Merge remote-tracking branch 'upstream/master'

23 files changed, 685 insertions, 354 deletions

diff --git a/bsp/stm32f107/drivers/stm32_eth.c b/bsp/stm32f107/drivers/stm32_eth.c
index 886ed5765a..bd7317090f 100644
--- a/bsp/stm32f107/drivers/stm32_eth.c
+++ b/bsp/stm32f107/drivers/stm32_eth.c
@@ -3027,6 +3027,9 @@ struct rt_stm32_eth
 
     /* interface address info. */
     rt_uint8_t  dev_addr[MAX_ADDR_LEN];			/* hw address	*/
+
+	uint32_t ETH_HashTableHigh;
+	uint32_t ETH_HashTableLow;
 };
 static struct rt_stm32_eth stm32_eth_device;
 static struct rt_semaphore tx_buf_free;
@@ -3082,10 +3085,118 @@ void ETH_IRQHandler(void)
 
 /* RT-Thread Device Interface */
 
+#if (LWIP_IPV4 && LWIP_IGMP) || (LWIP_IPV6 && LWIP_IPV6_MLD)
+/* polynomial: 0x04C11DB7 */
+static uint32_t ethcrc(const uint8_t *data, size_t length)
+{
+	uint32_t crc = 0xffffffff;
+	size_t i;
+	int j;
+
+	for (i = 0; i < length; i++)
+	{
+		for (j = 0; j < 8; j++)
+		{
+			if (((crc >> 31) ^ (data[i] >> j)) & 0x01)
+			{
+				/* x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x+1 */
+				crc = (crc << 1) ^ 0x04C11DB7;
+			}
+			else
+			{
+				crc = crc << 1;
+			}
+		}
+	}
+
+	return ~crc;
+}
+
+#define HASH_BITS	6		/* #bits in hash */
+static void register_multicast_address(struct rt_stm32_eth *stm32_eth, const uint8_t *mac)
+{
+	uint32_t crc;
+	uint8_t hash;
+
+	/* calculate crc32 value of mac address */
+	crc = ethcrc(mac, 6);
+
+	/* only upper 6 bits (HASH_BITS) are used
+	* which point to specific bit in he hash registers
+	*/
+	hash = (crc >> 26) & 0x3F;
+	//rt_kprintf("register_multicast_address crc: %08X hash: %02X\n", crc, hash);
+
+	if (hash > 31)
+	{
+		stm32_eth->ETH_HashTableHigh |= 1 << (hash - 32);
+		ETH->MACHTHR = stm32_eth->ETH_HashTableHigh;
+	}
+	else
+	{
+		stm32_eth->ETH_HashTableLow |= 1 << hash;
+		ETH->MACHTLR = stm32_eth->ETH_HashTableLow;
+	}
+}
+#endif /* (LWIP_IPV4 && LWIP_IGMP) || (LWIP_IPV6 && LWIP_IPV6_MLD) */
+
+#if LWIP_IPV4 && LWIP_IGMP
+static err_t igmp_mac_filter( struct netif *netif, const ip4_addr_t *ip4_addr, u8_t action )
+{
+    uint8_t mac[6];
+	const uint8_t *p = (const uint8_t *)ip4_addr;
+    struct rt_stm32_eth *stm32_eth = (struct rt_stm32_eth *)netif->state;
+
+	mac[0] = 0x01;
+	mac[1] = 0x00;
+	mac[2] = 0x5E;
+	mac[3] = *(p+1) & 0x7F;
+	mac[4] = *(p+2);
+	mac[5] = *(p+3);
+
+	register_multicast_address(stm32_eth, mac);
+
+	if(1)
+	{
+		rt_kprintf("%s %s %s ", __FUNCTION__, (action==NETIF_ADD_MAC_FILTER)?"add":"del", ip4addr_ntoa(ip4_addr));
+		rt_kprintf("%02X:%02X:%02X:%02X:%02X:%02X\n", mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+	}
+
+	return 0;
+}
+#endif /* LWIP_IPV4 && LWIP_IGMP */
+
+#if LWIP_IPV6 && LWIP_IPV6_MLD
+static err_t mld_mac_filter( struct netif *netif, const ip6_addr_t *ip6_addr, u8_t action )
+{
+    uint8_t mac[6];
+	const uint8_t *p = (const uint8_t *)&ip6_addr->addr[3];
+    struct rt_stm32_eth *stm32_eth = (struct rt_stm32_eth *)netif->state;
+
+	mac[0] = 0x33;
+	mac[1] = 0x33;
+	mac[2] = *(p+0);
+	mac[3] = *(p+1);
+	mac[4] = *(p+2);
+	mac[5] = *(p+3);
+
+	register_multicast_address(stm32_eth, mac);
+
+	if(1)
+	{
+		rt_kprintf("%s %s %s ", __FUNCTION__, (action==NETIF_ADD_MAC_FILTER)?"add":"del", ip6addr_ntoa(ip6_addr));
+		rt_kprintf("%02X:%02X:%02X:%02X:%02X:%02X\n", mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+	}
+
+	return 0;
+}
+#endif /* LWIP_IPV6 && LWIP_IPV6_MLD */
+
 /* initialize the interface */
 static rt_err_t rt_stm32_eth_init(rt_device_t dev)
 {
     vu32 Value = 0;
+    struct rt_stm32_eth * stm32_eth = (struct rt_stm32_eth *)dev;
 
     /* Reset ETHERNET on AHB Bus */
     ETH_DeInit();
@@ -3112,7 +3223,9 @@ static rt_err_t rt_stm32_eth_init(rt_device_t dev)
     ETH_InitStructure.ETH_ReceiveAll = ETH_ReceiveAll_Enable;
     ETH_InitStructure.ETH_BroadcastFramesReception = ETH_BroadcastFramesReception_Disable;
     ETH_InitStructure.ETH_PromiscuousMode = ETH_PromiscuousMode_Disable;
-    ETH_InitStructure.ETH_MulticastFramesFilter = ETH_MulticastFramesFilter_Perfect;
+    ETH_InitStructure.ETH_MulticastFramesFilter = ETH_MulticastFramesFilter_HashTable;
+    ETH_InitStructure.ETH_HashTableHigh = stm32_eth->ETH_HashTableHigh;
+    ETH_InitStructure.ETH_HashTableLow  = stm32_eth->ETH_HashTableLow;
     ETH_InitStructure.ETH_UnicastFramesFilter = ETH_UnicastFramesFilter_Perfect;
 #if CHECKSUM_BY_HARDWARE
     ETH_InitStructure.ETH_ChecksumOffload = ETH_ChecksumOffload_Enable;
@@ -3153,6 +3266,14 @@ static rt_err_t rt_stm32_eth_init(rt_device_t dev)
     /* Enable MAC and DMA transmission and reception */
     ETH_Start();
 
+#if LWIP_IPV4 && LWIP_IGMP
+    netif_set_igmp_mac_filter(stm32_eth->parent.netif, igmp_mac_filter);
+#endif /* LWIP_IPV4 && LWIP_IGMP */
+
+#if LWIP_IPV6 && LWIP_IPV6_MLD
+    netif_set_mld_mac_filter(stm32_eth->parent.netif, mld_mac_filter);
+#endif /* LWIP_IPV6 && LWIP_IPV6_MLD */
+
     return RT_EOK;
 }
 
diff --git a/bsp/stm32f40x/drivers/stm32f4xx_eth.c b/bsp/stm32f40x/drivers/stm32f4xx_eth.c
index dea2f48339..bf4c70bc49 100644
--- a/bsp/stm32f40x/drivers/stm32f4xx_eth.c
+++ b/bsp/stm32f40x/drivers/stm32f4xx_eth.c
@@ -3274,6 +3274,9 @@ struct rt_stm32_eth
 
 	uint32_t    ETH_Speed; /*!< @ref ETH_Speed */
 	uint32_t    ETH_Mode;  /*!< @ref ETH_Duplex_Mode */
+
+	uint32_t ETH_HashTableHigh;
+	uint32_t ETH_HashTableLow;
 };
 static struct rt_stm32_eth stm32_eth_device;
 static struct rt_semaphore tx_wait;
@@ -3408,6 +3411,113 @@ void ETH_IRQHandler(void)
 #include <lwip/icmp.h>
 #include "lwipopts.h"
 
