Merge tag 'drm-intel-gt-next-2020-11-12-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Cross-subsystem Changes:
- DMA mapped scatterlist fixes in i915 to unblock merging of
  https://lkml.org/lkml/2020/9/27/70 (Tvrtko, Tom)

Driver Changes:

- Fix for user reported issue #2381 (Graphical output stops with "switching to inteldrmfb from simple"):
  Mark ininitial fb obj as WT on eLLC machines to avoid rcu lockup during fbdev init (Ville, Chris)
- Fix for Tigerlake (and earlier) to avoid spurious empty CSB events leading to hang (Chris, Bruce)
- Delay execlist processing for Tigerlake to avoid hang (Chris)
- Fix for Tigerlake RCS engine health check through heartbeat (Chris)
- Fix for Tigerlake reserved MOCS entries (Ayaz, Chris)
- Fix Media power gate sequence on Tigerlake (Rodrigo)
- Enable eLLC caching of display buffers for SKL+ (Ville)
- Support parsing of oversize batches on Gen9 (Matt, Chris)
- Exclude low pages (128KiB) of stolen from use to avoid thrashing during reset (Chris)
- Flush engines before Tigerlake breadcrumbs (Chris)

- Use the local HWSP offset during submission (Chris)
- Flush coherency domains on first set-domain-ioctl (Chris, Zbigniew)
- Use the active reference on the vma while capturing to avoid use-after-free (Chris)
- Fix MOCS PTE setting for gen9+ (Ville)
- Avoid NULL dereference on IPS driver callback while unbinding i915 (Chris)
- Avoid NULL dereference from PT/PD stash allocation error (Matt)
- Hold request reference for canceling an active context (Chris)
- Avoid infinite loop on x86-32 when mapping a lot of objects (Chris)
- Disallow WC mappings when processor doesn't support them (Chris)
- Return correct error in i915_gem_object_copy_blt() error path (Dan)
- Return correct error in intel_context_create_request() error path (Maarten)
- Tune down GuC communication enabled/disabled messages to debug (Jani)
- Fix rebased commit "Remove i915_request.lock requirement for execution callbacks" (Chris)
- Cancel outstanding work after disabling heartbeats on an engine (Chris)
- Signal cancelled requests (Chris)
- Retire cancelled requests on unload (Chris)
- Scrub HW state on driver remove (Chris)
- Undo forced context restores after trivial preemptions (Chris)
- Handle PCI unbind in PMU code (Tvrtko)
- Fix CPU hotplug with multiple GPUs in PMU code (Trtkko)
- Correctly set SFC capability for video engines (Venkata)

- Update GuC code to use firmware v49.0.1 (John, Matthew B., Daniele, Oscar, Michel, Rodrigo, Michal)
- Improve GuC warnings on loading failure (John)
- Avoid ownership race in buffer pool by clearing age (Chris)
- Use MMIO to read CSB in case of failure (Chris, Mika)
- Show engine properties in engine state dump to indicate changes (Chris, Joonas)
- Break up error capture compression loops with cond_resched() (Chris)
- Reduce GPU error capture mutex hold time to avoid khungtaskd (Chris)
- Serialise debugfs i915_gem_objects with ctx->mutex (Chris)
- Always test execution status on closing the context and close if not persistent (Chris)
- Avoid mixing integer types during batch copies (Chris, Jared)
- Skip over MI_NOOP when parsing to avoid overhead (Chris)
- Hold onto an explicit ref to i915_vma_work.pinned (Chris)
- Perform all asynchronous waits prior to marking payload start (Chris)
- Pull phys pread/pwrite implementations to the backend (Matt)

- Improve record of hung engines in error state (Tvrtko)
- Allow backends to override pread implementation (Matt)
- Reinforce LRC poisoning checks to confirm context survives execution (Chris)
- Fix memory region max size calculation (Matt)
- Fix order when adding blocks to memory region (Matt)
- Eliminate unused intel_virtual_engine_get_sibling func (Chris)
- Cleanup kasan warning for on-stack (unsigned long) casting (Chris)
- Onion unwind for scratch page allocation failure (Chris)
- Poison stolen pages before use (Chris)
- Selftest improvements (Chris)

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

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201112163407.GA20320@jlahtine-mobl.ger.corp.intel.com

1 files changed, 74 insertions, 22 deletions

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 69c0fa20eba1..cd786ad12be7 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -30,6 +30,7 @@
 #define ENGINE_SAMPLE_BITS (1 << I915_PMU_SAMPLE_BITS)
 
 static cpumask_t i915_pmu_cpumask;
+static unsigned int i915_pmu_target_cpu = -1;
 
 static u8 engine_config_sample(u64 config)
 {
@@ -445,6 +446,8 @@ static void i915_pmu_event_destroy(struct perf_event *event)
 		container_of(event->pmu, typeof(*i915), pmu.base);
 
 	drm_WARN_ON(&i915->drm, event->parent);
+
+	drm_dev_put(&i915->drm);
 }
 
 static int
@@ -510,8 +513,12 @@ static int i915_pmu_event_init(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
 		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = &i915->pmu;
 	int ret;
 
+	if (pmu->closed)
+		return -ENODEV;
+
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
@@ -536,8 +543,10 @@ static int i915_pmu_event_init(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (!event->parent)
+	if (!event->parent) {
+		drm_dev_get(&i915->drm);
 		event->destroy = i915_pmu_event_destroy;
+	}
 
 	return 0;
 }
@@ -594,9 +603,16 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 
 static void i915_pmu_event_read(struct perf_event *event)
 {
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
 	struct hw_perf_event *hwc = &event->hw;
+	struct i915_pmu *pmu = &i915->pmu;
 	u64 prev, new;
 
+	if (pmu->closed) {
+		event->hw.state = PERF_HES_STOPPED;
+		return;
+	}
 again:
 	prev = local64_read(&hwc->prev_count);
 	new = __i915_pmu_event_read(event);
@@ -724,6 +740,13 @@ static void i915_pmu_disable(struct perf_event *event)
 
 static void i915_pmu_event_start(struct perf_event *event, int flags)
 {
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = &i915->pmu;
+
+	if (pmu->closed)
+		return;
+
 	i915_pmu_enable(event);
 	event->hw.state = 0;
 }
@@ -738,6 +761,13 @@ static void i915_pmu_event_stop(struct perf_event *event, int flags)
 
 static int i915_pmu_event_add(struct perf_event *event, int flags)
 {
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct i915_pmu *pmu = &i915->pmu;
+
+	if (pmu->closed)
+		return -ENODEV;
+
 	if (flags & PERF_EF_START)
 		i915_pmu_event_start(event, flags);
 
@@ -1020,25 +1050,39 @@ static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
 {
 	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node);
-	unsigned int target;
+	unsigned int target = i915_pmu_target_cpu;
 
 	GEM_BUG_ON(!pmu->base.event_init);
 
+	/*
+	 * Unregistering an instance generates a CPU offline event which we must
+	 * ignore to avoid incorrectly modifying the shared i915_pmu_cpumask.
+	 */
+	if (pmu->closed)
+		return 0;
+
 	if (cpumask_test_and_clear_cpu(cpu, &i915_pmu_cpumask)) {
 		target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
+
 		/* Migrate events if there is a valid target */
 		if (target < nr_cpu_ids) {
 			cpumask_set_cpu(target, &i915_pmu_cpumask);
-			perf_pmu_migrate_context(&pmu->base, cpu, target);
+			i915_pmu_target_cpu = target;
 		}
 	}
 
+	if (target < nr_cpu_ids && target != pmu->cpuhp.cpu) {
+		perf_pmu_migrate_context(&pmu->base, cpu, target);
+		pmu->cpuhp.cpu = target;
+	}
+
 	return 0;
 }
 
-static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
+static enum cpuhp_state cpuhp_slot = CPUHP_INVALID;
+
+void i915_pmu_init(void)
 {
-	enum cpuhp_state slot;
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
@@ -1046,27 +1090,29 @@ static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
 				      i915_pmu_cpu_online,
 				      i915_pmu_cpu_offline);
 	if (ret < 0)
-		return ret;
+		pr_notice("Failed to setup cpuhp state for i915 PMU! (%d)\n",
+			  ret);
+	else
+		cpuhp_slot = ret;
+}
 
-	slot = ret;
-	ret = cpuhp_state_add_instance(slot, &pmu->cpuhp.node);
-	if (ret) {
-		cpuhp_remove_multi_state(slot);
-		return ret;
-	}
+void i915_pmu_exit(void)
+{
+	if (cpuhp_slot != CPUHP_INVALID)
+		cpuhp_remove_multi_state(cpuhp_slot);
+}
 
-	pmu->cpuhp.slot = slot;
-	return 0;
+static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
+{
+	if (cpuhp_slot == CPUHP_INVALID)
+		return -EINVAL;
+
+	return cpuhp_state_add_instance(cpuhp_slot, &pmu->cpuhp.node);
 }
 
 static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu)
 {
-	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
-
-	drm_WARN_ON(&i915->drm, pmu->cpuhp.slot == CPUHP_INVALID);
-	drm_WARN_ON(&i915->drm, cpuhp_state_remove_instance(pmu->cpuhp.slot, &pmu->cpuhp.node));
-	cpuhp_remove_multi_state(pmu->cpuhp.slot);
-	pmu->cpuhp.slot = CPUHP_INVALID;
+	cpuhp_state_remove_instance(cpuhp_slot, &pmu->cpuhp.node);
 }
 
 static bool is_igp(struct drm_i915_private *i915)
@@ -1100,7 +1146,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	spin_lock_init(&pmu->lock);
 	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->timer.function = i915_sample;
-	pmu->cpuhp.slot = CPUHP_INVALID;
+	pmu->cpuhp.cpu = -1;
 
 	if (!is_igp(i915)) {
 		pmu->name = kasprintf(GFP_KERNEL,
@@ -1167,7 +1213,13 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 	if (!pmu->base.event_init)
 		return;
 
-	drm_WARN_ON(&i915->drm, pmu->enable);
+	/*
+	 * "Disconnect" the PMU callbacks - since all are atomic synchronize_rcu
+	 * ensures all currently executing ones will have exited before we
+	 * proceed with unregistration.
+	 */
+	pmu->closed = true;
+	synchronize_rcu();
 
 	hrtimer_cancel(&pmu->timer);