From: Leon Romanovsky <leon@kernel.org>
To: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Leon Romanovsky <leonro@nvidia.com>,
Jason Gunthorpe <jgg@nvidia.com>,
Abdiel Janulgue <abdiel.janulgue@gmail.com>,
Alexander Potapenko <glider@google.com>,
Alex Gaynor <alex.gaynor@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>,
Christoph Hellwig <hch@lst.de>,
Danilo Krummrich <dakr@kernel.org>,
iommu@lists.linux.dev, Jason Wang <jasowang@redhat.com>,
Jens Axboe <axboe@kernel.dk>, Joerg Roedel <joro@8bytes.org>,
Jonathan Corbet <corbet@lwn.net>, Juergen Gross <jgross@suse.com>,
kasan-dev@googlegroups.com, Keith Busch <kbusch@kernel.org>,
linux-block@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-nvme@lists.infradead.org, linuxppc-dev@lists.ozlabs.org,
linux-trace-kernel@vger.kernel.org,
Madhavan Srinivasan <maddy@linux.ibm.com>,
Masami Hiramatsu <mhiramat@kernel.org>,
Michael Ellerman <mpe@ellerman.id.au>,
"Michael S. Tsirkin" <mst@redhat.com>,
Miguel Ojeda <ojeda@kernel.org>,
Robin Murphy <robin.murphy@arm.com>,
rust-for-linux@vger.kernel.org, Sagi Grimberg <sagi@grimberg.me>,
Stefano Stabellini <sstabellini@kernel.org>,
Steven Rostedt <rostedt@goodmis.org>,
virtualization@lists.linux.dev, Will Deacon <will@kernel.org>,
xen-devel@lists.xenproject.org
Subject: [PATCH v1 13/16] mm/hmm: properly take MMIO path
Date: Mon, 4 Aug 2025 15:42:47 +0300 [thread overview]
Message-ID: <79cf36301cc05d6dd1c88e9c3812ac5c3f57e32b.1754292567.git.leon@kernel.org> (raw)
In-Reply-To: <cover.1754292567.git.leon@kernel.org>
From: Leon Romanovsky <leonro@nvidia.com>
In case peer-to-peer transaction traverses through host bridge,
the IOMMU needs to have IOMMU_MMIO flag, together with skip of
CPU sync.
The latter was handled by provided DMA_ATTR_SKIP_CPU_SYNC flag,
but IOMMU flag was missed, due to assumption that such memory
can be treated as regular one.
Reuse newly introduced DMA attribute to properly take MMIO path.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
mm/hmm.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/mm/hmm.c b/mm/hmm.c
index 015ab243f0813..6556c0e074ba8 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -746,7 +746,7 @@ dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map,
case PCI_P2PDMA_MAP_NONE:
break;
case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+ attrs |= DMA_ATTR_MMIO;
pfns[idx] |= HMM_PFN_P2PDMA;
break;
case PCI_P2PDMA_MAP_BUS_ADDR:
@@ -776,7 +776,7 @@ dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map,
goto error;
dma_addr = dma_map_phys(dev, paddr, map->dma_entry_size,
- DMA_BIDIRECTIONAL, 0);
+ DMA_BIDIRECTIONAL, attrs);
if (dma_mapping_error(dev, dma_addr))
goto error;
@@ -811,16 +811,17 @@ bool hmm_dma_unmap_pfn(struct device *dev, struct hmm_dma_map *map, size_t idx)
if ((pfns[idx] & valid_dma) != valid_dma)
return false;
+ if (pfns[idx] & HMM_PFN_P2PDMA)
+ attrs |= DMA_ATTR_MMIO;
+
if (pfns[idx] & HMM_PFN_P2PDMA_BUS)
; /* no need to unmap bus address P2P mappings */
- else if (dma_use_iova(state)) {
- if (pfns[idx] & HMM_PFN_P2PDMA)
- attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+ else if (dma_use_iova(state))
dma_iova_unlink(dev, state, idx * map->dma_entry_size,
map->dma_entry_size, DMA_BIDIRECTIONAL, attrs);
- } else if (dma_need_unmap(dev))
+ else if (dma_need_unmap(dev))
dma_unmap_phys(dev, dma_addrs[idx], map->dma_entry_size,
- DMA_BIDIRECTIONAL, 0);
+ DMA_BIDIRECTIONAL, attrs);
pfns[idx] &=
~(HMM_PFN_DMA_MAPPED | HMM_PFN_P2PDMA | HMM_PFN_P2PDMA_BUS);
--
2.50.1
next prev parent reply other threads:[~2025-08-04 12:44 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-04 12:42 [PATCH v1 00/16] dma-mapping: migrate to physical address-based API Leon Romanovsky
2025-08-04 12:42 ` [PATCH v1 01/16] dma-mapping: introduce new DMA attribute to indicate MMIO memory Leon Romanovsky
2025-08-06 17:31 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 02/16] iommu/dma: handle MMIO path in dma_iova_link Leon Romanovsky
2025-08-06 18:10 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 03/16] dma-debug: refactor to use physical addresses for page mapping Leon Romanovsky
2025-08-06 18:26 ` Jason Gunthorpe
2025-08-06 18:38 ` Leon Romanovsky
2025-08-04 12:42 ` [PATCH v1 04/16] dma-mapping: rename trace_dma_*map_page to trace_dma_*map_phys Leon Romanovsky
2025-08-04 12:42 ` [PATCH v1 05/16] iommu/dma: rename iommu_dma_*map_page to iommu_dma_*map_phys Leon Romanovsky
2025-08-06 18:44 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 06/16] iommu/dma: extend iommu_dma_*map_phys API to handle MMIO memory Leon Romanovsky
2025-08-07 12:07 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 07/16] dma-mapping: convert dma_direct_*map_page to be phys_addr_t based Leon Romanovsky
2025-08-07 12:13 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 08/16] kmsan: convert kmsan_handle_dma to use physical addresses Leon Romanovsky
2025-08-07 12:21 ` Jason Gunthorpe
2025-08-13 15:07 ` Leon Romanovsky
2025-08-14 12:13 ` Jason Gunthorpe
2025-08-14 12:35 ` Leon Romanovsky
2025-08-14 12:44 ` Jason Gunthorpe
2025-08-14 13:31 ` Leon Romanovsky
2025-08-14 14:14 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 09/16] dma-mapping: handle MMIO flow in dma_map|unmap_page Leon Romanovsky
2025-08-07 13:08 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 10/16] xen: swiotlb: Open code map_resource callback Leon Romanovsky
2025-08-07 14:40 ` Jürgen Groß
2025-08-04 12:42 ` [PATCH v1 11/16] dma-mapping: export new dma_*map_phys() interface Leon Romanovsky
2025-08-07 13:38 ` Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 12/16] mm/hmm: migrate to physical address-based DMA mapping API Leon Romanovsky
2025-08-07 13:14 ` Jason Gunthorpe
2025-08-04 12:42 ` Leon Romanovsky [this message]
2025-08-07 13:14 ` [PATCH v1 13/16] mm/hmm: properly take MMIO path Jason Gunthorpe
2025-08-04 12:42 ` [PATCH v1 14/16] block-dma: migrate to dma_map_phys instead of map_page Leon Romanovsky
2025-08-04 12:42 ` [PATCH v1 15/16] block-dma: properly take MMIO path Leon Romanovsky
2025-08-04 12:42 ` [PATCH v1 16/16] nvme-pci: unmap MMIO pages with appropriate interface Leon Romanovsky
2025-08-07 13:45 ` Jason Gunthorpe
2025-08-13 15:37 ` Leon Romanovsky
2025-08-07 14:19 ` [PATCH v1 00/16] dma-mapping: migrate to physical address-based API Jason Gunthorpe
2025-08-08 18:51 ` Marek Szyprowski
2025-08-09 13:34 ` Jason Gunthorpe
2025-08-09 16:53 ` Demi Marie Obenour
2025-08-10 17:02 ` Jason Gunthorpe
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=79cf36301cc05d6dd1c88e9c3812ac5c3f57e32b.1754292567.git.leon@kernel.org \
--to=leon@kernel.org \
--cc=abdiel.janulgue@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=alex.gaynor@gmail.com \
--cc=axboe@kernel.dk \
--cc=corbet@lwn.net \
--cc=dakr@kernel.org \
--cc=glider@google.com \
--cc=hch@lst.de \
--cc=iommu@lists.linux.dev \
--cc=jasowang@redhat.com \
--cc=jgg@nvidia.com \
--cc=jgross@suse.com \
--cc=joro@8bytes.org \
--cc=kasan-dev@googlegroups.com \
--cc=kbusch@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-trace-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=m.szyprowski@samsung.com \
--cc=maddy@linux.ibm.com \
--cc=mhiramat@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=mst@redhat.com \
--cc=ojeda@kernel.org \
--cc=robin.murphy@arm.com \
--cc=rostedt@goodmis.org \
--cc=rust-for-linux@vger.kernel.org \
--cc=sagi@grimberg.me \
--cc=sstabellini@kernel.org \
--cc=virtualization@lists.linux.dev \
--cc=will@kernel.org \
--cc=xen-devel@lists.xenproject.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).