Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-05-31

The following pull-request contains BPF updates for your *net-next* tree.

Lots of exciting new features in the first PR of this developement cycle!
The main changes are:

1) misc verifier improvements, from Alexei.

2) bpftool can now convert btf to valid C, from Andrii.

3) verifier can insert explicit ZEXT insn when requested by 32-bit JITs.
   This feature greatly improves BPF speed on 32-bit architectures. From Jiong.

4) cgroups will now auto-detach bpf programs. This fixes issue of thousands
   bpf programs got stuck in dying cgroups. From Roman.

5) new bpf_send_signal() helper, from Yonghong.

6) cgroup inet skb programs can signal CN to the stack, from Lawrence.

7) miscellaneous cleanups, from many developers.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

tools/testing/selftests/bpf/.gitignore

@@ -22,6 +22,7 @@ test_lirc_mode2_user
 get_cgroup_id_user
 test_skb_cgroup_id_user
 test_socket_cookie
+test_cgroup_attach
 test_cgroup_storage
 test_select_reuseport
 test_flow_dissector
@@ -35,3 +36,6 @@ test_sysctl
 alu32
 libbpf.pc
 libbpf.so.*
+test_hashmap
+test_btf_dump
+xdping

tools/testing/selftests/bpf/Makefile

@@ -15,7 +15,9 @@ LLC		?= llc
 LLVM_OBJCOPY	?= llvm-objcopy
 LLVM_READELF	?= llvm-readelf
 BTF_PAHOLE	?= pahole
-CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include \
+	  -Dbpf_prog_load=bpf_prog_test_load \
+	  -Dbpf_load_program=bpf_test_load_program
 LDLIBS += -lcap -lelf -lrt -lpthread
 
 # Order correspond to 'make run_tests' order
@@ -23,7 +25,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
 	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
-	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl
+	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
+	test_btf_dump test_cgroup_attach xdping
 
 BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
 TEST_GEN_FILES = $(BPF_OBJ_FILES)
@@ -54,7 +57,8 @@ TEST_PROGS := test_kmod.sh \
 	test_lwt_ip_encap.sh \
 	test_tcp_check_syncookie.sh \
 	test_tc_tunnel.sh \
-	test_tc_edt.sh
+	test_tc_edt.sh \
+	test_xdping.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
@@ -78,9 +82,9 @@ $(OUTPUT)/test_maps: map_tests/*.c
 
 BPFOBJ := $(OUTPUT)/libbpf.a
 
-$(TEST_GEN_PROGS): $(BPFOBJ)
+$(TEST_GEN_PROGS): test_stub.o $(BPFOBJ)
 
-$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
+$(TEST_GEN_PROGS_EXTENDED): test_stub.o $(OUTPUT)/libbpf.a
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
@@ -96,6 +100,7 @@ $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
 $(OUTPUT)/test_netcnt: cgroup_helpers.c
 $(OUTPUT)/test_sock_fields: cgroup_helpers.c
 $(OUTPUT)/test_sysctl: cgroup_helpers.c
+$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c
 
 .PHONY: force
 
@@ -176,7 +181,7 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\
 						$(ALU32_BUILD_DIR)/urandom_read
 	$(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \
 		-o $(ALU32_BUILD_DIR)/test_progs_32 \
-		test_progs.c trace_helpers.c prog_tests/*.c \
+		test_progs.c test_stub.c trace_helpers.c prog_tests/*.c \
 		$(OUTPUT)/libbpf.a $(LDLIBS)
 
 $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H)

tools/testing/selftests/bpf/bpf_helpers.h

@@ -8,6 +8,14 @@
  */
 #define SEC(NAME) __attribute__((section(NAME), used))
 
+/* helper macro to print out debug messages */
+#define bpf_printk(fmt, ...)				\
+({							\
+	char ____fmt[] = fmt;				\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			 ##__VA_ARGS__);		\
+})
+
 /* helper functions called from eBPF programs written in C */
 static void *(*bpf_map_lookup_elem)(void *map, const void *key) =
 	(void *) BPF_FUNC_map_lookup_elem;
@@ -216,6 +224,7 @@ static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk,
 	(void *) BPF_FUNC_sk_storage_get;
 static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) =
 	(void *)BPF_FUNC_sk_storage_delete;
+static int (*bpf_send_signal)(unsigned sig) = (void *)BPF_FUNC_send_signal;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions

tools/testing/selftests/bpf/cgroup_helpers.c

@@ -33,6 +33,60 @@
 	snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
 		 CGROUP_WORK_DIR, path)
 
+/**
+ * enable_all_controllers() - Enable all available cgroup v2 controllers
+ *
+ * Enable all available cgroup v2 controllers in order to increase
+ * the code coverage.
+ *
+ * If successful, 0 is returned.
+ */
+int enable_all_controllers(char *cgroup_path)
+{
+	char path[PATH_MAX + 1];
+	char buf[PATH_MAX];
+	char *c, *c2;
+	int fd, cfd;
+	size_t len;
+
+	snprintf(path, sizeof(path), "%s/cgroup.controllers", cgroup_path);
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		log_err("Opening cgroup.controllers: %s", path);
+		return 1;
+	}
+
+	len = read(fd, buf, sizeof(buf) - 1);
+	if (len < 0) {
+		close(fd);
+		log_err("Reading cgroup.controllers: %s", path);
+		return 1;
+	}
+	buf[len] = 0;
+	close(fd);
+
+	/* No controllers available? We're probably on cgroup v1. */
+	if (len == 0)
+		return 0;
+
+	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);
+	cfd = open(path, O_RDWR);
+	if (cfd < 0) {
+		log_err("Opening cgroup.subtree_control: %s", path);
+		return 1;
+	}
+
+	for (c = strtok_r(buf, " ", &c2); c; c = strtok_r(NULL, " ", &c2)) {
+		if (dprintf(cfd, "+%s\n", c) <= 0) {
+			log_err("Enabling controller %s: %s", c, path);
+			close(cfd);
+			return 1;
+		}
+	}
+	close(cfd);
+	return 0;
+}
+
 /**
  * setup_cgroup_environment() - Setup the cgroup environment
  *
@@ -71,6 +125,9 @@ int setup_cgroup_environment(void)
 		return 1;
 	}
 
+	if (enable_all_controllers(cgroup_workdir))
+		return 1;
+
 	return 0;
 }
 

tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c

@@ -12,7 +12,7 @@ static int libbpf_debug_print(enum libbpf_print_level level,
 	return vfprintf(stderr, "%s", args);
 }
 
-static int check_load(const char *file)
+static int check_load(const char *file, enum bpf_prog_type type)
 {
 	struct bpf_prog_load_attr attr;
 	struct bpf_object *obj = NULL;
@@ -20,8 +20,9 @@ static int check_load(const char *file)
 
 	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
 	attr.file = file;
-	attr.prog_type = BPF_PROG_TYPE_SCHED_CLS;
+	attr.prog_type = type;
 	attr.log_level = 4;
+	attr.prog_flags = BPF_F_TEST_RND_HI32;
 	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
 	bpf_object__close(obj);
 	if (err)
@@ -31,19 +32,24 @@ static int check_load(const char *file)
 
 void test_bpf_verif_scale(void)
 {
-	const char *file1 = "./test_verif_scale1.o";
-	const char *file2 = "./test_verif_scale2.o";
-	const char *file3 = "./test_verif_scale3.o";
-	int err;
+	const char *scale[] = {
+		"./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o"
+	};
+	const char *pyperf[] = {
+		"./pyperf50.o",	"./pyperf100.o", "./pyperf180.o"
+	};
+	int err, i;
 
 	if (verifier_stats)
 		libbpf_set_print(libbpf_debug_print);
 
-	err = check_load(file1);
-	err |= check_load(file2);
-	err |= check_load(file3);
-	if (!err)
-		printf("test_verif_scale:OK\n");
-	else
-		printf("test_verif_scale:FAIL\n");
+	for (i = 0; i < ARRAY_SIZE(scale); i++) {
+		err = check_load(scale[i], BPF_PROG_TYPE_SCHED_CLS);
+		printf("test_scale:%s:%s\n", scale[i], err ? "FAIL" : "OK");
+	}
+
+	for (i = 0; i < ARRAY_SIZE(pyperf); i++) {
+		err = check_load(pyperf[i], BPF_PROG_TYPE_RAW_TRACEPOINT);
+		printf("test_scale:%s:%s\n", pyperf[i], err ? "FAIL" : "OK");
+	}
 }

tools/testing/selftests/bpf/prog_tests/send_signal.c

@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+static volatile int sigusr1_received = 0;
+
+static void sigusr1_handler(int signum)
+{
+	sigusr1_received++;
+}
+
+static int test_send_signal_common(struct perf_event_attr *attr,
+				    int prog_type,
+				    const char *test_name)
+{
+	int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd;
+	const char *file = "./test_send_signal_kern.o";
+	struct bpf_object *obj = NULL;
+	int pipe_c2p[2], pipe_p2c[2];
+	__u32 key = 0, duration = 0;
+	char buf[256];
+	pid_t pid;
+	__u64 val;
+
+	if (CHECK(pipe(pipe_c2p), test_name,
+		  "pipe pipe_c2p error: %s\n", strerror(errno)))
+		goto no_fork_done;
+
+	if (CHECK(pipe(pipe_p2c), test_name,
+		  "pipe pipe_p2c error: %s\n", strerror(errno))) {
+		close(pipe_c2p[0]);
+		close(pipe_c2p[1]);
+		goto no_fork_done;
+	}
+
+	pid = fork();
+	if (CHECK(pid < 0, test_name, "fork error: %s\n", strerror(errno))) {
+		close(pipe_c2p[0]);
+		close(pipe_c2p[1]);
+		close(pipe_p2c[0]);
+		close(pipe_p2c[1]);
+		goto no_fork_done;
+	}
+
+	if (pid == 0) {
+		/* install signal handler and notify parent */
+		signal(SIGUSR1, sigusr1_handler);
+
+		close(pipe_c2p[0]); /* close read */
+		close(pipe_p2c[1]); /* close write */
+
+		/* notify parent signal handler is installed */
+		write(pipe_c2p[1], buf, 1);
+
+		/* make sure parent enabled bpf program to send_signal */
+		read(pipe_p2c[0], buf, 1);
+
+		/* wait a little for signal handler */
+		sleep(1);
+
+		if (sigusr1_received)
+			write(pipe_c2p[1], "2", 1);
+		else
+			write(pipe_c2p[1], "0", 1);
+
+		/* wait for parent notification and exit */
+		read(pipe_p2c[0], buf, 1);
+
+		close(pipe_c2p[1]);
+		close(pipe_p2c[0]);
+		exit(0);
+	}
+
+	close(pipe_c2p[1]); /* close write */
+	close(pipe_p2c[0]); /* close read */
+
+	err = bpf_prog_load(file, prog_type, &obj, &prog_fd);
+	if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n",
+		  strerror(errno)))
+		goto prog_load_failure;
+
+	pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
+			 -1 /* group id */, 0 /* flags */);
+	if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
+		  strerror(errno))) {
+		err = -1;
+		goto close_prog;
+	}
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n",
+		  strerror(errno)))
+		goto disable_pmu;
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
+	if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n",
+		  strerror(errno)))
+		goto disable_pmu;
+
+	err = -1;
+	info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map");
+	if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map"))
+		goto disable_pmu;
+
+	status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map");
+	if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map"))
+		goto disable_pmu;
+
+	/* wait until child signal handler installed */
+	read(pipe_c2p[0], buf, 1);
+
+	/* trigger the bpf send_signal */
+	key = 0;
+	val = (((__u64)(SIGUSR1)) << 32) | pid;
+	bpf_map_update_elem(info_map_fd, &key, &val, 0);
+
+	/* notify child that bpf program can send_signal now */
+	write(pipe_p2c[1], buf, 1);
+
+	/* wait for result */
+	err = read(pipe_c2p[0], buf, 1);
+	if (CHECK(err < 0, test_name, "reading pipe error: %s\n", strerror(errno)))
+		goto disable_pmu;
+	if (CHECK(err == 0, test_name, "reading pipe error: size 0\n")) {
+		err = -1;
+		goto disable_pmu;
+	}
+
+	err = CHECK(buf[0] != '2', test_name, "incorrect result\n");
+
+	/* notify child safe to exit */
+	write(pipe_p2c[1], buf, 1);
+
+disable_pmu:
+	close(pmu_fd);
+close_prog:
+	bpf_object__close(obj);
+prog_load_failure:
+	close(pipe_c2p[0]);
+	close(pipe_p2c[1]);
+	wait(NULL);
+no_fork_done:
+	return err;
+}
+
+static int test_send_signal_tracepoint(void)
+{
+	const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id";
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_TRACEPOINT,
+		.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN,
+		.sample_period = 1,
+		.wakeup_events = 1,
+	};
+	__u32 duration = 0;
+	int bytes, efd;
+	char buf[256];
+
+	efd = open(id_path, O_RDONLY, 0);
+	if (CHECK(efd < 0, "tracepoint",
+		  "open syscalls/sys_enter_nanosleep/id failure: %s\n",
+		  strerror(errno)))
+		return -1;
+
+	bytes = read(efd, buf, sizeof(buf));
+	close(efd);
+	if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint",
+		  "read syscalls/sys_enter_nanosleep/id failure: %s\n",
+		  strerror(errno)))
+		return -1;
+
+	attr.config = strtol(buf, NULL, 0);
+
+	return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
+}
+
+static int test_send_signal_nmi(void)
+{
+	struct perf_event_attr attr = {
+		.sample_freq = 50,
+		.freq = 1,
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+	};
+
+	return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, "perf_event");
+}
+
+void test_send_signal(void)
+{
+	int ret = 0;
+
+	ret |= test_send_signal_tracepoint();
+	ret |= test_send_signal_nmi();
+	if (!ret)
+		printf("test_send_signal:OK\n");
+	else
+		printf("test_send_signal:FAIL\n");
+}

tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c

@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C dumper tests for bitfield.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#include <stdbool.h>
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct bitfields_only_mixed_types {
+ *	int a: 3;
+ *	long int b: 2;
+ *	_Bool c: 1;
+ *	enum {
+ *		A = 0,
+ *		B = 1,
+ *	} d: 1;
+ *	short e: 5;
+ *	int: 20;
+ *	unsigned int f: 30;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct bitfields_only_mixed_types {
+	int a: 3;
+	long int b: 2;
+	bool c: 1; /* it's really a _Bool type */
+	enum {
+		A, /* A = 0, dumper is very explicit */
+		B, /* B = 1, same */
+	} d: 1;
+	short e: 5;
+	/* 20-bit padding here */
+	unsigned f: 30; /* this gets aligned on 4-byte boundary */
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct bitfield_mixed_with_others {
+ *	char: 4;
+ *	int a: 4;
+ *	short b;
+ *	long int c;
+ *	long int d: 8;
+ *	int e;
+ *	int f;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+struct bitfield_mixed_with_others {
+	long: 4; /* char is enough as a backing field */
+	int a: 4;
+	/* 8-bit implicit padding */
+	short b; /* combined with previous bitfield */
+	/* 4 more bytes of implicit padding */
+	long c;
+	long d: 8;
+	/* 24 bits implicit padding */
+	int e; /* combined with previous bitfield */
+	int f;
+	/* 4 bytes of padding */
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct bitfield_flushed {
+ *	int a: 4;
+ *	long: 60;
+ *	long int b: 16;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+struct bitfield_flushed {
+	int a: 4;
+	long: 0; /* flush until next natural alignment boundary */
+	long b: 16;
+};
+
+int f(struct {
+	struct bitfields_only_mixed_types _1;
+	struct bitfield_mixed_with_others _2;
+	struct bitfield_flushed _3;
+} *_)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c

@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C dumper test for multi-dimensional array output.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+typedef int arr_t[2];
+
+typedef int multiarr_t[3][4][5];
+
+typedef int *ptr_arr_t[6];
+
+typedef int *ptr_multiarr_t[7][8][9][10];
+
+typedef int * (*fn_ptr_arr_t[11])();
+
+typedef int * (*fn_ptr_multiarr_t[12][13])();
+
+struct root_struct {
+	arr_t _1;
+	multiarr_t _2;
+	ptr_arr_t _3;
+	ptr_multiarr_t _4;
+	fn_ptr_arr_t _5;
+	fn_ptr_multiarr_t _6;
+};
+
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+int f(struct root_struct *s)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/btf_dump_test_case_namespacing.c

@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C dumper test validating no name versioning happens between
+ * independent C namespaces (struct/union/enum vs typedef/enum values).
+ *
+ * Copyright (c) 2019 Facebook
+ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct S {
+	int S;
+	int U;
+};
+
+typedef struct S S;
+
+union U {
+	int S;
+	int U;
+};
+
+typedef union U U;
+
+enum E {
+	V = 0,
+};
+
+typedef enum E E;
+
+struct A {};
+
+union B {};
+
+enum C {
+	A = 1,
+	B = 2,
+	C = 3,
+};
+
+struct X {};
+
+union Y {};
+
+enum Z;
+
+typedef int X;
+
+typedef int Y;
+
+typedef int Z;
+
+/*------ END-EXPECTED-OUTPUT ------ */
+
+int f(struct {
+	struct S _1;
+	S _2;
+	union U _3;
+	U _4;
+	enum E _5;
+	E _6;
+	struct A a;
+	union B b;
+	enum C c;
+	struct X x;
+	union Y y;
+	enum Z *z;
+	X xx;
+	Y yy;
+	Z zz;
+} *_)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/btf_dump_test_case_ordering.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C dumper test for topological sorting of dependent structs.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct s1 {};
+
+struct s3;
+
+struct s4;
+
+struct s2 {
+	struct s2 *s2;
+	struct s3 *s3;
+	struct s4 *s4;
+};
+
+struct s3 {
+	struct s1 s1;
+	struct s2 s2;
+};
+
+struct s4 {
+	struct s1 s1;
+	struct s3 s3;
+};
+
+struct list_head {
+	struct list_head *next;
+	struct list_head *prev;
+};
+
+struct hlist_node {
+	struct hlist_node *next;
+	struct hlist_node **pprev;
+};
+
+struct hlist_head {
+	struct hlist_node *first;
+};
+
+struct callback_head {
+	struct callback_head *next;
+	void (*func)(struct callback_head *);
+};
+
+struct root_struct {
+	struct s4 s4;
+	struct list_head l;
+	struct hlist_node n;
+	struct hlist_head h;
+	struct callback_head cb;
+};
+
+/*------ END-EXPECTED-OUTPUT ------ */
+
+int f(struct root_struct *root)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c

@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C dumper tests for struct packing determination.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct packed_trailing_space {
+	int a;
+	short b;
+} __attribute__((packed));
+
+struct non_packed_trailing_space {
+	int a;
+	short b;
+};
+
+struct packed_fields {
+	short a;
+	int b;
+} __attribute__((packed));
+
+struct non_packed_fields {
+	short a;
+	int b;
+};
+
+struct nested_packed {
+	char: 4;
+	int a: 4;
+	long int b;
+	struct {
+		char c;
+		int d;
+	} __attribute__((packed)) e;
+} __attribute__((packed));
+
+union union_is_never_packed {
+	int a: 4;
+	char b;
+	char c: 1;
+};
+
+union union_does_not_need_packing {
+	struct {
+		long int a;
+		int b;
+	} __attribute__((packed));
+	int c;
+};
+
+union jump_code_union {
+	char code[5];
+	struct {
+		char jump;
+		int offset;
+	} __attribute__((packed));
+};
+
+/*------ END-EXPECTED-OUTPUT ------ */
+
+int f(struct {
+	struct packed_trailing_space _1;
+	struct non_packed_trailing_space _2;
+	struct packed_fields _3;
+	struct non_packed_fields _4;
+	struct nested_packed _5;
+	union union_is_never_packed _6;
+	union union_does_not_need_packing _7;
+	union jump_code_union _8;
+} *_)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c

@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C dumper tests for implicit and explicit padding between fields and
+ * at the end of a struct.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct padded_implicitly {
+	int a;
+	long int b;
+	char c;
+};
+
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct padded_explicitly {
+ *	int a;
+ *	int: 32;
+ *	int b;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct padded_explicitly {
+	int a;
+	int: 1; /* algo will explicitly pad with full 32 bits here */
+	int b;
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct padded_a_lot {
+ *	int a;
+ *	long: 32;
+ *	long: 64;
+ *	long: 64;
+ *	int b;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct padded_a_lot {
+	int a;
+	/* 32 bit of implicit padding here, which algo will make explicit */
+	long: 64;
+	long: 64;
+	int b;
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct padded_cache_line {
+ *	int a;
+ *	long: 32;
+ *	long: 64;
+ *	long: 64;
+ *	long: 64;
+ *	int b;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct padded_cache_line {
+	int a;
+	int b __attribute__((aligned(32)));
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct zone_padding {
+ *	char x[0];
+ *};
+ *
+ *struct zone {
+ *	int a;
+ *	short b;
+ *	short: 16;
+ *	struct zone_padding __pad__;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct zone_padding {
+	char x[0];
+} __attribute__((__aligned__(8)));
+
+struct zone {
+	int a;
+	short b;
+	short: 16;
+	struct zone_padding __pad__;
+};
+
+int f(struct {
+	struct padded_implicitly _1;
+	struct padded_explicitly _2;
+	struct padded_a_lot _3;
+	struct padded_cache_line _4;
+	struct zone _5;
+} *_)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c

@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * BTF-to-C dumper test for majority of C syntax quirks.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+enum e1 {
+	A = 0,
+	B = 1,
+};
+
+enum e2 {
+	C = 100,
+	D = -100,
+	E = 0,
+};
+
+typedef enum e2 e2_t;
+
+typedef enum {
+	F = 0,
+	G = 1,
+	H = 2,
+} e3_t;
+
+typedef int int_t;
+
+typedef volatile const int * volatile const crazy_ptr_t;
+
+typedef int *****we_need_to_go_deeper_ptr_t;
+
+typedef volatile const we_need_to_go_deeper_ptr_t * restrict * volatile * const * restrict volatile * restrict const * volatile const * restrict volatile const how_about_this_ptr_t;
+
+typedef int *ptr_arr_t[10];
+
+typedef void (*fn_ptr1_t)(int);
+
+typedef void (*printf_fn_t)(const char *, ...);
+
+/* ------ END-EXPECTED-OUTPUT ------ */
+/*
+ * While previous function pointers are pretty trivial (C-syntax-level
+ * trivial), the following are deciphered here for future generations:
+ *
+ * - `fn_ptr2_t`: function, taking anonymous struct as a first arg and pointer
+ *   to a function, that takes int and returns int, as a second arg; returning
+ *   a pointer to a const pointer to a char. Equivalent to:
+ *	typedef struct { int a; } s_t;
+ *	typedef int (*fn_t)(int);
+ *	typedef char * const * (*fn_ptr2_t)(s_t, fn_t);
+ *
+ * - `fn_complext_t`: pointer to a function returning struct and accepting
+ *   union and struct. All structs and enum are anonymous and defined inline.
+ *
+ * - `signal_t: pointer to a function accepting a pointer to a function as an
+ *   argument and returning pointer to a function as a result. Sane equivalent:
+ *	typedef void (*signal_handler_t)(int);
+ *	typedef signal_handler_t (*signal_ptr_t)(int, signal_handler_t);
+ *
+ * - fn_ptr_arr1_t: array of pointers to a function accepting pointer to
+ *   a pointer to an int and returning pointer to a char. Easy.
+ *
+ * - fn_ptr_arr2_t: array of const pointers to a function taking no arguments
+ *   and returning a const pointer to a function, that takes pointer to a
+ *   `int -> char *` function and returns pointer to a char. Equivalent:
+ *   typedef char * (*fn_input_t)(int);
+ *   typedef char * (*fn_output_outer_t)(fn_input_t);
+ *   typedef const fn_output_outer_t (* fn_output_inner_t)();
+ *   typedef const fn_output_inner_t fn_ptr_arr2_t[5];
+ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+typedef char * const * (*fn_ptr2_t)(struct {
+	int a;
+}, int (*)(int));
+
+typedef struct {
+	int a;
+	void (*b)(int, struct {
+		int c;
+	}, union {
+		char d;
+		int e[5];
+	});
+} (*fn_complex_t)(union {
+	void *f;
+	char g[16];
+}, struct {
+	int h;
+});
+
+typedef void (* (*signal_t)(int, void (*)(int)))(int);
+
+typedef char * (*fn_ptr_arr1_t[10])(int **);
+
+typedef char * (* const (* const fn_ptr_arr2_t[5])())(char * (*)(int));
+
+struct struct_w_typedefs {
+	int_t a;
+	crazy_ptr_t b;
+	we_need_to_go_deeper_ptr_t c;
+	how_about_this_ptr_t d;
+	ptr_arr_t e;
+	fn_ptr1_t f;
+	printf_fn_t g;
+	fn_ptr2_t h;
+	fn_complex_t i;
+	signal_t j;
+	fn_ptr_arr1_t k;
+	fn_ptr_arr2_t l;
+};
+
+typedef struct {
+	int x;
+	int y;
+	int z;
+} anon_struct_t;
+
+struct struct_fwd;
+
+typedef struct struct_fwd struct_fwd_t;
+
+typedef struct struct_fwd *struct_fwd_ptr_t;
+
+union union_fwd;
+
+typedef union union_fwd union_fwd_t;
+
+typedef union union_fwd *union_fwd_ptr_t;
+
+struct struct_empty {};
+
+struct struct_simple {
+	int a;
+	char b;
+	const int_t *p;
+	struct struct_empty s;
+	enum e2 e;
+	enum {
+		ANON_VAL1 = 1,
+		ANON_VAL2 = 2,
+	} f;
+	int arr1[13];
+	enum e2 arr2[5];
+};
+
+union union_empty {};
+
+union union_simple {
+	void *ptr;
+	int num;
+	int_t num2;
+	union union_empty u;
+};
+
+struct struct_in_struct {
+	struct struct_simple simple;
+	union union_simple also_simple;
+	struct {
+		int a;
+	} not_so_hard_as_well;
+	union {
+		int b;
+		int c;
+	} anon_union_is_good;
+	struct {
+		int d;
+		int e;
+	};
+	union {
+		int f;
+		int g;
+	};
+};
+
+struct struct_with_embedded_stuff {
+	int a;
+	struct {
+		int b;
+		struct {
+			struct struct_with_embedded_stuff *c;
+			const char *d;
+		} e;
+		union {
+			volatile long int f;
+			void * restrict g;
+		};
+	};
+	union {
+		const int_t *h;
+		void (*i)(char, int, void *);
+	} j;
+	enum {
+		K = 100,
+		L = 200,
+	} m;
+	char n[16];
+	struct {
+		char o;
+		int p;
+		void (*q)(int);
+	} r[5];
+	struct struct_in_struct s[10];
+	int t[11];
+};
+
+struct root_struct {
+	enum e1 _1;
+	enum e2 _2;
+	e2_t _2_1;
+	e3_t _2_2;
+	struct struct_w_typedefs _3;
+	anon_struct_t _7;
+	struct struct_fwd *_8;
+	struct_fwd_t *_9;
+	struct_fwd_ptr_t _10;
+	union union_fwd *_11;
+	union_fwd_t *_12;
+	union_fwd_ptr_t _13;
+	struct struct_with_embedded_stuff _14;
+};
+
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+int f(struct root_struct *s)
+{
+	return 0;
+}

tools/testing/selftests/bpf/progs/pyperf.h

@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <stdint.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define FUNCTION_NAME_LEN 64
+#define FILE_NAME_LEN 128
+#define TASK_COMM_LEN 16
+
+typedef struct {
+	int PyThreadState_frame;
+	int PyThreadState_thread;
+	int PyFrameObject_back;
+	int PyFrameObject_code;
+	int PyFrameObject_lineno;
+	int PyCodeObject_filename;
+	int PyCodeObject_name;
+	int String_data;
+	int String_size;
+} OffsetConfig;
+
+typedef struct {
+	uintptr_t current_state_addr;
+	uintptr_t tls_key_addr;
+	OffsetConfig offsets;
+	bool use_tls;
+} PidData;
+
+typedef struct {
+	uint32_t success;
+} Stats;
+
+typedef struct {
+	char name[FUNCTION_NAME_LEN];
+	char file[FILE_NAME_LEN];
+} Symbol;
+
+typedef struct {
+	uint32_t pid;
+	uint32_t tid;
+	char comm[TASK_COMM_LEN];
+	int32_t kernel_stack_id;
+	int32_t user_stack_id;
+	bool thread_current;
+	bool pthread_match;
+	bool stack_complete;
+	int16_t stack_len;
+	int32_t stack[STACK_MAX_LEN];
+
+	int has_meta;
+	int metadata;
+	char dummy_safeguard;
+} Event;
+
+
+struct bpf_elf_map {
+	__u32 type;
+	__u32 size_key;
+	__u32 size_value;
+	__u32 max_elem;
+	__u32 flags;
+};
+
+typedef int pid_t;
+
+typedef struct {
+	void* f_back; // PyFrameObject.f_back, previous frame
+	void* f_code; // PyFrameObject.f_code, pointer to PyCodeObject
+	void* co_filename; // PyCodeObject.co_filename
+	void* co_name; // PyCodeObject.co_name
+} FrameData;
+
+static inline __attribute__((__always_inline__)) void*
+get_thread_state(void* tls_base, PidData* pidData)
+{
+	void* thread_state;
+	int key;
+
+	bpf_probe_read(&key, sizeof(key), (void*)(long)pidData->tls_key_addr);
+	bpf_probe_read(&thread_state, sizeof(thread_state),
+		       tls_base + 0x310 + key * 0x10 + 0x08);
+	return thread_state;
+}
+
+static inline __attribute__((__always_inline__)) bool
+get_frame_data(void* frame_ptr, PidData* pidData, FrameData* frame, Symbol* symbol)
+{
+	// read data from PyFrameObject
+	bpf_probe_read(&frame->f_back,
+		       sizeof(frame->f_back),
+		       frame_ptr + pidData->offsets.PyFrameObject_back);
+	bpf_probe_read(&frame->f_code,
+		       sizeof(frame->f_code),
+		       frame_ptr + pidData->offsets.PyFrameObject_code);
+
+	// read data from PyCodeObject
+	if (!frame->f_code)
+		return false;
+	bpf_probe_read(&frame->co_filename,
+		       sizeof(frame->co_filename),
+		       frame->f_code + pidData->offsets.PyCodeObject_filename);
+	bpf_probe_read(&frame->co_name,
+		       sizeof(frame->co_name),
+		       frame->f_code + pidData->offsets.PyCodeObject_name);
+	// read actual names into symbol
+	if (frame->co_filename)
+		bpf_probe_read_str(&symbol->file,
+				   sizeof(symbol->file),
+				   frame->co_filename + pidData->offsets.String_data);
+	if (frame->co_name)
+		bpf_probe_read_str(&symbol->name,
+				   sizeof(symbol->name),
+				   frame->co_name + pidData->offsets.String_data);
+	return true;
+}
+
+struct bpf_elf_map SEC("maps") pidmap = {
+	.type = BPF_MAP_TYPE_HASH,
+	.size_key = sizeof(int),
+	.size_value = sizeof(PidData),
+	.max_elem = 1,
+};
+
+struct bpf_elf_map SEC("maps") eventmap = {
+	.type = BPF_MAP_TYPE_HASH,
+	.size_key = sizeof(int),
+	.size_value = sizeof(Event),
+	.max_elem = 1,
+};
+
+struct bpf_elf_map SEC("maps") symbolmap = {
+	.type = BPF_MAP_TYPE_HASH,
+	.size_key = sizeof(Symbol),
+	.size_value = sizeof(int),
+	.max_elem = 1,
+};
+
+struct bpf_elf_map SEC("maps") statsmap = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.size_key = sizeof(Stats),
+	.size_value = sizeof(int),
+	.max_elem = 1,
+};
+
+struct bpf_elf_map SEC("maps") perfmap = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.size_key = sizeof(int),
+	.size_value = sizeof(int),
+	.max_elem = 32,
+};
+
+struct bpf_elf_map SEC("maps") stackmap = {
+	.type = BPF_MAP_TYPE_STACK_TRACE,
+	.size_key = sizeof(int),
+	.size_value = sizeof(long long) * 127,
+	.max_elem = 1000,
+};
+
+static inline __attribute__((__always_inline__)) int __on_event(struct pt_regs *ctx)
+{
+	uint64_t pid_tgid = bpf_get_current_pid_tgid();
+	pid_t pid = (pid_t)(pid_tgid >> 32);
+	PidData* pidData = bpf_map_lookup_elem(&pidmap, &pid);
+	if (!pidData)
+		return 0;
+
+	int zero = 0;
+	Event* event = bpf_map_lookup_elem(&eventmap, &zero);
+	if (!event)
+		return 0;
+
+	event->pid = pid;
+
+	event->tid = (pid_t)pid_tgid;
+	bpf_get_current_comm(&event->comm, sizeof(event->comm));
+
+	event->user_stack_id = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK);
+	event->kernel_stack_id = bpf_get_stackid(ctx, &stackmap, 0);
+
+	void* thread_state_current = (void*)0;
+	bpf_probe_read(&thread_state_current,
+		       sizeof(thread_state_current),
+		       (void*)(long)pidData->current_state_addr);
+
+	struct task_struct* task = (struct task_struct*)bpf_get_current_task();
+	void* tls_base = (void*)task;
+
+	void* thread_state = pidData->use_tls ? get_thread_state(tls_base, pidData)
+		: thread_state_current;
+	event->thread_current = thread_state == thread_state_current;
+
+	if (pidData->use_tls) {
+		uint64_t pthread_created;
+		uint64_t pthread_self;
+		bpf_probe_read(&pthread_self, sizeof(pthread_self), tls_base + 0x10);
+
+		bpf_probe_read(&pthread_created,
+			       sizeof(pthread_created),
+			       thread_state + pidData->offsets.PyThreadState_thread);
+		event->pthread_match = pthread_created == pthread_self;
+	} else {
+		event->pthread_match = 1;
+	}
+
+	if (event->pthread_match || !pidData->use_tls) {
+		void* frame_ptr;
+		FrameData frame;
+		Symbol sym = {};
+		int cur_cpu = bpf_get_smp_processor_id();
+
+		bpf_probe_read(&frame_ptr,
+			       sizeof(frame_ptr),
+			       thread_state + pidData->offsets.PyThreadState_frame);
+
+		int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym);
+		if (symbol_counter == NULL)
+			return 0;
+#pragma unroll
+		/* Unwind python stack */
+		for (int i = 0; i < STACK_MAX_LEN; ++i) {
+			if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) {
+				int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu;
+				int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, &sym);
+				if (!symbol_id) {
+					bpf_map_update_elem(&symbolmap, &sym, &zero, 0);
+					symbol_id = bpf_map_lookup_elem(&symbolmap, &sym);
+					if (!symbol_id)
+						return 0;
+				}
+				if (*symbol_id == new_symbol_id)
+					(*symbol_counter)++;
+				event->stack[i] = *symbol_id;
+				event->stack_len = i + 1;
+				frame_ptr = frame.f_back;
+			}
+		}
+		event->stack_complete = frame_ptr == NULL;
+	} else {
+		event->stack_complete = 1;
+	}
+
+	Stats* stats = bpf_map_lookup_elem(&statsmap, &zero);
+	if (stats)
+		stats->success++;
+
+	event->has_meta = 0;
+	bpf_perf_event_output(ctx, &perfmap, 0, event, offsetof(Event, metadata));
+	return 0;
+}
+
+SEC("raw_tracepoint/kfree_skb")
+int on_event(struct pt_regs* ctx)
+{
+	int i, ret = 0;
+	ret |= __on_event(ctx);
+	ret |= __on_event(ctx);
+	ret |= __on_event(ctx);
+	ret |= __on_event(ctx);
+	ret |= __on_event(ctx);
+	return ret;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/pyperf100.c

@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#define STACK_MAX_LEN 100
+#include "pyperf.h"

tools/testing/selftests/bpf/progs/pyperf180.c

@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#define STACK_MAX_LEN 180
+#include "pyperf.h"

tools/testing/selftests/bpf/progs/pyperf50.c

@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#define STACK_MAX_LEN 50
+#include "pyperf.h"

tools/testing/selftests/bpf/progs/sockmap_parse_prog.c

@@ -5,13 +5,6 @@
 
 int _version SEC("version") = 1;
 
-#define bpf_printk(fmt, ...)					\
-({								\
-	       char ____fmt[] = fmt;				\
-	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
-				##__VA_ARGS__);			\
-})
-
 SEC("sk_skb1")
 int bpf_prog1(struct __sk_buff *skb)
 {

tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c

@@ -5,13 +5,6 @@
 
 int _version SEC("version") = 1;
 
-#define bpf_printk(fmt, ...)					\
-({								\
-	       char ____fmt[] = fmt;				\
-	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
-				##__VA_ARGS__);			\
-})
-
 SEC("sk_msg1")
 int bpf_prog1(struct sk_msg_md *msg)
 {

tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c

@@ -5,13 +5,6 @@
 
 int _version SEC("version") = 1;
 
-#define bpf_printk(fmt, ...)					\
-({								\
-	       char ____fmt[] = fmt;				\
-	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
-				##__VA_ARGS__);			\
-})
-
 struct bpf_map_def SEC("maps") sock_map_rx = {
 	.type = BPF_MAP_TYPE_SOCKMAP,
 	.key_size = sizeof(int),

tools/testing/selftests/bpf/progs/test_lwt_seg6local.c

@@ -6,13 +6,6 @@
 #include "bpf_helpers.h"
 #include "bpf_endian.h"
 
-#define bpf_printk(fmt, ...)				\
-({							\
-	char ____fmt[] = fmt;				\
-	bpf_trace_printk(____fmt, sizeof(____fmt),	\
-			##__VA_ARGS__);			\
-})
-
 /* Packet parsing state machine helpers. */
 #define cursor_advance(_cursor, _len) \
 	({ void *_tmp = _cursor; _cursor += _len; _tmp; })

tools/testing/selftests/bpf/progs/test_send_signal_kern.c

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") info_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = 1,
+};
+
+BPF_ANNOTATE_KV_PAIR(info_map, __u32, __u64);
+
+struct bpf_map_def SEC("maps") status_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = 1,
+};
+
+BPF_ANNOTATE_KV_PAIR(status_map, __u32, __u64);
+
+SEC("send_signal_demo")
+int bpf_send_signal_test(void *ctx)
+{
+	__u64 *info_val, *status_val;
+	__u32 key = 0, pid, sig;
+	int ret;
+
+	status_val = bpf_map_lookup_elem(&status_map, &key);
+	if (!status_val || *status_val != 0)
+		return 0;
+
+	info_val = bpf_map_lookup_elem(&info_map, &key);
+	if (!info_val || *info_val == 0)
+		return 0;
+
+	sig = *info_val >> 32;
+	pid = *info_val & 0xffffFFFF;
+
+	if ((bpf_get_current_pid_tgid() >> 32) == pid) {
+		ret = bpf_send_signal(sig);
+		if (ret == 0)
+			*status_val = 1;
+	}
+
+	return 0;
+}
+char __license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_xdp_noinline.c

@@ -15,13 +15,6 @@
 #include <linux/udp.h>
 #include "bpf_helpers.h"
 
-#define bpf_printk(fmt, ...)				\
-({							\
-	char ____fmt[] = fmt;				\
-	bpf_trace_printk(____fmt, sizeof(____fmt),	\
-			##__VA_ARGS__);			\
-})
-
 static __u32 rol32(__u32 word, unsigned int shift)
 {
 	return (word << shift) | (word >> ((-shift) & 31));

tools/testing/selftests/bpf/progs/xdping_kern.c

@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */
+
+#define KBUILD_MODNAME "foo"
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/icmp.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#include "xdping.h"
+
+struct bpf_map_def SEC("maps") ping_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct pinginfo),
+	.max_entries = 256,
+};
+
+static __always_inline void swap_src_dst_mac(void *data)
+{
+	unsigned short *p = data;
+	unsigned short dst[3];
+
+	dst[0] = p[0];
+	dst[1] = p[1];
+	dst[2] = p[2];
+	p[0] = p[3];
+	p[1] = p[4];
+	p[2] = p[5];
+	p[3] = dst[0];
+	p[4] = dst[1];
+	p[5] = dst[2];
+}
+
+static __always_inline __u16 csum_fold_helper(__wsum sum)
+{
+	sum = (sum & 0xffff) + (sum >> 16);
+	return ~((sum & 0xffff) + (sum >> 16));
+}
+
+static __always_inline __u16 ipv4_csum(void *data_start, int data_size)
+{
+	__wsum sum;
+
+	sum = bpf_csum_diff(0, 0, data_start, data_size, 0);
+	return csum_fold_helper(sum);
+}
+
+#define ICMP_ECHO_LEN		64
+
+static __always_inline int icmp_check(struct xdp_md *ctx, int type)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	struct icmphdr *icmph;
+	struct iphdr *iph;
+
+	if (data + sizeof(*eth) + sizeof(*iph) + ICMP_ECHO_LEN > data_end)
+		return XDP_PASS;
+
+	if (eth->h_proto != bpf_htons(ETH_P_IP))
+		return XDP_PASS;
+
+	iph = data + sizeof(*eth);
+
+	if (iph->protocol != IPPROTO_ICMP)
+		return XDP_PASS;
+
+	if (bpf_ntohs(iph->tot_len) - sizeof(*iph) != ICMP_ECHO_LEN)
+		return XDP_PASS;
+
+	icmph = data + sizeof(*eth) + sizeof(*iph);
+
+	if (icmph->type != type)
+		return XDP_PASS;
+
+	return XDP_TX;
+}
+
+SEC("xdpclient")
+int xdping_client(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct pinginfo *pinginfo = NULL;
+	struct ethhdr *eth = data;
+	struct icmphdr *icmph;
+	struct iphdr *iph;
+	__u64 recvtime;
+	__be32 raddr;
+	__be16 seq;
+	int ret;
+	__u8 i;
+
+	ret = icmp_check(ctx, ICMP_ECHOREPLY);
+
+	if (ret != XDP_TX)
+		return ret;
+
+	iph = data + sizeof(*eth);
+	icmph = data + sizeof(*eth) + sizeof(*iph);
+	raddr = iph->saddr;
+
+	/* Record time reply received. */
+	recvtime = bpf_ktime_get_ns();
+	pinginfo = bpf_map_lookup_elem(&ping_map, &raddr);
+	if (!pinginfo || pinginfo->seq != icmph->un.echo.sequence)
+		return XDP_PASS;
+
+	if (pinginfo->start) {
+#pragma clang loop unroll(full)
+		for (i = 0; i < XDPING_MAX_COUNT; i++) {
+			if (pinginfo->times[i] == 0)
+				break;
+		}
+		/* verifier is fussy here... */
+		if (i < XDPING_MAX_COUNT) {
+			pinginfo->times[i] = recvtime -
+					     pinginfo->start;
+			pinginfo->start = 0;
+			i++;
+		}
+		/* No more space for values? */
+		if (i == pinginfo->count || i == XDPING_MAX_COUNT)
+			return XDP_PASS;
+	}
+
+	/* Now convert reply back into echo request. */
+	swap_src_dst_mac(data);
+	iph->saddr = iph->daddr;
+	iph->daddr = raddr;
+	icmph->type = ICMP_ECHO;
+	seq = bpf_htons(bpf_ntohs(icmph->un.echo.sequence) + 1);
+	icmph->un.echo.sequence = seq;
+	icmph->checksum = 0;
+	icmph->checksum = ipv4_csum(icmph, ICMP_ECHO_LEN);
+
+	pinginfo->seq = seq;
+	pinginfo->start = bpf_ktime_get_ns();
+
+	return XDP_TX;
+}
+
+SEC("xdpserver")
+int xdping_server(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	struct icmphdr *icmph;
+	struct iphdr *iph;
+	__be32 raddr;
+	int ret;
+
+	ret = icmp_check(ctx, ICMP_ECHO);
+
+	if (ret != XDP_TX)
+		return ret;
+
+	iph = data + sizeof(*eth);
+	icmph = data + sizeof(*eth) + sizeof(*iph);
+	raddr = iph->saddr;
+
+	/* Now convert request into echo reply. */
+	swap_src_dst_mac(data);
+	iph->saddr = iph->daddr;
+	iph->daddr = raddr;
+	icmph->type = ICMP_ECHOREPLY;
+	icmph->checksum = 0;
+	icmph->checksum = ipv4_csum(icmph, ICMP_ECHO_LEN);
+
+	return XDP_TX;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_btf.c

@@ -4025,62 +4025,13 @@ static struct btf_file_test file_tests[] = {
 },
 };
 
-static int file_has_btf_elf(const char *fn, bool *has_btf_ext)
-{
-	Elf_Scn *scn = NULL;
-	GElf_Ehdr ehdr;
-	int ret = 0;
-	int elf_fd;
-	Elf *elf;
-
-	if (CHECK(elf_version(EV_CURRENT) == EV_NONE,
-		  "elf_version(EV_CURRENT) == EV_NONE"))
-		return -1;
-
-	elf_fd = open(fn, O_RDONLY);
-	if (CHECK(elf_fd == -1, "open(%s): errno:%d", fn, errno))
-		return -1;
-
-	elf = elf_begin(elf_fd, ELF_C_READ, NULL);
-	if (CHECK(!elf, "elf_begin(%s): %s", fn, elf_errmsg(elf_errno()))) {
-		ret = -1;
-		goto done;
-	}
-
-	if (CHECK(!gelf_getehdr(elf, &ehdr), "!gelf_getehdr(%s)", fn)) {
-		ret = -1;
-		goto done;
-	}
-
-	while ((scn = elf_nextscn(elf, scn))) {
-		const char *sh_name;
-		GElf_Shdr sh;
-
-		if (CHECK(gelf_getshdr(scn, &sh) != &sh,
-			  "file:%s gelf_getshdr != &sh", fn)) {
-			ret = -1;
-			goto done;
-		}
-
-		sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
-		if (!strcmp(sh_name, BTF_ELF_SEC))
-			ret = 1;
-		if (!strcmp(sh_name, BTF_EXT_ELF_SEC))
-			*has_btf_ext = true;
-	}
-
-done:
-	close(elf_fd);
-	elf_end(elf);
-	return ret;
-}
-
 static int do_test_file(unsigned int test_num)
 {
 	const struct btf_file_test *test = &file_tests[test_num - 1];
 	const char *expected_fnames[] = {"_dummy_tracepoint",
 					 "test_long_fname_1",
 					 "test_long_fname_2"};
+	struct btf_ext *btf_ext = NULL;
 	struct bpf_prog_info info = {};
 	struct bpf_object *obj = NULL;
 	struct bpf_func_info *finfo;
@@ -4095,15 +4046,19 @@ static int do_test_file(unsigned int test_num)
 	fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num,
 		test->file);
 
-	err = file_has_btf_elf(test->file, &has_btf_ext);
-	if (err == -1)
-		return err;
-
-	if (err == 0) {
-		fprintf(stderr, "SKIP. No ELF %s found", BTF_ELF_SEC);
-		skip_cnt++;
-		return 0;
+	btf = btf__parse_elf(test->file, &btf_ext);
+	if (IS_ERR(btf)) {
+		if (PTR_ERR(btf) == -ENOENT) {
+			fprintf(stderr, "SKIP. No ELF %s found", BTF_ELF_SEC);
+			skip_cnt++;
+			return 0;
+		}
+		return PTR_ERR(btf);
 	}
+	btf__free(btf);
+
+	has_btf_ext = btf_ext != NULL;
+	btf_ext__free(btf_ext);
 
 	obj = bpf_object__open(test->file);
 	if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))

tools/testing/selftests/bpf/test_btf_dump.c

@@ -0,0 +1,143 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <btf.h>
+
+#define CHECK(condition, format...) ({					\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__);	\
+		fprintf(stderr, format);				\
+	}								\
+	__ret;								\
+})
+
+void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+	vfprintf(ctx, fmt, args);
+}
+
+struct btf_dump_test_case {
+	const char *name;
+	struct btf_dump_opts opts;
+} btf_dump_test_cases[] = {
+	{.name = "btf_dump_test_case_syntax", .opts = {}},
+	{.name = "btf_dump_test_case_ordering", .opts = {}},
+	{.name = "btf_dump_test_case_padding", .opts = {}},
+	{.name = "btf_dump_test_case_packing", .opts = {}},
+	{.name = "btf_dump_test_case_bitfields", .opts = {}},
+	{.name = "btf_dump_test_case_multidim", .opts = {}},
+	{.name = "btf_dump_test_case_namespacing", .opts = {}},
+};
+
+static int btf_dump_all_types(const struct btf *btf,
+			      const struct btf_dump_opts *opts)
+{
+	size_t type_cnt = btf__get_nr_types(btf);
+	struct btf_dump *d;
+	int err = 0, id;
+
+	d = btf_dump__new(btf, NULL, opts, btf_dump_printf);
+	if (IS_ERR(d))
+		return PTR_ERR(d);
+
+	for (id = 1; id <= type_cnt; id++) {
+		err = btf_dump__dump_type(d, id);
+		if (err)
+			goto done;
+	}
+
+done:
+	btf_dump__free(d);
+	return err;
+}
+
+int test_btf_dump_case(int n, struct btf_dump_test_case *test_case)
+{
+	char test_file[256], out_file[256], diff_cmd[1024];
+	struct btf *btf = NULL;
+	int err = 0, fd = -1;
+	FILE *f = NULL;
+
+	fprintf(stderr, "Test case #%d (%s): ", n, test_case->name);
+
+	snprintf(test_file, sizeof(test_file), "%s.o", test_case->name);
+
+	btf = btf__parse_elf(test_file, NULL);
+	if (CHECK(IS_ERR(btf),
+	    "failed to load test BTF: %ld\n", PTR_ERR(btf))) {
+		err = -PTR_ERR(btf);
+		btf = NULL;
+		goto done;
+	}
+
+	snprintf(out_file, sizeof(out_file),
+		 "/tmp/%s.output.XXXXXX", test_case->name);
+	fd = mkstemp(out_file);
+	if (CHECK(fd < 0, "failed to create temp output file: %d\n", fd)) {
+		err = fd;
+		goto done;
+	}
+	f = fdopen(fd, "w");
+	if (CHECK(f == NULL, "failed to open temp output file: %s(%d)\n",
+		  strerror(errno), errno)) {
+		close(fd);
+		goto done;
+	}
+
+	test_case->opts.ctx = f;
+	err = btf_dump_all_types(btf, &test_case->opts);
+	fclose(f);
+	close(fd);
+	if (CHECK(err, "failure during C dumping: %d\n", err)) {
+		goto done;
+	}
+
+	snprintf(test_file, sizeof(test_file), "progs/%s.c", test_case->name);
+	/*
+	 * Diff test output and expected test output, contained between
+	 * START-EXPECTED-OUTPUT and END-EXPECTED-OUTPUT lines in test case.
+	 * For expected output lines, everything before '*' is stripped out.
+	 * Also lines containing comment start and comment end markers are
+	 * ignored. 
+	 */
+	snprintf(diff_cmd, sizeof(diff_cmd),
+		 "awk '/START-EXPECTED-OUTPUT/{out=1;next} "
+		 "/END-EXPECTED-OUTPUT/{out=0} "
+		 "/\\/\\*|\\*\\//{next} " /* ignore comment start/end lines */
+		 "out {sub(/^[ \\t]*\\*/, \"\"); print}' '%s' | diff -u - '%s'",
+		 test_file, out_file);
+	err = system(diff_cmd);
+	if (CHECK(err,
+		  "differing test output, output=%s, err=%d, diff cmd:\n%s\n",
+		  out_file, err, diff_cmd))
+		goto done;
+
+	remove(out_file);
+	fprintf(stderr, "OK\n");
+
+done:
+	btf__free(btf);
+	return err;
+}
+
+int main() {
+	int test_case_cnt, i, err, failed = 0;
+
+	test_case_cnt = sizeof(btf_dump_test_cases) /
+			sizeof(btf_dump_test_cases[0]);
+
+	for (i = 0; i < test_case_cnt; i++) {
+		err = test_btf_dump_case(i, &btf_dump_test_cases[i]);
+		if (err)
+			failed++;
+	}
+
+	fprintf(stderr, "%d tests succeeded, %d tests failed.\n",
+		test_case_cnt - failed, failed);
+
+	return failed;
+}

tools/testing/selftests/bpf/test_cgroup_attach.c

@@ -0,0 +1,571 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* eBPF example program:
+ *
+ * - Creates arraymap in kernel with 4 bytes keys and 8 byte values
+ *
+ * - Loads eBPF program
+ *
+ *   The eBPF program accesses the map passed in to store two pieces of
+ *   information. The number of invocations of the program, which maps
+ *   to the number of packets received, is stored to key 0. Key 1 is
+ *   incremented on each iteration by the number of bytes stored in
+ *   the skb. The program also stores the number of received bytes
+ *   in the cgroup storage.
+ *
+ * - Attaches the new program to a cgroup using BPF_PROG_ATTACH
+ *
+ * - Every second, reads map[0] and map[1] to see how many bytes and
+ *   packets were seen on any socket of tasks in the given cgroup.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <sys/resource.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <linux/filter.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+
+#include "bpf_util.h"
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+#define FOO		"/foo"
+#define BAR		"/foo/bar/"
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+#ifdef DEBUG
+#define debug(args...) printf(args)
+#else
+#define debug(args...)
+#endif
+
+static int prog_load(int verdict)
+{
+	int ret;
+	struct bpf_insn prog[] = {
+		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+
+	ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+
+	if (ret < 0) {
+		log_err("Loading program");
+		printf("Output from verifier:\n%s\n-------\n", bpf_log_buf);
+		return 0;
+	}
+	return ret;
+}
+
+static int test_foo_bar(void)
+{
+	int drop_prog, allow_prog, foo = 0, bar = 0, rc = 0;
+
+	allow_prog = prog_load(1);
+	if (!allow_prog)
+		goto err;
+
+	drop_prog = prog_load(0);
+	if (!drop_prog)
+		goto err;
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	/* Create cgroup /foo, get fd, and join it */
+	foo = create_and_get_cgroup(FOO);
+	if (foo < 0)
+		goto err;
+
+	if (join_cgroup(FOO))
+		goto err;
+
+	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE)) {
+		log_err("Attaching prog to /foo");
+		goto err;
+	}
+
+	debug("Attached DROP prog. This ping in cgroup /foo should fail...\n");
+	assert(system(PING_CMD) != 0);
+
+	/* Create cgroup /foo/bar, get fd, and join it */
+	bar = create_and_get_cgroup(BAR);
+	if (bar < 0)
+		goto err;
+
+	if (join_cgroup(BAR))
+		goto err;
+
+	debug("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n");
+	assert(system(PING_CMD) != 0);
+
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE)) {
+		log_err("Attaching prog to /foo/bar");
+		goto err;
+	}
+
+	debug("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n");
+	assert(system(PING_CMD) == 0);
+
+	if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching program from /foo/bar");
+		goto err;
+	}
+
+	debug("Detached PASS from /foo/bar while DROP is attached to /foo.\n"
+	       "This ping in cgroup /foo/bar should fail...\n");
+	assert(system(PING_CMD) != 0);
+
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE)) {
+		log_err("Attaching prog to /foo/bar");
+		goto err;
+	}
+
+	if (bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching program from /foo");
+		goto err;
+	}
+
+	debug("Attached PASS from /foo/bar and detached DROP from /foo.\n"
+	       "This ping in cgroup /foo/bar should pass...\n");
+	assert(system(PING_CMD) == 0);
+
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE)) {
+		log_err("Attaching prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+		errno = 0;
+		log_err("Unexpected success attaching prog to /foo/bar");
+		goto err;
+	}
+
+	if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching program from /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) {
+		errno = 0;
+		log_err("Unexpected success in double detach from /foo");
+		goto err;
+	}
+
+	if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching non-overridable prog to /foo");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+		errno = 0;
+		log_err("Unexpected success attaching non-overridable prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+			     BPF_F_ALLOW_OVERRIDE)) {
+		errno = 0;
+		log_err("Unexpected success attaching overridable prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS,
+			     BPF_F_ALLOW_OVERRIDE)) {
+		errno = 0;
+		log_err("Unexpected success attaching overridable prog to /foo");
+		goto err;
+	}
+
+	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching different non-overridable prog to /foo");
+		goto err;
+	}
+
+	goto out;
+
+err:
+	rc = 1;
+
+out:
+	close(foo);
+	close(bar);
+	cleanup_cgroup_environment();
+	if (!rc)
+		printf("#override:PASS\n");
+	else
+		printf("#override:FAIL\n");
+	return rc;
+}
+
+static int map_fd = -1;
+
+static int prog_load_cnt(int verdict, int val)
+{
+	int cgroup_storage_fd, percpu_cgroup_storage_fd;
+
+	if (map_fd < 0)
+		map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+	if (map_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+				sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	percpu_cgroup_storage_fd = bpf_create_map(
+		BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+		sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (percpu_cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	struct bpf_insn prog[] = {
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+
+		BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+		BPF_MOV64_IMM(BPF_REG_1, val),
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0),
+
+		BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
+		BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+
+		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+	int ret;
+
+	ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+
+	if (ret < 0) {
+		log_err("Loading program");
+		printf("Output from verifier:\n%s\n-------\n", bpf_log_buf);
+		return 0;
+	}
+	close(cgroup_storage_fd);
+	return ret;
+}
+
+
+static int test_multiprog(void)
+{
+	__u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
+	int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
+	int drop_prog, allow_prog[6] = {}, rc = 0;
+	unsigned long long value;
+	int i = 0;
+
+	for (i = 0; i < 6; i++) {
+		allow_prog[i] = prog_load_cnt(1, 1 << i);
+		if (!allow_prog[i])
+			goto err;
+	}
+	drop_prog = prog_load_cnt(0, 1);
+	if (!drop_prog)
+		goto err;
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cg1 = create_and_get_cgroup("/cg1");
+	if (cg1 < 0)
+		goto err;
+	cg2 = create_and_get_cgroup("/cg1/cg2");
+	if (cg2 < 0)
+		goto err;
+	cg3 = create_and_get_cgroup("/cg1/cg2/cg3");
+	if (cg3 < 0)
+		goto err;
+	cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4");
+	if (cg4 < 0)
+		goto err;
+	cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5");
+	if (cg5 < 0)
+		goto err;
+
+	if (join_cgroup("/cg1/cg2/cg3/cg4/cg5"))
+		goto err;
+
+	if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_MULTI)) {
+		log_err("Attaching prog to cg1");
+		goto err;
+	}
+	if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
+			     BPF_F_ALLOW_MULTI)) {
+		log_err("Unexpected success attaching the same prog to cg1");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_MULTI)) {
+		log_err("Attaching prog2 to cg1");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE)) {
+		log_err("Attaching prog to cg2");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_MULTI)) {
+		log_err("Attaching prog to cg3");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE)) {
+		log_err("Attaching prog to cg4");
+		goto err;
+	}
+	if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching prog to cg5");
+		goto err;
+	}
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 8 + 32);
+
+	/* query the number of effective progs in cg5 */
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      NULL, NULL, &prog_cnt) == 0);
+	assert(prog_cnt == 4);
+	/* retrieve prog_ids of effective progs in cg5 */
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 4);
+	assert(attach_flags == 0);
+	saved_prog_id = prog_ids[0];
+	/* check enospc handling */
+	prog_ids[0] = 0;
+	prog_cnt = 2;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == -1 &&
+	       errno == ENOSPC);
+	assert(prog_cnt == 4);
+	/* check that prog_ids are returned even when buffer is too small */
+	assert(prog_ids[0] == saved_prog_id);
+	/* retrieve prog_id of single attached prog in cg5 */
+	prog_ids[0] = 0;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
+			      NULL, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 1);
+	assert(prog_ids[0] == saved_prog_id);
+
+	/* detach bottom program and ping again */
+	if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching prog from cg5");
+		goto err;
+	}
+	value = 0;
+	assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 8 + 16);
+
+	/* detach 3rd from bottom program and ping again */
+	errno = 0;
+	if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Unexpected success on detach from cg3");
+		goto err;
+	}
+	if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching from cg3");
+		goto err;
+	}
+	value = 0;
+	assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 16);
+
+	/* detach 2nd from bottom program and ping again */
+	if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching prog from cg4");
+		goto err;
+	}
+	value = 0;
+	assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0);
+	assert(system(PING_CMD) == 0);
+	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
+	assert(value == 1 + 2 + 4);
+
+	prog_cnt = 4;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 3);
+	assert(attach_flags == 0);
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
+			      NULL, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 0);
+	goto out;
+err:
+	rc = 1;
+
+out:
+	for (i = 0; i < 6; i++)
+		if (allow_prog[i] > 0)
+			close(allow_prog[i]);
+	close(cg1);
+	close(cg2);
+	close(cg3);
+	close(cg4);
+	close(cg5);
+	cleanup_cgroup_environment();
+	if (!rc)
+		printf("#multi:PASS\n");
+	else
+		printf("#multi:FAIL\n");
+	return rc;
+}
+
+static int test_autodetach(void)
+{
+	__u32 prog_cnt = 4, attach_flags;
+	int allow_prog[2] = {0};
+	__u32 prog_ids[2] = {0};
+	int cg = 0, i, rc = -1;
+	void *ptr = NULL;
+	int attempts;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		allow_prog[i] = prog_load_cnt(1, 1 << i);
+		if (!allow_prog[i])
+			goto err;
+	}
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	/* create a cgroup, attach two programs and remember their ids */
+	cg = create_and_get_cgroup("/cg_autodetach");
+	if (cg < 0)
+		goto err;
+
+	if (join_cgroup("/cg_autodetach"))
+		goto err;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		if (bpf_prog_attach(allow_prog[i], cg, BPF_CGROUP_INET_EGRESS,
+				    BPF_F_ALLOW_MULTI)) {
+			log_err("Attaching prog[%d] to cg:egress", i);
+			goto err;
+		}
+	}
+
+	/* make sure that programs are attached and run some traffic */
+	assert(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags,
+			      prog_ids, &prog_cnt) == 0);
+	assert(system(PING_CMD) == 0);
+
+	/* allocate some memory (4Mb) to pin the original cgroup */
+	ptr = malloc(4 * (1 << 20));
+	if (!ptr)
+		goto err;
+
+	/* close programs and cgroup fd */
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		close(allow_prog[i]);
+		allow_prog[i] = 0;
+	}
+
+	close(cg);
+	cg = 0;
+
+	/* leave the cgroup and remove it. don't detach programs */
+	cleanup_cgroup_environment();
+
+	/* wait for the asynchronous auto-detachment.
+	 * wait for no more than 5 sec and give up.
+	 */
+	for (i = 0; i < ARRAY_SIZE(prog_ids); i++) {
+		for (attempts = 5; attempts >= 0; attempts--) {
+			int fd = bpf_prog_get_fd_by_id(prog_ids[i]);
+
+			if (fd < 0)
+				break;
+
+			/* don't leave the fd open */
+			close(fd);
+
+			if (!attempts)
+				goto err;
+
+			sleep(1);
+		}
+	}
+
+	rc = 0;
+err:
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (allow_prog[i] > 0)
+			close(allow_prog[i]);
+	if (cg)
+		close(cg);
+	free(ptr);
+	cleanup_cgroup_environment();
+	if (!rc)
+		printf("#autodetach:PASS\n");
+	else
+		printf("#autodetach:FAIL\n");
+	return rc;
+}
+
+int main(void)
+{
+	int (*tests[])(void) = {
+		test_foo_bar,
+		test_multiprog,
+		test_autodetach,
+	};
+	int errors = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++)
+		if (tests[i]())
+			errors++;
+
+	if (errors)
+		printf("test_cgroup_attach:FAIL\n");
+	else
+		printf("test_cgroup_attach:PASS\n");
+
+	return errors ? EXIT_FAILURE : EXIT_SUCCESS;
+}

tools/testing/selftests/bpf/test_hashmap.c

@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * Tests for libbpf's hashmap.
+ *
+ * Copyright (c) 2019 Facebook
+ */
+#include <stdio.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "hashmap.h"
+
+#define CHECK(condition, format...) ({					\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__);	\
+		fprintf(stderr, format);				\
+	}								\
+	__ret;								\
+})
+
+size_t hash_fn(const void *k, void *ctx)
+{
+	return (long)k;
+}
+
+bool equal_fn(const void *a, const void *b, void *ctx)
+{
+	return (long)a == (long)b;
+}
+
+static inline size_t next_pow_2(size_t n)
+{
+	size_t r = 1;
+
+	while (r < n)
+		r <<= 1;
+	return r;
+}
+
+static inline size_t exp_cap(size_t sz)
+{
+	size_t r = next_pow_2(sz);
+
+	if (sz * 4 / 3 > r)
+		r <<= 1;
+	return r;
+}
+
+#define ELEM_CNT 62
+
+int test_hashmap_generic(void)
+{
+	struct hashmap_entry *entry, *tmp;
+	int err, bkt, found_cnt, i;
+	long long found_msk;
+	struct hashmap *map;
+
+	fprintf(stderr, "%s: ", __func__);
+
+	map = hashmap__new(hash_fn, equal_fn, NULL);
+	if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
+		return 1;
+
+	for (i = 0; i < ELEM_CNT; i++) {
+		const void *oldk, *k = (const void *)(long)i;
+		void *oldv, *v = (void *)(long)(1024 + i);
+
+		err = hashmap__update(map, k, v, &oldk, &oldv);
+		if (CHECK(err != -ENOENT, "unexpected result: %d\n", err))
+			return 1;
+
+		if (i % 2) {
+			err = hashmap__add(map, k, v);
+		} else {
+			err = hashmap__set(map, k, v, &oldk, &oldv);
+			if (CHECK(oldk != NULL || oldv != NULL,
+				  "unexpected k/v: %p=%p\n", oldk, oldv))
+				return 1;
+		}
+
+		if (CHECK(err, "failed to add k/v %ld = %ld: %d\n",
+			       (long)k, (long)v, err))
+			return 1;
+
+		if (CHECK(!hashmap__find(map, k, &oldv),
+			  "failed to find key %ld\n", (long)k))
+			return 1;
+		if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv))
+			return 1;
+	}
+
+	if (CHECK(hashmap__size(map) != ELEM_CNT,
+		  "invalid map size: %zu\n", hashmap__size(map)))
+		return 1;
+	if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+		  "unexpected map capacity: %zu\n", hashmap__capacity(map)))
+		return 1;
+
+	found_msk = 0;
+	hashmap__for_each_entry(map, entry, bkt) {
+		long k = (long)entry->key;
+		long v = (long)entry->value;
+
+		found_msk |= 1ULL << k;
+		if (CHECK(v - k != 1024, "invalid k/v pair: %ld = %ld\n", k, v))
+			return 1;
+	}
+	if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1,
+		  "not all keys iterated: %llx\n", found_msk))
+		return 1;
+
+	for (i = 0; i < ELEM_CNT; i++) {
+		const void *oldk, *k = (const void *)(long)i;
+		void *oldv, *v = (void *)(long)(256 + i);
+
+		err = hashmap__add(map, k, v);
+		if (CHECK(err != -EEXIST, "unexpected add result: %d\n", err))
+			return 1;
+
+		if (i % 2)
+			err = hashmap__update(map, k, v, &oldk, &oldv);
+		else
+			err = hashmap__set(map, k, v, &oldk, &oldv);
+
+		if (CHECK(err, "failed to update k/v %ld = %ld: %d\n",
+			       (long)k, (long)v, err))
+			return 1;
+		if (CHECK(!hashmap__find(map, k, &oldv),
+			  "failed to find key %ld\n", (long)k))
+			return 1;
+		if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv))
+			return 1;
+	}
+
+	if (CHECK(hashmap__size(map) != ELEM_CNT,
+		  "invalid updated map size: %zu\n", hashmap__size(map)))
+		return 1;
+	if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+		  "unexpected map capacity: %zu\n", hashmap__capacity(map)))
+		return 1;
+
+	found_msk = 0;
+	hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
+		long k = (long)entry->key;
+		long v = (long)entry->value;
+
+		found_msk |= 1ULL << k;
+		if (CHECK(v - k != 256,
+			  "invalid updated k/v pair: %ld = %ld\n", k, v))
+			return 1;
+	}
+	if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1,
+		  "not all keys iterated after update: %llx\n", found_msk))
+		return 1;
+
+	found_cnt = 0;
+	hashmap__for_each_key_entry(map, entry, (void *)0) {
+		found_cnt++;
+	}
+	if (CHECK(!found_cnt, "didn't find any entries for key 0\n"))
+		return 1;
+
+	found_msk = 0;
+	found_cnt = 0;
+	hashmap__for_each_key_entry_safe(map, entry, tmp, (void *)0) {
+		const void *oldk, *k;
+		void *oldv, *v;
+
+		k = entry->key;
+		v = entry->value;
+
+		found_cnt++;
+		found_msk |= 1ULL << (long)k;
+
+		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv),
+			  "failed to delete k/v %ld = %ld\n",
+			  (long)k, (long)v))
+			return 1;
+		if (CHECK(oldk != k || oldv != v,
+			  "invalid deleted k/v: expected %ld = %ld, got %ld = %ld\n",
+			  (long)k, (long)v, (long)oldk, (long)oldv))
+			return 1;
+		if (CHECK(hashmap__delete(map, k, &oldk, &oldv),
+			  "unexpectedly deleted k/v %ld = %ld\n",
+			  (long)oldk, (long)oldv))
+			return 1;
+	}
+
+	if (CHECK(!found_cnt || !found_msk,
+		  "didn't delete any key entries\n"))
+		return 1;
+	if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt,
+		  "invalid updated map size (already deleted: %d): %zu\n",
+		  found_cnt, hashmap__size(map)))
+		return 1;
+	if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+		  "unexpected map capacity: %zu\n", hashmap__capacity(map)))
+		return 1;
+
+	hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
+		const void *oldk, *k;
+		void *oldv, *v;
+
+		k = entry->key;
+		v = entry->value;
+
+		found_cnt++;
+		found_msk |= 1ULL << (long)k;
+
+		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv),
+			  "failed to delete k/v %ld = %ld\n",
+			  (long)k, (long)v))
+			return 1;
+		if (CHECK(oldk != k || oldv != v,
+			  "invalid old k/v: expect %ld = %ld, got %ld = %ld\n",
+			  (long)k, (long)v, (long)oldk, (long)oldv))
+			return 1;
+		if (CHECK(hashmap__delete(map, k, &oldk, &oldv),
+			  "unexpectedly deleted k/v %ld = %ld\n",
+			  (long)k, (long)v))
+			return 1;
+	}
+
+	if (CHECK(found_cnt != ELEM_CNT || found_msk != (1ULL << ELEM_CNT) - 1,
+		  "not all keys were deleted: found_cnt:%d, found_msk:%llx\n",
+		  found_cnt, found_msk))
+		return 1;
+	if (CHECK(hashmap__size(map) != 0,
+		  "invalid updated map size (already deleted: %d): %zu\n",
+		  found_cnt, hashmap__size(map)))
+		return 1;
+
+	found_cnt = 0;
+	hashmap__for_each_entry(map, entry, bkt) {
+		CHECK(false, "unexpected map entries left: %ld = %ld\n",
+			     (long)entry->key, (long)entry->value);
+		return 1;
+	}
+
+	hashmap__free(map);
+	hashmap__for_each_entry(map, entry, bkt) {
+		CHECK(false, "unexpected map entries left: %ld = %ld\n",
+			     (long)entry->key, (long)entry->value);
+		return 1;
+	}
+
+	fprintf(stderr, "OK\n");
+	return 0;
+}
+
+size_t collision_hash_fn(const void *k, void *ctx)
+{
+	return 0;
+}
+
+int test_hashmap_multimap(void)
+{
+	void *k1 = (void *)0, *k2 = (void *)1;
+	struct hashmap_entry *entry;
+	struct hashmap *map;
+	long found_msk;
+	int err, bkt;
+
+	fprintf(stderr, "%s: ", __func__);
+
+	/* force collisions */
+	map = hashmap__new(collision_hash_fn, equal_fn, NULL);
+	if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
+		return 1;
+
+
+	/* set up multimap:
+	 * [0] -> 1, 2, 4;
+	 * [1] -> 8, 16, 32;
+	 */
+	err = hashmap__append(map, k1, (void *)1);
+	if (CHECK(err, "failed to add k/v: %d\n", err))
+		return 1;
+	err = hashmap__append(map, k1, (void *)2);
+	if (CHECK(err, "failed to add k/v: %d\n", err))
+		return 1;
+	err = hashmap__append(map, k1, (void *)4);
+	if (CHECK(err, "failed to add k/v: %d\n", err))
+		return 1;
+
+	err = hashmap__append(map, k2, (void *)8);
+	if (CHECK(err, "failed to add k/v: %d\n", err))
+		return 1;
+	err = hashmap__append(map, k2, (void *)16);
+	if (CHECK(err, "failed to add k/v: %d\n", err))
+		return 1;
+	err = hashmap__append(map, k2, (void *)32);
+	if (CHECK(err, "failed to add k/v: %d\n", err))
+		return 1;
+
+	if (CHECK(hashmap__size(map) != 6,
+		  "invalid map size: %zu\n", hashmap__size(map)))
+		return 1;
+
+	/* verify global iteration still works and sees all values */
+	found_msk = 0;
+	hashmap__for_each_entry(map, entry, bkt) {
+		found_msk |= (long)entry->value;
+	}
+	if (CHECK(found_msk != (1 << 6) - 1,
+		  "not all keys iterated: %lx\n", found_msk))
+		return 1;
+
+	/* iterate values for key 1 */
+	found_msk = 0;
+	hashmap__for_each_key_entry(map, entry, k1) {
+		found_msk |= (long)entry->value;
+	}
+	if (CHECK(found_msk != (1 | 2 | 4),
+		  "invalid k1 values: %lx\n", found_msk))
+		return 1;
+
+	/* iterate values for key 2 */
+	found_msk = 0;
+	hashmap__for_each_key_entry(map, entry, k2) {
+		found_msk |= (long)entry->value;
+	}
+	if (CHECK(found_msk != (8 | 16 | 32),
+		  "invalid k2 values: %lx\n", found_msk))
+		return 1;
+
+	fprintf(stderr, "OK\n");
+	return 0;
+}
+
+int test_hashmap_empty()
+{
+	struct hashmap_entry *entry;
+	int bkt;
+	struct hashmap *map;
+	void *k = (void *)0;
+
+	fprintf(stderr, "%s: ", __func__);
+
+	/* force collisions */
+	map = hashmap__new(hash_fn, equal_fn, NULL);
+	if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
+		return 1;
+
+	if (CHECK(hashmap__size(map) != 0,
+		  "invalid map size: %zu\n", hashmap__size(map)))
+		return 1;
+	if (CHECK(hashmap__capacity(map) != 0,
+		  "invalid map capacity: %zu\n", hashmap__capacity(map)))
+		return 1;
+	if (CHECK(hashmap__find(map, k, NULL), "unexpected find\n"))
+		return 1;
+	if (CHECK(hashmap__delete(map, k, NULL, NULL), "unexpected delete\n"))
+		return 1;
+
+	hashmap__for_each_entry(map, entry, bkt) {
+		CHECK(false, "unexpected iterated entry\n");
+		return 1;
+	}
+	hashmap__for_each_key_entry(map, entry, k) {
+		CHECK(false, "unexpected key entry\n");
+		return 1;
+	}
+
+	fprintf(stderr, "OK\n");
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	bool failed = false;
+
+	if (test_hashmap_generic())
+		failed = true;
+	if (test_hashmap_multimap())
+		failed = true;
+	if (test_hashmap_empty())
+		failed = true;
+
+	return failed;
+}

tools/testing/selftests/bpf/test_sock_addr.c

@@ -745,6 +745,7 @@ static int load_path(const struct sock_addr_test *test, const char *path)
 	attr.file = path;
 	attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 	attr.expected_attach_type = test->expected_attach_type;
+	attr.prog_flags = BPF_F_TEST_RND_HI32;
 
 	if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) {
 		if (test->expected_result != LOAD_REJECT)

tools/testing/selftests/bpf/test_sock_fields.c

@@ -414,6 +414,7 @@ int main(int argc, char **argv)
 	struct bpf_prog_load_attr attr = {
 		.file = "test_sock_fields_kern.o",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+		.prog_flags = BPF_F_TEST_RND_HI32,
 	};
 	int cgroup_fd, egress_fd, ingress_fd, err;
 	struct bpf_program *ingress_prog;

tools/testing/selftests/bpf/test_socket_cookie.c

@@ -148,6 +148,7 @@ static int run_test(int cgfd)
 	memset(&attr, 0, sizeof(attr));
 	attr.file = SOCKET_COOKIE_PROG;
 	attr.prog_type = BPF_PROG_TYPE_UNSPEC;
+	attr.prog_flags = BPF_F_TEST_RND_HI32;
 
 	err = bpf_prog_load_xattr(&attr, &pobj, &prog_fd);
 	if (err) {

tools/testing/selftests/bpf/test_sockmap_kern.h

@@ -28,13 +28,6 @@
  * are established and verdicts are decided.
  */
 
-#define bpf_printk(fmt, ...)					\
-({								\
-	       char ____fmt[] = fmt;				\
-	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
-				##__VA_ARGS__);			\
-})
-
 struct bpf_map_def SEC("maps") sock_map = {
 	.type = TEST_MAP_TYPE,
 	.key_size = sizeof(int),

tools/testing/selftests/bpf/test_stub.c

@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <string.h>
+
+int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
+		       struct bpf_object **pobj, int *prog_fd)
+{
+	struct bpf_prog_load_attr attr;
+
+	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+	attr.file = file;
+	attr.prog_type = type;
+	attr.expected_attach_type = 0;
+	attr.prog_flags = BPF_F_TEST_RND_HI32;
+
+	return bpf_prog_load_xattr(&attr, pobj, prog_fd);
+}
+
+int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+			  size_t insns_cnt, const char *license,
+			  __u32 kern_version, char *log_buf,
+		     size_t log_buf_sz)
+{
+	struct bpf_load_program_attr load_attr;
+
+	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
+	load_attr.prog_type = type;
+	load_attr.expected_attach_type = 0;
+	load_attr.name = NULL;
+	load_attr.insns = insns;
+	load_attr.insns_cnt = insns_cnt;
+	load_attr.license = license;
+	load_attr.kern_version = kern_version;
+	load_attr.prog_flags = BPF_F_TEST_RND_HI32;
+
+	return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz);
+}

tools/testing/selftests/bpf/test_tunnel.sh

@@ -696,30 +696,57 @@ check_err()
 
 bpf_tunnel_test()
 {
+	local errors=0
+
 	echo "Testing GRE tunnel..."
 	test_gre
+	errors=$(( $errors + $? ))
+
 	echo "Testing IP6GRE tunnel..."
 	test_ip6gre
+	errors=$(( $errors + $? ))
+
 	echo "Testing IP6GRETAP tunnel..."
 	test_ip6gretap
+	errors=$(( $errors + $? ))
+
 	echo "Testing ERSPAN tunnel..."
 	test_erspan v2
+	errors=$(( $errors + $? ))
+
 	echo "Testing IP6ERSPAN tunnel..."
 	test_ip6erspan v2
+	errors=$(( $errors + $? ))
+
 	echo "Testing VXLAN tunnel..."
 	test_vxlan
+	errors=$(( $errors + $? ))
+
 	echo "Testing IP6VXLAN tunnel..."
 	test_ip6vxlan
+	errors=$(( $errors + $? ))
+
 	echo "Testing GENEVE tunnel..."
 	test_geneve
+	errors=$(( $errors + $? ))
+
 	echo "Testing IP6GENEVE tunnel..."
 	test_ip6geneve
+	errors=$(( $errors + $? ))
+
 	echo "Testing IPIP tunnel..."
 	test_ipip
+	errors=$(( $errors + $? ))
+
 	echo "Testing IPIP6 tunnel..."
 	test_ipip6
+	errors=$(( $errors + $? ))
+
 	echo "Testing IPSec tunnel..."
 	test_xfrm_tunnel
+	errors=$(( $errors + $? ))
+
+	return $errors
 }
 
 trap cleanup 0 3 6
@@ -728,4 +755,9 @@ trap cleanup_exit 2 9
 cleanup
 bpf_tunnel_test
 
+if [ $? -ne 0 ]; then
+	echo -e "$(basename $0): ${RED}FAIL${NC}"
+	exit 1
+fi
+echo -e "$(basename $0): ${GREEN}PASS${NC}"
 exit 0

tools/testing/selftests/bpf/test_verifier.c

@@ -138,32 +138,36 @@ static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
 loop:
 	for (j = 0; j < PUSH_CNT; j++) {
 		insn[i++] = BPF_LD_ABS(BPF_B, 0);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+		/* jump to error label */
+		insn[i] = BPF_JMP32_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 3);
 		i++;
 		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
 		insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1);
 		insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2);
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 					 BPF_FUNC_skb_vlan_push),
-		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3);
 		i++;
 	}
 
 	for (j = 0; j < PUSH_CNT; j++) {
 		insn[i++] = BPF_LD_ABS(BPF_B, 0);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+		insn[i] = BPF_JMP32_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 3);
 		i++;
 		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 					 BPF_FUNC_skb_vlan_pop),
-		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3);
 		i++;
 	}
 	if (++k < 5)
 		goto loop;
 
-	for (; i < len - 1; i++)
-		insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
+	for (; i < len - 3; i++)
+		insn[i] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0xbef);
+	insn[len - 3] = BPF_JMP_A(1);
+	/* error label */
+	insn[len - 2] = BPF_MOV32_IMM(BPF_REG_0, 0);
 	insn[len - 1] = BPF_EXIT_INSN();
 	self->prog_len = len;
 }
@@ -171,8 +175,13 @@ loop:
 static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
 {
 	struct bpf_insn *insn = self->fill_insns;
-	/* jump range is limited to 16 bit. every ld_abs is replaced by 6 insns */
-	unsigned int len = (1 << 15) / 6;
+	/* jump range is limited to 16 bit. every ld_abs is replaced by 6 insns,
+	 * but on arches like arm, ppc etc, there will be one BPF_ZEXT inserted
+	 * to extend the error value of the inlined ld_abs sequence which then
+	 * contains 7 insns. so, set the dividend to 7 so the testcase could
+	 * work on all arches.
+	 */
+	unsigned int len = (1 << 15) / 7;
 	int i = 0;
 
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
@@ -210,33 +219,35 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	self->retval = (uint32_t)res;
 }
 
-/* test the sequence of 1k jumps */
+#define MAX_JMP_SEQ 8192
+
+/* test the sequence of 8k jumps */
 static void bpf_fill_scale1(struct bpf_test *self)
 {
 	struct bpf_insn *insn = self->fill_insns;
 	int i = 0, k = 0;
 
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
-	/* test to check that the sequence of 1024 jumps is acceptable */
-	while (k++ < 1024) {
+	/* test to check that the long sequence of jumps is acceptable */
+	while (k++ < MAX_JMP_SEQ) {
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 					 BPF_FUNC_get_prandom_u32);
-		insn[i++] = BPF_JMP_IMM(BPF_JGT, BPF_REG_0, bpf_semi_rand_get(), 2);
+		insn[i++] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, bpf_semi_rand_get(), 2);
 		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_10);
 		insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6,
 					-8 * (k % 64 + 1));
 	}
-	/* every jump adds 1024 steps to insn_processed, so to stay exactly
-	 * within 1m limit add MAX_TEST_INSNS - 1025 MOVs and 1 EXIT
+	/* every jump adds 1 step to insn_processed, so to stay exactly
+	 * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT
 	 */
-	while (i < MAX_TEST_INSNS - 1025)
-		insn[i++] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 42);
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
+		insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42);
 	insn[i] = BPF_EXIT_INSN();
 	self->prog_len = i + 1;
 	self->retval = 42;
 }
 
-/* test the sequence of 1k jumps in inner most function (function depth 8)*/
+/* test the sequence of 8k jumps in inner most function (function depth 8)*/
 static void bpf_fill_scale2(struct bpf_test *self)
 {
 	struct bpf_insn *insn = self->fill_insns;
@@ -248,20 +259,21 @@ static void bpf_fill_scale2(struct bpf_test *self)
 		insn[i++] = BPF_EXIT_INSN();
 	}
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
-	/* test to check that the sequence of 1024 jumps is acceptable */
-	while (k++ < 1024) {
+	/* test to check that the long sequence of jumps is acceptable */
+	k = 0;
+	while (k++ < MAX_JMP_SEQ) {
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 					 BPF_FUNC_get_prandom_u32);
-		insn[i++] = BPF_JMP_IMM(BPF_JGT, BPF_REG_0, bpf_semi_rand_get(), 2);
+		insn[i++] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, bpf_semi_rand_get(), 2);
 		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_10);
 		insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6,
 					-8 * (k % (64 - 4 * FUNC_NEST) + 1));
 	}
-	/* every jump adds 1024 steps to insn_processed, so to stay exactly
-	 * within 1m limit add MAX_TEST_INSNS - 1025 MOVs and 1 EXIT
+	/* every jump adds 1 step to insn_processed, so to stay exactly
+	 * within 1m limit add MAX_TEST_INSNS - MAX_JMP_SEQ - 1 MOVs and 1 EXIT
 	 */
-	while (i < MAX_TEST_INSNS - 1025)
-		insn[i++] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 42);
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
+		insn[i++] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 42);
 	insn[i] = BPF_EXIT_INSN();
 	self->prog_len = i + 1;
 	self->retval = 42;
@@ -870,7 +882,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (fixup_skips != skips)
 		return;
 
-	pflags = 0;
+	pflags = BPF_F_TEST_RND_HI32;
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)

tools/testing/selftests/bpf/test_xdping.sh

@@ -0,0 +1,99 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# xdping tests
+#   Here we setup and teardown configuration required to run
+#   xdping, exercising its options.
+#
+#   Setup is similar to test_tunnel tests but without the tunnel.
+#
+# Topology:
+# ---------
+#     root namespace   |     tc_ns0 namespace
+#                      |
+#      ----------      |     ----------
+#      |  veth1  | --------- |  veth0  |
+#      ----------    peer    ----------
+#
+# Device Configuration
+# --------------------
+# Root namespace with BPF
+# Device names and addresses:
+#	veth1 IP: 10.1.1.200
+#	xdp added to veth1, xdpings originate from here.
+#
+# Namespace tc_ns0 with BPF
+# Device names and addresses:
+#       veth0 IPv4: 10.1.1.100
+#	For some tests xdping run in server mode here.
+#
+
+readonly TARGET_IP="10.1.1.100"
+readonly TARGET_NS="xdp_ns0"
+
+readonly LOCAL_IP="10.1.1.200"
+
+setup()
+{
+	ip netns add $TARGET_NS
+	ip link add veth0 type veth peer name veth1
+	ip link set veth0 netns $TARGET_NS
+	ip netns exec $TARGET_NS ip addr add ${TARGET_IP}/24 dev veth0
+	ip addr add ${LOCAL_IP}/24 dev veth1
+	ip netns exec $TARGET_NS ip link set veth0 up
+	ip link set veth1 up
+}
+
+cleanup()
+{
+	set +e
+	ip netns delete $TARGET_NS 2>/dev/null
+	ip link del veth1 2>/dev/null
+	if [[ $server_pid -ne 0 ]]; then
+		kill -TERM $server_pid
+	fi
+}
+
+test()
+{
+	client_args="$1"
+	server_args="$2"
+
+	echo "Test client args '$client_args'; server args '$server_args'"
+
+	server_pid=0
+	if [[ -n "$server_args" ]]; then
+		ip netns exec $TARGET_NS ./xdping $server_args &
+		server_pid=$!
+		sleep 10
+	fi
+	./xdping $client_args $TARGET_IP
+
+	if [[ $server_pid -ne 0 ]]; then
+		kill -TERM $server_pid
+		server_pid=0
+	fi
+
+	echo "Test client args '$client_args'; server args '$server_args': PASS"
+}
+
+set -e
+
+server_pid=0
+
+trap cleanup EXIT
+
+setup
+
+for server_args in "" "-I veth0 -s -S" ; do
+	# client in skb mode
+	client_args="-I veth1 -S"
+	test "$client_args" "$server_args"
+
+	# client with count of 10 RTT measurements.
+	client_args="-I veth1 -S -c 10"
+	test "$client_args" "$server_args"
+done
+
+echo "OK. All tests passed"
+exit 0

tools/testing/selftests/bpf/trace_helpers.c

@@ -30,9 +30,7 @@ int load_kallsyms(void)
 	if (!f)
 		return -ENOENT;
 
-	while (!feof(f)) {
-		if (!fgets(buf, sizeof(buf), f))
-			break;
+	while (fgets(buf, sizeof(buf), f)) {
 		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
 			break;
 		if (!addr)

tools/testing/selftests/bpf/xdping.c

@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */
+
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <arpa/inet.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <sys/resource.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netdb.h>
+
+#include "bpf/bpf.h"
+#include "bpf/libbpf.h"
+
+#include "xdping.h"
+
+static int ifindex;
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+
+static void cleanup(int sig)
+{
+	bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+	if (sig)
+		exit(1);
+}
+
+static int get_stats(int fd, __u16 count, __u32 raddr)
+{
+	struct pinginfo pinginfo = { 0 };
+	char inaddrbuf[INET_ADDRSTRLEN];
+	struct in_addr inaddr;
+	__u16 i;
+
+	inaddr.s_addr = raddr;
+
+	printf("\nXDP RTT data:\n");
+
+	if (bpf_map_lookup_elem(fd, &raddr, &pinginfo)) {
+		perror("bpf_map_lookup elem: ");
+		return 1;
+	}
+
+	for (i = 0; i < count; i++) {
+		if (pinginfo.times[i] == 0)
+			break;
+
+		printf("64 bytes from %s: icmp_seq=%d ttl=64 time=%#.5f ms\n",
+		       inet_ntop(AF_INET, &inaddr, inaddrbuf,
+				 sizeof(inaddrbuf)),
+		       count + i + 1,
+		       (double)pinginfo.times[i]/1000000);
+	}
+
+	if (i < count) {
+		fprintf(stderr, "Expected %d samples, got %d.\n", count, i);
+		return 1;
+	}
+
+	bpf_map_delete_elem(fd, &raddr);
+
+	return 0;
+}
+
+static void show_usage(const char *prog)
+{
+	fprintf(stderr,
+		"usage: %s [OPTS] -I interface destination\n\n"
+		"OPTS:\n"
+		"    -c count		Stop after sending count requests\n"
+		"			(default %d, max %d)\n"
+		"    -I interface	interface name\n"
+		"    -N			Run in driver mode\n"
+		"    -s			Server mode\n"
+		"    -S			Run in skb mode\n",
+		prog, XDPING_DEFAULT_COUNT, XDPING_MAX_COUNT);
+}
+
+int main(int argc, char **argv)
+{
+	__u32 mode_flags = XDP_FLAGS_DRV_MODE | XDP_FLAGS_SKB_MODE;
+	struct addrinfo *a, hints = { .ai_family = AF_INET };
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	__u16 count = XDPING_DEFAULT_COUNT;
+	struct pinginfo pinginfo = { 0 };
+	const char *optstr = "c:I:NsS";
+	struct bpf_program *main_prog;
+	int prog_fd = -1, map_fd = -1;
+	struct sockaddr_in rin;
+	struct bpf_object *obj;
+	struct bpf_map *map;
+	char *ifname = NULL;
+	char filename[256];
+	int opt, ret = 1;
+	__u32 raddr = 0;
+	int server = 0;
+	char cmd[256];
+
+	while ((opt = getopt(argc, argv, optstr)) != -1) {
+		switch (opt) {
+		case 'c':
+			count = atoi(optarg);
+			if (count < 1 || count > XDPING_MAX_COUNT) {
+				fprintf(stderr,
+					"min count is 1, max count is %d\n",
+					XDPING_MAX_COUNT);
+				return 1;
+			}
+			break;
+		case 'I':
+			ifname = optarg;
+			ifindex = if_nametoindex(ifname);
+			if (!ifindex) {
+				fprintf(stderr, "Could not get interface %s\n",
+					ifname);
+				return 1;
+			}
+			break;
+		case 'N':
+			xdp_flags |= XDP_FLAGS_DRV_MODE;
+			break;
+		case 's':
+			/* use server program */
+			server = 1;
+			break;
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
+		default:
+			show_usage(basename(argv[0]));
+			return 1;
+		}
+	}
+
+	if (!ifname) {
+		show_usage(basename(argv[0]));
+		return 1;
+	}
+	if (!server && optind == argc) {
+		show_usage(basename(argv[0]));
+		return 1;
+	}
+
+	if ((xdp_flags & mode_flags) == mode_flags) {
+		fprintf(stderr, "-N or -S can be specified, not both.\n");
+		show_usage(basename(argv[0]));
+		return 1;
+	}
+
+	if (!server) {
+		/* Only supports IPv4; see hints initiailization above. */
+		if (getaddrinfo(argv[optind], NULL, &hints, &a) || !a) {
+			fprintf(stderr, "Could not resolve %s\n", argv[optind]);
+			return 1;
+		}
+		memcpy(&rin, a->ai_addr, sizeof(rin));
+		raddr = rin.sin_addr.s_addr;
+		freeaddrinfo(a);
+	}
+
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (bpf_prog_load(filename, BPF_PROG_TYPE_XDP, &obj, &prog_fd)) {
+		fprintf(stderr, "load of %s failed\n", filename);
+		return 1;
+	}
+
+	main_prog = bpf_object__find_program_by_title(obj,
+						      server ? "xdpserver" :
+							       "xdpclient");
+	if (main_prog)
+		prog_fd = bpf_program__fd(main_prog);
+	if (!main_prog || prog_fd < 0) {
+		fprintf(stderr, "could not find xdping program");
+		return 1;
+	}
+
+	map = bpf_map__next(NULL, obj);
+	if (map)
+		map_fd = bpf_map__fd(map);
+	if (!map || map_fd < 0) {
+		fprintf(stderr, "Could not find ping map");
+		goto done;
+	}
+
+	signal(SIGINT, cleanup);
+	signal(SIGTERM, cleanup);
+
+	printf("Setting up XDP for %s, please wait...\n", ifname);
+
+	printf("XDP setup disrupts network connectivity, hit Ctrl+C to quit\n");
+
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
+		fprintf(stderr, "Link set xdp fd failed for %s\n", ifname);
+		goto done;
+	}
+
+	if (server) {
+		close(prog_fd);
+		close(map_fd);
+		printf("Running server on %s; press Ctrl+C to exit...\n",
+		       ifname);
+		do { } while (1);
+	}
+
+	/* Start xdping-ing from last regular ping reply, e.g. for a count
+	 * of 10 ICMP requests, we start xdping-ing using reply with seq number
+	 * 10.  The reason the last "real" ping RTT is much higher is that
+	 * the ping program sees the ICMP reply associated with the last
+	 * XDP-generated packet, so ping doesn't get a reply until XDP is done.
+	 */
+	pinginfo.seq = htons(count);
+	pinginfo.count = count;
+
+	if (bpf_map_update_elem(map_fd, &raddr, &pinginfo, BPF_ANY)) {
+		fprintf(stderr, "could not communicate with BPF map: %s\n",
+			strerror(errno));
+		cleanup(0);
+		goto done;
+	}
+
+	/* We need to wait for XDP setup to complete. */
+	sleep(10);
+
+	snprintf(cmd, sizeof(cmd), "ping -c %d -I %s %s",
+		 count, ifname, argv[optind]);
+
+	printf("\nNormal ping RTT data\n");
+	printf("[Ignore final RTT; it is distorted by XDP using the reply]\n");
+
+	ret = system(cmd);
+
+	if (!ret)
+		ret = get_stats(map_fd, count, raddr);
+
+	cleanup(0);
+
+done:
+	if (prog_fd > 0)
+		close(prog_fd);
+	if (map_fd > 0)
+		close(map_fd);
+
+	return ret;
+}

tools/testing/selftests/bpf/xdping.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */
+
+#define	XDPING_MAX_COUNT	10
+#define	XDPING_DEFAULT_COUNT	4
+
+struct pinginfo {
+	__u64	start;
+	__be16	seq;
+	__u16	count;
+	__u32	pad;
+	__u64	times[XDPING_MAX_COUNT];
+};