AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: James Zhu <James.Zhu@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: Felix.kuehling@amd.com, jamesz@amd.com
Subject: [PATCH v3 0/5] new event wait support
Date: Thu, 8 Jun 2023 13:07:00 -0400	[thread overview]
Message-ID: <20230608170705.2271276-1-James.Zhu@amd.com> (raw)

In kernel amdgpu driver, kfd_wait_on_events is used to support user space signal event wait
function. For multiple threads waiting on same event scenery, race condition could occur
since some threads after checking signal condition, before calling kfd_wait_on_events, the
event interrupt could be fired and wake up other thread which are sleeping on this event.
Then those threads could fall into sleep without waking up again. Adding event age tracking
in both kernel and user mode, will help avoiding this race condition.

The changes for The user space ROCT-Thunk-Interface/ROCR-Runtime are listed below for
review togehter with kernel mode changes.

ROCT-Thunk-Interface:
https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/efdbf6cfbc026bd68ac3c35d00dacf84370eb81e
https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/910108272091d1ce61dbc48bd9519731e0e9cf52

ROCR-Runtime:
https://github.com/RadeonOpenCompute/ROCR-Runtime/compare/master...zhums:ROCR-Runtime:new_event_wait_review
https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/e1f5bdb88eb882ac798aeca2c00ea3fbb2dba459
https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/7d26afd14107b5c2a754c1a3f415d89f3aabb503

-v2: remove unnecessay link

-v3: 1. update kfd test cases (910108272091d1ce61dbc48bd9519731e0e9cf52)
     2. move event age match checking into init_event_waiter
     3. move last event age update into copy_signaled_event_data

James Zhu (5):
  drm/amdkfd: add event age tracking
  drm/amdkfd: add event_age tracking when receiving interrupt
  drm/amdkfd: set activated flag true when event age unmatchs
  drm/amdkfd: update user space last_event_age
  drm/amdkfd: bump kfd ioctl minor version for event age availability

 drivers/gpu/drm/amd/amdkfd/kfd_events.c | 44 ++++++++++++++++++-------
 drivers/gpu/drm/amd/amdkfd/kfd_events.h |  1 +
 include/uapi/linux/kfd_ioctl.h          | 13 ++++++--
 3 files changed, 44 insertions(+), 14 deletions(-)

-- 
2.34.1


             reply	other threads:[~2023-06-08 17:07 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-06-08 17:07 James Zhu [this message]
2023-06-08 17:07 ` [PATCH v3 1/5] drm/amdkfd: add event age tracking James Zhu
2023-06-08 17:07 ` [PATCH v3 2/5] drm/amdkfd: add event_age tracking when receiving interrupt James Zhu
2023-06-08 17:07 ` [PATCH v3 3/5] drm/amdkfd: set activated flag true when event age unmatchs James Zhu
2023-06-09 19:43   ` Felix Kuehling
2023-06-09 19:47     ` James Zhu
2023-06-09 20:13   ` [PATCH v4 " James Zhu
2023-06-09 20:22     ` Felix Kuehling
2023-06-09 20:27       ` James Zhu
2023-06-09 20:43   ` [PATCH v5 " James Zhu
2023-06-09 22:44     ` Felix Kuehling
2023-06-12 16:19       ` Yat Sin, David
2023-06-12 16:31         ` Felix Kuehling
2023-06-08 17:07 ` [PATCH v3 4/5] drm/amdkfd: update user space last_event_age James Zhu
2023-06-08 17:07 ` [PATCH v3 5/5] drm/amdkfd: bump kfd ioctl minor version for event age availability James Zhu

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=20230608170705.2271276-1-James.Zhu@amd.com \
    --to=james.zhu@amd.com \
    --cc=Felix.kuehling@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=jamesz@amd.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