libxl: functions to build vmemranges for PV guest

Introduce a arch-independent routine to generate one vmemrange per
vnode. Also introduce arch-dependent routines for different
architectures because part of the process is arch-specific -- ARM has
yet have NUMA support and E820 is x86 only.

For those x86 guests who care about machine E820 map (i.e. with
e820_host=1), vnode is further split into several vmemranges to
accommodate memory holes.  A few stubs for libxl_arm.c are created.

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: Dario Faggioli <dario.faggioli@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Ian Jackson <ian.jackson@eu.citrix.com>
Cc: Dario Faggioli <dario.faggioli@citrix.com>
Cc: Elena Ufimtseva <ufimtseva@gmail.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>

diff --git a/tools/libxl/libxl_arch.h b/tools/libxl/libxl_arch.h
index d3bc1369ec31c79a00460bed7f4840de975d3167..e2490487c26b4c6c91a9372c96ea10e6b5815f28 100644 (file)
--- 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 65a762b7e484829ba67de3d7eb1c7c25cd591d60..7da254fc06d629b5f2164bb6342c9c869ae0b3bd 100644 (file)
--- a/tools/libxl/libxl_arm.c
+++ b/tools/libxl/libxl_arm.c
@@ -707,6 +707,14 @@ 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)
+{
+    return libxl__vnuma_build_vmemrange_pv_generic(gc, domid, info, state);
+}
+
 /*
  * Local variables:
  * mode: C

diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index 52c823917cd49291849b38db71292c6fb001942e..4a2f9ed851e0279029626f978ae617db6a7c0191 100644 (file)
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -3421,6 +3421,14 @@ void libxl__numa_candidate_put_nodemap(libxl__gc *gc,
 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_generic(libxl__gc *gc,
+                                            uint32_t domid,
+                                            libxl_domain_build_info *b_info,
+                                            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 89532ef76c94c68d56d44af498dcd062cdb61195..bef3cc548e30ef097b8fc75758a2a499ed361b3a 100644 (file)
--- 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" */
@@ -142,6 +143,45 @@ out:
     return rc;
 }
 
+int libxl__vnuma_build_vmemrange_pv_generic(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;
+
+    /* Generate one vmemrange for each virtual node. */
+    GCREALLOC_ARRAY(v, b_info->num_vnuma_nodes);
+    next = 0;
+    for (i = 0; i < b_info->num_vnuma_nodes; i++) {
+        libxl_vnode_info *p = &b_info->vnuma_nodes[i];
+
+        v[i].start = next;
+        v[i].end = next + (p->memkb << 10);
+        v[i].flags = 0;
+        v[i].nid = i;
+
+        next = v[i].end;
+    }
+
+    state->vmemranges = v;
+    state->num_vmemranges = i;
+
+    return 0;
+}
+
+/* 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)
+{
+    assert(state->vmemranges == NULL);
+    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 d012b4ddaebc366473f924abc760d6d0de7b2bd6..fd45ead2d6de738e071917086373f1901faef7e5 100644 (file)
--- a/tools/libxl/libxl_x86.c
+++ b/tools/libxl/libxl_x86.c
@@ -339,6 +339,84 @@ int libxl__arch_domain_finalise_hw_description(libxl__gc *gc,
     return 0;
 }
 
+/* Return 0 on success, ERROR_* on failure. */
+int libxl__arch_vnuma_build_vmemrange(libxl__gc *gc,
+                                      uint32_t domid,
+                                      libxl_domain_build_info *b_info,
+                                      libxl__domain_build_state *state)
+{
+    int nid, nr_vmemrange, rc;
+    uint32_t nr_e820, e820_count;
+    struct e820entry map[E820MAX];
+    xen_vmemrange_t *vmemranges;
+    unsigned int array_size;
+
+    /* If e820_host is not set, call the generic function */
+    if (!(b_info->type == LIBXL_DOMAIN_TYPE_PV &&
+          libxl_defbool_val(b_info->u.pv.e820_host)))
+        return libxl__vnuma_build_vmemrange_pv_generic(gc, domid, b_info,
+                                                       state);
+
+    assert(state->vmemranges == NULL);
+
+    nr_e820 = E820MAX;
+    rc = e820_host_sanitize(gc, b_info, map, &nr_e820);
+    if (rc) goto out;
+
+    e820_count = 0;
+    nr_vmemrange = 0;
+    vmemranges = NULL;
+    array_size = 0;
+    for (nid = 0; nid < b_info->num_vnuma_nodes; nid++) {
+        libxl_vnode_info *p = &b_info->vnuma_nodes[nid];
+        uint64_t remaining_bytes = (p->memkb << 10), bytes;
+
+        while (remaining_bytes > 0) {
+            if (e820_count >= nr_e820) {
+                rc = ERROR_NOMEM;
+                goto out;
+            }
+
+            /* Skip non RAM region */
+            if (map[e820_count].type != E820_RAM) {
+                e820_count++;
+                continue;
+            }
+
+            if (nr_vmemrange >= array_size) {
+                array_size += 32;
+                GCREALLOC_ARRAY(vmemranges, array_size);
+            }
+
+            bytes = map[e820_count].size >= remaining_bytes ?
+                remaining_bytes : map[e820_count].size;
+
+            vmemranges[nr_vmemrange].start = map[e820_count].addr;
+            vmemranges[nr_vmemrange].end = map[e820_count].addr + bytes;
+
+            if (map[e820_count].size >= remaining_bytes) {
+                map[e820_count].addr += bytes;
+                map[e820_count].size -= bytes;
+            } else {
+                e820_count++;
+            }
+
+            remaining_bytes -= bytes;
+
+            vmemranges[nr_vmemrange].flags = 0;
+            vmemranges[nr_vmemrange].nid = nid;
+            nr_vmemrange++;
+        }
+    }
+
+    state->vmemranges = vmemranges;
+    state->num_vmemranges = nr_vmemrange;
+
+    rc = 0;
+out:
+    return rc;
+}
+
 /*
  * Local variables:
  * mode: C