From: Logan Gunthorpe <logang@deltatee.com>
To: Christoph Hellwig <hch@lst.de>
Cc: linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org,
linux-block@vger.kernel.org, linux-pci@vger.kernel.org,
linux-mm@kvack.org, iommu@lists.linux-foundation.org,
"Stephen Bates" <sbates@raithlin.com>,
"Dan Williams" <dan.j.williams@intel.com>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Christian König" <christian.koenig@amd.com>,
"John Hubbard" <jhubbard@nvidia.com>,
"Don Dutile" <ddutile@redhat.com>,
"Matthew Wilcox" <willy@infradead.org>,
"Daniel Vetter" <daniel.vetter@ffwll.ch>,
"Jakowski Andrzej" <andrzej.jakowski@intel.com>,
"Minturn Dave B" <dave.b.minturn@intel.com>,
"Jason Ekstrand" <jason@jlekstrand.net>,
"Dave Hansen" <dave.hansen@linux.intel.com>,
"Xiong Jianxin" <jianxin.xiong@intel.com>,
"Bjorn Helgaas" <helgaas@kernel.org>,
"Ira Weiny" <ira.weiny@intel.com>,
"Robin Murphy" <robin.murphy@arm.com>,
"Martin Oliveira" <martin.oliveira@eideticom.com>,
"Chaitanya Kulkarni" <ckulkarnilinux@gmail.com>
Subject: Re: [PATCH v4 21/23] mm: use custom page_free for P2PDMA pages
Date: Tue, 21 Dec 2021 10:27:12 -0700 [thread overview]
Message-ID: <369770be-c2d1-fcbf-f317-279981707cb9@deltatee.com> (raw)
In-Reply-To: <20211221090648.GE7949@lst.de>
On 2021-12-21 2:06 a.m., Christoph Hellwig wrote:
> On Wed, Nov 17, 2021 at 02:54:08PM -0700, Logan Gunthorpe wrote:
>> When P2PDMA pages are passed to userspace, they will need to be
>> reference counted properly and returned to their genalloc after their
>> reference count returns to 1. This is accomplished with the existing
>> DEV_PAGEMAP_OPS and the .page_free() operation.
>>
>> Change CONFIG_P2PDMA to select CONFIG_DEV_PAGEMAP_OPS and add
>> MEMORY_DEVICE_PCI_P2PDMA to page_is_devmap_managed(),
>> devmap_managed_enable_[put|get]() and free_devmap_managed_page().
>
> Uuuh. We are trying hard to kill off this magic free at refcount 1
> behavior in the amdgpu device coherent series. We really should not
> add more of this.
Ah, ok. I found Ralph's patch that cleans this up and I can try to
rebase this onto it for future postings until it gets merged.
Your other comments I can address for the next time I post this series.
Thanks for the review!
