This option controls will mmap the memory backend file with MAP_SYNC flag,
which can ensure filesystem metadata consistent even after a system crash
or power failure, 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 not pass this flags to
mmap(2)
- off: default, never pass MAP_SYNC to mmap(2)
Signed-off-by: Haozhong Zhang <haozhong.zh...@intel.com>
Signed-off-by: Zhang Yi <yi.z.zh...@linux.intel.com>
---
backends/hostmem-file.c | 28 ++++++++++++++++++++++++++++
docs/nvdimm.txt | 23 ++++++++++++++++++++++-
exec.c | 2 +-
include/exec/memory.h | 4 ++++
include/exec/ram_addr.h | 1 +
include/qemu/mmap-alloc.h | 1 +
qemu-options.hx | 19 ++++++++++++++++++-
util/mmap-alloc.c | 4 ++--
8 files changed, 77 insertions(+), 5 deletions(-)
diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c
index 0dd7a90..3d39032 100644
--- a/backends/hostmem-file.c
+++ b/backends/hostmem-file.c
@@ -36,6 +36,7 @@ struct HostMemoryBackendFile {
uint64_t align;
bool discard_data;
bool is_pmem;
+ bool sync;
};
static void
@@ -62,6 +63,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error
**errp)
path,
backend->size, fb->align,
(backend->share ? RAM_SHARED : 0) |
+ (fb->sync ? RAM_SYNC : 0) |
(fb->is_pmem ? RAM_PMEM : 0),
fb->mem_path, errp);
g_free(path);
@@ -136,6 +138,29 @@ static void file_memory_backend_set_align(Object *o,
Visitor *v,
error_propagate(errp, local_err);
}
+static bool file_memory_backend_get_sync(Object *o, Error **errp)
+{
+ return MEMORY_BACKEND_FILE(o)->sync;
+}
+
+static void file_memory_backend_set_sync(
+ Object *obj, bool value, Error **errp)
+{
+ HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+ HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(obj);
+
+ if (host_memory_backend_mr_inited(backend)) {
+ error_setg(errp, "cannot change property sync of %s",
+ object_get_typename(obj));
+ goto out;
+ }
+
+ fb->sync = value;
+
+ out:
+ return;
+}
+
static bool file_memory_backend_get_pmem(Object *o, Error **errp)
{
return MEMORY_BACKEND_FILE(o)->is_pmem;
@@ -203,6 +228,9 @@ 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_bool(oc, "sync",
+ file_memory_backend_get_sync, file_memory_backend_set_sync,
+ &error_abort);
}
static void file_backend_instance_finalize(Object *o)
diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt
index 5f158a6..30db458 100644
--- a/docs/nvdimm.txt
+++ b/docs/nvdimm.txt
@@ -142,11 +142,32 @@ 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 ensure
+filesystem metadata consistent even after a system crash or power
+failure. 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 on, 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/exec.c b/exec.c
index e92a7da..dc4d180 100644
--- a/exec.c
+++ b/exec.c
@@ -2241,7 +2241,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size,
MemoryRegion *mr,
int64_t file_size;
/* Just support these ram flags by now. */
- assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) == 0);
+ assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_SYNC)) == 0);
if (xen_enabled()) {
error_setg(errp, "-mem-path not supported with Xen");
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 6e30c23..9297b1c 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 +137,9 @@ typedef unsigned QEMU_BITWISE QemuMmapFlags;
/* RAM is a persistent kind memory */
#define RAM_PMEM ((QEMU_FORCE QemuMmapFlags) (1 << 5))
+/* RAM can be mmap by a MAP_SYNC flag */
+#define RAM_SYNC ((QEMU_FORCE QemuMmapFlags) (1 << 6))
+
static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
IOMMUNotifierFlag flags,
hwaddr start, hwaddr end,
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index 9ecd911..d239ce7 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -87,6 +87,7 @@ long qemu_getrampagesize(void);
* or bit-or of following values
* - RAM_SHARED: mmap the backing file or device with MAP_SHARED
* - RAM_PMEM: the backend @mem_path or @fd is persistent memory
+ * - RAM_SYNC: mmap with MAP_SYNC flag
* Other bits are ignored.
* @mem_path or @fd: specify the backing file or device
* @errp: pointer to Error*, to store an error if it happens
diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h
index 6fe6ed4..1755a8b 100644
--- a/include/qemu/mmap-alloc.h
+++ b/include/qemu/mmap-alloc.h
@@ -18,6 +18,7 @@ size_t qemu_mempath_getpagesize(const char *mem_path);
* @flags: specifies additional properties of the mapping, which can be one or
* bit-or of following values
* - RAM_SHARED: mmap with MAP_SHARED flag
+ * - RAM_SYNC: mmap with MAP_SYNC flag
* Other bits are ignored.
*
* Return:
diff --git a/qemu-options.hx b/qemu-options.hx
index 08f8516..0f51d08 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}
Creates a memory file backend object, which can be used to back
the guest RAM with huge pages.
@@ -4003,6 +4003,23 @@ 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 ensure the file metadata is in sync 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 not pass
+this flags to kernel.
+
+@item @var{off} (default)
+never pass MAP_SYNC to mmap(2)
+@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.
diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index a9d5e56..33a7639 100644
--- a/util/mmap-alloc.c
+++ b/util/mmap-alloc.c
@@ -99,7 +99,7 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align,
uint32_t flags)
void *ptr = mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
#endif
bool shared = flags & RAM_SHARED;
- bool is_pmem = flags & RAM_PMEM;
+ bool is_pmemsync = (flags & RAM_PMEM) && (flags & RAM_SYNC);
int mmap_xflags = 0;
size_t offset;
void *ptr1;
@@ -111,7 +111,7 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align,
uint32_t flags)
assert(is_power_of_2(align));
/* Always align to host page size */
assert(align >= getpagesize());
- if (shared && is_pmem) {
+ if (shared && is_pmemsync) {
mmap_xflags |= MAP_SYNC;
}
--
2.7.4
