summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/driver-api/pci/p2pdma.rst97
-rw-r--r--block/blk-mq-dma.c2
-rw-r--r--drivers/dma-buf/Makefile2
-rw-r--r--drivers/dma-buf/dma-buf-mapping.c248
-rw-r--r--drivers/iommu/dma-iommu.c4
-rw-r--r--drivers/iommu/iommufd/io_pagetable.c78
-rw-r--r--drivers/iommu/iommufd/io_pagetable.h54
-rw-r--r--drivers/iommu/iommufd/ioas.c8
-rw-r--r--drivers/iommu/iommufd/iommufd_private.h14
-rw-r--r--drivers/iommu/iommufd/iommufd_test.h10
-rw-r--r--drivers/iommu/iommufd/main.c10
-rw-r--r--drivers/iommu/iommufd/pages.c414
-rw-r--r--drivers/iommu/iommufd/selftest.c143
-rw-r--r--drivers/pci/p2pdma.c186
-rw-r--r--drivers/vfio/pci/Kconfig3
-rw-r--r--drivers/vfio/pci/Makefile1
-rw-r--r--drivers/vfio/pci/nvgrace-gpu/main.c52
-rw-r--r--drivers/vfio/pci/vfio_pci.c5
-rw-r--r--drivers/vfio/pci/vfio_pci_config.c22
-rw-r--r--drivers/vfio/pci/vfio_pci_core.c53
-rw-r--r--drivers/vfio/pci/vfio_pci_dmabuf.c350
-rw-r--r--drivers/vfio/pci/vfio_pci_priv.h23
-rw-r--r--drivers/vfio/vfio_main.c2
-rw-r--r--include/linux/dma-buf-mapping.h17
-rw-r--r--include/linux/dma-buf.h11
-rw-r--r--include/linux/pci-p2pdma.h120
-rw-r--r--include/linux/vfio.h2
-rw-r--r--include/linux/vfio_pci_core.h46
-rw-r--r--include/uapi/linux/vfio.h28
-rw-r--r--kernel/dma/direct.c4
-rw-r--r--mm/hmm.c2
-rw-r--r--tools/testing/selftests/iommu/iommufd.c43
-rw-r--r--tools/testing/selftests/iommu/iommufd_utils.h44
33 files changed, 1887 insertions, 211 deletions
diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst
index d0b241628cf1..280673b50350 100644
--- a/Documentation/driver-api/pci/p2pdma.rst
+++ b/Documentation/driver-api/pci/p2pdma.rst
@@ -9,22 +9,48 @@ between two devices on the bus. This type of transaction is henceforth
called Peer-to-Peer (or P2P). However, there are a number of issues that
make P2P transactions tricky to do in a perfectly safe way.
-One of the biggest issues is that PCI doesn't require forwarding
-transactions between hierarchy domains, and in PCIe, each Root Port
-defines a separate hierarchy domain. To make things worse, there is no
-simple way to determine if a given Root Complex supports this or not.
-(See PCIe r4.0, sec 1.3.1). Therefore, as of this writing, the kernel
-only supports doing P2P when the endpoints involved are all behind the
-same PCI bridge, as such devices are all in the same PCI hierarchy
-domain, and the spec guarantees that all transactions within the
-hierarchy will be routable, but it does not require routing
-between hierarchies.
-
-The second issue is that to make use of existing interfaces in Linux,
-memory that is used for P2P transactions needs to be backed by struct
-pages. However, PCI BARs are not typically cache coherent so there are
-a few corner case gotchas with these pages so developers need to
-be careful about what they do with them.
+For PCIe the routing of Transaction Layer Packets (TLPs) is well-defined up
+until they reach a host bridge or root port. If the path includes PCIe switches
+then based on the ACS settings the transaction can route entirely within
+the PCIe hierarchy and never reach the root port. The kernel will evaluate
+the PCIe topology and always permit P2P in these well-defined cases.
+
+However, if the P2P transaction reaches the host bridge then it might have to
+hairpin back out the same root port, be routed inside the CPU SOC to another
+PCIe root port, or routed internally to the SOC.
+
+The PCIe specification doesn't define the forwarding of transactions between
+hierarchy domains and kernel defaults to blocking such routing. There is an
+allow list to allow detecting known-good HW, in which case P2P between any
+two PCIe devices will be permitted.
+
+Since P2P inherently is doing transactions between two devices it requires two
+drivers to be co-operating inside the kernel. The providing driver has to convey
+its MMIO to the consuming driver. To meet the driver model lifecycle rules the
+MMIO must have all DMA mapping removed, all CPU accesses prevented, all page
+table mappings undone before the providing driver completes remove().
+
+This requires the providing and consuming driver to actively work together to
+guarantee that the consuming driver has stopped using the MMIO during a removal
+cycle. This is done by either a synchronous invalidation shutdown or waiting
+for all usage refcounts to reach zero.
+
+At the lowest level the P2P subsystem offers a naked struct p2p_provider that
+delegates lifecycle management to the providing driver. It is expected that
+drivers using this option will wrap their MMIO memory in DMABUF and use DMABUF
+to provide an invalidation shutdown. These MMIO addresess have no struct page, and
+if used with mmap() must create special PTEs. As such there are very few
+kernel uAPIs that can accept pointers to them; in particular they cannot be used
+with read()/write(), including O_DIRECT.
+
+Building on this, the subsystem offers a layer to wrap the MMIO in a ZONE_DEVICE
+pgmap of MEMORY_DEVICE_PCI_P2PDMA to create struct pages. The lifecycle of
+pgmap ensures that when the pgmap is destroyed all other drivers have stopped
+using the MMIO. This option works with O_DIRECT flows, in some cases, if the
+underlying subsystem supports handling MEMORY_DEVICE_PCI_P2PDMA through
+FOLL_PCI_P2PDMA. The use of FOLL_LONGTERM is prevented. As this relies on pgmap
+it also relies on architecture support along with alignment and minimum size
+limitations.
Driver Writer's Guide
@@ -114,14 +140,39 @@ allocating scatter-gather lists with P2P memory.
Struct Page Caveats
-------------------
-Driver writers should be very careful about not passing these special
-struct pages to code that isn't prepared for it. At this time, the kernel
-interfaces do not have any checks for ensuring this. This obviously
-precludes passing these pages to userspace.
+While the MEMORY_DEVICE_PCI_P2PDMA pages can be installed in VMAs,
+pin_user_pages() and related will not return them unless FOLL_PCI_P2PDMA is set.
-P2P memory is also technically IO memory but should never have any side
-effects behind it. Thus, the order of loads and stores should not be important
-and ioreadX(), iowriteX() and friends should not be necessary.
+The MEMORY_DEVICE_PCI_P2PDMA pages require care to support in the kernel. The
+KVA is still MMIO and must still be accessed through the normal
+readX()/writeX()/etc helpers. Direct CPU access (e.g. memcpy) is forbidden, just
+like any other MMIO mapping. While this will actually work on some
+architectures, others will experience corruption or just crash in the kernel.
+Supporting FOLL_PCI_P2PDMA in a subsystem requires scrubbing it to ensure no CPU
+access happens.
+
+
+Usage With DMABUF
+=================
+
+DMABUF provides an alternative to the above struct page-based
+client/provider/orchestrator system and should be used when struct page
+doesn't exist. In this mode the exporting driver will wrap
+some of its MMIO in a DMABUF and give the DMABUF FD to userspace.
+
+Userspace can then pass the FD to an importing driver which will ask the
+exporting driver to map it to the importer.
+
+In this case the initiator and target pci_devices are known and the P2P subsystem
+is used to determine the mapping type. The phys_addr_t-based DMA API is used to
+establish the dma_addr_t.
+
+Lifecycle is controlled by DMABUF move_notify(). When the exporting driver wants
+to remove() it must deliver an invalidation shutdown to all DMABUF importing
+drivers through move_notify() and synchronously DMA unmap all the MMIO.
+
+No importing driver can continue to have a DMA map to the MMIO after the
+exporting driver has destroyed its p2p_provider.
P2P DMA Support Library
diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c
index 449950029872..a1b623744b2f 100644
--- a/block/blk-mq-dma.c
+++ b/block/blk-mq-dma.c
@@ -85,7 +85,7 @@ static inline bool blk_can_dma_map_iova(struct request *req,
static bool blk_dma_map_bus(struct blk_dma_iter *iter, struct phys_vec *vec)
{
- iter->addr = pci_p2pdma_bus_addr_map(&iter->p2pdma, vec->paddr);
+ iter->addr = pci_p2pdma_bus_addr_map(iter->p2pdma.mem, vec->paddr);
iter->len = vec->len;
return true;
}
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 70ec901edf2c..2008fb7481b3 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
- dma-fence-unwrap.o dma-resv.o
+ dma-fence-unwrap.o dma-resv.o dma-buf-mapping.o
obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o
obj-$(CONFIG_DMABUF_HEAPS) += heaps/
obj-$(CONFIG_SYNC_FILE) += sync_file.o
diff --git a/drivers/dma-buf/dma-buf-mapping.c b/drivers/dma-buf/dma-buf-mapping.c
new file mode 100644
index 000000000000..b4819811a64a
--- /dev/null
+++ b/drivers/dma-buf/dma-buf-mapping.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * DMA BUF Mapping Helpers
+ *
+ */
+#include <linux/dma-buf-mapping.h>
+#include <linux/dma-resv.h>
+
+static struct scatterlist *fill_sg_entry(struct scatterlist *sgl, size_t 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(size_t, length, UINT_MAX);
+ length -= len;
+ /*
+ * DMABUF abuses scatterlist to create a scatterlist
+ * that does not have any CPU list, only the DMA list.
+ * Always set the page related values to NULL to ensure
+ * importers can't use it. The phys_addr based DMA API
+ * does not require the CPU list for mapping or unmapping.
+ */
+ sg_set_page(sgl, NULL, 0, 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 dma_iova_state *state,
+ struct dma_buf_phys_vec *phys_vec,
+ size_t nr_ranges, size_t size)
+{
+ unsigned int nents = 0;
+ size_t i;
+
+ if (!state || !dma_use_iova(state)) {
+ for (i = 0; i < 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(size, UINT_MAX);
+ }
+
+ return nents;
+}
+
+/**
+ * struct dma_buf_dma - holds DMA mapping information
+ * @sgt: Scatter-gather table
+ * @state: DMA IOVA state relevant in IOMMU-based DMA
+ * @size: Total size of DMA transfer
+ */
+struct dma_buf_dma {
+ struct sg_table sgt;
+ struct dma_iova_state *state;
+ size_t size;
+};
+
+/**
+ * dma_buf_phys_vec_to_sgt - Returns the scatterlist table of the attachment
+ * from arrays of physical vectors. This funciton is intended for MMIO memory
+ * only.
+ * @attach: [in] attachment whose scatterlist is to be returned
+ * @provider: [in] p2pdma provider
+ * @phys_vec: [in] array of physical vectors
+ * @nr_ranges: [in] number of entries in phys_vec array
+ * @size: [in] total size of phys_vec
+ * @dir: [in] direction of DMA transfer
+ *
+ * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR
+ * on error. May return -EINTR if it is interrupted by a signal.
