[PATCH 57/89] drm/i915/execlists: Force preemption via reset on timeout
Chris Wilson
chris at chris-wilson.co.uk
Fri Sep 21 14:08:27 UTC 2018
Install a timer when trying to preempt on behalf of an important
context such that if the active context does not honour the preemption
request within the desired timeout, then we reset the GPU to allow the
important context to run.
v2: Install the timer on scheduling the preempt request; long before we
even try to inject preemption into the ELSP, as the tasklet/injection
may itself be blocked.
v3: Update the guc to handle the preemption/tasklet timer.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_scheduler.c | 2 +-
drivers/gpu/drm/i915/intel_engine_cs.c | 4 +
drivers/gpu/drm/i915/intel_guc_submission.c | 1 +
drivers/gpu/drm/i915/intel_lrc.c | 85 ++++++++++++++++++++-
drivers/gpu/drm/i915/intel_ringbuffer.h | 7 +-
drivers/gpu/drm/i915/selftests/intel_lrc.c | 65 ++++++++++++++++
6 files changed, 157 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index cfb0a0353e15..508e5feacba7 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -367,7 +367,7 @@ static void __i915_schedule(struct i915_request *rq,
continue;
/* Defer (tasklet) submission until after all of our updates. */
- engine->execlists.queue_priority = prio;
+ //engine->schedule_submit_queue(engine, prio, timeout);
tasklet_hi_schedule(&engine->execlists.tasklet);
}
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index cfd4bac00e99..3b23c14aca15 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -468,6 +468,9 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
execlists->queue_priority = INT_MIN;
execlists->queue = RB_ROOT_CACHED;
+
+ hrtimer_init(&execlists->preempt_timer,
+ CLOCK_MONOTONIC, HRTIMER_MODE_REL);
}
/**
@@ -1178,6 +1181,7 @@ void intel_engines_park(struct drm_i915_private *i915)
for_each_engine(engine, i915, id) {
/* Flush the residual irq tasklets first. */
+ hrtimer_cancel(&engine->execlists.preempt_timer);
intel_engine_disarm_breadcrumbs(engine);
tasklet_kill(&engine->execlists.tasklet);
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 449368c08021..ef4c4d4d45b2 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -772,6 +772,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
kmem_cache_free(engine->i915->priorities, p);
}
done:
+ execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT_TIMEOUT);
execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN;
if (submit)
port_assign(port, last);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 420844c64bfe..5898c1f014fd 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -563,6 +563,49 @@ static void inject_preempt_context(struct intel_engine_cs *engine)
execlists_set_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
}
+static enum hrtimer_restart preempt_timeout(struct hrtimer *hrtimer)
+{
+ struct intel_engine_execlists *execlists =
+ container_of(hrtimer, typeof(*execlists), preempt_timer);
+ struct intel_engine_cs *engine =
+ container_of(execlists, typeof(*engine), execlists);
+
+ GEM_TRACE("%s active=%x\n", engine->name, execlists->active);
+
+ synchronize_hardirq(engine->i915->drm.irq);
+ if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT_TIMEOUT))
+ return HRTIMER_NORESTART;
+
+ if (GEM_SHOW_DEBUG()) {
+ struct drm_printer p = drm_debug_printer(__func__);
+
+ intel_engine_dump(engine, &p, "%s\n", engine->name);
+ }
+
+ queue_work(system_highpri_wq, &execlists->preempt_reset);
+
+ return HRTIMER_NORESTART;
+}
+
+static void preempt_reset(struct work_struct *work)
+{
+ struct intel_engine_execlists *execlists =
+ container_of(work, typeof(*execlists), preempt_reset);
+ struct intel_engine_cs *engine =
+ container_of(execlists, struct intel_engine_cs, execlists);
+
+ GEM_TRACE("%s\n", engine->name);
+
+ tasklet_disable(&execlists->tasklet);
+
+ execlists->tasklet.func(execlists->tasklet.data);
+ if (execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT_TIMEOUT))
+ i915_handle_error(engine->i915, BIT(engine->id), 0,
+ "preemption time out on %s", engine->name);
+
+ tasklet_enable(&execlists->tasklet);
+}
+
static void complete_preempt_context(struct intel_engine_execlists *execlists)
{
GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
@@ -726,7 +769,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
* priorities of the ports haven't been switch.
