Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2021-11-05

We've added 15 non-merge commits during the last 3 day(s) which contain
a total of 14 files changed, 199 insertions(+), 90 deletions(-).

The main changes are:

1) Fix regression from stack spill/fill of <8 byte scalars, from Martin KaFai Lau.

2) Fix perf's build of bpftool's bootstrap version due to missing libbpf
   headers, from Quentin Monnet.

3) Fix riscv{32,64} BPF exception tables build errors and warnings, from Björn Töpel.

4) Fix bpf fs to allow RENAME_EXCHANGE support for atomic upgrades on sk_lookup
   control planes, from Lorenz Bauer.

5) Fix libbpf's error reporting in bpf_map_lookup_and_delete_elem_flags() due to
   missing libbpf_err_errno(), from Mehrdad Arshad Rad.

6) Various fixes to make xdp_redirect_multi selftest more reliable, from Hangbin Liu.

7) Fix netcnt selftest to make it run serial and thus avoid conflicts with other
   cgroup/skb selftests run in parallel that could cause flakes, from Andrii Nakryiko.

8) Fix reuseport_bpf_numa networking selftest to skip unavailable NUMA nodes,
   from Kleber Sacilotto de Souza.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  riscv, bpf: Fix RV32 broken build, and silence RV64 warning
  selftests/bpf/xdp_redirect_multi: Limit the tests in netns
  selftests/bpf/xdp_redirect_multi: Give tcpdump a chance to terminate cleanly
  selftests/bpf/xdp_redirect_multi: Use arping to accurate the arp number
  selftests/bpf/xdp_redirect_multi: Put the logs to tmp folder
  libbpf: Fix lookup_and_delete_elem_flags error reporting
  bpftool: Install libbpf headers for the bootstrap version, too
  selftests/net: Fix reuseport_bpf_numa by skipping unavailable nodes
  selftests/bpf: Verifier test on refill from a smaller spill
  bpf: Do not reject when the stack read size is different from the tracked scalar size
  selftests/bpf: Make netcnt selftests serial to avoid spurious failures
  selftests/bpf: Test RENAME_EXCHANGE and RENAME_NOREPLACE on bpffs
  selftests/bpf: Convert test_bpffs to ASSERT macros
  libfs: Support RENAME_EXCHANGE in simple_rename()
  libfs: Move shmem_exchange to simple_rename_exchange
====================

Link: https://lore.kernel.org/r/20211105165803.29372-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 133 insertions, 41 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c
index 6ede48bde91b..954964f0ac3d 100644
--- a/tools/testing/selftests/bpf/prog_tests/netcnt.c
+++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c
@@ -8,7 +8,7 @@
 
 #define CG_NAME "/netcnt"
 
-void test_netcnt(void)
+void serial_test_netcnt(void)
 {
 	union percpu_net_cnt *percpu_netcnt = NULL;
 	struct bpf_cgroup_storage_key key;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
index 172c999e523c..d29ebfeef9c5 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
 #define _GNU_SOURCE
+#include <stdio.h>
 #include <sched.h>
 #include <sys/mount.h>
 #include <sys/stat.h>
@@ -29,44 +30,106 @@ static int read_iter(char *file)
 
 static int fn(void)
 {
-	int err, duration = 0;
+	struct stat a, b, c;
+	int err, map;
 
 	err = unshare(CLONE_NEWNS);
-	if (CHECK(err, "unshare", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "unshare"))
 		goto out;
 
 	err = mount("", "/", "", MS_REC | MS_PRIVATE, NULL);
-	if (CHECK(err, "mount /", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount /"))
 		goto out;
 
 	err = umount(TDIR);
-	if (CHECK(err, "umount " TDIR, "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "umount " TDIR))
 		goto out;
 
 	err = mount("none", TDIR, "tmpfs", 0, NULL);
-	if (CHECK(err, "mount", "mount root failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount tmpfs"))
 		goto out;
 
 	err = mkdir(TDIR "/fs1", 0777);
-	if (CHECK(err, "mkdir "TDIR"/fs1", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mkdir " TDIR "/fs1"))
 		goto out;
 	err = mkdir(TDIR "/fs2", 0777);
-	if (CHECK(err, "mkdir "TDIR"/fs2", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mkdir " TDIR "/fs2"))
 		goto out;
 
