[PATCH 02 of 10 v3] libxl, libxc: introduce libxl_get_numainfo()

[Dario Faggioli <raistlin@linux.it>]

# HG changeset patch
# User Dario Faggioli <raistlin@linux.it>
# Date 1341416323 -7200
# Node ID 0ca91a203fc95d3d18bb436ecdc7106b0b2ff22f
# Parent  8e367818e194c212cd1470aad663f3243ff53bdb
libxl,libxc: introduce libxl_get_numainfo()

Make some NUMA node information available to the toolstack. Achieve
this by means of xc_numainfo(), which exposes memory size and amount
of free memory of each node, as well as the relative distances of
each node to all the others.

For properly exposing distances we need the IDL to support arrays.

Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>

---
Changes from v2:
 * converted libxl__zalloc(NULL, ...) to libxl_calloc(NOGC, ...).
 * Fixed the comment about memory ownership of libxl_get_numainfo().
 * Added a comment for libxl_numainfo in libxl_types.idl.

Changes from v1:
 * malloc converted to libxl__zalloc(NOGC, ...).
 * The patch also accommodates some bits of what was in "libxc,
   libxl: introduce xc_nodemap_t and libxl_nodemap" which was
   removed as well, as full support for node maps at libxc
   level is not needed (yet!).

diff --git a/tools/libxc/xc_misc.c b/tools/libxc/xc_misc.c
--- a/tools/libxc/xc_misc.c
+++ b/tools/libxc/xc_misc.c
@@ -35,6 +35,20 @@ int xc_get_max_cpus(xc_interface *xch)
     return max_cpus;
 }
 
+int xc_get_max_nodes(xc_interface *xch)
+{
+    static int max_nodes = 0;
+    xc_physinfo_t physinfo;
+
+    if ( max_nodes )
+        return max_nodes;
+
+    if ( !xc_physinfo(xch, &physinfo) )
+        max_nodes = physinfo.max_node_id + 1;
+
+    return max_nodes;
+}
+
 int xc_get_cpumap_size(xc_interface *xch)
 {
     return (xc_get_max_cpus(xch) + 7) / 8;
diff --git a/tools/libxc/xenctrl.h b/tools/libxc/xenctrl.h
--- a/tools/libxc/xenctrl.h
+++ b/tools/libxc/xenctrl.h
@@ -329,6 +329,12 @@ int xc_get_cpumap_size(xc_interface *xch
 /* allocate a cpumap */
 xc_cpumap_t xc_cpumap_alloc(xc_interface *xch);
 
+ /*
+ * NODEMAP handling
+ */
+/* return maximum number of NUMA nodes the hypervisor supports */
+int xc_get_max_nodes(xc_interface *xch);
+
 /*
  * DOMAIN DEBUGGING FUNCTIONS
  */
diff --git a/tools/libxl/libxl.c b/tools/libxl/libxl.c
--- a/tools/libxl/libxl.c
+++ b/tools/libxl/libxl.c
@@ -3298,6 +3298,75 @@ fail:
     return ret;
 }
 
+libxl_numainfo *libxl_get_numainfo(libxl_ctx *ctx, int *nr)
+{
+    GC_INIT(ctx);
+    xc_numainfo_t ninfo;
+    DECLARE_HYPERCALL_BUFFER(xc_node_to_memsize_t, memsize);
+    DECLARE_HYPERCALL_BUFFER(xc_node_to_memfree_t, memfree);
+    DECLARE_HYPERCALL_BUFFER(uint32_t, node_dists);
+    libxl_numainfo *ret = NULL;
+    int i, j, max_nodes;
+
+    max_nodes = libxl_get_max_nodes(ctx);
+    if (max_nodes == 0)
+    {
+        LIBXL__LOG(ctx, XTL_ERROR, "Unable to determine number of NODES");
+        ret = NULL;
+        goto out;
+    }
+
+    memsize = xc_hypercall_buffer_alloc
+        (ctx->xch, memsize, sizeof(*memsize) * max_nodes);
+    memfree = xc_hypercall_buffer_alloc
+        (ctx->xch, memfree, sizeof(*memfree) * max_nodes);
+    node_dists = xc_hypercall_buffer_alloc
+        (ctx->xch, node_dists, sizeof(*node_dists) * max_nodes * max_nodes);
+    if ((memsize == NULL) || (memfree == NULL) || (node_dists == NULL)) {
+        LIBXL__LOG_ERRNOVAL(ctx, XTL_ERROR, ENOMEM,
+                            "Unable to allocate hypercall arguments");
+        goto fail;
+    }
+
+    set_xen_guest_handle(ninfo.node_to_memsize, memsize);
+    set_xen_guest_handle(ninfo.node_to_memfree, memfree);
+    set_xen_guest_handle(ninfo.node_to_node_distance, node_dists);
+    ninfo.max_node_index = max_nodes - 1;
+    if (xc_numainfo(ctx->xch, &ninfo) != 0) {
+        LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "getting numainfo");
+        goto fail;
+    }
+
+    if (ninfo.max_node_index < max_nodes - 1)
+        max_nodes = ninfo.max_node_index + 1;
+
+    *nr = max_nodes;
+
+    ret = libxl__zalloc(NOGC, sizeof(libxl_numainfo) * max_nodes);
+    for (i = 0; i < max_nodes; i++)
+        ret[i].dists = libxl__calloc(NOGC, max_nodes, sizeof(*node_dists));
+
+    for (i = 0; i < max_nodes; i++) {
+#define V(mem, i) (mem[i] == INVALID_NUMAINFO_ID) ? \
+    LIBXL_NUMAINFO_INVALID_ENTRY : mem[i]
+        ret[i].size = V(memsize, i);
+        ret[i].free = V(memfree, i);
+        ret[i].num_dists = max_nodes;
+        for (j = 0; j < ret[i].num_dists; j++)
+            ret[i].dists[j] = V(node_dists, i * max_nodes + j);
+#undef V
+    }
+
+ fail:
+    xc_hypercall_buffer_free(ctx->xch, memsize);
+    xc_hypercall_buffer_free(ctx->xch, memfree);
+    xc_hypercall_buffer_free(ctx->xch, node_dists);
+
+ out:
+    GC_FREE;
+    return ret;
+}
+
 const libxl_version_info* libxl_get_version_info(libxl_ctx *ctx)
 {
     union {
diff --git a/tools/libxl/libxl.h b/tools/libxl/libxl.h
--- a/tools/libxl/libxl.h
+++ b/tools/libxl/libxl.h
@@ -532,6 +532,9 @@ int libxl_domain_preserve(libxl_ctx *ctx
 /* get max. number of cpus supported by hypervisor */
 int libxl_get_max_cpus(libxl_ctx *ctx);
 
