From abcc2ddae5f82aa6cfca162e3db643dd33f0a2e8 Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Wed, 27 Nov 2024 09:40:04 -0800 Subject: [PATCH 1/3] i915/guc: Reset engine utilization buffer before registration On GT reset, we store total busyness counts for all engines and re-register the utilization buffer with GuC. At that time we should reset the buffer, so that we don't get spurious busyness counts on subsequent queries. To repro this issue, run igt@perf_pmu@busy-hang followed by igt@perf_pmu@most-busy-idle-check-all for a couple iterations. Fixes: 77cdd054dd2c ("drm/i915/pmu: Connect engine busyness stats from GuC to pmu") Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20241127174006.190128-2-umesh.nerlige.ramappa@intel.com (cherry picked from commit abd318237fa6556c1e5225529af145ef15d5ff0d) Signed-off-by: Tvrtko Ursulin --- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) 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 9ede6f240d79..b1d0c66e166f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1243,6 +1243,21 @@ static void __get_engine_usage_record(struct intel_engine_cs *engine, } while (++i < 6); } +static void __set_engine_usage_record(struct intel_engine_cs *engine, + u32 last_in, u32 id, u32 total) +{ + struct iosys_map rec_map = intel_guc_engine_usage_record_map(engine); + +#define record_write(map_, field_, val_) \ + iosys_map_wr_field(map_, 0, struct guc_engine_usage_record, field_, val_) + + record_write(&rec_map, last_switch_in_stamp, last_in); + record_write(&rec_map, current_context_index, id); + record_write(&rec_map, total_runtime, total); + +#undef record_write +} + static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) { struct intel_engine_guc_stats *stats = &engine->stats.guc; @@ -1543,6 +1558,9 @@ static void guc_timestamp_ping(struct work_struct *wrk) static int guc_action_enable_usage_stats(struct intel_guc *guc) { + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; u32 offset = intel_guc_engine_usage_offset(guc); u32 action[] = { INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF, @@ -1550,6 +1568,9 @@ static int guc_action_enable_usage_stats(struct intel_guc *guc) 0, }; + for_each_engine(engine, gt, id) + __set_engine_usage_record(engine, 0, 0xffffffff, 0); + return intel_guc_send(guc, action, ARRAY_SIZE(action)); } From 59a0b46788d58fdcee8d2f6b4e619d264a1799bf Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Wed, 27 Nov 2024 09:40:05 -0800 Subject: [PATCH 2/3] i915/guc: Ensure busyness counter increases motonically Active busyness of an engine is calculated using gt timestamp and the context switch in time. While capturing the gt timestamp, it's possible that the context switches out. This race could result in an active busyness value that is greater than the actual context runtime value by a small amount. This leads to a negative delta and throws off busyness calculations for the user. If a subsequent count is smaller than the previous one, just return the previous one, since we expect the busyness to catch up. Fixes: 77cdd054dd2c ("drm/i915/pmu: Connect engine busyness stats from GuC to pmu") Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20241127174006.190128-3-umesh.nerlige.ramappa@intel.com (cherry picked from commit cf907f6d294217985e9dafd9985dce874e04ca37) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/gt/intel_engine_types.h | 5 +++++ drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 5 ++++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index ba55c059063d..fe1f85e5dda3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -343,6 +343,11 @@ struct intel_engine_guc_stats { * @start_gt_clk: GT clock time of last idle to active transition. */ u64 start_gt_clk; + + /** + * @total: The last value of total returned + */ + u64 total; }; union intel_engine_tlb_inv_reg { 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 b1d0c66e166f..9dcf76d440d8 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1378,9 +1378,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) total += intel_gt_clock_interval_to_ns(gt, clk); } + if (total > stats->total) + stats->total = total; + spin_unlock_irqrestore(&guc->timestamp.lock, flags); - return ns_to_ktime(total); + return ns_to_ktime(stats->total); } static void guc_enable_busyness_worker(struct intel_guc *guc) From 1622ed27d26ab4c234476be746aa55bcd39159dd Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Wed, 27 Nov 2024 09:40:06 -0800 Subject: [PATCH 3/3] i915/guc: Accumulate active runtime on gt reset On gt reset, if a context is running, then accumulate it's active time into the busyness counter since there will be no chance for the context to switch out and update it's run time. v2: Move comment right above the if (John) Fixes: 77cdd054dd2c ("drm/i915/pmu: Connect engine busyness stats from GuC to pmu") Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20241127174006.190128-4-umesh.nerlige.ramappa@intel.com (cherry picked from commit 7ed047da59cfa1acb558b95169d347acc8d85da1) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) 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 9dcf76d440d8..c0bd730383f2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1449,8 +1449,21 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) guc_update_pm_timestamp(guc, &unused); for_each_engine(engine, gt, id) { + struct intel_engine_guc_stats *stats = &engine->stats.guc; + guc_update_engine_gt_clks(engine); - engine->stats.guc.prev_total = 0; + + /* + * If resetting a running context, accumulate the active + * time as well since there will be no context switch. + */ + if (stats->running) { + u64 clk = guc->timestamp.gt_stamp - stats->start_gt_clk; + + stats->total_gt_clks += clk; + } + stats->prev_total = 0; + stats->running = 0; } spin_unlock_irqrestore(&guc->timestamp.lock, flags);