drm/lima: Add optional devfreq and cooling device support

Most platforms with a Mali-400 or Mali-450 GPU also have support for
changing the GPU clock frequency. Add devfreq support so the GPU clock
rate is updated based on the actual GPU usage when the
"operating-points-v2" property is present in the board.dts.

The actual devfreq code is taken from panfrost_devfreq.c and modified so
it matches what the lima hardware needs:
- a call to dev_pm_opp_set_clkname() during initialization because there
  are two clocks on Mali-4x0 IPs. "core" is the one that actually clocks
  the GPU so we need to control it using devfreq.
- locking when reading or writing the devfreq statistics because (unlike
  than panfrost) we have multiple PP and GP IRQs which may finish jobs
  concurrently.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200319203427.2259891-3-martin.blumenstingl@googlemail.com

drivers/gpu/drm/lima/lima_sched.c

@@ -5,6 +5,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
+#include "lima_devfreq.h"
 #include "lima_drv.h"
 #include "lima_sched.h"
 #include "lima_vm.h"
@@ -216,6 +217,8 @@ static struct dma_fence *lima_sched_run_job(struct drm_sched_job *job)
 	 */
 	ret = dma_fence_get(task->fence);
 
+	lima_devfreq_record_busy(&pipe->ldev->devfreq);
+
 	pipe->current_task = task;
 
 	/* this is needed for MMU to work correctly, otherwise GP/PP
@@ -418,6 +421,8 @@ static void lima_sched_timedout_job(struct drm_sched_job *job)
 	pipe->current_vm = NULL;
 	pipe->current_task = NULL;
 
+	lima_devfreq_record_idle(&pipe->ldev->devfreq);
+
 	drm_sched_resubmit_jobs(&pipe->base);
 	drm_sched_start(&pipe->base, true);
 }
@@ -497,5 +502,7 @@ void lima_sched_pipe_task_done(struct lima_sched_pipe *pipe)
 	} else {
 		pipe->task_fini(pipe);
 		dma_fence_signal(task->fence);
+
+		lima_devfreq_record_idle(&pipe->ldev->devfreq);
 	}
 }