diff options
author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2020-08-06 14:15:47 +0300 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2020-08-06 14:15:47 +0300 |
commit | 94fb1afb14c4f0ceb8c5508ddddac6819f662e95 (patch) | |
tree | 4988e5769dc7482caa7f441475ae31f50bbd37ef /drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c | |
parent | c4735d990268399da9133b0ad445e488ece009ad (diff) | |
parent | 47ec5303d73ea344e84f46660fff693c57641386 (diff) | |
download | linux-94fb1afb14c4f0ceb8c5508ddddac6819f662e95.tar.xz |
Mgerge remote-tracking branch 'torvalds/master' into perf/core
To sync headers, for instance, in this case tools/perf was ahead of
upstream till Linus merged tip/perf/core to get the
PERF_RECORD_TEXT_POKE changes:
Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h'
diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c')
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c | 41 |
1 files changed, 34 insertions, 7 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index 5136c8bf112d..8ffdf676c0a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -4,6 +4,7 @@ * Copyright © 2019 Intel Corporation */ +#include "i915_drv.h" #include "i915_request.h" #include "intel_context.h" @@ -31,7 +32,7 @@ static bool next_heartbeat(struct intel_engine_cs *engine) delay = msecs_to_jiffies_timeout(delay); if (delay >= HZ) delay = round_jiffies_up_relative(delay); - mod_delayed_work(system_wq, &engine->heartbeat.work, delay); + mod_delayed_work(system_highpri_wq, &engine->heartbeat.work, delay); return true; } @@ -48,8 +49,10 @@ static void show_heartbeat(const struct i915_request *rq, struct drm_printer p = drm_debug_printer("heartbeat"); intel_engine_dump(engine, &p, - "%s heartbeat {prio:%d} not ticking\n", + "%s heartbeat {seqno:%llx:%lld, prio:%d} not ticking\n", engine->name, + rq->fence.context, + rq->fence.seqno, rq->sched.attr.priority); } @@ -62,6 +65,10 @@ static void heartbeat(struct work_struct *wrk) container_of(wrk, typeof(*engine), heartbeat.work.work); struct intel_context *ce = engine->kernel_context; struct i915_request *rq; + unsigned long serial; + + /* Just in case everything has gone horribly wrong, give it a kick */ + intel_engine_flush_submission(engine); rq = engine->heartbeat.systole; if (rq && i915_request_completed(rq)) { @@ -76,8 +83,19 @@ static void heartbeat(struct work_struct *wrk) goto out; if (engine->heartbeat.systole) { - if (engine->schedule && - rq->sched.attr.priority < I915_PRIORITY_BARRIER) { + if (!i915_sw_fence_signaled(&rq->submit)) { + /* + * Not yet submitted, system is stalled. + * + * This more often happens for ring submission, + * where all contexts are funnelled into a common + * ringbuffer. If one context is blocked on an + * external fence, not only is it not submitted, + * but all other contexts, including the kernel + * context are stuck waiting for the signal. + */ + } else if (engine->schedule && + rq->sched.attr.priority < I915_PRIORITY_BARRIER) { /* * Gradually raise the priority of the heartbeat to * give high priority work [which presumably desires @@ -105,10 +123,19 @@ static void heartbeat(struct work_struct *wrk) goto out; } - if (engine->wakeref_serial == engine->serial) + serial = READ_ONCE(engine->serial); + if (engine->wakeref_serial == serial) goto out; - mutex_lock(&ce->timeline->mutex); + if (!mutex_trylock(&ce->timeline->mutex)) { + /* Unable to lock the kernel timeline, is the engine stuck? */ + if (xchg(&engine->heartbeat.blocked, serial) == serial) + intel_gt_handle_error(engine->gt, engine->mask, + I915_ERROR_CAPTURE, + "no heartbeat on %s", + engine->name); + goto out; + } intel_context_enter(ce); rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN); @@ -117,7 +144,7 @@ static void heartbeat(struct work_struct *wrk) goto unlock; idle_pulse(engine, rq); - if (i915_modparams.enable_hangcheck) + if (engine->i915->params.enable_hangcheck) engine->heartbeat.systole = i915_request_get(rq); __i915_request_commit(rq); |