From 1f87dcf116adedd6b9f47258d4fdf4fa9ce74002 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 25 Feb 2021 15:43:16 -0800
Subject: selftests/bpf: Add non-BPF_LSM test for task local storage

Task local storage is enabled for tracing programs. Add two tests for
task local storage without CONFIG_BPF_LSM.

The first test stores a value in sys_enter and read it back in sys_exit.

The second test checks whether the kernel allows allocating task local
storage in exit_creds() (which it should not).

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210225234319.336131-4-songliubraving@fb.com
---
 .../selftests/bpf/prog_tests/task_local_storage.c  | 69 ++++++++++++++++++++++
 .../selftests/bpf/progs/task_local_storage.c       | 64 ++++++++++++++++++++
 .../bpf/progs/task_local_storage_exit_creds.c      | 32 ++++++++++
 3 files changed, 165 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/task_local_storage.c
 create mode 100644 tools/testing/selftests/bpf/progs/task_local_storage.c
 create mode 100644 tools/testing/selftests/bpf/progs/task_local_storage_exit_creds.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
new file mode 100644
index 000000000000..dbb7525cdd56
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#define _GNU_SOURCE         /* See feature_test_macros(7) */
+#include <unistd.h>
+#include <sys/syscall.h>   /* For SYS_xxx definitions */
+#include <sys/types.h>
+#include <test_progs.h>
+#include "task_local_storage.skel.h"
+#include "task_local_storage_exit_creds.skel.h"
+
+static void test_sys_enter_exit(void)
+{
+	struct task_local_storage *skel;
+	int err;
+
+	skel = task_local_storage__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	skel->bss->target_pid = syscall(SYS_gettid);
+
+	err = task_local_storage__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	syscall(SYS_gettid);
+	syscall(SYS_gettid);
+
+	/* 3x syscalls: 1x attach and 2x gettid */
+	ASSERT_EQ(skel->bss->enter_cnt, 3, "enter_cnt");
+	ASSERT_EQ(skel->bss->exit_cnt, 3, "exit_cnt");
+	ASSERT_EQ(skel->bss->mismatch_cnt, 0, "mismatch_cnt");
+out:
+	task_local_storage__destroy(skel);
+}
+
+static void test_exit_creds(void)
+{
+	struct task_local_storage_exit_creds *skel;
+	int err;
+
+	skel = task_local_storage_exit_creds__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	err = task_local_storage_exit_creds__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	/* trigger at least one exit_creds() */
+	if (CHECK_FAIL(system("ls > /dev/null")))
+		goto out;
+
+	/* sync rcu to make sure exit_creds() is called for "ls" */
+	kern_sync_rcu();
+	ASSERT_EQ(skel->bss->valid_ptr_count, 0, "valid_ptr_count");
+	ASSERT_NEQ(skel->bss->null_ptr_count, 0, "null_ptr_count");
+out:
+	task_local_storage_exit_creds__destroy(skel);
+}
+
+void test_task_local_storage(void)
+{
+	if (test__start_subtest("sys_enter_exit"))
+		test_sys_enter_exit();
+	if (test__start_subtest("exit_creds"))
+		test_exit_creds();
+}
diff --git a/tools/testing/selftests/bpf/progs/task_local_storage.c b/tools/testing/selftests/bpf/progs/task_local_storage.c
new file mode 100644
index 000000000000..80a0a20db88d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_local_storage.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, long);
+} enter_id SEC(".maps");
+
+#define MAGIC_VALUE 0xabcd1234
+
+pid_t target_pid = 0;
+int mismatch_cnt = 0;
+int enter_cnt = 0;
+int exit_cnt = 0;
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+{
+	struct task_struct *task;
+	long *ptr;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	ptr = bpf_task_storage_get(&enter_id, task, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!ptr)
+		return 0;
+
+	__sync_fetch_and_add(&enter_cnt, 1);
+	*ptr = MAGIC_VALUE + enter_cnt;
+
+	return 0;
+}
+
+SEC("tp_btf/sys_exit")
+int BPF_PROG(on_exit, struct pt_regs *regs, long id)
+{
+	struct task_struct *task;
+	long *ptr;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	ptr = bpf_task_storage_get(&enter_id, task, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!ptr)
+		return 0;
+
+	__sync_fetch_and_add(&exit_cnt, 1);
+	if (*ptr != MAGIC_VALUE + exit_cnt)
+		__sync_fetch_and_add(&mismatch_cnt, 1);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_local_storage_exit_creds.c b/tools/testing/selftests/bpf/progs/task_local_storage_exit_creds.c
new file mode 100644
index 000000000000..81758c0aef99
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_local_storage_exit_creds.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, __u64);
+} task_storage SEC(".maps");
+
+int valid_ptr_count = 0;
+int null_ptr_count = 0;
+
+SEC("fentry/exit_creds")
+int BPF_PROG(trace_exit_creds, struct task_struct *task)
+{
+	__u64 *ptr;
+
+	ptr = bpf_task_storage_get(&task_storage, task, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		__sync_fetch_and_add(&valid_ptr_count, 1);
+	else
+		__sync_fetch_and_add(&null_ptr_count, 1);
+	return 0;
+}
-- 
cgit v1.2.3


From c540957a4d1d13934e93e53ce3056ac4108ffc29 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 25 Feb 2021 15:43:17 -0800
Subject: selftests/bpf: Test deadlock from recursive
 bpf_task_storage_[get|delete]

Add a test with recursive bpf_task_storage_[get|delete] from fentry
programs on bpf_local_storage_lookup and bpf_local_storage_update. Without
proper deadlock prevent mechanism, this test would cause deadlock.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210225234319.336131-5-songliubraving@fb.com
---
 .../selftests/bpf/prog_tests/task_local_storage.c  | 23 +++++++
 .../selftests/bpf/progs/task_ls_recursion.c        | 70 ++++++++++++++++++++++
 2 files changed, 93 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/task_ls_recursion.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
index dbb7525cdd56..035c263aab1b 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
@@ -8,6 +8,7 @@
 #include <test_progs.h>
 #include "task_local_storage.skel.h"
 #include "task_local_storage_exit_creds.skel.h"
+#include "task_ls_recursion.skel.h"
 
 static void test_sys_enter_exit(void)
 {
@@ -60,10 +61,32 @@ out:
 	task_local_storage_exit_creds__destroy(skel);
 }
 
+static void test_recursion(void)
+{
+	struct task_ls_recursion *skel;
+	int err;
+
+	skel = task_ls_recursion__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	err = task_ls_recursion__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	/* trigger sys_enter, make sure it does not cause deadlock */
+	syscall(SYS_gettid);
+
+out:
+	task_ls_recursion__destroy(skel);
+}
+
 void test_task_local_storage(void)
 {
 	if (test__start_subtest("sys_enter_exit"))
 		test_sys_enter_exit();
 	if (test__start_subtest("exit_creds"))
 		test_exit_creds();
+	if (test__start_subtest("recursion"))
+		test_recursion();
 }
diff --git a/tools/testing/selftests/bpf/progs/task_ls_recursion.c b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
new file mode 100644
index 000000000000..564583dca7c8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, long);
+} map_a SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, long);
+} map_b SEC(".maps");
+
+SEC("fentry/bpf_local_storage_lookup")
+int BPF_PROG(on_lookup)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+
+	bpf_task_storage_delete(&map_a, task);
+	bpf_task_storage_delete(&map_b, task);
+	return 0;
+}
+
+SEC("fentry/bpf_local_storage_update")
+int BPF_PROG(on_update)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	long *ptr;
+
+	ptr = bpf_task_storage_get(&map_a, task, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		*ptr += 1;
+
+	ptr = bpf_task_storage_get(&map_b, task, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		*ptr += 1;
+
+	return 0;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+{
+	struct task_struct *task;
+	long *ptr;
+
+	task = bpf_get_current_task_btf();
+	ptr = bpf_task_storage_get(&map_a, task, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		*ptr = 200;
+
+	ptr = bpf_task_storage_get(&map_b, task, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		*ptr = 100;
+	return 0;
+}
-- 
cgit v1.2.3


From ecde60614d5ed60fde1c80b38b71582a3ea2e662 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 23 Feb 2021 16:23:01 +0000
Subject: selftest/bpf: Make xsk tests less verbose

Make the xsk tests less verbose by only printing the
essentials. Currently, it is hard to see if the tests passed or not
due to all the printouts. Move the extra printouts to a verbose
option, if further debugging is needed when a problem arises.

To run the xsk tests with verbose output:
./test_xsk.sh -v

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210223162304.7450-2-ciara.loftus@intel.com
---
 tools/testing/selftests/bpf/test_xsk.sh    | 27 ++++++++++++++++++++------
 tools/testing/selftests/bpf/xdpxceiver.c   | 31 +++++++++++++++++-------------
 tools/testing/selftests/bpf/xdpxceiver.h   | 13 ++++++++-----
 tools/testing/selftests/bpf/xsk_prereqs.sh |  9 +++------
 4 files changed, 50 insertions(+), 30 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 88a7483eaae4..f4cedf4c2718 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -71,13 +71,17 @@
 #
 # Run (full output without color-coding):
 #   sudo ./test_xsk.sh
+#
+# Run with verbose output:
+#   sudo ./test_xsk.sh -v
 
 . xsk_prereqs.sh
 
-while getopts c flag
+while getopts "cv" flag
 do
 	case "${flag}" in
 		c) colorconsole=1;;
+		v) verbose=1;;
 	esac
 done
 
@@ -95,13 +99,17 @@ NS1=af_xdp${VETH1_POSTFIX}
 MTU=1500
 
 setup_vethPairs() {
-	echo "setting up ${VETH0}: namespace: ${NS0}"
+	if [[ $verbose -eq 1 ]]; then
+	        echo "setting up ${VETH0}: namespace: ${NS0}"
+	fi
 	ip netns add ${NS1}
 	ip link add ${VETH0} type veth peer name ${VETH1}
 	if [ -f /proc/net/if_inet6 ]; then
 		echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
 	fi
-	echo "setting up ${VETH1}: namespace: ${NS1}"
+	if [[ $verbose -eq 1 ]]; then
+	        echo "setting up ${VETH1}: namespace: ${NS1}"
+	fi
 	ip link set ${VETH1} netns ${NS1}
 	ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
 	ip link set ${VETH0} mtu ${MTU}
@@ -125,7 +133,10 @@ echo "${VETH0}:${VETH1},${NS1}" > ${SPECFILE}
 
 validate_veth_spec_file
 
-echo "Spec file created: ${SPECFILE}"
+if [[ $verbose -eq 1 ]]; then
+        echo "Spec file created: ${SPECFILE}"
+	VERBOSE_ARG="-v"
+fi
 
 test_status $retval "${TEST_NAME}"
 
@@ -136,12 +147,16 @@ statusList=()
 ### TEST 1
 TEST_NAME="XSK KSELFTEST FRAMEWORK"
 
-echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Generic mode"
+if [[ $verbose -eq 1 ]]; then
+        echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Generic mode"
+fi
 vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
 
 retval=$?
 if [ $retval -eq 0 ]; then
-	echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Native mode"
+        if [[ $verbose -eq 1 ]]; then
+	        echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Native mode"
+	fi
 	vethXDPnative ${VETH0} ${VETH1} ${NS1}
 fi
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index f4a96d5ff524..8af746c9a6b6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -341,6 +341,7 @@ static struct option long_options[] = {
 	{"tear-down", no_argument, 0, 'T'},
 	{"bidi", optional_argument, 0, 'B'},
 	{"debug", optional_argument, 0, 'D'},
+	{"verbose", no_argument, 0, 'v'},
 	{"tx-pkt-count", optional_argument, 0, 'C'},
 	{0, 0, 0, 0}
 };
@@ -359,6 +360,7 @@ static void usage(const char *prog)
 	    "  -T, --tear-down      Tear down sockets by repeatedly recreating them\n"
 	    "  -B, --bidi           Bi-directional sockets test\n"
 	    "  -D, --debug          Debug mode - dump packets L2 - L5\n"
+	    "  -v, --verbose        Verbose output\n"
 	    "  -C, --tx-pkt-count=n Number of packets to send\n";
 	ksft_print_msg(str, prog);
 }
@@ -392,7 +394,7 @@ static void *nsswitchthread(void *args)
 			ksft_test_result_fail("ERROR: [%s] interface \"%s\" does not exist\n",
 					      __func__, ifdict[targs->idx]->ifname);
 		} else {
-			ksft_print_msg("Interface found: %s\n", ifdict[targs->idx]->ifname);
+			print_verbose("Interface found: %s\n", ifdict[targs->idx]->ifname);
 			targs->retptr = true;
 		}
 	}
@@ -422,7 +424,7 @@ static int validate_interfaces(void)
 			pthread_join(ns_thread, NULL);
 
 			if (targs->retptr)
-				ksft_print_msg("NS switched: %s\n", ifdict[i]->nsname);
+				print_verbose("NS switched: %s\n", ifdict[i]->nsname);
 
 			free(targs);
 		} else {
@@ -432,7 +434,7 @@ static int validate_interfaces(void)
 				    ("ERROR: interface \"%s\" does not exist\n", ifdict[i]->ifname);
 				ret = false;
 			} else {
-				ksft_print_msg("Interface found: %s\n", ifdict[i]->ifname);
+				print_verbose("Interface found: %s\n", ifdict[i]->ifname);
 			}
 		}
 	}
@@ -446,7 +448,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:q:pSNcTBDC:", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:q:pSNcTBDC:v", long_options, &option_index);
 
 		if (c == -1)
 			break;
@@ -497,6 +499,9 @@ static void parse_command_line(int argc, char **argv)
 		case 'C':
 			opt_pkt_count = atoi(optarg);
 			break;
+		case 'v':
+			opt_verbose = 1;
+			break;
 		default:
 			usage(basename(argv[0]));
 			ksft_exit_xfail();
@@ -714,7 +719,7 @@ static void worker_pkt_dump(void)
 		int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
 
 		if (payload == EOT) {
-			ksft_print_msg("End-of-transmission frame received\n");
+			print_verbose("End-of-transmission frame received\n");
 			fprintf(stdout, "---------------------------------------\n");
 			break;
 		}
@@ -746,7 +751,7 @@ static void worker_pkt_validate(void)
 			}
 
 			if (payloadseqnum == EOT) {
-				ksft_print_msg("End-of-transmission frame received: PASS\n");
+				print_verbose("End-of-transmission frame received: PASS\n");
 				sigvar = 1;
 				break;
 			}
@@ -836,7 +841,7 @@ static void *worker_testapp_validate(void *arg)
 			usleep(USLEEP_MAX);
 		}
 
-		ksft_print_msg("Interface [%s] vector [Tx]\n", ifobject->ifname);
+		print_verbose("Interface [%s] vector [Tx]\n", ifobject->ifname);
 		for (int i = 0; i < num_frames; i++) {
 			/*send EOT frame */
 			if (i == (num_frames - 1))
@@ -850,7 +855,7 @@ static void *worker_testapp_validate(void *arg)
 			gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
 		}
 
-		ksft_print_msg("Sending %d packets on interface %s\n",
+		print_verbose("Sending %d packets on interface %s\n",
 			       (opt_pkt_count - 1), ifobject->ifname);
 		tx_only_all(ifobject);
 	} else if (ifobject->fv.vector == rx) {
@@ -860,7 +865,7 @@ static void *worker_testapp_validate(void *arg)
 		if (!bidi_pass)
 			thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
 
-		ksft_print_msg("Interface [%s] vector [Rx]\n", ifobject->ifname);
+		print_verbose("Interface [%s] vector [Rx]\n", ifobject->ifname);
 		xsk_populate_fill_ring(ifobject->umem);
 
 		TAILQ_INIT(&head);
@@ -890,11 +895,11 @@ static void *worker_testapp_validate(void *arg)
 				break;
 		}
 
-		ksft_print_msg("Received %d packets on interface %s\n",
+		print_verbose("Received %d packets on interface %s\n",
 			       pkt_counter, ifobject->ifname);
 
 		if (opt_teardown)
-			ksft_print_msg("Destroying socket\n");
+			print_verbose("Destroying socket\n");
 	}
 
 	if (!opt_bidi || bidi_pass) {
@@ -914,7 +919,7 @@ static void testapp_validate(void)
 	if (opt_bidi && bidi_pass) {
 		pthread_init_mutex();
 		if (!switching_notify) {
-			ksft_print_msg("Switching Tx/Rx vectors\n");
+			print_verbose("Switching Tx/Rx vectors\n");
 			switching_notify++;
 		}
 	}
@@ -974,7 +979,7 @@ static void testapp_sockets(void)
 		pkt_counter = 0;
 		prev_pkt = -1;
 		sigvar = 0;
-		ksft_print_msg("Creating socket\n");
+		print_verbose("Creating socket\n");
 		testapp_validate();
 		opt_bidi ? bidi_pass++ : bidi_pass;
 	}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 0e9f9b7e61c2..f66f399dfb2d 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -42,6 +42,8 @@
 #define POLL_TMOUT 1000
 #define NEED_WAKEUP true
 
+#define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
+
 typedef __u32 u32;
 typedef __u16 u16;
 typedef __u8 u8;
@@ -51,11 +53,11 @@ enum TESTS {
 	ORDER_CONTENT_VALIDATE_XDP_DRV = 1,
 };
 
-u8 uut;
-u8 debug_pkt_dump;
-u32 num_frames;
-u8 switching_notify;
-u8 bidi_pass;
+static u8 uut;
+static u8 debug_pkt_dump;
+static u32 num_frames;
+static u8 switching_notify;
+static u8 bidi_pass;
 
 static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static int opt_queue;
@@ -64,6 +66,7 @@ static int opt_poll;
 static int opt_teardown;
 static int opt_bidi;
 static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
+static u8 opt_verbose;
 static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
 static u32 pkt_counter;
 static u32 prev_pkt = -1;
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index 9d54c4645127..ef8c5b31f4b6 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -82,24 +82,21 @@ clear_configs()
 {
 	if [ $(ip netns show | grep $3 &>/dev/null; echo $?;) == 0 ]; then
 		[ $(ip netns exec $3 ip link show $2 &>/dev/null; echo $?;) == 0 ] &&
-			{ echo "removing link $1:$2"; ip netns exec $3 ip link del $2; }
-		echo "removing ns $3"
+			{ ip netns exec $3 ip link del $2; }
 		ip netns del $3
 	fi
 	#Once we delete a veth pair node, the entire veth pair is removed,
 	#this is just to be cautious just incase the NS does not exist then
 	#veth node inside NS won't get removed so we explicitly remove it
 	[ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] &&
-		{ echo "removing link $1"; ip link del $1; }
+		{ ip link del $1; }
 	if [ -f ${SPECFILE} ]; then
-		echo "removing spec file:" ${SPECFILE}
 		rm -f ${SPECFILE}
 	fi
 }
 
 cleanup_exit()
 {
-	echo "cleaning up..."
 	clear_configs $1 $2 $3
 }
 
@@ -131,5 +128,5 @@ execxdpxceiver()
 			copy[$index]=${!current}
 		done
 
-	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS}
+	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS} ${VERBOSE_ARG}
 }
-- 
cgit v1.2.3


From d2b0dfd5d1f94fe74ed580b5a1d5fdb5bf11f2fb Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Tue, 23 Feb 2021 16:23:02 +0000
Subject: selftests/bpf: Expose and rename debug argument

Launching xdpxceiver with -D enables what was formerly know as 'debug'
mode. Rename this mode to 'dump-pkts' as it better describes the
behavior enabled by the option. New usage:

./xdpxceiver .. -D
or
./xdpxceiver .. --dump-pkts

Also make it possible to pass this flag to the app via the test_xsk.sh
shell script like so:

./test_xsk.sh -D

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210223162304.7450-3-ciara.loftus@intel.com
---
 tools/testing/selftests/bpf/test_xsk.sh    | 10 +++++++++-
 tools/testing/selftests/bpf/xdpxceiver.c   |  6 +++---
 tools/testing/selftests/bpf/xsk_prereqs.sh |  3 ++-
 3 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index f4cedf4c2718..dbb129a36606 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -74,14 +74,18 @@
 #
 # Run with verbose output:
 #   sudo ./test_xsk.sh -v
+#
+# Run and dump packet contents:
+#   sudo ./test_xsk.sh -D
 
 . xsk_prereqs.sh
 
-while getopts "cv" flag
+while getopts "cvD" flag
 do
 	case "${flag}" in
 		c) colorconsole=1;;
 		v) verbose=1;;
+		D) dump_pkts=1;;
 	esac
 done
 
@@ -138,6 +142,10 @@ if [[ $verbose -eq 1 ]]; then
 	VERBOSE_ARG="-v"
 fi
 
+if [[ $dump_pkts -eq 1 ]]; then
+	DUMP_PKTS_ARG="-D"
+fi
+
 test_status $retval "${TEST_NAME}"
 
 ## START TESTS
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 8af746c9a6b6..506423201197 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -58,7 +58,7 @@
  * - Rx thread verifies if all 10k packets were received and delivered in-order,
  *   and have the right content
  *
- * Enable/disable debug mode:
+ * Enable/disable packet dump mode:
  * --------------------------
  * To enable L2 - L4 headers and payload dump of each packet on STDOUT, add
  * parameter -D to params array in test_xsk.sh, i.e. params=("-S" "-D")
@@ -340,7 +340,7 @@ static struct option long_options[] = {
 	{"copy", no_argument, 0, 'c'},
 	{"tear-down", no_argument, 0, 'T'},
 	{"bidi", optional_argument, 0, 'B'},
-	{"debug", optional_argument, 0, 'D'},
+	{"dump-pkts", optional_argument, 0, 'D'},
 	{"verbose", no_argument, 0, 'v'},
 	{"tx-pkt-count", optional_argument, 0, 'C'},
 	{0, 0, 0, 0}
@@ -359,7 +359,7 @@ static void usage(const char *prog)
 	    "  -c, --copy           Force copy mode\n"
 	    "  -T, --tear-down      Tear down sockets by repeatedly recreating them\n"
 	    "  -B, --bidi           Bi-directional sockets test\n"
-	    "  -D, --debug          Debug mode - dump packets L2 - L5\n"
+	    "  -D, --dump-pkts      Dump packets L2 - L5\n"
 	    "  -v, --verbose        Verbose output\n"
 	    "  -C, --tx-pkt-count=n Number of packets to send\n";
 	ksft_print_msg(str, prog);
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index ef8c5b31f4b6..da93575d757a 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -128,5 +128,6 @@ execxdpxceiver()
 			copy[$index]=${!current}
 		done
 
-	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS} ${VERBOSE_ARG}
+	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS} ${VERBOSE_ARG} \
+		${DUMP_PKTS_ARG}
 }
-- 
cgit v1.2.3


From d3e3bf5b4c673e79c5a11608f53d4e0059a7ec79 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Tue, 23 Feb 2021 16:23:03 +0000
Subject: selftests/bpf: Restructure xsk selftests

Prior to this commit individual xsk tests were launched from the
shell script 'test_xsk.sh'. When adding a new test type, two new test
configurations had to be added to this file - one for each of the
supported XDP 'modes' (skb or drv). Should zero copy support be added to
the xsk selftest framework in the future, three new test configurations
would need to be added for each new test type. Each new test type also
typically requires new CLI arguments for the xdpxceiver program.

This commit aims to reduce the overhead of adding new tests, by launching
the test configurations from within the xdpxceiver program itself, using
simple loops. Every test is run every time the C program is executed. Many
of the CLI arguments can be removed as a result.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210223162304.7450-4-ciara.loftus@intel.com
---
 tools/testing/selftests/bpf/test_xsk.sh    | 112 +--------------
 tools/testing/selftests/bpf/xdpxceiver.c   | 218 ++++++++++++++++++-----------
 tools/testing/selftests/bpf/xdpxceiver.h   |  33 +++--
 tools/testing/selftests/bpf/xsk_prereqs.sh |  24 +---
 4 files changed, 159 insertions(+), 228 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index dbb129a36606..56d4474e2c83 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -152,117 +152,9 @@ test_status $retval "${TEST_NAME}"
 
 statusList=()
 
-### TEST 1
-TEST_NAME="XSK KSELFTEST FRAMEWORK"
+TEST_NAME="XSK KSELFTESTS"
 
-if [[ $verbose -eq 1 ]]; then
-        echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Generic mode"
-fi
-vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
-
-retval=$?
-if [ $retval -eq 0 ]; then
-        if [[ $verbose -eq 1 ]]; then
-	        echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Native mode"
-	fi
-	vethXDPnative ${VETH0} ${VETH1} ${NS1}
-fi
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 2
-TEST_NAME="SKB NOPOLL"
-
-vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
-
-params=("-S")
-execxdpxceiver params
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 3
-TEST_NAME="SKB POLL"
-
-vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
-
-params=("-S" "-p")
-execxdpxceiver params
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 4
-TEST_NAME="DRV NOPOLL"
-
-vethXDPnative ${VETH0} ${VETH1} ${NS1}
-
-params=("-N")
-execxdpxceiver params
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 5
-TEST_NAME="DRV POLL"
-
-vethXDPnative ${VETH0} ${VETH1} ${NS1}
-
-params=("-N" "-p")
-execxdpxceiver params
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 6
-TEST_NAME="SKB SOCKET TEARDOWN"
-
-vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
-
-params=("-S" "-T")
-execxdpxceiver params
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 7
-TEST_NAME="DRV SOCKET TEARDOWN"
-
-vethXDPnative ${VETH0} ${VETH1} ${NS1}
-
-params=("-N" "-T")
-execxdpxceiver params
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 8
-TEST_NAME="SKB BIDIRECTIONAL SOCKETS"
-
-vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
-
-params=("-S" "-B")
-execxdpxceiver params
-
-retval=$?
-test_status $retval "${TEST_NAME}"
-statusList+=($retval)
-
-### TEST 9
-TEST_NAME="DRV BIDIRECTIONAL SOCKETS"
-
-vethXDPnative ${VETH0} ${VETH1} ${NS1}
-
-params=("-N" "-B")
-execxdpxceiver params
+execxdpxceiver
 
 retval=$?
 test_status $retval "${TEST_NAME}"
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 506423201197..e7913444518d 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -18,12 +18,7 @@
  * These selftests test AF_XDP SKB and Native/DRV modes using veth
  * Virtual Ethernet interfaces.
  *
- * The following tests are run:
- *
- * 1. AF_XDP SKB mode
- *    Generic mode XDP is driver independent, used when the driver does
- *    not have support for XDP. Works on any netdevice using sockets and
- *    generic XDP path. XDP hook from netif_receive_skb().
+ * For each mode, the following tests are run:
  *    a. nopoll - soft-irq processing
  *    b. poll - using poll() syscall
  *    c. Socket Teardown
@@ -34,17 +29,6 @@
  *       completion rings on each socket, tx/rx in both directions. Only nopoll
  *       mode is used
  *
- * 2. AF_XDP DRV/Native mode
- *    Works on any netdevice with XDP_REDIRECT support, driver dependent. Processes
- *    packets before SKB allocation. Provides better performance than SKB. Driver
- *    hook available just after DMA of buffer descriptor.
- *    a. nopoll
- *    b. poll
- *    c. Socket Teardown
- *    d. Bi-directional sockets
- *    - Only copy mode is supported because veth does not currently support
- *      zero-copy mode
- *
  * Total tests: 8
  *
  * Flow:
@@ -98,17 +82,23 @@ typedef __u16 __sum16;
 
 static void __exit_with_error(int error, const char *file, const char *func, int line)
 {
-	ksft_test_result_fail
-	    ("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, strerror(error));
-	ksft_exit_xfail();
+	if (configured_mode == TEST_MODE_UNCONFIGURED) {
+		ksft_exit_fail_msg
+		("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, strerror(error));
+	} else {
+		ksft_test_result_fail
+		("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, strerror(error));
+		ksft_exit_xfail();
+	}
 }
 
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
 
 #define print_ksft_result(void)\
-	(ksft_test_result_pass("PASS: %s %s %s%s\n", uut ? "DRV" : "SKB", opt_poll ? "POLL" :\
-			       "NOPOLL", opt_teardown ? "Socket Teardown" : "",\
-			       opt_bidi ? "Bi-directional Sockets" : ""))
+	(ksft_test_result_pass("PASS: %s %s %s%s\n", configured_mode ? "DRV" : "SKB",\
+			       test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\
+			       test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\
+			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : ""))
 
 static void pthread_init_mutex(void)
 {
@@ -311,10 +301,10 @@ static int xsk_configure_socket(struct ifobject *ifobject)
 	cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
 	cfg.libbpf_flags = 0;
-	cfg.xdp_flags = opt_xdp_flags;
-	cfg.bind_flags = opt_xdp_bind_flags;
+	cfg.xdp_flags = xdp_flags;
+	cfg.bind_flags = xdp_bind_flags;
 
-	if (!opt_bidi) {
+	if (test_type != TEST_TYPE_BIDI) {
 		rxr = (ifobject->fv.vector == rx) ? &ifobject->xsk->rx : NULL;
 		txr = (ifobject->fv.vector == tx) ? &ifobject->xsk->tx : NULL;
 	} else {
@@ -334,12 +324,6 @@ static int xsk_configure_socket(struct ifobject *ifobject)
 static struct option long_options[] = {
 	{"interface", required_argument, 0, 'i'},
 	{"queue", optional_argument, 0, 'q'},
-	{"poll", no_argument, 0, 'p'},
-	{"xdp-skb", no_argument, 0, 'S'},
-	{"xdp-native", no_argument, 0, 'N'},
-	{"copy", no_argument, 0, 'c'},
-	{"tear-down", no_argument, 0, 'T'},
-	{"bidi", optional_argument, 0, 'B'},
 	{"dump-pkts", optional_argument, 0, 'D'},
 	{"verbose", no_argument, 0, 'v'},
 	{"tx-pkt-count", optional_argument, 0, 'C'},
@@ -353,12 +337,6 @@ static void usage(const char *prog)
 	    "  Options:\n"
 	    "  -i, --interface      Use interface\n"
 	    "  -q, --queue=n        Use queue n (default 0)\n"
-	    "  -p, --poll           Use poll syscall\n"
-	    "  -S, --xdp-skb=n      Use XDP SKB mode\n"
-	    "  -N, --xdp-native=n   Enforce XDP DRV (native) mode\n"
-	    "  -c, --copy           Force copy mode\n"
-	    "  -T, --tear-down      Tear down sockets by repeatedly recreating them\n"
-	    "  -B, --bidi           Bi-directional sockets test\n"
 	    "  -D, --dump-pkts      Dump packets L2 - L5\n"
 	    "  -v, --verbose        Verbose output\n"
 	    "  -C, --tx-pkt-count=n Number of packets to send\n";
@@ -448,7 +426,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:q:pSNcTBDC:v", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:q:DC:v", long_options, &option_index);
 
 		if (c == -1)
 			break;
@@ -471,28 +449,6 @@ static void parse_command_line(int argc, char **argv)
 		case 'q':
 			opt_queue = atoi(optarg);
 			break;
-		case 'p':
-			opt_poll = 1;
-			break;
-		case 'S':
-			opt_xdp_flags |= XDP_FLAGS_SKB_MODE;
-			opt_xdp_bind_flags |= XDP_COPY;
-			uut = ORDER_CONTENT_VALIDATE_XDP_SKB;
-			break;
-		case 'N':
-			opt_xdp_flags |= XDP_FLAGS_DRV_MODE;
-			opt_xdp_bind_flags |= XDP_COPY;
-			uut = ORDER_CONTENT_VALIDATE_XDP_DRV;
-			break;
-		case 'c':
-			opt_xdp_bind_flags |= XDP_COPY;
-			break;
-		case 'T':
-			opt_teardown = 1;
-			break;
-		case 'B':
-			opt_bidi = 1;
-			break;
 		case 'D':
 			debug_pkt_dump = 1;
 			break;
@@ -508,6 +464,11 @@ static void parse_command_line(int argc, char **argv)
 		}
 	}
 
+	if (!opt_pkt_count) {
+		print_verbose("No tx-pkt-count specified, using default %u\n", DEFAULT_PKT_CNT);
+		opt_pkt_count = DEFAULT_PKT_CNT;
+	}
+
 	if (!validate_interfaces()) {
 		usage(basename(argv[0]));
 		ksft_exit_xfail();
@@ -659,7 +620,7 @@ static void tx_only_all(struct ifobject *ifobject)
 	while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) {
 		int batch_size = get_batch_size(pkt_cnt);
 
-		if (opt_poll) {
+		if (test_type == TEST_TYPE_POLL) {
 			ret = poll(fds, 1, POLL_TMOUT);
 			if (ret <= 0)
 				continue;
@@ -883,7 +844,7 @@ static void *worker_testapp_validate(void *arg)
 		pthread_mutex_unlock(&sync_mutex);
 
 		while (1) {
-			if (opt_poll) {
+			if (test_type == TEST_TYPE_POLL) {
 				ret = poll(fds, 1, POLL_TMOUT);
 				if (ret <= 0)
 					continue;
@@ -898,11 +859,11 @@ static void *worker_testapp_validate(void *arg)
 		print_verbose("Received %d packets on interface %s\n",
 			       pkt_counter, ifobject->ifname);
 
-		if (opt_teardown)
+		if (test_type == TEST_TYPE_TEARDOWN)
 			print_verbose("Destroying socket\n");
 	}
 
-	if (!opt_bidi || bidi_pass) {
+	if ((test_type != TEST_TYPE_BIDI) || bidi_pass) {
 		xsk_socket__delete(ifobject->xsk->xsk);
 		(void)xsk_umem__delete(ifobject->umem->umem);
 	}
@@ -912,11 +873,12 @@ static void *worker_testapp_validate(void *arg)
 static void testapp_validate(void)
 {
 	struct timespec max_wait = { 0, 0 };
+	bool bidi = test_type == TEST_TYPE_BIDI;
 
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, THREAD_STACK);
 
-	if (opt_bidi && bidi_pass) {
+	if ((test_type == TEST_TYPE_BIDI) && bidi_pass) {
 		pthread_init_mutex();
 		if (!switching_notify) {
 			print_verbose("Switching Tx/Rx vectors\n");
@@ -927,10 +889,10 @@ static void testapp_validate(void)
 	pthread_mutex_lock(&sync_mutex);
 
 	/*Spawn RX thread */
-	if (!opt_bidi || !bidi_pass) {
+	if (!bidi || !bidi_pass) {
 		if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[1]))
 			exit_with_error(errno);
-	} else if (opt_bidi && bidi_pass) {
+	} else if (bidi && bidi_pass) {
 		/*switch Tx/Rx vectors */
 		ifdict[0]->fv.vector = rx;
 		if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[0]))
@@ -947,10 +909,10 @@ static void testapp_validate(void)
 	pthread_mutex_unlock(&sync_mutex);
 
 	/*Spawn TX thread */
-	if (!opt_bidi || !bidi_pass) {
+	if (!bidi || !bidi_pass) {
 		if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[0]))
 			exit_with_error(errno);
-	} else if (opt_bidi && bidi_pass) {
+	} else if (bidi && bidi_pass) {
 		/*switch Tx/Rx vectors */
 		ifdict[1]->fv.vector = tx;
 		if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[1]))
@@ -969,19 +931,20 @@ static void testapp_validate(void)
 		free(pkt_buf);
 	}
 
-	if (!opt_teardown && !opt_bidi)
+	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi)
 		print_ksft_result();
 }
 
 static void testapp_sockets(void)
 {
-	for (int i = 0; i < (opt_teardown ? MAX_TEARDOWN_ITER : MAX_BIDI_ITER); i++) {
+	for (int i = 0; i < ((test_type == TEST_TYPE_TEARDOWN) ? MAX_TEARDOWN_ITER : MAX_BIDI_ITER);
+	     i++) {
 		pkt_counter = 0;
 		prev_pkt = -1;
 		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
-		opt_bidi ? bidi_pass++ : bidi_pass;
+		test_type == TEST_TYPE_BIDI ? bidi_pass++ : bidi_pass;
 	}
 
 	print_ksft_result();
@@ -1008,6 +971,98 @@ static void init_iface_config(struct ifaceconfigobj *ifaceconfig)
 	ifdict[1]->src_port = ifaceconfig->dst_port;
 }
 
+static void *nsdisablemodethread(void *args)
+{
+	struct targs *targs = args;
+
+	targs->retptr = false;
+
+	if (switch_namespace(targs->idx)) {
+		targs->retptr = bpf_set_link_xdp_fd(ifdict[targs->idx]->ifindex, -1, targs->flags);
+	} else {
+		targs->retptr = errno;
+		print_verbose("Failed to switch namespace to %s\n", ifdict[targs->idx]->nsname);
+	}
+
+	pthread_exit(NULL);
+}
+
+static void disable_xdp_mode(int mode)
+{
+	int err = 0;
+	__u32 flags = XDP_FLAGS_UPDATE_IF_NOEXIST | mode;
+	char *mode_str = mode & XDP_FLAGS_SKB_MODE ? "skb" : "drv";
+
+	for (int i = 0; i < MAX_INTERFACES; i++) {
+		if (strcmp(ifdict[i]->nsname, "")) {
+			struct targs *targs;
+
+			targs = malloc(sizeof(*targs));
+			memset(targs, 0, sizeof(*targs));
+			if (!targs)
+				exit_with_error(errno);
+
+			targs->idx = i;
+			targs->flags = flags;
+			if (pthread_create(&ns_thread, NULL, nsdisablemodethread, targs))
+				exit_with_error(errno);
+
+			pthread_join(ns_thread, NULL);
+			err = targs->retptr;
+			free(targs);
+		} else {
+			err = bpf_set_link_xdp_fd(ifdict[i]->ifindex, -1, flags);
+		}
+
+		if (err) {
+			print_verbose("Failed to disable %s mode on interface %s\n",
+						mode_str, ifdict[i]->ifname);
+			exit_with_error(err);
+		}
+
+		print_verbose("Disabled %s mode for interface: %s\n", mode_str, ifdict[i]->ifname);
+		configured_mode = mode & XDP_FLAGS_SKB_MODE ? TEST_MODE_DRV : TEST_MODE_SKB;
+	}
+}
+
+static void run_pkt_test(int mode, int type)
+{
+	test_type = type;
+
+	/* reset defaults after potential previous test */
+	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+	pkt_counter = 0;
+	switching_notify = 0;
+	bidi_pass = 0;
+	prev_pkt = -1;
+	ifdict[0]->fv.vector = tx;
+	ifdict[1]->fv.vector = rx;
+
+	switch (mode) {
+	case (TEST_MODE_SKB):
+		if (configured_mode == TEST_MODE_DRV)
+			disable_xdp_mode(XDP_FLAGS_DRV_MODE);
+		xdp_flags |= XDP_FLAGS_SKB_MODE;
+		break;
+	case (TEST_MODE_DRV):
+		if (configured_mode == TEST_MODE_SKB)
+			disable_xdp_mode(XDP_FLAGS_SKB_MODE);
+		xdp_flags |= XDP_FLAGS_DRV_MODE;
+		break;
+	default:
+		break;
+	}
+
+	pthread_init_mutex();
+
+	if ((test_type != TEST_TYPE_TEARDOWN) && (test_type != TEST_TYPE_BIDI))
+		testapp_validate();
+	else
+		testapp_sockets();
+
+	pthread_destroy_mutex();
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
@@ -1021,6 +1076,7 @@ int main(int argc, char **argv)
 	const char *IP2 = "192.168.100.161";
 	u16 UDP_DST_PORT = 2020;
 	u16 UDP_SRC_PORT = 2121;
+	int i, j;
 
 	ifaceconfig = malloc(sizeof(struct ifaceconfigobj));
 	memcpy(ifaceconfig->dst_mac, MAC1, ETH_ALEN);
@@ -1046,24 +1102,18 @@ int main(int argc, char **argv)
 
 	init_iface_config(ifaceconfig);
 
-	pthread_init_mutex();
+	disable_xdp_mode(XDP_FLAGS_DRV_MODE);
 
-	ksft_set_plan(1);
+	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
-	if (!opt_teardown && !opt_bidi) {
-		testapp_validate();
-	} else if (opt_teardown && opt_bidi) {
-		ksft_test_result_fail("ERROR: parameters -T and -B cannot be used together\n");
-		ksft_exit_xfail();
-	} else {
-		testapp_sockets();
+	for (i = 0; i < TEST_MODE_MAX; i++) {
+		for (j = 0; j < TEST_TYPE_MAX; j++)
+			run_pkt_test(i, j);
 	}
 
 	for (int i = 0; i < MAX_INTERFACES; i++)
 		free(ifdict[i]);
 
-	pthread_destroy_mutex();
-
 	ksft_exit_pass();
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index f66f399dfb2d..e05703f661f8 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -41,6 +41,7 @@
 #define BATCH_SIZE 64
 #define POLL_TMOUT 1000
 #define NEED_WAKEUP true
+#define DEFAULT_PKT_CNT 10000
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
 
@@ -48,28 +49,37 @@ typedef __u32 u32;
 typedef __u16 u16;
 typedef __u8 u8;
 
-enum TESTS {
-	ORDER_CONTENT_VALIDATE_XDP_SKB = 0,
-	ORDER_CONTENT_VALIDATE_XDP_DRV = 1,
+enum TEST_MODES {
+	TEST_MODE_UNCONFIGURED = -1,
+	TEST_MODE_SKB,
+	TEST_MODE_DRV,
+	TEST_MODE_MAX
 };
 
-static u8 uut;
+enum TEST_TYPES {
+	TEST_TYPE_NOPOLL,
+	TEST_TYPE_POLL,
+	TEST_TYPE_TEARDOWN,
+	TEST_TYPE_BIDI,
+	TEST_TYPE_MAX
+};
+
+static int configured_mode = TEST_MODE_UNCONFIGURED;
 static u8 debug_pkt_dump;
 static u32 num_frames;
 static u8 switching_notify;
 static u8 bidi_pass;
+static int test_type;
 
-static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static int opt_queue;
 static int opt_pkt_count;
-static int opt_poll;
-static int opt_teardown;
-static int opt_bidi;
-static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
 static u8 opt_verbose;
+
+static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY;
 static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
 static u32 pkt_counter;
-static u32 prev_pkt = -1;
+static long prev_pkt = -1;
 static int sigvar;
 
 struct xsk_umem_info {
@@ -140,8 +150,9 @@ pthread_t t0, t1, ns_thread;
 pthread_attr_t attr;
 
 struct targs {
-	bool retptr;
+	u8 retptr;
 	int idx;
+	u32 flags;
 };
 
 TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index da93575d757a..dac1c5f78752 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -105,29 +105,7 @@ validate_ip_utility()
 	[ ! $(type -P ip) ] && { echo "'ip' not found. Skipping tests."; test_exit $ksft_skip 1; }
 }
 
-vethXDPgeneric()
-{
-	ip link set dev $1 xdpdrv off
-	ip netns exec $3 ip link set dev $2 xdpdrv off
-}
-
-vethXDPnative()
-{
-	ip link set dev $1 xdpgeneric off
-	ip netns exec $3 ip link set dev $2 xdpgeneric off
-}
-
 execxdpxceiver()
 {
-	local -a 'paramkeys=("${!'"$1"'[@]}")' copy
-	paramkeysstr=${paramkeys[*]}
-
-	for index in $paramkeysstr;
-		do
-			current=$1"[$index]"
-			copy[$index]=${!current}
-		done
-
-	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS} ${VERBOSE_ARG} \
-		${DUMP_PKTS_ARG}
+	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} -C ${NUMPKTS} ${VERBOSE_ARG} ${DUMP_PKTS_ARG}
 }
-- 
cgit v1.2.3


From b267e5a458a719f3f5eaaaebe87c5f4a13584832 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus@intel.com>
Date: Tue, 23 Feb 2021 16:23:04 +0000
Subject: selftests/bpf: Introduce xsk statistics tests

This commit introduces a range of tests to the xsk testsuite
for validating xsk statistics.

A new test type called 'stats' is added. Within it there are
four sub-tests. Each test configures a scenario which should
trigger the given error statistic. The test passes if the statistic
is successfully incremented.

The four statistics for which tests have been created are:
1. rx dropped
Increase the UMEM frame headroom to a value which results in
insufficient space in the rx buffer for both the packet and the headroom.
2. tx invalid
Set the 'len' field of tx descriptors to an invalid value (umem frame
size + 1).
3. rx ring full
Reduce the size of the RX ring to a fraction of the fill ring size.
4. fill queue empty
Do not populate the fill queue and then try to receive pkts.

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210223162304.7450-5-ciara.loftus@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 137 +++++++++++++++++++++++++++----
 tools/testing/selftests/bpf/xdpxceiver.h |  13 +++
 2 files changed, 136 insertions(+), 14 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index e7913444518d..8b0f7fdd9003 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -28,8 +28,21 @@
  *       Configure sockets as bi-directional tx/rx sockets, sets up fill and
  *       completion rings on each socket, tx/rx in both directions. Only nopoll
  *       mode is used
+ *    e. Statistics
+ *       Trigger some error conditions and ensure that the appropriate statistics
+ *       are incremented. Within this test, the following statistics are tested:
+ *       i.   rx dropped
+ *            Increase the UMEM frame headroom to a value which results in
+ *            insufficient space in the rx buffer for both the packet and the headroom.
+ *       ii.  tx invalid
+ *            Set the 'len' field of tx descriptors to an invalid value (umem frame
+ *            size + 1).
+ *       iii. rx ring full
+ *            Reduce the size of the RX ring to a fraction of the fill ring size.
+ *       iv.  fill queue empty
+ *            Do not populate the fill queue and then try to receive pkts.
  *
- * Total tests: 8
+ * Total tests: 10
  *
  * Flow:
  * -----
@@ -95,10 +108,11 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
 
 #define print_ksft_result(void)\
-	(ksft_test_result_pass("PASS: %s %s %s%s\n", configured_mode ? "DRV" : "SKB",\
+	(ksft_test_result_pass("PASS: %s %s %s%s%s\n", configured_mode ? "DRV" : "SKB",\
 			       test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\
 			       test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\
-			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : ""))
+			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\
+			       test_type == TEST_TYPE_STATS ? "Stats" : ""))
 
 static void pthread_init_mutex(void)
 {
@@ -260,13 +274,20 @@ static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
 static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
 {
 	int ret;
+	struct xsk_umem_config cfg = {
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
+		.frame_headroom = frame_headroom,
+		.flags = XSK_UMEM__DEFAULT_FLAGS
+	};
 
 	data->umem = calloc(1, sizeof(struct xsk_umem_info));
 	if (!data->umem)
 		exit_with_error(errno);
 
 	ret = xsk_umem__create(&data->umem->umem, buffer, size,
-			       &data->umem->fq, &data->umem->cq, NULL);
+			       &data->umem->fq, &data->umem->cq, &cfg);
 	if (ret)
 		exit_with_error(ret);
 
@@ -298,7 +319,7 @@ static int xsk_configure_socket(struct ifobject *ifobject)
 		exit_with_error(errno);
 
 	ifobject->xsk->umem = ifobject->umem;
-	cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+	cfg.rx_size = rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = xdp_flags;
@@ -565,6 +586,8 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
 {
 	u32 idx;
 	unsigned int i;
+	bool tx_invalid_test = stat_test_type == STAT_TEST_TX_INVALID;
+	u32 len = tx_invalid_test ? XSK_UMEM__DEFAULT_FRAME_SIZE + 1 : PKT_SIZE;
 
 	while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < batch_size)
 		complete_tx_only(xsk, batch_size);
@@ -573,11 +596,16 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
 		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
 
 		tx_desc->addr = (*frameptr + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
-		tx_desc->len = PKT_SIZE;
+		tx_desc->len = len;
 	}
 
 	xsk_ring_prod__submit(&xsk->tx, batch_size);
-	xsk->outstanding_tx += batch_size;
+	if (!tx_invalid_test) {
+		xsk->outstanding_tx += batch_size;
+	} else {
+		if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
+			kick_tx(xsk);
+	}
 	*frameptr += batch_size;
 	*frameptr %= num_frames;
 	complete_tx_only(xsk, batch_size);
@@ -689,6 +717,48 @@ static void worker_pkt_dump(void)
 	}
 }
 
+static void worker_stats_validate(struct ifobject *ifobject)
+{
+	struct xdp_statistics stats;
+	socklen_t optlen;
+	int err;
+	struct xsk_socket *xsk = stat_test_type == STAT_TEST_TX_INVALID ?
+							ifdict[!ifobject->ifdict_index]->xsk->xsk :
+							ifobject->xsk->xsk;
+	int fd = xsk_socket__fd(xsk);
+	unsigned long xsk_stat = 0, expected_stat = opt_pkt_count;
+
+	sigvar = 0;
+
+	optlen = sizeof(stats);
+	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
+	if (err)
+		return;
+
+	if (optlen == sizeof(struct xdp_statistics)) {
+		switch (stat_test_type) {
+		case STAT_TEST_RX_DROPPED:
+			xsk_stat = stats.rx_dropped;
+			break;
+		case STAT_TEST_TX_INVALID:
+			xsk_stat = stats.tx_invalid_descs;
+			break;
+		case STAT_TEST_RX_FULL:
+			xsk_stat = stats.rx_ring_full;
+			expected_stat -= RX_FULL_RXQSIZE;
+			break;
+		case STAT_TEST_RX_FILL_EMPTY:
+			xsk_stat = stats.rx_fill_ring_empty_descs;
+			break;
+		default:
+			break;
+		}
+
+		if (xsk_stat == expected_stat)
+			sigvar = 1;
+	}
+}
+
 static void worker_pkt_validate(void)
 {
 	u32 payloadseqnum = -2;
@@ -827,7 +897,8 @@ static void *worker_testapp_validate(void *arg)
 			thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
 
 		print_verbose("Interface [%s] vector [Rx]\n", ifobject->ifname);
-		xsk_populate_fill_ring(ifobject->umem);
+		if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
+			xsk_populate_fill_ring(ifobject->umem);
 
 		TAILQ_INIT(&head);
 		if (debug_pkt_dump) {
@@ -849,15 +920,21 @@ static void *worker_testapp_validate(void *arg)
 				if (ret <= 0)
 					continue;
 			}
-			rx_pkt(ifobject->xsk, fds);
-			worker_pkt_validate();
+
+			if (test_type != TEST_TYPE_STATS) {
+				rx_pkt(ifobject->xsk, fds);
+				worker_pkt_validate();
+			} else {
+				worker_stats_validate(ifobject);
+			}
 
 			if (sigvar)
 				break;
 		}
 
-		print_verbose("Received %d packets on interface %s\n",
-			       pkt_counter, ifobject->ifname);
+		if (test_type != TEST_TYPE_STATS)
+			print_verbose("Received %d packets on interface %s\n",
+				pkt_counter, ifobject->ifname);
 
 		if (test_type == TEST_TYPE_TEARDOWN)
 			print_verbose("Destroying socket\n");
@@ -931,7 +1008,7 @@ static void testapp_validate(void)
 		free(pkt_buf);
 	}
 
-	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi)
+	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !(test_type == TEST_TYPE_STATS))
 		print_ksft_result();
 }
 
@@ -950,6 +1027,32 @@ static void testapp_sockets(void)
 	print_ksft_result();
 }
 
+static void testapp_stats(void)
+{
+	for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) {
+		stat_test_type = i;
+
+		/* reset defaults */
+		rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+		frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
+
+		switch (stat_test_type) {
+		case STAT_TEST_RX_DROPPED:
+			frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE -
+						XDP_PACKET_HEADROOM - 1;
+			break;
+		case STAT_TEST_RX_FULL:
+			rxqsize = RX_FULL_RXQSIZE;
+			break;
+		default:
+			break;
+		}
+		testapp_validate();
+	}
+
+	print_ksft_result();
+}
+
 static void init_iface_config(struct ifaceconfigobj *ifaceconfig)
 {
 	/*Init interface0 */
@@ -1037,6 +1140,10 @@ static void run_pkt_test(int mode, int type)
 	prev_pkt = -1;
 	ifdict[0]->fv.vector = tx;
 	ifdict[1]->fv.vector = rx;
+	sigvar = 0;
+	stat_test_type = -1;
+	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+	frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 
 	switch (mode) {
 	case (TEST_MODE_SKB):
@@ -1055,7 +1162,9 @@ static void run_pkt_test(int mode, int type)
 
 	pthread_init_mutex();
 
-	if ((test_type != TEST_TYPE_TEARDOWN) && (test_type != TEST_TYPE_BIDI))
+	if (test_type == TEST_TYPE_STATS)
+		testapp_stats();
+	else if ((test_type != TEST_TYPE_TEARDOWN) && (test_type != TEST_TYPE_BIDI))
 		testapp_validate();
 	else
 		testapp_sockets();
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e05703f661f8..30314ef305c2 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -42,6 +42,7 @@
 #define POLL_TMOUT 1000
 #define NEED_WAKEUP true
 #define DEFAULT_PKT_CNT 10000
+#define RX_FULL_RXQSIZE 32
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
 
@@ -61,9 +62,18 @@ enum TEST_TYPES {
 	TEST_TYPE_POLL,
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
+	TEST_TYPE_STATS,
 	TEST_TYPE_MAX
 };
 
+enum STAT_TEST_TYPES {
+	STAT_TEST_RX_DROPPED,
+	STAT_TEST_TX_INVALID,
+	STAT_TEST_RX_FULL,
+	STAT_TEST_RX_FILL_EMPTY,
+	STAT_TEST_TYPE_MAX
+};
+
 static int configured_mode = TEST_MODE_UNCONFIGURED;
 static u8 debug_pkt_dump;
 static u32 num_frames;
@@ -81,6 +91,9 @@ static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
 static u32 pkt_counter;
 static long prev_pkt = -1;
 static int sigvar;
+static int stat_test_type;
+static u32 rxqsize;
+static u32 frame_headroom;
 
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
-- 
cgit v1.2.3


From ae8b8332fbb512f53bf50ff6a7586dd0f90ed18a Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Tue, 23 Feb 2021 10:49:30 -0800
Subject: sock_map: Rename skb_parser and skb_verdict

These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER
and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact
they are only used for TCP. And save the name 'skb_verdict' for
general use later.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Lorenz Bauer <lmb@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com
---
 include/linux/skmsg.h                              |  8 +--
 net/core/skmsg.c                                   | 14 ++---
 net/core/sock_map.c                                | 60 +++++++++++-----------
 .../selftests/bpf/prog_tests/sockmap_listen.c      |  8 +--
 .../selftests/bpf/progs/test_sockmap_listen.c      |  4 +-
 5 files changed, 47 insertions(+), 47 deletions(-)

(limited to 'tools/testing')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e0de45527bb6..d9f6ec4a9cf2 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -56,8 +56,8 @@ struct sk_msg {
 
 struct sk_psock_progs {
 	struct bpf_prog			*msg_parser;
-	struct bpf_prog			*skb_parser;
-	struct bpf_prog			*skb_verdict;
+	struct bpf_prog			*stream_parser;
+	struct bpf_prog			*stream_verdict;
 };
 
 enum sk_psock_state_bits {
@@ -443,8 +443,8 @@ static inline int psock_replace_prog(struct bpf_prog **pprog,
 static inline void psock_progs_drop(struct sk_psock_progs *progs)
 {
 	psock_set_prog(&progs->msg_parser, NULL);
-	psock_set_prog(&progs->skb_parser, NULL);
-	psock_set_prog(&progs->skb_verdict, NULL);
+	psock_set_prog(&progs->stream_parser, NULL);
+	psock_set_prog(&progs->stream_verdict, NULL);
 }
 
 int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 409258367bea..35f9caa3b125 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -691,9 +691,9 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 	write_lock_bh(&sk->sk_callback_lock);
 	sk_psock_restore_proto(sk, psock);
 	rcu_assign_sk_user_data(sk, NULL);
-	if (psock->progs.skb_parser)
+	if (psock->progs.stream_parser)
 		sk_psock_stop_strp(sk, psock);
-	else if (psock->progs.skb_verdict)
+	else if (psock->progs.stream_verdict)
 		sk_psock_stop_verdict(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);
 	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
@@ -803,7 +803,7 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 	int ret = __SK_PASS;
 
 	rcu_read_lock();
-	prog = READ_ONCE(psock->progs.skb_verdict);
+	prog = READ_ONCE(psock->progs.stream_verdict);
 	if (likely(prog)) {
 		/* We skip full set_owner_r here because if we do a SK_PASS
 		 * or SK_DROP we can skip skb memory accounting and use the
@@ -895,7 +895,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		goto out;
 	}
 	skb_set_owner_r(skb, sk);
-	prog = READ_ONCE(psock->progs.skb_verdict);
+	prog = READ_ONCE(psock->progs.stream_verdict);
 	if (likely(prog)) {
 		skb_dst_drop(skb);
 		skb_bpf_redirect_clear(skb);
@@ -919,7 +919,7 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
 	int ret = skb->len;
 
 	rcu_read_lock();
-	prog = READ_ONCE(psock->progs.skb_parser);
+	prog = READ_ONCE(psock->progs.stream_parser);
 	if (likely(prog)) {
 		skb->sk = psock->sk;
 		ret = sk_psock_bpf_run(psock, prog, skb);
@@ -982,7 +982,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 static void sk_psock_done_strp(struct sk_psock *psock)
 {
 	/* Parser has been stopped */
-	if (psock->progs.skb_parser)
+	if (psock->progs.stream_parser)
 		strp_done(&psock->strp);
 }
 #else
@@ -1015,7 +1015,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
 		goto out;
 	}
 	skb_set_owner_r(skb, sk);
-	prog = READ_ONCE(psock->progs.skb_verdict);
+	prog = READ_ONCE(psock->progs.stream_verdict);
 	if (likely(prog)) {
 		skb_dst_drop(skb);
 		skb_bpf_redirect_clear(skb);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index dbfcd7006338..69785070f02d 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -148,9 +148,9 @@ static void sock_map_del_link(struct sock *sk,
 			struct bpf_map *map = link->map;
 			struct bpf_stab *stab = container_of(map, struct bpf_stab,
 							     map);
-			if (psock->saved_data_ready && stab->progs.skb_parser)
+			if (psock->saved_data_ready && stab->progs.stream_parser)
 				strp_stop = true;
-			if (psock->saved_data_ready && stab->progs.skb_verdict)
+			if (psock->saved_data_ready && stab->progs.stream_verdict)
 				verdict_stop = true;
 			list_del(&link->list);
 			sk_psock_free_link(link);
@@ -224,23 +224,23 @@ out:
 static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 			 struct sock *sk)
 {
-	struct bpf_prog *msg_parser, *skb_parser, *skb_verdict;
+	struct bpf_prog *msg_parser, *stream_parser, *stream_verdict;
 	struct sk_psock *psock;
 	int ret;
 
-	skb_verdict = READ_ONCE(progs->skb_verdict);
-	if (skb_verdict) {
-		skb_verdict = bpf_prog_inc_not_zero(skb_verdict);
-		if (IS_ERR(skb_verdict))
-			return PTR_ERR(skb_verdict);
+	stream_verdict = READ_ONCE(progs->stream_verdict);
+	if (stream_verdict) {
+		stream_verdict = bpf_prog_inc_not_zero(stream_verdict);
+		if (IS_ERR(stream_verdict))
+			return PTR_ERR(stream_verdict);
 	}
 
-	skb_parser = READ_ONCE(progs->skb_parser);
-	if (skb_parser) {
-		skb_parser = bpf_prog_inc_not_zero(skb_parser);
-		if (IS_ERR(skb_parser)) {
-			ret = PTR_ERR(skb_parser);
-			goto out_put_skb_verdict;
+	stream_parser = READ_ONCE(progs->stream_parser);
+	if (stream_parser) {
+		stream_parser = bpf_prog_inc_not_zero(stream_parser);
+		if (IS_ERR(stream_parser)) {
+			ret = PTR_ERR(stream_parser);
+			goto out_put_stream_verdict;
 		}
 	}
 
@@ -249,7 +249,7 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 		msg_parser = bpf_prog_inc_not_zero(msg_parser);
 		if (IS_ERR(msg_parser)) {
 			ret = PTR_ERR(msg_parser);
-			goto out_put_skb_parser;
+			goto out_put_stream_parser;
 		}
 	}
 
@@ -261,8 +261,8 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 
 	if (psock) {
 		if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) ||
-		    (skb_parser  && READ_ONCE(psock->progs.skb_parser)) ||
-		    (skb_verdict && READ_ONCE(psock->progs.skb_verdict))) {
+		    (stream_parser  && READ_ONCE(psock->progs.stream_parser)) ||
+		    (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) {
 			sk_psock_put(sk, psock);
 			ret = -EBUSY;
 			goto out_progs;
@@ -283,15 +283,15 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 		goto out_drop;
 
 	write_lock_bh(&sk->sk_callback_lock);
-	if (skb_parser && skb_verdict && !psock->saved_data_ready) {
+	if (stream_parser && stream_verdict && !psock->saved_data_ready) {
 		ret = sk_psock_init_strp(sk, psock);
 		if (ret)
 			goto out_unlock_drop;
-		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
-		psock_set_prog(&psock->progs.skb_parser, skb_parser);
+		psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
+		psock_set_prog(&psock->progs.stream_parser, stream_parser);
 		sk_psock_start_strp(sk, psock);
-	} else if (!skb_parser && skb_verdict && !psock->saved_data_ready) {
-		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
+	} else if (!stream_parser && stream_verdict && !psock->saved_data_ready) {
+		psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
 		sk_psock_start_verdict(sk,psock);
 	}
 	write_unlock_bh(&sk->sk_callback_lock);
@@ -303,12 +303,12 @@ out_drop:
 out_progs:
 	if (msg_parser)
 		bpf_prog_put(msg_parser);
-out_put_skb_parser:
-	if (skb_parser)
-		bpf_prog_put(skb_parser);
-out_put_skb_verdict:
-	if (skb_verdict)
-		bpf_prog_put(skb_verdict);
+out_put_stream_parser:
+	if (stream_parser)
+		bpf_prog_put(stream_parser);
+out_put_stream_verdict:
+	if (stream_verdict)
+		bpf_prog_put(stream_verdict);
 	return ret;
 }
 
@@ -1459,11 +1459,11 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
 		break;
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 	case BPF_SK_SKB_STREAM_PARSER:
-		pprog = &progs->skb_parser;
+		pprog = &progs->stream_parser;
 		break;
 #endif
 	case BPF_SK_SKB_STREAM_VERDICT:
-		pprog = &progs->skb_verdict;
+		pprog = &progs->stream_verdict;
 		break;
 	default:
 		return -EOPNOTSUPP;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index d7d65a700799..c26e6bf05e49 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1014,8 +1014,8 @@ static void test_skb_redir_to_connected(struct test_sockmap_listen *skel,
 					struct bpf_map *inner_map, int family,
 					int sotype)
 {
-	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
-	int parser = bpf_program__fd(skel->progs.prog_skb_parser);
+	int verdict = bpf_program__fd(skel->progs.prog_stream_verdict);
+	int parser = bpf_program__fd(skel->progs.prog_stream_parser);
 	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
 	int sock_map = bpf_map__fd(inner_map);
 	int err;
@@ -1125,8 +1125,8 @@ static void test_skb_redir_to_listening(struct test_sockmap_listen *skel,
 					struct bpf_map *inner_map, int family,
 					int sotype)
 {
-	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
-	int parser = bpf_program__fd(skel->progs.prog_skb_parser);
+	int verdict = bpf_program__fd(skel->progs.prog_stream_verdict);
+	int parser = bpf_program__fd(skel->progs.prog_stream_parser);
 	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
 	int sock_map = bpf_map__fd(inner_map);
 	int err;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index a3a366c57ce1..fa221141e9c1 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -31,13 +31,13 @@ struct {
 static volatile bool test_sockmap; /* toggled by user-space */
 
 SEC("sk_skb/stream_parser")
-int prog_skb_parser(struct __sk_buff *skb)
+int prog_stream_parser(struct __sk_buff *skb)
 {
 	return skb->len;
 }
 
 SEC("sk_skb/stream_verdict")
-int prog_skb_verdict(struct __sk_buff *skb)
+int prog_stream_verdict(struct __sk_buff *skb)
 {
 	unsigned int *count;
 	__u32 zero = 0;
-- 
cgit v1.2.3


From 2854436612c4d2606c9246ce2976ab6634276337 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Thu, 25 Feb 2021 16:19:47 +0000
Subject: selftests/bpf: Propagate error code of the command to vmtest.sh

When vmtest.sh ran a command in a VM, it did not record or propagate the
error code of the command. This made the script less "script-able". The
script now saves the error code of the said command in a file in the VM,
copies the file back to the host and (when available) uses this error
code instead of its own.

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210225161947.1778590-1-kpsingh@kernel.org
---
 tools/testing/selftests/bpf/vmtest.sh | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 26ae8d0b6ce3..22554894db99 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -17,6 +17,9 @@ KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vm
 KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/latest.config"
 INDEX_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/INDEX"
 NUM_COMPILE_JOBS="$(nproc)"
+LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
+LOG_FILE="${LOG_FILE_BASE}.log"
+EXIT_STATUS_FILE="${LOG_FILE_BASE}.exit_status"
 
 usage()
 {
@@ -146,7 +149,6 @@ update_init_script()
 	local init_script_dir="${OUTPUT_DIR}/${MOUNT_DIR}/etc/rcS.d"
 	local init_script="${init_script_dir}/S50-startup"
 	local command="$1"
-	local log_file="$2"
 
 	mount_image
 
@@ -163,11 +165,16 @@ EOF
 	sudo bash -c "cat >${init_script}" <<EOF
 #!/bin/bash
 
+# Have a default value in the exit status file
+# incase the VM is forcefully stopped.
+echo "130" > "/root/${EXIT_STATUS_FILE}"
+
 {
 	cd /root/bpf
 	echo ${command}
 	stdbuf -oL -eL ${command}
-} 2>&1 | tee /root/${log_file}
+	echo "\$?" > "/root/${EXIT_STATUS_FILE}"
+} 2>&1 | tee "/root/${LOG_FILE}"
 poweroff -f
 EOF
 
@@ -221,10 +228,12 @@ EOF
 copy_logs()
 {
 	local mount_dir="${OUTPUT_DIR}/${MOUNT_DIR}"
-	local log_file="${mount_dir}/root/$1"
+	local log_file="${mount_dir}/root/${LOG_FILE}"
+	local exit_status_file="${mount_dir}/root/${EXIT_STATUS_FILE}"
 
 	mount_image
 	sudo cp ${log_file} "${OUTPUT_DIR}"
+	sudo cp ${exit_status_file} "${OUTPUT_DIR}"
 	sudo rm -f ${log_file}
 	unmount_image
 }
@@ -263,7 +272,6 @@ main()
 {
 	local script_dir="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"
 	local kernel_checkout=$(realpath "${script_dir}"/../../../../)
-	local log_file="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S.log")"
 	# By default the script searches for the kernel in the checkout directory but
 	# it also obeys environment variables O= and KBUILD_OUTPUT=
 	local kernel_bzimage="${kernel_checkout}/${X86_BZIMAGE}"
@@ -347,19 +355,23 @@ main()
 	fi
 
 	update_selftests "${kernel_checkout}" "${make_command}"
-	update_init_script "${command}" "${log_file}"
+	update_init_script "${command}"
 	run_vm "${kernel_bzimage}"
-	copy_logs "${log_file}"
-	echo "Logs saved in ${OUTPUT_DIR}/${log_file}"
+	copy_logs
+	echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}"
 }
 
 catch()
 {
 	local exit_code=$1
+	local exit_status_file="${OUTPUT_DIR}/${EXIT_STATUS_FILE}"
 	# This is just a cleanup and the directory may
 	# have already been unmounted. So, don't let this
 	# clobber the error code we intend to return.
 	unmount_image || true
+	if [[ -f "${exit_status_file}" ]]; then
+		exit_code="$(cat ${exit_status_file})"
+	fi
 	exit ${exit_code}
 }
 
-- 
cgit v1.2.3


From 86fd166575c38c17ecd3a6b8fb9c64fa19871486 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Wed, 24 Feb 2021 12:14:45 +0100
Subject: selftests/bpf: Copy extras in out-of-srctree builds

Building selftests in a separate directory like this:

    make O="$BUILD" -C tools/testing/selftests/bpf

and then running:

    cd "$BUILD" && ./test_progs -t btf

causes all the non-flavored btf_dump_test_case_*.c tests to fail,
because these files are not copied to where test_progs expects to find
them.

Fix by not skipping EXT-COPY when the original $(OUTPUT) is not empty
(lib.mk sets it to $(shell pwd) in that case) and using rsync instead
of cp: cp fails because e.g. urandom_read is being copied into itself,
and rsync simply skips such cases. rsync is already used by kselftests
and therefore is not a new dependency.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210224111445.102342-1-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/Makefile | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 044bfdcf5b74..a81af15e4ded 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -382,11 +382,12 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 	$$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@)
 	$(Q)$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
 
-# only copy extra resources if in flavored build
+# non-flavored in-srctree builds receive special treatment, in particular, we
+# do not need to copy extra resources (see e.g. test_btf_dump_case())
 $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT)
-ifneq ($2,)
+ifneq ($2:$(OUTPUT),:$(shell pwd))
 	$$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
-	$(Q)cp -a $$^ $(TRUNNER_OUTPUT)/
+	$(Q)rsync -aq $$^ $(TRUNNER_OUTPUT)/
 endif
 
 $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
-- 
cgit v1.2.3


From 9de7f0fdab326a37c9f741f0f6c0f1cbc320a5ab Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 26 Feb 2021 12:49:33 -0800
Subject: selftests/bpf: Add hashmap test for bpf_for_each_map_elem() helper

A test case is added for hashmap and percpu hashmap. The test
also exercises nested bpf_for_each_map_elem() calls like
    bpf_prog:
      bpf_for_each_map_elem(func1)
    func1:
      bpf_for_each_map_elem(func2)
    func2:

  $ ./test_progs -n 45
  #45/1 hash_map:OK
  #45 for_each:OK
  Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210226204933.3885657-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/for_each.c  | 73 +++++++++++++++++
 .../selftests/bpf/progs/for_each_hash_map_elem.c   | 95 ++++++++++++++++++++++
 tools/testing/selftests/bpf/test_progs.h           | 11 +++
 3 files changed, 179 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/for_each.c
 create mode 100644 tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
new file mode 100644
index 000000000000..aa847cd9f71f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "for_each_hash_map_elem.skel.h"
+
+static unsigned int duration;
+
+static void test_hash_map(void)
+{
+	int i, err, hashmap_fd, max_entries, percpu_map_fd;
+	struct for_each_hash_map_elem *skel;
+	__u64 *percpu_valbuf = NULL;
+	__u32 key, num_cpus, retval;
+	__u64 val;
+
+	skel = for_each_hash_map_elem__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_hash_map_elem__open_and_load"))
+		return;
+
+	hashmap_fd = bpf_map__fd(skel->maps.hashmap);
+	max_entries = bpf_map__max_entries(skel->maps.hashmap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i + 1;
+		err = bpf_map_update_elem(hashmap_fd, &key, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "map_update"))
+			goto out;
+	}
+
+	num_cpus = bpf_num_possible_cpus();
+	percpu_map_fd = bpf_map__fd(skel->maps.percpu_map);
+	percpu_valbuf = malloc(sizeof(__u64) * num_cpus);
+	if (!ASSERT_OK_PTR(percpu_valbuf, "percpu_valbuf"))
+		goto out;
+
+	key = 1;
+	for (i = 0; i < num_cpus; i++)
+		percpu_valbuf[i] = i + 1;
+	err = bpf_map_update_elem(percpu_map_fd, &key, percpu_valbuf, BPF_ANY);
+	if (!ASSERT_OK(err, "percpu_map_update"))
+		goto out;
+
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access),
+				1, &pkt_v4, sizeof(pkt_v4), NULL, NULL,
+				&retval, &duration);
+	if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n",
+		  err, errno, retval))
+		goto out;
+
+	ASSERT_EQ(skel->bss->hashmap_output, 4, "hashmap_output");
+	ASSERT_EQ(skel->bss->hashmap_elems, max_entries, "hashmap_elems");
+
+	key = 1;
+	err = bpf_map_lookup_elem(hashmap_fd, &key, &val);
+	ASSERT_ERR(err, "hashmap_lookup");
+
+	ASSERT_EQ(skel->bss->percpu_called, 1, "percpu_called");
+	ASSERT_LT(skel->bss->cpu, num_cpus, "num_cpus");
+	ASSERT_EQ(skel->bss->percpu_map_elems, 1, "percpu_map_elems");
+	ASSERT_EQ(skel->bss->percpu_key, 1, "percpu_key");
+	ASSERT_EQ(skel->bss->percpu_val, skel->bss->cpu + 1, "percpu_val");
+	ASSERT_EQ(skel->bss->percpu_output, 100, "percpu_output");
+out:
+	free(percpu_valbuf);
+	for_each_hash_map_elem__destroy(skel);
+}
+
+void test_for_each(void)
+{
+	if (test__start_subtest("hash_map"))
+		test_hash_map();
+}
diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c
new file mode 100644
index 000000000000..913dd91aafff
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 3);
+	__type(key, __u32);
+	__type(value, __u64);
+} hashmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} percpu_map SEC(".maps");
+
+struct callback_ctx {
+	struct __sk_buff *ctx;
+	int input;
+	int output;
+};
+
+static __u64
+check_hash_elem(struct bpf_map *map, __u32 *key, __u64 *val,
+		struct callback_ctx *data)
+{
+	struct __sk_buff *skb = data->ctx;
+	__u32 k;
+	__u64 v;
+
+	if (skb) {
+		k = *key;
+		v = *val;
+		if (skb->len == 10000 && k == 10 && v == 10)
+			data->output = 3; /* impossible path */
+		else
+			data->output = 4;
+	} else {
+		data->output = data->input;
+		bpf_map_delete_elem(map, key);
+	}
+
+	return 0;
+}
+
+__u32 cpu = 0;
+__u32 percpu_called = 0;
+__u32 percpu_key = 0;
+__u64 percpu_val = 0;
+int percpu_output = 0;
+
+static __u64
+check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val,
+		  struct callback_ctx *unused)
+{
+	struct callback_ctx data;
+
+	percpu_called++;
+	cpu = bpf_get_smp_processor_id();
+	percpu_key = *key;
+	percpu_val = *val;
+
+	data.ctx = 0;
+	data.input = 100;
+	data.output = 0;
+	bpf_for_each_map_elem(&hashmap, check_hash_elem, &data, 0);
+	percpu_output = data.output;
+
+	return 0;
+}
+
+int hashmap_output = 0;
+int hashmap_elems = 0;
+int percpu_map_elems = 0;
+
+SEC("classifier")
+int test_pkt_access(struct __sk_buff *skb)
+{
+	struct callback_ctx data;
+
+	data.ctx = skb;
+	data.input = 10;
+	data.output = 0;
+	hashmap_elems = bpf_for_each_map_elem(&hashmap, check_hash_elem, &data, 0);
+	hashmap_output = data.output;
+
+	percpu_map_elems = bpf_for_each_map_elem(&percpu_map, check_percpu_elem,
+						 (void *)0, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index f7c2fd89d01a..e87c8546230e 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -152,6 +152,17 @@ extern int test__join_cgroup(const char *path);
 	___ok;								\
 })
 
+#define ASSERT_LT(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act < ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld >= expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
 #define ASSERT_STREQ(actual, expected, name) ({				\
 	static int duration = 0;					\
 	const char *___act = actual;					\
-- 
cgit v1.2.3


From 6b9e3331347ee9e84fe5c71d3eba7ec204f9bb25 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 26 Feb 2021 12:49:34 -0800
Subject: selftests/bpf: Add arraymap test for bpf_for_each_map_elem() helper

A test is added for arraymap and percpu arraymap. The test also
exercises the early return for the helper which does not
traverse all elements.
    $ ./test_progs -n 45
    #45/1 hash_map:OK
    #45/2 array_map:OK
    #45 for_each:OK
    Summary: 1/2 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210226204934.3885756-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/for_each.c  | 57 ++++++++++++++++++++
 .../selftests/bpf/progs/for_each_array_map_elem.c  | 61 ++++++++++++++++++++++
 2 files changed, 118 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/for_each_array_map_elem.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index aa847cd9f71f..68eb12a287d4 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -3,6 +3,7 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "for_each_hash_map_elem.skel.h"
+#include "for_each_array_map_elem.skel.h"
 
 static unsigned int duration;
 
@@ -66,8 +67,64 @@ out:
 	for_each_hash_map_elem__destroy(skel);
 }
 
+static void test_array_map(void)
+{
+	__u32 key, num_cpus, max_entries, retval;
+	int i, arraymap_fd, percpu_map_fd, err;
+	struct for_each_array_map_elem *skel;
+	__u64 *percpu_valbuf = NULL;
+	__u64 val, expected_total;
+
+	skel = for_each_array_map_elem__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_array_map_elem__open_and_load"))
+		return;
+
+	arraymap_fd = bpf_map__fd(skel->maps.arraymap);
+	expected_total = 0;
+	max_entries = bpf_map__max_entries(skel->maps.arraymap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i + 1;
+		/* skip the last iteration for expected total */
+		if (i != max_entries - 1)
+			expected_total += val;
+		err = bpf_map_update_elem(arraymap_fd, &key, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "map_update"))
+			goto out;
+	}
+
+	num_cpus = bpf_num_possible_cpus();
+	percpu_map_fd = bpf_map__fd(skel->maps.percpu_map);
+	percpu_valbuf = malloc(sizeof(__u64) * num_cpus);
+	if (!ASSERT_OK_PTR(percpu_valbuf, "percpu_valbuf"))
+		goto out;
+
+	key = 0;
+	for (i = 0; i < num_cpus; i++)
+		percpu_valbuf[i] = i + 1;
+	err = bpf_map_update_elem(percpu_map_fd, &key, percpu_valbuf, BPF_ANY);
+	if (!ASSERT_OK(err, "percpu_map_update"))
+		goto out;
+
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access),
+				1, &pkt_v4, sizeof(pkt_v4), NULL, NULL,
+				&retval, &duration);
+	if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n",
+		  err, errno, retval))
+		goto out;
+
+	ASSERT_EQ(skel->bss->arraymap_output, expected_total, "array_output");
+	ASSERT_EQ(skel->bss->cpu + 1, skel->bss->percpu_val, "percpu_val");
+
+out:
+	free(percpu_valbuf);
+	for_each_array_map_elem__destroy(skel);
+}
+
 void test_for_each(void)
 {
 	if (test__start_subtest("hash_map"))
 		test_hash_map();
+	if (test__start_subtest("array_map"))
+		test_array_map();
 }
diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c
new file mode 100644
index 000000000000..75e8e1069fe7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 3);
+	__type(key, __u32);
+	__type(value, __u64);
+} arraymap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} percpu_map SEC(".maps");
+
+struct callback_ctx {
+	int output;
+};
+
+static __u64
+check_array_elem(struct bpf_map *map, __u32 *key, __u64 *val,
+		 struct callback_ctx *data)
+{
+	data->output += *val;
+	if (*key == 1)
+		return 1; /* stop the iteration */
+	return 0;
+}
+
+__u32 cpu = 0;
+__u64 percpu_val = 0;
+
+static __u64
+check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val,
+		  struct callback_ctx *data)
+{
+	cpu = bpf_get_smp_processor_id();
+	percpu_val = *val;
+	return 0;
+}
+
+u32 arraymap_output = 0;
+
+SEC("classifier")
+int test_pkt_access(struct __sk_buff *skb)
+{
+	struct callback_ctx data;
+
+	data.output = 0;
+	bpf_for_each_map_elem(&arraymap, check_array_elem, &data, 0);
+	arraymap_output = data.output;
+
+	bpf_for_each_map_elem(&percpu_map, check_percpu_elem, (void *)0, 0);
+	return 0;
+}
-- 
cgit v1.2.3


From 86a35af628e539f7ae9796f1984761e8d3232ac0 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 26 Feb 2021 14:38:10 -0800
Subject: selftests/bpf: Add a verifier scale test with unknown bounded loop

The original bcc pull request https://github.com/iovisor/bcc/pull/3270 exposed
a verifier failure with Clang 12/13 while Clang 4 works fine.

Further investigation exposed two issues:

  Issue 1: LLVM may generate code which uses less refined value. The issue is
           fixed in LLVM patch: https://reviews.llvm.org/D97479

  Issue 2: Spills with initial value 0 are marked as precise which makes later
           state pruning less effective. This is my rough initial analysis and
           further investigation is needed to find how to improve verifier
           pruning in such cases.

With the above LLVM patch, for the new loop6.c test, which has smaller loop
bound compared to original test, I got:

  $ test_progs -s -n 10/16
  ...
  stack depth 64
  processed 390735 insns (limit 1000000) max_states_per_insn 87
      total_states 8658 peak_states 964 mark_read 6
  #10/16 loop6.o:OK

Use the original loop bound, i.e., commenting out "#define WORKAROUND", I got:

  $ test_progs -s -n 10/16
  ...
  BPF program is too large. Processed 1000001 insn
  stack depth 64
  processed 1000001 insns (limit 1000000) max_states_per_insn 91
      total_states 23176 peak_states 5069 mark_read 6
  ...
  #10/16 loop6.o:FAIL

The purpose of this patch is to provide a regression test for the above LLVM fix
and also provide a test case for further analyzing the verifier pruning issue.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Zhenwei Pi <pizhenwei@bytedance.com>
Link: https://lore.kernel.org/bpf/20210226223810.236472-1-yhs@fb.com
---
 tools/testing/selftests/bpf/README.rst             | 39 +++++++++
 .../selftests/bpf/prog_tests/bpf_verif_scale.c     |  1 +
 tools/testing/selftests/bpf/progs/loop6.c          | 99 ++++++++++++++++++++++
 3 files changed, 139 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/loop6.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index fd148b8410fa..dbc8f6cc5c67 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -111,6 +111,45 @@ available in 10.0.1. The patch is available in llvm 11.0.0 trunk.
 
 __  https://reviews.llvm.org/D78466
 
+bpf_verif_scale/loop6.o test failure with Clang 12
+==================================================
+
+With Clang 12, the following bpf_verif_scale test failed:
+  * ``bpf_verif_scale/loop6.o``
+
+The verifier output looks like
+
+.. code-block:: c
+
+  R1 type=ctx expected=fp
+  The sequence of 8193 jumps is too complex.
+
+The reason is compiler generating the following code
+
+.. code-block:: c
+
+  ;       for (i = 0; (i < VIRTIO_MAX_SGS) && (i < num); i++) {
+      14:       16 05 40 00 00 00 00 00 if w5 == 0 goto +64 <LBB0_6>
+      15:       bc 51 00 00 00 00 00 00 w1 = w5
+      16:       04 01 00 00 ff ff ff ff w1 += -1
+      17:       67 05 00 00 20 00 00 00 r5 <<= 32
+      18:       77 05 00 00 20 00 00 00 r5 >>= 32
+      19:       a6 01 01 00 05 00 00 00 if w1 < 5 goto +1 <LBB0_4>
+      20:       b7 05 00 00 06 00 00 00 r5 = 6
+  00000000000000a8 <LBB0_4>:
+      21:       b7 02 00 00 00 00 00 00 r2 = 0
+      22:       b7 01 00 00 00 00 00 00 r1 = 0
+  ;       for (i = 0; (i < VIRTIO_MAX_SGS) && (i < num); i++) {
+      23:       7b 1a e0 ff 00 00 00 00 *(u64 *)(r10 - 32) = r1
+      24:       7b 5a c0 ff 00 00 00 00 *(u64 *)(r10 - 64) = r5
+
+Note that insn #15 has w1 = w5 and w1 is refined later but
+r5(w5) is eventually saved on stack at insn #24 for later use.
+This cause later verifier failure. The bug has been `fixed`__ in
+Clang 13.
+
+__  https://reviews.llvm.org/D97479
+
 BPF CO-RE-based tests and Clang version
 =======================================
 
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 e698ee6bb6c2..3d002c245d2b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -76,6 +76,7 @@ void test_bpf_verif_scale(void)
 		{ "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 		{ "loop4.o", BPF_PROG_TYPE_SCHED_CLS },
 		{ "loop5.o", BPF_PROG_TYPE_SCHED_CLS },
+		{ "loop6.o", BPF_PROG_TYPE_KPROBE },
 
 		/* partial unroll. 19k insn in a loop.
 		 * Total program size 20.8k insn.
diff --git a/tools/testing/selftests/bpf/progs/loop6.c b/tools/testing/selftests/bpf/progs/loop6.c
new file mode 100644
index 000000000000..2a7141ac1656
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/loop6.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ptrace.h>
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* typically virtio scsi has max SGs of 6 */
+#define VIRTIO_MAX_SGS	6
+
+/* Verifier will fail with SG_MAX = 128. The failure can be
+ * workarounded with a smaller SG_MAX, e.g. 10.
+ */
+#define WORKAROUND
+#ifdef WORKAROUND
+#define SG_MAX		10
+#else
+/* typically virtio blk has max SEG of 128 */
+#define SG_MAX		128
+#endif
+
+#define SG_CHAIN	0x01UL
+#define SG_END		0x02UL
+
+struct scatterlist {
+	unsigned long   page_link;
+	unsigned int    offset;
+	unsigned int    length;
+};
+
+#define sg_is_chain(sg)		((sg)->page_link & SG_CHAIN)
+#define sg_is_last(sg)		((sg)->page_link & SG_END)
+#define sg_chain_ptr(sg)	\
+	((struct scatterlist *) ((sg)->page_link & ~(SG_CHAIN | SG_END)))
+
+static inline struct scatterlist *__sg_next(struct scatterlist *sgp)
+{
+	struct scatterlist sg;
+
+	bpf_probe_read_kernel(&sg, sizeof(sg), sgp);
+	if (sg_is_last(&sg))
+		return NULL;
+
+	sgp++;
+
+	bpf_probe_read_kernel(&sg, sizeof(sg), sgp);
+	if (sg_is_chain(&sg))
+		sgp = sg_chain_ptr(&sg);
+
+	return sgp;
+}
+
+static inline struct scatterlist *get_sgp(struct scatterlist **sgs, int i)
+{
+	struct scatterlist *sgp;
+
+	bpf_probe_read_kernel(&sgp, sizeof(sgp), sgs + i);
+	return sgp;
+}
+
+int config = 0;
+int result = 0;
+
+SEC("kprobe/virtqueue_add_sgs")
+BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs,
+	   unsigned int out_sgs, unsigned int in_sgs)
+{
+	struct scatterlist *sgp = NULL;
+	__u64 length1 = 0, length2 = 0;
+	unsigned int i, n, len;
+
+	if (config != 0)
+		return 0;
+
+	for (i = 0; (i < VIRTIO_MAX_SGS) && (i < out_sgs); i++) {
+		for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX);
+		     sgp = __sg_next(sgp)) {
+			bpf_probe_read_kernel(&len, sizeof(len), &sgp->length);
+			length1 += len;
+			n++;
+		}
+	}
+
+	for (i = 0; (i < VIRTIO_MAX_SGS) && (i < in_sgs); i++) {
+		for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX);
+		     sgp = __sg_next(sgp)) {
+			bpf_probe_read_kernel(&len, sizeof(len), &sgp->length);
+			length2 += len;
+			n++;
+		}
+	}
+
+	config = 1;
+	result = length2 - length1;
+	return 0;
+}
-- 
cgit v1.2.3


From eea154a852e827c003215f7beed3e10f05471a86 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Fri, 26 Feb 2021 21:22:51 +0100
Subject: selftests/bpf: Use the 25th bit in the "invalid BTF_INFO" test

The bit being checked by this test is no longer reserved after
introducing BTF_KIND_FLOAT, so use the next one instead.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210226202256.116518-6-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/prog_tests/btf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 6a7ee7420701..c29406736138 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -1903,7 +1903,7 @@ static struct btf_raw_test raw_tests[] = {
 	.raw_types = {
 		/* int */				/* [1] */
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
-		BTF_TYPE_ENC(0, 0x10000000, 4),
+		BTF_TYPE_ENC(0, 0x20000000, 4),
 		BTF_END_RAW,
 	},
 	.str_sec = "",
-- 
cgit v1.2.3


From 7e72aad3a15c06e40e3ccd2352e5010e978f1acf Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Fri, 26 Feb 2021 21:22:53 +0100
Subject: selftest/bpf: Add BTF_KIND_FLOAT tests

Test the good variants as well as the potential malformed ones.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210226202256.116518-8-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/btf_helpers.c    |   4 +
 tools/testing/selftests/bpf/prog_tests/btf.c | 131 +++++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_btf.h       |   3 +
 3 files changed, 138 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c
index 48f90490f922..b692e6ead9b5 100644
--- a/tools/testing/selftests/bpf/btf_helpers.c
+++ b/tools/testing/selftests/bpf/btf_helpers.c
@@ -23,6 +23,7 @@ static const char * const btf_kind_str_mapping[] = {
 	[BTF_KIND_FUNC_PROTO]	= "FUNC_PROTO",
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
+	[BTF_KIND_FLOAT]	= "FLOAT",
 };
 
 static const char *btf_kind_str(__u16 kind)
@@ -173,6 +174,9 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
 		}
 		break;
 	}
+	case BTF_KIND_FLOAT:
+		fprintf(out, " size=%u", t->size);
+		break;
 	default:
 		break;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index c29406736138..11d98d3cf949 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3531,6 +3531,136 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 
+{
+	.descr = "float test #1, well-formed",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+								/* [1] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),		/* [2] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 4),		/* [3] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 8),		/* [4] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 12),		/* [5] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 16),		/* [6] */
+		BTF_STRUCT_ENC(NAME_TBD, 5, 48),		/* [7] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+		BTF_MEMBER_ENC(NAME_TBD, 3, 32),
+		BTF_MEMBER_ENC(NAME_TBD, 4, 64),
+		BTF_MEMBER_ENC(NAME_TBD, 5, 128),
+		BTF_MEMBER_ENC(NAME_TBD, 6, 256),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0_Float16\0float\0double\0_Float80\0long_double"
+		    "\0floats\0a\0b\0c\0d\0e"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "float_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 48,
+	.key_type_id = 1,
+	.value_type_id = 7,
+	.max_entries = 1,
+},
+{
+	.descr = "float test #2, invalid vlen",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+								/* [1] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 1), 4),
+								/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0float"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "float_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 2,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "vlen != 0",
+},
+{
+	.descr = "float test #3, invalid kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+								/* [1] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FLOAT, 1, 0), 4),
+								/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0float"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "float_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 2,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+{
+	.descr = "float test #4, member does not fit",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+								/* [1] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 4),		/* [2] */
+		BTF_STRUCT_ENC(NAME_TBD, 1, 2),			/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0float\0floats\0x"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "float_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 3,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Member exceeds struct_size",
+},
+{
+	.descr = "float test #5, member is not properly aligned",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+								/* [1] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 4),		/* [2] */
+		BTF_STRUCT_ENC(NAME_TBD, 1, 8),			/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, 8),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0float\0floats\0x"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "float_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 3,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Member is not properly aligned",
+},
+{
+	.descr = "float test #6, invalid size",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+								/* [1] */
+		BTF_TYPE_FLOAT_ENC(NAME_TBD, 6),		/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0float"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "float_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 6,
+	.key_type_id = 1,
+	.value_type_id = 2,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type_size",
+},
+
 }; /* struct btf_raw_test raw_tests[] */
 
 static const char *get_next_str(const char *start, const char *end)
@@ -6630,6 +6760,7 @@ static int btf_type_size(const struct btf_type *t)
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+	case BTF_KIND_FLOAT:
 		return base_size;
 	case BTF_KIND_INT:
 		return base_size + sizeof(__u32);
diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h
index 2023725f1962..e2394eea4b7f 100644
--- a/tools/testing/selftests/bpf/test_btf.h
+++ b/tools/testing/selftests/bpf/test_btf.h
@@ -66,4 +66,7 @@
 #define BTF_FUNC_ENC(name, func_proto) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto)
 
+#define BTF_TYPE_FLOAT_ENC(name, sz) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
+
 #endif /* _TEST_BTF_H */
-- 
cgit v1.2.3


From 7999cf7df899caf244236dcc11cce844347dab4a Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Fri, 26 Feb 2021 21:22:54 +0100
Subject: selftests/bpf: Add BTF_KIND_FLOAT to the existing deduplication tests

Check that floats don't interfere with struct deduplication, that they
are not merged with another kinds and that floats of different sizes are
not merged with each other.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210226202256.116518-9-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/prog_tests/btf.c | 43 ++++++++++++++++++++--------
 1 file changed, 31 insertions(+), 12 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 11d98d3cf949..0457ae32b270 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -6411,11 +6411,12 @@ const struct btf_dedup_test dedup_tests[] = {
 			/* int[16] */
 			BTF_TYPE_ARRAY_ENC(1, 1, 16),					/* [2] */
 			/* struct s { */
-			BTF_STRUCT_ENC(NAME_NTH(2), 4, 84),				/* [3] */
+			BTF_STRUCT_ENC(NAME_NTH(2), 5, 88),				/* [3] */
 				BTF_MEMBER_ENC(NAME_NTH(3), 4, 0),	/* struct s *next;	*/
 				BTF_MEMBER_ENC(NAME_NTH(4), 5, 64),	/* const int *a;	*/
 				BTF_MEMBER_ENC(NAME_NTH(5), 2, 128),	/* int b[16];		*/
 				BTF_MEMBER_ENC(NAME_NTH(6), 1, 640),	/* int c;		*/
+				BTF_MEMBER_ENC(NAME_NTH(8), 13, 672),	/* float d;		*/
 			/* ptr -> [3] struct s */
 			BTF_PTR_ENC(3),							/* [4] */
 			/* ptr -> [6] const int */
@@ -6426,39 +6427,43 @@ const struct btf_dedup_test dedup_tests[] = {
 			/* full copy of the above */
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),	/* [7] */
 			BTF_TYPE_ARRAY_ENC(7, 7, 16),					/* [8] */
-			BTF_STRUCT_ENC(NAME_NTH(2), 4, 84),				/* [9] */
+			BTF_STRUCT_ENC(NAME_NTH(2), 5, 88),				/* [9] */
 				BTF_MEMBER_ENC(NAME_NTH(3), 10, 0),
 				BTF_MEMBER_ENC(NAME_NTH(4), 11, 64),
 				BTF_MEMBER_ENC(NAME_NTH(5), 8, 128),
 				BTF_MEMBER_ENC(NAME_NTH(6), 7, 640),
+				BTF_MEMBER_ENC(NAME_NTH(8), 13, 672),
 			BTF_PTR_ENC(9),							/* [10] */
 			BTF_PTR_ENC(12),						/* [11] */
 			BTF_CONST_ENC(7),						/* [12] */
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [13] */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0"),
+		BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"),
 	},
 	.expect = {
 		.raw_types = {
 			/* int */
-			BTF_TYPE_INT_ENC(NAME_NTH(4), BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_TYPE_INT_ENC(NAME_NTH(5), BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 			/* int[16] */
 			BTF_TYPE_ARRAY_ENC(1, 1, 16),					/* [2] */
 			/* struct s { */
-			BTF_STRUCT_ENC(NAME_NTH(6), 4, 84),				/* [3] */
-				BTF_MEMBER_ENC(NAME_NTH(5), 4, 0),	/* struct s *next;	*/
+			BTF_STRUCT_ENC(NAME_NTH(8), 5, 88),				/* [3] */
+				BTF_MEMBER_ENC(NAME_NTH(7), 4, 0),	/* struct s *next;	*/
 				BTF_MEMBER_ENC(NAME_NTH(1), 5, 64),	/* const int *a;	*/
 				BTF_MEMBER_ENC(NAME_NTH(2), 2, 128),	/* int b[16];		*/
 				BTF_MEMBER_ENC(NAME_NTH(3), 1, 640),	/* int c;		*/
+				BTF_MEMBER_ENC(NAME_NTH(4), 7, 672),	/* float d;		*/
 			/* ptr -> [3] struct s */
 			BTF_PTR_ENC(3),							/* [4] */
 			/* ptr -> [6] const int */
 			BTF_PTR_ENC(6),							/* [5] */
 			/* const -> [1] int */
 			BTF_CONST_ENC(1),						/* [6] */
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [7] */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0a\0b\0c\0int\0next\0s"),
+		BTF_STR_SEC("\0a\0b\0c\0d\0int\0float\0next\0s"),
 	},
 	.opts = {
 		.dont_resolve_fwds = false,
@@ -6579,9 +6584,10 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
+			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"),
 	},
 	.expect = {
 		.raw_types = {
@@ -6604,16 +6610,17 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
+			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"),
 	},
 	.opts = {
 		.dont_resolve_fwds = false,
 	},
 },
 {
-	.descr = "dedup: no int duplicates",
+	.descr = "dedup: no int/float duplicates",
 	.input = {
 		.raw_types = {
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 8),
@@ -6628,9 +6635,15 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 27, 8),
 			/* different byte size */
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),
+			/* all allowed sizes */
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 2),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 4),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 8),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 12),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 16),
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0int\0some other int"),
+		BTF_STR_SEC("\0int\0some other int\0float"),
 	},
 	.expect = {
 		.raw_types = {
@@ -6646,9 +6659,15 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 27, 8),
 			/* different byte size */
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),
+			/* all allowed sizes */
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 2),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 4),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 8),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 12),
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(3), 16),
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0int\0some other int"),
+		BTF_STR_SEC("\0int\0some other int\0float"),
 	},
 	.opts = {
 		.dont_resolve_fwds = false,
-- 
cgit v1.2.3


From a01d935b2e0916d32cb567f90c32a0c4eb46993c Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@cilium.io>
Date: Tue, 2 Mar 2021 09:19:43 -0800
Subject: tools/bpf: Remove bpf-helpers from bpftool docs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This logic is used for validating the manual pages from selftests, so
move the infra under tools/testing/selftests/bpf/ and rely on selftests
for validation rather than tying it into the bpftool build.

Signed-off-by: Joe Stringer <joe@cilium.io>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210302171947.2268128-12-joe@cilium.io
---
 tools/bpf/Makefile.helpers                        | 60 ----------------------
 tools/bpf/bpftool/.gitignore                      |  1 -
 tools/bpf/bpftool/Documentation/Makefile          | 11 ++--
 tools/testing/selftests/bpf/.gitignore            |  1 +
 tools/testing/selftests/bpf/Makefile              | 20 ++++++--
 tools/testing/selftests/bpf/Makefile.docs         | 62 +++++++++++++++++++++++
 tools/testing/selftests/bpf/test_bpftool_build.sh | 21 --------
 tools/testing/selftests/bpf/test_doc_build.sh     | 13 +++++
 8 files changed, 95 insertions(+), 94 deletions(-)
 delete mode 100644 tools/bpf/Makefile.helpers
 create mode 100644 tools/testing/selftests/bpf/Makefile.docs
 create mode 100755 tools/testing/selftests/bpf/test_doc_build.sh

(limited to 'tools/testing')

diff --git a/tools/bpf/Makefile.helpers b/tools/bpf/Makefile.helpers
deleted file mode 100644
index a26599022fd6..000000000000
--- a/tools/bpf/Makefile.helpers
+++ /dev/null
@@ -1,60 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-ifndef allow-override
-  include ../scripts/Makefile.include
-  include ../scripts/utilities.mak
-else
-  # Assume Makefile.helpers is being run from bpftool/Documentation
-  # subdirectory. Go up two more directories to fetch bpf.h header and
-  # associated script.
-  UP2DIR := ../../
-endif
-
-INSTALL ?= install
-RM ?= rm -f
-RMDIR ?= rmdir --ignore-fail-on-non-empty
-
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
-prefix ?= /usr/local
-mandir ?= $(prefix)/man
-man7dir = $(mandir)/man7
-
-HELPERS_RST = bpf-helpers.rst
-MAN7_RST = $(HELPERS_RST)
-
-_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST))
-DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7))
-
-helpers: man7
-man7: $(DOC_MAN7)
-
-RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
-
-$(OUTPUT)$(HELPERS_RST): $(UP2DIR)../../include/uapi/linux/bpf.h
-	$(QUIET_GEN)$(UP2DIR)../../scripts/bpf_doc.py --filename $< > $@
-
-$(OUTPUT)%.7: $(OUTPUT)%.rst
-ifndef RST2MAN_DEP
-	$(error "rst2man not found, but required to generate man pages")
-endif
-	$(QUIET_GEN)rst2man $< > $@
-
-helpers-clean:
-	$(call QUIET_CLEAN, eBPF_helpers-manpage)
-	$(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST)
-
-helpers-install: helpers
-	$(call QUIET_INSTALL, eBPF_helpers-manpage)
-	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
-	$(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
-
-helpers-uninstall:
-	$(call QUIET_UNINST, eBPF_helpers-manpage)
-	$(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7))
-	$(Q)$(RMDIR) $(DESTDIR)$(man7dir)
-
-.PHONY: helpers helpers-clean helpers-install helpers-uninstall
diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore
index 944cb4b7c95d..05ce4446b780 100644
--- a/tools/bpf/bpftool/.gitignore
+++ b/tools/bpf/bpftool/.gitignore
@@ -3,7 +3,6 @@
 /bootstrap/
 /bpftool
 bpftool*.8
-bpf-helpers.*
 FEATURE-DUMP.bpftool
 feature
 libbpf
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index f33cb02de95c..c49487905ceb 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -16,15 +16,12 @@ prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man8dir = $(mandir)/man8
 
-# Load targets for building eBPF helpers man page.
-include ../../Makefile.helpers
-
 MAN8_RST = $(wildcard bpftool*.rst)
 
 _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
 DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
 
-man: man8 helpers
+man: man8
 man8: $(DOC_MAN8)
 
 RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
@@ -46,16 +43,16 @@ ifndef RST2MAN_DEP
 endif
 	$(QUIET_GEN)( cat $< ; printf "%b" $(call see_also,$<) ) | rst2man $(RST2MAN_OPTS) > $@
 
-clean: helpers-clean
+clean:
 	$(call QUIET_CLEAN, Documentation)
 	$(Q)$(RM) $(DOC_MAN8)
 
-install: man helpers-install
+install: man
 	$(call QUIET_INSTALL, Documentation-man)
 	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir)
 	$(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir)
 
-uninstall: helpers-uninstall
+uninstall:
 	$(call QUIET_UNINST, Documentation-man)
 	$(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8))
 	$(Q)$(RMDIR) $(DESTDIR)$(man8dir)
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index c0c48fdb9ac1..a0d5ec3cfc24 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
+bpf-helpers*
 test_verifier
 test_maps
 test_lru_map
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a81af15e4ded..b5827464c6b5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -68,6 +68,7 @@ TEST_PROGS := test_kmod.sh \
 	test_bpftool_build.sh \
 	test_bpftool.sh \
 	test_bpftool_metadata.sh \
+	test_docs_build.sh \
 	test_xsk.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
@@ -103,6 +104,7 @@ override define CLEAN
 	$(call msg,CLEAN)
 	$(Q)$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
 	$(Q)$(MAKE) -C bpf_testmod clean
+	$(Q)$(MAKE) docs-clean
 endef
 
 include ../lib.mk
@@ -180,6 +182,7 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
 		    cp $(SCRATCH_DIR)/runqslower $@
 
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
+$(TEST_GEN_FILES): docs
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
@@ -200,11 +203,16 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    CC=$(HOSTCC) LD=$(HOSTLD)				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
-	$(Q)mkdir -p $(BUILD_DIR)/bpftool/Documentation
-	$(Q)RST2MAN_OPTS="--exit-status=1" $(MAKE) $(submake_extras)	       \
-		    -C $(BPFTOOLDIR)/Documentation			       \
-		    OUTPUT=$(BUILD_DIR)/bpftool/Documentation/		       \
-		    prefix= DESTDIR=$(SCRATCH_DIR)/ install
+
+docs:
+	$(Q)RST2MAN_OPTS="--exit-status=1" $(MAKE) $(submake_extras)	\
+	            -f Makefile.docs					\
+	            prefix= OUTPUT=$(OUTPUT)/ DESTDIR=$(OUTPUT)/ $@
+
+docs-clean:
+	$(Q)$(MAKE) $(submake_extras)					\
+	            -f Makefile.docs					\
+	            prefix= OUTPUT=$(OUTPUT)/ DESTDIR=$(OUTPUT)/ $@
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   ../../../include/uapi/linux/bpf.h                                   \
@@ -477,3 +485,5 @@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature								\
 	$(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc bpf_testmod.ko)
+
+.PHONY: docs docs-clean
diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs
new file mode 100644
index 000000000000..546c4a763b46
--- /dev/null
+++ b/tools/testing/selftests/bpf/Makefile.docs
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+include ../../../scripts/Makefile.include
+include ../../../scripts/utilities.mak
+
+INSTALL ?= install
+RM ?= rm -f
+RMDIR ?= rmdir --ignore-fail-on-non-empty
+
+ifeq ($(V),1)
+  Q =
+else
+  Q = @
+endif
+
+prefix ?= /usr/local
+mandir ?= $(prefix)/man
+man7dir = $(mandir)/man7
+
+HELPERS_RST = bpf-helpers.rst
+MAN7_RST = $(HELPERS_RST)
+
+_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST))
+DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7))
+
+DOCTARGETS := helpers
+
+docs: $(DOCTARGETS)
+helpers: man7
+man7: $(DOC_MAN7)
+
+RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
+
+# Configure make rules for the man page bpf-$1.$2.
+# $1 - target for scripts/bpf_doc.py
+# $2 - man page section to generate the troff file
+define DOCS_RULES =
+$(OUTPUT)bpf-$1.rst: ../../../../include/uapi/linux/bpf.h
+	$$(QUIET_GEN)../../../../scripts/bpf_doc.py $1 \
+		--filename $$< > $$@
+
+$(OUTPUT)%.7: $(OUTPUT)%.rst
+ifndef RST2MAN_DEP
+	$(error "rst2man not found, but required to generate man pages")
+endif
+	$(QUIET_GEN)rst2man $< > $@
+
+docs-clean:
+	$(call QUIET_CLEAN, eBPF_helpers-manpage)
+	$(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST)
+
+docs-install: helpers
+	$(call QUIET_INSTALL, eBPF_helpers-manpage)
+	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
+	$(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+docs-uninstall:
+	$(call QUIET_UNINST, eBPF_helpers-manpage)
+	$(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7))
+	$(Q)$(RMDIR) $(DESTDIR)$(man7dir)
+
+.PHONY: docs docs-clean docs-install docs-uninstall
diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh
index 2db3c60e1e61..ac349a5cea7e 100755
--- a/tools/testing/selftests/bpf/test_bpftool_build.sh
+++ b/tools/testing/selftests/bpf/test_bpftool_build.sh
@@ -85,23 +85,6 @@ make_with_tmpdir() {
 	echo
 }
 
-make_doc_and_clean() {
-	echo -e "\$PWD:    $PWD"
-	echo -e "command: make -s $* doc >/dev/null"
-	RST2MAN_OPTS="--exit-status=1" make $J -s $* doc
-	if [ $? -ne 0 ] ; then
-		ERROR=1
-		printf "FAILURE: Errors or warnings when building documentation\n"
-	fi
-	(
-		if [ $# -ge 1 ] ; then
-			cd ${@: -1}
-		fi
-		make -s doc-clean
-	)
-	echo
-}
-
 echo "Trying to build bpftool"
 echo -e "... through kbuild\n"
 
@@ -162,7 +145,3 @@ make_and_clean
 make_with_tmpdir OUTPUT
 
 make_with_tmpdir O
-
-echo -e "Checking documentation build\n"
-# From tools/bpf/bpftool
-make_doc_and_clean
diff --git a/tools/testing/selftests/bpf/test_doc_build.sh b/tools/testing/selftests/bpf/test_doc_build.sh
new file mode 100755
index 000000000000..7eb940a7b2eb
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_doc_build.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+
+# Assume script is located under tools/testing/selftests/bpf/. We want to start
+# build attempts from the top of kernel repository.
+SCRIPT_REL_PATH=$(realpath --relative-to=$PWD $0)
+SCRIPT_REL_DIR=$(dirname $SCRIPT_REL_PATH)
+KDIR_ROOT_DIR=$(realpath $PWD/$SCRIPT_REL_DIR/../../../../)
+cd $KDIR_ROOT_DIR
+
+for tgt in docs docs-clean; do
+	make -s -C $PWD/$SCRIPT_REL_DIR $tgt;
+done
-- 
cgit v1.2.3


From 62b379a233a79e6f4d2e8b14750ae8fa13b8caf8 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@cilium.io>
Date: Tue, 2 Mar 2021 09:19:44 -0800
Subject: selftests/bpf: Templatize man page generation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Previously, the Makefile here was only targeting a single manual page so
it just hardcoded a bunch of individual rules to specifically handle
build, clean, install, uninstall for that particular page.

Upcoming commits will generate manual pages for an additional section,
so this commit prepares the makefile first by converting the existing
targets into an evaluated set of targets based on the manual page name
and section.

Signed-off-by: Joe Stringer <joe@cilium.io>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210302171947.2268128-13-joe@cilium.io
---
 tools/testing/selftests/bpf/Makefile.docs | 40 +++++++++++++++++++------------
 1 file changed, 25 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs
index 546c4a763b46..f39ad19317c8 100644
--- a/tools/testing/selftests/bpf/Makefile.docs
+++ b/tools/testing/selftests/bpf/Makefile.docs
@@ -39,24 +39,34 @@ $(OUTPUT)bpf-$1.rst: ../../../../include/uapi/linux/bpf.h
 	$$(QUIET_GEN)../../../../scripts/bpf_doc.py $1 \
 		--filename $$< > $$@
 
-$(OUTPUT)%.7: $(OUTPUT)%.rst
+$(OUTPUT)%.$2: $(OUTPUT)%.rst
 ifndef RST2MAN_DEP
-	$(error "rst2man not found, but required to generate man pages")
+	$$(error "rst2man not found, but required to generate man pages")
 endif
-	$(QUIET_GEN)rst2man $< > $@
+	$$(QUIET_GEN)rst2man $$< > $$@
 
-docs-clean:
-	$(call QUIET_CLEAN, eBPF_helpers-manpage)
-	$(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST)
+docs-clean-$1:
+	$$(call QUIET_CLEAN, eBPF_$1-manpage)
+	$(Q)$(RM) $$(DOC_MAN$2) $(OUTPUT)bpf-$1.rst
 
-docs-install: helpers
-	$(call QUIET_INSTALL, eBPF_helpers-manpage)
-	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
-	$(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+docs-install-$1: docs
+	$$(call QUIET_INSTALL, eBPF_$1-manpage)
+	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$$(man$2dir)
+	$(Q)$(INSTALL) -m 644 $$(DOC_MAN$2) $(DESTDIR)$$(man$2dir)
 
-docs-uninstall:
-	$(call QUIET_UNINST, eBPF_helpers-manpage)
-	$(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7))
-	$(Q)$(RMDIR) $(DESTDIR)$(man7dir)
+docs-uninstall-$1:
+	$$(call QUIET_UNINST, eBPF_$1-manpage)
+	$(Q)$(RM) $$(addprefix $(DESTDIR)$$(man$2dir)/,$$(_DOC_MAN$2))
+	$(Q)$(RMDIR) $(DESTDIR)$$(man$2dir)
 
-.PHONY: docs docs-clean docs-install docs-uninstall
+.PHONY: $1 docs-clean-$1 docs-install-$1 docs-uninstall-$1
+endef
+
+# Create the make targets to generate manual pages by name and section
+$(eval $(call DOCS_RULES,helpers,7))
+
+docs-clean: $(foreach doctarget,$(DOCTARGETS), docs-clean-$(doctarget))
+docs-install: $(foreach doctarget,$(DOCTARGETS), docs-install-$(doctarget))
+docs-uninstall: $(foreach doctarget,$(DOCTARGETS), docs-uninstall-$(doctarget))
+
+.PHONY: docs docs-clean docs-install docs-uninstall man7
-- 
cgit v1.2.3


From accbd33a9b0328777899a85d148040e4d8921d87 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@cilium.io>
Date: Tue, 2 Mar 2021 09:19:45 -0800
Subject: selftests/bpf: Test syscall command parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add building of the bpf(2) syscall commands documentation as part of the
docs building step in the build. This allows us to pick up on potential
parse errors from the docs generator script as part of selftests.

The generated manual pages here are not intended for distribution, they
are just a fragment that can be integrated into the other static text of
bpf(2) to form the full manual page.

Signed-off-by: Joe Stringer <joe@cilium.io>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210302171947.2268128-14-joe@cilium.io
---
 tools/testing/selftests/bpf/.gitignore    |  1 +
 tools/testing/selftests/bpf/Makefile.docs | 14 ++++++++++++--
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index a0d5ec3cfc24..4866f6a21901 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 bpf-helpers*
+bpf-syscall*
 test_verifier
 test_maps
 test_lru_map
diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs
index f39ad19317c8..ccf260021e83 100644
--- a/tools/testing/selftests/bpf/Makefile.docs
+++ b/tools/testing/selftests/bpf/Makefile.docs
@@ -15,18 +15,27 @@ endif
 
 prefix ?= /usr/local
 mandir ?= $(prefix)/man
+man2dir = $(mandir)/man2
 man7dir = $(mandir)/man7
 
+SYSCALL_RST = bpf-syscall.rst
+MAN2_RST = $(SYSCALL_RST)
+
 HELPERS_RST = bpf-helpers.rst
 MAN7_RST = $(HELPERS_RST)
 
+_DOC_MAN2 = $(patsubst %.rst,%.2,$(MAN2_RST))
+DOC_MAN2 = $(addprefix $(OUTPUT),$(_DOC_MAN2))
+
 _DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST))
 DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7))
 
-DOCTARGETS := helpers
+DOCTARGETS := helpers syscall
 
 docs: $(DOCTARGETS)
+syscall: man2
 helpers: man7
+man2: $(DOC_MAN2)
 man7: $(DOC_MAN7)
 
 RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
@@ -64,9 +73,10 @@ endef
 
 # Create the make targets to generate manual pages by name and section
 $(eval $(call DOCS_RULES,helpers,7))
+$(eval $(call DOCS_RULES,syscall,2))
 
 docs-clean: $(foreach doctarget,$(DOCTARGETS), docs-clean-$(doctarget))
 docs-install: $(foreach doctarget,$(DOCTARGETS), docs-install-$(doctarget))
 docs-uninstall: $(foreach doctarget,$(DOCTARGETS), docs-uninstall-$(doctarget))
 
-.PHONY: docs docs-clean docs-install docs-uninstall man7
+.PHONY: docs docs-clean docs-install docs-uninstall man2 man7
-- 
cgit v1.2.3


From 509b2937bce90089fd2785db9f27951a3d850c34 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Wed, 3 Mar 2021 10:18:14 +0000
Subject: selftests: bpf: Convert sk_lookup ctx access tests to PROG_TEST_RUN

Convert the selftests for sk_lookup narrow context access to use
PROG_TEST_RUN instead of creating actual sockets. This ensures that
ctx is populated correctly when using PROG_TEST_RUN.

Assert concrete values since we now control remote_ip and remote_port.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210303101816.36774-4-lmb@cloudflare.com
---
 tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 83 ++++++++++++++++++----
 tools/testing/selftests/bpf/progs/test_sk_lookup.c | 62 ++++++++++------
 2 files changed, 109 insertions(+), 36 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index 9ff0412e1fd3..45c82db3c58c 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -241,6 +241,48 @@ fail:
 	return -1;
 }
 
+static __u64 socket_cookie(int fd)
+{
+	__u64 cookie;
+	socklen_t cookie_len = sizeof(cookie);
+
+	if (CHECK(getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len) < 0,
+		  "getsockopt(SO_COOKIE)", "%s\n", strerror(errno)))
+		return 0;
+	return cookie;
+}
+
+static int fill_sk_lookup_ctx(struct bpf_sk_lookup *ctx, const char *local_ip, __u16 local_port,
+			      const char *remote_ip, __u16 remote_port)
+{
+	void *local, *remote;
+	int err;
+
+	memset(ctx, 0, sizeof(*ctx));
+	ctx->local_port = local_port;
+	ctx->remote_port = htons(remote_port);
+
+	if (is_ipv6(local_ip)) {
+		ctx->family = AF_INET6;
+		local = &ctx->local_ip6[0];
+		remote = &ctx->remote_ip6[0];
+	} else {
+		ctx->family = AF_INET;
+		local = &ctx->local_ip4;
+		remote = &ctx->remote_ip4;
+	}
+
+	err = inet_pton(ctx->family, local_ip, local);
+	if (CHECK(err != 1, "inet_pton", "local_ip failed\n"))
+		return 1;
+
+	err = inet_pton(ctx->family, remote_ip, remote);
+	if (CHECK(err != 1, "inet_pton", "remote_ip failed\n"))
+		return 1;
+
+	return 0;
+}
+
 static int send_byte(int fd)
 {
 	ssize_t n;
@@ -1009,18 +1051,27 @@ static void test_drop_on_reuseport(struct test_sk_lookup *skel)
 
 static void run_sk_assign(struct test_sk_lookup *skel,
 			  struct bpf_program *lookup_prog,
-			  const char *listen_ip, const char *connect_ip)
+			  const char *remote_ip, const char *local_ip)
 {
-	int client_fd, peer_fd, server_fds[MAX_SERVERS] = { -1 };
-	struct bpf_link *lookup_link;
+	int server_fds[MAX_SERVERS] = { -1 };
+	struct bpf_sk_lookup ctx;
+	__u64 server_cookie;
 	int i, err;
 
-	lookup_link = attach_lookup_prog(lookup_prog);
-	if (!lookup_link)
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.ctx_in = &ctx,
+		.ctx_size_in = sizeof(ctx),
+		.ctx_out = &ctx,
+		.ctx_size_out = sizeof(ctx),
+	);
+
+	if (fill_sk_lookup_ctx(&ctx, local_ip, EXT_PORT, remote_ip, INT_PORT))
 		return;
 
+	ctx.protocol = IPPROTO_TCP;
+
 	for (i = 0; i < ARRAY_SIZE(server_fds); i++) {
-		server_fds[i] = make_server(SOCK_STREAM, listen_ip, 0, NULL);
+		server_fds[i] = make_server(SOCK_STREAM, local_ip, 0, NULL);
 		if (server_fds[i] < 0)
 			goto close_servers;
 
@@ -1030,23 +1081,25 @@ static void run_sk_assign(struct test_sk_lookup *skel,
 			goto close_servers;
 	}
 
-	client_fd = make_client(SOCK_STREAM, connect_ip, EXT_PORT);
-	if (client_fd < 0)
+	server_cookie = socket_cookie(server_fds[SERVER_B]);
+	if (!server_cookie)
+		return;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(lookup_prog), &opts);
+	if (CHECK(err, "test_run", "failed with error %d\n", errno))
+		goto close_servers;
+
+	if (CHECK(ctx.cookie == 0, "ctx.cookie", "no socket selected\n"))
 		goto close_servers;
 
-	peer_fd = accept(server_fds[SERVER_B], NULL, NULL);
-	if (CHECK(peer_fd < 0, "accept", "failed\n"))
-		goto close_client;
+	CHECK(ctx.cookie != server_cookie, "ctx.cookie",
+	      "selected sk %llu instead of %llu\n", ctx.cookie, server_cookie);
 
-	close(peer_fd);
-close_client:
-	close(client_fd);
 close_servers:
 	for (i = 0; i < ARRAY_SIZE(server_fds); i++) {
 		if (server_fds[i] != -1)
 			close(server_fds[i]);
 	}
-	bpf_link__destroy(lookup_link);
 }
 
 static void run_sk_assign_v4(struct test_sk_lookup *skel,
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
index 1032b292af5b..ac6f7f205e25 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -64,6 +64,10 @@ static const int PROG_DONE = 1;
 static const __u32 KEY_SERVER_A = SERVER_A;
 static const __u32 KEY_SERVER_B = SERVER_B;
 
+static const __u16 SRC_PORT = bpf_htons(8008);
+static const __u32 SRC_IP4 = IP4(127, 0, 0, 2);
+static const __u32 SRC_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000002);
+
 static const __u16 DST_PORT = 7007; /* Host byte order */
 static const __u32 DST_IP4 = IP4(127, 0, 0, 1);
 static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001);
@@ -398,11 +402,12 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx)
 	if (LSW(ctx->protocol, 0) != IPPROTO_TCP)
 		return SK_DROP;
 
-	/* Narrow loads from remote_port field. Expect non-0 value. */
-	if (LSB(ctx->remote_port, 0) == 0 && LSB(ctx->remote_port, 1) == 0 &&
-	    LSB(ctx->remote_port, 2) == 0 && LSB(ctx->remote_port, 3) == 0)
+	/* Narrow loads from remote_port field. Expect SRC_PORT. */
+	if (LSB(ctx->remote_port, 0) != ((SRC_PORT >> 0) & 0xff) ||
+	    LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff) ||
+	    LSB(ctx->remote_port, 2) != 0 || LSB(ctx->remote_port, 3) != 0)
 		return SK_DROP;
-	if (LSW(ctx->remote_port, 0) == 0)
+	if (LSW(ctx->remote_port, 0) != SRC_PORT)
 		return SK_DROP;
 
 	/* Narrow loads from local_port field. Expect DST_PORT. */
@@ -415,11 +420,14 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx)
 
 	/* Narrow loads from IPv4 fields */
 	if (v4) {
-		/* Expect non-0.0.0.0 in remote_ip4 */
-		if (LSB(ctx->remote_ip4, 0) == 0 && LSB(ctx->remote_ip4, 1) == 0 &&
-		    LSB(ctx->remote_ip4, 2) == 0 && LSB(ctx->remote_ip4, 3) == 0)
+		/* Expect SRC_IP4 in remote_ip4 */
+		if (LSB(ctx->remote_ip4, 0) != ((SRC_IP4 >> 0) & 0xff) ||
+		    LSB(ctx->remote_ip4, 1) != ((SRC_IP4 >> 8) & 0xff) ||
+		    LSB(ctx->remote_ip4, 2) != ((SRC_IP4 >> 16) & 0xff) ||
+		    LSB(ctx->remote_ip4, 3) != ((SRC_IP4 >> 24) & 0xff))
 			return SK_DROP;
-		if (LSW(ctx->remote_ip4, 0) == 0 && LSW(ctx->remote_ip4, 1) == 0)
+		if (LSW(ctx->remote_ip4, 0) != ((SRC_IP4 >> 0) & 0xffff) ||
+		    LSW(ctx->remote_ip4, 1) != ((SRC_IP4 >> 16) & 0xffff))
 			return SK_DROP;
 
 		/* Expect DST_IP4 in local_ip4 */
@@ -448,20 +456,32 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx)
 
 	/* Narrow loads from IPv6 fields */
 	if (!v4) {
-		/* Expect non-:: IP in remote_ip6 */
-		if (LSB(ctx->remote_ip6[0], 0) == 0 && LSB(ctx->remote_ip6[0], 1) == 0 &&
-		    LSB(ctx->remote_ip6[0], 2) == 0 && LSB(ctx->remote_ip6[0], 3) == 0 &&
-		    LSB(ctx->remote_ip6[1], 0) == 0 && LSB(ctx->remote_ip6[1], 1) == 0 &&
-		    LSB(ctx->remote_ip6[1], 2) == 0 && LSB(ctx->remote_ip6[1], 3) == 0 &&
-		    LSB(ctx->remote_ip6[2], 0) == 0 && LSB(ctx->remote_ip6[2], 1) == 0 &&
-		    LSB(ctx->remote_ip6[2], 2) == 0 && LSB(ctx->remote_ip6[2], 3) == 0 &&
-		    LSB(ctx->remote_ip6[3], 0) == 0 && LSB(ctx->remote_ip6[3], 1) == 0 &&
-		    LSB(ctx->remote_ip6[3], 2) == 0 && LSB(ctx->remote_ip6[3], 3) == 0)
+		/* Expect SRC_IP6 in remote_ip6 */
+		if (LSB(ctx->remote_ip6[0], 0) != ((SRC_IP6[0] >> 0) & 0xff) ||
+		    LSB(ctx->remote_ip6[0], 1) != ((SRC_IP6[0] >> 8) & 0xff) ||
+		    LSB(ctx->remote_ip6[0], 2) != ((SRC_IP6[0] >> 16) & 0xff) ||
+		    LSB(ctx->remote_ip6[0], 3) != ((SRC_IP6[0] >> 24) & 0xff) ||
+		    LSB(ctx->remote_ip6[1], 0) != ((SRC_IP6[1] >> 0) & 0xff) ||
+		    LSB(ctx->remote_ip6[1], 1) != ((SRC_IP6[1] >> 8) & 0xff) ||
+		    LSB(ctx->remote_ip6[1], 2) != ((SRC_IP6[1] >> 16) & 0xff) ||
+		    LSB(ctx->remote_ip6[1], 3) != ((SRC_IP6[1] >> 24) & 0xff) ||
+		    LSB(ctx->remote_ip6[2], 0) != ((SRC_IP6[2] >> 0) & 0xff) ||
+		    LSB(ctx->remote_ip6[2], 1) != ((SRC_IP6[2] >> 8) & 0xff) ||
+		    LSB(ctx->remote_ip6[2], 2) != ((SRC_IP6[2] >> 16) & 0xff) ||
+		    LSB(ctx->remote_ip6[2], 3) != ((SRC_IP6[2] >> 24) & 0xff) ||
+		    LSB(ctx->remote_ip6[3], 0) != ((SRC_IP6[3] >> 0) & 0xff) ||
+		    LSB(ctx->remote_ip6[3], 1) != ((SRC_IP6[3] >> 8) & 0xff) ||
+		    LSB(ctx->remote_ip6[3], 2) != ((SRC_IP6[3] >> 16) & 0xff) ||
+		    LSB(ctx->remote_ip6[3], 3) != ((SRC_IP6[3] >> 24) & 0xff))
 			return SK_DROP;
-		if (LSW(ctx->remote_ip6[0], 0) == 0 && LSW(ctx->remote_ip6[0], 1) == 0 &&
-		    LSW(ctx->remote_ip6[1], 0) == 0 && LSW(ctx->remote_ip6[1], 1) == 0 &&
-		    LSW(ctx->remote_ip6[2], 0) == 0 && LSW(ctx->remote_ip6[2], 1) == 0 &&
-		    LSW(ctx->remote_ip6[3], 0) == 0 && LSW(ctx->remote_ip6[3], 1) == 0)
+		if (LSW(ctx->remote_ip6[0], 0) != ((SRC_IP6[0] >> 0) & 0xffff) ||
+		    LSW(ctx->remote_ip6[0], 1) != ((SRC_IP6[0] >> 16) & 0xffff) ||
+		    LSW(ctx->remote_ip6[1], 0) != ((SRC_IP6[1] >> 0) & 0xffff) ||
+		    LSW(ctx->remote_ip6[1], 1) != ((SRC_IP6[1] >> 16) & 0xffff) ||
+		    LSW(ctx->remote_ip6[2], 0) != ((SRC_IP6[2] >> 0) & 0xffff) ||
+		    LSW(ctx->remote_ip6[2], 1) != ((SRC_IP6[2] >> 16) & 0xffff) ||
+		    LSW(ctx->remote_ip6[3], 0) != ((SRC_IP6[3] >> 0) & 0xffff) ||
+		    LSW(ctx->remote_ip6[3], 1) != ((SRC_IP6[3] >> 16) & 0xffff))
 			return SK_DROP;
 		/* Expect DST_IP6 in local_ip6 */
 		if (LSB(ctx->local_ip6[0], 0) != ((DST_IP6[0] >> 0) & 0xff) ||
-- 
cgit v1.2.3


From abab306ff04b570e817be3f026068fe9a5d99fbb Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Wed, 3 Mar 2021 10:18:15 +0000
Subject: selftests: bpf: Check that PROG_TEST_RUN repeats as requested

Extend a simple prog_run test to check that PROG_TEST_RUN adheres
to the requested repetitions. Convert it to use BPF skeleton.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210303101816.36774-5-lmb@cloudflare.com
---
 .../selftests/bpf/prog_tests/prog_run_xattr.c      | 51 ++++++++++++++++++----
 1 file changed, 42 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
index 935a294f049a..131d7f7eeb42 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
@@ -2,12 +2,31 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 
-void test_prog_run_xattr(void)
+#include "test_pkt_access.skel.h"
+
+static const __u32 duration;
+
+static void check_run_cnt(int prog_fd, __u64 run_cnt)
 {
-	const char *file = "./test_pkt_access.o";
-	struct bpf_object *obj;
-	char buf[10];
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
 	int err;
+
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd))
+		return;
+
+	CHECK(run_cnt != info.run_cnt, "run_cnt",
+	      "incorrect number of repetitions, want %llu have %llu\n", run_cnt, info.run_cnt);
+}
+
+void test_prog_run_xattr(void)
+{
+	struct test_pkt_access *skel;
+	int err, stats_fd = -1;
+	char buf[10] = {};
+	__u64 run_cnt = 0;
+
 	struct bpf_prog_test_run_attr tattr = {
 		.repeat = 1,
 		.data_in = &pkt_v4,
@@ -16,12 +35,15 @@ void test_prog_run_xattr(void)
 		.data_size_out = 5,
 	};
 
-	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj,
-			    &tattr.prog_fd);
-	if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+	stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME);
+	if (CHECK_ATTR(stats_fd < 0, "enable_stats", "failed %d\n", errno))
 		return;
 
-	memset(buf, 0, sizeof(buf));
+	skel = test_pkt_access__open_and_load();
+	if (CHECK_ATTR(!skel, "open_and_load", "failed\n"))
+		goto cleanup;
+
+	tattr.prog_fd = bpf_program__fd(skel->progs.test_pkt_access);
 
 	err = bpf_prog_test_run_xattr(&tattr);
 	CHECK_ATTR(err != -1 || errno != ENOSPC || tattr.retval, "run",
@@ -34,8 +56,12 @@ void test_prog_run_xattr(void)
 	CHECK_ATTR(buf[5] != 0, "overflow",
 	      "BPF_PROG_TEST_RUN ignored size hint\n");
 
+	run_cnt += tattr.repeat;
+	check_run_cnt(tattr.prog_fd, run_cnt);
+
 	tattr.data_out = NULL;
 	tattr.data_size_out = 0;
+	tattr.repeat = 2;
 	errno = 0;
 
 	err = bpf_prog_test_run_xattr(&tattr);
@@ -46,5 +72,12 @@ void test_prog_run_xattr(void)
 	err = bpf_prog_test_run_xattr(&tattr);
 	CHECK_ATTR(err != -EINVAL, "run_wrong_size_out", "err %d\n", err);
 
-	bpf_object__close(obj);
+	run_cnt += tattr.repeat;
+	check_run_cnt(tattr.prog_fd, run_cnt);
+
+cleanup:
+	if (skel)
+		test_pkt_access__destroy(skel);
+	if (stats_fd != -1)
+		close(stats_fd);
 }
-- 
cgit v1.2.3


From b4f894633fa14d7d46ba7676f950b90a401504bb Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Wed, 3 Mar 2021 10:18:16 +0000
Subject: selftests: bpf: Don't run sk_lookup in verifier tests

sk_lookup doesn't allow setting data_in for bpf_prog_run. This doesn't
play well with the verifier tests, since they always set a 64 byte
input buffer. Allow not running verifier tests by setting
bpf_test.runs to a negative value and don't run the ctx access case
for sk_lookup. We have dedicated ctx access tests so skipping here
doesn't reduce coverage.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210303101816.36774-6-lmb@cloudflare.com
---
 tools/testing/selftests/bpf/test_verifier.c          | 4 ++--
 tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 58b5a349d3ba..1512092e1e68 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -105,7 +105,7 @@ struct bpf_test {
 	enum bpf_prog_type prog_type;
 	uint8_t flags;
 	void (*fill_helper)(struct bpf_test *self);
-	uint8_t runs;
+	int runs;
 #define bpf_testdata_struct_t					\
 	struct {						\
 		uint32_t retval, retval_unpriv;			\
@@ -1165,7 +1165,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 
 	run_errs = 0;
 	run_successes = 0;
-	if (!alignment_prevented_execution && fd_prog >= 0) {
+	if (!alignment_prevented_execution && fd_prog >= 0 && test->runs >= 0) {
 		uint32_t expected_val;
 		int i;
 
diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
index fb13ca2d5606..d78627be060f 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
@@ -239,6 +239,7 @@
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
 	.expected_attach_type = BPF_SK_LOOKUP,
+	.runs = -1,
 },
 /* invalid 8-byte reads from a 4-byte fields in bpf_sk_lookup */
 {
-- 
cgit v1.2.3


From bce8623135fbe54bd86797df72cb85bfe4118b6e Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Wed, 3 Mar 2021 15:52:10 +0800
Subject: selftests/bpf: Simplify the calculation of variables

Fix the following coccicheck warnings:

./tools/testing/selftests/bpf/test_sockmap.c:735:35-37: WARNING !A || A
&& B is equivalent to !A || B.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/1614757930-17197-1-git-send-email-jiapeng.chong@linux.alibaba.com
---
 tools/testing/selftests/bpf/test_sockmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 427ca00a3217..eefd445b96fc 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -732,7 +732,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 		 * socket is not a valid test. So in this case lets not
 		 * enable kTLS but still run the test.
 		 */
-		if (!txmsg_redir || (txmsg_redir && txmsg_ingress)) {
+		if (!txmsg_redir || txmsg_ingress) {
 			err = sockmap_init_ktls(opt->verbose, rx_fd);
 			if (err)
 				return err;
-- 
cgit v1.2.3


From 256becd450172eec74566f1aa7819ce80181d7e1 Mon Sep 17 00:00:00 2001
From: Xuesen Huang <huangxuesen@kuaishou.com>
Date: Fri, 5 Mar 2021 20:33:47 +0800
Subject: selftests, bpf: Extend test_tc_tunnel test with vxlan

Add BPF_F_ADJ_ROOM_ENCAP_L2_ETH flag to the existing tests which
encapsulates the ethernet as the inner l2 header.

Update a vxlan encapsulation test case.

Signed-off-by: Xuesen Huang <huangxuesen@kuaishou.com>
Signed-off-by: Li Wang <wangli09@kuaishou.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/bpf/20210305123347.15311-1-hxseverything@gmail.com
---
 tools/testing/selftests/bpf/progs/test_tc_tunnel.c | 113 ++++++++++++++++++---
 tools/testing/selftests/bpf/test_tc_tunnel.sh      |  15 ++-
 2 files changed, 111 insertions(+), 17 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 37bce7a7c394..84cd63259554 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -24,14 +24,29 @@ static const int cfg_port = 8000;
 
 static const int cfg_udp_src = 20000;
 
+#define	L2_PAD_SZ	(sizeof(struct vxlanhdr) + ETH_HLEN)
+
 #define	UDP_PORT		5555
 #define	MPLS_OVER_UDP_PORT	6635
 #define	ETH_OVER_UDP_PORT	7777
+#define	VXLAN_UDP_PORT		8472
+
+#define	EXTPROTO_VXLAN	0x1
+
+#define	VXLAN_N_VID     (1u << 24)
+#define	VXLAN_VNI_MASK	bpf_htonl((VXLAN_N_VID - 1) << 8)
+#define	VXLAN_FLAGS     0x8
+#define	VXLAN_VNI       1
 
 /* MPLS label 1000 with S bit (last label) set and ttl of 255. */
 static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
 						     MPLS_LS_S_MASK | 0xff);
 
+struct vxlanhdr {
+	__be32 vx_flags;
+	__be32 vx_vni;
+} __attribute__((packed));
+
 struct gre_hdr {
 	__be16 flags;
 	__be16 protocol;
@@ -45,13 +60,13 @@ union l4hdr {
 struct v4hdr {
 	struct iphdr ip;
 	union l4hdr l4hdr;
-	__u8 pad[16];			/* enough space for L2 header */
+	__u8 pad[L2_PAD_SZ];		/* space for L2 header / vxlan header ... */
 } __attribute__((packed));
 
 struct v6hdr {
 	struct ipv6hdr ip;
 	union l4hdr l4hdr;
-	__u8 pad[16];			/* enough space for L2 header */
+	__u8 pad[L2_PAD_SZ];		/* space for L2 header / vxlan header ... */
 } __attribute__((packed));
 
 static __always_inline void set_ipv4_csum(struct iphdr *iph)
@@ -69,14 +84,15 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph)
 	iph->check = ~((csum & 0xffff) + (csum >> 16));
 }
 
-static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
-				      __u16 l2_proto)
+static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
+					__u16 l2_proto, __u16 ext_proto)
 {
 	__u16 udp_dst = UDP_PORT;
 	struct iphdr iph_inner;
 	struct v4hdr h_outer;
 	struct tcphdr tcph;
 	int olen, l2_len;
+	__u8 *l2_hdr = NULL;
 	int tcp_off;
 	__u64 flags;
 
@@ -141,7 +157,11 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 		break;
 	case ETH_P_TEB:
 		l2_len = ETH_HLEN;
-		udp_dst = ETH_OVER_UDP_PORT;
+		if (ext_proto & EXTPROTO_VXLAN) {
+			udp_dst = VXLAN_UDP_PORT;
+			l2_len += sizeof(struct vxlanhdr);
+		} else
+			udp_dst = ETH_OVER_UDP_PORT;
 		break;
 	}
 	flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
@@ -171,14 +191,26 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 	}
 
 	/* add L2 encap (if specified) */
+	l2_hdr = (__u8 *)&h_outer + olen;
 	switch (l2_proto) {
 	case ETH_P_MPLS_UC:
-		*((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+		*(__u32 *)l2_hdr = mpls_label;
 		break;
 	case ETH_P_TEB:
-		if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
-				       ETH_HLEN))
+		flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH;
+
+		if (ext_proto & EXTPROTO_VXLAN) {
+			struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
+
+			vxlan_hdr->vx_flags = VXLAN_FLAGS;
+			vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8);
+
+			l2_hdr += sizeof(struct vxlanhdr);
+		}
+
+		if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN))
 			return TC_ACT_SHOT;
+
 		break;
 	}
 	olen += l2_len;
@@ -214,14 +246,21 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 	return TC_ACT_OK;
 }
 
-static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 				      __u16 l2_proto)
+{
+	return __encap_ipv4(skb, encap_proto, l2_proto, 0);
+}
+
+static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+					__u16 l2_proto, __u16 ext_proto)
 {
 	__u16 udp_dst = UDP_PORT;
 	struct ipv6hdr iph_inner;
 	struct v6hdr h_outer;
 	struct tcphdr tcph;
 	int olen, l2_len;
+	__u8 *l2_hdr = NULL;
 	__u16 tot_len;
 	__u64 flags;
 
@@ -249,7 +288,11 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 		break;
 	case ETH_P_TEB:
 		l2_len = ETH_HLEN;
-		udp_dst = ETH_OVER_UDP_PORT;
+		if (ext_proto & EXTPROTO_VXLAN) {
+			udp_dst = VXLAN_UDP_PORT;
+			l2_len += sizeof(struct vxlanhdr);
+		} else
+			udp_dst = ETH_OVER_UDP_PORT;
 		break;
 	}
 	flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
@@ -267,7 +310,7 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 		h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
 		h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
 		tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) +
-			  sizeof(h_outer.l4hdr.udp);
+			  sizeof(h_outer.l4hdr.udp) + l2_len;
 		h_outer.l4hdr.udp.check = 0;
 		h_outer.l4hdr.udp.len = bpf_htons(tot_len);
 		break;
@@ -278,13 +321,24 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 	}
 
 	/* add L2 encap (if specified) */
+	l2_hdr = (__u8 *)&h_outer + olen;
 	switch (l2_proto) {
 	case ETH_P_MPLS_UC:
-		*((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+		*(__u32 *)l2_hdr = mpls_label;
 		break;
 	case ETH_P_TEB:
-		if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
-				       ETH_HLEN))
+		flags |= BPF_F_ADJ_ROOM_ENCAP_L2_ETH;
+
+		if (ext_proto & EXTPROTO_VXLAN) {
+			struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
+
+			vxlan_hdr->vx_flags = VXLAN_FLAGS;
+			vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8);
+
+			l2_hdr += sizeof(struct vxlanhdr);
+		}
+
+		if (bpf_skb_load_bytes(skb, 0, l2_hdr, ETH_HLEN))
 			return TC_ACT_SHOT;
 		break;
 	}
@@ -309,6 +363,12 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 	return TC_ACT_OK;
 }
 
+static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+				      __u16 l2_proto)
+{
+	return __encap_ipv6(skb, encap_proto, l2_proto, 0);
+}
+
 SEC("encap_ipip_none")
 int __encap_ipip_none(struct __sk_buff *skb)
 {
@@ -372,6 +432,17 @@ int __encap_udp_eth(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
+SEC("encap_vxlan_eth")
+int __encap_vxlan_eth(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return __encap_ipv4(skb, IPPROTO_UDP,
+				    ETH_P_TEB,
+				    EXTPROTO_VXLAN);
+	else
+		return TC_ACT_OK;
+}
+
 SEC("encap_sit_none")
 int __encap_sit_none(struct __sk_buff *skb)
 {
@@ -444,6 +515,17 @@ int __encap_ip6udp_eth(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
+SEC("encap_ip6vxlan_eth")
+int __encap_ip6vxlan_eth(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+		return __encap_ipv6(skb, IPPROTO_UDP,
+				    ETH_P_TEB,
+				    EXTPROTO_VXLAN);
+	else
+		return TC_ACT_OK;
+}
+
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
 	char buf[sizeof(struct v6hdr)];
@@ -479,6 +561,9 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		case ETH_OVER_UDP_PORT:
 			olen += ETH_HLEN;
 			break;
+		case VXLAN_UDP_PORT:
+			olen += ETH_HLEN + sizeof(struct vxlanhdr);
+			break;
 		}
 		break;
 	default:
diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
index 7c76b841b17b..c9dde9b9d987 100755
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh
@@ -44,8 +44,8 @@ setup() {
 	# clamp route to reserve room for tunnel headers
 	ip -netns "${ns1}" -4 route flush table main
 	ip -netns "${ns1}" -6 route flush table main
-	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1458 dev veth1
-	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1438 dev veth1
+	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1450 dev veth1
+	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1430 dev veth1
 
 	sleep 1
 
@@ -105,6 +105,12 @@ if [[ "$#" -eq "0" ]]; then
 	echo "sit"
 	$0 ipv6 sit none 100
 
+	echo "ip4 vxlan"
+	$0 ipv4 vxlan eth 2000
+
+	echo "ip6 vxlan"
+	$0 ipv6 ip6vxlan eth 2000
+
 	for mac in none mpls eth ; do
 		echo "ip gre $mac"
 		$0 ipv4 gre $mac 100
@@ -214,6 +220,9 @@ if [[ "$tuntype" =~ "udp" ]]; then
 	targs="encap fou encap-sport auto encap-dport $dport"
 elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
 	ttype=$gretaptype
+elif [[ "$tuntype" =~ "vxlan" && "$mac" == "eth" ]]; then
+	ttype="vxlan"
+	targs="id 1 dstport 8472 udp6zerocsumrx"
 else
 	ttype=$tuntype
 	targs=""
@@ -242,7 +251,7 @@ if [[ "$tuntype" == "ip6udp" && "$mac" == "mpls" ]]; then
 elif [[ "$tuntype" =~ "udp" && "$mac" == "eth" ]]; then
 	# No support for TEB fou tunnel; expect failure.
 	expect_tun_fail=1
-elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
+elif [[ "$tuntype" =~ (gre|vxlan) && "$mac" == "eth" ]]; then
 	# Share ethernet address between tunnel/veth2 so L2 decap works.
 	ethaddr=$(ip netns exec "${ns2}" ip link show veth2 | \
 		  awk '/ether/ { print $2 }')
-- 
cgit v1.2.3


From 299194a91451263020c73dd2a3b7e0218c88dbd0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 5 Mar 2021 14:40:50 +0100
Subject: selftests/bpf: Fix test_attach_probe for powerpc uprobes

When testing uprobes we the test gets GEP (Global Entry Point)
address from kallsyms, but then the function is called locally
so the uprobe is not triggered.

Fixing this by adjusting the address to LEP (Local Entry Point)
for powerpc arch plus instruction check stolen from ppc_function_entry
function pointed out and explained by Michael and Naveen.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Link: https://lore.kernel.org/bpf/20210305134050.139840-1-jolsa@kernel.org
---
 .../selftests/bpf/prog_tests/attach_probe.c        | 40 +++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index a0ee87c8e1ea..9dc4e3dfbcf3 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -2,6 +2,44 @@
 #include <test_progs.h>
 #include "test_attach_probe.skel.h"
 
+#if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2
+
+#define OP_RT_RA_MASK   0xffff0000UL
+#define LIS_R2          0x3c400000UL
+#define ADDIS_R2_R12    0x3c4c0000UL
+#define ADDI_R2_R2      0x38420000UL
+
+static ssize_t get_offset(ssize_t addr, ssize_t base)
+{
+	u32 *insn = (u32 *) addr;
+
+	/*
+	 * A PPC64 ABIv2 function may have a local and a global entry
+	 * point. We need to use the local entry point when patching
+	 * functions, so identify and step over the global entry point
+	 * sequence.
+	 *
+	 * The global entry point sequence is always of the form:
+	 *
+	 * addis r2,r12,XXXX
+	 * addi  r2,r2,XXXX
+	 *
+	 * A linker optimisation may convert the addis to lis:
+	 *
+	 * lis   r2,XXXX
+	 * addi  r2,r2,XXXX
+	 */
+	if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
+	     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
+	    ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2))
+		return (ssize_t)(insn + 2) - base;
+	else
+		return addr - base;
+}
+#else
+#define get_offset(addr, base) (addr - base)
+#endif
+
 ssize_t get_base_addr() {
 	size_t start, offset;
 	char buf[256];
@@ -36,7 +74,7 @@ void test_attach_probe(void)
 	if (CHECK(base_addr < 0, "get_base_addr",
 		  "failed to find base addr: %zd", base_addr))
 		return;
-	uprobe_offset = (size_t)&get_base_addr - base_addr;
+	uprobe_offset = get_offset((size_t)&get_base_addr, base_addr);
 
 	skel = test_attach_probe__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
-- 
cgit v1.2.3


From a0d73acc1e4bc1c542701e37b2e0e233fe6a271d Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Mon, 8 Mar 2021 19:28:31 +0100
Subject: selftests/bpf: Fix typo in Makefile

The selftest build fails when trying to install the scripts:

rsync: [sender] link_stat "tools/testing/selftests/bpf/test_docs_build.sh" failed: No such file or directory (2)

Fix the filename.

Fixes: a01d935b2e09 ("tools/bpf: Remove bpf-helpers from bpftool docs")
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210308182830.155784-1-jean-philippe@linaro.org
---
 tools/testing/selftests/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index b5827464c6b5..c3999587bc23 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -68,7 +68,7 @@ TEST_PROGS := test_kmod.sh \
 	test_bpftool_build.sh \
 	test_bpftool.sh \
 	test_bpftool_metadata.sh \
-	test_docs_build.sh \
+	test_doc_build.sh \
 	test_xsk.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
-- 
cgit v1.2.3


From 3fcd50d6f9a963a21e142d71be135eff6a374d2d Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 9 Mar 2021 01:56:48 +0100
Subject: selftests/bpf: Add BTF_KIND_FLOAT to test_core_reloc_size

Verify that bpf_core_field_size() is working correctly with floats.
Also document the required clang version.

Suggested-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210309005649.162480-2-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/README.rst                   | 9 +++++++++
 tools/testing/selftests/bpf/prog_tests/core_reloc.c      | 1 +
 tools/testing/selftests/bpf/progs/core_reloc_types.h     | 5 +++++
 tools/testing/selftests/bpf/progs/test_core_reloc_size.c | 3 +++
 4 files changed, 18 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index dbc8f6cc5c67..3464161c8eea 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -170,3 +170,12 @@ failures:
 .. _2: https://reviews.llvm.org/D85174
 .. _3: https://reviews.llvm.org/D83878
 .. _4: https://reviews.llvm.org/D83242
+
+Floating-point tests and Clang version
+======================================
+
+Certain selftests, e.g. core_reloc, require support for the floating-point
+types, which was introduced in `Clang 13`__. The older Clang versions will
+either crash when compiling these tests, or generate an incorrect BTF.
+
+__  https://reviews.llvm.org/D83289
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 06eb956ff7bb..d94dcead72e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -266,6 +266,7 @@ static int duration = 0;
 		.arr_elem_sz = sizeof(((type *)0)->arr_field[0]),	\
 		.ptr_sz = 8, /* always 8-byte pointer for BPF */	\
 		.enum_sz = sizeof(((type *)0)->enum_field),		\
+		.float_sz = sizeof(((type *)0)->float_field),		\
 	}
 
 #define SIZE_CASE(name) {						\
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 9a2850850121..9982eb969048 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -807,6 +807,7 @@ struct core_reloc_size_output {
 	int arr_elem_sz;
 	int ptr_sz;
 	int enum_sz;
+	int float_sz;
 };
 
 struct core_reloc_size {
@@ -816,6 +817,7 @@ struct core_reloc_size {
 	int arr_field[4];
 	void *ptr_field;
 	enum { VALUE = 123 } enum_field;
+	float float_field;
 };
 
 struct core_reloc_size___diff_sz {
@@ -825,6 +827,7 @@ struct core_reloc_size___diff_sz {
 	char arr_field[10];
 	void *ptr_field;
 	enum { OTHER_VALUE = 0xFFFFFFFFFFFFFFFF } enum_field;
+	double float_field;
 };
 
 /* Error case of two candidates with the fields (int_field) at the same
@@ -839,6 +842,7 @@ struct core_reloc_size___err_ambiguous1 {
 	int arr_field[4];
 	void *ptr_field;
 	enum { VALUE___1 = 123 } enum_field;
+	float float_field;
 };
 
 struct core_reloc_size___err_ambiguous2 {
@@ -850,6 +854,7 @@ struct core_reloc_size___err_ambiguous2 {
 	int arr_field[4];
 	void *ptr_field;
 	enum { VALUE___2 = 123 } enum_field;
+	float float_field;
 };
 
 /*
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
index d7fb6cfc7891..7b2d576aeea1 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c
@@ -21,6 +21,7 @@ struct core_reloc_size_output {
 	int arr_elem_sz;
 	int ptr_sz;
 	int enum_sz;
+	int float_sz;
 };
 
 struct core_reloc_size {
@@ -30,6 +31,7 @@ struct core_reloc_size {
 	int arr_field[4];
 	void *ptr_field;
 	enum { VALUE = 123 } enum_field;
+	float float_field;
 };
 
 SEC("raw_tracepoint/sys_enter")
@@ -45,6 +47,7 @@ int test_core_size(void *ctx)
 	out->arr_elem_sz = bpf_core_field_size(in->arr_field[0]);
 	out->ptr_sz = bpf_core_field_size(in->ptr_field);
 	out->enum_sz = bpf_core_field_size(in->enum_field);
+	out->float_sz = bpf_core_field_size(in->float_field);
 
 	return 0;
 }
-- 
cgit v1.2.3


From ccb0e23ca27445e2408f52944660f9e5e5d1c4b1 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 9 Mar 2021 01:56:49 +0100
Subject: selftests/bpf: Add BTF_KIND_FLOAT to btf_dump_test_case_syntax

Check that dumping various floating-point types produces a valid C
code.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210309005649.162480-3-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 31975c96e2c9..12b40dc81e14 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -205,6 +205,12 @@ struct struct_with_embedded_stuff {
 	int t[11];
 };
 
+struct float_struct {
+	float f;
+	const double *d;
+	volatile long double *ld;
+};
+
 struct root_struct {
 	enum e1 _1;
 	enum e2 _2;
@@ -219,6 +225,7 @@ struct root_struct {
 	union_fwd_t *_12;
 	union_fwd_ptr_t _13;
 	struct struct_with_embedded_stuff _14;
+	struct float_struct _15;
 };
 
 /* ------ END-EXPECTED-OUTPUT ------ */
-- 
cgit v1.2.3


From 11d39cfeecfc9d92a5faa2a55c228e796478e0cb Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 8 Mar 2021 20:43:22 -0800
Subject: selftests/bpf: Fix compiler warning in BPF_KPROBE definition in
 loop6.c

Add missing return type to BPF_KPROBE definition. Without it, compiler
generates the following warning:

progs/loop6.c:68:12: warning: type specifier missing, defaults to 'int' [-Wimplicit-int]
BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs,
           ^
1 warning generated.

Fixes: 86a35af628e5 ("selftests/bpf: Add a verifier scale test with unknown bounded loop")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210309044322.3487636-1-andrii@kernel.org
---
 tools/testing/selftests/bpf/progs/loop6.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/loop6.c b/tools/testing/selftests/bpf/progs/loop6.c
index 2a7141ac1656..38de0331e6b4 100644
--- a/tools/testing/selftests/bpf/progs/loop6.c
+++ b/tools/testing/selftests/bpf/progs/loop6.c
@@ -65,8 +65,8 @@ int config = 0;
 int result = 0;
 
 SEC("kprobe/virtqueue_add_sgs")
-BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs,
-	   unsigned int out_sgs, unsigned int in_sgs)
+int BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs,
+	       unsigned int out_sgs, unsigned int in_sgs)
 {
 	struct scatterlist *sgp = NULL;
 	__u64 length1 = 0, length2 = 0;
-- 
cgit v1.2.3


From 04ea63e34a2ee85cfd38578b3fc97b2d4c9dd573 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Wed, 10 Mar 2021 14:22:46 +0800
Subject: selftests/bpf: Fix warning comparing pointer to 0

Fix the following coccicheck warning:

./tools/testing/selftests/bpf/progs/test_global_func10.c:17:12-13:
WARNING comparing pointer to 0.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/1615357366-97612-1-git-send-email-jiapeng.chong@linux.alibaba.com
---
 tools/testing/selftests/bpf/progs/test_global_func10.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c
index 61c2ae92ce41..97b7031d0e22 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func10.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func10.c
@@ -14,7 +14,7 @@ struct Big {
 
 __noinline int foo(const struct Big *big)
 {
-	if (big == 0)
+	if (!big)
 		return 0;
 
 	return bpf_get_prandom_u32() < big->y;
-- 
cgit v1.2.3


From a9c80b03e586fd3819089fbd33c38fb65ad5e00c Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Wed, 10 Mar 2021 15:18:34 +0800
Subject: bpf: Fix warning comparing pointer to 0

Fix the following coccicheck warning:

./tools/testing/selftests/bpf/progs/fentry_test.c:67:12-13: WARNING
comparing pointer to 0.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/1615360714-30381-1-git-send-email-jiapeng.chong@linux.alibaba.com
---
 tools/testing/selftests/bpf/progs/fentry_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 5f645fdaba6f..52a550d281d9 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -64,7 +64,7 @@ __u64 test7_result = 0;
 SEC("fentry/bpf_fentry_test7")
 int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
 {
-	if (arg == 0)
+	if (!arg)
 		test7_result = 1;
 	return 0;
 }
-- 
cgit v1.2.3


From 8e815284a5f9351973a5860447941823acf1182d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 12 Mar 2021 17:50:21 +0100
Subject: selftests: fib_nexthops: Declutter test output

Before:

 # ./fib_nexthops.sh -t ipv4_torture

IPv4 runtime torture
--------------------
TEST: IPv4 torture test                                             [ OK ]
./fib_nexthops.sh: line 213: 19376 Killed                  ipv4_del_add_loop1
./fib_nexthops.sh: line 213: 19377 Killed                  ipv4_grp_replace_loop
./fib_nexthops.sh: line 213: 19378 Killed                  ip netns exec me ping -f 172.16.101.1 > /dev/null 2>&1
./fib_nexthops.sh: line 213: 19380 Killed                  ip netns exec me ping -f 172.16.101.2 > /dev/null 2>&1
./fib_nexthops.sh: line 213: 19381 Killed                  ip netns exec me mausezahn veth1 -B 172.16.101.2 -A 172.16.1.1 -c 0 -t tcp "dp=1-1023, flags=syn" > /dev/null 2>&1

Tests passed:   1
Tests failed:   0

 # ./fib_nexthops.sh -t ipv6_torture

IPv6 runtime torture
--------------------
TEST: IPv6 torture test                                             [ OK ]
./fib_nexthops.sh: line 213: 24453 Killed                  ipv6_del_add_loop1
./fib_nexthops.sh: line 213: 24454 Killed                  ipv6_grp_replace_loop
./fib_nexthops.sh: line 213: 24456 Killed                  ip netns exec me ping -f 2001:db8:101::1 > /dev/null 2>&1
./fib_nexthops.sh: line 213: 24457 Killed                  ip netns exec me ping -f 2001:db8:101::2 > /dev/null 2>&1
./fib_nexthops.sh: line 213: 24458 Killed                  ip netns exec me mausezahn -6 veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" > /dev/null 2>&1

Tests passed:   1
Tests failed:   0

After:

 # ./fib_nexthops.sh -t ipv4_torture

IPv4 runtime torture
--------------------
TEST: IPv4 torture test                                             [ OK ]

Tests passed:   1
Tests failed:   0

 # ./fib_nexthops.sh -t ipv6_torture

IPv6 runtime torture
--------------------
TEST: IPv6 torture test                                             [ OK ]

Tests passed:   1
Tests failed:   0

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_nexthops.sh | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index d98fb85e201c..91226ac50112 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -874,6 +874,7 @@ ipv6_torture()
 
 	sleep 300
 	kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+	wait $pid1 $pid2 $pid3 $pid4 $pid5 2>/dev/null
 
 	# if we did not crash, success
 	log_test 0 0 "IPv6 torture test"
@@ -1476,6 +1477,7 @@ ipv4_torture()
 
 	sleep 300
 	kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+	wait $pid1 $pid2 $pid3 $pid4 $pid5 2>/dev/null
 
 	# if we did not crash, success
 	log_test 0 0 "IPv4 torture test"
-- 
cgit v1.2.3


From a8f9952d218d816ff1a13c9385edd821a8da527d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 12 Mar 2021 17:50:22 +0100
Subject: selftests: fib_nexthops: List each test case in a different line

The lines with the IPv4 and IPv6 test cases are already very long and
more test cases will be added in subsequent patches.

List each test case in a different line to make it easier to extend the
test with more test cases.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_nexthops.sh | 30 +++++++++++++++++++++++++----
 1 file changed, 26 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 91226ac50112..c840aa88ff18 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -19,10 +19,32 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-IPV4_TESTS="ipv4_fcnal ipv4_grp_fcnal ipv4_withv6_fcnal ipv4_fcnal_runtime ipv4_large_grp ipv4_compat_mode ipv4_fdb_grp_fcnal ipv4_torture"
-IPV6_TESTS="ipv6_fcnal ipv6_grp_fcnal ipv6_fcnal_runtime ipv6_large_grp ipv6_compat_mode ipv6_fdb_grp_fcnal ipv6_torture"
-
-ALL_TESTS="basic ${IPV4_TESTS} ${IPV6_TESTS}"
+IPV4_TESTS="
+	ipv4_fcnal
+	ipv4_grp_fcnal
+	ipv4_withv6_fcnal
+	ipv4_fcnal_runtime
+	ipv4_large_grp
+	ipv4_compat_mode
+	ipv4_fdb_grp_fcnal
+	ipv4_torture
+"
+
+IPV6_TESTS="
+	ipv6_fcnal
+	ipv6_grp_fcnal
+	ipv6_fcnal_runtime
+	ipv6_large_grp
+	ipv6_compat_mode
+	ipv6_fdb_grp_fcnal
+	ipv6_torture
+"
+
+ALL_TESTS="
+	basic
+	${IPV4_TESTS}
+	${IPV6_TESTS}
+"
 TESTS="${ALL_TESTS}"
 VERBOSE=0
 PAUSE_ON_FAIL=no
-- 
cgit v1.2.3


From 557205f47dc47afeaf80707845cda8ec79ea4cb0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 12 Mar 2021 17:50:23 +0100
Subject: selftests: fib_nexthops: Test resilient nexthop groups

Add test cases for resilient nexthop groups. Exhaustive forwarding tests
are added separately under net/forwarding/.

Examples:

 # ./fib_nexthops.sh -t basic_res

Basic resilient nexthop group functional tests
----------------------------------------------
TEST: Add a nexthop group with default parameters                   [ OK ]
TEST: Get a nexthop group with default parameters                   [ OK ]
TEST: Get a nexthop group with non-default parameters               [ OK ]
TEST: Add a nexthop group with 0 buckets                            [ OK ]
TEST: Replace nexthop group parameters                              [ OK ]
TEST: Get a nexthop group after replacing parameters                [ OK ]
TEST: Replace idle timer                                            [ OK ]
TEST: Get a nexthop group after replacing idle timer                [ OK ]
TEST: Replace unbalanced timer                                      [ OK ]
TEST: Get a nexthop group after replacing unbalanced timer          [ OK ]
TEST: Replace with no parameters                                    [ OK ]
TEST: Get a nexthop group after replacing no parameters             [ OK ]
TEST: Replace nexthop group type - implicit                         [ OK ]
TEST: Replace nexthop group type - explicit                         [ OK ]
TEST: Replace number of nexthop buckets                             [ OK ]
TEST: Get a nexthop group after replacing with invalid parameters   [ OK ]
TEST: Dump all nexthop buckets                                      [ OK ]
TEST: Dump all nexthop buckets in a group                           [ OK ]
TEST: Dump all nexthop buckets with a specific nexthop device       [ OK ]
TEST: Dump all nexthop buckets with a specific nexthop identifier   [ OK ]
TEST: Dump all nexthop buckets in a non-existent group              [ OK ]
TEST: Dump all nexthop buckets in a non-resilient group             [ OK ]
TEST: Dump all nexthop buckets using a non-existent device          [ OK ]
TEST: Dump all nexthop buckets with invalid 'groups' keyword        [ OK ]
TEST: Dump all nexthop buckets with invalid 'fdb' keyword           [ OK ]
TEST: Get a valid nexthop bucket                                    [ OK ]
TEST: Get a nexthop bucket with valid group, but invalid index      [ OK ]
TEST: Get a nexthop bucket from a non-resilient group               [ OK ]
TEST: Get a nexthop bucket from a non-existent group                [ OK ]

Tests passed:  29
Tests failed:   0

 # ./fib_nexthops.sh -t ipv4_large_res_grp

IPv4 large resilient group (128k buckets)
-----------------------------------------
TEST: Dump large (x131072) nexthop buckets                          [ OK ]

Tests passed:   1
Tests failed:   0

 # ./fib_nexthops.sh -t ipv6_large_res_grp

IPv6 large resilient group (128k buckets)
-----------------------------------------
TEST: Dump large (x131072) nexthop buckets                          [ OK ]

Tests passed:   1
Tests failed:   0

 # ./fib_nexthops.sh -t ipv4_res_torture

IPv4 runtime resilient nexthop group torture
--------------------------------------------
TEST: IPv4 resilient nexthop group torture test                     [ OK ]

Tests passed:   1
Tests failed:   0

 # ./fib_nexthops.sh -t ipv6_res_torture

IPv6 runtime resilient nexthop group torture
--------------------------------------------
TEST: IPv6 resilient nexthop group torture test                     [ OK ]

Tests passed:   1
Tests failed:   0

 # ./fib_nexthops.sh -t ipv4_res_grp_fcnal

IPv4 resilient groups functional
--------------------------------
TEST: Nexthop group updated when entry is deleted                   [ OK ]
TEST: Nexthop buckets updated when entry is deleted                 [ OK ]
TEST: Nexthop group updated after replace                           [ OK ]
TEST: Nexthop buckets updated after replace                         [ OK ]
TEST: Nexthop group updated when entry is deleted - nECMP           [ OK ]
TEST: Nexthop buckets updated when entry is deleted - nECMP         [ OK ]
TEST: Nexthop group updated after replace - nECMP                   [ OK ]
TEST: Nexthop buckets updated after replace - nECMP                 [ OK ]

Tests passed:   8
Tests failed:   0

 # ./fib_nexthops.sh -t ipv6_res_grp_fcnal

IPv6 resilient groups functional
--------------------------------
TEST: Nexthop group updated when entry is deleted                   [ OK ]
TEST: Nexthop buckets updated when entry is deleted                 [ OK ]
TEST: Nexthop group updated after replace                           [ OK ]
TEST: Nexthop buckets updated after replace                         [ OK ]
TEST: Nexthop group updated when entry is deleted - nECMP           [ OK ]
TEST: Nexthop buckets updated when entry is deleted - nECMP         [ OK ]
TEST: Nexthop group updated after replace - nECMP                   [ OK ]
TEST: Nexthop buckets updated after replace - nECMP                 [ OK ]

Tests passed:   8
Tests failed:   0

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Co-developed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_nexthops.sh | 517 ++++++++++++++++++++++++++++
 1 file changed, 517 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index c840aa88ff18..56dd0c6f2e96 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -22,26 +22,33 @@ ksft_skip=4
 IPV4_TESTS="
 	ipv4_fcnal
 	ipv4_grp_fcnal
+	ipv4_res_grp_fcnal
 	ipv4_withv6_fcnal
 	ipv4_fcnal_runtime
 	ipv4_large_grp
+	ipv4_large_res_grp
 	ipv4_compat_mode
 	ipv4_fdb_grp_fcnal
 	ipv4_torture
+	ipv4_res_torture
 "
 
 IPV6_TESTS="
 	ipv6_fcnal
 	ipv6_grp_fcnal
+	ipv6_res_grp_fcnal
 	ipv6_fcnal_runtime
 	ipv6_large_grp
+	ipv6_large_res_grp
 	ipv6_compat_mode
 	ipv6_fdb_grp_fcnal
 	ipv6_torture
+	ipv6_res_torture
 "
 
 ALL_TESTS="
 	basic
+	basic_res
 	${IPV4_TESTS}
 	${IPV6_TESTS}
 "
@@ -254,6 +261,19 @@ check_nexthop()
 	check_output "${out}" "${expected}"
 }
 
+check_nexthop_bucket()
+{
+	local nharg="$1"
+	local expected="$2"
+	local out
+
+	# remove the idle time since we cannot match it
+	out=$($IP nexthop bucket ${nharg} \
+		| sed s/idle_time\ [0-9.]*\ // 2>/dev/null)
+
+	check_output "${out}" "${expected}"
+}
+
 check_route()
 {
 	local pfx="$1"
@@ -330,6 +350,25 @@ check_large_grp()
 	log_test $? 0 "Dump large (x$ecmp) ecmp groups"
 }
 
+check_large_res_grp()
+{
+	local ipv=$1
+	local buckets=$2
+	local ipstr=""
+
+	if [ $ipv -eq 4 ]; then
+		ipstr="172.16.1.2"
+	else
+		ipstr="2001:db8:91::2"
+	fi
+
+	# create a resilient group with $buckets buckets and dump them
+	run_cmd "$IP nexthop add id 100 via $ipstr dev veth1"
+	run_cmd "$IP nexthop add id 1000 group 100 type resilient buckets $buckets"
+	run_cmd "$IP nexthop bucket list"
+	log_test $? 0 "Dump large (x$buckets) nexthop buckets"
+}
+
 start_ip_monitor()
 {
 	local mtype=$1
@@ -366,6 +405,15 @@ check_nexthop_fdb_support()
 	fi
 }
 
+check_nexthop_res_support()
+{
+	$IP nexthop help 2>&1 | grep -q resilient
+	if [ $? -ne 0 ]; then
+		echo "SKIP: iproute2 too old, missing resilient nexthop group support"
+		return $ksft_skip
+	fi
+}
+
 ipv6_fdb_grp_fcnal()
 {
 	local rc
@@ -688,6 +736,70 @@ ipv6_grp_fcnal()
 	log_test $? 2 "Nexthop group can not have a blackhole and another nexthop"
 }
 
+ipv6_res_grp_fcnal()
+{
+	local rc
+
+	echo
+	echo "IPv6 resilient groups functional"
+	echo "--------------------------------"
+
+	check_nexthop_res_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	#
+	# migration of nexthop buckets - equal weights
+	#
+	run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop add id 102 group 62/63 type resilient buckets 2 idle_timer 0"
+
+	run_cmd "$IP nexthop del id 63"
+	check_nexthop "id 102" \
+		"id 102 group 62 type resilient buckets 2 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated when entry is deleted"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 62 id 102 index 1 nhid 62"
+	log_test $? 0 "Nexthop buckets updated when entry is deleted"
+
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop replace id 102 group 62/63 type resilient buckets 2 idle_timer 0"
+	check_nexthop "id 102" \
+		"id 102 group 62/63 type resilient buckets 2 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated after replace"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 63 id 102 index 1 nhid 62"
+	log_test $? 0 "Nexthop buckets updated after replace"
+
+	$IP nexthop flush >/dev/null 2>&1
+
+	#
+	# migration of nexthop buckets - unequal weights
+	#
+	run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop add id 102 group 62,3/63,1 type resilient buckets 4 idle_timer 0"
+
+	run_cmd "$IP nexthop del id 63"
+	check_nexthop "id 102" \
+		"id 102 group 62,3 type resilient buckets 4 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated when entry is deleted - nECMP"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 62 id 102 index 1 nhid 62 id 102 index 2 nhid 62 id 102 index 3 nhid 62"
+	log_test $? 0 "Nexthop buckets updated when entry is deleted - nECMP"
+
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop replace id 102 group 62,3/63,1 type resilient buckets 4 idle_timer 0"
+	check_nexthop "id 102" \
+		"id 102 group 62,3/63 type resilient buckets 4 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated after replace - nECMP"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 63 id 102 index 1 nhid 62 id 102 index 2 nhid 62 id 102 index 3 nhid 62"
+	log_test $? 0 "Nexthop buckets updated after replace - nECMP"
+}
+
 ipv6_fcnal_runtime()
 {
 	local rc
@@ -846,6 +958,22 @@ ipv6_large_grp()
 	$IP nexthop flush >/dev/null 2>&1
 }
 
+ipv6_large_res_grp()
+{
+	echo
+	echo "IPv6 large resilient group (128k buckets)"
+	echo "-----------------------------------------"
+
+	check_nexthop_res_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	check_large_res_grp 6 $((128 * 1024))
+
+	$IP nexthop flush >/dev/null 2>&1
+}
+
 ipv6_del_add_loop1()
 {
 	while :; do
@@ -902,6 +1030,61 @@ ipv6_torture()
 	log_test 0 0 "IPv6 torture test"
 }
 
+ipv6_res_grp_replace_loop()
+{
+	while :; do
+		$IP nexthop replace id 102 group 100/101 type resilient
+	done >/dev/null 2>&1
+}
+
+ipv6_res_torture()
+{
+	local pid1
+	local pid2
+	local pid3
+	local pid4
+	local pid5
+
+	echo
+	echo "IPv6 runtime resilient nexthop group torture"
+	echo "--------------------------------------------"
+
+	check_nexthop_res_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	if [ ! -x "$(command -v mausezahn)" ]; then
+		echo "SKIP: Could not run test; need mausezahn tool"
+		return
+	fi
+
+	run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth3"
+	run_cmd "$IP nexthop add id 102 group 100/101 type resilient buckets 512 idle_timer 0"
+	run_cmd "$IP route add 2001:db8:101::1 nhid 102"
+	run_cmd "$IP route add 2001:db8:101::2 nhid 102"
+
+	ipv6_del_add_loop1 &
+	pid1=$!
+	ipv6_res_grp_replace_loop &
+	pid2=$!
+	ip netns exec me ping -f 2001:db8:101::1 >/dev/null 2>&1 &
+	pid3=$!
+	ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
+	pid4=$!
+	ip netns exec me mausezahn -6 veth1 \
+			    -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 \
+			    -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	pid5=$!
+
+	sleep 300
+	kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+	wait $pid1 $pid2 $pid3 $pid4 $pid5 2>/dev/null
+
+	# if we did not crash, success
+	log_test 0 0 "IPv6 resilient nexthop group torture test"
+}
 
 ipv4_fcnal()
 {
@@ -1061,6 +1244,70 @@ ipv4_grp_fcnal()
 	log_test $? 2 "Nexthop group can not have a blackhole and another nexthop"
 }
 
+ipv4_res_grp_fcnal()
+{
+	local rc
+
+	echo
+	echo "IPv4 resilient groups functional"
+	echo "--------------------------------"
+
+	check_nexthop_res_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	#
+	# migration of nexthop buckets - equal weights
+	#
+	run_cmd "$IP nexthop add id 12 via 172.16.1.2 dev veth1"
+	run_cmd "$IP nexthop add id 13 via 172.16.1.3 dev veth1"
+	run_cmd "$IP nexthop add id 102 group 12/13 type resilient buckets 2 idle_timer 0"
+
+	run_cmd "$IP nexthop del id 13"
+	check_nexthop "id 102" \
+		"id 102 group 12 type resilient buckets 2 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated when entry is deleted"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 12 id 102 index 1 nhid 12"
+	log_test $? 0 "Nexthop buckets updated when entry is deleted"
+
+	run_cmd "$IP nexthop add id 13 via 172.16.1.3 dev veth1"
+	run_cmd "$IP nexthop replace id 102 group 12/13 type resilient buckets 2 idle_timer 0"
+	check_nexthop "id 102" \
+		"id 102 group 12/13 type resilient buckets 2 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated after replace"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 13 id 102 index 1 nhid 12"
+	log_test $? 0 "Nexthop buckets updated after replace"
+
+	$IP nexthop flush >/dev/null 2>&1
+
+	#
+	# migration of nexthop buckets - unequal weights
+	#
+	run_cmd "$IP nexthop add id 12 via 172.16.1.2 dev veth1"
+	run_cmd "$IP nexthop add id 13 via 172.16.1.3 dev veth1"
+	run_cmd "$IP nexthop add id 102 group 12,3/13,1 type resilient buckets 4 idle_timer 0"
+
+	run_cmd "$IP nexthop del id 13"
+	check_nexthop "id 102" \
+		"id 102 group 12,3 type resilient buckets 4 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated when entry is deleted - nECMP"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 12 id 102 index 1 nhid 12 id 102 index 2 nhid 12 id 102 index 3 nhid 12"
+	log_test $? 0 "Nexthop buckets updated when entry is deleted - nECMP"
+
+	run_cmd "$IP nexthop add id 13 via 172.16.1.3 dev veth1"
+	run_cmd "$IP nexthop replace id 102 group 12,3/13,1 type resilient buckets 4 idle_timer 0"
+	check_nexthop "id 102" \
+		"id 102 group 12,3/13 type resilient buckets 4 idle_timer 0 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Nexthop group updated after replace - nECMP"
+	check_nexthop_bucket "list id 102" \
+		"id 102 index 0 nhid 13 id 102 index 1 nhid 12 id 102 index 2 nhid 12 id 102 index 3 nhid 12"
+	log_test $? 0 "Nexthop buckets updated after replace - nECMP"
+}
+
 ipv4_withv6_fcnal()
 {
 	local lladdr
@@ -1282,6 +1529,22 @@ ipv4_large_grp()
 	$IP nexthop flush >/dev/null 2>&1
 }
 
+ipv4_large_res_grp()
+{
+	echo
+	echo "IPv4 large resilient group (128k buckets)"
+	echo "-----------------------------------------"
+
+	check_nexthop_res_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	check_large_res_grp 4 $((128 * 1024))
+
+	$IP nexthop flush >/dev/null 2>&1
+}
+
 sysctl_nexthop_compat_mode_check()
 {
 	local sysctlname="net.ipv4.nexthop_compat_mode"
@@ -1505,6 +1768,62 @@ ipv4_torture()
 	log_test 0 0 "IPv4 torture test"
 }
 
+ipv4_res_grp_replace_loop()
+{
+	while :; do
+		$IP nexthop replace id 102 group 100/101 type resilient
+	done >/dev/null 2>&1
+}
+
+ipv4_res_torture()
+{
+	local pid1
+	local pid2
+	local pid3
+	local pid4
+	local pid5
+
+	echo
+	echo "IPv4 runtime resilient nexthop group torture"
+	echo "--------------------------------------------"
+
+	check_nexthop_res_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	if [ ! -x "$(command -v mausezahn)" ]; then
+		echo "SKIP: Could not run test; need mausezahn tool"
+		return
+	fi
+
+	run_cmd "$IP nexthop add id 100 via 172.16.1.2 dev veth1"
+	run_cmd "$IP nexthop add id 101 via 172.16.2.2 dev veth3"
+	run_cmd "$IP nexthop add id 102 group 100/101 type resilient buckets 512 idle_timer 0"
+	run_cmd "$IP route add 172.16.101.1 nhid 102"
+	run_cmd "$IP route add 172.16.101.2 nhid 102"
+
+	ipv4_del_add_loop1 &
+	pid1=$!
+	ipv4_res_grp_replace_loop &
+	pid2=$!
+	ip netns exec me ping -f 172.16.101.1 >/dev/null 2>&1 &
+	pid3=$!
+	ip netns exec me ping -f 172.16.101.2 >/dev/null 2>&1 &
+	pid4=$!
+	ip netns exec me mausezahn veth1 \
+				-B 172.16.101.2 -A 172.16.1.1 -c 0 \
+				-t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	pid5=$!
+
+	sleep 300
+	kill -9 $pid1 $pid2 $pid3 $pid4 $pid5
+	wait $pid1 $pid2 $pid3 $pid4 $pid5 2>/dev/null
+
+	# if we did not crash, success
+	log_test 0 0 "IPv4 resilient nexthop group torture test"
+}
+
 basic()
 {
 	echo
@@ -1616,6 +1935,204 @@ basic()
 	$IP nexthop flush >/dev/null 2>&1
 }
 
+check_nexthop_buckets_balance()
+{
+	local nharg=$1; shift
+	local ret
+
+	while (($# > 0)); do
+		local selector=$1; shift
+		local condition=$1; shift
+		local count
+
+		count=$($IP -j nexthop bucket ${nharg} ${selector} | jq length)
+		(( $count $condition ))
+		ret=$?
+		if ((ret != 0)); then
+			return $ret
+		fi
+	done
+
+	return 0
+}
+
+basic_res()
+{
+	echo
+	echo "Basic resilient nexthop group functional tests"
+	echo "----------------------------------------------"
+
+	check_nexthop_res_support
+	if [ $? -eq $ksft_skip ]; then
+		return $ksft_skip
+	fi
+
+	run_cmd "$IP nexthop add id 1 dev veth1"
+
+	#
+	# resilient nexthop group addition
+	#
+
+	run_cmd "$IP nexthop add id 101 group 1 type resilient buckets 8"
+	log_test $? 0 "Add a nexthop group with default parameters"
+
+	run_cmd "$IP nexthop get id 101"
+	check_nexthop "id 101" \
+		"id 101 group 1 type resilient buckets 8 idle_timer 120 unbalanced_timer 0 unbalanced_time 0"
+	log_test $? 0 "Get a nexthop group with default parameters"
+
+	run_cmd "$IP nexthop add id 102 group 1 type resilient
+			buckets 4 idle_timer 100 unbalanced_timer 5"
+	run_cmd "$IP nexthop get id 102"
+	check_nexthop "id 102" \
+		"id 102 group 1 type resilient buckets 4 idle_timer 100 unbalanced_timer 5 unbalanced_time 0"
+	log_test $? 0 "Get a nexthop group with non-default parameters"
+
+	run_cmd "$IP nexthop add id 103 group 1 type resilient buckets 0"
+	log_test $? 2 "Add a nexthop group with 0 buckets"
+
+	#
+	# resilient nexthop group replacement
+	#
+
+	run_cmd "$IP nexthop replace id 101 group 1 type resilient
+			buckets 8 idle_timer 240 unbalanced_timer 80"
+	log_test $? 0 "Replace nexthop group parameters"
+	check_nexthop "id 101" \
+		"id 101 group 1 type resilient buckets 8 idle_timer 240 unbalanced_timer 80 unbalanced_time 0"
+	log_test $? 0 "Get a nexthop group after replacing parameters"
+
+	run_cmd "$IP nexthop replace id 101 group 1 type resilient idle_timer 512"
+	log_test $? 0 "Replace idle timer"
+	check_nexthop "id 101" \
+		"id 101 group 1 type resilient buckets 8 idle_timer 512 unbalanced_timer 80 unbalanced_time 0"
+	log_test $? 0 "Get a nexthop group after replacing idle timer"
+
+	run_cmd "$IP nexthop replace id 101 group 1 type resilient unbalanced_timer 256"
+	log_test $? 0 "Replace unbalanced timer"
+	check_nexthop "id 101" \
+		"id 101 group 1 type resilient buckets 8 idle_timer 512 unbalanced_timer 256 unbalanced_time 0"
+	log_test $? 0 "Get a nexthop group after replacing unbalanced timer"
+
+	run_cmd "$IP nexthop replace id 101 group 1 type resilient"
+	log_test $? 0 "Replace with no parameters"
+	check_nexthop "id 101" \
+		"id 101 group 1 type resilient buckets 8 idle_timer 512 unbalanced_timer 256 unbalanced_time 0"
+	log_test $? 0 "Get a nexthop group after replacing no parameters"
+
+	run_cmd "$IP nexthop replace id 101 group 1"
+	log_test $? 2 "Replace nexthop group type - implicit"
+
+	run_cmd "$IP nexthop replace id 101 group 1 type mpath"
+	log_test $? 2 "Replace nexthop group type - explicit"
+
+	run_cmd "$IP nexthop replace id 101 group 1 type resilient buckets 1024"
+	log_test $? 2 "Replace number of nexthop buckets"
+
+	check_nexthop "id 101" \
+		"id 101 group 1 type resilient buckets 8 idle_timer 512 unbalanced_timer 256 unbalanced_time 0"
+	log_test $? 0 "Get a nexthop group after replacing with invalid parameters"
+
+	#
+	# resilient nexthop buckets dump
+	#
+
+	$IP nexthop flush >/dev/null 2>&1
+	run_cmd "$IP nexthop add id 1 dev veth1"
+	run_cmd "$IP nexthop add id 2 dev veth3"
+	run_cmd "$IP nexthop add id 101 group 1/2 type resilient buckets 4"
+	run_cmd "$IP nexthop add id 201 group 1/2"
+
+	check_nexthop_bucket "" \
+		"id 101 index 0 nhid 2 id 101 index 1 nhid 2 id 101 index 2 nhid 1 id 101 index 3 nhid 1"
+	log_test $? 0 "Dump all nexthop buckets"
+
+	check_nexthop_bucket "list id 101" \
+		"id 101 index 0 nhid 2 id 101 index 1 nhid 2 id 101 index 2 nhid 1 id 101 index 3 nhid 1"
+	log_test $? 0 "Dump all nexthop buckets in a group"
+
+	(( $($IP -j nexthop bucket list id 101 |
+	     jq '[.[] | select(.bucket.idle_time > 0 and
+	                       .bucket.idle_time < 2)] | length') == 4 ))
+	log_test $? 0 "All nexthop buckets report a positive near-zero idle time"
+
+	check_nexthop_bucket "list dev veth1" \
+		"id 101 index 2 nhid 1 id 101 index 3 nhid 1"
+	log_test $? 0 "Dump all nexthop buckets with a specific nexthop device"
+
+	check_nexthop_bucket "list nhid 2" \
+		"id 101 index 0 nhid 2 id 101 index 1 nhid 2"
+	log_test $? 0 "Dump all nexthop buckets with a specific nexthop identifier"
+
+	run_cmd "$IP nexthop bucket list id 111"
+	log_test $? 2 "Dump all nexthop buckets in a non-existent group"
+
+	run_cmd "$IP nexthop bucket list id 201"
+	log_test $? 2 "Dump all nexthop buckets in a non-resilient group"
+
+	run_cmd "$IP nexthop bucket list dev bla"
+	log_test $? 255 "Dump all nexthop buckets using a non-existent device"
+
+	run_cmd "$IP nexthop bucket list groups"
+	log_test $? 255 "Dump all nexthop buckets with invalid 'groups' keyword"
+
+	run_cmd "$IP nexthop bucket list fdb"
+	log_test $? 255 "Dump all nexthop buckets with invalid 'fdb' keyword"
+
+	#
+	# resilient nexthop buckets get requests
+	#
+
+	check_nexthop_bucket "get id 101 index 0" "id 101 index 0 nhid 2"
+	log_test $? 0 "Get a valid nexthop bucket"
+
+	run_cmd "$IP nexthop bucket get id 101 index 999"
+	log_test $? 2 "Get a nexthop bucket with valid group, but invalid index"
+
+	run_cmd "$IP nexthop bucket get id 201 index 0"
+	log_test $? 2 "Get a nexthop bucket from a non-resilient group"
+
+	run_cmd "$IP nexthop bucket get id 999 index 0"
+	log_test $? 2 "Get a nexthop bucket from a non-existent group"
+
+	#
+	# tests for bucket migration
+	#
+
+	$IP nexthop flush >/dev/null 2>&1
+
+	run_cmd "$IP nexthop add id 1 dev veth1"
+	run_cmd "$IP nexthop add id 2 dev veth3"
+	run_cmd "$IP nexthop add id 101
+			group 1/2 type resilient buckets 10
+			idle_timer 1 unbalanced_timer 20"
+
+	check_nexthop_buckets_balance "list id 101" \
+				      "nhid 1" "== 5" \
+				      "nhid 2" "== 5"
+	log_test $? 0 "Initial bucket allocation"
+
+	run_cmd "$IP nexthop replace id 101
+			group 1,2/2,3 type resilient"
+	check_nexthop_buckets_balance "list id 101" \
+				      "nhid 1" "== 4" \
+				      "nhid 2" "== 6"
+	log_test $? 0 "Bucket allocation after replace"
+
+	# Check that increase in idle timer does not make buckets appear busy.
+	run_cmd "$IP nexthop replace id 101
+			group 1,2/2,3 type resilient
+			idle_timer 10"
+	run_cmd "$IP nexthop replace id 101
+			group 1/2 type resilient"
+	check_nexthop_buckets_balance "list id 101" \
+				      "nhid 1" "== 5" \
+				      "nhid 2" "== 5"
+	log_test $? 0 "Buckets migrated after idle timer change"
+
+	$IP nexthop flush >/dev/null 2>&1
+}
+
 ################################################################################
 # usage
 
-- 
cgit v1.2.3


From 386e3792b52a4d815aefb30d8c049484dce7bdd2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 12 Mar 2021 17:50:24 +0100
Subject: selftests: forwarding: Add resilient hashing test

Verify that IPv4 and IPv6 multipath forwarding works correctly with
resilient nexthop groups and with different weights.

Test that when the idle timer is not zero, the resilient groups are not
rebalanced - because the nexthop buckets are considered active - and the
initial weights (1:1) are used.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/router_mpath_nh_res.sh          | 400 +++++++++++++++++++++
 1 file changed, 400 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
new file mode 100755
index 000000000000..4898dd4118f1
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
@@ -0,0 +1,400 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	multipath_test
+"
+NUM_NETIFS=8
+source lib.sh
+
+h1_create()
+{
+	vrf_create "vrf-h1"
+	ip link set dev $h1 master vrf-h1
+
+	ip link set dev vrf-h1 up
+	ip link set dev $h1 up
+
+	ip address add 192.0.2.2/24 dev $h1
+	ip address add 2001:db8:1::2/64 dev $h1
+
+	ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+	ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+	ip route del 2001:db8:2::/64 vrf vrf-h1
+	ip route del 198.51.100.0/24 vrf vrf-h1
+
+	ip address del 2001:db8:1::2/64 dev $h1
+	ip address del 192.0.2.2/24 dev $h1
+
+	ip link set dev $h1 down
+	vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+	vrf_create "vrf-h2"
+	ip link set dev $h2 master vrf-h2
+
+	ip link set dev vrf-h2 up
+	ip link set dev $h2 up
+
+	ip address add 198.51.100.2/24 dev $h2
+	ip address add 2001:db8:2::2/64 dev $h2
+
+	ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+	ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del 2001:db8:1::/64 vrf vrf-h2
+	ip route del 192.0.2.0/24 vrf vrf-h2
+
+	ip address del 2001:db8:2::2/64 dev $h2
+	ip address del 198.51.100.2/24 dev $h2
+
+	ip link set dev $h2 down
+	vrf_destroy "vrf-h2"
+}
+
+router1_create()
+{
+	vrf_create "vrf-r1"
+	ip link set dev $rp11 master vrf-r1
+	ip link set dev $rp12 master vrf-r1
+	ip link set dev $rp13 master vrf-r1
+
+	ip link set dev vrf-r1 up
+	ip link set dev $rp11 up
+	ip link set dev $rp12 up
+	ip link set dev $rp13 up
+
+	ip address add 192.0.2.1/24 dev $rp11
+	ip address add 2001:db8:1::1/64 dev $rp11
+
+	ip address add 169.254.2.12/24 dev $rp12
+	ip address add fe80:2::12/64 dev $rp12
+
+	ip address add 169.254.3.13/24 dev $rp13
+	ip address add fe80:3::13/64 dev $rp13
+}
+
+router1_destroy()
+{
+	ip route del 2001:db8:2::/64 vrf vrf-r1
+	ip route del 198.51.100.0/24 vrf vrf-r1
+
+	ip address del fe80:3::13/64 dev $rp13
+	ip address del 169.254.3.13/24 dev $rp13
+
+	ip address del fe80:2::12/64 dev $rp12
+	ip address del 169.254.2.12/24 dev $rp12
+
+	ip address del 2001:db8:1::1/64 dev $rp11
+	ip address del 192.0.2.1/24 dev $rp11
+
+	ip nexthop del id 103
+	ip nexthop del id 101
+	ip nexthop del id 102
+	ip nexthop del id 106
+	ip nexthop del id 104
+	ip nexthop del id 105
+
+	ip link set dev $rp13 down
+	ip link set dev $rp12 down
+	ip link set dev $rp11 down
+
+	vrf_destroy "vrf-r1"
+}
+
+router2_create()
+{
+	vrf_create "vrf-r2"
+	ip link set dev $rp21 master vrf-r2
+	ip link set dev $rp22 master vrf-r2
+	ip link set dev $rp23 master vrf-r2
+
+	ip link set dev vrf-r2 up
+	ip link set dev $rp21 up
+	ip link set dev $rp22 up
+	ip link set dev $rp23 up
+
+	ip address add 198.51.100.1/24 dev $rp21
+	ip address add 2001:db8:2::1/64 dev $rp21
+
+	ip address add 169.254.2.22/24 dev $rp22
+	ip address add fe80:2::22/64 dev $rp22
+
+	ip address add 169.254.3.23/24 dev $rp23
+	ip address add fe80:3::23/64 dev $rp23
+}
+
+router2_destroy()
+{
+	ip route del 2001:db8:1::/64 vrf vrf-r2
+	ip route del 192.0.2.0/24 vrf vrf-r2
+
+	ip address del fe80:3::23/64 dev $rp23
+	ip address del 169.254.3.23/24 dev $rp23
+
+	ip address del fe80:2::22/64 dev $rp22
+	ip address del 169.254.2.22/24 dev $rp22
+
+	ip address del 2001:db8:2::1/64 dev $rp21
+	ip address del 198.51.100.1/24 dev $rp21
+
+	ip nexthop del id 201
+	ip nexthop del id 202
+	ip nexthop del id 204
+	ip nexthop del id 205
+
+	ip link set dev $rp23 down
+	ip link set dev $rp22 down
+	ip link set dev $rp21 down
+
+	vrf_destroy "vrf-r2"
+}
+
+routing_nh_obj()
+{
+	ip nexthop add id 101 via 169.254.2.22 dev $rp12
+	ip nexthop add id 102 via 169.254.3.23 dev $rp13
+	ip nexthop add id 103 group 101/102 type resilient buckets 512 \
+		idle_timer 0
+	ip route add 198.51.100.0/24 vrf vrf-r1 nhid 103
+
+	ip nexthop add id 104 via fe80:2::22 dev $rp12
+	ip nexthop add id 105 via fe80:3::23 dev $rp13
+	ip nexthop add id 106 group 104/105 type resilient buckets 512 \
+		idle_timer 0
+	ip route add 2001:db8:2::/64 vrf vrf-r1 nhid 106
+
+	ip nexthop add id 201 via 169.254.2.12 dev $rp22
+	ip nexthop add id 202 via 169.254.3.13 dev $rp23
+	ip nexthop add id 203 group 201/202 type resilient buckets 512 \
+		idle_timer 0
+	ip route add 192.0.2.0/24 vrf vrf-r2 nhid 203
+
+	ip nexthop add id 204 via fe80:2::12 dev $rp22
+	ip nexthop add id 205 via fe80:3::13 dev $rp23
+	ip nexthop add id 206 group 204/205 type resilient buckets 512 \
+		idle_timer 0
+	ip route add 2001:db8:1::/64 vrf vrf-r2 nhid 206
+}
+
+multipath4_test()
+{
+	local desc="$1"
+	local weight_rp12=$2
+	local weight_rp13=$3
+	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
+	local packets_rp12 packets_rp13
+
+	# Transmit multiple flows from h1 to h2 and make sure they are
+	# distributed between both multipath links (rp12 and rp13)
+	# according to the provided weights.
+	sysctl_set net.ipv4.fib_multipath_hash_policy 1
+
+	t0_rp12=$(link_stats_tx_packets_get $rp12)
+	t0_rp13=$(link_stats_tx_packets_get $rp13)
+
+	ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
+		-d 1msec -t udp "sp=1024,dp=0-32768"
+
+	t1_rp12=$(link_stats_tx_packets_get $rp12)
+	t1_rp13=$(link_stats_tx_packets_get $rp13)
+
+	let "packets_rp12 = $t1_rp12 - $t0_rp12"
+	let "packets_rp13 = $t1_rp13 - $t0_rp13"
+	multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13
+
+	# Restore settings.
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+	local desc="$1"
+	local weight_rp12=$2
+	local weight_rp13=$3
+	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
+	local packets_rp12 packets_rp13
+
+	# Transmit multiple flows from h1 to h2 and make sure they are
+	# distributed between both multipath links (rp12 and rp13)
+	# according to the provided weights.
+	sysctl_set net.ipv6.fib_multipath_hash_policy 1
+
+	t0_rp12=$(link_stats_tx_packets_get $rp12)
+	t0_rp13=$(link_stats_tx_packets_get $rp13)
+
+	$MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=1024,dp=0-32768"
+
+	t1_rp12=$(link_stats_tx_packets_get $rp12)
+	t1_rp13=$(link_stats_tx_packets_get $rp13)
+
+	let "packets_rp12 = $t1_rp12 - $t0_rp12"
+	let "packets_rp13 = $t1_rp13 - $t0_rp13"
+	multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13
+
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath_test()
+{
+	# Without an idle timer, weight replacement should happen immediately.
+	log_info "Running multipath tests without an idle timer"
+	ip nexthop replace id 103 group 101/102 type resilient idle_timer 0
+	ip nexthop replace id 106 group 104/105 type resilient idle_timer 0
+
+	log_info "Running IPv4 multipath tests"
+	ip nexthop replace id 103 group 101,1/102,1 type resilient
+	multipath4_test "ECMP" 1 1
+	ip nexthop replace id 103 group 101,2/102,1 type resilient
+	multipath4_test "Weighted MP 2:1" 2 1
+	ip nexthop replace id 103 group 101,11/102,45 type resilient
+	multipath4_test "Weighted MP 11:45" 11 45
+
+	ip nexthop replace id 103 group 101,1/102,1 type resilient
+
+	log_info "Running IPv6 L4 hash multipath tests"
+	ip nexthop replace id 106 group 104,1/105,1 type resilient
+	multipath6_l4_test "ECMP" 1 1
+	ip nexthop replace id 106 group 104,2/105,1 type resilient
+	multipath6_l4_test "Weighted MP 2:1" 2 1
+	ip nexthop replace id 106 group 104,11/105,45 type resilient
+	multipath6_l4_test "Weighted MP 11:45" 11 45
+
+	ip nexthop replace id 106 group 104,1/105,1 type resilient
+
+	# With an idle timer, weight replacement should not happen, so the
+	# expected ratio should always be the initial one (1:1).
+	log_info "Running multipath tests with an idle timer of 120 seconds"
+	ip nexthop replace id 103 group 101/102 type resilient idle_timer 120
+	ip nexthop replace id 106 group 104/105 type resilient idle_timer 120
+
+	log_info "Running IPv4 multipath tests"
+	ip nexthop replace id 103 group 101,1/102,1 type resilient
+	multipath4_test "ECMP" 1 1
+	ip nexthop replace id 103 group 101,2/102,1 type resilient
+	multipath4_test "Weighted MP 2:1" 1 1
+	ip nexthop replace id 103 group 101,11/102,45 type resilient
+	multipath4_test "Weighted MP 11:45" 1 1
+
+	ip nexthop replace id 103 group 101,1/102,1 type resilient
+
+	log_info "Running IPv6 L4 hash multipath tests"
+	ip nexthop replace id 106 group 104,1/105,1 type resilient
+	multipath6_l4_test "ECMP" 1 1
+	ip nexthop replace id 106 group 104,2/105,1 type resilient
+	multipath6_l4_test "Weighted MP 2:1" 1 1
+	ip nexthop replace id 106 group 104,11/105,45 type resilient
+	multipath6_l4_test "Weighted MP 11:45" 1 1
+
+	ip nexthop replace id 106 group 104,1/105,1 type resilient
+
+	# With a short idle timer and enough idle time, weight replacement
+	# should happen.
+	log_info "Running multipath tests with an idle timer of 5 seconds"
+	ip nexthop replace id 103 group 101/102 type resilient idle_timer 5
+	ip nexthop replace id 106 group 104/105 type resilient idle_timer 5
+
+	log_info "Running IPv4 multipath tests"
+	sleep 10
+	ip nexthop replace id 103 group 101,1/102,1 type resilient
+	multipath4_test "ECMP" 1 1
+	sleep 10
+	ip nexthop replace id 103 group 101,2/102,1 type resilient
+	multipath4_test "Weighted MP 2:1" 2 1
+	sleep 10
+	ip nexthop replace id 103 group 101,11/102,45 type resilient
+	multipath4_test "Weighted MP 11:45" 11 45
+
+	ip nexthop replace id 103 group 101,1/102,1 type resilient
+
+	log_info "Running IPv6 L4 hash multipath tests"
+	sleep 10
+	ip nexthop replace id 106 group 104,1/105,1 type resilient
+	multipath6_l4_test "ECMP" 1 1
+	sleep 10
+	ip nexthop replace id 106 group 104,2/105,1 type resilient
+	multipath6_l4_test "Weighted MP 2:1" 2 1
+	sleep 10
+	ip nexthop replace id 106 group 104,11/105,45 type resilient
+	multipath6_l4_test "Weighted MP 11:45" 11 45
+
+	ip nexthop replace id 106 group 104,1/105,1 type resilient
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp11=${NETIFS[p2]}
+
+	rp12=${NETIFS[p3]}
+	rp22=${NETIFS[p4]}
+
+	rp13=${NETIFS[p5]}
+	rp23=${NETIFS[p6]}
+
+	rp21=${NETIFS[p7]}
+	h2=${NETIFS[p8]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router1_create
+	router2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router2_destroy
+	router1_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 198.51.100.2
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+ip nexthop ls >/dev/null 2>&1
+if [ $? -ne 0 ]; then
+	echo "Nexthop objects not supported; skipping tests"
+	exit 0
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+routing_nh_obj
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 902280cacc0367dcaa8be8261e02ead932a1488d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 12 Mar 2021 17:50:25 +0100
Subject: selftests: forwarding: Add resilient multipath tunneling nexthop test

Add a resilient nexthop objects version of gre_multipath_nh.sh. Test
that both IPv4 and IPv6 overlays work with resilient nexthop groups
where the nexthops are two GRE tunnels.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/gre_multipath_nh_res.sh         | 361 +++++++++++++++++++++
 1 file changed, 361 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh
new file mode 100755
index 000000000000..088b65e64d66
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh
@@ -0,0 +1,361 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1                      |
+# |               $h1 +     |
+# |      192.0.2.1/28 |     |
+# |  2001:db8:1::1/64 |     |
+# +-------------------|-----+
+#                     |
+# +-------------------|------------------------+
+# | SW1               |                        |
+# |              $ol1 +                        |
+# |      192.0.2.2/28                          |
+# |  2001:db8:1::2/64                          |
+# |                                            |
+# |  + g1a (gre)          + g1b (gre)          |
+# |    loc=192.0.2.65       loc=192.0.2.81     |
+# |    rem=192.0.2.66 --.   rem=192.0.2.82 --. |
+# |    tos=inherit      |   tos=inherit      | |
+# |  .------------------'                    | |
+# |  |                    .------------------' |
+# |  v                    v                    |
+# |  + $ul1.111 (vlan)    + $ul1.222 (vlan)    |
+# |  | 192.0.2.129/28     | 192.0.2.145/28     |
+# |   \                  /                     |
+# |    \________________/                      |
+# |            |                               |
+# |            + $ul1                          |
+# +------------|-------------------------------+
+#              |
+# +------------|-------------------------------+
+# | SW2        + $ul2                          |
+# |     _______|________                       |
+# |    /                \                      |
+# |   /                  \                     |
+# |  + $ul2.111 (vlan)    + $ul2.222 (vlan)    |
+# |  ^ 192.0.2.130/28     ^ 192.0.2.146/28     |
+# |  |                    |                    |
+# |  |                    '------------------. |
+# |  '------------------.                    | |
+# |  + g2a (gre)        | + g2b (gre)        | |
+# |    loc=192.0.2.66   |   loc=192.0.2.82   | |
+# |    rem=192.0.2.65 --'   rem=192.0.2.81 --' |
+# |    tos=inherit          tos=inherit        |
+# |                                            |
+# |              $ol2 +                        |
+# |     192.0.2.17/28 |                        |
+# |  2001:db8:2::1/64 |                        |
+# +-------------------|------------------------+
+#                     |
+# +-------------------|-----+
+# | H2                |     |
+# |               $h2 +     |
+# |     192.0.2.18/28       |
+# |  2001:db8:2::2/64       |
+# +-------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	multipath_ipv4
+	multipath_ipv6
+	multipath_ipv6_l4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+	ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+	ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+	simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+	__simple_if_init $ul1 v$ol1
+	vlan_create $ul1 111 v$ol1 192.0.2.129/28
+	vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+	tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+	__simple_if_init g1a v$ol1 192.0.2.65/32
+	ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+	tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+	__simple_if_init g1b v$ol1 192.0.2.81/32
+	ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+	ip -6 nexthop add id 101 dev g1a
+	ip -6 nexthop add id 102 dev g1b
+	ip nexthop add id 103 group 101/102 type resilient buckets 512 \
+		idle_timer 0
+
+	ip route add vrf v$ol1 192.0.2.16/28 nhid 103
+	ip route add vrf v$ol1 2001:db8:2::/64 nhid 103
+}
+
+sw1_destroy()
+{
+	ip route del vrf v$ol1 2001:db8:2::/64
+	ip route del vrf v$ol1 192.0.2.16/28
+
+	ip nexthop del id 103
+	ip -6 nexthop del id 102
+	ip -6 nexthop del id 101
+
+	ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+	__simple_if_fini g1b 192.0.2.81/32
+	tunnel_destroy g1b
+
+	ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+	__simple_if_fini g1a 192.0.2.65/32
+	tunnel_destroy g1a
+
+	vlan_destroy $ul1 222
+	vlan_destroy $ul1 111
+	__simple_if_fini $ul1
+	simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+}
+
+sw2_create()
+{
+	simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+	__simple_if_init $ul2 v$ol2
+	vlan_create $ul2 111 v$ol2 192.0.2.130/28
+	vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+	tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+	__simple_if_init g2a v$ol2 192.0.2.66/32
+	ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+	tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+	__simple_if_init g2b v$ol2 192.0.2.82/32
+	ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+	ip -6 nexthop add id 201 dev g2a
+	ip -6 nexthop add id 202 dev g2b
+	ip nexthop add id 203 group 201/202 type resilient buckets 512 \
+		idle_timer 0
+
+	ip route add vrf v$ol2 192.0.2.0/28 nhid 203
+	ip route add vrf v$ol2 2001:db8:1::/64 nhid 203
+
+	tc qdisc add dev $ul2 clsact
+	tc filter add dev $ul2 ingress pref 111 prot 802.1Q \
+	   flower vlan_id 111 action pass
+	tc filter add dev $ul2 ingress pref 222 prot 802.1Q \
+	   flower vlan_id 222 action pass
+}
+
+sw2_destroy()
+{
+	tc qdisc del dev $ul2 clsact
+
+	ip route del vrf v$ol2 2001:db8:1::/64
+	ip route del vrf v$ol2 192.0.2.0/28
+
+	ip nexthop del id 203
+	ip -6 nexthop del id 202
+	ip -6 nexthop del id 201
+
+	ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+	__simple_if_fini g2b 192.0.2.82/32
+	tunnel_destroy g2b
+
+	ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+	__simple_if_fini g2a 192.0.2.66/32
+	tunnel_destroy g2a
+
+	vlan_destroy $ul2 222
+	vlan_destroy $ul2 111
+	__simple_if_fini $ul2
+	simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+	ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+	ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	vrf_prepare
+	h1_create
+	sw1_create
+	sw2_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	sw2_destroy
+	sw1_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+multipath4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv4.fib_multipath_hash_policy 1
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2 \
+		type resilient
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	ip vrf exec v$h1 \
+	   $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+	       -d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102 type resilient
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 0
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2 \
+		type resilient
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	# Generate 16384 echo requests, each with a random flow label.
+	for ((i=0; i < 16384; ++i)); do
+		ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
+	done
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102 type resilient
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 1
+	ip nexthop replace id 103 group 101,$weight1/102,$weight2 \
+		type resilient
+
+	local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	ip vrf exec v$h1 \
+		$MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
+		-d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+	local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip nexthop replace id 103 group 101/102 type resilient
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+multipath_ipv4()
+{
+	log_info "Running IPv4 multipath tests"
+	multipath4_test "ECMP" 1 1
+	multipath4_test "Weighted MP 2:1" 2 1
+	multipath4_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6()
+{
+	log_info "Running IPv6 multipath tests"
+	multipath6_test "ECMP" 1 1
+	multipath6_test "Weighted MP 2:1" 2 1
+	multipath6_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6_l4()
+{
+	log_info "Running IPv6 L4 hash multipath tests"
+	multipath6_l4_test "ECMP" 1 1
+	multipath6_l4_test "Weighted MP 2:1" 2 1
+	multipath6_l4_test "Weighted MP 11:45" 11 45
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From b8a07c4cea04c14008f34880424852d38ae03758 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 12 Mar 2021 17:50:26 +0100
Subject: selftests: netdevsim: Add test for resilient nexthop groups offload
 API

Test various aspects of the resilient nexthop group offload API on top
of the netdevsim implementation. Both good and bad flows are tested.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Co-developed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/netdevsim/nexthop.sh     | 620 +++++++++++++++++++++
 1 file changed, 620 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
index be0c1b5ee6b8..ba75c81cda91 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
@@ -11,14 +11,33 @@ ALL_TESTS="
 	nexthop_single_add_err_test
 	nexthop_group_add_test
 	nexthop_group_add_err_test
+	nexthop_res_group_add_test
+	nexthop_res_group_add_err_test
 	nexthop_group_replace_test
 	nexthop_group_replace_err_test
+	nexthop_res_group_replace_test
+	nexthop_res_group_replace_err_test
+	nexthop_res_group_idle_timer_test
+	nexthop_res_group_idle_timer_del_test
+	nexthop_res_group_increase_idle_timer_test
+	nexthop_res_group_decrease_idle_timer_test
+	nexthop_res_group_unbalanced_timer_test
+	nexthop_res_group_unbalanced_timer_del_test
+	nexthop_res_group_no_unbalanced_timer_test
+	nexthop_res_group_short_unbalanced_timer_test
+	nexthop_res_group_increase_unbalanced_timer_test
+	nexthop_res_group_decrease_unbalanced_timer_test
+	nexthop_res_group_force_migrate_busy_test
 	nexthop_single_replace_test
 	nexthop_single_replace_err_test
 	nexthop_single_in_group_replace_test
 	nexthop_single_in_group_replace_err_test
+	nexthop_single_in_res_group_replace_test
+	nexthop_single_in_res_group_replace_err_test
 	nexthop_single_in_group_delete_test
 	nexthop_single_in_group_delete_err_test
+	nexthop_single_in_res_group_delete_test
+	nexthop_single_in_res_group_delete_err_test
 	nexthop_replay_test
 	nexthop_replay_err_test
 "
@@ -27,6 +46,7 @@ DEV_ADDR=1337
 DEV=netdevsim${DEV_ADDR}
 DEVLINK_DEV=netdevsim/${DEV}
 SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
+DEBUGFS_NET_DIR=/sys/kernel/debug/netdevsim/$DEV/
 NUM_NETIFS=0
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
@@ -44,6 +64,28 @@ nexthop_check()
 	return 0
 }
 
+nexthop_bucket_nhid_count_check()
+{
+	local group_id=$1; shift
+	local expected
+	local count
+	local nhid
+	local ret
+
+	while (($# > 0)); do
+		nhid=$1; shift
+		expected=$1; shift
+
+		count=$($IP nexthop bucket show id $group_id nhid $nhid |
+			grep "trap" | wc -l)
+		if ((expected != count)); then
+			return 1
+		fi
+	done
+
+	return 0
+}
+
 nexthop_resource_check()
 {
 	local expected_occ=$1; shift
@@ -159,6 +201,71 @@ nexthop_group_add_err_test()
 	nexthop_resource_set 9999
 }
 
+nexthop_res_group_add_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	$IP nexthop add id 10 group 1/2 type resilient buckets 4
+	nexthop_check "id 10" "id 10 group 1/2 type resilient buckets 4 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_bucket_nhid_count_check 10 1 2
+	check_err $? "Wrong nexthop buckets count"
+	nexthop_bucket_nhid_count_check 10 2 2
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 6
+	check_err $? "Wrong nexthop occupancy"
+
+	$IP nexthop del id 10
+	nexthop_resource_check 2
+	check_err $? "Wrong nexthop occupancy after delete"
+
+	$IP nexthop add id 10 group 1,3/2,2 type resilient buckets 5
+	nexthop_check "id 10" "id 10 group 1,3/2,2 type resilient buckets 5 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 trap"
+	check_err $? "Unexpected weighted nexthop group entry"
+
+	nexthop_bucket_nhid_count_check 10 1 3
+	check_err $? "Wrong nexthop buckets count"
+	nexthop_bucket_nhid_count_check 10 2 2
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 7
+	check_err $? "Wrong weighted nexthop occupancy"
+
+	$IP nexthop del id 10
+	nexthop_resource_check 2
+	check_err $? "Wrong nexthop occupancy after delete"
+
+	log_test "Resilient nexthop group add and delete"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_add_err_test()
+{
+	RET=0
+
+	nexthop_resource_set 2
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	$IP nexthop add id 10 group 1/2 type resilient buckets 4 &> /dev/null
+	check_fail $? "Nexthop group addition succeeded when should fail"
+
+	nexthop_resource_check 2
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Resilient nexthop group add failure"
+
+	$IP nexthop flush &> /dev/null
+	nexthop_resource_set 9999
+}
+
 nexthop_group_replace_test()
 {
 	RET=0
@@ -206,6 +313,411 @@ nexthop_group_replace_err_test()
 	nexthop_resource_set 9999
 }
 
+nexthop_res_group_replace_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.4 dev dummy1
+	$IP nexthop add id 10 group 1/2 type resilient buckets 6
+
+	$IP nexthop replace id 10 group 1/2/3 type resilient
+	nexthop_check "id 10" "id 10 group 1/2/3 type resilient buckets 6 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_bucket_nhid_count_check 10 1 2
+	check_err $? "Wrong nexthop buckets count"
+	nexthop_bucket_nhid_count_check 10 2 2
+	check_err $? "Wrong nexthop buckets count"
+	nexthop_bucket_nhid_count_check 10 3 2
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 9
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Resilient nexthop group replace"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_replace_err_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.4 dev dummy1
+	$IP nexthop add id 10 group 1/2 type resilient buckets 6
+
+	ip netns exec testns1 \
+		echo 1 > $DEBUGFS_NET_DIR/fib/fail_res_nexthop_group_replace
+	$IP nexthop replace id 10 group 1/2/3 type resilient &> /dev/null
+	check_fail $? "Nexthop group replacement succeeded when should fail"
+
+	nexthop_check "id 10" "id 10 group 1/2 type resilient buckets 6 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 trap"
+	check_err $? "Unexpected nexthop group entry after failure"
+
+	nexthop_bucket_nhid_count_check 10 1 3
+	check_err $? "Wrong nexthop buckets count"
+	nexthop_bucket_nhid_count_check 10 2 3
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 9
+	check_err $? "Wrong nexthop occupancy after failure"
+
+	log_test "Resilient nexthop group replace failure"
+
+	$IP nexthop flush &> /dev/null
+	ip netns exec testns1 \
+		echo 0 > $DEBUGFS_NET_DIR/fib/fail_res_nexthop_group_replace
+}
+
+nexthop_res_mark_buckets_busy()
+{
+	local group_id=$1; shift
+	local nhid=$1; shift
+	local count=$1; shift
+	local index
+
+	for index in $($IP -j nexthop bucket show id $group_id nhid $nhid |
+		       jq '.[].bucket.index' | head -n ${count:--0})
+	do
+		echo $group_id $index \
+			> $DEBUGFS_NET_DIR/fib/nexthop_bucket_activity
+	done
+}
+
+nexthop_res_num_nhid_buckets()
+{
+	local group_id=$1; shift
+	local nhid=$1; shift
+
+	$IP -j nexthop bucket show id $group_id nhid $nhid | jq length
+}
+
+nexthop_res_group_idle_timer_test()
+{
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1/2 type resilient buckets 8 idle_timer 4
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1/2,3 type resilient
+
+	nexthop_bucket_nhid_count_check 10  1 4  2 4
+	check_err $? "Group expected to be unbalanced"
+
+	sleep 6
+
+	nexthop_bucket_nhid_count_check 10  1 2  2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after idle timer"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_idle_timer_del_test()
+{
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1,50/2,50/3,1 \
+	    type resilient buckets 8 idle_timer 6
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1,50/2,150/3,1 type resilient
+
+	nexthop_bucket_nhid_count_check 10  1 4  2 4  3 0
+	check_err $? "Group expected to be unbalanced"
+
+	sleep 4
+
+	# Deletion prompts group replacement. Check that the bucket timers
+	# are kept.
+	$IP nexthop delete id 3
+
+	nexthop_bucket_nhid_count_check 10  1 4  2 4
+	check_err $? "Group expected to still be unbalanced"
+
+	sleep 4
+
+	nexthop_bucket_nhid_count_check 10  1 2  2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after idle timer (with delete)"
+
+	$IP nexthop flush &> /dev/null
+}
+
+__nexthop_res_group_increase_timer_test()
+{
+	local timer=$1; shift
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1/2 type resilient buckets 8 $timer 4
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1/2,3 type resilient
+
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_fail $? "Group expected to be unbalanced"
+
+	sleep 2
+	$IP nexthop replace id 10 group 1/2,3 type resilient $timer 8
+	sleep 4
+
+	# 6 seconds, past the original timer.
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_fail $? "Group still expected to be unbalanced"
+
+	sleep 4
+
+	# 10 seconds, past the new timer.
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after $timer increase"
+
+	$IP nexthop flush &> /dev/null
+}
+
+__nexthop_res_group_decrease_timer_test()
+{
+	local timer=$1; shift
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1/2 type resilient buckets 8 $timer 8
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1/2,3 type resilient
+
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_fail $? "Group expected to be unbalanced"
+
+	sleep 2
+	$IP nexthop replace id 10 group 1/2,3 type resilient $timer 4
+	sleep 4
+
+	# 6 seconds, past the new timer, before the old timer.
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after $timer decrease"
+
+	$IP nexthop flush &> /dev/null
+}
+
+__nexthop_res_group_increase_timer_del_test()
+{
+	local timer=$1; shift
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1,100/2,100/3,1 \
+	    type resilient buckets 8 $timer 4
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1,100/2,300/3,1 type resilient
+
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_fail $? "Group expected to be unbalanced"
+
+	sleep 2
+	$IP nexthop replace id 10 group 1/2,3 type resilient $timer 8
+	sleep 4
+
+	# 6 seconds, past the original timer.
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_fail $? "Group still expected to be unbalanced"
+
+	sleep 4
+
+	# 10 seconds, past the new timer.
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after $timer increase"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_increase_idle_timer_test()
+{
+	__nexthop_res_group_increase_timer_test idle_timer
+}
+
+nexthop_res_group_decrease_idle_timer_test()
+{
+	__nexthop_res_group_decrease_timer_test idle_timer
+}
+
+nexthop_res_group_unbalanced_timer_test()
+{
+	local i
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1/2 type resilient \
+	    buckets 8 idle_timer 6 unbalanced_timer 10
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1/2,3 type resilient
+
+	for i in 1 2; do
+		sleep 4
+		nexthop_bucket_nhid_count_check 10  1 4  2 4
+		check_err $? "$i: Group expected to be unbalanced"
+		nexthop_res_mark_buckets_busy 10 1
+	done
+
+	# 3 x sleep 4 > unbalanced timer 10
+	sleep 4
+	nexthop_bucket_nhid_count_check 10  1 2  2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after unbalanced timer"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_unbalanced_timer_del_test()
+{
+	local i
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1,50/2,50/3,1 type resilient \
+	    buckets 8 idle_timer 6 unbalanced_timer 10
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1,50/2,150/3,1 type resilient
+
+	# Check that NH delete does not reset unbalanced time.
+	sleep 4
+	$IP nexthop delete id 3
+	nexthop_bucket_nhid_count_check 10  1 4  2 4
+	check_err $? "1: Group expected to be unbalanced"
+	nexthop_res_mark_buckets_busy 10 1
+
+	sleep 4
+	nexthop_bucket_nhid_count_check 10  1 4  2 4
+	check_err $? "2: Group expected to be unbalanced"
+	nexthop_res_mark_buckets_busy 10 1
+
+	# 3 x sleep 4 > unbalanced timer 10
+	sleep 4
+	nexthop_bucket_nhid_count_check 10  1 2  2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after unbalanced timer (with delete)"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_no_unbalanced_timer_test()
+{
+	local i
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1/2 type resilient buckets 8
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1/2,3 type resilient
+
+	for i in $(seq 3); do
+		sleep 60
+		nexthop_bucket_nhid_count_check 10 2 6
+		check_fail $? "$i: Group expected to be unbalanced"
+		nexthop_res_mark_buckets_busy 10 1
+	done
+
+	log_test "Buckets never force-migrated without unbalanced timer"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_short_unbalanced_timer_test()
+{
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1/2 type resilient \
+	    buckets 8 idle_timer 120 unbalanced_timer 4
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1/2,3 type resilient
+
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_fail $? "Group expected to be unbalanced"
+
+	sleep 5
+
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_err $? "Group expected to be balanced"
+
+	log_test "Bucket migration after unbalanced < idle timer"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_res_group_increase_unbalanced_timer_test()
+{
+	__nexthop_res_group_increase_timer_test unbalanced_timer
+}
+
+nexthop_res_group_decrease_unbalanced_timer_test()
+{
+	__nexthop_res_group_decrease_timer_test unbalanced_timer
+}
+
+nexthop_res_group_force_migrate_busy_test()
+{
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+	RET=0
+
+	$IP nexthop add id 10 group 1/2 type resilient \
+	    buckets 8 idle_timer 120
+	nexthop_res_mark_buckets_busy 10 1
+	$IP nexthop replace id 10 group 1/2,3 type resilient
+
+	nexthop_bucket_nhid_count_check 10 2 6
+	check_fail $? "Group expected to be unbalanced"
+
+	$IP nexthop replace id 10 group 2 type resilient
+	nexthop_bucket_nhid_count_check 10 2 8
+	check_err $? "All buckets expected to have migrated"
+
+	log_test "Busy buckets force-migrated when NH removed"
+
+	$IP nexthop flush &> /dev/null
+}
+
 nexthop_single_replace_test()
 {
 	RET=0
@@ -299,6 +811,63 @@ nexthop_single_in_group_replace_err_test()
 	nexthop_resource_set 9999
 }
 
+nexthop_single_in_res_group_replace_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2 type resilient buckets 4
+
+	$IP nexthop replace id 1 via 192.0.2.4 dev dummy1
+	check_err $? "Failed to replace nexthop when should not"
+
+	nexthop_check "id 10" "id 10 group 1/2 type resilient buckets 4 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_bucket_nhid_count_check 10  1 2  2 2
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 6
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop replace while in resilient group"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_res_group_replace_err_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2 type resilient buckets 4
+
+	ip netns exec testns1 \
+		echo 1 > $DEBUGFS_NET_DIR/fib/fail_nexthop_bucket_replace
+	$IP nexthop replace id 1 via 192.0.2.4 dev dummy1 &> /dev/null
+	check_fail $? "Nexthop replacement succeeded when should fail"
+
+	nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+	check_err $? "Unexpected nexthop entry after failure"
+
+	nexthop_check "id 10" "id 10 group 1/2 type resilient buckets 4 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 trap"
+	check_err $? "Unexpected nexthop group entry after failure"
+
+	nexthop_bucket_nhid_count_check 10  1 2  2 2
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 6
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop replace while in resilient group failure"
+
+	$IP nexthop flush &> /dev/null
+	ip netns exec testns1 \
+		echo 0 > $DEBUGFS_NET_DIR/fib/fail_nexthop_bucket_replace
+}
+
 nexthop_single_in_group_delete_test()
 {
 	RET=0
@@ -346,6 +915,57 @@ nexthop_single_in_group_delete_err_test()
 	nexthop_resource_set 9999
 }
 
+nexthop_single_in_res_group_delete_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 10 group 1/2 type resilient buckets 4
+
+	$IP nexthop del id 1
+	nexthop_check "id 10" "id 10 group 2 type resilient buckets 4 idle_timer 120 unbalanced_timer 0 unbalanced_time 0 trap"
+	check_err $? "Unexpected nexthop group entry"
+
+	nexthop_bucket_nhid_count_check 10 2 4
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 5
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop delete while in resilient group"
+
+	$IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_res_group_delete_err_test()
+{
+	RET=0
+
+	$IP nexthop add id 1 via 192.0.2.2 dev dummy1
+	$IP nexthop add id 2 via 192.0.2.3 dev dummy1
+	$IP nexthop add id 3 via 192.0.2.4 dev dummy1
+	$IP nexthop add id 10 group 1/2/3 type resilient buckets 6
+
+	ip netns exec testns1 \
+		echo 1 > $DEBUGFS_NET_DIR/fib/fail_nexthop_bucket_replace
+	$IP nexthop del id 1
+
+	# We failed to replace the two nexthop buckets that were originally
+	# assigned to nhid 1.
+	nexthop_bucket_nhid_count_check 10  2 2  3 2
+	check_err $? "Wrong nexthop buckets count"
+
+	nexthop_resource_check 8
+	check_err $? "Wrong nexthop occupancy"
+
+	log_test "Single nexthop delete while in resilient group failure"
+
+	$IP nexthop flush &> /dev/null
+	ip netns exec testns1 \
+		echo 0 > $DEBUGFS_NET_DIR/fib/fail_nexthop_bucket_replace
+}
+
 nexthop_replay_test()
 {
 	RET=0
-- 
cgit v1.2.3


From 7028ba8ac9683b7e4f4db4db63a306d7497e7150 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Fri, 12 Mar 2021 17:16:19 -0800
Subject: selftests: mptcp: add invert argument for chk_rm_nr

Some of the removing testcases used two zeros as arguments for chk_rm_nr
like this: chk_rm_nr 0 0. This doesn't mean that no RM_ADDR has been sent.
It only means that RM_ADDR had been sent in the opposite direction that
chk_rm_nr is checking.

This patch added a new argument invert for chk_rm_nr to allow it can
check the RM_ADDR from the opposite direction.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 964db9ed544f..15b71ddee615 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -610,11 +610,22 @@ chk_rm_nr()
 {
 	local rm_addr_nr=$1
 	local rm_subflow_nr=$2
+	local invert=${3:-""}
 	local count
 	local dump_stats
+	local addr_ns
+	local subflow_ns
+
+	if [ -z $invert ]; then
+		addr_ns=$ns1
+		subflow_ns=$ns2
+	elif [ $invert = "invert" ]; then
+		addr_ns=$ns2
+		subflow_ns=$ns1
+	fi
 
 	printf "%-39s %s" " " "rm "
-	count=`ip netns exec $ns1 nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'`
+	count=`ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'`
 	[ -z "$count" ] && count=0
 	if [ "$count" != "$rm_addr_nr" ]; then
 		echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr"
@@ -625,7 +636,7 @@ chk_rm_nr()
 	fi
 
 	echo -n " - sf    "
-	count=`ip netns exec $ns2 nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'`
+	count=`ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'`
 	[ -z "$count" ] && count=0
 	if [ "$count" != "$rm_subflow_nr" ]; then
 		echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr"
@@ -833,7 +844,7 @@ remove_tests()
 	run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow
 	chk_join_nr "remove single address" 1 1 1
 	chk_add_nr 1 1
-	chk_rm_nr 0 0
+	chk_rm_nr 1 1 invert
 
 	# subflow and signal, remove
 	reset
@@ -945,7 +956,7 @@ ipv6_tests()
 	run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow
 	chk_join_nr "remove single address IPv6" 1 1 1
 	chk_add_nr 1 1
-	chk_rm_nr 0 0
+	chk_rm_nr 1 1 invert
 
 	# subflow and signal IPv6, remove
 	reset
@@ -1088,7 +1099,7 @@ add_addr_ports_tests()
 	run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow
 	chk_join_nr "remove single address with port" 1 1 1
 	chk_add_nr 1 1 1
-	chk_rm_nr 0 0
+	chk_rm_nr 1 1 invert
 
 	# subflow and signal with port, remove
 	reset
-- 
cgit v1.2.3


From f87744ad42446c8510296f11fdc73f6e6f1376cc Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Fri, 12 Mar 2021 17:16:20 -0800
Subject: selftests: mptcp: set addr id for removing testcases

The removing testcases can only delete the addresses from id 1, this
patch added the support for deleting the addresses from any id that user
set.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 38 ++++++++++++++++---------
 1 file changed, 24 insertions(+), 14 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 15b71ddee615..6782a891b3e7 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -284,14 +284,19 @@ do_transfer()
 		let rm_nr_ns1=-addr_nr_ns1
 		if [ $rm_nr_ns1 -lt 8 ]; then
 			counter=1
-			sleep 1
-
-			while [ $counter -le $rm_nr_ns1 ]
-			do
-				ip netns exec ${listener_ns} ./pm_nl_ctl del $counter
+			dump=(`ip netns exec ${listener_ns} ./pm_nl_ctl dump`)
+			if [ ${#dump[@]} -gt 0 ]; then
+				id=${dump[1]}
 				sleep 1
-				let counter+=1
-			done
+
+				while [ $counter -le $rm_nr_ns1 ]
+				do
+					ip netns exec ${listener_ns} ./pm_nl_ctl del $id
+					sleep 1
+					let counter+=1
+					let id+=1
+				done
+			fi
 		else
 			sleep 1
 			ip netns exec ${listener_ns} ./pm_nl_ctl flush
@@ -318,14 +323,19 @@ do_transfer()
 		let rm_nr_ns2=-addr_nr_ns2
 		if [ $rm_nr_ns2 -lt 8 ]; then
 			counter=1
-			sleep 1
-
-			while [ $counter -le $rm_nr_ns2 ]
-			do
-				ip netns exec ${connector_ns} ./pm_nl_ctl del $counter
+			dump=(`ip netns exec ${connector_ns} ./pm_nl_ctl dump`)
+			if [ ${#dump[@]} -gt 0 ]; then
+				id=${dump[1]}
 				sleep 1
-				let counter+=1
-			done
+
+				while [ $counter -le $rm_nr_ns2 ]
+				do
+					ip netns exec ${connector_ns} ./pm_nl_ctl del $id
+					sleep 1
+					let counter+=1
+					let id+=1
+				done
+			fi
 		else
 			sleep 1
 			ip netns exec ${connector_ns} ./pm_nl_ctl flush
-- 
cgit v1.2.3


From d2c4333a801c73a8bc2e4bde75b573e2d1014436 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Fri, 12 Mar 2021 17:16:21 -0800
Subject: selftests: mptcp: add testcases for removing addrs

This patch added the testcases for removing a list of addresses. Used
the netlink to flush the addresses in the testcases.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 6782a891b3e7..191303b652a6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -890,6 +890,29 @@ remove_tests()
 	chk_join_nr "flush subflows and signal" 3 3 3
 	chk_add_nr 1 1
 	chk_rm_nr 2 2
+
+	# subflows flush
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow id 150
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+	run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow
+	chk_join_nr "flush subflows" 3 3 3
+	chk_rm_nr 3 3
+
+	# addresses flush
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+	run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow
+	chk_join_nr "flush addresses" 3 3 3
+	chk_add_nr 3 3
+	chk_rm_nr 3 3 invert
 }
 
 add_tests()
-- 
cgit v1.2.3


From f26b30918dac568425811f71fd21a53ed2307f44 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 14 Mar 2021 14:19:33 +0200
Subject: selftests: netdevsim: Test psample functionality

Test various aspects of psample functionality over netdevsim and in
particular test that the psample module correctly reports the provided
metadata.

Example:

 # ./psample.sh
 TEST: psample enable / disable                                      [ OK ]
 TEST: psample group number                                          [ OK ]
 TEST: psample metadata                                              [ OK ]

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/netdevsim/psample.sh     | 181 +++++++++++++++++++++
 1 file changed, 181 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/netdevsim/psample.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/psample.sh b/tools/testing/selftests/drivers/net/netdevsim/psample.sh
new file mode 100755
index 000000000000..ee10b1a8933c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/psample.sh
@@ -0,0 +1,181 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the psample module. It makes use of netdevsim
+# which periodically generates "sampled" packets.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	psample_enable_test
+	psample_group_num_test
+	psample_md_test
+"
+NETDEVSIM_PATH=/sys/bus/netdevsim/
+DEV_ADDR=1337
+DEV=netdevsim${DEV_ADDR}
+DEVLINK_DEV=netdevsim/${DEV}
+SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
+PSAMPLE_DIR=/sys/kernel/debug/netdevsim/$DEV/psample/
+CAPTURE_FILE=$(mktemp)
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+# Available at https://github.com/Mellanox/libpsample
+require_command psample
+
+psample_capture()
+{
+	rm -f $CAPTURE_FILE
+
+	timeout 2 ip netns exec testns1 psample &> $CAPTURE_FILE
+}
+
+psample_enable_test()
+{
+	RET=0
+
+	echo 1 > $PSAMPLE_DIR/enable
+	check_err $? "Failed to enable sampling when should not"
+
+	echo 1 > $PSAMPLE_DIR/enable 2>/dev/null
+	check_fail $? "Sampling enablement succeeded when should fail"
+
+	psample_capture
+	if [ $(cat $CAPTURE_FILE | wc -l) -eq 0 ]; then
+		check_err 1 "Failed to capture sampled packets"
+	fi
+
+	echo 0 > $PSAMPLE_DIR/enable
+	check_err $? "Failed to disable sampling when should not"
+
+	echo 0 > $PSAMPLE_DIR/enable 2>/dev/null
+	check_fail $? "Sampling disablement succeeded when should fail"
+
+	psample_capture
+	if [ $(cat $CAPTURE_FILE | wc -l) -ne 0 ]; then
+		check_err 1 "Captured sampled packets when should not"
+	fi
+
+	log_test "psample enable / disable"
+}
+
+psample_group_num_test()
+{
+	RET=0
+
+	echo 1234 > $PSAMPLE_DIR/group_num
+	echo 1 > $PSAMPLE_DIR/enable
+
+	psample_capture
+	grep -q -e "group 1234" $CAPTURE_FILE
+	check_err $? "Sampled packets reported with wrong group number"
+
+	# New group number should only be used after disable / enable.
+	echo 4321 > $PSAMPLE_DIR/group_num
+
+	psample_capture
+	grep -q -e "group 4321" $CAPTURE_FILE
+	check_fail $? "Group number changed while sampling is active"
+
+	echo 0 > $PSAMPLE_DIR/enable && echo 1 > $PSAMPLE_DIR/enable
+
+	psample_capture
+	grep -q -e "group 4321" $CAPTURE_FILE
+	check_err $? "Group number did not change after restarting sampling"
+
+	log_test "psample group number"
+
+	echo 0 > $PSAMPLE_DIR/enable
+}
+
+psample_md_test()
+{
+	RET=0
+
+	echo 1 > $PSAMPLE_DIR/enable
+
+	echo 1234 > $PSAMPLE_DIR/in_ifindex
+	echo 4321 > $PSAMPLE_DIR/out_ifindex
+	psample_capture
+
+	grep -q -e "in-ifindex 1234" $CAPTURE_FILE
+	check_err $? "Sampled packets reported with wrong in-ifindex"
+
+	grep -q -e "out-ifindex 4321" $CAPTURE_FILE
+	check_err $? "Sampled packets reported with wrong out-ifindex"
+
+	echo 5 > $PSAMPLE_DIR/out_tc
+	psample_capture
+
+	grep -q -e "out-tc 5" $CAPTURE_FILE
+	check_err $? "Sampled packets reported with wrong out-tc"
+
+	echo $((2**16 - 1)) > $PSAMPLE_DIR/out_tc
+	psample_capture
+
+	grep -q -e "out-tc " $CAPTURE_FILE
+	check_fail $? "Sampled packets reported with out-tc when should not"
+
+	echo 1 > $PSAMPLE_DIR/out_tc
+	echo 10000 > $PSAMPLE_DIR/out_tc_occ_max
+	psample_capture
+
+	grep -q -e "out-tc-occ " $CAPTURE_FILE
+	check_err $? "Sampled packets not reported with out-tc-occ when should"
+
+	echo 0 > $PSAMPLE_DIR/out_tc_occ_max
+	psample_capture
+
+	grep -q -e "out-tc-occ " $CAPTURE_FILE
+	check_fail $? "Sampled packets reported with out-tc-occ when should not"
+
+	echo 10000 > $PSAMPLE_DIR/latency_max
+	psample_capture
+
+	grep -q -e "latency " $CAPTURE_FILE
+	check_err $? "Sampled packets not reported with latency when should"
+
+	echo 0 > $PSAMPLE_DIR/latency_max
+	psample_capture
+
+	grep -q -e "latency " $CAPTURE_FILE
+	check_fail $? "Sampled packets reported with latency when should not"
+
+	log_test "psample metadata"
+
+	echo 0 > $PSAMPLE_DIR/enable
+}
+
+setup_prepare()
+{
+	modprobe netdevsim &> /dev/null
+
+	echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
+	while [ ! -d $SYSFS_NET_DIR ] ; do :; done
+
+	set -e
+
+	ip netns add testns1
+	devlink dev reload $DEVLINK_DEV netns testns1
+
+	set +e
+}
+
+cleanup()
+{
+	pre_cleanup
+	rm -f $CAPTURE_FILE
+	ip netns del testns1
+	echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
+	modprobe -r netdevsim &> /dev/null
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From bb24d592e66eb059e086595510e0f0b064e4114d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 14 Mar 2021 14:19:40 +0200
Subject: selftests: mlxsw: Add tc sample tests

Test that packets are sampled when tc-sample is used and that reported
metadata is correct. Two sets of hosts (with and without LAG) are used,
since metadata extraction in mlxsw is a bit different when LAG is
involved.

 # ./tc_sample.sh
 TEST: tc sample rate (forward)                                      [ OK ]
 TEST: tc sample rate (local receive)                                [ OK ]
 TEST: tc sample maximum rate                                        [ OK ]
 TEST: tc sample group conflict test                                 [ OK ]
 TEST: tc sample iif                                                 [ OK ]
 TEST: tc sample lag iif                                             [ OK ]
 TEST: tc sample oif                                                 [ OK ]
 TEST: tc sample lag oif                                             [ OK ]
 TEST: tc sample out-tc                                              [ OK ]
 TEST: tc sample out-tc-occ                                          [ OK ]

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/tc_sample.sh       | 492 +++++++++++++++++++++
 1 file changed, 492 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
new file mode 100755
index 000000000000..75d00104f291
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -0,0 +1,492 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that packets are sampled when tc-sample is used and that reported
+# metadata is correct. Two sets of hosts (with and without LAG) are used, since
+# metadata extraction in mlxsw is a bit different when LAG is involved.
+#
+# +---------------------------------+       +---------------------------------+
+# | H1 (vrf)                        |       | H3 (vrf)                        |
+# |    + $h1                        |       |    + $h3_lag                    |
+# |    | 192.0.2.1/28               |       |    | 192.0.2.17/28              |
+# |    |                            |       |    |                            |
+# |    |  default via 192.0.2.2     |       |    |  default via 192.0.2.18    |
+# +----|----------------------------+       +----|----------------------------+
+#      |                                         |
+# +----|-----------------------------------------|----------------------------+
+# |    | 192.0.2.2/28                            | 192.0.2.18/28              |
+# |    + $rp1                                    + $rp3_lag                   |
+# |                                                                           |
+# |    + $rp2                                    + $rp4_lag                   |
+# |    | 198.51.100.2/28                         | 198.51.100.18/28           |
+# +----|-----------------------------------------|----------------------------+
+#      |                                         |
+# +----|----------------------------+       +----|----------------------------+
+# |    |  default via 198.51.100.2  |       |    |  default via 198.51.100.18 |
+# |    |                            |       |    |                            |
+# |    | 198.51.100.1/28            |       |    | 198.51.100.17/28           |
+# |    + $h2                        |       |    + $h4_lag                    |
+# | H2 (vrf)                        |       | H4 (vrf)                        |
+# +---------------------------------+       +---------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	tc_sample_rate_test
+	tc_sample_max_rate_test
+	tc_sample_group_conflict_test
+	tc_sample_md_iif_test
+	tc_sample_md_lag_iif_test
+	tc_sample_md_oif_test
+	tc_sample_md_lag_oif_test
+	tc_sample_md_out_tc_test
+	tc_sample_md_out_tc_occ_test
+"
+NUM_NETIFS=8
+CAPTURE_FILE=$(mktemp)
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+# Available at https://github.com/Mellanox/libpsample
+require_command psample
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28
+
+	ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
+}
+
+h1_destroy()
+{
+	ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
+
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+	simple_if_init $h2 198.51.100.1/28
+
+	ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
+}
+
+h2_destroy()
+{
+	ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
+
+	simple_if_fini $h2 198.51.100.1/28
+}
+
+h3_create()
+{
+	ip link set dev $h3 down
+	ip link add name ${h3}_bond type bond mode 802.3ad
+	ip link set dev $h3 master ${h3}_bond
+
+	simple_if_init ${h3}_bond 192.0.2.17/28
+
+	ip -4 route add default vrf v${h3}_bond nexthop via 192.0.2.18
+}
+
+h3_destroy()
+{
+	ip -4 route del default vrf v${h3}_bond nexthop via 192.0.2.18
+
+	simple_if_fini ${h3}_bond 192.0.2.17/28
+
+	ip link set dev $h3 nomaster
+	ip link del dev ${h3}_bond
+}
+
+h4_create()
+{
+	ip link set dev $h4 down
+	ip link add name ${h4}_bond type bond mode 802.3ad
+	ip link set dev $h4 master ${h4}_bond
+
+	simple_if_init ${h4}_bond 198.51.100.17/28
+
+	ip -4 route add default vrf v${h4}_bond nexthop via 198.51.100.18
+}
+
+h4_destroy()
+{
+	ip -4 route del default vrf v${h4}_bond nexthop via 198.51.100.18
+
+	simple_if_fini ${h4}_bond 198.51.100.17/28
+
+	ip link set dev $h4 nomaster
+	ip link del dev ${h4}_bond
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	__addr_add_del $rp1 add 192.0.2.2/28
+	tc qdisc add dev $rp1 clsact
+
+	ip link set dev $rp2 up
+	__addr_add_del $rp2 add 198.51.100.2/28
+	tc qdisc add dev $rp2 clsact
+
+	ip link add name ${rp3}_bond type bond mode 802.3ad
+	ip link set dev $rp3 master ${rp3}_bond
+	__addr_add_del ${rp3}_bond add 192.0.2.18/28
+	tc qdisc add dev $rp3 clsact
+	ip link set dev ${rp3}_bond up
+
+	ip link add name ${rp4}_bond type bond mode 802.3ad
+	ip link set dev $rp4 master ${rp4}_bond
+	__addr_add_del ${rp4}_bond add 198.51.100.18/28
+	tc qdisc add dev $rp4 clsact
+	ip link set dev ${rp4}_bond up
+}
+
+router_destroy()
+{
+	ip link set dev ${rp4}_bond down
+	tc qdisc del dev $rp4 clsact
+	__addr_add_del ${rp4}_bond del 198.51.100.18/28
+	ip link set dev $rp4 nomaster
+	ip link del dev ${rp4}_bond
+
+	ip link set dev ${rp3}_bond down
+	tc qdisc del dev $rp3 clsact
+	__addr_add_del ${rp3}_bond del 192.0.2.18/28
+	ip link set dev $rp3 nomaster
+	ip link del dev ${rp3}_bond
+
+	tc qdisc del dev $rp2 clsact
+	__addr_add_del $rp2 del 198.51.100.2/28
+	ip link set dev $rp2 down
+
+	tc qdisc del dev $rp1 clsact
+	__addr_add_del $rp1 del 192.0.2.2/28
+	ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+	h3=${NETIFS[p5]}
+	rp3=${NETIFS[p6]}
+	h4=${NETIFS[p7]}
+	rp4=${NETIFS[p8]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+	h4_create
+	router_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	rm -f $CAPTURE_FILE
+
+	router_destroy
+	h4_destroy
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+psample_capture_start()
+{
+	rm -f $CAPTURE_FILE
+
+	psample &> $CAPTURE_FILE &
+
+	sleep 1
+}
+
+psample_capture_stop()
+{
+	{ kill %% && wait %%; } 2>/dev/null
+}
+
+__tc_sample_rate_test()
+{
+	local desc=$1; shift
+	local dip=$1; shift
+	local pkts pct
+
+	RET=0
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 32 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B $dip -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l)
+	pct=$((100 * (pkts - 100) / 100))
+	(( -25 <= pct && pct <= 25))
+	check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%"
+
+	log_test "tc sample rate ($desc)"
+
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_rate_test()
+{
+	__tc_sample_rate_test "forward" 198.51.100.1
+	__tc_sample_rate_test "local receive" 192.0.2.2
+}
+
+tc_sample_max_rate_test()
+{
+	RET=0
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate $((35 * 10 ** 8)) group 1
+	check_err $? "Failed to configure sampling rule with max rate"
+
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate $((35 * 10 ** 8 + 1)) \
+		group 1 &> /dev/null
+	check_fail $? "Managed to configure sampling rate above maximum"
+
+	log_test "tc sample maximum rate"
+}
+
+tc_sample_group_conflict_test()
+{
+	RET=0
+
+	# Test that two sampling rules cannot be configured on the same port
+	# with different groups.
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 1024 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	tc filter add dev $rp1 ingress protocol all pref 2 handle 102 matchall \
+		skip_sw action sample rate 1024 group 2 &> /dev/null
+	check_fail $? "Managed to configure sampling rule with conflicting group"
+
+	log_test "tc sample group conflict test"
+
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_md_iif_test()
+{
+	local rp1_ifindex
+
+	RET=0
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 5 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	rp1_ifindex=$(ip -j -p link show dev $rp1 | jq '.[]["ifindex"]')
+	grep -q -e "in-ifindex $rp1_ifindex " $CAPTURE_FILE
+	check_err $? "Sampled packets do not have expected in-ifindex"
+
+	log_test "tc sample iif"
+
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_md_lag_iif_test()
+{
+	local rp3_ifindex
+
+	RET=0
+
+	tc filter add dev $rp3 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 5 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v${h3}_bond $MZ ${h3}_bond -c 3200 -d 1msec -p 64 \
+		-A 192.0.2.17 -B 198.51.100.17 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	rp3_ifindex=$(ip -j -p link show dev $rp3 | jq '.[]["ifindex"]')
+	grep -q -e "in-ifindex $rp3_ifindex " $CAPTURE_FILE
+	check_err $? "Sampled packets do not have expected in-ifindex"
+
+	log_test "tc sample lag iif"
+
+	tc filter del dev $rp3 ingress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_md_oif_test()
+{
+	local rp2_ifindex
+
+	RET=0
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 5 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	rp2_ifindex=$(ip -j -p link show dev $rp2 | jq '.[]["ifindex"]')
+	grep -q -e "out-ifindex $rp2_ifindex " $CAPTURE_FILE
+	check_err $? "Sampled packets do not have expected out-ifindex"
+
+	log_test "tc sample oif"
+
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_md_lag_oif_test()
+{
+	local rp4_ifindex
+
+	RET=0
+
+	tc filter add dev $rp3 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 5 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v${h3}_bond $MZ ${h3}_bond -c 3200 -d 1msec -p 64 \
+		-A 192.0.2.17 -B 198.51.100.17 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	rp4_ifindex=$(ip -j -p link show dev $rp4 | jq '.[]["ifindex"]')
+	grep -q -e "out-ifindex $rp4_ifindex " $CAPTURE_FILE
+	check_err $? "Sampled packets do not have expected out-ifindex"
+
+	log_test "tc sample lag oif"
+
+	tc filter del dev $rp3 ingress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_md_out_tc_test()
+{
+	RET=0
+
+	# Output traffic class is not supported on Spectrum-1.
+	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 5 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	# By default, all the packets should go to the same traffic class (0).
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	grep -q -e "out-tc 0 " $CAPTURE_FILE
+	check_err $? "Sampled packets do not have expected out-tc (0)"
+
+	# Map all priorities to highest traffic class (7) and check reported
+	# out-tc.
+	tc qdisc replace dev $rp2 root handle 1: \
+		prio bands 3 priomap 0 0 0 0 0 0 0 0
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	grep -q -e "out-tc 7 " $CAPTURE_FILE
+	check_err $? "Sampled packets do not have expected out-tc (7)"
+
+	log_test "tc sample out-tc"
+
+	tc qdisc del dev $rp2 root handle 1:
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_md_out_tc_occ_test()
+{
+	local backlog pct occ
+
+	RET=0
+
+	# Output traffic class occupancy is not supported on Spectrum-1.
+	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 1024 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	# Configure a shaper on egress to create congestion.
+	tc qdisc replace dev $rp2 root handle 1: \
+		tbf rate 1Mbit burst 256k limit 1M
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 0 -d 1usec -p 1400 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q &
+
+	# Allow congestion to reach steady state.
+	sleep 10
+
+	backlog=$(tc -j -p -s qdisc show dev $rp2 | jq '.[0]["backlog"]')
+
+	# Kill mausezahn.
+	{ kill %% && wait %%; } 2>/dev/null
+
+	psample_capture_stop
+
+	# Record last congestion sample.
+	occ=$(grep -e "out-tc-occ " $CAPTURE_FILE | tail -n 1 | \
+		cut -d ' ' -f 16)
+
+	pct=$((100 * (occ - backlog) / backlog))
+	(( -1 <= pct && pct <= 1))
+	check_err $? "Recorded a congestion of $backlog bytes, but sampled congestion is $occ bytes, which is $pct% off. Required accuracy is +-5%"
+
+	log_test "tc sample out-tc-occ"
+
+	tc qdisc del dev $rp2 root handle 1:
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 6503b9f29a47cdb4ebd6c36d8bbb018418415c2a Mon Sep 17 00:00:00 2001
From: Manu Bretelle <chantra@fb.com>
Date: Wed, 10 Mar 2021 10:23:05 -0800
Subject: bpf: Add getter and setter for SO_REUSEPORT through
 bpf_{g,s}etsockopt

Augment the current set of options that are accessible via
bpf_{g,s}etsockopt to also support SO_REUSEPORT.

Signed-off-by: Manu Bretelle <chantra@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210310182305.1910312-1-chantra@fb.com
---
 net/core/filter.c                              |  6 ++++++
 tools/testing/selftests/bpf/progs/bind4_prog.c | 25 +++++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/bind6_prog.c | 25 +++++++++++++++++++++++++
 3 files changed, 56 insertions(+)

(limited to 'tools/testing')

diff --git a/net/core/filter.c b/net/core/filter.c
index b6732000d8a2..10dac9dd5086 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4729,6 +4729,9 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				sk->sk_prot->keepalive(sk, valbool);
 			sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
 			break;
+		case SO_REUSEPORT:
+			sk->sk_reuseport = valbool;
+			break;
 		default:
 			ret = -EINVAL;
 		}
@@ -4898,6 +4901,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
 		case SO_BINDTOIFINDEX:
 			*((int *)optval) = sk->sk_bound_dev_if;
 			break;
+		case SO_REUSEPORT:
+			*((int *)optval) = sk->sk_reuseport;
+			break;
 		default:
 			goto err_clear;
 		}
diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c
index 115a3b0ad984..474c6a62078a 100644
--- a/tools/testing/selftests/bpf/progs/bind4_prog.c
+++ b/tools/testing/selftests/bpf/progs/bind4_prog.c
@@ -57,6 +57,27 @@ static __inline int bind_to_device(struct bpf_sock_addr *ctx)
 	return 0;
 }
 
+static __inline int bind_reuseport(struct bpf_sock_addr *ctx)
+{
+	int val = 1;
+
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)))
+		return 1;
+	if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)) || !val)
+		return 1;
+	val = 0;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)))
+		return 1;
+	if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)) || val)
+		return 1;
+
+	return 0;
+}
+
 static __inline int misc_opts(struct bpf_sock_addr *ctx, int opt)
 {
 	int old, tmp, new = 0xeb9f;
@@ -127,6 +148,10 @@ int bind_v4_prog(struct bpf_sock_addr *ctx)
 	if (misc_opts(ctx, SO_MARK) || misc_opts(ctx, SO_PRIORITY))
 		return 0;
 
+	/* Set reuseport and unset */
+	if (bind_reuseport(ctx))
+		return 0;
+
 	ctx->user_ip4 = bpf_htonl(SERV4_REWRITE_IP);
 	ctx->user_port = bpf_htons(SERV4_REWRITE_PORT);
 
diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c
index 4c0d348034b9..c19cfa869f30 100644
--- a/tools/testing/selftests/bpf/progs/bind6_prog.c
+++ b/tools/testing/selftests/bpf/progs/bind6_prog.c
@@ -63,6 +63,27 @@ static __inline int bind_to_device(struct bpf_sock_addr *ctx)
 	return 0;
 }
 
+static __inline int bind_reuseport(struct bpf_sock_addr *ctx)
+{
+	int val = 1;
+
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)))
+		return 1;
+	if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)) || !val)
+		return 1;
+	val = 0;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)))
+		return 1;
+	if (bpf_getsockopt(ctx, SOL_SOCKET, SO_REUSEPORT,
+			   &val, sizeof(val)) || val)
+		return 1;
+
+	return 0;
+}
+
 static __inline int misc_opts(struct bpf_sock_addr *ctx, int opt)
 {
 	int old, tmp, new = 0xeb9f;
@@ -141,6 +162,10 @@ int bind_v6_prog(struct bpf_sock_addr *ctx)
 	if (misc_opts(ctx, SO_MARK) || misc_opts(ctx, SO_PRIORITY))
 		return 0;
 
+	/* Set reuseport and unset */
+	if (bind_reuseport(ctx))
+		return 0;
+
 	ctx->user_ip6[0] = bpf_htonl(SERV6_REWRITE_IP_0);
 	ctx->user_ip6[1] = bpf_htonl(SERV6_REWRITE_IP_1);
 	ctx->user_ip6[2] = bpf_htonl(SERV6_REWRITE_IP_2);
-- 
cgit v1.2.3


From 23f50b5ac331c8c27c421a7116618355508e8427 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@gmail.com>
Date: Mon, 15 Mar 2021 14:29:51 +0100
Subject: bpf: selftests: Remove unused 'nospace_err' in tests for batched ops
 in array maps

This seems to be a reminiscent from the hashmap tests.

Signed-off-by: Pedro Tammela <pctammela@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210315132954.603108-1-pctammela@gmail.com
---
 tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
index f0a64d8ac59a..e42ea1195d18 100644
--- a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
@@ -55,7 +55,6 @@ void test_array_map_batch_ops(void)
 	int map_fd, *keys, *values, *visited;
 	__u32 count, total, total_success;
 	const __u32 max_entries = 10;
-	bool nospace_err;
 	__u64 batch = 0;
 	int err, step;
 	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
@@ -90,7 +89,6 @@ void test_array_map_batch_ops(void)
 		 * elements each.
 		 */
 		count = step;
-		nospace_err = false;
 		while (true) {
 			err = bpf_map_lookup_batch(map_fd,
 						total ? &batch : NULL, &batch,
@@ -107,9 +105,6 @@ void test_array_map_batch_ops(void)
 
 		}
 
-		if (nospace_err == true)
-			continue;
-
 		CHECK(total != max_entries, "lookup with steps",
 		      "total = %u, max_entries = %u\n", total, max_entries);
 
-- 
cgit v1.2.3


From 105b842ba4ef2ddc287645cb33f90b960c16075b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Sat, 13 Mar 2021 13:09:19 -0800
Subject: selftests/bpf: Fix maybe-uninitialized warning in xdpxceiver test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

xsk_ring_prod__reserve() doesn't necessarily set idx in some conditions, so
from static analysis point of view compiler is right about the problems like:

In file included from xdpxceiver.c:92:
xdpxceiver.c: In function ‘xsk_populate_fill_ring’:
/data/users/andriin/linux/tools/testing/selftests/bpf/tools/include/bpf/xsk.h:119:20: warning: ‘idx’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  return &addrs[idx & fill->mask];
                ~~~~^~~~~~~~~~~~
xdpxceiver.c:300:6: note: ‘idx’ was declared here
  u32 idx;
      ^~~
xdpxceiver.c: In function ‘tx_only’:
xdpxceiver.c:596:30: warning: ‘idx’ may be used uninitialized in this function [-Wmaybe-uninitialized]
   struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
                              ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Fix two warnings reported by compiler by pre-initializing variable.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210313210920.1959628-4-andrii@kernel.org
---
 tools/testing/selftests/bpf/xdpxceiver.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 8b0f7fdd9003..1e21a3172687 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -297,7 +297,7 @@ static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
 static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
 {
 	int ret, i;
-	u32 idx;
+	u32 idx = 0;
 
 	ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
 	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
@@ -584,7 +584,7 @@ static void rx_pkt(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
 {
-	u32 idx;
+	u32 idx = 0;
 	unsigned int i;
 	bool tx_invalid_test = stat_test_type == STAT_TEST_TX_INVALID;
 	u32 len = tx_invalid_test ? XSK_UMEM__DEFAULT_FRAME_SIZE + 1 : PKT_SIZE;
-- 
cgit v1.2.3


From 252e3cbf2b623422b359b965b94060e8d68597e1 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Sat, 13 Mar 2021 13:09:20 -0800
Subject: selftests/bpf: Build everything in debug mode

Build selftests, bpftool, and libbpf in debug mode with DWARF data to
facilitate easier debugging.

In terms of impact on building and running selftests. Build is actually faster
now:

BEFORE: make -j60  380.21s user 37.87s system 1466% cpu 28.503 total
AFTER:  make -j60  345.47s user 37.37s system 1599% cpu 23.939 total

test_progs runtime seems to be the same:

BEFORE:
real    1m5.139s
user    0m1.600s
sys     0m43.977s

AFTER:
real    1m3.799s
user    0m1.721s
sys     0m42.420s

Huge difference is being able to debug issues throughout test_progs, bpftool,
and libbpf without constantly updating 3 Makefiles by hand (including GDB
seeing the source code without any extra incantations).

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210313210920.1959628-5-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c3999587bc23..d0db2b673c6f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -21,7 +21,7 @@ endif
 
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 SAN_CFLAGS	?=
-CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) $(SAN_CFLAGS)		\
+CFLAGS += -g -Og -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS)		\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)			\
 	  -Dbpf_prog_load=bpf_prog_test_load				\
@@ -201,6 +201,7 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
 		    CC=$(HOSTCC) LD=$(HOSTLD)				       \
+		    EXTRA_CFLAGS='-g -Og'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
 
@@ -218,6 +219,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   ../../../include/uapi/linux/bpf.h                                   \
 	   | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
+		    EXTRA_CFLAGS='-g -Og'					       \
 		    DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
 
 ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
@@ -225,7 +227,8 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)                \
 	   ../../../include/uapi/linux/bpf.h                                   \
 	   | $(INCLUDE_DIR) $(HOST_BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR)                             \
-		OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD)     \
+		    EXTRA_CFLAGS='-g -Og'					       \
+		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
 endif
 
-- 
cgit v1.2.3


From f0b692c4ee2fdd0d4291fe3cbde156792896895e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 16 Mar 2021 17:03:02 +0200
Subject: selftests: mlxsw: Add tc sample tests for new triggers

Test that packets are sampled when tc-sample is used with matchall
egress binding and flower classifier. Verify that when performing
sampling on egress the end-to-end latency is reported as metadata.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/tc_sample.sh       | 135 +++++++++++++++++++++
 1 file changed, 135 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
index 75d00104f291..57b05f042787 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -41,6 +41,10 @@ ALL_TESTS="
 	tc_sample_md_lag_oif_test
 	tc_sample_md_out_tc_test
 	tc_sample_md_out_tc_occ_test
+	tc_sample_md_latency_test
+	tc_sample_acl_group_conflict_test
+	tc_sample_acl_rate_test
+	tc_sample_acl_max_rate_test
 "
 NUM_NETIFS=8
 CAPTURE_FILE=$(mktemp)
@@ -482,6 +486,137 @@ tc_sample_md_out_tc_occ_test()
 	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
 }
 
+tc_sample_md_latency_test()
+{
+	RET=0
+
+	# Egress sampling not supported on Spectrum-1.
+	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+	tc filter add dev $rp2 egress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 5 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	grep -q -e "latency " $CAPTURE_FILE
+	check_err $? "Sampled packets do not have latency attribute"
+
+	log_test "tc sample latency"
+
+	tc filter del dev $rp2 egress protocol all pref 1 handle 101 matchall
+}
+
+tc_sample_acl_group_conflict_test()
+{
+	RET=0
+
+	# Test that two flower sampling rules cannot be configured on the same
+	# port with different groups.
+
+	# Policy-based sampling is not supported on Spectrum-1.
+	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+		skip_sw action sample rate 1024 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	tc filter add dev $rp1 ingress protocol ip pref 2 handle 102 flower \
+		skip_sw action sample rate 1024 group 1
+	check_err $? "Failed to configure sampling rule with same group"
+
+	tc filter add dev $rp1 ingress protocol ip pref 3 handle 103 flower \
+		skip_sw action sample rate 1024 group 2 &> /dev/null
+	check_fail $? "Managed to configure sampling rule with conflicting group"
+
+	log_test "tc sample (w/ flower) group conflict test"
+
+	tc filter del dev $rp1 ingress protocol ip pref 2 handle 102 flower
+	tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+}
+
+__tc_sample_acl_rate_test()
+{
+	local bind=$1; shift
+	local port=$1; shift
+	local pkts pct
+
+	RET=0
+
+	# Policy-based sampling is not supported on Spectrum-1.
+	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+	tc filter add dev $port $bind protocol ip pref 1 handle 101 flower \
+		skip_sw dst_ip 198.51.100.1 action sample rate 32 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l)
+	pct=$((100 * (pkts - 100) / 100))
+	(( -25 <= pct && pct <= 25))
+	check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%"
+
+	# Setup a filter that should not match any packet and make sure packets
+	# are not sampled.
+	tc filter del dev $port $bind protocol ip pref 1 handle 101 flower
+
+	tc filter add dev $port $bind protocol ip pref 1 handle 101 flower \
+		skip_sw dst_ip 198.51.100.10 action sample rate 32 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	psample_capture_start
+
+	ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \
+		-B 198.51.100.1 -t udp dp=52768,sp=42768 -q
+
+	psample_capture_stop
+
+	grep -q -e "group 1 " $CAPTURE_FILE
+	check_fail $? "Sampled packets when should not"
+
+	log_test "tc sample (w/ flower) rate ($bind)"
+
+	tc filter del dev $port $bind protocol ip pref 1 handle 101 flower
+}
+
+tc_sample_acl_rate_test()
+{
+	__tc_sample_acl_rate_test ingress $rp1
+	__tc_sample_acl_rate_test egress $rp2
+}
+
+tc_sample_acl_max_rate_test()
+{
+	RET=0
+
+	# Policy-based sampling is not supported on Spectrum-1.
+	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+
+	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+		skip_sw action sample rate $((2 ** 24 - 1)) group 1
+	check_err $? "Failed to configure sampling rule with max rate"
+
+	tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+
+	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+		skip_sw action sample rate $((2 ** 24)) \
+		group 1 &> /dev/null
+	check_fail $? "Managed to configure sampling rate above maximum"
+
+	log_test "tc sample (w/ flower) maximum rate"
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From 0f967d9e5a20aeee51bb004295e83c2c913cceda Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 16 Mar 2021 17:03:03 +0200
Subject: selftests: mlxsw: Test egress sampling limitation on Spectrum-1 only

Make sure egress sampling configuration only fails on Spectrum-1, given
that mlxsw now supports it on Spectrum-{2,3}.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
index 553cb9fad508..b4dbda706c4d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
@@ -18,6 +18,7 @@ NUM_NETIFS=2
 
 source $lib_dir/tc_common.sh
 source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
 
 switch_create()
 {
@@ -166,7 +167,8 @@ matchall_sample_egress_test()
 	RET=0
 
 	# It is forbidden in mlxsw driver to have matchall with sample action
-	# bound on egress
+	# bound on egress. Spectrum-1 specific restriction
+	[[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return
 
 	tc qdisc add dev $swp1 clsact
 
-- 
cgit v1.2.3


From ebda107e5f222a086c83ddf6d1ab1da97dd15810 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Tue, 16 Mar 2021 15:59:37 +0800
Subject: selftests/bpf: Fix warning comparing pointer to 0

Fix the following coccicheck warnings:

  ./tools/testing/selftests/bpf/progs/fexit_test.c:77:15-16: WARNING
  comparing pointer to 0.

  ./tools/testing/selftests/bpf/progs/fexit_test.c:68:12-13: WARNING
  comparing pointer to 0.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/1615881577-3493-1-git-send-email-jiapeng.chong@linux.alibaba.com
---
 tools/testing/selftests/bpf/progs/fexit_test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
index 0952affb22a6..8f1ccb7302e1 100644
--- a/tools/testing/selftests/bpf/progs/fexit_test.c
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -65,7 +65,7 @@ __u64 test7_result = 0;
 SEC("fexit/bpf_fentry_test7")
 int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
 {
-	if (arg == 0)
+	if (!arg)
 		test7_result = 1;
 	return 0;
 }
@@ -74,7 +74,7 @@ __u64 test8_result = 0;
 SEC("fexit/bpf_fentry_test8")
 int BPF_PROG(test8, struct bpf_fentry_test_t *arg)
 {
-	if (arg->a == 0)
+	if (!arg->a)
 		test8_result = 1;
 	return 0;
 }
-- 
cgit v1.2.3


From 56901d483bf14ca729a6c4e06d2b49590b9f1971 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Date: Tue, 16 Mar 2021 21:00:48 +0530
Subject: selftests/bpf: Use nanosleep() syscall instead of sleep() in
 get_cgroup_id

Glibc's sleep() switched to clock_nanosleep() from nanosleep(), and thus
syscalls:sys_enter_nanosleep tracepoint is not hitting which is causing
testcase failure. Instead of depending on glibc sleep(), call nanosleep()
systemcall directly.

Before:

  # ./get_cgroup_id_user
  ...
  main:FAIL:compare_cgroup_id kern cgid 0 user cgid 483

After:

  # ./get_cgroup_id_user
  ...
  main:PASS:compare_cgroup_id

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210316153048.136447-1-ravi.bangoria@linux.ibm.com
---
 tools/testing/selftests/bpf/get_cgroup_id_user.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c
index b8d6aef99db4..99628e1a1e58 100644
--- a/tools/testing/selftests/bpf/get_cgroup_id_user.c
+++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c
@@ -57,6 +57,10 @@ int main(int argc, char **argv)
 	__u32 key = 0, pid;
 	int exit_code = 1;
 	char buf[256];
+	const struct timespec req = {
+		.tv_sec = 1,
+		.tv_nsec = 0,
+	};
 
 	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
 	if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno))
@@ -115,7 +119,7 @@ int main(int argc, char **argv)
 		goto close_pmu;
 
 	/* trigger some syscalls */
-	sleep(1);
+	syscall(__NR_nanosleep, &req, NULL);
 
 	err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid);
 	if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno))
-- 
cgit v1.2.3


From 35f15ab378fa7e1eaa25798076a457523b5ace75 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 17 Mar 2021 12:35:28 +0200
Subject: selftests: forwarding: Add test for dual VxLAN bridge

Configure VxLAN with an 802.1ad bridge and VxLAN with an 802.1d bridge
at the same time in same switch, verify that traffic passed as expected.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/dual_vxlan_bridge.sh  | 366 +++++++++++++++++++++
 1 file changed, 366 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh
new file mode 100755
index 000000000000..5148d97a5df8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/dual_vxlan_bridge.sh
@@ -0,0 +1,366 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------+                               +----------------------+
+# | H1 (vrf)           |                               |             H2 (vrf) |
+# |    + h1.10         |                               |  + h2.20             |
+# |    | 192.0.2.1/28  |                               |  | 192.0.2.2/28      |
+# |    |               |                               |  |                   |
+# |    + $h1           |                               |  + $h2               |
+# |    |               |                               |  |                   |
+# +----|---------------+                               +--|-------------------+
+#      |                                                  |
+# +----|--------------------------------------------------|--------------------+
+# | SW |                                                  |                    |
+# | +--|-------------------------------+ +----------------|------------------+ |
+# | |  + $swp1         BR1 (802.1ad)   | | BR2 (802.1d)   + $swp2            | |
+# | |    vid 100 pvid untagged         | |                |                  | |
+# | |                                  | |                + $swp2.20         | |
+# | |                                  | |                                   | |
+# | |  + vx100 (vxlan)                 | |  + vx200 (vxlan)                  | |
+# | |    local 192.0.2.17              | |    local 192.0.2.17               | |
+# | |    remote 192.0.2.34             | |    remote 192.0.2.50              | |
+# | |    id 1000 dstport $VXPORT       | |    id 2000 dstport $VXPORT        | |
+# | |    vid 100 pvid untagged         | |                                   | |
+# | +--------------------------------- + +-----------------------------------+ |
+# |                                                                            |
+# |  192.0.2.32/28 via 192.0.2.18                                              |
+# |  192.0.2.48/28 via 192.0.2.18                                              |
+# |                                                                            |
+# |    + $rp1                                                                  |
+# |    | 192.0.2.17/28                                                         |
+# +----|-----------------------------------------------------------------------+
+#      |
+# +----|--------------------------------------------------------+
+# |    |                                             VRP2 (vrf) |
+# |    + $rp2                                                   |
+# |      192.0.2.18/28                                          |
+# |                                                             |   (maybe) HW
+# =============================================================================
+# |                                                             |  (likely) SW
+# |    + v1 (veth)                             + v3 (veth)      |
+# |    | 192.0.2.33/28                         | 192.0.2.49/28  |
+# +----|---------------------------------------|----------------+
+#      |                                       |
+# +----|------------------------------+   +----|------------------------------+
+# |    + v2 (veth)        NS1 (netns) |   |    + v4 (veth)        NS2 (netns) |
+# |      192.0.2.34/28                |   |      192.0.2.50/28                |
+# |                                   |   |                                   |
+# |   192.0.2.16/28 via 192.0.2.33    |   |   192.0.2.16/28 via 192.0.2.49    |
+# |   192.0.2.50/32 via 192.0.2.33    |   |   192.0.2.34/32 via 192.0.2.49    |
+# |                                   |   |                                   |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# | |                 BR3 (802.1ad) | |   | |                  BR3 (802.1d) | |
+# | |  + vx100 (vxlan)              | |   | |  + vx200 (vxlan)              | |
+# | |    local 192.0.2.34           | |   | |    local 192.0.2.50           | |
+# | |    remote 192.0.2.17          | |   | |    remote 192.0.2.17          | |
+# | |    remote 192.0.2.50          | |   | |    remote 192.0.2.34          | |
+# | |    id 1000 dstport $VXPORT    | |   | |    id 2000 dstport $VXPORT    | |
+# | |    vid 100 pvid untagged      | |   | |                               | |
+# | |                               | |   | |  + w1.20                      | |
+# | |                               | |   | |  |                            | |
+# | |  + w1 (veth)                  | |   | |  + w1 (veth)                  | |
+# | |  | vid 100 pvid untagged      | |   | |  |                            | |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# |    |                              |   |    |                              |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# | |  |                  VW2 (vrf) | |   | |  |                  VW2 (vrf) | |
+# | |  + w2 (veth)                  | |   | |  + w2 (veth)                  | |
+# | |  |                            | |   | |  |                            | |
+# | |  |                            | |   | |  |                            | |
+# | |  + w2.10                      | |   | |  + w2.20                      | |
+# | |    192.0.2.3/28               | |   | |    192.0.2.4/28               | |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# +-----------------------------------+   +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+	ping_ipv4
+    "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	tc qdisc add dev $h1 clsact
+	vlan_create $h1 10 v$h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+	vlan_destroy $h1 10
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	tc qdisc add dev $h2 clsact
+	vlan_create $h2 20 v$h2 192.0.2.2/28
+}
+
+h2_destroy()
+{
+	vlan_destroy $h2 20
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2
+}
+
+rp1_set_addr()
+{
+	ip address add dev $rp1 192.0.2.17/28
+
+	ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+	ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+	ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+	ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+	ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+	#### BR1 ####
+	ip link add name br1 type bridge vlan_filtering 1 \
+		vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+	# Make sure the bridge uses the MAC address of the local port and not
+	# that of the VxLAN's device.
+	ip link set dev br1 address $(mac_get $swp1)
+	ip link set dev br1 up
+
+	#### BR2 ####
+	ip link add name br2 type bridge vlan_filtering 0 mcast_snooping 0
+	# Make sure the bridge uses the MAC address of the local port and not
+	# that of the VxLAN's device.
+	ip link set dev br2 address $(mac_get $swp2)
+	ip link set dev br2 up
+
+	ip link set dev $rp1 up
+	rp1_set_addr
+
+	#### VX100 ####
+	ip link add name vx100 type vxlan id 1000 local 192.0.2.17 \
+		dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+	ip link set dev vx100 up
+
+	ip link set dev vx100 master br1
+	bridge vlan add vid 100 dev vx100 pvid untagged
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+	bridge vlan add vid 100 dev $swp1 pvid untagged
+
+	#### VX200 ####
+	ip link add name vx200 type vxlan id 2000 local 192.0.2.17 \
+		dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+	ip link set dev vx200 up
+
+	ip link set dev vx200 master br2
+
+	ip link set dev $swp2 up
+	ip link add name $swp2.20 link $swp2 type vlan id 20
+	ip link set dev $swp2.20 master br2
+	ip link set dev $swp2.20 up
+
+	bridge fdb append dev vx100 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx200 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+	bridge fdb del dev vx200 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx100 00:00:00:00:00:00 dst 192.0.2.34 self
+
+	ip link set dev vx200 nomaster
+	ip link set dev vx200 down
+	ip link del dev vx200
+
+	ip link del dev $swp2.20
+	ip link set dev $swp2 down
+	ip link set dev $swp2 nomaster
+
+	bridge vlan del vid 100 dev $swp1
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link set dev vx100 nomaster
+	ip link set dev vx100 down
+	ip link del dev vx100
+
+	rp1_unset_addr
+	ip link set dev $rp1 down
+
+	ip link set dev br2 down
+	ip link del dev br2
+
+	ip link set dev br1 down
+	ip link del dev br1
+}
+
+vrp2_create()
+{
+	simple_if_init $rp2 192.0.2.18/28
+	__simple_if_init v1 v$rp2 192.0.2.33/28
+	__simple_if_init v3 v$rp2 192.0.2.49/28
+	tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+	tc qdisc del dev v1 clsact
+	__simple_if_fini v3 192.0.2.49/28
+	__simple_if_fini v1 192.0.2.33/28
+	simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+	local in_if=$1; shift
+	local in_addr=$1; shift
+	local other_in_addr=$1; shift
+	local vxlan_name=$1; shift
+	local vxlan_id=$1; shift
+	local vlan_id=$1; shift
+	local host_addr=$1; shift
+	local nh_addr=$1; shift
+
+	ip link set dev $in_if up
+	ip address add dev $in_if $in_addr/28
+	tc qdisc add dev $in_if clsact
+
+	ip link add name br3 type bridge vlan_filtering 0
+	ip link set dev br3 up
+
+	ip link add name w1 type veth peer name w2
+
+	ip link set dev w1 master br3
+	ip link set dev w1 up
+
+	ip link add name $vxlan_name type vxlan id $vxlan_id local $in_addr \
+		dstport "$VXPORT"
+	ip link set dev $vxlan_name up
+	bridge fdb append dev $vxlan_name 00:00:00:00:00:00 dst 192.0.2.17 self
+	bridge fdb append dev $vxlan_name 00:00:00:00:00:00 dst $other_in_addr self
+
+	ip link set dev $vxlan_name master br3
+	tc qdisc add dev $vxlan_name clsact
+
+	simple_if_init w2
+	vlan_create w2 $vlan_id vw2 $host_addr/28
+
+	ip route add 192.0.2.16/28 nexthop via $nh_addr
+	ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+	ip netns add ns1
+	ip link set dev v2 netns ns1
+	in_ns ns1 \
+	      ns_init_common v2 192.0.2.34 192.0.2.50 vx100 1000 10 192.0.2.3 \
+	      192.0.2.33
+
+	in_ns ns1 bridge vlan add vid 100 dev vx100 pvid untagged
+}
+
+ns1_destroy()
+{
+	ip netns exec ns1 ip link set dev v2 netns 1
+	ip netns del ns1
+}
+
+ns2_create()
+{
+	ip netns add ns2
+	ip link set dev v4 netns ns2
+	in_ns ns2 \
+	      ns_init_common v4 192.0.2.50 192.0.2.34 vx200 2000 20 192.0.2.4 \
+	      192.0.2.49
+
+	in_ns ns2 ip link add name w1.20 link w1 type vlan id 20
+	in_ns ns2 ip link set dev w1.20 master br3
+	in_ns ns2 ip link set dev w1.20 up
+}
+
+ns2_destroy()
+{
+	ip netns exec ns2 ip link set dev v4 netns 1
+	ip netns del ns2
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1=${NETIFS[p5]}
+	rp2=${NETIFS[p6]}
+
+	vrf_prepare
+	forwarding_enable
+
+	h1_create
+	h2_create
+	switch_create
+
+	ip link add name v1 type veth peer name v2
+	ip link add name v3 type veth peer name v4
+	vrp2_create
+	ns1_create
+	ns2_create
+
+	r1_mac=$(in_ns ns1 mac_get w2)
+	r2_mac=$(in_ns ns2 mac_get w2)
+	h2_mac=$(mac_get $h2)
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ns2_destroy
+	ns1_destroy
+	vrp2_destroy
+	ip link del dev v3
+	ip link del dev v1
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	forwarding_restore
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.3 ": local->remote 1 through VxLAN with an 802.1ad bridge"
+	ping_test $h2 192.0.2.4 ": local->remote 2 through VxLAN with an 802.1d bridge"
+}
+
+test_all()
+{
+	echo "Running tests with UDP port $VXPORT"
+	tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 1724c97d2f9ddcfe2e372f9b02d6efde15b885b0 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 17 Mar 2021 12:35:29 +0200
Subject: selftests: mlxsw: spectrum-2: Remove q_in_vni_veto test

q_in_vni_veto.sh is not needed anymore because VxLAN with an 802.1ad
bridge and VxLAN with an 802.1d bridge can coexist.

Remove the test.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh  | 77 ----------------------
 1 file changed, 77 deletions(-)
 delete mode 100755 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh
deleted file mode 100755
index 0231205a7147..000000000000
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh
+++ /dev/null
@@ -1,77 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-lib_dir=$(dirname $0)/../../../../net/forwarding
-
-VXPORT=4789
-
-ALL_TESTS="
-	create_dot1d_and_dot1ad_vxlans
-"
-NUM_NETIFS=2
-source $lib_dir/lib.sh
-
-setup_prepare()
-{
-	swp1=${NETIFS[p1]}
-	swp2=${NETIFS[p2]}
-
-	ip link set dev $swp1 up
-	ip link set dev $swp2 up
-}
-
-cleanup()
-{
-	pre_cleanup
-
-	ip link set dev $swp2 down
-	ip link set dev $swp1 down
-}
-
-create_dot1d_and_dot1ad_vxlans()
-{
-	RET=0
-
-	ip link add dev br0 type bridge vlan_filtering 1 vlan_protocol 802.1ad \
-		vlan_default_pvid 0 mcast_snooping 0
-	ip link set dev br0 up
-
-	ip link add name vx100 type vxlan id 1000 local 192.0.2.17 dstport \
-		"$VXPORT" nolearning noudpcsum tos inherit ttl 100
-	ip link set dev vx100 up
-
-	ip link set dev $swp1 master br0
-	ip link set dev vx100 master br0
-	bridge vlan add vid 100 dev vx100 pvid untagged
-
-	ip link add dev br1 type bridge vlan_filtering 0 mcast_snooping 0
-	ip link set dev br1 up
-
-	ip link add name vx200 type vxlan id 2000 local 192.0.2.17 dstport \
-		"$VXPORT" nolearning noudpcsum tos inherit ttl 100
-	ip link set dev vx200 up
-
-	ip link set dev $swp2 master br1
-	ip link set dev vx200 master br1 2>/dev/null
-	check_fail $? "802.1d and 802.1ad VxLANs at the same time not rejected"
-
-	ip link set dev vx200 master br1 2>&1 >/dev/null \
-		| grep -q mlxsw_spectrum
-	check_err $? "802.1d and 802.1ad VxLANs at the same time rejected without extack"
-
-	log_test "create 802.1d and 802.1ad VxLANs"
-
-	ip link del dev vx200
-	ip link del dev br1
-	ip link del dev vx100
-	ip link del dev br0
-}
-
-trap cleanup EXIT
-
-setup_prepare
-setup_wait
-
-tests_run
-
-exit $EXIT_STATUS
-- 
cgit v1.2.3


From c53a3355eb2976fc4eb4d42862db0eea205045a1 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 17 Mar 2021 13:05:10 -0700
Subject: selftests/bpf: drop custom NULL #define in skb_pkt_end selftest

Now that bpftool generates NULL definition as part of vmlinux.h, drop custom
NULL definition in skb_pkt_end.c.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20210317200510.1354627-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/skb_pkt_end.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
index cf6823f42e80..7f2eaa2f89f8 100644
--- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c
+++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
@@ -4,7 +4,6 @@
 #include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 
-#define NULL 0
 #define INLINE __always_inline
 
 #define skb_shorter(skb, len) ((void *)(long)(skb)->data + (len) > (void *)(long)skb->data_end)
-- 
cgit v1.2.3


From cab62c37be057379a2a17b1b2eacd9dcba1e14dc Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 18 Mar 2021 12:40:34 -0700
Subject: selftests/bpf: Re-generate vmlinux.h and BPF skeletons if bpftool
 changed

Trigger vmlinux.h and BPF skeletons re-generation if detected that bpftool was
re-compiled. Otherwise full `make clean` is required to get updated skeletons,
if bpftool is modified.

Fixes: acbd06206bbb ("selftests/bpf: Add vmlinux.h selftest exercising tracing of syscalls")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210318194036.3521577-11-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d0db2b673c6f..dbca39f45382 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -232,7 +232,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)                \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
 endif
 
-$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR)
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
 ifeq ($(VMLINUX_H),)
 	$(call msg,GEN,,$@)
 	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
@@ -357,7 +357,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 
 $(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h:			\
 		      $(TRUNNER_OUTPUT)/%.o				\
-		      | $(BPFTOOL) $(TRUNNER_OUTPUT)
+		      $(BPFTOOL)					\
+		      | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
 	$(Q)$$(BPFTOOL) gen skeleton $$< > $$@
 endif
-- 
cgit v1.2.3


From 14137f3c62186799b01eea8a338f90c9cbc57f00 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 18 Mar 2021 12:40:35 -0700
Subject: selftests/bpf: Pass all BPF .o's through BPF static linker

Pass all individual BPF object files (generated from progs/*.c) through
`bpftool gen object` command to validate that BPF static linker doesn't
corrupt them.

As an additional sanity checks, validate that passing resulting object files
through linker again results in identical ELF files. Exact same ELF contents
can be guaranteed only after two passes, as after the first pass ELF sections
order changes, and thus .BTF.ext data sections order changes. That, in turn,
means that strings are added into the final BTF string sections in different
order, so .BTF strings data might not be exactly the same. But doing another
round of linking afterwards should result in the identical ELF file, which is
checked with additional `diff` command.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210318194036.3521577-12-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index dbca39f45382..3a7c02add70c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -355,12 +355,13 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS))
 
-$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h:			\
-		      $(TRUNNER_OUTPUT)/%.o				\
-		      $(BPFTOOL)					\
-		      | $(TRUNNER_OUTPUT)
+$(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
-	$(Q)$$(BPFTOOL) gen skeleton $$< > $$@
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked.o) $$<
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked.o)
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o)
+	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
+	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked.o) name $$(notdir $$(<:.o=)) > $$@
 endif
 
 # ensure we set up tests.h header generation rule just once
-- 
cgit v1.2.3


From a0964f526df6facd4e12a4c416185013026eecf9 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 18 Mar 2021 12:40:36 -0700
Subject: selftests/bpf: Add multi-file statically linked BPF object file test

Add Makefile infra to specify multi-file BPF object files (and derivative
skeletons). Add first selftest validating BPF static linker can merge together
successfully two independent BPF object files and resulting object and
skeleton are correct and usable.

Use the same F(F(F(X))) = F(F(X)) identity test on linked object files as for
the case of single BPF object files.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210318194036.3521577-13-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile               | 21 ++++++++++--
 .../selftests/bpf/prog_tests/static_linked.c       | 40 ++++++++++++++++++++++
 .../selftests/bpf/progs/test_static_linked1.c      | 30 ++++++++++++++++
 .../selftests/bpf/progs/test_static_linked2.c      | 31 +++++++++++++++++
 4 files changed, 119 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/static_linked.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_static_linked1.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_static_linked2.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 3a7c02add70c..6448c626498f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -303,6 +303,10 @@ endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 
+LINKED_SKELS := test_static_linked.skel.h
+
+test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
+
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
 # Parameters:
@@ -323,6 +327,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)
 TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
 				 $$(filter-out $(SKEL_BLACKLIST),	\
 					       $$(TRUNNER_BPF_SRCS)))
+TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
 TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
 
 # Evaluate rules now with extra TRUNNER_XXX variables above already defined
@@ -357,11 +362,20 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 
 $(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
-	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked.o) $$<
-	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked.o)
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked1.o) $$<
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked1.o)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o)
 	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
-	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked.o) name $$(notdir $$(<:.o=)) > $$@
+	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@
+
+$(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
+	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o))
+	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps))
+	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked1.o)
+	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked3.o) $$(@:.skel.h=.linked2.o)
+	$(Q)diff $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked3.o)
+	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
+	$(Q)$$(BPFTOOL) gen skeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$@
 endif
 
 # ensure we set up tests.h header generation rule just once
@@ -383,6 +397,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_EXTRA_HDRS)				\
 		      $(TRUNNER_BPF_OBJS)				\
 		      $(TRUNNER_BPF_SKELS)				\
+		      $(TRUNNER_BPF_SKELS_LINKED)			\
 		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
 	$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
diff --git a/tools/testing/selftests/bpf/prog_tests/static_linked.c b/tools/testing/selftests/bpf/prog_tests/static_linked.c
new file mode 100644
index 000000000000..46556976dccc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/static_linked.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <test_progs.h>
+#include "test_static_linked.skel.h"
+
+void test_static_linked(void)
+{
+	int err;
+	struct test_static_linked* skel;
+
+	skel = test_static_linked__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->rodata->rovar1 = 1;
+	skel->bss->static_var1 = 2;
+	skel->bss->static_var11 = 3;
+
+	skel->rodata->rovar2 = 4;
+	skel->bss->static_var2 = 5;
+	skel->bss->static_var22 = 6;
+
+	err = test_static_linked__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = test_static_linked__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->var1, 1 * 2 + 2 + 3, "var1");
+	ASSERT_EQ(skel->bss->var2, 4 * 3 + 5 + 6, "var2");
+
+cleanup:
+	test_static_linked__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_static_linked1.c b/tools/testing/selftests/bpf/progs/test_static_linked1.c
new file mode 100644
index 000000000000..ea1a6c4c7172
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_static_linked1.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/* 8-byte aligned .bss */
+static volatile long static_var1;
+static volatile int static_var11;
+int var1 = 0;
+/* 4-byte aligned .rodata */
+const volatile int rovar1;
+
+/* same "subprog" name in both files */
+static __noinline int subprog(int x)
+{
+	/* but different formula */
+	return x * 2;
+}
+
+SEC("raw_tp/sys_enter")
+int handler1(const void *ctx)
+{
+	var1 = subprog(rovar1) + static_var1 + static_var11;
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
+int VERSION SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_static_linked2.c b/tools/testing/selftests/bpf/progs/test_static_linked2.c
new file mode 100644
index 000000000000..54d8d1ab577c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_static_linked2.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/* 4-byte aligned .bss */
+static volatile int static_var2;
+static volatile int static_var22;
+int var2 = 0;
+/* 8-byte aligned .rodata */
+const volatile long rovar2;
+
+/* same "subprog" name in both files */
+static __noinline int subprog(int x)
+{
+	/* but different formula */
+	return x * 3;
+}
+
+SEC("raw_tp/sys_enter")
+int handler2(const void *ctx)
+{
+	var2 = subprog(rovar2) + static_var2 + static_var22;
+
+	return 0;
+}
+
+/* different name and/or type of the variable doesn't matter */
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
-- 
cgit v1.2.3


From 38cb57602369cf194556460a52bd18e53c76e13d Mon Sep 17 00:00:00 2001
From: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Date: Fri, 19 Mar 2021 04:59:45 +0530
Subject: selftests: net: forwarding: Fix a typo

s/verfied/verified/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/fib_offload_lib.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
index 66496659bea7..e134a5f529c9 100644
--- a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
+++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh
@@ -224,7 +224,7 @@ fib_ipv4_plen_test()
 	ip -n $ns link set dev dummy1 up
 
 	# Add two routes with the same key and different prefix length and
-	# make sure both are in hardware. It can be verfied that both are
+	# make sure both are in hardware. It can be verified that both are
 	# sharing the same leaf by checking the /proc/net/fib_trie
 	ip -n $ns route add 192.0.2.0/24 dev dummy1
 	ip -n $ns route add 192.0.2.0/25 dev dummy1
-- 
cgit v1.2.3


From 79d4071ea4c49260286cf75dc669a0ed354d1c4e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 24 Mar 2021 02:30:45 +0100
Subject: selftests: netfilter: flowtable bridge and vlan support

This patch adds two new tests to cover bridge and vlan support:

- Add a bridge device to the Router1 (nsr1) container and attach the
  veth0 device to the bridge. Set the IP address to the bridge device
  to exercise the bridge forwarding path.

- Add vlan encapsulation between to the bridge device in the Router1 and
  one of the sender containers (ns1).

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/netfilter/nft_flowtable.sh | 82 ++++++++++++++++++++++
 1 file changed, 82 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index 431296c0f91c..427d94816f2d 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -371,6 +371,88 @@ else
 	ip netns exec nsr1 nft list ruleset
 fi
 
+# Another test:
+# Add bridge interface br0 to Router1, with NAT enabled.
+ip -net nsr1 link add name br0 type bridge
+ip -net nsr1 addr flush dev veth0
+ip -net nsr1 link set up dev veth0
+ip -net nsr1 link set veth0 master br0
+ip -net nsr1 addr add 10.0.1.1/24 dev br0
+ip -net nsr1 addr add dead:1::1/64 dev br0
+ip -net nsr1 link set up dev br0
+
+ip netns exec nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
+
+# br0 with NAT enabled.
+ip netns exec nsr1 nft -f - <<EOF
+flush table ip nat
+table ip nat {
+   chain prerouting {
+      type nat hook prerouting priority 0; policy accept;
+      meta iif "br0" ip daddr 10.6.6.6 tcp dport 1666 counter dnat ip to 10.0.2.99:12345
+   }
+
+   chain postrouting {
+      type nat hook postrouting priority 0; policy accept;
+      meta oifname "veth1" counter masquerade
+   }
+}
+EOF
+
+if test_tcp_forwarding_nat ns1 ns2; then
+	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT"
+else
+	echo "FAIL: flow offload for ns1/ns2 with bridge NAT" 1>&2
+	ip netns exec nsr1 nft list ruleset
+	ret=1
+fi
+
+# Another test:
+# Add bridge interface br0 to Router1, with NAT and VLAN.
+ip -net nsr1 link set veth0 nomaster
+ip -net nsr1 link set down dev veth0
+ip -net nsr1 link add link veth0 name veth0.10 type vlan id 10
+ip -net nsr1 link set up dev veth0
+ip -net nsr1 link set up dev veth0.10
+ip -net nsr1 link set veth0.10 master br0
+
+ip -net ns1 addr flush dev eth0
+ip -net ns1 link add link eth0 name eth0.10 type vlan id 10
+ip -net ns1 link set eth0 up
+ip -net ns1 link set eth0.10 up
+ip -net ns1 addr add 10.0.1.99/24 dev eth0.10
+ip -net ns1 route add default via 10.0.1.1
+ip -net ns1 addr add dead:1::99/64 dev eth0.10
+
+if test_tcp_forwarding_nat ns1 ns2; then
+	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT and VLAN"
+else
+	echo "FAIL: flow offload for ns1/ns2 with bridge NAT and VLAN" 1>&2
+	ip netns exec nsr1 nft list ruleset
+	ret=1
+fi
+
+# restore test topology (remove bridge and VLAN)
+ip -net nsr1 link set veth0 nomaster
+ip -net nsr1 link set veth0 down
+ip -net nsr1 link set veth0.10 down
+ip -net nsr1 link delete veth0.10 type vlan
+ip -net nsr1 link delete br0 type bridge
+ip -net ns1 addr flush dev eth0.10
+ip -net ns1 link set eth0.10 down
+ip -net ns1 link set eth0 down
+ip -net ns1 link delete eth0.10 type vlan
+
+# restore address in ns1 and nsr1
+ip -net ns1 link set eth0 up
+ip -net ns1 addr add 10.0.1.99/24 dev eth0
+ip -net ns1 route add default via 10.0.1.1
+ip -net ns1 addr add dead:1::99/64 dev eth0
+ip -net ns1 route add default via dead:1::1
+ip -net nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net nsr1 addr add dead:1::1/64 dev veth0
+ip -net nsr1 link set up dev veth0
+
 KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
 KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
 SPI1=$RANDOM
-- 
cgit v1.2.3


From 861584724c44e63bfb684090c70ade660dae6c69 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 24 Mar 2021 22:14:23 +0200
Subject: selftests: mlxsw: Test unresolved neigh trap with resilient nexthop
 groups

The number of nexthop buckets in a resilient nexthop group never
changes, so when the gateway address of a nexthop cannot be resolved,
the nexthop buckets are programmed to trap packets to the CPU in order
to trigger resolution. For example:

 # ip nexthop add id 1 via 198.51.100.1 dev swp3
 # ip nexthop add id 10 group 1 type resilient buckets 32
 # ip nexthop bucket get id 10 index 0
 id 10 index 0 idle_time 1.44 nhid 1 trap

Where 198.51.100.1 is a made-up IP.

Test that in this case packets are indeed trapped to the CPU via the
unresolved neigh trap.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/mlxsw/devlink_trap_l3_exceptions.sh        | 31 ++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
index 1fedfc9da434..42d44e27802c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
@@ -446,6 +446,35 @@ __invalid_nexthop_test()
 	log_test "Unresolved neigh: nexthop does not exist: $desc"
 }
 
+__invalid_nexthop_bucket_test()
+{
+	local desc=$1; shift
+	local dip=$1; shift
+	local via_add=$1; shift
+	local trap_name="unresolved_neigh"
+
+	RET=0
+
+	# Check that route to nexthop that does not exist triggers
+	# unresolved_neigh
+	ip nexthop add id 1 via $via_add dev $rp2
+	ip nexthop add id 10 group 1 type resilient buckets 32
+	ip route add $dip nhid 10
+
+	t0_packets=$(devlink_trap_rx_packets_get $trap_name)
+	ping_do $h1 $dip
+	t1_packets=$(devlink_trap_rx_packets_get $trap_name)
+
+	if [[ $t0_packets -eq $t1_packets ]]; then
+		check_err 1 "Trap counter did not increase"
+	fi
+
+	ip route del $dip nhid 10
+	ip nexthop del id 10
+	ip nexthop del id 1
+	log_test "Unresolved neigh: nexthop bucket does not exist: $desc"
+}
+
 unresolved_neigh_test()
 {
 	__host_miss_test "IPv4" 198.51.100.1
@@ -453,6 +482,8 @@ unresolved_neigh_test()
 	__invalid_nexthop_test "IPv4" 198.51.100.1 198.51.100.3 24 198.51.100.4
 	__invalid_nexthop_test "IPv6" 2001:db8:2::1 2001:db8:2::3 64 \
 		2001:db8:2::4
+	__invalid_nexthop_bucket_test "IPv4" 198.51.100.1 198.51.100.4
+	__invalid_nexthop_bucket_test "IPv6" 2001:db8:2::1 2001:db8:2::4
 }
 
 vrf_without_routes_create()
-- 
cgit v1.2.3


From ffd3e9b07b9ee3242fa5f5bc76385b6a0e69437d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 24 Mar 2021 22:14:24 +0200
Subject: selftests: mlxsw: Add resilient nexthop groups configuration tests

Test that unsupported resilient nexthop group configurations are
rejected and that offload / trap indication is correctly set on nexthop
buckets in a resilient group.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh       | 82 ++++++++++++++++++++++
 tools/testing/selftests/net/forwarding/lib.sh      |  5 ++
 2 files changed, 87 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index ed346da5d3cb..a217f9f6775b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -33,6 +33,7 @@ ALL_TESTS="
 	nexthop_obj_invalid_test
 	nexthop_obj_offload_test
 	nexthop_obj_group_offload_test
+	nexthop_obj_bucket_offload_test
 	nexthop_obj_blackhole_offload_test
 	nexthop_obj_route_offload_test
 	devlink_reload_test
@@ -739,11 +740,28 @@ nexthop_obj_invalid_test()
 
 	ip nexthop add id 1 dev $swp1
 	ip nexthop add id 2 dev $swp1
+	ip nexthop add id 3 via 192.0.2.3 dev $swp1
 	ip nexthop add id 10 group 1/2
 	check_fail $? "managed to configure a nexthop group with device-only nexthops when should not"
 
+	ip nexthop add id 10 group 3 type resilient buckets 7
+	check_fail $? "managed to configure a too small resilient nexthop group when should not"
+
+	ip nexthop add id 10 group 3 type resilient buckets 129
+	check_fail $? "managed to configure a resilient nexthop group with invalid number of buckets when should not"
+
+	ip nexthop add id 10 group 1/2 type resilient buckets 32
+	check_fail $? "managed to configure a resilient nexthop group with device-only nexthops when should not"
+
+	ip nexthop add id 10 group 3 type resilient buckets 32
+	check_err $? "failed to configure a valid resilient nexthop group"
+	ip nexthop replace id 3 dev $swp1
+	check_fail $? "managed to populate a nexthop bucket with a device-only nexthop when should not"
+
 	log_test "nexthop objects - invalid configurations"
 
+	ip nexthop del id 10
+	ip nexthop del id 3
 	ip nexthop del id 2
 	ip nexthop del id 1
 
@@ -858,6 +876,70 @@ nexthop_obj_group_offload_test()
 	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
 }
 
+nexthop_obj_bucket_offload_test()
+{
+	# Test offload indication of nexthop buckets
+	RET=0
+
+	simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+	simple_if_init $swp2
+	setup_wait
+
+	ip nexthop add id 1 via 192.0.2.2 dev $swp1
+	ip nexthop add id 2 via 2001:db8:1::2 dev $swp1
+	ip nexthop add id 10 group 1/2 type resilient buckets 32 idle_timer 0
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop bucket show nhid 1
+	check_err $? "IPv4 nexthop buckets not marked as offloaded when should"
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop bucket show nhid 2
+	check_err $? "IPv6 nexthop buckets not marked as offloaded when should"
+
+	# Invalidate nexthop id 1
+	ip neigh replace 192.0.2.2 nud failed dev $swp1
+	busywait "$TIMEOUT" wait_for_trap \
+		ip nexthop bucket show nhid 1
+	check_err $? "IPv4 nexthop buckets not marked with trap when should"
+
+	# Invalidate nexthop id 2
+	ip neigh replace 2001:db8:1::2 nud failed dev $swp1
+	busywait "$TIMEOUT" wait_for_trap \
+		ip nexthop bucket show nhid 2
+	check_err $? "IPv6 nexthop buckets not marked with trap when should"
+
+	# Revalidate nexthop id 1 by changing its configuration
+	ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop bucket show nhid 1
+	check_err $? "nexthop bucket not marked as offloaded after revalidating nexthop"
+
+	# Revalidate nexthop id 2 by changing its neighbour
+	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+		dev $swp1
+	busywait "$TIMEOUT" wait_for_offload \
+		ip nexthop bucket show nhid 2
+	check_err $? "nexthop bucket not marked as offloaded after revalidating neighbour"
+
+	log_test "nexthop bucket offload indication"
+
+	ip neigh del 2001:db8:1::2 dev $swp1
+	ip neigh del 192.0.2.3 dev $swp1
+	ip neigh del 192.0.2.2 dev $swp1
+	ip nexthop del id 10
+	ip nexthop del id 2
+	ip nexthop del id 1
+
+	simple_if_fini $swp2
+	simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
 nexthop_obj_blackhole_offload_test()
 {
 	# Test offload indication of blackhole nexthop objects
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index be71012b8fc5..05c05e02bade 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -353,6 +353,11 @@ wait_for_offload()
 	"$@" | grep -q offload
 }
 
+wait_for_trap()
+{
+	"$@" | grep -q trap
+}
+
 until_counter_is()
 {
 	local expr=$1; shift
-- 
cgit v1.2.3


From cff908463d91a6b2fb8c8ab6c41d9c308c29fd42 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@kernel.org>
Date: Mon, 22 Mar 2021 17:07:20 +0000
Subject: selftests/bpf: Better error messages for ima_setup.sh failures

The current implementation uses the CHECK_FAIL macro which does not
provide useful error messages when the script fails. Use the CHECK macro
instead and provide more descriptive messages to aid debugging.

Signed-off-by: KP Singh <kpsingh@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210322170720.2926715-1-kpsingh@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/test_ima.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
index b54bc0c351b7..0252f61d611a 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_ima.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -68,7 +68,8 @@ void test_test_ima(void)
 		goto close_prog;
 
 	snprintf(cmd, sizeof(cmd), "./ima_setup.sh setup %s", measured_dir);
-	if (CHECK_FAIL(system(cmd)))
+	err = system(cmd);
+	if (CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno))
 		goto close_clean;
 
 	err = run_measured_process(measured_dir, &skel->bss->monitored_pid);
@@ -81,7 +82,8 @@ void test_test_ima(void)
 
 close_clean:
 	snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir);
-	CHECK_FAIL(system(cmd));
+	err = system(cmd);
+	CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno);
 close_prog:
 	ima__destroy(skel);
 }
-- 
cgit v1.2.3


From e9bd8cbd970bedd3cca8ee334c76ab90feb78760 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Mon, 22 Mar 2021 23:50:54 -0300
Subject: bpf: selftests: Add tests for batched ops in LPM trie maps

Uses the already existing infrastructure for testing batched ops.
The testing code is essentially the same, with minor tweaks for this use
case.

Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210323025058.315763-3-pctammela@gmail.com
---
 .../bpf/map_tests/lpm_trie_map_batch_ops.c         | 158 +++++++++++++++++++++
 1 file changed, 158 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
new file mode 100644
index 000000000000..2e986e5e4cac
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <arpa/inet.h>
+#include <linux/bpf.h>
+#include <netinet/in.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+struct test_lpm_key {
+	__u32 prefix;
+	struct in_addr ipv4;
+};
+
+static void map_batch_update(int map_fd, __u32 max_entries,
+			     struct test_lpm_key *keys, int *values)
+{
+	__u32 i;
+	int err;
+	char buff[16] = { 0 };
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	for (i = 0; i < max_entries; i++) {
+		keys[i].prefix = 32;
+		snprintf(buff, 16, "192.168.1.%d", i + 1);
+		inet_pton(AF_INET, buff, &keys[i].ipv4);
+		values[i] = i + 1;
+	}
+
+	err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+	CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+			     struct test_lpm_key *keys, int *values)
+{
+	char buff[16] = { 0 };
+	int lower_byte = 0;
+	__u32 i;
+
+	memset(visited, 0, max_entries * sizeof(*visited));
+	for (i = 0; i < max_entries; i++) {
+		inet_ntop(AF_INET, &keys[i].ipv4, buff, 32);
+		CHECK(sscanf(buff, "192.168.1.%d", &lower_byte) == EOF,
+		      "sscanf()", "error: i %d\n", i);
+		CHECK(lower_byte != values[i], "key/value checking",
+		      "error: i %d key %s value %d\n", i, buff, values[i]);
+		visited[i] = 1;
+	}
+	for (i = 0; i < max_entries; i++) {
+		CHECK(visited[i] != 1, "visited checking",
+		      "error: keys array at index %d missing\n", i);
+	}
+}
+
+void test_lpm_trie_map_batch_ops(void)
+{
+	struct bpf_create_map_attr xattr = {
+		.name = "lpm_trie_map",
+		.map_type = BPF_MAP_TYPE_LPM_TRIE,
+		.key_size = sizeof(struct test_lpm_key),
+		.value_size = sizeof(int),
+		.map_flags = BPF_F_NO_PREALLOC,
+	};
+	struct test_lpm_key *keys, key;
+	int map_fd, *values, *visited;
+	__u32 step, count, total, total_success;
+	const __u32 max_entries = 10;
+	__u64 batch = 0;
+	int err;
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	xattr.max_entries = max_entries;
+	map_fd = bpf_create_map_xattr(&xattr);
+	CHECK(map_fd == -1, "bpf_create_map_xattr()", "error:%s\n",
+	      strerror(errno));
+
+	keys = malloc(max_entries * sizeof(struct test_lpm_key));
+	values = malloc(max_entries * sizeof(int));
+	visited = malloc(max_entries * sizeof(int));
+	CHECK(!keys || !values || !visited, "malloc()", "error:%s\n",
+	      strerror(errno));
+
+	total_success = 0;
+	for (step = 1; step < max_entries; step++) {
+		map_batch_update(map_fd, max_entries, keys, values);
+		map_batch_verify(visited, max_entries, keys, values);
+		memset(keys, 0, max_entries * sizeof(*keys));
+		memset(values, 0, max_entries * sizeof(*values));
+		batch = 0;
+		total = 0;
+		/* iteratively lookup/delete elements with 'step'
+		 * elements each.
+		 */
+		count = step;
+		while (true) {
+			err = bpf_map_lookup_batch(map_fd,
+				total ? &batch : NULL, &batch,
+				keys + total, values + total, &count, &opts);
+
+			CHECK((err && errno != ENOENT), "lookup with steps",
+			      "error: %s\n", strerror(errno));
+
+			total += count;
+			if (err)
+				break;
+		}
+
+		CHECK(total != max_entries, "lookup with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+
+		map_batch_verify(visited, max_entries, keys, values);
+
+		total = 0;
+		count = step;
+		while (total < max_entries) {
+			if (max_entries - total < step)
+				count = max_entries - total;
+			err = bpf_map_delete_batch(map_fd, keys + total, &count,
+						   &opts);
+			CHECK((err && errno != ENOENT), "delete batch",
+			      "error: %s\n", strerror(errno));
+			total += count;
+			if (err)
+				break;
+		}
+		CHECK(total != max_entries, "delete with steps",
+		      "total = %u, max_entries = %u\n", total, max_entries);
+
+		/* check map is empty, errono == ENOENT */
+		err = bpf_map_get_next_key(map_fd, NULL, &key);
+		CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
+		      "error: %s\n", strerror(errno));
+
+		total_success++;
+	}
+
+	CHECK(total_success == 0, "check total_success",
+	      "unexpected failure\n");
+
+	printf("%s:PASS\n", __func__);
+
+	free(keys);
+	free(values);
+	free(visited);
+}
-- 
cgit v1.2.3


From 2e580a63b5c214a89bcc3e243ee2058691cee001 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Fri, 26 Mar 2021 11:26:35 -0700
Subject: selftests: mptcp: add cfg_do_w for cfg_remove

In some testcases, we need to slow down the transmitting process. This
patch added a new argument named cfg_do_w for cfg_remove to allow the
caller to pass an argument to cfg_remove.

In do_rnd_write, use this cfg_do_w to control the transmitting speed.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 77bb62feb872..69d89b5d666f 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -55,6 +55,7 @@ static int cfg_sndbuf;
 static int cfg_rcvbuf;
 static bool cfg_join;
 static bool cfg_remove;
+static unsigned int cfg_do_w;
 static int cfg_wait;
 
 static void die_usage(void)
@@ -272,8 +273,8 @@ static size_t do_rnd_write(const int fd, char *buf, const size_t len)
 	if (cfg_join && first && do_w > 100)
 		do_w = 100;
 
-	if (cfg_remove && do_w > 50)
-		do_w = 50;
+	if (cfg_remove && do_w > cfg_do_w)
+		do_w = cfg_do_w;
 
 	bw = write(fd, buf, do_w);
 	if (bw < 0)
@@ -829,7 +830,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jrlp:s:hut:m:S:R:w:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -840,6 +841,9 @@ static void parse_opts(int argc, char **argv)
 			cfg_remove = true;
 			cfg_mode = CFG_MODE_POLL;
 			cfg_wait = 400000;
+			cfg_do_w = atoi(optarg);
+			if (cfg_do_w <= 0)
+				cfg_do_w = 50;
 			break;
 		case 'l':
 			listen_mode = true;
-- 
cgit v1.2.3


From 8da6229b9524d9a4ea91ed1308f7e45bfe0b2799 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Fri, 26 Mar 2021 11:26:36 -0700
Subject: selftests: mptcp: timeout testcases for multi addresses

This patch added the timeout testcases for multi addresses, valid and
invalid.

These testcases need to transmit 8 ADD_ADDRs, so add a new speed level
'least' to set 10 to mptcp_connect to slow down the transmitting process.
The original speed level 'slow' still uses 50.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 26 +++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index fe990d8696a9..32379efa2276 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -234,8 +234,10 @@ do_transfer()
 
 	if [ $speed = "fast" ]; then
 		mptcp_connect="./mptcp_connect -j"
-	else
-		mptcp_connect="./mptcp_connect -r"
+	elif [ $speed = "slow" ]; then
+		mptcp_connect="./mptcp_connect -r 50"
+	elif [ $speed = "least" ]; then
+		mptcp_connect="./mptcp_connect -r 10"
 	fi
 
 	local local_addr
@@ -818,6 +820,26 @@ add_addr_timeout_tests()
 	run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
 	chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1
 	chk_add_nr 4 0
+
+	# signal addresses timeout
+	reset_with_add_addr_timeout
+	ip netns exec $ns1 ./pm_nl_ctl limits 2 2
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 2 2
+	run_tests $ns1 $ns2 10.0.1.1 0 0 0 least
+	chk_join_nr "signal addresses, ADD_ADDR timeout" 2 2 2
+	chk_add_nr 8 0
+
+	# signal invalid addresses timeout
+	reset_with_add_addr_timeout
+	ip netns exec $ns1 ./pm_nl_ctl limits 2 2
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 2 2
+	run_tests $ns1 $ns2 10.0.1.1 0 0 0 least
+	chk_join_nr "invalid address, ADD_ADDR timeout" 1 1 1
+	chk_add_nr 8 0
 }
 
 remove_tests()
-- 
cgit v1.2.3


From ef360019db4043d53d631aec1e630bd6e6ce54f4 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Fri, 26 Mar 2021 11:26:42 -0700
Subject: selftests: mptcp: signal addresses testcases

This patch adds testcases for signalling multi valid and invalid
addresses for both signal_address_tests and remove_tests.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 58 +++++++++++++++++++++++++
 1 file changed, 58 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 32379efa2276..679de3abaf34 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -785,6 +785,28 @@ signal_address_tests()
 	run_tests $ns1 $ns2 10.0.1.1
 	chk_join_nr "multiple subflows and signal" 3 3 3
 	chk_add_nr 1 1
+
+	# signal addresses
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_join_nr "signal addresses" 3 3 3
+	chk_add_nr 3 3
+
+	# signal invalid addresses
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_join_nr "signal invalid addresses" 1 1 1
+	chk_add_nr 3 3
 }
 
 link_failure_tests()
@@ -896,6 +918,30 @@ remove_tests()
 	chk_add_nr 1 1
 	chk_rm_nr 2 2
 
+	# addresses remove
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+	run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow
+	chk_join_nr "remove addresses" 3 3 3
+	chk_add_nr 3 3
+	chk_rm_nr 3 3 invert
+
+	# invalid addresses remove
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+	run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow
+	chk_join_nr "remove invalid addresses" 1 1 1
+	chk_add_nr 3 3
+	chk_rm_nr 3 1 invert
+
 	# subflows and signal, flush
 	reset
 	ip netns exec $ns1 ./pm_nl_ctl limits 0 3
@@ -930,6 +976,18 @@ remove_tests()
 	chk_join_nr "flush addresses" 3 3 3
 	chk_add_nr 3 3
 	chk_rm_nr 3 3 invert
+
+	# invalid addresses flush
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 3 3
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 3 3
+	run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow
+	chk_join_nr "flush invalid addresses" 1 1 1
+	chk_add_nr 3 3
+	chk_rm_nr 3 1 invert
 }
 
 add_tests()
-- 
cgit v1.2.3


From e6ac2450d6dee3121cd8bbf2907b78a68a8a353d Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:51:42 -0700
Subject: bpf: Support bpf program calling kernel function

This patch adds support to BPF verifier to allow bpf program calling
kernel function directly.

The use case included in this set is to allow bpf-tcp-cc to directly
call some tcp-cc helper functions (e.g. "tcp_cong_avoid_ai()").  Those
functions have already been used by some kernel tcp-cc implementations.

This set will also allow the bpf-tcp-cc program to directly call the
kernel tcp-cc implementation,  For example, a bpf_dctcp may only want to
implement its own dctcp_cwnd_event() and reuse other dctcp_*() directly
from the kernel tcp_dctcp.c instead of reimplementing (or
copy-and-pasting) them.

The tcp-cc kernel functions mentioned above will be white listed
for the struct_ops bpf-tcp-cc programs to use in a later patch.
The white listed functions are not bounded to a fixed ABI contract.
Those functions have already been used by the existing kernel tcp-cc.
If any of them has changed, both in-tree and out-of-tree kernel tcp-cc
implementations have to be changed.  The same goes for the struct_ops
bpf-tcp-cc programs which have to be adjusted accordingly.

This patch is to make the required changes in the bpf verifier.

First change is in btf.c, it adds a case in "btf_check_func_arg_match()".
When the passed in "btf->kernel_btf == true", it means matching the
verifier regs' states with a kernel function.  This will handle the
PTR_TO_BTF_ID reg.  It also maps PTR_TO_SOCK_COMMON, PTR_TO_SOCKET,
and PTR_TO_TCP_SOCK to its kernel's btf_id.

In the later libbpf patch, the insn calling a kernel function will
look like:

insn->code == (BPF_JMP | BPF_CALL)
insn->src_reg == BPF_PSEUDO_KFUNC_CALL /* <- new in this patch */
insn->imm == func_btf_id /* btf_id of the running kernel */

[ For the future calling function-in-kernel-module support, an array
  of module btf_fds can be passed at the load time and insn->off
  can be used to index into this array. ]

At the early stage of verifier, the verifier will collect all kernel
function calls into "struct bpf_kfunc_desc".  Those
descriptors are stored in "prog->aux->kfunc_tab" and will
be available to the JIT.  Since this "add" operation is similar
to the current "add_subprog()" and looking for the same insn->code,
they are done together in the new "add_subprog_and_kfunc()".

In the "do_check()" stage, the new "check_kfunc_call()" is added
to verify the kernel function call instruction:
1. Ensure the kernel function can be used by a particular BPF_PROG_TYPE.
   A new bpf_verifier_ops "check_kfunc_call" is added to do that.
   The bpf-tcp-cc struct_ops program will implement this function in
   a later patch.
2. Call "btf_check_kfunc_args_match()" to ensure the regs can be
   used as the args of a kernel function.
3. Mark the regs' type, subreg_def, and zext_dst.

At the later do_misc_fixups() stage, the new fixup_kfunc_call()
will replace the insn->imm with the function address (relative
to __bpf_call_base).  If needed, the jit can find the btf_func_model
by calling the new bpf_jit_find_kfunc_model(prog, insn).
With the imm set to the function address, "bpftool prog dump xlated"
will be able to display the kernel function calls the same way as
it displays other bpf helper calls.

gpl_compatible program is required to call kernel function.

This feature currently requires JIT.

The verifier selftests are adjusted because of the changes in
the verbose log in add_subprog_and_kfunc().

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015142.1544736-1-kafai@fb.com
---
 arch/x86/net/bpf_jit_comp.c                      |   5 +
 include/linux/bpf.h                              |  24 ++
 include/linux/btf.h                              |   1 +
 include/linux/filter.h                           |   1 +
 include/uapi/linux/bpf.h                         |   4 +
 kernel/bpf/btf.c                                 |  65 +++-
 kernel/bpf/core.c                                |  18 +-
 kernel/bpf/disasm.c                              |  13 +-
 kernel/bpf/syscall.c                             |   1 +
 kernel/bpf/verifier.c                            | 368 +++++++++++++++++++++--
 tools/include/uapi/linux/bpf.h                   |   4 +
 tools/testing/selftests/bpf/verifier/calls.c     |  12 +-
 tools/testing/selftests/bpf/verifier/dead_code.c |  10 +-
 13 files changed, 480 insertions(+), 46 deletions(-)

(limited to 'tools/testing')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b35fc8023884..9eead60f0301 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2346,3 +2346,8 @@ out:
 					   tmp : orig_prog);
 	return prog;
 }
+
+bool bpf_jit_supports_kfunc_call(void)
+{
+	return true;
+}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eaae618a90b5..b5b7967e3ff3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -427,6 +427,7 @@ enum bpf_reg_type {
 	PTR_TO_PERCPU_BTF_ID,	 /* reg points to a percpu kernel variable */
 	PTR_TO_FUNC,		 /* reg points to a bpf program function */
 	PTR_TO_MAP_KEY,		 /* reg points to a map element key */
+	__BPF_REG_TYPE_MAX,
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -480,6 +481,7 @@ struct bpf_verifier_ops {
 				 const struct btf_type *t, int off, int size,
 				 enum bpf_access_type atype,
 				 u32 *next_btf_id);
+	bool (*check_kfunc_call)(u32 kfunc_btf_id);
 };
 
 struct bpf_prog_offload_ops {
@@ -796,6 +798,8 @@ struct btf_mod_pair {
 	struct module *module;
 };
 
+struct bpf_kfunc_desc_tab;
+
 struct bpf_prog_aux {
 	atomic64_t refcnt;
 	u32 used_map_cnt;
@@ -832,6 +836,7 @@ struct bpf_prog_aux {
 	struct bpf_prog **func;
 	void *jit_data; /* JIT specific data. arch dependent */
 	struct bpf_jit_poke_descriptor *poke_tab;
+	struct bpf_kfunc_desc_tab *kfunc_tab;
 	u32 size_poke_tab;
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
@@ -1547,6 +1552,9 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 struct bpf_reg_state;
 int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
 				struct bpf_reg_state *regs);
+int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
+			      const struct btf *btf, u32 func_id,
+			      struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			  struct bpf_reg_state *reg);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
@@ -1557,6 +1565,10 @@ struct bpf_link *bpf_link_by_id(u32 id);
 
 const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
 void bpf_task_storage_free(struct task_struct *task);
+bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
+const struct btf_func_model *
+bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
+			 const struct bpf_insn *insn);
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -1737,6 +1749,18 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 static inline void bpf_task_storage_free(struct task_struct *task)
 {
 }
+
+static inline bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog)
+{
+	return false;
+}
+
+static inline const struct btf_func_model *
+bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
+			 const struct bpf_insn *insn)
+{
+	return NULL;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 8a05687a4ee2..3bac66e0183a 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -110,6 +110,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
 const struct btf_type *
 btf_resolve_size(const struct btf *btf, const struct btf_type *type,
 		 u32 *type_size);
+const char *btf_type_str(const struct btf_type *t);
 
 #define for_each_member(i, struct_type, member)			\
 	for (i = 0, member = btf_type_member(struct_type);	\
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0d9c710eb050..eecfd82db648 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -918,6 +918,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
 void bpf_jit_compile(struct bpf_prog *prog);
 bool bpf_jit_needs_zext(void);
+bool bpf_jit_supports_kfunc_call(void);
 bool bpf_helper_changes_pkt_data(void *func);
 
 static inline bool bpf_dump_raw_ok(const struct cred *cred)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 008edc1dc8c1..598716742593 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1117,6 +1117,10 @@ enum bpf_link_type {
  * offset to another bpf function
  */
 #define BPF_PSEUDO_CALL		1
+/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL,
+ * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel
+ */
+#define BPF_PSEUDO_KFUNC_CALL	2
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
 enum {
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3c489adacf3b..ec8afc4bc560 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -283,7 +283,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_FLOAT]	= "FLOAT",
 };
 
-static const char *btf_type_str(const struct btf_type *t)
+const char *btf_type_str(const struct btf_type *t)
 {
 	return btf_kind_str[BTF_INFO_KIND(t->info)];
 }
@@ -5362,6 +5362,14 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr
 	return btf_check_func_type_match(log, btf1, t1, btf2, t2);
 }
 
+static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
+#ifdef CONFIG_NET
+	[PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
+	[PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	[PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
+#endif
+};
+
 static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 				    const struct btf *btf, u32 func_id,
 				    struct bpf_reg_state *regs,
@@ -5371,12 +5379,12 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 	const char *func_name, *ref_tname;
 	const struct btf_type *t, *ref_t;
 	const struct btf_param *args;
-	u32 i, nargs;
+	u32 i, nargs, ref_id;
 
 	t = btf_type_by_id(btf, func_id);
 	if (!t || !btf_type_is_func(t)) {
 		/* These checks were already done by the verifier while loading
-		 * struct bpf_func_info
+		 * struct bpf_func_info or in add_kfunc_call().
 		 */
 		bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n",
 			func_id);
@@ -5418,9 +5426,49 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			return -EINVAL;
 		}
 
-		ref_t = btf_type_skip_modifiers(btf, t->type, NULL);
+		ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
 		ref_tname = btf_name_by_offset(btf, ref_t->name_off);
-		if (btf_get_prog_ctx_type(log, btf, t, env->prog->type, i)) {
+		if (btf_is_kernel(btf)) {
+			const struct btf_type *reg_ref_t;
+			const struct btf *reg_btf;
+			const char *reg_ref_tname;
+			u32 reg_ref_id;
+
+			if (!btf_type_is_struct(ref_t)) {
+				bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n",
+					func_name, i, btf_type_str(ref_t),
+					ref_tname);
+				return -EINVAL;
+			}
+
+			if (reg->type == PTR_TO_BTF_ID) {
+				reg_btf = reg->btf;
+				reg_ref_id = reg->btf_id;
+			} else if (reg2btf_ids[reg->type]) {
+				reg_btf = btf_vmlinux;
+				reg_ref_id = *reg2btf_ids[reg->type];
+			} else {
+				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d is not a pointer to btf_id\n",
+					func_name, i,
+					btf_type_str(ref_t), ref_tname, regno);
+				return -EINVAL;
+			}
+
+			reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id,
+							    &reg_ref_id);
+			reg_ref_tname = btf_name_by_offset(reg_btf,
+							   reg_ref_t->name_off);
+			if (!btf_struct_ids_match(log, reg_btf, reg_ref_id,
+						  reg->off, btf, ref_id)) {
+				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n",
+					func_name, i,
+					btf_type_str(ref_t), ref_tname,
+					regno, btf_type_str(reg_ref_t),
+					reg_ref_tname);
+				return -EINVAL;
+			}
+		} else if (btf_get_prog_ctx_type(log, btf, t,
+						 env->prog->type, i)) {
 			/* If function expects ctx type in BTF check that caller
 			 * is passing PTR_TO_CTX.
 			 */
@@ -5493,6 +5541,13 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
 	return err;
 }
 
+int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
+			      const struct btf *btf, u32 func_id,
+			      struct bpf_reg_state *regs)
+{
+	return btf_check_func_arg_match(env, btf, func_id, regs, false);
+}
+
 /* Convert BTF of a function into bpf_reg_state if possible
  * Returns:
  * EFAULT - there is a verifier bug. Abort verification.
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a35eb3d7b126..f5423251c118 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -159,6 +159,9 @@ void bpf_prog_jit_attempt_done(struct bpf_prog *prog)
 		kvfree(prog->aux->jited_linfo);
 		prog->aux->jited_linfo = NULL;
 	}
+
+	kfree(prog->aux->kfunc_tab);
+	prog->aux->kfunc_tab = NULL;
 }
 
 /* The jit engine is responsible to provide an array
@@ -1840,9 +1843,15 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	/* In case of BPF to BPF calls, verifier did all the prep
 	 * work with regards to JITing, etc.
 	 */
+	bool jit_needed = false;
+
 	if (fp->bpf_func)
 		goto finalize;
 
+	if (IS_ENABLED(CONFIG_BPF_JIT_ALWAYS_ON) ||
+	    bpf_prog_has_kfunc_call(fp))
+		jit_needed = true;
+
 	bpf_prog_select_func(fp);
 
 	/* eBPF JITs can rewrite the program in case constant
@@ -1858,12 +1867,10 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 
 		fp = bpf_int_jit_compile(fp);
 		bpf_prog_jit_attempt_done(fp);
-#ifdef CONFIG_BPF_JIT_ALWAYS_ON
-		if (!fp->jited) {
+		if (!fp->jited && jit_needed) {
 			*err = -ENOTSUPP;
 			return fp;
 		}
-#endif
 	} else {
 		*err = bpf_prog_offload_compile(fp);
 		if (*err)
@@ -2343,6 +2350,11 @@ bool __weak bpf_jit_needs_zext(void)
 	return false;
 }
 
+bool __weak bpf_jit_supports_kfunc_call(void)
+{
+	return false;
+}
+
 /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
  * skb_copy_bits(), so provide a weak definition of it for NET-less config.
  */
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 3acc7e0b6916..dad821c8ecd0 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -19,16 +19,23 @@ static const char *__func_get_name(const struct bpf_insn_cbs *cbs,
 {
 	BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
 
-	if (insn->src_reg != BPF_PSEUDO_CALL &&
+	if (!insn->src_reg &&
 	    insn->imm >= 0 && insn->imm < __BPF_FUNC_MAX_ID &&
 	    func_id_str[insn->imm])
 		return func_id_str[insn->imm];
 
-	if (cbs && cbs->cb_call)
-		return cbs->cb_call(cbs->private_data, insn);
+	if (cbs && cbs->cb_call) {
+		const char *res;
+
+		res = cbs->cb_call(cbs->private_data, insn);
+		if (res)
+			return res;
+	}
 
 	if (insn->src_reg == BPF_PSEUDO_CALL)
 		snprintf(buff, len, "%+d", insn->imm);
+	else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
+		snprintf(buff, len, "kernel-function");
 
 	return buff;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index eaf85bf51c5a..9603de81811a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1696,6 +1696,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
 	btf_put(prog->aux->btf);
 	kvfree(prog->aux->jited_linfo);
 	kvfree(prog->aux->linfo);
+	kfree(prog->aux->kfunc_tab);
 	if (prog->aux->attach_btf)
 		btf_put(prog->aux->attach_btf);
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b31e62daafbd..852541a435ef 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -234,6 +234,12 @@ static bool bpf_pseudo_call(const struct bpf_insn *insn)
 	       insn->src_reg == BPF_PSEUDO_CALL;
 }
 
+static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_JMP | BPF_CALL) &&
+	       insn->src_reg == BPF_PSEUDO_KFUNC_CALL;
+}
+
 static bool bpf_pseudo_func(const struct bpf_insn *insn)
 {
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
@@ -1554,47 +1560,205 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
 		verbose(env, "too many subprograms\n");
 		return -E2BIG;
 	}
+	/* determine subprog starts. The end is one before the next starts */
 	env->subprog_info[env->subprog_cnt++].start = off;
 	sort(env->subprog_info, env->subprog_cnt,
 	     sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
 	return env->subprog_cnt - 1;
 }
 
-static int check_subprogs(struct bpf_verifier_env *env)
+struct bpf_kfunc_desc {
+	struct btf_func_model func_model;
+	u32 func_id;
+	s32 imm;
+};
+
+#define MAX_KFUNC_DESCS 256
+struct bpf_kfunc_desc_tab {
+	struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS];
+	u32 nr_descs;
+};
+
+static int kfunc_desc_cmp_by_id(const void *a, const void *b)
+{
+	const struct bpf_kfunc_desc *d0 = a;
+	const struct bpf_kfunc_desc *d1 = b;
+
+	/* func_id is not greater than BTF_MAX_TYPE */
+	return d0->func_id - d1->func_id;
+}
+
+static const struct bpf_kfunc_desc *
+find_kfunc_desc(const struct bpf_prog *prog, u32 func_id)
+{
+	struct bpf_kfunc_desc desc = {
+		.func_id = func_id,
+	};
+	struct bpf_kfunc_desc_tab *tab;
+
+	tab = prog->aux->kfunc_tab;
+	return bsearch(&desc, tab->descs, tab->nr_descs,
+		       sizeof(tab->descs[0]), kfunc_desc_cmp_by_id);
+}
+
+static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
+{
+	const struct btf_type *func, *func_proto;
+	struct bpf_kfunc_desc_tab *tab;
+	struct bpf_prog_aux *prog_aux;
+	struct bpf_kfunc_desc *desc;
+	const char *func_name;
+	unsigned long addr;
+	int err;
+
+	prog_aux = env->prog->aux;
+	tab = prog_aux->kfunc_tab;
+	if (!tab) {
+		if (!btf_vmlinux) {
+			verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n");
+			return -ENOTSUPP;
+		}
+
+		if (!env->prog->jit_requested) {
+			verbose(env, "JIT is required for calling kernel function\n");
+			return -ENOTSUPP;
+		}
+
+		if (!bpf_jit_supports_kfunc_call()) {
+			verbose(env, "JIT does not support calling kernel function\n");
+			return -ENOTSUPP;
+		}
+
+		if (!env->prog->gpl_compatible) {
+			verbose(env, "cannot call kernel function from non-GPL compatible program\n");
+			return -EINVAL;
+		}
+
+		tab = kzalloc(sizeof(*tab), GFP_KERNEL);
+		if (!tab)
+			return -ENOMEM;
+		prog_aux->kfunc_tab = tab;
+	}
+
+	if (find_kfunc_desc(env->prog, func_id))
+		return 0;
+
+	if (tab->nr_descs == MAX_KFUNC_DESCS) {
+		verbose(env, "too many different kernel function calls\n");
+		return -E2BIG;
+	}
+
+	func = btf_type_by_id(btf_vmlinux, func_id);
+	if (!func || !btf_type_is_func(func)) {
+		verbose(env, "kernel btf_id %u is not a function\n",
+			func_id);
+		return -EINVAL;
+	}
+	func_proto = btf_type_by_id(btf_vmlinux, func->type);
+	if (!func_proto || !btf_type_is_func_proto(func_proto)) {
+		verbose(env, "kernel function btf_id %u does not have a valid func_proto\n",
+			func_id);
+		return -EINVAL;
+	}
+
+	func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
+	addr = kallsyms_lookup_name(func_name);
+	if (!addr) {
+		verbose(env, "cannot find address for kernel function %s\n",
+			func_name);
+		return -EINVAL;
+	}
+
+	desc = &tab->descs[tab->nr_descs++];
+	desc->func_id = func_id;
+	desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base;
+	err = btf_distill_func_proto(&env->log, btf_vmlinux,
+				     func_proto, func_name,
+				     &desc->func_model);
+	if (!err)
+		sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
+		     kfunc_desc_cmp_by_id, NULL);
+	return err;
+}
+
+static int kfunc_desc_cmp_by_imm(const void *a, const void *b)
+{
+	const struct bpf_kfunc_desc *d0 = a;
+	const struct bpf_kfunc_desc *d1 = b;
+
+	if (d0->imm > d1->imm)
+		return 1;
+	else if (d0->imm < d1->imm)
+		return -1;
+	return 0;
+}
+
+static void sort_kfunc_descs_by_imm(struct bpf_prog *prog)
+{
+	struct bpf_kfunc_desc_tab *tab;
+
+	tab = prog->aux->kfunc_tab;
+	if (!tab)
+		return;
+
+	sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
+	     kfunc_desc_cmp_by_imm, NULL);
+}
+
+bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog)
+{
+	return !!prog->aux->kfunc_tab;
+}
+
+const struct btf_func_model *
+bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
+			 const struct bpf_insn *insn)
+{
+	const struct bpf_kfunc_desc desc = {
+		.imm = insn->imm,
+	};
+	const struct bpf_kfunc_desc *res;
+	struct bpf_kfunc_desc_tab *tab;
+
+	tab = prog->aux->kfunc_tab;
+	res = bsearch(&desc, tab->descs, tab->nr_descs,
+		      sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm);
+
+	return res ? &res->func_model : NULL;
+}
+
+static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 {
-	int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
-	int insn_cnt = env->prog->len;
+	int i, ret, insn_cnt = env->prog->len;
 
 	/* Add entry function. */
 	ret = add_subprog(env, 0);
-	if (ret < 0)
+	if (ret)
 		return ret;
 
-	/* determine subprog starts. The end is one before the next starts */
-	for (i = 0; i < insn_cnt; i++) {
-		if (bpf_pseudo_func(insn + i)) {
-			if (!env->bpf_capable) {
-				verbose(env,
-					"function pointers are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
-				return -EPERM;
-			}
-			ret = add_subprog(env, i + insn[i].imm + 1);
-			if (ret < 0)
-				return ret;
-			/* remember subprog */
-			insn[i + 1].imm = ret;
-			continue;
-		}
-		if (!bpf_pseudo_call(insn + i))
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn) &&
+		    !bpf_pseudo_kfunc_call(insn))
 			continue;
+
 		if (!env->bpf_capable) {
-			verbose(env,
-				"function calls to other bpf functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
+			verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
 			return -EPERM;
 		}
-		ret = add_subprog(env, i + insn[i].imm + 1);
+
+		if (bpf_pseudo_func(insn)) {
+			ret = add_subprog(env, i + insn->imm + 1);
+			if (ret >= 0)
+				/* remember subprog */
+				insn[1].imm = ret;
+		} else if (bpf_pseudo_call(insn)) {
+			ret = add_subprog(env, i + insn->imm + 1);
+		} else {
+			ret = add_kfunc_call(env, insn->imm);
+		}
+
 		if (ret < 0)
 			return ret;
 	}
@@ -1608,6 +1772,16 @@ static int check_subprogs(struct bpf_verifier_env *env)
 		for (i = 0; i < env->subprog_cnt; i++)
 			verbose(env, "func#%d @%d\n", i, subprog[i].start);
 
+	return 0;
+}
+
+static int check_subprogs(struct bpf_verifier_env *env)
+{
+	int i, subprog_start, subprog_end, off, cur_subprog = 0;
+	struct bpf_subprog_info *subprog = env->subprog_info;
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+
 	/* now check that all jumps are within the same subprog */
 	subprog_start = subprog[cur_subprog].start;
 	subprog_end = subprog[cur_subprog + 1].start;
@@ -1916,6 +2090,17 @@ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
 	return i;
 }
 
+static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
+{
+	const struct btf_type *func;
+
+	if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL)
+		return NULL;
+
+	func = btf_type_by_id(btf_vmlinux, insn->imm);
+	return btf_name_by_offset(btf_vmlinux, func->name_off);
+}
+
 /* For given verifier state backtrack_insn() is called from the last insn to
  * the first insn. Its purpose is to compute a bitmask of registers and
  * stack slots that needs precision in the parent verifier state.
@@ -1924,6 +2109,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			  u32 *reg_mask, u64 *stack_mask)
 {
 	const struct bpf_insn_cbs cbs = {
+		.cb_call	= disasm_kfunc_name,
 		.cb_print	= verbose,
 		.private_data	= env,
 	};
@@ -5960,6 +6146,98 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	return 0;
 }
 
+/* mark_btf_func_reg_size() is used when the reg size is determined by
+ * the BTF func_proto's return value size and argument.
+ */
+static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno,
+				   size_t reg_size)
+{
+	struct bpf_reg_state *reg = &cur_regs(env)[regno];
+
+	if (regno == BPF_REG_0) {
+		/* Function return value */
+		reg->live |= REG_LIVE_WRITTEN;
+		reg->subreg_def = reg_size == sizeof(u64) ?
+			DEF_NOT_SUBREG : env->insn_idx + 1;
+	} else {
+		/* Function argument */
+		if (reg_size == sizeof(u64)) {
+			mark_insn_zext(env, reg);
+			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+		} else {
+			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ32);
+		}
+	}
+}
+
+static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
+{
+	const struct btf_type *t, *func, *func_proto, *ptr_type;
+	struct bpf_reg_state *regs = cur_regs(env);
+	const char *func_name, *ptr_type_name;
+	u32 i, nargs, func_id, ptr_type_id;
+	const struct btf_param *args;
+	int err;
+
+	func_id = insn->imm;
+	func = btf_type_by_id(btf_vmlinux, func_id);
+	func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
+	func_proto = btf_type_by_id(btf_vmlinux, func->type);
+
+	if (!env->ops->check_kfunc_call ||
+	    !env->ops->check_kfunc_call(func_id)) {
+		verbose(env, "calling kernel function %s is not allowed\n",
+			func_name);
+		return -EACCES;
+	}
+
+	/* Check the arguments */
+	err = btf_check_kfunc_arg_match(env, btf_vmlinux, func_id, regs);
+	if (err)
+		return err;
+
+	for (i = 0; i < CALLER_SAVED_REGS; i++)
+		mark_reg_not_init(env, regs, caller_saved[i]);
+
+	/* Check return type */
+	t = btf_type_skip_modifiers(btf_vmlinux, func_proto->type, NULL);
+	if (btf_type_is_scalar(t)) {
+		mark_reg_unknown(env, regs, BPF_REG_0);
+		mark_btf_func_reg_size(env, BPF_REG_0, t->size);
+	} else if (btf_type_is_ptr(t)) {
+		ptr_type = btf_type_skip_modifiers(btf_vmlinux, t->type,
+						   &ptr_type_id);
+		if (!btf_type_is_struct(ptr_type)) {
+			ptr_type_name = btf_name_by_offset(btf_vmlinux,
+							   ptr_type->name_off);
+			verbose(env, "kernel function %s returns pointer type %s %s is not supported\n",
+				func_name, btf_type_str(ptr_type),
+				ptr_type_name);
+			return -EINVAL;
+		}
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].btf = btf_vmlinux;
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID;
+		regs[BPF_REG_0].btf_id = ptr_type_id;
+		mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *));
+	} /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */
+
+	nargs = btf_type_vlen(func_proto);
+	args = (const struct btf_param *)(func_proto + 1);
+	for (i = 0; i < nargs; i++) {
+		u32 regno = i + 1;
+
+		t = btf_type_skip_modifiers(btf_vmlinux, args[i].type, NULL);
+		if (btf_type_is_ptr(t))
+			mark_btf_func_reg_size(env, regno, sizeof(void *));
+		else
+			/* scalar. ensured by btf_check_kfunc_arg_match() */
+			mark_btf_func_reg_size(env, regno, t->size);
+	}
+
+	return 0;
+}
+
 static bool signed_add_overflows(s64 a, s64 b)
 {
 	/* Do the add in u64, where overflow is well-defined */
@@ -10162,6 +10440,7 @@ static int do_check(struct bpf_verifier_env *env)
 
 		if (env->log.level & BPF_LOG_LEVEL) {
 			const struct bpf_insn_cbs cbs = {
+				.cb_call	= disasm_kfunc_name,
 				.cb_print	= verbose,
 				.private_data	= env,
 			};
@@ -10309,7 +10588,8 @@ static int do_check(struct bpf_verifier_env *env)
 				if (BPF_SRC(insn->code) != BPF_K ||
 				    insn->off != 0 ||
 				    (insn->src_reg != BPF_REG_0 &&
-				     insn->src_reg != BPF_PSEUDO_CALL) ||
+				     insn->src_reg != BPF_PSEUDO_CALL &&
+				     insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
 				    insn->dst_reg != BPF_REG_0 ||
 				    class == BPF_JMP32) {
 					verbose(env, "BPF_CALL uses reserved fields\n");
@@ -10324,6 +10604,8 @@ static int do_check(struct bpf_verifier_env *env)
 				}
 				if (insn->src_reg == BPF_PSEUDO_CALL)
 					err = check_func_call(env, insn, &env->insn_idx);
+				else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
+					err = check_kfunc_call(env, insn);
 				else
 					err = check_helper_call(env, insn, &env->insn_idx);
 				if (err)
@@ -11634,6 +11916,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->name[0] = 'F';
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
+		func[i]->aux->kfunc_tab = prog->aux->kfunc_tab;
 		func[i]->aux->linfo = prog->aux->linfo;
 		func[i]->aux->nr_linfo = prog->aux->nr_linfo;
 		func[i]->aux->jited_linfo = prog->aux->jited_linfo;
@@ -11773,6 +12056,7 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	struct bpf_prog *prog = env->prog;
 	struct bpf_insn *insn = prog->insnsi;
+	bool has_kfunc_call = bpf_prog_has_kfunc_call(prog);
 	int i, depth;
 #endif
 	int err = 0;
@@ -11786,6 +12070,10 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 			return err;
 	}
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+	if (has_kfunc_call) {
+		verbose(env, "calling kernel functions are not allowed in non-JITed programs\n");
+		return -EINVAL;
+	}
 	if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) {
 		/* When JIT fails the progs with bpf2bpf calls and tail_calls
 		 * have to be rejected, since interpreter doesn't support them yet.
@@ -11814,6 +12102,26 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 	return err;
 }
 
+static int fixup_kfunc_call(struct bpf_verifier_env *env,
+			    struct bpf_insn *insn)
+{
+	const struct bpf_kfunc_desc *desc;
+
+	/* insn->imm has the btf func_id. Replace it with
+	 * an address (relative to __bpf_base_call).
+	 */
+	desc = find_kfunc_desc(env->prog, insn->imm);
+	if (!desc) {
+		verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n",
+			insn->imm);
+		return -EFAULT;
+	}
+
+	insn->imm = desc->imm;
+
+	return 0;
+}
+
 /* Do various post-verification rewrites in a single program pass.
  * These rewrites simplify JIT and interpreter implementations.
  */
@@ -11949,6 +12257,12 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			continue;
 		if (insn->src_reg == BPF_PSEUDO_CALL)
 			continue;
+		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
+			ret = fixup_kfunc_call(env, insn);
+			if (ret)
+				return ret;
+			continue;
+		}
 
 		if (insn->imm == BPF_FUNC_get_route_realm)
 			prog->dst_needed = 1;
@@ -12178,6 +12492,8 @@ patch_call_imm:
 		}
 	}
 
+	sort_kfunc_descs_by_imm(env->prog);
+
 	return 0;
 }
 
@@ -12883,6 +13199,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (!env->explored_states)
 		goto skip_full_check;
 
+	ret = add_subprog_and_kfunc(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = check_subprogs(env);
 	if (ret < 0)
 		goto skip_full_check;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2d3036e292a9..ab9f2233607c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1117,6 +1117,10 @@ enum bpf_link_type {
  * offset to another bpf function
  */
 #define BPF_PSEUDO_CALL		1
+/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL,
+ * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel
+ */
+#define BPF_PSEUDO_KFUNC_CALL	2
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
 enum {
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index eb888c8479c3..336a749673d1 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -19,7 +19,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 2),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 1,
@@ -136,7 +136,7 @@
 {
 	"calls: wrong src reg",
 	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 2, 0, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 3, 0, 0),
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
@@ -397,7 +397,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.fixup_map_hash_48b = { 3 },
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
@@ -1977,7 +1977,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
@@ -2003,7 +2003,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
@@ -2028,7 +2028,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 5cf361d8eb1c..17fe33a75034 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -85,7 +85,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 12),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -103,7 +103,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 12),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -121,7 +121,7 @@
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -137,7 +137,7 @@
 	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
@@ -152,7 +152,7 @@
 	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for",
+	.errstr_unpriv = "loading/calling other bpf or kernel functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
-- 
cgit v1.2.3


From 39cd9e0f6783fd2dd2b0e95500e34575b3707ed8 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:52:40 -0700
Subject: bpf: selftests: Rename bictcp to bpf_cubic

As a similar chanage in the kernel, this patch gives the proper
name to the bpf cubic.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015240.1550074-1-kafai@fb.com
---
 tools/testing/selftests/bpf/progs/bpf_cubic.c | 30 +++++++++++++--------------
 1 file changed, 15 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index 6939bfd8690f..33c4d2bded64 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -174,8 +174,8 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk)
  * as long as it is used in one of the func ptr
  * under SEC(".struct_ops").
  */
-SEC("struct_ops/bictcp_init")
-void BPF_PROG(bictcp_init, struct sock *sk)
+SEC("struct_ops/bpf_cubic_init")
+void BPF_PROG(bpf_cubic_init, struct sock *sk)
 {
 	struct bictcp *ca = inet_csk_ca(sk);
 
@@ -192,7 +192,7 @@ void BPF_PROG(bictcp_init, struct sock *sk)
  * The remaining tcp-cubic functions have an easier way.
  */
 SEC("no-sec-prefix-bictcp_cwnd_event")
-void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event)
 {
 	if (event == CA_EVENT_TX_START) {
 		struct bictcp *ca = inet_csk_ca(sk);
@@ -384,7 +384,7 @@ tcp_friendliness:
 }
 
 /* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
-void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -403,7 +403,7 @@ void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
 	tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
-__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
+__u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -420,7 +420,7 @@ __u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
 	return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
 }
 
-void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state)
+void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state)
 {
 	if (new_state == TCP_CA_Loss) {
 		bictcp_reset(inet_csk_ca(sk));
@@ -496,7 +496,7 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay)
 	}
 }
 
-void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
+void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
 		    const struct ack_sample *sample)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -525,7 +525,7 @@ void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
 		hystart_update(sk, delay);
 }
 
-__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
+__u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
@@ -534,12 +534,12 @@ __u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
 
 SEC(".struct_ops")
 struct tcp_congestion_ops cubic = {
-	.init		= (void *)bictcp_init,
-	.ssthresh	= (void *)bictcp_recalc_ssthresh,
-	.cong_avoid	= (void *)bictcp_cong_avoid,
-	.set_state	= (void *)bictcp_state,
-	.undo_cwnd	= (void *)tcp_reno_undo_cwnd,
-	.cwnd_event	= (void *)bictcp_cwnd_event,
-	.pkts_acked     = (void *)bictcp_acked,
+	.init		= (void *)bpf_cubic_init,
+	.ssthresh	= (void *)bpf_cubic_recalc_ssthresh,
+	.cong_avoid	= (void *)bpf_cubic_cong_avoid,
+	.set_state	= (void *)bpf_cubic_state,
+	.undo_cwnd	= (void *)bpf_cubic_undo_cwnd,
+	.cwnd_event	= (void *)bpf_cubic_cwnd_event,
+	.pkts_acked     = (void *)bpf_cubic_acked,
 	.name		= "bpf_cubic",
 };
-- 
cgit v1.2.3


From 78e60bbbe8e8f614b6a453d8a780d9e6f77749a8 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:52:46 -0700
Subject: bpf: selftests: Bpf_cubic and bpf_dctcp calling kernel functions

This patch removes the bpf implementation of tcp_slow_start()
and tcp_cong_avoid_ai().  Instead, it directly uses the kernel
implementation.

It also replaces the bpf_cubic_undo_cwnd implementation by directly
calling tcp_reno_undo_cwnd().  bpf_dctcp also directly calls
tcp_reno_cong_avoid() instead.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015246.1551062-1-kafai@fb.com
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h | 29 ++-------------------------
 tools/testing/selftests/bpf/progs/bpf_cubic.c |  6 +++---
 tools/testing/selftests/bpf/progs/bpf_dctcp.c | 22 ++++++--------------
 3 files changed, 11 insertions(+), 46 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 91f0fac632f4..029589c008c9 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -187,16 +187,6 @@ struct tcp_congestion_ops {
 	typeof(y) __y = (y);			\
 	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
 
-static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked)
-{
-	__u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
-
-	acked -= cwnd - tp->snd_cwnd;
-	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
-
-	return acked;
-}
-
 static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
 {
 	return tp->snd_cwnd < tp->snd_ssthresh;
@@ -213,22 +203,7 @@ static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
 	return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
 }
 
-static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked)
-{
-	/* If credits accumulated at a higher w, apply them gently now. */
-	if (tp->snd_cwnd_cnt >= w) {
-		tp->snd_cwnd_cnt = 0;
-		tp->snd_cwnd++;
-	}
-
-	tp->snd_cwnd_cnt += acked;
-	if (tp->snd_cwnd_cnt >= w) {
-		__u32 delta = tp->snd_cwnd_cnt / w;
-
-		tp->snd_cwnd_cnt -= delta * w;
-		tp->snd_cwnd += delta;
-	}
-	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
-}
+extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
+extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
 
 #endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index 33c4d2bded64..f62df4d023f9 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -525,11 +525,11 @@ void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
 		hystart_update(sk, delay);
 }
 
+extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym;
+
 __u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk)
 {
-	const struct tcp_sock *tp = tcp_sk(sk);
-
-	return max(tp->snd_cwnd, tp->prior_cwnd);
+	return tcp_reno_undo_cwnd(sk);
 }
 
 SEC(".struct_ops")
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 4dc1a967776a..fd42247da8b4 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -194,22 +194,12 @@ __u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
 	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
 }
 
-SEC("struct_ops/tcp_reno_cong_avoid")
-void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (!tcp_is_cwnd_limited(sk))
-		return;
+extern void tcp_reno_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym;
 
-	/* In "safe" area, increase. */
-	if (tcp_in_slow_start(tp)) {
-		acked = tcp_slow_start(tp, acked);
-		if (!acked)
-			return;
-	}
-	/* In dangerous area, increase slowly. */
-	tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+SEC("struct_ops/dctcp_reno_cong_avoid")
+void BPF_PROG(dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+	tcp_reno_cong_avoid(sk, ack, acked);
 }
 
 SEC(".struct_ops")
@@ -226,7 +216,7 @@ struct tcp_congestion_ops dctcp = {
 	.in_ack_event   = (void *)dctcp_update_alpha,
 	.cwnd_event	= (void *)dctcp_cwnd_event,
 	.ssthresh	= (void *)dctcp_ssthresh,
-	.cong_avoid	= (void *)tcp_reno_cong_avoid,
+	.cong_avoid	= (void *)dctcp_cong_avoid,
 	.undo_cwnd	= (void *)dctcp_cwnd_undo,
 	.set_state	= (void *)dctcp_state,
 	.flags		= TCP_CONG_NEEDS_ECN,
-- 
cgit v1.2.3


From 7bd1590d4eba1583f6ee85e8cfe556505f761e19 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Mar 2021 18:52:52 -0700
Subject: bpf: selftests: Add kfunc_call test

This patch adds a few kernel function bpf_kfunc_call_test*() for the
selftest's test_run purpose.  They will be allowed for tc_cls prog.

The selftest calling the kernel function bpf_kfunc_call_test*()
is also added in this patch.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210325015252.1551395-1-kafai@fb.com
---
 include/linux/bpf.h                                |  6 +++
 net/bpf/test_run.c                                 | 28 ++++++++++
 net/core/filter.c                                  |  1 +
 .../testing/selftests/bpf/prog_tests/kfunc_call.c  | 59 ++++++++++++++++++++++
 .../testing/selftests/bpf/progs/kfunc_call_test.c  | 47 +++++++++++++++++
 .../selftests/bpf/progs/kfunc_call_test_subprog.c  | 42 +++++++++++++++
 6 files changed, 183 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/kfunc_call.c
 create mode 100644 tools/testing/selftests/bpf/progs/kfunc_call_test.c
 create mode 100644 tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c

(limited to 'tools/testing')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b5b7967e3ff3..9fdd839b418c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1532,6 +1532,7 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
 int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
 				const union bpf_attr *kattr,
 				union bpf_attr __user *uattr);
+bool bpf_prog_test_check_kfunc_call(u32 kfunc_id);
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info);
@@ -1731,6 +1732,11 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
 	return -ENOTSUPP;
 }
 
+static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id)
+{
+	return false;
+}
+
 static inline void bpf_map_put(struct bpf_map *map)
 {
 }
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 4aabf71cd95d..a5d72c48fb66 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2017 Facebook
  */
 #include <linux/bpf.h>
+#include <linux/btf_ids.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/etherdevice.h>
@@ -213,10 +214,37 @@ int noinline bpf_modify_return_test(int a, int *b)
 	*b += 1;
 	return a + *b;
 }
+
+u64 noinline bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d)
+{
+	return a + b + c + d;
+}
+
+int noinline bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b)
+{
+	return a + b;
+}
+
+struct sock * noinline bpf_kfunc_call_test3(struct sock *sk)
+{
+	return sk;
+}
+
 __diag_pop();
 
 ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO);
 
+BTF_SET_START(test_sk_kfunc_ids)
+BTF_ID(func, bpf_kfunc_call_test1)
+BTF_ID(func, bpf_kfunc_call_test2)
+BTF_ID(func, bpf_kfunc_call_test3)
+BTF_SET_END(test_sk_kfunc_ids)
+
+bool bpf_prog_test_check_kfunc_call(u32 kfunc_id)
+{
+	return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id);
+}
+
 static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 			   u32 headroom, u32 tailroom)
 {
diff --git a/net/core/filter.c b/net/core/filter.c
index 17dc159ec40c..cae56d08a670 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9813,6 +9813,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
 	.gen_ld_abs		= bpf_gen_ld_abs,
+	.check_kfunc_call	= bpf_prog_test_check_kfunc_call,
 };
 
 const struct bpf_prog_ops tc_cls_act_prog_ops = {
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
new file mode 100644
index 000000000000..7fc0951ee75f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "kfunc_call_test.skel.h"
+#include "kfunc_call_test_subprog.skel.h"
+
+static void test_main(void)
+{
+	struct kfunc_call_test *skel;
+	int prog_fd, retval, err;
+
+	skel = kfunc_call_test__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		return;
+
+	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1);
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run(test1)");
+	ASSERT_EQ(retval, 12, "test1-retval");
+
+	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test2);
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run(test2)");
+	ASSERT_EQ(retval, 3, "test2-retval");
+
+	kfunc_call_test__destroy(skel);
+}
+
+static void test_subprog(void)
+{
+	struct kfunc_call_test_subprog *skel;
+	int prog_fd, retval, err;
+
+	skel = kfunc_call_test_subprog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		return;
+
+	prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1);
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run(test1)");
+	ASSERT_EQ(retval, 10, "test1-retval");
+	ASSERT_NEQ(skel->data->active_res, -1, "active_res");
+	ASSERT_EQ(skel->data->sk_state, BPF_TCP_CLOSE, "sk_state");
+
+	kfunc_call_test_subprog__destroy(skel);
+}
+
+void test_kfunc_call(void)
+{
+	if (test__start_subtest("main"))
+		test_main();
+
+	if (test__start_subtest("subprog"))
+		test_subprog();
+}
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
new file mode 100644
index 000000000000..470f8723e463
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
+extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
+				  __u32 c, __u64 d) __ksym;
+
+SEC("classifier")
+int kfunc_call_test2(struct __sk_buff *skb)
+{
+	struct bpf_sock *sk = skb->sk;
+
+	if (!sk)
+		return -1;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk)
+		return -1;
+
+	return bpf_kfunc_call_test2((struct sock *)sk, 1, 2);
+}
+
+SEC("classifier")
+int kfunc_call_test1(struct __sk_buff *skb)
+{
+	struct bpf_sock *sk = skb->sk;
+	__u64 a = 1ULL << 32;
+	__u32 ret;
+
+	if (!sk)
+		return -1;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk)
+		return -1;
+
+	a = bpf_kfunc_call_test1((struct sock *)sk, 1, a | 2, 3, a | 4);
+	ret = a >> 32;   /* ret should be 2 */
+	ret += (__u32)a; /* ret should be 12 */
+
+	return ret;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
new file mode 100644
index 000000000000..b2dcb7d9cb03
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+extern const int bpf_prog_active __ksym;
+extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
+				  __u32 c, __u64 d) __ksym;
+extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
+int active_res = -1;
+int sk_state = -1;
+
+int __noinline f1(struct __sk_buff *skb)
+{
+	struct bpf_sock *sk = skb->sk;
+	int *active;
+
+	if (!sk)
+		return -1;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk)
+		return -1;
+
+	active = (int *)bpf_per_cpu_ptr(&bpf_prog_active,
+					bpf_get_smp_processor_id());
+	if (active)
+		active_res = *active;
+
+	sk_state = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state;
+
+	return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4);
+}
+
+SEC("classifier")
+int kfunc_call_test1(struct __sk_buff *skb)
+{
+	return f1(skb);
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From c127ffa23e41e6cb2251d5c30e54d60777034caa Mon Sep 17 00:00:00 2001
From: Baowen Zheng <baowen.zheng@corigine.com>
Date: Fri, 26 Mar 2021 14:09:37 +0100
Subject: selftests: tc-testing: add action police selftest for packets per
 second

Add selftest cases in action police for packets per second.
These tests depend on corresponding iproute2 command support.

Signed-off-by: Baowen Zheng <baowen.zheng@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/police.json        | 48 ++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index b8268da5adaa..8e45792703ed 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -764,5 +764,53 @@
         "teardown": [
             "$TC actions flush action police"
         ]
+    },
+    {
+        "id": "cdd7",
+        "name": "Add valid police action with packets per second rate limit",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police pkts_rate 1000 pkts_burst 200 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 0bit burst 0b mtu 4096Mb pkts_rate 1000 pkts_burst 200",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
+    },
+    {
+        "id": "f5bc",
+        "name": "Add invalid police action with both bps and pps",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1kbit burst 10k pkts_rate 1000 pkts_burst 200 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 ",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 53b61f29367df398243b7298ad1e5793c289a493 Mon Sep 17 00:00:00 2001
From: Baowen Zheng <baowen.zheng@corigine.com>
Date: Fri, 26 Mar 2021 14:09:38 +0100
Subject: selftests: forwarding: Add tc-police tests for packets per second

Test tc-police action for packets per second.
The test is mainly in scenarios Rx policing and Tx policing.
The test passes with veth pairs ports.

Signed-off-by: Baowen Zheng <baowen.zheng@corigine.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh      |  9 ++++
 .../testing/selftests/net/forwarding/tc_police.sh  | 56 ++++++++++++++++++++++
 2 files changed, 65 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 05c05e02bade..42e28c983d41 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -772,6 +772,15 @@ rate()
 	echo $((8 * (t1 - t0) / interval))
 }
 
+packets_rate()
+{
+	local t0=$1; shift
+	local t1=$1; shift
+	local interval=$1; shift
+
+	echo $(((t1 - t0) / interval))
+}
+
 mac_get()
 {
 	local if_name=$1
diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh
index 160f9cccdfb7..4f9f17cb45d6 100755
--- a/tools/testing/selftests/net/forwarding/tc_police.sh
+++ b/tools/testing/selftests/net/forwarding/tc_police.sh
@@ -35,6 +35,8 @@ ALL_TESTS="
 	police_shared_test
 	police_rx_mirror_test
 	police_tx_mirror_test
+	police_pps_rx_test
+	police_pps_tx_test
 "
 NUM_NETIFS=6
 source tc_common.sh
@@ -290,6 +292,60 @@ police_tx_mirror_test()
 	police_mirror_common_test $rp2 egress "police tx and mirror"
 }
 
+police_pps_common_test()
+{
+	local test_name=$1; shift
+
+	RET=0
+
+	# Rule to measure bandwidth on ingress of $h2
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action drop
+
+	mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \
+		-t udp sp=12345,dp=54321 -p 1000 -c 0 -q &
+
+	local t0=$(tc_rule_stats_get $h2 1 ingress .packets)
+	sleep 10
+	local t1=$(tc_rule_stats_get $h2 1 ingress .packets)
+
+	local er=$((2000))
+	local nr=$(packets_rate $t0 $t1 10)
+	local nr_pct=$((100 * (nr - er) / er))
+	((-10 <= nr_pct && nr_pct <= 10))
+	check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-10%."
+
+	log_test "$test_name"
+
+	{ kill %% && wait %%; } 2>/dev/null
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_pps_rx_test()
+{
+	# Rule to police traffic destined to $h2 on ingress of $rp1
+	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action police pkts_rate 2000 pkts_burst 400 conform-exceed drop/ok
+
+	police_pps_common_test "police pps on rx"
+
+	tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+}
+
+police_pps_tx_test()
+{
+	# Rule to police traffic destined to $h2 on egress of $rp2
+	tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \
+		dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \
+		action police pkts_rate 2000 pkts_burst 400 conform-exceed drop/ok
+
+	police_pps_common_test "police pps on tx"
+
+	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.2.3


From c3572a0b731fc0de13afef300f1f5afb929e4d4c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 29 Mar 2021 13:09:46 +0300
Subject: selftests: mlxsw: Test matchall failure with protocol match

The driver can only offload matchall rules that do not match on a
protocol. Test that matchall rules that match on a protocol are vetoed.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/tc_restrictions.sh      | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
index b4dbda706c4d..5ec3beb637c8 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
@@ -11,6 +11,7 @@ ALL_TESTS="
 	matchall_mirror_behind_flower_ingress_test
 	matchall_sample_behind_flower_ingress_test
 	matchall_mirror_behind_flower_egress_test
+	matchall_proto_match_test
 	police_limits_test
 	multi_police_test
 "
@@ -291,6 +292,22 @@ matchall_mirror_behind_flower_egress_test()
 	matchall_behind_flower_egress_test "mirror" "mirred egress mirror dev $swp2"
 }
 
+matchall_proto_match_test()
+{
+	RET=0
+
+	tc qdisc add dev $swp1 clsact
+
+	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
+		matchall skip_sw \
+		action sample group 1 rate 100
+	check_fail $? "Incorrect success to add matchall rule with protocol match"
+
+	tc qdisc del dev $swp1 clsact
+
+	log_test "matchall protocol match"
+}
+
 police_limits_test()
 {
 	RET=0
-- 
cgit v1.2.3


From 7ede22e6583290c832306e23414cc2c1e336c4b7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 29 Mar 2021 13:09:48 +0300
Subject: selftests: mlxsw: Test vetoing of double sampling

Test that two sampling rules cannot be configured on the same port with
the same trigger.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/tc_sample.sh       | 30 ++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
index 57b05f042787..093bed088ad0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -34,6 +34,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 ALL_TESTS="
 	tc_sample_rate_test
 	tc_sample_max_rate_test
+	tc_sample_conflict_test
 	tc_sample_group_conflict_test
 	tc_sample_md_iif_test
 	tc_sample_md_lag_iif_test
@@ -272,6 +273,35 @@ tc_sample_max_rate_test()
 	log_test "tc sample maximum rate"
 }
 
+tc_sample_conflict_test()
+{
+	RET=0
+
+	# Test that two sampling rules cannot be configured on the same port,
+	# even when they share the same parameters.
+
+	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
+		skip_sw action sample rate 1024 group 1
+	check_err $? "Failed to configure sampling rule"
+
+	tc filter add dev $rp1 ingress protocol all pref 2 handle 102 matchall \
+		skip_sw action sample rate 1024 group 1 &> /dev/null
+	check_fail $? "Managed to configure second sampling rule"
+
+	# Delete the first rule and make sure the second rule can now be
+	# configured.
+
+	tc filter del dev $rp1 ingress protocol all pref 1 handle 101 matchall
+
+	tc filter add dev $rp1 ingress protocol all pref 2 handle 102 matchall \
+		skip_sw action sample rate 1024 group 1
+	check_err $? "Failed to configure sampling rule after deletion"
+
+	log_test "tc sample conflict test"
+
+	tc filter del dev $rp1 ingress protocol all pref 2 handle 102 matchall
+}
+
 tc_sample_group_conflict_test()
 {
 	RET=0
-- 
cgit v1.2.3


From 2ba4badca9977b64c966b0177920daadbd5501fe Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 29 Mar 2021 22:41:56 -0700
Subject: bpf: selftests: Update clang requirement in README.rst for testing
 kfunc call

This patch updates the README.rst to specify the clang requirement
to compile the bpf selftests that call kernel function.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210330054156.2933804-1-kafai@fb.com
---
 tools/testing/selftests/bpf/README.rst | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 3464161c8eea..65fe318d1e71 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -179,3 +179,17 @@ types, which was introduced in `Clang 13`__. The older Clang versions will
 either crash when compiling these tests, or generate an incorrect BTF.
 
 __  https://reviews.llvm.org/D83289
+
+Kernel function call test and Clang version
+===========================================
+
+Some selftests (e.g. kfunc_call and bpf_tcp_ca) require a LLVM support
+to generate extern function in BTF.  It was introduced in `Clang 13`__.
+
+Without it, the error from compiling bpf selftests looks like:
+
+.. code-block:: console
+
+  libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
+
+__ https://reviews.llvm.org/D93563
-- 
cgit v1.2.3


From 9f33df73a929ed91dddad036f518d690b3094eda Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:00 +0200
Subject: selftests: xsk: Don't call worker_pkt_dump() for stats test

For TEST_TYPE_STATS, worker_pkt_validate() that places frames onto
pkt_buf is not called. Therefore, when dump mode is set, don't call
worker_pkt_dump() for mentioned test type, so that it won't crash on
pkt_buf() access.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-2-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 1e21a3172687..09429ed2ddf6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -999,7 +999,7 @@ static void testapp_validate(void)
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
 
-	if (debug_pkt_dump) {
+	if (debug_pkt_dump && test_type != TEST_TYPE_STATS) {
 		worker_pkt_dump();
 		for (int iter = 0; iter < num_frames - 1; iter++) {
 			free(pkt_buf[iter]->payload);
-- 
cgit v1.2.3


From e623bfdef713ddda1b9f57d1759df3a1cd97255a Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:01 +0200
Subject: selftests: xsk: Remove struct ifaceconfigobj

ifaceconfigobj is not really useful, it is possible to keep the
functionality and simplify the code.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-3-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 65 +++++++++++++++-----------------
 tools/testing/selftests/bpf/xdpxceiver.h |  9 -----
 2 files changed, 30 insertions(+), 44 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 09429ed2ddf6..e2ff3cd48ccf 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -93,6 +93,13 @@ typedef __u16 __sum16;
 #include "xdpxceiver.h"
 #include "../kselftest.h"
 
+static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
+static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
+static const char *IP1 = "192.168.100.162";
+static const char *IP2 = "192.168.100.161";
+static const u16 UDP_PORT1 = 2020;
+static const u16 UDP_PORT2 = 2121;
+
 static void __exit_with_error(int error, const char *file, const char *func, int line)
 {
 	if (configured_mode == TEST_MODE_UNCONFIGURED) {
@@ -1053,25 +1060,24 @@ static void testapp_stats(void)
 	print_ksft_result();
 }
 
-static void init_iface_config(struct ifaceconfigobj *ifaceconfig)
+static void init_iface(struct ifobject *ifobj, const char *dst_mac,
+		       const char *src_mac, const char *dst_ip,
+		       const char *src_ip, const u16 dst_port,
+		       const u16 src_port)
 {
-	/*Init interface0 */
-	ifdict[0]->fv.vector = tx;
-	memcpy(ifdict[0]->dst_mac, ifaceconfig->dst_mac, ETH_ALEN);
-	memcpy(ifdict[0]->src_mac, ifaceconfig->src_mac, ETH_ALEN);
-	ifdict[0]->dst_ip = ifaceconfig->dst_ip.s_addr;
-	ifdict[0]->src_ip = ifaceconfig->src_ip.s_addr;
-	ifdict[0]->dst_port = ifaceconfig->dst_port;
-	ifdict[0]->src_port = ifaceconfig->src_port;
-
-	/*Init interface1 */
-	ifdict[1]->fv.vector = rx;
-	memcpy(ifdict[1]->dst_mac, ifaceconfig->src_mac, ETH_ALEN);
-	memcpy(ifdict[1]->src_mac, ifaceconfig->dst_mac, ETH_ALEN);
-	ifdict[1]->dst_ip = ifaceconfig->src_ip.s_addr;
-	ifdict[1]->src_ip = ifaceconfig->dst_ip.s_addr;
-	ifdict[1]->dst_port = ifaceconfig->src_port;
-	ifdict[1]->src_port = ifaceconfig->dst_port;
+	struct in_addr ip;
+
+	memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN);
+	memcpy(ifobj->src_mac, src_mac, ETH_ALEN);
+
+	inet_aton(dst_ip, &ip);
+	ifobj->dst_ip = ip.s_addr;
+
+	inet_aton(src_ip, &ip);
+	ifobj->src_ip = ip.s_addr;
+
+	ifobj->dst_port = dst_port;
+	ifobj->src_port = src_port;
 }
 
 static void *nsdisablemodethread(void *args)
@@ -1175,26 +1181,11 @@ static void run_pkt_test(int mode, int type)
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+	int i, j;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
 		exit_with_error(errno);
 
-	const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
-	const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
-	const char *IP1 = "192.168.100.162";
-	const char *IP2 = "192.168.100.161";
-	u16 UDP_DST_PORT = 2020;
-	u16 UDP_SRC_PORT = 2121;
-	int i, j;
-
-	ifaceconfig = malloc(sizeof(struct ifaceconfigobj));
-	memcpy(ifaceconfig->dst_mac, MAC1, ETH_ALEN);
-	memcpy(ifaceconfig->src_mac, MAC2, ETH_ALEN);
-	inet_aton(IP1, &ifaceconfig->dst_ip);
-	inet_aton(IP2, &ifaceconfig->src_ip);
-	ifaceconfig->dst_port = UDP_DST_PORT;
-	ifaceconfig->src_port = UDP_SRC_PORT;
-
 	for (int i = 0; i < MAX_INTERFACES; i++) {
 		ifdict[i] = malloc(sizeof(struct ifobject));
 		if (!ifdict[i])
@@ -1209,7 +1200,11 @@ int main(int argc, char **argv)
 
 	num_frames = ++opt_pkt_count;
 
-	init_iface_config(ifaceconfig);
+	ifdict[0]->fv.vector = tx;
+	init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2);
+
+	ifdict[1]->fv.vector = rx;
+	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1);
 
 	disable_xdp_mode(XDP_FLAGS_DRV_MODE);
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 30314ef305c2..8f9308099318 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -125,15 +125,6 @@ struct generic_data {
 	u32 seqnum;
 };
 
-struct ifaceconfigobj {
-	u8 dst_mac[ETH_ALEN];
-	u8 src_mac[ETH_ALEN];
-	struct in_addr dst_ip;
-	struct in_addr src_ip;
-	u16 src_port;
-	u16 dst_port;
-} *ifaceconfig;
-
 struct ifobject {
 	int ifindex;
 	int ifdict_index;
-- 
cgit v1.2.3


From 7519c387e69d367075bf493de8a9ea427c9d2a1b Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:02 +0200
Subject: selftests: xsk: Remove unused function

Probably it was ported from xdpsock but is not used anywhere.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-4-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index e2ff3cd48ccf..593e8be41fce 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -153,19 +153,6 @@ static void *memset32_htonl(void *dest, u32 val, u32 size)
 	return dest;
 }
 
-/*
- * This function code has been taken from
- * Linux kernel lib/checksum.c
- */
-static inline unsigned short from32to16(unsigned int x)
-{
-	/* add up 16-bit and 16-bit for 16+c bit */
-	x = (x & 0xffff) + (x >> 16);
-	/* add up carry.. */
-	x = (x & 0xffff) + (x >> 16);
-	return x;
-}
-
 /*
  * Fold a partial checksum
  * This function code has been taken from
-- 
cgit v1.2.3


From 965d2cb0f675e5f60af441c9bd430c284d66179d Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:03 +0200
Subject: selftests: xsk: Remove inline keyword from source file

Follow the kernel coding style guidelines and let compiler do the
decision about inlining.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-5-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 593e8be41fce..77880abd818c 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -158,7 +158,7 @@ static void *memset32_htonl(void *dest, u32 val, u32 size)
  * This function code has been taken from
  * Linux kernel include/asm-generic/checksum.h
  */
-static inline __u16 csum_fold(__u32 csum)
+static __u16 csum_fold(__u32 csum)
 {
 	u32 sum = (__force u32)csum;
 
@@ -171,7 +171,7 @@ static inline __u16 csum_fold(__u32 csum)
  * This function code has been taken from
  * Linux kernel lib/checksum.c
  */
-static inline u32 from64to32(u64 x)
+static u32 from64to32(u64 x)
 {
 	/* add up 32-bit and 32-bit for 32+c bit */
 	x = (x & 0xffffffff) + (x >> 32);
@@ -180,13 +180,11 @@ static inline u32 from64to32(u64 x)
 	return (u32)x;
 }
 
-__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum);
-
 /*
  * This function code has been taken from
  * Linux kernel lib/checksum.c
  */
-__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
 {
 	unsigned long long s = (__force u32)sum;
 
@@ -204,13 +202,12 @@ __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u3
  * This function has been taken from
  * Linux kernel include/asm-generic/checksum.h
  */
-static inline __u16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
 
-static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
+static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
 {
 	u32 csum = 0;
 	u32 cnt = 0;
@@ -500,7 +497,7 @@ static void kick_tx(struct xsk_socket_info *xsk)
 	exit_with_error(errno);
 }
 
-static inline void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
+static void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
 {
 	unsigned int rcvd;
 	u32 idx;
@@ -605,7 +602,7 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
 	complete_tx_only(xsk, batch_size);
 }
 
-static inline int get_batch_size(int pkt_cnt)
+static int get_batch_size(int pkt_cnt)
 {
 	if (!opt_pkt_count)
 		return BATCH_SIZE;
-- 
cgit v1.2.3


From aa2d61c154f9387883664e3873bc0700419640a3 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:04 +0200
Subject: selftests: xsk: Simplify frame traversal in dumping thread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Store offsets to each layer in a separate variables rather than compute
them every single time.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-6-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 47 ++++++++++++++------------------
 1 file changed, 21 insertions(+), 26 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 77880abd818c..ae2f7d71f041 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -658,45 +658,40 @@ static void tx_only_all(struct ifobject *ifobject)
 
 static void worker_pkt_dump(void)
 {
-	struct in_addr ipaddr;
+	struct ethhdr *ethhdr;
+	struct iphdr *iphdr;
+	struct udphdr *udphdr;
+	char s[128];
+	int payload;
+	void *ptr;
 
 	fprintf(stdout, "---------------------------------------\n");
 	for (int iter = 0; iter < num_frames - 1; iter++) {
+		ptr = pkt_buf[iter]->payload;
+		ethhdr = ptr;
+		iphdr = ptr + sizeof(*ethhdr);
+		udphdr = ptr + sizeof(*ethhdr) + sizeof(*iphdr);
+
 		/*extract L2 frame */
 		fprintf(stdout, "DEBUG>> L2: dst mac: ");
 		for (int i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ((struct ethhdr *)
-						 pkt_buf[iter]->payload)->h_dest[i]);
+			fprintf(stdout, "%02X", ethhdr->h_dest[i]);
 
 		fprintf(stdout, "\nDEBUG>> L2: src mac: ");
 		for (int i = 0; i < ETH_ALEN; i++)
-			fprintf(stdout, "%02X", ((struct ethhdr *)
-						 pkt_buf[iter]->payload)->h_source[i]);
+			fprintf(stdout, "%02X", ethhdr->h_source[i]);
 
 		/*extract L3 frame */
-		fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n",
-			((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->ihl);
-
-		ipaddr.s_addr =
-		    ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->saddr;
-		fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", inet_ntoa(ipaddr));
-
-		ipaddr.s_addr =
-		    ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->daddr;
-		fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", inet_ntoa(ipaddr));
-
+		fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl);
+		fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n",
+			inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s)));
+		fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n",
+			inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s)));
 		/*extract L4 frame */
-		fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n",
-			ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
-						 sizeof(struct ethhdr) +
-						 sizeof(struct iphdr)))->source));
-
-		fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n",
-			ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
-						 sizeof(struct ethhdr) +
-						 sizeof(struct iphdr)))->dest));
+		fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source));
+		fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest));
 		/*extract L5 frame */
-		int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
+		payload = *((uint32_t *)(ptr + PKT_HDR_SIZE));
 
 		if (payload == EOT) {
 			print_verbose("End-of-transmission frame received\n");
-- 
cgit v1.2.3


From ef9280789773c974b45f809d58b47b481f2cf9f5 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:07 +0200
Subject: selftests: xsk: Remove thread for netns switch

Currently, there is a dedicated thread for following remote ns operations:
- grabbing the ifindex of the interface moved to remote netns
- removing xdp prog from that interface

With bpf_link usage in place, this can be simply omitted, so remove
mentioned thread, as BPF resources will be managed by bpf_link itself,
so there's no further need for creating the thread that will switch to
remote netns and do the cleanup.

Keep most of the logic for switching the ns, though, but make
switch_namespace() return the fd so that it will be possible to close it
at the process termination time. Get rid of logic around making sure
that it's possible to switch ns in validate_interfaces().

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-9-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 123 +++----------------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  10 +--
 2 files changed, 14 insertions(+), 119 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index ae2f7d71f041..a856b2935d66 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -355,12 +355,15 @@ static void usage(const char *prog)
 	ksft_print_msg(str, prog);
 }
 
-static bool switch_namespace(int idx)
+static int switch_namespace(const char *nsname)
 {
 	char fqns[26] = "/var/run/netns/";
 	int nsfd;
 
-	strncat(fqns, ifdict[idx]->nsname, sizeof(fqns) - strlen(fqns) - 1);
+	if (!nsname || strlen(nsname) == 0)
+		return -1;
+
+	strncat(fqns, nsname, sizeof(fqns) - strlen(fqns) - 1);
 	nsfd = open(fqns, O_RDONLY);
 
 	if (nsfd == -1)
@@ -369,26 +372,9 @@ static bool switch_namespace(int idx)
 	if (setns(nsfd, 0) == -1)
 		exit_with_error(errno);
 
-	return true;
-}
-
-static void *nsswitchthread(void *args)
-{
-	struct targs *targs = args;
+	print_verbose("NS switched: %s\n", nsname);
 
-	targs->retptr = false;
-
-	if (switch_namespace(targs->idx)) {
-		ifdict[targs->idx]->ifindex = if_nametoindex(ifdict[targs->idx]->ifname);
-		if (!ifdict[targs->idx]->ifindex) {
-			ksft_test_result_fail("ERROR: [%s] interface \"%s\" does not exist\n",
-					      __func__, ifdict[targs->idx]->ifname);
-		} else {
-			print_verbose("Interface found: %s\n", ifdict[targs->idx]->ifname);
-			targs->retptr = true;
-		}
-	}
-	pthread_exit(NULL);
+	return nsfd;
 }
 
 static int validate_interfaces(void)
@@ -400,33 +386,6 @@ static int validate_interfaces(void)
 			ret = false;
 			ksft_test_result_fail("ERROR: interfaces: -i <int>,<ns> -i <int>,<ns>.");
 		}
-		if (strcmp(ifdict[i]->nsname, "")) {
-			struct targs *targs;
-
-			targs = malloc(sizeof(*targs));
-			if (!targs)
-				exit_with_error(errno);
-
-			targs->idx = i;
-			if (pthread_create(&ns_thread, NULL, nsswitchthread, targs))
-				exit_with_error(errno);
-
-			pthread_join(ns_thread, NULL);
-
-			if (targs->retptr)
-				print_verbose("NS switched: %s\n", ifdict[i]->nsname);
-
-			free(targs);
-		} else {
-			ifdict[i]->ifindex = if_nametoindex(ifdict[i]->ifname);
-			if (!ifdict[i]->ifindex) {
-				ksft_test_result_fail
-				    ("ERROR: interface \"%s\" does not exist\n", ifdict[i]->ifname);
-				ret = false;
-			} else {
-				print_verbose("Interface found: %s\n", ifdict[i]->ifname);
-			}
-		}
 	}
 	return ret;
 }
@@ -843,8 +802,7 @@ static void *worker_testapp_validate(void *arg)
 		if (bufs == MAP_FAILED)
 			exit_with_error(errno);
 
-		if (strcmp(ifobject->nsname, ""))
-			switch_namespace(ifobject->ifdict_index);
+		ifobject->ns_fd = switch_namespace(ifobject->nsname);
 	}
 
 	if (ifobject->fv.vector == tx) {
@@ -1059,60 +1017,6 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac,
 	ifobj->src_port = src_port;
 }
 
-static void *nsdisablemodethread(void *args)
-{
-	struct targs *targs = args;
-
-	targs->retptr = false;
-
-	if (switch_namespace(targs->idx)) {
-		targs->retptr = bpf_set_link_xdp_fd(ifdict[targs->idx]->ifindex, -1, targs->flags);
-	} else {
-		targs->retptr = errno;
-		print_verbose("Failed to switch namespace to %s\n", ifdict[targs->idx]->nsname);
-	}
-
-	pthread_exit(NULL);
-}
-
-static void disable_xdp_mode(int mode)
-{
-	int err = 0;
-	__u32 flags = XDP_FLAGS_UPDATE_IF_NOEXIST | mode;
-	char *mode_str = mode & XDP_FLAGS_SKB_MODE ? "skb" : "drv";
-
-	for (int i = 0; i < MAX_INTERFACES; i++) {
-		if (strcmp(ifdict[i]->nsname, "")) {
-			struct targs *targs;
-
-			targs = malloc(sizeof(*targs));
-			memset(targs, 0, sizeof(*targs));
-			if (!targs)
-				exit_with_error(errno);
-
-			targs->idx = i;
-			targs->flags = flags;
-			if (pthread_create(&ns_thread, NULL, nsdisablemodethread, targs))
-				exit_with_error(errno);
-
-			pthread_join(ns_thread, NULL);
-			err = targs->retptr;
-			free(targs);
-		} else {
-			err = bpf_set_link_xdp_fd(ifdict[i]->ifindex, -1, flags);
-		}
-
-		if (err) {
-			print_verbose("Failed to disable %s mode on interface %s\n",
-						mode_str, ifdict[i]->ifname);
-			exit_with_error(err);
-		}
-
-		print_verbose("Disabled %s mode for interface: %s\n", mode_str, ifdict[i]->ifname);
-		configured_mode = mode & XDP_FLAGS_SKB_MODE ? TEST_MODE_DRV : TEST_MODE_SKB;
-	}
-}
-
 static void run_pkt_test(int mode, int type)
 {
 	test_type = type;
@@ -1132,13 +1036,9 @@ static void run_pkt_test(int mode, int type)
 
 	switch (mode) {
 	case (TEST_MODE_SKB):
-		if (configured_mode == TEST_MODE_DRV)
-			disable_xdp_mode(XDP_FLAGS_DRV_MODE);
 		xdp_flags |= XDP_FLAGS_SKB_MODE;
 		break;
 	case (TEST_MODE_DRV):
-		if (configured_mode == TEST_MODE_SKB)
-			disable_xdp_mode(XDP_FLAGS_SKB_MODE);
 		xdp_flags |= XDP_FLAGS_DRV_MODE;
 		break;
 	default:
@@ -1185,8 +1085,6 @@ int main(int argc, char **argv)
 	ifdict[1]->fv.vector = rx;
 	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1);
 
-	disable_xdp_mode(XDP_FLAGS_DRV_MODE);
-
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
 	for (i = 0; i < TEST_MODE_MAX; i++) {
@@ -1194,8 +1092,11 @@ int main(int argc, char **argv)
 			run_pkt_test(i, j);
 	}
 
-	for (int i = 0; i < MAX_INTERFACES; i++)
+	for (int i = 0; i < MAX_INTERFACES; i++) {
+		if (ifdict[i]->ns_fd != -1)
+			close(ifdict[i]->ns_fd);
 		free(ifdict[i]);
+	}
 
 	ksft_exit_pass();
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 8f9308099318..493f7498d40e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -126,7 +126,7 @@ struct generic_data {
 };
 
 struct ifobject {
-	int ifindex;
+	int ns_fd;
 	int ifdict_index;
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
@@ -150,15 +150,9 @@ pthread_mutex_t sync_mutex;
 pthread_mutex_t sync_mutex_tx;
 pthread_cond_t signal_rx_condition;
 pthread_cond_t signal_tx_condition;
-pthread_t t0, t1, ns_thread;
+pthread_t t0, t1;
 pthread_attr_t attr;
 
-struct targs {
-	u8 retptr;
-	int idx;
-	u32 flags;
-};
-
 TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
 struct head_s *head_p;
 struct pkt {
-- 
cgit v1.2.3


From 9866bcd6635c264aaf3de1d89e44773a269048eb Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:08 +0200
Subject: selftests: xsk: Split worker thread

Let's a have a separate Tx/Rx worker threads instead of a one common
thread packed with Tx/Rx specific checks.

Move mmap for umem buffer space and a switch_namespace() call to
thread_common_ops.

This also allows for a bunch of simplifactions that are the subject of
the next commits. The final result will be a code base that is much
easier to follow.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-10-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 156 +++++++++++++++----------------
 1 file changed, 77 insertions(+), 79 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index a856b2935d66..cb6583b8ad67 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -760,6 +760,15 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 	int ctr = 0;
 	int ret;
 
+	pthread_attr_setstacksize(&attr, THREAD_STACK);
+
+	bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
+		    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (bufs == MAP_FAILED)
+		exit_with_error(errno);
+
+	ifobject->ns_fd = switch_namespace(ifobject->nsname);
+
 	xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
 	ret = xsk_configure_socket(ifobject);
 
@@ -782,9 +791,12 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 
 	if (ctr >= SOCK_RECONF_CTR)
 		exit_with_error(ret);
+
+	print_verbose("Interface [%s] vector [%s]\n",
+		      ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx");
 }
 
-static void *worker_testapp_validate(void *arg)
+static void *worker_testapp_validate_tx(void *arg)
 {
 	struct udphdr *udp_hdr =
 	    (struct udphdr *)(pkt_data + sizeof(struct ethhdr) + sizeof(struct iphdr));
@@ -792,97 +804,83 @@ static void *worker_testapp_validate(void *arg)
 	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
 	struct ifobject *ifobject = (struct ifobject *)arg;
 	struct generic_data data;
+	int spinningrxctr = 0;
 	void *bufs = NULL;
 
-	pthread_attr_setstacksize(&attr, THREAD_STACK);
-
-	if (!bidi_pass) {
-		bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
-			    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
-		if (bufs == MAP_FAILED)
-			exit_with_error(errno);
+	if (!bidi_pass)
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_tx);
 
-		ifobject->ns_fd = switch_namespace(ifobject->nsname);
+	while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
+		spinningrxctr++;
+		usleep(USLEEP_MAX);
 	}
 
-	if (ifobject->fv.vector == tx) {
-		int spinningrxctr = 0;
+	for (int i = 0; i < num_frames; i++) {
+		/*send EOT frame */
+		if (i == (num_frames - 1))
+			data.seqnum = -1;
+		else
+			data.seqnum = i;
+		gen_udp_hdr(&data, ifobject, udp_hdr);
+		gen_ip_hdr(ifobject, ip_hdr);
+		gen_udp_csum(udp_hdr, ip_hdr);
+		gen_eth_hdr(ifobject, eth_hdr);
+		gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
+	}
 
-		if (!bidi_pass)
-			thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_tx);
+	print_verbose("Sending %d packets on interface %s\n",
+		      (opt_pkt_count - 1), ifobject->ifname);
+	tx_only_all(ifobject);
 
-		while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
-			spinningrxctr++;
-			usleep(USLEEP_MAX);
-		}
+	if (test_type != TEST_TYPE_BIDI || bidi_pass) {
+		xsk_socket__delete(ifobject->xsk->xsk);
+		(void)xsk_umem__delete(ifobject->umem->umem);
+	}
+	pthread_exit(NULL);
+}
 
-		print_verbose("Interface [%s] vector [Tx]\n", ifobject->ifname);
-		for (int i = 0; i < num_frames; i++) {
-			/*send EOT frame */
-			if (i == (num_frames - 1))
-				data.seqnum = -1;
-			else
-				data.seqnum = i;
-			gen_udp_hdr(&data, ifobject, udp_hdr);
-			gen_ip_hdr(ifobject, ip_hdr);
-			gen_udp_csum(udp_hdr, ip_hdr);
-			gen_eth_hdr(ifobject, eth_hdr);
-			gen_eth_frame(ifobject->umem, i * XSK_UMEM__DEFAULT_FRAME_SIZE);
-		}
+static void *worker_testapp_validate_rx(void *arg)
+{
+	struct ifobject *ifobject = (struct ifobject *)arg;
+	struct pollfd fds[MAX_SOCKS] = { };
+	void *bufs = NULL;
 
-		print_verbose("Sending %d packets on interface %s\n",
-			       (opt_pkt_count - 1), ifobject->ifname);
-		tx_only_all(ifobject);
-	} else if (ifobject->fv.vector == rx) {
-		struct pollfd fds[MAX_SOCKS] = { };
-		int ret;
-
-		if (!bidi_pass)
-			thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
-
-		print_verbose("Interface [%s] vector [Rx]\n", ifobject->ifname);
-		if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
-			xsk_populate_fill_ring(ifobject->umem);
-
-		TAILQ_INIT(&head);
-		if (debug_pkt_dump) {
-			pkt_buf = calloc(num_frames, sizeof(*pkt_buf));
-			if (!pkt_buf)
-				exit_with_error(errno);
-		}
+	if (!bidi_pass)
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
 
-		fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
-		fds[0].events = POLLIN;
+	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
+		xsk_populate_fill_ring(ifobject->umem);
 
-		pthread_mutex_lock(&sync_mutex);
-		pthread_cond_signal(&signal_rx_condition);
-		pthread_mutex_unlock(&sync_mutex);
+	TAILQ_INIT(&head);
+	if (debug_pkt_dump) {
+		pkt_buf = calloc(num_frames, sizeof(*pkt_buf));
+		if (!pkt_buf)
+			exit_with_error(errno);
+	}
 
-		while (1) {
-			if (test_type == TEST_TYPE_POLL) {
-				ret = poll(fds, 1, POLL_TMOUT);
-				if (ret <= 0)
-					continue;
-			}
+	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
+	fds[0].events = POLLIN;
 
-			if (test_type != TEST_TYPE_STATS) {
-				rx_pkt(ifobject->xsk, fds);
-				worker_pkt_validate();
-			} else {
-				worker_stats_validate(ifobject);
-			}
+	pthread_mutex_lock(&sync_mutex);
+	pthread_cond_signal(&signal_rx_condition);
+	pthread_mutex_unlock(&sync_mutex);
 
-			if (sigvar)
-				break;
+	while (1) {
+		if (test_type != TEST_TYPE_STATS) {
+			rx_pkt(ifobject->xsk, fds);
+			worker_pkt_validate();
+		} else {
+			worker_stats_validate(ifobject);
 		}
+		if (sigvar)
+			break;
+	}
 
-		if (test_type != TEST_TYPE_STATS)
-			print_verbose("Received %d packets on interface %s\n",
-				pkt_counter, ifobject->ifname);
+	print_verbose("Received %d packets on interface %s\n",
+		      pkt_counter, ifobject->ifname);
 
-		if (test_type == TEST_TYPE_TEARDOWN)
-			print_verbose("Destroying socket\n");
-	}
+	if (test_type == TEST_TYPE_TEARDOWN)
+		print_verbose("Destroying socket\n");
 
 	if ((test_type != TEST_TYPE_BIDI) || bidi_pass) {
 		xsk_socket__delete(ifobject->xsk->xsk);
@@ -911,12 +909,12 @@ static void testapp_validate(void)
 
 	/*Spawn RX thread */
 	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[1]))
+		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[1]))
 			exit_with_error(errno);
 	} else if (bidi && bidi_pass) {
 		/*switch Tx/Rx vectors */
 		ifdict[0]->fv.vector = rx;
-		if (pthread_create(&t0, &attr, worker_testapp_validate, ifdict[0]))
+		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[0]))
 			exit_with_error(errno);
 	}
 
@@ -931,12 +929,12 @@ static void testapp_validate(void)
 
 	/*Spawn TX thread */
 	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[0]))
+		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[0]))
 			exit_with_error(errno);
 	} else if (bidi && bidi_pass) {
 		/*switch Tx/Rx vectors */
 		ifdict[1]->fv.vector = tx;
-		if (pthread_create(&t1, &attr, worker_testapp_validate, ifdict[1]))
+		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[1]))
 			exit_with_error(errno);
 	}
 
-- 
cgit v1.2.3


From 99f9bcb65705dda07288b759c569d30d8a4f297c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:09 +0200
Subject: selftests: xsk: Remove Tx synchronization resources

Tx thread needs to be started after the Rx side is fully initialized so
that packets are not xmitted until xsk Rx socket is ready to be used.

It can be observed that atomic variable spinning_tx is not checked from
Rx side in any way, so thread_common_ops can be modified to only address
the spinning_rx. This means that spinning_tx can be removed altogheter.

signal_tx_condition is never utilized, so simply remove it.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-11-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 15 +++++++--------
 tools/testing/selftests/bpf/xdpxceiver.h |  2 --
 2 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index cb6583b8ad67..9f7ee9a38752 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -126,7 +126,6 @@ static void pthread_init_mutex(void)
 	pthread_mutex_init(&sync_mutex, NULL);
 	pthread_mutex_init(&sync_mutex_tx, NULL);
 	pthread_cond_init(&signal_rx_condition, NULL);
-	pthread_cond_init(&signal_tx_condition, NULL);
 }
 
 static void pthread_destroy_mutex(void)
@@ -134,7 +133,6 @@ static void pthread_destroy_mutex(void)
 	pthread_mutex_destroy(&sync_mutex);
 	pthread_mutex_destroy(&sync_mutex_tx);
 	pthread_cond_destroy(&signal_rx_condition);
-	pthread_cond_destroy(&signal_tx_condition);
 }
 
 static void *memset32_htonl(void *dest, u32 val, u32 size)
@@ -754,8 +752,7 @@ static void worker_pkt_validate(void)
 	}
 }
 
-static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mutex_t *mutexptr,
-			      atomic_int *spinningptr)
+static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mutex_t *mutexptr)
 {
 	int ctr = 0;
 	int ret;
@@ -780,13 +777,15 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 	 */
 	pthread_mutex_lock(mutexptr);
 	while (ret && ctr < SOCK_RECONF_CTR) {
-		atomic_store(spinningptr, 1);
+		if (ifobject->fv.vector == rx)
+			atomic_store(&spinning_rx, 1);
 		xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
 		ret = xsk_configure_socket(ifobject);
 		usleep(USLEEP_MAX);
 		ctr++;
 	}
-	atomic_store(spinningptr, 0);
+	if (ifobject->fv.vector == rx)
+		atomic_store(&spinning_rx, 0);
 	pthread_mutex_unlock(mutexptr);
 
 	if (ctr >= SOCK_RECONF_CTR)
@@ -808,7 +807,7 @@ static void *worker_testapp_validate_tx(void *arg)
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_tx);
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
 
 	while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
 		spinningrxctr++;
@@ -846,7 +845,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx, &spinning_rx);
+		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
 		xsk_populate_fill_ring(ifobject->umem);
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 493f7498d40e..483be41229c6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -144,12 +144,10 @@ struct ifobject {
 static struct ifobject *ifdict[MAX_INTERFACES];
 
 /*threads*/
-atomic_int spinning_tx;
 atomic_int spinning_rx;
 pthread_mutex_t sync_mutex;
 pthread_mutex_t sync_mutex_tx;
 pthread_cond_t signal_rx_condition;
-pthread_cond_t signal_tx_condition;
 pthread_t t0, t1;
 pthread_attr_t attr;
 
-- 
cgit v1.2.3


From 9445f8c765838edf84dd0d3910ff309bdab8f95f Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:10 +0200
Subject: selftests: xsk: Refactor teardown/bidi test cases and
 testapp_validate

Currently, there is a testapp_sockets() that acts like a wrapper around
testapp_validate() and it is called for bidi and teardown test types.
Other test types call testapp_validate() directly.

Split testapp_sockets() onto two separate functions so a bunch of bidi
specific logic can be moved there and out of testapp_validate() itself.

Introduce function pointer to ifobject struct which will be used for
assigning the Rx/Tx function that is assigned to worker thread. Let's
also have a global ifobject Rx/Tx pointers so it's easier to swap the
vectors on a second run of a bi-directional test. Thread creation now is
easey to follow.

switching_notify variable is useless, info about vector switch can be
printed based on bidi_pass state.

Last but not least, init/destroy synchronization variables only once,
not per each test.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-12-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 117 ++++++++++++++++++-------------
 tools/testing/selftests/bpf/xdpxceiver.h |  14 ++--
 2 files changed, 78 insertions(+), 53 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 9f7ee9a38752..c0ebca8f55f8 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -896,26 +896,10 @@ static void testapp_validate(void)
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, THREAD_STACK);
 
-	if ((test_type == TEST_TYPE_BIDI) && bidi_pass) {
-		pthread_init_mutex();
-		if (!switching_notify) {
-			print_verbose("Switching Tx/Rx vectors\n");
-			switching_notify++;
-		}
-	}
-
 	pthread_mutex_lock(&sync_mutex);
 
 	/*Spawn RX thread */
-	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[1]))
-			exit_with_error(errno);
-	} else if (bidi && bidi_pass) {
-		/*switch Tx/Rx vectors */
-		ifdict[0]->fv.vector = rx;
-		if (pthread_create(&t0, &attr, worker_testapp_validate_rx, ifdict[0]))
-			exit_with_error(errno);
-	}
+	pthread_create(&t0, &attr, ifdict_rx->func_ptr, ifdict_rx);
 
 	if (clock_gettime(CLOCK_REALTIME, &max_wait))
 		exit_with_error(errno);
@@ -927,15 +911,7 @@ static void testapp_validate(void)
 	pthread_mutex_unlock(&sync_mutex);
 
 	/*Spawn TX thread */
-	if (!bidi || !bidi_pass) {
-		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[0]))
-			exit_with_error(errno);
-	} else if (bidi && bidi_pass) {
-		/*switch Tx/Rx vectors */
-		ifdict[1]->fv.vector = tx;
-		if (pthread_create(&t1, &attr, worker_testapp_validate_tx, ifdict[1]))
-			exit_with_error(errno);
-	}
+	pthread_create(&t1, &attr, ifdict_tx->func_ptr, ifdict_tx);
 
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
@@ -953,18 +929,53 @@ static void testapp_validate(void)
 		print_ksft_result();
 }
 
-static void testapp_sockets(void)
+static void testapp_teardown(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
+		pkt_counter = 0;
+		prev_pkt = -1;
+		sigvar = 0;
+		print_verbose("Creating socket\n");
+		testapp_validate();
+	}
+
+	print_ksft_result();
+}
+
+static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2)
+{
+	void *(*tmp_func_ptr)(void *) = ifobj1->func_ptr;
+	enum fvector tmp_vector = ifobj1->fv.vector;
+
+	ifobj1->func_ptr = ifobj2->func_ptr;
+	ifobj1->fv.vector = ifobj2->fv.vector;
+
+	ifobj2->func_ptr = tmp_func_ptr;
+	ifobj2->fv.vector = tmp_vector;
+
+	ifdict_tx = ifobj1;
+	ifdict_rx = ifobj2;
+}
+
+static void testapp_bidi(void)
 {
-	for (int i = 0; i < ((test_type == TEST_TYPE_TEARDOWN) ? MAX_TEARDOWN_ITER : MAX_BIDI_ITER);
-	     i++) {
+	for (int i = 0; i < MAX_BIDI_ITER; i++) {
 		pkt_counter = 0;
 		prev_pkt = -1;
 		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
-		test_type == TEST_TYPE_BIDI ? bidi_pass++ : bidi_pass;
+		if (!bidi_pass) {
+			print_verbose("Switching Tx/Rx vectors\n");
+			swap_vectors(ifdict[1], ifdict[0]);
+		}
+		bidi_pass++;
 	}
 
+	swap_vectors(ifdict[0], ifdict[1]);
+
 	print_ksft_result();
 }
 
@@ -997,7 +1008,7 @@ static void testapp_stats(void)
 static void init_iface(struct ifobject *ifobj, const char *dst_mac,
 		       const char *src_mac, const char *dst_ip,
 		       const char *src_ip, const u16 dst_port,
-		       const u16 src_port)
+		       const u16 src_port, enum fvector vector)
 {
 	struct in_addr ip;
 
@@ -1012,6 +1023,16 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac,
 
 	ifobj->dst_port = dst_port;
 	ifobj->src_port = src_port;
+
+	if (vector == tx) {
+		ifobj->fv.vector = tx;
+		ifobj->func_ptr = worker_testapp_validate_tx;
+		ifdict_tx = ifobj;
+	} else {
+		ifobj->fv.vector = rx;
+		ifobj->func_ptr = worker_testapp_validate_rx;
+		ifdict_rx = ifobj;
+	}
 }
 
 static void run_pkt_test(int mode, int type)
@@ -1021,11 +1042,8 @@ static void run_pkt_test(int mode, int type)
 	/* reset defaults after potential previous test */
 	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	pkt_counter = 0;
-	switching_notify = 0;
 	bidi_pass = 0;
 	prev_pkt = -1;
-	ifdict[0]->fv.vector = tx;
-	ifdict[1]->fv.vector = rx;
 	sigvar = 0;
 	stat_test_type = -1;
 	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
@@ -1042,16 +1060,20 @@ static void run_pkt_test(int mode, int type)
 		break;
 	}
 
-	pthread_init_mutex();
-
-	if (test_type == TEST_TYPE_STATS)
+	switch (test_type) {
+	case TEST_TYPE_STATS:
 		testapp_stats();
-	else if ((test_type != TEST_TYPE_TEARDOWN) && (test_type != TEST_TYPE_BIDI))
+		break;
+	case TEST_TYPE_TEARDOWN:
+		testapp_teardown();
+		break;
+	case TEST_TYPE_BIDI:
+		testapp_bidi();
+		break;
+	default:
 		testapp_validate();
-	else
-		testapp_sockets();
-
-	pthread_destroy_mutex();
+		break;
+	}
 }
 
 int main(int argc, char **argv)
@@ -1076,14 +1098,13 @@ int main(int argc, char **argv)
 
 	num_frames = ++opt_pkt_count;
 
-	ifdict[0]->fv.vector = tx;
-	init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2);
-
-	ifdict[1]->fv.vector = rx;
-	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1);
+	init_iface(ifdict[0], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx);
+	init_iface(ifdict[1], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx);
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
+	pthread_init_mutex();
+
 	for (i = 0; i < TEST_MODE_MAX; i++) {
 		for (j = 0; j < TEST_TYPE_MAX; j++)
 			run_pkt_test(i, j);
@@ -1095,6 +1116,8 @@ int main(int argc, char **argv)
 		free(ifdict[i]);
 	}
 
+	pthread_destroy_mutex();
+
 	ksft_exit_pass();
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 483be41229c6..3945746900af 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -77,7 +77,6 @@ enum STAT_TEST_TYPES {
 static int configured_mode = TEST_MODE_UNCONFIGURED;
 static u8 debug_pkt_dump;
 static u32 num_frames;
-static u8 switching_notify;
 static u8 bidi_pass;
 static int test_type;
 
@@ -126,22 +125,25 @@ struct generic_data {
 };
 
 struct ifobject {
-	int ns_fd;
-	int ifdict_index;
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
-	struct flow_vector fv;
 	struct xsk_socket_info *xsk;
 	struct xsk_umem_info *umem;
-	u8 dst_mac[ETH_ALEN];
-	u8 src_mac[ETH_ALEN];
+	void *(*func_ptr)(void *arg);
+	struct flow_vector fv;
+	int ns_fd;
+	int ifdict_index;
 	u32 dst_ip;
 	u32 src_ip;
 	u16 src_port;
 	u16 dst_port;
+	u8 dst_mac[ETH_ALEN];
+	u8 src_mac[ETH_ALEN];
 };
 
 static struct ifobject *ifdict[MAX_INTERFACES];
+static struct ifobject *ifdict_rx;
+static struct ifobject *ifdict_tx;
 
 /*threads*/
 atomic_int spinning_rx;
-- 
cgit v1.2.3


From 0464b1ed07677f869005bde3fade1580b48de67e Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:11 +0200
Subject: selftests: xsk: Remove sync_mutex_tx and atomic var

Although thread_common_ops() are called in both Tx and Rx threads,
testapp_validate() will not spawn Tx thread until Rx thread signals that
it has finished its initialization via condition variable.

Therefore, locking in thread_common_ops is not needed and furthermore Tx
thread does not have to spin on atomic variable.

Note that this simplification wouldn't be possible if there would still
be a common worker thread.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-13-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 31 +++++++------------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  2 --
 2 files changed, 7 insertions(+), 26 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index c0ebca8f55f8..35e14ad8097e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -121,17 +121,15 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\
 			       test_type == TEST_TYPE_STATS ? "Stats" : ""))
 
-static void pthread_init_mutex(void)
+static void init_sync_resources(void)
 {
 	pthread_mutex_init(&sync_mutex, NULL);
-	pthread_mutex_init(&sync_mutex_tx, NULL);
 	pthread_cond_init(&signal_rx_condition, NULL);
 }
 
-static void pthread_destroy_mutex(void)
+static void destroy_sync_resources(void)
 {
 	pthread_mutex_destroy(&sync_mutex);
-	pthread_mutex_destroy(&sync_mutex_tx);
 	pthread_cond_destroy(&signal_rx_condition);
 }
 
@@ -752,7 +750,7 @@ static void worker_pkt_validate(void)
 	}
 }
 
-static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mutex_t *mutexptr)
+static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 {
 	int ctr = 0;
 	int ret;
@@ -771,22 +769,13 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs, pthread_mut
 
 	/* Retry Create Socket if it fails as xsk_socket__create()
 	 * is asynchronous
-	 *
-	 * Essential to lock Mutex here to prevent Tx thread from
-	 * entering before Rx and causing a deadlock
 	 */
-	pthread_mutex_lock(mutexptr);
 	while (ret && ctr < SOCK_RECONF_CTR) {
-		if (ifobject->fv.vector == rx)
-			atomic_store(&spinning_rx, 1);
 		xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
 		ret = xsk_configure_socket(ifobject);
 		usleep(USLEEP_MAX);
 		ctr++;
 	}
-	if (ifobject->fv.vector == rx)
-		atomic_store(&spinning_rx, 0);
-	pthread_mutex_unlock(mutexptr);
 
 	if (ctr >= SOCK_RECONF_CTR)
 		exit_with_error(ret);
@@ -803,16 +792,10 @@ static void *worker_testapp_validate_tx(void *arg)
 	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
 	struct ifobject *ifobject = (struct ifobject *)arg;
 	struct generic_data data;
-	int spinningrxctr = 0;
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
-
-	while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
-		spinningrxctr++;
-		usleep(USLEEP_MAX);
-	}
+		thread_common_ops(ifobject, bufs);
 
 	for (int i = 0; i < num_frames; i++) {
 		/*send EOT frame */
@@ -845,7 +828,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	void *bufs = NULL;
 
 	if (!bidi_pass)
-		thread_common_ops(ifobject, bufs, &sync_mutex_tx);
+		thread_common_ops(ifobject, bufs);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
 		xsk_populate_fill_ring(ifobject->umem);
@@ -1103,7 +1086,7 @@ int main(int argc, char **argv)
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
-	pthread_init_mutex();
+	init_sync_resources();
 
 	for (i = 0; i < TEST_MODE_MAX; i++) {
 		for (j = 0; j < TEST_TYPE_MAX; j++)
@@ -1116,7 +1099,7 @@ int main(int argc, char **argv)
 		free(ifdict[i]);
 	}
 
-	pthread_destroy_mutex();
+	destroy_sync_resources();
 
 	ksft_exit_pass();
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 3945746900af..e304229d8a4c 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -146,9 +146,7 @@ static struct ifobject *ifdict_rx;
 static struct ifobject *ifdict_tx;
 
 /*threads*/
-atomic_int spinning_rx;
 pthread_mutex_t sync_mutex;
-pthread_mutex_t sync_mutex_tx;
 pthread_cond_t signal_rx_condition;
 pthread_t t0, t1;
 pthread_attr_t attr;
-- 
cgit v1.2.3


From 27e1ca2525de264901b5c2d9d0c4403c3fe8608c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 30 Mar 2021 00:43:13 +0200
Subject: selftests: xsk: Implement bpf_link test

Introduce a test that is supposed to verify the persistence of BPF
resources based on underlying bpf_link usage.

Test will:
1) create and bind two sockets on queue ids 0 and 1
2) run a traffic on queue ids 0
3) remove xsk sockets from queue 0 on both veth interfaces
4) run a traffic on queues ids 1

Running traffic successfully on qids 1 means that BPF resources were
not removed on step 3).

In order to make it work, change the command that creates veth pair to
have the 4 queue pairs by default.

Introduce the arrays of xsks and umems to ifobject struct but keep a
pointers to single entities, so rest of the logic around Rx/Tx can be
kept as-is.

For umem handling, double the size of mmapped space and split that
between the two sockets.

Rename also bidi_pass to a variable 'second_step' of a boolean type as
it's now used also for the test that is introduced here and it doesn't
have anything in common with bi-directional testing.

Drop opt_queue command line argument as it wasn't working before anyway.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-15-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/test_xsk.sh  |   3 +-
 tools/testing/selftests/bpf/xdpxceiver.c | 179 +++++++++++++++++++++++--------
 tools/testing/selftests/bpf/xdpxceiver.h |   7 +-
 3 files changed, 139 insertions(+), 50 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index 56d4474e2c83..46633a3bfb0b 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -107,7 +107,7 @@ setup_vethPairs() {
 	        echo "setting up ${VETH0}: namespace: ${NS0}"
 	fi
 	ip netns add ${NS1}
-	ip link add ${VETH0} type veth peer name ${VETH1}
+	ip link add ${VETH0} numtxqueues 4 numrxqueues 4 type veth peer name ${VETH1} numtxqueues 4 numrxqueues 4
 	if [ -f /proc/net/if_inet6 ]; then
 		echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
 	fi
@@ -118,6 +118,7 @@ setup_vethPairs() {
 	ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
 	ip link set ${VETH0} mtu ${MTU}
 	ip netns exec ${NS1} ip link set ${VETH1} up
+	ip netns exec ${NS1} ip link set dev lo up
 	ip link set ${VETH0} up
 }
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 35e14ad8097e..5c0d6dbd076f 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -41,8 +41,12 @@
  *            Reduce the size of the RX ring to a fraction of the fill ring size.
  *       iv.  fill queue empty
  *            Do not populate the fill queue and then try to receive pkts.
+ *    f. bpf_link resource persistence
+ *       Configure sockets at indexes 0 and 1, run a traffic on queue ids 0,
+ *       then remove xsk sockets from queue 0 on both veth interfaces and
+ *       finally run a traffic on queues ids 1
  *
- * Total tests: 10
+ * Total tests: 12
  *
  * Flow:
  * -----
@@ -115,11 +119,12 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
 
 #define print_ksft_result(void)\
-	(ksft_test_result_pass("PASS: %s %s %s%s%s\n", configured_mode ? "DRV" : "SKB",\
+	(ksft_test_result_pass("PASS: %s %s %s%s%s%s\n", configured_mode ? "DRV" : "SKB",\
 			       test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\
 			       test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\
 			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\
-			       test_type == TEST_TYPE_STATS ? "Stats" : ""))
+			       test_type == TEST_TYPE_STATS ? "Stats" : "",\
+			       test_type == TEST_TYPE_BPF_RES ? "BPF RES" : ""))
 
 static void init_sync_resources(void)
 {
@@ -258,9 +263,8 @@ static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
 	memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, PKT_SIZE);
 }
 
-static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
+static void xsk_configure_umem(struct ifobject *data, void *buffer, int idx)
 {
-	int ret;
 	struct xsk_umem_config cfg = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
@@ -268,17 +272,22 @@ static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
 		.frame_headroom = frame_headroom,
 		.flags = XSK_UMEM__DEFAULT_FLAGS
 	};
+	int size = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	struct xsk_umem_info *umem;
+	int ret;
 
-	data->umem = calloc(1, sizeof(struct xsk_umem_info));
-	if (!data->umem)
+	umem = calloc(1, sizeof(struct xsk_umem_info));
+	if (!umem)
 		exit_with_error(errno);
 
-	ret = xsk_umem__create(&data->umem->umem, buffer, size,
-			       &data->umem->fq, &data->umem->cq, &cfg);
+	ret = xsk_umem__create(&umem->umem, buffer, size,
+			       &umem->fq, &umem->cq, &cfg);
 	if (ret)
 		exit_with_error(ret);
 
-	data->umem->buffer = buffer;
+	umem->buffer = buffer;
+
+	data->umem_arr[idx] = umem;
 }
 
 static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
@@ -294,18 +303,19 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
 	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
 }
 
-static int xsk_configure_socket(struct ifobject *ifobject)
+static int xsk_configure_socket(struct ifobject *ifobject, int idx)
 {
 	struct xsk_socket_config cfg;
+	struct xsk_socket_info *xsk;
 	struct xsk_ring_cons *rxr;
 	struct xsk_ring_prod *txr;
 	int ret;
 
-	ifobject->xsk = calloc(1, sizeof(struct xsk_socket_info));
-	if (!ifobject->xsk)
+	xsk = calloc(1, sizeof(struct xsk_socket_info));
+	if (!xsk)
 		exit_with_error(errno);
 
-	ifobject->xsk->umem = ifobject->umem;
+	xsk->umem = ifobject->umem;
 	cfg.rx_size = rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
 	cfg.libbpf_flags = 0;
@@ -313,19 +323,20 @@ static int xsk_configure_socket(struct ifobject *ifobject)
 	cfg.bind_flags = xdp_bind_flags;
 
 	if (test_type != TEST_TYPE_BIDI) {
-		rxr = (ifobject->fv.vector == rx) ? &ifobject->xsk->rx : NULL;
-		txr = (ifobject->fv.vector == tx) ? &ifobject->xsk->tx : NULL;
+		rxr = (ifobject->fv.vector == rx) ? &xsk->rx : NULL;
+		txr = (ifobject->fv.vector == tx) ? &xsk->tx : NULL;
 	} else {
-		rxr = &ifobject->xsk->rx;
-		txr = &ifobject->xsk->tx;
+		rxr = &xsk->rx;
+		txr = &xsk->tx;
 	}
 
-	ret = xsk_socket__create(&ifobject->xsk->xsk, ifobject->ifname,
-				 opt_queue, ifobject->umem->umem, rxr, txr, &cfg);
-
+	ret = xsk_socket__create(&xsk->xsk, ifobject->ifname, idx,
+				 ifobject->umem->umem, rxr, txr, &cfg);
 	if (ret)
 		return 1;
 
+	ifobject->xsk_arr[idx] = xsk;
+
 	return 0;
 }
 
@@ -393,7 +404,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:q:DC:v", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:DC:v", long_options, &option_index);
 
 		if (c == -1)
 			break;
@@ -413,9 +424,6 @@ static void parse_command_line(int argc, char **argv)
 				       MAX_INTERFACES_NAMESPACE_CHARS);
 			interface_index++;
 			break;
-		case 'q':
-			opt_queue = atoi(optarg);
-			break;
 		case 'D':
 			debug_pkt_dump = 1;
 			break;
@@ -752,27 +760,33 @@ static void worker_pkt_validate(void)
 
 static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 {
+	int umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
 	int ctr = 0;
 	int ret;
 
 	pthread_attr_setstacksize(&attr, THREAD_STACK);
 
-	bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
+	ifobject->ns_fd = switch_namespace(ifobject->nsname);
+
+	if (test_type == TEST_TYPE_BPF_RES)
+		umem_sz *= 2;
+
+	bufs = mmap(NULL, umem_sz,
 		    PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	if (bufs == MAP_FAILED)
 		exit_with_error(errno);
 
-	ifobject->ns_fd = switch_namespace(ifobject->nsname);
-
-	xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
-	ret = xsk_configure_socket(ifobject);
+	xsk_configure_umem(ifobject, bufs, 0);
+	ifobject->umem = ifobject->umem_arr[0];
+	ret = xsk_configure_socket(ifobject, 0);
 
 	/* Retry Create Socket if it fails as xsk_socket__create()
 	 * is asynchronous
 	 */
 	while (ret && ctr < SOCK_RECONF_CTR) {
-		xsk_configure_umem(ifobject, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
-		ret = xsk_configure_socket(ifobject);
+		xsk_configure_umem(ifobject, bufs, 0);
+		ifobject->umem = ifobject->umem_arr[0];
+		ret = xsk_configure_socket(ifobject, 0);
 		usleep(USLEEP_MAX);
 		ctr++;
 	}
@@ -780,10 +794,34 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 	if (ctr >= SOCK_RECONF_CTR)
 		exit_with_error(ret);
 
+	ifobject->umem = ifobject->umem_arr[0];
+	ifobject->xsk = ifobject->xsk_arr[0];
+
+	if (test_type == TEST_TYPE_BPF_RES) {
+		xsk_configure_umem(ifobject, (u8 *)bufs + (umem_sz / 2), 1);
+		ifobject->umem = ifobject->umem_arr[1];
+		ret = xsk_configure_socket(ifobject, 1);
+	}
+
+	ifobject->umem = ifobject->umem_arr[0];
+	ifobject->xsk = ifobject->xsk_arr[0];
 	print_verbose("Interface [%s] vector [%s]\n",
 		      ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx");
 }
 
+static bool testapp_is_test_two_stepped(void)
+{
+	return (test_type != TEST_TYPE_BIDI && test_type != TEST_TYPE_BPF_RES) || second_step;
+}
+
+static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
+{
+	if (testapp_is_test_two_stepped()) {
+		xsk_socket__delete(ifobj->xsk->xsk);
+		(void)xsk_umem__delete(ifobj->umem->umem);
+	}
+}
+
 static void *worker_testapp_validate_tx(void *arg)
 {
 	struct udphdr *udp_hdr =
@@ -794,7 +832,7 @@ static void *worker_testapp_validate_tx(void *arg)
 	struct generic_data data;
 	void *bufs = NULL;
 
-	if (!bidi_pass)
+	if (!second_step)
 		thread_common_ops(ifobject, bufs);
 
 	for (int i = 0; i < num_frames; i++) {
@@ -814,10 +852,7 @@ static void *worker_testapp_validate_tx(void *arg)
 		      (opt_pkt_count - 1), ifobject->ifname);
 	tx_only_all(ifobject);
 
-	if (test_type != TEST_TYPE_BIDI || bidi_pass) {
-		xsk_socket__delete(ifobject->xsk->xsk);
-		(void)xsk_umem__delete(ifobject->umem->umem);
-	}
+	testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
 }
 
@@ -827,7 +862,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	struct pollfd fds[MAX_SOCKS] = { };
 	void *bufs = NULL;
 
-	if (!bidi_pass)
+	if (!second_step)
 		thread_common_ops(ifobject, bufs);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
@@ -864,10 +899,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	if (test_type == TEST_TYPE_TEARDOWN)
 		print_verbose("Destroying socket\n");
 
-	if ((test_type != TEST_TYPE_BIDI) || bidi_pass) {
-		xsk_socket__delete(ifobject->xsk->xsk);
-		(void)xsk_umem__delete(ifobject->umem->umem);
-	}
+	testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
 }
 
@@ -875,6 +907,7 @@ static void testapp_validate(void)
 {
 	struct timespec max_wait = { 0, 0 };
 	bool bidi = test_type == TEST_TYPE_BIDI;
+	bool bpf = test_type == TEST_TYPE_BPF_RES;
 
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, THREAD_STACK);
@@ -908,7 +941,7 @@ static void testapp_validate(void)
 		free(pkt_buf);
 	}
 
-	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !(test_type == TEST_TYPE_STATS))
+	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS))
 		print_ksft_result();
 }
 
@@ -950,11 +983,11 @@ static void testapp_bidi(void)
 		sigvar = 0;
 		print_verbose("Creating socket\n");
 		testapp_validate();
-		if (!bidi_pass) {
+		if (!second_step) {
 			print_verbose("Switching Tx/Rx vectors\n");
 			swap_vectors(ifdict[1], ifdict[0]);
 		}
-		bidi_pass++;
+		second_step = true;
 	}
 
 	swap_vectors(ifdict[0], ifdict[1]);
@@ -962,6 +995,36 @@ static void testapp_bidi(void)
 	print_ksft_result();
 }
 
+static void swap_xsk_res(void)
+{
+	xsk_socket__delete(ifdict_tx->xsk->xsk);
+	xsk_umem__delete(ifdict_tx->umem->umem);
+	xsk_socket__delete(ifdict_rx->xsk->xsk);
+	xsk_umem__delete(ifdict_rx->umem->umem);
+	ifdict_tx->umem = ifdict_tx->umem_arr[1];
+	ifdict_tx->xsk = ifdict_tx->xsk_arr[1];
+	ifdict_rx->umem = ifdict_rx->umem_arr[1];
+	ifdict_rx->xsk = ifdict_rx->xsk_arr[1];
+}
+
+static void testapp_bpf_res(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_BPF_ITER; i++) {
+		pkt_counter = 0;
+		prev_pkt = -1;
+		sigvar = 0;
+		print_verbose("Creating socket\n");
+		testapp_validate();
+		if (!second_step)
+			swap_xsk_res();
+		second_step = true;
+	}
+
+	print_ksft_result();
+}
+
 static void testapp_stats(void)
 {
 	for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) {
@@ -1025,13 +1088,15 @@ static void run_pkt_test(int mode, int type)
 	/* reset defaults after potential previous test */
 	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	pkt_counter = 0;
-	bidi_pass = 0;
+	second_step = 0;
 	prev_pkt = -1;
 	sigvar = 0;
 	stat_test_type = -1;
 	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 	frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 
+	configured_mode = mode;
+
 	switch (mode) {
 	case (TEST_MODE_SKB):
 		xdp_flags |= XDP_FLAGS_SKB_MODE;
@@ -1053,6 +1118,9 @@ static void run_pkt_test(int mode, int type)
 	case TEST_TYPE_BIDI:
 		testapp_bidi();
 		break;
+	case TEST_TYPE_BPF_RES:
+		testapp_bpf_res();
+		break;
 	default:
 		testapp_validate();
 		break;
@@ -1062,6 +1130,7 @@ static void run_pkt_test(int mode, int type)
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+	bool failure = false;
 	int i, j;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
@@ -1073,6 +1142,16 @@ int main(int argc, char **argv)
 			exit_with_error(errno);
 
 		ifdict[i]->ifdict_index = i;
+		ifdict[i]->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *));
+		if (!ifdict[i]->xsk_arr) {
+			failure = true;
+			goto cleanup;
+		}
+		ifdict[i]->umem_arr = calloc(2, sizeof(struct xsk_umem_info *));
+		if (!ifdict[i]->umem_arr) {
+			failure = true;
+			goto cleanup;
+		}
 	}
 
 	setlocale(LC_ALL, "");
@@ -1093,13 +1172,19 @@ int main(int argc, char **argv)
 			run_pkt_test(i, j);
 	}
 
+	destroy_sync_resources();
+
+cleanup:
 	for (int i = 0; i < MAX_INTERFACES; i++) {
 		if (ifdict[i]->ns_fd != -1)
 			close(ifdict[i]->ns_fd);
+		free(ifdict[i]->xsk_arr);
+		free(ifdict[i]->umem_arr);
 		free(ifdict[i]);
 	}
 
-	destroy_sync_resources();
+	if (failure)
+		exit_with_error(errno);
 
 	ksft_exit_pass();
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e304229d8a4c..e431ecb9bb95 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -23,6 +23,7 @@
 #define MAX_SOCKS 1
 #define MAX_TEARDOWN_ITER 10
 #define MAX_BIDI_ITER 2
+#define MAX_BPF_ITER 2
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
 			sizeof(struct udphdr))
 #define MIN_PKT_SIZE 64
@@ -63,6 +64,7 @@ enum TEST_TYPES {
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
 	TEST_TYPE_STATS,
+	TEST_TYPE_BPF_RES,
 	TEST_TYPE_MAX
 };
 
@@ -77,10 +79,9 @@ enum STAT_TEST_TYPES {
 static int configured_mode = TEST_MODE_UNCONFIGURED;
 static u8 debug_pkt_dump;
 static u32 num_frames;
-static u8 bidi_pass;
+static bool second_step;
 static int test_type;
 
-static int opt_queue;
 static int opt_pkt_count;
 static u8 opt_verbose;
 
@@ -128,6 +129,8 @@ struct ifobject {
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
 	struct xsk_socket_info *xsk;
+	struct xsk_socket_info **xsk_arr;
+	struct xsk_umem_info **umem_arr;
 	struct xsk_umem_info *umem;
 	void *(*func_ptr)(void *arg);
 	struct flow_vector fv;
-- 
cgit v1.2.3


From 7651910257c8fb1ec76b50bef0330fcf739105c7 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Tue, 30 Mar 2021 00:43:14 +0200
Subject: selftests: xsk: Remove thread attribute
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is really no reason to have a non-default thread stack
size. Remove that.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-16-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 9 ++-------
 tools/testing/selftests/bpf/xdpxceiver.h | 2 --
 2 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 5c0d6dbd076f..ec09b8fe1178 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -764,8 +764,6 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 	int ctr = 0;
 	int ret;
 
-	pthread_attr_setstacksize(&attr, THREAD_STACK);
-
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
 	if (test_type == TEST_TYPE_BPF_RES)
@@ -909,13 +907,10 @@ static void testapp_validate(void)
 	bool bidi = test_type == TEST_TYPE_BIDI;
 	bool bpf = test_type == TEST_TYPE_BPF_RES;
 
-	pthread_attr_init(&attr);
-	pthread_attr_setstacksize(&attr, THREAD_STACK);
-
 	pthread_mutex_lock(&sync_mutex);
 
 	/*Spawn RX thread */
-	pthread_create(&t0, &attr, ifdict_rx->func_ptr, ifdict_rx);
+	pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx);
 
 	if (clock_gettime(CLOCK_REALTIME, &max_wait))
 		exit_with_error(errno);
@@ -927,7 +922,7 @@ static void testapp_validate(void)
 	pthread_mutex_unlock(&sync_mutex);
 
 	/*Spawn TX thread */
-	pthread_create(&t1, &attr, ifdict_tx->func_ptr, ifdict_tx);
+	pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx);
 
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e431ecb9bb95..78863820fb81 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -37,7 +37,6 @@
 #define TMOUT_SEC (3)
 #define EOT (-1)
 #define USLEEP_MAX 200000
-#define THREAD_STACK 60000000
 #define SOCK_RECONF_CTR 10
 #define BATCH_SIZE 64
 #define POLL_TMOUT 1000
@@ -152,7 +151,6 @@ static struct ifobject *ifdict_tx;
 pthread_mutex_t sync_mutex;
 pthread_cond_t signal_rx_condition;
 pthread_t t0, t1;
-pthread_attr_t attr;
 
 TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
 struct head_s *head_p;
-- 
cgit v1.2.3


From 96539f1c5efb0022b94412e8623722aad23dee6b Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Tue, 30 Mar 2021 00:43:15 +0200
Subject: selftests: xsk: Remove mutex and condition variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The usage of the condition variable is broken, and overkill. Replace it
with a pthread barrier.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-17-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 33 +++++---------------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  3 +--
 2 files changed, 6 insertions(+), 30 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index ec09b8fe1178..6d87bdf3574a 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -126,18 +126,6 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 			       test_type == TEST_TYPE_STATS ? "Stats" : "",\
 			       test_type == TEST_TYPE_BPF_RES ? "BPF RES" : ""))
 
-static void init_sync_resources(void)
-{
-	pthread_mutex_init(&sync_mutex, NULL);
-	pthread_cond_init(&signal_rx_condition, NULL);
-}
-
-static void destroy_sync_resources(void)
-{
-	pthread_mutex_destroy(&sync_mutex);
-	pthread_cond_destroy(&signal_rx_condition);
-}
-
 static void *memset32_htonl(void *dest, u32 val, u32 size)
 {
 	u32 *ptr = (u32 *)dest;
@@ -876,9 +864,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds[0].events = POLLIN;
 
-	pthread_mutex_lock(&sync_mutex);
-	pthread_cond_signal(&signal_rx_condition);
-	pthread_mutex_unlock(&sync_mutex);
+	pthread_barrier_wait(&barr);
 
 	while (1) {
 		if (test_type != TEST_TYPE_STATS) {
@@ -903,24 +889,19 @@ static void *worker_testapp_validate_rx(void *arg)
 
 static void testapp_validate(void)
 {
-	struct timespec max_wait = { 0, 0 };
 	bool bidi = test_type == TEST_TYPE_BIDI;
 	bool bpf = test_type == TEST_TYPE_BPF_RES;
 
-	pthread_mutex_lock(&sync_mutex);
+	if (pthread_barrier_init(&barr, NULL, 2))
+		exit_with_error(errno);
 
 	/*Spawn RX thread */
 	pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx);
 
-	if (clock_gettime(CLOCK_REALTIME, &max_wait))
-		exit_with_error(errno);
-	max_wait.tv_sec += TMOUT_SEC;
-
-	if (pthread_cond_timedwait(&signal_rx_condition, &sync_mutex, &max_wait) == ETIMEDOUT)
+	pthread_barrier_wait(&barr);
+	if (pthread_barrier_destroy(&barr))
 		exit_with_error(errno);
 
-	pthread_mutex_unlock(&sync_mutex);
-
 	/*Spawn TX thread */
 	pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx);
 
@@ -1160,15 +1141,11 @@ int main(int argc, char **argv)
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
-	init_sync_resources();
-
 	for (i = 0; i < TEST_MODE_MAX; i++) {
 		for (j = 0; j < TEST_TYPE_MAX; j++)
 			run_pkt_test(i, j);
 	}
 
-	destroy_sync_resources();
-
 cleanup:
 	for (int i = 0; i < MAX_INTERFACES; i++) {
 		if (ifdict[i]->ns_fd != -1)
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 78863820fb81..ef219c0785eb 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -148,8 +148,7 @@ static struct ifobject *ifdict_rx;
 static struct ifobject *ifdict_tx;
 
 /*threads*/
-pthread_mutex_t sync_mutex;
-pthread_cond_t signal_rx_condition;
+pthread_barrier_t barr;
 pthread_t t0, t1;
 
 TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
-- 
cgit v1.2.3


From ae6b6a17800f34dd5215286b44a4e99a0a1cf862 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Tue, 30 Mar 2021 00:43:16 +0200
Subject: selftests: xsk: Remove unused defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove two unused defines.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210329224316.17793-18-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 7 +++----
 tools/testing/selftests/bpf/xdpxceiver.h | 2 --
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 6d87bdf3574a..1135fb980814 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -456,7 +456,7 @@ static void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
 	if (!xsk->outstanding_tx)
 		return;
 
-	if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
+	if (xsk_ring_prod__needs_wakeup(&xsk->tx))
 		kick_tx(xsk);
 
 	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
@@ -544,9 +544,8 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
 	xsk_ring_prod__submit(&xsk->tx, batch_size);
 	if (!tx_invalid_test) {
 		xsk->outstanding_tx += batch_size;
-	} else {
-		if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
-			kick_tx(xsk);
+	} else if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
+		kick_tx(xsk);
 	}
 	*frameptr += batch_size;
 	*frameptr %= num_frames;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index ef219c0785eb..6c428b276ab6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -34,13 +34,11 @@
 #define IP_PKT_TOS 0x9
 #define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))
 #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
-#define TMOUT_SEC (3)
 #define EOT (-1)
 #define USLEEP_MAX 200000
 #define SOCK_RECONF_CTR 10
 #define BATCH_SIZE 64
 #define POLL_TMOUT 1000
-#define NEED_WAKEUP true
 #define DEFAULT_PKT_CNT 10000
 #define RX_FULL_RXQSIZE 32
 
-- 
cgit v1.2.3


From a062260a9d5fce22977744ed6dab64b7b1508ab3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 30 Mar 2021 12:28:56 +0200
Subject: selftests: net: add UDP GRO forwarding self-tests

Create a bunch of virtual topologies and verify that
NETIF_F_GRO_FRAGLIST or NETIF_F_GRO_UDP_FWD-enabled
devices aggregate the ingress packets as expected.
Additionally check that the aggregate packets are
segmented correctly when landing on a socket

Also test SKB_GSO_FRAGLIST and SKB_GSO_UDP_L4 aggregation
on top of UDP tunnel (vxlan)

v1 -> v2:
 - hopefully clarify the commit message
 - moved the overlay network ipv6 range into the 'documentation'
   reserved range (Willem)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile      |   1 +
 tools/testing/selftests/net/udpgro_fwd.sh | 251 ++++++++++++++++++++++++++++++
 2 files changed, 252 insertions(+)
 create mode 100755 tools/testing/selftests/net/udpgro_fwd.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 25f198bec0b2..2d71b283dde3 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -23,6 +23,7 @@ TEST_PROGS += drop_monitor_tests.sh
 TEST_PROGS += vrf_route_leaking.sh
 TEST_PROGS += bareudp.sh
 TEST_PROGS += unicast_extensions.sh
+TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
new file mode 100755
index 000000000000..a8fa64136282
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -0,0 +1,251 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+readonly BASE="ns-$(mktemp -u XXXXXX)"
+readonly SRC=2
+readonly DST=1
+readonly DST_NAT=100
+readonly NS_SRC=$BASE$SRC
+readonly NS_DST=$BASE$DST
+
+# "baremetal" network used for raw UDP traffic
+readonly BM_NET_V4=192.168.1.
+readonly BM_NET_V6=2001:db8::
+
+# "overlay" network used for UDP over UDP tunnel traffic
+readonly OL_NET_V4=172.16.1.
+readonly OL_NET_V6=2001:db8:1::
+readonly NPROCS=`nproc`
+
+cleanup() {
+	local ns
+	local -r jobs="$(jobs -p)"
+	[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+
+	for ns in $NS_SRC $NS_DST; do
+		ip netns del $ns 2>/dev/null
+	done
+}
+
+trap cleanup EXIT
+
+create_ns() {
+	local net
+	local ns
+
+	for ns in $NS_SRC $NS_DST; do
+		ip netns add $ns
+		ip -n $ns link set dev lo up
+	done
+
+	ip link add name veth$SRC type veth peer name veth$DST
+
+	for ns in $SRC $DST; do
+		ip link set dev veth$ns netns $BASE$ns
+		ip -n $BASE$ns link set dev veth$ns up
+		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
+		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
+	done
+	ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+}
+
+create_vxlan_endpoint() {
+	local -r netns=$1
+	local -r bm_dev=$2
+	local -r bm_rem_addr=$3
+	local -r vxlan_dev=$4
+	local -r vxlan_id=$5
+	local -r vxlan_port=4789
+
+	ip -n $netns link set dev $bm_dev up
+	ip -n $netns link add dev $vxlan_dev type vxlan id $vxlan_id \
+				dstport $vxlan_port remote $bm_rem_addr
+	ip -n $netns link set dev $vxlan_dev up
+}
+
+create_vxlan_pair() {
+	local ns
+
+	create_ns
+
+	for ns in $SRC $DST; do
+		# note that 3 - $SRC == $DST and 3 - $DST == $SRC
+		create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V4$((3 - $ns)) vxlan$ns 4
+		ip -n $BASE$ns addr add dev vxlan$ns $OL_NET_V4$ns/24
+	done
+	for ns in $SRC $DST; do
+		create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6
+		ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad
+	done
+}
+
+is_ipv6() {
+	if [[ $1 =~ .*:.* ]]; then
+		return 0
+	fi
+	return 1
+}
+
+run_test() {
+	local -r msg=$1
+	local -r dst=$2
+	local -r pkts=$3
+	local -r vxpkts=$4
+	local bind=$5
+	local rx_args=""
+	local rx_family="-4"
+	local family=-4
+	local filter=IpInReceives
+	local ipt=iptables
+
+	printf "%-40s" "$msg"
+
+	if is_ipv6 $dst; then
+		# rx program does not support '-6' and implies ipv6 usage by default
+		rx_family=""
+		family=-6
+		filter=Ip6InReceives
+		ipt=ip6tables
+	fi
+
+	rx_args="$rx_family"
+	[ -n "$bind" ] && rx_args="$rx_args -b $bind"
+
+	# send a single GSO packet, segmented in 10 UDP frames.
+	# Always expect 10 UDP frames on RX side as rx socket does
+	# not enable GRO
+	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789
+	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
+	ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
+	local spid=$!
+	sleep 0.1
+	ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
+	local retc=$?
+	wait $spid
+	local rets=$?
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " fail client exit code $retc, server $rets"
+		ret=1
+		return
+	fi
+
+	local rcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 8000' | \
+							  sed -e 's/\[//' -e 's/:.*//'`
+	if [ $rcv != $pkts ]; then
+		echo " fail - received $rvs packets, expected $pkts"
+		ret=1
+		return
+	fi
+
+	local vxrcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 4789' | \
+							    sed -e 's/\[//' -e 's/:.*//'`
+
+	# upper net can generate a little noise, allow some tolerance
+	if [ $vxrcv -lt $vxpkts -o $vxrcv -gt $((vxpkts + 3)) ]; then
+		echo " fail - received $vxrcv vxlan packets, expected $vxpkts"
+		ret=1
+		return
+	fi
+	echo " ok"
+}
+
+run_bench() {
+	local -r msg=$1
+	local -r dst=$2
+	local family=-4
+
+	printf "%-40s" "$msg"
+	if [ $NPROCS -lt 2 ]; then
+		echo " skip - needed 2 CPUs found $NPROCS"
+		return
+	fi
+
+	is_ipv6 $dst && family=-6
+
+	# bind the sender and the receiver to different CPUs to try
+	# get reproducible results
+	ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
+	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10  &
+	local spid=$!
+	sleep 0.1
+	ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
+	local retc=$?
+	wait $spid
+	local rets=$?
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " fail client exit code $retc, server $rets"
+		ret=1
+		return
+	fi
+}
+
+for family in 4 6; do
+	BM_NET=$BM_NET_V4
+	OL_NET=$OL_NET_V4
+	IPT=iptables
+	SUFFIX=24
+	VXDEV=vxlan
+
+	if [ $family = 6 ]; then
+		BM_NET=$BM_NET_V6
+		OL_NET=$OL_NET_V6
+		SUFFIX="64 nodad"
+		VXDEV=vxlan6
+		IPT=ip6tables
+	fi
+
+	echo "IPv$family"
+
+	create_ns
+	run_test "No GRO" $BM_NET$DST 10 0
+	cleanup
+
+	create_ns
+	ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
+	run_test "GRO frag list" $BM_NET$DST 1 0
+	cleanup
+
+	# UDP GRO fwd skips aggregation when find an udp socket with the GRO option
+	# if there is an UDP tunnel in the running system, such lookup happen
+	# take place.
+	# use NAT to circumvent GRO FWD check
+	create_ns
+	ip -n $NS_DST addr add dev veth$DST $BM_NET$DST_NAT/$SUFFIX
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $BM_NET$DST_NAT \
+					-j DNAT --to-destination $BM_NET$DST
+	run_test "GRO fwd" $BM_NET$DST_NAT 1 0 $BM_NET$DST
+	cleanup
+
+	create_ns
+	run_bench "UDP fwd perf" $BM_NET$DST
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	run_bench "UDP GRO fwd perf" $BM_NET$DST
+	cleanup
+
+	create_vxlan_pair
+	ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
+	run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1
+	cleanup
+
+	# use NAT to circumvent GRO FWD check
+	create_vxlan_pair
+	ip -n $NS_DST addr add dev $VXDEV$DST $OL_NET$DST_NAT/$SUFFIX
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $OL_NET$DST_NAT \
+					-j DNAT --to-destination $OL_NET$DST
+
+	# load arp cache before running the test to reduce the amount of
+	# stray traffic on top of the UDP tunnel
+	ip netns exec $NS_SRC ping -q -c 1 $OL_NET$DST_NAT >/dev/null
+	run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST
+	cleanup
+
+	create_vxlan_pair
+	run_bench "UDP tunnel fwd perf" $OL_NET$DST
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST
+	cleanup
+done
+
+exit $ret
-- 
cgit v1.2.3


From e48792a9ec7898444fec6577611a6205e36dfdb9 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Tue, 30 Mar 2021 13:41:10 +0300
Subject: tc-testing: add simple action change test

Use act_simple to verify that action created with 'tc actions change'
command exists after command returns. The goal is to verify internal action
API reference counting to ensure that the case when netlink message has
NLM_F_REPLACE flag set but action with specified index doesn't exist is
handled correctly.

Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/simple.json        | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
index 8e8c1ae12260..e15f708b0fa4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -23,6 +23,30 @@
             "$TC actions flush action simple"
         ]
     },
+    {
+        "id": "4297",
+        "name": "Add simple action with change command",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions change action simple sdata \"Not changed\" index 60",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <Not changed>.*index 60 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
+    },
     {
         "id": "6d4c",
         "name": "Add simple action with duplicate index",
-- 
cgit v1.2.3


From 6254ad408820ca84283798c8fdbda3b01259a9a8 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Tue, 30 Mar 2021 17:08:54 -0700
Subject: selftests: mptcp: avoid calling pm_nl_ctl with bad IDs

IDs are supposed to be between 0 and 255.

In pm_nl_ctl, for both the 'add' and 'get' instruction, the ID is casted
in a u_int8_t. So if we give 256, we will delete ID 0. Obviously, the
goal is not to delete this ID by giving 256.

We could modify pm_nl_ctl and stop if the ID is negative or higher than
255 but probably better not to increase the number of lines for such
things in this tool which is only used in selftests. Instead, we use it
within the limits.

This modification also means that we will no longer add a new ID for the
2nd entry. That's why we removed an expected entry from the dump and
introduced with
commit dc8eb10e95a8 ("selftests: mptcp: add testcases for setting the address ID").

So now we delete ID 9 like before and we add entries for IDs 10 to 255
that are deleted just after.

Note that this could be seen as a fix but it was not really an issue so
far: we were simply playing with ID 0/1 once again. With the following
commit ("selftests: mptcp: add addr argument for del_addr"), it will be
different because ID 0 is going to required an address. We don't want
errors when trying to delete ID 0 without the address argument.

Acked-and-tested-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/pm_netlink.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index a617e293734c..3c741abe034e 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -100,12 +100,12 @@ done
 check "ip netns exec $ns1 ./pm_nl_ctl get 9" "id 9 flags signal 10.0.1.9" "hard addr limit"
 check "ip netns exec $ns1 ./pm_nl_ctl get 10" "" "above hard addr limit"
 
-for i in `seq 9 256`; do
+ip netns exec $ns1 ./pm_nl_ctl del 9
+for i in `seq 10 255`; do
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9 id $i
 	ip netns exec $ns1 ./pm_nl_ctl del $i
-	ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9 id $((i+1))
 done
 check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags  10.0.1.1
-id 2 flags  10.0.0.9
 id 3 flags signal,backup 10.0.1.3
 id 4 flags signal 10.0.1.4
 id 5 flags signal 10.0.1.5
-- 
cgit v1.2.3


From 2d121c9a882a93d5b229fc13deb10036a1b35967 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Tue, 30 Mar 2021 17:08:55 -0700
Subject: selftests: mptcp: add addr argument for del_addr

For the id 0 address, different MPTCP connections could be using
different IP addresses for id 0.

This patch added an extra argument IP address for del_addr when
using id 0.

Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 34 ++++++++++++++++++++++++---
 1 file changed, 31 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
index 7b4167f3f9a2..115decfdc1ef 100644
--- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -26,7 +26,7 @@ static void syntax(char *argv[])
 {
 	fprintf(stderr, "%s add|get|set|del|flush|dump|accept [<args>]\n", argv[0]);
 	fprintf(stderr, "\tadd [flags signal|subflow|backup] [id <nr>] [dev <name>] <ip>\n");
-	fprintf(stderr, "\tdel <id>\n");
+	fprintf(stderr, "\tdel <id> [<ip>]\n");
 	fprintf(stderr, "\tget <id>\n");
 	fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n");
 	fprintf(stderr, "\tflush\n");
@@ -301,6 +301,7 @@ int del_addr(int fd, int pm_family, int argc, char *argv[])
 		  1024];
 	struct rtattr *rta, *nest;
 	struct nlmsghdr *nh;
+	u_int16_t family;
 	int nest_start;
 	u_int8_t id;
 	int off = 0;
@@ -310,11 +311,14 @@ int del_addr(int fd, int pm_family, int argc, char *argv[])
 	off = init_genl_req(data, pm_family, MPTCP_PM_CMD_DEL_ADDR,
 			    MPTCP_PM_VER);
 
-	/* the only argument is the address id */
-	if (argc != 3)
+	/* the only argument is the address id (nonzero) */
+	if (argc != 3 && argc != 4)
 		syntax(argv);
 
 	id = atoi(argv[2]);
+	/* zero id with the IP address */
+	if (!id && argc != 4)
+		syntax(argv);
 
 	nest_start = off;
 	nest = (void *)(data + off);
@@ -328,6 +332,30 @@ int del_addr(int fd, int pm_family, int argc, char *argv[])
 	rta->rta_len = RTA_LENGTH(1);
 	memcpy(RTA_DATA(rta), &id, 1);
 	off += NLMSG_ALIGN(rta->rta_len);
+
+	if (!id) {
+		/* addr data */
+		rta = (void *)(data + off);
+		if (inet_pton(AF_INET, argv[3], RTA_DATA(rta))) {
+			family = AF_INET;
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4;
+			rta->rta_len = RTA_LENGTH(4);
+		} else if (inet_pton(AF_INET6, argv[3], RTA_DATA(rta))) {
+			family = AF_INET6;
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6;
+			rta->rta_len = RTA_LENGTH(16);
+		} else {
+			error(1, errno, "can't parse ip %s", argv[3]);
+		}
+		off += NLMSG_ALIGN(rta->rta_len);
+
+		/* family */
+		rta = (void *)(data + off);
+		rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY;
+		rta->rta_len = RTA_LENGTH(2);
+		memcpy(RTA_DATA(rta), &family, 2);
+		off += NLMSG_ALIGN(rta->rta_len);
+	}
 	nest->rta_len = off - nest_start;
 
 	do_nl_req(fd, nh, off, 0);
-- 
cgit v1.2.3


From 5e287fe761495eb669b5e2543919bd5124edecf1 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Tue, 30 Mar 2021 17:08:56 -0700
Subject: selftests: mptcp: remove id 0 address testcases

This patch added the testcases for removing the id 0 subflow and the id 0
address.

In do_transfer, use the removing addresses number '9' for deleting the id
0 address.

Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 35 +++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 679de3abaf34..d2273b88e72c 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -294,9 +294,12 @@ do_transfer()
 					let id+=1
 				done
 			fi
-		else
+		elif [ $rm_nr_ns1 -eq 8 ]; then
 			sleep 1
 			ip netns exec ${listener_ns} ./pm_nl_ctl flush
+		elif [ $rm_nr_ns1 -eq 9 ]; then
+			sleep 1
+			ip netns exec ${listener_ns} ./pm_nl_ctl del 0 ${connect_addr}
 		fi
 	fi
 
@@ -333,9 +336,18 @@ do_transfer()
 					let id+=1
 				done
 			fi
-		else
+		elif [ $rm_nr_ns2 -eq 8 ]; then
 			sleep 1
 			ip netns exec ${connector_ns} ./pm_nl_ctl flush
+		elif [ $rm_nr_ns2 -eq 9 ]; then
+			local addr
+			if is_v6 "${connect_addr}"; then
+				addr="dead:beef:1::2"
+			else
+				addr="10.0.1.2"
+			fi
+			sleep 1
+			ip netns exec ${connector_ns} ./pm_nl_ctl del 0 $addr
 		fi
 	fi
 
@@ -988,6 +1000,25 @@ remove_tests()
 	chk_join_nr "flush invalid addresses" 1 1 1
 	chk_add_nr 3 3
 	chk_rm_nr 3 1 invert
+
+	# remove id 0 subflow
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+	run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow
+	chk_join_nr "remove id 0 subflow" 1 1 1
+	chk_rm_nr 1 1
+
+	# remove id 0 address
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+	run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow
+	chk_join_nr "remove id 0 address" 1 1 1
+	chk_add_nr 1 1
+	chk_rm_nr 1 1 invert
 }
 
 add_tests()
-- 
cgit v1.2.3


From 63f8af0fc34197a276674fa0d4d865aeff1f0172 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@kernel.org>
Date: Tue, 23 Mar 2021 01:47:52 +0000
Subject: selftests/bpf: Add an option for a debug shell in vmtest.sh

The newly introduced -s command line option starts an interactive shell.
If a command is specified, the shell is started after the command
finishes executing. It's useful to have a shell especially when
debugging failing tests or developing new tests.

Since the user may terminate the VM forcefully, an extra "sync" is added
after the execution of the command to persist any logs from the command
into the log file.

Signed-off-by: KP Singh <kpsingh@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210323014752.3198283-1-kpsingh@kernel.org
---
 tools/testing/selftests/bpf/vmtest.sh | 39 +++++++++++++++++++++++++----------
 1 file changed, 28 insertions(+), 11 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 22554894db99..8889b3f55236 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -24,15 +24,15 @@ EXIT_STATUS_FILE="${LOG_FILE_BASE}.exit_status"
 usage()
 {
 	cat <<EOF
-Usage: $0 [-i] [-d <output_dir>] -- [<command>]
+Usage: $0 [-i] [-s] [-d <output_dir>] -- [<command>]
 
 <command> is the command you would normally run when you are in
 tools/testing/selftests/bpf. e.g:
 
 	$0 -- ./test_progs -t test_lsm
 
-If no command is specified, "${DEFAULT_COMMAND}" will be run by
-default.
+If no command is specified and a debug shell (-s) is not requested,
+"${DEFAULT_COMMAND}" will be run by default.
 
 If you build your kernel using KBUILD_OUTPUT= or O= options, these
 can be passed as environment variables to the script:
@@ -49,6 +49,9 @@ Options:
 	-d)		Update the output directory (default: ${OUTPUT_DIR})
 	-j)		Number of jobs for compilation, similar to -j in make
 			(default: ${NUM_COMPILE_JOBS})
+	-s)		Instead of powering off the VM, start an interactive
+			shell. If <command> is specified, the shell runs after
+			the command finishes executing
 EOF
 }
 
@@ -149,6 +152,7 @@ update_init_script()
 	local init_script_dir="${OUTPUT_DIR}/${MOUNT_DIR}/etc/rcS.d"
 	local init_script="${init_script_dir}/S50-startup"
 	local command="$1"
+	local exit_command="$2"
 
 	mount_image
 
@@ -162,9 +166,10 @@ EOF
 
 	fi
 
-	sudo bash -c "cat >${init_script}" <<EOF
-#!/bin/bash
+	sudo bash -c "echo '#!/bin/bash' > ${init_script}"
 
+	if [[ "${command}" != "" ]]; then
+		sudo bash -c "cat >>${init_script}" <<EOF
 # Have a default value in the exit status file
 # incase the VM is forcefully stopped.
 echo "130" > "/root/${EXIT_STATUS_FILE}"
@@ -175,9 +180,12 @@ echo "130" > "/root/${EXIT_STATUS_FILE}"
 	stdbuf -oL -eL ${command}
 	echo "\$?" > "/root/${EXIT_STATUS_FILE}"
 } 2>&1 | tee "/root/${LOG_FILE}"
-poweroff -f
+# Ensure that the logs are written to disk
+sync
 EOF
+	fi
 
+	sudo bash -c "echo ${exit_command} >> ${init_script}"
 	sudo chmod a+x "${init_script}"
 	unmount_image
 }
@@ -277,8 +285,10 @@ main()
 	local kernel_bzimage="${kernel_checkout}/${X86_BZIMAGE}"
 	local command="${DEFAULT_COMMAND}"
 	local update_image="no"
+	local exit_command="poweroff -f"
+	local debug_shell="no"
 
-	while getopts 'hkid:j:' opt; do
+	while getopts 'hskid:j:' opt; do
 		case ${opt} in
 		i)
 			update_image="yes"
@@ -289,6 +299,11 @@ main()
 		j)
 			NUM_COMPILE_JOBS="$OPTARG"
 			;;
+		s)
+			command=""
+			debug_shell="yes"
+			exit_command="bash"
+			;;
 		h)
 			usage
 			exit 0
@@ -307,7 +322,7 @@ main()
 	done
 	shift $((OPTIND -1))
 
-	if [[ $# -eq 0 ]]; then
+	if [[ $# -eq 0  && "${debug_shell}" == "no" ]]; then
 		echo "No command specified, will run ${DEFAULT_COMMAND} in the vm"
 	else
 		command="$@"
@@ -355,10 +370,12 @@ main()
 	fi
 
 	update_selftests "${kernel_checkout}" "${make_command}"
-	update_init_script "${command}"
+	update_init_script "${command}" "${exit_command}"
 	run_vm "${kernel_bzimage}"
-	copy_logs
-	echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}"
+	if [[ "${command}" != "" ]]; then
+		copy_logs
+		echo "Logs saved in ${OUTPUT_DIR}/${LOG_FILE}"
+	fi
 }
 
 catch()
-- 
cgit v1.2.3


From 1da07e5db3564789eb598bc772ea50b547194691 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 29 Mar 2021 20:59:54 -0700
Subject: selftests: ethtool: add a netdevsim FEC test

Test FEC settings, iterate over configs.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/netdevsim/ethtool-common.sh        |   5 +-
 .../selftests/drivers/net/netdevsim/ethtool-fec.sh | 110 +++++++++++++++++++++
 2 files changed, 114 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
index 9f64d5c7107b..7ca1f030d209 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
@@ -24,8 +24,11 @@ function check {
     local code=$1
     local str=$2
     local exp_str=$3
+    local exp_fail=$4
 
-    if [ $code -ne 0 ]; then
+    [ -z "$exp_fail" ] && cop="-ne" || cop="-eq"
+
+    if [ $code $cop 0 ]; then
 	((num_errors++))
 	return
     fi
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
new file mode 100755
index 000000000000..0c56746e9ce0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
@@ -0,0 +1,110 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+NSIM_NETDEV=$(make_netdev)
+[ a$ETHTOOL == a ] && ETHTOOL=ethtool
+
+set -o pipefail
+
+# netdevsim starts out with None/None
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: None
+Active FEC encoding: None"
+
+# Test Auto
+$ETHTOOL --set-fec $NSIM_NETDEV encoding auto
+check $?
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: Auto
+Active FEC encoding: Off"
+
+# Test case in-sensitivity
+for o in off Off OFF; do
+    $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
+    check $?
+    s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+    check $? "$s" "Configured FEC encodings: Off
+Active FEC encoding: Off"
+done
+
+for o in BaseR baser BAser; do
+    $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
+    check $?
+    s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+    check $? "$s" "Configured FEC encodings: BaseR
+Active FEC encoding: BaseR"
+done
+
+for o in llrs rs; do
+    $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
+    check $?
+    s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+    check $? "$s" "Configured FEC encodings: ${o^^}
+Active FEC encoding: ${o^^}"
+done
+
+# Test mutliple bits
+$ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs
+check $?
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: RS LLRS
+Active FEC encoding: LLRS"
+
+$ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto
+check $?
+s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
+check $? "$s" "Configured FEC encodings: Auto Off RS
+Active FEC encoding: RS"
+
+# Make sure other link modes are rejected
+$ETHTOOL --set-fec $NSIM_NETDEV encoding FIBRE 2>/dev/null
+check $? '' '' 1
+
+$ETHTOOL --set-fec $NSIM_NETDEV encoding bla-bla-bla 2>/dev/null
+check $? '' '' 1
+
+# Try JSON
+$ETHTOOL --json --show-fec $NSIM_NETDEV | jq empty >>/dev/null 2>&1
+if [ $? -eq 0 ]; then
+    $ETHTOOL --set-fec $NSIM_NETDEV encoding auto
+    check $?
+
+    s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].config[]')
+    check $? "$s" '"Auto"'
+    s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].active[]')
+    check $? "$s" '"Off"'
+
+    $ETHTOOL --set-fec $NSIM_NETDEV encoding auto RS
+    check $?
+
+    s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].config[]')
+    check $? "$s" '"Auto"
+"RS"'
+    s=$($ETHTOOL --json --show-fec $NSIM_NETDEV | jq '.[].active[]')
+    check $? "$s" '"RS"'
+fi
+
+# Test error injection
+echo 11 > $NSIM_DEV_DFS/ethtool/get_err
+
+$ETHTOOL --show-fec $NSIM_NETDEV >>/dev/null 2>&1
+check $? '' '' 1
+
+echo 0 > $NSIM_DEV_DFS/ethtool/get_err
+echo 11 > $NSIM_DEV_DFS/ethtool/set_err
+
+$ETHTOOL --show-fec $NSIM_NETDEV  >>/dev/null 2>&1
+check $?
+
+$ETHTOOL --set-fec $NSIM_NETDEV encoding RS 2>/dev/null
+check $? '' '' 1
+
+if [ $num_errors -eq 0 ]; then
+    echo "PASSED all $((num_passes)) checks"
+    exit 0
+else
+    echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+    exit 1
+fi
-- 
cgit v1.2.3


From 040806343bb4ef6365166eae666ced8a91b95321 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Thu, 1 Apr 2021 00:40:20 +0000
Subject: selftests/net: so_txtime multi-host support

SO_TXTIME hardware offload requires testing across devices, either
between machines or separate network namespaces.

Split up SO_TXTIME test into tx and rx modes, so traffic can be
sent from one process to another. Create a veth-pair on different
namespaces and bind each process to an end point via [-S]ource and
[-D]estination parameters. Optional start [-t]ime parameter can be
passed to synchronize the test across the hosts (with synchorinzed
clocks).

Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/so_txtime.c  | 247 +++++++++++++++++++++++--------
 tools/testing/selftests/net/so_txtime.sh |  97 +++++++++---
 2 files changed, 259 insertions(+), 85 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c
index b4cca382d125..59067f64b775 100644
--- a/tools/testing/selftests/net/so_txtime.c
+++ b/tools/testing/selftests/net/so_txtime.c
@@ -2,9 +2,12 @@
 /*
  * 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.
+ * Takes a stream of { payload, delivery time }[], to be sent across two
+ * processes. Start this program on two separate network namespaces or
+ * connected hosts, one instance in transmit mode and the other in receive
+ * mode using the '-r' option. Receiver will compare arrival timestamps to
+ * the expected stream. Sender will read transmit timestamps from the error
+ * queue. The streams can differ due to out-of-order delivery and drops.
  */
 
 #define _GNU_SOURCE
@@ -28,14 +31,17 @@
 #include <sys/types.h>
 #include <time.h>
 #include <unistd.h>
+#include <poll.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	= 4000;
+static uint64_t	cfg_start_time_ns;
+static int	cfg_mark;
+static bool	cfg_rx;
 
 static uint64_t glob_tstart;
+static uint64_t tdeliver_max;
 
 /* encode one timed transmission (of a 1B payload) */
 struct timed_send {
@@ -44,18 +50,21 @@ struct timed_send {
 };
 
 #define MAX_NUM_PKT	8
-static struct timed_send cfg_in[MAX_NUM_PKT];
-static struct timed_send cfg_out[MAX_NUM_PKT];
+static struct timed_send cfg_buf[MAX_NUM_PKT];
 static int cfg_num_pkt;
 
 static int cfg_errq_level;
 static int cfg_errq_type;
 
-static uint64_t gettime_ns(void)
+static struct sockaddr_storage cfg_dst_addr;
+static struct sockaddr_storage cfg_src_addr;
+static socklen_t cfg_alen;
+
+static uint64_t gettime_ns(clockid_t clock)
 {
 	struct timespec ts;
 
-	if (clock_gettime(cfg_clockid, &ts))
+	if (clock_gettime(clock, &ts))
 		error(1, errno, "gettime");
 
 	return ts.tv_sec * (1000ULL * 1000 * 1000) + ts.tv_nsec;
@@ -75,6 +84,8 @@ static void do_send_one(int fdt, struct timed_send *ts)
 
 	msg.msg_iov = &iov;
 	msg.msg_iovlen = 1;
+	msg.msg_name = (struct sockaddr *)&cfg_dst_addr;
+	msg.msg_namelen = cfg_alen;
 
 	if (ts->delay_us >= 0) {
 		memset(control, 0, sizeof(control));
@@ -82,6 +93,8 @@ static void do_send_one(int fdt, struct timed_send *ts)
 		msg.msg_controllen = sizeof(control);
 
 		tdeliver = glob_tstart + ts->delay_us * 1000;
+		tdeliver_max = tdeliver_max > tdeliver ?
+			       tdeliver_max : tdeliver;
 
 		cm = CMSG_FIRSTHDR(&msg);
 		cm->cmsg_level = SOL_SOCKET;
@@ -98,7 +111,7 @@ static void do_send_one(int fdt, struct timed_send *ts)
 
 }
 
-static bool do_recv_one(int fdr, struct timed_send *ts)
+static void do_recv_one(int fdr, struct timed_send *ts)
 {
 	int64_t tstop, texpect;
 	char rbuf[2];
@@ -106,13 +119,13 @@ static bool do_recv_one(int fdr, struct timed_send *ts)
 
 	ret = recv(fdr, rbuf, sizeof(rbuf), 0);
 	if (ret == -1 && errno == EAGAIN)
-		return true;
+		error(1, EAGAIN, "recv: timeout");
 	if (ret == -1)
 		error(1, errno, "read");
 	if (ret != 1)
 		error(1, 0, "read: %dB", ret);
 
-	tstop = (gettime_ns() - glob_tstart) / 1000;
+	tstop = (gettime_ns(cfg_clockid) - glob_tstart) / 1000;
 	texpect = ts->delay_us >= 0 ? ts->delay_us : 0;
 
 	fprintf(stderr, "payload:%c delay:%lld expected:%lld (us)\n",
@@ -123,8 +136,6 @@ static bool do_recv_one(int fdr, struct timed_send *ts)
 
 	if (llabs(tstop - texpect) > cfg_variance_us)
 		error(1, 0, "exceeds variance (%d us)", cfg_variance_us);
-
-	return false;
 }
 
 static void do_recv_verify_empty(int fdr)
@@ -137,18 +148,18 @@ static void do_recv_verify_empty(int fdr)
 		error(1, 0, "recv: not empty as expected (%d, %d)", ret, errno);
 }
 
-static void do_recv_errqueue_timeout(int fdt)
+static int do_recv_errqueue_timeout(int fdt)
 {
 	char control[CMSG_SPACE(sizeof(struct sock_extended_err)) +
 		     CMSG_SPACE(sizeof(struct sockaddr_in6))] = {0};
 	char data[sizeof(struct ethhdr) + sizeof(struct ipv6hdr) +
 		  sizeof(struct udphdr) + 1];
 	struct sock_extended_err *err;
+	int ret, num_tstamp = 0;
 	struct msghdr msg = {0};
 	struct iovec iov = {0};
 	struct cmsghdr *cm;
 	int64_t tstamp = 0;
-	int ret;
 
 	iov.iov_base = data;
 	iov.iov_len = sizeof(data);
@@ -206,9 +217,47 @@ static void do_recv_errqueue_timeout(int fdt)
 
 		msg.msg_flags = 0;
 		msg.msg_controllen = sizeof(control);
+		num_tstamp++;
 	}
 
-	error(1, 0, "recv: timeout");
+	return num_tstamp;
+}
+
+static void recv_errqueue_msgs(int fdt)
+{
+	struct pollfd pfd = { .fd = fdt, .events = POLLERR };
+	const int timeout_ms = 10;
+	int ret, num_tstamp = 0;
+
+	do {
+		ret = poll(&pfd, 1, timeout_ms);
+		if (ret == -1)
+			error(1, errno, "poll");
+
+		if (ret && (pfd.revents & POLLERR))
+			num_tstamp += do_recv_errqueue_timeout(fdt);
+
+		if (num_tstamp == cfg_num_pkt)
+			break;
+
+	} while (gettime_ns(cfg_clockid) < tdeliver_max);
+}
+
+static void start_time_wait(void)
+{
+	uint64_t now;
+	int err;
+
+	if (!cfg_start_time_ns)
+		return;
+
+	now = gettime_ns(CLOCK_REALTIME);
+	if (cfg_start_time_ns < now)
+		return;
+
+	err = usleep((cfg_start_time_ns - now) / 1000);
+	if (err)
+		error(1, errno, "usleep");
 }
 
 static void setsockopt_txtime(int fd)
@@ -245,6 +294,10 @@ static int setup_tx(struct sockaddr *addr, socklen_t alen)
 
 	setsockopt_txtime(fd);
 
+	if (cfg_mark &&
+	    setsockopt(fd, SOL_SOCKET, SO_MARK, &cfg_mark, sizeof(cfg_mark)))
+		error(1, errno, "setsockopt mark");
+
 	return fd;
 }
 
@@ -266,31 +319,70 @@ static int setup_rx(struct sockaddr *addr, socklen_t alen)
 	return fd;
 }
 
-static void do_test(struct sockaddr *addr, socklen_t alen)
+static void do_test_tx(struct sockaddr *addr, socklen_t alen)
 {
-	int fdt, fdr, i;
+	int fdt, 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();
+	start_time_wait();
+	glob_tstart = gettime_ns(cfg_clockid);
 
 	for (i = 0; i < cfg_num_pkt; i++)
-		do_send_one(fdt, &cfg_in[i]);
+		do_send_one(fdt, &cfg_buf[i]);
+
+	recv_errqueue_msgs(fdt);
+
+	if (close(fdt))
+		error(1, errno, "close t");
+}
+
+static void do_test_rx(struct sockaddr *addr, socklen_t alen)
+{
+	int fdr, i;
+
+	fdr = setup_rx(addr, alen);
+
+	start_time_wait();
+	glob_tstart = gettime_ns(cfg_clockid);
+
 	for (i = 0; i < cfg_num_pkt; i++)
-		if (do_recv_one(fdr, &cfg_out[i]))
-			do_recv_errqueue_timeout(fdt);
+		do_recv_one(fdr, &cfg_buf[i]);
 
 	do_recv_verify_empty(fdr);
 
 	if (close(fdr))
 		error(1, errno, "close r");
-	if (close(fdt))
-		error(1, errno, "close t");
+}
+
+static void setup_sockaddr(int domain, const char *str_addr,
+			   struct sockaddr_storage *sockaddr)
+{
+	struct sockaddr_in6 *addr6 = (void *) sockaddr;
+	struct sockaddr_in *addr4 = (void *) sockaddr;
+
+	switch (domain) {
+	case PF_INET:
+		memset(addr4, 0, sizeof(*addr4));
+		addr4->sin_family = AF_INET;
+		addr4->sin_port = htons(cfg_port);
+		if (str_addr &&
+		    inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+			error(1, 0, "ipv4 parse error: %s", str_addr);
+		break;
+	case PF_INET6:
+		memset(addr6, 0, sizeof(*addr6));
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_port = htons(cfg_port);
+		if (str_addr &&
+		    inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+			error(1, 0, "ipv6 parse error: %s", str_addr);
+		break;
+	}
 }
 
 static int parse_io(const char *optarg, struct timed_send *array)
@@ -323,17 +415,46 @@ static int parse_io(const char *optarg, struct timed_send *array)
 	return aoff / 2;
 }
 
+static void usage(const char *progname)
+{
+	fprintf(stderr, "\nUsage: %s [options] <payload>\n"
+			"Options:\n"
+			"  -4            only IPv4\n"
+			"  -6            only IPv6\n"
+			"  -c <clock>    monotonic (default) or tai\n"
+			"  -D <addr>     destination IP address (server)\n"
+			"  -S <addr>     source IP address (client)\n"
+			"  -r            run rx mode\n"
+			"  -t <nsec>     start time (UTC nanoseconds)\n"
+			"  -m <mark>     socket mark\n"
+			"\n",
+			progname);
+	exit(1);
+}
+
 static void parse_opts(int argc, char **argv)
 {
-	int c, ilen, olen;
+	char *daddr = NULL, *saddr = NULL;
+	int domain = PF_UNSPEC;
+	int c;
 
-	while ((c = getopt(argc, argv, "46c:")) != -1) {
+	while ((c = getopt(argc, argv, "46c:S:D:rt:m:")) != -1) {
 		switch (c) {
 		case '4':
-			cfg_do_ipv4 = true;
+			if (domain != PF_UNSPEC)
+				error(1, 0, "Pass one of -4 or -6");
+			domain = PF_INET;
+			cfg_alen = sizeof(struct sockaddr_in);
+			cfg_errq_level = SOL_IP;
+			cfg_errq_type = IP_RECVERR;
 			break;
 		case '6':
-			cfg_do_ipv6 = true;
+			if (domain != PF_UNSPEC)
+				error(1, 0, "Pass one of -4 or -6");
+			domain = PF_INET6;
+			cfg_alen = sizeof(struct sockaddr_in6);
+			cfg_errq_level = SOL_IPV6;
+			cfg_errq_type = IPV6_RECVERR;
 			break;
 		case 'c':
 			if (!strcmp(optarg, "tai"))
@@ -344,50 +465,50 @@ static void parse_opts(int argc, char **argv)
 			else
 				error(1, 0, "unknown clock id %s", optarg);
 			break;
+		case 'S':
+			saddr = optarg;
+			break;
+		case 'D':
+			daddr = optarg;
+			break;
+		case 'r':
+			cfg_rx = true;
+			break;
+		case 't':
+			cfg_start_time_ns = strtol(optarg, NULL, 0);
+			break;
+		case 'm':
+			cfg_mark = strtol(optarg, NULL, 0);
+			break;
 		default:
-			error(1, 0, "parse error at %d", optind);
+			usage(argv[0]);
 		}
 	}
 
-	if (argc - optind != 2)
-		error(1, 0, "Usage: %s [-46] -c <clock> <in> <out>", argv[0]);
+	if (argc - optind != 1)
+		usage(argv[0]);
+
+	if (domain == PF_UNSPEC)
+		error(1, 0, "Pass one of -4 or -6");
+	if (!daddr)
+		error(1, 0, "-D <server addr> required\n");
+	if (!cfg_rx && !saddr)
+		error(1, 0, "-S <client addr> required\n");
 
-	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;
+	setup_sockaddr(domain, daddr, &cfg_dst_addr);
+	setup_sockaddr(domain, saddr, &cfg_src_addr);
+
+	cfg_num_pkt = parse_io(argv[optind], cfg_buf);
 }
 
 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;
-
-		cfg_errq_level = SOL_IPV6;
-		cfg_errq_type = IPV6_RECVERR;
-
-		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);
-
-		cfg_errq_level = SOL_IP;
-		cfg_errq_type = IP_RECVERR;
-
-		do_test((void *)&addr4, sizeof(addr4));
-	}
+	if (cfg_rx)
+		do_test_rx((void *)&cfg_dst_addr, cfg_alen);
+	else
+		do_test_tx((void *)&cfg_src_addr, cfg_alen);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh
index 3f7800eaecb1..3f06f4d286a9 100755
--- a/tools/testing/selftests/net/so_txtime.sh
+++ b/tools/testing/selftests/net/so_txtime.sh
@@ -3,32 +3,85 @@
 #
 # Regression tests for the SO_TXTIME interface
 
-# Run in network namespace
-if [[ $# -eq 0 ]]; then
-	if ! ./in_netns.sh $0 __subprocess; then
-		# test is time sensitive, can be flaky
-		echo "test failed: retry once"
-		./in_netns.sh $0 __subprocess
+set -e
+
+readonly DEV="veth0"
+readonly BIN="./so_txtime"
+
+readonly RAND="$(mktemp -u XXXXXX)"
+readonly NSPREFIX="ns-${RAND}"
+readonly NS1="${NSPREFIX}1"
+readonly NS2="${NSPREFIX}2"
+
+readonly SADDR4='192.168.1.1'
+readonly DADDR4='192.168.1.2'
+readonly SADDR6='fd::1'
+readonly DADDR6='fd::2'
+
+cleanup() {
+	ip netns del "${NS2}"
+	ip netns del "${NS1}"
+}
+
+trap cleanup EXIT
+
+# Create virtual ethernet pair between network namespaces
+ip netns add "${NS1}"
+ip netns add "${NS2}"
+
+ip link add "${DEV}" netns "${NS1}" type veth \
+  peer name "${DEV}" netns "${NS2}"
+
+# Bring the devices up
+ip -netns "${NS1}" link set "${DEV}" up
+ip -netns "${NS2}" link set "${DEV}" up
+
+# Set fixed MAC addresses on the devices
+ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02
+ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06
+
+# Add fixed IP addresses to the devices
+ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}"
+ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
+ip -netns "${NS1}" addr add       fd::1/64 dev "${DEV}" nodad
+ip -netns "${NS2}" addr add       fd::2/64 dev "${DEV}" nodad
+
+do_test() {
+	local readonly IP="$1"
+	local readonly CLOCK="$2"
+	local readonly TXARGS="$3"
+	local readonly RXARGS="$4"
+
+	if [[ "${IP}" == "4" ]]; then
+		local readonly SADDR="${SADDR4}"
+		local readonly DADDR="${DADDR4}"
+	elif [[ "${IP}" == "6" ]]; then
+		local readonly SADDR="${SADDR6}"
+		local readonly DADDR="${DADDR6}"
+	else
+		echo "Invalid IP version ${IP}"
+		exit 1
 	fi
 
-	exit $?
-fi
+	local readonly START="$(date +%s%N --date="+ 0.1 seconds")"
+	ip netns exec "${NS2}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${RXARGS}" -r &
+	ip netns exec "${NS1}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${TXARGS}"
+	wait "$!"
+}
 
-set -e
+ip netns exec "${NS1}" tc qdisc add dev "${DEV}" root fq
+do_test 4 mono a,-1 a,-1
+do_test 6 mono a,0 a,0
+do_test 6 mono a,10 a,10
+do_test 4 mono a,10,b,20 a,10,b,20
+do_test 6 mono a,20,b,10 b,20,a,20
 
-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 400000; 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
+if ip netns exec "${NS1}" tc qdisc replace dev "${DEV}" root etf clockid CLOCK_TAI delta 400000; then
+	! do_test 4 tai a,-1 a,-1
+	! do_test 6 tai a,0 a,0
+	do_test 6 tai a,10 a,10
+	do_test 4 tai a,10,b,20 a,10,b,20
+	do_test 6 tai a,20,b,10 b,10,a,20
 else
 	echo "tc ($(tc -V)) does not support qdisc etf. skipping"
 fi
-- 
cgit v1.2.3


From d6378af615275435ce6e390a538c980ac19b6659 Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Tue, 30 Mar 2021 19:32:36 -0700
Subject: selftests/bpf: Add a test case for udp sockmap

Add a test case to ensure redirection between two UDP sockets work.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-16-xiyou.wangcong@gmail.com
---
 .../selftests/bpf/prog_tests/sockmap_listen.c      | 136 +++++++++++++++++++++
 .../selftests/bpf/progs/test_sockmap_listen.c      |  22 ++++
 2 files changed, 158 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index c26e6bf05e49..648d9ae898d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1603,6 +1603,141 @@ static void test_reuseport(struct test_sockmap_listen *skel,
 	}
 }
 
+static void udp_redir_to_connected(int family, int sotype, int sock_mapfd,
+				   int verd_mapfd, enum redir_mode mode)
+{
+	const char *log_prefix = redir_mode_str(mode);
+	struct sockaddr_storage addr;
+	int c0, c1, p0, p1;
+	unsigned int pass;
+	socklen_t len;
+	int err, n;
+	u64 value;
+	u32 key;
+	char b;
+
+	zero_verdict_count(verd_mapfd);
+
+	p0 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+	if (p0 < 0)
+		return;
+	len = sizeof(addr);
+	err = xgetsockname(p0, sockaddr(&addr), &len);
+	if (err)
+		goto close_peer0;
+
+	c0 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+	if (c0 < 0)
+		goto close_peer0;
+	err = xconnect(c0, sockaddr(&addr), len);
+	if (err)
+		goto close_cli0;
+	err = xgetsockname(c0, sockaddr(&addr), &len);
+	if (err)
+		goto close_cli0;
+	err = xconnect(p0, sockaddr(&addr), len);
+	if (err)
+		goto close_cli0;
+
+	p1 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+	if (p1 < 0)
+		goto close_cli0;
+	err = xgetsockname(p1, sockaddr(&addr), &len);
+	if (err)
+		goto close_cli0;
+
+	c1 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+	if (c1 < 0)
+		goto close_peer1;
+	err = xconnect(c1, sockaddr(&addr), len);
+	if (err)
+		goto close_cli1;
+	err = xgetsockname(c1, sockaddr(&addr), &len);
+	if (err)
+		goto close_cli1;
+	err = xconnect(p1, sockaddr(&addr), len);
+	if (err)
+		goto close_cli1;
+
+	key = 0;
+	value = p0;
+	err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+	if (err)
+		goto close_cli1;
+
+	key = 1;
+	value = p1;
+	err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+	if (err)
+		goto close_cli1;
+
+	n = write(c1, "a", 1);
+	if (n < 0)
+		FAIL_ERRNO("%s: write", log_prefix);
+	if (n == 0)
+		FAIL("%s: incomplete write", log_prefix);
+	if (n < 1)
+		goto close_cli1;
+
+	key = SK_PASS;
+	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+	if (err)
+		goto close_cli1;
+	if (pass != 1)
+		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+	if (n < 0)
+		FAIL_ERRNO("%s: read", log_prefix);
+	if (n == 0)
+		FAIL("%s: incomplete read", log_prefix);
+
+close_cli1:
+	xclose(c1);
+close_peer1:
+	xclose(p1);
+close_cli0:
+	xclose(c0);
+close_peer0:
+	xclose(p0);
+}
+
+static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
+				       struct bpf_map *inner_map, int family)
+{
+	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+	int sock_map = bpf_map__fd(inner_map);
+	int err;
+
+	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
+	if (err)
+		return;
+
+	skel->bss->test_ingress = false;
+	udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+			       REDIR_EGRESS);
+	skel->bss->test_ingress = true;
+	udp_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+			       REDIR_INGRESS);
+
+	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
+			   int family)
+{
+	const char *family_name, *map_name;
+	char s[MAX_TEST_NAME];
+
+	family_name = family_str(family);
+	map_name = map_type_str(map);
+	snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
+	if (!test__start_subtest(s))
+		return;
+	udp_skb_redir_to_connected(skel, map, family);
+}
+
 static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 		      int family)
 {
@@ -1611,6 +1746,7 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 	test_redir(skel, map, family, SOCK_STREAM);
 	test_reuseport(skel, map, family, SOCK_STREAM);
 	test_reuseport(skel, map, family, SOCK_DGRAM);
+	test_udp_redir(skel, map, family);
 }
 
 void test_sockmap_listen(void)
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index fa221141e9c1..a39eba9f5201 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -29,6 +29,7 @@ struct {
 } verdict_map SEC(".maps");
 
 static volatile bool test_sockmap; /* toggled by user-space */
+static volatile bool test_ingress; /* toggled by user-space */
 
 SEC("sk_skb/stream_parser")
 int prog_stream_parser(struct __sk_buff *skb)
@@ -55,6 +56,27 @@ int prog_stream_verdict(struct __sk_buff *skb)
 	return verdict;
 }
 
+SEC("sk_skb/skb_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	unsigned int *count;
+	__u32 zero = 0;
+	int verdict;
+
+	if (test_sockmap)
+		verdict = bpf_sk_redirect_map(skb, &sock_map, zero,
+					      test_ingress ? BPF_F_INGRESS : 0);
+	else
+		verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero,
+					       test_ingress ? BPF_F_INGRESS : 0);
+
+	count = bpf_map_lookup_elem(&verdict_map, &verdict);
+	if (count)
+		(*count)++;
+
+	return verdict;
+}
+
 SEC("sk_msg")
 int prog_msg_verdict(struct sk_msg_md *msg)
 {
-- 
cgit v1.2.3


From 8d7cb74f2ccb5486ab8c631a8fcdc7621bbbc42c Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Tue, 30 Mar 2021 19:32:37 -0700
Subject: selftests/bpf: Add a test case for loading BPF_SK_SKB_VERDICT

This adds a test case to ensure BPF_SK_SKB_VERDICT and
BPF_SK_STREAM_VERDICT will never be attached at the same time.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-17-xiyou.wangcong@gmail.com
---
 .../selftests/bpf/prog_tests/sockmap_basic.c       | 40 ++++++++++++++++++++++
 .../bpf/progs/test_sockmap_skb_verdict_attach.c    | 18 ++++++++++
 2 files changed, 58 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index b8b48cac2ac3..ab77596b64e3 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -7,6 +7,7 @@
 #include "test_skmsg_load_helpers.skel.h"
 #include "test_sockmap_update.skel.h"
 #include "test_sockmap_invalid_update.skel.h"
+#include "test_sockmap_skb_verdict_attach.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
@@ -281,6 +282,39 @@ out:
 	bpf_iter_sockmap__destroy(skel);
 }
 
+static void test_sockmap_skb_verdict_attach(enum bpf_attach_type first,
+					    enum bpf_attach_type second)
+{
+	struct test_sockmap_skb_verdict_attach *skel;
+	int err, map, verdict;
+
+	skel = test_sockmap_skb_verdict_attach__open_and_load();
+	if (CHECK_FAIL(!skel)) {
+		perror("test_sockmap_skb_verdict_attach__open_and_load");
+		return;
+	}
+
+	verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	map = bpf_map__fd(skel->maps.sock_map);
+
+	err = bpf_prog_attach(verdict, map, first, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach");
+		goto out;
+	}
+
+	err = bpf_prog_attach(verdict, map, second, 0);
+	assert(err == -1 && errno == EBUSY);
+
+	err = bpf_prog_detach2(verdict, map, first);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_detach2");
+		goto out;
+	}
+out:
+	test_sockmap_skb_verdict_attach__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -301,4 +335,10 @@ void test_sockmap_basic(void)
 		test_sockmap_copy(BPF_MAP_TYPE_SOCKMAP);
 	if (test__start_subtest("sockhash copy"))
 		test_sockmap_copy(BPF_MAP_TYPE_SOCKHASH);
+	if (test__start_subtest("sockmap skb_verdict attach")) {
+		test_sockmap_skb_verdict_attach(BPF_SK_SKB_VERDICT,
+						BPF_SK_SKB_STREAM_VERDICT);
+		test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT,
+						BPF_SK_SKB_VERDICT);
+	}
 }
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
new file mode 100644
index 000000000000..2d31f66e4f23
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} sock_map SEC(".maps");
+
+SEC("sk_skb/skb_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	return SK_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 5888a61cb4e00695075bbacfd86f3fa73af00413 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Thu, 1 Apr 2021 16:19:45 -0700
Subject: selftests: mptcp: launch mptcp_connect with timeout

'mptcp_connect' already has a timeout for poll() but in some cases, it
is not enough.

With "timeout" tool, we will force the command to fail if it doesn't
finish on time. Thanks to that, the script will continue and display
details about the current state before marking the test as failed.
Displaying this state is very important to be able to understand the
issue. Best to have our CI reporting the issue than just "the test
hanged".

Note that in mptcp_connect.sh, we were using a long timeout to validate
the fact we cannot create a socket if a sysctl is set. We don't need
this timeout.

