Merge 5.0-rc6 into char-misc-next

We need the char-misc fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

19 files changed, 1406 insertions, 60 deletions

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 1a2bd15c5b6e..400ee81a3043 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -10,6 +10,7 @@ TARGETS += drivers/dma-buf
 TARGETS += efivarfs
 TARGETS += exec
 TARGETS += filesystems
+TARGETS += filesystems/binderfs
 TARGETS += firmware
 TARGETS += ftrace
 TARGETS += futex
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 315a44fa32af..84fd6f1bf33e 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -13,7 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void)
 	unsigned int start, end, possible_cpus = 0;
 	char buff[128];
 	FILE *fp;
-	int n;
+	int len, n, i, j = 0;
 
 	fp = fopen(fcpu, "r");
 	if (!fp) {
@@ -21,17 +21,27 @@ static inline unsigned int bpf_num_possible_cpus(void)
 		exit(1);
 	}
 
-	while (fgets(buff, sizeof(buff), fp)) {
-		n = sscanf(buff, "%u-%u", &start, &end);
-		if (n == 0) {
-			printf("Failed to retrieve # possible CPUs!\n");
-			exit(1);
-		} else if (n == 1) {
-			end = start;
+	if (!fgets(buff, sizeof(buff), fp)) {
+		printf("Failed to read %s!\n", fcpu);
+		exit(1);
+	}
+
+	len = strlen(buff);
+	for (i = 0; i <= len; i++) {
+		if (buff[i] == ',' || buff[i] == '\0') {
+			buff[i] = '\0';
+			n = sscanf(&buff[j], "%u-%u", &start, &end);
+			if (n <= 0) {
+				printf("Failed to retrieve # possible CPUs!\n");
+				exit(1);
+			} else if (n == 1) {
+				end = start;
+			}
+			possible_cpus += end - start + 1;
+			j = i + 1;
 		}
-		possible_cpus = start == 0 ? end + 1 : 0;
-		break;
 	}
+
 	fclose(fp);
 
 	return possible_cpus;
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index a0bd04befe87..91420fa83b08 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -1881,13 +1881,12 @@ static struct btf_raw_test raw_tests[] = {
 },
 
 {
-	.descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)",
+	.descr = "func proto (TYPEDEF=>FUNC_PROTO)",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
-		BTF_CONST_ENC(4),				/* [3] */
-		BTF_TYPEDEF_ENC(NAME_TBD, 5),			/* [4] */
-		BTF_FUNC_PROTO_ENC(0, 2),			/* [5] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),			/* [3] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [4] */
 			BTF_FUNC_PROTO_ARG_ENC(0, 1),
 			BTF_FUNC_PROTO_ARG_ENC(0, 2),
 		BTF_END_RAW,
@@ -1901,8 +1900,6 @@ static struct btf_raw_test raw_tests[] = {
 	.key_type_id = 1,
 	.value_type_id = 1,
 	.max_entries = 4,
-	.btf_load_err = true,
-	.err_str = "Invalid type_id",
 },
 
 {
diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
index bab13dd025a6..0d26b5e3f966 100755
--- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
+++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
@@ -37,6 +37,10 @@ prerequisite()
 		exit $ksft_skip
 	fi
 
+	present_cpus=`cat $SYSFS/devices/system/cpu/present`
+	present_max=${present_cpus##*-}
+	echo "present_cpus = $present_cpus present_max = $present_max"
+
 	echo -e "\t Cpus in online state: $online_cpus"
 
 	offline_cpus=`cat $SYSFS/devices/system/cpu/offline`
@@ -151,6 +155,8 @@ online_cpus=0
 online_max=0
 offline_cpus=0
 offline_max=0
+present_cpus=0
+present_max=0
 
 while getopts e:ahp: opt; do
 	case $opt in
@@ -190,9 +196,10 @@ if [ $allcpus -eq 0 ]; then
 	online_cpu_expect_success $online_max
 
