[V5,05/23] machine: aux-ram-share option

Commit Message

Steve Sistare Dec. 24, 2024, 4:16 p.m. UTC

Allocate auxilliary guest RAM as an anonymous file that is shareable
with an external process.  This option applies to memory allocated as
a side effect of creating various devices. It does not apply to
memory-backend-objects, whether explicitly specified on the command
line, or implicitly created by the -m command line option.

This option is intended to support new migration modes, in which the
memory region can be transferred in place to a new QEMU process, by sending
the memfd file descriptor to the process.  Memory contents are preserved,
and if the mode also transfers device descriptors, then pages that are
locked in memory for DMA remain locked.  This behavior is a pre-requisite
for supporting vfio, vdpa, and iommufd devices with the new modes.

Signed-off-by: Steve Sistare <[e-mail]>
Reviewed-by: Peter Xu <[e-mail]>
---
 hw/core/machine.c   | 20 ++++++++++++++++++++
 include/hw/boards.h |  1 +
 qemu-options.hx     | 11 +++++++++++
 system/physmem.c    |  3 +++
 4 files changed, 35 insertions(+)

Patch

diff --git a/hw/core/machine.c b/hw/core/machine.c
index c949af9..75c8cba 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -455,6 +455,20 @@  static void machine_set_mem_merge(Object *obj, bool value, Error **errp)
     ms->mem_merge = value;
 }
 
+static bool machine_get_aux_ram_share(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->aux_ram_share;
+}
+
+static void machine_set_aux_ram_share(Object *obj, bool value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->aux_ram_share = value;
+}
+
 static bool machine_get_usb(Object *obj, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
@@ -1160,6 +1174,12 @@  static void machine_class_init(ObjectClass *oc, void *data)
     object_class_property_set_description(oc, "mem-merge",
         "Enable/disable memory merge support");
 
+#ifdef CONFIG_POSIX
+    object_class_property_add_bool(oc, "aux-ram-share",
+                                   machine_get_aux_ram_share,
+                                   machine_set_aux_ram_share);
+#endif
+
     object_class_property_add_bool(oc, "usb",
         machine_get_usb, machine_set_usb);
     object_class_property_set_description(oc, "usb",
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 2ad711e..e1f41b2 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -410,6 +410,7 @@  struct MachineState {
     bool enable_graphics;
     ConfidentialGuestSupport *cgs;
     HostMemoryBackend *memdev;
+    bool aux_ram_share;
     /*
      * convenience alias to ram_memdev_id backend memory region
      * or to numa container memory region
diff --git a/qemu-options.hx b/qemu-options.hx
index cc694d3..b1f56b7 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -38,6 +38,9 @@  DEF("machine", HAS_ARG, QEMU_OPTION_machine, \
     "                nvdimm=on|off controls NVDIMM support (default=off)\n"
     "                memory-encryption=@var{} memory encryption object to use (default=none)\n"
     "                hmat=on|off controls ACPI HMAT support (default=off)\n"
+#ifdef CONFIG_POSIX
+    "                aux-ram-share=on|off allocate auxiliary guest RAM as shared (default: off)\n"
+#endif
     "                memory-backend='backend-id' specifies explicitly provided backend for main RAM (default=none)\n"
     "                cxl-fmw.0.targets.0=firsttarget,cxl-fmw.0.targets.1=secondtarget,cxl-fmw.0.size=size[,cxl-fmw.0.interleave-granularity=granularity]\n",
     QEMU_ARCH_ALL)
@@ -101,6 +104,14 @@  SRST
         Enables or disables ACPI Heterogeneous Memory Attribute Table
         (HMAT) support. The default is off.
 
+    ``aux-ram-share=on|off``
+        Allocate auxiliary guest RAM as an anonymous file that is
+        shareable with an external process.  This option applies to
+        memory allocated as a side effect of creating various devices.
+        It does not apply to memory-backend-objects, whether explicitly
+        specified on the command line, or implicitly created by the -m
+        command line option.  The default is off.
+
     ``memory-backend='id'``
         An alternative to legacy ``-mem-path`` and ``mem-prealloc`` options.
         Allows to use a memory backend as main RAM.
diff --git a/system/physmem.c b/system/physmem.c
index eb1c3a7..0e629ee 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -2112,6 +2112,9 @@  RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
 
 #ifdef CONFIG_POSIX         /* ignore RAM_SHARED for Windows */
     if (!host) {
+        if (!share_flags && current_machine->aux_ram_share) {
+            ram_flags |= RAM_SHARED;
+        }
         if (ram_flags & RAM_SHARED) {
             const char *name = memory_region_name(mr);
             int fd = qemu_ram_get_shared_fd(name, errp);