vfio/pci: Allow MMIO regions to be exported through dma-buf

---
 drivers/pci/p2pdma.c       | 1 -
 include/linux/pci-p2pdma.h | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

drivers/pci/p2pdma.c +0 -1

index da5657a020074..274bb7bcc0bc5 100644
@@ -1009,7 +1009,6 @@ void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state,
 {
 	state->pgmap = page_pgmap(page);
 	state->map = pci_p2pdma_map_type(state->pgmap, dev);
-	state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
 }
 
 /**

include/linux/pci-p2pdma.h +1 -2

index 075c20b161d98..b502fc8b49bf9 100644
@@ -146,7 +146,6 @@ enum pci_p2pdma_map_type {
 struct pci_p2pdma_map_state {
 	struct dev_pagemap *pgmap;
 	enum pci_p2pdma_map_type map;
-	u64 bus_off;
 };
 
 /* helper for pci_p2pdma_state(), do not use directly */

@@ -186,7 +185,7 @@ 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 + to_p2p_pgmap(state->pgmap)->bus_offsetf;
 }
 
 #endif /* _LINUX_PCI_P2P_H */

Signature · 1 line

2.50.1

Alex Williamson

2025-08-06 20:58 UTC #2 lore raw

Re: [PATCH v1 01/10] PCI/P2PDMA: Remove redundant bus_offset from map state

Quoted 40 lines · On Mon, 4 Aug 2025 16:00:36 +0300 Leon Romanovsky <[email protected]> wrote:

From: Leon Romanovsky <[email protected]>
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.
Reviewed-by Christoph Hellwig <[email protected]>
Signed-off-by Jason Gunthorpe <[email protected]>
Signed-off-by Leon Romanovsky <[email protected]>
---
 drivers/pci/p2pdma.c       | 1 -
 include/linux/pci-p2pdma.h | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)
drivers/pci/p2pdma.c +0 -1
index da5657a020074..274bb7bcc0bc5 100644
@@ -1009,7 +1009,6 @@ void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state,
 {
 	state->pgmap = page_pgmap(page);
 	state->map = pci_p2pdma_map_type(state->pgmap, dev);
-	state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
 }
 
 /**
include/linux/pci-p2pdma.h +0 -1
index 075c20b161d98..b502fc8b49bf9 100644
@@ -146,7 +146,6 @@ enum pci_p2pdma_map_type {
 struct pci_p2pdma_map_state {
 	struct dev_pagemap *pgmap;
 	enum pci_p2pdma_map_type map;
-	u64 bus_off;
 };
 
 /* helper for pci_p2pdma_state(), do not use directly */

include/linux/pci-p2pdma.h static inline dma_addr_t · line 191

Quoted 8 lines

include/linux/pci-p2pdma.h +1 -1

@@ -186,7 +185,7 @@ 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 + to_p2p_pgmap(state->pgmap)->bus_offsetf;
 }
 
 #endif /* _LINUX_PCI_P2P_H */

Looks like you're relying on this bogus code getting resolved in the next patch...

In file included from kernel/dma/direct.c:16:
./include/linux/pci-p2pdma.h: In function ‘pci_p2pdma_bus_addr_map’:
./include/linux/pci-p2pdma.h:188:24: error: implicit declaration of function ‘to_p2p_pgmap’ [-Wimplicit-function-declaration]

  188 |         return paddr + to_p2p_pgmap(state->pgmap)->bus_offsetf;
      |                        ^~~~~~~~~~~~

./include/linux/pci-p2pdma.h:188:50: error: invalid type argument of ‘->’ (have ‘int’)
188 | return paddr + to_p2p_pgmap(state->pgmap)->bus_offsetf;
| ^~
./include/linux/pci-p2pdma.h:189:1: error: control reaches end of non-void function [-Werror=return-type]
189 | }

| ^

to_p2p_pgmap() is a static function and struct pci_p2pdma_pagemap doesn't have a bus_offsetf member. Thanks,

Alex

Leon Romanovsky

author

2025-09-02 11:06 UTC #3 lore raw

Re: [PATCH v1 01/10] PCI/P2PDMA: Remove redundant bus_offset from map state

Quoted 50 lines · Alex Williamson

Quoted 47 lines · On Mon, 4 Aug 2025 16:00:36 +0300 Leon Romanovsky <[email protected]> wrote:
From: Leon Romanovsky <[email protected]>
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.
Reviewed-by Christoph Hellwig <[email protected]>
Signed-off-by Jason Gunthorpe <[email protected]>
Signed-off-by Leon Romanovsky <[email protected]>
---
 drivers/pci/p2pdma.c       | 1 -
 include/linux/pci-p2pdma.h | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)
drivers/pci/p2pdma.c +0 -1
index da5657a020074..274bb7bcc0bc5 100644
@@ -1009,7 +1009,6 @@ void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state,
 {
 	state->pgmap = page_pgmap(page);
 	state->map = pci_p2pdma_map_type(state->pgmap, dev);
-	state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset;
 }
 
