#include "hw/mem/pc-dimm.h"
#include "sysemu/balloon.h"
#include "hw/virtio/virtio-balloon.h"
-#include "sysemu/kvm.h"
#include "exec/address-spaces.h"
#include "qapi/error.h"
+#include "qapi/qapi-events-misc.h"
#include "qapi/visitor.h"
-#include "qapi-event.h"
#include "trace.h"
#include "qemu/error-report.h"
+#include "migration/misc.h"
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio-access.h"
#define BALLOON_PAGE_SIZE (1 << VIRTIO_BALLOON_PFN_SHIFT)
-static void balloon_page(void *addr, int deflate)
+struct PartiallyBalloonedPage {
+ RAMBlock *rb;
+ ram_addr_t base;
+ unsigned long bitmap[];
+};
+
+static void balloon_inflate_page(VirtIOBalloon *balloon,
+ MemoryRegion *mr, hwaddr offset)
+{
+ void *addr = memory_region_get_ram_ptr(mr) + offset;
+ 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_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);
+ /* We ignore errors from ram_block_discard_range(), because it
+ * has already reported them, and failing to discard a balloon
+ * page is not fatal */
+ return;
+ }
+
+ /* Hard case
+ *
+ * We've put a piece of a larger host page into the balloon - we
+ * need to keep track until we have a whole host page to
+ * discard
+ */
+ warn_report_once(
+"Balloon used with backing page size > 4kiB, this may not be reliable");
+
+ subpages = rb_page_size / BALLOON_PAGE_SIZE;
+
+ if (balloon->pbp
+ && (rb != balloon->pbp->rb
+ || host_page_base != balloon->pbp->base)) {
+ /* 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 */
+ g_free(balloon->pbp);
+ balloon->pbp = NULL;
+ }
+
+ 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;
+ }
+
+ bitmap_set(balloon->pbp->bitmap,
+ (ram_offset - balloon->pbp->base) / BALLOON_PAGE_SIZE,
+ subpages);
+
+ if (bitmap_full(balloon->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);
+ /* We ignore errors from ram_block_discard_range(), because it
+ * has already reported them, and failing to discard a balloon
+ * page is not fatal */
+
+ g_free(balloon->pbp);
+ balloon->pbp = NULL;
+ }
+}
+
+static void balloon_deflate_page(VirtIOBalloon *balloon,
+ MemoryRegion *mr, hwaddr offset)
{
- if (!qemu_balloon_is_inhibited() && (!kvm_enabled() ||
- kvm_has_sync_mmu())) {
- qemu_madvise(addr, BALLOON_PAGE_SIZE,
- deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
+ void *addr = memory_region_get_ram_ptr(mr) + offset;
+ RAMBlock *rb;
+ size_t rb_page_size;
+ ram_addr_t ram_offset, host_page_base;
+ void *host_addr;
+ int ret;
+
+ /* 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_page_size = qemu_ram_pagesize(rb);
+ host_page_base = ram_offset & ~(rb_page_size - 1);
+
+ if (balloon->pbp
+ && rb == balloon->pbp->rb
+ && host_page_base == balloon->pbp->base) {
+ int subpages = rb_page_size / BALLOON_PAGE_SIZE;
+
+ /*
+ * This means the guest has asked to discard some of the 4kiB
+ * subpages of a host page, but then changed its mind and
+ * asked to keep them after all. It's exceedingly unlikely
+ * for a guest to do this in practice, but handle it anyway,
+ * since getting it wrong could mean discarding memory the
+ * guest is still using. */
+ bitmap_clear(balloon->pbp->bitmap,
