qemu/hw/virtio/virtio-balloon.c
Denis V. Lunev e3816255bf balloon: add a feature bit to let Guest OS deflate balloon on oom
Excessive virtio_balloon inflation can cause invocation of OOM-killer,
when Linux is under severe memory pressure. Various mechanisms are
responsible for correct virtio_balloon memory management. Nevertheless it
is often the case that these control tools does not have enough time to
react on fast changing memory load. As a result OS runs out of memory and
invokes OOM-killer. The balancing of memory by use of the virtio balloon
should not cause the termination of processes while there are pages in the
balloon. Now there is no way for virtio balloon driver to free memory at
the last moment before some process get killed by OOM-killer.

This does not provide a security breach as balloon itself is running
inside Guest OS and is working in the cooperation with the host. Thus
some improvements from Guest side should be considered as normal.

To solve the problem, introduce a virtio_balloon callback which is
expected to be called from the oom notifier call chain in out_of_memory()
function. If virtio balloon could release some memory, it will make the
system return and retry the allocation that forced the out of memory
killer to run.

This behavior should be enabled if and only if appropriate feature bit
is set on the device. It is off by default.

This functionality was recently merged into vanilla Linux.

  commit 5a10b7dbf904bfe01bb9fcc6298f7df09eed77d5
  Author: Raushaniya Maksudova <rmaksudova@parallels.com>
  Date:   Mon Nov 10 09:36:29 2014 +1030

This patch adds respective control bits into QEMU. It introduces
deflate-on-oom option for balloon device which does the trick.

Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Raushaniya Maksudova <rmaksudova@parallels.com>
CC: Anthony Liguori <aliguori@amazon.com>
CC: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Acked-by: James Bottomley <JBottomley@Odin.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
2015-06-23 17:08:21 +02:00

