Merge tag 'patchew/20200219160953.13771-1-imammedo@redhat.com' of https://github.com/patchew-project/qemu into HEAD

This series removes ad hoc RAM allocation API (memory_region_allocate_system_memory)
and consolidates it around hostmem backend. It allows to

* resolve conflicts between global -mem-prealloc and hostmem's "policy" option,
  fixing premature allocation before binding policy is applied

* simplify complicated memory allocation routines which had to deal with 2 ways
  to allocate RAM.

* reuse hostmem backends of a choice for main RAM without adding extra CLI
  options to duplicate hostmem features.  A recent case was -mem-shared, to
  enable vhost-user on targets that don't support hostmem backends [1] (ex: s390)

* move RAM allocation from individual boards into generic machine code and
  provide them with prepared MemoryRegion.

* clean up deprecated NUMA features which were tied to the old API (see patches)
  - "numa: remove deprecated -mem-path fallback to anonymous RAM"
  - (POSTPONED, waiting on libvirt side) "forbid '-numa node,mem' for 5.0 and newer machine types"
  - (POSTPONED) "numa: remove deprecated implicit RAM distribution between nodes"

Introduce a new machine.memory-backend property and wrapper code that aliases
global -mem-path and -mem-alloc into automatically created hostmem backend
properties (provided memory-backend was not set explicitly given by user).
A bulk of trivial patches then follow to incrementally convert individual
boards to using machine.memory-backend provided MemoryRegion.

Board conversion typically involves:

* providing MachineClass::default_ram_size and MachineClass::default_ram_id
  so generic code could create default backend if user didn't explicitly provide
  memory-backend or -m options

* dropping memory_region_allocate_system_memory() call

* using convenience MachineState::ram MemoryRegion, which points to MemoryRegion
   allocated by ram-memdev

On top of that for some boards:

* missing ram_size checks are added (typically it were boards with fixed ram size)

* ram_size fixups are replaced by checks and hard errors, forcing user to
  provide correct "-m" values instead of ignoring it and continuing running.

After all boards are converted, the old API is removed and memory allocation
routines are cleaned up.

hw/core/machine.c

@@ -26,6 +26,7 @@
 #include "sysemu/qtest.h"
 #include "hw/pci/pci.h"
 #include "hw/mem/nvdimm.h"
+#include "migration/vmstate.h"
 
 GlobalProperty hw_compat_4_2[] = {
     { "virtio-blk-device", "queue-size", "128"},
@@ -510,6 +511,22 @@ static void validate_sysbus_device(SysBusDevice *sbdev, void *opaque)
     }
 }
 
+static char *machine_get_memdev(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->ram_memdev_id);
+}
+
+static void machine_set_memdev(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    g_free(ms->ram_memdev_id);
+    ms->ram_memdev_id = g_strdup(value);
+}
+
+
 static void machine_init_notify(Notifier *notifier, void *data)
 {
     MachineState *machine = MACHINE(qdev_get_machine());
@@ -891,6 +908,14 @@ static void machine_initfn(Object *obj)
                                         "Table (HMAT)", NULL);
     }
 
+    object_property_add_str(obj, "memory-backend",
+                            machine_get_memdev, machine_set_memdev,
+                            &error_abort);
+    object_property_set_description(obj, "memory-backend",
+                                    "Set RAM backend"
+                                    "Valid value is ID of hostmem based backend",
+                                     &error_abort);
+
     /* Register notifier when init is done for sysbus sanity checks */
     ms->sysbus_notifier.notify = machine_init_notify;
     qemu_add_machine_init_done_notifier(&ms->sysbus_notifier);
@@ -1037,10 +1062,33 @@ static void machine_numa_finish_cpu_init(MachineState *machine)
     g_string_free(s, true);
 }
 
+MemoryRegion *machine_consume_memdev(MachineState *machine,
+                                     HostMemoryBackend *backend)
+{
+    MemoryRegion *ret = host_memory_backend_get_memory(backend);
+
+    if (memory_region_is_mapped(ret)) {
+        char *path = object_get_canonical_path_component(OBJECT(backend));
+        error_report("memory backend %s can't be used multiple times.", path);
+        g_free(path);
+        exit(EXIT_FAILURE);
+    }
+    host_memory_backend_set_mapped(backend, true);
+    vmstate_register_ram_global(ret);
+    return ret;
+}
+
 void machine_run_board_init(MachineState *machine)
 {
     MachineClass *machine_class = MACHINE_GET_CLASS(machine);
 
+    if (machine->ram_memdev_id) {
+        Object *o;
+        o = object_resolve_path_type(machine->ram_memdev_id,
+                                     TYPE_MEMORY_BACKEND, NULL);
+        machine->ram = machine_consume_memdev(machine, MEMORY_BACKEND(o));
+    }
+
     if (machine->numa_state) {
         numa_complete_configuration(machine);
         if (machine->numa_state->num_nodes) {

hw/core/null-machine.c

@@ -32,11 +32,8 @@ static void machine_none_init(MachineState *mch)
     }
 
     /* RAM at address zero */
-    if (mch->ram_size) {
-        MemoryRegion *ram = g_new(MemoryRegion, 1);
-
-        memory_region_allocate_system_memory(ram, NULL, "ram", mch->ram_size);
-        memory_region_add_subregion(get_system_memory(), 0, ram);
+    if (mch->ram) {
+        memory_region_add_subregion(get_system_memory(), 0, mch->ram);
     }
 
     if (mch->kernel_filename) {
@@ -52,6 +49,7 @@ static void machine_none_machine_init(MachineClass *mc)
     mc->init = machine_none_init;
     mc->max_cpus = 1;
     mc->default_ram_size = 0;
+    mc->default_ram_id = "ram";
 }
 
 DEFINE_MACHINE("none", machine_none_machine_init)

hw/core/numa.c

@@ -52,6 +52,11 @@ QemuOptsList qemu_numa_opts = {
 };
 
 static int have_memdevs;
+bool numa_uses_legacy_mem(void)
+{
+    return !have_memdevs;
+}
+
 static int have_mem;
 static int max_numa_nodeid; /* Highest specified NUMA node ID, plus one.
                              * For all nodes, nodeid < max_numa_nodeid
@@ -652,6 +657,23 @@ void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
     nodes[i].node_mem = size - usedmem;
 }
 
+static void numa_init_memdev_container(MachineState *ms, MemoryRegion *ram)
+{
+    int i;
+    uint64_t addr = 0;
+
+    for (i = 0; i < ms->numa_state->num_nodes; i++) {
+        uint64_t size = ms->numa_state->nodes[i].node_mem;
+        HostMemoryBackend *backend = ms->numa_state->nodes[i].node_memdev;
+        if (!backend) {
+            continue;
+        }
+        MemoryRegion *seg = machine_consume_memdev(ms, backend);
+        memory_region_add_subregion(ram, addr, seg);
+        addr += size;
+    }
+}
+
 void numa_complete_configuration(MachineState *ms)
 {
     int i;
@@ -734,6 +756,12 @@ void numa_complete_configuration(MachineState *ms)
             exit(1);
         }
 
+        if (!numa_uses_legacy_mem() && mc->default_ram_id) {
+            ms->ram = g_new(MemoryRegion, 1);
+            memory_region_init(ms->ram, OBJECT(ms), mc->default_ram_id,
+                               ram_size);
+            numa_init_memdev_container(ms, ms->ram);
+        }
         /* QEMU needs at least all unique node pair distances to build
          * the whole NUMA distance table. QEMU treats the distance table
          * as symmetric by default, i.e. distance A->B == distance B->A.
@@ -778,79 +806,6 @@ void numa_cpu_pre_plug(const CPUArchId *slot, DeviceState *dev, Error **errp)
     }
 }
 
-static void allocate_system_memory_nonnuma(MemoryRegion *mr, Object *owner,
-                                           const char *name,
-                                           uint64_t ram_size)
-{
-    if (mem_path) {
-#ifdef __linux__
-        Error *err = NULL;
-        memory_region_init_ram_from_file(mr, owner, name, ram_size, 0, 0,
-                                         mem_path, &err);
-        if (err) {
-            error_report_err(err);
-            if (mem_prealloc) {
-                exit(1);
-            }
-            warn_report("falling back to regular RAM allocation");
-            error_printf("This is deprecated. Make sure that -mem-path "
-                         " specified path has sufficient resources to allocate"
-                         " -m specified RAM amount\n");
-            /* Legacy behavior: if allocation failed, fall back to
-             * regular RAM allocation.
-             */
-            mem_path = NULL;
-            memory_region_init_ram_nomigrate(mr, owner, name, ram_size, &error_fatal);
-        }
-#else
-        fprintf(stderr, "-mem-path not supported on this host\n");
-        exit(1);
-#endif
-    } else {
-        memory_region_init_ram_nomigrate(mr, owner, name, ram_size, &error_fatal);
-    }
-    vmstate_register_ram_global(mr);
-}
-
-void memory_region_allocate_system_memory(MemoryRegion *mr, Object *owner,
-                                          const char *name,
-                                          uint64_t ram_size)
-{
-    uint64_t addr = 0;
-    int i;
-    MachineState *ms = MACHINE(qdev_get_machine());
-
-    if (ms->numa_state == NULL ||
-        ms->numa_state->num_nodes == 0 || !have_memdevs) {
-        allocate_system_memory_nonnuma(mr, owner, name, ram_size);
-        return;
-    }
-
-    memory_region_init(mr, owner, name, ram_size);
-    for (i = 0; i < ms->numa_state->num_nodes; i++) {
-        uint64_t size = ms->numa_state->nodes[i].node_mem;
-        HostMemoryBackend *backend = ms->numa_state->nodes[i].node_memdev;
-        if (!backend) {
-            continue;
-        }
-        MemoryRegion *seg = host_memory_backend_get_memory(backend);
-
-        if (memory_region_is_mapped(seg)) {
-            char *path = object_get_canonical_path_component(OBJECT(backend));
-            error_report("memory backend %s is used multiple times. Each "
-                         "-numa option must use a different memdev value.",
-                         path);
-            g_free(path);
-            exit(1);
-        }
-
-        host_memory_backend_set_mapped(backend, true);
-        memory_region_add_subregion(mr, addr, seg);
-        vmstate_register_ram_global(seg);
-        addr += size;
-    }
-}
-
 static void numa_stat_memory_devices(NumaNodeMem node_mem[])
 {
     MemoryDeviceInfoList *info_list = qmp_memory_device_list();