ss: allow to retrieve AF_PACKET info via netlink

This patch add support of netlink messages for AF_PACKET and thus it allows
to get filter information of this kind of sockets.
To dump these filters info the option --bfp must be specified and the user
must have admin rights.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>

misc/ss.c

@@ -36,6 +36,9 @@
 #include <linux/sock_diag.h>
 #include <linux/inet_diag.h>
 #include <linux/unix_diag.h>
+#include <linux/netdevice.h>	/* for MAX_ADDR_LEN */
+#include <linux/filter.h>
+#include <linux/packet_diag.h>
 
 int resolve_hosts = 0;
 int resolve_services = 1;
@@ -45,6 +48,7 @@ int show_details = 0;
 int show_users = 0;
 int show_mem = 0;
 int show_tcpinfo = 0;
+int show_bpf = 0;
 
 int netid_width;
 int state_width;
@@ -2389,6 +2393,181 @@ static int unix_show(struct filter *f)
 	return 0;
 }
 
+static int packet_show_sock(struct nlmsghdr *nlh, struct filter *f)
+{
+	struct packet_diag_msg *r = NLMSG_DATA(nlh);
+	struct rtattr *tb[PACKET_DIAG_MAX+1];
+	__u32 rq;
+
+	parse_rtattr(tb, PACKET_DIAG_MAX, (struct rtattr*)(r+1),
+		     nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+	/* use /proc/net/packet if all info are not available */
+	if (!tb[PACKET_DIAG_MEMINFO])
+		return -1;
+
+	if (netid_width)
+		printf("%-*s ", netid_width,
+				r->pdiag_type == SOCK_RAW ? "p_raw" : "p_dgr");
+	if (state_width)
+		printf("%-*s ", state_width, "UNCONN");
+
+	if (tb[PACKET_DIAG_MEMINFO]) {
+		__u32 *skmeminfo = RTA_DATA(tb[PACKET_DIAG_MEMINFO]);
+
+		rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+	} else
+		rq = 0;
+	printf("%-6d %-6d ", rq, 0);
+
+	if (r->pdiag_num == 3) {
+		printf("%*s:", addr_width, "*");
+	} else {
+		char tb2[16];
+		printf("%*s:", addr_width,
+		       ll_proto_n2a(htons(r->pdiag_num), tb2, sizeof(tb2)));
+	}
+	if (tb[PACKET_DIAG_INFO]) {
+		struct packet_diag_info *pinfo = RTA_DATA(tb[PACKET_DIAG_INFO]);
+
+		if (pinfo->pdi_index == 0)
+			printf("%-*s ", serv_width, "*");
+		else
+			printf("%-*s ", serv_width, xll_index_to_name(pinfo->pdi_index));
+	} else
+		printf("%-*s ", serv_width, "*");
+
+	printf("%*s*%-*s",
+	       addr_width, "", serv_width, "");
+
+	if (show_users) {
+		char ubuf[4096];
+		if (find_users(r->pdiag_ino, ubuf, sizeof(ubuf)) > 0)
+			printf(" users:(%s)", ubuf);
+	}
+	if (show_details) {
+		__u32 uid = 0;
+
+		if (tb[PACKET_DIAG_UID])
+			uid = *(__u32 *)RTA_DATA(tb[PACKET_DIAG_UID]);
+
+		printf(" ino=%u uid=%u sk=", r->pdiag_ino, uid);
+		if (r->pdiag_cookie[1] != 0)
+			printf("%08x", r->pdiag_cookie[1]);
+		printf("%08x", r->pdiag_cookie[0]);
+	}
+
+	if (show_bpf && tb[PACKET_DIAG_FILTER]) {
+		struct sock_filter *fil =
+		       RTA_DATA(tb[PACKET_DIAG_FILTER]);
+		int num = RTA_PAYLOAD(tb[PACKET_DIAG_FILTER]) /
+			  sizeof(struct sock_filter);
+
+		printf("\n\tbpf filter (%d): ", num);
+		while (num) {
+			printf(" 0x%02x %u %u %u,",
+			      fil->code, fil->jt, fil->jf, fil->k);
+			num--;
+			fil++;
+		}
+	}
+	printf("\n");
+	return 0;
+}
+
+static int packet_show_netlink(struct filter *f, FILE *dump_fp)
+{
+	int fd;
+	struct {
+		struct nlmsghdr nlh;
+		struct packet_diag_req r;
+	} req;
+	char	buf[8192];
+
+	if ((fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_INET_DIAG)) < 0)
+		return -1;
+
+	memset(&req, 0, sizeof(req));
+	req.nlh.nlmsg_len = sizeof(req);
+	req.nlh.nlmsg_type = SOCK_DIAG_BY_FAMILY;
+	req.nlh.nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
+	req.nlh.nlmsg_seq = 123456;
+
+	req.r.sdiag_family = AF_PACKET;
+	req.r.pdiag_show = PACKET_SHOW_INFO | PACKET_SHOW_MEMINFO | PACKET_SHOW_FILTER;
+
+	if (send(fd, &req, sizeof(req), 0) < 0) {
+		close(fd);
+		return -1;
+	}
+
+	while (1) {
+		ssize_t status;
+		struct nlmsghdr *h;
+		struct sockaddr_nl nladdr;
+		socklen_t slen = sizeof(nladdr);
+
+		status = recvfrom(fd, buf, sizeof(buf), 0,
+				  (struct sockaddr *) &nladdr, &slen);
+		if (status < 0) {
+			if (errno == EINTR)
+				continue;
+			perror("OVERRUN");
+			continue;
+		}
+		if (status == 0) {
+			fprintf(stderr, "EOF on netlink\n");
+			goto close_it;
+		}
+
+		if (dump_fp)
+			fwrite(buf, 1, NLMSG_ALIGN(status), dump_fp);
+
+		h = (struct nlmsghdr*)buf;
+		while (NLMSG_OK(h, status)) {
+			int err;
+
+			if (h->nlmsg_seq != 123456)
+				goto skip_it;
+
+			if (h->nlmsg_type == NLMSG_DONE)
+				goto close_it;
+
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				struct nlmsgerr *err = (struct nlmsgerr*)NLMSG_DATA(h);
+				if (h->nlmsg_len < NLMSG_LENGTH(sizeof(struct nlmsgerr))) {
+					fprintf(stderr, "ERROR truncated\n");
+				} else {
+					errno = -err->error;
+					if (errno != ENOENT)
+						fprintf(stderr, "UDIAG answers %d\n", errno);
+				}
+				close(fd);
+				return -1;
+			}
+			if (!dump_fp) {
+				err = packet_show_sock(h, f);
+				if (err < 0) {
+					close(fd);
+					return err;
+				}
+			}
+
+skip_it:
+			h = NLMSG_NEXT(h, status);
+		}
+
+		if (status) {
+			fprintf(stderr, "!!!Remnant of size %zd\n", status);
+			exit(1);
+		}
+	}
+
+close_it:
+	close(fd);
+	return 0;
+}
+
 
 static int packet_show(struct filter *f)
 {
@@ -2406,6 +2585,9 @@ static int packet_show(struct filter *f)
 	if (!(f->states & (1<<SS_CLOSE)))
 		return 0;
 
+	if (packet_show_netlink(f, NULL) == 0)
+		return 0;
+
 	if ((fp = net_packet_open()) == NULL)
 		return -1;
 	fgets(buf, sizeof(buf)-1, fp);
@@ -2730,6 +2912,7 @@ static void _usage(FILE *dest)
 "   -p, --processes	show process using socket\n"
 "   -i, --info		show internal TCP information\n"
 "   -s, --summary	show socket usage summary\n"
+"   -b, --bfp           show bpf filter socket information\n"
 "\n"
 "   -4, --ipv4          display only IP version 4 sockets\n"
 "   -6, --ipv6          display only IP version 6 sockets\n"
@@ -2800,6 +2983,7 @@ static const struct option long_opts[] = {
 	{ "memory", 0, 0, 'm' },
 	{ "info", 0, 0, 'i' },
 	{ "processes", 0, 0, 'p' },
+	{ "bpf", 0, 0, 'b' },
 	{ "dccp", 0, 0, 'd' },
 	{ "tcp", 0, 0, 't' },
 	{ "udp", 0, 0, 'u' },
@@ -2836,7 +3020,7 @@ int main(int argc, char *argv[])
 
 	current_filter.states = default_filter.states;
 
-	while ((ch = getopt_long(argc, argv, "dhaletuwxnro460spf:miA:D:F:vV",
+	while ((ch = getopt_long(argc, argv, "dhaletuwxnro460spbf:miA:D:F:vV",
 				 long_opts, NULL)) != EOF) {
 		switch(ch) {
 		case 'n':
@@ -2862,6 +3046,10 @@ int main(int argc, char *argv[])
 			show_users++;
 			user_ent_hash_build();
 			break;
+		case 'b':
+			show_options = 1;
+			show_bpf++;
+			break;
 		case 'd':
 			current_filter.dbs |= (1<<DCCP_DB);
 			do_default = 0;