Merge branch 'introduce-queue-and-napi-support-in-netdev-genl-was-introduce-napi-queues-support'

Amritha Nambiar says:

====================
Introduce queue and NAPI support in netdev-genl (Was: Introduce NAPI queues support)

Add the capability to export the following via netdev-genl interface:
- queue information supported by the device
- NAPI information supported by the device

Introduce support for associating queue and NAPI instance.
Extend the netdev_genl generic netlink family for netdev
with queue and NAPI data.

The queue parameters exposed are:
- queue index
- queue type
- ifindex
- NAPI id associated with the queue

Additional rx and tx queue parameters can be exposed in follow up
patches by stashing them in netdev queue structures. XDP queue type
can also be supported in future.

The NAPI fields exposed are:
- NAPI id
- NAPI device ifindex
- Interrupt number associated with the NAPI instance
- PID for the NAPI thread

This series only supports 'get' ability for retrieving
certain queue and NAPI attributes. The 'set' ability for
configuring queue and associated NAPI instance via netdev-genl
will be submitted as a separate patch series.

Previous discussion at:
https://lore.kernel.org/netdev/c8476530638a5f4381d64db0e024ed49c2db3b02.camel@gmail.com/T/#m00999652a8b4731fbdb7bf698d2e3666c65a60e7

$ ./cli.py --spec netdev.yaml --do queue-get  --json='{"ifindex": 12, "id": 0, "type": 0}'
{'id': 0, 'ifindex': 12, 'napi-id': 593, 'type': 'rx'}

$ ./cli.py --spec netdev.yaml  --do queue-get --json='{"ifindex": 12, "id": 0, "type": 1}'
{'id': 0, 'ifindex': 12, 'napi-id': 593, 'type': 'tx'}

$ ./cli.py --spec netdev.yaml  --dump queue-get --json='{"ifindex": 12}'
[{'id': 0, 'ifindex': 12, 'napi-id': 593, 'type': 'rx'},
 {'id': 1, 'ifindex': 12, 'napi-id': 594, 'type': 'rx'},
 {'id': 2, 'ifindex': 12, 'napi-id': 595, 'type': 'rx'},
 {'id': 3, 'ifindex': 12, 'napi-id': 596, 'type': 'rx'},
 {'id': 0, 'ifindex': 12, 'napi-id': 593, 'type': 'tx'},
 {'id': 1, 'ifindex': 12, 'napi-id': 594, 'type': 'tx'},
 {'id': 2, 'ifindex': 12, 'napi-id': 595, 'type': 'tx'},
 {'id': 3, 'ifindex': 12, 'napi-id': 596, 'type': 'tx'}]

$ ./cli.py --spec netdev.yaml --do napi-get --json='{"id": 593}'
{'id': 593, 'ifindex': 12, 'irq': 291, 'pid': 3727}

$ ./cli.py --spec netdev.yaml --dump napi-get --json='{"ifindex": 12}'
[{'id': 596, 'ifindex': 12, 'irq': 294, 'pid': 3724},
 {'id': 595, 'ifindex': 12, 'irq': 293, 'pid': 3725},
 {'id': 594, 'ifindex': 12, 'irq': 292, 'pid': 3726},
 {'id': 593, 'ifindex': 12, 'irq': 291, 'pid': 3727}]
====================

Link: https://lore.kernel.org/r/170147307026.5260.9300080745237900261.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 330 insertions, 1 deletions

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 10f2124e9e23..fd98936da3ae 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -7,8 +7,25 @@
 #include <net/sock.h>
 #include <net/xdp.h>
 #include <net/xdp_sock.h>
+#include <net/netdev_rx_queue.h>
+#include <net/busy_poll.h>
 
 #include "netdev-genl-gen.h"
+#include "dev.h"
+
+struct netdev_nl_dump_ctx {
+	unsigned long	ifindex;
+	unsigned int	rxq_idx;
+	unsigned int	txq_idx;
+	unsigned int	napi_id;
+};
+
+static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb)
+{
+	NL_ASSERT_DUMP_CTX_FITS(struct netdev_nl_dump_ctx);
+
+	return (struct netdev_nl_dump_ctx *)cb->ctx;
+}
 
 static int
 netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
@@ -122,12 +139,13 @@ err_free_msg:
 
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
 	struct net *net = sock_net(skb->sk);
 	struct net_device *netdev;
 	int err = 0;
 
 	rtnl_lock();
-	for_each_netdev_dump(net, netdev, cb->args[0]) {
+	for_each_netdev_dump(net, netdev, ctx->ifindex) {
 		err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb));
 		if (err < 0)
 			break;
@@ -140,6 +158,317 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int
+netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
+			const struct genl_info *info)
+{
+	void *hdr;
+	pid_t pid;
+
+	if (WARN_ON_ONCE(!napi->dev))
+		return -EINVAL;
+	if (!(napi->dev->flags & IFF_UP))
+		return 0;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (napi->napi_id >= MIN_NAPI_ID &&
+	    nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id))
+		goto nla_put_failure;
+
+	if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex))
+		goto nla_put_failure;
+
+	if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq))
+		goto nla_put_failure;
+
+	if (napi->thread) {
+		pid = task_pid_nr(napi->thread);
+		if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
+			goto nla_put_failure;
+	}
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+}
+
+int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct napi_struct *napi;
+	struct sk_buff *rsp;
+	u32 napi_id;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID))
+		return -EINVAL;
+
+	napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	rtnl_lock();
+
+	napi = napi_by_id(napi_id);
+	if (napi)
+		err = netdev_nl_napi_fill_one(rsp, napi, info);
+	else
+		err = -EINVAL;
+
+	rtnl_unlock();
+
+	if (err)
+		goto err_free_msg;
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+	return err;
+}
+
+static int
+netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp,
+			const struct genl_info *info,
+			struct netdev_nl_dump_ctx *ctx)
+{
+	struct napi_struct *napi;
+	int err = 0;
+
+	if (!(netdev->flags & IFF_UP))
+		return err;
+
+	list_for_each_entry(napi, &netdev->napi_list, dev_list) {
+		if (ctx->napi_id && napi->napi_id >= ctx->napi_id)
+			continue;
+
+		err = netdev_nl_napi_fill_one(rsp, napi, info);
+		if (err)
+			return err;
+		ctx->napi_id = napi->napi_id;
+	}
+	return err;
+}
+
+int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	u32 ifindex = 0;
+	int err = 0;
+
+	if (info->attrs[NETDEV_A_NAPI_IFINDEX])
+		ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]);
+
+	rtnl_lock();
+	if (ifindex) {
+		netdev = __dev_get_by_index(net, ifindex);
+		if (netdev)
+			err = netdev_nl_napi_dump_one(netdev, skb, info, ctx);
+		else
+			err = -ENODEV;
+	} else {
+		for_each_netdev_dump(net, netdev, ctx->ifindex) {
+			err = netdev_nl_napi_dump_one(netdev, skb, info, ctx);
+			if (err < 0)
+				break;
+			ctx->napi_id = 0;
+		}
+	}
+	rtnl_unlock();
+
+	if (err != -EMSGSIZE)
+		return err;
+
+	return skb->len;
+}
+
+static int
+netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
+			 u32 q_idx, u32 q_type, const struct genl_info *info)
+{
+	struct netdev_rx_queue *rxq;
+	struct netdev_queue *txq;
+	void *hdr;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, q_idx) ||
+	    nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type) ||
+	    nla_put_u32(rsp, NETDEV_A_QUEUE_IFINDEX, netdev->ifindex))
+		goto nla_put_failure;
+
+	switch (q_type) {
+	case NETDEV_QUEUE_TYPE_RX:
+		rxq = __netif_get_rx_queue(netdev, q_idx);
+		if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
+					     rxq->napi->napi_id))
+			goto nla_put_failure;
+		break;
+	case NETDEV_QUEUE_TYPE_TX:
+		txq = netdev_get_tx_queue(netdev, q_idx);
+		if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
+					     txq->napi->napi_id))
+			goto nla_put_failure;
+	}
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+}
+
+static int netdev_nl_queue_validate(struct net_device *netdev, u32 q_id,
+				    u32 q_type)
+{
+	switch (q_type) {
+	case NETDEV_QUEUE_TYPE_RX:
+		if (q_id >= netdev->real_num_rx_queues)
+			return -EINVAL;
+		return 0;
+	case NETDEV_QUEUE_TYPE_TX:
+		if (q_id >= netdev->real_num_tx_queues)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int
+netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx,
+		     u32 q_type, const struct genl_info *info)
+{
+	int err = 0;
+
+	if (!(netdev->flags & IFF_UP))
+		return err;
+
+	err = netdev_nl_queue_validate(netdev, q_idx, q_type);
+	if (err)
+		return err;
+
+	return netdev_nl_queue_fill_one(rsp, netdev, q_idx, q_type, info);
+}
+
+int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	u32 q_id, q_type, ifindex;
+	struct net_device *netdev;
+	struct sk_buff *rsp;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX))
+		return -EINVAL;
+
+	q_id = nla_get_u32(info->attrs[NETDEV_A_QUEUE_ID]);
+	q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]);
+	ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	rtnl_lock();
+
+	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+	if (netdev)
+		err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info);
+	else
+		err = -ENODEV;
+
+	rtnl_unlock();
+
+	if (err)
+		goto err_free_msg;
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+	return err;
+}
+
+static int
+netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp,
+			 const struct genl_info *info,
+			 struct netdev_nl_dump_ctx *ctx)
+{
+	int err = 0;
+	int i;
+
+	if (!(netdev->flags & IFF_UP))
+		return err;
+
+	for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) {
+		err = netdev_nl_queue_fill_one(rsp, netdev, i,
+					       NETDEV_QUEUE_TYPE_RX, info);
+		if (err)
+			return err;
+		ctx->rxq_idx = i++;
+	}
+	for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) {
+		err = netdev_nl_queue_fill_one(rsp, netdev, i,
+					       NETDEV_QUEUE_TYPE_TX, info);
+		if (err)
+			return err;
+		ctx->txq_idx = i++;
+	}
+
+	return err;
+}
+
+int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	u32 ifindex = 0;
+	int err = 0;
+
+	if (info->attrs[NETDEV_A_QUEUE_IFINDEX])
+		ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]);
+
+	rtnl_lock();
+	if (ifindex) {
+		netdev = __dev_get_by_index(net, ifindex);
+		if (netdev)
+			err = netdev_nl_queue_dump_one(netdev, skb, info, ctx);
+		else
+			err = -ENODEV;
+	} else {
+		for_each_netdev_dump(net, netdev, ctx->ifindex) {
+			err = netdev_nl_queue_dump_one(netdev, skb, info, ctx);
+			if (err < 0)
+				break;
+			ctx->rxq_idx = 0;
+			ctx->txq_idx = 0;
+		}
+	}
+	rtnl_unlock();
+
+	if (err != -EMSGSIZE)
+		return err;
+
+	return skb->len;
+}
+
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
 				       unsigned long event, void *ptr)
 {