On Fri, Aug 18, 2023 at 05:26:34PM +0800, Tong Tiangen wrote: > > > 在 2023/8/17 13:36, Naoya Horiguchi 写道: > > On Tue, Aug 15, 2023 at 09:01:54PM +0800, Tong Tiangen wrote: > > > We found a softlock issue in our test, analyzed the logs, and found that > > > the relevant CPU call trace as follows: > > > > > > CPU0: > > > _do_fork > > > -> copy_process() > > > -> write_lock_irq(&tasklist_lock) //Disable irq,waiting for > > > //tasklist_lock > > > > > > CPU1: > > > wp_page_copy() > > > ->pte_offset_map_lock() > > > -> spin_lock(&page->ptl); //Hold page->ptl > > > -> ptep_clear_flush() > > > -> flush_tlb_others() ... > > > -> smp_call_function_many() > > > -> arch_send_call_function_ipi_mask() > > > -> csd_lock_wait() //Waiting for other CPUs respond > > > //IPI > > > > > > CPU2: > > > collect_procs_anon() > > > -> read_lock(&tasklist_lock) //Hold tasklist_lock > > > ->for_each_process(tsk) > > > -> page_mapped_in_vma() > > > -> page_vma_mapped_walk() > > > -> map_pte() > > > ->spin_lock(&page->ptl) //Waiting for page->ptl > > > > > > We can see that CPU1 waiting for CPU0 respond IPI，CPU0 waiting for CPU2 > > > unlock tasklist_lock, CPU2 waiting for CPU1 unlock page->ptl. As a result, > > > softlockup is triggered. > > > > > > For collect_procs_anon(), we will not modify the tasklist, but only perform > > > read traversal. Therefore, we can use rcu lock instead of spin lock > > > tasklist_lock, from this, we can break the softlock chain above. > > > > > > The same logic can also be applied to: > > > - collect_procs_file() > > > - collect_procs_fsdax() > > > - collect_procs_ksm() > > > - find_early_kill_thread() > > > > > > Signed-off-by: Tong Tiangen <tongtiangen@xxxxxxxxxx> > > > > Hello Tiangen, thank you for finding the issue. > > mm/filemap.c mentions tasklist_lock in the comment about locking order, > > > > * ->i_mmap_rwsem > > * ->tasklist_lock (memory_failure, collect_procs_ao) > > > > so you can update this together? > > Otherwise looks good to me. > > > > Thanks, > > Naoya Horiguchi > > Thank you for your reply. Since tasklist_lock is no longer used in > collect_procs_xxx(), Should I delete these two comments in mm/filemap.c? Yes, I think you should. - Naoya Horiguchi
