From: ALOK TIWARI <alok.a.tiwari@oracle.com>
To: Leon Romanovsky <leon@kernel.org>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
Keith Busch <kbusch@kernel.org>
Cc: "Jake Edge" <jake@lwn.net>, "Jonathan Corbet" <corbet@lwn.net>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Zhu Yanjun" <zyjzyj2000@gmail.com>,
"Robin Murphy" <robin.murphy@arm.com>,
"Joerg Roedel" <joro@8bytes.org>, "Will Deacon" <will@kernel.org>,
"Sagi Grimberg" <sagi@grimberg.me>,
"Bjorn Helgaas" <bhelgaas@google.com>,
"Logan Gunthorpe" <logang@deltatee.com>,
"Yishai Hadas" <yishaih@nvidia.com>,
"Shameer Kolothum" <shameerali.kolothum.thodi@huawei.com>,
"Kevin Tian" <kevin.tian@intel.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
iommu@lists.linux.dev, linux-nvme@lists.infradead.org,
linux-pci@vger.kernel.org, kvm@vger.kernel.org,
linux-mm@kvack.org, "Niklas Schnelle" <schnelle@linux.ibm.com>,
"Chuck Lever" <chuck.lever@oracle.com>,
"Luis Chamberlain" <mcgrof@kernel.org>,
"Matthew Wilcox" <willy@infradead.org>,
"Dan Williams" <dan.j.williams@intel.com>,
"Kanchan Joshi" <joshi.k@samsung.com>,
"Chaitanya Kulkarni" <kch@nvidia.com>,
"Leon Romanovsky" <leonro@nvidia.com>
Subject: Re: [PATCH v8 20/24] blk-mq: add scatterlist-less DMA mapping helpers
Date: Fri, 18 Apr 2025 23:33:09 +0530 [thread overview]
Message-ID: <65b0070e-3386-4725-8e8a-15b0409b8368@oracle.com> (raw)
In-Reply-To: <87b151a3791d71e58ec6f1b42bcf5fe06304cf80.1744825142.git.leon@kernel.org>
> + * Start DMA mapping @req to @dma_dev. @state and @iter are provided by the
> + * caller and don't need to be initialized. @state needs to be stored for use
> + * at unmap time, @iter is only needed at map time.
> + *
> + * Returns %false if there is no segment to map, including due to an error, or
> + * %true it it did map a segment.
typo - it it -> if it
> + *
> + * If a segment was mapped, the DMA address for it is returned in @iter.addr and
> + * the length in @iter.len. If no segment was mapped the status code is
> + * returned in @iter.status.
> + *
> + * The caller can call blk_rq_dma_map_coalesce() to check if further segments
> + * need to be mapped after this, or go straight to blk_rq_dma_map_iter_next()
> + * to try to map the following segments.
> + */
> +bool blk_rq_dma_map_iter_start(struct request *req, struct device *dma_dev,
> + struct dma_iova_state *state, struct blk_dma_iter *iter)
> +{
> + unsigned int total_len = blk_rq_payload_bytes(req);
> + struct phys_vec vec;
> +
> + iter->iter.bio = req->bio;
> + iter->iter.iter = req->bio->bi_iter;
> + memset(&iter->p2pdma, 0, sizeof(iter->p2pdma));
> + iter->status = BLK_STS_OK;
> +
> + /*
> + * Grab the first segment ASAP because we'll need it to check for P2P
> + * transfers.
> + */
> + if (!blk_map_iter_next(req, &iter->iter, &vec))
> + return false;
> +
> + if (IS_ENABLED(CONFIG_PCI_P2PDMA) && (req->cmd_flags & REQ_P2PDMA)) {
> + switch (pci_p2pdma_state(&iter->p2pdma, dma_dev,
> + blk_phys_to_page(vec.paddr))) {
> + case PCI_P2PDMA_MAP_BUS_ADDR:
> + return blk_dma_map_bus(req, dma_dev, iter, &vec);
> + case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
> + /*
> + * P2P transfers through the host bridge are treated the
> + * same as non-P2P transfers below and during unmap.
