Re: [RFC KERNEL PATCH v2 1/3] xen/pci: Add xen_reset_device_state function

[Stefano Stabellini]

On Fri, 24 Nov 2023, Jiqian Chen wrote:
> When device on dom0 side has been reset, the vpci on Xen side
> won't get notification, so that the cached state in vpci is
> all out of date with the real device state.
> To solve that problem, this patch add a function to clear all
> vpci device state when device is reset on dom0 side.
> 
> And call that function in pcistub_init_device. Because when
> we use "pci-assignable-add" to assign a passthrough device in
> Xen, it will reset passthrough device and the vpci state will
> out of date, and then device will fail to restore bar state.
> 
> Signed-off-by: Jiqian Chen <Jiqian.Chen@xxxxxxx>
> Signed-off-by: Huang Rui <ray.huang@xxxxxxx>
> ---
>  drivers/xen/pci.c                  | 12 ++++++++++++
>  drivers/xen/xen-pciback/pci_stub.c |  3 +++
>  include/xen/interface/physdev.h    |  2 ++
>  include/xen/pci.h                  |  6 ++++++
>  4 files changed, 23 insertions(+)
> 
> diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
> index 72d4e3f193af..e9b30bc09139 100644
> --- a/drivers/xen/pci.c
> +++ b/drivers/xen/pci.c
> @@ -177,6 +177,18 @@ static int xen_remove_device(struct device *dev)
>  	return r;
>  }
>  
> +int xen_reset_device_state(const struct pci_dev *dev)
> +{
> +	struct physdev_pci_device device = {
> +		.seg = pci_domain_nr(dev->bus),
> +		.bus = dev->bus->number,
> +		.devfn = dev->devfn
> +	};
> +
> +	return HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_state_reset, &device);
> +}
> +EXPORT_SYMBOL_GPL(xen_reset_device_state);
> +
>  static int xen_pci_notifier(struct notifier_block *nb,
>  			    unsigned long action, void *data)
>  {
> diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
> index e34b623e4b41..5a96b6c66c07 100644
> --- a/drivers/xen/xen-pciback/pci_stub.c
> +++ b/drivers/xen/xen-pciback/pci_stub.c
> @@ -421,6 +421,9 @@ static int pcistub_init_device(struct pci_dev *dev)
>  	else {
>  		dev_dbg(&dev->dev, "resetting (FLR, D3, etc) the device\n");
>  		__pci_reset_function_locked(dev);
> +		err = xen_reset_device_state(dev);
> +		if (err)
> +			goto config_release;

Older versions of Xen won't have the hypercall
PHYSDEVOP_pci_device_state_reset implemented. I think we should do
something like:

if (err && xen_pvh_domain())
    goto config_release;


Or even:

if (xen_pvh_domain()) {
    err = xen_reset_device_state(dev);
    if (err)
        goto config_release;
}

depending on whether we want to call xen_reset_device_state also for PV
guests or not. I am assuming we don't want to error out on failure such
as -ENOENT for PV guests.


>  		pci_restore_state(dev);
>  	}
>  	/* Now disable the device (this also ensures some private device
> diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h
> index a237af867873..231526f80f6c 100644
> --- a/include/xen/interface/physdev.h
> +++ b/include/xen/interface/physdev.h
> @@ -263,6 +263,8 @@ struct physdev_pci_device {
>      uint8_t devfn;
>  };
>  
> +#define PHYSDEVOP_pci_device_state_reset     32
> +
>  #define PHYSDEVOP_DBGP_RESET_PREPARE    1
>  #define PHYSDEVOP_DBGP_RESET_DONE       2
>  
> diff --git a/include/xen/pci.h b/include/xen/pci.h
> index b8337cf85fd1..b2e2e856efd6 100644
> --- a/include/xen/pci.h
> +++ b/include/xen/pci.h
> @@ -4,10 +4,16 @@
>  #define __XEN_PCI_H__
>  
>  #if defined(CONFIG_XEN_DOM0)
> +int xen_reset_device_state(const struct pci_dev *dev);
>  int xen_find_device_domain_owner(struct pci_dev *dev);
>  int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
>  int xen_unregister_device_domain_owner(struct pci_dev *dev);
>  #else
> +static inline int xen_reset_device_state(const struct pci_dev *dev)
> +{
> +	return -1;
> +}
> +
>  static inline int xen_find_device_domain_owner(struct pci_dev *dev)
>  {
>  	return -1;
> -- 
> 2.34.1
>