diff --git a/exec-all.h b/exec-all.h
index 2ea0e4f..ad6d22b 100644
--- a/exec-all.h
+++ b/exec-all.h
@@ -310,6 +310,42 @@
 # define GETPC() ((uintptr_t)__builtin_return_address(0) - 1)
 #endif
 
+#if defined(CONFIG_QEMU_LDST_OPTIMIZATION) && defined(CONFIG_SOFTMMU)
+/* qemu_ld/st optimization split code generation to fast and slow path, thus,
+   it needs special handling for an MMU helper which is called from the slow
+   path, to get the fast path's pc without any additional argument.
+   It uses a tricky solution which embeds the fast path pc into the slow path.
+
+   Code flow in slow path:
+   (1) pre-process
+   (2) call MMU helper
+   (3) jump to (5)
+   (4) fast path information (implementation specific)
+   (5) post-process (e.g. stack adjust)
+   (6) jump to corresponding code of the next of fast path
+ */
+# if defined(__i386__) || defined(__x86_64__)
+/* To avoid broken disassembling, long jmp is used for embedding fast path pc,
+   so that the destination is the next code of fast path, though this jmp is
+   never executed.
+
+   call MMU helper
+   jmp POST_PROC (2byte)    <- GETRA()
+   jmp NEXT_CODE (5byte)
+   POST_PROCESS ...         <- GETRA() + 7
+ */
+#  define GETRA() ((uintptr_t)__builtin_return_address(0))
+#  define GETPC_LDST() ((uintptr_t)(GETRA() + 7 + \
+                                    *(int32_t *)((void *)GETRA() + 3) - 1))
+# else
+#  error "CONFIG_QEMU_LDST_OPTIMIZATION needs GETPC_LDST() implementation!"
+# endif
+bool is_tcg_gen_code(uintptr_t pc_ptr);
+# define GETPC_EXT() (is_tcg_gen_code(GETRA()) ? GETPC_LDST() : GETPC())
+#else
+# define GETPC_EXT() GETPC()
+#endif
+
 #if !defined(CONFIG_USER_ONLY)
 
 struct MemoryRegion *iotlb_to_region(hwaddr index);
diff --git a/exec.c b/exec.c
index df67938..8bff743 100644
--- a/exec.c
+++ b/exec.c
@@ -1390,6 +1390,17 @@
     mmap_unlock();
 }
 
+#if defined(CONFIG_QEMU_LDST_OPTIMIZATION) && defined(CONFIG_SOFTMMU)
+/* check whether the given addr is in TCG generated code buffer or not */
+bool is_tcg_gen_code(uintptr_t tc_ptr)
+{
+    /* This can be called during code generation, code_gen_buffer_max_size
+       is used instead of code_gen_ptr for upper boundary checking */
+    return (tc_ptr >= (uintptr_t)code_gen_buffer &&
+            tc_ptr < (uintptr_t)(code_gen_buffer + code_gen_buffer_max_size));
+}
+#endif
+
 /* find the TB 'tb' such that tb[0].tc_ptr <= tc_ptr <
    tb[1].tc_ptr. Return NULL if not found */
 TranslationBlock *tb_find_pc(uintptr_t tc_ptr)
diff --git a/softmmu_template.h b/softmmu_template.h
index 20d6bab..ce30d8b 100644
--- a/softmmu_template.h
+++ b/softmmu_template.h
@@ -111,13 +111,13 @@
             /* IO access */
             if ((addr & (DATA_SIZE - 1)) != 0)
                 goto do_unaligned_access;
-            retaddr = GETPC();
+            retaddr = GETPC_EXT();
             ioaddr = env->iotlb[mmu_idx][index];
             res = glue(io_read, SUFFIX)(env, ioaddr, addr, retaddr);
         } else if (((addr & ~TARGET_PAGE_MASK) + DATA_SIZE - 1) >= TARGET_PAGE_SIZE) {
             /* slow unaligned access (it spans two pages or IO) */
         do_unaligned_access:
-            retaddr = GETPC();
+            retaddr = GETPC_EXT();
 #ifdef ALIGNED_ONLY
             do_unaligned_access(env, addr, READ_ACCESS_TYPE, mmu_idx, retaddr);
 #endif
@@ -128,7 +128,7 @@
             uintptr_t addend;
 #ifdef ALIGNED_ONLY
             if ((addr & (DATA_SIZE - 1)) != 0) {
-                retaddr = GETPC();
+                retaddr = GETPC_EXT();
                 do_unaligned_access(env, addr, READ_ACCESS_TYPE, mmu_idx, retaddr);
             }
 #endif
@@ -138,7 +138,7 @@
         }
     } else {
         /* the page is not in the TLB : fill it */
-        retaddr = GETPC();
+        retaddr = GETPC_EXT();
 #ifdef ALIGNED_ONLY
         if ((addr & (DATA_SIZE - 1)) != 0)
             do_unaligned_access(env, addr, READ_ACCESS_TYPE, mmu_idx, retaddr);
@@ -257,12 +257,12 @@
             /* IO access */
             if ((addr & (DATA_SIZE - 1)) != 0)
                 goto do_unaligned_access;
-            retaddr = GETPC();
+            retaddr = GETPC_EXT();
             ioaddr = env->iotlb[mmu_idx][index];
             glue(io_write, SUFFIX)(env, ioaddr, val, addr, retaddr);
         } else if (((addr & ~TARGET_PAGE_MASK) + DATA_SIZE - 1) >= TARGET_PAGE_SIZE) {
         do_unaligned_access:
-            retaddr = GETPC();
+            retaddr = GETPC_EXT();
 #ifdef ALIGNED_ONLY
             do_unaligned_access(env, addr, 1, mmu_idx, retaddr);
 #endif
@@ -273,7 +273,7 @@
             uintptr_t addend;
 #ifdef ALIGNED_ONLY
             if ((addr & (DATA_SIZE - 1)) != 0) {
-                retaddr = GETPC();
+                retaddr = GETPC_EXT();
                 do_unaligned_access(env, addr, 1, mmu_idx, retaddr);
             }
 #endif
@@ -283,7 +283,7 @@
         }
     } else {
         /* the page is not in the TLB : fill it */
-        retaddr = GETPC();
+        retaddr = GETPC_EXT();
 #ifdef ALIGNED_ONLY
         if ((addr & (DATA_SIZE - 1)) != 0)
             do_unaligned_access(env, addr, 1, mmu_idx, retaddr);