Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

51 participants
6030 discussions

[PATCH v3 0/6] dma-buf: heaps: add coherent reserved-memory heap

by Albert Esteve

This patch series adds a new dma-buf heap driver that exposes coherent, non‑reusable reserved-memory regions as named heaps, so userspace can explicitly allocate buffers from those device‑specific pools. Motivation: we want cgroup accounting for all userspace‑visible buffer allocations (DRM, v4l2, dma‑buf heaps, etc.). That’s hard to do when drivers call dma_alloc_attrs() directly because the accounting controller (memcg vs dmem) is ambiguous. The long‑term plan is to steer those paths toward dma‑buf heaps, where each heap can unambiguously charge a single controller. To reach that goal, we need a heap backend for each dma_alloc_attrs() memory type. CMA and system heaps already exist; coherent reserved‑memory was the missing piece, since many SoCs define dedicated, device‑local coherent pools in DT under /reserved-memory using "shared-dma-pool" with non‑reusable regions (i.e., not CMA) that are carved out exclusively for coherent DMA and are currently only usable by in‑kernel drivers. Because these regions are device‑dependent, each heap instance binds a heap device to its reserved‑mem region via a newly introduced helper function -namely, of_reserved_mem_device_init_with_mem()- so coherent allocations use the correct dev->dma_mem. Charging to cgroups for these buffers is intentionally left out to keep review focused on the new heap; I plan to follow up based on Eric’s [1] and Maxime’s [2] work on dmem charging from userspace. This series also makes the new heap driver modular, in line with the CMA heap change in [3]. [1] https://lore.kernel.org/all/20260218-dmabuf-heap-cma-dmem-v2-0-b249886fb7b2… [2] https://lore.kernel.org/all/20250310-dmem-cgroups-v1-0-2984c1bc9312@kernel.… [3] https://lore.kernel.org/all/20260303-dma-buf-heaps-as-modules-v3-0-24344812… Signed-off-by: Albert Esteve <aesteve(a)redhat.com> --- Changes in v3: - Reorganized changesets among patches to ensure bisectability - Removed unused dma_heap_coherent_register() leftover - Removed fallback when setting mask in coherent heap dev, since dma_set_mask() already truncates to supported masks - Moved struct rmem_assigned_device (rd) logic to of_reserved_mem_device_init_with_mem() to allow listing the device - Link to v2: https://lore.kernel.org/r/20260303-b4-dmabuf-heap-coherent-rmem-v2-0-65a465… Changes in v2: - Removed dmem charging parts - Moved coherent heap registering logic to coherent.c - Made heap device a member of struct dma_heap - Split dma_heap_add logic into create/register, to be able to access the stored heap device before registered. - Avoid platform device in favour of heap device - Added a wrapper to rmem device_init() op - Switched from late_initcall() to module_init() - Made the coherent heap driver modular - Link to v1: https://lore.kernel.org/r/20260224-b4-dmabuf-heap-coherent-rmem-v1-1-dffef4… --- Albert Esteve (5): dma-buf: dma-heap: split dma_heap_add of_reserved_mem: add a helper for rmem device_init op dma: coherent: store reserved memory coherent regions dma-buf: heaps: Add Coherent heap to dmabuf heaps dma-buf: heaps: coherent: Turn heap into a module John Stultz (1): dma-buf: dma-heap: Keep track of the heap device struct drivers/dma-buf/dma-heap.c | 138 +++++++++-- drivers/dma-buf/heaps/Kconfig | 9 + drivers/dma-buf/heaps/Makefile | 1 + drivers/dma-buf/heaps/coherent_heap.c | 417 ++++++++++++++++++++++++++++++++++ drivers/of/of_reserved_mem.c | 68 ++++-- include/linux/dma-heap.h | 5 + include/linux/dma-map-ops.h | 7 + include/linux/of_reserved_mem.h | 8 + kernel/dma/coherent.c | 34 +++ 9 files changed, 640 insertions(+), 47 deletions(-) --- base-commit: 6de23f81a5e08be8fbf5e8d7e9febc72a5b5f27f change-id: 20260223-b4-dmabuf-heap-coherent-rmem-91fd3926afe9 Best regards, -- Albert Esteve <aesteve(a)redhat.com>

2 hours, 46 minutes

[PATCH] udmabuf: Do not create malformed scatterlists

by Jason Gunthorpe

Using a sg_set_folio() loop for every 4K results in a malformed scatterlist because sg_set_folio() has an issue with offsets > PAGE_SIZE and because scatterlist expects the creator to build a list which consolidates any physical contiguity. sg_alloc_table_from_pages() creates a valid scatterlist directly from a struct page array, so go back to that. Remove the offsets allocation and just store an array of tail pages as it did before the below commit. Everything wants that anyhow. Fixes: 0c8b91ef5100 ("udmabuf: add back support for mapping hugetlb pages") Reported-by: Julian Orth <ju.orth(a)gmail.com> Closes: https://lore.kernel.org/all/20260308-scatterlist-v1-1-39c4566b0bba@gmail.co… Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> --- drivers/dma-buf/udmabuf.c | 49 +++++++++++---------------------------- 1 file changed, 13 insertions(+), 36 deletions(-) diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 94b8ecb892bb17..5d687860445137 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -26,10 +26,10 @@ MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is struct udmabuf { pgoff_t pagecount; - struct folio **folios; + struct page **pages; /** - * Unlike folios, pinned_folios is only used for unpin. + * Unlike pages, pinned_folios is only used for unpin. * So, nr_pinned is not the same to pagecount, the pinned_folios * only set each folio which already pinned when udmabuf_create. * Note that, since a folio may be pinned multiple times, each folio @@ -41,7 +41,6 @@ struct udmabuf { struct sg_table *sg; struct miscdevice *device; - pgoff_t *offsets; }; static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) @@ -55,8 +54,7 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) if (pgoff >= ubuf->pagecount) return VM_FAULT_SIGBUS; - pfn = folio_pfn(ubuf->folios[pgoff]); - pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; + pfn = page_to_pfn(ubuf->pages[pgoff]); ret = vmf_insert_pfn(vma, vmf->address, pfn); if (ret & VM_FAULT_ERROR) @@ -73,8 +71,7 @@ static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf) if (WARN_ON(pgoff >= ubuf->pagecount)) break; - pfn = folio_pfn(ubuf->folios[pgoff]); - pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT; + pfn = page_to_pfn(ubuf->pages[pgoff]); /** * If the below vmf_insert_pfn() fails, we do not return an @@ -109,22 +106,11 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma) static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map) { struct udmabuf *ubuf = buf->priv; - struct page **pages; void *vaddr; - pgoff_t pg; dma_resv_assert_held(buf->resv); - pages = kvmalloc_objs(*pages, ubuf->pagecount); - if (!pages) - return -ENOMEM; - - for (pg = 0; pg < ubuf->pagecount; pg++) - pages[pg] = folio_page(ubuf->folios[pg], - ubuf->offsets[pg] >> PAGE_SHIFT); - - vaddr = vm_map_ram(pages, ubuf->pagecount, -1); - kvfree(pages); + vaddr = vm_map_ram(ubuf->pages, ubuf->pagecount, -1); if (!vaddr) return -EINVAL; @@ -146,22 +132,18 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf, { struct udmabuf *ubuf = buf->priv; struct sg_table *sg; - struct scatterlist *sgl; - unsigned int i = 0; int ret; sg = kzalloc_obj(*sg); if (!sg) return ERR_PTR(-ENOMEM); - ret = sg_alloc_table(sg, ubuf->pagecount, GFP_KERNEL); + ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->pagecount, 0, + ubuf->pagecount << PAGE_SHIFT, + GFP_KERNEL); if (ret < 0) goto err_alloc; - for_each_sg(sg->sgl, sgl, ubuf->pagecount, i) - sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE, - ubuf->offsets[i]); - ret = dma_map_sgtable(dev, sg, direction, 0); if (ret < 0) goto err_map; @@ -207,12 +189,8 @@ static void unpin_all_folios(struct udmabuf *ubuf) static __always_inline int init_udmabuf(struct udmabuf *ubuf, pgoff_t pgcnt) { - ubuf->folios = kvmalloc_objs(*ubuf->folios, pgcnt); - if (!ubuf->folios) - return -ENOMEM; - - ubuf->offsets = kvzalloc_objs(*ubuf->offsets, pgcnt); - if (!ubuf->offsets) + ubuf->pages = kvmalloc_objs(*ubuf->pages, pgcnt); + if (!ubuf->pages) return -ENOMEM; ubuf->pinned_folios = kvmalloc_objs(*ubuf->pinned_folios, pgcnt); @@ -225,8 +203,7 @@ static __always_inline int init_udmabuf(struct udmabuf *ubuf, pgoff_t pgcnt) static __always_inline void deinit_udmabuf(struct udmabuf *ubuf) { unpin_all_folios(ubuf); - kvfree(ubuf->offsets); - kvfree(ubuf->folios); + kvfree(ubuf->pages); } static void release_udmabuf(struct dma_buf *buf) @@ -344,8 +321,8 @@ static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, ubuf->pinned_folios[nr_pinned++] = folios[cur_folio]; for (; subpgoff < fsize; subpgoff += PAGE_SIZE) { - ubuf->folios[upgcnt] = folios[cur_folio]; - ubuf->offsets[upgcnt] = subpgoff; + ubuf->pages[upgcnt] = folio_page(folios[cur_folio], + subpgoff >> PAGE_SHIFT); ++upgcnt; if (++cur_pgcnt >= pgcnt) base-commit: 1f318b96cc84d7c2ab792fcc0bfd42a7ca890681 -- 2.43.0

