ath10k: enable RX bundle receive for sdio

The existing implementation of initiating multiple sdio transfers for
receive bundling is slowing down the receive speed. Combining the
transfers using a bundle method would be ideal.

The transmission utilization ratio for sdio bus for small packet is
slow, because the space and time cost for sdio bus is same for large
length packet and small length packet. So the speed of data for large
length packet is higher than small length.

Test result of different length of data:
data packet(byte)   cost time(us)   calculated rate(Mbps)
      256               28                73
      512               33               124
     1024               35               234
     1792               45               318
    14336              168               682
    28672              333               688
    57344              660               695

Tested with QCA6174 SDIO with firmware
WLAN.RMH.4.4.1-00017-QCARMSWPZ-1

Signed-off-by: Alagu Sankar <alagusankar@silex-india.com>
Signed-off-by: Wen Gong <wgong@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

drivers/net/wireless/ath/ath10k/sdio.h

@@ -138,8 +138,8 @@ struct ath10k_sdio_irq_proc_regs {
 	u8 rx_lookahead_valid;
 	u8 host_int_status2;
 	u8 gmbox_rx_avail;
-	__le32 rx_lookahead[2];
-	__le32 rx_gmbox_lookahead_alias[2];
+	__le32 rx_lookahead[2 * ATH10K_HIF_MBOX_NUM_MAX];
+	__le32 int_status_enable;
 };
 
 struct ath10k_sdio_irq_enable_regs {
@@ -196,6 +196,13 @@ struct ath10k_sdio {
 	struct ath10k *ar;
 	struct ath10k_sdio_irq_data irq_data;
 
+	/* temporary buffer for sdio read.
+	 * It is allocated when probe, and used for receive bundled packets,
+	 * the read for bundled packets is not parallel, so it does not need
+	 * protected.
+	 */
+	u8 *vsg_buffer;
+
 	/* temporary buffer for BMI requests */
 	u8 *bmi_buf;