Re: [PATCH v2 2/3] rtmutex: update rt-mutex
From: Alex Shi
Date: Tue Jul 11 2017 - 10:37:57 EST
Any comments for this patch? or time to pick it up?
On 07/07/2017 10:52 AM, Alex Shi wrote:
> The rtmutex remove a pending owner bit in in rt_mutex::owner, in
> commit 8161239a8bcc ("rtmutex: Simplify PI algorithm and make highest prio task get lock")
> But the document was changed accordingly. Updating it to a meaningful
> BTW, as 'Steven Rostedt' mentioned:
> There is still technically a "Pending Owner", it's just not called
> that anymore. The pending owner happens to be the top_waiter of a lock
> that has no owner and has been woken up to grab the lock.
> Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Cc: Sebastian Siewior <bigeasy@xxxxxxxxxxxxx>
> Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
> Cc: Juri Lelli <juri.lelli@xxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> To: linux-doc@xxxxxxxxxxxxxxx
> To: linux-kernel@xxxxxxxxxxxxxxx
> To: Jonathan Corbet <corbet@xxxxxxx>
> To: Ingo Molnar <mingo@xxxxxxxxxx>
> To: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Documentation/locking/rt-mutex.txt | 58 +++++++++++++++++---------------------
> 1 file changed, 26 insertions(+), 32 deletions(-)
> diff --git a/Documentation/locking/rt-mutex.txt b/Documentation/locking/rt-mutex.txt
> index 243393d..35793e0 100644
> --- a/Documentation/locking/rt-mutex.txt
> +++ b/Documentation/locking/rt-mutex.txt
> @@ -28,14 +28,13 @@ magic bullet for poorly designed applications, but it allows
> well-designed applications to use userspace locks in critical parts of
> an high priority thread, without losing determinism.
> -The enqueueing of the waiters into the rtmutex waiter list is done in
> +The enqueueing of the waiters into the rtmutex waiter tree is done in
> priority order. For same priorities FIFO order is chosen. For each
> rtmutex, only the top priority waiter is enqueued into the owner's
> -priority waiters list. This list too queues in priority order. Whenever
> +priority waiters tree. This tree too queues in priority order. Whenever
> the top priority waiter of a task changes (for example it timed out or
> -got a signal), the priority of the owner task is readjusted. [The
> -priority enqueueing is handled by "plists", see include/linux/plist.h
> -for more details.]
> +got a signal), the priority of the owner task is readjusted. The
> +priority enqueueing is handled by "pi_waiters".
> RT-mutexes are optimized for fastpath operations and have no internal
> locking overhead when locking an uncontended mutex or unlocking a mutex
> @@ -46,34 +45,29 @@ is used]
> The state of the rt-mutex is tracked via the owner field of the rt-mutex
> -rt_mutex->owner holds the task_struct pointer of the owner. Bit 0 and 1
> -are used to keep track of the "owner is pending" and "rtmutex has
> -waiters" state.
> +lock->owner holds the task_struct pointer of the owner. Bit 0 is used to
> +keep track of the "lock has waiters" state.
> - owner bit1 bit0
> - NULL 0 0 mutex is free (fast acquire possible)
> - NULL 0 1 invalid state
> - NULL 1 0 Transitional state*
> - NULL 1 1 invalid state
> - taskpointer 0 0 mutex is held (fast release possible)
> - taskpointer 0 1 task is pending owner
> - taskpointer 1 0 mutex is held and has waiters
> - taskpointer 1 1 task is pending owner and mutex has waiters
> + owner bit0
> + NULL 0 lock is free (fast acquire possible)
> + NULL 1 lock is free and has waiters and the top waiter
> + is going to take the lock*
> + taskpointer 0 lock is held (fast release possible)
> + taskpointer 1 lock is held and has waiters**
> -Pending-ownership handling is a performance optimization:
> -pending-ownership is assigned to the first (highest priority) waiter of
> -the mutex, when the mutex is released. The thread is woken up and once
> -it starts executing it can acquire the mutex. Until the mutex is taken
> -by it (bit 0 is cleared) a competing higher priority thread can "steal"
> -the mutex which puts the woken up thread back on the waiters list.
> +The fast atomic compare exchange based acquire and release is only
> +possible when bit 0 of lock->owner is 0.
> -The pending-ownership optimization is especially important for the
> -uninterrupted workflow of high-prio tasks which repeatedly
> -takes/releases locks that have lower-prio waiters. Without this
> -optimization the higher-prio thread would ping-pong to the lower-prio
> -task [because at unlock time we always assign a new owner].
> +(*) It also can be a transitional state when grabbing the lock
> +with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
> +we need to set the bit0 before looking at the lock, and the owner may be
> +NULL in this small time, hence this can be a transitional state.
> -(*) The "mutex has waiters" bit gets set to take the lock. If the lock
> -doesn't already have an owner, this bit is quickly cleared if there are
> -no waiters. So this is a transitional state to synchronize with looking
> -at the owner field of the mutex and the mutex owner releasing the lock.
> +(**) There is a small time when bit 0 is set but there are no
> +waiters. This can happen when grabbing the lock in the slow path.
> +To prevent a cmpxchg of the owner releasing the lock, we need to
> +set this bit before looking at the lock.
> +BTW, there is still technically a "Pending Owner", it's just not called
> +that anymore. The pending owner happens to be the top_waiter of a lock
> +that has no owner and has been woken up to grab the lock.