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 PATCH 5/7] vfio/pci: Permanently revoke a DMABUF on request
Date: Thu, 26 Feb 2026 12:22:01 -0800 [thread overview]
Message-ID: <20260226202211.929005-6-mattev@meta.com> (raw)
In-Reply-To: <20260226202211.929005-1-mattev@meta.com>
Expand the VFIO DMABUF revocation state to three states:
Not revoked, temporarily revoked, and permanently revoked.
The first two are for existing transient revocation, e.g. across a
function reset, and the DMABUF is put into the last in response to an
ioctl(DMA_BUF_IOCTL_REVOKE) request.
When triggered, dynamic imports are removed, PTEs zapped, and the
state changed such that no future mappings/imports are allowed.
This is useful to reclaim VFIO PCI BAR ranges previously delegated to
a subordinate process: The driver process can ensure that the loans
are closed down before repurposing exported ranges.
Signed-off-by: Matt Evans <mattev@meta.com>
---
drivers/vfio/pci/vfio_pci_dmabuf.c | 64 +++++++++++++++++++++++++-----
1 file changed, 53 insertions(+), 11 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index bebb496bd0f2..af30ca205f31 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -9,6 +9,17 @@
MODULE_IMPORT_NS("DMA_BUF");
+enum vfio_pci_dma_buf_status {
+ /*
+ * A buffer can move freely between OK/accessible and revoked
+ * states (for example, a device reset will temporarily revoke
+ * it). It can also be permanently revoked.
+ */
+ VFIO_PCI_DMABUF_OK = 0,
+ VFIO_PCI_DMABUF_TEMP_REVOKED = 1,
+ VFIO_PCI_DMABUF_PERM_REVOKED = 2,
+};
+
struct vfio_pci_dma_buf {
struct dma_buf *dmabuf;
struct vfio_pci_core_device *vdev;
@@ -17,9 +28,11 @@ struct vfio_pci_dma_buf {
struct dma_buf_phys_vec *phys_vec;
struct p2pdma_provider *provider;
u32 nr_ranges;
- u8 revoked : 1;
+ enum vfio_pci_dma_buf_status status;
};
+static int vfio_pci_dma_buf_revoke(struct dma_buf *dmabuf);
+
static int vfio_pci_dma_buf_pin(struct dma_buf_attachment *attachment)
{
return -EOPNOTSUPP;
@@ -38,7 +51,7 @@ static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,
if (!attachment->peer2peer)
return -EOPNOTSUPP;
- if (priv->revoked)
+ if (priv->status != VFIO_PCI_DMABUF_OK)
return -ENODEV;
return 0;
@@ -52,7 +65,7 @@ vfio_pci_dma_buf_map(struct dma_buf_attachment *attachment,
dma_resv_assert_held(priv->dmabuf->resv);
- if (priv->revoked)
+ if (priv->status != VFIO_PCI_DMABUF_OK)
return ERR_PTR(-ENODEV);
return dma_buf_phys_vec_to_sgt(attachment, priv->provider,
@@ -205,7 +218,7 @@ static vm_fault_t vfio_pci_dma_buf_mmap_huge_fault(struct vm_fault *vmf,
* revocation/unmap and status change occurs
* whilst holding memory_lock.
*/
- if (priv->revoked)
+ if (priv->status != VFIO_PCI_DMABUF_OK)
ret = VM_FAULT_SIGBUS;
else
ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order);
@@ -246,7 +259,7 @@ static bool vfio_pci_dma_buf_is_mappable(struct dma_buf *dmabuf)
* on: for example, users should not be mmap()ing a buffer
* that's being moved [by a user-triggered activity].
*/
- if (priv->revoked)
+ if (priv->status != VFIO_PCI_DMABUF_OK)
return false;
return true;
@@ -296,6 +309,7 @@ static const struct dma_buf_ops vfio_pci_dmabuf_ops = {
.unmap_dma_buf = vfio_pci_dma_buf_unmap,
.release = vfio_pci_dma_buf_release,
.mmap = vfio_pci_dma_buf_mmap,
+ .revoke = vfio_pci_dma_buf_revoke,
};
/*
@@ -320,7 +334,7 @@ int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
return -EOPNOTSUPP;
priv = attachment->dmabuf->priv;
- if (priv->revoked)
+ if (priv->status != VFIO_PCI_DMABUF_OK)
return -ENODEV;
/* More than one range to iommufd will require proper DMABUF support */
@@ -506,7 +520,8 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
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);
+ priv->status = __vfio_pci_memory_enabled(vdev) ? VFIO_PCI_DMABUF_OK :
+ VFIO_PCI_DMABUF_TEMP_REVOKED;
list_add_tail(&priv->dmabufs_elm, &vdev->dmabufs);
dma_resv_unlock(priv->dmabuf->resv);
up_write(&vdev->memory_lock);
@@ -541,7 +556,7 @@ void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked)
lockdep_assert_held_write(&vdev->memory_lock);
/*
* Holding memory_lock ensures a racing
- * vfio_pci_dma_buf_mmap_*_fault() observes priv->revoked
+ * vfio_pci_dma_buf_mmap_*_fault() observes priv->status
* properly.
*/
@@ -549,9 +564,11 @@ void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked)
if (!get_file_active(&priv->dmabuf->file))
continue;
- if (priv->revoked != revoked) {
+ if ((priv->status == VFIO_PCI_DMABUF_OK && revoked) ||
+ (priv->status == VFIO_PCI_DMABUF_TEMP_REVOKED && !revoked)) {
dma_resv_lock(priv->dmabuf->resv, NULL);
- priv->revoked = revoked;
+ priv->status = revoked ? VFIO_PCI_DMABUF_TEMP_REVOKED :
+ VFIO_PCI_DMABUF_OK;
dma_buf_move_notify(priv->dmabuf);
dma_resv_unlock(priv->dmabuf->resv);
@@ -580,7 +597,7 @@ void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev)
dma_resv_lock(priv->dmabuf->resv, NULL);
list_del_init(&priv->dmabufs_elm);
priv->vdev = NULL;
- priv->revoked = true;
+ priv->status = VFIO_PCI_DMABUF_PERM_REVOKED;
dma_buf_move_notify(priv->dmabuf);
dma_resv_unlock(priv->dmabuf->resv);
unmap_mapping_range(priv->dmabuf->file->f_mapping,
@@ -590,3 +607,28 @@ void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev)
}
up_write(&vdev->memory_lock);
}
+
+static int vfio_pci_dma_buf_revoke(struct dma_buf *dmabuf)
+{
+ struct vfio_pci_dma_buf *priv = dmabuf->priv;
+ struct vfio_pci_core_device *vdev;
+
+ vdev = READ_ONCE(priv->vdev);
+
+ if (!vdev)
+ return -ENODEV;
+
+ scoped_guard(rwsem_read, &vdev->memory_lock) {
+ if (priv->status == VFIO_PCI_DMABUF_PERM_REVOKED)
+ return -EBADFD;
+
+ dma_resv_lock(priv->dmabuf->resv, NULL);
+ priv->status = VFIO_PCI_DMABUF_PERM_REVOKED;
+ dma_buf_move_notify(priv->dmabuf);
+ dma_resv_unlock(priv->dmabuf->resv);
+
+ unmap_mapping_range(priv->dmabuf->file->f_mapping,
+ 0, priv->size, 1);
+ }
+ return 0;
+}
--
2.47.3
next prev parent reply other threads:[~2026-02-26 20:23 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-26 20:21 [RFC PATCH 0/7] vfio/pci: Add mmap() for DMABUFs Matt Evans
2026-02-26 20:21 ` [RFC PATCH 1/7] vfio/pci: Ensure VFIO barmap is set up before creating a DMABUF Matt Evans
2026-02-26 20:21 ` [RFC PATCH 2/7] vfio/pci: Clean up DMABUFs before disabling function Matt Evans
2026-02-26 20:21 ` [RFC PATCH 3/7] vfio/pci: Support mmap() of a DMABUF Matt Evans
2026-02-27 10:09 ` Christian König
2026-02-27 12:51 ` Jason Gunthorpe
2026-02-27 19:42 ` Matt Evans
2026-02-27 19:48 ` Jason Gunthorpe
2026-02-27 21:52 ` Alex Mastro
2026-02-27 22:00 ` Alex Mastro
2026-02-27 22:04 ` Jason Gunthorpe
2026-03-02 10:07 ` Christian König
2026-03-02 12:54 ` Jason Gunthorpe
2026-03-02 13:20 ` Christian König
2026-02-26 20:22 ` [RFC PATCH 4/7] dma-buf: uapi: Mechanism to revoke DMABUFs via ioctl() Matt Evans
2026-02-27 10:05 ` Christian König
2026-02-27 12:56 ` Jason Gunthorpe
2026-02-27 13:02 ` Matt Evans
2026-02-27 15:20 ` Christian König
2026-02-27 16:19 ` Matt Evans
2026-02-26 20:22 ` Matt Evans [this message]
2026-02-26 20:22 ` [RFC PATCH 6/7] vfio/pci: Add mmap() attributes to DMABUF feature Matt Evans
2026-02-26 20:22 ` [RFC PATCH 7/7] [RFC ONLY] selftests: vfio: Add standalone vfio_dmabuf_mmap_test 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=20260226202211.929005-6-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