In diag.sh, we want to send signals to mptcp_connect instances that have
been started in the netns. But we cannot send this signal to 'timeout'
otherwise that will stop the timeout and messages telling us SIGUSR1 has
been received will be printed. Instead of trying to find the right PID
and storing them in an array, we can simply use the output of
'ip netns pids' which is all the PIDs we want to send signal to.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/160
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/diag.sh          | 55 ++++++++++++++--------
 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 15 ++++--
 tools/testing/selftests/net/mptcp/mptcp_join.sh    | 22 ++++++---
 tools/testing/selftests/net/mptcp/simult_flows.sh  | 13 +++--
 4 files changed, 72 insertions(+), 33 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 39edce4f541c..2674ba20d524 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -5,8 +5,9 @@ rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
 ns="ns1-$rndh"
 ksft_skip=4
 test_cnt=1
+timeout_poll=100
+timeout_test=$((timeout_poll * 2 + 1))
 ret=0
-pids=()
 
 flush_pids()
 {
@@ -14,18 +15,14 @@ flush_pids()
 	# give it some time
 	sleep 1.1
 
-	for pid in ${pids[@]}; do
-		[ -d /proc/$pid ] && kill -SIGUSR1 $pid >/dev/null 2>&1
-	done
-	pids=()
+	ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null
 }
 
 cleanup()
 {
+	ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null
+
 	ip netns del $ns
-	for pid in ${pids[@]}; do
-		[ -d /proc/$pid ] && kill -9 $pid >/dev/null 2>&1
-	done
 }
 
 ip -Version > /dev/null 2>&1
@@ -79,39 +76,57 @@ trap cleanup EXIT
 ip netns add $ns
 ip -n $ns link set dev lo up
 
-echo "a" | ip netns exec $ns ./mptcp_connect -p 10000 -l 0.0.0.0 -t 100 >/dev/null &
+echo "a" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10000 -l -t ${timeout_poll} \
+				0.0.0.0 >/dev/null &
 sleep 0.1
-pids[0]=$!
 chk_msk_nr 0 "no msk on netns creation"
 
-echo "b" | ip netns exec $ns ./mptcp_connect -p 10000 127.0.0.1 -j -t 100 >/dev/null &
+echo "b" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10000 -j -t ${timeout_poll} \
+				127.0.0.1 >/dev/null &
 sleep 0.1
-pids[1]=$!
 chk_msk_nr 2 "after MPC handshake "
 chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
 flush_pids
 
 
-echo "a" | ip netns exec $ns ./mptcp_connect -p 10001 -s TCP -l 0.0.0.0 -t 100 >/dev/null &
-pids[0]=$!
+echo "a" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
+				0.0.0.0 >/dev/null &
 sleep 0.1
-echo "b" | ip netns exec $ns ./mptcp_connect -p 10001 127.0.0.1 -j -t 100 >/dev/null &
-pids[1]=$!
+echo "b" | \
+	timeout ${timeout_test} \
+		ip netns exec $ns \
+			./mptcp_connect -p 10001 -j -t ${timeout_poll} \
+				127.0.0.1 >/dev/null &
 sleep 0.1
 chk_msk_fallback_nr 1 "check fallback"
 flush_pids
 
 NR_CLIENTS=100
 for I in `seq 1 $NR_CLIENTS`; do
-	echo "a" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) -l 0.0.0.0 -t 100 -w 10 >/dev/null  &
-	pids[$((I*2))]=$!
+	echo "a" | \
+		timeout ${timeout_test} \
+			ip netns exec $ns \
+				./mptcp_connect -p $((I+10001)) -l -w 10 \
+					-t ${timeout_poll} 0.0.0.0 >/dev/null &
 done
 sleep 0.1
 
 for I in `seq 1 $NR_CLIENTS`; do
-	echo "b" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) 127.0.0.1 -t 100 -w 10 >/dev/null &
-	pids[$((I*2 + 1))]=$!
+	echo "b" | \
+		timeout ${timeout_test} \
+			ip netns exec $ns \
+				./mptcp_connect -p $((I+10001)) -w 10 \
+					-t ${timeout_poll} 127.0.0.1 >/dev/null &
 done
 sleep 1.5
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 10a030b53b23..65b3b983efc2 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -11,7 +11,8 @@ cin=""
 cout=""
 ksft_skip=4
 capture=false
-timeout=30
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
 ipv6=true
 ethtool_random_on=true
 tc_delay="$((RANDOM%50))"
@@ -273,7 +274,7 @@ check_mptcp_disabled()
 	ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0
 
 	local err=0
-	LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -t $timeout -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \
+	LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \
 		grep -q "^socket: Protocol not available$" && err=1
 	ip netns delete ${disabled_ns}
 
@@ -430,14 +431,20 @@ do_transfer()
 	local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
 	local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv")
 
-	ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" &
+	timeout ${timeout_test} \
+		ip netns exec ${listener_ns} \
+			./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \
+				$extra_args $local_addr < "$sin" > "$sout" &
 	local spid=$!
 
 	wait_local_port_listen "${listener_ns}" "${port}"
 
 	local start
 	start=$(date +%s%3N)
-	ip netns exec ${connector_ns} ./mptcp_connect -t $timeout -p $port -s ${cl_proto} $extra_args $connect_addr < "$cin" > "$cout" &
+	timeout ${timeout_test} \
+		ip netns exec ${connector_ns} \
+			./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
+				$extra_args $connect_addr < "$cin" > "$cout" &
 	local cpid=$!
 
 	wait $cpid
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index d2273b88e72c..56ffdad01526 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -8,7 +8,8 @@ cin=""
 cinsent=""
 cout=""
 ksft_skip=4
-timeout=30
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
 mptcp_connect=""
 capture=0
 do_all_tests=1
@@ -247,17 +248,26 @@ do_transfer()
 		local_addr="0.0.0.0"
 	fi
 
-	ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port \
-		-s ${srv_proto} ${local_addr} < "$sin" > "$sout" &
+	timeout ${timeout_test} \
+		ip netns exec ${listener_ns} \
+			$mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \
+				${local_addr} < "$sin" > "$sout" &
 	spid=$!
 
 	sleep 1
 
 	if [ "$test_link_fail" -eq 0 ];then
-		ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+		timeout ${timeout_test} \
+			ip netns exec ${connector_ns} \
+				$mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
+					$connect_addr < "$cin" > "$cout" &
 	else
-		( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | tee "$cinsent" | \
-		ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr > "$cout" &
+		( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | \
+			tee "$cinsent" | \
+			timeout ${timeout_test} \
+				ip netns exec ${connector_ns} \
+					$mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
+						$connect_addr > "$cout" &
 	fi
 	cpid=$!
 
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index f039ee57eb3c..3aeef3bcb101 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -7,7 +7,8 @@ ns2="ns2-$rndh"
 ns3="ns3-$rndh"
 capture=false
 ksft_skip=4
-timeout=30
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
 test_cnt=1
 ret=0
 bail=0
@@ -157,14 +158,20 @@ do_transfer()
 		sleep 1
 	fi
 
-	ip netns exec ${ns3} ./mptcp_connect -jt $timeout -l -p $port 0.0.0.0 < "$sin" > "$sout" &
+	timeout ${timeout_test} \
+		ip netns exec ${ns3} \
+			./mptcp_connect -jt ${timeout_poll} -l -p $port \
+				0.0.0.0 < "$sin" > "$sout" &
 	local spid=$!
 
 	wait_local_port_listen "${ns3}" "${port}"
 
 	local start
 	start=$(date +%s%3N)
-	ip netns exec ${ns1} ./mptcp_connect -jt $timeout -p $port 10.0.3.3 < "$cin" > "$cout" &
+	timeout ${timeout_test} \
+		ip netns exec ${ns1} \
+			./mptcp_connect -jt ${timeout_poll} -p $port \
+				10.0.3.3 < "$cin" > "$cout" &
 	local cpid=$!
 
 	wait $cpid
-- 
cgit v1.2.3


From 76e5e27ca98748242ba7c1fc24f06c09002eee45 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Thu, 1 Apr 2021 16:19:46 -0700
Subject: selftests: mptcp: init nstat history

Not to be impacted by packets sent between sub-tests.

Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 65b3b983efc2..385cdc98aed8 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -426,6 +426,13 @@ do_transfer()
 		sleep 1
 	fi
 
+	NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
+		nstat -n
+	if [ ${listener_ns} != ${connector_ns} ]; then
+		NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \
+			nstat -n
+	fi
+
 	local stat_synrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX")
 	local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
 	local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
-- 
cgit v1.2.3


From c2a55e8fd80f1cd9a16a24a08f6df50fc20a65ed Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Thu, 1 Apr 2021 16:19:47 -0700
Subject: selftests: mptcp: dump more info on mpjoin errors

Very occasionally, MPTCP selftests fail. Yeah, I saw that at least once!

Here we provide more details in case of errors with mptcp_join.sh script
like it was done with mptcp_connect.sh, see
commit 767389c8dd55 ("selftests: mptcp: dump more info on errors")

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 56ffdad01526..abeb24b7f8ec 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -78,6 +78,7 @@ cleanup_partial()
 
 	for netns in "$ns1" "$ns2"; do
 		ip netns del $netns
+		rm -f /tmp/$netns.{nstat,out}
 	done
 }
 
@@ -233,6 +234,11 @@ do_transfer()
 		sleep 1
 	fi
 
+	NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
+		nstat -n
+	NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \
+		nstat -n
+
 	if [ $speed = "fast" ]; then
 		mptcp_connect="./mptcp_connect -j"
 	elif [ $speed = "slow" ]; then
@@ -383,12 +389,19 @@ do_transfer()
 	    kill $cappid
 	fi
 
+	NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
+		nstat | grep Tcp > /tmp/${listener_ns}.out
+	NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \
+		nstat | grep Tcp > /tmp/${connector_ns}.out
+
 	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
 		echo " client exit code $retc, server $rets" 1>&2
 		echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
-		ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port"
+		ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port"
+		cat /tmp/${listener_ns}.out
 		echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
-		ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
+		ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port"
+		cat /tmp/${connector_ns}.out
 
 		cat "$capout"
 		ret=1
-- 
cgit v1.2.3


From 007bdc12d4b466566784c1a39b9fb3985f875b3d Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 1 Apr 2021 15:25:56 -0700
Subject: bpf, selftests: test_maps generating unrecognized data section

With a relatively recent clang master branch test_map skips a section,

 libbpf: elf: skipping unrecognized data section(5) .rodata.str1.1

the cause is some pointless strings from bpf_printks in the BPF program
loaded during testing. After just removing the prints to fix above error
Daniel points out the program is a bit pointless and could be simply the
empty program returning SK_PASS.

Here we do just that and return simply SK_PASS. This program is used with
test_maps selftests to test insert/remove of a program into the sockmap
and sockhash maps. Its not testing actual functionality of the TCP
sockmap programs, these are tested from test_sockmap. So we shouldn't
lose in test coverage and fix above warnings. This original test was
added before test_sockmap existed and has been copied around ever since,
clean it up now.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/161731595664.74613.1603087410166945302.stgit@john-XPS-13-9370
---
 tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'tools/testing')

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 fdb4bf4408fa..eeaf6e75c9a2 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
@@ -8,18 +8,6 @@ int _version SEC("version") = 1;
 SEC("sk_msg1")
 int bpf_prog1(struct sk_msg_md *msg)
 {
-	void *data_end = (void *)(long) msg->data_end;
-	void *data = (void *)(long) msg->data;
-
-	char *d;
-
-	if (data + 8 > data_end)
-		return SK_DROP;
-
-	bpf_printk("data length %i\n", (__u64)msg->data_end - (__u64)msg->data);
-	d = (char *)data;
-	bpf_printk("hello sendmsg hook %i %i\n", d[0], d[1]);
-
 	return SK_PASS;
 }
 
-- 
cgit v1.2.3


From f73ea1eb4cce66376cc1dd94b4a083ffb9eeb123 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 2 Apr 2021 17:29:21 -0700
Subject: bpf: selftests: Specify CONFIG_DYNAMIC_FTRACE in the testing config

The tracing test and the recent kfunc call test require
CONFIG_DYNAMIC_FTRACE.  This patch adds it to the config file.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210403002921.3419721-1-kafai@fb.com
---
 tools/testing/selftests/bpf/config | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 37e1f303fc11..5192305159ec 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -44,3 +44,5 @@ CONFIG_SECURITYFS=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_READ_POLICY=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_DYNAMIC_FTRACE=y
-- 
cgit v1.2.3


From c3eaa5f667cb60ea23c1bbc59e83c4f71de18e48 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Tue, 6 Apr 2021 17:16:03 -0700
Subject: selftests: mptcp: add the net device name testcase

This patch added a new testcase for setting the net device name. In it,
pass the net device name to pm_nl_ctl to set the ifindex field of struct
mptcp_pm_addr_entry.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index abeb24b7f8ec..fd99485cf2a4 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -777,6 +777,14 @@ subflows_tests()
 	ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
 	run_tests $ns1 $ns2 10.0.1.1
 	chk_join_nr "multiple subflows, limited by server" 2 2 1
+
+	# single subflow, dev
+	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow dev ns2eth3
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_join_nr "single subflow, dev" 1 1 1
 }
 
 signal_address_tests()
-- 
cgit v1.2.3


From 79749ae19de6863d0748419d413b231b0d57e28a Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Wed, 7 Apr 2021 18:46:42 +0300
Subject: tc-testing: add simple action test to verify batch add cleanup

Verify cleanup of failed actions batch add where second action in batch
fails after successful init of first action.

Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/simple.json        | 30 ++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
index e15f708b0fa4..d5bcbb919dcc 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -175,5 +175,35 @@
         "teardown": [
             "$TC actions flush action simple"
         ]
+    },
+    {
+        "id": "8d07",
+        "name": "Verify cleanup of failed actions batch add",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"2\" index 2",
+            [
+                "$TC actions add action simple sdata \"1\" index 1 action simple sdata \"2\" index 2",
+                255
+            ],
+            "$TC actions flush action simple"
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"2\" index 2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <2>.*index 2 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 652e3124c3ee60d9770e070afab0e0a862e9bfd7 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Wed, 7 Apr 2021 18:46:43 +0300
Subject: tc-testing: add simple action test to verify batch change cleanup

Verify cleanup of failed actions batch change where second action in batch
fails after successful init of first action.

Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/simple.json        | 29 ++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
index d5bcbb919dcc..e0c5f060ccb9 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -205,5 +205,34 @@
         "teardown": [
             "$TC actions flush action simple"
         ]
+    },
+    {
+        "id": "a68a",
+        "name": "Verify cleanup of failed actions batch change",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            [
+                "$TC actions change action simple sdata \"1\" index 1 action simple sdata \"2\" goto chain 42 index 2",
+                255
+            ],
+            "$TC actions flush action simple"
+        ],
+        "cmdUnderTest": "$TC actions add action simple sdata \"1\" index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <1>.*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
     }
 ]
-- 
cgit v1.2.3


From ff182bc572cec4ca757775bf2a33a3ce8611227a Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:02 +0300
Subject: selftests/bpf: test_progs/sockopt_sk: Remove version

As pointed by Andrii Nakryiko, _version is useless now, remove it.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-1-yauheni.kaliuta@redhat.com
---
 tools/testing/selftests/bpf/progs/sockopt_sk.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index d3597f81e6e9..978a68005966 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -6,7 +6,6 @@
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1;
 
 #ifndef PAGE_SIZE
 #define PAGE_SIZE 4096
-- 
cgit v1.2.3


From cad99cce133dd5377f22da1e75d7eb5c4b886d75 Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:03 +0300
Subject: selftests/bpf: test_progs/sockopt_sk: Convert to use BPF skeleton

Switch the test to use BPF skeleton to save some boilerplate and
make it easy to access bpf program bss segment.

The latter will be used to pass PAGE_SIZE from userspace since there
is no convenient way for bpf program to get it from inside of the
kernel.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-2-yauheni.kaliuta@redhat.com
---
 .../testing/selftests/bpf/prog_tests/sockopt_sk.c  | 65 ++++++----------------
 1 file changed, 17 insertions(+), 48 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index d5b44b135c00..7274b12abe17 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -3,6 +3,7 @@
 #include "cgroup_helpers.h"
 
 #include <linux/tcp.h>
+#include "sockopt_sk.skel.h"
 
 #ifndef SOL_TCP
 #define SOL_TCP IPPROTO_TCP
@@ -191,60 +192,28 @@ err:
 	return -1;
 }
 
-static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
-{
-	enum bpf_attach_type attach_type;
-	enum bpf_prog_type prog_type;
-	struct bpf_program *prog;
-	int err;
-
-	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
-	if (err) {
-		log_err("Failed to deduct types for %s BPF program", title);
-		return -1;
-	}
-
-	prog = bpf_object__find_program_by_title(obj, title);
-	if (!prog) {
-		log_err("Failed to find %s BPF program", title);
-		return -1;
-	}
-
-	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
-			      attach_type, 0);
-	if (err) {
-		log_err("Failed to attach %s BPF program", title);
-		return -1;
-	}
-
-	return 0;
-}
-
 static void run_test(int cgroup_fd)
 {
-	struct bpf_prog_load_attr attr = {
-		.file = "./sockopt_sk.o",
-	};
-	struct bpf_object *obj;
-	int ignored;
-	int err;
-
-	err = bpf_prog_load_xattr(&attr, &obj, &ignored);
-	if (CHECK_FAIL(err))
-		return;
+	struct sockopt_sk *skel;
+
+	skel = sockopt_sk__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
 
-	err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt");
-	if (CHECK_FAIL(err))
-		goto close_bpf_object;
+	skel->links._setsockopt =
+		bpf_program__attach_cgroup(skel->progs._setsockopt, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links._setsockopt, "setsockopt_link"))
+		goto cleanup;
 
-	err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt");
-	if (CHECK_FAIL(err))
-		goto close_bpf_object;
+	skel->links._getsockopt =
+		bpf_program__attach_cgroup(skel->progs._getsockopt, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links._getsockopt, "getsockopt_link"))
+		goto cleanup;
 
-	CHECK_FAIL(getsetsockopt());
+	ASSERT_OK(getsetsockopt(), "getsetsockopt");
 
-close_bpf_object:
-	bpf_object__close(obj);
+cleanup:
+	sockopt_sk__destroy(skel);
 }
 
 void test_sockopt_sk(void)
-- 
cgit v1.2.3


From 361d32028c7d52d28d7f0562193a2f4a41d10351 Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:04 +0300
Subject: selftests/bpf: Pass page size from userspace in sockopt_sk

Since there is no convenient way for bpf program to get PAGE_SIZE
from inside of the kernel, pass the value from userspace.

Zero-initialize the variable in bpf prog, otherwise it will cause
problems on some versions of Clang.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-3-yauheni.kaliuta@redhat.com
---
 tools/testing/selftests/bpf/prog_tests/sockopt_sk.c |  2 ++
 tools/testing/selftests/bpf/progs/sockopt_sk.c      | 10 ++++------
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index 7274b12abe17..4b937e5dbaca 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -200,6 +200,8 @@ static void run_test(int cgroup_fd)
 	if (!ASSERT_OK_PTR(skel, "skel_load"))
 		goto cleanup;
 
+	skel->bss->page_size = getpagesize();
+
 	skel->links._setsockopt =
 		bpf_program__attach_cgroup(skel->progs._setsockopt, cgroup_fd);
 	if (!ASSERT_OK_PTR(skel->links._setsockopt, "setsockopt_link"))
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index 978a68005966..8acdb99b5959 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -7,9 +7,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-#ifndef PAGE_SIZE
-#define PAGE_SIZE 4096
-#endif
+int page_size = 0; /* userspace should set it */
 
 #ifndef SOL_TCP
 #define SOL_TCP IPPROTO_TCP
@@ -89,7 +87,7 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		 * program can only see the first PAGE_SIZE
 		 * bytes of data.
 		 */
-		if (optval_end - optval != PAGE_SIZE)
+		if (optval_end - optval != page_size)
 			return 0; /* EPERM, unexpected data size */
 
 		return 1;
@@ -160,7 +158,7 @@ int _setsockopt(struct bpf_sockopt *ctx)
 
 	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
 		/* Original optlen is larger than PAGE_SIZE. */
-		if (ctx->optlen != PAGE_SIZE * 2)
+		if (ctx->optlen != page_size * 2)
 			return 0; /* EPERM, unexpected data size */
 
 		if (optval + 1 > optval_end)
@@ -174,7 +172,7 @@ int _setsockopt(struct bpf_sockopt *ctx)
 		 * program can only see the first PAGE_SIZE
 		 * bytes of data.
 		 */
-		if (optval_end - optval != PAGE_SIZE)
+		if (optval_end - optval != page_size)
 			return 0; /* EPERM, unexpected data size */
 
 		return 1;
-- 
cgit v1.2.3


From 7a85e4dfa7f5d052ae5016e96f1ee426a8870e78 Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:05 +0300
Subject: selftests/bpf: Pass page size from userspace in map_ptr

Use ASSERT to check result but keep CHECK where format was used to
report error.

Use bpf_map__set_max_entries() to set map size dynamically from
userspace according to page size.

Zero-initialize the variable in bpf prog, otherwise it will cause
problems on some versions of Clang.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-4-yauheni.kaliuta@redhat.com
---
 tools/testing/selftests/bpf/prog_tests/map_ptr.c | 15 +++++++++++++--
 tools/testing/selftests/bpf/progs/map_ptr_kern.c |  4 ++--
 2 files changed, 15 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c
index c230a573c373..4972f92205c7 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_ptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c
@@ -12,11 +12,22 @@ void test_map_ptr(void)
 	__u32 duration = 0, retval;
 	char buf[128];
 	int err;
+	int page_size = getpagesize();
 
-	skel = map_ptr_kern__open_and_load();
-	if (CHECK(!skel, "skel_open_load", "open_load failed\n"))
+	skel = map_ptr_kern__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	err = bpf_map__set_max_entries(skel->maps.m_ringbuf, page_size);
+	if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
+		goto cleanup;
+
+	err = map_ptr_kern__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	skel->bss->page_size = page_size;
+
 	err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4,
 				sizeof(pkt_v4), buf, NULL, &retval, NULL);
 
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index d8850bc6a9f1..d1d304c980f0 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -12,6 +12,7 @@ _Static_assert(MAX_ENTRIES < LOOP_BOUND, "MAX_ENTRIES must be < LOOP_BOUND");
 
 enum bpf_map_type g_map_type = BPF_MAP_TYPE_UNSPEC;
 __u32 g_line = 0;
+int page_size = 0; /* userspace should set it */
 
 #define VERIFY_TYPE(type, func) ({	\
 	g_map_type = type;		\
@@ -635,7 +636,6 @@ struct bpf_ringbuf_map {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_RINGBUF);
-	__uint(max_entries, 1 << 12);
 } m_ringbuf SEC(".maps");
 
 static inline int check_ringbuf(void)
@@ -643,7 +643,7 @@ static inline int check_ringbuf(void)
 	struct bpf_ringbuf_map *ringbuf = (struct bpf_ringbuf_map *)&m_ringbuf;
 	struct bpf_map *map = (struct bpf_map *)&m_ringbuf;
 
-	VERIFY(check(&ringbuf->map, map, 0, 0, 1 << 12));
+	VERIFY(check(&ringbuf->map, map, 0, 0, page_size));
 
 	return 1;
 }
-- 
cgit v1.2.3


From 34090aaf256e469a39401cc04d5cd43275ccd97d Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:06 +0300
Subject: selftests/bpf: mmap: Use runtime page size

Replace hardcoded 4096 with runtime value in the userspace part of
the test and set bpf table sizes dynamically according to the value.

Do not switch to ASSERT macros, keep CHECK, for consistency with the
rest of the test. Can be a separate cleanup patch.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-5-yauheni.kaliuta@redhat.com
---
 tools/testing/selftests/bpf/prog_tests/mmap.c | 24 +++++++++++++++++++-----
 tools/testing/selftests/bpf/progs/test_mmap.c |  2 --
 2 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 9c3c5c0f068f..37b002ca1167 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -29,22 +29,36 @@ void test_mmap(void)
 	struct test_mmap *skel;
 	__u64 val = 0;
 
-	skel = test_mmap__open_and_load();
-	if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
+	skel = test_mmap__open();
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
 		return;
 
+	err = bpf_map__set_max_entries(skel->maps.rdonly_map, page_size);
+	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
+		goto cleanup;
+
+	/* at least 4 pages of data */
+	err = bpf_map__set_max_entries(skel->maps.data_map,
+				       4 * (page_size / sizeof(u64)));
+	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
+		goto cleanup;
+
+	err = test_mmap__load(skel);
+	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
+		goto cleanup;
+
 	bss_map = skel->maps.bss;
 	data_map = skel->maps.data_map;
 	data_map_fd = bpf_map__fd(data_map);
 
 	rdmap_fd = bpf_map__fd(skel->maps.rdonly_map);
-	tmp1 = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0);
+	tmp1 = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0);
 	if (CHECK(tmp1 != MAP_FAILED, "rdonly_write_mmap", "unexpected success\n")) {
-		munmap(tmp1, 4096);
+		munmap(tmp1, page_size);
 		goto cleanup;
 	}
 	/* now double-check if it's mmap()'able at all */
-	tmp1 = mmap(NULL, 4096, PROT_READ, MAP_SHARED, rdmap_fd, 0);
+	tmp1 = mmap(NULL, page_size, PROT_READ, MAP_SHARED, rdmap_fd, 0);
 	if (CHECK(tmp1 == MAP_FAILED, "rdonly_read_mmap", "failed: %d\n", errno))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c
index 4eb42cff5fe9..5a5cc19a15bf 100644
--- a/tools/testing/selftests/bpf/progs/test_mmap.c
+++ b/tools/testing/selftests/bpf/progs/test_mmap.c
@@ -9,7 +9,6 @@ char _license[] SEC("license") = "GPL";
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 4096);
 	__uint(map_flags, BPF_F_MMAPABLE | BPF_F_RDONLY_PROG);
 	__type(key, __u32);
 	__type(value, char);
@@ -17,7 +16,6 @@ struct {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 512 * 4); /* at least 4 pages of data */
 	__uint(map_flags, BPF_F_MMAPABLE);
 	__type(key, __u32);
 	__type(value, __u64);
-- 
cgit v1.2.3


From 23a65766066bb6e42a44e9097ddf79f72292a19f Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:07 +0300
Subject: selftests/bpf: ringbuf: Use runtime page size

Replace hardcoded 4096 with runtime value in the userspace part of
the test and set bpf table sizes dynamically according to the value.

Do not switch to ASSERT macros, keep CHECK, for consistency with the
rest of the test. Can be a separate cleanup patch.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-6-yauheni.kaliuta@redhat.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf.c | 17 +++++++++++++----
 tools/testing/selftests/bpf/progs/test_ringbuf.c |  1 -
 2 files changed, 13 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index fddbc5db5d6a..de78617f6550 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -87,11 +87,20 @@ void test_ringbuf(void)
 	pthread_t thread;
 	long bg_ret = -1;
 	int err, cnt;
+	int page_size = getpagesize();
 
-	skel = test_ringbuf__open_and_load();
-	if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+	skel = test_ringbuf__open();
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
 		return;
 
+	err = bpf_map__set_max_entries(skel->maps.ringbuf, page_size);
+	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
+		goto cleanup;
+
+	err = test_ringbuf__load(skel);
+	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
+		goto cleanup;
+
 	/* only trigger BPF program for current process */
 	skel->bss->pid = getpid();
 
@@ -110,9 +119,9 @@ void test_ringbuf(void)
 	CHECK(skel->bss->avail_data != 3 * rec_sz,
 	      "err_avail_size", "exp %ld, got %ld\n",
 	      3L * rec_sz, skel->bss->avail_data);
-	CHECK(skel->bss->ring_size != 4096,
+	CHECK(skel->bss->ring_size != page_size,
 	      "err_ring_size", "exp %ld, got %ld\n",
-	      4096L, skel->bss->ring_size);
+	      (long)page_size, skel->bss->ring_size);
 	CHECK(skel->bss->cons_pos != 0,
 	      "err_cons_pos", "exp %ld, got %ld\n",
 	      0L, skel->bss->cons_pos);
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c
index 8ba9959b036b..6b3f288b7c63 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c
@@ -15,7 +15,6 @@ struct sample {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_RINGBUF);
-	__uint(max_entries, 1 << 12);
 } ringbuf SEC(".maps");
 
 /* inputs */
-- 
cgit v1.2.3


From f3f4c23e1238783f3d719cfbda6c5e2fd03a48c4 Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:09 +0300
Subject: selftests/bpf: ringbuf_multi: Use runtime page size

Set bpf table sizes dynamically according to the runtime page size
value.

Do not switch to ASSERT macros, keep CHECK, for consistency with the
rest of the test. Can be a separate cleanup patch.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-8-yauheni.kaliuta@redhat.com
---
 .../selftests/bpf/prog_tests/ringbuf_multi.c       | 23 +++++++++++++++++++---
 .../selftests/bpf/progs/test_ringbuf_multi.c       |  1 -
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index d37161e59bb2..159de99621c7 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -41,13 +41,30 @@ static int process_sample(void *ctx, void *data, size_t len)
 void test_ringbuf_multi(void)
 {
 	struct test_ringbuf_multi *skel;
-	struct ring_buffer *ringbuf;
+	struct ring_buffer *ringbuf = NULL;
 	int err;
+	int page_size = getpagesize();
 
-	skel = test_ringbuf_multi__open_and_load();
-	if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+	skel = test_ringbuf_multi__open();
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
 		return;
 
+	err = bpf_map__set_max_entries(skel->maps.ringbuf1, page_size);
+	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
+		goto cleanup;
+
+	err = bpf_map__set_max_entries(skel->maps.ringbuf2, page_size);
+	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
+		goto cleanup;
+
+	err = bpf_map__set_max_entries(bpf_map__inner_map(skel->maps.ringbuf_arr), page_size);
+	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
+		goto cleanup;
+
+	err = test_ringbuf_multi__load(skel);
+	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
+		goto cleanup;
+
 	/* only trigger BPF program for current process */
 	skel->bss->pid = getpid();
 
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
index edf3b6953533..055c10b2ff80 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
@@ -15,7 +15,6 @@ struct sample {
 
 struct ringbuf_map {
 	__uint(type, BPF_MAP_TYPE_RINGBUF);
-	__uint(max_entries, 1 << 12);
 } ringbuf1 SEC(".maps"),
   ringbuf2 SEC(".maps");
 
-- 
cgit v1.2.3


From cfc0889cebccbc398a9d7a14e4e1b4724afe4bb3 Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Thu, 8 Apr 2021 09:13:10 +0300
Subject: selftests/bpf: ringbuf_multi: Test bpf_map__set_inner_map_fd

Test map__set_inner_map_fd() interaction with map-in-map
initialization. Use hashmap of maps just to make it different to
existing array of maps.

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210408061310.95877-9-yauheni.kaliuta@redhat.com
---
 tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c | 14 ++++++++++++++
 tools/testing/selftests/bpf/progs/test_ringbuf_multi.c | 11 +++++++++++
 2 files changed, 25 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index 159de99621c7..cef63e703924 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -44,6 +44,7 @@ void test_ringbuf_multi(void)
 	struct ring_buffer *ringbuf = NULL;
 	int err;
 	int page_size = getpagesize();
+	int proto_fd = -1;
 
 	skel = test_ringbuf_multi__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
@@ -61,10 +62,21 @@ void test_ringbuf_multi(void)
 	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
 		goto cleanup;
 
+	proto_fd = bpf_create_map(BPF_MAP_TYPE_RINGBUF, 0, 0, page_size, 0);
+	if (CHECK(proto_fd == -1, "bpf_create_map", "bpf_create_map failed\n"))
+		goto cleanup;
+
+	err = bpf_map__set_inner_map_fd(skel->maps.ringbuf_hash, proto_fd);
+	if (CHECK(err != 0, "bpf_map__set_inner_map_fd", "bpf_map__set_inner_map_fd failed\n"))
+		goto cleanup;
+
 	err = test_ringbuf_multi__load(skel);
 	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
 		goto cleanup;
 
+	close(proto_fd);
+	proto_fd = -1;
+
 	/* only trigger BPF program for current process */
 	skel->bss->pid = getpid();
 
@@ -114,6 +126,8 @@ void test_ringbuf_multi(void)
 	      2L, skel->bss->total);
 
 cleanup:
+	if (proto_fd >= 0)
+		close(proto_fd);
 	ring_buffer__free(ringbuf);
 	test_ringbuf_multi__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
index 055c10b2ff80..197b86546dca 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
@@ -30,6 +30,17 @@ struct {
 	},
 };
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__array(values, struct ringbuf_map);
+} ringbuf_hash SEC(".maps") = {
+	.values = {
+		[0] = &ringbuf1,
+	},
+};
+
 /* inputs */
 int pid = 0;
 int target_ring = 0;
-- 
cgit v1.2.3


From 1c3cadbe02420e6c85251c416a78a16f17761231 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 9 Apr 2021 13:04:40 +0200
Subject: self-tests: add veth tests

Add some basic veth tests, that verify the expected flags and
aggregation with different setups (default, xdp, etc...)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile |   1 +
 tools/testing/selftests/net/veth.sh  | 177 +++++++++++++++++++++++++++++++++++
 2 files changed, 178 insertions(+)
 create mode 100755 tools/testing/selftests/net/veth.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 2d71b283dde3..f4242a961088 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -24,6 +24,7 @@ TEST_PROGS += vrf_route_leaking.sh
 TEST_PROGS += bareudp.sh
 TEST_PROGS += unicast_extensions.sh
 TEST_PROGS += udpgro_fwd.sh
+TEST_PROGS += veth.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
new file mode 100755
index 000000000000..2fedc0781ce8
--- /dev/null
+++ b/tools/testing/selftests/net/veth.sh
@@ -0,0 +1,177 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
+readonly BASE=`basename $STATS`
+readonly SRC=2
+readonly DST=1
+readonly DST_NAT=100
+readonly NS_SRC=$BASE$SRC
+readonly NS_DST=$BASE$DST
+
+# "baremetal" network used for raw UDP traffic
+readonly BM_NET_V4=192.168.1.
+readonly BM_NET_V6=2001:db8::
+
+readonly NPROCS=`nproc`
+ret=0
+
+cleanup() {
+	local ns
+	local -r jobs="$(jobs -p)"
+	[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+	rm -f $STATS
+
+	for ns in $NS_SRC $NS_DST; do
+		ip netns del $ns 2>/dev/null
+	done
+}
+
+trap cleanup EXIT
+
+create_ns() {
+	local ns
+
+	for ns in $NS_SRC $NS_DST; do
+		ip netns add $ns
+		ip -n $ns link set dev lo up
+	done
+
+	ip link add name veth$SRC type veth peer name veth$DST
+
+	for ns in $SRC $DST; do
+		ip link set dev veth$ns netns $BASE$ns up
+		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
+		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
+	done
+	echo "#kernel" > $BASE
+	chmod go-rw $BASE
+}
+
+__chk_flag() {
+	local msg="$1"
+	local target=$2
+	local expected=$3
+	local flagname=$4
+
+	local flag=`ip netns exec $BASE$target ethtool -k veth$target |\
+		    grep $flagname | awk '{print $2}'`
+
+	printf "%-60s" "$msg"
+	if [ "$flag" = "$expected" ]; then
+		echo " ok "
+	else
+		echo " fail - expected $expected found $flag"
+		ret=1
+	fi
+}
+
+chk_gro_flag() {
+	__chk_flag "$1" $2 $3 generic-receive-offload
+}
+
+chk_tso_flag() {
+	__chk_flag "$1" $2 $3 tcp-segmentation-offload
+}
+
+chk_gro() {
+	local msg="$1"
+	local expected=$2
+
+	ip netns exec $BASE$SRC ping -qc 1 $BM_NET_V4$DST >/dev/null
+	NSTAT_HISTORY=$STATS ip netns exec $NS_DST nstat -n
+
+	printf "%-60s" "$msg"
+	ip netns exec $BASE$DST ./udpgso_bench_rx -C 1000 -R 10 &
+	local spid=$!
+	sleep 0.1
+
+	ip netns exec $NS_SRC ./udpgso_bench_tx -4 -s 13000 -S 1300 -M 1 -D $BM_NET_V4$DST
+	local retc=$?
+	wait $spid
+	local rets=$?
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " fail client exit code $retc, server $rets"
+		ret=1
+		return
+	fi
+
+	local pkts=`NSTAT_HISTORY=$STATS ip netns exec $NS_DST nstat IpInReceives | \
+		    awk '{print $2}' | tail -n 1`
+	if [ "$pkts" = "$expected" ]; then
+		echo " ok "
+	else
+		echo " fail - got $pkts packets, expected $expected "
+		ret=1
+	fi
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+	echo "Missing xdp_dummy helper. Build bpf selftest first"
+	exit -1
+fi
+
+create_ns
+chk_gro_flag "default - gro flag" $SRC off
+chk_gro_flag "        - peer gro flag" $DST off
+chk_tso_flag "        - tso flag" $SRC on
+chk_tso_flag "        - peer tso flag" $DST on
+chk_gro "        - aggregation" 1
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+chk_gro "        - aggregation with TSO off" 10
+cleanup
+
+create_ns
+ip netns exec $NS_DST ethtool -K veth$DST gro on
+chk_gro_flag "with gro on - gro flag" $DST on
+chk_gro_flag "        - peer gro flag" $SRC off
+chk_tso_flag "        - tso flag" $SRC on
+chk_tso_flag "        - peer tso flag" $DST on
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+chk_gro "        - aggregation with TSO off" 1
+cleanup
+
+create_ns
+ip -n $NS_DST link set dev veth$DST down
+ip netns exec $NS_DST ethtool -K veth$DST gro on
+chk_gro_flag "with gro enabled on link down - gro flag" $DST on
+chk_gro_flag "        - peer gro flag" $SRC off
+chk_tso_flag "        - tso flag" $SRC on
+chk_tso_flag "        - peer tso flag" $DST on
+ip -n $NS_DST link set dev veth$DST up
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+chk_gro "        - aggregation with TSO off" 1
+cleanup
+
+create_ns
+ip -n $NS_DST link set dev veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+chk_gro_flag "with xdp attached - gro flag" $DST on
+chk_gro_flag "        - peer gro flag" $SRC off
+chk_tso_flag "        - tso flag" $SRC off
+chk_tso_flag "        - peer tso flag" $DST on
+ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+chk_gro "        - aggregation" 1
+
+
+ip -n $NS_DST link set dev veth$DST down
+ip -n $NS_SRC link set dev veth$SRC down
+chk_gro_flag "        - after dev off, flag" $DST on
+chk_gro_flag "        - peer flag" $SRC off
+
+ip netns exec $NS_DST ethtool -K veth$DST gro on
+ip -n $NS_DST link set dev veth$DST xdp off
+chk_gro_flag "        - after gro on xdp off, gro flag" $DST on
+chk_gro_flag "        - peer gro flag" $SRC off
+chk_tso_flag "        - tso flag" $SRC on
+chk_tso_flag "        - peer tso flag" $DST on
+ip -n $NS_DST link set dev veth$DST up
+ip -n $NS_SRC link set dev veth$SRC up
+chk_gro "        - aggregation" 1
+
+ip netns exec $NS_DST ethtool -K veth$DST gro off
+ip netns exec $NS_SRC ethtool -K veth$SRC tx-udp-segmentation off
+chk_gro "aggregation again with default and TSO off" 10
+
+exit $ret
-- 
cgit v1.2.3


From 463c2149ede72b696c42b0d6c5a03c061600d04c Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 13 Apr 2021 11:16:07 +0200
Subject: selftests/bpf: Add tests for target information in bpf_link info
 queries
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend the fexit_bpf2bpf test to check that the info for the bpf_link
returned by the kernel matches the expected values.

While we're updating the test, change existing uses of CHEC() to use the
much easier to read ASSERT_*() macros.

v2:
- Convert last CHECK() call and get rid of 'duration' var
- Split ASSERT_OK_PTR() checks to two separate if statements

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210413091607.58945-2-toke@redhat.com
---
 .../selftests/bpf/prog_tests/fexit_bpf2bpf.c       | 58 ++++++++++++++++------
 1 file changed, 44 insertions(+), 14 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 5c0448910426..63990842d20f 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -58,42 +58,73 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 				      test_cb cb)
 {
 	struct bpf_object *obj = NULL, *tgt_obj;
+	__u32 retval, tgt_prog_id, info_len;
+	struct bpf_prog_info prog_info = {};
 	struct bpf_program **prog = NULL;
 	struct bpf_link **link = NULL;
-	__u32 duration = 0, retval;
 	int err, tgt_fd, i;
+	struct btf *btf;
 
 	err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC,
 			    &tgt_obj, &tgt_fd);
-	if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
-		  target_obj_file, err, errno))
+	if (!ASSERT_OK(err, "tgt_prog_load"))
 		return;
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
 			    .attach_prog_fd = tgt_fd,
 			   );
 
+	info_len = sizeof(prog_info);
+	err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len);
+	if (!ASSERT_OK(err, "tgt_fd_get_info"))
+		goto close_prog;
+
+	tgt_prog_id = prog_info.id;
+	btf = bpf_object__btf(tgt_obj);
+
 	link = calloc(sizeof(struct bpf_link *), prog_cnt);
+	if (!ASSERT_OK_PTR(link, "link_ptr"))
+		goto close_prog;
+
 	prog = calloc(sizeof(struct bpf_program *), prog_cnt);
-	if (CHECK(!link || !prog, "alloc_memory", "failed to alloc memory"))
+	if (!ASSERT_OK_PTR(prog, "prog_ptr"))
 		goto close_prog;
 
 	obj = bpf_object__open_file(obj_file, &opts);
-	if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
-		  "failed to open %s: %ld\n", obj_file,
-		  PTR_ERR(obj)))
+	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		goto close_prog;
 
 	err = bpf_object__load(obj);
-	if (CHECK(err, "obj_load", "err %d\n", err))
+	if (!ASSERT_OK(err, "obj_load"))
 		goto close_prog;
 
 	for (i = 0; i < prog_cnt; i++) {
+		struct bpf_link_info link_info;
+		char *tgt_name;
+		__s32 btf_id;
+
+		tgt_name = strstr(prog_name[i], "/");
+		if (!ASSERT_OK_PTR(tgt_name, "tgt_name"))
+			goto close_prog;
+		btf_id = btf__find_by_name_kind(btf, tgt_name + 1, BTF_KIND_FUNC);
+
 		prog[i] = bpf_object__find_program_by_title(obj, prog_name[i]);
-		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name[i]))
+		if (!ASSERT_OK_PTR(prog[i], prog_name[i]))
 			goto close_prog;
+
 		link[i] = bpf_program__attach_trace(prog[i]);
-		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
+		if (!ASSERT_OK_PTR(link[i], "attach_trace"))
 			goto close_prog;
+
+		info_len = sizeof(link_info);
+		memset(&link_info, 0, sizeof(link_info));
+		err = bpf_obj_get_info_by_fd(bpf_link__fd(link[i]),
+					     &link_info, &info_len);
+		ASSERT_OK(err, "link_fd_get_info");
+		ASSERT_EQ(link_info.tracing.attach_type,
+			  bpf_program__get_expected_attach_type(prog[i]),
+			  "link_attach_type");
+		ASSERT_EQ(link_info.tracing.target_obj_id, tgt_prog_id, "link_tgt_obj_id");
+		ASSERT_EQ(link_info.tracing.target_btf_id, btf_id, "link_tgt_btf_id");
 	}
 
 	if (cb) {
@@ -106,10 +137,9 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 		goto close_prog;
 
 	err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6),
-				NULL, NULL, &retval, &duration);
-	CHECK(err || retval, "ipv6",
-	      "err %d errno %d retval %d duration %d\n",
-	      err, errno, retval, duration);
+				NULL, NULL, &retval, NULL);
+	ASSERT_OK(err, "prog_run");
+	ASSERT_EQ(retval, 0, "prog_run_ret");
 
 	if (check_data_map(obj, prog_cnt, false))
 		goto close_prog;
-- 
cgit v1.2.3


From 1969b3c60db675040ec0d1b09698807647aac7ed Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Wed, 14 Apr 2021 17:56:32 +0200
Subject: selftests/bpf: Fix the ASSERT_ERR_PTR macro

It is just missing a ';'. This macro is not used by any test yet.

Fixes: 22ba36351631 ("selftests/bpf: Move and extend ASSERT_xxx() testing macros")
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210414155632.737866-1-revest@chromium.org
---
 tools/testing/selftests/bpf/test_progs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index e87c8546230e..ee7e3b45182a 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -210,7 +210,7 @@ extern int test__join_cgroup(const char *path);
 #define ASSERT_ERR_PTR(ptr, name) ({					\
 	static int duration = 0;					\
 	const void *___res = (ptr);					\
-	bool ___ok = IS_ERR(___res)					\
+	bool ___ok = IS_ERR(___res);					\
 	CHECK(!___ok, (name), "unexpected pointer: %p\n", ___res);	\
 	___ok;								\
 })
-- 
cgit v1.2.3


From 069904ce318e0e15dc67f3c2829303237c5e912b Mon Sep 17 00:00:00 2001
From: zuoqilin <zuoqilin@yulong.com>
Date: Wed, 14 Apr 2021 22:16:39 +0800
Subject: tools/testing: Remove unused variable

Remove unused variable "ret2".

Signed-off-by: zuoqilin <zuoqilin@yulong.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210414141639.1446-1-zuoqilin1@163.com
---
 tools/testing/selftests/bpf/progs/test_tunnel_kern.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index ba6eadfec565..e7b673117436 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -396,7 +396,7 @@ int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
 SEC("geneve_set_tunnel")
 int _geneve_set_tunnel(struct __sk_buff *skb)
 {
-	int ret, ret2;
+	int ret;
 	struct bpf_tunnel_key key;
 	struct geneve_opt gopt;
 
-- 
cgit v1.2.3


From 26e6dd1072763cd5696b75994c03982dde952ad9 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 13 Apr 2021 08:34:13 -0700
Subject: selftests: Set CC to clang in lib.mk if LLVM is set

selftests/bpf/Makefile includes lib.mk. With the following command
  make -j60 LLVM=1 LLVM_IAS=1  <=== compile kernel
  make -j60 -C tools/testing/selftests/bpf LLVM=1 LLVM_IAS=1 V=1
some files are still compiled with gcc. This patch
fixed lib.mk issue which sets CC to gcc in all cases.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210413153413.3027426-1-yhs@fb.com
---
 tools/testing/selftests/lib.mk | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index a5ce26d548e4..9a41d8bb9ff1 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -1,6 +1,10 @@
 # This mimics the top-level Makefile. We do it explicitly here so that this
 # Makefile can operate with or without the kbuild infrastructure.
+ifneq ($(LLVM),)
+CC := clang
+else
 CC := $(CROSS_COMPILE)gcc
+endif
 
 ifeq (0,$(MAKELEVEL))
     ifeq ($(OUTPUT),)
-- 
cgit v1.2.3


From a22c0c81da644223d911466746ef414a786cb1c8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 13 Apr 2021 08:34:24 -0700
Subject: selftests/bpf: Fix test_cpp compilation failure with clang

With clang compiler:
  make -j60 LLVM=1 LLVM_IAS=1  <=== compile kernel
  make -j60 -C tools/testing/selftests/bpf LLVM=1 LLVM_IAS=1
the test_cpp build failed due to the failure:
  warning: treating 'c-header' input as 'c++-header' when in C++ mode, this behavior is deprecated [-Wdeprecated]
  clang-13: error: cannot specify -o when generating multiple output files

test_cpp compilation flag looks like:
  clang++ -g -Og -rdynamic -Wall -I<...> ... \
  -Dbpf_prog_load=bpf_prog_test_load -Dbpf_load_program=bpf_test_load_program \
  test_cpp.cpp <...>/test_core_extern.skel.h <...>/libbpf.a <...>/test_stub.o \
  -lcap -lelf -lz -lrt -lpthread -o <...>/test_cpp

The clang++ compiler complains the header file in the command line and
also failed the compilation due to this.
Let us remove the header file from the command line which is not intended
any way, and this fixed the compilation problem.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210413153424.3028986-1-yhs@fb.com
---
 tools/testing/selftests/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6448c626498f..dcc2dc1f2a86 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -481,7 +481,7 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
 # Make sure we are able to include and link libbpf against c++.
 $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(call msg,CXX,,$@)
-	$(Q)$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
+	$(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
 
 # Benchmark runner
 $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h
-- 
cgit v1.2.3


From ef9985893caf905b769fae8984780847e8527065 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 13 Apr 2021 08:34:29 -0700
Subject: selftests/bpf: Silence clang compilation warnings

With clang compiler:
  make -j60 LLVM=1 LLVM_IAS=1  <=== compile kernel
  make -j60 -C tools/testing/selftests/bpf LLVM=1 LLVM_IAS=1
Some linker flags are not used/effective for some binaries and
we have warnings like:
  warning: -lelf: 'linker' input unused [-Wunused-command-line-argument]

We also have warnings like:
  .../selftests/bpf/prog_tests/ns_current_pid_tgid.c:74:57: note: treat the string as an argument to avoid this
        if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
                                                               ^
                                                               "%s",
  .../selftests/bpf/test_progs.h:129:35: note: expanded from macro 'CHECK'
        _CHECK(condition, tag, duration, format)
                                         ^
  .../selftests/bpf/test_progs.h:108:21: note: expanded from macro '_CHECK'
                fprintf(stdout, ##format);                              \
                                  ^
The first warning can be silenced with clang option -Wno-unused-command-line-argument.
For the second warning, source codes are modified as suggested by the compiler
to silence the warning. Since gcc does not support the option
-Wno-unused-command-line-argument and the warning only happens with clang
compiler, the option -Wno-unused-command-line-argument is enabled only when
clang compiler is used.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210413153429.3029377-1-yhs@fb.com
---
 tools/testing/selftests/bpf/Makefile                         | 5 +++++
 tools/testing/selftests/bpf/prog_tests/fexit_sleep.c         | 4 ++--
 tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c | 4 ++--
 3 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index dcc2dc1f2a86..c45ae13b88a0 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -28,6 +28,11 @@ CFLAGS += -g -Og -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS)		\
 	  -Dbpf_load_program=bpf_test_load_program
 LDLIBS += -lcap -lelf -lz -lrt -lpthread
 
+# Silence some warnings when compiled with clang
+ifneq ($(LLVM),)
+CFLAGS += -Wno-unused-command-line-argument
+endif
+
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_verifier_log test_dev_cgroup \
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
index 6c4d42a2386f..ccc7e8a34ab6 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -39,7 +39,7 @@ void test_fexit_sleep(void)
 		goto cleanup;
 
 	cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
-	if (CHECK(cpid == -1, "clone", strerror(errno)))
+	if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
 		goto cleanup;
 
 	/* wait until first sys_nanosleep ends and second sys_nanosleep starts */
@@ -65,7 +65,7 @@ void test_fexit_sleep(void)
 	/* kill the thread to unwind sys_nanosleep stack through the trampoline */
 	kill(cpid, 9);
 
-	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
+	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", "%s\n", strerror(errno)))
 		goto cleanup;
 	if (CHECK(WEXITSTATUS(wstatus) != 0, "exitstatus", "failed"))
 		goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index 31a3114906e2..2535788e135f 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -68,10 +68,10 @@ static void test_ns_current_pid_tgid_new_ns(void)
 	cpid = clone(test_current_pid_tgid, child_stack + STACK_SIZE,
 		     CLONE_NEWPID | SIGCHLD, NULL);
 
-	if (CHECK(cpid == -1, "clone", strerror(errno)))
+	if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
 		return;
 
-	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
+	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", "%s\n", strerror(errno)))
 		return;
 
 	if (CHECK(WEXITSTATUS(wstatus) != 0, "newns_pidtgid", "failed"))
-- 
cgit v1.2.3


From dc65fe82fb07e610e03a9b05bd445f46f93175f5 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 15 Apr 2021 16:45:02 -0700
Subject: selftests: mptcp: add packet mark test case

Extend mptcp_connect tool with SO_MARK support (-M <value>) and
add a test case that checks that the packet mark gets copied to all
subflows.

This is done by only allowing packets with either skb->mark 1 or 2
via iptables.

DROP rule packet counter is checked; if its not zero, print an error
message and fail the test case.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/Makefile         |   2 +-
 tools/testing/selftests/net/mptcp/mptcp_connect.c  |  23 +-
 tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 276 +++++++++++++++++++++
 3 files changed, 299 insertions(+), 2 deletions(-)
 create mode 100755 tools/testing/selftests/net/mptcp/mptcp_sockopt.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 00bb158b4a5d..f1464f09b080 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -6,7 +6,7 @@ KSFT_KHDR_INSTALL := 1
 CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g  -I$(top_srcdir)/usr/include
 
 TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
-	      simult_flows.sh
+	      simult_flows.sh mptcp_sockopt.sh
 
 TEST_GEN_FILES = mptcp_connect pm_nl_ctl
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 69d89b5d666f..2f207cf33661 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -57,6 +57,7 @@ static bool cfg_join;
 static bool cfg_remove;
 static unsigned int cfg_do_w;
 static int cfg_wait;
+static uint32_t cfg_mark;
 
 static void die_usage(void)
 {
@@ -69,6 +70,7 @@ static void die_usage(void)
 	fprintf(stderr, "\t-p num -- use port num\n");
 	fprintf(stderr, "\t-s [MPTCP|TCP] -- use mptcp(default) or tcp sockets\n");
 	fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+write/sendfile\n");
+	fprintf(stderr, "\t-M mark -- set socket packet mark\n");
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
 	exit(1);
@@ -140,6 +142,17 @@ static void set_sndbuf(int fd, unsigned int size)
 	}
 }
 
+static void set_mark(int fd, uint32_t mark)
+{
+	int err;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (err) {
+		perror("set SO_MARK");
+		exit(1);
+	}
+}
+
 static int sock_listen_mptcp(const char * const listenaddr,
 			     const char * const port)
 {
@@ -248,6 +261,9 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			continue;
 		}
 
+		if (cfg_mark)
+			set_mark(sock, cfg_mark);
+
 		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
 			break; /* success */
 
@@ -830,7 +846,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -880,6 +896,9 @@ static void parse_opts(int argc, char **argv)
 		case 'w':
 			cfg_wait = atoi(optarg)*1000000;
 			break;
+		case 'M':
+			cfg_mark = strtol(optarg, NULL, 0);
+			break;
 		}
 	}
 
@@ -911,6 +930,8 @@ int main(int argc, char *argv[])
 			set_rcvbuf(fd, cfg_rcvbuf);
 		if (cfg_sndbuf)
 			set_sndbuf(fd, cfg_sndbuf);
+		if (cfg_mark)
+			set_mark(fd, cfg_mark);
 
 		return main_loop_s(fd);
 	}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
new file mode 100755
index 000000000000..2fa13946ac04
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -0,0 +1,276 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ret=0
+sin=""
+sout=""
+cin=""
+cout=""
+ksft_skip=4
+timeout_poll=30
+timeout_test=$((timeout_poll * 2 + 1))
+mptcp_connect=""
+do_all_tests=1
+
+add_mark_rules()
+{
+	local ns=$1
+	local m=$2
+
+	for t in iptables ip6tables; do
+		# just to debug: check we have multiple subflows connection requests
+		ip netns exec $ns $t -A OUTPUT -p tcp --syn -m mark --mark $m -j ACCEPT
+
+		# RST packets might be handled by a internal dummy socket
+		ip netns exec $ns $t -A OUTPUT -p tcp --tcp-flags RST RST -m mark --mark 0 -j ACCEPT
+
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark $m -j ACCEPT
+		ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark 0 -j DROP
+	done
+}
+
+init()
+{
+	rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
+
+	ns1="ns1-$rndh"
+	ns2="ns2-$rndh"
+
+	for netns in "$ns1" "$ns2";do
+		ip netns add $netns || exit $ksft_skip
+		ip -net $netns link set lo up
+		ip netns exec $netns sysctl -q net.mptcp.enabled=1
+		ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0
+		ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0
+	done
+
+	for i in `seq 1 4`; do
+		ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2"
+		ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i
+		ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad
+		ip -net "$ns1" link set ns1eth$i up
+
+		ip -net "$ns2" addr add 10.0.$i.2/24 dev ns2eth$i
+		ip -net "$ns2" addr add dead:beef:$i::2/64 dev ns2eth$i nodad
+		ip -net "$ns2" link set ns2eth$i up
+
+		# let $ns2 reach any $ns1 address from any interface
+		ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i
+
+		ip netns exec $ns1 ./pm_nl_ctl add 10.0.$i.1 flags signal
+		ip netns exec $ns1 ./pm_nl_ctl add dead:beef:$i::1 flags signal
+
+		ip netns exec $ns2 ./pm_nl_ctl add 10.0.$i.2 flags signal
+		ip netns exec $ns2 ./pm_nl_ctl add dead:beef:$i::2 flags signal
+	done
+
+	ip netns exec $ns1 ./pm_nl_ctl limits 8 8
+	ip netns exec $ns2 ./pm_nl_ctl limits 8 8
+
+	add_mark_rules $ns1 1
+	add_mark_rules $ns2 2
+}
+
+cleanup()
+{
+	for netns in "$ns1" "$ns2"; do
+		ip netns del $netns
+	done
+	rm -f "$cin" "$cout"
+	rm -f "$sin" "$sout"
+}
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+iptables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run all tests without iptables tool"
+	exit $ksft_skip
+fi
+
+ip6tables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run all tests without ip6tables tool"
+	exit $ksft_skip
+fi
+
+check_mark()
+{
+	local ns=$1
+	local af=$2
+
+	tables=iptables
+
+	if [ $af -eq 6 ];then
+		tables=ip6tables
+	fi
+
+	counters=$(ip netns exec $ns $tables -v -L OUTPUT | grep DROP)
+	values=${counters%DROP*}
+
+	for v in $values; do
+		if [ $v -ne 0 ]; then
+			echo "FAIL: got $tables $values in ns $ns , not 0 - not all expected packets marked" 1>&2
+			return 1
+		fi
+	done
+
+	return 0
+}
+
+print_file_err()
+{
+	ls -l "$1" 1>&2
+	echo "Trailing bytes are: "
+	tail -c 27 "$1"
+}
+
+check_transfer()
+{
+	in=$1
+	out=$2
+	what=$3
+
+	cmp "$in" "$out" > /dev/null 2>&1
+	if [ $? -ne 0 ] ;then
+		echo "[ FAIL ] $what does not match (in, out):"
+		print_file_err "$in"
+		print_file_err "$out"
+		ret=1
+
+		return 1
+	fi
+
+	return 0
+}
+
+# $1: IP address
+is_v6()
+{
+	[ -z "${1##*:*}" ]
+}
+
+do_transfer()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	cl_proto="$3"
+	srv_proto="$4"
+	connect_addr="$5"
+
+	port=12001
+
+	:> "$cout"
+	:> "$sout"
+
+	mptcp_connect="./mptcp_connect -r 20"
+
+	local local_addr
+	if is_v6 "${connect_addr}"; then
+		local_addr="::"
+	else
+		local_addr="0.0.0.0"
+	fi
+
+	timeout ${timeout_test} \
+		ip netns exec ${listener_ns} \
+			$mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} \
+				${local_addr} < "$sin" > "$sout" &
+	spid=$!
+
+	sleep 1
+
+	timeout ${timeout_test} \
+		ip netns exec ${connector_ns} \
+			$mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} \
+				$connect_addr < "$cin" > "$cout" &
+
+	cpid=$!
+
+	wait $cpid
+	retc=$?
+	wait $spid
+	rets=$?
+
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " client exit code $retc, server $rets" 1>&2
+		echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port"
+
+		echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2
+		ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port"
+
+		ret=1
+		return 1
+	fi
+
+	if [ $local_addr = "::" ];then
+		check_mark $listener_ns 6
+		check_mark $connector_ns 6
+	else
+		check_mark $listener_ns 4
+		check_mark $connector_ns 4
+	fi
+
+	check_transfer $cin $sout "file received by server"
+
+	rets=$?
+
+	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
+		return 0
+	fi
+
+	return 1
+}
+
+make_file()
+{
+	name=$1
+	who=$2
+	size=$3
+
+	dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
+	echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
+
+	echo "Created $name (size $size KB) containing data sent by $who"
+}
+
+run_tests()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	connect_addr="$3"
+	lret=0
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
+
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return
+	fi
+}
+
+sin=$(mktemp)
+sout=$(mktemp)
+cin=$(mktemp)
+cout=$(mktemp)
+init
+make_file "$cin" "client" 1
+make_file "$sin" "server" 1
+trap cleanup EXIT
+
+run_tests $ns1 $ns2 10.0.1.1
+run_tests $ns1 $ns2 dead:beef:1::1
+
+
+if [ $ret -eq 0 ];then
+	echo "PASS: all packets had packet mark set"
+fi
+
+exit $ret
-- 
cgit v1.2.3


From 8826218215de1aae9d89a6ea8d3786f224711334 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Apr 2021 11:20:33 +0300
Subject: selftests: fib_tests: Add test cases for interaction with mangling

Test that packets are correctly routed when netfilter mangling rules are
present.

Without previous patch:

 # ./fib_tests.sh -t ipv4_mangle

 IPv4 mangling tests
     TEST:     Connection with correct parameters                        [ OK ]
     TEST:     Connection with incorrect parameters                      [ OK ]
     TEST:     Connection with correct parameters - mangling             [FAIL]
     TEST:     Connection with correct parameters - no mangling          [ OK ]
     TEST:     Connection check - server side                            [FAIL]

 Tests passed:   3
 Tests failed:   2

 # ./fib_tests.sh -t ipv6_mangle

 IPv6 mangling tests
     TEST:     Connection with correct parameters                        [ OK ]
     TEST:     Connection with incorrect parameters                      [ OK ]
     TEST:     Connection with correct parameters - mangling             [FAIL]
     TEST:     Connection with correct parameters - no mangling          [ OK ]
     TEST:     Connection check - server side                            [FAIL]

 Tests passed:   3
 Tests failed:   2

With previous patch:

 # ./fib_tests.sh -t ipv4_mangle

 IPv4 mangling tests
     TEST:     Connection with correct parameters                        [ OK ]
     TEST:     Connection with incorrect parameters                      [ OK ]
     TEST:     Connection with correct parameters - mangling             [ OK ]
     TEST:     Connection with correct parameters - no mangling          [ OK ]
     TEST:     Connection check - server side                            [ OK ]

 Tests passed:   5
 Tests failed:   0

 # ./fib_tests.sh -t ipv6_mangle

 IPv6 mangling tests
     TEST:     Connection with correct parameters                        [ OK ]
     TEST:     Connection with incorrect parameters                      [ OK ]
     TEST:     Connection with correct parameters - mangling             [ OK ]
     TEST:     Connection with correct parameters - no mangling          [ OK ]
     TEST:     Connection check - server side                            [ OK ]

 Tests passed:   5
 Tests failed:   0

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/net/fib_tests.sh | 152 ++++++++++++++++++++++++++++++-
 1 file changed, 151 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 2b5707738609..76d9487fb03c 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,7 +9,7 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr"
+TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -1653,6 +1653,154 @@ ipv4_route_v6_gw_test()
 	route_cleanup
 }
 
+socat_check()
+{
+	if [ ! -x "$(command -v socat)" ]; then
+		echo "socat command not found. Skipping test"
+		return 1
+	fi
+
+	return 0
+}
+
+iptables_check()
+{
+	iptables -t mangle -L OUTPUT &> /dev/null
+	if [ $? -ne 0 ]; then
+		echo "iptables configuration not supported. Skipping test"
+		return 1
+	fi
+
+	return 0
+}
+
+ip6tables_check()
+{
+	ip6tables -t mangle -L OUTPUT &> /dev/null
+	if [ $? -ne 0 ]; then
+		echo "ip6tables configuration not supported. Skipping test"
+		return 1
+	fi
+
+	return 0
+}
+
+ipv4_mangle_test()
+{
+	local rc
+
+	echo
+	echo "IPv4 mangling tests"
+
+	socat_check || return 1
+	iptables_check || return 1
+
+	route_setup
+	sleep 2
+
+	local tmp_file=$(mktemp)
+	ip netns exec ns2 socat UDP4-LISTEN:54321,fork $tmp_file &
+
+	# Add a FIB rule and a route that will direct our connection to the
+	# listening server.
+	$IP rule add pref 100 ipproto udp sport 12345 dport 54321 table 123
+	$IP route add table 123 172.16.101.0/24 dev veth1
+
+	# Add an unreachable route to the main table that will block our
+	# connection in case the FIB rule is not hit.
+	$IP route add unreachable 172.16.101.2/32
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP4:172.16.101.2:54321,sourceport=12345"
+	log_test $? 0 "    Connection with correct parameters"
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP4:172.16.101.2:54321,sourceport=11111"
+	log_test $? 1 "    Connection with incorrect parameters"
+
+	# Add a mangling rule and make sure connection is still successful.
+	$NS_EXEC iptables -t mangle -A OUTPUT -j MARK --set-mark 1
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP4:172.16.101.2:54321,sourceport=12345"
+	log_test $? 0 "    Connection with correct parameters - mangling"
+
+	# Delete the mangling rule and make sure connection is still
+	# successful.
+	$NS_EXEC iptables -t mangle -D OUTPUT -j MARK --set-mark 1
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP4:172.16.101.2:54321,sourceport=12345"
+	log_test $? 0 "    Connection with correct parameters - no mangling"
+
+	# Verify connections were indeed successful on server side.
+	[[ $(cat $tmp_file | wc -l) -eq 3 ]]
+	log_test $? 0 "    Connection check - server side"
+
+	$IP route del unreachable 172.16.101.2/32
+	$IP route del table 123 172.16.101.0/24 dev veth1
+	$IP rule del pref 100
+
+	{ kill %% && wait %%; } 2>/dev/null
+	rm $tmp_file
+
+	route_cleanup
+}
+
+ipv6_mangle_test()
+{
+	local rc
+
+	echo
+	echo "IPv6 mangling tests"
+
+	socat_check || return 1
+	ip6tables_check || return 1
+
+	route_setup
+	sleep 2
+
+	local tmp_file=$(mktemp)
+	ip netns exec ns2 socat UDP6-LISTEN:54321,fork $tmp_file &
+
+	# Add a FIB rule and a route that will direct our connection to the
+	# listening server.
+	$IP -6 rule add pref 100 ipproto udp sport 12345 dport 54321 table 123
+	$IP -6 route add table 123 2001:db8:101::/64 dev veth1
+
+	# Add an unreachable route to the main table that will block our
+	# connection in case the FIB rule is not hit.
+	$IP -6 route add unreachable 2001:db8:101::2/128
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP6:[2001:db8:101::2]:54321,sourceport=12345"
+	log_test $? 0 "    Connection with correct parameters"
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP6:[2001:db8:101::2]:54321,sourceport=11111"
+	log_test $? 1 "    Connection with incorrect parameters"
+
+	# Add a mangling rule and make sure connection is still successful.
+	$NS_EXEC ip6tables -t mangle -A OUTPUT -j MARK --set-mark 1
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP6:[2001:db8:101::2]:54321,sourceport=12345"
+	log_test $? 0 "    Connection with correct parameters - mangling"
+
+	# Delete the mangling rule and make sure connection is still
+	# successful.
+	$NS_EXEC ip6tables -t mangle -D OUTPUT -j MARK --set-mark 1
+
+	run_cmd "echo a | $NS_EXEC socat STDIN UDP6:[2001:db8:101::2]:54321,sourceport=12345"
+	log_test $? 0 "    Connection with correct parameters - no mangling"
+
+	# Verify connections were indeed successful on server side.
+	[[ $(cat $tmp_file | wc -l) -eq 3 ]]
+	log_test $? 0 "    Connection check - server side"
+
+	$IP -6 route del unreachable 2001:db8:101::2/128
+	$IP -6 route del table 123 2001:db8:101::/64 dev veth1
+	$IP -6 rule del pref 100
+
+	{ kill %% && wait %%; } 2>/dev/null
+	rm $tmp_file
+
+	route_cleanup
+}
+
 ################################################################################
 # usage
 
@@ -1725,6 +1873,8 @@ do
 	ipv6_route_metrics)		ipv6_route_metrics_test;;
 	ipv4_route_metrics)		ipv4_route_metrics_test;;
 	ipv4_route_v6_gw)		ipv4_route_v6_gw_test;;
+	ipv4_mangle)			ipv4_mangle_test;;
+	ipv6_mangle)			ipv6_mangle_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac
-- 
cgit v1.2.3


From bf5eb67dc80a75e0756269084b087c06f0360b78 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 16 Apr 2021 18:55:35 +0300
Subject: selftests: fib_nexthops: Test large scale nexthop flushing

Test that all the nexthops are flushed when a multi-part nexthop dump is
required for the flushing.

Without previous patch:

 # ./fib_nexthops.sh
 TEST: Large scale nexthop flushing                                  [FAIL]

With previous patch:

 # ./fib_nexthops.sh
 TEST: Large scale nexthop flushing                                  [ OK ]

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_nexthops.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 56dd0c6f2e96..49774a8a7736 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -1933,6 +1933,21 @@ basic()
 	log_test $? 2 "Nexthop group and blackhole"
 
 	$IP nexthop flush >/dev/null 2>&1
+
+	# Test to ensure that flushing with a multi-part nexthop dump works as
+	# expected.
+	local batch_file=$(mktemp)
+
+	for i in $(seq 1 $((64 * 1024))); do
+		echo "nexthop add id $i blackhole" >> $batch_file
+	done
+
+	$IP -b $batch_file
+	$IP nexthop flush >/dev/null 2>&1
+	[[ $($IP nexthop | wc -l) -eq 0 ]]
+	log_test $? 0 "Large scale nexthop flushing"
+
+	rm $batch_file
 }
 
 check_nexthop_buckets_balance()
-- 
cgit v1.2.3


From c2e39c6bdc7eb48459ec1d34d4f27eb82299f4b7 Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Mon, 19 Apr 2021 17:52:43 +0200
Subject: selftests/bpf: Add a series of tests for bpf_snprintf

The "positive" part tests all format specifiers when things go well.

The "negative" part makes sure that incorrect format strings fail at
load time.

Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210419155243.1632274-7-revest@chromium.org
---
 tools/testing/selftests/bpf/prog_tests/snprintf.c  | 125 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_snprintf.c  |  73 ++++++++++++
 .../selftests/bpf/progs/test_snprintf_single.c     |  20 ++++
 3 files changed, 218 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/snprintf.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_snprintf.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_snprintf_single.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c
new file mode 100644
index 000000000000..a958c22aec75
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google LLC. */
+
+#include <test_progs.h>
+#include "test_snprintf.skel.h"
+#include "test_snprintf_single.skel.h"
+
+#define EXP_NUM_OUT  "-8 9 96 -424242 1337 DABBAD00"
+#define EXP_NUM_RET  sizeof(EXP_NUM_OUT)
+
+#define EXP_IP_OUT   "127.000.000.001 0000:0000:0000:0000:0000:0000:0000:0001"
+#define EXP_IP_RET   sizeof(EXP_IP_OUT)
+
+/* The third specifier, %pB, depends on compiler inlining so don't check it */
+#define EXP_SYM_OUT  "schedule schedule+0x0/"
+#define MIN_SYM_RET  sizeof(EXP_SYM_OUT)
+
+/* The third specifier, %p, is a hashed pointer which changes on every reboot */
+#define EXP_ADDR_OUT "0000000000000000 ffff00000add4e55 "
+#define EXP_ADDR_RET sizeof(EXP_ADDR_OUT "unknownhashedptr")
+
+#define EXP_STR_OUT  "str1 longstr"
+#define EXP_STR_RET  sizeof(EXP_STR_OUT)
+
+#define EXP_OVER_OUT "%over"
+#define EXP_OVER_RET 10
+
+#define EXP_PAD_OUT "    4 000"
+#define EXP_PAD_RET 900007
+
+#define EXP_NO_ARG_OUT "simple case"
+#define EXP_NO_ARG_RET 12
+
+#define EXP_NO_BUF_RET 29
+
+void test_snprintf_positive(void)
+{
+	char exp_addr_out[] = EXP_ADDR_OUT;
+	char exp_sym_out[]  = EXP_SYM_OUT;
+	struct test_snprintf *skel;
+
+	skel = test_snprintf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	if (!ASSERT_OK(test_snprintf__attach(skel), "skel_attach"))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	ASSERT_STREQ(skel->bss->num_out, EXP_NUM_OUT, "num_out");
+	ASSERT_EQ(skel->bss->num_ret, EXP_NUM_RET, "num_ret");
+
+	ASSERT_STREQ(skel->bss->ip_out, EXP_IP_OUT, "ip_out");
+	ASSERT_EQ(skel->bss->ip_ret, EXP_IP_RET, "ip_ret");
+
+	ASSERT_OK(memcmp(skel->bss->sym_out, exp_sym_out,
+			 sizeof(exp_sym_out) - 1), "sym_out");
+	ASSERT_LT(MIN_SYM_RET, skel->bss->sym_ret, "sym_ret");
+
+	ASSERT_OK(memcmp(skel->bss->addr_out, exp_addr_out,
+			 sizeof(exp_addr_out) - 1), "addr_out");
+	ASSERT_EQ(skel->bss->addr_ret, EXP_ADDR_RET, "addr_ret");
+
+	ASSERT_STREQ(skel->bss->str_out, EXP_STR_OUT, "str_out");
+	ASSERT_EQ(skel->bss->str_ret, EXP_STR_RET, "str_ret");
+
+	ASSERT_STREQ(skel->bss->over_out, EXP_OVER_OUT, "over_out");
+	ASSERT_EQ(skel->bss->over_ret, EXP_OVER_RET, "over_ret");
+
+	ASSERT_STREQ(skel->bss->pad_out, EXP_PAD_OUT, "pad_out");
+	ASSERT_EQ(skel->bss->pad_ret, EXP_PAD_RET, "pad_ret");
+
+	ASSERT_STREQ(skel->bss->noarg_out, EXP_NO_ARG_OUT, "no_arg_out");
+	ASSERT_EQ(skel->bss->noarg_ret, EXP_NO_ARG_RET, "no_arg_ret");
+
+	ASSERT_EQ(skel->bss->nobuf_ret, EXP_NO_BUF_RET, "no_buf_ret");
+
+cleanup:
+	test_snprintf__destroy(skel);
+}
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+/* Loads an eBPF object calling bpf_snprintf with up to 10 characters of fmt */
+static int load_single_snprintf(char *fmt)
+{
+	struct test_snprintf_single *skel;
+	int ret;
+
+	skel = test_snprintf_single__open();
+	if (!skel)
+		return -EINVAL;
+
+	memcpy(skel->rodata->fmt, fmt, min(strlen(fmt) + 1, 10));
+
+	ret = test_snprintf_single__load(skel);
+	test_snprintf_single__destroy(skel);
+
+	return ret;
+}
+
+void test_snprintf_negative(void)
+{
+	ASSERT_OK(load_single_snprintf("valid %d"), "valid usage");
+
+	ASSERT_ERR(load_single_snprintf("0123456789"), "no terminating zero");
+	ASSERT_ERR(load_single_snprintf("%d %d"), "too many specifiers");
+	ASSERT_ERR(load_single_snprintf("%pi5"), "invalid specifier 1");
+	ASSERT_ERR(load_single_snprintf("%a"), "invalid specifier 2");
+	ASSERT_ERR(load_single_snprintf("%"), "invalid specifier 3");
+	ASSERT_ERR(load_single_snprintf("%12345678"), "invalid specifier 4");
+	ASSERT_ERR(load_single_snprintf("%--------"), "invalid specifier 5");
+	ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character");
+	ASSERT_ERR(load_single_snprintf("\x1"), "non printable character");
+}
+
+void test_snprintf(void)
+{
+	if (test__start_subtest("snprintf_positive"))
+		test_snprintf_positive();
+	if (test__start_subtest("snprintf_negative"))
+		test_snprintf_negative();
+}
diff --git a/tools/testing/selftests/bpf/progs/test_snprintf.c b/tools/testing/selftests/bpf/progs/test_snprintf.c
new file mode 100644
index 000000000000..951a0301c553
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_snprintf.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char num_out[64] = {};
+long num_ret = 0;
+
+char ip_out[64] = {};
+long ip_ret = 0;
+
+char sym_out[64] = {};
+long sym_ret = 0;
+
+char addr_out[64] = {};
+long addr_ret = 0;
+
+char str_out[64] = {};
+long str_ret = 0;
+
+char over_out[6] = {};
+long over_ret = 0;
+
+char pad_out[10] = {};
+long pad_ret = 0;
+
+char noarg_out[64] = {};
+long noarg_ret = 0;
+
+long nobuf_ret = 0;
+
+extern const void schedule __ksym;
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	/* Convenient values to pretty-print */
+	const __u8 ex_ipv4[] = {127, 0, 0, 1};
+	const __u8 ex_ipv6[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1};
+	static const char str1[] = "str1";
+	static const char longstr[] = "longstr";
+
+	/* Integer types */
+	num_ret  = BPF_SNPRINTF(num_out, sizeof(num_out),
+				"%d %u %x %li %llu %lX",
+				-8, 9, 150, -424242, 1337, 0xDABBAD00);
+	/* IP addresses */
+	ip_ret   = BPF_SNPRINTF(ip_out, sizeof(ip_out), "%pi4 %pI6",
+				&ex_ipv4, &ex_ipv6);
+	/* Symbol lookup formatting */
+	sym_ret  = BPF_SNPRINTF(sym_out,  sizeof(sym_out), "%ps %pS %pB",
+				&schedule, &schedule, &schedule);
+	/* Kernel pointers */
+	addr_ret = BPF_SNPRINTF(addr_out, sizeof(addr_out), "%pK %px %p",
+				0, 0xFFFF00000ADD4E55, 0xFFFF00000ADD4E55);
+	/* Strings embedding */
+	str_ret  = BPF_SNPRINTF(str_out, sizeof(str_out), "%s %+05s",
+				str1, longstr);
+	/* Overflow */
+	over_ret = BPF_SNPRINTF(over_out, sizeof(over_out), "%%overflow");
+	/* Padding of fixed width numbers */
+	pad_ret = BPF_SNPRINTF(pad_out, sizeof(pad_out), "%5d %0900000X", 4, 4);
+	/* No args */
+	noarg_ret = BPF_SNPRINTF(noarg_out, sizeof(noarg_out), "simple case");
+	/* No buffer */
+	nobuf_ret = BPF_SNPRINTF(NULL, 0, "only interested in length %d", 60);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_snprintf_single.c b/tools/testing/selftests/bpf/progs/test_snprintf_single.c
new file mode 100644
index 000000000000..402adaf344f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_snprintf_single.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/* The format string is filled from the userspace such that loading fails */
+static const char fmt[10];
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	unsigned long long arg = 42;
+
+	bpf_snprintf(NULL, 0, fmt, &arg, sizeof(arg));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From bdc4e369454fcae108e18feb0fcbb6f06815f94b Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 16 Apr 2021 13:47:03 -0700
Subject: bpf/selftests: Add bpf_get_task_stack retval bounds verifier test

Add a bpf_iter test which feeds bpf_get_task_stack's return value into
seq_write after confirming it's positive. No attempt to bound the value
from above is made.

Load will fail if verifier does not refine retval range based on
buf sz input to bpf_get_task_stack.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210416204704.2816874-3-davemarchevsky@fb.com
---
 .../testing/selftests/bpf/verifier/bpf_get_stack.c | 43 ++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
index 69b048cf46d9..3e024c891178 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
@@ -42,3 +42,46 @@
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
+{
+	"bpf_get_task_stack return R0 range is refined",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_6, 0), // ctx->meta->seq
+	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, 8), // ctx->task
+	BPF_LD_MAP_FD(BPF_REG_1, 0), // fixup_map_array_48b
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), // keep buf for seq_write
+	BPF_MOV64_IMM(BPF_REG_3, 48),
+	BPF_MOV64_IMM(BPF_REG_4, 0),
+	BPF_EMIT_CALL(BPF_FUNC_get_task_stack),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_9),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_seq_write),
+
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_ITER,
+	.kfunc = "task",
+	.runs = -1, // Don't run, just load
+	.fixup_map_array_48b = { 3 },
+},
-- 
cgit v1.2.3


From c77cec5c207b68a3cbc2af2f81070ec428f41145 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 16 Apr 2021 13:47:04 -0700
Subject: bpf/selftests: Add bpf_get_task_stack retval bounds test_prog

Add a libbpf test prog which feeds bpf_get_task_stack's return value
into seq_write after confirming it's positive. No attempt to bound the
value from above is made.

Load will fail if verifier does not refine retval range based on buf sz
input to bpf_get_task_stack.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210416204704.2816874-4-davemarchevsky@fb.com
---
 tools/testing/selftests/bpf/prog_tests/bpf_iter.c  |  1 +
 .../selftests/bpf/progs/bpf_iter_task_stack.c      | 27 ++++++++++++++++++++++
 2 files changed, 28 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 74c45d557a2b..2d3590cfb5e1 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -147,6 +147,7 @@ static void test_task_stack(void)
 		return;
 
 	do_dummy_read(skel->progs.dump_task_stack);
+	do_dummy_read(skel->progs.get_task_user_stacks);
 
 	bpf_iter_task_stack__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
index 50e59a2e142e..43c36f5f7649 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
@@ -35,3 +35,30 @@ int dump_task_stack(struct bpf_iter__task *ctx)
 
 	return 0;
 }
+
+SEC("iter/task")
+int get_task_user_stacks(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	uint64_t buf_sz = 0;
+	int64_t res;
+
+	if (task == (void *)0)
+		return 0;
+
+	res = bpf_get_task_stack(task, entries,
+			MAX_STACK_TRACE_DEPTH * SIZE_OF_ULONG, BPF_F_USER_STACK);
+	if (res <= 0)
+		return 0;
+
+	buf_sz += res;
+
+	/* If the verifier doesn't refine bpf_get_task_stack res, and instead
+	 * assumes res is entirely unknown, this program will fail to load as
+	 * the verifier will believe that max buf_sz value allows reading
+	 * past the end of entries in bpf_seq_write call
+	 */
+	bpf_seq_write(seq, &entries, buf_sz);
+	return 0;
+}
-- 
cgit v1.2.3


From d044d9fc1380b66917dcb418ef4ec7e59dd6e597 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 20 Apr 2021 15:24:28 +0200
Subject: selftests/bpf: Add docs target as all dependency

Currently docs target is make dependency for TEST_GEN_FILES,
which makes tests to be rebuilt every time you run make.

Adding docs as all target dependency, so when running make
on top of built selftests it will show just:

  $ make
  make[1]: Nothing to be done for 'docs'.

After cleaning docs, only docs is rebuilt:

  $ make docs-clean
  CLEAN    eBPF_helpers-manpage
  CLEAN    eBPF_syscall-manpage
  $ make
  GEN      ...selftests/bpf/bpf-helpers.rst
  GEN      ...selftests/bpf/bpf-helpers.7
  GEN      ...selftests/bpf/bpf-syscall.rst
  GEN      ...selftests/bpf/bpf-syscall.2
  $ make
  make[1]: Nothing to be done for 'docs'.