 	err = mount("bpf", TDIR "/fs1", "bpf", 0, NULL);
-	if (CHECK(err, "mount bpffs "TDIR"/fs1", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs1"))
 		goto out;
 	err = mount("bpf", TDIR "/fs2", "bpf", 0, NULL);
-	if (CHECK(err, "mount bpffs " TDIR "/fs2", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs2"))
 		goto out;
 
 	err = read_iter(TDIR "/fs1/maps.debug");
-	if (CHECK(err, "reading " TDIR "/fs1/maps.debug", "failed\n"))
+	if (!ASSERT_OK(err, "reading " TDIR "/fs1/maps.debug"))
 		goto out;
 	err = read_iter(TDIR "/fs2/progs.debug");
-	if (CHECK(err, "reading " TDIR "/fs2/progs.debug", "failed\n"))
+	if (!ASSERT_OK(err, "reading " TDIR "/fs2/progs.debug"))
 		goto out;
+
+	err = mkdir(TDIR "/fs1/a", 0777);
+	if (!ASSERT_OK(err, "creating " TDIR "/fs1/a"))
+		goto out;
+	err = mkdir(TDIR "/fs1/a/1", 0777);
+	if (!ASSERT_OK(err, "creating " TDIR "/fs1/a/1"))
+		goto out;
+	err = mkdir(TDIR "/fs1/b", 0777);
+	if (!ASSERT_OK(err, "creating " TDIR "/fs1/b"))
+		goto out;
+
+	map = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0);
+	if (!ASSERT_GT(map, 0, "create_map(ARRAY)"))
+		goto out;
+	err = bpf_obj_pin(map, TDIR "/fs1/c");
+	if (!ASSERT_OK(err, "pin map"))
+		goto out;
+	close(map);
+
+	/* Check that RENAME_EXCHANGE works for directories. */
+	err = stat(TDIR "/fs1/a", &a);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/a)"))
+		goto out;
+	err = renameat2(0, TDIR "/fs1/a", 0, TDIR "/fs1/b", RENAME_EXCHANGE);
+	if (!ASSERT_OK(err, "renameat2(/fs1/a, /fs1/b, RENAME_EXCHANGE)"))
+		goto out;
+	err = stat(TDIR "/fs1/b", &b);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)"))
+		goto out;
+	if (!ASSERT_EQ(a.st_ino, b.st_ino, "b should have a's inode"))
+		goto out;
+	err = access(TDIR "/fs1/b/1", F_OK);
+	if (!ASSERT_OK(err, "access(" TDIR "/fs1/b/1)"))
+		goto out;
+
+	/* Check that RENAME_EXCHANGE works for mixed file types. */
+	err = stat(TDIR "/fs1/c", &c);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/map)"))
+		goto out;
+	err = renameat2(0, TDIR "/fs1/c", 0, TDIR "/fs1/b", RENAME_EXCHANGE);
+	if (!ASSERT_OK(err, "renameat2(/fs1/c, /fs1/b, RENAME_EXCHANGE)"))
+		goto out;
+	err = stat(TDIR "/fs1/b", &b);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)"))
+		goto out;
+	if (!ASSERT_EQ(c.st_ino, b.st_ino, "b should have c's inode"))
+		goto out;
+	err = access(TDIR "/fs1/c/1", F_OK);
+	if (!ASSERT_OK(err, "access(" TDIR "/fs1/c/1)"))
+		goto out;
+
+	/* Check that RENAME_NOREPLACE works. */
+	err = renameat2(0, TDIR "/fs1/b", 0, TDIR "/fs1/a", RENAME_NOREPLACE);
+	if (!ASSERT_ERR(err, "renameat2(RENAME_NOREPLACE)")) {
+		err = -EINVAL;
+		goto out;
+	}
+	err = access(TDIR "/fs1/b", F_OK);
+	if (!ASSERT_OK(err, "access(" TDIR "/fs1/b)"))
+		goto out;
+
 out:
 	umount(TDIR "/fs1");
 	umount(TDIR "/fs2");
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
index 351955c2bdfd..05f872740999 100755
--- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
+++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
@@ -2,11 +2,11 @@
 # SPDX-License-Identifier: GPL-2.0
 #
 # Test topology:
-#     - - - - - - - - - - - - - - - - - - - - - - - - -
-#    | veth1         veth2         veth3 |  ... init net
+#    - - - - - - - - - - - - - - - - - - -
+#    | veth1         veth2         veth3 |  ns0
 #     - -| - - - - - - | - - - - - - | - -
 #    ---------     ---------     ---------
-#    | veth0 |     | veth0 |     | veth0 |  ...
+#    | veth0 |     | veth0 |     | veth0 |
 #    ---------     ---------     ---------
 #       ns1           ns2           ns3
 #
@@ -31,6 +31,7 @@ IFACES=""
 DRV_MODE="xdpgeneric xdpdrv xdpegress"
 PASS=0
 FAIL=0
+LOG_DIR=$(mktemp -d)
 
 test_pass()
 {
@@ -50,6 +51,7 @@ clean_up()
 		ip link del veth$i 2> /dev/null
 		ip netns del ns$i 2> /dev/null
 	done
+	ip netns del ns0 2> /dev/null
 }
 
 # Kselftest framework requirement - SKIP code is 4.
@@ -77,10 +79,12 @@ setup_ns()
 		mode="xdpdrv"
 	fi
 
+	ip netns add ns0
 	for i in $(seq $NUM); do
 	        ip netns add ns$i
-	        ip link add veth$i type veth peer name veth0 netns ns$i
-		ip link set veth$i up
+		ip -n ns$i link add veth0 index 2 type veth \
+			peer name veth$i netns ns0 index $((1 + $i))
+		ip -n ns0 link set veth$i up
 		ip -n ns$i link set veth0 up
 
 		ip -n ns$i addr add 192.0.2.$i/24 dev veth0
@@ -91,7 +95,7 @@ setup_ns()
 			xdp_dummy.o sec xdp &> /dev/null || \
 			{ test_fail "Unable to load dummy xdp" && exit 1; }
 		IFACES="$IFACES veth$i"
-		veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}')
+		veth_mac[$i]=$(ip -n ns0 link show veth$i | awk '/link\/ether/ {print $2}')
 	done
 }
 
@@ -100,17 +104,17 @@ do_egress_tests()
 	local mode=$1
 
 	# mac test
-	ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-2_${mode}.log &
-	ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-3_${mode}.log &
+	ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log &
+	ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log &
 	sleep 0.5
 	ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
 	sleep 0.5
-	pkill -9 tcpdump
+	pkill tcpdump
 
 	# mac check
-	grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" mac_ns1-2_${mode}.log && \
+	grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-2_${mode}.log && \
 	       test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2"
-	grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" mac_ns1-3_${mode}.log && \
+	grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-3_${mode}.log && \
 		test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3"
 }
 
@@ -121,46 +125,46 @@ do_ping_tests()
 	# ping6 test: echo request should be redirect back to itself, not others
 	ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02
 
-	ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ns1-1_${mode}.log &
-	ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ns1-2_${mode}.log &
-	ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ns1-3_${mode}.log &
+	ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log &
+	ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log &
+	ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log &
 	sleep 0.5
 	# ARP test
-	ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
+	ip netns exec ns1 arping -q -c 2 -I veth0 192.0.2.254
 	# IPv4 test
 	ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null
 	# IPv6 test
 	ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null
 	sleep 0.5
-	pkill -9 tcpdump
+	pkill tcpdump
 
 	# All netns should receive the redirect arp requests
-	[ $(grep -c "who-has 192.0.2.254" ns1-1_${mode}.log) -gt 4 ] && \
+	[ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
 		test_pass "$mode arp(F_BROADCAST) ns1-1" || \
 		test_fail "$mode arp(F_BROADCAST) ns1-1"
-	[ $(grep -c "who-has 192.0.2.254" ns1-2_${mode}.log) -le 4 ] && \
+	[ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-2_${mode}.log) -eq 2 ] && \
 		test_pass "$mode arp(F_BROADCAST) ns1-2" || \
 		test_fail "$mode arp(F_BROADCAST) ns1-2"
-	[ $(grep -c "who-has 192.0.2.254" ns1-3_${mode}.log) -le 4 ] && \
+	[ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-3_${mode}.log) -eq 2 ] && \
 		test_pass "$mode arp(F_BROADCAST) ns1-3" || \
 		test_fail "$mode arp(F_BROADCAST) ns1-3"
 
 	# ns1 should not receive the redirect echo request, others should
-	[ $(grep -c "ICMP echo request" ns1-1_${mode}.log) -eq 4 ] && \
+	[ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
 		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \
 		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1"
-	[ $(grep -c "ICMP echo request" ns1-2_${mode}.log) -eq 4 ] && \
+	[ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 4 ] && \
 		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \
 		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2"
-	[ $(grep -c "ICMP echo request" ns1-3_${mode}.log) -eq 4 ] && \
+	[ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-3_${mode}.log) -eq 4 ] && \
 		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \
 		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3"
 
 	# ns1 should receive the echo request, ns2 should not
-	[ $(grep -c "ICMP6, echo request" ns1-1_${mode}.log) -eq 4 ] && \
+	[ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
 		test_pass "$mode IPv6 (no flags) ns1-1" || \
 		test_fail "$mode IPv6 (no flags) ns1-1"
-	[ $(grep -c "ICMP6, echo request" ns1-2_${mode}.log) -eq 0 ] && \
+	[ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 0 ] && \
 		test_pass "$mode IPv6 (no flags) ns1-2" || \
 		test_fail "$mode IPv6 (no flags) ns1-2"
 }
@@ -176,9 +180,13 @@ do_tests()
 		xdpgeneric) drv_p="-S";;
 	esac
 
-	./xdp_redirect_multi $drv_p $IFACES &> xdp_redirect_${mode}.log &
+	ip netns exec ns0 ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log &
 	xdp_pid=$!
 	sleep 1
+	if ! ps -p $xdp_pid > /dev/null; then
+		test_fail "$mode xdp_redirect_multi start failed"
+		return 1
+	fi
 
 	if [ "$mode" = "xdpegress" ]; then
 		do_egress_tests $mode
@@ -189,16 +197,16 @@ do_tests()
 	kill $xdp_pid
 }
 
-trap clean_up 0 2 3 6 9
+trap clean_up EXIT
 
 check_env
-rm -f xdp_redirect_*.log ns*.log mac_ns*.log
 
 for mode in ${DRV_MODE}; do
 	setup_ns $mode
 	do_tests $mode
 	clean_up
 done
+rm -rf ${LOG_DIR}
 
 echo "Summary: PASS $PASS, FAIL $FAIL"
 [ $FAIL -eq 0 ] && exit 0 || exit 1
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index c9991c3f3bd2..7ab3de108761 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -265,3 +265,20 @@
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 },
+{
+	"Spill a u32 scalar at fp-4 and then at fp-8",
+	.insns = {
+	/* r4 = 4321 */
+	BPF_MOV32_IMM(BPF_REG_4, 4321),
+	/* *(u32 *)(r10 -4) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4),
+	/* *(u32 *)(r10 -8) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
+	/* r4 = *(u64 *)(r10 -8) */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c
index 3696a8f32c23..f5ffba341c17 100644
--- a/tools/testing/selftests/bpf/xdp_redirect_multi.c
+++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c
@@ -129,7 +129,7 @@ int main(int argc, char **argv)
 		goto err_out;
 	}
 
-	printf("Get interfaces");
+	printf("Get interfaces:");
 	for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
 		ifaces[i] = if_nametoindex(argv[optind + i]);
 		if (!ifaces[i])
@@ -139,7 +139,7 @@ int main(int argc, char **argv)
 			goto err_out;
 		}
 		if (ifaces[i] > MAX_INDEX_NUM) {
-			printf("Interface index to large\n");
+			printf(" interface index too large\n");
 			goto err_out;
 		}
 		printf(" %d", ifaces[i]);
diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c
index c9f478b40996..b2eebf669b8c 100644
--- a/tools/testing/selftests/net/reuseport_bpf_numa.c
+++ b/tools/testing/selftests/net/reuseport_bpf_numa.c
@@ -211,12 +211,16 @@ static void test(int *rcv_fd, int len, int family, int proto)
 
 	/* Forward iterate */
 	for (node = 0; node < len; ++node) {
+		if (!numa_bitmask_isbitset(numa_nodes_ptr, node))
+			continue;
 		send_from_node(node, family, proto);
 		receive_on_node(rcv_fd, len, epfd, node, proto);
 	}
 
 	/* Reverse iterate */
 	for (node = len - 1; node >= 0; --node) {
+		if (!numa_bitmask_isbitset(numa_nodes_ptr, node))
+			continue;
 		send_from_node(node, family, proto);
 		receive_on_node(rcv_fd, len, epfd, node, proto);
 	}