Re: context switch within RCU read-side critical section in next-20260518+ with PREEMPT_RT
From: Bert Karwatzki
Date: Thu May 21 2026 - 06:24:35 EST
Am Donnerstag, dem 21.05.2026 um 12:17 +0200 schrieb Thomas Gleixner:
> On Thu, May 21 2026 at 11:20, Bert Karwatzki wrote:
> > Am Donnerstag, dem 21.05.2026 um 11:09 +0200 schrieb Mateusz Guzik:
> >
> > with next-20260519 (no RT, no LOCKDEP) and got no crash so far (4 boots only though (next-20260619
> > crashed in 2 out of 3 boots without RT)) but I get this warning on every boot:
> >
> > [ 2.793416] [ T331] ------------[ cut here ]------------
> > [ 2.793433] [ T331] DEBUG_LOCKS_WARN_ON(lock->magic != lock)
> > [ 2.793434] [ T331] WARNING: kernel/locking/mutex.c:625 at __mutex_lock+0x586/0x10c0, CPU#17: (udev-worker)/331
>
> So either the mutex is corrupted or was never initialized.
>
> > [ 2.793463] [ T331] Modules linked in: amdgpu(+) hid_generic usbhid drm_client_lib i2c_algo_bit drm_buddy hid drm_ttm_helper ttm drm_exec
> > drm_suballoc_helper mfd_core drm_panel_backlight_quirks gpu_sched amdxcp drm_display_helper drm_kms_helper ahci libahci xhci_pci libata xhci_hcd drm nvme
> > scsi_mod igc usbcore nvme_core scsi_common video nvme_keyring i2c_piix4 cec nvme_auth usb_common crc16 i2c_smbus wmi gpio_amdpt gpio_generic
> > [ 2.793518] [ T331] CPU: 17 UID: 0 PID: 331 Comm: (udev-worker) Not tainted 7.1.0-rc4-next-20260519-rcunortlockdep-dirty #465 PREEMPT
> > [ 2.793534] [ T331] Hardware name: ASUS System Product Name/ROG STRIX B850-F GAMING WIFI, BIOS 1627 02/05/2026
> > [ 2.793547] [ T331] RIP: 0010:__mutex_lock+0x58d/0x10c0
> > [ 2.793555] [ T331] Code: 4c 8b 4d 88 85 c0 0f 84 f8 fa ff ff 44 8b 15 ca 9b 81 00 45 85 d2 0f 85 e8 fa ff ff 48 8d 3d 1a 57 82 00 48 c7 c6 a6 51 9e 83
> > <67> 48 0f b9 3a 4c 8b 4d 88 e9 cc fa ff ff 48 8b bd 78 ff ff ff e8
> > [ 2.793579] [ T331] RSP: 0018:ffffa497016c3510 EFLAGS: 00010246
> > [ 2.793588] [ T331] RAX: 0000000000000001 RBX: ffff88c33a4c2ad8 RCX: 0000000000000000
> > [ 2.793598] [ T331] RDX: 0000000000000001 RSI: ffffffff839e51a6 RDI: ffffffff83de3c00
> > [ 2.793609] [ T331] RBP: ffffa497016c35c0 R08: ffffffffc0a55d92 R09: 0000000000000000
> > [ 2.793619] [ T331] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
> > [ 2.793629] [ T331] R13: 0000000000000002 R14: ffffa497016c3550 R15: 0000000000268000
> > [ 2.793641] [ T331] FS: 00007f1f32e5b9c0(0000) GS:ffff88d23b2ca000(0000) knlGS:0000000000000000
> > [ 2.793653] [ T331] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > [ 2.793662] [ T331] CR2: 000055cdfa28f588 CR3: 0000000112e73000 CR4: 0000000000f50ef0
> > [ 2.793673] [ T331] PKRU: 55555554
> > [ 2.793678] [ T331] Call Trace:
> > [ 2.793683] [ T331] <TASK>
> > [ 2.793687] [ T331] ? lock_acquire+0xbe/0x2d0
> > [ 2.793696] [ T331] ? init_mqd+0x122/0x190 [amdgpu]
> > [ 2.793809] [ T331] ? lock_release+0xc6/0x2a0
> > [ 2.793816] [ T331] ? init_mqd+0x122/0x190 [amdgpu]
> > [ 2.793902] [ T331] init_mqd+0x122/0x190 [amdgpu]
> > [ 2.793961] [ T331] init_mqd_hiq+0xd/0x20 [amdgpu]
> > [ 2.794015] [ T331] kq_initialize.constprop.0+0x2b8/0x370 [amdgpu]
> > [ 2.794071] [ T331] kernel_queue_init+0x3f/0x60 [amdgpu]
> > [ 2.794125] [ T331] pm_init+0x6b/0x100 [amdgpu]
> > [ 2.794178] [ T331] start_cpsch+0x1d6/0x270 [amdgpu]
> > [ 2.794234] [ T331] kgd2kfd_device_init.cold+0x7b9/0xa1a [amdgpu]
> > [ 2.794365] [ T331] amdgpu_amdkfd_device_init+0x190/0x260 [amdgpu]
>
> amdgpu_amdkfd_device_init()
> kgd2kfd_device_init() {
> ....
> init_mqd()
> mutex_lock(... profiler_lock); <- FAIL
>
> mutex_init(...profiler_lock);
> }
>
> Seems the famous graphics CI failed to catch this...
>
> Thanks,
>
> tglx
> ---
> --- 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);
Actually, when I test next-20260519 with the improved fix, I do not see
the warning from amdgpu.
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 771fc31a69b8..712316a1e3e0 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -269,7 +269,7 @@ static __cold noinline int regen_filesystems_string(void)
hlist_for_each_entry_rcu(p, &file_systems, list) {
if (!(p->fs_flags & FS_REQUIRES_DEV))
newlen += strlen("nodev");
- newlen += strlen("\t") + strlen(p->name) + strlen("\n");
+ newlen += strlen("\t") + strlen(p->name) + strlen("\n");
}
spin_unlock(&file_systems_lock);
@@ -289,6 +289,7 @@ static __cold noinline int regen_filesystems_string(void)
* Did someone beat us to it?
*/
if (old && old->gen == file_systems_gen) {
+ spin_unlock(&file_systems_lock);
kfree(new);
return 0;
}
@@ -297,6 +298,7 @@ static __cold noinline int regen_filesystems_string(void)
* Did the list change in the meantime?
*/
if (gen != file_systems_gen) {
+ spin_unlock(&file_systems_lock);
kfree(new);
goto retry;
}
@@ -321,13 +323,12 @@ static __cold noinline int regen_filesystems_string(void)
* generation above and messes it up.
*/
spin_unlock(&file_systems_lock);
- if (old)
- kfree_rcu(old, rcu);
+ kfree(new);
return -EINVAL;
}
/*
- * Paired with consume fence in READ_ONCE() in filesystems_proc_show()
+ * Paired with consume fence in rcu_dereference() in filesystems_proc_show()
*/
smp_store_release(&file_systems_string, new);
spin_unlock(&file_systems_lock);
Bert Karwatzki