Re: [RFC for QEMU] virtio-balloon: Add option thp-order to set VIRTIO_BALLOON_F_THP_ORDER

[teawater <teawaterz@linux.alibaba.com>]

> 2020年3月12日 16:25，Michael S. Tsirkin <mst@redhat.com> 写道：
> 
> On Thu, Mar 12, 2020 at 03:49:55PM +0800, Hui Zhu wrote:
>> If the guest kernel has many fragmentation pages, use virtio_balloon
>> will split THP of QEMU when it calls MADV_DONTNEED madvise to release
>> the balloon pages.
>> Set option thp-order to on will open flags VIRTIO_BALLOON_F_THP_ORDER.
>> It will set balloon size to THP size to handle the THP split issue.
>> 
>> Signed-off-by: Hui Zhu <teawaterz@linux.alibaba.com>
> 
> What's wrong with just using the PartiallyBalloonedPage machinery
> instead? That would make it guest transparent.

In balloon_inflate_page:
    rb_page_size = qemu_ram_pagesize(rb);

    if (rb_page_size == BALLOON_PAGE_SIZE) {
        /* Easy case */

It seems that PartiallyBalloonedPage is only used when rb_page_size is greater than BALLOON_PAGE_SIZE.
Do you mean I should modify the working mechanism of balloon_inflate_page function?

Thanks,
Hui

> 
>> ---
>> hw/virtio/virtio-balloon.c                      | 67 ++++++++++++++++---------
>> include/standard-headers/linux/virtio_balloon.h |  4 ++
>> 2 files changed, 47 insertions(+), 24 deletions(-)
>> 
>> diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
>> index a4729f7..cfe86b0 100644
>> --- a/hw/virtio/virtio-balloon.c
>> +++ b/hw/virtio/virtio-balloon.c
>> @@ -340,37 +340,49 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
>>         while (iov_to_buf(elem->out_sg, elem->out_num, offset, &pfn, 4) == 4) {
>>             unsigned int p = virtio_ldl_p(vdev, &pfn);
>>             hwaddr pa;
>> +            size_t handle_size = BALLOON_PAGE_SIZE;
>> 
>>             pa = (hwaddr) p << VIRTIO_BALLOON_PFN_SHIFT;
>>             offset += 4;
>> 
>> -            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);
>> -                memory_region_unref(section.mr);
>> -                continue;
>> -            }
>> +            if (virtio_has_feature(s->host_features,
>> +                                   VIRTIO_BALLOON_F_THP_ORDER))
>> +                handle_size = BALLOON_PAGE_SIZE << VIRTIO_BALLOON_THP_ORDER;
>> +
>> +            while (handle_size > 0) {
>> +                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);
>> +                    memory_region_unref(section.mr);
>> +                    continue;
>> +                }
>> 
>> -            trace_virtio_balloon_handle_output(memory_region_name(section.mr),
>> -                                               pa);
>> -            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();
>> +                trace_virtio_balloon_handle_output(memory_region_name(section.mr),
>> +                                                   pa);
>> +                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);
>> +
>> +                pa += BALLOON_PAGE_SIZE;
>> +                handle_size -= BALLOON_PAGE_SIZE;
>>             }
>> -            memory_region_unref(section.mr);
>>         }
>> 
>>         virtqueue_push(vq, elem, offset);
>> @@ -693,6 +705,8 @@ static void virtio_balloon_set_config(VirtIODevice *vdev,
>> 
>>     memcpy(&config, config_data, virtio_balloon_config_size(dev));
>>     dev->actual = le32_to_cpu(config.actual);
>> +    if (virtio_has_feature(vdev->host_features, VIRTIO_BALLOON_F_THP_ORDER))
>> +        dev->actual <<= VIRTIO_BALLOON_THP_ORDER;
>>     if (dev->actual != oldactual) {
>>         qapi_event_send_balloon_change(vm_ram_size -
>>                         ((ram_addr_t) dev->actual << VIRTIO_BALLOON_PFN_SHIFT));
>> @@ -728,6 +742,9 @@ static void virtio_balloon_to_target(void *opaque, ram_addr_t target)
>>     }
>>     if (target) {
>>         dev->num_pages = (vm_ram_size - target) >> VIRTIO_BALLOON_PFN_SHIFT;
>> +        if (virtio_has_feature(dev->host_features,
>> +                               VIRTIO_BALLOON_F_THP_ORDER))
>> +            dev->num_pages >>= VIRTIO_BALLOON_THP_ORDER;
>>         virtio_notify_config(vdev);
>>     }
>>     trace_virtio_balloon_to_target(target, dev->num_pages);
>> @@ -916,6 +933,8 @@ static Property virtio_balloon_properties[] = {
>>                     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_BIT("thp-order", VirtIOBalloon, host_features,
>> +                    VIRTIO_BALLOON_F_THP_ORDER, 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.
>> diff --git a/include/standard-headers/linux/virtio_balloon.h b/include/standard-headers/linux/virtio_balloon.h
>> index 9375ca2..f54d613 100644
>> --- a/include/standard-headers/linux/virtio_balloon.h
>> +++ b/include/standard-headers/linux/virtio_balloon.h
>> @@ -36,10 +36,14 @@
>> #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
>> #define VIRTIO_BALLOON_F_FREE_PAGE_HINT	3 /* VQ to report free pages */
>> #define VIRTIO_BALLOON_F_PAGE_POISON	4 /* Guest is using page poisoning */
>> +#define VIRTIO_BALLOON_F_THP_ORDER	5 /* Set balloon page order to thp order */
>> 
>> /* Size of a PFN in the balloon interface. */
>> #define VIRTIO_BALLOON_PFN_SHIFT 12
>> 
>> +/* The order of the balloon page */
>> +#define VIRTIO_BALLOON_THP_ORDER 9
>> +
>> #define VIRTIO_BALLOON_CMD_ID_STOP	0
>> #define VIRTIO_BALLOON_CMD_ID_DONE	1
>> struct virtio_balloon_config {
>> -- 
>> 2.7.4