 /**
include/linux/pci-p2pdma.h +1 -2
index 075c20b161d98..b502fc8b49bf9 100644
@@ -146,7 +146,6 @@ enum pci_p2pdma_map_type {
 struct pci_p2pdma_map_state {
 	struct dev_pagemap *pgmap;
 	enum pci_p2pdma_map_type map;
-	u64 bus_off;
 };
 
 /* helper for pci_p2pdma_state(), do not use directly */
@@ -186,7 +185,7 @@ 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 + to_p2p_pgmap(state->pgmap)->bus_offsetf;
 }
 

Quoted 1 line

include/linux/pci-p2pdma.h static inline dma_addr_t · line 191
Quoted 1 line
include/linux/pci-p2pdma.h +0 -0
 #endif /* _LINUX_PCI_P2P_H */

Sorry for long time to reply, I waited to see what is going on with DMA phys_vec basic series and together with my summer vacation, it took a while.

Quoted 14 lines

Looks like you're relying on this bogus code getting resolved in the next patch...
In file included from kernel/dma/direct.c:16:
./include/linux/pci-p2pdma.h: In function ‘pci_p2pdma_bus_addr_map’:
./include/linux/pci-p2pdma.h:188:24: error: implicit declaration of function ‘to_p2p_pgmap’ [-Wimplicit-function-declaration]
  188 |         return paddr + to_p2p_pgmap(state->pgmap)->bus_offsetf;
      |                        ^~~~~~~~~~~~
./include/linux/pci-p2pdma.h:188:50: error: invalid type argument of ‘->’ (have ‘int’)
188 | return paddr + to_p2p_pgmap(state->pgmap)->bus_offsetf;
| ^~
./include/linux/pci-p2pdma.h:189:1: error: control reaches end of non-void function [-Werror=return-type]
189 | }

Quoted 4 lines

      | ^
to_p2p_pgmap() is a static function and struct pci_p2pdma_pagemap doesn't have a bus_offsetf member. Thanks,

You are right, probably the best way to fix the error is simply squash this change into the next patch.

Thanks

Quoted 3 lines

Alex

Leon Romanovsky

author

2025-08-04 13:01 UTC #4 lore raw

PATCH 2/10 PCI/P2PDMA: Separate the mmap() support from the core logic

From: Leon Romanovsky <[email protected]>

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.

---
 drivers/pci/p2pdma.c       | 42 +++++++++++++++++++++-----------------
 include/linux/pci-p2pdma.h | 18 ++++++++++++----
 2 files changed, 37 insertions(+), 23 deletions(-)

drivers/pci/p2pdma.c +23 ~~-19~~

index 274bb7bcc0bc5..176a99232fdca 100644
@@ -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;
 }

@@ -1007,8 +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);
+	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);
 }
 
 /**

include/linux/pci-p2pdma.h +14 -4

index b502fc8b49bf9..27a2c399f47da 100644
@@ -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);

@@ -144,10 +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;
 };
 
+
 /* 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);

@@ -166,8 +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;

@@ -185,7 +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 + to_p2p_pgmap(state->pgmap)->bus_offsetf;
+	return paddr + state->mem->bus_offset;
 }
 
 #endif /* _LINUX_PCI_P2P_H */

Signature · 1 line

2.50.1

Leon Romanovsky

author

2025-08-04 13:01 UTC #5 lore raw

PATCH 3/10 PCI/P2PDMA: Simplify bus address mapping API

From: Leon Romanovsky <[email protected]>

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.

---
 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(-)

block/blk-mq-dma.c +1 -1

index d415088ed9fd2..430e51ec494a6 100644
@@ -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;
 }

drivers/iommu/dma-iommu.c +2 -2

index 69f85209be7ab..7c1c25ffb804d 100644
@@ -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;

include/linux/pci-p2pdma.h +3 -4

index 27a2c399f47da..eef96636c67e6 100644
@@ -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 */

kernel/dma/direct.c +2 -2

index 1062caac47e7b..3e058c99fe856 100644
@@ -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:

mm/hmm.c +1 -1

index 6556c0e074ba8..012b78688fa18 100644
@@ -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;
 	}

Signature · 1 line

2.50.1

Leon Romanovsky

author

2025-08-04 13:01 UTC #6 lore raw

PATCH 4/10 PCI/P2PDMA: Refactor to separate core P2P functionality from memory allocation

From: Leon Romanovsky <[email protected]>

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 pci_p2pdma_enable() function that returns a p2pdma_provider structure.

---
 drivers/pci/p2pdma.c       | 118 ++++++++++++++++++++++++++-----------
 include/linux/pci-p2pdma.h |   5 ++
 2 files changed, 89 insertions(+), 34 deletions(-)

drivers/pci/p2pdma.c +84 ~~-34~~

index 176a99232fdca..24a6c8ff88520 100644
@@ -25,11 +25,12 @@ struct pci_p2pdma {
 	struct gen_pool *pool;
 	bool p2pmem_published;
 	struct xarray map_types;
+	struct p2pdma_provider mem;
 };
 
 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 +228,82 @@ 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)
+/**
+ * pci_p2pdma_enable - Enable peer-to-peer DMA support for a PCI device
+ * @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.
+ */
+struct p2pdma_provider *pci_p2pdma_enable(struct pci_dev *pdev)
 {
-	int error = -ENOMEM;
 	struct pci_p2pdma *p2p;
+	int ret;
+
+	p2p = rcu_dereference_protected(pdev->p2pdma, 1);
+	if (p2p)
+		/* PCI device was "rebound" to the driver */
+		return &p2p->mem;
 
 	p2p = devm_kzalloc(&pdev->dev, sizeof(*p2p), GFP_KERNEL);
 	if (!p2p)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	xa_init(&p2p->map_types);
+	p2p->mem.owner = &pdev->dev;
+	/* On all p2p platforms bus_offset is the same for all BARs */
+	p2p->mem.bus_offset =
+		pci_bus_address(pdev, 0) - pci_resource_start(pdev, 0);
 
-	p2p->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev));
-	if (!p2p->pool)
-		goto out;
+	ret = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev);
+	if (ret)
+		goto out_p2p;
 
-	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev);
-	if (error)
-		goto out_pool_destroy;
+	rcu_assign_pointer(pdev->p2pdma, p2p);
+	return &p2p->mem;
 
-	error = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group);
-	if (error)
+out_p2p:
+	devm_kfree(&pdev->dev, p2p);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(pci_p2pdma_enable);
+
+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 +315,7 @@ 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 +334,7 @@ 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;

@@ -312,15 +352,25 @@ 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);
+	p2pdma = rcu_dereference_protected(pdev->p2pdma, 1);
+	if (!p2pdma) {
+		mem = pci_p2pdma_enable(pdev);
+		if (IS_ERR(mem))
+			return PTR_ERR(mem);
+
+		error = pci_p2pdma_setup_pool(pdev);
 		if (error)
 			return error;
-	}
+
+		p2pdma = rcu_dereference_protected(pdev->p2pdma, 1);
+	} else
+		mem = &p2pdma->mem;
 
 	p2p_pgmap = devm_kzalloc(&pdev->dev, sizeof(*p2p_pgmap), GFP_KERNEL);
-	if (!p2p_pgmap)
-		return -ENOMEM;
+	if (!p2p_pgmap) {
+		error = -ENOMEM;
+		goto free_pool;
+	}
 
 	pgmap = &p2p_pgmap->pgmap;
 	pgmap->range.start = pci_resource_start(pdev, bar) + offset;

@@ -328,9 +378,7 @@ 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)) {

@@ -343,7 +391,6 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	if (error)
 		goto pages_free;
 
-	p2pdma = rcu_dereference_protected(pdev->p2pdma, 1);
 	error = gen_pool_add_owner(p2pdma->pool, (unsigned long)addr,
 			pci_bus_address(pdev, bar) + offset,
 			range_len(&pgmap->range), dev_to_node(&pdev->dev),

@@ -359,7 +406,10 @@ 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);
+free_pool:
+	sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group);
+	gen_pool_destroy(p2pdma->pool);
 	return error;
 }
 EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource);

@@ -1008,11 +1058,11 @@ 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);
 }
 
 /**

include/linux/pci-p2pdma.h +5 -0

index eef96636c67e6..83f11dc8659a7 100644
@@ -27,6 +27,7 @@ struct p2pdma_provider {
 };
 
 #ifdef CONFIG_PCI_P2PDMA
+struct p2pdma_provider *pci_p2pdma_enable(struct pci_dev *pdev);
 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 +46,10 @@ 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 struct p2pdma_provider *pci_p2pdma_enable(struct pci_dev *pdev)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
 static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar,
 		size_t size, u64 offset)
 {

Signature · 1 line

2.50.1

Alex Williamson

2025-08-06 21:42 UTC #7 lore raw

Re: [PATCH v1 04/10] PCI/P2PDMA: Refactor to separate core P2P functionality from memory allocation

Quoted 90 lines · On Mon, 4 Aug 2025 16:00:39 +0300 Leon Romanovsky <[email protected]> wrote:

From: Leon Romanovsky <[email protected]>

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 optional upper layer provides memory allocation capabilities including gen_pool allocator, struct page support, and sysfs interface for user space access.

---
 drivers/pci/p2pdma.c       | 118 ++++++++++++++++++++++++++-----------
 include/linux/pci-p2pdma.h |   5 ++
 2 files changed, 89 insertions(+), 34 deletions(-)

drivers/pci/p2pdma.c +24 -6

index 176a99232fdca..24a6c8ff88520 100644
@@ -25,11 +25,12 @@ struct pci_p2pdma {
 	struct gen_pool *pool;
 	bool p2pmem_published;
 	struct xarray map_types;
+	struct p2pdma_provider mem;
 };
 
 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 +228,82 @@ 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)
+/**
+ * pci_p2pdma_enable - Enable peer-to-peer DMA support for a PCI device
+ * @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.
+ */
+struct p2pdma_provider *pci_p2pdma_enable(struct pci_dev *pdev)
 {
-	int error = -ENOMEM;
 	struct pci_p2pdma *p2p;
+	int ret;
+
+	p2p = rcu_dereference_protected(pdev->p2pdma, 1);
+	if (p2p)
+		/* PCI device was "rebound" to the driver */
+		return &p2p->mem;

drivers/pci/p2pdma.c static void pci_p2pdma_release(void *data) · line 268

Quoted 10 lines

drivers/pci/p2pdma.c +5 -1

 	p2p = devm_kzalloc(&pdev->dev, sizeof(*p2p), GFP_KERNEL);
 	if (!p2p)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	xa_init(&p2p->map_types);
+	p2p->mem.owner = &pdev->dev;
+	/* On all p2p platforms bus_offset is the same for all BARs */
+	p2p->mem.bus_offset =
+		pci_bus_address(pdev, 0) - pci_resource_start(pdev, 0);

But not all devices implement BAR0, nor is BAR0 necessarily in the memory space, wouldn't this calculation be wrong if BAR0 were unimplemented or an IO BAR? Even within memory BARs I can imagine different translations for 32 vs 64 bit, prefetch vs non-prefetch, but per the comment I guess we're excluding those. Thanks,

Alex

Jason Gunthorpe

maintainer

2025-08-07 00:02 UTC #8 lore raw

Re: [PATCH v1 04/10] PCI/P2PDMA: Refactor to separate core P2P functionality from memory allocation

Quoted 8 lines · Alex Williamson

drivers/pci/p2pdma.c static void pci_p2pdma_release(void *data) · line 268
Quoted 4 lines
drivers/pci/p2pdma.c +4 -0
+	p2p->mem.owner = &pdev->dev;
+	/* On all p2p platforms bus_offset is the same for all BARs */
+	p2p->mem.bus_offset =
+		pci_bus_address(pdev, 0) - pci_resource_start(pdev, 0);
But not all devices implement BAR0, nor is BAR0 necessarily in the memory space, wouldn't this calculation be wrong if BAR0 were unimplemented or an IO BAR?

I think you are correct about this.

Quoted 3 lines

Even within memory BARs I can imagine different translations for 32 vs 64 bit, prefetch vs non-prefetch, but per the comment I guess we're excluding those. Thanks,

Humm, I had thought it was consistent for the device, but I guess not:

	resource_list_for_each_entry(window, &bridge->windows) {
		if (resource_contains(window->res, res)) {
			offset = window->offset;

Seems like each window can have its own offset.

So the p2p should be made per-bar, and hold the bar index from the constructor..

Jason

Leon Romanovsky

author

2025-08-04 13:01 UTC #9 lore raw

PATCH 5/10 PCI/P2PDMA: Export pci_p2pdma_map_type() function

From: Leon Romanovsky <[email protected]>

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.

---
 drivers/pci/p2pdma.c       | 15 ++++++-
 include/linux/pci-p2pdma.h | 85 +++++++++++++++++++++-----------------
 2 files changed, 59 insertions(+), 41 deletions(-)

drivers/pci/p2pdma.c +13 -2

index 24a6c8ff88520..3fa1292c8d917 100644
@@ -1022,8 +1022,18 @@ 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);

@@ -1052,6 +1062,7 @@ 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)

include/linux/pci-p2pdma.h +46 ~~-39~~

109 lines not on this page · raw message

Signature · 1 line

2.50.1

Leon Romanovsky

author

2025-08-04 13:01 UTC #10 lore raw

PATCH 6/10 types: move phys_vec definition to common header

From: Leon Romanovsky <[email protected]>

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.

---
 block/blk-mq-dma.c    | 5 -----
 include/linux/types.h | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

block/blk-mq-dma.c +0 -5

index 430e51ec494a6..8d2646ab27953 100644
@@ -5,11 +5,6 @@
 #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 request *req, struct req_iterator *iter,
 			      struct phys_vec *vec)
 {

include/linux/types.h +5 -0

index 6dfdb8e8e4c35..2bc56681b2e62 100644
@@ -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;
 
 /*

Signature · 1 line

2.50.1

Leon Romanovsky

author

2025-08-04 13:01 UTC #11 lore raw

PATCH 7/10 vfio: Export vfio device get and put registration helpers

From: Vivek Kasireddy <[email protected]>

These helpers are useful for managing additional references taken on the device from other associated VFIO modules.

