From: Thomas Gleixner <tglx@kernel.org>
To: Bert Karwatzki <spasswolf@web.de>
Cc: linux-kernel@vger.kernel.org,
Alex Deucher <alexander.deucher@amd.com>,
amd-gfx@lists.freedesktop.org,
Felix Kuehling <Felix.Kuehling@amd.com>
Subject: [PATCH] amd/amdkfd: Initialize kfd_dev::profiler lock early
Date: Thu, 21 May 2026 14:55:37 +0200 [thread overview]
Message-ID: <87wlwwvs52.ffs@tglx> (raw)
In-Reply-To: <878q9dvzh0.ffs@tglx>
Bert reported the following lockdep splat:
DEBUG_LOCKS_WARN_ON(lock->magic != lock)
WARNING: kernel/locking/mutex.c:625 at __mutex_lock+0x586/0x10c0, CPU#17: (udev-worker)/331
RIP: 0010:__mutex_lock+0x58d/0x10c0
init_mqd+0x122/0x190 [amdgpu]
init_mqd_hiq+0xd/0x20 [amdgpu]
kq_initialize.constprop.0+0x2b8/0x370 [amdgpu]
kernel_queue_init+0x3f/0x60 [amdgpu]
pm_init+0x6b/0x100 [amdgpu]
start_cpsch+0x1d6/0x270 [amdgpu]
kgd2kfd_device_init.cold+0x7b9/0xa1a [amdgpu]
amdgpu_amdkfd_device_init+0x190/0x260 [amdgpu]
amdgpu_device_init.cold+0x1952/0x1c79 [amdgpu]
amdgpu_driver_load_kms+0x14/0x80 [amdgpu]
Some implementations of init_mqd() acquire kfd_dev->profile_lock, which is
initialized in kgd2kfd_device_init() after init_mqd() was invoked via the
above callchain. So init_mqd() tries to lock an uninitialized mutex.
Move the initialization to the beginning of kgd2kfd_device_init() to cure
that.
Fixes: a789761de305 ("amd/amdkfd: Add kfd_ioctl_profiler to contain profiler kernel driver changes")
Reported-by: Bert Karwatzki <spasswolf@web.de>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: Benjamin Welton <bewelton@amd.com>
Closes: https://lore.kernel.org/lkml/4f548d61b2dd12e01f401ce4b8c865f238f7b23c.camel@web.de/
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -744,6 +744,9 @@ bool kgd2kfd_device_init(struct kfd_dev
KGD_ENGINE_SDMA1);
kfd->shared_resources = *gpu_resources;
+ kfd->profiler_process = NULL;
+ mutex_init(&kfd->profiler_lock);
+
kfd->num_nodes = amdgpu_xcp_get_num_xcp(kfd->adev->xcp_mgr);
if (kfd->num_nodes == 0) {
@@ -936,9 +939,6 @@ bool kgd2kfd_device_init(struct kfd_dev
svm_range_set_max_pages(kfd->adev);
- kfd->profiler_process = NULL;
- mutex_init(&kfd->profiler_lock);
-
kfd->init_complete = true;
dev_info(kfd_device, "added device %x:%x\n", kfd->adev->pdev->vendor,
kfd->adev->pdev->device);
next prev parent reply other threads:[~2026-05-21 12:55 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-20 22:52 context switch within RCU read-side critical section in next-20260518+ with PREEMPT_RT Bert Karwatzki
2026-05-21 8:37 ` Thomas Gleixner
2026-05-21 8:53 ` Mateusz Guzik
2026-05-21 9:08 ` Sebastian Andrzej Siewior
2026-05-21 9:17 ` Mateusz Guzik
2026-05-21 9:09 ` Mateusz Guzik
2026-05-21 9:20 ` Bert Karwatzki
2026-05-21 9:25 ` Mateusz Guzik
2026-05-21 9:57 ` Bert Karwatzki
2026-05-21 10:17 ` Thomas Gleixner
2026-05-21 10:21 ` Bert Karwatzki
2026-05-21 10:33 ` Mateusz Guzik
2026-05-21 11:50 ` Bert Karwatzki
2026-05-21 12:01 ` Mateusz Guzik
2026-05-28 17:59 ` Bert Karwatzki
2026-05-29 17:20 ` Mateusz Guzik
2026-05-21 12:55 ` Thomas Gleixner [this message]
2026-05-21 10:05 ` Thomas Gleixner
2026-05-21 10:13 ` Bert Karwatzki
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=87wlwwvs52.ffs@tglx \
--to=tglx@kernel.org \
--cc=Felix.Kuehling@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=spasswolf@web.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.