+#if (LWIP_IPV4 && LWIP_IGMP) || (LWIP_IPV6 && LWIP_IPV6_MLD)
+/* polynomial: 0x04C11DB7 */
+static uint32_t ethcrc(const uint8_t *data, size_t length)
+{
+	uint32_t crc = 0xffffffff;
+	size_t i;
+	int j;
+
+	for (i = 0; i < length; i++)
+	{
+		for (j = 0; j < 8; j++)
+		{
+			if (((crc >> 31) ^ (data[i] >> j)) & 0x01)
+			{
+				/* x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x+1 */
+				crc = (crc << 1) ^ 0x04C11DB7;
+			}
+			else
+			{
+				crc = crc << 1;
+			}
+		}
+	}
+
+	return ~crc;
+}
+
+#define HASH_BITS	6		/* #bits in hash */
+static void register_multicast_address(struct rt_stm32_eth *stm32_eth, const uint8_t *mac)
+{
+	uint32_t crc;
+	uint8_t hash;
+
+	/* calculate crc32 value of mac address */
+	crc = ethcrc(mac, 6);
+
+	/* only upper 6 bits (HASH_BITS) are used
+	* which point to specific bit in he hash registers
+	*/
+	hash = (crc >> 26) & 0x3F;
+	//rt_kprintf("register_multicast_address crc: %08X hash: %02X\n", crc, hash);
+
+	if (hash > 31)
+	{
+		stm32_eth->ETH_HashTableHigh |= 1 << (hash - 32);
+		ETH->MACHTHR = stm32_eth->ETH_HashTableHigh;
+	}
+	else
+	{
+		stm32_eth->ETH_HashTableLow |= 1 << hash;
+		ETH->MACHTLR = stm32_eth->ETH_HashTableLow;
+	}
+}
+#endif /* (LWIP_IPV4 && LWIP_IGMP) || (LWIP_IPV6 && LWIP_IPV6_MLD) */
+
+#if LWIP_IPV4 && LWIP_IGMP
+static err_t igmp_mac_filter( struct netif *netif, const ip4_addr_t *ip4_addr, u8_t action )
+{
+    uint8_t mac[6];
+	const uint8_t *p = (const uint8_t *)ip4_addr;
+    struct rt_stm32_eth *stm32_eth = (struct rt_stm32_eth *)netif->state;
+
+	mac[0] = 0x01;
+	mac[1] = 0x00;
+	mac[2] = 0x5E;
+	mac[3] = *(p+1) & 0x7F;
+	mac[4] = *(p+2);
+	mac[5] = *(p+3);
+
+	register_multicast_address(stm32_eth, mac);
+
+	if(1)
+	{
+		rt_kprintf("%s %s %s ", __FUNCTION__, (action==NETIF_ADD_MAC_FILTER)?"add":"del", ip4addr_ntoa(ip4_addr));
+		rt_kprintf("%02X:%02X:%02X:%02X:%02X:%02X\n", mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+	}
+
+	return 0;
+}
+#endif /* LWIP_IPV4 && LWIP_IGMP */
+
+#if LWIP_IPV6 && LWIP_IPV6_MLD
+static err_t mld_mac_filter( struct netif *netif, const ip6_addr_t *ip6_addr, u8_t action )
+{
+    uint8_t mac[6];
+	const uint8_t *p = (const uint8_t *)&ip6_addr->addr[3];
+    struct rt_stm32_eth *stm32_eth = (struct rt_stm32_eth *)netif->state;
+
+	mac[0] = 0x33;
+	mac[1] = 0x33;
+	mac[2] = *(p+0);
+	mac[3] = *(p+1);
+	mac[4] = *(p+2);
+	mac[5] = *(p+3);
+
+	register_multicast_address(stm32_eth, mac);
+
+	if(1)
+	{
+		rt_kprintf("%s %s %s ", __FUNCTION__, (action==NETIF_ADD_MAC_FILTER)?"add":"del", ip6addr_ntoa(ip6_addr));
+		rt_kprintf("%02X:%02X:%02X:%02X:%02X:%02X\n", mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+	}
+
+	return 0;
+}
+#endif /* LWIP_IPV6 && LWIP_IPV6_MLD */
+
 /* initialize the interface */
 static rt_err_t rt_stm32_eth_init(rt_device_t dev)
 {
@@ -3445,7 +3555,9 @@ static rt_err_t rt_stm32_eth_init(rt_device_t dev)
     ETH_InitStructure.ETH_ReceiveAll = ETH_ReceiveAll_Disable;
     ETH_InitStructure.ETH_BroadcastFramesReception = ETH_BroadcastFramesReception_Enable;
     ETH_InitStructure.ETH_PromiscuousMode = ETH_PromiscuousMode_Disable;
-    ETH_InitStructure.ETH_MulticastFramesFilter = ETH_MulticastFramesFilter_Perfect;
+    ETH_InitStructure.ETH_MulticastFramesFilter = ETH_MulticastFramesFilter_HashTable;
+    ETH_InitStructure.ETH_HashTableHigh = stm32_eth->ETH_HashTableHigh;
+    ETH_InitStructure.ETH_HashTableLow  = stm32_eth->ETH_HashTableLow;
     ETH_InitStructure.ETH_UnicastFramesFilter = ETH_UnicastFramesFilter_Perfect;
 #ifdef CHECKSUM_BY_HARDWARE
     ETH_InitStructure.ETH_ChecksumOffload = ETH_ChecksumOffload_Enable;
@@ -3486,6 +3598,14 @@ static rt_err_t rt_stm32_eth_init(rt_device_t dev)
     /* Enable MAC and DMA transmission and reception */
     ETH_Start();
 
