qemu/numa.c

551 lines
16 KiB
C
Raw Normal View History

/*
* NUMA parameter parsing routines
*
* Copyright (c) 2014 Fujitsu Ltd.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "sysemu/numa.h"
#include "exec/cpu-common.h"
#include "qemu/bitmap.h"
#include "qom/cpu.h"
#include "qemu/error-report.h"
#include "include/exec/cpu-common.h" /* for RAM_ADDR_FMT */
#include "qapi-visit.h"
#include "qapi/opts-visitor.h"
#include "hw/boards.h"
#include "sysemu/hostmem.h"
#include "qmp-commands.h"
#include "hw/mem/pc-dimm.h"
#include "qemu/option.h"
#include "qemu/config-file.h"
QemuOptsList qemu_numa_opts = {
.name = "numa",
.implied_opt_name = "type",
.head = QTAILQ_HEAD_INITIALIZER(qemu_numa_opts.head),
.desc = { { 0 } } /* validated with OptsVisitor */
};
static int have_memdevs = -1;
static int max_numa_nodeid; /* Highest specified NUMA node ID, plus one.
* For all nodes, nodeid < max_numa_nodeid
*/
int nb_numa_nodes;
NodeInfo numa_info[MAX_NODES];
void numa_set_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node)
{
struct numa_addr_range *range;
/*
* Memory-less nodes can come here with 0 size in which case,
* there is nothing to do.
*/
if (!size) {
return;
}
range = g_malloc0(sizeof(*range));
range->mem_start = addr;
range->mem_end = addr + size - 1;
QLIST_INSERT_HEAD(&numa_info[node].addr, range, entry);
}
void numa_unset_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node)
{
struct numa_addr_range *range, *next;
QLIST_FOREACH_SAFE(range, &numa_info[node].addr, entry, next) {
if (addr == range->mem_start && (addr + size - 1) == range->mem_end) {
QLIST_REMOVE(range, entry);
g_free(range);
return;
}
}
}
static void numa_set_mem_ranges(void)
{
int i;
ram_addr_t mem_start = 0;
/*
* Deduce start address of each node and use it to store
* the address range info in numa_info address range list
*/
for (i = 0; i < nb_numa_nodes; i++) {
numa_set_mem_node_id(mem_start, numa_info[i].node_mem, i);
mem_start += numa_info[i].node_mem;
}
}
/*
* Check if @addr falls under NUMA @node.
*/
static bool numa_addr_belongs_to_node(ram_addr_t addr, uint32_t node)
{
struct numa_addr_range *range;
QLIST_FOREACH(range, &numa_info[node].addr, entry) {
if (addr >= range->mem_start && addr <= range->mem_end) {
return true;
}
}
return false;
}
/*
* Given an address, return the index of the NUMA node to which the
* address belongs to.
*/
uint32_t numa_get_node(ram_addr_t addr, Error **errp)
{
uint32_t i;
/* For non NUMA configurations, check if the addr falls under node 0 */
if (!nb_numa_nodes) {
if (numa_addr_belongs_to_node(addr, 0)) {
return 0;
}
}
for (i = 0; i < nb_numa_nodes; i++) {
if (numa_addr_belongs_to_node(addr, i)) {
return i;
}
}
error_setg(errp, "Address 0x" RAM_ADDR_FMT " doesn't belong to any "
"NUMA node", addr);
return -1;
}
static void numa_node_parse(NumaNodeOptions *node, QemuOpts *opts, Error **errp)
{
uint16_t nodenr;
uint16List *cpus = NULL;
if (node->has_nodeid) {
nodenr = node->nodeid;
} else {
nodenr = nb_numa_nodes;
}
if (nodenr >= MAX_NODES) {
error_setg(errp, "Max number of NUMA nodes reached: %"
PRIu16 "", nodenr);
return;
}
if (numa_info[nodenr].present) {
error_setg(errp, "Duplicate NUMA nodeid: %" PRIu16, nodenr);
return;
}
for (cpus = node->cpus; cpus; cpus = cpus->next) {
if (cpus->value >= max_cpus) {
error_setg(errp,
"CPU index (%" PRIu16 ")"
" should be smaller than maxcpus (%d)",
cpus->value, max_cpus);
return;
}
bitmap_set(numa_info[nodenr].node_cpu, cpus->value, 1);
}
if (node->has_mem && node->has_memdev) {
error_setg(errp, "qemu: cannot specify both mem= and memdev=");
return;
}
if (have_memdevs == -1) {
have_memdevs = node->has_memdev;
}
if (node->has_memdev != have_memdevs) {
error_setg(errp, "qemu: memdev option must be specified for either "
"all or no nodes");
return;
}
if (node->has_mem) {
uint64_t mem_size = node->mem;
const char *mem_str = qemu_opt_get(opts, "mem");
/* Fix up legacy suffix-less format */
if (g_ascii_isdigit(mem_str[strlen(mem_str) - 1])) {
mem_size <<= 20;
}
numa_info[nodenr].node_mem = mem_size;
}
if (node->has_memdev) {
Object *o;
o = object_resolve_path_type(node->memdev, TYPE_MEMORY_BACKEND, NULL);
if (!o) {
error_setg(errp, "memdev=%s is ambiguous", node->memdev);
return;
}
object_ref(o);
numa_info[nodenr].node_mem = object_property_get_int(o, "size", NULL);
numa_info[nodenr].node_memdev = MEMORY_BACKEND(o);
}
numa_info[nodenr].present = true;
max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1);
}
static int parse_numa(void *opaque, QemuOpts *opts, Error **errp)
{
NumaOptions *object = NULL;
Error *err = NULL;
{
OptsVisitor *ov = opts_visitor_new(opts);
qapi: Swap visit_* arguments for consistent 'name' placement JSON uses "name":value, but many of our visitor interfaces were called with visit_type_FOO(v, &value, name, errp). This can be a bit confusing to have to mentally swap the parameter order to match JSON order. It's particularly bad for visit_start_struct(), where the 'name' parameter is smack in the middle of the otherwise-related group of 'obj, kind, size' parameters! It's time to do a global swap of the parameter ordering, so that the 'name' parameter is always immediately after the Visitor argument. Additional reason in favor of the swap: the existing include/qjson.h prefers listing 'name' first in json_prop_*(), and I have plans to unify that file with the qapi visitors; listing 'name' first in qapi will minimize churn to the (admittedly few) qjson.h clients. Later patches will then fix docs, object.h, visitor-impl.h, and those clients to match. Done by first patching scripts/qapi*.py by hand to make generated files do what I want, then by running the following Coccinelle script to affect the rest of the code base: $ spatch --sp-file script `git grep -l '\bvisit_' -- '**/*.[ch]'` I then had to apply some touchups (Coccinelle insisted on TAB indentation in visitor.h, and botched the signature of visit_type_enum() by rewriting 'const char *const strings[]' to the syntactically invalid 'const char*const[] strings'). The movement of parameters is sufficient to provoke compiler errors if any callers were missed. // Part 1: Swap declaration order @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_start_struct -(TV v, TObj OBJ, T1 ARG1, const char *name, T2 ARG2, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type bool, TV, T1; identifier ARG1; @@ bool visit_optional -(TV v, T1 ARG1, const char *name) +(TV v, const char *name, T1 ARG1) { ... } @@ type TV, TErr, TObj, T1; identifier OBJ, ARG1; @@ void visit_get_next_type -(TV v, TObj OBJ, T1 ARG1, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, TErr errp) { ... } @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_type_enum -(TV v, TObj OBJ, T1 ARG1, T2 ARG2, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type TV, TErr, TObj; identifier OBJ; identifier VISIT_TYPE =~ "^visit_type_"; @@ void VISIT_TYPE -(TV v, TObj OBJ, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, TErr errp) { ... } // Part 2: swap caller order @@ expression V, NAME, OBJ, ARG1, ARG2, ERR; identifier VISIT_TYPE =~ "^visit_type_"; @@ ( -visit_start_struct(V, OBJ, ARG1, NAME, ARG2, ERR) +visit_start_struct(V, NAME, OBJ, ARG1, ARG2, ERR) | -visit_optional(V, ARG1, NAME) +visit_optional(V, NAME, ARG1) | -visit_get_next_type(V, OBJ, ARG1, NAME, ERR) +visit_get_next_type(V, NAME, OBJ, ARG1, ERR) | -visit_type_enum(V, OBJ, ARG1, ARG2, NAME, ERR) +visit_type_enum(V, NAME, OBJ, ARG1, ARG2, ERR) | -VISIT_TYPE(V, OBJ, NAME, ERR) +VISIT_TYPE(V, NAME, OBJ, ERR) ) Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-Id: <1454075341-13658-19-git-send-email-eblake@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-01-29 16:48:54 +03:00
visit_type_NumaOptions(opts_get_visitor(ov), NULL, &object, &err);
opts_visitor_cleanup(ov);
}
if (err) {
goto error;
}
switch (object->type) {
case NUMA_OPTIONS_KIND_NODE:
qapi: Don't special-case simple union wrappers Simple unions were carrying a special case that hid their 'data' QMP member from the resulting C struct, via the hack method QAPISchemaObjectTypeVariant.simple_union_type(). But by using the work we started by unboxing flat union and alternate branches, coupled with the ability to visit the members of an implicit type, we can now expose the simple union's implicit type in qapi-types.h: | struct q_obj_ImageInfoSpecificQCow2_wrapper { | ImageInfoSpecificQCow2 *data; | }; | | struct q_obj_ImageInfoSpecificVmdk_wrapper { | ImageInfoSpecificVmdk *data; | }; ... | struct ImageInfoSpecific { | ImageInfoSpecificKind type; | union { /* union tag is @type */ | void *data; |- ImageInfoSpecificQCow2 *qcow2; |- ImageInfoSpecificVmdk *vmdk; |+ q_obj_ImageInfoSpecificQCow2_wrapper qcow2; |+ q_obj_ImageInfoSpecificVmdk_wrapper vmdk; | } u; | }; Doing this removes asymmetry between QAPI's QMP side and its C side (both sides now expose 'data'), and means that the treatment of a simple union as sugar for a flat union is now equivalent in both languages (previously the two approaches used a different layer of dereferencing, where the simple union could be converted to a flat union with equivalent C layout but different {} on the wire, or to an equivalent QMP wire form but with different C representation). Using the implicit type also lets us get rid of the simple_union_type() hack. Of course, now all clients of simple unions have to adjust from using su->u.member to using su->u.member.data; while this touches a number of files in the tree, some earlier cleanup patches helped minimize the change to the initialization of a temporary variable rather than every single member access. The generated qapi-visit.c code is also affected by the layout change: |@@ -7393,10 +7393,10 @@ void visit_type_ImageInfoSpecific_member | } | switch (obj->type) { | case IMAGE_INFO_SPECIFIC_KIND_QCOW2: |- visit_type_ImageInfoSpecificQCow2(v, "data", &obj->u.qcow2, &err); |+ visit_type_q_obj_ImageInfoSpecificQCow2_wrapper_members(v, &obj->u.qcow2, &err); | break; | case IMAGE_INFO_SPECIFIC_KIND_VMDK: |- visit_type_ImageInfoSpecificVmdk(v, "data", &obj->u.vmdk, &err); |+ visit_type_q_obj_ImageInfoSpecificVmdk_wrapper_members(v, &obj->u.vmdk, &err); | break; | default: | abort(); Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <1458254921-17042-13-git-send-email-eblake@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-03-18 01:48:37 +03:00
