Message-ID: <20200716045602.3896926-5-andriin@fb.com>
Date:   Wed, 15 Jul 2020 21:55:56 -0700
From:   Andrii Nakryiko <andriin@...com>
To:     <bpf@...r.kernel.org>, <netdev@...r.kernel.org>, <ast@...com>,
        <daniel@...earbox.net>, <dsahern@...il.com>
CC:     <andrii.nakryiko@...il.com>, <kernel-team@...com>,
        Andrii Nakryiko <andriin@...com>
Subject: [PATCH v3 bpf-next 4/9] bpf, xdp: add bpf_link-based XDP attachment API

Add bpf_link-based API (bpf_xdp_link) to attach BPF XDP program through
BPF_LINK_CREATE command.

bpf_xdp_link is mutually exclusive with direct BPF program attachment,
previous BPF program should be detached prior to attempting to create a new
bpf_xdp_link attachment (for a given XDP mode). Once BPF link is attached, it
can't be replaced by other BPF program attachment or link attachment. It will
be detached only when the last BPF link FD is closed.

bpf_xdp_link will be auto-detached when net_device is shutdown, similarly to
how other BPF links behave (cgroup, flow_dissector). At that point bpf_link
will become defunct, but won't be destroyed until last FD is closed.

Signed-off-by: Andrii Nakryiko <andriin@...com>
---
 include/linux/netdevice.h |   4 +
 include/uapi/linux/bpf.h  |   7 +-
 kernel/bpf/syscall.c      |   5 ++
 net/core/dev.c            | 169 ++++++++++++++++++++++++++++++++++++--
 4 files changed, 178 insertions(+), 7 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cad44b40c776..7d3c412fcfe5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -888,6 +888,7 @@ struct bpf_prog_offload_ops;
 struct netlink_ext_ack;
 struct xdp_umem;
 struct xdp_dev_bulk_queue;
+struct bpf_xdp_link;
 
 enum bpf_xdp_mode {
 	XDP_MODE_SKB = 0,
@@ -898,6 +899,7 @@ enum bpf_xdp_mode {
 
 struct bpf_xdp_entity {
 	struct bpf_prog *prog;
+	struct bpf_xdp_link *link;
 };
 
 struct netdev_bpf {
@@ -3831,7 +3833,9 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags);
+int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
+
 int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5e386389913a..b4385e516aeb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -227,6 +227,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
 	BPF_CGROUP_INET_SOCK_RELEASE,
+	BPF_XDP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -239,6 +240,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_CGROUP = 3,
 	BPF_LINK_TYPE_ITER = 4,
 	BPF_LINK_TYPE_NETNS = 5,
+	BPF_LINK_TYPE_XDP = 6,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -604,7 +606,10 @@ union bpf_attr {
 
 	struct { /* struct used by BPF_LINK_CREATE command */
 		__u32		prog_fd;	/* eBPF program to attach */
-		__u32		target_fd;	/* object to attach to */
+		union {
+			__u32		target_fd;	/* object to attach to */
+			__u32		target_ifindex; /* target ifindex */
+		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 	} link_create;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7ea9dfbebd8c..23e9c5807274 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2817,6 +2817,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_CGROUP_SOCKOPT;
 	case BPF_TRACE_ITER:
 		return BPF_PROG_TYPE_TRACING;
+	case BPF_XDP:
+		return BPF_PROG_TYPE_XDP;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -3893,6 +3895,9 @@ static int link_create(union bpf_attr *attr)
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 		ret = netns_bpf_link_create(attr, prog);
 		break;
+	case BPF_PROG_TYPE_XDP:
+		ret = bpf_xdp_link_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index 6c315af8f588..ba50f68a6121 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8714,6 +8714,12 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down_generic);
 
+struct bpf_xdp_link {
+	struct bpf_link link;
+	struct net_device *dev; /* protected by rtnl_lock, no refcnt held */
+	int flags;
+};
+
 static enum bpf_xdp_mode dev_xdp_mode(u32 flags)
 {
 	if (flags & XDP_FLAGS_HW_MODE)
@@ -8736,9 +8742,19 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
 	};
 }
 
+static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
+					 enum bpf_xdp_mode mode)
+{
+	return dev->xdp_state[mode].link;
+}
+
 static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
 				     enum bpf_xdp_mode mode)
 {
+	struct bpf_xdp_link *link = dev_xdp_link(dev, mode);
+
+	if (link)
+		return link->link.prog;
 	return dev->xdp_state[mode].prog;
 }
 
@@ -8749,9 +8765,17 @@ u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 	return prog ? prog->aux->id : 0;
 }
 
+static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode,
+			     struct bpf_xdp_link *link)
+{
+	dev->xdp_state[mode].link = link;
+	dev->xdp_state[mode].prog = NULL;
+}
+
 static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode,
 			     struct bpf_prog *prog)
 {
+	dev->xdp_state[mode].link = NULL;
 	dev->xdp_state[mode].prog = prog;
 }
 
@@ -8791,6 +8815,7 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
 
 static void dev_xdp_uninstall(struct net_device *dev)
 {
+	struct bpf_xdp_link *link;
 	struct bpf_prog *prog;
 	enum bpf_xdp_mode mode;
 	bpf_op_t bpf_op;
@@ -8808,14 +8833,20 @@ static void dev_xdp_uninstall(struct net_device *dev)
 
 		WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
 
-		bpf_prog_put(prog);
-		dev_xdp_set_prog(dev, mode, NULL);
+		/* auto-detach link from net device */
+		link = dev_xdp_link(dev, mode);
+		if (link)
+			link->dev = NULL;
+		else
+			bpf_prog_put(prog);
+
+		dev_xdp_set_link(dev, mode, NULL);
 	}
 }
 
 static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack,
-			  struct bpf_prog *new_prog, struct bpf_prog *old_prog,
-			  u32 flags)
+			  struct bpf_xdp_link *link, struct bpf_prog *new_prog,
+			  struct bpf_prog *old_prog, u32 flags)
 {
 	struct bpf_prog *cur_prog;
 	enum bpf_xdp_mode mode;
@@ -8824,6 +8855,14 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 
 	ASSERT_RTNL();
 
+	/* either link or prog attachment, never both */
+	if (link && (new_prog || old_prog))
+		return -EINVAL;
+	/* link supports only XDP mode flags */
+	if (link && (flags & ~XDP_FLAGS_MODES)) {
+		NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment");
+		return -EINVAL;
+	}
 	/* just one XDP mode bit should be set, zero defaults to SKB mode */
 	if (hweight32(flags & XDP_FLAGS_MODES) > 1) {
 		NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set");
@@ -8836,7 +8875,18 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 	}
 
 	mode = dev_xdp_mode(flags);
+	/* can't replace attached link */
+	if (dev_xdp_link(dev, mode)) {
+		NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link");
+		return -EBUSY;
+	}
+
 	cur_prog = dev_xdp_prog(dev, mode);
+	/* can't replace attached prog with link */
+	if (link && cur_prog) {
+		NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link");
+		return -EBUSY;
+	}
 	if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) {
 		NL_SET_ERR_MSG(extack, "Active program does not match expected");
 		return -EEXIST;
@@ -8846,6 +8896,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		return -EBUSY;
 	}
 
+	/* put effective new program into new_prog */
+	if (link)
+		new_prog = link->link.prog;
+
 	if (new_prog) {
 		bool offload = mode == XDP_MODE_HW;
 		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
@@ -8878,13 +8932,116 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 			return err;
 	}
 
-	dev_xdp_set_prog(dev, mode, new_prog);
+	if (link)
+		dev_xdp_set_link(dev, mode, link);
+	else
+		dev_xdp_set_prog(dev, mode, new_prog);
 	if (cur_prog)
 		bpf_prog_put(cur_prog);
 
 	return 0;
 }
 
+static int dev_xdp_attach_link(struct net_device *dev,
+			       struct netlink_ext_ack *extack,
+			       struct bpf_xdp_link *link)
+{
+	return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags);
+}
+
+static int dev_xdp_detach_link(struct net_device *dev,
+			       struct netlink_ext_ack *extack,
+			       struct bpf_xdp_link *link)
+{
+	enum bpf_xdp_mode mode;
+	bpf_op_t bpf_op;
+
+	ASSERT_RTNL();
+
+	mode = dev_xdp_mode(link->flags);
+	if (dev_xdp_link(dev, mode) != link)
+		return -EINVAL;
+
+	bpf_op = dev_xdp_bpf_op(dev, mode);
+	WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL));
+	dev_xdp_set_link(dev, mode, NULL);
+	return 0;
+}
+
+static void bpf_xdp_link_release(struct bpf_link *link)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+
+	rtnl_lock();
+
+	/* if racing with net_device's tear down, xdp_link->dev might be
+	 * already NULL, in which case link was already auto-detached
+	 */
+	if (xdp_link->dev)
+		WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link));
+
+	rtnl_unlock();
+}
+
+static void bpf_xdp_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link);
+
+	kfree(xdp_link);
+}
+
+static const struct bpf_link_ops bpf_xdp_link_lops = {
+	.release = bpf_xdp_link_release,
+	.dealloc = bpf_xdp_link_dealloc,
+};
+
+int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_link_primer link_primer;
+	struct bpf_xdp_link *link;
+	struct net_device *dev;
+	int err, fd;
+
+	dev = dev_get_by_index(net, attr->link_create.target_ifindex);
+	if (!dev)
+		return -EINVAL;
+
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
+		goto out_put_dev;
+	}
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
+	link->dev = dev;
+	link->flags = attr->link_create.flags;
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		goto out_put_dev;
+	}
+
+	rtnl_lock();
+	err = dev_xdp_attach_link(dev, NULL, link);
+	rtnl_unlock();
+
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		goto out_put_dev;
+	}
+
+	fd = bpf_link_settle(&link_primer);
+	/* link itself doesn't hold dev's refcnt to not complicate shutdown */
+	dev_put(dev);
+	return fd;
+
+out_put_dev:
+	dev_put(dev);
+	return err;
+}
+
 /**
  *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
  *	@dev: device
@@ -8921,7 +9078,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		}
 	}
 
-	err = dev_xdp_attach(dev, extack, new_prog, old_prog, flags);
+	err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags);
 
 err_out:
 	if (err && new_prog)
-- 
2.24.1

Powered by blists - more mailing lists