+ *
+ * On success, the DMA addresses and lengths in the returned scatterlist are
+ * PAGE_SIZE aligned.
+ *
+ * A mapping must be unmapped by using dma_buf_free_sgt().
+ *
+ * NOTE: This function is intended for exporters. If direct traffic routing is
+ * mandatory exporter should call routing pci_p2pdma_map_type() before calling
+ * this function.
+ */
+struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach,
+ struct p2pdma_provider *provider,
+ struct dma_buf_phys_vec *phys_vec,
+ size_t nr_ranges, size_t size,
+ enum dma_data_direction dir)
+{
+ unsigned int nents, mapped_len = 0;
+ struct dma_buf_dma *dma;
+ struct scatterlist *sgl;
+ dma_addr_t addr;
+ size_t i;
+ int ret;
+
+ dma_resv_assert_held(attach->dmabuf->resv);
+
+ if (WARN_ON(!attach || !attach->dmabuf || !provider))
+ /* This function is supposed to work on MMIO memory only */
+ return ERR_PTR(-EINVAL);
+
+ dma = kzalloc(sizeof(*dma), GFP_KERNEL);
+ if (!dma)
+ return ERR_PTR(-ENOMEM);
+
+ switch (pci_p2pdma_map_type(provider, attach->dev)) {
+ case PCI_P2PDMA_MAP_BUS_ADDR:
+ /*
+ * There is no need in IOVA at all for this flow.
+ */
+ break;
+ case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+ dma->state = kzalloc(sizeof(*dma->state), GFP_KERNEL);
+ if (!dma->state) {
+ ret = -ENOMEM;
+ goto err_free_dma;
+ }
+
+ dma_iova_try_alloc(attach->dev, dma->state, 0, size);
+ break;
+ default:
+ ret = -EINVAL;
+ goto err_free_dma;
+ }
+
+ nents = calc_sg_nents(dma->state, phys_vec, nr_ranges, size);
+ ret = sg_alloc_table(&dma->sgt, nents, GFP_KERNEL | __GFP_ZERO);
+ if (ret)
+ goto err_free_state;
+
+ sgl = dma->sgt.sgl;
+
+ for (i = 0; i < nr_ranges; i++) {
+ if (!dma->state) {
+ addr = pci_p2pdma_bus_addr_map(provider,
+ phys_vec[i].paddr);
+ } else if (dma_use_iova(dma->state)) {
+ ret = dma_iova_link(attach->dev, dma->state,
+ phys_vec[i].paddr, 0,
+ phys_vec[i].len, dir,
+ DMA_ATTR_MMIO);
+ if (ret)
+ goto err_unmap_dma;
+
+ mapped_len += phys_vec[i].len;
+ } else {
+ addr = dma_map_phys(attach->dev, phys_vec[i].paddr,
+ phys_vec[i].len, dir,
+ DMA_ATTR_MMIO);
+ ret = dma_mapping_error(attach->dev, addr);
+ if (ret)
+ goto err_unmap_dma;
+ }
+
+ if (!dma->state || !dma_use_iova(dma->state))
+ sgl = fill_sg_entry(sgl, phys_vec[i].len, addr);
+ }
+
+ if (dma->state && dma_use_iova(dma->state)) {
+ WARN_ON_ONCE(mapped_len != size);
+ ret = dma_iova_sync(attach->dev, dma->state, 0, mapped_len);
+ if (ret)
+ goto err_unmap_dma;
+
+ sgl = fill_sg_entry(sgl, mapped_len, dma->state->addr);
+ }
+
+ dma->size = size;
+
+ /*
+ * No CPU list included — set orig_nents = 0 so others can detect
+ * this via SG table (use nents only).
+ */
+ dma->sgt.orig_nents = 0;
+
+
+ /*
+ * 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 &dma->sgt;
+
+err_unmap_dma:
+ if (!i || !dma->state) {
+ ; /* Do nothing */
+ } else if (dma_use_iova(dma->state)) {
+ dma_iova_destroy(attach->dev, dma->state, mapped_len, dir,
+ DMA_ATTR_MMIO);
+ } else {
+ for_each_sgtable_dma_sg(&dma->sgt, sgl, i)
+ dma_unmap_phys(attach->dev, sg_dma_address(sgl),
+ sg_dma_len(sgl), dir, DMA_ATTR_MMIO);
+ }
+ sg_free_table(&dma->sgt);
+err_free_state:
+ kfree(dma->state);
+err_free_dma:
+ kfree(dma);
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_NS_GPL(dma_buf_phys_vec_to_sgt, "DMA_BUF");
+
+/**
+ * dma_buf_free_sgt- unmaps the buffer
+ * @attach: [in] attachment to unmap buffer from
+ * @sgt: [in] scatterlist info of the buffer to unmap
+ * @dir: [in] direction of DMA transfer
+ *
+ * This unmaps a DMA mapping for @attached obtained
+ * by dma_buf_phys_vec_to_sgt().
+ */
+void dma_buf_free_sgt(struct dma_buf_attachment *attach, struct sg_table *sgt,
+ enum dma_data_direction dir)
+{
+ struct dma_buf_dma *dma = container_of(sgt, struct dma_buf_dma, sgt);
+ int i;
+
+ dma_resv_assert_held(attach->dmabuf->resv);
+
+ if (!dma->state) {
+ ; /* Do nothing */
+ } else if (dma_use_iova(dma->state)) {
+ dma_iova_destroy(attach->dev, dma->state, dma->size, dir,
+ DMA_ATTR_MMIO);
+ } else {
+ struct scatterlist *sgl;
+
+ for_each_sgtable_dma_sg(sgt, sgl, i)
+ dma_unmap_phys(attach->dev, sg_dma_address(sgl),
+ sg_dma_len(sgl), dir, DMA_ATTR_MMIO);
+ }
+
+ sg_free_table(sgt);
+ kfree(dma->state);
+ kfree(dma);
+
+}
+EXPORT_SYMBOL_NS_GPL(dma_buf_free_sgt, "DMA_BUF");
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 7944a3af4545..e52d19d2e833 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1439,8 +1439,8 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
* as a bus address, __finalise_sg() will copy the dma
* address into the output segment.
*/
- s->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state,
- sg_phys(s));
+ s->dma_address = pci_p2pdma_bus_addr_map(
+ p2pdma_state.mem, sg_phys(s));
sg_dma_len(s) = sg->length;
sg_dma_mark_bus_address(s);
continue;
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 75d60f2ad900..54cf4d856179 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -8,8 +8,10 @@
* The datastructure uses the iopt_pages to optimize the storage of the PFNs
* between the domains and xarray.
*/
+#include <linux/dma-buf.h>
#include <linux/err.h>
#include <linux/errno.h>
+#include <linux/file.h>
#include <linux/iommu.h>
#include <linux/iommufd.h>
#include <linux/lockdep.h>
@@ -284,6 +286,9 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt,
case IOPT_ADDRESS_FILE:
start = elm->start_byte + elm->pages->start;
break;
+ case IOPT_ADDRESS_DMABUF:
+ start = elm->start_byte + elm->pages->dmabuf.start;
+ break;
}
rc = iopt_alloc_iova(iopt, dst_iova, start, length);
if (rc)
@@ -468,25 +473,53 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
* @iopt: io_pagetable to act on
* @iova: If IOPT_ALLOC_IOVA is set this is unused on input and contains
* the chosen iova on output. Otherwise is the iova to map to on input
- * @file: file to map
+ * @fd: fdno of a file to map
* @start: map file starting at this byte offset
* @length: Number of bytes to map
* @iommu_prot: Combination of IOMMU_READ/WRITE/etc bits for the mapping
* @flags: IOPT_ALLOC_IOVA or zero
*/
int iopt_map_file_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
- unsigned long *iova, struct file *file,
- unsigned long start, unsigned long length,
- int iommu_prot, unsigned int flags)
+ unsigned long *iova, int fd, unsigned long start,
+ unsigned long length, int iommu_prot,
+ unsigned int flags)
{
struct iopt_pages *pages;
+ struct dma_buf *dmabuf;
+ unsigned long start_byte;
+ unsigned long last;
+
+ if (!length)
+ return -EINVAL;
+ if (check_add_overflow(start, length - 1, &last))
+ return -EOVERFLOW;
+
+ start_byte = start - ALIGN_DOWN(start, PAGE_SIZE);
+ dmabuf = dma_buf_get(fd);
+ if (!IS_ERR(dmabuf)) {
+ pages = iopt_alloc_dmabuf_pages(ictx, dmabuf, start_byte, start,
+ length,
+ iommu_prot & IOMMU_WRITE);
+ if (IS_ERR(pages)) {
+ dma_buf_put(dmabuf);
+ return PTR_ERR(pages);
+ }
+ } else {
+ struct file *file;
+
+ file = fget(fd);
+ if (!file)
+ return -EBADF;
+
+ pages = iopt_alloc_file_pages(file, start_byte, start, length,
+ iommu_prot & IOMMU_WRITE);
+ fput(file);
+ if (IS_ERR(pages))
+ return PTR_ERR(pages);
+ }
- pages = iopt_alloc_file_pages(file, start, length,
- iommu_prot & IOMMU_WRITE);
- if (IS_ERR(pages))
- return PTR_ERR(pages);
return iopt_map_common(ictx, iopt, pages, iova, length,
- start - pages->start, iommu_prot, flags);
+ start_byte, iommu_prot, flags);
}
struct iova_bitmap_fn_arg {
@@ -961,9 +994,15 @@ static void iopt_unfill_domain(struct io_pagetable *iopt,
WARN_ON(!area->storage_domain);
if (area->storage_domain == domain)
area->storage_domain = storage_domain;
+ if (iopt_is_dmabuf(pages)) {
+ if (!iopt_dmabuf_revoked(pages))
+ iopt_area_unmap_domain(area, domain);
+ iopt_dmabuf_untrack_domain(pages, area, domain);
+ }
mutex_unlock(&pages->mutex);
- iopt_area_unmap_domain(area, domain);
+ if (!iopt_is_dmabuf(pages))
+ iopt_area_unmap_domain(area, domain);
}
return;
}
@@ -980,6 +1019,8 @@ static void iopt_unfill_domain(struct io_pagetable *iopt,
WARN_ON(area->storage_domain != domain);
area->storage_domain = NULL;
iopt_area_unfill_domain(area, pages, domain);
+ if (iopt_is_dmabuf(pages))
+ iopt_dmabuf_untrack_domain(pages, area, domain);
mutex_unlock(&pages->mutex);
}
}
@@ -1009,10 +1050,16 @@ static int iopt_fill_domain(struct io_pagetable *iopt,
