diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index b12fbfda63..d56c1e51e4 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -29,6 +29,7 @@
 #error "unsupported code generation mode"
 #endif
 
+#include "../tcg-ldst.c.inc"
 #include "../tcg-pool.c.inc"
 #include "elf.h"
 
@@ -136,6 +137,7 @@ typedef enum S390Opcode {
     RI_OIHL     = 0xa509,
     RI_OILH     = 0xa50a,
     RI_OILL     = 0xa50b,
+    RI_TMLL     = 0xa701,
 
     RIE_CGIJ    = 0xec7c,
     RIE_CGRJ    = 0xec64,
@@ -1804,8 +1806,6 @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg data,
 }
 
 #if defined(CONFIG_SOFTMMU)
-#include "../tcg-ldst.c.inc"
-
 /* We're expecting to use a 20-bit negative offset on the tlb memory ops.  */
 QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0);
 QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 19));
@@ -1942,6 +1942,53 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
     return true;
 }
 #else
+static void tcg_out_test_alignment(TCGContext *s, bool is_ld,
+                                   TCGReg addrlo, unsigned a_bits)
+{
+    unsigned a_mask = (1 << a_bits) - 1;
+    TCGLabelQemuLdst *l = new_ldst_label(s);
+
+    l->is_ld = is_ld;
+    l->addrlo_reg = addrlo;
+
+    /* We are expecting a_bits to max out at 7, much lower than TMLL. */
+    tcg_debug_assert(a_bits < 16);
+    tcg_out_insn(s, RI, TMLL, addrlo, a_mask);
+
+    tcg_out16(s, RI_BRC | (7 << 4)); /* CC in {1,2,3} */
+    l->label_ptr[0] = s->code_ptr;
+    s->code_ptr += 1;
+
+    l->raddr = tcg_splitwx_to_rx(s->code_ptr);
+}
+
+static bool tcg_out_fail_alignment(TCGContext *s, TCGLabelQemuLdst *l)
+{
+    if (!patch_reloc(l->label_ptr[0], R_390_PC16DBL,
+                     (intptr_t)tcg_splitwx_to_rx(s->code_ptr), 2)) {
+        return false;
+    }
+
+    tcg_out_mov(s, TCG_TYPE_TL, TCG_REG_R3, l->addrlo_reg);
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_R2, TCG_AREG0);
+
+    /* "Tail call" to the helper, with the return address back inline. */
+    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R14, (uintptr_t)l->raddr);
+    tgen_gotoi(s, S390_CC_ALWAYS, (const void *)(l->is_ld ? helper_unaligned_ld
+                                                 : helper_unaligned_st));
+    return true;
+}
+
+static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
+{
+    return tcg_out_fail_alignment(s, l);
+}
+
+static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
+{
+    return tcg_out_fail_alignment(s, l);
+}
+
 static void tcg_prepare_user_ldst(TCGContext *s, TCGReg *addr_reg,
                                   TCGReg *index_reg, tcg_target_long *disp)
 {
@@ -1980,7 +2027,11 @@ static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg,
 #else
     TCGReg index_reg;
     tcg_target_long disp;
+    unsigned a_bits = get_alignment_bits(opc);
 
+    if (a_bits) {
+        tcg_out_test_alignment(s, true, addr_reg, a_bits);
+    }
     tcg_prepare_user_ldst(s, &addr_reg, &index_reg, &disp);
     tcg_out_qemu_ld_direct(s, opc, data_reg, addr_reg, index_reg, disp);
 #endif
@@ -2007,7 +2058,11 @@ static void tcg_out_qemu_st(TCGContext* s, TCGReg data_reg, TCGReg addr_reg,
 #else
     TCGReg index_reg;
     tcg_target_long disp;
+    unsigned a_bits = get_alignment_bits(opc);
 
+    if (a_bits) {
+        tcg_out_test_alignment(s, false, addr_reg, a_bits);
+    }
     tcg_prepare_user_ldst(s, &addr_reg, &index_reg, &disp);
     tcg_out_qemu_st_direct(s, opc, data_reg, addr_reg, index_reg, disp);
 #endif
diff --git a/tcg/s390x/tcg-target.h b/tcg/s390x/tcg-target.h
index 527ada0f63..69217d995b 100644
--- a/tcg/s390x/tcg-target.h
+++ b/tcg/s390x/tcg-target.h
@@ -178,9 +178,7 @@ static inline void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_rx,
     /* no need to flush icache explicitly */
 }
 
-#ifdef CONFIG_SOFTMMU
 #define TCG_TARGET_NEED_LDST_LABELS
-#endif
 #define TCG_TARGET_NEED_POOL_LABELS
 
 #endif