8 hours, 12 minutes

Re: [PATCH net-next v3 1/2] dma-mapping: introduce DMA_ATTR_CC_DECRYPTED for pre-decrypted memory

by Leon Romanovsky

On Thu, Mar 05, 2026 at 01:36:40PM +0100, Jiri Pirko wrote: > From: Jiri Pirko <jiri(a)nvidia.com> > > Current CC designs don't place a vIOMMU in front of untrusted devices. > Instead, the DMA API forces all untrusted device DMA through swiotlb > bounce buffers (is_swiotlb_force_bounce()) which copies data into > decrypted memory on behalf of the device. > > When a caller has already arranged for the memory to be decrypted > via set_memory_decrypted(), the DMA API needs to know so it can map > directly using the unencrypted physical address rather than bounce > buffering. Following the pattern of DMA_ATTR_MMIO, add > DMA_ATTR_CC_DECRYPTED for this purpose. Like the MMIO case, only the > caller knows what kind of memory it has and must inform the DMA API > for it to work correctly. > > Signed-off-by: Jiri Pirko <jiri(a)nvidia.com> > --- > v1->v2: > - rebased on top of recent dma-mapping-fixes > --- > include/linux/dma-mapping.h | 6 ++++++ > include/trace/events/dma.h | 3 ++- > kernel/dma/direct.h | 14 +++++++++++--- > 3 files changed, 19 insertions(+), 4 deletions(-) > > diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h > index 29973baa0581..ae3d85e494ec 100644 > --- a/include/linux/dma-mapping.h > +++ b/include/linux/dma-mapping.h > @@ -85,6 +85,12 @@ > * a cacheline must have this attribute for this to be considered safe. > */ > #define DMA_ATTR_CPU_CACHE_CLEAN (1UL << 11) > +/* > + * DMA_ATTR_CC_DECRYPTED: Indicates memory that has been explicitly decrypted > + * (shared) for confidential computing guests. The caller must have > + * called set_memory_decrypted(). A struct page is required. > + */ > +#define DMA_ATTR_CC_DECRYPTED (1UL << 12) While adding the new attribute is fine, I would expect additional checks in dma_map_phys() to ensure the attribute cannot be misused. For example, WARN_ON(attrs & (DMA_ATTR_CC_DECRYPTED | DMA_ATTR_MMIO)), along with a check that we are taking the direct path only. Thanks

15 hours, 23 minutes

Re: [RFC v2 PATCH 00/10] vfio/pci: Add mmap() for DMABUFs

by Christian König

On 3/12/26 19:45, Matt Evans wrote: > Hi all, > > > There were various suggestions in the September 2025 thread "[TECH > TOPIC] vfio, iommufd: Enabling user space drivers to vend more > granular access to client processes" [0], and LPC discussions, around > improving the situation for multi-process userspace driver designs. > This RFC series implements some of these ideas. > > (Thanks for feedback on v1! Revised series, with changes noted > inline.) > > Background: Multi-process USDs > ============================== > > The userspace driver scenario discussed in that thread involves a > primary process driving a PCIe function through VFIO/iommufd, which > manages the function-wide ownership/lifecycle. The function is > designed to provide multiple distinct programming interfaces (for > example, several independent MMIO register frames in one function), > and the primary process delegates control of these interfaces to > multiple independent client processes (which do the actual work). > This scenario clearly relies on a HW design that provides appropriate > isolation between the programming interfaces. > > The two key needs are: > > 1. Mechanisms to safely delegate a subset of the device MMIO > resources to a client process without over-sharing wider access > (or influence over whole-device activities, such as reset). > > 2. Mechanisms to allow a client process to do its own iommufd > management w.r.t. its address space, in a way that's isolated > from DMA relating to other clients. > > > mmap() of VFIO DMABUFs > ====================== > > This RFC addresses #1 in "vfio/pci: Support mmap() of a VFIO DMABUF", > implementing the proposals in [0] to add mmap() support to the > existing VFIO DMABUF exporter. > > This enables a userspace driver to define DMABUF ranges corresponding > to sub-ranges of a BAR, and grant a given client (via a shared fd) > the capability to access (only) those sub-ranges. The VFIO device fds > would be kept private to the primary process. All the client can do > with that fd is map (or iomap via iommufd) that specific subset of > resources, and the impact of bugs/malice is contained. > > (We'll follow up on #2 separately, as a related-but-distinct problem. > PASIDs are one way to achieve per-client isolation of DMA; another > could be sharing of a single IOVA space via 'constrained' iommufds.) > > > New in v2: To achieve this, the existing VFIO BAR mmap() path is > converted to use DMABUFs behind the scenes, in "vfio/pci: Convert BAR > mmap() to use a DMABUF" plus new helper functions, as Jason/Christian > suggested in the v1 discussion [3]. > > This means: > > - Both regular and new DMABUF BAR mappings share the same vm_ops, > i.e. mmap()ing DMABUFs is a smaller change on top of the existing > mmap(). > > - The zapping of mappings occurs via vfio_pci_dma_buf_move(), and the > vfio_pci_zap_bars() originally paired with the _move()s can go > away. Each DMABUF has a unique address_space. > > - It's a step towards future iommufd VFIO Type1 emulation > implementing P2P, since iommufd can now get a DMABUF from a VA that > it's mapping for IO; the VMAs' vm_file is that of the backing > DMABUF. > > > Revocation/reclaim > ================== > > Mapping a BAR subset is useful, but the lifetime of access granted to > a client needs to be managed well. For example, a protocol between > the primary process and the client can indicate when the client is > done, and when it's safe to reuse the resources elsewhere, but cleanup > can't practically be cooperative. > > For robustness, we enable the driver to make the resources > guaranteed-inaccessible when it chooses, so that it can re-assign them > to other uses in future. > > "vfio/pci: Permanently revoke a DMABUF on request" adds a new VFIO > device fd ioctl, VFIO_DEVICE_PCI_DMABUF_REVOKE. This takes a DMABUF > fd parameter previously exported (from that device!) and permanently > revokes the DMABUF. This notifies/detaches importers, zaps PTEs for > any mappings, and guarantees no future attachment/import/map/access is > possible by any means. > > A primary driver process would use this operation when the client's > tenure ends to reclaim "loaned-out" MMIO interfaces, at which point > the interfaces could be safely re-used. > > New in v2: ioctl() on VFIO driver fd, rather than DMABUF fd. A DMABUF > is revoked using code common to