public inbox for drm-ai-reviews@public-inbox.freedesktop.org
 help / color / mirror / Atom feed
From: Boris Brezillon <boris.brezillon@collabora.com>
To: Steven Price <steven.price@arm.com>, Liviu Dudau <liviu.dudau@arm.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>,
	Maxime Ripard <mripard@kernel.org>,
	Thomas Zimmermann <tzimmermann@suse.de>,
	David Airlie <airlied@gmail.com>, Simona Vetter <simona@ffwll.ch>,
	dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org,
	Boris Brezillon <boris.brezillon@collabora.com>
Subject: [PATCH v2 00/11] drm/panthor: Reduce dma_fence signalling latency
Date: Tue, 12 May 2026 13:37:30 +0200	[thread overview]
Message-ID: <20260512-panthor-signal-from-irq-v2-0-95c614a739cb@collabora.com> (raw)

Right now, panthor is one of the rare drivers to signal fences
from work items (not even from the threaded IRQ handler). We
could move that to the threaded handler, but that would still
leave the latency caused by the scheduling of the IRQ thread.

Instead, this patchset moves all the JOB/GPU IRQ processing to
the raw IRQ handler, which is fine because what the current
code does is demux the interrupts and defer actual handling
to sub work items. The only non-trivial thing we keep in the
IRQ path is the dma_fence signalling, which should be acceptable
in term of CPU cycles burnt in IRQ context.

Note that the MMU event handling is left in a threaded handler
because it requires acquiring sleepable locks and fixing that
is non-trivial.

Still very basic testing done, but glmark2 and gfxbench's
manhattan test show a ~5% perf improvement on a rk3588 with this
patchset applied.

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
---
Changes in v2:
- Fix commit message in patch 4
- Move devm_kasprintf() before panthor_irq_resume() in patch 3
- Fix erroneous lockdep_assert_held() in patch 6
- Make sure events_lock is held when calling
  csg_slot_sync_update_locked() in patch 6
- Restore a csg_slot_sync_update_locked() call in patch 7
- Fix a potential deadlock in patch 9
- Drop the IRQ coalescing patch (formerly patch 10)
- Change panthor_irq_request() so we don't have to define a dummy
  threaded handler, and we can let RT kernels move the hard handler
  to a thread
- Add patches to transition GPU event processing to the hard IRQ handler
- Link to v1: https://lore.kernel.org/r/20260429-panthor-signal-from-irq-v1-0-4b92ae4142d2@collabora.com

---
Boris Brezillon (11):
      drm/panthor: Make panthor_irq::state a non-atomic field
      drm/panthor: Move the register accessors before the IRQ helpers
      drm/panthor: Replace the panthor_irq macro machinery by inline helpers
      drm/panthor: Extend the IRQ logic to allow fast/hard IRQ handlers
      drm/panthor: Make panthor_fw_{update,toggle}_reqs() callable from IRQ context
      drm/panthor: Prepare the scheduler logic for FW events in IRQ context
      drm/panthor: Automate CSG IRQ processing at group unbind time
      drm/panthor: Automatically enable interrupts in panthor_fw_wait_acks()
      drm/panthor: Process FW events in IRQ context
      drm/panthor: Use the irqsave variant of spin_lock in panthor_gpu_irq_handler()
      drm/panthor: Process GPU events in IRQ context

 drivers/gpu/drm/panthor/panthor_device.h | 281 +++++++++---------
 drivers/gpu/drm/panthor/panthor_fw.c     |  76 +++--
 drivers/gpu/drm/panthor/panthor_fw.h     |   9 +-
 drivers/gpu/drm/panthor/panthor_gpu.c    |  31 +-
 drivers/gpu/drm/panthor/panthor_mmu.c    |  38 +--
 drivers/gpu/drm/panthor/panthor_pwr.c    |  21 +-
 drivers/gpu/drm/panthor/panthor_sched.c  | 483 ++++++++++++++-----------------
 7 files changed, 476 insertions(+), 463 deletions(-)
---
base-commit: ac5ac0acf11df04295eb1811066097b7022d6c7f
change-id: 20260429-panthor-signal-from-irq-d33684f4d292

Best regards,
-- 
Boris Brezillon <boris.brezillon@collabora.com>


             reply	other threads:[~2026-05-12 11:37 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-12 11:37 Boris Brezillon [this message]
2026-05-12 11:37 ` [PATCH v2 01/11] drm/panthor: Make panthor_irq::state a non-atomic field Boris Brezillon
2026-05-12 18:40   ` Chia-I Wu
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 02/11] drm/panthor: Move the register accessors before the IRQ helpers Boris Brezillon
2026-05-12 18:41   ` Chia-I Wu
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 03/11] drm/panthor: Replace the panthor_irq macro machinery by inline helpers Boris Brezillon
2026-05-12 18:58   ` Chia-I Wu
2026-05-13  8:03     ` Boris Brezillon
2026-05-13 16:46       ` Chia-I Wu
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 04/11] drm/panthor: Extend the IRQ logic to allow fast/hard IRQ handlers Boris Brezillon
2026-05-12 19:11   ` Chia-I Wu
2026-05-13  8:09     ` Boris Brezillon
2026-05-13 17:06       ` Chia-I Wu
2026-05-13 17:30         ` Boris Brezillon
2026-05-13 18:17           ` Chia-I Wu
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 05/11] drm/panthor: Make panthor_fw_{update,toggle}_reqs() callable from IRQ context Boris Brezillon
2026-05-12 19:29   ` [PATCH v2 05/11] drm/panthor: Make panthor_fw_{update, toggle}_reqs() " Chia-I Wu
2026-05-16  3:32   ` Claude review: drm/panthor: Make panthor_fw_{update,toggle}_reqs() " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 06/11] drm/panthor: Prepare the scheduler logic for FW events in " Boris Brezillon
2026-05-12 21:04   ` Chia-I Wu
2026-05-13  8:29     ` Boris Brezillon
2026-05-13 17:47       ` Chia-I Wu
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 07/11] drm/panthor: Automate CSG IRQ processing at group unbind time Boris Brezillon
2026-05-12 21:16   ` Chia-I Wu
2026-05-14 14:17   ` Steven Price
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 08/11] drm/panthor: Automatically enable interrupts in panthor_fw_wait_acks() Boris Brezillon
2026-05-12 21:55   ` Chia-I Wu
2026-05-13  8:42     ` Boris Brezillon
2026-05-13 17:14       ` Chia-I Wu
2026-05-14 14:25   ` Steven Price
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 09/11] drm/panthor: Process FW events in IRQ context Boris Brezillon
2026-05-12 22:05   ` Chia-I Wu
2026-05-12 22:09     ` Chia-I Wu
2026-05-13  8:44       ` Boris Brezillon
2026-05-14 15:23   ` Steven Price
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 10/11] drm/panthor: Use the irqsave variant of spin_lock in panthor_gpu_irq_handler() Boris Brezillon
2026-05-14 15:26   ` Steven Price
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-12 11:37 ` [PATCH v2 11/11] drm/panthor: Process GPU events in IRQ context Boris Brezillon
2026-05-12 11:50   ` Boris Brezillon
2026-05-12 22:40     ` Chia-I Wu
2026-05-13  8:54       ` Boris Brezillon
2026-05-13 18:07         ` Chia-I Wu
2026-05-16  3:32   ` Claude review: " Claude Code Review Bot
2026-05-16  3:32 ` Claude review: drm/panthor: Reduce dma_fence signalling latency Claude Code Review Bot

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=20260512-panthor-signal-from-irq-v2-0-95c614a739cb@collabora.com \
    --to=boris.brezillon@collabora.com \
    --cc=airlied@gmail.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=liviu.dudau@arm.com \
    --cc=maarten.lankhorst@linux.intel.com \
    --cc=mripard@kernel.org \
    --cc=simona@ffwll.ch \
    --cc=steven.price@arm.com \
    --cc=tzimmermann@suse.de \
    /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