Hi Eric,
Not sure about your preference. I've modified my patch as below, which
HostIOMMUContext to provide callbacks for vIOMMU to call into VFIO.
Please feel free to give your suggestions.
https://patchwork.ozlabs.org/patch/1259665/
Regards,
Yi Liu
> From: Eric Auger <eric.auger@redhat.com>
> Sent: Saturday, March 21, 2020 12:58 AM
> To: eric.auger.pro@gmail.com; eric.auger@redhat.com; qemu-devel@nongnu.org;
> Subject: [RFC v6 08/24] pci: introduce PCIPASIDOps to PCIDevice
>
> From: Liu Yi L <yi.l.liu@intel.com>
>
> This patch introduces PCIPASIDOps for IOMMU related operations.
>
> https://lists.gnu.org/archive/html/qemu-devel/2018-03/msg00078.html
> https://lists.gnu.org/archive/html/qemu-devel/2018-03/msg00940.html
>
> So far, to setup virt-SVA for assigned SVA capable device, needs to
> configure host translation structures for specific pasid. (e.g. bind
> guest page table to host and enable nested translation in host).
> Besides, vIOMMU emulator needs to forward guest's cache invalidation
> to host since host nested translation is enabled. e.g. on VT-d, guest
> owns 1st level translation table, thus cache invalidation for 1st
> level should be propagated to host.
>
> This patch adds two functions: alloc_pasid and free_pasid to support
> guest pasid allocation and free. The implementations of the callbacks
> would be device passthru modules. Like vfio.
>
> Cc: Kevin Tian <kevin.tian@intel.com>
> Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Cc: Peter Xu <peterx@redhat.com>
> Cc: Eric Auger <eric.auger@redhat.com>
> Cc: Yi Sun <yi.y.sun@linux.intel.com>
> Cc: David Gibson <david@gibson.dropbear.id.au>
> Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
> Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
> ---
> hw/pci/pci.c | 34 ++++++++++++++++++++++++++++++++++
> include/hw/pci/pci.h | 11 +++++++++++
> 2 files changed, 45 insertions(+)
>
> diff --git a/hw/pci/pci.c b/hw/pci/pci.c
> index e1ed6677e1..67e03b8db1 100644
> --- a/hw/pci/pci.c
> +++ b/hw/pci/pci.c
> @@ -2695,6 +2695,40 @@ void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn,
> void *opaque)
> bus->iommu_opaque = opaque;
> }
>
> +void pci_setup_pasid_ops(PCIDevice *dev, PCIPASIDOps *ops)
> +{
> + assert(ops && !dev->pasid_ops);
> + dev->pasid_ops = ops;
> +}
> +
> +bool pci_device_is_pasid_ops_set(PCIBus *bus, int32_t devfn)
> +{
> + PCIDevice *dev;
> +
> + if (!bus) {
> + return false;
> + }
> +
> + dev = bus->devices[devfn];
> + return !!(dev && dev->pasid_ops);
> +}
> +
> +int pci_device_set_pasid_table(PCIBus *bus, int32_t devfn,
> + IOMMUConfig *config)
> +{
> + PCIDevice *dev;
> +
> + if (!bus) {
> + return -EINVAL;
> + }
> +
> + dev = bus->devices[devfn];
> + if (dev && dev->pasid_ops && dev->pasid_ops->set_pasid_table) {
> + return dev->pasid_ops->set_pasid_table(bus, devfn, config);
> + }
> + return -ENOENT;
> +}
> +
> static void pci_dev_get_w64(PCIBus *b, PCIDevice *dev, void *opaque)
> {
> Range *range = opaque;
> diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
> index cfedf5a995..2146cb7519 100644
> --- a/include/hw/pci/pci.h
> +++ b/include/hw/pci/pci.h
> @@ -8,6 +8,7 @@
> #include "hw/isa/isa.h"
>
> #include "hw/pci/pcie.h"
> +#include "hw/iommu/iommu.h"
>
> extern bool pci_available;
>
> @@ -264,6 +265,11 @@ struct PCIReqIDCache {
> };
> typedef struct PCIReqIDCache PCIReqIDCache;
>
> +struct PCIPASIDOps {
> + int (*set_pasid_table)(PCIBus *bus, int32_t devfn, IOMMUConfig *config);
> +};
> +typedef struct PCIPASIDOps PCIPASIDOps;
> +
> struct PCIDevice {
> DeviceState qdev;
> bool partially_hotplugged;
> @@ -357,6 +363,7 @@ struct PCIDevice {
>
> /* ID of standby device in net_failover pair */
> char *failover_pair_id;
> + PCIPASIDOps *pasid_ops;
> };
>
> void pci_register_bar(PCIDevice *pci_dev, int region_num,
> @@ -490,6 +497,10 @@ typedef AddressSpace *(*PCIIOMMUFunc)(PCIBus *, void
> *, int);
> AddressSpace *pci_device_iommu_address_space(PCIDevice *dev);
> void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn, void *opaque);
>
> +void pci_setup_pasid_ops(PCIDevice *dev, PCIPASIDOps *ops);
> +bool pci_device_is_pasid_ops_set(PCIBus *bus, int32_t devfn);
> +int pci_device_set_pasid_table(PCIBus *bus, int32_t devfn, IOMMUConfig *config);
> +
> static inline void
> pci_set_byte(uint8_t *config, uint8_t val)
> {
> --
> 2.20.1