#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/tipc_netlink.h>
#include <linux/tipc_sockets_diag.h>
+/* 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
+
#define MAGIC_SEQ 123456
-#define BUF_CHUNK (1024 * 1024)
+#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)
#define DIAG_REQUEST(_req, _r) \
}
#endif
-int resolve_services = 1;
+static int resolve_services = 1;
int preferred_family = AF_UNSPEC;
-int show_options;
+static int show_options;
int show_details;
-int show_users;
-int show_mem;
-int show_tcpinfo;
-int show_bpf;
-int show_proc_ctx;
-int show_sock_ctx;
-int show_header = 1;
-int follow_events;
-int sctp_ino;
-int show_tipcinfo;
+static int show_users;
+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;
enum col_id {
COL_NETID,
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";
VSOCK_ST_DB,
VSOCK_DG_DB,
TIPC_DB,
+ XDP_DB,
MAX_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] = {
.dbs = (1 << TIPC_DB),
.states = TIPC_SS_CONN,
},
+ [AF_XDP] = {
+ .dbs = (1 << XDP_DB),
+ .states = (1 << SS_CLOSE),
+ },
};
static int do_default = 1;
ENTRY(all, UDP_DB, DCCP_DB, TCP_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),
+ SCTP_DB, VSOCK_ST_DB, VSOCK_DG_DB, XDP_DB),
ENTRY(inet, UDP_DB, DCCP_DB, TCP_DB, SCTP_DB, RAW_DB),
ENTRY(udp, UDP_DB),
ENTRY(dccp, DCCP_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;
};
#define USER_ENT_HASH_SIZE 256
-struct user_ent *user_ent_hash[USER_ENT_HASH_SIZE];
+static struct user_ent *user_ent_hash[USER_ENT_HASH_SIZE];
static int user_ent_hashfn(unsigned int ino)
{
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;
int rcv_space;
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_sack_opt;
bool has_ecn_opt;
new->end = buffer.cur->data;
+ buffer.chunks++;
+
return new;
}
return f - columns == COL_MAX - 1;
}
-static void field_next(void)
-{
- 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();
- }
-}
-
/* Get the next available token in the buffer starting from the current token */
static struct buf_token *buf_token_next(struct buf_token *cur)
{
free(tmp);
}
buffer.head = NULL;
+ buffer.chunks = 0;
}
/* Get current screen width, default to 80 columns if TIOCGWINSZ fails */
while (token) {
/* Print left delimiter only if we already started a line */
if (line_started++)
- printed = printf("%s", current_field->ldelim);
+ printed = printf("%s", f->ldelim);
else
printed = 0;
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;
case AF_VSOCK:
sock_name = vsock_netid_name(s->type);
break;
+ case AF_XDP:
+ sock_name = "xdp";
+ break;
default:
sock_name = "unknown";
}
const char *proto;
};
-struct scache *rlist;
+static struct scache *rlist;
static void init_service_resolver(void)
{
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)
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");
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)
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;
tcp_stats_print(&s);
free(s.dctcp);
free(s.bbr_info);
}
}
+ 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_mem || (show_tcpinfo && s->type != IPPROTO_UDP)) {
out("\n\t");
if (s->type == IPPROTO_SCTP)
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)
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)
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)
+{
+ 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)
+{
+ 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 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;
+ 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 (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 (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;
+
+ 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,
case AF_VSOCK:
ret = vsock_show_sock(nlh, arg);
break;
+ case AF_XDP:
+ ret = xdp_show_sock(nlh, arg);
+ break;
default:
ret = -1;
}
" -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"
" -b, --bpf show bpf filter socket information\n"
" -E, --events continually display sockets as they are destroyed\n"
" -Z, --context display process SELinux security contexts\n"
" --tipc display only TIPC sockets\n"
" --vsock display only vsock sockets\n"
" -f, --family=FAMILY display sockets of type FAMILY\n"
-" FAMILY := {inet|inet6|link|unix|netlink|vsock|tipc|help}\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"
#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
+
static const struct option long_opts[] = {
{ "numeric", 0, 0, 'n' },
{ "resolve", 0, 0, 'r' },
{ "contexts", 0, 0, 'z' },
{ "net", 1, 0, 'N' },
{ "tipcinfo", 0, 0, OPT_TIPCINFO},
+ { "tos", 0, 0, OPT_TOS },
{ "kill", 0, 0, 'K' },
{ "no-header", 0, 0, 'H' },
+ { "xdp", 0, 0, OPT_XDPSOCK},
{ 0 }
};
case '0':
filter_af_set(¤t_filter, AF_PACKET);
break;
+ case OPT_XDPSOCK:
+ filter_af_set(¤t_filter, AF_XDP);
+ break;
case 'f':
if (strcmp(optarg, "inet") == 0)
filter_af_set(¤t_filter, AF_INET);
filter_af_set(¤t_filter, AF_TIPC);
else if (strcmp(optarg, "vsock") == 0)
filter_af_set(¤t_filter, AF_VSOCK);
+ else if (strcmp(optarg, "xdp") == 0)
+ filter_af_set(¤t_filter, AF_XDP);
else if (strcmp(optarg, "help") == 0)
help();
else {
case OPT_TIPCINFO:
show_tipcinfo = 1;
break;
+ case OPT_TOS:
+ show_tos = 1;
+ break;
case 'K':
current_filter.kill = 1;
break;
vsock_show(¤t_filter);
if (current_filter.dbs & (1<<TIPC_DB))
tipc_show(¤t_filter);
+ if (current_filter.dbs & (1<<XDP_DB))
+ xdp_show(¤t_filter);
if (show_users || show_proc_ctx || show_sock_ctx)
user_ent_destroy();
projects / mirror_iproute2.git / blobdiff