[v6,11/13] vpci: add initial support for virtual PCI bus topology

Commit Message

Oleksandr Andrushchenko Feb. 4, 2022, 6:34 a.m. UTC

From: Oleksandr Andrushchenko <[e-mail]>

Assign SBDF to the PCI devices being passed through with bus 0.
The resulting topology is where PCIe devices reside on the bus 0 of the
root complex itself (embedded endpoints).
This implementation is limited to 32 devices which are allowed on
a single PCI bus.

Please note, that at the moment only function 0 of a multifunction
device can be passed through.

Signed-off-by: Oleksandr Andrushchenko <[e-mail]>
---
Since v5:
- s/vpci_add_virtual_device/add_virtual_device and make it static
- call add_virtual_device from vpci_assign_device and do not use
  REGISTER_VPCI_INIT machinery
- add pcidevs_locked ASSERT
- use DECLARE_BITMAP for vpci_dev_assigned_map
Since v4:
- moved and re-worked guest sbdf initializers
- s/set_bit/__set_bit
- s/clear_bit/__clear_bit
- minor comment fix s/Virtual/Guest/
- added VPCI_MAX_VIRT_DEV constant (PCI_SLOT(~0) + 1) which will be used
  later for counting the number of MMIO handlers required for a guest
  (Julien)
Since v3:
 - make use of VPCI_INIT
 - moved all new code to vpci.c which belongs to it
 - changed open-coded 31 to PCI_SLOT(~0)
 - added comments and code to reject multifunction devices with
   functions other than 0
 - updated comment about vpci_dev_next and made it unsigned int
 - implement roll back in case of error while assigning/deassigning devices
 - s/dom%pd/%pd
Since v2:
 - remove casts that are (a) malformed and (b) unnecessary
 - add new line for better readability
 - remove CONFIG_HAS_VPCI_GUEST_SUPPORT ifdef's as the relevant vPCI
    functions are now completely gated with this config
 - gate common code with CONFIG_HAS_VPCI_GUEST_SUPPORT
New in v2
---
 xen/drivers/vpci/vpci.c | 74 +++++++++++++++++++++++++++++++++++++++--
 xen/include/xen/sched.h |  8 +++++
 xen/include/xen/vpci.h  | 11 ++++++
 3 files changed, 91 insertions(+), 2 deletions(-)

Patch

diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
index 3177f13c1c22..7d422d11f83d 100644
--- a/xen/drivers/vpci/vpci.c
+++ b/xen/drivers/vpci/vpci.c
@@ -89,6 +89,9 @@  int vpci_add_handlers(struct pci_dev *pdev)
         return -ENOMEM;
 
     INIT_LIST_HEAD(&vpci->handlers);
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+    vpci->guest_sbdf.sbdf = ~0;
+#endif
 
     spin_lock(&pdev->vpci_lock);
     pdev->vpci = vpci;
@@ -114,6 +117,57 @@  int vpci_add_handlers(struct pci_dev *pdev)
 }
 
 #ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+static int add_virtual_device(struct pci_dev *pdev)
+{
+    struct domain *d = pdev->domain;
+    pci_sbdf_t sbdf = { 0 };
+    unsigned long new_dev_number;
+
+    if ( is_hardware_domain(d) )
+        return 0;
+
+    ASSERT(pcidevs_locked());
+
+    /*
+     * Each PCI bus supports 32 devices/slots at max or up to 256 when
+     * there are multi-function ones which are not yet supported.
+     */
+    if ( pdev->info.is_extfn )
+    {
+        gdprintk(XENLOG_ERR, "%pp: only function 0 passthrough supported\n",
+                 &pdev->sbdf);
+        return -EOPNOTSUPP;
+    }
+
+    new_dev_number = find_first_zero_bit(d->vpci_dev_assigned_map,
+                                         VPCI_MAX_VIRT_DEV);
+    if ( new_dev_number >= VPCI_MAX_VIRT_DEV )
+        return -ENOSPC;
+
+    __set_bit(new_dev_number, &d->vpci_dev_assigned_map);
+
+    /*
+     * Both segment and bus number are 0:
+     *  - we emulate a single host bridge for the guest, e.g. segment 0
+     *  - with bus 0 the virtual devices are seen as embedded
+     *    endpoints behind the root complex
+     *
+     * TODO: add support for multi-function devices.
+     */
+    sbdf.devfn = PCI_DEVFN(new_dev_number, 0);
+    pdev->vpci->guest_sbdf = sbdf;
+
+    return 0;
+
+}
+
+static void vpci_remove_virtual_device(struct domain *d,
+                                       const struct pci_dev *pdev)
+{
+    __clear_bit(pdev->vpci->guest_sbdf.dev, &d->vpci_dev_assigned_map);
+    pdev->vpci->guest_sbdf.sbdf = ~0;
+}
+
 /* Notify vPCI that device is assigned to guest. */
 int vpci_assign_device(struct domain *d, struct pci_dev *pdev)
 {
@@ -124,8 +178,16 @@  int vpci_assign_device(struct domain *d, struct pci_dev *pdev)
 
     rc = vpci_add_handlers(pdev);
     if ( rc )
-        vpci_deassign_device(d, pdev);
+        goto fail;
+
+    rc = add_virtual_device(pdev);
+    if ( rc )
+        goto fail;
 
+    return 0;
+
+ fail:
+    vpci_deassign_device(d, pdev);
     return rc;
 }
 
@@ -135,7 +197,15 @@  void vpci_deassign_device(struct domain *d, struct pci_dev *pdev)
     if ( !has_vpci(d) )
         return;
 
-    vpci_remove_device(pdev);
+    spin_lock(&pdev->vpci_lock);
+    if ( !pdev->vpci )
+        goto done;
+
+    vpci_remove_virtual_device(d, pdev);
+    vpci_remove_device_locked(pdev);
+
+ done:
+    spin_unlock(&pdev->vpci_lock);
 }
 #endif /* CONFIG_HAS_VPCI_GUEST_SUPPORT */
 
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 37f78cc4c4c9..3c25e265eaa8 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -444,6 +444,14 @@  struct domain
 
 #ifdef CONFIG_HAS_PCI
     struct list_head pdev_list;
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+    /*
+     * The bitmap which shows which device numbers are already used by the
+     * virtual PCI bus topology and is used to assign a unique SBDF to the
+     * next passed through virtual PCI device.
+     */
+    DECLARE_BITMAP(vpci_dev_assigned_map, VPCI_MAX_VIRT_DEV);
+#endif
 #endif
 
 #ifdef CONFIG_HAS_PASSTHROUGH
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index f1f49db959c7..1f04d34a2369 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -21,6 +21,13 @@  typedef int vpci_register_init_t(struct pci_dev *dev);
 
 #define VPCI_ECAM_BDF(addr)     (((addr) & 0x0ffff000) >> 12)
 
+/*
+ * Maximum number of devices supported by the virtual bus topology:
+ * each PCI bus supports 32 devices/slots at max or up to 256 when
+ * there are multi-function ones which are not yet supported.
+ */
+#define VPCI_MAX_VIRT_DEV       (PCI_SLOT(~0) + 1)
+
 #define REGISTER_VPCI_INIT(x, p)                \
   static vpci_register_init_t *const x##_entry  \
                __used_section(".data.vpci." p) = x
@@ -140,6 +147,10 @@  struct vpci {
             struct vpci_arch_msix_entry arch;
         } entries[];
     } *msix;
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+    /* Guest SBDF of the device. */
+    pci_sbdf_t guest_sbdf;
+#endif
 #endif
 };