[Libguestfs] [PATCH v3] launch: direct: Add DAX root filesystem support.

[Richard W.M. Jones]

Allow the appliance / root filesystem to be placed on a virtual NVDIMM
and accessed directly by the guest kernel (DAX).

This requires corresponding changes in supermin.
---
 src/launch-direct.c | 66 ++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 53 insertions(+), 13 deletions(-)

diff --git a/src/launch-direct.c b/src/launch-direct.c
index a6f06ee..daeff67 100644
--- a/src/launch-direct.c
+++ b/src/launch-direct.c
@@ -235,6 +235,7 @@ launch_direct (guestfs_h *g, void *datav, const char *arg)
   struct hv_param *hp;
   bool has_kvm;
   int force_tcg;
+  bool dax;
   const char *cpu_model;
 
   /* At present you must add drives before starting the appliance.  In
@@ -374,15 +375,29 @@ launch_direct (guestfs_h *g, void *datav, const char *arg)
     warning (g, "qemu debugging is enabled, connect gdb to tcp::1234 to begin");
   }
 
+  /* Can we use DAX? */
+#ifdef __x86_64__
+  dax = guestfs_int_version_ge (&data->qemu_version, 2, 6, 0) &&
+    guestfs_int_qemu_supports_device (g, data->qemu_data, "nvdimm");
+#else
+  dax = false;
+#endif
+
   ADD_CMDLINE ("-machine");
   ADD_CMDLINE_PRINTF (
 #ifdef MACHINE_TYPE
                       MACHINE_TYPE ","
+                      "%s"
+#elif __x86_64__
+                      "pc,%s"
+#else
+                      "%s"
 #endif
 #ifdef __aarch64__
                       "gic-version=host,"
 #endif
                       "accel=%s",
+                      dax ? "nvdimm," : "",
                       !force_tcg ? "kvm:tcg" : "tcg");
 
   cpu_model = guestfs_int_get_cpu_model (has_kvm && !force_tcg);
@@ -397,7 +412,10 @@ launch_direct (guestfs_h *g, void *datav, const char *arg)
   }
 
   ADD_CMDLINE ("-m");
-  ADD_CMDLINE_PRINTF ("%d", g->memsize);
+  if (dax)
+    ADD_CMDLINE_PRINTF ("%d,maxmem=32G,slots=32", g->memsize);
+  else
+    ADD_CMDLINE_PRINTF ("%d", g->memsize);
 
   /* Force exit instead of reboot on panic */
   ADD_CMDLINE ("-no-reboot");
@@ -551,21 +569,43 @@ launch_direct (guestfs_h *g, void *datav, const char *arg)
 
   /* Add the ext2 appliance drive (after all the drives). */
   if (has_appliance_drive) {
-    ADD_CMDLINE ("-drive");
-    ADD_CMDLINE_PRINTF ("file=%s,snapshot=on,id=appliance,"
-                        "cache=unsafe,if=none,format=raw",
-                        appliance);
+    if (dax) {
+      struct stat statbuf;
 
-    if (virtio_scsi) {
-      ADD_CMDLINE ("-device");
-      ADD_CMDLINE ("scsi-hd,drive=appliance");
-    }
-    else {
+      if (stat (appliance, &statbuf) == -1) {
+        perrorf (g, "stat: %s", appliance);
+        goto cleanup0;
+      }
+
+      ADD_CMDLINE ("-object");
+      /* share=off corresponds to mmap MAP_PRIVATE inside qemu, so
+       * this should not affect the underlying file.  IOW parallel
+       * access should be fine.
+       */
+      ADD_CMDLINE_PRINTF ("memory-backend-file,id=mem1,share=off,"
+                          "mem-path=%s,size=%" PRIu64 "b",
+                          appliance, (uint64_t) statbuf.st_size);
       ADD_CMDLINE ("-device");
-      ADD_CMDLINE (VIRTIO_BLK ",drive=appliance");
-    }
+      ADD_CMDLINE ("nvdimm,memdev=mem1,id=nv1");
 
-    appliance_dev = make_appliance_dev (g, virtio_scsi);
+      appliance_dev = safe_strdup (g, "/dev/pmem0");
+    } else {
+      ADD_CMDLINE ("-drive");
+      ADD_CMDLINE_PRINTF ("file=%s,snapshot=on,id=appliance,"
+                          "cache=unsafe,if=none,format=raw",
+                          appliance);
+
+      if (virtio_scsi) {
+        ADD_CMDLINE ("-device");
+        ADD_CMDLINE ("scsi-hd,drive=appliance");
+      }
+      else {
+        ADD_CMDLINE ("-device");
+        ADD_CMDLINE (VIRTIO_BLK ",drive=appliance");
+      }
+
+      appliance_dev = make_appliance_dev (g, virtio_scsi);
+    }
   }
 
   /* Create the virtio serial bus. */
-- 
2.7.4