Merge branch 'bpf-flow-dissector-tests'

Stanislav Fomichev says:

====================
This patch series adds support for testing flow dissector BPF programs
by extending already existing BPF_PROG_TEST_RUN. The goal is to have
a packet as an input and `struct bpf_flow_key' as an output. That way
we can easily test flow dissector programs' behavior. I've also modified
existing test_progs.c test to do a simple flow dissector run as well.

* first patch introduces new __skb_flow_bpf_dissect to simplify
  sharing between __skb_flow_bpf_dissect and BPF_PROG_TEST_RUN
* second patch adds actual BPF_PROG_TEST_RUN support
* third patch adds example usage to the selftests

v3:
* rebased on top of latest bpf-next

v2:
* loop over 'kattr->test.repeat' inside of
  bpf_prog_test_run_flow_dissector, don't reuse
  bpf_test_run/bpf_test_run_one
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/linux/bpf.h

@@ -404,6 +404,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
 int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+				     const union bpf_attr *kattr,
+				     union bpf_attr __user *uattr);
 
 /* an array of programs to be executed under rcu_lock.
  *

include/linux/skbuff.h

@@ -1221,6 +1221,11 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
 }
 #endif
 
+struct bpf_flow_keys;
+bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
+			    const struct sk_buff *skb,
+			    struct flow_dissector *flow_dissector,
+			    struct bpf_flow_keys *flow_keys);
 bool __skb_flow_dissect(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
 			void *target_container,

net/bpf/test_run.c

@@ -240,3 +240,85 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	kfree(data);
 	return ret;
 }
+
+int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+				     const union bpf_attr *kattr,
+				     union bpf_attr __user *uattr)
+{
+	u32 size = kattr->test.data_size_in;
+	u32 repeat = kattr->test.repeat;
+	struct bpf_flow_keys flow_keys;
+	u64 time_start, time_spent = 0;
+	struct bpf_skb_data_end *cb;
+	u32 retval, duration;
+	struct sk_buff *skb;
+	struct sock *sk;
+	void *data;
+	int ret;
+	u32 i;
+
+	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
+		return -EINVAL;
+
+	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
+			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	sk = kzalloc(sizeof(*sk), GFP_USER);
+	if (!sk) {
+		kfree(data);
+		return -ENOMEM;
+	}
+	sock_net_set(sk, current->nsproxy->net_ns);
+	sock_init_data(NULL, sk);
+
+	skb = build_skb(data, 0);
+	if (!skb) {
+		kfree(data);
+		kfree(sk);
+		return -ENOMEM;
+	}
+	skb->sk = sk;
+
+	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+	__skb_put(skb, size);
+	skb->protocol = eth_type_trans(skb,
+				       current->nsproxy->net_ns->loopback_dev);
+	skb_reset_network_header(skb);
+
+	cb = (struct bpf_skb_data_end *)skb->cb;
+	cb->qdisc_cb.flow_keys = &flow_keys;
+
+	if (!repeat)
+		repeat = 1;
+
+	time_start = ktime_get_ns();
+	for (i = 0; i < repeat; i++) {
+		preempt_disable();
+		rcu_read_lock();
+		retval = __skb_flow_bpf_dissect(prog, skb,
+						&flow_keys_dissector,
+						&flow_keys);
+		rcu_read_unlock();
+		preempt_enable();
+
+		if (need_resched()) {
+			if (signal_pending(current))
+				break;
+			time_spent += ktime_get_ns() - time_start;
+			cond_resched();
+			time_start = ktime_get_ns();
+		}
+	}
+	time_spent += ktime_get_ns() - time_start;
+	do_div(time_spent, repeat);
+	duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+
+	ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
+			      retval, duration);
+
+	kfree_skb(skb);
+	kfree(sk);
+	return ret;
+}

net/core/filter.c

@@ -7711,6 +7711,7 @@ const struct bpf_verifier_ops flow_dissector_verifier_ops = {
 };
 
 const struct bpf_prog_ops flow_dissector_prog_ops = {
+	.test_run		= bpf_prog_test_run_flow_dissector,
 };
 
 int sk_detach_filter(struct sock *sk)

net/core/flow_dissector.c

@@ -683,6 +683,46 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 	}
 }
 
+bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
+			    const struct sk_buff *skb,
+			    struct flow_dissector *flow_dissector,
+			    struct bpf_flow_keys *flow_keys)
+{
+	struct bpf_skb_data_end cb_saved;
+	struct bpf_skb_data_end *cb;
+	u32 result;
+
+	/* Note that even though the const qualifier is discarded
+	 * throughout the execution of the BPF program, all changes(the
+	 * control block) are reverted after the BPF program returns.
+	 * Therefore, __skb_flow_dissect does not alter the skb.
+	 */
+
+	cb = (struct bpf_skb_data_end *)skb->cb;
+
+	/* Save Control Block */
+	memcpy(&cb_saved, cb, sizeof(cb_saved));
+	memset(cb, 0, sizeof(*cb));
+
+	/* Pass parameters to the BPF program */
+	memset(flow_keys, 0, sizeof(*flow_keys));
+	cb->qdisc_cb.flow_keys = flow_keys;
+	flow_keys->nhoff = skb_network_offset(skb);
+	flow_keys->thoff = flow_keys->nhoff;
+
+	bpf_compute_data_pointers((struct sk_buff *)skb);
+	result = BPF_PROG_RUN(prog, skb);
+
+	/* Restore state */
+	memcpy(cb, &cb_saved, sizeof(cb_saved));
+
+	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len);
+	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
+				   flow_keys->nhoff, skb->len);
+
+	return result == BPF_OK;
+}
+
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
@@ -714,7 +754,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_vlan *key_vlan;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
-	struct bpf_prog *attached = NULL;
 	int num_hdrs = 0;
 	u8 ip_proto = 0;
 	bool ret;
@@ -754,53 +793,30 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 					      FLOW_DISSECTOR_KEY_BASIC,
 					      target_container);
 
-	rcu_read_lock();
 	if (skb) {
+		struct bpf_flow_keys flow_keys;
+		struct bpf_prog *attached = NULL;
+
+		rcu_read_lock();
+
 		if (skb->dev)
 			attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog);
 		else if (skb->sk)
 			attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog);
 		else
 			WARN_ON_ONCE(1);
-	}
-	if (attached) {
-		/* Note that even though the const qualifier is discarded
-		 * throughout the execution of the BPF program, all changes(the
-		 * control block) are reverted after the BPF program returns.
-		 * Therefore, __skb_flow_dissect does not alter the skb.
-		 */
-		struct bpf_flow_keys flow_keys = {};
-		struct bpf_skb_data_end cb_saved;
-		struct bpf_skb_data_end *cb;
-		u32 result;
-
-		cb = (struct bpf_skb_data_end *)skb->cb;
-
-		/* Save Control Block */
-		memcpy(&cb_saved, cb, sizeof(cb_saved));
-		memset(cb, 0, sizeof(cb_saved));
 
-		/* Pass parameters to the BPF program */
-		cb->qdisc_cb.flow_keys = &flow_keys;
-		flow_keys.nhoff = nhoff;
-		flow_keys.thoff = nhoff;
-
-		bpf_compute_data_pointers((struct sk_buff *)skb);
-		result = BPF_PROG_RUN(attached, skb);
-
-		/* Restore state */
-		memcpy(cb, &cb_saved, sizeof(cb_saved));
-
-		flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len);
-		flow_keys.thoff = clamp_t(u16, flow_keys.thoff,
-					  flow_keys.nhoff, skb->len);
-
-		__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
-					 target_container);
+		if (attached) {
+			ret = __skb_flow_bpf_dissect(attached, skb,
+						     flow_dissector,
+						     &flow_keys);
+			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
+						 target_container);
+			rcu_read_unlock();
+			return ret;
+		}
 		rcu_read_unlock();
-		return result == BPF_OK;
 	}
-	rcu_read_unlock();
 
 	if (dissector_uses_key(flow_dissector,
 			       FLOW_DISSECTOR_KEY_ETH_ADDRS)) {

tools/testing/selftests/bpf/Makefile

@@ -148,6 +148,9 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_queue_map.o: test_queue_stack_map.h
 $(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
 
+$(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
+$(OUTPUT)/test_progs.o: flow_dissector_load.h
+
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')

tools/testing/selftests/bpf/flow_dissector_load.c

@@ -12,6 +12,7 @@
 #include <bpf/libbpf.h>
 
 #include "bpf_rlimit.h"
+#include "flow_dissector_load.h"
 
 const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
 const char *cfg_map_name = "jmp_table";
@@ -21,46 +22,13 @@ char *cfg_path_name;
 
 static void load_and_attach_program(void)
 {
-	struct bpf_program *prog, *main_prog;
-	struct bpf_map *prog_array;
-	int i, fd, prog_fd, ret;
+	int prog_fd, ret;
 	struct bpf_object *obj;
-	int prog_array_fd;
 
-	ret = bpf_prog_load(cfg_path_name, BPF_PROG_TYPE_FLOW_DISSECTOR, &obj,
-			    &prog_fd);
+	ret = bpf_flow_load(&obj, cfg_path_name, cfg_section_name,
+			    cfg_map_name, &prog_fd);
 	if (ret)
-		error(1, 0, "bpf_prog_load %s", cfg_path_name);
-
-	main_prog = bpf_object__find_program_by_title(obj, cfg_section_name);
-	if (!main_prog)
-		error(1, 0, "bpf_object__find_program_by_title %s",
-		      cfg_section_name);
-
-	prog_fd = bpf_program__fd(main_prog);
-	if (prog_fd < 0)
-		error(1, 0, "bpf_program__fd");
-
-	prog_array = bpf_object__find_map_by_name(obj, cfg_map_name);
-	if (!prog_array)
-		error(1, 0, "bpf_object__find_map_by_name %s", cfg_map_name);
-
-	prog_array_fd = bpf_map__fd(prog_array);
-	if (prog_array_fd < 0)
-		error(1, 0, "bpf_map__fd %s", cfg_map_name);
-
-	i = 0;
-	bpf_object__for_each_program(prog, obj) {
-		fd = bpf_program__fd(prog);
-		if (fd < 0)
-			error(1, 0, "bpf_program__fd");
-
-		if (fd != prog_fd) {
-			printf("%d: %s\n", i, bpf_program__title(prog, false));
-			bpf_map_update_elem(prog_array_fd, &i, &fd, BPF_ANY);
-			++i;
-		}
-	}
+		error(1, 0, "bpf_flow_load %s", cfg_path_name);
 
 	ret = bpf_prog_attach(prog_fd, 0 /* Ignore */, BPF_FLOW_DISSECTOR, 0);
 	if (ret)
@@ -69,7 +37,6 @@ static void load_and_attach_program(void)
 	ret = bpf_object__pin(obj, cfg_pin_path);
 	if (ret)
 		error(1, 0, "bpf_object__pin %s", cfg_pin_path);
-
 }
 
 static void detach_program(void)

tools/testing/selftests/bpf/flow_dissector_load.h

+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+#ifndef FLOW_DISSECTOR_LOAD
+#define FLOW_DISSECTOR_LOAD
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+static inline int bpf_flow_load(struct bpf_object **obj,
+				const char *path,
+				const char *section_name,
+				const char *map_name,
+				int *prog_fd)
+{
+	struct bpf_program *prog, *main_prog;
+	struct bpf_map *prog_array;
+	int prog_array_fd;
+	int ret, fd, i;
+
+	ret = bpf_prog_load(path, BPF_PROG_TYPE_FLOW_DISSECTOR, obj,
+			    prog_fd);
+	if (ret)
+		return ret;
+
+	main_prog = bpf_object__find_program_by_title(*obj, section_name);
+	if (!main_prog)
+		return ret;
+
+	*prog_fd = bpf_program__fd(main_prog);
+	if (*prog_fd < 0)
+		return ret;
+
+	prog_array = bpf_object__find_map_by_name(*obj, map_name);
+	if (!prog_array)
+		return ret;
+
+	prog_array_fd = bpf_map__fd(prog_array);
+	if (prog_array_fd < 0)
+		return ret;
+
+	i = 0;
+	bpf_object__for_each_program(prog, *obj) {
+		fd = bpf_program__fd(prog);
+		if (fd < 0)
+			return fd;
+
+		if (fd != *prog_fd) {
+			bpf_map_update_elem(prog_array_fd, &i, &fd, BPF_ANY);
+			++i;
+		}
+	}
+
+	return 0;
+}
+
+#endif /* FLOW_DISSECTOR_LOAD */

tools/testing/selftests/bpf/test_progs.c

@@ -39,6 +39,7 @@ typedef __u16 __sum16;
 #include "bpf_endian.h"
 #include "bpf_rlimit.h"
 #include "trace_helpers.h"
+#include "flow_dissector_load.h"
 
 static int error_cnt, pass_cnt;
 static bool jit_enabled;
@@ -53,9 +54,10 @@ static struct {
 } __packed pkt_v4 = {
 	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
 	.iph.ihl = 5,
-	.iph.protocol = 6,
+	.iph.protocol = IPPROTO_TCP,
 	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
 	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
 };
 
 /* ipv6 test vector */
@@ -65,9 +67,10 @@ static struct {
 	struct tcphdr tcp;
 } __packed pkt_v6 = {
 	.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
-	.iph.nexthdr = 6,
+	.iph.nexthdr = IPPROTO_TCP,
 	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
 	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
 };
 
 #define _CHECK(condition, tag, duration, format...) ({			\
@@ -1882,6 +1885,76 @@ static void test_queue_stack_map(int type)
 	bpf_object__close(obj);
 }
 
+#define CHECK_FLOW_KEYS(desc, got, expected)				\
+	CHECK(memcmp(&got, &expected, sizeof(got)) != 0,		\
+	      desc,							\
+	      "nhoff=%u/%u "						\
+	      "thoff=%u/%u "						\
+	      "addr_proto=0x%x/0x%x "					\
+	      "is_frag=%u/%u "						\
+	      "is_first_frag=%u/%u "					\
+	      "is_encap=%u/%u "						\
+	      "n_proto=0x%x/0x%x "					\
+	      "sport=%u/%u "						\
+	      "dport=%u/%u\n",						\
+	      got.nhoff, expected.nhoff,				\
+	      got.thoff, expected.thoff,				\
+	      got.addr_proto, expected.addr_proto,			\
+	      got.is_frag, expected.is_frag,				\
+	      got.is_first_frag, expected.is_first_frag,		\
+	      got.is_encap, expected.is_encap,				\
+	      got.n_proto, expected.n_proto,				\
+	      got.sport, expected.sport,				\
+	      got.dport, expected.dport)
+
+static struct bpf_flow_keys pkt_v4_flow_keys = {
+	.nhoff = 0,
+	.thoff = sizeof(struct iphdr),
+	.addr_proto = ETH_P_IP,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = bpf_htons(ETH_P_IP),
+};
+
+static struct bpf_flow_keys pkt_v6_flow_keys = {
+	.nhoff = 0,
+	.thoff = sizeof(struct ipv6hdr),
+	.addr_proto = ETH_P_IPV6,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = bpf_htons(ETH_P_IPV6),
+};
+
+static void test_flow_dissector(void)
+{
+	struct bpf_flow_keys flow_keys;
+	struct bpf_object *obj;
+	__u32 duration, retval;
+	int err, prog_fd;
+	__u32 size;
+
+	err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector",
+			    "jmp_table", &prog_fd);
+	if (err) {
+		error_cnt++;
+		return;
+	}
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv4",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("ipv4_flow_keys", flow_keys, pkt_v4_flow_keys);
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_v6, sizeof(pkt_v6),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv6",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
+
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
 	srand(time(NULL));
@@ -1909,6 +1982,7 @@ int main(void)
 	test_reference_tracking();
 	test_queue_stack_map(QUEUE);
 	test_queue_stack_map(STACK);
+	test_flow_dissector();
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;