From: Leon Romanovsky Currently the P2PDMA code requires a pgmap and a struct page to function. The was serving three important purposes: - DMA API compatibility, where scatterlist required a struct page as input - Life cycle management, the percpu_ref is used to prevent UAF during device hot unplug - A way to get the P2P provider data through the pci_p2pdma_pagemap The DMA API now has a new flow, and has gained phys_addr_t support, so it no longer needs struct pages to perform P2P mapping. Lifecycle management can be delegated to the user, DMABUF for instance has a suitable invalidation protocol that does not require struct page. Finding the P2P provider data can also be managed by the caller without need to look it up from the phys_addr. Split the P2PDMA code into two layers. The optional upper layer, effectively, provides a way to mmap() P2P memory into a VMA by providing struct page, pgmap, a genalloc and sysfs. The lower layer provides the actual P2P infrastructure and is wrapped up in a new struct p2pdma_provider. Rework the mmap layer to use new p2pdma_provider based APIs. Drivers that do not want to put P2P memory into VMA's can allocate a struct p2pdma_provider after probe() starts and free it before remove() completes. When DMA mapping the driver must convey the struct p2pdma_provider to the DMA mapping code along with a phys_addr of the MMIO BAR slice to map. The driver must ensure that no DMA mapping outlives the lifetime of the struct p2pdma_provider. The intended target of this new API layer is DMABUF. There is usually only a single p2pdma_provider for a DMABUF exporter. Most drivers can establish the p2pdma_provider during probe, access the single instance during DMABUF attach and use that to drive the DMA mapping. DMABUF provides an invalidation mechanism that can guarantee all DMA is halted and the DMA mappings are undone prior to destroying the struct p2pdma_provider. This ensures there is no UAF through DMABUFs that are lingering past driver removal. The new p2pdma_provider layer cannot be used to create P2P memory that can be mapped into VMA's, be used with pin_user_pages(), O_DIRECT, and so on. These use cases must still use the mmap() layer. The p2pdma_provider layer is principally for DMABUF-like use cases where DMABUF natively manages the life cycle and access instead of vmas/pin_user_pages()/struct page. In addition, remove the bus_off field from pci_p2pdma_map_state since it duplicates information already available in the pgmap structure. The bus_offset is only used in one location (pci_p2pdma_bus_addr_map) and is always identical to pgmap->bus_offset. Signed-off-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky --- drivers/pci/p2pdma.c | 43 ++++++++++++++++++++------------------ include/linux/pci-p2pdma.h | 19 ++++++++++++----- 2 files changed, 37 insertions(+), 25 deletions(-) diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index da5657a02007..176a99232fdc 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -28,9 +28,8 @@ struct pci_p2pdma { }; struct pci_p2pdma_pagemap { - struct pci_dev *provider; - u64 bus_offset; struct dev_pagemap pgmap; + struct p2pdma_provider mem; }; static struct pci_p2pdma_pagemap *to_p2p_pgmap(struct dev_pagemap *pgmap) @@ -204,8 +203,8 @@ static void p2pdma_page_free(struct page *page) { struct pci_p2pdma_pagemap *pgmap = to_p2p_pgmap(page_pgmap(page)); /* safe to dereference while a reference is held to the percpu ref */ - struct pci_p2pdma *p2pdma = - rcu_dereference_protected(pgmap->provider->p2pdma, 1); + struct pci_p2pdma *p2pdma = rcu_dereference_protected( + to_pci_dev(pgmap->mem.owner)->p2pdma, 1); struct percpu_ref *ref; gen_pool_free_owner(p2pdma->pool, (uintptr_t)page_to_virt(page), @@ -270,14 +269,15 @@ static int pci_p2pdma_setup(struct pci_dev *pdev) static void pci_p2pdma_unmap_mappings(void *data) { - struct pci_dev *pdev = data; + struct pci_p2pdma_pagemap *p2p_pgmap = data; /* * Removing the alloc attribute from sysfs will call * unmap_mapping_range() on the inode, teardown any existing userspace * mappings and prevent new ones from being created. */ - sysfs_remove_file_from_group(&pdev->dev.kobj, &p2pmem_alloc_attr.attr, + sysfs_remove_file_from_group(&p2p_pgmap->mem.owner->kobj, + &p2pmem_alloc_attr.attr, p2pmem_group.name); } @@ -328,10 +328,9 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pgmap->nr_range = 1; pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; pgmap->ops = &p2pdma_pgmap_ops; - - p2p_pgmap->provider = pdev; - p2p_pgmap->bus_offset = pci_bus_address(pdev, bar) - - pci_resource_start(pdev, bar); + p2p_pgmap->mem.owner = &pdev->dev; + p2p_pgmap->mem.bus_offset = + pci_bus_address(pdev, bar) - pci_resource_start(pdev, bar); addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { @@ -340,7 +339,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, } error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_unmap_mappings, - pdev); + p2p_pgmap); if (error) goto pages_free; @@ -973,16 +972,16 @@ void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) } EXPORT_SYMBOL_GPL(pci_p2pmem_publish); -static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap, - struct device *dev) +static enum pci_p2pdma_map_type +pci_p2pdma_map_type(struct p2pdma_provider *provider, struct device *dev) { enum pci_p2pdma_map_type type = PCI_P2PDMA_MAP_NOT_SUPPORTED; - struct pci_dev *provider = to_p2p_pgmap(pgmap)->provider; + struct pci_dev *pdev = to_pci_dev(provider->owner); struct pci_dev *client; struct pci_p2pdma *p2pdma; int dist; - if (!provider->p2pdma) + if (!pdev->p2pdma) return PCI_P2PDMA_MAP_NOT_SUPPORTED; if (!dev_is_pci(dev)) @@ -991,7 +990,7 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap, client = to_pci_dev(dev); rcu_read_lock(); - p2pdma = rcu_dereference(provider->p2pdma); + p2pdma = rcu_dereference(pdev->p2pdma); if (p2pdma) type = xa_to_value(xa_load(&p2pdma->map_types, @@ -999,7 +998,7 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap, rcu_read_unlock(); if (type == PCI_P2PDMA_MAP_UNKNOWN) - return calc_map_type_and_dist(provider, client, &dist, true); + return calc_map_type_and_dist(pdev, client, &dist, true); return type; } @@ -1007,9 +1006,13 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap, void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state, struct device *dev, struct page *page) { - state->pgmap = page_pgmap(page); - state->map = pci_p2pdma_map_type(state->pgmap, dev); - state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset; + struct pci_p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(page_pgmap(page)); + + if (state->mem == &p2p_pgmap->mem) + return; + + state->mem = &p2p_pgmap->mem; + state->map = pci_p2pdma_map_type(&p2p_pgmap->mem, dev); } /** diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index 075c20b161d9..27a2c399f47d 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -16,6 +16,16 @@ struct block_device; struct scatterlist; +/** + * struct p2pdma_provider + * + * A p2pdma provider is a range of MMIO address space available to the CPU. + */ +struct p2pdma_provider { + struct device *owner; + u64 bus_offset; +}; + #ifdef CONFIG_PCI_P2PDMA int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset); @@ -144,11 +154,11 @@ enum pci_p2pdma_map_type { }; struct pci_p2pdma_map_state { - struct dev_pagemap *pgmap; + struct p2pdma_provider *mem; enum pci_p2pdma_map_type map; - u64 bus_off; }; + /* helper for pci_p2pdma_state(), do not use directly */ void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state, struct device *dev, struct page *page); @@ -167,8 +177,7 @@ pci_p2pdma_state(struct pci_p2pdma_map_state *state, struct device *dev, struct page *page) { if (IS_ENABLED(CONFIG_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { - if (state->pgmap != page_pgmap(page)) - __pci_p2pdma_update_state(state, dev, page); + __pci_p2pdma_update_state(state, dev, page); return state->map; } return PCI_P2PDMA_MAP_NONE; @@ -186,7 +195,7 @@ static inline dma_addr_t pci_p2pdma_bus_addr_map(struct pci_p2pdma_map_state *state, phys_addr_t paddr) { WARN_ON_ONCE(state->map != PCI_P2PDMA_MAP_BUS_ADDR); - return paddr + state->bus_off; + return paddr + state->mem->bus_offset; } #endif /* _LINUX_PCI_P2P_H */ -- 2.51.0 From: Leon Romanovsky Update the pci_p2pdma_bus_addr_map() function to take a direct pointer to the p2pdma_provider structure instead of the pci_p2pdma_map_state. This simplifies the API by removing the need for callers to extract the provider from the state structure. The change updates all callers across the kernel (block layer, IOMMU, DMA direct, and HMM) to pass the provider pointer directly, making the code more explicit and reducing unnecessary indirection. This also removes the runtime warning check since callers now have direct control over which provider they use. Signed-off-by: Leon Romanovsky --- block/blk-mq-dma.c | 2 +- drivers/iommu/dma-iommu.c | 4 ++-- include/linux/pci-p2pdma.h | 7 +++---- kernel/dma/direct.c | 4 ++-- mm/hmm.c | 2 +- 5 files changed, 9 insertions(+), 10 deletions(-) diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c index d415088ed9fd..430e51ec494a 100644 --- a/block/blk-mq-dma.c +++ b/block/blk-mq-dma.c @@ -79,7 +79,7 @@ static inline bool blk_can_dma_map_iova(struct request *req, static bool blk_dma_map_bus(struct blk_dma_iter *iter, struct phys_vec *vec) { - iter->addr = pci_p2pdma_bus_addr_map(&iter->p2pdma, vec->paddr); + iter->addr = pci_p2pdma_bus_addr_map(iter->p2pdma.mem, vec->paddr); iter->len = vec->len; return true; } diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 7944a3af4545..e52d19d2e833 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1439,8 +1439,8 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, * as a bus address, __finalise_sg() will copy the dma * address into the output segment. */ - s->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state, - sg_phys(s)); + s->dma_address = pci_p2pdma_bus_addr_map( + p2pdma_state.mem, sg_phys(s)); sg_dma_len(s) = sg->length; sg_dma_mark_bus_address(s); continue; diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index 27a2c399f47d..eef96636c67e 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -186,16 +186,15 @@ pci_p2pdma_state(struct pci_p2pdma_map_state *state, struct device *dev, /** * pci_p2pdma_bus_addr_map - Translate a physical address to a bus address * for a PCI_P2PDMA_MAP_BUS_ADDR transfer. - * @state: P2P state structure + * @provider: P2P provider structure * @paddr: physical address to map * * Map a physically contiguous PCI_P2PDMA_MAP_BUS_ADDR transfer. */ static inline dma_addr_t -pci_p2pdma_bus_addr_map(struct pci_p2pdma_map_state *state, phys_addr_t paddr) +pci_p2pdma_bus_addr_map(struct p2pdma_provider *provider, phys_addr_t paddr) { - WARN_ON_ONCE(state->map != PCI_P2PDMA_MAP_BUS_ADDR); - return paddr + state->mem->bus_offset; + return paddr + provider->bus_offset; } #endif /* _LINUX_PCI_P2P_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 1062caac47e7..3e058c99fe85 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -484,8 +484,8 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, } break; case PCI_P2PDMA_MAP_BUS_ADDR: - sg->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state, - sg_phys(sg)); + sg->dma_address = pci_p2pdma_bus_addr_map( + p2pdma_state.mem, sg_phys(sg)); sg_dma_mark_bus_address(sg); continue; default: diff --git a/mm/hmm.c b/mm/hmm.c index 6556c0e074ba..012b78688fa1 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -751,7 +751,7 @@ dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map, break; case PCI_P2PDMA_MAP_BUS_ADDR: pfns[idx] |= HMM_PFN_P2PDMA_BUS | HMM_PFN_DMA_MAPPED; - return pci_p2pdma_bus_addr_map(p2pdma_state, paddr); + return pci_p2pdma_bus_addr_map(p2pdma_state->mem, paddr); default: return DMA_MAPPING_ERROR; } -- 2.51.0 From: Leon Romanovsky Refactor the PCI P2PDMA subsystem to separate the core peer-to-peer DMA functionality from the optional memory allocation layer. This creates a two-tier architecture: The core layer provides P2P mapping functionality for physical addresses based on PCI device MMIO BARs and integrates with the DMA API for mapping operations. This layer is required for all P2PDMA users. The optional upper layer provides memory allocation capabilities including gen_pool allocator, struct page support, and sysfs interface for user space access. This separation allows subsystems like VFIO to use only the core P2P mapping functionality without the overhead of memory allocation features they don't need. The core functionality is now available through the new pcim_p2pdma_provider() function that returns a p2pdma_provider structure. Signed-off-by: Leon Romanovsky --- drivers/pci/p2pdma.c | 141 ++++++++++++++++++++++++++++--------- include/linux/pci-p2pdma.h | 11 +++ 2 files changed, 120 insertions(+), 32 deletions(-) diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 176a99232fdc..b433764dd36d 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -25,11 +25,12 @@ struct pci_p2pdma { struct gen_pool *pool; bool p2pmem_published; struct xarray map_types; + struct p2pdma_provider mem[PCI_STD_NUM_BARS]; }; struct pci_p2pdma_pagemap { struct dev_pagemap pgmap; - struct p2pdma_provider mem; + struct p2pdma_provider *mem; }; static struct pci_p2pdma_pagemap *to_p2p_pgmap(struct dev_pagemap *pgmap) @@ -204,7 +205,7 @@ static void p2pdma_page_free(struct page *page) struct pci_p2pdma_pagemap *pgmap = to_p2p_pgmap(page_pgmap(page)); /* safe to dereference while a reference is held to the percpu ref */ struct pci_p2pdma *p2pdma = rcu_dereference_protected( - to_pci_dev(pgmap->mem.owner)->p2pdma, 1); + to_pci_dev(pgmap->mem->owner)->p2pdma, 1); struct percpu_ref *ref; gen_pool_free_owner(p2pdma->pool, (uintptr_t)page_to_virt(page), @@ -227,44 +228,111 @@ static void pci_p2pdma_release(void *data) /* Flush and disable pci_alloc_p2p_mem() */ pdev->p2pdma = NULL; - synchronize_rcu(); + if (p2pdma->pool) + synchronize_rcu(); + xa_destroy(&p2pdma->map_types); + + if (!p2pdma->pool) + return; gen_pool_destroy(p2pdma->pool); sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group); - xa_destroy(&p2pdma->map_types); } -static int pci_p2pdma_setup(struct pci_dev *pdev) +/** + * pcim_p2pdma_init - Initialise peer-to-peer DMA providers + * @pdev: The PCI device to enable P2PDMA for + * + * This function initializes the peer-to-peer DMA infrastructure + * for a PCI device. It allocates and sets up the necessary data + * structures to support P2PDMA operations, including mapping type + * tracking. + */ +int pcim_p2pdma_init(struct pci_dev *pdev) { - int error = -ENOMEM; struct pci_p2pdma *p2p; + int i, ret; + + p2p = rcu_dereference_protected(pdev->p2pdma, 1); + if (p2p) + return 0; p2p = devm_kzalloc(&pdev->dev, sizeof(*p2p), GFP_KERNEL); if (!p2p) return -ENOMEM; xa_init(&p2p->map_types); + /* + * Iterate over all standard PCI BARs and record only those that + * correspond to MMIO regions. Skip non-memory resources (e.g. I/O + * port BARs) since they cannot be used for peer-to-peer (P2P) + * transactions. + */ + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM)) + continue; - p2p->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev)); - if (!p2p->pool) - goto out; + p2p->mem[i].owner = &pdev->dev; + p2p->mem[i].bus_offset = + pci_bus_address(pdev, i) - pci_resource_start(pdev, i); + } - error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev); - if (error) - goto out_pool_destroy; + ret = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev); + if (ret) + goto out_p2p; - error = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group); - if (error) + rcu_assign_pointer(pdev->p2pdma, p2p); + return 0; + +out_p2p: + devm_kfree(&pdev->dev, p2p); + return ret; +} +EXPORT_SYMBOL_GPL(pcim_p2pdma_init); + +/** + * pcim_p2pdma_provider - Get peer-to-peer DMA provider + * @pdev: The PCI device to enable P2PDMA for + * @bar: BAR index to get provider + * + * This function gets peer-to-peer DMA provider for a PCI device. + */ +struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar) +{ + struct pci_p2pdma *p2p; + + if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) + return NULL; + + p2p = rcu_dereference_protected(pdev->p2pdma, 1); + return &p2p->mem[bar]; +} +EXPORT_SYMBOL_GPL(pcim_p2pdma_provider); + +static int pci_p2pdma_setup_pool(struct pci_dev *pdev) +{ + struct pci_p2pdma *p2pdma; + int ret; + + p2pdma = rcu_dereference_protected(pdev->p2pdma, 1); + if (p2pdma->pool) + /* We already setup pools, do nothing, */ + return 0; + + p2pdma->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev)); + if (!p2pdma->pool) + return -ENOMEM; + + ret = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group); + if (ret) goto out_pool_destroy; - rcu_assign_pointer(pdev->p2pdma, p2p); return 0; out_pool_destroy: - gen_pool_destroy(p2p->pool); -out: - devm_kfree(&pdev->dev, p2p); - return error; + gen_pool_destroy(p2pdma->pool); + p2pdma->pool = NULL; + return ret; } static void pci_p2pdma_unmap_mappings(void *data) @@ -276,7 +344,7 @@ static void pci_p2pdma_unmap_mappings(void *data) * unmap_mapping_range() on the inode, teardown any existing userspace * mappings and prevent new ones from being created. */ - sysfs_remove_file_from_group(&p2p_pgmap->mem.owner->kobj, + sysfs_remove_file_from_group(&p2p_pgmap->mem->owner->kobj, &p2pmem_alloc_attr.attr, p2pmem_group.name); } @@ -295,6 +363,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) { struct pci_p2pdma_pagemap *p2p_pgmap; + struct p2pdma_provider *mem; struct dev_pagemap *pgmap; struct pci_p2pdma *p2pdma; void *addr; @@ -312,11 +381,21 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, if (size + offset > pci_resource_len(pdev, bar)) return -EINVAL; - if (!pdev->p2pdma) { - error = pci_p2pdma_setup(pdev); - if (error) - return error; - } + error = pcim_p2pdma_init(pdev); + if (error) + return error; + + error = pci_p2pdma_setup_pool(pdev); + if (error) + return error; + + mem = pcim_p2pdma_provider(pdev, bar); + /* + * We checked validity of BAR prior to call + * to pcim_p2pdma_provider. It should never return NULL. + */ + if (WARN_ON(!mem)) + return -EINVAL; p2p_pgmap = devm_kzalloc(&pdev->dev, sizeof(*p2p_pgmap), GFP_KERNEL); if (!p2p_pgmap) @@ -328,9 +407,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pgmap->nr_range = 1; pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; pgmap->ops = &p2pdma_pgmap_ops; - p2p_pgmap->mem.owner = &pdev->dev; - p2p_pgmap->mem.bus_offset = - pci_bus_address(pdev, bar) - pci_resource_start(pdev, bar); + p2p_pgmap->mem = mem; addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { @@ -359,7 +436,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pages_free: devm_memunmap_pages(&pdev->dev, pgmap); pgmap_free: - devm_kfree(&pdev->dev, pgmap); + devm_kfree(&pdev->dev, p2p_pgmap); return error; } EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource); @@ -1008,11 +1085,11 @@ void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state, { struct pci_p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(page_pgmap(page)); - if (state->mem == &p2p_pgmap->mem) + if (state->mem == p2p_pgmap->mem) return; - state->mem = &p2p_pgmap->mem; - state->map = pci_p2pdma_map_type(&p2p_pgmap->mem, dev); + state->mem = p2p_pgmap->mem; + state->map = pci_p2pdma_map_type(p2p_pgmap->mem, dev); } /** diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index eef96636c67e..ce0f163e1600 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -27,6 +27,8 @@ struct p2pdma_provider { }; #ifdef CONFIG_PCI_P2PDMA +int pcim_p2pdma_init(struct pci_dev *pdev); +struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar); int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset); int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, @@ -45,6 +47,15 @@ int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev, bool use_p2pdma); #else /* CONFIG_PCI_P2PDMA */ +static inline int pcim_p2pdma_init(struct pci_dev *pdev) +{ + return -EOPNOTSUPP; +} +static inline struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, + int bar) +{ + return ERR_PTR(-EOPNOTSUPP); +} static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) { -- 2.51.0 From: Leon Romanovsky Export the pci_p2pdma_map_type() function to allow external modules and subsystems to determine the appropriate mapping type for P2PDMA transfers between a provider and target device. The function determines whether peer-to-peer DMA transfers can be done directly through PCI switches (PCI_P2PDMA_MAP_BUS_ADDR) or must go through the host bridge (PCI_P2PDMA_MAP_THRU_HOST_BRIDGE), or if the transfer is not supported at all. This export enables subsystems like VFIO to properly handle P2PDMA operations by querying the mapping type before attempting transfers, ensuring correct DMA address programming and error handling. Signed-off-by: Leon Romanovsky --- drivers/pci/p2pdma.c | 15 ++++++- include/linux/pci-p2pdma.h | 85 +++++++++++++++++++++----------------- 2 files changed, 59 insertions(+), 41 deletions(-) diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index b433764dd36d..6edf9a211f11 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -1049,8 +1049,18 @@ void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) } EXPORT_SYMBOL_GPL(pci_p2pmem_publish); -static enum pci_p2pdma_map_type -pci_p2pdma_map_type(struct p2pdma_provider *provider, struct device *dev) +/** + * pci_p2pdma_map_type - Determine the mapping type for P2PDMA transfers + * @provider: P2PDMA provider structure + * @dev: Target device for the transfer + * + * Determines how peer-to-peer DMA transfers should be mapped between + * the provider and the target device. The mapping type indicates whether + * the transfer can be done directly through PCI switches or must go + * through the host bridge. + */ +enum pci_p2pdma_map_type pci_p2pdma_map_type(struct p2pdma_provider *provider, + struct device *dev) { enum pci_p2pdma_map_type type = PCI_P2PDMA_MAP_NOT_SUPPORTED; struct pci_dev *pdev = to_pci_dev(provider->owner); @@ -1079,6 +1089,7 @@ pci_p2pdma_map_type(struct p2pdma_provider *provider, struct device *dev) return type; } +EXPORT_SYMBOL_GPL(pci_p2pdma_map_type); void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state, struct device *dev, struct page *page) diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index ce0f163e1600..2efbcbcecd67 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -26,6 +26,45 @@ struct p2pdma_provider { u64 bus_offset; }; +enum pci_p2pdma_map_type { + /* + * PCI_P2PDMA_MAP_UNKNOWN: Used internally as an initial state before + * the mapping type has been calculated. Exported routines for the API + * will never return this value. + */ + PCI_P2PDMA_MAP_UNKNOWN = 0, + + /* + * Not a PCI P2PDMA transfer. + */ + PCI_P2PDMA_MAP_NONE, + + /* + * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will + * traverse the host bridge and the host bridge is not in the + * allowlist. DMA Mapping routines should return an error when + * this is returned. + */ + PCI_P2PDMA_MAP_NOT_SUPPORTED, + + /* + * PCI_P2PDMA_MAP_BUS_ADDR: Indicates that two devices can talk to + * each other directly through a PCI switch and the transaction will + * not traverse the host bridge. Such a mapping should program + * the DMA engine with PCI bus addresses. + */ + PCI_P2PDMA_MAP_BUS_ADDR, + + /* + * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk + * to each other, but the transaction traverses a host bridge on the + * allowlist. In this case, a normal mapping either with CPU physical + * addresses (in the case of dma-direct) or IOVA addresses (in the + * case of IOMMUs) should be used to program the DMA engine. + */ + PCI_P2PDMA_MAP_THRU_HOST_BRIDGE, +}; + #ifdef CONFIG_PCI_P2PDMA int pcim_p2pdma_init(struct pci_dev *pdev); struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar); @@ -46,6 +85,8 @@ int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, bool *use_p2pdma); ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev, bool use_p2pdma); +enum pci_p2pdma_map_type pci_p2pdma_map_type(struct p2pdma_provider *provider, + struct device *dev); #else /* CONFIG_PCI_P2PDMA */ static inline int pcim_p2pdma_init(struct pci_dev *pdev) { @@ -111,6 +152,11 @@ static inline ssize_t pci_p2pdma_enable_show(char *page, { return sprintf(page, "none\n"); } +static inline enum pci_p2pdma_map_type +pci_p2pdma_map_type(struct p2pdma_provider *provider, struct device *dev) +{ + return PCI_P2PDMA_MAP_NOT_SUPPORTED; +} #endif /* CONFIG_PCI_P2PDMA */ @@ -125,45 +171,6 @@ static inline struct pci_dev *pci_p2pmem_find(struct device *client) return pci_p2pmem_find_many(&client, 1); } -enum pci_p2pdma_map_type { - /* - * PCI_P2PDMA_MAP_UNKNOWN: Used internally as an initial state before - * the mapping type has been calculated. Exported routines for the API - * will never return this value. - */ - PCI_P2PDMA_MAP_UNKNOWN = 0, - - /* - * Not a PCI P2PDMA transfer. - */ - PCI_P2PDMA_MAP_NONE, - - /* - * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will - * traverse the host bridge and the host bridge is not in the - * allowlist. DMA Mapping routines should return an error when - * this is returned. - */ - PCI_P2PDMA_MAP_NOT_SUPPORTED, - - /* - * PCI_P2PDMA_MAP_BUS_ADDR: Indicates that two devices can talk to - * each other directly through a PCI switch and the transaction will - * not traverse the host bridge. Such a mapping should program - * the DMA engine with PCI bus addresses. - */ - PCI_P2PDMA_MAP_BUS_ADDR, - - /* - * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk - * to each other, but the transaction traverses a host bridge on the - * allowlist. In this case, a normal mapping either with CPU physical - * addresses (in the case of dma-direct) or IOVA addresses (in the - * case of IOMMUs) should be used to program the DMA engine. - */ - PCI_P2PDMA_MAP_THRU_HOST_BRIDGE, -}; - struct pci_p2pdma_map_state { struct p2pdma_provider *mem; enum pci_p2pdma_map_type map; -- 2.51.0 From: Leon Romanovsky Move the struct phys_vec definition from block/blk-mq-dma.c to include/linux/types.h to make it available for use across the kernel. The phys_vec structure represents a physical address range with a length, which is used by the new physical address-based DMA mapping API. This structure is already used by the block layer and will be needed by upcoming VFIO patches for dma-buf operations. Moving this definition to types.h provides a centralized location for this common data structure and eliminates code duplication across subsystems that need to work with physical address ranges. Signed-off-by: Leon Romanovsky --- block/blk-mq-dma.c | 5 ----- include/linux/types.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c index 430e51ec494a..8d2646ab2795 100644 --- a/block/blk-mq-dma.c +++ b/block/blk-mq-dma.c @@ -5,11 +5,6 @@ #include #include "blk.h" -struct phys_vec { - phys_addr_t paddr; - u32 len; -}; - static bool blk_map_iter_next(struct request *req, struct req_iterator *iter, struct phys_vec *vec) { diff --git a/include/linux/types.h b/include/linux/types.h index 6dfdb8e8e4c3..2bc56681b2e6 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -170,6 +170,11 @@ typedef u64 phys_addr_t; typedef u32 phys_addr_t; #endif +struct phys_vec { + phys_addr_t paddr; + u32 len; +}; + typedef phys_addr_t resource_size_t; /* -- 2.51.0 From: Vivek Kasireddy These helpers are useful for managing additional references taken on the device from other associated VFIO modules. Original-patch-by: Jason Gunthorpe Signed-off-by: Vivek Kasireddy Signed-off-by: Leon Romanovsky --- drivers/vfio/vfio_main.c | 2 ++ include/linux/vfio.h | 2 ++ 2 files changed, 4 insertions(+) diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 5046cae05222..2f0dcec67ffe 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -171,11 +171,13 @@ void vfio_device_put_registration(struct vfio_device *device) if (refcount_dec_and_test(&device->refcount)) complete(&device->comp); } +EXPORT_SYMBOL_GPL(vfio_device_put_registration); bool vfio_device_try_get_registration(struct vfio_device *device) { return refcount_inc_not_zero(&device->refcount); } +EXPORT_SYMBOL_GPL(vfio_device_try_get_registration); /* * VFIO driver API diff --git a/include/linux/vfio.h b/include/linux/vfio.h index eb563f538dee..217ba4ef1752 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -297,6 +297,8 @@ static inline void vfio_put_device(struct vfio_device *device) int vfio_register_group_dev(struct vfio_device *device); int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); +bool vfio_device_try_get_registration(struct vfio_device *device); +void vfio_device_put_registration(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set); -- 2.51.0 From: Leon Romanovsky Add new kernel config which indicates support for dma-buf export of MMIO regions, which implementation is provided in next patches. Signed-off-by: Leon Romanovsky --- drivers/vfio/pci/Kconfig | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index 2b0172f54665..55ae888bf26a 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -55,6 +55,26 @@ config VFIO_PCI_ZDEV_KVM To enable s390x KVM vfio-pci extensions, say Y. +config VFIO_PCI_DMABUF + bool "VFIO PCI extensions for DMA-BUF" + depends on VFIO_PCI_CORE + depends on PCI_P2PDMA && DMA_SHARED_BUFFER + default y + help + Enable support for VFIO PCI extensions that allow exporting + device MMIO regions as DMA-BUFs for peer devices to access via + peer-to-peer (P2P) DMA. + + This feature enables a VFIO-managed PCI device to export a portion + of its MMIO BAR as a DMA-BUF file descriptor, which can be passed + to other userspace drivers or kernel subsystems capable of + initiating DMA to that region. + + Say Y here if you want to enable VFIO DMABUF-based MMIO export + support for peer-to-peer DMA use cases. + + If unsure, say N. + source "drivers/vfio/pci/mlx5/Kconfig" source "drivers/vfio/pci/hisilicon/Kconfig" -- 2.51.0 From: Leon Romanovsky Make sure that all VFIO PCI devices have peer-to-peer capabilities enables, so we would be able to export their MMIO memory through DMABUF, Signed-off-by: Leon Romanovsky --- drivers/vfio/pci/vfio_pci_core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 7dcf5439dedc..608af135308e 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -28,6 +28,9 @@ #include #include #include +#ifdef CONFIG_VFIO_PCI_DMABUF +#include +#endif #if IS_ENABLED(CONFIG_EEH) #include #endif @@ -2085,6 +2088,7 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev) { struct vfio_pci_core_device *vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev); + int __maybe_unused ret; vdev->pdev = to_pci_dev(core_vdev->dev); vdev->irq_type = VFIO_PCI_NUM_IRQS; @@ -2094,6 +2098,11 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev) INIT_LIST_HEAD(&vdev->dummy_resources_list); INIT_LIST_HEAD(&vdev->ioeventfds_list); INIT_LIST_HEAD(&vdev->sriov_pfs_item); +#ifdef CONFIG_VFIO_PCI_DMABUF + ret = pcim_p2pdma_init(vdev->pdev); + if (ret) + return ret; +#endif init_rwsem(&vdev->memory_lock); xa_init(&vdev->ctx); -- 2.51.0 From: Vivek Kasireddy There is no need to share the main device pointer (struct vfio_device *) with all the feature functions as they only need the core device pointer. Therefore, extract the core device pointer once in the caller (vfio_pci_core_ioctl_feature) and share it instead. Signed-off-by: Vivek Kasireddy Signed-off-by: Leon Romanovsky --- drivers/vfio/pci/vfio_pci_core.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 608af135308e..0c39368280d7 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -302,11 +302,9 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev, return 0; } -static int vfio_pci_core_pm_entry(struct vfio_device *device, u32 flags, +static int vfio_pci_core_pm_entry(struct vfio_pci_core_device *vdev, u32 flags, void __user *arg, size_t argsz) { - struct vfio_pci_core_device *vdev = - container_of(device, struct vfio_pci_core_device, vdev); int ret; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); @@ -323,12 +321,10 @@ static int vfio_pci_core_pm_entry(struct vfio_device *device, u32 flags, } static int vfio_pci_core_pm_entry_with_wakeup( - struct vfio_device *device, u32 flags, + struct vfio_pci_core_device *vdev, u32 flags, struct vfio_device_low_power_entry_with_wakeup __user *arg, size_t argsz) { - struct vfio_pci_core_device *vdev = - container_of(device, struct vfio_pci_core_device, vdev); struct vfio_device_low_power_entry_with_wakeup entry; struct eventfd_ctx *efdctx; int ret; @@ -379,11 +375,9 @@ static void vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev) up_write(&vdev->memory_lock); } -static int vfio_pci_core_pm_exit(struct vfio_device *device, u32 flags, +static int vfio_pci_core_pm_exit(struct vfio_pci_core_device *vdev, u32 flags, void __user *arg, size_t argsz) { - struct vfio_pci_core_device *vdev = - container_of(device, struct vfio_pci_core_device, vdev); int ret; ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); @@ -1476,11 +1470,10 @@ long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, } EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl); -static int vfio_pci_core_feature_token(struct vfio_device *device, u32 flags, - uuid_t __user *arg, size_t argsz) +static int vfio_pci_core_feature_token(struct vfio_pci_core_device *vdev, + u32 flags, uuid_t __user *arg, + size_t argsz) { - struct vfio_pci_core_device *vdev = - container_of(device, struct vfio_pci_core_device, vdev); uuid_t uuid; int ret; @@ -1507,16 +1500,19 @@ static int vfio_pci_core_feature_token(struct vfio_device *device, u32 flags, int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) { + struct vfio_pci_core_device *vdev = + container_of(device, struct vfio_pci_core_device, vdev); + switch (flags & VFIO_DEVICE_FEATURE_MASK) { case VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY: - return vfio_pci_core_pm_entry(device, flags, arg, argsz); + return vfio_pci_core_pm_entry(vdev, flags, arg, argsz); case VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP: - return vfio_pci_core_pm_entry_with_wakeup(device, flags, + return vfio_pci_core_pm_entry_with_wakeup(vdev, flags, arg, argsz); case VFIO_DEVICE_FEATURE_LOW_POWER_EXIT: - return vfio_pci_core_pm_exit(device, flags, arg, argsz); + return vfio_pci_core_pm_exit(vdev, flags, arg, argsz); case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN: - return vfio_pci_core_feature_token(device, flags, arg, argsz); + return vfio_pci_core_feature_token(vdev, flags, arg, argsz); default: return -ENOTTY; } -- 2.51.0 From: Leon Romanovsky Add support for exporting PCI device MMIO regions through dma-buf, enabling safe sharing of non-struct page memory with controlled lifetime management. This allows RDMA and other subsystems to import dma-buf FDs and build them into memory regions for PCI P2P operations. The implementation provides a revocable attachment mechanism using dma-buf move operations. MMIO regions are normally pinned as BARs don't change physical addresses, but access is revoked when the VFIO device is closed or a PCI reset is issued. This ensures kernel self-defense against potentially hostile userspace. Signed-off-by: Jason Gunthorpe Signed-off-by: Vivek Kasireddy Signed-off-by: Leon Romanovsky --- drivers/vfio/pci/Makefile | 2 + drivers/vfio/pci/vfio_pci_config.c | 22 +- drivers/vfio/pci/vfio_pci_core.c | 17 ++ drivers/vfio/pci/vfio_pci_dmabuf.c | 398 +++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_priv.h | 23 ++ include/linux/vfio_pci_core.h | 3 + include/uapi/linux/vfio.h | 25 ++ 7 files changed, 486 insertions(+), 4 deletions(-) create mode 100644 drivers/vfio/pci/vfio_pci_dmabuf.c diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index cf00c0a7e55c..f9155e9c5f63 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -2,7 +2,9 @@ vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o + obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o +vfio-pci-core-$(CONFIG_VFIO_PCI_DMABUF) += vfio_pci_dmabuf.o vfio-pci-y := vfio_pci.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 8f02f236b5b4..1f6008eabf23 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -589,10 +589,12 @@ 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) + if (!new_mem) { vfio_pci_zap_and_down_write_memory_lock(vdev); - else + 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 @@ -627,6 +629,8 @@ static int vfio_basic_config_write(struct vfio_pci_core_device *vdev, int pos, *virt_cmd &= cpu_to_le16(~mask); *virt_cmd |= cpu_to_le16(new_cmd & mask); + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); up_write(&vdev->memory_lock); } @@ -707,12 +711,16 @@ 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) + if (state >= PCI_D3hot) { vfio_pci_zap_and_down_write_memory_lock(vdev); - else + 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)) + vfio_pci_dma_buf_move(vdev, false); up_write(&vdev->memory_lock); } @@ -900,7 +908,10 @@ static int vfio_exp_config_write(struct vfio_pci_core_device *vdev, int pos, if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) { vfio_pci_zap_and_down_write_memory_lock(vdev); + vfio_pci_dma_buf_move(vdev, true); pci_try_reset_function(vdev->pdev); + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); up_write(&vdev->memory_lock); } } @@ -982,7 +993,10 @@ static int vfio_af_config_write(struct vfio_pci_core_device *vdev, int pos, if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) { vfio_pci_zap_and_down_write_memory_lock(vdev); + vfio_pci_dma_buf_move(vdev, true); pci_try_reset_function(vdev->pdev); + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); up_write(&vdev->memory_lock); } } diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 0c39368280d7..aa88c42db69b 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -289,6 +289,8 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev, * semaphore. */ vfio_pci_zap_and_down_write_memory_lock(vdev); + vfio_pci_dma_buf_move(vdev, true); + if (vdev->pm_runtime_engaged) { up_write(&vdev->memory_lock); return -EINVAL; @@ -372,6 +374,8 @@ static void vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev) */ down_write(&vdev->memory_lock); __vfio_pci_runtime_pm_exit(vdev); + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); up_write(&vdev->memory_lock); } @@ -692,6 +696,8 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev) #endif vfio_pci_core_disable(vdev); + vfio_pci_dma_buf_cleanup(vdev); + mutex_lock(&vdev->igate); if (vdev->err_trigger) { eventfd_ctx_put(vdev->err_trigger); @@ -1224,7 +1230,10 @@ static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev, */ vfio_pci_set_power_state(vdev, PCI_D0); + vfio_pci_dma_buf_move(vdev, true); ret = pci_try_reset_function(vdev->pdev); + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); up_write(&vdev->memory_lock); return ret; @@ -1513,6 +1522,8 @@ int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, return vfio_pci_core_pm_exit(vdev, flags, arg, argsz); case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN: return vfio_pci_core_feature_token(vdev, flags, arg, argsz); + case VFIO_DEVICE_FEATURE_DMA_BUF: + return vfio_pci_core_feature_dma_buf(vdev, flags, arg, argsz); default: return -ENOTTY; } @@ -2098,6 +2109,7 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev) ret = pcim_p2pdma_init(vdev->pdev); if (ret) return ret; + INIT_LIST_HEAD(&vdev->dmabufs); #endif init_rwsem(&vdev->memory_lock); xa_init(&vdev->ctx); @@ -2463,6 +2475,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, break; } + vfio_pci_dma_buf_move(vdev, true); vfio_pci_zap_bars(vdev); } @@ -2486,6 +2499,10 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, ret = pci_reset_bus(pdev); + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); + vdev = list_last_entry(&dev_set->device_list, struct vfio_pci_core_device, vdev.dev_set_list); diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c new file mode 100644 index 000000000000..838619f812aa --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c @@ -0,0 +1,398 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. + */ +#include +#include +#include + +#include "vfio_pci_priv.h" + +MODULE_IMPORT_NS("DMA_BUF"); + +struct vfio_pci_dma_buf { + struct dma_buf *dmabuf; + struct vfio_pci_core_device *vdev; + struct list_head dmabufs_elm; + size_t size; + struct phys_vec *phys_vec; + struct p2pdma_provider *provider; + u32 nr_ranges; + u8 revoked : 1; +}; + +static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct vfio_pci_dma_buf *priv = dmabuf->priv; + + if (!attachment->peer2peer) + return -EOPNOTSUPP; + + if (priv->revoked) + return -ENODEV; + + switch (pci_p2pdma_map_type(priv->provider, attachment->dev)) { + case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: + break; + case PCI_P2PDMA_MAP_BUS_ADDR: + /* + * There is no need in IOVA at all for this flow. + * We rely on attachment->priv == NULL as a marker + * for this mode. + */ + return 0; + default: + return -EINVAL; + } + + attachment->priv = kzalloc(sizeof(struct dma_iova_state), GFP_KERNEL); + if (!attachment->priv) + return -ENOMEM; + + dma_iova_try_alloc(attachment->dev, attachment->priv, 0, priv->size); + return 0; +} + +static void vfio_pci_dma_buf_detach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + kfree(attachment->priv); +} + +static void fill_sg_entry(struct scatterlist *sgl, unsigned int length, + dma_addr_t addr) +{ + /* + * Follow the DMABUF rules for scatterlist, the struct page can be + * NULL'd for MMIO only memort. + */ + sg_set_page(sgl, NULL, length, 0); + sg_dma_address(sgl) = addr; + sg_dma_len(sgl) = length; +} + +static struct sg_table * +vfio_pci_dma_buf_map(struct dma_buf_attachment *attachment, + enum dma_data_direction dir) +{ + struct vfio_pci_dma_buf *priv = attachment->dmabuf->priv; + struct dma_iova_state *state = attachment->priv; + struct phys_vec *phys_vec = priv->phys_vec; + unsigned long attrs = DMA_ATTR_MMIO; + unsigned int mapped_len = 0; + struct scatterlist *sgl; + struct sg_table *sgt; + dma_addr_t addr; + int ret, i; + + dma_resv_assert_held(priv->dmabuf->resv); + + if (priv->revoked) + return ERR_PTR(-ENODEV); + + sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); + if (!sgt) + return ERR_PTR(-ENOMEM); + + ret = sg_alloc_table(sgt, 1, GFP_KERNEL | __GFP_ZERO); + if (ret) + goto err_kfree_sgt; + + sgl = sgt->sgl; + + for (i = 0; i < priv->nr_ranges; i++) { + if (!state) { + addr = pci_p2pdma_bus_addr_map(priv->provider, + phys_vec[i].paddr); + } else if (dma_use_iova(state)) { + ret = dma_iova_link(attachment->dev, state, + phys_vec[i].paddr, 0, + phys_vec[i].len, dir, attrs); + if (ret) + goto err_unmap_dma; + + mapped_len += phys_vec[i].len; + } else { + addr = dma_map_phys(attachment->dev, phys_vec[i].paddr, + phys_vec[i].len, dir, attrs); + ret = dma_mapping_error(attachment->dev, addr); + if (ret) + goto err_unmap_dma; + } + + if (!state || !dma_use_iova(state)) { + /* + * In IOVA case, there is only one SG entry which spans + * for whole IOVA address space. So there is no need + * to call to sg_next() here. + */ + fill_sg_entry(sgl, phys_vec[i].len, addr); + sgl = sg_next(sgl); + } + } + + if (state && dma_use_iova(state)) { + WARN_ON_ONCE(mapped_len != priv->size); + ret = dma_iova_sync(attachment->dev, state, 0, mapped_len); + if (ret) + goto err_unmap_dma; + fill_sg_entry(sgl, mapped_len, state->addr); + } + + return sgt; + +err_unmap_dma: + if (!i || !state) + ; /* Do nothing */ + else if (dma_use_iova(state)) + dma_iova_destroy(attachment->dev, state, mapped_len, dir, + attrs); + else + for_each_sgtable_dma_sg(sgt, sgl, i) + dma_unmap_phys(attachment->dev, sg_dma_address(sgl), + sg_dma_len(sgl), dir, attrs); + sg_free_table(sgt); +err_kfree_sgt: + kfree(sgt); + return ERR_PTR(ret); +} + +static void vfio_pci_dma_buf_unmap(struct dma_buf_attachment *attachment, + struct sg_table *sgt, + enum dma_data_direction dir) +{ + struct vfio_pci_dma_buf *priv = attachment->dmabuf->priv; + struct dma_iova_state *state = attachment->priv; + unsigned long attrs = DMA_ATTR_MMIO; + struct scatterlist *sgl; + int i; + + if (!state) + ; /* Do nothing */ + else if (dma_use_iova(state)) + dma_iova_destroy(attachment->dev, state, priv->size, dir, + attrs); + else + for_each_sgtable_dma_sg(sgt, sgl, i) + dma_unmap_phys(attachment->dev, sg_dma_address(sgl), + sg_dma_len(sgl), dir, attrs); + + sg_free_table(sgt); + kfree(sgt); +} + +static void vfio_pci_dma_buf_release(struct dma_buf *dmabuf) +{ + struct vfio_pci_dma_buf *priv = dmabuf->priv; + + /* + * Either this or vfio_pci_dma_buf_cleanup() will remove from the list. + * The refcount prevents both. + */ + if (priv->vdev) { + down_write(&priv->vdev->memory_lock); + list_del_init(&priv->dmabufs_elm); + up_write(&priv->vdev->memory_lock); + vfio_device_put_registration(&priv->vdev->vdev); + } + kfree(priv->phys_vec); + kfree(priv); +} + +static const struct dma_buf_ops vfio_pci_dmabuf_ops = { + .attach = vfio_pci_dma_buf_attach, + .detach = vfio_pci_dma_buf_detach, + .map_dma_buf = vfio_pci_dma_buf_map, + .release = vfio_pci_dma_buf_release, + .unmap_dma_buf = vfio_pci_dma_buf_unmap, +}; + +static void dma_ranges_to_p2p_phys(struct vfio_pci_dma_buf *priv, + struct vfio_device_feature_dma_buf *dma_buf, + struct vfio_region_dma_range *dma_ranges, + struct p2pdma_provider *provider) +{ + struct pci_dev *pdev = priv->vdev->pdev; + phys_addr_t pci_start; + int i; + + pci_start = pci_resource_start(pdev, dma_buf->region_index); + for (i = 0; i < dma_buf->nr_ranges; i++) { + priv->phys_vec[i].len = dma_ranges[i].length; + priv->phys_vec[i].paddr = pci_start + dma_ranges[i].offset; + priv->size += priv->phys_vec[i].len; + } + priv->nr_ranges = dma_buf->nr_ranges; + priv->provider = provider; +} + +static int validate_dmabuf_input(struct vfio_pci_core_device *vdev, + struct vfio_device_feature_dma_buf *dma_buf, + struct vfio_region_dma_range *dma_ranges, + struct p2pdma_provider **provider) +{ + struct pci_dev *pdev = vdev->pdev; + u32 bar = dma_buf->region_index; + resource_size_t bar_size; + u64 sum; + int i; + + if (dma_buf->flags) + return -EINVAL; + /* + * For PCI the region_index is the BAR number like everything else. + */ + if (bar >= VFIO_PCI_ROM_REGION_INDEX) + return -ENODEV; + + *provider = pcim_p2pdma_provider(pdev, bar); + if (!provider) + return -EINVAL; + + bar_size = pci_resource_len(pdev, bar); + for (i = 0; i < dma_buf->nr_ranges; i++) { + u64 offset = dma_ranges[i].offset; + u64 len = dma_ranges[i].length; + + if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len)) + return -EINVAL; + + if (check_add_overflow(offset, len, &sum) || sum > bar_size) + return -EINVAL; + } + + return 0; +} + +int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags, + struct vfio_device_feature_dma_buf __user *arg, + size_t argsz) +{ + struct vfio_device_feature_dma_buf get_dma_buf = {}; + struct vfio_region_dma_range *dma_ranges; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + struct p2pdma_provider *provider; + struct vfio_pci_dma_buf *priv; + int ret; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET, + sizeof(get_dma_buf)); + if (ret != 1) + return ret; + + if (copy_from_user(&get_dma_buf, arg, sizeof(get_dma_buf))) + return -EFAULT; + + if (!get_dma_buf.nr_ranges) + return -EINVAL; + + dma_ranges = memdup_array_user(&arg->dma_ranges, get_dma_buf.nr_ranges, + sizeof(*dma_ranges)); + if (IS_ERR(dma_ranges)) + return PTR_ERR(dma_ranges); + + ret = validate_dmabuf_input(vdev, &get_dma_buf, dma_ranges, &provider); + if (ret) + return ret; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + ret = -ENOMEM; + goto err_free_ranges; + } + priv->phys_vec = kcalloc(get_dma_buf.nr_ranges, sizeof(*priv->phys_vec), + GFP_KERNEL); + if (!priv->phys_vec) { + ret = -ENOMEM; + goto err_free_priv; + } + + priv->vdev = vdev; + dma_ranges_to_p2p_phys(priv, &get_dma_buf, dma_ranges, provider); + kfree(dma_ranges); + dma_ranges = NULL; + + if (!vfio_device_try_get_registration(&vdev->vdev)) { + ret = -ENODEV; + goto err_free_phys; + } + + exp_info.ops = &vfio_pci_dmabuf_ops; + exp_info.size = priv->size; + exp_info.flags = get_dma_buf.open_flags; + exp_info.priv = priv; + + priv->dmabuf = dma_buf_export(&exp_info); + if (IS_ERR(priv->dmabuf)) { + ret = PTR_ERR(priv->dmabuf); + goto err_dev_put; + } + + /* dma_buf_put() now frees priv */ + INIT_LIST_HEAD(&priv->dmabufs_elm); + down_write(&vdev->memory_lock); + dma_resv_lock(priv->dmabuf->resv, NULL); + priv->revoked = !__vfio_pci_memory_enabled(vdev); + list_add_tail(&priv->dmabufs_elm, &vdev->dmabufs); + dma_resv_unlock(priv->dmabuf->resv); + up_write(&vdev->memory_lock); + + /* + * dma_buf_fd() consumes the reference, when the file closes the dmabuf + * will be released. + */ + return dma_buf_fd(priv->dmabuf, get_dma_buf.open_flags); + +err_dev_put: + vfio_device_put_registration(&vdev->vdev); +err_free_phys: + kfree(priv->phys_vec); +err_free_priv: + kfree(priv); +err_free_ranges: + kfree(dma_ranges); + return ret; +} + +void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked) +{ + struct vfio_pci_dma_buf *priv; + struct vfio_pci_dma_buf *tmp; + + lockdep_assert_held_write(&vdev->memory_lock); + + list_for_each_entry_safe(priv, tmp, &vdev->dmabufs, dmabufs_elm) { + if (!get_file_active(&priv->dmabuf->file)) + continue; + + if (priv->revoked != revoked) { + dma_resv_lock(priv->dmabuf->resv, NULL); + priv->revoked = revoked; + dma_buf_move_notify(priv->dmabuf); + dma_resv_unlock(priv->dmabuf->resv); + } + dma_buf_put(priv->dmabuf); + } +} + +void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev) +{ + struct vfio_pci_dma_buf *priv; + struct vfio_pci_dma_buf *tmp; + + down_write(&vdev->memory_lock); + list_for_each_entry_safe(priv, tmp, &vdev->dmabufs, dmabufs_elm) { + if (!get_file_active(&priv->dmabuf->file)) + continue; + + dma_resv_lock(priv->dmabuf->resv, NULL); + list_del_init(&priv->dmabufs_elm); + priv->vdev = NULL; + priv->revoked = true; + dma_buf_move_notify(priv->dmabuf); + dma_resv_unlock(priv->dmabuf->resv); + vfio_device_put_registration(&vdev->vdev); + dma_buf_put(priv->dmabuf); + } + up_write(&vdev->memory_lock); +} diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h index a9972eacb293..28a405f8b97c 100644 --- a/drivers/vfio/pci/vfio_pci_priv.h +++ b/drivers/vfio/pci/vfio_pci_priv.h @@ -107,4 +107,27 @@ static inline bool vfio_pci_is_vga(struct pci_dev *pdev) return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA; } +#ifdef CONFIG_VFIO_PCI_DMABUF +int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags, + struct vfio_device_feature_dma_buf __user *arg, + size_t argsz); +void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev); +void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked); +#else +static inline int +vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags, + struct vfio_device_feature_dma_buf __user *arg, + size_t argsz) +{ + return -ENOTTY; +} +static inline void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev) +{ +} +static inline void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, + bool revoked) +{ +} +#endif + #endif diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index f541044e42a2..68afa18630d4 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -94,6 +94,9 @@ struct vfio_pci_core_device { struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct rw_semaphore memory_lock; +#ifdef CONFIG_VFIO_PCI_DMABUF + struct list_head dmabufs; +#endif }; /* Will be exported for vfio pci drivers usage */ diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 75100bf009ba..63214467c875 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1478,6 +1478,31 @@ struct vfio_device_feature_bus_master { }; #define VFIO_DEVICE_FEATURE_BUS_MASTER 10 +/** + * Upon VFIO_DEVICE_FEATURE_GET create a dma_buf fd for the + * regions selected. + * + * open_flags are the typical flags passed to open(2), eg O_RDWR, O_CLOEXEC, + * etc. offset/length specify a slice of the region to create the dmabuf from. + * nr_ranges is the total number of (P2P DMA) ranges that comprise the dmabuf. + * + * Return: The fd number on success, -1 and errno is set on failure. + */ +#define VFIO_DEVICE_FEATURE_DMA_BUF 11 + +struct vfio_region_dma_range { + __u64 offset; + __u64 length; +}; + +struct vfio_device_feature_dma_buf { + __u32 region_index; + __u32 open_flags; + __u32 flags; + __u32 nr_ranges; + struct vfio_region_dma_range dma_ranges[]; +}; + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- 2.51.0