qemu/hw/virtio/virtio-balloon.c

416 lines
12 KiB
C
Raw Normal View History

/*
* 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"
#if defined(__linux__)
#include <sys/mman.h>
#endif
#include "hw/virtio/virtio-bus.h"
static void balloon_page(void *addr, int deflate)
{
#if defined(__linux__)
if (!kvm_enabled() || kvm_has_sync_mmu())
Introduce qemu_madvise() vl.c has a Sun-specific hack to supply a prototype for madvise(), but the call site has apparently moved to arch_init.c. Haiku doesn't implement madvise() in favor of posix_madvise(). OpenBSD and Solaris 10 don't implement posix_madvise() but madvise(). MinGW implements neither. Check for madvise() and posix_madvise() in configure and supply qemu_madvise() as wrapper. Prefer madvise() over posix_madvise() due to flag availability. Convert all callers to use qemu_madvise() and QEMU_MADV_*. Note that on Solaris the warning is fixed by moving the madvise() prototype, not by qemu_madvise() itself. It helps with porting though, and it simplifies most call sites. v7 -> v8: * Some versions of MinGW have no sys/mman.h header. Reported by Blue Swirl. v6 -> v7: * Adopt madvise() rather than posix_madvise() semantics for returning errors. * Use EINVAL in place of ENOTSUP. v5 -> v6: * Replace two leftover instances of POSIX_MADV_NORMAL with QEMU_MADV_INVALID. Spotted by Blue Swirl. v4 -> v5: * Introduce QEMU_MADV_INVALID, suggested by Alexander Graf. Note that this relies on -1 not being a valid advice value. v3 -> v4: * Eliminate #ifdefs at qemu_advise() call sites. Requested by Blue Swirl. This will currently break the check in kvm-all.c by calling madvise() with a supported flag, which will not fail. Ideas/patches welcome. v2 -> v3: * Reuse the *_MADV_* defines for QEMU_MADV_*. Suggested by Alexander Graf. * Add configure check for madvise(), too. Add defines to Makefile, not QEMU_CFLAGS. Convert all callers, untested. Suggested by Blue Swirl. * Keep Solaris' madvise() prototype around. Pointed out by Alexander Graf. * Display configure check results. v1 -> v2: * Don't rely on posix_madvise() availability, add qemu_madvise(). Suggested by Blue Swirl. Signed-off-by: Andreas Färber <afaerber@opensolaris.org> Cc: Blue Swirl <blauwirbel@gmail.com> Cc: Alexander Graf <agraf@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
2010-09-25 15:26:05 +04:00
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 vdev->guest_features & (1 << 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, int 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)
{
VirtIOBalloon *s = opaque;
int i;
if (!s->stats_last_update) {
error_setg(errp, "guest hasn't updated any stats yet");
return;
}
visit_start_struct(v, NULL, "guest-stats", name, 0, errp);
visit_type_int(v, &s->stats_last_update, "last-update", errp);
visit_start_struct(v, NULL, NULL, "stats", 0, errp);
for (i = 0; i < VIRTIO_BALLOON_S_NR; i++) {
visit_type_int64(v, (int64_t *) &s->stats[i], balloon_stat_names[i],
errp);
}
visit_end_struct(v, errp);
visit_end_struct(v, errp);
}
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;
int64_t value;
visit_type_int(v, &value, name, errp);
if (error_is_set(errp)) {
return;
}
if (value < 0) {
error_setg(errp, "timer value must be greater than zero");
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;
pa = (ram_addr_t)ldl_p(&pfn) << 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;
/* 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 = tswap16(stat.tag);
uint64_t val = tswap64(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);
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;
memcpy(&config, config_data, sizeof(struct virtio_balloon_config));
dev->actual = le32_to_cpu(config.actual);
if (dev->actual != oldactual) {
qemu_balloon_changed(ram_size -
((ram_addr_t) dev->actual << VIRTIO_BALLOON_PFN_SHIFT));
}
}
static uint32_t virtio_balloon_get_features(VirtIODevice *vdev, uint32_t f)
{
f |= (1 << VIRTIO_BALLOON_F_STATS_VQ);
return f;
}
static void virtio_balloon_stat(void *opaque, BalloonInfo *info)
{
VirtIOBalloon *dev = opaque;
info->actual = ram_size - ((uint64_t) dev->actual <<
VIRTIO_BALLOON_PFN_SHIFT);
}
balloon: Separate out stat and balloon handling Passing on '0' as ballooning target to indicate retrieval of stats is bad API. It also makes 'balloon 0' in the monitor cause a segfault. Have two different functions handle the different functionality instead. Detailed explanation from Markus's review: 1. do_info_balloon() is an info_async() method. It receives a callback with argument, to be called exactly once (callback frees the argument). It passes the callback via qemu_balloon_status() and indirectly through qemu_balloon_event to virtio_balloon_to_target(). virtio_balloon_to_target() executes its balloon stats half. It stores the callback in the device state. If it can't send a stats request, it resets stats and calls the callback right away. Else, it sends a stats request. The device model runs the callback when it receives the answer. Works. 2. do_balloon() is a cmd_async() method. It receives a callback with argument, to be called when the command completes. do_balloon() calls it right before it succeeds. Odd, but should work. Nevertheless, it passes the callback on via qemu_ballon() and indirectly through qemu_balloon_event to virtio_balloon_to_target(). a. If the argument is non-zero, virtio_balloon_to_target() executes its balloon half, which doesn't use the callback in any way. Odd, but works. b. If the argument is zero, virtio_balloon_to_target() executes its balloon stats half, just like in 1. It either calls the callback right away, or arranges for it to be called later. Thus, the callback runs twice: use after free and double free. Test case: start with -S -device virtio-balloon, execute "balloon 0" in human monitor. Runs the callback first from virtio_balloon_to_target(), then again from do_balloon(). Reported-by: Mike Cao <bcao@redhat.com> Signed-off-by: Amit Shah <amit.shah@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com>
2011-07-20 12:00:56 +04:00
static void virtio_balloon_to_target(void *opaque, ram_addr_t target)
{
VirtIOBalloon *dev = VIRTIO_BALLOON(opaque);
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
if (target > ram_size) {
target = ram_size;
}
if (target) {
dev->num_pages = (ram_size - target) >> VIRTIO_BALLOON_PFN_SHIFT;
virtio_notify_config(vdev);
}
}
static void virtio_balloon_save(QEMUFile *f, void *opaque)
{
VirtIOBalloon *s = VIRTIO_BALLOON(opaque);
VirtIODevice *vdev = VIRTIO_DEVICE(s);
virtio_save(vdev, f);
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)
{
VirtIOBalloon *s = VIRTIO_BALLOON(opaque);
VirtIODevice *vdev = VIRTIO_DEVICE(s);
int ret;
if (version_id != 1)
return -EINVAL;
ret = virtio_load(vdev, f);
if (ret) {
return ret;
}
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, "Adding balloon handler failed");
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);
register_savevm(dev, "virtio-balloon", -1, 1,
virtio_balloon_save, virtio_balloon_load, s);
object_property_add(OBJECT(dev), "guest-stats", "guest statistics",
balloon_stats_get_all, NULL, NULL, s, NULL);
object_property_add(OBJECT(dev), "guest-stats-polling-interval", "int",
balloon_stats_get_poll_interval,
balloon_stats_set_poll_interval,
NULL, s, NULL);
}
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 Property virtio_balloon_properties[] = {
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;
}
static const TypeInfo virtio_balloon_info = {
.name = TYPE_VIRTIO_BALLOON,
.parent = TYPE_VIRTIO_DEVICE,
.instance_size = sizeof(VirtIOBalloon),
.class_init = virtio_balloon_class_init,
};
static void virtio_register_types(void)
{
type_register_static(&virtio_balloon_info);
}
type_init(virtio_register_types)