Re: [QEMU PATCH] kvm: Support for guest page hinting

[Pankaj Gupta <pagupta@redhat.com>]

Hi Nitesh,

> 
> This patch enables QEMU to handle page hinting requests
> from the guest. Once the guest kicks QEMU to free a page,
> QEMU retrives the guest physical address and converts it to
> host virtual address and then MADVISE that memory.
> 
> Signed-off-by: Nitesh Narayan Lal <nilal@redhat.com>
> ---
>  hw/virtio/virtio-balloon.c         | 81
>  ++++++++++++++++++++++++++++++++++++++
>  hw/virtio/virtio.c                 | 24 +++++++++++
>  include/hw/virtio/virtio-access.h  |  1 +
>  include/hw/virtio/virtio-balloon.h |  2 +-
>  include/qemu/osdep.h               |  7 ++++
>  5 files changed, 114 insertions(+), 1 deletion(-)
> 
> diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
> index 37cde38..de10350 100644
> --- a/hw/virtio/virtio-balloon.c
> +++ b/hw/virtio/virtio-balloon.c
> @@ -33,6 +33,8 @@
>  
>  #define BALLOON_PAGE_SIZE  (1 << VIRTIO_BALLOON_PFN_SHIFT)
>  
> +void page_hinting_request(uint64_t addr, uint32_t len);
> +
>  static void balloon_page(void *addr, int deflate)
>  {
>      if (!qemu_balloon_is_inhibited() && (!kvm_enabled() ||
> @@ -205,6 +207,84 @@ static void balloon_stats_set_poll_interval(Object *obj,
> Visitor *v,
>      balloon_stats_change_timer(s, 0);
>  }
>  
> +static void *gpa2hva(MemoryRegion **p_mr, hwaddr addr, Error **errp)
> +{
> +    MemoryRegionSection mrs = memory_region_find(get_system_memory(),
> +                                                 addr, 1);
> +
> +    if (!mrs.mr) {
> +        error_setg(errp, "No memory is mapped at address 0x%" HWADDR_PRIx,
> addr);
> +        return NULL;
> +    }
> +
> +    if (!memory_region_is_ram(mrs.mr) && !memory_region_is_romd(mrs.mr)) {
> +        error_setg(errp, "Memory at address 0x%" HWADDR_PRIx "is not RAM",
> addr);
> +        memory_region_unref(mrs.mr);
> +        return NULL;
> +    }
> +
> +    *p_mr = mrs.mr;
> +    return qemu_map_ram_ptr(mrs.mr->ram_block, mrs.offset_within_region);
> +}
> +
> +struct guest_pages {
> +	unsigned long pfn;
> +	unsigned int pages;
> +};
> +
> +
> +void page_hinting_request(uint64_t addr, uint32_t len)
> +{
> +    Error *local_err = NULL;
> +    MemoryRegion *mr = NULL;
> +    void *hvaddr;
> +    int ret = 0;
> +    struct guest_pages *guest_obj;
> +    int i = 0;
> +    void *hvaddr_to_free;
> +    unsigned long pfn, pfn_end;
> +    uint64_t gpaddr_to_free;
> +
> +    /*ptr is the host physical address*/

Could not understand the comment?

> +    hvaddr = gpa2hva(&mr, addr, &local_err);
> +    if (local_err) {
> +        error_report_err(local_err);
> +        return;
> +    }
> +    guest_obj = hvaddr;
> +
> +    while (i < len) {
> +        pfn = guest_obj[i].pfn;
> +	pfn_end = guest_obj[i].pfn + guest_obj[i].pages - 1;
> +	while (pfn <= pfn_end) {
> +	        gpaddr_to_free = pfn << VIRTIO_BALLOON_PFN_SHIFT;
> +	        hvaddr_to_free = gpa2hva(&mr, gpaddr_to_free, &local_err);
> +	        if (local_err) {
> +			error_report_err(local_err);
> +		        return;
> +		}
> +		ret = qemu_madvise((void *)hvaddr_to_free, 4096, QEMU_MADV_FREE);
> +		if (ret == -1)
> +		    printf("\n%d:%s Error: Madvise failed with error:%d\n", __LINE__,
> __func__, ret);
> +		pfn++;
> +	}
> +	i++;
> +    }
> +}
> +
> +
> +static void virtio_balloon_page_hinting(VirtIODevice *vdev, VirtQueue *vq)
> +{
> +    uint64_t addr;
> +    uint32_t len;
> +    VirtQueueElement elem = {};
> +
> +    pop_hinting_addr(vq, &addr, &len);
> +    page_hinting_request(addr, len);
> +    virtqueue_push(vq, &elem, 0);
> +    virtio_notify(vdev, vq);
> +}
> +
>  static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
>  {
>      VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
> @@ -443,6 +523,7 @@ static void virtio_balloon_device_realize(DeviceState
> *dev, Error **errp)
>      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);
> +    s->hvq = virtio_add_queue(vdev, 128, virtio_balloon_page_hinting);
>  
>      reset_stats(s);
>  }
> diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
> index 311929e..24e26ec 100644
> --- a/hw/virtio/virtio.c
> +++ b/hw/virtio/virtio.c
> @@ -825,6 +825,30 @@ static void *virtqueue_alloc_element(size_t sz, unsigned
> out_num, unsigned in_nu
>      return elem;
>  }
>  
> +void pop_hinting_addr(VirtQueue *vq, uint64_t *addr, uint32_t *len)
> +{
> +   VRingMemoryRegionCaches *caches;
> +   VRingDesc desc;
> +   MemoryRegionCache *desc_cache;
> +   VirtIODevice *vdev = vq->vdev;
> +   unsigned int head, i, max;
> +
> +   max = vq->vring.num;
> +   if (!virtqueue_get_head(vq, vq->last_avail_idx++, &head)) {
> +	printf("\n%d:%sError: Unable to read head\n", __LINE__, __func__);
> +   }
> +   i = head;