vfio_pci_dma_buf_move(), selectively > zapping mappings (after waiting for completion on the > dma_buf_invalidate_mappings() request). > > > BAR mapping access attributes > ============================= > > Inspired by Alex [Mastro] and Jason's comments in [0] and Mahmoud's > work in [1] with the goal of controlling CPU access attributes for > VFIO BAR mappings (e.g. WC), we can decorate DMABUFs with access > attributes that are then used by a mapping's PTEs. > > I've proposed reserving a field in struct > vfio_device_feature_dma_buf's flags to specify an attribute for its > ranges. Although that keeps the (UAPI) struct unchanged, it means all > ranges in a DMABUF share the same attribute. I feel a single > attribute-to-mmap() relation is logical/reasonable. An application > can also create multiple DMABUFs to describe any BAR layout and mix of > attributes. > > > Tests > ===== > > (Still sharing the [RFC ONLY] userspace test/demo program for context, > not for merge.) > > It illustrates & tests various map/revoke cases, but doesn't use the > existing VFIO selftests and relies on a (tweaked) QEMU EDU function. > I'm (still) working on integrating the scenarios into the existing > VFIO selftests. > > This code has been tested in mapping DMABUFs of single/multiple > ranges, aliasing mmap()s, aliasing ranges across DMABUFs, vm_pgoff > > 0, revocation, shutdown/cleanup scenarios, and hugepage mappings seem > to work correctly. I've lightly tested WC mappings also (by observing > resulting PTEs as having the correct attributes...). > > > Fin > === > > v2 is based on next-20260310 (to build on Leon's recent series > "vfio: Wait for dma-buf invalidation to complete" [2]). > > > Please share your thoughts! I'd like to de-RFC if we feel this > approach is now fair. I only skimmed over it, but at least of hand I couldn't find anything fundamentally wrong. The locking order seems to change in patch #6. In general I strongly recommend to enable lockdep while testing anyway but explicitly when I see such changes. Additional to that it might also be a good idea to have a lockdep initcall function which defines the locking order in the way all the VFIO code should follow. See function dma_resv_lockdep() for an example on how to do that. Especially with mmap support and all the locks involved with that it has proven to be a good practice to have something like that. Regards, Christian. > > > Many thanks, > > > Matt > > > > References: > > [0]: https://lore.kernel.org/linux-iommu/20250918214425.2677057-1-amastro@fb.com/ > [1]: https://lore.kernel.org/all/20250804104012.87915-1-mngyadam@amazon.de/ > [2]: https://lore.kernel.org/linux-iommu/20260205-nocturnal-poetic-chamois-f566a… > [3]: https://lore.kernel.org/all/20260226202211.929005-1-mattev@meta.com/ > > -------------------------------------------------------------------------------- > Changelog: > > v2: Respin based on the feedback/suggestions: > > - Transform the existing VFIO BAR mmap path to also use DMABUFs behind > the scenes, and then simply share that code for explicitly-mapped > DMABUFs. > > - Refactors the export itself out of vfio_pci_core_feature_dma_buf, > and shared by a new vfio_pci_core_mmap_prep_dmabuf helper used by > the regular VFIO mmap to create a DMABUF. > > - Revoke buffers using a VFIO device fd ioctl > > v1: https://lore.kernel.org/all/20260226202211.929005-1-mattev@meta.com/ > > > Matt Evans (10): > vfio/pci: Set up VFIO barmap before creating a DMABUF > vfio/pci: Clean up DMABUFs before disabling function > vfio/pci: Add helper to look up PFNs for DMABUFs > vfio/pci: Add a helper to create a DMABUF for a BAR-map VMA > vfio/pci: Convert BAR mmap() to use a DMABUF > vfio/pci: Remove vfio_pci_zap_bars() > vfio/pci: Support mmap() of a VFIO DMABUF > vfio/pci: Permanently revoke a DMABUF on request > vfio/pci: Add mmap() attributes to DMABUF feature > [RFC ONLY] selftests: vfio: Add standalone vfio_dmabuf_mmap_test > > drivers/vfio/pci/Kconfig | 3 +- > drivers/vfio/pci/Makefile | 3 +- > drivers/vfio/pci/vfio_pci_config.c | 18 +- > drivers/vfio/pci/vfio_pci_core.c | 123 +-- > drivers/vfio/pci/vfio_pci_dmabuf.c | 425 +++++++-- > drivers/vfio/pci/vfio_pci_priv.h | 46 +- > include/uapi/linux/vfio.h | 42 +- > tools/testing/selftests/vfio/Makefile | 1 + > .../vfio/standalone/vfio_dmabuf_mmap_test.c | 837 ++++++++++++++++++ > 9 files changed, 1339 insertions(+), 159 deletions(-) > create mode 100644 tools/testing/selftests/vfio/standalone/vfio_dmabuf_mmap_test.c >

16 hours, 31 minutes

Re: [RFC v2 PATCH 06/10] vfio/pci: Remove vfio_pci_zap_bars()

by Christian König

On 3/12/26 19:46, Matt Evans wrote: > vfio_pci_zap_bars() and the wrapper > vfio_pci_zap_and_down_write_memory_lock() are redundant as of > "vfio/pci: Convert BAR mmap() to use a DMABUF". The DMABUFs used for > BAR mappings already zap PTEs via the existing > vfio_pci_dma_buf_move(), which notifies changes to the BAR space > (e.g. around reset). > > Remove the old functions, and the various points needing to zap BARs > become slightly cleaner. No a full review, but it looks like you now take the DMA buf reservation lock while holding vdev->memory_lock. I strongly recommend enabling lockdep while testing that, just to be on the sure side that all locks are taken in a consistend order. Regards, Christian. > > Signed-off-by: Matt Evans <mattev(a)meta.com> > --- > drivers/vfio/pci/vfio_pci_config.c | 18 ++++++------------ > drivers/vfio/pci/vfio_pci_core.c | 30 +++++++----------------------- > drivers/vfio/pci/vfio_pci_priv.h | 1 - > 3 files changed, 13 insertions(+), 36 deletions(-) > > diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c > index b4e39253f98d..c7ed28be1104 100644 > --- a/drivers/vfio/pci/vfio_pci_config.c > +++ b/drivers/vfio/pci/vfio_pci_config.c > @@ -590,12 +590,9 @@ static int vfio_basic_config_write(struct vfio_pci_core_device *vdev, int pos, > virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY); > new_mem = !!(new_cmd & PCI_COMMAND_MEMORY); > > - if (!new_mem) { > - vfio_pci_zap_and_down_write_memory_lock(vdev); > + down_write(&vdev->memory_lock); > + if (!new_mem) > vfio_pci_dma_buf_move(vdev, true); > - } else { > - down_write(&vdev->memory_lock); > - } > > /* > * If the user is writing mem/io enable (new_mem/io) and we > @@ -712,12 +709,9 @@ static int __init init_pci_cap_basic_perm(struct perm_bits *perm) > static void vfio_lock_and_set_power_state(struct vfio_pci_core_device *vdev, > pci_power_t state) > { > - if (state >= PCI_D3hot) { > - vfio_pci_zap_and_down_write_memory_lock(vdev); > + down_write(&vdev->memory_lock); > + if (state >= PCI_D3hot) > vfio_pci_dma_buf_move(vdev, true); > - } else { > - down_write(&vdev->memory_lock); > - } > > vfio_pci_set_power_state(vdev, state); > if (__vfio_pci_memory_enabled(vdev)) > @@ -908,7 +902,7 @@ static int vfio_exp_config_write(struct vfio_pci_core_device *vdev, int pos, > &cap); > > if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) { > - vfio_pci_zap_and_down_write_memory_lock(vdev); > + down_write(&vdev->memory_lock); > vfio_pci_dma_buf_move(vdev, true); > pci_try_reset_function(vdev->pdev); > if (__vfio_pci_memory_enabled(vdev)) > @@ -993,7 +987,7 @@ static int vfio_af_config_write(struct vfio_pci_core_device *vdev, int pos, > &cap); > > if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) { > - vfio_pci_zap_and_down_write_memory_lock(vdev); > + down_write(&vdev->memory_lock); > vfio_pci_dma_buf_move(vdev, true); > pci_try_reset_function(vdev->pdev); > if (__vfio_pci_memory_enabled(vdev)) > diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c > index 41224efa58d8..9e9ad97c2f7f 100644 > --- a/drivers/vfio/pci/vfio_pci_core.c > +++ b/drivers/vfio/pci/vfio_pci_core.c > @@ -319,7 +319,7 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev, > * The vdev power related flags are protected with 'memory_lock' > * semaphore. > */ > - vfio_pci_zap_and_down_write_memory_lock(vdev); > + down_write(&vdev->memory_lock); > vfio_pci_dma_buf_move(vdev, true); > > if (vdev->pm_runtime_engaged) { > @@ -1229,7 +1229,7 @@ static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev, > if (!vdev->reset_works) > return -EINVAL; > > - vfio_pci_zap_and_down_write_memory_lock(vdev); > + down_write(&vdev->memory_lock); > > /* > * This function can be invoked while the power state is non-D0. If > @@ -1613,22 +1613,6 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu > } > EXPORT_SYMBOL_GPL(vfio_pci_core_write); > > -static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev) > -{ > - struct vfio_device *core_vdev = &vdev->vdev; > - loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX); > - loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX); > - loff_t len = end - start; > - > - unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true); > -} > - > -void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev) > -{ > - down_write(&vdev->memory_lock); > - vfio_pci_zap_bars(vdev); > -} > - > u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev) > { > u16 cmd; > @@ -2487,10 +2471,11 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, > } > > /* > - * Take the memory write lock for each device and zap BAR > - * mappings to prevent the user accessing the device while in > - * reset. Locking multiple devices is prone to deadlock, > - * runaway and unwind if we hit contention. > + * Take the memory write lock for each device and > + * revoke all DMABUFs, which will prevent any access > + * to the device while in reset. Locking multiple > + * devices is prone to deadlock, runaway and unwind if > + * we hit contention. > */ > if (!down_write_trylock(&vdev->memory_lock)) { > ret = -EBUSY; > @@ -2498,7 +2483,6 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, > } > > vfio_pci_dma_buf_move(vdev, true); > - vfio_pci_zap_bars(vdev); > } > > if (!list_entry_is_head(vdev, > diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h > index 37ece9b4b5bd..e201c96bbb14 100644 > --- a/drivers/vfio/pci/vfio_pci_priv.h > +++ b/drivers/vfio/pci/vfio_pci_priv.h > @@ -78,7 +78,6 @@ void vfio_config_free(struct vfio_pci_core_device *vdev); > int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, > pci_power_t state); > > -void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev); > u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); > void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, > u16 cmd);

