Merge tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:
   - AMD adds some more upcoming HW platforms
   - Intel made Meteorlake stable and started adding Lunarlake
   - nouveau has a bunch of display rework in prepartion for the NVIDIA
     GSP firmware support
   - msm adds a7xx support
   - habanalabs has finished migration to accel subsystem

  Detail summary:

  kernel:
   - add initial vmemdup-user-array

  core:
   - fix platform remove() to return void
   - drm_file owner updated to reflect owner
   - move size calcs to drm buddy allocator
   - let GPUVM build as a module
   - allow variable number of run-queues in scheduler

  edid:
   - handle bad h/v sync_end in EDIDs

  panfrost:
   - add Boris as maintainer

  fbdev:
   - use fb_ops helpers more
   - only allow logo use from fbcon
   - rename fb_pgproto to pgprot_framebuffer
   - add HPD state to drm_connector_oob_hotplug_event
   - convert to fbdev i/o mem helpers

  i915:
   - Enable meteorlake by default
   - Early Xe2 LPD/Lunarlake display enablement
   - Rework subplatforms into IP version checks
   - GuC based TLB invalidation for Meteorlake
   - Display rework for future Xe driver integration
   - LNL FBC features
   - LNL display feature capability reads
   - update recommended fw versions for DG2+
   - drop fastboot module parameter
   - added deviceid for Arrowlake-S
   - drop preproduction workarounds
   - don't disable preemption for resets
   - cleanup inlines in headers
   - PXP firmware loading fix
   - Fix sg list lengths
   - DSC PPS state readout/verification
   - Add more RPL P/U PCI IDs
   - Add new DG2-G12 stepping
   - DP enhanced framing support to state checker
   - Improve shared link bandwidth management
   - stop using GEM macros in display code
   - refactor related code into display code
   - locally enable W=1 warnings
   - remove PSR watchdog timers on LNL

  amdgpu:
   - RAS/FRU EEPROM updatse
   - IP discovery updatses
   - GC 11.5 support
   - DCN 3.5 support
   - VPE 6.1 support
   - NBIO 7.11 support
   - DML2 support
   - lots of IP updates
   - use flexible arrays for bo list handling
   - W=1 fixes
   - Enable seamless boot in more cases
   - Enable context type property for HDMI
   - Rework GPUVM TLB flushing
   - VCN IB start/size alignment fixes

  amdkfd:
   - GC 10/11 fixes
   - GC 11.5 support
   - use partial migration in GPU faults

  radeon:
   - W=1 Fixes
   - fix some possible buffer overflow/NULL derefs

  nouveau:
   - update uapi for NO_PREFETCH
   - scheduler/fence fixes
   - rework suspend/resume for GSP-RM
   - rework display in preparation for GSP-RM

  habanalabs:
   - uapi: expose tsc clock
   - uapi: block access to eventfd through control device
   - uapi: force dma-buf export to PAGE_SIZE alignments
   - complete move to accel subsystem
   - move firmware interface include files
   - perform hard reset on PCIe AXI drain event
   - optimise user interrupt handling

  msm:
   - DP: use existing helpers for DPCD
   - DPU: interrupts reworked
   - gpu: a7xx (a730/a740) support
   - decouple msm_drv from kms for headless devices

  mediatek:
   - MT8188 dsi/dp/edp support
   - DDP GAMMA - 12 bit LUT support
   - connector dynamic selection capability

  rockchip:
   - rv1126 mipi-dsi/vop support
   - add planar formats

  ast:
   - rename constants

  panels:
   - Mitsubishi AA084XE01
   - JDI LPM102A188A
   - LTK050H3148W-CTA6

  ivpu:
   - power management fixes

  qaic:
   - add detach slice bo api

  komeda:
   - add NV12 writeback

  tegra:
   - support NVSYNC/NHSYNC
   - host1x suspend fixes

  ili9882t:
   - separate into own driver"

* tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm: (1803 commits)
  drm/amdgpu: Remove unused variables from amdgpu_show_fdinfo
  drm/amdgpu: Remove duplicate fdinfo fields
  drm/amd/amdgpu: avoid to disable gfxhub interrupt when driver is unloaded
  drm/amdgpu: Add EXT_COHERENT support for APU and NUMA systems
  drm/amdgpu: Retrieve CE count from ce_count_lo_chip in EccInfo table
  drm/amdgpu: Identify data parity error corrected in replay mode
  drm/amdgpu: Fix typo in IP discovery parsing
  drm/amd/display: fix S/G display enablement
  drm/amdxcp: fix amdxcp unloads incompletely
  drm/amd/amdgpu: fix the GPU power print error in pm info
  drm/amdgpu: Use pcie domain of xcc acpi objects
  drm/amd: check num of link levels when update pcie param
  drm/amdgpu: Add a read to GFX v9.4.3 ring test
  drm/amd/pm: call smu_cmn_get_smc_version in is_mode1_reset_supported.
  drm/amdgpu: get RAS poison status from DF v4_6_2
  drm/amdgpu: Use discovery table's subrevision
  drm/amd/display: 3.2.256
  drm/amd/display: add interface to query SubVP status
  drm/amd/display: Read before writing Backlight Mode Set Register
  drm/amd/display: Disable SYMCLK32_SE RCO on DCN314
  ...

1 files changed, 27 insertions, 2 deletions

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a8b4827dc425..ecd2e035147f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -159,6 +159,16 @@ panfrost_dequeue_job(struct panfrost_device *pfdev, int slot)
 	struct panfrost_job *job = pfdev->jobs[slot][0];
 
 	WARN_ON(!job);
+	if (job->is_profiled) {
+		if (job->engine_usage) {
+			job->engine_usage->elapsed_ns[slot] +=
+				ktime_to_ns(ktime_sub(ktime_get(), job->start_time));
+			job->engine_usage->cycles[slot] +=
+				panfrost_cycle_counter_read(pfdev) - job->start_cycles;
+		}
+		panfrost_cycle_counter_put(job->pfdev);
+	}
+
 	pfdev->jobs[slot][0] = pfdev->jobs[slot][1];
 	pfdev->jobs[slot][1] = NULL;
 
@@ -233,6 +243,13 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 	subslot = panfrost_enqueue_job(pfdev, js, job);
 	/* Don't queue the job if a reset is in progress */
 	if (!atomic_read(&pfdev->reset.pending)) {
+		if (atomic_read(&pfdev->profile_mode)) {
+			panfrost_cycle_counter_get(pfdev);
+			job->is_profiled = true;
+			job->start_time = ktime_get();
+			job->start_cycles = panfrost_cycle_counter_read(pfdev);
+		}
+
 		job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START);
 		dev_dbg(pfdev->dev,
 			"JS: Submitting atom %p to js[%d][%d] with head=0x%llx AS %d",
@@ -660,10 +677,14 @@ panfrost_reset(struct panfrost_device *pfdev,
 	 * stuck jobs. Let's make sure the PM counters stay balanced by
 	 * manually calling pm_runtime_put_noidle() and
 	 * panfrost_devfreq_record_idle() for each stuck job.
+	 * Let's also make sure the cycle counting register's refcnt is
+	 * kept balanced to prevent it from running forever
 	 */
 	spin_lock(&pfdev->js->job_lock);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
 		for (j = 0; j < ARRAY_SIZE(pfdev->jobs[0]) && pfdev->jobs[i][j]; j++) {
+			if (pfdev->jobs[i][j]->is_profiled)
+				panfrost_cycle_counter_put(pfdev->jobs[i][j]->pfdev);
 			pm_runtime_put_noidle(pfdev->dev);
 			panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
 		}
@@ -810,8 +831,8 @@ int panfrost_job_init(struct panfrost_device *pfdev)
 	spin_lock_init(&js->job_lock);
 
 	js->irq = platform_get_irq_byname(to_platform_device(pfdev->dev), "job");
-	if (js->irq <= 0)
-		return -ENODEV;
+	if (js->irq < 0)
+		return js->irq;
 
 	ret = devm_request_threaded_irq(pfdev->dev, js->irq,
 					panfrost_job_irq_handler,
@@ -832,6 +853,7 @@ int panfrost_job_init(struct panfrost_device *pfdev)
 
 		ret = drm_sched_init(&js->queue[j].sched,
 				     &panfrost_sched_ops,
+				     DRM_SCHED_PRIORITY_COUNT,
 				     nentries, 0,
 				     msecs_to_jiffies(JOB_TIMEOUT_MS),
 				     pfdev->reset.wq,
@@ -926,6 +948,9 @@ void panfrost_job_close(struct panfrost_file_priv *panfrost_priv)
 			}
 
 			job_write(pfdev, JS_COMMAND(i), cmd);
+
+			/* Jobs can outlive their file context */
+			job->engine_usage = NULL;
 		}
 	}
 	spin_unlock(&pfdev->js->job_lock);