Hi, all, On Sat, Jul 31, 2021 at 2:40 AM Waiman Long <llong@xxxxxxxxxx> wrote: > > On 7/29/21 6:18 AM, hev wrote: > > Hi, Will, > > > > On Thu, Jul 29, 2021 at 5:39 PM Will Deacon <will@xxxxxxxxxx> wrote: > >> On Wed, Jul 28, 2021 at 07:48:22PM +0800, Rui Wang wrote: > >>> From: wangrui <wangrui@xxxxxxxxxxx> > >>> > >>> This patch introduce a new atomic primitive 'and_or', It may be have three > >>> types of implemeations: > >>> > >>> * The generic implementation is based on arch_cmpxchg. > >>> * The hardware supports atomic 'and_or' of single instruction. > >> Do any architectures actually support this instruction? > > No, I'm not sure now. > > > >> On arm64, we can clear arbitrary bits and we can set arbitrary bits, but we > >> can't combine the two in a fashion which provides atomicity and > >> forward-progress guarantees. > >> > >> Please can you explain how this new primitive will be used, in case there's > >> an alternative way of doing it which maps better to what CPUs can actually > >> do? > > I think we can easily exchange arbitrary bits of a machine word with atomic > > andnot_or/and_or. Otherwise, we can only use xchg8/16 to do it. It depends on > > hardware support, and the key point is that the bits to be exchanged > > must be in the > > same sub-word. qspinlock adjusted memory layout for this reason, and waste some > > bits(_Q_PENDING_BITS == 8). > > It is not actually a waste of bits. With _Q_PENDING_BITS==8, more > optimized code can be used for pending bit processing. It is only in the > rare case that NR_CPUS >= 16k - 1 that we have to fall back to > _Q_PENDING_BITS==1. In fact, that should be the only condition that will > make _Q_PENDING_BITS=1. Our original goal is to let LoongArch (and CSKY, RISC-V, etc) can use qspinlock, but these archs lack sub-word xchg/cmpxchg. Arnd suggests we not use qspinlock, but LoongArch has large SMP (and NUMA) so we need it. Peter suggests we implement atomic_fetch_and_or, but it seems not agreed by everyone. So, I think we can only fix the badly-implemented xchg_small() for MIPS and LoongArch. Huacai > > Cheers, > Longman >
