On Sun, 17 Mar 2019 18:22:13 +0100
Eric Auger <eric.auger@xxxxxxxxxx> wrote:
> From: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
>
> Traditionally, device specific faults are detected and handled within
> their own device drivers. When IOMMU is enabled, faults such as DMA
> related transactions are detected by IOMMU. There is no generic
> reporting mechanism to report faults back to the in-kernel device
> driver or the guest OS in case of assigned devices.
>
> This patch introduces a registration API for device specific fault
> handlers. This differs from the existing iommu_set_fault_handler/
> report_iommu_fault infrastructures in several ways:
> - it allows to report more sophisticated fault events (both
> unrecoverable faults and page request faults) due to the nature
> of the iommu_fault struct
> - it is device specific and not domain specific.
>
> The current iommu_report_device_fault() implementation only handles
> the "shoot and forget" unrecoverable fault case. Handling of page
> request faults or stalled faults will come later.
>
> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> Signed-off-by: Ashok Raj <ashok.raj@xxxxxxxxx>
> Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@xxxxxxx>
> Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
>
> ---
>
> v4 -> v5:
> - remove stuff related to recoverable faults
> ---
> drivers/iommu/iommu.c | 134 +++++++++++++++++++++++++++++++++++++++++-
> include/linux/iommu.h | 36 +++++++++++-
> 2 files changed, 168 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> index 33a982e33716..56d5bf68de53 100644
> --- a/drivers/iommu/iommu.c
> +++ b/drivers/iommu/iommu.c
> @@ -648,6 +648,13 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
> goto err_free_name;
> }
>
> + dev->iommu_param = kzalloc(sizeof(*dev->iommu_param), GFP_KERNEL);
> + if (!dev->iommu_param) {
> + ret = -ENOMEM;
> + goto err_free_name;
> + }
> + mutex_init(&dev->iommu_param->lock);
> +
> kobject_get(group->devices_kobj);
>
> dev->iommu_group = group;
> @@ -678,6 +685,7 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
> mutex_unlock(&group->mutex);
> dev->iommu_group = NULL;
> kobject_put(group->devices_kobj);
> + kfree(dev->iommu_param);
> err_free_name:
> kfree(device->name);
> err_remove_link:
> @@ -724,7 +732,7 @@ void iommu_group_remove_device(struct device *dev)
> sysfs_remove_link(&dev->kobj, "iommu_group");
>
> trace_remove_device_from_group(group->id, dev);
> -
> + kfree(dev->iommu_param);
> kfree(device->name);
> kfree(device);
> dev->iommu_group = NULL;
> @@ -858,6 +866,130 @@ int iommu_group_unregister_notifier(struct iommu_group *group,
> }
> EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier);
>
> +/**
> + * iommu_register_device_fault_handler() - Register a device fault handler
> + * @dev: the device
> + * @handler: the fault handler
> + * @data: private data passed as argument to the handler
> + *
> + * When an IOMMU fault event is received, this handler gets called with the
> + * fault event and data as argument.
> + *
> + * Return 0 if the fault handler was installed successfully, or an error.
> + */
> +int iommu_register_device_fault_handler(struct device *dev,
> + iommu_dev_fault_handler_t handler,
> + void *data)
> +{
> + struct iommu_param *param = dev->iommu_param;
> + int ret = 0;
> +
> + /*
> + * Device iommu_param should have been allocated when device is
> + * added to its iommu_group.
> + */
> + if (!param)
> + return -EINVAL;
> +
> + mutex_lock(¶m->lock);
> + /* Only allow one fault handler registered for each device */
> + if (param->fault_param) {
> + ret = -EBUSY;
> + goto done_unlock;
> + }
> +
> + get_device(dev);
> + param->fault_param =
> + kzalloc(sizeof(struct iommu_fault_param), GFP_KERNEL);
> + if (!param->fault_param) {
> + put_device(dev);
> + ret = -ENOMEM;
> + goto done_unlock;
> + }
> + mutex_init(¶m->fault_param->lock);
> + param->fault_param->handler = handler;
> + param->fault_param->data = data;
> + INIT_LIST_HEAD(¶m->fault_param->faults);
> +
> +done_unlock:
> + mutex_unlock(¶m->lock);
> +
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(iommu_register_device_fault_handler);
> +
> +/**
> + * iommu_unregister_device_fault_handler() - Unregister the device fault handler
> + * @dev: the device
> + *
> + * Remove the device fault handler installed with
> + * iommu_register_device_fault_handler().
> + *
> + * Return 0 on success, or an error.
