
It seems commit4a9d4b024a
("switch fput to task_work_add") re- introduced the problem addressed in944be0b224
("close_files(): add scheduling point") If a server process with a lot of files (say 2 million tcp sockets) is killed, we can spend a lot of time in task_work_run() and trigger a soft lockup. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1.7 KiB
1.7 KiB