[Xen-devel] [PATCH v2 09/19] libxl: functions to build vmemranges for PV guest

[Wei Liu <wei.liu2@xxxxxxxxxx>]

One vmemrange is generated for each vnode. And for those guests who care
about machine E820 map, vmemranges are further split to accommodate
memory holes.

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>
---
 tools/libxl/libxl_arch.h     |    6 ++++
 tools/libxl/libxl_arm.c      |    9 +++++
 tools/libxl/libxl_internal.h |    5 +++
 tools/libxl/libxl_vnuma.c    |   34 +++++++++++++++++++
 tools/libxl/libxl_x86.c      |   74 ++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 128 insertions(+)

diff --git a/tools/libxl/libxl_arch.h b/tools/libxl/libxl_arch.h
index d3bc136..e249048 100644
--- a/tools/libxl/libxl_arch.h
+++ b/tools/libxl/libxl_arch.h
@@ -27,4 +27,10 @@ int libxl__arch_domain_init_hw_description(libxl__gc *gc,
 int libxl__arch_domain_finalise_hw_description(libxl__gc *gc,
                                       libxl_domain_build_info *info,
                                       struct xc_dom_image *dom);
+
+/* build vNUMA vmemrange with arch specific information */
+int libxl__arch_vnuma_build_vmemrange(libxl__gc *gc,
+                                      uint32_t domid,
+                                      libxl_domain_build_info *b_info,
+                                      libxl__domain_build_state *state);
 #endif
diff --git a/tools/libxl/libxl_arm.c b/tools/libxl/libxl_arm.c
index 34d21f5..1f1bc24 100644
--- a/tools/libxl/libxl_arm.c
+++ b/tools/libxl/libxl_arm.c
@@ -707,6 +707,15 @@ int libxl__arch_domain_finalise_hw_description(libxl__gc 
*gc,
     return 0;
 }
 
+int libxl__arch_vnuma_build_vmemrange(libxl__gc *gc,
+                                      uint32_t domid,
+                                      libxl_domain_build_info *info,
+                                      libxl__domain_build_state *state)
+{
+    /* Don't touch anything. */
+    return 0;
+}
+
 /*
  * Local variables:
  * mode: C
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index 88da7ba..1678715 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -3397,6 +3397,11 @@ int libxl__vnuma_config_check(libxl__gc *gc,
                               const libxl_domain_build_info *b_info,
                               const libxl__domain_build_state *state);
 
+int libxl__vnuma_build_vmemrange_pv(libxl__gc *gc,
+                                    uint32_t domid,
+                                    libxl_domain_build_info *b_info,
+                                    libxl__domain_build_state *state);
+
 _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 d92376d..b8d9268 100644
--- a/tools/libxl/libxl_vnuma.c
+++ b/tools/libxl/libxl_vnuma.c
@@ -14,6 +14,7 @@
  */
 #include "libxl_osdeps.h" /* must come before any other headers */
 #include "libxl_internal.h"
+#include "libxl_arch.h"
 #include <stdlib.h>
 
 /* Sort vmemranges in ascending order with "start" */
@@ -129,6 +130,39 @@ out:
     return rc;
 }
 
+/* Build vmemranges for PV guest */
+int libxl__vnuma_build_vmemrange_pv(libxl__gc *gc,
+                                    uint32_t domid,
+                                    libxl_domain_build_info *b_info,
+                                    libxl__domain_build_state *state)
+{
+    int i;
+    uint64_t next;
+    xen_vmemrange_t *v = NULL;
+
+    assert(state->vmemranges == NULL);
+
+    /* Generate one vmemrange for each virtual node. */
+    next = 0;
+    for (i = 0; i < b_info->num_vnuma_nodes; i++) {
+        libxl_vnode_info *p = &b_info->vnuma_nodes[i];
+
+        v = libxl__realloc(gc, v, sizeof(*v) * (i+1));
+
+        v[i].start = next;
+        v[i].end = next + (p->mem << 20); /* mem is in MiB */
+        v[i].flags = 0;
+        v[i].nid = i;
+
+        next = v[i].end;
+    }
+
+    state->vmemranges = v;
+    state->num_vmemranges = i;
+
+    return libxl__arch_vnuma_build_vmemrange(gc, domid, b_info, state);
+}
+
 /*
  * Local variables:
  * mode: C
diff --git a/tools/libxl/libxl_x86.c b/tools/libxl/libxl_x86.c
index e959e37..2018afc 100644
--- a/tools/libxl/libxl_x86.c
+++ b/tools/libxl/libxl_x86.c
@@ -338,6 +338,80 @@ int libxl__arch_domain_finalise_hw_description(libxl__gc 
*gc,
     return 0;
 }
 
+int libxl__arch_vnuma_build_vmemrange(libxl__gc *gc,
+                                      uint32_t domid,
+                                      libxl_domain_build_info *b_info,
+                                      libxl__domain_build_state *state)
+{
+    int i, x, n, rc;
+    uint32_t nr_e820;
+    struct e820entry map[E820MAX];
+    xen_vmemrange_t *v;
+
+    /* Only touch vmemranges if it's PV guest and e820_host is true */
+    if (!(b_info->type == LIBXL_DOMAIN_TYPE_PV &&
+          libxl_defbool_val(b_info->u.pv.e820_host))) {
+        rc = 0;
+        goto out;
+    }
+
+    rc = e820_host_sanitize(gc, b_info, map, &nr_e820);
+    if (rc) goto out;
+
+    /* Ditch old vmemranges and start with host E820 map. Note, memory
+     * was gc allocated.
+     */
+    state->vmemranges = NULL;
+    state->num_vmemranges = 0;
+
+    n = 0; /* E820 counter */
+    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) {
+            if (n >= nr_e820) {
+                rc = ERROR_FAIL;
+                goto out;
+            }
+
+            /* Skip non RAM region */
+            if (map[n].type != E820_RAM) {
+                n++;
+                continue;
+            }
+
+            v = libxl__realloc(gc, v, sizeof(xen_vmemrange_t) * (x+1));
+
+            if (map[n].size >= remaining) {
+                v[x].start = map[n].addr;
+                v[x].end = map[n].addr + remaining;
+                map[n].addr += remaining;
+                map[n].size -= remaining;
+                remaining = 0;
+            } else {
+                v[x].start = map[n].addr;
+                v[x].end = map[n].addr + map[n].size;
+                remaining -= map[n].size;
+                n++;
+            }
+
+            v[x].flags = 0;
+            v[x].nid = i;
+            x++;
+        }
+    }
+
+    state->vmemranges = v;
+    state->num_vmemranges = x;
+
+    rc = 0;
+out:
+    return rc;
+}
+
 /*
  * Local variables:
  * mode: C
-- 
1.7.10.4


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