From 9b7e94e6e89be284df94554c8b3c08f91c5c04c3 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 22 May 2019 12:09:16 -0700
Subject: selftests: fib-onlink: Make quiet by default

Add VERBOSE argument to fib-onlink-tests.sh and make output quiet by
default. Add getopt parsing of inputs and support for -v (verbose) and
-p (pause on fail).

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib-onlink-tests.sh | 48 ++++++++++++++++++++++---
 1 file changed, 43 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh
index 864f865eee55..c287b90b8af8 100755
--- a/tools/testing/selftests/net/fib-onlink-tests.sh
+++ b/tools/testing/selftests/net/fib-onlink-tests.sh
@@ -4,6 +4,7 @@
 # IPv4 and IPv6 onlink tests
 
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+VERBOSE=0
 
 # Network interfaces
 # - odd in current namespace; even in peer ns
@@ -91,10 +92,10 @@ log_test()
 
 	if [ ${rc} -eq ${expected} ]; then
 		nsuccess=$((nsuccess+1))
-		printf "\n    TEST: %-50s  [ OK ]\n" "${msg}"
+		printf "    TEST: %-50s  [ OK ]\n" "${msg}"
 	else
 		nfail=$((nfail+1))
-		printf "\n    TEST: %-50s  [FAIL]\n" "${msg}"
+		printf "    TEST: %-50s  [FAIL]\n" "${msg}"
 		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
 			echo
 			echo "hit enter to continue, 'q' to quit"
@@ -121,9 +122,23 @@ log_subsection()
 
 run_cmd()
 {
-	echo
-	echo "COMMAND: $*"
-	eval $*
+	local cmd="$*"
+	local out
+	local rc
+
+	if [ "$VERBOSE" = "1" ]; then
+		printf "    COMMAND: $cmd\n"
+	fi
+
+	out=$(eval $cmd 2>&1)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+
+	return $rc
 }
 
 get_linklocal()
@@ -450,12 +465,35 @@ run_onlink_tests()
 	invalid_onlink_ipv6
 }
 
+################################################################################
+# usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+
+        -p          Pause on fail
+        -v          verbose mode (show commands and output)
+EOF
+}
+
 ################################################################################
 # main
 
 nsuccess=0
 nfail=0
 
+while getopts :t:pPhv o
+do
+	case $o in
+		p) PAUSE_ON_FAIL=yes;;
+		v) VERBOSE=$(($VERBOSE + 1));;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
 cleanup
 setup
 run_onlink_tests
-- 
cgit v1.2.3


From a92a0a7b8e7c1e3dbc0c8a7fed7b52e7915e8c11 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 22 May 2019 12:11:06 -0700
Subject: selftests: pmtu: Simplify cleanup and namespace names

The point of the pause-on-fail argument is to leave the setup as is after
a test fails to allow a user to debug why it failed. Move the cleanup
after posting the result to the user to make it so.

Random names for the namespaces are not user friendly when trying to
debug a failure. Make them simpler and more direct for the tests. Run
cleanup at the beginning to ensure they are cleaned up if they already
exist.

Remove cleanup_done. There is no harm in doing cleanup twice; just
ignore any errors related to not existing - which is already done.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index b9171a7b3aaa..ab77e6344d17 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -152,10 +152,10 @@ tests="
 	cleanup_ipv4_exception		ipv4: cleanup of cached exceptions
 	cleanup_ipv6_exception		ipv6: cleanup of cached exceptions"
 
-NS_A="ns-$(mktemp -u XXXXXX)"
-NS_B="ns-$(mktemp -u XXXXXX)"
-NS_R1="ns-$(mktemp -u XXXXXX)"
-NS_R2="ns-$(mktemp -u XXXXXX)"
+NS_A="ns-A"
+NS_B="ns-B"
+NS_R1="ns-R1"
+NS_R2="ns-R2"
 ns_a="ip netns exec ${NS_A}"
 ns_b="ip netns exec ${NS_B}"
 ns_r1="ip netns exec ${NS_R1}"
@@ -212,7 +212,6 @@ dummy6_0_addr="fc00:1000::0"
 dummy6_1_addr="fc00:1001::0"
 dummy6_mask="64"
 
-cleanup_done=1
 err_buf=
 tcpdump_pids=
 
@@ -495,7 +494,7 @@ setup_routing() {
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
-	cleanup_done=0
+	cleanup
 	for arg do
 		eval setup_${arg} || { echo "  ${arg} not supported"; return 1; }
 	done
@@ -519,11 +518,9 @@ cleanup() {
 	done
 	tcpdump_pids=
 
-	[ ${cleanup_done} -eq 1 ] && return
 	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
 		ip netns del ${n} 2> /dev/null
 	done
-	cleanup_done=1
 }
 
 mtu() {
@@ -1136,6 +1133,9 @@ done
 
 trap cleanup EXIT
 
+# start clean
+cleanup
+
 for t in ${tests}; do
 	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
 
@@ -1156,7 +1156,6 @@ for t in ${tests}; do
 
 		eval test_${name}
 		ret=$?
-		cleanup
 
 		if [ $ret -eq 0 ]; then
 			printf "TEST: %-60s  [ OK ]\n" "${t}"
-- 
cgit v1.2.3


From 9efc7794496d531593751a3fb008030d5f9ba87c Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Wed, 22 May 2019 10:51:28 -0700
Subject: libbpf: emit diff of mismatched public API, if any

It's easy to have a mismatch of "intended to be public" vs really
exposed API functions. While Makefile does check for this mismatch, if
it actually occurs it's not trivial to determine which functions are
accidentally exposed. This patch dumps out a diff showing what's not
supposed to be exposed facilitating easier fixing.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index f91639bf5650..a2aceadf68db 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -204,6 +204,16 @@ check_abi: $(OUTPUT)libbpf.so
 		     "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \
 		     "Please make sure all LIBBPF_API symbols are"	 \
 		     "versioned in $(VERSION_SCRIPT)." >&2;		 \
+		readelf -s --wide $(OUTPUT)libbpf-in.o |		 \
+		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'|   \
+		    sort -u > $(OUTPUT)libbpf_global_syms.tmp;		 \
+		readelf -s --wide $(OUTPUT)libbpf.so |			 \
+		    grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 |		 \
+		    sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; 	 \
+		diff -u $(OUTPUT)libbpf_global_syms.tmp			 \
+		     $(OUTPUT)libbpf_versioned_syms.tmp;		 \
+		rm $(OUTPUT)libbpf_global_syms.tmp			 \
+		   $(OUTPUT)libbpf_versioned_syms.tmp;			 \
 		exit 1;							 \
 	fi
 
-- 
cgit v1.2.3


From 7c0c6095d48dcd0e67c917aa73cdbb2715aafc36 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 21 May 2019 20:14:20 -0700
Subject: selftests/bpf: adjust verifier scale test

Adjust scale tests to check for new jmp sequence limit.

