Merge tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:

   - Core DRM had a lot of refactoring around managed drm resources to
     make drivers simpler.

   - Intel Tigerlake support is on by default

   - amdgpu now support p2p PCI buffer sharing and encrypted GPU memory

  Details:

  core:
   - uapi: error out EBUSY when existing master
   - uapi: rework SET/DROP MASTER permission handling
   - remove drm_pci.h
   - drm_pci* are now legacy
   - introduced managed DRM resources
   - subclassing support for drm_framebuffer
   - simple encoder helper
   - edid improvements
   - vblank + writeback documentation improved
   - drm/mm - optimise tree searches
   - port drivers to use devm_drm_dev_alloc

  dma-buf:
   - add flag for p2p buffer support

  mst:
   - ACT timeout improvements
   - remove drm_dp_mst_has_audio
   - don't use 2nd TX slot - spec recommends against it

  bridge:
   - dw-hdmi various improvements
   - chrontel ch7033 support
   - fix stack issues with old gcc

  hdmi:
   - add unpack function for drm infoframe

  fbdev:
   - misc fbdev driver fixes

  i915:
   - uapi: global sseu pinning
   - uapi: OA buffer polling
   - uapi: remove generated perf code
   - uapi: per-engine default property values in sysfs
   - Tigerlake GEN12 enabled.
   - Lots of gem refactoring
   - Tigerlake enablement patches
   - move to drm_device logging
   - Icelake gamma HW readout
   - push MST link retrain to hotplug work
   - bandwidth atomic helpers
   - ICL fixes
   - RPS/GT refactoring
   - Cherryview full-ppgtt support
   - i915 locking guidelines documented
   - require linear fb stride to be 512 multiple on gen9
   - Tigerlake SAGV support

  amdgpu:
   - uapi: encrypted GPU memory handling
   - uapi: add MEM_SYNC IB flag
   - p2p dma-buf support
   - export VRAM dma-bufs
   - FRU chip access support
   - RAS/SR-IOV updates
   - Powerplay locking fixes
   - VCN DPG (powergating) enablement
   - GFX10 clockgating fixes
   - DC fixes
   - GPU reset fixes
   - navi SDMA fix
   - expose FP16 for modesetting
   - DP 1.4 compliance fixes
   - gfx10 soft recovery
   - Improved Critical Thermal Faults handling
   - resizable BAR on gmc10

  amdkfd:
   - uapi: GWS resource management
   - track GPU memory per process
   - report PCI domain in topology

  radeon:
   - safe reg list generator fixes

  nouveau:
   - HD audio fixes on recent systems
   - vGPU detection (fail probe if we're on one, for now)
   - Interlaced mode fixes (mostly avoidance on Turing, which doesn't support it)
   - SVM improvements/fixes
   - NVIDIA format modifier support
   - Misc other fixes.

  adv7511:
   - HDMI SPDIF support

  ast:
   - allocate crtc state size
   - fix double assignment
   - fix suspend

  bochs:
   - drop connector register

  cirrus:
   - move to tiny drivers.

  exynos:
   - fix imported dma-buf mapping
   - enable runtime PM
   - fixes and cleanups

  mediatek:
   - DPI pin mode swap
   - config mipi_tx current/impedance

  lima:
   - devfreq + cooling device support
   - task handling improvements
   - runtime PM support

  pl111:
   - vexpress init improvements
   - fix module auto-load

  rcar-du:
   - DT bindings conversion to YAML
   - Planes zpos sanity check and fix
   - MAINTAINERS entry for LVDS panel driver

  mcde:
   - fix return value

  mgag200:
   - use managed config init

  stm:
   - read endpoints from DT

  vboxvideo:
   - use PCI managed functions
   - drop WC mtrr

  vkms:
   - enable cursor by default

  rockchip:
   - afbc support

  virtio:
   - various cleanups

  qxl:
   - fix cursor notify port

  hisilicon:
   - 128-byte stride alignment fix

  sun4i:
   - improved format handling"

* tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drm: (1401 commits)
  drm/amd/display: Fix potential integer wraparound resulting in a hang
  drm/amd/display: drop cursor position check in atomic test
  drm/amdgpu: fix device attribute node create failed with multi gpu
  drm/nouveau: use correct conflicting framebuffer API
  drm/vblank: Fix -Wformat compile warnings on some arches
  drm/amdgpu: Sync with VM root BO when switching VM to CPU update mode
  drm/amd/display: Handle GPU reset for DC block
  drm/amdgpu: add apu flags (v2)
  drm/amd/powerpay: Disable gfxoff when setting manual mode on picasso and raven
  drm/amdgpu: fix pm sysfs node handling (v2)
  drm/amdgpu: move gpu_info parsing after common early init
  drm/amdgpu: move discovery gfx config fetching
  drm/nouveau/dispnv50: fix runtime pm imbalance on error
  drm/nouveau: fix runtime pm imbalance on error
  drm/nouveau: fix runtime pm imbalance on error
  drm/nouveau/debugfs: fix runtime pm imbalance on error
  drm/nouveau/nouveau/hmm: fix migrate zero page to GPU
  drm/nouveau/nouveau/hmm: fix nouveau_dmem_chunk allocations
  drm/nouveau/kms/nv50-: Share DP SST mode_valid() handling with MST
  drm/nouveau/kms/nv50-: Move 8BPC limit for MST into nv50_mstc_get_modes()
  ...

1 files changed, 602 insertions, 21 deletions

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index f89d9c42f1fa..6014e8dfcbb1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -23,11 +23,13 @@
  */
 
 #include <linux/prime_numbers.h>
+#include <linux/pm_qos.h>
 
 #include "gem/i915_gem_pm.h"
 #include "gem/selftests/mock_context.h"
 
 #include "gt/intel_engine_pm.h"
+#include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 
 #include "i915_random.h"
@@ -51,6 +53,11 @@ static unsigned int num_uabi_engines(struct drm_i915_private *i915)
 	return count;
 }
 
+static struct intel_engine_cs *rcs0(struct drm_i915_private *i915)
+{
+	return intel_engine_lookup_user(i915, I915_ENGINE_CLASS_RENDER, 0);
+}
+
 static int igt_add_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -58,7 +65,7 @@ static int igt_add_request(void *arg)
 
 	/* Basic preliminary test to create a request and let it loose! */
 
-	request = mock_request(i915->engine[RCS0]->kernel_context, HZ / 10);
+	request = mock_request(rcs0(i915)->kernel_context, HZ / 10);
 	if (!request)
 		return -ENOMEM;
 
@@ -76,7 +83,7 @@ static int igt_wait_request(void *arg)
 
 	/* Submit a request, then wait upon it */
 
-	request = mock_request(i915->engine[RCS0]->kernel_context, T);
+	request = mock_request(rcs0(i915)->kernel_context, T);
 	if (!request)
 		return -ENOMEM;
 
@@ -145,7 +152,7 @@ static int igt_fence_wait(void *arg)
 
 	/* Submit a request, treat it as a fence and wait upon it */
 
-	request = mock_request(i915->engine[RCS0]->kernel_context, T);
+	request = mock_request(rcs0(i915)->kernel_context, T);
 	if (!request)
 		return -ENOMEM;
 
@@ -420,7 +427,7 @@ static int mock_breadcrumbs_smoketest(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct smoketest t = {
-		.engine = i915->engine[RCS0],
+		.engine = rcs0(i915),
 		.ncontexts = 1024,
 		.max_batch = 1024,
 		.request_alloc = __mock_request_alloc
@@ -809,10 +816,12 @@ static int recursive_batch_resolve(struct i915_vma *batch)
 		return PTR_ERR(cmd);
 
 	*cmd = MI_BATCH_BUFFER_END;
-	intel_gt_chipset_flush(batch->vm->gt);
 
+	__i915_gem_object_flush_map(batch->obj, 0, sizeof(*cmd));
 	i915_gem_object_unpin_map(batch->obj);
 
+	intel_gt_chipset_flush(batch->vm->gt);
+
 	return 0;
 }
 
@@ -858,13 +867,6 @@ static int live_all_engines(void *arg)
 			goto out_request;
 		}
 
-		err = engine->emit_bb_start(request[idx],
-					    batch->node.start,
-					    batch->node.size,
-					    0);
-		GEM_BUG_ON(err);
-		request[idx]->batch = batch;
-
 		i915_vma_lock(batch);
 		err = i915_request_await_object(request[idx], batch->obj, 0);
 		if (err == 0)
@@ -872,6 +874,13 @@ static int live_all_engines(void *arg)
 		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
+		err = engine->emit_bb_start(request[idx],
+					    batch->node.start,
+					    batch->node.size,
+					    0);
+		GEM_BUG_ON(err);
+		request[idx]->batch = batch;
+
 		i915_request_get(request[idx]);
 		i915_request_add(request[idx]);
 		idx++;
@@ -986,13 +995,6 @@ static int live_sequential_engines(void *arg)
 			}
 		}
 
-		err = engine->emit_bb_start(request[idx],
-					    batch->node.start,
-					    batch->node.size,
-					    0);
-		GEM_BUG_ON(err);
-		request[idx]->batch = batch;
-
 		i915_vma_lock(batch);
 		err = i915_request_await_object(request[idx],
 						batch->obj, false);
@@ -1001,6 +1003,13 @@ static int live_sequential_engines(void *arg)
 		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
+		err = engine->emit_bb_start(request[idx],
+					    batch->node.start,
+					    batch->node.size,
+					    0);
+		GEM_BUG_ON(err);
+		request[idx]->batch = batch;
+
 		i915_request_get(request[idx]);
 		i915_request_add(request[idx]);
 
@@ -1053,9 +1062,12 @@ out_request:
 					      I915_MAP_WC);
 		if (!IS_ERR(cmd)) {
 			*cmd = MI_BATCH_BUFFER_END;
-			intel_gt_chipset_flush(engine->gt);
 
+			__i915_gem_object_flush_map(request[idx]->batch->obj,
+						    0, sizeof(*cmd));
 			i915_gem_object_unpin_map(request[idx]->batch->obj);
+
+			intel_gt_chipset_flush(engine->gt);
 		}
 
 		i915_vma_put(request[idx]->batch);
@@ -1233,7 +1245,7 @@ static int live_parallel_engines(void *arg)
 		struct igt_live_test t;
 		unsigned int idx;
 
-		snprintf(name, sizeof(name), "%pS", fn);
+		snprintf(name, sizeof(name), "%ps", *fn);
 		err = igt_live_test_begin(&t, i915, __func__, name);
 		if (err)
 			break;
@@ -1470,3 +1482,572 @@ int i915_request_live_selftests(struct drm_i915_private *i915)
 
