#include "qemu/osdep.h"
#include "qemu/iov.h"
+#include "qemu/module.h"
#include "qemu/timer.h"
-#include "qemu-common.h"
#include "hw/virtio/virtio.h"
#include "hw/mem/pc-dimm.h"
+#include "hw/qdev-properties.h"
#include "sysemu/balloon.h"
#include "hw/virtio/virtio-balloon.h"
#include "exec/address-spaces.h"
#define BALLOON_PAGE_SIZE (1 << VIRTIO_BALLOON_PFN_SHIFT)
-struct PartiallyBalloonedPage {
- RAMBlock *rb;
- ram_addr_t base;
- unsigned long bitmap[];
-};
+typedef struct PartiallyBalloonedPage {
+ ram_addr_t base_gpa;
+ unsigned long *bitmap;
+} PartiallyBalloonedPage;
+
+static void virtio_balloon_pbp_free(PartiallyBalloonedPage *pbp)
+{
+ if (!pbp->bitmap) {
+ return;
+ }
+ g_free(pbp->bitmap);
+ pbp->bitmap = NULL;
+}
+
+static void virtio_balloon_pbp_alloc(PartiallyBalloonedPage *pbp,
+ ram_addr_t base_gpa,
+ long subpages)
+{
+ pbp->base_gpa = base_gpa;
+ pbp->bitmap = bitmap_new(subpages);
+}
+
+static bool virtio_balloon_pbp_matches(PartiallyBalloonedPage *pbp,
+ ram_addr_t base_gpa)
+{
+ return pbp->base_gpa == base_gpa;
+}
static void balloon_inflate_page(VirtIOBalloon *balloon,
- MemoryRegion *mr, hwaddr offset)
+ MemoryRegion *mr, hwaddr mr_offset,
+ PartiallyBalloonedPage *pbp)
{
- void *addr = memory_region_get_ram_ptr(mr) + offset;
+ void *addr = memory_region_get_ram_ptr(mr) + mr_offset;
+ ram_addr_t rb_offset, rb_aligned_offset, base_gpa;
RAMBlock *rb;
size_t rb_page_size;
int subpages;
- ram_addr_t ram_offset, host_page_base;
/* XXX is there a better way to get to the RAMBlock than via a
* host address? */
- rb = qemu_ram_block_from_host(addr, false, &ram_offset);
+ rb = qemu_ram_block_from_host(addr, false, &rb_offset);
rb_page_size = qemu_ram_pagesize(rb);
- host_page_base = ram_offset & ~(rb_page_size - 1);
if (rb_page_size == BALLOON_PAGE_SIZE) {
/* Easy case */
- ram_block_discard_range(rb, ram_offset, rb_page_size);
+ ram_block_discard_range(rb, rb_offset, rb_page_size);
/* We ignore errors from ram_block_discard_range(), because it
* has already reported them, and failing to discard a balloon
* page is not fatal */
warn_report_once(
"Balloon used with backing page size > 4kiB, this may not be reliable");
+ rb_aligned_offset = QEMU_ALIGN_DOWN(rb_offset, rb_page_size);
subpages = rb_page_size / BALLOON_PAGE_SIZE;
+ base_gpa = memory_region_get_ram_addr(mr) + mr_offset -
+ (rb_offset - rb_aligned_offset);
- if (balloon->pbp
- && (rb != balloon->pbp->rb
- || host_page_base != balloon->pbp->base)) {
+ if (pbp->bitmap && !virtio_balloon_pbp_matches(pbp, base_gpa)) {
/* We've partially ballooned part of a host page, but now
* we're trying to balloon part of a different one. Too hard,
* give up on the old partial page */
- free(balloon->pbp);
- balloon->pbp = NULL;
+ virtio_balloon_pbp_free(pbp);
}
- if (!balloon->pbp) {
- /* Starting on a new host page */
- size_t bitlen = BITS_TO_LONGS(subpages) * sizeof(unsigned long);
- balloon->pbp = g_malloc0(sizeof(PartiallyBalloonedPage) + bitlen);
- balloon->pbp->rb = rb;
- balloon->pbp->base = host_page_base;
+ if (!pbp->bitmap) {
+ virtio_balloon_pbp_alloc(pbp, base_gpa, subpages);
}
- bitmap_set(balloon->pbp->bitmap,
- (ram_offset - balloon->pbp->base) / BALLOON_PAGE_SIZE,
