summaryrefslogtreecommitdiffstats
path: root/misc
diff options
context:
space:
mode:
Diffstat (limited to 'misc')
-rw-r--r--misc/.gitignore7
-rw-r--r--misc/Makefile42
-rw-r--r--misc/arpd.c833
-rw-r--r--misc/ifstat.c1040
-rw-r--r--misc/lnstat.c379
-rw-r--r--misc/lnstat.h43
-rw-r--r--misc/lnstat_util.c325
-rw-r--r--misc/nstat.c776
-rw-r--r--misc/rtacct.c622
-rw-r--r--misc/ss.c5887
-rw-r--r--misc/ss_util.h23
-rw-r--r--misc/ssfilter.h34
-rw-r--r--misc/ssfilter.y369
-rw-r--r--misc/ssfilter_check.c104
14 files changed, 10484 insertions, 0 deletions
diff --git a/misc/.gitignore b/misc/.gitignore
new file mode 100644
index 0000000..d7df0b0
--- /dev/null
+++ b/misc/.gitignore
@@ -0,0 +1,7 @@
+arpd
+ifstat
+ss
+ssfilter.tab.c
+nstat
+lnstat
+rtacct
diff --git a/misc/Makefile b/misc/Makefile
new file mode 100644
index 0000000..50dae79
--- /dev/null
+++ b/misc/Makefile
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+SSOBJ=ss.o ssfilter_check.o ssfilter.tab.o
+LNSTATOBJ=lnstat.o lnstat_util.o
+
+TARGETS=ss nstat ifstat rtacct lnstat
+
+include ../config.mk
+
+ifeq ($(HAVE_BERKELEY_DB),y)
+ TARGETS += arpd
+endif
+
+all: $(TARGETS)
+
+ss: $(SSOBJ)
+ $(QUIET_LINK)$(CC) $^ $(LDFLAGS) $(LDLIBS) -o $@
+
+nstat: nstat.c
+ $(QUIET_CC)$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) -o nstat nstat.c $(LDLIBS) -lm
+
+ifstat: ifstat.c
+ $(QUIET_CC)$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) -o ifstat ifstat.c $(LDLIBS) -lm
+
+rtacct: rtacct.c
+ $(QUIET_CC)$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) -o rtacct rtacct.c $(LDLIBS) -lm
+
+arpd: arpd.c
+ $(QUIET_CC)$(CC) $(CFLAGS) -I$(DBM_INCLUDE) $(CPPFLAGS) $(LDFLAGS) -o arpd arpd.c $(LDLIBS) -ldb
+
+ssfilter.tab.c: ssfilter.y
+ $(QUIET_YACC)$(YACC) -b ssfilter ssfilter.y
+
+lnstat: $(LNSTATOBJ)
+ $(QUIET_LINK)$(CC) $^ $(LDFLAGS) $(LDLIBS) -o $@
+
+install: all
+ install -m 0755 $(TARGETS) $(DESTDIR)$(SBINDIR)
+ ln -sf lnstat $(DESTDIR)$(SBINDIR)/rtstat
+ ln -sf lnstat $(DESTDIR)$(SBINDIR)/ctstat
+
+clean:
+ rm -f *.o $(TARGETS) ssfilter.c
diff --git a/misc/arpd.c b/misc/arpd.c
new file mode 100644
index 0000000..1ef837c
--- /dev/null
+++ b/misc/arpd.c
@@ -0,0 +1,833 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * arpd.c ARP helper daemon.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <syslog.h>
+#include <malloc.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <netdb.h>
+#include <db_185.h>
+#include <sys/ioctl.h>
+#include <sys/poll.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/uio.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <time.h>
+#include <signal.h>
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_arp.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <linux/if_packet.h>
+#include <linux/filter.h>
+
+#include "libnetlink.h"
+#include "utils.h"
+#include "rt_names.h"
+
+DB *dbase;
+char *dbname = "/var/lib/arpd/arpd.db";
+
+int ifnum;
+int *ifvec;
+char **ifnames;
+
+struct dbkey {
+ __u32 iface;
+ __u32 addr;
+};
+
+#define IS_NEG(x) (((__u8 *)(x))[0] == 0xFF)
+#define NEG_TIME(x) (((x)[2]<<24)|((x)[3]<<16)|((x)[4]<<8)|(x)[5])
+#define NEG_AGE(x) ((__u32)time(NULL) - NEG_TIME((__u8 *)x))
+#define NEG_VALID(x) (NEG_AGE(x) < negative_timeout)
+#define NEG_CNT(x) (((__u8 *)(x))[1])
+
+struct rtnl_handle rth;
+
+struct pollfd pset[2];
+int udp_sock = -1;
+
+volatile int do_exit;
+volatile int do_sync;
+volatile int do_stats;
+
+struct {
+ unsigned long arp_new;
+ unsigned long arp_change;
+
+ unsigned long app_recv;
+ unsigned long app_success;
+ unsigned long app_bad;
+ unsigned long app_neg;
+ unsigned long app_suppressed;
+
+ unsigned long kern_neg;
+ unsigned long kern_new;
+ unsigned long kern_change;
+
+ unsigned long probes_sent;
+ unsigned long probes_suppressed;
+} stats;
+
+int active_probing;
+int negative_timeout = 60;
+int no_kernel_broadcasts;
+int broadcast_rate = 1000;
+int broadcast_burst = 3000;
+int poll_timeout = 30000;
+
+static void usage(void)
+{
+ fprintf(stderr,
+ "Usage: arpd [ -lkh? ] [ -a N ] [ -b dbase ] [ -B number ] [ -f file ] [ -n time ] [-p interval ] [ -R rate ] [ interfaces ]\n");
+ exit(1);
+}
+
+static int handle_if(int ifindex)
+{
+ int i;
+
+ if (ifnum == 0)
+ return 1;
+
+ for (i = 0; i < ifnum; i++)
+ if (ifvec[i] == ifindex)
+ return 1;
+ return 0;
+}
+
+int sysctl_adjusted;
+
+static void do_sysctl_adjustments(void)
+{
+ int i;
+
+ if (!ifnum)
+ return;
+
+ for (i = 0; i < ifnum; i++) {
+ char buf[128];
+ FILE *fp;
+
+ if (active_probing) {
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/mcast_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ if (no_kernel_broadcasts)
+ strcpy(buf, "0\n");
+ else
+ sprintf(buf, "%d\n", active_probing >= 2 ? 1 : 3-active_probing);
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/app_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ sprintf(buf, "%d\n", active_probing <= 1 ? 1 : active_probing);
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+ sysctl_adjusted = 1;
+}
+
+static void undo_sysctl_adjustments(void)
+{
+ int i;
+
+ if (!sysctl_adjusted)
+ return;
+
+ for (i = 0; i < ifnum; i++) {
+ char buf[128];
+ FILE *fp;
+
+ if (active_probing) {
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/mcast_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ strcpy(buf, "3\n");
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+ sprintf(buf, "/proc/sys/net/ipv4/neigh/%s/app_solicit", ifnames[i]);
+ if ((fp = fopen(buf, "w")) != NULL) {
+ strcpy(buf, "0\n");
+ fputs(buf, fp);
+ fclose(fp);
+ }
+ }
+ sysctl_adjusted = 0;
+}
+
+
+static int send_probe(int ifindex, __u32 addr)
+{
+ struct ifreq ifr = { .ifr_ifindex = ifindex };
+ struct sockaddr_in dst = {
+ .sin_family = AF_INET,
+ .sin_port = htons(1025),
+ .sin_addr.s_addr = addr,
+ };
+ socklen_t len;
+ unsigned char buf[256];
+ struct arphdr *ah = (struct arphdr *)buf;
+ unsigned char *p = (unsigned char *)(ah+1);
+ struct sockaddr_ll sll = {
+ .sll_family = AF_PACKET,
+ .sll_ifindex = ifindex,
+ .sll_protocol = htons(ETH_P_ARP),
+ };
+
+ if (ioctl(udp_sock, SIOCGIFNAME, &ifr))
+ return -1;
+ if (ioctl(udp_sock, SIOCGIFHWADDR, &ifr))
+ return -1;
+ if (ifr.ifr_hwaddr.sa_family != ARPHRD_ETHER)
+ return -1;
+ if (setsockopt(udp_sock, SOL_SOCKET, SO_BINDTODEVICE, ifr.ifr_name, strlen(ifr.ifr_name)+1) < 0)
+ return -1;
+
+ if (connect(udp_sock, (struct sockaddr *)&dst, sizeof(dst)) < 0)
+ return -1;
+ len = sizeof(dst);
+ if (getsockname(udp_sock, (struct sockaddr *)&dst, &len) < 0)
+ return -1;
+
+ ah->ar_hrd = htons(ifr.ifr_hwaddr.sa_family);
+ ah->ar_pro = htons(ETH_P_IP);
+ ah->ar_hln = 6;
+ ah->ar_pln = 4;
+ ah->ar_op = htons(ARPOP_REQUEST);
+
+ memcpy(p, ifr.ifr_hwaddr.sa_data, ah->ar_hln);
+ p += ah->ar_hln;
+
+ memcpy(p, &dst.sin_addr, 4);
+ p += 4;
+
+ memset(sll.sll_addr, 0xFF, sizeof(sll.sll_addr));
+ memcpy(p, &sll.sll_addr, ah->ar_hln);
+ p += ah->ar_hln;
+
+ memcpy(p, &addr, 4);
+ p += 4;
+
+ if (sendto(pset[0].fd, buf, p-buf, 0, (struct sockaddr *)&sll, sizeof(sll)) < 0)
+ return -1;
+ stats.probes_sent++;
+ return 0;
+}
+
+/* Be very tough on sending probes: 1 per second with burst of 3. */
+
+static int queue_active_probe(int ifindex, __u32 addr)
+{
+ static struct timeval prev;
+ static int buckets;
+ struct timeval now;
+
+ gettimeofday(&now, NULL);
+ if (prev.tv_sec) {
+ int diff = (now.tv_sec-prev.tv_sec)*1000+(now.tv_usec-prev.tv_usec)/1000;
+
+ buckets += diff;
+ } else {
+ buckets = broadcast_burst;
+ }
+ if (buckets > broadcast_burst)
+ buckets = broadcast_burst;
+ if (buckets >= broadcast_rate && !send_probe(ifindex, addr)) {
+ buckets -= broadcast_rate;
+ prev = now;
+ return 0;
+ }
+ stats.probes_suppressed++;
+ return -1;
+}
+
+static int respond_to_kernel(int ifindex, __u32 addr, char *lla, int llalen)
+{
+ struct {
+ struct nlmsghdr n;
+ struct ndmsg ndm;
+ char buf[256];
+ } req = {
+ .n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ndmsg)),
+ .n.nlmsg_flags = NLM_F_REQUEST,
+ .n.nlmsg_type = RTM_NEWNEIGH,
+ .ndm.ndm_family = AF_INET,
+ .ndm.ndm_state = NUD_STALE,
+ .ndm.ndm_ifindex = ifindex,
+ .ndm.ndm_type = RTN_UNICAST,
+ };
+
+ addattr_l(&req.n, sizeof(req), NDA_DST, &addr, 4);
+ addattr_l(&req.n, sizeof(req), NDA_LLADDR, lla, llalen);
+ return rtnl_send(&rth, &req, req.n.nlmsg_len) <= 0;
+}
+
+static void prepare_neg_entry(__u8 *ndata, __u32 stamp)
+{
+ ndata[0] = 0xFF;
+ ndata[1] = 0;
+ ndata[2] = stamp>>24;
+ ndata[3] = stamp>>16;
+ ndata[4] = stamp>>8;
+ ndata[5] = stamp;
+}
+
+
+static int do_one_request(struct nlmsghdr *n)
+{
+ struct ndmsg *ndm = NLMSG_DATA(n);
+ int len = n->nlmsg_len;
+ struct rtattr *tb[NDA_MAX+1];
+ struct dbkey key;
+ DBT dbkey, dbdat;
+ int do_acct = 0;
+
+ if (n->nlmsg_type == NLMSG_DONE) {
+ dbase->sync(dbase, 0);
+
+ /* Now we have at least mirror of kernel db, so that
+ * may start real resolution.
+ */
+ do_sysctl_adjustments();
+ return 0;
+ }
+
+ if (n->nlmsg_type != RTM_GETNEIGH && n->nlmsg_type != RTM_NEWNEIGH)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*ndm));
+ if (len < 0)
+ return -1;
+
+ if (ndm->ndm_family != AF_INET ||
+ (ifnum && !handle_if(ndm->ndm_ifindex)) ||
+ ndm->ndm_flags ||
+ ndm->ndm_type != RTN_UNICAST ||
+ !(ndm->ndm_state&~NUD_NOARP))
+ return 0;
+
+ parse_rtattr(tb, NDA_MAX, NDA_RTA(ndm), len);
+
+ if (!tb[NDA_DST])
+ return 0;
+
+ key.iface = ndm->ndm_ifindex;
+ memcpy(&key.addr, RTA_DATA(tb[NDA_DST]), 4);
+ dbkey.data = &key;
+ dbkey.size = sizeof(key);
+
+ if (dbase->get(dbase, &dbkey, &dbdat, 0) != 0) {
+ dbdat.data = 0;
+ dbdat.size = 0;
+ }
+
+ if (n->nlmsg_type == RTM_GETNEIGH) {
+ if (!(n->nlmsg_flags&NLM_F_REQUEST))
+ return 0;
+
+ if (!(ndm->ndm_state&(NUD_PROBE|NUD_INCOMPLETE))) {
+ stats.app_bad++;
+ return 0;
+ }
+
+ if (ndm->ndm_state&NUD_PROBE) {
+ /* If we get this, kernel still has some valid
+ * address, but unicast probing failed and host
+ * is either dead or changed its mac address.
+ * Kernel is going to initiate broadcast resolution.
+ * OK, we invalidate our information as well.
+ */
+ if (dbdat.data && !IS_NEG(dbdat.data))
+ stats.app_neg++;
+
+ dbase->del(dbase, &dbkey, 0);
+ } else {
+ /* If we get this kernel does not have any information.
+ * If we have something tell this to kernel. */
+ stats.app_recv++;
+ if (dbdat.data && !IS_NEG(dbdat.data)) {
+ stats.app_success++;
+ respond_to_kernel(key.iface, key.addr, dbdat.data, dbdat.size);
+ return 0;
+ }
+
+ /* Sheeit! We have nothing to tell. */
+ /* If we have recent negative entry, be silent. */
+ if (dbdat.data && NEG_VALID(dbdat.data)) {
+ if (NEG_CNT(dbdat.data) >= active_probing) {
+ stats.app_suppressed++;
+ return 0;
+ }
+ do_acct = 1;
+ }
+ }
+
+ if (active_probing &&
+ queue_active_probe(ndm->ndm_ifindex, key.addr) == 0 &&
+ do_acct) {
+ NEG_CNT(dbdat.data)++;
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+ }
+ } else if (n->nlmsg_type == RTM_NEWNEIGH) {
+ if (n->nlmsg_flags&NLM_F_REQUEST)
+ return 0;
+
+ if (ndm->ndm_state&NUD_FAILED) {
+ /* Kernel was not able to resolve. Host is dead.
+ * Create negative entry if it is not present
+ * or renew it if it is too old. */
+ if (!dbdat.data ||
+ !IS_NEG(dbdat.data) ||
+ !NEG_VALID(dbdat.data)) {
+ __u8 ndata[6];
+
+ stats.kern_neg++;
+ prepare_neg_entry(ndata, time(NULL));
+ dbdat.data = ndata;
+ dbdat.size = sizeof(ndata);
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+ }
+ } else if (tb[NDA_LLADDR]) {
+ if (dbdat.data && !IS_NEG(dbdat.data)) {
+ if (memcmp(RTA_DATA(tb[NDA_LLADDR]), dbdat.data, dbdat.size) == 0)
+ return 0;
+ stats.kern_change++;
+ } else {
+ stats.kern_new++;
+ }
+ dbdat.data = RTA_DATA(tb[NDA_LLADDR]);
+ dbdat.size = RTA_PAYLOAD(tb[NDA_LLADDR]);
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+ }
+ }
+ return 0;
+}
+
+static void load_initial_table(void)
+{
+ if (rtnl_neighdump_req(&rth, AF_INET, NULL) < 0) {
+ perror("dump request failed");
+ exit(1);
+ }
+
+}
+
+static void get_kern_msg(void)
+{
+ int status;
+ struct nlmsghdr *h;
+ struct sockaddr_nl nladdr = {};
+ struct iovec iov;
+ char buf[8192];
+ struct msghdr msg = {
+ (void *)&nladdr, sizeof(nladdr),
+ &iov, 1,
+ NULL, 0,
+ 0
+ };
+
+ iov.iov_base = buf;
+ iov.iov_len = sizeof(buf);
+
+ status = recvmsg(rth.fd, &msg, MSG_DONTWAIT);
+
+ if (status <= 0)
+ return;
+
+ if (msg.msg_namelen != sizeof(nladdr))
+ return;
+
+ if (nladdr.nl_pid)
+ return;
+
+ for (h = (struct nlmsghdr *)buf; status >= sizeof(*h); ) {
+ int len = h->nlmsg_len;
+ int l = len - sizeof(*h);
+
+ if (l < 0 || len > status)
+ return;
+
+ if (do_one_request(h) < 0)
+ return;
+
+ status -= NLMSG_ALIGN(len);
+ h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len));
+ }
+}
+
+/* Receive gratuitous ARP messages and store them, that's all. */
+static void get_arp_pkt(void)
+{
+ unsigned char buf[1024];
+ struct sockaddr_ll sll;
+ socklen_t sll_len = sizeof(sll);
+ struct arphdr *a = (struct arphdr *)buf;
+ struct dbkey key;
+ DBT dbkey, dbdat;
+ int n;
+
+ n = recvfrom(pset[0].fd, buf, sizeof(buf), MSG_DONTWAIT,
+ (struct sockaddr *)&sll, &sll_len);
+ if (n < 0) {
+ if (errno != EINTR && errno != EAGAIN)
+ syslog(LOG_ERR, "recvfrom: %m");
+ return;
+ }
+
+ if (ifnum && !handle_if(sll.sll_ifindex))
+ return;
+
+ /* Sanity checks */
+
+ if (n < sizeof(*a) ||
+ (a->ar_op != htons(ARPOP_REQUEST) &&
+ a->ar_op != htons(ARPOP_REPLY)) ||
+ a->ar_pln != 4 ||
+ a->ar_pro != htons(ETH_P_IP) ||
+ a->ar_hln != sll.sll_halen ||
+ sizeof(*a) + 2*4 + 2*a->ar_hln > n)
+ return;
+
+ key.iface = sll.sll_ifindex;
+ memcpy(&key.addr, (char *)(a+1) + a->ar_hln, 4);
+
+ /* DAD message, ignore. */
+ if (key.addr == 0)
+ return;
+
+ dbkey.data = &key;
+ dbkey.size = sizeof(key);
+
+ if (dbase->get(dbase, &dbkey, &dbdat, 0) == 0 && !IS_NEG(dbdat.data)) {
+ if (memcmp(dbdat.data, a+1, dbdat.size) == 0)
+ return;
+ stats.arp_change++;
+ } else {
+ stats.arp_new++;
+ }
+
+ dbdat.data = a+1;
+ dbdat.size = a->ar_hln;
+ dbase->put(dbase, &dbkey, &dbdat, 0);
+}
+
+static void catch_signal(int sig, void (*handler)(int))
+{
+ struct sigaction sa = { .sa_handler = handler };
+
+#ifdef SA_INTERRUPT
+ sa.sa_flags = SA_INTERRUPT;
+#endif
+ sigaction(sig, &sa, NULL);
+}
+
+#include <setjmp.h>
+sigjmp_buf env;
+volatile int in_poll;
+
+static void sig_exit(int signo)
+{
+ do_exit = 1;
+ if (in_poll)
+ siglongjmp(env, 1);
+}
+
+static void sig_sync(int signo)
+{
+ do_sync = 1;
+ if (in_poll)
+ siglongjmp(env, 1);
+}
+
+static void sig_stats(int signo)
+{
+ do_sync = 1;
+ do_stats = 1;
+ if (in_poll)
+ siglongjmp(env, 1);
+}
+
+static void send_stats(void)
+{
+ syslog(LOG_INFO, "arp_rcv: n%lu c%lu app_rcv: tot %lu hits %lu bad %lu neg %lu sup %lu",
+ stats.arp_new, stats.arp_change,
+
+ stats.app_recv, stats.app_success,
+ stats.app_bad, stats.app_neg, stats.app_suppressed
+ );
+ syslog(LOG_INFO, "kern: n%lu c%lu neg %lu arp_send: %lu rlim %lu",
+ stats.kern_new, stats.kern_change, stats.kern_neg,
+
+ stats.probes_sent, stats.probes_suppressed
+ );
+ do_stats = 0;
+}
+
+
+int main(int argc, char **argv)
+{
+ int opt;
+ int do_list = 0;
+ char *do_load = NULL;
+
+ while ((opt = getopt(argc, argv, "h?b:lf:a:n:p:kR:B:")) != EOF) {
+ switch (opt) {
+ case 'b':
+ dbname = optarg;
+ break;
+ case 'f':
+ if (do_load) {
+ fprintf(stderr, "Duplicate option -f\n");
+ usage();
+ }
+ do_load = optarg;
+ break;
+ case 'l':
+ do_list = 1;
+ break;
+ case 'a':
+ active_probing = atoi(optarg);
+ break;
+ case 'n':
+ negative_timeout = atoi(optarg);
+ break;
+ case 'k':
+ no_kernel_broadcasts = 1;
+ break;
+ case 'p':
+ if ((poll_timeout = 1000 * strtod(optarg, NULL)) < 100) {
+ fprintf(stderr, "Invalid poll timeout\n");
+ exit(-1);
+ }
+ break;
+ case 'R':
+ if ((broadcast_rate = atoi(optarg)) <= 0 ||
+ (broadcast_rate = 1000/broadcast_rate) <= 0) {
+ fprintf(stderr, "Invalid ARP rate\n");
+ exit(-1);
+ }
+ break;
+ case 'B':
+ if ((broadcast_burst = atoi(optarg)) <= 0 ||
+ (broadcast_burst = 1000*broadcast_burst) <= 0) {
+ fprintf(stderr, "Invalid ARP burst\n");
+ exit(-1);
+ }
+ break;
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+ argc -= optind;
+ argv += optind;
+
+ if (argc > 0) {
+ ifnum = argc;
+ ifnames = argv;
+ ifvec = malloc(argc*sizeof(int));
+ if (!ifvec) {
+ perror("malloc");
+ exit(-1);
+ }
+ }
+
+ if ((udp_sock = socket(AF_INET, SOCK_DGRAM, 0)) < 0) {
+ perror("socket");
+ exit(-1);
+ }
+
+ if (ifnum) {
+ int i;
+ struct ifreq ifr = {};
+
+ for (i = 0; i < ifnum; i++) {
+ if (get_ifname(ifr.ifr_name, ifnames[i]))
+ invarg("not a valid ifname", ifnames[i]);
+ if (ioctl(udp_sock, SIOCGIFINDEX, &ifr)) {
+ perror("ioctl(SIOCGIFINDEX)");
+ exit(-1);
+ }
+ ifvec[i] = ifr.ifr_ifindex;
+ }
+ }
+
+ dbase = dbopen(dbname, O_CREAT|O_RDWR, 0644, DB_HASH, NULL);
+ if (dbase == NULL) {
+ perror("db_open");
+ exit(-1);
+ }
+
+ if (do_load) {
+ char buf[128];
+ FILE *fp;
+ struct dbkey k;
+ DBT dbkey, dbdat;
+
+ dbkey.data = &k;
+ dbkey.size = sizeof(k);
+
+ if (strcmp(do_load, "-") == 0 || strcmp(do_load, "--") == 0) {
+ fp = stdin;
+ } else if ((fp = fopen(do_load, "r")) == NULL) {
+ perror("fopen");
+ goto do_abort;
+ }
+
+ buf[sizeof(buf)-1] = 0;
+ while (fgets(buf, sizeof(buf), fp)) {
+ __u8 b1[6];
+ char ipbuf[128];
+ char macbuf[128];
+
+ if (buf[0] == '#')
+ continue;
+
+ if (sscanf(buf, "%u%s%s", &k.iface, ipbuf, macbuf) != 3) {
+ fprintf(stderr, "Wrong format of input file \"%s\"\n", do_load);
+ goto do_abort;
+ }
+ if (strncmp(macbuf, "FAILED:", 7) == 0)
+ continue;
+ if (!inet_aton(ipbuf, (struct in_addr *)&k.addr)) {
+ fprintf(stderr, "Invalid IP address: \"%s\"\n", ipbuf);
+ goto do_abort;
+ }
+
+ if (ll_addr_a2n((char *) b1, 6, macbuf) != 6)
+ goto do_abort;
+ dbdat.size = 6;
+
+ if (dbase->put(dbase, &dbkey, &dbdat, 0)) {
+ perror("hash->put");
+ goto do_abort;
+ }
+ }
+ dbase->sync(dbase, 0);
+ if (fp != stdin)
+ fclose(fp);
+ }
+
+ if (do_list) {
+ DBT dbkey, dbdat;
+
+ printf("%-8s %-15s %s\n", "#Ifindex", "IP", "MAC");
+ while (dbase->seq(dbase, &dbkey, &dbdat, R_NEXT) == 0) {
+ struct dbkey *key = dbkey.data;
+
+ if (handle_if(key->iface)) {
+ if (!IS_NEG(dbdat.data)) {
+ char b1[18];
+
+ printf("%-8d %-15s %s\n",
+ key->iface,
+ inet_ntoa(*(struct in_addr *)&key->addr),
+ ll_addr_n2a(dbdat.data, 6, ARPHRD_ETHER, b1, 18));
+ } else {
+ printf("%-8d %-15s FAILED: %dsec ago\n",
+ key->iface,
+ inet_ntoa(*(struct in_addr *)&key->addr),
+ NEG_AGE(dbdat.data));
+ }
+ }
+ }
+ }
+
+ if (do_load || do_list)
+ goto out;
+
+ pset[0].fd = socket(PF_PACKET, SOCK_DGRAM, 0);
+ if (pset[0].fd < 0) {
+ perror("socket");
+ exit(-1);
+ }
+
+ if (1) {
+ struct sockaddr_ll sll = {
+ .sll_family = AF_PACKET,
+ .sll_protocol = htons(ETH_P_ARP),
+ .sll_ifindex = (ifnum == 1 ? ifvec[0] : 0),
+ };
+
+ if (bind(pset[0].fd, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
+ perror("bind");
+ goto do_abort;
+ }
+ }
+
+ if (rtnl_open(&rth, RTMGRP_NEIGH) < 0) {
+ perror("rtnl_open");
+ goto do_abort;
+ }
+ pset[1].fd = rth.fd;
+
+ load_initial_table();
+
+ if (daemon(0, 0)) {
+ perror("arpd: daemon");
+ goto do_abort;
+ }
+
+ openlog("arpd", LOG_PID | LOG_CONS, LOG_DAEMON);
+ catch_signal(SIGINT, sig_exit);
+ catch_signal(SIGTERM, sig_exit);
+ catch_signal(SIGHUP, sig_sync);
+ catch_signal(SIGUSR1, sig_stats);
+
+#define EVENTS (POLLIN|POLLPRI|POLLERR|POLLHUP)
+ pset[0].events = EVENTS;
+ pset[0].revents = 0;
+ pset[1].events = EVENTS;
+ pset[1].revents = 0;
+
+ sigsetjmp(env, 1);
+
+ for (;;) {
+ in_poll = 1;
+
+ if (do_exit)
+ break;
+ if (do_sync) {
+ in_poll = 0;
+ dbase->sync(dbase, 0);
+ do_sync = 0;
+ in_poll = 1;
+ }
+ if (do_stats)
+ send_stats();
+ if (poll(pset, 2, poll_timeout) > 0) {
+ in_poll = 0;
+ if (pset[0].revents&EVENTS)
+ get_arp_pkt();
+ if (pset[1].revents&EVENTS)
+ get_kern_msg();
+ } else {
+ do_sync = 1;
+ }
+ }
+
+ undo_sysctl_adjustments();
+out:
+ dbase->close(dbase);
+ exit(0);
+
+do_abort:
+ dbase->close(dbase);
+ exit(-1);
+}
diff --git a/misc/ifstat.c b/misc/ifstat.c
new file mode 100644
index 0000000..7290109
--- /dev/null
+++ b/misc/ifstat.c
@@ -0,0 +1,1040 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * ifstat.c handy utility to read net interface statistics
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <fnmatch.h>
+#include <sys/file.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/poll.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <signal.h>
+#include <math.h>
+#include <getopt.h>
+
+#include <linux/if.h>
+#include <linux/if_link.h>
+
+#include "libnetlink.h"
+#include "json_writer.h"
+#include "version.h"
+#include "utils.h"
+
+int dump_zeros;
+int reset_history;
+int ignore_history;
+int no_output;
+int json_output;
+int no_update;
+int scan_interval;
+int time_constant;
+int show_errors;
+double W;
+char **patterns;
+int npatterns;
+bool is_extended;
+int filter_type;
+int sub_type;
+
+char info_source[128];
+int source_mismatch;
+
+#define MAXS (sizeof(struct rtnl_link_stats)/sizeof(__u32))
+#define NO_SUB_TYPE 0xffff
+
+struct ifstat_ent {
+ struct ifstat_ent *next;
+ char *name;
+ int ifindex;
+ unsigned long long val[MAXS];
+ double rate[MAXS];
+ __u32 ival[MAXS];
+};
+
+static const char *stats[MAXS] = {
+ "rx_packets",
+ "tx_packets",
+ "rx_bytes",
+ "tx_bytes",
+ "rx_errors",
+ "tx_errors",
+ "rx_dropped",
+ "tx_dropped",
+ "multicast",
+ "collisions",
+ "rx_length_errors",
+ "rx_over_errors",
+ "rx_crc_errors",
+ "rx_frame_errors",
+ "rx_fifo_errors",
+ "rx_missed_errors",
+ "tx_aborted_errors",
+ "tx_carrier_errors",
+ "tx_fifo_errors",
+ "tx_heartbeat_errors",
+ "tx_window_errors",
+ "rx_compressed",
+ "tx_compressed"
+};
+
+struct ifstat_ent *kern_db;
+struct ifstat_ent *hist_db;
+
+static int match(const char *id)
+{
+ int i;
+
+ if (npatterns == 0)
+ return 1;
+
+ for (i = 0; i < npatterns; i++) {
+ if (!fnmatch(patterns[i], id, FNM_CASEFOLD))
+ return 1;
+ }
+ return 0;
+}
+
+static int get_nlmsg_extended(struct nlmsghdr *m, void *arg)
+{
+ struct if_stats_msg *ifsm = NLMSG_DATA(m);
+ struct rtattr *tb[IFLA_STATS_MAX+1];
+ int len = m->nlmsg_len;
+ struct ifstat_ent *n;
+
+ if (m->nlmsg_type != RTM_NEWSTATS)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*ifsm));
+ if (len < 0) {
+ errno = EINVAL;
+ return -1;
+ }
+
+ parse_rtattr(tb, IFLA_STATS_MAX, IFLA_STATS_RTA(ifsm), len);
+ if (tb[filter_type] == NULL)
+ return 0;
+
+ n = malloc(sizeof(*n));
+ if (!n) {
+ errno = ENOMEM;
+ return -1;
+ }
+
+ n->ifindex = ifsm->ifindex;
+ n->name = strdup(ll_index_to_name(ifsm->ifindex));
+
+ if (sub_type == NO_SUB_TYPE) {
+ memcpy(&n->val, RTA_DATA(tb[filter_type]), sizeof(n->val));
+ } else {
+ struct rtattr *attr;
+
+ attr = parse_rtattr_one_nested(sub_type, tb[filter_type]);
+ if (attr == NULL) {
+ free(n);
+ return 0;
+ }
+ memcpy(&n->val, RTA_DATA(attr), sizeof(n->val));
+ }
+ memset(&n->rate, 0, sizeof(n->rate));
+ n->next = kern_db;
+ kern_db = n;
+ return 0;
+}
+
+static int get_nlmsg(struct nlmsghdr *m, void *arg)
+{
+ struct ifinfomsg *ifi = NLMSG_DATA(m);
+ struct rtattr *tb[IFLA_MAX+1];
+ int len = m->nlmsg_len;
+ struct ifstat_ent *n;
+ int i;
+
+ if (m->nlmsg_type != RTM_NEWLINK)
+ return 0;
+
+ len -= NLMSG_LENGTH(sizeof(*ifi));
+ if (len < 0) {
+ errno = EINVAL;
+ return -1;
+ }
+
+ if (!(ifi->ifi_flags&IFF_UP))
+ return 0;
+
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(ifi), len);
+ if (tb[IFLA_IFNAME] == NULL || tb[IFLA_STATS] == NULL)
+ return 0;
+
+ n = malloc(sizeof(*n));
+ if (!n) {
+ errno = ENOMEM;
+ return -1;
+ }
+ n->ifindex = ifi->ifi_index;
+ n->name = strdup(RTA_DATA(tb[IFLA_IFNAME]));
+ memcpy(&n->ival, RTA_DATA(tb[IFLA_STATS]), sizeof(n->ival));
+ memset(&n->rate, 0, sizeof(n->rate));
+ for (i = 0; i < MAXS; i++)
+ n->val[i] = n->ival[i];
+ n->next = kern_db;
+ kern_db = n;
+ return 0;
+}
+
+static void load_info(void)
+{
+ struct ifstat_ent *db, *n;
+ struct rtnl_handle rth;
+ __u32 filter_mask;
+
+ if (rtnl_open(&rth, 0) < 0)
+ exit(1);
+
+ if (is_extended) {
+ ll_init_map(&rth);
+ filter_mask = IFLA_STATS_FILTER_BIT(filter_type);
+ if (rtnl_statsdump_req_filter(&rth, AF_UNSPEC,
+ filter_mask, NULL, NULL) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, get_nlmsg_extended, NULL) < 0) {
+ perror("Dump terminated\n");
+ exit(1);
+ }
+ } else {
+ if (rtnl_linkdump_req(&rth, AF_INET) < 0) {
+ perror("Cannot send dump request");
+ exit(1);
+ }
+
+ if (rtnl_dump_filter(&rth, get_nlmsg, NULL) < 0) {
+ perror("Dump terminated\n");
+ exit(1);
+ }
+ }
+
+ rtnl_close(&rth);
+
+ db = kern_db;
+ kern_db = NULL;
+
+ while (db) {
+ n = db;
+ db = db->next;
+ n->next = kern_db;
+ kern_db = n;
+ }
+}
+
+static void load_raw_table(FILE *fp)
+{
+ char buf[4096];
+ struct ifstat_ent *db = NULL;
+ struct ifstat_ent *n;
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ char *p;
+ char *next;
+ int i;
+
+ if (buf[0] == '#') {
+ buf[strlen(buf)-1] = 0;
+ if (info_source[0] && strcmp(info_source, buf+1))
+ source_mismatch = 1;
+ strlcpy(info_source, buf+1, sizeof(info_source));
+ continue;
+ }
+ if ((n = malloc(sizeof(*n))) == NULL)
+ abort();
+
+ if (!(p = strchr(buf, ' ')))
+ abort();
+ *p++ = 0;
+
+ if (sscanf(buf, "%d", &n->ifindex) != 1)
+ abort();
+ if (!(next = strchr(p, ' ')))
+ abort();
+ *next++ = 0;
+
+ n->name = strdup(p);
+ p = next;
+
+ for (i = 0; i < MAXS; i++) {
+ unsigned int rate;
+
+ if (!(next = strchr(p, ' ')))
+ abort();
+ *next++ = 0;
+ if (sscanf(p, "%llu", n->val+i) != 1)
+ abort();
+ n->ival[i] = (__u32)n->val[i];
+ p = next;
+ if (!(next = strchr(p, ' ')))
+ abort();
+ *next++ = 0;
+ if (sscanf(p, "%u", &rate) != 1)
+ abort();
+ n->rate[i] = rate;
+ p = next;
+ }
+ n->next = db;
+ db = n;
+ }
+
+ while (db) {
+ n = db;
+ db = db->next;
+ n->next = kern_db;
+ kern_db = n;
+ }
+}
+
+static void dump_raw_db(FILE *fp, int to_hist)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct ifstat_ent *n, *h;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_start_object(jw);
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ fprintf(fp, "#%s\n", info_source);
+
+ for (n = kern_db; n; n = n->next) {
+ int i;
+ unsigned long long *vals = n->val;
+ double *rates = n->rate;
+
+ if (!match(n->name)) {
+ struct ifstat_ent *h1;
+
+ if (!to_hist)
+ continue;
+ for (h1 = h; h1; h1 = h1->next) {
+ if (h1->ifindex == n->ifindex) {
+ vals = h1->val;
+ rates = h1->rate;
+ h = h1->next;
+ break;
+ }
+ }
+ }
+
+ if (jw) {
+ jsonw_name(jw, n->name);
+ jsonw_start_object(jw);
+
+ for (i = 0; i < MAXS && stats[i]; i++)
+ jsonw_uint_field(jw, stats[i], vals[i]);
+ jsonw_end_object(jw);
+ } else {
+ fprintf(fp, "%d %s ", n->ifindex, n->name);
+ for (i = 0; i < MAXS; i++)
+ fprintf(fp, "%llu %u ", vals[i],
+ (unsigned int)rates[i]);
+ fprintf(fp, "\n");
+ }
+ }
+ if (jw) {
+ jsonw_end_object(jw);
+
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+/* use communication definitions of meg/kilo etc */
+static const unsigned long long giga = 1000000000ull;
+static const unsigned long long mega = 1000000;
+static const unsigned long long kilo = 1000;
+
+static void format_rate(FILE *fp, const unsigned long long *vals,
+ const double *rates, int i)
+{
+ char temp[64];
+
+ if (vals[i] > giga)
+ fprintf(fp, "%7lluM ", vals[i]/mega);
+ else if (vals[i] > mega)
+ fprintf(fp, "%7lluK ", vals[i]/kilo);
+ else
+ fprintf(fp, "%8llu ", vals[i]);
+
+ if (rates[i] > mega) {
+ sprintf(temp, "%uM", (unsigned int)(rates[i]/mega));
+ fprintf(fp, "%-6s ", temp);
+ } else if (rates[i] > kilo) {
+ sprintf(temp, "%uK", (unsigned int)(rates[i]/kilo));
+ fprintf(fp, "%-6s ", temp);
+ } else
+ fprintf(fp, "%-6u ", (unsigned int)rates[i]);
+}
+
+static void format_pair(FILE *fp, const unsigned long long *vals, int i, int k)
+{
+ char temp[64];
+
+ if (vals[i] > giga)
+ fprintf(fp, "%7lluM ", vals[i]/mega);
+ else if (vals[i] > mega)
+ fprintf(fp, "%7lluK ", vals[i]/kilo);
+ else
+ fprintf(fp, "%8llu ", vals[i]);
+
+ if (vals[k] > giga) {
+ sprintf(temp, "%uM", (unsigned int)(vals[k]/mega));
+ fprintf(fp, "%-6s ", temp);
+ } else if (vals[k] > mega) {
+ sprintf(temp, "%uK", (unsigned int)(vals[k]/kilo));
+ fprintf(fp, "%-6s ", temp);
+ } else
+ fprintf(fp, "%-6u ", (unsigned int)vals[k]);
+}
+
+static void print_head(FILE *fp)
+{
+ fprintf(fp, "#%s\n", info_source);
+ fprintf(fp, "%-15s ", "Interface");
+
+ fprintf(fp, "%8s/%-6s ", "RX Pkts", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Pkts", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Data", "Rate");
+ fprintf(fp, "%8s/%-6s\n", "TX Data", "Rate");
+
+ if (!show_errors) {
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "RX Errs", "Drop");
+ fprintf(fp, "%8s/%-6s ", "TX Errs", "Drop");
+ fprintf(fp, "%8s/%-6s ", "RX Over", "Rate");
+ fprintf(fp, "%8s/%-6s\n", "TX Coll", "Rate");
+ } else {
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "RX Errs", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Drop", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Over", "Rate");
+ fprintf(fp, "%8s/%-6s\n", "RX Leng", "Rate");
+
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "RX Crc", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Frm", "Rate");
+ fprintf(fp, "%8s/%-6s ", "RX Fifo", "Rate");
+ fprintf(fp, "%8s/%-6s\n", "RX Miss", "Rate");
+
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "TX Errs", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Drop", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Coll", "Rate");
+ fprintf(fp, "%8s/%-6s\n", "TX Carr", "Rate");
+
+ fprintf(fp, "%-15s ", "");
+ fprintf(fp, "%8s/%-6s ", "TX Abrt", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Fifo", "Rate");
+ fprintf(fp, "%8s/%-6s ", "TX Hear", "Rate");
+ fprintf(fp, "%8s/%-6s\n", "TX Wind", "Rate");
+ }
+}
+
+static void print_one_json(json_writer_t *jw, const struct ifstat_ent *n,
+ const unsigned long long *vals)
+{
+ int i, m = show_errors ? 20 : 10;
+
+ jsonw_name(jw, n->name);
+ jsonw_start_object(jw);
+
+ for (i = 0; i < m && stats[i]; i++)
+ jsonw_uint_field(jw, stats[i], vals[i]);
+
+ jsonw_end_object(jw);
+}
+
+static void print_one_if(FILE *fp, const struct ifstat_ent *n,
+ const unsigned long long *vals)
+{
+ int i;
+
+ fprintf(fp, "%-15s ", n->name);
+ for (i = 0; i < 4; i++)
+ format_rate(fp, vals, n->rate, i);
+ fprintf(fp, "\n");
+
+ if (!show_errors) {
+ fprintf(fp, "%-15s ", "");
+ format_pair(fp, vals, 4, 6);
+ format_pair(fp, vals, 5, 7);
+ format_rate(fp, vals, n->rate, 11);
+ format_rate(fp, vals, n->rate, 9);
+ fprintf(fp, "\n");
+ } else {
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 4);
+ format_rate(fp, vals, n->rate, 6);
+ format_rate(fp, vals, n->rate, 11);
+ format_rate(fp, vals, n->rate, 10);
+ fprintf(fp, "\n");
+
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 12);
+ format_rate(fp, vals, n->rate, 13);
+ format_rate(fp, vals, n->rate, 14);
+ format_rate(fp, vals, n->rate, 15);
+ fprintf(fp, "\n");
+
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 5);
+ format_rate(fp, vals, n->rate, 7);
+ format_rate(fp, vals, n->rate, 9);
+ format_rate(fp, vals, n->rate, 17);
+ fprintf(fp, "\n");
+
+ fprintf(fp, "%-15s ", "");
+ format_rate(fp, vals, n->rate, 16);
+ format_rate(fp, vals, n->rate, 18);
+ format_rate(fp, vals, n->rate, 19);
+ format_rate(fp, vals, n->rate, 20);
+ fprintf(fp, "\n");
+ }
+}
+
+static void dump_kern_db(FILE *fp)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct ifstat_ent *n;
+
+ if (jw) {
+ jsonw_start_object(jw);
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ print_head(fp);
+
+ for (n = kern_db; n; n = n->next) {
+ if (!match(n->name))
+ continue;
+
+ if (jw)
+ print_one_json(jw, n, n->val);
+ else
+ print_one_if(fp, n, n->val);
+ }
+ if (jw) {
+ jsonw_end_object(jw);
+
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+static void dump_incr_db(FILE *fp)
+{
+ struct ifstat_ent *n, *h;
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_start_object(jw);
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ print_head(fp);
+
+ for (n = kern_db; n; n = n->next) {
+ int i;
+ unsigned long long vals[MAXS];
+ struct ifstat_ent *h1;
+
+ memcpy(vals, n->val, sizeof(vals));
+
+ for (h1 = h; h1; h1 = h1->next) {
+ if (h1->ifindex == n->ifindex) {
+ for (i = 0; i < MAXS; i++)
+ vals[i] -= h1->val[i];
+ h = h1->next;
+ break;
+ }
+ }
+ if (!match(n->name))
+ continue;
+
+ if (jw)
+ print_one_json(jw, n, n->val);
+ else
+ print_one_if(fp, n, vals);
+ }
+
+ if (jw) {
+ jsonw_end_object(jw);
+
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+static int children;
+
+static void sigchild(int signo)
+{
+}
+
+static void update_db(int interval)
+{
+ struct ifstat_ent *n, *h;
+
+ n = kern_db;
+ kern_db = NULL;
+
+ load_info();
+
+ h = kern_db;
+ kern_db = n;
+
+ for (n = kern_db; n; n = n->next) {
+ struct ifstat_ent *h1;
+
+ for (h1 = h; h1; h1 = h1->next) {
+ if (h1->ifindex == n->ifindex) {
+ int i;
+
+ for (i = 0; i < MAXS; i++) {
+ if (h1->ival[i] < n->ival[i]) {
+ memset(n->ival, 0, sizeof(n->ival));
+ break;
+ }
+ }
+ for (i = 0; i < MAXS; i++) {
+ double sample;
+ __u64 incr;
+
+ if (is_extended) {
+ incr = h1->val[i] - n->val[i];
+ n->val[i] = h1->val[i];
+ } else {
+ incr = (__u32) (h1->ival[i] - n->ival[i]);
+ n->val[i] += incr;
+ n->ival[i] = h1->ival[i];
+ }
+
+ sample = (double)(incr*1000)/interval;
+ if (interval >= scan_interval) {
+ n->rate[i] += W*(sample-n->rate[i]);
+ } else if (interval >= 1000) {
+ if (interval >= time_constant) {
+ n->rate[i] = sample;
+ } else {
+ double w = W*(double)interval/scan_interval;
+
+ n->rate[i] += w*(sample-n->rate[i]);
+ }
+ }
+ }
+
+ while (h != h1) {
+ struct ifstat_ent *tmp = h;
+
+ h = h->next;
+ free(tmp->name);
+ free(tmp);
+ };
+ h = h1->next;
+ free(h1->name);
+ free(h1);
+ break;
+ }
+ }
+ }
+}
+
+#define T_DIFF(a, b) (((a).tv_sec-(b).tv_sec)*1000 + ((a).tv_usec-(b).tv_usec)/1000)
+
+
+static void server_loop(int fd)
+{
+ struct timeval snaptime = { 0 };
+ struct pollfd p;
+
+ p.fd = fd;
+ p.events = p.revents = POLLIN;
+
+ sprintf(info_source, "%d.%lu sampling_interval=%d time_const=%d",
+ getpid(), (unsigned long)random(), scan_interval/1000, time_constant/1000);
+
+ load_info();
+
+ for (;;) {
+ int status;
+ time_t tdiff;
+ struct timeval now;
+
+ gettimeofday(&now, NULL);
+ tdiff = T_DIFF(now, snaptime);
+ if (tdiff >= scan_interval) {
+ update_db(tdiff);
+ snaptime = now;
+ tdiff = 0;
+ }
+
+ if (poll(&p, 1, scan_interval - tdiff) > 0
+ && (p.revents&POLLIN)) {
+ int clnt = accept(fd, NULL, NULL);
+
+ if (clnt >= 0) {
+ pid_t pid;
+
+ if (children >= 5) {
+ close(clnt);
+ } else if ((pid = fork()) != 0) {
+ if (pid > 0)
+ children++;
+ close(clnt);
+ } else {
+ FILE *fp = fdopen(clnt, "w");
+
+ if (fp)
+ dump_raw_db(fp, 0);
+ exit(0);
+ }
+ }
+ }
+ while (children && waitpid(-1, &status, WNOHANG) > 0)
+ children--;
+ }
+}
+
+static int verify_forging(int fd)
+{
+ struct ucred cred;
+ socklen_t olen = sizeof(cred);
+
+ if (getsockopt(fd, SOL_SOCKET, SO_PEERCRED, (void *)&cred, &olen) ||
+ olen < sizeof(cred))
+ return -1;
+ if (cred.uid == getuid() || cred.uid == 0)
+ return 0;
+ return -1;
+}
+
+static void xstat_usage(void)
+{
+ fprintf(stderr,
+"Usage: ifstat supported xstats:\n"
+" cpu_hits Counts only packets that went via the CPU.\n");
+}
+
+struct extended_stats_options_t {
+ char *name;
+ int id;
+ int sub_type;
+};
+
+/* Note: if one xstat name is subset of another, it should be before it in this
+ * list.