Logan
next prev parent reply other threads:[~2021-12-21 17:27 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-17 21:53 [PATCH v4 00/23] Userspace P2PDMA with O_DIRECT NVMe devices Logan Gunthorpe
2021-11-17 21:53 ` [PATCH v4 01/23] lib/scatterlist: cleanup macros into static inline functions Logan Gunthorpe
2021-12-13 21:51 ` Chaitanya Kulkarni
2021-12-21 9:00 ` Christoph Hellwig
2021-12-21 17:23 ` Logan Gunthorpe
2021-12-22 8:22 ` Christoph Hellwig
2021-11-17 21:53 ` [PATCH v4 02/23] lib/scatterlist: add flag for indicating P2PDMA segments in an SGL Logan Gunthorpe
2021-12-13 21:55 ` Chaitanya Kulkarni
2021-12-21 9:02 ` Christoph Hellwig
2021-11-17 21:53 ` [PATCH v4 03/23] PCI/P2PDMA: Attempt to set map_type if it has not been set Logan Gunthorpe
2021-12-13 22:00 ` Chaitanya Kulkarni
2021-11-17 21:53 ` [PATCH v4 04/23] PCI/P2PDMA: Expose pci_p2pdma_map_type() Logan Gunthorpe
2021-12-13 22:05 ` Chaitanya Kulkarni
2021-11-17 21:53 ` [PATCH v4 05/23] PCI/P2PDMA: Introduce helpers for dma_map_sg implementations Logan Gunthorpe
2021-11-17 21:53 ` [PATCH v4 06/23] dma-mapping: allow EREMOTEIO return code for P2PDMA transfers Logan Gunthorpe
2021-11-17 21:53 ` [PATCH v4 07/23] dma-direct: support PCI P2PDMA pages in dma-direct map_sg Logan Gunthorpe
2021-11-17 21:53 ` [PATCH v4 08/23] dma-mapping: add flags to dma_map_ops to indicate PCI P2PDMA support Logan Gunthorpe
2021-11-17 21:53 ` [PATCH v4 09/23] iommu/dma: support PCI P2PDMA pages in dma-iommu map_sg Logan Gunthorpe
2021-11-17 21:53 ` [PATCH v4 10/23] nvme-pci: check DMA ops when indicating support for PCI P2PDMA Logan Gunthorpe
2021-12-13 22:10 ` Chaitanya Kulkarni
2021-11-17 21:53 ` [PATCH v4 11/23] nvme-pci: convert to using dma_map_sgtable() Logan Gunthorpe
2021-12-13 22:21 ` Chaitanya Kulkarni
2021-12-13 22:28 ` Logan Gunthorpe
2021-11-17 21:53 ` [PATCH v4 12/23] RDMA/core: introduce ib_dma_pci_p2p_dma_supported() Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 13/23] RDMA/rw: drop pci_p2pdma_[un]map_sg() Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 14/23] PCI/P2PDMA: Remove pci_p2pdma_[un]map_sg() Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 15/23] mm: introduce FOLL_PCI_P2PDMA to gate getting PCI P2PDMA pages Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 16/23] iov_iter: introduce iov_iter_get_pages_[alloc_]flags() Logan Gunthorpe
2021-12-21 9:04 ` Christoph Hellwig
2021-11-17 21:54 ` [PATCH v4 17/23] block: add check when merging zone device pages Logan Gunthorpe
2021-12-21 9:05 ` Christoph Hellwig
2021-11-17 21:54 ` [PATCH v4 18/23] lib/scatterlist: " Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 19/23] block: set FOLL_PCI_P2PDMA in __bio_iov_iter_get_pages() Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 20/23] block: set FOLL_PCI_P2PDMA in bio_map_user_iov() Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 21/23] mm: use custom page_free for P2PDMA pages Logan Gunthorpe
2021-12-21 9:06 ` Christoph Hellwig
2021-12-21 17:27 ` Logan Gunthorpe [this message]
2021-11-17 21:54 ` [PATCH v4 22/23] PCI/P2PDMA: Introduce pci_mmap_p2pmem() Logan Gunthorpe
2021-11-17 21:54 ` [PATCH v4 23/23] nvme-pci: allow mmaping the CMB in userspace Logan Gunthorpe
2021-12-21 9:07 ` Christoph Hellwig
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=369770be-c2d1-fcbf-f317-279981707cb9@deltatee.com \
--to=logang@deltatee.com \
--cc=andrzej.jakowski@intel.com \
--cc=christian.koenig@amd.com \
--cc=ckulkarnilinux@gmail.com \
--cc=dan.j.williams@intel.com \
--cc=daniel.vetter@ffwll.ch \
--cc=dave.b.minturn@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=ddutile@redhat.com \
--cc=hch@lst.de \
--cc=helgaas@kernel.org \
--cc=iommu@lists.linux-foundation.org \
--cc=ira.weiny@intel.com \
--cc=jason@jlekstrand.net \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=jianxin.xiong@intel.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=martin.oliveira@eideticom.com \
--cc=robin.murphy@arm.com \
--cc=sbates@raithlin.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).