Re: [PATCH v4 0/5] nfs: modernize direct I/O path
Pranjal Shrivastava <[email protected]>
| Newsgroups | org.kernel.vger.linux-rdma,org.kernel.vger.linux-kernel,org.kernel.vger.linux-nfs,org.kernel.vger.linux-pci |
|---|---|
| Message-ID | <[email protected]> |
On Mon, Aug 10, 2026 at 08:38:49PM +0000, Pranjal Shrivastava wrote: > On Mon, Aug 10, 2026 at 07:50:34PM +0000, Pranjal Shrivastava wrote: > > Modernize the NFS Direct I/O path as a preparatory step to enable PCI > > Peer-to-Peer DMA (P2PDMA) support. Following feedback on the initial > > RFC [1], the modernization and architectural changes are split into > > different series. Additionally, based on the discussion in the v2 [2] > > of this series, the migration of NFS Direct I/O to folios would be > > handled in a separate follow-up series. > > > > Currently, NFS O_DIRECT relies on the legacy iov_iter_get_pages_alloc2() > > API which does not support the pinning requirements for P2P memory. > > The implementation moves NFS to the modern iov_iter_extract_pages() API. > > > > [...] > > I'm calling out a few typos / non-code mistakes: > > 1. On the cover letter I missed updating the subject to v5 for this series > (the changelog is noted below). > > 2. I also accidentally dropped Christoph's Reviewed-by tags on patches > 1, 2, and 3 during the rebase (given while reviewing v4 [1]). > > Everything else in the series is correct as per the v5 changelog. > Please let me know what the right etiquette is? Shall I resend the series? > > Apologies for the noise! > Quick update: I've posted a v6 [1] with fixes for unpin bugs reported by Sashiko [2] and with R-bs from Christoph that were dropped mistakenly in v5. Thanks, Praan [1] https://lore.kernel.org/all/[email protected]/ [2] https://sashiko.dev/#/patchset/20260810195040.2877784-1-praan%40google.com