diff mbox series

[RFC,v2,01/11] net: add netdev netlink api to bind dma-buf to a net device

Message ID 20230810015751.3297321-2-almasrymina@google.com (mailing list archive)
State New, archived
Headers show
Series Device Memory TCP | expand

Commit Message

Mina Almasry Aug. 10, 2023, 1:57 a.m. UTC
API takes the dma-buf fd as input, and binds it to the netdevice. The
user can specify the rx queue to bind the dma-buf to. The user should be
able to bind the same dma-buf to multiple queues, but that is left as
a (minor) TODO in this iteration.

Suggested-by: Stanislav Fomichev <sdf@google.com>

Signed-off-by: Mina Almasry <almasrymina@google.com>
---
 Documentation/netlink/specs/netdev.yaml | 27 +++++++++++++++
 include/uapi/linux/netdev.h             | 10 ++++++
 net/core/netdev-genl-gen.c              | 14 ++++++++
 net/core/netdev-genl-gen.h              |  1 +
 net/core/netdev-genl.c                  |  6 ++++
 tools/include/uapi/linux/netdev.h       | 10 ++++++
 tools/net/ynl/generated/netdev-user.c   | 41 ++++++++++++++++++++++
 tools/net/ynl/generated/netdev-user.h   | 46 +++++++++++++++++++++++++
 8 files changed, 155 insertions(+)

Comments

Samudrala, Sridhar Aug. 10, 2023, 4:04 p.m. UTC | #1
On 8/9/2023 6:57 PM, Mina Almasry wrote:
> API takes the dma-buf fd as input, and binds it to the netdevice. The
> user can specify the rx queue to bind the dma-buf to. The user should be
> able to bind the same dma-buf to multiple queues, but that is left as
> a (minor) TODO in this iteration.

To support binding dma-buf fd to multiple queues, can we extend/change 
this interface to bind dma-buf fd to a napi_id? Amritha is currently 
working on a patchset that exposes napi_id's and their association with 
the queues.

https://lore.kernel.org/netdev/169059098829.3736.381753570945338022.stgit@anambiarhost.jf.intel.com/
Mina Almasry Aug. 11, 2023, 2:19 a.m. UTC | #2
On Thu, Aug 10, 2023 at 9:09 AM Samudrala, Sridhar
<sridhar.samudrala@intel.com> wrote:
>
>
>
> On 8/9/2023 6:57 PM, Mina Almasry wrote:
> > API takes the dma-buf fd as input, and binds it to the netdevice. The
> > user can specify the rx queue to bind the dma-buf to. The user should be
> > able to bind the same dma-buf to multiple queues, but that is left as
> > a (minor) TODO in this iteration.
>
> To support binding dma-buf fd to multiple queues, can we extend/change
> this interface to bind dma-buf fd to a napi_id? Amritha is currently
> working on a patchset that exposes napi_id's and their association with
> the queues.
>
> https://lore.kernel.org/netdev/169059098829.3736.381753570945338022.stgit@anambiarhost.jf.intel.com/
>

Thank you Sridhar,

I think honestly implementing multiple rx queue binding is trivial,
even without the napi_id association. The user should be able to call
the bind-rx API multiple times with the same dma-buf to bind to
multiple queues, or I can convert the queue-idx to a multi-attr
netlink attribute to let the user specify multiple rx queues in 1
call.

Without doing some homework it's not immediately obvious to me that
coupling the dma-buf binding with the napi_id is necessary or
advantageous. Is there a reason coupling those is better?

It seems like napi_id can also refer to TX queues, and binding a
dma-buf with a TX queue doesn't make much sense to me. For TX we need
to couple the dma-buf with the netdev that's sending the dma-buf data,
but not a specific TX queue on the netdev, I think.
diff mbox series

Patch

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index e41015310a6e..907a45260e95 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -68,6 +68,23 @@  attribute-sets:
         type: u32
         checks:
           min: 1
+  -
+    name: bind-dmabuf
+    attributes:
+      -
+        name: ifindex
+        doc: netdev ifindex to bind the dma-buf to.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: queue-idx
+        doc: receive queue index to bind the dma-buf to.
+        type: u32
+      -
+        name: dmabuf-fd
+        doc: dmabuf file descriptor to bind.
+        type: u32
 
 operations:
   list:
@@ -100,6 +117,16 @@  operations:
       doc: Notification about device configuration being changed.
       notify: dev-get
       mcgrp: mgmt
+    -
+      name: bind-rx
+      doc: Bind dmabuf to netdev
+      attribute-set: bind-dmabuf
+      do:
+        request:
+          attributes:
+            - ifindex
+            - dmabuf-fd
+            - queue-idx
 
 mcast-groups:
   list:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index bf71698a1e82..242b2b65161c 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -47,11 +47,21 @@  enum {
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
+enum {
+	NETDEV_A_BIND_DMABUF_IFINDEX = 1,
+	NETDEV_A_BIND_DMABUF_QUEUE_IDX,
+	NETDEV_A_BIND_DMABUF_DMABUF_FD,
+
+	__NETDEV_A_BIND_DMABUF_MAX,
+	NETDEV_A_BIND_DMABUF_MAX = (__NETDEV_A_BIND_DMABUF_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
+	NETDEV_CMD_BIND_RX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index ea9231378aa6..2e34ad5cccfa 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -15,6 +15,13 @@  static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1
 	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
 };
 
+/* NETDEV_CMD_BIND_RX - do */
+static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_BIND_DMABUF_DMABUF_FD + 1] = {
+	[NETDEV_A_BIND_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+	[NETDEV_A_BIND_DMABUF_DMABUF_FD] = { .type = NLA_U32, },
+	[NETDEV_A_BIND_DMABUF_QUEUE_IDX] = { .type = NLA_U32, },
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -29,6 +36,13 @@  static const struct genl_split_ops netdev_nl_ops[] = {
 		.dumpit	= netdev_nl_dev_get_dumpit,
 		.flags	= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= NETDEV_CMD_BIND_RX,
+		.doit		= netdev_nl_bind_rx_doit,
+		.policy		= netdev_bind_rx_nl_policy,
+		.maxattr	= NETDEV_A_BIND_DMABUF_DMABUF_FD,
+		.flags		= GENL_CMD_CAP_DO,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 7b370c073e7d..5aaeb435ec08 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -13,6 +13,7 @@ 
 
 int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 65ef4867fc49..bf7324dd6c36 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -141,6 +141,12 @@  int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+/* Stub */
+int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return 0;
+}
+
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
 				       unsigned long event, void *ptr)
 {
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index bf71698a1e82..242b2b65161c 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -47,11 +47,21 @@  enum {
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
+enum {
+	NETDEV_A_BIND_DMABUF_IFINDEX = 1,
+	NETDEV_A_BIND_DMABUF_QUEUE_IDX,
+	NETDEV_A_BIND_DMABUF_DMABUF_FD,
+
+	__NETDEV_A_BIND_DMABUF_MAX,
+	NETDEV_A_BIND_DMABUF_MAX = (__NETDEV_A_BIND_DMABUF_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
+	NETDEV_CMD_BIND_RX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 4eb8aefef0cd..2716e63820d2 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -18,6 +18,7 @@  static const char * const netdev_op_strmap[] = {
 	[NETDEV_CMD_DEV_ADD_NTF] = "dev-add-ntf",
 	[NETDEV_CMD_DEV_DEL_NTF] = "dev-del-ntf",
 	[NETDEV_CMD_DEV_CHANGE_NTF] = "dev-change-ntf",
+	[NETDEV_CMD_BIND_RX] = "bind-rx",
 };
 
 const char *netdev_op_str(int op)
@@ -57,6 +58,17 @@  struct ynl_policy_nest netdev_dev_nest = {
 	.table = netdev_dev_policy,
 };
 
+struct ynl_policy_attr netdev_bind_dmabuf_policy[NETDEV_A_BIND_DMABUF_MAX + 1] = {
+	[NETDEV_A_BIND_DMABUF_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
+	[NETDEV_A_BIND_DMABUF_QUEUE_IDX] = { .name = "queue-idx", .type = YNL_PT_U32, },
+	[NETDEV_A_BIND_DMABUF_DMABUF_FD] = { .name = "dmabuf-fd", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest netdev_bind_dmabuf_nest = {
+	.max_attr = NETDEV_A_BIND_DMABUF_MAX,
+	.table = netdev_bind_dmabuf_policy,
+};
+
 /* Common nested types */
 /* ============== NETDEV_CMD_DEV_GET ============== */
 /* NETDEV_CMD_DEV_GET - do */
@@ -172,6 +184,35 @@  void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp)
 	free(rsp);
 }
 
+/* ============== NETDEV_CMD_BIND_RX ============== */
+/* NETDEV_CMD_BIND_RX - do */
+void netdev_bind_rx_req_free(struct netdev_bind_rx_req *req)
+{
+	free(req);
+}
+
+int netdev_bind_rx(struct ynl_sock *ys, struct netdev_bind_rx_req *req)
+{
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_BIND_RX, 1);
+	ys->req_policy = &netdev_bind_dmabuf_nest;
+
+	if (req->_present.ifindex)
+		mnl_attr_put_u32(nlh, NETDEV_A_BIND_DMABUF_IFINDEX, req->ifindex);
+	if (req->_present.dmabuf_fd)
+		mnl_attr_put_u32(nlh, NETDEV_A_BIND_DMABUF_DMABUF_FD, req->dmabuf_fd);
+	if (req->_present.queue_idx)
+		mnl_attr_put_u32(nlh, NETDEV_A_BIND_DMABUF_QUEUE_IDX, req->queue_idx);
+
+	err = ynl_exec(ys, nlh, NULL);
+	if (err < 0)
+		return -1;
+
+	return 0;
+}
+
 static const struct ynl_ntf_info netdev_ntf_info[] =  {
 	[NETDEV_CMD_DEV_ADD_NTF] =  {
 		.alloc_sz	= sizeof(struct netdev_dev_get_ntf),
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index 5554dc69bb9c..74a43bb53627 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -82,4 +82,50 @@  struct netdev_dev_get_ntf {
 
 void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp);
 
+/* ============== NETDEV_CMD_BIND_RX ============== */
+/* NETDEV_CMD_BIND_RX - do */
+struct netdev_bind_rx_req {
+	struct {
+		__u32 ifindex:1;
+		__u32 dmabuf_fd:1;
+		__u32 queue_idx:1;
+	} _present;
+
+	__u32 ifindex;
+	__u32 dmabuf_fd;
+	__u32 queue_idx;
+};
+
+static inline struct netdev_bind_rx_req *netdev_bind_rx_req_alloc(void)
+{
+	return calloc(1, sizeof(struct netdev_bind_rx_req));
+}
+void netdev_bind_rx_req_free(struct netdev_bind_rx_req *req);
+
+static inline void
+netdev_bind_rx_req_set_ifindex(struct netdev_bind_rx_req *req, __u32 ifindex)
+{
+	req->_present.ifindex = 1;
+	req->ifindex = ifindex;
+}
+static inline void
+netdev_bind_rx_req_set_dmabuf_fd(struct netdev_bind_rx_req *req,
+				 __u32 dmabuf_fd)
+{
+	req->_present.dmabuf_fd = 1;
+	req->dmabuf_fd = dmabuf_fd;
+}
+static inline void
+netdev_bind_rx_req_set_queue_idx(struct netdev_bind_rx_req *req,
+				 __u32 queue_idx)
+{
+	req->_present.queue_idx = 1;
+	req->queue_idx = queue_idx;
+}
+
+/*
+ * Bind dmabuf to netdev
+ */
+int netdev_bind_rx(struct ynl_sock *ys, struct netdev_bind_rx_req *req);
+
 #endif /* _LINUX_NETDEV_GEN_H */