diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index f580e4dd7e..88cc8389e9 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -1045,6 +1045,8 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
     if (unlikely(!tlb_hit(entry->addr_code, addr))) {
         if (!VICTIM_TLB_HIT(addr_code, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, 0, MMU_INST_FETCH, mmu_idx, 0);
+            index = tlb_index(env, mmu_idx, addr);
+            entry = tlb_entry(env, mmu_idx, addr);
         }
         assert(tlb_hit(entry->addr_code, addr));
     }
@@ -1125,6 +1127,8 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
         if (!VICTIM_TLB_HIT(addr_write, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, 1 << s_bits, MMU_DATA_STORE,
                      mmu_idx, retaddr);
+            index = tlb_index(env, mmu_idx, addr);
+            tlbe = tlb_entry(env, mmu_idx, addr);
         }
         tlb_addr = tlb_addr_write(tlbe) & ~TLB_INVALID_MASK;
     }
diff --git a/accel/tcg/softmmu_template.h b/accel/tcg/softmmu_template.h
index 1fdd262ea4..e970a8b378 100644
--- a/accel/tcg/softmmu_template.h
+++ b/accel/tcg/softmmu_template.h
@@ -129,6 +129,8 @@ WORD_TYPE helper_le_ld_name(CPUArchState *env, target_ulong addr,
         if (!VICTIM_TLB_HIT(ADDR_READ, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, READ_ACCESS_TYPE,
                      mmu_idx, retaddr);
+            index = tlb_index(env, mmu_idx, addr);
+            entry = tlb_entry(env, mmu_idx, addr);
         }
         tlb_addr = entry->ADDR_READ;
     }
@@ -198,6 +200,8 @@ WORD_TYPE helper_be_ld_name(CPUArchState *env, target_ulong addr,
         if (!VICTIM_TLB_HIT(ADDR_READ, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, READ_ACCESS_TYPE,
                      mmu_idx, retaddr);
+            index = tlb_index(env, mmu_idx, addr);
+            entry = tlb_entry(env, mmu_idx, addr);
         }
         tlb_addr = entry->ADDR_READ;
     }
@@ -294,6 +298,8 @@ void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
         if (!VICTIM_TLB_HIT(addr_write, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, MMU_DATA_STORE,
                      mmu_idx, retaddr);
+            index = tlb_index(env, mmu_idx, addr);
+            entry = tlb_entry(env, mmu_idx, addr);
         }
         tlb_addr = tlb_addr_write(entry) & ~TLB_INVALID_MASK;
     }
@@ -372,6 +378,8 @@ void helper_be_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
         if (!VICTIM_TLB_HIT(addr_write, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, MMU_DATA_STORE,
                      mmu_idx, retaddr);
+            index = tlb_index(env, mmu_idx, addr);
+            entry = tlb_entry(env, mmu_idx, addr);
         }
         tlb_addr = tlb_addr_write(entry) & ~TLB_INVALID_MASK;
     }
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index aa7b81aaf0..97b90cb0db 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -475,6 +475,11 @@ static inline void assert_no_pages_locked(void)
 struct MemoryRegionSection *iotlb_to_section(CPUState *cpu,
                                              hwaddr index, MemTxAttrs attrs);
 
+/*
+ * Note: tlb_fill() can trigger a resize of the TLB. This means that all of the
+ * caller's prior references to the TLB table (e.g. CPUTLBEntry pointers) must
+ * be discarded and looked up again (e.g. via tlb_entry()).
+ */
 void tlb_fill(CPUState *cpu, target_ulong addr, int size,
               MMUAccessType access_type, int mmu_idx, uintptr_t retaddr);
 
diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index 4d84aea3a9..e0670e5098 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -2615,7 +2615,7 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         OPC_PADDSB, OPC_PADDSW, OPC_UD2, OPC_UD2
     };
     static int const usadd_insn[4] = {
-        OPC_PADDSB, OPC_PADDSW, OPC_UD2, OPC_UD2
+        OPC_PADDUB, OPC_PADDUW, OPC_UD2, OPC_UD2
     };
     static int const sub_insn[4] = {
         OPC_PSUBB, OPC_PSUBW, OPC_PSUBD, OPC_PSUBQ
@@ -2624,7 +2624,7 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         OPC_PSUBSB, OPC_PSUBSW, OPC_UD2, OPC_UD2
     };
     static int const ussub_insn[4] = {
-        OPC_PSUBSB, OPC_PSUBSW, OPC_UD2, OPC_UD2
+        OPC_PSUBUB, OPC_PSUBUW, OPC_UD2, OPC_UD2
     };
     static int const mul_insn[4] = {
         OPC_UD2, OPC_PMULLW, OPC_PMULLD, OPC_UD2
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 2d98868d8f..d3e51b15af 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -255,6 +255,7 @@ static inline void tcg_gen_op6ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
 
 static inline void gen_set_label(TCGLabel *l)
 {
+    l->present = 1;
     tcg_gen_op1(INDEX_op_set_label, label_arg(l));
 }
 
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 20a5d8f315..9b2bf7f439 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -305,6 +305,9 @@ TCGLabel *gen_new_label(void)
     *l = (TCGLabel){
         .id = s->nb_labels++
     };
+#ifdef CONFIG_DEBUG_TCG
+    QSIMPLEQ_INSERT_TAIL(&s->labels, l, next);
+#endif
 
     return l;
 }
@@ -1092,6 +1095,9 @@ void tcg_func_start(TCGContext *s)
 
     QTAILQ_INIT(&s->ops);
     QTAILQ_INIT(&s->free_ops);
+#ifdef CONFIG_DEBUG_TCG
+    QSIMPLEQ_INIT(&s->labels);
+#endif
 }
 
 static inline TCGTemp *tcg_temp_alloc(TCGContext *s)
@@ -3841,6 +3847,23 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb)
     }
 #endif
 
+#ifdef CONFIG_DEBUG_TCG
+    /* Ensure all labels referenced have been emitted.  */
+    {
+        TCGLabel *l;
+        bool error = false;
+
+        QSIMPLEQ_FOREACH(l, &s->labels, next) {
+            if (unlikely(!l->present) && l->refs) {
+                qemu_log_mask(CPU_LOG_TB_OP,
+                              "$L%d referenced but not present.\n", l->id);
+                error = true;
+            }
+        }
+        assert(!error);
+    }
+#endif
+
 #ifdef CONFIG_PROFILER
     atomic_set(&prof->opt_time, prof->opt_time - profile_getclock());
 #endif
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 045c24a357..32b7cf3489 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -244,16 +244,21 @@ typedef struct TCGRelocation {
     intptr_t addend;
 } TCGRelocation; 
 
-typedef struct TCGLabel {
+typedef struct TCGLabel TCGLabel;
+struct TCGLabel {
+    unsigned present : 1;
     unsigned has_value : 1;
-    unsigned id : 15;
+    unsigned id : 14;
     unsigned refs : 16;
     union {
         uintptr_t value;
         tcg_insn_unit *value_ptr;
         TCGRelocation *first_reloc;
     } u;
-} TCGLabel;
+#ifdef CONFIG_DEBUG_TCG
+    QSIMPLEQ_ENTRY(TCGLabel) next;
+#endif
+};
 
 typedef struct TCGPool {
     struct TCGPool *next;
@@ -685,6 +690,7 @@ struct TCGContext {
 #endif
 
 #ifdef CONFIG_DEBUG_TCG
+    QSIMPLEQ_HEAD(, TCGLabel) labels;
     int temps_in_use;
     int goto_tb_issue_mask;
 #endif