Re: [EXT] [PATCH v2 2/5] virtio-iommu: Implement RESV_MEM probe request

[Auger Eric]

Hi Bharat,

On 5/11/20 10:42 AM, Bharat Bhushan wrote:
> Hi Eric,
> 
>> -----Original Message-----
>> From: Auger Eric <address@hidden>
>> Sent: Monday, May 11, 2020 12:26 PM
>> To: Bharat Bhushan <address@hidden>; address@hidden;
>> address@hidden; address@hidden; address@hidden;
>> address@hidden; address@hidden; address@hidden;
>> address@hidden; address@hidden
>> Subject: Re: [EXT] [PATCH v2 2/5] virtio-iommu: Implement RESV_MEM probe
>> request
>>
>> Hi Bharat,
>> On 5/11/20 8:38 AM, Bharat Bhushan wrote:
>>> Hi Eric,
>>>
>>>> -----Original Message-----
>>>> From: Eric Auger <address@hidden>
>>>> Sent: Friday, May 8, 2020 11:01 PM
>>>> To: address@hidden; address@hidden;
>>>> address@hidden; address@hidden; address@hidden;
>>>> address@hidden; jean- address@hidden; Bharat Bhushan
>>>> <address@hidden>; address@hidden; address@hidden;
>>>> address@hidden
>>>> Subject: [EXT] [PATCH v2 2/5] virtio-iommu: Implement RESV_MEM probe
>>>> request
>>>>
>>>> External Email
>>>>
>>>> ---------------------------------------------------------------------
>>>> - This patch implements the PROBE request. At the moment, only THE
>>>> RESV_MEM property is handled. The first goal is to report iommu wide
>>>> reserved regions such as the MSI regions set by the machine code. On
>>>> x86 this will be the IOAPIC MSI region,
>>>> [0xFEE00000 - 0xFEEFFFFF], on ARM this may be the ITS doorbell.
>>>>
>>>> In the future we may introduce per device reserved regions.
>>>> This will be useful when protecting host assigned devices which may
>>>> expose their own reserved regions
>>>>
>>>> Signed-off-by: Eric Auger <address@hidden>
>>>>
>>>> ---
>>>>
>>>> v1 -> v2:
>>>> - move the unlock back to the same place
>>>> - remove the push label and factorize the code after the out label
>>>> - fix a bunch of cpu_to_leX according to the latest spec revision
>>>> - do not remove sizeof(last) from free space
>>>> - check the ep exists
>>>> ---
>>>>  include/hw/virtio/virtio-iommu.h |  2 +
>>>>  hw/virtio/virtio-iommu.c         | 94 ++++++++++++++++++++++++++++++--
>>>>  hw/virtio/trace-events           |  1 +
>>>>  3 files changed, 93 insertions(+), 4 deletions(-)
>>>>
>>>> diff --git a/include/hw/virtio/virtio-iommu.h
>>>> b/include/hw/virtio/virtio-iommu.h
>>>> index e653004d7c..49eb105cd8 100644
>>>> --- a/include/hw/virtio/virtio-iommu.h
>>>> +++ b/include/hw/virtio/virtio-iommu.h
>>>> @@ -53,6 +53,8 @@ typedef struct VirtIOIOMMU {
>>>>      GHashTable *as_by_busptr;
>>>>      IOMMUPciBus *iommu_pcibus_by_bus_num[PCI_BUS_MAX];
>>>>      PCIBus *primary_bus;
>>>> +    ReservedRegion *reserved_regions;
>>>> +    uint32_t nb_reserved_regions;
>>>>      GTree *domains;
>>>>      QemuMutex mutex;
>>>>      GTree *endpoints;
>>>> diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c
>>>> index
>>>> 22ba8848c2..35d772e021 100644
>>>> --- a/hw/virtio/virtio-iommu.c
>>>> +++ b/hw/virtio/virtio-iommu.c
>>>> @@ -38,6 +38,7 @@
>>>>
>>>>  /* Max size */
>>>>  #define VIOMMU_DEFAULT_QUEUE_SIZE 256
>>>> +#define VIOMMU_PROBE_SIZE 512
>>>>
>>>>  typedef struct VirtIOIOMMUDomain {
>>>>      uint32_t id;
>>>> @@ -378,6 +379,65 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s,
>>>>      return ret;
>>>>  }
>>>>
>>>> +static ssize_t virtio_iommu_fill_resv_mem_prop(VirtIOIOMMU *s, uint32_t 
>>>> ep,
>>>> +                                               uint8_t *buf, size_t
>>>> +free) {
>>>> +    struct virtio_iommu_probe_resv_mem prop = {};
>>>> +    size_t size = sizeof(prop), length = size - sizeof(prop.head), total;
>>>> +    int i;
>>>> +
>>>> +    total = size * s->nb_reserved_regions;
>>>> +
>>>> +    if (total > free) {
>>>> +        return -ENOSPC;
>>>> +    }
>>>> +
>>>> +    for (i = 0; i < s->nb_reserved_regions; i++) {
>>>> +        prop.head.type = cpu_to_le16(VIRTIO_IOMMU_PROBE_T_RESV_MEM);
>>>> +        prop.head.length = cpu_to_le16(length);
>>>> +        prop.subtype = s->reserved_regions[i].type;
>>>> +        prop.start = cpu_to_le64(s->reserved_regions[i].low);
>>>> +        prop.end = cpu_to_le64(s->reserved_regions[i].high);
>>>> +
>>>> +        memcpy(buf, &prop, size);
>>>> +
>>>> +        trace_virtio_iommu_fill_resv_property(ep, prop.subtype,
>>>> +                                              prop.start, prop.end);
>>>> +        buf += size;
>>>> +    }
>>>> +    return total;
>>>> +}
>>>> +
>>>> +/**
>>>> + * virtio_iommu_probe - Fill the probe request buffer with
>>>> + * the properties the device is able to return and add a NONE
>>>> + * property at the end.
>>>> + */
>>>> +static int virtio_iommu_probe(VirtIOIOMMU *s,
>>>> +                              struct virtio_iommu_req_probe *req,
>>>> +                              uint8_t *buf) {
>>>> +    uint32_t ep_id = le32_to_cpu(req->endpoint);
>>>> +    size_t free = VIOMMU_PROBE_SIZE;
>>>> +    ssize_t count;
>>>> +
>>>> +    if (!virtio_iommu_mr(s, ep_id)) {
>>>> +        return VIRTIO_IOMMU_S_NOENT;
>>>> +    }
>>>> +
>>>> +    count = virtio_iommu_fill_resv_mem_prop(s, ep_id, buf, free);
>>>> +    if (count < 0) {
>>>> +        return VIRTIO_IOMMU_S_INVAL;
>>>> +    }
>>>> +    buf += count;
>>>> +    free -= count;
>>>> +
>>>> +    /* Fill the rest with zeroes */
>>>> +    memset(buf, 0, free);
>>>
>>> No need to fill with zero here as "buf" is set to zero on allocation, no?
>>
>> You're right. I will remove this in the next version.
>>
>> Thanks
>>
>> Eric
>>>
>>> Thanks
>>> -Bharat
>>>
>>>> +
>>>> +    return VIRTIO_IOMMU_S_OK;
>>>> +}
>>>> +
>>>>  static int virtio_iommu_iov_to_req(struct iovec *iov,
>>>>                                     unsigned int iov_cnt,
>>>>                                     void *req, size_t req_sz) @@
>>>> -407,15 +467,27 @@
>>>> virtio_iommu_handle_req(detach)
>>>>  virtio_iommu_handle_req(map)
>>>>  virtio_iommu_handle_req(unmap)
>>>>
>>>> +static int virtio_iommu_handle_probe(VirtIOIOMMU *s,
>>>> +                                     struct iovec *iov,
>>>> +                                     unsigned int iov_cnt,
>>>> +                                     uint8_t *buf) {
>>>> +    struct virtio_iommu_req_probe req;
>>>> +    int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req,
>>>> +sizeof(req));
>>>> +
>>>> +    return ret ? ret : virtio_iommu_probe(s, &req, buf); }
>>>> +
>>>>  static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue
>> *vq)  {
>>>>      VirtIOIOMMU *s = VIRTIO_IOMMU(vdev);
>>>>      struct virtio_iommu_req_head head;
>>>>      struct virtio_iommu_req_tail tail = {};
>>>> +    size_t output_size = sizeof(tail), sz;
>>>>      VirtQueueElement *elem;
>>>>      unsigned int iov_cnt;
>>>>      struct iovec *iov;
>>>> -    size_t sz;
>>>> +    void *buf = NULL;
>>>>
>>>>      for (;;) {
>>>>          elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); @@
>>>> -452,6 +524,17 @@ static void virtio_iommu_handle_command(VirtIODevice
>> *vdev, VirtQueue *vq)
>>>>          case VIRTIO_IOMMU_T_UNMAP:
>>>>              tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt);
>>>>              break;
>>>> +        case VIRTIO_IOMMU_T_PROBE:
> 
> As per spec
>   "
>    If the device does not offer the VIRTIO_IOMMU_F_PROBE feature, and if the 
> driver sends a VIRTIO_-
>    IOMMU_T_PROBE request, then the device SHOULD NOT write the buffer and 
> SHOULD set the used
>    length to zero.
>   "
> So we should check if device supports "VIRTIO_IOMMU_F_PROBE" before proceed?
But are the device and from that patch onwards we do support the
VIRTIO_IOMMU_F_PROBE feature, right?

Thanks

Eric
> 
> Thanks
> -Bharat
> 
>>>> +        {
>>>> +            struct virtio_iommu_req_tail *ptail;
>>>> +
>>>> +            output_size = s->config.probe_size + sizeof(tail);
>>>> +            buf = g_malloc0(output_size);
>>>> +
>>>> +            ptail = (struct virtio_iommu_req_tail *)
>>>> +                        (buf + s->config.probe_size);
>>>> +            ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, 
>>>> buf);
>>>> +        }
>>>>          default:
>>>>              tail.status = VIRTIO_IOMMU_S_UNSUPP;
>>>>          }
>>>> @@ -459,12 +542,13 @@ static void
>>>> virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq)
>>>>
>>>>  out:
>>>>          sz = iov_from_buf(elem->in_sg, elem->in_num, 0,
>>>> -                          &tail, sizeof(tail));
>>>> -        assert(sz == sizeof(tail));
>>>> +                          buf ? buf : &tail, output_size);
>>>> +        assert(sz == output_size);
>>>>
>>>> -        virtqueue_push(vq, elem, sizeof(tail));
>>>> +        virtqueue_push(vq, elem, sz);
>>>>          virtio_notify(vdev, vq);
>>>>          g_free(elem);
>>>> +        g_free(buf);
>>>>      }
>>>>  }
>>>>
>>>> @@ -667,6 +751,7 @@ static void
>>>> virtio_iommu_device_realize(DeviceState *dev, Error **errp)
>>>>      s->config.page_size_mask = TARGET_PAGE_MASK;
>>>>      s->config.input_range.end = -1UL;
>>>>      s->config.domain_range.end = 32;
>>>> +    s->config.probe_size = VIOMMU_PROBE_SIZE;
>>>>
>>>>      virtio_add_feature(&s->features, VIRTIO_RING_F_EVENT_IDX);
>>>>      virtio_add_feature(&s->features, VIRTIO_RING_F_INDIRECT_DESC);
>>>> @@ -676,6
>>>> +761,7 @@ static void virtio_iommu_device_realize(DeviceState *dev,
>>>> +Error
>>>> **errp)
>>>>      virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MAP_UNMAP);
>>>>      virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS);
>>>>      virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MMIO);
>>>> +    virtio_add_feature(&s->features, VIRTIO_IOMMU_F_PROBE);
>>>>
>>>>      qemu_mutex_init(&s->mutex);
>>>>
>>>> diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index
>>>> e83500bee9..5550475691 100644
>>>> --- a/hw/virtio/trace-events
>>>> +++ b/hw/virtio/trace-events
>>>> @@ -73,3 +73,4 @@ virtio_iommu_get_domain(uint32_t domain_id) "Alloc
>>>> domain=%d"
>>>>  virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d"
>>>>  virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr,
>>>> uint32_t sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d"
>>>>  virtio_iommu_report_fault(uint8_t reason, uint32_t flags, uint32_t
>>>> endpoint, uint64_t addr) "FAULT reason=%d flags=%d endpoint=%d
>>>> address =0x%"PRIx64
>>>> +virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype,
>>>> +uint64_t start, uint64_t end) "dev= %d, type=%d start=0x%"PRIx64"
>>>> +end=0x%"PRIx64
>>>> --
>>>> 2.20.1
>>>
>>>
>