Re: [PATCH] locking/qrwlock: Fix ordering in queued_write_lock_slowpath

[Ali Saidi <alisaidi@amazon.com>]

On Thu, 15 Apr 2021 16:02:29 +0100, Will Deacon wrote:
> On Thu, Apr 15, 2021 at 02:25:52PM +0000, Ali Saidi wrote:
> > While this code is executed with the wait_lock held, a reader can
> > acquire the lock without holding wait_lock.  The writer side loops
> > checking the value with the atomic_cond_read_acquire(), but only truly
> > acquires the lock when the compare-and-exchange is completed
> > successfully which isn’t ordered. The other atomic operations from this
> > point are release-ordered and thus reads after the lock acquisition can
> > be completed before the lock is truly acquired which violates the
> > guarantees the lock should be making.
> 
> I think it would be worth spelling this out with an example. The issue
> appears to be a concurrent reader in interrupt context taking and releasing
> the lock in the window where the writer has returned from the
> atomic_cond_read_acquire() but has not yet performed the cmpxchg(). Loads
> can be speculated during this time, but the A-B-A of the lock word
> from _QW_WAITING to (_QW_WAITING | _QR_BIAS) and back to _QW_WAITING allows
> the atomic_cmpxchg_relaxed() to succeed. Is that right?

You're right. What we're seeing is an A-B-A problem that can allow 
atomic_cond_read_acquire() to succeed and before the cmpxchg succeeds a reader
performs an A-B-A on the lock which allows the core to observe a read that
follows the cmpxchg ahead of the cmpxchg succeeding. 

We've seen a problem in epoll where the reader does a xchg while
holding the read lock, but the writer can see a value change out from under it. 

Writer                               | Reader 2
--------------------------------------------------------------------------------
ep_scan_ready_list()                 |
|- write_lock_irq()                  |
    |- queued_write_lock_slowpath()  |
      |- atomic_cond_read_acquire()  |
                                     | read_lock_irqsave(&ep->lock, flags);
                                     | chain_epi_lockless()
                                     |    epi->next = xchg(&ep->ovflist, epi);
                                     | read_unlock_irqrestore(&ep->lock, flags);
                                     |       
         atomic_cmpxchg_relaxed()    |
  READ_ONCE(ep->ovflist);    

> 
> With that in mind, it would probably be a good idea to eyeball the qspinlock
> slowpath as well, as that uses both atomic_cond_read_acquire() and
> atomic_try_cmpxchg_relaxed().

It seems plausible that the same thing could occur here in qspinlock:
          if ((val & _Q_TAIL_MASK) == tail) {
                  if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
                          goto release; /* No contention */
          }

> 
> > Fixes: b519b56e378ee ("locking/qrwlock: Use atomic_cond_read_acquire() when spinning in qrwloc")

Ack, will fix. 

> Typo in the quoted subject ('qrwloc').
> 
> > Signed-off-by: Ali Saidi <alisaidi@amazon.com>
> > Cc: stable@vger.kernel.org
> > ---
> >  kernel/locking/qrwlock.c | 4 ++--
> >  1 file changed, 2 insertions(+), 2 deletions(-)
> > 
> > diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
> > index 4786dd271b45..10770f6ac4d9 100644
> > --- a/kernel/locking/qrwlock.c
> > +++ b/kernel/locking/qrwlock.c
> > @@ -73,8 +73,8 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
> >  
> >  	/* When no more readers or writers, set the locked flag */
> >  	do {
> > -		atomic_cond_read_acquire(&lock->cnts, VAL == _QW_WAITING);
> > -	} while (atomic_cmpxchg_relaxed(&lock->cnts, _QW_WAITING,
> > +		atomic_cond_read_relaxed(&lock->cnts, VAL == _QW_WAITING);
> > +	} while (atomic_cmpxchg_acquire(&lock->cnts, _QW_WAITING,
> >  					_QW_LOCKED) != _QW_WAITING);
> 
> Patch looks good, so with an updated message:
> 
> Acked-by: Will Deacon <will@kernel.org>
> 
> Will