intel_iommu: Fix DMA failure when guest switches IOMMU domain

Kernel allows user to switch IOMMU domain, e.g., switch between DMA
and identity domain. When this happen in IOMMU scalable mode, a pasid
cache invalidation request is sent, this request is ignored by vIOMMU
which leads to device binding to wrong address space, then DMA fails.

This issue exists in scalable mode with both first stage and second
stage translations, both emulated and passthrough devices.

Take network device for example, below sequence trigger issue:

1. start a guest with iommu=pt
2. echo 0000:01:00.0 > /sys/bus/pci/drivers/virtio-pci/unbind
3. echo DMA > /sys/kernel/iommu_groups/6/type
4. echo 0000:01:00.0 > /sys/bus/pci/drivers/virtio-pci/bind
5. Ping test

Fix it by switching address space in invalidation handler.

Fixes: 4a4f219e8a10 ("intel_iommu: add scalable-mode option to make scalable mode work")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20251017093602.525338-4-zhenzhong.duan@intel.com>

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index cf0b62f29e972de46f867929b443b9d0f09526a2..78b142cceab3c4bb08ce1151930722135ed2717c 100644 (file)
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -3086,6 +3086,11 @@ static inline int vtd_dev_get_pe_from_pasid(VTDAddressSpace *vtd_as,
     return vtd_ce_get_rid2pasid_entry(s, &ce, pe, vtd_as->pasid);
 }
 
+static int vtd_pasid_entry_compare(VTDPASIDEntry *p1, VTDPASIDEntry *p2)
+{
+    return memcmp(p1, p2, sizeof(*p1));
+}
+
 /* Update or invalidate pasid cache based on the pasid entry in guest memory. */
 static void vtd_pasid_cache_sync_locked(gpointer key, gpointer value,
                                         gpointer user_data)
@@ -3094,15 +3099,28 @@ static void vtd_pasid_cache_sync_locked(gpointer key, gpointer value,
     VTDAddressSpace *vtd_as = value;
     VTDPASIDCacheEntry *pc_entry = &vtd_as->pasid_cache_entry;
     VTDPASIDEntry pe;
+    IOMMUNotifier *n;
     uint16_t did;
 
     if (vtd_dev_get_pe_from_pasid(vtd_as, &pe)) {
+        if (!pc_entry->valid) {
+            return;
+        }
         /*
          * No valid pasid entry in guest memory. e.g. pasid entry was modified
          * to be either all-zero or non-present. Either case means existing
          * pasid cache should be invalidated.
          */
         pc_entry->valid = false;
+
+        /*
+         * When a pasid entry isn't valid any more, we should unmap all
+         * mappings in shadow pages instantly to ensure DMA security.
+         */
+        IOMMU_NOTIFIER_FOREACH(n, &vtd_as->iommu) {
+            vtd_address_space_unmap(vtd_as, n);
+        }
+        vtd_switch_address_space(vtd_as);
         return;
     }
 
@@ -3128,8 +3146,15 @@ static void vtd_pasid_cache_sync_locked(gpointer key, gpointer value,
         }
     }
 
-    pc_entry->pasid_entry = pe;
-    pc_entry->valid = true;
+    if (!pc_entry->valid) {
+        pc_entry->pasid_entry = pe;
+        pc_entry->valid = true;
+    } else if (!vtd_pasid_entry_compare(&pe, &pc_entry->pasid_entry)) {
+        return;
+    }
+
+    vtd_switch_address_space(vtd_as);
+    vtd_address_space_sync(vtd_as);
 }
 
 static void vtd_pasid_cache_sync(IntelIOMMUState *s, VTDPASIDCacheInfo *pc_info)