we can avoid 'i' here and directly pass head
'to vring_desc_read' function?

> +
> +   caches = vring_get_region_caches(vq);
> +   if (caches->desc.len < max * sizeof(VRingDesc)) {
> +       virtio_error(vdev, "Cannot map descriptor ring");
> +   }
> +   desc_cache = &caches->desc;
> +   vring_desc_read(vdev, &desc, desc_cache, i);
> +   *addr = desc.addr;
> +   *len = desc.len;
> +}
> +
>  void *virtqueue_pop(VirtQueue *vq, size_t sz)
>  {
>      unsigned int i, head, max;
> diff --git a/include/hw/virtio/virtio-access.h
> b/include/hw/virtio/virtio-access.h
> index 2e92074..568d71f 100644
> --- a/include/hw/virtio/virtio-access.h
> +++ b/include/hw/virtio/virtio-access.h
> @@ -24,6 +24,7 @@
>  #define LEGACY_VIRTIO_IS_BIENDIAN 1
>  #endif
>  
> +void pop_hinting_addr(VirtQueue *vq, uint64_t *addr, uint32_t *len);
>  static inline bool virtio_access_is_big_endian(VirtIODevice *vdev)
>  {
>  #if defined(LEGACY_VIRTIO_IS_BIENDIAN)
> diff --git a/include/hw/virtio/virtio-balloon.h
> b/include/hw/virtio/virtio-balloon.h
> index 1ea13bd..dfb5782 100644
> --- a/include/hw/virtio/virtio-balloon.h
> +++ b/include/hw/virtio/virtio-balloon.h
> @@ -33,7 +33,7 @@ typedef struct virtio_balloon_stat_modern {
>  
>  typedef struct VirtIOBalloon {
>      VirtIODevice parent_obj;
> -    VirtQueue *ivq, *dvq, *svq;
> +    VirtQueue *ivq, *dvq, *svq, *hvq;
>      uint32_t num_pages;
>      uint32_t actual;
>      uint64_t stats[VIRTIO_BALLOON_S_NR];
> diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
> index 9dd318a..033d64c 100644
> --- a/include/qemu/osdep.h
> +++ b/include/qemu/osdep.h
> @@ -278,6 +278,11 @@ void qemu_anon_ram_free(void *ptr, size_t size);
>  #else
>  #define QEMU_MADV_REMOVE QEMU_MADV_INVALID
>  #endif
> +#ifdef MADV_FREE
> +#define QEMU_MADV_FREE MADV_FREE
> +#else
> +#define QEMU_MADV_FREE QEMU_MAD_INVALID
> +#endif
>  
>  #elif defined(CONFIG_POSIX_MADVISE)
>  
> @@ -291,6 +296,7 @@ void qemu_anon_ram_free(void *ptr, size_t size);
>  #define QEMU_MADV_HUGEPAGE  QEMU_MADV_INVALID
>  #define QEMU_MADV_NOHUGEPAGE  QEMU_MADV_INVALID
>  #define QEMU_MADV_REMOVE QEMU_MADV_INVALID
> +#define QEMU_MADV_FREE QEMU_MAD_INVALID
>  
>  #else /* no-op */
>  
> @@ -304,6 +310,7 @@ void qemu_anon_ram_free(void *ptr, size_t size);
>  #define QEMU_MADV_HUGEPAGE  QEMU_MADV_INVALID
>  #define QEMU_MADV_NOHUGEPAGE  QEMU_MADV_INVALID
>  #define QEMU_MADV_REMOVE QEMU_MADV_INVALID
> +#define QEMU_MADV_FREE QEMU_MAD_INVALID
>  
>  #endif
>  
> --
> 2.9.4
> 
>