drm/v3d: Replace wait_for macros to remove use of msleep

The wait_for macro's for Broadcom V3D driver used msleep, which is
inappropriate due to its inaccuracy at low values (minimum wait time
is about 30ms on the Raspberry Pi).  This sleep was triggering in
v3d_clean_caches(), causing us to only be able to dispatch ~33 compute
jobs per second.

This patch replaces the macro with the one from the Intel i915 version
which uses usleep_range to provide more accurate waits.

v2: Split from the vc4 patch so that we can confidently apply to
    stable (by anholt)
Signed-off-by: James Hughes <james.hughes@raspberrypi.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20200217153145.13780-1-james.hughes@raspberrypi.com
Link: https://github.com/raspberrypi/linux/issues/3460
Fixes: 57692c94 ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")

drivers/gpu/drm/v3d/v3d_drv.h

@@ -254,27 +254,42 @@ struct v3d_csd_job {
 };
 
 /**
- * _wait_for - magic (register) wait macro
+ * __wait_for - magic wait macro
  *
- * Does the right thing for modeset paths when run under kdgb or similar atomic
- * contexts. Note that it's important that we check the condition again after
- * having timed out, since the timeout could be due to preemption or similar and
- * we've never had a chance to check the condition before the timeout.
+ * Macro to help avoid open coding check/wait/timeout patterns. Note that it's
+ * important that we check the condition again after having timed out, since the
+ * timeout could be due to preemption or similar and we've never had a chance to
+ * check the condition before the timeout.
  */
-#define wait_for(COND, MS) ({ \
-	unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1;	\
-	int ret__ = 0;							\
-	while (!(COND)) {						\
-		if (time_after(jiffies, timeout__)) {			\
-			if (!(COND))					\
-				ret__ = -ETIMEDOUT;			\
+#define __wait_for(OP, COND, US, Wmin, Wmax) ({ \
+	const ktime_t end__ = ktime_add_ns(ktime_get_raw(), 1000ll * (US)); \
+	long wait__ = (Wmin); /* recommended min for usleep is 10 us */	\
+	int ret__;							\
+	might_sleep();							\
+	for (;;) {							\
+		const bool expired__ = ktime_after(ktime_get_raw(), end__); \
+		OP;							\
+		/* Guarantee COND check prior to timeout */		\
+		barrier();						\
+		if (COND) {						\
+			ret__ = 0;					\
 			break;						\
 		}							\
-		msleep(1);					\
+		if (expired__) {					\
+			ret__ = -ETIMEDOUT;				\
+			break;						\
+		}							\
+		usleep_range(wait__, wait__ * 2);			\
+		if (wait__ < (Wmax))					\
+			wait__ <<= 1;					\
 	}								\
 	ret__;								\
 })
 
+#define _wait_for(COND, US, Wmin, Wmax)	__wait_for(, (COND), (US), (Wmin), \
+						   (Wmax))
+#define wait_for(COND, MS)		_wait_for((COND), (MS) * 1000, 10, 1000)
+
 static inline unsigned long nsecs_to_jiffies_timeout(const u64 n)
 {
 	/* nsecs_to_jiffies64() does not guard against overflow */