Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

9 participants
3613 discussions

[PATCH] dma-buf: heaps: cma: register a dmem region for each cma heap

by Eric Chanudet

The cma dma-buf heaps let userspace allocate buffers in CMA regions without enforcing limits. Register a dmem region per cma heap and charge against it when allocating a buffer in a cma heap. For the default cma region, two heaps may be created for the same cma range: commit 854acbe75ff4 ("dma-buf: heaps: Give default CMA heap a fixed name") Introduced /dev/dma_heap/default_cma_region commit 4f5f8baf7341 ("dma-buf: heaps: cma: Create CMA heap for each CMA reserved region") Created a CMA heap for each CMA region, which might create a duplicate heap to the default one, e.g: /dev/dma_heap/default_cma_region /dev/dma_heap/reserved Removing the legacy heap would break user API. So handle the special case by using one dmem between the two heaps to account charges correctly. Signed-off-by: Eric Chanudet <echanude(a)redhat.com> --- In continuation with introducing cgroup for the system heap[1], this behavior is enabled based on dma_heap.mem_accounting, disabled by default. dmem is chosen for CMA heaps as it allows limits to be set for each region backing each heap. There is one caveat for the default cma range that may accessible through two different cma heaps, which is treated as a special case. [1] https://lore.kernel.org/all/20260116-dmabuf-heap-system-memcg-v3-0-ecc6b62c… --- drivers/dma-buf/heaps/cma_heap.c | 51 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 46 insertions(+), 5 deletions(-) diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 49cc45fb42dd7200c3c14384bcfdbe85323454b1..608af8ad6bce7fe0321da6d8f1b65a69f5d8d950 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -27,6 +27,7 @@ #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/cgroup_dmem.h> #define DEFAULT_CMA_NAME "default_cma_region" @@ -46,7 +47,9 @@ int __init dma_heap_cma_register_heap(struct cma *cma) struct cma_heap { struct dma_heap *heap; struct cma *cma; + struct dmem_cgroup_region *cg; }; +static struct dmem_cgroup_region *default_cma_cg; struct cma_heap_buffer { struct cma_heap *heap; @@ -58,6 +61,7 @@ struct cma_heap_buffer { pgoff_t pagecount; int vmap_cnt; void *vaddr; + struct dmem_cgroup_pool_state *pool; }; struct dma_heap_attachment { @@ -276,6 +280,7 @@ static void cma_heap_dma_buf_release(struct dma_buf *dmabuf) kfree(buffer->pages); /* release memory */ cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount); + dmem_cgroup_uncharge(buffer->pool, buffer->len); kfree(buffer); } @@ -319,9 +324,16 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, if (align > CONFIG_CMA_ALIGNMENT) align = CONFIG_CMA_ALIGNMENT; + if (mem_accounting) { + ret = dmem_cgroup_try_charge(cma_heap->cg, size, + &buffer->pool, NULL); + if (ret) + goto free_buffer; + } + cma_pages = cma_alloc(cma_heap->cma, pagecount, align, false); if (!cma_pages) - goto free_buffer; + goto uncharge_cgroup; /* Clear the cma pages */ if (PageHighMem(cma_pages)) { @@ -376,6 +388,8 @@ static struct dma_buf *cma_heap_allocate(struct dma_heap *heap, kfree(buffer->pages); free_cma: cma_release(cma_heap->cma, cma_pages, pagecount); +uncharge_cgroup: + dmem_cgroup_uncharge(buffer->pool, size); free_buffer: kfree(buffer); @@ -390,25 +404,52 @@ static int __init __add_cma_heap(struct cma *cma, const char *name) { struct dma_heap_export_info exp_info; struct cma_heap *cma_heap; + struct dmem_cgroup_region *region; + int ret; cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL); if (!cma_heap) return -ENOMEM; cma_heap->cma = cma; + /* + * If two heaps are created for the default cma region, use the same + * dmem for them. They both use the same memory pool. + */ + if (dev_get_cma_area(NULL) == cma && default_cma_cg) + region = default_cma_cg; + else { + region = dmem_cgroup_register_region(cma_get_size(cma), "cma/%s", name); + if (IS_ERR(region)) { + ret = PTR_ERR(region); + goto free_cma_heap; + } + } + cma_heap->cg = region; + exp_info.name = name; exp_info.ops = &cma_heap_ops; exp_info.priv = cma_heap; cma_heap->heap = dma_heap_add(&exp_info); if (IS_ERR(cma_heap->heap)) { - int ret = PTR_ERR(cma_heap->heap); - - kfree(cma_heap); - return ret; + ret = PTR_ERR(cma_heap->heap); + goto cg_unregister; } + if (dev_get_cma_area(NULL) == cma && !default_cma_cg) + default_cma_cg = region; + return 0; + +cg_unregister: + /* default_cma_cg == cma_heap->cg only for the duplicate heap. */ + if (default_cma_cg != cma_heap->cg) + dmem_cgroup_unregister_region(cma_heap->cg); +free_cma_heap: + kfree(cma_heap); + + return ret; } static int __init add_cma_heaps(void) --- base-commit: 3d65e4c276b32c03450261d114e495fda03c8e97 change-id: 20260128-dmabuf-heap-cma-dmem-f4120a2df4a8 Best regards, -- Eric Chanudet <echanude(a)redhat.com>

