This option controls whether QEMU mmap(2) the memory backend file with
MAP_SYNC flag, which could consistent filesystem metadata for each guest
write, if MAP_SYNC flag is supported by the host kernel(Linux kernel 4.15
and later) and the backend is a file supporting DAX (e.g., file on ext4/xfs
file system mounted with '-o dax').
It can take one of following values:
- on: try to pass MAP_SYNC to mmap(2); if MAP_SYNC is not supported or
'share=off' or 'pmem!=on', QEMU will abort
- off: never pass MAP_SYNC to mmap(2)
- auto (default): if MAP_SYNC is supported and 'share=on' 'pmem=on', work as
if 'sync=on'; otherwise, work as if 'sync=off'
Signed-off-by: Haozhong Zhang <haozhong.zh...@intel.com>
Signed-off-by: Zhang Yi <yi.z.zh...@linux.intel.com>
---
backends/hostmem-file.c | 39 +++++++++++++++++++++++++++++++++++++++
docs/nvdimm.txt | 22 +++++++++++++++++++++-
include/exec/memory.h | 8 ++++++++
qemu-options.hx | 22 +++++++++++++++++++++-
4 files changed, 89 insertions(+), 2 deletions(-)
diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c
index 0dd7a90..73cf181 100644
--- a/backends/hostmem-file.c
+++ b/backends/hostmem-file.c
@@ -16,6 +16,7 @@
#include "sysemu/hostmem.h"
#include "sysemu/sysemu.h"
#include "qom/object_interfaces.h"
+#include "qapi/qapi-visit.h"
/* hostmem-file.c */
/**
@@ -36,6 +37,7 @@ struct HostMemoryBackendFile {
uint64_t align;
bool discard_data;
bool is_pmem;
+ OnOffAuto sync;
};
static void
@@ -62,6 +64,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error
**errp)
path,
backend->size, fb->align,
(backend->share ? RAM_SHARED : 0) |
+ qemu_ram_sync_flags(fb->sync) |
(fb->is_pmem ? RAM_PMEM : 0),
fb->mem_path, errp);
g_free(path);
@@ -136,6 +139,39 @@ 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",
+ name, object_get_typename(obj));
+ 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 bool file_memory_backend_get_pmem(Object *o, Error **errp)
{
return MEMORY_BACKEND_FILE(o)->is_pmem;
@@ -203,6 +239,9 @@ file_backend_class_init(ObjectClass *oc, void *data)
object_class_property_add_bool(oc, "pmem",
file_memory_backend_get_pmem, file_memory_backend_set_pmem,
&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)
diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt
index 5f158a6..d86a270 100644
--- a/docs/nvdimm.txt
+++ b/docs/nvdimm.txt
@@ -142,11 +142,31 @@ 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 could
+consistent filesystem metadata for each guest write. 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'.
+
+ - 'pmem' 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
diff --git a/include/exec/memory.h b/include/exec/memory.h
index c74c467..b398abb 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -26,6 +26,7 @@
#include "qom/object.h"
#include "qemu/rcu.h"
#include "hw/qdev-core.h"
+#include "qapi/error.h"
#define RAM_ADDR_INVALID (~(ram_addr_t)0)
@@ -136,6 +137,13 @@ typedef struct IOMMUNotifier IOMMUNotifier;
#define RAM_SYNC (RAM_SYNC_ON_OFF_AUTO_ON | RAM_SYNC_ON_OFF_AUTO_AUTO)
+static inline uint64_t qemu_ram_sync_flags(OnOffAuto v)
+{
+ return v == ON_OFF_AUTO_OFF ? RAM_SYNC_ON_OFF_AUTO_OFF :
+ v == ON_OFF_AUTO_ON ? RAM_SYNC_ON_OFF_AUTO_ON :
+ RAM_SYNC_ON_OFF_AUTO_AUTO;
+}
+
static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
IOMMUNotifierFlag flags,
hwaddr start, hwaddr end,
diff --git a/qemu-options.hx b/qemu-options.hx
index 08f8516..624f634 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3928,7 +3928,7 @@ 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.
@@ -4003,6 +4003,26 @@ If @option{pmem} is set to 'on', QEMU will take
necessary operations to
guarantee the persistence of its own writes to @option{mem-path}
(e.g. in vNVDIMM label emulation and live migration).
+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}, @option{pmem}=@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}, @option{pmem}=@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},share=@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.
--
2.7.4
