[Qemu-devel] [PATCH V6 3/7] hostmem-file: add the 'pmem' option

[junyan . he]

From: Junyan He <address@hidden>

When QEMU emulates vNVDIMM labels and migrates vNVDIMM devices, it
needs to know whether the backend storage is a real persistent memory,
in order to decide whether special operations should be performed to
ensure the data persistence.

This boolean option 'pmem' allows users to specify whether the backend
storage of memory-backend-file is a real persistent memory. If
'pmem=on', QEMU will set the flag RAM_PMEM in the RAM block of the
corresponding memory region.

Signed-off-by: Junyan He <address@hidden>
Signed-off-by: Haozhong Zhang <address@hidden>
---
 backends/hostmem-file.c | 27 ++++++++++++++++++++++++++-
 docs/nvdimm.txt         | 14 ++++++++++++++
 exec.c                  |  9 +++++++++
 include/exec/memory.h   |  6 ++++++
 include/exec/ram_addr.h |  3 +++
 qemu-options.hx         |  7 +++++++
 6 files changed, 65 insertions(+), 1 deletion(-)

diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c
index 34c68bb..ccca7a1 100644
--- a/backends/hostmem-file.c
+++ b/backends/hostmem-file.c
@@ -34,6 +34,7 @@ struct HostMemoryBackendFile {
     bool discard_data;
     char *mem_path;
     uint64_t align;
+    bool is_pmem;
 };
 
 static void
@@ -59,7 +60,8 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error 
**errp)
         memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
                                  path,
                                  backend->size, fb->align,
-                                 backend->share ? RAM_SHARED : 0,
+                                 (backend->share ? RAM_SHARED : 0) |
+                                 (fb->is_pmem ? RAM_PMEM : 0),
                                  fb->mem_path, errp);
         g_free(path);
     }
@@ -131,6 +133,26 @@ static void file_memory_backend_set_align(Object *o, 
Visitor *v,
     error_propagate(errp, local_err);
 }
 
+static bool file_memory_backend_get_pmem(Object *o, Error **errp)
+{
+    return MEMORY_BACKEND_FILE(o)->is_pmem;
+}
+
+static void file_memory_backend_set_pmem(Object *o, bool value, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(o);
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+
+    if (host_memory_backend_mr_inited(backend)) {
+        error_setg(errp, "cannot change property 'pmem' of %s '%s'",
+                   object_get_typename(o),
+                   object_get_canonical_path_component(OBJECT(backend)));
+        return;
+    }
+
+    fb->is_pmem = value;
+}
+
 static void file_backend_unparent(Object *obj)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
@@ -162,6 +184,9 @@ 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_bool(oc, "pmem",
+        file_memory_backend_get_pmem, file_memory_backend_set_pmem,
+        &error_abort);
 }
 
 static void file_backend_instance_finalize(Object *o)
diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt
index e903d8b..bcb2032 100644
--- a/docs/nvdimm.txt
+++ b/docs/nvdimm.txt
@@ -153,3 +153,17 @@ guest NVDIMM region mapping structure.  This unarmed flag 
indicates
 guest software that this vNVDIMM device contains a region that cannot
 accept persistent writes. In result, for example, the guest Linux
 NVDIMM driver, marks such vNVDIMM device as read-only.
+
+If the vNVDIMM backend is on the host persistent memory that can be
+accessed in SNIA NVM Programming Model [1] (e.g., Intel NVDIMM), it's
+suggested to set the 'pmem' option of memory-backend-file to 'on'. When
+'pmem=on' and QEMU is built with libpmem [2] support (configured with
+--enable-libpmem), QEMU will take necessary operations to guarantee
+the persistence of its own writes to the vNVDIMM backend (e.g., in
+vNVDIMM label emulation and live migration).
+
+References
+----------
+
+[1] SNIA NVM Programming Model: 
https://www.snia.org/sites/default/files/technical_work/final/NVMProgrammingModel_v1.2.pdf
+[2] PMDK: http://pmem.io/pmdk/
diff --git a/exec.c b/exec.c
index f2082fa..f066705 100644
--- a/exec.c
+++ b/exec.c
@@ -2061,6 +2061,9 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, 
MemoryRegion *mr,
     Error *local_err = NULL;
     int64_t file_size;
 
+    /* Just support these ram flags by now. */
+    assert(ram_flags == 0 || (ram_flags & (RAM_SHARED | RAM_PMEM)));
+
     if (xen_enabled()) {
         error_setg(errp, "-mem-path not supported with Xen");
         return NULL;
@@ -3971,6 +3974,11 @@ err:
     return ret;
 }
 
+bool ramblock_is_pmem(RAMBlock *rb)
+{
+    return rb->flags & RAM_PMEM;
+}
+
 #endif
 
 void page_size_init(void)
@@ -4069,3 +4077,4 @@ void mtree_print_dispatch(fprintf_function mon, void *f,
 }
 
 #endif
+
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 3b68a43..6523512 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -119,6 +119,11 @@ typedef struct IOMMUNotifier IOMMUNotifier;
  */
 #define RAM_UF_ZEROPAGE (1 << 3)
 
+/* QEMU_RAM_PMEM is available on this RAMBlock to specify that the
+ * memory is a persistent kind memory.
+ */
+#define RAM_PMEM (1 << 4)
+
 static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
                                        IOMMUNotifierFlag flags,
                                        hwaddr start, hwaddr end)
@@ -611,6 +616,7 @@ void memory_region_init_resizeable_ram(MemoryRegion *mr,
  * @ram_flags: specify properties of this memory region, which can be one or
  *             bit-or of following values:
  *             - RAM_SHARED: memory must be mmaped with the MAP_SHARED flag
+ *             - RAM_PMEM: the backend @path is persistent memory
  *             Other bits are ignored.
  * @path: the path in which to allocate the RAM.
  * @errp: pointer to Error*, to store an error if it happens.
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index b478455..722bd1a 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -70,6 +70,8 @@ static inline unsigned long int 
ramblock_recv_bitmap_offset(void *host_addr,
     return host_addr_offset >> TARGET_PAGE_BITS;
 }
 
+bool ramblock_is_pmem(RAMBlock *rb);
+
 long qemu_getrampagesize(void);
 unsigned long last_ram_page(void);
 
@@ -84,6 +86,7 @@ unsigned long last_ram_page(void);
  *  @ram_flags: specify the properties of the ram block, which can be one
  *              or bit-or of following values
  *              - RAM_SHARED: mmap the back file or device with MAP_SHARED
+ *              - RAM_PMEM: the backend @mem_path or @fd is persistent memory
  *              Other bits are ignored.
  *  @mem_path or @fd: specify the back file or device
  *  @errp: pointer to Error*, to store an error if it happens
diff --git a/qemu-options.hx b/qemu-options.hx
index 2f61ea4..228e154 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4042,6 +4042,13 @@ 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{pmem} option specifies whether the backend store specified
+by @option{mem-path} is on the persistent memory that can be accessed
+in the SNIA NVM programming model (e.g. Intel NVDIMM).
+If @address@hidden, 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).
+
 @item -object 
memory-backend-ram,address@hidden,address@hidden|off},address@hidden|off},address@hidden|off},address@hidden|off},address@hidden,address@hidden,address@hidden|preferred|bind|interleave}
 
 Creates a memory backend object, which can be used to back the guest RAM.
-- 
2.7.4