[PATCH bpf-next 0/3] add XDP loading support to libbpf

[PATCH bpf-next 0/3] add XDP loading support to libbpf

[Eric Leblond]

Hello,

This patchset adds a function to load XDP eBPF file in the libbpf
library. It gets the netlink extended ack from the driver in case
of failure and print the error to stderr.

Best regards,
--
Eric Leblond

[PATCH bpf-next 1/3] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/lib/bpf/bpf.c    | 126 ++++++++++++++++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 130 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..1e3cfe6b9fce 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef IFLA_XDP_MAX
+#define IFLA_XDP	43
+#define IFLA_XDP_FD	1
+#define IFLA_XDP_FLAGS	3
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,8 +56,6 @@
 # endif
 #endif
 
-#define min(x, y) ((x) < (y) ? (x) : (y))
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -413,3 +421,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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 = 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 | 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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c4b7cabcf2..5fe8aaa2123e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH bpf-next 2/3] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |   9 +++
 tools/lib/bpf/nlattr.c | 188 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h | 164 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 362 insertions(+), 1 deletion(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1e3cfe6b9fce..cfd30a0cbce4 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,6 +26,7 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
+#include "nlattr.h"
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -436,6 +437,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -445,6 +447,12 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		return -errno;
 	}
 
+	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one)) < 0) {
+		/* debug/verbose message that it is not supported */
+		fprintf(stderr, "Netlink error reporting not supported\n"); 
+	}
+
 	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
 		ret = -errno;
 		goto cleanup;
@@ -521,6 +529,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			if (!err->error)
 				continue;
 			ret = err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..962de14f74e3
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,188 @@
+
+/*
+ * NETLINK      Netlink attributes
+ *
+ *		Authors:	Thomas Graf <tgraf@suug.ch>
+ *				Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <errno.h>
+#include "nlattr.h"
+#include <linux/rtnetlink.h>
+#include <string.h>
+#include <stdio.h>
+
+static const __u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
+	[NLA_U8]	= sizeof(__u8),
+	[NLA_U16]	= sizeof(__u16),
+	[NLA_U32]	= sizeof(__u32),
+	[NLA_U64]	= sizeof(__u64),
+	[NLA_MSECS]	= sizeof(__u64),
+	[NLA_NESTED]	= NLA_HDRLEN,
+	[NLA_S8]	= sizeof(__s8),
+	[NLA_S16]	= sizeof(__s16),
+	[NLA_S32]	= sizeof(__s32),
+	[NLA_S64]	= sizeof(__s64),
+};
+
+static int validate_nla(const struct nlattr *nla, int maxtype,
+			const struct nla_policy *policy)
+{
+	const struct nla_policy *pt;
+	int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla);
+
+	if (type <= 0 || type > maxtype)
+		return 0;
+
+	pt = &policy[type];
+
+	if (pt->type > NLA_TYPE_MAX)
+		return -EINVAL;
+
+	switch (pt->type) {
+	case NLA_FLAG:
+		if (attrlen > 0)
+			return -ERANGE;
+		break;
+
+	case NLA_NUL_STRING:
+		if (pt->len)
+			minlen = min(attrlen, pt->len + 1);
+		else
+			minlen = attrlen;
+
+		if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL)
+			return -EINVAL;
+		/* fall through */
+
+	case NLA_STRING:
+		if (attrlen < 1)
+			return -ERANGE;
+
+		if (pt->len) {
+			char *buf = nla_data(nla);
+
+			if (buf[attrlen - 1] == '\0')
+				attrlen--;
+
+			if (attrlen > pt->len)
+				return -ERANGE;
+		}
+		break;
+
+	case NLA_BINARY:
+		if (pt->len && attrlen > pt->len)
+			return -ERANGE;
+		break;
+
+	case NLA_NESTED_COMPAT:
+		if (attrlen < pt->len)
+			return -ERANGE;
+		if (attrlen < NLA_ALIGN(pt->len))
+			break;
+		if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN)
+			return -ERANGE;
+		nla = nla_data(nla) + NLA_ALIGN(pt->len);
+		if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN + nla_len(nla))
+			return -ERANGE;
+		break;
+	case NLA_NESTED:
+		/* a nested attributes is allowed to be empty; if its not,
+		 * it must have a size of at least NLA_HDRLEN.
+		 */
+		if (attrlen == 0)
+			break;
+	default:
+		if (pt->len)
+			minlen = pt->len;
+		else if (pt->type != NLA_UNSPEC)
+			minlen = nla_attr_minlen[pt->type];
+
+		if (attrlen < minlen)
+			return -ERANGE;
+	}
+
+	return 0;
+}
+
+/**
+ * nla_parse - Parse a stream of attributes into a tb buffer
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @head: head of attribute stream
+ * @len: length of attribute stream
+ * @policy: validation policy
+ *
+ * Parses a stream of attributes and stores a pointer to each attribute in
+ * the tb array accessible via the attribute type. Attributes with a type
+ * exceeding maxtype will be silently ignored for backwards compatibility
+ * reasons. policy may be set to NULL if no validation is required.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
+	      int len, const struct nla_policy *policy)
+{
+	const struct nlattr *nla;
+	int rem, err;
+
+	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+
+	nla_for_each_attr(nla, head, len, rem) {
+		__u16 type = nla_type(nla);
+
+		if (type > 0 && type <= maxtype) {
+			if (policy) {
+				err = validate_nla(nla, maxtype, policy);
+				if (err < 0)
+					goto errout;
+			}
+
+			tb[type] = (struct nlattr *)nla;
+		}
+	}
+
+	err = 0;
+errout:
+	return err;
+}
+
+/* dump netlink extended ack error message */
+int nla_dump_errormsg(struct nlmsghdr *nlh)
+{
+	const 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..b95f3e64c14d
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,164 @@
+#ifndef __NLATTR_H
+#define __NLATTR_H
+
+#include <linux/netlink.h>
+
+/**
+ * Standard attribute types to specify validation policy
+ */
+enum {
+	NLA_UNSPEC,
+	NLA_U8,
+	NLA_U16,
+	NLA_U32,
+	NLA_U64,
+	NLA_STRING,
+	NLA_FLAG,
+	NLA_MSECS,
+	NLA_NESTED,
+	NLA_NESTED_COMPAT,
+	NLA_NUL_STRING,
+	NLA_BINARY,
+	NLA_S8,
+	NLA_S16,
+	NLA_S32,
+	NLA_S64,
+	__NLA_TYPE_MAX,
+};
+
+#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+
+/**
+ * nla_type - attribute type
+ * @nla: netlink attribute
+ */
+static inline int nla_type(const struct nlattr *nla)
+{
+	return nla->nla_type & NLA_TYPE_MASK;
+}
+
+/**
+ * nla_len - length of payload
+ * @nla: netlink attribute
+ */
+static inline int nla_len(const struct nlattr *nla)
+{
+	return nla->nla_len - NLA_HDRLEN;
+}
+
+/**
+ * struct nla_policy - attribute validation policy
+ * @type: Type of attribute or NLA_UNSPEC
+ * @len: Type specific length of payload
+ *
+ * Policies are defined as arrays of this struct, the array must be
+ * accessible by attribute type up to the highest identifier to be expected.
+ *
+ * Meaning of `len' field:
+ *    NLA_STRING           Maximum length of string
+ *    NLA_NUL_STRING       Maximum length of string (excluding NUL)
+ *    NLA_FLAG             Unused
+ *    NLA_BINARY           Maximum length of attribute payload
+ *    NLA_NESTED           Don't use `len' field -- length verification is
+ *                         done by checking len of nested header (or empty)
+ *    NLA_NESTED_COMPAT    Minimum length of structure payload
+ *    NLA_U8, NLA_U16,
+ *    NLA_U32, NLA_U64,
+ *    NLA_S8, NLA_S16,
+ *    NLA_S32, NLA_S64,
+ *    NLA_MSECS            Leaving the length field zero will verify the
+ *                         given type fits, using it verifies minimum length
+ *                         just like "All other"
+ *    All other            Minimum length of attribute payload
+ *
+ * Example:
+ * static const struct nla_policy my_policy[ATTR_MAX+1] = {
+ *      [ATTR_FOO] = { .type = NLA_U16 },
+ *      [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ },
+ *      [ATTR_BAZ] = { .len = sizeof(struct mystruct) },
+ * };
+ */
+struct nla_policy {
+	__u16	type;
+	__u16	len;
+};
+
+/**
+ * nla_ok - check if the netlink attribute fits into the remaining bytes
+ * @nla: netlink attribute
+ * @remaining: number of bytes remaining in attribute stream
+ */
+static inline int nla_ok(const struct nlattr *nla, int remaining)
+{
+	return remaining >= (int) sizeof(*nla) &&
+	       nla->nla_len >= sizeof(*nla) &&
+	       nla->nla_len <= remaining;
+}
+
+/**
+ * nla_next - next netlink attribute in attribute stream
+ * @nla: netlink attribute
+ * @remaining: number of bytes remaining in attribute stream
+ *
+ * Returns the next netlink attribute in the attribute stream and
+ * decrements remaining by the size of the current attribute.
+ */
+static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
+{
+	unsigned int totlen = NLA_ALIGN(nla->nla_len);
+
+	*remaining -= totlen;
+	return (struct nlattr *) ((char *) nla + totlen);
+}
+
+/**
+ * nla_for_each_attr - iterate over a stream of attributes
+ * @pos: loop counter, set to current attribute
+ * @head: head of attribute stream
+ * @len: length of attribute stream
+ * @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)))
+
+/**
+ * nla_data - head of payload
+ * @nla: netlink attribute
+ */
+static inline void *nla_data(const struct nlattr *nla)
+{
+	return (char *) nla + NLA_HDRLEN;
+}
+
+/**
+ * nla_get_u32 - return payload of u32 attribute
+ * @nla: u32 netlink attribute
+ */
+static inline __u32 nla_get_u32(const struct nlattr *nla)
+{
+	return *(__u32 *) nla_data(nla);
+}
+
+/**
+ * nla_get_u16 - return payload of u16 attribute
+ * @nla: u16 netlink attribute
+ */
+static inline __u16 nla_get_u16(const struct nlattr *nla)
+{
+	return *(__u16 *) nla_data(nla);
+}
+
+/**
+ * nlmsg_len - length of message payload
+ * @nlh: netlink message header
+ */
+static inline int nlmsg_len(const struct nlmsghdr *nlh)
+{
+	return nlh->nlmsg_len - NLMSG_HDRLEN;
+}
+
+int nla_dump_errormsg(struct nlmsghdr *nlh);
+
+#endif /* __NLATTR_H */
-- 
2.15.1

[PATCH bpf-next 3/3] libbpf: break loop earlier

[Eric Leblond]

Get out of the loop when we have a match.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/lib/bpf/libbpf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5fe8aaa2123e..d263748aa341 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -412,6 +412,7 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 					   prog->section_name);
 				return -LIBBPF_ERRNO__LIBELF;
 			}
+			break;
 		}
 
 		if (!name) {
-- 
2.15.1

Re: [PATCH bpf-next 2/3] libbpf: add error reporting in XDP

[Alexei Starovoitov]

On Mon, Dec 25, 2017 at 11:13:24PM +0100, Eric Leblond wrote:
> Parse netlink ext attribute to get the error message returned by
> the card.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>
...
> diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
> new file mode 100644
> index 000000000000..962de14f74e3
> --- /dev/null
> +++ b/tools/lib/bpf/nlattr.c
> @@ -0,0 +1,188 @@
> +
> +/*
> + * NETLINK      Netlink attributes
> + *
> + *		Authors:	Thomas Graf <tgraf@suug.ch>
> + *				Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
> + */
...
> diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
> new file mode 100644
> index 000000000000..b95f3e64c14d
> --- /dev/null
> +++ b/tools/lib/bpf/nlattr.h
> @@ -0,0 +1,164 @@
> +#ifndef __NLATTR_H
> +#define __NLATTR_H

Every file in kernel repo has to have SPDX license identifier.
Also note that tools/lib/bpf is LGPL whereas _if_ you're copying
these functions from kernel lib/nlattr.c then it's GPL which we cannot mix.
Probably easier to copy from libnl instead which is LGPL.

[PATCH bpf-next v2 0/4] libbpf: add function to setup XDP

[Eric Leblond]

Hello,

This patchset address the remark about license. It now uses libnl
code as a base for the netlink parsing.

The library seems to report error correctly when used over a
netdevsim interface. I did not manage to test it on a real
hardware.

