Merge branch 'libbpf-xdp-support'

Eric Leblond says:

====================
Here is an updated v8 version:
- add if_link.h in uapi and remove the definition
- fix a commit message
- remove uapi from a include
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

samples/bpf/Makefile

@@ -45,7 +45,7 @@ hostprogs-y += xdp_rxq_info
 hostprogs-y += syscall_tp
 
 # Libbpf dependencies
-LIBBPF := ../../tools/lib/bpf/bpf.o
+LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
 CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
 
 test_lru_dist-objs := test_lru_dist.o $(LIBBPF)

samples/bpf/bpf_load.c

@@ -695,105 +695,3 @@ struct ksym *ksym_search(long key)
 	return &syms[0];
 }
 
-int set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
-	struct sockaddr_nl sa;
-	int sock, seq = 0, len, ret = -1;
-	char buf[4096];
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
-	struct nlmsghdr *nh;
-	struct nlmsgerr *err;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.nl_family = AF_NETLINK;
-
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
-	if (sock < 0) {
-		printf("open netlink socket: %s\n", strerror(errno));
-		return -1;
-	}
-
-	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
-		printf("bind to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
-	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
-	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		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) {
-		printf("send to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	len = recv(sock, buf, sizeof(buf), 0);
-	if (len < 0) {
-		printf("recv from netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
-	     nh = NLMSG_NEXT(nh, len)) {
-		if (nh->nlmsg_pid != getpid()) {
-			printf("Wrong pid %d, expected %d\n",
-			       nh->nlmsg_pid, getpid());
-			goto cleanup;
-		}
-		if (nh->nlmsg_seq != seq) {
-			printf("Wrong seq %d, expected %d\n",
-			       nh->nlmsg_seq, seq);
-			goto cleanup;
-		}
-		switch (nh->nlmsg_type) {
-		case NLMSG_ERROR:
-			err = (struct nlmsgerr *)NLMSG_DATA(nh);
-			if (!err->error)
-				continue;
-			printf("nlmsg error %s\n", strerror(-err->error));
-			goto cleanup;
-		case NLMSG_DONE:
-			break;
-		}
-	}
-
-	ret = 0;
-
-cleanup:
-	close(sock);
-	return ret;
-}

samples/bpf/bpf_load.h

@@ -61,5 +61,5 @@ struct ksym {
 
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
-int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 #endif

samples/bpf/xdp1_user.c

@@ -25,7 +25,7 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -116,7 +116,7 @@ int main(int argc, char **argv)
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}

samples/bpf/xdp_redirect_cpu_user.c

@@ -26,7 +26,7 @@ static const char *__doc__ =
 
 /* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
  * use bpf/libbpf.h), but cannot as (currently) needed for XDP
- * attaching to a device via set_link_xdp_fd()
+ * attaching to a device via bpf_set_link_xdp_fd()
  */
 #include "libbpf.h"
 #include "bpf_load.h"
@@ -67,7 +67,7 @@ static void int_exit(int sig)
 		"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
 		ifindex, ifname);
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(EXIT_OK);
 }
 
@@ -682,7 +682,7 @@ int main(int argc, char **argv)
 	/* Remove XDP program when program is interrupted */
 	signal(SIGINT, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
 		fprintf(stderr, "link set xdp fd failed\n");
 		return EXIT_FAIL_XDP;
 	}

samples/bpf/xdp_redirect_map_user.c

@@ -34,9 +34,9 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
 	if (ifindex_out_xdp_dummy_attached)
-		set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
 	exit(0);
 }
 
@@ -120,13 +120,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
 		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
 		return 1;
 	}
 
 	/* Loading dummy XDP prog on out-device */
-	if (set_link_xdp_fd(ifindex_out, prog_fd[1],
+	if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
 			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
 		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
 		ifindex_out_xdp_dummy_attached = false;

samples/bpf/xdp_redirect_user.c

@@ -33,9 +33,9 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
 	if (ifindex_out_xdp_dummy_attached)
-		set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
 	exit(0);
 }
 
@@ -114,13 +114,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
 		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
 		return 1;
 	}
 
 	/* Loading dummy XDP prog on out-device */
-	if (set_link_xdp_fd(ifindex_out, prog_fd[1],
+	if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
 			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
 		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
 		ifindex_out_xdp_dummy_attached = false;

samples/bpf/xdp_router_ipv4_user.c

@@ -37,7 +37,7 @@ static void int_exit(int sig)
 	int i = 0;
 
 	for (i = 0; i < total_ifindex; i++)
-		set_link_xdp_fd(ifindex_list[i], -1, flags);
+		bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 	exit(0);
 }
 
@@ -49,7 +49,7 @@ static void close_and_exit(int sig)
 	close(sock_arp);
 
 	for (i = 0; i < total_ifindex; i++)
-		set_link_xdp_fd(ifindex_list[i], -1, flags);
+		bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 	exit(0);
 }
 
@@ -183,7 +183,7 @@ static void read_route(struct nlmsghdr *nh, int nll)
 			int i = 0;
 
 			for (i = 0; i < total_ifindex; i++)
-				set_link_xdp_fd(ifindex_list[i], -1, flags);
+				bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 			exit(0);
 		}
 		assert(bpf_map_update_elem(map_fd[4], &route.iface, &route.iface, 0) == 0);
@@ -633,12 +633,12 @@ int main(int ac, char **argv)
 		}
 	}
 	for (i = 0; i < total_ifindex; i++) {
-		if (set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) {
+		if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) {
 			printf("link set xdp fd failed\n");
 			int recovery_index = i;
 
 			for (i = 0; i < recovery_index; i++)
-				set_link_xdp_fd(ifindex_list[i], -1, flags);
+				bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 
 			return 1;
 		}

samples/bpf/xdp_rxq_info_user.c

@@ -56,7 +56,7 @@ static void int_exit(int sig)
 		"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
 		ifindex, ifname);
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(EXIT_OK);
 }
 
@@ -521,7 +521,7 @@ int main(int argc, char **argv)
 	/* Remove XDP program when program is interrupted */
 	signal(SIGINT, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		fprintf(stderr, "link set xdp fd failed\n");
 		return EXIT_FAIL_XDP;
 	}

samples/bpf/xdp_tx_iptunnel_user.c

@@ -30,7 +30,7 @@ static __u32 xdp_flags = 0;
 static void int_exit(int sig)
 {
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -254,14 +254,14 @@ int main(int argc, char **argv)
 		}
 	}
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}
 
 	poll_stats(kill_after_s);
 
-	set_link_xdp_fd(ifindex, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 
 	return 0;
 }

tools/include/uapi/linux/netlink.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__LINUX_NETLINK_H
+#define _UAPI__LINUX_NETLINK_H
+
+#include <linux/kernel.h>
+#include <linux/socket.h> /* for __kernel_sa_family_t */
+#include <linux/types.h>
+
+#define NETLINK_ROUTE		0	/* Routing/device hook				*/
+#define NETLINK_UNUSED		1	/* Unused number				*/
+#define NETLINK_USERSOCK	2	/* Reserved for user mode socket protocols 	*/
+#define NETLINK_FIREWALL	3	/* Unused number, formerly ip_queue		*/
+#define NETLINK_SOCK_DIAG	4	/* socket monitoring				*/
+#define NETLINK_NFLOG		5	/* netfilter/iptables ULOG */
+#define NETLINK_XFRM		6	/* ipsec */
+#define NETLINK_SELINUX		7	/* SELinux event notifications */
+#define NETLINK_ISCSI		8	/* Open-iSCSI */
+#define NETLINK_AUDIT		9	/* auditing */
+#define NETLINK_FIB_LOOKUP	10	
+#define NETLINK_CONNECTOR	11
+#define NETLINK_NETFILTER	12	/* netfilter subsystem */
+#define NETLINK_IP6_FW		13
+#define NETLINK_DNRTMSG		14	/* DECnet routing messages */
+#define NETLINK_KOBJECT_UEVENT	15	/* Kernel messages to userspace */
+#define NETLINK_GENERIC		16
+/* leave room for NETLINK_DM (DM Events) */
+#define NETLINK_SCSITRANSPORT	18	/* SCSI Transports */
+#define NETLINK_ECRYPTFS	19
+#define NETLINK_RDMA		20
+#define NETLINK_CRYPTO		21	/* Crypto layer */
+#define NETLINK_SMC		22	/* SMC monitoring */
+
+#define NETLINK_INET_DIAG	NETLINK_SOCK_DIAG
+
+#define MAX_LINKS 32		
+
+struct sockaddr_nl {
+	__kernel_sa_family_t	nl_family;	/* AF_NETLINK	*/
+	unsigned short	nl_pad;		/* zero		*/
+	__u32		nl_pid;		/* port ID	*/
+       	__u32		nl_groups;	/* multicast groups mask */
+};
+
+struct nlmsghdr {
+	__u32		nlmsg_len;	/* Length of message including header */
+	__u16		nlmsg_type;	/* Message content */
+	__u16		nlmsg_flags;	/* Additional flags */
+	__u32		nlmsg_seq;	/* Sequence number */
+	__u32		nlmsg_pid;	/* Sending process port ID */
+};
+
+/* Flags values */
+
+#define NLM_F_REQUEST		0x01	/* It is request message. 	*/
+#define NLM_F_MULTI		0x02	/* Multipart message, terminated by NLMSG_DONE */
+#define NLM_F_ACK		0x04	/* Reply with ack, with zero or error code */
+#define NLM_F_ECHO		0x08	/* Echo this request 		*/
+#define NLM_F_DUMP_INTR		0x10	/* Dump was inconsistent due to sequence change */
+#define NLM_F_DUMP_FILTERED	0x20	/* Dump was filtered as requested */
+
+/* Modifiers to GET request */
+#define NLM_F_ROOT	0x100	/* specify tree	root	*/
+#define NLM_F_MATCH	0x200	/* return all matching	*/
+#define NLM_F_ATOMIC	0x400	/* atomic GET		*/
+#define NLM_F_DUMP	(NLM_F_ROOT|NLM_F_MATCH)
+
+/* Modifiers to NEW request */
+#define NLM_F_REPLACE	0x100	/* Override existing		*/
+#define NLM_F_EXCL	0x200	/* Do not touch, if it exists	*/
+#define NLM_F_CREATE	0x400	/* Create, if it does not exist	*/
+#define NLM_F_APPEND	0x800	/* Add to end of list		*/
+
+/* Modifiers to DELETE request */
+#define NLM_F_NONREC	0x100	/* Do not delete recursively	*/
+
+/* Flags for ACK message */
+#define NLM_F_CAPPED	0x100	/* request was capped */
+#define NLM_F_ACK_TLVS	0x200	/* extended ACK TVLs were included */
+
+/*
+   4.4BSD ADD		NLM_F_CREATE|NLM_F_EXCL
+   4.4BSD CHANGE	NLM_F_REPLACE
+
+   True CHANGE		NLM_F_CREATE|NLM_F_REPLACE
+   Append		NLM_F_CREATE
+   Check		NLM_F_EXCL
+ */
+
+#define NLMSG_ALIGNTO	4U
+#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
+#define NLMSG_HDRLEN	 ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
+#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
+#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
+#define NLMSG_DATA(nlh)  ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
+#define NLMSG_NEXT(nlh,len)	 ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
+				  (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
+#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
+			   (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
+			   (nlh)->nlmsg_len <= (len))
+#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
+
+#define NLMSG_NOOP		0x1	/* Nothing.		*/
+#define NLMSG_ERROR		0x2	/* Error		*/
+#define NLMSG_DONE		0x3	/* End of a dump	*/
+#define NLMSG_OVERRUN		0x4	/* Data lost		*/
+
+#define NLMSG_MIN_TYPE		0x10	/* < 0x10: reserved control messages */
+
+struct nlmsgerr {
+	int		error;
+	struct nlmsghdr msg;
+	/*
+	 * followed by the message contents unless NETLINK_CAP_ACK was set
+	 * or the ACK indicates success (error == 0)
+	 * message length is aligned with NLMSG_ALIGN()
+	 */
+	/*
+	 * followed by TLVs defined in enum nlmsgerr_attrs
+	 * if NETLINK_EXT_ACK was set
+	 */
+};
+
+/**
+ * enum nlmsgerr_attrs - nlmsgerr attributes
+ * @NLMSGERR_ATTR_UNUSED: unused
+ * @NLMSGERR_ATTR_MSG: error message string (string)
+ * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original
+ *	 message, counting from the beginning of the header (u32)
+ * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
+ *	be used - in the success case - to identify a created
+ *	object or operation or similar (binary)
+ * @__NLMSGERR_ATTR_MAX: number of attributes
+ * @NLMSGERR_ATTR_MAX: highest attribute number
+ */
+enum nlmsgerr_attrs {
+	NLMSGERR_ATTR_UNUSED,
+	NLMSGERR_ATTR_MSG,
+	NLMSGERR_ATTR_OFFS,
+	NLMSGERR_ATTR_COOKIE,
+
+	__NLMSGERR_ATTR_MAX,
+	NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
+};
+
+#define NETLINK_ADD_MEMBERSHIP		1
+#define NETLINK_DROP_MEMBERSHIP		2
+#define NETLINK_PKTINFO			3
+#define NETLINK_BROADCAST_ERROR		4
+#define NETLINK_NO_ENOBUFS		5
+#ifndef __KERNEL__
+#define NETLINK_RX_RING			6
+#define NETLINK_TX_RING			7
+#endif
+#define NETLINK_LISTEN_ALL_NSID		8
+#define NETLINK_LIST_MEMBERSHIPS	9
+#define NETLINK_CAP_ACK			10
+#define NETLINK_EXT_ACK			11
+
+struct nl_pktinfo {
+	__u32	group;
+};
+
+struct nl_mmap_req {
+	unsigned int	nm_block_size;
+	unsigned int	nm_block_nr;
+	unsigned int	nm_frame_size;
+	unsigned int	nm_frame_nr;
+};
+
+struct nl_mmap_hdr {
+	unsigned int	nm_status;
+	unsigned int	nm_len;
+	__u32		nm_group;
+	/* credentials */
+	__u32		nm_pid;
+	__u32		nm_uid;
+	__u32		nm_gid;
+};
+
+#ifndef __KERNEL__
+enum nl_mmap_status {
+	NL_MMAP_STATUS_UNUSED,
+	NL_MMAP_STATUS_RESERVED,
+	NL_MMAP_STATUS_VALID,
+	NL_MMAP_STATUS_COPY,
+	NL_MMAP_STATUS_SKIP,
+};
+
+#define NL_MMAP_MSG_ALIGNMENT		NLMSG_ALIGNTO
+#define NL_MMAP_MSG_ALIGN(sz)		__ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
+#define NL_MMAP_HDRLEN			NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+#endif
+
+#define NET_MAJOR 36		/* Major 36 is reserved for networking 						*/
+
+enum {
+	NETLINK_UNCONNECTED = 0,
+	NETLINK_CONNECTED,
+};
+
+/*
+ *  <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * |        Header       | Pad |     Payload       | Pad |
+ * |   (struct nlattr)   | ing |                   | ing |
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ *  <-------------- nlattr->nla_len -------------->
+ */
+
+struct nlattr {
+	__u16           nla_len;
+	__u16           nla_type;
+};
+
+/*
+ * nla_type (16 bits)
+ * +---+---+-------------------------------+
+ * | N | O | Attribute Type                |
+ * +---+---+-------------------------------+
+ * N := Carries nested attributes
+ * O := Payload stored in network byte order
+ *
+ * Note: The N and O flag are mutually exclusive.
+ */
+#define NLA_F_NESTED		(1 << 15)
+#define NLA_F_NET_BYTEORDER	(1 << 14)
+#define NLA_TYPE_MASK		~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
+
+#define NLA_ALIGNTO		4
+#define NLA_ALIGN(len)		(((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
+#define NLA_HDRLEN		((int) NLA_ALIGN(sizeof(struct nlattr)))
+
+/* Generic 32 bitflags attribute content sent to the kernel.
+ *
+ * The value is a bitmap that defines the values being set
+ * The selector is a bitmask that defines which value is legit
+ *
+ * Examples:
+ *  value = 0x0, and selector = 0x1
+ *  implies we are selecting bit 1 and we want to set its value to 0.
+ *
+ *  value = 0x2, and selector = 0x2
+ *  implies we are selecting bit 2 and we want to set its value to 1.
+ *
+ */
+struct nla_bitfield32 {
+	__u32 value;
+	__u32 selector;
+};
+
+#endif /* _UAPI__LINUX_NETLINK_H */

