diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h
index 009e2778c5..01d2ac7118 100644
--- a/include/tcg/tcg-op-common.h
+++ b/include/tcg/tcg-op-common.h
@@ -150,6 +150,7 @@ void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_ussub_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_abs_i32(TCGv_i32, TCGv_i32);
 
 /* Replicate a value of size @vece from @in to all the lanes in @out */
@@ -258,6 +259,7 @@ void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_ussub_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_abs_i64(TCGv_i64, TCGv_i64);
 
 /* Replicate a value of size @vece from @in to all the lanes in @out */
diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h
index a02850583b..389b8545d6 100644
--- a/include/tcg/tcg-op.h
+++ b/include/tcg/tcg-op.h
@@ -259,6 +259,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64)
 #define tcg_gen_umin_tl tcg_gen_umin_i64
 #define tcg_gen_smax_tl tcg_gen_smax_i64
 #define tcg_gen_umax_tl tcg_gen_umax_i64
+#define tcg_gen_ussub_tl tcg_gen_ussub_i64
 #define tcg_gen_atomic_cmpxchg_tl tcg_gen_atomic_cmpxchg_i64
 #define tcg_gen_atomic_xchg_tl tcg_gen_atomic_xchg_i64
 #define tcg_gen_atomic_fetch_add_tl tcg_gen_atomic_fetch_add_i64
@@ -377,6 +378,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64)
 #define tcg_gen_umin_tl tcg_gen_umin_i32
 #define tcg_gen_smax_tl tcg_gen_smax_i32
 #define tcg_gen_umax_tl tcg_gen_umax_i32
+#define tcg_gen_ussub_tl tcg_gen_ussub_i32
 #define tcg_gen_atomic_cmpxchg_tl tcg_gen_atomic_cmpxchg_i32
 #define tcg_gen_atomic_xchg_tl tcg_gen_atomic_xchg_i32
 #define tcg_gen_atomic_fetch_add_tl tcg_gen_atomic_fetch_add_i32
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index d32a4f146d..bd750509ad 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -2304,20 +2304,6 @@ void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs,
     tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
 }
 
-static void tcg_gen_ussub_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
-{
-    TCGv_i32 min = tcg_constant_i32(0);
-    tcg_gen_sub_i32(d, a, b);
-    tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, min, d);
-}
-
-static void tcg_gen_ussub_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
-{
-    TCGv_i64 min = tcg_constant_i64(0);
-    tcg_gen_sub_i64(d, a, b);
-    tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, min, d);
-}
-
 void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs,
                         uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
 {
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index fec6d678a2..29aa59429f 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -1421,6 +1421,16 @@ void tcg_gen_umax_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b)
     tcg_gen_movcond_i32(TCG_COND_LTU, ret, a, b, b, a);
 }
 
+void tcg_gen_ussub_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t = tcg_temp_ebb_new_i32();
+    TCGv_i32 z = tcg_constant_i32(0);
+
+    tcg_gen_sub_i32(t, a, b);
+    tcg_gen_movcond_i32(TCG_COND_LTU, ret, a, b, z, t);
+    tcg_temp_free_i32(t);
+}
+
 void tcg_gen_abs_i32(TCGv_i32 ret, TCGv_i32 a)
 {
     TCGv_i32 t = tcg_temp_ebb_new_i32();
@@ -3148,6 +3158,16 @@ void tcg_gen_umax_i64(TCGv_i64 ret, TCGv_i64 a, TCGv_i64 b)
     tcg_gen_movcond_i64(TCG_COND_LTU, ret, a, b, b, a);
 }
 
+void tcg_gen_ussub_i64(TCGv_i64 ret, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t = tcg_temp_ebb_new_i64();
+    TCGv_i64 z = tcg_constant_i64(0);
+
+    tcg_gen_sub_i64(t, a, b);
+    tcg_gen_movcond_i64(TCG_COND_LTU, ret, a, b, z, t);
+    tcg_temp_free_i64(t);
+}
+
 void tcg_gen_abs_i64(TCGv_i64 ret, TCGv_i64 a)
 {
     TCGv_i64 t = tcg_temp_ebb_new_i64();