drm/panfrost: Expose performance counters through unstable ioctls

Expose performance counters through 2 driver specific ioctls: one to
enable/disable the perfcnt block, and one to dump the counter values.

There are discussions to expose global performance monitors (those
counters that can't be retrieved on a per-job basis) in a consistent
way, but this is likely to take time to settle on something that works
for various HW/users.
The ioctls are marked unstable so we can get rid of them when the time
comes. We initally went for a debugfs-based interface, but this was
making the transition to per-FD address space more complicated (we need
to specify the namespace the GPU has to use when dumping the perf
counters), hence the decision to switch back to driver specific ioctls
which are passed the FD they operate on and thus will have a dedicated
address space attached to them.

Other than that, the implementation is pretty simple: it basically dumps
all counters and copy the values to a userspace buffer. The parsing is
left to userspace which has to know the specific layout that's used
by the GPU (layout differs on a per-revision basis).

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20190618081648.17297-5-boris.brezillon@collabora.com

drivers/gpu/drm/panfrost/Makefile

@@ -7,6 +7,7 @@ panfrost-y := \
 	panfrost_gem.o \
 	panfrost_gpu.o \
 	panfrost_job.o \
-	panfrost_mmu.o
+	panfrost_mmu.o \
+	panfrost_perfcnt.o
 
 obj-$(CONFIG_DRM_PANFROST) += panfrost.o

drivers/gpu/drm/panfrost/panfrost_device.c

@@ -14,6 +14,7 @@
 #include "panfrost_gpu.h"
 #include "panfrost_job.h"
 #include "panfrost_mmu.h"
+#include "panfrost_perfcnt.h"
 
 static int panfrost_reset_init(struct panfrost_device *pfdev)
 {
@@ -171,7 +172,13 @@ int panfrost_device_init(struct panfrost_device *pfdev)
 	pm_runtime_mark_last_busy(pfdev->dev);
 	pm_runtime_put_autosuspend(pfdev->dev);
 
+	err = panfrost_perfcnt_init(pfdev);
+	if (err)
+		goto err_out5;
+
 	return 0;
+err_out5:
+	panfrost_job_fini(pfdev);
 err_out4:
 	panfrost_mmu_fini(pfdev);
 err_out3:
@@ -187,6 +194,7 @@ int panfrost_device_init(struct panfrost_device *pfdev)
 
 void panfrost_device_fini(struct panfrost_device *pfdev)
 {
+	panfrost_perfcnt_fini(pfdev);
 	panfrost_job_fini(pfdev);
 	panfrost_mmu_fini(pfdev);
 	panfrost_gpu_fini(pfdev);

drivers/gpu/drm/panfrost/panfrost_device.h

@@ -14,6 +14,7 @@ struct panfrost_device;
 struct panfrost_mmu;
 struct panfrost_job_slot;
 struct panfrost_job;
+struct panfrost_perfcnt;
 
 #define NUM_JOB_SLOTS 3
 
@@ -78,6 +79,8 @@ struct panfrost_device {
 	struct panfrost_job *jobs[NUM_JOB_SLOTS];
 	struct list_head scheduled_jobs;
 
+	struct panfrost_perfcnt *perfcnt;
+
 	struct mutex sched_lock;
 	struct mutex reset_lock;
 

drivers/gpu/drm/panfrost/panfrost_drv.c

@@ -19,6 +19,7 @@
 #include "panfrost_mmu.h"
 #include "panfrost_job.h"
 #include "panfrost_gpu.h"
+#include "panfrost_perfcnt.h"
 
 static bool unstable_ioctls;
 module_param_unsafe(unstable_ioctls, bool, 0600);
@@ -329,6 +330,7 @@ panfrost_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct panfrost_file_priv *panfrost_priv = file->driver_priv;
 
+	panfrost_perfcnt_close(panfrost_priv);
 	panfrost_job_close(panfrost_priv);
 
 	kfree(panfrost_priv);
@@ -348,6 +350,8 @@ static const struct drm_ioctl_desc panfrost_drm_driver_ioctls[] = {
 	PANFROST_IOCTL(MMAP_BO,		mmap_bo,	DRM_RENDER_ALLOW),
 	PANFROST_IOCTL(GET_PARAM,	get_param,	DRM_RENDER_ALLOW),
 	PANFROST_IOCTL(GET_BO_OFFSET,	get_bo_offset,	DRM_RENDER_ALLOW),
+	PANFROST_IOCTL(PERFCNT_ENABLE,	perfcnt_enable,	DRM_RENDER_ALLOW),
+	PANFROST_IOCTL(PERFCNT_DUMP,	perfcnt_dump,	DRM_RENDER_ALLOW),
 };
 
 DEFINE_DRM_GEM_SHMEM_FOPS(panfrost_drm_driver_fops);

drivers/gpu/drm/panfrost/panfrost_gpu.c

@@ -15,6 +15,7 @@
 #include "panfrost_features.h"
 #include "panfrost_issues.h"
 #include "panfrost_gpu.h"
+#include "panfrost_perfcnt.h"
 #include "panfrost_regs.h"
 
 static irqreturn_t panfrost_gpu_irq_handler(int irq, void *data)
@@ -40,6 +41,12 @@ static irqreturn_t panfrost_gpu_irq_handler(int irq, void *data)
 		gpu_write(pfdev, GPU_INT_MASK, 0);
 	}
 
+	if (state & GPU_IRQ_PERFCNT_SAMPLE_COMPLETED)
+		panfrost_perfcnt_sample_done(pfdev);
+
+	if (state & GPU_IRQ_CLEAN_CACHES_COMPLETED)
+		panfrost_perfcnt_clean_cache_done(pfdev);
+
 	gpu_write(pfdev, GPU_INT_CLEAR, state);
 
 	return IRQ_HANDLED;