[PATCH v2 3/5] libnvdimm/nvdimm/flush: Allow architecture to override the flush barrier

[Dan Williams]

On Tue, May 12, 2020 at 8:47 PM Aneesh Kumar K.V
<aneesh.kumar at linux.ibm.com> wrote:
>
> Architectures like ppc64 provide persistent memory specific barriers
> that will ensure that all stores for which the modifications are
> written to persistent storage by preceding dcbfps and dcbstps
> instructions have updated persistent storage before any data
> access or data transfer caused by subsequent instructions is initiated.
> This is in addition to the ordering done by wmb()
>
> Update nvdimm core such that architecture can use barriers other than
> wmb to ensure all previous writes are architecturally visible for
> the platform buffer flush.

This seems like an exceedingly bad idea, maybe I'm missing something.
This implies that the deployed base of DAX applications using the old
instruction sequence are going to regress on new hardware that
requires the new instructions to be deployed. I'm thinking the kernel
should go as far as to disable DAX operation by default on new
hardware until userspace asserts that it is prepared to switch to the
new implementation. Is there any other way to ensure the forward
compatibility of deployed ppc64 DAX applications?

>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.ibm.com>
> ---
>  drivers/nvdimm/region_devs.c | 8 ++++----
>  include/linux/libnvdimm.h    | 4 ++++
>  2 files changed, 8 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
> index ccbb5b43b8b2..88ea34a9c7fd 100644
> --- a/drivers/nvdimm/region_devs.c
> +++ b/drivers/nvdimm/region_devs.c
> @@ -1216,13 +1216,13 @@ int generic_nvdimm_flush(struct nd_region *nd_region)
>         idx = this_cpu_add_return(flush_idx, hash_32(current->pid + idx, 8));
>
>         /*
> -        * The first wmb() is needed to 'sfence' all previous writes
> -        * such that they are architecturally visible for the platform
> -        * buffer flush.  Note that we've already arranged for pmem
> +        * The first arch_pmem_flush_barrier() is needed to 'sfence' all
> +        * previous writes such that they are architecturally visible for
> +        * the platform buffer flush. Note that we've already arranged for pmem
>          * writes to avoid the cache via memcpy_flushcache().  The final
>          * wmb() ensures ordering for the NVDIMM flush write.
>          */
> -       wmb();
> +       arch_pmem_flush_barrier();
>         for (i = 0; i < nd_region->ndr_mappings; i++)
>                 if (ndrd_get_flush_wpq(ndrd, i, 0))
>                         writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));
> diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
> index 18da4059be09..66f6c65bd789 100644
> --- a/include/linux/libnvdimm.h
> +++ b/include/linux/libnvdimm.h
> @@ -286,4 +286,8 @@ static inline void arch_invalidate_pmem(void *addr, size_t size)
>  }
>  #endif
>
> +#ifndef arch_pmem_flush_barrier
> +#define arch_pmem_flush_barrier() wmb()
> +#endif
> +
>  #endif /* __LIBNVDIMM_H__ */
> --
> 2.26.2
>