Re: [PATCH v4 6/7] iommu/virtio: Add probe request
Hi Jean,
On 11/15/18 5:52 PM, Jean-Philippe Brucker wrote:
> When the device offers the probe feature, send a probe request for each
> device managed by the IOMMU. Extract RESV_MEM information. When we
> encounter a MSI doorbell region, set it up as a IOMMU_RESV_MSI region.
> This will tell other subsystems that there is no need to map the MSI
> doorbell in the virtio-iommu, because MSIs bypass it.
>
> Signed-off-by: Jean-Philippe Brucker
Reviewed-by: Eric Auger
Thanks
Eric
> ---
> drivers/iommu/virtio-iommu.c | 156 --
> include/uapi/linux/virtio_iommu.h | 38
> 2 files changed, 188 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
> index 2a9cb6285a1e..c547ebd79c43 100644
> --- a/drivers/iommu/virtio-iommu.c
> +++ b/drivers/iommu/virtio-iommu.c
> @@ -46,6 +46,7 @@ struct viommu_dev {
> struct iommu_domain_geometrygeometry;
> u64 pgsize_bitmap;
> u8 domain_bits;
> + u32 probe_size;
> };
>
> struct viommu_mapping {
> @@ -67,8 +68,10 @@ struct viommu_domain {
> };
>
> struct viommu_endpoint {
> + struct device *dev;
> struct viommu_dev *viommu;
> struct viommu_domain*vdomain;
> + struct list_headresv_regions;
> };
>
> struct viommu_request {
> @@ -119,6 +122,9 @@ static off_t viommu_get_req_offset(struct viommu_dev
> *viommu,
> {
> size_t tail_size = sizeof(struct virtio_iommu_req_tail);
>
> + if (req->type == VIRTIO_IOMMU_T_PROBE)
> + return len - viommu->probe_size - tail_size;
> +
> return len - tail_size;
> }
>
> @@ -394,6 +400,110 @@ static int viommu_replay_mappings(struct viommu_domain
> *vdomain)
> return ret;
> }
>
> +static int viommu_add_resv_mem(struct viommu_endpoint *vdev,
> +struct virtio_iommu_probe_resv_mem *mem,
> +size_t len)
> +{
> + size_t size;
> + u64 start64, end64;
> + phys_addr_t start, end;
> + struct iommu_resv_region *region = NULL;
> + unsigned long prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
> +
> + start = start64 = le64_to_cpu(mem->start);
> + end = end64 = le64_to_cpu(mem->end);
> + size = end64 - start64 + 1;
> +
> + /* Catch any overflow, including the unlikely end64 - start64 + 1 = 0 */
> + if (start != start64 || end != end64 || size < end64 - start64)
> + return -EOVERFLOW;
> +
> + if (len < sizeof(*mem))
> + return -EINVAL;
> +
> + switch (mem->subtype) {
> + default:
> + dev_warn(vdev->dev, "unknown resv mem subtype 0x%x\n",
> + mem->subtype);
> + /* Fall-through */
> + case VIRTIO_IOMMU_RESV_MEM_T_RESERVED:
> + region = iommu_alloc_resv_region(start, size, 0,
> + IOMMU_RESV_RESERVED);
> + break;
> + case VIRTIO_IOMMU_RESV_MEM_T_MSI:
> + region = iommu_alloc_resv_region(start, size, prot,
> + IOMMU_RESV_MSI);
> + break;
> + }
> + if (!region)
> + return -ENOMEM;
> +
> + list_add(>resv_regions, >list);
> + return 0;
> +}
> +
> +static int viommu_probe_endpoint(struct viommu_dev *viommu, struct device
> *dev)
> +{
> + int ret;
> + u16 type, len;
> + size_t cur = 0;
> + size_t probe_len;
> + struct virtio_iommu_req_probe *probe;
> + struct virtio_iommu_probe_property *prop;
> + struct iommu_fwspec *fwspec = dev->iommu_fwspec;
> + struct viommu_endpoint *vdev = fwspec->iommu_priv;
> +
> + if (!fwspec->num_ids)
> + return -EINVAL;
> +
> + probe_len = sizeof(*probe) + viommu->probe_size +
> + sizeof(struct virtio_iommu_req_tail);
> + probe = kzalloc(probe_len, GFP_KERNEL);
> + if (!probe)
> + return -ENOMEM;
> +
> + probe->head.type = VIRTIO_IOMMU_T_PROBE;
> + /*
> + * For now, assume that properties of an endpoint that outputs multiple
> + * IDs are consistent. Only probe the first one.
> + */
> + probe->endpoint = cpu_to_le32(fwspec->ids[0]);
> +
> + ret = viommu_send_req_sync(viommu, probe, probe_len);
> + if (ret)
> + goto out_free;
> +
> + prop = (void *)probe->properties;
> + type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK;
> +
> + while (type != VIRTIO_IOMMU_PROBE_T_NONE &&
> +cur < viommu->probe_size) {
> + len = le16_to_cpu(prop->length) + sizeof(*prop);
> +
> + switch (type) {
> + case VIRTIO_IOMMU_PROBE_T_RESV_MEM:
> + ret = viommu_add_resv_mem(vdev, (void *)prop, len);
> + break;
> + default:
> +
[PATCH v4 6/7] iommu/virtio: Add probe request
When the device offers the probe feature, send a probe request for each
device managed by the IOMMU. Extract RESV_MEM information. When we
encounter a MSI doorbell region, set it up as a IOMMU_RESV_MSI region.
This will tell other subsystems that there is no need to map the MSI
doorbell in the virtio-iommu, because MSIs bypass it.
Signed-off-by: Jean-Philippe Brucker
---
drivers/iommu/virtio-iommu.c | 156 --
include/uapi/linux/virtio_iommu.h | 38
2 files changed, 188 insertions(+), 6 deletions(-)
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 2a9cb6285a1e..c547ebd79c43 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -46,6 +46,7 @@ struct viommu_dev {
struct iommu_domain_geometrygeometry;
u64 pgsize_bitmap;
u8 domain_bits;
+ u32 probe_size;
};
struct viommu_mapping {
@@ -67,8 +68,10 @@ struct viommu_domain {
};
struct viommu_endpoint {
+ struct device *dev;
struct viommu_dev *viommu;
struct viommu_domain*vdomain;
+ struct list_headresv_regions;
};
struct viommu_request {
@@ -119,6 +122,9 @@ static off_t viommu_get_req_offset(struct viommu_dev
*viommu,
{
size_t tail_size = sizeof(struct virtio_iommu_req_tail);
+ if (req->type == VIRTIO_IOMMU_T_PROBE)
+ return len - viommu->probe_size - tail_size;
+
return len - tail_size;
}
@@ -394,6 +400,110 @@ static int viommu_replay_mappings(struct viommu_domain
*vdomain)
return ret;
}
+static int viommu_add_resv_mem(struct viommu_endpoint *vdev,
+ struct virtio_iommu_probe_resv_mem *mem,
+ size_t len)
+{
+ size_t size;
+ u64 start64, end64;
+ phys_addr_t start, end;
+ struct iommu_resv_region *region = NULL;
+ unsigned long prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+ start = start64 = le64_to_cpu(mem->start);
+ end = end64 = le64_to_cpu(mem->end);
+ size = end64 - start64 + 1;
+
+ /* Catch any overflow, including the unlikely end64 - start64 + 1 = 0 */
+ if (start != start64 || end != end64 || size < end64 - start64)
+ return -EOVERFLOW;
+
+ if (len < sizeof(*mem))
+ return -EINVAL;
+
+ switch (mem->subtype) {
+ default:
+ dev_warn(vdev->dev, "unknown resv mem subtype 0x%x\n",
+mem->subtype);
+ /* Fall-through */
+ case VIRTIO_IOMMU_RESV_MEM_T_RESERVED:
+ region = iommu_alloc_resv_region(start, size, 0,
+IOMMU_RESV_RESERVED);
+ break;
+ case VIRTIO_IOMMU_RESV_MEM_T_MSI:
+ region = iommu_alloc_resv_region(start, size, prot,
+IOMMU_RESV_MSI);
+ break;
+ }
+ if (!region)
+ return -ENOMEM;
+
+ list_add(>resv_regions, >list);
+ return 0;
+}
+
+static int viommu_probe_endpoint(struct viommu_dev *viommu, struct device *dev)
+{
+ int ret;
+ u16 type, len;
+ size_t cur = 0;
+ size_t probe_len;
+ struct virtio_iommu_req_probe *probe;
+ struct virtio_iommu_probe_property *prop;
+ struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+ struct viommu_endpoint *vdev = fwspec->iommu_priv;
+
+ if (!fwspec->num_ids)
+ return -EINVAL;
+
+ probe_len = sizeof(*probe) + viommu->probe_size +
+ sizeof(struct virtio_iommu_req_tail);
+ probe = kzalloc(probe_len, GFP_KERNEL);
+ if (!probe)
+ return -ENOMEM;
+
+ probe->head.type = VIRTIO_IOMMU_T_PROBE;
+ /*
+* For now, assume that properties of an endpoint that outputs multiple
+* IDs are consistent. Only probe the first one.
+*/
+ probe->endpoint = cpu_to_le32(fwspec->ids[0]);
+
+ ret = viommu_send_req_sync(viommu, probe, probe_len);
+ if (ret)
+ goto out_free;
+
+ prop = (void *)probe->properties;
+ type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK;
+
+ while (type != VIRTIO_IOMMU_PROBE_T_NONE &&
+ cur < viommu->probe_size) {
+ len = le16_to_cpu(prop->length) + sizeof(*prop);
+
+ switch (type) {
+ case VIRTIO_IOMMU_PROBE_T_RESV_MEM:
+ ret = viommu_add_resv_mem(vdev, (void *)prop, len);
+ break;
+ default:
+ dev_err(dev, "unknown viommu prop 0x%x\n", type);
+ }
+
+ if (ret)
+ dev_err(dev, "failed to parse viommu prop 0x%x\n",
type);
+
+ cur +=
