When run in server mode, the sample RDS program opens PF_RDS socket,
attaches ebpf program to RDS socket which then uses bpf_skb_next_frag
helper along with bpf tail calls to inspect skb linear and non-linear
data.
To ease testing, RDS client functionality is also added so that users
can generate RDS packet.
Run server:
[root@lab71 bpf]# ./rds_skb -s 192.168.3.71
running server in a loop
transport tcp
server bound to address: 192.168.3.71 port 4000
server listening on 192.168.3.71
192.168.3.71 received a packet from 192.168.3.71 of len 8192 cmsg len 0,
on port 52287
payload contains:30 31 32 33 34 35 36 37 38 39 3a 3b 3c 3d 3e 3f 40 41
42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f 50 51 52 53 54 55 56 57 58 59
5a 5b 5c 5d 5e 5f 60 61 62 63 64 65 66 67 68 69 6a 6b ...
server listening on 192.168.3.71
Run client:
[root@lab70 bpf]# ./rds_skb -s 192.168.3.71 -c 192.168.3.70
transport tcp
client bound to address: 192.168.3.71 port 47437
client sending 8192 byte message from 192.168.3.71 to 192.168.3.70 on
port 47437
bpf program output:
[root@lab71]# cat /sys/kernel/debug/tracing/trace_pipe
<idle>-0 [000] ..s. 218923.839673: 0: 30 31 32
<idle>-0 [000] ..s. 218923.839682: 0: 33 34 35
<idle>-0 [000] ..s. 218923.845133: 0: be bf c0
<idle>-0 [000] ..s. 218923.845135: 0: c1 c2 c3
<idle>-0 [000] ..s. 218923.850581: 0: be bf c0
<idle>-0 [000] ..s. 218923.850582: 0: c1 c2 c3
<idle>-0 [000] ..s. 218923.850582: 0: no more skb frag
Note: changing MTU to 9000 help assure that RDS get skb with
fragments.
Signed-off-by: Tushar Dave <tushar.n.d...@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nel...@oracle.com>
Reviewed-by: Sowmini Varadhan <sowmini.varad...@oracle.com>
---
samples/bpf/Makefile | 3 +
samples/bpf/rds_skb_kern.c | 87 +++++++++++++
samples/bpf/rds_skb_user.c | 311 +++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 401 insertions(+)
create mode 100644 samples/bpf/rds_skb_kern.c
create mode 100644 samples/bpf/rds_skb_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 62a99ab..a05c3b2 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -51,6 +51,7 @@ hostprogs-y += cpustat
hostprogs-y += xdp_adjust_tail
hostprogs-y += xdpsock
hostprogs-y += xdp_fwd
+hostprogs-y += rds_skb
# Libbpf dependencies
LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
@@ -105,6 +106,7 @@ cpustat-objs := bpf_load.o cpustat_user.o
xdp_adjust_tail-objs := xdp_adjust_tail_user.o
xdpsock-objs := bpf_load.o xdpsock_user.o
xdp_fwd-objs := bpf_load.o xdp_fwd_user.o
+rds_skb-objs := bpf_load.o rds_skb_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -160,6 +162,7 @@ always += cpustat_kern.o
always += xdp_adjust_tail_kern.o
always += xdpsock_kern.o
always += xdp_fwd_kern.o
+always += rds_skb_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/
diff --git a/samples/bpf/rds_skb_kern.c b/samples/bpf/rds_skb_kern.c
new file mode 100644
index 0000000..c8832d4
--- /dev/null
+++ b/samples/bpf/rds_skb_kern.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/filter.h>
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <linux/rds.h>
+#include "bpf_helpers.h"
+
+
+#define PROG(F) SEC("socket/"__stringify(F)) int bpf_func_##F
+
+#define bpf_printk(fmt, ...) \
+({ \
+ char ____fmt[] = fmt; \
+ bpf_trace_printk(____fmt, sizeof(____fmt), \
+ ##__VA_ARGS__); \
+})
+
+
+struct bpf_map_def SEC("maps") jmp_table = {
+ .type = BPF_MAP_TYPE_PROG_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = 2,
+};
+
+#define FRAG 1
+
+static inline void dump_skb(struct __sk_buff *skb)
+{
+ void *data = (void *)(long) skb->data_meta;
+ void *data_end = (void *)(long) skb->data_end;
+ unsigned char *d;
+
+ if (data + 6 > data_end)
+ return;
+
+ d = (unsigned char *)data;
+ bpf_printk("%x %x %x\n", d[0], d[1], d[2]);
+ bpf_printk("%x %x %x\n", d[3], d[4], d[5]);
+ return;
+}
+
+static void populate_skb_frags(struct __sk_buff *skb)
+{
+ int ret;
+
+ ret = bpf_next_skb_frag(skb);
+ if (ret == -ENODATA) {
+ bpf_printk("no more skb frag\n");
+ return;
+ }
+
+ bpf_tail_call(skb, &jmp_table, 1);
+}
+
+/* walk skb frag */
+
+PROG(FRAG)(struct __sk_buff *skb)
+{
+ dump_skb(skb);
+ populate_skb_frags(skb);
+ return 0;
+}
+
+SEC("socket/0")
+int main_prog(struct __sk_buff *skb)
+{
+ void *data = (void *)(long) skb->data;
+ void *data_end = (void *)(long) skb->data_end;
+ int ret;
+ unsigned char *d;
+
+ if (data + 6 > data_end) {
+ bpf_printk("out\n");
+ return 0;
+ }
+
+ d = (unsigned char *)data;
+ bpf_printk("%x %x %x\n", d[0], d[1], d[2]);
+ bpf_printk("%x %x %x\n", d[3], d[4], d[5]);
+
+ populate_skb_frags(skb);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/rds_skb_user.c b/samples/bpf/rds_skb_user.c
new file mode 100644
index 0000000..9f73dc3
--- /dev/null
+++ b/samples/bpf/rds_skb_user.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <arpa/inet.h>
+#include <assert.h>
+#include "bpf_load.h"
+#include <getopt.h>
+#include <errno.h>
+#include <netinet/in.h>
+#include <limits.h>
+#include <linux/sockios.h>
+#include <linux/rds.h>
+#include <linux/errqueue.h>
+#include <linux/bpf.h>
+#include <strings.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#define TESTPORT 4000
+#define BUFSIZE 8192
+
+static const char *trans2str(int trans)
+{
+ switch (trans) {
+ case RDS_TRANS_TCP:
+ return ("tcp");
+ case RDS_TRANS_NONE:
+ return ("none");
+ default:
+ return ("unknown");
+ }
+}
+
+static int gettransport(int sock)
+{
+ int err;
+ char val;
+ socklen_t len = sizeof(int);
+
+ err = getsockopt(sock, SOL_RDS, SO_RDS_TRANSPORT,
+ (char *)&val, &len);
+ if (err < 0) {
+ fprintf(stderr, "%s: getsockopt %s\n",
+ __func__, strerror(errno));
+ return err;
+ }
+ return (int)val;
+}
+
+static int settransport(int sock, int transport)
+{
+ int err;
+
+ err = setsockopt(sock, SOL_RDS, SO_RDS_TRANSPORT,
+ (char *)&transport, sizeof(transport));
+ if (err < 0) {
+ fprintf(stderr, "could not set transport %s, %s\n",
+ trans2str(transport), strerror(errno));
+ }
+ return err;
+}
+
+static void print_sock_local_info(int fd, char *str, struct sockaddr_in *ret)
+{
+ socklen_t sin_size = sizeof(struct sockaddr_in);
+ struct sockaddr_in sin;
+ int err;
+
+ err = getsockname(fd, (struct sockaddr *)&sin, &sin_size);
+ if (err < 0) {
+ fprintf(stderr, "%s getsockname %s\n",
+ __func__, strerror(errno));
+ return;
+ }
+ printf("%s address: %s port %d\n",
+ (str ? str : ""), inet_ntoa(sin.sin_addr), ntohs(sin.sin_port));
+
+ if (ret != NULL)
+ *ret = sin;
+}
+
+static void server(char *address, in_port_t port)
+{
+ struct sockaddr_in sin, din;
+ struct msghdr msg;
+ struct iovec *iov;
+ int rc, sock;
+ char *buf;
+
+ buf = calloc(BUFSIZE, sizeof(char));
+ if (!buf) {
+ fprintf(stderr, "%s: calloc %s\n", __func__, strerror(errno));
+ return;
+ }
+
+ sock = socket(PF_RDS, SOCK_SEQPACKET, 0);
+ if (sock < 0) {
+ fprintf(stderr, "%s: socket %s\n", __func__, strerror(errno));
+ goto out;
+ }
+ if (settransport(sock, RDS_TRANS_TCP) < 0)
+ goto out;
+
+ printf("transport %s\n", trans2str(gettransport(sock)));
+
+ memset(&sin, 0, sizeof(sin));
+ sin.sin_family = AF_INET;
+ sin.sin_addr.s_addr = inet_addr(address);
+ sin.sin_port = htons(port);
+
+ rc = bind(sock, (struct sockaddr *)&sin, sizeof(sin));
+ if (rc < 0) {
+ fprintf(stderr, "%s: bind %s\n", __func__, strerror(errno));
+ goto out;
+ }
+
+ /* attach eBPF program */
+ assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd[1],
+ sizeof(prog_fd[0])) == 0);
+
+ print_sock_local_info(sock, "server bound to", NULL);
+
+ iov = calloc(1, sizeof(struct iovec));
+ if (!iov) {
+ fprintf(stderr, "%s: calloc %s\n", __func__, strerror(errno));
+ goto out;
+ }
+
+ while (1) {
+ memset(buf, 0, BUFSIZE);
+ iov[0].iov_base = buf;
+ iov[0].iov_len = BUFSIZE;
+
+ memset(&msg, 0, sizeof(msg));
+ msg.msg_name = &din;
+ msg.msg_namelen = sizeof(din);
+ msg.msg_iov = iov;
+ msg.msg_iovlen = 1;
+
+ printf("server listening on %s\n", inet_ntoa(sin.sin_addr));
+
+ rc = recvmsg(sock, &msg, 0);
+ if (rc < 0) {
+ fprintf(stderr, "%s: recvmsg %s\n",
+ __func__, strerror(errno));
+ break;
+ }
+
+ printf("%s received a packet from %s of len %d cmsg len %d, on
port %d\n",
+ inet_ntoa(sin.sin_addr),
+ inet_ntoa(din.sin_addr),
+ (uint32_t) iov[0].iov_len,
+ (uint32_t) msg.msg_controllen,
+ ntohs(din.sin_port));
+
+ {
+ int i;
+
+ printf("payload contains:");
+ for (i = 0; i < 60; i++)
+ printf("%x ", buf[i]);
+ printf("...\n");
+ }
+ }
+ free(iov);
+out:
+ free(buf);
+}
+
+static void create_message(char *buf)
+{
+ unsigned int i;
+
+ for (i = 0; i < BUFSIZE; i++) {
+ buf[i] = i + 0x30;
+ }
+}
+
+static int build_rds_packet(struct msghdr *msg, char *buf)
+{
+ struct iovec *iov;
+
+ iov = calloc(1, sizeof(struct iovec));
+ if (!iov) {
+ fprintf(stderr, "%s: calloc %s\n", __func__, strerror(errno));
+ return -1;
+ }
+
+ msg->msg_iov = iov;
+ msg->msg_iovlen = 1;
+
+ iov[0].iov_base = buf;
+ iov[0].iov_len = BUFSIZE * sizeof(char);
+
+ return 0;
+}
+
+static void client(char *localaddr, char *remoteaddr, in_port_t server_port)
+{
+ struct sockaddr_in sin, din;
+ struct msghdr msg;
+ int rc, sock;
+ char *buf;
+
+ buf = calloc(BUFSIZE, sizeof(char));
+ if (!buf) {
+ fprintf(stderr, "%s: calloc %s\n", __func__, strerror(errno));
+ return;
+ }
+
+ create_message(buf);
+
+ sock = socket(PF_RDS, SOCK_SEQPACKET, 0);
+ if (sock < 0) {
+ fprintf(stderr, "%s: socket %s\n", __func__, strerror(errno));
+ goto out;
+ }
+
+ if (settransport(sock, RDS_TRANS_TCP) < 0)
+ goto out;
+
+ printf("transport %s\n", trans2str(gettransport(sock)));
+
+ memset(&sin, 0, sizeof(sin));
+ sin.sin_family = AF_INET;
+ sin.sin_addr.s_addr = inet_addr(localaddr);
+ sin.sin_port = 0;
+
+ rc = bind(sock, (struct sockaddr *)&sin, sizeof(sin));
+ if (rc < 0) {
+ fprintf(stderr, "%s: bind %s\n", __func__, strerror(errno));
+ goto out;
+ }
+ print_sock_local_info(sock, "client bound to", &sin);
+
+ memset(&msg, 0, sizeof(msg));
+ msg.msg_name = &din;
+ msg.msg_namelen = sizeof(din);
+
+ memset(&din, 0, sizeof(din));
+ din.sin_family = AF_INET;
+ din.sin_addr.s_addr = inet_addr(remoteaddr);
+ din.sin_port = htons(server_port);
+
+ rc = build_rds_packet(&msg, buf);
+ if (rc < 0)
+ goto out;
+
+ printf("client sending %d byte message from %s to %s on port %d\n",
+ (uint32_t) msg.msg_iov->iov_len, localaddr,
+ remoteaddr, ntohs(sin.sin_port));
+
+ rc = sendmsg(sock, &msg, 0);
+ if (rc < 0)
+ fprintf(stderr, "%s: sendmsg %s\n", __func__, strerror(errno));
+
+ if (msg.msg_control)
+ free(msg.msg_control);
+ if (msg.msg_iov)
+ free(msg.msg_iov);
+out:
+ free(buf);
+
+ return;
+}
+
+static void usage(char *progname)
+{
+ fprintf(stderr, "Usage %s [-s srvaddr] [-c clientaddr]\n", progname);
+}
+
+int main(int argc, char **argv)
+{
+ in_port_t server_port = TESTPORT;
+ char *serveraddr = NULL;
+ char *clientaddr = NULL;
+ char filename[256];
+ int opt;
+
+ while ((opt = getopt(argc, argv, "s:c:")) != -1) {
+ switch (opt) {
+ case 's':
+ serveraddr = optarg;
+ break;
+ case 'c':
+ clientaddr = optarg;
+ break;
+ default:
+ usage(argv[0]);
+ return 1;
+ }
+ }
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ fprintf(stderr, "Error: load_bpf_file %s", bpf_log_buf);
+ return 1;
+ }
+
+ if (serveraddr && !clientaddr) {
+ printf("running server in a loop\n");
+ server(serveraddr, server_port);
+ } else if (serveraddr && clientaddr) {
+ client(clientaddr, serveraddr, server_port);
+ }
+
+ return 0;
+}
--
1.8.3.1
