Merge tag 'drm-intel-gt-next-2021-01-14' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:
- Deprecate I915_PMU_LAST and optimize state tracking (Tvrtko)

  Avoid relying on last item ABI marker in i915_drm.h, add a
  comment to mark as deprecated.

Cross-subsystem Changes:

Core Changes:

Driver Changes:

- Restore clear residuals security mitigations for Ivybridge and
  Baytrail (Chris)
- Close #1858: Allow sysadmin to choose applied GPU security mitigations
  through i915.mitigations=... similar to CPU (Chris)
- Fix for #2024: GPU hangs on HSW GT1 (Chris)
- Fix for #2707: Driver hang when editing UVs in Blender (Chris, Ville)
- Fix for #2797: False positive GuC loading error message (Chris)
- Fix for #2859: Missing GuC firmware for older Cometlakes (Chris)
- Lessen probability of GPU hang due to DMAR faults [reason 7,
  next page table ptr is invalid] on Tigerlake (Chris)
- Fix REVID macros for TGL to fetch correct stepping (Aditya)
- Limit frequency drop to RPe on parking (Chris, Edward)
- Limit W/A 1406941453 to TGL, RKL and DG1 (Swathi)
- Make W/A 22010271021 permanent on DG1 (Lucas)
- Implement W/A 16011163337 to prevent a HS/DS hang on DG1 (Swathi)
- Only disable preemption on gen8 render engines (Chris)
- Disable arbitration around Braswell's PDP updates (Chris)
- Disable arbitration on no-preempt requests (Chris)
- Check for arbitration after writing start seqno before busywaiting (Chris)
- Retain default context state across shrinking (Venkata, CQ)
- Fix mismatch between misplaced vma check and vma insert for 32-bit
  addressing userspaces (Chris, CQ)
- Propagate error for vmap() failure instead kernel NULL deref (Chris)
- Propagate error from cancelled submit due to context closure
  immediately (Chris)
- Fix RCU race on HWSP tracking per request (Chris)
- Clear CMD parser shadow and GPU reloc batches (Matt A)

- Populate logical context during first pin (Maarten)
- Optimistically prune dma-resv from the shrinker (Chris)
- Fix for virtual engine ownership race (Chris)
- Remove timeslice suppression to restore fairness for virtual engines (Chris)
- Rearrange IVB/HSW workarounds properly between GT and engine (Chris)
- Taint the reset mutex with the shrinker (Chris)
- Replace direct submit with direct call to tasklet (Chris)
- Multiple corrections to virtual engine dequeue and breadcrumbs code (Chris)
- Avoid wakeref from potentially hard IRQ context in PMU (Tvrtko)
- Use raw clock for RC6 time estimation in PMU (Tvrtko)
- Differentiate OOM failures from invalid map types (Chris)
- Fix Gen9 to have 64 MOCS entries similar to Gen11 (Chris)
- Ignore repeated attempts to suspend request flow across reset (Chris)
- Remove livelock from "do_idle_maps" VT-d W/A (Chris)
- Cancel the preemption timeout early in case engine reset fails (Chris)
- Code flow optimization in the scheduling code (Chris)
- Clear the execlists timers upon reset (Chris)
- Drain the breadcrumbs just once (Chris, Matt A)
- Track the overall GT awake/busy time (Chris)
- Tweak submission tasklet flushing to avoid starvation (Chris)
- Track timelines created using the HWSP to restore on resume (Chris)
- Use cmpxchg64 for 32b compatilibity for active tracking (Chris)
- Prefer recycling an idle GGTT fence to avoid GPU wait (Chris)

- Restructure GT code organization for clearer split between GuC
  and execlists (Chris, Daniele, John, Matt A)
- Remove GuC code that will remain unused by new interfaces (Matt B)
- Restructure the CS timestamp clocks code to local to GT (Chris)
- Fix error return paths in perf code (Zhang)
- Replace idr_init() by idr_init_base() in perf (Deepak)
- Fix shmem_pin_map error path (Colin)
- Drop redundant free_work worker for GEM contexts (Chris, Mika)
- Increase readability and understandability of intel_workarounds.c (Lucas)
- Defer enabling the breadcrumb interrupt to after submission (Chris)
- Deal with buddy alloc block sizes beyond 4G (Venkata, Chris)
- Encode fence specific waitqueue behaviour into the wait.flags (Chris)
- Don't cancel the breadcrumb interrupt shadow too early (Chris)
- Cancel submitted requests upon context reset (Chris)
- Use correct locks in GuC code (Tvrtko)
- Prevent use of engine->wa_ctx after error (Chris, Matt R)

- Fix build warning on 32-bit (Arnd)
- Avoid memory leak if platform would have more than 16 W/A (Tvrtko)
- Avoid unnecessary #if CONFIG_PM in PMU code (Chris, Tvrtko)
- Improve debugging output (Chris, Tvrtko, Matt R)
- Make file local variables static (Jani)
- Avoid uint*_t types in i915 (Jani)
- Selftest improvements (Chris, Matt A, Dan)
- Documentation fixes (Chris, Jose)

Signed-off-by: Dave Airlie <airlied@redhat.com>

# Conflicts:
#	drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
#	drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
#	drivers/gpu/drm/i915/gt/intel_lrc.c
#	drivers/gpu/drm/i915/gvt/mmio_context.h
#	drivers/gpu/drm/i915/i915_drv.h
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210114152232.GA21588@jlahtine-mobl.ger.corp.intel.com

1 files changed, 22 insertions, 17 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a61e9b095896..de8e0e44cfb6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -45,6 +45,7 @@
 #include "i915_debugfs.h"
 #include "i915_debugfs_params.h"
 #include "i915_irq.h"
+#include "i915_scheduler.h"
 #include "i915_trace.h"
 #include "intel_pm.h"
 #include "intel_sideband.h"
@@ -634,27 +635,27 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
 		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
 		seq_printf(m, "CAGF: %dMHz\n", cagf);
-		seq_printf(m, "RP CUR UP EI: %d (%dns)\n",
+		seq_printf(m, "RP CUR UP EI: %d (%lldns)\n",
 			   rpupei,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpupei));
-		seq_printf(m, "RP CUR UP: %d (%dun)\n",
+		seq_printf(m, "RP CUR UP: %d (%lldun)\n",
 			   rpcurup,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpcurup));
-		seq_printf(m, "RP PREV UP: %d (%dns)\n",
+		seq_printf(m, "RP PREV UP: %d (%lldns)\n",
 			   rpprevup,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt, rpprevup));
 		seq_printf(m, "Up threshold: %d%%\n",
 			   rps->power.up_threshold);
 
-		seq_printf(m, "RP CUR DOWN EI: %d (%dns)\n",
+		seq_printf(m, "RP CUR DOWN EI: %d (%lldns)\n",
 			   rpdownei,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
 						      rpdownei));
-		seq_printf(m, "RP CUR DOWN: %d (%dns)\n",
+		seq_printf(m, "RP CUR DOWN: %d (%lldns)\n",
 			   rpcurdown,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
 						      rpcurdown));
-		seq_printf(m, "RP PREV DOWN: %d (%dns)\n",
+		seq_printf(m, "RP PREV DOWN: %d (%lldns)\n",
 			   rpprevdown,
 			   intel_gt_pm_interval_to_ns(&dev_priv->gt,
 						      rpprevdown));
@@ -810,7 +811,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 		   intel_gpu_freq(rps, rps->efficient_freq),
 		   intel_gpu_freq(rps, rps->boost_freq));
 
-	seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
+	seq_printf(m, "Wait boosts: %d\n", READ_ONCE(rps->boosts));
 
 	return 0;
 }
@@ -850,24 +851,28 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 
 static int i915_engine_info(struct seq_file *m, void *unused)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	struct drm_i915_private *i915 = node_to_i915(m->private);
 	struct intel_engine_cs *engine;
 	intel_wakeref_t wakeref;
 	struct drm_printer p;
 
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
-	seq_printf(m, "GT awake? %s [%d]\n",
-		   yesno(dev_priv->gt.awake),
-		   atomic_read(&dev_priv->gt.wakeref.count));
-	seq_printf(m, "CS timestamp frequency: %u Hz\n",
-		   RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_hz);
+	seq_printf(m, "GT awake? %s [%d], %llums\n",
+		   yesno(i915->gt.awake),
+		   atomic_read(&i915->gt.wakeref.count),
+		   ktime_to_ms(intel_gt_get_awake_time(&i915->gt)));
+	seq_printf(m, "CS timestamp frequency: %u Hz, %d ns\n",
+		   i915->gt.clock_frequency,
+		   i915->gt.clock_period_ns);
 
 	p = drm_seq_file_printer(m);
-	for_each_uabi_engine(engine, dev_priv)
+	for_each_uabi_engine(engine, i915)
 		intel_engine_dump(engine, &p, "%s\n", engine->name);
 
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
+	intel_gt_show_timelines(&i915->gt, &p, i915_request_show_with_schedule);
+
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
 	return 0;
 }
@@ -945,7 +950,7 @@ i915_perf_noa_delay_set(void *data, u64 val)
 	 * This would lead to infinite waits as we're doing timestamp
 	 * difference on the CS with only 32bits.
 	 */
-	if (i915_cs_timestamp_ns_to_ticks(i915, val) > U32_MAX)
+	if (intel_gt_ns_to_clock_interval(&i915->gt, val) > U32_MAX)
 		return -EINVAL;
 
 	atomic64_set(&i915->perf.noa_programming_delay, val);