Merge branch 'linus' into sched/urgent, to resolve conflicts

 Conflicts:
	arch/arm64/kernel/entry.S
	arch/x86/Kconfig
	include/linux/sched/mm.h
	kernel/fork.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

22 files changed, 5958 insertions, 114 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 541d9d7fad5a..1e09d77f1948 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -3,3 +3,10 @@ test_maps
 test_lru_map
 test_lpm_map
 test_tag
+FEATURE-DUMP.libbpf
+fixdep
+test_align
+test_dev_cgroup
+test_progs
+test_verifier_log
+feature
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 9316e648a880..bf05bc5e36e5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -11,16 +11,19 @@ ifneq ($(wildcard $(GENHDR)),)
 endif
 
 CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
-LDLIBS += -lcap -lelf -lrt
+LDLIBS += -lcap -lelf -lrt -lpthread
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_align test_verifier_log test_dev_cgroup
+	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
-	sockmap_verdict_prog.o dev_cgroup.o
+	sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
+	test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+	sample_map_ret0.o test_tcpbpf_kern.o
 
-TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh
+TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
+	test_offload.py
 
 include ../lib.mk
 
@@ -49,8 +52,13 @@ else
   CPU ?= generic
 endif
 
+CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
+	      -Wno-compare-distinct-pointer-types
+
+$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
+$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
+
 %.o: %.c
-	$(CLANG) -I. -I./include/uapi -I../../../include/uapi \
-		 -Wno-compare-distinct-pointer-types          \
+	$(CLANG) $(CLANG_FLAGS) \
 		 -O2 -target bpf -emit-llvm -c $< -o - |      \
 	$(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index fd9a17fa8a8b..dde2c11d7771 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -71,6 +71,8 @@ static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_getsockopt;
+static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) =
+	(void *) BPF_FUNC_sock_ops_cb_flags_set;
 static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
@@ -82,7 +84,8 @@ static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
 static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
 				       unsigned int buf_size) =
 	(void *) BPF_FUNC_perf_prog_read_value;
-
+static int (*bpf_override_return)(void *ctx, unsigned long rc) =
+	(void *) BPF_FUNC_override_return;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 52d53ed08769..983dd25d49f4 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -3,3 +3,5 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_NET_CLS_BPF=m
 CONFIG_BPF_EVENTS=y
 CONFIG_TEST_BPF=m
+CONFIG_CGROUP_BPF=y
+CONFIG_NETDEVSIM=m
diff --git a/tools/testing/selftests/bpf/sample_map_ret0.c b/tools/testing/selftests/bpf/sample_map_ret0.c
new file mode 100644
index 000000000000..0756303676ac
--- /dev/null
+++ b/tools/testing/selftests/bpf/sample_map_ret0.c
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") htab = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(long),
+	.max_entries = 2,
+};
+
+struct bpf_map_def SEC("maps") array = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(long),
+	.max_entries = 2,
+};
+
+/* Sample program which should always load for testing control paths. */
+SEC(".text") int func()
+{
+	__u64 key64 = 0;
+	__u32 key = 0;
+	long *value;
+
+	value = bpf_map_lookup_elem(&htab, &key);
+	if (!value)
+		return 1;
+	value = bpf_map_lookup_elem(&array, &key64);
+	if (!value)
+		return 1;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/sample_ret0.c b/tools/testing/selftests/bpf/sample_ret0.c
new file mode 100644
index 000000000000..fec99750d6ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/sample_ret0.c
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
+
+/* Sample program which should always load for testing control paths. */
+int func()
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
new file mode 100755
index 000000000000..481dccdf140c
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -0,0 +1,51 @@
+#!/usr/bin/env python2
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+    buf = ''
+    while len(buf) < n:
+        rem = n - len(buf)
+        try: s = sock.recv(rem)
+        except (socket.error), e: return ''
+        buf += s
+    return buf
+
+def send(sock, s):
+    total = len(s)
+    count = 0
+    while count < total:
+        try: n = sock.send(s)
+        except (socket.error), e: n = 0
+        if n == 0:
+            return count;
+        count += n
+    return count
+
+
+serverPort = int(sys.argv[1])
+HostName = socket.gethostname()
+
+# create active socket
+sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+try:
+    sock.connect((HostName, serverPort))
+except socket.error as e:
+    sys.exit(1)
+
+buf = ''
+n = 0
+while n < 1000:
+    buf += '+'
+    n += 1
+
+sock.settimeout(1);
+n = send(sock, buf)
+n = read(sock, 500)
+sys.exit(0)
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
new file mode 100755
index 000000000000..bc454d7d0be2
--- /dev/null
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -0,0 +1,83 @@
+#!/usr/bin/env python2
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+
+import sys, os, os.path, getopt
+import socket, time
+import subprocess
+import select
+
+def read(sock, n):
+    buf = ''
+    while len(buf) < n:
+        rem = n - len(buf)
+        try: s = sock.recv(rem)
+        except (socket.error), e: return ''
+        buf += s
+    return buf
+
+def send(sock, s):
+    total = len(s)
+    count = 0
+    while count < total:
+        try: n = sock.send(s)
+        except (socket.error), e: n = 0
+        if n == 0:
+            return count;
+        count += n
+    return count
+
+
+SERVER_PORT = 12877
+MAX_PORTS = 2
+
+serverPort = SERVER_PORT
+serverSocket = None
+
+HostName = socket.gethostname()
+
+# create passive socket
+serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+host = socket.gethostname()
+
+try: serverSocket.bind((host, 0))
+except socket.error as msg:
+    print 'bind fails: ', msg
+
+sn = serverSocket.getsockname()
+serverPort = sn[1]
+
+cmdStr = ("./tcp_client.py %d &") % (serverPort)
+os.system(cmdStr)
+
+buf = ''
+n = 0
+while n < 500:
+    buf += '.'
+    n += 1
+
+serverSocket.listen(MAX_PORTS)
+readList = [serverSocket]
+
+while True:
+    readyRead, readyWrite, inError = \
+        select.select(readList, [], [], 2)
+
+    if len(readyRead) > 0:
+        waitCount = 0
+        for sock in readyRead:
+            if sock == serverSocket:
+                (clientSocket, address) = serverSocket.accept()
+                address = str(address[0])
+                readList.append(clientSocket)
+            else:
+                sock.settimeout(1);
+                s = read(sock, 1000)
+                n = send(sock, buf)
+                sock.close()
+                serverSocket.close()
+                sys.exit(0)
+    else:
+        print 'Select timeout!'
+        sys.exit(1)
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c
index 471bbbdb94db..ff8bd7e3e50c 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -64,11 +64,11 @@ static struct bpf_align_test tests[] = {
 		.matches = {
 			{1, "R1=ctx(id=0,off=0,imm=0)"},
 			{1, "R10=fp0"},
-			{1, "R3=inv2"},
-			{2, "R3=inv4"},
-			{3, "R3=inv8"},
-			{4, "R3=inv16"},
-			{5, "R3=inv32"},
+			{1, "R3_w=inv2"},
+			{2, "R3_w=inv4"},
+			{3, "R3_w=inv8"},
+			{4, "R3_w=inv16"},
+			{5, "R3_w=inv32"},
 		},
 	},
 	{
@@ -92,17 +92,17 @@ static struct bpf_align_test tests[] = {
 		.matches = {
 			{1, "R1=ctx(id=0,off=0,imm=0)"},
 			{1, "R10=fp0"},
-			{1, "R3=inv1"},
-			{2, "R3=inv2"},
-			{3, "R3=inv4"},
-			{4, "R3=inv8"},
-			{5, "R3=inv16"},
-			{6, "R3=inv1"},
-			{7, "R4=inv32"},
-			{8, "R4=inv16"},
-			{9, "R4=inv8"},
-			{10, "R4=inv4"},
-			{11, "R4=inv2"},
+			{1, "R3_w=inv1"},
+			{2, "R3_w=inv2"},
+			{3, "R3_w=inv4"},
+			{4, "R3_w=inv8"},
+			{5, "R3_w=inv16"},
+			{6, "R3_w=inv1"},
+			{7, "R4_w=inv32"},
+			{8, "R4_w=inv16"},
+			{9, "R4_w=inv8"},
+			{10, "R4_w=inv4"},
+			{11, "R4_w=inv2"},
 		},
 	},
 	{
@@ -121,12 +121,12 @@ static struct bpf_align_test tests[] = {
 		.matches = {
 			{1, "R1=ctx(id=0,off=0,imm=0)"},
 			{1, "R10=fp0"},
-			{1, "R3=inv4"},
-			{2, "R3=inv8"},
-			{3, "R3=inv10"},
-			{4, "R4=inv8"},
-			{5, "R4=inv12"},
-			{6, "R4=inv14"},
+			{1, "R3_w=inv4"},
+			{2, "R3_w=inv8"},
+			{3, "R3_w=inv10"},
+			{4, "R4_w=inv8"},
+			{5, "R4_w=inv12"},
+			{6, "R4_w=inv14"},
 		},
 	},
 	{
@@ -143,10 +143,10 @@ static struct bpf_align_test tests[] = {
 		.matches = {
 			{1, "R1=ctx(id=0,off=0,imm=0)"},
 			{1, "R10=fp0"},
-			{1, "R3=inv7"},
-			{2, "R3=inv7"},
-			{3, "R3=inv14"},
-			{4, "R3=inv56"},
+			{1, "R3_w=inv7"},
+			{2, "R3_w=inv7"},
+			{3, "R3_w=inv14"},
+			{4, "R3_w=inv56"},
 		},
 	},
 
@@ -185,18 +185,18 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
 			{7, "R0=pkt(id=0,off=8,r=8,imm=0)"},
-			{7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{8, "R3=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
-			{9, "R3=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{10, "R3=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
-			{11, "R3=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+			{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+			{9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+			{11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
 			{18, "R3=pkt_end(id=0,off=0,imm=0)"},
-			{18, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{19, "R4=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
-			{20, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
-			{21, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
-			{22, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{23, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+			{18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
+			{20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+			{21, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+			{22, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{23, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
 		},
 	},
 	{
@@ -217,16 +217,16 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{8, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{9, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{11, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
-			{12, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{13, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{14, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{15, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
-			{16, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+			{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+			{12, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{14, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+			{16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
 		},
 	},
 	{
@@ -257,14 +257,14 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{4, "R5=pkt(id=0,off=0,r=0,imm=0)"},
-			{5, "R5=pkt(id=0,off=14,r=0,imm=0)"},
-			{6, "R4=pkt(id=0,off=14,r=0,imm=0)"},
+			{4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"},
+			{5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"},
+			{6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"},
 			{10, "R2=pkt(id=0,off=0,r=18,imm=0)"},
 			{10, "R5=pkt(id=0,off=14,r=18,imm=0)"},
-			{10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{14, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
-			{15, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
+			{10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
+			{15, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
 		},
 	},
 	{
@@ -320,11 +320,11 @@ static struct bpf_align_test tests[] = {
 			 * alignment of 4.
 			 */
 			{8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
-			{8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Offset is added to packet pointer R5, resulting in
 			 * known fixed offset, and variable offset from R6.
 			 */
-			{11, "R5=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{11, "R5_w=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* At the time the word size load is performed from R5,
 			 * it's total offset is NET_IP_ALIGN + reg->off (0) +
 			 * reg->aux_off (14) which is 16.  Then the variable
@@ -336,11 +336,11 @@ static struct bpf_align_test tests[] = {
 			/* Variable offset is added to R5 packet pointer,
 			 * resulting in auxiliary alignment of 4.
 			 */
-			{18, "R5=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant offset is added to R5, resulting in
 			 * reg->off of 14.
 			 */
-			{19, "R5=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off
 			 * (14) which is 16.  Then the variable offset is 4-byte
@@ -352,18 +352,18 @@ static struct bpf_align_test tests[] = {
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{26, "R5=pkt(id=0,off=14,r=8"},
+			{26, "R5_w=pkt(id=0,off=14,r=8"},
 			/* Variable offset is added to R5, resulting in a
 			 * variable offset of (4n).
 			 */
-			{27, "R5=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant is added to R5 again, setting reg->off to 18. */
-			{28, "R5=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* And once more we add a variable; resulting var_off
 			 * is still (4n), fixed offset is not changed.
 			 * Also, we create a new reg->id.
 			 */
-			{29, "R5=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"},
+			{29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (18)
 			 * which is 20.  Then the variable offset is (4n), so
@@ -410,11 +410,11 @@ static struct bpf_align_test tests[] = {
 			 * alignment of 4.
 			 */
 			{8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
-			{8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{9, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* Packet pointer has (4n+2) offset */
-			{11, "R5=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			{13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
@@ -426,11 +426,11 @@ static struct bpf_align_test tests[] = {
 			/* Newly read value in R6 was shifted left by 2, so has
 			 * known alignment of 4.
 			 */
-			{18, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{18, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Added (4n) to packet pointer's (4n+2) var_off, giving
 			 * another (4n+2).
 			 */
-			{19, "R5=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+			{19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
 			{21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
@@ -446,11 +446,9 @@ static struct bpf_align_test tests[] = {
 		.insns = {
 			PREP_PKT_POINTERS,
 			BPF_MOV64_IMM(BPF_REG_0, 0),
-			/* ptr & const => unknown & const */
-			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
-			BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 0x40),
-			/* ptr << const => unknown << const */
-			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+			/* (ptr - ptr) << 2 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_5, BPF_REG_2),
 			BPF_ALU64_IMM(BPF_LSH, BPF_REG_5, 2),
 			/* We have a (4n) value.  Let's make a packet offset
 			 * out of it.  First add 14, to make it a (4n+2)
@@ -473,8 +471,26 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = REJECT,
 		.matches = {
-			{4, "R5=pkt(id=0,off=0,r=0,imm=0)"},
-			/* R5 bitwise operator &= on pointer prohibited */
+			{4, "R5_w=pkt_end(id=0,off=0,imm=0)"},
+			/* (ptr - ptr) << 2 == unknown, (4n) */
+			{6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"},
+			/* (4n) + 14 == (4n+2).  We blow our bounds, because
+			 * the add could overflow.
+			 */
+			{7, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"},
+			/* Checked s>=0 */
+			{9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			/* packet pointer + nonnegative (4n+2) */
+			{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			{13, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
+			 * We checked the bounds, but it might have been able
+			 * to overflow if the packet pointer started in the
+			 * upper half of the address space.
+			 * So we did not get a 'range' on R6, and the access
+			 * attempt will fail.
+			 */
+			{15, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
 		}
 	},
 	{
@@ -510,11 +526,11 @@ static struct bpf_align_test tests[] = {
 			 * alignment of 4.
 			 */
 			{7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
-			{9, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{10, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* New unknown value in R7 is (4n) */
-			{11, "R7=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Subtracting it from R6 blows our unsigned bounds */
 			{12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"},
 			/* Checked s>= 0 */
@@ -563,15 +579,15 @@ static struct bpf_align_test tests[] = {
 			 * alignment of 4.
 			 */
 			{7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
-			{10, "R6=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
+			{10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{11, "R6=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
+			{11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
 			/* Subtracting from packet pointer overflows ubounds */
-			{13, "R5=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"},
+			{13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"},
 			/* New unknown value in R7 is (4n), >= 76 */
-			{15, "R7=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
+			{15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
 			/* Adding it to packet pointer gives nice bounds again */
-			{16, "R5=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
+			{16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c
index 02c85d6c89b0..3489cc283433 100644
--- a/tools/testing/selftests/bpf/test_dev_cgroup.c
+++ b/tools/testing/selftests/bpf/test_dev_cgroup.c
@@ -10,6 +10,8 @@
 #include <string.h>
 #include <errno.h>
 #include <assert.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
@@ -19,19 +21,23 @@
 
 #define DEV_CGROUP_PROG "./dev_cgroup.o"
 
-#define TEST_CGROUP "test-bpf-based-device-cgroup/"
+#define TEST_CGROUP "/test-bpf-based-device-cgroup/"
 
 int main(int argc, char **argv)
 {
+	struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
 	struct bpf_object *obj;
 	int error = EXIT_FAILURE;
 	int prog_fd, cgroup_fd;
 	__u32 prog_cnt;
 
+	if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0)
+		perror("Unable to lift memlock rlimit");
+
 	if (bpf_prog_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE,
 			  &obj, &prog_fd)) {
 		printf("Failed to load DEV_CGROUP program\n");
-		goto err;
+		goto out;
 	}
 
 	if (setup_cgroup_environment()) {
@@ -89,5 +95,6 @@ int main(int argc, char **argv)
 err:
 	cleanup_cgroup_environment();
 
