[PATCH] hw/arm/smmuv3: Simplify range invalidation

[PATCH] hw/arm/smmuv3: Simplify range invalidation

[Liu, Renwei]

Simplify range invalidation which can avoid to iterate over all
iotlb entries multi-times. For instance invalidations patterns like
"invalidate 32 4kB pages starting from 0xffacd000" need to iterate over
all iotlb entries 6 times (num_pages: 1, 2, 16, 8, 4, 1). It only needs
to iterate over all iotlb entries once with new implementation.

Signed-off-by: Renwei Liu <renwei.liu@verisilicon.com>
---
 hw/arm/smmu-common.c   |  6 +++---
 hw/arm/smmu-internal.h |  2 +-
 hw/arm/smmuv3.c        | 22 ++++------------------
 3 files changed, 8 insertions(+), 22 deletions(-)
 mode change 100644 => 100755 hw/arm/smmu-common.c
 mode change 100644 => 100755 hw/arm/smmu-internal.h
 mode change 100644 => 100755 hw/arm/smmuv3.c

diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
old mode 100644
new mode 100755
index 0459850a93..ccb085f83c
--- a/hw/arm/smmu-common.c
+++ b/hw/arm/smmu-common.c
@@ -142,8 +142,8 @@ static gboolean smmu_hash_remove_by_asid_iova(gpointer key, gpointer value,
     if (info->asid >= 0 && info->asid != SMMU_IOTLB_ASID(iotlb_key)) {
         return false;
     }
-    return ((info->iova & ~entry->addr_mask) == entry->iova) ||
-           ((entry->iova & ~info->mask) == info->iova);
+    return (entry->iova >= info->iova) &&
+           ((entry->iova + entry->addr_mask) < (info->iova + info->range));
 }
 
 inline void
@@ -167,7 +167,7 @@ smmu_iotlb_inv_iova(SMMUState *s, int asid, dma_addr_t iova,
 
     SMMUIOTLBPageInvInfo info = {
         .asid = asid, .iova = iova,
-        .mask = (num_pages * 1 << granule) - 1};
+        .range = num_pages * 1 << granule};
 
     g_hash_table_foreach_remove(s->iotlb,
                                 smmu_hash_remove_by_asid_iova,
diff --git a/hw/arm/smmu-internal.h b/hw/arm/smmu-internal.h
old mode 100644
new mode 100755
index 2d75b31953..f0e3a777af
--- a/hw/arm/smmu-internal.h
+++ b/hw/arm/smmu-internal.h
@@ -101,7 +101,7 @@ uint64_t iova_level_offset(uint64_t iova, int inputsize,
 typedef struct SMMUIOTLBPageInvInfo {
     int asid;
     uint64_t iova;
-    uint64_t mask;
+    uint64_t range;
 } SMMUIOTLBPageInvInfo;
 
 typedef struct SMMUSIDRange {
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
old mode 100644
new mode 100755
index 01b60bee49..0b009107d1
--- a/hw/arm/smmuv3.c
+++ b/hw/arm/smmuv3.c
@@ -857,7 +857,7 @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova,
 
 static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
 {
-    dma_addr_t end, addr = CMD_ADDR(cmd);
+    dma_addr_t addr = CMD_ADDR(cmd);
     uint8_t type = CMD_TYPE(cmd);
     uint16_t vmid = CMD_VMID(cmd);
     uint8_t scale = CMD_SCALE(cmd);
@@ -866,7 +866,6 @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
     bool leaf = CMD_LEAF(cmd);
     uint8_t tg = CMD_TG(cmd);
     uint64_t num_pages;
-    uint8_t granule;
     int asid = -1;
 
     if (type == SMMU_CMD_TLBI_NH_VA) {
@@ -880,23 +879,10 @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
         return;
     }
 
-    /* RIL in use */
-
     num_pages = (num + 1) * BIT_ULL(scale);
-    granule = tg * 2 + 10;
-
-    /* Split invalidations into ^2 range invalidations */
-    end = addr + (num_pages << granule) - 1;
-
-    while (addr != end + 1) {
-        uint64_t mask = dma_aligned_pow2_mask(addr, end, 64);
-
-        num_pages = (mask + 1) >> granule;
-        trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
-        smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages);
-        smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl);
-        addr += mask + 1;
-    }
+    trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
+    smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages);
+    smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl);
 }
 
 static gboolean
-- 
2.32.0