[Xen-devel] [PATCH v4 08/21] libxl: functions to build vmemranges for PV guest

[Wei Liu <wei.liu2@xxxxxxxxxx>]

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@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 v4:
1. Adapt to new interface.
2. Address Ian Jackson's comments.

Changes in v3:
1. Rewrite commit log.
---
 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      |   76 ++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 130 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 65a762b..d3968a7 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 39356ba..73d533a 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -3399,6 +3399,11 @@ 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 4edfaa4..0189a4b 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" */
@@ -128,6 +129,39 @@ 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];
+
+        GCREALLOC_ARRAY(v, i+1);
+
+        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 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 d012b4d..4841fef 100644
--- a/tools/libxl/libxl_x86.c
+++ b/tools/libxl/libxl_x86.c
@@ -339,6 +339,82 @@ 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 nid, nr_vmemrange, rc;
+    uint32_t nr_e820, e820_count;
+    struct e820entry map[E820MAX];
+    xen_vmemrange_t *vmemranges;
+
+    /* 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;
+
+    e820_count = 0;
+    nr_vmemrange = 0;
+    vmemranges = NULL;
+    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;
+            }
+
+            GCREALLOC_ARRAY(vmemranges, nr_vmemrange+1);
+
+            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
-- 
1.7.10.4


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