uacce: add uacce driver

Uacce (Unified/User-space-access-intended Accelerator Framework) targets to
provide Shared Virtual Addressing (SVA) between accelerators and processes.
So accelerator can access any data structure of the main cpu.
This differs from the data sharing between cpu and io device, which share
only data content rather than address.
Since unified address, hardware and user space of process can share the
same virtual address in the communication.

Uacce create a chrdev for every registration, the queue is allocated to
the process when the chrdev is opened. Then the process can access the
hardware resource by interact with the queue file. By mmap the queue
file space to user space, the process can directly put requests to the
hardware without syscall to the kernel space.

The IOMMU core only tracks mm<->device bonds at the moment, because it
only needs to handle IOTLB invalidation and PASID table entries. However
uacce needs a finer granularity since multiple queues from the same
device can be bound to an mm. When the mm exits, all bound queues must
be stopped so that the IOMMU can safely clear the PASID table entry and
reallocate the PASID.

An intermediate struct uacce_mm links uacce devices and queues.
Note that an mm may be bound to multiple devices but an uacce_mm
structure only ever belongs to a single device, because we don't need
anything more complex (if multiple devices are bound to one mm, then
we'll create one uacce_mm for each bond).

        uacce_device --+-- uacce_mm --+-- uacce_queue
                       |              '-- uacce_queue
                       |
                       '-- uacce_mm --+-- uacce_queue
                                      +-- uacce_queue
                                      '-- uacce_queue

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Kenneth Lee <liguozhu@hisilicon.com>
Signed-off-by: Zaibo Xu <xuzaibo@huawei.com>
Signed-off-by: Zhou Wang <wangzhou1@hisilicon.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

3 files changed, 632 insertions, 0 deletions

diff --git a/drivers/misc/uacce/Kconfig b/drivers/misc/uacce/Kconfig
new file mode 100644
index 000000000000..5e39b6083b0f
--- /dev/null
+++ b/drivers/misc/uacce/Kconfig
@@ -0,0 +1,13 @@
+config UACCE
+	tristate "Accelerator Framework for User Land"
+	depends on IOMMU_API
+	help
+	  UACCE provides interface for the user process to access the hardware
+	  without interaction with the kernel space in data path.
+
+	  The user-space interface is described in
+	  include/uapi/misc/uacce/uacce.h
+
+	  See Documentation/misc-devices/uacce.rst for more details.
+
+	  If you don't know what to do here, say N.
diff --git a/drivers/misc/uacce/Makefile b/drivers/misc/uacce/Makefile
new file mode 100644
index 000000000000..5b4374e8b5f2
--- /dev/null
+++ b/drivers/misc/uacce/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+obj-$(CONFIG_UACCE) += uacce.o
diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c
new file mode 100644
index 000000000000..ffced4da3c2c
--- /dev/null
+++ b/drivers/misc/uacce/uacce.c
@@ -0,0 +1,617 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/compat.h>
+#include <linux/dma-mapping.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/uacce.h>
+
+static struct class *uacce_class;
+static dev_t uacce_devt;
+static DEFINE_MUTEX(uacce_mutex);
+static DEFINE_XARRAY_ALLOC(uacce_xa);
+
+static int uacce_start_queue(struct uacce_queue *q)
+{
+	int ret = 0;
+
+	mutex_lock(&uacce_mutex);
+
+	if (q->state != UACCE_Q_INIT) {
+		ret = -EINVAL;
+		goto out_with_lock;
+	}
+
+	if (q->uacce->ops->start_queue) {
+		ret = q->uacce->ops->start_queue(q);
+		if (ret < 0)
+			goto out_with_lock;
+	}
+
+	q->state = UACCE_Q_STARTED;
+
+out_with_lock:
+	mutex_unlock(&uacce_mutex);
+
+	return ret;
+}
+
+static int uacce_put_queue(struct uacce_queue *q)
+{
+	struct uacce_device *uacce = q->uacce;
+
+	mutex_lock(&uacce_mutex);
+
+	if (q->state == UACCE_Q_ZOMBIE)
+		goto out;
+
+	if ((q->state == UACCE_Q_STARTED) && uacce->ops->stop_queue)
+		uacce->ops->stop_queue(q);
+
+	if ((q->state == UACCE_Q_INIT || q->state == UACCE_Q_STARTED) &&
+	     uacce->ops->put_queue)
+		uacce->ops->put_queue(q);
+
+	q->state = UACCE_Q_ZOMBIE;
+out:
+	mutex_unlock(&uacce_mutex);
+
+	return 0;
+}
+
+static long uacce_fops_unl_ioctl(struct file *filep,
+				 unsigned int cmd, unsigned long arg)
+{
+	struct uacce_queue *q = filep->private_data;
+	struct uacce_device *uacce = q->uacce;
+
+	switch (cmd) {
+	case UACCE_CMD_START_Q:
+		return uacce_start_queue(q);
+
+	case UACCE_CMD_PUT_Q:
+		return uacce_put_queue(q);
+
+	default:
+		if (!uacce->ops->ioctl)
+			return -EINVAL;
+
+		return uacce->ops->ioctl(q, cmd, arg);
+	}
+}
+
+#ifdef CONFIG_COMPAT
+static long uacce_fops_compat_ioctl(struct file *filep,
+				   unsigned int cmd, unsigned long arg)
+{
+	arg = (unsigned long)compat_ptr(arg);
+
+	return uacce_fops_unl_ioctl(filep, cmd, arg);
+}
+#endif
+
+static int uacce_sva_exit(struct device *dev, struct iommu_sva *handle,
+			  void *data)
+{
+	struct uacce_mm *uacce_mm = data;
+	struct uacce_queue *q;
+
+	/*
+	 * No new queue can be added concurrently because no caller can have a
+	 * reference to this mm. But there may be concurrent calls to
+	 * uacce_mm_put(), so we need the lock.
+	 */
+	mutex_lock(&uacce_mm->lock);
+	list_for_each_entry(q, &uacce_mm->queues, list)
+		uacce_put_queue(q);
+	uacce_mm->mm = NULL;
+	mutex_unlock(&uacce_mm->lock);
+
+	return 0;
+}
+
+static struct iommu_sva_ops uacce_sva_ops = {
+	.mm_exit = uacce_sva_exit,
+};
+
+static struct uacce_mm *uacce_mm_get(struct uacce_device *uacce,
+				     struct uacce_queue *q,
+				     struct mm_struct *mm)
+{
+	struct uacce_mm *uacce_mm = NULL;
+	struct iommu_sva *handle = NULL;
+	int ret;
+
+	lockdep_assert_held(&uacce->mm_lock);
+
+	list_for_each_entry(uacce_mm, &uacce->mm_list, list) {
+		if (uacce_mm->mm == mm) {
+			mutex_lock(&uacce_mm->lock);
+			list_add(&q->list, &uacce_mm->queues);
+			mutex_unlock(&uacce_mm->lock);
+			return uacce_mm;
+		}
+	}
+
+	uacce_mm = kzalloc(sizeof(*uacce_mm), GFP_KERNEL);
+	if (!uacce_mm)
+		return NULL;
+
+	if (uacce->flags & UACCE_DEV_SVA) {
+		/*
+		 * Safe to pass an incomplete uacce_mm, since mm_exit cannot
+		 * fire while we hold a reference to the mm.
+		 */
+		handle = iommu_sva_bind_device(uacce->parent, mm, uacce_mm);
+		if (IS_ERR(handle))
+			goto err_free;
+
+		ret = iommu_sva_set_ops(handle, &uacce_sva_ops);
+		if (ret)
+			goto err_unbind;
+
+		uacce_mm->pasid = iommu_sva_get_pasid(handle);
+		if (uacce_mm->pasid == IOMMU_PASID_INVALID)
+			goto err_unbind;
+	}
+
+	uacce_mm->mm = mm;
+	uacce_mm->handle = handle;
+	INIT_LIST_HEAD(&uacce_mm->queues);
+	mutex_init(&uacce_mm->lock);
+	list_add(&q->list, &uacce_mm->queues);
+	list_add(&uacce_mm->list, &uacce->mm_list);
+
+	return uacce_mm;
+
+err_unbind:
+	if (handle)
+		iommu_sva_unbind_device(handle);
+err_free:
+	kfree(uacce_mm);
+	return NULL;
+}
+
+static void uacce_mm_put(struct uacce_queue *q)
+{
+	struct uacce_mm *uacce_mm = q->uacce_mm;
+
+	lockdep_assert_held(&q->uacce->mm_lock);
+
+	mutex_lock(&uacce_mm->lock);
+	list_del(&q->list);
+	mutex_unlock(&uacce_mm->lock);
+
+	if (list_empty(&uacce_mm->queues)) {
+		if (uacce_mm->handle)
+			iommu_sva_unbind_device(uacce_mm->handle);
+		list_del(&uacce_mm->list);
+		kfree(uacce_mm);
+	}
+}
+
+static int uacce_fops_open(struct inode *inode, struct file *filep)
+{
+	struct uacce_mm *uacce_mm = NULL;
+	struct uacce_device *uacce;
+	struct uacce_queue *q;
+	int ret = 0;
+
+	uacce = xa_load(&uacce_xa, iminor(inode));
+	if (!uacce)
+		return -ENODEV;
+
+	q = kzalloc(sizeof(struct uacce_queue), GFP_KERNEL);
+	if (!q)
+		return -ENOMEM;
+
+	mutex_lock(&uacce->mm_lock);
+	uacce_mm = uacce_mm_get(uacce, q, current->mm);
+	mutex_unlock(&uacce->mm_lock);
+	if (!uacce_mm) {
+		ret = -ENOMEM;
+		goto out_with_mem;
+	}
+
+	q->uacce = uacce;
+	q->uacce_mm = uacce_mm;
+
+	if (uacce->ops->get_queue) {
+		ret = uacce->ops->get_queue(uacce, uacce_mm->pasid, q);
+		if (ret < 0)
+			goto out_with_mm;
+	}
+
+	init_waitqueue_head(&q->wait);
+	filep->private_data = q;
+	q->state = UACCE_Q_INIT;
+
+	return 0;
+
+out_with_mm:
+	mutex_lock(&uacce->mm_lock);
+	uacce_mm_put(q);
+	mutex_unlock(&uacce->mm_lock);
+out_with_mem:
+	kfree(q);
+	return ret;
+}
+
+static int uacce_fops_release(struct inode *inode, struct file *filep)
+{
+	struct uacce_queue *q = filep->private_data;
+	struct uacce_device *uacce = q->uacce;
+
+	uacce_put_queue(q);
+
+	mutex_lock(&uacce->mm_lock);
+	uacce_mm_put(q);
+	mutex_unlock(&uacce->mm_lock);
+
+	kfree(q);
+
+	return 0;
+}
+
+static void uacce_vma_close(struct vm_area_struct *vma)
+{
+	struct uacce_queue *q = vma->vm_private_data;
+	struct uacce_qfile_region *qfr = NULL;
+
+	if (vma->vm_pgoff < UACCE_MAX_REGION)
+		qfr = q->qfrs[vma->vm_pgoff];
+
+	kfree(qfr);
+}
+
+static const struct vm_operations_struct uacce_vm_ops = {
+	.close = uacce_vma_close,
+};
+
+static int uacce_fops_mmap(struct file *filep, struct vm_area_struct *vma)
+{
+	struct uacce_queue *q = filep->private_data;
+	struct uacce_device *uacce = q->uacce;
+	struct uacce_qfile_region *qfr;
+	enum uacce_qfrt type = UACCE_MAX_REGION;
+	int ret = 0;
+
+	if (vma->vm_pgoff < UACCE_MAX_REGION)
+		type = vma->vm_pgoff;
+	else
+		return -EINVAL;
+
+	qfr = kzalloc(sizeof(*qfr), GFP_KERNEL);
+	if (!qfr)
+		return -ENOMEM;
+
+	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_WIPEONFORK;
+	vma->vm_ops = &uacce_vm_ops;
+	vma->vm_private_data = q;
+	qfr->type = type;
+
+	mutex_lock(&uacce_mutex);
+
+	if (q->state != UACCE_Q_INIT && q->state != UACCE_Q_STARTED) {
+		ret = -EINVAL;
+		goto out_with_lock;
+	}
+
+	if (q->qfrs[type]) {
+		ret = -EEXIST;
+		goto out_with_lock;
+	}
+
+	switch (type) {
+	case UACCE_QFRT_MMIO:
+		if (!uacce->ops->mmap) {
+			ret = -EINVAL;
+			goto out_with_lock;
+		}
+
+		ret = uacce->ops->mmap(q, vma, qfr);
+		if (ret)
+			goto out_with_lock;
+
+		break;
+
+	case UACCE_QFRT_DUS:
+		if (!uacce->ops->mmap) {
+			ret = -EINVAL;
+			goto out_with_lock;
+		}
+
+		ret = uacce->ops->mmap(q, vma, qfr);
+		if (ret)
+			goto out_with_lock;
+		break;
+
+	default:
+		ret = -EINVAL;
+		goto out_with_lock;
+	}
+
+	q->qfrs[type] = qfr;
+	mutex_unlock(&uacce_mutex);
+
+	return ret;
+
+out_with_lock:
+	mutex_unlock(&uacce_mutex);
+	kfree(qfr);
+	return ret;
+}
+
+static __poll_t uacce_fops_poll(struct file *file, poll_table *wait)
+{
+	struct uacce_queue *q = file->private_data;
+	struct uacce_device *uacce = q->uacce;
+
+	poll_wait(file, &q->wait, wait);
+	if (uacce->ops->is_q_updated && uacce->ops->is_q_updated(q))
+		return EPOLLIN | EPOLLRDNORM;
+
+	return 0;
+}
+
+static const struct file_operations uacce_fops = {
+	.owner		= THIS_MODULE,
+	.open		= uacce_fops_open,
+	.release	= uacce_fops_release,
+	.unlocked_ioctl	= uacce_fops_unl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= uacce_fops_compat_ioctl,
+#endif
+	.mmap		= uacce_fops_mmap,
+	.poll		= uacce_fops_poll,
+};
+
+#define to_uacce_device(dev) container_of(dev, struct uacce_device, dev)
+
+static ssize_t api_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	return sprintf(buf, "%s\n", uacce->api_ver);
+}
+
+static ssize_t flags_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	return sprintf(buf, "%u\n", uacce->flags);
+}
+
+static ssize_t available_instances_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	if (!uacce->ops->get_available_instances)
+		return -ENODEV;
+
+	return sprintf(buf, "%d\n",
+		       uacce->ops->get_available_instances(uacce));
+}
+
+static ssize_t algorithms_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	return sprintf(buf, "%s\n", uacce->algs);
+}
+
+static ssize_t region_mmio_size_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	return sprintf(buf, "%lu\n",
+		       uacce->qf_pg_num[UACCE_QFRT_MMIO] << PAGE_SHIFT);
+}
+
+static ssize_t region_dus_size_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	return sprintf(buf, "%lu\n",
+		       uacce->qf_pg_num[UACCE_QFRT_DUS] << PAGE_SHIFT);
+}
+
+static DEVICE_ATTR_RO(api);
+static DEVICE_ATTR_RO(flags);
+static DEVICE_ATTR_RO(available_instances);
+static DEVICE_ATTR_RO(algorithms);
+static DEVICE_ATTR_RO(region_mmio_size);
+static DEVICE_ATTR_RO(region_dus_size);
+
+static struct attribute *uacce_dev_attrs[] = {
+	&dev_attr_api.attr,
+	&dev_attr_flags.attr,
+	&dev_attr_available_instances.attr,
+	&dev_attr_algorithms.attr,
+	&dev_attr_region_mmio_size.attr,
+	&dev_attr_region_dus_size.attr,
+	NULL,
+};
+
+static umode_t uacce_dev_is_visible(struct kobject *kobj,
+				    struct attribute *attr, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	if (((attr == &dev_attr_region_mmio_size.attr) &&
+	    (!uacce->qf_pg_num[UACCE_QFRT_MMIO])) ||
+	    ((attr == &dev_attr_region_dus_size.attr) &&
+	    (!uacce->qf_pg_num[UACCE_QFRT_DUS])))
+		return 0;
+
+	return attr->mode;
+}
+
+static struct attribute_group uacce_dev_group = {
+	.is_visible	= uacce_dev_is_visible,
+	.attrs		= uacce_dev_attrs,
+};
+
+__ATTRIBUTE_GROUPS(uacce_dev);
+
+static void uacce_release(struct device *dev)
+{
+	struct uacce_device *uacce = to_uacce_device(dev);
+
+	kfree(uacce);
+}
+
+/**
+ * uacce_alloc() - alloc an accelerator
+ * @parent: pointer of uacce parent device
+ * @interface: pointer of uacce_interface for register
+ *
+ * Returns uacce pointer if success and ERR_PTR if not
+ * Need check returned negotiated uacce->flags
+ */
+struct uacce_device *uacce_alloc(struct device *parent,
+				 struct uacce_interface *interface)
+{
+	unsigned int flags = interface->flags;
+	struct uacce_device *uacce;
+	int ret;
+