 	if [[ $offline_cpus -gt 0 ]]; then
-		echo -e "\t offline to online to offline: cpu $offline_max"
-		online_cpu_expect_success $offline_max
-		offline_cpu_expect_success $offline_max
+		echo -e "\t offline to online to offline: cpu $present_max"
+		online_cpu_expect_success $present_max
+		offline_cpu_expect_success $present_max
+		online_cpu $present_max
 	fi
 	exit 0
 else
diff --git a/tools/testing/selftests/filesystems/binderfs/.gitignore b/tools/testing/selftests/filesystems/binderfs/.gitignore
new file mode 100644
index 000000000000..8a5d9bf63dd4
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/.gitignore
@@ -0,0 +1 @@
+binderfs_test
diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile
new file mode 100644
index 000000000000..58cb659b56b4
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += -I../../../../../usr/include/
+TEST_GEN_PROGS := binderfs_test
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
new file mode 100644
index 000000000000..8c2ed962e1c7
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <linux/android/binder.h>
+#include <linux/android/binderfs.h>
+#include "../../kselftest.h"
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+	ssize_t ret;
+again:
+	ret = write(fd, buf, count);
+	if (ret < 0 && errno == EINTR)
+		goto again;
+
+	return ret;
+}
+
+static void write_to_file(const char *filename, const void *buf, size_t count,
+			  int allowed_errno)
+{
+	int fd, saved_errno;
+	ssize_t ret;
+
+	fd = open(filename, O_WRONLY | O_CLOEXEC);
+	if (fd < 0)
+		ksft_exit_fail_msg("%s - Failed to open file %s\n",
+				   strerror(errno), filename);
+
+	ret = write_nointr(fd, buf, count);
+	if (ret < 0) {
+		if (allowed_errno && (errno == allowed_errno)) {
+			close(fd);
+			return;
+		}
+
+		goto on_error;
+	}
+
+	if ((size_t)ret != count)
+		goto on_error;
+
+	close(fd);
+	return;
+
+on_error:
+	saved_errno = errno;
+	close(fd);
+	errno = saved_errno;
+
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to write to file %s\n",
+				   strerror(errno), filename);
+
+	ksft_exit_fail_msg("Failed to write to file %s\n", filename);
+}
+
+static void change_to_userns(void)
+{
+	int ret;
+	uid_t uid;
+	gid_t gid;
+	/* {g,u}id_map files only allow a max of 4096 bytes written to them */
+	char idmap[4096];
+
+	uid = getuid();
+	gid = getgid();
+
+	ret = unshare(CLONE_NEWUSER);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to unshare user namespace\n",
+				   strerror(errno));
+
+	write_to_file("/proc/self/setgroups", "deny", strlen("deny"), ENOENT);
+
+	ret = snprintf(idmap, sizeof(idmap), "0 %d 1", uid);
+	if (ret < 0 || (size_t)ret >= sizeof(idmap))
+		ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n",
+				   strerror(errno));
+
+	write_to_file("/proc/self/uid_map", idmap, strlen(idmap), 0);
+
+	ret = snprintf(idmap, sizeof(idmap), "0 %d 1", gid);
+	if (ret < 0 || (size_t)ret >= sizeof(idmap))
+		ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n",
+				   strerror(errno));
+
+	write_to_file("/proc/self/gid_map", idmap, strlen(idmap), 0);
+
+	ret = setgid(0);
+	if (ret)
+		ksft_exit_fail_msg("%s - Failed to setgid(0)\n",
+				   strerror(errno));
+
+	ret = setuid(0);
+	if (ret)
+		ksft_exit_fail_msg("%s - Failed to setgid(0)\n",
+				   strerror(errno));
+}
+
+static void change_to_mountns(void)
+{
+	int ret;
+
+	ret = unshare(CLONE_NEWNS);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n",
+				   strerror(errno));
+
+	ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to mount / as private\n",
+				   strerror(errno));
+}
+
+static void rmdir_protect_errno(const char *dir)
+{
+	int saved_errno = errno;
+	(void)rmdir(dir);
+	errno = saved_errno;
+}
+
+static void __do_binderfs_test(void)
+{
+	int fd, ret, saved_errno;
+	size_t len;
+	ssize_t wret;
+	bool keep = false;
+	struct binderfs_device device = { 0 };
+	struct binder_version version = { 0 };
+
+	change_to_mountns();
+
+	ret = mkdir("/dev/binderfs", 0755);
+	if (ret < 0) {
+		if (errno != EEXIST)
+			ksft_exit_fail_msg(
+				"%s - Failed to create binderfs mountpoint\n",
+				strerror(errno));
+
+		keep = true;
+	}
+
+	ret = mount(NULL, "/dev/binderfs", "binder", 0, 0);
+	if (ret < 0) {
+		if (errno != ENODEV)
+			ksft_exit_fail_msg("%s - Failed to mount binderfs\n",
+					   strerror(errno));
+
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_skip(
+			"The Android binderfs filesystem is not available\n");
+	}
+
+	/* binderfs mount test passed */
+	ksft_inc_pass_cnt();
+
+	memcpy(device.name, "my-binder", strlen("my-binder"));
+
+	fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC);
+	if (fd < 0)
+		ksft_exit_fail_msg(
+			"%s - Failed to open binder-control device\n",
+			strerror(errno));
+
+	ret = ioctl(fd, BINDER_CTL_ADD, &device);
+	saved_errno = errno;
+	close(fd);
+	errno = saved_errno;
+	if (ret < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg(
+			"%s - Failed to allocate new binder device\n",
+			strerror(errno));
+	}
+
+	ksft_print_msg(
+		"Allocated new binder device with major %d, minor %d, and name %s\n",
+		device.major, device.minor, device.name);
+
+	/* binder device allocation test passed */
+	ksft_inc_pass_cnt();
+
+	fd = open("/dev/binderfs/my-binder", O_CLOEXEC | O_RDONLY);
+	if (fd < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg("%s - Failed to open my-binder device\n",
+				   strerror(errno));
+	}
+
+	ret = ioctl(fd, BINDER_VERSION, &version);
+	saved_errno = errno;
+	close(fd);
+	errno = saved_errno;
+	if (ret < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg(
+			"%s - Failed to open perform BINDER_VERSION request\n",
+			strerror(errno));
+	}
+
+	ksft_print_msg("Detected binder version: %d\n",
+		       version.protocol_version);
+
+	/* binder transaction with binderfs binder device passed */
+	ksft_inc_pass_cnt();
+
+	ret = unlink("/dev/binderfs/my-binder");
+	if (ret < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg("%s - Failed to delete binder device\n",
+				   strerror(errno));
+	}
+
+	/* binder device removal passed */
+	ksft_inc_pass_cnt();
+
+	ret = unlink("/dev/binderfs/binder-control");
+	if (!ret) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg("Managed to delete binder-control device\n");
+	} else if (errno != EPERM) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg(
+			"%s - Failed to delete binder-control device but exited with unexpected error code\n",
+			strerror(errno));
+	}
+
+	/* binder-control device removal failed as expected */
+	ksft_inc_xfail_cnt();
+
+on_error:
+	ret = umount2("/dev/binderfs", MNT_DETACH);
+	keep ?: rmdir_protect_errno("/dev/binderfs");
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to unmount binderfs\n",
+				   strerror(errno));
+
+	/* binderfs unmount test passed */
+	ksft_inc_pass_cnt();
+}
+
+static void binderfs_test_privileged()
+{
+	if (geteuid() != 0)
+		ksft_print_msg(
+			"Tests are not run as root. Skipping privileged tests\n");
+	else
+		__do_binderfs_test();
+}
+
+static void binderfs_test_unprivileged()
+{
+	change_to_userns();
+	__do_binderfs_test();
+}
+
+int main(int argc, char *argv[])
+{
+	binderfs_test_privileged();
+	binderfs_test_unprivileged();
+	ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/filesystems/binderfs/config b/tools/testing/selftests/filesystems/binderfs/config
new file mode 100644
index 000000000000..02dd6cc9cf99
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/config
@@ -0,0 +1,3 @@
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDERFS=y
+CONFIG_ANDROID_BINDER_IPC=y
diff --git a/tools/testing/selftests/ir/Makefile b/tools/testing/selftests/ir/Makefile
index f4ba8eb84b95..ad06489c22a5 100644
--- a/tools/testing/selftests/ir/Makefile
+++ b/tools/testing/selftests/ir/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := ir_loopback.sh
 TEST_GEN_PROGS_EXTENDED := ir_loopback
+APIDIR := ../../../include/uapi
+CFLAGS += -Wall -O2 -I$(APIDIR)
 
