hostmem-file: add "align" option

When mmap(2) the backend files, QEMU uses the host page size
(getpagesize(2)) by default as the alignment of mapping address.
However, some backends may require alignments different than the page
size. For example, mmap a device DAX (e.g., /dev/dax0.0) on Linux
kernel 4.13 to an address, which is 4K-aligned but not 2M-aligned,
fails with a kernel message like

[617494.969768] dax dax0.0: qemu-system-x86: dax_mmap: fail, unaligned vma (0x7fa37c579000 - 0x7fa43c579000, 0x1fffff)

Because there is no common approach to get such alignment requirement,
we add the 'align' option to 'memory-backend-file', so that users or
management utils, which have enough knowledge about the backend, can
specify a proper alignment via this option.

Signed-off-by: Haozhong Zhang <haozhong.zhang@intel.com>
Message-Id: <20171211072806.2812-2-haozhong.zhang@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
[ehabkost: fixed typo, fixed error_setg() format string]
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>

diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c
index e44c319915acac43183176ce993c515932948dd8..e319ec1ad8aff043d54141807de1ec1ac8ec12e6 100644 (file)
--- a/backends/hostmem-file.c
+++ b/backends/hostmem-file.c
@@ -34,6 +34,7 @@ struct HostMemoryBackendFile {
     bool share;
     bool discard_data;
     char *mem_path;
+    uint64_t align;
 };
 
 static void
@@ -58,7 +59,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
         path = object_get_canonical_path(OBJECT(backend));
         memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
                                  path,
-                                 backend->size, fb->share,
+                                 backend->size, fb->align, fb->share,
                                  fb->mem_path, errp);
         g_free(path);
     }
@@ -115,6 +116,40 @@ static void file_memory_backend_set_discard_data(Object *o, bool value,
     MEMORY_BACKEND_FILE(o)->discard_data = value;
 }
 
+static void file_memory_backend_get_align(Object *o, Visitor *v,
+                                          const char *name, void *opaque,
+                                          Error **errp)
+{
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+    uint64_t val = fb->align;
+
+    visit_type_size(v, name, &val, errp);
+}
+
+static void file_memory_backend_set_align(Object *o, Visitor *v,
+                                          const char *name, void *opaque,
+                                          Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(o);
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+    Error *local_err = NULL;
+    uint64_t val;
+
+    if (host_memory_backend_mr_inited(backend)) {
+        error_setg(&local_err, "cannot change property value");
+        goto out;
+    }
+
+    visit_type_size(v, name, &val, &local_err);
+    if (local_err) {
+        goto out;
+    }
+    fb->align = val;
+
+ out:
+    error_propagate(errp, local_err);
+}
+
 static void file_backend_unparent(Object *obj)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
@@ -145,6 +180,10 @@ file_backend_class_init(ObjectClass *oc, void *data)
     object_class_property_add_str(oc, "mem-path",
         get_mem_path, set_mem_path,
         &error_abort);
+    object_class_property_add(oc, "align", "int",
+        file_memory_backend_get_align,
+        file_memory_backend_set_align,
+        NULL, NULL, &error_abort);
 }
 
 static void file_backend_instance_finalize(Object *o)

diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt
index 2d9f8c0e8cfd1043df7fa8f8bf4076e38be3ca65..21249dd0626aea3e49c244e5bfd3e1b0e7d98b53 100644 (file)
--- a/docs/nvdimm.txt
+++ b/docs/nvdimm.txt
@@ -122,3 +122,19 @@ Note:
      M >= size of RAM devices +
           size of statically plugged vNVDIMM devices +
           size of hotplugged vNVDIMM devices
+
+Alignment
+---------
+
+QEMU uses mmap(2) to maps vNVDIMM backends and aligns the mapping
+address to the page size (getpagesize(2)) by default. However, some
+types of backends may require an alignment different than the page
+size. In that case, QEMU v2.12.0 and later provide 'align' option to
+memory-backend-file to allow users to specify the proper alignment.
+
+For example, device dax require the 2 MB alignment, so we can use
+following QEMU command line options to use it (/dev/dax0.0) as the
+backend of vNVDIMM:
+
+ -object memory-backend-file,id=mem1,share=on,mem-path=/dev/dax0.0,size=4G,align=2M
+ -device nvdimm,id=nvdimm1,memdev=mem1

diff --git a/exec.c b/exec.c
index d28fc0cd3d9fd2e0a77aaa27d0343202d46bef88..629a5083851d5c3a4d3db64008196df052ce9778 100644 (file)
--- a/exec.c
+++ b/exec.c
@@ -1612,7 +1612,13 @@ static void *file_ram_alloc(RAMBlock *block,
     void *area;
 
     block->page_size = qemu_fd_getpagesize(fd);
-    block->mr->align = block->page_size;
+    if (block->mr->align % block->page_size) {
+        error_setg(errp, "alignment 0x%" PRIx64
+                   " must be multiples of page size 0x%zx",
+                   block->mr->align, block->page_size);
+        return NULL;
+    }
+    block->mr->align = MAX(block->page_size, block->mr->align);
 #if defined(__s390x__)
     if (kvm_enabled()) {
         block->mr->align = MAX(block->mr->align, QEMU_VMALLOC_ALIGN);

diff --git a/include/exec/memory.h b/include/exec/memory.h
index a4cabdf44c353ed840b3b16c86f8bbdc6e265814..07c5d6d59796b92f21152ab99f949f9dc21e4c0a 100644 (file)
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -465,6 +465,8 @@ void memory_region_init_resizeable_ram(MemoryRegion *mr,
  * @name: Region name, becomes part of RAMBlock name used in migration stream
  *        must be unique within any device
  * @size: size of the region.
+ * @align: alignment of the region base address; if 0, the default alignment
+ *         (getpagesize()) will be used.
  * @share: %true if memory must be mmaped with the MAP_SHARED flag
  * @path: the path in which to allocate the RAM.
  * @errp: pointer to Error*, to store an error if it happens.
@@ -476,6 +478,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr,
                                       struct Object *owner,
                                       const char *name,
                                       uint64_t size,
+                                      uint64_t align,
                                       bool share,
                                       const char *path,
                                       Error **errp);

diff --git a/memory.c b/memory.c
index 4b41fb837b40c7b0dc6b3bd979f0431ad1232863..449a1429b946c57034a286d0f50cc43f321069ff 100644 (file)
--- a/memory.c
+++ b/memory.c
@@ -1570,6 +1570,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr,
                                       struct Object *owner,
                                       const char *name,
                                       uint64_t size,
+                                      uint64_t align,
                                       bool share,
                                       const char *path,
                                       Error **errp)
@@ -1578,6 +1579,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr,
     mr->ram = true;
     mr->terminates = true;
     mr->destructor = memory_region_destructor_ram;
+    mr->align = align;
     mr->ram_block = qemu_ram_alloc_from_file(size, mr, share, path, errp);
     mr->dirty_log_mask = tcg_enabled() ? (1 << DIRTY_MEMORY_CODE) : 0;
 }

diff --git a/numa.c b/numa.c
index 7b9c33ad1208047fc73e7f52faf2eea7beeb5f5a..83675a03f3cb65cc945d3bed92951464ae7256d0 100644 (file)
--- a/numa.c
+++ b/numa.c
@@ -456,7 +456,7 @@ static void allocate_system_memory_nonnuma(MemoryRegion *mr, Object *owner,
     if (mem_path) {
 #ifdef __linux__
         Error *err = NULL;
-        memory_region_init_ram_from_file(mr, owner, name, ram_size, false,
+        memory_region_init_ram_from_file(mr, owner, name, ram_size, 0, false,
                                          mem_path, &err);
         if (err) {
             error_report_err(err);

diff --git a/qemu-options.hx b/qemu-options.hx
index b3e03c5464d3545f6bb8ca38b555001c8301958e..5ff741a4af4f8ee00bff3be2ca92f77951f5469e 100644 (file)
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3974,7 +3974,7 @@ 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}
+@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}
 
 Creates a memory file backend object, which can be used to back
 the guest RAM with huge pages.
@@ -4027,6 +4027,13 @@ restrict memory allocation to the given host node list
 interleave memory allocations across the given host node list
 @end table
 
+The @option{align} option specifies the base address alignment when
+QEMU mmap(2) @option{mem-path}, and accepts common suffixes, eg
+@option{2M}. Some backend store specified by @option{mem-path}
+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.
+
 @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.