[Qemu-devel] [RFC v4 10/16] virtio-iommu: Implement probe request

[Eric Auger]

This patch implements the PROBE request. At the moment,
no reserved regions are returned.

At the moment reserved regions are stored per device.

Signed-off-by: Eric Auger <address@hidden>

---

Waiting for clarifications on v0.4 spec
---
 hw/virtio/trace-events   |   2 +
 hw/virtio/virtio-iommu.c | 173 ++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 173 insertions(+), 2 deletions(-)

diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 9010fbd..9ccfad1 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -46,3 +46,5 @@ virtio_iommu_unmap_left_interval(uint64_t low, uint64_t high, 
uint64_t next_low,
 virtio_iommu_unmap_right_interval(uint64_t low, uint64_t high, uint64_t 
next_low, uint64_t next_high) "Unmap right [0x%"PRIx64",0x%"PRIx64"], new 
interval=[0x%"PRIx64",0x%"PRIx64"]"
 virtio_iommu_unmap_inc_interval(uint64_t low, uint64_t high) "Unmap inc 
[0x%"PRIx64",0x%"PRIx64"]"
 virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr, uint32_t 
sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d"
+virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype, uint64_t 
addr, uint64_t size, uint32_t flags, size_t filled) "dev= %d, subtype=%d 
addr=0x%"PRIx64" size=0x%"PRIx64" flags=%d filled=0x%lx"
+virtio_iommu_fill_none_property(uint32_t devid) "devid=%d"
diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c
index db46a91..281b0f8 100644
--- a/hw/virtio/virtio-iommu.c
+++ b/hw/virtio/virtio-iommu.c
@@ -37,6 +37,11 @@
 
 /* Max size */
 #define VIOMMU_DEFAULT_QUEUE_SIZE 256
+#define VIOMMU_PROBE_SIZE 512
+
+#define SUPPORTED_PROBE_PROPERTIES (\
+    VIRTIO_IOMMU_PROBE_T_NONE | \
+    VIRTIO_IOMMU_PROBE_T_RESV_MEM)
 
 typedef struct viommu_as {
     uint32_t id;
@@ -49,6 +54,7 @@ typedef struct viommu_dev {
     viommu_as *as;
     QLIST_ENTRY(viommu_dev) next;
     VirtIOIOMMU *viommu;
+    GTree *reserved_regions;
 } viommu_dev;
 
 typedef struct viommu_interval {
@@ -63,6 +69,13 @@ typedef struct viommu_mapping {
     uint32_t flags;
 } viommu_mapping;
 
+typedef struct viommu_property_buffer {
+    viommu_dev *dev;
+    size_t filled;
+    uint8_t *start;
+    bool error;
+} viommu_property_buffer;
+
 static inline uint16_t virtio_iommu_get_sid(IOMMUDevice *dev)
 {
     return PCI_BUILD_BDF(pci_bus_num(dev->bus), dev->devfn);
@@ -101,6 +114,9 @@ static viommu_dev *virtio_iommu_get_dev(VirtIOIOMMU *s, 
uint32_t devid)
     dev->viommu = s;
     trace_virtio_iommu_get_dev(devid);
     g_tree_insert(s->devices, GUINT_TO_POINTER(devid), dev);
+    dev->reserved_regions = g_tree_new_full((GCompareDataFunc)interval_cmp,
+                                            NULL, (GDestroyNotify)g_free,
+                                            (GDestroyNotify)g_free);
     return dev;
 }
 
@@ -114,6 +130,7 @@ static void virtio_iommu_put_dev(gpointer data)
     }
 
     trace_virtio_iommu_put_dev(dev->id);
+    g_tree_destroy(dev->reserved_regions);
     g_free(dev);
 }
 
@@ -369,6 +386,123 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s,
     return VIRTIO_IOMMU_S_INVAL;
 }
 
+static gboolean virtio_iommu_fill_resv_mem_prop(gpointer key,
+                                                gpointer value,
+                                                gpointer data)
+{
+    struct virtio_iommu_probe_resv_mem *resv =
+        (struct virtio_iommu_probe_resv_mem *)value;
+    struct virtio_iommu_probe_property *prop;
+    struct virtio_iommu_probe_resv_mem *current;
+    viommu_property_buffer *bufstate = (viommu_property_buffer *)data;
+    size_t size = sizeof(*resv), total_size;
+
+    total_size = size + 4;
+
+    if (bufstate->filled >= VIOMMU_PROBE_SIZE) {
+        bufstate->error = true;
+        return true;
+    }
+    prop = (struct virtio_iommu_probe_property *)
+                (bufstate->start + bufstate->filled);
+    prop->type = cpu_to_le16(VIRTIO_IOMMU_PROBE_T_RESV_MEM) &
+                    VIRTIO_IOMMU_PROBE_T_MASK;
+    prop->length = size;
+
+    current = (struct virtio_iommu_probe_resv_mem *)prop->value;
+    *current = *resv;
+    bufstate->filled += total_size;
+    trace_virtio_iommu_fill_resv_property(bufstate->dev->id,
+                                          resv->subtype, resv->addr,
+                                          resv->size, resv->flags,
+                                          bufstate->filled);
+    return false;
+}
+
+static int virtio_iommu_fill_none_prop(viommu_property_buffer *bufstate)
+{
+    struct virtio_iommu_probe_property *prop;
+
+    prop = (struct virtio_iommu_probe_property *)
+                (bufstate->start + bufstate->filled);
+    prop->type = cpu_to_le16(VIRTIO_IOMMU_PROBE_T_NONE)
+                    & VIRTIO_IOMMU_PROBE_T_MASK;
+    prop->length = 0;
+    bufstate->filled += 4;
+    trace_virtio_iommu_fill_none_property(bufstate->dev->id);
+    return 0;
+}
+
+static int virtio_iommu_fill_property(int devid, int type,
+                                      viommu_property_buffer *bufstate)
+{
+    int ret = -ENOSPC;
+
+    if (bufstate->filled + 4 >= VIOMMU_PROBE_SIZE) {
+        bufstate->error = true;
+        goto out;
+    }
+
+    switch (type) {
+    case VIRTIO_IOMMU_PROBE_T_NONE:
+        ret = virtio_iommu_fill_none_prop(bufstate);
+        break;
+    case VIRTIO_IOMMU_PROBE_T_RESV_MEM:
+    {
+        viommu_dev *dev = bufstate->dev;
+
+        g_tree_foreach(dev->reserved_regions,
+                       virtio_iommu_fill_resv_mem_prop,
+                       bufstate);
+        if (!bufstate->error) {
+            ret = 0;
+        }
+        break;
+    }
+    default:
+        ret = -ENOENT;
+        break;
+    }
+out:
+    if (ret) {
+        error_report("%s property of type=%d could not be filled (%d),"
+                     " remaining size = 0x%lx",
+                     __func__, type, ret, bufstate->filled);
+    }
+    return ret;
+}
+
+static int virtio_iommu_probe(VirtIOIOMMU *s,
+                              struct virtio_iommu_req_probe *req,
+                              uint8_t *buf)
+{
+    uint32_t devid = le32_to_cpu(req->device);
+    int16_t prop_types = SUPPORTED_PROBE_PROPERTIES, type;
+    viommu_property_buffer bufstate;
+    viommu_dev *dev;
+    int ret;
+
+    dev = g_tree_lookup(s->devices, GUINT_TO_POINTER(devid));
+    if (!dev) {
+        return -EINVAL;
+    }
+
+    bufstate.start = buf;
+    bufstate.filled = 0;
+    bufstate.dev = dev;
+
+    while ((type = ctz32(prop_types)) != 32) {
+        ret = virtio_iommu_fill_property(devid, 1 << type, &bufstate);
+        if (ret) {
+            break;
+        }
+        prop_types &= ~(1 << type);
+    }
+    virtio_iommu_fill_property(devid, VIRTIO_IOMMU_PROBE_T_NONE, &bufstate);
+
+    return VIRTIO_IOMMU_S_OK;
+}
+
 #define get_payload_size(req) (\
 sizeof((req)) - sizeof(struct virtio_iommu_req_tail))
 
@@ -433,6 +567,24 @@ static int virtio_iommu_handle_unmap(VirtIOIOMMU *s,
     return virtio_iommu_unmap(s, &req);
 }
 
+static int virtio_iommu_handle_probe(VirtIOIOMMU *s,
+                                     struct iovec *iov,
+                                     unsigned int iov_cnt,
+                                     uint8_t *buf)
+{
+    struct virtio_iommu_req_probe req;
+    size_t sz, payload_sz;
+
+    payload_sz = get_payload_size(req);
+
+    sz = iov_to_buf(iov, iov_cnt, 0, &req, payload_sz);
+    if (sz != payload_sz) {
+        return VIRTIO_IOMMU_S_INVAL;
+    }
+
+    return virtio_iommu_probe(s, &req, buf);
+}
+
 static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq)
 {
     VirtIOIOMMU *s = VIRTIO_IOMMU(vdev);
@@ -477,16 +629,31 @@ 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:
+        {
+            struct virtio_iommu_req_tail *ptail;
+            uint8_t *buf = g_malloc0(s->config.probe_size + sizeof(tail));
+
+            ptail = (struct virtio_iommu_req_tail *)buf + s->config.probe_size;
+            ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf);
+
+            sz = iov_from_buf(elem->in_sg, elem->in_num, 0,
+                              buf, s->config.probe_size + sizeof(tail));
+            g_free(buf);
+            assert(sz == s->config.probe_size + sizeof(tail));
+            goto push;
+        }
         default:
             tail.status = VIRTIO_IOMMU_S_UNSUPP;
         }
-        qemu_mutex_unlock(&s->mutex);
 
         sz = iov_from_buf(elem->in_sg, elem->in_num, 0,
                           &tail, sizeof(tail));
         assert(sz == sizeof(tail));
 
-        virtqueue_push(vq, elem, sizeof(tail));
+push:
+        qemu_mutex_unlock(&s->mutex);
+        virtqueue_push(vq, elem, sz);
         virtio_notify(vdev, vq);
         g_free(elem);
     }
@@ -574,6 +741,7 @@ static uint64_t virtio_iommu_get_features(VirtIODevice 
*vdev, uint64_t f,
     virtio_add_feature(&f, VIRTIO_RING_F_INDIRECT_DESC);
     virtio_add_feature(&f, VIRTIO_IOMMU_F_INPUT_RANGE);
     virtio_add_feature(&f, VIRTIO_IOMMU_F_MAP_UNMAP);
+    virtio_add_feature(&f, VIRTIO_IOMMU_F_PROBE);
     return f;
 }
 
@@ -631,6 +799,7 @@ 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.probe_size = VIOMMU_PROBE_SIZE;
 
     qemu_mutex_init(&s->mutex);
 
-- 
2.5.5