> + */
> + req->cmd_flags &= ~REQ_P2PDMA;
> + break;
> + default:
> + iter->status = BLK_STS_INVAL;
> + return false;
> + }
> + }
> +
> + if (blk_can_dma_map_iova(req, dma_dev) &&
> + dma_iova_try_alloc(dma_dev, state, vec.paddr, total_len))
> + return blk_rq_dma_map_iova(req, dma_dev, state, iter, &vec);
> + return blk_dma_map_direct(req, dma_dev, iter, &vec);
> +}
> +EXPORT_SYMBOL_GPL(blk_rq_dma_map_iter_start);
> +
> +/**
> + * blk_rq_dma_map_iter_next - map the next DMA segment for a request
> + * @req: request to map
> + * @dma_dev: device to map to
> + * @state: DMA IOVA state
> + * @iter: block layer DMA iterator
> + *
> + * Iterate to the next mapping after a previous call to
> + * blk_rq_dma_map_iter_start(). See there for a detailed description of the
> + * arguments.
> + *
> + * Returns %false if there is no segment to map, including due to an error, or
> + * %true it it did map a segment.
typo - it it -> if it
> + *
> + * If a segment was mapped, the DMA address for it is returned in @iter.addr and
> + * the length in @iter.len. If no segment was mapped the status code is
> + * returned in @iter.status.
> + */
> +bool blk_rq_dma_map_iter_next(struct request *req, struct device *dma_dev,
> + struct dma_iova_state *state, struct blk_dma_iter *iter)
> +{
> + struct phys_vec vec;
> +
> + if (!blk_map_iter_next(req, &iter->iter, &vec))
> + return false;
> +
> + if (iter->p2pdma.map == PCI_P2PDMA_MAP_BUS_ADDR)
> + return blk_dma_map_bus(req, dma_dev, iter, &vec);
> + return blk_dma_map_direct(req, dma_dev, iter, &vec);
> +}
> +EXPORT_SYMBOL_GPL(blk_rq_dma_map_iter_next);
> +
> static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
> struct scatterlist *sglist)
> {
> diff --git a/include/linux/blk-mq-dma.h b/include/linux/blk-mq-dma.h
> new file mode 100644
> index 000000000000..588dc3c1ad1f
> --- /dev/null
> +++ b/include/linux/blk-mq-dma.h
> @@ -0,0 +1,62 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef BLK_MQ_DMA_H
> +#define BLK_MQ_DMA_H
> +
> +#include <linux/blk-mq.h>
> +#include <linux/pci-p2pdma.h>
> +
> +struct blk_dma_iter {
> + /* Output address range for this iteration */
> + dma_addr_t addr;
> + u32 len;
> +
> + /* Status code. Only valid when blk_rq_dma_map_iter_* returned false */
> + blk_status_t status;
> +
> + /* Internal to blk_rq_dma_map_iter_* */
> + struct req_iterator iter;
> + struct pci_p2pdma_map_state p2pdma;
> +};
> +
> +bool blk_rq_dma_map_iter_start(struct request *req, struct device *dma_dev,
> + struct dma_iova_state *state, struct blk_dma_iter *iter);
> +bool blk_rq_dma_map_iter_next(struct request *req, struct device *dma_dev,
> + struct dma_iova_state *state, struct blk_dma_iter *iter);
> +
> +/**
> + * blk_rq_dma_map_coalesce - were all segments coalesced?
> + * @state: DMA state to check
> + *
> + * Returns true if blk_rq_dma_map_iter_start coalesced all segments into a
> + * single DMA range.
> + */
> +static inline bool blk_rq_dma_map_coalesce(struct dma_iova_state *state)
> +{
> + return dma_use_iova(state);
> +}
> +
> +/**
> + * blk_rq_dma_map_coalesce - try to DMA unmap a request
> + * @req: request to unmap
> + * @dma_dev: device to unmap from
> + * @state: DMA IOVA state
> + * @mapped_len: number of bytes to unmap
> + *
> + * Returns %false if the callers needs to manually unmap every DMA segment
typo needs -> need
> + * mapped using @iter or %true if no work is left to be done.
> + */
Thanks,
Alok
next prev parent reply other threads:[~2025-04-21 15:04 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-18 6:47 [PATCH v8 00/24] Provide a new two step DMA mapping API Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 01/24] PCI/P2PDMA: Refactor the p2pdma mapping helpers Leon Romanovsky
2025-04-20 20:05 ` ALOK TIWARI
2025-04-18 6:47 ` [PATCH v8 02/24] dma-mapping: move the PCI P2PDMA mapping helpers to pci-p2pdma.h Leon Romanovsky
2025-04-20 20:09 ` ALOK TIWARI
2025-04-18 6:47 ` [PATCH v8 03/24] iommu: generalize the batched sync after map interface Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 04/24] iommu: add kernel-doc for iommu_unmap and iommu_unmap_fast Leon Romanovsky
2025-04-22 4:23 ` Christoph Hellwig
2025-04-22 6:27 ` Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 05/24] dma-mapping: Provide an interface to allow allocate IOVA Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 06/24] iommu/dma: Factor out a iommu_dma_map_swiotlb helper Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 07/24] dma-mapping: Implement link/unlink ranges API Leon Romanovsky
2025-04-20 20:23 ` ALOK TIWARI
2025-04-18 6:47 ` [PATCH v8 08/24] dma-mapping: add a dma_need_unmap helper Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 09/24] docs: core-api: document the IOVA-based API Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 10/24] mm/hmm: let users to tag specific PFN with DMA mapped bit Leon Romanovsky
2025-04-22 4:24 ` Christoph Hellwig
2025-04-18 6:47 ` [PATCH v8 11/24] mm/hmm: provide generic DMA managing logic Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 12/24] RDMA/umem: Store ODP access mask information in PFN Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 13/24] RDMA/core: Convert UMEM ODP DMA mapping to caching IOVA and page linkage Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 14/24] RDMA/umem: Separate implicit ODP initialization from explicit ODP Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 15/24] vfio/mlx5: Explicitly use number of pages instead of allocated length Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 16/24] vfio/mlx5: Rewrite create mkey flow to allow better code reuse Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 17/24] vfio/mlx5: Enable the DMA link API Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 18/24] block: share more code for bio addition helper Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 19/24] block: don't merge different kinds of P2P transfers in a single bio Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 20/24] blk-mq: add scatterlist-less DMA mapping helpers Leon Romanovsky
2025-04-18 18:03 ` ALOK TIWARI [this message]
2025-04-20 7:09 ` Leon Romanovsky
2025-04-22 4:27 ` Christoph Hellwig
2025-04-22 6:36 ` Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 21/24] nvme-pci: remove struct nvme_descriptor Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 22/24] nvme-pci: use a better encoding for small prp pool allocations Leon Romanovsky
2025-04-18 6:47 ` [PATCH v8 23/24] nvme-pci: convert to blk_rq_dma_map Leon Romanovsky
2025-04-18 18:29 ` ALOK TIWARI
2025-04-22 5:00 ` Christoph Hellwig
2025-04-22 7:26 ` Leon Romanovsky
2025-04-22 7:32 ` Christoph Hellwig
2025-04-18 6:47 ` [PATCH v8 24/24] nvme-pci: optimize single-segment handling Leon Romanovsky
2025-04-18 8:02 ` Damien Le Moal
2025-04-18 11:19 ` Leon Romanovsky
2025-04-18 12:32 ` Kanchan Joshi
2025-04-22 4:39 ` Christoph Hellwig
2025-04-22 7:44 ` Leon Romanovsky
2025-04-22 11:36 ` Leon Romanovsky
2025-04-18 11:16 ` [PATCH v8 00/24] Provide a new two step DMA mapping API Leon Romanovsky
2025-04-18 12:18 ` Jens Axboe
2025-04-20 7:14 ` Leon Romanovsky
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=65b0070e-3386-4725-8e8a-15b0409b8368@oracle.com \
--to=alok.a.tiwari@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=alex.williamson@redhat.com \
--cc=axboe@kernel.dk \
--cc=bhelgaas@google.com \
--cc=chuck.lever@oracle.com \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=hch@lst.de \
--cc=iommu@lists.linux.dev \
--cc=jake@lwn.net \
--cc=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=joro@8bytes.org \
--cc=joshi.k@samsung.com \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=leon@kernel.org \
--cc=leonro@nvidia.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-doc@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=linux-rdma@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=m.szyprowski@samsung.com \
--cc=mcgrof@kernel.org \
--cc=robin.murphy@arm.com \
--cc=sagi@grimberg.me \
--cc=schnelle@linux.ibm.com \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=yishaih@nvidia.com \
--cc=zyjzyj2000@gmail.com \
/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