+	uacce = kzalloc(sizeof(struct uacce_device), GFP_KERNEL);
+	if (!uacce)
+		return ERR_PTR(-ENOMEM);
+
+	if (flags & UACCE_DEV_SVA) {
+		ret = iommu_dev_enable_feature(parent, IOMMU_DEV_FEAT_SVA);
+		if (ret)
+			flags &= ~UACCE_DEV_SVA;
+	}
+
+	uacce->parent = parent;
+	uacce->flags = flags;
+	uacce->ops = interface->ops;
+
+	ret = xa_alloc(&uacce_xa, &uacce->dev_id, uacce, xa_limit_32b,
+		       GFP_KERNEL);
+	if (ret < 0)
+		goto err_with_uacce;
+
+	INIT_LIST_HEAD(&uacce->mm_list);
+	mutex_init(&uacce->mm_lock);
+	device_initialize(&uacce->dev);
+	uacce->dev.devt = MKDEV(MAJOR(uacce_devt), uacce->dev_id);
+	uacce->dev.class = uacce_class;
+	uacce->dev.groups = uacce_dev_groups;
+	uacce->dev.parent = uacce->parent;
+	uacce->dev.release = uacce_release;
+	dev_set_name(&uacce->dev, "%s-%d", interface->name, uacce->dev_id);
+
+	return uacce;
+
+err_with_uacce:
+	if (flags & UACCE_DEV_SVA)
+		iommu_dev_disable_feature(uacce->parent, IOMMU_DEV_FEAT_SVA);
+	kfree(uacce);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(uacce_alloc);
+
+/**
+ * uacce_register() - add the accelerator to cdev and export to user space
+ * @uacce: The initialized uacce device
+ *
+ * Return 0 if register succeeded, or an error.
+ */
+int uacce_register(struct uacce_device *uacce)
+{
+	if (!uacce)
+		return -ENODEV;
+
+	uacce->cdev = cdev_alloc();
+	if (!uacce->cdev)
+		return -ENOMEM;
+
+	uacce->cdev->ops = &uacce_fops;
+	uacce->cdev->owner = THIS_MODULE;
+
+	return cdev_device_add(uacce->cdev, &uacce->dev);
+}
+EXPORT_SYMBOL_GPL(uacce_register);
+
+/**
+ * uacce_remove() - remove the accelerator
+ * @uacce: the accelerator to remove
+ */
+void uacce_remove(struct uacce_device *uacce)
+{
+	struct uacce_mm *uacce_mm;
+	struct uacce_queue *q;
+
+	if (!uacce)
+		return;
+
+	/* ensure no open queue remains */
+	mutex_lock(&uacce->mm_lock);
+	list_for_each_entry(uacce_mm, &uacce->mm_list, list) {
+		/*
+		 * We don't take the uacce_mm->lock here. Since we hold the
+		 * device's mm_lock, no queue can be added to or removed from
+		 * this uacce_mm. We may run concurrently with mm_exit, but
+		 * uacce_put_queue() is serialized and iommu_sva_unbind_device()
+		 * waits for the lock that mm_exit is holding.
+		 */
+		list_for_each_entry(q, &uacce_mm->queues, list)
+			uacce_put_queue(q);
+
+		if (uacce->flags & UACCE_DEV_SVA) {
+			iommu_sva_unbind_device(uacce_mm->handle);
+			uacce_mm->handle = NULL;
+		}
+	}
+	mutex_unlock(&uacce->mm_lock);
+
+	/* disable sva now since no opened queues */
+	if (uacce->flags & UACCE_DEV_SVA)
+		iommu_dev_disable_feature(uacce->parent, IOMMU_DEV_FEAT_SVA);
+
+	if (uacce->cdev)
+		cdev_device_del(uacce->cdev, &uacce->dev);
+	xa_erase(&uacce_xa, uacce->dev_id);
+	put_device(&uacce->dev);
+}
+EXPORT_SYMBOL_GPL(uacce_remove);
+
+static int __init uacce_init(void)
+{
+	int ret;
+
+	uacce_class = class_create(THIS_MODULE, UACCE_NAME);
+	if (IS_ERR(uacce_class))
+		return PTR_ERR(uacce_class);
+
+	ret = alloc_chrdev_region(&uacce_devt, 0, MINORMASK, UACCE_NAME);
+	if (ret)
+		class_destroy(uacce_class);
+
+	return ret;
+}
+
+static __exit void uacce_exit(void)
+{
+	unregister_chrdev_region(uacce_devt, MINORMASK);
+	class_destroy(uacce_class);
+}
+
+subsys_initcall(uacce_init);
+module_exit(uacce_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Hisilicon Tech. Co., Ltd.");
+MODULE_DESCRIPTION("Accelerator interface for Userland applications");