[Xen-devel] [PATCH v3 16/19] libxl: build, check and pass vNUMA info to Xen for HVM guest

[Wei Liu <wei.liu2@xxxxxxxxxx>]

Transform user supplied vNUMA configuration into libxl internal
representations then libxc representations. Check validity along the
line.

Libxc has more involvement in building vmemranges in HVM case compared
to PV case. The building of vmemranges is placed after xc_hvm_build
returns, because it relies on memory hole information provided by
xc_hvm_build.

Signed-off-by: Wei Liu <wei.liu2@xxxxxxxxxx>
Cc: Ian Campbell <ian.campbell@xxxxxxxxxx>
Cc: Ian Jackson <ian.jackson@xxxxxxxxxxxxx>
Cc: Dario Faggioli <dario.faggioli@xxxxxxxxxx>
Cc: Elena Ufimtseva <ufimtseva@xxxxxxxxx>
---
Changes in v3:
1. Rewrite commit log.
---
 tools/libxl/libxl_create.c   |    9 +++++++
 tools/libxl/libxl_dom.c      |   28 +++++++++++++++++++++
 tools/libxl/libxl_internal.h |    5 ++++
 tools/libxl/libxl_vnuma.c    |   56 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 98 insertions(+)

diff --git a/tools/libxl/libxl_create.c b/tools/libxl/libxl_create.c
index 6f87d1c..9700172 100644
--- a/tools/libxl/libxl_create.c
+++ b/tools/libxl/libxl_create.c
@@ -845,6 +845,15 @@ static void initiate_domain_create(libxl__egc *egc,
         goto error_out;
     }
 
+    /* Disallow PoD and vNUMA to be enabled at the same time because PoD
+     * pool is not vNUMA-aware yet.
+     */
+    if (pod_enabled && d_config->b_info.num_vnuma_nodes) {
+        ret = ERROR_INVAL;
+        LOG(ERROR, "Cannot enable PoD and vNUMA at the same time");
+        goto error_out;
+    }
+
     ret = libxl__domain_create_info_setdefault(gc, &d_config->c_info);
     if (ret) goto error_out;
 
diff --git a/tools/libxl/libxl_dom.c b/tools/libxl/libxl_dom.c
index f06c88b..592904f 100644
--- a/tools/libxl/libxl_dom.c
+++ b/tools/libxl/libxl_dom.c
@@ -887,12 +887,40 @@ int libxl__build_hvm(libxl__gc *gc, uint32_t domid,
         goto out;
     }
 
+    if (info->num_vnuma_nodes != 0) {
+        int i;
+
+        args.nr_vnodes = info->num_vnuma_nodes;
+        args.vnode_to_pnode = libxl__malloc(gc, sizeof(*args.vnode_to_pnode) *
+                                            args.nr_vnodes);
+        args.vnode_size = libxl__malloc(gc, sizeof(*args.vnode_size) *
+                                        args.nr_vnodes);
+        for (i = 0; i < args.nr_vnodes; i++) {
+            args.vnode_to_pnode[i] = info->vnuma_nodes[i].pnode;
+            args.vnode_size[i] = info->vnuma_nodes[i].mem;
+        }
+
+        /* Consider video ram belongs to node 0 */
+        args.vnode_size[0] -= (info->video_memkb >> 10);
+    }
+
     ret = xc_hvm_build(ctx->xch, domid, &args);
     if (ret) {
         LOGEV(ERROR, ret, "hvm building failed");
         goto out;
     }
 
+    if (info->num_vnuma_nodes != 0) {
+        ret = libxl__vnuma_build_vmemrange_hvm(gc, domid, info, state, &args);
+        if (ret) {
+            LOGEV(ERROR, ret, "hvm build vmemranges failed");
+            goto out;
+        }
+        ret = libxl__vnuma_config_check(gc, info, state);
+        if (ret) goto out;
+        ret = set_vnuma_info(gc, domid, info, state);
+        if (ret) goto out;
+    }
     ret = hvm_build_set_params(ctx->xch, domid, info, state->store_port,
                                &state->store_mfn, state->console_port,
                                &state->console_mfn, state->store_domid,
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index 73d533a..a5513c9 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -3403,6 +3403,11 @@ int libxl__vnuma_build_vmemrange_pv(libxl__gc *gc,
                                     uint32_t domid,
                                     libxl_domain_build_info *b_info,
                                     libxl__domain_build_state *state);
+int libxl__vnuma_build_vmemrange_hvm(libxl__gc *gc,
+                                     uint32_t domid,
+                                     libxl_domain_build_info *b_info,
+                                     libxl__domain_build_state *state,
+                                     struct xc_hvm_build_args *args);
 
 _hidden int libxl__ms_vm_genid_set(libxl__gc *gc, uint32_t domid,
                                    const libxl_ms_vm_genid *id);
diff --git a/tools/libxl/libxl_vnuma.c b/tools/libxl/libxl_vnuma.c
index a72abe2..c6e949f 100644
--- a/tools/libxl/libxl_vnuma.c
+++ b/tools/libxl/libxl_vnuma.c
@@ -162,6 +162,62 @@ int libxl__vnuma_build_vmemrange_pv(libxl__gc *gc,
     return libxl__arch_vnuma_build_vmemrange(gc, domid, b_info, state);
 }
 
+/* Build vmemranges for HVM guest */
+int libxl__vnuma_build_vmemrange_hvm(libxl__gc *gc,
+                                     uint32_t domid,
+                                     libxl_domain_build_info *b_info,
+                                     libxl__domain_build_state *state,
+                                     struct xc_hvm_build_args *args)
+{
+    uint64_t hole_start, hole_end, next;
+    int i, x;
+    xen_vmemrange_t *v;
+
+    /* Derive vmemranges from vnode size and memory hole.
+     *
+     * Guest physical address space layout:
+     * [0, hole_start) [hole_start, hole_end) [hole_end, highmem_end)
+     */
+    hole_start = args->lowmem_end < args->mmio_start ?
+        args->lowmem_end : args->mmio_start;
+    hole_end = (args->mmio_start + args->mmio_size) > (1ULL << 32) ?
+        (args->mmio_start + args->mmio_size) : (1ULL << 32);
+
+    assert(state->vmemranges == NULL);
+
+    next = 0;
+    x = 0;
+    v = NULL;
+    for (i = 0; i < b_info->num_vnuma_nodes; i++) {
+        libxl_vnode_info *p = &b_info->vnuma_nodes[i];
+        uint64_t remaining = (p->mem << 20);
+
+        while (remaining > 0) {
+            uint64_t count = remaining;
+
+            if (next >= hole_start && next < hole_end)
+                next = hole_end;
+            if ((next < hole_start) && (next + remaining >= hole_start))
+                count = hole_start - next;
+
+            v = libxl__realloc(gc, v, sizeof(xen_vmemrange_t) * (x + 1));
+            v[x].start = next;
+            v[x].end = next + count;
+            v[x].flags = 0;
+            v[x].nid = i;
+
+            x++;
+            remaining -= count;
+            next += count;
+        }
+    }
+
+    state->vmemranges = v;
+    state->num_vmemranges = x;
+
+    return 0;
+}
+
 /*
  * Local variables:
  * mode: C
-- 
1.7.10.4


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