numa_node_parse(object->u.node.data, opts, &err);
if (err) {
goto error;
}
nb_numa_nodes++;
break;
default:
abort();
}
return 0;
error:
error_report_err(err);
qapi_free_NumaOptions(object);
return -1;
}
static char *enumerate_cpus(unsigned long *cpus, int max_cpus)
{
int cpu;
bool first = true;
GString *s = g_string_new(NULL);
for (cpu = find_first_bit(cpus, max_cpus);
cpu < max_cpus;
cpu = find_next_bit(cpus, max_cpus, cpu + 1)) {
g_string_append_printf(s, "%s%d", first ? "" : " ", cpu);
first = false;
}
return g_string_free(s, FALSE);
}
static void validate_numa_cpus(void)
{
int i;
DECLARE_BITMAP(seen_cpus, MAX_CPUMASK_BITS);
bitmap_zero(seen_cpus, MAX_CPUMASK_BITS);
for (i = 0; i < nb_numa_nodes; i++) {
if (bitmap_intersects(seen_cpus, numa_info[i].node_cpu,
MAX_CPUMASK_BITS)) {
bitmap_and(seen_cpus, seen_cpus,
numa_info[i].node_cpu, MAX_CPUMASK_BITS);
error_report("CPU(s) present in multiple NUMA nodes: %s",
enumerate_cpus(seen_cpus, max_cpus));
exit(EXIT_FAILURE);
}
bitmap_or(seen_cpus, seen_cpus,
numa_info[i].node_cpu, MAX_CPUMASK_BITS);
}
2015-02-09 22:35:04 +03:00
if (!bitmap_full(seen_cpus, max_cpus)) {
char *msg;
bitmap_complement(seen_cpus, seen_cpus, max_cpus);
msg = enumerate_cpus(seen_cpus, max_cpus);
error_report("warning: CPU(s) not present in any NUMA nodes: %s", msg);
error_report("warning: All CPU(s) up to maxcpus should be described "
"in NUMA config");
g_free(msg);
}
}
void parse_numa_opts(MachineClass *mc)
{
int i;
if (qemu_opts_foreach(qemu_find_opts("numa"), parse_numa, NULL, NULL)) {
exit(1);
}
assert(max_numa_nodeid <= MAX_NODES);
/* No support for sparse NUMA node IDs yet: */
for (i = max_numa_nodeid - 1; i >= 0; i--) {
/* Report large node IDs first, to make mistakes easier to spot */
if (!numa_info[i].present) {
error_report("numa: Node ID missing: %d", i);
exit(1);
}
}
/* This must be always true if all nodes are present: */
assert(nb_numa_nodes == max_numa_nodeid);
if (nb_numa_nodes > 0) {
uint64_t numa_total;
if (nb_numa_nodes > MAX_NODES) {
nb_numa_nodes = MAX_NODES;
}
/* If no memory size is given for any node, assume the default case
* and distribute the available memory equally across all nodes
*/
for (i = 0; i < nb_numa_nodes; i++) {
if (numa_info[i].node_mem != 0) {
break;
}
}
if (i == nb_numa_nodes) {
uint64_t usedmem = 0;
/* On Linux, each node's border has to be 8MB aligned,
* the final node gets the rest.
*/
for (i = 0; i < nb_numa_nodes - 1; i++) {
numa_info[i].node_mem = (ram_size / nb_numa_nodes) &
~((1 << 23UL) - 1);
usedmem += numa_info[i].node_mem;
}
numa_info[i].node_mem = ram_size - usedmem;
}
numa_total = 0;
for (i = 0; i < nb_numa_nodes; i++) {
numa_total += numa_info[i].node_mem;
}
if (numa_total != ram_size) {
error_report("total memory for NUMA nodes (0x%" PRIx64 ")"
" should equal RAM size (0x" RAM_ADDR_FMT ")",
numa_total, ram_size);
exit(1);
}
for (i = 0; i < nb_numa_nodes; i++) {
QLIST_INIT(&numa_info[i].addr);
}
numa_set_mem_ranges();
for (i = 0; i < nb_numa_nodes; i++) {
if (!bitmap_empty(numa_info[i].node_cpu, MAX_CPUMASK_BITS)) {
break;
}
}
/* Historically VCPUs were assigned in round-robin order to NUMA
* nodes. However it causes issues with guest not handling it nice
* in case where cores/threads from a multicore CPU appear on
* different nodes. So allow boards to override default distribution
* rule grouping VCPUs by socket so that VCPUs from the same socket
* would be on the same node.
