Merge branch 'net-next'

bridge/br_common.h

@@ -16,4 +16,5 @@ extern int preferred_family;
 extern int show_stats;
 extern int show_details;
 extern int timestamp;
+extern int compress_vlans;
 extern struct rtnl_handle rth;

bridge/bridge.c

@@ -21,6 +21,7 @@ int resolve_hosts;
 int oneline = 0;
 int show_stats;
 int show_details;
+int compress_vlans;
 int timestamp;
 char * _SL_ = NULL;
 
@@ -32,7 +33,8 @@ static void usage(void)
 "Usage: bridge [ OPTIONS ] OBJECT { COMMAND | help }\n"
 "where  OBJECT := { link | fdb | mdb | vlan | monitor }\n"
 "       OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] |\n"
-"                    -o[neline] | -t[imestamp] | -n[etns] name }\n");
+"                    -o[neline] | -t[imestamp] | -n[etns] name |\n"
+"                    -c[ompressvlans] }\n");
 	exit(-1);
 }
 
@@ -117,6 +119,8 @@ main(int argc, char **argv)
 			NEXT_ARG();
 			if (netns_switch(argv[1]))
 				exit(-1);
+		} else if (matches(opt, "-compressvlans") == 0) {
+			++compress_vlans;
 		} else {
 			fprintf(stderr, "Option \"%s\" is unknown, try \"bridge help\".\n", opt);
 			exit(-1);

bridge/vlan.c

@@ -32,6 +32,7 @@ static int vlan_modify(int cmd, int argc, char **argv)
 	} req;
 	char *d = NULL;
 	short vid = -1;
+	short vid_end = -1;
 	struct rtattr *afspec;
 	struct bridge_vlan_info vinfo;
 	unsigned short flags = 0;
@@ -49,8 +50,18 @@ static int vlan_modify(int cmd, int argc, char **argv)
 			NEXT_ARG();
 			d = *argv;
 		} else if (strcmp(*argv, "vid") == 0) {
+			char *p;
 			NEXT_ARG();
+			p = strchr(*argv, '-');
+			if (p) {
+				*p = '\0';
+				p++;
 				vid = atoi(*argv);
+				vid_end = atoi(p);
+				vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN;
+			} else {
+				vid = atoi(*argv);
+			}
 		} else if (strcmp(*argv, "self") == 0) {
 			flags |= BRIDGE_FLAGS_SELF;
 		} else if (strcmp(*argv, "master") == 0) {
@@ -83,15 +94,40 @@ static int vlan_modify(int cmd, int argc, char **argv)
 		return -1;
 	}
 
-	vinfo.vid = vid;
+	if (vinfo.flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
+		if (vid_end == -1 || vid_end >= 4096 || vid >= vid_end) {
+			fprintf(stderr, "Invalid VLAN range \"%hu-%hu\"\n",
+				vid, vid_end);
+			return -1;
+		}
+		if (vinfo.flags & BRIDGE_VLAN_INFO_PVID) {
+			fprintf(stderr,
+				"pvid cannot be configured for a vlan range\n");
+			return -1;
+		}
+	}
 
 	afspec = addattr_nest(&req.n, sizeof(req), IFLA_AF_SPEC);
 
 	if (flags)
 		addattr16(&req.n, sizeof(req), IFLA_BRIDGE_FLAGS, flags);
 
+	vinfo.vid = vid;
+	if (vid_end != -1) {
+		/* send vlan range start */
 		addattr_l(&req.n, sizeof(req), IFLA_BRIDGE_VLAN_INFO, &vinfo,
 			  sizeof(vinfo));
+		vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN;
+
+		/* Now send the vlan range end */
+		vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_END;
+		vinfo.vid = vid_end;
+		addattr_l(&req.n, sizeof(req), IFLA_BRIDGE_VLAN_INFO, &vinfo,
+			  sizeof(vinfo));
+	} else {
+		addattr_l(&req.n, sizeof(req), IFLA_BRIDGE_VLAN_INFO, &vinfo,
+			  sizeof(vinfo));
+	}
 
 	addattr_nest_end(&req.n, afspec);
 