*/
if (port_count(&port[1]))
- return;
+ goto clear_preempt_timeout;
/*
* WaIdleLiteRestore:bdw,skl
@@ -889,6 +932,9 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
!port_isset(execlists->port));
+clear_preempt_timeout:
+ execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT_TIMEOUT);
+
/* Re-evaluate the executing context setup after each preemptive kick */
if (last)
execlists_user_begin(execlists, execlists->port);
@@ -1207,6 +1253,33 @@ static void queue_request(struct intel_engine_cs *engine,
list_add_tail(&node->link, i915_sched_lookup_priolist(engine, prio));
}
+static void __update_queue(struct intel_engine_cs *engine,
+ int prio, unsigned int timeout)
+{
+ struct intel_engine_execlists * const execlists = &engine->execlists;
+
+ GEM_TRACE("%s prio=%d (previous=%d)\n",
+ engine->name, prio, execlists->queue_priority);
+
+ if (unlikely(execlists_is_active(execlists,
+ EXECLISTS_ACTIVE_PREEMPT_TIMEOUT)))
+ hrtimer_cancel(&execlists->preempt_timer);
+
+ /* Set a timer to force preemption vs hostile userspace */
+ if (timeout &&
+ __execlists_need_preempt(prio, execlists->queue_priority)) {
+ GEM_TRACE("%s preempt timeout=%uns\n", engine->name, timeout);
+
+ execlists_set_active(execlists,
+ EXECLISTS_ACTIVE_PREEMPT_TIMEOUT);
+ hrtimer_start(&execlists->preempt_timer,
+ ns_to_ktime(timeout),
+ HRTIMER_MODE_REL);
+ }
+
+ engine->execlists.queue_priority = prio;
+}
+
static void __submit_queue_imm(struct intel_engine_cs *engine)
{
struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1220,10 +1293,11 @@ static void __submit_queue_imm(struct intel_engine_cs *engine)
tasklet_hi_schedule(&execlists->tasklet);
}
-static void submit_queue(struct intel_engine_cs *engine, int prio)
+static void submit_queue(struct intel_engine_cs *engine,
+ int prio, unsigned int timeout)
{
if (prio > engine->execlists.queue_priority) {
- engine->execlists.queue_priority = prio;
+ __update_queue(engine, prio, timeout);
__submit_queue_imm(engine);
}
}
@@ -1241,7 +1315,7 @@ static void execlists_submit_request(struct i915_request *request)
GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
GEM_BUG_ON(list_empty(&request->sched.link));
- submit_queue(engine, rq_prio(request));
+ submit_queue(engine, rq_prio(request), 0);
spin_unlock_irqrestore(&engine->timeline.lock, flags);
}
@@ -2353,6 +2427,9 @@ logical_ring_setup(struct intel_engine_cs *engine)
tasklet_init(&engine->execlists.tasklet,
execlists_submission_tasklet, (unsigned long)engine);
+ INIT_WORK(&engine->execlists.preempt_reset, preempt_reset);
+ engine->execlists.preempt_timer.function = preempt_timeout;
+
logical_ring_default_vfuncs(engine);
logical_ring_default_irqs(engine);
}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index cde12069b867..8eccf1c7aa5f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -288,8 +288,9 @@ struct intel_engine_execlists {
*/
unsigned int active;
#define EXECLISTS_ACTIVE_USER 0
-#define EXECLISTS_ACTIVE_PREEMPT 1
-#define EXECLISTS_ACTIVE_HWACK 2
+#define EXECLISTS_ACTIVE_HWACK 1
+#define EXECLISTS_ACTIVE_PREEMPT 2
+#define EXECLISTS_ACTIVE_PREEMPT_TIMEOUT 3
/**
* @port_mask: number of execlist ports - 1
@@ -352,6 +353,8 @@ struct intel_engine_execlists {
*/
u8 csb_head;
+ struct hrtimer preempt_timer;
+ struct work_struct preempt_reset;
I915_SELFTEST_DECLARE(struct st_preempt_hang preempt_hang;)
};
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index ceaf7453e3ab..d5ddc5c31327 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -585,6 +585,70 @@ static int live_preempt_hang(void *arg)
return err;
}
+static void mark_preemption_hang(struct intel_engine_execlists *execlists)
+{
+ execlists_set_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
+ execlists_set_active(execlists, EXECLISTS_ACTIVE_PREEMPT_TIMEOUT);
+}
+
+static int live_preempt_timeout(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ struct intel_engine_cs *engine;
+ struct i915_gem_context *ctx;
+ enum intel_engine_id id;
+ struct spinner spin;
+ int err = -ENOMEM;
+
+ if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+ return 0;
+
+ mutex_lock(&i915->drm.struct_mutex);
+
+ if (spinner_init(&spin, i915))
+ goto err_unlock;
+
+ ctx = kernel_context(i915);
+ if (!ctx)
+ goto err_spin;
+
+ for_each_engine(engine, i915, id) {
+ struct i915_request *rq;
+
+ rq = spinner_create_request(&spin, ctx, engine, MI_NOOP);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto err_ctx;
+ }
+
+ i915_request_add(rq);
+ if (!wait_for_spinner(&spin, rq)) {
+ i915_gem_set_wedged(i915);
+ err = -EIO;
+ goto err_ctx;
+ }
+
+ GEM_TRACE("%s triggering reset\n", engine->name);
+ mark_preemption_hang(&engine->execlists);
+ preempt_reset(&engine->execlists.preempt_reset);
+
+ if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+ err = -EIO;
+ goto err_ctx;
+ }
+ }
+
+ err = 0;
+err_ctx:
+ kernel_context_close(ctx);
+err_spin:
+ spinner_fini(&spin);
+err_unlock:
+ igt_flush_test(i915, I915_WAIT_LOCKED);
+ mutex_unlock(&i915->drm.struct_mutex);
+ return err;
+}
+
static int random_range(struct rnd_state *rnd, int min, int max)
{
return i915_prandom_u32_max_state(max - min, rnd) + min;
@@ -1106,6 +1170,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
SUBTEST(live_preempt),
SUBTEST(live_late_preempt),
SUBTEST(live_preempt_hang),
+ SUBTEST(live_preempt_timeout),
SUBTEST(live_preempt_smoke),
SUBTEST(live_virtual_engine),
SUBTEST(live_virtual_bond),
--
2.19.0
More information about the Intel-gfx-trybot
mailing list