tools/lib/bpf/Build

-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o

tools/lib/bpf/Makefile

@@ -160,6 +160,12 @@ $(BPF_IN): force elfdep bpfdep
 	@(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
 	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true
+	@(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \
+	(diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true
+	@(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \
+	(diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)

tools/lib/bpf/bpf.c

+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * common eBPF ELF operations.
  *
@@ -25,6 +27,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include "nlattr.h"
+#include <linux/rtnetlink.h>
+#include <linux/if_link.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,7 +58,9 @@
 # endif
 #endif
 
+#ifndef min
 #define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
 
 static inline __u64 ptr_to_u64(const void *ptr)
 {
@@ -413,3 +427,124 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
 
 	return err;
 }
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	struct sockaddr_nl sa;
+	int sock, seq = 0, len, ret = -1;
+	char buf[4096];
+	struct nlattr *nla, *nla_xdp;
+	struct {
+		struct nlmsghdr  nh;
+		struct ifinfomsg ifinfo;
+		char             attrbuf[64];
+	} req;
+	struct nlmsghdr *nh;
+	struct nlmsgerr *err;
+	socklen_t addrlen;
+	int one = 1;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one)) < 0) {
+		fprintf(stderr, "Netlink error reporting not supported\n");
+	}
+
+	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	addrlen = sizeof(sa);
+	if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	if (addrlen != sizeof(sa)) {
+		ret = -LIBBPF_ERRNO__INTERNAL;
+		goto cleanup;
+	}
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_SETLINK;
+	req.nh.nlmsg_pid = 0;
+	req.nh.nlmsg_seq = ++seq;
+	req.ifinfo.ifi_family = AF_UNSPEC;
+	req.ifinfo.ifi_index = ifindex;
+
+	/* started nested attribute for XDP */
+	nla = (struct nlattr *)(((char *)&req)
+				+ NLMSG_ALIGN(req.nh.nlmsg_len));
+	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
+	nla->nla_len = NLA_HDRLEN;
+
+	/* add XDP fd */
+	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+	nla_xdp->nla_type = IFLA_XDP_FD;
+	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+	nla->nla_len += nla_xdp->nla_len;
+
+	/* if user passed in any flags, add those too */
+	if (flags) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = IFLA_XDP_FLAGS;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+		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) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	len = recv(sock, buf, sizeof(buf), 0);
+	if (len < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+	     nh = NLMSG_NEXT(nh, len)) {
+		if (nh->nlmsg_pid != sa.nl_pid) {
+			ret = -LIBBPF_ERRNO__WRNGPID;
+			goto cleanup;
+		}
+		if (nh->nlmsg_seq != seq) {
+			ret = -LIBBPF_ERRNO__INVSEQ;
+			goto cleanup;
+		}
+		switch (nh->nlmsg_type) {
+		case NLMSG_ERROR:
+			err = (struct nlmsgerr *)NLMSG_DATA(nh);
+			if (!err->error)
+				continue;
+			ret = err->error;
+			nla_dump_errormsg(nh);
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}

tools/lib/bpf/bpf.h

+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *

tools/lib/bpf/libbpf.c

+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * Common eBPF ELF object loading operations.
  *
@@ -106,6 +108,8 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
 	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
 	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
+	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
+	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
 };
 
 int libbpf_strerror(int err, char *buf, size_t size)

tools/lib/bpf/libbpf.h

+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
@@ -42,6 +44,8 @@ enum libbpf_errno {
 	LIBBPF_ERRNO__PROG2BIG,	/* Program too big */
 	LIBBPF_ERRNO__KVER,	/* Incorrect kernel version */
 	LIBBPF_ERRNO__PROGTYPE,	/* Kernel doesn't support this program type */
+	LIBBPF_ERRNO__WRNGPID,	/* Wrong pid in netlink message */
+	LIBBPF_ERRNO__INVSEQ,	/* Invalid netlink sequence */
 	__LIBBPF_ERRNO__END,
 };
 
@@ -246,4 +250,6 @@ long libbpf_get_error(const void *ptr);
 
 int bpf_prog_load(const char *file, enum bpf_prog_type type,
 		  struct bpf_object **pobj, int *prog_fd);
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 #endif

tools/lib/bpf/nlattr.c

+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * NETLINK      Netlink attributes
+ *
+ *	This library is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU Lesser General Public
+ *	License as published by the Free Software Foundation version 2.1
+ *	of the License.
+ *
+ * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <errno.h>
+#include "nlattr.h"
+#include <linux/rtnetlink.h>
+#include <string.h>
+#include <stdio.h>
+
+static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
+	[NLA_U8]	= sizeof(uint8_t),
+	[NLA_U16]	= sizeof(uint16_t),
+	[NLA_U32]	= sizeof(uint32_t),
+	[NLA_U64]	= sizeof(uint64_t),
+	[NLA_STRING]	= 1,
+	[NLA_FLAG]	= 0,
+};
+
+static int nla_len(const struct nlattr *nla)
+{
+	return nla->nla_len - NLA_HDRLEN;
+}
+
+static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
+{
+	int totlen = NLA_ALIGN(nla->nla_len);
+
+	*remaining -= totlen;
+	return (struct nlattr *) ((char *) nla + totlen);
+}
+
+static int nla_ok(const struct nlattr *nla, int remaining)
+{
+	return remaining >= sizeof(*nla) &&
+	       nla->nla_len >= sizeof(*nla) &&
+	       nla->nla_len <= remaining;
+}
+
+static void *nla_data(const struct nlattr *nla)
+{
+	return (char *) nla + NLA_HDRLEN;
+}
+
+static int nla_type(const struct nlattr *nla)
+{
+	return nla->nla_type & NLA_TYPE_MASK;
+}
+
+static int validate_nla(struct nlattr *nla, int maxtype,
+			struct nla_policy *policy)
+{
+	struct nla_policy *pt;
+	unsigned int minlen = 0;
+	int type = nla_type(nla);
+
+	if (type < 0 || type > maxtype)
+		return 0;
+
+	pt = &policy[type];
+
+	if (pt->type > NLA_TYPE_MAX)
+		return 0;
+
+	if (pt->minlen)
+		minlen = pt->minlen;
+	else if (pt->type != NLA_UNSPEC)
+		minlen = nla_attr_minlen[pt->type];
+
+	if (nla_len(nla) < minlen)
+		return -1;
+
+	if (pt->maxlen && nla_len(nla) > pt->maxlen)
+		return -1;
+
+	if (pt->type == NLA_STRING) {
+		char *data = nla_data(nla);
+		if (data[nla_len(nla) - 1] != '\0')
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline int nlmsg_len(const struct nlmsghdr *nlh)
+{
+	return nlh->nlmsg_len - NLMSG_HDRLEN;
+}
+
+/**
+ * Create attribute index based on a stream of attributes.
+ * @arg tb		Index array to be filled (maxtype+1 elements).
+ * @arg maxtype		Maximum attribute type expected and accepted.
+ * @arg head		Head of attribute stream.
+ * @arg len		Length of attribute stream.
+ * @arg policy		Attribute validation policy.
+ *
+ * Iterates over the stream of attributes and stores a pointer to each
+ * attribute in the index array using the attribute type as index to
+ * the array. Attribute with a type greater than the maximum type
+ * specified will be silently ignored in order to maintain backwards
+ * compatibility. If \a policy is not NULL, the attribute will be
+ * validated using the specified policy.
+ *
+ * @see nla_validate
+ * @return 0 on success or a negative error code.
+ */
+static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+		     struct nla_policy *policy)
+{
+	struct nlattr *nla;
+	int rem, err;
+
+	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+
+	nla_for_each_attr(nla, head, len, rem) {
+		int type = nla_type(nla);
+
+		if (type > maxtype)
+			continue;
+
+		if (policy) {
+			err = validate_nla(nla, maxtype, policy);
+			if (err < 0)
+				goto errout;
+		}
+
+		if (tb[type])
+			fprintf(stderr, "Attribute of type %#x found multiple times in message, "
+				  "previous attribute is being ignored.\n", type);
+
+		tb[type] = nla;
+	}
+
+	err = 0;
+errout:
+	return err;
+}
+
+/* dump netlink extended ack error message */
+int nla_dump_errormsg(struct nlmsghdr *nlh)
+{
+	struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
+		[NLMSGERR_ATTR_MSG]	= { .type = NLA_STRING },
+		[NLMSGERR_ATTR_OFFS]	= { .type = NLA_U32 },
+	};
+	struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr;
+	struct nlmsgerr *err;
+	char *errmsg = NULL;
+	int hlen, alen;
+
+	/* no TLVs, nothing to do here */
+	if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+		return 0;
+
+	err = (struct nlmsgerr *)NLMSG_DATA(nlh);
+	hlen = sizeof(*err);
+
+	/* if NLM_F_CAPPED is set then the inner err msg was capped */
+	if (!(nlh->nlmsg_flags & NLM_F_CAPPED))
+		hlen += nlmsg_len(&err->msg);
+
+	attr = (struct nlattr *) ((void *) err + hlen);
+	alen = nlh->nlmsg_len - hlen;
+
+	if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) {
+		fprintf(stderr,
+			"Failed to parse extended error attributes\n");
+		return 0;
+	}
+
+	if (tb[NLMSGERR_ATTR_MSG])
+		errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]);
+
+	fprintf(stderr, "Kernel error message: %s\n", errmsg);
+
+	return 0;
+}

tools/lib/bpf/nlattr.h

+/* SPDX-License-Identifier: LGPL-2.1 */
+
+/*
+ * NETLINK      Netlink attributes
+ *
+ *	This library is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU Lesser General Public
+ *	License as published by the Free Software Foundation version 2.1
+ *	of the License.
+ *
+ * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
+ */
+
+#ifndef __NLATTR_H
+#define __NLATTR_H
+
+#include <stdint.h>
+#include <linux/netlink.h>
+/* avoid multiple definition of netlink features */
+#define __LINUX_NETLINK_H
+
+/**
+ * Standard attribute types to specify validation policy
+ */
+enum {
+	NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
+	NLA_U8,		/**< 8 bit integer */
+	NLA_U16,	/**< 16 bit integer */
+	NLA_U32,	/**< 32 bit integer */
+	NLA_U64,	/**< 64 bit integer */
+	NLA_STRING,	/**< NUL terminated character string */
+	NLA_FLAG,	/**< Flag */
+	NLA_MSECS,	/**< Micro seconds (64bit) */
+	NLA_NESTED,	/**< Nested attributes */
+	__NLA_TYPE_MAX,
+};
+
+#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+
+/**
+ * @ingroup attr
+ * Attribute validation policy.
+ *
+ * See section @core_doc{core_attr_parse,Attribute Parsing} for more details.
+ */
+struct nla_policy {
+	/** Type of attribute or NLA_UNSPEC */
+	uint16_t	type;
+
+	/** Minimal length of payload required */
+	uint16_t	minlen;
+
+	/** Maximal length of payload allowed */
+	uint16_t	maxlen;
+};
+
+/**
+ * @ingroup attr
+ * Iterate over a stream of attributes
+ * @arg pos	loop counter, set to current attribute
+ * @arg head	head of attribute stream
+ * @arg len	length of attribute stream
+ * @arg rem	initialized to len, holds bytes currently remaining in stream
+ */
+#define nla_for_each_attr(pos, head, len, rem) \
+	for (pos = head, rem = len; \
+	     nla_ok(pos, rem); \
+	     pos = nla_next(pos, &(rem)))
+
+int nla_dump_errormsg(struct nlmsghdr *nlh);
+
+#endif /* __NLATTR_H */