On Mon, Jan 16, 2023 at 3:15 AM Hyeonggon Yoo <42.hyeyoo@xxxxxxxxx> wrote: > > On Mon, Jan 09, 2023 at 12:53:36PM -0800, Suren Baghdasaryan wrote: > > diff --git a/include/linux/mm.h b/include/linux/mm.h > > index d40bf8a5e19e..294dd44b2198 100644 > > --- a/include/linux/mm.h > > +++ b/include/linux/mm.h > > @@ -627,12 +627,16 @@ static inline void vma_write_lock(struct vm_area_struct *vma) > > * mm->mm_lock_seq can't be concurrently modified. > > */ > > mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); > > - if (vma->vm_lock_seq == mm_lock_seq) > > + if (vma->vm_lock->lock_seq == mm_lock_seq) > > return; > > > > - down_write(&vma->vm_lock->lock); > > - vma->vm_lock_seq = mm_lock_seq; > > - up_write(&vma->vm_lock->lock); > > + if (atomic_cmpxchg(&vma->vm_lock->count, 0, -1)) > > + wait_event(vma->vm_mm->vma_writer_wait, > > + atomic_cmpxchg(&vma->vm_lock->count, 0, -1) == 0); > > + vma->vm_lock->lock_seq = mm_lock_seq; > > + /* Write barrier to ensure lock_seq change is visible before count */ > > + smp_wmb(); > > + atomic_set(&vma->vm_lock->count, 0); > > } > > > > /* > > @@ -643,20 +647,28 @@ static inline void vma_write_lock(struct vm_area_struct *vma) > > static inline bool vma_read_trylock(struct vm_area_struct *vma) > > { > > /* Check before locking. A race might cause false locked result. */ > > - if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) > > + if (vma->vm_lock->lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) > > return false; > > > > - if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) > > + if (unlikely(!atomic_inc_unless_negative(&vma->vm_lock->count))) > > return false; > > > > + /* If atomic_t overflows, restore and fail to lock. */ > > + if (unlikely(atomic_read(&vma->vm_lock->count) < 0)) { > > + if (atomic_dec_and_test(&vma->vm_lock->count)) > > + wake_up(&vma->vm_mm->vma_writer_wait); > > + return false; > > + } > > + > > /* > > * Overflow might produce false locked result. > > * False unlocked result is impossible because we modify and check > > * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq > > * modification invalidates all existing locks. > > */ > > - if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { > > - up_read(&vma->vm_lock->lock); > > + if (unlikely(vma->vm_lock->lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { > > + if (atomic_dec_and_test(&vma->vm_lock->count)) > > + wake_up(&vma->vm_mm->vma_writer_wait); > > return false; > > } > > With this change readers can cause writers to starve. > What about checking waitqueue_active() before or after increasing > vma->vm_lock->count? The readers are in page fault path, which is the fast path, while writers performing updates are in slow path. Therefore I *think* starving writers should not be a big issue. So far in benchmarks I haven't seen issues with that but maybe there is such a case? > > -- > Thanks, > Hyeonggon > > -- > To unsubscribe from this group and stop receiving emails from it, send an email to kernel-team+unsubscribe@xxxxxxxxxxx. >