if (!pages)
continue;
- mutex_lock(&pages->mutex);
+ guard(mutex)(&pages->mutex);
+ if (iopt_is_dmabuf(pages)) {
+ rc = iopt_dmabuf_track_domain(pages, area, domain);
+ if (rc)
+ goto out_unfill;
+ }
rc = iopt_area_fill_domain(area, domain);
if (rc) {
- mutex_unlock(&pages->mutex);
+ if (iopt_is_dmabuf(pages))
+ iopt_dmabuf_untrack_domain(pages, area, domain);
goto out_unfill;
}
if (!area->storage_domain) {
@@ -1021,7 +1068,6 @@ static int iopt_fill_domain(struct io_pagetable *iopt,
interval_tree_insert(&area->pages_node,
&pages->domains_itree);
}
- mutex_unlock(&pages->mutex);
}
return 0;
@@ -1042,6 +1088,8 @@ out_unfill:
area->storage_domain = NULL;
}
iopt_area_unfill_domain(area, pages, domain);
+ if (iopt_is_dmabuf(pages))
+ iopt_dmabuf_untrack_domain(pages, area, domain);
mutex_unlock(&pages->mutex);
}
return rc;
@@ -1252,6 +1300,10 @@ static int iopt_area_split(struct iopt_area *area, unsigned long iova)
if (!pages || area->prevent_access)
return -EBUSY;
+ /* Maintaining the domains_itree below is a bit complicated */
+ if (iopt_is_dmabuf(pages))
+ return -EOPNOTSUPP;
+
if (new_start & (alignment - 1) ||
iopt_area_start_byte(area, new_start) & (alignment - 1))
return -EINVAL;
diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h
index b6064f4ce4af..14cd052fd320 100644
--- a/drivers/iommu/iommufd/io_pagetable.h
+++ b/drivers/iommu/iommufd/io_pagetable.h
@@ -5,6 +5,7 @@
#ifndef __IO_PAGETABLE_H
#define __IO_PAGETABLE_H
+#include <linux/dma-buf.h>
#include <linux/interval_tree.h>
#include <linux/kref.h>
#include <linux/mutex.h>
@@ -69,6 +70,16 @@ void iopt_area_unfill_domain(struct iopt_area *area, struct iopt_pages *pages,
void iopt_area_unmap_domain(struct iopt_area *area,
struct iommu_domain *domain);
+int iopt_dmabuf_track_domain(struct iopt_pages *pages, struct iopt_area *area,
+ struct iommu_domain *domain);
+void iopt_dmabuf_untrack_domain(struct iopt_pages *pages,
+ struct iopt_area *area,
+ struct iommu_domain *domain);
+int iopt_dmabuf_track_all_domains(struct iopt_area *area,
+ struct iopt_pages *pages);
+void iopt_dmabuf_untrack_all_domains(struct iopt_area *area,
+ struct iopt_pages *pages);
+
static inline unsigned long iopt_area_index(struct iopt_area *area)
{
return area->pages_node.start;
@@ -179,7 +190,22 @@ enum {
enum iopt_address_type {
IOPT_ADDRESS_USER = 0,
- IOPT_ADDRESS_FILE = 1,
+ IOPT_ADDRESS_FILE,
+ IOPT_ADDRESS_DMABUF,
+};
+
+struct iopt_pages_dmabuf_track {
+ struct iommu_domain *domain;
+ struct iopt_area *area;
+ struct list_head elm;
+};
+
+struct iopt_pages_dmabuf {
+ struct dma_buf_attachment *attach;
+ struct dma_buf_phys_vec phys;
+ /* Always PAGE_SIZE aligned */
+ unsigned long start;
+ struct list_head tracker;
};
/*
@@ -209,6 +235,8 @@ struct iopt_pages {
struct file *file;
unsigned long start;
};
+ /* IOPT_ADDRESS_DMABUF */
+ struct iopt_pages_dmabuf dmabuf;
};
bool writable:1;
u8 account_mode;
@@ -220,10 +248,32 @@ struct iopt_pages {
struct rb_root_cached domains_itree;
};
+static inline bool iopt_is_dmabuf(struct iopt_pages *pages)
+{
+ if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER))
+ return false;
+ return pages->type == IOPT_ADDRESS_DMABUF;
+}
+
+static inline bool iopt_dmabuf_revoked(struct iopt_pages *pages)
+{
+ lockdep_assert_held(&pages->mutex);
+ if (iopt_is_dmabuf(pages))
+ return pages->dmabuf.phys.len == 0;
+ return false;
+}
+
struct iopt_pages *iopt_alloc_user_pages(void __user *uptr,
unsigned long length, bool writable);
-struct iopt_pages *iopt_alloc_file_pages(struct file *file, unsigned long start,
+struct iopt_pages *iopt_alloc_file_pages(struct file *file,
+ unsigned long start_byte,
+ unsigned long start,
unsigned long length, bool writable);
+struct iopt_pages *iopt_alloc_dmabuf_pages(struct iommufd_ctx *ictx,
+ struct dma_buf *dmabuf,
+ unsigned long start_byte,
+ unsigned long start,
+ unsigned long length, bool writable);
void iopt_release_pages(struct kref *kref);
static inline void iopt_put_pages(struct iopt_pages *pages)
{
diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c
index 459a7c516915..f4721afedadc 100644
--- a/drivers/iommu/iommufd/ioas.c
+++ b/drivers/iommu/iommufd/ioas.c
@@ -207,7 +207,6 @@ int iommufd_ioas_map_file(struct iommufd_ucmd *ucmd)
unsigned long iova = cmd->iova;
struct iommufd_ioas *ioas;
unsigned int flags = 0;
- struct file *file;
int rc;
if (cmd->flags &
@@ -229,11 +228,7 @@ int iommufd_ioas_map_file(struct iommufd_ucmd *ucmd)
if (!(cmd->flags & IOMMU_IOAS_MAP_FIXED_IOVA))
flags = IOPT_ALLOC_IOVA;
- file = fget(cmd->fd);
- if (!file)
- return -EBADF;
-
- rc = iopt_map_file_pages(ucmd->ictx, &ioas->iopt, &iova, file,
+ rc = iopt_map_file_pages(ucmd->ictx, &ioas->iopt, &iova, cmd->fd,
cmd->start, cmd->length,
conv_iommu_prot(cmd->flags), flags);
if (rc)
@@ -243,7 +238,6 @@ int iommufd_ioas_map_file(struct iommufd_ucmd *ucmd)
rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
out_put:
iommufd_put_object(ucmd->ictx, &ioas->obj);
- fput(file);
return rc;
}
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 627f9b78483a..ef2db82e3d7b 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -19,6 +19,8 @@ struct iommu_domain;
struct iommu_group;
struct iommu_option;
struct iommufd_device;
+struct dma_buf_attachment;
+struct dma_buf_phys_vec;
struct iommufd_sw_msi_map {
struct list_head sw_msi_item;
@@ -108,7 +110,7 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
unsigned long length, int iommu_prot,
unsigned int flags);
int iopt_map_file_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
- unsigned long *iova, struct file *file,
+ unsigned long *iova, int fd,
unsigned long start, unsigned long length,
int iommu_prot, unsigned int flags);
int iopt_map_pages(struct io_pagetable *iopt, struct list_head *pages_list,
@@ -504,6 +506,8 @@ void iommufd_device_pre_destroy(struct iommufd_object *obj);
void iommufd_device_destroy(struct iommufd_object *obj);
int iommufd_get_hw_info(struct iommufd_ucmd *ucmd);
+struct device *iommufd_global_device(void);
+
struct iommufd_access {
struct iommufd_object obj;
struct iommufd_ctx *ictx;
@@ -711,6 +715,8 @@ bool iommufd_should_fail(void);
int __init iommufd_test_init(void);
void iommufd_test_exit(void);
bool iommufd_selftest_is_mock_dev(struct device *dev);
+int iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+ struct dma_buf_phys_vec *phys);
#else
static inline void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
unsigned int ioas_id,
@@ -732,5 +738,11 @@ static inline bool iommufd_selftest_is_mock_dev(struct device *dev)
{
return false;
}
+static inline int
+iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+ struct dma_buf_phys_vec *phys)
+{
+ return -EOPNOTSUPP;
+}
#endif
#endif
diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 8fc618b2bcf9..9166c39eb0c8 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -29,6 +29,8 @@ enum {
IOMMU_TEST_OP_PASID_REPLACE,
IOMMU_TEST_OP_PASID_DETACH,
IOMMU_TEST_OP_PASID_CHECK_HWPT,
+ IOMMU_TEST_OP_DMABUF_GET,
+ IOMMU_TEST_OP_DMABUF_REVOKE,
};
enum {
@@ -176,6 +178,14 @@ struct iommu_test_cmd {
__u32 hwpt_id;
/* @id is stdev_id */
} pasid_check;
+ struct {
+ __u32 length;
+ __u32 open_flags;
+ } dmabuf_get;
+ struct {
+ __s32 dmabuf_fd;
+ __u32 revoked;
+ } dmabuf_revoke;
};
__u32 last;
};
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index ce775fbbae94..5cc4b08c25f5 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -751,6 +751,15 @@ static struct miscdevice vfio_misc_dev = {
.mode = 0666,
};
+/*
+ * Used only by DMABUF, returns a valid struct device to use as a dummy struct
+ * device for attachment.
+ */
+struct device *iommufd_global_device(void)
+{
+ return iommu_misc_dev.this_device;
+}
+
static int __init iommufd_init(void)
{
int ret;
@@ -794,5 +803,6 @@ MODULE_ALIAS("devname:vfio/vfio");
#endif
MODULE_IMPORT_NS("IOMMUFD_INTERNAL");
MODULE_IMPORT_NS("IOMMUFD");
+MODULE_IMPORT_NS("DMA_BUF");
MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices");
MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c
index c3433b845561..dbe51ecb9a20 100644
--- a/drivers/iommu/iommufd/pages.c
+++ b/drivers/iommu/iommufd/pages.c
@@ -45,6 +45,8 @@
* last_iova + 1 can overflow. An iopt_pages index will always be much less than
* ULONG_MAX so last_index + 1 cannot overflow.
*/
+#include <linux/dma-buf.h>
+#include <linux/dma-resv.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/iommu.h>
@@ -53,6 +55,7 @@
#include <linux/overflow.h>
#include <linux/slab.h>
#include <linux/sched/mm.h>
+#include <linux/vfio_pci_core.h>
#include "double_span.h"
#include "io_pagetable.h"
@@ -258,6 +261,11 @@ static struct iopt_area *iopt_pages_find_domain_area(struct iopt_pages *pages,
return container_of(node, struct iopt_area, pages_node);
}
+enum batch_kind {
+ BATCH_CPU_MEMORY = 0,
+ BATCH_MMIO,
+};
+
/*
* A simple datastructure to hold a vector of PFNs, optimized for contiguous
* PFNs. This is used as a temporary holding memory for shuttling pfns from one
@@ -271,7 +279,9 @@ struct pfn_batch {
unsigned int array_size;
unsigned int end;
unsigned int total_pfns;
+ enum batch_kind kind;
};
+enum { MAX_NPFNS = type_max(typeof(((struct pfn_batch *)0)->npfns[0])) };
static void batch_clear(struct pfn_batch *batch)
{
@@ -348,11 +358,17 @@ static void batch_destroy(struct pfn_batch *batch, void *backup)
}
static bool batch_add_pfn_num(struct pfn_batch *batch, unsigned long pfn,
- u32 nr)
+ u32 nr, enum batch_kind kind)
{
- const unsigned int MAX_NPFNS = type_max(typeof(*batch->npfns));
unsigned int end = batch->end;
+ if (batch->kind != kind) {
+ /* One kind per batch */
+ if (batch->end != 0)
+ return false;
+ batch->kind = kind;
+ }
+
if (end && pfn == batch->pfns[end - 1] + batch->npfns[end - 1] &&
nr <= MAX_NPFNS - batch->npfns[end - 1]) {
batch->npfns[end - 1] += nr;
@@ -379,7 +395,7 @@ static void batch_remove_pfn_num(struct pfn_batch *batch, unsigned long nr)
/* true if the pfn was added, false otherwise */
static bool batch_add_pfn(struct pfn_batch *batch, unsigned long pfn)
{
- return batch_add_pfn_num(batch, pfn, 1);
+ return batch_add_pfn_num(batch, pfn, 1, BATCH_CPU_MEMORY);
}
/*
@@ -492,6 +508,7 @@ static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain,
{
bool disable_large_pages = area->iopt->disable_large_pages;
unsigned long last_iova = iopt_area_last_iova(area);
+ int iommu_prot = area->iommu_prot;
unsigned int page_offset = 0;
unsigned long start_iova;
unsigned long next_iova;
@@ -499,6 +516,11 @@ static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain,
unsigned long iova;
int rc;
+ if (batch->kind == BATCH_MMIO) {
+ iommu_prot &= ~IOMMU_CACHE;
+ iommu_prot |= IOMMU_MMIO;
+ }
+
/* The first index might be a partial page */
if (start_index == iopt_area_index(area))
page_offset = area->page_offset;
@@ -512,11 +534,11 @@ static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain,
rc = batch_iommu_map_small(
domain, iova,
PFN_PHYS(batch->pfns[cur]) + page_offset,
- next_iova - iova, area->iommu_prot);
+ next_iova - iova, iommu_prot);
else
rc = iommu_map(domain, iova,
PFN_PHYS(batch->pfns[cur]) + page_offset,
- next_iova - iova, area->iommu_prot,
+ next_iova - iova, iommu_prot,
GFP_KERNEL_ACCOUNT);
if (rc)
goto err_unmap;
@@ -652,7 +674,7 @@ static int batch_from_folios(struct pfn_batch *batch, struct folio ***folios_p,
nr = min(nr, npages);
npages -= nr;
- if (!batch_add_pfn_num(batch, pfn, nr))
+ if (!batch_add_pfn_num(batch, pfn, nr, BATCH_CPU_MEMORY))
break;
if (nr > 1) {
rc = folio_add_pins(folio, nr - 1);
@@ -1054,6 +1076,41 @@ static int pfn_reader_user_update_pinned(struct pfn_reader_user *user,
return iopt_pages_update_pinned(pages, npages, inc, user);
}
+struct pfn_reader_dmabuf {
+ struct dma_buf_phys_vec phys;
+ unsigned long start_offset;
+};
+
+static int pfn_reader_dmabuf_init(struct pfn_reader_dmabuf *dmabuf,
+ struct iopt_pages *pages)
+{
+ /* Callers must not get here if the dmabuf was already revoked */
+ if (WARN_ON(iopt_dmabuf_revoked(pages)))
+ return -EINVAL;
+
+ dmabuf->phys = pages->dmabuf.phys;
+ dmabuf->start_offset = pages->dmabuf.start;
+ return 0;
+}
+
+static int pfn_reader_fill_dmabuf(struct pfn_reader_dmabuf *dmabuf,
+ struct pfn_batch *batch,
+ unsigned long start_index,
+ unsigned long last_index)
+{
+ unsigned long start = dmabuf->start_offset + start_index * PAGE_SIZE;
+
+ /*
+ * start/last_index and start are all PAGE_SIZE aligned, the batch is
+ * always filled using page size aligned PFNs just like the other types.
+ * If the dmabuf has been sliced on a sub page offset then the common
+ * batch to domain code will adjust it before mapping to the domain.
+ */
+ batch_add_pfn_num(batch, PHYS_PFN(dmabuf->phys.paddr + start),
+ last_index - start_index + 1, BATCH_MMIO);
+ return 0;
+}
+
/*
* PFNs are stored in three places, in order of preference:
* - The iopt_pages xarray. This is only populated if there is a
@@ -1072,7 +1129,10 @@ struct pfn_reader {
unsigned long batch_end_index;
unsigned long last_index;
- struct pfn_reader_user user;
+ union {
+ struct pfn_reader_user user;
+ struct pfn_reader_dmabuf dmabuf;
+ };
};
static int pfn_reader_update_pinned(struct pfn_reader *pfns)
@@ -1108,7 +1168,7 @@ static int pfn_reader_fill_span(struct pfn_reader *pfns)
{
struct interval_tree_double_span_iter *span = &pfns->span;
unsigned long start_index = pfns->batch_end_index;
- struct pfn_reader_user *user = &pfns->user;
+ struct pfn_reader_user *user;
unsigned long npages;
struct iopt_area *area;
int rc;
@@ -1140,8 +1200,13 @@ static int pfn_reader_fill_span(struct pfn_reader *pfns)
return 0;
}
- if (start_index >= pfns->user.upages_end) {
- rc = pfn_reader_user_pin(&pfns->user, pfns->pages, start_index,
+ if (iopt_is_dmabuf(pfns->pages))
+ return pfn_reader_fill_dmabuf(&pfns->dmabuf, &pfns->batch,
+ start_index, span->last_hole);
+
+ user = &pfns->user;
+ if (start_index >= user->upages_end) {
+ rc = pfn_reader_user_pin(user, pfns->pages, start_index,
span->last_hole);
if (rc)
return rc;
@@ -1209,7 +1274,10 @@ static int pfn_reader_init(struct pfn_reader *pfns, struct iopt_pages *pages,
pfns->batch_start_index = start_index;
pfns->batch_end_index = start_index;
pfns->last_index = last_index;
- pfn_reader_user_init(&pfns->user, pages);
+ if (iopt_is_dmabuf(pages))
+ pfn_reader_dmabuf_init(&pfns->dmabuf, pages);
+ else
+ pfn_reader_user_init(&pfns->user, pages);
rc = batch_init(&pfns->batch, last_index - start_index + 1);
if (rc)
return rc;
@@ -1230,8 +1298,12 @@ static int pfn_reader_init(struct pfn_reader *pfns, struct iopt_pages *pages,
static void pfn_reader_release_pins(struct pfn_reader *pfns)
{
struct iopt_pages *pages = pfns->pages;
- struct pfn_reader_user *user = &pfns->user;
+ struct pfn_reader_user *user;
+
+ if (iopt_is_dmabuf(pages))
+ return;
+ user = &pfns->user;
if (user->upages_end > pfns->batch_end_index) {
/* Any pages not transferred to the batch are just unpinned */
@@ -1261,7 +1333,8 @@ static void pfn_reader_destroy(struct pfn_reader *pfns)
struct iopt_pages *pages = pfns->pages;
pfn_reader_release_pins(pfns);
- pfn_reader_user_destroy(&pfns->user, pfns->pages);
+ if (!iopt_is_dmabuf(pfns->pages))
+ pfn_reader_user_destroy(&pfns->user, pfns->pages);
batch_destroy(&pfns->batch, NULL);
WARN_ON(pages->last_npinned != pages->npinned);
}
@@ -1340,26 +1413,234 @@ struct iopt_pages *iopt_alloc_user_pages(void __user *uptr,
return pages;
}
-struct iopt_pages *iopt_alloc_file_pages(struct file *file, unsigned long start,
+struct iopt_pages *iopt_alloc_file_pages(struct file *file,
+ unsigned long start_byte,
+ unsigned long start,
unsigned long length, bool writable)
{
struct iopt_pages *pages;
- unsigned long start_down = ALIGN_DOWN(start, PAGE_SIZE);
- unsigned long end;
- if (length && check_add_overflow(start, length - 1, &end))
- return ERR_PTR(-EOVERFLOW);
-
- pages = iopt_alloc_pages(start - start_down, length, writable);
+ pages = iopt_alloc_pages(start_byte, length, writable);
if (IS_ERR(pages))
return pages;
pages->file = get_file(file);
- pages->start = start_down;
+ pages->start = start - start_byte;
pages->type = IOPT_ADDRESS_FILE;
return pages;
}
+static void iopt_revoke_notify(struct dma_buf_attachment *attach)
+{
+ struct iopt_pages *pages = attach->importer_priv;
+ struct iopt_pages_dmabuf_track *track;
+
+ guard(mutex)(&pages->mutex);
+ if (iopt_dmabuf_revoked(pages))
+ return;
+
+ list_for_each_entry(track, &pages->dmabuf.tracker, elm) {
+ struct iopt_area *area = track->area;
+
+ iopt_area_unmap_domain_range(area, track->domain,
+ iopt_area_index(area),
+ iopt_area_last_index(area));
+ }
+ pages->dmabuf.phys.len = 0;
+}
+
+static struct dma_buf_attach_ops iopt_dmabuf_attach_revoke_ops = {
+ .allow_peer2peer = true,
+ .move_notify = iopt_revoke_notify,
+};
+
+/*
+ * iommufd and vfio have a circular dependency. Future work for a phys
+ * based private interconnect will remove this.
+ */
+static int
+sym_vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+ struct dma_buf_phys_vec *phys)
+{
+ typeof(&vfio_pci_dma_buf_iommufd_map) fn;
+ int rc;
+
+ rc = iommufd_test_dma_buf_iommufd_map(attachment, phys);
+ if (rc != -EOPNOTSUPP)
+ return rc;
+
+ if (!IS_ENABLED(CONFIG_VFIO_PCI_DMABUF))
+ return -EOPNOTSUPP;
+
+ fn = symbol_get(vfio_pci_dma_buf_iommufd_map);
+ if (!fn)
+ return -EOPNOTSUPP;
+ rc = fn(attachment, phys);
+ symbol_put(vfio_pci_dma_buf_iommufd_map);
+ return rc;
+}
+
+static int iopt_map_dmabuf(struct iommufd_ctx *ictx, struct iopt_pages *pages,
+ struct dma_buf *dmabuf)
+{
+ struct dma_buf_attachment *attach;
+ int rc;
+
+ attach = dma_buf_dynamic_attach(dmabuf, iommufd_global_device(),
+ &iopt_dmabuf_attach_revoke_ops, pages);
+ if (IS_ERR(attach))
+ return PTR_ERR(attach);
+
+ dma_resv_lock(dmabuf->resv, NULL);
+ /*
+ * Lock ordering requires the mutex to be taken inside the reservation,
+ * make sure lockdep sees this.
+ */
+ if (IS_ENABLED(CONFIG_LOCKDEP)) {
+ mutex_lock(&pages->mutex);
+ mutex_unlock(&pages->mutex);
+ }
+
+ rc = sym_vfio_pci_dma_buf_iommufd_map(attach, &pages->dmabuf.phys);
+ if (rc)
+ goto err_detach;
+
+ dma_resv_unlock(dmabuf->resv);
+
+ /* On success iopt_release_pages() will detach and put the dmabuf. */
+ pages->dmabuf.attach = attach;
+ return 0;
+
+err_detach:
+ dma_resv_unlock(dmabuf->resv);
+ dma_buf_detach(dmabuf, attach);
+ return rc;
+}
+
+struct iopt_pages *iopt_alloc_dmabuf_pages(struct iommufd_ctx *ictx,
+ struct dma_buf *dmabuf,
+ unsigned long start_byte,
+ unsigned long start,
+ unsigned long length, bool writable)
+{
+ static struct lock_class_key pages_dmabuf_mutex_key;
+ struct iopt_pages *pages;
+ int rc;
+
+ if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ if (dmabuf->size <= (start + length - 1) ||
+ length / PAGE_SIZE >= MAX_NPFNS)
+ return ERR_PTR(-EINVAL);
+
+ pages = iopt_alloc_pages(start_byte, length, writable);
+ if (IS_ERR(pages))
+ return pages;
+
+ /*
+ * The mmap_lock can be held when obtaining the dmabuf reservation lock
+ * which creates a locking cycle with the pages mutex which is held
+ * while obtaining the mmap_lock. This locking path is not present for
+ * IOPT_ADDRESS_DMABUF so split the lock class.
+ */
+ lockdep_set_class(&pages->mutex, &pages_dmabuf_mutex_key);
+
+ /* dmabuf does not use pinned page accounting. */
+ pages->account_mode = IOPT_PAGES_ACCOUNT_NONE;
+ pages->type = IOPT_ADDRESS_DMABUF;
+ pages->dmabuf.start = start - start_byte;
+ INIT_LIST_HEAD(&pages->dmabuf.tracker);
+
+ rc = iopt_map_dmabuf(ictx, pages, dmabuf);
+ if (rc) {
+ iopt_put_pages(pages);
+ return ERR_PTR(rc);
+ }
+
+ return pages;
+}
+
+int iopt_dmabuf_track_domain(struct iopt_pages *pages, struct iopt_area *area,
+ struct iommu_domain *domain)
+{
+ struct iopt_pages_dmabuf_track *track;
+
+ lockdep_assert_held(&pages->mutex);
+ if (WARN_ON(!iopt_is_dmabuf(pages)))
+ return -EINVAL;
+
+ list_for_each_entry(track, &pages->dmabuf.tracker, elm)
+ if (WARN_ON(track->domain == domain && track->area == area))
+ return -EINVAL;
+
+ track = kzalloc(sizeof(*track), GFP_KERNEL);
+ if (!track)
+ return -ENOMEM;
+ track->domain = domain;
+ track->area = area;
+ list_add_tail(&track->elm, &pages->dmabuf.tracker);
+
+ return 0;
+}
+
+void iopt_dmabuf_untrack_domain(struct iopt_pages *pages,
+ struct iopt_area *area,
+ struct iommu_domain *domain)
+{
+ struct iopt_pages_dmabuf_track *track;
+
+ lockdep_assert_held(&pages->mutex);
+ WARN_ON(!iopt_is_dmabuf(pages));
+
+ list_for_each_entry(track, &pages->dmabuf.tracker, elm) {
+ if (track->domain == domain && track->area == area) {
+ list_del(&track->elm);
+ kfree(track);
+ return;
+ }
+ }
+ WARN_ON(true);
+}
+
+int iopt_dmabuf_track_all_domains(struct iopt_area *area,
+ struct iopt_pages *pages)
+{
+ struct iopt_pages_dmabuf_track *track;
+ struct iommu_domain *domain;
+ unsigned long index;
+ int rc;
+
+ list_for_each_entry(track, &pages->dmabuf.tracker, elm)
+ if (WARN_ON(track->area == area))
+ return -EINVAL;
+
+ xa_for_each(&area->iopt->domains, index, domain) {
+ rc = iopt_dmabuf_track_domain(pages, area, domain);
+ if (rc)
+ goto err_untrack;
+ }
+ return 0;
+err_untrack:
+ iopt_dmabuf_untrack_all_domains(area, pages);
+ return rc;
+}
+
+void iopt_dmabuf_untrack_all_domains(struct iopt_area *area,
+ struct iopt_pages *pages)
+{
+ struct iopt_pages_dmabuf_track *track;
+ struct iopt_pages_dmabuf_track *tmp;
+
+ list_for_each_entry_safe(track, tmp, &pages->dmabuf.tracker,
+ elm) {
+ if (track->area == area) {
+ list_del(&track->elm);
+ kfree(track);
+ }
+ }
+}
+
void iopt_release_pages(struct kref *kref)
{
struct iopt_pages *pages = container_of(kref, struct iopt_pages, kref);
@@ -1372,8 +1653,15 @@ void iopt_release_pages(struct kref *kref)
mutex_destroy(&pages->mutex);
put_task_struct(pages->source_task);
free_uid(pages->source_user);
- if (pages->type == IOPT_ADDRESS_FILE)
+ if (iopt_is_dmabuf(pages) && pages->dmabuf.attach) {
+ struct dma_buf *dmabuf = pages->dmabuf.attach->dmabuf;
+
+ dma_buf_detach(dmabuf, pages->dmabuf.attach);
+ dma_buf_put(dmabuf);
+ WARN_ON(!list_empty(&pages->dmabuf.tracker));
+ } else if (pages->type == IOPT_ADDRESS_FILE) {
fput(pages->file);
+ }
kfree(pages);
}
@@ -1451,6 +1739,14 @@ static void __iopt_area_unfill_domain(struct iopt_area *area,
lockdep_assert_held(&pages->mutex);
+ if (iopt_is_dmabuf(pages)) {
+ if (WARN_ON(iopt_dmabuf_revoked(pages)))
+ return;
+ iopt_area_unmap_domain_range(area, domain, start_index,
+ last_index);
+ return;
+ }
+
/*
* For security we must not unpin something that is still DMA mapped,
* so this must unmap any IOVA before we go ahead and unpin the pages.
@@ -1526,6 +1822,9 @@ void iopt_area_unmap_domain(struct iopt_area *area, struct iommu_domain *domain)
void iopt_area_unfill_domain(struct iopt_area *area, struct iopt_pages *pages,
struct iommu_domain *domain)
{
+ if (iopt_dmabuf_revoked(pages))
+ return;
+
__iopt_area_unfill_domain(area, pages, domain,
iopt_area_last_index(area));
}
@@ -1546,6 +1845,9 @@ int iopt_area_fill_domain(struct iopt_area *area, struct iommu_domain *domain)
lockdep_assert_held(&area->pages->mutex);
+ if (iopt_dmabuf_revoked(area->pages))
+ return 0;
+
rc = pfn_reader_first(&pfns, area->pages, iopt_area_index(area),
iopt_area_last_index(area));
if (rc)
@@ -1605,33 +1907,44 @@ int iopt_area_fill_domains(struct iopt_area *area, struct iopt_pages *pages)
return 0;
mutex_lock(&pages->mutex);
- rc = pfn_reader_first(&pfns, pages, iopt_area_index(area),
- iopt_area_last_index(area));
- if (rc)
- goto out_unlock;
+ if (iopt_is_dmabuf(pages)) {
+ rc = iopt_dmabuf_track_all_domains(area, pages);
+ if (rc)
+ goto out_unlock;
+ }
- while (!pfn_reader_done(&pfns)) {
- done_first_end_index = pfns.batch_end_index;
- done_all_end_index = pfns.batch_start_index;
- xa_for_each(&area->iopt->domains, index, domain) {
- rc = batch_to_domain(&pfns.batch, domain, area,
- pfns.batch_start_index);
+ if (!iopt_dmabuf_revoked(pages)) {
+ rc = pfn_reader_first(&pfns, pages, iopt_area_index(area),
+ iopt_area_last_index(area));
+ if (rc)
+ goto out_untrack;
+
+ while (!pfn_reader_done(&pfns)) {
+ done_first_end_index = pfns.batch_end_index;
+ done_all_end_index = pfns.batch_start_index;
+ xa_for_each(&area->iopt->domains, index, domain) {
+ rc = batch_to_domain(&pfns.batch, domain, area,
+ pfns.batch_start_index);
+ if (rc)
+ goto out_unmap;
+ }
+ done_all_end_index = done_first_end_index;
+
+ rc = pfn_reader_next(&pfns);
if (rc)
goto out_unmap;
}
- done_all_end_index = done_first_end_index;
-
- rc = pfn_reader_next(&pfns);
+ rc = pfn_reader_update_pinned(&pfns);
if (rc)
goto out_unmap;
+
+ pfn_reader_destroy(&pfns);
}
- rc = pfn_reader_update_pinned(&pfns);
- if (rc)
- goto out_unmap;
area->storage_domain = xa_load(&area->iopt->domains, 0);
interval_tree_insert(&area->pages_node, &pages->domains_itree);
- goto out_destroy;
+ mutex_unlock(&pages->mutex);
+ return 0;
out_unmap:
pfn_reader_release_pins(&pfns);
@@ -1658,8 +1971,10 @@ out_unmap:
end_index);
}
}
-out_destroy:
pfn_reader_destroy(&pfns);
+out_untrack:
+ if (iopt_is_dmabuf(pages))
+ iopt_dmabuf_untrack_all_domains(area, pages);
out_unlock:
mutex_unlock(&pages->mutex);
return rc;
@@ -1685,16 +2000,22 @@ void iopt_area_unfill_domains(struct iopt_area *area, struct iopt_pages *pages)
if (!area->storage_domain)
goto out_unlock;
- xa_for_each(&iopt->domains, index, domain)
- if (domain != area->storage_domain)
+ xa_for_each(&iopt->domains, index, domain) {
+ if (domain == area->storage_domain)
+ continue;
+
+ if (!iopt_dmabuf_revoked(pages))
iopt_area_unmap_domain_range(
area, domain, iopt_area_index(area),
iopt_area_last_index(area));
+ }
if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
WARN_ON(RB_EMPTY_NODE(&area->pages_node.rb));
interval_tree_remove(&area->pages_node, &pages->domains_itree);
iopt_area_unfill_domain(area, pages, area->storage_domain);
+ if (iopt_is_dmabuf(pages))
+ iopt_dmabuf_untrack_all_domains(area, pages);
area->storage_domain = NULL;
out_unlock:
mutex_unlock(&pages->mutex);
@@ -2031,15 +2352,14 @@ int iopt_pages_rw_access(struct iopt_pages *pages, unsigned long start_byte,
if ((flags & IOMMUFD_ACCESS_RW_WRITE) && !pages->writable)
return -EPERM;
- if (pages->type == IOPT_ADDRESS_FILE)
+ if (iopt_is_dmabuf(pages))
+ return -EINVAL;
+
+ if (pages->type != IOPT_ADDRESS_USER)
return iopt_pages_rw_slow(pages, start_index, last_index,
start_byte % PAGE_SIZE, data, length,
flags);
- if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
- WARN_ON(pages->type != IOPT_ADDRESS_USER))
- return -EINVAL;
-
if (!(flags & IOMMUFD_ACCESS_RW_KTHREAD) && change_mm) {
if (start_index == last_index)
return iopt_pages_rw_page(pages, start_index,
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index de178827a078..5d14dd0fb37d 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -5,6 +5,8 @@
*/
#include <linux/anon_inodes.h>
#include <linux/debugfs.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-resv.h>
#include <linux/fault-inject.h>
#include <linux/file.h>
#include <linux/iommu.h>
@@ -2031,6 +2033,140 @@ void iommufd_selftest_destroy(struct iommufd_object *obj)
}
}
+struct iommufd_test_dma_buf {
+ void *memory;
+ size_t length;
+ bool revoked;
+};
+
+static int iommufd_test_dma_buf_attach(struct dma_buf *dmabuf,
+ struct dma_buf_attachment *attachment)
+{
+ return 0;
+}
+
+static void iommufd_test_dma_buf_detach(struct dma_buf *dmabuf,
+ struct dma_buf_attachment *attachment)
+{
+}
+
+static struct sg_table *
+iommufd_test_dma_buf_map(struct dma_buf_attachment *attachment,
+ enum dma_data_direction dir)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static void iommufd_test_dma_buf_unmap(struct dma_buf_attachment *attachment,
+ struct sg_table *sgt,
+ enum dma_data_direction dir)
+{
+}
+
+static void iommufd_test_dma_buf_release(struct dma_buf *dmabuf)
+{
+ struct iommufd_test_dma_buf *priv = dmabuf->priv;
+
+ kfree(priv->memory);
+ kfree(priv);
+}
+
+static const struct dma_buf_ops iommufd_test_dmabuf_ops = {
+ .attach = iommufd_test_dma_buf_attach,
+ .detach = iommufd_test_dma_buf_detach,
+ .map_dma_buf = iommufd_test_dma_buf_map,
+ .release = iommufd_test_dma_buf_release,
+ .unmap_dma_buf = iommufd_test_dma_buf_unmap,
+};
+
+int iommufd_test_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+ struct dma_buf_phys_vec *phys)
+{
+ struct iommufd_test_dma_buf *priv = attachment->dmabuf->priv;
+
+ dma_resv_assert_held(attachment->dmabuf->resv);
+
+ if (attachment->dmabuf->ops != &iommufd_test_dmabuf_ops)
+ return -EOPNOTSUPP;
+
+ if (priv->revoked)
+ return -ENODEV;
+
+ phys->paddr = virt_to_phys(priv->memory);
+ phys->len = priv->length;
+ return 0;
+}
+
+static int iommufd_test_dmabuf_get(struct iommufd_ucmd *ucmd,
+ unsigned int open_flags,
+ size_t len)
+{
+ DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+ struct iommufd_test_dma_buf *priv;
+ struct dma_buf *dmabuf;
+ int rc;
+
+ len = ALIGN(len, PAGE_SIZE);
+ if (len == 0 || len > PAGE_SIZE * 512)
+ return -EINVAL;
+
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->length = len;
+ priv->memory = kzalloc(len, GFP_KERNEL);
+ if (!priv->memory) {
+ rc = -ENOMEM;
+ goto err_free;
+ }
+
+ exp_info.ops = &iommufd_test_dmabuf_ops;
+ exp_info.size = len;
+ exp_info.flags = open_flags;
+ exp_info.priv = priv;
+
+ dmabuf = dma_buf_export(&exp_info);
+ if (IS_ERR(dmabuf)) {
+ rc = PTR_ERR(dmabuf);
+ goto err_free;
+ }
+
+ return dma_buf_fd(dmabuf, open_flags);
+
+err_free:
+ kfree(priv->memory);
+ kfree(priv);
+ return rc;
+}
+
+static int iommufd_test_dmabuf_revoke(struct iommufd_ucmd *ucmd, int fd,
+ bool revoked)
+{
+ struct iommufd_test_dma_buf *priv;
+ struct dma_buf *dmabuf;
+ int rc = 0;
+
+ dmabuf = dma_buf_get(fd);
+ if (IS_ERR(dmabuf))
+ return PTR_ERR(dmabuf);
+
+ if (dmabuf->ops != &iommufd_test_dmabuf_ops) {
+ rc = -EOPNOTSUPP;
+ goto err_put;
+ }
+
+ priv = dmabuf->priv;
+ dma_resv_lock(dmabuf->resv, NULL);
+ priv->revoked = revoked;
+ dma_buf_move_notify(dmabuf);
+ dma_resv_unlock(dmabuf->resv);
+
+err_put:
+ dma_buf_put(dmabuf);
+ return rc;
+}
+
int iommufd_test(struct iommufd_ucmd *ucmd)
{
struct iommu_test_cmd *cmd = ucmd->cmd;
@@ -2109,6 +2245,13 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
return iommufd_test_pasid_detach(ucmd, cmd);
case IOMMU_TEST_OP_PASID_CHECK_HWPT:
return iommufd_test_pasid_check_hwpt(ucmd, cmd);
+ case IOMMU_TEST_OP_DMABUF_GET:
+ return iommufd_test_dmabuf_get(ucmd, cmd->dmabuf_get.open_flags,
+ cmd->dmabuf_get.length);
+ case IOMMU_TEST_OP_DMABUF_REVOKE:
+ return iommufd_test_dmabuf_revoke(ucmd,
+ cmd->dmabuf_revoke.dmabuf_fd,
+ cmd->dmabuf_revoke.revoked);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 78e108e47254..981a76b6b7c0 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -25,12 +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 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 +204,8 @@ 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),
@@ -228,56 +228,136 @@ 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. The lifetime
+ * of the provider (and of course the MMIO) is bound to the lifetime of the
+ * driver. A driver calling this function must ensure that all references to the
+ * provider, and any DMA mappings created for any MMIO, are all cleaned up
+ * before the driver remove() completes.
+ *
+ * Since P2P is almost always shared with a second driver this means some system
+ * to notify, invalidate and revoke the MMIO's DMA must be in place to use this
+ * function. For example a revoke can be built using DMABUF.
+ */
+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);
+ if (WARN_ON(!p2p))
+ /* Someone forgot to call to pcim_p2pdma_init() before */
+ return NULL;
+
+ 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)
{
- 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);
}
@@ -295,6 +375,7 @@ 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 +393,21 @@ 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)
@@ -328,10 +419,7 @@ 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->provider = pdev;
- p2p_pgmap->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)) {
@@ -340,7 +428,7 @@ 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 +1060,26 @@ 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)
+/**
+ * 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 *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 +1088,7 @@ 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 +1096,7 @@ 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 +1104,13 @@ 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/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..53f59226ae01 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -2,6 +2,7 @@
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
+vfio-pci-core-$(CONFIG_VFIO_PCI_DMABUF) += vfio_pci_dmabuf.o
obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
vfio-pci-y := vfio_pci.o
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index e346392b72f6..f19a679b5bf2 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -7,6 +7,7 @@
#include <linux/vfio_pci_core.h>
#include <linux/delay.h>
#include <linux/jiffies.h>
+#include <linux/pci-p2pdma.h>
/*
* The device memory usable to the workloads running in the VM is cached
@@ -683,6 +684,50 @@ nvgrace_gpu_write(struct vfio_device *core_vdev,
return vfio_pci_core_write(core_vdev, buf, count, ppos);
}
+static int nvgrace_get_dmabuf_phys(struct vfio_pci_core_device *core_vdev,
+ struct p2pdma_provider **provider,
+ unsigned int region_index,
+ struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t nr_ranges)
+{
+ struct nvgrace_gpu_pci_core_device *nvdev = container_of(
+ core_vdev, struct nvgrace_gpu_pci_core_device, core_device);
+ struct pci_dev *pdev = core_vdev->pdev;
+ struct mem_region *mem_region;
+
+ /*
+ * if (nvdev->resmem.memlength && region_index == RESMEM_REGION_INDEX) {
+ * The P2P properties of the non-BAR memory is the same as the
+ * BAR memory, so just use the provider for index 0. Someday
+ * when CXL gets P2P support we could create CXLish providers
+ * for the non-BAR memory.
+ * } else if (region_index == USEMEM_REGION_INDEX) {
+ * This is actually cachable memory and isn't treated as P2P in
+ * the chip. For now we have no way to push cachable memory
+ * through everything and the Grace HW doesn't care what caching
+ * attribute is programmed into the SMMU. So use BAR 0.
+ * }
+ */
+ mem_region = nvgrace_gpu_memregion(region_index, nvdev);
+ if (mem_region) {
+ *provider = pcim_p2pdma_provider(pdev, 0);
+ if (!*provider)
+ return -EINVAL;
+ return vfio_pci_core_fill_phys_vec(phys_vec, dma_ranges,
+ nr_ranges,
+ mem_region->memphys,
+ mem_region->memlength);
+ }
+
+ return vfio_pci_core_get_dmabuf_phys(core_vdev, provider, region_index,
+ phys_vec, dma_ranges, nr_ranges);
+}
+
+static const struct vfio_pci_device_ops nvgrace_gpu_pci_dev_ops = {
+ .get_dmabuf_phys = nvgrace_get_dmabuf_phys,
+};
+
static const struct vfio_device_ops nvgrace_gpu_pci_ops = {
.name = "nvgrace-gpu-vfio-pci",
.init = vfio_pci_core_init_dev,
@@ -703,6 +748,10 @@ static const struct vfio_device_ops nvgrace_gpu_pci_ops = {
.detach_ioas = vfio_iommufd_physical_detach_ioas,
};
+static const struct vfio_pci_device_ops nvgrace_gpu_pci_dev_core_ops = {
+ .get_dmabuf_phys = vfio_pci_core_get_dmabuf_phys,
+};
+
static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = {
.name = "nvgrace-gpu-vfio-pci-core",
.init = vfio_pci_core_init_dev,
@@ -965,6 +1014,9 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev,
memphys, memlength);
if (ret)
goto out_put_vdev;
+ nvdev->core_device.pci_ops = &nvgrace_gpu_pci_dev_ops;
+ } else {
+ nvdev->core_device.pci_ops = &nvgrace_gpu_pci_dev_core_ops;
}
ret = vfio_pci_core_register_device(&nvdev->core_device);
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index ac10f14417f2..6d41cf26b539 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -147,6 +147,10 @@ static const struct vfio_device_ops vfio_pci_ops = {
.pasid_detach_ioas = vfio_iommufd_physical_pasid_detach_ioas,
};
+static const struct vfio_pci_device_ops vfio_pci_dev_ops = {
+ .get_dmabuf_phys = vfio_pci_core_get_dmabuf_phys,
+};
+
static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct vfio_pci_core_device *vdev;
@@ -161,6 +165,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return PTR_ERR(vdev);
dev_set_drvdata(&pdev->dev, vdev);
+ vdev->pci_ops = &vfio_pci_dev_ops;
ret = vfio_pci_core_register_device(vdev);
if (ret)
goto out_put_vdev;
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 7dcf5439dedc..9449cf44c18a 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -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
@@ -286,6 +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;
@@ -299,11 +302,9 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev,
return 0;
}
-static int vfio_pci_core_pm_entry(struct vfio_device *device, u32 flags,
+static int vfio_pci_core_pm_entry(struct vfio_pci_core_device *vdev, u32 flags,
void __user *arg, size_t argsz)
{
- struct vfio_pci_core_device *vdev =
- container_of(device, struct vfio_pci_core_device, vdev);
int ret;
ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0);
@@ -320,12 +321,10 @@ static int vfio_pci_core_pm_entry(struct vfio_device *device, u32 flags,
}
static int vfio_pci_core_pm_entry_with_wakeup(
- struct vfio_device *device, u32 flags,
+ struct vfio_pci_core_device *vdev, u32 flags,
struct vfio_device_low_power_entry_with_wakeup __user *arg,
size_t argsz)
{
- struct vfio_pci_core_device *vdev =
- container_of(device, struct vfio_pci_core_device, vdev);
struct vfio_device_low_power_entry_with_wakeup entry;
struct eventfd_ctx *efdctx;
int ret;
@@ -373,14 +372,14 @@ 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);
}
-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);
@@ -695,6 +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);
@@ -1227,7 +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;
@@ -1473,11 +1477,10 @@ 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 +1507,21 @@ 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);
+ case VFIO_DEVICE_FEATURE_DMA_BUF:
+ return vfio_pci_core_feature_dma_buf(vdev, flags, arg, argsz);
default:
return -ENOTTY;
}
@@ -2085,6 +2093,7 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev)
{
struct vfio_pci_core_device *vdev =
container_of(core_vdev, struct vfio_pci_core_device, vdev);
+ int ret;
vdev->pdev = to_pci_dev(core_vdev->dev);
vdev->irq_type = VFIO_PCI_NUM_IRQS;
@@ -2094,6 +2103,10 @@ 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);
+ ret = pcim_p2pdma_init(vdev->pdev);
+ if (ret && ret != -EOPNOTSUPP)
+ return ret;
+ INIT_LIST_HEAD(&vdev->dmabufs);
init_rwsem(&vdev->memory_lock);
xa_init(&vdev->ctx);
@@ -2458,6 +2471,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
break;
}
+ vfio_pci_dma_buf_move(vdev, true);
vfio_pci_zap_bars(vdev);
}
@@ -2486,8 +2500,11 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
err_undo:
list_for_each_entry_from_reverse(vdev, &dev_set->device_list,
- vdev.dev_set_list)
+ vdev.dev_set_list) {
+ if (vdev->vdev.open_count && __vfio_pci_memory_enabled(vdev))
+ vfio_pci_dma_buf_move(vdev, false);
up_write(&vdev->memory_lock);
+ }
list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list)
pm_runtime_put(&vdev->pdev->dev);
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
new file mode 100644
index 000000000000..d4d0f7d08c53
--- /dev/null
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES.
+ */
+#include <linux/dma-buf-mapping.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 dma_buf_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;
+
+ return 0;
+}
+
+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;
+
+ dma_resv_assert_held(priv->dmabuf->resv);
+
+ if (priv->revoked)
+ return ERR_PTR(-ENODEV);
+
+ return dma_buf_phys_vec_to_sgt(attachment, priv->provider,
+ priv->phys_vec, priv->nr_ranges,
+ priv->size, dir);
+}
+
+static void vfio_pci_dma_buf_unmap(struct dma_buf_attachment *attachment,
+ struct sg_table *sgt,
+ enum dma_data_direction dir)
+{
+ dma_buf_free_sgt(attachment, sgt, dir);
+}
+
+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,
+ .map_dma_buf = vfio_pci_dma_buf_map,
+ .unmap_dma_buf = vfio_pci_dma_buf_unmap,
+ .release = vfio_pci_dma_buf_release,
+};
+
+/*
+ * This is a temporary "private interconnect" between VFIO DMABUF and iommufd.
+ * It allows the two co-operating drivers to exchange the physical address of
+ * the BAR. This is to be replaced with a formal DMABUF system for negotiated
+ * interconnect types.
+ *
+ * If this function succeeds the following are true:
+ * - There is one physical range and it is pointing to MMIO
+ * - When move_notify is called it means revoke, not move, vfio_dma_buf_map
+ * will fail if it is currently revoked
+ */
+int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+ struct dma_buf_phys_vec *phys)
+{
+ struct vfio_pci_dma_buf *priv;
+
+ dma_resv_assert_held(attachment->dmabuf->resv);
+
+ if (attachment->dmabuf->ops != &vfio_pci_dmabuf_ops)
+ return -EOPNOTSUPP;
+
+ priv = attachment->dmabuf->priv;
+ if (priv->revoked)
+ return -ENODEV;
+
+ /* More than one range to iommufd will require proper DMABUF support */
+ if (priv->nr_ranges != 1)
+ return -EOPNOTSUPP;
+
+ *phys = priv->phys_vec[0];
+ return 0;
+}
+EXPORT_SYMBOL_FOR_MODULES(vfio_pci_dma_buf_iommufd_map, "iommufd");
+
+int vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t nr_ranges, phys_addr_t start,
+ phys_addr_t len)
+{
+ phys_addr_t max_addr;
+ unsigned int i;
+
+ max_addr = start + len;
+ for (i = 0; i < nr_ranges; i++) {
+ phys_addr_t end;
+
+ if (!dma_ranges[i].length)
+ return -EINVAL;
+
+ if (check_add_overflow(start, dma_ranges[i].offset,
+ &phys_vec[i].paddr) ||
+ check_add_overflow(phys_vec[i].paddr,
+ dma_ranges[i].length, &end))
+ return -EOVERFLOW;
+ if (end > max_addr)
+ return -EINVAL;
+
+ phys_vec[i].len = dma_ranges[i].length;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_pci_core_fill_phys_vec);
+
+int vfio_pci_core_get_dmabuf_phys(struct vfio_pci_core_device *vdev,
+ struct p2pdma_provider **provider,
+ unsigned int region_index,
+ struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t nr_ranges)
+{
+ struct pci_dev *pdev = vdev->pdev;
+
+ *provider = pcim_p2pdma_provider(pdev, region_index);
+ if (!*provider)
+ return -EINVAL;
+
+ return vfio_pci_core_fill_phys_vec(
+ phys_vec, dma_ranges, nr_ranges,
+ pci_resource_start(pdev, region_index),
+ pci_resource_len(pdev, region_index));
+}
+EXPORT_SYMBOL_GPL(vfio_pci_core_get_dmabuf_phys);
+
+static int validate_dmabuf_input(struct vfio_device_feature_dma_buf *dma_buf,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t *lengthp)
+{
+ size_t length = 0;
+ u32 i;
+
+ 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(length, len, &length))
+ return -EINVAL;
+ }
+
+ /*
+ * dma_iova_try_alloc() will WARN on if userspace proposes a size that
+ * is too big, eg with lots of ranges.
+ */
+ if ((u64)(length) & DMA_IOVA_USE_SWIOTLB)
+ return -EINVAL;
+
+ *lengthp = length;
+ 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 vfio_pci_dma_buf *priv;
+ size_t length;
+ int ret;
+
+ if (!vdev->pci_ops || !vdev->pci_ops->get_dmabuf_phys)
+ return -EOPNOTSUPP;
+
+ 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 || get_dma_buf.flags)
+ return -EINVAL;
+
+ /*
+ * For PCI the region_index is the BAR number like everything else.
+ */
+ if (get_dma_buf.region_index >= VFIO_PCI_ROM_REGION_INDEX)
+ return -ENODEV;
+
+ 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(&get_dma_buf, dma_ranges, &length);
+ 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;
+ priv->nr_ranges = get_dma_buf.nr_ranges;
+ priv->size = length;
+ ret = vdev->pci_ops->get_dmabuf_phys(vdev, &priv->provider,
+ get_dma_buf.region_index,
+ priv->phys_vec, dma_ranges,
+ priv->nr_ranges);
+ if (ret)
+ goto err_free_phys;
+
+ 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.
+ */
+ ret = dma_buf_fd(priv->dmabuf, get_dma_buf.open_flags);
+ if (ret < 0)
+ goto err_dma_buf;
+ return ret;
+
+err_dma_buf:
+ dma_buf_put(priv->dmabuf);
+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);
+ }
+ fput(priv->dmabuf->file);
+ }
+}
+
+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);
+ fput(priv->dmabuf->file);
+ }
+ 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/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 38c8e9350a60..9aa4a5d081e8 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -172,11 +172,13 @@ void vfio_device_put_registration(struct vfio_device *device)
if (refcount_dec_and_test(&device->refcount))
complete(&device->comp);
}
+EXPORT_SYMBOL_GPL(vfio_device_put_registration);
bool vfio_device_try_get_registration(struct vfio_device *device)
{
return refcount_inc_not_zero(&device->refcount);
}
+EXPORT_SYMBOL_GPL(vfio_device_try_get_registration);
/*
* VFIO driver API
diff --git a/include/linux/dma-buf-mapping.h b/include/linux/dma-buf-mapping.h
new file mode 100644
index 000000000000..a3c0ce2d3a42
--- /dev/null
+++ b/include/linux/dma-buf-mapping.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * DMA BUF Mapping Helpers
+ *
+ */
+#ifndef __DMA_BUF_MAPPING_H__
+#define __DMA_BUF_MAPPING_H__
+#include <linux/dma-buf.h>
+
+struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach,
+ struct p2pdma_provider *provider,
+ struct dma_buf_phys_vec *phys_vec,
+ size_t nr_ranges, size_t size,
+ enum dma_data_direction dir);
+void dma_buf_free_sgt(struct dma_buf_attachment *attach, struct sg_table *sgt,
+ enum dma_data_direction dir);
+#endif
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index d58e329ac0e7..0bc492090237 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -22,6 +22,7 @@
#include <linux/fs.h>
#include <linux/dma-fence.h>
#include <linux/wait.h>
+#include <linux/pci-p2pdma.h>
struct device;
struct dma_buf;
@@ -531,6 +532,16 @@ struct dma_buf_export_info {
};
/**
+ * struct dma_buf_phys_vec - describe continuous chunk of memory
+ * @paddr: physical address of that chunk
+ * @len: Length of this chunk
+ */
+struct dma_buf_phys_vec {
+ phys_addr_t paddr;
+ size_t len;
+};
+
+/**
* DEFINE_DMA_BUF_EXPORT_INFO - helper macro for exporters
* @name: export-info name
*
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
index 951f81a38f3a..517e121d2598 100644
--- a/include/linux/pci-p2pdma.h
+++ b/include/linux/pci-p2pdma.h
@@ -16,7 +16,58 @@
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;
+};
+
+enum pci_p2pdma_map_type {
+ /*
+ * PCI_P2PDMA_MAP_UNKNOWN: Used internally as an initial state before
+ * the mapping type has been calculated. Exported routines for the API
+ * will never return this value.
+ */
+ PCI_P2PDMA_MAP_UNKNOWN = 0,
+
+ /*
+ * Not a PCI P2PDMA transfer.
+ */
+ PCI_P2PDMA_MAP_NONE,
+
+ /*
+ * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
+ * traverse the host bridge and the host bridge is not in the
+ * allowlist. DMA Mapping routines should return an error when
+ * this is returned.
+ */
+ PCI_P2PDMA_MAP_NOT_SUPPORTED,
+
+ /*
+ * PCI_P2PDMA_MAP_BUS_ADDR: Indicates that two devices can talk to
+ * each other directly through a PCI switch and the transaction will
+ * not traverse the host bridge. Such a mapping should program
+ * the DMA engine with PCI bus addresses.
+ */
+ PCI_P2PDMA_MAP_BUS_ADDR,
+
+ /*
+ * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
+ * to each other, but the transaction traverses a host bridge on the
+ * allowlist. In this case, a normal mapping either with CPU physical
+ * addresses (in the case of dma-direct) or IOVA addresses (in the
+ * case of IOMMUs) should be used to program the DMA engine.
+ */
+ PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
+};
+
#ifdef CONFIG_PCI_P2PDMA
+int pcim_p2pdma_init(struct pci_dev *pdev);
+struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar);
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,
@@ -33,7 +84,18 @@ int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev,
bool *use_p2pdma);
ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev,
bool use_p2pdma);
+enum pci_p2pdma_map_type pci_p2pdma_map_type(struct p2pdma_provider *provider,
+ struct device *dev);
#else /* CONFIG_PCI_P2PDMA */
+static inline int pcim_p2pdma_init(struct pci_dev *pdev)
+{
+ return -EOPNOTSUPP;
+}
+static inline struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev,
+ int bar)
+{
+ return NULL;
+}
static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar,
size_t size, u64 offset)
{
@@ -85,6 +147,11 @@ static inline ssize_t pci_p2pdma_enable_show(char *page,
{
return sprintf(page, "none\n");
}
+static inline enum pci_p2pdma_map_type
+pci_p2pdma_map_type(struct p2pdma_provider *provider, struct device *dev)
+{
+ return PCI_P2PDMA_MAP_NOT_SUPPORTED;
+}
#endif /* CONFIG_PCI_P2PDMA */
@@ -99,51 +166,12 @@ static inline struct pci_dev *pci_p2pmem_find(struct device *client)
return pci_p2pmem_find_many(&client, 1);
}
-enum pci_p2pdma_map_type {
- /*
- * PCI_P2PDMA_MAP_UNKNOWN: Used internally as an initial state before
- * the mapping type has been calculated. Exported routines for the API
- * will never return this value.
- */
- PCI_P2PDMA_MAP_UNKNOWN = 0,
-
- /*
- * Not a PCI P2PDMA transfer.
- */
- PCI_P2PDMA_MAP_NONE,
-
- /*
- * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
- * traverse the host bridge and the host bridge is not in the
- * allowlist. DMA Mapping routines should return an error when
- * this is returned.
- */
- PCI_P2PDMA_MAP_NOT_SUPPORTED,
-
- /*
- * PCI_P2PDMA_MAP_BUS_ADDR: Indicates that two devices can talk to
- * each other directly through a PCI switch and the transaction will
- * not traverse the host bridge. Such a mapping should program
- * the DMA engine with PCI bus addresses.
- */
- PCI_P2PDMA_MAP_BUS_ADDR,
-
- /*
- * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
- * to each other, but the transaction traverses a host bridge on the
- * allowlist. In this case, a normal mapping either with CPU physical
- * addresses (in the case of dma-direct) or IOVA addresses (in the
- * case of IOMMUs) should be used to program the DMA engine.
- */
- PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
-};
-
struct pci_p2pdma_map_state {
- struct 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 +190,7 @@ 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;
@@ -172,16 +199,15 @@ 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->bus_off;
+ return paddr + provider->bus_offset;
}
#endif /* _LINUX_PCI_P2P_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index eb563f538dee..217ba4ef1752 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -297,6 +297,8 @@ static inline void vfio_put_device(struct vfio_device *device)
int vfio_register_group_dev(struct vfio_device *device);
int vfio_register_emulated_iommu_dev(struct vfio_device *device);
void vfio_unregister_group_dev(struct vfio_device *device);
+bool vfio_device_try_get_registration(struct vfio_device *device);
+void vfio_device_put_registration(struct vfio_device *device);
int vfio_assign_device_set(struct vfio_device *device, void *set_id);
unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index f541044e42a2..6a3074f2cf1c 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -26,6 +26,9 @@
struct vfio_pci_core_device;
struct vfio_pci_region;
+struct p2pdma_provider;
+struct dma_buf_phys_vec;
+struct dma_buf_attachment;
struct vfio_pci_regops {
ssize_t (*rw)(struct vfio_pci_core_device *vdev, char __user *buf,
@@ -49,9 +52,48 @@ struct vfio_pci_region {
u32 flags;
};
+struct vfio_pci_device_ops {
+ int (*get_dmabuf_phys)(struct vfio_pci_core_device *vdev,
+ struct p2pdma_provider **provider,
+ unsigned int region_index,
+ struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t nr_ranges);
+};
+
+#if IS_ENABLED(CONFIG_VFIO_PCI_DMABUF)
+int vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t nr_ranges, phys_addr_t start,
+ phys_addr_t len);
+int vfio_pci_core_get_dmabuf_phys(struct vfio_pci_core_device *vdev,
+ struct p2pdma_provider **provider,
+ unsigned int region_index,
+ struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t nr_ranges);
+#else
+static inline int
+vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges,
+ size_t nr_ranges, phys_addr_t start,
+ phys_addr_t len)
+{
+ return -EINVAL;
+}
+static inline int vfio_pci_core_get_dmabuf_phys(
+ struct vfio_pci_core_device *vdev, struct p2pdma_provider **provider,
+ unsigned int region_index, struct dma_buf_phys_vec *phys_vec,
+ struct vfio_region_dma_range *dma_ranges, size_t nr_ranges)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
struct vfio_pci_core_device {
struct vfio_device vdev;
struct pci_dev *pdev;
+ const struct vfio_pci_device_ops *pci_ops;
void __iomem *barmap[PCI_STD_NUM_BARS];
bool bar_mmap_supported[PCI_STD_NUM_BARS];
u8 *pci_config_map;
@@ -94,6 +136,7 @@ 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 */
@@ -161,4 +204,7 @@ VFIO_IOREAD_DECLARATION(32)
VFIO_IOREAD_DECLARATION(64)
#endif
+int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+ struct dma_buf_phys_vec *phys);
+
#endif /* VFIO_PCI_CORE_H */
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 75100bf009ba..ac2329f24141 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/ioctl.h>
+#include <linux/stddef.h>
#define VFIO_API_VERSION 0
@@ -1478,6 +1479,33 @@ 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.
+ *
+ * flags should be 0.
+ *
+ * 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[] __counted_by(nr_ranges);
+};
+
/* -------- API for Type1 VFIO IOMMU -------- */
/**
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 1f9ee9759426..d8b3dfc598b2 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -479,8 +479,8 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
}
break;
case PCI_P2PDMA_MAP_BUS_ADDR:
- sg->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state,
- sg_phys(sg));
+ sg->dma_address = pci_p2pdma_bus_addr_map(
+ p2pdma_state.mem, sg_phys(sg));
sg_dma_mark_bus_address(sg);
continue;
default:
diff --git a/mm/hmm.c b/mm/hmm.c
index 87562914670a..9bf0b831a029 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -811,7 +811,7 @@ 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;
}
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index bb4d33dde3c8..44eb2e1366eb 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -1574,6 +1574,49 @@ TEST_F(iommufd_ioas, copy_sweep)
test_ioctl_destroy(dst_ioas_id);
}
+TEST_F(iommufd_ioas, dmabuf_simple)
+{
+ size_t buf_size = PAGE_SIZE*4;
+ __u64 iova;
+ int dfd;
+
+ test_cmd_get_dmabuf(buf_size, &dfd);
+ test_err_ioctl_ioas_map_file(EINVAL, dfd, 0, 0, &iova);
+ test_err_ioctl_ioas_map_file(EINVAL, dfd, buf_size, buf_size, &iova);
+ test_err_ioctl_ioas_map_file(EINVAL, dfd, 0, buf_size + 1, &iova);
+ test_ioctl_ioas_map_file(dfd, 0, buf_size, &iova);
+
+ close(dfd);
+}
+
+TEST_F(iommufd_ioas, dmabuf_revoke)
+{
+ size_t buf_size = PAGE_SIZE*4;
+ __u32 hwpt_id;
+ __u64 iova;
+ __u64 iova2;
+ int dfd;
+
+ test_cmd_get_dmabuf(buf_size, &dfd);
+ test_ioctl_ioas_map_file(dfd, 0, buf_size, &iova);
+ test_cmd_revoke_dmabuf(dfd, true);
+
+ if (variant->mock_domains)
+ test_cmd_hwpt_alloc(self->device_id, self->ioas_id, 0,
+ &hwpt_id);
+
+ test_err_ioctl_ioas_map_file(ENODEV, dfd, 0, buf_size, &iova2);
+
+ test_cmd_revoke_dmabuf(dfd, false);
+ test_ioctl_ioas_map_file(dfd, 0, buf_size, &iova2);
+
+ /* Restore the iova back */
+ test_ioctl_ioas_unmap(iova, buf_size);
+ test_ioctl_ioas_map_fixed_file(dfd, 0, buf_size, iova);
+
+ close(dfd);
+}
+
FIXTURE(iommufd_mock_domain)
{
int fd;
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index 9f472c20c190..55c285dbbf52 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -548,6 +548,39 @@ static int _test_cmd_destroy_access_pages(int fd, unsigned int access_id,
EXPECT_ERRNO(_errno, _test_cmd_destroy_access_pages( \
self->fd, access_id, access_pages_id))
+static int _test_cmd_get_dmabuf(int fd, size_t len, int *out_fd)
+{
+ struct iommu_test_cmd cmd = {
+ .size = sizeof(cmd),
+ .op = IOMMU_TEST_OP_DMABUF_GET,
+ .dmabuf_get = { .length = len, .open_flags = O_CLOEXEC },
+ };
+
+ *out_fd = ioctl(fd, IOMMU_TEST_CMD, &cmd);
+ if (*out_fd < 0)
+ return -1;
+ return 0;
+}
+#define test_cmd_get_dmabuf(len, out_fd) \
+ ASSERT_EQ(0, _test_cmd_get_dmabuf(self->fd, len, out_fd))
+
+static int _test_cmd_revoke_dmabuf(int fd, int dmabuf_fd, bool revoked)
+{
+ struct iommu_test_cmd cmd = {
+ .size = sizeof(cmd),
+ .op = IOMMU_TEST_OP_DMABUF_REVOKE,
+ .dmabuf_revoke = { .dmabuf_fd = dmabuf_fd, .revoked = revoked },
+ };
+ int ret;
+
+ ret = ioctl(fd, IOMMU_TEST_CMD, &cmd);
+ if (ret < 0)
+ return -1;
+ return 0;
+}
+#define test_cmd_revoke_dmabuf(dmabuf_fd, revoke) \
+ ASSERT_EQ(0, _test_cmd_revoke_dmabuf(self->fd, dmabuf_fd, revoke))
+
static int _test_ioctl_destroy(int fd, unsigned int id)
{
struct iommu_destroy cmd = {
@@ -718,6 +751,17 @@ static int _test_ioctl_ioas_map_file(int fd, unsigned int ioas_id, int mfd,
self->fd, ioas_id, mfd, start, length, iova_p, \
IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE))
+#define test_ioctl_ioas_map_fixed_file(mfd, start, length, iova) \
+ ({ \
+ __u64 __iova = iova; \
+ ASSERT_EQ(0, _test_ioctl_ioas_map_file( \
+ self->fd, self->ioas_id, mfd, start, \
+ length, &__iova, \
+ IOMMU_IOAS_MAP_FIXED_IOVA | \
+ IOMMU_IOAS_MAP_WRITEABLE | \
+ IOMMU_IOAS_MAP_READABLE)); \
+ })
+
static int _test_ioctl_set_temp_memory_limit(int fd, unsigned int limit)
{
struct iommu_test_cmd memlimit_cmd = {