Merge tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux

Pull drm u pdates from Dave Airlie:
 "This is the main drm pull request for v4.12. Apart from two fixes
  pulls, everything should have been in drm-next for at least 2 weeks.

  The biggest thing in here is AMD released the public headers for their
  upcoming VEGA GPUs. These as always are quite a sizeable chunk of
  header files. They've also added initial non-display support for those
  GPUs, though they aren't available in production yet.

  Otherwise it's pretty much normal.

  New bridge drivers:
   - megachips-stdpxxxx-ge-b850v3-fw LVDS->DP++
   - generic LVDS bridge support.

  Core:
   - Displayport link train failure reporting to userspace
   - debugfs interface cleaned up
   - subsystem TODO in kerneldoc now
   - Extended fbdev support (flipping and vblank wait)
   - drm_platform removed
   - EDP CRC support in helper
   - HF-VSDB SCDC support in EDID parser
   - Lots of code cleanups and header extraction
   - Thunderbolt external GPU awareness
   - Atomic helper improvements
   - Documentation improvements

  panel:
   - Sitronix and Samsung new panel support

  amdgpu:
   - Preliminary vega10 support
   - Multi-level page table support
   - GPU sensor support for userspace
   - PRT support for sparse buffers
   - SR-IOV improvements
   - Non-contig VRAM CPU mapping

  i915:
   - Atomic modesetting enabled by default on Gen5+
   - LSPCON improvements
   - Atomic state handling for cdclk
   - GPU reset improvements
   - In-kernel unit tests
   - Geminilake improvements and color manager support
   - Designware i2c fixes
   - vblank evasion improvements
   - Hotplug safe connector iterators
   - GVT scheduler QoS support
   - GVT Kabylake support

  nouveau:
   - Acceleration support for Pascal (GP10x).
   - Rearchitecture of code handling proprietary signed firmware
   - Fix GTX 970 with odd MMU configuration
   - GP10B support
   - GP107 acceleration support

  vmwgfx:
   - Atomic modesetting support for vmwgfx

  omapdrm:
   - Support for render nodes
   - Refactor omapdss code
   - Fix some probe ordering issues
   - Fix too dark RGB565 rendering

  sunxi:
   - prelim rework for multiple pipes.

  mali-dp:
   - Color management support
   - Plane scaling
   - Power management improvements

  imx-drm:
   - Prefetch Resolve Engine/Gasket on i.MX6QP
   - Deferred plane disabling
   - Separate alpha support

  mediatek:
   - Mediatek SoC MT2701 support

  rcar-du:
   - Gen3 HDMI support

  msm:
   - 4k support for newer chips
   - OPP bindings for gpu
   - prep work for per-process pagetables

  vc4:
   - HDMI audio support
   - fixes

  qxl:
   - minor fixes.

  dw-hdmi:
   - PHY improvements
   - CSC fixes
   - Amlogic GX SoC support"

* tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux: (1778 commits)
  drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection
  drm/nouveau/secboot/gm20b: fix the error return code in gm20b_secboot_tegra_read_wpr()
  drm/nouveau/kms: Increase max retries in scanout position queries.
  drm/nouveau/bios/bitP: check that table is long enough for optional pointers
  drm/nouveau/fifo/nv40: no ctxsw for pre-nv44 mpeg engine
  drm: mali-dp: use div_u64 for expensive 64-bit divisions
  drm/i915: Confirm the request is still active before adding it to the await
  drm/i915: Avoid busy-spinning on VLV_GLTC_PW_STATUS mmio
  drm/i915/selftests: Allocate inode/file dynamically
  drm/i915: Fix system hang with EI UP masked on Haswell
  drm/i915: checking for NULL instead of IS_ERR() in mock selftests
  drm/i915: Perform link quality check unconditionally during long pulse
  drm/i915: Fix use after free in lpe_audio_platdev_destroy()
  drm/i915: Use the right mapping_gfp_mask for final shmem allocation
  drm/i915: Make legacy cursor updates more unsynced
  drm/i915: Apply a cond_resched() to the saturated signaler
  drm/i915: Park the signaler before sleeping
  drm: mali-dp: Check the mclk rate and allow up/down scaling
  drm: mali-dp: Enable image enhancement when scaling
  drm: mali-dp: Add plane upscaling support
  ...

1 files changed, 74 insertions, 32 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index a18ae1e97860..ee9d0f346d75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -11,6 +11,9 @@
 #define TRACE_SYSTEM amdgpu
 #define TRACE_INCLUDE_FILE amdgpu_trace
 
+#define AMDGPU_JOB_GET_TIMELINE_NAME(job) \
+	 job->base.s_fence->finished.ops->get_timeline_name(&job->base.s_fence->finished)
+
 TRACE_EVENT(amdgpu_mm_rreg,
 	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
 	    TP_ARGS(did, reg, value),
@@ -49,6 +52,43 @@ TRACE_EVENT(amdgpu_mm_wreg,
 		      (unsigned long)__entry->value)
 );
 
