Cause: Data bus error (return address in the stack frame is not related to the instruction that caused the error)

[vernon]

Dears,

I'm trying to run the mbedtls library with thread safety with the freertos, already defined MBEDTLS_THREADING_C and MBEDTLS_THREADING_ALT in the user_mbedtls_config.h, but the program runs into a crash when calling xSemaphoreTake( mutex->mutex, portMAX_DELAY ), it seems it's a concurrency issues, so I'm asking for help how to solve this problem, any suggestion is appreciated.

IDE: SES
SDK: nRF5_SDK_for_Thread_and_Zigbee_v3.1.0_c7c4730

the threading_alt.c file is:

void user_mbedtls_mutex_init( mbedtls_threading_mutex_t * mutex )
{
mutex->mutex = xSemaphoreCreateMutex();

if( mutex->mutex != NULL )
{
mutex->is_valid = 1;
}
else
{
mutex->is_valid = 0;
NRF_LOG_DEBUG( ( "Failed to initialize mbedTLS mutex.\r\n" ) );
NRF_LOG_FLUSH();
}
}

/**
* @brief Implementation of mbedtls_mutex_free for thread-safety.
*
*/
void user_mbedtls_mutex_free( mbedtls_threading_mutex_t * mutex )
{
if( mutex->is_valid == 1 )
{
vSemaphoreDelete( mutex->mutex );
mutex->is_valid = 0;
}
}

/**
* @brief Implementation of mbedtls_mutex_lock for thread-safety.
*
* @return 0 if successful, MBEDTLS_ERR_THREADING_MUTEX_ERROR if timeout,
* MBEDTLS_ERR_THREADING_BAD_INPUT_DATA if the mutex is not valid.
*/
int user_mbedtls_mutex_lock( mbedtls_threading_mutex_t * mutex )
{
int ret = MBEDTLS_ERR_THREADING_BAD_INPUT_DATA;

if( mutex->is_valid == 1 )
{
if( xSemaphoreTake( mutex->mutex, portMAX_DELAY ) )
{
ret = 0;
}
else
{
ret = MBEDTLS_ERR_THREADING_MUTEX_ERROR;
NRF_LOG_DEBUG( ( "Failed to obtain mbedTLS mutex.\r\n" ) );
NRF_LOG_FLUSH();
}
}

return ret;
}

/**
* @brief Implementation of mbedtls_mutex_unlock for thread-safety.
*
* @return 0 if successful, MBEDTLS_ERR_THREADING_MUTEX_ERROR if timeout,
* MBEDTLS_ERR_THREADING_BAD_INPUT_DATA if the mutex is not valid.
*/
int user_mbedtls_mutex_unlock( mbedtls_threading_mutex_t * mutex )
{
int ret = MBEDTLS_ERR_THREADING_BAD_INPUT_DATA;

if( mutex->is_valid == 1 )
{
if( xSemaphoreGive( mutex->mutex ) )
{
ret = 0;
}
else
{
ret = MBEDTLS_ERR_THREADING_MUTEX_ERROR;
NRF_LOG_DEBUG( ( "Failed to unlock mbedTLS mutex.\r\n" ) );
NRF_LOG_FLUSH();
}
}

return ret;
}



void user_mbedtls_threading_set_alt(void)
{
/* Configure mbedtls to use FreeRTOS mutexes. */
mbedtls_threading_set_alt( user_mbedtls_mutex_init,
user_mbedtls_mutex_free,
user_mbedtls_mutex_lock,
user_mbedtls_mutex_unlock );
}





the trace of the calling function is:

step 1:--->/SDK/external/mbedtls/library/ssl_cli.c --->line3273
---> int mbedtls_ssl_handshake_client_step( mbedtls_ssl_context *ssl )
case MBEDTLS_SSL_CLIENT_HELLO:
ret = ssl_write_client_hello( ssl );
break;


step 2--->/SDK/external/mbedtls/library/ssl_cli.c --->line707
---> static int ssl_write_client_hello( mbedtls_ssl_context *ssl )
MBEDTLS_SSL_DEBUG_MSG( 3, ( "client hello, max version: [%d:%d]",
buf[4], buf[5] ) );

if( ( ret = ssl_generate_random( ssl ) ) != 0 )
{
MBEDTLS_SSL_DEBUG_RET( 1, "ssl_generate_random", ret );
return( ret );
}


step 3--->/SDK/external/mbedtls/library/ssl_cli.c --->line667
---> static int ssl_generate_random( mbedtls_ssl_context *ssl )
if( ( ret = ssl->conf->f_rng( ssl->conf->p_rng, p, 28 ) ) != 0 )
return( ret );

step 4--->/SDK/external/mbedtls/library/ctr_drbg.c --->line399
---> int mbedtls_ctr_drbg_random( void *p_rng, unsigned char *output, size_t output_len )
#if defined(MBEDTLS_THREADING_C)
if( ( ret = mbedtls_mutex_lock( &ctx->mutex ) ) != 0 )
return( ret );
#endif

step 5 -- threading_alt.c 
int user_mbedtls_mutex_lock( mbedtls_threading_mutex_t * mutex )
{
int ret = MBEDTLS_ERR_THREADING_BAD_INPUT_DATA;

if( mutex->is_valid == 1 )
{
if( xSemaphoreTake( mutex->mutex, portMAX_DELAY ) )
{

the program stuck here and then hardfault happened, see the following log:

<error> hardfault: HARD FAULT at 0x00026DFE

<error> hardfault: R0: 0x200136D4 R1: 0x00000004 R2: 0xFFFFC2F7 R3: 0x000148B5

<error> hardfault: R12: 0x2002EF94 LR: 0x00027A1B PSR: 0x21000000

<error> hardfault: Cause: Data bus error (return address in the stack frame is not related to the instruction that caused the error).

Thanks so much if any help

[Susheel Nuguru]

can you keep a count on calls to xSemaphoreGive and xSemaphoreTake to see if the semaphore is given enough times for this mutex to be unlocked? What I mean to say is, could it be possible that the application is not unlocking the mutex properly?

[vernon]

I add two variable to the struct mbedtls_threading_mutex_t  for counting the take/give mutex control and update the mute_take/mutex_give function, please see the following snippet code
typedef struct
{
SemaphoreHandle_t mutex;
char is_valid;
uint8_t take_count;
uint8_t give_count;
} mbedtls_threading_mutex_t;

/**
* @brief Implementation of mbedtls_mutex_init for thread-safety.
*
*/
void user_mbedtls_mutex_init( mbedtls_threading_mutex_t * mutex )
{
mutex->mutex = xSemaphoreCreateMutex();

if( mutex->mutex != NULL )
{
mutex->is_valid = 1;
mutex->take_count = 0;
mutex->give_count = 0;
}
else
{
mutex->is_valid = 0;
NRF_LOG_DEBUG( ( "Failed to initialize mbedTLS mutex.\r\n" ) );
NRF_LOG_FLUSH();
}
}

/**
* @brief Implementation of mbedtls_mutex_free for thread-safety.
*
*/
void user_mbedtls_mutex_free( mbedtls_threading_mutex_t * mutex )
{
if( mutex->is_valid == 1 )
{
mutex->take_count = 0;
mutex->give_count = 0;
vSemaphoreDelete( mutex->mutex );
mutex->is_valid = 0;
}
}

/**
* @brief Implementation of mbedtls_mutex_lock for thread-safety.
*
* @return 0 if successful, MBEDTLS_ERR_THREADING_MUTEX_ERROR if timeout,
* MBEDTLS_ERR_THREADING_BAD_INPUT_DATA if the mutex is not valid.
*/
int user_mbedtls_mutex_lock( mbedtls_threading_mutex_t * mutex )
{
int ret = MBEDTLS_ERR_THREADING_BAD_INPUT_DATA;

if( mutex->is_valid == 1 )
{
if( xSemaphoreTake( mutex->mutex, portMAX_DELAY ) )
{
mutex->take_count++;
ret = 0;
}
else
{
ret = MBEDTLS_ERR_THREADING_MUTEX_ERROR;
NRF_LOG_DEBUG( ( "Failed to obtain mbedTLS mutex.\r\n" ) );
NRF_LOG_FLUSH();
}
}

return ret;
}

/**
* @brief Implementation of mbedtls_mutex_unlock for thread-safety.
*
* @return 0 if successful, MBEDTLS_ERR_THREADING_MUTEX_ERROR if timeout,
* MBEDTLS_ERR_THREADING_BAD_INPUT_DATA if the mutex is not valid.
*/
int user_mbedtls_mutex_unlock( mbedtls_threading_mutex_t * mutex )
{
int ret = MBEDTLS_ERR_THREADING_BAD_INPUT_DATA;

if( mutex->is_valid == 1 )
{
if( xSemaphoreGive( mutex->mutex ) )
{
mutex->give_count++;
ret = 0;
}
else
{
ret = MBEDTLS_ERR_THREADING_MUTEX_ERROR;
NRF_LOG_DEBUG( ( "Failed to unlock mbedTLS mutex.\r\n" ) );
NRF_LOG_FLUSH();
}
}

return ret;
}

the take and give mutex count is 0, so I think it would be successful to take the mutex, BUT the program would stuck at the if statement "if( xSemaphoreTake( mutex->mutex, portMAX_DELAY ) ) " forever.