Fix request cancellation + add request cancel low level trace point.
Signed-off-by: Matthew Brost matthew.brost@intel.com
Matthew Brost (2): drm/i915: Add request cancel low level trace point drm/i915/guc: Cancel requests immediately
drivers/gpu/drm/i915/gt/intel_context.h | 1 + drivers/gpu/drm/i915/gt/intel_context_types.h | 5 ++ .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 46 +++++++++++-------- drivers/gpu/drm/i915/i915_trace.h | 10 ++++ 4 files changed, 42 insertions(+), 20 deletions(-)
Add request cancel trace point guarded by CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINT.
Signed-off-by: Matthew Brost matthew.brost@intel.com --- drivers/gpu/drm/i915/gt/intel_context.h | 1 + drivers/gpu/drm/i915/i915_trace.h | 10 ++++++++++ 2 files changed, 11 insertions(+)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index d8c74bbf9aae2..3aed4d77f116c 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -124,6 +124,7 @@ intel_context_is_pinned(struct intel_context *ce) static inline void intel_context_cancel_request(struct intel_context *ce, struct i915_request *rq) { + trace_i915_request_cancel(rq); GEM_BUG_ON(!ce->ops->cancel_request); return ce->ops->cancel_request(ce, rq); } diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 37b5c9e9d260e..d0a11a8bb0ca3 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -324,6 +324,11 @@ DEFINE_EVENT(i915_request, i915_request_add, );
#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) +DEFINE_EVENT(i915_request, i915_request_cancel, + TP_PROTO(struct i915_request *rq), + TP_ARGS(rq) +); + DEFINE_EVENT(i915_request, i915_request_guc_submit, TP_PROTO(struct i915_request *rq), TP_ARGS(rq) @@ -497,6 +502,11 @@ DEFINE_EVENT(intel_context, intel_context_do_unpin,
#else #if !defined(TRACE_HEADER_MULTI_READ) +static inline void +trace_i915_request_cancel(struct i915_request *rq) +{ +} + static inline void trace_i915_request_guc_submit(struct i915_request *rq) {
Change the preemption timeout to the smallest possible value (1 us) when disabling scheduling to cancel a request and restore it after cancelation. This not only cancels the request as fast as possible, it fixes a bug where the preemption timeout is 0 which results in the schedule disable hanging forever.
Reported-by: Jani Saarinen jani.saarinen@intel.com Fixes: 62eaf0ae217d4 ("drm/i915/guc: Support request cancellation") Link: https://gitlab.freedesktop.org/drm/intel/-/issues/4960 Signed-off-by: Matthew Brost matthew.brost@intel.com --- drivers/gpu/drm/i915/gt/intel_context_types.h | 5 ++ .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 46 +++++++++++-------- 2 files changed, 31 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 30cd81ad8911a..730998823dbea 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -198,6 +198,11 @@ struct intel_context { * each priority bucket */ u32 prio_count[GUC_CLIENT_PRIORITY_NUM]; + /** + * @preemption_timeout: preemption timeout of the context, used + * to restore this value after request cancellation + */ + u32 preemption_timeout; } guc_state;
struct { 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 3918f1be114fa..966947c450253 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -2147,7 +2147,8 @@ static inline u32 get_children_join_value(struct intel_context *ce, return __get_parent_scratch(ce)->join[child_index].semaphore; }
-static void guc_context_policy_init(struct intel_engine_cs *engine, +static void guc_context_policy_init(struct intel_context *ce, + struct intel_engine_cs *engine, struct guc_lrc_desc *desc) { desc->policy_flags = 0; @@ -2157,7 +2158,8 @@ static void guc_context_policy_init(struct intel_engine_cs *engine,
/* NB: For both of these, zero means disabled. */ desc->execution_quantum = engine->props.timeslice_duration_ms * 1000; - desc->preemption_timeout = engine->props.preempt_timeout_ms * 1000; + ce->guc_state.preemption_timeout = engine->props.preempt_timeout_ms * 1000; + desc->preemption_timeout = ce->guc_state.preemption_timeout; }
static int guc_lrc_desc_pin(struct intel_context *ce, bool loop) @@ -2193,7 +2195,7 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop) desc->hw_context_desc = ce->lrc.lrca; desc->priority = ce->guc_state.prio; desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; - guc_context_policy_init(engine, desc); + guc_context_policy_init(ce, engine, desc);
/* * If context is a parent, we need to register a process descriptor @@ -2226,7 +2228,7 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop) desc->hw_context_desc = child->lrc.lrca; desc->priority = ce->guc_state.prio; desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; - guc_context_policy_init(engine, desc); + guc_context_policy_init(child, engine, desc); }
clear_children_join_go_memory(ce); @@ -2409,6 +2411,19 @@ static u16 prep_context_pending_disable(struct intel_context *ce) return ce->guc_id.id; }
+static void __guc_context_set_preemption_timeout(struct intel_guc *guc, + u16 guc_id, + u32 preemption_timeout) +{ + u32 action[] = { + INTEL_GUC_ACTION_SET_CONTEXT_PREEMPTION_TIMEOUT, + guc_id, + preemption_timeout + }; + + intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); +} + static struct i915_sw_fence *guc_context_block(struct intel_context *ce) { struct intel_guc *guc = ce_to_guc(ce); @@ -2442,8 +2457,10 @@ static struct i915_sw_fence *guc_context_block(struct intel_context *ce)
spin_unlock_irqrestore(&ce->guc_state.lock, flags);
- with_intel_runtime_pm(runtime_pm, wakeref) + with_intel_runtime_pm(runtime_pm, wakeref) { + __guc_context_set_preemption_timeout(guc, guc_id, 1); __guc_context_sched_disable(guc, ce, guc_id); + }
return &ce->guc_state.blocked; } @@ -2492,8 +2509,10 @@ static void guc_context_unblock(struct intel_context *ce)
spin_unlock_irqrestore(&ce->guc_state.lock, flags);
- if (enable) { - with_intel_runtime_pm(runtime_pm, wakeref) + with_intel_runtime_pm(runtime_pm, wakeref) { + __guc_context_set_preemption_timeout(guc, ce->guc_id.id, + ce->guc_state.preemption_timeout); + if (enable) __guc_context_sched_enable(guc, ce); } } @@ -2521,19 +2540,6 @@ static void guc_context_cancel_request(struct intel_context *ce, } }
-static void __guc_context_set_preemption_timeout(struct intel_guc *guc, - u16 guc_id, - u32 preemption_timeout) -{ - u32 action[] = { - INTEL_GUC_ACTION_SET_CONTEXT_PREEMPTION_TIMEOUT, - guc_id, - preemption_timeout - }; - - intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); -} - static void guc_context_ban(struct intel_context *ce, struct i915_request *rq) { struct intel_guc *guc = ce_to_guc(ce);
dri-devel@lists.freedesktop.org
-
Matthew Brost