Problem configuring STM32F4 Discovery as SPI slave

// this function initializes the SPI1 peripheral
void init_SPI1(void){
	
	GPIO_InitTypeDef GPIO_InitStruct;
	SPI_InitTypeDef SPI_InitStruct;
	
	// enable clock for used IO pins
	RCC_AHB1PeriphClockCmd(RCC_AHB1Periph_GPIOA, ENABLE);
	
	/* configure pins used by SPI1
	 * PA5 = SCK
	 * PA6 = MISO
	 * PA7 = MOSI
	 */
	GPIO_InitStruct.GPIO_Pin = GPIO_Pin_7 | GPIO_Pin_6 | GPIO_Pin_5;
	GPIO_InitStruct.GPIO_Mode = GPIO_Mode_AF;
	GPIO_InitStruct.GPIO_OType = GPIO_OType_PP;
	GPIO_InitStruct.GPIO_Speed = GPIO_Speed_100MHz;
	GPIO_InitStruct.GPIO_PuPd = GPIO_PuPd_NOPULL;
	GPIO_Init(GPIOA, &GPIO_InitStruct);
	
	// connect SPI1 pins to SPI alternate function
	GPIO_PinAFConfig(GPIOA, GPIO_PinSource5, GPIO_AF_SPI1);
	GPIO_PinAFConfig(GPIOA, GPIO_PinSource6, GPIO_AF_SPI1);
	GPIO_PinAFConfig(GPIOA, GPIO_PinSource7, GPIO_AF_SPI1);

	// enable clock for used IO pins
	RCC_AHB1PeriphClockCmd(RCC_AHB1Periph_GPIOE, ENABLE);
	
	// enable peripheral clock
	RCC_APB2PeriphClockCmd(RCC_APB2Periph_SPI1, ENABLE);
	
	/* configure SPI1
	 * CPOL = 1 --> clock is high when idle
	 * CPHA = 0 --> data is sampled at the second edge
	 */
	SPI_InitStruct.SPI_Direction = SPI_Direction_2Lines_FullDuplex; // set to full duplex mode, seperate MOSI and MISO lines
	SPI_InitStruct.SPI_Mode = SPI_Mode_Master;     // transmit in master mode, NSS pin has to be always high
	SPI_InitStruct.SPI_DataSize = SPI_DataSize_8b; // one packet of data is 8 bits wide
	SPI_InitStruct.SPI_CPOL = SPI_CPOL_High;        // clock is high when idle
	SPI_InitStruct.SPI_CPHA = SPI_CPHA_2Edge;      // data sampled at second edge
	SPI_InitStruct.SPI_NSS = SPI_NSS_Soft; // set the NSS management to internal and pull internal NSS high
	SPI_InitStruct.SPI_BaudRatePrescaler = SPI_BaudRatePrescaler_4; // SPI frequency is APB2 frequency / 4
	SPI_InitStruct.SPI_FirstBit = SPI_FirstBit_MSB;// data is transmitted MSB first
	SPI_Init(SPI1, &SPI_InitStruct); 
	
	SPI_Cmd(SPI1, ENABLE); // enable SPI1
}

/* This funtion is used to transmit and receive data 
 * with SPI1
 * 			data --> data to be transmitted
 * 			returns received value
 */
uint8_t SPI1_send(uint8_t data){

	SPI1->DR = data; // write data to be transmitted to the SPI data register
	while( !(SPI1->SR & SPI_I2S_FLAG_TXE) ); // wait until transmit complete
	while( !(SPI1->SR & SPI_I2S_FLAG_RXNE) ); // wait until receive complete
	while( SPI1->SR & SPI_I2S_FLAG_BSY ); // wait until SPI is not busy anymore
	return SPI1->DR; // return received data from SPI data register
}

int main(void) {
	init_SPI1();
	while(1){
		SPI1_send(0x00);  // transmit data
	}
}

/*********************************************************************
*
*                             Defines
*
*********************************************************************/
#define _MASTER_MODE     0
#define _SLAVE_MODE      1

#define _SMP            0    /*  0 = Input data sampled at middle of data output time (SMP must be cleared in slave mode) */
#define _CKE            0     /* 0 = Transmit occurs on transition from idle to active clock state */
#define _CKP            1     /* 1 = Idle state for clock is a high level */
#define _SSPM_MASTER    0b0000     /* 0000 = Master mode, clock = Fosc/4 */
#define _SSPM_SLAVE     0b0101      /*  0101 = Slave mode, clock = SCK pin, SS pin disabled (can be used as I/O pin) */

void SPI_init(unsigned char mode) {
    TRISA = 0x00;               /* set all port A pins as output pins */
    ADCON1 = 0x0F;              /* set all port A pins, including SS (RA5), as digital I/O */

    if (mode == _MASTER_MODE) {
    TRISC = 0b00010000;         /* Set SCK pin (RC3) as output
                                 * SDI pin (RC4) as input
                                 * SDO pin (RC5) as output */
    } else {
    TRISC = 0b00011000;         /* Set SCK pin (RC3) as input
                                 * SDI pin (RC4) as input
                                 * SDO pin (RC5) as output */
    }

    SSPSTAT = 0b00000000;       /* Initialize SSPSTAT register to POR state */
    SSPSTATbits.SMP = _SMP;     /* Configure sample bit */
    SSPSTATbits.CKE = _CKE;     /* Configure clock select bit */

    SSPCON1 = 0b00000000;       /* Initialize SSPCON1 register to POR state */
    SSPCON1bits.CKP = _CKP;     /* Configure clock polarity select bit */
    SSPCON1bits.SSPEN = 1;      /* Enable SPI (set SCK, SDO, SDI, and SS as serial port pins)*/

    if (mode == _MASTER_MODE)
        SSPCON1bits.SSPM = _SSPM_MASTER;    /* Configure sync mode bits for master */
    else
        SSPCON1bits.SSPM = _SSPM_SLAVE;     /* Configure sync mode bits for slave */
}

unsigned char SPI_send(unsigned char data) {
    unsigned char TempVar;

    TempVar = SSPBUF;           /* Clears BF */
    PIR1bits.SSPIF = 0;         /* Clear interrupt flag */
    SSPCON1bits.WCOL = 0;	/* Clear any previous write collision */
    SSPBUF = data;              /* clock out data */
    while(!PIR1bits.SSPIF);     /* wait until transmission completed */
    PIR1bits.SSPIF = 0;         /* clear interrupt flag bit */
    return (SSPBUF);
}

int main(void) {
    SPI_init(_SLAVE_MODE);

    while (1) {
        SPI_send('A');
    }

    return (EXIT_SUCCESS);
}

              .....
	SPI_InitStruct.SPI_Mode = SPI_Mode_Slave;     // transmit in slave mode
              .....

    .....
    SPI_init(_MASTER_MODE);
    .....