- subpages);
+ set_bit((rb_offset - rb_aligned_offset) / BALLOON_PAGE_SIZE,
+ pbp->bitmap);
- if (bitmap_full(balloon->pbp->bitmap, subpages)) {
+ if (bitmap_full(pbp->bitmap, subpages)) {
/* We've accumulated a full host page, we can actually discard
* it now */
- ram_block_discard_range(rb, balloon->pbp->base, rb_page_size);
+ ram_block_discard_range(rb, rb_aligned_offset, rb_page_size);
/* We ignore errors from ram_block_discard_range(), because it
* has already reported them, and failing to discard a balloon
* page is not fatal */
+ virtio_balloon_pbp_free(pbp);
+ }
+}
+
+static void balloon_deflate_page(VirtIOBalloon *balloon,
+ MemoryRegion *mr, hwaddr mr_offset)
+{
+ void *addr = memory_region_get_ram_ptr(mr) + mr_offset;
+ ram_addr_t rb_offset;
+ RAMBlock *rb;
+ size_t rb_page_size;
+ void *host_addr;
+ int ret;
- free(balloon->pbp);
- balloon->pbp = NULL;
+ /* XXX is there a better way to get to the RAMBlock than via a
+ * host address? */
+ rb = qemu_ram_block_from_host(addr, false, &rb_offset);
+ rb_page_size = qemu_ram_pagesize(rb);
+
+ host_addr = (void *)((uintptr_t)addr & ~(rb_page_size - 1));
+
+ /* When a page is deflated, we hint the whole host page it lives
+ * on, since we can't do anything smaller */
+ ret = qemu_madvise(host_addr, rb_page_size, QEMU_MADV_WILLNEED);
+ if (ret != 0) {
+ warn_report("Couldn't MADV_WILLNEED on balloon deflate: %s",
+ strerror(errno));
+ /* Otherwise ignore, failing to page hint shouldn't be fatal */
}
}
MemoryRegionSection section;
for (;;) {
+ PartiallyBalloonedPage pbp = {};
size_t offset = 0;
uint32_t pfn;
+
elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
if (!elem) {
- return;
+ break;
}
while (iov_to_buf(elem->out_sg, elem->out_num, offset, &pfn, 4) == 4) {
+ unsigned int p = virtio_ldl_p(vdev, &pfn);
hwaddr pa;
- int p = virtio_ldl_p(vdev, &pfn);
pa = (hwaddr) p << VIRTIO_BALLOON_PFN_SHIFT;
offset += 4;
trace_virtio_balloon_handle_output(memory_region_name(section.mr),
pa);
- if (!qemu_balloon_is_inhibited() && vq != s->dvq) {
- balloon_inflate_page(s, section.mr, section.offset_within_region);
+ if (!qemu_balloon_is_inhibited()) {
+ if (vq == s->ivq) {
+ balloon_inflate_page(s, section.mr,
+ section.offset_within_region, &pbp);
+ } else if (vq == s->dvq) {
+ balloon_deflate_page(s, section.mr, section.offset_within_region);
+ } else {
+ g_assert_not_reached();
+ }
}
memory_region_unref(section.mr);
}
virtqueue_push(vq, elem, offset);
virtio_notify(vdev, vq);
g_free(elem);
+ virtio_balloon_pbp_free(&pbp);
}
}
VirtQueueElement *elem;
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtQueue *vq = dev->free_page_vq;
+ bool ret = true;
while (dev->block_iothread) {
qemu_cond_wait(&dev->free_page_cond, &dev->free_page_lock);
uint32_t id;
size_t size = iov_to_buf(elem->out_sg, elem->out_num, 0,
&id, sizeof(id));
- virtqueue_push(vq, elem, size);
- g_free(elem);
virtio_tswap32s(vdev, &id);
if (unlikely(size != sizeof(id))) {
virtio_error(vdev, "received an incorrect cmd id");
- return false;
+ ret = false;
+ goto out;
}
if (id == dev->free_page_report_cmd_id) {
dev->free_page_report_status = FREE_PAGE_REPORT_S_START;
qemu_guest_free_page_hint(elem->in_sg[0].iov_base,
elem->in_sg[0].iov_len);
}
- virtqueue_push(vq, elem, 1);
- g_free(elem);
}
- return true;
+out:
+ virtqueue_push(vq, elem, 1);
+ g_free(elem);
+ return ret;
}
static void virtio_ballloon_get_free_page_hints(void *opaque)
return 0;
}
+static size_t virtio_balloon_config_size(VirtIOBalloon *s)
+{
+ uint64_t features = s->host_features;
+
+ if (s->qemu_4_0_config_size) {
+ return sizeof(struct virtio_balloon_config);
+ }
+ if (virtio_has_feature(features, VIRTIO_BALLOON_F_PAGE_POISON)) {
+ return sizeof(struct virtio_balloon_config);
+ }
+ if (virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ return offsetof(struct virtio_balloon_config, poison_val);
+ }
+ return offsetof(struct virtio_balloon_config, free_page_report_cmd_id);
+}
+
static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
{
VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
}
trace_virtio_balloon_get_config(config.num_pages, config.actual);
- memcpy(config_data, &config, sizeof(struct virtio_balloon_config));
+ memcpy(config_data, &config, virtio_balloon_config_size(dev));
}
static int build_dimm_list(Object *obj, void *opaque)
uint32_t oldactual = dev->actual;
ram_addr_t vm_ram_size = get_current_ram_size();
- memcpy(&config, config_data, sizeof(struct virtio_balloon_config));
+ memcpy(&config, config_data, virtio_balloon_config_size(dev));
dev->actual = le32_to_cpu(config.actual);
if (dev->actual != oldactual) {
qapi_event_send_balloon_change(vm_ram_size -
int ret;
virtio_init(vdev, "virtio-balloon", VIRTIO_ID_BALLOON,
- sizeof(struct virtio_balloon_config));
+ virtio_balloon_config_size(s));
ret = qemu_add_balloon_handler(virtio_balloon_to_target,
virtio_balloon_stat, s);
}
balloon_stats_destroy_timer(s);
qemu_remove_balloon_handler(s);
+
+ virtio_delete_queue(s->ivq);
+ virtio_delete_queue(s->dvq);
+ virtio_delete_queue(s->svq);
+ if (s->free_page_vq) {
+ virtio_delete_queue(s->free_page_vq);
+ }
virtio_cleanup(vdev);
}
VirtIOBalloon *s = VIRTIO_BALLOON(obj);
object_property_add(obj, "guest-stats", "guest statistics",
- balloon_stats_get_all, NULL, NULL, s, NULL);
+ balloon_stats_get_all, NULL, NULL, s);
object_property_add(obj, "guest-stats-polling-interval", "int",
balloon_stats_get_poll_interval,
balloon_stats_set_poll_interval,
- NULL, s, NULL);
+ NULL, s);
}
static const VMStateDescription vmstate_virtio_balloon = {
VIRTIO_BALLOON_F_DEFLATE_ON_OOM, false),
DEFINE_PROP_BIT("free-page-hint", VirtIOBalloon, host_features,
VIRTIO_BALLOON_F_FREE_PAGE_HINT, false),
+ /* QEMU 4.0 accidentally changed the config size even when free-page-hint
+ * is disabled, resulting in QEMU 3.1 migration incompatibility. This
+ * property retains this quirk for QEMU 4.1 machine types.
+ */
+ DEFINE_PROP_BOOL("qemu-4-0-config-size", VirtIOBalloon,
+ qemu_4_0_config_size, false),
DEFINE_PROP_LINK("iothread", VirtIOBalloon, iothread, TYPE_IOTHREAD,
IOThread *),
DEFINE_PROP_END_OF_LIST(),
DeviceClass *dc = DEVICE_CLASS(klass);
VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
- dc->props = virtio_balloon_properties;
+ device_class_set_props(dc, virtio_balloon_properties);
dc->vmsd = &vmstate_virtio_balloon;
set_bit(DEVICE_CATEGORY_MISC, dc->categories);
vdc->realize = virtio_balloon_device_realize;