From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 18 Mar 2018 12:57:41 -0700
Subject: bpf: sockmap sample, add option to attach SK_MSG program
Patch-mainline: v4.17-rc1
Git-commit: 4c4c3c276c099f265c8b11e0132ce826ee718e2c
References: bsc#1109837
Add sockmap option to use SK_MSG program types.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
samples/bpf/bpf_load.c | 8 ++-
samples/sockmap/sockmap_kern.c | 52 +++++++++++++++++++++++
samples/sockmap/sockmap_user.c | 67 +++++++++++++++++++++++++++---
tools/include/uapi/linux/bpf.h | 13 +++++
tools/lib/bpf/libbpf.c | 1
tools/testing/selftests/bpf/bpf_helpers.h | 3 -
6 files changed, 134 insertions(+), 10 deletions(-)
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -66,6 +66,7 @@ static int load_and_attach(const char *e
bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0;
bool is_sockops = strncmp(event, "sockops", 7) == 0;
bool is_sk_skb = strncmp(event, "sk_skb", 6) == 0;
+ bool is_sk_msg = strncmp(event, "sk_msg", 6) == 0;
size_t insns_cnt = size / sizeof(struct bpf_insn);
enum bpf_prog_type prog_type;
char buf[256];
@@ -95,6 +96,8 @@ static int load_and_attach(const char *e
prog_type = BPF_PROG_TYPE_SOCK_OPS;
} else if (is_sk_skb) {
prog_type = BPF_PROG_TYPE_SK_SKB;
+ } else if (is_sk_msg) {
+ prog_type = BPF_PROG_TYPE_SK_MSG;
} else {
printf("Unknown event '%s'\n", event);
return -1;
@@ -112,7 +115,7 @@ static int load_and_attach(const char *e
if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk)
return 0;
- if (is_socket || is_sockops || is_sk_skb) {
+ if (is_socket || is_sockops || is_sk_skb || is_sk_msg) {
if (is_socket)
event += 6;
else
@@ -588,7 +591,8 @@ static int do_load_bpf_file(const char *
memcmp(shname, "socket", 6) == 0 ||
memcmp(shname, "cgroup/", 7) == 0 ||
memcmp(shname, "sockops", 7) == 0 ||
- memcmp(shname, "sk_skb", 6) == 0) {
+ memcmp(shname, "sk_skb", 6) == 0 ||
+ memcmp(shname, "sk_msg", 6) == 0) {
ret = load_and_attach(shname, data->d_buf,
data->d_size);
if (ret != 0)
--- a/samples/sockmap/sockmap_kern.c
+++ b/samples/sockmap/sockmap_kern.c
@@ -43,6 +43,20 @@ struct bpf_map_def SEC("maps") sock_map
.max_entries = 20,
};
+struct bpf_map_def SEC("maps") sock_map_txmsg = {
+ .type = BPF_MAP_TYPE_SOCKMAP,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_map_redir = {
+ .type = BPF_MAP_TYPE_SOCKMAP,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 1,
+};
+
SEC("sk_skb1")
int bpf_prog1(struct __sk_buff *skb)
{
@@ -105,4 +119,42 @@ int bpf_sockmap(struct bpf_sock_ops *sko
return 0;
}
+
+SEC("sk_msg1")
+int bpf_prog4(struct sk_msg_md *msg)
+{
+ return SK_PASS;
+}
+
+SEC("sk_msg2")
+int bpf_prog5(struct sk_msg_md *msg)
+{
+ void *data_end = (void *)(long) msg->data_end;
+ void *data = (void *)(long) msg->data;
+
+ bpf_printk("sk_msg2: data length %i\n", (__u32)data_end - (__u32)data);
+ return SK_PASS;
+}
+
+SEC("sk_msg3")
+int bpf_prog6(struct sk_msg_md *msg)
+{
+ void *data_end = (void *)(long) msg->data_end;
+ void *data = (void *)(long) msg->data;
+ int ret = 0;
+
+ return bpf_msg_redirect_map(msg, &sock_map_redir, ret, 0);
+}
+
+SEC("sk_msg4")
+int bpf_prog7(struct sk_msg_md *msg)
+{
+ void *data_end = (void *)(long) msg->data_end;
+ void *data = (void *)(long) msg->data;
+ int ret = 0;
+
+ bpf_printk("sk_msg3: redirect(%iB)\n", (__u32)data_end - (__u32)data);
+ return bpf_msg_redirect_map(msg, &sock_map_redir, ret, 0);
+}
+
char _license[] SEC("license") = "GPL";
--- a/samples/sockmap/sockmap_user.c
+++ b/samples/sockmap/sockmap_user.c
@@ -54,6 +54,11 @@ void running_handler(int a);
/* global sockets */
int s1, s2, c1, c2, p1, p2;
+int txmsg_pass;
+int txmsg_noisy;
+int txmsg_redir;
+int txmsg_redir_noisy;
+
static const struct option long_options[] = {
{"help", no_argument, NULL, 'h' },
{"cgroup", required_argument, NULL, 'c' },
@@ -62,6 +67,10 @@ static const struct option long_options[
{"iov_count", required_argument, NULL, 'i' },
{"length", required_argument, NULL, 'l' },
{"test", required_argument, NULL, 't' },
+ {"txmsg", no_argument, &txmsg_pass, 1 },
+ {"txmsg_noisy", no_argument, &txmsg_noisy, 1 },
+ {"txmsg_redir", no_argument, &txmsg_redir, 1 },
+ {"txmsg_redir_noisy", no_argument, &txmsg_redir_noisy, 1},
{0, 0, NULL, 0 }
};
@@ -447,13 +456,13 @@ enum {
int main(int argc, char **argv)
{
- int iov_count = 1, length = 1024, rate = 1, verbose = 0;
+ int iov_count = 1, length = 1024, rate = 1, verbose = 0, tx_prog_fd;
struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
int opt, longindex, err, cg_fd = 0;
int test = PING_PONG;
char filename[256];
- while ((opt = getopt_long(argc, argv, "hvc:r:i:l:t:",
+ while ((opt = getopt_long(argc, argv, ":hvc:r:i:l:t:",
long_options, &longindex)) != -1) {
switch (opt) {
/* Cgroup configuration */
@@ -490,6 +499,8 @@ int main(int argc, char **argv)
return -1;
}
break;
+ case 0:
+ break;
case 'h':
default:
usage(argv);
@@ -515,16 +526,16 @@ int main(int argc, char **argv)
/* catch SIGINT */
signal(SIGINT, running_handler);
- /* If base test skip BPF setup */
- if (test == BASE)
- goto run;
-
if (load_bpf_file(filename)) {
fprintf(stderr, "load_bpf_file: (%s) %s\n",
filename, strerror(errno));
return 1;
}
+ /* If base test skip BPF setup */
+ if (test == BASE)
+ goto run;
+
/* Attach programs to sockmap */
err = bpf_prog_attach(prog_fd[0], map_fd[0],
BPF_SK_SKB_STREAM_PARSER, 0);
@@ -557,6 +568,50 @@ run:
goto out;
}
+ /* Attach txmsg program to sockmap */
+ if (txmsg_pass)
+ tx_prog_fd = prog_fd[3];
+ else if (txmsg_noisy)
+ tx_prog_fd = prog_fd[4];
+ else if (txmsg_redir)
+ tx_prog_fd = prog_fd[5];
+ else if (txmsg_redir_noisy)
+ tx_prog_fd = prog_fd[6];
+ else
+ tx_prog_fd = 0;
+
+ if (tx_prog_fd) {
+ int redir_fd, i = 0;
+
+ err = bpf_prog_attach(tx_prog_fd,
+ map_fd[1], BPF_SK_MSG_VERDICT, 0);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_prog_attach (txmsg): %d (%s)\n",
+ err, strerror(errno));
+ return err;
+ }
+
+ err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg): %d (%s\n",
+ err, strerror(errno));
+ return err;
+ }
+ if (test == SENDMSG)
+ redir_fd = c2;
+ else
+ redir_fd = c1;
+
+ err = bpf_map_update_elem(map_fd[2], &i, &redir_fd, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg): %d (%s\n",
+ err, strerror(errno));
+ return err;
+ }
+ }
if (test == PING_PONG)
err = forever_ping_pong(rate, verbose);
else if (test == SENDMSG)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -716,6 +716,15 @@ union bpf_attr {
* @buf: buf to fill
* @buf_size: size of the buf
* Return : 0 on success or negative error code
+ *
+ * int bpf_msg_redirect_map(map, key, flags)
+ * Redirect msg to a sock in map using key as a lookup key for the
+ * sock in map.
+ * @map: pointer to sockmap
+ * @key: key to lookup sock in map
+ * @flags: reserved for future use
+ * Return: SK_PASS
+ *
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -776,7 +785,9 @@ union bpf_attr {
FN(perf_event_read_value), \
FN(perf_prog_read_value), \
FN(getsockopt), \
- FN(sock_ops_cb_flags_set),
+ FN(sock_ops_cb_flags_set), \
+ FN(msg_redirect_map), \
+ FN(msg_apply_bytes),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1857,6 +1857,7 @@ static const struct {
BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT),
BPF_PROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS),
BPF_PROG_SEC("sk_skb", BPF_PROG_TYPE_SK_SKB),
+ BPF_PROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG),
};
#undef BPF_PROG_SEC
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -83,7 +83,8 @@ static int (*bpf_perf_event_read_value)(
static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
unsigned int buf_size) =
(void *) BPF_FUNC_perf_prog_read_value;
-
+static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) =
+ (void *) BPF_FUNC_msg_redirect_map;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions