lkml.org 
[lkml]   [2016]   [Dec]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH v2 05/11] locking/ww_mutex: Add waiters in stamp order
On Thu, Dec 01, 2016 at 03:06:48PM +0100, Nicolai Hähnle wrote:
> +static inline int __sched
> +__ww_mutex_add_waiter(struct mutex_waiter *waiter,
> + struct mutex *lock,
> + struct ww_acquire_ctx *ww_ctx)
> +{
> + struct mutex_waiter *cur;
> +
> + if (!ww_ctx) {
> + list_add_tail(&waiter->list, &lock->wait_list);
> + return 0;
> + }
> +
> + /*
> + * Add the waiter before the first waiter with a higher stamp.
> + * Waiters without a context are skipped to avoid starving
> + * them.
> + */
> + list_for_each_entry(cur, &lock->wait_list, list) {
> + if (!cur->ww_ctx)
> + continue;
> +
> + if (__ww_mutex_stamp_after(ww_ctx, cur->ww_ctx)) {
> + /* Back off immediately if necessary. */
> + if (ww_ctx->acquired > 0) {
> +#ifdef CONFIG_DEBUG_MUTEXES
> + struct ww_mutex *ww;
> +
> + ww = container_of(lock, struct ww_mutex, base);
> + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
> + ww_ctx->contending_lock = ww;
> +#endif
> + return -EDEADLK;
> + }
> +
> + continue;
> + }
> +
> + list_add_tail(&waiter->list, &cur->list);
> + return 0;
> + }
> +
> + list_add_tail(&waiter->list, &lock->wait_list);
> + return 0;
> +}

So you keep the list in order of stamp, and in general stamps come in,
in-order. That is, barring races on concurrent ww_mutex_lock(), things
are already ordered.

So it doesn't make sense to scan the entire list forwards, that's almost
guarantees you scan the entire list every single time.

Or am I reading this wrong? Which in itself is a hint a comment might be
in place.

\
 
 \ /
  Last update: 2016-12-06 16:37    [W:0.241 / U:3.764 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site