@@ -146,7 +182,12 @@ static int print_vlan(const struct sockaddr_nl *who,
 				continue;
 
 			vinfo = RTA_DATA(i);
+			if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END)
+				fprintf(fp, "-%hu", vinfo->vid);
+			else
 				fprintf(fp, "\t %hu", vinfo->vid);
+			if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN)
+				continue;
 			if (vinfo->flags & BRIDGE_VLAN_INFO_PVID)
 				fprintf(fp, " PVID");
 			if (vinfo->flags & BRIDGE_VLAN_INFO_UNTAGGED)
@@ -182,7 +223,9 @@ static int vlan_show(int argc, char **argv)
 	}
 
 	if (rtnl_wilddump_req_filter(&rth, PF_BRIDGE, RTM_GETLINK,
-				     RTEXT_FILTER_BRVLAN) < 0) {
+				    (compress_vlans ?
+				    RTEXT_FILTER_BRVLAN_COMPRESSED :
+				    RTEXT_FILTER_BRVLAN)) < 0) {
 		perror("Cannont send dump request");
 		exit(1);
 	}

include/linux/if_bridge.h

@@ -125,6 +125,8 @@ enum {
 #define BRIDGE_VLAN_INFO_MASTER	(1<<0)	/* Operate on Bridge device as well */
 #define BRIDGE_VLAN_INFO_PVID	(1<<1)	/* VLAN is PVID, ingress untagged */
 #define BRIDGE_VLAN_INFO_UNTAGGED	(1<<2)	/* VLAN egresses untagged */
+#define BRIDGE_VLAN_INFO_RANGE_BEGIN	(1<<3) /* VLAN is start of vlan range */
+#define BRIDGE_VLAN_INFO_RANGE_END	(1<<4) /* VLAN is end of vlan range */
 
 struct bridge_vlan_info {
 	__u16 flags;

include/linux/if_link.h

@@ -146,6 +146,7 @@ enum {
 	IFLA_PHYS_PORT_ID,
 	IFLA_CARRIER_CHANGES,
 	IFLA_PHYS_SWITCH_ID,
+	IFLA_LINK_NETNSID,
 	__IFLA_MAX
 };
 
@@ -368,6 +369,9 @@ enum {
 	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_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)

include/linux/l2tp.h

@@ -176,5 +176,6 @@ enum l2tp_seqmode {
  */
 #define L2TP_GENL_NAME		"l2tp"
 #define L2TP_GENL_VERSION	0x1
+#define L2TP_GENL_MCGROUP       "l2tp"
 
 #endif /* _LINUX_L2TP_H_ */

include/linux/libc-compat.h

@@ -70,6 +70,8 @@
 #define __UAPI_DEF_IPV6_MREQ		0
 #define __UAPI_DEF_IPPROTO_V6		0
 #define __UAPI_DEF_IPV6_OPTIONS		0
+#define __UAPI_DEF_IN6_PKTINFO		0
+#define __UAPI_DEF_IP6_MTUINFO		0
 
 #else
 
@@ -84,6 +86,8 @@
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
 #define __UAPI_DEF_IPV6_OPTIONS		1
+#define __UAPI_DEF_IN6_PKTINFO		1
+#define __UAPI_DEF_IP6_MTUINFO		1
 
 #endif /* _NETINET_IN_H */
 
@@ -106,6 +110,8 @@
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
 #define __UAPI_DEF_IPV6_OPTIONS		1
+#define __UAPI_DEF_IN6_PKTINFO		1
+#define __UAPI_DEF_IP6_MTUINFO		1
 
 /* Definitions for xattr.h */
 #define __UAPI_DEF_XATTR		1

include/linux/neighbour.h

@@ -25,6 +25,7 @@ enum {
 	NDA_VNI,
 	NDA_IFINDEX,
 	NDA_MASTER,
+	NDA_LINK_NETNSID,
 	__NDA_MAX
 };
 

include/linux/rtnetlink.h

@@ -132,6 +132,11 @@ enum {
 	RTM_GETMDB = 86,
 #define RTM_GETMDB RTM_GETMDB
 
+	RTM_NEWNSID = 88,
+#define RTM_NEWNSID RTM_NEWNSID
+	RTM_GETNSID = 90,
+#define RTM_GETNSID RTM_GETNSID
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
@@ -389,6 +394,8 @@ enum {
 #define RTAX_INITRWND RTAX_INITRWND
 	RTAX_QUICKACK,
 #define RTAX_QUICKACK RTAX_QUICKACK
+	RTAX_CC_ALGO,
+#define RTAX_CC_ALGO RTAX_CC_ALGO
 	__RTAX_MAX
 };
 
@@ -632,6 +639,7 @@ struct tcamsg {
 /* New extended info filters for IFLA_EXT_MASK */
 #define RTEXT_FILTER_VF		(1 << 0)
 #define RTEXT_FILTER_BRVLAN	(1 << 1)
+#define RTEXT_FILTER_BRVLAN_COMPRESSED	(1 << 2)
 
