On 6/13/24 02:35, Mina Almasry wrote:
Add a netdev_dmabuf_binding struct which represents the
dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to
rx queues on the netdevice. On the binding, the dma_buf_attach
& dma_buf_map_attachment will occur. The entries in the sg_table from
mapping will be inserted into a genpool to make it ready
for allocation.
The chunks in the genpool are owned by a dmabuf_chunk_owner struct which
holds the dma-buf offset of the base of the chunk and the dma_addr of
the chunk. Both are needed to use allocations that come from this chunk.
We create a new type that represents an allocation from the genpool:
net_iov. We setup the net_iov allocation size in the
genpool to PAGE_SIZE for simplicity: to match the PAGE_SIZE normally
allocated by the page pool and given to the drivers.
The user can unbind the dmabuf from the netdevice by closing the netlink
socket that established the binding. We do this so that the binding is
automatically unbound even if the userspace process crashes.
The binding and unbinding leaves an indicator in struct netdev_rx_queue
that the given queue is bound, but the binding doesn't take effect until
the driver actually reconfigures its queues, and re-initializes its page
pool.
The netdev_dmabuf_binding struct is refcounted, and releases its
resources only when all the refs are released.
Signed-off-by: Willem de Bruijn <willemb@xxxxxxxxxx>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@xxxxxxxxxx>
Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
Apart from the comment below
Reviewed-by: Pavel Begunkov <asml.silence@xxxxxxxxx> # excluding netlink
diff --git a/include/net/devmem.h b/include/net/devmem.h
new file mode 100644
index 0000000000000..eaf3fd965d7a8
...
diff --git a/net/core/dev.c b/net/core/dev.c
index c361a7b69da86..84c9f96a6c9bf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -158,6 +158,9 @@
#include <net/page_pool/types.h>
#include <net/page_pool/helpers.h>
#include <net/rps.h>
+#include <linux/genalloc.h>
+#include <linux/dma-buf.h>
+#include <net/devmem.h>
#include "dev.h"
#include "net-sysfs.h"
diff --git a/net/core/devmem.c b/net/core/devmem.c
new file mode 100644
index 0000000000000..951a06004c430
--- /dev/null
+++ b/net/core/devmem.c
@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Devmem TCP
+ *
+ * Authors: Mina Almasry <almasrymina@xxxxxxxxxx>
+ * Willem de Bruijn <willemdebruijn.kernel@xxxxxxxxx>
+ * Kaiyuan Zhang <kaiyuanz@xxxxxxxxxx
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/netdevice.h>
+#include <trace/events/page_pool.h>
+#include <net/netdev_rx_queue.h>
+#include <net/page_pool/types.h>
+#include <net/page_pool/helpers.h>
+#include <linux/genalloc.h>
+#include <linux/dma-buf.h>
+#include <net/devmem.h>
+#include <net/netdev_queues.h>
+
+/* Device memory support */
+
+#if defined(CONFIG_DMA_SHARED_BUFFER) && defined(CONFIG_GENERIC_ALLOCATOR)
+static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
+ struct gen_pool_chunk *chunk,
+ void *not_used)
+{
+ struct dmabuf_genpool_chunk_owner *owner = chunk->owner;
+
+ kvfree(owner->niovs);
+ kfree(owner);
+}
+
+void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
+{
+ size_t size, avail;
+
+ gen_pool_for_each_chunk(binding->chunk_pool,
+ net_devmem_dmabuf_free_chunk_owner, NULL);
+
+ size = gen_pool_size(binding->chunk_pool);
+ avail = gen_pool_avail(binding->chunk_pool);
+
+ if (!WARN(size != avail, "can't destroy genpool. size=%zu, avail=%zu",
+ size, avail))
+ gen_pool_destroy(binding->chunk_pool);
+
+ dma_buf_unmap_attachment(binding->attachment, binding->sgt,
+ DMA_FROM_DEVICE);
It's unmapped here as DMA_FROM_DEVICE, a fail path does DMA_BIDIRECTIONAL,
dma_buf_map_attachment() passes BIDIRECTIONAL.
+ dma_buf_detach(binding->dmabuf, binding->attachment);
+ dma_buf_put(binding->dmabuf);
+ xa_destroy(&binding->bound_rxq_list);
+ kfree(binding);
+}
+
+/* Protected by rtnl_lock() */
+static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);
+
...
--
Pavel Begunkov
