Merge branch 'af-xdp-sock-diag'

Björn Töpel says:

====================
This series adds an AF_XDP sock_diag interface for querying sockets
from user-space. Tools like iproute2 ss(8) can use this interface to
list open AF_XDP sockets.

The diagnostic provides information about the Rx/Tx/fill/completetion
rings, umem, memory usage and such. For a complete list, please refer
to the xsk_diag.c file.

The AF_XDP sock_diag interface is optional, and can be built as a
module. A separate patch series, adding ss(8) iproute2 support, will
follow.

v1->v2:
* Removed extra newline
* Zero-out all user-space facing structures prior setting the
members
* Added explicit "pad" member in _msg struct
* Removed unused variable "req" in xsk_diag_handler_dump()

Thanks to Daniel for reviewing the series!
====================

Signed-off-by: Daniel Borkmann <[e-mail]>

include/net/net_namespace.h

···
 #include <net/netns/xfrm.h>
 #include <net/netns/mpls.h>
 #include <net/netns/can.h>
+#include <net/netns/xdp.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 #include <linux/skbuff.h>
···
 #endif
 #if IS_ENABLED(CONFIG_CAN)
 	struct netns_can	can;
+#endif
+#ifdef CONFIG_XDP_SOCKETS
+	struct netns_xdp	xdp;
 #endif
 	struct sock		*diag_nlsk;
 	atomic_t		fnhe_genid;

include/net/netns/xdp.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NETNS_XDP_H__
+#define __NETNS_XDP_H__
+
+#include <linux/rculist.h>
+#include <linux/mutex.h>
+
+struct netns_xdp {
+	struct mutex		lock;
+	struct hlist_head	list;
+};
+
+#endif /* __NETNS_XDP_H__ */

include/net/xdp_sock.h

···
 	struct work_struct work;
 	struct page **pgs;
 	u32 npgs;
+	int id;
 	struct net_device *dev;
 	struct xdp_umem_fq_reuse *fq_reuse;
 	u16 queue_id;

include/uapi/linux/xdp_diag.h

···
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * xdp_diag: interface for query/monitor XDP sockets
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+#ifndef _LINUX_XDP_DIAG_H
+#define _LINUX_XDP_DIAG_H
+
+#include <linux/types.h>
+
+struct xdp_diag_req {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+	__u16	pad;
+	__u32	xdiag_ino;
+	__u32	xdiag_show;
+	__u32	xdiag_cookie[2];
+};
+
+struct xdp_diag_msg {
+	__u8	xdiag_family;
+	__u8	xdiag_type;
+	__u16	pad;
+	__u32	xdiag_ino;
+	__u32	xdiag_cookie[2];
+};
+
+#define XDP_SHOW_INFO		(1 << 0) /* Basic information */
+#define XDP_SHOW_RING_CFG	(1 << 1)
+#define XDP_SHOW_UMEM		(1 << 2)
+#define XDP_SHOW_MEMINFO	(1 << 3)
+
+enum {
+	XDP_DIAG_NONE,
+	XDP_DIAG_INFO,
+	XDP_DIAG_UID,
+	XDP_DIAG_RX_RING,
+	XDP_DIAG_TX_RING,
+	XDP_DIAG_UMEM,
+	XDP_DIAG_UMEM_FILL_RING,
+	XDP_DIAG_UMEM_COMPLETION_RING,
+	XDP_DIAG_MEMINFO,
+	__XDP_DIAG_MAX,
+};
+
+#define XDP_DIAG_MAX (__XDP_DIAG_MAX - 1)
+
+struct xdp_diag_info {
+	__u32	ifindex;
+	__u32	queue_id;
+};
+
+struct xdp_diag_ring {
+	__u32	entries; /*num descs */
+};
+
+#define XDP_DU_F_ZEROCOPY (1 << 0)
+
+struct xdp_diag_umem {
+	__u64	size;
+	__u32	id;
+	__u32	num_pages;
+	__u32	chunk_size;
+	__u32	headroom;
+	__u32	ifindex;
+	__u32	queue_id;
+	__u32	flags;
+	__u32	refs;
+};
+
+#endif /* _LINUX_XDP_DIAG_H */

net/xdp/Kconfig

···
 	help
 	  XDP sockets allows a channel between XDP programs and
 	  userspace applications.
+
+config XDP_SOCKETS_DIAG
+	tristate "XDP sockets: monitoring interface"
+	depends on XDP_SOCKETS
+	default n
+	help
+	  Support for PF_XDP sockets monitoring interface used by the ss tool.
+	  If unsure, say Y.

net/xdp/Makefile

···
 obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o
+obj-$(CONFIG_XDP_SOCKETS_DIAG) += xsk_diag.o

net/xdp/xdp_umem.c

···
 #include <linux/mm.h>
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
+#include <linux/idr.h>
 
 #include "xdp_umem.h"
 #include "xsk_queue.h"
 
 #define XDP_UMEM_MIN_CHUNK_SIZE 2048
+
+static DEFINE_IDA(umem_ida);
 
 void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 {
···
 	struct mm_struct *mm;
 
 	xdp_umem_clear_dev(umem);
+
+	ida_simple_remove(&umem_ida, umem->id);
 
 	if (umem->fq) {
 		xskq_destroy(umem->fq);
···
 	if (!umem)
 		return ERR_PTR(-ENOMEM);
 
+	err = ida_simple_get(&umem_ida, 0, 0, GFP_KERNEL);
+	if (err < 0) {
+		kfree(umem);
+		return ERR_PTR(err);
+	}
+	umem->id = err;
+
 	err = xdp_umem_reg(umem, mr);
 	if (err) {
+		ida_simple_remove(&umem_ida, umem->id);
 		kfree(umem);
 		return ERR_PTR(err);
 	}

net/xdp/xsk.c

···
 
 #include "xsk_queue.h"
 #include "xdp_umem.h"
+#include "xsk.h"
 
 #define TX_BATCH_SIZE 16
-
-static struct xdp_sock *xdp_sk(struct sock *sk)
-{
-	return (struct xdp_sock *)sk;
-}
 
 bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
 {
···
 		return 0;
 
 	net = sock_net(sk);
+
+	mutex_lock(&net->xdp.lock);
+	sk_del_node_init_rcu(sk);
+	mutex_unlock(&net->xdp.lock);
 
 	local_bh_disable();
 	sock_prot_inuse_add(net, sk->sk_prot, -1);
···
 	mutex_init(&xs->mutex);
 	spin_lock_init(&xs->tx_completion_lock);
 
+	mutex_lock(&net->xdp.lock);
+	sk_add_node_rcu(sk, &net->xdp.list);
+	mutex_unlock(&net->xdp.lock);
+
 	local_bh_disable();
 	sock_prot_inuse_add(net, &xsk_proto, 1);
 	local_bh_enable();
···
 	.family = PF_XDP,
 	.create = xsk_create,
 	.owner	= THIS_MODULE,
+};
+
+static int __net_init xsk_net_init(struct net *net)
+{
+	mutex_init(&net->xdp.lock);
+	INIT_HLIST_HEAD(&net->xdp.list);
+	return 0;
+}
+
+static void __net_exit xsk_net_exit(struct net *net)
+{
+	WARN_ON_ONCE(!hlist_empty(&net->xdp.list));
+}
+
+static struct pernet_operations xsk_net_ops = {
+	.init = xsk_net_init,
+	.exit = xsk_net_exit,
 };
 
 static int __init xsk_init(void)
···
 	if (err)
 		goto out_proto;
 
+	err = register_pernet_subsys(&xsk_net_ops);
+	if (err)
+		goto out_sk;
 	return 0;
 
+out_sk:
+	sock_unregister(PF_XDP);
 out_proto:
 	proto_unregister(&xsk_proto);
 out:

net/xdp/xsk.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2019 Intel Corporation. */
+
+#ifndef XSK_H_
+#define XSK_H_
+
+static inline struct xdp_sock *xdp_sk(struct sock *sk)
+{
+	return (struct xdp_sock *)sk;
+}
+
+#endif /* XSK_H_ */

net/xdp/xsk_diag.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* XDP sockets monitoring support
+ *
+ * Copyright(c) 2019 Intel Corporation.
+ *
+ * Author: Björn Töpel <[e-mail]>
+ */
+
+#include <linux/module.h>
+#include <net/xdp_sock.h>
+#include <linux/xdp_diag.h>
+#include <linux/sock_diag.h>
+
+#include "xsk_queue.h"
+#include "xsk.h"
+
+static int xsk_diag_put_info(const struct xdp_sock *xs, struct sk_buff *nlskb)
+{
+	struct xdp_diag_info di = {};
+
+	di.ifindex = xs->dev ? xs->dev->ifindex : 0;
+	di.queue_id = xs->queue_id;
+	return nla_put(nlskb, XDP_DIAG_INFO, sizeof(di), &di);
+}
+
+static int xsk_diag_put_ring(const struct xsk_queue *queue, int nl_type,
+			     struct sk_buff *nlskb)
+{
+	struct xdp_diag_ring dr = {};
+
+	dr.entries = queue->nentries;
+	return nla_put(nlskb, nl_type, sizeof(dr), &dr);
+}
+
+static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs,
+				  struct sk_buff *nlskb)
+{
+	int err = 0;
+
+	if (xs->rx)
+		err = xsk_diag_put_ring(xs->rx, XDP_DIAG_RX_RING, nlskb);
+	if (!err && xs->tx)
+		err = xsk_diag_put_ring(xs->tx, XDP_DIAG_TX_RING, nlskb);
+	return err;
+}
+
+static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
+{
+	struct xdp_umem *umem = xs->umem;
+	struct xdp_diag_umem du = {};
+	int err;
+
+	if (!umem)
+		return 0;
+
+	du.id = umem->id;
+	du.size = umem->size;
+	du.num_pages = umem->npgs;
+	du.chunk_size = (__u32)(~umem->chunk_mask + 1);
+	du.headroom = umem->headroom;
+	du.ifindex = umem->dev ? umem->dev->ifindex : 0;
+	du.queue_id = umem->queue_id;
+	du.flags = 0;
+	if (umem->zc)
+		du.flags |= XDP_DU_F_ZEROCOPY;
+	du.refs = refcount_read(&umem->users);
+
+	err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du);
+
+	if (!err && umem->fq)
+		err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_FILL_RING, nlskb);
+	if (!err && umem->cq) {
+		err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_COMPLETION_RING,
+					nlskb);
+	}
+	return err;
+}
+
+static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb,
+			 struct xdp_diag_req *req,
+			 struct user_namespace *user_ns,
+			 u32 portid, u32 seq, u32 flags, int sk_ino)
+{
+	struct xdp_sock *xs = xdp_sk(sk);
+	struct xdp_diag_msg *msg;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(nlskb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*msg),
+			flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	msg = nlmsg_data(nlh);
+	memset(msg, 0, sizeof(*msg));
+	msg->xdiag_family = AF_XDP;
+	msg->xdiag_type = sk->sk_type;
+	msg->xdiag_ino = sk_ino;
+	sock_diag_save_cookie(sk, msg->xdiag_cookie);
+
+	if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_INFO) &&
+	    nla_put_u32(nlskb, XDP_DIAG_UID,
+			from_kuid_munged(user_ns, sock_i_uid(sk))))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_RING_CFG) &&
+	    xsk_diag_put_rings_cfg(xs, nlskb))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_UMEM) &&
+	    xsk_diag_put_umem(xs, nlskb))
+		goto out_nlmsg_trim;
+
+	if ((req->xdiag_show & XDP_SHOW_MEMINFO) &&
+	    sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO))
+		goto out_nlmsg_trim;
+
+	nlmsg_end(nlskb, nlh);
+	return 0;
+
+out_nlmsg_trim:
+	nlmsg_cancel(nlskb, nlh);
+	return -EMSGSIZE;
+}
+
+static int xsk_diag_dump(struct sk_buff *nlskb, struct netlink_callback *cb)
+{
+	struct xdp_diag_req *req = nlmsg_data(cb->nlh);
+	struct net *net = sock_net(nlskb->sk);
+	int num = 0, s_num = cb->args[0];
+	struct sock *sk;
+
+	mutex_lock(&net->xdp.lock);
+
+	sk_for_each(sk, &net->xdp.list) {
+		if (!net_eq(sock_net(sk), net))
+			continue;
+		if (num++ < s_num)
+			continue;
+
+		if (xsk_diag_fill(sk, nlskb, req,
+				  sk_user_ns(NETLINK_CB(cb->skb).sk),
+				  NETLINK_CB(cb->skb).portid,
+				  cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				  sock_i_ino(sk)) < 0) {
+			num--;
+			break;
+		}
+	}
+
+	mutex_unlock(&net->xdp.lock);
+	cb->args[0] = num;
+	return nlskb->len;
+}
+
+static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr)
+{
+	struct netlink_dump_control c = { .dump = xsk_diag_dump };
+	int hdrlen = sizeof(struct xdp_diag_req);
+	struct net *net = sock_net(nlskb->sk);
+
+	if (nlmsg_len(hdr) < hdrlen)
+		return -EINVAL;
+
+	if (!(hdr->nlmsg_flags & NLM_F_DUMP))
+		return -EOPNOTSUPP;
+
+	return netlink_dump_start(net->diag_nlsk, nlskb, hdr, &c);
+}
+
+static const struct sock_diag_handler xsk_diag_handler = {
+	.family = AF_XDP,
+	.dump = xsk_diag_handler_dump,
+};
+
+static int __init xsk_diag_init(void)
+{
+	return sock_diag_register(&xsk_diag_handler);
+}
+
+static void __exit xsk_diag_exit(void)
+{
+	sock_diag_unregister(&xsk_diag_handler);
+}
+
+module_init(xsk_diag_init);
+module_exit(xsk_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP);