hostmem: Wire up RAM_NORESERVE via "reserve" property

Let's provide a way to control the use of RAM_NORESERVE via memory
backends using the "reserve" property which defaults to true (old
behavior).

Only Linux currently supports clearing the flag (and support is checked at
runtime, depending on the setting of "/proc/sys/vm/overcommit_memory").
Windows and other POSIX systems will bail out with "reserve=false".

The target use case is virtio-mem, which dynamically exposes memory
inside a large, sparse memory area to the VM. This essentially allows
avoiding to set "/proc/sys/vm/overcommit_memory == 0") when using
virtio-mem and also supporting hugetlbfs in the future.

As really only Linux implements RAM_NORESERVE right now, let's expose
the property only with CONFIG_LINUX. Setting the property to "false"
will then only fail in corner cases -- for example on very old kernels
or when memory overcommit was completely disabled by the admin.

Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com> for memory backend and machine core
Cc: Markus Armbruster <armbru@redhat.com>
Cc: Eric Blake <eblake@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210510114328.21835-11-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

6 files changed, 55 insertions, 6 deletions

diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c
index 9b1b9f0a56..cd038024fa 100644
--- a/backends/hostmem-file.c
+++ b/backends/hostmem-file.c
@@ -39,6 +39,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
                object_get_typename(OBJECT(backend)));
 #else
     HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(backend);
+    uint32_t ram_flags;
     gchar *name;
 
     if (!backend->size) {
@@ -51,11 +52,11 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
     }
 
     name = host_memory_backend_get_name(backend);
-    memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
-                                     name,
-                                     backend->size, fb->align,
-                                     (backend->share ? RAM_SHARED : 0) |
-                                     (fb->is_pmem ? RAM_PMEM : 0),
+    ram_flags = backend->share ? RAM_SHARED : 0;
+    ram_flags |= backend->reserve ? 0 : RAM_NORESERVE;
+    ram_flags |= fb->is_pmem ? RAM_PMEM : 0;
+    memory_region_init_ram_from_file(&backend->mr, OBJECT(backend), name,
+                                     backend->size, fb->align, ram_flags,
                                      fb->mem_path, fb->readonly, errp);
     g_free(name);
 #endif
diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c
index 3076da146d..3fc85c3db8 100644
--- a/backends/hostmem-memfd.c
+++ b/backends/hostmem-memfd.c
@@ -54,6 +54,7 @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
 
     name = host_memory_backend_get_name(backend);
     ram_flags = backend->share ? RAM_SHARED : 0;
+    ram_flags |= backend->reserve ? 0 : RAM_NORESERVE;
     memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), name,
                                    backend->size, ram_flags, fd, 0, errp);
     g_free(name);
diff --git a/backends/hostmem-ram.c b/backends/hostmem-ram.c
index 741e701062..b8e55cdbd0 100644
--- a/backends/hostmem-ram.c
+++ b/backends/hostmem-ram.c
@@ -29,6 +29,7 @@ ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
 
     name = host_memory_backend_get_name(backend);
     ram_flags = backend->share ? RAM_SHARED : 0;
+    ram_flags |= backend->reserve ? 0 : RAM_NORESERVE;
     memory_region_init_ram_flags_nomigrate(&backend->mr, OBJECT(backend), name,
                                            backend->size, ram_flags, errp);
     g_free(name);
diff --git a/backends/hostmem.c b/backends/hostmem.c
index aab3de8408..4c05862ed5 100644
--- a/backends/hostmem.c
+++ b/backends/hostmem.c
@@ -216,6 +216,11 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
     Error *local_err = NULL;
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
 
+    if (!backend->reserve && value) {
+        error_setg(errp, "'prealloc=on' and 'reserve=off' are incompatible");
+        return;
+    }
+
     if (!host_memory_backend_mr_inited(backend)) {
         backend->prealloc = value;
         return;
@@ -267,6 +272,7 @@ static void host_memory_backend_init(Object *obj)
     /* TODO: convert access to globals to compat properties */
     backend->merge = machine_mem_merge(machine);
     backend->dump = machine_dump_guest_core(machine);
+    backend->reserve = true;
     backend->prealloc_threads = 1;
 }
 
@@ -425,6 +431,30 @@ static void host_memory_backend_set_share(Object *o, bool value, Error **errp)
     backend->share = value;
 }
 
+#ifdef CONFIG_LINUX
+static bool host_memory_backend_get_reserve(Object *o, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(o);
+
+    return backend->reserve;
+}
+
+static void host_memory_backend_set_reserve(Object *o, bool value, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(o);
+
+    if (host_memory_backend_mr_inited(backend)) {
+        error_setg(errp, "cannot change property value");
+        return;
+    }
+    if (backend->prealloc && !value) {
+        error_setg(errp, "'prealloc=on' and 'reserve=off' are incompatible");
+        return;
+    }
+    backend->reserve = value;
+}
+#endif /* CONFIG_LINUX */
+
 static bool
 host_memory_backend_get_use_canonical_path(Object *obj, Error **errp)
 {
@@ -493,6 +523,12 @@ host_memory_backend_class_init(ObjectClass *oc, void *data)
         host_memory_backend_get_share, host_memory_backend_set_share);
     object_class_property_set_description(oc, "share",
         "Mark the memory as private to QEMU or shared");
+#ifdef CONFIG_LINUX
+    object_class_property_add_bool(oc, "reserve",
+        host_memory_backend_get_reserve, host_memory_backend_set_reserve);
+    object_class_property_set_description(oc, "reserve",
+        "Reserve swap space (or huge pages) if applicable");
+#endif /* CONFIG_LINUX */
     /*
      * Do not delete/rename option. This option must be considered stable
      * (as if it didn't have the 'x-' prefix including deprecation period) as
diff --git a/include/sysemu/hostmem.h b/include/sysemu/hostmem.h
index df5644723a..9ff5c16963 100644
--- a/include/sysemu/hostmem.h
+++ b/include/sysemu/hostmem.h
@@ -64,7 +64,7 @@ struct HostMemoryBackend {
     /* protected */
     uint64_t size;
     bool merge, dump, use_canonical_path;
-    bool prealloc, is_mapped, share;
+    bool prealloc, is_mapped, share, reserve;
     uint32_t prealloc_threads;
     DECLARE_BITMAP(host_nodes, MAX_NODES + 1);
     HostMemPolicy policy;
diff --git a/qapi/qom.json b/qapi/qom.json
index f7ef30f940..652be317b8 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -545,6 +545,9 @@
 # @share: if false, the memory is private to QEMU; if true, it is shared
 #         (default: false)
 #
+# @reserve: if true, reserve swap space (or huge pages) if applicable
+#           (default: true) (since 6.1)
+#
 # @size: size of the memory region in bytes
 #
 # @x-use-canonical-path-for-ramblock-id: if true, the canoncial path is used
@@ -556,6 +559,12 @@
 #                                        false generally, but true for machine
 #                                        types <= 4.0)
 #
+# Note: prealloc=true and reserve=false cannot be set at the same time. With
+#       reserve=true, the behavior depends on the operating system: for example,
+#       Linux will not reserve swap space for shared file mappings --
+#       "not applicable". In contrast, reserve=false will bail out if it cannot
+#       be configured accordingly.
+#
 # Since: 2.1
 ##
 { 'struct': 'MemoryBackendProperties',
@@ -566,6 +575,7 @@
             '*prealloc': 'bool',
             '*prealloc-threads': 'uint32',
             '*share': 'bool',
+            '*reserve': 'bool',
             'size': 'size',
             '*x-use-canonical-path-for-ramblock-id': 'bool' } }