Hi, A few updates while going through the powerpc port of the qspinlock.
Patches 1 and 2 are straightforward, while patch 3 can be considered more of an rfc as I've only tested on a single machine, and there could be an alternative way if it doesn't end up being nearly a universal performance win. Thanks! Davidlohr Bueso (3): powerpc/spinlock: Define smp_mb__after_spinlock only once powerpc/spinlock: Unserialize spin_is_locked powerpc/qspinlock: Use generic smp_cond_load_relaxed arch/powerpc/include/asm/barrier.h | 16 ---------------- arch/powerpc/include/asm/qspinlock.h | 14 -------------- arch/powerpc/include/asm/simple_spinlock.h | 6 +----- arch/powerpc/include/asm/spinlock.h | 3 +++ 4 files changed, 4 insertions(+), 35 deletions(-) -- 2.26.2