 /* End of information exported to user level */
 

include/linux/tc_act/tc_bpf.h

+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+	tc_gen;
+};
+
+enum {
+	TCA_ACT_BPF_UNSPEC,
+	TCA_ACT_BPF_TM,
+	TCA_ACT_BPF_PARMS,
+	TCA_ACT_BPF_OPS_LEN,
+	TCA_ACT_BPF_OPS,
+	__TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif

ip/iplink_vxlan.c

@@ -30,6 +30,7 @@ static void print_explain(FILE *f)
 	fprintf(f, "                 [ [no]l2miss ] [ [no]l3miss ]\n");
 	fprintf(f, "                 [ ageing SECONDS ] [ maxaddress NUMBER ]\n");
 	fprintf(f, "                 [ [no]udpcsum ] [ [no]udp6zerocsumtx ] [ [no]udp6zerocsumrx ]\n");
+	fprintf(f, "                 [ gbp ]\n");
 	fprintf(f, "\n");
 	fprintf(f, "Where: VNI := 0-16777215\n");
 	fprintf(f, "       ADDR := { IP_ADDRESS | any }\n");
@@ -68,6 +69,7 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 	__u8 udpcsum = 0;
 	__u8 udp6zerocsumtx = 0;
 	__u8 udp6zerocsumrx = 0;
+	__u8 gbp = 0;
 	int dst_port_set = 0;
 	struct ifla_vxlan_port_range range = { 0, 0 };
 
@@ -197,6 +199,8 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 			udp6zerocsumrx = 1;
 		} else if (!matches(*argv, "noudp6zerocsumrx")) {
 			udp6zerocsumrx = 0;
+		} else if (!matches(*argv, "gbp")) {
+			gbp = 1;
 		} else if (matches(*argv, "help") == 0) {
 			explain();
 			return -1;
@@ -268,6 +272,10 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
 	if (dstport)
 		addattr16(n, 1024, IFLA_VXLAN_PORT, htons(dstport));
 
+	if (gbp)
+		addattr_l(n, 1024, IFLA_VXLAN_GBP, NULL, 0);
+
+
 	return 0;
 }
 
@@ -398,6 +406,9 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
 	if (tb[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] &&
 	    rta_getattr_u8(tb[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		fputs("udp6zerocsumrx ", f);
+
+	if (tb[IFLA_VXLAN_GBP])
+		fputs("gbp ", f);
 }
 
 static void vxlan_print_help(struct link_util *lu, int argc, char **argv,

ip/iproute.c

@@ -53,6 +53,7 @@ static const char *mx_names[RTAX_MAX+1] = {
 	[RTAX_RTO_MIN]	= "rto_min",
 	[RTAX_INITRWND]	= "initrwnd",
 	[RTAX_QUICKACK]	= "quickack",
+	[RTAX_CC_ALGO]	= "congctl",
 };
 static void usage(void) __attribute__((noreturn));
 
@@ -80,8 +81,7 @@ static void usage(void)
 	fprintf(stderr, "           [ window NUMBER] [ cwnd NUMBER ] [ initcwnd NUMBER ]\n");
 	fprintf(stderr, "           [ ssthresh NUMBER ] [ realms REALM ] [ src ADDRESS ]\n");
 	fprintf(stderr, "           [ rto_min TIME ] [ hoplimit NUMBER ] [ initrwnd NUMBER ]\n");
-	fprintf(stderr, "           [ features FEATURES ]\n");
-	fprintf(stderr, "           [ quickack BOOL ]\n");
+	fprintf(stderr, "           [ features FEATURES ] [ quickack BOOL ] [ congctl NAME ]\n");
 	fprintf(stderr, "TYPE := [ unicast | local | broadcast | multicast | throw |\n");
 	fprintf(stderr, "          unreachable | prohibit | blackhole | nat ]\n");
 	fprintf(stderr, "TABLE_ID := [ local | main | default | all | NUMBER ]\n");
@@ -536,7 +536,7 @@ int print_route(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
 			mxlock = *(unsigned*)RTA_DATA(mxrta[RTAX_LOCK]);
 
 		for (i=2; i<= RTAX_MAX; i++) {
-			unsigned val;
+			__u32 val;
 
 			if (mxrta[i] == NULL)
 				continue;
@@ -545,10 +545,12 @@ int print_route(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
 				fprintf(fp, " %s", mx_names[i]);
 			else
 				fprintf(fp, " metric %d", i);
+
 			if (mxlock & (1<<i))
 				fprintf(fp, " lock");
+			if (i != RTAX_CC_ALGO)
+				val = rta_getattr_u32(mxrta[i]);
 
-			val = *(unsigned*)RTA_DATA(mxrta[i]);
 			switch (i) {
 			case RTAX_FEATURES:
 				print_rtax_features(fp, val);
@@ -573,6 +575,10 @@ int print_route(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
 					fprintf(fp, " %gs", val/1e3);
 				else
 					fprintf(fp, " %ums", val);
+				break;
+			case RTAX_CC_ALGO:
+				fprintf(fp, " %s", rta_getattr_str(mxrta[i]));
+				break;
 			}
 		}
 	}
@@ -925,6 +931,14 @@ static int iproute_modify(int cmd, unsigned flags, int argc, char **argv)
 			if (quickack != 1 && quickack != 0)
 				invarg("\"quickack\" value should be 0 or 1\n", *argv);
 			rta_addattr32(mxrta, sizeof(mxbuf), RTAX_QUICKACK, quickack);
+		} else if (matches(*argv, "congctl") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "lock") == 0) {
+				mxlock |= 1 << RTAX_CC_ALGO;
+				NEXT_ARG();
+			}
+			rta_addattr_l(mxrta, sizeof(mxbuf), RTAX_CC_ALGO, *argv,
+				      strlen(*argv));
 		} else if (matches(*argv, "rttvar") == 0) {
 			unsigned win;
 			NEXT_ARG();

man/man8/ip-link.8.in

@@ -276,6 +276,8 @@ the following additional arguments are supported:
 .BI ageing " SECONDS "
 .R " ] [ "
 .BI maxaddress " NUMBER "
+.R " ] [ "
+.B gbp
 .R " ]"
 
 .in +8
@@ -348,6 +350,49 @@ are entered into the VXLAN device forwarding database.
 .BI maxaddress " NUMBER"
 - specifies the maximum number of FDB entries.
 
+.sp
+.B gbp
+- enables the Group Policy extension (VXLAN-GBP).
+
+.in +4
+Allows to transport group policy context across VXLAN network peers.
+If enabled, includes the mark of a packet in the VXLAN header for outgoing
+packets and fills the packet mark based on the information found in the
+VXLAN header for incomming packets.
+
+Format of upper 16 bits of packet mark (flags);
+
+.in +2
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+.br
+|-|-|-|-|-|-|-|-|-|D|-|-|A|-|-|-|
+.br
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+.B D :=
+Don't Learn bit. When set, this bit indicates that the egress
+VTEP MUST NOT learn the source address of the encapsulated frame.
+
+.B A :=
+Indicates that the group policy has already been applied to
+this packet. Policies MUST NOT be applied by devices when the A bit is set.
+.in -2
+
+Format of lower 16 bits of packet mark (policy ID):
+
+.in +2
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+.br
+|        Group Policy ID        |
+.br
++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+.in -2
+
+Example:
+  iptables -A OUTPUT [...] -j MARK --set-mark 0x800FF
+
+.in -4
+
 .in -8
 
 .TP

man/man8/ip-route.8.in

@@ -116,7 +116,9 @@ replace " } "
 .B  features
 .IR FEATURES " ] [ "
 .B  quickack
-.IR BOOL " ]"
+.IR BOOL " ] [ "
+.B  congctl
+.IR NAME " ]"
 
 .ti -8
 .IR TYPE " := [ "
@@ -432,6 +434,21 @@ sysctl is set to 0.
 .BI quickack " BOOL " "(3.11+ only)"
 Enable or disable quick ack for connections to this destination.
 
+.TP
+.BI congctl " NAME " "(3.20+ only)"
+.TP
+.BI "congctl lock" " NAME " "(3.20+ only)"
+Sets a specific TCP congestion control algorithm only for a given destination.
+If not specified, Linux keeps the current global default TCP congestion control
+algorithm, or the one set from the application. If the modifier
+.B lock
+is not used, an application may nevertheless overwrite the suggested congestion
+control algorithm for that destination. If the modifier
+.B lock
+is used, then an application is not allowed to overwrite the specified congestion
+control algorithm for that destination, thus it will be enforced/guaranteed to
+use the proposed algorithm.
+
 .TP
 .BI advmss " NUMBER " "(2.3.15+ only)"
 the MSS ('Maximal Segment Size') to advertise to these

man/man8/ss.8

@@ -84,6 +84,9 @@ context of the creating process, however the context shown will reflect
 any policy role, type and/or range transition rules applied,
 and is therefore a useful reference.
 .TP
+.B \-N NSNAME, \-\-net=NSNAME
+Switch to the specified network namespace name.
+.TP
 .B \-b, \-\-bpf
 Show socket BPF filters (only administrators are allowed to get these information).
 .TP

misc/Makefile

@@ -10,6 +10,10 @@ ifeq ($(HAVE_SELINUX),y)
 	CFLAGS += $(shell pkg-config --cflags libselinux) -DHAVE_SELINUX
 endif
 
+ifeq ($(IP_CONFIG_SETNS),y)
+	CFLAGS += -DHAVE_SETNS
+endif
+
 all: $(TARGETS)
 
 ss: $(SSOBJ)

misc/ss.c

@@ -31,6 +31,7 @@
 #include "rt_names.h"
 #include "ll_map.h"
 #include "libnetlink.h"
+#include "namespace.h"
 #include "SNAPSHOT.h"
 
