drm/msm: Trigger fence completion from GPU

Interrupt commands causes the CP to trigger an interrupt as the command
is processed, regardless of the GPU being done processing previous
commands. This is seen by the interrupt being delivered before the
fence is written on 8974 and is likely the cause of the additional
CP_WAIT_FOR_IDLE workaround found for a306, which would cause the CP to
wait for the GPU to go idle before triggering the interrupt.

Instead we can set the (undocumented) BIT(31) of the CACHE_FLUSH_TS
which will cause a special CACHE_FLUSH_TS interrupt to be triggered from
the GPU as the write event is processed.

Add CACHE_FLUSH_TS to the IRQ masks of A3xx and A4xx and remove the
workaround for A306.

Suggested-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>

drivers/gpu/drm/msm/adreno/a3xx_gpu.c

@@ -35,6 +35,7 @@
 	 A3XX_INT0_CP_RB_INT |             \
 	 A3XX_INT0_CP_REG_PROTECT_FAULT |  \
 	 A3XX_INT0_CP_AHB_ERROR_HALT |     \
+	 A3XX_INT0_CACHE_FLUSH_TS |        \
 	 A3XX_INT0_UCHE_OOB_ACCESS)
 
 extern bool hang_debug;

drivers/gpu/drm/msm/adreno/a4xx_gpu.c

@@ -27,6 +27,7 @@
 	 A4XX_INT0_CP_RB_INT |             \
 	 A4XX_INT0_CP_REG_PROTECT_FAULT |  \
 	 A4XX_INT0_CP_AHB_ERROR_HALT |     \
+	 A4XX_INT0_CACHE_FLUSH_TS |        \
 	 A4XX_INT0_UCHE_OOB_ACCESS)
 
 extern bool hang_debug;

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -313,26 +313,12 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		OUT_RING(ring, 0x00000000);
 	}
 
+	/* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */
 	OUT_PKT3(ring, CP_EVENT_WRITE, 3);
-	OUT_RING(ring, CACHE_FLUSH_TS);
+	OUT_RING(ring, CACHE_FLUSH_TS | BIT(31));
 	OUT_RING(ring, rbmemptr(ring, fence));
 	OUT_RING(ring, submit->seqno);
 
-	/* we could maybe be clever and only CP_COND_EXEC the interrupt: */
-	OUT_PKT3(ring, CP_INTERRUPT, 1);
-	OUT_RING(ring, 0x80000000);
-
-	/* Workaround for missing irq issue on 8x16/a306.  Unsure if the
-	 * root cause is a platform issue or some a306 quirk, but this
-	 * keeps things humming along:
-	 */
-	if (adreno_is_a306(adreno_gpu)) {
-		OUT_PKT3(ring, CP_WAIT_FOR_IDLE, 1);
-		OUT_RING(ring, 0x00000000);
-		OUT_PKT3(ring, CP_INTERRUPT, 1);
-		OUT_RING(ring, 0x80000000);
-	}
-
 #if 0
 	if (adreno_is_a3xx(adreno_gpu)) {
 		/* Dummy set-constant to trigger context rollover */