UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdgpu: add command submission workflow tracepoint 

OGL needs these tracepoints to investigate performance issue.

Change-Id: I5e58187d061253f7d665dfce8e4e163ba91d3e2b
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
This commit is contained in:
Chunming Zhou 2015-11-11 14:56:00 +08:00 committed by Alex Deucher
parent 5f2e816b29
commit 7034decf6a
5 changed files with 76 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
View File

@ -888,7 +888,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
ttm_eu_fence_buffer_objects(&parser.ticket, ttm_eu_fence_buffer_objects(&parser.ticket,
&parser.validated, &parser.validated,
&job->base.s_fence->base); &job->base.s_fence->base);
trace_amdgpu_cs_ioctl(job);
mutex_unlock(&job->job_lock); mutex_unlock(&job->job_lock);
amdgpu_cs_parser_fini_late(&parser); amdgpu_cs_parser_fini_late(&parser);
mutex_unlock(&vm->mutex); mutex_unlock(&vm->mutex);

2
drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
View File

@ -26,6 +26,7 @@
#include <linux/sched.h> #include <linux/sched.h>
#include <drm/drmP.h> #include <drm/drmP.h>
#include "amdgpu.h" #include "amdgpu.h"
#include "amdgpu_trace.h"
static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job) static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job)
{ {
@ -45,6 +46,7 @@ static struct fence *amdgpu_sched_run_job(struct amd_sched_job *sched_job)
} }
job = to_amdgpu_job(sched_job); job = to_amdgpu_job(sched_job);
mutex_lock(&job->job_lock); mutex_lock(&job->job_lock);
trace_amdgpu_sched_run_job(job);
r = amdgpu_ib_schedule(job->adev, r = amdgpu_ib_schedule(job->adev,
job->num_ibs, job->num_ibs,
job->ibs, job->ibs,

51
drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
View File

@ -48,6 +48,57 @@ TRACE_EVENT(amdgpu_cs,
__entry->fences) __entry->fences)
); );
TRACE_EVENT(amdgpu_cs_ioctl,
TP_PROTO(struct amdgpu_job *job),
TP_ARGS(job),
TP_STRUCT__entry(
__field(struct amdgpu_device *, adev)
__field(struct amd_sched_job *, sched_job)
__field(struct amdgpu_ib *, ib)
__field(struct fence *, fence)
__field(char *, ring_name)
__field(u32, num_ibs)
),
TP_fast_assign(
__entry->adev = job->adev;
__entry->sched_job = &job->base;
__entry->ib = job->ibs;
__entry->fence = &job->base.s_fence->base;
__entry->ring_name = job->ibs[0].ring->name;
__entry->num_ibs = job->num_ibs;
),
TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
__entry->adev, __entry->sched_job, __entry->ib,
__entry->fence, __entry->ring_name, __entry->num_ibs)
);
TRACE_EVENT(amdgpu_sched_run_job,
TP_PROTO(struct amdgpu_job *job),
TP_ARGS(job),
TP_STRUCT__entry(
__field(struct amdgpu_device *, adev)
__field(struct amd_sched_job *, sched_job)
__field(struct amdgpu_ib *, ib)
__field(struct fence *, fence)
__field(char *, ring_name)
__field(u32, num_ibs)
),
TP_fast_assign(
__entry->adev = job->adev;
__entry->sched_job = &job->base;
__entry->ib = job->ibs;
__entry->fence = &job->base.s_fence->base;
__entry->ring_name = job->ibs[0].ring->name;
__entry->num_ibs = job->num_ibs;
),
TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
__entry->adev, __entry->sched_job, __entry->ib,
__entry->fence, __entry->ring_name, __entry->num_ibs)
);
TRACE_EVENT(amdgpu_vm_grab_id, TRACE_EVENT(amdgpu_vm_grab_id,
TP_PROTO(unsigned vmid, int ring), TP_PROTO(unsigned vmid, int ring),
TP_ARGS(vmid, ring), TP_ARGS(vmid, ring),

24
drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
View File

@ -16,6 +16,8 @@ TRACE_EVENT(amd_sched_job,
TP_ARGS(sched_job), TP_ARGS(sched_job),
TP_STRUCT__entry( TP_STRUCT__entry(
__field(struct amd_sched_entity *, entity) __field(struct amd_sched_entity *, entity)
__field(struct amd_sched_job *, sched_job)
__field(struct fence *, fence)
__field(const char *, name) __field(const char *, name)
__field(u32, job_count) __field(u32, job_count)
__field(int, hw_job_count) __field(int, hw_job_count)
@ -23,16 +25,32 @@ TRACE_EVENT(amd_sched_job,
TP_fast_assign( TP_fast_assign(
__entry->entity = sched_job->s_entity; __entry->entity = sched_job->s_entity;
__entry->sched_job = sched_job;
__entry->fence = &sched_job->s_fence->base;
__entry->name = sched_job->sched->name; __entry->name = sched_job->sched->name;
__entry->job_count = kfifo_len( __entry->job_count = kfifo_len(
&sched_job->s_entity->job_queue) / sizeof(sched_job); &sched_job->s_entity->job_queue) / sizeof(sched_job);
__entry->hw_job_count = atomic_read( __entry->hw_job_count = atomic_read(
&sched_job->sched->hw_rq_count); &sched_job->sched->hw_rq_count);
), ),
TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d", TP_printk("entity=%p, sched job=%p, fence=%p, ring=%s, job count:%u, hw job count:%d",
__entry->entity, __entry->name, __entry->job_count, __entry->entity, __entry->sched_job, __entry->fence, __entry->name,
__entry->hw_job_count) __entry->job_count, __entry->hw_job_count)
); );
TRACE_EVENT(amd_sched_process_job,
TP_PROTO(struct amd_sched_fence *fence),
TP_ARGS(fence),
TP_STRUCT__entry(
__field(struct fence *, fence)
),
TP_fast_assign(
__entry->fence = &fence->base;
),
TP_printk("fence=%p signaled", __entry->fence)
);
#endif #endif
/* This part must be outside protection */ /* This part must be outside protection */

1
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
View File

@ -346,6 +346,7 @@ static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
list_del_init(&s_fence->list); list_del_init(&s_fence->list);
spin_unlock_irqrestore(&sched->fence_list_lock, flags); spin_unlock_irqrestore(&sched->fence_list_lock, flags);
} }
trace_amd_sched_process_job(s_fence);
fence_put(&s_fence->base); fence_put(&s_fence->base);
wake_up_interruptible(&sched->wake_up_worker); wake_up_interruptible(&sched->wake_up_worker);
} }