Hi Jean,
On 2020/4/30 22:34, Jean-Philippe Brucker wrote:
Some systems allow devices to handle I/O Page Faults in the core mm. For
example systems implementing the PCIe PRI extension or Arm SMMU stall
model. Infrastructure for reporting these recoverable page faults was
added to the IOMMU core by commit 0c830e6b3282 ("iommu: Introduce device
fault report API"). Add a page fault handler for host SVA.
IOMMU driver can now instantiate several fault workqueues and link them
to IOPF-capable devices. Drivers can choose between a single global
workqueue, one per IOMMU device, one per low-level fault queue, one per
domain, etc.
When it receives a fault event, supposedly in an IRQ handler, the IOMMU
driver reports the fault using iommu_report_device_fault(), which calls
the registered handler. The page fault handler then calls the mm fault
handler, and reports either success or failure with iommu_page_response().
When the handler succeeded, the IOMMU retries the access.
The iopf_param pointer could be embedded into iommu_fault_param. But
putting iopf_param into the iommu_param structure allows us not to care
about ordering between calls to iopf_queue_add_device() and
iommu_register_device_fault_handler().
Signed-off-by: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>
---
v5->v6: Simplify flush. As we're not flushing in the mm exit path
anymore, we can mandate that IOMMU drivers flush their low-level queue
themselves before calling iopf_queue_flush_dev(). No need to register
a flush callback anymore.
---
drivers/iommu/Kconfig | 3 +
drivers/iommu/Makefile | 1 +
include/linux/iommu.h | 51 +++++
drivers/iommu/io-pgfault.c | 383 +++++++++++++++++++++++++++++++++++++
4 files changed, 438 insertions(+)
create mode 100644 drivers/iommu/io-pgfault.c
[...]
+
+static void iopf_handle_group(struct work_struct *work)
+{
+ struct iopf_group *group;
+ struct iopf_fault *iopf, *next;
+ enum iommu_page_response_code status = IOMMU_PAGE_RESP_SUCCESS;
+
+ group = container_of(work, struct iopf_group, work);
+
+ list_for_each_entry_safe(iopf, next, &group->faults, head) {
+ /*
+ * For the moment, errors are sticky: don't handle subsequent
+ * faults in the group if there is an error.
+ */
+ if (status == IOMMU_PAGE_RESP_SUCCESS)
+ status = iopf_handle_single(iopf);
+
+ if (!(iopf->fault.prm.flags &
+ IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE))
+ kfree(iopf);
The iopf is freed,but not removed from the list. This will cause wild
pointer in code.
+ }
+
+ iopf_complete_group(group->dev, &group->last_fault, status);
+ kfree(group);
+}
+
[...]
+/**
+ * iopf_queue_flush_dev - Ensure that all queued faults have been processed
+ * @dev: the endpoint whose faults need to be flushed.
+ * @pasid: the PASID affected by this flush
+ *
+ * The IOMMU driver calls this before releasing a PASID, to ensure that all
+ * pending faults for this PASID have been handled, and won't hit the address
+ * space of the next process that uses this PASID. The driver must make sure
+ * that no new fault is added to the queue. In particular it must flush its
+ * low-level queue before calling this function.
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_flush_dev(struct device *dev, int pasid)
+{
+ int ret = 0;
+ struct iopf_device_param *iopf_param;
+ struct dev_iommu *param = dev->iommu;
+
+ if (!param)
+ return -ENODEV;
+
+ mutex_lock(¶m->lock);
+ iopf_param = param->iopf_param;
+ if (iopf_param)
+ flush_workqueue(iopf_param->queue->wq);
There may be other pasid iopf in the workqueue. Flush all tasks in
the workqueue will hurt other pasids. I might lose any context.
+ else
+ ret = -ENODEV;
+ mutex_unlock(¶m->lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_flush_dev);
+
+/**
+ * iopf_queue_discard_partial - Remove all pending partial fault
+ * @queue: the queue whose partial faults need to be discarded
+ *
+ * When the hardware queue overflows, last page faults in a group may have been
+ * lost and the IOMMU driver calls this to discard all partial faults. The
+ * driver shouldn't be adding new faults to this queue concurrently.