8 months

[PATCH v6 0/8] dma-buf: Use revoke mechanism to invalidate shared buffers

by Leon Romanovsky

Changelog: v6: * Added Reviewed-by tags. * Changed for blocking wait_for_completion() in VFIO * Fixed race between ->attach and move_notify, where priv->revoked is flipped and lock is released. v5: https://patch.msgid.link/20260124-dmabuf-revoke-v5-0-f98fca917e96@nvidia.com * Documented the DMA-BUF expectations around DMA unmap. * Added wait support in VFIO for DMA unmap. * Reordered patches. * Improved commit messages to document even more. v4: https://lore.kernel.org/all/20260121-dmabuf-revoke-v4-0-d311cbc8633d@nvidia… * Changed DMA_RESV_USAGE_KERNEL to DMA_RESV_USAGE_BOOKKEEP. * Made .invalidate_mapping() truly optional. * Added patch which renames dma_buf_move_notify() to be dma_buf_invalidate_mappings(). * Restored dma_buf_attachment_is_dynamic() function. v3: https://lore.kernel.org/all/20260120-dmabuf-revoke-v3-0-b7e0b07b8214@nvidia… * Used Jason's wordings for commits and cover letter. * Removed IOMMUFD patch. * Renamed dma_buf_attachment_is_revoke() to be dma_buf_attach_revocable(). * Added patch to remove CONFIG_DMABUF_MOVE_NOTIFY. * Added Reviewed-by tags. * Called to dma_resv_wait_timeout() after dma_buf_move_notify() in VFIO. * Added dma_buf_attach_revocable() check to VFIO DMABUF attach function. * Slightly changed commit messages. v2: https://patch.msgid.link/20260118-dmabuf-revoke-v2-0-a03bb27c0875@nvidia.com * Changed series to document the revoke semantics instead of implementing it. v1: https://patch.msgid.link/20260111-dmabuf-revoke-v1-0-fb4bcc8c259b@nvidia.com ------------------------------------------------------------------------- This series is based on latest VFIO fix, which will be sent to Linus very soon. https://lore.kernel.org/all/20260121-vfio-add-pin-v1-1-4e04916b17f1@nvidia.… Thanks ------------------------------------------------------------------------- This series documents a dma-buf “revoke” mechanism: to allow a dma-buf exporter to explicitly invalidate (“kill”) a shared buffer after it has been distributed to importers, so that further CPU and device access is prevented and importers reliably observe failure. The change in this series is to properly document and use existing core “revoked” state on the dma-buf object and a corresponding exporter-triggered revoke operation. dma-buf has quietly allowed calling move_notify on pinned dma-bufs, even though legacy importers using dma_buf_attach() would simply ignore these calls. The intention was that move_notify() would tell the importer to expedite it's unmapping process and once the importer is fully finished with DMA it would unmap the dma-buf which finally signals that the importer is no longer ever going to touch the memory again. Importers that touch past their unmap() call can trigger IOMMU errors, AER and beyond, however read-and-discard access between move_notify() and unmap is allowed. Thus, we can define the exporter's revoke sequence for pinned dma-buf as: dma_resv_lock(dmabuf->resv, NULL); // Prevent new mappings from being established priv->revoked = true; // Tell all importers to eventually unmap dma_buf_invalidate_mappings(dmabuf); // Wait for any inprogress fences on the old mapping dma_resv_wait_timeout(dmabuf->resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); dma_resv_unlock(dmabuf->resv, NULL); // Wait for all importers to complete unmap wait_for_completion(&priv->unmapp_comp); However, dma-buf also supports importers that don't do anything on move_notify(), and will not unmap the buffer in bounded time. Since such importers would cause the above sequence to hang, a new mechanism is needed to detect incompatible importers. Introduce dma_buf_attach_revocable() which if true indicates the above sequence is safe to use and will complete in kernel-only bounded time for this attachment. Unfortunately dma_buf_attach_revocable() is going to fail for the popular RDMA pinned importer, which means we cannot introduce it to existing places using pinned move_notify() without potentially breaking existing userspace flows. Existing exporters that only trigger this flow for RAS errors should not call dma_buf_attach_revocable() and will suffer an unbounded block on the final completion, hoping that the userspace will notice the RAS and clean things up. Without revoke support on the RDMA pinned importers it doesn't seem like any other non-breaking option is currently possible. For new exporters, like VFIO and RDMA, that have userspace triggered revoke events, the unbouned sleep would not be acceptable. They can call dma_buf_attach_revocable() and will not work with the RDMA pinned importer from day 0, preventing regressions. In the process add documentation explaining the above details. Thanks Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> --- Leon Romanovsky (8): dma-buf: Rename .move_notify() callback to a clearer identifier dma-buf: Rename dma_buf_move_notify() to dma_buf_invalidate_mappings() dma-buf: Always build with DMABUF_MOVE_NOTIFY vfio: Wait for dma-buf invalidation to complete dma-buf: Make .invalidate_mapping() truly optional dma-buf: Add dma_buf_attach_revocable() vfio: Permit VFIO to work with pinned importers iommufd: Add dma_buf_pin() drivers/dma-buf/Kconfig | 12 ----- drivers/dma-buf/dma-buf.c | 69 +++++++++++++++++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 14 ++--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- drivers/gpu/drm/amd/amdkfd/Kconfig | 2 +- drivers/gpu/drm/virtio/virtgpu_prime.c | 2 +- drivers/gpu/drm/xe/tests/xe_dma_buf.c | 7 ++- drivers/gpu/drm/xe/xe_bo.c | 2 +- drivers/gpu/drm/xe/xe_dma_buf.c | 14 ++--- drivers/infiniband/core/umem_dmabuf.c | 13 ----- drivers/infiniband/hw/mlx5/mr.c | 2 +- drivers/iommu/iommufd/pages.c | 11 +++- drivers/iommu/iommufd/selftest.c | 2 +- drivers/vfio/pci/vfio_pci_dmabuf.c | 84 ++++++++++++++++++++++------- include/linux/dma-buf.h | 17 +++--- 15 files changed, 157 insertions(+), 96 deletions(-) --- base-commit: 61ceaf236115f20f4fdd7cf60f883ada1063349a change-id: 20251221-dmabuf-revoke-b90ef16e4236 Best regards, -- Leon Romanovsky <leonro(a)nvidia.com>

8 months, 1 week

[PATCH v5 0/8] dma-buf: Use revoke mechanism to invalidate shared buffers

by Leon Romanovsky

Changelog: v5: * Documented the DMA-BUF expectations around DMA unmap. * Added wait support in VFIO for DMA unmap. * Reordered patches. * Improved commit messages to document even more. v4: https://lore.kernel.org/all/20260121-dmabuf-revoke-v4-0-d311cbc8633d@nvidia… * Changed DMA_RESV_USAGE_KERNEL to DMA_RESV_USAGE_BOOKKEEP. * Made .invalidate_mapping() truly optional. * Added patch which renames dma_buf_move_notify() to be dma_buf_invalidate_mappings(). * Restored dma_buf_attachment_is_dynamic() function. v3: https://lore.kernel.org/all/20260120-dmabuf-revoke-v3-0-b7e0b07b8214@nvidia… * Used Jason's wordings for commits and cover letter. * Removed IOMMUFD patch. * Renamed dma_buf_attachment_is_revoke() to be dma_buf_attach_revocable(). * Added patch to remove CONFIG_DMABUF_MOVE_NOTIFY. * Added Reviewed-by tags. * Called to dma_resv_wait_timeout() after dma_buf_move_notify() in VFIO. * Added dma_buf_attach_revocable() check to VFIO DMABUF attach function. * Slightly changed commit messages. v2: https://patch.msgid.link/20260118-dmabuf-revoke-v2-0-a03bb27c0875@nvidia.com * Changed series to document the revoke semantics instead of implementing it. v1: https://patch.msgid.link/20260111-dmabuf-revoke-v1-0-fb4bcc8c259b@nvidia.com ------------------------------------------------------------------------- This series is based on latest VFIO fix, which will be sent to Linus very soon. https://lore.kernel.org/all/20260121-vfio-add-pin-v1-1-4e04916b17f1@nvidia.… Thanks ------------------------------------------------------------------------- This series documents a dma-buf “revoke” mechanism: to allow a dma-buf exporter to explicitly invalidate (“kill”) a shared buffer after it has been distributed to importers, so that further CPU and device access is prevented and importers reliably observe failure. The change in this series is to properly document and use existing core “revoked” state on the dma-buf object and a corresponding exporter-triggered revoke operation. dma-buf has quietly allowed calling move_notify on pinned dma-bufs, even though legacy importers using dma_buf_attach() would simply ignore these calls. The intention was that move_notify() would tell the importer to expedite it's unmapping process and once the importer is fully finished with DMA it would unmap the dma-buf which finally signals that the importer is no longer ever going to touch the memory again. Importers that touch past their unmap() call can trigger IOMMU errors, AER and beyond, however read-and-discard access between move_notify() and unmap is allowed. Thus, we can define the exporter's revoke sequence for pinned dma-buf as: dma_resv_lock(dmabuf->resv, NULL); // Prevent new mappings from being established priv->revoked = true; // Tell all importers to eventually unmap dma_buf_invalidate_mappings(dmabuf); // Wait for any inprogress fences on the old mapping dma_resv_wait_timeout(dmabuf->resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); dma_resv_unlock(dmabuf->resv, NULL); // Wait for all importers to complete unmap wait_for_completion(&priv->unmapp_comp); However, dma-buf also supports importers that don't do anything on move_notify(), and will not unmap the buffer in bounded time. Since such importers would cause the above sequence to hang, a new mechanism is needed to detect incompatible importers. Introduce dma_buf_attach_revocable() which if true indicates the above sequence is safe to use and will complete in kernel-only bounded time for this attachment. Unfortunately dma_buf_attach_revocable() is going to fail for the popular RDMA pinned importer, which means we cannot introduce it to existing places using pinned move_notify() without potentially breaking existing userspace flows. Existing exporters that only trigger this flow for RAS errors should not call dma_buf_attach_revocable() and will suffer an unbounded block on the final completion, hoping that the userspace will notice the RAS and clean things up. Without revoke support on the RDMA pinned importers it doesn't seem like any other non-breaking option is currently possible. For new exporters, like VFIO and RDMA, that have userspace triggered revoke events, the unbouned sleep would not be acceptable. They can call dma_buf_attach_revocable() and will not work with the RDMA pinned importer from day 0, preventing regressions. In the process add documentation explaining the above details. Thanks Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> --- Leon Romanovsky (8): dma-buf: Rename .move_notify() callback to a clearer identifier dma-buf: Rename dma_buf_move_notify() to dma_buf_invalidate_mappings() dma-buf: Always build with DMABUF_MOVE_NOTIFY vfio: Wait for dma-buf invalidation to complete dma-buf: Make .invalidate_mapping() truly optional dma-buf: Add dma_buf_attach_revocable() vfio: Permit VFIO to work with pinned importers iommufd: Add dma_buf_pin() drivers/dma-buf/Kconfig | 12 ---- drivers/dma-buf/dma-buf.c | 69 +++++++++++++++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 14 ++--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- drivers/gpu/drm/amd/amdkfd/Kconfig | 2 +- drivers/gpu/drm/virtio/virtgpu_prime.c | 2 +- drivers/gpu/drm/xe/tests/xe_dma_buf.c | 7 +-- drivers/gpu/drm/xe/xe_bo.c | 2 +- drivers/gpu/drm/xe/xe_dma_buf.c | 14 ++--- drivers/infiniband/core/umem_dmabuf.c | 13 ----- drivers/infiniband/hw/mlx5/mr.c | 2 +- drivers/iommu/iommufd/pages.c | 11 +++- drivers/iommu/iommufd/selftest.c | 2 +- drivers/vfio/pci/vfio_pci_dmabuf.c | 90 +++++++++++++++++++++++------ include/linux/dma-buf.h | 17 +++--- 15 files changed, 164 insertions(+), 95 deletions(-) --- base-commit: 61ceaf236115f20f4fdd7cf60f883ada1063349a change-id: 20251221-dmabuf-revoke-b90ef16e4236 Best regards, -- Leon Romanovsky <leonro(a)nvidia.com>

8 months, 1 week

[RFC v2 0/8] dma-buf: Add support for mapping dmabufs via interconnects

by Vivek Kasireddy

In a typical dma-buf use case, a dmabuf exporter makes its buffer buffer available to an importer by mapping it using DMA APIs such as dma_map_sgtable() or dma_map_resource(). However, this is not desirable in some cases where the exporter and importer are directly connected via a physical or virtual link (or interconnect) and the importer can access the buffer without having it DMA mapped. So, to address this scenario, this patch series adds APIs to map/ unmap dmabufs via interconnects and also provides a helper to identify the first common interconnect between the exporter and importer. Furthermore, this patch series also adds support for IOV interconnect in the vfio-pci driver and Intel Xe driver. The IOV interconnect is a virtual interconnect between an SRIOV physical function (PF) and its virtual functions (VFs). And, for the IOV interconnect, the addresses associated with a buffer are shared using an xarray (instead of an sg_table) that is populated with entries of type struct range. The dma-buf patches in this series are based on ideas/suggestions provided by Jason Gunthorpe, Christian Koenig and Thomas Hellström. Changelog: RFC -> RFCv2: - Add documentation for the new dma-buf APIs and types (Thomas) - Change the interconnect type from enum to unique pointer (Thomas) - Moved the new dma-buf APIs to a separate file - Store a copy of the interconnect matching data in the attachment - Simplified the macros to create and match interconnects - Use struct device instead of struct pci_dev in match data - Replace DRM_INTERCONNECT_DRIVER with XE_INTERCONNECT_VRAM during address encoding (Matt, Thomas) - Drop is_devmem_external and instead rely on bo->dma_data.dma_addr to check for imported VRAM BOs (Matt) - Pass XE_PAGE_SIZE as the last parameter to xe_bo_addr (Matt) - Add a check to prevent malicious VF from accessing other VF's addresses (Thomas) - Fallback to legacy (map_dma_buf) mapping method if mapping via interconnect fails Patchset overview: Patch 1-3: Add dma-buf APIs to map/unmap and match Patch 4: Add support for IOV interconnect in vfio-pci driver Patch 5: Add support for IOV interconnect in Xe driver Patch 6-8: Create and use a new dma_addr array for LMEM based dmabuf BOs to store translated addresses (DPAs) This series is rebased on top of the following repo: https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma.git/log/?h=… Associated Qemu patch series: https://lore.kernel.org/qemu-devel/20251003234138.85820-1-vivek.kasireddy@i… Associated vfio-pci patch series: https://lore.kernel.org/dri-devel/cover.1760368250.git.leon@kernel.org/ This series is tested using the following method: - Run Qemu with the following relevant options: qemu-system-x86_64 -m 4096m .... -device ioh3420,id=root_port1,bus=pcie.0 -device x3130-upstream,id=upstream1,bus=root_port1 -device xio3130-downstream,id=downstream1,bus=upstream1,chassis=9 -device xio3130-downstream,id=downstream2,bus=upstream1,chassis=10 -device vfio-pci,host=0000:03:00.1,bus=downstream1 -device virtio-gpu,max_outputs=1,blob=true,xres=1920,yres=1080,bus=downstream2 -display gtk,gl=on -object memory-backend-memfd,id=mem1,size=4096M -machine q35,accel=kvm,memory-backend=mem1 ... - Run Gnome Wayland with the following options in the Guest VM: # cat /usr/lib/udev/rules.d/61-mutter-primary-gpu.rules ENV{DEVNAME}=="/dev/dri/card1", TAG+="mutter-device-preferred-primary", TAG+="mutter-device-disable-kms-modifiers" # XDG_SESSION_TYPE=wayland dbus-run-session -- /usr/bin/gnome-shell --wayland --no-x11 & Cc: Jason Gunthorpe <jgg(a)nvidia.com> Cc: Leon Romanovsky <leonro(a)nvidia.com> Cc: Christian Koenig <christian.koenig(a)amd.com> Cc: Sumit Semwal <sumit.semwal(a)linaro.org> Cc: Thomas Hellström <thomas.hellstrom(a)linux.intel.com> Cc: Simona Vetter <simona.vetter(a)ffwll.ch> Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: Dongwon Kim <dongwon.kim(a)intel.com> Vivek Kasireddy (8): dma-buf: Add support for map/unmap APIs for interconnects dma-buf: Add a helper to match interconnects between exporter/importer dma-buf: Create and expose IOV interconnect to all exporters/importers vfio/pci/dmabuf: Add support for IOV interconnect drm/xe/dma_buf: Add support for IOV interconnect drm/xe/pf: Add a helper function to get a VF's backing object in LMEM drm/xe/bo: Create new dma_addr array for dmabuf BOs associated with VFs drm/xe/pt: Add an additional check for dmabuf BOs while doing bind drivers/dma-buf/Makefile | 2 +- drivers/dma-buf/dma-buf-interconnect.c | 164 +++++++++++++++++++++ drivers/dma-buf/dma-buf.c | 12 +- drivers/gpu/drm/xe/xe_bo.c | 162 ++++++++++++++++++-- drivers/gpu/drm/xe/xe_bo_types.h | 6 + drivers/gpu/drm/xe/xe_dma_buf.c | 17 ++- drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 24 +++ drivers/gpu/drm/xe/xe_gt_sriov_pf_config.h | 1 + drivers/gpu/drm/xe/xe_pt.c | 8 + drivers/gpu/drm/xe/xe_sriov_pf_types.h | 19 +++ drivers/vfio/pci/vfio_pci_dmabuf.c | 135 ++++++++++++++++- include/linux/dma-buf-interconnect.h | 122 +++++++++++++++ include/linux/dma-buf.h | 41 ++++++ 13 files changed, 691 insertions(+), 22 deletions(-) create mode 100644 drivers/dma-buf/dma-buf-interconnect.c create mode 100644 include/linux/dma-buf-interconnect.h -- 2.50.1

8 months, 1 week

[PATCH rdma-next v2 0/3] RDMA: Add support for exporting dma-buf file descriptors

by Edward Srouji

This patch series introduces dma-buf export support for RDMA/InfiniBand devices, enabling userspace applications to export RDMA PCI-backed memory regions (such as device memory or mlx5 UAR pages) as dma-buf file descriptors. This allows PCI device memory to be shared with other kernel subsystems (e.g., graphics or media) or between userspace processes, via the standard dma-buf interface, avoiding unnecessary copies and enabling efficient peer-to-peer (P2P) DMA transfers. See [1] for background on dma-buf. As part of this series, we introduce a new uverbs object of type FD for dma-buf export, along with the corresponding APIs for allocation and teardown. This object encapsulates all attributes required to export a dma-buf. The implementation enforces P2P-only mappings and properly manages resource lifecycle, including: - Cleanup during driver removal or RDMA context destruction. - Revocation via dma_buf_move_notify() when the underlying mmap entries are removed. - Refactors common cleanup logic for reuse across FD uobject types. The infrastructure is generic within uverbs, allowing individual drivers to easily integrate and supply their vendor-specific implementation. The mlx5 driver is the first consumer of this new API, providing: - Initialization of PCI peer-to-peer DMA support. - mlx5-specific implementations of the mmap_get_pfns and pgoff_to_mmap_entry device operations required for dma-buf export. [1] https://docs.kernel.org/driver-api/dma-buf.html Signed-off-by: Yishai Hadas <yishaih(a)nvidia.com> Signed-off-by: Edward Srouji <edwards(a)nvidia.com> --- Changes in v2: - Split the FD uobject refactoring into a separate patch ("RDMA: Add support for exporting dma-buf file descriptors") - Remove redundant revoked check from attach callback. It is checked during map - Add pin callback that returns -EOPNOTSUPP to explicitly refuse pinned importers - Wait for pending fences after dma_buf_move_notify() using dma_resv_wait_timeout() to ensure hardware has completed all in-flight operations before proceeding - Link to v1: https://lore.kernel.org/r/20260108-dmabuf-export-v1-0-6d47d46580d3@nvidia.c… --- Yishai Hadas (3): RDMA/uverbs: Support external FD uobjects RDMA/uverbs: Add DMABUF object type and operations RDMA/mlx5: Implement DMABUF export ops drivers/infiniband/core/Makefile | 1 + drivers/infiniband/core/device.c | 2 + drivers/infiniband/core/ib_core_uverbs.c | 22 +++ drivers/infiniband/core/rdma_core.c | 63 ++++---- drivers/infiniband/core/rdma_core.h | 1 + drivers/infiniband/core/uverbs.h | 10 ++ drivers/infiniband/core/uverbs_std_types_dmabuf.c | 176 ++++++++++++++++++++++ drivers/infiniband/core/uverbs_uapi.c | 1 + drivers/infiniband/hw/mlx5/main.c | 72 +++++++++ include/rdma/ib_verbs.h | 9 ++ include/rdma/uverbs_types.h | 1 + include/uapi/rdma/ib_user_ioctl_cmds.h | 10 ++ 12 files changed, 342 insertions(+), 26 deletions(-) --- base-commit: 325e3b5431ddd27c5f93156b36838a351e3b2f72 change-id: 20260108-dmabuf-export-0d598058dd1e Best regards, -- Edward Srouji <edwards(a)nvidia.com>

8 months, 2 weeks

[PATCH v3 0/7] dma-buf: Use revoke mechanism to invalidate shared buffers

by Leon Romanovsky

Changelog: v3: * Used Jason's wordings for commits and cover letter. * Removed IOMMUFD patch. * Renamed dma_buf_attachment_is_revoke() to be dma_buf_attach_revocable(). * Added patch to remove CONFIG_DMABUF_MOVE_NOTIFY. * Added Reviewed-by tags. * Called to dma_resv_wait_timeout() after dma_buf_move_notify() in VFIO. * Added dma_buf_attach_revocable() check to VFIO DMABUF attach function. * Slightly changed commit messages. v2: https://patch.msgid.link/20260118-dmabuf-revoke-v2-0-a03bb27c0875@nvidia.com * Changed series to document the revoke semantics instead of implementing it. v1: https://patch.msgid.link/20260111-dmabuf-revoke-v1-0-fb4bcc8c259b@nvidia.com ------------------------------------------------------------------------- This series documents a dma-buf “revoke” mechanism: to allow a dma-buf exporter to explicitly invalidate (“kill”) a shared buffer after it has been distributed to importers, so that further CPU and device access is prevented and importers reliably observe failure. The change in this series is to properly document and use existing core “revoked” state on the dma-buf object and a corresponding exporter-triggered revoke operation. dma-buf has quietly allowed calling move_notify on pinned dma-bufs, even though legacy importers using dma_buf_attach() would simply ignore these calls. RDMA saw this and needed to use allow_peer2peer=true, so implemented a new-style pinned importer with an explicitly non-working move_notify() callback. This has been tolerable because the existing exporters are thought to only call move_notify() on a pinned DMABUF under RAS events and we have been willing to tolerate the UAF that results by allowing the importer to continue to use the mapping in this rare case. VFIO wants to implement a pin supporting exporter that will issue a revoking move_notify() around FLRs and a few other user triggerable operations. Since this is much more common we are not willing to tolerate the security UAF caused by interworking with non-move_notify() supporting drivers. Thus till now VFIO has required dynamic importers, even though it never actually moves the buffer location. To allow VFIO to work with pinned importers, according to how dma-buf was intended, we need to allow VFIO to detect if an importer is legacy or RDMA and does not actually implement move_notify(). Introduce a new function that exporters can call to detect these less capable importers. VFIO can then refuse to accept them during attach. In theory all exporters that call move_notify() on pinned dma-buf's should call this function, however that would break a number of widely used NIC/GPU flows. Thus for now do not spread this further than VFIO until we can understand how much of RDMA can implement the full semantic. In the process clarify how move_notify is intended to be used with pinned dma-bufs. Thanks Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> --- Leon Romanovsky (7): dma-buf: Rename .move_notify() callback to a clearer identifier dma-buf: Always build with DMABUF_MOVE_NOTIFY dma-buf: Document RDMA non-ODP invalidate_mapping() special case dma-buf: Add check function for revoke semantics iommufd: Pin dma-buf importer for revoke semantics vfio: Wait for dma-buf invalidation to complete vfio: Validate dma-buf revocation semantics drivers/dma-buf/Kconfig | 12 ----- drivers/dma-buf/dma-buf.c | 69 +++++++++++++++++++++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 14 +++--- drivers/gpu/drm/amd/amdkfd/Kconfig | 2 +- drivers/gpu/drm/virtio/virtgpu_prime.c | 2 +- drivers/gpu/drm/xe/tests/xe_dma_buf.c | 7 ++- drivers/gpu/drm/xe/xe_dma_buf.c | 14 +++--- drivers/infiniband/core/umem_dmabuf.c | 13 +----- drivers/infiniband/hw/mlx5/mr.c | 2 +- drivers/iommu/iommufd/pages.c | 11 ++++- drivers/vfio/pci/vfio_pci_dmabuf.c | 8 ++++ include/linux/dma-buf.h | 9 ++-- 12 files changed, 96 insertions(+), 67 deletions(-) --- base-commit: 9ace4753a5202b02191d54e9fdf7f9e3d02b85eb change-id: 20251221-dmabuf-revoke-b90ef16e4236 Best regards, -- Leon Romanovsky <leonro(a)nvidia.com>

8 months, 2 weeks

[PATCH rdma-next 0/2] RDMA: Add support for exporting dma-buf file descriptors

by Edward Srouji

This patch series introduces dma-buf export support for RDMA/InfiniBand devices, enabling userspace applications to export RDMA PCI-backed memory regions (such as device memory or mlx5 UAR pages) as dma-buf file descriptors. This allows PCI device memory to be shared with other kernel subsystems (e.g., graphics or media) or between userspace processes, via the standard dma-buf interface, avoiding unnecessary copies and enabling efficient peer-to-peer (P2P) DMA transfers. See [1] for background on dma-buf. As part of this series, we introduce a new uverbs object of type FD for dma-buf export, along with the corresponding APIs for allocation and teardown. This object encapsulates all attributes required to export a dma-buf. The implementation enforces P2P-only mappings and properly manages resource lifecycle, including: - Cleanup during driver removal or RDMA context destruction. - Revocation via dma_buf_move_notify() when the underlying mmap entries are removed. - Refactors common cleanup logic for reuse across FD uobject types. The infrastructure is generic within uverbs, allowing individual drivers to easily integrate and supply their vendor-specific implementation. The mlx5 driver is the first consumer of this new API, providing: - Initialization of PCI peer-to-peer DMA support. - mlx5-specific implementations of the mmap_get_pfns and pgoff_to_mmap_entry device operations required for dma-buf export. [1] https://docs.kernel.org/driver-api/dma-buf.html Signed-off-by: Yishai Hadas <yishaih(a)nvidia.com> Signed-off-by: Edward Srouji <edwards(a)nvidia.com> --- Yishai Hadas (2): RDMA/uverbs: Add DMABUF object type and operations RDMA/mlx5: Implement DMABUF export ops drivers/infiniband/core/Makefile | 1 + drivers/infiniband/core/device.c | 2 + drivers/infiniband/core/ib_core_uverbs.c | 19 +++ drivers/infiniband/core/rdma_core.c | 63 ++++---- drivers/infiniband/core/rdma_core.h | 1 + drivers/infiniband/core/uverbs.h | 10 ++ drivers/infiniband/core/uverbs_std_types_dmabuf.c | 172 ++++++++++++++++++++++ drivers/infiniband/core/uverbs_uapi.c | 1 + drivers/infiniband/hw/mlx5/main.c | 72 +++++++++ include/rdma/ib_verbs.h | 9 ++ include/rdma/uverbs_types.h | 1 + include/uapi/rdma/ib_user_ioctl_cmds.h | 10 ++ 12 files changed, 335 insertions(+), 26 deletions(-) --- base-commit: 325e3b5431ddd27c5f93156b36838a351e3b2f72 change-id: 20260108-dmabuf-export-0d598058dd1e Best regards, -- Edward Srouji <edwards(a)nvidia.com>

8 months, 2 weeks

[PATCH v4 0/8] dma-buf: Use revoke mechanism to invalidate shared buffers

by Leon Romanovsky

Changelog: v4: * Changed DMA_RESV_USAGE_KERNEL to DMA_RESV_USAGE_BOOKKEEP. * Made .invalidate_mapping() truly optional. * Added patch which renames dma_buf_move_notify() to be dma_buf_invalidate_mappings(). * Restored dma_buf_attachment_is_dynamic() function. v3: https://lore.kernel.org/all/20260120-dmabuf-revoke-v3-0-b7e0b07b8214@nvidia… * Used Jason's wordings for commits and cover letter. * Removed IOMMUFD patch. * Renamed dma_buf_attachment_is_revoke() to be dma_buf_attach_revocable(). * Added patch to remove CONFIG_DMABUF_MOVE_NOTIFY. * Added Reviewed-by tags. * Called to dma_resv_wait_timeout() after dma_buf_move_notify() in VFIO. * Added dma_buf_attach_revocable() check to VFIO DMABUF attach function. * Slightly changed commit messages. v2: https://patch.msgid.link/20260118-dmabuf-revoke-v2-0-a03bb27c0875@nvidia.com * Changed series to document the revoke semantics instead of implementing it. v1: https://patch.msgid.link/20260111-dmabuf-revoke-v1-0-fb4bcc8c259b@nvidia.com ------------------------------------------------------------------------- This series documents a dma-buf “revoke” mechanism: to allow a dma-buf exporter to explicitly invalidate (“kill”) a shared buffer after it has been distributed to importers, so that further CPU and device access is prevented and importers reliably observe failure. The change in this series is to properly document and use existing core “revoked” state on the dma-buf object and a corresponding exporter-triggered revoke operation. dma-buf has quietly allowed calling move_notify on pinned dma-bufs, even though legacy importers using dma_buf_attach() would simply ignore these calls. RDMA saw this and needed to use allow_peer2peer=true, so implemented a new-style pinned importer with an explicitly non-working move_notify() callback. This has been tolerable because the existing exporters are thought to only call move_notify() on a pinned DMABUF under RAS events and we have been willing to tolerate the UAF that results by allowing the importer to continue to use the mapping in this rare case. VFIO wants to implement a pin supporting exporter that will issue a revoking move_notify() around FLRs and a few other user triggerable operations. Since this is much more common we are not willing to tolerate the security UAF caused by interworking with non-move_notify() supporting drivers. Thus till now VFIO has required dynamic importers, even though it never actually moves the buffer location. To allow VFIO to work with pinned importers, according to how dma-buf was intended, we need to allow VFIO to detect if an importer is legacy or RDMA and does not actually implement move_notify(). In theory all exporters that call move_notify() on pinned dma-buf's should call this function, however that would break a number of widely used NIC/GPU flows. Thus for now do not spread this further than VFIO until we can understand how much of RDMA can implement the full semantic. In the process clarify how move_notify is intended to be used with pinned dma-bufs. Thanks Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> --- Leon Romanovsky (8): dma-buf: Rename .move_notify() callback to a clearer identifier dma-buf: Rename dma_buf_move_notify() to dma_buf_invalidate_mappings() dma-buf: Always build with DMABUF_MOVE_NOTIFY dma-buf: Make .invalidate_mapping() truly optional dma-buf: Add check function for revoke semantics iommufd: Pin dma-buf importer for revoke semantics vfio: Wait for dma-buf invalidation to complete vfio: Validate dma-buf revocation semantics drivers/dma-buf/Kconfig | 12 ------- drivers/dma-buf/dma-buf.c | 53 ++++++++++++++++++++++------- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 14 +++----- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- drivers/gpu/drm/amd/amdkfd/Kconfig | 2 +- drivers/gpu/drm/virtio/virtgpu_prime.c | 2 +- drivers/gpu/drm/xe/tests/xe_dma_buf.c | 7 ++-- drivers/gpu/drm/xe/xe_bo.c | 2 +- drivers/gpu/drm/xe/xe_dma_buf.c | 14 +++----- drivers/infiniband/core/umem_dmabuf.c | 13 ------- drivers/infiniband/hw/mlx5/mr.c | 2 +- drivers/iommu/iommufd/pages.c | 11 ++++-- drivers/iommu/iommufd/selftest.c | 2 +- drivers/vfio/pci/vfio_pci_dmabuf.c | 13 +++++-- include/linux/dma-buf.h | 9 ++--- 15 files changed, 84 insertions(+), 74 deletions(-) --- base-commit: 9ace4753a5202b02191d54e9fdf7f9e3d02b85eb change-id: 20251221-dmabuf-revoke-b90ef16e4236 Best regards, -- Leon Romanovsky <leonro(a)nvidia.com>

8 months, 2 weeks

types: reuse common phys_vec type instead of DMABUF open‑coded variant

by Leon Romanovsky

From: Leon Romanovsky <leonro(a)nvidia.com> After commit fcf463b92a08 ("types: move phys_vec definition to common header"), we can use the shared phys_vec type instead of the DMABUF‑specific dma_buf_phys_vec, which duplicated the same structure and semantics. Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> --- Alex, According to diffstat, VFIO is the subsystem with the largest set of changes, so it would be great if you could take it through your tree. The series is based on the for-7.0/blk-pvec shared branch from Jens: https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux.git/log/?h=for-… Thanks --- Cc: linux-media(a)vger.kernel.org Cc: dri-devel(a)lists.freedesktop.org Cc: linaro-mm-sig(a)lists.linaro.org Cc: linux-kernel(a)vger.kernel.org Cc: iommu(a)lists.linux.dev Cc: kvm(a)vger.kernel.org To: Sumit Semwal <sumit.semwal(a)linaro.org> To: Christian König <christian.koenig(a)amd.com> To: Jason Gunthorpe <jgg(a)ziepe.ca> To: Kevin Tian <kevin.tian(a)intel.com> To: Joerg Roedel <joro(a)8bytes.org> To: Will Deacon <will(a)kernel.org> To: Robin Murphy <robin.murphy(a)arm.com> To: Yishai Hadas <yishaih(a)nvidia.com> To: Shameer Kolothum <skolothumtho(a)nvidia.com> To: Ankit Agrawal <ankita(a)nvidia.com> To: Alex Williamson <alex(a)shazbot.org> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Jens Axboe <axboe(a)kernel.dk> --- drivers/dma-buf/dma-buf-mapping.c | 6 +++--- drivers/iommu/iommufd/io_pagetable.h | 2 +- drivers/iommu/iommufd/iommufd_private.h | 5 ++--- drivers/iommu/iommufd/pages.c | 4 ++-- drivers/iommu/iommufd/selftest.c | 2 +- drivers/vfio/pci/nvgrace-gpu/main.c | 2 +- drivers/vfio/pci/vfio_pci_dmabuf.c | 8 ++++---- include/linux/dma-buf-mapping.h | 2 +- include/linux/dma-buf.h | 10 ---------- include/linux/vfio_pci_core.h | 13 ++++++------- 10 files changed, 21 insertions(+), 33 deletions(-) diff --git a/drivers/dma-buf/dma-buf-mapping.c b/drivers/dma-buf/dma-buf-mapping.c index b7352e609fbd..174677faa577 100644 --- a/drivers/dma-buf/dma-buf-mapping.c +++ b/drivers/dma-buf/dma-buf-mapping.c @@ -33,8 +33,8 @@ static struct scatterlist *fill_sg_entry(struct scatterlist *sgl, size_t length, } static unsigned int calc_sg_nents(struct dma_iova_state *state, - struct dma_buf_phys_vec *phys_vec, - size_t nr_ranges, size_t size) + struct phys_vec *phys_vec, size_t nr_ranges, + size_t size) { unsigned int nents = 0; size_t i; @@ -91,7 +91,7 @@ struct dma_buf_dma { */ struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach, struct p2pdma_provider *provider, - struct dma_buf_phys_vec *phys_vec, + struct phys_vec *phys_vec, size_t nr_ranges, size_t size, enum dma_data_direction dir) { diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index 14cd052fd320..27e3e311d395 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -202,7 +202,7 @@ struct iopt_pages_dmabuf_track { struct iopt_pages_dmabuf { struct dma_buf_attachment *attach; - struct dma_buf_phys_vec phys; + struct phys_vec phys; /* Always PAGE_SIZE aligned */ unsigned long start; struct list_head tracker; diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index eb6d1a70f673..6ac1965199e9 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -20,7 +20,6 @@ struct iommu_group; struct iommu_option; struct iommufd_device; struct dma_buf_attachment; -struct dma_buf_phys_vec; struct iommufd_sw_msi_map { struct list_head sw_msi_item; @@ -718,7 +717,7 @@ int __init iommufd_test_init(void); void iommufd_test_exit(void); bool iommufd_selftest_is_mock_dev(struct device *dev); int iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, - struct dma_buf_phys_vec *phys); + struct phys_vec *phys); #else static inline void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd, unsigned int ioas_id, @@ -742,7 +741,7 @@ static inline bool iommufd_selftest_is_mock_dev(struct device *dev) } static inline int iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, - struct dma_buf_phys_vec *phys) + struct phys_vec *phys) { return -EOPNOTSUPP; } diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index dbe51ecb9a20..bababd564cf9 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -1077,7 +1077,7 @@ static int pfn_reader_user_update_pinned(struct pfn_reader_user *user, } struct pfn_reader_dmabuf { - struct dma_buf_phys_vec phys; + struct phys_vec phys; unsigned long start_offset; }; @@ -1460,7 +1460,7 @@ static struct dma_buf_attach_ops iopt_dmabuf_attach_revoke_ops = { */ static int sym_vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, - struct dma_buf_phys_vec *phys) + struct phys_vec *phys) { typeof(&vfio_pci_dma_buf_iommufd_map) fn; int rc; diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 550ff36dec3a..989d8c4c60a7 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -2002,7 +2002,7 @@ static const struct dma_buf_ops iommufd_test_dmabuf_ops = { }; int iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, - struct dma_buf_phys_vec *phys) + struct phys_vec *phys) { struct iommufd_test_dma_buf *priv = attachment->dmabuf->priv; diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index 84d142a47ec6..a0f4edd6a30b 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -784,7 +784,7 @@ nvgrace_gpu_write(struct vfio_device *core_vdev, static int nvgrace_get_dmabuf_phys(struct vfio_pci_core_device *core_vdev, struct p2pdma_provider **provider, unsigned int region_index, - struct dma_buf_phys_vec *phys_vec, + struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges) { diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c index d4d0f7d08c53..9a84c238c013 100644 --- a/drivers/vfio/pci/vfio_pci_dmabuf.c +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c @@ -14,7 +14,7 @@ struct vfio_pci_dma_buf { struct vfio_pci_core_device *vdev; struct list_head dmabufs_elm; size_t size; - struct dma_buf_phys_vec *phys_vec; + struct phys_vec *phys_vec; struct p2pdma_provider *provider; u32 nr_ranges; u8 revoked : 1; @@ -94,7 +94,7 @@ static const struct dma_buf_ops vfio_pci_dmabuf_ops = { * will fail if it is currently revoked */ int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, - struct dma_buf_phys_vec *phys) + struct phys_vec *phys) { struct vfio_pci_dma_buf *priv; @@ -116,7 +116,7 @@ int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, } EXPORT_SYMBOL_FOR_MODULES(vfio_pci_dma_buf_iommufd_map, "iommufd"); -int vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec, +int vfio_pci_core_fill_phys_vec(struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges, phys_addr_t start, phys_addr_t len) @@ -148,7 +148,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_fill_phys_vec); int vfio_pci_core_get_dmabuf_phys(struct vfio_pci_core_device *vdev, struct p2pdma_provider **provider, unsigned int region_index, - struct dma_buf_phys_vec *phys_vec, + struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges) { diff --git a/include/linux/dma-buf-mapping.h b/include/linux/dma-buf-mapping.h index a3c0ce2d3a42..09bde3f748e4 100644 --- a/include/linux/dma-buf-mapping.h +++ b/include/linux/dma-buf-mapping.h @@ -9,7 +9,7 @@ struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach, struct p2pdma_provider *provider, - struct dma_buf_phys_vec *phys_vec, + struct phys_vec *phys_vec, size_t nr_ranges, size_t size, enum dma_data_direction dir); void dma_buf_free_sgt(struct dma_buf_attachment *attach, struct sg_table *sgt, diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 0bc492090237..400a5311368e 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -531,16 +531,6 @@ struct dma_buf_export_info { void *priv; }; -/** - * struct dma_buf_phys_vec - describe continuous chunk of memory - * @paddr: physical address of that chunk - * @len: Length of this chunk - */ -struct dma_buf_phys_vec { - phys_addr_t paddr; - size_t len; -}; - /** * DEFINE_DMA_BUF_EXPORT_INFO - helper macro for exporters * @name: export-info name diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 706877f998ff..2ac288bb2c60 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -28,7 +28,6 @@ struct vfio_pci_core_device; struct vfio_pci_region; struct p2pdma_provider; -struct dma_buf_phys_vec; struct dma_buf_attachment; struct vfio_pci_eventfd { @@ -62,25 +61,25 @@ struct vfio_pci_device_ops { int (*get_dmabuf_phys)(struct vfio_pci_core_device *vdev, struct p2pdma_provider **provider, unsigned int region_index, - struct dma_buf_phys_vec *phys_vec, + struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges); }; #if IS_ENABLED(CONFIG_VFIO_PCI_DMABUF) -int vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec, +int vfio_pci_core_fill_phys_vec(struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges, phys_addr_t start, phys_addr_t len); int vfio_pci_core_get_dmabuf_phys(struct vfio_pci_core_device *vdev, struct p2pdma_provider **provider, unsigned int region_index, - struct dma_buf_phys_vec *phys_vec, + struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges); #else static inline int -vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec, +vfio_pci_core_fill_phys_vec(struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges, phys_addr_t start, phys_addr_t len) @@ -89,7 +88,7 @@ vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec, } static inline int vfio_pci_core_get_dmabuf_phys( struct vfio_pci_core_device *vdev, struct p2pdma_provider **provider, - unsigned int region_index, struct dma_buf_phys_vec *phys_vec, + unsigned int region_index, struct phys_vec *phys_vec, struct vfio_region_dma_range *dma_ranges, size_t nr_ranges) { return -EOPNOTSUPP; @@ -228,6 +227,6 @@ static inline bool is_aligned_for_order(struct vm_area_struct *vma, } int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment, - struct dma_buf_phys_vec *phys); + struct phys_vec *phys); #endif /* VFIO_PCI_CORE_H */ --- base-commit: fcf463b92a08686d1aeb1e66674a72eb7a8bfb9b change-id: 20260107-convert-to-pvec-bf04dfcf3d12 Best regards, -- Leon Romanovsky <leonro(a)nvidia.com>

8 months, 2 weeks

[PATCH] dma-buf: Remove DMA-BUF sysfs stats

by T.J. Mercier

Commit bdb8d06dfefd ("dmabuf: Add the capability to expose DMA-BUF stats in sysfs") added dmabuf statistics to sysfs in 2021 under CONFIG_DMABUF_SYSFS_STATS. After being used in production, performance problems were discovered leading to its deprecation in 2022 in commit e0a9f1fe206a ("dma-buf: deprecate DMABUF_SYSFS_STATS"). Some of the problems with this interface were discussed in my LPC 2025 talk. [1][2] Android was probably the last user of the interface, which has since been migrated to use the dmabuf BPF iterator [3] to obtain the same information more cheaply. As promised in that series, now that the longterm stable 6.18 kernel has been released let's remove the sysfs dmabuf statistics from the kernel. [1] https://www.youtube.com/watch?v=D83qygudq9c [2] https://lpc.events/event/19/contributions/2118/ [3] https://lore.kernel.org/all/20250522230429.941193-1-tjmercier@google.com/ Signed-off-by: T.J. Mercier <tjmercier(a)google.com> --- .../ABI/testing/sysfs-kernel-dmabuf-buffers | 24 --- Documentation/driver-api/dma-buf.rst | 5 - drivers/dma-buf/Kconfig | 15 -- drivers/dma-buf/Makefile | 1 - drivers/dma-buf/dma-buf-sysfs-stats.c | 202 ------------------ drivers/dma-buf/dma-buf-sysfs-stats.h | 35 --- drivers/dma-buf/dma-buf.c | 18 -- include/linux/dma-buf.h | 12 -- 8 files changed, 312 deletions(-) delete mode 100644 Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers delete mode 100644 drivers/dma-buf/dma-buf-sysfs-stats.c delete mode 100644 drivers/dma-buf/dma-buf-sysfs-stats.h diff --git a/Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers b/Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers deleted file mode 100644 index 5d3bc997dc64..000000000000 --- a/Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers +++ /dev/null @@ -1,24 +0,0 @@ -What: /sys/kernel/dmabuf/buffers -Date: May 2021 -KernelVersion: v5.13 -Contact: Hridya Valsaraju <hridya(a)google.com> -Description: The /sys/kernel/dmabuf/buffers directory contains a - snapshot of the internal state of every DMA-BUF. - /sys/kernel/dmabuf/buffers/<inode_number> will contain the - statistics for the DMA-BUF with the unique inode number - <inode_number> -Users: kernel memory tuning/debugging tools - -What: /sys/kernel/dmabuf/buffers/<inode_number>/exporter_name -Date: May 2021 -KernelVersion: v5.13 -Contact: Hridya Valsaraju <hridya(a)google.com> -Description: This file is read-only and contains the name of the exporter of - the DMA-BUF. - -What: /sys/kernel/dmabuf/buffers/<inode_number>/size -Date: May 2021 -KernelVersion: v5.13 -Contact: Hridya Valsaraju <hridya(a)google.com> -Description: This file is read-only and specifies the size of the DMA-BUF in - bytes. diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 29abf1eebf9f..2f36c21d9948 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -125,11 +125,6 @@ Implicit Fence Poll Support .. kernel-doc:: drivers/dma-buf/dma-buf.c :doc: implicit fence polling -DMA-BUF statistics -~~~~~~~~~~~~~~~~~~ -.. kernel-doc:: drivers/dma-buf/dma-buf-sysfs-stats.c - :doc: overview - DMA Buffer ioctls ~~~~~~~~~~~~~~~~~ diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index fdd823e446cc..012d22e941d6 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -75,21 +75,6 @@ menuconfig DMABUF_HEAPS allows userspace to allocate dma-bufs that can be shared between drivers. -menuconfig DMABUF_SYSFS_STATS - bool "DMA-BUF sysfs statistics (DEPRECATED)" - depends on DMA_SHARED_BUFFER - help - Choose this option to enable DMA-BUF sysfs statistics - in location /sys/kernel/dmabuf/buffers. - - /sys/kernel/dmabuf/buffers/<inode_number> will contain - statistics for the DMA-BUF with the unique inode number - <inode_number>. - - This option is deprecated and should sooner or later be removed. - Android is the only user of this and it turned out that this resulted - in quite some performance problems. - source "drivers/dma-buf/heaps/Kconfig" endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 2008fb7481b3..7a85565d906b 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -6,7 +6,6 @@ obj-$(CONFIG_DMABUF_HEAPS) += heaps/ obj-$(CONFIG_SYNC_FILE) += sync_file.o obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o obj-$(CONFIG_UDMABUF) += udmabuf.o -obj-$(CONFIG_DMABUF_SYSFS_STATS) += dma-buf-sysfs-stats.o dmabuf_selftests-y := \ selftest.o \ diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c deleted file mode 100644 index b5b62e40ccc1..000000000000 --- a/drivers/dma-buf/dma-buf-sysfs-stats.c +++ /dev/null @@ -1,202 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * DMA-BUF sysfs statistics. - * - * Copyright (C) 2021 Google LLC. - */ - -#include <linux/dma-buf.h> -#include <linux/dma-resv.h> -#include <linux/kobject.h> -#include <linux/printk.h> -#include <linux/slab.h> -#include <linux/sysfs.h> - -#include "dma-buf-sysfs-stats.h" - -#define to_dma_buf_entry_from_kobj(x) container_of(x, struct dma_buf_sysfs_entry, kobj) - -/** - * DOC: overview - * - * ``/sys/kernel/debug/dma_buf/bufinfo`` provides an overview of every DMA-BUF - * in the system. However, since debugfs is not safe to be mounted in - * production, procfs and sysfs can be used to gather DMA-BUF statistics on - * production systems. - * - * The ``/proc/<pid>/fdinfo/<fd>`` files in procfs can be used to gather - * information about DMA-BUF fds. Detailed documentation about the interface - * is present in Documentation/filesystems/proc.rst. - * - * Unfortunately, the existing procfs interfaces can only provide information - * about the DMA-BUFs for which processes hold fds or have the buffers mmapped - * into their address space. This necessitated the creation of the DMA-BUF sysfs - * statistics interface to provide per-buffer information on production systems. - * - * The interface at ``/sys/kernel/dmabuf/buffers`` exposes information about - * every DMA-BUF when ``CONFIG_DMABUF_SYSFS_STATS`` is enabled. - * - * The following stats are exposed by the interface: - * - * * ``/sys/kernel/dmabuf/buffers/<inode_number>/exporter_name`` - * * ``/sys/kernel/dmabuf/buffers/<inode_number>/size`` - * - * The information in the interface can also be used to derive per-exporter - * statistics. The data from the interface can be gathered on error conditions - * or other important events to provide a snapshot of DMA-BUF usage. - * It can also be collected periodically by telemetry to monitor various metrics. - * - * Detailed documentation about the interface is present in - * Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers. - */ - -struct dma_buf_stats_attribute { - struct attribute attr; - ssize_t (*show)(struct dma_buf *dmabuf, - struct dma_buf_stats_attribute *attr, char *buf); -}; -#define to_dma_buf_stats_attr(x) container_of(x, struct dma_buf_stats_attribute, attr) - -static ssize_t dma_buf_stats_attribute_show(struct kobject *kobj, - struct attribute *attr, - char *buf) -{ - struct dma_buf_stats_attribute *attribute; - struct dma_buf_sysfs_entry *sysfs_entry; - struct dma_buf *dmabuf; - - attribute = to_dma_buf_stats_attr(attr); - sysfs_entry = to_dma_buf_entry_from_kobj(kobj); - dmabuf = sysfs_entry->dmabuf; - - if (!dmabuf || !attribute->show) - return -EIO; - - return attribute->show(dmabuf, attribute, buf); -} - -static const struct sysfs_ops dma_buf_stats_sysfs_ops = { - .show = dma_buf_stats_attribute_show, -}; - -static ssize_t exporter_name_show(struct dma_buf *dmabuf, - struct dma_buf_stats_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%s\n", dmabuf->exp_name); -} - -static ssize_t size_show(struct dma_buf *dmabuf, - struct dma_buf_stats_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%zu\n", dmabuf->size); -} - -static struct dma_buf_stats_attribute exporter_name_attribute = - __ATTR_RO(exporter_name); -static struct dma_buf_stats_attribute size_attribute = __ATTR_RO(size); - -static struct attribute *dma_buf_stats_default_attrs[] = { - &exporter_name_attribute.attr, - &size_attribute.attr, - NULL, -}; -ATTRIBUTE_GROUPS(dma_buf_stats_default); - -static void dma_buf_sysfs_release(struct kobject *kobj) -{ - struct dma_buf_sysfs_entry *sysfs_entry; - - sysfs_entry = to_dma_buf_entry_from_kobj(kobj); - kfree(sysfs_entry); -} - -static const struct kobj_type dma_buf_ktype = { - .sysfs_ops = &dma_buf_stats_sysfs_ops, - .release = dma_buf_sysfs_release, - .default_groups = dma_buf_stats_default_groups, -}; - -void dma_buf_stats_teardown(struct dma_buf *dmabuf) -{ - struct dma_buf_sysfs_entry *sysfs_entry; - - sysfs_entry = dmabuf->sysfs_entry; - if (!sysfs_entry) - return; - - kobject_del(&sysfs_entry->kobj); - kobject_put(&sysfs_entry->kobj); -} - - -/* Statistics files do not need to send uevents. */ -static int dmabuf_sysfs_uevent_filter(const struct kobject *kobj) -{ - return 0; -} - -static const struct kset_uevent_ops dmabuf_sysfs_no_uevent_ops = { - .filter = dmabuf_sysfs_uevent_filter, -}; - -static struct kset *dma_buf_stats_kset; -static struct kset *dma_buf_per_buffer_stats_kset; -int dma_buf_init_sysfs_statistics(void) -{ - dma_buf_stats_kset = kset_create_and_add("dmabuf", - &dmabuf_sysfs_no_uevent_ops, - kernel_kobj); - if (!dma_buf_stats_kset) - return -ENOMEM; - - dma_buf_per_buffer_stats_kset = kset_create_and_add("buffers", - &dmabuf_sysfs_no_uevent_ops, - &dma_buf_stats_kset->kobj); - if (!dma_buf_per_buffer_stats_kset) { - kset_unregister(dma_buf_stats_kset); - return -ENOMEM; - } - - return 0; -} - -void dma_buf_uninit_sysfs_statistics(void) -{ - kset_unregister(dma_buf_per_buffer_stats_kset); - kset_unregister(dma_buf_stats_kset); -} - -int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file) -{ - struct dma_buf_sysfs_entry *sysfs_entry; - int ret; - - if (!dmabuf->exp_name) { - pr_err("exporter name must not be empty if stats needed\n"); - return -EINVAL; - } - - sysfs_entry = kzalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL); - if (!sysfs_entry) - return -ENOMEM; - - sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset; - sysfs_entry->dmabuf = dmabuf; - - dmabuf->sysfs_entry = sysfs_entry; - - /* create the directory for buffer stats */ - ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL, - "%lu", file_inode(file)->i_ino); - if (ret) - goto err_sysfs_dmabuf; - - return 0; - -err_sysfs_dmabuf: - kobject_put(&sysfs_entry->kobj); - dmabuf->sysfs_entry = NULL; - return ret; -} diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.h b/drivers/dma-buf/dma-buf-sysfs-stats.h deleted file mode 100644 index 7a8a995b75ba..000000000000 --- a/drivers/dma-buf/dma-buf-sysfs-stats.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * DMA-BUF sysfs statistics. - * - * Copyright (C) 2021 Google LLC. - */ - -#ifndef _DMA_BUF_SYSFS_STATS_H -#define _DMA_BUF_SYSFS_STATS_H - -#ifdef CONFIG_DMABUF_SYSFS_STATS - -int dma_buf_init_sysfs_statistics(void); -void dma_buf_uninit_sysfs_statistics(void); - -int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file); - -void dma_buf_stats_teardown(struct dma_buf *dmabuf); -#else - -static inline int dma_buf_init_sysfs_statistics(void) -{ - return 0; -} - -static inline void dma_buf_uninit_sysfs_statistics(void) {} - -static inline int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file) -{ - return 0; -} - -static inline void dma_buf_stats_teardown(struct dma_buf *dmabuf) {} -#endif -#endif // _DMA_BUF_SYSFS_STATS_H diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index a4d8f2ff94e4..8e23580f1754 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -33,8 +33,6 @@ #include <uapi/linux/dma-buf.h> #include <uapi/linux/magic.h> -#include "dma-buf-sysfs-stats.h" - #define CREATE_TRACE_POINTS #include <trace/events/dma_buf.h> @@ -184,7 +182,6 @@ static void dma_buf_release(struct dentry *dentry) */ BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); - dma_buf_stats_teardown(dmabuf); dmabuf->ops->release(dmabuf); if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) @@ -765,10 +762,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf->resv = resv; } - ret = dma_buf_stats_setup(dmabuf, file); - if (ret) - goto err_dmabuf; - file->private_data = dmabuf; file->f_path.dentry->d_fsdata = dmabuf; dmabuf->file = file; @@ -779,10 +772,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) return dmabuf; -err_dmabuf: - if (!resv) - dma_resv_fini(dmabuf->resv); - kfree(dmabuf); err_file: fput(file); err_module: @@ -1802,12 +1791,6 @@ static inline void dma_buf_uninit_debugfs(void) static int __init dma_buf_init(void) { - int ret; - - ret = dma_buf_init_sysfs_statistics(); - if (ret) - return ret; - dma_buf_mnt = kern_mount(&dma_buf_fs_type); if (IS_ERR(dma_buf_mnt)) return PTR_ERR(dma_buf_mnt); @@ -1821,6 +1804,5 @@ static void __exit dma_buf_deinit(void) { dma_buf_uninit_debugfs(); kern_unmount(dma_buf_mnt); - dma_buf_uninit_sysfs_statistics(); } __exitcall(dma_buf_deinit); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 0bc492090237..91f4939db89b 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -429,18 +429,6 @@ struct dma_buf { __poll_t active; } cb_in, cb_out; -#ifdef CONFIG_DMABUF_SYSFS_STATS - /** - * @sysfs_entry: - * - * For exposing information about this buffer in sysfs. See also - * `DMA-BUF statistics`_ for the uapi this enables. - */ - struct dma_buf_sysfs_entry { - struct kobject kobj; - struct dma_buf *dmabuf; - } *sysfs_entry; -#endif }; /** base-commit: 26b4309a3ab82a0697751cde52eb336c29c19035 -- 2.52.0.457.g6b5491de43-goog

8 months, 2 weeks

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig