Re: [PATCH/RFC] Futex mmap_sem deadlock

[David Howells <dhowells@redhat.com>]

Olof Johansson <olof@austin.ibm.com> wrote:

> > Alternately, you could just have do_page_fault() do:
> > 
> > 	while (!down_read_trylock(&current->mm->mmap_sem))
> > 		continue;
> > 
> > However, note that this can suffer from starvation due to a never ending
> > flow of mixed write-locks and read-locks on other CPUs. Unlikely, true,
> > but not impossible.
> 
> How can this help? 
> 
> The semaphore is held for reading by the thread that faulted in
> futex_wait() -> get_user(), so no writers will be let through. Until the
> writer has been let through, the down_read_trylock will never succeed
> either. No forward progress can be made even with the above loop.

You're right. The "writers" would have to spin instead.

David