+ (ram_offset - balloon->pbp->base) / BALLOON_PAGE_SIZE,
+ subpages);
+
+ if (bitmap_empty(balloon->pbp->bitmap, subpages)) {
+ g_free(balloon->pbp);
+ balloon->pbp = NULL;
+ }
+ }
+
+ 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 */
}
}
[VIRTIO_BALLOON_S_MEMTOT] = "stat-total-memory",
[VIRTIO_BALLOON_S_AVAIL] = "stat-available-memory",
[VIRTIO_BALLOON_S_CACHES] = "stat-disk-caches",
+ [VIRTIO_BALLOON_S_HTLB_PGALLOC] = "stat-htlb-pgalloc",
+ [VIRTIO_BALLOON_S_HTLB_PGFAIL] = "stat-htlb-pgfail",
[VIRTIO_BALLOON_S_NR] = NULL
};
}
while (iov_to_buf(elem->out_sg, elem->out_num, offset, &pfn, 4) == 4) {
- ram_addr_t pa;
- ram_addr_t addr;
+ hwaddr pa;
int p = virtio_ldl_p(vdev, &pfn);
- pa = (ram_addr_t) p << VIRTIO_BALLOON_PFN_SHIFT;
+ pa = (hwaddr) 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) ||
+ section = memory_region_find(get_system_memory(), pa,
+ BALLOON_PAGE_SIZE);
+ if (!section.mr) {
+ trace_virtio_balloon_bad_addr(pa);
+ continue;
+ }
+ if (!memory_region_is_ram(section.mr) ||
memory_region_is_rom(section.mr) ||
memory_region_is_romd(section.mr)) {
trace_virtio_balloon_bad_addr(pa);
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));
+ if (!qemu_balloon_is_inhibited()) {
+ if (vq == s->ivq) {
+ balloon_inflate_page(s, section.mr,
+ section.offset_within_region);
+ } 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);
}
}
}
+static void virtio_balloon_handle_free_page_vq(VirtIODevice *vdev,
+ VirtQueue *vq)
+{
+ VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
+ qemu_bh_schedule(s->free_page_bh);
+}
+
+static bool get_free_page_hints(VirtIOBalloon *dev)
+{
+ 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);
+ }
+
+ elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
+ if (!elem) {
+ return false;
+ }
+
+ if (elem->out_num) {
+ uint32_t id;
+ size_t size = iov_to_buf(elem->out_sg, elem->out_num, 0,
+ &id, sizeof(id));
+
+ virtio_tswap32s(vdev, &id);
+ if (unlikely(size != sizeof(id))) {
+ virtio_error(vdev, "received an incorrect cmd id");
+ ret = false;
+ goto out;
+ }
+ if (id == dev->free_page_report_cmd_id) {
+ dev->free_page_report_status = FREE_PAGE_REPORT_S_START;
+ } else {
+ /*
+ * Stop the optimization only when it has started. This
+ * avoids a stale stop sign for the previous command.
+ */
+ if (dev->free_page_report_status == FREE_PAGE_REPORT_S_START) {
+ dev->free_page_report_status = FREE_PAGE_REPORT_S_STOP;
+ }
+ }
+ }
+
+ if (elem->in_num) {
+ if (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);
+ }
+ }
+
+out:
+ virtqueue_push(vq, elem, 1);
+ g_free(elem);
+ return ret;
+}
+
+static void virtio_ballloon_get_free_page_hints(void *opaque)
+{
+ VirtIOBalloon *dev = opaque;
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VirtQueue *vq = dev->free_page_vq;
+ bool continue_to_get_hints;
+
+ do {
+ qemu_mutex_lock(&dev->free_page_lock);
+ virtio_queue_set_notification(vq, 0);
+ continue_to_get_hints = get_free_page_hints(dev);
+ qemu_mutex_unlock(&dev->free_page_lock);
+ virtio_notify(vdev, vq);
+ /*
+ * Start to poll the vq once the reporting started. Otherwise, continue
+ * only when there are entries on the vq, which need to be given back.