+/* get max. number of NUMA nodes supported by hypervisor */
+int libxl_get_max_nodes(libxl_ctx *ctx);
+
 int libxl_domain_rename(libxl_ctx *ctx, uint32_t domid,
                         const char *old_name, const char *new_name);
 
@@ -604,6 +607,10 @@ void libxl_vminfo_list_free(libxl_vminfo
 libxl_cputopology *libxl_get_cpu_topology(libxl_ctx *ctx, int *nb_cpu_out);
 void libxl_cputopology_list_free(libxl_cputopology *, int nb_cpu);
 
+#define LIBXL_NUMAINFO_INVALID_ENTRY (~(uint32_t)0)
+libxl_numainfo *libxl_get_numainfo(libxl_ctx *ctx, int *nr);
+void libxl_numainfo_list_free(libxl_numainfo *, int nr);
+
 libxl_vcpuinfo *libxl_list_vcpu(libxl_ctx *ctx, uint32_t domid,
                                 int *nb_vcpu, int *nr_vcpus_out);
 void libxl_vcpuinfo_list_free(libxl_vcpuinfo *, int nr_vcpus);
diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
--- a/tools/libxl/libxl_types.idl
+++ b/tools/libxl/libxl_types.idl
@@ -433,6 +433,15 @@ libxl_physinfo = Struct("physinfo", [
     ("cap_hvm_directio", bool),
     ], dir=DIR_OUT)
 
+# NUMA node characteristics: size and free are how much memory it has, and how
+# much of it is free, respectively. dists is an array of distances from this
+# node to each other node.
+libxl_numainfo = Struct("numainfo", [
+    ("size", uint64),
+    ("free", uint64),
+    ("dists", Array(uint32, "num_dists")),
+    ], dir=DIR_OUT)
+
 libxl_cputopology = Struct("cputopology", [
     ("core", uint32),
     ("socket", uint32),
diff --git a/tools/libxl/libxl_utils.c b/tools/libxl/libxl_utils.c
--- a/tools/libxl/libxl_utils.c
+++ b/tools/libxl/libxl_utils.c
@@ -572,6 +572,11 @@ int libxl_get_max_cpus(libxl_ctx *ctx)
     return xc_get_max_cpus(ctx->xch);
 }
 
+int libxl_get_max_nodes(libxl_ctx *ctx)
+{
+    return xc_get_max_nodes(ctx->xch);
+}
+
 int libxl__enum_from_string(const libxl_enum_string_table *t,
                             const char *s, int *e)
 {
@@ -594,6 +599,14 @@ void libxl_cputopology_list_free(libxl_c
     free(list);
 }
 
+void libxl_numainfo_list_free(libxl_numainfo *list, int nr)
+{
+    int i;
+    for (i = 0; i < nr; i++)
+        libxl_numainfo_dispose(&list[i]);
+    free(list);
+}
+
 void libxl_vcpuinfo_list_free(libxl_vcpuinfo *list, int nr)
 {
     int i;
diff --git a/xen/include/public/sysctl.h b/xen/include/public/sysctl.h
--- a/xen/include/public/sysctl.h
+++ b/xen/include/public/sysctl.h
@@ -484,6 +484,7 @@ typedef struct xen_sysctl_topologyinfo x
 DEFINE_XEN_GUEST_HANDLE(xen_sysctl_topologyinfo_t);
 
 /* XEN_SYSCTL_numainfo */
+#define INVALID_NUMAINFO_ID (~0U)
 struct xen_sysctl_numainfo {
     /*
      * IN: maximum addressable entry in the caller-provided arrays.