From: Jesse Barnes <jbarnes@virtuousgeek.org>
To: John.C.Harrison@Intel.com, Intel-GFX@Lists.FreeDesktop.Org
Subject: Re: [PATCH v5 24/35] drm/i915: Added trace points to scheduler
Date: Tue, 23 Feb 2016 12:42:17 -0800 [thread overview]
Message-ID: <56CCC429.30106@virtuousgeek.org> (raw)
In-Reply-To: <1455805644-6450-25-git-send-email-John.C.Harrison@Intel.com>
On 02/18/2016 06:27 AM, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
>
> Added trace points to the scheduler to track all the various events,
> node state transitions and other interesting things that occur.
>
> v2: Updated for new request completion tracking implementation.
>
> v3: Updated for changes to node kill code.
>
> v4: Wrapped some long lines to keep the style checker happy.
>
> For: VIZ-1587
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +
> drivers/gpu/drm/i915/i915_scheduler.c | 26 ++++
> drivers/gpu/drm/i915/i915_trace.h | 196 +++++++++++++++++++++++++++++
> drivers/gpu/drm/i915/intel_lrc.c | 2 +
> 4 files changed, 226 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index b9ad0fd..d4de8c7 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1272,6 +1272,8 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
>
> i915_gem_execbuffer_move_to_active(vmas, params->request);
>
> + trace_i915_gem_ring_queue(ring, params);
> +
> qe = container_of(params, typeof(*qe), params);
> ret = i915_scheduler_queue_execbuffer(qe);
> if (ret)
> diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
> index 47d7de4..e56ce08 100644
> --- a/drivers/gpu/drm/i915/i915_scheduler.c
> +++ b/drivers/gpu/drm/i915/i915_scheduler.c
> @@ -88,6 +88,8 @@ static void i915_scheduler_node_requeue(struct i915_scheduler_queue_entry *node)
> /* Seqno will be reassigned on relaunch */
> node->params.request->seqno = 0;
> node->status = i915_sqs_queued;
> + trace_i915_scheduler_unfly(node->params.ring, node);
> + trace_i915_scheduler_node_state_change(node->params.ring, node);
> }
>
> /*
> @@ -99,7 +101,11 @@ static void i915_scheduler_node_kill(struct i915_scheduler_queue_entry *node)
> WARN_ON(!node);
> WARN_ON(I915_SQS_IS_COMPLETE(node));
>
> + if (I915_SQS_IS_FLYING(node))
> + trace_i915_scheduler_unfly(node->params.ring, node);
> +
> node->status = i915_sqs_dead;
> + trace_i915_scheduler_node_state_change(node->params.ring, node);
> }
>
> /* Mark a node as in flight on the hardware. */
> @@ -124,6 +130,9 @@ static int i915_scheduler_node_fly(struct i915_scheduler_queue_entry *node)
>
> node->status = i915_sqs_flying;
>
> + trace_i915_scheduler_fly(ring, node);
> + trace_i915_scheduler_node_state_change(ring, node);
> +
> if (!(scheduler->flags[ring->id] & i915_sf_interrupts_enabled)) {
> bool success = true;
>
> @@ -280,6 +289,8 @@ static int i915_scheduler_pop_from_queue_locked(struct intel_engine_cs *ring,
> INIT_LIST_HEAD(&best->link);
> best->status = i915_sqs_popped;
>
> + trace_i915_scheduler_node_state_change(ring, best);
> +
> ret = 0;
> } else {
> /* Can only get here if:
> @@ -297,6 +308,8 @@ static int i915_scheduler_pop_from_queue_locked(struct intel_engine_cs *ring,
> }
> }
>
> + trace_i915_scheduler_pop_from_queue(ring, best);
> +
> *pop_node = best;
> return ret;
> }
> @@ -506,6 +519,8 @@ static int i915_scheduler_queue_execbuffer_bypass(struct i915_scheduler_queue_en
> struct i915_scheduler *scheduler = dev_priv->scheduler;
> int ret;
>
> + trace_i915_scheduler_queue(qe->params.ring, qe);
> +
> intel_ring_reserved_space_cancel(qe->params.request->ringbuf);
>
> scheduler->flags[qe->params.ring->id] |= i915_sf_submitting;
> @@ -628,6 +643,9 @@ int i915_scheduler_queue_execbuffer(struct i915_scheduler_queue_entry *qe)
> not_flying = i915_scheduler_count_flying(scheduler, ring) <
> scheduler->min_flying;
>
> + trace_i915_scheduler_queue(ring, node);
> + trace_i915_scheduler_node_state_change(ring, node);
> +
> spin_unlock_irq(&scheduler->lock);
>
> if (not_flying)
> @@ -657,6 +675,8 @@ bool i915_scheduler_notify_request(struct drm_i915_gem_request *req)
> struct i915_scheduler_queue_entry *node = req->scheduler_qe;
> unsigned long flags;
>
> + trace_i915_scheduler_landing(req);
> +
> if (!node)
> return false;
>
> @@ -670,6 +690,8 @@ bool i915_scheduler_notify_request(struct drm_i915_gem_request *req)
> else
> node->status = i915_sqs_complete;
>
> + trace_i915_scheduler_node_state_change(req->ring, node);
> +
> spin_unlock_irqrestore(&scheduler->lock, flags);
>
> return true;
> @@ -877,6 +899,8 @@ static bool i915_scheduler_remove(struct i915_scheduler *scheduler,
> /* Launch more packets now? */
> do_submit = (queued > 0) && (flying < scheduler->min_flying);
>
> + trace_i915_scheduler_remove(ring, min_seqno, do_submit);
> +
> spin_unlock_irq(&scheduler->lock);
>
> return do_submit;
> @@ -912,6 +936,8 @@ static void i915_scheduler_process_work(struct intel_engine_cs *ring)
> node = list_first_entry(&remove, typeof(*node), link);
> list_del(&node->link);
>
> + trace_i915_scheduler_destroy(ring, node);
> +
> /* Free up all the DRM references */
> i915_scheduler_clean_node(node);
>
> diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
> index 455c215..c3c4e58 100644
> --- a/drivers/gpu/drm/i915/i915_trace.h
> +++ b/drivers/gpu/drm/i915/i915_trace.h
> @@ -9,6 +9,7 @@
> #include "i915_drv.h"
> #include "intel_drv.h"
> #include "intel_ringbuffer.h"
> +#include "i915_scheduler.h"
>
> #undef TRACE_SYSTEM
> #define TRACE_SYSTEM i915
> @@ -826,6 +827,201 @@ TRACE_EVENT(switch_mm,
> __entry->dev, __entry->ring, __entry->to, __entry->vm)
> );
>
> +TRACE_EVENT(i915_scheduler_queue,
> + TP_PROTO(struct intel_engine_cs *ring,
> + struct i915_scheduler_queue_entry *node),
> + TP_ARGS(ring, node),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->uniq = node ? node->params.request->uniq : 0;
> + __entry->seqno = node ? node->params.request->seqno : 0;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d",
> + __entry->ring, __entry->uniq, __entry->seqno)
> +);
> +
> +TRACE_EVENT(i915_scheduler_fly,
> + TP_PROTO(struct intel_engine_cs *ring,
> + struct i915_scheduler_queue_entry *node),
> + TP_ARGS(ring, node),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->uniq = node ? node->params.request->uniq : 0;
> + __entry->seqno = node ? node->params.request->seqno : 0;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d",
> + __entry->ring, __entry->uniq, __entry->seqno)
> +);
> +
> +TRACE_EVENT(i915_scheduler_unfly,
> + TP_PROTO(struct intel_engine_cs *ring,
> + struct i915_scheduler_queue_entry *node),
> + TP_ARGS(ring, node),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->uniq = node ? node->params.request->uniq : 0;
> + __entry->seqno = node ? node->params.request->seqno : 0;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d",
> + __entry->ring, __entry->uniq, __entry->seqno)
> +);
> +
> +TRACE_EVENT(i915_scheduler_landing,
> + TP_PROTO(struct drm_i915_gem_request *req),
> + TP_ARGS(req),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + __field(u32, status)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = req->ring->id;
> + __entry->uniq = req->uniq;
> + __entry->seqno = req->seqno;
> + __entry->status = req->scheduler_qe ?
> + req->scheduler_qe->status : ~0U;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d, status=%d",
> + __entry->ring, __entry->uniq, __entry->seqno,
> + __entry->status)
> +);
> +
> +TRACE_EVENT(i915_scheduler_remove,
> + TP_PROTO(struct intel_engine_cs *ring,
> + u32 min_seqno, bool do_submit),
> + TP_ARGS(ring, min_seqno, do_submit),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, min_seqno)
> + __field(bool, do_submit)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->min_seqno = min_seqno;
> + __entry->do_submit = do_submit;
> + ),
> +
> + TP_printk("ring=%d, min_seqno = %d, do_submit=%d",
> + __entry->ring, __entry->min_seqno, __entry->do_submit)
> +);
> +
> +TRACE_EVENT(i915_scheduler_destroy,
> + TP_PROTO(struct intel_engine_cs *ring,
> + struct i915_scheduler_queue_entry *node),
> + TP_ARGS(ring, node),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->uniq = node ? node->params.request->uniq : 0;
> + __entry->seqno = node ? node->params.request->seqno : 0;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d",
> + __entry->ring, __entry->uniq, __entry->seqno)
> +);
> +
> +TRACE_EVENT(i915_scheduler_pop_from_queue,
> + TP_PROTO(struct intel_engine_cs *ring,
> + struct i915_scheduler_queue_entry *node),
> + TP_ARGS(ring, node),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->uniq = node ? node->params.request->uniq : 0;
> + __entry->seqno = node ? node->params.request->seqno : 0;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d",
> + __entry->ring, __entry->uniq, __entry->seqno)
> +);
> +
> +TRACE_EVENT(i915_scheduler_node_state_change,
> + TP_PROTO(struct intel_engine_cs *ring,
> + struct i915_scheduler_queue_entry *node),
> + TP_ARGS(ring, node),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + __field(u32, status)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->uniq = node ? node->params.request->uniq : 0;
> + __entry->seqno = node->params.request->seqno;
> + __entry->status = node->status;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d, status=%d",
> + __entry->ring, __entry->uniq, __entry->seqno,
> + __entry->status)
> +);
> +
> +TRACE_EVENT(i915_gem_ring_queue,
> + TP_PROTO(struct intel_engine_cs *ring,
> + struct i915_execbuffer_params *params),
> + TP_ARGS(ring, params),
> +
> + TP_STRUCT__entry(
> + __field(u32, ring)
> + __field(u32, uniq)
> + __field(u32, seqno)
> + ),
> +
> + TP_fast_assign(
> + __entry->ring = ring->id;
> + __entry->uniq = params->request->uniq;
> + __entry->seqno = params->request->seqno;
> + ),
> +
> + TP_printk("ring=%d, uniq=%d, seqno=%d", __entry->ring,
> + __entry->uniq, __entry->seqno)
> +);
> +
> #endif /* _I915_TRACE_H_ */
>
> /* This part must be outside protection */
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 9c7a79a..2b9f49c 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -954,6 +954,8 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
>
> i915_gem_execbuffer_move_to_active(vmas, params->request);
>
> + trace_i915_gem_ring_queue(ring, params);
> +
> qe = container_of(params, typeof(*qe), params);
> ret = i915_scheduler_queue_execbuffer(qe);
> if (ret)
>
Looks fine.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2016-02-23 20:42 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-18 14:26 [PATCH v5 00/35] GPU scheduler for i915 driver John.C.Harrison
2016-02-18 14:26 ` [PATCH v5 01/35] drm/i915: Add total count to context status debugfs output John.C.Harrison
2016-02-18 14:26 ` [PATCH v5 02/35] drm/i915: Prelude to splitting i915_gem_do_execbuffer in two John.C.Harrison
2016-02-18 14:26 ` [PATCH v5 03/35] drm/i915: Split i915_dem_do_execbuffer() in half John.C.Harrison
2016-02-18 14:26 ` [PATCH v5 04/35] drm/i915: Cache request pointer in *_submission_final() John.C.Harrison
2016-02-18 14:26 ` [PATCH v5 05/35] drm/i915: Re-instate request->uniq because it is extremely useful John.C.Harrison
2016-02-18 14:26 ` [PATCH v5 06/35] drm/i915: Start of GPU scheduler John.C.Harrison
2016-02-19 13:03 ` Joonas Lahtinen
2016-02-19 17:03 ` John Harrison
2016-02-26 9:13 ` Joonas Lahtinen
2016-02-26 14:18 ` John Harrison
2016-02-18 14:26 ` [PATCH v5 07/35] drm/i915: Prepare retire_requests to handle out-of-order seqnos John.C.Harrison
2016-02-19 19:23 ` Jesse Barnes
2016-02-18 14:26 ` [PATCH v5 08/35] drm/i915: Disable hardware semaphores when GPU scheduler is enabled John.C.Harrison
2016-02-19 19:27 ` Jesse Barnes
2016-02-18 14:26 ` [PATCH v5 09/35] drm/i915: Force MMIO flips when scheduler enabled John.C.Harrison
2016-02-19 19:28 ` Jesse Barnes
2016-02-19 19:53 ` Ville Syrjälä
2016-02-19 20:01 ` Jesse Barnes
2016-02-22 9:41 ` Lankhorst, Maarten
2016-02-22 12:53 ` John Harrison
2016-02-20 9:22 ` Chris Wilson
2016-02-22 20:42 ` Jesse Barnes
2016-02-23 11:16 ` Chris Wilson
2016-02-18 14:26 ` [PATCH v5 10/35] drm/i915: Added scheduler hook when closing DRM file handles John.C.Harrison
2016-03-01 8:59 ` Joonas Lahtinen
2016-03-01 14:52 ` John Harrison
2016-02-18 14:26 ` [PATCH v5 11/35] drm/i915: Added scheduler hook into i915_gem_request_notify() John.C.Harrison
2016-03-01 9:10 ` Joonas Lahtinen
2016-02-18 14:27 ` [PATCH v5 12/35] drm/i915: Added deferred work handler for scheduler John.C.Harrison
2016-03-01 9:16 ` Joonas Lahtinen
2016-03-01 15:12 ` John Harrison
2016-02-18 14:27 ` [PATCH v5 13/35] drm/i915: Redirect execbuffer_final() via scheduler John.C.Harrison
2016-02-19 19:33 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 14/35] drm/i915: Keep the reserved space mechanism happy John.C.Harrison
2016-02-19 19:36 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 15/35] drm/i915: Added tracking/locking of batch buffer objects John.C.Harrison
2016-02-19 19:42 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 16/35] drm/i915: Hook scheduler node clean up into retire requests John.C.Harrison
2016-02-19 19:44 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 17/35] drm/i915: Added scheduler support to __wait_request() calls John.C.Harrison
2016-03-01 10:02 ` Joonas Lahtinen
2016-03-11 11:47 ` John Harrison
2016-02-18 14:27 ` [PATCH v5 18/35] drm/i915: Added scheduler support to page fault handler John.C.Harrison
2016-02-19 19:45 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 19/35] drm/i915: Added scheduler flush calls to ring throttle and idle functions John.C.Harrison
2016-03-07 11:31 ` Joonas Lahtinen
2016-03-11 16:22 ` John Harrison
2016-02-18 14:27 ` [PATCH v5 20/35] drm/i915: Add scheduler hook to GPU reset John.C.Harrison
2016-02-23 20:27 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 21/35] drm/i915: Added a module parameter to allow the scheduler to be disabled John.C.Harrison
2016-02-23 20:29 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 22/35] drm/i915: Support for 'unflushed' ring idle John.C.Harrison
2016-02-23 20:35 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 23/35] drm/i915: Defer seqno allocation until actual hardware submission time John.C.Harrison
2016-03-07 12:16 ` Joonas Lahtinen
2016-02-18 14:27 ` [PATCH v5 24/35] drm/i915: Added trace points to scheduler John.C.Harrison
2016-02-23 20:42 ` Jesse Barnes [this message]
2016-02-23 20:42 ` Jesse Barnes
2016-02-26 15:55 ` John Harrison
2016-02-26 17:12 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 25/35] drm/i915: Added scheduler queue throttling by DRM file handle John.C.Harrison
2016-02-23 21:02 ` Jesse Barnes
2016-03-01 15:52 ` John Harrison
2016-02-18 14:27 ` [PATCH v5 26/35] drm/i915: Added debugfs interface to scheduler tuning parameters John.C.Harrison
2016-02-23 21:06 ` Jesse Barnes
2016-03-11 16:28 ` John Harrison
2016-03-11 17:25 ` Jesse Barnes
2016-02-18 14:27 ` [PATCH v5 27/35] drm/i915: Added debug state dump facilities to scheduler John.C.Harrison
2016-03-07 12:31 ` Joonas Lahtinen
2016-03-11 16:38 ` John Harrison
2016-03-15 10:53 ` Joonas Lahtinen
2016-02-18 14:27 ` [PATCH v5 28/35] drm/i915: Add early exit to execbuff_final() if insufficient ring space John.C.Harrison
2016-02-18 14:27 ` [PATCH v5 29/35] drm/i915: Added scheduler statistic reporting to debugfs John.C.Harrison
2016-02-18 14:27 ` [PATCH v5 30/35] drm/i915: Add scheduler support functions for TDR John.C.Harrison
2016-02-18 14:27 ` [PATCH v5 31/35] drm/i915: Scheduler state dump via debugfs John.C.Harrison
2016-02-18 14:27 ` [PATCH v5 32/35] drm/i915: Enable GPU scheduler by default John.C.Harrison
2016-02-18 14:27 ` [PATCH v5 33/35] drm/i915: Add scheduling priority to per-context parameters John.C.Harrison
2016-02-18 14:27 ` [PATCH v5 34/35] drm/i915: Add support for retro-actively banning batch buffers John.C.Harrison
2016-02-18 14:27 ` [PATCH v5 35/35] drm/i915: Allow scheduler to manage inter-ring object synchronisation John.C.Harrison
2016-02-18 14:27 ` [PATCH 01/20] igt/gem_ctx_param_basic: Updated to support scheduler priority interface John.C.Harrison
2016-02-18 15:30 ` ✗ Fi.CI.BAT: failure for GPU scheduler for i915 driver Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=56CCC429.30106@virtuousgeek.org \
--to=jbarnes@virtuousgeek.org \
--cc=Intel-GFX@Lists.FreeDesktop.Org \
--cc=John.C.Harrison@Intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).