Re: [PATCH v2 2/2] pci: allow slot_reserved_mask to be ignored with manual slot assignment

["Michael S. Tsirkin" <mst@redhat.com>]

On Tue, Mar 14, 2023 at 12:43:12PM +0000, Mark Cave-Ayland wrote:
> On 14/03/2023 06:33, Michael S. Tsirkin wrote:
> 
> > On Tue, Mar 14, 2023 at 12:01:09AM -0400, Chuck Zmudzinski wrote:
> > > Commit 4f67543bb8c5 ("xen/pt: reserve PCI slot 2 for Intel igd-passthru")
> > > uses slot_reserved_mask to reserve slot 2 for the Intel IGD for the
> > > xenfv machine when the guest is configured for igd-passthru.
> > > 
> > > A desired extension to that commit is to allow use of the reserved slot
> > > if the administrator manually configures a device to use the reserved
> > > slot. Currently, slot_reserved_mask is enforced unconditionally. With
> > > this patch, the pci bus can be configured so the slot is only reserved
> > > if the pci device to be added to the bus is configured for automatic
> > > slot assignment.
> > > 
> > > To enable the desired behavior of slot_reserved_mask machine, add a
> > > boolean member enforce_slot_reserved_mask_manual to struct PCIBus and
> > > add a function pci_bus_ignore_slot_reserved_mask_manual which can be
> > > called to change the default behavior of always enforcing
> > > slot_reserved_mask so, in that case, slot_reserved_mask is only enforced
> > > when the pci device being added is configured for automatic slot
> > > assignment.
> > > 
> > > Call the new pci_bus_ignore_slot_reserved_mask_manual function after
> > > creating the pci bus for the pc/i440fx/xenfv machine type to implement
> > > the desired behavior of causing slot_reserved_mask to only apply when
> > > the pci device to be added to a pc/i440fx/xenfv machine is configured
> > > for automatic slot assignment.
> > > 
> > > Link: https://lore.kernel.org/qemu-devel/20230106064838-mutt-send-email-mst@kernel.org/
> > > Signed-off-by: Chuck Zmudzinski <brchuckz@aol.com>
> > 
> > I really dislike this.
> > It seems that xen should not have used slot_reserved_mask,
> > and instead needs something new like slot_manual_mask.
> > No?
> 
> My suggestion was to move the validation logic to a separate callback
> function in PCIBus (see
> https://lists.gnu.org/archive/html/qemu-devel/2023-03/msg03988.html) but
> perhaps I wasn't clear enough in pointing out that I was thinking this could
> *replace* the existing slot_reserved_mask mechanism, rather than providing a
> hook to allow it to be manipulated.
> 
> Here's a very rough patch put together over lunch that attempts this for
> pci_bus_devfn_reserved(): the idea is that sun4u and Xen would call
> pci_bus_set_slot_reserved_fn() with a suitable pci_slot_reserved_fn
> implementation, and slot_reserved_mask gets removed completely i.e.:
> 
> 
> diff --git a/hw/pci/pci.c b/hw/pci/pci.c
> index def5000e7b..30b856499a 100644
> --- a/hw/pci/pci.c
> +++ b/hw/pci/pci.c
> @@ -493,6 +493,13 @@ bool pci_bus_bypass_iommu(PCIBus *bus)
>      return host_bridge->bypass_iommu;
>  }
> 
> +static bool pci_bus_default_slot_reserved(PCISlotReservationType restype,
> +                                          int devfn)
> +{
> +    /* All slots accessible by default */
> +    return false;
> +}
> +
>  static void pci_root_bus_internal_init(PCIBus *bus, DeviceState *parent,
>                                         MemoryRegion *address_space_mem,
>                                         MemoryRegion *address_space_io,
> @@ -500,7 +507,7 @@ static void pci_root_bus_internal_init(PCIBus *bus,
> DeviceState *parent,
>  {
>      assert(PCI_FUNC(devfn_min) == 0);
>      bus->devfn_min = devfn_min;
> -    bus->slot_reserved_mask = 0x0;
> +    bus->slot_reserved_fn = pci_bus_default_slot_reserved;
>      bus->address_space_mem = address_space_mem;
>      bus->address_space_io = address_space_io;
>      bus->flags |= PCI_BUS_IS_ROOT;
> @@ -1111,9 +1118,15 @@ static bool pci_bus_devfn_available(PCIBus *bus, int devfn)
>      return !(bus->devices[devfn]);
>  }
> 
> -static bool pci_bus_devfn_reserved(PCIBus *bus, int devfn)
> +static bool pci_bus_devfn_reserved(PCIBus *bus, int devfn,
> +                                   PCISlotReservationType restype)
> +{
> +    return bus->slot_reserved_fn(restype, devfn);
> +}
> +
> +void pci_bus_set_slot_reserved_fn(PCIBus *bus, pci_slot_reserved_fn fn)
>  {
> -    return bus->slot_reserved_mask & (1UL << PCI_SLOT(devfn));
> +    bus->slot_reserved_fn = fn;
>  }
> 
>  /* -1 for devfn means auto assign */
