[PATCH v15 3/5] vpci: add initial support for virtual PCI bus topology

[Stewart Hildebrand <stewart.hildebrand@xxxxxxx>]

From: Oleksandr Andrushchenko <oleksandr_andrushchenko@xxxxxxxx>

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 <oleksandr_andrushchenko@xxxxxxxx>
Signed-off-by: Volodymyr Babchuk <volodymyr_babchuk@xxxxxxxx>
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@xxxxxxx>
Acked-by: Jan Beulich <jbeulich@xxxxxxxx>
---
In v15:
- add Jan's A-b
In v13:
- s/depends on/select/ in Kconfig
- check pdev->sbdf.fn instead of two booleans in add_virtual_device()
- comment #endifs in sched.h
- clarify comment about limits in vpci.h with seg/bus limit
In v11:
- Fixed code formatting
- Removed bogus write_unlock() call
- Fixed type for new_dev_number
In v10:
- Removed ASSERT(pcidevs_locked())
- Removed redundant code (local sbdf variable, clearing sbdf during
device removal, etc)
- Added __maybe_unused attribute to "out:" label
- Introduced HAS_VPCI_GUEST_SUPPORT Kconfig option, as this is the
  first patch where it is used (previously was in "vpci: add hooks for
  PCI device assign/de-assign")
In v9:
- Lock in add_virtual_device() replaced with ASSERT (thanks, Stewart)
In v8:
- Added write lock in add_virtual_device
Since v6:
- re-work wrt new locking scheme
- OT: add ASSERT(pcidevs_write_locked()); to add_virtual_device()
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/Kconfig     |  4 +++
 xen/drivers/vpci/vpci.c | 57 +++++++++++++++++++++++++++++++++++++++++
 xen/include/xen/sched.h | 10 +++++++-
 xen/include/xen/vpci.h  | 12 +++++++++
 4 files changed, 82 insertions(+), 1 deletion(-)

diff --git a/xen/drivers/Kconfig b/xen/drivers/Kconfig
index db94393f47a6..20050e9bb8b3 100644
--- a/xen/drivers/Kconfig
+++ b/xen/drivers/Kconfig
@@ -15,4 +15,8 @@ source "drivers/video/Kconfig"
 config HAS_VPCI
        bool
 
+config HAS_VPCI_GUEST_SUPPORT
+       bool
+       select HAS_VPCI
+
 endmenu
diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
index 97e115dc5798..23722634d50b 100644
--- a/xen/drivers/vpci/vpci.c
+++ b/xen/drivers/vpci/vpci.c
@@ -40,6 +40,49 @@ extern vpci_register_init_t *const __start_vpci_array[];
 extern vpci_register_init_t *const __end_vpci_array[];
 #define NUM_VPCI_INIT (__end_vpci_array - __start_vpci_array)
 
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+static int add_virtual_device(struct pci_dev *pdev)
+{
+    struct domain *d = pdev->domain;
+    unsigned int new_dev_number;
+
+    if ( is_hardware_domain(d) )
+        return 0;
+
+    ASSERT(rw_is_write_locked(&pdev->domain->pci_lock));
+
+    /*
+     * 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->sbdf.fn )
+    {
+        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.
+     */
+    pdev->vpci->guest_sbdf = PCI_SBDF(0, 0, new_dev_number, 0);
+
+    return 0;
+}
+
+#endif /* CONFIG_HAS_VPCI_GUEST_SUPPORT */
+
 void vpci_deassign_device(struct pci_dev *pdev)
 {
     unsigned int i;
@@ -49,6 +92,12 @@ void vpci_deassign_device(struct pci_dev *pdev)
     if ( !has_vpci(pdev->domain) || !pdev->vpci )
         return;
 
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+    if ( pdev->vpci->guest_sbdf.sbdf != ~0 )
+        __clear_bit(pdev->vpci->guest_sbdf.dev,
+                    &pdev->domain->vpci_dev_assigned_map);
+#endif
+
     spin_lock(&pdev->vpci->lock);
     while ( !list_empty(&pdev->vpci->handlers) )
     {
@@ -103,6 +152,13 @@ int vpci_assign_device(struct pci_dev *pdev)
     INIT_LIST_HEAD(&pdev->vpci->handlers);
     spin_lock_init(&pdev->vpci->lock);
 
+#ifdef CONFIG_HAS_VPCI_GUEST_SUPPORT
+    pdev->vpci->guest_sbdf.sbdf = ~0;
+    rc = add_virtual_device(pdev);
+    if ( rc )
+        goto out;
+#endif
+
     for ( i = 0; i < NUM_VPCI_INIT; i++ )
     {
         rc = __start_vpci_array[i](pdev);
@@ -110,6 +166,7 @@ int vpci_assign_device(struct pci_dev *pdev)
             break;
     }
 
+ out: __maybe_unused;
     if ( rc )
         vpci_deassign_device(pdev);
 
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 132b84199598..2dcd1d1a4f8a 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -486,7 +486,15 @@ struct domain
      * 2. pdev->vpci->lock
      */
     rwlock_t pci_lock;
-#endif
+#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 /* CONFIG_HAS_VPCI_GUEST_SUPPORT */
+#endif /* CONFIG_HAS_PCI */
 
 #ifdef CONFIG_HAS_PASSTHROUGH
     struct domain_iommu iommu;
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index 2064d9354f5b..980aded26fc1 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -21,6 +21,14 @@ 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.
+ * This limit implies only segment 0, bus 0 is 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)
@@ -175,6 +183,10 @@ 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
 };
 
-- 
2.45.1