*/
if (i == nb_numa_nodes) {
for (i = 0; i < max_cpus; i++) {
unsigned node_id = i % nb_numa_nodes;
if (mc->cpu_index_to_socket_id) {
node_id = mc->cpu_index_to_socket_id(i) % nb_numa_nodes;
}
set_bit(i, numa_info[node_id].node_cpu);
}
}
validate_numa_cpus();
} else {
numa_set_mem_node_id(0, ram_size, 0);
}
}
void numa_post_machine_init(void)
{
CPUState *cpu;
int i;
CPU_FOREACH(cpu) {
for (i = 0; i < nb_numa_nodes; i++) {
if (test_bit(cpu->cpu_index, numa_info[i].node_cpu)) {
cpu->numa_node = i;
}
}
}
}
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, false,
mem_path, &err);
if (err) {
error_report_err(err);
if (mem_prealloc) {
exit(1);
}
/* Legacy behavior: if allocation failed, fall back to
* regular RAM allocation.
*/
Fix bad error handling after memory_region_init_ram() Symptom: $ qemu-system-x86_64 -m 10000000 Unexpected error in ram_block_add() at /work/armbru/qemu/exec.c:1456: upstream-qemu: cannot set up guest memory 'pc.ram': Cannot allocate memory Aborted (core dumped) Root cause: commit ef701d7 screwed up handling of out-of-memory conditions. Before the commit, we report the error and exit(1), in one place, ram_block_add(). The commit lifts the error handling up the call chain some, to three places. Fine. Except it uses &error_abort in these places, changing the behavior from exit(1) to abort(), and thus undoing the work of commit 3922825 "exec: Don't abort when we can't allocate guest memory". The three places are: * memory_region_init_ram() Commit 4994653 (right after commit ef701d7) lifted the error handling further, through memory_region_init_ram(), multiplying the incorrect use of &error_abort. Later on, imitation of existing (bad) code may have created more. * memory_region_init_ram_ptr() The &error_abort is still there. * memory_region_init_rom_device() Doesn't need fixing, because commit 33e0eb5 (soon after commit ef701d7) lifted the error handling further, and in the process changed it from &error_abort to passing it up the call chain. Correct, because the callers are realize() methods. Fix the error handling after memory_region_init_ram() with a Coccinelle semantic patch: @r@ expression mr, owner, name, size, err; position p; @@ memory_region_init_ram(mr, owner, name, size, ( - &error_abort + &error_fatal | err@p ) ); @script:python@ p << r.p; @@ print "%s:%s:%s" % (p[0].file, p[0].line, p[0].column) When the last argument is &error_abort, it gets replaced by &error_fatal. This is the fix. If the last argument is anything else, its position is reported. This lets us check the fix is complete. Four positions get reported: * ram_backend_memory_alloc() Error is passed up the call chain, ultimately through user_creatable_complete(). As far as I can tell, it's callers all handle the error sanely. * fsl_imx25_realize(), fsl_imx31_realize(), dp8393x_realize() DeviceClass.realize() methods, errors handled sanely further up the call chain. We're good. Test case again behaves: $ qemu-system-x86_64 -m 10000000 qemu-system-x86_64: cannot set up guest memory 'pc.ram': Cannot allocate memory [Exit 1 ] The next commits will repair the rest of commit ef701d7's damage. Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <1441983105-26376-3-git-send-email-armbru@redhat.com> Reviewed-by: Peter Crosthwaite <crosthwaite.peter@gmail.com>
2015-09-11 17:51:43 +03:00
memory_region_init_ram(mr, owner, name, ram_size, &error_fatal);
}
#else
fprintf(stderr, "-mem-path not supported on this host\n");
exit(1);
#endif
} else {
Fix bad error handling after memory_region_init_ram() Symptom: $ qemu-system-x86_64 -m 10000000 Unexpected error in ram_block_add() at /work/armbru/qemu/exec.c:1456: upstream-qemu: cannot set up guest memory 'pc.ram': Cannot allocate memory Aborted (core dumped) Root cause: commit ef701d7 screwed up handling of out-of-memory conditions. Before the commit, we report the error and exit(1), in one place, ram_block_add(). The commit lifts the error handling up the call chain some, to three places. Fine. Except it uses &error_abort in these places, changing the behavior from exit(1) to abort(), and thus undoing the work of commit 3922825 "exec: Don't abort when we can't allocate guest memory". The three places are: * memory_region_init_ram() Commit 4994653 (right after commit ef701d7) lifted the error handling further, through memory_region_init_ram(), multiplying the incorrect use of &error_abort. Later on, imitation of existing (bad) code may have created more. * memory_region_init_ram_ptr() The &error_abort is still there. * memory_region_init_rom_device() Doesn't need fixing, because commit 33e0eb5 (soon after commit ef701d7) lifted the error handling further, and in the process changed it from &error_abort to passing it up the call chain. Correct, because the callers are realize() methods. Fix the error handling after memory_region_init_ram() with a Coccinelle semantic patch: @r@ expression mr, owner, name, size, err; position p; @@ memory_region_init_ram(mr, owner, name, size, ( - &error_abort + &error_fatal | err@p ) ); @script:python@ p << r.p; @@ print "%s:%s:%s" % (p[0].file, p[0].line, p[0].column) When the last argument is &error_abort, it gets replaced by &error_fatal. This is the fix. If the last argument is anything else, its position is reported. This lets us check the fix is complete. Four positions get reported: * ram_backend_memory_alloc() Error is passed up the call chain, ultimately through user_creatable_complete(). As far as I can tell, it's callers all handle the error sanely. * fsl_imx25_realize(), fsl_imx31_realize(), dp8393x_realize() DeviceClass.realize() methods, errors handled sanely further up the call chain. We're good. Test case again behaves: $ qemu-system-x86_64 -m 10000000 qemu-system-x86_64: cannot set up guest memory 'pc.ram': Cannot allocate memory [Exit 1 ] The next commits will repair the rest of commit ef701d7's damage. Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <1441983105-26376-3-git-send-email-armbru@redhat.com> Reviewed-by: Peter Crosthwaite <crosthwaite.peter@gmail.com>
2015-09-11 17:51:43 +03:00
memory_region_init_ram(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;
if (nb_numa_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 < MAX_NODES; i++) {
uint64_t size = numa_info[i].node_mem;
HostMemoryBackend *backend = numa_info[i].node_memdev;
if (!backend) {
continue;
}
MemoryRegion *seg = host_memory_backend_get_memory(backend,
&error_fatal);
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);
exit(1);
}
memory_region_add_subregion(mr, addr, seg);
vmstate_register_ram_global(seg);
addr += size;
}
}
static void numa_stat_memory_devices(uint64_t node_mem[])
{
MemoryDeviceInfoList *info_list = NULL;
MemoryDeviceInfoList **prev = &info_list;
MemoryDeviceInfoList *info;
qmp_pc_dimm_device_list(qdev_get_machine(), &prev);
for (info = info_list; info; info = info->next) {
MemoryDeviceInfo *value = info->value;
if (value) {
switch (value->type) {
case MEMORY_DEVICE_INFO_KIND_DIMM:
qapi: Don't special-case simple union wrappers Simple unions were carrying a special case that hid their 'data' QMP member from the resulting C struct, via the hack method QAPISchemaObjectTypeVariant.simple_union_type(). But by using the work we started by unboxing flat union and alternate branches, coupled with the ability to visit the members of an implicit type, we can now expose the simple union's implicit type in qapi-types.h: | struct q_obj_ImageInfoSpecificQCow2_wrapper { | ImageInfoSpecificQCow2 *data; | }; | | struct q_obj_ImageInfoSpecificVmdk_wrapper { | ImageInfoSpecificVmdk *data; | }; ... | struct ImageInfoSpecific { | ImageInfoSpecificKind type; | union { /* union tag is @type */ | void *data; |- ImageInfoSpecificQCow2 *qcow2; |- ImageInfoSpecificVmdk *vmdk; |+ q_obj_ImageInfoSpecificQCow2_wrapper qcow2; |+ q_obj_ImageInfoSpecificVmdk_wrapper vmdk; | } u; | }; Doing this removes asymmetry between QAPI's QMP side and its C side (both sides now expose 'data'), and means that the treatment of a simple union as sugar for a flat union is now equivalent in both languages (previously the two approaches used a different layer of dereferencing, where the simple union could be converted to a flat union with equivalent C layout but different {} on the wire, or to an equivalent QMP wire form but with different C representation). Using the implicit type also lets us get rid of the simple_union_type() hack. Of course, now all clients of simple unions have to adjust from using su->u.member to using su->u.member.data; while this touches a number of files in the tree, some earlier cleanup patches helped minimize the change to the initialization of a temporary variable rather than every single member access. The generated qapi-visit.c code is also affected by the layout change: |@@ -7393,10 +7393,10 @@ void visit_type_ImageInfoSpecific_member | } | switch (obj->type) { | case IMAGE_INFO_SPECIFIC_KIND_QCOW2: |- visit_type_ImageInfoSpecificQCow2(v, "data", &obj->u.qcow2, &err); |+ visit_type_q_obj_ImageInfoSpecificQCow2_wrapper_members(v, &obj->u.qcow2, &err); | break; | case IMAGE_INFO_SPECIFIC_KIND_VMDK: |- visit_type_ImageInfoSpecificVmdk(v, "data", &obj->u.vmdk, &err); |+ visit_type_q_obj_ImageInfoSpecificVmdk_wrapper_members(v, &obj->u.vmdk, &err); | break; | default: | abort(); Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <1458254921-17042-13-git-send-email-eblake@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2016-03-18 01:48:37 +03:00
node_mem[value->u.dimm.data->node] += value->u.dimm.data->size;
break;
default:
break;
}
}
}
qapi_free_MemoryDeviceInfoList(info_list);
}
void query_numa_node_mem(uint64_t node_mem[])
{
int i;
if (nb_numa_nodes <= 0) {
return;
}
numa_stat_memory_devices(node_mem);
for (i = 0; i < nb_numa_nodes; i++) {
node_mem[i] += numa_info[i].node_mem;
}
}
static int query_memdev(Object *obj, void *opaque)
{
MemdevList **list = opaque;
MemdevList *m = NULL;
if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) {
m = g_malloc0(sizeof(*m));
m->value = g_malloc0(sizeof(*m->value));
m->value->size = object_property_get_int(obj, "size",
&error_abort);
m->value->merge = object_property_get_bool(obj, "merge",
&error_abort);
m->value->dump = object_property_get_bool(obj, "dump",
&error_abort);
m->value->prealloc = object_property_get_bool(obj,
"prealloc",
&error_abort);
m->value->policy = object_property_get_enum(obj,
"policy",
"HostMemPolicy",
&error_abort);
object_property_get_uint16List(obj, "host-nodes",
&m->value->host_nodes,
&error_abort);
m->next = *list;
*list = m;
}
return 0;
}
MemdevList *qmp_query_memdev(Error **errp)
{
Object *obj = object_get_objects_root();
MemdevList *list = NULL;
object_child_foreach(obj, query_memdev, &list);
return list;
}