From: Pranjal Shrivastava <praan@google.com>
To: linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
kvm@vger.kernel.org
Cc: Bjorn Helgaas <bhelgaas@google.com>,
Logan Gunthorpe <logang@deltatee.com>,
Alex Williamson <alex@shazbot.org>,
Jason Gunthorpe <jgg@ziepe.ca>, Kevin Tian <kevin.tian@intel.com>,
Pranjal Shrivastava <praan@google.com>,
Ankit Agrawal <ankita@nvidia.com>, Matt Evans <mattev@meta.com>,
Vivek Kasireddy <vivek.kasireddy@intel.com>,
Leon Romanovsky <leon@kernel.org>,
Shivaji Kant <shivajikant@google.com>,
Samiullah Khawaja <skhawaja@google.com>,
Unnati Sachan <unnatisachan@google.com>
Subject: [RFC PATCH v2 2/5] vfio/pci: Implement ZONE_DEVICE registration for DMABUFs
Date: Tue, 4 Aug 2026 18:50:47 +0000 [thread overview]
Message-ID: <20260804185050.2053672-3-praan@google.com> (raw)
In-Reply-To: <20260804185050.2053672-1-praan@google.com>
When a DMABUF is requested with the VFIO_DMA_BUF_FLAG_ZONE_DEVICE_BACKED
flag is requested during DMABUF export, invoke pci_p2pdma_add_resource()
to register the target BAR with the ZONE_DEVICE framework. This allocates
the underlying struct page metadata. Add internal state tracking for
ZONE_DEVICE-backed DMABUF exports. Add p2p_struct_page_bars, a bitmask to
track PCI BARs that have been registered. Add a zone_device_backed flag
to track whether a specific DMABUF contains page-backed memory.
Introduce a new Kconfig option, VFIO_PCI_DMABUF_ZONE_DEVICE to handle
the dependency on PCI_P2PDMA without clobbering existing dependencies.
Signed-off-by: Pranjal Shrivastava <praan@google.com>
---
drivers/vfio/pci/Kconfig | 11 ++++++
drivers/vfio/pci/vfio_pci_dmabuf.c | 55 +++++++++++++++++++++++++++++-
drivers/vfio/pci/vfio_pci_priv.h | 1 +
include/linux/vfio_pci_core.h | 1 +
4 files changed, 67 insertions(+), 1 deletion(-)
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 67a2ae1fbc04..c9cd04a16297 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -61,6 +61,17 @@ config VFIO_PCI_DMABUF
def_bool y if PCI_P2PDMA
depends on VFIO_PCI_CORE
+config VFIO_PCI_DMABUF_ZONE_DEVICE
+ bool "VFIO PCI DMABUF ZONE_DEVICE page-backed export support"
+ depends on VFIO_PCI_DMABUF
+ depends on PCI_P2PDMA
+ help
+ Say Y here to enable optional struct page backing (ZONE_DEVICE)
+ for VFIO exported DMABUFs. This is required to support peer-to-peer
+ (P2P) DMA transactions with subsystems that rely on page metadata.
+
+ If unsure, say N.
+
source "drivers/vfio/pci/mlx5/Kconfig"
source "drivers/vfio/pci/ism/Kconfig"
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 36bf07530840..900ac1851c9f 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -427,6 +427,41 @@ static int validate_dmabuf_input(struct vfio_device_feature_dma_buf *dma_buf,
return 0;
}
+#ifdef CONFIG_VFIO_PCI_DMABUF_ZONE_DEVICE
+static int vfio_pci_dma_buf_alloc_struct_pages(struct vfio_pci_core_device *vdev,
+ struct vfio_device_feature_dma_buf *dma_buf)
+{
+ struct pci_dev *pdev = vdev->pdev;
+ u32 bar_index = dma_buf->region_index;
+ int ret;
+
+ if (vdev->p2p_struct_page_bars & (1 << bar_index))
+ return 0;
+
+ /*
+ * Allocate vmemmap (struct pages) for the ENTIRE BAR, even if the
+ * specific DMABUF only exports a partial slice of it. This prevents
+ * vmemmap fragmentation and ensures that any subsequent slice exports
+ * from the same BAR get struct page backing instantly.
+ */
+ ret = pci_p2pdma_add_resource(pdev, bar_index, 0, 0);
+ if (ret) {
+ if (ret != -EEXIST)
+ return ret;
+ }
+
+ vdev->p2p_struct_page_bars |= (1 << bar_index);
+
+ return 0;
+}
+#else
+static inline int vfio_pci_dma_buf_alloc_struct_pages(struct vfio_pci_core_device *vdev,
+ struct vfio_device_feature_dma_buf *dma_buf)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
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)
@@ -448,7 +483,8 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
if (copy_from_user(&get_dma_buf, arg, sizeof(get_dma_buf)))
return -EFAULT;
- if (!get_dma_buf.nr_ranges || get_dma_buf.flags)
+ if (!get_dma_buf.nr_ranges ||
+ (get_dma_buf.flags & ~VFIO_DMA_BUF_FLAG_ZONE_DEVICE_BACKED))
return -EINVAL;
/*
@@ -468,6 +504,21 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
if (ret)
goto err_free_ranges;
+ if (get_dma_buf.flags & VFIO_DMA_BUF_FLAG_ZONE_DEVICE_BACKED) {
+ /*
+ * Serialize the allocation and the page initialization.
+ * Holding the memory_lock here prevents a race where a
+ * concurrent ioctl bypasses the allocation + init, handing
+ * a DMABUF to the user before the ZONE_DEVICE registration
+ * is completed successfully.
+ */
+ down_write(&vdev->memory_lock);
+ ret = vfio_pci_dma_buf_alloc_struct_pages(vdev, &get_dma_buf);
+ up_write(&vdev->memory_lock);
+ if (ret)
+ goto err_free_ranges;
+ }
+
priv = kzalloc_obj(*priv);
if (!priv) {
ret = -ENOMEM;
@@ -480,6 +531,8 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
}
priv->vdev = vdev;
+ if (get_dma_buf.flags & VFIO_DMA_BUF_FLAG_ZONE_DEVICE_BACKED)
+ priv->zone_device_backed = 1;
priv->nr_ranges = get_dma_buf.nr_ranges;
priv->size = length;
ret = vdev->pci_ops->get_dmabuf_phys(vdev, &priv->provider,
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index 8741abd04461..d0bf5c118793 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -42,6 +42,7 @@ struct vfio_pci_dma_buf {
struct completion comp;
unsigned long vma_pgoff_adjust;
enum vfio_pci_dma_buf_status status;
+ u8 zone_device_backed : 1;
};
bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index e2b4252e7c3f..c28f06bae302 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -135,6 +135,7 @@ struct vfio_pci_core_device {
bool pm_runtime_engaged;
bool sriov_active;
bool zap_bars_on_revoke;
+ u8 p2p_struct_page_bars;
struct pci_saved_state *pci_saved_state;
struct pci_saved_state *pm_save;
int ioeventfds_nr;
--
2.55.0.571.g244d577d93-goog
next prev parent reply other threads:[~2026-08-04 18:51 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-04 18:50 [RFC PATCH v2 0/5] vfio/pci: Support ZONE_DEVICE-backed DMABUF Exports Pranjal Shrivastava
2026-08-04 18:50 ` [RFC PATCH v2 1/5] vfio: Add UAPI flag for ZONE_DEVICE-backed DMABUF exports Pranjal Shrivastava
2026-08-04 18:50 ` Pranjal Shrivastava [this message]
2026-08-04 18:50 ` [RFC PATCH v2 3/5] vfio/pci: Implement page-backed .map_dma_buf handler Pranjal Shrivastava
2026-08-04 18:50 ` [RFC PATCH v2 4/5] vfio/pci: Add .mmap handler for page-backed DMABUFs Pranjal Shrivastava
2026-08-04 18:50 ` [RFC PATCH v2 5/5] vfio/pci: Add revocation fence for ZONE_DEVICE DMABUFs Pranjal Shrivastava
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=20260804185050.2053672-3-praan@google.com \
--to=praan@google.com \
--cc=alex@shazbot.org \
--cc=ankita@nvidia.com \
--cc=bhelgaas@google.com \
--cc=jgg@ziepe.ca \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=mattev@meta.com \
--cc=shivajikant@google.com \
--cc=skhawaja@google.com \
--cc=unnatisachan@google.com \
--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