bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-18 14:53:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: Convert to common fdinfo format v5

Browse Source 
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>
This commit is contained in:
Christian König
2022-05-11 11:06:26 +02:00
committed by Alex Deucher
parent 08cffb3eb7
commit af0b541670
3 changed files with 126 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
View File

@@ -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