[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Qemu-devel] [PATCH v4 6/6] hostmem-file: add 'sync' option

From: Haozhong Zhang
Subject: [Qemu-devel] [PATCH v4 6/6] hostmem-file: add 'sync' option
Date: Wed, 31 Jan 2018 14:02:29 +0800

This option controls whether QEMU mmap(2) the memory backend file with
MAP_SYNC flag, which can fully guarantee the guest write persistence
to the backend, 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', QEMU will abort
 - off: never pass MAP_SYNC to mmap(2)
 - auto (default): if MAP_SYNC is supported and 'share=on', work as if
        'sync=on'; otherwise, work as if 'sync=off'

Signed-off-by: Haozhong Zhang <address@hidden>
Suggested-by: Eduardo Habkost <address@hidden>
Reviewed-by: Michael S. Tsirkin <address@hidden>
 backends/hostmem-file.c | 41 ++++++++++++++++++++++++++++++++++++++++-
 docs/nvdimm.txt         | 20 +++++++++++++++++++-
 qemu-options.hx         | 22 +++++++++++++++++++++-
 3 files changed, 80 insertions(+), 3 deletions(-)

diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c
index df06b547a6..ade80d76f1 100644
--- a/backends/hostmem-file.c
+++ b/backends/hostmem-file.c
@@ -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 
         memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
                                  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);
@@ -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)
         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)
diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt
index e903d8bb09..5e9cee5f5e 100644
--- a/docs/nvdimm.txt
+++ b/docs/nvdimm.txt
@@ -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
diff --git a/qemu-options.hx b/qemu-options.hx
index 8ce427da78..4e8ec5ed97 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3957,7 +3957,7 @@ property must be set.  These objects are placed in the
 @table @option
address@hidden -object 
address@hidden -object 
 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
address@hidden 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:
address@hidden @option
address@hidden @var{on}
+try to pass MAP_SYNC to mmap(2); if MAP_SYNC is not supported or
address@hidden@var{off}, QEMU will abort
address@hidden @var{off}
+never pass MAP_SYNC to mmap(2)
address@hidden @var{auto} (default)
+if MAP_SYNC is supported and @address@hidden, work as if
address@hidden@var{on}; otherwise, work as if @address@hidden
address@hidden table
 @item -object 
 Creates a memory backend object, which can be used to back the guest RAM.

reply via email to

[Prev in Thread] Current Thread [Next in Thread]