BPF_JGT had to be changed to BPF_JEQ because the verifier was
too smart. It tracked the known safe range of R0 values
and pruned the search earlier before hitting exact 8192 limit.
bpf_semi_rand_get() was too (un)?lucky.

k = 0; was missing in bpf_fill_scale2.
It was testing a bit shorter sequence of jumps than intended.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 31 ++++++++++++++++-------------
 1 file changed, 17 insertions(+), 14 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index ccd896b98cac..6e2fec84c929 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -210,33 +210,35 @@ 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)
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
 		insn[i++] = BPF_ALU32_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;
@@ -248,19 +250,20 @@ 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)
+	while (i < MAX_TEST_INSNS - MAX_JMP_SEQ - 1)
 		insn[i++] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 42);
 	insn[i] = BPF_EXIT_INSN();
 	self->prog_len = i + 1;
-- 
cgit v1.2.3


From 7c9441066ab53168093c79477aabd575f7c14129 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 21 May 2019 20:14:21 -0700
Subject: selftests/bpf: add pyperf scale test

Add a snippet of pyperf bpf program used to collect python stack traces
as a scale test for the verifier.

At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll'
and generates partially unrolled loop instead.
Hence use 50, 100, and 180 loop iterations to stress test.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../selftests/bpf/prog_tests/bpf_verif_scale.c     |  31 ++-
 tools/testing/selftests/bpf/progs/pyperf.h         | 268 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/pyperf100.c      |   4 +
 tools/testing/selftests/bpf/progs/pyperf180.c      |   4 +
 tools/testing/selftests/bpf/progs/pyperf50.c       |   4 +
 5 files changed, 298 insertions(+), 13 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/pyperf.h
 create mode 100644 tools/testing/selftests/bpf/progs/pyperf100.c
 create mode 100644 tools/testing/selftests/bpf/progs/pyperf180.c
 create mode 100644 tools/testing/selftests/bpf/progs/pyperf50.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index b74e2f6e96d0..ce03289c9077 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/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;
@@ -20,7 +20,7 @@ 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;
 	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
 	bpf_object__close(obj);
@@ -31,19 +31,24 @@ 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");
+	}
 }
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
new file mode 100644
index 000000000000..0cc5e4ee90bd
--- /dev/null
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/pyperf100.c b/tools/testing/selftests/bpf/progs/pyperf100.c
new file mode 100644
index 000000000000..29786325db54
--- /dev/null
+++ b/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"
diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c
new file mode 100644
index 000000000000..c39f559d3100
--- /dev/null
+++ b/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"
diff --git a/tools/testing/selftests/bpf/progs/pyperf50.c b/tools/testing/selftests/bpf/progs/pyperf50.c
new file mode 100644
index 000000000000..ef7ce340a292
--- /dev/null
+++ b/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"
-- 
cgit v1.2.3


From ec8105352869766569f657464c8a78d7bc0e2406 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 22 May 2019 20:28:01 -0700
Subject: selftests: Add redirect tests