Best regards,
--
Eric Leblond

[PATCH 1/4] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/lib/bpf/bpf.c    | 126 ++++++++++++++++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 130 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..1e3cfe6b9fce 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef IFLA_XDP_MAX
+#define IFLA_XDP	43
+#define IFLA_XDP_FD	1
+#define IFLA_XDP_FLAGS	3
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,8 +56,6 @@
 # endif
 #endif
 
-#define min(x, y) ((x) < (y) ? (x) : (y))
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -413,3 +421,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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 = 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 | 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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c4b7cabcf2..5fe8aaa2123e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH 2/4] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card. Code is partially take from libnl.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |   9 +++
 tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h |  69 ++++++++++++++++++
 4 files changed, 266 insertions(+), 1 deletion(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1e3cfe6b9fce..cdfabbe118cc 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,6 +26,7 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
+#include "nlattr.h"
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -436,6 +437,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -445,6 +447,12 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		return -errno;
 	}
 
+	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one)) < 0) {
+		/* debug/verbose message that it is not supported */
+		fprintf(stderr, "Netlink error reporting not supported\n");
+	}
+
 	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
 		ret = -errno;
 		goto cleanup;
@@ -521,6 +529,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			if (!err->error)
 				continue;
 			ret = err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..5cc74fa98049
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,187 @@
+/* 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..fa2d015334ef
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,69 @@
+/* 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 <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 */
-- 
2.15.1

[PATCH 3/4] libbpf: break loop earlier

[Eric Leblond]

Get out of the loop when we have a match.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/lib/bpf/libbpf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5fe8aaa2123e..d263748aa341 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -412,6 +412,7 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 					   prog->section_name);
 				return -LIBBPF_ERRNO__LIBELF;
 			}
+			break;
 		}
 
 		if (!name) {
-- 
2.15.1

[PATCH 4/4] libbpf: add missing SPDX-License-Identifier

[Eric Leblond]

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/lib/bpf/bpf.c    | 2 ++
 tools/lib/bpf/bpf.h    | 2 ++
 tools/lib/bpf/libbpf.c | 2 ++
 tools/lib/bpf/libbpf.h | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index cdfabbe118cc..9e53dbbca2bd 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9f44c196931e..8d18fb73d7fb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d263748aa341..50d4b5e73d0e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e42f96900318..f85906533cdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
-- 
2.15.1

Re: [PATCH 2/4] libbpf: add error reporting in XDP

[Alexei Starovoitov]

On Wed, Dec 27, 2017 at 07:02:27PM +0100, Eric Leblond wrote:
> Parse netlink ext attribute to get the error message returned by
> the card. Code is partially take from libnl.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>

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

Re: [PATCH 1/4] libbpf: add function to setup XDP

[Alexei Starovoitov]

On Wed, Dec 27, 2017 at 07:02:26PM +0100, Eric Leblond wrote:
> Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
> slightly modified to be library compliant.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>

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

Re: [PATCH 3/4] libbpf: break loop earlier

[Alexei Starovoitov]

On Wed, Dec 27, 2017 at 07:02:28PM +0100, Eric Leblond wrote:
> Get out of the loop when we have a match.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>
> ---
>  tools/lib/bpf/libbpf.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 5fe8aaa2123e..d263748aa341 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -412,6 +412,7 @@ bpf_object__init_prog_names(struct bpf_object *obj)
>  					   prog->section_name);
>  				return -LIBBPF_ERRNO__LIBELF;
>  			}
> +			break;

why this is needed?
The top of the loop is:
 for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;

so as soon as name is found the loop will exit.
I agree that the loop structure is non-standard is confusing,
but adding break here will make it even more so.
If 'break' is added then '&& !name' should be removed.

Re: [PATCH 4/4] libbpf: add missing SPDX-License-Identifier

[Alexei Starovoitov]

On Wed, Dec 27, 2017 at 07:02:29PM +0100, Eric Leblond wrote:
> Signed-off-by: Eric Leblond <eric@regit.org>

thank you.
Acked-by: Alexei Starovoitov <ast@kernel.org>

Re: [PATCH 3/4] libbpf: break loop earlier

[Eric Leblond]

Hello,

On Wed, 2017-12-27 at 11:00 -0800, Alexei Starovoitov wrote:
> On Wed, Dec 27, 2017 at 07:02:28PM +0100, Eric Leblond wrote:
> > Get out of the loop when we have a match.
> > 
> > Signed-off-by: Eric Leblond <eric@regit.org>
> > ---
> >  tools/lib/bpf/libbpf.c | 1 +
> >  1 file changed, 1 insertion(+)
> > 
> > diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> > index 5fe8aaa2123e..d263748aa341 100644
> > --- a/tools/lib/bpf/libbpf.c
> > +++ b/tools/lib/bpf/libbpf.c
> > @@ -412,6 +412,7 @@ bpf_object__init_prog_names(struct bpf_object
> > *obj)
> >  					   prog->section_name);
> >  				return -LIBBPF_ERRNO__LIBELF;
> >  			}
> > +			break;
> 
> why this is needed?

It was just cosmetic, no related bug.

> The top of the loop is:
>  for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
> 
> so as soon as name is found the loop will exit.

OK, I've missed that. Please disregard this patch.

BR,
-- 
Eric Leblond <eric@regit.org>

Re: [PATCH 3/4] libbpf: break loop earlier

[Daniel Borkmann]

On 12/27/2017 09:30 PM, Eric Leblond wrote:
> On Wed, 2017-12-27 at 11:00 -0800, Alexei Starovoitov wrote:
>> On Wed, Dec 27, 2017 at 07:02:28PM +0100, Eric Leblond wrote:
>>> Get out of the loop when we have a match.
>>>
>>> Signed-off-by: Eric Leblond <eric@regit.org>
>>> ---
>>>  tools/lib/bpf/libbpf.c | 1 +
>>>  1 file changed, 1 insertion(+)
>>>
>>> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
>>> index 5fe8aaa2123e..d263748aa341 100644
>>> --- a/tools/lib/bpf/libbpf.c
>>> +++ b/tools/lib/bpf/libbpf.c
>>> @@ -412,6 +412,7 @@ bpf_object__init_prog_names(struct bpf_object
>>> *obj)
>>>  					   prog->section_name);
>>>  				return -LIBBPF_ERRNO__LIBELF;
>>>  			}
>>> +			break;
>>
>> why this is needed?
> 
> It was just cosmetic, no related bug.
> 
>> The top of the loop is:
>>  for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
>>
>> so as soon as name is found the loop will exit.
> 
> OK, I've missed that. Please disregard this patch.

Ok, please respin the series one last time w/o this patch then.

Please also keep the already given ACKs on the other patches.

Thanks, Eric!

Re: [PATCH 1/4] libbpf: add function to setup XDP

[Toshiaki Makita]

On 2017/12/28 3:02, Eric Leblond wrote:
> Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
> slightly modified to be library compliant.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>
> ---
...
> +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
...
> +	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;

forgot to prepend '-'?

> +		goto cleanup;
> +	}
> +
> +	if (addrlen != sizeof(sa)) {
> +		ret = errno;

errno is not set?

> +		goto cleanup;
> +	}

-- 
Toshiaki Makita

[PATCH bpf-next v3 0/3] libbpf: add XDP setup support

[Eric Leblond]

Hello,

This patchset adds support for loading eBPF code as XDP filter.

Best regards,
--
Eric Leblond

[PATCH bpf-next v3 1/3] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 126 ++++++++++++++++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 130 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..1e3cfe6b9fce 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef IFLA_XDP_MAX
+#define IFLA_XDP	43
+#define IFLA_XDP_FD	1
+#define IFLA_XDP_FLAGS	3
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,8 +56,6 @@
 # endif
 #endif
 
-#define min(x, y) ((x) < (y) ? (x) : (y))
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -413,3 +421,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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 = 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 | 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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c4b7cabcf2..5fe8aaa2123e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH bpf-next v3 2/3] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card. Code is partially take from libnl.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |   9 +++
 tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h |  69 ++++++++++++++++++
 4 files changed, 266 insertions(+), 1 deletion(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 1e3cfe6b9fce..cdfabbe118cc 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,6 +26,7 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
+#include "nlattr.h"
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -436,6 +437,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -445,6 +447,12 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		return -errno;
 	}
 
+	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one)) < 0) {
+		/* debug/verbose message that it is not supported */
+		fprintf(stderr, "Netlink error reporting not supported\n");
+	}
+
 	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
 		ret = -errno;
 		goto cleanup;
@@ -521,6 +529,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			if (!err->error)
 				continue;
 			ret = err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..5cc74fa98049
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,187 @@
+/* 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..fa2d015334ef
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,69 @@
+/* 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 <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 */
-- 
2.15.1

[PATCH bpf-next v3 3/3] libbpf: add missing SPDX-License-Identifier

[Eric Leblond]

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 2 ++
 tools/lib/bpf/bpf.h    | 2 ++
 tools/lib/bpf/libbpf.c | 2 ++
 tools/lib/bpf/libbpf.h | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index cdfabbe118cc..9e53dbbca2bd 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9f44c196931e..8d18fb73d7fb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5fe8aaa2123e..878e240a681b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e42f96900318..f85906533cdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
-- 
2.15.1

Re: [PATCH bpf-next v3 1/3] libbpf: add function to setup XDP

[Toshiaki Makita]

On 2017/12/28 17:04, Eric Leblond wrote:
> Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
> slightly modified to be library compliant.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>
> ---
...
> +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
...
> +	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;

Still errno is not inverted,

> +		goto cleanup;
> +	}
> +
> +	if (addrlen != sizeof(sa)) {
> +		ret = errno;

And not set here.

> +		goto cleanup;
> +	}

-- 
Toshiaki Makita

Re: [PATCH bpf-next v3 3/3] libbpf: add missing SPDX-License-Identifier

[Philippe Ombredanne]

Eric,

On Thu, Dec 28, 2017 at 9:04 AM, Eric Leblond <eric@regit.org> wrote:
> Signed-off-by: Eric Leblond <eric@regit.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>
> ---
>  tools/lib/bpf/bpf.c    | 2 ++
>  tools/lib/bpf/bpf.h    | 2 ++
>  tools/lib/bpf/libbpf.c | 2 ++
>  tools/lib/bpf/libbpf.h | 2 ++
>  4 files changed, 8 insertions(+)
>
> diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> index cdfabbe118cc..9e53dbbca2bd 100644
> --- a/tools/lib/bpf/bpf.c
> +++ b/tools/lib/bpf/bpf.c
> @@ -1,3 +1,5 @@
> +/* SPDX-License-Identifier: LGPL-2.1 */


In a .c file these should using C++-style comments as in //.
As requested by Linus, discussed on list and documented in Thomas doc patches.

> +
>  /*
>   * common eBPF ELF operations.
>   *
> diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
> index 9f44c196931e..8d18fb73d7fb 100644
> --- a/tools/lib/bpf/bpf.h
> +++ b/tools/lib/bpf/bpf.h
> @@ -1,3 +1,5 @@
> +/* SPDX-License-Identifier: LGPL-2.1 */

And this is correct for a .h

> +
>  /*
>   * common eBPF ELF operations.
>   *
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 5fe8aaa2123e..878e240a681b 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -1,3 +1,5 @@
> +/* SPDX-License-Identifier: LGPL-2.1 */

Use  // here.

> +
>  /*
>   * Common eBPF ELF object loading operations.
>   *
> diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
> index e42f96900318..f85906533cdd 100644
> --- a/tools/lib/bpf/libbpf.h
> +++ b/tools/lib/bpf/libbpf.h
> @@ -1,3 +1,5 @@
> +/* SPDX-License-Identifier: LGPL-2.1 */
> +
>  /*
>   * Common eBPF ELF object loading operations.
>   *
> --
> 2.15.1
>


-- 
Cordially
Philippe Ombredanne

[PATCH bpf-next v4 0/3] libbpf: add function to setup XDP

[Eric Leblond]

Hello,

This updated patchset address the remarks by Toshiaki Makita and
Philippe Ombredanne:
 - fixes on errno handling
 - correct usage of SPDX header

Best regards,
--
Eric Leblond 

[PATCH bpf-next v4 1/3] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 126 ++++++++++++++++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 130 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..f00fba2edeae 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef IFLA_XDP_MAX
+#define IFLA_XDP	43
+#define IFLA_XDP_FD	1
+#define IFLA_XDP_FLAGS	3
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,8 +56,6 @@
 # endif
 #endif
 
-#define min(x, y) ((x) < (y) ? (x) : (y))
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -413,3 +421,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c4b7cabcf2..5fe8aaa2123e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH bpf-next v4 2/3] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card. Code is partially take from libnl.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |  10 ++-
 tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h |  69 ++++++++++++++++++
 4 files changed, 266 insertions(+), 2 deletions(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index f00fba2edeae..ceb20c5cae3b 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,6 +26,7 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
+#include "nlattr.h"
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -436,6 +437,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -445,6 +447,11 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		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;
@@ -520,7 +527,8 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			err = (struct nlmsgerr *)NLMSG_DATA(nh);
 			if (!err->error)
 				continue;
-			ret = err->error;
+			ret = -err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..4719434278b2
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,187 @@
+// 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..fa2d015334ef
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,69 @@
+/* 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 <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 */
-- 
2.15.1

[PATCH bpf-next v4 3/3] libbpf: add missing SPDX-License-Identifier

[Eric Leblond]

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 2 ++
 tools/lib/bpf/bpf.h    | 2 ++
 tools/lib/bpf/libbpf.c | 2 ++
 tools/lib/bpf/libbpf.h | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ceb20c5cae3b..ab8b2eb31273 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9f44c196931e..8d18fb73d7fb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5fe8aaa2123e..924a8b8431ab 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * Common eBPF ELF object loading operations.
  *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e42f96900318..f85906533cdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
-- 
2.15.1

Re: [PATCH bpf-next v4 2/3] libbpf: add error reporting in XDP

[Philippe Ombredanne]

On Sat, Dec 30, 2017 at 9:41 PM, Eric Leblond <eric@regit.org> wrote:
> Parse netlink ext attribute to get the error message returned by
> the card. Code is partially take from libnl.
>
> Signed-off-by: Eric Leblond <eric@regit.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>

<snip>

> --- /dev/null
> +++ b/tools/lib/bpf/nlattr.c
> @@ -0,0 +1,187 @@
> +// 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>
> + */

Do you think you could get an ack or signoff from the author
(i.e.Thomas Graf)  to get a more streamlined thing such as this:

> +// SPDX-License-Identifier: LGPL-2.1
> +// NETLINK      Netlink attributes
> +// Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>


-- 
Cordially
Philippe Ombredanne

Re: [PATCH bpf-next v4 1/3] libbpf: add function to setup XDP

[Eric Leblond]

Hello,

On Sat, 2017-12-30 at 21:41 +0100, Eric Leblond wrote:
> Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
> slightly modified to be library compliant.

I've just discovered this patch is breaking the build of samples/bpf/
(nlattr not included at least and some int type problem). I'm going to
resubmit a patchset fixing this.

Sorry for the noise.

Best regards,
-- 
Eric Leblond <eric@regit.org>
Blog: https://home.regit.org/

[PATCH bpf-next v5 1/4] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 126 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 132 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..e6c61035b64c 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef IFLA_XDP_MAX
+#define IFLA_XDP	43
+#define IFLA_XDP_FD	1
+#define IFLA_XDP_FLAGS	3
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,7 +56,9 @@
 # endif
 #endif
 
+#ifndef min
 #define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
 
 static inline __u64 ptr_to_u64(const void *ptr)
 {
@@ -413,3 +425,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c4b7cabcf2..5fe8aaa2123e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH bpf-next v5 2/4] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card. Code is partially take from libnl.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile   |   2 +-
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |  10 ++-
 tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h |  70 ++++++++++++++++++
 5 files changed, 268 insertions(+), 3 deletions(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4fb944a7ecf8..c889ebcba9b3 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -44,7 +44,7 @@ hostprogs-y += xdp_monitor
 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)
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index e6c61035b64c..10d71b9fdbd0 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,6 +26,7 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
+#include "nlattr.h"
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -440,6 +441,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -449,6 +451,11 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		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;
@@ -524,7 +531,8 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			err = (struct nlmsgerr *)NLMSG_DATA(nh);
 			if (!err->error)
 				continue;
-			ret = err->error;
+			ret = -err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..4719434278b2
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,187 @@
+// 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..373444fbdd7d
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,70 @@
+/* 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>
+
+/**
+ * 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 */
-- 
2.15.1

[PATCH bpf-next v5 3/4] libbpf: add missing SPDX-License-Identifier

[Eric Leblond]

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 2 ++
 tools/lib/bpf/bpf.h    | 2 ++
 tools/lib/bpf/libbpf.c | 2 ++
 tools/lib/bpf/libbpf.h | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 10d71b9fdbd0..38d720466fe8 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9f44c196931e..8d18fb73d7fb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5fe8aaa2123e..924a8b8431ab 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * Common eBPF ELF object loading operations.
  *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e42f96900318..f85906533cdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
-- 
2.15.1

[PATCH bpf-next v5 4/4] samples/bpf: use bpf_set_link_xdp_fd

[Eric Leblond]

Use bpf_set_link_xdp_fd instead of set_link_xdp_fd to remove some
code duplication and benefit of netlink ext ack errors message.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 samples/bpf/bpf_load.c              | 102 ------------------------------------
 samples/bpf/bpf_load.h              |   2 +-
 samples/bpf/xdp1_user.c             |   4 +-
 samples/bpf/xdp_redirect_cpu_user.c |   6 +--
 samples/bpf/xdp_redirect_map_user.c |   8 +--
 samples/bpf/xdp_redirect_user.c     |   8 +--
 samples/bpf/xdp_router_ipv4_user.c  |  10 ++--
 samples/bpf/xdp_tx_iptunnel_user.c  |   6 +--
 8 files changed, 22 insertions(+), 124 deletions(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 242631aa4ea2..69806d74fa53 100644
--- a/samples/bpf/bpf_load.c
+++ b/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;
-}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 7d57a4248893..453c200b389b 100644
--- a/samples/bpf/bpf_load.h
+++ b/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
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index fdaefe91801d..b901ee2b3336 100644
--- a/samples/bpf/xdp1_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 35fec9fecb57..23744a8aaf21 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index 978a532f0748..7eae07d7293e 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 4475d837bf2c..d54e91eb6cbf 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index 916462112d55..6296741c1fbd 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/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;
 		}
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 715cd12eaca5..f0a787268a87 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/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;
 }
-- 
2.15.1

Re: [PATCH bpf-next v5 3/4] libbpf: add missing SPDX-License-Identifier

[Philippe Ombredanne]

On Thu, Jan 4, 2018 at 9:21 AM, Eric Leblond <eric@regit.org> wrote:
> Signed-off-by: Eric Leblond <eric@regit.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>
> ---
>  tools/lib/bpf/bpf.c    | 2 ++
>  tools/lib/bpf/bpf.h    | 2 ++
>  tools/lib/bpf/libbpf.c | 2 ++
>  tools/lib/bpf/libbpf.h | 2 ++
>  4 files changed, 8 insertions(+)
>
> diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> index 10d71b9fdbd0..38d720466fe8 100644
> --- a/tools/lib/bpf/bpf.c
> +++ b/tools/lib/bpf/bpf.c
> @@ -1,3 +1,5 @@
> +// SPDX-License-Identifier: LGPL-2.1
> +
>  /*
>   * common eBPF ELF operations.
>   *
> diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
> index 9f44c196931e..8d18fb73d7fb 100644
> --- a/tools/lib/bpf/bpf.h
> +++ b/tools/lib/bpf/bpf.h
> @@ -1,3 +1,5 @@
> +/* SPDX-License-Identifier: LGPL-2.1 */
> +
>  /*
>   * common eBPF ELF operations.
>   *
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 5fe8aaa2123e..924a8b8431ab 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -1,3 +1,5 @@
> +// SPDX-License-Identifier: LGPL-2.1
> +
>  /*
>   * Common eBPF ELF object loading operations.
>   *
> diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
> index e42f96900318..f85906533cdd 100644
> --- a/tools/lib/bpf/libbpf.h
> +++ b/tools/lib/bpf/libbpf.h
> @@ -1,3 +1,5 @@
> +/* SPDX-License-Identifier: LGPL-2.1 */
> +
>  /*
>   * Common eBPF ELF object loading operations.
>   *
> --
> 2.15.1
>

Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>

Thank you for using the SPDX tags!

-- 
Cordially
Philippe Ombredanne

Re: [PATCH bpf-next v5 2/4] libbpf: add error reporting in XDP

[Daniel Borkmann]

On 01/04/2018 09:21 AM, Eric Leblond wrote:
> Parse netlink ext attribute to get the error message returned by
> the card. Code is partially take from libnl.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>
> ---
>  samples/bpf/Makefile   |   2 +-
>  tools/lib/bpf/Build    |   2 +-
>  tools/lib/bpf/bpf.c    |  10 ++-
>  tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
>  tools/lib/bpf/nlattr.h |  70 ++++++++++++++++++
>  5 files changed, 268 insertions(+), 3 deletions(-)
>  create mode 100644 tools/lib/bpf/nlattr.c
>  create mode 100644 tools/lib/bpf/nlattr.h
> 
> diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
> index 4fb944a7ecf8..c889ebcba9b3 100644
> --- a/samples/bpf/Makefile
> +++ b/samples/bpf/Makefile
> @@ -44,7 +44,7 @@ hostprogs-y += xdp_monitor
>  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)
> diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
> index d8749756352d..64c679d67109 100644
> --- a/tools/lib/bpf/Build
> +++ b/tools/lib/bpf/Build
> @@ -1 +1 @@
> -libbpf-y := libbpf.o bpf.o
> +libbpf-y := libbpf.o bpf.o nlattr.o
> diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> index e6c61035b64c..10d71b9fdbd0 100644
> --- a/tools/lib/bpf/bpf.c
> +++ b/tools/lib/bpf/bpf.c
> @@ -26,6 +26,7 @@
>  #include <linux/bpf.h>
>  #include "bpf.h"
>  #include "libbpf.h"
> +#include "nlattr.h"
>  #include <linux/rtnetlink.h>
>  #include <sys/socket.h>
>  #include <errno.h>
> @@ -440,6 +441,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
>  	struct nlmsghdr *nh;
>  	struct nlmsgerr *err;
>  	socklen_t addrlen;
> +	int one;

Hmm, it's not initialized here to 1 ...

>  	memset(&sa, 0, sizeof(sa));
>  	sa.nl_family = AF_NETLINK;
> @@ -449,6 +451,11 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
>  		return -errno;
>  	}
>  
> +	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
> +		       &one, sizeof(one)) < 0) {

... so we turn it on by chance here.

> +		fprintf(stderr, "Netlink error reporting not supported\n");
> +	}
> +
>  	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
>  		ret = -errno;
>  		goto cleanup;
> @@ -524,7 +531,8 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
>  			err = (struct nlmsgerr *)NLMSG_DATA(nh);
>  			if (!err->error)
>  				continue;
> -			ret = err->error;
> +			ret = -err->error;

This one looks strange. Your prior patch added the 'ret = err->error'
and this one negates it. Which variant is the correct version? From
digging into the kernel code, my take is that 'ret = err->error' was
the correct variant since it already holds the negative error code.
Could you double check?

> +			nla_dump_errormsg(nh);
>  			goto cleanup;
>  		case NLMSG_DONE:
>  			break;
Thanks,
Daniel

Re: [PATCH bpf-next v5 2/4] libbpf: add error reporting in XDP

[Eric Leblond]

Hi,

Sorry for the delay, missed the mail.

On Sat, 2018-01-06 at 22:16 +0100, Daniel Borkmann wrote:
> On 01/04/2018 09:21 AM, Eric Leblond wrote:
> > Parse netlink ext attribute to get the error message returned by
> > the card. Code is partially take from libnl.
> > 
> > Signed-off-by: Eric Leblond <eric@regit.org>
> > Acked-by: Alexei Starovoitov <ast@kernel.org>
> > ---
> >  samples/bpf/Makefile   |   2 +-
> >  tools/lib/bpf/Build    |   2 +-
> >  tools/lib/bpf/bpf.c    |  10 ++-
> >  tools/lib/bpf/nlattr.c | 187
> > +++++++++++++++++++++++++++++++++++++++++++++++++
> >  tools/lib/bpf/nlattr.h |  70 ++++++++++++++++++
> >  5 files changed, 268 insertions(+), 3 deletions(-)
> >  create mode 100644 tools/lib/bpf/nlattr.c
> >  create mode 100644 tools/lib/bpf/nlattr.h
> > 
> > diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
> > index 4fb944a7ecf8..c889ebcba9b3 100644
> > --- a/samples/bpf/Makefile
> > +++ b/samples/bpf/Makefile
> > @@ -44,7 +44,7 @@ hostprogs-y += xdp_monitor
> >  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)
> > diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
> > index d8749756352d..64c679d67109 100644
> > --- a/tools/lib/bpf/Build
> > +++ b/tools/lib/bpf/Build
> > @@ -1 +1 @@
> > -libbpf-y := libbpf.o bpf.o
> > +libbpf-y := libbpf.o bpf.o nlattr.o
> > diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> > index e6c61035b64c..10d71b9fdbd0 100644
> > --- a/tools/lib/bpf/bpf.c
> > +++ b/tools/lib/bpf/bpf.c
> > @@ -26,6 +26,7 @@
> >  #include <linux/bpf.h>
> >  #include "bpf.h"
> >  #include "libbpf.h"
> > +#include "nlattr.h"
> >  #include <linux/rtnetlink.h>
> >  #include <sys/socket.h>
> >  #include <errno.h>
> > @@ -440,6 +441,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd,
> > __u32 flags)
> >  	struct nlmsghdr *nh;
> >  	struct nlmsgerr *err;
> >  	socklen_t addrlen;
> > +	int one;
> 
> Hmm, it's not initialized here to 1 ...
> 
> >  	memset(&sa, 0, sizeof(sa));
> >  	sa.nl_family = AF_NETLINK;
> > @@ -449,6 +451,11 @@ int bpf_set_link_xdp_fd(int ifindex, int fd,
> > __u32 flags)
> >  		return -errno;
> >  	}
> >  
> > +	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
> > +		       &one, sizeof(one)) < 0) {
> 
> ... so we turn it on by chance here.

Indeed, fixing that.

> > +		fprintf(stderr, "Netlink error reporting not
> > supported\n");
> > +	}
> > +
> >  	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
> >  		ret = -errno;
> >  		goto cleanup;
> > @@ -524,7 +531,8 @@ int bpf_set_link_xdp_fd(int ifindex, int fd,
> > __u32 flags)
> >  			err = (struct nlmsgerr *)NLMSG_DATA(nh);
> >  			if (!err->error)
> >  				continue;
> > -			ret = err->error;
> > +			ret = -err->error;
> 
> This one looks strange. Your prior patch added the 'ret = err->error'
> and this one negates it. Which variant is the correct version? From
> digging into the kernel code, my take is that 'ret = err->error' was
> the correct variant since it already holds the negative error code.
> Could you double check?

Yes all netlink_ack usage I have seen are using the negative value of
the error. Fixing that too.

BR,
-- 
Eric Leblond <eric@regit.org>
Blog: https://home.regit.org/

[PATCH bpf-next 0/4] libbpf: add XDP binding support

[Eric Leblond]

Hello,

This patchset rebases the libbpf code on latest bpf-next code and addresses
remarks by Daniel.

Best regards,
--
Eric Leblond

[PATCH bpf-next v6 1/4] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 126 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 132 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..e6c61035b64c 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef IFLA_XDP_MAX
+#define IFLA_XDP	43
+#define IFLA_XDP_FD	1
+#define IFLA_XDP_FLAGS	3
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,7 +56,9 @@
 # endif
 #endif
 
+#ifndef min
 #define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
 
 static inline __u64 ptr_to_u64(const void *ptr)
 {
@@ -413,3 +425,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 30c776375118..c60122d3ea85 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH bpf-next v6 2/4] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card. Code is partially take from libnl.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile   |   2 +-
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |   8 +++
 tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h |  70 ++++++++++++++++++
 5 files changed, 267 insertions(+), 2 deletions(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 7f61a3d57fa7..5c4cd3745282 100644
--- a/samples/bpf/Makefile
+++ b/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)
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index e6c61035b64c..4517dce6849d 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,6 +26,7 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
+#include "nlattr.h"
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -440,6 +441,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one = 1;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -449,6 +451,11 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		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;
@@ -525,6 +532,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			if (!err->error)
 				continue;
 			ret = err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..4719434278b2
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,187 @@
+// 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..373444fbdd7d
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,70 @@
+/* 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>
+
+/**
+ * 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 */
-- 
2.15.1

[PATCH bpf-next v6 3/4] libbpf: add missing SPDX-License-Identifier

[Eric Leblond]

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 2 ++
 tools/lib/bpf/bpf.h    | 2 ++
 tools/lib/bpf/libbpf.c | 2 ++
 tools/lib/bpf/libbpf.h | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 4517dce6849d..991bd72c4153 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9f44c196931e..8d18fb73d7fb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c60122d3ea85..71ddc481f349 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * Common eBPF ELF object loading operations.
  *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e42f96900318..f85906533cdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
-- 
2.15.1

[PATCH bpf-next v6 4/4] samples/bpf: use bpf_set_link_xdp_fd

[Eric Leblond]

Use bpf_set_link_xdp_fd instead of set_link_xdp_fd to remove some
code duplication and benefit of netlink ext ack errors message.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 samples/bpf/bpf_load.c              | 102 ------------------------------------
 samples/bpf/bpf_load.h              |   2 +-
 samples/bpf/xdp1_user.c             |   4 +-
 samples/bpf/xdp_redirect_cpu_user.c |   6 +--
 samples/bpf/xdp_redirect_map_user.c |   8 +--
 samples/bpf/xdp_redirect_user.c     |   8 +--
 samples/bpf/xdp_router_ipv4_user.c  |  10 ++--
 samples/bpf/xdp_tx_iptunnel_user.c  |   6 +--
 8 files changed, 22 insertions(+), 124 deletions(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 242631aa4ea2..69806d74fa53 100644
--- a/samples/bpf/bpf_load.c
+++ b/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;
-}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 7d57a4248893..453c200b389b 100644
--- a/samples/bpf/bpf_load.h
+++ b/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
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index fdaefe91801d..b901ee2b3336 100644
--- a/samples/bpf/xdp1_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 35fec9fecb57..23744a8aaf21 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index 978a532f0748..7eae07d7293e 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 4475d837bf2c..d54e91eb6cbf 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index 916462112d55..6296741c1fbd 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/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;
 		}
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 715cd12eaca5..f0a787268a87 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/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;
 }
-- 
2.15.1

Re: [PATCH bpf-next 0/4] libbpf: add XDP binding support

[Daniel Borkmann]

On 01/19/2018 12:43 AM, Eric Leblond wrote:
> Hello,
> 
> This patchset rebases the libbpf code on latest bpf-next code and addresses
> remarks by Daniel.

Ok, I think it's a good start. We should later on clean up the
netlink handling code a bit, but that's all internal and can be
done in a second step. Applied to bpf-next, thanks Eric.

Re: [PATCH bpf-next 0/4] libbpf: add XDP binding support

[Alexei Starovoitov]

On Sat, Jan 20, 2018 at 03:00:37AM +0100, Daniel Borkmann wrote:
> On 01/19/2018 12:43 AM, Eric Leblond wrote:
> > Hello,
> > 
> > This patchset rebases the libbpf code on latest bpf-next code and addresses
> > remarks by Daniel.
> 
> Ok, I think it's a good start. We should later on clean up the
> netlink handling code a bit, but that's all internal and can be
> done in a second step. Applied to bpf-next, thanks Eric.

Sorry, Eric, Daniel.
I had to revert this patch set. It breaks build on systems
where headers are not the most recent.

Since libbpf is used by perf it has to be built cleanly on centos7 at least.

The errors I got:
bpf.c: In function ‘bpf_set_link_xdp_fd’:
bpf.c:456:23: error: ‘SOL_NETLINK’ undeclared (first use in this function)
  if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
                       ^~~~~~~~~~~
bpf.c:456:23: note: each undeclared identifier is reported only once for each function it appears in
bpf.c:456:36: error: ‘NETLINK_EXT_ACK’ undeclared (first use in this function)
  if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
                                    ^~~~~~~~~~~~~~~
nlattr.c: In function ‘nla_dump_errormsg’:
nlattr.c:152:34: error: ‘NLMSGERR_ATTR_MAX’ undeclared (first use in this function)
  struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {

Re: [PATCH bpf-next 0/4] libbpf: add XDP binding support

[Daniel Borkmann]

On 01/20/2018 03:27 AM, Alexei Starovoitov wrote:
> On Sat, Jan 20, 2018 at 03:00:37AM +0100, Daniel Borkmann wrote:
>> On 01/19/2018 12:43 AM, Eric Leblond wrote:
>>> Hello,
>>>
>>> This patchset rebases the libbpf code on latest bpf-next code and addresses
>>> remarks by Daniel.
>>
>> Ok, I think it's a good start. We should later on clean up the
>> netlink handling code a bit, but that's all internal and can be
>> done in a second step. Applied to bpf-next, thanks Eric.
> 
> Sorry, Eric, Daniel.
> I had to revert this patch set. It breaks build on systems
> where headers are not the most recent.
> 
> Since libbpf is used by perf it has to be built cleanly on centos7 at least.
> 
> The errors I got:
> bpf.c: In function ‘bpf_set_link_xdp_fd’:
> bpf.c:456:23: error: ‘SOL_NETLINK’ undeclared (first use in this function)
>   if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
>                        ^~~~~~~~~~~
> bpf.c:456:23: note: each undeclared identifier is reported only once for each function it appears in
> bpf.c:456:36: error: ‘NETLINK_EXT_ACK’ undeclared (first use in this function)
>   if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
>                                     ^~~~~~~~~~~~~~~
> nlattr.c: In function ‘nla_dump_errormsg’:
> nlattr.c:152:34: error: ‘NLMSGERR_ATTR_MAX’ undeclared (first use in this function)
>   struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {

Yeah, fully agree, thanks for catching this, Alexei!

[PATCH bpf-next v7 0/5] libbpf: add XDP setup support

[Eric Leblond]

Hello,

This patchset fixes the problem found by Alexei when building libbpf on a
system with old headers. It has been tested on an old Ubuntu and seems
to behave fine.

Best regards,
--
Eric

[PATCH bpf-next v7 1/5] tools: import netlink header in tools uapi

[Eric Leblond]

The header is necessary for libbpf compilation on system with older
version of the headers.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/include/uapi/linux/netlink.h | 251 +++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/Makefile             |   3 +
 2 files changed, 254 insertions(+)
 create mode 100644 tools/include/uapi/linux/netlink.h

diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
new file mode 100644
index 000000000000..776bc92e9118
--- /dev/null
+++ b/tools/include/uapi/linux/netlink.h
@@ -0,0 +1,251 @@
+/* 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 */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 83714ca1f22b..cbaa078e2aa1 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -160,6 +160,9 @@ $(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
 	$(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)
-- 
2.15.1

[PATCH bpf-next v7 2/5] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 127 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 133 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..749a447ec9ed 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,17 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include "nlattr.h"
+#include <uapi/linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef IFLA_XDP_MAX
+#define IFLA_XDP	43
+#define IFLA_XDP_FD	1
+#define IFLA_XDP_FLAGS	3
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,7 +57,9 @@
 # endif
 #endif
 
+#ifndef min
 #define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
 
 static inline __u64 ptr_to_u64(const void *ptr)
 {
@@ -413,3 +426,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 30c776375118..c60122d3ea85 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH bpf-next v7 3/5] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card. Code is partially take from libnl.

We add netlink.h to the uapi include of tools. And we need to
avoid include of userspace netlink header to have a successful
build of sample so nlattr.h has a define to avoid
the inclusion. Using a direct define could have been an issue
as NLMSGERR_ATTR_MAX can change in the future.

We also define SOL_NETLINK if not defined to avoid to have to
copy socket.h for a fixed value.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>

remote rtne

Signed-off-by: Eric Leblond <eric@regit.org>
---
 samples/bpf/Makefile   |   2 +-
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |  13 +++-
 tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h |  72 +++++++++++++++++++
 5 files changed, 273 insertions(+), 3 deletions(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 7f61a3d57fa7..5c4cd3745282 100644
--- a/samples/bpf/Makefile
+++ b/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)
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 749a447ec9ed..765fd95b0657 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -27,7 +27,7 @@
 #include "bpf.h"
 #include "libbpf.h"
 #include "nlattr.h"
-#include <uapi/linux/rtnetlink.h>
+#include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
 
@@ -37,6 +37,10 @@
 #define IFLA_XDP_FLAGS	3
 #endif
 
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
+
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
  * required to be defined explicitly.
@@ -441,6 +445,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one = 1;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -450,6 +455,11 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		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;
@@ -526,6 +536,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			if (!err->error)
 				continue;
 			ret = err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..4719434278b2
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,187 @@
+// 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..0a574aaa97f3
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,72 @@
+/* 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 <uapi/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 */
-- 
2.15.1

[PATCH bpf-next v7 4/5] libbpf: add missing SPDX-License-Identifier

[Eric Leblond]

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 2 ++
 tools/lib/bpf/bpf.h    | 2 ++
 tools/lib/bpf/libbpf.c | 2 ++
 tools/lib/bpf/libbpf.h | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 765fd95b0657..e850d8365100 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9f44c196931e..8d18fb73d7fb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c60122d3ea85..71ddc481f349 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * Common eBPF ELF object loading operations.
  *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e42f96900318..f85906533cdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
-- 
2.15.1

[PATCH bpf-next v7 5/5] samples/bpf: use bpf_set_link_xdp_fd

[Eric Leblond]

Use bpf_set_link_xdp_fd instead of set_link_xdp_fd to remove some
code duplication and benefit of netlink ext ack errors message.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 samples/bpf/bpf_load.c              | 102 ------------------------------------
 samples/bpf/bpf_load.h              |   2 +-
 samples/bpf/xdp1_user.c             |   4 +-
 samples/bpf/xdp_redirect_cpu_user.c |   6 +--
 samples/bpf/xdp_redirect_map_user.c |   8 +--
 samples/bpf/xdp_redirect_user.c     |   8 +--
 samples/bpf/xdp_router_ipv4_user.c  |  10 ++--
 samples/bpf/xdp_rxq_info_user.c     |   4 +-
 samples/bpf/xdp_tx_iptunnel_user.c  |   6 +--
 9 files changed, 24 insertions(+), 126 deletions(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 242631aa4ea2..69806d74fa53 100644
--- a/samples/bpf/bpf_load.c
+++ b/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;
-}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 7d57a4248893..453c200b389b 100644
--- a/samples/bpf/bpf_load.h
+++ b/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
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index fdaefe91801d..b901ee2b3336 100644
--- a/samples/bpf/xdp1_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 35fec9fecb57..23744a8aaf21 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index 978a532f0748..7eae07d7293e 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 4475d837bf2c..d54e91eb6cbf 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index 916462112d55..6296741c1fbd 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/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;
 		}
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index 32430e8b3a6a..478d95412de4 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 715cd12eaca5..f0a787268a87 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/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;
 }
-- 
2.15.1

Re: [PATCH bpf-next v7 2/5] libbpf: add function to setup XDP

[Daniel Borkmann]

On 01/25/2018 01:05 AM, Eric Leblond wrote:
> Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
> slightly modified to be library compliant.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>
> ---
>  tools/lib/bpf/bpf.c    | 127 +++++++++++++++++++++++++++++++++++++++++++++++++
>  tools/lib/bpf/libbpf.c |   2 +
>  tools/lib/bpf/libbpf.h |   4 ++
>  3 files changed, 133 insertions(+)
> 
> diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> index 5128677e4117..749a447ec9ed 100644
> --- a/tools/lib/bpf/bpf.c
> +++ b/tools/lib/bpf/bpf.c
> @@ -25,6 +25,17 @@
>  #include <asm/unistd.h>
>  #include <linux/bpf.h>
>  #include "bpf.h"
> +#include "libbpf.h"
> +#include "nlattr.h"
> +#include <uapi/linux/rtnetlink.h>

Doesn't libbpf pull in already -I$(srctree)/tools/include/uapi? Seems the
other headers don't need 'uapi/' path prefix.

> +#include <sys/socket.h>
> +#include <errno.h>
> +
> +#ifndef IFLA_XDP_MAX
> +#define IFLA_XDP	43
> +#define IFLA_XDP_FD	1
> +#define IFLA_XDP_FLAGS	3
> +#endif

Hm, given we pull in tools/include/uapi/linux/netlink.h, shouldn't we also
get include/uapi/linux/if_link.h dependency in here, so above ifdef workaround
can be avoided?

>  /*
>   * When building perf, unistd.h is overridden. __NR_bpf is
> @@ -46,7 +57,9 @@
>  # endif
>  #endif
>  
> +#ifndef min
>  #define min(x, y) ((x) < (y) ? (x) : (y))
> +#endif
>  
>  static inline __u64 ptr_to_u64(const void *ptr)
>  {
> @@ -413,3 +426,117 @@ 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 {
[...]

Re: [PATCH bpf-next v7 3/5] libbpf: add error reporting in XDP

[Daniel Borkmann]

On 01/25/2018 01:05 AM, Eric Leblond wrote:
> Parse netlink ext attribute to get the error message returned by
> the card. Code is partially take from libnl.
> 
> We add netlink.h to the uapi include of tools. And we need to
> avoid include of userspace netlink header to have a successful
> build of sample so nlattr.h has a define to avoid
> the inclusion. Using a direct define could have been an issue
> as NLMSGERR_ATTR_MAX can change in the future.
> 
> We also define SOL_NETLINK if not defined to avoid to have to
> copy socket.h for a fixed value.
> 
> Signed-off-by: Eric Leblond <eric@regit.org>
> Acked-by: Alexei Starovoitov <ast@kernel.org>
> 
> remote rtne
> 
> Signed-off-by: Eric Leblond <eric@regit.org>

Some leftover artifact from squashing commits?

>  samples/bpf/Makefile   |   2 +-
>  tools/lib/bpf/Build    |   2 +-
>  tools/lib/bpf/bpf.c    |  13 +++-
>  tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
>  tools/lib/bpf/nlattr.h |  72 +++++++++++++++++++
>  5 files changed, 273 insertions(+), 3 deletions(-)
>  create mode 100644 tools/lib/bpf/nlattr.c
>  create mode 100644 tools/lib/bpf/nlattr.h
> 
> diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
> index 7f61a3d57fa7..5c4cd3745282 100644
> --- a/samples/bpf/Makefile
> +++ b/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)
> diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
> index d8749756352d..64c679d67109 100644
> --- a/tools/lib/bpf/Build
> +++ b/tools/lib/bpf/Build
> @@ -1 +1 @@
> -libbpf-y := libbpf.o bpf.o
> +libbpf-y := libbpf.o bpf.o nlattr.o
> diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> index 749a447ec9ed..765fd95b0657 100644
> --- a/tools/lib/bpf/bpf.c
> +++ b/tools/lib/bpf/bpf.c
> @@ -27,7 +27,7 @@
>  #include "bpf.h"
>  #include "libbpf.h"
>  #include "nlattr.h"
> -#include <uapi/linux/rtnetlink.h>
> +#include <linux/rtnetlink.h>

Okay, so here it's put back from prior added uapi/linux/rtnetlink.h
into linux/rtnetlink.h. Could you add this properly in the first
commit rather than relative adjustment/fix within the same set?

>  #include <sys/socket.h>
>  #include <errno.h>
>  
> @@ -37,6 +37,10 @@
>  #define IFLA_XDP_FLAGS	3
>  #endif
>  
> +#ifndef SOL_NETLINK
> +#define SOL_NETLINK 270
> +#endif

This would need include/linux/socket.h into tools/ include infra
as well, no?

>  /*
>   * When building perf, unistd.h is overridden. __NR_bpf is
>   * required to be defined explicitly.
> @@ -441,6 +445,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
>  	struct nlmsghdr *nh;
>  	struct nlmsgerr *err;
>  	socklen_t addrlen;

Re: [PATCH bpf-next v7 2/5] libbpf: add function to setup XDP

[Eric Leblond]

Hi,

On Sat, 2018-01-27 at 02:23 +0100, Daniel Borkmann wrote:
> On 01/25/2018 01:05 AM, Eric Leblond wrote:
> > Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
> > slightly modified to be library compliant.
> > 
> > Signed-off-by: Eric Leblond <eric@regit.org>
> > Acked-by: Alexei Starovoitov <ast@kernel.org>
> > ---
> >  tools/lib/bpf/bpf.c    | 127
> > +++++++++++++++++++++++++++++++++++++++++++++++++
> >  tools/lib/bpf/libbpf.c |   2 +
> >  tools/lib/bpf/libbpf.h |   4 ++
> >  3 files changed, 133 insertions(+)
> > 
> > diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> > index 5128677e4117..749a447ec9ed 100644
> > --- a/tools/lib/bpf/bpf.c
> > +++ b/tools/lib/bpf/bpf.c
> > @@ -25,6 +25,17 @@
> >  #include <asm/unistd.h>
> >  #include <linux/bpf.h>
> >  #include "bpf.h"
> > +#include "libbpf.h"
> > +#include "nlattr.h"
> > +#include <uapi/linux/rtnetlink.h>
> 
> Doesn't libbpf pull in already -I$(srctree)/tools/include/uapi? Seems
> the
> other headers don't need 'uapi/' path prefix.

Right, it works without the uapi.
> 
> > +#include <sys/socket.h>
> > +#include <errno.h>
> > +
> > +#ifndef IFLA_XDP_MAX
> > +#define IFLA_XDP	43
> > +#define IFLA_XDP_FD	1
> > +#define IFLA_XDP_FLAGS	3
> > +#endif
> 
> Hm, given we pull in tools/include/uapi/linux/netlink.h, shouldn't we
> also
> get include/uapi/linux/if_link.h dependency in here, so above ifdef
> workaround
> can be avoided?

This values are fixed so we risk nothing by keeping a definition if
ever it is not available in system headers. But it is fine with me if
you want me to add if_link.h to include/uapi/. 

BR,
-- 
Eric Leblond <eric@regit.org>
Blog: https://home.regit.org/

Re: [PATCH bpf-next v7 3/5] libbpf: add error reporting in XDP

[Eric Leblond]

Hi,

On Sat, 2018-01-27 at 02:28 +0100, Daniel Borkmann wrote:
> On 01/25/2018 01:05 AM, Eric Leblond wrote:
> > Parse netlink ext attribute to get the error message returned by
> > the card. Code is partially take from libnl.
> > 
> > We add netlink.h to the uapi include of tools. And we need to
> > avoid include of userspace netlink header to have a successful
> > build of sample so nlattr.h has a define to avoid
> > the inclusion. Using a direct define could have been an issue
> > as NLMSGERR_ATTR_MAX can change in the future.
> > 
> > We also define SOL_NETLINK if not defined to avoid to have to
> > copy socket.h for a fixed value.
> > 
> > Signed-off-by: Eric Leblond <eric@regit.org>
> > Acked-by: Alexei Starovoitov <ast@kernel.org>
> > 
> > remote rtne
> > 
> > Signed-off-by: Eric Leblond <eric@regit.org>
> 
> Some leftover artifact from squashing commits?

Outch

> >  samples/bpf/Makefile   |   2 +-
> >  tools/lib/bpf/Build    |   2 +-
> >  tools/lib/bpf/bpf.c    |  13 +++-
> >  tools/lib/bpf/nlattr.c | 187
> > +++++++++++++++++++++++++++++++++++++++++++++++++
> >  tools/lib/bpf/nlattr.h |  72 +++++++++++++++++++
> >  5 files changed, 273 insertions(+), 3 deletions(-)
> >  create mode 100644 tools/lib/bpf/nlattr.c
> >  create mode 100644 tools/lib/bpf/nlattr.h
> > 
> > diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
> > index 7f61a3d57fa7..5c4cd3745282 100644
> > --- a/samples/bpf/Makefile
> > +++ b/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)
> > diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
> > index d8749756352d..64c679d67109 100644
> > --- a/tools/lib/bpf/Build
> > +++ b/tools/lib/bpf/Build
> > @@ -1 +1 @@
> > -libbpf-y := libbpf.o bpf.o
> > +libbpf-y := libbpf.o bpf.o nlattr.o
> > diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
> > index 749a447ec9ed..765fd95b0657 100644
> > --- a/tools/lib/bpf/bpf.c
> > +++ b/tools/lib/bpf/bpf.c
> > @@ -27,7 +27,7 @@
> >  #include "bpf.h"
> >  #include "libbpf.h"
> >  #include "nlattr.h"
> > -#include <uapi/linux/rtnetlink.h>
> > +#include <linux/rtnetlink.h>
> 
> Okay, so here it's put back from prior added uapi/linux/rtnetlink.h
> into linux/rtnetlink.h. Could you add this properly in the first
> commit rather than relative adjustment/fix within the same set?

Yes, sure.

> >  #include <sys/socket.h>
> >  #include <errno.h>
> >  
> > @@ -37,6 +37,10 @@
> >  #define IFLA_XDP_FLAGS	3
> >  #endif
> >  
> > +#ifndef SOL_NETLINK
> > +#define SOL_NETLINK 270
> > +#endif
> 
> This would need include/linux/socket.h into tools/ include infra
> as well, no?

Yes, and I fear a lot of dependencies.

++
-- 
Eric Leblond <eric@regit.org>
Blog: https://home.regit.org/

Re: [PATCH bpf-next v7 3/5] libbpf: add error reporting in XDP

[Daniel Borkmann]

Hi Eric,

On 01/27/2018 11:32 AM, Eric Leblond wrote:
> On Sat, 2018-01-27 at 02:28 +0100, Daniel Borkmann wrote:
>> On 01/25/2018 01:05 AM, Eric Leblond wrote:
>>> Parse netlink ext attribute to get the error message returned by
>>> the card. Code is partially take from libnl.
>>>
>>> We add netlink.h to the uapi include of tools. And we need to
>>> avoid include of userspace netlink header to have a successful
>>> build of sample so nlattr.h has a define to avoid
>>> the inclusion. Using a direct define could have been an issue
>>> as NLMSGERR_ATTR_MAX can change in the future.
>>>
>>> We also define SOL_NETLINK if not defined to avoid to have to
>>> copy socket.h for a fixed value.
>>>
>>> Signed-off-by: Eric Leblond <eric@regit.org>
>>> Acked-by: Alexei Starovoitov <ast@kernel.org>
>>>
>>> remote rtne
>>>
>>> Signed-off-by: Eric Leblond <eric@regit.org>
>>
>> Some leftover artifact from squashing commits?
> 
> Outch
> 
>>>  samples/bpf/Makefile   |   2 +-
>>>  tools/lib/bpf/Build    |   2 +-
>>>  tools/lib/bpf/bpf.c    |  13 +++-
>>>  tools/lib/bpf/nlattr.c | 187
>>> +++++++++++++++++++++++++++++++++++++++++++++++++
>>>  tools/lib/bpf/nlattr.h |  72 +++++++++++++++++++
>>>  5 files changed, 273 insertions(+), 3 deletions(-)
>>>  create mode 100644 tools/lib/bpf/nlattr.c
>>>  create mode 100644 tools/lib/bpf/nlattr.h
>>>
>>> diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
>>> index 7f61a3d57fa7..5c4cd3745282 100644
>>> --- a/samples/bpf/Makefile
>>> +++ b/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)
>>> diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
>>> index d8749756352d..64c679d67109 100644
>>> --- a/tools/lib/bpf/Build
>>> +++ b/tools/lib/bpf/Build
>>> @@ -1 +1 @@
>>> -libbpf-y := libbpf.o bpf.o
>>> +libbpf-y := libbpf.o bpf.o nlattr.o
>>> diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
>>> index 749a447ec9ed..765fd95b0657 100644
>>> --- a/tools/lib/bpf/bpf.c
>>> +++ b/tools/lib/bpf/bpf.c
>>> @@ -27,7 +27,7 @@
>>>  #include "bpf.h"
>>>  #include "libbpf.h"
>>>  #include "nlattr.h"
>>> -#include <uapi/linux/rtnetlink.h>
>>> +#include <linux/rtnetlink.h>
>>
>> Okay, so here it's put back from prior added uapi/linux/rtnetlink.h
>> into linux/rtnetlink.h. Could you add this properly in the first
>> commit rather than relative adjustment/fix within the same set?
> 
> Yes, sure.
> 
>>>  #include <sys/socket.h>
>>>  #include <errno.h>
>>>  
>>> @@ -37,6 +37,10 @@
>>>  #define IFLA_XDP_FLAGS	3
>>>  #endif
>>>  
>>> +#ifndef SOL_NETLINK
>>> +#define SOL_NETLINK 270
>>> +#endif
>>
>> This would need include/linux/socket.h into tools/ include infra
>> as well, no?
> 
> Yes, and I fear a lot of dependencies.

Sorry for the delay! So, once you pull these two headers in, are there more
follow-up dependencies with other headers required on your old test system?
I'd also be fine with keeping SOL_NETLINK here as is, but I would try to
have the if_link.h in the tools/ include infra, so we have all XDP definitions
available and up to date from the lib's pov. The dependency for if_link.h
seems minimal and probably enough to to only get in this single header. Could
you give that a try?

Thanks a lot,
Daniel

[PATCH bpf-next v8 0/5] libbpf: add XDP binding support

[Eric Leblond]

Hello Daniel,

No problem with the delay in the answer. I'm doing far worse.

Here is an updated version:
- add if_link.h in uapi and remove the definition
- fix a commit message
- remove uapi from a include

Best Regards,
--
Eric

[PATCH bpf-next v8 1/5] tools: add netlink.h and if_link.h in tools uapi

[Eric Leblond]

The headers are necessary for libbpf compilation on system with older
version of the headers.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 tools/include/uapi/linux/if_link.h | 943 +++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/netlink.h | 251 ++++++++++
 tools/lib/bpf/Makefile             |   6 +
 3 files changed, 1200 insertions(+)
 create mode 100644 tools/include/uapi/linux/if_link.h
 create mode 100644 tools/include/uapi/linux/netlink.h

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
new file mode 100644
index 000000000000..8616131e2c61
--- /dev/null
+++ b/tools/include/uapi/linux/if_link.h
@@ -0,0 +1,943 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_IF_LINK_H
+#define _UAPI_LINUX_IF_LINK_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+/* This struct should be in sync with struct rtnl_link_stats64 */
+struct rtnl_link_stats {
+	__u32	rx_packets;		/* total packets received	*/
+	__u32	tx_packets;		/* total packets transmitted	*/
+	__u32	rx_bytes;		/* total bytes received 	*/
+	__u32	tx_bytes;		/* total bytes transmitted	*/
+	__u32	rx_errors;		/* bad packets received		*/
+	__u32	tx_errors;		/* packet transmit problems	*/
+	__u32	rx_dropped;		/* no space in linux buffers	*/
+	__u32	tx_dropped;		/* no space available in linux	*/
+	__u32	multicast;		/* multicast packets received	*/
+	__u32	collisions;
+
+	/* detailed rx_errors: */
+	__u32	rx_length_errors;
+	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
+	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
+	__u32	rx_frame_errors;	/* recv'd frame alignment error */
+	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
+	__u32	rx_missed_errors;	/* receiver missed packet	*/
+
+	/* detailed tx_errors */
+	__u32	tx_aborted_errors;
+	__u32	tx_carrier_errors;
+	__u32	tx_fifo_errors;
+	__u32	tx_heartbeat_errors;
+	__u32	tx_window_errors;
+
+	/* for cslip etc */
+	__u32	rx_compressed;
+	__u32	tx_compressed;
+
+	__u32	rx_nohandler;		/* dropped, no handler found	*/
+};
+
+/* The main device statistics structure */
+struct rtnl_link_stats64 {
+	__u64	rx_packets;		/* total packets received	*/
+	__u64	tx_packets;		/* total packets transmitted	*/
+	__u64	rx_bytes;		/* total bytes received 	*/
+	__u64	tx_bytes;		/* total bytes transmitted	*/
+	__u64	rx_errors;		/* bad packets received		*/
+	__u64	tx_errors;		/* packet transmit problems	*/
+	__u64	rx_dropped;		/* no space in linux buffers	*/
+	__u64	tx_dropped;		/* no space available in linux	*/
+	__u64	multicast;		/* multicast packets received	*/
+	__u64	collisions;
+
+	/* detailed rx_errors: */
+	__u64	rx_length_errors;
+	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
+	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
+	__u64	rx_frame_errors;	/* recv'd frame alignment error */
+	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
+	__u64	rx_missed_errors;	/* receiver missed packet	*/
+
+	/* detailed tx_errors */
+	__u64	tx_aborted_errors;
+	__u64	tx_carrier_errors;
+	__u64	tx_fifo_errors;
+	__u64	tx_heartbeat_errors;
+	__u64	tx_window_errors;
+
+	/* for cslip etc */
+	__u64	rx_compressed;
+	__u64	tx_compressed;
+
+	__u64	rx_nohandler;		/* dropped, no handler found	*/
+};
+
+/* The struct should be in sync with struct ifmap */
+struct rtnl_link_ifmap {
+	__u64	mem_start;
+	__u64	mem_end;
+	__u64	base_addr;
+	__u16	irq;
+	__u8	dma;
+	__u8	port;
+};
+
+/*
+ * IFLA_AF_SPEC
+ *   Contains nested attributes for address family specific attributes.
+ *   Each address family may create a attribute with the address family
+ *   number as type and create its own attribute structure in it.
+ *
+ *   Example:
+ *   [IFLA_AF_SPEC] = {
+ *       [AF_INET] = {
+ *           [IFLA_INET_CONF] = ...,
+ *       },
+ *       [AF_INET6] = {
+ *           [IFLA_INET6_FLAGS] = ...,
+ *           [IFLA_INET6_CONF] = ...,
+ *       }
+ *   }
+ */
+
+enum {
+	IFLA_UNSPEC,
+	IFLA_ADDRESS,
+	IFLA_BROADCAST,
+	IFLA_IFNAME,
+	IFLA_MTU,
+	IFLA_LINK,
+	IFLA_QDISC,
+	IFLA_STATS,
+	IFLA_COST,
+#define IFLA_COST IFLA_COST
+	IFLA_PRIORITY,
+#define IFLA_PRIORITY IFLA_PRIORITY
+	IFLA_MASTER,
+#define IFLA_MASTER IFLA_MASTER
+	IFLA_WIRELESS,		/* Wireless Extension event - see wireless.h */
+#define IFLA_WIRELESS IFLA_WIRELESS
+	IFLA_PROTINFO,		/* Protocol specific information for a link */
+#define IFLA_PROTINFO IFLA_PROTINFO
+	IFLA_TXQLEN,
+#define IFLA_TXQLEN IFLA_TXQLEN
+	IFLA_MAP,
+#define IFLA_MAP IFLA_MAP
+	IFLA_WEIGHT,
+#define IFLA_WEIGHT IFLA_WEIGHT
+	IFLA_OPERSTATE,
+	IFLA_LINKMODE,
+	IFLA_LINKINFO,
+#define IFLA_LINKINFO IFLA_LINKINFO
+	IFLA_NET_NS_PID,
+	IFLA_IFALIAS,
+	IFLA_NUM_VF,		/* Number of VFs if device is SR-IOV PF */
+	IFLA_VFINFO_LIST,
+	IFLA_STATS64,
+	IFLA_VF_PORTS,
+	IFLA_PORT_SELF,
+	IFLA_AF_SPEC,
+	IFLA_GROUP,		/* Group the device belongs to */
+	IFLA_NET_NS_FD,
+	IFLA_EXT_MASK,		/* Extended info mask, VFs, etc */
+	IFLA_PROMISCUITY,	/* Promiscuity count: > 0 means acts PROMISC */
+#define IFLA_PROMISCUITY IFLA_PROMISCUITY
+	IFLA_NUM_TX_QUEUES,
+	IFLA_NUM_RX_QUEUES,
+	IFLA_CARRIER,
+	IFLA_PHYS_PORT_ID,
+	IFLA_CARRIER_CHANGES,
+	IFLA_PHYS_SWITCH_ID,
+	IFLA_LINK_NETNSID,
+	IFLA_PHYS_PORT_NAME,
+	IFLA_PROTO_DOWN,
+	IFLA_GSO_MAX_SEGS,
+	IFLA_GSO_MAX_SIZE,
+	IFLA_PAD,
+	IFLA_XDP,
+	IFLA_EVENT,
+	IFLA_NEW_NETNSID,
+	IFLA_IF_NETNSID,
+	IFLA_CARRIER_UP_COUNT,
+	IFLA_CARRIER_DOWN_COUNT,
+	__IFLA_MAX
+};
+
+
+#define IFLA_MAX (__IFLA_MAX - 1)
+
+/* backwards compatibility for userspace */
+#ifndef __KERNEL__
+#define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
+#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
+#endif
+
+enum {
+	IFLA_INET_UNSPEC,
+	IFLA_INET_CONF,
+	__IFLA_INET_MAX,
+};
+
+#define IFLA_INET_MAX (__IFLA_INET_MAX - 1)
+
+/* ifi_flags.
+
+   IFF_* flags.
+
+   The only change is:
+   IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are
+   more not changeable by user. They describe link media
+   characteristics and set by device driver.
+
+   Comments:
+   - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid
+   - If neither of these three flags are set;
+     the interface is NBMA.
+
+   - IFF_MULTICAST does not mean anything special:
+   multicasts can be used on all not-NBMA links.
+   IFF_MULTICAST means that this media uses special encapsulation
+   for multicast frames. Apparently, all IFF_POINTOPOINT and
+   IFF_BROADCAST devices are able to use multicasts too.
+ */
+
+/* IFLA_LINK.
+   For usual devices it is equal ifi_index.
+   If it is a "virtual interface" (f.e. tunnel), ifi_link
+   can point to real physical interface (f.e. for bandwidth calculations),
+   or maybe 0, what means, that real media is unknown (usual
+   for IPIP tunnels, when route to endpoint is allowed to change)
+ */
+
+/* Subtype attributes for IFLA_PROTINFO */
+enum {
+	IFLA_INET6_UNSPEC,
+	IFLA_INET6_FLAGS,	/* link flags			*/
+	IFLA_INET6_CONF,	/* sysctl parameters		*/
+	IFLA_INET6_STATS,	/* statistics			*/
+	IFLA_INET6_MCAST,	/* MC things. What of them?	*/
+	IFLA_INET6_CACHEINFO,	/* time values and max reasm size */
+	IFLA_INET6_ICMP6STATS,	/* statistics (icmpv6)		*/
+	IFLA_INET6_TOKEN,	/* device token			*/
+	IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+	__IFLA_INET6_MAX
+};
+
+#define IFLA_INET6_MAX	(__IFLA_INET6_MAX - 1)
+
+enum in6_addr_gen_mode {
+	IN6_ADDR_GEN_MODE_EUI64,
+	IN6_ADDR_GEN_MODE_NONE,
+	IN6_ADDR_GEN_MODE_STABLE_PRIVACY,
+	IN6_ADDR_GEN_MODE_RANDOM,
+};
+
+/* Bridge section */
+
+enum {
+	IFLA_BR_UNSPEC,
+	IFLA_BR_FORWARD_DELAY,
+	IFLA_BR_HELLO_TIME,
+	IFLA_BR_MAX_AGE,
+	IFLA_BR_AGEING_TIME,
+	IFLA_BR_STP_STATE,
+	IFLA_BR_PRIORITY,
+	IFLA_BR_VLAN_FILTERING,
+	IFLA_BR_VLAN_PROTOCOL,
+	IFLA_BR_GROUP_FWD_MASK,
+	IFLA_BR_ROOT_ID,
+	IFLA_BR_BRIDGE_ID,
+	IFLA_BR_ROOT_PORT,
+	IFLA_BR_ROOT_PATH_COST,
+	IFLA_BR_TOPOLOGY_CHANGE,
+	IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
+	IFLA_BR_HELLO_TIMER,
+	IFLA_BR_TCN_TIMER,
+	IFLA_BR_TOPOLOGY_CHANGE_TIMER,
+	IFLA_BR_GC_TIMER,
+	IFLA_BR_GROUP_ADDR,
+	IFLA_BR_FDB_FLUSH,
+	IFLA_BR_MCAST_ROUTER,
+	IFLA_BR_MCAST_SNOOPING,
+	IFLA_BR_MCAST_QUERY_USE_IFADDR,
+	IFLA_BR_MCAST_QUERIER,
+	IFLA_BR_MCAST_HASH_ELASTICITY,
+	IFLA_BR_MCAST_HASH_MAX,
+	IFLA_BR_MCAST_LAST_MEMBER_CNT,
+	IFLA_BR_MCAST_STARTUP_QUERY_CNT,
+	IFLA_BR_MCAST_LAST_MEMBER_INTVL,
+	IFLA_BR_MCAST_MEMBERSHIP_INTVL,
+	IFLA_BR_MCAST_QUERIER_INTVL,
+	IFLA_BR_MCAST_QUERY_INTVL,
+	IFLA_BR_MCAST_QUERY_RESPONSE_INTVL,
+	IFLA_BR_MCAST_STARTUP_QUERY_INTVL,
+	IFLA_BR_NF_CALL_IPTABLES,
+	IFLA_BR_NF_CALL_IP6TABLES,
+	IFLA_BR_NF_CALL_ARPTABLES,
+	IFLA_BR_VLAN_DEFAULT_PVID,
+	IFLA_BR_PAD,
+	IFLA_BR_VLAN_STATS_ENABLED,
+	IFLA_BR_MCAST_STATS_ENABLED,
+	IFLA_BR_MCAST_IGMP_VERSION,
+	IFLA_BR_MCAST_MLD_VERSION,
+	__IFLA_BR_MAX,
+};
+
+#define IFLA_BR_MAX	(__IFLA_BR_MAX - 1)
+
+struct ifla_bridge_id {
+	__u8	prio[2];
+	__u8	addr[6]; /* ETH_ALEN */
+};
+
+enum {
+	BRIDGE_MODE_UNSPEC,
+	BRIDGE_MODE_HAIRPIN,
+};
+
+enum {
+	IFLA_BRPORT_UNSPEC,
+	IFLA_BRPORT_STATE,	/* Spanning tree state     */
+	IFLA_BRPORT_PRIORITY,	/* "             priority  */
+	IFLA_BRPORT_COST,	/* "             cost      */
+	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
+	IFLA_BRPORT_GUARD,	/* bpdu guard              */
+	IFLA_BRPORT_PROTECT,	/* root port protection    */
+	IFLA_BRPORT_FAST_LEAVE,	/* multicast fast leave    */
+	IFLA_BRPORT_LEARNING,	/* mac learning */
+	IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */
+	IFLA_BRPORT_PROXYARP,	/* proxy ARP */
+	IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */
+	IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */
+	IFLA_BRPORT_ROOT_ID,	/* designated root */
+	IFLA_BRPORT_BRIDGE_ID,	/* designated bridge */
+	IFLA_BRPORT_DESIGNATED_PORT,
+	IFLA_BRPORT_DESIGNATED_COST,
+	IFLA_BRPORT_ID,
+	IFLA_BRPORT_NO,
+	IFLA_BRPORT_TOPOLOGY_CHANGE_ACK,
+	IFLA_BRPORT_CONFIG_PENDING,
+	IFLA_BRPORT_MESSAGE_AGE_TIMER,
+	IFLA_BRPORT_FORWARD_DELAY_TIMER,
+	IFLA_BRPORT_HOLD_TIMER,
+	IFLA_BRPORT_FLUSH,
+	IFLA_BRPORT_MULTICAST_ROUTER,
+	IFLA_BRPORT_PAD,
+	IFLA_BRPORT_MCAST_FLOOD,
+	IFLA_BRPORT_MCAST_TO_UCAST,
+	IFLA_BRPORT_VLAN_TUNNEL,
+	IFLA_BRPORT_BCAST_FLOOD,
+	IFLA_BRPORT_GROUP_FWD_MASK,
+	IFLA_BRPORT_NEIGH_SUPPRESS,
+	__IFLA_BRPORT_MAX
+};
+#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
+
+struct ifla_cacheinfo {
+	__u32	max_reasm_len;
+	__u32	tstamp;		/* ipv6InterfaceTable updated timestamp */
+	__u32	reachable_time;
+	__u32	retrans_time;
+};
+
+enum {
+	IFLA_INFO_UNSPEC,
+	IFLA_INFO_KIND,
+	IFLA_INFO_DATA,
+	IFLA_INFO_XSTATS,
+	IFLA_INFO_SLAVE_KIND,
+	IFLA_INFO_SLAVE_DATA,
+	__IFLA_INFO_MAX,
+};
+
+#define IFLA_INFO_MAX	(__IFLA_INFO_MAX - 1)
+
+/* VLAN section */
+
+enum {
+	IFLA_VLAN_UNSPEC,
+	IFLA_VLAN_ID,
+	IFLA_VLAN_FLAGS,
+	IFLA_VLAN_EGRESS_QOS,
+	IFLA_VLAN_INGRESS_QOS,
+	IFLA_VLAN_PROTOCOL,
+	__IFLA_VLAN_MAX,
+};
+
+#define IFLA_VLAN_MAX	(__IFLA_VLAN_MAX - 1)
+
+struct ifla_vlan_flags {
+	__u32	flags;
+	__u32	mask;
+};
+
+enum {
+	IFLA_VLAN_QOS_UNSPEC,
+	IFLA_VLAN_QOS_MAPPING,
+	__IFLA_VLAN_QOS_MAX
+};
+
+#define IFLA_VLAN_QOS_MAX	(__IFLA_VLAN_QOS_MAX - 1)
+
+struct ifla_vlan_qos_mapping {
+	__u32 from;
+	__u32 to;
+};
+
+/* MACVLAN section */
+enum {
+	IFLA_MACVLAN_UNSPEC,
+	IFLA_MACVLAN_MODE,
+	IFLA_MACVLAN_FLAGS,
+	IFLA_MACVLAN_MACADDR_MODE,
+	IFLA_MACVLAN_MACADDR,
+	IFLA_MACVLAN_MACADDR_DATA,
+	IFLA_MACVLAN_MACADDR_COUNT,
+	__IFLA_MACVLAN_MAX,
+};
+
+#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1)
+
+enum macvlan_mode {
+	MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */
+	MACVLAN_MODE_VEPA    = 2, /* talk to other ports through ext bridge */
+	MACVLAN_MODE_BRIDGE  = 4, /* talk to bridge ports directly */
+	MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */
+	MACVLAN_MODE_SOURCE  = 16,/* use source MAC address list to assign */
+};
+
+enum macvlan_macaddr_mode {
+	MACVLAN_MACADDR_ADD,
+	MACVLAN_MACADDR_DEL,
+	MACVLAN_MACADDR_FLUSH,
+	MACVLAN_MACADDR_SET,
+};
+
+#define MACVLAN_FLAG_NOPROMISC	1
+
+/* VRF section */
+enum {
+	IFLA_VRF_UNSPEC,
+	IFLA_VRF_TABLE,
+	__IFLA_VRF_MAX
+};
+
+#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1)
+
+enum {
+	IFLA_VRF_PORT_UNSPEC,
+	IFLA_VRF_PORT_TABLE,
+	__IFLA_VRF_PORT_MAX
+};
+
+#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1)
+
+/* MACSEC section */
+enum {
+	IFLA_MACSEC_UNSPEC,
+	IFLA_MACSEC_SCI,
+	IFLA_MACSEC_PORT,
+	IFLA_MACSEC_ICV_LEN,
+	IFLA_MACSEC_CIPHER_SUITE,
+	IFLA_MACSEC_WINDOW,
+	IFLA_MACSEC_ENCODING_SA,
+	IFLA_MACSEC_ENCRYPT,
+	IFLA_MACSEC_PROTECT,
+	IFLA_MACSEC_INC_SCI,
+	IFLA_MACSEC_ES,
+	IFLA_MACSEC_SCB,
+	IFLA_MACSEC_REPLAY_PROTECT,
+	IFLA_MACSEC_VALIDATION,
+	IFLA_MACSEC_PAD,
+	__IFLA_MACSEC_MAX,
+};
+
+#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
+
+enum macsec_validation_type {
+	MACSEC_VALIDATE_DISABLED = 0,
+	MACSEC_VALIDATE_CHECK = 1,
+	MACSEC_VALIDATE_STRICT = 2,
+	__MACSEC_VALIDATE_END,
+	MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
+};
+
+/* IPVLAN section */
+enum {
+	IFLA_IPVLAN_UNSPEC,
+	IFLA_IPVLAN_MODE,
+	IFLA_IPVLAN_FLAGS,
+	__IFLA_IPVLAN_MAX
+};
+
+#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1)
+
+enum ipvlan_mode {
+	IPVLAN_MODE_L2 = 0,
+	IPVLAN_MODE_L3,
+	IPVLAN_MODE_L3S,
+	IPVLAN_MODE_MAX
+};
+
+#define IPVLAN_F_PRIVATE	0x01
+#define IPVLAN_F_VEPA		0x02
+
+/* VXLAN section */
+enum {
+	IFLA_VXLAN_UNSPEC,
+	IFLA_VXLAN_ID,
+	IFLA_VXLAN_GROUP,	/* group or remote address */
+	IFLA_VXLAN_LINK,
+	IFLA_VXLAN_LOCAL,
+	IFLA_VXLAN_TTL,
+	IFLA_VXLAN_TOS,
+	IFLA_VXLAN_LEARNING,
+	IFLA_VXLAN_AGEING,
+	IFLA_VXLAN_LIMIT,
+	IFLA_VXLAN_PORT_RANGE,	/* source port */
+	IFLA_VXLAN_PROXY,
+	IFLA_VXLAN_RSC,
+	IFLA_VXLAN_L2MISS,
+	IFLA_VXLAN_L3MISS,
+	IFLA_VXLAN_PORT,	/* destination port */
+	IFLA_VXLAN_GROUP6,
+	IFLA_VXLAN_LOCAL6,
+	IFLA_VXLAN_UDP_CSUM,
+	IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
+	IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+	IFLA_VXLAN_REMCSUM_TX,
+	IFLA_VXLAN_REMCSUM_RX,
+	IFLA_VXLAN_GBP,
+	IFLA_VXLAN_REMCSUM_NOPARTIAL,
+	IFLA_VXLAN_COLLECT_METADATA,
+	IFLA_VXLAN_LABEL,
+	IFLA_VXLAN_GPE,
+	__IFLA_VXLAN_MAX
+};
+#define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
+
+struct ifla_vxlan_port_range {
+	__be16	low;
+	__be16	high;
+};
+
+/* GENEVE section */
+enum {
+	IFLA_GENEVE_UNSPEC,
+	IFLA_GENEVE_ID,
+	IFLA_GENEVE_REMOTE,
+	IFLA_GENEVE_TTL,
+	IFLA_GENEVE_TOS,
+	IFLA_GENEVE_PORT,	/* destination port */
+	IFLA_GENEVE_COLLECT_METADATA,
+	IFLA_GENEVE_REMOTE6,
+	IFLA_GENEVE_UDP_CSUM,
+	IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
+	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
+	IFLA_GENEVE_LABEL,
+	__IFLA_GENEVE_MAX
+};
+#define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
+
+/* PPP section */
+enum {
+	IFLA_PPP_UNSPEC,
+	IFLA_PPP_DEV_FD,
+	__IFLA_PPP_MAX
+};
+#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
+
+/* GTP section */
+
+enum ifla_gtp_role {
+	GTP_ROLE_GGSN = 0,
+	GTP_ROLE_SGSN,
+};
+
+enum {
+	IFLA_GTP_UNSPEC,
+	IFLA_GTP_FD0,
+	IFLA_GTP_FD1,
+	IFLA_GTP_PDP_HASHSIZE,
+	IFLA_GTP_ROLE,
+	__IFLA_GTP_MAX,
+};
+#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
+
+/* Bonding section */
+
+enum {
+	IFLA_BOND_UNSPEC,
+	IFLA_BOND_MODE,
+	IFLA_BOND_ACTIVE_SLAVE,
+	IFLA_BOND_MIIMON,
+	IFLA_BOND_UPDELAY,
+	IFLA_BOND_DOWNDELAY,
+	IFLA_BOND_USE_CARRIER,
+	IFLA_BOND_ARP_INTERVAL,
+	IFLA_BOND_ARP_IP_TARGET,
+	IFLA_BOND_ARP_VALIDATE,
+	IFLA_BOND_ARP_ALL_TARGETS,
+	IFLA_BOND_PRIMARY,
+	IFLA_BOND_PRIMARY_RESELECT,
+	IFLA_BOND_FAIL_OVER_MAC,
+	IFLA_BOND_XMIT_HASH_POLICY,
+	IFLA_BOND_RESEND_IGMP,
+	IFLA_BOND_NUM_PEER_NOTIF,
+	IFLA_BOND_ALL_SLAVES_ACTIVE,
+	IFLA_BOND_MIN_LINKS,
+	IFLA_BOND_LP_INTERVAL,
+	IFLA_BOND_PACKETS_PER_SLAVE,
+	IFLA_BOND_AD_LACP_RATE,
+	IFLA_BOND_AD_SELECT,
+	IFLA_BOND_AD_INFO,
+	IFLA_BOND_AD_ACTOR_SYS_PRIO,
+	IFLA_BOND_AD_USER_PORT_KEY,
+	IFLA_BOND_AD_ACTOR_SYSTEM,
+	IFLA_BOND_TLB_DYNAMIC_LB,
+	__IFLA_BOND_MAX,
+};
+
+#define IFLA_BOND_MAX	(__IFLA_BOND_MAX - 1)
+
+enum {
+	IFLA_BOND_AD_INFO_UNSPEC,
+	IFLA_BOND_AD_INFO_AGGREGATOR,
+	IFLA_BOND_AD_INFO_NUM_PORTS,
+	IFLA_BOND_AD_INFO_ACTOR_KEY,
+	IFLA_BOND_AD_INFO_PARTNER_KEY,
+	IFLA_BOND_AD_INFO_PARTNER_MAC,
+	__IFLA_BOND_AD_INFO_MAX,
+};
+
+#define IFLA_BOND_AD_INFO_MAX	(__IFLA_BOND_AD_INFO_MAX - 1)
+
+enum {
+	IFLA_BOND_SLAVE_UNSPEC,
+	IFLA_BOND_SLAVE_STATE,
+	IFLA_BOND_SLAVE_MII_STATUS,
+	IFLA_BOND_SLAVE_LINK_FAILURE_COUNT,
+	IFLA_BOND_SLAVE_PERM_HWADDR,
+	IFLA_BOND_SLAVE_QUEUE_ID,
+	IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
+	IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
+	IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+	__IFLA_BOND_SLAVE_MAX,
+};
+
+#define IFLA_BOND_SLAVE_MAX	(__IFLA_BOND_SLAVE_MAX - 1)
+
+/* SR-IOV virtual function management section */
+
+enum {
+	IFLA_VF_INFO_UNSPEC,
+	IFLA_VF_INFO,
+	__IFLA_VF_INFO_MAX,
+};
+
+#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1)
+
+enum {
+	IFLA_VF_UNSPEC,
+	IFLA_VF_MAC,		/* Hardware queue specific attributes */
+	IFLA_VF_VLAN,		/* VLAN ID and QoS */
+	IFLA_VF_TX_RATE,	/* Max TX Bandwidth Allocation */
+	IFLA_VF_SPOOFCHK,	/* Spoof Checking on/off switch */
+	IFLA_VF_LINK_STATE,	/* link state enable/disable/auto switch */
+	IFLA_VF_RATE,		/* Min and Max TX Bandwidth Allocation */
+	IFLA_VF_RSS_QUERY_EN,	/* RSS Redirection Table and Hash Key query
+				 * on/off switch
+				 */
+	IFLA_VF_STATS,		/* network device statistics */
+	IFLA_VF_TRUST,		/* Trust VF */
+	IFLA_VF_IB_NODE_GUID,	/* VF Infiniband node GUID */
+	IFLA_VF_IB_PORT_GUID,	/* VF Infiniband port GUID */
+	IFLA_VF_VLAN_LIST,	/* nested list of vlans, option for QinQ */
+	__IFLA_VF_MAX,
+};
+
+#define IFLA_VF_MAX (__IFLA_VF_MAX - 1)
+
+struct ifla_vf_mac {
+	__u32 vf;
+	__u8 mac[32]; /* MAX_ADDR_LEN */
+};
+
+struct ifla_vf_vlan {
+	__u32 vf;
+	__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
+	__u32 qos;
+};
+
+enum {
+	IFLA_VF_VLAN_INFO_UNSPEC,
+	IFLA_VF_VLAN_INFO,	/* VLAN ID, QoS and VLAN protocol */
+	__IFLA_VF_VLAN_INFO_MAX,
+};
+
+#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1)
+#define MAX_VLAN_LIST_LEN 1
+
+struct ifla_vf_vlan_info {
+	__u32 vf;
+	__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
+	__u32 qos;
+	__be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */
+};
+
+struct ifla_vf_tx_rate {
+	__u32 vf;
+	__u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */
+};
+
+struct ifla_vf_rate {
+	__u32 vf;
+	__u32 min_tx_rate; /* Min Bandwidth in Mbps */
+	__u32 max_tx_rate; /* Max Bandwidth in Mbps */
+};
+
+struct ifla_vf_spoofchk {
+	__u32 vf;
+	__u32 setting;
+};
+
+struct ifla_vf_guid {
+	__u32 vf;
+	__u64 guid;
+};
+
+enum {
+	IFLA_VF_LINK_STATE_AUTO,	/* link state of the uplink */
+	IFLA_VF_LINK_STATE_ENABLE,	/* link always up */
+	IFLA_VF_LINK_STATE_DISABLE,	/* link always down */
+	__IFLA_VF_LINK_STATE_MAX,
+};
+
+struct ifla_vf_link_state {
+	__u32 vf;
+	__u32 link_state;
+};
+
+struct ifla_vf_rss_query_en {
+	__u32 vf;
+	__u32 setting;
+};
+
+enum {
+	IFLA_VF_STATS_RX_PACKETS,
+	IFLA_VF_STATS_TX_PACKETS,
+	IFLA_VF_STATS_RX_BYTES,
+	IFLA_VF_STATS_TX_BYTES,
+	IFLA_VF_STATS_BROADCAST,
+	IFLA_VF_STATS_MULTICAST,
+	IFLA_VF_STATS_PAD,
+	IFLA_VF_STATS_RX_DROPPED,
+	IFLA_VF_STATS_TX_DROPPED,
+	__IFLA_VF_STATS_MAX,
+};
+
+#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1)
+
+struct ifla_vf_trust {
+	__u32 vf;
+	__u32 setting;
+};
+
+/* VF ports management section
+ *
+ *	Nested layout of set/get msg is:
+ *
+ *		[IFLA_NUM_VF]
+ *		[IFLA_VF_PORTS]
+ *			[IFLA_VF_PORT]
+ *				[IFLA_PORT_*], ...
+ *			[IFLA_VF_PORT]
+ *				[IFLA_PORT_*], ...
+ *			...
+ *		[IFLA_PORT_SELF]
+ *			[IFLA_PORT_*], ...
+ */
+
+enum {
+	IFLA_VF_PORT_UNSPEC,
+	IFLA_VF_PORT,			/* nest */
+	__IFLA_VF_PORT_MAX,
+};
+
+#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1)
+
+enum {
+	IFLA_PORT_UNSPEC,
+	IFLA_PORT_VF,			/* __u32 */
+	IFLA_PORT_PROFILE,		/* string */
+	IFLA_PORT_VSI_TYPE,		/* 802.1Qbg (pre-)standard VDP */
+	IFLA_PORT_INSTANCE_UUID,	/* binary UUID */
+	IFLA_PORT_HOST_UUID,		/* binary UUID */
+	IFLA_PORT_REQUEST,		/* __u8 */
+	IFLA_PORT_RESPONSE,		/* __u16, output only */
+	__IFLA_PORT_MAX,
+};
+
+#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1)
+
+#define PORT_PROFILE_MAX	40
+#define PORT_UUID_MAX		16
+#define PORT_SELF_VF		-1
+
+enum {
+	PORT_REQUEST_PREASSOCIATE = 0,
+	PORT_REQUEST_PREASSOCIATE_RR,
+	PORT_REQUEST_ASSOCIATE,
+	PORT_REQUEST_DISASSOCIATE,
+};
+
+enum {
+	PORT_VDP_RESPONSE_SUCCESS = 0,
+	PORT_VDP_RESPONSE_INVALID_FORMAT,
+	PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES,
+	PORT_VDP_RESPONSE_UNUSED_VTID,
+	PORT_VDP_RESPONSE_VTID_VIOLATION,
+	PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION,
+	PORT_VDP_RESPONSE_OUT_OF_SYNC,
+	/* 0x08-0xFF reserved for future VDP use */
+	PORT_PROFILE_RESPONSE_SUCCESS = 0x100,
+	PORT_PROFILE_RESPONSE_INPROGRESS,
+	PORT_PROFILE_RESPONSE_INVALID,
+	PORT_PROFILE_RESPONSE_BADSTATE,
+	PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES,
+	PORT_PROFILE_RESPONSE_ERROR,
+};
+
+struct ifla_port_vsi {
+	__u8 vsi_mgr_id;
+	__u8 vsi_type_id[3];
+	__u8 vsi_type_version;
+	__u8 pad[3];
+};
+
+
+/* IPoIB section */
+
+enum {
+	IFLA_IPOIB_UNSPEC,
+	IFLA_IPOIB_PKEY,
+	IFLA_IPOIB_MODE,
+	IFLA_IPOIB_UMCAST,
+	__IFLA_IPOIB_MAX
+};
+
+enum {
+	IPOIB_MODE_DATAGRAM  = 0, /* using unreliable datagram QPs */
+	IPOIB_MODE_CONNECTED = 1, /* using connected QPs */
+};
+
+#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
+
+
+/* HSR section */
+
+enum {
+	IFLA_HSR_UNSPEC,
+	IFLA_HSR_SLAVE1,
+	IFLA_HSR_SLAVE2,
+	IFLA_HSR_MULTICAST_SPEC,	/* Last byte of supervision addr */
+	IFLA_HSR_SUPERVISION_ADDR,	/* Supervision frame multicast addr */
+	IFLA_HSR_SEQ_NR,
+	IFLA_HSR_VERSION,		/* HSR version */
+	__IFLA_HSR_MAX,
+};
+
+#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1)
+
+/* STATS section */
+
+struct if_stats_msg {
+	__u8  family;
+	__u8  pad1;
+	__u16 pad2;
+	__u32 ifindex;
+	__u32 filter_mask;
+};
+
+/* A stats attribute can be netdev specific or a global stat.
+ * For netdev stats, lets use the prefix IFLA_STATS_LINK_*
+ */
+enum {
+	IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */
+	IFLA_STATS_LINK_64,
+	IFLA_STATS_LINK_XSTATS,
+	IFLA_STATS_LINK_XSTATS_SLAVE,
+	IFLA_STATS_LINK_OFFLOAD_XSTATS,
+	IFLA_STATS_AF_SPEC,
+	__IFLA_STATS_MAX,
+};
+
+#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1)
+
+#define IFLA_STATS_FILTER_BIT(ATTR)	(1 << (ATTR - 1))
+
+/* These are embedded into IFLA_STATS_LINK_XSTATS:
+ * [IFLA_STATS_LINK_XSTATS]
+ * -> [LINK_XSTATS_TYPE_xxx]
+ *    -> [rtnl link type specific attributes]
+ */
+enum {
+	LINK_XSTATS_TYPE_UNSPEC,
+	LINK_XSTATS_TYPE_BRIDGE,
+	__LINK_XSTATS_TYPE_MAX
+};
+#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
+
+/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */
+enum {
+	IFLA_OFFLOAD_XSTATS_UNSPEC,
+	IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
+	__IFLA_OFFLOAD_XSTATS_MAX
+};
+#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
+
+/* XDP section */
+
+#define XDP_FLAGS_UPDATE_IF_NOEXIST	(1U << 0)
+#define XDP_FLAGS_SKB_MODE		(1U << 1)
+#define XDP_FLAGS_DRV_MODE		(1U << 2)
+#define XDP_FLAGS_HW_MODE		(1U << 3)
+#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)
+
+/* These are stored into IFLA_XDP_ATTACHED on dump. */
+enum {
+	XDP_ATTACHED_NONE = 0,
+	XDP_ATTACHED_DRV,
+	XDP_ATTACHED_SKB,
+	XDP_ATTACHED_HW,
+};
+
+enum {
+	IFLA_XDP_UNSPEC,
+	IFLA_XDP_FD,
+	IFLA_XDP_ATTACHED,
+	IFLA_XDP_FLAGS,
+	IFLA_XDP_PROG_ID,
+	__IFLA_XDP_MAX,
+};
+
+#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1)
+
+enum {
+	IFLA_EVENT_NONE,
+	IFLA_EVENT_REBOOT,		/* internal reset / reboot */
+	IFLA_EVENT_FEATURES,		/* change in offload features */
+	IFLA_EVENT_BONDING_FAILOVER,	/* change in active slave */
+	IFLA_EVENT_NOTIFY_PEERS,	/* re-sent grat. arp/ndisc */
+	IFLA_EVENT_IGMP_RESEND,		/* re-sent IGMP JOIN */
+	IFLA_EVENT_BONDING_OPTIONS,	/* change in bonding options */
+};
+
+#endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
new file mode 100644
index 000000000000..776bc92e9118
--- /dev/null
+++ b/tools/include/uapi/linux/netlink.h
@@ -0,0 +1,251 @@
+/* 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 */
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 83714ca1f22b..e6d5f8d1477f 100644
--- a/tools/lib/bpf/Makefile
+++ b/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)
-- 
2.15.1

[PATCH bpf-next v8 2/5] libbpf: add function to setup XDP

[Eric Leblond]

Most of the code is taken from set_link_xdp_fd() in bpf_load.c and
slightly modified to be library compliant.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 122 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c |   2 +
 tools/lib/bpf/libbpf.h |   4 ++
 3 files changed, 128 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 5128677e4117..bf2772566240 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -25,6 +25,12 @@
 #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>
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,7 +52,9 @@
 # endif
 #endif
 
+#ifndef min
 #define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
 
 static inline __u64 ptr_to_u64(const void *ptr)
 {
@@ -413,3 +421,117 @@ 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;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	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;
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 30c776375118..c60122d3ea85 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -106,6 +106,8 @@ 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)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6e20003109e0..e42f96900318 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -42,6 +42,8 @@ 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 +248,6 @@ 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
-- 
2.15.1

[PATCH bpf-next v8 3/5] libbpf: add error reporting in XDP

[Eric Leblond]

Parse netlink ext attribute to get the error message returned by
the card. Code is partially take from libnl.

We add netlink.h to the uapi include of tools. And we need to
avoid include of userspace netlink header to have a successful
build of sample so nlattr.h has a define to avoid
the inclusion. Using a direct define could have been an issue
as NLMSGERR_ATTR_MAX can change in the future.

We also define SOL_NETLINK if not defined to avoid to have to
copy socket.h for a fixed value.

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/Makefile   |   2 +-
 tools/lib/bpf/Build    |   2 +-
 tools/lib/bpf/bpf.c    |  11 +++
 tools/lib/bpf/nlattr.c | 187 +++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/nlattr.h |  72 +++++++++++++++++++
 5 files changed, 272 insertions(+), 2 deletions(-)
 create mode 100644 tools/lib/bpf/nlattr.c
 create mode 100644 tools/lib/bpf/nlattr.h

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 64335bb94f9f..ec3fc8d88e87 100644
--- a/samples/bpf/Makefile
+++ b/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)
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index d8749756352d..64c679d67109 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index bf2772566240..9c88f6e4156d 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -32,6 +32,10 @@
 #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
  * required to be defined explicitly.
@@ -436,6 +440,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	struct nlmsghdr *nh;
 	struct nlmsgerr *err;
 	socklen_t addrlen;
+	int one = 1;
 
 	memset(&sa, 0, sizeof(sa));
 	sa.nl_family = AF_NETLINK;
@@ -445,6 +450,11 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		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;
@@ -521,6 +531,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 			if (!err->error)
 				continue;
 			ret = err->error;
+			nla_dump_errormsg(nh);
 			goto cleanup;
 		case NLMSG_DONE:
 			break;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
new file mode 100644
index 000000000000..4719434278b2
--- /dev/null
+++ b/tools/lib/bpf/nlattr.c
@@ -0,0 +1,187 @@
+// 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;
+}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
new file mode 100644
index 000000000000..931a71f68f93
--- /dev/null
+++ b/tools/lib/bpf/nlattr.h
@@ -0,0 +1,72 @@
+/* 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 */
-- 
2.15.1

[PATCH bpf-next v8 4/5] libbpf: add missing SPDX-License-Identifier

[Eric Leblond]

Signed-off-by: Eric Leblond <eric@regit.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c    | 2 ++
 tools/lib/bpf/bpf.h    | 2 ++
 tools/lib/bpf/libbpf.c | 2 ++
 tools/lib/bpf/libbpf.h | 2 ++
 4 files changed, 8 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9c88f6e4156d..592a58a2b681 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9f44c196931e..8d18fb73d7fb 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c60122d3ea85..71ddc481f349 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * Common eBPF ELF object loading operations.
  *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e42f96900318..f85906533cdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
-- 
2.15.1

[PATCH bpf-next v8 5/5] samples/bpf: use bpf_set_link_xdp_fd

[Eric Leblond]

Use bpf_set_link_xdp_fd instead of set_link_xdp_fd to remove some
code duplication and benefit of netlink ext ack errors message.

Signed-off-by: Eric Leblond <eric@regit.org>
---
 samples/bpf/bpf_load.c              | 102 ------------------------------------
 samples/bpf/bpf_load.h              |   2 +-
 samples/bpf/xdp1_user.c             |   4 +-
 samples/bpf/xdp_redirect_cpu_user.c |   6 +--
 samples/bpf/xdp_redirect_map_user.c |   8 +--
 samples/bpf/xdp_redirect_user.c     |   8 +--
 samples/bpf/xdp_router_ipv4_user.c  |  10 ++--
 samples/bpf/xdp_rxq_info_user.c     |   4 +-
 samples/bpf/xdp_tx_iptunnel_user.c  |   6 +--
 9 files changed, 24 insertions(+), 126 deletions(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 242631aa4ea2..69806d74fa53 100644
--- a/samples/bpf/bpf_load.c
+++ b/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;
-}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 7d57a4248893..453c200b389b 100644
--- a/samples/bpf/bpf_load.h
+++ b/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
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index fdaefe91801d..b901ee2b3336 100644
--- a/samples/bpf/xdp1_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 35fec9fecb57..23744a8aaf21 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index 978a532f0748..7eae07d7293e 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c
index 4475d837bf2c..d54e91eb6cbf 100644
--- a/samples/bpf/xdp_redirect_user.c
+++ b/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;
diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c
index 916462112d55..6296741c1fbd 100644
--- a/samples/bpf/xdp_router_ipv4_user.c
+++ b/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;
 		}
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index 32430e8b3a6a..478d95412de4 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/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;
 	}
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 715cd12eaca5..f0a787268a87 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/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;
 }
-- 
2.15.1

Re: [PATCH bpf-next v8 0/5] libbpf: add XDP binding support

[Daniel Borkmann]

On 01/30/2018 09:50 PM, Eric Leblond wrote:
> Hello Daniel,
> 
> No problem with the delay in the answer. I'm doing far worse.
> 
> Here is an updated version:
> - add if_link.h in uapi and remove the definition
> - fix a commit message
> - remove uapi from a include

Fyi, this still needs to wait for a bit in the queue due to current
merge window where bpf-next is closed during that time [0]. Thanks!

  [0] https://www.spinics.net/lists/netdev/msg481490.html

Re: [PATCH bpf-next v8 0/5] libbpf: add XDP binding support

[Alexei Starovoitov]

On Wed, Jan 31, 2018 at 05:53:13PM +0100, Daniel Borkmann wrote:
> On 01/30/2018 09:50 PM, Eric Leblond wrote:
> > Hello Daniel,
> > 
> > No problem with the delay in the answer. I'm doing far worse.
> > 
> > Here is an updated version:
> > - add if_link.h in uapi and remove the definition
> > - fix a commit message
> > - remove uapi from a include
> 
> Fyi, this still needs to wait for a bit in the queue due to current
> merge window where bpf-next is closed during that time [0]. Thanks!
> 
>   [0] https://www.spinics.net/lists/netdev/msg481490.html

I've tested it and applied to bpf tree considering that
the series were practically ready long before bpf-next was closed.
Thank you Eric.
perf build was also fine, but please watch out for any unexpected
breakages, since perf has to be built on variety of distros.