lkml.org 
[lkml]   [2018]   [Sep]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH v5 13/23] iommu: introduce device fault report API
On Fri, 14 Sep 2018 15:24:41 +0200
Auger Eric <eric.auger@redhat.com> wrote:

> Hi Jacob,
>
> On 5/11/18 10:54 PM, Jacob Pan wrote:
> > 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.
> >
> > Faults detected by IOMMU is based on the transaction's source ID
> > which can be reported at per device basis, regardless of the device
> > type is a PCI device or not.
> >
> > The fault types include recoverable (e.g. page request) and
> > unrecoverable faults(e.g. access error). In most cases, faults can
> > be handled by IOMMU drivers internally. The primary use cases are as
> > follows:
> > 1. page request fault originated from an SVM capable device that is
> > assigned to guest via vIOMMU. In this case, the first level page
> > tables are owned by the guest. Page request must be propagated to
> > the guest to let guest OS fault in the pages then send page
> > response. In this mechanism, the direct receiver of IOMMU fault
> > notification is VFIO, which can relay notification events to QEMU
> > or other user space software.
> >
> > 2. faults need more subtle handling by device drivers. Other than
> > simply invoke reset function, there are needs to let device driver
> > handle the fault with a smaller impact.
> >
> > This patchset is intended to create a generic fault report API such
> > that it can scale as follows:
> > - all IOMMU types
> > - PCI and non-PCI devices
> > - recoverable and unrecoverable faults
> > - VFIO and other other in kernel users
> > - DMA & IRQ remapping (TBD)
> > The original idea was brought up by David Woodhouse and discussions
> > summarized at https://lwn.net/Articles/608914/.
> >
> > Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> > Signed-off-by: Ashok Raj <ashok.raj@intel.com>
> > Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
> > ---
> > drivers/iommu/iommu.c | 149
> > +++++++++++++++++++++++++++++++++++++++++++++++++-
> > include/linux/iommu.h | 35 +++++++++++- 2 files changed, 181
> > insertions(+), 3 deletions(-)
> >
> > diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> > index 3a49b96..b3f9daf 100644
> > --- a/drivers/iommu/iommu.c
> > +++ b/drivers/iommu/iommu.c
> > @@ -609,6 +609,13 @@ 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;
> > @@ -639,6 +646,7 @@ 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:
> > @@ -685,7 +693,7 @@ 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;
> > @@ -820,6 +828,145 @@ 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, call this handler with
> > the fault event
> > + * and data as argument. The handler should return 0 on success.
> > If the fault is
> > + * recoverable (IOMMU_FAULT_PAGE_REQ), the handler can also
> > complete
> > + * the fault by calling iommu_page_response() with one of the
> > following
> > + * response code:
> > + * - IOMMU_PAGE_RESP_SUCCESS: retry the translation
> > + * - IOMMU_PAGE_RESP_INVALID: terminate the fault
> > + * - IOMMU_PAGE_RESP_FAILURE: terminate the fault and stop
> > reporting
> > + * page faults if possible.
> > + *
> > + * 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(&param->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(&param->fault_param->lock);
> > + param->fault_param->handler = handler;
> > + param->fault_param->data = data;
> > + INIT_LIST_HEAD(&param->fault_param->faults);
> > +
> > +done_unlock:
> > + mutex_unlock(&param->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(&param->lock);
> > + /* we cannot unregister handler if there are pending
> > faults */
> > + if (!list_empty(&param->fault_param->faults)) {
> > + ret = -EBUSY;
> > + goto unlock;
> > + }
> > +
> > + kfree(param->fault_param);
> > + param->fault_param = NULL;
> > + put_device(dev);
> don't you need to test if (param->fault_param) is set first. Otherwise
> you may end up with an unpaired put_device()?
You are right, thanks.

I am also working on allowing multiple registrations per handler. i.e.
device can register the same fault handler with different data. Then I
will add refcount. The motivation is that for PCIe device with
sub-device partitioned at PASID granularity, fault reporting needs to
be at PCI device + PASID level.
>
> [...]
> s/needs/need
>
taken, thanks
> Thanks
>
> Eric
> > + * @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;
> > };
> >
> > @@ -357,6 +362,7 @@ struct iommu_fault_param {
> > * struct iommu_fwspec *iommu_fwspec;
> > */
> > struct iommu_param {
> > + struct mutex lock;
> > struct iommu_fault_param *fault_param;
> > };
> >
> > @@ -456,6 +462,14 @@ 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 *); @@ -727,6
> > +741,23 @@ 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;
> >

[Jacob Pan]

\
 
 \ /
  Last update: 2018-09-17 18:56    [W:0.255 / U:0.756 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site