futex,rt_mutex: Restructure rt_mutex_finish_proxy_lock()
authorPeter Zijlstra <peterz@infradead.org>
Wed, 22 Mar 2017 10:35:57 +0000 (11:35 +0100)
committerThomas Gleixner <tglx@linutronix.de>
Thu, 23 Mar 2017 18:10:09 +0000 (19:10 +0100)
commit38d589f2fd08f1296aea3ce62bebd185125c6d81
treefcc744619e787f2519a7d240184edef73b809a29
parent50809358dd7199aa7ce232f6877dd09ec30ef374
futex,rt_mutex: Restructure rt_mutex_finish_proxy_lock()

With the ultimate goal of keeping rt_mutex wait_list and futex_q waiters
consistent it's necessary to split 'rt_mutex_futex_lock()' into finer
parts, such that only the actual blocking can be done without hb->lock
held.

Split split_mutex_finish_proxy_lock() into two parts, one that does the
blocking and one that does remove_waiter() when the lock acquire failed.

When the rtmutex was acquired successfully the waiter can be removed in the
acquisiton path safely, since there is no concurrency on the lock owner.

This means that, except for futex_lock_pi(), all wait_list modifications
are done with both hb->lock and wait_lock held.

[bigeasy@linutronix.de: fix for futex_requeue_pi_signal_restart]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170322104152.001659630@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
kernel/futex.c
kernel/locking/rtmutex.c
kernel/locking/rtmutex_common.h