+TRACE_EVENT(amdgpu_iv,
+	    TP_PROTO(struct amdgpu_iv_entry *iv),
+	    TP_ARGS(iv),
+	    TP_STRUCT__entry(
+			     __field(unsigned, client_id)
+			     __field(unsigned, src_id)
+			     __field(unsigned, ring_id)
+			     __field(unsigned, vm_id)
+			     __field(unsigned, vm_id_src)
+			     __field(uint64_t, timestamp)
+			     __field(unsigned, timestamp_src)
+			     __field(unsigned, pas_id)
+			     __array(unsigned, src_data, 4)
+			    ),
+	    TP_fast_assign(
+			   __entry->client_id = iv->client_id;
+			   __entry->src_id = iv->src_id;
+			   __entry->ring_id = iv->ring_id;
+			   __entry->vm_id = iv->vm_id;
+			   __entry->vm_id_src = iv->vm_id_src;
+			   __entry->timestamp = iv->timestamp;
+			   __entry->timestamp_src = iv->timestamp_src;
+			   __entry->pas_id = iv->pas_id;
+			   __entry->src_data[0] = iv->src_data[0];
+			   __entry->src_data[1] = iv->src_data[1];
+			   __entry->src_data[2] = iv->src_data[2];
+			   __entry->src_data[3] = iv->src_data[3];
+			   ),
+	    TP_printk("client_id:%u src_id:%u ring:%u vm_id:%u timestamp: %llu pas_id:%u src_data: %08x %08x %08x %08x\n",
+		      __entry->client_id, __entry->src_id,
+		      __entry->ring_id, __entry->vm_id,
+		      __entry->timestamp, __entry->pas_id,
+		      __entry->src_data[0], __entry->src_data[1],
+		      __entry->src_data[2], __entry->src_data[3])
+);
+
+
 TRACE_EVENT(amdgpu_bo_create,
 	    TP_PROTO(struct amdgpu_bo *bo),
 	    TP_ARGS(bo),
@@ -70,7 +110,7 @@ TRACE_EVENT(amdgpu_bo_create,
 			   __entry->visible = bo->flags;
 			   ),
 
-	    TP_printk("bo=%p,pages=%u,type=%d,prefered=%d,allowed=%d,visible=%d",
+	    TP_printk("bo=%p, pages=%u, type=%d, prefered=%d, allowed=%d, visible=%d",
 		       __entry->bo, __entry->pages, __entry->type,
 		       __entry->prefer, __entry->allow, __entry->visible)
 );
@@ -101,50 +141,51 @@ 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(uint64_t, sched_job_id)
+			     __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			     __field(unsigned int, context)
+			     __field(unsigned int, seqno)
 			     __field(struct dma_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->finished;
+			   __entry->sched_job_id = job->base.id;
+			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			   __entry->context = job->base.s_fence->finished.context;
+			   __entry->seqno = job->base.s_fence->finished.seqno;
 			   __entry->ring_name = job->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)
+	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
+		      __entry->sched_job_id, __get_str(timeline), __entry->context,
+		      __entry->seqno, __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 dma_fence *, fence)
+			     __field(uint64_t, sched_job_id)
+			     __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			     __field(unsigned int, context)
+			     __field(unsigned int, seqno)
 			     __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->finished;
+			   __entry->sched_job_id = job->base.id;
+			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
+			   __entry->context = job->base.s_fence->finished.context;
+			   __entry->seqno = job->base.s_fence->finished.seqno;
 			   __entry->ring_name = job->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)
+	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
+		      __entry->sched_job_id, __get_str(timeline), __entry->context,
+		      __entry->seqno, __entry->ring_name, __entry->num_ibs)
 );
 
 
@@ -184,9 +225,9 @@ TRACE_EVENT(amdgpu_vm_bo_map,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->bo = bo_va->bo;
-			   __entry->start = mapping->it.start;
-			   __entry->last = mapping->it.last;
+			   __entry->bo = bo_va ? bo_va->bo : NULL;
+			   __entry->start = mapping->start;
+			   __entry->last = mapping->last;
 			   __entry->offset = mapping->offset;
 			   __entry->flags = mapping->flags;
 			   ),
@@ -209,8 +250,8 @@ TRACE_EVENT(amdgpu_vm_bo_unmap,
 
 	    TP_fast_assign(
 			   __entry->bo = bo_va->bo;
-			   __entry->start = mapping->it.start;
-			   __entry->last = mapping->it.last;
+			   __entry->start = mapping->start;
+			   __entry->last = mapping->last;
 			   __entry->offset = mapping->offset;
 			   __entry->flags = mapping->flags;
 			   ),
@@ -229,8 +270,8 @@ DECLARE_EVENT_CLASS(amdgpu_vm_mapping,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->soffset = mapping->it.start;
-			   __entry->eoffset = mapping->it.last + 1;
+			   __entry->soffset = mapping->start;
+			   __entry->eoffset = mapping->last + 1;
 			   __entry->flags = mapping->flags;
 			   ),
 	    TP_printk("soffs=%010llx, eoffs=%010llx, flags=%08x",
@@ -321,7 +362,7 @@ TRACE_EVENT(amdgpu_bo_list_set,
 			   __entry->bo = bo;
 			   __entry->bo_size = amdgpu_bo_size(bo);
 			   ),
-	    TP_printk("list=%p, bo=%p, bo_size = %Ld",
+	    TP_printk("list=%p, bo=%p, bo_size=%Ld",
 		      __entry->list,
 		      __entry->bo,
 		      __entry->bo_size)
@@ -339,7 +380,7 @@ TRACE_EVENT(amdgpu_cs_bo_status,
 			__entry->total_bo = total_bo;
 			__entry->total_size = total_size;
 			),
-	    TP_printk("total bo size = %Ld, total bo count = %Ld",
+	    TP_printk("total_bo_size=%Ld, total_bo_count=%Ld",
 			__entry->total_bo, __entry->total_size)
 );
 
@@ -359,11 +400,12 @@ TRACE_EVENT(amdgpu_ttm_bo_move,
 			__entry->new_placement = new_placement;
 			__entry->old_placement = old_placement;
 			),
-	    TP_printk("bo=%p from:%d to %d with size = %Ld",
+	    TP_printk("bo=%p, from=%d, to=%d, size=%Ld",
 			__entry->bo, __entry->old_placement,
 			__entry->new_placement, __entry->bo_size)
 );
 
+#undef AMDGPU_JOB_GET_TIMELINE_NAME
 #endif
 
 /* This part must be outside protection */