Add intel_context tracing. These trace points are particular helpful when debugging the GuC firmware and can be enabled via CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS kernel config option.
Cc: John Harrison john.c.harrison@intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com --- drivers/gpu/drm/i915/gt/intel_context.c | 6 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 14 ++ drivers/gpu/drm/i915/i915_trace.h | 148 +++++++++++++++++- 3 files changed, 166 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 7f97753ab164..b24a1b7a3f88 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -8,6 +8,7 @@
#include "i915_drv.h" #include "i915_globals.h" +#include "i915_trace.h"
#include "intel_context.h" #include "intel_engine.h" @@ -28,6 +29,7 @@ static void rcu_context_free(struct rcu_head *rcu) { struct intel_context *ce = container_of(rcu, typeof(*ce), rcu);
+ trace_intel_context_free(ce); kmem_cache_free(global.slab_ce, ce); }
@@ -46,6 +48,7 @@ intel_context_create(struct intel_engine_cs *engine) return ERR_PTR(-ENOMEM);
intel_context_init(ce, engine); + trace_intel_context_create(ce); return ce; }
@@ -268,6 +271,8 @@ int __intel_context_do_pin_ww(struct intel_context *ce,
GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */
+ trace_intel_context_do_pin(ce); + err_unlock: mutex_unlock(&ce->pin_mutex); err_post_unpin: @@ -323,6 +328,7 @@ void __intel_context_do_unpin(struct intel_context *ce, int sub) */ intel_context_get(ce); intel_context_active_release(ce); + trace_intel_context_do_unpin(ce); intel_context_put(ce); }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 87ed00f272e7..a789994d6de7 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -347,6 +347,7 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
err = intel_guc_send_nb(guc, action, len, g2h_len_dw); if (!enabled && !err) { + trace_intel_context_sched_enable(ce); atomic_inc(&guc->outstanding_submission_g2h); set_context_enabled(ce); } else if (!enabled) { @@ -815,6 +816,8 @@ static int register_context(struct intel_context *ce) u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool) + ce->guc_id * sizeof(struct guc_lrc_desc);
+ trace_intel_context_register(ce); + return __guc_action_register_context(guc, ce->guc_id, offset); }
@@ -834,6 +837,8 @@ static int deregister_context(struct intel_context *ce, u32 guc_id) { struct intel_guc *guc = ce_to_guc(ce);
+ trace_intel_context_deregister(ce); + return __guc_action_deregister_context(guc, guc_id); }
@@ -908,6 +913,7 @@ static int guc_lrc_desc_pin(struct intel_context *ce) * GuC before registering this context. */ if (context_registered) { + trace_intel_context_steal_guc_id(ce); set_context_wait_for_deregister_to_register(ce); intel_context_get(ce);
@@ -966,6 +972,7 @@ static void __guc_context_sched_disable(struct intel_guc *guc,
GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID);
+ trace_intel_context_sched_disable(ce); intel_context_get(ce);
guc_submission_busy_loop(guc, action, ARRAY_SIZE(action), @@ -1122,6 +1129,9 @@ static void __guc_signal_context_fence(struct intel_context *ce)
lockdep_assert_held(&ce->guc_state.lock);
+ if (!list_empty(&ce->guc_state.fences)) + trace_intel_context_fence_release(ce); + list_for_each_entry(rq, &ce->guc_state.fences, guc_fence_link) i915_sw_fence_complete(&rq->submit);
@@ -1536,6 +1546,8 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, if (unlikely(!ce)) return -EPROTO;
+ trace_intel_context_deregister_done(ce); + if (context_wait_for_deregister_to_register(ce)) { struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm; @@ -1587,6 +1599,8 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc, return -EPROTO; }
+ trace_intel_context_sched_done(ce); + if (context_pending_enable(ce)) { clr_context_pending_enable(ce); } else if (context_pending_disable(ce)) { diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index b02d04b6c8f6..97c2e83984ed 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -818,8 +818,8 @@ DECLARE_EVENT_CLASS(i915_request, );
DEFINE_EVENT(i915_request, i915_request_add, - TP_PROTO(struct i915_request *rq), - TP_ARGS(rq) + TP_PROTO(struct i915_request *rq), + TP_ARGS(rq) );
#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) @@ -905,6 +905,90 @@ TRACE_EVENT(i915_request_out, __entry->ctx, __entry->seqno, __entry->completed) );
+DECLARE_EVENT_CLASS(intel_context, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce), + + TP_STRUCT__entry( + __field(u32, guc_id) + __field(int, pin_count) + __field(u32, sched_state) + __field(u32, guc_sched_state_no_lock) + ), + + TP_fast_assign( + __entry->guc_id = ce->guc_id; + __entry->pin_count = atomic_read(&ce->pin_count); + __entry->sched_state = ce->guc_state.sched_state; + __entry->guc_sched_state_no_lock = + atomic_read(&ce->guc_sched_state_no_lock); + ), + + TP_printk("guc_id=%d, pin_count=%d sched_state=0x%x,0x%x", + __entry->guc_id, __entry->pin_count, __entry->sched_state, + __entry->guc_sched_state_no_lock) +); + +DEFINE_EVENT(intel_context, intel_context_register, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_deregister, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_deregister_done, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_sched_enable, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_sched_disable, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_sched_done, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_create, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_fence_release, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_free, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_steal_guc_id, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_do_pin, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_do_unpin, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + #else #if !defined(TRACE_HEADER_MULTI_READ) static inline void @@ -941,6 +1025,66 @@ static inline void trace_i915_request_out(struct i915_request *rq) { } + +static inline void +trace_intel_context_register(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_deregister(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_deregister_done(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_sched_enable(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_sched_disable(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_sched_done(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_create(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_fence_release(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_free(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_steal_guc_id(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_do_pin(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_do_unpin(struct intel_context *ce) +{ +} #endif #endif