 	return i915_subtests(tests, i915);
 }
+
+static int switch_to_kernel_sync(struct intel_context *ce, int err)
+{
+	struct i915_request *rq;
+	struct dma_fence *fence;
+
+	rq = intel_engine_create_kernel_request(ce->engine);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	fence = i915_active_fence_get(&ce->timeline->last_request);
+	if (fence) {
+		i915_request_await_dma_fence(rq, fence);
+		dma_fence_put(fence);
+	}
+
+	rq = i915_request_get(rq);
+	i915_request_add(rq);
+	if (i915_request_wait(rq, 0, HZ / 2) < 0 && !err)
+		err = -ETIME;
+	i915_request_put(rq);
+
+	while (!err && !intel_engine_is_idle(ce->engine))
+		intel_engine_flush_submission(ce->engine);
+
+	return err;
+}
+
+struct perf_stats {
+	struct intel_engine_cs *engine;
+	unsigned long count;
+	ktime_t time;
+	ktime_t busy;
+	u64 runtime;
+};
+
+struct perf_series {
+	struct drm_i915_private *i915;
+	unsigned int nengines;
+	struct intel_context *ce[];
+};
+
+static int s_sync0(void *arg)
+{
+	struct perf_series *ps = arg;
+	IGT_TIMEOUT(end_time);
+	unsigned int idx = 0;
+	int err = 0;
+
+	GEM_BUG_ON(!ps->nengines);
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ps->ce[idx]);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (i915_request_wait(rq, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(rq);
+		if (err)
+			break;
+
+		if (++idx == ps->nengines)
+			idx = 0;
+	} while (!__igt_timeout(end_time, NULL));
+
+	return err;
+}
+
+static int s_sync1(void *arg)
+{
+	struct perf_series *ps = arg;
+	struct i915_request *prev = NULL;
+	IGT_TIMEOUT(end_time);
+	unsigned int idx = 0;
+	int err = 0;
+
+	GEM_BUG_ON(!ps->nengines);
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ps->ce[idx]);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (prev && i915_request_wait(prev, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(prev);
+		prev = rq;
+		if (err)
+			break;
+
+		if (++idx == ps->nengines)
+			idx = 0;
+	} while (!__igt_timeout(end_time, NULL));
+	i915_request_put(prev);
+
+	return err;
+}
+
+static int s_many(void *arg)
+{
+	struct perf_series *ps = arg;
+	IGT_TIMEOUT(end_time);
+	unsigned int idx = 0;
+
+	GEM_BUG_ON(!ps->nengines);
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ps->ce[idx]);
+		if (IS_ERR(rq))
+			return PTR_ERR(rq);
+
+		i915_request_add(rq);
+
+		if (++idx == ps->nengines)
+			idx = 0;
+	} while (!__igt_timeout(end_time, NULL));
+
+	return 0;
+}
+
+static int perf_series_engines(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	static int (* const func[])(void *arg) = {
+		s_sync0,
+		s_sync1,
+		s_many,
+		NULL,
+	};
+	const unsigned int nengines = num_uabi_engines(i915);
+	struct intel_engine_cs *engine;
+	int (* const *fn)(void *arg);
+	struct pm_qos_request qos;
+	struct perf_stats *stats;
+	struct perf_series *ps;
+	unsigned int idx;
+	int err = 0;
+
+	stats = kcalloc(nengines, sizeof(*stats), GFP_KERNEL);
+	if (!stats)
+		return -ENOMEM;
+
+	ps = kzalloc(struct_size(ps, ce, nengines), GFP_KERNEL);
+	if (!ps) {
+		kfree(stats);
+		return -ENOMEM;
+	}
+
+	cpu_latency_qos_add_request(&qos, 0); /* disable cstates */
+
+	ps->i915 = i915;
+	ps->nengines = nengines;
+
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
+		struct intel_context *ce;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce))
+			goto out;
+
+		err = intel_context_pin(ce);
+		if (err) {
+			intel_context_put(ce);
+			goto out;
+		}
+
+		ps->ce[idx++] = ce;
+	}
+	GEM_BUG_ON(idx != ps->nengines);
+
+	for (fn = func; *fn && !err; fn++) {
+		char name[KSYM_NAME_LEN];
+		struct igt_live_test t;
+
+		snprintf(name, sizeof(name), "%ps", *fn);
+		err = igt_live_test_begin(&t, i915, __func__, name);
+		if (err)
+			break;
+
+		for (idx = 0; idx < nengines; idx++) {
+			struct perf_stats *p =
+				memset(&stats[idx], 0, sizeof(stats[idx]));
+			struct intel_context *ce = ps->ce[idx];
+
+			p->engine = ps->ce[idx]->engine;
+			intel_engine_pm_get(p->engine);
+
+			if (intel_engine_supports_stats(p->engine))
+				p->busy = intel_engine_get_busy_time(p->engine) + 1;
+			p->runtime = -intel_context_get_total_runtime_ns(ce);
+			p->time = ktime_get();
+		}
+
+		err = (*fn)(ps);
+		if (igt_live_test_end(&t))
+			err = -EIO;
+
+		for (idx = 0; idx < nengines; idx++) {
+			struct perf_stats *p = &stats[idx];
+			struct intel_context *ce = ps->ce[idx];
+			int integer, decimal;
+			u64 busy, dt;
+
+			p->time = ktime_sub(ktime_get(), p->time);
+			if (p->busy) {
+				p->busy = ktime_sub(intel_engine_get_busy_time(p->engine),
+						    p->busy - 1);
+			}
+
+			err = switch_to_kernel_sync(ce, err);
+			p->runtime += intel_context_get_total_runtime_ns(ce);
+			intel_engine_pm_put(p->engine);
+
+			busy = 100 * ktime_to_ns(p->busy);
+			dt = ktime_to_ns(p->time);
+			if (dt) {
+				integer = div64_u64(busy, dt);
+				busy -= integer * dt;
+				decimal = div64_u64(100 * busy, dt);
+			} else {
+				integer = 0;
+				decimal = 0;
+			}
+
+			pr_info("%s %5s: { seqno:%d, busy:%d.%02d%%, runtime:%lldms, walltime:%lldms }\n",
+				name, p->engine->name, ce->timeline->seqno,
+				integer, decimal,
+				div_u64(p->runtime, 1000 * 1000),
+				div_u64(ktime_to_ns(p->time), 1000 * 1000));
+		}
+	}
+
+out:
+	for (idx = 0; idx < nengines; idx++) {
+		if (IS_ERR_OR_NULL(ps->ce[idx]))
+			break;
+
+		intel_context_unpin(ps->ce[idx]);
+		intel_context_put(ps->ce[idx]);
+	}
+	kfree(ps);
+
+	cpu_latency_qos_remove_request(&qos);
+	kfree(stats);
+	return err;
+}
+
+static int p_sync0(void *arg)
+{
+	struct perf_stats *p = arg;
+	struct intel_engine_cs *engine = p->engine;
+	struct intel_context *ce;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+	bool busy;
+	int err = 0;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	err = intel_context_pin(ce);
+	if (err) {
+		intel_context_put(ce);
+		return err;
+	}
+
+	busy = false;
+	if (intel_engine_supports_stats(engine)) {
+		p->busy = intel_engine_get_busy_time(engine);
+		busy = true;
+	}
+
+	p->time = ktime_get();
+	count = 0;
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		err = 0;
+		if (i915_request_wait(rq, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(rq);
+		if (err)
+			break;
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+	p->time = ktime_sub(ktime_get(), p->time);
+
+	if (busy) {
+		p->busy = ktime_sub(intel_engine_get_busy_time(engine),
+				    p->busy);
+	}
+
+	err = switch_to_kernel_sync(ce, err);
+	p->runtime = intel_context_get_total_runtime_ns(ce);
+	p->count = count;
+
+	intel_context_unpin(ce);
+	intel_context_put(ce);
+	return err;
+}
+
+static int p_sync1(void *arg)
+{
+	struct perf_stats *p = arg;
+	struct intel_engine_cs *engine = p->engine;
+	struct i915_request *prev = NULL;
+	struct intel_context *ce;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+	bool busy;
+	int err = 0;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	err = intel_context_pin(ce);
+	if (err) {
+		intel_context_put(ce);
+		return err;
+	}
+
+	busy = false;
+	if (intel_engine_supports_stats(engine)) {
+		p->busy = intel_engine_get_busy_time(engine);
+		busy = true;
+	}
+
+	p->time = ktime_get();
+	count = 0;
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		err = 0;
+		if (prev && i915_request_wait(prev, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(prev);
+		prev = rq;
+		if (err)
+			break;
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+	i915_request_put(prev);
+	p->time = ktime_sub(ktime_get(), p->time);
+
+	if (busy) {
+		p->busy = ktime_sub(intel_engine_get_busy_time(engine),
+				    p->busy);
+	}
+
+	err = switch_to_kernel_sync(ce, err);
+	p->runtime = intel_context_get_total_runtime_ns(ce);
+	p->count = count;
+
+	intel_context_unpin(ce);
+	intel_context_put(ce);
+	return err;
+}
+
+static int p_many(void *arg)
+{
+	struct perf_stats *p = arg;
+	struct intel_engine_cs *engine = p->engine;
+	struct intel_context *ce;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+	int err = 0;
+	bool busy;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	err = intel_context_pin(ce);
+	if (err) {
+		intel_context_put(ce);
+		return err;
+	}
+
+	busy = false;
+	if (intel_engine_supports_stats(engine)) {
+		p->busy = intel_engine_get_busy_time(engine);
+		busy = true;
+	}
+
+	count = 0;
+	p->time = ktime_get();
+	do {
+		struct i915_request *rq;
+
+		rq = i915_request_create(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_add(rq);
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+	p->time = ktime_sub(ktime_get(), p->time);
+
+	if (busy) {
+		p->busy = ktime_sub(intel_engine_get_busy_time(engine),
+				    p->busy);
+	}
+
+	err = switch_to_kernel_sync(ce, err);
+	p->runtime = intel_context_get_total_runtime_ns(ce);
+	p->count = count;
+
+	intel_context_unpin(ce);
+	intel_context_put(ce);
+	return err;
+}
+
+static int perf_parallel_engines(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	static int (* const func[])(void *arg) = {
+		p_sync0,
+		p_sync1,
+		p_many,
+		NULL,
+	};
+	const unsigned int nengines = num_uabi_engines(i915);
+	struct intel_engine_cs *engine;
+	int (* const *fn)(void *arg);
+	struct pm_qos_request qos;
+	struct {
+		struct perf_stats p;
+		struct task_struct *tsk;
+	} *engines;
+	int err = 0;
+
+	engines = kcalloc(nengines, sizeof(*engines), GFP_KERNEL);
+	if (!engines)
+		return -ENOMEM;
+
+	cpu_latency_qos_add_request(&qos, 0);
+
+	for (fn = func; *fn; fn++) {
+		char name[KSYM_NAME_LEN];
+		struct igt_live_test t;
+		unsigned int idx;
+
+		snprintf(name, sizeof(name), "%ps", *fn);
+		err = igt_live_test_begin(&t, i915, __func__, name);
+		if (err)
+			break;
+
+		atomic_set(&i915->selftest.counter, nengines);
+
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
+			intel_engine_pm_get(engine);
+
+			memset(&engines[idx].p, 0, sizeof(engines[idx].p));
+			engines[idx].p.engine = engine;
+
+			engines[idx].tsk = kthread_run(*fn, &engines[idx].p,
+						       "igt:%s", engine->name);
+			if (IS_ERR(engines[idx].tsk)) {
+				err = PTR_ERR(engines[idx].tsk);
+				intel_engine_pm_put(engine);
+				break;
+			}
+			get_task_struct(engines[idx++].tsk);
+		}
+
+		yield(); /* start all threads before we kthread_stop() */
+
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
+			int status;
+
+			if (IS_ERR(engines[idx].tsk))
+				break;
+
+			status = kthread_stop(engines[idx].tsk);
+			if (status && !err)
+				err = status;
+
+			intel_engine_pm_put(engine);
+			put_task_struct(engines[idx++].tsk);
+		}
+
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		if (err)
+			break;
+
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
+			struct perf_stats *p = &engines[idx].p;
+			u64 busy = 100 * ktime_to_ns(p->busy);
+			u64 dt = ktime_to_ns(p->time);
+			int integer, decimal;
+
+			if (dt) {
+				integer = div64_u64(busy, dt);
+				busy -= integer * dt;
+				decimal = div64_u64(100 * busy, dt);
+			} else {
+				integer = 0;
+				decimal = 0;
+			}
+
+			GEM_BUG_ON(engine != p->engine);
+			pr_info("%s %5s: { count:%lu, busy:%d.%02d%%, runtime:%lldms, walltime:%lldms }\n",
+				name, engine->name, p->count, integer, decimal,
+				div_u64(p->runtime, 1000 * 1000),
+				div_u64(ktime_to_ns(p->time), 1000 * 1000));
+			idx++;
+		}
+	}
+
+	cpu_latency_qos_remove_request(&qos);
+	kfree(engines);
+	return err;
+}
+
+int i915_request_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_series_engines),
+		SUBTEST(perf_parallel_engines),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_subtests(tests, i915);
+}