+#if LWIP_IPV4 && LWIP_IGMP
+    netif_set_igmp_mac_filter(stm32_eth->parent.netif, igmp_mac_filter);
+#endif /* LWIP_IPV4 && LWIP_IGMP */
+
+#if LWIP_IPV6 && LWIP_IPV6_MLD
+    netif_set_mld_mac_filter(stm32_eth->parent.netif, mld_mac_filter);
+#endif /* LWIP_IPV6 && LWIP_IPV6_MLD */
+
     return RT_EOK;
 }
 
diff --git a/components/CMSIS/Kconfig b/components/CMSIS/Kconfig
new file mode 100644
index 0000000000..8a27f44405
--- /dev/null
+++ b/components/CMSIS/Kconfig
@@ -0,0 +1,20 @@
+if ARCH_ARM_CORTEX_M
+
+menu "ARM CMSIS"
+
+config RT_USING_CMSIS_OS
+    bool "Using CMSIS RTOS API"
+    default n
+    help
+        Enable CMSIS RTOS API, which is implemented above RT-Thread.
+
+config RT_USING_RTT_CMSIS
+    bool "Using CMSIS Header files in RT-Thread"
+    default n
+    help
+        Use CMSIS header files in RT-Thread/components/CMSIS. Otherwise, use the 
+        CMSIS header files in BSP.
+
+endmenu
+
+endif
diff --git a/components/Kconfig b/components/Kconfig
index b8c94b558a..40d9bee5e2 100644
--- a/components/Kconfig
+++ b/components/Kconfig
@@ -28,4 +28,6 @@ source "$RTT_DIR/components/vbus/Kconfig"
 
 source "$RTT_DIR/components/utilities/Kconfig"
 
+source "$RTT_DIR/components/CMSIS/Kconfig"
+
 endmenu
diff --git a/components/dfs/Kconfig b/components/dfs/Kconfig
index 91df96cb08..ec9985e21c 100644
--- a/components/dfs/Kconfig
+++ b/components/dfs/Kconfig
@@ -12,17 +12,20 @@ if RT_USING_DFS
         default y
 
     config DFS_FILESYSTEMS_MAX
-        int "The maximal number of mounted file system"
-        default 2
+        int "The maximal number of mounted file system"        
+        default 4 if RT_USING_DFS_NFS
+        default 2 
 
     config DFS_FILESYSTEM_TYPES_MAX
         int "The maximal number of file system type"
-        default 2
+        default 4 if RT_USING_DFS_NFS
+        default 2 
 
     config DFS_FD_MAX
         int "The maximal number of opened files"
+        default 16 if RT_USING_DFS_NFS
         default 4
-    
+
     config RT_USING_DFS_ELMFAT
         bool "Enable elm-chan fatfs"
         default y
@@ -51,18 +54,18 @@ if RT_USING_DFS
 
             config RT_DFS_ELM_USE_LFN_2
                 bool "2: LFN with dynamic LFN working buffer on the stack"
-            
+
             config RT_DFS_ELM_USE_LFN_3
                 bool "3: LFN with dynamic LFN working buffer on the heap"
         endchoice
-        
+
         config RT_DFS_ELM_USE_LFN
             int
             default 0 if RT_DFS_ELM_USE_LFN_0
             default 1 if RT_DFS_ELM_USE_LFN_1
             default 2 if RT_DFS_ELM_USE_LFN_2
             default 3 if RT_DFS_ELM_USE_LFN_3
-        
+
         config RT_DFS_ELM_MAX_LFN
             int "Maximal size of file name length"
             range 12 255
@@ -81,7 +84,7 @@ if RT_USING_DFS
         config RT_DFS_ELM_USE_ERASE
             bool "Enable sector erase feature"
             default n
-        
+
         config RT_DFS_ELM_REENTRANT
             bool "Enable the reentrancy (thread safe) of the FatFs module"
             default y
@@ -91,7 +94,7 @@ if RT_USING_DFS
     config RT_USING_DFS_DEVFS
         bool "Using devfs for device objects"
         default y
-    
+
     config RT_USING_DFS_NET
         bool "Enable BSD socket operated by file system API"
         select RT_USING_LWIP
@@ -140,23 +143,23 @@ if RT_USING_DFS
 
             config RT_UFFS_ECC_MODE_2
                 bool "2: Flash driver(or by hardware) calculate the ECC"
-            
+
             config RT_UFFS_ECC_MODE_3
                 bool "3: Hardware calculate the ECC and automatically write to spare."
         endchoice
-        
+
         config RT_UFFS_ECC_MODE
             int
             default 0 if RT_UFFS_ECC_MODE_0
             default 1 if RT_UFFS_ECC_MODE_1
             default 2 if RT_UFFS_ECC_MODE_2
             default 3 if RT_UFFS_ECC_MODE_3
-        
+
     endif
 
     config RT_USING_DFS_NFS
         bool "Using NFS v3 client file system"
-        depends on RT_USING_LWIP
+        select RT_USING_LWIP
         default n
 
     if RT_USING_DFS_NFS
diff --git a/components/net/Kconfig b/components/net/Kconfig
index af375e6c03..f75ed461b1 100644
--- a/components/net/Kconfig
+++ b/components/net/Kconfig
@@ -27,7 +27,7 @@ config RT_USING_LWIP
 
         config RT_LWIP_IGMP
             bool "IGMP protocol"
-            default n
+            default y
 
         config RT_LWIP_ICMP
             bool "ICMP protocol"
@@ -91,12 +91,12 @@ config RT_USING_LWIP
             config RT_LWIP_PPPOE
                 bool "PPPoE protocol"
                 default n
-    
+
             config RT_LWIP_PPPOS
                 bool "PPPoS protocol"
                 default n
         endif
-        
+
         config RT_MEMP_NUM_NETCONN
             int "the number of struct netconns"
             default 8
@@ -111,6 +111,7 @@ config RT_USING_LWIP
 
         config RT_LWIP_UDP_PCB_NUM
             int "the number of UDP socket"
+            default 8 if RT_USING_DFS_NFS
             default 4
 
         if RT_LWIP_TCP
diff --git a/components/net/lwip-2.0.2/src/netif/ethernetif.c b/components/net/lwip-2.0.2/src/netif/ethernetif.c
index bd28815c4b..ba23528c58 100644
--- a/components/net/lwip-2.0.2/src/netif/ethernetif.c
+++ b/components/net/lwip-2.0.2/src/netif/ethernetif.c
@@ -173,10 +173,26 @@ static err_t eth_netif_device_init(struct netif *netif)
         netif->flags = (ethif->flags & 0xff);
 
 #if LWIP_IPV6
-		netif->output_ip6 = ethip6_output;
-		netif->ip6_autoconfig_enabled = 1;
-		netif_create_ip6_linklocal_address(netif, 1);
-		netif->flags |= NETIF_FLAG_MLD6;
+        netif->output_ip6 = ethip6_output;
+        netif->ip6_autoconfig_enabled = 1;
+        netif_create_ip6_linklocal_address(netif, 1);
+
+#if LWIP_IPV6_MLD
+        netif->flags |= NETIF_FLAG_MLD6;
+
+        /*
+        * For hardware/netifs that implement MAC filtering.
+        * All-nodes link-local is handled by default, so we must let the hardware know
+        * to allow multicast packets in.
+        * Should set mld_mac_filter previously. */
+        if (netif->mld_mac_filter != NULL)
+        {
+            ip6_addr_t ip6_allnodes_ll;
+            ip6_addr_set_allnodes_linklocal(&ip6_allnodes_ll);
+            netif->mld_mac_filter(netif, &ip6_allnodes_ll, NETIF_ADD_MAC_FILTER);
+        }
+#endif /* LWIP_IPV6_MLD */
+
 #endif /* LWIP_IPV6 */
 
         /* set default netif */
diff --git a/libcpu/Kconfig b/libcpu/Kconfig
index 0279ca1bcf..1c63f114ca 100644
--- a/libcpu/Kconfig
+++ b/libcpu/Kconfig
@@ -33,6 +33,14 @@ config ARCH_ARM_MMU
     bool
     depends on ARCH_ARM
 
+config ARCH_ARM_ARM9
+    bool
+    select ARCH_ARM
+
+config ARCH_ARM_ARM11
+    bool
+    select ARCH_ARM
+
 config ARCH_ARM_CORTEX_A
     bool
     select ARCH_ARM
diff --git a/libcpu/arm/AT91SAM7S/stack.c b/libcpu/arm/AT91SAM7S/stack.c
index b0dc78db2c..14acc54456 100644
--- a/libcpu/arm/AT91SAM7S/stack.c
+++ b/libcpu/arm/AT91SAM7S/stack.c
@@ -30,31 +30,34 @@
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	unsigned long *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (unsigned long *)stack_addr;
-	*(stk) 	 = (unsigned long)tentry;		/* entry point */
-	*(--stk) = (unsigned long)texit;		/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (unsigned long)parameter;	/* r0 : argument */
-	*(--stk) = SVCMODE;						/* cpsr */
-	*(--stk) = SVCMODE;						/* spsr */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
+    *(--stk) = SVCMODE;                     /* cpsr */
+    *(--stk) = SVCMODE;                     /* spsr */
+
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/AT91SAM7X/stack.c b/libcpu/arm/AT91SAM7X/stack.c
index 6060b63722..d6711a5296 100644
--- a/libcpu/arm/AT91SAM7X/stack.c
+++ b/libcpu/arm/AT91SAM7X/stack.c
@@ -13,7 +13,7 @@
  */
 #include <rtthread.h>
 
-#define SVCMODE				0x13
+#define SVCMODE             0x13
 
 /**
  * @addtogroup AT91SAM7
@@ -31,31 +31,33 @@
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	unsigned long *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (unsigned long *)stack_addr;
-	*(stk) 	 = (unsigned long)tentry;		/* entry point */
-	*(--stk) = (unsigned long)texit;		/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (unsigned long)parameter;	/* r0 : argument */
-	*(--stk) = SVCMODE;						/* cpsr */
-	*(--stk) = SVCMODE;						/* spsr */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
+    *(--stk) = SVCMODE;                     /* cpsr */
+    *(--stk) = SVCMODE;                     /* spsr */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/am335x/stack.c b/libcpu/arm/am335x/stack.c
index e46f34f7cd..7415e230f5 100644
--- a/libcpu/arm/am335x/stack.c
+++ b/libcpu/arm/am335x/stack.c
@@ -24,42 +24,45 @@
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	rt_uint32_t *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (rt_uint32_t*)stack_addr;
-	*(stk) 	 = (rt_uint32_t)tentry;			/* entry point */
-	*(--stk) = (rt_uint32_t)texit;			/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (rt_uint32_t)parameter;		/* r0 : argument */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
 