+ */
+ } while (continue_to_get_hints ||
+ dev->free_page_report_status == FREE_PAGE_REPORT_S_START);
+ virtio_queue_set_notification(vq, 1);
+}
+
+static bool virtio_balloon_free_page_support(void *opaque)
+{
+ VirtIOBalloon *s = opaque;
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+
+ return virtio_vdev_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT);
+}
+
+static void virtio_balloon_free_page_start(VirtIOBalloon *s)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+
+ /* For the stop and copy phase, we don't need to start the optimization */
+ if (!vdev->vm_running) {
+ return;
+ }
+
+ if (s->free_page_report_cmd_id == UINT_MAX) {
+ s->free_page_report_cmd_id =
+ VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN;
+ } else {
+ s->free_page_report_cmd_id++;
+ }
+
+ s->free_page_report_status = FREE_PAGE_REPORT_S_REQUESTED;
+ virtio_notify_config(vdev);
+}
+
+static void virtio_balloon_free_page_stop(VirtIOBalloon *s)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+
+ if (s->free_page_report_status != FREE_PAGE_REPORT_S_STOP) {
+ /*
+ * The lock also guarantees us that the
+ * virtio_ballloon_get_free_page_hints exits after the
+ * free_page_report_status is set to S_STOP.
+ */
+ qemu_mutex_lock(&s->free_page_lock);
+ /*
+ * The guest hasn't done the reporting, so host sends a notification
+ * to the guest to actively stop the reporting.
+ */
+ s->free_page_report_status = FREE_PAGE_REPORT_S_STOP;
+ qemu_mutex_unlock(&s->free_page_lock);
+ virtio_notify_config(vdev);
+ }
+}
+
+static void virtio_balloon_free_page_done(VirtIOBalloon *s)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(s);
+
+ s->free_page_report_status = FREE_PAGE_REPORT_S_DONE;
+ virtio_notify_config(vdev);
+}
+
+static int
+virtio_balloon_free_page_report_notify(NotifierWithReturn *n, void *data)
+{
+ VirtIOBalloon *dev = container_of(n, VirtIOBalloon,
+ free_page_report_notify);
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ PrecopyNotifyData *pnd = data;
+
+ if (!virtio_balloon_free_page_support(dev)) {
+ /*
+ * This is an optimization provided to migration, so just return 0 to
+ * have the normal migration process not affected when this feature is
+ * not supported.
+ */
+ return 0;
+ }
+
+ switch (pnd->reason) {
+ case PRECOPY_NOTIFY_SETUP:
+ precopy_enable_free_page_optimization();
+ break;
+ case PRECOPY_NOTIFY_COMPLETE:
+ case PRECOPY_NOTIFY_CLEANUP:
+ case PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC:
+ virtio_balloon_free_page_stop(dev);
+ break;
+ case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC:
+ if (vdev->vm_running) {
+ virtio_balloon_free_page_start(dev);
+ } else {
+ virtio_balloon_free_page_done(dev);
+ }
+ break;
+ default:
+ virtio_error(vdev, "%s: %d reason unknown", __func__, pnd->reason);
+ }
+
+ return 0;
+}
+
static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
{
VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
- struct virtio_balloon_config config;
+ struct virtio_balloon_config config = {};
config.num_pages = cpu_to_le32(dev->num_pages);
config.actual = cpu_to_le32(dev->actual);
+ if (dev->free_page_report_status == FREE_PAGE_REPORT_S_REQUESTED) {
+ config.free_page_report_cmd_id =
+ cpu_to_le32(dev->free_page_report_cmd_id);
+ } else if (dev->free_page_report_status == FREE_PAGE_REPORT_S_STOP) {
+ config.free_page_report_cmd_id =
+ cpu_to_le32(VIRTIO_BALLOON_CMD_ID_STOP);
+ } else if (dev->free_page_report_status == FREE_PAGE_REPORT_S_DONE) {
+ config.free_page_report_cmd_id =
+ cpu_to_le32(VIRTIO_BALLOON_CMD_ID_DONE);
+ }
+
trace_virtio_balloon_get_config(config.num_pages, config.actual);
memcpy(config_data, &config, 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);
+ ((ram_addr_t) dev->actual << VIRTIO_BALLOON_PFN_SHIFT));
}
trace_virtio_balloon_set_config(dev->actual, oldactual);
}
VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
f |= dev->host_features;
virtio_add_feature(&f, VIRTIO_BALLOON_F_STATS_VQ);
+
return f;
}
return 0;
}
+static const VMStateDescription vmstate_virtio_balloon_free_page_report = {
+ .name = "virtio-balloon-device/free-page-report",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = virtio_balloon_free_page_support,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT32(free_page_report_cmd_id, VirtIOBalloon),
+ VMSTATE_UINT32(free_page_report_status, VirtIOBalloon),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
static const VMStateDescription vmstate_virtio_balloon_device = {
.name = "virtio-balloon-device",
.version_id = 1,
VMSTATE_UINT32(actual, VirtIOBalloon),
VMSTATE_END_OF_LIST()
},
+ .subsections = (const VMStateDescription * []) {
+ &vmstate_virtio_balloon_free_page_report,
+ NULL
+ }
};
static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats);
+ if (virtio_has_feature(s->host_features,
+ VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ s->free_page_vq = virtio_add_queue(vdev, VIRTQUEUE_MAX_SIZE,
+ virtio_balloon_handle_free_page_vq);
+ s->free_page_report_status = FREE_PAGE_REPORT_S_STOP;
+ s->free_page_report_cmd_id =
+ VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN;
+ s->free_page_report_notify.notify =
+ virtio_balloon_free_page_report_notify;
+ precopy_add_notifier(&s->free_page_report_notify);
+ if (s->iothread) {
+ object_ref(OBJECT(s->iothread));
+ s->free_page_bh = aio_bh_new(iothread_get_aio_context(s->iothread),
+ virtio_ballloon_get_free_page_hints, s);
+ qemu_mutex_init(&s->free_page_lock);
+ qemu_cond_init(&s->free_page_cond);
+ s->block_iothread = false;
+ } else {
+ /* Simply disable this feature if the iothread wasn't created. */
+ s->host_features &= ~(1 << VIRTIO_BALLOON_F_FREE_PAGE_HINT);
+ virtio_error(vdev, "iothread is missing");
+ }
+ }
reset_stats(s);
}
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOBalloon *s = VIRTIO_BALLOON(dev);
+ if (virtio_balloon_free_page_support(s)) {
+ qemu_bh_delete(s->free_page_bh);
+ virtio_balloon_free_page_stop(s);
+ precopy_remove_notifier(&s->free_page_report_notify);
+ }
balloon_stats_destroy_timer(s);
qemu_remove_balloon_handler(s);
virtio_cleanup(vdev);
{
VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
+ if (virtio_balloon_free_page_support(s)) {
+ virtio_balloon_free_page_stop(s);
+ }
+
if (s->stats_vq_elem != NULL) {
virtqueue_unpop(s->svq, s->stats_vq_elem, 0);
g_free(s->stats_vq_elem);
* was stopped */
virtio_balloon_receive_stats(vdev, s->svq);
}
+
+ if (virtio_balloon_free_page_support(s)) {
+ /*
+ * The VM is woken up and the iothread was blocked, so signal it to
+ * continue.
+ */
+ if (vdev->vm_running && s->block_iothread) {
+ qemu_mutex_lock(&s->free_page_lock);
+ s->block_iothread = false;
+ qemu_cond_signal(&s->free_page_cond);
+ qemu_mutex_unlock(&s->free_page_lock);
+ }
+
+ /* The VM is stopped, block the iothread. */
+ if (!vdev->vm_running) {
+ qemu_mutex_lock(&s->free_page_lock);
+ s->block_iothread = true;
+ qemu_mutex_unlock(&s->free_page_lock);
+ }
+ }
}
static void virtio_balloon_instance_init(Object *obj)
static Property virtio_balloon_properties[] = {
DEFINE_PROP_BIT("deflate-on-oom", VirtIOBalloon, host_features,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM, false),
+ DEFINE_PROP_BIT("free-page-hint", VirtIOBalloon, host_features,
+ VIRTIO_BALLOON_F_FREE_PAGE_HINT, false),
+ DEFINE_PROP_LINK("iothread", VirtIOBalloon, iothread, TYPE_IOTHREAD,
+ IOThread *),
DEFINE_PROP_END_OF_LIST(),
};
projects / qemu.git / blobdiff