+ * Name length must be under 64 chars.
+ */
+static const struct extended_stats_options_t extended_stats_options[] = {
+ {"cpu_hits", IFLA_STATS_LINK_OFFLOAD_XSTATS, IFLA_OFFLOAD_XSTATS_CPU_HIT},
+};
+
+static const char *get_filter_type(const char *name)
+{
+ int name_len;
+ int i;
+
+ name_len = strlen(name);
+ for (i = 0; i < ARRAY_SIZE(extended_stats_options); i++) {
+ const struct extended_stats_options_t *xstat;
+
+ xstat = &extended_stats_options[i];
+ if (strncmp(name, xstat->name, name_len) == 0) {
+ filter_type = xstat->id;
+ sub_type = xstat->sub_type;
+ return xstat->name;
+ }
+ }
+
+ fprintf(stderr, "invalid ifstat extension %s\n", name);
+ xstat_usage();
+ return NULL;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+"Usage: ifstat [OPTION] [ PATTERN [ PATTERN ] ]\n"
+" -h, --help this message\n"
+" -a, --ignore ignore history\n"
+" -d, --scan=SECS sample every statistics every SECS\n"
+" -e, --errors show errors\n"
+" -j, --json format output in JSON\n"
+" -n, --nooutput do history only\n"
+" -p, --pretty pretty print\n"
+" -r, --reset reset history\n"
+" -s, --noupdate don't update history\n"
+" -t, --interval=SECS report average over the last SECS\n"
+" -V, --version output version information\n"
+" -z, --zeros show entries with zero activity\n"
+" -x, --extended=TYPE show extended stats of TYPE\n");
+
+ exit(-1);
+}
+
+static const struct option longopts[] = {
+ { "help", 0, 0, 'h' },
+ { "ignore", 0, 0, 'a' },
+ { "scan", 1, 0, 'd'},
+ { "errors", 0, 0, 'e' },
+ { "nooutput", 0, 0, 'n' },
+ { "json", 0, 0, 'j' },
+ { "reset", 0, 0, 'r' },
+ { "pretty", 0, 0, 'p' },
+ { "noupdate", 0, 0, 's' },
+ { "interval", 1, 0, 't' },
+ { "version", 0, 0, 'V' },
+ { "zeros", 0, 0, 'z' },
+ { "extended", 1, 0, 'x'},
+ { 0 }
+};
+
+int main(int argc, char *argv[])
+{
+ char hist_name[128];
+ struct sockaddr_un sun;
+ FILE *hist_fp = NULL;
+ const char *stats_type = NULL;
+ int ch;
+ int fd;
+
+ is_extended = false;
+ while ((ch = getopt_long(argc, argv, "hjpvVzrnasd:t:ex:",
+ longopts, NULL)) != EOF) {
+ switch (ch) {
+ case 'z':
+ dump_zeros = 1;
+ break;
+ case 'r':
+ reset_history = 1;
+ break;
+ case 'a':
+ ignore_history = 1;
+ break;
+ case 's':
+ no_update = 1;
+ break;
+ case 'n':
+ no_output = 1;
+ break;
+ case 'e':
+ show_errors = 1;
+ break;
+ case 'j':
+ json_output = 1;
+ break;
+ case 'p':
+ pretty = 1;
+ break;
+ case 'd':
+ scan_interval = atoi(optarg) * 1000;
+ if (scan_interval <= 0) {
+ fprintf(stderr, "ifstat: invalid scan interval\n");
+ exit(-1);
+ }
+ break;
+ case 't':
+ time_constant = atoi(optarg);
+ if (time_constant <= 0) {
+ fprintf(stderr, "ifstat: invalid time constant divisor\n");
+ exit(-1);
+ }
+ break;
+ case 'x':
+ stats_type = optarg;
+ is_extended = true;
+ break;
+ case 'v':
+ case 'V':
+ printf("ifstat utility, iproute2-%s\n", version);
+ exit(0);
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ if (stats_type) {
+ stats_type = get_filter_type(stats_type);
+ if (!stats_type)
+ exit(-1);
+ }
+
+ sun.sun_family = AF_UNIX;
+ sun.sun_path[0] = 0;
+ sprintf(sun.sun_path+1, "ifstat%d", getuid());
+
+ if (scan_interval > 0) {
+ if (time_constant == 0)
+ time_constant = 60;
+ time_constant *= 1000;
+ W = 1 - 1/exp(log(10)*(double)scan_interval/time_constant);
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
+ perror("ifstat: socket");
+ exit(-1);
+ }
+ if (bind(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) < 0) {
+ perror("ifstat: bind");
+ exit(-1);
+ }
+ if (listen(fd, 5) < 0) {
+ perror("ifstat: listen");
+ exit(-1);
+ }
+ if (daemon(0, 0)) {
+ perror("ifstat: daemon");
+ exit(-1);
+ }
+ signal(SIGPIPE, SIG_IGN);
+ signal(SIGCHLD, sigchild);
+ server_loop(fd);
+ exit(0);
+ }
+
+ patterns = argv;
+ npatterns = argc;
+
+ if (getenv("IFSTAT_HISTORY"))
+ snprintf(hist_name, sizeof(hist_name),
+ "%s", getenv("IFSTAT_HISTORY"));
+ else
+ if (!stats_type)
+ snprintf(hist_name, sizeof(hist_name),
+ "%s/.ifstat.u%d", P_tmpdir, getuid());
+ else
+ snprintf(hist_name, sizeof(hist_name),
+ "%s/.%s_ifstat.u%d", P_tmpdir, stats_type,
+ getuid());
+
+ if (reset_history && unlink(hist_name) < 0) {
+ perror("ifstat: unlink history file");
+ exit(-1);
+ }
+
+ if (!ignore_history || !no_update) {
+ struct stat stb;
+
+ fd = open(hist_name, O_RDWR|O_CREAT|O_NOFOLLOW, 0600);
+ if (fd < 0) {
+ perror("ifstat: open history file");
+ exit(-1);
+ }
+ if ((hist_fp = fdopen(fd, "r+")) == NULL) {
+ perror("ifstat: fdopen history file");
+ exit(-1);
+ }
+ if (flock(fileno(hist_fp), LOCK_EX)) {
+ perror("ifstat: flock history file");
+ exit(-1);
+ }
+ if (fstat(fileno(hist_fp), &stb) != 0) {
+ perror("ifstat: fstat history file");
+ exit(-1);
+ }
+ if (stb.st_nlink != 1 || stb.st_uid != getuid()) {
+ fprintf(stderr, "ifstat: something is so wrong with history file, that I prefer not to proceed.\n");
+ exit(-1);
+ }
+ if (!ignore_history) {
+ FILE *tfp;
+ long uptime = -1;
+
+ if ((tfp = fopen("/proc/uptime", "r")) != NULL) {
+ if (fscanf(tfp, "%ld", &uptime) != 1)
+ uptime = -1;
+ fclose(tfp);
+ }
+ if (uptime >= 0 && time(NULL) >= stb.st_mtime+uptime) {
+ fprintf(stderr, "ifstat: history is aged out, resetting\n");
+ if (ftruncate(fileno(hist_fp), 0))
+ perror("ifstat: ftruncate");
+ }
+ }
+
+ load_raw_table(hist_fp);
+
+ hist_db = kern_db;
+ kern_db = NULL;
+ }
+
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) >= 0 &&
+ (connect(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) == 0
+ || (strcpy(sun.sun_path+1, "ifstat0"),
+ connect(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) == 0))
+ && verify_forging(fd) == 0) {
+ FILE *sfp = fdopen(fd, "r");
+
+ if (!sfp) {
+ fprintf(stderr, "ifstat: fdopen failed: %s\n",
+ strerror(errno));
+ close(fd);
+ } else {
+ load_raw_table(sfp);
+ if (hist_db && source_mismatch) {
+ fprintf(stderr, "ifstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+ fclose(sfp);
+ }
+ } else {
+ if (fd >= 0)
+ close(fd);
+ if (hist_db && info_source[0] && strcmp(info_source, "kernel")) {
+ fprintf(stderr, "ifstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ info_source[0] = 0;
+ }
+ load_info();
+ if (info_source[0] == 0)
+ strcpy(info_source, "kernel");
+ }
+
+ if (!no_output) {
+ if (ignore_history || hist_db == NULL)
+ dump_kern_db(stdout);
+ else
+ dump_incr_db(stdout);
+ }
+
+ if (!no_update) {
+ if (ftruncate(fileno(hist_fp), 0))
+ perror("ifstat: ftruncate");
+ rewind(hist_fp);
+
+ json_output = 0;
+ dump_raw_db(hist_fp, 1);
+ fclose(hist_fp);
+ }
+ exit(0);
+}
diff --git a/misc/lnstat.c b/misc/lnstat.c
new file mode 100644
index 0000000..f802a0f
--- /dev/null
+++ b/misc/lnstat.c
@@ -0,0 +1,379 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* lnstat - Unified linux network statistics
+ *
+ * Copyright (C) 2004 by Harald Welte <laforge@gnumonks.org>
+ *
+ * Development of this code was funded by Astaro AG, http://www.astaro.com/
+ *
+ * Based on original concept and ideas from predecessor rtstat.c:
+ *
+ * Copyright 2001 by Robert Olsson <robert.olsson@its.uu.se>
+ * Uppsala University, Sweden
+ */
+
+/* Maximum number of fields that can be displayed */
+#define MAX_FIELDS 128
+
+/* Maximum number of header lines */
+#define HDR_LINES 10
+
+/* default field width if none specified */
+#define FIELD_WIDTH_DEFAULT 8
+#define FIELD_WIDTH_MAX 20
+
+#define DEFAULT_INTERVAL 2
+
+#define HDR_LINE_LENGTH (MAX_FIELDS*FIELD_WIDTH_MAX)
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <getopt.h>
+
+#include <json_writer.h>
+#include "lnstat.h"
+#include "version.h"
+
+static struct option opts[] = {
+ { "version", 0, NULL, 'V' },
+ { "count", 1, NULL, 'c' },
+ { "dump", 0, NULL, 'd' },
+ { "json", 0, NULL, 'j' },
+ { "file", 1, NULL, 'f' },
+ { "help", 0, NULL, 'h' },
+ { "interval", 1, NULL, 'i' },
+ { "keys", 1, NULL, 'k' },
+ { "subject", 1, NULL, 's' },
+ { "width", 1, NULL, 'w' },
+ { "oneline", 0, NULL, 0 },
+};
+
+static int usage(char *name, int exit_code)
+{
+ fprintf(stderr,
+ "%s Version %s\n"
+ "Copyright (C) 2004 by Harald Welte <laforge@gnumonks.org>\n"
+ "This program is free software licensed under GNU GPLv2\nwith ABSOLUTELY NO WARRANTY.\n"
+ "\n"
+ "Parameters:\n"
+ " -V --version Print Version of Program\n"
+ " -c --count <count> "
+ "Print <count> number of intervals\n"
+ " -d --dump "
+ "Dump list of available files/keys\n"
+ " -j --json "
+ "Display in JSON format\n"
+ " -f --file <file> Statistics file to use\n"
+ " -h --help This help message\n"
+ " -i --interval <intv> "
+ "Set interval to 'intv' seconds\n"
+ " -k --keys k,k,k,... Display only keys specified\n"
+ " -s --subject [0-2] Control header printing:\n"
+ " 0 = never\n"
+ " 1 = once\n"
+ " 2 = every 20 lines (default))\n"
+ " -w --width n,n,n,... Width for each field\n"
+ "\n",
+ name, version);
+
+ exit(exit_code);
+}
+
+struct field_param {
+ const char *name;
+ struct lnstat_field *lf;
+ struct {
+ unsigned int width;
+ } print;
+};
+
+struct field_params {
+ unsigned int num;
+ struct field_param params[MAX_FIELDS];
+};
+
+static void print_line(FILE *of, const struct lnstat_file *lnstat_files,
+ const struct field_params *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->num; i++) {
+ const struct lnstat_field *lf = fp->params[i].lf;
+
+ fprintf(of, "%*lu|", fp->params[i].print.width, lf->result);
+ }
+ fputc('\n', of);
+}
+
+static void print_json(FILE *of, const struct lnstat_file *lnstat_files,
+ const struct field_params *fp)
+{
+ json_writer_t *jw = jsonw_new(of);
+ int i;
+
+ if (jw == NULL) {
+ fprintf(stderr, "Failed to create JSON writer\n");
+ exit(1);
+ }
+ jsonw_start_object(jw);
+ for (i = 0; i < fp->num; i++) {
+ const struct lnstat_field *lf = fp->params[i].lf;
+
+ jsonw_uint_field(jw, lf->name, lf->result);
+ }
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+}
+
+/* find lnstat_field according to user specification */
+static int map_field_params(struct lnstat_file *lnstat_files,
+ struct field_params *fps, int interval)
+{
+ int i, j = 0;
+ struct lnstat_file *lf;
+
+ /* no field specification on commandline, need to build default */
+ if (!fps->num) {
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ for (i = 0; i < lf->num_fields; i++) {
+ fps->params[j].lf = &lf->fields[i];
+ fps->params[j].lf->file->interval.tv_sec =
+ interval;
+ if (!fps->params[j].print.width)
+ fps->params[j].print.width =
+ FIELD_WIDTH_DEFAULT;
+
+ if (++j >= MAX_FIELDS - 1) {
+ fprintf(stderr,
+ "WARN: MAX_FIELDS (%d) reached, truncating number of keys\n",
+ MAX_FIELDS);
+ goto full;
+ }
+ }
+ }
+full:
+ fps->num = j;
+ return 1;
+ }
+
+ for (i = 0; i < fps->num; i++) {
+ fps->params[i].lf = lnstat_find_field(lnstat_files,
+ fps->params[i].name);
+ if (!fps->params[i].lf) {
+ fprintf(stderr, "Field `%s' unknown\n",
+ fps->params[i].name);
+ return 0;
+ }
+ fps->params[i].lf->file->interval.tv_sec = interval;
+ if (!fps->params[i].print.width)
+ fps->params[i].print.width = FIELD_WIDTH_DEFAULT;
+ }
+ return 1;
+}
+
+struct table_hdr {
+ int num_lines;
+ char *hdr[HDR_LINES];
+};
+
+static struct table_hdr *build_hdr_string(struct lnstat_file *lnstat_files,
+ struct field_params *fps,
+ int linewidth)
+{
+ int h, i;
+ static struct table_hdr th;
+ int ofs = 0;
+
+ for (i = 0; i < HDR_LINES; i++)
+ th.hdr[i] = calloc(1, HDR_LINE_LENGTH);
+
+ for (i = 0; i < fps->num; i++) {
+ char *cname, *fname = fps->params[i].lf->name;
+ unsigned int width = fps->params[i].print.width;
+
+ snprintf(th.hdr[0]+ofs, width+2, "%*.*s|", width, width,
+ fps->params[i].lf->file->basename);
+
+ cname = fname;
+ for (h = 1; h < HDR_LINES; h++) {
+ if (cname - fname >= strlen(fname))
+ snprintf(th.hdr[h]+ofs, width+2,
+ "%*.*s|", width, width, "");
+ else {
+ th.num_lines = h+1;
+ snprintf(th.hdr[h]+ofs, width+2,
+ "%*.*s|", width, width, cname);
+ }
+ cname += width;
+ }
+ ofs += width+1;
+ }
+
+ /* fill in spaces */
+ for (h = 1; h < th.num_lines; h++) {
+ for (i = 0; i < ofs; i++) {
+ if (th.hdr[h][i] == '\0')
+ th.hdr[h][i] = ' ';
+ }
+ }
+
+ return &th;
+}
+
+static int print_hdr(FILE *of, struct table_hdr *th)
+{
+ int i;
+
+ for (i = 0; i < th->num_lines; i++) {
+ fputs(th->hdr[i], of);
+ fputc('\n', of);
+ }
+ return 0;
+}
+
+
+int main(int argc, char **argv)
+{
+ struct lnstat_file *lnstat_files;
+ const char *basename;
+ int i, c;
+ int interval = DEFAULT_INTERVAL;
+ int hdr = 2;
+ enum {
+ MODE_DUMP,
+ MODE_JSON,
+ MODE_NORMAL,
+ } mode = MODE_NORMAL;
+ unsigned long count = 0;
+ struct table_hdr *header;
+ static struct field_params fp;
+ int num_req_files = 0;
+ char *req_files[LNSTAT_MAX_FILES];
+
+ /* backwards compatibility mode for old tools */
+ basename = strrchr(argv[0], '/');
+ if (basename)
+ basename += 1; /* name after slash */
+ else
+ basename = argv[0]; /* no slash */
+
+ if (!strcmp(basename, "rtstat")) {
+ /* rtstat compatibility mode */
+ req_files[0] = "rt_cache";
+ num_req_files = 1;
+ } else if (!strcmp(basename, "ctstat")) {
+ /* ctstat compatibility mode */
+ req_files[0] = "ip_conntrack";
+ num_req_files = 1;
+ }
+
+ while ((c = getopt_long(argc, argv, "Vc:djpf:h?i:k:s:w:",
+ opts, NULL)) != -1) {
+ int len = 0;
+ char *tmp, *tok;
+
+ switch (c) {
+ case 'c':
+ count = strtoul(optarg, NULL, 0);
+ break;
+ case 'd':
+ mode = MODE_DUMP;
+ break;
+ case 'j':
+ mode = MODE_JSON;
+ break;
+ case 'f':
+ req_files[num_req_files++] = strdup(optarg);
+ break;
+ case '?':
+ case 'h':
+ usage(argv[0], 0);
+ break;
+ case 'i':
+ sscanf(optarg, "%u", &interval);
+ break;
+ case 'k':
+ tmp = strdup(optarg);
+ if (!tmp)
+ break;
+ for (tok = strtok(tmp, ",");
+ tok;
+ tok = strtok(NULL, ",")) {
+ if (fp.num >= MAX_FIELDS) {
+ fprintf(stderr,
+ "WARN: too many keys requested: (%d max)\n",
+ MAX_FIELDS);
+ break;
+ }
+ fp.params[fp.num++].name = tok;
+ }
+ break;
+ case 's':
+ sscanf(optarg, "%u", &hdr);
+ break;
+ case 'w':
+ tmp = strdup(optarg);
+ if (!tmp)
+ break;
+ i = 0;
+ for (tok = strtok(tmp, ",");
+ tok;
+ tok = strtok(NULL, ",")) {
+ len = strtoul(tok, NULL, 0);
+ if (len > FIELD_WIDTH_MAX)
+ len = FIELD_WIDTH_MAX;
+ fp.params[i].print.width = len;
+ i++;
+ }
+ if (i == 1) {
+ for (i = 0; i < MAX_FIELDS; i++)
+ fp.params[i].print.width = len;
+ }
+ free(tmp);
+ break;
+ default:
+ usage(argv[0], 1);
+ break;
+ }
+ }
+
+ lnstat_files = lnstat_scan_dir(PROC_NET_STAT, num_req_files,
+ (const char **) req_files);
+
+ switch (mode) {
+ case MODE_DUMP:
+ lnstat_dump(stdout, lnstat_files);
+ break;
+
+ case MODE_NORMAL:
+ case MODE_JSON:
+ if (!map_field_params(lnstat_files, &fp, interval))
+ exit(1);
+
+ header = build_hdr_string(lnstat_files, &fp, 80);
+ if (!header)
+ exit(1);
+
+ if (interval < 1)
+ interval = 1;
+
+ for (i = 0; i < count || !count; i++) {
+ lnstat_update(lnstat_files);
+ if (mode == MODE_JSON)
+ print_json(stdout, lnstat_files, &fp);
+ else {
+ if ((hdr > 1 && !(i % 20)) ||
+ (hdr == 1 && i == 0))
+ print_hdr(stdout, header);
+ print_line(stdout, lnstat_files, &fp);
+ }
+ fflush(stdout);
+ if (i < count - 1 || !count)
+ sleep(interval);
+ }
+ break;
+ }
+
+ return 1;
+}
diff --git a/misc/lnstat.h b/misc/lnstat.h
new file mode 100644
index 0000000..433599c
--- /dev/null
+++ b/misc/lnstat.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LNSTAT_H
+#define _LNSTAT_H
+
+#include <limits.h>
+#include <sys/select.h>
+
+#define PROC_NET_STAT "/proc/net/stat"
+
+#define LNSTAT_MAX_FILES 32
+#define LNSTAT_MAX_FIELDS_PER_LINE 32
+#define LNSTAT_MAX_FIELD_NAME_LEN 32
+
+struct lnstat_file;
+
+struct lnstat_field {
+ struct lnstat_file *file;
+ unsigned int num; /* field number in line */
+ char name[LNSTAT_MAX_FIELD_NAME_LEN+1];
+ unsigned long values[2]; /* two buffers for values */
+ unsigned long result;
+};
+
+struct lnstat_file {
+ struct lnstat_file *next;
+ char path[PATH_MAX+1];
+ char basename[NAME_MAX+1];
+ struct timeval last_read; /* last time of read */
+ struct timeval interval; /* interval */
+ int compat; /* 1 == backwards compat mode */
+ FILE *fp;
+ unsigned int num_fields; /* number of fields */
+ struct lnstat_field fields[LNSTAT_MAX_FIELDS_PER_LINE];
+};
+
+
+struct lnstat_file *lnstat_scan_dir(const char *path, const int num_req_files,
+ const char **req_files);
+int lnstat_update(struct lnstat_file *lnstat_files);
+int lnstat_dump(FILE *outfd, struct lnstat_file *lnstat_files);
+struct lnstat_field *lnstat_find_field(struct lnstat_file *lnstat_files,
+ const char *name);
+#endif /* _LNSTAT_H */
diff --git a/misc/lnstat_util.c b/misc/lnstat_util.c
new file mode 100644
index 0000000..3f53e91
--- /dev/null
+++ b/misc/lnstat_util.c
@@ -0,0 +1,325 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* lnstat.c: Unified linux network statistics
+ *
+ * Copyright (C) 2004 by Harald Welte <laforge@gnumonks.org>
+ *
+ * Development of this code was funded by Astaro AG, http://www.astaro.com/
+ *
+ * Based on original concept and ideas from predecessor rtstat.c:
+ *
+ * Copyright 2001 by Robert Olsson <robert.olsson@its.uu.se>
+ * Uppsala University, Sweden
+ */
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <dirent.h>
+#include <limits.h>
+#include <time.h>
+
+#include <sys/time.h>
+#include <sys/types.h>
+
+#include "lnstat.h"
+
+/* size of temp buffer used to read lines from procfiles */
+#define FGETS_BUF_SIZE 1024
+
+
+#define RTSTAT_COMPAT_LINE "entries in_hit in_slow_tot in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"
+
+/* Read (and summarize for SMP) the different stats vars. */
+static int scan_lines(struct lnstat_file *lf, int i)
+{
+ char buf[FGETS_BUF_SIZE];
+ int j, num_lines = 0;
+
+ for (j = 0; j < lf->num_fields; j++)
+ lf->fields[j].values[i] = 0;
+
+ rewind(lf->fp);
+ /* skip first line */
+ if (!lf->compat && !fgets(buf, sizeof(buf)-1, lf->fp))
+ return -1;
+
+ while (!feof(lf->fp) && fgets(buf, sizeof(buf)-1, lf->fp)) {
+ char *ptr = buf;
+
+ num_lines++;
+
+ gettimeofday(&lf->last_read, NULL);
+
+ for (j = 0; j < lf->num_fields; j++) {
+ unsigned long f = strtoul(ptr, &ptr, 16);
+
+ if (j == 0)
+ lf->fields[j].values[i] = f;
+ else
+ lf->fields[j].values[i] += f;
+ }
+ }
+ return num_lines;
+}
+
+static int time_after(struct timeval *last,
+ struct timeval *tout,
+ struct timeval *now)
+{
+ if (now->tv_sec > last->tv_sec + tout->tv_sec)
+ return 1;
+
+ if (now->tv_sec == last->tv_sec + tout->tv_sec) {
+ if (now->tv_usec > last->tv_usec + tout->tv_usec)
+ return 1;
+ }
+
+ return 0;
+}
+
+int lnstat_update(struct lnstat_file *lnstat_files)
+{
+ struct lnstat_file *lf;
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ if (time_after(&lf->last_read, &lf->interval, &tv)) {
+ int i;
+ struct lnstat_field *lfi;
+
+ scan_lines(lf, 1);
+
+ for (i = 0, lfi = &lf->fields[i];
+ i < lf->num_fields; i++, lfi = &lf->fields[i]) {
+ if (i == 0)
+ lfi->result = lfi->values[1];
+ else
+ lfi->result = (lfi->values[1]-lfi->values[0])
+ / lf->interval.tv_sec;
+ }
+
+ scan_lines(lf, 0);
+ }
+ }
+
+ return 0;
+}
+
+/* scan first template line and fill in per-field data structures */
+static int __lnstat_scan_fields(struct lnstat_file *lf, char *buf)
+{
+ char *tok;
+ int i;
+
+ tok = strtok(buf, " \t\n");
+ for (i = 0; i < LNSTAT_MAX_FIELDS_PER_LINE; i++) {
+ lf->fields[i].file = lf;
+ strncpy(lf->fields[i].name, tok, LNSTAT_MAX_FIELD_NAME_LEN);
+ /* has to be null-terminate since we initialize to zero
+ * and field size is NAME_LEN + 1 */
+ tok = strtok(NULL, " \t\n");
+ if (!tok) {
+ lf->num_fields = i+1;
+ return 0;
+ }
+ }
+ return 0;
+}
+
+static int lnstat_scan_fields(struct lnstat_file *lf)
+{
+ char buf[FGETS_BUF_SIZE];
+
+ rewind(lf->fp);
+ if (!fgets(buf, sizeof(buf)-1, lf->fp))
+ return -1;
+
+ return __lnstat_scan_fields(lf, buf);
+}
+
+/* fake function emulating lnstat_scan_fields() for old kernels */
+static int lnstat_scan_compat_rtstat_fields(struct lnstat_file *lf)
+{
+ char buf[FGETS_BUF_SIZE];
+
+ strncpy(buf, RTSTAT_COMPAT_LINE, sizeof(buf) - 1);
+ buf[sizeof(buf) - 1] = '\0';
+
+ return __lnstat_scan_fields(lf, buf);
+}
+
+/* find out whether string 'name; is in given string array */
+static int name_in_array(const int num, const char **arr, const char *name)
+{
+ int i;
+
+ for (i = 0; i < num; i++) {
+ if (!strcmp(arr[i], name))
+ return 1;
+ }
+ return 0;
+}
+
+/* allocate lnstat_file and open given file */
+static struct lnstat_file *alloc_and_open(const char *path, const char *file)
+{
+ struct lnstat_file *lf;
+
+ /* allocate */
+ lf = calloc(1, sizeof(*lf));
+ if (!lf) {
+ fprintf(stderr, "out of memory\n");
+ return NULL;
+ }
+
+ /* initialize */
+ snprintf(lf->basename, sizeof(lf->basename), "%s", file);
+ snprintf(lf->path, sizeof(lf->path), "%s/%s", path, file);
+
+ /* initialize to default */
+ lf->interval.tv_sec = 1;
+
+ /* open */
+ lf->fp = fopen(lf->path, "r");
+ if (!lf->fp) {
+ perror(lf->path);
+ free(lf);
+ return NULL;
+ }
+
+ return lf;
+}
+
+
+/* lnstat_scan_dir - find and parse all available statistics files/fields */
+struct lnstat_file *lnstat_scan_dir(const char *path, const int num_req_files,
+ const char **req_files)
+{
+ DIR *dir;
+ struct lnstat_file *lnstat_files = NULL;
+ struct dirent *de;
+
+ if (!path)
+ path = PROC_NET_STAT;
+
+ dir = opendir(path);
+ if (!dir) {
+ struct lnstat_file *lf;
+ /* Old kernel, before /proc/net/stat was introduced */
+ fprintf(stderr, "Your kernel doesn't have lnstat support. ");
+
+ /* we only support rtstat, not multiple files */
+ if (num_req_files >= 2) {
+ fputc('\n', stderr);
+ return NULL;
+ }
+
+ /* we really only accept rt_cache */
+ if (num_req_files && !name_in_array(num_req_files,
+ req_files, "rt_cache")) {
+ fputc('\n', stderr);
+ return NULL;
+ }
+
+ fprintf(stderr, "Fallback to old rtstat-only operation\n");
+
+ lf = alloc_and_open("/proc/net", "rt_cache_stat");
+ if (!lf)
+ return NULL;
+ lf->compat = 1;
+ strncpy(lf->basename, "rt_cache", sizeof(lf->basename));
+
+ /* FIXME: support for old files */
+ if (lnstat_scan_compat_rtstat_fields(lf) < 0)
+ return NULL;
+
+ lf->next = lnstat_files;
+ lnstat_files = lf;
+ return lnstat_files;
+ }
+
+ while ((de = readdir(dir))) {
+ struct lnstat_file *lf;
+
+ if (de->d_type != DT_REG)
+ continue;
+
+ if (num_req_files && !name_in_array(num_req_files,
+ req_files, de->d_name))
+ continue;
+
+ lf = alloc_and_open(path, de->d_name);
+ if (!lf) {
+ closedir(dir);
+ return NULL;
+ }
+
+ /* fill in field structure */
+ if (lnstat_scan_fields(lf) < 0) {
+ closedir(dir);
+ return NULL;
+ }
+
+ /* prepend to global list */
+ lf->next = lnstat_files;
+ lnstat_files = lf;
+ }
+ closedir(dir);
+
+ return lnstat_files;
+}
+
+int lnstat_dump(FILE *outfd, struct lnstat_file *lnstat_files)
+{
+ struct lnstat_file *lf;
+
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ int i;
+
+ fprintf(outfd, "%s:\n", lf->path);
+
+ for (i = 0; i < lf->num_fields; i++)
+ fprintf(outfd, "\t%2u: %s\n", i+1, lf->fields[i].name);
+
+ }
+ return 0;
+}
+
+struct lnstat_field *lnstat_find_field(struct lnstat_file *lnstat_files,
+ const char *name)
+{
+ struct lnstat_file *lf;
+ struct lnstat_field *ret = NULL;
+ const char *colon = strchr(name, ':');
+ char *file;
+ const char *field;
+
+ if (colon) {
+ file = strndup(name, colon-name);
+ field = colon+1;
+ } else {
+ file = NULL;
+ field = name;
+ }
+
+ for (lf = lnstat_files; lf; lf = lf->next) {
+ int i;
+
+ if (file && strcmp(file, lf->basename))
+ continue;
+
+ for (i = 0; i < lf->num_fields; i++) {
+ if (!strcmp(field, lf->fields[i].name)) {
+ ret = &lf->fields[i];
+ goto out;
+ }
+ }
+ }
+out:
+ free(file);
+
+ return ret;
+}
diff --git a/misc/nstat.c b/misc/nstat.c
new file mode 100644
index 0000000..2c10fea
--- /dev/null
+++ b/misc/nstat.c
@@ -0,0 +1,776 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * nstat.c handy utility to read counters /proc/net/netstat and snmp
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <fnmatch.h>
+#include <sys/file.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/poll.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <signal.h>
+#include <math.h>
+#include <getopt.h>
+
+#include <json_writer.h>
+#include "version.h"
+#include "utils.h"
+
+int dump_zeros;
+int reset_history;
+int ignore_history;
+int no_output;
+int json_output;
+int no_update;
+int scan_interval;
+int time_constant;
+double W;
+char **patterns;
+int npatterns;
+
+char info_source[128];
+int source_mismatch;
+
+static int generic_proc_open(const char *env, char *name)
+{
+ char store[128];
+ char *p = getenv(env);
+
+ if (!p) {
+ p = getenv("PROC_ROOT") ? : "/proc";
+ snprintf(store, sizeof(store)-1, "%s/%s", p, name);
+ p = store;
+ }
+ return open(p, O_RDONLY);
+}
+
+static int net_netstat_open(void)
+{
+ return generic_proc_open("PROC_NET_NETSTAT", "net/netstat");
+}
+
+static int net_snmp_open(void)
+{
+ return generic_proc_open("PROC_NET_SNMP", "net/snmp");
+}
+
+static int net_snmp6_open(void)
+{
+ return generic_proc_open("PROC_NET_SNMP6", "net/snmp6");
+}
+
+static int net_sctp_snmp_open(void)
+{
+ return generic_proc_open("PROC_NET_SCTP_SNMP", "net/sctp/snmp");
+}
+
+struct nstat_ent {
+ struct nstat_ent *next;
+ char *id;
+ unsigned long long val;
+ double rate;
+};
+
+struct nstat_ent *kern_db;
+struct nstat_ent *hist_db;
+
+static const char *useless_numbers[] = {
+ "IpForwarding", "IpDefaultTTL",
+ "TcpRtoAlgorithm", "TcpRtoMin", "TcpRtoMax",
+ "TcpMaxConn", "TcpCurrEstab"
+};
+
+static int useless_number(const char *id)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(useless_numbers); i++)
+ if (strcmp(id, useless_numbers[i]) == 0)
+ return 1;
+ return 0;
+}
+
+static int match(const char *id)
+{
+ int i;
+
+ if (npatterns == 0)
+ return 1;
+
+ for (i = 0; i < npatterns; i++) {
+ if (!fnmatch(patterns[i], id, FNM_CASEFOLD))
+ return 1;
+ }
+ return 0;
+}
+
+static void load_good_table(FILE *fp)
+{
+ char buf[4096];
+ struct nstat_ent *db = NULL;
+ struct nstat_ent *n;
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ int nr;
+ unsigned long long val;
+ double rate;
+ char idbuf[sizeof(buf)];
+
+ if (buf[0] == '#') {
+ buf[strlen(buf)-1] = 0;
+ if (info_source[0] && strcmp(info_source, buf+1))
+ source_mismatch = 1;
+ strlcpy(info_source, buf + 1, sizeof(info_source));
+ continue;
+ }
+ /* idbuf is as big as buf, so this is safe */
+ nr = sscanf(buf, "%s%llu%lg", idbuf, &val, &rate);
+ if (nr < 2) {
+ fprintf(stderr, "%s:%d: error parsing history file\n",
+ __FILE__, __LINE__);
+ exit(-2);
+ }
+ if (nr < 3)
+ rate = 0;
+ if (useless_number(idbuf))
+ continue;
+ if ((n = malloc(sizeof(*n))) == NULL) {
+ perror("nstat: malloc");
+ exit(-1);
+ }
+ n->id = strdup(idbuf);
+ n->val = val;
+ n->rate = rate;
+ n->next = db;
+ db = n;
+ }
+
+ while (db) {
+ n = db;
+ db = db->next;
+ n->next = kern_db;
+ kern_db = n;
+ }
+}
+
+static int count_spaces(const char *line)
+{
+ int count = 0;
+ char c;
+
+ while ((c = *line++) != 0)
+ count += c == ' ' || c == '\n';
+ return count;
+}
+
+static void load_ugly_table(FILE *fp)
+{
+ char *buf = NULL;
+ size_t buflen = 0;
+ ssize_t nread;
+ struct nstat_ent *db = NULL;
+ struct nstat_ent *n;
+
+ while ((nread = getline(&buf, &buflen, fp)) != -1) {
+ char idbuf[4096];
+ int off;
+ char *p;
+ int count1, count2, skip = 0;
+
+ p = strchr(buf, ':');
+ if (!p) {
+ fprintf(stderr, "%s:%d: error parsing history file\n",
+ __FILE__, __LINE__);
+ exit(-2);
+ }
+ count1 = count_spaces(buf);
+ *p = 0;
+ idbuf[0] = 0;
+ strncat(idbuf, buf, sizeof(idbuf) - 1);
+ off = p - buf;
+ p += 2;
+
+ while (*p) {
+ char *next;
+
+ if ((next = strchr(p, ' ')) != NULL)
+ *next++ = 0;
+ else if ((next = strchr(p, '\n')) != NULL)
+ *next++ = 0;
+ if (off < sizeof(idbuf)) {
+ idbuf[off] = 0;
+ strncat(idbuf, p, sizeof(idbuf) - off - 1);
+ }
+ n = malloc(sizeof(*n));
+ if (!n) {
+ perror("nstat: malloc");
+ exit(-1);
+ }
+ n->id = strdup(idbuf);
+ if (n->id == NULL) {
+ perror("nstat: strdup");
+ exit(-1);
+ }
+ n->rate = 0;
+ n->next = db;
+ db = n;
+ if (next == NULL)
+ break;
+ p = next;
+ }
+ n = db;
+ nread = getline(&buf, &buflen, fp);
+ if (nread == -1) {
+ fprintf(stderr, "%s:%d: error parsing history file\n",
+ __FILE__, __LINE__);
+ exit(-2);
+ }
+ count2 = count_spaces(buf);
+ if (count2 > count1)
+ skip = count2 - count1;
+ do {
+ p = strrchr(buf, ' ');
+ if (!p) {
+ fprintf(stderr, "%s:%d: error parsing history file\n",
+ __FILE__, __LINE__);
+ exit(-2);
+ }
+ *p = 0;
+ if (sscanf(p+1, "%llu", &n->val) != 1) {
+ fprintf(stderr, "%s:%d: error parsing history file\n",
+ __FILE__, __LINE__);
+ exit(-2);
+ }
+ /* Trick to skip "dummy" trailing ICMP MIB in 2.4 */
+ if (skip)
+ skip--;
+ else
+ n = n->next;
+ } while (p > buf + off + 2);
+ }
+ free(buf);
+
+ while (db) {
+ n = db;
+ db = db->next;
+ if (useless_number(n->id)) {
+ free(n->id);
+ free(n);
+ } else {
+ n->next = kern_db;
+ kern_db = n;
+ }
+ }
+}
+
+static void load_sctp_snmp(void)
+{
+ FILE *fp = fdopen(net_sctp_snmp_open(), "r");
+
+ if (fp) {
+ load_good_table(fp);
+ fclose(fp);
+ }
+}
+
+static void load_snmp(void)
+{
+ FILE *fp = fdopen(net_snmp_open(), "r");
+
+ if (fp) {
+ load_ugly_table(fp);
+ fclose(fp);
+ }
+}
+
+static void load_snmp6(void)
+{
+ FILE *fp = fdopen(net_snmp6_open(), "r");
+
+ if (fp) {
+ load_good_table(fp);
+ fclose(fp);
+ }
+}
+
+static void load_netstat(void)
+{
+ FILE *fp = fdopen(net_netstat_open(), "r");
+
+ if (fp) {
+ load_ugly_table(fp);
+ fclose(fp);
+ }
+}
+
+
+static void dump_kern_db(FILE *fp, int to_hist)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct nstat_ent *n, *h;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_start_object(jw);
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ fprintf(fp, "#%s\n", info_source);
+
+ for (n = kern_db; n; n = n->next) {
+ unsigned long long val = n->val;
+
+ if (!dump_zeros && !val && !n->rate)
+ continue;
+ if (!match(n->id)) {
+ struct nstat_ent *h1;
+
+ if (!to_hist)
+ continue;
+ for (h1 = h; h1; h1 = h1->next) {
+ if (strcmp(h1->id, n->id) == 0) {
+ val = h1->val;
+ h = h1->next;
+ break;
+ }
+ }
+ }
+
+ if (jw)
+ jsonw_uint_field(jw, n->id, val);
+ else
+ fprintf(fp, "%-32s%-16llu%6.1f\n", n->id, val, n->rate);
+ }
+
+ if (jw) {
+ jsonw_end_object(jw);
+
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+static void dump_incr_db(FILE *fp)
+{
+ json_writer_t *jw = json_output ? jsonw_new(fp) : NULL;
+ struct nstat_ent *n, *h;
+
+ h = hist_db;
+ if (jw) {
+ jsonw_start_object(jw);
+ jsonw_pretty(jw, pretty);
+ jsonw_name(jw, info_source);
+ jsonw_start_object(jw);
+ } else
+ fprintf(fp, "#%s\n", info_source);
+
+ for (n = kern_db; n; n = n->next) {
+ int ovfl = 0;
+ unsigned long long val = n->val;
+ struct nstat_ent *h1;
+
+ for (h1 = h; h1; h1 = h1->next) {
+ if (strcmp(h1->id, n->id) == 0) {
+ if (val < h1->val) {
+ ovfl = 1;
+ val = h1->val;
+ }
+ val -= h1->val;
+ h = h1->next;
+ break;
+ }
+ }
+ if (!dump_zeros && !val && !n->rate)
+ continue;
+ if (!match(n->id))
+ continue;
+
+ if (jw)
+ jsonw_uint_field(jw, n->id, val);
+ else
+ fprintf(fp, "%-32s%-16llu%6.1f%s\n", n->id, val,
+ n->rate, ovfl?" (overflow)":"");
+ }
+
+ if (jw) {
+ jsonw_end_object(jw);
+
+ jsonw_end_object(jw);
+ jsonw_destroy(&jw);
+ }
+}
+
+static int children;
+
+static void sigchild(int signo)
+{
+}
+
+static void update_db(int interval)
+{
+ struct nstat_ent *n, *h;
+
+ n = kern_db;
+ kern_db = NULL;
+
+ load_netstat();
+ load_snmp6();
+ load_snmp();
+ load_sctp_snmp();
+
+ h = kern_db;
+ kern_db = n;
+
+ for (n = kern_db; n; n = n->next) {
+ struct nstat_ent *h1;
+
+ for (h1 = h; h1; h1 = h1->next) {
+ if (strcmp(h1->id, n->id) == 0) {
+ double sample;
+ unsigned long long incr = h1->val - n->val;
+
+ n->val = h1->val;
+ sample = (double)incr * 1000.0 / interval;
+ if (interval >= scan_interval) {
+ n->rate += W*(sample-n->rate);
+ } else if (interval >= 1000) {
+ if (interval >= time_constant) {
+ n->rate = sample;
+ } else {
+ double w = W*(double)interval/scan_interval;
+
+ n->rate += w*(sample-n->rate);
+ }
+ }
+
+ while (h != h1) {
+ struct nstat_ent *tmp = h;
+
+ h = h->next;
+ free(tmp->id);
+ free(tmp);
+ };
+ h = h1->next;
+ free(h1->id);
+ free(h1);
+ break;
+ }
+ }
+ }
+}
+
+#define T_DIFF(a, b) (((a).tv_sec-(b).tv_sec)*1000 + ((a).tv_usec-(b).tv_usec)/1000)
+
+
+static void server_loop(int fd)
+{
+ struct timeval snaptime = { 0 };
+ struct pollfd p;
+
+ p.fd = fd;
+ p.events = p.revents = POLLIN;
+
+ sprintf(info_source, "%d.%lu sampling_interval=%d time_const=%d",
+ getpid(), (unsigned long)random(), scan_interval/1000, time_constant/1000);
+
+ load_netstat();
+ load_snmp6();
+ load_snmp();
+ load_sctp_snmp();
+
+ for (;;) {
+ int status;
+ time_t tdiff;
+ struct timeval now;
+
+ gettimeofday(&now, NULL);
+ tdiff = T_DIFF(now, snaptime);
+ if (tdiff >= scan_interval) {
+ update_db(tdiff);
+ snaptime = now;
+ tdiff = 0;
+ }
+ if (poll(&p, 1, scan_interval - tdiff) > 0
+ && (p.revents&POLLIN)) {
+ int clnt = accept(fd, NULL, NULL);
+
+ if (clnt >= 0) {
+ pid_t pid;
+
+ if (children >= 5) {
+ close(clnt);
+ } else if ((pid = fork()) != 0) {
+ if (pid > 0)
+ children++;
+ close(clnt);
+ } else {
+ FILE *fp = fdopen(clnt, "w");
+
+ if (fp)
+ dump_kern_db(fp, 0);
+ exit(0);
+ }
+ }
+ }
+ while (children && waitpid(-1, &status, WNOHANG) > 0)
+ children--;
+ }
+}
+
+static int verify_forging(int fd)
+{
+ struct ucred cred;
+ socklen_t olen = sizeof(cred);
+
+ if (getsockopt(fd, SOL_SOCKET, SO_PEERCRED, (void *)&cred, &olen) ||
+ olen < sizeof(cred))
+ return -1;
+ if (cred.uid == getuid() || cred.uid == 0)
+ return 0;
+ return -1;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+ "Usage: nstat [OPTION] [ PATTERN [ PATTERN ] ]\n"
+ " -h, --help this message\n"
+ " -a, --ignore ignore history\n"
+ " -d, --scan=SECS sample every statistics every SECS\n"
+ " -j, --json format output in JSON\n"
+ " -n, --nooutput do history only\n"
+ " -p, --pretty pretty print\n"
+ " -r, --reset reset history\n"
+ " -s, --noupdate don't update history\n"
+ " -t, --interval=SECS report average over the last SECS\n"
+ " -V, --version output version information\n"
+ " -z, --zeros show entries with zero activity\n");
+ exit(-1);
+}
+
+static const struct option longopts[] = {
+ { "help", 0, 0, 'h' },
+ { "ignore", 0, 0, 'a' },
+ { "scan", 1, 0, 'd'},
+ { "nooutput", 0, 0, 'n' },
+ { "json", 0, 0, 'j' },
+ { "reset", 0, 0, 'r' },
+ { "noupdate", 0, 0, 's' },
+ { "pretty", 0, 0, 'p' },
+ { "interval", 1, 0, 't' },
+ { "version", 0, 0, 'V' },
+ { "zeros", 0, 0, 'z' },
+ { 0 }
+};
+
+int main(int argc, char *argv[])
+{
+ char *hist_name;
+ struct sockaddr_un sun;
+ FILE *hist_fp = NULL;
+ int ch;
+ int fd;
+
+ while ((ch = getopt_long(argc, argv, "h?vVzrnasd:t:jp",
+ longopts, NULL)) != EOF) {
+ switch (ch) {
+ case 'z':
+ dump_zeros = 1;
+ break;
+ case 'r':
+ reset_history = 1;
+ break;
+ case 'a':
+ ignore_history = 1;
+ break;
+ case 's':
+ no_update = 1;
+ break;
+ case 'n':
+ no_output = 1;
+ break;
+ case 'd':
+ scan_interval = 1000*atoi(optarg);
+ break;
+ case 't':
+ if (sscanf(optarg, "%d", &time_constant) != 1 ||
+ time_constant <= 0) {
+ fprintf(stderr, "nstat: invalid time constant divisor\n");
+ exit(-1);
+ }
+ break;
+ case 'j':
+ json_output = 1;
+ break;
+ case 'p':
+ pretty = 1;
+ break;
+ case 'v':
+ case 'V':
+ printf("nstat utility, iproute2-%s\n", version);
+ exit(0);
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ sun.sun_family = AF_UNIX;
+ sun.sun_path[0] = 0;
+ sprintf(sun.sun_path+1, "nstat%d", getuid());
+
+ if (scan_interval > 0) {
+ if (time_constant == 0)
+ time_constant = 60;
+ time_constant *= 1000;
+ W = 1 - 1/exp(log(10)*(double)scan_interval/time_constant);
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
+ perror("nstat: socket");
+ exit(-1);
+ }
+ if (bind(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) < 0) {
+ perror("nstat: bind");
+ exit(-1);
+ }
+ if (listen(fd, 5) < 0) {
+ perror("nstat: listen");
+ exit(-1);
+ }
+ if (daemon(0, 0)) {
+ perror("nstat: daemon");
+ exit(-1);
+ }
+ signal(SIGPIPE, SIG_IGN);
+ signal(SIGCHLD, sigchild);
+ server_loop(fd);
+ exit(0);
+ }
+
+ patterns = argv;
+ npatterns = argc;
+
+ if ((hist_name = getenv("NSTAT_HISTORY")) == NULL) {
+ hist_name = malloc(128);
+ sprintf(hist_name, "/tmp/.nstat.u%d", getuid());
+ }
+
+ if (reset_history)
+ unlink(hist_name);
+
+ if (!ignore_history || !no_update) {
+ struct stat stb;
+
+ fd = open(hist_name, O_RDWR|O_CREAT|O_NOFOLLOW, 0600);
+ if (fd < 0) {
+ perror("nstat: open history file");
+ exit(-1);
+ }
+ if ((hist_fp = fdopen(fd, "r+")) == NULL) {
+ perror("nstat: fdopen history file");
+ exit(-1);
+ }
+ if (flock(fileno(hist_fp), LOCK_EX)) {
+ perror("nstat: flock history file");
+ exit(-1);
+ }
+ if (fstat(fileno(hist_fp), &stb) != 0) {
+ perror("nstat: fstat history file");
+ exit(-1);
+ }
+ if (stb.st_nlink != 1 || stb.st_uid != getuid()) {
+ fprintf(stderr, "nstat: something is so wrong with history file, that I prefer not to proceed.\n");
+ exit(-1);
+ }
+ if (!ignore_history) {
+ FILE *tfp;
+ long uptime = -1;
+
+ if ((tfp = fopen("/proc/uptime", "r")) != NULL) {
+ if (fscanf(tfp, "%ld", &uptime) != 1)
+ uptime = -1;
+ fclose(tfp);
+ }
+ if (uptime >= 0 && time(NULL) >= stb.st_mtime+uptime) {
+ fprintf(stderr, "nstat: history is aged out, resetting\n");
+ if (ftruncate(fileno(hist_fp), 0) < 0)
+ perror("nstat: ftruncate");
+ }
+ }
+
+ load_good_table(hist_fp);
+
+ hist_db = kern_db;
+ kern_db = NULL;
+ }
+
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) >= 0 &&
+ (connect(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) == 0
+ || (strcpy(sun.sun_path+1, "nstat0"),
+ connect(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) == 0))
+ && verify_forging(fd) == 0) {
+ FILE *sfp = fdopen(fd, "r");
+
+ if (!sfp) {
+ fprintf(stderr, "nstat: fdopen failed: %s\n",
+ strerror(errno));
+ close(fd);
+ } else {
+ load_good_table(sfp);
+ if (hist_db && source_mismatch) {
+ fprintf(stderr, "nstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+ fclose(sfp);
+ }
+ } else {
+ if (fd >= 0)
+ close(fd);
+ if (hist_db && info_source[0] && strcmp(info_source, "kernel")) {
+ fprintf(stderr, "nstat: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ info_source[0] = 0;
+ }
+ load_netstat();
+ load_snmp6();
+ load_snmp();
+ load_sctp_snmp();
+ if (info_source[0] == 0)
+ strcpy(info_source, "kernel");
+ }
+
+ if (!no_output) {
+ if (ignore_history || hist_db == NULL)
+ dump_kern_db(stdout, 0);
+ else
+ dump_incr_db(stdout);
+ }
+ if (!no_update) {
+ if (ftruncate(fileno(hist_fp), 0) < 0)
+ perror("nstat: ftruncate");
+ rewind(hist_fp);
+
+ json_output = 0;
+ dump_kern_db(hist_fp, 1);
+ fclose(hist_fp);
+ }
+ exit(0);
+}
diff --git a/misc/rtacct.c b/misc/rtacct.c
new file mode 100644
index 0000000..08363bf
--- /dev/null
+++ b/misc/rtacct.c
@@ -0,0 +1,622 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * rtacct.c Applet to display contents of /proc/net/rt_acct.
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <sys/file.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/poll.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <math.h>
+
+#include "rt_names.h"
+
+#include "version.h"
+
+int reset_history;
+int ignore_history;
+int no_output;
+int no_update;
+int scan_interval;
+int time_constant;
+int dump_zeros;
+unsigned long magic_number;
+double W;
+
+static int generic_proc_open(const char *env, const char *name)
+{
+ char store[1024];
+ char *p = getenv(env);
+
+ if (!p) {
+ p = getenv("PROC_ROOT") ? : "/proc";
+ snprintf(store, sizeof(store)-1, "%s/%s", p, name);
+ p = store;
+ }
+ return open(p, O_RDONLY);
+}
+
+static int net_rtacct_open(void)
+{
+ return generic_proc_open("PROC_NET_RTACCT", "net/rt_acct");
+}
+
+static __u32 rmap[256/4];
+
+struct rtacct_data {
+ __u32 ival[256*4];
+
+ unsigned long long val[256*4];
+ double rate[256*4];
+ char signature[128];
+};
+
+static struct rtacct_data kern_db_static;
+
+static struct rtacct_data *kern_db = &kern_db_static;
+static struct rtacct_data *hist_db;
+
+static void nread(int fd, char *buf, int tot)
+{
+ int count = 0;
+
+ while (count < tot) {
+ int n = read(fd, buf+count, tot-count);
+
+ if (n < 0) {
+ if (errno == EINTR)
+ continue;
+ exit(-1);
+ }
+ if (n == 0)
+ exit(-1);
+ count += n;
+ }
+}
+
+static __u32 *read_kern_table(__u32 *tbl)
+{
+ static __u32 *tbl_ptr;
+ int fd;
+
+ if (magic_number) {
+ if (tbl_ptr != NULL)
+ return tbl_ptr;
+
+ fd = open("/dev/mem", O_RDONLY);
+ if (fd < 0) {
+ perror("magic open");
+ exit(-1);
+ }
+ tbl_ptr = mmap(NULL, 4096,
+ PROT_READ,
+ MAP_SHARED,
+ fd, magic_number);
+ if ((unsigned long)tbl_ptr == ~0UL) {
+ perror("magic mmap");
+ exit(-1);
+ }
+ close(fd);
+ return tbl_ptr;
+ }
+
+ fd = net_rtacct_open();
+ if (fd >= 0) {
+ nread(fd, (char *)tbl, 256*16);
+ close(fd);
+ } else {
+ memset(tbl, 0, 256*16);
+ }
+ return tbl;
+}
+
+static void format_rate(FILE *fp, double rate)
+{
+ char temp[64];
+
+ if (rate > 1024*1024) {
+ sprintf(temp, "%uM", (unsigned int)rint(rate/(1024*1024)));
+ fprintf(fp, " %-10s", temp);
+ } else if (rate > 1024) {
+ sprintf(temp, "%uK", (unsigned int)rint(rate/1024));
+ fprintf(fp, " %-10s", temp);
+ } else
+ fprintf(fp, " %-10u", (unsigned int)rate);
+}
+
+static void format_count(FILE *fp, unsigned long long val)
+{
+ if (val > 1024*1024*1024)
+ fprintf(fp, " %10lluM", val/(1024*1024));
+ else if (val > 1024*1024)
+ fprintf(fp, " %10lluK", val/1024);
+ else
+ fprintf(fp, " %10llu", val);
+}
+
+static void dump_abs_db(FILE *fp)
+{
+ int realm;
+ char b1[16];
+
+ if (!no_output) {
+ fprintf(fp, "#%s\n", kern_db->signature);
+ fprintf(fp,
+"%-10s %-10s "
+"%-10s %-10s "
+"%-10s \n"
+ , "Realm", "BytesTo", "PktsTo", "BytesFrom", "PktsFrom");
+ fprintf(fp,
+"%-10s %-10s "
+"%-10s %-10s "
+"%-10s \n"
+ , "", "BPSTo", "PPSTo", "BPSFrom", "PPSFrom");
+
+ }
+
+ for (realm = 0; realm < 256; realm++) {
+ int i;
+ unsigned long long *val;
+ double *rate;
+
+ if (!(rmap[realm>>5] & (1<<(realm&0x1f))))
+ continue;
+
+ val = &kern_db->val[realm*4];
+ rate = &kern_db->rate[realm*4];
+
+ if (!dump_zeros &&
+ !val[0] && !rate[0] &&
+ !val[1] && !rate[1] &&
+ !val[2] && !rate[2] &&
+ !val[3] && !rate[3])
+ continue;
+
+ if (hist_db) {
+ memcpy(&hist_db->val[realm*4], val, sizeof(*val)*4);
+ }
+
+ if (no_output)
+ continue;
+
+ fprintf(fp, "%-10s", rtnl_rtrealm_n2a(realm, b1, sizeof(b1)));
+ for (i = 0; i < 4; i++)
+ format_count(fp, val[i]);
+ fprintf(fp, "\n%-10s", "");
+ for (i = 0; i < 4; i++)
+ format_rate(fp, rate[i]);
+ fprintf(fp, "\n");
+ }
+}
+
+
+static void dump_incr_db(FILE *fp)
+{
+ int k, realm;
+ char b1[16];
+
+ if (!no_output) {
+ fprintf(fp, "#%s\n", kern_db->signature);
+ fprintf(fp,
+"%-10s %-10s "
+"%-10s %-10s "
+"%-10s \n"
+ , "Realm", "BytesTo", "PktsTo", "BytesFrom", "PktsFrom");
+ fprintf(fp,
+"%-10s %-10s "
+"%-10s %-10s "
+"%-10s \n"
+ , "", "BPSTo", "PPSTo", "BPSFrom", "PPSFrom");
+ }
+
+ for (realm = 0; realm < 256; realm++) {
+ int ovfl = 0;
+ int i;
+ unsigned long long *val;
+ double *rate;
+ unsigned long long rval[4];
+
+ if (!(rmap[realm>>5] & (1<<(realm&0x1f))))
+ continue;
+
+ val = &kern_db->val[realm*4];
+ rate = &kern_db->rate[realm*4];
+
+ for (k = 0; k < 4; k++) {
+ rval[k] = val[k];
+ if (rval[k] < hist_db->val[realm*4+k])
+ ovfl = 1;
+ else
+ rval[k] -= hist_db->val[realm*4+k];
+ }
+ if (ovfl) {
+ for (k = 0; k < 4; k++)
+ rval[k] = val[k];
+ }
+ if (hist_db) {
+ memcpy(&hist_db->val[realm*4], val, sizeof(*val)*4);
+ }
+
+ if (no_output)
+ continue;
+
+ if (!dump_zeros &&
+ !rval[0] && !rate[0] &&
+ !rval[1] && !rate[1] &&
+ !rval[2] && !rate[2] &&
+ !rval[3] && !rate[3])
+ continue;
+
+
+ fprintf(fp, "%-10s", rtnl_rtrealm_n2a(realm, b1, sizeof(b1)));
+ for (i = 0; i < 4; i++)
+ format_count(fp, rval[i]);
+ fprintf(fp, "\n%-10s", "");
+ for (i = 0; i < 4; i++)
+ format_rate(fp, rate[i]);
+ fprintf(fp, "\n");
+ }
+}
+
+
+static int children;
+
+static void sigchild(int signo)
+{
+}
+
+/* Server side only: read kernel data, update tables, calculate rates. */
+
+static void update_db(int interval)
+{
+ int i;
+ __u32 *ival;
+ __u32 _ival[256*4];
+
+ ival = read_kern_table(_ival);
+
+ for (i = 0; i < 256*4; i++) {
+ double sample;
+ __u32 incr = ival[i] - kern_db->ival[i];
+
+ if (ival[i] == 0 && incr == 0 &&
+ kern_db->val[i] == 0 && kern_db->rate[i] == 0)
+ continue;
+
+ kern_db->val[i] += incr;
+ kern_db->ival[i] = ival[i];
+ sample = (double)(incr*1000)/interval;
+ if (interval >= scan_interval) {
+ kern_db->rate[i] += W*(sample-kern_db->rate[i]);
+ } else if (interval >= 1000) {
+ if (interval >= time_constant) {
+ kern_db->rate[i] = sample;
+ } else {
+ double w = W*(double)interval/scan_interval;
+
+ kern_db->rate[i] += w*(sample-kern_db->rate[i]);
+ }
+ }
+ }
+}
+
+static void send_db(int fd)
+{
+ int tot = 0;
+
+ while (tot < sizeof(*kern_db)) {
+ int n = write(fd, ((char *)kern_db) + tot, sizeof(*kern_db)-tot);
+
+ if (n < 0) {
+ if (errno == EINTR)
+ continue;
+ return;
+ }
+ tot += n;
+ }
+}
+
+
+
+#define T_DIFF(a, b) (((a).tv_sec-(b).tv_sec)*1000 + ((a).tv_usec-(b).tv_usec)/1000)
+
+
+static void pad_kern_table(struct rtacct_data *dat, __u32 *ival)
+{
+ int i;
+
+ memset(dat->rate, 0, sizeof(dat->rate));
+ if (dat->ival != ival)
+ memcpy(dat->ival, ival, sizeof(dat->ival));
+ for (i = 0; i < 256*4; i++)
+ dat->val[i] = ival[i];
+}
+
+static void server_loop(int fd)
+{
+ struct timeval snaptime = { 0 };
+ struct pollfd p;
+
+ p.fd = fd;
+ p.events = p.revents = POLLIN;
+
+ sprintf(kern_db->signature,
+ "%u.%lu sampling_interval=%d time_const=%d",
+ (unsigned int) getpid(), (unsigned long)random(),
+ scan_interval/1000, time_constant/1000);
+
+ pad_kern_table(kern_db, read_kern_table(kern_db->ival));
+
+ for (;;) {
+ int status;
+ int tdiff;
+ struct timeval now;
+
+ gettimeofday(&now, NULL);
+ tdiff = T_DIFF(now, snaptime);
+ if (tdiff >= scan_interval) {
+ update_db(tdiff);
+ snaptime = now;
+ tdiff = 0;
+ }
+ if (poll(&p, 1, tdiff + scan_interval) > 0
+ && (p.revents&POLLIN)) {
+ int clnt = accept(fd, NULL, NULL);
+
+ if (clnt >= 0) {
+ pid_t pid;
+
+ if (children >= 5) {
+ close(clnt);
+ } else if ((pid = fork()) != 0) {
+ if (pid > 0)
+ children++;
+ close(clnt);
+ } else {
+ if (tdiff > 0)
+ update_db(tdiff);
+ send_db(clnt);
+ exit(0);
+ }
+ }
+ }
+ while (children && waitpid(-1, &status, WNOHANG) > 0)
+ children--;
+ }
+}
+
+static int verify_forging(int fd)
+{
+ struct ucred cred;
+ socklen_t olen = sizeof(cred);
+
+ if (getsockopt(fd, SOL_SOCKET, SO_PEERCRED, (void *)&cred, &olen) ||
+ olen < sizeof(cred))
+ return -1;
+ if (cred.uid == getuid() || cred.uid == 0)
+ return 0;
+ return -1;
+}
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+ fprintf(stderr,
+"Usage: rtacct [ -h?vVzrnasd:t: ] [ ListOfRealms ]\n"
+ );
+ exit(-1);
+}
+
+int main(int argc, char *argv[])
+{
+ char hist_name[128];
+ struct sockaddr_un sun;
+ int ch;
+ int fd;
+
+ while ((ch = getopt(argc, argv, "h?vVzrM:nasd:t:")) != EOF) {
+ switch (ch) {
+ case 'z':
+ dump_zeros = 1;
+ break;
+ case 'r':
+ reset_history = 1;
+ break;
+ case 'a':
+ ignore_history = 1;
+ break;
+ case 's':
+ no_update = 1;
+ break;
+ case 'n':
+ no_output = 1;
+ break;
+ case 'd':
+ scan_interval = 1000*atoi(optarg);
+ break;
+ case 't':
+ if (sscanf(optarg, "%d", &time_constant) != 1 ||
+ time_constant <= 0) {
+ fprintf(stderr, "rtacct: invalid time constant divisor\n");
+ exit(-1);
+ }
+ break;
+ case 'v':
+ case 'V':
+ printf("rtacct utility, iproute2-%s\n", version);
+ exit(0);
+ case 'M':
+ /* Some secret undocumented option, nobody
+ * is expected to ask about its sense. See?
+ */
+ sscanf(optarg, "%lx", &magic_number);
+ break;
+ case 'h':
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ if (argc) {
+ while (argc > 0) {
+ __u32 realm;
+
+ if (rtnl_rtrealm_a2n(&realm, argv[0])) {
+ fprintf(stderr, "Warning: realm \"%s\" does not exist.\n", argv[0]);
+ exit(-1);
+ }
+ rmap[realm>>5] |= (1<<(realm&0x1f));
+ argc--; argv++;
+ }
+ } else {
+ memset(rmap, ~0, sizeof(rmap));
+ /* Always suppress zeros. */
+ dump_zeros = 0;
+ }
+
+ sun.sun_family = AF_UNIX;
+ sun.sun_path[0] = 0;
+ sprintf(sun.sun_path+1, "rtacct%d", getuid());
+
+ if (scan_interval > 0) {
+ if (time_constant == 0)
+ time_constant = 60;
+ time_constant *= 1000;
+ W = 1 - 1/exp(log(10)*(double)scan_interval/time_constant);
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) < 0) {
+ perror("rtacct: socket");
+ exit(-1);
+ }
+ if (bind(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) < 0) {
+ perror("rtacct: bind");
+ exit(-1);
+ }
+ if (listen(fd, 5) < 0) {
+ perror("rtacct: listen");
+ exit(-1);
+ }
+ if (daemon(0, 0)) {
+ perror("rtacct: daemon");
+ exit(-1);
+ }
+ signal(SIGPIPE, SIG_IGN);
+ signal(SIGCHLD, sigchild);
+ server_loop(fd);
+ exit(0);
+ }
+
+ if (getenv("RTACCT_HISTORY"))
+ snprintf(hist_name, sizeof(hist_name), "%s", getenv("RTACCT_HISTORY"));
+ else
+ sprintf(hist_name, "/tmp/.rtacct.u%d", getuid());
+
+ if (reset_history)
+ unlink(hist_name);
+
+ if (!ignore_history || !no_update) {
+ struct stat stb;
+
+ fd = open(hist_name, O_RDWR|O_CREAT|O_NOFOLLOW, 0600);
+ if (fd < 0) {
+ perror("rtacct: open history file");
+ exit(-1);
+ }
+ if (flock(fd, LOCK_EX)) {
+ perror("rtacct: flock history file");
+ exit(-1);
+ }
+ if (fstat(fd, &stb) != 0) {
+ perror("rtacct: fstat history file");
+ exit(-1);
+ }
+ if (stb.st_nlink != 1 || stb.st_uid != getuid()) {
+ fprintf(stderr, "rtacct: something is so wrong with history file, that I prefer not to proceed.\n");
+ exit(-1);
+ }
+ if (stb.st_size != sizeof(*hist_db))
+ if (write(fd, kern_db, sizeof(*hist_db)) < 0) {
+ perror("rtacct: write history file");
+ exit(-1);
+ }
+
+ hist_db = mmap(NULL, sizeof(*hist_db),
+ PROT_READ|PROT_WRITE,
+ no_update ? MAP_PRIVATE : MAP_SHARED,
+ fd, 0);
+
+ if ((unsigned long)hist_db == ~0UL) {
+ perror("mmap");
+ exit(-1);
+ }
+
+ if (!ignore_history) {
+ FILE *tfp;
+ long uptime = -1;
+
+ if ((tfp = fopen("/proc/uptime", "r")) != NULL) {
+ if (fscanf(tfp, "%ld", &uptime) != 1)
+ uptime = -1;
+ fclose(tfp);
+ }
+
+ if (uptime >= 0 && time(NULL) >= stb.st_mtime+uptime) {
+ fprintf(stderr, "rtacct: history is aged out, resetting\n");
+ memset(hist_db, 0, sizeof(*hist_db));
+ }
+ }
+
+ close(fd);
+ }
+
+ if ((fd = socket(AF_UNIX, SOCK_STREAM, 0)) >= 0 &&
+ (connect(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) == 0
+ || (strcpy(sun.sun_path+1, "rtacct0"),
+ connect(fd, (struct sockaddr *)&sun, 2+1+strlen(sun.sun_path+1)) == 0))
+ && verify_forging(fd) == 0) {
+ nread(fd, (char *)kern_db, sizeof(*kern_db));
+ if (hist_db && hist_db->signature[0] &&
+ strcmp(kern_db->signature, hist_db->signature)) {
+ fprintf(stderr, "rtacct: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+ close(fd);
+ } else {
+ if (fd >= 0)
+ close(fd);
+
+ if (hist_db && hist_db->signature[0] &&
+ strcmp(hist_db->signature, "kernel")) {
+ fprintf(stderr, "rtacct: history is stale, ignoring it.\n");
+ hist_db = NULL;
+ }
+
+ pad_kern_table(kern_db, read_kern_table(kern_db->ival));
+ strcpy(kern_db->signature, "kernel");
+ }
+
+ if (ignore_history || hist_db == NULL)
+ dump_abs_db(stdout);
+ else
+ dump_incr_db(stdout);
+
+ exit(0);
+}
diff --git a/misc/ss.c b/misc/ss.c
new file mode 100644
index 0000000..fb560a5
--- /dev/null
+++ b/misc/ss.c
@@ -0,0 +1,5887 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * ss.c "sockstat", socket statistics
+ *
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/uio.h>
+#include <sys/sysmacros.h>
+#include <netinet/in.h>
+#include <string.h>
+#include <errno.h>
+#include <netdb.h>
+#include <arpa/inet.h>
+#include <dirent.h>
+#include <fnmatch.h>
+#include <getopt.h>
+#include <stdbool.h>
+#include <limits.h>
+#include <stdarg.h>
+#include <ctype.h>
+
+#include "ss_util.h"
+#include "utils.h"
+#include "ll_map.h"
+#include "libnetlink.h"
+#include "namespace.h"
+#include "version.h"
+#include "rt_names.h"
+#include "cg_map.h"
+#include "selinux.h"
+
+#include <linux/tcp.h>
+#include <linux/unix_diag.h>
+#include <linux/netdevice.h> /* for MAX_ADDR_LEN */
+#include <linux/filter.h>
+#include <linux/xdp_diag.h>
+#include <linux/packet_diag.h>
+#include <linux/netlink_diag.h>
+#include <linux/sctp.h>
+#include <linux/vm_sockets_diag.h>
+#include <linux/net.h>
+#include <linux/tipc.h>
+#include <linux/tipc_netlink.h>
+#include <linux/tipc_sockets_diag.h>
+#include <linux/tls.h>
+#include <linux/mptcp.h>
+
+#if HAVE_RPC
+#include <rpc/rpc.h>
+#include <rpc/xdr.h>
+#endif
+
+/* AF_VSOCK/PF_VSOCK is only provided since glibc 2.18 */
+#ifndef PF_VSOCK
+#define PF_VSOCK 40
+#endif
+#ifndef AF_VSOCK
+#define AF_VSOCK PF_VSOCK
+#endif
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+#define BUF_CHUNK (1024 * 1024) /* Buffer chunk allocation size */
+#define BUF_CHUNKS_MAX 5 /* Maximum number of allocated buffer chunks */
+#define LEN_ALIGN(x) (((x) + 1) & ~1)
+
+int preferred_family = AF_UNSPEC;
+static int show_options;
+int show_details;
+static int show_processes;
+static int show_threads;
+static int show_mem;
+static int show_tcpinfo;
+static int show_bpf;
+static int show_proc_ctx;
+static int show_sock_ctx;
+static int show_header = 1;
+static int follow_events;
+static int sctp_ino;
+static int show_tipcinfo;
+static int show_tos;
+static int show_cgroup;
+static int show_inet_sockopt;
+int oneline;
+
+enum col_id {
+ COL_NETID,
+ COL_STATE,
+ COL_RECVQ,
+ COL_SENDQ,
+ COL_ADDR,
+ COL_SERV,
+ COL_RADDR,
+ COL_RSERV,
+ COL_PROC,
+ COL_EXT,
+ COL_MAX
+};
+
+enum col_align {
+ ALIGN_LEFT,
+ ALIGN_CENTER,
+ ALIGN_RIGHT
+};
+
+struct column {
+ const enum col_align align;
+ const char *header;
+ const char *ldelim;
+ int disabled;
+ int width; /* Calculated, including additional layout spacing */
+ int max_len; /* Measured maximum field length in this column */
+};
+
+static struct column columns[] = {
+ { ALIGN_LEFT, "Netid", "", 0, 0, 0 },
+ { ALIGN_LEFT, "State", " ", 0, 0, 0 },
+ { ALIGN_LEFT, "Recv-Q", " ", 0, 0, 0 },
+ { ALIGN_LEFT, "Send-Q", " ", 0, 0, 0 },
+ { ALIGN_RIGHT, "Local Address:", " ", 0, 0, 0 },
+ { ALIGN_LEFT, "Port", "", 0, 0, 0 },
+ { ALIGN_RIGHT, "Peer Address:", " ", 0, 0, 0 },
+ { ALIGN_LEFT, "Port", "", 0, 0, 0 },
+ { ALIGN_LEFT, "Process", "", 0, 0, 0 },
+ { ALIGN_LEFT, "", "", 0, 0, 0 },
+};
+
+static struct column *current_field = columns;
+
+/* Output buffer: chained chunks of BUF_CHUNK bytes. Each field is written to
+ * the buffer as a variable size token. A token consists of a 16 bits length
+ * field, followed by a string which is not NULL-terminated.
+ *
+ * A new chunk is allocated and linked when the current chunk doesn't have
+ * enough room to store the current token as a whole.
