[Qemu-devel] [RFC v6 11/22] virtio-iommu: Implement map/unmap

[Eric Auger <eric.auger@redhat.com>]

This patch implements virtio_iommu_map/unmap.

Signed-off-by: Eric Auger <eric.auger@redhat.com>

---

v5 -> v6:
- use new v0.6 fields
- replace error_report by qemu_log_mask

v3 -> v4:
- implement unmap semantics as specified in v0.4
---
 hw/virtio/trace-events   |  3 ++
 hw/virtio/virtio-iommu.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 95 insertions(+), 2 deletions(-)

diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index a7743d2..7f7ea50 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -48,3 +48,6 @@ virtio_iommu_get_endpoint(uint32_t ep_id) "Alloc endpoint=%d"
 virtio_iommu_put_endpoint(uint32_t ep_id) "Free endpoint=%d"
 virtio_iommu_get_domain(uint32_t domain_id) "Alloc domain=%d"
 virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d"
+virtio_iommu_unmap_left_interval(uint64_t low, uint64_t high, uint64_t next_low, uint64_t next_high) "Unmap left [0x%"PRIx64",0x%"PRIx64"], new interval=[0x%"PRIx64",0x%"PRIx64"]"
+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"]"
diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c
index 69ff516..1986565 100644
--- a/hw/virtio/virtio-iommu.c
+++ b/hw/virtio/virtio-iommu.c
@@ -18,6 +18,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "qemu/iov.h"
 #include "qemu-common.h"
 #include "hw/virtio/virtio.h"
@@ -59,6 +60,13 @@ typedef struct viommu_interval {
     uint64_t high;
 } viommu_interval;
 
+typedef struct viommu_mapping {
+    uint64_t virt_addr;
+    uint64_t phys_addr;
+    uint64_t size;
+    uint32_t flags;
+} viommu_mapping;
+
 static inline uint16_t virtio_iommu_get_sid(IOMMUDevice *dev)
 {
     return PCI_BUILD_BDF(pci_bus_num(dev->bus), dev->devfn);
@@ -254,10 +262,37 @@ static int virtio_iommu_map(VirtIOIOMMU *s,
     uint64_t virt_start = le64_to_cpu(req->virt_start);
     uint64_t virt_end = le64_to_cpu(req->virt_end);
     uint32_t flags = le32_to_cpu(req->flags);
+    viommu_domain *domain;
+    viommu_interval *interval;
+    viommu_mapping *mapping;
+
+    interval = g_malloc0(sizeof(*interval));
+
+    interval->low = virt_start;
+    interval->high = virt_end;
+
+    domain = g_tree_lookup(s->domains, GUINT_TO_POINTER(domain_id));
+    if (!domain) {
+        return VIRTIO_IOMMU_S_NOENT;
+    }
+
+    mapping = g_tree_lookup(domain->mappings, (gpointer)interval);
+    if (mapping) {
+        g_free(interval);
+        return VIRTIO_IOMMU_S_INVAL;
+    }
 
     trace_virtio_iommu_map(domain_id, virt_start, virt_end, phys_start, flags);
 
-    return VIRTIO_IOMMU_S_UNSUPP;
+    mapping = g_malloc0(sizeof(*mapping));
+    mapping->virt_addr = virt_start;
+    mapping->phys_addr = phys_start;
+    mapping->size = virt_end - virt_start + 1;
+    mapping->flags = flags;
+
+    g_tree_insert(domain->mappings, interval, mapping);
+
+    return VIRTIO_IOMMU_S_OK;
 }
 
 static int virtio_iommu_unmap(VirtIOIOMMU *s,
@@ -266,10 +301,65 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s,
     uint32_t domain_id = le32_to_cpu(req->domain);
     uint64_t virt_start = le64_to_cpu(req->virt_start);
     uint64_t virt_end = le64_to_cpu(req->virt_end);
+    uint64_t size = virt_end - virt_start + 1;
+    viommu_mapping *mapping;
+    viommu_interval interval;
+    viommu_domain *domain;
 
     trace_virtio_iommu_unmap(domain_id, virt_start, virt_end);
 
-    return VIRTIO_IOMMU_S_UNSUPP;
+    domain = g_tree_lookup(s->domains, GUINT_TO_POINTER(domain_id));
+    if (!domain) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: no domain\n", __func__);
+        return VIRTIO_IOMMU_S_NOENT;
+    }
+    interval.low = virt_start;
+    interval.high = virt_end;
+
+    mapping = g_tree_lookup(domain->mappings, (gpointer)(&interval));
+
+    while (mapping) {
+        viommu_interval current;
+        uint64_t low  = mapping->virt_addr;
+        uint64_t high = mapping->virt_addr + mapping->size - 1;
+
+        current.low = low;
+        current.high = high;
+
+        if (low == interval.low && size >= mapping->size) {
+            g_tree_remove(domain->mappings, (gpointer)(&current));
+            interval.low = high + 1;
+            trace_virtio_iommu_unmap_left_interval(current.low, current.high,
+                interval.low, interval.high);
+        } else if (high == interval.high && size >= mapping->size) {
+            trace_virtio_iommu_unmap_right_interval(current.low, current.high,
+                interval.low, interval.high);
+            g_tree_remove(domain->mappings, (gpointer)(&current));
+            interval.high = low - 1;
+        } else if (low > interval.low && high < interval.high) {
+            trace_virtio_iommu_unmap_inc_interval(current.low, current.high);
+            g_tree_remove(domain->mappings, (gpointer)(&current));
+        } else {
+            break;
+        }
+        if (interval.low >= interval.high) {
+            return VIRTIO_IOMMU_S_OK;
+        } else {
+            mapping = g_tree_lookup(domain->mappings, (gpointer)(&interval));
+        }
+    }
+
+    if (mapping) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "****** %s: Unmap 0x%"PRIx64" size=0x%"PRIx64
+                     " from 0x%"PRIx64" size=0x%"PRIx64" is not supported\n",
+                     __func__, interval.low, size,
+                     mapping->virt_addr, mapping->size);
+    } else {
+        return VIRTIO_IOMMU_S_OK;
+    }
+
+    return VIRTIO_IOMMU_S_INVAL;
 }
 
 #define get_payload_size(req) (\
-- 
1.9.1