 #include <linux/tcp.h>
@@ -3246,6 +3247,7 @@ static void _usage(FILE *dest)
 "   -b, --bpf           show bpf filter socket information\n"
 "   -Z, --context       display process SELinux security contexts\n"
 "   -z, --contexts      display process and socket SELinux security contexts\n"
+"   -N, --net           switch to the specified network namespace name\n"
 "\n"
 "   -4, --ipv4          display only IP version 4 sockets\n"
 "   -6, --ipv6          display only IP version 6 sockets\n"
@@ -3345,6 +3347,7 @@ static const struct option long_opts[] = {
 	{ "help", 0, 0, 'h' },
 	{ "context", 0, 0, 'Z' },
 	{ "contexts", 0, 0, 'z' },
+	{ "net", 1, 0, 'N' },
 	{ 0 }
 
 };
@@ -3360,7 +3363,7 @@ int main(int argc, char *argv[])
 	struct filter dbs_filter = {};
 	int state_filter = 0;
 
-	while ((ch = getopt_long(argc, argv, "dhaletuwxnro460spbf:miA:D:F:vVzZ",
+	while ((ch = getopt_long(argc, argv, "dhaletuwxnro460spbf:miA:D:F:vVzZN:",
 				 long_opts, NULL)) != EOF) {
 		switch(ch) {
 		case 'n':
@@ -3532,6 +3535,10 @@ int main(int argc, char *argv[])
 			show_proc_ctx++;
 			user_ent_hash_build();
 			break;
+		case 'N':
+			if (netns_switch(optarg))
+				exit(1);
+			break;
 		case 'h':
 		case '?':
 			help();

tc/Makefile

 TCOBJ= tc.o tc_qdisc.o tc_class.o tc_filter.o tc_util.o \
-       tc_monitor.o m_police.o m_estimator.o m_action.o \
+       tc_monitor.o tc_bpf.o m_police.o m_estimator.o m_action.o \
        m_ematch.o emp_ematch.yacc.o emp_ematch.lex.o
 
 include ../Config
@@ -46,6 +46,7 @@ TCMODULES += m_skbedit.o
 TCMODULES += m_csum.o
 TCMODULES += m_simple.o
 TCMODULES += m_vlan.o
+TCMODULES += m_bpf.o
 TCMODULES += p_ip.o
 TCMODULES += p_icmp.o
 TCMODULES += p_tcp.o

tc/f_bpf.c

@@ -26,6 +26,7 @@
 
 #include "utils.h"
 #include "tc_util.h"
+#include "tc_bpf.h"
 
 static void explain(void)
 {
@@ -44,130 +45,6 @@ static void explain(void)
 	fprintf(stderr, "NOTE: CLASSID is parsed as hexadecimal input.\n");
 }
 
-static int bpf_parse_string(char *arg, bool from_file, __u16 *bpf_len,
-			    char **bpf_string, bool *need_release,
-			    const char separator)
-{
-	char sp;
-
-	if (from_file) {
-		size_t tmp_len, op_len = sizeof("65535 255 255 4294967295,");
-		char *tmp_string;
-		FILE *fp;
-
-		tmp_len = sizeof("4096,") + BPF_MAXINSNS * op_len;
-		tmp_string = malloc(tmp_len);
-		if (tmp_string == NULL)
-			return -ENOMEM;
-
-		memset(tmp_string, 0, tmp_len);
-
-		fp = fopen(arg, "r");
-		if (fp == NULL) {
-			perror("Cannot fopen");
-			free(tmp_string);
-			return -ENOENT;
-		}
-
-		if (!fgets(tmp_string, tmp_len, fp)) {
-			free(tmp_string);
-			fclose(fp);
-			return -EIO;
-		}
-
-		fclose(fp);
-
-		*need_release = true;
-		*bpf_string = tmp_string;
-	} else {
-		*need_release = false;
-		*bpf_string = arg;
-	}
-
-	if (sscanf(*bpf_string, "%hu%c", bpf_len, &sp) != 2 ||
-	    sp != separator) {
-		if (*need_release)
-			free(*bpf_string);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int bpf_parse_ops(int argc, char **argv, struct nlmsghdr *n,
-			 bool from_file)
-{
-	char *bpf_string, *token, separator = ',';
-	struct sock_filter bpf_ops[BPF_MAXINSNS];
-	int ret = 0, i = 0;
-	bool need_release;
-	__u16 bpf_len = 0;
-
-	if (argc < 1)
-		return -EINVAL;
-	if (bpf_parse_string(argv[0], from_file, &bpf_len, &bpf_string,
-			     &need_release, separator))
-		return -EINVAL;
-	if (bpf_len == 0 || bpf_len > BPF_MAXINSNS) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	token = bpf_string;
-	while ((token = strchr(token, separator)) && (++token)[0]) {
-		if (i >= bpf_len) {
-			fprintf(stderr, "Real program length exceeds encoded "
-				"length parameter!\n");
-			ret = -EINVAL;
-			goto out;
-		}
-
-		if (sscanf(token, "%hu %hhu %hhu %u,",
-			   &bpf_ops[i].code, &bpf_ops[i].jt,
-			   &bpf_ops[i].jf, &bpf_ops[i].k) != 4) {
-			fprintf(stderr, "Error at instruction %d!\n", i);
-			ret = -EINVAL;
-			goto out;
-		}
-
-		i++;
-	}
-
-	if (i != bpf_len) {
-		fprintf(stderr, "Parsed program length is less than encoded"
-			"length parameter!\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	addattr_l(n, MAX_MSG, TCA_BPF_OPS_LEN, &bpf_len, sizeof(bpf_len));
-	addattr_l(n, MAX_MSG, TCA_BPF_OPS, &bpf_ops,
-		  bpf_len * sizeof(struct sock_filter));
-out:
-	if (need_release)
-		free(bpf_string);
-
-	return ret;
-}
-
-static void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len)
-{
-	struct sock_filter *ops = (struct sock_filter *) RTA_DATA(bpf_ops);
-	int i;
-
-	if (len == 0)
-		return;
-
-	fprintf(f, "bytecode \'%u,", len);
-
-	for (i = 0; i < len - 1; i++)
-		fprintf(f, "%hu %hhu %hhu %u,", ops[i].code, ops[i].jt,
-			ops[i].jf, ops[i].k);
-
-	fprintf(f, "%hu %hhu %hhu %u\'\n", ops[i].code, ops[i].jt,
-		ops[i].jf, ops[i].k);
-}
-
 static int bpf_parse_opt(struct filter_util *qu, char *handle,
 			 int argc, char **argv, struct nlmsghdr *n)
 {
@@ -195,6 +72,10 @@ static int bpf_parse_opt(struct filter_util *qu, char *handle,
 	while (argc > 0) {
 		if (matches(*argv, "run") == 0) {
 			bool from_file;
+			struct sock_filter bpf_ops[BPF_MAXINSNS];
+			__u16 bpf_len;
+			int ret;
+
 			NEXT_ARG();
 			if (strcmp(*argv, "bytecode-file") == 0) {
 				from_file = true;
@@ -206,10 +87,15 @@ static int bpf_parse_opt(struct filter_util *qu, char *handle,
 				return -1;
 			}
 			NEXT_ARG();
-			if (bpf_parse_ops(argc, argv, n, from_file)) {
+			ret = bpf_parse_ops(argc, argv, bpf_ops, from_file);
+			if (ret < 0) {
 				fprintf(stderr, "Illegal \"bytecode\"\n");
 				return -1;
 			}
+			bpf_len = ret;
+			addattr16(n, MAX_MSG, TCA_BPF_OPS_LEN, bpf_len);
+			addattr_l(n, MAX_MSG, TCA_BPF_OPS, &bpf_ops,
+				  bpf_len * sizeof(struct sock_filter));
 		} else if (matches(*argv, "classid") == 0 ||
 			   strcmp(*argv, "flowid") == 0) {
 			unsigned handle;

