Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Jani Nikula <jani.nikula@linux.intel.com>
To: Radhakrishna Sripada <radhakrishna.sripada@intel.com>,
	intel-xe@lists.freedesktop.org
Cc: lucas.demarchi@intel.com,
	Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Subject: Re: [PATCH v3 0/6] Tracing cleanup and add mmio tracing
Date: Thu, 30 May 2024 18:32:55 +0300	[thread overview]
Message-ID: <87ikyvgvrs.fsf@intel.com> (raw)
In-Reply-To: <20240530151313.2284182-1-radhakrishna.sripada@intel.com>

On Thu, 30 May 2024, Radhakrishna Sripada <radhakrishna.sripada@intel.com> wrote:
> xe_trace.h is getting bloated. Group related events to their own
> files. All bo, vm and vma related events have been moved to 
> xe_trace_bo.h. GuC related trace events have been moved to
> xe_trace_guc.h. Patches 1 and 2 splits the trace events into
> seperate files.
>
> In multi gpu environments, it is important to know the device from
> which the event was triggered. Print the device id information along
> with the trace information being printed. Patches 3, 4 and 5 make
> changes to print the device id's if not already captured.
>
> Mmio reg read writes are important tracing information that needs to be
> captured and will be helpful in display debug. Patch 6 adds the reg
> read/write tracing support.
>
> Earlier versions of patch 6 can be found here:
> v1: https://patchwork.freedesktop.org/series/119312/
> v2: https://patchwork.freedesktop.org/series/132626/
>
> Radhakrishna Sripada (6):
>   drm/xe/trace: Extract bo, vm, vma traces
>   drm/xe/trace: Extract guc related traces
>   drm/xe/trace: Print device_id in xe_trace_bo events
>   drm/xe/trace: Print device_id in xe_trace_guc events
>   drm/xe/trace: Print device_id in xe_trace events
>   drm/xe: Add reg read/write trace
>
>  drivers/gpu/drm/xe/Makefile                 |   2 +
>  drivers/gpu/drm/xe/xe_bo.c                  |   2 +-
>  drivers/gpu/drm/xe/xe_gt_pagefault.c        |   2 +-
>  drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c |  27 +-
>  drivers/gpu/drm/xe/xe_guc_ct.c              |  15 +-
>  drivers/gpu/drm/xe/xe_migrate.c             |   2 +-
>  drivers/gpu/drm/xe/xe_mmio.c                |  22 +-
>  drivers/gpu/drm/xe/xe_pt.c                  |   8 +-
>  drivers/gpu/drm/xe/xe_trace.h               | 368 +++-----------------
>  drivers/gpu/drm/xe/xe_trace_bo.c            |   9 +
>  drivers/gpu/drm/xe/xe_trace_bo.h            | 244 +++++++++++++
>  drivers/gpu/drm/xe/xe_trace_guc.c           |   9 +
>  drivers/gpu/drm/xe/xe_trace_guc.h           | 107 ++++++

Seems nice. Now y'all can bikeshed whether to name them
xe_trace_foo.[ch] or xe_foo_trace.[ch]!

*ducks*

>  drivers/gpu/drm/xe/xe_vm.c                  |   2 +-
>  14 files changed, 480 insertions(+), 339 deletions(-)
>  create mode 100644 drivers/gpu/drm/xe/xe_trace_bo.c
>  create mode 100644 drivers/gpu/drm/xe/xe_trace_bo.h
>  create mode 100644 drivers/gpu/drm/xe/xe_trace_guc.c
>  create mode 100644 drivers/gpu/drm/xe/xe_trace_guc.h

-- 
Jani Nikula, Intel

  parent reply	other threads:[~2024-05-30 15:33 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-30 15:13 [PATCH v3 0/6] Tracing cleanup and add mmio tracing Radhakrishna Sripada
2024-05-30 15:13 ` [PATCH v3 1/6] drm/xe/trace: Extract bo, vm, vma traces Radhakrishna Sripada
2024-05-31 14:33   ` Gustavo Sousa
2024-05-30 15:13 ` [PATCH v3 2/6] drm/xe/trace: Extract guc related traces Radhakrishna Sripada
2024-05-31 14:34   ` Gustavo Sousa
2024-05-30 15:13 ` [PATCH v3 3/6] drm/xe/trace: Print device_id in xe_trace_bo events Radhakrishna Sripada
2024-05-31 20:07   ` Gustavo Sousa
2024-05-30 15:13 ` [PATCH v3 4/6] drm/xe/trace: Print device_id in xe_trace_guc events Radhakrishna Sripada
2024-06-03 14:16   ` Gustavo Sousa
2024-06-03 15:03     ` Sripada, Radhakrishna
2024-05-30 15:13 ` [PATCH v3 5/6] drm/xe/trace: Print device_id in xe_trace events Radhakrishna Sripada
2024-05-30 15:13 ` [PATCH v3 6/6] drm/xe: Add reg read/write trace Radhakrishna Sripada
2024-06-03 15:44   ` Gustavo Sousa
2024-06-03 15:49     ` Sripada, Radhakrishna
2024-05-30 15:32 ` Jani Nikula [this message]
2024-05-30 16:26 ` ✓ CI.Patch_applied: success for Tracing cleanup and add mmio tracing Patchwork
2024-05-30 16:27 ` ✗ CI.checkpatch: warning " Patchwork
2024-05-30 16:28 ` ✓ CI.KUnit: success " Patchwork
2024-05-30 16:39 ` ✓ CI.Build: " Patchwork
2024-05-30 16:40 ` ✗ CI.Hooks: failure " Patchwork
2024-05-30 16:41 ` ✓ CI.checksparse: success " Patchwork
2024-05-30 17:16 ` ✓ CI.BAT: " Patchwork
2024-05-30 21:22 ` ✗ CI.FULL: failure " Patchwork
2024-06-03 15:50 ` [PATCH v3 0/6] " Gustavo Sousa

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=87ikyvgvrs.fsf@intel.com \
    --to=jani.nikula@linux.intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=lucas.demarchi@intel.com \
    --cc=radhakrishna.sripada@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