> + */
> +int iommu_unregister_device_fault_handler(struct device *dev)
> +{
> + struct iommu_param *param = dev->iommu_param;
> + int ret = 0;
> +
> + if (!param)
> + return -EINVAL;
> +
> + mutex_lock(¶m->lock);
> +
> + if (!param->fault_param)
> + goto unlock;
> +
> + /* we cannot unregister handler if there are pending faults */
> + if (!list_empty(¶m->fault_param->faults)) {
> + ret = -EBUSY;
> + goto unlock;
> + }
> +
> + kfree(param->fault_param);
> + param->fault_param = NULL;
> + put_device(dev);
> +unlock:
> + mutex_unlock(¶m->lock);
> +
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(iommu_unregister_device_fault_handler);
> +
> +
> +/**
> + * iommu_report_device_fault() - Report fault event to device
> + * @dev: the device
> + * @evt: fault event data
> + *
> + * Called by IOMMU model specific drivers when fault is detected, typically
> + * in a threaded IRQ handler.
> + *
> + * Return 0 on success, or an error.
> + */
> +int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
> +{
> + struct iommu_fault_param *fparam;
> + int ret = 0;
> +
Nit, for consistency with above functions, it'd be useful to have:
struct iommu_param *param = dev->iommu_param;
It's not as obvious as it could be that we're using the same mutex here
as in the register/unregister above. Thanks,
Alex
> + /* iommu_param is allocated when device is added to group */
> + if (!dev->iommu_param || !evt)
> + return -EINVAL;
> + /* we only report device fault if there is a handler registered */
> + mutex_lock(&dev->iommu_param->lock);
> + if (!dev->iommu_param->fault_param ||
> + !dev->iommu_param->fault_param->handler) {
> + ret = -EINVAL;
> + goto done_unlock;
> + }
> + fparam = dev->iommu_param->fault_param;
> + ret = fparam->handler(evt, fparam->data);
> +done_unlock:
> + mutex_unlock(&dev->iommu_param->lock);
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(iommu_report_device_fault);
> +
> /**
> * iommu_group_id - Return ID for a group
> * @group: the group to ID
> diff --git a/include/linux/iommu.h b/include/linux/iommu.h
> index c6f398f7e6e0..aeb4b615cb44 100644
> --- a/include/linux/iommu.h
> +++ b/include/linux/iommu.h
> @@ -257,11 +257,13 @@ struct iommu_device {
> * unrecoverable faults such as DMA or IRQ remapping faults.
> *
> * @fault: fault descriptor
> + * @list pending fault event list, used for tracking responses
> * @iommu_private: used by the IOMMU driver for storing fault-specific
> * data. Users should not modify this field before
> * sending the fault response.
> */
> struct iommu_fault_event {
> + struct list_head list;
> struct iommu_fault fault;
> u64 iommu_private;
> };
> @@ -270,10 +272,13 @@ struct iommu_fault_event {
> * struct iommu_fault_param - per-device IOMMU fault data
> * @dev_fault_handler: Callback function to handle IOMMU faults at device level
> * @data: handler private data
> - *
> + * @faults: holds the pending faults which needs response, e.g. page response.
> + * @lock: protect pending PRQ event list
> */
> struct iommu_fault_param {
> iommu_dev_fault_handler_t handler;
> + struct list_head faults;
> + struct mutex lock;
> void *data;
> };
>
> @@ -287,6 +292,7 @@ struct iommu_fault_param {
> * struct iommu_fwspec *iommu_fwspec;
> */
> struct iommu_param {
> + struct mutex lock;
> struct iommu_fault_param *fault_param;
> };
>
> @@ -379,6 +385,15 @@ extern int iommu_group_register_notifier(struct iommu_group *group,
> struct notifier_block *nb);
> extern int iommu_group_unregister_notifier(struct iommu_group *group,
> struct notifier_block *nb);
> +extern int iommu_register_device_fault_handler(struct device *dev,
> + iommu_dev_fault_handler_t handler,
> + void *data);
> +
> +extern int iommu_unregister_device_fault_handler(struct device *dev);
> +
> +extern int iommu_report_device_fault(struct device *dev,
> + struct iommu_fault_event *evt);
> +
> extern int iommu_group_id(struct iommu_group *group);
> extern struct iommu_group *iommu_group_get_for_dev(struct device *dev);
> extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *);
> @@ -659,6 +674,25 @@ static inline int iommu_group_unregister_notifier(struct iommu_group *group,
> return 0;
> }
>
> +static inline
> +int iommu_register_device_fault_handler(struct device *dev,
> + iommu_dev_fault_handler_t handler,
> + void *data)
> +{
> + return -ENODEV;
> +}
> +
> +static inline int iommu_unregister_device_fault_handler(struct device *dev)
> +{
> + return 0;
> +}
> +
> +static inline
> +int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
> +{
> + return -ENODEV;
> +}
> +
> static inline int iommu_group_id(struct iommu_group *group)
> {
> return -ENODEV;
