enable multi-function hot-add

Enable PCIe device multi-function hot-add, just ensure function 0 is added
last, then driver will get the notification to scan the slot.

Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

4 files changed, 64 insertions, 10 deletions

diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index b0bf54061f..168b9cc56b 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -847,6 +847,9 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
     PCIConfigWriteFunc *config_write = pc->config_write;
     Error *local_err = NULL;
     AddressSpace *dma_as;
+    DeviceState *dev = DEVICE(pci_dev);
+
+    pci_dev->bus = bus;
 
     if (devfn < 0) {
         for(devfn = bus->devfn_min ; devfn < ARRAY_SIZE(bus->devices);
@@ -864,9 +867,17 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
                    PCI_SLOT(devfn), PCI_FUNC(devfn), name,
                    bus->devices[devfn]->name);
         return NULL;
+    } else if (dev->hotplugged &&
+               pci_get_function_0(pci_dev)) {
+        error_setg(errp, "PCI: slot %d function 0 already ocuppied by %s,"
+                   " new func %s cannot be exposed to guest.",
+                   PCI_SLOT(devfn),
+                   bus->devices[PCI_DEVFN(PCI_SLOT(devfn), 0)]->name,
+                   name);
+
+       return NULL;
     }
 
-    pci_dev->bus = bus;
     pci_dev->devfn = devfn;
     dma_as = pci_device_iommu_address_space(pci_dev);
 
@@ -2454,6 +2465,33 @@ void pci_bus_get_w64_range(PCIBus *bus, Range *range)
     pci_for_each_device_under_bus(bus, pci_dev_get_w64, range);
 }
 
+static bool pcie_has_upstream_port(PCIDevice *dev)
+{
+    PCIDevice *parent_dev = pci_bridge_get_device(dev->bus);
+
+    /* Device associated with an upstream port.
+     * As there are several types of these, it's easier to check the
+     * parent device: upstream ports are always connected to
+     * root or downstream ports.
+     */
+    return parent_dev &&
+        pci_is_express(parent_dev) &&
+        parent_dev->exp.exp_cap &&
+        (pcie_cap_get_type(parent_dev) == PCI_EXP_TYPE_ROOT_PORT ||
+         pcie_cap_get_type(parent_dev) == PCI_EXP_TYPE_DOWNSTREAM);
+}
+
+PCIDevice *pci_get_function_0(PCIDevice *pci_dev)
+{
+    if(pcie_has_upstream_port(pci_dev)) {
+        /* With an upstream PCIe port, we only support 1 device at slot 0 */
+        return pci_dev->bus->devices[0];
+    } else {
+        /* Other bus types might support multiple devices at slots 0-31 */
+        return pci_dev->bus->devices[PCI_DEVFN(PCI_SLOT(pci_dev->devfn), 0)];
+    }
+}
+
 static const TypeInfo pci_device_type_info = {
     .name = TYPE_PCI_DEVICE,
     .parent = TYPE_DEVICE,
diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c
index 3e26f9256c..49f59a5dbc 100644
--- a/hw/pci/pci_host.c
+++ b/hw/pci/pci_host.c
@@ -20,6 +20,7 @@
 
 #include "hw/pci/pci.h"
 #include "hw/pci/pci_host.h"
+#include "hw/pci/pci_bus.h"
 #include "trace.h"
 
 /* debug PCI */
@@ -52,6 +53,13 @@ void pci_host_config_write_common(PCIDevice *pci_dev, uint32_t addr,
                                   uint32_t limit, uint32_t val, uint32_t len)
 {
     assert(len <= 4);
+    /* non-zero functions are only exposed when function 0 is present,
+     * allowing direct removal of unexposed functions.
+     */
+    if (pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) {
+        return;
+    }
+
     trace_pci_cfg_write(pci_dev->name, PCI_SLOT(pci_dev->devfn),
                         PCI_FUNC(pci_dev->devfn), addr, val);
     pci_dev->config_write(pci_dev, addr, val, MIN(len, limit - addr));
@@ -63,6 +71,13 @@ uint32_t pci_host_config_read_common(PCIDevice *pci_dev, uint32_t addr,
     uint32_t ret;
 
     assert(len <= 4);
+    /* non-zero functions are only exposed when function 0 is present,
+     * allowing direct removal of unexposed functions.
+     */
+    if (pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) {
+        return ~0x0;
+    }
+
     ret = pci_dev->config_read(pci_dev, addr, MIN(len, limit - addr));
     trace_pci_cfg_read(pci_dev->name, PCI_SLOT(pci_dev->devfn),
                        PCI_FUNC(pci_dev->devfn), addr, ret);
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index a72d516e4f..32c65c27a4 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -249,16 +249,16 @@ void pcie_cap_slot_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
         return;
     }
 
-    /* TODO: multifunction hot-plug.
-     * Right now, only a device of function = 0 is allowed to be
-     * hot plugged/unplugged.
+    /* To enable multifunction hot-plug, we just ensure the function
+     * 0 added last. When function 0 is added, we set the sltsta and
+     * inform OS via event notification.
      */
-    assert(PCI_FUNC(pci_dev->devfn) == 0);
-
-    pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
-                               PCI_EXP_SLTSTA_PDS);
-    pcie_cap_slot_event(PCI_DEVICE(hotplug_dev),
-                        PCI_EXP_HP_EV_PDC | PCI_EXP_HP_EV_ABP);
+    if (pci_get_function_0(pci_dev)) {
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
+                                   PCI_EXP_SLTSTA_PDS);
+        pcie_cap_slot_event(PCI_DEVICE(hotplug_dev),
+                            PCI_EXP_HP_EV_PDC | PCI_EXP_HP_EV_ABP);
+    }
 }
 
 static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque)
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index f5e7fd818a..379b6e1a45 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -397,6 +397,7 @@ void pci_for_each_bus_depth_first(PCIBus *bus,
                                   void *(*begin)(PCIBus *bus, void *parent_state),
                                   void (*end)(PCIBus *bus, void *state),
                                   void *parent_state);
+PCIDevice *pci_get_function_0(PCIDevice *pci_dev);
 
 /* Use this wrapper when specific scan order is not required. */
 static inline