+ */
+struct buf_chunk {
+ struct buf_chunk *next; /* Next chained chunk */
+ char *end; /* Current end of content */
+ char data[0];
+};
+
+struct buf_token {
+ uint16_t len; /* Data length, excluding length descriptor */
+ char data[0];
+};
+
+static struct {
+ struct buf_token *cur; /* Position of current token in chunk */
+ struct buf_chunk *head; /* First chunk */
+ struct buf_chunk *tail; /* Current chunk */
+ int chunks; /* Number of allocated chunks */
+} buffer;
+
+static const char *TCP_PROTO = "tcp";
+static const char *UDP_PROTO = "udp";
+#ifdef HAVE_RPC
+static const char *TCP6_PROTO = "tcp6";
+static const char *UDP6_PROTO = "udp6";
+static const char *SCTP_PROTO = "sctp";
+#endif
+static const char *RAW_PROTO = "raw";
+static const char *dg_proto;
+
+enum {
+ TCP_DB,
+ MPTCP_DB,
+ DCCP_DB,
+ UDP_DB,
+ RAW_DB,
+ UNIX_DG_DB,
+ UNIX_ST_DB,
+ UNIX_SQ_DB,
+ PACKET_DG_DB,
+ PACKET_R_DB,
+ NETLINK_DB,
+ SCTP_DB,
+ VSOCK_ST_DB,
+ VSOCK_DG_DB,
+ TIPC_DB,
+ XDP_DB,
+ MAX_DB
+};
+
+#define PACKET_DBM ((1<<PACKET_DG_DB)|(1<<PACKET_R_DB))
+#define UNIX_DBM ((1<<UNIX_DG_DB)|(1<<UNIX_ST_DB)|(1<<UNIX_SQ_DB))
+#define ALL_DB ((1<<MAX_DB)-1)
+#define INET_L4_DBM ((1<<TCP_DB)|(1<<MPTCP_DB)|(1<<UDP_DB)|(1<<DCCP_DB)|(1<<SCTP_DB))
+#define INET_DBM (INET_L4_DBM | (1<<RAW_DB))
+#define VSOCK_DBM ((1<<VSOCK_ST_DB)|(1<<VSOCK_DG_DB))
+
+enum {
+ SS_UNKNOWN,
+ SS_ESTABLISHED,
+ SS_SYN_SENT,
+ SS_SYN_RECV,
+ SS_FIN_WAIT1,
+ SS_FIN_WAIT2,
+ SS_TIME_WAIT,
+ SS_CLOSE,
+ SS_CLOSE_WAIT,
+ SS_LAST_ACK,
+ SS_LISTEN,
+ SS_CLOSING,
+ SS_NEW_SYN_RECV, /* Kernel only value, not for use in user space */
+ SS_BOUND_INACTIVE,
+ SS_MAX
+};
+
+enum {
+ SCTP_STATE_CLOSED = 0,
+ SCTP_STATE_COOKIE_WAIT = 1,
+ SCTP_STATE_COOKIE_ECHOED = 2,
+ SCTP_STATE_ESTABLISHED = 3,
+ SCTP_STATE_SHUTDOWN_PENDING = 4,
+ SCTP_STATE_SHUTDOWN_SENT = 5,
+ SCTP_STATE_SHUTDOWN_RECEIVED = 6,
+ SCTP_STATE_SHUTDOWN_ACK_SENT = 7,
+};
+
+#define SS_ALL ((1 << SS_MAX) - 1)
+#define SS_CONN (SS_ALL & ~((1<<SS_LISTEN)|(1<<SS_CLOSE)|(1<<SS_TIME_WAIT)|(1<<SS_SYN_RECV)))
+#define TIPC_SS_CONN ((1<<SS_ESTABLISHED)|(1<<SS_LISTEN)|(1<<SS_CLOSE))
+
+#include "ssfilter.h"
+
+struct filter {
+ int dbs;
+ int states;
+ uint64_t families;
+ struct ssfilter *f;
+ bool kill;
+ struct rtnl_handle *rth_for_killing;
+};
+
+#define FAMILY_MASK(family) ((uint64_t)1 << (family))
+
+static const struct filter default_dbs[MAX_DB] = {
+ [TCP_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
+ },
+ [MPTCP_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
+ },
+ [DCCP_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
+ },
+ [UDP_DB] = {
+ .states = (1 << SS_ESTABLISHED),
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
+ },
+ [RAW_DB] = {
+ .states = (1 << SS_ESTABLISHED),
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
+ },
+ [UNIX_DG_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = FAMILY_MASK(AF_UNIX),
+ },
+ [UNIX_ST_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_UNIX),
+ },
+ [UNIX_SQ_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_UNIX),
+ },
+ [PACKET_DG_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = FAMILY_MASK(AF_PACKET),
+ },
+ [PACKET_R_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = FAMILY_MASK(AF_PACKET),
+ },
+ [NETLINK_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = FAMILY_MASK(AF_NETLINK),
+ },
+ [SCTP_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
+ },
+ [VSOCK_ST_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_VSOCK),
+ },
+ [VSOCK_DG_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_VSOCK),
+ },
+ [TIPC_DB] = {
+ .states = TIPC_SS_CONN,
+ .families = FAMILY_MASK(AF_TIPC),
+ },
+ [XDP_DB] = {
+ .states = (1 << SS_CLOSE),
+ .families = FAMILY_MASK(AF_XDP),
+ },
+};
+
+static const struct filter default_afs[AF_MAX] = {
+ [AF_INET] = {
+ .dbs = INET_DBM,
+ .states = SS_CONN,
+ },
+ [AF_INET6] = {
+ .dbs = INET_DBM,
+ .states = SS_CONN,
+ },
+ [AF_UNIX] = {
+ .dbs = UNIX_DBM,
+ .states = SS_CONN,
+ },
+ [AF_PACKET] = {
+ .dbs = PACKET_DBM,
+ .states = (1 << SS_CLOSE),
+ },
+ [AF_NETLINK] = {
+ .dbs = (1 << NETLINK_DB),
+ .states = (1 << SS_CLOSE),
+ },
+ [AF_VSOCK] = {
+ .dbs = VSOCK_DBM,
+ .states = SS_CONN,
+ },
+ [AF_TIPC] = {
+ .dbs = (1 << TIPC_DB),
+ .states = TIPC_SS_CONN,
+ },
+ [AF_XDP] = {
+ .dbs = (1 << XDP_DB),
+ .states = (1 << SS_CLOSE),
+ },
+};
+
+static int do_default = 1;
+static struct filter current_filter;
+
+static void filter_db_set(struct filter *f, int db, bool enable)
+{
+ if (enable) {
+ f->states |= default_dbs[db].states;
+ f->dbs |= 1 << db;
+ } else {
+ f->dbs &= ~(1 << db);
+ }
+ do_default = 0;
+}
+
+static int filter_db_parse(struct filter *f, const char *s)
+{
+ const struct {
+ const char *name;
+ int dbs[MAX_DB + 1];
+ } db_name_tbl[] = {
+#define ENTRY(name, ...) { #name, { __VA_ARGS__, MAX_DB } }
+ ENTRY(all, UDP_DB, DCCP_DB, TCP_DB, MPTCP_DB, RAW_DB,
+ UNIX_ST_DB, UNIX_DG_DB, UNIX_SQ_DB,
+ PACKET_R_DB, PACKET_DG_DB, NETLINK_DB,
+ SCTP_DB, VSOCK_ST_DB, VSOCK_DG_DB, XDP_DB),
+ ENTRY(inet, UDP_DB, DCCP_DB, TCP_DB, MPTCP_DB, SCTP_DB, RAW_DB),
+ ENTRY(udp, UDP_DB),
+ ENTRY(dccp, DCCP_DB),
+ ENTRY(tcp, TCP_DB),
+ ENTRY(mptcp, MPTCP_DB),
+ ENTRY(sctp, SCTP_DB),
+ ENTRY(raw, RAW_DB),
+ ENTRY(unix, UNIX_ST_DB, UNIX_DG_DB, UNIX_SQ_DB),
+ ENTRY(unix_stream, UNIX_ST_DB),
+ ENTRY(u_str, UNIX_ST_DB), /* alias for unix_stream */
+ ENTRY(unix_dgram, UNIX_DG_DB),
+ ENTRY(u_dgr, UNIX_DG_DB), /* alias for unix_dgram */
+ ENTRY(unix_seqpacket, UNIX_SQ_DB),
+ ENTRY(u_seq, UNIX_SQ_DB), /* alias for unix_seqpacket */
+ ENTRY(packet, PACKET_R_DB, PACKET_DG_DB),
+ ENTRY(packet_raw, PACKET_R_DB),
+ ENTRY(p_raw, PACKET_R_DB), /* alias for packet_raw */
+ ENTRY(packet_dgram, PACKET_DG_DB),
+ ENTRY(p_dgr, PACKET_DG_DB), /* alias for packet_dgram */
+ ENTRY(netlink, NETLINK_DB),
+ ENTRY(tipc, TIPC_DB),
+ ENTRY(vsock, VSOCK_ST_DB, VSOCK_DG_DB),
+ ENTRY(vsock_stream, VSOCK_ST_DB),
+ ENTRY(v_str, VSOCK_ST_DB), /* alias for vsock_stream */
+ ENTRY(vsock_dgram, VSOCK_DG_DB),
+ ENTRY(v_dgr, VSOCK_DG_DB), /* alias for vsock_dgram */
+ ENTRY(xdp, XDP_DB),
+#undef ENTRY
+ };
+ bool enable = true;
+ unsigned int i;
+ const int *dbp;
+
+ if (s[0] == '!') {
+ enable = false;
+ s++;
+ }
+ for (i = 0; i < ARRAY_SIZE(db_name_tbl); i++) {
+ if (strcmp(s, db_name_tbl[i].name))
+ continue;
+ for (dbp = db_name_tbl[i].dbs; *dbp != MAX_DB; dbp++)
+ filter_db_set(f, *dbp, enable);
+ return 0;
+ }
+ return -1;
+}
+
+static void filter_af_set(struct filter *f, int af)
+{
+ f->states |= default_afs[af].states;
+ f->families |= FAMILY_MASK(af);
+ do_default = 0;
+ preferred_family = af;
+}
+
+static int filter_af_get(struct filter *f, int af)
+{
+ return !!(f->families & FAMILY_MASK(af));
+}
+
+static void filter_states_set(struct filter *f, int states)
+{
+ if (states)
+ f->states = states;
+}
+
+static void filter_merge_defaults(struct filter *f)
+{
+ int db;
+ int af;
+
+ for (db = 0; db < MAX_DB; db++) {
+ if (!(f->dbs & (1 << db)))
+ continue;
+
+ if (!(default_dbs[db].families & f->families))
+ f->families |= default_dbs[db].families;
+ }
+ for (af = 0; af < AF_MAX; af++) {
+ if (!(f->families & FAMILY_MASK(af)))
+ continue;
+
+ if (!(default_afs[af].dbs & f->dbs))
+ f->dbs |= default_afs[af].dbs;
+ }
+}
+
+static FILE *generic_proc_open(const char *env, const char *name)
+{
+ const char *p = getenv(env);
+ char store[128];
+
+ if (!p) {
+ p = getenv("PROC_ROOT") ? : "/proc";
+ snprintf(store, sizeof(store)-1, "%s/%s", p, name);
+ p = store;
+ }
+
+ return fopen(p, "r");
+}
+#define net_tcp_open() generic_proc_open("PROC_NET_TCP", "net/tcp")
+#define net_tcp6_open() generic_proc_open("PROC_NET_TCP6", "net/tcp6")
+#define net_udp_open() generic_proc_open("PROC_NET_UDP", "net/udp")
+#define net_udp6_open() generic_proc_open("PROC_NET_UDP6", "net/udp6")
+#define net_raw_open() generic_proc_open("PROC_NET_RAW", "net/raw")
+#define net_raw6_open() generic_proc_open("PROC_NET_RAW6", "net/raw6")
+#define net_unix_open() generic_proc_open("PROC_NET_UNIX", "net/unix")
+#define net_packet_open() generic_proc_open("PROC_NET_PACKET", \
+ "net/packet")
+#define net_netlink_open() generic_proc_open("PROC_NET_NETLINK", \
+ "net/netlink")
+#define net_sockstat_open() generic_proc_open("PROC_NET_SOCKSTAT", \
+ "net/sockstat")
+#define net_sockstat6_open() generic_proc_open("PROC_NET_SOCKSTAT6", \
+ "net/sockstat6")
+#define net_snmp_open() generic_proc_open("PROC_NET_SNMP", "net/snmp")
+#define ephemeral_ports_open() generic_proc_open("PROC_IP_LOCAL_PORT_RANGE", \
+ "sys/net/ipv4/ip_local_port_range")
+
+struct user_ent {
+ struct user_ent *next;
+ unsigned int ino;
+ int pid;
+ int tid;
+ int fd;
+ char *task;
+ char *task_ctx;
+ char *socket_ctx;
+};
+
+#define USER_ENT_HASH_SIZE 256
+static struct user_ent *user_ent_hash[USER_ENT_HASH_SIZE];
+
+static int user_ent_hashfn(unsigned int ino)
+{
+ int val = (ino >> 24) ^ (ino >> 16) ^ (ino >> 8) ^ ino;
+
+ return val & (USER_ENT_HASH_SIZE - 1);
+}
+
+static void user_ent_add(unsigned int ino, char *task,
+ int pid, int tid, int fd,
+ char *task_ctx,
+ char *sock_ctx)
+{
+ struct user_ent *p, **pp;
+
+ p = malloc(sizeof(struct user_ent));
+ if (!p) {
+ fprintf(stderr, "ss: failed to malloc buffer\n");
+ abort();
+ }
+ p->next = NULL;
+ p->ino = ino;
+ p->pid = pid;
+ p->tid = tid;
+ p->fd = fd;
+ p->task = strdup(task);
+ p->task_ctx = strdup(task_ctx);
+ p->socket_ctx = strdup(sock_ctx);
+
+ pp = &user_ent_hash[user_ent_hashfn(ino)];
+ p->next = *pp;
+ *pp = p;
+}
+
+#define MAX_PATH_LEN 1024
+
+static void user_ent_hash_build_task(char *path, int pid, int tid)
+{
+ const char *no_ctx = "unavailable";
+ char task[16] = {'\0', };
+ char stat[MAX_PATH_LEN];
+ int pos_id, pos_fd;
+ char *task_context;
+ struct dirent *d;
+ DIR *dir;
+
+ if (getpidcon(tid, &task_context) != 0)
+ task_context = strdup(no_ctx);
+
+ pos_id = strlen(path); /* $PROC_ROOT/$ID/ */
+
+ snprintf(path + pos_id, MAX_PATH_LEN - pos_id, "fd/");
+ dir = opendir(path);
+ if (!dir) {
+ freecon(task_context);
+ return;
+ }
+
+ pos_fd = strlen(path); /* $PROC_ROOT/$ID/fd/ */
+
+ while ((d = readdir(dir)) != NULL) {
+ const char *pattern = "socket:[";
+ char *sock_context;
+ unsigned int ino;
+ ssize_t link_len;
+ char lnk[64];
+ int fd;
+
+ if (sscanf(d->d_name, "%d%*c", &fd) != 1)
+ continue;
+
+ snprintf(path + pos_fd, MAX_PATH_LEN - pos_fd, "%d", fd);
+
+ link_len = readlink(path, lnk, sizeof(lnk) - 1);
+ if (link_len == -1)
+ continue;
+ lnk[link_len] = '\0';
+
+ if (strncmp(lnk, pattern, strlen(pattern)))
+ continue;
+
+ if (sscanf(lnk, "socket:[%u]", &ino) != 1)
+ continue;
+
+ if (getfilecon(path, &sock_context) <= 0)
+ sock_context = strdup(no_ctx);
+
+ if (task[0] == '\0') {
+ FILE *fp;
+
+ strlcpy(stat, path, pos_id + 1);
+ snprintf(stat + pos_id, sizeof(stat) - pos_id, "stat");
+
+ fp = fopen(stat, "r");
+ if (fp) {
+ if (fscanf(fp, "%*d (%[^)])", task) < 1) {
+ ; /* ignore */
+ }
+ fclose(fp);
+ }
+ }
+
+ user_ent_add(ino, task, pid, tid, fd, task_context, sock_context);
+ freecon(sock_context);
+ }
+
+ freecon(task_context);
+ closedir(dir);
+}
+
+static void user_ent_destroy(void)
+{
+ struct user_ent *p, *p_next;
+ int cnt = 0;
+
+ while (cnt != USER_ENT_HASH_SIZE) {
+ p = user_ent_hash[cnt];
+ while (p) {
+ free(p->task);
+ free(p->task_ctx);
+ free(p->socket_ctx);
+ p_next = p->next;
+ free(p);
+ p = p_next;
+ }
+ cnt++;
+ }
+}
+
+static void user_ent_hash_build(void)
+{
+ const char *root = getenv("PROC_ROOT") ? : "/proc/";
+ char name[MAX_PATH_LEN];
+ struct dirent *d;
+ int nameoff;
+ DIR *dir;
+
+ strlcpy(name, root, sizeof(name));
+
+ if (strlen(name) == 0 || name[strlen(name) - 1] != '/')
+ strcat(name, "/");
+
+ nameoff = strlen(name);
+
+ dir = opendir(name);
+ if (!dir)
+ return;
+
+ while ((d = readdir(dir)) != NULL) {
+ int pid;
+
+ if (sscanf(d->d_name, "%d%*c", &pid) != 1)
+ continue;
+
+ snprintf(name + nameoff, sizeof(name) - nameoff, "%d/", pid);
+ user_ent_hash_build_task(name, pid, pid);
+
+ if (show_threads) {
+ struct dirent *task_d;
+ DIR *task_dir;
+
+ snprintf(name + nameoff, sizeof(name) - nameoff, "%d/task/", pid);
+
+ task_dir = opendir(name);
+ if (!task_dir)
+ continue;
+
+ while ((task_d = readdir(task_dir)) != NULL) {
+ int tid;
+
+ if (sscanf(task_d->d_name, "%d%*c", &tid) != 1)
+ continue;
+ if (tid == pid)
+ continue;
+
+ snprintf(name + nameoff, sizeof(name) - nameoff, "%d/", tid);
+ user_ent_hash_build_task(name, pid, tid);
+ }
+ closedir(task_dir);
+ }
+ }
+ closedir(dir);
+}
+
+enum entry_types {
+ USERS,
+ PROC_CTX,
+ PROC_SOCK_CTX
+};
+
+#define ENTRY_BUF_SIZE 512
+static int find_entry(unsigned int ino, char **buf, int type)
+{
+ struct user_ent *p;
+ int cnt = 0;
+ char *ptr;
+ char thread_info[16] = {'\0', };
+ char *new_buf;
+ int len, new_buf_len;
+ int buf_used = 0;
+ int buf_len = 0;
+
+ if (!ino)
+ return 0;
+
+ p = user_ent_hash[user_ent_hashfn(ino)];
+ ptr = *buf = NULL;
+ while (p) {
+ if (p->ino != ino)
+ goto next;
+
+ while (1) {
+ ptr = *buf + buf_used;
+
+ if (show_threads)
+ snprintf(thread_info, sizeof(thread_info), "tid=%d,", p->tid);
+
+ switch (type) {
+ case USERS:
+ len = snprintf(ptr, buf_len - buf_used,
+ "(\"%s\",pid=%d,%sfd=%d),",
+ p->task, p->pid, thread_info, p->fd);
+ break;
+ case PROC_CTX:
+ len = snprintf(ptr, buf_len - buf_used,
+ "(\"%s\",pid=%d,%sproc_ctx=%s,fd=%d),",
+ p->task, p->pid, thread_info,
+ p->task_ctx, p->fd);
+ break;
+ case PROC_SOCK_CTX:
+ len = snprintf(ptr, buf_len - buf_used,
+ "(\"%s\",pid=%d,%sproc_ctx=%s,fd=%d,sock_ctx=%s),",
+ p->task, p->pid, thread_info,
+ p->task_ctx, p->fd,
+ p->socket_ctx);
+ break;
+ default:
+ fprintf(stderr, "ss: invalid type: %d\n", type);
+ abort();
+ }
+
+ if (len < 0 || len >= buf_len - buf_used) {
+ new_buf_len = buf_len + ENTRY_BUF_SIZE;
+ new_buf = realloc(*buf, new_buf_len);
+ if (!new_buf) {
+ fprintf(stderr, "ss: failed to malloc buffer\n");
+ abort();
+ }
+ *buf = new_buf;
+ buf_len = new_buf_len;
+ continue;
+ } else {
+ buf_used += len;
+ break;
+ }
+ }
+ cnt++;
+next:
+ p = p->next;
+ }
+ if (buf_used) {
+ ptr = *buf + buf_used;
+ ptr[-1] = '\0';
+ }
+ return cnt;
+}
+
+static unsigned long long cookie_sk_get(const uint32_t *cookie)
+{
+ return (((unsigned long long)cookie[1] << 31) << 1) | cookie[0];
+}
+
+static const char *sctp_sstate_name[] = {
+ [SCTP_STATE_CLOSED] = "CLOSED",
+ [SCTP_STATE_COOKIE_WAIT] = "COOKIE_WAIT",
+ [SCTP_STATE_COOKIE_ECHOED] = "COOKIE_ECHOED",
+ [SCTP_STATE_ESTABLISHED] = "ESTAB",
+ [SCTP_STATE_SHUTDOWN_PENDING] = "SHUTDOWN_PENDING",
+ [SCTP_STATE_SHUTDOWN_SENT] = "SHUTDOWN_SENT",
+ [SCTP_STATE_SHUTDOWN_RECEIVED] = "SHUTDOWN_RECEIVED",
+ [SCTP_STATE_SHUTDOWN_ACK_SENT] = "ACK_SENT",
+};
+
+static const char * const stype_nameg[] = {
+ "UNKNOWN",
+ [SOCK_STREAM] = "STREAM",
+ [SOCK_DGRAM] = "DGRAM",
+ [SOCK_RDM] = "RDM",
+ [SOCK_SEQPACKET] = "SEQPACKET",
+};
+
+struct sockstat {
+ struct sockstat *next;
+ unsigned int type;
+ uint16_t prot;
+ uint16_t raw_prot;
+ inet_prefix local;
+ inet_prefix remote;
+ int lport;
+ int rport;
+ int state;
+ int rq, wq;
+ unsigned int ino;
+ unsigned int uid;
+ int refcnt;
+ unsigned int iface;
+ unsigned long long sk;
+ char *name;
+ char *peer_name;
+ __u32 mark;
+ __u64 cgroup_id;
+};
+
+struct dctcpstat {
+ unsigned int ce_state;
+ unsigned int alpha;
+ unsigned int ab_ecn;
+ unsigned int ab_tot;
+ bool enabled;
+};
+
+struct tcpstat {
+ struct sockstat ss;
+ unsigned int timer;
+ unsigned int timeout;
+ int probes;
+ char cong_alg[16];
+ double rto, ato, rtt, rttvar;
+ int qack, ssthresh, backoff;
+ double send_bps;
+ int snd_wscale;
+ int rcv_wscale;
+ int mss;
+ int rcv_mss;
+ int advmss;
+ unsigned int pmtu;
+ unsigned int cwnd;
+ unsigned int lastsnd;
+ unsigned int lastrcv;
+ unsigned int lastack;
+ double pacing_rate;
+ double pacing_rate_max;
+ double delivery_rate;
+ unsigned long long bytes_acked;
+ unsigned long long bytes_received;
+ unsigned int segs_out;
+ unsigned int segs_in;
+ unsigned int data_segs_out;
+ unsigned int data_segs_in;
+ unsigned int unacked;
+ unsigned int retrans;
+ unsigned int retrans_total;
+ unsigned int lost;
+ unsigned int sacked;
+ unsigned int fackets;
+ unsigned int reordering;
+ unsigned int not_sent;
+ unsigned int delivered;
+ unsigned int delivered_ce;
+ unsigned int dsack_dups;
+ unsigned int reord_seen;
+ double rcv_rtt;
+ double min_rtt;
+ unsigned int rcv_ooopack;
+ unsigned int snd_wnd;
+ unsigned int rcv_wnd;
+ unsigned int rehash;
+ int rcv_space;
+ unsigned int rcv_ssthresh;
+ unsigned long long busy_time;
+ unsigned long long rwnd_limited;
+ unsigned long long sndbuf_limited;
+ unsigned long long bytes_sent;
+ unsigned long long bytes_retrans;
+ bool has_ts_opt;
+ bool has_usec_ts_opt;
+ bool has_sack_opt;
+ bool has_ecn_opt;
+ bool has_ecnseen_opt;
+ bool has_fastopen_opt;
+ bool has_wscale_opt;
+ bool app_limited;
+ struct dctcpstat *dctcp;
+ struct tcp_bbr_info *bbr_info;
+};
+
+/* SCTP assocs share the same inode number with their parent endpoint. So if we
+ * have seen the inode number before, it must be an assoc instead of the next
+ * endpoint. */
+static bool is_sctp_assoc(struct sockstat *s, const char *sock_name)
+{
+ if (strcmp(sock_name, "sctp"))
+ return false;
+ if (!sctp_ino || sctp_ino != s->ino)
+ return false;
+ return true;
+}
+
+static const char *unix_netid_name(int type)
+{
+ switch (type) {
+ case SOCK_STREAM:
+ return "u_str";
+ case SOCK_SEQPACKET:
+ return "u_seq";
+ case SOCK_DGRAM:
+ default:
+ return "u_dgr";
+ }
+}
+
+static const char *proto_name(int protocol)
+{
+ switch (protocol) {
+ case 0:
+ return "raw";
+ case IPPROTO_UDP:
+ return "udp";
+ case IPPROTO_TCP:
+ return "tcp";
+ case IPPROTO_MPTCP:
+ return "mptcp";
+ case IPPROTO_SCTP:
+ return "sctp";
+ case IPPROTO_DCCP:
+ return "dccp";
+ case IPPROTO_ICMPV6:
+ return "icmp6";
+ }
+
+ return "???";
+}
+
+static const char *vsock_netid_name(int type)
+{
+ switch (type) {
+ case SOCK_STREAM:
+ return "v_str";
+ case SOCK_DGRAM:
+ return "v_dgr";
+ default:
+ return "???";
+ }
+}
+
+static const char *tipc_netid_name(int type)
+{
+ switch (type) {
+ case SOCK_STREAM:
+ return "ti_st";
+ case SOCK_DGRAM:
+ return "ti_dg";
+ case SOCK_RDM:
+ return "ti_rd";
+ case SOCK_SEQPACKET:
+ return "ti_sq";
+ default:
+ return "???";
+ }
+}
+
+/* Allocate and initialize a new buffer chunk */
+static struct buf_chunk *buf_chunk_new(void)
+{
+ struct buf_chunk *new = malloc(BUF_CHUNK);
+
+ if (!new)
+ abort();
+
+ new->next = NULL;
+
+ /* This is also the last block */
+ buffer.tail = new;
+
+ /* Next token will be stored at the beginning of chunk data area, and
+ * its initial length is zero.
+ */
+ buffer.cur = (struct buf_token *)new->data;
+ buffer.cur->len = 0;
+
+ new->end = buffer.cur->data;
+
+ buffer.chunks++;
+
+ return new;
+}
+
+/* Return available tail room in given chunk */
+static int buf_chunk_avail(struct buf_chunk *chunk)
+{
+ return BUF_CHUNK - offsetof(struct buf_chunk, data) -
+ (chunk->end - chunk->data);
+}
+
+/* Update end pointer and token length, link new chunk if we hit the end of the
+ * current one. Return -EAGAIN if we got a new chunk, caller has to print again.
+ */
+static int buf_update(int len)
+{
+ struct buf_chunk *chunk = buffer.tail;
+ struct buf_token *t = buffer.cur;
+
+ /* Claim success if new content fits in the current chunk, and anyway
+ * if this is the first token in the chunk: in the latter case,
+ * allocating a new chunk won't help, so we'll just cut the output.
+ */
+ if ((len < buf_chunk_avail(chunk) && len != -1 /* glibc < 2.0.6 */) ||
+ t == (struct buf_token *)chunk->data) {
+ len = min(len, buf_chunk_avail(chunk));
+
+ /* Total field length can't exceed 2^16 bytes, cut as needed */
+ len = min(len, USHRT_MAX - t->len);
+
+ chunk->end += len;
+ t->len += len;
+ return 0;
+ }
+
+ /* Content truncated, time to allocate more */
+ chunk->next = buf_chunk_new();
+
+ /* Copy current token over to new chunk, including length descriptor */
+ memcpy(chunk->next->data, t, sizeof(t->len) + t->len);
+ chunk->next->end += t->len;
+
+ /* Discard partially written field in old chunk */
+ chunk->end -= t->len + sizeof(t->len);
+
+ return -EAGAIN;
+}
+
+/* Append content to buffer as part of the current field */
+__attribute__((format(printf, 1, 2)))
+static void out(const char *fmt, ...)
+{
+ struct column *f = current_field;
+ va_list args;
+ char *pos;
+ int len;
+
+ if (f->disabled)
+ return;
+
+ if (!buffer.head)
+ buffer.head = buf_chunk_new();
+
+again: /* Append to buffer: if we have a new chunk, print again */
+
+ pos = buffer.cur->data + buffer.cur->len;
+ va_start(args, fmt);
+
+ /* Limit to tail room. If we hit the limit, buf_update() will tell us */
+ len = vsnprintf(pos, buf_chunk_avail(buffer.tail), fmt, args);
+ va_end(args);
+
+ if (buf_update(len))
+ goto again;
+}
+
+static int print_left_spacing(struct column *f, int stored, int printed)
+{
+ int s;
+
+ if (!f->width || f->align == ALIGN_LEFT)
+ return 0;
+
+ s = f->width - stored - printed;
+ if (f->align == ALIGN_CENTER)
+ /* If count of total spacing is odd, shift right by one */
+ s = (s + 1) / 2;
+
+ if (s > 0)
+ return printf("%*c", s, ' ');
+
+ return 0;
+}
+
+static void print_right_spacing(struct column *f, int printed)
+{
+ int s;
+
+ if (!f->width || f->align == ALIGN_RIGHT)
+ return;
+
+ s = f->width - printed;
+ if (f->align == ALIGN_CENTER)
+ s /= 2;
+
+ if (s > 0)
+ printf("%*c", s, ' ');
+}
+
+/* Done with field: update buffer pointer, start new token after current one */
+static void field_flush(struct column *f)
+{
+ struct buf_chunk *chunk;
+ unsigned int pad;
+
+ if (f->disabled)
+ return;
+
+ chunk = buffer.tail;
+ pad = buffer.cur->len % 2;
+
+ if (buffer.cur->len > f->max_len)
+ f->max_len = buffer.cur->len;
+
+ /* We need a new chunk if we can't store the next length descriptor.
+ * Mind the gap between end of previous token and next aligned position
+ * for length descriptor.
+ */
+ if (buf_chunk_avail(chunk) - pad < sizeof(buffer.cur->len)) {
+ chunk->end += pad;
+ chunk->next = buf_chunk_new();
+ return;
+ }
+
+ buffer.cur = (struct buf_token *)(buffer.cur->data +
+ LEN_ALIGN(buffer.cur->len));
+ buffer.cur->len = 0;
+ buffer.tail->end = buffer.cur->data;
+}
+
+static int field_is_last(struct column *f)
+{
+ return f - columns == COL_MAX - 1;
+}
+
+/* Get the next available token in the buffer starting from the current token */
+static struct buf_token *buf_token_next(struct buf_token *cur)
+{
+ struct buf_chunk *chunk = buffer.tail;
+
+ /* If we reached the end of chunk contents, get token from next chunk */
+ if (cur->data + LEN_ALIGN(cur->len) == chunk->end) {
+ buffer.tail = chunk = chunk->next;
+ return chunk ? (struct buf_token *)chunk->data : NULL;
+ }
+
+ return (struct buf_token *)(cur->data + LEN_ALIGN(cur->len));
+}
+
+/* Free up all allocated buffer chunks */
+static void buf_free_all(void)
+{
+ struct buf_chunk *tmp;
+
+ for (buffer.tail = buffer.head; buffer.tail; ) {
+ tmp = buffer.tail;
+ buffer.tail = buffer.tail->next;
+ free(tmp);
+ }
+ buffer.head = NULL;
+ buffer.chunks = 0;
+}
+
+/* Get current screen width, returns -1 if TIOCGWINSZ fails */
+static int render_screen_width(void)
+{
+ int width = -1;
+
+ if (isatty(STDOUT_FILENO)) {
+ struct winsize w;
+
+ if (ioctl(STDOUT_FILENO, TIOCGWINSZ, &w) != -1) {
+ if (w.ws_col > 0)
+ width = w.ws_col;
+ }
+ }
+
+ return width;
+}
+
+/* Calculate column width from contents length. If columns don't fit on one
+ * line, break them into the least possible amount of lines and keep them
+ * aligned across lines. Available screen space is equally spread between fields
+ * as additional spacing.
+ */
+static void render_calc_width(void)
+{
+ int screen_width, first, len = 0, linecols = 0;
+ struct column *c, *eol = columns - 1;
+ bool compact_output = false;
+
+ screen_width = render_screen_width();
+ if (screen_width == -1) {
+ screen_width = INT_MAX;
+ compact_output = true;
+ }
+
+ /* First pass: set width for each column to measured content length */
+ for (first = 1, c = columns; c - columns < COL_MAX; c++) {
+ if (c->disabled)
+ continue;
+
+ if (!first && c->max_len)
+ c->width = c->max_len + strlen(c->ldelim);
+ else
+ c->width = c->max_len;
+
+ /* But don't exceed screen size. If we exceed the screen size
+ * for even a single field, it will just start on a line of its
+ * own and then naturally wrap.
+ */
+ c->width = min(c->width, screen_width);
+
+ if (c->width)
+ first = 0;
+ }
+
+ if (compact_output) {
+ /* Compact output, skip extending columns. */
+ return;
+ }
+
+ /* Second pass: find out newlines and distribute available spacing */
+ for (c = columns; c - columns < COL_MAX; c++) {
+ int pad, spacing, rem, last;
+ struct column *tmp;
+
+ if (!c->width)
+ continue;
+
+ linecols++;
+ len += c->width;
+
+ for (last = 1, tmp = c + 1; tmp - columns < COL_MAX; tmp++) {
+ if (tmp->width) {
+ last = 0;
+ break;
+ }
+ }
+
+ if (!last && len < screen_width) {
+ /* Columns fit on screen so far, nothing to do yet */
+ continue;
+ }
+
+ if (len == screen_width) {
+ /* Exact fit, just start with new line */
+ goto newline;
+ }
+
+ if (len > screen_width) {
+ /* Screen width exceeded: go back one column */
+ len -= c->width;
+ c--;
+ linecols--;
+ }
+
+ /* Distribute remaining space to columns on this line */
+ pad = screen_width - len;
+ spacing = pad / linecols;
+ rem = pad % linecols;
+ for (tmp = c; tmp > eol; tmp--) {
+ if (!tmp->width)
+ continue;
+
+ tmp->width += spacing;
+ if (rem) {
+ tmp->width++;
+ rem--;
+ }
+ }
+
+newline:
+ /* Line break: reset line counters, mark end-of-line */
+ eol = c;
+ len = 0;
+ linecols = 0;
+ }
+}
+
+/* Render buffered output with spacing and delimiters, then free up buffers */
+static void render(void)
+{
+ struct buf_token *token;
+ int printed, line_started = 0;
+ struct column *f;
+
+ if (!buffer.head)
+ return;
+
+ token = (struct buf_token *)buffer.head->data;
+
+ /* Ensure end alignment of last token, it wasn't necessarily flushed */
+ buffer.tail->end += buffer.cur->len % 2;
+
+ render_calc_width();
+
+ /* Rewind and replay */
+ buffer.tail = buffer.head;
+
+ f = columns;
+ while (!f->width)
+ f++;
+
+ while (token) {
+ /* Print left delimiter only if we already started a line */
+ if (line_started++)
+ printed = printf("%s", f->ldelim);
+ else
+ printed = 0;
+
+ /* Print field content from token data with spacing */
+ printed += print_left_spacing(f, token->len, printed);
+ printed += fwrite(token->data, 1, token->len, stdout);
+ print_right_spacing(f, printed);
+
+ /* Go to next non-empty field, deal with end-of-line */
+ do {
+ if (field_is_last(f)) {
+ printf("\n");
+ f = columns;
+ line_started = 0;
+ } else {
+ f++;
+ }
+ } while (f->disabled);
+
+ token = buf_token_next(token);
+ }
+ /* Deal with final end-of-line when the last non-empty field printed
+ * is not the last field.
+ */
+ if (line_started)
+ printf("\n");
+
+ buf_free_all();
+ current_field = columns;
+}
+
+/* Move to next field, and render buffer if we reached the maximum number of
+ * chunks, at the last field in a line.
+ */
+static void field_next(void)
+{
+ if (field_is_last(current_field) && buffer.chunks >= BUF_CHUNKS_MAX) {
+ render();
+ return;
+ }
+
+ field_flush(current_field);
+ if (field_is_last(current_field))
+ current_field = columns;
+ else
+ current_field++;
+}
+
+/* Walk through fields and flush them until we reach the desired one */
+static void field_set(enum col_id id)
+{
+ while (id != current_field - columns)
+ field_next();
+}
+
+/* Print header for all non-empty columns */
+static void print_header(void)
+{
+ while (!field_is_last(current_field)) {
+ if (!current_field->disabled)
+ out("%s", current_field->header);
+ field_next();
+ }
+}
+
+static void sock_state_print(struct sockstat *s)
+{
+ const char *sock_name;
+ static const char * const sstate_name[] = {
+ "UNKNOWN",
+ [SS_ESTABLISHED] = "ESTAB",
+ [SS_SYN_SENT] = "SYN-SENT",
+ [SS_SYN_RECV] = "SYN-RECV",
+ [SS_FIN_WAIT1] = "FIN-WAIT-1",
+ [SS_FIN_WAIT2] = "FIN-WAIT-2",
+ [SS_TIME_WAIT] = "TIME-WAIT",
+ [SS_CLOSE] = "UNCONN",
+ [SS_CLOSE_WAIT] = "CLOSE-WAIT",
+ [SS_LAST_ACK] = "LAST-ACK",
+ [SS_LISTEN] = "LISTEN",
+ [SS_CLOSING] = "CLOSING",
+ [SS_NEW_SYN_RECV] = "UNDEF", /* Never returned by kernel */
+ [SS_BOUND_INACTIVE] = "UNDEF", /* Never returned by kernel */
+ };
+
+ switch (s->local.family) {
+ case AF_UNIX:
+ sock_name = unix_netid_name(s->type);
+ break;
+ case AF_INET:
+ case AF_INET6:
+ sock_name = proto_name(s->type);
+ break;
+ case AF_PACKET:
+ sock_name = s->type == SOCK_RAW ? "p_raw" : "p_dgr";
+ break;
+ case AF_NETLINK:
+ sock_name = "nl";
+ break;
+ case AF_TIPC:
+ sock_name = tipc_netid_name(s->type);
+ break;
+ case AF_VSOCK:
+ sock_name = vsock_netid_name(s->type);
+ break;
+ case AF_XDP:
+ sock_name = "xdp";
+ break;
+ default:
+ sock_name = "unknown";
+ }
+
+ if (is_sctp_assoc(s, sock_name)) {
+ field_set(COL_STATE); /* Empty Netid field */
+ out("`- %s", sctp_sstate_name[s->state]);
+ } else {
+ field_set(COL_NETID);
+ out("%s", sock_name);
+ field_set(COL_STATE);
+ out("%s", sstate_name[s->state]);
+ }
+
+ field_set(COL_RECVQ);
+ out("%-6d", s->rq);
+ field_set(COL_SENDQ);
+ out("%-6d", s->wq);
+ field_set(COL_ADDR);
+}
+
+static void sock_details_print(struct sockstat *s)
+{
+ if (s->uid)
+ out(" uid:%u", s->uid);
+
+ out(" ino:%u", s->ino);
+ out(" sk:%llx", s->sk);
+
+ if (s->mark)
+ out(" fwmark:0x%x", s->mark);
+
+ if (s->cgroup_id)
+ out(" cgroup:%s", cg_id_to_path(s->cgroup_id));
+}
+
+static void sock_addr_print(const char *addr, char *delim, const char *port,
+ const char *ifname)
+{
+ if (ifname)
+ out("%s" "%%" "%s%s", addr, ifname, delim);
+ else
+ out("%s%s", addr, delim);
+
+ field_next();
+ out("%s", port);
+ field_next();
+}
+
+static const char *print_ms_timer(unsigned int timeout)
+{
+ static char buf[64];
+ int secs, msecs, minutes;
+
+ secs = timeout/1000;
+ minutes = secs/60;
+ secs = secs%60;
+ msecs = timeout%1000;
+ buf[0] = 0;
+ if (minutes) {
+ msecs = 0;
+ snprintf(buf, sizeof(buf)-16, "%dmin", minutes);
+ if (minutes > 9)
+ secs = 0;
+ }
+ if (secs) {
+ if (secs > 9)
+ msecs = 0;
+ sprintf(buf+strlen(buf), "%d%s", secs, msecs ? "." : "sec");
+ }
+ if (msecs)
+ sprintf(buf+strlen(buf), "%03dms", msecs);
+ return buf;
+}
+
+struct scache {
+ struct scache *next;
+ int port;
+ char *name;
+ const char *proto;
+};
+
+static struct scache *rlist;
+
+#ifdef HAVE_RPC
+static CLIENT *rpc_client_create(rpcprog_t prog, rpcvers_t vers)
+{
+ struct netbuf nbuf;
+ struct sockaddr_un saddr;
+ int sock;
+
+ memset(&saddr, 0, sizeof(saddr));
+ sock = socket(AF_LOCAL, SOCK_STREAM, 0);
+ if (sock < 0)
+ return NULL;
+
+ saddr.sun_family = AF_LOCAL;
+ strcpy(saddr.sun_path, _PATH_RPCBINDSOCK);
+ nbuf.len = SUN_LEN(&saddr);
+ nbuf.maxlen = sizeof(struct sockaddr_un);
+ nbuf.buf = &saddr;
+
+ return clnt_vc_create(sock, &nbuf, prog, vers, 0, 0);
+}
+
+static void init_service_resolver(void)
+{
+ struct rpcblist *rhead = NULL;
+ struct timeval timeout;
+ struct rpcent *rpc;
+ enum clnt_stat res;
+ CLIENT *client;
+
+ timeout.tv_sec = 5;
+ timeout.tv_usec = 0;
+
+ client = rpc_client_create(PMAPPROG, RPCBVERS4);
+ if (!client)
+ return;
+
+ res = clnt_call(client, RPCBPROC_DUMP, (xdrproc_t)xdr_void, NULL,
+ (xdrproc_t)xdr_rpcblist_ptr, (char *)&rhead,
+ timeout);
+ if (res != RPC_SUCCESS)
+ return;
+
+ for (; rhead; rhead = rhead->rpcb_next) {
+ char prog[128] = "rpc.";
+ struct scache *c;
+ int hport, lport, ok;
+
+ c = malloc(sizeof(*c));
+ if (!c)
+ continue;
+
+ ok = sscanf(rhead->rpcb_map.r_addr, "::.%d.%d", &hport, &lport);
+ if (!ok)
+ ok = sscanf(rhead->rpcb_map.r_addr, "0.0.0.0.%d.%d",
+ &hport, &lport);
+ if (!ok)
+ continue;
+ c->port = hport << 8 | lport;
+
+ if (strcmp(rhead->rpcb_map.r_netid, TCP_PROTO) == 0 ||
+ strcmp(rhead->rpcb_map.r_netid, TCP6_PROTO) == 0)
+ c->proto = TCP_PROTO;
+ else if (strcmp(rhead->rpcb_map.r_netid, UDP_PROTO) == 0 ||
+ strcmp(rhead->rpcb_map.r_netid, UDP6_PROTO) == 0)
+ c->proto = UDP_PROTO;
+ else if (strcmp(rhead->rpcb_map.r_netid, SCTP_PROTO) == 0)
+ c->proto = SCTP_PROTO;
+ else
+ continue;
+
+ rpc = getrpcbynumber(rhead->rpcb_map.r_prog);
+ if (rpc) {
+ strncat(prog, rpc->r_name, 128 - strlen(prog));
+ c->name = strdup(prog);
+ }
+
+ c->next = rlist;
+ rlist = c;
+ }
+}
+#endif
+
+/* Even do not try default linux ephemeral port ranges:
+ * default /etc/services contains so much of useless crap
+ * wouldbe "allocated" to this area that resolution
+ * is really harmful. I shrug each time when seeing
+ * "socks" or "cfinger" in dumps.
+ */
+static int is_ephemeral(int port)
+{
+ static int min = 0, max;
+
+ if (!min) {
+ FILE *f = ephemeral_ports_open();
+
+ if (!f || fscanf(f, "%d %d", &min, &max) < 2) {
+ min = 1024;
+ max = 4999;
+ }
+ if (f)
+ fclose(f);
+ }
+ return port >= min && port <= max;
+}
+
+
+static const char *__resolve_service(int port)
+{
+ struct scache *c;
+
+ for (c = rlist; c; c = c->next) {
+ if (c->port == port && c->proto == dg_proto)
+ return c->name;
+ }
+
+ if (!is_ephemeral(port)) {
+ static int notfirst;
+ struct servent *se;
+
+ if (!notfirst) {
+ setservent(1);
+ notfirst = 1;
+ }
+ se = getservbyport(htons(port), dg_proto);
+ if (se)
+ return se->s_name;
+ }
+
+ return NULL;
+}
+
+#define SCACHE_BUCKETS 1024
+static struct scache *cache_htab[SCACHE_BUCKETS];
+
+static const char *resolve_service(int port)
+{
+ static char buf[128];
+ struct scache *c;
+ const char *res;
+ int hash;
+
+ if (port == 0) {
+ buf[0] = '*';
+ buf[1] = 0;
+ return buf;
+ }
+
+ if (numeric)
+ goto do_numeric;
+
+ if (dg_proto == RAW_PROTO)
+ return inet_proto_n2a(port, buf, sizeof(buf));
+
+
+ hash = (port^(((unsigned long)dg_proto)>>2)) % SCACHE_BUCKETS;
+
+ for (c = cache_htab[hash]; c; c = c->next) {
+ if (c->port == port && c->proto == dg_proto)
+ goto do_cache;
+ }
+
+ c = malloc(sizeof(*c));
+ if (!c)
+ goto do_numeric;
+ res = __resolve_service(port);
+ c->port = port;
+ c->name = res ? strdup(res) : NULL;
+ c->proto = dg_proto;
+ c->next = cache_htab[hash];
+ cache_htab[hash] = c;
+
+do_cache:
+ if (c->name)
+ return c->name;
+
+do_numeric:
+ sprintf(buf, "%u", port);
+ return buf;
+}
+
+static void inet_addr_print(const inet_prefix *a, int port,
+ unsigned int ifindex, bool v6only)
+{
+ char buf[1024];
+ const char *ap = buf;
+ const char *ifname = NULL;
+
+ if (a->family == AF_INET) {
+ ap = format_host(AF_INET, 4, a->data);
+ } else {
+ if (!v6only &&
+ !memcmp(a->data, &in6addr_any, sizeof(in6addr_any))) {
+ buf[0] = '*';
+ buf[1] = 0;
+ } else {
+ ap = format_host(a->family, 16, a->data);
+
+ /* Numeric IPv6 addresses should be bracketed */
+ if (strchr(ap, ':')) {
+ snprintf(buf, sizeof(buf),
+ "[%s]", ap);
+ ap = buf;
+ }
+ }
+ }
+
+ if (ifindex)
+ ifname = ll_index_to_name(ifindex);
+
+ sock_addr_print(ap, ":", resolve_service(port), ifname);
+}
+
+struct aafilter {
+ inet_prefix addr;
+ long port;
+ unsigned int iface;
+ __u32 mark;
+ __u32 mask;
+ __u64 cgroup_id;
+ struct aafilter *next;
+};
+
+static int inet2_addr_match(const inet_prefix *a, const inet_prefix *p,
+ int plen)
+{
+ if (!inet_addr_match(a, p, plen))
+ return 0;
+
+ /* Cursed "v4 mapped" addresses: v4 mapped socket matches
+ * pure IPv4 rule, but v4-mapped rule selects only v4-mapped
+ * sockets. Fair? */
+ if (p->family == AF_INET && a->family == AF_INET6) {
+ if (a->data[0] == 0 && a->data[1] == 0 &&
+ a->data[2] == htonl(0xffff)) {
+ inet_prefix tmp = *a;
+
+ tmp.data[0] = a->data[3];
+ return inet_addr_match(&tmp, p, plen);
+ }
+ }
+ return 1;
+}
+
+static int unix_match(const inet_prefix *a, const inet_prefix *p)
+{
+ char *addr, *pattern;
+
+ memcpy(&addr, a->data, sizeof(addr));
+ memcpy(&pattern, p->data, sizeof(pattern));
+ if (pattern == NULL)
+ return 1;
+ if (addr == NULL)
+ addr = "";
+ return !fnmatch(pattern, addr, FNM_CASEFOLD);
+}
+
+static int run_ssfilter(struct ssfilter *f, struct sockstat *s)
+{
+ switch (f->type) {
+ case SSF_S_AUTO:
+ {
+ if (s->local.family == AF_UNIX) {
+ char *p;
+
+ memcpy(&p, s->local.data, sizeof(p));
+ return p == NULL || (p[0] == '@' && strlen(p) == 6 &&
+ strspn(p+1, "0123456789abcdef") == 5);
+ }
+ if (s->local.family == AF_PACKET)
+ return s->lport == 0 && s->local.data[0] == 0;
+ if (s->local.family == AF_NETLINK)
+ return s->lport < 0;
+ if (s->local.family == AF_VSOCK)
+ return s->lport > 1023;
+
+ return is_ephemeral(s->lport);
+ }
+ case SSF_DCOND:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ if (a->addr.family == AF_UNIX)
+ return unix_match(&s->remote, &a->addr);
+ if (a->port != -1 && a->port != s->rport)
+ return 0;
+ if (a->addr.bitlen) {
+ do {
+ if (!inet2_addr_match(&s->remote, &a->addr, a->addr.bitlen))
+ return 1;
+ } while ((a = a->next) != NULL);
+ return 0;
+ }
+ return 1;
+ }
+ case SSF_SCOND:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ if (a->addr.family == AF_UNIX)
+ return unix_match(&s->local, &a->addr);
+ if (a->port != -1 && a->port != s->lport)
+ return 0;
+ if (a->addr.bitlen) {
+ do {
+ if (!inet2_addr_match(&s->local, &a->addr, a->addr.bitlen))
+ return 1;
+ } while ((a = a->next) != NULL);
+ return 0;
+ }
+ return 1;
+ }
+ case SSF_D_GE:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ return s->rport >= a->port;
+ }
+ case SSF_D_LE:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ return s->rport <= a->port;
+ }
+ case SSF_S_GE:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ return s->lport >= a->port;
+ }
+ case SSF_S_LE:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ return s->lport <= a->port;
+ }
+ case SSF_DEVCOND:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ return s->iface == a->iface;
+ }
+ case SSF_MARKMASK:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ return (s->mark & a->mask) == a->mark;
+ }
+ case SSF_CGROUPCOND:
+ {
+ struct aafilter *a = (void *)f->pred;
+
+ return s->cgroup_id == a->cgroup_id;
+ }
+ /* Yup. It is recursion. Sorry. */
+ case SSF_AND:
+ return run_ssfilter(f->pred, s) && run_ssfilter(f->post, s);
+ case SSF_OR:
+ return run_ssfilter(f->pred, s) || run_ssfilter(f->post, s);
+ case SSF_NOT:
+ return !run_ssfilter(f->pred, s);
+ default:
+ abort();
+ }
+}
+
+/* Relocate external jumps by reloc. */
+static void ssfilter_patch(char *a, int len, int reloc)
+{
+ while (len > 0) {
+ struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)a;
+
+ if (op->no == len+4)
+ op->no += reloc;
+ len -= op->yes;
+ a += op->yes;
+ }
+ if (len < 0)
+ abort();
+}
+
+static int ssfilter_bytecompile(struct ssfilter *f, char **bytecode)
+{
+ switch (f->type) {
+ case SSF_S_AUTO:
+ {
+ if (!(*bytecode = malloc(4))) abort();
+ ((struct inet_diag_bc_op *)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_AUTO, 4, 8 };
+ return 4;
+ }
+ case SSF_DCOND:
+ case SSF_SCOND:
+ {
+ struct aafilter *a = (void *)f->pred;
+ struct aafilter *b;
+ char *ptr;
+ int code = (f->type == SSF_DCOND ? INET_DIAG_BC_D_COND : INET_DIAG_BC_S_COND);
+ int len = 0;
+
+ for (b = a; b; b = b->next) {
+ len += 4 + sizeof(struct inet_diag_hostcond);
+ if (a->addr.family == AF_INET6)
+ len += 16;
+ else
+ len += 4;
+ if (b->next)
+ len += 4;
+ }
+ if (!(ptr = malloc(len))) abort();
+ *bytecode = ptr;
+ for (b = a; b; b = b->next) {
+ struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)ptr;
+ int alen = (a->addr.family == AF_INET6 ? 16 : 4);
+ int oplen = alen + 4 + sizeof(struct inet_diag_hostcond);
+ struct inet_diag_hostcond *cond = (struct inet_diag_hostcond *)(ptr+4);
+
+ *op = (struct inet_diag_bc_op){ code, oplen, oplen+4 };
+ cond->family = a->addr.family;
+ cond->port = a->port;
+ cond->prefix_len = a->addr.bitlen;
+ memcpy(cond->addr, a->addr.data, alen);
+ ptr += oplen;
+ if (b->next) {
+ op = (struct inet_diag_bc_op *)ptr;
+ *op = (struct inet_diag_bc_op){ INET_DIAG_BC_JMP, 4, len - (ptr-*bytecode)};
+ ptr += 4;
+ }
+ }
+ return ptr - *bytecode;
+ }
+ case SSF_D_GE:
+ {
+ struct aafilter *x = (void *)f->pred;
+
+ if (!(*bytecode = malloc(8))) abort();
+ ((struct inet_diag_bc_op *)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_D_GE, 8, 12 };
+ ((struct inet_diag_bc_op *)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+ case SSF_D_LE:
+ {
+ struct aafilter *x = (void *)f->pred;
+
+ if (!(*bytecode = malloc(8))) abort();
+ ((struct inet_diag_bc_op *)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_D_LE, 8, 12 };
+ ((struct inet_diag_bc_op *)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+ case SSF_S_GE:
+ {
+ struct aafilter *x = (void *)f->pred;
+
+ if (!(*bytecode = malloc(8))) abort();
+ ((struct inet_diag_bc_op *)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_S_GE, 8, 12 };
+ ((struct inet_diag_bc_op *)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+ case SSF_S_LE:
+ {
+ struct aafilter *x = (void *)f->pred;
+
+ if (!(*bytecode = malloc(8))) abort();
+ ((struct inet_diag_bc_op *)*bytecode)[0] = (struct inet_diag_bc_op){ INET_DIAG_BC_S_LE, 8, 12 };
+ ((struct inet_diag_bc_op *)*bytecode)[1] = (struct inet_diag_bc_op){ 0, 0, x->port };
+ return 8;
+ }
+
+ case SSF_AND:
+ {
+ char *a1 = NULL, *a2 = NULL, *a;
+ int l1, l2;
+
+ l1 = ssfilter_bytecompile(f->pred, &a1);
+ l2 = ssfilter_bytecompile(f->post, &a2);
+ if (!l1 || !l2) {
+ free(a1);
+ free(a2);
+ return 0;
+ }
+ if (!(a = malloc(l1+l2))) abort();
+ memcpy(a, a1, l1);
+ memcpy(a+l1, a2, l2);
+ free(a1); free(a2);
+ ssfilter_patch(a, l1, l2);
+ *bytecode = a;
+ return l1+l2;
+ }
+ case SSF_OR:
+ {
+ char *a1 = NULL, *a2 = NULL, *a;
+ int l1, l2;
+
+ l1 = ssfilter_bytecompile(f->pred, &a1);
+ l2 = ssfilter_bytecompile(f->post, &a2);
+ if (!l1 || !l2) {
+ free(a1);
+ free(a2);
+ return 0;
+ }
+ if (!(a = malloc(l1+l2+4))) abort();
+ memcpy(a, a1, l1);
+ memcpy(a+l1+4, a2, l2);
+ free(a1); free(a2);
+ *(struct inet_diag_bc_op *)(a+l1) = (struct inet_diag_bc_op){ INET_DIAG_BC_JMP, 4, l2+4 };
+ *bytecode = a;
+ return l1+l2+4;
+ }
+ case SSF_NOT:
+ {
+ char *a1 = NULL, *a;
+ int l1;
+
+ l1 = ssfilter_bytecompile(f->pred, &a1);
+ if (!l1) {
+ free(a1);
+ return 0;
+ }
+ if (!(a = malloc(l1+4))) abort();
+ memcpy(a, a1, l1);
+ free(a1);
+ *(struct inet_diag_bc_op *)(a+l1) = (struct inet_diag_bc_op){ INET_DIAG_BC_JMP, 4, 8 };
+ *bytecode = a;
+ return l1+4;
+ }
+ case SSF_DEVCOND:
+ {
+ /* bytecompile for SSF_DEVCOND not supported yet */
+ return 0;
+ }
+ case SSF_MARKMASK:
+ {
+ struct aafilter *a = (void *)f->pred;
+ struct instr {
+ struct inet_diag_bc_op op;
+ struct inet_diag_markcond cond;
+ };
+ int inslen = sizeof(struct instr);
+
+ if (!(*bytecode = malloc(inslen))) abort();
+ ((struct instr *)*bytecode)[0] = (struct instr) {
+ { INET_DIAG_BC_MARK_COND, inslen, inslen + 4 },
+ { a->mark, a->mask},
+ };
+
+ return inslen;
+ }
+ case SSF_CGROUPCOND:
+ {
+ struct aafilter *a = (void *)f->pred;
+ struct instr {
+ struct inet_diag_bc_op op;
+ __u64 cgroup_id;
+ } __attribute__((packed));
+ int inslen = sizeof(struct instr);
+
+ if (!(*bytecode = malloc(inslen))) abort();
+ ((struct instr *)*bytecode)[0] = (struct instr) {
+ { INET_DIAG_BC_CGROUP_COND, inslen, inslen + 4 },
+ a->cgroup_id,
+ };
+
+ return inslen;
+ }
+ default:
+ abort();
+ }
+}
+
+static int remember_he(struct aafilter *a, struct hostent *he)
+{
+ char **ptr = he->h_addr_list;
+ int cnt = 0;
+ int len;
+
+ if (he->h_addrtype == AF_INET)
+ len = 4;
+ else if (he->h_addrtype == AF_INET6)
+ len = 16;
+ else
+ return 0;
+
+ while (*ptr) {
+ struct aafilter *b = a;
+
+ if (a->addr.bitlen) {
+ if ((b = malloc(sizeof(*b))) == NULL)
+ return cnt;
+ *b = *a;
+ a->next = b;
+ }
+ memcpy(b->addr.data, *ptr, len);
+ b->addr.bytelen = len;
+ b->addr.bitlen = len*8;
+ b->addr.family = he->h_addrtype;
+ ptr++;
+ cnt++;
+ }
+ return cnt;
+}
+
+static int get_dns_host(struct aafilter *a, const char *addr, int fam)
+{
+ static int notfirst;
+ int cnt = 0;
+ struct hostent *he;
+
+ a->addr.bitlen = 0;
+ if (!notfirst) {
+ sethostent(1);
+ notfirst = 1;
+ }
+ he = gethostbyname2(addr, fam == AF_UNSPEC ? AF_INET : fam);
+ if (he)
+ cnt = remember_he(a, he);
+ if (fam == AF_UNSPEC) {
+ he = gethostbyname2(addr, AF_INET6);
+ if (he)
+ cnt += remember_he(a, he);
+ }
+ return !cnt;
+}
+
+static int xll_initted;
+
+static void xll_init(void)
+{
+ struct rtnl_handle rth;
+
+ if (rtnl_open(&rth, 0) < 0)
+ exit(1);
+
+ ll_init_map(&rth);
+ rtnl_close(&rth);
+ xll_initted = 1;
+}
+
+static const char *xll_index_to_name(int index)
+{
+ if (!xll_initted)
+ xll_init();
+ return ll_index_to_name(index);
+}
+
+static int xll_name_to_index(const char *dev)
+{
+ if (!xll_initted)
+ xll_init();
+ return ll_name_to_index(dev);
+}
+
+void *parse_devcond(char *name)
+{
+ struct aafilter a = { .iface = 0 };
+ struct aafilter *res;
+
+ a.iface = xll_name_to_index(name);
+ if (a.iface == 0) {
+ char *end;
+ unsigned long n;
+
+ n = strtoul(name, &end, 0);
+ if (!end || end == name || *end || n > UINT_MAX)
+ return NULL;
+
+ a.iface = n;
+ }
+
+ res = malloc(sizeof(*res));
+ *res = a;
+
+ return res;
+}
+
+static void vsock_set_inet_prefix(inet_prefix *a, __u32 cid)
+{
+ *a = (inet_prefix){
+ .bytelen = sizeof(cid),
+ .family = AF_VSOCK,
+ };
+ memcpy(a->data, &cid, sizeof(cid));
+}
+
+static char* find_port(char *addr, bool is_port)
+{
+ char *port = NULL;
+ if (is_port)
+ port = addr;
+ else
+ port = strchr(addr, ':');
+ if (port && *port == ':')
+ *port++ = '\0';
+ return port;
+}
+
+void *parse_hostcond(char *addr, bool is_port)
+{
+ char *port = NULL;
+ struct aafilter a = { .port = -1 };
+ struct aafilter *res;
+ int fam = preferred_family;
+ struct filter *f = &current_filter;
+
+ if (strncmp(addr, "unix:", 5) == 0) {
+ fam = AF_UNIX;
+ addr += 5;
+ } else if (strncmp(addr, "link:", 5) == 0) {
+ fam = AF_PACKET;
+ addr += 5;
+ } else if (strncmp(addr, "netlink:", 8) == 0) {
+ fam = AF_NETLINK;
+ addr += 8;
+ } else if (strncmp(addr, "vsock:", 6) == 0) {
+ fam = AF_VSOCK;
+ addr += 6;
+ } else if (strncmp(addr, "inet:", 5) == 0) {
+ fam = AF_INET;
+ addr += 5;
+ } else if (strncmp(addr, "inet6:", 6) == 0) {
+ fam = AF_INET6;
+ addr += 6;
+ }
+
+ if (fam == AF_UNIX) {
+ char *p;
+
+ a.addr.family = AF_UNIX;
+ p = strdup(addr);
+ a.addr.bitlen = 8*strlen(p);
+ memcpy(a.addr.data, &p, sizeof(p));
+ goto out;
+ }
+
+ if (fam == AF_PACKET) {
+ a.addr.family = AF_PACKET;
+ a.addr.bitlen = 0;
+ port = find_port(addr, is_port);
+ if (port) {
+ if (*port && strcmp(port, "*")) {
+ if (get_long(&a.port, port, 0)) {
+ if ((a.port = xll_name_to_index(port)) <= 0)
+ return NULL;
+ }
+ }
+ }
+ if (!is_port && addr[0] && strcmp(addr, "*")) {
+ unsigned short tmp;
+
+ a.addr.bitlen = 32;
+ if (ll_proto_a2n(&tmp, addr))
+ return NULL;
+ a.addr.data[0] = ntohs(tmp);
+ }
+ goto out;
+ }
+
+ if (fam == AF_NETLINK) {
+ a.addr.family = AF_NETLINK;
+ a.addr.bitlen = 0;
+ port = find_port(addr, is_port);
+ if (port) {
+ if (*port && strcmp(port, "*")) {
+ if (get_long(&a.port, port, 0)) {
+ if (strcmp(port, "kernel") == 0)
+ a.port = 0;
+ else
+ return NULL;
+ }
+ }
+ }
+ if (!is_port && addr[0] && strcmp(addr, "*")) {
+ a.addr.bitlen = 32;
+ if (nl_proto_a2n(&a.addr.data[0], addr) == -1)
+ return NULL;
+ }
+ goto out;
+ }
+
+ if (fam == AF_VSOCK) {
+ __u32 cid = ~(__u32)0;
+
+ a.addr.family = AF_VSOCK;
+
+ port = find_port(addr, is_port);
+
+ if (port && strcmp(port, "*") &&
+ get_u32((__u32 *)&a.port, port, 0))
+ return NULL;
+
+ if (!is_port && addr[0] && strcmp(addr, "*")) {
+ a.addr.bitlen = 32;
+ if (get_u32(&cid, addr, 0))
+ return NULL;
+ }
+ vsock_set_inet_prefix(&a.addr, cid);
+ goto out;
+ }
+
+ /* URL-like literal [] */
+ if (addr[0] == '[') {
+ addr++;
+ if ((port = strchr(addr, ']')) == NULL)
+ return NULL;
+ *port++ = 0;
+ } else if (addr[0] == '*') {
+ port = addr+1;
+ } else {
+ port = strrchr(strchr(addr, '/') ? : addr, ':');
+ }
+
+ if (is_port)
+ port = addr;
+
+ if (port && *port) {
+ if (*port == ':')
+ *port++ = 0;
+
+ if (*port && *port != '*') {
+ if (get_long(&a.port, port, 0)) {
+ struct servent *se1 = NULL;
+ struct servent *se2 = NULL;
+
+ if (current_filter.dbs&(1<<UDP_DB))
+ se1 = getservbyname(port, UDP_PROTO);
+ if (current_filter.dbs&(1<<TCP_DB))
+ se2 = getservbyname(port, TCP_PROTO);
+ if (se1 && se2 && se1->s_port != se2->s_port) {
+ fprintf(stderr, "Error: ambiguous port \"%s\".\n", port);
+ return NULL;
+ }
+ if (!se1)
+ se1 = se2;
+ if (se1) {
+ a.port = ntohs(se1->s_port);
+ } else {
+ struct scache *s;
+
+ for (s = rlist; s; s = s->next) {
+ if ((s->proto == UDP_PROTO &&
+ (current_filter.dbs&(1<<UDP_DB))) ||
+ (s->proto == TCP_PROTO &&
+ (current_filter.dbs&(1<<TCP_DB)))) {
+ if (s->name && strcmp(s->name, port) == 0) {
+ if (a.port > 0 && a.port != s->port) {
+ fprintf(stderr, "Error: ambiguous port \"%s\".\n", port);
+ return NULL;
+ }
+ a.port = s->port;
+ }
+ }
+ }
+ if (a.port <= 0) {
+ fprintf(stderr, "Error: \"%s\" does not look like a port.\n", port);
+ return NULL;
+ }
+ }
+ }
+ }
+ }
+ if (!is_port && *addr && *addr != '*') {
+ if (get_prefix_1(&a.addr, addr, fam)) {
+ if (get_dns_host(&a, addr, fam)) {
+ fprintf(stderr, "Error: an inet prefix is expected rather than \"%s\".\n", addr);
+ return NULL;
+ }
+ }
+ }
+
+out:
+ if (fam != AF_UNSPEC) {
+ int states = f->states;
+ f->families = 0;
+ filter_af_set(f, fam);
+ filter_states_set(f, states);
+ }
+
+ res = malloc(sizeof(*res));
+ if (res)
+ memcpy(res, &a, sizeof(a));
+ return res;
+}
+
+void *parse_markmask(const char *markmask)
+{
+ struct aafilter a, *res;
+
+ if (strchr(markmask, '/')) {
+ if (sscanf(markmask, "%i/%i", &a.mark, &a.mask) != 2)
+ return NULL;
+ } else {
+ a.mask = 0xffffffff;
+ if (sscanf(markmask, "%i", &a.mark) != 1)
+ return NULL;
+ }
+
+ res = malloc(sizeof(*res));
+ if (res)
+ memcpy(res, &a, sizeof(a));
+ return res;
+}
+
+void *parse_cgroupcond(const char *path)
+{
+ struct aafilter *res;
+ __u64 id;
+
+ id = get_cgroup2_id(path);
+ if (!id)
+ return NULL;
+
+ res = malloc(sizeof(*res));
+ if (res)
+ res->cgroup_id = id;
+
+ return res;
+}
+
+static void proc_ctx_print(struct sockstat *s)
+{
+ char *buf;
+
+ if (show_proc_ctx || show_sock_ctx) {
+ if (find_entry(s->ino, &buf,
+ (show_proc_ctx & show_sock_ctx) ?
+ PROC_SOCK_CTX : PROC_CTX) > 0) {
+ out(" users:(%s)", buf);
+ free(buf);
+ }
+ } else if (show_processes || show_threads) {
+ if (find_entry(s->ino, &buf, USERS) > 0) {
+ out(" users:(%s)", buf);
+ free(buf);
+ }
+ }
+
+ field_next();
+}
+
+static void inet_stats_print(struct sockstat *s, bool v6only)
+{
+ sock_state_print(s);
+
+ inet_addr_print(&s->local, s->lport, s->iface, v6only);
+ inet_addr_print(&s->remote, s->rport, 0, v6only);
+
+ proc_ctx_print(s);
+}
+
+static int proc_parse_inet_addr(char *loc, char *rem, int family, struct
+ sockstat * s)
+{
+ s->local.family = s->remote.family = family;
+ if (family == AF_INET) {
+ sscanf(loc, "%x:%x", s->local.data, (unsigned *)&s->lport);
+ sscanf(rem, "%x:%x", s->remote.data, (unsigned *)&s->rport);
+ s->local.bytelen = s->remote.bytelen = 4;
+ return 0;
+ } else {
+ sscanf(loc, "%08x%08x%08x%08x:%x",
+ s->local.data,
+ s->local.data + 1,
+ s->local.data + 2,
+ s->local.data + 3,
+ &s->lport);
+ sscanf(rem, "%08x%08x%08x%08x:%x",
+ s->remote.data,
+ s->remote.data + 1,
+ s->remote.data + 2,
+ s->remote.data + 3,
+ &s->rport);
+ s->local.bytelen = s->remote.bytelen = 16;
+ return 0;
+ }
+ return -1;
+}
+
+static int proc_inet_split_line(char *line, char **loc, char **rem, char **data)
+{
+ char *p;
+
+ if ((p = strchr(line, ':')) == NULL)
+ return -1;
+
+ *loc = p+2;
+ if ((p = strchr(*loc, ':')) == NULL)
+ return -1;
+
+ p[5] = 0;
+ *rem = p+6;
+ if ((p = strchr(*rem, ':')) == NULL)
+ return -1;
+
+ p[5] = 0;
+ *data = p+6;
+ return 0;
+}
+
+/*
+ * Display bandwidth in standard units
+ * See: https://en.wikipedia.org/wiki/Data-rate_units
+ * bw is in bits per second
+ */
+static char *sprint_bw(char *buf, double bw)
+{
+ if (numeric)
+ sprintf(buf, "%.0f", bw);
+ else if (bw >= 1e12)
+ sprintf(buf, "%.3gT", bw / 1e12);
+ else if (bw >= 1e9)
+ sprintf(buf, "%.3gG", bw / 1e9);
+ else if (bw >= 1e6)
+ sprintf(buf, "%.3gM", bw / 1e6);
+ else if (bw >= 1e3)
+ sprintf(buf, "%.3gk", bw / 1e3);
+ else
+ sprintf(buf, "%g", bw);
+
+ return buf;
+}
+
+static void sctp_stats_print(struct sctp_info *s)
+{
+ if (s->sctpi_tag)
+ out(" tag:%x", s->sctpi_tag);
+ if (s->sctpi_state)
+ out(" state:%s", sctp_sstate_name[s->sctpi_state]);
+ if (s->sctpi_rwnd)
+ out(" rwnd:%d", s->sctpi_rwnd);
+ if (s->sctpi_unackdata)
+ out(" unackdata:%d", s->sctpi_unackdata);
+ if (s->sctpi_penddata)
+ out(" penddata:%d", s->sctpi_penddata);
+ if (s->sctpi_instrms)
+ out(" instrms:%d", s->sctpi_instrms);
+ if (s->sctpi_outstrms)
+ out(" outstrms:%d", s->sctpi_outstrms);
+ if (s->sctpi_inqueue)
+ out(" inqueue:%d", s->sctpi_inqueue);
+ if (s->sctpi_outqueue)
+ out(" outqueue:%d", s->sctpi_outqueue);
+ if (s->sctpi_overall_error)
+ out(" overerr:%d", s->sctpi_overall_error);
+ if (s->sctpi_max_burst)
+ out(" maxburst:%d", s->sctpi_max_burst);
+ if (s->sctpi_maxseg)
+ out(" maxseg:%d", s->sctpi_maxseg);
+ if (s->sctpi_peer_rwnd)
+ out(" prwnd:%d", s->sctpi_peer_rwnd);
+ if (s->sctpi_peer_tag)
+ out(" ptag:%x", s->sctpi_peer_tag);
+ if (s->sctpi_peer_capable)
+ out(" pcapable:%d", s->sctpi_peer_capable);
+ if (s->sctpi_peer_sack)
+ out(" psack:%d", s->sctpi_peer_sack);
+ if (s->sctpi_s_autoclose)
+ out(" autoclose:%d", s->sctpi_s_autoclose);
+ if (s->sctpi_s_adaptation_ind)
+ out(" adapind:%d", s->sctpi_s_adaptation_ind);
+ if (s->sctpi_s_pd_point)
+ out(" pdpoint:%d", s->sctpi_s_pd_point);
+ if (s->sctpi_s_nodelay)
+ out(" nodelay:%d", s->sctpi_s_nodelay);
+ if (s->sctpi_s_disable_fragments)
+ out(" nofrag:%d", s->sctpi_s_disable_fragments);
+ if (s->sctpi_s_v4mapped)
+ out(" v4mapped:%d", s->sctpi_s_v4mapped);
+ if (s->sctpi_s_frag_interleave)
+ out(" fraginl:%d", s->sctpi_s_frag_interleave);
+}
+
+static void tcp_stats_print(struct tcpstat *s)
+{
+ char b1[64];
+
+ if (s->has_ts_opt)
+ out(" ts");
+ if (s->has_usec_ts_opt)
+ out(" usec_ts");
+ if (s->has_sack_opt)
+ out(" sack");
+ if (s->has_ecn_opt)
+ out(" ecn");
+ if (s->has_ecnseen_opt)
+ out(" ecnseen");
+ if (s->has_fastopen_opt)
+ out(" fastopen");
+ if (s->cong_alg[0])
+ out(" %s", s->cong_alg);
+ if (s->has_wscale_opt)
+ out(" wscale:%d,%d", s->snd_wscale, s->rcv_wscale);
+ if (s->rto)
+ out(" rto:%g", s->rto);
+ if (s->backoff)
+ out(" backoff:%u", s->backoff);
+ if (s->rtt)
+ out(" rtt:%g/%g", s->rtt, s->rttvar);
+ if (s->ato)
+ out(" ato:%g", s->ato);
+
+ if (s->qack)
+ out(" qack:%d", s->qack);
+ if (s->qack & 1)
+ out(" bidir");
+
+ if (s->mss)
+ out(" mss:%d", s->mss);
+ if (s->pmtu)
+ out(" pmtu:%u", s->pmtu);
+ if (s->rcv_mss)
+ out(" rcvmss:%d", s->rcv_mss);
+ if (s->advmss)
+ out(" advmss:%d", s->advmss);
+ if (s->cwnd)
+ out(" cwnd:%u", s->cwnd);
+ if (s->ssthresh)
+ out(" ssthresh:%d", s->ssthresh);
+
+ if (s->bytes_sent)
+ out(" bytes_sent:%llu", s->bytes_sent);
+ if (s->bytes_retrans)
+ out(" bytes_retrans:%llu", s->bytes_retrans);
+ if (s->bytes_acked)
+ out(" bytes_acked:%llu", s->bytes_acked);
+ if (s->bytes_received)
+ out(" bytes_received:%llu", s->bytes_received);
+ if (s->segs_out)
+ out(" segs_out:%u", s->segs_out);
+ if (s->segs_in)
+ out(" segs_in:%u", s->segs_in);
+ if (s->data_segs_out)
+ out(" data_segs_out:%u", s->data_segs_out);
+ if (s->data_segs_in)
+ out(" data_segs_in:%u", s->data_segs_in);
+
+ if (s->dctcp && s->dctcp->enabled) {
+ struct dctcpstat *dctcp = s->dctcp;
+
+ out(" dctcp:(ce_state:%u,alpha:%u,ab_ecn:%u,ab_tot:%u)",
+ dctcp->ce_state, dctcp->alpha, dctcp->ab_ecn,
+ dctcp->ab_tot);
+ } else if (s->dctcp) {
+ out(" dctcp:fallback_mode");
+ }
+
+ if (s->bbr_info) {
+ __u64 bw;
+
+ bw = s->bbr_info->bbr_bw_hi;
+ bw <<= 32;
+ bw |= s->bbr_info->bbr_bw_lo;
+
+ out(" bbr:(bw:%sbps,mrtt:%g",
+ sprint_bw(b1, bw * 8.0),
+ (double)s->bbr_info->bbr_min_rtt / 1000.0);
+ if (s->bbr_info->bbr_pacing_gain)
+ out(",pacing_gain:%g",
+ (double)s->bbr_info->bbr_pacing_gain / 256.0);
+ if (s->bbr_info->bbr_cwnd_gain)
+ out(",cwnd_gain:%g",
+ (double)s->bbr_info->bbr_cwnd_gain / 256.0);
+ out(")");
+ }
+
+ if (s->send_bps)
+ out(" send %sbps", sprint_bw(b1, s->send_bps));
+ if (s->lastsnd)
+ out(" lastsnd:%u", s->lastsnd);
+ if (s->lastrcv)
+ out(" lastrcv:%u", s->lastrcv);
+ if (s->lastack)
+ out(" lastack:%u", s->lastack);
+
+ if (s->pacing_rate) {
+ out(" pacing_rate %sbps", sprint_bw(b1, s->pacing_rate));
+ if (s->pacing_rate_max)
+ out("/%sbps", sprint_bw(b1, s->pacing_rate_max));
+ }
+
+ if (s->delivery_rate)
+ out(" delivery_rate %sbps", sprint_bw(b1, s->delivery_rate));
+ if (s->delivered)
+ out(" delivered:%u", s->delivered);
+ if (s->delivered_ce)
+ out(" delivered_ce:%u", s->delivered_ce);
+ if (s->app_limited)
+ out(" app_limited");
+
+ if (s->busy_time) {
+ out(" busy:%llums", s->busy_time / 1000);
+ if (s->rwnd_limited)
+ out(" rwnd_limited:%llums(%.1f%%)",
+ s->rwnd_limited / 1000,
+ 100.0 * s->rwnd_limited / s->busy_time);
+ if (s->sndbuf_limited)
+ out(" sndbuf_limited:%llums(%.1f%%)",
+ s->sndbuf_limited / 1000,
+ 100.0 * s->sndbuf_limited / s->busy_time);
+ }
+
+ if (s->unacked)
+ out(" unacked:%u", s->unacked);
+ if (s->retrans || s->retrans_total)
+ out(" retrans:%u/%u", s->retrans, s->retrans_total);
+ if (s->lost)
+ out(" lost:%u", s->lost);
+ if (s->sacked && s->ss.state != SS_LISTEN)
+ out(" sacked:%u", s->sacked);
+ if (s->dsack_dups)
+ out(" dsack_dups:%u", s->dsack_dups);
+ if (s->fackets)
+ out(" fackets:%u", s->fackets);
+ if (s->reordering != 3)
+ out(" reordering:%d", s->reordering);
+ if (s->reord_seen)
+ out(" reord_seen:%d", s->reord_seen);
+ if (s->rcv_rtt)
+ out(" rcv_rtt:%g", s->rcv_rtt);
+ if (s->rcv_space)
+ out(" rcv_space:%d", s->rcv_space);
+ if (s->rcv_ssthresh)
+ out(" rcv_ssthresh:%u", s->rcv_ssthresh);
+ if (s->not_sent)
+ out(" notsent:%u", s->not_sent);
+ if (s->min_rtt)
+ out(" minrtt:%g", s->min_rtt);
+ if (s->rcv_ooopack)
+ out(" rcv_ooopack:%u", s->rcv_ooopack);
+ if (s->snd_wnd)
+ out(" snd_wnd:%u", s->snd_wnd);
+ if (s->rcv_wnd)
+ out(" rcv_wnd:%u", s->rcv_wnd);
+ if (s->rehash)
+ out(" rehash:%u", s->rehash);
+}
+
+static void tcp_timer_print(struct tcpstat *s)
+{
+ static const char * const tmr_name[] = {
+ "off",
+ "on",
+ "keepalive",
+ "timewait",
+ "persist",
+ "unknown"
+ };
+
+ if (s->timer) {
+ if (s->timer > 4)
+ s->timer = 5;
+ out(" timer:(%s,%s,%d)",
+ tmr_name[s->timer],
+ print_ms_timer(s->timeout),
+ s->retrans);
+ }
+}
+
+static void sctp_timer_print(struct tcpstat *s)
+{
+ if (s->timer)
+ out(" timer:(T3_RTX,%s,%d)",
+ print_ms_timer(s->timeout), s->retrans);
+}
+
+static int tcp_show_line(char *line, const struct filter *f, int family)
+{
+ int rto = 0, ato = 0;
+ struct tcpstat s = {};
+ char *loc, *rem, *data;
+ char opt[256];
+ int n;
+ int hz = get_user_hz();
+
+ if (proc_inet_split_line(line, &loc, &rem, &data))
+ return -1;
+
+ int state = (data[1] >= 'A') ? (data[1] - 'A' + 10) : (data[1] - '0');
+
+ if (!(f->states & (1 << state)))
+ return 0;
+
+ proc_parse_inet_addr(loc, rem, family, &s.ss);
+
+ if (f->f && run_ssfilter(f->f, &s.ss) == 0)
+ return 0;
+
+ opt[0] = 0;
+ n = sscanf(data, "%x %x:%x %x:%x %x %d %d %u %d %llx %d %d %d %u %d %[^\n]\n",
+ &s.ss.state, &s.ss.wq, &s.ss.rq,
+ &s.timer, &s.timeout, &s.retrans, &s.ss.uid, &s.probes,
+ &s.ss.ino, &s.ss.refcnt, &s.ss.sk, &rto, &ato, &s.qack, &s.cwnd,
+ &s.ssthresh, opt);
+
+ if (n < 17)
+ opt[0] = 0;
+
+ if (n < 12) {
+ rto = 0;
+ s.cwnd = 2;
+ s.ssthresh = -1;
+ ato = s.qack = 0;
+ }
+
+ s.retrans = s.timer != 1 ? s.probes : s.retrans;
+ s.timeout = (s.timeout * 1000 + hz - 1) / hz;
+ s.ato = (double)ato / hz;
+ s.qack /= 2;
+ s.rto = (double)rto;
+ s.ssthresh = s.ssthresh == -1 ? 0 : s.ssthresh;
+ s.rto = s.rto != 3 * hz ? s.rto / hz : 0;
+ s.ss.type = IPPROTO_TCP;
+
+ inet_stats_print(&s.ss, false);
+
+ if (show_options)
+ tcp_timer_print(&s);
+
+ if (show_details) {
+ sock_details_print(&s.ss);
+ if (opt[0])
+ out(" opt:\"%s\"", opt);
+ }
+
+ if (show_tcpinfo)
+ tcp_stats_print(&s);
+
+ return 0;
+}
+
+static int generic_record_read(FILE *fp,
+ int (*worker)(char*, const struct filter *, int),
+ const struct filter *f, int fam)
+{
+ char line[256];
+
+ /* skip header */
+ if (fgets(line, sizeof(line), fp) == NULL)
+ goto outerr;
+
+ while (fgets(line, sizeof(line), fp) != NULL) {
+ int n = strlen(line);
+
+ if (n == 0 || line[n-1] != '\n') {
+ errno = -EINVAL;
+ return -1;
+ }
+ line[n-1] = 0;
+
+ if (worker(line, f, fam) < 0)
+ return 0;
+ }
+outerr:
+
+ return ferror(fp) ? -1 : 0;
+}
+
+static void print_skmeminfo(struct rtattr *tb[], int attrtype)
+{
+ const __u32 *skmeminfo;
+
+ if (!tb[attrtype]) {
+ if (attrtype == INET_DIAG_SKMEMINFO) {
+ if (!tb[INET_DIAG_MEMINFO])
+ return;
+
+ const struct inet_diag_meminfo *minfo =
+ RTA_DATA(tb[INET_DIAG_MEMINFO]);
+
+ out(" mem:(r%u,w%u,f%u,t%u)",
+ minfo->idiag_rmem,
+ minfo->idiag_wmem,
+ minfo->idiag_fmem,
+ minfo->idiag_tmem);
+ }
+ return;
+ }
+
+ skmeminfo = RTA_DATA(tb[attrtype]);
+
+ out(" skmem:(r%u,rb%u,t%u,tb%u,f%u,w%u,o%u",
+ skmeminfo[SK_MEMINFO_RMEM_ALLOC],
+ skmeminfo[SK_MEMINFO_RCVBUF],
+ skmeminfo[SK_MEMINFO_WMEM_ALLOC],
+ skmeminfo[SK_MEMINFO_SNDBUF],
+ skmeminfo[SK_MEMINFO_FWD_ALLOC],
+ skmeminfo[SK_MEMINFO_WMEM_QUEUED],
+ skmeminfo[SK_MEMINFO_OPTMEM]);
+
+ if (RTA_PAYLOAD(tb[attrtype]) >=
+ (SK_MEMINFO_BACKLOG + 1) * sizeof(__u32))
+ out(",bl%u", skmeminfo[SK_MEMINFO_BACKLOG]);
+
+ if (RTA_PAYLOAD(tb[attrtype]) >=
+ (SK_MEMINFO_DROPS + 1) * sizeof(__u32))
+ out(",d%u", skmeminfo[SK_MEMINFO_DROPS]);
+
+ out(")");
+}
+
+/* like lib/utils.c print_escape_buf(), but use out(), not printf()! */
+static void out_escape_buf(const __u8 *buf, size_t len, const char *escape)
+{
+ size_t i;
+
+ for (i = 0; i < len; ++i) {
+ if (isprint(buf[i]) && buf[i] != '\\' &&
+ !strchr(escape, buf[i]))
+ out("%c", buf[i]);
+ else
+ out("\\%03o", buf[i]);
+ }
+}
+
+static void print_md5sig(struct tcp_diag_md5sig *sig)
+{
+ out("%s/%d=",
+ format_host(sig->tcpm_family,
+ sig->tcpm_family == AF_INET6 ? 16 : 4,
+ &sig->tcpm_addr),
+ sig->tcpm_prefixlen);
+ out_escape_buf(sig->tcpm_key, sig->tcpm_keylen, " ,");
+}
+
+static void tcp_tls_version(struct rtattr *attr)
+{
+ u_int16_t val;
+
+ if (!attr)
+ return;
+ val = rta_getattr_u16(attr);
+
+ switch (val) {
+ case TLS_1_2_VERSION:
+ out(" version: 1.2");
+ break;
+ case TLS_1_3_VERSION:
+ out(" version: 1.3");
+ break;
+ default:
+ out(" version: unknown(%hu)", val);
+ break;
+ }
+}
+
+static void tcp_tls_cipher(struct rtattr *attr)
+{
+ u_int16_t val;
+
+ if (!attr)
+ return;
+ val = rta_getattr_u16(attr);
+
+ switch (val) {
+ case TLS_CIPHER_AES_GCM_128:
+ out(" cipher: aes-gcm-128");
+ break;
+ case TLS_CIPHER_AES_GCM_256:
+ out(" cipher: aes-gcm-256");
+ break;
+ }
+}
+
+static void tcp_tls_conf(const char *name, struct rtattr *attr)
+{
+ u_int16_t val;
+
+ if (!attr)
+ return;
+ val = rta_getattr_u16(attr);
+
+ switch (val) {
+ case TLS_CONF_BASE:
+ out(" %s: none", name);
+ break;
+ case TLS_CONF_SW:
+ out(" %s: sw", name);
+ break;
+ case TLS_CONF_HW:
+ out(" %s: hw", name);
+ break;
+ case TLS_CONF_HW_RECORD:
+ out(" %s: hw-record", name);
+ break;
+ default:
+ out(" %s: unknown(%hu)", name, val);
+ break;
+ }
+}
+
+static void mptcp_subflow_info(struct rtattr *tb[])
+{
+ u_int32_t flags = 0;
+
+ if (tb[MPTCP_SUBFLOW_ATTR_FLAGS]) {
+ char caps[32 + 1] = { 0 }, *cap = &caps[0];
+
+ flags = rta_getattr_u32(tb[MPTCP_SUBFLOW_ATTR_FLAGS]);
+
+ if (flags & MPTCP_SUBFLOW_FLAG_MCAP_REM)
+ *cap++ = 'M';
+ if (flags & MPTCP_SUBFLOW_FLAG_MCAP_LOC)
+ *cap++ = 'm';
+ if (flags & MPTCP_SUBFLOW_FLAG_JOIN_REM)
+ *cap++ = 'J';
+ if (flags & MPTCP_SUBFLOW_FLAG_JOIN_LOC)
+ *cap++ = 'j';
+ if (flags & MPTCP_SUBFLOW_FLAG_BKUP_REM)
+ *cap++ = 'B';
+ if (flags & MPTCP_SUBFLOW_FLAG_BKUP_LOC)
+ *cap++ = 'b';
+ if (flags & MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED)
+ *cap++ = 'e';
+ if (flags & MPTCP_SUBFLOW_FLAG_CONNECTED)
+ *cap++ = 'c';
+ if (flags & MPTCP_SUBFLOW_FLAG_MAPVALID)
+ *cap++ = 'v';
+ if (flags)
+ out(" flags:%s", caps);
+ }
+ if (tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM] &&
+ tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC] &&
+ tb[MPTCP_SUBFLOW_ATTR_ID_REM] &&
+ tb[MPTCP_SUBFLOW_ATTR_ID_LOC])
+ out(" token:%04x(id:%hhu)/%04x(id:%hhu)",
+ rta_getattr_u32(tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM]),
+ rta_getattr_u8(tb[MPTCP_SUBFLOW_ATTR_ID_REM]),
+ rta_getattr_u32(tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC]),
+ rta_getattr_u8(tb[MPTCP_SUBFLOW_ATTR_ID_LOC]));
+ if (tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ])
+ out(" seq:%llx",
+ rta_getattr_u64(tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ]));
+ if (tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ])
+ out(" sfseq:%x",
+ rta_getattr_u32(tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ]));
+ if (tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET])
+ out(" ssnoff:%x",
+ rta_getattr_u32(tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET]));
+ if (tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN])
+ out(" maplen:%x",
+ rta_getattr_u32(tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN]));
+}
+
+#define TCPI_HAS_OPT(info, opt) !!(info->tcpi_options & (opt))
+
+static void tcp_show_info(const struct nlmsghdr *nlh, struct inet_diag_msg *r,
+ struct rtattr *tb[])
+{
+ double rtt = 0;
+ struct tcpstat s = {};
+
+ s.ss.state = r->idiag_state;
+
+ print_skmeminfo(tb, INET_DIAG_SKMEMINFO);
+
+ if (tb[INET_DIAG_INFO]) {
+ struct tcp_info *info;
+ int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
+
+ /* workaround for older kernels with less fields */
+ if (len < sizeof(*info)) {
+ info = alloca(sizeof(*info));
+ memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len);
+ memset((char *)info + len, 0, sizeof(*info) - len);
+ } else
+ info = RTA_DATA(tb[INET_DIAG_INFO]);
+
+ if (show_options) {
+ s.has_ts_opt = TCPI_HAS_OPT(info, TCPI_OPT_TIMESTAMPS);
+ s.has_usec_ts_opt = TCPI_HAS_OPT(info, TCPI_OPT_USEC_TS);
+ s.has_sack_opt = TCPI_HAS_OPT(info, TCPI_OPT_SACK);
+ s.has_ecn_opt = TCPI_HAS_OPT(info, TCPI_OPT_ECN);
+ s.has_ecnseen_opt = TCPI_HAS_OPT(info, TCPI_OPT_ECN_SEEN);
+ s.has_fastopen_opt = TCPI_HAS_OPT(info, TCPI_OPT_SYN_DATA);
+ }
+
+ if (tb[INET_DIAG_CONG])
+ strncpy(s.cong_alg,
+ rta_getattr_str(tb[INET_DIAG_CONG]),
+ sizeof(s.cong_alg) - 1);
+
+ if (TCPI_HAS_OPT(info, TCPI_OPT_WSCALE)) {
+ s.has_wscale_opt = true;
+ s.snd_wscale = info->tcpi_snd_wscale;
+ s.rcv_wscale = info->tcpi_rcv_wscale;
+ }
+
+ if (info->tcpi_rto && info->tcpi_rto != 3000000)
+ s.rto = (double)info->tcpi_rto / 1000;
+
+ s.backoff = info->tcpi_backoff;
+ s.rtt = (double)info->tcpi_rtt / 1000;
+ s.rttvar = (double)info->tcpi_rttvar / 1000;
+ s.ato = (double)info->tcpi_ato / 1000;
+ s.mss = info->tcpi_snd_mss;
+ s.rcv_mss = info->tcpi_rcv_mss;
+ s.advmss = info->tcpi_advmss;
+ s.rcv_space = info->tcpi_rcv_space;
+ s.rcv_rtt = (double)info->tcpi_rcv_rtt / 1000;
+ s.lastsnd = info->tcpi_last_data_sent;
+ s.lastrcv = info->tcpi_last_data_recv;
+ s.lastack = info->tcpi_last_ack_recv;
+ s.unacked = info->tcpi_unacked;
+ s.retrans = info->tcpi_retrans;
+ s.retrans_total = info->tcpi_total_retrans;
+ s.lost = info->tcpi_lost;
+ s.sacked = info->tcpi_sacked;
+ s.fackets = info->tcpi_fackets;
+ s.reordering = info->tcpi_reordering;
+ s.rcv_ssthresh = info->tcpi_rcv_ssthresh;
+ s.cwnd = info->tcpi_snd_cwnd;
+ s.pmtu = info->tcpi_pmtu;
+
+ if (info->tcpi_snd_ssthresh < 0xFFFF)
+ s.ssthresh = info->tcpi_snd_ssthresh;
+
+ rtt = (double) info->tcpi_rtt;
+ if (tb[INET_DIAG_VEGASINFO]) {
+ const struct tcpvegas_info *vinfo
+ = RTA_DATA(tb[INET_DIAG_VEGASINFO]);
+
+ if (vinfo->tcpv_enabled &&
+ vinfo->tcpv_rtt && vinfo->tcpv_rtt != 0x7fffffff)
+ rtt = vinfo->tcpv_rtt;
+ }
+
+ if (tb[INET_DIAG_DCTCPINFO]) {
+ struct dctcpstat *dctcp = malloc(sizeof(struct
+ dctcpstat));
+
+ const struct tcp_dctcp_info *dinfo
+ = RTA_DATA(tb[INET_DIAG_DCTCPINFO]);
+
+ dctcp->enabled = !!dinfo->dctcp_enabled;
+ dctcp->ce_state = dinfo->dctcp_ce_state;
+ dctcp->alpha = dinfo->dctcp_alpha;
+ dctcp->ab_ecn = dinfo->dctcp_ab_ecn;
+ dctcp->ab_tot = dinfo->dctcp_ab_tot;
+ s.dctcp = dctcp;
+ }
+
+ if (tb[INET_DIAG_BBRINFO]) {
+ const void *bbr_info = RTA_DATA(tb[INET_DIAG_BBRINFO]);
+ int len = min(RTA_PAYLOAD(tb[INET_DIAG_BBRINFO]),
+ sizeof(*s.bbr_info));
+
+ s.bbr_info = calloc(1, sizeof(*s.bbr_info));
+ if (s.bbr_info && bbr_info)
+ memcpy(s.bbr_info, bbr_info, len);
+ }
+
+ if (rtt > 0 && info->tcpi_snd_mss && info->tcpi_snd_cwnd) {
+ s.send_bps = (double) info->tcpi_snd_cwnd *
+ (double)info->tcpi_snd_mss * 8000000. / rtt;
+ }
+
+ if (info->tcpi_pacing_rate &&
+ info->tcpi_pacing_rate != ~0ULL) {
+ s.pacing_rate = info->tcpi_pacing_rate * 8.;
+
+ if (info->tcpi_max_pacing_rate &&
+ info->tcpi_max_pacing_rate != ~0ULL)
+ s.pacing_rate_max = info->tcpi_max_pacing_rate * 8.;
+ }
+ s.bytes_acked = info->tcpi_bytes_acked;
+ s.bytes_received = info->tcpi_bytes_received;
+ s.segs_out = info->tcpi_segs_out;
+ s.segs_in = info->tcpi_segs_in;
+ s.data_segs_out = info->tcpi_data_segs_out;
+ s.data_segs_in = info->tcpi_data_segs_in;
+ s.not_sent = info->tcpi_notsent_bytes;
+ if (info->tcpi_min_rtt && info->tcpi_min_rtt != ~0U)
+ s.min_rtt = (double) info->tcpi_min_rtt / 1000;
+ s.delivery_rate = info->tcpi_delivery_rate * 8.;
+ s.app_limited = info->tcpi_delivery_rate_app_limited;
+ s.busy_time = info->tcpi_busy_time;
+ s.rwnd_limited = info->tcpi_rwnd_limited;
+ s.sndbuf_limited = info->tcpi_sndbuf_limited;
+ s.delivered = info->tcpi_delivered;
+ s.delivered_ce = info->tcpi_delivered_ce;
+ s.dsack_dups = info->tcpi_dsack_dups;
+ s.reord_seen = info->tcpi_reord_seen;
+ s.bytes_sent = info->tcpi_bytes_sent;
+ s.bytes_retrans = info->tcpi_bytes_retrans;
+ s.rcv_ooopack = info->tcpi_rcv_ooopack;
+ s.snd_wnd = info->tcpi_snd_wnd;
+ s.rcv_wnd = info->tcpi_rcv_wnd;
+ s.rehash = info->tcpi_rehash;
+ tcp_stats_print(&s);
+ free(s.dctcp);
+ free(s.bbr_info);
+ }
+ if (tb[INET_DIAG_MD5SIG]) {
+ struct tcp_diag_md5sig *sig = RTA_DATA(tb[INET_DIAG_MD5SIG]);
+ int len = RTA_PAYLOAD(tb[INET_DIAG_MD5SIG]);
+
+ out(" md5keys:");
+ print_md5sig(sig++);
+ for (len -= sizeof(*sig); len > 0; len -= sizeof(*sig)) {
+ out(",");
+ print_md5sig(sig++);
+ }
+ }
+ if (tb[INET_DIAG_ULP_INFO]) {
+ struct rtattr *ulpinfo[INET_ULP_INFO_MAX + 1] = { 0 };
+
+ parse_rtattr_nested(ulpinfo, INET_ULP_INFO_MAX,
+ tb[INET_DIAG_ULP_INFO]);
+
+ if (ulpinfo[INET_ULP_INFO_NAME])
+ out(" tcp-ulp-%s",
+ rta_getattr_str(ulpinfo[INET_ULP_INFO_NAME]));
+
+ if (ulpinfo[INET_ULP_INFO_TLS]) {
+ struct rtattr *tlsinfo[TLS_INFO_MAX + 1] = { 0 };
+
+ parse_rtattr_nested(tlsinfo, TLS_INFO_MAX,
+ ulpinfo[INET_ULP_INFO_TLS]);
+
+ tcp_tls_version(tlsinfo[TLS_INFO_VERSION]);
+ tcp_tls_cipher(tlsinfo[TLS_INFO_CIPHER]);
+ tcp_tls_conf("rxconf", tlsinfo[TLS_INFO_RXCONF]);
+ tcp_tls_conf("txconf", tlsinfo[TLS_INFO_TXCONF]);
+ if (!!tlsinfo[TLS_INFO_ZC_RO_TX])
+ out(" zc_ro_tx");
+ if (!!tlsinfo[TLS_INFO_RX_NO_PAD])
+ out(" no_pad_rx");
+ }
+ if (ulpinfo[INET_ULP_INFO_MPTCP]) {
+ struct rtattr *sfinfo[MPTCP_SUBFLOW_ATTR_MAX + 1] =
+ { 0 };
+
+ parse_rtattr_nested(sfinfo, MPTCP_SUBFLOW_ATTR_MAX,
+ ulpinfo[INET_ULP_INFO_MPTCP]);
+ mptcp_subflow_info(sfinfo);
+ }
+ }
+}
+
+static void mptcp_stats_print(struct mptcp_info *s)
+{
+ if (s->mptcpi_subflows)
+ out(" subflows:%u", s->mptcpi_subflows);
+ if (s->mptcpi_add_addr_signal)
+ out(" add_addr_signal:%u", s->mptcpi_add_addr_signal);
+ if (s->mptcpi_add_addr_accepted)
+ out(" add_addr_accepted:%u", s->mptcpi_add_addr_accepted);
+ if (s->mptcpi_subflows_max)
+ out(" subflows_max:%u", s->mptcpi_subflows_max);
+ if (s->mptcpi_add_addr_signal_max)
+ out(" add_addr_signal_max:%u", s->mptcpi_add_addr_signal_max);
+ if (s->mptcpi_add_addr_accepted_max)
+ out(" add_addr_accepted_max:%u", s->mptcpi_add_addr_accepted_max);
+ if (s->mptcpi_flags & MPTCP_INFO_FLAG_FALLBACK)
+ out(" fallback");
+ if (s->mptcpi_flags & MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED)
+ out(" remote_key");
+ if (s->mptcpi_token)
+ out(" token:%x", s->mptcpi_token);
+ if (s->mptcpi_write_seq)
+ out(" write_seq:%llu", s->mptcpi_write_seq);
+ if (s->mptcpi_snd_una)
+ out(" snd_una:%llu", s->mptcpi_snd_una);
+ if (s->mptcpi_rcv_nxt)
+ out(" rcv_nxt:%llu", s->mptcpi_rcv_nxt);
+ if (s->mptcpi_local_addr_used)
+ out(" local_addr_used:%u", s->mptcpi_local_addr_used);
+ if (s->mptcpi_local_addr_max)
+ out(" local_addr_max:%u", s->mptcpi_local_addr_max);
+ if (s->mptcpi_csum_enabled)
+ out(" csum_enabled:%u", s->mptcpi_csum_enabled);
+ if (s->mptcpi_retransmits)
+ out(" retransmits:%u", s->mptcpi_retransmits);
+ if (s->mptcpi_bytes_retrans)
+ out(" bytes_retrans:%llu", s->mptcpi_bytes_retrans);
+ if (s->mptcpi_bytes_sent)
+ out(" bytes_sent:%llu", s->mptcpi_bytes_sent);
+ if (s->mptcpi_bytes_received)
+ out(" bytes_received:%llu", s->mptcpi_bytes_received);
+ if (s->mptcpi_bytes_acked)
+ out(" bytes_acked:%llu", s->mptcpi_bytes_acked);
+ if (s->mptcpi_subflows_total)
+ out(" subflows_total:%u", s->mptcpi_subflows_total);
+}
+
+static void mptcp_show_info(const struct nlmsghdr *nlh, struct inet_diag_msg *r,
+ struct rtattr *tb[])
+{
+ print_skmeminfo(tb, INET_DIAG_SKMEMINFO);
+
+ if (tb[INET_DIAG_INFO]) {
+ struct mptcp_info *info;
+ int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
+
+ /* workaround for older kernels with less fields */
+ if (len < sizeof(*info)) {
+ info = alloca(sizeof(*info));
+ memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len);
+ memset((char *)info + len, 0, sizeof(*info) - len);
+ } else
+ info = RTA_DATA(tb[INET_DIAG_INFO]);
+
+ mptcp_stats_print(info);
+ }
+}
+
+static const char *format_host_sa(struct sockaddr_storage *sa)
+{
+ union {
+ struct sockaddr_in sin;
+ struct sockaddr_in6 sin6;
+ } *saddr = (void *)sa;
+
+ switch (sa->ss_family) {
+ case AF_INET:
+ return format_host(AF_INET, 4, &saddr->sin.sin_addr);
+ case AF_INET6:
+ return format_host(AF_INET6, 16, &saddr->sin6.sin6_addr);
+ default:
+ return "";
+ }
+}
+
+static void sctp_show_info(const struct nlmsghdr *nlh, struct inet_diag_msg *r,
+ struct rtattr *tb[])
+{
+ struct sockaddr_storage *sa;
+ int len;
+
+ print_skmeminfo(tb, INET_DIAG_SKMEMINFO);
+
+ if (tb[INET_DIAG_LOCALS]) {
+ len = RTA_PAYLOAD(tb[INET_DIAG_LOCALS]);
+ sa = RTA_DATA(tb[INET_DIAG_LOCALS]);
+
+ out(" locals:%s", format_host_sa(sa));
+ for (sa++, len -= sizeof(*sa); len > 0; sa++, len -= sizeof(*sa))
+ out(",%s", format_host_sa(sa));
+
+ }
+ if (tb[INET_DIAG_PEERS]) {
+ len = RTA_PAYLOAD(tb[INET_DIAG_PEERS]);
+ sa = RTA_DATA(tb[INET_DIAG_PEERS]);
+
+ out(" peers:%s", format_host_sa(sa));
+ for (sa++, len -= sizeof(*sa); len > 0; sa++, len -= sizeof(*sa))
+ out(",%s", format_host_sa(sa));
+ }
+ if (tb[INET_DIAG_INFO]) {
+ struct sctp_info *info;
+ len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
+
+ /* workaround for older kernels with less fields */
+ if (len < sizeof(*info)) {
+ info = alloca(sizeof(*info));
+ memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len);
+ memset((char *)info + len, 0, sizeof(*info) - len);
+ } else
+ info = RTA_DATA(tb[INET_DIAG_INFO]);
+
+ sctp_stats_print(info);
+ }
+}
+
+static void parse_diag_msg(struct nlmsghdr *nlh, struct sockstat *s)
+{
+ struct rtattr *tb[INET_DIAG_MAX+1];
+ struct inet_diag_msg *r = NLMSG_DATA(nlh);
+
+ parse_rtattr(tb, INET_DIAG_MAX, (struct rtattr *)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ s->state = r->idiag_state;
+ s->local.family = s->remote.family = r->idiag_family;
+ s->lport = ntohs(r->id.idiag_sport);
+ s->rport = ntohs(r->id.idiag_dport);
+ s->wq = r->idiag_wqueue;
+ s->rq = r->idiag_rqueue;
+ s->ino = r->idiag_inode;
+ s->uid = r->idiag_uid;
+ s->iface = r->id.idiag_if;
+ s->sk = cookie_sk_get(&r->id.idiag_cookie[0]);
+
+ s->mark = 0;
+ if (tb[INET_DIAG_MARK])
+ s->mark = rta_getattr_u32(tb[INET_DIAG_MARK]);
+ s->cgroup_id = 0;
+ if (tb[INET_DIAG_CGROUP_ID])
+ s->cgroup_id = rta_getattr_u64(tb[INET_DIAG_CGROUP_ID]);
+ if (tb[INET_DIAG_PROTOCOL])
+ s->raw_prot = rta_getattr_u8(tb[INET_DIAG_PROTOCOL]);
+ else
+ s->raw_prot = 0;
+
+ if (s->local.family == AF_INET)
+ s->local.bytelen = s->remote.bytelen = 4;
+ else
+ s->local.bytelen = s->remote.bytelen = 16;
+
+ memcpy(s->local.data, r->id.idiag_src, s->local.bytelen);
+ memcpy(s->remote.data, r->id.idiag_dst, s->local.bytelen);
+}
+
+static int inet_show_sock(struct nlmsghdr *nlh,
+ struct sockstat *s)
+{
+ struct rtattr *tb[INET_DIAG_MAX+1];
+ struct inet_diag_msg *r = NLMSG_DATA(nlh);
+ unsigned char v6only = 0;
+
+ parse_rtattr(tb, INET_DIAG_MAX, (struct rtattr *)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ if (tb[INET_DIAG_PROTOCOL])
+ s->type = rta_getattr_u8(tb[INET_DIAG_PROTOCOL]);
+
+ if (s->local.family == AF_INET6 && tb[INET_DIAG_SKV6ONLY])
+ v6only = rta_getattr_u8(tb[INET_DIAG_SKV6ONLY]);
+
+ inet_stats_print(s, v6only);
+
+ if (show_options) {
+ struct tcpstat t = {};
+
+ t.timer = r->idiag_timer;
+ t.timeout = r->idiag_expires;
+ t.retrans = r->idiag_retrans;
+ if (s->type == IPPROTO_SCTP)
+ sctp_timer_print(&t);
+ else
+ tcp_timer_print(&t);
+ }
+
+ if (show_details) {
+ sock_details_print(s);
+ if (s->local.family == AF_INET6 && tb[INET_DIAG_SKV6ONLY])
+ out(" v6only:%u", v6only);
+
+ if (tb[INET_DIAG_SHUTDOWN]) {
+ unsigned char mask;
+
+ mask = rta_getattr_u8(tb[INET_DIAG_SHUTDOWN]);
+ out(" %c-%c",
+ mask & 1 ? '-' : '<', mask & 2 ? '-' : '>');
+ }
+ }
+
+ if (show_tos) {
+ if (tb[INET_DIAG_TOS])
+ out(" tos:%#x", rta_getattr_u8(tb[INET_DIAG_TOS]));
+ if (tb[INET_DIAG_TCLASS])
+ out(" tclass:%#x", rta_getattr_u8(tb[INET_DIAG_TCLASS]));
+ if (tb[INET_DIAG_CLASS_ID])
+ out(" class_id:%#x", rta_getattr_u32(tb[INET_DIAG_CLASS_ID]));
+ }
+
+ if (show_cgroup) {
+ if (tb[INET_DIAG_CGROUP_ID])
+ out(" cgroup:%s", cg_id_to_path(rta_getattr_u64(tb[INET_DIAG_CGROUP_ID])));
+ }
+
+ if (show_inet_sockopt) {
+ if (tb[INET_DIAG_SOCKOPT] && RTA_PAYLOAD(tb[INET_DIAG_SOCKOPT]) >=
+ sizeof(struct inet_diag_sockopt)) {
+ const struct inet_diag_sockopt *sockopt =
+ RTA_DATA(tb[INET_DIAG_SOCKOPT]);
+ if (!oneline)
+ out("\n\tinet-sockopt: (");
+ else
+ out(" inet-sockopt: (");
+ if (sockopt->recverr)
+ out(" recverr");
+ if (sockopt->is_icsk)
+ out(" is_icsk");
+ if (sockopt->freebind)
+ out(" freebind");
+ if (sockopt->hdrincl)
+ out(" hdrincl");
+ if (sockopt->mc_loop)
+ out(" mc_loop");
+ if (sockopt->transparent)
+ out(" transparent");
+ if (sockopt->mc_all)
+ out(" mc_all");
+ if (sockopt->nodefrag)
+ out(" nodefrag");
+ if (sockopt->bind_address_no_port)
+ out(" bind_addr_no_port");
+ if (sockopt->recverr_rfc4884)
+ out(" recverr_rfc4884");
+ if (sockopt->defer_connect)
+ out(" defer_connect");
+ out(")");
+ }
+ }
+
+ if (show_mem || (show_tcpinfo && s->type != IPPROTO_UDP)) {
+ if (!oneline)
+ out("\n\t");
+ if (s->type == IPPROTO_SCTP)
+ sctp_show_info(nlh, r, tb);
+ else if (s->type == IPPROTO_MPTCP)
+ mptcp_show_info(nlh, r, tb);
+ else
+ tcp_show_info(nlh, r, tb);
+ }
+ sctp_ino = s->ino;
+
+ return 0;
+}
+
+static int tcpdiag_send(int fd, int protocol, struct filter *f)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ struct {
+ struct nlmsghdr nlh;
+ struct inet_diag_req r;
+ } req = {
+ .nlh.nlmsg_len = sizeof(req),
+ .nlh.nlmsg_flags = NLM_F_ROOT | NLM_F_MATCH | NLM_F_REQUEST,
+ .nlh.nlmsg_seq = MAGIC_SEQ,
+ .r.idiag_family = AF_INET,
+ .r.idiag_states = f->states,
+ };
+ char *bc = NULL;
+ int bclen;
+ struct msghdr msg;
+ struct rtattr rta;
+ struct iovec iov[3];
+ int iovlen = 1;
+
+ if (protocol == IPPROTO_TCP)
+ req.nlh.nlmsg_type = TCPDIAG_GETSOCK;
+ else if (protocol == IPPROTO_DCCP)
+ req.nlh.nlmsg_type = DCCPDIAG_GETSOCK;
+ else
+ return -1;
+
+ if (show_mem) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_MEMINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_SKMEMINFO-1));
+ }
+
+ if (show_tcpinfo) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_INFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_VEGASINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_CONG-1));
+ }
+
+ if (show_tos) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_TOS-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_TCLASS-1));
+ }
+
+ iov[0] = (struct iovec){
+ .iov_base = &req,
+ .iov_len = sizeof(req)
+ };
+ if (f->f) {
+ bclen = ssfilter_bytecompile(f->f, &bc);
+ if (bclen) {
+ rta.rta_type = INET_DIAG_REQ_BYTECODE;
+ rta.rta_len = RTA_LENGTH(bclen);
+ iov[1] = (struct iovec){ &rta, sizeof(rta) };
+ iov[2] = (struct iovec){ bc, bclen };
+ req.nlh.nlmsg_len += RTA_LENGTH(bclen);
+ iovlen = 3;
+ }
+ }
+
+ msg = (struct msghdr) {
+ .msg_name = (void *)&nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = iovlen,
+ };
+
+ if (sendmsg(fd, &msg, 0) < 0) {
+ close(fd);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int sockdiag_send(int family, int fd, int protocol, struct filter *f)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ DIAG_REQUEST(req, struct inet_diag_req_v2 r);
+ char *bc = NULL;
+ int bclen;
+ __u32 proto;
+ struct msghdr msg;
+ struct rtattr rta_bc;
+ struct rtattr rta_proto;
+ struct iovec iov[5];
+ int iovlen = 1;
+
+ if (family == PF_UNSPEC)
+ return tcpdiag_send(fd, protocol, f);
+
+ memset(&req.r, 0, sizeof(req.r));
+ req.r.sdiag_family = family;
+ req.r.sdiag_protocol = protocol;
+ req.r.idiag_states = f->states;
+ if (show_mem) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_MEMINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_SKMEMINFO-1));
+ }
+
+ if (show_tcpinfo) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_INFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_VEGASINFO-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_CONG-1));
+ }
+
+ if (show_tos) {
+ req.r.idiag_ext |= (1<<(INET_DIAG_TOS-1));
+ req.r.idiag_ext |= (1<<(INET_DIAG_TCLASS-1));
+ }
+
+ iov[0] = (struct iovec){
+ .iov_base = &req,
+ .iov_len = sizeof(req)
+ };
+ if (f->f) {
+ bclen = ssfilter_bytecompile(f->f, &bc);
+ if (bclen) {
+ rta_bc.rta_type = INET_DIAG_REQ_BYTECODE;
+ rta_bc.rta_len = RTA_LENGTH(bclen);
+ iov[1] = (struct iovec){ &rta_bc, sizeof(rta_bc) };
+ iov[2] = (struct iovec){ bc, bclen };
+ req.nlh.nlmsg_len += RTA_LENGTH(bclen);
+ iovlen = 3;
+ }
+ }
+
+ /* put extended protocol attribute, if required */
+ if (protocol > 255) {
+ rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
+ rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+ proto = protocol;
+ iov[iovlen] = (struct iovec){ &rta_proto, sizeof(rta_proto) };
+ iov[iovlen + 1] = (struct iovec){ &proto, sizeof(proto) };
+ req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
+ iovlen += 2;
+ }
+
+ msg = (struct msghdr) {
+ .msg_name = (void *)&nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = iovlen,
+ };
+
+ if (sendmsg(fd, &msg, 0) < 0) {
+ close(fd);
+ return -1;
+ }
+
+ return 0;
+}
+
+struct inet_diag_arg {
+ struct filter *f;
+ int protocol;
+ struct rtnl_handle *rth;
+};
+
+static int kill_inet_sock(struct nlmsghdr *h, void *arg, struct sockstat *s)
+{
+ struct inet_diag_msg *d = NLMSG_DATA(h);
+ struct inet_diag_arg *diag_arg = arg;
+ struct rtnl_handle *rth = diag_arg->rth;
+
+ DIAG_REQUEST(req, struct inet_diag_req_v2 r);
+
+ req.nlh.nlmsg_type = SOCK_DESTROY;
+ req.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nlh.nlmsg_seq = ++rth->seq;
+ req.r.sdiag_family = d->idiag_family;
+ req.r.sdiag_protocol = diag_arg->protocol;
+ req.r.id = d->id;
+
+ if (diag_arg->protocol == IPPROTO_RAW) {
+ struct inet_diag_req_raw *raw = (void *)&req.r;
+
+ BUILD_BUG_ON(sizeof(req.r) != sizeof(*raw));
+ raw->sdiag_raw_protocol = s->raw_prot;
+ }
+
+ return rtnl_talk(rth, &req.nlh, NULL);
+}
+
+static int show_one_inet_sock(struct nlmsghdr *h, void *arg)
+{
+ int err;
+ struct inet_diag_arg *diag_arg = arg;
+ struct inet_diag_msg *r = NLMSG_DATA(h);
+ struct sockstat s = {};
+
+ if (!(diag_arg->f->families & FAMILY_MASK(r->idiag_family)))
+ return 0;
+
+ parse_diag_msg(h, &s);
+ s.type = diag_arg->protocol;
+
+ if (diag_arg->f->f && run_ssfilter(diag_arg->f->f, &s) == 0)
+ return 0;
+
+ if (diag_arg->f->kill && kill_inet_sock(h, arg, &s) != 0) {
+ if (errno == EOPNOTSUPP || errno == ENOENT) {
+ /* Socket can't be closed, or is already closed. */
+ return 0;
+ } else {
+ perror("SOCK_DESTROY answers");
+ return -1;
+ }
+ }
+
+ err = inet_show_sock(h, &s);
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
+static int inet_show_netlink(struct filter *f, FILE *dump_fp, int protocol)
+{
+ int err = 0;
+ struct rtnl_handle rth, rth2;
+ int family = PF_INET;
+ struct inet_diag_arg arg = { .f = f, .protocol = protocol };
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_SOCK_DIAG))
+ return -1;
+
+ if (f->kill) {
+ if (rtnl_open_byproto(&rth2, 0, NETLINK_SOCK_DIAG)) {
+ rtnl_close(&rth);
+ return -1;
+ }
+ arg.rth = &rth2;
+ }
+
+ rth.dump = MAGIC_SEQ;
+ rth.dump_fp = dump_fp;
+ if (preferred_family == PF_INET6)
+ family = PF_INET6;
+
+ /* extended protocol will use INET_DIAG_REQ_PROTOCOL,
+ * not supported by older kernels. On such kernel
+ * rtnl_dump will bail with rtnl_dump_error().
+ * Suppress the error to avoid confusing the user
+ */
+ if (protocol > 255)
+ rth.flags |= RTNL_HANDLE_F_SUPPRESS_NLERR;
+
+again:
+ if ((err = sockdiag_send(family, rth.fd, protocol, f)))
+ goto Exit;
+
+ if ((err = rtnl_dump_filter(&rth, show_one_inet_sock, &arg))) {
+ if (family != PF_UNSPEC) {
+ family = PF_UNSPEC;
+ goto again;
+ }
+ goto Exit;
+ }
+ if (family == PF_INET && preferred_family != PF_INET) {
+ family = PF_INET6;
+ goto again;
+ }
+
+Exit:
+ rtnl_close(&rth);
+ if (arg.rth)
+ rtnl_close(arg.rth);
+ return err;
+}
+
+static int tcp_show_netlink_file(struct filter *f)
+{
+ FILE *fp;
+ char buf[16384];
+ int err = -1;
+
+ if ((fp = fopen(getenv("TCPDIAG_FILE"), "r")) == NULL) {
+ perror("fopen($TCPDIAG_FILE)");
+ return err;
+ }
+
+ while (1) {
+ int err2;
+ size_t status, nitems;
+ struct nlmsghdr *h = (struct nlmsghdr *)buf;
+ struct sockstat s = {};
+
+ status = fread(buf, 1, sizeof(*h), fp);
+ if (status != sizeof(*h)) {
+ if (ferror(fp))
+ perror("Reading header from $TCPDIAG_FILE");
+ if (feof(fp))
+ fprintf(stderr, "Unexpected EOF reading $TCPDIAG_FILE");
+ break;
+ }
+
+ nitems = NLMSG_ALIGN(h->nlmsg_len - sizeof(*h));
+ status = fread(h+1, 1, nitems, fp);
+
+ if (status != nitems) {
+ if (ferror(fp))
+ perror("Reading $TCPDIAG_FILE");
+ if (feof(fp))
+ fprintf(stderr, "Unexpected EOF reading $TCPDIAG_FILE");
+ break;
+ }
+
+ /* The only legal exit point */
+ if (h->nlmsg_type == NLMSG_DONE) {
+ err = 0;
+ break;
+ }
+
+ 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;
+ perror("TCPDIAG answered");
+ }
+ break;
+ }
+
+ parse_diag_msg(h, &s);
+ s.type = IPPROTO_TCP;
+
+ if (f && f->f && run_ssfilter(f->f, &s) == 0)
+ continue;
+
+ err2 = inet_show_sock(h, &s);
+ if (err2 < 0) {
+ err = err2;
+ break;
+ }
+ }
+
+ fclose(fp);
+ return err;
+}
+
+static int tcp_show(struct filter *f)
+{
+ FILE *fp = NULL;
+ char *buf = NULL;
+ int bufsize = 1024*1024;
+
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ dg_proto = TCP_PROTO;
+
+ if (getenv("TCPDIAG_FILE"))
+ return tcp_show_netlink_file(f);
+
+ if (!getenv("PROC_NET_TCP") && !getenv("PROC_ROOT")
+ && inet_show_netlink(f, NULL, IPPROTO_TCP) == 0)
+ return 0;
+
+ /* Sigh... We have to parse /proc/net/tcp... */
+ while (bufsize >= 64*1024) {
+ if ((buf = malloc(bufsize)) != NULL)
+ break;
+ bufsize /= 2;
+ }
+ if (buf == NULL) {
+ errno = ENOMEM;
+ return -1;
+ }
+
+ if (f->families & FAMILY_MASK(AF_INET)) {
+ if ((fp = net_tcp_open()) == NULL)
+ goto outerr;
+
+ setbuffer(fp, buf, bufsize);
+ if (generic_record_read(fp, tcp_show_line, f, AF_INET))
+ goto outerr;
+ fclose(fp);
+ }
+
+ if ((f->families & FAMILY_MASK(AF_INET6)) &&
+ (fp = net_tcp6_open()) != NULL) {
+ setbuffer(fp, buf, bufsize);
+ if (generic_record_read(fp, tcp_show_line, f, AF_INET6))
+ goto outerr;
+ fclose(fp);
+ }
+
+ free(buf);
+ return 0;
+
+outerr:
+ do {
+ int saved_errno = errno;
+
+ free(buf);
+ if (fp)
+ fclose(fp);
+ errno = saved_errno;
+ return -1;
+ } while (0);
+}
+
+static int mptcp_show(struct filter *f)
+{
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ if (!getenv("PROC_NET_MPTCP") && !getenv("PROC_ROOT")
+ && inet_show_netlink(f, NULL, IPPROTO_MPTCP) == 0)
+ return 0;
+
+ return 0;
+}
+
+static int dccp_show(struct filter *f)
+{
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ if (!getenv("PROC_NET_DCCP") && !getenv("PROC_ROOT")
+ && inet_show_netlink(f, NULL, IPPROTO_DCCP) == 0)
+ return 0;
+
+ return 0;
+}
+
+static int sctp_show(struct filter *f)
+{
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ if (!getenv("PROC_NET_SCTP") && !getenv("PROC_ROOT")
+ && inet_show_netlink(f, NULL, IPPROTO_SCTP) == 0)
+ return 0;
+
+ return 0;
+}
+
+static int dgram_show_line(char *line, const struct filter *f, int family)
+{
+ struct sockstat s = {};
+ char *loc, *rem, *data;
+ char opt[256];
+ int n;
+
+ if (proc_inet_split_line(line, &loc, &rem, &data))
+ return -1;
+
+ int state = (data[1] >= 'A') ? (data[1] - 'A' + 10) : (data[1] - '0');
+
+ if (!(f->states & (1 << state)))
+ return 0;
+
+ proc_parse_inet_addr(loc, rem, family, &s);
+
+ if (f->f && run_ssfilter(f->f, &s) == 0)
+ return 0;
+
+ opt[0] = 0;
+ n = sscanf(data, "%x %x:%x %*x:%*x %*x %d %*d %u %d %llx %[^\n]\n",
+ &s.state, &s.wq, &s.rq,
+ &s.uid, &s.ino,
+ &s.refcnt, &s.sk, opt);
+
+ if (n < 9)
+ opt[0] = 0;
+
+ s.type = dg_proto == UDP_PROTO ? IPPROTO_UDP : 0;
+ inet_stats_print(&s, false);
+
+ if (show_details && opt[0])
+ out(" opt:\"%s\"", opt);
+
+ return 0;
+}
+
+static int udp_show(struct filter *f)
+{
+ FILE *fp = NULL;
+
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ dg_proto = UDP_PROTO;
+
+ if (!getenv("PROC_NET_UDP") && !getenv("PROC_ROOT")
+ && inet_show_netlink(f, NULL, IPPROTO_UDP) == 0)
+ return 0;
+
+ if (f->families&FAMILY_MASK(AF_INET)) {
+ if ((fp = net_udp_open()) == NULL)
+ goto outerr;
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET))
+ goto outerr;
+ fclose(fp);
+ }
+
+ if ((f->families&FAMILY_MASK(AF_INET6)) &&
+ (fp = net_udp6_open()) != NULL) {
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET6))
+ goto outerr;
+ fclose(fp);
+ }
+ return 0;
+
+outerr:
+ do {
+ int saved_errno = errno;
+
+ if (fp)
+ fclose(fp);
+ errno = saved_errno;
+ return -1;
+ } while (0);
+}
+
+static int raw_show(struct filter *f)
+{
+ FILE *fp = NULL;
+
+ if (!filter_af_get(f, AF_INET) && !filter_af_get(f, AF_INET6))
+ return 0;
+
+ dg_proto = RAW_PROTO;
+
+ if (!getenv("PROC_NET_RAW") && !getenv("PROC_ROOT") &&
+ inet_show_netlink(f, NULL, IPPROTO_RAW) == 0)
+ return 0;
+
+ if (f->families&FAMILY_MASK(AF_INET)) {
+ if ((fp = net_raw_open()) == NULL)
+ goto outerr;
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET))
+ goto outerr;
+ fclose(fp);
+ }
+
+ if ((f->families&FAMILY_MASK(AF_INET6)) &&
+ (fp = net_raw6_open()) != NULL) {
+ if (generic_record_read(fp, dgram_show_line, f, AF_INET6))
+ goto outerr;
+ fclose(fp);
+ }
+ return 0;
+
+outerr:
+ do {
+ int saved_errno = errno;
+
+ if (fp)
+ fclose(fp);
+ errno = saved_errno;
+ return -1;
+ } while (0);
+}
+
+#define MAX_UNIX_REMEMBER (1024*1024/sizeof(struct sockstat))
+
+static void unix_list_drop_first(struct sockstat **list)
+{
+ struct sockstat *s = *list;
+
+ (*list) = (*list)->next;
+ free(s->name);
+ free(s);
+}
+
+static bool unix_type_skip(struct sockstat *s, struct filter *f)
+{
+ if (s->type == SOCK_STREAM && !(f->dbs&(1<<UNIX_ST_DB)))
+ return true;
+ if (s->type == SOCK_DGRAM && !(f->dbs&(1<<UNIX_DG_DB)))
+ return true;
+ if (s->type == SOCK_SEQPACKET && !(f->dbs&(1<<UNIX_SQ_DB)))
+ return true;
+ return false;
+}
+
+static void unix_stats_print(struct sockstat *s, struct filter *f)
+{
+ char port_name[30] = {};
+
+ sock_state_print(s);
+
+ sock_addr_print(s->name ?: "*", " ",
+ uint_to_str(s->lport, port_name), NULL);
+ sock_addr_print(s->peer_name ?: "*", " ",
+ uint_to_str(s->rport, port_name), NULL);
+
+ proc_ctx_print(s);
+}
+
+static int unix_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+ struct filter *f = (struct filter *)arg;
+ struct unix_diag_msg *r = NLMSG_DATA(nlh);
+ struct rtattr *tb[UNIX_DIAG_MAX+1];
+ char name[128];
+ struct sockstat stat = { .name = "*", .peer_name = "*" };
+
+ parse_rtattr(tb, UNIX_DIAG_MAX, (struct rtattr *)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ stat.type = r->udiag_type;
+ stat.state = r->udiag_state;
+ stat.ino = stat.lport = r->udiag_ino;
+ stat.local.family = stat.remote.family = AF_UNIX;
+
+ if (unix_type_skip(&stat, f))
+ return 0;
+
+ if (tb[UNIX_DIAG_RQLEN]) {
+ struct unix_diag_rqlen *rql = RTA_DATA(tb[UNIX_DIAG_RQLEN]);
+
+ stat.rq = rql->udiag_rqueue;
+ stat.wq = rql->udiag_wqueue;
+ }
+ if (tb[UNIX_DIAG_NAME]) {
+ int len = RTA_PAYLOAD(tb[UNIX_DIAG_NAME]);
+
+ memcpy(name, RTA_DATA(tb[UNIX_DIAG_NAME]), len);
+ name[len] = '\0';
+ if (name[0] == '\0') {
+ int i;
+ for (i = 0; i < len; i++)
+ if (name[i] == '\0')
+ name[i] = '@';
+ }
+ stat.name = &name[0];
+ memcpy(stat.local.data, &stat.name, sizeof(stat.name));
+ }
+ if (tb[UNIX_DIAG_PEER])
+ stat.rport = rta_getattr_u32(tb[UNIX_DIAG_PEER]);
+
+ if (f->f && run_ssfilter(f->f, &stat) == 0)
+ return 0;
+
+ unix_stats_print(&stat, f);
+
+ if (show_mem)
+ print_skmeminfo(tb, UNIX_DIAG_MEMINFO);
+ if (show_details) {
+ if (tb[UNIX_DIAG_SHUTDOWN]) {
+ unsigned char mask;
+
+ mask = rta_getattr_u8(tb[UNIX_DIAG_SHUTDOWN]);
+ out(" %c-%c",
+ mask & 1 ? '-' : '<', mask & 2 ? '-' : '>');
+ }
+ if (tb[UNIX_DIAG_VFS]) {
+ struct unix_diag_vfs *uv = RTA_DATA(tb[UNIX_DIAG_VFS]);
+
+ out(" ino:%u dev:%u/%u", uv->udiag_vfs_ino, major(uv->udiag_vfs_dev),
+ minor(uv->udiag_vfs_dev));
+ }
+ if (tb[UNIX_DIAG_ICONS]) {
+ int len = RTA_PAYLOAD(tb[UNIX_DIAG_ICONS]);
+ __u32 *peers = RTA_DATA(tb[UNIX_DIAG_ICONS]);
+ int i;
+
+ out(" peers:");
+ for (i = 0; i < len / sizeof(__u32); i++)
+ out(" %u", peers[i]);
+ }
+ }
+
+ return 0;
+}
+
+static int handle_netlink_request(struct filter *f, struct nlmsghdr *req,
+ size_t size, rtnl_filter_t show_one_sock)
+{
+ int ret = -1;
+ struct rtnl_handle rth;
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_SOCK_DIAG))
+ return -1;
+
+ rth.dump = MAGIC_SEQ;
+
+ if (rtnl_send(&rth, req, size) < 0)
+ goto Exit;
+
+ if (rtnl_dump_filter(&rth, show_one_sock, f))
+ goto Exit;
+
+ ret = 0;
+Exit:
+ rtnl_close(&rth);
+ return ret;
+}
+
+static int unix_show_netlink(struct filter *f)
+{
+ DIAG_REQUEST(req, struct unix_diag_req r);
+
+ req.r.sdiag_family = AF_UNIX;
+ req.r.udiag_states = f->states;
+ req.r.udiag_show = UDIAG_SHOW_NAME | UDIAG_SHOW_PEER | UDIAG_SHOW_RQLEN;
+ if (show_mem)
+ req.r.udiag_show |= UDIAG_SHOW_MEMINFO;
+ if (show_details)
+ req.r.udiag_show |= UDIAG_SHOW_VFS | UDIAG_SHOW_ICONS;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), unix_show_sock);
+}
+
+static int unix_show(struct filter *f)
+{
+ FILE *fp;
+ char buf[256];
+ char name[128];
+ int newformat = 0;
+ int cnt;
+ struct sockstat *list = NULL;
+ const int unix_state_map[] = { SS_CLOSE, SS_SYN_SENT,
+ SS_ESTABLISHED, SS_CLOSING };
+
+ if (!filter_af_get(f, AF_UNIX))
+ return 0;
+
+ if (!getenv("PROC_NET_UNIX") && !getenv("PROC_ROOT")
+ && unix_show_netlink(f) == 0)
+ return 0;
+
+ if ((fp = net_unix_open()) == NULL)
+ return -1;
+ if (!fgets(buf, sizeof(buf), fp)) {
+ fclose(fp);
+ return -1;
+ }
+
+ if (memcmp(buf, "Peer", 4) == 0)
+ newformat = 1;
+ cnt = 0;
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ struct sockstat *u, **insp;
+ int flags;
+
+ if (!(u = calloc(1, sizeof(*u))))
+ break;
+
+ if (sscanf(buf, "%x: %x %x %x %x %x %d %s",
+ &u->rport, &u->rq, &u->wq, &flags, &u->type,
+ &u->state, &u->ino, name) < 8)
+ name[0] = 0;
+
+ u->lport = u->ino;
+ u->local.family = u->remote.family = AF_UNIX;
+
+ if (flags & (1 << 16)) {
+ u->state = SS_LISTEN;
+ } else if (u->state > 0 &&
+ u->state <= ARRAY_SIZE(unix_state_map)) {
+ u->state = unix_state_map[u->state-1];
+ if (u->type == SOCK_DGRAM && u->state == SS_CLOSE && u->rport)
+ u->state = SS_ESTABLISHED;
+ }
+ if (unix_type_skip(u, f) ||
+ !(f->states & (1 << u->state))) {
+ free(u);
+ continue;
+ }
+
+ if (!newformat) {
+ u->rport = 0;
+ u->rq = 0;
+ u->wq = 0;
+ }
+
+ if (name[0]) {
+ u->name = strdup(name);
+ if (!u->name) {
+ free(u);
+ break;
+ }
+ }
+
+ if (u->rport) {
+ struct sockstat *p;
+
+ for (p = list; p; p = p->next) {
+ if (u->rport == p->lport)
+ break;
+ }
+ if (!p)
+ u->peer_name = "?";
+ else
+ u->peer_name = p->name ? : "*";
+ }
+
+ if (f->f) {
+ struct sockstat st = {
+ .local.family = AF_UNIX,
+ .remote.family = AF_UNIX,
+ };
+
+ memcpy(st.local.data, &u->name, sizeof(u->name));
+ /* when parsing the old format rport is set to 0 and
+ * therefore peer_name remains NULL
+ */
+ if (u->peer_name && strcmp(u->peer_name, "*"))
+ memcpy(st.remote.data, &u->peer_name,
+ sizeof(u->peer_name));
+ if (run_ssfilter(f->f, &st) == 0) {
+ free(u->name);
+ free(u);
+ continue;
+ }
+ }
+
+ insp = &list;
+ while (*insp) {
+ if (u->type < (*insp)->type ||
+ (u->type == (*insp)->type &&
+ u->ino < (*insp)->ino))
+ break;
+ insp = &(*insp)->next;
+ }
+ u->next = *insp;
+ *insp = u;
+
+ if (++cnt > MAX_UNIX_REMEMBER) {
+ while (list) {
+ unix_stats_print(list, f);
+ unix_list_drop_first(&list);
+ }
+ cnt = 0;
+ }
+ }
+ fclose(fp);
+ while (list) {
+ unix_stats_print(list, f);
+ unix_list_drop_first(&list);
+ }
+
+ return 0;
+}
+
+static int packet_stats_print(struct sockstat *s, const struct filter *f)
+{
+ const char *addr, *port;
+ char ll_name[16];
+
+ s->local.family = s->remote.family = AF_PACKET;
+
+ if (f->f) {
+ s->local.data[0] = s->prot;
+ if (run_ssfilter(f->f, s) == 0)
+ return 1;
+ }
+
+ sock_state_print(s);
+
+ if (s->prot == 3)
+ addr = "*";
+ else
+ addr = ll_proto_n2a(htons(s->prot), ll_name, sizeof(ll_name));
+
+ if (s->iface == 0)
+ port = "*";
+ else
+ port = xll_index_to_name(s->iface);
+
+ sock_addr_print(addr, ":", port, NULL);
+ sock_addr_print("", "*", "", NULL);
+
+ proc_ctx_print(s);
+
+ if (show_details)
+ sock_details_print(s);
+
+ return 0;
+}
+
+static void packet_show_ring(struct packet_diag_ring *ring)
+{
+ out("blk_size:%d", ring->pdr_block_size);
+ out(",blk_nr:%d", ring->pdr_block_nr);
+ out(",frm_size:%d", ring->pdr_frame_size);
+ out(",frm_nr:%d", ring->pdr_frame_nr);
+ out(",tmo:%d", ring->pdr_retire_tmo);
+ out(",features:0x%x", ring->pdr_features);
+}
+
+static int packet_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+ const struct filter *f = arg;
+ struct packet_diag_msg *r = NLMSG_DATA(nlh);
+ struct packet_diag_info *pinfo = NULL;
+ struct packet_diag_ring *ring_rx = NULL, *ring_tx = NULL;
+ struct rtattr *tb[PACKET_DIAG_MAX+1];
+ struct sockstat stat = {};
+ uint32_t fanout = 0;
+ bool has_fanout = false;
+
+ 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;
+
+ stat.type = r->pdiag_type;
+ stat.prot = r->pdiag_num;
+ stat.ino = r->pdiag_ino;
+ stat.state = SS_CLOSE;
+ stat.sk = cookie_sk_get(&r->pdiag_cookie[0]);
+
+ if (tb[PACKET_DIAG_MEMINFO]) {
+ __u32 *skmeminfo = RTA_DATA(tb[PACKET_DIAG_MEMINFO]);
+
+ stat.rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+ }
+
+ if (tb[PACKET_DIAG_INFO]) {
+ pinfo = RTA_DATA(tb[PACKET_DIAG_INFO]);
+ stat.lport = stat.iface = pinfo->pdi_index;
+ }
+
+ if (tb[PACKET_DIAG_UID])
+ stat.uid = rta_getattr_u32(tb[PACKET_DIAG_UID]);
+
+ if (tb[PACKET_DIAG_RX_RING])
+ ring_rx = RTA_DATA(tb[PACKET_DIAG_RX_RING]);
+
+ if (tb[PACKET_DIAG_TX_RING])
+ ring_tx = RTA_DATA(tb[PACKET_DIAG_TX_RING]);
+
+ if (tb[PACKET_DIAG_FANOUT]) {
+ has_fanout = true;
+ fanout = rta_getattr_u32(tb[PACKET_DIAG_FANOUT]);
+ }
+
+ if (packet_stats_print(&stat, f))
+ return 0;
+
+ if (show_details) {
+ if (pinfo) {
+ if (oneline)
+ out(" ver:%d", pinfo->pdi_version);
+ else
+ out("\n\tver:%d", pinfo->pdi_version);
+ out(" cpy_thresh:%d", pinfo->pdi_copy_thresh);
+ out(" flags( ");
+ if (pinfo->pdi_flags & PDI_RUNNING)
+ out("running");
+ if (pinfo->pdi_flags & PDI_AUXDATA)
+ out(" auxdata");
+ if (pinfo->pdi_flags & PDI_ORIGDEV)
+ out(" origdev");
+ if (pinfo->pdi_flags & PDI_VNETHDR)
+ out(" vnethdr");
+ if (pinfo->pdi_flags & PDI_LOSS)
+ out(" loss");
+ if (!pinfo->pdi_flags)
+ out("0");
+ out(" )");
+ }
+ if (ring_rx) {
+ if (oneline)
+ out(" ring_rx(");
+ else
+ out("\n\tring_rx(");
+ packet_show_ring(ring_rx);
+ out(")");
+ }
+ if (ring_tx) {
+ if (oneline)
+ out(" ring_tx(");
+ else
+ out("\n\tring_tx(");
+ packet_show_ring(ring_tx);
+ out(")");
+ }
+ if (has_fanout) {
+ uint16_t type = (fanout >> 16) & 0xffff;
+
+ if (oneline)
+ out(" fanout(");
+ else
+ out("\n\tfanout(");
+ out("id:%d,", fanout & 0xffff);
+ out("type:");
+
+ if (type == 0)
+ out("hash");
+ else if (type == 1)
+ out("lb");
+ else if (type == 2)
+ out("cpu");
+ else if (type == 3)
+ out("roll");
+ else if (type == 4)
+ out("random");
+ else if (type == 5)
+ out("qm");
+ else
+ out("0x%x", type);
+
+ out(")");
+ }
+ }
+
+ 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);
+
+ if (oneline)
+ out(" bpf filter (%d): ", num);
+ else
+ out("\n\tbpf filter (%d): ", num);
+ while (num) {
+ out(" 0x%02x %u %u %u,",
+ fil->code, fil->jt, fil->jf, fil->k);
+ num--;
+ fil++;
+ }
+ }
+
+ if (show_mem)
+ print_skmeminfo(tb, PACKET_DIAG_MEMINFO);
+ return 0;
+}
+
+static int packet_show_netlink(struct filter *f)
+{
+ DIAG_REQUEST(req, struct packet_diag_req r);
+
+ req.r.sdiag_family = AF_PACKET;
+ req.r.pdiag_show = PACKET_SHOW_INFO | PACKET_SHOW_MEMINFO |
+ PACKET_SHOW_FILTER | PACKET_SHOW_RING_CFG | PACKET_SHOW_FANOUT;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), packet_show_sock);
+}
+
+static int packet_show_line(char *buf, const struct filter *f, int fam)
+{
+ unsigned long long sk;
+ struct sockstat stat = {};
+ int type, prot, iface, state, rq, uid, ino;
+
+ sscanf(buf, "%llx %*d %d %x %d %d %u %u %u",
+ &sk,
+ &type, &prot, &iface, &state,
+ &rq, &uid, &ino);
+
+ if (type == SOCK_RAW && !(f->dbs & (1<<PACKET_R_DB)))
+ return 0;
+ if (type == SOCK_DGRAM && !(f->dbs & (1<<PACKET_DG_DB)))
+ return 0;
+
+ stat.type = type;
+ stat.prot = prot;
+ stat.lport = stat.iface = iface;
+ stat.state = state;
+ stat.rq = rq;
+ stat.uid = uid;
+ stat.ino = ino;
+ stat.state = SS_CLOSE;
+
+ if (packet_stats_print(&stat, f))
+ return 0;
+
+ return 0;
+}
+
+static int packet_show(struct filter *f)
+{
+ FILE *fp;
+ int rc = 0;
+
+ if (!filter_af_get(f, AF_PACKET) || !(f->states & (1 << SS_CLOSE)))
+ return 0;
+
+ if (!getenv("PROC_NET_PACKET") && !getenv("PROC_ROOT") &&
+ packet_show_netlink(f) == 0)
+ return 0;
+
+ if ((fp = net_packet_open()) == NULL)
+ return -1;
+ if (generic_record_read(fp, packet_show_line, f, AF_PACKET))
+ rc = -1;
+
+ fclose(fp);
+ return rc;
+}
+
+static int xdp_stats_print(struct sockstat *s, const struct filter *f)
+{
+ const char *addr, *port;
+ char q_str[16];
+
+ s->local.family = s->remote.family = AF_XDP;
+
+ if (f->f) {
+ if (run_ssfilter(f->f, s) == 0)
+ return 1;
+ }
+
+ sock_state_print(s);
+
+ if (s->iface) {
+ addr = xll_index_to_name(s->iface);
+ snprintf(q_str, sizeof(q_str), "q%d", s->lport);
+ port = q_str;
+ sock_addr_print(addr, ":", port, NULL);
+ } else {
+ sock_addr_print("", "*", "", NULL);
+ }
+
+ sock_addr_print("", "*", "", NULL);
+
+ proc_ctx_print(s);
+
+ if (show_details)
+ sock_details_print(s);
+
+ return 0;
+}
+
+static void xdp_show_ring(const char *name, struct xdp_diag_ring *ring)
+{
+ if (oneline)
+ out(" %s(", name);
+ else
+ out("\n\t%s(", name);
+ out("entries:%u", ring->entries);
+ out(")");
+}
+
+static void xdp_show_umem(struct xdp_diag_umem *umem, struct xdp_diag_ring *fr,
+ struct xdp_diag_ring *cr)
+{
+ if (oneline)
+ out(" tumem(");
+ else
+ out("\n\tumem(");
+ out("id:%u", umem->id);
+ out(",size:%llu", umem->size);
+ out(",num_pages:%u", umem->num_pages);
+ out(",chunk_size:%u", umem->chunk_size);
+ out(",headroom:%u", umem->headroom);
+ out(",ifindex:%u", umem->ifindex);
+ out(",qid:%u", umem->queue_id);
+ out(",zc:%u", umem->flags & XDP_DU_F_ZEROCOPY);
+ out(",refs:%u", umem->refs);
+ out(")");
+
+ if (fr)
+ xdp_show_ring("fr", fr);
+ if (cr)
+ xdp_show_ring("cr", cr);
+}
+
+static void xdp_show_stats(struct xdp_diag_stats *stats)
+{
+ if (oneline)
+ out(" stats(");
+ else
+ out("\n\tstats(");
+ out("rx dropped:%llu", stats->n_rx_dropped);
+ out(",rx invalid:%llu", stats->n_rx_invalid);
+ out(",rx queue full:%llu", stats->n_rx_full);
+ out(",rx fill ring empty:%llu", stats->n_fill_ring_empty);
+ out(",tx invalid:%llu", stats->n_tx_invalid);
+ out(",tx ring empty:%llu", stats->n_tx_ring_empty);
+ out(")");
+}
+
+static int xdp_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+ struct xdp_diag_ring *rx = NULL, *tx = NULL, *fr = NULL, *cr = NULL;
+ struct xdp_diag_msg *msg = NLMSG_DATA(nlh);
+ struct rtattr *tb[XDP_DIAG_MAX + 1];
+ struct xdp_diag_info *info = NULL;
+ struct xdp_diag_umem *umem = NULL;
+ struct xdp_diag_stats *stats = NULL;
+ const struct filter *f = arg;
+ struct sockstat stat = {};
+
+ parse_rtattr(tb, XDP_DIAG_MAX, (struct rtattr *)(msg + 1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*msg)));
+
+ stat.type = msg->xdiag_type;
+ stat.ino = msg->xdiag_ino;
+ stat.state = SS_CLOSE;
+ stat.sk = cookie_sk_get(&msg->xdiag_cookie[0]);
+
+ if (tb[XDP_DIAG_INFO]) {
+ info = RTA_DATA(tb[XDP_DIAG_INFO]);
+ stat.iface = info->ifindex;
+ stat.lport = info->queue_id;
+ }
+
+ if (tb[XDP_DIAG_UID])
+ stat.uid = rta_getattr_u32(tb[XDP_DIAG_UID]);
+ if (tb[XDP_DIAG_RX_RING])
+ rx = RTA_DATA(tb[XDP_DIAG_RX_RING]);
+ if (tb[XDP_DIAG_TX_RING])
+ tx = RTA_DATA(tb[XDP_DIAG_TX_RING]);
+ if (tb[XDP_DIAG_UMEM])
+ umem = RTA_DATA(tb[XDP_DIAG_UMEM]);
+ if (tb[XDP_DIAG_UMEM_FILL_RING])
+ fr = RTA_DATA(tb[XDP_DIAG_UMEM_FILL_RING]);
+ if (tb[XDP_DIAG_UMEM_COMPLETION_RING])
+ cr = RTA_DATA(tb[XDP_DIAG_UMEM_COMPLETION_RING]);
+ if (tb[XDP_DIAG_MEMINFO]) {
+ __u32 *skmeminfo = RTA_DATA(tb[XDP_DIAG_MEMINFO]);
+
+ stat.rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+ }
+ if (tb[XDP_DIAG_STATS])
+ stats = RTA_DATA(tb[XDP_DIAG_STATS]);
+
+ if (xdp_stats_print(&stat, f))
+ return 0;
+
+ if (show_details) {
+ if (rx)
+ xdp_show_ring("rx", rx);
+ if (tx)
+ xdp_show_ring("tx", tx);
+ if (umem)
+ xdp_show_umem(umem, fr, cr);
+ if (stats)
+ xdp_show_stats(stats);
+ }
+
+ if (show_mem)
+ print_skmeminfo(tb, XDP_DIAG_MEMINFO); // really?
+
+
+ return 0;
+}
+
+static int xdp_show(struct filter *f)
+{
+ DIAG_REQUEST(req, struct xdp_diag_req r);
+
+ if (!filter_af_get(f, AF_XDP) || !(f->states & (1 << SS_CLOSE)))
+ return 0;
+
+ req.r.sdiag_family = AF_XDP;
+ req.r.xdiag_show = XDP_SHOW_INFO | XDP_SHOW_RING_CFG | XDP_SHOW_UMEM |
+ XDP_SHOW_MEMINFO | XDP_SHOW_STATS;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), xdp_show_sock);
+}
+
+static int netlink_show_one(struct filter *f,
+ int prot, int pid, unsigned int groups,
+ int state, int dst_pid, unsigned int dst_group,
+ int rq, int wq,
+ unsigned long long sk, unsigned long long cb)
+{
+ struct sockstat st = {
+ .state = SS_CLOSE,
+ .rq = rq,
+ .wq = wq,
+ .local.family = AF_NETLINK,
+ .remote.family = AF_NETLINK,
+ };
+
+ SPRINT_BUF(prot_buf) = {};
+ const char *prot_name;
+ char procname[64] = {};
+
+ if (f->f) {
+ st.rport = -1;
+ st.lport = pid;
+ st.local.data[0] = prot;
+ if (run_ssfilter(f->f, &st) == 0)
+ return 1;
+ }
+
+ sock_state_print(&st);
+
+ prot_name = nl_proto_n2a(prot, prot_buf, sizeof(prot_buf));
+
+ if (pid == -1) {
+ procname[0] = '*';
+ } else if (!numeric) {
+ int done = 0;
+
+ if (!pid) {
+ done = 1;
+ strncpy(procname, "kernel", 7);
+ } else if (pid > 0) {
+ FILE *fp;
+
+ snprintf(procname, sizeof(procname), "%s/%d/stat",
+ getenv("PROC_ROOT") ? : "/proc", pid);
+ if ((fp = fopen(procname, "r")) != NULL) {
+ if (fscanf(fp, "%*d (%[^)])", procname) == 1) {
+ snprintf(procname+strlen(procname),
+ sizeof(procname)-strlen(procname),
+ "/%d", pid);
+ done = 1;
+ }
+ fclose(fp);
+ }
+ }
+ if (!done)
+ int_to_str(pid, procname);
+ } else {
+ int_to_str(pid, procname);
+ }
+
+ sock_addr_print(prot_name, ":", procname, NULL);
+
+ if (state == NETLINK_CONNECTED) {
+ char dst_group_buf[30];
+ char dst_pid_buf[30];
+
+ sock_addr_print(int_to_str(dst_group, dst_group_buf), ":",
+ int_to_str(dst_pid, dst_pid_buf), NULL);
+ } else {
+ sock_addr_print("", "*", "", NULL);
+ }
+
+ char *pid_context = NULL;
+
+ if (show_proc_ctx) {
+ /* The pid value will either be:
+ * 0 if destination kernel - show kernel initial context.
+ * A valid process pid - use getpidcon.
+ * A unique value allocated by the kernel or netlink user
+ * to the process - show context as "not available".
+ */
+ if (!pid)
+ security_get_initial_context("kernel", &pid_context);
+ else if (pid > 0)
+ getpidcon(pid, &pid_context);
+
+ out(" proc_ctx=%s", pid_context ? : "unavailable");
+ freecon(pid_context);
+ }
+
+ if (show_details) {
+ out(" sk=%llx cb=%llx groups=0x%08x", sk, cb, groups);
+ }
+
+ return 0;
+}
+
+static int netlink_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+ struct filter *f = (struct filter *)arg;
+ struct netlink_diag_msg *r = NLMSG_DATA(nlh);
+ struct rtattr *tb[NETLINK_DIAG_MAX+1];
+ int rq = 0, wq = 0;
+ unsigned long groups = 0;
+
+ parse_rtattr(tb, NETLINK_DIAG_MAX, (struct rtattr *)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ if (tb[NETLINK_DIAG_GROUPS] && RTA_PAYLOAD(tb[NETLINK_DIAG_GROUPS]))
+ groups = *(unsigned long *) RTA_DATA(tb[NETLINK_DIAG_GROUPS]);
+
+ if (tb[NETLINK_DIAG_MEMINFO]) {
+ const __u32 *skmeminfo;
+
+ skmeminfo = RTA_DATA(tb[NETLINK_DIAG_MEMINFO]);
+
+ rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+ wq = skmeminfo[SK_MEMINFO_WMEM_ALLOC];
+ }
+
+ if (netlink_show_one(f, r->ndiag_protocol, r->ndiag_portid, groups,
+ r->ndiag_state, r->ndiag_dst_portid, r->ndiag_dst_group,
+ rq, wq, 0, 0)) {
+ return 0;
+ }
+
+ if (show_mem) {
+ out("\t");
+ print_skmeminfo(tb, NETLINK_DIAG_MEMINFO);
+ }
+
+ return 0;
+}
+
+static int netlink_show_netlink(struct filter *f)
+{
+ DIAG_REQUEST(req, struct netlink_diag_req r);
+
+ req.r.sdiag_family = AF_NETLINK;
+ req.r.sdiag_protocol = NDIAG_PROTO_ALL;
+ req.r.ndiag_show = NDIAG_SHOW_GROUPS | NDIAG_SHOW_MEMINFO;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), netlink_show_sock);
+}
+
+static int netlink_show(struct filter *f)
+{
+ FILE *fp;
+ char buf[256];
+ int prot, pid;
+ unsigned int groups;
+ int rq, wq, rc;
+ unsigned long long sk, cb;
+
+ if (!filter_af_get(f, AF_NETLINK) || !(f->states & (1 << SS_CLOSE)))
+ return 0;
+
+ if (!getenv("PROC_NET_NETLINK") && !getenv("PROC_ROOT") &&
+ netlink_show_netlink(f) == 0)
+ return 0;
+
+ if ((fp = net_netlink_open()) == NULL)
+ return -1;
+ if (!fgets(buf, sizeof(buf), fp)) {
+ fclose(fp);
+ return -1;
+ }
+
+ while (fgets(buf, sizeof(buf), fp)) {
+ sscanf(buf, "%llx %d %d %x %d %d %llx %d",
+ &sk,
+ &prot, &pid, &groups, &rq, &wq, &cb, &rc);
+
+ netlink_show_one(f, prot, pid, groups, 0, 0, 0, rq, wq, sk, cb);
+ }
+
+ fclose(fp);
+ return 0;
+}
+
+static bool vsock_type_skip(struct sockstat *s, struct filter *f)
+{
+ if (s->type == SOCK_STREAM && !(f->dbs & (1 << VSOCK_ST_DB)))
+ return true;
+ if (s->type == SOCK_DGRAM && !(f->dbs & (1 << VSOCK_DG_DB)))
+ return true;
+ return false;
+}
+
+static void vsock_addr_print(inet_prefix *a, __u32 port)
+{
+ char cid_str[sizeof("4294967295")];
+ char port_str[sizeof("4294967295")];
+ __u32 cid;
+
+ memcpy(&cid, a->data, sizeof(cid));
+
+ if (cid == ~(__u32)0)
+ snprintf(cid_str, sizeof(cid_str), "*");
+ else
+ snprintf(cid_str, sizeof(cid_str), "%u", cid);
+
+ if (port == ~(__u32)0)
+ snprintf(port_str, sizeof(port_str), "*");
+ else
+ snprintf(port_str, sizeof(port_str), "%u", port);
+
+ sock_addr_print(cid_str, ":", port_str, NULL);
+}
+
+static void vsock_stats_print(struct sockstat *s, struct filter *f)
+{
+ sock_state_print(s);
+
+ vsock_addr_print(&s->local, s->lport);
+ vsock_addr_print(&s->remote, s->rport);
+
+ proc_ctx_print(s);
+}
+
+static int vsock_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+ struct filter *f = (struct filter *)arg;
+ struct vsock_diag_msg *r = NLMSG_DATA(nlh);
+ struct sockstat stat = {
+ .type = r->vdiag_type,
+ .lport = r->vdiag_src_port,
+ .rport = r->vdiag_dst_port,
+ .state = r->vdiag_state,
+ .ino = r->vdiag_ino,
+ };
+
+ vsock_set_inet_prefix(&stat.local, r->vdiag_src_cid);
+ vsock_set_inet_prefix(&stat.remote, r->vdiag_dst_cid);
+
+ if (vsock_type_skip(&stat, f))
+ return 0;
+
+ if (f->f && run_ssfilter(f->f, &stat) == 0)
+ return 0;
+
+ vsock_stats_print(&stat, f);
+
+ return 0;
+}
+
+static int vsock_show(struct filter *f)
+{
+ DIAG_REQUEST(req, struct vsock_diag_req r);
+
+ if (!filter_af_get(f, AF_VSOCK))
+ return 0;
+
+ req.r.sdiag_family = AF_VSOCK;
+ req.r.vdiag_states = f->states;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), vsock_show_sock);
+}
+
+static void tipc_sock_addr_print(struct rtattr *net_addr, struct rtattr *id)
+{
+ uint32_t node = rta_getattr_u32(net_addr);
+ uint32_t identity = rta_getattr_u32(id);
+
+ SPRINT_BUF(addr) = {};
+ SPRINT_BUF(port) = {};
+
+ sprintf(addr, "%u", node);
+ sprintf(port, "%u", identity);
+ sock_addr_print(addr, ":", port, NULL);
+
+}
+
+static int tipc_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+ struct rtattr *stat[TIPC_NLA_SOCK_STAT_MAX + 1] = {};
+ struct rtattr *attrs[TIPC_NLA_SOCK_MAX + 1] = {};
+ struct rtattr *con[TIPC_NLA_CON_MAX + 1] = {};
+ struct rtattr *info[TIPC_NLA_MAX + 1] = {};
+ struct rtattr *msg_ref;
+ struct sockstat ss = {};
+
+ parse_rtattr(info, TIPC_NLA_MAX, NLMSG_DATA(nlh),
+ NLMSG_PAYLOAD(nlh, 0));
+
+ if (!info[TIPC_NLA_SOCK])
+ return 0;
+
+ msg_ref = info[TIPC_NLA_SOCK];
+ parse_rtattr(attrs, TIPC_NLA_SOCK_MAX, RTA_DATA(msg_ref),
+ RTA_PAYLOAD(msg_ref));
+
+ msg_ref = attrs[TIPC_NLA_SOCK_STAT];
+ parse_rtattr(stat, TIPC_NLA_SOCK_STAT_MAX,
+ RTA_DATA(msg_ref), RTA_PAYLOAD(msg_ref));
+
+
+ ss.local.family = AF_TIPC;
+ ss.type = rta_getattr_u32(attrs[TIPC_NLA_SOCK_TYPE]);
+ ss.state = rta_getattr_u32(attrs[TIPC_NLA_SOCK_TIPC_STATE]);
+ ss.uid = rta_getattr_u32(attrs[TIPC_NLA_SOCK_UID]);
+ ss.ino = rta_getattr_u32(attrs[TIPC_NLA_SOCK_INO]);
+ ss.rq = rta_getattr_u32(stat[TIPC_NLA_SOCK_STAT_RCVQ]);
+ ss.wq = rta_getattr_u32(stat[TIPC_NLA_SOCK_STAT_SENDQ]);
+ ss.sk = rta_getattr_u64(attrs[TIPC_NLA_SOCK_COOKIE]);
+
+ sock_state_print (&ss);
+
+ tipc_sock_addr_print(attrs[TIPC_NLA_SOCK_ADDR],
+ attrs[TIPC_NLA_SOCK_REF]);
+
+ msg_ref = attrs[TIPC_NLA_SOCK_CON];
+ if (msg_ref) {
+ parse_rtattr(con, TIPC_NLA_CON_MAX,
+ RTA_DATA(msg_ref), RTA_PAYLOAD(msg_ref));
+
+ tipc_sock_addr_print(con[TIPC_NLA_CON_NODE],
+ con[TIPC_NLA_CON_SOCK]);
+ } else
+ sock_addr_print("", "-", "", NULL);
+
+ if (show_details)
+ sock_details_print(&ss);
+
+ proc_ctx_print(&ss);
+
+ if (show_tipcinfo) {
+ if (oneline)
+ out(" type:%s", stype_nameg[ss.type]);
+ else
+ out("\n type:%s", stype_nameg[ss.type]);
+ out(" cong:%s ",
+ stat[TIPC_NLA_SOCK_STAT_LINK_CONG] ? "link" :
+ stat[TIPC_NLA_SOCK_STAT_CONN_CONG] ? "conn" : "none");
+ out(" drop:%d ",
+ rta_getattr_u32(stat[TIPC_NLA_SOCK_STAT_DROP]));
+
+ if (attrs[TIPC_NLA_SOCK_HAS_PUBL])
+ out(" publ");
+
+ if (con[TIPC_NLA_CON_FLAG])
+ out(" via {%u,%u} ",
+ rta_getattr_u32(con[TIPC_NLA_CON_TYPE]),
+ rta_getattr_u32(con[TIPC_NLA_CON_INST]));
+ }
+
+ return 0;
+}
+
+static int tipc_show(struct filter *f)
+{
+ DIAG_REQUEST(req, struct tipc_sock_diag_req r);
+
+ memset(&req.r, 0, sizeof(req.r));
+ req.r.sdiag_family = AF_TIPC;
+ req.r.tidiag_states = f->states;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), tipc_show_sock);
+}
+
+struct sock_diag_msg {
+ __u8 sdiag_family;
+};
+
+static int generic_show_sock(struct nlmsghdr *nlh, void *arg)
+{
+ struct sock_diag_msg *r = NLMSG_DATA(nlh);
+ struct inet_diag_arg inet_arg = { .f = arg, .protocol = IPPROTO_MAX };
+ int ret;
+
+ switch (r->sdiag_family) {
+ case AF_INET:
+ case AF_INET6:
+ inet_arg.rth = inet_arg.f->rth_for_killing;
+ ret = show_one_inet_sock(nlh, &inet_arg);
+ break;
+ case AF_UNIX:
+ ret = unix_show_sock(nlh, arg);
+ break;
+ case AF_PACKET:
+ ret = packet_show_sock(nlh, arg);
+ break;
+ case AF_NETLINK:
+ ret = netlink_show_sock(nlh, arg);
+ break;
+ case AF_VSOCK:
+ ret = vsock_show_sock(nlh, arg);
+ break;
+ case AF_XDP:
+ ret = xdp_show_sock(nlh, arg);
+ break;
+ default:
+ ret = -1;
+ }
+
+ render();
+
+ return ret;
+}
+
+static int handle_follow_request(struct filter *f)
+{
+ int ret = 0;
+ int groups = 0;
+ struct rtnl_handle rth, rth2;
+
+ if (f->families & FAMILY_MASK(AF_INET) && f->dbs & (1 << TCP_DB))
+ groups |= 1 << (SKNLGRP_INET_TCP_DESTROY - 1);
+ if (f->families & FAMILY_MASK(AF_INET) && f->dbs & (1 << UDP_DB))
+ groups |= 1 << (SKNLGRP_INET_UDP_DESTROY - 1);
+ if (f->families & FAMILY_MASK(AF_INET6) && f->dbs & (1 << TCP_DB))
+ groups |= 1 << (SKNLGRP_INET6_TCP_DESTROY - 1);
+ if (f->families & FAMILY_MASK(AF_INET6) && f->dbs & (1 << UDP_DB))
+ groups |= 1 << (SKNLGRP_INET6_UDP_DESTROY - 1);
+
+ if (groups == 0)
+ return -1;
+
+ if (rtnl_open_byproto(&rth, groups, NETLINK_SOCK_DIAG))
+ return -1;
+
+ rth.dump = 0;
+ rth.local.nl_pid = 0;
+
+ if (f->kill) {
+ if (rtnl_open_byproto(&rth2, groups, NETLINK_SOCK_DIAG)) {
+ rtnl_close(&rth);
+ return -1;
+ }
+ f->rth_for_killing = &rth2;
+ }
+
+ if (rtnl_dump_filter(&rth, generic_show_sock, f))
+ ret = -1;
+
+ rtnl_close(&rth);
+ if (f->rth_for_killing)
+ rtnl_close(f->rth_for_killing);
+ return ret;
+}
+
+static int get_snmp_int(char *proto, char *key, int *result)
+{
+ char buf[1024];
+ FILE *fp;
+ int protolen = strlen(proto);
+ int keylen = strlen(key);
+
+ *result = 0;
+
+ if ((fp = net_snmp_open()) == NULL)
+ return -1;
+
+ while (fgets(buf, sizeof(buf), fp) != NULL) {
+ char *p = buf;
+ int pos = 0;
+
+ if (memcmp(buf, proto, protolen))
+ continue;
+ while ((p = strchr(p, ' ')) != NULL) {
+ pos++;
+ p++;
+ if (memcmp(p, key, keylen) == 0 &&
+ (p[keylen] == ' ' || p[keylen] == '\n'))
+ break;
+ }
+ if (fgets(buf, sizeof(buf), fp) == NULL)
+ break;
+ if (memcmp(buf, proto, protolen))
+ break;
+ p = buf;
+ while ((p = strchr(p, ' ')) != NULL) {
+ p++;
+ if (--pos == 0) {
+ sscanf(p, "%d", result);
+ fclose(fp);
+ return 0;
+ }
+ }
+ }
+
+ fclose(fp);
+ errno = ESRCH;
+ return -1;
+}
+
+
+/* Get stats from sockstat */
+
+struct ssummary {
+ int socks;
+ int tcp_mem;
+ int tcp_total;
+ int tcp_orphans;
+ int tcp_tws;
+ int tcp4_hashed;
+ int udp4;
+ int raw4;
+ int frag4;
+ int frag4_mem;
+ int tcp6_hashed;
+ int udp6;
+ int raw6;
+ int frag6;
+ int frag6_mem;
+};
+
+static void get_sockstat_line(char *line, struct ssummary *s)
+{
+ char id[256], rem[256];
+
+ if (sscanf(line, "%[^ ] %[^\n]\n", id, rem) != 2)
+ return;
+
+ if (strcmp(id, "sockets:") == 0)
+ sscanf(rem, "%*s%d", &s->socks);
+ else if (strcmp(id, "UDP:") == 0)
+ sscanf(rem, "%*s%d", &s->udp4);
+ else if (strcmp(id, "UDP6:") == 0)
+ sscanf(rem, "%*s%d", &s->udp6);
+ else if (strcmp(id, "RAW:") == 0)
+ sscanf(rem, "%*s%d", &s->raw4);
+ else if (strcmp(id, "RAW6:") == 0)
+ sscanf(rem, "%*s%d", &s->raw6);
+ else if (strcmp(id, "TCP6:") == 0)
+ sscanf(rem, "%*s%d", &s->tcp6_hashed);
+ else if (strcmp(id, "FRAG:") == 0)
+ sscanf(rem, "%*s%d%*s%d", &s->frag4, &s->frag4_mem);
+ else if (strcmp(id, "FRAG6:") == 0)
+ sscanf(rem, "%*s%d%*s%d", &s->frag6, &s->frag6_mem);
+ else if (strcmp(id, "TCP:") == 0)
+ sscanf(rem, "%*s%d%*s%d%*s%d%*s%d%*s%d",
+ &s->tcp4_hashed,
+ &s->tcp_orphans, &s->tcp_tws, &s->tcp_total, &s->tcp_mem);
+}
+
+static int get_sockstat(struct ssummary *s)
+{
+ char buf[256];
+ FILE *fp;
+
+ memset(s, 0, sizeof(*s));
+
+ if ((fp = net_sockstat_open()) == NULL)
+ return -1;
+ while (fgets(buf, sizeof(buf), fp) != NULL)
+ get_sockstat_line(buf, s);
+ fclose(fp);
+
+ if ((fp = net_sockstat6_open()) == NULL)
+ return 0;
+ while (fgets(buf, sizeof(buf), fp) != NULL)
+ get_sockstat_line(buf, s);
+ fclose(fp);
+
+ return 0;
+}
+
+static int print_summary(void)
+{
+ struct ssummary s;
+ int tcp_estab;
+
+ if (get_sockstat(&s) < 0)
+ perror("ss: get_sockstat");
+ if (get_snmp_int("Tcp:", "CurrEstab", &tcp_estab) < 0)
+ perror("ss: get_snmpstat");
+
+ printf("Total: %d\n", s.socks);
+
+ printf("TCP: %d (estab %d, closed %d, orphaned %d, timewait %d)\n",
+ s.tcp_total + s.tcp_tws, tcp_estab,
+ s.tcp_total - (s.tcp4_hashed + s.tcp6_hashed - s.tcp_tws),
+ s.tcp_orphans, s.tcp_tws);
+
+ printf("\n");
+ printf("Transport Total IP IPv6\n");
+ printf("RAW %-9d %-9d %-9d\n", s.raw4+s.raw6, s.raw4, s.raw6);
+ printf("UDP %-9d %-9d %-9d\n", s.udp4+s.udp6, s.udp4, s.udp6);
+ printf("TCP %-9d %-9d %-9d\n", s.tcp4_hashed+s.tcp6_hashed, s.tcp4_hashed, s.tcp6_hashed);
+ printf("INET %-9d %-9d %-9d\n",
+ s.raw4+s.udp4+s.tcp4_hashed+
+ s.raw6+s.udp6+s.tcp6_hashed,
+ s.raw4+s.udp4+s.tcp4_hashed,
+ s.raw6+s.udp6+s.tcp6_hashed);
+ printf("FRAG %-9d %-9d %-9d\n", s.frag4+s.frag6, s.frag4, s.frag6);
+
+ printf("\n");
+
+ return 0;
+}
+
+static void _usage(FILE *dest)
+{
+ fprintf(dest,
+"Usage: ss [ OPTIONS ]\n"
+" ss [ OPTIONS ] [ FILTER ]\n"
+" -h, --help this message\n"
+" -V, --version output version information\n"
+" -n, --numeric don't resolve service names\n"
+" -r, --resolve resolve host names\n"
+" -a, --all display all sockets\n"
+" -l, --listening display listening sockets\n"
+" -B, --bound-inactive display TCP bound but inactive sockets\n"
+" -o, --options show timer information\n"
+" -e, --extended show detailed socket information\n"
+" -m, --memory show socket memory usage\n"
+" -p, --processes show process using socket\n"
+" -T, --threads show thread using socket\n"
+" -i, --info show internal TCP information\n"
+" --tipcinfo show internal tipc socket information\n"
+" -s, --summary show socket usage summary\n"
+" --tos show tos and priority information\n"
+" --cgroup show cgroup information\n"
+" -b, --bpf show bpf filter socket information\n"
+" -E, --events continually display sockets as they are destroyed\n"
+" -Z, --context display task SELinux security contexts\n"
+" -z, --contexts display task 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"
+" -0, --packet display PACKET sockets\n"
+" -t, --tcp display only TCP sockets\n"
+" -M, --mptcp display only MPTCP sockets\n"
+" -S, --sctp display only SCTP sockets\n"
+" -u, --udp display only UDP sockets\n"
+" -d, --dccp display only DCCP sockets\n"
+" -w, --raw display only RAW sockets\n"
+" -x, --unix display only Unix domain sockets\n"
+" --tipc display only TIPC sockets\n"
+" --vsock display only vsock sockets\n"
+" --xdp display only XDP sockets\n"
+" -f, --family=FAMILY display sockets of type FAMILY\n"
+" FAMILY := {inet|inet6|link|unix|netlink|vsock|tipc|xdp|help}\n"
+"\n"
+" -K, --kill forcibly close sockets, display what was closed\n"
+" -H, --no-header Suppress header line\n"
+" -O, --oneline socket's data printed on a single line\n"
+" --inet-sockopt show various inet socket options\n"
+"\n"
+" -A, --query=QUERY, --socket=QUERY\n"
+" QUERY := {all|inet|tcp|mptcp|udp|raw|unix|unix_dgram|unix_stream|unix_seqpacket|packet|packet_raw|packet_dgram|netlink|dccp|sctp|vsock_stream|vsock_dgram|tipc|xdp}[,QUERY]\n"
+"\n"
+" -D, --diag=FILE Dump raw information about TCP sockets to FILE\n"
+" -F, --filter=FILE read filter information from FILE\n"
+" FILTER := [ state STATE-FILTER ] [ EXPRESSION ]\n"
+" STATE-FILTER := {all|connected|synchronized|bucket|big|TCP-STATES}\n"
+" TCP-STATES := {established|syn-sent|syn-recv|fin-wait-{1,2}|time-wait|closed|close-wait|last-ack|listening|closing}\n"
+" connected := {established|syn-sent|syn-recv|fin-wait-{1,2}|time-wait|close-wait|last-ack|closing}\n"
+" synchronized := {established|syn-recv|fin-wait-{1,2}|time-wait|close-wait|last-ack|closing}\n"
+" bucket := {syn-recv|time-wait}\n"
+" big := {established|syn-sent|fin-wait-{1,2}|closed|close-wait|last-ack|listening|closing}\n"
+ );
+}
+
+static void help(void) __attribute__((noreturn));
+static void help(void)
+{
+ _usage(stdout);
+ exit(0);
+}
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+ _usage(stderr);
+ exit(-1);
+}
+
+
+static int scan_state(const char *state)
+{
+ static const char * const sstate_namel[] = {
+ "UNKNOWN",
+ [SS_ESTABLISHED] = "established",
+ [SS_SYN_SENT] = "syn-sent",
+ [SS_SYN_RECV] = "syn-recv",
+ [SS_FIN_WAIT1] = "fin-wait-1",
+ [SS_FIN_WAIT2] = "fin-wait-2",
+ [SS_TIME_WAIT] = "time-wait",
+ [SS_CLOSE] = "unconnected",
+ [SS_CLOSE_WAIT] = "close-wait",
+ [SS_LAST_ACK] = "last-ack",
+ [SS_LISTEN] = "listening",
+ [SS_CLOSING] = "closing",
+ [SS_NEW_SYN_RECV] = "new-syn-recv",
+ [SS_BOUND_INACTIVE] = "bound-inactive",
+ };
+ int i;
+
+ /* NEW_SYN_RECV is a kernel implementation detail. It shouldn't be used
+ * or even be visible by users.
+ */
+ if (strcasecmp(state, "new-syn-recv") == 0)
+ goto wrong_state;
+
+ if (strcasecmp(state, "close") == 0 ||
+ strcasecmp(state, "closed") == 0)
+ return (1<<SS_CLOSE);
+ if (strcasecmp(state, "syn-rcv") == 0)
+ return (1<<SS_SYN_RECV);
+ if (strcasecmp(state, "established") == 0)
+ return (1<<SS_ESTABLISHED);
+ if (strcasecmp(state, "all") == 0)
+ return SS_ALL;
+ if (strcasecmp(state, "connected") == 0)
+ return SS_ALL & ~((1<<SS_CLOSE)|(1<<SS_LISTEN));
+ if (strcasecmp(state, "synchronized") == 0)
+ return SS_ALL & ~((1<<SS_CLOSE)|(1<<SS_LISTEN)|(1<<SS_SYN_SENT));
+ if (strcasecmp(state, "bucket") == 0)
+ return (1<<SS_SYN_RECV)|(1<<SS_TIME_WAIT);
+ if (strcasecmp(state, "big") == 0)
+ return SS_ALL & ~((1<<SS_SYN_RECV)|(1<<SS_TIME_WAIT));
+ for (i = 0; i < SS_MAX; i++) {
+ if (strcasecmp(state, sstate_namel[i]) == 0)
+ return (1<<i);
+ }
+
+wrong_state:
+ fprintf(stderr, "ss: wrong state name: %s\n", state);
+ exit(-1);
+}
+
+/* Values 'v' and 'V' are already used so a non-character is used */
+#define OPT_VSOCK 256
+
+/* Values of 't' are already used so a non-character is used */
+#define OPT_TIPCSOCK 257
+#define OPT_TIPCINFO 258
+
+#define OPT_TOS 259
+
+/* Values of 'x' are already used so a non-character is used */
+#define OPT_XDPSOCK 260
+
+#define OPT_CGROUP 261
+
+#define OPT_INET_SOCKOPT 262
+
+static const struct option long_opts[] = {
+ { "numeric", 0, 0, 'n' },
+ { "resolve", 0, 0, 'r' },
+ { "options", 0, 0, 'o' },
+ { "extended", 0, 0, 'e' },
+ { "memory", 0, 0, 'm' },
+ { "info", 0, 0, 'i' },
+ { "processes", 0, 0, 'p' },
+ { "threads", 0, 0, 'T' },
+ { "bpf", 0, 0, 'b' },
+ { "events", 0, 0, 'E' },
+ { "dccp", 0, 0, 'd' },
+ { "tcp", 0, 0, 't' },
+ { "sctp", 0, 0, 'S' },
+ { "udp", 0, 0, 'u' },
+ { "raw", 0, 0, 'w' },
+ { "unix", 0, 0, 'x' },
+ { "tipc", 0, 0, OPT_TIPCSOCK},
+ { "vsock", 0, 0, OPT_VSOCK },
+ { "all", 0, 0, 'a' },
+ { "listening", 0, 0, 'l' },
+ { "bound-inactive", 0, 0, 'B' },
+ { "ipv4", 0, 0, '4' },
+ { "ipv6", 0, 0, '6' },
+ { "packet", 0, 0, '0' },
+ { "family", 1, 0, 'f' },
+ { "socket", 1, 0, 'A' },
+ { "query", 1, 0, 'A' },
+ { "summary", 0, 0, 's' },
+ { "diag", 1, 0, 'D' },
+ { "filter", 1, 0, 'F' },
+ { "version", 0, 0, 'V' },
+ { "help", 0, 0, 'h' },
+ { "context", 0, 0, 'Z' },
+ { "contexts", 0, 0, 'z' },
+ { "net", 1, 0, 'N' },
+ { "tipcinfo", 0, 0, OPT_TIPCINFO},
+ { "tos", 0, 0, OPT_TOS },
+ { "cgroup", 0, 0, OPT_CGROUP },
+ { "kill", 0, 0, 'K' },
+ { "no-header", 0, 0, 'H' },
+ { "xdp", 0, 0, OPT_XDPSOCK},
+ { "mptcp", 0, 0, 'M' },
+ { "oneline", 0, 0, 'O' },
+ { "inet-sockopt", 0, 0, OPT_INET_SOCKOPT },
+ { 0 }
+
+};
+
+int main(int argc, char *argv[])
+{
+ int saw_states = 0;
+ int saw_query = 0;
+ int do_summary = 0;
+ const char *dump_tcpdiag = NULL;
+ FILE *filter_fp = NULL;
+ int ch;
+ int state_filter = 0;
+
+ while ((ch = getopt_long(argc, argv,
+ "dhalBetuwxnro460spTbEf:mMiA:D:F:vVzZN:KHSO",
+ long_opts, NULL)) != EOF) {
+ switch (ch) {
+ case 'n':
+ numeric = 1;
+ break;
+ case 'r':
+ resolve_hosts = 1;
+ break;
+ case 'o':
+ show_options = 1;
+ break;
+ case 'e':
+ show_options = 1;
+ show_details++;
+ break;
+ case 'm':
+ show_mem = 1;
+ break;
+ case 'i':
+ show_tcpinfo = 1;
+ break;
+ case 'p':
+ show_processes++;
+ break;
+ case 'T':
+ show_threads++;
+ break;
+ case 'b':
+ show_options = 1;
+ show_bpf++;
+ break;
+ case 'E':
+ follow_events = 1;
+ break;
+ case 'd':
+ filter_db_set(&current_filter, DCCP_DB, true);
+ break;
+ case 't':
+ filter_db_set(&current_filter, TCP_DB, true);
+ break;
+ case 'S':
+ filter_db_set(&current_filter, SCTP_DB, true);
+ break;
+ case 'u':
+ filter_db_set(&current_filter, UDP_DB, true);
+ break;
+ case 'w':
+ filter_db_set(&current_filter, RAW_DB, true);
+ break;
+ case 'x':
+ filter_af_set(&current_filter, AF_UNIX);
+ break;
+ case OPT_VSOCK:
+ filter_af_set(&current_filter, AF_VSOCK);
+ break;
+ case OPT_TIPCSOCK:
+ filter_af_set(&current_filter, AF_TIPC);
+ break;
+ case 'a':
+ state_filter = SS_ALL;
+ break;
+ case 'l':
+ state_filter = (1 << SS_LISTEN) | (1 << SS_CLOSE);
+ break;
+ case 'B':
+ state_filter = 1 << SS_BOUND_INACTIVE;
+ break;
+ case '4':
+ filter_af_set(&current_filter, AF_INET);
+ break;
+ case '6':
+ filter_af_set(&current_filter, AF_INET6);
+ break;
+ case '0':
+ filter_af_set(&current_filter, AF_PACKET);
+ break;
+ case OPT_XDPSOCK:
+ filter_af_set(&current_filter, AF_XDP);
+ break;
+ case 'M':
+ filter_db_set(&current_filter, MPTCP_DB, true);
+ break;
+ case 'f':
+ if (strcmp(optarg, "inet") == 0)
+ filter_af_set(&current_filter, AF_INET);
+ else if (strcmp(optarg, "inet6") == 0)
+ filter_af_set(&current_filter, AF_INET6);
+ else if (strcmp(optarg, "link") == 0)
+ filter_af_set(&current_filter, AF_PACKET);
+ else if (strcmp(optarg, "unix") == 0)
+ filter_af_set(&current_filter, AF_UNIX);
+ else if (strcmp(optarg, "netlink") == 0)
+ filter_af_set(&current_filter, AF_NETLINK);
+ else if (strcmp(optarg, "tipc") == 0)
+ filter_af_set(&current_filter, AF_TIPC);
+ else if (strcmp(optarg, "vsock") == 0)
+ filter_af_set(&current_filter, AF_VSOCK);
+ else if (strcmp(optarg, "xdp") == 0)
+ filter_af_set(&current_filter, AF_XDP);
+ else if (strcmp(optarg, "help") == 0)
+ help();
+ else {
+ fprintf(stderr, "ss: \"%s\" is invalid family\n",
+ optarg);
+ usage();
+ }
+ break;
+ case 'A':
+ {
+ char *p, *p1;
+
+ if (!saw_query) {
+ current_filter.dbs = 0;
+ state_filter = state_filter ?
+ state_filter : SS_CONN;
+ saw_query = 1;
+ do_default = 0;
+ }
+ p = p1 = optarg;
+ do {
+ if ((p1 = strchr(p, ',')) != NULL)
+ *p1 = 0;
+ if (filter_db_parse(&current_filter, p)) {
+ fprintf(stderr, "ss: \"%s\" is illegal socket table id\n", p);
+ usage();
+ }
+ p = p1 + 1;
+ } while (p1);
+ break;
+ }
+ case 's':
+ do_summary = 1;
+ break;
+ case 'D':
+ dump_tcpdiag = optarg;
+ break;
+ case 'F':
+ if (filter_fp) {
+ fprintf(stderr, "More than one filter file\n");
+ exit(-1);
+ }
+ if (optarg[0] == '-')
+ filter_fp = stdin;
+ else
+ filter_fp = fopen(optarg, "r");
+ if (!filter_fp) {
+ perror("fopen filter file");
+ exit(-1);
+ }
+ break;
+ case 'v':
+ case 'V':
+ printf("ss utility, iproute2-%s\n", version);
+ exit(0);
+ case 'z':
+ show_sock_ctx++;
+ /* fall through */
+ case 'Z':
+ if (!is_selinux_enabled()) {
+ fprintf(stderr, "ss: SELinux is not enabled.\n");
+ exit(1);
+ }
+ show_proc_ctx++;
+ break;
+ case 'N':
+ if (netns_switch(optarg))
+ exit(1);
+ break;
+ case OPT_TIPCINFO:
+ show_tipcinfo = 1;
+ break;
+ case OPT_TOS:
+ show_tos = 1;
+ break;
+ case OPT_CGROUP:
+ show_cgroup = 1;
+ break;
+ case 'K':
+ current_filter.kill = 1;
+ break;
+ case 'H':
+ show_header = 0;
+ break;
+ case 'O':
+ oneline = 1;
+ break;
+ case OPT_INET_SOCKOPT:
+ show_inet_sockopt = 1;
+ break;
+ case 'h':
+ help();
+ case '?':
+ default:
+ usage();
+ }
+ }
+
+ if (show_processes || show_threads || show_proc_ctx || show_sock_ctx)
+ user_ent_hash_build();
+
+ argc -= optind;
+ argv += optind;
+
+ if (do_summary) {
+ print_summary();
+ if (do_default && argc == 0)
+ exit(0);
+ }
+
+ while (argc > 0) {
+ if (strcmp(*argv, "state") == 0) {
+ NEXT_ARG();
+ if (!saw_states)
+ state_filter = 0;
+ state_filter |= scan_state(*argv);
+ saw_states = 1;
+ } else if (strcmp(*argv, "exclude") == 0 ||
+ strcmp(*argv, "excl") == 0) {
+ NEXT_ARG();
+ if (!saw_states)
+ state_filter = SS_ALL;
+ state_filter &= ~scan_state(*argv);
+ saw_states = 1;
+ } else {
+ break;
+ }
+ argc--; argv++;
+ }
+
+ if (do_default) {
+ state_filter = state_filter ? state_filter : SS_CONN;
+ filter_db_parse(&current_filter, "all");
+ }
+
+ filter_states_set(&current_filter, state_filter);
+ filter_merge_defaults(&current_filter);
+
+#ifdef HAVE_RPC
+ if (!numeric && resolve_hosts &&
+ (current_filter.dbs & (UNIX_DBM|INET_L4_DBM)))
+ init_service_resolver();
+#endif
+
+ if (current_filter.dbs == 0) {
+ fprintf(stderr, "ss: no socket tables to show with such filter.\n");
+ exit(0);
+ }
+ if (current_filter.families == 0) {
+ fprintf(stderr, "ss: no families to show with such filter.\n");
+ exit(0);
+ }
+ if (current_filter.states == 0) {
+ fprintf(stderr, "ss: no socket states to show with such filter.\n");
+ exit(0);
+ }
+
+ if (dump_tcpdiag) {
+ FILE *dump_fp = stdout;
+
+ if (!(current_filter.dbs & (1<<TCP_DB))) {
+ fprintf(stderr, "ss: tcpdiag dump requested and no tcp in filter.\n");
+ exit(0);
+ }
+ if (dump_tcpdiag[0] != '-') {
+ dump_fp = fopen(dump_tcpdiag, "w");
+ if (!dump_tcpdiag) {
+ perror("fopen dump file");
+ exit(-1);
+ }
+ }
+ inet_show_netlink(&current_filter, dump_fp, IPPROTO_TCP);
+ fflush(dump_fp);
+ exit(0);
+ }
+
+ if (ssfilter_parse(&current_filter.f, argc, argv, filter_fp))
+ usage();
+
+ if (!show_processes)
+ columns[COL_PROC].disabled = 1;
+
+ if (!(current_filter.dbs & (current_filter.dbs - 1)))
+ columns[COL_NETID].disabled = 1;
+
+ if (!(current_filter.states & (current_filter.states - 1)))
+ columns[COL_STATE].disabled = 1;
+
+ if (show_header)
+ print_header();
+
+ fflush(stdout);
+
+ if (follow_events)
+ exit(handle_follow_request(&current_filter));
+
+ if (current_filter.dbs & (1<<NETLINK_DB))
+ netlink_show(&current_filter);
+ if (current_filter.dbs & PACKET_DBM)
+ packet_show(&current_filter);
+ if (current_filter.dbs & UNIX_DBM)
+ unix_show(&current_filter);
+ if (current_filter.dbs & (1<<RAW_DB))
+ raw_show(&current_filter);
+ if (current_filter.dbs & (1<<UDP_DB))
+ udp_show(&current_filter);
+ if (current_filter.dbs & (1<<TCP_DB))
+ tcp_show(&current_filter);
+ if (current_filter.dbs & (1<<DCCP_DB))
+ dccp_show(&current_filter);
+ if (current_filter.dbs & (1<<SCTP_DB))
+ sctp_show(&current_filter);
+ if (current_filter.dbs & VSOCK_DBM)
+ vsock_show(&current_filter);
+ if (current_filter.dbs & (1<<TIPC_DB))
+ tipc_show(&current_filter);
+ if (current_filter.dbs & (1<<XDP_DB))
+ xdp_show(&current_filter);
+ if (current_filter.dbs & (1<<MPTCP_DB))
+ mptcp_show(&current_filter);
+
+ if (show_processes || show_threads || show_proc_ctx || show_sock_ctx)
+ user_ent_destroy();
+
+ render();
+
+ return 0;
+}
diff --git a/misc/ss_util.h b/misc/ss_util.h
new file mode 100644
index 0000000..37936c6
--- /dev/null
+++ b/misc/ss_util.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __SS_UTIL_H__
+#define __SS_UTIL_H__
+
+#include <linux/sock_diag.h>
+#include <linux/inet_diag.h>
+
+#define MAGIC_SEQ 123456
+
+#define DIAG_REQUEST(_req, _r) \
+ struct { \
+ struct nlmsghdr nlh; \
+ _r; \
+ } _req = { \
+ .nlh = { \
+ .nlmsg_type = SOCK_DIAG_BY_FAMILY, \
+ .nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST,\
+ .nlmsg_seq = MAGIC_SEQ, \
+ .nlmsg_len = sizeof(_req), \
+ }, \
+ }
+
+#endif /* __SS_UTIL_H__ */
diff --git a/misc/ssfilter.h b/misc/ssfilter.h
new file mode 100644
index 0000000..73e55e0
--- /dev/null
+++ b/misc/ssfilter.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <stdbool.h>
+
+enum {
+ SSF_DCOND,
+ SSF_SCOND,
+ SSF_OR,
+ SSF_AND,
+ SSF_NOT,
+ SSF_D_GE,
+ SSF_D_LE,
+ SSF_S_GE,
+ SSF_S_LE,
+ SSF_S_AUTO,
+ SSF_DEVCOND,
+ SSF_MARKMASK,
+ SSF_CGROUPCOND,
+ SSF__MAX
+};
+
+bool ssfilter_is_supported(int type);
+
+struct ssfilter
+{
+ int type;
+ struct ssfilter *post;
+ struct ssfilter *pred;
+};
+
+int ssfilter_parse(struct ssfilter **f, int argc, char **argv, FILE *fp);
+void *parse_hostcond(char *addr, bool is_port);
+void *parse_devcond(char *name);
+void *parse_markmask(const char *markmask);
+void *parse_cgroupcond(const char *path);
diff --git a/misc/ssfilter.y b/misc/ssfilter.y
new file mode 100644
index 0000000..3195723
--- /dev/null
+++ b/misc/ssfilter.y
@@ -0,0 +1,369 @@
+%{
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <malloc.h>
+#include <string.h>
+#include "ssfilter.h"
+
+typedef struct ssfilter * ssfilter_t;
+
+#define YYSTYPE ssfilter_t
+
+static struct ssfilter * alloc_node(int type, void *pred)
+{
+ struct ssfilter *n;
+
+ if (!ssfilter_is_supported(type)) {
+ fprintf(stderr, "It looks like such filter is not supported! Too old kernel?\n");
+ exit(-1);
+ }
+
+ n = malloc(sizeof(*n));
+ if (n == NULL)
+ abort();
+ n->type = type;
+ n->pred = pred;
+ n->post = NULL;
+ return n;
+}
+
+static char **yy_argv;
+static int yy_argc;
+static FILE *yy_fp;
+static ssfilter_t *yy_ret;
+static int tok_type = -1;
+
+static int yylex(void);
+
+static void yyerror(char *s)
+{
+ fprintf(stderr, "ss: bison bellows (while parsing filter): \"%s!\"", s);
+}
+
+%}
+
+%token HOSTCOND DCOND SCOND DPORT SPORT LEQ GEQ NEQ AUTOBOUND DEVCOND DEVNAME MARKMASK FWMARK CGROUPCOND CGROUPPATH
+%left '|'
+%left '&'
+%nonassoc '!'
+
+%%
+applet: exprlist
+ {
+ *yy_ret = $1;
+ $$ = $1;
+ }
+ | null
+ ;
+
+null: /* NOTHING */ { $$ = NULL; }
+ ;
+
+exprlist: expr
+ | exprlist '|' expr
+ {
+ $$ = alloc_node(SSF_OR, $1);
+ $$->post = $3;
+ }
+ | exprlist '&' expr
+ {
+ $$ = alloc_node(SSF_AND, $1);
+ $$->post = $3;
+ }
+ | exprlist expr
+ {
+ $$ = alloc_node(SSF_AND, $1);
+ $$->post = $2;
+ }
+ ;
+
+eq: '='
+ | /* nothing */
+ ;
+
+expr: '(' exprlist ')'
+ {
+ $$ = $2;
+ }
+ | '!' expr
+ {
+ $$ = alloc_node(SSF_NOT, $2);
+ }
+ | DCOND eq HOSTCOND
+ {
+ $$ = alloc_node(SSF_DCOND, $3);
+ }
+ | SCOND eq HOSTCOND
+ {
+ $$ = alloc_node(SSF_SCOND, $3);
+ }
+ | DPORT GEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_D_GE, $3);
+ }
+ | DPORT LEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_D_LE, $3);
+ }
+ | DPORT '>' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_D_LE, $3));
+ }
+ | DPORT '<' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_D_GE, $3));
+ }
+ | DPORT eq HOSTCOND
+ {
+ $$ = alloc_node(SSF_DCOND, $3);
+ }
+ | DPORT NEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_DCOND, $3));
+ }
+
+ | SPORT GEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_S_GE, $3);
+ }
+ | SPORT LEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_S_LE, $3);
+ }
+ | SPORT '>' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_S_LE, $3));
+ }
+ | SPORT '<' HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_S_GE, $3));
+ }
+ | SPORT eq HOSTCOND
+ {
+ $$ = alloc_node(SSF_SCOND, $3);
+ }
+ | SPORT NEQ HOSTCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_SCOND, $3));
+ }
+ | DEVNAME eq DEVCOND
+ {
+ $$ = alloc_node(SSF_DEVCOND, $3);
+ }
+ | DEVNAME NEQ DEVCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_DEVCOND, $3));
+ }
+ | FWMARK eq MARKMASK
+ {
+ $$ = alloc_node(SSF_MARKMASK, $3);
+ }
+ | FWMARK NEQ MARKMASK
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_MARKMASK, $3));
+ }
+ | CGROUPPATH eq CGROUPCOND
+ {
+ $$ = alloc_node(SSF_CGROUPCOND, $3);
+ }
+ | CGROUPPATH NEQ CGROUPCOND
+ {
+ $$ = alloc_node(SSF_NOT, alloc_node(SSF_CGROUPCOND, $3));
+ }
+ | AUTOBOUND
+ {
+ $$ = alloc_node(SSF_S_AUTO, NULL);
+ }
+;
+%%
+
+static char *get_token_from_line(char **ptr)
+{
+ char *tok, *cp = *ptr;
+
+ while (*cp == ' ' || *cp == '\t') cp++;
+
+ if (*cp == 0) {
+ *ptr = cp;
+ return NULL;
+ }
+
+ tok = cp;
+
+ while (*cp != 0 && *cp != ' ' && *cp != '\t') {
+ /* Backslash escapes everything. */
+ if (*cp == '\\') {
+ char *tp;
+ for (tp = cp; tp != tok; tp--)
+ *tp = *(tp-1);
+ cp++;
+ tok++;
+ if (*cp == 0)
+ break;
+ }
+ cp++;
+ }
+ if (*cp)
+ *cp++ = 0;
+ *ptr = cp;
+ return tok;
+}
+
+int yylex(void)
+{
+ static char argbuf[1024];
+ static char *tokptr = argbuf;
+ static int argc;
+ char *curtok;
+
+ do {
+ while (*tokptr == 0) {
+ tokptr = NULL;
+ if (argc < yy_argc) {
+ tokptr = yy_argv[argc];
+ argc++;
+ } else if (yy_fp) {
+ while (tokptr == NULL) {
+ size_t len;
+
+ if (fgets(argbuf, sizeof(argbuf), yy_fp) == NULL)
+ return 0;
+
+ len = strnlen(argbuf, sizeof(argbuf));
+ if (len == 0) {
+ fprintf(stderr, "Invalid line\n");
+ exit(-1);
+ }
+
+ if (len >= sizeof(argbuf) - 1) {
+ fprintf(stderr, "Too long line in filter\n");
+ exit(-1);
+ }
+ if (argbuf[len - 1] == '\n')
+ argbuf[len-1] = 0;
+ if (argbuf[0] == '#' || argbuf[0] == '0')
+ continue;
+ tokptr = argbuf;
+ }
+ } else {
+ return 0;
+ }
+ }
+ } while ((curtok = get_token_from_line(&tokptr)) == NULL);
+
+ if (strcmp(curtok, "!") == 0 ||
+ strcmp(curtok, "not") == 0)
+ return '!';
+ if (strcmp(curtok, "&") == 0 ||
+ strcmp(curtok, "&&") == 0 ||
+ strcmp(curtok, "and") == 0)
+ return '&';
+ if (strcmp(curtok, "|") == 0 ||
+ strcmp(curtok, "||") == 0 ||
+ strcmp(curtok, "or") == 0)
+ return '|';
+ if (strcmp(curtok, "(") == 0)
+ return '(';
+ if (strcmp(curtok, ")") == 0)
+ return ')';
+ if (strcmp(curtok, "dst") == 0) {
+ tok_type = DCOND;
+ return DCOND;
+ }
+ if (strcmp(curtok, "src") == 0) {
+ tok_type = SCOND;
+ return SCOND;
+ }
+ if (strcmp(curtok, "dport") == 0) {
+ tok_type = DPORT;
+ return DPORT;
+ }
+ if (strcmp(curtok, "sport") == 0) {
+ tok_type = SPORT;
+ return SPORT;
+ }
+ if (strcmp(curtok, "dev") == 0) {
+ tok_type = DEVNAME;
+ return DEVNAME;
+ }
+ if (strcmp(curtok, "fwmark") == 0) {
+ tok_type = FWMARK;
+ return FWMARK;
+ }
+ if (strcmp(curtok, "cgroup") == 0) {
+ tok_type = CGROUPPATH;
+ return CGROUPPATH;
+ }
+ if (strcmp(curtok, ">=") == 0 ||
+ strcmp(curtok, "ge") == 0 ||
+ strcmp(curtok, "geq") == 0)
+ return GEQ;
+ if (strcmp(curtok, "<=") == 0 ||
+ strcmp(curtok, "le") == 0 ||
+ strcmp(curtok, "leq") == 0)
+ return LEQ;
+ if (strcmp(curtok, "!=") == 0 ||
+ strcmp(curtok, "ne") == 0 ||
+ strcmp(curtok, "neq") == 0)
+ return NEQ;
+ if (strcmp(curtok, "=") == 0 ||
+ strcmp(curtok, "==") == 0 ||
+ strcmp(curtok, "eq") == 0)
+ return '=';
+ if (strcmp(curtok, ">") == 0 ||
+ strcmp(curtok, "gt") == 0)
+ return '>';
+ if (strcmp(curtok, "<") == 0 ||
+ strcmp(curtok, "lt") == 0)
+ return '<';
+ if (strcmp(curtok, "autobound") == 0) {
+ tok_type = AUTOBOUND;
+ return AUTOBOUND;
+ }
+ if (tok_type == DEVNAME) {
+ yylval = (void*)parse_devcond(curtok);
+ if (yylval == NULL) {
+ fprintf(stderr, "Cannot parse device.\n");
+ exit(1);
+ }
+ return DEVCOND;
+ }
+ if (tok_type == FWMARK) {
+ yylval = (void*)parse_markmask(curtok);
+ if (yylval == NULL) {
+ fprintf(stderr, "Cannot parse mark %s.\n", curtok);
+ exit(1);
+ }
+ return MARKMASK;
+ }
+ if (tok_type == CGROUPPATH) {
+ yylval = (void*)parse_cgroupcond(curtok);
+ if (yylval == NULL) {
+ fprintf(stderr, "Cannot parse cgroup %s.\n", curtok);
+ exit(1);
+ }
+ return CGROUPCOND;
+ }
+ yylval = (void*)parse_hostcond(curtok, tok_type == SPORT || tok_type == DPORT);
+ if (yylval == NULL) {
+ fprintf(stderr, "Cannot parse dst/src address.\n");
+ exit(1);
+ }
+ return HOSTCOND;
+}
+
+int ssfilter_parse(struct ssfilter **f, int argc, char **argv, FILE *fp)
+{
+ yy_argc = argc;
+ yy_argv = argv;
+ yy_fp = fp;
+ yy_ret = f;
+
+ if (yyparse()) {
+ fprintf(stderr, " Sorry.\n");
+ return -1;
+ }
+ return 0;
+}
diff --git a/misc/ssfilter_check.c b/misc/ssfilter_check.c
new file mode 100644
index 0000000..02709ce
--- /dev/null
+++ b/misc/ssfilter_check.c
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <stdio.h>
+#include <stdlib.h>
+#include <errno.h>
+
+#include "libnetlink.h"
+#include "ssfilter.h"
+#include "ss_util.h"
+
+static int dummy_filter(struct nlmsghdr *n, void *arg)
+{
+ /* just stops rtnl_dump_filter() */
+ return -1;
+}
+
+static bool cgroup_filter_check(void)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ DIAG_REQUEST(req, struct inet_diag_req_v2 r);
+ struct instr {
+ struct inet_diag_bc_op op;
+ __u64 cgroup_id;
+ } __attribute__((packed));
+ int inslen = sizeof(struct instr);
+ struct instr instr = {
+ { INET_DIAG_BC_CGROUP_COND, inslen, inslen + 4 },
+ 0
+ };
+ struct rtnl_handle rth;
+ struct iovec iov[3];
+ struct msghdr msg;
+ struct rtattr rta;
+ int ret = false;
+ int iovlen = 3;
+
+ if (rtnl_open_byproto(&rth, 0, NETLINK_SOCK_DIAG))
+ return false;
+ rth.dump = MAGIC_SEQ;
+ rth.flags = RTNL_HANDLE_F_SUPPRESS_NLERR;
+
+ memset(&req.r, 0, sizeof(req.r));
+ req.r.sdiag_family = AF_INET;
+ req.r.sdiag_protocol = IPPROTO_TCP;
+ req.nlh.nlmsg_len += RTA_LENGTH(inslen);
+
+ rta.rta_type = INET_DIAG_REQ_BYTECODE;
+ rta.rta_len = RTA_LENGTH(inslen);
+
+ iov[0] = (struct iovec) { &req, sizeof(req) };
+ iov[1] = (struct iovec) { &rta, sizeof(rta) };
+ iov[2] = (struct iovec) { &instr, inslen };
+
+ msg = (struct msghdr) {
+ .msg_name = (void *)&nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = iovlen,
+ };
+
+ if (sendmsg(rth.fd, &msg, 0) < 0)
+ goto out;
+
+ if (rtnl_dump_filter(&rth, dummy_filter, NULL) < 0) {
+ ret = (errno != EINVAL);
+ goto out;
+ }
+
+ ret = true;
+
+out:
+ rtnl_close(&rth);
+
+ return ret;
+}
+
+
+struct filter_check_t {
+ bool (*check)(void);
+ unsigned int checked:1,
+ supported:1;
+};
+
+static struct filter_check_t filter_checks[SSF__MAX] = {
+ [SSF_CGROUPCOND] = { cgroup_filter_check, 0 },
+};
+
+bool ssfilter_is_supported(int type)
+{
+ struct filter_check_t f;
+
+ if (type >= SSF__MAX)
+ return false;
+
+ f = filter_checks[type];
+ if (!f.check)
+ return true;
+
+ if (!f.checked) {
+ f.supported = f.check();
+ f.checked = 1;
+ }
+
+ return f.supported;
+}
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-08 21:11:14 +0000