Re: [PATCH v4 3/3] vdpa: Check for iova range at mappings changes

[Jason Wang <jasowang@redhat.com>]

在 2021/10/14 下午10:12, Eugenio Pérez 写道:
> Check vdpa device range before updating memory regions so we don't add
> any outside of it, and report the invalid change if any.
>
> Signed-off-by: Eugenio Pérez <eperezma@redhat.com>


Acked-by: Jason Wang <jasowang@redhat.com>


> ---
>   include/hw/virtio/vhost-vdpa.h |  2 ++
>   hw/virtio/vhost-vdpa.c         | 62 +++++++++++++++++++++++++---------
>   hw/virtio/trace-events         |  1 +
>   3 files changed, 49 insertions(+), 16 deletions(-)
>
> diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
> index a8963da2d9..c288cf7ecb 100644
> --- a/include/hw/virtio/vhost-vdpa.h
> +++ b/include/hw/virtio/vhost-vdpa.h
> @@ -13,6 +13,7 @@
>   #define HW_VIRTIO_VHOST_VDPA_H
>   
>   #include "hw/virtio/virtio.h"
> +#include "standard-headers/linux/vhost_types.h"
>   
>   typedef struct VhostVDPAHostNotifier {
>       MemoryRegion mr;
> @@ -24,6 +25,7 @@ typedef struct vhost_vdpa {
>       uint32_t msg_type;
>       bool iotlb_batch_begin_sent;
>       MemoryListener listener;
> +    struct vhost_vdpa_iova_range iova_range;
>       struct vhost_dev *dev;
>       VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX];
>   } VhostVDPA;
> diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
> index be7c63b4ba..7691e904ac 100644
> --- a/hw/virtio/vhost-vdpa.c
> +++ b/hw/virtio/vhost-vdpa.c
> @@ -37,20 +37,34 @@ static Int128 vhost_vdpa_section_end(const MemoryRegionSection *section)
>       return llend;
>   }
>   
> -static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section)
> -{
> -    return (!memory_region_is_ram(section->mr) &&
> -            !memory_region_is_iommu(section->mr)) ||
> -            memory_region_is_protected(section->mr) ||
> -           /* vhost-vDPA doesn't allow MMIO to be mapped  */
> -            memory_region_is_ram_device(section->mr) ||
> -           /*
> -            * Sizing an enabled 64-bit BAR can cause spurious mappings to
> -            * addresses in the upper part of the 64-bit address space.  These
> -            * are never accessed by the CPU and beyond the address width of
> -            * some IOMMU hardware.  TODO: VDPA should tell us the IOMMU width.
> -            */
> -           section->offset_within_address_space & (1ULL << 63);
> +static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section,
> +                                                uint64_t iova_min,
> +                                                uint64_t iova_max)
> +{
> +    Int128 llend;
> +
> +    if ((!memory_region_is_ram(section->mr) &&
> +         !memory_region_is_iommu(section->mr)) ||
> +        memory_region_is_protected(section->mr) ||
> +        /* vhost-vDPA doesn't allow MMIO to be mapped  */
> +        memory_region_is_ram_device(section->mr)) {
> +        return true;
> +    }
> +
> +    if (section->offset_within_address_space < iova_min) {
> +        error_report("RAM section out of device range (min=%lu, addr=%lu)",
> +                     iova_min, section->offset_within_address_space);
> +        return true;
> +    }
> +
> +    llend = vhost_vdpa_section_end(section);
> +    if (int128_gt(llend, int128_make64(iova_max))) {
> +        error_report("RAM section out of device range (max=%lu, end addr=%lu)",
> +                     iova_max, int128_get64(llend));
> +        return true;
> +    }
> +
> +    return false;
>   }
>   
>   static int vhost_vdpa_dma_map(struct vhost_vdpa *v, hwaddr iova, hwaddr size,
> @@ -162,7 +176,8 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
>       void *vaddr;
>       int ret;
>   
> -    if (vhost_vdpa_listener_skipped_section(section)) {
> +    if (vhost_vdpa_listener_skipped_section(section, v->iova_range.first,
> +                                            v->iova_range.last)) {
>           return;
>       }
>   
> @@ -220,7 +235,8 @@ static void vhost_vdpa_listener_region_del(MemoryListener *listener,
>       Int128 llend, llsize;
>       int ret;
>   
> -    if (vhost_vdpa_listener_skipped_section(section)) {
> +    if (vhost_vdpa_listener_skipped_section(section, v->iova_range.first,
> +                                            v->iova_range.last)) {
>           return;
>       }
>   
> @@ -288,6 +304,19 @@ static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status)
>       vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &s);
>   }
>   
> +static void vhost_vdpa_get_iova_range(struct vhost_vdpa *v)
> +{
> +    int ret = vhost_vdpa_call(v->dev, VHOST_VDPA_GET_IOVA_RANGE,
> +                              &v->iova_range);
> +    if (ret != 0) {
> +        v->iova_range.first = 0;
> +        v->iova_range.last = UINT64_MAX;
> +    }
> +
> +    trace_vhost_vdpa_get_iova_range(v->dev, v->iova_range.first,
> +                                    v->iova_range.last);
> +}
> +
>   static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp)
>   {
>       struct vhost_vdpa *v;
> @@ -300,6 +329,7 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp)
>       v->listener = vhost_vdpa_memory_listener;
>       v->msg_type = VHOST_IOTLB_MSG_V2;
>   
> +    vhost_vdpa_get_iova_range(v);
>       vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE |
>                                  VIRTIO_CONFIG_S_DRIVER);
>   
> diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
> index 8ed19e9d0c..650e521e35 100644
> --- a/hw/virtio/trace-events
> +++ b/hw/virtio/trace-events
> @@ -52,6 +52,7 @@ vhost_vdpa_set_vring_call(void *dev, unsigned int index, int fd) "dev: %p index:
>   vhost_vdpa_get_features(void *dev, uint64_t features) "dev: %p features: 0x%"PRIx64
>   vhost_vdpa_set_owner(void *dev) "dev: %p"
>   vhost_vdpa_vq_get_addr(void *dev, void *vq, uint64_t desc_user_addr, uint64_t avail_user_addr, uint64_t used_user_addr) "dev: %p vq: %p desc_user_addr: 0x%"PRIx64" avail_user_addr: 0x%"PRIx64" used_user_addr: 0x%"PRIx64
> +vhost_vdpa_get_iova_range(void *dev, uint64_t first, uint64_t last) "dev: %p first: 0x%"PRIx64" last: 0x%"PRIx64
>   
>   # virtio.c
>   virtqueue_alloc_element(void *elem, size_t sz, unsigned in_num, unsigned out_num) "elem %p size %zd in_num %u out_num %u"