[Xen-devel] [PATCH 1/4] pci: Do not ignore device's PXM information

[Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>]

If ACPI provides PXM data for IO devices then dom0 will pass it to
hypervisor during PHYSDEVOP_pci_device_add call. This information,
however, is currently ignored.

We should remember it (in the form of nodeID). We will also print it
when user requests device information dump.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
---
 xen/arch/x86/physdev.c        | 20 +++++++++++++++++---
 xen/drivers/passthrough/pci.c | 13 +++++++++----
 xen/include/xen/pci.h         |  5 ++++-
 3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/xen/arch/x86/physdev.c b/xen/arch/x86/physdev.c
index 6b3201b..7775f80 100644
--- a/xen/arch/x86/physdev.c
+++ b/xen/arch/x86/physdev.c
@@ -565,7 +565,8 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) 
arg)
         if ( copy_from_guest(&manage_pci, arg, 1) != 0 )
             break;
 
-        ret = pci_add_device(0, manage_pci.bus, manage_pci.devfn, NULL);
+        ret = pci_add_device(0, manage_pci.bus, manage_pci.devfn,
+                             NULL, NUMA_NO_NODE);
         break;
     }
 
@@ -597,13 +598,14 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) 
arg)
         pdev_info.physfn.devfn = manage_pci_ext.physfn.devfn;
         ret = pci_add_device(0, manage_pci_ext.bus,
                              manage_pci_ext.devfn,
-                             &pdev_info);
+                             &pdev_info, NUMA_NO_NODE);
         break;
     }
 
     case PHYSDEVOP_pci_device_add: {
         struct physdev_pci_device_add add;
         struct pci_dev_info pdev_info;
+        int node;
 
         ret = -EFAULT;
         if ( copy_from_guest(&add, arg, 1) != 0 )
@@ -618,7 +620,19 @@ ret_t do_physdev_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) 
arg)
         }
         else
             pdev_info.is_virtfn = 0;
-        ret = pci_add_device(add.seg, add.bus, add.devfn, &pdev_info);
+
+        if ( add.flags & XEN_PCI_DEV_PXM ) {
+            int optarr_off = offsetof(struct physdev_pci_device_add, optarr) /
+                             sizeof(add.optarr[0]);
+
+            if ( copy_from_guest_offset(&add.optarr[0], arg, optarr_off, 1) )
+                break;
+
+            node = pxm_to_node(add.optarr[0]);
+        } else
+            node = NUMA_NO_NODE;
+
+        ret = pci_add_device(add.seg, add.bus, add.devfn, &pdev_info, node);
         break;
     }
 
diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index 78c6977..898edaa 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -568,7 +568,8 @@ static void pci_enable_acs(struct pci_dev *pdev)
     pci_conf_write16(seg, bus, dev, func, pos + PCI_ACS_CTRL, ctrl);
 }
 
-int pci_add_device(u16 seg, u8 bus, u8 devfn, const struct pci_dev_info *info)
+int pci_add_device(u16 seg, u8 bus, u8 devfn,
+                   const struct pci_dev_info *info, const int node)
 {
     struct pci_seg *pseg;
     struct pci_dev *pdev;
@@ -586,7 +587,8 @@ int pci_add_device(u16 seg, u8 bus, u8 devfn, const struct 
pci_dev_info *info)
         pdev = pci_get_pdev(seg, info->physfn.bus, info->physfn.devfn);
         spin_unlock(&pcidevs_lock);
         if ( !pdev )
-            pci_add_device(seg, info->physfn.bus, info->physfn.devfn, NULL);
+            pci_add_device(seg, info->physfn.bus, info->physfn.devfn,
+                           NULL, node);
         pdev_type = "virtual function";
     }
     else
@@ -609,6 +611,8 @@ int pci_add_device(u16 seg, u8 bus, u8 devfn, const struct 
pci_dev_info *info)
     if ( !pdev )
         goto out;
 
+    pdev->node = node;
+
     if ( info )
         pdev->info = *info;
     else if ( !pdev->vf_rlen[0] )
@@ -1191,10 +1195,11 @@ static int _dump_pci_devices(struct pci_seg *pseg, void 
*arg)
 
     list_for_each_entry ( pdev, &pseg->alldevs_list, alldevs_list )
     {
-        printk("%04x:%02x:%02x.%u - dom %-3d - MSIs < ",
+        printk("%04x:%02x:%02x.%u - dom %-3d - node %-3d - MSIs < ",
                pseg->nr, pdev->bus,
                PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn),
-               pdev->domain ? pdev->domain->domain_id : -1);
+               pdev->domain ? pdev->domain->domain_id : -1,
+               (pdev->node != NUMA_NO_NODE) ? pdev->node : -1);
         list_for_each_entry ( msi, &pdev->msi_list, list )
                printk("%d ", msi->irq);
         printk(">\n");
diff --git a/xen/include/xen/pci.h b/xen/include/xen/pci.h
index 5f295f3..a2a0a1c 100644
--- a/xen/include/xen/pci.h
+++ b/xen/include/xen/pci.h
@@ -56,6 +56,8 @@ struct pci_dev {
 
     u8 phantom_stride;
 
+    int node; /* NUMA node */
+
     enum pdev_type {
         DEV_TYPE_PCI_UNKNOWN,
         DEV_TYPE_PCIe_ENDPOINT,
@@ -102,7 +104,8 @@ void setup_hwdom_pci_devices(struct domain *,
 int pci_release_devices(struct domain *d);
 int pci_add_segment(u16 seg);
 const unsigned long *pci_get_ro_map(u16 seg);
-int pci_add_device(u16 seg, u8 bus, u8 devfn, const struct pci_dev_info *);
+int pci_add_device(u16 seg, u8 bus, u8 devfn,
+                   const struct pci_dev_info *, const int);
 int pci_remove_device(u16 seg, u8 bus, u8 devfn);
 int pci_ro_device(int seg, int bus, int devfn);
 void arch_pci_ro_device(int seg, int bdf);
-- 
1.8.4.2


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel