Merge branch 'ifla_xdp_expected_fd'

Toke Høiland-Jørgensen says:

====================
This series adds support for atomically replacing the XDP program loaded on an
interface. This is achieved by means of a new netlink attribute that can specify
the expected previous program to replace on the interface. If set, the kernel
will compare this "expected fd" attribute with the program currently loaded on
the interface, and reject the operation if it does not match.

With this primitive, userspace applications can avoid stepping on each other's
toes when simultaneously updating the loaded XDP program.

Changelog:

v4:
- Switch back to passing FD instead of ID (Andrii)
- Rename flag to XDP_FLAGS_REPLACE (for consistency with other similar uses)

v3:
- Pass existing ID instead of FD (Jakub)
- Use opts struct for new libbpf function (Andrii)

v2:
- Fix checkpatch nits and add .strict_start_type to netlink policy (Jakub)
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/netdevice.h

@@ -3768,7 +3768,7 @@ 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, u32 flags);
+		      int fd, int expected_fd, u32 flags);
 u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
 		    enum bpf_netdev_command cmd);
 int xdp_umem_query(struct net_device *dev, u16 queue_id);

include/uapi/linux/if_link.h

@@ -972,11 +972,12 @@ enum {
 #define XDP_FLAGS_SKB_MODE		(1U << 1)
 #define XDP_FLAGS_DRV_MODE		(1U << 2)
 #define XDP_FLAGS_HW_MODE		(1U << 3)
+#define XDP_FLAGS_REPLACE		(1U << 4)
 #define XDP_FLAGS_MODES			(XDP_FLAGS_SKB_MODE | \
 					 XDP_FLAGS_DRV_MODE | \
 					 XDP_FLAGS_HW_MODE)
 #define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST | \
-					 XDP_FLAGS_MODES)
+					 XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
 
 /* These are stored into IFLA_XDP_ATTACHED on dump. */
 enum {
@@ -996,6 +997,7 @@ enum {
 	IFLA_XDP_DRV_PROG_ID,
 	IFLA_XDP_SKB_PROG_ID,
 	IFLA_XDP_HW_PROG_ID,
+	IFLA_XDP_EXPECTED_FD,
 	__IFLA_XDP_MAX,
 };
 

net/core/dev.c

@@ -8655,15 +8655,17 @@ static void dev_xdp_uninstall(struct net_device *dev)
  *	@dev: device
  *	@extack: netlink extended ack
  *	@fd: new program fd or negative value to clear
+ *	@expected_fd: old program fd that userspace expects to replace or clear
  *	@flags: xdp-related flags
  *
  *	Set or clear a bpf program for a device
  */
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
-		      int fd, u32 flags)
+		      int fd, int expected_fd, u32 flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	enum bpf_netdev_command query;
+	u32 prog_id, expected_id = 0;
 	struct bpf_prog *prog = NULL;
 	bpf_op_t bpf_op, bpf_chk;
 	bool offload;
@@ -8684,15 +8686,29 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 	if (bpf_op == bpf_chk)
 		bpf_chk = generic_xdp_install;
 
-	if (fd >= 0) {
-		u32 prog_id;
+	prog_id = __dev_xdp_query(dev, bpf_op, query);
+	if (flags & XDP_FLAGS_REPLACE) {
+		if (expected_fd >= 0) {
+			prog = bpf_prog_get_type_dev(expected_fd,
+						     BPF_PROG_TYPE_XDP,
+						     bpf_op == ops->ndo_bpf);
+			if (IS_ERR(prog))
+				return PTR_ERR(prog);
+			expected_id = prog->aux->id;
+			bpf_prog_put(prog);
+		}
 
+		if (prog_id != expected_id) {
+			NL_SET_ERR_MSG(extack, "Active program does not match expected");
+			return -EEXIST;
+		}
+	}
+	if (fd >= 0) {
 		if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) {
 			NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time");
 			return -EEXIST;
 		}
 
-		prog_id = __dev_xdp_query(dev, bpf_op, query);
 		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) {
 			NL_SET_ERR_MSG(extack, "XDP program already attached");
 			return -EBUSY;
@@ -8715,7 +8731,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return 0;
 		}
 	} else {
-		if (!__dev_xdp_query(dev, bpf_op, query))
+		if (!prog_id)
 			return 0;
 	}
 

net/core/rtnetlink.c

@@ -1872,7 +1872,9 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
 };
 
 static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = {
+	[IFLA_XDP_UNSPEC]	= { .strict_start_type = IFLA_XDP_EXPECTED_FD },
 	[IFLA_XDP_FD]		= { .type = NLA_S32 },
+	[IFLA_XDP_EXPECTED_FD]	= { .type = NLA_S32 },
 	[IFLA_XDP_ATTACHED]	= { .type = NLA_U8 },
 	[IFLA_XDP_FLAGS]	= { .type = NLA_U32 },
 	[IFLA_XDP_PROG_ID]	= { .type = NLA_U32 },
@@ -2799,8 +2801,20 @@ static int do_setlink(const struct sk_buff *skb,
 		}
 
 		if (xdp[IFLA_XDP_FD]) {
+			int expected_fd = -1;
+
+			if (xdp_flags & XDP_FLAGS_REPLACE) {
+				if (!xdp[IFLA_XDP_EXPECTED_FD]) {
+					err = -EINVAL;
+					goto errout;
+				}
+				expected_fd =
+					nla_get_s32(xdp[IFLA_XDP_EXPECTED_FD]);
+			}
+
 			err = dev_change_xdp_fd(dev, extack,
 						nla_get_s32(xdp[IFLA_XDP_FD]),
+						expected_fd,
 						xdp_flags);
 			if (err)
 				goto errout;

tools/include/uapi/linux/if_link.h

@@ -960,11 +960,12 @@ enum {
 #define XDP_FLAGS_SKB_MODE		(1U << 1)
 #define XDP_FLAGS_DRV_MODE		(1U << 2)
 #define XDP_FLAGS_HW_MODE		(1U << 3)
+#define XDP_FLAGS_REPLACE		(1U << 4)
 #define XDP_FLAGS_MODES			(XDP_FLAGS_SKB_MODE | \
 					 XDP_FLAGS_DRV_MODE | \
 					 XDP_FLAGS_HW_MODE)
 #define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST | \
-					 XDP_FLAGS_MODES)
+					 XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
 
 /* These are stored into IFLA_XDP_ATTACHED on dump. */
 enum {
@@ -984,6 +985,7 @@ enum {
 	IFLA_XDP_DRV_PROG_ID,
 	IFLA_XDP_SKB_PROG_ID,
 	IFLA_XDP_HW_PROG_ID,
+	IFLA_XDP_EXPECTED_FD,
 	__IFLA_XDP_MAX,
 };
 

tools/lib/bpf/libbpf.h

@@ -444,7 +444,15 @@ struct xdp_link_info {
 	__u8 attach_mode;
 };
 
+struct bpf_xdp_set_link_opts {
+	size_t sz;
+	__u32 old_fd;
+};
+#define bpf_xdp_set_link_opts__last_field old_fd
+
 LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
+					const struct bpf_xdp_set_link_opts *opts);
 LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
 LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 				     size_t info_size, __u32 flags);

tools/lib/bpf/libbpf.map

@@ -244,4 +244,5 @@ LIBBPF_0.0.8 {
 		bpf_link__pin_path;
 		bpf_link__unpin;
 		bpf_program__set_attach_target;
+		bpf_set_link_xdp_fd_opts;
 } LIBBPF_0.0.7;

tools/lib/bpf/netlink.c

@@ -132,7 +132,8 @@ done:
 	return ret;
 }
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
+					 __u32 flags)
 {
 	int sock, seq = 0, ret;
 	struct nlattr *nla, *nla_xdp;
@@ -178,6 +179,14 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		nla->nla_len += nla_xdp->nla_len;
 	}
 
+	if (flags & XDP_FLAGS_REPLACE) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd));
+		nla->nla_len += nla_xdp->nla_len;
+	}
+
 	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
 
 	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
@@ -191,6 +200,29 @@ cleanup:
 	return ret;
 }
 
+int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
+			     const struct bpf_xdp_set_link_opts *opts)
+{
+	int old_fd = -1;
+
+	if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
+		return -EINVAL;
+
+	if (OPTS_HAS(opts, old_fd)) {
+		old_fd = OPTS_GET(opts, old_fd, -1);
+		flags |= XDP_FLAGS_REPLACE;
+	}
+
+	return __bpf_set_link_xdp_fd_replace(ifindex, fd,
+					     old_fd,
+					     flags);
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	return __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+}
+
 static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 			     libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {

tools/testing/selftests/bpf/prog_tests/xdp_attach.c

@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+#define IFINDEX_LO 1
+#define XDP_FLAGS_REPLACE		(1U << 4)
+
+void test_xdp_attach(void)
+{
+	struct bpf_object *obj1, *obj2, *obj3;
+	const char *file = "./test_xdp.o";
+	int err, fd1, fd2, fd3;
+	__u32 duration = 0;
+	DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts,
+			    .old_fd = -1);
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1);
+	if (CHECK_FAIL(err))
+		return;
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2);
+	if (CHECK_FAIL(err))
+		goto out_1;
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3);
+	if (CHECK_FAIL(err))
+		goto out_2;
+
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE,
+				       &opts);
+	if (CHECK(err, "load_ok", "initial load failed"))
+		goto out_close;
+
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE,
+				       &opts);
+	if (CHECK(!err, "load_fail", "load with expected id didn't fail"))
+		goto out;
+
+	opts.old_fd = fd1;
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts);
+	if (CHECK(err, "replace_ok", "replace valid old_fd failed"))
+		goto out;
+
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts);
+	if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail"))
+		goto out;
+
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts);
+	if (CHECK(!err, "remove_fail", "remove invalid old_fd didn't fail"))
+		goto out;
+
+	opts.old_fd = fd2;
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts);
+	if (CHECK(err, "remove_ok", "remove valid old_fd failed"))
+		goto out;
+
+out:
+	bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
+out_close:
+	bpf_object__close(obj3);
+out_2:
+	bpf_object__close(obj2);
+out_1:
+	bpf_object__close(obj1);
+}