From: Ville Syrjala <ville.syrjala@linux.intel.com>
To: intel-gfx@lists.freedesktop.org
Cc: intel-xe@lists.freedesktop.org
Subject: [PATCH v2 12/13] drm/i915/dsb: Add tracepoints for DSB commit
Date: Wed, 9 Sep 2026 19:17:29 +0300 [thread overview]
Message-ID: <20260909161730.12969-13-ville.syrjala@linux.intel.com> (raw)
In-Reply-To: <20260909161730.12969-1-ville.syrjala@linux.intel.com>
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Currently DSB based commits don't leave any breadcrumbs via
tracepoints. Add new intel_dsb_commit and intel_dsb_done
tracepoints that at least indicates when the DSB does something.
We might want to improve this later somehow to have a slightly
better idea what the DSB might end up doing. But at least this
now shows that *something* is happening on the hardware.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
.../drm/i915/display/intel_display_trace.h | 51 +++++++++++++++++++
drivers/gpu/drm/i915/display/intel_dsb.c | 5 ++
2 files changed, 56 insertions(+)
diff --git a/drivers/gpu/drm/i915/display/intel_display_trace.h b/drivers/gpu/drm/i915/display/intel_display_trace.h
index 504d105935bc..06cf662931fe 100644
--- a/drivers/gpu/drm/i915/display/intel_display_trace.h
+++ b/drivers/gpu/drm/i915/display/intel_display_trace.h
@@ -22,6 +22,7 @@
#include "intel_display_core.h"
#include "intel_display_limits.h"
#include "intel_display_types.h"
+#include "intel_dsb.h"
#include "intel_vblank.h"
#define __dev_name_display(display) dev_name((display)->drm->dev)
@@ -681,6 +682,56 @@ TRACE_EVENT(intel_fbc_nuke,
__entry->frame, __entry->scanline)
);
+TRACE_EVENT(intel_dsb_commit,
+ TP_PROTO(struct intel_crtc *crtc, enum intel_dsb_id dsb_id),
+ TP_ARGS(crtc, dsb_id),
+
+ TP_STRUCT__entry(
+ __string(dev, __dev_name_kms(crtc))
+ __field(char, pipe_name)
+ __field(u32, dsb_id)
+ __field(u32, frame)
+ __field(u32, scanline)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev);
+ __entry->pipe_name = pipe_name(crtc->pipe);
+ __entry->dsb_id = dsb_id;
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
+ __entry->scanline = intel_get_crtc_scanline(crtc);
+ ),
+
+ TP_printk("dev %s, pipe %c, DSB %d, frame=%u, scanline=%u",
+ __get_str(dev), __entry->pipe_name, __entry->dsb_id,
+ __entry->frame, __entry->scanline)
+);
+
+TRACE_EVENT(intel_dsb_done,
+ TP_PROTO(struct intel_crtc *crtc, enum intel_dsb_id dsb_id),
+ TP_ARGS(crtc, dsb_id),
+
+ TP_STRUCT__entry(
+ __string(dev, __dev_name_kms(crtc))
+ __field(char, pipe_name)
+ __field(u32, dsb_id)
+ __field(u32, frame)
+ __field(u32, scanline)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev);
+ __entry->pipe_name = pipe_name(crtc->pipe);
+ __entry->dsb_id = dsb_id;
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
+ __entry->scanline = intel_get_crtc_scanline(crtc);
+ ),
+
+ TP_printk("dev %s, pipe %c, DSB %d, frame=%u, scanline=%u",
+ __get_str(dev), __entry->pipe_name, __entry->dsb_id,
+ __entry->frame, __entry->scanline)
+);
+
TRACE_EVENT(intel_crtc_vblank_work_start,
TP_PROTO(struct intel_crtc *crtc),
TP_ARGS(crtc),
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 8e01e1eed291..299d778520a2 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -14,6 +14,7 @@
#include "intel_de.h"
#include "intel_display_regs.h"
#include "intel_display_rpm.h"
+#include "intel_display_trace.h"
#include "intel_display_types.h"
#include "intel_dsb.h"
#include "intel_dsb_regs.h"
@@ -982,6 +983,8 @@ void intel_dsb_commit(struct intel_dsb *dsb)
intel_de_write_fw(display, DSB_HEAD(pipe, dsb->id),
intel_dsb_head(dsb));
+ trace_intel_dsb_commit(crtc, dsb->id);
+
intel_de_write_fw(display, DSB_TAIL(pipe, dsb->id),
intel_dsb_tail(dsb));
}
@@ -1124,6 +1127,8 @@ void intel_dsb_irq_handler(struct intel_display *display,
spin_lock(&display->drm->event_lock);
if (crtc->dsb_event) {
+ trace_intel_dsb_done(crtc, dsb_id);
+
/*
* Update vblank counter/timestamp in case it
* hasn't been done yet for this frame.
--
2.54.0
next prev parent reply other threads:[~2026-09-09 16:18 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-09 16:17 [PATCH v2 00/13] drm/i915: Some DSB/flipq stuff Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 01/13] drm/i915: Give up on DSB/flip queue if we fail to allocate the color DSB buffer Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 02/13] drm/i915: Check use_flipq in intel_crtc_needs_vblank_work() Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 03/13] drm/i915: Don't initialize flip queue on pre-LNL Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 04/13] drm/i915: Warn about use_flip==true in MMIO commit codepaths Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 05/13] drm/i915: Refine vblank evasion DSB check Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 06/13] drm/i915: Make intel_crtc_needs_vblank_work() easier on the eye Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 07/13] drm/i915: Extract intel_dsb_supported() Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 08/13] drm/i915: Use intel_dsb_supported() to determine 'use_dsb' Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 09/13] drm/i915: Extract commit_dsb_max_cmds() Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 10/13] drm/i915: Introduce enum intel_commit_type Ville Syrjala
2026-09-09 16:17 ` [PATCH v2 11/13] drm/i915: Carve intel_atomic_commit_type() up a bit Ville Syrjala
2026-09-09 16:17 ` Ville Syrjala [this message]
2026-09-09 16:34 ` [PATCH v2 12/13] drm/i915/dsb: Add tracepoints for DSB commit sashiko-bot
2026-09-10 11:23 ` Ville Syrjälä
2026-09-09 16:17 ` [PATCH v2 13/13] drm/i915/dsb: Add tracepoints for flip queue Ville Syrjala
2026-09-09 16:25 ` ✗ CI.checkpatch: warning for drm/i915: Some DSB/flipq stuff (rev2) Patchwork
2026-09-09 16:27 ` ✓ CI.KUnit: success " Patchwork
2026-09-09 17:11 ` ✓ Xe.CI.BAT: " Patchwork
2026-09-10 0:25 ` ✗ Xe.CI.FULL: failure " 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=20260909161730.12969-13-ville.syrjala@linux.intel.com \
--to=ville.syrjala@linux.intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
/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).