Add test for ICMP redirects and exception processing. Test is setup
for later addition of tests using nexthop objects for routing.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/icmp_redirect.sh | 455 +++++++++++++++++++++++++++
 1 file changed, 455 insertions(+)
 create mode 100755 tools/testing/selftests/net/icmp_redirect.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
new file mode 100755
index 000000000000..e8d8496f5b16
--- /dev/null
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -0,0 +1,455 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# redirect test
+#
+#                     .253 +----+
+#                     +----| r1 |
+#                     |    +----+
+# +----+              |       |.1
+# | h1 |--------------+       |   10.1.1.0/30 2001:db8:1::0/126
+# +----+ .1           |       |.2
+#         172.16.1/24 |    +----+                   +----+
+#    2001:db8:16:1/64 +----| r2 |-------------------| h2 |
+#                     .254 +----+ .254           .2 +----+
+#                                    172.16.2/24
+#                                  2001:db8:16:2/64
+#
+# Route from h1 to h2 goes through r1, eth1 - connection between r1 and r2.
+# Route on r1 changed to go to r2 via eth0. This causes a redirect to be sent
+# from r1 to h1 telling h1 to use r2 when talking to h2.
+
+VERBOSE=0
+PAUSE_ON_FAIL=no
+
+H1_N1_IP=172.16.1.1
+R1_N1_IP=172.16.1.253
+R2_N1_IP=172.16.1.254
+
+H1_N1_IP6=2001:db8:16:1::1
+R1_N1_IP6=2001:db8:16:1::253
+R2_N1_IP6=2001:db8:16:1::254
+
+R1_R2_N1_IP=10.1.1.1
+R2_R1_N1_IP=10.1.1.2
+
+R1_R2_N1_IP6=2001:db8:1::1
+R2_R1_N1_IP6=2001:db8:1::2
+
+H2_N2=172.16.2.0/24
+H2_N2_6=2001:db8:16:2::/64
+H2_N2_IP=172.16.2.2
+R2_N2_IP=172.16.2.254
+H2_N2_IP6=2001:db8:16:2::2
+R2_N2_IP6=2001:db8:16:2::254
+
+VRF=red
+VRF_TABLE=1111
+
+################################################################################
+# helpers
+
+log_section()
+{
+	echo
+	echo "###########################################################################"
+	echo "$*"
+	echo "###########################################################################"
+	echo
+}
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		printf "TEST: %-60s  [ OK ]\n" "${msg}"
+		nsuccess=$((nsuccess+1))
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "TEST: %-60s  [FAIL]\n" "${msg}"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+			echo
+			echo "hit enter to continue, 'q' to quit"
+			read a
+			[ "$a" = "q" ] && exit 1
+		fi
+	fi
+}
+
+run_cmd()
+{
+	local cmd="$*"
+	local out
+	local rc
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo "COMMAND: $cmd"
+	fi
+
+	out=$(eval $cmd 2>&1)
+	rc=$?
+	if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+		echo "$out"
+	fi
+
+	[ "$VERBOSE" = "1" ] && echo
+
+	return $rc
+}
+
+get_linklocal()
+{
+	local ns=$1
+	local dev=$2
+	local addr
+
+	addr=$(ip -netns $ns -6 -br addr show dev ${dev} | \
+	awk '{
+		for (i = 3; i <= NF; ++i) {
+			if ($i ~ /^fe80/)
+				print $i
+		}
+	}'
+	)
+	addr=${addr/\/*}
+
+	[ -z "$addr" ] && return 1
+
+	echo $addr
+
+	return 0
+}
+
+################################################################################
+# setup and teardown
+
+cleanup()
+{
+	local ns
+
+	for ns in h1 h2 r1 r2; do
+		ip netns del $ns 2>/dev/null
+	done
+}
+
+create_vrf()
+{
+	local ns=$1
+
+	ip -netns ${ns} link add ${VRF} type vrf table ${VRF_TABLE}
+	ip -netns ${ns} link set ${VRF} up
+	ip -netns ${ns} route add vrf ${VRF} unreachable default metric 8192
+	ip -netns ${ns} -6 route add vrf ${VRF} unreachable default metric 8192
+
+	ip -netns ${ns} addr add 127.0.0.1/8 dev ${VRF}
+	ip -netns ${ns} -6 addr add ::1 dev ${VRF} nodad
+
+	ip -netns ${ns} ru del pref 0
+	ip -netns ${ns} ru add pref 32765 from all lookup local
+	ip -netns ${ns} -6 ru del pref 0
+	ip -netns ${ns} -6 ru add pref 32765 from all lookup local
+}
+
+setup()
+{
+	local ns
+
+	#
+	# create nodes as namespaces
+	#
+	for ns in h1 h2 r1 r2; do
+		ip netns add $ns
+		ip -netns $ns li set lo up
+
+		case "${ns}" in
+		h[12]) ip netns exec $ns sysctl -q -w net.ipv4.conf.all.accept_redirects=1
+		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.accept_redirects=1
+		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1
+			;;
+		r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
+		       ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
+
+		       ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
+		       ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
+		esac
+	done
+
+	#
+	# create interconnects
+	#
+	ip -netns h1 li add eth0 type veth peer name r1h1
+	ip -netns h1 li set r1h1 netns r1 name eth0 up
+
+	ip -netns h1 li add eth1 type veth peer name r2h1
+	ip -netns h1 li set r2h1 netns r2 name eth0 up
+
+	ip -netns h2 li add eth0 type veth peer name r2h2
+	ip -netns h2 li set eth0 up
+	ip -netns h2 li set r2h2 netns r2 name eth2 up
+
+	ip -netns r1 li add eth1 type veth peer name r2r1
+	ip -netns r1 li set eth1 up
+	ip -netns r1 li set r2r1 netns r2 name eth1 up
+
+	#
+	# h1
+	#
+	if [ "${WITH_VRF}" = "yes" ]; then
+		create_vrf "h1"
+		H1_VRF_ARG="vrf ${VRF}"
+		H1_PING_ARG="-I ${VRF}"
+	else
+		H1_VRF_ARG=
+		H1_PING_ARG=
+	fi
+	ip -netns h1 li add br0 type bridge
+	if [ "${WITH_VRF}" = "yes" ]; then
+		ip -netns h1 li set br0 vrf ${VRF} up
+	else
+		ip -netns h1 li set br0 up
+	fi
+	ip -netns h1 addr add dev br0 ${H1_N1_IP}/24
+	ip -netns h1 -6 addr add dev br0 ${H1_N1_IP6}/64 nodad
+	ip -netns h1 li set eth0 master br0 up
+	ip -netns h1 li set eth1 master br0 up
+
+	#
+	# h2
+	#
+	ip -netns h2 addr add dev eth0 ${H2_N2_IP}/24
+	ip -netns h2 ro add default via ${R2_N2_IP} dev eth0
+	ip -netns h2 -6 addr add dev eth0 ${H2_N2_IP6}/64 nodad
+	ip -netns h2 -6 ro add default via ${R2_N2_IP6} dev eth0
+
+	#
+	# r1
+	#
+	ip -netns r1 addr add dev eth0 ${R1_N1_IP}/24
+	ip -netns r1 -6 addr add dev eth0 ${R1_N1_IP6}/64 nodad
+	ip -netns r1 addr add dev eth1 ${R1_R2_N1_IP}/30
+	ip -netns r1 -6 addr add dev eth1 ${R1_R2_N1_IP6}/126 nodad
+
+	#
+	# r2
+	#
+	ip -netns r2 addr add dev eth0 ${R2_N1_IP}/24
+	ip -netns r2 -6 addr add dev eth0 ${R2_N1_IP6}/64 nodad
+	ip -netns r2 addr add dev eth1 ${R2_R1_N1_IP}/30
+	ip -netns r2 -6 addr add dev eth1 ${R2_R1_N1_IP6}/126 nodad
+	ip -netns r2 addr add dev eth2 ${R2_N2_IP}/24
+	ip -netns r2 -6 addr add dev eth2 ${R2_N2_IP6}/64 nodad
+
+	sleep 2
+
+	R1_LLADDR=$(get_linklocal r1 eth0)
+	if [ $? -ne 0 ]; then
+		echo "Error: Failed to get link-local address of r1's eth0"
+		exit 1
+	fi
+
+	R2_LLADDR=$(get_linklocal r2 eth0)
+	if [ $? -ne 0 ]; then
+		echo "Error: Failed to get link-local address of r2's eth0"
+		exit 1
+	fi
+}
+
+change_h2_mtu()
+{
+	local mtu=$1
+
+	run_cmd ip -netns h2 li set eth0 mtu ${mtu}
+	run_cmd ip -netns r2 li set eth2 mtu ${mtu}
+}
+
+check_exception()
+{
+	local mtu="$1"
+	local with_redirect="$2"
+	local desc="$3"
+
+	# From 172.16.1.101: icmp_seq=1 Redirect Host(New nexthop: 172.16.1.102)
+	if [ "$VERBOSE" = "1" ]; then
+		echo "Commands to check for exception:"
+		run_cmd ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP}
+		run_cmd ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6}
+	fi
+
+	if [ -n "${mtu}" ]; then
+		mtu=" mtu ${mtu}"
+	fi
+	if [ "$with_redirect" = "yes" ]; then
+		ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
+		grep -q "cache <redirected> expires [0-9]*sec${mtu}"
+	elif [ -n "${mtu}" ]; then
+		ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
+		grep -q "cache expires [0-9]*sec${mtu}"
+	else
+		ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
+		grep -q "cache"
+	fi
+	log_test $? 0 "IPv4: ${desc}"
+
+	if [ "$with_redirect" = "yes" ]; then
+		ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | grep -q "${H2_N2_IP6} from :: via ${R2_LLADDR} dev br0.*${mtu}"
+	else
+		ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | grep -q "${mtu}"
+	fi
+	log_test $? 0 "IPv6: ${desc}"
+}
+
+run_ping()
+{
+	local sz=$1
+
+	run_cmd ip netns exec h1 ping -q -M want -i 0.2 -c 10 -w 2 -s ${sz} ${H1_PING_ARG} ${H2_N2_IP}
+	run_cmd ip netns exec h1 ${ping6} -q -M want -i 0.2 -c 10 -w 2 -s ${sz} ${H1_PING_ARG} ${H2_N2_IP6}
+}
+
+replace_route_legacy()
+{
+	# r1 to h2 via r2 and eth0
+	run_cmd ip -netns r1    ro replace ${H2_N2}   via ${R2_N1_IP}  dev eth0
+	run_cmd ip -netns r1 -6 ro replace ${H2_N2_6} via ${R2_LLADDR} dev eth0
+}
+
+initial_route_legacy()
+{
+	# r1 to h2 via r2 and eth1
+	run_cmd ip -netns r1    ro add ${H2_N2}   via ${R2_R1_N1_IP}  dev eth1
+	run_cmd ip -netns r1 -6 ro add ${H2_N2_6} via ${R2_R1_N1_IP6} dev eth1
+
+	# h1 to h2 via r1
+	# - IPv6 redirect only works if gateway is the LLA
+	run_cmd ip -netns h1    ro add ${H1_VRF_ARG} ${H2_N2} via ${R1_N1_IP} dev br0
+	run_cmd ip -netns h1 -6 ro add ${H1_VRF_ARG} ${H2_N2_6} via ${R1_LLADDR} dev br0
+}
+
+check_connectivity()
+{
+	local rc
+
+	run_cmd ip netns exec h1 ping -c1 -w1 ${H1_PING_ARG} ${H2_N2_IP}
+	rc=$?
+	run_cmd ip netns exec h1 ${ping6} -c1 -w1 ${H1_PING_ARG} ${H2_N2_IP6}
+	[ $? -ne 0 ] && rc=$?
+
+	return $rc
+}
+
+do_test()
+{
+	local ttype="$1"
+
+	eval initial_route_${ttype}
+
+	# verify connectivity
+	check_connectivity
+	if [ $? -ne 0 ]; then
+		echo "Error: Basic connectivity is broken"
+		ret=1
+		return
+	fi
+
+	# redirect exception followed by mtu
+	eval replace_route_${ttype}
+	run_ping 64
+	check_exception "" "yes" "redirect exception"
+
+	check_connectivity
+	if [ $? -ne 0 ]; then
+		echo "Error: Basic connectivity is broken after redirect"
+		ret=1
+		return
+	fi
+
+	change_h2_mtu 1300
+	run_ping 1350
+	check_exception "1300" "yes" "redirect exception plus mtu"
+
+	# remove exceptions and restore routing
+	change_h2_mtu 1500
+	ip -netns h1 li set br0 down
+	ip -netns h1 li set br0 up
+	eval initial_route_${ttype}
+
+	check_connectivity
+	if [ $? -ne 0 ]; then
+		echo "Error: Basic connectivity is broken after reset"
+		ret=1
+		return
+	fi
+	check_exception "" "no" "routing reset"
+
+	# MTU exception followed by redirect
+	change_h2_mtu 1300
+	run_ping 1350
+	check_exception "1300" "no" "mtu exception"
+
+	eval replace_route_${ttype}
+	run_ping 64
+	check_exception "1300" "yes" "mtu exception plus redirect"
+
+	check_connectivity
+	if [ $? -ne 0 ]; then
+		echo "Error: Basic connectivity is broken after redirect"
+		ret=1
+		return
+	fi
+}
+
+################################################################################
+# usage
+
+usage()
+{
+        cat <<EOF
+usage: ${0##*/} OPTS
+
+	-p          Pause on fail
+	-v          verbose mode (show commands and output)
+EOF
+}
+
+################################################################################
+# main
+
+# Some systems don't have a ping6 binary anymore
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
+ret=0
+nsuccess=0
+nfail=0
+
+while getopts :pv o
+do
+	case $o in
+                p) PAUSE_ON_FAIL=yes;;
+                v) VERBOSE=$(($VERBOSE + 1));;
+                *) usage; exit 1;;
+	esac
+done
+
+trap cleanup EXIT
+
+cleanup
+WITH_VRF=no
+setup
+
+log_section "Legacy routing"
+do_test "legacy"
+
+cleanup
+log_section "Legacy routing with VRF"
+WITH_VRF=yes
+setup
+do_test "legacy"
+
+printf "\nTests passed: %3d\n" ${nsuccess}
+printf "Tests failed: %3d\n"   ${nfail}
+
+exit $ret
-- 
cgit v1.2.3


From af5136f95045b6c4bb8a53d2f288a905c3bd6f25 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 23 May 2019 13:48:46 -0400
Subject: selftests/net: SO_TXTIME with ETF and FQ

The SO_TXTIME API enables packet tranmission with delayed delivery.
This is currently supported by the ETF and FQ packet schedulers.

Evaluate the interface with both schedulers. Install the scheduler
and send a variety of packets streams: without delay, with one
delayed packet, with multiple ordered delays and with reordering.
Verify that packets are released by the scheduler in expected order.

The ETF qdisc requires a timestamp in the future on every packet. It
needs a delay on the qdisc else the packet is dropped on dequeue for
having a delivery time in the past. The test value is experimentally
derived. ETF requires clock_id CLOCK_TAI. It checks this base and
drops for non-conformance.

The FQ qdisc expects clock_id CLOCK_MONOTONIC, the base used by TCP
as of commit fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC").
Within a flow there is an expecation of ordered delivery, as shown by
delivery times of test 4. The FQ qdisc does not require all packets to
have timestamps and does not drop for non-conformance.

The large (msec) delays are chosen to avoid flakiness.

	Output:

	SO_TXTIME ipv6 clock monotonic
	payload:a delay:28 expected:0 (us)

	SO_TXTIME ipv4 clock monotonic
	payload:a delay:38 expected:0 (us)

	SO_TXTIME ipv6 clock monotonic
	payload:a delay:40 expected:0 (us)

	SO_TXTIME ipv4 clock monotonic
	payload:a delay:33 expected:0 (us)

	SO_TXTIME ipv6 clock monotonic
	payload:a delay:10120 expected:10000 (us)

	SO_TXTIME ipv4 clock monotonic
	payload:a delay:10102 expected:10000 (us)

	[.. etc ..]

