@@ -15,6 +15,7 @@
#include "sysemu/hostmem.h"
#include "sysemu/sysemu.h"
#include "qom/object_interfaces.h"
+#include "qapi-visit.h"
/* hostmem-file.c */
/**
@@ -35,6 +36,7 @@ struct HostMemoryBackendFile {
bool discard_data;
char *mem_path;
uint64_t align;
+ OnOffAuto sync;
};
static void
@@ -60,7 +62,8 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
path,
backend->size, fb->align,
- fb->share ? QEMU_RAM_SHARE : 0,
+ (fb->share ? QEMU_RAM_SHARE : 0) |
+ qemu_ram_sync_flags(fb->sync),
fb->mem_path, errp);
g_free(path);
}
@@ -154,6 +157,39 @@ static void file_memory_backend_set_align(Object *o, Visitor *v,
error_propagate(errp, local_err);
}
+static void file_memory_backend_get_sync(
+ Object *obj, Visitor *v, const char *name, void *opaque, Error **errp)
+{
+ HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(obj);
+ OnOffAuto value = fb->sync;
+
+ visit_type_OnOffAuto(v, name, &value, errp);
+}
+
+static void file_memory_backend_set_sync(
+ Object *obj, Visitor *v, const char *name, void *opaque, Error **errp)
+{
+ HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+ HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(obj);
+ Error *local_err = NULL;
+ OnOffAuto value;
+
+ if (host_memory_backend_mr_inited(backend)) {
+ error_setg(&local_err, "cannot change property '%s' of %s '%s'",
+ name, object_get_typename(obj), backend->id);
+ goto out;
+ }
+
+ visit_type_OnOffAuto(v, name, &value, &local_err);
+ if (local_err) {
+ goto out;
+ }
+ fb->sync = value;
+
+ out:
+ error_propagate(errp, local_err);
+}
+
static void file_backend_unparent(Object *obj)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
@@ -188,6 +224,9 @@ file_backend_class_init(ObjectClass *oc, void *data)
file_memory_backend_get_align,
file_memory_backend_set_align,
NULL, NULL, &error_abort);
+ object_class_property_add(oc, "sync", "OnOffAuto",
+ file_memory_backend_get_sync, file_memory_backend_set_sync,
+ NULL, NULL, &error_abort);
}
static void file_backend_instance_finalize(Object *o)
@@ -142,11 +142,29 @@ backend of vNVDIMM:
Guest Data Persistence
----------------------
+vNVDIMM is designed and implemented to guarantee the guest data
+persistence on the backends even on the host crash and power
+failures. However, there are still some requirements and limitations
+as explained below.
+
Though QEMU supports multiple types of vNVDIMM backends on Linux,
-currently the only one that can guarantee the guest write persistence
+if MAP_SYNC is not supported by the host kernel and the backends,
+the only backend that can guarantee the guest write persistence
is the device DAX on the real NVDIMM device (e.g., /dev/dax0.0), to
which all guest access do not involve any host-side kernel cache.
+mmap(2) flag MAP_SYNC is added since Linux kernel 4.15. On such
+systems, QEMU can mmap(2) the backend with MAP_SYNC, which can
+guarantee the guest write persistence to vNVDIMM. Besides the host
+kernel support, enabling MAP_SYNC in QEMU also requires:
+
+ - the backend is a file supporting DAX, e.g., a file on an ext4 or
+ xfs file system mounted with '-o dax',
+
+ - 'sync' option of memory-backend-file is not 'off', and
+
+ - 'share' option of memory-backend-file is 'on'.
+
When using other types of backends, it's suggested to set 'unarmed'
option of '-device nvdimm' to 'on', which sets the unarmed flag of the
guest NVDIMM region mapping structure. This unarmed flag indicates
@@ -3957,7 +3957,7 @@ property must be set. These objects are placed in the
@table @option
-@item -object memory-backend-file,id=@var{id},size=@var{size},mem-path=@var{dir},share=@var{on|off},discard-data=@var{on|off},merge=@var{on|off},dump=@var{on|off},prealloc=@var{on|off},host-nodes=@var{host-nodes},policy=@var{default|preferred|bind|interleave},align=@var{align}
+@item -object memory-backend-file,id=@var{id},size=@var{size},mem-path=@var{dir},share=@var{on|off},discard-data=@var{on|off},merge=@var{on|off},dump=@var{on|off},prealloc=@var{on|off},host-nodes=@var{host-nodes},policy=@var{default|preferred|bind|interleave},align=@var{align},sync=@var{on|off|auto}
Creates a memory file backend object, which can be used to back
the guest RAM with huge pages.
@@ -4017,6 +4017,26 @@ requires an alignment different than the default one used by QEMU, eg
the device DAX /dev/dax0.0 requires 2M alignment rather than 4K. In
such cases, users can specify the required alignment via this option.
+The @option{sync} option specifies whether QEMU mmap(2) @option{mem-path}
+with MAP_SYNC flag, which can guarantee the guest write persistence to
+@option{mem-path} even on the host crash and power failures. MAP_SYNC
+requires supports from both the host kernel (since Linux kernel 4.15)
+and @option{mem-path} (only files supporting DAX). It can take one of
+following values:
+
+@table @option
+@item @var{on}
+try to pass MAP_SYNC to mmap(2); if MAP_SYNC is not supported or
+@option{share}=@var{off}, QEMU will abort
+
+@item @var{off}
+never pass MAP_SYNC to mmap(2)
+
+@item @var{auto} (default)
+if MAP_SYNC is supported and @option{share}=@var{on}, work as if
+@option{sync}=@var{on}; otherwise, work as if @option{sync}=@var{off}
+@end table
+
@item -object memory-backend-ram,id=@var{id},merge=@var{on|off},dump=@var{on|off},prealloc=@var{on|off},size=@var{size},host-nodes=@var{host-nodes},policy=@var{default|preferred|bind|interleave}
Creates a memory backend object, which can be used to back the guest RAM.