diff --git a/examples/device/cdc_msc_hid/ses/lpc43xx/lpc43xx.emProject b/examples/device/cdc_msc_hid/ses/lpc43xx/lpc43xx.emProject
index 3b91cf865..363fae3e2 100644
--- a/examples/device/cdc_msc_hid/ses/lpc43xx/lpc43xx.emProject
+++ b/examples/device/cdc_msc_hid/ses/lpc43xx/lpc43xx.emProject
@@ -19,7 +19,7 @@
       arm_target_device_name="LPC4357_M4"
       arm_target_interface_type="SWD"
       build_treat_warnings_as_errors="Yes"
-      c_preprocessor_definitions="CORE_M4;__LPC4300_FAMILY;__LPC435x_SUBFAMILY;ARM_MATH_CM4;FLASH_PLACEMENT=1;BOARD_EA4357;CFG_TUSB_MCU=OPT_MCU_LPC43XX"
+      c_preprocessor_definitions="CORE_M4;__LPC4300_FAMILY;__LPC435x_SUBFAMILY;ARM_MATH_CM4;FLASH_PLACEMENT=1;BOARD_EA4357;CFG_TUSB_MCU=OPT_MCU_LPC43XX;CFG_TUSB_MEM_SECTION= __attribute__((section(".bss2")))"
       c_user_include_directories="../../src;$(rootDir)/hw/cmsis/Include;$(rootDir)/hw;$(rootDir)/src;$(lpcDir)/CMSIS_LPC43xx_DriverLib/inc"
       debug_register_definition_file="LPC43xx_Registers.xml"
       debug_target_connection="J-Link"
diff --git a/examples/device/cdc_msc_hid/src/tusb_config.h b/examples/device/cdc_msc_hid/src/tusb_config.h
index 3af109188..9bc97ecff 100644
--- a/examples/device/cdc_msc_hid/src/tusb_config.h
+++ b/examples/device/cdc_msc_hid/src/tusb_config.h
@@ -58,16 +58,24 @@
 #define CFG_TUSB_DEBUG              2
 #define CFG_TUSB_OS                 OPT_OS_NONE
 
-//--------------------------------------------------------------------
-// USB RAM PLACEMENT
-//--------------------------------------------------------------------
-#define CFG_TUSB_ATTR_USBRAM
+/* USB DMA on some MCUs can only access a specific SRAM region with restriction on alignment.
+ * Tinyusb use follows macros to declare transferring memory so that they can be put
+ * into those specific section.
+ * e.g
+ * - CFG_TUSB_MEM SECTION : __attribute__ (( section(".usb_ram") ))
+ * - CFG_TUSB_MEM_ALIGN   : __attribute__ ((aligned(4)))
+ */
+#ifndef CFG_TUSB_MEM_SECTION
+#define CFG_TUSB_MEM_SECTION
+#endif
+
+#ifndef CFG_TUSB_MEM_ALIGN
 #define CFG_TUSB_MEM_ALIGN          ATTR_ALIGNED(4)
+#endif
 
 //--------------------------------------------------------------------
 // DEVICE CONFIGURATION
 //--------------------------------------------------------------------
-
 #define CFG_TUD_ENDOINT0_SIZE       64
 
 /*------------- Descriptors -------------*/
diff --git a/src/common/compiler/tusb_compiler_gcc.h b/src/common/compiler/tusb_compiler_gcc.h
index c9f716d48..e40ad9c41 100644
--- a/src/common/compiler/tusb_compiler_gcc.h
+++ b/src/common/compiler/tusb_compiler_gcc.h
@@ -66,10 +66,8 @@
 
 /// The packed attribute specifies that a variable or structure field should have the smallest possible alignment—one byte for a variable, and one bit for a field, unless you specify a larger value with the aligned attribute
 #define ATTR_PACKED                __attribute__ ((packed))
-
 #define ATTR_PREPACKED
 
-#define ATTR_PACKED_STRUCT(x)     x __attribute__ ((packed))
 /** @} */
 
 /** \defgroup Group_FuncAttr Function Attributes
diff --git a/src/common/compiler/tusb_compiler_iar.h b/src/common/compiler/tusb_compiler_iar.h
index 1703ea45f..1f8936859 100644
--- a/src/common/compiler/tusb_compiler_iar.h
+++ b/src/common/compiler/tusb_compiler_iar.h
@@ -53,8 +53,6 @@
 #endif
 
 #define ALIGN_OF(x)     __ALIGNOF__(x)
-
-#define ATTR_PACKED_STRUCT(x)     __packed x
 #define ATTR_PREPACKED  __packed
 #define ATTR_PACKED
 //#define ATTR_SECTION(section)      _Pragma((#section))
diff --git a/src/portable/nxp/lpc43xx_lpc18xx/dcd_lpc43xx.c b/src/portable/nxp/lpc43xx_lpc18xx/dcd_lpc43xx.c
index 64a2c257a..07f6eef82 100644
--- a/src/portable/nxp/lpc43xx_lpc18xx/dcd_lpc43xx.c
+++ b/src/portable/nxp/lpc43xx_lpc18xx/dcd_lpc43xx.c
@@ -237,40 +237,7 @@ static inline uint8_t qtd_find_free(uint8_t rhport)
 }
 
 //--------------------------------------------------------------------+
-// CONTROL PIPE API
-//--------------------------------------------------------------------+
-
-// control transfer does not need to use qtd find function
-// follows UM 24.10.8.1.1 Setup packet handling using setup lockout mechanism
-bool dcd_control_xfer(uint8_t rhport, uint8_t dir, uint8_t * p_buffer, uint16_t length)
-{
-  LPC_USB0_Type* const lpc_usb = LPC_USB[rhport];
-  dcd_data_t* const p_dcd      = dcd_data_ptr[rhport];
-
-  uint8_t const ep_phy = (dir == TUSB_DIR_IN) ? 1 : 0;
-
-  dcd_qhd_t* qhd = &p_dcd->qhd[ep_phy];
-
-  // wait until ENDPTSETUPSTAT before priming data/status in response TODO add time out
-  while(lpc_usb->ENDPTSETUPSTAT & BIT_(0)) {}
-
-  TU_VERIFY( !qhd->qtd_overlay.active );
-
-  dcd_qtd_t* qtd = &p_dcd->qtd[0];
-  qtd_init(qtd, p_buffer, length);
-
-  // skip xfer complete for Status
-  qtd->int_on_complete = (length > 0 ? 1 : 0);
-
-  qhd->qtd_overlay.next = (uint32_t) qtd;
-
-  lpc_usb->ENDPTPRIME = BIT_(edpt_phy2pos(ep_phy));
-
-  return true;
-}
-
-//--------------------------------------------------------------------+
-// BULK/INTERRUPT/ISOCHRONOUS PIPE API
+// DCD Endpoint Port
 //--------------------------------------------------------------------+
 static inline volatile uint32_t * get_reg_control_addr(uint8_t rhport, uint8_t physical_endpoint)
 {
@@ -345,6 +312,36 @@ bool dcd_edpt_busy(uint8_t rhport, uint8_t ep_addr)
 //  return !p_qhd->qtd_overlay.halted && p_qhd->qtd_overlay.active;
 }
 
+// control transfer does not need to use qtd find function
+// follows UM 24.10.8.1.1 Setup packet handling using setup lockout mechanism
+bool dcd_control_xfer(uint8_t rhport, uint8_t dir, uint8_t * p_buffer, uint16_t length)
+{
+  LPC_USB0_Type* const lpc_usb = LPC_USB[rhport];
+  dcd_data_t* const p_dcd      = dcd_data_ptr[rhport];
+
+  uint8_t const ep_phy = (dir == TUSB_DIR_IN) ? 1 : 0;
+
+  dcd_qhd_t* qhd = &p_dcd->qhd[ep_phy];
+
+  // wait until ENDPTSETUPSTAT before priming data/status in response TODO add time out
+  while(lpc_usb->ENDPTSETUPSTAT & BIT_(0)) {}
+
+  TU_VERIFY( !qhd->qtd_overlay.active );
+
+  dcd_qtd_t* qtd = &p_dcd->qtd[0];
+  qtd_init(qtd, p_buffer, length);
+
+  // skip xfer complete for Status
+  qtd->int_on_complete = (length > 0 ? 1 : 0);
+
+  qhd->qtd_overlay.next = (uint32_t) qtd;
+
+  lpc_usb->ENDPTPRIME = BIT_(edpt_phy2pos(ep_phy));
+
+  return true;
+}
+
+
 // add only, controller virtually cannot know
 // TODO remove and merge to dcd_edpt_xfer
 static bool pipe_add_xfer(uint8_t rhport, uint8_t ed_idx, void * buffer, uint16_t total_bytes, bool int_on_complete)
@@ -377,6 +374,11 @@ static bool pipe_add_xfer(uint8_t rhport, uint8_t ed_idx, void * buffer, uint16_
 
 bool  dcd_edpt_xfer(uint8_t rhport, uint8_t ep_addr, uint8_t * buffer, uint16_t total_bytes)
 {
+  if ( edpt_number(ep_addr) == 0 )
+  {
+    return dcd_control_xfer(rhport, edpt_dir(ep_addr), buffer, total_bytes);
+  }
+
   uint8_t ep_idx = edpt_addr2phy(ep_addr);
 
   TU_VERIFY ( pipe_add_xfer(rhport, ep_idx, buffer, total_bytes, true) );
@@ -391,6 +393,7 @@ bool  dcd_edpt_xfer(uint8_t rhport, uint8_t ep_addr, uint8_t * buffer, uint16_t
 	return true;
 }
 
+
 //--------------------------------------------------------------------+
 // ISR
 //--------------------------------------------------------------------+