	OK. All tests passed

Changes v1->v2: update commit message output

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore   |   1 +
 tools/testing/selftests/net/Makefile     |   3 +-
 tools/testing/selftests/net/config       |   2 +
 tools/testing/selftests/net/so_txtime.c  | 296 +++++++++++++++++++++++++++++++
 tools/testing/selftests/net/so_txtime.sh |  31 ++++
 5 files changed, 332 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/net/so_txtime.c
 create mode 100755 tools/testing/selftests/net/so_txtime.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 6f81130605d7..27ef4d07ac91 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -17,3 +17,4 @@ tcp_inq
 tls
 txring_overwrite
 ip_defrag
+so_txtime
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 1e6d14d2825c..8af7869e0f1c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -9,12 +9,13 @@ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
-TEST_PROGS += test_vxlan_fdb_changelink.sh
+TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
 TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
+TEST_GEN_FILES += so_txtime
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 474040448601..89f84b5118bf 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -25,3 +25,5 @@ CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NET_SCH_FQ=m
+CONFIG_NET_SCH_ETF=m
diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c
new file mode 100644
index 000000000000..53f598f06647
--- /dev/null
+++ b/tools/testing/selftests/net/so_txtime.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test the SO_TXTIME API
+ *
+ * Takes two streams of { payload, delivery time }[], one input and one output.
+ * Sends the input stream and verifies arrival matches the output stream.
+ * The two streams can differ due to out-of-order delivery and drops.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <linux/net_tstamp.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+
+static int	cfg_clockid	= CLOCK_TAI;
+static bool	cfg_do_ipv4;
+static bool	cfg_do_ipv6;
+static uint16_t	cfg_port	= 8000;
+static int	cfg_variance_us	= 2000;
+
+static uint64_t glob_tstart;
+
+/* encode one timed transmission (of a 1B payload) */
+struct timed_send {
+	char	data;
+	int64_t	delay_us;
+};
+
+#define MAX_NUM_PKT	8
+static struct timed_send cfg_in[MAX_NUM_PKT];
+static struct timed_send cfg_out[MAX_NUM_PKT];
+static int cfg_num_pkt;
+
+static uint64_t gettime_ns(void)
+{
+	struct timespec ts;
+
+	if (clock_gettime(cfg_clockid, &ts))
+		error(1, errno, "gettime");
+
+	return ts.tv_sec * (1000ULL * 1000 * 1000) + ts.tv_nsec;
+}
+
+static void do_send_one(int fdt, struct timed_send *ts)
+{
+	char control[CMSG_SPACE(sizeof(uint64_t))];
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+	struct cmsghdr *cm;
+	uint64_t tdeliver;
+	int ret;
+
+	iov.iov_base = &ts->data;
+	iov.iov_len = 1;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	if (ts->delay_us >= 0) {
+		memset(control, 0, sizeof(control));
+		msg.msg_control = &control;
+		msg.msg_controllen = sizeof(control);
+
+		tdeliver = glob_tstart + ts->delay_us * 1000;
+
+		cm = CMSG_FIRSTHDR(&msg);
+		cm->cmsg_level = SOL_SOCKET;
+		cm->cmsg_type = SCM_TXTIME;
+		cm->cmsg_len = CMSG_LEN(sizeof(tdeliver));
+		memcpy(CMSG_DATA(cm), &tdeliver, sizeof(tdeliver));
+	}
+
+	ret = sendmsg(fdt, &msg, 0);
+	if (ret == -1)
+		error(1, errno, "write");
+	if (ret == 0)
+		error(1, 0, "write: 0B");
+
+}
+
+static void do_recv_one(int fdr, struct timed_send *ts)
+{
+	int64_t tstop, texpect;
+	char rbuf[2];
+	int ret;
+
+	ret = recv(fdr, rbuf, sizeof(rbuf), 0);
+	if (ret == -1)
+		error(1, errno, "read");
+	if (ret != 1)
+		error(1, 0, "read: %dB", ret);
+
+	tstop = (gettime_ns() - glob_tstart) / 1000;
+	texpect = ts->delay_us >= 0 ? ts->delay_us : 0;
+
+	fprintf(stderr, "payload:%c delay:%ld expected:%ld (us)\n",
+			rbuf[0], tstop, texpect);
+
+	if (rbuf[0] != ts->data)
+		error(1, 0, "payload mismatch. expected %c", ts->data);
+
+	if (labs(tstop - texpect) > cfg_variance_us)
+		error(1, 0, "exceeds variance (%d us)", cfg_variance_us);
+}
+
+static void do_recv_verify_empty(int fdr)
+{
+	char rbuf[1];
+	int ret;
+
+	ret = recv(fdr, rbuf, sizeof(rbuf), 0);
+	if (ret != -1 || errno != EAGAIN)
+		error(1, 0, "recv: not empty as expected (%d, %d)", ret, errno);
+}
+
+static void setsockopt_txtime(int fd)
+{
+	struct sock_txtime so_txtime_val = { .clockid = cfg_clockid };
+	struct sock_txtime so_txtime_val_read = { 0 };
+	socklen_t vallen = sizeof(so_txtime_val);
+
+	if (setsockopt(fd, SOL_SOCKET, SO_TXTIME,
+		       &so_txtime_val, sizeof(so_txtime_val)))
+		error(1, errno, "setsockopt txtime");
+
+	if (getsockopt(fd, SOL_SOCKET, SO_TXTIME,
+		       &so_txtime_val_read, &vallen))
+		error(1, errno, "getsockopt txtime");
+
+	if (vallen != sizeof(so_txtime_val) ||
+	    memcmp(&so_txtime_val, &so_txtime_val_read, vallen))
+		error(1, 0, "getsockopt txtime: mismatch");
+}
+
+static int setup_tx(struct sockaddr *addr, socklen_t alen)
+{
+	int fd;
+
+	fd = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket t");
+
+	if (connect(fd, addr, alen))
+		error(1, errno, "connect");
+
+	setsockopt_txtime(fd);
+
+	return fd;
+}
+
+static int setup_rx(struct sockaddr *addr, socklen_t alen)
+{
+	struct timeval tv = { .tv_usec = 100 * 1000 };
+	int fd;
+
+	fd = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket r");
+
+	if (bind(fd, addr, alen))
+		error(1, errno, "bind");
+
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	return fd;
+}
+
+static void do_test(struct sockaddr *addr, socklen_t alen)
+{
+	int fdt, fdr, i;
+
+	fprintf(stderr, "\nSO_TXTIME ipv%c clock %s\n",
+			addr->sa_family == PF_INET ? '4' : '6',
+			cfg_clockid == CLOCK_TAI ? "tai" : "monotonic");
+
+	fdt = setup_tx(addr, alen);
+	fdr = setup_rx(addr, alen);
+
+	glob_tstart = gettime_ns();
+
+	for (i = 0; i < cfg_num_pkt; i++)
+		do_send_one(fdt, &cfg_in[i]);
+	for (i = 0; i < cfg_num_pkt; i++)
+		do_recv_one(fdr, &cfg_out[i]);
+
+	do_recv_verify_empty(fdr);
+
+	if (close(fdr))
+		error(1, errno, "close r");
+	if (close(fdt))
+		error(1, errno, "close t");
+}
+
+static int parse_io(const char *optarg, struct timed_send *array)
+{
+	char *arg, *tok;
+	int aoff = 0;
+
+	arg = strdup(optarg);
+	if (!arg)
+		error(1, errno, "strdup");
+
+	while ((tok = strtok(arg, ","))) {
+		arg = NULL;	/* only pass non-zero on first call */
+
+		if (aoff / 2 == MAX_NUM_PKT)
+			error(1, 0, "exceeds max pkt count (%d)", MAX_NUM_PKT);
+
+		if (aoff & 1) {	/* parse delay */
+			array->delay_us = strtol(tok, NULL, 0) * 1000;
+			array++;
+		} else {	/* parse character */
+			array->data = tok[0];
+		}
+
+		aoff++;
+	}
+
+	free(arg);
+
+	return aoff / 2;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c, ilen, olen;
+
+	while ((c = getopt(argc, argv, "46c:")) != -1) {
+		switch (c) {
+		case '4':
+			cfg_do_ipv4 = true;
+			break;
+		case '6':
+			cfg_do_ipv6 = true;
+			break;
+		case 'c':
+			if (!strcmp(optarg, "tai"))
+				cfg_clockid = CLOCK_TAI;
+			else if (!strcmp(optarg, "monotonic") ||
+				 !strcmp(optarg, "mono"))
+				cfg_clockid = CLOCK_MONOTONIC;
+			else
+				error(1, 0, "unknown clock id %s", optarg);
+			break;
+		default:
+			error(1, 0, "parse error at %d", optind);
+		}
+	}
+
+	if (argc - optind != 2)
+		error(1, 0, "Usage: %s [-46] -c <clock> <in> <out>", argv[0]);
+
+	ilen = parse_io(argv[optind], cfg_in);
+	olen = parse_io(argv[optind + 1], cfg_out);
+	if (ilen != olen)
+		error(1, 0, "i/o streams len mismatch (%d, %d)\n", ilen, olen);
+	cfg_num_pkt = ilen;
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+
+	if (cfg_do_ipv6) {
+		struct sockaddr_in6 addr6 = {0};
+
+		addr6.sin6_family = AF_INET6;
+		addr6.sin6_port = htons(cfg_port);
+		addr6.sin6_addr = in6addr_loopback;
+		do_test((void *)&addr6, sizeof(addr6));
+	}
+
+	if (cfg_do_ipv4) {
+		struct sockaddr_in addr4 = {0};
+
+		addr4.sin_family = AF_INET;
+		addr4.sin_port = htons(cfg_port);
+		addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+		do_test((void *)&addr4, sizeof(addr4));
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh
new file mode 100755
index 000000000000..5aa519328a5b
--- /dev/null
+++ b/tools/testing/selftests/net/so_txtime.sh
@@ -0,0 +1,31 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Regression tests for the SO_TXTIME interface
+
+# Run in network namespace
+if [[ $# -eq 0 ]]; then
+	./in_netns.sh $0 __subprocess
+	exit $?
+fi
+
+set -e
+
+tc qdisc add dev lo root fq
+./so_txtime -4 -6 -c mono a,-1 a,-1
+./so_txtime -4 -6 -c mono a,0 a,0
+./so_txtime -4 -6 -c mono a,10 a,10
+./so_txtime -4 -6 -c mono a,10,b,20 a,10,b,20
+./so_txtime -4 -6 -c mono a,20,b,10 b,20,a,20
+
+if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 200000; then
+	! ./so_txtime -4 -6 -c tai a,-1 a,-1
+	! ./so_txtime -4 -6 -c tai a,0 a,0
+	./so_txtime -4 -6 -c tai a,10 a,10
+	./so_txtime -4 -6 -c tai a,10,b,20 a,10,b,20
+	./so_txtime -4 -6 -c tai a,20,b,10 b,10,a,20
+else
+	echo "tc ($(tc -V)) does not support qdisc etf. skipping"
+fi
+
+echo OK. All tests passed
-- 
cgit v1.2.3


From 37739d1b4fe744da9c2f342224000ae7fbb5c063 Mon Sep 17 00:00:00 2001
From: Michal Rostecki <mrostecki@opensuse.org>
Date: Thu, 23 May 2019 14:53:54 +0200
Subject: selftests: bpf: Move bpf_printk to bpf_helpers.h

bpf_printk is a macro which is commonly used to print out debug messages
in BPF programs and it was copied in many selftests and samples. Since
all of them include bpf_helpers.h, this change moves the macro there.

Signed-off-by: Michal Rostecki <mrostecki@opensuse.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_helpers.h                | 8 ++++++++
 tools/testing/selftests/bpf/progs/sockmap_parse_prog.c   | 7 -------
 tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c | 7 -------
 tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c | 7 -------
 tools/testing/selftests/bpf/progs/test_lwt_seg6local.c   | 7 -------
 tools/testing/selftests/bpf/progs/test_xdp_noinline.c    | 7 -------
 tools/testing/selftests/bpf/test_sockmap_kern.h          | 7 -------
 7 files changed, 8 insertions(+), 42 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 5f6f9e7aba2a..4b27840b8109 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/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;
diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
index 0f92858f6226..ed3e4a551c57 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
+++ b/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)
 {
diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
index 12a7b5c82ed6..65fbfdb6cd3a 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
+++ b/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)
 {
diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index 2ce7634a4012..bdc22be46f2e 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/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),
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 0575751bc1bc..7c7cb3177463 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
+++ b/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; })
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index 5e4aac74f9d0..4fe6aaad22a4 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/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));
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index e7639f66a941..4e7d3da21357 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/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),
-- 
cgit v1.2.3


From 1d7a08b3bdaec1e25ba7979ff598272b7e34318f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 24 May 2019 11:58:56 -0700
Subject: libbpf: ensure libbpf.h is included along libbpf_internal.h

libbpf_internal.h expects a bunch of stuff defined in libbpf.h to be
defined. This patch makes sure that libbpf.h is always included.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf_internal.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index f3025b4d90e1..850f7bdec5cb 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -9,6 +9,8 @@
 #ifndef __LIBBPF_LIBBPF_INTERNAL_H
 #define __LIBBPF_LIBBPF_INTERNAL_H
 
+#include "libbpf.h"
+
 #define BTF_INFO_ENC(kind, kind_flag, vlen) \
 	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
-- 
cgit v1.2.3


From e6c64855fd7ad565d87b2bd617f4a50d3bdad82f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 24 May 2019 11:58:57 -0700
Subject: libbpf: add btf__parse_elf API to load .BTF and .BTF.ext

Loading BTF and BTF.ext from ELF file is a common need. Instead of
requiring every user to re-implement it, let's provide this API from
libbpf itself. It's mostly copy/paste from `bpftool btf dump`
implementation, which will be switched to libbpf's version in next
patch. btf__parse_elf allows to load BTF and optionally BTF.ext.
This is also useful for tests that need to load/work with BTF, loaded
from test ELF files.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/btf.c      | 128 +++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/btf.h      |   2 +
 tools/lib/bpf/libbpf.map |   5 ++
 3 files changed, 135 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 03348c4d6bd4..6139550810a1 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -4,10 +4,12 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
 #include <linux/err.h>
 #include <linux/btf.h>
+#include <gelf.h>
 #include "btf.h"
 #include "bpf.h"
 #include "libbpf.h"
@@ -417,6 +419,132 @@ done:
 	return btf;
 }
 
+static bool btf_check_endianness(const GElf_Ehdr *ehdr)
+{
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+}
+
+struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
+{
+	Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
+	int err = 0, fd = -1, idx = 0;
+	struct btf *btf = NULL;
+	Elf_Scn *scn = NULL;
+	Elf *elf = NULL;
+	GElf_Ehdr ehdr;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		pr_warning("failed to init libelf for %s\n", path);
+		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
+	}
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		err = -errno;
+		pr_warning("failed to open %s: %s\n", path, strerror(errno));
+		return ERR_PTR(err);
+	}
+
+	err = -LIBBPF_ERRNO__FORMAT;
+
+	elf = elf_begin(fd, ELF_C_READ, NULL);
+	if (!elf) {
+		pr_warning("failed to open %s as ELF file\n", path);
+		goto done;
+	}
+	if (!gelf_getehdr(elf, &ehdr)) {
+		pr_warning("failed to get EHDR from %s\n", path);
+		goto done;
+	}
+	if (!btf_check_endianness(&ehdr)) {
+		pr_warning("non-native ELF endianness is not supported\n");
+		goto done;
+	}
+	if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
+		pr_warning("failed to get e_shstrndx from %s\n", path);
+		goto done;
+	}
+
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		GElf_Shdr sh;
+		char *name;
+
+		idx++;
+		if (gelf_getshdr(scn, &sh) != &sh) {
+			pr_warning("failed to get section(%d) header from %s\n",
+				   idx, path);
+			goto done;
+		}
+		name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+		if (!name) {
+			pr_warning("failed to get section(%d) name from %s\n",
+				   idx, path);
+			goto done;
+		}
+		if (strcmp(name, BTF_ELF_SEC) == 0) {
+			btf_data = elf_getdata(scn, 0);
+			if (!btf_data) {
+				pr_warning("failed to get section(%d, %s) data from %s\n",
+					   idx, name, path);
+				goto done;
+			}
+			continue;
+		} else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+			btf_ext_data = elf_getdata(scn, 0);
+			if (!btf_ext_data) {
+				pr_warning("failed to get section(%d, %s) data from %s\n",
+					   idx, name, path);
+				goto done;
+			}
+			continue;
+		}
+	}
+
+	err = 0;
+
+	if (!btf_data) {
+		err = -ENOENT;
+		goto done;
+	}
+	btf = btf__new(btf_data->d_buf, btf_data->d_size);
+	if (IS_ERR(btf))
+		goto done;
+
+	if (btf_ext && btf_ext_data) {
+		*btf_ext = btf_ext__new(btf_ext_data->d_buf,
+					btf_ext_data->d_size);
+		if (IS_ERR(*btf_ext))
+			goto done;
+	} else if (btf_ext) {
+		*btf_ext = NULL;
+	}
+done:
+	if (elf)
+		elf_end(elf);
+	close(fd);
+
+	if (err)
+		return ERR_PTR(err);
+	/*
+	 * btf is always parsed before btf_ext, so no need to clean up
+	 * btf_ext, if btf loading failed
+	 */
+	if (IS_ERR(btf))
+		return btf;
+	if (btf_ext && IS_ERR(*btf_ext)) {
+		btf__free(btf);
+		err = PTR_ERR(*btf_ext);
+		return ERR_PTR(err);
+	}
+	return btf;
+}
+
 static int compare_vsi_off(const void *_a, const void *_b)
 {
 	const struct btf_var_secinfo *a = _a;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index c7b399e81fce..bded210df9e8 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -59,6 +59,8 @@ struct btf_ext_header {
 
