On Thu, Jun 26, 2025 at 05:49:54PM +0200, Sebastian Andrzej Siewior wrote:
> On 2025-06-26 17:29:46 [+0206], John Ogness wrote:
> > > @@ -361,10 +348,14 @@ static inline int ep_cmp_ffd(struct epoll_filefd *p1,
> > > (p1->file < p2->file ? -1 : p1->fd - p2->fd));
> > > }
> > >
> > > -/* Tells us if the item is currently linked */
> > > -static inline int ep_is_linked(struct epitem *epi)
> > > +/*
> > > + * Add the item to its container eventpoll's rdllist; do nothing if the item is already on rdllist.
> > > + */
> > > +static void epitem_ready(struct epitem *epi)
> > > {
> > > - return !list_empty(&epi->rdllink);
> > > + if (&epi->rdllink == cmpxchg(&epi->rdllink.next, &epi->rdllink, NULL))
> >
> > Perhaps:
> >
> > if (try_cmpxchg(&epi->rdllink.next, &epi->rdllink, NULL))
>
> Not sure this is the same.
> This will write back the current value of epi->rdllink.next to
> epi->rdllink if epi->rdllink.next is not &epi->rdllink.
>
> The intention is to check if epi->rdllink.next is set to &epi->rdllink
> (pointing to itself) and if so set it NULL just to avoid to ensure
> further cmpxchg() will fail here.
Exactly, thanks Sebastian.
I tested the suggestion, and systemd blew up.
Nam
