drm/amdgpu: Convert to common fdinfo format v5

Convert fdinfo format to one documented in drm-usage-stats.rst.

It turned out that the existing implementation was actually completely
nonsense. The calculated percentages indeed represented the usage of the
engine, but with varying time slices.

So 10% usage for application A could mean something completely different
than 10% usage for application B.

Completely nuke that and just use the now standardized nanosecond
interface.

v2: drop the documentation change for now, nuke percentage calculation
v3: only account for each hw_ip, move the time_spend to the ctx mgr.
v4: move general ctx changes into separate patch, rework the fdinfo to
    ctx_mgr interface so that all usages are calculated at once, drop
    some unecessary and dangerous refcount dance.
v5: add one more comment how we calculate the time spend

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Shashank Sharma <shashank.sharma@amd.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 9 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
index 681050bc828c..cc7c8afff414 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
@@ -23,16 +23,20 @@
 #ifndef __AMDGPU_CTX_H__
 #define __AMDGPU_CTX_H__
 
+#include <linux/ktime.h>
+#include <linux/types.h>
+
 #include "amdgpu_ring.h"
 
 struct drm_device;
 struct drm_file;
 struct amdgpu_fpriv;
+struct amdgpu_ctx_mgr;
 
 #define AMDGPU_MAX_ENTITY_NUM 4
-#define AMDGPU_CTX_FENCE_USAGE_MIN_RATIO(max, total) ((max) > 16384ULL*(total))
 
 struct amdgpu_ctx_entity {
+	uint32_t		hw_ip;
 	uint64_t		sequence;
 	struct drm_sched_entity	entity;
 	struct dma_fence	*fences[];
@@ -61,6 +65,7 @@ struct amdgpu_ctx_mgr {
 	struct mutex		lock;
 	/* protected by lock */
 	struct idr		ctx_handles;
+	atomic64_t		time_spend[AMDGPU_HW_IP_NUM];
 };
 
 extern const unsigned int amdgpu_ctx_num_entities[AMDGPU_HW_IP_NUM];
@@ -90,6 +95,7 @@ void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr,
 void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
 long amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr, long timeout);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
-ktime_t amdgpu_ctx_mgr_fence_usage(struct amdgpu_ctx_mgr *mgr, uint32_t hwip,
-		uint32_t idx, uint64_t *elapsed);
+void amdgpu_ctx_mgr_usage(struct amdgpu_ctx_mgr *mgr,
+			  ktime_t usage[AMDGPU_HW_IP_NUM]);
+
 #endif