 LIBBPF_API void btf__free(struct btf *btf);
 LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API struct btf *btf__parse_elf(const char *path,
+				      struct btf_ext **btf_ext);
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 673001787cba..6ea5ce19b9e0 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -164,3 +164,8 @@ LIBBPF_0.0.3 {
 		bpf_map_freeze;
 		btf__finalize_data;
 } LIBBPF_0.0.2;
+
+LIBBPF_0.0.4 {
+	global:
+		btf__parse_elf;
+} LIBBPF_0.0.3;
-- 
cgit v1.2.3


From 58650cc47382af7d87282f53a5b508ac4bf734af Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 24 May 2019 11:58:58 -0700
Subject: bpftool: use libbpf's btf__parse_elf API

Use btf__parse_elf() API, provided by libbpf, instead of implementing
ELF parsing by itself.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/btf.c | 117 ++++--------------------------------------------
 1 file changed, 8 insertions(+), 109 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 7317438ecd9e..a22ef6587ebe 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -8,8 +8,8 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
-#include <gelf.h>
 #include <bpf.h>
+#include <libbpf.h>
 #include <linux/btf.h>
 
 #include "btf.h"
@@ -340,112 +340,6 @@ static int dump_btf_raw(const struct btf *btf,
 	return 0;
 }
 
-static bool check_btf_endianness(GElf_Ehdr *ehdr)
-{
-	static unsigned int const endian = 1;
-
-	switch (ehdr->e_ident[EI_DATA]) {
-	case ELFDATA2LSB:
-		return *(unsigned char const *)&endian == 1;
-	case ELFDATA2MSB:
-		return *(unsigned char const *)&endian == 0;
-	default:
-		return 0;
-	}
-}
-
-static int btf_load_from_elf(const char *path, struct btf **btf)
-{
-	int err = -1, fd = -1, idx = 0;
-	Elf_Data *btf_data = NULL;
-	Elf_Scn *scn = NULL;
-	Elf *elf = NULL;
-	GElf_Ehdr ehdr;
-
-	if (elf_version(EV_CURRENT) == EV_NONE) {
-		p_err("failed to init libelf for %s", path);
-		return -1;
-	}
-
-	fd = open(path, O_RDONLY);
-	if (fd < 0) {
-		p_err("failed to open %s: %s", path, strerror(errno));
-		return -1;
-	}
-
-	elf = elf_begin(fd, ELF_C_READ, NULL);
-	if (!elf) {
-		p_err("failed to open %s as ELF file", path);
-		goto done;
-	}
-	if (!gelf_getehdr(elf, &ehdr)) {
-		p_err("failed to get EHDR from %s", path);
-		goto done;
-	}
-	if (!check_btf_endianness(&ehdr)) {
-		p_err("non-native ELF endianness is not supported");
-		goto done;
-	}
-	if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
-		p_err("failed to get e_shstrndx from %s\n", path);
-		goto done;
-	}
-
-	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		GElf_Shdr sh;
-		char *name;
-
-		idx++;
-		if (gelf_getshdr(scn, &sh) != &sh) {
-			p_err("failed to get section(%d) header from %s",
-			      idx, path);
-			goto done;
-		}
-		name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
-		if (!name) {
-			p_err("failed to get section(%d) name from %s",
-			      idx, path);
-			goto done;
-		}
-		if (strcmp(name, BTF_ELF_SEC) == 0) {
-			btf_data = elf_getdata(scn, 0);
-			if (!btf_data) {
-				p_err("failed to get section(%d, %s) data from %s",
-				      idx, name, path);
-				goto done;
-			}
-			break;
-		}
-	}
-
-	if (!btf_data) {
-		p_err("%s ELF section not found in %s", BTF_ELF_SEC, path);
-		goto done;
-	}
-
-	*btf = btf__new(btf_data->d_buf, btf_data->d_size);
-	if (IS_ERR(*btf)) {
-		err = PTR_ERR(*btf);
-		*btf = NULL;
-		p_err("failed to load BTF data from %s: %s",
-		      path, strerror(err));
-		goto done;
-	}
-
-	err = 0;
-done:
-	if (err) {
-		if (*btf) {
-			btf__free(*btf);
-			*btf = NULL;
-		}
-	}
-	if (elf)
-		elf_end(elf);
-	close(fd);
-	return err;
-}
-
 static int do_dump(int argc, char **argv)
 {
 	struct btf *btf = NULL;
@@ -522,9 +416,14 @@ static int do_dump(int argc, char **argv)
 		}
 		NEXT_ARG();
 	} else if (is_prefix(src, "file")) {
-		err = btf_load_from_elf(*argv, &btf);
-		if (err)
+		btf = btf__parse_elf(*argv, NULL);
+		if (IS_ERR(btf)) {
+			err = PTR_ERR(btf);
+			btf = NULL;
+			p_err("failed to load BTF from %s: %s", 
+			      *argv, strerror(err));
 			goto done;
+		}
 		NEXT_ARG();
 	} else {
 		err = -1;
-- 
cgit v1.2.3


From 9db324314d29442c8bb8212dd40a3bb26f86c1c9 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andriin@fb.com>
Date: Fri, 24 May 2019 11:58:59 -0700
Subject: selftests/bpf: use btf__parse_elf to check presence of BTF/BTF.ext

Switch test_btf.c to rely on btf__parse_elf to check presence of BTF and
BTF.ext data, instead of implementing its own ELF parsing.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c | 71 +++++++---------------------------
 1 file changed, 13 insertions(+), 58 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 42c1ce988945..289daf54dec4 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/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;
+	bt