public inbox for linux-media@vger.kernel.org
 help / color / mirror / Atom feed
From: Matt Evans <mattev@meta.com>
To: Alex Williamson <alex@shazbot.org>,
	Leon Romanovsky <leon@kernel.org>,
	Jason Gunthorpe <jgg@nvidia.com>, Alex Mastro <amastro@fb.com>,
	Mahmoud Adam <mngyadam@amazon.de>,
	David Matlack <dmatlack@google.com>
Cc: "Björn Töpel" <bjorn@kernel.org>,
	"Sumit Semwal" <sumit.semwal@linaro.org>,
	"Christian König" <christian.koenig@amd.com>,
	"Kevin Tian" <kevin.tian@intel.com>,
	"Ankit Agrawal" <ankita@nvidia.com>,
	"Pranjal Shrivastava" <praan@google.com>,
	"Alistair Popple" <apopple@nvidia.com>,
	"Vivek Kasireddy" <vivek.kasireddy@intel.com>,
	linux-kernel@vger.kernel.org, linux-media@vger.kernel.org,
	dri-devel@lists.freedesktop.org, linaro-mm-sig@lists.linaro.org,
	kvm@vger.kernel.org
Subject: [RFC v2 PATCH 07/10] vfio/pci: Support mmap() of a VFIO DMABUF
Date: Thu, 12 Mar 2026 11:46:05 -0700	[thread overview]
Message-ID: <20260312184613.3710705-8-mattev@meta.com> (raw)
In-Reply-To: <20260312184613.3710705-1-mattev@meta.com>

A VFIO DMABUF can export a subset of a BAR to userspace by fd; add
support for mmap() of this fd.  This provides another route for a
process to map BARs, except one where the process can only map a specific
subset of a BAR represented by the exported DMABUF.

mmap() support enables userspace driver designs that safely delegate
access to BAR sub-ranges to other client processes by sharing a DMABUF
fd, without having to share the (omnipotent) VFIO device fd with them.

Since the main VFIO BAR mmap() path is now DMABUF-aware, this path
reuses the existing vm_ops.

Signed-off-by: Matt Evans <mattev@meta.com>
---
 drivers/vfio/pci/vfio_pci_core.c   |  2 +-
 drivers/vfio/pci/vfio_pci_dmabuf.c | 28 ++++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_priv.h   |  2 ++
 3 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 9e9ad97c2f7f..4f411a0b980c 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1712,7 +1712,7 @@ static vm_fault_t vfio_pci_mmap_page_fault(struct vm_fault *vmf)
 	return vfio_pci_mmap_huge_fault(vmf, 0);
 }
 
-static const struct vm_operations_struct vfio_pci_mmap_ops = {
+const struct vm_operations_struct vfio_pci_mmap_ops = {
 	.fault = vfio_pci_mmap_page_fault,
 #ifdef CONFIG_ARCH_SUPPORTS_HUGE_PFNMAP
 	.huge_fault = vfio_pci_mmap_huge_fault,
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 197f50365ee1..ab665db66904 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -26,6 +26,33 @@ static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,
 
 	return 0;
 }
+
+static int vfio_pci_dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+	struct vfio_pci_dma_buf *priv = dmabuf->priv;
+	u64 req_len, req_start;
+
+	if (priv->revoked)
+		return -ENODEV;
+	if ((vma->vm_flags & VM_SHARED) == 0)
+		return -EINVAL;
+
+	req_len = vma->vm_end - vma->vm_start;
+	req_start = vma->vm_pgoff << PAGE_SHIFT;
+	if (req_start + req_len > priv->size)
+		return -EINVAL;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+
+	/* See comments in vfio_pci_core_mmap() re VM_ALLOW_ANY_UNCACHED. */
+	vm_flags_set(vma, VM_ALLOW_ANY_UNCACHED | VM_IO | VM_PFNMAP |
+				  VM_DONTEXPAND | VM_DONTDUMP);
+	vma->vm_private_data = priv;
+	vma->vm_ops = &vfio_pci_mmap_ops;
+
+	return 0;
+}
 #endif /* CONFIG_VFIO_PCI_DMABUF */
 
 static void vfio_pci_dma_buf_done(struct kref *kref)
@@ -93,6 +120,7 @@ static void vfio_pci_dma_buf_release(struct dma_buf *dmabuf)
 static const struct dma_buf_ops vfio_pci_dmabuf_ops = {
 #ifdef CONFIG_VFIO_PCI_DMABUF
 	.attach = vfio_pci_dma_buf_attach,
+	.mmap = vfio_pci_dma_buf_mmap,
 #endif
 	.map_dma_buf = vfio_pci_dma_buf_map,
 	.unmap_dma_buf = vfio_pci_dma_buf_unmap,
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index e201c96bbb14..b16a8d22563c 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -37,6 +37,8 @@ struct vfio_pci_dma_buf {
 	u8 revoked : 1;
 };
 
+extern const struct vm_operations_struct vfio_pci_mmap_ops;
+
 bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev);
 void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev);
 
-- 
2.47.3


  parent reply	other threads:[~2026-03-12 18:47 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-12 18:45 [RFC v2 PATCH 00/10] vfio/pci: Add mmap() for DMABUFs Matt Evans
2026-03-12 18:45 ` [RFC v2 PATCH 01/10] vfio/pci: Set up VFIO barmap before creating a DMABUF Matt Evans
2026-03-12 18:46 ` [RFC v2 PATCH 02/10] vfio/pci: Clean up DMABUFs before disabling function Matt Evans
2026-03-12 18:46 ` [RFC v2 PATCH 03/10] vfio/pci: Add helper to look up PFNs for DMABUFs Matt Evans
2026-03-12 18:46 ` [RFC v2 PATCH 04/10] vfio/pci: Add a helper to create a DMABUF for a BAR-map VMA Matt Evans
2026-03-18 20:04   ` Alex Williamson
2026-03-23 13:25     ` Jason Gunthorpe
2026-03-23 14:55     ` Matt Evans
2026-03-12 18:46 ` [RFC v2 PATCH 05/10] vfio/pci: Convert BAR mmap() to use a DMABUF Matt Evans
2026-03-12 18:46 ` [RFC v2 PATCH 06/10] vfio/pci: Remove vfio_pci_zap_bars() Matt Evans
2026-03-13  9:12   ` Christian König
2026-03-12 18:46 ` Matt Evans [this message]
2026-03-12 18:46 ` [RFC v2 PATCH 08/10] vfio/pci: Permanently revoke a DMABUF on request Matt Evans
2026-03-12 18:46 ` [RFC v2 PATCH 09/10] vfio/pci: Add mmap() attributes to DMABUF feature Matt Evans
2026-03-12 18:46 ` [RFC v2 PATCH 10/10] [RFC ONLY] selftests: vfio: Add standalone vfio_dmabuf_mmap_test Matt Evans
2026-03-13  9:21 ` [RFC v2 PATCH 00/10] vfio/pci: Add mmap() for DMABUFs Christian König
2026-03-13 13:28   ` Matt Evans

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260312184613.3710705-8-mattev@meta.com \
    --to=mattev@meta.com \
    --cc=alex@shazbot.org \
    --cc=amastro@fb.com \
    --cc=ankita@nvidia.com \
    --cc=apopple@nvidia.com \
    --cc=bjorn@kernel.org \
    --cc=christian.koenig@amd.com \
    --cc=dmatlack@google.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=jgg@nvidia.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=leon@kernel.org \
    --cc=linaro-mm-sig@lists.linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-media@vger.kernel.org \
    --cc=mngyadam@amazon.de \
    --cc=praan@google.com \
    --cc=sumit.semwal@linaro.org \
    --cc=vivek.kasireddy@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox