All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stefan Hajnoczi <stefanha@redhat.com>
To: netdev@vger.kernel.org
Cc: Stephen Hemminger <stephen@networkplumber.org>,
	Jorgen Hansen <jhansen@vmware.com>,
	Dexuan Cui <decui@microsoft.com>,
	Stefan Hajnoczi <stefanha@redhat.com>
Subject: [PATCH iproute2 v2 3/3] ss: add AF_VSOCK support
Date: Fri,  6 Oct 2017 11:48:41 -0400	[thread overview]
Message-ID: <20171006154841.10495-4-stefanha@redhat.com> (raw)
In-Reply-To: <20171006154841.10495-1-stefanha@redhat.com>

The AF_VSOCK address family is a host<->guest communications channel
supported by VMware, KVM, and Hyper-V.  Initial VMware support was
released in Linux 3.9 in 2013 and transports for other hypervisors were
added later.

AF_VSOCK addresses are <u32 cid, u32 port> tuples.  The 32-bit cid
integer is comparable to an IP address.  AF_VSOCK ports work like
TCP/UDP ports.

Both SOCK_STREAM and SOCK_DGRAM socket types are available.

This patch adds AF_VSOCK support to ss(8) so that sockets can be
observed.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 misc/ss.c     | 184 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 man/man8/ss.8 |   8 ++-
 2 files changed, 188 insertions(+), 4 deletions(-)

diff --git a/misc/ss.c b/misc/ss.c
index 005e781d..8b563bd4 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -44,6 +44,7 @@
 #include <linux/packet_diag.h>
 #include <linux/netlink_diag.h>
 #include <linux/sctp.h>
+#include <linux/vm_sockets_diag.h>
 
 #define MAGIC_SEQ 123456
 
@@ -126,6 +127,8 @@ enum {
 	PACKET_R_DB,
 	NETLINK_DB,
 	SCTP_DB,
+	VSOCK_ST_DB,
+	VSOCK_DG_DB,
 	MAX_DB
 };
 
@@ -134,6 +137,7 @@ enum {
 #define ALL_DB ((1<<MAX_DB)-1)
 #define INET_L4_DBM ((1<<TCP_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,
@@ -222,6 +226,14 @@ static const struct filter default_dbs[MAX_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),
+	},
 };
 
 static const struct filter default_afs[AF_MAX] = {
@@ -245,6 +257,10 @@ static const struct filter default_afs[AF_MAX] = {
 		.dbs    = (1 << NETLINK_DB),
 		.states = (1 << SS_CLOSE),
 	},
+	[AF_VSOCK] = {
+		.dbs    = VSOCK_DBM,
+		.states = SS_CONN,
+	},
 };
 
 static int do_default = 1;
@@ -283,6 +299,8 @@ static void filter_default_dbs(struct filter *f)
 	filter_db_set(f, PACKET_DG_DB);
 	filter_db_set(f, NETLINK_DB);
 	filter_db_set(f, SCTP_DB);
+	filter_db_set(f, VSOCK_ST_DB);
+	filter_db_set(f, VSOCK_DG_DB);
 }
 
 static void filter_states_set(struct filter *f, int states)
@@ -791,6 +809,18 @@ static const char *proto_name(int protocol)
 	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 void sock_state_print(struct sockstat *s)
 {
 	const char *sock_name;
@@ -823,6 +853,9 @@ static void sock_state_print(struct sockstat *s)
 	case AF_NETLINK:
 		sock_name = "nl";
 		break;
+	case AF_VSOCK:
+		sock_name = vsock_netid_name(s->type);
+		break;
 	default:
 		sock_name = "unknown";
 	}
@@ -1149,6 +1182,8 @@ static int run_ssfilter(struct ssfilter *f, struct sockstat *s)
 			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);
 	}
@@ -1524,6 +1559,15 @@ void *parse_devcond(char *name)
 	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));
+}
+
 void *parse_hostcond(char *addr, bool is_port)
 {
 	char *port = NULL;
@@ -1598,6 +1642,37 @@ void *parse_hostcond(char *addr, bool is_port)
 		goto out;
 	}
 
+	if (fam == AF_VSOCK || strncmp(addr, "vsock:", 6) == 0) {
+		__u32 cid = ~(__u32)0;
+
+		a.addr.family = AF_VSOCK;
+		if (strncmp(addr, "vsock:", 6) == 0)
+			addr += 6;
+
+		if (is_port)
+			port = addr;
+		else {
+			port = strchr(addr, ':');
+			if (port) {
+				*port = '\0';
+				port++;
+			}
+		}
+
+		if (port && strcmp(port, "*") &&
+		    get_u32((__u32 *)&a.port, port, 0))
+			return NULL;
+
+		if (addr[0] && strcmp(addr, "*")) {
+			a.addr.bitlen = 32;
+			if (get_u32(&cid, addr, 0))
+				return NULL;
+		}
+		vsock_set_inet_prefix(&a.addr, cid);
+		fam = AF_VSOCK;
+		goto out;
+	}
+
 	if (fam == AF_INET || !strncmp(addr, "inet:", 5)) {
 		fam = AF_INET;
 		if (!strncmp(addr, "inet:", 5))
@@ -3674,6 +3749,88 @@ static int netlink_show(struct filter *f)
 	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);
+
+	printf("\n");
+}
+
+static int vsock_show_sock(const struct sockaddr_nl *addr,
+			   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);
+}
+
 struct sock_diag_msg {
 	__u8 sdiag_family;
 };
@@ -3694,6 +3851,8 @@ static int generic_show_sock(const struct sockaddr_nl *addr,
 		return packet_show_sock(addr, nlh, arg);
 	case AF_NETLINK:
 		return netlink_show_sock(addr, nlh, arg);
+	case AF_VSOCK:
+		return vsock_show_sock(addr, nlh, arg);
 	default:
 		return -1;
 	}
@@ -3921,14 +4080,15 @@ static void _usage(FILE *dest)
 "   -d, --dccp          display only DCCP sockets\n"
 "   -w, --raw           display only RAW sockets\n"
 "   -x, --unix          display only Unix domain sockets\n"
+"       --vsock         display only vsock sockets\n"
 "   -f, --family=FAMILY display sockets of type FAMILY\n"
-"       FAMILY := {inet|inet6|link|unix|netlink|help}\n"
+"       FAMILY := {inet|inet6|link|unix|netlink|vsock|help}\n"
 "\n"
 "   -K, --kill          forcibly close sockets, display what was closed\n"
 "   -H, --no-header     Suppress header line\n"
 "\n"
 "   -A, --query=QUERY, --socket=QUERY\n"
-"       QUERY := {all|inet|tcp|udp|raw|unix|unix_dgram|unix_stream|unix_seqpacket|packet|netlink}[,QUERY]\n"
+"       QUERY := {all|inet|tcp|udp|raw|unix|unix_dgram|unix_stream|unix_seqpacket|packet|netlink|vsock_stream|vsock_dgram}[,QUERY]\n"
 "\n"
 "   -D, --diag=FILE     Dump raw information about TCP sockets to FILE\n"
 "   -F, --filter=FILE   read filter information from FILE\n"
@@ -4001,6 +4161,9 @@ static int scan_state(const char *state)
 	exit(-1);
 }
 
+/* Values 'v' and 'V' are already used so a non-character is used */
+#define OPT_VSOCK 256
+
 static const struct option long_opts[] = {
 	{ "numeric", 0, 0, 'n' },
 	{ "resolve", 0, 0, 'r' },
@@ -4017,6 +4180,7 @@ static const struct option long_opts[] = {
 	{ "udp", 0, 0, 'u' },
 	{ "raw", 0, 0, 'w' },
 	{ "unix", 0, 0, 'x' },
+	{ "vsock", 0, 0, OPT_VSOCK },
 	{ "all", 0, 0, 'a' },
 	{ "listening", 0, 0, 'l' },
 	{ "ipv4", 0, 0, '4' },
@@ -4102,6 +4266,9 @@ int main(int argc, char *argv[])
 		case 'x':
 			filter_af_set(&current_filter, AF_UNIX);
 			break;
+		case OPT_VSOCK:
+			filter_af_set(&current_filter, AF_VSOCK);
+			break;
 		case 'a':
 			state_filter = SS_ALL;
 			break;
@@ -4128,6 +4295,8 @@ int main(int argc, char *argv[])
 				filter_af_set(&current_filter, AF_UNIX);
 			else if (strcmp(optarg, "netlink") == 0)
 				filter_af_set(&current_filter, AF_NETLINK);
+			else if (strcmp(optarg, "vsock") == 0)
+				filter_af_set(&current_filter, AF_VSOCK);
 			else if (strcmp(optarg, "help") == 0)
 				help();
 			else {
@@ -4193,6 +4362,15 @@ int main(int argc, char *argv[])
 					filter_db_set(&current_filter, PACKET_DG_DB);
 				} else if (strcmp(p, "netlink") == 0) {
 					filter_db_set(&current_filter, NETLINK_DB);
+				} else if (strcmp(p, "vsock") == 0) {
+					filter_db_set(&current_filter, VSOCK_ST_DB);
+					filter_db_set(&current_filter, VSOCK_DG_DB);
+				} else if (strcmp(p, "vsock_stream") == 0 ||
+					   strcmp(p, "v_str") == 0) {
+					filter_db_set(&current_filter, VSOCK_ST_DB);
+				} else if (strcmp(p, "vsock_dgram") == 0 ||
+					   strcmp(p, "v_dgr") == 0) {
+					filter_db_set(&current_filter, VSOCK_DG_DB);
 				} else {
 					fprintf(stderr, "ss: \"%s\" is illegal socket table id\n", p);
 					usage();
@@ -4408,6 +4586,8 @@ int main(int argc, char *argv[])
 		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 (show_users || show_proc_ctx || show_sock_ctx)
 		user_ent_destroy();
diff --git a/man/man8/ss.8 b/man/man8/ss.8
index 3bec97f0..3af509e9 100644
--- a/man/man8/ss.8
+++ b/man/man8/ss.8
@@ -125,14 +125,18 @@ Display Unix domain sockets (alias for -f unix).
 .B \-S, \-\-sctp
 Display SCTP sockets.
 .TP
+.B \-\-vsock
+Display vsock sockets (alias for -f vsock).
+.TP
 .B \-f FAMILY, \-\-family=FAMILY
 Display sockets of type FAMILY.
-Currently the following families are supported: unix, inet, inet6, link, netlink.
+Currently the following families are supported: unix, inet, inet6, link, netlink, vsock.
 .TP
 .B \-A QUERY, \-\-query=QUERY, \-\-socket=QUERY
 List of socket tables to dump, separated by commas. The following identifiers
 are understood: all, inet, tcp, udp, raw, unix, packet, netlink, unix_dgram,
-unix_stream, unix_seqpacket, packet_raw, packet_dgram, dccp, sctp.
+unix_stream, unix_seqpacket, packet_raw, packet_dgram, dccp, sctp,
+vsock_stream, vsock_dgram.
 .TP
 .B \-D FILE, \-\-diag=FILE
 Do not display anything, just dump raw information about TCP sockets to FILE after applying filters. If FILE is - stdout is used.
-- 
2.13.6

  parent reply	other threads:[~2017-10-06 15:49 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-06 15:48 [PATCH iproute2 v2 0/3] ss: add AF_VSOCK support Stefan Hajnoczi
2017-10-06 15:48 ` [PATCH iproute2 v2 1/3] ss: allow AF_FAMILY constants >32 Stefan Hajnoczi
2017-10-06 15:48 ` [PATCH iproute2 v2 2/3] include: add <linux/vm_sockets_diag.h> Stefan Hajnoczi
2017-10-06 15:48 ` Stefan Hajnoczi [this message]
2017-10-11 17:52 ` [PATCH iproute2 v2 0/3] ss: add AF_VSOCK support Stephen Hemminger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20171006154841.10495-4-stefanha@redhat.com \
    --to=stefanha@redhat.com \
    --cc=decui@microsoft.com \
    --cc=jhansen@vmware.com \
    --cc=netdev@vger.kernel.org \
    --cc=stephen@networkplumber.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.