--- zzzz-none-000/linux-4.4.60/drivers/spi/spi-gpio.c	2017-04-08 07:53:53.000000000 +0000
+++ wasp-540e-714/linux-4.4.60/drivers/spi/spi-gpio.c	2019-07-03 09:21:34.000000000 +0000
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
+#include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
@@ -69,6 +70,7 @@
  *		#define	SPI_MOSI_GPIO	120
  *		#define	SPI_SCK_GPIO	121
  *		#define	SPI_N_CHIPSEL	4
+ *		#undef NEED_SPIDELAY
  *		#include "spi-gpio.c"
  */
 
@@ -76,6 +78,7 @@
 #define DRIVER_NAME	"spi_gpio"
 
 #define GENERIC_BITBANG	/* vs tight inlines */
+#define NEED_SPIDELAY	1
 
 /* all functions referencing these symbols must define pdata */
 #define SPI_MISO_GPIO	((pdata)->miso)
@@ -126,12 +129,20 @@
 #undef pdata
 
 /*
- * NOTE:  this clocks "as fast as we can".  It "should" be a function of the
- * requested device clock.  Software overhead means we usually have trouble
- * reaching even one Mbit/sec (except when we can inline bitops), so for now
- * we'll just assume we never need additional per-bit slowdowns.
+ * NOTE:  to clock "as fast as we can", set spi_device.max_speed_hz
+ * and spi_transfer.speed_hz to 0.
+ * Otherwise this is a function of the requested device clock.
+ * Software overhead means we usually have trouble
+ * reaching even one Mbit/sec (except when we can inline bitops). So on small
+ * embedded devices with fast SPI slaves you usually don't need a delay.
  */
-#define spidelay(nsecs)	do {} while (0)
+static inline void spidelay(unsigned nsecs)
+{
+#ifdef NEED_SPIDELAY
+	if (unlikely(nsecs))
+		ndelay(nsecs);
+#endif /* NEED_SPIDELAY */
+}
 
 #include "spi-bitbang-txrx.h"