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
+
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/arm926/stack.c b/libcpu/arm/arm926/stack.c
index ee29aad3ac..966088f829 100644
--- a/libcpu/arm/arm926/stack.c
+++ b/libcpu/arm/arm926/stack.c
@@ -50,10 +50,9 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
 {
     rt_uint32_t *stk;
 
-    //stk      = (rt_uint32_t*)stack_addr;
     stack_addr += sizeof(rt_uint32_t);
     stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
-    stk  = (rt_uint32_t *)stack_addr;
+    stk      = (rt_uint32_t *)stack_addr;
 
     *(--stk) = (rt_uint32_t)tentry;         /* entry point */
     *(--stk) = (rt_uint32_t)texit;          /* lr */
@@ -70,11 +69,11 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
     *(--stk) = 0xdeadbeef;                  /* r2 */
     *(--stk) = 0xdeadbeef;                  /* r1 */
     *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
 
     /* return task's current stack address */
     return (rt_uint8_t *)stk;
diff --git a/libcpu/arm/armv6/stack.c b/libcpu/arm/armv6/stack.c
index ceb04f0985..648ea7dbf5 100644
--- a/libcpu/arm/armv6/stack.c
+++ b/libcpu/arm/armv6/stack.c
@@ -26,54 +26,57 @@
 /*****************************/
 /* CPU Mode                  */
 /*****************************/
-#define USERMODE		0x10
-#define FIQMODE			0x11
-#define IRQMODE			0x12
-#define SVCMODE			0x13
-#define ABORTMODE		0x17
-#define UNDEFMODE		0x1b
-#define MODEMASK		0x1f
-#define NOINT			0xc0
+#define USERMODE        0x10
+#define FIQMODE         0x11
+#define IRQMODE         0x12
+#define SVCMODE         0x13
+#define ABORTMODE       0x17
+#define UNDEFMODE       0x1b
+#define MODEMASK        0x1f
+#define NOINT           0xc0
 
 /**
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	rt_uint32_t *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (rt_uint32_t*)stack_addr;
-	*(stk) 	 = (rt_uint32_t)tentry;			/* entry point */
-	*(--stk) = (rt_uint32_t)texit;			/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (rt_uint32_t)parameter;		/* r0 : argument */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
 
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
+
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
diff --git a/libcpu/arm/cortex-a/stack.c b/libcpu/arm/cortex-a/stack.c
index e653c5d111..e60e8c7170 100644
--- a/libcpu/arm/cortex-a/stack.c
+++ b/libcpu/arm/cortex-a/stack.c
@@ -32,35 +32,37 @@
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	rt_uint32_t *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (rt_uint32_t*)stack_addr;
-	*(stk) 	 = (rt_uint32_t)tentry;			/* entry point */
-	*(--stk) = (rt_uint32_t)texit;			/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (rt_uint32_t)parameter;		/* r0 : argument */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/cortex-r4/stack.c b/libcpu/arm/cortex-r4/stack.c
index 3c8e89444c..852c6ea384 100644
--- a/libcpu/arm/cortex-r4/stack.c
+++ b/libcpu/arm/cortex-r4/stack.c
@@ -24,39 +24,41 @@
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	unsigned long *stk;
+    rt_uint32_t *stk;
 
-	    stk  = (unsigned long*)stack_addr;
-	*(  stk) = (unsigned long) tentry;		/* entry point */
-	*(--stk) = (unsigned long) texit;		/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (unsigned long)parameter;	/* r0 : argument */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
 
 #if defined(__TI_VFP_SUPPORT__) || (defined (__VFP_FP__) && !defined(__SOFTFP__))
 #ifndef RT_VFP_LAZY_STACKING
@@ -73,13 +75,13 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
         *(--stk) = 0x40000000;
     }
 #else
-        /* FPEXC. Disable the FVP by default. */
-        *(--stk) = 0x00000000;
+    /* FPEXC. Disable the FVP by default. */
+    *(--stk) = 0x00000000;
 #endif
 #endif
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/dm36x/stack.c b/libcpu/arm/dm36x/stack.c
index b41b0b859c..fd56e7a497 100644
--- a/libcpu/arm/dm36x/stack.c
+++ b/libcpu/arm/dm36x/stack.c
@@ -26,54 +26,56 @@
 /*****************************/
 /* CPU Mode                  */
 /*****************************/
-#define USERMODE		0x10
-#define FIQMODE			0x11
-#define IRQMODE			0x12
-#define SVCMODE			0x13
-#define ABORTMODE		0x17
-#define UNDEFMODE		0x1b
-#define MODEMASK		0x1f
-#define NOINT			0xc0
+#define USERMODE        0x10
+#define FIQMODE         0x11
+#define IRQMODE         0x12
+#define SVCMODE         0x13
+#define ABORTMODE       0x17
+#define UNDEFMODE       0x1b
+#define MODEMASK        0x1f
+#define NOINT           0xc0
 
 /**
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	rt_uint32_t *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (rt_uint32_t*)stack_addr;
-	*(stk) 	 = (rt_uint32_t)tentry;			/* entry point */
-	*(--stk) = (rt_uint32_t)texit;			/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (rt_uint32_t)parameter;		/* r0 : argument */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
diff --git a/libcpu/arm/lpc24xx/stack.c b/libcpu/arm/lpc24xx/stack.c
index ad6419da4b..f160e9c167 100644
--- a/libcpu/arm/lpc24xx/stack.c
+++ b/libcpu/arm/lpc24xx/stack.c
@@ -23,42 +23,45 @@
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	unsigned long *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (unsigned long *)stack_addr;
-	*(stk) 	 = (unsigned long)tentry;		/* entry point */
-	*(--stk) = (unsigned long)texit;		/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (unsigned long)parameter;	/* r0 : argument */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
 
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
+
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/realview-a8-vmm/stack.c b/libcpu/arm/realview-a8-vmm/stack.c
index 4ae1536a20..94080ae746 100644
--- a/libcpu/arm/realview-a8-vmm/stack.c
+++ b/libcpu/arm/realview-a8-vmm/stack.c
@@ -24,42 +24,44 @@
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	rt_uint32_t *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (rt_uint32_t*)stack_addr;
-	*(stk) 	 = (rt_uint32_t)tentry;			/* entry point */
-	*(--stk) = (rt_uint32_t)texit;			/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (rt_uint32_t)parameter;		/* r0 : argument */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
-	/* cpsr */
-	if ((rt_uint32_t)tentry & 0x01)
-		*(--stk) = SVCMODE | 0x20;			/* thumb mode */
-	else
-		*(--stk) = SVCMODE;					/* arm mode   */
+    /* cpsr */
+    if ((rt_uint32_t)tentry & 0x01)
+        *(--stk) = SVCMODE | 0x20;          /* thumb mode */
+    else
+        *(--stk) = SVCMODE;                 /* arm mode   */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/s3c24x0/stack.c b/libcpu/arm/s3c24x0/stack.c
index a284989fe8..315091d907 100644
--- a/libcpu/arm/s3c24x0/stack.c
+++ b/libcpu/arm/s3c24x0/stack.c
@@ -23,38 +23,41 @@
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	rt_uint32_t *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (rt_uint32_t*)stack_addr;
-	*(stk) 	 = (rt_uint32_t)tentry;			/* entry point */
-	*(--stk) = (rt_uint32_t)texit;			/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (rt_uint32_t)parameter;		/* r0 : argument */
-	*(--stk) = SVCMODE;						/* cpsr */
-	*(--stk) = SVCMODE;						/* spsr */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
+    *(--stk) = SVCMODE;                     /* cpsr */
+    *(--stk) = SVCMODE;                     /* spsr */
+
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/s3c44b0/stack.c b/libcpu/arm/s3c44b0/stack.c
index 3f1d88a390..6f838cb173 100644
--- a/libcpu/arm/s3c44b0/stack.c
+++ b/libcpu/arm/s3c44b0/stack.c
@@ -30,31 +30,33 @@
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	unsigned long *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (unsigned long *)stack_addr;
-	*(stk) 	 = (unsigned long)tentry;		/* entry point */
-	*(--stk) = (unsigned long)texit;		/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (unsigned long)parameter;	/* r0 : argument */
-	*(--stk) = SVCMODE;						/* cpsr */
-	*(--stk) = SVCMODE;						/* spsr */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
+    *(--stk) = SVCMODE;                     /* cpsr */
+    *(--stk) = SVCMODE;                     /* spsr */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/sep4020/stack.c b/libcpu/arm/sep4020/stack.c
index 7700373ff1..318b435f8e 100644
--- a/libcpu/arm/sep4020/stack.c
+++ b/libcpu/arm/sep4020/stack.c
@@ -22,38 +22,40 @@
  * This function will initialize thread stack
  *
  * @param tentry the entry of thread
- * @param parameter the parameter of entry 
+ * @param parameter the parameter of entry
  * @param stack_addr the beginning stack address
  * @param texit the function will be called when thread exit
  *
  * @return stack address
  */
 rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
-	rt_uint8_t *stack_addr, void *texit)
+                             rt_uint8_t *stack_addr, void *texit)
 {
-	rt_uint32_t *stk;
+    rt_uint32_t *stk;
 
