[RFC v6 21/24] hw/arm/smmuv3: Fill the IOTLBEntry leaf field on NH_VA invalidation

[Eric Auger]

Let's propagate the leaf attribute throughout the invalidation path.
This hint is used to reduce the scope of the invalidations to the
last level of translation. Not enforcing it induces large performance
penalties in nested mode.

Signed-off-by: Eric Auger <address@hidden>
---
 hw/arm/smmuv3.c     | 16 +++++++++-------
 hw/arm/trace-events |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
index 66603c1fde..edd76bce4c 100644
--- a/hw/arm/smmuv3.c
+++ b/hw/arm/smmuv3.c
@@ -811,8 +811,7 @@ epilogue:
  */
 static void smmuv3_notify_iova(IOMMUMemoryRegion *mr,
                                IOMMUNotifier *n,
-                               int asid,
-                               dma_addr_t iova)
+                               int asid, dma_addr_t iova, bool leaf)
 {
     SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu);
     SMMUEventInfo event = {.inval_ste_allowed = true};
@@ -839,12 +838,14 @@ static void smmuv3_notify_iova(IOMMUMemoryRegion *mr,
     entry.addr_mask = (1 << tt->granule_sz) - 1;
     entry.perm = IOMMU_NONE;
     entry.arch_id = asid;
+    entry.leaf = leaf;
 
     memory_region_notify_one(n, &entry);
 }
 
 /* invalidate an asid/iova tuple in all mr's */
-static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova)
+static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid,
+                                      dma_addr_t iova, bool leaf)
 {
     SMMUDevice *sdev;
 
@@ -855,7 +856,7 @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int 
asid, dma_addr_t iova)
         trace_smmuv3_inv_notifiers_iova(mr->parent_obj.name, asid, iova);
 
         IOMMU_NOTIFIER_FOREACH(n, mr) {
-            smmuv3_notify_iova(mr, n, asid, iova);
+            smmuv3_notify_iova(mr, n, asid, iova, leaf);
         }
     }
 }
@@ -993,9 +994,10 @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
         {
             dma_addr_t addr = CMD_ADDR(&cmd);
             uint16_t vmid = CMD_VMID(&cmd);
+            bool leaf = CMD_LEAF(&cmd);
 
-            trace_smmuv3_cmdq_tlbi_nh_vaa(vmid, addr);
-            smmuv3_inv_notifiers_iova(bs, -1, addr);
+            trace_smmuv3_cmdq_tlbi_nh_vaa(vmid, addr, leaf);
+            smmuv3_inv_notifiers_iova(bs, -1, addr, leaf);
             smmu_iotlb_inv_all(bs);
             break;
         }
@@ -1007,7 +1009,7 @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
             bool leaf = CMD_LEAF(&cmd);
 
             trace_smmuv3_cmdq_tlbi_nh_va(vmid, asid, addr, leaf);
-            smmuv3_inv_notifiers_iova(bs, asid, addr);
+            smmuv3_inv_notifiers_iova(bs, asid, addr, leaf);
             smmu_iotlb_inv_iova(bs, asid, addr);
             break;
         }
diff --git a/hw/arm/trace-events b/hw/arm/trace-events
index 0acedcedc6..3809005cba 100644
--- a/hw/arm/trace-events
+++ b/hw/arm/trace-events
@@ -43,7 +43,7 @@ smmuv3_cmdq_cfgi_cd(uint32_t sid) "streamid = %d"
 smmuv3_config_cache_hit(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t 
perc) "Config cache HIT for sid %d (hits=%d, misses=%d, hit rate=%d)"
 smmuv3_config_cache_miss(uint32_t sid, uint32_t hits, uint32_t misses, 
uint32_t perc) "Config cache MISS for sid %d (hits=%d, misses=%d, hit rate=%d)"
 smmuv3_cmdq_tlbi_nh_va(int vmid, int asid, uint64_t addr, bool leaf) "vmid =%d 
asid =%d addr=0x%"PRIx64" leaf=%d"
-smmuv3_cmdq_tlbi_nh_vaa(int vmid, uint64_t addr) "vmid =%d addr=0x%"PRIx64
+smmuv3_cmdq_tlbi_nh_vaa(int vmid, uint64_t addr, bool leaf) "vmid =%d 
addr=0x%"PRIx64" leaf=%d"
 smmuv3_cmdq_tlbi_nh(void) ""
 smmuv3_cmdq_tlbi_nh_asid(uint16_t asid) "asid=%d"
 smmu_iotlb_cache_hit(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t 
miss, uint32_t p) "IOTLB cache HIT asid=%d addr=0x%"PRIx64" hit=%d miss=%d hit 
rate=%d"
-- 
2.20.1