[PATCH v4 1/7] xen: vNUMA support for PV guests

[Elena Ufimtseva <ufimtseva@gmail.com>]

Defines interface, structures and hypercalls for toolstack to
build vnuma topology and for guests that wish to retreive it.
Two subop hypercalls introduced by patch:
XEN_DOMCTL_setvnumainfo to define vNUMA domain topology per domain
and XENMEM_get_vnuma_info to retreive that topology by guest.

Signed-off-by: Elena Ufimtseva <ufimtseva@gmail.com>
---
Changes since v3:
- added subop hypercall to retrive number of vnodes
and vcpus for domain to make correct allocations before
requesting vnuma topology.
---
 xen/common/domain.c         |   10 +++++
 xen/common/domctl.c         |   79 +++++++++++++++++++++++++++++++++++
 xen/common/memory.c         |   96 +++++++++++++++++++++++++++++++++++++++++++
 xen/include/public/domctl.h |   29 +++++++++++++
 xen/include/public/memory.h |   17 ++++++++
 xen/include/public/vnuma.h  |   59 ++++++++++++++++++++++++++
 xen/include/xen/domain.h    |    8 ++++
 xen/include/xen/sched.h     |    1 +
 8 files changed, 299 insertions(+)
 create mode 100644 xen/include/public/vnuma.h

diff --git a/xen/common/domain.c b/xen/common/domain.c
index 2cbc489..8f5c665 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -511,6 +511,15 @@ int rcu_lock_live_remote_domain_by_id(domid_t dom, struct domain **d)
     return 0;
 }
 
+static void vnuma_destroy(struct vnuma_info *vnuma)
+{
+    vnuma->nr_vnodes = 0;
+    xfree(vnuma->vmemrange);
+    xfree(vnuma->vcpu_to_vnode);
+    xfree(vnuma->vdistance);
+    xfree(vnuma->vnode_to_pnode);
+}
+
 int domain_kill(struct domain *d)
 {
     int rc = 0;
@@ -531,6 +540,7 @@ int domain_kill(struct domain *d)
         tmem_destroy(d->tmem);
         domain_set_outstanding_pages(d, 0);
         d->tmem = NULL;
+        vnuma_destroy(&d->vnuma);
         /* fallthrough */
     case DOMDYING_dying:
         rc = domain_relinquish_resources(d);
diff --git a/xen/common/domctl.c b/xen/common/domctl.c
index 904d27b..4f5a17c 100644
--- a/xen/common/domctl.c
+++ b/xen/common/domctl.c
@@ -29,6 +29,7 @@
 #include <asm/page.h>
 #include <public/domctl.h>
 #include <xsm/xsm.h>
+#include <public/vnuma.h>
 
 static DEFINE_SPINLOCK(domctl_lock);
 DEFINE_SPINLOCK(vcpu_alloc_lock);
@@ -889,6 +890,84 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
     }
     break;
 
+    case XEN_DOMCTL_setvnumainfo:
+    {
+        unsigned int dist_size, nr_vnodes, i;
+
+        ret = -EINVAL;
+
+        /*
+         * If number of vnodes was set before,
+         * dont initilize it again.
+         */
+        if ( d->vnuma.nr_vnodes > 0 )
+            break;
+
+        nr_vnodes = op->u.vnuma.nr_vnodes;
+        if ( nr_vnodes == 0 )
+            break;
+        if ( nr_vnodes > (UINT_MAX / nr_vnodes) )
+            break;
+
+        ret = -EFAULT;
+        if ( guest_handle_is_null(op->u.vnuma.vdistance)     ||
+             guest_handle_is_null(op->u.vnuma.vmemrange)     ||
+             guest_handle_is_null(op->u.vnuma.vcpu_to_vnode) ||
+             guest_handle_is_null(op->u.vnuma.vnode_to_pnode) )
+            goto setvnumainfo_out;
+
+        dist_size = nr_vnodes * nr_vnodes;
+
+        d->vnuma.vdistance = xmalloc_array(unsigned int, dist_size);
+        d->vnuma.vmemrange = xmalloc_array(vmemrange_t, nr_vnodes);
+        d->vnuma.vcpu_to_vnode = xmalloc_array(unsigned int, d->max_vcpus);
+        d->vnuma.vnode_to_pnode = xmalloc_array(unsigned int, nr_vnodes);
+
+        if ( d->vnuma.vdistance == NULL ||
+             d->vnuma.vmemrange == NULL ||
+             d->vnuma.vcpu_to_vnode == NULL ||
+             d->vnuma.vnode_to_pnode == NULL )
+        {
+            ret = -ENOMEM;
+            goto setvnumainfo_out;
+        }
+
+        if ( unlikely(copy_from_guest(d->vnuma.vdistance,
+                                    op->u.vnuma.vdistance,
+                                    dist_size)) )
+            goto setvnumainfo_out;
+        if ( unlikely(copy_from_guest(d->vnuma.vmemrange,
+                                    op->u.vnuma.vmemrange,
+                                    nr_vnodes)) )
+            goto setvnumainfo_out;
+        if ( unlikely(copy_from_guest(d->vnuma.vcpu_to_vnode,
+                                    op->u.vnuma.vcpu_to_vnode,
+                                    d->max_vcpus)) )
+            goto setvnumainfo_out;
+        if ( unlikely(copy_from_guest(d->vnuma.vnode_to_pnode,
+                                    op->u.vnuma.vnode_to_pnode,
+                                    nr_vnodes)) )
+            goto setvnumainfo_out;
+
+        /* Everything is good, lets set the number of vnodes */
+        d->vnuma.nr_vnodes = nr_vnodes;
+
+        for ( i = 0; i < nr_vnodes; i++ )
+            d->vnuma.vmemrange[i]._reserved = 0;
+
+        ret = 0;
+
+    setvnumainfo_out:
+        if ( ret != 0 )
+        {
+            xfree(d->vnuma.vdistance);
+            xfree(d->vnuma.vmemrange);
+            xfree(d->vnuma.vcpu_to_vnode);
+            xfree(d->vnuma.vnode_to_pnode);
+        }
+    }
+    break;
+
     default:
         ret = arch_do_domctl(op, d, u_domctl);
         break;
diff --git a/xen/common/memory.c b/xen/common/memory.c
index 50b740f..5bfab08 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -28,6 +28,7 @@
 #include <public/memory.h>
 #include <xsm/xsm.h>
 #include <xen/trace.h>
+#include <public/vnuma.h>
 
 struct memop_args {
     /* INPUT */
@@ -733,6 +734,101 @@ long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
 
         break;
 
+    case XENMEM_get_vnuma_info:
+    {
+        struct vnuma_topology_info mtopology;
+        struct domain *d;
+
+        if ( copy_from_guest(&mtopology, arg, 1) )
+        {
+            printk(KERN_INFO "COpy from guest of mtopology failed.\n");
+            return -EFAULT;
+        }
+        if ( (d = rcu_lock_domain_by_any_id(mtopology.domid)) == NULL )
+            return -ESRCH;
+
+        if ( (d->vnuma.nr_vnodes == 0) ||
+             (d->vnuma.nr_vnodes > d->max_vcpus) )
+        {
+            rc = -EOPNOTSUPP;
+            goto vnumainfo_out;
+        }
+
+        rc = -EFAULT;
+
+        if ( guest_handle_is_null(mtopology.vmemrange.h)    ||
+             guest_handle_is_null(mtopology.vdistance.h)    ||
+             guest_handle_is_null(mtopology.vcpu_to_vnode.h)||
+             guest_handle_is_null(mtopology.nr_vnodes.h) )
+            goto vnumainfo_out;
+
+        if ( __copy_to_guest(mtopology.vmemrange.h,
+                                d->vnuma.vmemrange,
+                                d->vnuma.nr_vnodes) != 0 )
+            goto vnumainfo_out;
+        if ( __copy_to_guest(mtopology.vdistance.h,
+                                d->vnuma.vdistance,
+                                d->vnuma.nr_vnodes * d->vnuma.nr_vnodes) != 0 )
+            goto vnumainfo_out;
+        if ( __copy_to_guest(mtopology.vcpu_to_vnode.h,
+                                d->vnuma.vcpu_to_vnode,
+                                d->max_vcpus) != 0 )
+            goto vnumainfo_out;
+
+        if ( __copy_to_guest(mtopology.nr_vnodes.h, &d->vnuma.nr_vnodes, 1) != 0 )
+            goto vnumainfo_out;
+
+        rc = 0;
+
+    vnumainfo_out:
+        rcu_unlock_domain(d);
+        if ( rc != 0 ) {
+            printk(KERN_INFO "Problem with some parts of vnuma hypercall\n");
+        }
+        break;
+    }
+
+    /* only two fields are used here from vnuma_topology_info:
+     * nr_vnodes and max_vcpus. Used by guest to allocate correct
+     * size of vnuma topology arrays.
+     */
+    case XENMEM_get_vnodes_vcpus:
+    {
+        struct vnuma_topology_info mtopology;
+        struct domain *d;
+        unsigned int nr_vnodes, max_vcpus;
+
+        if ( copy_from_guest(&mtopology, arg, 1) )
+        {
+            printk(KERN_INFO "Null pointer vnuma_nodes.\n");
+            return -EFAULT;
+        }
+        if ( (d = rcu_lock_domain_by_any_id(mtopology.domid)) == NULL )
+            return -ESRCH;
+
+        nr_vnodes = d->vnuma.nr_vnodes;
+        max_vcpus = d->max_vcpus;
+        rcu_unlock_domain(d);
+
+        rc = -EFAULT;
+
+        /* check if its request to get number of nodes, first one */
+        if ( guest_handle_is_null(mtopology.nr_vnodes.h) ||
+            guest_handle_is_null(mtopology.nr_vcpus.h) )
+            return rc;
+
+        rc = __copy_to_guest(mtopology.nr_vnodes.h, &nr_vnodes, 1);
+        if (rc)
+            return rc;
+
+        rc = __copy_to_guest(mtopology.nr_vcpus.h, &max_vcpus, 1);
+        if (rc)
+            return rc;
+
+        rc = 0;
+        break;
+    }
+
     default:
         rc = arch_memory_op(op, arg);
         break;
diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index 01a3652..0157a16 100644
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -35,6 +35,7 @@
 #include "xen.h"
 #include "grant_table.h"
 #include "hvm/save.h"
+#include "vnuma.h"
 
 #define XEN_DOMCTL_INTERFACE_VERSION 0x00000009
 
@@ -869,6 +870,32 @@ struct xen_domctl_set_max_evtchn {
 typedef struct xen_domctl_set_max_evtchn xen_domctl_set_max_evtchn_t;
 DEFINE_XEN_GUEST_HANDLE(xen_domctl_set_max_evtchn_t);
 
+/*
+ * XEN_DOMCTL_setvnumainfo: sets the vNUMA topology
+ * parameters from toolstack.
+ */
+struct xen_domctl_vnuma {
+    uint32_t nr_vnodes;
+    uint32_t __pad;
+    XEN_GUEST_HANDLE_64(uint) vdistance;
+    XEN_GUEST_HANDLE_64(uint) vcpu_to_vnode;
+    /*
+     * vnodes to physical NUMA nodes mask.
+     * This will be kept on per-domain basis
+     * for requests by consumers as vnuma
+     * aware ballooning.
+     */
+    XEN_GUEST_HANDLE_64(uint) vnode_to_pnode;
+    /*
+     * memory rages that vNUMA node can represent
+     * If more than one, its a linked list.
+     */
+    XEN_GUEST_HANDLE_64(vmemrange_t) vmemrange;
+};
+
+typedef struct xen_domctl_vnuma xen_domctl_vnuma_t;
+DEFINE_XEN_GUEST_HANDLE(xen_domctl_vnuma_t);
+
 struct xen_domctl {
     uint32_t cmd;
 #define XEN_DOMCTL_createdomain                   1
@@ -938,6 +965,7 @@ struct xen_domctl {
 #define XEN_DOMCTL_setnodeaffinity               68
 #define XEN_DOMCTL_getnodeaffinity               69
 #define XEN_DOMCTL_set_max_evtchn                70
+#define XEN_DOMCTL_setvnumainfo                  71
 #define XEN_DOMCTL_gdbsx_guestmemio            1000
 #define XEN_DOMCTL_gdbsx_pausevcpu             1001
 #define XEN_DOMCTL_gdbsx_unpausevcpu           1002
@@ -998,6 +1026,7 @@ struct xen_domctl {
         struct xen_domctl_set_broken_page_p2m set_broken_page_p2m;
         struct xen_domctl_gdbsx_pauseunp_vcpu gdbsx_pauseunp_vcpu;
         struct xen_domctl_gdbsx_domstatus   gdbsx_domstatus;
+        struct xen_domctl_vnuma             vnuma;
         uint8_t                             pad[128];
     } u;
 };
diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
index 7a26dee..f5ea6af 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -339,6 +339,23 @@ struct xen_pod_target {
 };
 typedef struct xen_pod_target xen_pod_target_t;
 
