include/linux/netdevice.h | 21 +++++++++++++++++++++ io_uring/zcrx.c | 2 +- net/core/devmem.c | 10 +++++++++- 3 files changed, 31 insertions(+), 2 deletions(-)
For zerocopy (io_uring, devmem), there is an assumption that the
parent device can do DMA. However that is not always the case:
scalable function netdevs [1] have the DMA device in the grandparent.
This patch adds a helper for getting the DMA device for a netdev from
its parent or grandparent if necessary. The NULL case is handled in the
callers.
devmem and io_uring are updated accordingly to use this helper instead
of directly using the parent.
[1] Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Cosmin Ratio <cratiu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
----
Changes in v2 [2]:
- Dropped the Fixes tag.
- Added more documentation as requeseted.
- Renamed the patch title to better reflect its purpose.
Changes in v1 [1]:
- Upgraded from RFC status.
- Dropped driver specific bits for generic solution.
- Implemented single patch as a fix as requested in RFC.
- Handling of multi-PF netdevs will be handled in a subsequent patch
series.
[1] RFC: https://lore.kernel.org/all/20250702172433.1738947-2-dtatulea@nvidia.com/
[2] v2: https://lore.kernel.org/all/20250709124059.516095-2-dtatulea@nvidia.com/
---
include/linux/netdevice.h | 21 +++++++++++++++++++++
io_uring/zcrx.c | 2 +-
net/core/devmem.c | 10 +++++++++-
3 files changed, 31 insertions(+), 2 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5847c20994d3..53aa63d6e5a3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5560,4 +5560,25 @@ extern struct net_device *blackhole_netdev;
atomic_long_add((VAL), &(DEV)->stats.__##FIELD)
#define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD)
+static inline struct device *netdev_get_dma_dev(const struct net_device *dev)
+{
+ struct device *dma_dev = dev->dev.parent;
+
+ if (!dma_dev)
+ return NULL;
+
+ /* Common case: dma device is parent device of netdev. */
+ if (dma_dev->dma_mask)
+ return dma_dev;
+
+ /* SF netdevs have an auxdev device as parent, the dma device being the
+ * grandparent.
+ */
+ dma_dev = dma_dev->parent;
+ if (dma_dev && dma_dev->dma_mask)
+ return dma_dev;
+
+ return NULL;
+}
+
#endif /* _LINUX_NETDEVICE_H */
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 797247a34cb7..93462e5b2207 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -584,7 +584,7 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
goto err;
}
- ifq->dev = ifq->netdev->dev.parent;
+ ifq->dev = netdev_get_dma_dev(ifq->netdev);
if (!ifq->dev) {
ret = -EOPNOTSUPP;
goto err;
diff --git a/net/core/devmem.c b/net/core/devmem.c
index b3a62ca0df65..881044e0ae0e 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -183,6 +183,7 @@ net_devmem_bind_dmabuf(struct net_device *dev,
{
struct net_devmem_dmabuf_binding *binding;
static u32 id_alloc_next;
+ struct device *dma_dev;
struct scatterlist *sg;
struct dma_buf *dmabuf;
unsigned int sg_idx, i;
@@ -193,6 +194,13 @@ net_devmem_bind_dmabuf(struct net_device *dev,
if (IS_ERR(dmabuf))
return ERR_CAST(dmabuf);
+ dma_dev = netdev_get_dma_dev(dev);
+ if (!dma_dev) {
+ err = -EOPNOTSUPP;
+ NL_SET_ERR_MSG(extack, "Device doesn't support dma");
+ goto err_put_dmabuf;
+ }
+
binding = kzalloc_node(sizeof(*binding), GFP_KERNEL,
dev_to_node(&dev->dev));
if (!binding) {
@@ -209,7 +217,7 @@ net_devmem_bind_dmabuf(struct net_device *dev,
binding->dmabuf = dmabuf;
- binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent);
+ binding->attachment = dma_buf_attach(binding->dmabuf, dma_dev);
if (IS_ERR(binding->attachment)) {
err = PTR_ERR(binding->attachment);
NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device");
--
2.43.0On Fri, 11 Jul 2025 09:26:34 +0000 Dragos Tatulea wrote:
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index 5847c20994d3..53aa63d6e5a3 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -5560,4 +5560,25 @@ extern struct net_device *blackhole_netdev;
> atomic_long_add((VAL), &(DEV)->stats.__##FIELD)
> #define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD)
>
> +static inline struct device *netdev_get_dma_dev(const struct net_device *dev)
> +{
> + struct device *dma_dev = dev->dev.parent;
> +
> + if (!dma_dev)
> + return NULL;
> +
> + /* Common case: dma device is parent device of netdev. */
> + if (dma_dev->dma_mask)
> + return dma_dev;
> +
> + /* SF netdevs have an auxdev device as parent, the dma device being the
> + * grandparent.
> + */
> + dma_dev = dma_dev->parent;
> + if (dma_dev && dma_dev->dma_mask)
> + return dma_dev;
> +
> + return NULL;
> +}
LGTM, but we need a better place for this function. netdevice.h is
included directly by 1.5k files, and indirectly by probably another 5k.
It's not a great place to put random helpers with 2 callers.
Maybe net/netdev_rx_queue.h and net/core/netdev_rx_queue.c?
I don't think it needs to be a static inline either.
--
pw-bot: cr
On Mon, Jul 14, 2025 at 06:11:36PM -0700, Jakub Kicinski wrote:
> > +static inline struct device *netdev_get_dma_dev(const struct net_device *dev)
> > +{
> > + struct device *dma_dev = dev->dev.parent;
> > +
> > + if (!dma_dev)
> > + return NULL;
> > +
> > + /* Common case: dma device is parent device of netdev. */
> > + if (dma_dev->dma_mask)
> > + return dma_dev;
> > +
> > + /* SF netdevs have an auxdev device as parent, the dma device being the
> > + * grandparent.
> > + */
> > + dma_dev = dma_dev->parent;
> > + if (dma_dev && dma_dev->dma_mask)
> > + return dma_dev;
> > +
> > + return NULL;
> > +}
>
> LGTM, but we need a better place for this function. netdevice.h is
> included directly by 1.5k files, and indirectly by probably another 5k.
> It's not a great place to put random helpers with 2 callers.
> Maybe net/netdev_rx_queue.h and net/core/netdev_rx_queue.c?
> I don't think it needs to be a static inline either.
The whole concept is also buggy. Trying to get a dma-able device by
walking down from an upper level construct like the netdevice can't work
reliably. You'll need to explicitly provide the dma_device using either
a method or a pointer to it instead of this guesswork.
On Mon, 14 Jul 2025 21:39:30 -0700 Christoph Hellwig wrote: > > LGTM, but we need a better place for this function. netdevice.h is > > included directly by 1.5k files, and indirectly by probably another 5k. > > It's not a great place to put random helpers with 2 callers. > > Maybe net/netdev_rx_queue.h and net/core/netdev_rx_queue.c? > > I don't think it needs to be a static inline either. > > The whole concept is also buggy. Trying to get a dma-able device by > walking down from an upper level construct like the netdevice can't work > reliably. You'll need to explicitly provide the dma_device using either > a method or a pointer to it instead of this guesswork. Yeah, I'm pretty sure we'll end up with a method in queue ops. But it's not that deep, an easy thing to change.
On Tue, Jul 15, 2025 at 06:06:49AM -0700, Jakub Kicinski wrote: > On Mon, 14 Jul 2025 21:39:30 -0700 Christoph Hellwig wrote: > > > LGTM, but we need a better place for this function. netdevice.h is > > > included directly by 1.5k files, and indirectly by probably another 5k. > > > It's not a great place to put random helpers with 2 callers. > > > Maybe net/netdev_rx_queue.h and net/core/netdev_rx_queue.c? > > > I don't think it needs to be a static inline either. > > > > The whole concept is also buggy. Trying to get a dma-able device by > > walking down from an upper level construct like the netdevice can't work > > reliably. You'll need to explicitly provide the dma_device using either > > a method or a pointer to it instead of this guesswork. > > Yeah, I'm pretty sure we'll end up with a method in queue ops. > But it's not that deep, an easy thing to change. Why not get this right now instead of adding more of the hacky parent walking?
© 2016 - 2025 Red Hat, Inc.