* [BUG] INFO: rcu detected stall in sys_io_submit
@ 2025-05-19 4:39 Guoyu Yin
0 siblings, 0 replies; only message in thread
From: Guoyu Yin @ 2025-05-19 4:39 UTC (permalink / raw)
To: anna-maria; +Cc: frederic, tglx, linux-kernel, akpm, linux-mm
Hi,
I discovered a kernel crash using the Syzkaller framework, described
as "INFO: rcu detected stall in sys_io_submit". This issue occurs
during the execution of the sys_io_submit system call, where RCU
detects a stall on CPU 3.
From the dmesg log, CPU 3 is stuck in the enqueue_hrtimer function
(kernel/time/hrtimer.c:1085) while handling an hrtimer interrupt.
Meanwhile, the task syz-executor.1 is stuck in memory management
functions (e.g., unmap_mapping_pages, mm/memory.c:3849) during
sys_io_submit execution. This likely causes the RCU stall.
I suspect this is due to delays in hrtimer processing or prolonged
blocking in memory management operations. I recommend reviewing the
enqueue_hrtimer implementation and the interaction between
sys_io_submit, AIO, and the EXT4 filesystem.
The full dmesg log is attached. Please feel free to contact me for
additional information or reproduction steps.
This can be reproduced on:
HEAD commit:
fac04efc5c793dccbd07e2d59af9f90b7fc0dca4
report: https://pastebin.com/raw/D6PmW878
console output : https://pastebin.com/raw/qeLqJsRF
kernel config: https://pastebin.com/raw/zrj9jd1V
C reproducer : https://pastebin.com/raw/EprKHENh
Best regards,
Guoyu
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2025-05-19 4:39 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2025-05-19 4:39 [BUG] INFO: rcu detected stall in sys_io_submit Guoyu Yin
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox