Linaro-mm-sig July 2025

linaro-mm-sig@lists.linaro.org

25 participants
79 discussions

[PATCH v5 0/2] dma-buf: heaps: Support carved-out heaps

by Maxime Ripard

Hi, This series is the follow-up of the discussion that John and I had some time ago here: https://lore.kernel.org/all/CANDhNCquJn6bH3KxKf65BWiTYLVqSd9892-xtFDHHqqyrr… The initial problem we were discussing was that I'm currently working on a platform which has a memory layout with ECC enabled. However, enabling the ECC has a number of drawbacks on that platform: lower performance, increased memory usage, etc. So for things like framebuffers, the trade-off isn't great and thus there's a memory region with ECC disabled to allocate from for such use cases. After a suggestion from John, I chose to first start using heap allocations flags to allow for userspace to ask for a particular ECC setup. This is then backed by a new heap type that runs from reserved memory chunks flagged as such, and the existing DT properties to specify the ECC properties. After further discussion, it was considered that flags were not the right solution, and relying on the names of the heaps would be enough to let userspace know the kind of buffer it deals with. Thus, even though the uAPI part of it has been dropped in this second version, we still need a driver to create heaps out of carved-out memory regions. In addition to the original usecase, a similar driver can be found in BSPs from most vendors, so I believe it would be a useful addition to the kernel. Let me know what you think, Maxime Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- Changes in v5: - Rebased on 6.16-rc2 - Switch from property to dedicated binding - Link to v4: https://lore.kernel.org/r/20250520-dma-buf-ecc-heap-v4-1-bd2e1f1bb42c@kerne… Changes in v4: - Rebased on 6.15-rc7 - Map buffers only when map is actually called, not at allocation time - Deal with restricted-dma-pool and shared-dma-pool - Reword Kconfig options - Properly report dma_map_sgtable failures - Link to v3: https://lore.kernel.org/r/20250407-dma-buf-ecc-heap-v3-0-97cdd36a5f29@kerne… Changes in v3: - Reworked global variable patch - Link to v2: https://lore.kernel.org/r/20250401-dma-buf-ecc-heap-v2-0-043fd006a1af@kerne… Changes in v2: - Add vmap/vunmap operations - Drop ECC flags uapi - Rebase on top of 6.14 - Link to v1: https://lore.kernel.org/r/20240515-dma-buf-ecc-heap-v1-0-54cbbd049511@kerne… --- Maxime Ripard (2): dt-bindings: reserved-memory: Introduce carved-out memory region binding dma-buf: heaps: Introduce a new heap for reserved memory .../bindings/reserved-memory/carved-out.yaml | 49 +++ drivers/dma-buf/heaps/Kconfig | 8 + drivers/dma-buf/heaps/Makefile | 1 + drivers/dma-buf/heaps/carveout_heap.c | 362 +++++++++++++++++++++ 4 files changed, 420 insertions(+) --- base-commit: d076bed8cb108ba2236d4d49c92303fda4036893 change-id: 20240515-dma-buf-ecc-heap-28a311d2c94e Best regards, -- Maxime Ripard <mripard(a)kernel.org>

1 week, 4 days

[PATCH 00/10] vfio/pci: Allow MMIO regions to be exported through dma-buf

by Leon Romanovsky

From: Leon Romanovsky <leonro(a)nvidia.com> --------------------------------------------------------------------------- Based on blk and DMA patches which will be sent during coming merge window. --------------------------------------------------------------------------- This series extends the VFIO PCI subsystem to support exporting MMIO regions from PCI device BARs as dma-buf objects, enabling safe sharing of non-struct page memory with controlled lifetime management. This allows RDMA and other subsystems to import dma-buf FDs and build them into memory regions for PCI P2P operations. The series supports a use case for SPDK where a NVMe device will be owned by SPDK through VFIO but interacting with a RDMA device. The RDMA device may directly access the NVMe CMB or directly manipulate the NVMe device's doorbell using PCI P2P. However, as a general mechanism, it can support many other scenarios with VFIO. This dmabuf approach can be usable by iommufd as well for generic and safe P2P mappings. In addition to the SPDK use-case mentioned above, the capability added in this patch series can also be useful when a buffer (located in device memory such as VRAM) needs to be shared between any two dGPU devices or instances (assuming one of them is bound to VFIO PCI) as long as they are P2P DMA compatible. The implementation provides a revocable attachment mechanism using dma-buf move operations. MMIO regions are normally pinned as BARs don't change physical addresses, but access is revoked when the VFIO device is closed or a PCI reset is issued. This ensures kernel self-defense against potentially hostile userspace. The series includes significant refactoring of the PCI P2PDMA subsystem to separate core P2P functionality from memory allocation features, making it more modular and suitable for VFIO use cases that don't need struct page support. ----------------------------------------------------------------------- This is based on https://lore.kernel.org/all/20250307052248.405803-1-vivek.kasireddy@intel.c… but heavily rewritten to be based on DMA physical API. ----------------------------------------------------------------------- The WIP branch can be found here: https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma.git/log/?h=… Thanks Leon Romanovsky (8): PCI/P2PDMA: Remove redundant bus_offset from map state PCI/P2PDMA: Introduce p2pdma_provider structure for cleaner abstraction PCI/P2PDMA: Simplify bus address mapping API PCI/P2PDMA: Refactor to separate core P2P functionality from memory allocation PCI/P2PDMA: Export pci_p2pdma_map_type() function types: move phys_vec definition to common header vfio/pci: Enable peer-to-peer DMA transactions by default vfio/pci: Add dma-buf export support for MMIO regions Vivek Kasireddy (2): vfio: Export vfio device get and put registration helpers vfio/pci: Share the core device pointer while invoking feature functions block/blk-mq-dma.c | 7 +- drivers/iommu/dma-iommu.c | 4 +- drivers/pci/p2pdma.c | 144 +++++++++---- drivers/vfio/pci/Kconfig | 20 ++ drivers/vfio/pci/Makefile | 2 + drivers/vfio/pci/vfio_pci_config.c | 22 +- drivers/vfio/pci/vfio_pci_core.c | 59 ++++-- drivers/vfio/pci/vfio_pci_dmabuf.c | 321 +++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_priv.h | 23 +++ drivers/vfio/vfio_main.c | 2 + include/linux/dma-buf.h | 1 + include/linux/pci-p2pdma.h | 114 +++++----- include/linux/types.h | 5 + include/linux/vfio.h | 2 + include/linux/vfio_pci_core.h | 4 + include/uapi/linux/vfio.h | 19 ++ kernel/dma/direct.c | 4 +- mm/hmm.c | 2 +- 18 files changed, 631 insertions(+), 124 deletions(-) create mode 100644 drivers/vfio/pci/vfio_pci_dmabuf.c -- 2.50.1

2 weeks, 5 days

Re: [PATCH 05/10] PCI/P2PDMA: Export pci_p2pdma_map_type() function

by Leon Romanovsky

2 weeks, 6 days

Re: [PATCH 05/10] PCI/P2PDMA: Export pci_p2pdma_map_type() function

by Jason Gunthorpe

On Tue, Jul 29, 2025 at 02:54:13PM -0600, Logan Gunthorpe wrote: > > > On 2025-07-28 17:11, Jason Gunthorpe wrote: > >> If the dma mapping for P2P memory doesn't need to create an iommu > >> mapping then that's fine. But it should be the dma-iommu layer to decide > >> that. > > > > So above, we can't use dma-iommu.c, it might not be compiled into the > > kernel but the dma_map_phys() path is still valid. > > This is an easily solved problem. I did a very rough sketch below to say > it's really not that hard. (Note it has some rough edges that could be > cleaned up and I based it off Leon's git repo which appears to not be > the same as what was posted, but the core concept is sound). I did hope for something like this in the early days, but it proved not so easy to get agreements on details :( My feeling was we should get some actual examples of using this thing and then it is far easier to discuss ideas, like yours here, to improve it. Many of the discussions kind of got confused without enough actual usering code for everyone to refer to. For instance the nvme use case is a big driver for the API design, and it is quite different from these simpler flows, this idea needs to see how it would work there. Maybe this idea could also have provider = NULL meaning it is CPU cachable memory? > +static inline void dma_iova_try_alloc_p2p(struct p2pdma_provider *provider, > + struct device *dev, struct dma_iova_state *state, phys_addr_t phys, > + size_t size) > +{ > +} Can't be empty - PCI_P2PDMA_MAP_THRU_HOST_BRIDGE vs PCI_P2PDMA_MAP_BUS_ADDR still matters so it still must set dma_iova_state::bus_addr to get dma_map_phys_prealloc() to do the right thing. Still, it would make sense to put something like that in dma/mapping.c and rely on the static inline stub for dma_iova_try_alloc().. > for (i = 0; i < priv->nr_ranges; i++) { > - if (!state) { > - addr = pci_p2pdma_bus_addr_map(provider, > - phys_vec[i].paddr); > - } else if (dma_use_iova(state)) { > - ret = dma_iova_link(attachment->dev, state, > - phys_vec[i].paddr, 0, > - phys_vec[i].len, dir, attrs); > - if (ret) > - goto err_unmap_dma; > - > - mapped_len += phys_vec[i].len; > - } else { > - addr = dma_map_phys(attachment->dev, phys_vec[i].paddr, > - phys_vec[i].len, dir, attrs); > - ret = dma_mapping_error(attachment->dev, addr); > - if (ret) > - goto err_unmap_dma; > - } > + addr = dma_map_phys_prealloc(attachment->dev, phys_vec[i].paddr, > + phys_vec[i].len, dir, attrs, state, > + provider); There was a draft of something like this at some point. The DMA_MAPPING_USE_IOVA is a new twist though > #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) > struct dma_iova_state { > dma_addr_t addr; > u64 __size; > + bool bus_addr; > }; Gowing this structure has been strongly pushed back on. This probably can be solved in some other way, a bitfield on size perhaps.. > +dma_addr_t dma_map_phys_prealloc(struct device *dev, phys_addr_t phys, > size_t size, > + enum dma_data_direction dir, unsigned long attrs, > + struct dma_iova_state *state, struct p2pdma_provider *provider) > +{ > + int ret; > + > + if (state->bus_addr) > + return pci_p2pdma_bus_addr_map(provider, phys); > + > + if (dma_use_iova(state)) { > + ret = dma_iova_link(dev, state, phys, 0, size, dir, attrs); > + if (ret) > + return DMA_MAPPING_ERROR; > + > + return DMA_MAPPING_USE_IOVA; > + } > + > + return dma_map_phys(dev, phys, size, dir, attrs); > +} > +EXPORT_SYMBOL_GPL(dma_map_phys_prealloc); I would be tempted to inline this Overall, yeah I would certainly welcome improvements like this if everyone can agree, but I'd really like to see nvme merged before we start working on ideas. That way the proposal can be properly evaluated by all the stake holders. Jason

2 weeks, 6 days

Re: [PATCH 05/10] PCI/P2PDMA: Export pci_p2pdma_map_type() function

by Jason Gunthorpe

On Mon, Jul 28, 2025 at 11:07:34AM -0600, Logan Gunthorpe wrote: > > > On 2025-07-28 10:41, Leon Romanovsky wrote: > > On Mon, Jul 28, 2025 at 10:12:31AM -0600, Logan Gunthorpe wrote: > >> > >> > >> On 2025-07-27 13:05, Jason Gunthorpe wrote: > >>> On Fri, Jul 25, 2025 at 10:30:46AM -0600, Logan Gunthorpe wrote: > >>>> > >>>> > >>>> On 2025-07-24 02:13, Leon Romanovsky wrote: > >>>>> On Thu, Jul 24, 2025 at 10:03:13AM +0200, Christoph Hellwig wrote: > >>>>>> On Wed, Jul 23, 2025 at 04:00:06PM +0300, Leon Romanovsky wrote: > >>>>>>> From: Leon Romanovsky <leonro(a)nvidia.com> > >>>>>>> > >>>>>>> Export the pci_p2pdma_map_type() function to allow external modules > >>>>>>> and subsystems to determine the appropriate mapping type for P2PDMA > >>>>>>> transfers between a provider and target device. > >>>>>> > >>>>>> External modules have no business doing this. > >>>>> > >>>>> VFIO PCI code is built as module. There is no way to access PCI p2p code > >>>>> without exporting functions in it. > >>>> > >>>> The solution that would make more sense to me would be for either > >>>> dma_iova_try_alloc() or another helper in dma-iommu.c to handle the > >>>> P2PDMA case. > >>> > >>> This has nothing to do with dma-iommu.c, the decisions here still need > >>> to be made even if dma-iommu.c is not compiled in. > >> > >> Doesn't it though? Every single call in patch 10 to the newly exported > >> PCI functions calls into the the dma-iommu functions. Patch 10 has lots of flows, only one will end up in dma-iommu.c vfio_pci_dma_buf_map() calls pci_p2pdma_bus_addr_map(), dma_iova_link(), dma_map_phys(). Only iova_link would call to dma-iommu.c - if dma_map_phys() is called we know that dma-iommu.c won't be called by it. > >> If there were non-iommu paths then I would expect the code would > >> use the regular DMA api directly which would then call in to > >> dma-iommu. > > > > If p2p type is PCI_P2PDMA_MAP_BUS_ADDR, there will no dma-iommu and DMA > > at all. > > I understand that and it is completely beside my point. > > If the dma mapping for P2P memory doesn't need to create an iommu > mapping then that's fine. But it should be the dma-iommu layer to decide > that. So above, we can't use dma-iommu.c, it might not be compiled into the kernel but the dma_map_phys() path is still valid. > It's not a decision that should be made by every driver doing this > kind of thing. Sort of, I think we are trying to get to some place where there are subsystem, or at least data structure specific helpers that do this (ie nvme has BIO helpers), but the helpers should be running this logic directly for performance. Leon hasn't done it but I think we should see helpers for DMABUF too encapsulating the logic shown in patch 10. I think we need to prove it out these basic points first before trying to go and convert a bunch of GPU drivers. The vfio in patch 10 is not the full example since it only has a single scatter/gather" effectively, but the generalized version loops over pci_p2pdma_bus_addr_map(), dma_iova_link(), dma_map_phys() for each page. Part of the new API design is to only do one kind of mapping operation at once, and part of the design is we know that the P2P type is fixed. It makes no performance sense to check the type inside the pci_p2pdma_bus_addr_map()/ dma_iova_link()/dma_map_phys() within the per-page loop. I do think some level of abstraction has been lost here in pursuit of performance. If someone does have a better way to structure this without a performance hit then fantastic, but thats going back and revising the new DMA API. This just builds on top of that, and yes, it is not so abstract. Jason

3 weeks

Re: [PATCH 05/10] PCI/P2PDMA: Export pci_p2pdma_map_type() function

by Leon Romanovsky

On Mon, Jul 28, 2025 at 10:12:31AM -0600, Logan Gunthorpe wrote: > > > On 2025-07-27 13:05, Jason Gunthorpe wrote: > > On Fri, Jul 25, 2025 at 10:30:46AM -0600, Logan Gunthorpe wrote: > >> > >> > >> On 2025-07-24 02:13, Leon Romanovsky wrote: > >>> On Thu, Jul 24, 2025 at 10:03:13AM +0200, Christoph Hellwig wrote: > >>>> On Wed, Jul 23, 2025 at 04:00:06PM +0300, Leon Romanovsky wrote: > >>>>> From: Leon Romanovsky <leonro(a)nvidia.com> > >>>>> > >>>>> Export the pci_p2pdma_map_type() function to allow external modules > >>>>> and subsystems to determine the appropriate mapping type for P2PDMA > >>>>> transfers between a provider and target device. > >>>> > >>>> External modules have no business doing this. > >>> > >>> VFIO PCI code is built as module. There is no way to access PCI p2p code > >>> without exporting functions in it. > >> > >> The solution that would make more sense to me would be for either > >> dma_iova_try_alloc() or another helper in dma-iommu.c to handle the > >> P2PDMA case. > > > > This has nothing to do with dma-iommu.c, the decisions here still need > > to be made even if dma-iommu.c is not compiled in. > > Doesn't it though? Every single call in patch 10 to the newly exported > PCI functions calls into the the dma-iommu functions. If there were > non-iommu paths then I would expect the code would use the regular DMA > api directly which would then call in to dma-iommu. If p2p type is PCI_P2PDMA_MAP_BUS_ADDR, there will no dma-iommu and DMA at all. +static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct vfio_pci_dma_buf *priv = dmabuf->priv; + + if (!attachment->peer2peer) + return -EOPNOTSUPP; + + if (priv->revoked) + return -ENODEV; + + switch (pci_p2pdma_map_type(priv->vdev->provider, attachment->dev)) { + case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: + break; + case PCI_P2PDMA_MAP_BUS_ADDR: + /* + * There is no need in IOVA at all for this flow. + * We rely on attachment->priv == NULL as a marker + * for this mode. + */ + return 0; + default: + return -EINVAL; + } + + attachment->priv = kzalloc(sizeof(struct dma_iova_state), GFP_KERNEL); + if (!attachment->priv) + return -ENOMEM; + + dma_iova_try_alloc(attachment->dev, attachment->priv, 0, priv->phys_vec.len); + return 0; +}

3 weeks, 1 day

[PATCH v4] Documentation: dma-buf: heaps: Add naming guidelines

by Maxime Ripard

We've discussed a number of times of how some heap names are bad, but not really what makes a good heap name. Let's document what we expect the heap names to look like. Reviewed-by: Andrew Davis <afd(a)ti.com> Reviewed-by: Bagas Sanjaya <bagasdotme(a)gmail.com> Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- Changes in v4: - Dropped *all* the cacheable mentions - Link to v3: https://lore.kernel.org/r/20250717-dma-buf-heap-names-doc-v3-1-d2dbb4b95ef6… Changes in v3: - Grammar, spelling fixes - Remove the cacheable / uncacheable name suggestion - Link to v2: https://lore.kernel.org/r/20250616-dma-buf-heap-names-doc-v2-1-8ae43174cdbf… Changes in v2: - Added justifications for each requirement / suggestions - Added a mention and example of buffer attributes - Link to v1: https://lore.kernel.org/r/20250520-dma-buf-heap-names-doc-v1-1-ab31f74809ee… --- Documentation/userspace-api/dma-buf-heaps.rst | 35 +++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/Documentation/userspace-api/dma-buf-heaps.rst b/Documentation/userspace-api/dma-buf-heaps.rst index 535f49047ce6450796bf4380c989e109355efc05..1ced2720f929432661182f1a3a88aa1ff80bd6af 100644 --- a/Documentation/userspace-api/dma-buf-heaps.rst +++ b/Documentation/userspace-api/dma-buf-heaps.rst @@ -21,5 +21,40 @@ following heaps: usually created either through the kernel commandline through the `cma` parameter, a memory region Device-Tree node with the `linux,cma-default` property set, or through the `CMA_SIZE_MBYTES` or `CMA_SIZE_PERCENTAGE` Kconfig options. Depending on the platform, it might be called ``reserved``, ``linux,cma``, or ``default-pool``. + +Naming Convention +================= + +``dma-buf`` heaps name should meet a number of constraints: + +- The name must be stable, and must not change from one version to the other. + Userspace identifies heaps by their name, so if the names ever change, we + would be likely to introduce regressions. + +- The name must describe the memory region the heap will allocate from, and + must uniquely identify it in a given platform. Since userspace applications + use the heap name as the discriminant, it must be able to tell which heap it + wants to use reliably if there's multiple heaps. + +- The name must not mention implementation details, such as the allocator. The + heap driver will change over time, and implementation details when it was + introduced might not be relevant in the future. + +- The name should describe properties of the buffers that would be allocated. + Doing so will make heap identification easier for userspace. Such properties + are: + + - ``contiguous`` for physically contiguous buffers; + + - ``protected`` for encrypted buffers not accessible the OS; + +- The name may describe intended usage. Doing so will make heap identification + easier for userspace applications and users. + +For example, assuming a platform with a reserved memory region located +at the RAM address 0x42000000, intended to allocate video framebuffers, +physically contiguous, and backed by the CMA kernel allocator, good +names would be ``memory@42000000-contiguous`` or ``video@42000000``, but +``cma-video`` wouldn't. --- base-commit: 038d61fd642278bab63ee8ef722c50d10ab01e8f change-id: 20250520-dma-buf-heap-names-doc-31261aa0cfe6 Best regards, -- Maxime Ripard <mripard(a)kernel.org>

3 weeks, 1 day

[PATCH v3] Documentation: dma-buf: heaps: Add naming guidelines

by Maxime Ripard

We've discussed a number of times of how some heap names are bad, but not really what makes a good heap name. Let's document what we expect the heap names to look like. Reviewed-by: Bagas Sanjaya <bagasdotme(a)gmail.com> Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- Changes in v3: - Grammar, spelling fixes - Remove the cacheable / uncacheable name suggestion - Link to v2: https://lore.kernel.org/r/20250616-dma-buf-heap-names-doc-v2-1-8ae43174cdbf… Changes in v2: - Added justifications for each requirement / suggestions - Added a mention and example of buffer attributes - Link to v1: https://lore.kernel.org/r/20250520-dma-buf-heap-names-doc-v1-1-ab31f74809ee… --- Documentation/userspace-api/dma-buf-heaps.rst | 35 +++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/Documentation/userspace-api/dma-buf-heaps.rst b/Documentation/userspace-api/dma-buf-heaps.rst index 535f49047ce6450796bf4380c989e109355efc05..3ee4e7961fe390ba356a2125d53b060546c3e4a6 100644 --- a/Documentation/userspace-api/dma-buf-heaps.rst +++ b/Documentation/userspace-api/dma-buf-heaps.rst @@ -21,5 +21,40 @@ following heaps: usually created either through the kernel commandline through the `cma` parameter, a memory region Device-Tree node with the `linux,cma-default` property set, or through the `CMA_SIZE_MBYTES` or `CMA_SIZE_PERCENTAGE` Kconfig options. Depending on the platform, it might be called ``reserved``, ``linux,cma``, or ``default-pool``. + +Naming Convention +================= + +``dma-buf`` heaps name should meet a number of constraints: + +- The name must be stable, and must not change from one version to the other. + Userspace identifies heaps by their name, so if the names ever change, we + would be likely to introduce regressions. + +- The name must describe the memory region the heap will allocate from, and + must uniquely identify it in a given platform. Since userspace applications + use the heap name as the discriminant, it must be able to tell which heap it + wants to use reliably if there's multiple heaps. + +- The name must not mention implementation details, such as the allocator. The + heap driver will change over time, and implementation details when it was + introduced might not be relevant in the future. + +- The name should describe properties of the buffers that would be allocated. + Doing so will make heap identification easier for userspace. Such properties + are: + + - ``contiguous`` for physically contiguous buffers; + + - ``protected`` for encrypted buffers not accessible the OS; + +- The name may describe intended usage. Doing so will make heap identification + easier for userspace applications and users. + +For example, assuming a platform with a reserved memory region located at the +RAM address 0x42000000, intended to allocate video framebuffers, physically +contiguous, and backed by the CMA kernel allocator, good names would be +``memory@42000000-cacheable-contiguous`` or ``video@42000000``, but +``cma-video`` wouldn't. --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250520-dma-buf-heap-names-doc-31261aa0cfe6 Best regards, -- Maxime Ripard <mripard(a)kernel.org>

3 weeks, 1 day

Re: [PATCH 05/10] PCI/P2PDMA: Export pci_p2pdma_map_type() function

by Jason Gunthorpe

On Fri, Jul 25, 2025 at 10:30:46AM -0600, Logan Gunthorpe wrote: > > > On 2025-07-24 02:13, Leon Romanovsky wrote: > > On Thu, Jul 24, 2025 at 10:03:13AM +0200, Christoph Hellwig wrote: > >> On Wed, Jul 23, 2025 at 04:00:06PM +0300, Leon Romanovsky wrote: > >>> From: Leon Romanovsky <leonro(a)nvidia.com> > >>> > >>> Export the pci_p2pdma_map_type() function to allow external modules > >>> and subsystems to determine the appropriate mapping type for P2PDMA > >>> transfers between a provider and target device. > >> > >> External modules have no business doing this. > > > > VFIO PCI code is built as module. There is no way to access PCI p2p code > > without exporting functions in it. > > The solution that would make more sense to me would be for either > dma_iova_try_alloc() or another helper in dma-iommu.c to handle the > P2PDMA case. This has nothing to do with dma-iommu.c, the decisions here still need to be made even if dma-iommu.c is not compiled in. It could be exported from the main dma code, but I think it would just be a 1 line wrapper around the existing function? I'd rather rename the functions and leave them in the p2pdma.c files... Jason

3 weeks, 2 days

Re: [PATCH 10/10] vfio/pci: Add dma-buf export support for MMIO regions

by Leon Romanovsky

On Fri, Jul 25, 2025 at 05:34:40AM +0000, Kasireddy, Vivek wrote: > Hi Leon, > > > Subject: Re: [PATCH 10/10] vfio/pci: Add dma-buf export support for MMIO > > regions > > > > > > > > > > From: Leon Romanovsky <leonro(a)nvidia.com> > > > > > > > > Add support for exporting PCI device MMIO regions through dma-buf, > > > > enabling safe sharing of non-struct page memory with controlled > > > > lifetime management. This allows RDMA and other subsystems to > > import > > > > dma-buf FDs and build them into memory regions for PCI P2P > > operations. > > > > > > > > The implementation provides a revocable attachment mechanism using > > > > dma-buf move operations. MMIO regions are normally pinned as BARs > > > > don't change physical addresses, but access is revoked when the VFIO > > > > device is closed or a PCI reset is issued. This ensures kernel > > > > self-defense against potentially hostile userspace. > > > > > > > > Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> > > > > Signed-off-by: Vivek Kasireddy <vivek.kasireddy(a)intel.com> > > > > Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> > > > > --- > > > > drivers/vfio/pci/Kconfig | 20 ++ > > > > drivers/vfio/pci/Makefile | 2 + > > > > drivers/vfio/pci/vfio_pci_config.c | 22 +- > > > > drivers/vfio/pci/vfio_pci_core.c | 25 ++- > > > > drivers/vfio/pci/vfio_pci_dmabuf.c | 321 > > +++++++++++++++++++++++++++++ > > > > drivers/vfio/pci/vfio_pci_priv.h | 23 +++ > > > > include/linux/dma-buf.h | 1 + > > > > include/linux/vfio_pci_core.h | 3 + > > > > include/uapi/linux/vfio.h | 19 ++ > > > > 9 files changed, 431 insertions(+), 5 deletions(-) > > > > create mode 100644 drivers/vfio/pci/vfio_pci_dmabuf.c > > > > <...> > > > > > > +static int validate_dmabuf_input(struct vfio_pci_core_device *vdev, > > > > + struct vfio_device_feature_dma_buf > > *dma_buf) > > > > +{ > > > > + struct pci_dev *pdev = vdev->pdev; > > > > + u32 bar = dma_buf->region_index; > > > > + u64 offset = dma_buf->offset; > > > > + u64 len = dma_buf->length; > > > > + resource_size_t bar_size; > > > > + u64 sum; > > > > + > > > > + /* > > > > + * For PCI the region_index is the BAR number like everything else. > > > > + */ > > > > + if (bar >= VFIO_PCI_ROM_REGION_INDEX) > > > > + return -ENODEV; > > > > <...> > > > > > > +/** > > > > + * Upon VFIO_DEVICE_FEATURE_GET create a dma_buf fd for the > > > > + * regions selected. > > > > + * > > > > + * open_flags are the typical flags passed to open(2), eg O_RDWR, > > > > O_CLOEXEC, > > > > + * etc. offset/length specify a slice of the region to create the dmabuf > > from. > > > > + * nr_ranges is the total number of (P2P DMA) ranges that comprise the > > > > dmabuf. > > > Any particular reason why you dropped the option (nr_ranges) of creating > > a > > > single dmabuf from multiple ranges of an MMIO region? > > > > I did it for two reasons. First, I wanted to simplify the code in order > > to speed-up discussion over the patchset itself. Second, I failed to > > find justification for need of multiple ranges, as the number of BARs > > are limited by VFIO_PCI_ROM_REGION_INDEX (6) and same functionality > > can be achieved by multiple calls to DMABUF import. > I don't think the same functionality can be achieved by multiple calls to > dmabuf import. AFAIU, a dmabuf (as of today) is backed by a SGL that can > have multiple entries because it represents a scattered buffer (multiple > non-contiguous entries in System RAM or an MMIO region). I don't know all the reasons why SG was chosen, but one of the main reasons is that DMA SG API was the only one possible way to handle p2p transfers (peer2peer flag). > But in this patch you are constraining it such that only one entry associated with a > buffer would be included, which effectively means that we cannot create > a dmabuf to represent scattered buffers (located in a single MMIO region > such as VRAM or other device memory) anymore. Yes > > > > > > > > > Restricting the dmabuf to a single range (or having to create multiple > > dmabufs > > > to represent multiple regions/ranges associated with a single scattered > > buffer) > > > would be very limiting and may not work in all cases. For instance, in my > > use-case, > > > I am trying to share a large (4k mode) framebuffer (FB) located in GPU's > > VRAM > > > between two (p2p compatible) GPU devices. And, this would probably not > > work > > > given that allocating a large contiguous FB (nr_ranges = 1) in VRAM may > > not be > > > feasible when there is memory pressure. > > > > Can you please help me and point to the place in the code where this can > > fail? > > I'm probably missing something basic as there are no large allocations > > in the current patchset. > Sorry, I was not very clear. What I meant is that it is not prudent to assume that > there will only be one range associated with an MMIO region which we need to > consider while creating a dmabuf. And, I was pointing out my use-case as an > example where vfio-pci needs to create a dmabuf for a large buffer (FB) that > would likely be scattered (and not contiguous) in an MMIO region (such as VRAM). > > Let me further explain with my use-case. Here is a link to my Qemu-based test: > https://gitlab.freedesktop.org/Vivek/qemu/-/commit/b2bdb16d9cfaf55384c95b1f… Ohh, thanks. I'll add nr_ranges in next version. I see that you are using same region_index for all ranges and this is how I would like to keep it: "multiple nr_ranges, same region_index". Thanks

3 weeks, 2 days

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig July 2025