tc/m_bpf.c

+/*
+ * m_bpf.c	BFP based action module
+ *
+ *              This program is free software; you can redistribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ *
+ * Authors:     Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+#include <linux/tc_act/tc_bpf.h>
+
+#include "utils.h"
+#include "rt_names.h"
+#include "tc_util.h"
+#include "tc_bpf.h"
+
+static void explain(void)
+{
+	fprintf(stderr, "Usage: ... bpf ...\n");
+	fprintf(stderr, "\n");
+	fprintf(stderr, " [inline]:     run bytecode BPF_BYTECODE\n");
+	fprintf(stderr, " [from file]:  run bytecode-file FILE\n");
+	fprintf(stderr, "\n");
+	fprintf(stderr, "Where BPF_BYTECODE := \'s,c t f k,c t f k,c t f k,...\'\n");
+	fprintf(stderr, "      c,t,f,k and s are decimals; s denotes number of 4-tuples\n");
+	fprintf(stderr, "Where FILE points to a file containing the BPF_BYTECODE string\n");
+	fprintf(stderr, "\nACTION_SPEC := ... look at individual actions\n");
+	fprintf(stderr, "NOTE: CLASSID is parsed as hexadecimal input.\n");
+}
+
+static void usage(void)
+{
+	explain();
+	exit(-1);
+}
+
+static int parse_bpf(struct action_util *a, int *argc_p, char ***argv_p,
+		     int tca_id, struct nlmsghdr *n)
+{
+	int argc = *argc_p;
+	char **argv = *argv_p;
+	struct rtattr *tail;
+	struct tc_act_bpf parm = { 0 };
+	struct sock_filter bpf_ops[BPF_MAXINSNS];
+	__u16 bpf_len = 0;
+
+	if (matches(*argv, "bpf") != 0)
+		return -1;
+
+	NEXT_ARG();
+
+	while (argc > 0) {
+		if (matches(*argv, "run") == 0) {
+			bool from_file;
+			int ret;
+
+			NEXT_ARG();
+			if (strcmp(*argv, "bytecode-file") == 0) {
+				from_file = true;
+			} else if (strcmp(*argv, "bytecode") == 0) {
+				from_file = false;
+			} else {
+				fprintf(stderr, "unexpected \"%s\"\n", *argv);
+				explain();
+				return -1;
+			}
+			NEXT_ARG();
+			ret = bpf_parse_ops(argc, argv, bpf_ops, from_file);
+			if (ret < 0) {
+				fprintf(stderr, "Illegal \"bytecode\"\n");
+				return -1;
+			}
+			bpf_len = ret;
+		} else if (matches(*argv, "help") == 0) {
+			usage();
+		} else {
+			break;
+		}
+		argc--;
+		argv++;
+	}
+
+	parm.action = TC_ACT_PIPE;
+	if (argc) {
+		if (matches(*argv, "reclassify") == 0) {
+			parm.action = TC_ACT_RECLASSIFY;
+			NEXT_ARG();
+		} else if (matches(*argv, "pipe") == 0) {
+			parm.action = TC_ACT_PIPE;
+			NEXT_ARG();
+		} else if (matches(*argv, "drop") == 0 ||
+			   matches(*argv, "shot") == 0) {
+			parm.action = TC_ACT_SHOT;
+			NEXT_ARG();
+		} else if (matches(*argv, "continue") == 0) {
+			parm.action = TC_ACT_UNSPEC;
+			NEXT_ARG();
+		} else if (matches(*argv, "pass") == 0) {
+			parm.action = TC_ACT_OK;
+			NEXT_ARG();
+		}
+	}
+
+	if (argc) {
+		if (matches(*argv, "index") == 0) {
+			NEXT_ARG();
+			if (get_u32(&parm.index, *argv, 10)) {
+				fprintf(stderr, "bpf: Illegal \"index\"\n");
+				return -1;
+			}
+			argc--;
+			argv++;
+		}
+	}
+
+	if (!bpf_len) {
+		fprintf(stderr, "bpf: Bytecode needs to be passed\n");
+		explain();
+		return -1;
+	}
+
+	tail = NLMSG_TAIL(n);
+	addattr_l(n, MAX_MSG, tca_id, NULL, 0);
+	addattr_l(n, MAX_MSG, TCA_ACT_BPF_PARMS, &parm, sizeof(parm));
+	addattr16(n, MAX_MSG, TCA_ACT_BPF_OPS_LEN, bpf_len);
+	addattr_l(n, MAX_MSG, TCA_ACT_BPF_OPS, &bpf_ops,
+		  bpf_len * sizeof(struct sock_filter));
+	tail->rta_len = (char *)NLMSG_TAIL(n) - (char *)tail;
+
+	*argc_p = argc;
+	*argv_p = argv;
+	return 0;
+}
+
+static int print_bpf(struct action_util *au, FILE *f, struct rtattr *arg)
+{
+	struct rtattr *tb[TCA_ACT_BPF_MAX + 1];
+	struct tc_act_bpf *parm;
+
+	if (arg == NULL)
+		return -1;
+
+	parse_rtattr_nested(tb, TCA_ACT_BPF_MAX, arg);
+
+	if (!tb[TCA_ACT_BPF_PARMS]) {
+		fprintf(f, "[NULL bpf parameters]");
+		return -1;
+	}
+	parm = RTA_DATA(tb[TCA_ACT_BPF_PARMS]);
+
+	fprintf(f, " bpf ");
+
+	if (tb[TCA_ACT_BPF_OPS] && tb[TCA_ACT_BPF_OPS_LEN])
+		bpf_print_ops(f, tb[TCA_ACT_BPF_OPS],
+			      rta_getattr_u16(tb[TCA_ACT_BPF_OPS_LEN]));
+
+	fprintf(f, "\n\tindex %d ref %d bind %d", parm->index, parm->refcnt,
+		parm->bindcnt);
+
+	if (show_stats) {
+		if (tb[TCA_ACT_BPF_TM]) {
+			struct tcf_t *tm = RTA_DATA(tb[TCA_ACT_BPF_TM]);
+			print_tm(f, tm);
+		}
+	}
+
+	fprintf(f, "\n ");
+
+	return 0;
+}
+
+struct action_util bpf_action_util = {
+	.id = "bpf",
+	.parse_aopt = parse_bpf,
+	.print_aopt = print_bpf,
+};

tc/tc_bpf.c

+/*
+ * tc_bpf.c	BPF common code
+ *
+ *		This program is free software; you can distribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Daniel Borkmann <dborkman@redhat.com>
+ *		Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <linux/filter.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
+#include "utils.h"
+#include "tc_util.h"
+#include "tc_bpf.h"
+
+int bpf_parse_string(char *arg, bool from_file, __u16 *bpf_len,
+		     char **bpf_string, bool *need_release,
+		     const char separator)
+{
+	char sp;
+
+	if (from_file) {
+		size_t tmp_len, op_len = sizeof("65535 255 255 4294967295,");
+		char *tmp_string;
+		FILE *fp;
+
+		tmp_len = sizeof("4096,") + BPF_MAXINSNS * op_len;
+		tmp_string = malloc(tmp_len);
+		if (tmp_string == NULL)
+			return -ENOMEM;
+
+		memset(tmp_string, 0, tmp_len);
+
+		fp = fopen(arg, "r");
+		if (fp == NULL) {
+			perror("Cannot fopen");
+			free(tmp_string);
+			return -ENOENT;
+		}
+
+		if (!fgets(tmp_string, tmp_len, fp)) {
+			free(tmp_string);
+			fclose(fp);
+			return -EIO;
+		}
+
+		fclose(fp);
+
+		*need_release = true;
+		*bpf_string = tmp_string;
+	} else {
+		*need_release = false;
+		*bpf_string = arg;
+	}
+
+	if (sscanf(*bpf_string, "%hu%c", bpf_len, &sp) != 2 ||
+	    sp != separator) {
+		if (*need_release)
+			free(*bpf_string);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int bpf_parse_ops(int argc, char **argv, struct sock_filter *bpf_ops,
+		  bool from_file)
+{
+	char *bpf_string, *token, separator = ',';
+	int ret = 0, i = 0;
+	bool need_release;
+	__u16 bpf_len = 0;
+
+	if (argc < 1)
+		return -EINVAL;
+	if (bpf_parse_string(argv[0], from_file, &bpf_len, &bpf_string,
+			     &need_release, separator))
+		return -EINVAL;
+	if (bpf_len == 0 || bpf_len > BPF_MAXINSNS) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	token = bpf_string;
+	while ((token = strchr(token, separator)) && (++token)[0]) {
+		if (i >= bpf_len) {
+			fprintf(stderr, "Real program length exceeds encoded "
+				"length parameter!\n");
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if (sscanf(token, "%hu %hhu %hhu %u,",
+			   &bpf_ops[i].code, &bpf_ops[i].jt,
+			   &bpf_ops[i].jf, &bpf_ops[i].k) != 4) {
+			fprintf(stderr, "Error at instruction %d!\n", i);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		i++;
+	}
+
+	if (i != bpf_len) {
+		fprintf(stderr, "Parsed program length is less than encoded"
+			"length parameter!\n");
+		ret = -EINVAL;
+		goto out;
+	}
+	ret = bpf_len;
+
+out:
+	if (need_release)
+		free(bpf_string);
+
+	return ret;
+}
+
+void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len)
+{
+	struct sock_filter *ops = (struct sock_filter *) RTA_DATA(bpf_ops);
+	int i;
+
+	if (len == 0)
+		return;
+
+	fprintf(f, "bytecode \'%u,", len);
+
+	for (i = 0; i < len - 1; i++)
+		fprintf(f, "%hu %hhu %hhu %u,", ops[i].code, ops[i].jt,
+			ops[i].jf, ops[i].k);
+
+	fprintf(f, "%hu %hhu %hhu %u\'\n", ops[i].code, ops[i].jt,
+		ops[i].jf, ops[i].k);
+}

tc/tc_bpf.h

+/*
+ * tc_bpf.h	BPF common code
+ *
+ *		This program is free software; you can distribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Daniel Borkmann <dborkman@redhat.com>
+ *		Jiri Pirko <jiri@resnulli.us>
+ */
+
+#ifndef _TC_BPF_H_
+#define _TC_BPF_H_ 1
+
+#include <stdio.h>
+#include <linux/filter.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
+int bpf_parse_string(char *arg, bool from_file, __u16 *bpf_len,
+		     char **bpf_string, bool *need_release,
+		     const char separator);
+int bpf_parse_ops(int argc, char **argv, struct sock_filter *bpf_ops,
+		  bool from_file);
+void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len);
+
+#endif