Linux Virtualization - Apr 2018 - [RFC PATCH 1/3] qemu: virtio-bypass should explicitly bind to a passthrough device

On Sun, Apr 01, 2018 at 05:13:08AM -0400, Si-Wei Liu
wrote:
> @@ -896,6 +898,68 @@ void qmp_device_del(const char *id, Error **errp)
>      }
>  }
>  
> +int pci_get_busdevfn_by_id(const char *id, uint16_t *busnr,
> +                           uint16_t *devfn, Error **errp)
> +{
> +    uint16_t busnum = 0, slot = 0, func = 0;
> +    const char *pc, *pd, *pe;
> +    Error *local_err = NULL;
> +    ObjectClass *class;
> +    char value[1024];
> +    BusState *bus;
> +    uint64_t u64;
> +
> +    if (!(pc = strchr(id, ':'))) {
> +        error_setg(errp, "Invalid id: backup=%s, "
> +                   "correct format should be backup="
> +                  
"'<bus-id>:<slot>[.<function>]'", id);
> +        return -1;
> +    }
> +    get_opt_name(value, sizeof(value), id, ':');
> +    if (pc != id + 1) {
> +        bus = qbus_find(value, errp);
> +        if (!bus)
> +            return -1;
> +
> +        class = object_get_class(OBJECT(bus));
> +        if (class != object_class_by_name(TYPE_PCI_BUS) &&
> +            class != object_class_by_name(TYPE_PCIE_BUS)) {
> +            error_setg(errp, "%s is not a device on pci bus",
id);
> +            return -1;
> +        }
> +        busnum = (uint16_t)pci_bus_num(PCI_BUS(bus));
> +    }
pci_bus_num is almost always a bug if not done within
a context of a PCI host, bridge, etc.

In particular this will not DTRT if run before guest assigns bus
numbers.

> +
> +    if (!devfn)
> +        goto out;
> +
> +    pd = strchr(pc, '.');
> +    pe = get_opt_name(value, sizeof(value), pc + 1, '.');
> +    if (pe != pc + 1) {
> +        parse_option_number("slot", value, &u64,
&local_err);
> +        if (local_err) {
> +            error_propagate(errp, local_err);
> +            return -1;
> +        }
> +        slot = (uint16_t)u64;
> +    }
> +    if (pd && *(pd + 1) != '\0') {
> +        parse_option_number("function", pd, &u64,
&local_err);
> +        if (local_err) {
> +            error_propagate(errp, local_err);
> +            return -1;
> +        }
> +        func = (uint16_t)u64;
> +    }
> +
> +out:
> +    if (busnr)
> +        *busnr = busnum;
> +    if (devfn)
> +        *devfn = ((slot & 0x1F) << 3) | (func & 0x7);
> +    return 0;
> +}
> +
>  BlockBackend *blk_by_qdev_id(const char *id, Error **errp)
>  {
>      DeviceState *dev;
> -- 
> 1.8.3.1

On Tue, Apr 3, 2018 at 5:25 AM, Michael S. Tsirkin <mst at redhat.com>
wrote:
> On Sun, Apr 01, 2018 at 05:13:08AM -0400, Si-Wei Liu wrote:
>> @@ -896,6 +898,68 @@ void qmp_device_del(const char *id, Error **errp)
>>      }
>>  }
>>
>> +int pci_get_busdevfn_by_id(const char *id, uint16_t *busnr,
>> +                           uint16_t *devfn, Error **errp)
>> +{
>> +    uint16_t busnum = 0, slot = 0, func = 0;
>> +    const char *pc, *pd, *pe;
>> +    Error *local_err = NULL;
>> +    ObjectClass *class;
>> +    char value[1024];
>> +    BusState *bus;
>> +    uint64_t u64;
>> +
>> +    if (!(pc = strchr(id, ':'))) {
>> +        error_setg(errp, "Invalid id: backup=%s, "
>> +                   "correct format should be backup="
>> +                  
"'<bus-id>:<slot>[.<function>]'", id);
>> +        return -1;
>> +    }
>> +    get_opt_name(value, sizeof(value), id, ':');
>> +    if (pc != id + 1) {
>> +        bus = qbus_find(value, errp);
>> +        if (!bus)
>> +            return -1;
>> +
>> +        class = object_get_class(OBJECT(bus));
>> +        if (class != object_class_by_name(TYPE_PCI_BUS) &&
>> +            class != object_class_by_name(TYPE_PCIE_BUS)) {
>> +            error_setg(errp, "%s is not a device on pci
bus", id);
>> +            return -1;
>> +        }
>> +        busnum = (uint16_t)pci_bus_num(PCI_BUS(bus));
>> +    }
>
> pci_bus_num is almost always a bug if not done within
> a context of a PCI host, bridge, etc.
>
> In particular this will not DTRT if run before guest assigns bus
> numbers.
>
I was seeking means to reserve a specific pci bus slot from drivers,
and update the driver when guest assigns the bus number but it seems
there's no low-hanging fruits. Because of that reason the bus_num is
only obtained until it's really needed (during get_config) and I
assume at that point the pci bus assignment is already done. I know
the current one is not perfect, but we need that information (PCI
bus:slot.func number) to name the guest device correctly.

Regards,
-Siwei
>
>> +
>> +    if (!devfn)
>> +        goto out;
>> +
>> +    pd = strchr(pc, '.');
>> +    pe = get_opt_name(value, sizeof(value), pc + 1, '.');
>> +    if (pe != pc + 1) {
>> +        parse_option_number("slot", value, &u64,
&local_err);
>> +        if (local_err) {
>> +            error_propagate(errp, local_err);
>> +            return -1;
>> +        }
>> +        slot = (uint16_t)u64;
>> +    }
>> +    if (pd && *(pd + 1) != '\0') {
>> +        parse_option_number("function", pd, &u64,
&local_err);
>> +        if (local_err) {
>> +            error_propagate(errp, local_err);
>> +            return -1;
>> +        }
>> +        func = (uint16_t)u64;
>> +    }
>> +
>> +out:
>> +    if (busnr)
>> +        *busnr = busnum;
>> +    if (devfn)
>> +        *devfn = ((slot & 0x1F) << 3) | (func & 0x7);
>> +    return 0;
>> +}
>> +
>>  BlockBackend *blk_by_qdev_id(const char *id, Error **errp)
>>  {
>>      DeviceState *dev;
>> --
>> 1.8.3.1
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: virtio-dev-unsubscribe at lists.oasis-open.org
> For additional commands, e-mail: virtio-dev-help at lists.oasis-open.org
>

On 04/04/2018 10:02, Siwei Liu wrote:
>> pci_bus_num is almost always a bug if not done within
>> a context of a PCI host, bridge, etc.
>>
>> In particular this will not DTRT if run before guest assigns bus
>> numbers.
>>
> I was seeking means to reserve a specific pci bus slot from drivers,
> and update the driver when guest assigns the bus number but it seems
> there's no low-hanging fruits. Because of that reason the bus_num is
> only obtained until it's really needed (during get_config) and I
> assume at that point the pci bus assignment is already done. I know
> the current one is not perfect, but we need that information (PCI
> bus:slot.func number) to name the guest device correctly.
Can you use the -device "id", and look it up as

    devices = container_get(qdev_get_machine(), "/peripheral");
    return object_resolve_path_component(devices, id);

?

Thanks,

Paolo