 include ../lib.mk
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index f8f3e90700c0..1e6d14d2825c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -21,6 +21,6 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
-$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
+$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
 $(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
index 8db35b99457c..71d7fdc513c1 100755
--- a/tools/testing/selftests/net/xfrm_policy.sh
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -28,6 +28,19 @@ KEY_AES=0x0123456789abcdef0123456789012345
 SPI1=0x1
 SPI2=0x2
 
+do_esp_policy() {
+    local ns=$1
+    local me=$2
+    local remote=$3
+    local lnet=$4
+    local rnet=$5
+
+    # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+    ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow
+    # to fwd decrypted packets after esp processing:
+    ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
+}
+
 do_esp() {
     local ns=$1
     local me=$2
@@ -40,10 +53,59 @@ do_esp() {
     ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in  enc aes $KEY_AES  auth sha1 $KEY_SHA  mode tunnel sel src $rnet dst $lnet
     ip -net $ns xfrm state add src $me  dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
 
-    # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
-    ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow
-    # to fwd decrypted packets after esp processing:
-    ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow
+    do_esp_policy $ns $me $remote $lnet $rnet
+}
+
+# add policies with different netmasks, to make sure kernel carries
+# the policies contained within new netmask over when search tree is
+# re-built.
+# peer netns that are supposed to be encapsulated via esp have addresses
+# in the 10.0.1.0/24 and 10.0.2.0/24 subnets, respectively.
+#
+# Adding a policy for '10.0.1.0/23' will make it necessary to
+# alter the prefix of 10.0.1.0 subnet.
+# In case new prefix overlaps with existing node, the node and all
+# policies it carries need to be merged with the existing one(s).
+#
+# Do that here.
+do_overlap()
+{
+    local ns=$1
+
+    # adds new nodes to tree (neither network exists yet in policy database).
+    ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block
+
+    # adds a new node in the 10.0.0.0/24 tree (dst node exists).
+    ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block
+
+    # adds a 10.2.0.0/23 node, but for different dst.
+    ip -net $ns xfrm policy add src 10.2.0.0/23 dst 10.0.1.0/24 dir fwd priority 200 action block
+
+    # dst now overlaps with the 10.0.1.0/24 ESP policy in fwd.
+    # kernel must 'promote' existing one (10.0.0.0/24) to 10.0.0.0/23.
+    # But 10.0.0.0/23 also includes existing 10.0.1.0/24, so that node
+    # also has to be merged too, including source-sorted subtrees.
+    # old:
+    # 10.0.0.0/24 (node 1 in dst tree of the bin)
+    #    10.1.0.0/24 (node in src tree of dst node 1)
+    #    10.2.0.0/24 (node in src tree of dst node 1)
+    # 10.0.1.0/24 (node 2 in dst tree of the bin)
+    #    10.0.2.0/24 (node in src tree of dst node 2)
+    #    10.2.0.0/24 (node in src tree of dst node 2)
+    #
+    # The next 'policy add' adds dst '10.0.0.0/23', which means
+    # that dst node 1 and dst node 2 have to be merged including
+    # the sub-tree.  As no duplicates are allowed, policies in
+    # the two '10.0.2.0/24' are also merged.
+    #
+    # after the 'add', internal search tree should look like this:
+    # 10.0.0.0/23 (node in dst tree of bin)
+    #     10.0.2.0/24 (node in src tree of dst node)
+    #     10.1.0.0/24 (node in src tree of dst node)
+    #     10.2.0.0/24 (node in src tree of dst node)
+    #
+    # 10.0.0.0/24 and 10.0.1.0/24 nodes have been merged as 10.0.0.0/23.
+    ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/23 dir fwd priority 200 action block
 }
 
 do_esp_policy_get_check() {
@@ -160,6 +222,41 @@ check_xfrm() {
 	return $lret
 }
 
+check_exceptions()
+{
+	logpostfix="$1"
+	local lret=0
+
+	# ping to .254 should be excluded from the tunnel (exception is in place).
+	check_xfrm 0 254
+	if [ $? -ne 0 ]; then
+		echo "FAIL: expected ping to .254 to fail ($logpostfix)"
+		lret=1
+	else
+		echo "PASS: ping to .254 bypassed ipsec tunnel ($logpostfix)"
+	fi
+
+	# ping to .253 should use use ipsec due to direct policy exception.
+	check_xfrm 1 253
+	if [ $? -ne 0 ]; then
+		echo "FAIL: expected ping to .253 to use ipsec tunnel ($logpostfix)"
+		lret=1
+	else
+		echo "PASS: direct policy matches ($logpostfix)"
+	fi
+
+	# ping to .2 should use ipsec.
+	check_xfrm 1 2
+	if [ $? -ne 0 ]; then
+		echo "FAIL: expected ping to .2 to use ipsec tunnel ($logpostfix)"
+		lret=1
+	else
+		echo "PASS: policy matches ($logpostfix)"
+	fi
+
+	return $lret
+}
+
 #check for needed privileges
 if [ "$(id -u)" -ne 0 ];then
 	echo "SKIP: Need root privileges"
@@ -270,33 +367,45 @@ do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28
 do_exception ns3 dead:3::1 dead:3::10 dead:2::fd  dead:2:f0::/96
 do_exception ns4 dead:3::10 dead:3::1 dead:1::fd  dead:1:f0::/96
 
-# ping to .254 should now be excluded from the tunnel
-check_xfrm 0 254
+check_exceptions "exceptions"
 if [ $? -ne 0 ]; then
-	echo "FAIL: expected ping to .254 to fail"
 	ret=1
-else
-	echo "PASS: ping to .254 bypassed ipsec tunnel"
 fi
 
-# ping to .253 should use use ipsec due to direct policy exception.
-check_xfrm 1 253
-if [ $? -ne 0 ]; then
-	echo "FAIL: expected ping to .253 to use ipsec tunnel"
-	ret=1
-else
-	echo "PASS: direct policy matches"
-fi
+# insert block policies with adjacent/overlapping netmasks
+do_overlap ns3
 
-# ping to .2 should use ipsec.
-check_xfrm 1 2
+check_exceptions "exceptions and block policies"
 if [ $? -ne 0 ]; then
-	echo "FAIL: expected ping to .2 to use ipsec tunnel"
 	ret=1
-else
-	echo "PASS: policy matches"
 fi
 
+for n in ns3 ns4;do
+	ip -net $n xfrm policy set hthresh4 28 24 hthresh6 126 125
+	sleep $((RANDOM%5))
+done
+
+check_exceptions "exceptions and block policies after hresh changes"
+
+# full flush of policy db, check everything gets freed incl. internal meta data
+ip -net ns3 xfrm policy flush
+
+do_esp_policy ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24
+do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28
+
+# move inexact policies to hash table
+ip -net ns3 xfrm policy set hthresh4 16 16
+
+sleep $((RANDOM%5))
+check_exceptions "exceptions and block policies after hthresh change in ns3"
+
+# restore original hthresh settings -- move policies back to tables
+for n in ns3 ns4;do
+	ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128
+	sleep $((RANDOM%5))
+done
+check_exceptions "exceptions and block policies after hresh change to normal"
+
 for i in 1 2 3 4;do ip netns del ns$i;done
 
 exit $ret
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 47ed6cef93fb..c9ff2b47bd1c 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for netfilter selftests
 
-TEST_PROGS := nft_trans_stress.sh
+TEST_PROGS := nft_trans_stress.sh nft_nat.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
index 1017313e41a8..59caa8f71cd8 100644
--- a/tools/testing/selftests/netfilter/config
+++ b/tools/testing/selftests/netfilter/config
@@ -1,2 +1,2 @@
 CONFIG_NET_NS=y
-NF_TABLES_INET=y
+CONFIG_NF_TABLES_INET=y
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
new file mode 100755
index 000000000000..8ec76681605c
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -0,0 +1,762 @@
+#!/bin/bash
+#
+# This test is for basic NAT functionality: snat, dnat, redirect, masquerade.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+ip netns add ns0
+ip netns add ns1
+ip netns add ns2
+
+ip link add veth0 netns ns0 type veth peer name eth0 netns ns1
+ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
+
+ip -net ns0 link set lo up
+ip -net ns0 link set veth0 up
+ip -net ns0 addr add 10.0.1.1/24 dev veth0
+ip -net ns0 addr add dead:1::1/64 dev veth0
+
+ip -net ns0 link set veth1 up
+ip -net ns0 addr add 10.0.2.1/24 dev veth1
+ip -net ns0 addr add dead:2::1/64 dev veth1
+
+for i in 1 2; do
+  ip -net ns$i link set lo up
+  ip -net ns$i link set eth0 up
+  ip -net ns$i addr add 10.0.$i.99/24 dev eth0
+  ip -net ns$i route add default via 10.0.$i.1
+  ip -net ns$i addr add dead:$i::99/64 dev eth0
+  ip -net ns$i route add default via dead:$i::1
+done
+
+bad_counter()
+{
+	local ns=$1
+	local counter=$2
+	local expect=$3
+
+	echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2
+	ip netns exec $ns nft list counter inet filter $counter 1>&2
+}
+
+check_counters()
+{
+	ns=$1
+	local lret=0
+
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0in "packets 1 bytes 84"
+		lret=1
+	fi
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0out "packets 1 bytes 84"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 104"
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0in6 "$expect"
+		lret=1
+	fi
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0out6 "$expect"
+		lret=1
+	fi
+
+	return $lret
+}
+
+check_ns0_counters()
+{
+	local ns=$1
+	local lret=0
+
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0in "packets 0 bytes 0"
+		lret=1
+	fi
+
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0in6 "packets 0 bytes 0"
+		lret=1
+	fi
+
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0out "packets 0 bytes 0"
+		lret=1
+	fi
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0out6 "packets 0 bytes 0"
+		lret=1
+	fi
+
+	for dir in "in" "out" ; do
+		expect="packets 1 bytes 84"
+		cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 $ns$dir "$expect"
+			lret=1
+		fi
+
+		expect="packets 1 bytes 104"
+		cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 $ns$dir6 "$expect"
+			lret=1
+		fi
+	done
+
+	return $lret
+}
+
+reset_counters()
+{
+	for i in 0 1 2;do
+		ip netns exec ns$i nft reset counters inet > /dev/null
+	done
+}
+
+test_local_dnat6()
+{
+	local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+	chain output {
+		type nat hook output priority 0; policy accept;
+		ip6 daddr dead:1::99 dnat to dead:2::99
+	}
+}
+EOF
+	if [ $? -ne 0 ]; then
+		echo "SKIP: Could not add add ip6 dnat hook"
+		return $ksft_skip
+	fi
+
+	# ping netns1, expect rewrite to netns2
+	ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null
+	if [ $? -ne 0 ]; then
+		lret=1
+		echo "ERROR: ping6 failed"
+		return $lret
+	fi
+
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 0 count in ns1
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 1 packet in ns2
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2"
+	ip netns exec ns0 nft flush chain ip6 nat output
+
+	return $lret
+}
+
+test_local_dnat()
+{
+	local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+	chain output {
+		type nat hook output priority 0; policy accept;
+		ip daddr 10.0.1.99 dnat to 10.0.2.99
+	}
+}
+EOF
+	# ping netns1, expect rewrite to netns2
+	ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+	if [ $? -ne 0 ]; then
+		lret=1
+		echo "ERROR: ping failed"
+		return $lret
+	fi
+
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 0 count in ns1
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 1 packet in ns2
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2"
+
+	ip netns exec ns0 nft flush chain ip nat output
+
+	reset_counters
+	ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+	if [ $? -ne 0 ]; then
+		lret=1
+		echo "ERROR: ping failed"
+		return $lret
+	fi
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 1 count in ns1
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 0 packet in ns2
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush"
+
+	return $lret
+}
+
+
+test_masquerade6()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 via ipv6"
+		return 1
+		lret=1
+	fi
+
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+	chain postrouting {
+		type nat hook postrouting priority 0; policy accept;
+		meta oif veth0 masquerade
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading"
+		lret=1
+	fi
+
+	# ns1 should have seen packets from ns0, due to masquerade
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns1 should not have seen packets from ns2, due to masquerade
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft flush chain ip6 nat postrouting
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not flush ip6 nat postrouting" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2"
+
+	return $lret
+}
+
+test_masquerade()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: canot ping ns1 from ns2"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0; policy accept;
+		meta oif veth0 masquerade
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading"
+		lret=1
+	fi
+
+	# ns1 should have seen packets from ns0, due to masquerade
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns1 should not have seen packets from ns2, due to masquerade
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft flush chain ip nat postrouting
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not flush nat postrouting" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IP masquerade for ns2"
+
+	return $lret
+}
+
+test_redirect6()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannnot ping ns1 from ns2 via ipv6"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+	chain prerouting {
+		type nat hook prerouting priority 0; policy accept;
+		meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect"
+		lret=1
+	fi
+
+	# ns1 should have seen no packets from ns2, due to redirection
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns0 should have seen packets from ns2, due to masquerade
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft delete table ip6 nat
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not delete ip6 nat table" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2"
+
+	return $lret
+}
+
+test_redirect()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+	chain prerouting {
+		type nat hook prerouting priority 0; policy accept;
+		meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ip redirect"
+		lret=1
+	fi
+
+	# ns1 should have seen no packets from ns2, due to redirection
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns0 should have seen packets from ns2, due to masquerade
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft delete table ip nat
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not delete nat table" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IP redirection for ns2"
+
+	return $lret
+}
+
+
+# ip netns exec ns0 ping -c 1 -q 10.0.$i.99
+for i in 0 1 2; do
+ip netns exec ns$i nft -f - <<EOF
+table inet filter {
+	counter ns0in {}
+	counter ns1in {}
+	counter ns2in {}
+
+	counter ns0out {}
+	counter ns1out {}
+	counter ns2out {}
+
+	counter ns0in6 {}
+	counter ns1in6 {}
+	counter ns2in6 {}
+
+	counter ns0out6 {}
+	counter ns1out6 {}
+	counter ns2out6 {}
+
+	map nsincounter {
+		type ipv4_addr : counter
+		elements = { 10.0.1.1 : "ns0in",
+			     10.0.2.1 : "ns0in",
+			     10.0.1.99 : "ns1in",
+			     10.0.2.99 : "ns2in" }
+	}
+
+	map nsincounter6 {
+		type ipv6_addr : counter
+		elements = { dead:1::1 : "ns0in6",
+			     dead:2::1 : "ns0in6",
+			     dead:1::99 : "ns1in6",
+			     dead:2::99 : "ns2in6" }
+	}
+
+	map nsoutcounter {
+		type ipv4_addr : counter
+		elements = { 10.0.1.1 : "ns0out",
+			     10.0.2.1 : "ns0out",
+			     10.0.1.99: "ns1out",
+			     10.0.2.99: "ns2out" }
+	}
+
+	map nsoutcounter6 {
+		type ipv6_addr : counter
+		elements = { dead:1::1 : "ns0out6",
+			     dead:2::1 : "ns0out6",
+			     dead:1::99 : "ns1out6",
+			     dead:2::99 : "ns2out6" }
+	}
+
+	chain input {
+		type filter hook input priority 0; policy accept;
+		counter name ip saddr map @nsincounter
+		icmpv6 type { "echo-request", "echo-reply" } counter name ip6 saddr map @nsincounter6
+	}
+	chain output {
+		type filter hook output priority 0; policy accept;
+		counter name ip daddr map @nsoutcounter
+		icmpv6 type { "echo-request", "echo-reply" } counter name ip6 daddr map @nsoutcounter6
+	}
+}
+EOF
+done
+
+sleep 3
+# test basic connectivity
+for i in 1 2; do
+  ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null
+  if [ $? -ne 0 ];then
+  	echo "ERROR: Could not reach other namespace(s)" 1>&2
+	ret=1
+  fi
+
+  ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null
+  if [ $? -ne 0 ];then
+	echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2
+	ret=1
+  fi
+  check_counters ns$i
+  if [ $? -ne 0 ]; then
+	ret=1
+  fi
+
+  check_ns0_counters ns$i
+  if [ $? -ne 0 ]; then
+	ret=1
+  fi
+  reset_counters
+done
+
+if [ $ret -eq 0 ];then
+	echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2"
+fi
+
+reset_counters
+test_local_dnat
+test_local_dnat6
+
+reset_counters
+test_masquerade
+test_masquerade6
+
+reset_counters
+test_redirect
+test_redirect6
+
+for i in 0 1 2; do ip netns del ns$i;done
+
+exit $ret
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 82121a81681f..29bac5ef9a93 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -10,4 +10,5 @@
 /proc-uptime-002
 /read
 /self
+/setns-dcache
 /thread-self
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index 1c12c34cf85d..434d033ee067 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001
 TEST_GEN_PROGS += proc-uptime-002
 TEST_GEN_PROGS += read
 TEST_GEN_PROGS += self
+TEST_GEN_PROGS += setns-dcache
 TEST_GEN_PROGS += thread-self
 
 include ../lib.mk
diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c
new file mode 100644
index 000000000000..60ab197a73fc
--- /dev/null
+++ b/tools/testing/selftests/proc/setns-dcache.c
@@ -0,0 +1,129 @@
+/*
+ * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/*
+ * Test that setns(CLONE_NEWNET) points to new /proc/net content even
+ * if old one is in dcache.
+ *
+ * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+
+static pid_t pid = -1;
+
+static void f(void)
+{
+	if (pid > 0) {
+		kill(pid, SIGTERM);
+	}
+}
+
+int main(void)
+{
+	int fd[2];
+	char _ = 0;
+	int nsfd;
+
+	atexit(f);
+
+	/* Check for priviledges and syscall availability straight away. */
+	if (unshare(CLONE_NEWNET) == -1) {
+		if (errno == ENOSYS || errno == EPERM) {
+			return 4;
+		}
+		return 1;
+	}
+	/* Distinguisher between two otherwise empty net namespaces. */
+	if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) {
+		return 1;
+	}
+
+	if (pipe(fd) == -1) {
+		return 1;
+	}
+
+	pid = fork();
+	if (pid == -1) {
+		return 1;
+	}
+
+	if (pid == 0) {
+		if (unshare(CLONE_NEWNET) == -1) {
+			return 1;
+		}
+
+		if (write(fd[1], &_, 1) != 1) {
+			return 1;
+		}
+
+		pause();
+
+		return 0;
+	}
+
+	if (read(fd[0], &_, 1) != 1) {
+		return 1;
+	}
+
+	{
+		char buf[64];
+		snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid);
+		nsfd = open(buf, O_RDONLY);
+		if (nsfd == -1) {
+			return 1;
+		}
+	}
+
+	/* Reliably pin dentry into dcache. */
+	(void)open("/proc/net/unix", O_RDONLY);
+
+	if (setns(nsfd, CLONE_NEWNET) == -1) {
+		return 1;
+	}
+
+	kill(pid, SIGTERM);
+	pid = 0;
+
+	{
+		char buf[4096];
+		ssize_t rv;
+		int fd;
+
+		fd = open("/proc/net/unix", O_RDONLY);
+		if (fd == -1) {
+			return 1;
+		}
+
+#define S "Num       RefCount Protocol Flags    Type St Inode Path\n"
+		rv = read(fd, buf, sizeof(buf));
+
+		assert(rv == strlen(S));
+		assert(memcmp(buf, S, strlen(S)) == 0);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 496a9a8c773a..7e632b465ab4 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1608,7 +1608,16 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 #ifdef SYSCALL_NUM_RET_SHARE_REG
 # define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(-1, action)
 #else
-# define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(val, action)
+# define EXPECT_SYSCALL_RETURN(val, action)		\
+	do {						\
+		errno = 0;				\
+		if (val < 0) {				\
+			EXPECT_EQ(-1, action);		\
+			EXPECT_EQ(-(val), errno);	\
+		} else {				\
+			EXPECT_EQ(val, action);		\
+		}					\
+	} while (0)
 #endif
 
 /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
@@ -1647,7 +1656,7 @@ int get_syscall(struct __test_metadata *_metadata, pid_t tracee)
 
 /* Architecture-specific syscall changing routine. */
 void change_syscall(struct __test_metadata *_metadata,
-		    pid_t tracee, int syscall)
+		    pid_t tracee, int syscall, int result)
 {
 	int ret;
 	ARCH_REGS regs;
@@ -1706,7 +1715,7 @@ void change_syscall(struct __test_metadata *_metadata,
 #ifdef SYSCALL_NUM_RET_SHARE_REG
 		TH_LOG("Can't modify syscall return on this architecture");
 #else
-		regs.SYSCALL_RET = EPERM;
+		regs.SYSCALL_RET = result;
 #endif
 
 #ifdef HAVE_GETREGS
@@ -1734,14 +1743,19 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee,
 	case 0x1002:
 		/* change getpid to getppid. */
 		EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee));
-		change_syscall(_metadata, tracee, __NR_getppid);
+		change_syscall(_metadata, tracee, __NR_getppid, 0);
 		break;
 	case 0x1003:
-		/* skip gettid. */
+		/* skip gettid with valid return code. */
 		EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee));
-		change_syscall(_metadata, tracee, -1);
+		change_syscall(_metadata, tracee, -1, 45000);
 		break;
 	case 0x1004:
+		/* skip openat with error. */
+		EXPECT_EQ(__NR_openat, get_syscall(_metadata, tracee));
+		change_syscall(_metadata, tracee, -1, -ESRCH);
+		break;
+	case 0x1005:
 		/* do nothing (allow getppid) */
 		EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee));
 		break;
@@ -1774,9 +1788,11 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee,
 	nr = get_syscall(_metadata, tracee);
 
 	if (nr == __NR_getpid)
-		change_syscall(_metadata, tracee, __NR_getppid);
+		change_syscall(_metadata, tracee, __NR_getppid, 0);
+	if (nr == __NR_gettid)
+		change_syscall(_metadata, tracee, -1, 45000);
 	if (nr == __NR_openat)
-		change_syscall(_metadata, tracee, -1);
+		change_syscall(_metadata, tracee, -1, -ESRCH);
 }
 
 FIXTURE_DATA(TRACE_syscall) {
@@ -1793,8 +1809,10 @@ FIXTURE_SETUP(TRACE_syscall)
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1002),
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_gettid, 0, 1),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1003),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_openat, 0, 1),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1004),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 	};
 
@@ -1842,15 +1860,26 @@ TEST_F(TRACE_syscall, ptrace_syscall_redirected)
 	EXPECT_NE(self->mypid, syscall(__NR_getpid));
 }
 
-TEST_F(TRACE_syscall, ptrace_syscall_dropped)
+TEST_F(TRACE_syscall, ptrace_syscall_errno)
+{
+	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+	teardown_trace_fixture(_metadata, self->tracer);
+	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+					   true);
+
+	/* Tracer should skip the open syscall, resulting in ESRCH. */
+	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
+}
+
+TEST_F(TRACE_syscall, ptrace_syscall_faked)
 {
 	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
 	teardown_trace_fixture(_metadata, self->tracer);
 	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
 					   true);
 
-	/* Tracer should skip the open syscall, resulting in EPERM. */
-	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_openat));
+	/* Tracer should skip the gettid syscall, resulting fake pid. */
+	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
 }
 
 TEST_F(TRACE_syscall, syscall_allowed)
@@ -1883,7 +1912,21 @@ TEST_F(TRACE_syscall, syscall_redirected)
 	EXPECT_NE(self->mypid, syscall(__NR_getpid));
 }
 
-TEST_F(TRACE_syscall, syscall_dropped)
+TEST_F(TRACE_syscall, syscall_errno)
+{
+	long ret;
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	/* openat has been skipped and an errno return. */
+	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
+}
+
+TEST_F(TRACE_syscall, syscall_faked)
 {
 	long ret;
 
@@ -1894,8 +1937,7 @@ TEST_F(TRACE_syscall, syscall_dropped)
 	ASSERT_EQ(0, ret);
 
 	/* gettid has been skipped and an altered return value stored. */
-	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid));
-	EXPECT_NE(self->mytid, syscall(__NR_gettid));
+	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
 }
 
 TEST_F(TRACE_syscall, skip_after_RET_TRACE)
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index c02683cfb6c9..7656c7ce79d9 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -O3 -Wl,-no-as-needed -Wall
-LDFLAGS += -lrt -lpthread -lm
+LDLIBS += -lrt -lpthread -lm
 
 # these are all "safe" tests that don't modify
 # system time or require escalated privileges