Fixes: a01d935b2e09 ("tools/bpf: Remove bpf-helpers from bpftool docs")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210420132428.15710-1-jolsa@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c45ae13b88a0..c5bcdb3d4b12 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -187,7 +187,6 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
 		    cp $(SCRATCH_DIR)/runqslower $@
 
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
-$(TEST_GEN_FILES): docs
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
@@ -210,6 +209,8 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
 
+all: docs
+
 docs:
 	$(Q)RST2MAN_OPTS="--exit-status=1" $(MAKE) $(submake_extras)	\
 	            -f Makefile.docs					\
-- 
cgit v1.2.3


From 0a4d0cb1a326cf0070a625036e19871f544f2d25 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Tue, 20 Apr 2021 16:53:48 +0200
Subject: selftests: mlxsw: sch_red_ets: Test proper counter cleaning in ETS

There was a bug introduced during the rework which cause non-zero backlog
being stuck at ETS. Introduce a selftest that would have caught the issue
earlier.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
index 3f007c5f8361..f3ef3274f9b3 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -67,6 +67,13 @@ red_test()
 {
 	install_qdisc
 
+	# Make sure that we get the non-zero value if there is any.
+	local cur=$(busywait 1100 until_counter_is "> 0" \
+			    qdisc_stats_get $swp3 10: .backlog)
+	(( cur == 0 ))
+	check_err $? "backlog of $cur observed on non-busy qdisc"
+	log_test "$QDISC backlog properly cleaned"
+
 	do_red_test 10 $BACKLOG1
 	do_red_test 11 $BACKLOG2
 
-- 
cgit v1.2.3


From c8d0260cdd96fdccdef0509c4160e28a1012a5d7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 23 Apr 2021 14:19:43 +0200
Subject: selftests: net: mirror_gre_vlan_bridge_1q: Make an FDB entry static

The FDB roaming test installs a destination MAC address on the wrong
interface of an FDB database and tests whether the mirroring fails, because
packets are sent to the wrong port. The test by mistake installs the FDB
entry as local. This worked previously, because drivers were notified of
local FDB entries in the same way as of static entries. However that has
been fixed in the commit 6ab4c3117aec ("net: bridge: don't notify switchdev
for local FDB addresses"), and local entries are not notified anymore. As a
result, the HW is not reconfigured for the FDB roam, and mirroring keeps
working, failing the test.

To fix the issue, mark the FDB entry as static.

Fixes: 9c7c8a82442c ("selftests: forwarding: mirror_gre_vlan_bridge_1q: Add more tests")
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
index c02291e9841e..880e3ab9d088 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -271,7 +271,7 @@ test_span_gre_fdb_roaming()
 
 	while ((RET == 0)); do
 		bridge fdb del dev $swp3 $h3mac vlan 555 master 2>/dev/null
-		bridge fdb add dev $swp2 $h3mac vlan 555 master
+		bridge fdb add dev $swp2 $h3mac vlan 555 master static
 		sleep 1
 		fail_test_span_gre_dir $tundev ingress
 
-- 
cgit v1.2.3


From b6fc2f212108b3676f54d00a2c38e3bc36753980 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Fri, 23 Apr 2021 14:19:44 +0200
Subject: selftests: mlxsw: Remove a redundant if statement in port_scale test

Currently, the error return code of the failure condition is lost after
using an if statement, so the test doesn't fail when it should.

Remove the if statement that separates the condition and the error code
check, so the test won't always pass.

Fixes: 5154b1b826d9b ("selftests: mlxsw: Add a scale test for physical ports")
Reported-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/port_scale.sh | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh
index f813ffefc07e..65f43a7ce9c9 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh
@@ -55,10 +55,6 @@ port_test()
 	      | jq '.[][][] | select(.name=="physical_ports") |.["occ"]')
 
 	[[ $occ -eq $max_ports ]]
-	if [[ $should_fail -eq 0 ]]; then
-		check_err $? "Mismatch ports number: Expected $max_ports, got $occ."
-	else
-		check_err_fail $should_fail $? "Reached more ports than expected"
-	fi
+	check_err_fail $should_fail $? "Attempt to create $max_ports ports (actual result $occ)"
 
 }
-- 
cgit v1.2.3


From 1f1c92139e36223b89d8140f2b72f75e79baf8bd Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Fri, 23 Apr 2021 14:19:45 +0200
Subject: selftests: mlxsw: Remove a redundant if statement in tc_flower_scale
 test

Currently, the error return code of the failure condition is lost after
using an if statement, so the test doesn't fail when it should.

Remove the if statement that separates the condition and the error code
check, so the test won't always pass.

Fixes: abfce9e062021 ("selftests: mlxsw: Reduce running time using offload indication")
Reported-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
index cc0f07e72cf2..aa74be9f47c8 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
@@ -98,11 +98,7 @@ __tc_flower_test()
 			jq -r '[ .[] | select(.kind == "flower") |
 			.options | .in_hw ]' | jq .[] | wc -l)
 	[[ $((offload_count - 1)) -eq $count ]]
-	if [[ $should_fail -eq 0 ]]; then
-		check_err $? "Offload mismatch"
-	else
-		check_err_fail $should_fail $? "Offload more than expacted"
-	fi
+	check_err_fail $should_fail $? "Attempt to offload $count rules (actual result $((offload_count - 1)))"
 }
 
 tc_flower_test()
-- 
cgit v1.2.3


From 059b18e21c631b0eb1668831ae99f4764fb8e7eb Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Fri, 23 Apr 2021 14:19:46 +0200
Subject: selftests: mlxsw: Return correct error code in resource scale tests

Currently, the resource scale test checks a few cases, when the error code
resets between the cases. So for example, if one case fails and the
consecutive case passes, the error code eventually will fit the last test
and will be 0.

Save a new return code that will hold the 'or' return codes of all the
cases, so the final return code will consider all the cases.

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh  | 4 +++-
 tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh  | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index 4a1c9328555f..50654f8a8c37 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -30,6 +30,7 @@ trap cleanup EXIT
 
 ALL_TESTS="router tc_flower mirror_gre tc_police port"
 for current_test in ${TESTS:-$ALL_TESTS}; do
+	RET_FIN=0
 	source ${current_test}_scale.sh
 
 	num_netifs_var=${current_test^^}_NUM_NETIFS
@@ -48,8 +49,9 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 		else
 			log_test "'$current_test' overflow $target"
 		fi
+		RET_FIN=$(( RET_FIN || RET ))
 	done
 done
 current_test=""
 
-exit "$RET"
+exit "$RET_FIN"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index 087a884f66cd..685dfb3478b3 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -24,6 +24,7 @@ trap cleanup EXIT
 
 ALL_TESTS="router tc_flower mirror_gre tc_police port"
 for current_test in ${TESTS:-$ALL_TESTS}; do
+	RET_FIN=0
 	source ${current_test}_scale.sh
 
 	num_netifs_var=${current_test^^}_NUM_NETIFS
@@ -50,8 +51,9 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 				log_test "'$current_test' [$profile] overflow $target"
 			fi
 		done
+		RET_FIN=$(( RET_FIN || RET ))
 	done
 done
 current_test=""
 
-exit "$RET"
+exit "$RET_FIN"
-- 
cgit v1.2.3


From dda7f4fa55839baeb72ae040aeaf9ccf89d3e416 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 23 Apr 2021 14:19:47 +0200
Subject: selftests: mlxsw: Increase the tolerance of backlog buildup

The intention behind this test is to make sure that qdisc limit is
correctly projected to the HW. However, first, due to rounding in the
qdisc, and then in the driver, the number cannot actually be accurate. And
second, the approach to testing this is to oversubscribe the port with
traffic generated on the same switch. The actual backlog size therefore
fluctuates.

In practice, this test proved to be noisier than the rest, and spuriously
fails every now and then. Increase the tolerance to 10 % to avoid these
issues.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index b0cb1aaffdda..33ddd01689be 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -507,8 +507,8 @@ do_red_test()
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
 	local diff=$((limit - backlog))
 	pct=$((100 * diff / limit))
-	((0 <= pct && pct <= 5))
-	check_err $? "backlog $backlog / $limit expected <= 5% distance"
+	((0 <= pct && pct <= 10))
+	check_err $? "backlog $backlog / $limit expected <= 10% distance"
 	log_test "TC $((vlan - 10)): RED backlog > limit"
 
 	stop_traffic
-- 
cgit v1.2.3


From 1233898ab758cbcf5f6fea10b8dd16a0b2c24fab Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 23 Apr 2021 14:19:48 +0200
Subject: selftests: mlxsw: Fix mausezahn invocation in ERSPAN scale test

The mirror_gre_scale test creates as many ERSPAN sessions as the underlying
chip supports, and tests that they all work. In order to determine that it
issues a stream of ICMP packets and checks if they are mirrored as
expected.

However, the mausezahn invocation missed the -6 flag to identify the use of
IPv6 protocol, and was sending ICMP messages over IPv6, as opposed to
ICMP6. It also didn't pass an explicit source IP address, which apparently
worked at some point in the past, but does not anymore.

To fix these issues, extend the function mirror_test() in mirror_lib by
detecting the IPv6 protocol addresses, and using a different ICMP scheme.
Fix __mirror_gre_test() in the selftest itself to pass a source IP address.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/mirror_gre_scale.sh   |  3 ++-
 tools/testing/selftests/net/forwarding/mirror_lib.sh  | 19 +++++++++++++++++--
 2 files changed, 19 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
index 6f3a70df63bc..e00435753008 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
@@ -120,12 +120,13 @@ __mirror_gre_test()
 	sleep 5
 
 	for ((i = 0; i < count; ++i)); do
+		local sip=$(mirror_gre_ipv6_addr 1 $i)::1
 		local dip=$(mirror_gre_ipv6_addr 1 $i)::2
 		local htun=h3-gt6-$i
 		local message
 
 		icmp6_capture_install $htun
-		mirror_test v$h1 "" $dip $htun 100 10
+		mirror_test v$h1 $sip $dip $htun 100 10
 		icmp6_capture_uninstall $htun
 	done
 }
diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh
index 13db1cb50e57..6406cd76a19d 100644
--- a/tools/testing/selftests/net/forwarding/mirror_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh
@@ -20,6 +20,13 @@ mirror_uninstall()
 	tc filter del dev $swp1 $direction pref 1000
 }
 
+is_ipv6()
+{
+	local addr=$1; shift
+
+	[[ -z ${addr//[0-9a-fA-F:]/} ]]
+}
+
 mirror_test()
 {
 	local vrf_name=$1; shift
@@ -29,9 +36,17 @@ mirror_test()
 	local pref=$1; shift
 	local expect=$1; shift
 
+	if is_ipv6 $dip; then
+		local proto=-6
+		local type="icmp6 type=128" # Echo request.
+	else
+		local proto=
+		local type="icmp echoreq"
+	fi
+
 	local t0=$(tc_rule_stats_get $dev $pref)
-	$MZ $vrf_name ${sip:+-A $sip} -B $dip -a own -b bc -q \
-	    -c 10 -d 100msec -t icmp type=8
+	$MZ $proto $vrf_name ${sip:+-A $sip} -B $dip -a own -b bc -q \
+	    -c 10 -d 100msec -t $type
 	sleep 0.5
 	local t1=$(tc_rule_stats_get $dev $pref)
 	local delta=$((t1 - t0))
-- 
cgit v1.2.3


From 41c472e85b531a228067bee9be59a508900bcd9f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 23 Apr 2021 11:13:43 -0700
Subject: selftests/bpf: Use -O0 instead of -Og in selftests builds

While -Og is designed to work well with debugger, it's still inferior to -O0
in terms of debuggability experience. It will cause some variables to still be
inlined, it will also prevent single-stepping some statements and otherwise
interfere with debugging experience. So switch to -O0 which turns off any
optimization and provides the best debugging experience.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210423181348.1801389-14-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c5bcdb3d4b12..dd8061069b08 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -21,7 +21,7 @@ endif
 
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 SAN_CFLAGS	?=
-CFLAGS += -g -Og -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS)		\
+CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS)		\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)			\
 	  -Dbpf_prog_load=bpf_prog_test_load				\
@@ -205,7 +205,7 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
 		    CC=$(HOSTCC) LD=$(HOSTLD)				       \
-		    EXTRA_CFLAGS='-g -Og'				       \
+		    EXTRA_CFLAGS='-g -O0'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
 
@@ -225,7 +225,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   ../../../include/uapi/linux/bpf.h                                   \
 	   | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
-		    EXTRA_CFLAGS='-g -Og'					       \
+		    EXTRA_CFLAGS='-g -O0'				       \
 		    DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
 
 ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
@@ -233,7 +233,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)                \
 	   ../../../include/uapi/linux/bpf.h                                   \
 	   | $(INCLUDE_DIR) $(HOST_BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR)                             \
-		    EXTRA_CFLAGS='-g -Og'					       \
+		    EXTRA_CFLAGS='-g -O0'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
 endif
-- 
cgit v1.2.3


From b131aed910097a2eeac8180bf3cf214eea475d9a Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 23 Apr 2021 11:13:44 -0700
Subject: selftests/bpf: Omit skeleton generation for multi-linked BPF object
 files

Skip generating individual BPF skeletons for files that are supposed to be
linked together to form the final BPF object file. Very often such files are
"incomplete" BPF object files, which will fail libbpf bpf_object__open() step,
if used individually, thus failing BPF skeleton generation. This is by design,
so skip individual BPF skeletons and only validate them as part of their
linked final BPF object file and skeleton.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210423181348.1801389-15-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index dd8061069b08..dd3692ec56d3 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -313,6 +313,8 @@ LINKED_SKELS := test_static_linked.skel.h
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
 
+LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
+
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
 # Parameters:
@@ -331,7 +333,7 @@ TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h
 TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))
 TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS))
 TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
-				 $$(filter-out $(SKEL_BLACKLIST),	\
+				 $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\
 					       $$(TRUNNER_BPF_SRCS)))
 TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
 TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
-- 
cgit v1.2.3


From f2644fb44de9abd54e57b55f584c7c67526f7c02 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 23 Apr 2021 11:13:45 -0700
Subject: selftests/bpf: Add function linking selftest

Add selftest validating various aspects of statically linking functions:
  - no conflicts and correct resolution for name-conflicting static funcs;
  - correct resolution of extern functions;
  - correct handling of weak functions, both resolution itself and libbpf's
    handling of unused weak function that "lost" (it leaves gaps in code with
    no ELF symbols);
  - correct handling of hidden visibility to turn global function into
    "static" for the purpose of BPF verification.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210423181348.1801389-16-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile               |  3 +-
 .../selftests/bpf/prog_tests/linked_funcs.c        | 42 +++++++++++++
 tools/testing/selftests/bpf/progs/linked_funcs1.c  | 73 ++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/linked_funcs2.c  | 73 ++++++++++++++++++++++
 4 files changed, 190 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/linked_funcs.c
 create mode 100644 tools/testing/selftests/bpf/progs/linked_funcs1.c
 create mode 100644 tools/testing/selftests/bpf/progs/linked_funcs2.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index dd3692ec56d3..ab7b129a8408 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -309,9 +309,10 @@ endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 
-LINKED_SKELS := test_static_linked.skel.h
+LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
+linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
 
 LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
 
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_funcs.c b/tools/testing/selftests/bpf/prog_tests/linked_funcs.c
new file mode 100644
index 000000000000..e9916f2817ec
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/linked_funcs.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include "linked_funcs.skel.h"
+
+void test_linked_funcs(void)
+{
+	int err;
+	struct linked_funcs *skel;
+
+	skel = linked_funcs__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->rodata->my_tid = syscall(SYS_gettid);
+	skel->bss->syscall_id = SYS_getpgid;
+
+	err = linked_funcs__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = linked_funcs__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->output_val1, 2000 + 2000, "output_val1");
+	ASSERT_EQ(skel->bss->output_ctx1, SYS_getpgid, "output_ctx1");
+	ASSERT_EQ(skel->bss->output_weak1, 42, "output_weak1");
+
+	ASSERT_EQ(skel->bss->output_val2, 2 * 1000 + 2 * (2 * 1000), "output_val2");
+	ASSERT_EQ(skel->bss->output_ctx2, SYS_getpgid, "output_ctx2");
+	/* output_weak2 should never be updated */
+	ASSERT_EQ(skel->bss->output_weak2, 0, "output_weak2");
+
+cleanup:
+	linked_funcs__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c
new file mode 100644
index 000000000000..b964ec1390c2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* weak and shared between two files */
+const volatile int my_tid __weak;
+long syscall_id __weak;
+
+int output_val1;
+int output_ctx1;
+int output_weak1;
+
+/* same "subprog" name in all files, but it's ok because they all are static */
+static __noinline int subprog(int x)
+{
+	/* but different formula */
+	return x * 1;
+}
+
+/* Global functions can't be void */
+int set_output_val1(int x)
+{
+	output_val1 = x + subprog(x);
+	return x;
+}
+
+/* This function can't be verified as global, as it assumes raw_tp/sys_enter
+ * context and accesses syscall id (second argument). So we mark it as
+ * __hidden, so that libbpf will mark it as static in the final object file,
+ * right before verifying it in the kernel.
+ *
+ * But we don't mark it as __hidden here, rather at extern site. __hidden is
+ * "contaminating" visibility, so it will get propagated from either extern or
+ * actual definition (including from the losing __weak definition).
+ */
+void set_output_ctx1(__u64 *ctx)
+{
+	output_ctx1 = ctx[1]; /* long id, same as in BPF_PROG below */
+}
+
+/* this weak instance should win because it's the first one */
+__weak int set_output_weak(int x)
+{
+	output_weak1 = x;
+	return x;
+}
+
+extern int set_output_val2(int x);
+
+/* here we'll force set_output_ctx2() to be __hidden in the final obj file */
+__hidden extern void set_output_ctx2(__u64 *ctx);
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler1, struct pt_regs *regs, long id)
+{
+	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+		return 0;
+
+	set_output_val2(1000);
+	set_output_ctx2(ctx); /* ctx definition is hidden in BPF_PROG macro */
+
+	/* keep input value the same across both files to avoid dependency on
+	 * handler call order; differentiate by output_weak1 vs output_weak2.
+	 */
+	set_output_weak(42);
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c
new file mode 100644
index 000000000000..575e958e60b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* weak and shared between both files */
+const volatile int my_tid __weak;
+long syscall_id __weak;
+
+int output_val2;
+int output_ctx2;
+int output_weak2; /* should stay zero */
+
+/* same "subprog" name in all files, but it's ok because they all are static */
+static __noinline int subprog(int x)
+{
+	/* but different formula */
+	return x * 2;
+}
+
+/* Global functions can't be void */
+int set_output_val2(int x)
+{
+	output_val2 = 2 * x + 2 * subprog(x);
+	return 2 * x;
+}
+
+/* This function can't be verified as global, as it assumes raw_tp/sys_enter
+ * context and accesses syscall id (second argument). So we mark it as
+ * __hidden, so that libbpf will mark it as static in the final object file,
+ * right before verifying it in the kernel.
+ *
+ * But we don't mark it as __hidden here, rather at extern site. __hidden is
+ * "contaminating" visibility, so it will get propagated from either extern or
+ * actual definition (including from the losing __weak definition).
+ */
+void set_output_ctx2(__u64 *ctx)
+{
+	output_ctx2 = ctx[1]; /* long id, same as in BPF_PROG below */
+}
+
+/* this weak instance should lose, because it will be processed second */
+__weak int set_output_weak(int x)
+{
+	output_weak2 = x;
+	return 2 * x;
+}
+
+extern int set_output_val1(int x);
+
+/* here we'll force set_output_ctx1() to be __hidden in the final obj file */
+__hidden extern void set_output_ctx1(__u64 *ctx);
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler2, struct pt_regs *regs, long id)
+{
+	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+		return 0;
+
+	set_output_val1(2000);
+	set_output_ctx1(ctx); /* ctx definition is hidden in BPF_PROG macro */
+
+	/* keep input value the same across both files to avoid dependency on
+	 * handler call order; differentiate by output_weak1 vs output_weak2.
+	 */
+	set_output_weak(42);
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 14f1aae17ee13d08315873d4b68d573e91df892f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 23 Apr 2021 11:13:46 -0700
Subject: selftests/bpf: Add global variables linking selftest

Add selftest validating various aspects of statically linking global
variables:
  - correct resolution of extern variables across .bss, .data, and .rodata
    sections;
  - correct handling of weak definitions;
  - correct de-duplication of repeating special externs (.kconfig, .ksyms).

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210423181348.1801389-17-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile               |  3 +-
 .../testing/selftests/bpf/prog_tests/linked_vars.c | 43 +++++++++++++++++
 tools/testing/selftests/bpf/progs/linked_vars1.c   | 54 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/linked_vars2.c   | 55 ++++++++++++++++++++++
 4 files changed, 154 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/linked_vars.c
 create mode 100644 tools/testing/selftests/bpf/progs/linked_vars1.c
 create mode 100644 tools/testing/selftests/bpf/progs/linked_vars2.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index ab7b129a8408..411e2cf07ba5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -309,10 +309,11 @@ endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 
-LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h
+LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h linked_vars.skel.h
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
 linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
+linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o
 
 LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
 
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_vars.c b/tools/testing/selftests/bpf/prog_tests/linked_vars.c
new file mode 100644
index 000000000000..267166abe4c1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/linked_vars.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include "linked_vars.skel.h"
+
+void test_linked_vars(void)
+{
+	int err;
+	struct linked_vars *skel;
+
+	skel = linked_vars__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->bss->input_bss1 = 1000;
+	skel->bss->input_bss2 = 2000;
+	skel->bss->input_bss_weak = 3000;
+
+	err = linked_vars__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = linked_vars__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->output_bss1, 1000 + 2000 + 3000, "output_bss1");
+	ASSERT_EQ(skel->bss->output_bss2, 1000 + 2000 + 3000, "output_bss2");
+	/* 10 comes from "winner" input_data_weak in first obj file */
+	ASSERT_EQ(skel->bss->output_data1, 1 + 2 + 10, "output_bss1");
+	ASSERT_EQ(skel->bss->output_data2, 1 + 2 + 10, "output_bss2");
+	/* 100 comes from "winner" input_rodata_weak in first obj file */
+	ASSERT_EQ(skel->bss->output_rodata1, 11 + 22 + 100, "output_weak1");
+	ASSERT_EQ(skel->bss->output_rodata2, 11 + 22 + 100, "output_weak2");
+
+cleanup:
+	linked_vars__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/linked_vars1.c b/tools/testing/selftests/bpf/progs/linked_vars1.c
new file mode 100644
index 000000000000..ef9e9d0bb0ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/linked_vars1.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern int LINUX_KERNEL_VERSION __kconfig;
+/* this weak extern will be strict due to the other file's strong extern */
+extern bool CONFIG_BPF_SYSCALL __kconfig __weak;
+extern const void bpf_link_fops __ksym __weak;
+
+int input_bss1;
+int input_data1 = 1;
+const volatile int input_rodata1 = 11;
+
+int input_bss_weak __weak;
+/* these two definitions should win */
+int input_data_weak __weak = 10;
+const volatile int input_rodata_weak __weak = 100;
+
+extern int input_bss2;
+extern int input_data2;
+extern const int input_rodata2;
+
+int output_bss1;
+int output_data1;
+int output_rodata1;
+
+long output_sink1;
+
+static __noinline int get_bss_res(void)
+{
+	/* just make sure all the relocations work against .text as well */
+	return input_bss1 + input_bss2 + input_bss_weak;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler1)
+{
+	output_bss1 = get_bss_res();
+	output_data1 = input_data1 + input_data2 + input_data_weak;
+	output_rodata1 = input_rodata1 + input_rodata2 + input_rodata_weak;
+
+	/* make sure we actually use above special externs, otherwise compiler
+	 * will optimize them out
+	 */
+	output_sink1 = LINUX_KERNEL_VERSION
+		       + CONFIG_BPF_SYSCALL
+		       + (long)&bpf_link_fops;
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/linked_vars2.c b/tools/testing/selftests/bpf/progs/linked_vars2.c
new file mode 100644
index 000000000000..e4f5bd388a3c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/linked_vars2.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern int LINUX_KERNEL_VERSION __kconfig;
+/* when an extern is defined as both strong and weak, resulting symbol will be strong */
+extern bool CONFIG_BPF_SYSCALL __kconfig;
+extern const void __start_BTF __ksym;
+
+int input_bss2;
+int input_data2 = 2;
+const volatile int input_rodata2 = 22;
+
+int input_bss_weak __weak;
+/* these two weak variables should lose */
+int input_data_weak __weak = 20;
+const volatile int input_rodata_weak __weak = 200;
+
+extern int input_bss1;
+extern int input_data1;
+extern const int input_rodata1;
+
+int output_bss2;
+int output_data2;
+int output_rodata2;
+
+int output_sink2;
+
+static __noinline int get_data_res(void)
+{
+	/* just make sure all the relocations work against .text as well */
+	return input_data1 + input_data2 + input_data_weak;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler2)
+{
+	output_bss2 = input_bss1 + input_bss2 + input_bss_weak;
+	output_data2 = get_data_res();
+	output_rodata2 = input_rodata1 + input_rodata2 + input_rodata_weak;
+
+	/* make sure we actually use above special externs, otherwise compiler
+	 * will optimize them out
+	 */
+	output_sink2 = LINUX_KERNEL_VERSION
+		       + CONFIG_BPF_SYSCALL
+		       + (long)&__start_BTF;
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 3b2ad502256b7f0f9415978fd7f158656d11401e Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 23 Apr 2021 11:13:47 -0700
Subject: selftests/bpf: Add map linking selftest

Add selftest validating various aspects of statically linking BTF-defined map
definitions. Legacy map definitions do not support extern resolution between
object files. Some of the aspects validated:
  - correct resolution of extern maps against concrete map definitions;
  - extern maps can currently only specify map type and key/value size and/or
    type information;
  - weak concrete map definitions are resolved properly.

Static map definitions are not yet supported by libbpf, so they are not
explicitly tested, though manual testing showes that BPF linker handles them
properly.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210423181348.1801389-18-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile               |  4 +-
 .../testing/selftests/bpf/prog_tests/linked_maps.c | 30 ++++++++
 tools/testing/selftests/bpf/progs/linked_maps1.c   | 82 ++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/linked_maps2.c   | 76 ++++++++++++++++++++
 4 files changed, 191 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/linked_maps.c
 create mode 100644 tools/testing/selftests/bpf/progs/linked_maps1.c
 create mode 100644 tools/testing/selftests/bpf/progs/linked_maps2.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 411e2cf07ba5..283e5ad8385e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -309,11 +309,13 @@ endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 
-LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h linked_vars.skel.h
+LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
+		linked_vars.skel.h linked_maps.skel.h
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
 linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
 linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o
+linked_maps.skel.h-deps := linked_maps1.o linked_maps2.o
 
 LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
 
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_maps.c b/tools/testing/selftests/bpf/prog_tests/linked_maps.c
new file mode 100644
index 000000000000..85dcaaaf2775
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/linked_maps.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include "linked_maps.skel.h"
+
+void test_linked_maps(void)
+{
+	int err;
+	struct linked_maps *skel;
+
+	skel = linked_maps__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	err = linked_maps__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->output_first1, 2000, "output_first1");
+	ASSERT_EQ(skel->bss->output_second1, 2, "output_second1");
+	ASSERT_EQ(skel->bss->output_weak1, 2, "output_weak1");
+
+cleanup:
+	linked_maps__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/linked_maps1.c b/tools/testing/selftests/bpf/progs/linked_maps1.c
new file mode 100644
index 000000000000..52291515cc72
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/linked_maps1.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct my_key { long x; };
+struct my_value { long x; };
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct my_key);
+	__type(value, struct my_value);
+	__uint(max_entries, 16);
+} map1 SEC(".maps");
+
+ /* Matches map2 definition in linked_maps2.c. Order of the attributes doesn't
+  * matter.
+  */
+typedef struct {
+	__uint(max_entries, 8);
+	__type(key, int);
+	__type(value, int);
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+} map2_t;
+
+extern map2_t map2 SEC(".maps");
+
+/* This should be the winning map definition, but we have no way of verifying,
+ * so we just make sure that it links and works without errors
+ */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 16);
+} map_weak __weak SEC(".maps");
+
+int output_first1;
+int output_second1;
+int output_weak1;
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler_enter1)
+{
+	/* update values with key = 1 */
+	int key = 1, val = 1;
+	struct my_key key_struct = { .x = 1 };
+	struct my_value val_struct = { .x = 1000 };
+
+	bpf_map_update_elem(&map1, &key_struct, &val_struct, 0);
+	bpf_map_update_elem(&map2, &key, &val, 0);
+	bpf_map_update_elem(&map_weak, &key, &val, 0);
+
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int BPF_PROG(handler_exit1)
+{
+	/* lookup values with key = 2, set in another file */
+	int key = 2, *val;
+	struct my_key key_struct = { .x = 2 };
+	struct my_value *value_struct;
+
+	value_struct = bpf_map_lookup_elem(&map1, &key_struct);
+	if (value_struct)
+		output_first1 = value_struct->x;
+
+	val = bpf_map_lookup_elem(&map2, &key);
+	if (val)
+		output_second1 = *val;
+
+	val = bpf_map_lookup_elem(&map_weak, &key);
+	if (val)
+		output_weak1 = *val;
+	
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/linked_maps2.c b/tools/testing/selftests/bpf/progs/linked_maps2.c
new file mode 100644
index 000000000000..0693687474ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/linked_maps2.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+/* modifiers and typedefs are ignored when comparing key/value types */
+typedef struct my_key { long x; } key_type;
+typedef struct my_value { long x; } value_type;
+
+extern struct {
+	__uint(max_entries, 16);
+	__type(key, key_type);
+	__type(value, value_type);
+	__uint(type, BPF_MAP_TYPE_HASH);
+} map1 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 8);
+} map2 SEC(".maps");
+
+/* this definition will lose, but it has to exactly match the winner */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 16);
+} map_weak __weak SEC(".maps");
+
+int output_first2;
+int output_second2;
+int output_weak2;
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(handler_enter2)
+{
+	/* update values with key = 2 */
+	int key = 2, val = 2;
+	key_type key_struct = { .x = 2 };
+	value_type val_struct = { .x = 2000 };
+
+	bpf_map_update_elem(&map1, &key_struct, &val_struct, 0);
+	bpf_map_update_elem(&map2, &key, &val, 0);
+	bpf_map_update_elem(&map_weak, &key, &val, 0);
+
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int BPF_PROG(handler_exit2)
+{
+	/* lookup values with key = 1, set in another file */
+	int key = 1, *val;
+	key_type key_struct = { .x = 1 };
+	value_type *value_struct;
+
+	value_struct = bpf_map_lookup_elem(&map1, &key_struct);
+	if (value_struct)
+		output_first2 = value_struct->x;
+
+	val = bpf_map_lookup_elem(&map2, &key);
+	if (val)
+		output_second2 = *val;
+
+	val = bpf_map_lookup_elem(&map_weak, &key);
+	if (val)
+		output_weak2 = *val;
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From a9dab4e4569425e26cd9c2d8bdcc74bd12fcb8bf Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 23 Apr 2021 11:13:48 -0700
Subject: selftests/bpf: Document latest Clang fix expectations for linking
 tests

Document which fixes are required to generate correct static linking
selftests.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210423181348.1801389-19-andrii@kernel.org
---
 tools/testing/selftests/bpf/README.rst | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 65fe318d1e71..3353778c30f8 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -193,3 +193,12 @@ Without it, the error from compiling bpf selftests looks like:
   libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
 
 __ https://reviews.llvm.org/D93563
+
+Clang dependencies for static linking tests
+===========================================
+
+linked_vars, linked_maps, and linked_funcs tests depend on `Clang fix`__ to
+generate valid BTF information for weak variables. Please make sure you use
+Clang that contains the fix.
+
+__ https://reviews.llvm.org/D100362
-- 
cgit v1.2.3


From df8aee6d6fa520ff77f48d46ebd2034249669033 Mon Sep 17 00:00:00 2001
From: Yonglong Li <liyonglong@chinatelecom.cn>
Date: Fri, 23 Apr 2021 11:17:09 -0700
Subject: selftests: mptcp: add a test case for MSG_PEEK

Extend mptcp_connect tool with MSG_PEEK support and add a test case in
mptcp_connect.sh that checks the data received from/after recv() with
MSG_PEEK.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Yonglong Li <liyonglong@chinatelecom.cn>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.c  | 48 +++++++++++++++++++++-
 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 29 ++++++++++---
 2 files changed, 69 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 2f207cf33661..d88e1fdfb147 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -45,7 +45,14 @@ enum cfg_mode {
 	CFG_MODE_SENDFILE,
 };
 
+enum cfg_peek {
+	CFG_NONE_PEEK,
+	CFG_WITH_PEEK,
+	CFG_AFTER_PEEK,
+};
+
 static enum cfg_mode cfg_mode = CFG_MODE_POLL;
+static enum cfg_peek cfg_peek = CFG_NONE_PEEK;
 static const char *cfg_host;
 static const char *cfg_port	= "12000";
 static int cfg_sock_proto	= IPPROTO_MPTCP;
@@ -73,6 +80,8 @@ static void die_usage(void)
 	fprintf(stderr, "\t-M mark -- set socket packet mark\n");
 	fprintf(stderr, "\t-u -- check mptcp ulp\n");
 	fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n");
+	fprintf(stderr,
+		"\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n");
 	exit(1);
 }
 
@@ -331,6 +340,8 @@ static size_t do_write(const int fd, char *buf, const size_t len)
 
 static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
 {
+	int ret = 0;
+	char tmp[16384];
 	size_t cap = rand();
 
 	cap &= 0xffff;
@@ -340,7 +351,17 @@ static ssize_t do_rnd_read(const int fd, char *buf, const size_t len)
 	else if (cap > len)
 		cap = len;
 
-	return read(fd, buf, cap);
+	if (cfg_peek == CFG_WITH_PEEK) {
+		ret = recv(fd, buf, cap, MSG_PEEK);
+		ret = (ret < 0) ? ret : read(fd, tmp, ret);
+	} else if (cfg_peek == CFG_AFTER_PEEK) {
+		ret = recv(fd, buf, cap, MSG_PEEK);
+		ret = (ret < 0) ? ret : read(fd, buf, cap);
+	} else {
+		ret = read(fd, buf, cap);
+	}
+
+	return ret;
 }
 
 static void set_nonblock(int fd)
@@ -819,6 +840,26 @@ int parse_mode(const char *mode)
 	return 0;
 }
 
+int parse_peek(const char *mode)
+{
+	if (!strcasecmp(mode, "saveWithPeek"))
+		return CFG_WITH_PEEK;
+	if (!strcasecmp(mode, "saveAfterPeek"))
+		return CFG_AFTER_PEEK;
+
+	fprintf(stderr, "Unknown: %s\n", mode);
+	fprintf(stderr, "Supported MSG_PEEK mode are:\n");
+	fprintf(stderr,
+		"\t\t\"saveWithPeek\" - recv data with flags 'MSG_PEEK' and save the peek data into file\n");
+	fprintf(stderr,
+		"\t\t\"saveAfterPeek\" - read and save data into file after recv with flags 'MSG_PEEK'\n");
+
+	die_usage();
+
+	/* silence compiler warning */
+	return 0;
+}
+
 static int parse_int(const char *size)
 {
 	unsigned long s;
@@ -846,7 +887,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
@@ -899,6 +940,9 @@ static void parse_opts(int argc, char **argv)
 		case 'M':
 			cfg_mark = strtol(optarg, NULL, 0);
 			break;
+		case 'P':
+			cfg_peek = parse_peek(optarg);
+			break;
 		}
 	}
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 385cdc98aed8..9236609731b1 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -375,7 +375,7 @@ do_transfer()
 	local srv_proto="$4"
 	local connect_addr="$5"
 	local local_addr="$6"
-	local extra_args=""
+	local extra_args="$7"
 
 	local port
 	port=$((10000+$TEST_COUNT))
@@ -394,9 +394,9 @@ do_transfer()
 	fi
 
 	if [ -n "$extra_args" ] && $options_log; then
-		options_log=false
 		echo "INFO: extra options: $extra_args"
 	fi
+	options_log=false
 
 	:> "$cout"
 	:> "$sout"
@@ -589,6 +589,7 @@ run_tests_lo()
 	local connector_ns="$2"
 	local connect_addr="$3"
 	local loopback="$4"
+	local extra_args="$5"
 	local lret=0
 
 	# skip if test programs are running inside same netns for subsequent runs.
@@ -608,7 +609,8 @@ run_tests_lo()
 		local_addr="0.0.0.0"
 	fi
 
-	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${local_addr}
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
@@ -622,14 +624,16 @@ run_tests_lo()
 		fi
 	fi
 
-	do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr}
+	do_transfer ${listener_ns} ${connector_ns} MPTCP TCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
 		return 1
 	fi
 
-	do_transfer ${listener_ns} ${connector_ns} TCP MPTCP ${connect_addr} ${local_addr}
+	do_transfer ${listener_ns} ${connector_ns} TCP MPTCP \
+		    ${connect_addr} ${local_addr} "${extra_args}"
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
@@ -637,7 +641,8 @@ run_tests_lo()
 	fi
 
 	if [ $do_tcp -gt 1 ] ;then
-		do_transfer ${listener_ns} ${connector_ns} TCP TCP ${connect_addr} ${local_addr}
+		do_transfer ${listener_ns} ${connector_ns} TCP TCP \
+			    ${connect_addr} ${local_addr} "${extra_args}"
 		lret=$?
 		if [ $lret -ne 0 ]; then
 			ret=$lret
@@ -653,6 +658,15 @@ run_tests()
 	run_tests_lo $1 $2 $3 0
 }
 
+run_tests_peekmode()
+{
+	local peekmode="$1"
+
+	echo "INFO: with peek mode: ${peekmode}"
+	run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-P ${peekmode}"
+	run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}"
+}
+
 make_file "$cin" "client"
 make_file "$sin" "server"
 
@@ -732,6 +746,9 @@ for sender in $ns1 $ns2 $ns3 $ns4;do
 	run_tests "$ns4" $sender dead:beef:3::1
 done
 
+run_tests_peekmode "saveWithPeek"
+run_tests_peekmode "saveAfterPeek"
+
 time_end=$(date +%s)
 time_run=$((time_end-time_start))
 
-- 
cgit v1.2.3


From b881d089c7c9c7032da812cda1b4b0818f477780 Mon Sep 17 00:00:00 2001
From: Po-Hsu Lin <po-hsu.lin@canonical.com>
Date: Fri, 23 Apr 2021 19:15:38 +0800
Subject: selftests/net: bump timeout to 5 minutes

We found that with the latest mainline kernel (5.12.0-051200rc8) on
some KVM instances / bare-metal systems, the following tests will take
longer than the kselftest framework default timeout (45 seconds) to
run and thus got terminated with TIMEOUT error:
* xfrm_policy.sh - took about 2m20s
* pmtu.sh - took about 3m5s
* udpgso_bench.sh - took about 60s

Bump the timeout setting to 5 minutes to allow them have a chance to
finish.

https://bugs.launchpad.net/bugs/1856010
Signed-off-by: Po-Hsu Lin <po-hsu.lin@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile | 2 ++
 tools/testing/selftests/net/settings | 1 +
 2 files changed, 3 insertions(+)
 create mode 100644 tools/testing/selftests/net/settings

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index f4242a961088..3915bb7bfc39 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -39,6 +39,8 @@ TEST_GEN_FILES += ipsec
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
+TEST_FILES := settings
+
 KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings
new file mode 100644
index 000000000000..694d70710ff0
--- /dev/null
+++ b/tools/testing/selftests/net/settings
@@ -0,0 +1 @@
+timeout=300
-- 
cgit v1.2.3


From 56dda5a48f4f610ac9a0487c6fb64d31950e4a3e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 14 Apr 2021 21:51:43 +0200
Subject: selftests/bpf: Add re-attach test to fentry_test

Adding the test to re-attach (detach/attach again) tracing
fentry programs, plus check that already linked program can't
be attached again.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210414195147.1624932-4-jolsa@kernel.org
---
 .../testing/selftests/bpf/prog_tests/fentry_test.c | 52 +++++++++++++++-------
 1 file changed, 37 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index 04ebbf1cb390..7cb111b11995 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -3,35 +3,57 @@
 #include <test_progs.h>
 #include "fentry_test.skel.h"
 
-void test_fentry_test(void)
+static int fentry_test(struct fentry_test *fentry_skel)
 {
-	struct fentry_test *fentry_skel = NULL;
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
+	struct bpf_link *link;
 	__u64 *result;
 
-	fentry_skel = fentry_test__open_and_load();
-	if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
-		goto cleanup;
-
 	err = fentry_test__attach(fentry_skel);
-	if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err))
-		goto cleanup;
+	if (!ASSERT_OK(err, "fentry_attach"))
+		return err;
+
+	/* Check that already linked program can't be attached again. */
+	link = bpf_program__attach(fentry_skel->progs.test1);
+	if (!ASSERT_ERR_PTR(link, "fentry_attach_link"))
+		return -1;
 
 	prog_fd = bpf_program__fd(fentry_skel->progs.test1);
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	CHECK(err || retval, "test_run",
-	      "err %d errno %d retval %d duration %d\n",
-	      err, errno, retval, duration);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(retval, 0, "test_run");
 
 	result = (__u64 *)fentry_skel->bss;
-	for (i = 0; i < 6; i++) {
-		if (CHECK(result[i] != 1, "result",
-			  "fentry_test%d failed err %lld\n", i + 1, result[i]))
-			goto cleanup;
+	for (i = 0; i < sizeof(*fentry_skel->bss) / sizeof(__u64); i++) {
+		if (!ASSERT_EQ(result[i], 1, "fentry_result"))
+			return -1;
 	}
 
+	fentry_test__detach(fentry_skel);
+
+	/* zero results for re-attach test */
+	memset(fentry_skel->bss, 0, sizeof(*fentry_skel->bss));
+	return 0;
+}
+
+void test_fentry_test(void)
+{
+	struct fentry_test *fentry_skel = NULL;
+	int err;
+
+	fentry_skel = fentry_test__open_and_load();
+	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
+		goto cleanup;
+
+	err = fentry_test(fentry_skel);
+	if (!ASSERT_OK(err, "fentry_first_attach"))
+		goto cleanup;
+
+	err = fentry_test(fentry_skel);
+	ASSERT_OK(err, "fentry_second_attach");
+
 cleanup:
 	fentry_test__destroy(fentry_skel);
 }
-- 
cgit v1.2.3


From 8caadc43f2019caebbf314f7a6ae2faed791e783 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 14 Apr 2021 21:51:44 +0200
Subject: selftests/bpf: Add re-attach test to fexit_test

Adding the test to re-attach (detach/attach again) tracing
fexit programs, plus check that already linked program can't
be attached again.

Also switching to ASSERT* macros.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210414195147.1624932-5-jolsa@kernel.org
---
 .../testing/selftests/bpf/prog_tests/fexit_test.c  | 52 +++++++++++++++-------
 1 file changed, 37 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index 78d7a2765c27..6792e41f7f69 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -3,35 +3,57 @@
 #include <test_progs.h>
 #include "fexit_test.skel.h"
 
-void test_fexit_test(void)
+static int fexit_test(struct fexit_test *fexit_skel)
 {
-	struct fexit_test *fexit_skel = NULL;
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
+	struct bpf_link *link;
 	__u64 *result;
 
-	fexit_skel = fexit_test__open_and_load();
-	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
-		goto cleanup;
-
 	err = fexit_test__attach(fexit_skel);
-	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
-		goto cleanup;
+	if (!ASSERT_OK(err, "fexit_attach"))
+		return err;
+
+	/* Check that already linked program can't be attached again. */
+	link = bpf_program__attach(fexit_skel->progs.test1);
+	if (!ASSERT_ERR_PTR(link, "fexit_attach_link"))
+		return -1;
 
 	prog_fd = bpf_program__fd(fexit_skel->progs.test1);
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	CHECK(err || retval, "test_run",
-	      "err %d errno %d retval %d duration %d\n",
-	      err, errno, retval, duration);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(retval, 0, "test_run");
 
 	result = (__u64 *)fexit_skel->bss;
-	for (i = 0; i < 6; i++) {
-		if (CHECK(result[i] != 1, "result",
-			  "fexit_test%d failed err %lld\n", i + 1, result[i]))
-			goto cleanup;
+	for (i = 0; i < sizeof(*fexit_skel->bss) / sizeof(__u64); i++) {
+		if (!ASSERT_EQ(result[i], 1, "fexit_result"))
+			return -1;
 	}
 
+	fexit_test__detach(fexit_skel);
+
+	/* zero results for re-attach test */
+	memset(fexit_skel->bss, 0, sizeof(*fexit_skel->bss));
+	return 0;
+}
+
+void test_fexit_test(void)
+{
+	struct fexit_test *fexit_skel = NULL;
+	int err;
+
+	fexit_skel = fexit_test__open_and_load();
+	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
+		goto cleanup;
+
+	err = fexit_test(fexit_skel);
+	if (!ASSERT_OK(err, "fexit_first_attach"))
+		goto cleanup;
+
+	err = fexit_test(fexit_skel);
+	ASSERT_OK(err, "fexit_second_attach");
+
 cleanup:
 	fexit_test__destroy(fexit_skel);
 }
-- 
cgit v1.2.3


From cede72ad367a105852e814ef91717aac4383b853 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 14 Apr 2021 21:51:45 +0200
Subject: selftests/bpf: Add re-attach test to lsm test

Adding the test to re-attach (detach/attach again) lsm programs,
plus check that already linked program can't be attached again.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210414195147.1624932-6-jolsa@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/test_lsm.c | 48 ++++++++++++++++++-----
 1 file changed, 38 insertions(+), 10 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
index 2755e4f81499..d492e76e01cf 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
@@ -18,6 +18,8 @@ char *CMD_ARGS[] = {"true", NULL};
 #define GET_PAGE_ADDR(ADDR, PAGE_SIZE)					\
 	(char *)(((unsigned long) (ADDR + PAGE_SIZE)) & ~(PAGE_SIZE-1))
 
+static int duration = 0;
+
 int stack_mprotect(void)
 {
 	void *buf;
@@ -51,23 +53,25 @@ int exec_cmd(int *monitored_pid)
 	return -EINVAL;
 }
 
-void test_test_lsm(void)
+static int test_lsm(struct lsm *skel)
 {
-	struct lsm *skel = NULL;
-	int err, duration = 0;
+	struct bpf_link *link;
 	int buf = 1234;
-
-	skel = lsm__open_and_load();
-	if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
-		goto close_prog;
+	int err;
 
 	err = lsm__attach(skel);
 	if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
-		goto close_prog;
+		return err;
+
+	/* Check that already linked program can't be attached again. */
+	link = bpf_program__attach(skel->progs.test_int_hook);
+	if (CHECK(!IS_ERR(link), "attach_link",
+		  "re-attach without detach should not succeed"))
+		return -1;
 
 	err = exec_cmd(&skel->bss->monitored_pid);
 	if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno))
-		goto close_prog;
+		return err;
 
 	CHECK(skel->bss->bprm_count != 1, "bprm_count", "bprm_count = %d\n",
 	      skel->bss->bprm_count);
@@ -77,7 +81,7 @@ void test_test_lsm(void)
 	err = stack_mprotect();
 	if (CHECK(errno != EPERM, "stack_mprotect", "want err=EPERM, got %d\n",
 		  errno))
-		goto close_prog;
+		return err;
 
 	CHECK(skel->bss->mprotect_count != 1, "mprotect_count",
 	      "mprotect_count = %d\n", skel->bss->mprotect_count);
@@ -89,6 +93,30 @@ void test_test_lsm(void)
 	CHECK(skel->bss->copy_test != 3, "copy_test",
 	      "copy_test = %d\n", skel->bss->copy_test);
 
+	lsm__detach(skel);
+
+	skel->bss->copy_test = 0;
+	skel->bss->bprm_count = 0;
+	skel->bss->mprotect_count = 0;
+	return 0;
+}
+
+void test_test_lsm(void)
+{
+	struct lsm *skel = NULL;
+	int err;
+
+	skel = lsm__open_and_load();
+	if (CHECK(!skel, "lsm_skel_load", "lsm skeleton failed\n"))
+		goto close_prog;
+
+	err = test_lsm(skel);
+	if (CHECK(err, "test_lsm", "first attach failed\n"))
+		goto close_prog;
+
+	err = test_lsm(skel);
+	CHECK(err, "test_lsm", "second attach failed\n");
+
 close_prog:
 	lsm__destroy(skel);
 }
-- 
cgit v1.2.3


From a1c05c3b09e0a92b26b94650837bf06c664beb1b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 14 Apr 2021 21:51:46 +0200
Subject: selftests/bpf: Test that module can't be unloaded with attached
 trampoline

Adding test to verify that once we attach module's trampoline,
the module can't be unloaded.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210414195147.1624932-7-jolsa@kernel.org
---
 .../selftests/bpf/prog_tests/module_attach.c       | 23 ++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index 5bc53d53d86e..d85a69b7ce44 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -45,12 +45,18 @@ static int trigger_module_test_write(int write_sz)
 	return 0;
 }
 
+static int delete_module(const char *name, int flags)
+{
+	return syscall(__NR_delete_module, name, flags);
+}
+
 void test_module_attach(void)
 {
 	const int READ_SZ = 456;
 	const int WRITE_SZ = 457;
 	struct test_module_attach* skel;
 	struct test_module_attach__bss *bss;
+	struct bpf_link *link;
 	int err;
 
 	skel = test_module_attach__open();
@@ -84,6 +90,23 @@ void test_module_attach(void)
 	ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet");
 	ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret");
 
+	test_module_attach__detach(skel);
+
+	/* attach fentry/fexit and make sure it get's module reference */
+	link = bpf_program__attach(skel->progs.handle_fentry);
+	if (!ASSERT_OK_PTR(link, "attach_fentry"))
+		goto cleanup;
+
+	ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module");
+	bpf_link__destroy(link);
+
+	link = bpf_program__attach(skel->progs.handle_fexit);
+	if (!ASSERT_OK_PTR(link, "attach_fexit"))
+		goto cleanup;
+
+	ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module");
+	bpf_link__destroy(link);
+
 cleanup:
 	test_module_attach__destroy(skel);
 }
-- 
cgit v1.2.3


From 7bb2cc19aee8f7150851bb8668c9ff655a5e7678 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 14 Apr 2021 21:51:47 +0200
Subject: selftests/bpf: Use ASSERT macros in lsm test

Replacing CHECK with ASSERT macros.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210414195147.1624932-8-jolsa@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/test_lsm.c | 27 +++++++++--------------
 1 file changed, 10 insertions(+), 17 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
index d492e76e01cf..244c01125126 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
@@ -18,8 +18,6 @@ char *CMD_ARGS[] = {"true", NULL};
 #define GET_PAGE_ADDR(ADDR, PAGE_SIZE)					\
 	(char *)(((unsigned long) (ADDR + PAGE_SIZE)) & ~(PAGE_SIZE-1))
 
-static int duration = 0;
-
 int stack_mprotect(void)
 {
 	void *buf;
@@ -60,38 +58,33 @@ static int test_lsm(struct lsm *skel)
 	int err;
 
 	err = lsm__attach(skel);
-	if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "attach"))
 		return err;
 
 	/* Check that already linked program can't be attached again. */
 	link = bpf_program__attach(skel->progs.test_int_hook);
-	if (CHECK(!IS_ERR(link), "attach_link",
-		  "re-attach without detach should not succeed"))
+	if (!ASSERT_ERR_PTR(link, "attach_link"))
 		return -1;
 
 	err = exec_cmd(&skel->bss->monitored_pid);
-	if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno))
+	if (!ASSERT_OK(err, "exec_cmd"))
 		return err;
 
-	CHECK(skel->bss->bprm_count != 1, "bprm_count", "bprm_count = %d\n",
-	      skel->bss->bprm_count);
+	ASSERT_EQ(skel->bss->bprm_count, 1, "bprm_count");
 
 	skel->bss->monitored_pid = getpid();
 
 	err = stack_mprotect();
-	if (CHECK(errno != EPERM, "stack_mprotect", "want err=EPERM, got %d\n",
-		  errno))
+	if (!ASSERT_EQ(errno, EPERM, "stack_mprotect"))
 		return err;
 
-	CHECK(skel->bss->mprotect_count != 1, "mprotect_count",
-	      "mprotect_count = %d\n", skel->bss->mprotect_count);
+	ASSERT_EQ(skel->bss->mprotect_count, 1, "mprotect_count");
 
 	syscall(__NR_setdomainname, &buf, -2L);
 	syscall(__NR_setdomainname, 0, -3L);
 	syscall(__NR_setdomainname, ~0L, -4L);
 
-	CHECK(skel->bss->copy_test != 3, "copy_test",
-	      "copy_test = %d\n", skel->bss->copy_test);
+	ASSERT_EQ(skel->bss->copy_test, 3, "copy_test");
 
 	lsm__detach(skel);
 
@@ -107,15 +100,15 @@ void test_test_lsm(void)
 	int err;
 
 	skel = lsm__open_and_load();
-	if (CHECK(!skel, "lsm_skel_load", "lsm skeleton failed\n"))
+	if (!ASSERT_OK_PTR(skel, "lsm_skel_load"))
 		goto close_prog;
 
 	err = test_lsm(skel);
-	if (CHECK(err, "test_lsm", "first attach failed\n"))
+	if (!ASSERT_OK(err, "test_lsm_first_attach"))
 		goto close_prog;
 
 	err = test_lsm(skel);
-	CHECK(err, "test_lsm", "second attach failed\n");
+	ASSERT_OK(err, "test_lsm_second_attach");
 
 close_prog:
 	lsm__destroy(skel);
-- 
cgit v1.2.3


From 7a2fa70aaffc2f8823feca22709a00f5c069a8a9 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 26 Apr 2021 12:29:45 -0700
Subject: selftests/bpf: Add remaining ASSERT_xxx() variants

Add ASSERT_TRUE/ASSERT_FALSE for conditions calculated with custom logic to
true/false. Also add remaining arithmetical assertions:
  - ASSERT_LE -- less than or equal;
  - ASSERT_GT -- greater than;
  - ASSERT_GE -- greater than or equal.
This should cover most scenarios where people fall back to error-prone
CHECK()s.

Also extend ASSERT_ERR() to print out errno, in addition to direct error.

Also convert few CHECK() instances to ensure new ASSERT_xxx() variants work as
expected. Subsequent patch will also use ASSERT_TRUE/ASSERT_FALSE more
extensively.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210426192949.416837-2-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/btf_dump.c  |  2 +-
 .../testing/selftests/bpf/prog_tests/btf_endian.c  |  4 +-
 .../testing/selftests/bpf/prog_tests/cgroup_link.c |  2 +-
 tools/testing/selftests/bpf/prog_tests/kfree_skb.c |  2 +-
 .../selftests/bpf/prog_tests/resolve_btfids.c      |  7 +--
 .../selftests/bpf/prog_tests/snprintf_btf.c        |  4 +-
 tools/testing/selftests/bpf/test_progs.h           | 50 +++++++++++++++++++++-
 7 files changed, 56 insertions(+), 15 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index c60091ee8a21..5e129dc2073c 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -77,7 +77,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
 
 	snprintf(out_file, sizeof(out_file), "/tmp/%s.output.XXXXXX", t->file);
 	fd = mkstemp(out_file);
-	if (CHECK(fd < 0, "create_tmp", "failed to create file: %d\n", fd)) {
+	if (!ASSERT_GE(fd, 0, "create_tmp")) {
 		err = fd;
 		goto done;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_endian.c b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
index 8c52d72c876e..8ab5d3e358dd 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_endian.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
@@ -6,8 +6,6 @@
 #include <test_progs.h>
 #include <bpf/btf.h>
 
-static int duration = 0;
-
 void test_btf_endian() {
 #if __BYTE_ORDER == __LITTLE_ENDIAN
 	enum btf_endianness endian = BTF_LITTLE_ENDIAN;
@@ -71,7 +69,7 @@ void test_btf_endian() {
 
 	/* now modify original BTF */
 	var_id = btf__add_var(btf, "some_var", BTF_VAR_GLOBAL_ALLOCATED, 1);
-	CHECK(var_id <= 0, "var_id", "failed %d\n", var_id);
+	ASSERT_GT(var_id, 0, "var_id");
 
 	btf__free(swap_btf);
 	swap_btf = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
index 4d9b514b3fd9..736796e56ed1 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
@@ -54,7 +54,7 @@ void test_cgroup_link(void)
 
 	for (i = 0; i < cg_nr; i++) {
 		cgs[i].fd = create_and_get_cgroup(cgs[i].path);
-		if (CHECK(cgs[i].fd < 0, "cg_create", "fail: %d\n", cgs[i].fd))
+		if (!ASSERT_GE(cgs[i].fd, 0, "cg_create"))
 			goto cleanup;
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 42c3a3103c26..d65107919998 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -134,7 +134,7 @@ void test_kfree_skb(void)
 	/* make sure kfree_skb program was triggered
 	 * and it sent expected skb into ring buffer
 	 */
-	CHECK_FAIL(!passed);
+	ASSERT_TRUE(passed, "passed");
 
 	err = bpf_map_lookup_elem(bpf_map__fd(global_data), &zero, test_ok);
 	if (CHECK(err, "get_result",
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index 6ace5e9efec1..d3c2de2c24d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -160,11 +160,8 @@ int test_resolve_btfids(void)
 			break;
 
 		if (i > 0) {
-			ret = CHECK(test_set.ids[i - 1] > test_set.ids[i],
-				    "sort_check",
-				    "test_set is not sorted\n");
-			if (ret)
-				break;
+			if (!ASSERT_LE(test_set.ids[i - 1], test_set.ids[i], "sort_check"))
+				return -1;
 		}
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
index 686b40f11a45..76e1f5fe18fa 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
@@ -42,9 +42,7 @@ void test_snprintf_btf(void)
 	 * and it set expected return values from bpf_trace_printk()s
 	 * and all tests ran.
 	 */
-	if (CHECK(bss->ret <= 0,
-		  "bpf_snprintf_btf: got return value",
-		  "ret <= 0 %ld test %d\n", bss->ret, bss->ran_subtests))
+	if (!ASSERT_GT(bss->ret, 0, "bpf_snprintf_ret"))
 		goto cleanup;
 
 	if (CHECK(bss->ran_subtests == 0, "check if subtests ran",
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index ee7e3b45182a..dda52cb649dc 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -130,6 +130,20 @@ extern int test__join_cgroup(const char *path);
 #define CHECK_ATTR(condition, tag, format...) \
 	_CHECK(condition, tag, tattr.duration, format)
 
+#define ASSERT_TRUE(actual, name) ({					\
+	static int duration = 0;					\
+	bool ___ok = (actual);						\
+	CHECK(!___ok, (name), "unexpected %s: got FALSE\n", (name));	\
+	___ok;								\
+})
+
+#define ASSERT_FALSE(actual, name) ({					\
+	static int duration = 0;					\
+	bool ___ok = !(actual);						\
+	CHECK(!___ok, (name), "unexpected %s: got TRUE\n", (name));	\
+	___ok;								\
+})
+
 #define ASSERT_EQ(actual, expected, name) ({				\
 	static int duration = 0;					\
 	typeof(actual) ___act = (actual);				\
@@ -163,6 +177,39 @@ extern int test__join_cgroup(const char *path);
 	___ok;								\
 })
 
+#define ASSERT_LE(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act <= ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld > expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
+#define ASSERT_GT(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act > ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld <= expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
+#define ASSERT_GE(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act >= ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld < expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
 #define ASSERT_STREQ(actual, expected, name) ({				\
 	static int duration = 0;					\
 	const char *___act = actual;					\
@@ -178,7 +225,8 @@ extern int test__join_cgroup(const char *path);
 	static int duration = 0;					\
 	long long ___res = (res);					\
 	bool ___ok = ___res == 0;					\
-	CHECK(!___ok, (name), "unexpected error: %lld\n", ___res);	\
+	CHECK(!___ok, (name), "unexpected error: %lld (errno %d)\n",	\
+	      ___res, errno);						\
 	___ok;								\
 })
 
-- 
cgit v1.2.3


From 5a30eb23922b52f33222c6729b6b3ff1c37a6c66 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 26 Apr 2021 12:29:48 -0700
Subject: selftests/bpf: Fix field existence CO-RE reloc tests

Negative field existence cases for have a broken assumption that FIELD_EXISTS
CO-RE relo will fail for fields that match the name but have incompatible type
signature. That's not how CO-RE relocations generally behave. Types and fields
that match by name but not by expected type are treated as non-matching
candidates and are skipped. Error later is reported if no matching candidate
was found. That's what happens for most relocations, but existence relocations
(FIELD_EXISTS and TYPE_EXISTS) are more permissive and they are designed to
return 0 or 1, depending if a match is found. This allows to handle
name-conflicting but incompatible types in BPF code easily. Combined with
___flavor suffixes, it's possible to handle pretty much any structural type
changes in kernel within the compiled once BPF source code.

So, long story short, negative field existence test cases are invalid in their
assumptions, so this patch reworks them into a single consolidated positive
case that doesn't match any of the fields.

Fixes: c7566a69695c ("selftests/bpf: Add field existence CO-RE relocs tests")
Reported-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210426192949.416837-5-andrii@kernel.org
---
 .../testing/selftests/bpf/prog_tests/core_reloc.c  | 31 +++++++++++++---------
 ...tf__core_reloc_existence___err_wrong_arr_kind.c |  3 ---
 ...re_reloc_existence___err_wrong_arr_value_type.c |  3 ---
 ...tf__core_reloc_existence___err_wrong_int_kind.c |  3 ---
 .../btf__core_reloc_existence___err_wrong_int_sz.c |  3 ---
 ...tf__core_reloc_existence___err_wrong_int_type.c |  3 ---
 ..._core_reloc_existence___err_wrong_struct_type.c |  3 ---
 .../btf__core_reloc_existence___wrong_field_defs.c |  3 +++
 .../testing/selftests/bpf/progs/core_reloc_types.h | 20 ++------------
 9 files changed, 24 insertions(+), 48 deletions(-)
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_kind.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_value_type.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_kind.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_sz.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_type.c
 delete mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_struct_type.c
 create mode 100644 tools/testing/selftests/bpf/progs/btf__core_reloc_existence___wrong_field_defs.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index d94dcead72e6..385fd7696a2e 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -210,11 +210,6 @@ static int duration = 0;
 	.bpf_obj_file = "test_core_reloc_existence.o",			\
 	.btf_src_file = "btf__core_reloc_" #name ".o"			\
 
-#define FIELD_EXISTS_ERR_CASE(name) {					\
-	FIELD_EXISTS_CASE_COMMON(name),					\
-	.fails = true,							\
-}
-
 #define BITFIELDS_CASE_COMMON(objfile, test_name_prefix,  name)		\
 	.case_name = test_name_prefix#name,				\
 	.bpf_obj_file = objfile,					\
@@ -643,13 +638,25 @@ static struct core_reloc_test_case test_cases[] = {
 		},
 		.output_len = sizeof(struct core_reloc_existence_output),
 	},
-
-	FIELD_EXISTS_ERR_CASE(existence__err_int_sz),
-	FIELD_EXISTS_ERR_CASE(existence__err_int_type),
-	FIELD_EXISTS_ERR_CASE(existence__err_int_kind),
-	FIELD_EXISTS_ERR_CASE(existence__err_arr_kind),
-	FIELD_EXISTS_ERR_CASE(existence__err_arr_value_type),
-	FIELD_EXISTS_ERR_CASE(existence__err_struct_type),
+	{
+		FIELD_EXISTS_CASE_COMMON(existence___wrong_field_defs),
+		.input = STRUCT_TO_CHAR_PTR(core_reloc_existence___wrong_field_defs) {
+		},
+		.input_len = sizeof(struct core_reloc_existence___wrong_field_defs),
+		.output = STRUCT_TO_CHAR_PTR(core_reloc_existence_output) {
+			.a_exists = 0,
+			.b_exists = 0,
+			.c_exists = 0,
+			.arr_exists = 0,
+			.s_exists = 0,
+			.a_value = 0xff000001u,
+			.b_value = 0xff000002u,
+			.c_value = 0xff000003u,
+			.arr_value = 0xff000004u,
+			.s_value = 0xff000005u,
+		},
+		.output_len = sizeof(struct core_reloc_existence_output),
+	},
 
 	/* bitfield relocation checks */
 	BITFIELDS_CASE(bitfields, {
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_kind.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_kind.c
deleted file mode 100644
index dd0ffa518f36..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_kind.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_existence___err_wrong_arr_kind x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_value_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_value_type.c
deleted file mode 100644
index bc83372088ad..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_arr_value_type.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_existence___err_wrong_arr_value_type x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_kind.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_kind.c
deleted file mode 100644
index 917bec41be08..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_kind.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_existence___err_wrong_int_kind x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_sz.c
deleted file mode 100644
index 6ec7e6ec1c91..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_sz.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_existence___err_wrong_int_sz x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_type.c
deleted file mode 100644
index 7bbcacf2b0d1..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_int_type.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_existence___err_wrong_int_type x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_struct_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_struct_type.c
deleted file mode 100644
index f384dd38ec70..000000000000
--- a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___err_wrong_struct_type.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include "core_reloc_types.h"
-
-void f(struct core_reloc_existence___err_wrong_struct_type x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___wrong_field_defs.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___wrong_field_defs.c
new file mode 100644
index 000000000000..d14b496190c3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_existence___wrong_field_defs.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_existence___wrong_field_defs x) {}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 9982eb969048..c95c0cabe951 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -700,27 +700,11 @@ struct core_reloc_existence___minimal {
 	int a;
 };
 
-struct core_reloc_existence___err_wrong_int_sz {
-	short a;
-};
-
-struct core_reloc_existence___err_wrong_int_type {
+struct core_reloc_existence___wrong_field_defs {
+	void *a;
 	int b[1];
-};
-
-struct core_reloc_existence___err_wrong_int_kind {
 	struct{ int x; } c;
-};
-
-struct core_reloc_existence___err_wrong_arr_kind {
 	int arr;
-};
-
-struct core_reloc_existence___err_wrong_arr_value_type {
-	short arr[1];
-};
-
-struct core_reloc_existence___err_wrong_struct_type {
 	int s;
 };
 
-- 
cgit v1.2.3


From bede0ebf0be87e9678103486a77f39e0334c6791 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 26 Apr 2021 12:29:49 -0700
Subject: selftests/bpf: Fix core_reloc test runner

Fix failed tests checks in core_reloc test runner, which allowed failing tests
to pass quietly. Also add extra check to make sure that expected to fail test cases with
invalid names are caught as test failure anyway, as this is not an expected
failure mode. Also fix mislabeled probed vs direct bitfield test cases.

Fixes: 124a892d1c41 ("selftests/bpf: Test TYPE_EXISTS and TYPE_SIZE CO-RE relocations")
Reported-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210426192949.416837-6-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/core_reloc.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 385fd7696a2e..607710826dca 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -217,7 +217,7 @@ static int duration = 0;
 
 #define BITFIELDS_CASE(name, ...) {					\
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o",	\
-			      "direct:", name),				\
+			      "probed:", name),				\
 	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) __VA_ARGS__,	\
 	.input_len = sizeof(struct core_reloc_##name),			\
 	.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output)	\
@@ -225,7 +225,7 @@ static int duration = 0;
 	.output_len = sizeof(struct core_reloc_bitfields_output),	\
 }, {									\
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
-			      "probed:", name),				\
+			      "direct:", name),				\
 	.input = STRUCT_TO_CHAR_PTR(core_reloc_##name) __VA_ARGS__,	\
 	.input_len = sizeof(struct core_reloc_##name),			\
 	.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output)	\
@@ -546,8 +546,7 @@ static struct core_reloc_test_case test_cases[] = {
 	ARRAYS_ERR_CASE(arrays___err_too_small),
 	ARRAYS_ERR_CASE(arrays___err_too_shallow),
 	ARRAYS_ERR_CASE(arrays___err_non_array),
-	ARRAYS_ERR_CASE(arrays___err_wrong_val_type1),
-	ARRAYS_ERR_CASE(arrays___err_wrong_val_type2),
+	ARRAYS_ERR_CASE(arrays___err_wrong_val_type),
 	ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr),
 
 	/* enum/ptr/int handling scenarios */
@@ -865,13 +864,20 @@ void test_core_reloc(void)
 			  "prog '%s' not found\n", probe_name))
 			goto cleanup;
 
+
+		if (test_case->btf_src_file) {
+			err = access(test_case->btf_src_file, R_OK);
+			if (!ASSERT_OK(err, "btf_src_file"))
+				goto cleanup;
+		}
+
 		load_attr.obj = obj;
 		load_attr.log_level = 0;
 		load_attr.target_btf_path = test_case->btf_src_file;
 		err = bpf_object__load_xattr(&load_attr);
 		if (err) {
 			if (!test_case->fails)
-				CHECK(false, "obj_load", "failed to load prog '%s': %d\n", probe_name, err);
+				ASSERT_OK(err, "obj_load");
 			goto cleanup;
 		}
 
@@ -910,10 +916,8 @@ void test_core_reloc(void)
 			goto cleanup;
 		}
 
-		if (test_case->fails) {
-			CHECK(false, "obj_load_fail", "should fail to load prog '%s'\n", probe_name);
+		if (!ASSERT_FALSE(test_case->fails, "obj_load_should_fail"))
 			goto cleanup;
-		}
 
 		equal = memcmp(data->out, test_case->output,
 			       test_case->output_len) == 0;
-- 
cgit v1.2.3


From 10bf4e83167cc68595b85fd73bb91e8f2c086e36 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 23 Apr 2021 13:59:55 +0000
Subject: bpf: Fix propagation of 32 bit unsigned bounds from 64 bit bounds

Similarly as b02709587ea3 ("bpf: Fix propagation of 32-bit signed bounds
from 64-bit bounds."), we also need to fix the propagation of 32 bit
unsigned bounds from 64 bit counterparts. That is, really only set the
u32_{min,max}_value when /both/ {umin,umax}_value safely fit in 32 bit
space. For example, the register with a umin_value == 1 does /not/ imply
that u32_min_value is also equal to 1, since umax_value could be much
larger than 32 bit subregister can hold, and thus u32_min_value is in
the interval [0,1] instead.

Before fix, invalid tracking result of R2_w=inv1:

  [...]
  5: R0_w=inv1337 R1=ctx(id=0,off=0,imm=0) R2_w=inv(id=0) R10=fp0
  5: (35) if r2 >= 0x1 goto pc+1
  [...] // goto path
  7: R0=inv1337 R1=ctx(id=0,off=0,imm=0) R2=inv(id=0,umin_value=1) R10=fp0
  7: (b6) if w2 <= 0x1 goto pc+1
  [...] // goto path
  9: R0=inv1337 R1=ctx(id=0,off=0,imm=0) R2=inv(id=0,smin_value=-9223372036854775807,smax_value=9223372032559808513,umin_value=1,umax_value=18446744069414584321,var_off=(0x1; 0xffffffff00000000),s32_min_value=1,s32_max_value=1,u32_max_value=1) R10=fp0
  9: (bc) w2 = w2
  10: R0=inv1337 R1=ctx(id=0,off=0,imm=0) R2_w=inv1 R10=fp0
  [...]

After fix, correct tracking result of R2_w=inv(id=0,umax_value=1,var_off=(0x0; 0x1)):

  [...]
  5: R0_w=inv1337 R1=ctx(id=0,off=0,imm=0) R2_w=inv(id=0) R10=fp0
  5: (35) if r2 >= 0x1 goto pc+1
  [...] // goto path
  7: R0=inv1337 R1=ctx(id=0,off=0,imm=0) R2=inv(id=0,umin_value=1) R10=fp0
  7: (b6) if w2 <= 0x1 goto pc+1
  [...] // goto path
  9: R0=inv1337 R1=ctx(id=0,off=0,imm=0) R2=inv(id=0,smax_value=9223372032559808513,umax_value=18446744069414584321,var_off=(0x0; 0xffffffff00000001),s32_min_value=0,s32_max_value=1,u32_max_value=1) R10=fp0
  9: (bc) w2 = w2
  10: R0=inv1337 R1=ctx(id=0,off=0,imm=0) R2_w=inv(id=0,umax_value=1,var_off=(0x0; 0x1)) R10=fp0
  [...]

Thus, same issue as in b02709587ea3 holds for unsigned subregister tracking.
Also, align __reg64_bound_u32() similarly to __reg64_bound_s32() as done in
b02709587ea3 to make them uniform again.

Fixes: 3f50f132d840 ("bpf: Verifier, do explicit ALU32 bounds tracking")
Reported-by: Manfred Paul (@_manfp)
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                               | 8 +++-----
 tools/testing/selftests/bpf/verifier/array_access.c | 2 +-
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 637462e9b6ee..9145f88b2a0a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1398,9 +1398,7 @@ static bool __reg64_bound_s32(s64 a)
 
 static bool __reg64_bound_u32(u64 a)
 {
-	if (a > U32_MIN && a < U32_MAX)
-		return true;
-	return false;
+	return a > U32_MIN && a < U32_MAX;
 }
 
 static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
@@ -1411,10 +1409,10 @@ static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
 		reg->s32_min_value = (s32)reg->smin_value;
 		reg->s32_max_value = (s32)reg->smax_value;
 	}
-	if (__reg64_bound_u32(reg->umin_value))
+	if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) {
 		reg->u32_min_value = (u32)reg->umin_value;
-	if (__reg64_bound_u32(reg->umax_value))
 		reg->u32_max_value = (u32)reg->umax_value;
+	}
 
 	/* Intersecting with the old var_off might have improved our bounds
 	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index 1b138cd2b187..1b1c798e9248 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -186,7 +186,7 @@
 	},
 	.fixup_map_hash_48b = { 3 },
 	.errstr_unpriv = "R0 leaks addr",
-	.errstr = "invalid access to map value, value_size=48 off=44 size=8",
+	.errstr = "R0 unbounded memory access",
 	.result_unpriv = REJECT,
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-- 
cgit v1.2.3


From 3733bfbbdd28f7a65340d0058d15d15190a4944a Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@gmail.com>
Date: Sat, 24 Apr 2021 18:45:10 -0300
Subject: bpf, selftests: Update array map tests for per-cpu batched ops

Follows the same logic as the hashtable tests.

Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210424214510.806627-3-pctammela@mojatatu.com
---
 .../selftests/bpf/map_tests/array_map_batch_ops.c  | 104 +++++++++++++++------
 1 file changed, 75 insertions(+), 29 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
index e42ea1195d18..f4d870da7684 100644
--- a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
@@ -9,10 +9,13 @@
 
 #include <test_maps.h>
 
+static int nr_cpus;
+
 static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
-			     int *values)
+			     __s64 *values, bool is_pcpu)
 {
-	int i, err;
+	int i, j, err;
+	int cpu_offset = 0;
 	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
 		.elem_flags = 0,
 		.flags = 0,
@@ -20,22 +23,41 @@ static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
 
 	for (i = 0; i < max_entries; i++) {
 		keys[i] = i;
-		values[i] = i + 1;
+		if (is_pcpu) {
+			cpu_offset = i * nr_cpus;
+			for (j = 0; j < nr_cpus; j++)
+				(values + cpu_offset)[j] = i + 1 + j;
+		} else {
+			values[i] = i + 1;
+		}
 	}
 
 	err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
 	CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
 }
 
-static void map_batch_verify(int *visited, __u32 max_entries,
-			     int *keys, int *values)
+static void map_batch_verify(int *visited, __u32 max_entries, int *keys,
+			     __s64 *values, bool is_pcpu)
 {
-	int i;
+	int i, j;
+	int cpu_offset = 0;
 
 	memset(visited, 0, max_entries * sizeof(*visited));
 	for (i = 0; i < max_entries; i++) {
-		CHECK(keys[i] + 1 != values[i], "key/value checking",
-		      "error: i %d key %d value %d\n", i, keys[i], values[i]);
+		if (is_pcpu) {
+			cpu_offset = i * nr_cpus;
+			for (j = 0; j < nr_cpus; j++) {
+				__s64 value = (values + cpu_offset)[j];
+				CHECK(keys[i] + j + 1 != value,
+				      "key/value checking",
+				      "error: i %d j %d key %d value %lld\n", i,
+				      j, keys[i], value);
+			}
+		} else {
+			CHECK(keys[i] + 1 != values[i], "key/value checking",
+			      "error: i %d key %d value %lld\n", i, keys[i],
+			      values[i]);
+		}
 		visited[i] = 1;
 	}
 	for (i = 0; i < max_entries; i++) {
@@ -44,19 +66,21 @@ static void map_batch_verify(int *visited, __u32 max_entries,
 	}
 }
 
-void test_array_map_batch_ops(void)
+static void __test_map_lookup_and_update_batch(bool is_pcpu)
 {
 	struct bpf_create_map_attr xattr = {
 		.name = "array_map",
-		.map_type = BPF_MAP_TYPE_ARRAY,
+		.map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_ARRAY :
+				      BPF_MAP_TYPE_ARRAY,
 		.key_size = sizeof(int),
-		.value_size = sizeof(int),
+		.value_size = sizeof(__s64),
 	};
-	int map_fd, *keys, *values, *visited;
+	int map_fd, *keys, *visited;
 	__u32 count, total, total_success;
 	const __u32 max_entries = 10;
 	__u64 batch = 0;
-	int err, step;
+	int err, step, value_size;
+	void *values;
 	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
 		.elem_flags = 0,
 		.flags = 0,
@@ -67,22 +91,23 @@ void test_array_map_batch_ops(void)
 	CHECK(map_fd == -1,
 	      "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
 
-	keys = malloc(max_entries * sizeof(int));
-	values = malloc(max_entries * sizeof(int));
-	visited = malloc(max_entries * sizeof(int));
+	value_size = sizeof(__s64);
+	if (is_pcpu)
+		value_size *= nr_cpus;
+
+	keys = calloc(max_entries, sizeof(*keys));
+	values = calloc(max_entries, value_size);
+	visited = calloc(max_entries, sizeof(*visited));
 	CHECK(!keys || !values || !visited, "malloc()", "error:%s\n",
 	      strerror(errno));
 
-	/* populate elements to the map */
-	map_batch_update(map_fd, max_entries, keys, values);
-
 	/* test 1: lookup in a loop with various steps. */
 	total_success = 0;
 	for (step = 1; step < max_entries; step++) {
-		map_batch_update(map_fd, max_entries, keys, values);
-		map_batch_verify(visited, max_entries, keys, values);
+		map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+		map_batch_verify(visited, max_entries, keys, values, is_pcpu);
 		memset(keys, 0, max_entries * sizeof(*keys));
-		memset(values, 0, max_entries * sizeof(*values));
+		memset(values, 0, max_entries * value_size);
 		batch = 0;
 		total = 0;
 		/* iteratively lookup/delete elements with 'step'
@@ -91,10 +116,10 @@ void test_array_map_batch_ops(void)
 		count = step;
 		while (true) {
 			err = bpf_map_lookup_batch(map_fd,
-						total ? &batch : NULL, &batch,
-						keys + total,
-						values + total,
-						&count, &opts);
+						   total ? &batch : NULL,
+						   &batch, keys + total,
+						   values + total * value_size,
+						   &count, &opts);
 
 			CHECK((err && errno != ENOENT), "lookup with steps",
 			      "error: %s\n", strerror(errno));
@@ -108,7 +133,7 @@ void test_array_map_batch_ops(void)
 		CHECK(total != max_entries, "lookup with steps",
 		      "total = %u, max_entries = %u\n", total, max_entries);
 
-		map_batch_verify(visited, max_entries, keys, values);
+		map_batch_verify(visited, max_entries, keys, values, is_pcpu);
 
 		total_success++;
 	}
@@ -116,9 +141,30 @@ void test_array_map_batch_ops(void)
 	CHECK(total_success == 0, "check total_success",
 	      "unexpected failure\n");
 
-	printf("%s:PASS\n", __func__);
-
 	free(keys);
 	free(values);
 	free(visited);
 }
+
+static void array_map_batch_ops(void)
+{
+	__test_map_lookup_and_update_batch(false);
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void array_percpu_map_batch_ops(void)
+{
+	__test_map_lookup_and_update_batch(true);
+	printf("test_%s:PASS\n", __func__);
+}
+
+void test_array_map_batch_ops(void)
+{
+	nr_cpus = libbpf_num_possible_cpus();
+
+	CHECK(nr_cpus < 0, "nr_cpus checking",
+	      "error: get possible cpus failed");
+
+	array_map_batch_ops();
+	array_percpu_map_batch_ops();
+}
-- 
cgit v1.2.3