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_discard_partial(struct iopf_queue *queue)
+{
+ struct iopf_fault *iopf, *next;
+ struct iopf_device_param *iopf_param;
+
+ if (!queue)
+ return -EINVAL;
+
+ mutex_lock(&queue->lock);
+ list_for_each_entry(iopf_param, &queue->devices, queue_list) {
+ list_for_each_entry_safe(iopf, next, &iopf_param->partial, head)
+ kfree(iopf);
iopf is freed but not removed from the list.
+ }
+ mutex_unlock(&queue->lock);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_discard_partial);
+
+/**
+ * iopf_queue_add_device - Add producer to the fault queue
+ * @queue: IOPF queue
+ * @dev: device to add
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev)
+{
+ int ret = -EBUSY;
+ struct iopf_device_param *iopf_param;
+ struct dev_iommu *param = dev->iommu;
+
+ if (!param)
+ return -ENODEV;
+
+ iopf_param = kzalloc(sizeof(*iopf_param), GFP_KERNEL);
+ if (!iopf_param)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&iopf_param->partial);
+ iopf_param->queue = queue;
+ iopf_param->dev = dev;
+
+ mutex_lock(&queue->lock);
+ mutex_lock(¶m->lock);
+ if (!param->iopf_param) {
+ list_add(&iopf_param->queue_list, &queue->devices);
+ param->iopf_param = iopf_param;
+ ret = 0;
+ }
+ mutex_unlock(¶m->lock);
+ mutex_unlock(&queue->lock);
+
+ if (ret)
+ kfree(iopf_param);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_add_device);
+
+/**
+ * iopf_queue_remove_device - Remove producer from fault queue
+ * @queue: IOPF queue
+ * @dev: device to remove
+ *
+ * Caller makes sure that no more faults are reported for this device.
+ *
+ * Return: 0 on success and <0 on error.
+ */
+int iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
+{
+ int ret = 0;
+ struct iopf_fault *iopf, *next;
+ struct iopf_device_param *iopf_param;
+ struct dev_iommu *param = dev->iommu;
+
+ if (!param || !queue)
+ return -EINVAL;
+
+ mutex_lock(&queue->lock);
+ mutex_lock(¶m->lock);
+ iopf_param = param->iopf_param;
+ if (iopf_param && iopf_param->queue == queue) {
+ list_del(&iopf_param->queue_list);
+ param->iopf_param = NULL;
+ } else {
+ ret = -EINVAL;
+ }
+ mutex_unlock(¶m->lock);
+ mutex_unlock(&queue->lock);
+ if (ret)
+ return ret;
+
+ /* Just in case some faults are still stuck */
+ list_for_each_entry_safe(iopf, next, &iopf_param->partial, head)
+ kfree(iopf);
The same here.
+
+ kfree(iopf_param);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_remove_device);
+
+/**
+ * iopf_queue_alloc - Allocate and initialize a fault queue
+ * @name: a unique string identifying the queue (for workqueue)
+ *
+ * Return: the queue on success and NULL on error.
+ */
+struct iopf_queue *iopf_queue_alloc(const char *name)
+{
+ struct iopf_queue *queue;
+
+ queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+ if (!queue)
+ return NULL;
+
+ /*
+ * The WQ is unordered because the low-level handler enqueues faults by
+ * group. PRI requests within a group have to be ordered, but once
+ * that's dealt with, the high-level function can handle groups out of
+ * order.
+ */
+ queue->wq = alloc_workqueue("iopf_queue/%s", WQ_UNBOUND, 0, name);
+ if (!queue->wq) {
+ kfree(queue);
+ return NULL;
+ }
+
+ INIT_LIST_HEAD(&queue->devices);
+ mutex_init(&queue->lock);
+
+ return queue;
+}
+EXPORT_SYMBOL_GPL(iopf_queue_alloc);
+
+/**
+ * iopf_queue_free - Free IOPF queue
+ * @queue: queue to free
+ *
+ * Counterpart to iopf_queue_alloc(). The driver must not be queuing faults or
+ * adding/removing devices on this queue anymore.
+ */
+void iopf_queue_free(struct iopf_queue *queue)
+{
+ struct iopf_device_param *iopf_param, *next;
+
+ if (!queue)
+ return;
+
+ list_for_each_entry_safe(iopf_param, next, &queue->devices, queue_list)
+ iopf_queue_remove_device(queue, iopf_param->dev);
+
+ destroy_workqueue(queue->wq);
+ kfree(queue);
+}
+EXPORT_SYMBOL_GPL(iopf_queue_free);
Best regards,
baolu
