[PATCH v2 3/4] sysctl: Add sysctl interface for querying PCI topology

[Boris Ostrovsky <boris.ostrovsky@oracle.com>]

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 xen/common/sysctl.c         |   60 +++++++++++++++++++++++++++++++++++++++++++
 xen/include/public/sysctl.h |   35 ++++++++++++++++++++++++-
 2 files changed, 94 insertions(+), 1 deletions(-)

diff --git a/xen/common/sysctl.c b/xen/common/sysctl.c
index 1254a24..f09d377 100644
--- a/xen/common/sysctl.c
+++ b/xen/common/sysctl.c
@@ -365,6 +365,66 @@ long do_sysctl(XEN_GUEST_HANDLE_PARAM(xen_sysctl_t) u_sysctl)
     }
     break;
 
+    case XEN_SYSCTL_pcitopoinfo:
+    {
+        xen_sysctl_pcitopoinfo_t *ti = &op->u.pcitopoinfo;
+
+        if ( guest_handle_is_null(ti->pcitopo) ||
+             (ti->first_dev >= ti->num_devs) )
+        {
+            ret = -EINVAL;
+            break;
+        }
+
+        for ( ; ti->first_dev < ti->num_devs; ti->first_dev++ )
+        {
+            xen_sysctl_pcitopo_t pcitopo;
+            struct pci_dev *pdev;
+
+            if ( copy_from_guest_offset(&pcitopo, ti->pcitopo,
+                                        ti->first_dev, 1) )
+            {
+                ret = -EFAULT;
+                break;
+            }
+
+            spin_lock(&pcidevs_lock);
+            pdev = pci_get_pdev(pcitopo.pcidev.seg, pcitopo.pcidev.bus,
+                                pcitopo.pcidev.devfn);
+            if ( !pdev || (pdev->node == NUMA_NO_NODE) )
+                pcitopo.node = INVALID_TOPOLOGY_ID;
+            else
+                pcitopo.node = pdev->node;
+            spin_unlock(&pcidevs_lock);
+
+            if ( copy_to_guest_offset(ti->pcitopo, ti->first_dev,
+                                      &pcitopo, 1) )
+            {
+                ret = -EFAULT;
+                break;
+            }
+
+            if ( hypercall_preempt_check() )
+                break;
+        }
+
+        if ( !ret )
+        {
+            if ( __copy_field_to_guest(u_sysctl, op,
+                                       u.pcitopoinfo.first_dev) )
+            {
+                ret = -EFAULT;
+                break;
+            }
+
+            if ( ti->first_dev < ti->num_devs )
+                ret = hypercall_create_continuation(__HYPERVISOR_sysctl,
+                                                   "h", u_sysctl);
+
+        }
+    }
+    break;
+
 #ifdef TEST_COVERAGE
     case XEN_SYSCTL_coverage_op:
         ret = sysctl_coverage_op(&op->u.coverage_op);
diff --git a/xen/include/public/sysctl.h b/xen/include/public/sysctl.h
index 512ad74..628ed6a 100644
--- a/xen/include/public/sysctl.h
+++ b/xen/include/public/sysctl.h
@@ -33,6 +33,7 @@
 
 #include "xen.h"
 #include "domctl.h"
+#include "physdev.h"
 
 #define XEN_SYSCTL_INTERFACE_VERSION 0x0000000C
 
@@ -463,7 +464,7 @@ typedef struct xen_sysctl_lockprof_op xen_sysctl_lockprof_op_t;
 DEFINE_XEN_GUEST_HANDLE(xen_sysctl_lockprof_op_t);
 
 /* XEN_SYSCTL_cputopoinfo */
-#define INVALID_TOPOLOGY_ID  (~0U)
+#define INVALID_TOPOLOGY_ID  (~0U) /* Also used by pcitopo */
 
 struct xen_sysctl_cputopo {
     uint32_t core;
@@ -492,6 +493,36 @@ struct xen_sysctl_cputopoinfo {
 typedef struct xen_sysctl_cputopoinfo xen_sysctl_cputopoinfo_t;
 DEFINE_XEN_GUEST_HANDLE(xen_sysctl_cputopoinfo_t);
 
+/* XEN_SYSCTL_pcitopoinfo */
+struct xen_sysctl_pcitopo {
+    struct physdev_pci_device pcidev;
+    uint32_t node;
+};
+typedef struct xen_sysctl_pcitopo xen_sysctl_pcitopo_t;
+DEFINE_XEN_GUEST_HANDLE(xen_sysctl_pcitopo_t);
+
+struct xen_sysctl_pcitopoinfo {
+    /* IN: Size of pcitopo array */
+    uint32_t num_devs;
+
+    /*
+     * IN/OUT: First element of pcitopo array that needs to be processed by
+     * hypervisor.
+     * This is used primarily by hypercall continuations and callers will
+     * typically set it to zero
+     */
+    uint32_t first_dev;
+
+    /*
+     * If not NULL, filled with node identifier for each pcidev
+     * If information for a particular device is not avalable then node is set
+     * to INVALID_TOPOLOGY_ID.
+     */
+    XEN_GUEST_HANDLE_64(xen_sysctl_pcitopo_t) pcitopo;
+};
+typedef struct xen_sysctl_pcitopoinfo xen_sysctl_pcitopoinfo_t;
+DEFINE_XEN_GUEST_HANDLE(xen_sysctl_pcitopoinfo_t);
+
 /* XEN_SYSCTL_numainfo */
 #define INVALID_NUMAINFO_ID (~0U)
 struct xen_sysctl_numainfo {
@@ -681,12 +712,14 @@ struct xen_sysctl {
 #define XEN_SYSCTL_scheduler_op                  19
 #define XEN_SYSCTL_coverage_op                   20
 #define XEN_SYSCTL_psr_cmt_op                    21
+#define XEN_SYSCTL_pcitopoinfo                   22
     uint32_t interface_version; /* XEN_SYSCTL_INTERFACE_VERSION */
     union {
         struct xen_sysctl_readconsole       readconsole;
         struct xen_sysctl_tbuf_op           tbuf_op;
         struct xen_sysctl_physinfo          physinfo;
         struct xen_sysctl_cputopoinfo       cputopoinfo;
+        struct xen_sysctl_pcitopoinfo       pcitopoinfo;
         struct xen_sysctl_numainfo          numainfo;
         struct xen_sysctl_sched_id          sched_id;
         struct xen_sysctl_perfc_op          perfc_op;
-- 
1.7.1