selftests/bpf: tests for using dynptrs to parse skb and xdp buffers

Test skb and xdp dynptr functionality in the following ways:

1) progs/test_cls_redirect_dynptr.c
   * Rewrite "progs/test_cls_redirect.c" test to use dynptrs to parse
     skb data

   * This is a great example of how dynptrs can be used to simplify a
     lot of the parsing logic for non-statically known values.

     When measuring the user + system time between the original version
     vs. using dynptrs, and averaging the time for 10 runs (using
     "time ./test_progs -t cls_redirect"):
         original version: 0.092 sec
         with dynptrs: 0.078 sec

2) progs/test_xdp_dynptr.c
   * Rewrite "progs/test_xdp.c" test to use dynptrs to parse xdp data

     When measuring the user + system time between the original version
     vs. using dynptrs, and averaging the time for 10 runs (using
     "time ./test_progs -t xdp_attach"):
         original version: 0.118 sec
         with dynptrs: 0.094 sec

3) progs/test_l4lb_noinline_dynptr.c
   * Rewrite "progs/test_l4lb_noinline.c" test to use dynptrs to parse
     skb data

     When measuring the user + system time between the original version
     vs. using dynptrs, and averaging the time for 10 runs (using
     "time ./test_progs -t l4lb_all"):
         original version: 0.062 sec
         with dynptrs: 0.081 sec

     For number of processed verifier instructions:
         original version: 6268 insns
         with dynptrs: 2588 insns

4) progs/test_parse_tcp_hdr_opt_dynptr.c
   * Add sample code for parsing tcp hdr opt lookup using dynptrs.
     This logic is lifted from a real-world use case of packet parsing
     in katran [0], a layer 4 load balancer. The original version
     "progs/test_parse_tcp_hdr_opt.c" (not using dynptrs) is included
     here as well, for comparison.

     When measuring the user + system time between the original version
     vs. using dynptrs, and averaging the time for 10 runs (using
     "time ./test_progs -t parse_tcp_hdr_opt"):
         original version: 0.031 sec
         with dynptrs: 0.045 sec

5) progs/dynptr_success.c
   * Add test case "test_skb_readonly" for testing attempts at writes
     on a prog type with read-only skb ctx.
   * Add "test_dynptr_skb_data" for testing that bpf_dynptr_data isn't
     supported for skb progs.

6) progs/dynptr_fail.c
   * Add test cases "skb_invalid_data_slice{1,2,3,4}" and
     "xdp_invalid_data_slice{1,2}" for testing that helpers that modify the
     underlying packet buffer automatically invalidate the associated
     data slice.
   * Add test cases "skb_invalid_ctx" and "xdp_invalid_ctx" for testing
     that prog types that do not support bpf_dynptr_from_skb/xdp don't
     have access to the API.
   * Add test case "dynptr_slice_var_len{1,2}" for testing that
     variable-sized len can't be passed in to bpf_dynptr_slice
   * Add test case "skb_invalid_slice_write" for testing that writes to a
     read-only data slice are rejected by the verifier.
   * Add test case "data_slice_out_of_bounds_skb" for testing that
     writes to an area outside the slice are rejected.
   * Add test case "invalid_slice_rdwr_rdonly" for testing that prog
     types that don't allow writes to packet data don't accept any calls
     to bpf_dynptr_slice_rdwr.

[0] https://github.com/facebookincubator/katran/blob/main/katran/lib/bpf/pckt_parsing.h

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230301154953.641654-11-joannelkoong@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 119 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c
new file mode 100644
index 000000000000..79bab9b50e9e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* This parsing logic is taken from the open source library katran, a layer 4
+ * load balancer.
+ *
+ * This code logic using dynptrs can be found in test_parse_tcp_hdr_opt_dynptr.c
+ *
+ * https://github.com/facebookincubator/katran/blob/main/katran/lib/bpf/pckt_parsing.h
+ */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/tcp.h>
+#include <stdbool.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+#include "test_tcp_hdr_options.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Kind number used for experiments */
+const __u32 tcp_hdr_opt_kind_tpr = 0xFD;
+/* Length of the tcp header option */
+const __u32 tcp_hdr_opt_len_tpr = 6;
+/* maximum number of header options to check to lookup server_id */
+const __u32 tcp_hdr_opt_max_opt_checks = 15;
+
+__u32 server_id;
+
+struct hdr_opt_state {
+	__u32 server_id;
+	__u8 byte_offset;
+	__u8 hdr_bytes_remaining;
+};
+
+static int parse_hdr_opt(const struct xdp_md *xdp, struct hdr_opt_state *state)
+{
+	const void *data = (void *)(long)xdp->data;
+	const void *data_end = (void *)(long)xdp->data_end;
+	__u8 *tcp_opt, kind, hdr_len;
+
+	tcp_opt = (__u8 *)(data + state->byte_offset);
+	if (tcp_opt + 1 > data_end)
+		return -1;
+
+	kind = tcp_opt[0];
+
+	if (kind == TCPOPT_EOL)
+		return -1;
+
+	if (kind == TCPOPT_NOP) {
+		state->hdr_bytes_remaining--;
+		state->byte_offset++;
+		return 0;
+	}
+
+	if (state->hdr_bytes_remaining < 2 ||
+	    tcp_opt + sizeof(__u8) + sizeof(__u8) > data_end)
+		return -1;
+
+	hdr_len = tcp_opt[1];
+	if (hdr_len > state->hdr_bytes_remaining)
+		return -1;
+
+	if (kind == tcp_hdr_opt_kind_tpr) {
+		if (hdr_len != tcp_hdr_opt_len_tpr)
+			return -1;
+
+		if (tcp_opt + tcp_hdr_opt_len_tpr > data_end)
+			return -1;
+
+		state->server_id = *(__u32 *)&tcp_opt[2];
+		return 1;
+	}
+
+	state->hdr_bytes_remaining -= hdr_len;
+	state->byte_offset += hdr_len;
+	return 0;
+}
+
+SEC("xdp")
+int xdp_ingress_v6(struct xdp_md *xdp)
+{
+	const void *data = (void *)(long)xdp->data;
+	const void *data_end = (void *)(long)xdp->data_end;
+	struct hdr_opt_state opt_state = {};
+	__u8 tcp_hdr_opt_len = 0;
+	struct tcphdr *tcp_hdr;
+	__u64 tcp_offset = 0;
+	__u32 off;
+	int err;
+
+	tcp_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
+	tcp_hdr = (struct tcphdr *)(data + tcp_offset);
+	if (tcp_hdr + 1 > data_end)
+		return XDP_DROP;
+
+	tcp_hdr_opt_len = (tcp_hdr->doff * 4) - sizeof(struct tcphdr);
+	if (tcp_hdr_opt_len < tcp_hdr_opt_len_tpr)
+		return XDP_DROP;
+
+	opt_state.hdr_bytes_remaining = tcp_hdr_opt_len;
+	opt_state.byte_offset = sizeof(struct tcphdr) + tcp_offset;
+
+	/* max number of bytes of options in tcp header is 40 bytes */
+	for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) {
+		err = parse_hdr_opt(xdp, &opt_state);
+
+		if (err || !opt_state.hdr_bytes_remaining)
+			break;
+	}
+
+	if (!opt_state.server_id)
+		return XDP_DROP;
+
+	server_id = opt_state.server_id;
+
+	return XDP_PASS;
+}