iproute: extend route get for mpls routes

This patch extends route get to support mpls specific
route attributes like RTA_NEWDST.

Input:
RTA_DST - input label
RTA_NEWDST - labels in packet for multipath selection

By default the getroute handler returns matched
nexthop label, via and oif

With fibmatch keyword (RTM_F_FIB_MATCH flag), full matched
route is returned.

example:
$ip -f mpls route show
101
        nexthop as to 102/103 via inet 172.16.2.2 dev virt1-2
        nexthop as to 302/303 via inet 172.16.12.2 dev virt1-12
201
        nexthop as to 202/203 via inet6 2001:db8:2::2 dev virt1-2
        nexthop as to 402/403 via inet6 2001:db8:12::2 dev virt1-12

$ip -f mpls route get 103
RTNETLINK answers: Network is unreachable

$ip -f mpls route get 101
101 as to 102/103 via inet 172.16.2.2 dev virt1-2

$ip -f mpls route get as to 302/303 101
101 as to 302/303 via inet 172.16.12.2 dev virt1-12

$ip -f mpls route get fibmatch 103
RTNETLINK answers: Network is unreachable

$ip -f mpls route get fibmatch 101
101
        nexthop as to 102/103 via inet 172.16.2.2 dev virt1-2
        nexthop as to 302/303 via inet 172.16.12.2 dev virt1-12

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>

include/linux/bpf.h

@@ -120,12 +120,14 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_IN,
 	BPF_PROG_TYPE_LWT_OUT,
 	BPF_PROG_TYPE_LWT_XMIT,
+	BPF_PROG_TYPE_SOCK_OPS,
 };
 
 enum bpf_attach_type {
 	BPF_CGROUP_INET_INGRESS,
 	BPF_CGROUP_INET_EGRESS,
 	BPF_CGROUP_INET_SOCK_CREATE,
+	BPF_CGROUP_SOCK_OPS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -518,6 +520,25 @@ union bpf_attr {
  *     Set full skb->hash.
  *     @skb: pointer to skb
  *     @hash: hash to set
+ *
+ * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
+ *     Calls setsockopt. Not all opts are available, only those with
+ *     integer optvals plus TCP_CONGESTION.
+ *     Supported levels: SOL_SOCKET and IPROTO_TCP
+ *     @bpf_socket: pointer to bpf_socket
+ *     @level: SOL_SOCKET or IPROTO_TCP
+ *     @optname: option name
+ *     @optval: pointer to option value
+ *     @optlen: length of optval in byes
+ *     Return: 0 or negative error
+ *
+ * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
+ *     Grow or shrink room in sk_buff.
+ *     @skb: pointer to skb
+ *     @len_diff: (signed) amount of room to grow/shrink
+ *     @mode: operation mode (enum bpf_adj_room_mode)
+ *     @flags: reserved for future use
+ *     Return: 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -568,7 +589,9 @@ union bpf_attr {
 	FN(probe_read_str),		\
 	FN(get_socket_cookie),		\
 	FN(get_socket_uid),		\
-	FN(set_hash),
+	FN(set_hash),			\
+	FN(setsockopt),			\
+	FN(skb_adjust_room),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -618,6 +641,11 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
 
+/* Mode for BPF_FUNC_skb_adjust_room helper. */
+enum bpf_adj_room_mode {
+	BPF_ADJ_ROOM_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -720,4 +748,56 @@ struct bpf_map_info {
 	__u32 map_flags;
 } __attribute__((aligned(8)));
 
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+	__u32 op;
+	union {
+		__u32 reply;
+		__u32 replylong[4];
+	};
+	__u32 family;
+	__u32 remote_ip4;	/* Stored in network byte order */
+	__u32 local_ip4;	/* Stored in network byte order */
+	__u32 remote_ip6[4];	/* Stored in network byte order */
+	__u32 local_ip6[4];	/* Stored in network byte order */
+	__u32 remote_port;	/* Stored in network byte order */
+	__u32 local_port;	/* stored in host byte order */
+};
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+	BPF_SOCK_OPS_VOID,
+	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
+					 * -1 if default value should be used
+					 */
+	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
+					 * window (in packets) or -1 if default
+					 * value should be used
+					 */
+	BPF_SOCK_OPS_TCP_CONNECT_CB,	/* Calls BPF program right before an
+					 * active connection is initialized
+					 */
+	BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB,	/* Calls BPF program when an
+						 * active connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,	/* Calls BPF program when a
+						 * passive connection is
+						 * established
+						 */
+	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
+					 * needs ECN
+					 */
+};
+
+#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
+#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */
+
 #endif /* __LINUX_BPF_H__ */

include/linux/magic.h

@@ -42,6 +42,7 @@
 #define MSDOS_SUPER_MAGIC	0x4d44		/* MD */
 #define NCP_SUPER_MAGIC		0x564c		/* Guess, what 0x564c is :-) */
 #define NFS_SUPER_MAGIC		0x6969
+#define OCFS2_SUPER_MAGIC	0x7461636f
 #define OPENPROM_SUPER_MAGIC	0x9fa1
 #define QNX4_SUPER_MAGIC	0x002f		/* qnx4 fs detection */
 #define QNX6_SUPER_MAGIC	0x68191122	/* qnx6 fs detection */
@@ -80,6 +81,8 @@
 #define BTRFS_TEST_MAGIC	0x73727279
 #define NSFS_MAGIC		0x6e736673
 #define BPF_FS_MAGIC		0xcafe4a11
+#define AAFS_MAGIC		0x5a3c69f0
+
 /* Since UDF 2.01 is ISO 13346 based... */
 #define UDF_SUPER_MAGIC		0x15013346
 #define BALLOON_KVM_MAGIC	0x13661366

include/linux/sctp.h

@@ -121,6 +121,7 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_RESET_STREAMS	119
 #define SCTP_RESET_ASSOC	120
 #define SCTP_ADD_STREAMS	121
+#define SCTP_SOCKOPT_PEELOFF_FLAGS 122
 
 /* PR-SCTP policies */
 #define SCTP_PR_SCTP_NONE	0x0000
@@ -972,6 +973,11 @@ typedef struct {
 	int sd;
 } sctp_peeloff_arg_t;
 
+typedef struct {
+	sctp_peeloff_arg_t p_arg;
+	unsigned flags;
+} sctp_peeloff_flags_arg_t;
+
 /*
  *  Peer Address Thresholds socket option
  */

ip/ipaddress.c

@@ -18,7 +18,6 @@
 #include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/socket.h>
-#include <sys/ioctl.h>
 #include <sys/param.h>
 #include <errno.h>
 #include <netinet/in.h>
@@ -1013,14 +1012,67 @@ static unsigned int get_ifa_flags(struct ifaddrmsg *ifa,
 				ifa->ifa_flags;
 }
 
+
+static const char *ifa_flag_names[] = {
+	"secondary",
+	"nodad",
+	"optimistic",
+	"dadfailed",
+	"home",
+	"deprecated",
+	"tentative",
+	"permanent",
+	"mngtmpaddr",
+	"noprefixroute",
+	"autojoin",
+	"stable-privacy",
+};
+
+static void print_ifa_flags(FILE *fp, const struct ifaddrmsg *ifa, unsigned int flags)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(ifa_flag_names); i++) {
+		unsigned int mask = 1u << i;
+
+		if (mask == IFA_F_PERMANENT) {
+			if (!(flags & mask))
+				fprintf(fp, "dynamic ");
+		} else if (flags & mask) {
+			if (mask == IFA_F_SECONDARY) {
+				if (ifa->ifa_family == AF_INET6)
+					fprintf(fp, "temporary ");
+				else
+					fprintf(fp, "secondary ");
+			} else
+				fprintf(fp, "%s ", ifa_flag_names[i]);
+		}
+
+		flags &= ~mask;
+	}
+
+	if (flags)
+		fprintf(fp, "flags %02x ", flags);
+
+}
+
+static unsigned int get_ifa_flag_mask(const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(ifa_flag_names); i++) {
+		if (!strcmp(name, ifa_flag_names[i]))
+			return 1u << i;
+	}
+	return 0;
+}
+
 int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
 		   void *arg)
 {
 	FILE *fp = arg;
 	struct ifaddrmsg *ifa = NLMSG_DATA(n);
 	int len = n->nlmsg_len;
-	int deprecated = 0;
-	/* Use local copy of ifa_flags to not interfere with filtering code */
 	unsigned int ifa_flags;
 	struct rtattr *rta_tb[IFA_MAX+1];
 
@@ -1040,6 +1092,7 @@ int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
 	parse_rtattr(rta_tb, IFA_MAX, IFA_RTA(ifa),
 		     n->nlmsg_len - NLMSG_LENGTH(sizeof(*ifa)));
 
+
 	ifa_flags = get_ifa_flags(ifa, rta_tb[IFA_FLAGS]);
 
 	if (!rta_tb[IFA_LOCAL])
@@ -1145,52 +1198,9 @@ int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
 					      rta_tb[IFA_ANYCAST]));
 	}
 	fprintf(fp, "scope %s ", rtnl_rtscope_n2a(ifa->ifa_scope, b1, sizeof(b1)));
-	if (ifa_flags & IFA_F_SECONDARY) {
+
-		ifa_flags &= ~IFA_F_SECONDARY;
+	print_ifa_flags(fp, ifa, ifa_flags);
-		if (ifa->ifa_family == AF_INET6)
+
-			fprintf(fp, "temporary ");
-		else
-			fprintf(fp, "secondary ");
-	}
-	if (ifa_flags & IFA_F_TENTATIVE) {
-		ifa_flags &= ~IFA_F_TENTATIVE;
-		fprintf(fp, "tentative ");
-	}
-	if (ifa_flags & IFA_F_DEPRECATED) {
-		ifa_flags &= ~IFA_F_DEPRECATED;
-		deprecated = 1;
-		fprintf(fp, "deprecated ");
-	}
-	if (ifa_flags & IFA_F_HOMEADDRESS) {
-		ifa_flags &= ~IFA_F_HOMEADDRESS;
-		fprintf(fp, "home ");
-	}
-	if (ifa_flags & IFA_F_NODAD) {
-		ifa_flags &= ~IFA_F_NODAD;
-		fprintf(fp, "nodad ");
-	}
-	if (ifa_flags & IFA_F_MANAGETEMPADDR) {
-		ifa_flags &= ~IFA_F_MANAGETEMPADDR;
-		fprintf(fp, "mngtmpaddr ");
-	}
-	if (ifa_flags & IFA_F_NOPREFIXROUTE) {
-		ifa_flags &= ~IFA_F_NOPREFIXROUTE;
-		fprintf(fp, "noprefixroute ");
-	}
-	if (ifa_flags & IFA_F_MCAUTOJOIN) {
-		ifa_flags &= ~IFA_F_MCAUTOJOIN;
-		fprintf(fp, "autojoin ");
-	}
-	if (!(ifa_flags & IFA_F_PERMANENT))
-		fprintf(fp, "dynamic ");
-	else
-		ifa_flags &= ~IFA_F_PERMANENT;
-	if (ifa_flags & IFA_F_DADFAILED) {
-		ifa_flags &= ~IFA_F_DADFAILED;
-		fprintf(fp, "dadfailed ");
-	}
-	if (ifa_flags)
-		fprintf(fp, "flags %02x ", ifa_flags);
 	if (rta_tb[IFA_LABEL])
 		fprintf(fp, "%s", rta_getattr_str(rta_tb[IFA_LABEL]));
 	if (rta_tb[IFA_CACHEINFO]) {
@@ -1206,7 +1216,7 @@ int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
 		if (ci->ifa_prefered == INFINITY_LIFE_TIME)
 			fprintf(fp, "forever");
 		else {
-			if (deprecated)
+			if (ifa_flags & IFA_F_DEPRECATED)
 				fprintf(fp, "%dsec", ci->ifa_prefered);
 			else
 				fprintf(fp, "%usec", ci->ifa_prefered);
@@ -1570,6 +1580,7 @@ static int ipaddr_list_flush_or_save(int argc, char **argv, int action)
 	struct nlmsg_chain _ainfo = { NULL, NULL}, *ainfo = NULL;
 	struct nlmsg_list *l;
 	char *filter_dev = NULL;
+	unsigned int mask;
 	int no_link = 0;
 
 	ipaddr_reset_filter(oneline, 0);
@@ -1612,49 +1623,15 @@ static int ipaddr_list_flush_or_save(int argc, char **argv, int action)
 		} else if (strcmp(*argv, "dynamic") == 0) {
 			filter.flags &= ~IFA_F_PERMANENT;
 			filter.flagmask |= IFA_F_PERMANENT;
-		} else if (strcmp(*argv, "permanent") == 0) {
+		} else if (strcmp(*argv, "temporary") == 0) {
-			filter.flags |= IFA_F_PERMANENT;
-			filter.flagmask |= IFA_F_PERMANENT;
-		} else if (strcmp(*argv, "secondary") == 0 ||
-			   strcmp(*argv, "temporary") == 0) {
 			filter.flags |= IFA_F_SECONDARY;
 			filter.flagmask |= IFA_F_SECONDARY;
 		} else if (strcmp(*argv, "primary") == 0) {
 			filter.flags &= ~IFA_F_SECONDARY;
 			filter.flagmask |= IFA_F_SECONDARY;
-		} else if (strcmp(*argv, "tentative") == 0) {
+		} else if ((mask = get_ifa_flag_mask(*argv)) != 0) {
-			filter.flags |= IFA_F_TENTATIVE;
+			filter.flags |= mask;
-			filter.flagmask |= IFA_F_TENTATIVE;
+			filter.flagmask |= mask;
-		} else if (strcmp(*argv, "-tentative") == 0) {
-			filter.flags &= ~IFA_F_TENTATIVE;
-			filter.flagmask |= IFA_F_TENTATIVE;
-		} else if (strcmp(*argv, "deprecated") == 0) {
-			filter.flags |= IFA_F_DEPRECATED;
-			filter.flagmask |= IFA_F_DEPRECATED;
-		} else if (strcmp(*argv, "-deprecated") == 0) {
-			filter.flags &= ~IFA_F_DEPRECATED;
-			filter.flagmask |= IFA_F_DEPRECATED;
-		} else if (strcmp(*argv, "home") == 0) {
-			filter.flags |= IFA_F_HOMEADDRESS;
-			filter.flagmask |= IFA_F_HOMEADDRESS;
-		} else if (strcmp(*argv, "nodad") == 0) {
-			filter.flags |= IFA_F_NODAD;
-			filter.flagmask |= IFA_F_NODAD;
-		} else if (strcmp(*argv, "mngtmpaddr") == 0) {
-			filter.flags |= IFA_F_MANAGETEMPADDR;
-			filter.flagmask |= IFA_F_MANAGETEMPADDR;
-		} else if (strcmp(*argv, "noprefixroute") == 0) {
-			filter.flags |= IFA_F_NOPREFIXROUTE;
-			filter.flagmask |= IFA_F_NOPREFIXROUTE;
-		} else if (strcmp(*argv, "autojoin") == 0) {
-			filter.flags |= IFA_F_MCAUTOJOIN;
-			filter.flagmask |= IFA_F_MCAUTOJOIN;
-		} else if (strcmp(*argv, "dadfailed") == 0) {
-			filter.flags |= IFA_F_DADFAILED;
-			filter.flagmask |= IFA_F_DADFAILED;
-		} else if (strcmp(*argv, "-dadfailed") == 0) {
-			filter.flags &= ~IFA_F_DADFAILED;
-			filter.flagmask |= IFA_F_DADFAILED;
 		} else if (strcmp(*argv, "label") == 0) {
 			NEXT_ARG();
 			filter.label = *argv;

ip/iplink.c

@@ -26,7 +26,6 @@
 #include <arpa/inet.h>
 #include <string.h>
 #include <sys/ioctl.h>
-#include <linux/sockios.h>
 #include <stdbool.h>
 #include <linux/mpls.h>
 

ip/iproute.c

@@ -1731,6 +1731,16 @@ static int iproute_get(int argc, char **argv)
 			addattr32(&req.n, sizeof(req), RTA_UID, uid);
 		} else if (matches(*argv, "fibmatch") == 0) {
 			fib_match = 1;
+		} else if (strcmp(*argv, "as") == 0) {
+			inet_prefix addr;
+
+			NEXT_ARG();
+			if (strcmp(*argv, "to") == 0)
+				NEXT_ARG();
+			get_addr(&addr, *argv, req.r.rtm_family);
+			if (req.r.rtm_family == AF_UNSPEC)
+				req.r.rtm_family = addr.family;
+			addattr_l(&req.n, sizeof(req), RTA_NEWDST, &addr.data, addr.bytelen);
 		} else {
 			inet_prefix addr;
 

lib/ll_addr.c

@@ -16,7 +16,6 @@
 #include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/socket.h>
-#include <sys/ioctl.h>
 #include <netinet/in.h>
 #include <arpa/inet.h>
 #include <string.h>

lib/ll_proto.c

@@ -16,7 +16,6 @@
 #include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/socket.h>
-#include <sys/ioctl.h>
 #include <netinet/in.h>
 #include <arpa/inet.h>
 #include <string.h>

lib/ll_types.c

@@ -16,7 +16,6 @@
 #include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/socket.h>
-#include <sys/ioctl.h>
 #include <netinet/in.h>
 #include <arpa/inet.h>
 #include <string.h>

netem/paretonormal.c

@@ -11,7 +11,6 @@
  */
 #include <stdio.h>
 #include <stdlib.h>
-#include <stdlib.h>
 #include <string.h>
 #include <math.h>
 #include <limits.h>