+/*
+ * XENMEM_get_vnuma_info used by caller to retrieve
+ * vNUMA topology constructed for particular domain.
+ *
+ * The data exchanged is presented by vnuma_topology_info.
+ */
+#define XENMEM_get_vnuma_info               25
+
+/*
+ * XENMEM_get_vnuma_nodes used to retreive number of nodes
+ * and vcpus for allocating correct amount of memory for
+ * vnuma topology.
+ */
+#define XENMEM_get_vnodes_vcpus             26
+
+#define XENMEM_get_vnuma_pnode              27
+
 #if defined(__XEN__) || defined(__XEN_TOOLS__)
 
 #ifndef uint64_aligned_t
diff --git a/xen/include/public/vnuma.h b/xen/include/public/vnuma.h
new file mode 100644
index 0000000..32f860f
--- /dev/null
+++ b/xen/include/public/vnuma.h
@@ -0,0 +1,59 @@
+#ifndef _XEN_PUBLIC_VNUMA_H
+#define _XEN_PUBLIC_VNUMA_H
+
+#include "xen.h"
+
+/*
+ * Following structures are used to represent vNUMA
+ * topology to guest if requested.
+ */
+
+/*
+ * Memory ranges can be used to define
+ * vNUMA memory node boundaries by the
+ * linked list. As of now, only one range
+ * per domain is suported.
+ */
+struct vmemrange {
+    uint64_t start, end;
+    uint64_t _reserved;
+};
+
+typedef struct vmemrange vmemrange_t;
+DEFINE_XEN_GUEST_HANDLE(vmemrange_t);
+
+/*
+ * vNUMA topology specifies vNUMA node
+ * number, distance table, memory ranges and
+ * vcpu mapping provided for guests.
+ */
+
+struct vnuma_topology_info {
+    /* IN */
+    domid_t domid;
+    /* OUT */
+    union {
+        XEN_GUEST_HANDLE(uint) h;
+        uint64_t    _pad;
+    } nr_vnodes;
+    union {
+        XEN_GUEST_HANDLE(uint) h;
+        uint64_t    _pad;
+    } nr_vcpus;
+    union {
+        XEN_GUEST_HANDLE(uint) h;
+        uint64_t    _pad;
+    } vdistance;
+    union {
+        XEN_GUEST_HANDLE(uint) h;
+        uint64_t    _pad;
+    } vcpu_to_vnode;
+    union {
+        XEN_GUEST_HANDLE(vmemrange_t) h;
+        uint64_t    _pad;
+    } vmemrange;
+};
+typedef struct vnuma_topology_info vnuma_topology_info_t;
+DEFINE_XEN_GUEST_HANDLE(vnuma_topology_info_t);
+
+#endif
diff --git a/xen/include/xen/domain.h b/xen/include/xen/domain.h
index a057069..ee0eeee 100644
--- a/xen/include/xen/domain.h
+++ b/xen/include/xen/domain.h
@@ -89,4 +89,12 @@ extern unsigned int xen_processor_pmbits;
 
 extern bool_t opt_dom0_vcpus_pin;
 
+struct vnuma_info {
+    unsigned int nr_vnodes;
+    unsigned int *vdistance;
+    unsigned int *vcpu_to_vnode;
+    unsigned int *vnode_to_pnode;
+    struct vmemrange *vmemrange;
+};
+
 #endif /* __XEN_DOMAIN_H__ */
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index cbdf377..3765eae 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -417,6 +417,7 @@ struct domain
     nodemask_t node_affinity;
     unsigned int last_alloc_node;
     spinlock_t node_affinity_lock;
+    struct vnuma_info vnuma;
 };
 
 struct domain_setup_info
-- 
1.7.10.4