vfio: add pcie extended capability support

For vfio pcie device, we could expose the extended capability on
PCIE bus. due to add a new pcie capability at the tail of the chain,
in order to avoid config space overwritten, we introduce a copy config
for parsing extended caps. and rebuild the pcie extended config space.

Signed-off-by: Chen Fan <chen.fan.fnst@cn.fujitsu.com>
Tested-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 71 insertions, 1 deletions

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 53b87b76ea..a171056b41 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1502,6 +1502,21 @@ static uint8_t vfio_std_cap_max_size(PCIDevice *pdev, uint8_t pos)
     return next - pos;
 }
 
+
+static uint16_t vfio_ext_cap_max_size(const uint8_t *config, uint16_t pos)
+{
+    uint16_t tmp, next = PCIE_CONFIG_SPACE_SIZE;
+
+    for (tmp = PCI_CONFIG_SPACE_SIZE; tmp;
+        tmp = PCI_EXT_CAP_NEXT(pci_get_long(config + tmp))) {
+        if (tmp > pos && tmp < next) {
+            next = tmp;
+        }
+    }
+
+    return next - pos;
+}
+
 static void vfio_set_word_bits(uint8_t *buf, uint16_t val, uint16_t mask)
 {
     pci_set_word(buf, (pci_get_word(buf) & ~mask) | val);
@@ -1749,16 +1764,71 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos)
     return 0;
 }
 
+static int vfio_add_ext_cap(VFIOPCIDevice *vdev)
+{
+    PCIDevice *pdev = &vdev->pdev;
+    uint32_t header;
+    uint16_t cap_id, next, size;
+    uint8_t cap_ver;
+    uint8_t *config;
+
+    /*
+     * pcie_add_capability always inserts the new capability at the tail
+     * of the chain.  Therefore to end up with a chain that matches the
+     * physical device, we cache the config space to avoid overwriting
+     * the original config space when we parse the extended capabilities.
+     */
+    config = g_memdup(pdev->config, vdev->config_size);
+
+    for (next = PCI_CONFIG_SPACE_SIZE; next;
+         next = PCI_EXT_CAP_NEXT(pci_get_long(config + next))) {
+        header = pci_get_long(config + next);
+        cap_id = PCI_EXT_CAP_ID(header);
+        cap_ver = PCI_EXT_CAP_VER(header);
+
+        /*
+         * If it becomes important to configure extended capabilities to their
+         * actual size, use this as the default when it's something we don't
+         * recognize. Since QEMU doesn't actually handle many of the config
+         * accesses, exact size doesn't seem worthwhile.
+         */
+        size = vfio_ext_cap_max_size(config, next);
+
+        pcie_add_capability(pdev, cap_id, cap_ver, next, size);
+        pci_set_long(pdev->config + next, PCI_EXT_CAP(cap_id, cap_ver, 0));
+
+        /* Use emulated next pointer to allow dropping extended caps */
+        pci_long_test_and_set_mask(vdev->emulated_config_bits + next,
+                                   PCI_EXT_CAP_NEXT_MASK);
+    }
+
+    g_free(config);
+    return 0;
+}
+
 static int vfio_add_capabilities(VFIOPCIDevice *vdev)
 {
     PCIDevice *pdev = &vdev->pdev;
+    int ret;
 
     if (!(pdev->config[PCI_STATUS] & PCI_STATUS_CAP_LIST) ||
         !pdev->config[PCI_CAPABILITY_LIST]) {
         return 0; /* Nothing to add */
     }
 
-    return vfio_add_std_cap(vdev, pdev->config[PCI_CAPABILITY_LIST]);
+    ret = vfio_add_std_cap(vdev, pdev->config[PCI_CAPABILITY_LIST]);
+    if (ret) {
+        return ret;
+    }
+
+    /* on PCI bus, it doesn't make sense to expose extended capabilities. */
+    if (!pci_is_express(pdev) ||
+        !pci_bus_is_express(pdev->bus) ||
+        !pci_get_long(pdev->config + PCI_CONFIG_SPACE_SIZE)) {
+        return 0;
+    }
+
+    return vfio_add_ext_cap(vdev);
 }
 
 static void vfio_pci_pre_reset(VFIOPCIDevice *vdev)