Re: [PATCH] vfio/pci: Support error recovery

[Michael S. Tsirkin]

On Wed, Nov 30, 2016 at 09:04:13PM -0700, Alex Williamson wrote:
> On Sun, 27 Nov 2016 19:34:17 +0800
> Cao jin <caoj.fnst@xxxxxxxxxxxxxx> wrote:
> 
> > It is user space driver's or device-specific driver's(in guest) responsbility
> > to do a serious recovery when error happened. Link-reset is one part of
> > recovery, when pci device is assigned to VM via vfio, link-reset will do
> > twice in host & guest separately, which will cause many trouble for a
> > successful recovery, so, disable the vfio-pci's link-reset in aer driver
> > in host, this is a keypoint for guest to do error recovery successfully.
> > 
> > CC: alex.williamson@xxxxxxxxxx
> > CC: mst@xxxxxxxxxx
> > Signed-off-by: Cao jin <caoj.fnst@xxxxxxxxxxxxxx>
> > ---
> > This is actually a RFC version(has debug lines left), and has minor changes in
> > aer driver, so I think maybe it is better not to CC pci guys in this round.
> > Later will do.
> > 
> >  drivers/pci/pcie/aer/aerdrv_core.c  | 12 ++++++-
> >  drivers/vfio/pci/vfio_pci.c         | 63 +++++++++++++++++++++++++++++++++++--
> >  drivers/vfio/pci/vfio_pci_private.h |  2 ++
> >  3 files changed, 74 insertions(+), 3 deletions(-)
> > 
> > diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
> > index 521e39c..289fb8e 100644
> > --- a/drivers/pci/pcie/aer/aerdrv_core.c
> > +++ b/drivers/pci/pcie/aer/aerdrv_core.c
> > @@ -496,7 +496,17 @@ static void do_recovery(struct pci_dev *dev, int severity)
> >  			"error_detected",
> >  			report_error_detected);
> >  
> > -	if (severity == AER_FATAL) {
> > +	/* vfio-pci as a general meta driver, it actually couldn't do any real
> > +	 * recovery for device. It is user space driver, or device-specific
> > +	 * driver in guest who should take care of the serious error recovery,
> > +	 * link reset actually is one part of whole recovery. Doing reset_link
> > +	 * in aer driver of host kernel for vfio-pci devices will cause many
> > +	 * trouble for user space driver or guest's device-specific driver,
> > +	 * for example: the serious recovery often need to read register in
> > +	 * config space, but if register reading happens during link-resetting,
> > +	 * it is quite possible to return invalid value like all F's, which
> > +	 * will result in unpredictable error. */
> > +	if (severity == AER_FATAL && strcmp(dev->driver->name, "vfio-pci")) {
> >  		result = reset_link(dev);
> >  		if (result != PCI_ERS_RESULT_RECOVERED)
> >  			goto failed;
> 
> This is not acceptable.  If we want to make a path through AER recovery
> that does not reset the link, there should be a way for the driver to
> request it.  Testing the driver name is a horrible hack.

Right, just set a flag or something.

> The other
> question is what guarantees does vfio make that the device does get
> reset?  If an AER fault occurs and the user doesn't do a reset, what
> happens when that device is released and a host driver tries to make
> use of it?  The user makes no commitment to do a reset and there are
> only limited configurations where we even allow the user to perform a
> reset.

Let's try to work out what can be done a bit more constructively.
Doesn't vfio already reset device on release?
How about detecting there was an unhandled AER event
and doing link reset at that point?



> > diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
> > index 712a849..aefd751 100644
> > --- a/drivers/vfio/pci/vfio_pci.c
> > +++ b/drivers/vfio/pci/vfio_pci.c
> > @@ -535,6 +535,15 @@ static long vfio_pci_ioctl(void *device_data,
> >  	struct vfio_pci_device *vdev = device_data;
> >  	unsigned long minsz;
> >  
> > +	if (vdev->aer_recovering && (cmd == VFIO_DEVICE_SET_IRQS ||
> > +	    cmd == VFIO_DEVICE_RESET || cmd == VFIO_DEVICE_PCI_HOT_RESET)) {
> > +		int ret;
> > +		ret = wait_for_completion_interruptible(
> > +			&vdev->aer_error_completion);
> > +		if (ret)
> > +			return ret;
> > +	}
> > +
> >  	if (cmd == VFIO_DEVICE_GET_INFO) {
> >  		struct vfio_device_info info;
> >  
> > @@ -1117,6 +1126,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
> >  	vdev->irq_type = VFIO_PCI_NUM_IRQS;
> >  	mutex_init(&vdev->igate);
> >  	spin_lock_init(&vdev->irqlock);
> > +	init_completion(&vdev->aer_error_completion);
> >  
> >  	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
> >  	if (ret) {
> > @@ -1176,6 +1186,9 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
> >  {
> >  	struct vfio_pci_device *vdev;
> >  	struct vfio_device *device;
> > +	u32 uncor_status = 0;
> > +	unsigned int aer_cap_offset = 0;
> 
> Unnecessary initialization.
> 
> > +	int ret;
> >  
> >  	device = vfio_device_get_from_dev(&pdev->dev);
> >  	if (device == NULL)
> > @@ -1187,10 +1200,30 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
> >  		return PCI_ERS_RESULT_DISCONNECT;
> >  	}
> >  
> > +	/* get device's uncorrectable error status as soon as possible,
> > +	 * and signal it to user space. The later we read it, the possibility
> > +	 * the register value is mangled grows. */
> 
> Bad comment style (throughout).
> 
> > +	aer_cap_offset = pci_find_ext_capability(vdev->pdev, PCI_EXT_CAP_ID_ERR);
> > +	ret = pci_read_config_dword(vdev->pdev, aer_cap_offset + 
> > +                                    PCI_ERR_UNCOR_STATUS, &uncor_status);
> > +        if (ret)
> > +                return PCI_ERS_RESULT_DISCONNECT;
> > +
> > +	pr_err("device %d got AER detect notification. uncorrectable error status = 0x%x\n", pdev->devfn, uncor_status);//to be removed
> >  	mutex_lock(&vdev->igate);
> > +    
> > +	vdev->aer_recovering = true;
> > +	reinit_completion(&vdev->aer_error_completion);
> > +
> > +	/* suspend config space access from user space,
> > +	 * when vfio-pci's error recovery process is on */
> > +	pci_cfg_access_trylock(vdev->pdev);
> >  
> > -	if (vdev->err_trigger)
> > -		eventfd_signal(vdev->err_trigger, 1);
> > +	if (vdev->err_trigger && uncor_status) {
> > +		pr_err("device %d signal uncor status to user space", pdev->devfn);//may be removed
> > +		/* signal uncorrectable error status to user space */
> > +		eventfd_signal(vdev->err_trigger, uncor_status);

What does this mean that we trigger with uncor_status as opposed to 1?

> > +        }
> 
> } else... what?  By bypassing the AER link reset we've assumed
> responsibility for resetting the device.  Even if we signal the user,
> what guarantee do we have that the device is recovered?

So set flag and recover ?

> >  
> >  	mutex_unlock(&vdev->igate);
> >  
> > @@ -1199,8 +1232,34 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
> >  	return PCI_ERS_RESULT_CAN_RECOVER;
> >  }
> >  
> > +static void vfio_pci_aer_resume(struct pci_dev *pdev)
> > +{
> > +	struct vfio_pci_device *vdev;
> > +	struct vfio_device *device;
> > +
> > +	device = vfio_device_get_from_dev(&pdev->dev);
> > +	if (device == NULL)
> > +		return;
> > +
> > +	vdev = vfio_device_data(device);
> > +	if (vdev == NULL) {
> > +		vfio_device_put(device);
> > +		return;
> > +	}
> > +
> > +	/* vfio-pci's error recovery is done, time to
> > +	 * resume pci config space's accesses */
> > +	pci_cfg_access_unlock(vdev->pdev);
> > +
> > +	vdev->aer_recovering = false;
> > +	complete_all(&vdev->aer_error_completion);
> > +
> > +	vfio_device_put(device);
> > +}
> > +
> >  static const struct pci_error_handlers vfio_err_handlers = {
> >  	.error_detected = vfio_pci_aer_err_detected,
> > +	.resume         = vfio_pci_aer_resume,
> >  };
> >  
> >  static struct pci_driver vfio_pci_driver = {
> > diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
> > index 8a7d546..ebf1041 100644
> > --- a/drivers/vfio/pci/vfio_pci_private.h
> > +++ b/drivers/vfio/pci/vfio_pci_private.h
> > @@ -83,6 +83,8 @@ struct vfio_pci_device {
> >  	bool			bardirty;
> >  	bool			has_vga;
> >  	bool			needs_reset;
> > +	bool			aer_recovering;
> > +	struct completion	aer_error_completion;
> >  	struct pci_saved_state	*pci_saved_state;
> >  	int			refcnt;
> >  	struct eventfd_ctx	*err_trigger;