Messages in this thread | | | Date | Wed, 4 Nov 2009 16:40:15 +0100 | From | Ingo Molnar <> | Subject | Re: [RFC,PATCH] mutex: mutex_is_owner() helper |
| |
* Eric Dumazet <eric.dumazet@gmail.com> wrote:
> mutex_is_locked() is called most of the time to check if mutex is locked by current > thread. But it's a lazy check, because mutex might be locked by another thread. > > Adds a new mutex_is_owned_by() helper, that can check ownership if CONFIG_SMP or > CONFIG_DEBUG_MUTEXES are set. > > Returns are > 0 if mutex is unlocked. > 1 if locked > -1 if not locked by designated thread. > > Last return value is possible only if CONFIG_SMP=y or CONFIG_DEBUG_MUTEXES=y > > Example of use : > > int rtnl_is_locked(void) > { > return mutex_is_locked(&rtnl_mutex); > } > -> > int rtnl_is_locked(void) > { > return mutex_is_owned_by(&rtnl_mutex, current_thread_info()) == 1; > }
To make sure this does not extend mutexes to be used a recursive mutexes, mind naming it more clearly, like debug_mutex_is_owned(), and adding a comment that says that this shouldnt be taken?
Also, it's somewhat imprecise: on !SMP && !DEBUG_MUTEXES we might return a false '1'. Which happens to work for the rtnl usecase - but might not in other cases.
Ingo
| |