> @@ -1141,7 +1154,7 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev,
>          for(devfn = bus->devfn_min ; devfn < ARRAY_SIZE(bus->devices);
>              devfn += PCI_FUNC_MAX) {
>              if (pci_bus_devfn_available(bus, devfn) &&
> -                   !pci_bus_devfn_reserved(bus, devfn)) {
> +                   !pci_bus_devfn_reserved(bus, devfn, PCI_SLOT_RESERVATION_AUTO)) {
>                  goto found;
>              }
>          }
> @@ -1149,7 +1162,7 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev,
>                     "or reserved", name);
>          return NULL;
>      found: ;
> -    } else if (pci_bus_devfn_reserved(bus, devfn)) {
> +    } else if (pci_bus_devfn_reserved(bus, devfn, PCI_SLOT_RESERVATION_MANUAL)) {
>          error_setg(errp, "PCI: slot %d function %d not available for %s,"
>                                         MemoryRegion *address_space_io,
> @@ -500,7 +507,7 @@ static void pci_root_bus_internal_init(PCIBus *bus,
> DeviceState *parent,
>  {
>      assert(PCI_FUNC(devfn_min) == 0);
>      bus->devfn_min = devfn_min;
> -    bus->slot_reserved_mask = 0x0;
> +    bus->slot_reserved_fn = pci_bus_default_slot_reserved;
>      bus->address_space_mem = address_space_mem;
>      bus->address_space_io = address_space_io;
>      bus->flags |= PCI_BUS_IS_ROOT;
> @@ -1111,9 +1118,15 @@ static bool pci_bus_devfn_available(PCIBus *bus, int devfn)
>      return !(bus->devices[devfn]);
>  }
> 
> -static bool pci_bus_devfn_reserved(PCIBus *bus, int devfn)
> +static bool pci_bus_devfn_reserved(PCIBus *bus, int devfn,
> +                                   PCISlotReservationType restype)
> +{
> +    return bus->slot_reserved_fn(restype, devfn);
> +}
> +
> +void pci_bus_set_slot_reserved_fn(PCIBus *bus, pci_slot_reserved_fn fn)
>  {
> -    return bus->slot_reserved_mask & (1UL << PCI_SLOT(devfn));
> +    bus->slot_reserved_fn = fn;
>  }
> 
>  /* -1 for devfn means auto assign */
> @@ -1141,7 +1154,7 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev,
>          for(devfn = bus->devfn_min ; devfn < ARRAY_SIZE(bus->devices);
>              devfn += PCI_FUNC_MAX) {
>              if (pci_bus_devfn_available(bus, devfn) &&
> -                   !pci_bus_devfn_reserved(bus, devfn)) {
> +                   !pci_bus_devfn_reserved(bus, devfn, PCI_SLOT_RESERVATION_AUTO)) {
>                  goto found;
>              }
>          }
> @@ -1149,7 +1162,7 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev,
>                     "or reserved", name);
>          return NULL;
>      found: ;
> -    } else if (pci_bus_devfn_reserved(bus, devfn)) {
> +    } else if (pci_bus_devfn_reserved(bus, devfn, PCI_SLOT_RESERVATION_MANUAL)) {
>          error_setg(errp, "PCI: slot %d function %d not available for %s,"
>                     " reserved",
>                     PCI_SLOT(devfn), PCI_FUNC(devfn), name);
> diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
> index d5a40cd058..8a949f7ae1 100644
> --- a/include/hw/pci/pci.h
> +++ b/include/hw/pci/pci.h
> @@ -257,10 +257,18 @@ MemoryRegion *pci_address_space_io(PCIDevice *dev);
>   */
>  int pci_bar(PCIDevice *d, int reg);
> 
> +typedef enum PCISlotReservationType {
> +    PCI_SLOT_RESERVATION_AUTO,
> +    PCI_SLOT_RESERVATION_MANUAL
> +} PCISlotReservationType;
> +
> +typedef bool (*pci_slot_reserved_fn)(PCISlotReservationType restype, int devfn);
>  typedef void (*pci_set_irq_fn)(void *opaque, int irq_num, int level);
>  typedef int (*pci_map_irq_fn)(PCIDevice *pci_dev, int irq_num);
>  typedef PCIINTxRoute (*pci_route_irq_fn)(void *opaque, int pin);
> 
> +void pci_bus_set_slot_reserved_fn(PCIBus *bus, pci_slot_reserved_fn fn);
> +
>  #define TYPE_PCI_BUS "PCI"
>  OBJECT_DECLARE_TYPE(PCIBus, PCIBusClass, PCI_BUS)
>  #define TYPE_PCIE_BUS "PCIE"
> diff --git a/include/hw/pci/pci_bus.h b/include/hw/pci/pci_bus.h
> index 5653175957..d68ea1418d 100644
> --- a/include/hw/pci/pci_bus.h
> +++ b/include/hw/pci/pci_bus.h
> @@ -36,7 +36,7 @@ struct PCIBus {
>      PCIIOMMUFunc iommu_fn;
>      void *iommu_opaque;
>      uint8_t devfn_min;
> -    uint32_t slot_reserved_mask;
> +    pci_slot_reserved_fn slot_reserved_fn;
>      pci_set_irq_fn set_irq;
>      pci_map_irq_fn map_irq;
>      pci_route_irq_fn route_intx_to_irq;
> 
> 
> If this approach seems reasonable, I'm happy for someone else to take this
> over and turn it into a proper series.
> 
> 
> ATB,
> 
> Mark.

It's ok too though I think I like chuck's proposal better:
less callbacks to chase.

-- 
MST