-	stk 	 = (rt_uint32_t*)stack_addr;
-	*(stk) 	 = (rt_uint32_t)tentry;			/* entry point */
-	*(--stk) = (rt_uint32_t)texit;			/* lr */
-	*(--stk) = 0;							/* r12 */
-	*(--stk) = 0;							/* r11 */
-	*(--stk) = 0;							/* r10 */
-	*(--stk) = 0;							/* r9 */
-	*(--stk) = 0;							/* r8 */
-	*(--stk) = 0;							/* r7 */
-	*(--stk) = 0;							/* r6 */
-	*(--stk) = 0;							/* r5 */
-	*(--stk) = 0;							/* r4 */
-	*(--stk) = 0;							/* r3 */
-	*(--stk) = 0;							/* r2 */
-	*(--stk) = 0;							/* r1 */
-	*(--stk) = (rt_uint32_t)parameter;		/* r0 : argument */
-	*(--stk) = Mode_SVC;					/* cpsr */
-	*(--stk) = Mode_SVC;					/* spsr */
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
+    stk      = (rt_uint32_t *)stack_addr;
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)texit;          /* lr */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
+    *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
+    *(--stk) = Mode_SVC;                    /* cpsr */
+    *(--stk) = Mode_SVC;                    /* spsr */
 
-	/* return task's current stack address */
-	return (rt_uint8_t *)stk;
+    /* return task's current stack address */
+    return (rt_uint8_t *)stk;
 }
 
 /*@}*/
diff --git a/libcpu/arm/zynq7000/stack.c b/libcpu/arm/zynq7000/stack.c
index 8e1b86432e..08dd4b4dac 100644
--- a/libcpu/arm/zynq7000/stack.c
+++ b/libcpu/arm/zynq7000/stack.c
@@ -31,21 +31,23 @@ rt_uint8_t *rt_hw_stack_init(void *tentry, void *parameter,
 {
     rt_uint32_t *stk;
 
+    stack_addr += sizeof(rt_uint32_t);
+    stack_addr  = (rt_uint8_t *)RT_ALIGN_DOWN((rt_uint32_t)stack_addr, 8);
     stk      = (rt_uint32_t *)stack_addr;
-    *(stk)   = (rt_uint32_t)tentry;         /* entry point */
+    *(--stk) = (rt_uint32_t)tentry;         /* entry point */
     *(--stk) = (rt_uint32_t)texit;          /* lr */
-    *(--stk) = 0;                           /* r12 */
-    *(--stk) = 0;                           /* r11 */
-    *(--stk) = 0;                           /* r10 */
-    *(--stk) = 0;                           /* r9 */
-    *(--stk) = 0;                           /* r8 */
-    *(--stk) = 0;                           /* r7 */
-    *(--stk) = 0;                           /* r6 */
-    *(--stk) = 0;                           /* r5 */
-    *(--stk) = 0;                           /* r4 */
-    *(--stk) = 0;                           /* r3 */
-    *(--stk) = 0;                           /* r2 */
-    *(--stk) = 0;                           /* r1 */
+    *(--stk) = 0xdeadbeef;                  /* r12 */
+    *(--stk) = 0xdeadbeef;                  /* r11 */
+    *(--stk) = 0xdeadbeef;                  /* r10 */
+    *(--stk) = 0xdeadbeef;                  /* r9 */
+    *(--stk) = 0xdeadbeef;                  /* r8 */
+    *(--stk) = 0xdeadbeef;                  /* r7 */
+    *(--stk) = 0xdeadbeef;                  /* r6 */
+    *(--stk) = 0xdeadbeef;                  /* r5 */
+    *(--stk) = 0xdeadbeef;                  /* r4 */
+    *(--stk) = 0xdeadbeef;                  /* r3 */
+    *(--stk) = 0xdeadbeef;                  /* r2 */
+    *(--stk) = 0xdeadbeef;                  /* r1 */
     *(--stk) = (rt_uint32_t)parameter;      /* r0 : argument */
 
     /* cpsr */
diff --git a/tools/menuconfig.py b/tools/menuconfig.py
index 4ffcd9372f..4a339ec14b 100644
--- a/tools/menuconfig.py
+++ b/tools/menuconfig.py
@@ -80,7 +80,17 @@ def touch_env():
         os.mkdir(env_dir)
         os.mkdir(os.path.join(env_dir, 'local_pkgs'))
         os.mkdir(os.path.join(env_dir, 'packages'))
+
+        os.system('git clone https://github.com/RT-Thread/packages.git ~/.env/packages/packages')
+
         kconfig = file(os.path.join(env_dir, 'packages', 'Kconfig'), 'w')
+        kconfig.write('source "$PKGS_DIR/packages/Kconfig"')
+
+        os.mkdir(os.path.join(env_dir, 'tools'))
+        os.system('git clone https://github.com/RT-Thread/env.git ~/.env/tools/scripts')
+
+        env_sh = file(os.path.join(env_dir, 'env.sh'), 'w')
+        env_sh.write('export $PATH=~/.env/tools/scripts:$PATH')
 
 # menuconfig for Linux
 def menuconfig(RTT_ROOT):