16 hours, 40 minutes

Re: [PATCH 00/15] tracepoint: Avoid double static_branch evaluation at guarded call sites

by Peter Zijlstra

On Thu, Mar 12, 2026 at 11:49:23AM -0400, Mathieu Desnoyers wrote: > On 2026-03-12 11:40, Steven Rostedt wrote: > > On Thu, 12 Mar 2026 11:28:07 -0400 > > Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> wrote: > > > > > > Note, Vineeth came up with the naming. I would have done "do" but when I > > > > saw "invoke" I thought it sounded better. > > > > > > It works as long as you don't have a tracing subsystem called > > > "invoke", then you get into identifier clash territory. > > > > True. Perhaps we should do the double underscore trick. > > > > Instead of: trace_invoke_foo() > > > > use: trace_invoke__foo() > > > > > > Which will make it more visible to what the trace event is. > > > > Hmm, we probably should have used: trace__foo() for all tracepoints, as > > there's still functions that are called trace_foo() that are not > > tracepoints :-p > > One certain way to eliminate identifier clash would be to go for a > prefix to "trace_", e.g. Oh, I know!, call them __do_trace_##foo(). /me runs like hell

1 day, 9 hours

Re: [PATCH 01/15] tracepoint: Add trace_invoke_##name() API

by Peter Zijlstra

On Thu, Mar 12, 2026 at 11:39:06AM -0400, Vineeth Remanan Pillai wrote: > On Thu, Mar 12, 2026 at 11:13 AM Steven Rostedt <rostedt(a)goodmis.org> wrote: > > > > On Thu, 12 Mar 2026 11:04:56 -0400 > > "Vineeth Pillai (Google)" <vineeth(a)bitbyteword.org> wrote: > > > > > Add trace_invoke_##name() as a companion to trace_##name(). When a > > > caller already guards a tracepoint with an explicit enabled check: > > > > > > if (trace_foo_enabled() && cond) > > > trace_foo(args); > > > > > > trace_foo() internally repeats the static_branch_unlikely() test, which > > > the compiler cannot fold since static branches are patched binary > > > instructions. This results in two static-branch evaluations for every > > > guarded call site. > > > > > > trace_invoke_##name() calls __do_trace_##name() directly, skipping the > > > redundant static-branch re-check. This avoids leaking the internal > > > __do_trace_##name() symbol into call sites while still eliminating the > > > double evaluation: > > > > > > if (trace_foo_enabled() && cond) > > > trace_invoke_foo(args); /* calls __do_trace_foo() directly */ > > > > > > Three locations are updated: > > > - __DECLARE_TRACE: invoke form omits static_branch_unlikely, retains > > > the LOCKDEP RCU-watching assertion. > > > - __DECLARE_TRACE_SYSCALL: same, plus retains might_fault(). > > > - !TRACEPOINTS_ENABLED stub: empty no-op so callers compile cleanly > > > when tracepoints are compiled out. > > > > > > Suggested-by: Steven Rostedt <rostedt(a)goodmis.org> > > > Suggested-by: Peter Zijlstra <peterz(a)infradead.org> > > > Signed-off-by: Vineeth Pillai (Google) <vineeth(a)bitbyteword.org> > > > Assisted-by: Claude:claude-sonnet-4-6 > > > > I'm guessing Claude helped with the other patches. Did it really help with this one? > > > > Claude wrote and build tested the whole series based on my guidance > and prompt :-). I verified the series before sending it out, but > claude did the initial work. That seems like an unreasonable waste of energy. You could've had claude write a Coccinelle script for you and saved a ton of tokens.

