Introduce a new IOMMUFD_OBJ_VEVENTQ object for vIOMMU Event Queue that provides user space (VMM) another FD to read the vIOMMU Events.
Allow a vIOMMU object to allocate vEVENTQs, with a condition that each vIOMMU can only have one single vEVENTQ per type.
Add iommufd_veventq_alloc() with iommufd_veventq_ops for the new ioctl.
Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 58 +++++++++++ include/linux/iommufd.h | 3 + include/uapi/linux/iommufd.h | 31 ++++++ drivers/iommu/iommufd/eventq.c | 129 ++++++++++++++++++++++++ drivers/iommu/iommufd/main.c | 7 ++ drivers/iommu/iommufd/viommu.c | 2 + 6 files changed, 230 insertions(+)
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index dfbc5cfbd164..9410f6275b5a 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -547,6 +547,50 @@ static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev, return iommu_group_replace_domain(idev->igroup->group, hwpt->domain); }
+/* + * An iommufd_veventq object represents an interface to deliver vIOMMU events to + * the user space. It is created/destroyed by the user space and associated with + * vIOMMU object(s) during the allocations. + */ +struct iommufd_veventq { + struct iommufd_eventq common; + struct iommufd_viommu *viommu; + struct list_head node; /* for iommufd_viommu::veventqs */ + + unsigned int type; +}; + +static inline struct iommufd_veventq * +eventq_to_veventq(struct iommufd_eventq *eventq) +{ + return container_of(eventq, struct iommufd_veventq, common); +} + +static inline struct iommufd_veventq * +iommufd_get_veventq(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_VEVENTQ), + struct iommufd_veventq, common.obj); +} + +int iommufd_veventq_alloc(struct iommufd_ucmd *ucmd); +void iommufd_veventq_destroy(struct iommufd_object *obj); +void iommufd_veventq_abort(struct iommufd_object *obj); + +/* An iommufd_vevent represents a vIOMMU event in an iommufd_veventq */ +struct iommufd_vevent { + struct list_head node; /* for iommufd_eventq::deliver */ + ssize_t data_len; + u64 event_data[] __counted_by(data_len); +}; + +static inline int iommufd_vevent_handler(struct iommufd_veventq *veventq, + struct iommufd_vevent *vevent) +{ + return iommufd_eventq_notify(&veventq->common, &vevent->node); +} + static inline struct iommufd_viommu * iommufd_get_viommu(struct iommufd_ucmd *ucmd, u32 id) { @@ -555,6 +599,20 @@ iommufd_get_viommu(struct iommufd_ucmd *ucmd, u32 id) struct iommufd_viommu, obj); }
+static inline struct iommufd_veventq * +iommufd_viommu_find_veventq(struct iommufd_viommu *viommu, u32 type) +{ + struct iommufd_veventq *veventq, *next; + + lockdep_assert_held(&viommu->veventqs_rwsem); + + list_for_each_entry_safe(veventq, next, &viommu->veventqs, node) { + if (veventq->type == type) + return veventq; + } + return NULL; +} + 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); diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 11110c749200..8948b1836940 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -34,6 +34,7 @@ enum iommufd_object_type { IOMMUFD_OBJ_FAULT, IOMMUFD_OBJ_VIOMMU, IOMMUFD_OBJ_VDEVICE, + IOMMUFD_OBJ_VEVENTQ, #ifdef CONFIG_IOMMUFD_TEST IOMMUFD_OBJ_SELFTEST, #endif @@ -93,6 +94,8 @@ struct iommufd_viommu { const struct iommufd_viommu_ops *ops;
struct xarray vdevs; + struct list_head veventqs; + struct rw_semaphore veventqs_rwsem;
unsigned int type; }; diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 34810f6ae2b5..0a08aa82e7cc 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -55,6 +55,7 @@ enum { IOMMUFD_CMD_VIOMMU_ALLOC = 0x90, IOMMUFD_CMD_VDEVICE_ALLOC = 0x91, IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92, + IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93, };
/** @@ -1012,4 +1013,34 @@ struct iommu_ioas_change_process { #define IOMMU_IOAS_CHANGE_PROCESS \ _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_CHANGE_PROCESS)
+/** + * enum iommu_veventq_type - Virtual Event Queue Type + * @IOMMU_VEVENTQ_TYPE_DEFAULT: Reserved for future use + */ +enum iommu_veventq_type { + IOMMU_VEVENTQ_TYPE_DEFAULT = 0, +}; + +/** + * struct iommu_veventq_alloc - ioctl(IOMMU_VEVENTQ_ALLOC) + * @size: sizeof(struct iommu_veventq_alloc) + * @flags: Must be 0 + * @viommu: virtual IOMMU ID to associate the vEVENTQ with + * @type: Type of the vEVENTQ. Must be defined in enum iommu_veventq_type + * @out_veventq_id: The ID of the new vEVENTQ + * @out_veventq_fd: The fd of the new vEVENTQ. User space must close the + * successfully returned fd after using it + * + * Explicitly allocate a virtual event queue interface for a vIOMMU. A vIOMMU + * can have multiple FDs for different types, but is confined to one per @type. + */ +struct iommu_veventq_alloc { + __u32 size; + __u32 flags; + __u32 viommu_id; + __u32 type; + __u32 out_veventq_id; + __u32 out_veventq_fd; +}; +#define IOMMU_VEVENTQ_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VEVENTQ_ALLOC) #endif diff --git a/drivers/iommu/iommufd/eventq.c b/drivers/iommu/iommufd/eventq.c index e386b6c3e6ab..bf0c04f571a7 100644 --- a/drivers/iommu/iommufd/eventq.c +++ b/drivers/iommu/iommufd/eventq.c @@ -346,6 +346,73 @@ static const struct iommufd_eventq_ops iommufd_fault_ops = { .write = &iommufd_fault_fops_write, };
+/* IOMMUFD_OBJ_VEVENTQ Functions */ + +void iommufd_veventq_abort(struct iommufd_object *obj) +{ + struct iommufd_eventq *eventq = + container_of(obj, struct iommufd_eventq, obj); + struct iommufd_veventq *veventq = eventq_to_veventq(eventq); + struct iommufd_viommu *viommu = veventq->viommu; + struct iommufd_vevent *cur, *next; + + lockdep_assert_held_write(&viommu->veventqs_rwsem); + + list_for_each_entry_safe(cur, next, &eventq->deliver, node) { + list_del(&cur->node); + kfree(cur); + } + + refcount_dec(&viommu->obj.users); + mutex_destroy(&eventq->mutex); + list_del(&veventq->node); +} + +void iommufd_veventq_destroy(struct iommufd_object *obj) +{ + struct iommufd_veventq *veventq = eventq_to_veventq( + container_of(obj, struct iommufd_eventq, obj)); + + down_write(&veventq->viommu->veventqs_rwsem); + iommufd_veventq_abort(obj); + up_write(&veventq->viommu->veventqs_rwsem); +} + +static ssize_t iommufd_veventq_fops_read(struct iommufd_eventq *eventq, + char __user *buf, size_t count, + loff_t *ppos) +{ + size_t done = 0; + int rc = 0; + + if (*ppos) + return -ESPIPE; + + mutex_lock(&eventq->mutex); + while (!list_empty(&eventq->deliver) && count > done) { + struct iommufd_vevent *cur = list_first_entry( + &eventq->deliver, struct iommufd_vevent, node); + + if (cur->data_len > count - done) + break; + + if (copy_to_user(buf + done, cur->event_data, cur->data_len)) { + rc = -EFAULT; + break; + } + done += cur->data_len; + list_del(&cur->node); + kfree(cur); + } + mutex_unlock(&eventq->mutex); + + return done == 0 ? rc : done; +} + +static const struct iommufd_eventq_ops iommufd_veventq_ops = { + .read = &iommufd_veventq_fops_read, +}; + /* Common Event Queue Functions */
static ssize_t iommufd_eventq_fops_read(struct file *filep, char __user *buf, @@ -473,3 +540,65 @@ int iommufd_fault_alloc(struct iommufd_ucmd *ucmd)
return rc; } + +int iommufd_veventq_alloc(struct iommufd_ucmd *ucmd) +{ + struct iommu_veventq_alloc *cmd = ucmd->cmd; + struct iommufd_veventq *veventq; + struct iommufd_viommu *viommu; + int fdno; + int rc; + + if (cmd->flags || cmd->type == IOMMU_VEVENTQ_TYPE_DEFAULT) + return -EOPNOTSUPP; + + viommu = iommufd_get_viommu(ucmd, cmd->viommu_id); + if (IS_ERR(viommu)) + return PTR_ERR(viommu); + down_write(&viommu->veventqs_rwsem); + + if (iommufd_viommu_find_veventq(viommu, cmd->type)) { + rc = -EEXIST; + goto out_unlock_veventqs; + } + + veventq = __iommufd_object_alloc(ucmd->ictx, veventq, + IOMMUFD_OBJ_VEVENTQ, common.obj); + if (IS_ERR(veventq)) { + rc = PTR_ERR(veventq); + goto out_unlock_veventqs; + } + + veventq->type = cmd->type; + veventq->viommu = viommu; + refcount_inc(&viommu->obj.users); + list_add_tail(&veventq->node, &viommu->veventqs); + + fdno = iommufd_eventq_init(&veventq->common, "[iommufd-viommu-event]", + ucmd->ictx, &iommufd_veventq_ops); + if (fdno < 0) { + rc = fdno; + goto out_abort; + } + + cmd->out_veventq_id = veventq->common.obj.id; + cmd->out_veventq_fd = fdno; + + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_put_fdno; + + iommufd_object_finalize(ucmd->ictx, &veventq->common.obj); + fd_install(fdno, veventq->common.filep); + goto out_unlock_veventqs; + +out_put_fdno: + put_unused_fd(fdno); + fput(veventq->common.filep); +out_abort: + iommufd_object_abort_and_destroy(ucmd->ictx, &veventq->common.obj); +out_unlock_veventqs: + up_write(&viommu->veventqs_rwsem); + iommufd_put_object(ucmd->ictx, &viommu->obj); + return rc; +} diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 49be19305d98..985661a4af07 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -310,6 +310,7 @@ union ucmd_buffer { struct iommu_vdevice_alloc vdev; struct iommu_vfio_ioas vfio_ioas; struct iommu_viommu_alloc viommu; + struct iommu_veventq_alloc veventq; #ifdef CONFIG_IOMMUFD_TEST struct iommu_test_cmd test; #endif @@ -367,6 +368,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { __reserved), IOCTL_OP(IOMMU_VIOMMU_ALLOC, iommufd_viommu_alloc_ioctl, struct iommu_viommu_alloc, out_viommu_id), + IOCTL_OP(IOMMU_VEVENTQ_ALLOC, iommufd_veventq_alloc, + struct iommu_veventq_alloc, out_veventq_fd), #ifdef CONFIG_IOMMUFD_TEST IOCTL_OP(IOMMU_TEST_CMD, iommufd_test, struct iommu_test_cmd, last), #endif @@ -502,6 +505,10 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { [IOMMUFD_OBJ_FAULT] = { .destroy = iommufd_fault_destroy, }, + [IOMMUFD_OBJ_VEVENTQ] = { + .destroy = iommufd_veventq_destroy, + .abort = iommufd_veventq_abort, + }, [IOMMUFD_OBJ_VIOMMU] = { .destroy = iommufd_viommu_destroy, }, diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 69b88e8c7c26..01df2b985f02 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -59,6 +59,8 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) viommu->ictx = ucmd->ictx; viommu->hwpt = hwpt_paging; refcount_inc(&viommu->hwpt->common.obj.users); + INIT_LIST_HEAD(&viommu->veventqs); + init_rwsem(&viommu->veventqs_rwsem); /* * It is the most likely case that a physical IOMMU is unpluggable. A * pluggable IOMMU instance (if exists) is responsible for refcounting