pcie_sriov: Allow user to create SR-IOV device

A user can create a SR-IOV device by specifying the PF with the
sriov-pf property of the VFs. The VFs must be added before the PF.

A user-creatable VF must have PCIDeviceClass::sriov_vf_user_creatable
set. Such a VF cannot refer to the PF because it is created before the
PF.

A PF that user-creatable VFs can be attached calls
pcie_sriov_pf_init_from_user_created_vfs() during realization and
pcie_sriov_pf_exit() when exiting.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20240715-sriov-v5-5-3f5539093ffc@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 38 insertions, 24 deletions

diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index cf27948..8ad5d7e 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -85,6 +85,7 @@ static Property pci_props[] = {
                     QEMU_PCIE_ERR_UNC_MASK_BITNR, true),
     DEFINE_PROP_BIT("x-pcie-ari-nextfn-1", PCIDevice, cap_present,
                     QEMU_PCIE_ARI_NEXTFN_1_BITNR, false),
+    DEFINE_PROP_STRING("sriov-pf", PCIDevice, sriov_pf),
     DEFINE_PROP_END_OF_LIST()
 };
 
@@ -959,13 +960,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp)
         dev->config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
     }
 
-    /*
-     * With SR/IOV and ARI, a device at function 0 need not be a multifunction
-     * device, as it may just be a VF that ended up with function 0 in
-     * the legacy PCI interpretation. Avoid failing in such cases:
-     */
-    if (pci_is_vf(dev) &&
-        dev->exp.sriov_vf.pf->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
+    /* SR/IOV is not handled here. */
+    if (pci_is_vf(dev)) {
         return;
     }
 
@@ -998,7 +994,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp)
     }
     /* function 0 indicates single function, so function > 0 must be NULL */
     for (func = 1; func < PCI_FUNC_MAX; ++func) {
-        if (bus->devices[PCI_DEVFN(slot, func)]) {
+        PCIDevice *device = bus->devices[PCI_DEVFN(slot, func)];
+        if (device && !pci_is_vf(device)) {
             error_setg(errp, "PCI: %x.0 indicates single function, "
                        "but %x.%x is already populated.",
                        slot, slot, func);
@@ -1283,6 +1280,7 @@ static void pci_qdev_unrealize(DeviceState *dev)
 
     pci_unregister_io_regions(pci_dev);
     pci_del_option_rom(pci_dev);
+    pcie_sriov_unregister_device(pci_dev);
 
     if (pc->exit) {
         pc->exit(pci_dev);
@@ -1314,7 +1312,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
     pcibus_t size = memory_region_size(memory);
     uint8_t hdr_type;
 
-    assert(!pci_is_vf(pci_dev)); /* VFs must use pcie_sriov_vf_register_bar */
     assert(region_num >= 0);
     assert(region_num < PCI_NUM_REGIONS);
     assert(is_power_of_2(size));
@@ -1325,7 +1322,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
     assert(hdr_type != PCI_HEADER_TYPE_BRIDGE || region_num < 2);
 
     r = &pci_dev->io_regions[region_num];
-    r->addr = PCI_BAR_UNMAPPED;
     r->size = size;
     r->type = type;
     r->memory = memory;
@@ -1333,22 +1329,35 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num,
                         ? pci_get_bus(pci_dev)->address_space_io
                         : pci_get_bus(pci_dev)->address_space_mem;
 
-    wmask = ~(size - 1);
-    if (region_num == PCI_ROM_SLOT) {
-        /* ROM enable bit is writable */
-        wmask |= PCI_ROM_ADDRESS_ENABLE;
-    }
-
-    addr = pci_bar(pci_dev, region_num);
-    pci_set_long(pci_dev->config + addr, type);
+    if (pci_is_vf(pci_dev)) {
+        PCIDevice *pf = pci_dev->exp.sriov_vf.pf;
+        assert(!pf || type == pf->exp.sriov_pf.vf_bar_type[region_num]);
 
-    if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) &&
-        r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
-        pci_set_quad(pci_dev->wmask + addr, wmask);
-        pci_set_quad(pci_dev->cmask + addr, ~0ULL);
+        r->addr = pci_bar_address(pci_dev, region_num, r->type, r->size);
+        if (r->addr != PCI_BAR_UNMAPPED) {
+            memory_region_add_subregion_overlap(r->address_space,
+                                                r->addr, r->memory, 1);
+        }
     } else {
-        pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff);
-        pci_set_long(pci_dev->cmask + addr, 0xffffffff);
+        r->addr = PCI_BAR_UNMAPPED;
+
+        wmask = ~(size - 1);
+        if (region_num == PCI_ROM_SLOT) {
+            /* ROM enable bit is writable */
+            wmask |= PCI_ROM_ADDRESS_ENABLE;
+        }
+
+        addr = pci_bar(pci_dev, region_num);
+        pci_set_long(pci_dev->config + addr, type);
+
+        if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) &&
+            r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+            pci_set_quad(pci_dev->wmask + addr, wmask);
+            pci_set_quad(pci_dev->cmask + addr, ~0ULL);
+        } else {
+            pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff);
+            pci_set_long(pci_dev->cmask + addr, 0xffffffff);
+        }
     }
 }
 
@@ -2109,6 +2118,11 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
         }
     }
 
+    if (!pcie_sriov_register_device(pci_dev, errp)) {
+        pci_qdev_unrealize(DEVICE(pci_dev));
+        return;
+    }
+
     /*
      * A PCIe Downstream Port that do not have ARI Forwarding enabled must
      * associate only Device 0 with the device attached to the bus