Re: [PATCH v9 0/9] dax: fix dma vs truncate/hole-punch

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Tue, Apr 24, 2018 at 4:33 PM, Dan Williams <dan.j.williams@xxxxxxxxx> wrote:
> Changes since v8 [1]:
> * Rebase on v4.17-rc2
>
> * Fix get_user_pages_fast() for ZONE_DEVICE pages to revalidate the pte,
>   pmd, pud after taking references (Jan)
>
> * Kill dax_layout_lock(). With get_user_pages_fast() for ZONE_DEVICE
>   fixed we can then rely on the {pte,pmd}_lock to synchronize
>   dax_layout_busy_page() vs new page references (Jan)
>
> * Hold the iolock over repeated invocations of dax_layout_busy_page() to
>   enable truncate/hole-punch to make forward progress in the presence of
>   a constant stream of new direct-I/O requests (Jan).
>
> [1]: https://lists.01.org/pipermail/linux-nvdimm/2018-March/015058.html

I'll push this for soak time in -next if there are no further comments...




[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux