From: Leon Romanovsky leonro@nvidia.com

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 jgg@nvidia.com Signed-off-by: Leon Romanovsky leonro@nvidia.com --- 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 78e108e47254..59cd6fb40e83 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;

@@ -972,16 +971,16 @@ 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)) @@ -990,7 +989,7 @@ 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, @@ -998,7 +997,7 @@ 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; } @@ -1006,9 +1005,13 @@ 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 951f81a38f3a..1400f3ad4299 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); @@ -139,11 +149,11 @@ 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); @@ -162,8 +172,7 @@ 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; @@ -181,7 +190,7 @@ 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 */

From: Leon Romanovsky leonro@nvidia.com

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 leonro@nvidia.com --- drivers/pci/p2pdma.c | 139 ++++++++++++++++++++++++++++--------- include/linux/pci-p2pdma.h | 11 +++ 2 files changed, 119 insertions(+), 31 deletions(-)

diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 59cd6fb40e83..a2ec7e93fd71 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)) { @@ -1007,11 +1084,11 @@ 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 9516ef97b17a..e307c9380d46 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, @@ -44,6 +46,15 @@ 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) {

From: Leon Romanovsky leonro@nvidia.com

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 leonro@nvidia.com --- 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 badef1d925b2..38f5c34ca223 100644 --- a/block/blk-mq-dma.c +++ b/block/blk-mq-dma.c @@ -6,11 +6,6 @@ #include <linux/blk-mq-dma.h> #include "blk.h"

-struct phys_vec { - phys_addr_t paddr; - u32 len; -}; - static bool __blk_map_iter_next(struct blk_map_iter *iter) { if (iter->iter.bi_size) 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;

/*

From: Vivek Kasireddy vivek.kasireddy@intel.com

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 vivek.kasireddy@intel.com Signed-off-by: Leon Romanovsky leonro@nvidia.com --- 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 7dcf5439dedc..ca9a95716a85 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -299,11 +299,9 @@ 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); @@ -320,12 +318,10 @@ 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; @@ -376,11 +372,9 @@ 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); @@ -1473,11 +1467,10 @@ 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;

@@ -1504,16 +1497,19 @@ 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; }

From: Leon Romanovsky leonro@nvidia.com

Add support for exporting PCI device MMIO regions through dma-buf, enabling safe sharing of non-struct page memory with controlled lifetime management. This allows RDMA and other subsystems to import dma-buf FDs and build them into memory regions for PCI P2P operations.

The implementation provides a revocable attachment mechanism using dma-buf move operations. MMIO regions are normally pinned as BARs don't change physical addresses, but access is revoked when the VFIO device is closed or a PCI reset is issued. This ensures kernel self-defense against potentially hostile userspace.

Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Vivek Kasireddy vivek.kasireddy@intel.com Signed-off-by: Leon Romanovsky leonro@nvidia.com --- drivers/vfio/pci/Kconfig | 3 + drivers/vfio/pci/Makefile | 2 + drivers/vfio/pci/vfio_pci_config.c | 22 +- drivers/vfio/pci/vfio_pci_core.c | 28 ++ drivers/vfio/pci/vfio_pci_dmabuf.c | 446 +++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_priv.h | 23 ++ include/linux/vfio_pci_core.h | 1 + include/uapi/linux/vfio.h | 25 ++ 8 files changed, 546 insertions(+), 4 deletions(-) create mode 100644 drivers/vfio/pci/vfio_pci_dmabuf.c

diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index 2b0172f54665..2b9fca00e9e8 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -55,6 +55,9 @@ config VFIO_PCI_ZDEV_KVM

To enable s390x KVM vfio-pci extensions, say Y.

+config VFIO_PCI_DMABUF + def_bool y if VFIO_PCI_CORE && PCI_P2PDMA && DMA_SHARED_BUFFER + source "drivers/vfio/pci/mlx5/Kconfig"

source "drivers/vfio/pci/hisilicon/Kconfig" 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 fe247d0e2831..56b1320238a9 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -287,6 +287,8 @@ 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; @@ -370,6 +372,8 @@ 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); }

@@ -690,6 +694,8 @@ 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); @@ -1222,7 +1228,10 @@ 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; @@ -1511,6 +1520,19 @@ 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: + if (device->ops->ioctl != vfio_pci_core_ioctl) + /* + * Devices that overwrite general .ioctl() callback + * usually do it to implement their own + * VFIO_DEVICE_GET_REGION_INFO handlerm and they present + * different BAR information from the real PCI. + * + * DMABUF relies on real PCI information. + */ + return -EOPNOTSUPP; + + return vfio_pci_core_feature_dma_buf(vdev, flags, arg, argsz); default: return -ENOTTY; } @@ -2095,6 +2117,7 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev) ret = pcim_p2pdma_init(vdev->pdev); if (ret != -EOPNOTSUPP) return ret; + INIT_LIST_HEAD(&vdev->dmabufs); init_rwsem(&vdev->memory_lock); xa_init(&vdev->ctx);

@@ -2459,6 +2482,7 @@ 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); }

@@ -2482,6 +2506,10 @@ 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..eaba010777f3 --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c @@ -0,0 +1,446 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. + */ +#include <linux/dma-buf.h> +#include <linux/pci-p2pdma.h> +#include <linux/dma-resv.h> + +#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 struct scatterlist *fill_sg_entry(struct scatterlist *sgl, u64 length, + dma_addr_t addr) +{ + unsigned int len, nents; + int i; + + nents = DIV_ROUND_UP(length, UINT_MAX); + for (i = 0; i < nents; i++) { + len = min_t(u64, length, UINT_MAX); + length -= len; + /* + * Follow the DMABUF rules for scatterlist, the struct page can + * be NULL'd for MMIO only memory. + */ + sg_set_page(sgl, NULL, len, 0); + sg_dma_address(sgl) = addr + i * UINT_MAX; + sg_dma_len(sgl) = len; + sgl = sg_next(sgl); + } + + return sgl; +} + +static unsigned int calc_sg_nents(struct vfio_pci_dma_buf *priv, + struct dma_iova_state *state) +{ + struct phys_vec *phys_vec = priv->phys_vec; + unsigned int nents = 0; + u32 i; + + if (!state || !dma_use_iova(state)) + for (i = 0; i < priv->nr_ranges; i++) + nents += DIV_ROUND_UP(phys_vec[i].len, UINT_MAX); + else + /* + * In IOVA case, there is only one SG entry which spans + * for whole IOVA address space, but we need to make sure + * that it fits sg->length, maybe we need more. + */ + nents = DIV_ROUND_UP(priv->size, UINT_MAX); + + return nents; +} + +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 nents, mapped_len = 0; + struct scatterlist *sgl; + struct sg_table *sgt; + dma_addr_t addr; + int ret; + u32 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); + + nents = calc_sg_nents(priv, state); + ret = sg_alloc_table(sgt, nents, 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)) + sgl = fill_sg_entry(sgl, phys_vec[i].len, addr); + } + + 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; + sgl = fill_sg_entry(sgl, mapped_len, state->addr); + } + + /* + * SGL must be NULL to indicate that SGL is the last one + * and we allocated correct number of entries in sg_alloc_table() + */ + WARN_ON_ONCE(sgl); + 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; + u32 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 length = 0, sum; + u32 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 (!len || !PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len)) + return -EINVAL; + + if (check_add_overflow(offset, len, &sum) || sum > bar_size) + return -EINVAL; + + /* Total requested length can't overflow IOVA size */ + if (check_add_overflow(length, len, &sum)) + return -EINVAL; + + length = sum; + } + + /* + * DMA API uses size_t, so make sure that requested region length + * can fit into size_t variable, which can be unsigned int (32bits). + * + * In addition make sure that high bit of total length is not used too + * as it is used as a marker for DMA IOVA API. + */ + if (overflows_type(length, size_t) || length & DMA_IOVA_USE_SWIOTLB) + 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) + goto err_free_ranges; + + 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..30d74b364f25 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -94,6 +94,7 @@ struct vfio_pci_core_device { struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct rw_semaphore memory_lock; + struct list_head dmabufs; };

/* 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 -------- */

/**