[PATCH] drm/amdgpu: fix the null pointer to get timeline by scheduler fence

[Huang Rui]

We won't initialize fence scheduler in drm_sched_fence_create() anymore, so it
will refer null fence scheduler if open trace event to get the timeline name.
Actually, it is the scheduler name from the entity, so add a macro to replace
legacy getting timeline name by job.

[  212.844281] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
[  212.852401] PGD 8000000427c13067 P4D 8000000427c13067 PUD 4235fc067 PMD 0
[  212.859419] Oops: 0000 [#1] SMP PTI
[  212.862981] CPU: 4 PID: 1520 Comm: amdgpu_test Tainted: G           OE     4.18.0-rc1-custom #1
[  212.872194] Hardware name: Gigabyte Technology Co., Ltd. Z170XP-SLI/Z170XP-SLI-CF, BIOS F20 11/04/2016
[  212.881704] RIP: 0010:drm_sched_fence_get_timeline_name+0x2b/0x30 [gpu_sched]
[  212.888948] Code: 1f 44 00 00 48 8b 47 08 48 3d c0 b1 4f c0 74 13 48 83 ef 60 48 3d 60 b1 4f c0 b8 00 00 00 00 48 0f 45 f8 48 8b 87 e0 00 00 00 <48> 8b 40 18 c3 0f 1f 44 00 00 b8 01 00 00 00 c3 0f 1f 44 00 00 0f
[  212.908162] RSP: 0018:ffffa3ed81f27af0 EFLAGS: 00010246
[  212.913483] RAX: 0000000000000000 RBX: 0000000000070034 RCX: ffffa3ed81f27da8
[  212.920735] RDX: ffff8f24ebfb5460 RSI: ffff8f24e40d3c00 RDI: ffff8f24ebfb5400
[  212.928008] RBP: ffff8f24e40d3c00 R08: 0000000000000000 R09: ffffffffae4deafc
[  212.935263] R10: ffffffffada000ed R11: 0000000000000001 R12: ffff8f24e891f898
[  212.942558] R13: 0000000000000000 R14: ffff8f24ebc46000 R15: ffff8f24e3de97a8
[  212.949796] FS:  00007ffff7fd2700(0000) GS:ffff8f24fed00000(0000) knlGS:0000000000000000
[  212.958047] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  212.963921] CR2: 0000000000000018 CR3: 0000000423422003 CR4: 00000000003606e0
[  212.971201] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  212.978482] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  212.985720] Call Trace:
[  212.988236]  trace_event_raw_event_amdgpu_cs_ioctl+0x4c/0x170 [amdgpu]
[  212.994904]  ? amdgpu_ctx_add_fence+0xa9/0x110 [amdgpu]
[  213.000246]  ? amdgpu_job_free_resources+0x4b/0x70 [amdgpu]
[  213.005944]  amdgpu_cs_ioctl+0x16d1/0x1b50 [amdgpu]
[  213.010920]  ? amdgpu_cs_find_mapping+0xf0/0xf0 [amdgpu]
[  213.016354]  drm_ioctl_kernel+0x8a/0xd0 [drm]
[  213.020794]  ? recalc_sigpending+0x17/0x50
[  213.024965]  drm_ioctl+0x2d7/0x390 [drm]
[  213.028979]  ? amdgpu_cs_find_mapping+0xf0/0xf0 [amdgpu]
[  213.034366]  ? do_signal+0x36/0x700
[  213.037928]  ? signal_wake_up_state+0x15/0x30
[  213.042375]  amdgpu_drm_ioctl+0x46/0x80 [amdgpu]

Signed-off-by: Huang Rui <ray.huang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h | 10 ++++++----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index e12871d..be01e1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1247,7 +1247,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	amdgpu_job_free_resources(job);
 
-	trace_amdgpu_cs_ioctl(job);
+	trace_amdgpu_cs_ioctl(job, entity);
 	amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->ticket);
 	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 8c2dab2..25cdcb7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -36,6 +36,8 @@
 
 #define AMDGPU_JOB_GET_TIMELINE_NAME(job) \
 	 job->base.s_fence->finished.ops->get_timeline_name(&job->base.s_fence->finished)
+#define AMDGPU_GET_SCHED_NAME(entity) \
+	 (entity->rq->sched->name)
 
 TRACE_EVENT(amdgpu_mm_rreg,
 	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
@@ -161,11 +163,11 @@ TRACE_EVENT(amdgpu_cs,
 );
 
 TRACE_EVENT(amdgpu_cs_ioctl,
-	    TP_PROTO(struct amdgpu_job *job),
-	    TP_ARGS(job),
+	    TP_PROTO(struct amdgpu_job *job, struct drm_sched_entity *entity),
+	    TP_ARGS(job, entity),
 	    TP_STRUCT__entry(
 			     __field(uint64_t, sched_job_id)
-			     __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			     __string(timeline, AMDGPU_GET_SCHED_NAME(entity))
 			     __field(unsigned int, context)
 			     __field(unsigned int, seqno)
 			     __field(struct dma_fence *, fence)
@@ -175,7 +177,7 @@ TRACE_EVENT(amdgpu_cs_ioctl,
 
 	    TP_fast_assign(
 			   __entry->sched_job_id = job->base.id;
-			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			   __assign_str(timeline, AMDGPU_GET_SCHED_NAME(entity))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
 			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
-- 
2.7.4