++++++----- .../selftests/iommu/iommufd_fail_nth.c | 5 ++-- 3 files changed, 39 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 72f6636e5d90..a5d4cbd089ba 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -897,7 +897,8 @@ static int _test_cmd_trigger_iopf(int fd, __u32 device_id, __u32 pasid, pasid, fault_fd))

static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id, - __u32 type, __u32 flags, __u32 *viommu_id) + __u32 flags, __u32 type, void *data, + __u32 data_len, __u32 *viommu_id) { struct iommu_viommu_alloc cmd = { .size = sizeof(cmd), @@ -905,6 +906,8 @@ static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id, .type = type, .dev_id = device_id, .hwpt_id = hwpt_id, + .data_uptr = (uint64_t)data, + .data_len = data_len, }; int ret;

@@ -916,13 +919,15 @@ static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id, return 0; }

-#define test_cmd_viommu_alloc(device_id, hwpt_id, type, viommu_id) \ - ASSERT_EQ(0, _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, \ - type, 0, viommu_id)) -#define test_err_viommu_alloc(_errno, device_id, hwpt_id, type, viommu_id) \ - EXPECT_ERRNO(_errno, \ - _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, \ - type, 0, viommu_id)) +#define test_cmd_viommu_alloc(device_id, hwpt_id, type, data, data_len, \ + viommu_id) \ + ASSERT_EQ(0, _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, 0, \ + type, data, data_len, viommu_id)) +#define test_err_viommu_alloc(_errno, device_id, hwpt_id, type, data, \ + data_len, viommu_id) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, 0, \ + type, data, data_len, viommu_id))

static int _test_cmd_vdevice_alloc(int fd, __u32 viommu_id, __u32 idev_id, __u64 virt_id, __u32 *vdev_id) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 1a8e85afe9aa..f22388dfacad 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -2688,7 +2688,7 @@ FIXTURE_SETUP(iommufd_viommu)

/* Allocate a vIOMMU taking refcount of the parent hwpt */ test_cmd_viommu_alloc(self->device_id, self->hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, &self->viommu_id);

/* Allocate a regular nested hwpt */ @@ -2727,24 +2727,27 @@ TEST_F(iommufd_viommu, viommu_negative_tests) if (self->device_id) { /* Negative test -- invalid hwpt (hwpt_id=0) */ test_err_viommu_alloc(ENOENT, device_id, 0, - IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + NULL);

/* Negative test -- not a nesting parent hwpt */ test_cmd_hwpt_alloc(device_id, ioas_id, 0, &hwpt_id); test_err_viommu_alloc(EINVAL, device_id, hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + NULL); test_ioctl_destroy(hwpt_id);

/* Negative test -- unsupported viommu type */ test_err_viommu_alloc(EOPNOTSUPP, device_id, self->hwpt_id, - 0xdead, NULL); + 0xdead, NULL, 0, NULL); EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, self->hwpt_id)); EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, self->viommu_id)); } else { test_err_viommu_alloc(ENOENT, self->device_id, self->hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + NULL); } }

@@ -2791,6 +2794,20 @@ TEST_F(iommufd_viommu, viommu_alloc_nested_iopf) } }

+TEST_F(iommufd_viommu, viommu_alloc_with_data) +{ + struct iommu_viommu_selftest data = { + .in_data = 0xbeef, + }; + + if (self->device_id) { + test_cmd_viommu_alloc(self->device_id, self->hwpt_id, + IOMMU_VIOMMU_TYPE_SELFTEST, &data, + sizeof(data), &self->viommu_id); + ASSERT_EQ(data.out_data, data.in_data); + } +} + TEST_F(iommufd_viommu, vdevice_alloc) { uint32_t viommu_id = self->viommu_id; @@ -3105,8 +3122,7 @@ TEST_F(iommufd_device_pasid, pasid_attach)

/* Allocate a regular nested hwpt based on viommu */ test_cmd_viommu_alloc(self->device_id, parent_hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, - &viommu_id); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, &viommu_id); test_cmd_hwpt_alloc_nested(self->device_id, viommu_id, IOMMU_HWPT_ALLOC_PASID, &nested_hwpt_id[2], diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index e11ec4b121fc..f7ccf1822108 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -688,8 +688,9 @@ TEST_FAIL_NTH(basic_fail_nth, device) IOMMU_HWPT_DATA_NONE, 0, 0)) return -1;

- if (_test_cmd_viommu_alloc(self->fd, idev_id, hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, 0, &viommu_id)) + if (_test_cmd_viommu_alloc(self->fd, idev_id, hwpt_id, 0, + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + &viommu_id)) return -1;

if (_test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, 0, &vdev_id))

The new HW QUEUE object will be added for HW to access the guest queue for HW-accelerated virtualization feature. Some of HW QUEUEs are designed in a way of accessing the guest queue via a host physical address without doing a translation using the nesting parent IO page table, while others can use the guest physical address. For the former case, kernel working with a VMM needs to pin the physical pages backing the guest memory to lock them when HW QUEUE is accessing, and to ensure those physical pages to be contiguous in the physical address space.

This is very like the existing iommufd_access_pin_pages() that outputs the pinned page list for the caller to test its contiguity.

Move those code from iommufd_access_pin/unpin_pages() and related function for a pair of iopt helpers that can be shared with the HW QUEUE allocator.

Rename check_area_prot() to align with the existing iopt_area helpers, and inline it to the header since iommufd_access_rw() still uses it.

Reviewed-by: Pranjal Shrivastava praan@google.com 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.h | 8 ++ drivers/iommu/iommufd/iommufd_private.h | 6 ++ drivers/iommu/iommufd/device.c | 119 ++---------------------- drivers/iommu/iommufd/io_pagetable.c | 97 +++++++++++++++++++ 4 files changed, 119 insertions(+), 111 deletions(-)

diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index 2f2a47a2f9ee..e04dcc79d309 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -115,6 +115,14 @@ static inline unsigned long iopt_area_iova_to_index(struct iopt_area *area, return iopt_area_start_byte(area, iova) / PAGE_SIZE; }

+static inline bool iopt_area_check_prot(struct iopt_area *area, + unsigned int flags) +{ + if (flags & IOMMUFD_ACCESS_RW_WRITE) + return area->iommu_prot & IOMMU_WRITE; + return area->iommu_prot & IOMMU_READ; +} + #define __make_iopt_iter(name) \ static inline struct iopt_##name *iopt_##name##_iter_first( \ struct io_pagetable *iopt, unsigned long start, \ diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 16767c231580..cef3e0e0bbb2 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -130,6 +130,12 @@ int iopt_cut_iova(struct io_pagetable *iopt, unsigned long *iovas, void iopt_enable_large_pages(struct io_pagetable *iopt); int iopt_disable_large_pages(struct io_pagetable *iopt);

+int iopt_pin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, struct page **out_pages, + unsigned int flags, bool is_owner); +void iopt_unpin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, bool is_owner); + struct iommufd_ucmd { struct iommufd_ctx *ictx; void __user *ubuffer; diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 2b1ed5c8dc5b..0f2bda9e9d84 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1239,59 +1239,17 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova, void iommufd_access_unpin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length) { - struct iopt_area_contig_iter iter; - struct io_pagetable *iopt; - unsigned long last_iova; - struct iopt_area *area; - - if (WARN_ON(!length) || - WARN_ON(check_add_overflow(iova, length - 1, &last_iova))) - return; - - mutex_lock(&access->ioas_lock); + guard(mutex)(&access->ioas_lock); /* * The driver must be doing something wrong if it calls this before an * iommufd_access_attach() or after an iommufd_access_detach(). */ - if (WARN_ON(!access->ioas_unpin)) { - mutex_unlock(&access->ioas_lock); + if (WARN_ON(!access->ioas_unpin)) return; - } - iopt = &access->ioas_unpin->iopt; - - down_read(&iopt->iova_rwsem); - iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) - iopt_area_remove_access( - area, iopt_area_iova_to_index(area, iter.cur_iova), - iopt_area_iova_to_index( - area, - min(last_iova, iopt_area_last_iova(area))), - false); - WARN_ON(!iopt_area_contig_done(&iter)); - up_read(&iopt->iova_rwsem); - mutex_unlock(&access->ioas_lock); + iopt_unpin_pages(&access->ioas_unpin->iopt, iova, length, false); } EXPORT_SYMBOL_NS_GPL(iommufd_access_unpin_pages, "IOMMUFD");

-static bool iopt_area_contig_is_aligned(struct iopt_area_contig_iter *iter) -{ - if (iopt_area_start_byte(iter->area, iter->cur_iova) % PAGE_SIZE) - return false; - - if (!iopt_area_contig_done(iter) && - (iopt_area_start_byte(iter->area, iopt_area_last_iova(iter->area)) % - PAGE_SIZE) != (PAGE_SIZE - 1)) - return false; - return true; -} - -static bool check_area_prot(struct iopt_area *area, unsigned int flags) -{ - if (flags & IOMMUFD_ACCESS_RW_WRITE) - return area->iommu_prot & IOMMU_WRITE; - return area->iommu_prot & IOMMU_READ; -} - /** * iommufd_access_pin_pages() - Return a list of pages under the iova * @access: IOAS access to act on @@ -1315,77 +1273,16 @@ int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length, struct page **out_pages, unsigned int flags) { - struct iopt_area_contig_iter iter; - struct io_pagetable *iopt; - unsigned long last_iova; - struct iopt_area *area; - int rc; - /* Driver's ops don't support pin_pages */ if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && WARN_ON(access->iova_alignment != PAGE_SIZE || !access->ops->unmap)) return -EINVAL;

- if (!length) - return -EINVAL; - if (check_add_overflow(iova, length - 1, &last_iova)) - return -EOVERFLOW; - - mutex_lock(&access->ioas_lock); - if (!access->ioas) { - mutex_unlock(&access->ioas_lock); + guard(mutex)(&access->ioas_lock); + if (!access->ioas) return -ENOENT; - } - iopt = &access->ioas->iopt; - - down_read(&iopt->iova_rwsem); - iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) { - unsigned long last = min(last_iova, iopt_area_last_iova(area)); - unsigned long last_index = iopt_area_iova_to_index(area, last); - unsigned long index = - iopt_area_iova_to_index(area, iter.cur_iova); - - if (area->prevent_access || - !iopt_area_contig_is_aligned(&iter)) { - rc = -EINVAL; - goto err_remove; - } - - if (!check_area_prot(area, flags)) { - rc = -EPERM; - goto err_remove; - } - - rc = iopt_area_add_access(area, index, last_index, out_pages, - flags, false); - if (rc) - goto err_remove; - out_pages += last_index - index + 1; - } - if (!iopt_area_contig_done(&iter)) { - rc = -ENOENT; - goto err_remove; - } - - up_read(&iopt->iova_rwsem); - mutex_unlock(&access->ioas_lock); - return 0; - -err_remove: - if (iova < iter.cur_iova) { - last_iova = iter.cur_iova - 1; - iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) - iopt_area_remove_access( - area, - iopt_area_iova_to_index(area, iter.cur_iova), - iopt_area_iova_to_index( - area, min(last_iova, - iopt_area_last_iova(area))), - false); - } - up_read(&iopt->iova_rwsem); - mutex_unlock(&access->ioas_lock); - return rc; + return iopt_pin_pages(&access->ioas->iopt, iova, length, out_pages, + flags, false); } EXPORT_SYMBOL_NS_GPL(iommufd_access_pin_pages, "IOMMUFD");

@@ -1432,7 +1329,7 @@ int iommufd_access_rw(struct iommufd_access *access, unsigned long iova, goto err_out; }

- if (!check_area_prot(area, flags)) { + if (!iopt_area_check_prot(area, flags)) { rc = -EPERM; goto err_out; } diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 51efebb1c6ed..3b164d364e53 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -1477,3 +1477,100 @@ int iopt_table_enforce_dev_resv_regions(struct io_pagetable *iopt, up_write(&iopt->iova_rwsem); return rc; } + +static bool iopt_area_contig_is_aligned(struct iopt_area_contig_iter *iter) +{ + if (iopt_area_start_byte(iter->area, iter->cur_iova) % PAGE_SIZE) + return false; + + if (!iopt_area_contig_done(iter) && + (iopt_area_start_byte(iter->area, iopt_area_last_iova(iter->area)) % + PAGE_SIZE) != (PAGE_SIZE - 1)) + return false; + return true; +} + +int iopt_pin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, struct page **out_pages, + unsigned int flags, bool is_owner) +{ + struct iopt_area_contig_iter iter; + unsigned long last_iova; + struct iopt_area *area; + int rc; + + if (!length) + return -EINVAL; + if (check_add_overflow(iova, length - 1, &last_iova)) + return -EOVERFLOW; + + down_read(&iopt->iova_rwsem); + iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) { + unsigned long last = min(last_iova, iopt_area_last_iova(area)); + unsigned long last_index = iopt_area_iova_to_index(area, last); + unsigned long index = + iopt_area_iova_to_index(area, iter.cur_iova); + + if (area->prevent_access || + !iopt_area_contig_is_aligned(&iter)) { + rc = -EINVAL; + goto err_remove; + } + + if (!iopt_area_check_prot(area, flags)) { + rc = -EPERM; + goto err_remove; + } + + rc = iopt_area_add_access(area, index, last_index, out_pages, + flags, is_owner); + if (rc) + goto err_remove; + out_pages += last_index - index + 1; + } + if (!iopt_area_contig_done(&iter)) { + rc = -ENOENT; + goto err_remove; + } + + up_read(&iopt->iova_rwsem); + return 0; + +err_remove: + if (iova < iter.cur_iova) { + last_iova = iter.cur_iova - 1; + iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) + iopt_area_remove_access( + area, + iopt_area_iova_to_index(area, iter.cur_iova), + iopt_area_iova_to_index( + area, min(last_iova, + iopt_area_last_iova(area))), + is_owner); + } + up_read(&iopt->iova_rwsem); + return rc; +} + +void iopt_unpin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, bool is_owner) +{ + struct iopt_area_contig_iter iter; + unsigned long last_iova; + struct iopt_area *area; + + if (WARN_ON(!length) || + WARN_ON(check_add_overflow(iova, length - 1, &last_iova))) + return; + + down_read(&iopt->iova_rwsem); + iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) + iopt_area_remove_access( + area, iopt_area_iova_to_index(area, iter.cur_iova), + iopt_area_iova_to_index( + area, + min(last_iova, iopt_area_last_iova(area))), + is_owner); + WARN_ON(!iopt_area_contig_done(&iter)); + up_read(&iopt->iova_rwsem); +}

To allow IOMMU drivers to allocate own vDEVICE structures, move the struct iommufd_vdevice to the public header and provide a pair of viommu ops.

The iommufd_vdevice_alloc_ioctl will prioritize the callback function from the viommu ops, i.e. a driver-allocated vDEVICE.

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/iommufd/iommufd_private.h | 8 ------ include/linux/iommufd.h | 36 +++++++++++++++++++++++++ drivers/iommu/iommufd/viommu.c | 10 ++++++- 3 files changed, 45 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 44286216ac5a..35088478cb07 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -604,14 +604,6 @@ 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_ctx *ictx; - struct iommufd_viommu *viommu; - struct device *dev; - u64 id; /* per-vIOMMU virtual 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 a07466333c48..266ac6805213 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -125,6 +125,14 @@ struct iommufd_viommu { unsigned int type; };

+struct iommufd_vdevice { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct iommufd_viommu *viommu; + struct device *dev; + u64 id; /* per-vIOMMU virtual ID */ +}; + /** * struct iommufd_viommu_ops - vIOMMU specific operations * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory @@ -141,6 +149,15 @@ 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_alloc: Allocate a vDEVICE object and init its driver-level structure + * or HW procedure. Note that the core-level structure is filled + * by the iommufd core after calling this op. @virt_id carries a + * per-vIOMMU virtual ID (refer to struct iommu_vdevice_alloc in + * include/uapi/linux/iommufd.h) for the driver to initialize HW + * for an attached physical device. + * @vdevice_destroy: Clean up all driver-specific parts of an iommufd_vdevice. + * The memory of the vDEVICE will be free-ed by iommufd core + * after calling this op */ struct iommufd_viommu_ops { void (*destroy)(struct iommufd_viommu *viommu); @@ -149,6 +166,11 @@ struct iommufd_viommu_ops { const struct iommu_user_data *user_data); int (*cache_invalidate)(struct iommufd_viommu *viommu, struct iommu_user_data_array *array); + struct iommufd_vdevice *(*vdevice_alloc)(struct iommufd_ucmd *ucmd, + struct iommufd_viommu *viommu, + struct device *dev, + u64 virt_id); + void (*vdevice_destroy)(struct iommufd_vdevice *vdev); };

#if IS_ENABLED(CONFIG_IOMMUFD) @@ -276,4 +298,18 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu, } \ ret; \ }) + +#define iommufd_vdevice_alloc(ucmd, viommu, drv_struct, member) \ + ({ \ + drv_struct *ret; \ + \ + static_assert(__same_type(struct iommufd_viommu, *viommu)); \ + ret = (drv_struct *)__iommufd_object_alloc_ucmd( \ + ucmd, ret, IOMMUFD_OBJ_VDEVICE, member.obj); \ + if (!IS_ERR(ret)) { \ + ret->member.viommu = viommu; \ + ret->member.ictx = viommu->ictx; \ + } \ + ret; \ + }) #endif diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 662f5c1b1935..7248fb7c7baf 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -95,6 +95,9 @@ void iommufd_vdevice_destroy(struct iommufd_object *obj) container_of(obj, struct iommufd_vdevice, obj); struct iommufd_viommu *viommu = vdev->viommu;

+ if (viommu->ops && viommu->ops->vdevice_destroy) + viommu->ops->vdevice_destroy(vdev); + /* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */ xa_cmpxchg(&viommu->vdevs, vdev->id, vdev, NULL, GFP_KERNEL); refcount_dec(&viommu->obj.users); @@ -129,7 +132,12 @@ 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_alloc) + vdev = viommu->ops->vdevice_alloc(ucmd, viommu, idev->dev, + virt_id); + else + vdev = iommufd_object_alloc_ucmd(ucmd, vdev, + IOMMUFD_OBJ_VDEVICE); if (IS_ERR(vdev)) { rc = PTR_ERR(vdev); goto out_put_idev;

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 Buffer, and PPR Log Buffer

This is a vIOMMU based ioctl. Simply increase the refcount of the vIOMMU.

Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 2 + include/uapi/linux/iommufd.h | 45 ++++++++++ drivers/iommu/iommufd/main.c | 6 ++ drivers/iommu/iommufd/viommu.c | 105 ++++++++++++++++++++++++ 4 files changed, 158 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 35088478cb07..a94d04ab0d2c 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -603,6 +603,8 @@ 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/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 272da7324a2b..aeed0127553e 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, };

/** @@ -1147,4 +1148,48 @@ struct iommu_veventq_alloc { __u32 __reserved; }; #define IOMMU_VEVENTQ_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VEVENTQ_ALLOC) + +/** + * enum iommu_hw_queue_type - HW Queue Type + * @IOMMU_HW_QUEUE_TYPE_DEFAULT: Reserved for future use + */ +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. + * + * Upon success, the underlying physical pages of the guest queue memory will be + * pinned to prevent VMM from unmapping them in the IOAS until the HW queue gets + * destroyed. + * + * A vIOMMU can allocate multiple queues, but it must use a different @index to + * separate each allocation, e.g. HW queue0, HW queue1, ... + */ +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 c6d0b446e632..0750e740fa1d 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -304,6 +304,7 @@ 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; @@ -346,6 +347,8 @@ 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, @@ -509,6 +512,9 @@ 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 7248fb7c7baf..9b4e99babdb4 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -164,3 +164,108 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) iommufd_put_object(ucmd->ictx, &viommu->obj); return rc; } + +void iommufd_hw_queue_destroy(struct iommufd_object *obj) +{ + struct iommufd_hw_queue *hw_queue = + container_of(obj, struct iommufd_hw_queue, obj); + struct iommufd_viommu *viommu = hw_queue->viommu; + + if (viommu->ops->hw_queue_destroy) + viommu->ops->hw_queue_destroy(hw_queue); + iopt_unpin_pages(&viommu->hwpt->ioas->iopt, hw_queue->base_addr, + hw_queue->length, true); + refcount_dec(&viommu->obj.users); +} + +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 page **pages; + int max_npages, i; + u64 last, offset; + int rc; + + if (cmd->flags || cmd->type == IOMMU_HW_QUEUE_TYPE_DEFAULT) + return -EOPNOTSUPP; + if (!cmd->nesting_parent_iova || !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->hw_queue_alloc) { + rc = -EOPNOTSUPP; + goto out_put_viommu; + } + + offset = + cmd->nesting_parent_iova - PAGE_ALIGN(cmd->nesting_parent_iova); + max_npages = DIV_ROUND_UP(offset + cmd->length, PAGE_SIZE); + pages = kcalloc(max_npages, sizeof(*pages), GFP_KERNEL); + if (!pages) { + rc = -ENOMEM; + goto out_put_viommu; + } + + /* + * The underlying physical pages must be pinned to prevent them from + * being unmapped (via IOMMUFD_CMD_IOAS_UNMAP) during the life cycle + * of the HW QUEUE object. And the pages should be contiguous too. + */ + if (viommu->ops->flags & IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA) { + rc = iopt_pin_pages(&viommu->hwpt->ioas->iopt, + cmd->nesting_parent_iova, cmd->length, + pages, 0, true); + if (rc) + goto out_free; + + /* Validate if the underlying physical pages are contiguous */ + for (i = 1; i < max_npages && pages[i]; i++) { + if (page_to_pfn(pages[i]) == + page_to_pfn(pages[i - 1]) + 1) + continue; + rc = -EFAULT; + goto out_unpin; + } + } + + hw_queue = viommu->ops->hw_queue_alloc(ucmd, viommu, cmd->type, + cmd->index, + cmd->nesting_parent_iova, + cmd->length); + if (IS_ERR(hw_queue)) { + rc = PTR_ERR(hw_queue); + goto out_unpin; + } + + /* The iommufd_hw_queue_alloc helper saves ictx in hw_queue->ictx */ + if (WARN_ON_ONCE(hw_queue->ictx != ucmd->ictx)) { + rc = -EINVAL; + goto out_unpin; + } + + hw_queue->viommu = viommu; + refcount_inc(&viommu->obj.users); + hw_queue->length = cmd->length; + hw_queue->base_addr = cmd->nesting_parent_iova; + cmd->out_hw_queue_id = hw_queue->obj.id; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + goto out_put_viommu; + +out_unpin: + if (viommu->ops->flags & IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA) + iopt_unpin_pages(&viommu->hwpt->ioas->iopt, + cmd->nesting_parent_iova, cmd->length, true); +out_free: + kfree(pages); +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.

Since the iommufd_hw_queue_alloc_ioctl() will call iommu_iova_to_phys(), for input address validation. It might intentionally pass in a bad input for a negative test. So drop the WARN_ON() in mock_domain_iova_to_phys().

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 | 71 ++++++++++++++++++- tools/testing/selftests/iommu/iommufd.c | 62 ++++++++++++++++ .../selftests/iommu/iommufd_fail_nth.c | 6 ++ 5 files changed, 172 insertions(+), 1 deletion(-)

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 ea2e4c626ad5..eca1a66fefed 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -148,6 +148,7 @@ 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]; };

static inline struct mock_viommu *to_mock_viommu(struct iommufd_viommu *viommu) @@ -155,6 +156,19 @@ 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, }; @@ -570,7 +584,8 @@ static phys_addr_t mock_domain_iova_to_phys(struct iommu_domain *domain,

WARN_ON(iova % MOCK_IO_PAGE_SIZE); ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE); - WARN_ON(!ent); + if (!ent) + return 0; return (xa_to_value(ent) & MOCK_PFN_MASK) * MOCK_IO_PAGE_SIZE; }

@@ -727,10 +742,64 @@ static int mock_viommu_cache_invalidate(struct iommufd_viommu *viommu, return rc; }

+/* Test iommufd_hw_queue_depend/undepend() */ +static struct iommufd_hw_queue * +mock_hw_queue_alloc(struct iommufd_ucmd *ucmd, struct iommufd_viommu *viommu, + unsigned int type, u32 index, u64 base_addr, size_t length) +{ + struct mock_viommu *mock_viommu = to_mock_viommu(viommu); + struct mock_hw_queue *mock_hw_queue, *prev = NULL; + int rc; + + if (type != IOMMU_HW_QUEUE_TYPE_SELFTEST) + return ERR_PTR(-EOPNOTSUPP); + if (index >= IOMMU_TEST_HW_QUEUE_MAX) + return ERR_PTR(-EINVAL); + if (mock_viommu->hw_queue[index]) + return ERR_PTR(-EEXIST); + if (index) { + prev = mock_viommu->hw_queue[index - 1]; + if (!prev) + return ERR_PTR(-EIO); + } + + mock_hw_queue = iommufd_hw_queue_alloc(ucmd, viommu, + struct mock_hw_queue, core); + if (IS_ERR(mock_hw_queue)) + return ERR_CAST(mock_hw_queue); + + if (prev) { + rc = iommufd_hw_queue_depend(mock_hw_queue, prev, core); + if (rc) + return ERR_PTR(rc); + } + mock_hw_queue->prev = prev; + mock_hw_queue->mock_viommu = mock_viommu; + mock_viommu->hw_queue[index] = mock_hw_queue; + + return &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; + + 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); + + /* iommufd core frees mock_hw_queue and hw_queue */ +} + static struct iommufd_viommu_ops mock_viommu_ops = { + .flags = IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA, .destroy = mock_viommu_destroy, .alloc_domain_nested = mock_viommu_alloc_domain_nested, .cache_invalidate = mock_viommu_cache_invalidate, + .hw_queue_alloc = mock_hw_queue_alloc, + .hw_queue_destroy = mock_hw_queue_destroy, };

static struct iommufd_viommu * diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index f22388dfacad..fabec1b551c6 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -3031,6 +3031,68 @@ TEST_F(iommufd_viommu, vdevice_cache) } }

+TEST_F(iommufd_viommu, hw_queue) +{ + uint32_t viommu_id = self->viommu_id; + __u64 iova = MOCK_APERTURE_START; + uint32_t hw_queue_id[2]; + + if (viommu_id) { + /* 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, 0, + PAGE_SIZE, &hw_queue_id[0]); + 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); + + /* 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); + + /* 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]); + } +} + 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 | 34 ++++++++++++++++++- tools/testing/selftests/iommu/iommufd.c | 22 ++++++++++++ 4 files changed, 63 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 eca1a66fefed..45276c137cee 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -149,6 +149,9 @@ struct mock_viommu { struct iommufd_viommu core; struct mock_iommu_domain *s2_parent; struct mock_hw_queue *hw_queue[IOMMU_TEST_HW_QUEUE_MAX]; + + 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) @@ -647,9 +650,14 @@ 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); + if (mock_viommu->mmap_offset) + iommufd_viommu_destroy_mmap(mock_viommu, core, + mock_viommu->mmap_offset); + free_page((unsigned long)mock_viommu->page);

/* iommufd core frees mock_viommu and viommu */ } @@ -829,15 +837,39 @@ mock_viommu_alloc(struct device *dev, struct iommu_domain *domain, return ERR_CAST(mock_viommu);

if (user_data) { + /* Allocate two pages */ + mock_viommu->page = + (u32 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + if (!mock_viommu->page) + return ERR_PTR(-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 ERR_PTR(rc); + goto err_destroy_mmap; }

refcount_inc(&mock_iommu->users); return &mock_viommu->core; + +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 ERR_PTR(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 fabec1b551c6..2b3274015832 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -2799,12 +2799,34 @@ TEST_F(iommufd_viommu, viommu_alloc_with_data) struct iommu_viommu_selftest data = { .in_data = 0xbeef, }; + uint32_t *test;

if (self->device_id) { test_cmd_viommu_alloc(self->device_id, self->hwpt_id, 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); } }

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

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 6 ++++-- 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, 22 insertions(+), 3 deletions(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4c54dd8f94e4..01a19b68a0ea 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -607,8 +607,10 @@ __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. The information type is one of enum iommu_hw_info_type defined - * in include/uapi/linux/iommufd.h. + * use. @type can input a requested type and output a supported type, + * either of which must be defined in enum iommu_hw_info_type in + * include/uapi/linux/iommufd.h. Driver should reject an unsupported + * data @type input * @domain_alloc: allocate and return an iommu domain if success. Otherwise * NULL is returned. The domain is not fully initialized until * the caller iommu_domain_alloc() returns. diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index aeed0127553e..1fc546acb231 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 adef56db4028..61a3f9134a9b 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 @@ -14,6 +14,10 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type) 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 cb0b993bebb4..8ad8714ece5e 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4149,6 +4149,10 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type) 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 0f2bda9e9d84..50337183eb1c 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1365,6 +1365,9 @@ 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 45276c137cee..299a8e1e7f6c 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -290,6 +290,10 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type) { 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 | 35 +++++++++++-------- tools/testing/selftests/iommu/iommufd.c | 32 ++++++++++++----- .../selftests/iommu/iommufd_fail_nth.c | 4 +-- 3 files changed, 47 insertions(+), 24 deletions(-)

diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 4a1b2bade018..399d0dd18daf 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -761,25 +761,29 @@ 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, + .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;

- assert(cmd.out_data_type == IOMMU_HW_INFO_TYPE_SELFTEST); + assert(cmd.data_type == IOMMU_HW_INFO_TYPE_SELFTEST);

/* * The struct iommu_test_hw_info should be the one defined @@ -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 2b3274015832..eb5b0adb16a5 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.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 1 + drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 8 ++++++-- 2 files changed, 7 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 a455ff97e53e..8328c8cc1899 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -727,6 +727,7 @@ struct arm_smmu_impl_ops { struct arm_smmu_domain *smmu_domain, struct iommufd_ucmd *ucmd, unsigned int viommu_type, const struct iommu_user_data *user_data); + void *(*hw_info)(struct arm_smmu_device *smmu, u32 *length, u32 *type); };

/* An SMMUv3 instance */ 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 8a13d0102c05..837f15e2d40f 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 @@ -10,13 +10,17 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *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.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 15 + include/uapi/linux/iommufd.h | 58 +++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 6 +- .../iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 419 +++++++++++++++++- 4 files changed, 491 insertions(+), 7 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 8328c8cc1899..187c47370652 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -1001,6 +1001,14 @@ int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, struct arm_smmu_cmdq *cmdq, u64 *cmds, int n, bool sync);

+static inline phys_addr_t +arm_smmu_domain_ipa_to_pa(struct arm_smmu_domain *smmu_domain, u64 ipa) +{ + if (WARN_ON_ONCE(smmu_domain->stage != ARM_SMMU_DOMAIN_S2)) + return 0; + return iommu_iova_to_phys(&smmu_domain->domain, ipa); +} + #ifdef CONFIG_ARM_SMMU_V3_SVA bool arm_smmu_sva_supported(struct arm_smmu_device *smmu); bool arm_smmu_master_sva_supported(struct arm_smmu_master *master); @@ -1077,9 +1085,16 @@ 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_hw_info NULL #define arm_vsmmu_alloc 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 7bcd3912180a..8a9090cc938f 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, };

/** @@ -966,10 +990,29 @@ 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) Virtual Interface (VINTF) */ 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; };

/** @@ -1166,9 +1209,24 @@ 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 837f15e2d40f..4917e5b6f562 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 @@ -224,7 +224,7 @@ 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) { @@ -335,8 +335,8 @@ 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..49f07f61673c 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 +142,29 @@ 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 * @base: MMIO base address + * @mmap_offset: Offset argument for mmap() syscall + * @sids: Stream ID replacement resources */ struct tegra241_vintf { + struct arm_vsmmu vsmmu; + u16 idx;

bool enabled; @@ -156,6 +174,24 @@ struct tegra241_vintf { struct tegra241_vcmdq **lvcmdqs;

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 Replacement + * @core: Embedded iommufd_vdevice structure, holding virtual Stream ID + * @vintf: Parent VINTF pointer + * @sid: Physical Stream ID + * @idx: Replacement index in the VINTF + */ +struct tegra241_vintf_sid { + struct iommufd_vdevice core; + struct tegra241_vintf *vintf; + u32 sid; + u8 idx; };

/** @@ -163,10 +199,12 @@ struct tegra241_vintf { * @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 replacements per VINTF * @vintf_ids: VINTF id allocator * @vintfs: List of VINTFs */ @@ -175,12 +213,14 @@ 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 +391,29 @@ 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 +427,8 @@ 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)); @@ -380,6 +445,12 @@ static void tegra241_vcmdq_hw_deinit(struct tegra241_vcmdq *vcmdq) dev_dbg(vcmdq->cmdqv->dev, "%sdeinited\n", h); }

+/* This function is for LVCMDQ, so @vcmdq must be mapped prior */ +static void _tegra241_vcmdq_hw_init(struct tegra241_vcmdq *vcmdq) +{ + writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); +} + /* This function is for LVCMDQ, so @vcmdq must be mapped prior */ static int tegra241_vcmdq_hw_init(struct tegra241_vcmdq *vcmdq) { @@ -390,7 +461,7 @@ static int tegra241_vcmdq_hw_init(struct tegra241_vcmdq *vcmdq) tegra241_vcmdq_hw_deinit(vcmdq);

/* Configure and enable VCMDQ */ - writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); + _tegra241_vcmdq_hw_init(vcmdq);

ret = vcmdq_write_config(vcmdq, VCMDQ_EN); if (ret) { @@ -420,6 +491,7 @@ 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 +501,10 @@ 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 +533,8 @@ 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 +661,9 @@ 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 +750,11 @@ 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) + ida_destroy(&vintf->sids); + /* Guest-owned VINTF is free-ed with viommu by iommufd core */ + if (vintf->hyp_own) + kfree(vintf); }

static void tegra241_cmdqv_remove(struct arm_smmu_device *smmu) @@ -699,10 +782,44 @@ static void tegra241_cmdqv_remove(struct arm_smmu_device *smmu) put_device(cmdqv->dev); /* smmu->impl_dev */ }

+static struct arm_vsmmu * +tegra241_cmdqv_alloc_vintf_user(struct arm_smmu_device *smmu, + struct arm_smmu_domain *smmu_domain, + struct iommufd_ucmd *ucmd, unsigned int type, + const struct iommu_user_data *user_data); + +static void *tegra241_cmdqv_hw_info(struct arm_smmu_device *smmu, u32 *length, + u32 *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 = { + .supported_vsmmu_type = IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV, .get_secondary_cmdq = tegra241_cmdqv_get_cmdq, .device_reset = tegra241_cmdqv_hw_reset, .device_remove = tegra241_cmdqv_remove, + .vsmmu_alloc = tegra241_cmdqv_alloc_vintf_user, + .hw_info = tegra241_cmdqv_hw_info, };

/* 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 +1033,294 @@ 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 int tegra241_vcmdq_hw_init_user(struct tegra241_vcmdq *vcmdq) +{ + char header[64]; + + /* Configure the vcmdq only; User space does the enabling */ + _tegra241_vcmdq_hw_init(vcmdq); + + 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 struct iommufd_hw_queue *tegra241_vintf_alloc_lvcmdq_user( + struct iommufd_ucmd *ucmd, struct iommufd_viommu *viommu, + unsigned int type, u32 lidx, u64 base_addr, size_t length) +{ + struct tegra241_vintf *vintf = viommu_to_vintf(viommu); + struct tegra241_cmdqv *cmdqv = vintf->cmdqv; + struct arm_smmu_device *smmu = &cmdqv->smmu; + struct tegra241_vcmdq *vcmdq, *prev = NULL; + u32 log2size, max_n_shift; + phys_addr_t q_base; + char header[64]; + int ret; + + if (type != IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV) + return ERR_PTR(-EOPNOTSUPP); + if (lidx >= cmdqv->num_lvcmdqs_per_vintf) + return ERR_PTR(-EINVAL); + if (vintf->lvcmdqs[lidx]) + return ERR_PTR(-EEXIST); + + /* + * 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) + return ERR_PTR(-EIO); + } + + /* + * @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(length) || length < 32 || + length > (1 << (max_n_shift + CMDQ_ENT_SZ_SHIFT))) + return ERR_PTR(-EINVAL); + log2size = ilog2(length) - CMDQ_ENT_SZ_SHIFT; + + /* @base_addr must be aligned to @length */ + if (base_addr & ~VCMDQ_ADDR || base_addr & (length - 1)) + return ERR_PTR(-EINVAL); + + /* @base_addr must be mapped in the s2_parent domain */ + q_base = arm_smmu_domain_ipa_to_pa(vintf->vsmmu.s2_parent, base_addr); + if (!q_base) + return ERR_PTR(-ENXIO); + + vcmdq = iommufd_hw_queue_alloc(ucmd, viommu, struct tegra241_vcmdq, + core); + if (!vcmdq) + return ERR_PTR(-ENOMEM); + + /* + * 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) + return ERR_PTR(ret); + } + 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 = q_base & VCMDQ_ADDR; + vcmdq->cmdq.q.q_base |= log2size; + + ret = tegra241_vcmdq_hw_init_user(vcmdq); + if (ret) + goto unmap_lvcmdq; + + return &vcmdq->core; + +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); + return ERR_PTR(ret); +} + +static void +tegra241_vintf_destroy_lvcmdq_user(struct iommufd_hw_queue *hw_queue) +{ + struct tegra241_vcmdq *vcmdq = hw_queue_to_vcmdq(hw_queue); + + 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); + + /* IOMMUFD core frees the memory of vcmdq and hw_queue */ +} + +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); + + /* IOMMUFD core frees the memory of vintf and viommu */ +} + +static struct iommufd_vdevice * +tegra241_vintf_alloc_vsid(struct iommufd_ucmd *ucmd, + struct iommufd_viommu *viommu, struct device *dev, + u64 virt_sid) +{ + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + struct tegra241_vintf *vintf = viommu_to_vintf(viommu); + struct arm_smmu_stream *stream = &master->streams[0]; + struct tegra241_vintf_sid *vsid; + int sidx; + + if (virt_sid > UINT_MAX) + return ERR_PTR(-EINVAL); + + vsid = iommufd_vdevice_alloc(ucmd, viommu, struct tegra241_vintf_sid, + core); + if (!vsid) + return ERR_PTR(-ENOMEM); + + 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 ERR_PTR(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; + + return &vsid->core; +} + +static void tegra241_vintf_destroy_vsid(struct iommufd_vdevice *vdev) +{ + struct tegra241_vintf_sid *vsid = + container_of(vdev, struct tegra241_vintf_sid, core); + 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); + + /* IOMMUFD core frees the memory of vsid and vdev */ +} + +static struct iommufd_viommu_ops tegra241_cmdqv_viommu_ops = { + .flags = IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA, + .destroy = tegra241_cmdqv_destroy_vintf_user, + .alloc_domain_nested = arm_vsmmu_alloc_domain_nested, + .cache_invalidate = arm_vsmmu_cache_invalidate, + .vdevice_alloc = tegra241_vintf_alloc_vsid, + .vdevice_destroy = tegra241_vintf_destroy_vsid, + .hw_queue_alloc = tegra241_vintf_alloc_lvcmdq_user, + .hw_queue_destroy = tegra241_vintf_destroy_lvcmdq_user, +}; + +static struct arm_vsmmu * +tegra241_cmdqv_alloc_vintf_user(struct arm_smmu_device *smmu, + struct arm_smmu_domain *s2_parent, + struct iommufd_ucmd *ucmd, unsigned int type, + const struct iommu_user_data *user_data) +{ + struct tegra241_cmdqv *cmdqv = + container_of(smmu, struct tegra241_cmdqv, smmu); + struct iommu_viommu_tegra241_cmdqv data; + struct tegra241_vintf *vintf; + phys_addr_t page0_base; + int ret; + + if (type != IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV) + return ERR_PTR(-EOPNOTSUPP); + if (!user_data) + return ERR_PTR(-EINVAL); + + ret = iommu_copy_struct_from_user(&data, user_data, + IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV, + out_vintf_mmap_length); + if (ret) + return ERR_PTR(ret); + + vintf = iommufd_viommu_alloc(ucmd, struct tegra241_vintf, vsmmu.core, + &tegra241_cmdqv_viommu_ops); + if (!vintf) + return ERR_PTR(-ENOMEM); + + ret = tegra241_cmdqv_init_vintf(cmdqv, cmdqv->num_vintfs - 1, vintf); + if (ret < 0) { + dev_err(cmdqv->dev, "no more available vintf\n"); + return ERR_PTR(ret); + } + + vintf->vsmmu.smmu = smmu; + vintf->vsmmu.s2_parent = s2_parent; + /* FIXME Move VMID allocation from the S2 domain allocation to here */ + vintf->vsmmu.vmid = s2_parent->s2_cfg.vmid; + + /* + * Initialize the user-owned VINTF without a LVCMDQ, because it has to + * wait for the allocation of a user-owned LVCMDQ, for security reason. + * 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; + + vintf->lvcmdqs = kcalloc(cmdqv->num_lvcmdqs_per_vintf, + sizeof(*vintf->lvcmdqs), GFP_KERNEL); + if (!vintf->lvcmdqs) { + ret = -ENOMEM; + goto hw_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); + + dev_dbg(cmdqv->dev, "VINTF%u: allocated with vmid (%d)\n", vintf->idx, + vintf->vsmmu.vmid); + + return &vintf->vsmmu; + +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 ERR_PTR(ret); +}