Original-patch-by Jason Gunthorpe <[email protected]>

---
 drivers/vfio/vfio_main.c | 2 ++
 include/linux/vfio.h     | 2 ++
 2 files changed, 4 insertions(+)

drivers/vfio/vfio_main.c +2 -0

index 1fd261efc582d..620a3ee5d04db 100644
@@ -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

include/linux/vfio.h +2 -0

index 707b00772ce1f..ba65bbdffd0b2 100644
@@ -293,6 +293,8 @@ 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);

Signature · 1 line

2.50.1

Leon Romanovsky

author

2025-08-04 13:01 UTC #12 lore raw

PATCH 8/10 vfio/pci: Enable peer-to-peer DMA transactions by default

From: Leon Romanovsky <[email protected]>

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,

---
 drivers/vfio/pci/vfio_pci_core.c | 4 ++++
 include/linux/vfio_pci_core.h    | 1 +
 2 files changed, 5 insertions(+)

drivers/vfio/pci/vfio_pci_core.c +4 -0

index 31bdb9110cc0f..df9a32d3deac9 100644
@@ -28,6 +28,7 @@
 #include <linux/nospec.h>
 #include <linux/sched/mm.h>
 #include <linux/iommufd.h>
+#include <linux/pci-p2pdma.h>
 #if IS_ENABLED(CONFIG_EEH)
 #include <asm/eeh.h>
 #endif

@@ -2088,6 +2089,9 @@ 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);
+	vdev->provider = pci_p2pdma_enable(vdev->pdev);
+	if (IS_ERR(vdev->provider))
+		return PTR_ERR(vdev->provider);
 	init_rwsem(&vdev->memory_lock);
 	xa_init(&vdev->ctx);

include/linux/vfio_pci_core.h +1 -0

index fbb472dd99b36..b017fae251811 100644
@@ -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 p2pdma_provider  *provider;
 };
 
 /* Will be exported for vfio pci drivers usage */

Signature · 1 line

2.50.1

Alex Williamson

2025-08-06 22:02 UTC #13 lore raw

Re: [PATCH v1 08/10] vfio/pci: Enable peer-to-peer DMA transactions by default

Quoted 24 lines · On Mon, 4 Aug 2025 16:00:43 +0300 Leon Romanovsky <[email protected]> wrote:

From: Leon Romanovsky <[email protected]>
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 <[email protected]>
---
 drivers/vfio/pci/vfio_pci_core.c | 4 ++++
 include/linux/vfio_pci_core.h    | 1 +
 2 files changed, 5 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +1 -0
index 31bdb9110cc0f..df9a32d3deac9 100644
@@ -28,6 +28,7 @@
 #include <linux/nospec.h>
 #include <linux/sched/mm.h>
 #include <linux/iommufd.h>
+#include <linux/pci-p2pdma.h>
 #if IS_ENABLED(CONFIG_EEH)
 #include <asm/eeh.h>
 #endif

drivers/vfio/pci/vfio_pci_core.c int vfio_pci_core_init_dev(struct vfio_device *core_vdev) · line 2094

Quoted 6 lines

drivers/vfio/pci/vfio_pci_core.c +3 -0

@@ -2088,6 +2089,9 @@ 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);
+	vdev->provider = pci_p2pdma_enable(vdev->pdev);
+	if (IS_ERR(vdev->provider))
+		return PTR_ERR(vdev->provider);

I think this just made all vfio-pci drivers functionally dependent on CONFIG_PCI_P2PDMA. Seems at best exporting a dma-buf should be restricted if this fails. Thanks,

Alex

Quoted 15 lines

drivers/vfio/pci/vfio_pci_core.c +0 -0

 	init_rwsem(&vdev->memory_lock);
 	xa_init(&vdev->ctx);

include/linux/vfio_pci_core.h +1 -0

index fbb472dd99b36..b017fae251811 100644
@@ -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 p2pdma_provider  *provider;
 };
 
 /* Will be exported for vfio pci drivers usage */

Leon Romanovsky

author

2025-09-02 12:58 UTC #14 lore raw

Re: [PATCH v1 08/10] vfio/pci: Enable peer-to-peer DMA transactions by default

Quoted 29 lines · Alex Williamson

Quoted 26 lines · On Mon, 4 Aug 2025 16:00:43 +0300 Leon Romanovsky <[email protected]> wrote:
From: Leon Romanovsky <[email protected]>
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 <[email protected]>
---
 drivers/vfio/pci/vfio_pci_core.c | 4 ++++
 include/linux/vfio_pci_core.h    | 1 +
 2 files changed, 5 insertions(+)
drivers/vfio/pci/vfio_pci_core.c +1 -0
index 31bdb9110cc0f..df9a32d3deac9 100644
@@ -28,6 +28,7 @@
 #include <linux/nospec.h>
 #include <linux/sched/mm.h>
 #include <linux/iommufd.h>
+#include <linux/pci-p2pdma.h>
 #if IS_ENABLED(CONFIG_EEH)
 #include <asm/eeh.h>
 #endif
@@ -2088,6 +2089,9 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev)
 	INIT_LIST_HEAD(&vdev->dummy_resources_list);
 	INIT_LIST_HEAD(&vdev->ioeventfds_list);

Quoted 8 lines

drivers/vfio/pci/vfio_pci_core.c int vfio_pci_core_init_dev(struct vfio_device *core_vdev) · line 2094
Quoted 4 lines
drivers/vfio/pci/vfio_pci_core.c +3 -0
 	INIT_LIST_HEAD(&vdev->sriov_pfs_item);
+	vdev->provider = pci_p2pdma_enable(vdev->pdev);
+	if (IS_ERR(vdev->provider))
+		return PTR_ERR(vdev->provider);
I think this just made all vfio-pci drivers functionally dependent on CONFIG_PCI_P2PDMA. Seems at best exporting a dma-buf should be restricted if this fails. Thanks,

It is temporary solution in next patch "vfio/pci: Add dma-buf export support for MMIO regions", the strict ifdef is added.

  2107 #ifdef CONFIG_VFIO_PCI_DMABUF
  2108         vdev->provider = pci_p2pdma_enable(vdev->pdev);
  2109         if (IS_ERR(vdev->provider))
  2110                 return PTR_ERR(vdev->provider);
  2111
  2112         INIT_LIST_HEAD(&vdev->dmabufs);
  2113 #endif

I will split "vfio/pci: Add dma-buf export ..." patch to introduce CONFIG_VFIO_PCI_DMABUF before this "vfio/pci: Enable peer-to-peer ..." patch.

Thanks

Quoted 19 lines

Alex

Quoted 15 lines

drivers/vfio/pci/vfio_pci_core.c +0 -0

 	init_rwsem(&vdev->memory_lock);
 	xa_init(&vdev->ctx);

include/linux/vfio_pci_core.h +1 -0

index fbb472dd99b36..b017fae251811 100644
@@ -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 p2pdma_provider  *provider;
 };
 
 /* Will be exported for vfio pci drivers usage */

Leon Romanovsky

author

2025-08-04 13:01 UTC #15 lore raw

PATCH 9/10 vfio/pci: Share the core device pointer while invoking feature functions

From: Vivek Kasireddy <[email protected]>

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.

---
 drivers/vfio/pci/vfio_pci_core.c | 30 +++++++++++++-----------------
 1 file changed, 13 insertions(+), 17 deletions(-)

drivers/vfio/pci/vfio_pci_core.c +13 ~~-17~~

index df9a32d3deac9..b1863d84b11aa 100644
@@ -300,11 +300,9 @@ 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);

@@ -321,12 +319,10 @@ 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;

@@ -377,11 +373,9 @@ 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);

@@ -1474,11 +1468,10 @@ 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;

@@ -1505,16 +1498,19 @@ 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;
 	}

Signature · 1 line

2.50.1

Leon Romanovsky

author

2025-08-04 13:01 UTC #16 lore raw

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

From: Leon Romanovsky <[email protected]>

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.

---
 drivers/vfio/pci/Kconfig           |  20 ++
 drivers/vfio/pci/Makefile          |   2 +
 drivers/vfio/pci/vfio_pci_config.c |  22 +-
 drivers/vfio/pci/vfio_pci_core.c   |  25 +-
 drivers/vfio/pci/vfio_pci_dmabuf.c | 390 +++++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_priv.h   |  23 ++
 include/linux/dma-buf.h            |   1 +
 include/linux/vfio_pci_core.h      |   3 +
 include/uapi/linux/vfio.h          |  25 ++
 9 files changed, 506 insertions(+), 5 deletions(-)
 create mode 100644 drivers/vfio/pci/vfio_pci_dmabuf.c

drivers/vfio/pci/Kconfig +20 -0

index 2b0172f546652..55ae888bf26ae 100644
@@ -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"

drivers/vfio/pci/Makefile +2 -0

index cf00c0a7e55c8..f9155e9c5f630 100644
@@ -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

drivers/vfio/pci/vfio_pci_config.c +18 -4

index 8f02f236b5b4b..7e23387a43b4d 100644
@@ -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, true);
 			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, true);
 			up_write(&vdev->memory_lock);
 		}
 	}

drivers/vfio/pci/vfio_pci_core.c +24 -1

index b1863d84b11aa..8e840ac413e9b 100644
@@ -28,7 +28,9 @@
 #include <linux/nospec.h>
 #include <linux/sched/mm.h>
 #include <linux/iommufd.h>
+#ifdef CONFIG_VFIO_PCI_DMABUF
 #include <linux/pci-p2pdma.h>
+#endif
 #if IS_ENABLED(CONFIG_EEH)
 #include <asm/eeh.h>
 #endif

@@ -287,6 +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;

@@ -370,6 +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);
 }

@@ -690,6 +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);

@@ -1222,7 +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;

@@ -1511,6 +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;
 	}

@@ -2085,9 +2098,13 @@ 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
 	vdev->provider = pci_p2pdma_enable(vdev->pdev);
 	if (IS_ERR(vdev->provider))
 		return PTR_ERR(vdev->provider);
+
+	INIT_LIST_HEAD(&vdev->dmabufs);
+#endif
 	init_rwsem(&vdev->memory_lock);
 	xa_init(&vdev->ctx);

@@ -2470,11 +2487,17 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
 	 * cause the PCI config space reset without restoring the original
 	 * state (saved locally in 'vdev->pm_save').
 	 */
-	list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list)
+	list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) {
+		vfio_pci_dma_buf_move(vdev, true);
 		vfio_pci_set_power_state(vdev, PCI_D0);
+	}
 
 	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);

drivers/vfio/pci/vfio_pci_dmabuf.c new file +390 -0

390 lines not on this page · raw message

drivers/vfio/pci/vfio_pci_priv.h +23 -0

index a9972eacb2936..28a405f8b97c9 100644
@@ -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

include/linux/dma-buf.h +1 -0

index d58e329ac0e71..f14b413aae48d 100644
@@ -483,6 +483,7 @@ struct dma_buf_attach_ops {
  * @dev: device attached to the buffer.
  * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf.
  * @peer2peer: true if the importer can handle peer resources without pages.
+ * #state: DMA structure to provide support for physical addresses DMA interface
  * @priv: exporter specific attachment data.
  * @importer_ops: importer operations for this attachment, if provided
  * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held.

include/linux/vfio_pci_core.h +3 -0

index b017fae251811..548cbb51bf146 100644
@@ -94,7 +94,10 @@ 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 p2pdma_provider  *provider;
+	struct list_head	dmabufs;
+#endif
 };
 
 /* Will be exported for vfio pci drivers usage */

include/uapi/linux/vfio.h +25 -0

index 5764f315137f9..89f86dd2dffb2 100644
@@ -1468,6 +1468,31 @@ 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 -------- */
 
 /**

Signature · 1 line

2.50.1

Leon Romanovsky

author

2025-08-04 15:26 UTC #17 lore raw

Re: [PATCH v1 10/10] vfio/pci: Add dma-buf export support for MMIO regions

Quoted 28 lines · Leon Romanovsky

From: Leon Romanovsky <[email protected]>
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 <[email protected]>
Signed-off-by Vivek Kasireddy <[email protected]>
Signed-off-by Leon Romanovsky <[email protected]>
---
 drivers/vfio/pci/Kconfig           |  20 ++
 drivers/vfio/pci/Makefile          |   2 +
 drivers/vfio/pci/vfio_pci_config.c |  22 +-
 drivers/vfio/pci/vfio_pci_core.c   |  25 +-
 drivers/vfio/pci/vfio_pci_dmabuf.c | 390 +++++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_priv.h   |  23 ++
 include/linux/dma-buf.h            |   1 +
 include/linux/vfio_pci_core.h      |   3 +
 include/uapi/linux/vfio.h          |  25 ++
 9 files changed, 506 insertions(+), 5 deletions(-)
 create mode 100644 drivers/vfio/pci/vfio_pci_dmabuf.c

<...>

include/linux/dma-buf.h struct dma_buf_attach_ops { · line 486

Quoted 9 lines

include/linux/dma-buf.h +1 -0

index d58e329ac0e71..f14b413aae48d 100644
@@ -483,6 +483,7 @@ struct dma_buf_attach_ops {
  * @dev: device attached to the buffer.
  * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf.
  * @peer2peer: true if the importer can handle peer resources without pages.
+ * #state: DMA structure to provide support for physical addresses DMA interface

This is rebase error, there is no need in this hunk.

Thanks

Alex Williamson

2025-08-06 22:25 UTC #18 lore raw

Re: [PATCH v1 10/10] vfio/pci: Add dma-buf export support for MMIO regions

Quoted 122 lines · On Mon, 4 Aug 2025 16:00:45 +0300 Leon Romanovsky <[email protected]> wrote:

From: Leon Romanovsky <[email protected]>

---
 drivers/vfio/pci/Kconfig           |  20 ++
 drivers/vfio/pci/Makefile          |   2 +
 drivers/vfio/pci/vfio_pci_config.c |  22 +-
 drivers/vfio/pci/vfio_pci_core.c   |  25 +-
 drivers/vfio/pci/vfio_pci_dmabuf.c | 390 +++++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_priv.h   |  23 ++
 include/linux/dma-buf.h            |   1 +
 include/linux/vfio_pci_core.h      |   3 +
 include/uapi/linux/vfio.h          |  25 ++
 9 files changed, 506 insertions(+), 5 deletions(-)
 create mode 100644 drivers/vfio/pci/vfio_pci_dmabuf.c

drivers/vfio/pci/Kconfig +20 -0

index 2b0172f546652..55ae888bf26ae 100644
@@ -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"

drivers/vfio/pci/Makefile +2 -0

index cf00c0a7e55c8..f9155e9c5f630 100644
@@ -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

drivers/vfio/pci/vfio_pci_config.c +12 -4

index 8f02f236b5b4b..7e23387a43b4d 100644
@@ -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);
 }

drivers/vfio/pci/vfio_pci_config.c static int vfio_exp_config_write(struct vfio_pci_core_device *vdev, int pos, · line 914

Quoted 7 lines

drivers/vfio/pci/vfio_pci_config.c +3 -0

@@ -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, true);

@revoked true -> true seems wrong.

drivers/vfio/pci/vfio_pci_config.c static int vfio_af_config_write(struct vfio_pci_core_device *vdev, int pos, · line 999

Quoted 11 lines

drivers/vfio/pci/vfio_pci_config.c +3 -0

 			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, true);

Same.

Quoted 79 lines

drivers/vfio/pci/vfio_pci_config.c +0 -0

 			up_write(&vdev->memory_lock);
 		}
 	}

drivers/vfio/pci/vfio_pci_core.c +17 -0

index b1863d84b11aa..8e840ac413e9b 100644
@@ -28,7 +28,9 @@
 #include <linux/nospec.h>
 #include <linux/sched/mm.h>
 #include <linux/iommufd.h>
+#ifdef CONFIG_VFIO_PCI_DMABUF
 #include <linux/pci-p2pdma.h>
+#endif
 #if IS_ENABLED(CONFIG_EEH)
 #include <asm/eeh.h>
 #endif

@@ -287,6 +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;

@@ -370,6 +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);
 }

@@ -690,6 +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);

@@ -1222,7 +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;

@@ -1511,6 +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;
 	}

@@ -2085,9 +2098,13 @@ 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
 	vdev->provider = pci_p2pdma_enable(vdev->pdev);
 	if (IS_ERR(vdev->provider))
 		return PTR_ERR(vdev->provider);
+
+	INIT_LIST_HEAD(&vdev->dmabufs);
+#endif
 	init_rwsem(&vdev->memory_lock);
 	xa_init(&vdev->ctx);

drivers/vfio/pci/vfio_pci_core.c static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, · line 2493

Quoted 8 lines

drivers/vfio/pci/vfio_pci_core.c +3 -1

@@ -2470,11 +2487,17 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
 	 * cause the PCI config space reset without restoring the original
 	 * state (saved locally in 'vdev->pm_save').
 	 */
-	list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list)
+	list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) {
+		vfio_pci_dma_buf_move(vdev, true);
 		vfio_pci_set_power_state(vdev, PCI_D0);
+	}

The revoke should have happened at the time the BARs were zapped. Thanks,

Alex

Quoted 10 lines

drivers/vfio/pci/vfio_pci_core.c +4 -0

 	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);

Alex Mastro

2025-09-12 20:06 UTC #19 lore raw

Re: [PATCH v1 10/10] vfio/pci: Add dma-buf export support for MMIO regions

drivers/vfio/pci/vfio_pci_dmabuf.c line 218

Quoted 12 lines · Leon Romanovsky

drivers/vfio/pci/vfio_pci_dmabuf.c new file +12 -0

+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 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;

Is the intent really to += paddr? I would have expected a plain assignment.

Quoted 4 lines

drivers/vfio/pci/vfio_pci_dmabuf.c new file +4 -0
+		priv->size += priv->phys_vec[i].len;
+	}
+	priv->nr_ranges = dma_buf->nr_ranges;
+}

...

Quoted 9 lines

drivers/vfio/pci/vfio_pci_dmabuf.c new file +9 -0

+	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);

Leon Romanovsky

author

2025-09-15 05:48 UTC #20 lore raw

Re: [PATCH v1 10/10] vfio/pci: Add dma-buf export support for MMIO regions

Quoted 15 lines · Alex Mastro

drivers/vfio/pci/vfio_pci_dmabuf.c line 218

Quoted 12 lines · Leon Romanovsky

drivers/vfio/pci/vfio_pci_dmabuf.c new file +12 -0

+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 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;

Is the intent really to += paddr? I would have expected a plain assignment.

In this specific case, there is no difference, because phys_vec is initialized to 0, but It needs to be "=" and not "+=".

Quoted 18 lines

Quoted 5 lines

drivers/vfio/pci/vfio_pci_dmabuf.c new file +4 -0
+		priv->size += priv->phys_vec[i].len;
+	}
+	priv->nr_ranges = dma_buf->nr_ranges;
+}

...

Quoted 9 lines

drivers/vfio/pci/vfio_pci_dmabuf.c new file +9 -0

+	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);

Benjamin LaHaise

2025-08-04 14:10 UTC #21 lore raw