1 day, 9 hours

Re: [PATCH net-next v3 1/2] dma-mapping: introduce DMA_ATTR_CC_DECRYPTED for pre-decrypted memory

by Jason Gunthorpe

On Thu, Mar 12, 2026 at 10:03:37AM +0100, Jiri Pirko wrote: > >Alot of device MMIO is decrypted by nature and can't be encrypted, so > >you'd have to use both flags. eg in VFIO we'd want to do this. > > Why both flags? Why MMIO flag is not enough? You still want to hit > "if (attrs & DMA_ATTR_MMIO) {" path, don't you? Because we will eventually have both decrypted and encrypted MMIO. > I mean, CC_DECRYPTED says the memory to be mapped was explicitly > decrypted before the call. MMIO was not explicitly decrypted, it is > decrypted by definition. For me that does not fit the CC_DECRYPTED > semantics. I would say CC_DECRYPTED means that pgprot_decrypted must be used to form a PTE, and !CC_DECRYPTED means that pgprot_encrypted() was used This flag should someday flow down into the vIOMMU driver and set the corresponding C bit the IOPTE (for AMD) exactly as the pgprot does. Less about set_memory_encrypted as that is only for DRAM. Jason

1 day, 13 hours

I HAVE RETRIEVED MY LOCKED BTC 🥳

by Ambrose MacQuoid

Hey everyone! I'm thrilled to announce that I have fully rec0vered my l0cked BTC from an inve stment platf0rm even after 3 months it happened. Here's a quick story. Early this year, I came across an inve stment platf0rm that gave me my profit after the first inve stment , I did the second it was successful and I tried the 3rd this time with a bigger amount of $120,000, when it was time for withdr awal I couldn't, the option was l0cked, After weeks of trying I l0st hope, fast-forward to last week I saw a post about rec0 vering l0cked or st0len fuñ ds, tho I was skeptical but I gave it a try what more could I lose?? In 2 4hrs ghosttrackhackers@gmail . com h€lped me r€trieve my full fuπds (of $120,000) including profit ($40,000). It's back safe in my w@ll€t. I know many have fallen v!ct!m too you can re@ch out to th€m for h€lp they're l€git and €asy to talk to. Goodluck. ✉️: ghosttrackhackers @ gmail . com

1 day, 16 hours

Re: [PATCH net-next v3 1/2] dma-mapping: introduce DMA_ATTR_CC_DECRYPTED for pre-decrypted memory

by Jason Gunthorpe

On Mon, Mar 09, 2026 at 06:51:21PM +0100, Jiri Pirko wrote: > Mon, Mar 09, 2026 at 04:18:57PM +0100, jgg(a)ziepe.ca wrote: > >On Mon, Mar 09, 2026 at 04:02:33PM +0200, Leon Romanovsky wrote: > >> On Mon, Mar 09, 2026 at 10:15:30AM -0300, Jason Gunthorpe wrote: > >> > On Sun, Mar 08, 2026 at 12:19:48PM +0200, Leon Romanovsky wrote: > >> > > >> > > > +/* > >> > > > + * DMA_ATTR_CC_DECRYPTED: Indicates memory that has been explicitly decrypted > >> > > > + * (shared) for confidential computing guests. The caller must have > >> > > > + * called set_memory_decrypted(). A struct page is required. > >> > > > + */ > >> > > > +#define DMA_ATTR_CC_DECRYPTED (1UL << 12) > >> > > > >> > > While adding the new attribute is fine, I would expect additional checks in > >> > > dma_map_phys() to ensure the attribute cannot be misused. For example, > >> > > WARN_ON(attrs & (DMA_ATTR_CC_DECRYPTED | DMA_ATTR_MMIO)), along with a check > >> > > that we are taking the direct path only. > >> > > >> > DECRYPYED and MMIO is something that needs to work, VFIO (inside a > >> > TVM) should be using that combination. > >> > >> So this sentence "A struct page is required" from the comment above is > >> not accurate. > > > >It would be clearer to say "Unless DMA_ATTR_MMIO is provided a struct > >page is required" > > > >We need to audit if that works properly, IIRC it does, but I don't > >remember.. Jiri? > > How can you do set_memory_decrypted if you don't have page/folio ? Alot of device MMIO is decrypted by nature and can't be encrypted, so you'd have to use both flags. eg in VFIO we'd want to do this. Jason

2 days, 1 hour

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig