Re: [Qemu-devel] [RFC v9 05/18] vfio: add pcie extanded capability support

[Alex Williamson <alex.williamson@redhat.com>]

On Tue, 2015-06-09 at 11:37 +0800, Chen Fan wrote:
> For vfio pcie device, we could expose the extended capability on
> PCIE bus. in order to avoid config space broken, we introduce
> a copy config for parsing extended caps. and rebuild the pcie
> extended config space.
> 
> Signed-off-by: Chen Fan <chen.fan.fnst@cn.fujitsu.com>
> ---
>  hw/vfio/pci.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 72 insertions(+), 1 deletion(-)
> 
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 52e8ad4..54303d9 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -2494,6 +2494,21 @@ static uint8_t vfio_std_cap_max_size(PCIDevice *pdev, uint8_t pos)
>      return next - pos;
>  }
>  
> +
> +static uint16_t vfio_ext_cap_max_size(const uint8_t *config, uint16_t pos)
> +{
> +    uint16_t tmp, next = PCIE_CONFIG_SPACE_SIZE;
> +
> +    for (tmp = PCI_CONFIG_SPACE_SIZE; tmp;
> +        tmp = PCI_EXT_CAP_NEXT(pci_get_long(config + tmp))) {
> +        if (tmp > pos && tmp < next) {
> +            next = tmp;
> +        }
> +    }
> +
> +    return next - pos;
> +}
> +
>  static void vfio_set_word_bits(uint8_t *buf, uint16_t val, uint16_t mask)
>  {
>      pci_set_word(buf, (pci_get_word(buf) & ~mask) | val);
> @@ -2804,16 +2819,72 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos)
>      return 0;
>  }
>  
> +static int vfio_add_ext_cap(VFIOPCIDevice *vdev, const uint8_t *config)
> +{
> +    PCIDevice *pdev = &vdev->pdev;
> +    uint32_t header;
> +    uint16_t cap_id, next, size;
> +    uint8_t cap_ver;
> +
> +    for (next = PCI_CONFIG_SPACE_SIZE; next;
> +         next = PCI_EXT_CAP_NEXT(pci_get_long(config + next))) {
> +        header = pci_get_long(config + next);
> +        cap_id = PCI_EXT_CAP_ID(header);
> +        cap_ver = PCI_EXT_CAP_VER(header);
> +
> +        /*
> +         * If it becomes important to configure extended capabilities to their
> +         * actual size, use this as the default when it's something we don't
> +         * recognize. Since QEMU doesn't actually handle many of the config
> +         * accesses, exact size doesn't seem worthwhile.
> +         */
> +        size = vfio_ext_cap_max_size(config, next);
> +
> +        pcie_add_capability(pdev, cap_id, cap_ver, next, size);
> +        if (next == PCI_CONFIG_SPACE_SIZE) {
> +            /* Begin the rebuild, we should set the next offset zero. */
> +            pci_set_long(pdev->config + next, PCI_EXT_CAP(cap_id, cap_ver, 0));
> +        }
> +
> +        /* Use emulated header pointer to allow dropping extended caps */
> +        pci_set_long(vdev->emulated_config_bits + next, 0xffffffff);
> +    }
> +
> +    return 0;
> +}
> +
>  static int vfio_add_capabilities(VFIOPCIDevice *vdev)
>  {
>      PCIDevice *pdev = &vdev->pdev;
> +    int ret;
> +    uint8_t *config;
>  
>      if (!(pdev->config[PCI_STATUS] & PCI_STATUS_CAP_LIST) ||
>          !pdev->config[PCI_CAPABILITY_LIST]) {
>          return 0; /* Nothing to add */
>      }
>  
> -    return vfio_add_std_cap(vdev, pdev->config[PCI_CAPABILITY_LIST]);
> +    ret = vfio_add_std_cap(vdev, pdev->config[PCI_CAPABILITY_LIST]);
> +    if (ret) {
> +        return ret;
> +    }
> +
> +    /* on PCI bus, it doesn't make sense to expose extended capabilities. */
> +    if (!pci_is_express(pdev) ||
> +        !pci_bus_is_express(pdev->bus) ||
> +        !pci_get_long(pdev->config + PCI_CONFIG_SPACE_SIZE)) {
> +        return 0;
> +    }
> +
> +    /*
> +     * In order to avoid breaking config space, create a copy to
> +     * use for parsing extended capabilities.
> +     */
> +    config = g_memdup(pdev->config, vdev->config_size);
> +    ret = vfio_add_ext_cap(vdev, config);
> +
> +    g_free(config);


nit: it probably makes sense to move this memdup/free inside
vfio_add_ext_cap().  It's an implementation detail that doesn't need to
be exposed outside the function.  This might be a left-over from a
version where the function was recursive.

> +    return ret;
>  }
>  
>  static void vfio_pci_pre_reset(VFIOPCIDevice *vdev)