463 lines
13 KiB
C

/*
* Virtio Balloon Device
*
* Copyright IBM, Corp. 2008
* Copyright (C) 2011 Red Hat, Inc.
* Copyright (C) 2011 Amit Shah <amit.shah@redhat.com>
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#include "qemu/iov.h"
#include "qemu/timer.h"
#include "qemu-common.h"
#include "hw/virtio/virtio.h"
#include "hw/i386/pc.h"
#include "cpu.h"
#include "sysemu/balloon.h"
#include "hw/virtio/virtio-balloon.h"
#include "sysemu/kvm.h"
#include "exec/address-spaces.h"
#include "qapi/visitor.h"
#include "qapi-event.h"
#include "trace.h"
#if defined(__linux__)
#include <sys/mman.h>
#endif
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio-access.h"
static void balloon_page(void *addr, int deflate)
{
#if defined(__linux__)
if (!kvm_enabled() || kvm_has_sync_mmu())
qemu_madvise(addr, TARGET_PAGE_SIZE,
deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
#endif
}
static const char *balloon_stat_names[] = {
[VIRTIO_BALLOON_S_SWAP_IN] = "stat-swap-in",
[VIRTIO_BALLOON_S_SWAP_OUT] = "stat-swap-out",
[VIRTIO_BALLOON_S_MAJFLT] = "stat-major-faults",
[VIRTIO_BALLOON_S_MINFLT] = "stat-minor-faults",
[VIRTIO_BALLOON_S_MEMFREE] = "stat-free-memory",
[VIRTIO_BALLOON_S_MEMTOT] = "stat-total-memory",
[VIRTIO_BALLOON_S_NR] = NULL
};
/*
* reset_stats - Mark all items in the stats array as unset
*
* This function needs to be called at device initialization and before
* updating to a set of newly-generated stats. This will ensure that no
* stale values stick around in case the guest reports a subset of the supported
* statistics.
*/
static inline void reset_stats(VirtIOBalloon *dev)
{
int i;
for (i = 0; i < VIRTIO_BALLOON_S_NR; dev->stats[i++] = -1);
}
static bool balloon_stats_supported(const VirtIOBalloon *s)
{
VirtIODevice *vdev = VIRTIO_DEVICE(s);
return virtio_has_feature(vdev, VIRTIO_BALLOON_F_STATS_VQ);
}
static bool balloon_stats_enabled(const VirtIOBalloon *s)
{
return s->stats_poll_interval > 0;
}
static void balloon_stats_destroy_timer(VirtIOBalloon *s)
{
if (balloon_stats_enabled(s)) {
timer_del(s->stats_timer);
timer_free(s->stats_timer);
s->stats_timer = NULL;
s->stats_poll_interval = 0;
}
}
static void balloon_stats_change_timer(VirtIOBalloon *s, int64_t secs)
{
timer_mod(s->stats_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + secs * 1000);
}
static void balloon_stats_poll_cb(void *opaque)
{
VirtIOBalloon *s = opaque;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
if (!balloon_stats_supported(s)) {
/* re-schedule */
balloon_stats_change_timer(s, s->stats_poll_interval);
return;
}
virtqueue_push(s->svq, &s->stats_vq_elem, s->stats_vq_offset);
virtio_notify(vdev, s->svq);
}
static void balloon_stats_get_all(Object *obj, struct Visitor *v,
void *opaque, const char *name, Error **errp)
{
Error *err = NULL;
VirtIOBalloon *s = opaque;
int i;
visit_start_struct(v, NULL, "guest-stats", name, 0, &err);
if (err) {
goto out;
}
visit_type_int(v, &s->stats_last_update, "last-update", &err);
if (err) {
goto out_end;
}
visit_start_struct(v, NULL, NULL, "stats", 0, &err);
if (err) {
goto out_end;
}
for (i = 0; !err && i < VIRTIO_BALLOON_S_NR; i++) {
visit_type_int64(v, (int64_t *) &s->stats[i], balloon_stat_names[i],
&err);
}
error_propagate(errp, err);
err = NULL;
visit_end_struct(v, &err);
out_end:
error_propagate(errp, err);
err = NULL;
visit_end_struct(v, &err);
out:
error_propagate(errp, err);
}
static void balloon_stats_get_poll_interval(Object *obj, struct Visitor *v,
void *opaque, const char *name,
Error **errp)
{
VirtIOBalloon *s = opaque;
visit_type_int(v, &s->stats_poll_interval, name, errp);
}
static void balloon_stats_set_poll_interval(Object *obj, struct Visitor *v,
void *opaque, const char *name,
Error **errp)
{
VirtIOBalloon *s = opaque;
Error *local_err = NULL;
int64_t value;
visit_type_int(v, &value, name, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
if (value < 0) {
error_setg(errp, "timer value must be greater than zero");
return;
}
if (value > UINT32_MAX) {
error_setg(errp, "timer value is too big");
return;
}
if (value == s->stats_poll_interval) {
return;
}
if (value == 0) {
/* timer=0 disables the timer */
balloon_stats_destroy_timer(s);
return;
}
if (balloon_stats_enabled(s)) {
/* timer interval change */
s->stats_poll_interval = value;
balloon_stats_change_timer(s, value);
return;
}
/* create a new timer */
g_assert(s->stats_timer == NULL);
s->stats_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL, balloon_stats_poll_cb, s);
s->stats_poll_interval = value;
balloon_stats_change_timer(s, 0);
}
static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
VirtQueueElement elem;
MemoryRegionSection section;
while (virtqueue_pop(vq, &elem)) {
size_t offset = 0;
uint32_t pfn;
while (iov_to_buf(elem.out_sg, elem.out_num, offset, &pfn, 4) == 4) {
ram_addr_t pa;
ram_addr_t addr;
int p = virtio_ldl_p(vdev, &pfn);
pa = (ram_addr_t) p << VIRTIO_BALLOON_PFN_SHIFT;
offset += 4;
/* FIXME: remove get_system_memory(), but how? */
section = memory_region_find(get_system_memory(), pa, 1);
if (!int128_nz(section.size) || !memory_region_is_ram(section.mr))
continue;
trace_virtio_balloon_handle_output(memory_region_name(section.mr),
pa);
/* Using memory_region_get_ram_ptr is bending the rules a bit, but
should be OK because we only want a single page. */
addr = section.offset_within_region;
balloon_page(memory_region_get_ram_ptr(section.mr) + addr,
!!(vq == s->dvq));
memory_region_unref(section.mr);
}
virtqueue_push(vq, &elem, offset);
virtio_notify(vdev, vq);
}
}
static void virtio_balloon_receive_stats(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
VirtQueueElement *elem = &s->stats_vq_elem;
VirtIOBalloonStat stat;
size_t offset = 0;
qemu_timeval tv;
if (!virtqueue_pop(vq, elem)) {
goto out;
}
/* Initialize the stats to get rid of any stale values. This is only
* needed to handle the case where a guest supports fewer stats than it
* used to (ie. it has booted into an old kernel).
*/
reset_stats(s);
while (iov_to_buf(elem->out_sg, elem->out_num, offset, &stat, sizeof(stat))
== sizeof(stat)) {
uint16_t tag = virtio_tswap16(vdev, stat.tag);
uint64_t val = virtio_tswap64(vdev, stat.val);
offset += sizeof(stat);
if (tag < VIRTIO_BALLOON_S_NR)
s->stats[tag] = val;
}
s->stats_vq_offset = offset;
if (qemu_gettimeofday(&tv) < 0) {
fprintf(stderr, "warning: %s: failed to get time of day\n", __func__);
goto out;
}
s->stats_last_update = tv.tv_sec;
out:
if (balloon_stats_enabled(s)) {
balloon_stats_change_timer(s, s->stats_poll_interval);
}
}
static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
{
VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
struct virtio_balloon_config config;
config.num_pages = cpu_to_le32(dev->num_pages);
config.actual = cpu_to_le32(dev->actual);
trace_virtio_balloon_get_config(config.num_pages, config.actual);
memcpy(config_data, &config, sizeof(struct virtio_balloon_config));
}
static void virtio_balloon_set_config(VirtIODevice *vdev,
const uint8_t *config_data)
{
VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
struct virtio_balloon_config config;
uint32_t oldactual = dev->actual;
ram_addr_t vm_ram_size = get_current_ram_size();
memcpy(&config, config_data, sizeof(struct virtio_balloon_config));
dev->actual = le32_to_cpu(config.actual);
if (dev->actual != oldactual) {
qapi_event_send_balloon_change(vm_ram_size -
((ram_addr_t) dev->actual << VIRTIO_BALLOON_PFN_SHIFT),
&error_abort);
}
trace_virtio_balloon_set_config(dev->actual, oldactual);
}
static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f)
{
VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
f |= dev->host_features;
virtio_add_feature(&f, VIRTIO_BALLOON_F_STATS_VQ);
return f;
}
static void virtio_balloon_stat(void *opaque, BalloonInfo *info)
{
VirtIOBalloon *dev = opaque;
info->actual = get_current_ram_size() - ((uint64_t) dev->actual <<
VIRTIO_BALLOON_PFN_SHIFT);
}
static void virtio_balloon_to_target(void *opaque, ram_addr_t target)
{
VirtIOBalloon *dev = VIRTIO_BALLOON(opaque);
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
ram_addr_t vm_ram_size = get_current_ram_size();
if (target > vm_ram_size) {
target = vm_ram_size;
}
if (target) {
dev->num_pages = (vm_ram_size - target) >> VIRTIO_BALLOON_PFN_SHIFT;
virtio_notify_config(vdev);
}
trace_virtio_balloon_to_target(target, dev->num_pages);
}
static void virtio_balloon_save(QEMUFile *f, void *opaque)
{
virtio_save(VIRTIO_DEVICE(opaque), f);
}
static void virtio_balloon_save_device(VirtIODevice *vdev, QEMUFile *f)
{
VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
qemu_put_be32(f, s->num_pages);
qemu_put_be32(f, s->actual);
}
static int virtio_balloon_load(QEMUFile *f, void *opaque, int version_id)
{
if (version_id != 1)
return -EINVAL;
return virtio_load(VIRTIO_DEVICE(opaque), f, version_id);
}
static int virtio_balloon_load_device(VirtIODevice *vdev, QEMUFile *f,
int version_id)
{
VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
s->num_pages = qemu_get_be32(f);
s->actual = qemu_get_be32(f);
return 0;
}
static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOBalloon *s = VIRTIO_BALLOON(dev);
int ret;
virtio_init(vdev, "virtio-balloon", VIRTIO_ID_BALLOON,
sizeof(struct virtio_balloon_config));
ret = qemu_add_balloon_handler(virtio_balloon_to_target,
virtio_balloon_stat, s);
if (ret < 0) {
error_setg(errp, "Only one balloon device is supported");
virtio_cleanup(vdev);
return;
}
s->ivq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats);
reset_stats(s);
register_savevm(dev, "virtio-balloon", -1, 1,
virtio_balloon_save, virtio_balloon_load, s);
}
static void virtio_balloon_device_unrealize(DeviceState *dev, Error **errp)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOBalloon *s = VIRTIO_BALLOON(dev);
balloon_stats_destroy_timer(s);
qemu_remove_balloon_handler(s);
unregister_savevm(dev, "virtio-balloon", s);
virtio_cleanup(vdev);
}
static void virtio_balloon_instance_init(Object *obj)
{
VirtIOBalloon *s = VIRTIO_BALLOON(obj);
object_property_add(obj, "guest-stats", "guest statistics",
balloon_stats_get_all, NULL, NULL, s, NULL);
object_property_add(obj, "guest-stats-polling-interval", "int",
balloon_stats_get_poll_interval,
balloon_stats_set_poll_interval,
NULL, s, NULL);
}
static Property virtio_balloon_properties[] = {
DEFINE_PROP_BIT("deflate-on-oom", VirtIOBalloon, host_features,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM, false),
DEFINE_PROP_END_OF_LIST(),
};
static void virtio_balloon_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
dc->props = virtio_balloon_properties;
set_bit(DEVICE_CATEGORY_MISC, dc->categories);
vdc->realize = virtio_balloon_device_realize;
vdc->unrealize = virtio_balloon_device_unrealize;
vdc->get_config = virtio_balloon_get_config;
vdc->set_config = virtio_balloon_set_config;
vdc->get_features = virtio_balloon_get_features;
vdc->save = virtio_balloon_save_device;
vdc->load = virtio_balloon_load_device;
}
static const TypeInfo virtio_balloon_info = {
.name = TYPE_VIRTIO_BALLOON,
.parent = TYPE_VIRTIO_DEVICE,
.instance_size = sizeof(VirtIOBalloon),
.instance_init = virtio_balloon_instance_init,
.class_init = virtio_balloon_class_init,
};
static void virtio_register_types(void)
{
type_register_static(&virtio_balloon_info);
}
type_init(virtio_register_types)