On Sun, 7 Aug 2022, Matthew Wilcox wrote:
> On Sun, Aug 07, 2022 at 07:37:22AM -0400, Mikulas Patocka wrote:
> > @@ -135,6 +133,49 @@ BUFFER_FNS(Meta, meta)
> > BUFFER_FNS(Prio, prio)
> > BUFFER_FNS(Defer_Completion, defer_completion)
> >
> > +static __always_inline void set_buffer_uptodate(struct buffer_head *bh)
> > +{
> > + /*
> > + * make it consistent with folio_mark_uptodate
> > + * pairs with smp_acquire__after_ctrl_dep in buffer_uptodate
> > + */
> > + smp_wmb();
> > + set_bit(BH_Uptodate, &bh->b_state);
> > +}
> > +
> > +static __always_inline void clear_buffer_uptodate(struct buffer_head *bh)
> > +{
> > + clear_bit(BH_Uptodate, &bh->b_state);
> > +}
> > +
> > +static __always_inline int buffer_uptodate(const struct buffer_head *bh)
> > +{
> > + bool ret = test_bit(BH_Uptodate, &bh->b_state);
> > + /*
> > + * make it consistent with folio_test_uptodate
> > + * pairs with smp_wmb in set_buffer_uptodate
> > + */
> > + if (ret)
> > + smp_acquire__after_ctrl_dep();
> > + return ret;
> > +}
>
> This all works for me. While we have the experts paying attention,
> would it be better to do
>
> return smp_load_acquire(&bh->b_state) & (1L << BH_Uptodate) > 0;
Yes, it may be nicer.
> > +static __always_inline void set_buffer_locked(struct buffer_head *bh)
> > +{
> > + set_bit(BH_Lock, &bh->b_state);
> > +}
> > +
> > +static __always_inline int buffer_locked(const struct buffer_head *bh)
> > +{
> > + bool ret = test_bit(BH_Lock, &bh->b_state);
> > + /*
> > + * pairs with smp_mb__after_atomic in unlock_buffer
> > + */
> > + if (!ret)
> > + smp_acquire__after_ctrl_dep();
> > + return ret;
> > +}
>
> Are there places that think that lock/unlock buffer implies a memory
> barrier?
There's this in fs/reiserfs:
if (!buffer_dirty(bh) && !buffer_locked(bh)) {
reiserfs_free_jh(bh); <--- this could be moved before buffer_locked
if (buffer_locked((journal->j_header_bh))) {
...
}
journal->j_last_flush_trans_id = trans_id;
journal->j_first_unflushed_offset = offset;
jh = (struct reiserfs_journal_header *)(journal->j_header_bh->b_data); <--- this could be moved before buffer_locked
Mikulas