+out:
 	return error;
 }
diff --git a/tools/testing/selftests/bpf/test_l4lb_noinline.c b/tools/testing/selftests/bpf/test_l4lb_noinline.c
new file mode 100644
index 000000000000..ba44a14e6dc4
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_l4lb_noinline.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include "bpf_helpers.h"
+#include "test_iptunnel_common.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+
+static __u32 rol32(__u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> ((-shift) & 31));
+}
+
+/* copy paste of jhash from kernel sources to make sure llvm
+ * can compile it into valid sequence of bpf instructions
+ */
+#define __jhash_mix(a, b, c)			\
+{						\
+	a -= c;  a ^= rol32(c, 4);  c += b;	\
+	b -= a;  b ^= rol32(a, 6);  a += c;	\
+	c -= b;  c ^= rol32(b, 8);  b += a;	\
+	a -= c;  a ^= rol32(c, 16); c += b;	\
+	b -= a;  b ^= rol32(a, 19); a += c;	\
+	c -= b;  c ^= rol32(b, 4);  b += a;	\
+}
+
+#define __jhash_final(a, b, c)			\
+{						\
+	c ^= b; c -= rol32(b, 14);		\
+	a ^= c; a -= rol32(c, 11);		\
+	b ^= a; b -= rol32(a, 25);		\
+	c ^= b; c -= rol32(b, 16);		\
+	a ^= c; a -= rol32(c, 4);		\
+	b ^= a; b -= rol32(a, 14);		\
+	c ^= b; c -= rol32(b, 24);		\
+}
+
+#define JHASH_INITVAL		0xdeadbeef
+
+typedef unsigned int u32;
+
+static u32 jhash(const void *key, u32 length, u32 initval)
+{
+	u32 a, b, c;
+	const unsigned char *k = key;
+
+	a = b = c = JHASH_INITVAL + length + initval;
+
+	while (length > 12) {
+		a += *(u32 *)(k);
+		b += *(u32 *)(k + 4);
+		c += *(u32 *)(k + 8);
+		__jhash_mix(a, b, c);
+		length -= 12;
+		k += 12;
+	}
+	switch (length) {
+	case 12: c += (u32)k[11]<<24;
+	case 11: c += (u32)k[10]<<16;
+	case 10: c += (u32)k[9]<<8;
+	case 9:  c += k[8];
+	case 8:  b += (u32)k[7]<<24;
+	case 7:  b += (u32)k[6]<<16;
+	case 6:  b += (u32)k[5]<<8;
+	case 5:  b += k[4];
+	case 4:  a += (u32)k[3]<<24;
+	case 3:  a += (u32)k[2]<<16;
+	case 2:  a += (u32)k[1]<<8;
+	case 1:  a += k[0];
+		 __jhash_final(a, b, c);
+	case 0: /* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
+
+static u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+	a += initval;
+	b += initval;
+	c += initval;
+	__jhash_final(a, b, c);
+	return c;
+}
+
+static u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+#define PCKT_FRAGMENTED 65343
+#define IPV4_HDR_LEN_NO_OPT 20
+#define IPV4_PLUS_ICMP_HDR 28
+#define IPV6_PLUS_ICMP_HDR 48
+#define RING_SIZE 2
+#define MAX_VIPS 12
+#define MAX_REALS 5
+#define CTL_MAP_SIZE 16
+#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
+#define F_IPV6 (1 << 0)
+#define F_HASH_NO_SRC_PORT (1 << 0)
+#define F_ICMP (1 << 0)
+#define F_SYN_SET (1 << 1)
+
+struct packet_description {
+	union {
+		__be32 src;
+		__be32 srcv6[4];
+	};
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	union {
+		__u32 ports;
+		__u16 port16[2];
+	};
+	__u8 proto;
+	__u8 flags;
+};
+
+struct ctl_value {
+	union {
+		__u64 value;
+		__u32 ifindex;
+		__u8 mac[6];
+	};
+};
+
+struct vip_meta {
+	__u32 flags;
+	__u32 vip_num;
+};
+
+struct real_definition {
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	__u8 flags;
+};
+
+struct vip_stats {
+	__u64 bytes;
+	__u64 pkts;
+};
+
+struct eth_hdr {
+	unsigned char eth_dest[ETH_ALEN];
+	unsigned char eth_source[ETH_ALEN];
+	unsigned short eth_proto;
+};
+
+struct bpf_map_def SEC("maps") vip_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip),
+	.value_size = sizeof(struct vip_meta),
+	.max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ch_rings = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = CH_RINGS_SIZE,
+};
+
+struct bpf_map_def SEC("maps") reals = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct real_definition),
+	.max_entries = MAX_REALS,
+};
+
+struct bpf_map_def SEC("maps") stats = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct vip_stats),
+	.max_entries = MAX_VIPS,
+};
+
+struct bpf_map_def SEC("maps") ctl_array = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct ctl_value),
+	.max_entries = CTL_MAP_SIZE,
+};
+
+static __u32 get_packet_hash(struct packet_description *pckt,
+			     bool ipv6)
+{
+	if (ipv6)
+		return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
+				    pckt->ports, CH_RINGS_SIZE);
+	else
+		return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
+}
+
+static bool get_packet_dst(struct real_definition **real,
+			   struct packet_description *pckt,
+			   struct vip_meta *vip_info,
+			   bool is_ipv6)
+{
+	__u32 hash = get_packet_hash(pckt, is_ipv6);
+	__u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE;
+	__u32 *real_pos;
+
+	if (hash != 0x358459b7 /* jhash of ipv4 packet */  &&
+	    hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
+		return 0;
+
+	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
+	if (!real_pos)
+		return false;
+	key = *real_pos;
+	*real = bpf_map_lookup_elem(&reals, &key);
+	if (!(*real))
+		return false;
+	return true;
+}
+
+static int parse_icmpv6(void *data, void *data_end, __u64 off,
+			struct packet_description *pckt)
+{
+	struct icmp6hdr *icmp_hdr;
+	struct ipv6hdr *ip6h;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
+		return TC_ACT_OK;
+	off += sizeof(struct icmp6hdr);
+	ip6h = data + off;
+	if (ip6h + 1 > data_end)
+		return TC_ACT_SHOT;
+	pckt->proto = ip6h->nexthdr;
+	pckt->flags |= F_ICMP;
+	memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
+	memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
+	return TC_ACT_UNSPEC;
+}
+
+static int parse_icmp(void *data, void *data_end, __u64 off,
+		      struct packet_description *pckt)
+{
+	struct icmphdr *icmp_hdr;
+	struct iphdr *iph;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (icmp_hdr->type != ICMP_DEST_UNREACH ||
+	    icmp_hdr->code != ICMP_FRAG_NEEDED)
+		return TC_ACT_OK;
+	off += sizeof(struct icmphdr);
+	iph = data + off;
+	if (iph + 1 > data_end)
+		return TC_ACT_SHOT;
+	if (iph->ihl != 5)
+		return TC_ACT_SHOT;
+	pckt->proto = iph->protocol;
+	pckt->flags |= F_ICMP;
+	pckt->src = iph->daddr;
+	pckt->dst = iph->saddr;
+	return TC_ACT_UNSPEC;
+}
+
+static bool parse_udp(void *data, __u64 off, void *data_end,
+		      struct packet_description *pckt)
+{
+	struct udphdr *udp;
+	udp = data + off;
+
+	if (udp + 1 > data_end)
+		return false;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = udp->source;
+		pckt->port16[1] = udp->dest;
+	} else {
+		pckt->port16[0] = udp->dest;
+		pckt->port16[1] = udp->source;
+	}
+	return true;
+}
+
+static bool parse_tcp(void *data, __u64 off, void *data_end,
+		      struct packet_description *pckt)
+{
+	struct tcphdr *tcp;
+
+	tcp = data + off;
+	if (tcp + 1 > data_end)
+		return false;
+
+	if (tcp->syn)
+		pckt->flags |= F_SYN_SET;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = tcp->source;
+		pckt->port16[1] = tcp->dest;
+	} else {
+		pckt->port16[0] = tcp->dest;
+		pckt->port16[1] = tcp->source;
+	}
+	return true;
+}
+
+static int process_packet(void *data, __u64 off, void *data_end,
+			  bool is_ipv6, struct __sk_buff *skb)
+{
+	void *pkt_start = (void *)(long)skb->data;
+	struct packet_description pckt = {};
+	struct eth_hdr *eth = pkt_start;
+	struct bpf_tunnel_key tkey = {};
+	struct vip_stats *data_stats;
+	struct real_definition *dst;
+	struct vip_meta *vip_info;
+	struct ctl_value *cval;
+	__u32 v4_intf_pos = 1;
+	__u32 v6_intf_pos = 2;
+	struct ipv6hdr *ip6h;
+	struct vip vip = {};
+	struct iphdr *iph;
+	int tun_flag = 0;
+	__u16 pkt_bytes;
+	__u64 iph_len;
+	__u32 ifindex;
+	__u8 protocol;
+	__u32 vip_num;
+	int action;
+
+	tkey.tunnel_ttl = 64;
+	if (is_ipv6) {
+		ip6h = data + off;
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		iph_len = sizeof(struct ipv6hdr);
+		protocol = ip6h->nexthdr;
+		pckt.proto = protocol;
+		pkt_bytes = bpf_ntohs(ip6h->payload_len);
+		off += iph_len;
+		if (protocol == IPPROTO_FRAGMENT) {
+			return TC_ACT_SHOT;
+		} else if (protocol == IPPROTO_ICMPV6) {
+			action = parse_icmpv6(data, data_end, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV6_PLUS_ICMP_HDR;
+		} else {
+			memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
+			memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
+		}
+	} else {
+		iph = data + off;
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+		if (iph->ihl != 5)
+			return TC_ACT_SHOT;
+
+		protocol = iph->protocol;
+		pckt.proto = protocol;
+		pkt_bytes = bpf_ntohs(iph->tot_len);
+		off += IPV4_HDR_LEN_NO_OPT;
+
+		if (iph->frag_off & PCKT_FRAGMENTED)
+			return TC_ACT_SHOT;
+		if (protocol == IPPROTO_ICMP) {
+			action = parse_icmp(data, data_end, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV4_PLUS_ICMP_HDR;
+		} else {
+			pckt.src = iph->saddr;
+			pckt.dst = iph->daddr;
+		}
+	}
+	protocol = pckt.proto;
+
+	if (protocol == IPPROTO_TCP) {
+		if (!parse_tcp(data, off, data_end, &pckt))
+			return TC_ACT_SHOT;
+	} else if (protocol == IPPROTO_UDP) {
+		if (!parse_udp(data, off, data_end, &pckt))
+			return TC_ACT_SHOT;
+	} else {
+		return TC_ACT_SHOT;
+	}
+
+	if (is_ipv6)
+		memcpy(vip.daddr.v6, pckt.dstv6, 16);
+	else
+		vip.daddr.v4 = pckt.dst;
+
+	vip.dport = pckt.port16[1];
+	vip.protocol = pckt.proto;
+	vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+	if (!vip_info) {
+		vip.dport = 0;
+		vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+		if (!vip_info)
+			return TC_ACT_SHOT;
+		pckt.port16[1] = 0;
+	}
+
+	if (vip_info->flags & F_HASH_NO_SRC_PORT)
+		pckt.port16[0] = 0;
+
+	if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
+		return TC_ACT_SHOT;
+
+	if (dst->flags & F_IPV6) {
+		cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		memcpy(tkey.remote_ipv6, dst->dstv6, 16);
+		tun_flag = BPF_F_TUNINFO_IPV6;
+	} else {
+		cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		tkey.remote_ipv4 = dst->dst;
+	}
+	vip_num = vip_info->vip_num;
+	data_stats = bpf_map_lookup_elem(&stats, &vip_num);
+	if (!data_stats)
+		return TC_ACT_SHOT;
+	data_stats->pkts++;
+	data_stats->bytes += pkt_bytes;
+	bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
+	*(u32 *)eth->eth_dest = tkey.remote_ipv4;
+	return bpf_redirect(ifindex, 0);
+}
+
+SEC("l4lb-demo")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct eth_hdr *eth = data;
+	__u32 eth_proto;
+	__u32 nh_off;
+
+	nh_off = sizeof(struct eth_hdr);
+	if (data + nh_off > data_end)
+		return TC_ACT_SHOT;
+	eth_proto = eth->eth_proto;
+	if (eth_proto == bpf_htons(ETH_P_IP))
+		return process_packet(data, nh_off, data_end, false, ctx);
+	else if (eth_proto == bpf_htons(ETH_P_IPV6))
+		return process_packet(data, nh_off, data_end, true, ctx);
+	else
+		return TC_ACT_SHOT;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index f61480641b6e..2be87e9ee28d 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -14,6 +14,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/bpf.h>
+#include <pthread.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -521,6 +522,218 @@ static void test_lpm_delete(void)
 	close(map_fd);
 }
 
+static void test_lpm_get_next_key(void)
+{
+	struct bpf_lpm_trie_key *key_p, *next_key_p;
+	size_t key_size;
+	__u32 value = 0;
+	int map_fd;
+
+	key_size = sizeof(*key_p) + sizeof(__u32);
+	key_p = alloca(key_size);
+	next_key_p = alloca(key_size);
+
+	map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, sizeof(value),
+				100, BPF_F_NO_PREALLOC);
+	assert(map_fd >= 0);
+
+	/* empty tree. get_next_key should return ENOENT */
+	assert(bpf_map_get_next_key(map_fd, NULL, key_p) == -1 &&
+	       errno == ENOENT);
+
+	/* get and verify the first key, get the second one should fail. */
+	key_p->prefixlen = 16;
+	inet_pton(AF_INET, "192.168.0.0", key_p->data);
+	assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+	memset(key_p, 0, key_size);
+	assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+	assert(key_p->prefixlen == 16 && key_p->data[0] == 192 &&
+	       key_p->data[1] == 168);
+
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+	       errno == ENOENT);
+
+	/* no exact matching key should get the first one in post order. */
+	key_p->prefixlen = 8;
+	assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+	assert(key_p->prefixlen == 16 && key_p->data[0] == 192 &&
+	       key_p->data[1] == 168);
+
+	/* add one more element (total two) */
+	key_p->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.0.0", key_p->data);
+	assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+	memset(key_p, 0, key_size);
+	assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+	assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
+	       key_p->data[1] == 168 && key_p->data[2] == 0);
+
+	memset(next_key_p, 0, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+	assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
+	       next_key_p->data[1] == 168);
+
+	memcpy(key_p, next_key_p, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+	       errno == ENOENT);
+
+	/* Add one more element (total three) */
+	key_p->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.128.0", key_p->data);
+	assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+	memset(key_p, 0, key_size);
+	assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+	assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
+	       key_p->data[1] == 168 && key_p->data[2] == 0);
+
+	memset(next_key_p, 0, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+	assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+	       next_key_p->data[1] == 168 && next_key_p->data[2] == 128);
+
+	memcpy(key_p, next_key_p, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+	assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
+	       next_key_p->data[1] == 168);
+
+	memcpy(key_p, next_key_p, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+	       errno == ENOENT);
+
+	/* Add one more element (total four) */
+	key_p->prefixlen = 24;
+	inet_pton(AF_INET, "192.168.1.0", key_p->data);
+	assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+	memset(key_p, 0, key_size);
+	assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+	assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
+	       key_p->data[1] == 168 && key_p->data[2] == 0);
+
+	memset(next_key_p, 0, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+	assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+	       next_key_p->data[1] == 168 && next_key_p->data[2] == 1);
+
+	memcpy(key_p, next_key_p, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+	assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+	       next_key_p->data[1] == 168 && next_key_p->data[2] == 128);
+
+	memcpy(key_p, next_key_p, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+	assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
+	       next_key_p->data[1] == 168);
+
+	memcpy(key_p, next_key_p, key_size);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+	       errno == ENOENT);
+
+	/* no exact matching key should return the first one in post order */
+	key_p->prefixlen = 22;
+	inet_pton(AF_INET, "192.168.1.0", key_p->data);
+	assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+	assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+	       next_key_p->data[1] == 168 && next_key_p->data[2] == 0);
+
+	close(map_fd);
+}
+
+#define MAX_TEST_KEYS	4
+struct lpm_mt_test_info {
+	int cmd; /* 0: update, 1: delete, 2: lookup, 3: get_next_key */
+	int iter;
+	int map_fd;
+	struct {
+		__u32 prefixlen;
+		__u32 data;
+	} key[MAX_TEST_KEYS];
+};
+
+static void *lpm_test_command(void *arg)
+{
+	int i, j, ret, iter, key_size;
+	struct lpm_mt_test_info *info = arg;
+	struct bpf_lpm_trie_key *key_p;
+
+	key_size = sizeof(struct bpf_lpm_trie_key) + sizeof(__u32);
+	key_p = alloca(key_size);
+	for (iter = 0; iter < info->iter; iter++)
+		for (i = 0; i < MAX_TEST_KEYS; i++) {
+			/* first half of iterations in forward order,
+			 * and second half in backward order.
+			 */
+			j = (iter < (info->iter / 2)) ? i : MAX_TEST_KEYS - i - 1;
+			key_p->prefixlen = info->key[j].prefixlen;
+			memcpy(key_p->data, &info->key[j].data, sizeof(__u32));
+			if (info->cmd == 0) {
+				__u32 value = j;
+				/* update must succeed */
+				assert(bpf_map_update_elem(info->map_fd, key_p, &value, 0) == 0);
+			} else if (info->cmd == 1) {
+				ret = bpf_map_delete_elem(info->map_fd, key_p);
+				assert(ret == 0 || errno == ENOENT);
+			} else if (info->cmd == 2) {
+				__u32 value;
+				ret = bpf_map_lookup_elem(info->map_fd, key_p, &value);
+				assert(ret == 0 || errno == ENOENT);
+			} else {
+				struct bpf_lpm_trie_key *next_key_p = alloca(key_size);
+				ret = bpf_map_get_next_key(info->map_fd, key_p, next_key_p);
+				assert(ret == 0 || errno == ENOENT || errno == ENOMEM);
+			}
+		}
+
+	// Pass successful exit info back to the main thread
+	pthread_exit((void *)info);
+}
+
+static void setup_lpm_mt_test_info(struct lpm_mt_test_info *info, int map_fd)
+{
+	info->iter = 2000;
+	info->map_fd = map_fd;
+	info->key[0].prefixlen = 16;
+	inet_pton(AF_INET, "192.168.0.0", &info->key[0].data);
+	info->key[1].prefixlen = 24;
+	inet_pton(AF_INET, "192.168.0.0", &info->key[1].data);
+	info->key[2].prefixlen = 24;
+	inet_pton(AF_INET, "192.168.128.0", &info->key[2].data);
+	info->key[3].prefixlen = 24;
+	inet_pton(AF_INET, "192.168.1.0", &info->key[3].data);
+}
+
+static void test_lpm_multi_thread(void)
+{
+	struct lpm_mt_test_info info[4];
+	size_t key_size, value_size;
+	pthread_t thread_id[4];
+	int i, map_fd;
+	void *ret;
+
+	/* create a trie */
+	value_size = sizeof(__u32);
+	key_size = sizeof(struct bpf_lpm_trie_key) + value_size;
+	map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, value_size,
+				100, BPF_F_NO_PREALLOC);
+
+	/* create 4 threads to test update, delete, lookup and get_next_key */
+	setup_lpm_mt_test_info(&info[0], map_fd);
+	for (i = 0; i < 4; i++) {
+		if (i != 0)
+			memcpy(&info[i], &info[0], sizeof(info[i]));
+		info[i].cmd = i;
+		assert(pthread_create(&thread_id[i], NULL, &lpm_test_command, &info[i]) == 0);
+	}
+
+	for (i = 0; i < 4; i++)
+		assert(pthread_join(thread_id[i], &ret) == 0 && ret == (void *)&info[i]);
+
+	close(map_fd);
+}
+
 int main(void)
 {
 	struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
@@ -545,6 +758,10 @@ int main(void)
 
 	test_lpm_delete();
 
+	test_lpm_get_next_key();
+
+	test_lpm_multi_thread();
+
 	printf("test_lpm: OK\n");
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 040356ecc862..436c4c72414f 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -242,7 +242,7 @@ static void test_hashmap_percpu(int task, void *data)
 
 static void test_hashmap_walk(int task, void *data)
 {
-	int fd, i, max_entries = 100000;
+	int fd, i, max_entries = 1000;
 	long long key, value, next_key;
 	bool next_key_valid = true;
 
@@ -463,7 +463,7 @@ static void test_devmap(int task, void *data)
 #define SOCKMAP_VERDICT_PROG "./sockmap_verdict_prog.o"
 static void test_sockmap(int tasks, void *data)
 {
-	int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc;
+	int one = 1, map_fd_rx = 0, map_fd_tx = 0, map_fd_break, s, sc, rc;
 	struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break;
 	int ports[] = {50200, 50201, 50202, 50204};
 	int err, i, fd, udp, sfd[6] = {0xdeadbeef};
@@ -868,9 +868,12 @@ static void test_sockmap(int tasks, void *data)
 		goto out_sockmap;
 	}
 
-	/* Test map close sockets */
-	for (i = 0; i < 6; i++)
+	/* Test map close sockets and empty maps */
+	for (i = 0; i < 6; i++) {
+		bpf_map_delete_elem(map_fd_tx, &i);
+		bpf_map_delete_elem(map_fd_rx, &i);
 		close(sfd[i]);
+	}
 	close(fd);
 	close(map_fd_rx);
 	bpf_object__close(obj);
@@ -881,8 +884,13 @@ out:
 	printf("Failed to create sockmap '%i:%s'!\n", i, strerror(errno));
 	exit(1);
 out_sockmap:
-	for (i = 0; i < 6; i++)
+	for (i = 0; i < 6; i++) {
+		if (map_fd_tx)
+			bpf_map_delete_elem(map_fd_tx, &i);
+		if (map_fd_rx)
+			bpf_map_delete_elem(map_fd_rx, &i);
 		close(sfd[i]);
+	}
 	close(fd);
 	exit(1);
 }
@@ -931,8 +939,12 @@ static void test_map_large(void)
 	close(fd);
 }
 
-static void run_parallel(int tasks, void (*fn)(int task, void *data),
-			 void *data)
+#define run_parallel(N, FN, DATA) \
+	printf("Fork %d tasks to '" #FN "'\n", N); \
+	__run_parallel(N, FN, DATA)
+
+static void __run_parallel(int tasks, void (*fn)(int task, void *data),
+			   void *data)
 {
 	pid_t pid[tasks];
 	int i;
@@ -972,7 +984,7 @@ static void test_map_stress(void)
 #define DO_UPDATE 1
 #define DO_DELETE 0
 
-static void do_work(int fn, void *data)
+static void test_update_delete(int fn, void *data)
 {
 	int do_update = ((int *)data)[1];
 	int fd = ((int *)data)[0];
@@ -1012,7 +1024,7 @@ static void test_map_parallel(void)
 	 */
 	data[0] = fd;
 	data[1] = DO_UPDATE;
-	run_parallel(TASKS, do_work, data);
+	run_parallel(TASKS, test_update_delete, data);
 
 	/* Check that key=0 is already there. */
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 &&
@@ -1035,7 +1047,7 @@ static void test_map_parallel(void)
 
 	/* Now let's delete all elemenets in parallel. */
 	data[1] = DO_DELETE;
-	run_parallel(TASKS, do_work, data);
+	run_parallel(TASKS, test_update_delete, data);
 
 	/* Nothing should be left. */
 	key = -1;
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
new file mode 100755
index 000000000000..e78aad0a68bb
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -0,0 +1,1085 @@
+#!/usr/bin/python3
+
+# Copyright (C) 2017 Netronome Systems, Inc.
+#
+# This software is licensed under the GNU General License Version 2,
+# June 1991 as shown in the file COPYING in the top-level directory of this
+# source tree.
+#
+# THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+# WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+# BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+# FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+# OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+# THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+from datetime import datetime
+import argparse
+import json
+import os
+import pprint
+import random
+import string
+import struct
+import subprocess
+import time
+
+logfile = None
+log_level = 1
+skip_extack = False
+bpf_test_dir = os.path.dirname(os.path.realpath(__file__))
+pp = pprint.PrettyPrinter()
+devs = [] # devices we created for clean up
+files = [] # files to be removed
+netns = [] # net namespaces to be removed
+
+def log_get_sec(level=0):
+    return "*" * (log_level + level)
+
+def log_level_inc(add=1):
+    global log_level
+    log_level += add
+
+def log_level_dec(sub=1):
+    global log_level
+    log_level -= sub
+
+def log_level_set(level):
+    global log_level
+    log_level = level
+
+def log(header, data, level=None):
+    """
+    Output to an optional log.
+    """
+    if logfile is None:
+        return
+    if level is not None:
+        log_level_set(level)
+
+    if not isinstance(data, str):
+        data = pp.pformat(data)
+
+    if len(header):
+        logfile.write("\n" + log_get_sec() + " ")
+        logfile.write(header)
+    if len(header) and len(data.strip()):
+        logfile.write("\n")
+    logfile.write(data)
+
+def skip(cond, msg):
+    if not cond:
+        return
+    print("SKIP: " + msg)
+    log("SKIP: " + msg, "", level=1)
+    os.sys.exit(0)
+
+def fail(cond, msg):
+    if not cond:
+        return
+    print("FAIL: " + msg)
+    log("FAIL: " + msg, "", level=1)
+    os.sys.exit(1)
+
+def start_test(msg):
+    log(msg, "", level=1)
+    log_level_inc()
+    print(msg)
+
+def cmd(cmd, shell=True, include_stderr=False, background=False, fail=True):
+    """
+    Run a command in subprocess and return tuple of (retval, stdout);
+    optionally return stderr as well as third value.
+    """
+    proc = subprocess.Popen(cmd, shell=shell, stdout=subprocess.PIPE,
+                            stderr=subprocess.PIPE)
+    if background:
+        msg = "%s START: %s" % (log_get_sec(1),
+                                datetime.now().strftime("%H:%M:%S.%f"))
+        log("BKG " + proc.args, msg)
+        return proc
+
+    return cmd_result(proc, include_stderr=include_stderr, fail=fail)
+
+def cmd_result(proc, include_stderr=False, fail=False):
+    stdout, stderr = proc.communicate()
+    stdout = stdout.decode("utf-8")
+    stderr = stderr.decode("utf-8")
+    proc.stdout.close()
+    proc.stderr.close()
+
+    stderr = "\n" + stderr
+    if stderr[-1] == "\n":
+        stderr = stderr[:-1]
+
+    sec = log_get_sec(1)
+    log("CMD " + proc.args,
+        "RETCODE: %d\n%s STDOUT:\n%s%s STDERR:%s\n%s END: %s" %
+        (proc.returncode, sec, stdout, sec, stderr,
+         sec, datetime.now().strftime("%H:%M:%S.%f")))
+
+    if proc.returncode != 0 and fail:
+        if len(stderr) > 0 and stderr[-1] == "\n":
+            stderr = stderr[:-1]
+        raise Exception("Command failed: %s\n%s" % (proc.args, stderr))
+
+    if include_stderr:
+        return proc.returncode, stdout, stderr
+    else:
+        return proc.returncode, stdout
+
+def rm(f):
+    cmd("rm -f %s" % (f))
+    if f in files:
+        files.remove(f)
+
+def tool(name, args, flags, JSON=True, ns="", fail=True, include_stderr=False):
+    params = ""
+    if JSON:
+        params += "%s " % (flags["json"])
+
+    if ns != "":
+        ns = "ip netns exec %s " % (ns)
+
+    if include_stderr:
+        ret, stdout, stderr = cmd(ns + name + " " + params + args,
+                                  fail=fail, include_stderr=True)
+    else:
+        ret, stdout = cmd(ns + name + " " + params + args,
+                          fail=fail, include_stderr=False)
+
+    if JSON and len(stdout.strip()) != 0:
+        out = json.loads(stdout)
+    else:
+        out = stdout
+
+    if include_stderr:
+        return ret, out, stderr
+    else:
+        return ret, out
+
+def bpftool(args, JSON=True, ns="", fail=True):
+    return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns, fail=fail)
+
+def bpftool_prog_list(expected=None, ns=""):
+    _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
+    if expected is not None:
+        if len(progs) != expected:
+            fail(True, "%d BPF programs loaded, expected %d" %
+                 (len(progs), expected))
+    return progs
+
+def bpftool_map_list(expected=None, ns=""):
+    _, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
+    if expected is not None:
+        if len(maps) != expected:
+            fail(True, "%d BPF maps loaded, expected %d" %
+                 (len(maps), expected))
+    return maps
+
+def bpftool_prog_list_wait(expected=0, n_retry=20):
+    for i in range(n_retry):
+        nprogs = len(bpftool_prog_list())
+        if nprogs == expected:
+            return
+        time.sleep(0.05)
+    raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs))
+
+def bpftool_map_list_wait(expected=0, n_retry=20):
+    for i in range(n_retry):
+        nmaps = len(bpftool_map_list())
+        if nmaps == expected:
+            return
+        time.sleep(0.05)
+    raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
+
+def ip(args, force=False, JSON=True, ns="", fail=True, include_stderr=False):
+    if force:
+        args = "-force " + args
+    return tool("ip", args, {"json":"-j"}, JSON=JSON, ns=ns,
+                fail=fail, include_stderr=include_stderr)
+
+def tc(args, JSON=True, ns="", fail=True, include_stderr=False):
+    return tool("tc", args, {"json":"-p"}, JSON=JSON, ns=ns,
+                fail=fail, include_stderr=include_stderr)
+
+def ethtool(dev, opt, args, fail=True):
+    return cmd("ethtool %s %s %s" % (opt, dev["ifname"], args), fail=fail)
+
+def bpf_obj(name, sec=".text", path=bpf_test_dir,):
+    return "obj %s sec %s" % (os.path.join(path, name), sec)
+
+def bpf_pinned(name):
+    return "pinned %s" % (name)
+
+def bpf_bytecode(bytecode):
+    return "bytecode \"%s\"" % (bytecode)
+
+def mknetns(n_retry=10):
+    for i in range(n_retry):
+        name = ''.join([random.choice(string.ascii_letters) for i in range(8)])
+        ret, _ = ip("netns add %s" % (name), fail=False)
+        if ret == 0:
+            netns.append(name)
+            return name
+    return None
+
+def int2str(fmt, val):
+    ret = []
+    for b in struct.pack(fmt, val):
+        ret.append(int(b))
+    return " ".join(map(lambda x: str(x), ret))
+
+def str2int(strtab):
+    inttab = []
+    for i in strtab:
+        inttab.append(int(i, 16))
+    ba = bytearray(inttab)
+    if len(strtab) == 4:
+        fmt = "I"
+    elif len(strtab) == 8:
+        fmt = "Q"
+    else:
+        raise Exception("String array of len %d can't be unpacked to an int" %
+                        (len(strtab)))
+    return struct.unpack(fmt, ba)[0]
+
+class DebugfsDir:
+    """
+    Class for accessing DebugFS directories as a dictionary.
+    """
+
+    def __init__(self, path):
+        self.path = path
+        self._dict = self._debugfs_dir_read(path)
+
+    def __len__(self):
+        return len(self._dict.keys())
+
+    def __getitem__(self, key):
+        if type(key) is int:
+            key = list(self._dict.keys())[key]
+        return self._dict[key]
+
+    def __setitem__(self, key, value):
+        log("DebugFS set %s = %s" % (key, value), "")
+        log_level_inc()
+
+        cmd("echo '%s' > %s/%s" % (value, self.path, key))
+        log_level_dec()
+
+        _, out = cmd('cat %s/%s' % (self.path, key))
+        self._dict[key] = out.strip()
+
+    def _debugfs_dir_read(self, path):
+        dfs = {}
+
+        log("DebugFS state for %s" % (path), "")
+        log_level_inc(add=2)
+
+        _, out = cmd('ls ' + path)
+        for f in out.split():
+            p = os.path.join(path, f)
+            if os.path.isfile(p):
+                _, out = cmd('cat %s/%s' % (path, f))
+                dfs[f] = out.strip()
+            elif os.path.isdir(p):
+                dfs[f] = DebugfsDir(p)
+            else:
+                raise Exception("%s is neither file nor directory" % (p))
+
+        log_level_dec()
+        log("DebugFS state", dfs)
+        log_level_dec()
+
+        return dfs
+
+class NetdevSim:
+    """
+    Class for netdevsim netdevice and its attributes.
+    """
+
+    def __init__(self):
+        self.dev = self._netdevsim_create()
+        devs.append(self)
+
+        self.ns = ""
+
+        self.dfs_dir = '/sys/kernel/debug/netdevsim/%s' % (self.dev['ifname'])
+        self.dfs_refresh()
+
+    def __getitem__(self, key):
+        return self.dev[key]
+
+    def _netdevsim_create(self):
+        _, old  = ip("link show")
+        ip("link add sim%d type netdevsim")
+        _, new  = ip("link show")
+
+        for dev in new:
+            f = filter(lambda x: x["ifname"] == dev["ifname"], old)
+            if len(list(f)) == 0:
+                return dev
+
+        raise Exception("failed to create netdevsim device")
+
+    def remove(self):
+        devs.remove(self)
+        ip("link del dev %s" % (self.dev["ifname"]), ns=self.ns)
+
+    def dfs_refresh(self):
+        self.dfs = DebugfsDir(self.dfs_dir)
+        return self.dfs
+
+    def dfs_num_bound_progs(self):
+        path = os.path.join(self.dfs_dir, "bpf_bound_progs")
+        _, progs = cmd('ls %s' % (path))
+        return len(progs.split())
+
+    def dfs_get_bound_progs(self, expected):
+        progs = DebugfsDir(os.path.join(self.dfs_dir, "bpf_bound_progs"))
+        if expected is not None:
+            if len(progs) != expected:
+                fail(True, "%d BPF programs bound, expected %d" %
+                     (len(progs), expected))
+        return progs
+
+    def wait_for_flush(self, bound=0, total=0, n_retry=20):
+        for i in range(n_retry):
+            nbound = self.dfs_num_bound_progs()
+            nprogs = len(bpftool_prog_list())
+            if nbound == bound and nprogs == total:
+                return
+            time.sleep(0.05)
+        raise Exception("Time out waiting for program counts to stabilize want %d/%d, have %d bound, %d loaded" % (bound, total, nbound, nprogs))
+
+    def set_ns(self, ns):
+        name = "1" if ns == "" else ns
+        ip("link set dev %s netns %s" % (self.dev["ifname"], name), ns=self.ns)
+        self.ns = ns
+
+    def set_mtu(self, mtu, fail=True):
+        return ip("link set dev %s mtu %d" % (self.dev["ifname"], mtu),
+                  fail=fail)
+
+    def set_xdp(self, bpf, mode, force=False, JSON=True, verbose=False,
+                fail=True, include_stderr=False):
+        if verbose:
+            bpf += " verbose"
+        return ip("link set dev %s xdp%s %s" % (self.dev["ifname"], mode, bpf),
+                  force=force, JSON=JSON,
+                  fail=fail, include_stderr=include_stderr)
+
+    def unset_xdp(self, mode, force=False, JSON=True,
+                  fail=True, include_stderr=False):
+        return ip("link set dev %s xdp%s off" % (self.dev["ifname"], mode),
+                  force=force, JSON=JSON,
+                  fail=fail, include_stderr=include_stderr)
+
+    def ip_link_show(self, xdp):
+        _, link = ip("link show dev %s" % (self['ifname']))
+        if len(link) > 1:
+            raise Exception("Multiple objects on ip link show")
+        if len(link) < 1:
+            return {}
+        fail(xdp != "xdp" in link,
+             "XDP program not reporting in iplink (reported %s, expected %s)" %
+             ("xdp" in link, xdp))
+        return link[0]
+
+    def tc_add_ingress(self):
+        tc("qdisc add dev %s ingress" % (self['ifname']))
+
+    def tc_del_ingress(self):
+        tc("qdisc del dev %s ingress" % (self['ifname']))
+
+    def tc_flush_filters(self, bound=0, total=0):
+        self.tc_del_ingress()
+        self.tc_add_ingress()
+        self.wait_for_flush(bound=bound, total=total)
+
+    def tc_show_ingress(self, expected=None):
+        # No JSON support, oh well...
+        flags = ["skip_sw", "skip_hw", "in_hw"]
+        named = ["protocol", "pref", "chain", "handle", "id", "tag"]
+
+        args = "-s filter show dev %s ingress" % (self['ifname'])
+        _, out = tc(args, JSON=False)
+
+        filters = []
+        lines = out.split('\n')
+        for line in lines:
+            words = line.split()
+            if "handle" not in words:
+                continue
+            fltr = {}
+            for flag in flags:
+                fltr[flag] = flag in words
+            for name in named:
+                try:
+                    idx = words.index(name)
+                    fltr[name] = words[idx + 1]
+                except ValueError:
+                    pass
+            filters.append(fltr)
+
+        if expected is not None:
+            fail(len(filters) != expected,
+                 "%d ingress filters loaded, expected %d" %
+                 (len(filters), expected))
+        return filters
+
+    def cls_filter_op(self, op, qdisc="ingress", prio=None, handle=None,
+                      chain=None, cls="", params="",
+                      fail=True, include_stderr=False):
+        spec = ""
+        if prio is not None:
+            spec += " prio %d" % (prio)
+        if handle:
+            spec += " handle %s" % (handle)
+        if chain is not None:
+            spec += " chain %d" % (chain)
+
+        return tc("filter {op} dev {dev} {qdisc} {spec} {cls} {params}"\
+                  .format(op=op, dev=self['ifname'], qdisc=qdisc, spec=spec,
+                          cls=cls, params=params),
+                  fail=fail, include_stderr=include_stderr)
+
+    def cls_bpf_add_filter(self, bpf, op="add", prio=None, handle=None,
+                           chain=None, da=False, verbose=False,
+                           skip_sw=False, skip_hw=False,
+                           fail=True, include_stderr=False):
+        cls = "bpf " + bpf
+
+        params = ""
+        if da:
+            params += " da"
+        if verbose:
+            params += " verbose"
+        if skip_sw:
+            params += " skip_sw"
+        if skip_hw:
+            params += " skip_hw"
+
+        return self.cls_filter_op(op=op, prio=prio, handle=handle, cls=cls,
+                                  chain=chain, params=params,
+                                  fail=fail, include_stderr=include_stderr)
+
+    def set_ethtool_tc_offloads(self, enable, fail=True):
+        args = "hw-tc-offload %s" % ("on" if enable else "off")
+        return ethtool(self, "-K", args, fail=fail)
+
+################################################################################
+def clean_up():
+    global files, netns, devs
+
+    for dev in devs:
+        dev.remove()
+    for f in files:
+        cmd("rm -f %s" % (f))
+    for ns in netns:
+        cmd("ip netns delete %s" % (ns))
+    files = []
+    netns = []
+
+def pin_prog(file_name, idx=0):
+    progs = bpftool_prog_list(expected=(idx + 1))
+    prog = progs[idx]
+    bpftool("prog pin id %d %s" % (prog["id"], file_name))
+    files.append(file_name)
+
+    return file_name, bpf_pinned(file_name)
+
+def pin_map(file_name, idx=0, expected=1):
+    maps = bpftool_map_list(expected=expected)
+    m = maps[idx]
+    bpftool("map pin id %d %s" % (m["id"], file_name))
+    files.append(file_name)
+
+    return file_name, bpf_pinned(file_name)
+
+def check_dev_info_removed(prog_file=None, map_file=None):
+    bpftool_prog_list(expected=0)
+    ret, err = bpftool("prog show pin %s" % (prog_file), fail=False)
+    fail(ret == 0, "Showing prog with removed device did not fail")
+    fail(err["error"].find("No such device") == -1,
+         "Showing prog with removed device expected ENODEV, error is %s" %
+         (err["error"]))
+
+    bpftool_map_list(expected=0)
+    ret, err = bpftool("map show pin %s" % (map_file), fail=False)
+    fail(ret == 0, "Showing map with removed device did not fail")
+    fail(err["error"].find("No such device") == -1,
+         "Showing map with removed device expected ENODEV, error is %s" %
+         (err["error"]))
+
+def check_dev_info(other_ns, ns, prog_file=None, map_file=None, removed=False):
+    progs = bpftool_prog_list(expected=1, ns=ns)
+    prog = progs[0]
+
+    fail("dev" not in prog.keys(), "Device parameters not reported")
+    dev = prog["dev"]
+    fail("ifindex" not in dev.keys(), "Device parameters not reported")
+    fail("ns_dev" not in dev.keys(), "Device parameters not reported")
+    fail("ns_inode" not in dev.keys(), "Device parameters not reported")
+
+    if not other_ns:
+        fail("ifname" not in dev.keys(), "Ifname not reported")
+        fail(dev["ifname"] != sim["ifname"],
+             "Ifname incorrect %s vs %s" % (dev["ifname"], sim["ifname"]))
+    else:
+        fail("ifname" in dev.keys(), "Ifname is reported for other ns")
+
+    maps = bpftool_map_list(expected=2, ns=ns)
+    for m in maps:
+        fail("dev" not in m.keys(), "Device parameters not reported")
+        fail(dev != m["dev"], "Map's device different than program's")
+
+def check_extack(output, reference, args):
+    if skip_extack:
+        return
+    lines = output.split("\n")
+    comp = len(lines) >= 2 and lines[1] == reference
+    fail(not comp, "Missing or incorrect netlink extack message")
+
+def check_extack_nsim(output, reference, args):
+    check_extack(output, "Error: netdevsim: " + reference, args)
+
+def check_no_extack(res, needle):
+    fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
+         "Found '%s' in command output, leaky extack?" % (needle))
+
+def check_verifier_log(output, reference):
+    lines = output.split("\n")
+    for l in reversed(lines):
+        if l == reference:
+            return
+    fail(True, "Missing or incorrect message from netdevsim in verifier log")
+
+def test_spurios_extack(sim, obj, skip_hw, needle):
+    res = sim.cls_bpf_add_filter(obj, prio=1, handle=1, skip_hw=skip_hw,
+                                 include_stderr=True)
+    check_no_extack(res, needle)
+    res = sim.cls_bpf_add_filter(obj, op="replace", prio=1, handle=1,
+                                 skip_hw=skip_hw, include_stderr=True)
+    check_no_extack(res, needle)
+    res = sim.cls_filter_op(op="delete", prio=1, handle=1, cls="bpf",
+                            include_stderr=True)
+    check_no_extack(res, needle)
+
+
+# Parse command line
+parser = argparse.ArgumentParser()
+parser.add_argument("--log", help="output verbose log to given file")
+args = parser.parse_args()
+if args.log:
+    logfile = open(args.log, 'w+')
+    logfile.write("# -*-Org-*-")
+
+log("Prepare...", "", level=1)
+log_level_inc()
+
+# Check permissions
+skip(os.getuid() != 0, "test must be run as root")
+
+# Check tools
+ret, progs = bpftool("prog", fail=False)
+skip(ret != 0, "bpftool not installed")
+# Check no BPF programs are loaded
+skip(len(progs) != 0, "BPF programs already loaded on the system")
+
+# Check netdevsim
+ret, out = cmd("modprobe netdevsim", fail=False)
+skip(ret != 0, "netdevsim module could not be loaded")
+
+# Check debugfs
+_, out = cmd("mount")
+if out.find("/sys/kernel/debug type debugfs") == -1:
+    cmd("mount -t debugfs none /sys/kernel/debug")
+
+# Check samples are compiled
+samples = ["sample_ret0.o", "sample_map_ret0.o"]
+for s in samples:
+    ret, out = cmd("ls %s/%s" % (bpf_test_dir, s), fail=False)
+    skip(ret != 0, "sample %s/%s not found, please compile it" %
+         (bpf_test_dir, s))
+
+# Check if iproute2 is built with libmnl (needed by extack support)
+_, _, err = cmd("tc qdisc delete dev lo handle 0",
+                fail=False, include_stderr=True)
+if err.find("Error: Failed to find qdisc with specified handle.") == -1:
+    print("Warning: no extack message in iproute2 output, libmnl missing?")
+    log("Warning: no extack message in iproute2 output, libmnl missing?", "")
+    skip_extack = True
+
+# Check if net namespaces seem to work
+ns = mknetns()
+skip(ns is None, "Could not create a net namespace")
+cmd("ip netns delete %s" % (ns))
+netns = []
+
+try:
+    obj = bpf_obj("sample_ret0.o")
+    bytecode = bpf_bytecode("1,6 0 0 4294967295,")
+
+    start_test("Test destruction of generic XDP...")
+    sim = NetdevSim()
+    sim.set_xdp(obj, "generic")
+    sim.remove()
+    bpftool_prog_list_wait(expected=0)
+
+    sim = NetdevSim()
+    sim.tc_add_ingress()
+
+    start_test("Test TC non-offloaded...")
+    ret, _ = sim.cls_bpf_add_filter(obj, skip_hw=True, fail=False)
+    fail(ret != 0, "Software TC filter did not load")
+
+    start_test("Test TC non-offloaded isn't getting bound...")
+    ret, _ = sim.cls_bpf_add_filter(obj, fail=False)
+    fail(ret != 0, "Software TC filter did not load")
+    sim.dfs_get_bound_progs(expected=0)
+
+    sim.tc_flush_filters()
+
+    start_test("Test TC offloads are off by default...")
+    ret, _, err = sim.cls_bpf_add_filter(obj, skip_sw=True,
+                                         fail=False, include_stderr=True)
+    fail(ret == 0, "TC filter loaded without enabling TC offloads")
+    check_extack(err, "Error: TC offload is disabled on net device.", args)
+    sim.wait_for_flush()
+
+    sim.set_ethtool_tc_offloads(True)
+    sim.dfs["bpf_tc_non_bound_accept"] = "Y"
+
+    start_test("Test TC offload by default...")
+    ret, _ = sim.cls_bpf_add_filter(obj, fail=False)
+    fail(ret != 0, "Software TC filter did not load")
+    sim.dfs_get_bound_progs(expected=0)
+    ingress = sim.tc_show_ingress(expected=1)
+    fltr = ingress[0]
+    fail(not fltr["in_hw"], "Filter not offloaded by default")
+
+    sim.tc_flush_filters()
+
+    start_test("Test TC cBPF bytcode tries offload by default...")
+    ret, _ = sim.cls_bpf_add_filter(bytecode, fail=False)
+    fail(ret != 0, "Software TC filter did not load")
+    sim.dfs_get_bound_progs(expected=0)
+    ingress = sim.tc_show_ingress(expected=1)
+    fltr = ingress[0]
+    fail(not fltr["in_hw"], "Bytecode not offloaded by default")
+
+    sim.tc_flush_filters()
+    sim.dfs["bpf_tc_non_bound_accept"] = "N"
+
+    start_test("Test TC cBPF unbound bytecode doesn't offload...")
+    ret, _, err = sim.cls_bpf_add_filter(bytecode, skip_sw=True,
+                                         fail=False, include_stderr=True)
+    fail(ret == 0, "TC bytecode loaded for offload")
+    check_extack_nsim(err, "netdevsim configured to reject unbound programs.",
+                      args)
+    sim.wait_for_flush()
+
+    start_test("Test non-0 chain offload...")
+    ret, _, err = sim.cls_bpf_add_filter(obj, chain=1, prio=1, handle=1,
+                                         skip_sw=True,
+                                         fail=False, include_stderr=True)
+    fail(ret == 0, "Offloaded a filter to chain other than 0")
+    check_extack(err, "Error: Driver supports only offload of chain 0.", args)
+    sim.tc_flush_filters()
+
+    start_test("Test TC replace...")
+    sim.cls_bpf_add_filter(obj, prio=1, handle=1)
+    sim.cls_bpf_add_filter(obj, op="replace", prio=1, handle=1)
+    sim.cls_filter_op(op="delete", prio=1, handle=1, cls="bpf")
+
+    sim.cls_bpf_add_filter(obj, prio=1, handle=1, skip_sw=True)
+    sim.cls_bpf_add_filter(obj, op="replace", prio=1, handle=1, skip_sw=True)
+    sim.cls_filter_op(op="delete", prio=1, handle=1, cls="bpf")
+
+    sim.cls_bpf_add_filter(obj, prio=1, handle=1, skip_hw=True)
+    sim.cls_bpf_add_filter(obj, op="replace", prio=1, handle=1, skip_hw=True)
+    sim.cls_filter_op(op="delete", prio=1, handle=1, cls="bpf")
+
+    start_test("Test TC replace bad flags...")
+    for i in range(3):
+        for j in range(3):
+            ret, _ = sim.cls_bpf_add_filter(obj, op="replace", prio=1, handle=1,
+                                            skip_sw=(j == 1), skip_hw=(j == 2),
+                                            fail=False)
+            fail(bool(ret) != bool(j),
+                 "Software TC incorrect load in replace test, iteration %d" %
+                 (j))
+        sim.cls_filter_op(op="delete", prio=1, handle=1, cls="bpf")
+
+    start_test("Test spurious extack from the driver...")
+    test_spurios_extack(sim, obj, False, "netdevsim")
+    test_spurios_extack(sim, obj, True, "netdevsim")
+
+    sim.set_ethtool_tc_offloads(False)
+
+    test_spurios_extack(sim, obj, False, "TC offload is disabled")
+    test_spurios_extack(sim, obj, True, "TC offload is disabled")
+
+    sim.set_ethtool_tc_offloads(True)
+
+    sim.tc_flush_filters()
+
+    start_test("Test TC offloads work...")
+    ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True,
+                                         fail=False, include_stderr=True)
+    fail(ret != 0, "TC filter did not load with TC offloads enabled")
+    check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
+
+    start_test("Test TC offload basics...")
+    dfs = sim.dfs_get_bound_progs(expected=1)
+    progs = bpftool_prog_list(expected=1)
+    ingress = sim.tc_show_ingress(expected=1)
+
+    dprog = dfs[0]
+    prog = progs[0]
+    fltr = ingress[0]
+    fail(fltr["skip_hw"], "TC does reports 'skip_hw' on offloaded filter")
+    fail(not fltr["in_hw"], "TC does not report 'in_hw' for offloaded filter")
+    fail(not fltr["skip_sw"], "TC does not report 'skip_sw' back")
+
+    start_test("Test TC offload is device-bound...")
+    fail(str(prog["id"]) != fltr["id"], "Program IDs don't match")
+    fail(prog["tag"] != fltr["tag"], "Program tags don't match")
+    fail(fltr["id"] != dprog["id"], "Program IDs don't match")
+    fail(dprog["state"] != "xlated", "Offloaded program state not translated")
+    fail(dprog["loaded"] != "Y", "Offloaded program is not loaded")
+
+    start_test("Test disabling TC offloads is rejected while filters installed...")
+    ret, _ = sim.set_ethtool_tc_offloads(False, fail=False)
+    fail(ret == 0, "Driver should refuse to disable TC offloads with filters installed...")
+
+    start_test("Test qdisc removal frees things...")
+    sim.tc_flush_filters()
+    sim.tc_show_ingress(expected=0)
+
+    start_test("Test disabling TC offloads is OK without filters...")
+    ret, _ = sim.set_ethtool_tc_offloads(False, fail=False)
+    fail(ret != 0,
+         "Driver refused to disable TC offloads without filters installed...")
+
+    sim.set_ethtool_tc_offloads(True)
+
+    start_test("Test destroying device gets rid of TC filters...")
+    sim.cls_bpf_add_filter(obj, skip_sw=True)
+    sim.remove()
+    bpftool_prog_list_wait(expected=0)
+
+    sim = NetdevSim()
+    sim.set_ethtool_tc_offloads(True)
+
+    start_test("Test destroying device gets rid of XDP...")
+    sim.set_xdp(obj, "offload")
+    sim.remove()
+    bpftool_prog_list_wait(expected=0)
+
+    sim = NetdevSim()
+    sim.set_ethtool_tc_offloads(True)
+
+    start_test("Test XDP prog reporting...")
+    sim.set_xdp(obj, "drv")
+    ipl = sim.ip_link_show(xdp=True)
+    progs = bpftool_prog_list(expected=1)
+    fail(ipl["xdp"]["prog"]["id"] != progs[0]["id"],
+         "Loaded program has wrong ID")
+
+    start_test("Test XDP prog replace without force...")
+    ret, _ = sim.set_xdp(obj, "drv", fail=False)
+    fail(ret == 0, "Replaced XDP program without -force")
+    sim.wait_for_flush(total=1)
+
+    start_test("Test XDP prog replace with force...")
+    ret, _ = sim.set_xdp(obj, "drv", force=True, fail=False)
+    fail(ret != 0, "Could not replace XDP program with -force")
+    bpftool_prog_list_wait(expected=1)
+    ipl = sim.ip_link_show(xdp=True)
+    progs = bpftool_prog_list(expected=1)
+    fail(ipl["xdp"]["prog"]["id"] != progs[0]["id"],
+         "Loaded program has wrong ID")
+    fail("dev" in progs[0].keys(),
+         "Device parameters reported for non-offloaded program")
+
+    start_test("Test XDP prog replace with bad flags...")
+    ret, _, err = sim.set_xdp(obj, "offload", force=True,
+                              fail=False, include_stderr=True)
+    fail(ret == 0, "Replaced XDP program with a program in different mode")
+    check_extack_nsim(err, "program loaded with different flags.", args)
+    ret, _, err = sim.set_xdp(obj, "", force=True,
+                              fail=False, include_stderr=True)
+    fail(ret == 0, "Replaced XDP program with a program in different mode")
+    check_extack_nsim(err, "program loaded with different flags.", args)
+
+    start_test("Test XDP prog remove with bad flags...")
+    ret, _, err = sim.unset_xdp("offload", force=True,
+                                fail=False, include_stderr=True)
+    fail(ret == 0, "Removed program with a bad mode mode")
+    check_extack_nsim(err, "program loaded with different flags.", args)
+    ret, _, err = sim.unset_xdp("", force=True,
+                                fail=False, include_stderr=True)
+    fail(ret == 0, "Removed program with a bad mode mode")
+    check_extack_nsim(err, "program loaded with different flags.", args)
+
+    start_test("Test MTU restrictions...")
+    ret, _ = sim.set_mtu(9000, fail=False)
+    fail(ret == 0,
+         "Driver should refuse to increase MTU to 9000 with XDP loaded...")
+    sim.unset_xdp("drv")
+    bpftool_prog_list_wait(expected=0)
+    sim.set_mtu(9000)
+    ret, _, err = sim.set_xdp(obj, "drv", fail=False, include_stderr=True)
+    fail(ret == 0, "Driver should refuse to load program with MTU of 9000...")
+    check_extack_nsim(err, "MTU too large w/ XDP enabled.", args)
+    sim.set_mtu(1500)
+
+    sim.wait_for_flush()
+    start_test("Test XDP offload...")
+    _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True)
+    ipl = sim.ip_link_show(xdp=True)
+    link_xdp = ipl["xdp"]["prog"]
+    progs = bpftool_prog_list(expected=1)
+    prog = progs[0]
+    fail(link_xdp["id"] != prog["id"], "Loaded program has wrong ID")
+    check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
+
+    start_test("Test XDP offload is device bound...")
+    dfs = sim.dfs_get_bound_progs(expected=1)
+    dprog = dfs[0]
+
+    fail(prog["id"] != link_xdp["id"], "Program IDs don't match")
+    fail(prog["tag"] != link_xdp["tag"], "Program tags don't match")
+    fail(str(link_xdp["id"]) != dprog["id"], "Program IDs don't match")
+    fail(dprog["state"] != "xlated", "Offloaded program state not translated")
+    fail(dprog["loaded"] != "Y", "Offloaded program is not loaded")
+
+    start_test("Test removing XDP program many times...")
+    sim.unset_xdp("offload")
+    sim.unset_xdp("offload")
+    sim.unset_xdp("drv")
+    sim.unset_xdp("drv")
+    sim.unset_xdp("")
+    sim.unset_xdp("")
+    bpftool_prog_list_wait(expected=0)
+
+    start_test("Test attempt to use a program for a wrong device...")
+    sim2 = NetdevSim()
+    sim2.set_xdp(obj, "offload")
+    pin_file, pinned = pin_prog("/sys/fs/bpf/tmp")
+
+    ret, _, err = sim.set_xdp(pinned, "offload",
+                              fail=False, include_stderr=True)
+    fail(ret == 0, "Pinned program loaded for a different device accepted")
+    check_extack_nsim(err, "program bound to different dev.", args)
+    sim2.remove()
+    ret, _, err = sim.set_xdp(pinned, "offload",
+                              fail=False, include_stderr=True)
+    fail(ret == 0, "Pinned program loaded for a removed device accepted")
+    check_extack_nsim(err, "xdpoffload of non-bound program.", args)
+    rm(pin_file)
+    bpftool_prog_list_wait(expected=0)
+
+    start_test("Test mixing of TC and XDP...")
+    sim.tc_add_ingress()
+    sim.set_xdp(obj, "offload")
+    ret, _, err = sim.cls_bpf_add_filter(obj, skip_sw=True,
+                                         fail=False, include_stderr=True)
+    fail(ret == 0, "Loading TC when XDP active should fail")
+    check_extack_nsim(err, "driver and netdev offload states mismatch.", args)
+    sim.unset_xdp("offload")
+    sim.wait_for_flush()
+
+    sim.cls_bpf_add_filter(obj, skip_sw=True)
+    ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True)
+    fail(ret == 0, "Loading XDP when TC active should fail")
+    check_extack_nsim(err, "TC program is already loaded.", args)
+
+    start_test("Test binding TC from pinned...")
+    pin_file, pinned = pin_prog("/sys/fs/bpf/tmp")
+    sim.tc_flush_filters(bound=1, total=1)
+    sim.cls_bpf_add_filter(pinned, da=True, skip_sw=True)
+    sim.tc_flush_filters(bound=1, total=1)
+
+    start_test("Test binding XDP from pinned...")
+    sim.set_xdp(obj, "offload")
+    pin_file, pinned = pin_prog("/sys/fs/bpf/tmp2", idx=1)
+
+    sim.set_xdp(pinned, "offload", force=True)
+    sim.unset_xdp("offload")
+    sim.set_xdp(pinned, "offload", force=True)
+    sim.unset_xdp("offload")
+
+    start_test("Test offload of wrong type fails...")
+    ret, _ = sim.cls_bpf_add_filter(pinned, da=True, skip_sw=True, fail=False)
+    fail(ret == 0, "Managed to attach XDP program to TC")
+
+    start_test("Test asking for TC offload of two filters...")
+    sim.cls_bpf_add_filter(obj, da=True, skip_sw=True)
+    ret, _, err = sim.cls_bpf_add_filter(obj, da=True, skip_sw=True,
+                                         fail=False, include_stderr=True)
+    fail(ret == 0, "Managed to offload two TC filters at the same time")
+    check_extack_nsim(err, "driver and netdev offload states mismatch.", args)
+
+    sim.tc_flush_filters(bound=2, total=2)
+
+    start_test("Test if netdev removal waits for translation...")
+    delay_msec = 500
+    sim.dfs["bpf_bind_verifier_delay"] = delay_msec
+    start = time.time()
+    cmd_line = "tc filter add dev %s ingress bpf %s da skip_sw" % \
+               (sim['ifname'], obj)
+    tc_proc = cmd(cmd_line, background=True, fail=False)
+    # Wait for the verifier to start
+    while sim.dfs_num_bound_progs() <= 2:
+        pass
+    sim.remove()
+    end = time.time()
+    ret, _ = cmd_result(tc_proc, fail=False)
+    time_diff = end - start
+    log("Time", "start:\t%s\nend:\t%s\ndiff:\t%s" % (start, end, time_diff))
+
+    fail(ret == 0, "Managed to load TC filter on a unregistering device")
+    delay_sec = delay_msec * 0.001
+    fail(time_diff < delay_sec, "Removal process took %s, expected %s" %
+         (time_diff, delay_sec))
+
+    # Remove all pinned files and reinstantiate the netdev
+    clean_up()
+    bpftool_prog_list_wait(expected=0)
+
+    sim = NetdevSim()
+    map_obj = bpf_obj("sample_map_ret0.o")
+    start_test("Test loading program with maps...")
+    sim.set_xdp(map_obj, "offload", JSON=False) # map fixup msg breaks JSON
+
+    start_test("Test bpftool bound info reporting (own ns)...")
+    check_dev_info(False, "")
+
+    start_test("Test bpftool bound info reporting (other ns)...")
+    ns = mknetns()
+    sim.set_ns(ns)
+    check_dev_info(True, "")
+
+    start_test("Test bpftool bound info reporting (remote ns)...")
+    check_dev_info(False, ns)
+
+    start_test("Test bpftool bound info reporting (back to own ns)...")
+    sim.set_ns("")
+    check_dev_info(False, "")
+
+    prog_file, _ = pin_prog("/sys/fs/bpf/tmp_prog")
+    map_file, _ = pin_map("/sys/fs/bpf/tmp_map", idx=1, expected=2)
+    sim.remove()
+
+    start_test("Test bpftool bound info reporting (removed dev)...")
+    check_dev_info_removed(prog_file=prog_file, map_file=map_file)
+
+    # Remove all pinned files and reinstantiate the netdev
+    clean_up()
+    bpftool_prog_list_wait(expected=0)
+
+    sim = NetdevSim()
+
+    start_test("Test map update (no flags)...")
+    sim.set_xdp(map_obj, "offload", JSON=False) # map fixup msg breaks JSON
+    maps = bpftool_map_list(expected=2)
+    array = maps[0] if maps[0]["type"] == "array" else maps[1]
+    htab = maps[0] if maps[0]["type"] == "hash" else maps[1]
+    for m in maps:
+        for i in range(2):
+            bpftool("map update id %d key %s value %s" %
+                    (m["id"], int2str("I", i), int2str("Q", i * 3)))
+
+    for m in maps:
+        ret, _ = bpftool("map update id %d key %s value %s" %
+                         (m["id"], int2str("I", 3), int2str("Q", 3 * 3)),
+                         fail=False)
+        fail(ret == 0, "added too many entries")
+
+    start_test("Test map update (exists)...")
+    for m in maps:
+        for i in range(2):
+            bpftool("map update id %d key %s value %s exist" %
+                    (m["id"], int2str("I", i), int2str("Q", i * 3)))
+
+    for m in maps:
+        ret, err = bpftool("map update id %d key %s value %s exist" %
+                           (m["id"], int2str("I", 3), int2str("Q", 3 * 3)),
+                           fail=False)
+        fail(ret == 0, "updated non-existing key")
+        fail(err["error"].find("No such file or directory") == -1,
+             "expected ENOENT, error is '%s'" % (err["error"]))
+
+    start_test("Test map update (noexist)...")
+    for m in maps:
+        for i in range(2):
+            ret, err = bpftool("map update id %d key %s value %s noexist" %
+                               (m["id"], int2str("I", i), int2str("Q", i * 3)),
+                               fail=False)
+        fail(ret == 0, "updated existing key")
+        fail(err["error"].find("File exists") == -1,
+             "expected EEXIST, error is '%s'" % (err["error"]))
+
+    start_test("Test map dump...")
+    for m in maps:
+        _, entries = bpftool("map dump id %d" % (m["id"]))
+        for i in range(2):
+            key = str2int(entries[i]["key"])
+            fail(key != i, "expected key %d, got %d" % (key, i))
+            val = str2int(entries[i]["value"])
+            fail(val != i * 3, "expected value %d, got %d" % (val, i * 3))
+
+    start_test("Test map getnext...")
+    for m in maps:
+        _, entry = bpftool("map getnext id %d" % (m["id"]))
+        key = str2int(entry["next_key"])
+        fail(key != 0, "next key %d, expected %d" % (key, 0))
+        _, entry = bpftool("map getnext id %d key %s" %
+                           (m["id"], int2str("I", 0)))
+        key = str2int(entry["next_key"])
+        fail(key != 1, "next key %d, expected %d" % (key, 1))
+        ret, err = bpftool("map getnext id %d key %s" %
+                           (m["id"], int2str("I", 1)), fail=False)
+        fail(ret == 0, "got next key past the end of map")
+        fail(err["error"].find("No such file or directory") == -1,
+             "expected ENOENT, error is '%s'" % (err["error"]))
+
+    start_test("Test map delete (htab)...")
+    for i in range(2):
+        bpftool("map delete id %d key %s" % (htab["id"], int2str("I", i)))
+
+    start_test("Test map delete (array)...")
+    for i in range(2):
+        ret, err = bpftool("map delete id %d key %s" %
+                           (htab["id"], int2str("I", i)), fail=False)
+        fail(ret == 0, "removed entry from an array")
+        fail(err["error"].find("No such file or directory") == -1,
+             "expected ENOENT, error is '%s'" % (err["error"]))
+
+    start_test("Test map remove...")
+    sim.unset_xdp("offload")
+    bpftool_map_list_wait(expected=0)
+    sim.remove()
+
+    sim = NetdevSim()
+    sim.set_xdp(map_obj, "offload", JSON=False) # map fixup msg breaks JSON
+    sim.remove()
+    bpftool_map_list_wait(expected=0)
+
+    start_test("Test map creation fail path...")
+    sim = NetdevSim()
+    sim.dfs["bpf_map_accept"] = "N"
+    ret, _ = sim.set_xdp(map_obj, "offload", JSON=False, fail=False)
+    fail(ret == 0,
+         "netdevsim didn't refuse to create a map with offload disabled")
+
+    print("%s: OK" % (os.path.basename(__file__)))
+
+finally:
+    log("Clean up...", "", level=1)
+    log_level_inc()
+    clean_up()
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 6761be18a91f..b549308abd19 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -21,8 +21,10 @@ typedef __u16 __sum16;
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
 #include <linux/filter.h>
+#include <linux/perf_event.h>
 #include <linux/unistd.h>
 
+#include <sys/ioctl.h>
 #include <sys/wait.h>
 #include <sys/resource.h>
 #include <sys/types.h>
@@ -167,10 +169,9 @@ out:
 #define NUM_ITER 100000
 #define VIP_NUM 5
 
-static void test_l4lb(void)
+static void test_l4lb(const char *file)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
-	const char *file = "./test_l4lb.o";
 	struct vip key = {.protocol = 6};
 	struct vip_meta {
 		__u32 flags;
@@ -247,6 +248,95 @@ out:
 	bpf_object__close(obj);
 }
 
+static void test_l4lb_all(void)
+{
+	const char *file1 = "./test_l4lb.o";
+	const char *file2 = "./test_l4lb_noinline.o";
+
+	test_l4lb(file1);
+	test_l4lb(file2);
+}
+
+static void test_xdp_noinline(void)
+{
+	const char *file = "./test_xdp_noinline.o";
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	struct vip key = {.protocol = 6};
+	struct vip_meta {
+		__u32 flags;
+		__u32 vip_num;
+	} value = {.vip_num = VIP_NUM};
+	__u32 stats_key = VIP_NUM;
+	struct vip_stats {
+		__u64 bytes;
+		__u64 pkts;
+	} stats[nr_cpus];
+	struct real_definition {
+		union {
+			__be32 dst;
+			__be32 dstv6[4];
+		};
+		__u8 flags;
+	} real_def = {.dst = MAGIC_VAL};
+	__u32 ch_key = 11, real_num = 3;
+	__u32 duration, retval, size;
+	int err, i, prog_fd, map_fd;
+	__u64 bytes = 0, pkts = 0;
+	struct bpf_object *obj;
+	char buf[128];
+	u32 *magic = (u32 *)buf;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (err) {
+		error_cnt++;
+		return;
+	}
+
+	map_fd = bpf_find_map(__func__, obj, "vip_map");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &key, &value, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "ch_rings");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
+
+	map_fd = bpf_find_map(__func__, obj, "reals");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != 1 || size != 54 ||
+	      *magic != MAGIC_VAL, "ipv4",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
+				buf, &size, &retval, &duration);
+	CHECK(err || errno || retval != 1 || size != 74 ||
+	      *magic != MAGIC_VAL, "ipv6",
+	      "err %d errno %d retval %d size %d magic %x\n",
+	      err, errno, retval, size, *magic);
+
+	map_fd = bpf_find_map(__func__, obj, "stats");
+	if (map_fd < 0)
+		goto out;
+	bpf_map_lookup_elem(map_fd, &stats_key, stats);
+	for (i = 0; i < nr_cpus; i++) {
+		bytes += stats[i].bytes;
+		pkts += stats[i].pkts;
+	}
+	if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) {
+		error_cnt++;
+		printf("test_xdp_noinline:FAIL:stats %lld %lld\n", bytes, pkts);
+	}
+out:
+	bpf_object__close(obj);
+}
+
 static void test_tcp_estats(void)
 {
 	const char *file = "./test_tcp_estats.o";
@@ -617,6 +707,262 @@ static void test_obj_name(void)
 	}
 }
 
+static void test_tp_attach_query(void)
+{
+	const int num_progs = 3;
+	int i, j, bytes, efd, err, prog_fd[num_progs], pmu_fd[num_progs];
+	__u32 duration = 0, info_len, saved_prog_ids[num_progs];
+	const char *file = "./test_tracepoint.o";
+	struct perf_event_query_bpf *query;
+	struct perf_event_attr attr = {};
+	struct bpf_object *obj[num_progs];
+	struct bpf_prog_info prog_info;
+	char buf[256];
+
+	snprintf(buf, sizeof(buf),
+		 "/sys/kernel/debug/tracing/events/sched/sched_switch/id");
+	efd = open(buf, O_RDONLY, 0);
+	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+		return;
+	bytes = read(efd, buf, sizeof(buf));
+	close(efd);
+	if (CHECK(bytes <= 0 || bytes >= sizeof(buf),
+		  "read", "bytes %d errno %d\n", bytes, errno))
+		return;
+
+	attr.config = strtol(buf, NULL, 0);
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN;
+	attr.sample_period = 1;
+	attr.wakeup_events = 1;
+
+	query = malloc(sizeof(*query) + sizeof(__u32) * num_progs);
+	for (i = 0; i < num_progs; i++) {
+		err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj[i],
+				    &prog_fd[i]);
+		if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+			goto cleanup1;
+
+		bzero(&prog_info, sizeof(prog_info));
+		prog_info.jited_prog_len = 0;
+		prog_info.xlated_prog_len = 0;
+		prog_info.nr_map_ids = 0;
+		info_len = sizeof(prog_info);
+		err = bpf_obj_get_info_by_fd(prog_fd[i], &prog_info, &info_len);
+		if (CHECK(err, "bpf_obj_get_info_by_fd", "err %d errno %d\n",
+			  err, errno))
+			goto cleanup1;
+		saved_prog_ids[i] = prog_info.id;
+
+		pmu_fd[i] = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+				    0 /* cpu 0 */, -1 /* group id */,
+				    0 /* flags */);
+		if (CHECK(pmu_fd[i] < 0, "perf_event_open", "err %d errno %d\n",
+			  pmu_fd[i], errno))
+			goto cleanup2;
+		err = ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0);
+		if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
+			  err, errno))
+			goto cleanup3;
+
+		if (i == 0) {
+			/* check NULL prog array query */
+			query->ids_len = num_progs;
+			err = ioctl(pmu_fd[i], PERF_EVENT_IOC_QUERY_BPF, query);
+			if (CHECK(err || query->prog_cnt != 0,
+				  "perf_event_ioc_query_bpf",
+				  "err %d errno %d query->prog_cnt %u\n",
+				  err, errno, query->prog_cnt))
+				goto cleanup3;
+		}
+
+		err = ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[i]);
+		if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
+			  err, errno))
+			goto cleanup3;
+
+		if (i == 1) {
+			/* try to get # of programs only */
+			query->ids_len = 0;
+			err = ioctl(pmu_fd[i], PERF_EVENT_IOC_QUERY_BPF, query);
+			if (CHECK(err || query->prog_cnt != 2,
+				  "perf_event_ioc_query_bpf",
+				  "err %d errno %d query->prog_cnt %u\n",
+				  err, errno, query->prog_cnt))
+				goto cleanup3;
+
+			/* try a few negative tests */
+			/* invalid query pointer */
+			err = ioctl(pmu_fd[i], PERF_EVENT_IOC_QUERY_BPF,
+				    (struct perf_event_query_bpf *)0x1);
+			if (CHECK(!err || errno != EFAULT,
+				  "perf_event_ioc_query_bpf",
+				  "err %d errno %d\n", err, errno))
+				goto cleanup3;
+
+			/* no enough space */
+			query->ids_len = 1;
+			err = ioctl(pmu_fd[i], PERF_EVENT_IOC_QUERY_BPF, query);
+			if (CHECK(!err || errno != ENOSPC || query->prog_cnt != 2,
+				  "perf_event_ioc_query_bpf",
+				  "err %d errno %d query->prog_cnt %u\n",
+				  err, errno, query->prog_cnt))
+				goto cleanup3;
+		}
+
+		query->ids_len = num_progs;
+		err = ioctl(pmu_fd[i], PERF_EVENT_IOC_QUERY_BPF, query);
+		if (CHECK(err || query->prog_cnt != (i + 1),
+			  "perf_event_ioc_query_bpf",
+			  "err %d errno %d query->prog_cnt %u\n",
+			  err, errno, query->prog_cnt))
+			goto cleanup3;
+		for (j = 0; j < i + 1; j++)
+			if (CHECK(saved_prog_ids[j] != query->ids[j],
+				  "perf_event_ioc_query_bpf",
+				  "#%d saved_prog_id %x query prog_id %x\n",
+				  j, saved_prog_ids[j], query->ids[j]))
+				goto cleanup3;
+	}
+
+	i = num_progs - 1;
+	for (; i >= 0; i--) {
+ cleanup3:
+		ioctl(pmu_fd[i], PERF_EVENT_IOC_DISABLE);
+ cleanup2:
+		close(pmu_fd[i]);
+ cleanup1:
+		bpf_object__close(obj[i]);
+	}
+	free(query);
+}
+
+static int compare_map_keys(int map1_fd, int map2_fd)
+{
+	__u32 key, next_key;
+	char val_buf[PERF_MAX_STACK_DEPTH * sizeof(__u64)];
+	int err;
+
+	err = bpf_map_get_next_key(map1_fd, NULL, &key);
+	if (err)
+		return err;
+	err = bpf_map_lookup_elem(map2_fd, &key, val_buf);
+	if (err)
+		return err;
+
+	while (bpf_map_get_next_key(map1_fd, &key, &next_key) == 0) {
+		err = bpf_map_lookup_elem(map2_fd, &next_key, val_buf);
+		if (err)
+			return err;
+
+		key = next_key;
+	}
+	if (errno != ENOENT)
+		return -1;
+
+	return 0;
+}
+
+static void test_stacktrace_map()
+{
+	int control_map_fd, stackid_hmap_fd, stackmap_fd;
+	const char *file = "./test_stacktrace_map.o";
+	int bytes, efd, err, pmu_fd, prog_fd;
+	struct perf_event_attr attr = {};
+	__u32 key, val, duration = 0;
+	struct bpf_object *obj;
+	char buf[256];
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
+	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+		goto out;
+
+	/* Get the ID for the sched/sched_switch tracepoint */
+	snprintf(buf, sizeof(buf),
+		 "/sys/kernel/debug/tracing/events/sched/sched_switch/id");
+	efd = open(buf, O_RDONLY, 0);
+	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+		goto close_prog;
+
+	bytes = read(efd, buf, sizeof(buf));
+	close(efd);
+	if (CHECK(bytes <= 0 || bytes >= sizeof(buf),
+		  "read", "bytes %d errno %d\n", bytes, errno))
+		goto close_prog;
+
+	/* Open the perf event and attach bpf progrram */
+	attr.config = strtol(buf, NULL, 0);
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN;
+	attr.sample_period = 1;
+	attr.wakeup_events = 1;
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+			 0 /* cpu 0 */, -1 /* group id */,
+			 0 /* flags */);
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
+		  pmu_fd, errno))
+		goto close_prog;
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
+		  err, errno))
+		goto close_pmu;
+
+	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
+	if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
+		  err, errno))
+		goto disable_pmu;
+
+	/* find map fds */
+	control_map_fd = bpf_find_map(__func__, obj, "control_map");
+	if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
+	if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
+	if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
+		  err, errno))
+		goto disable_pmu;
+
+	/* give some time for bpf program run */
+	sleep(1);
+
+	/* disable stack trace collection */
+	key = 0;
+	val = 1;
+	bpf_map_update_elem(control_map_fd, &key, &val, 0);
+
+	/* for every element in stackid_hmap, we can find a corresponding one
+	 * in stackmap, and vise versa.
+	 */
+	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
+	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
+		  "err %d errno %d\n", err, errno))
+		goto disable_pmu;
+
+	err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
+	if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
+		  "err %d errno %d\n", err, errno))
+		; /* fall through */
+
+disable_pmu:
+	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+
+close_pmu:
+	close(pmu_fd);
+
+close_prog:
+	bpf_object__close(obj);
+
+out:
+	return;
+}
+
 int main(void)
 {
 	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
@@ -625,11 +971,14 @@ int main(void)
 
 	test_pkt_access();
 	test_xdp();
-	test_l4lb();
+	test_l4lb_all();
+	test_xdp_noinline();
 	test_tcp_estats();
 	test_bpf_obj_id();
 	test_pkt_md_access();
 	test_obj_name();
+	test_tp_attach_query();
+	test_stacktrace_map();
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_stacktrace_map.c b/tools/testing/selftests/bpf/test_stacktrace_map.c
new file mode 100644
index 000000000000..76d85c5d08bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_stacktrace_map.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
+struct bpf_map_def SEC("maps") control_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") stackid_hmap = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 10000,
+};
+
+struct bpf_map_def SEC("maps") stackmap = {
+	.type = BPF_MAP_TYPE_STACK_TRACE,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
+	.max_entries = 10000,
+};
+
+/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
+struct sched_switch_args {
+	unsigned long long pad;
+	char prev_comm[16];
+	int prev_pid;
+	int prev_prio;
+	long long prev_state;
+	char next_comm[16];
+	int next_pid;
+	int next_prio;
+};
+
+SEC("tracepoint/sched/sched_switch")
+int oncpu(struct sched_switch_args *ctx)
+{
+	__u32 key = 0, val = 0, *value_p;
+
+	value_p = bpf_map_lookup_elem(&control_map, &key);
+	if (value_p && *value_p)
+		return 0; /* skip if non-zero *value_p */
+
+	/* The size of stackmap and stackid_hmap should be the same */
+	key = bpf_get_stackid(ctx, &stackmap, 0);
+	if ((int)key >= 0)
+		bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h
new file mode 100644
index 000000000000..2fe43289943c
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf.h
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpbpf_globals {
+	__u32 event_map;
+	__u32 total_retrans;
+	__u32 data_segs_in;
+	__u32 data_segs_out;
+	__u32 bad_cb_test_rv;
+	__u32 good_cb_test_rv;
+	__u64 bytes_received;
+	__u64 bytes_acked;
+};
+#endif
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
new file mode 100644
index 000000000000..57119ad57a3f
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/in6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcpbpf.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct tcpbpf_globals),
+	.max_entries = 2,
+};
+
+static inline void update_event_map(int event)
+{
+	__u32 key = 0;
+	struct tcpbpf_globals g, *gp;
+
+	gp = bpf_map_lookup_elem(&global_map, &key);
+	if (gp == NULL) {
+		struct tcpbpf_globals g = {0};
+
+		g.event_map |= (1 << event);
+		bpf_map_update_elem(&global_map, &key, &g,
+			    BPF_ANY);
+	} else {
+		g = *gp;
+		g.event_map |= (1 << event);
+		bpf_map_update_elem(&global_map, &key, &g,
+			    BPF_ANY);
+	}
+}
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int bad_call_rv = 0;
+	int good_call_rv = 0;
+	int op;
+	int v = 0;
+
+	op = (int) skops->op;
+
+	update_event_map(op);
+
+	switch (op) {
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		/* Test failure to set largest cb flag (assumes not defined) */
+		bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
+		/* Set callback */
+		good_call_rv = bpf_sock_ops_cb_flags_set(skops,
+						 BPF_SOCK_OPS_STATE_CB_FLAG);
+		/* Update results */
+		{
+			__u32 key = 0;
+			struct tcpbpf_globals g, *gp;
+
+			gp = bpf_map_lookup_elem(&global_map, &key);
+			if (!gp)
+				break;
+			g = *gp;
+			g.bad_cb_test_rv = bad_call_rv;
+			g.good_cb_test_rv = good_call_rv;
+			bpf_map_update_elem(&global_map, &key, &g,
+					    BPF_ANY);
+		}
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		skops->sk_txhash = 0x12345f;
+		v = 0xff;
+		rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
+				    sizeof(v));
+		break;
+	case BPF_SOCK_OPS_RTO_CB:
+		break;
+	case BPF_SOCK_OPS_RETRANS_CB:
+		break;
+	case BPF_SOCK_OPS_STATE_CB:
+		if (skops->args[1] == BPF_TCP_CLOSE) {
+			__u32 key = 0;
+			struct tcpbpf_globals g, *gp;
+
+			gp = bpf_map_lookup_elem(&global_map, &key);
+			if (!gp)
+				break;
+			g = *gp;
+			g.total_retrans = skops->total_retrans;
+			g.data_segs_in = skops->data_segs_in;
+			g.data_segs_out = skops->data_segs_out;
+			g.bytes_received = skops->bytes_received;
+			g.bytes_acked = skops->bytes_acked;
+			bpf_map_update_elem(&global_map, &key, &g,
+					    BPF_ANY);
+		}
+		break;
+	default:
+		rv = -1;
+	}
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
new file mode 100644
index 000000000000..95a370f3d378
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <assert.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include <linux/perf_event.h>
+#include "test_tcpbpf.h"
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+#define SYSTEM(CMD)						\
+	do {							\
+		if (system(CMD)) {				\
+			printf("system(%s) FAILS!\n", CMD);	\
+		}						\
+	} while (0)
+
+int main(int argc, char **argv)
+{
+	const char *file = "test_tcpbpf_kern.o";
+	struct tcpbpf_globals g = {0};
+	int cg_fd, prog_fd, map_fd;
+	bool debug_flag = false;
+	int error = EXIT_FAILURE;
+	struct bpf_object *obj;
+	char cmd[100], *dir;
+	struct stat buffer;
+	__u32 key = 0;
+	int pid;
+	int rv;
+
+	if (argc > 1 && strcmp(argv[1], "-d") == 0)
+		debug_flag = true;
+
+	dir = "/tmp/cgroupv2/foo";
+
+	if (stat(dir, &buffer) != 0) {
+		SYSTEM("mkdir -p /tmp/cgroupv2");
+		SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
+		SYSTEM("mkdir -p /tmp/cgroupv2/foo");
+	}
+	pid = (int) getpid();
+	sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
+	SYSTEM(cmd);
+
+	cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
+	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+		printf("FAILED: load_bpf_file failed for: %s\n", file);
+		goto err;
+	}
+
+	rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (rv) {
+		printf("FAILED: bpf_prog_attach: %d (%s)\n",
+		       error, strerror(errno));
+		goto err;
+	}
+
+	SYSTEM("./tcp_server.py");
+
+	map_fd = bpf_find_map(__func__, obj, "global_map");
+	if (map_fd < 0)
+		goto err;
+
+	rv = bpf_map_lookup_elem(map_fd, &key, &g);
+	if (rv != 0) {
+		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+		goto err;
+	}
+
+	if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
+	    g.data_segs_in != 1 || g.data_segs_out != 1 ||
+	    (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 ||
+		g.good_cb_test_rv != 0) {
+		printf("FAILED: Wrong stats\n");
+		if (debug_flag) {
+			printf("\n");
+			printf("bytes_received: %d (expecting 501)\n",
+			       (int)g.bytes_received);
+			printf("bytes_acked:    %d (expecting 1002)\n",
+			       (int)g.bytes_acked);
+			printf("data_segs_in:   %d (expecting 1)\n",
+			       g.data_segs_in);
+			printf("data_segs_out:  %d (expecting 1)\n",
+			       g.data_segs_out);
+			printf("event_map:      0x%x (at least 0x47e)\n",
+			       g.event_map);
+			printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n",
+			       g.bad_cb_test_rv);
+			printf("good_cb_test_rv:0x%x (expecting 0)\n",
+			       g.good_cb_test_rv);
+		}
+		goto err;
+	}
+	printf("PASSED!\n");
+	error = 0;
+err:
+	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	return error;
+
+}
diff --git a/tools/testing/selftests/bpf/test_tracepoint.c b/tools/testing/selftests/bpf/test_tracepoint.c
new file mode 100644
index 000000000000..04bf084517e0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tracepoint.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
+struct sched_switch_args {
+	unsigned long long pad;
+	char prev_comm[16];
+	int prev_pid;
+	int prev_prio;
+	long long prev_state;
+	char next_comm[16];
+	int next_pid;
+	int next_prio;
+};
+
+SEC("tracepoint/sched/sched_switch")
+int oncpu(struct sched_switch_args *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 5ed4175c4ff8..697bd83de295 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2,6 +2,7 @@
  * Testsuite for eBPF verifier
  *
  * Copyright (c) 2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2017 Facebook
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -20,6 +21,7 @@
 #include <stddef.h>
 #include <stdbool.h>
 #include <sched.h>
+#include <limits.h>
 
 #include <sys/capability.h>
 #include <sys/resource.h>
@@ -28,6 +30,7 @@
 #include <linux/filter.h>
 #include <linux/bpf_perf_event.h>
 #include <linux/bpf.h>
+#include <linux/if_ether.h>
 
 #include <bpf/bpf.h>
 
@@ -48,6 +51,8 @@
 #define MAX_INSNS	512
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	4
+#define POINTER_VALUE	0xcafe4all
+#define TEST_DATA_LEN	64
 
 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
 #define F_LOAD_WITH_STRICT_ALIGNMENT		(1 << 1)
@@ -61,6 +66,7 @@ struct bpf_test {
 	int fixup_map_in_map[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
+	uint32_t retval;
 	enum {
 		UNDEF,
 		ACCEPT,
@@ -94,6 +100,326 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = -3,
+	},
+	{
+		"DIV32 by 0, zero check 1",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_2, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"DIV32 by 0, zero check 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+			BPF_MOV32_IMM(BPF_REG_2, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"DIV64 by 0, zero check",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_2, 1),
+			BPF_ALU64_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"MOD32 by 0, zero check 1",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_2, 1),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"MOD32 by 0, zero check 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+			BPF_MOV32_IMM(BPF_REG_2, 1),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"MOD64 by 0, zero check",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_2, 1),
+			BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"DIV32 by 0, zero check ok, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 2),
+			BPF_MOV32_IMM(BPF_REG_2, 16),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 8,
+	},
+	{
+		"DIV32 by 0, zero check 1, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV32 by 0, zero check 2, cls",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV64 by 0, zero check, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU64_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"MOD32 by 0, zero check ok, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_MOV32_IMM(BPF_REG_1, 3),
+			BPF_MOV32_IMM(BPF_REG_2, 5),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"MOD32 by 0, zero check 1, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"MOD32 by 0, zero check 2, cls",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"MOD64 by 0, zero check 1, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 2),
+			BPF_ALU64_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"MOD64 by 0, zero check 2, cls",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, 0),
+			BPF_MOV32_IMM(BPF_REG_0, -1),
+			BPF_ALU64_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = -1,
+	},
+	/* Just make sure that JITs used udiv/umod as otherwise we get
+	 * an exception from INT_MIN/-1 overflow similarly as with div
+	 * by zero.
+	 */
+	{
+		"DIV32 overflow, check 1",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, -1),
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV32 overflow, check 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_IMM(BPF_DIV, BPF_REG_0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV64 overflow, check 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, -1),
+			BPF_LD_IMM64(BPF_REG_0, LLONG_MIN),
+			BPF_ALU64_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"DIV64 overflow, check 2",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_0, LLONG_MIN),
+			BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"MOD32 overflow, check 1",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_1, -1),
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = INT_MIN,
+	},
+	{
+		"MOD32 overflow, check 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
+			BPF_ALU32_IMM(BPF_MOD, BPF_REG_0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = INT_MIN,
+	},
+	{
+		"MOD64 overflow, check 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_1, -1),
+			BPF_LD_IMM64(BPF_REG_2, LLONG_MIN),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
+			BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_3, BPF_REG_2, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"MOD64 overflow, check 2",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_2, LLONG_MIN),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_MOD, BPF_REG_2, -1),
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_3, BPF_REG_2, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"xor32 zero extend check",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_2, -1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 32),
+			BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 0xffff),
+			BPF_ALU32_REG(BPF_XOR, BPF_REG_2, BPF_REG_2),
+			BPF_MOV32_IMM(BPF_REG_0, 2),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"empty prog",
+		.insns = {
+		},
+		.errstr = "unknown opcode 00",
+		.result = REJECT,
+	},
+	{
+		"only exit insn",
+		.insns = {
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R0 !read_ok",
+		.result = REJECT,
 	},
 	{
 		"unreachable",
@@ -209,6 +535,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = 1,
 	},
 	{
 		"test8 ld_imm64",
@@ -280,7 +607,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_ARSH not supported for 32 bit ALU",
+		.errstr = "unknown opcode c4",
 	},
 	{
 		"arsh32 on reg",
@@ -291,7 +618,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_ARSH not supported for 32 bit ALU",
+		.errstr = "unknown opcode cc",
 	},
 	{
 		"arsh64 on imm",
@@ -317,7 +644,7 @@ static struct bpf_test tests[] = {
 		.insns = {
 			BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2),
 		},
-		.errstr = "jump out of range",
+		.errstr = "not an exit",
 		.result = REJECT,
 	},
 	{
@@ -407,7 +734,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(BPF_JMP | BPF_CALL | BPF_X, 0, 0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_CALL uses reserved",
+		.errstr = "unknown opcode 8d",
 		.result = REJECT,
 	},
 	{
@@ -516,6 +843,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
+		.retval = POINTER_VALUE,
 	},
 	{
 		"check valid spill/fill, skb mark",
@@ -596,7 +924,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(0, 0, 0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid BPF_LD_IMM",
+		.errstr = "unknown opcode 00",
 		.result = REJECT,
 	},
 	{
@@ -614,7 +942,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(-1, 0, 0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid BPF_ALU opcode f0",
+		.errstr = "unknown opcode ff",
 		.result = REJECT,
 	},
 	{
@@ -623,7 +951,7 @@ static struct bpf_test tests[] = {
 			BPF_RAW_INSN(-1, -1, -1, -1, -1),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid BPF_ALU opcode f0",
+		.errstr = "unknown opcode ff",
 		.result = REJECT,
 	},
 	{
@@ -802,6 +1130,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R1 pointer comparison",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
+		.retval = -ENOENT,
 	},
 	{
 		"jump test 4",
@@ -1822,6 +2151,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = 0xfaceb00c,
 	},
 	{
 		"PTR_TO_STACK store/load - bad alignment on off",
@@ -1880,6 +2210,7 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
 		.errstr_unpriv = "R0 leaks addr",
+		.retval = POINTER_VALUE,
 	},
 	{
 		"unpriv: add const to pointer",
@@ -2053,6 +2384,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 				     BPF_FUNC_get_hash_recalc),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
@@ -2840,6 +3172,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 1,
 	},
 	{
 		"direct packet access: test12 (and, good access)",
@@ -2864,6 +3197,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 1,
 	},
 	{
 		"direct packet access: test13 (branches, good access)",
@@ -2894,6 +3228,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 1,
 	},
 	{
 		"direct packet access: test14 (pkt_ptr += 0, CONST_IMM, good access)",
@@ -2917,6 +3252,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 1,
 	},
 	{
 		"direct packet access: test15 (spill with xadd)",
@@ -3203,6 +3539,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 1,
 	},
 	{
 		"direct packet access: test28 (marking on <=, bad access)",
@@ -5700,7 +6037,7 @@ static struct bpf_test tests[] = {
 		"helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_1, 0),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_2, 1),
 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
 			BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
@@ -5822,6 +6159,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 0 /* csum_diff of 64-byte packet */,
 	},
 	{
 		"helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
@@ -5935,7 +6273,7 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_2, 1),
 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
 			BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63),
@@ -6190,6 +6528,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
+		.retval = 42 /* ultimate return value */,
 	},
 	{
 		"ld_ind: check calling conv, r1",
@@ -6261,6 +6600,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = 1,
 	},
 	{
 		"check bpf_perf_event_data->sample_period byte load permitted",
@@ -7248,6 +7588,7 @@ static struct bpf_test tests[] = {
 		},
 		.fixup_map1 = { 3 },
 		.result = ACCEPT,
+		.retval = POINTER_VALUE,
 		.result_unpriv = REJECT,
 		.errstr_unpriv = "R0 leaks addr as return value"
 	},
@@ -7268,6 +7609,7 @@ static struct bpf_test tests[] = {
 		},
 		.fixup_map1 = { 3 },
 		.result = ACCEPT,
+		.retval = POINTER_VALUE,
 		.result_unpriv = REJECT,
 		.errstr_unpriv = "R0 leaks addr as return value"
 	},
@@ -7434,7 +7776,7 @@ static struct bpf_test tests[] = {
 			},
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_END uses reserved fields",
+		.errstr = "unknown opcode d7",
 		.result = REJECT,
 	},
 	{
@@ -7709,6 +8051,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = TEST_DATA_LEN,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
@@ -8656,6 +8999,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = 1,
 	},
 	{
 		"check deducing bounds from const, 3",
@@ -8826,6 +9170,1959 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
 	},
+	{
+		"calls: basic sanity",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.result = ACCEPT,
+	},
+	{
+		"calls: not on unpriviledged",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"calls: div by 0 in subprog",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(BPF_REG_2, 0),
+			BPF_MOV32_IMM(BPF_REG_3, 1),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_3, BPF_REG_2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"calls: multiple ret types in subprog 1",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_MOV32_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = REJECT,
+		.errstr = "R0 invalid mem access 'inv'",
+	},
+	{
+		"calls: multiple ret types in subprog 2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 9),
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+				    offsetof(struct __sk_buff, data)),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 64),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.fixup_map1 = { 16 },
+		.result = REJECT,
+		.errstr = "R0 min value is outside of the array range",
+	},
+	{
+		"calls: overlapping caller/callee",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "last insn is not an exit or jmp",
+		.result = REJECT,
+	},
+	{
+		"calls: wrong recursive calls",
+		.insns = {
+			BPF_JMP_IMM(BPF_JA, 0, 0, 4),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 4),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "jump out of range",
+		.result = REJECT,
+	},
+	{
+		"calls: wrong src reg",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 2, 0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "BPF_CALL uses reserved fields",
+		.result = REJECT,
+	},
+	{
+		"calls: wrong off value",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, -1, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "BPF_CALL uses reserved fields",
+		.result = REJECT,
+	},
+	{
+		"calls: jump back loop",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -1),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "back-edge from insn 0 to 0",
+		.result = REJECT,
+	},
+	{
+		"calls: conditional call",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "jump out of range",
+		.result = REJECT,
+	},
+	{
+		"calls: conditional call 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.result = ACCEPT,
+	},
+	{
+		"calls: conditional call 3",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 4),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -6),
+			BPF_MOV64_IMM(BPF_REG_0, 3),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -6),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "back-edge from insn",
+		.result = REJECT,
+	},
+	{
+		"calls: conditional call 4",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.result = ACCEPT,
+	},
+	{
+		"calls: conditional call 5",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -6),
+			BPF_MOV64_IMM(BPF_REG_0, 3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "back-edge from insn",
+		.result = REJECT,
+	},
+	{
+		"calls: conditional call 6",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -2),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "back-edge from insn",
+		.result = REJECT,
+	},
+	{
+		"calls: using r0 returned by callee",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.result = ACCEPT,
+	},
+	{
+		"calls: using uninit r0 from callee",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"calls: callee is using r1",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_ACT,
+		.result = ACCEPT,
+		.retval = TEST_DATA_LEN,
+	},
+	{
+		"calls: callee using args1",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "allowed for root only",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+		.retval = POINTER_VALUE,
+	},
+	{
+		"calls: callee using wrong args2",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "R2 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"calls: callee using two args",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, len)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_6,
+				    offsetof(struct __sk_buff, len)),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "allowed for root only",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+		.retval = TEST_DATA_LEN + TEST_DATA_LEN - ETH_HLEN - ETH_HLEN,
+	},
+	{
+		"calls: callee changing pkt pointers",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_6),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_8, BPF_REG_7, 2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			/* clear_all_pkt_pointers() has to walk all frames
+			 * to make sure that pkt pointers in the caller
+			 * are cleared when callee is calling a helper that
+			 * adjusts packet size
+			 */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_xdp_adjust_head),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "R6 invalid mem access 'inv'",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"calls: two calls with args",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = TEST_DATA_LEN + TEST_DATA_LEN,
+	},
+	{
+		"calls: calls with stack arith",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"calls: calls with misaligned stack access",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -63),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -61),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -63),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
+		.errstr = "misaligned stack access",
+		.result = REJECT,
+	},
+	{
+		"calls: calls control flow, jump test",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 43),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 43,
+	},
+	{
+		"calls: calls control flow, jump test 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 43),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "jump out of range from insn 1 to 4",
+		.result = REJECT,
+	},
+	{
+		"calls: two calls with bad jump",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "jump out of range from insn 11 to 9",
+		.result = REJECT,
+	},
+	{
+		"calls: recursive call. test1",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "back-edge",
+		.result = REJECT,
+	},
+	{
+		"calls: recursive call. test2",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "back-edge",
+		.result = REJECT,
+	},
+	{
+		"calls: unreachable code",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "unreachable insn 6",
+		.result = REJECT,
+	},
+	{
+		"calls: invalid call",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -4),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "invalid destination",
+		.result = REJECT,
+	},
+	{
+		"calls: invalid call 2",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 0x7fffffff),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "invalid destination",
+		.result = REJECT,
+	},
+	{
+		"calls: jumping across function bodies. test1",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "jump out of range",
+		.result = REJECT,
+	},
+	{
+		"calls: jumping across function bodies. test2",
+		.insns = {
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "jump out of range",
+		.result = REJECT,
+	},
+	{
+		"calls: call without exit",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -2),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "not an exit",
+		.result = REJECT,
+	},
+	{
+		"calls: call into middle of ld_imm64",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_LD_IMM64(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "last insn",
+		.result = REJECT,
+	},
+	{
+		"calls: call into middle of other call",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "last insn",
+		.result = REJECT,
+	},
+	{
+		"calls: ld_abs with changing ctx data in callee",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_skb_vlan_push),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "BPF_LD_[ABS|IND] instructions cannot be mixed",
+		.result = REJECT,
+	},
+	{
+		"calls: two calls with bad fallthrough",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+		.errstr = "not an exit",
+		.result = REJECT,
+	},
+	{
+		"calls: two calls with stack read",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.result = ACCEPT,
+	},
+	{
+		"calls: two calls with stack write",
+		.insns = {
+			/* main prog */
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 7),
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_8),
+			/* write into stack frame of main prog */
+			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			/* read from stack frame of main prog */
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.result = ACCEPT,
+	},
+	{
+		"calls: stack overflow using two frames (pre-call access)",
+		.insns = {
+			/* prog 1 */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* prog 2 */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.errstr = "combined stack size",
+		.result = REJECT,
+	},
+	{
+		"calls: stack overflow using two frames (post-call access)",
+		.insns = {
+			/* prog 1 */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2),
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+			BPF_EXIT_INSN(),
+
+			/* prog 2 */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.errstr = "combined stack size",
+		.result = REJECT,
+	},
+	{
+		"calls: stack depth check using three frames. test1",
+		.insns = {
+			/* main */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 4), /* call A */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 5), /* call B */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -32, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			/* A */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -256, 0),
+			BPF_EXIT_INSN(),
+			/* B */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, -3), /* call A */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -64, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		/* stack_main=32, stack_A=256, stack_B=64
+		 * and max(main+A, main+A+B) < 512
+		 */
+		.result = ACCEPT,
+	},
+	{
+		"calls: stack depth check using three frames. test2",
+		.insns = {
+			/* main */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 4), /* call A */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 5), /* call B */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -32, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			/* A */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -64, 0),
+			BPF_EXIT_INSN(),
+			/* B */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, -3), /* call A */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -256, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		/* stack_main=32, stack_A=64, stack_B=256
+		 * and max(main+A, main+A+B) < 512
+		 */
+		.result = ACCEPT,
+	},
+	{
+		"calls: stack depth check using three frames. test3",
+		.insns = {
+			/* main */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 6), /* call A */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 8), /* call B */
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_6, 0, 1),
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -64, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			/* A */
+			BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 10, 1),
+			BPF_EXIT_INSN(),
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -224, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -3),
+			/* B */
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 2, 1),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, -6), /* call A */
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -256, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		/* stack_main=64, stack_A=224, stack_B=256
+		 * and max(main+A, main+A+B) > 512
+		 */
+		.errstr = "combined stack",
+		.result = REJECT,
+	},
+	{
+		"calls: stack depth check using three frames. test4",
+		/* void main(void) {
+		 *   func1(0);
+		 *   func1(1);
+		 *   func2(1);
+		 * }
+		 * void func1(int alloc_or_recurse) {
+		 *   if (alloc_or_recurse) {
+		 *     frame_pointer[-300] = 1;
+		 *   } else {
+		 *     func2(alloc_or_recurse);
+		 *   }
+		 * }
+		 * void func2(int alloc_or_recurse) {
+		 *   if (alloc_or_recurse) {
+		 *     frame_pointer[-300] = 1;
+		 *   }
+		 * }
+		 */
+		.insns = {
+			/* main */
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 6), /* call A */
+			BPF_MOV64_IMM(BPF_REG_1, 1),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 4), /* call A */
+			BPF_MOV64_IMM(BPF_REG_1, 1),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 7), /* call B */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			/* A */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2),
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+			BPF_EXIT_INSN(),
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call B */
+			BPF_EXIT_INSN(),
+			/* B */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.result = REJECT,
+		.errstr = "combined stack",
+	},
+	{
+		"calls: stack depth check using three frames. test5",
+		.insns = {
+			/* main */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */
+			BPF_EXIT_INSN(),
+			/* A */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call B */
+			BPF_EXIT_INSN(),
+			/* B */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */
+			BPF_EXIT_INSN(),
+			/* C */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */
+			BPF_EXIT_INSN(),
+			/* D */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */
+			BPF_EXIT_INSN(),
+			/* E */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */
+			BPF_EXIT_INSN(),
+			/* F */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */
+			BPF_EXIT_INSN(),
+			/* G */
+			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */
+			BPF_EXIT_INSN(),
+			/* H */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.errstr = "call stack",
+		.result = REJECT,
+	},
+	{
+		"calls: spill into caller stack frame",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.errstr = "cannot spill",
+		.result = REJECT,
+	},
+	{
+		"calls: write into caller stack frame",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+			BPF_EXIT_INSN(),
+			BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"calls: write into callee stack frame",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, -8),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.errstr = "cannot return stack pointer",
+		.result = REJECT,
+	},
+	{
+		"calls: two calls with stack write and void return",
+		.insns = {
+			/* main prog */
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			/* write into stack frame of main prog */
+			BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0),
+			BPF_EXIT_INSN(), /* void return */
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.result = ACCEPT,
+	},
+	{
+		"calls: ambiguous return value",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "allowed for root only",
+		.result_unpriv = REJECT,
+		.errstr = "R0 !read_ok",
+		.result = REJECT,
+	},
+	{
+		"calls: two calls that return map_value",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			/* fetch secound map_value_ptr from the stack */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			/* call 3rd function twice */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* first time with fp-8 */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			/* second time with fp-16 */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			/* lookup from map */
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			/* write map_value_ptr into stack frame of main prog */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(), /* return 0 */
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.fixup_map1 = { 23 },
+		.result = ACCEPT,
+	},
+	{
+		"calls: two calls that return map_value with bool condition",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			/* call 3rd function twice */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* first time with fp-8 */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 9),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			/* second time with fp-16 */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+			/* fetch secound map_value_ptr from the stack */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			/* lookup from map */
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			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(), /* return 0 */
+			/* write map_value_ptr into stack frame of main prog */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(), /* return 1 */
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.fixup_map1 = { 23 },
+		.result = ACCEPT,
+	},
+	{
+		"calls: two calls that return map_value with incorrect bool check",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			/* call 3rd function twice */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* first time with fp-8 */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 9),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			/* second time with fp-16 */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			/* fetch secound map_value_ptr from the stack */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			/* lookup from map */
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			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(), /* return 0 */
+			/* write map_value_ptr into stack frame of main prog */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(), /* return 1 */
+		},
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.fixup_map1 = { 23 },
+		.result = REJECT,
+		.errstr = "invalid read from stack off -16+0 size 8",
+	},
+	{
+		"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test1",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* 1st lookup from map */
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			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_8, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			/* write map_value_ptr into stack frame of main prog at fp-8 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_8, 1),
+
+			/* 2nd lookup from map */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), /* 20 */
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, /* 24 */
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_9, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			/* write map_value_ptr into stack frame of main prog at fp-16 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_9, 1),
+
+			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), /* 30 */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),  /* 34 */
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			/* if arg2 == 1 do *arg1 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+
+			/* if arg4 == 1 do *arg3 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.fixup_map1 = { 12, 22 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+	},
+	{
+		"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test2",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* 1st lookup from map */
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			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_8, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			/* write map_value_ptr into stack frame of main prog at fp-8 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_8, 1),
+
+			/* 2nd lookup from map */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), /* 20 */
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, /* 24 */
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_9, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			/* write map_value_ptr into stack frame of main prog at fp-16 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_9, 1),
+
+			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), /* 30 */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),  /* 34 */
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			/* if arg2 == 1 do *arg1 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+
+			/* if arg4 == 1 do *arg3 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.fixup_map1 = { 12, 22 },
+		.result = ACCEPT,
+	},
+	{
+		"calls: two jumps that receive map_value via arg=ptr_stack_of_jumper. test3",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* 1st lookup from map */
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -24, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -24),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			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_8, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			/* write map_value_ptr into stack frame of main prog at fp-8 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_8, 1),
+
+			/* 2nd lookup from map */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -24),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			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_9, 0),  // 26
+			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+			/* write map_value_ptr into stack frame of main prog at fp-16 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_9, 1),
+
+			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), // 30
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), // 34
+			BPF_JMP_IMM(BPF_JA, 0, 0, -30),
+
+			/* subprog 2 */
+			/* if arg2 == 1 do *arg1 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+
+			/* if arg4 == 1 do *arg3 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, -8),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.fixup_map1 = { 12, 22 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+	},
+	{
+		"calls: two calls that receive map_value_ptr_or_null via arg. test1",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* 1st lookup from map */
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			/* write map_value_ptr_or_null into stack frame of main prog at fp-8 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_8, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_MOV64_IMM(BPF_REG_8, 1),
+
+			/* 2nd lookup from map */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			/* write map_value_ptr_or_null into stack frame of main prog at fp-16 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_9, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_MOV64_IMM(BPF_REG_9, 1),
+
+			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			/* if arg2 == 1 do *arg1 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+
+			/* if arg4 == 1 do *arg3 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.fixup_map1 = { 12, 22 },
+		.result = ACCEPT,
+	},
+	{
+		"calls: two calls that receive map_value_ptr_or_null via arg. test2",
+		.insns = {
+			/* main prog */
+			/* pass fp-16, fp-8 into a function */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+			/* 1st lookup from map */
+			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_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			/* write map_value_ptr_or_null into stack frame of main prog at fp-8 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_8, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_MOV64_IMM(BPF_REG_8, 1),
+
+			/* 2nd lookup from map */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			/* write map_value_ptr_or_null into stack frame of main prog at fp-16 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_9, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_MOV64_IMM(BPF_REG_9, 1),
+
+			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			/* if arg2 == 1 do *arg1 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+
+			/* if arg4 == 0 do *arg3 = 0 */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 0, 2),
+			/* fetch map_value_ptr from the stack of this function */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+			/* write into map value */
+			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.fixup_map1 = { 12, 22 },
+		.result = REJECT,
+		.errstr = "R0 invalid mem access 'inv'",
+	},
+	{
+		"calls: pkt_ptr spill into caller stack",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			/* spill unchecked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+			/* now the pkt range is verified, read pkt_ptr from stack */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = POINTER_VALUE,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			/* Marking is still kept, but not in all cases safe. */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			/* spill unchecked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+			/* now the pkt range is verified, read pkt_ptr from stack */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "invalid access to packet",
+		.result = REJECT,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 3",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			/* Marking is still kept and safe here. */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			/* spill unchecked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			/* now the pkt range is verified, read pkt_ptr from stack */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 4",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			/* Check marking propagated. */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			/* spill unchecked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			/* don't read back pkt_ptr from stack here */
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 5",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+			/* spill checked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			/* don't read back pkt_ptr from stack here */
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "same insn cannot be used with different",
+		.result = REJECT,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 6",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+			/* spill checked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			/* don't read back pkt_ptr from stack here */
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R4 invalid mem access",
+		.result = REJECT,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 7",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+			/* spill checked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			/* don't read back pkt_ptr from stack here */
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R4 invalid mem access",
+		.result = REJECT,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 8",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+			/* spill checked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			/* don't read back pkt_ptr from stack here */
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"calls: pkt_ptr spill into caller stack 9",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			/* spill unchecked pkt_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+			BPF_MOV64_IMM(BPF_REG_5, 1),
+			/* don't read back pkt_ptr from stack here */
+			/* write 4 bytes into packet */
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "invalid access to packet",
+		.result = REJECT,
+	},
+	{
+		"calls: caller stack init to zero or map_value_or_null",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			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, 1, 0, 4),
+			/* fetch map_value_or_null or const_zero from stack */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			/* store into map_value */
+			BPF_ST_MEM(BPF_W, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			/* if (ctx == 0) return; */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8),
+			/* else bpf_map_lookup() and *(fp - 8) = r0 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			/* write map_value_ptr_or_null into stack frame of main prog at fp-8 */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 13 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"calls: stack init to zero and pruning",
+		.insns = {
+			/* first make allocated_stack 16 byte */
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+			/* now fork the execution such that the false branch
+			 * of JGT insn will be verified second and it skisp zero
+			 * init of fp-8 stack slot. If stack liveness marking
+			 * is missing live_read marks from call map_lookup
+			 * processing then pruning will incorrectly assume
+			 * that fp-8 stack slot was unused in the fall-through
+			 * branch and will accept the program incorrectly
+			 */
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 2, 2),
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map2 = { 6 },
+		.errstr = "invalid indirect read from stack off -8+0 size 8",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"search pruning: all branches should be verified (nop operation)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0xbeef, 2),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_JMP_A(1),
+			BPF_MOV64_IMM(BPF_REG_4, 1),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -16),
+			BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_5, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_6, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xdead),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.errstr = "R6 invalid mem access 'inv'",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
+	{
+		"search pruning: all branches should be verified (invalid stack access)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0xbeef, 2),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -16),
+			BPF_JMP_A(1),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -24),
+			BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.errstr = "invalid read from stack off -16+0 size 8",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -8937,10 +11234,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	int fd_prog, expected_ret, reject_from_alignment;
 	struct bpf_insn *prog = test->insns;
 	int prog_len = probe_filter_length(prog);
+	char data_in[TEST_DATA_LEN] = {};
 	int prog_type = test->prog_type;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
-	int i;
+	uint32_t retval;
+	int i, err;
 
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		map_fds[i] = -1;
@@ -8983,6 +11282,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		}
 	}
 
+	if (fd_prog >= 0) {
+		err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in),
+					NULL, NULL, &retval, NULL);
+		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
+			printf("Unexpected bpf_prog_test_run error\n");
+			goto fail_log;
+		}
+		if (!err && retval != test->retval &&
+		    test->retval != POINTER_VALUE) {
+			printf("FAIL retval %d != %d\n", retval, test->retval);
+			goto fail_log;
+		}
+	}
 	(*passes)++;
 	printf("OK%s\n", reject_from_alignment ?
 	       " (NOTE: reject due to unknown alignment)" : "");
diff --git a/tools/testing/selftests/bpf/test_xdp_noinline.c b/tools/testing/selftests/bpf/test_xdp_noinline.c
new file mode 100644
index 000000000000..5e4aac74f9d0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_noinline.c
@@ -0,0 +1,833 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include "bpf_helpers.h"
+
+#define bpf_printk(fmt, ...)				\
+({							\
+	char ____fmt[] = fmt;				\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			##__VA_ARGS__);			\
+})
+
+static __u32 rol32(__u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> ((-shift) & 31));
+}
+
+/* copy paste of jhash from kernel sources to make sure llvm
+ * can compile it into valid sequence of bpf instructions
+ */
+#define __jhash_mix(a, b, c)			\
+{						\
+	a -= c;  a ^= rol32(c, 4);  c += b;	\
+	b -= a;  b ^= rol32(a, 6);  a += c;	\
+	c -= b;  c ^= rol32(b, 8);  b += a;	\
+	a -= c;  a ^= rol32(c, 16); c += b;	\
+	b -= a;  b ^= rol32(a, 19); a += c;	\
+	c -= b;  c ^= rol32(b, 4);  b += a;	\
+}
+
+#define __jhash_final(a, b, c)			\
+{						\
+	c ^= b; c -= rol32(b, 14);		\
+	a ^= c; a -= rol32(c, 11);		\
+	b ^= a; b -= rol32(a, 25);		\
+	c ^= b; c -= rol32(b, 16);		\
+	a ^= c; a -= rol32(c, 4);		\
+	b ^= a; b -= rol32(a, 14);		\
+	c ^= b; c -= rol32(b, 24);		\
+}
+
+#define JHASH_INITVAL		0xdeadbeef
+
+typedef unsigned int u32;
+
+static __attribute__ ((noinline))
+u32 jhash(const void *key, u32 length, u32 initval)
+{
+	u32 a, b, c;
+	const unsigned char *k = key;
+
+	a = b = c = JHASH_INITVAL + length + initval;
+
+	while (length > 12) {
+		a += *(u32 *)(k);
+		b += *(u32 *)(k + 4);
+		c += *(u32 *)(k + 8);
+		__jhash_mix(a, b, c);
+		length -= 12;
+		k += 12;
+	}
+	switch (length) {
+	case 12: c += (u32)k[11]<<24;
+	case 11: c += (u32)k[10]<<16;
+	case 10: c += (u32)k[9]<<8;
+	case 9:  c += k[8];
+	case 8:  b += (u32)k[7]<<24;
+	case 7:  b += (u32)k[6]<<16;
+	case 6:  b += (u32)k[5]<<8;
+	case 5:  b += k[4];
+	case 4:  a += (u32)k[3]<<24;
+	case 3:  a += (u32)k[2]<<16;
+	case 2:  a += (u32)k[1]<<8;
+	case 1:  a += k[0];
+		 __jhash_final(a, b, c);
+	case 0: /* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
+
+static __attribute__ ((noinline))
+u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+	a += initval;
+	b += initval;
+	c += initval;
+	__jhash_final(a, b, c);
+	return c;
+}
+
+static __attribute__ ((noinline))
+u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+struct flow_key {
+	union {
+		__be32 src;
+		__be32 srcv6[4];
+	};
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	union {
+		__u32 ports;
+		__u16 port16[2];
+	};
+	__u8 proto;
+};
+
+struct packet_description {
+	struct flow_key flow;
+	__u8 flags;
+};
+
+struct ctl_value {
+	union {
+		__u64 value;
+		__u32 ifindex;
+		__u8 mac[6];
+	};
+};
+
+struct vip_definition {
+	union {
+		__be32 vip;
+		__be32 vipv6[4];
+	};
+	__u16 port;
+	__u16 family;
+	__u8 proto;
+};
+
+struct vip_meta {
+	__u32 flags;
+	__u32 vip_num;
+};
+
+struct real_pos_lru {
+	__u32 pos;
+	__u64 atime;
+};
+
+struct real_definition {
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	__u8 flags;
+};
+
+struct lb_stats {
+	__u64 v2;
+	__u64 v1;
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip_definition),
+	.value_size = sizeof(struct vip_meta),
+	.max_entries = 512,
+	.map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = {
+	.type = BPF_MAP_TYPE_LRU_HASH,
+	.key_size = sizeof(struct flow_key),
+	.value_size = sizeof(struct real_pos_lru),
+	.max_entries = 300,
+	.map_flags = 1U << 1,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 12 * 655,
+	.map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) reals = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct real_definition),
+	.max_entries = 40,
+	.map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) stats = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct lb_stats),
+	.max_entries = 515,
+	.map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct ctl_value),
+	.max_entries = 16,
+	.map_flags = 0,
+};
+
+struct eth_hdr {
+	unsigned char eth_dest[6];
+	unsigned char eth_source[6];
+	unsigned short eth_proto;
+};
+
+static inline __u64 calc_offset(bool is_ipv6, bool is_icmp)
+{
+	__u64 off = sizeof(struct eth_hdr);
+	if (is_ipv6) {
+		off += sizeof(struct ipv6hdr);
+		if (is_icmp)
+			off += sizeof(struct icmp6hdr) + sizeof(struct ipv6hdr);
+	} else {
+		off += sizeof(struct iphdr);
+		if (is_icmp)
+			off += sizeof(struct icmphdr) + sizeof(struct iphdr);
+	}
+	return off;
+}
+
+static __attribute__ ((noinline))
+bool parse_udp(void *data, void *data_end,
+	       bool is_ipv6, struct packet_description *pckt)
+{
+
+	bool is_icmp = !((pckt->flags & (1 << 0)) == 0);
+	__u64 off = calc_offset(is_ipv6, is_icmp);
+	struct udphdr *udp;
+	udp = data + off;
+
+	if (udp + 1 > data_end)
+		return 0;
+	if (!is_icmp) {
+		pckt->flow.port16[0] = udp->source;
+		pckt->flow.port16[1] = udp->dest;
+	} else {
+		pckt->flow.port16[0] = udp->dest;
+		pckt->flow.port16[1] = udp->source;
+	}
+	return 1;
+}
+
+static __attribute__ ((noinline))
+bool parse_tcp(void *data, void *data_end,
+	       bool is_ipv6, struct packet_description *pckt)
+{
+
+	bool is_icmp = !((pckt->flags & (1 << 0)) == 0);
+	__u64 off = calc_offset(is_ipv6, is_icmp);
+	struct tcphdr *tcp;
+
+	tcp = data + off;
+	if (tcp + 1 > data_end)
+		return 0;
+	if (tcp->syn)
+		pckt->flags |= (1 << 1);
+	if (!is_icmp) {
+		pckt->flow.port16[0] = tcp->source;
+		pckt->flow.port16[1] = tcp->dest;
+	} else {
+		pckt->flow.port16[0] = tcp->dest;
+		pckt->flow.port16[1] = tcp->source;
+	}
+	return 1;
+}
+
+static __attribute__ ((noinline))
+bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval,
+	      struct packet_description *pckt,
+	      struct real_definition *dst, __u32 pkt_bytes)
+{
+	struct eth_hdr *new_eth;
+	struct eth_hdr *old_eth;
+	struct ipv6hdr *ip6h;
+	__u32 ip_suffix;
+	void *data_end;
+	void *data;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+		return 0;
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+	new_eth = data;
+	ip6h = data + sizeof(struct eth_hdr);
+	old_eth = data + sizeof(struct ipv6hdr);
+	if (new_eth + 1 > data_end ||
+	    old_eth + 1 > data_end || ip6h + 1 > data_end)
+		return 0;
+	memcpy(new_eth->eth_dest, cval->mac, 6);
+	memcpy(new_eth->eth_source, old_eth->eth_dest, 6);
+	new_eth->eth_proto = 56710;
+	ip6h->version = 6;
+	ip6h->priority = 0;
+	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+
+	ip6h->nexthdr = IPPROTO_IPV6;
+	ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0];
+	ip6h->payload_len =
+	    __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr));
+	ip6h->hop_limit = 4;
+
+	ip6h->saddr.in6_u.u6_addr32[0] = 1;
+	ip6h->saddr.in6_u.u6_addr32[1] = 2;
+	ip6h->saddr.in6_u.u6_addr32[2] = 3;
+	ip6h->saddr.in6_u.u6_addr32[3] = ip_suffix;
+	memcpy(ip6h->daddr.in6_u.u6_addr32, dst->dstv6, 16);
+	return 1;
+}
+
+static __attribute__ ((noinline))
+bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
+	      struct packet_description *pckt,
+	      struct real_definition *dst, __u32 pkt_bytes)
+{
+
+	__u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]);
+	struct eth_hdr *new_eth;
+	struct eth_hdr *old_eth;
+	__u16 *next_iph_u16;
+	struct iphdr *iph;
+	__u32 csum = 0;
+	void *data_end;
+	void *data;
+
+	ip_suffix <<= 15;
+	ip_suffix ^= pckt->flow.src;
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+		return 0;
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+	new_eth = data;
+	iph = data + sizeof(struct eth_hdr);
+	old_eth = data + sizeof(struct iphdr);
+	if (new_eth + 1 > data_end ||
+	    old_eth + 1 > data_end || iph + 1 > data_end)
+		return 0;
+	memcpy(new_eth->eth_dest, cval->mac, 6);
+	memcpy(new_eth->eth_source, old_eth->eth_dest, 6);
+	new_eth->eth_proto = 8;
+	iph->version = 4;
+	iph->ihl = 5;
+	iph->frag_off = 0;
+	iph->protocol = IPPROTO_IPIP;
+	iph->check = 0;
+	iph->tos = 1;
+	iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr));
+	/* don't update iph->daddr, since it will overwrite old eth_proto
+	 * and multiple iterations of bpf_prog_run() will fail
+	 */
+
+	iph->saddr = ((0xFFFF0000 & ip_suffix) | 4268) ^ dst->dst;
+	iph->ttl = 4;
+
+	next_iph_u16 = (__u16 *) iph;
+#pragma clang loop unroll(full)
+	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
+		csum += *next_iph_u16++;
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr)))
+		return 0;
+	return 1;
+}
+
+static __attribute__ ((noinline))
+bool decap_v6(struct xdp_md *xdp, void **data, void **data_end, bool inner_v4)
+{
+	struct eth_hdr *new_eth;
+	struct eth_hdr *old_eth;
+
+	old_eth = *data;
+	new_eth = *data + sizeof(struct ipv6hdr);
+	memcpy(new_eth->eth_source, old_eth->eth_source, 6);
+	memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
+	if (inner_v4)
+		new_eth->eth_proto = 8;
+	else
+		new_eth->eth_proto = 56710;
+	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct ipv6hdr)))
+		return 0;
+	*data = (void *)(long)xdp->data;
+	*data_end = (void *)(long)xdp->data_end;
+	return 1;
+}
+
+static __attribute__ ((noinline))
+bool decap_v4(struct xdp_md *xdp, void **data, void **data_end)
+{
+	struct eth_hdr *new_eth;
+	struct eth_hdr *old_eth;
+
+	old_eth = *data;
+	new_eth = *data + sizeof(struct iphdr);
+	memcpy(new_eth->eth_source, old_eth->eth_source, 6);
+	memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
+	new_eth->eth_proto = 8;
+	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr)))
+		return 0;
+	*data = (void *)(long)xdp->data;
+	*data_end = (void *)(long)xdp->data_end;
+	return 1;
+}
+
+static __attribute__ ((noinline))
+int swap_mac_and_send(void *data, void *data_end)
+{
+	unsigned char tmp_mac[6];
+	struct eth_hdr *eth;
+
+	eth = data;
+	memcpy(tmp_mac, eth->eth_source, 6);
+	memcpy(eth->eth_source, eth->eth_dest, 6);
+	memcpy(eth->eth_dest, tmp_mac, 6);
+	return XDP_TX;
+}
+
+static __attribute__ ((noinline))
+int send_icmp_reply(void *data, void *data_end)
+{
+	struct icmphdr *icmp_hdr;
+	__u16 *next_iph_u16;
+	__u32 tmp_addr = 0;
+	struct iphdr *iph;
+	__u32 csum1 = 0;
+	__u32 csum = 0;
+	__u64 off = 0;
+
+	if (data + sizeof(struct eth_hdr)
+	     + sizeof(struct iphdr) + sizeof(struct icmphdr) > data_end)
+		return XDP_DROP;
+	off += sizeof(struct eth_hdr);
+	iph = data + off;
+	off += sizeof(struct iphdr);
+	icmp_hdr = data + off;
+	icmp_hdr->type = 0;
+	icmp_hdr->checksum += 0x0007;
+	iph->ttl = 4;
+	tmp_addr = iph->daddr;
+	iph->daddr = iph->saddr;
+	iph->saddr = tmp_addr;
+	iph->check = 0;
+	next_iph_u16 = (__u16 *) iph;
+#pragma clang loop unroll(full)
+	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
+		csum += *next_iph_u16++;
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+	return swap_mac_and_send(data, data_end);
+}
+
+static __attribute__ ((noinline))
+int send_icmp6_reply(void *data, void *data_end)
+{
+	struct icmp6hdr *icmp_hdr;
+	struct ipv6hdr *ip6h;
+	__be32 tmp_addr[4];
+	__u64 off = 0;
+
+	if (data + sizeof(struct eth_hdr)
+	     + sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) > data_end)
+		return XDP_DROP;
+	off += sizeof(struct eth_hdr);
+	ip6h = data + off;
+	off += sizeof(struct ipv6hdr);
+	icmp_hdr = data + off;
+	icmp_hdr->icmp6_type = 129;
+	icmp_hdr->icmp6_cksum -= 0x0001;
+	ip6h->hop_limit = 4;
+	memcpy(tmp_addr, ip6h->saddr.in6_u.u6_addr32, 16);
+	memcpy(ip6h->saddr.in6_u.u6_addr32, ip6h->daddr.in6_u.u6_addr32, 16);
+	memcpy(ip6h->daddr.in6_u.u6_addr32, tmp_addr, 16);
+	return swap_mac_and_send(data, data_end);
+}
+
+static __attribute__ ((noinline))
+int parse_icmpv6(void *data, void *data_end, __u64 off,
+		 struct packet_description *pckt)
+{
+	struct icmp6hdr *icmp_hdr;
+	struct ipv6hdr *ip6h;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return XDP_DROP;
+	if (icmp_hdr->icmp6_type == 128)
+		return send_icmp6_reply(data, data_end);
+	if (icmp_hdr->icmp6_type != 3)
+		return XDP_PASS;
+	off += sizeof(struct icmp6hdr);
+	ip6h = data + off;
+	if (ip6h + 1 > data_end)
+		return XDP_DROP;
+	pckt->flow.proto = ip6h->nexthdr;
+	pckt->flags |= (1 << 0);
+	memcpy(pckt->flow.srcv6, ip6h->daddr.in6_u.u6_addr32, 16);
+	memcpy(pckt->flow.dstv6, ip6h->saddr.in6_u.u6_addr32, 16);
+	return -1;
+}
+
+static __attribute__ ((noinline))
+int parse_icmp(void *data, void *data_end, __u64 off,
+	       struct packet_description *pckt)
+{
+	struct icmphdr *icmp_hdr;
+	struct iphdr *iph;
+
+	icmp_hdr = data + off;
+	if (icmp_hdr + 1 > data_end)
+		return XDP_DROP;
+	if (icmp_hdr->type == 8)
+		return send_icmp_reply(data, data_end);
+	if ((icmp_hdr->type != 3) || (icmp_hdr->code != 4))
+		return XDP_PASS;
+	off += sizeof(struct icmphdr);
+	iph = data + off;
+	if (iph + 1 > data_end)
+		return XDP_DROP;
+	if (iph->ihl != 5)
+		return XDP_DROP;
+	pckt->flow.proto = iph->protocol;
+	pckt->flags |= (1 << 0);
+	pckt->flow.src = iph->daddr;
+	pckt->flow.dst = iph->saddr;
+	return -1;
+}
+
+static __attribute__ ((noinline))
+__u32 get_packet_hash(struct packet_description *pckt,
+		      bool hash_16bytes)
+{
+	if (hash_16bytes)
+		return jhash_2words(jhash(pckt->flow.srcv6, 16, 12),
+				    pckt->flow.ports, 24);
+	else
+		return jhash_2words(pckt->flow.src, pckt->flow.ports,
+				    24);
+}
+
+__attribute__ ((noinline))
+static bool get_packet_dst(struct real_definition **real,
+			   struct packet_description *pckt,
+			   struct vip_meta *vip_info,
+			   bool is_ipv6, void *lru_map)
+{
+	struct real_pos_lru new_dst_lru = { };
+	bool hash_16bytes = is_ipv6;
+	__u32 *real_pos, hash, key;
+	__u64 cur_time;
+
+	if (vip_info->flags & (1 << 2))
+		hash_16bytes = 1;
+	if (vip_info->flags & (1 << 3)) {
+		pckt->flow.port16[0] = pckt->flow.port16[1];
+		memset(pckt->flow.srcv6, 0, 16);
+	}
+	hash = get_packet_hash(pckt, hash_16bytes);
+	if (hash != 0x358459b7 /* jhash of ipv4 packet */  &&
+	    hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
+		return 0;
+	key = 2 * vip_info->vip_num + hash % 2;
+	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
+	if (!real_pos)
+		return 0;
+	key = *real_pos;
+	*real = bpf_map_lookup_elem(&reals, &key);
+	if (!(*real))
+		return 0;
+	if (!(vip_info->flags & (1 << 1))) {
+		__u32 conn_rate_key = 512 + 2;
+		struct lb_stats *conn_rate_stats =
+		    bpf_map_lookup_elem(&stats, &conn_rate_key);
+
+		if (!conn_rate_stats)
+			return 1;
+		cur_time = bpf_ktime_get_ns();
+		if ((cur_time - conn_rate_stats->v2) >> 32 > 0xffFFFF) {
+			conn_rate_stats->v1 = 1;
+			conn_rate_stats->v2 = cur_time;
+		} else {
+			conn_rate_stats->v1 += 1;
+			if (conn_rate_stats->v1 >= 1)
+				return 1;
+		}
+		if (pckt->flow.proto == IPPROTO_UDP)
+			new_dst_lru.atime = cur_time;
+		new_dst_lru.pos = key;
+		bpf_map_update_elem(lru_map, &pckt->flow, &new_dst_lru, 0);
+	}
+	return 1;
+}
+
+__attribute__ ((noinline))
+static void connection_table_lookup(struct real_definition **real,
+				    struct packet_description *pckt,
+				    void *lru_map)
+{
+
+	struct real_pos_lru *dst_lru;
+	__u64 cur_time;
+	__u32 key;
+
+	dst_lru = bpf_map_lookup_elem(lru_map, &pckt->flow);
+	if (!dst_lru)
+		return;
+	if (pckt->flow.proto == IPPROTO_UDP) {
+		cur_time = bpf_ktime_get_ns();
+		if (cur_time - dst_lru->atime > 300000)
+			return;
+		dst_lru->atime = cur_time;
+	}
+	key = dst_lru->pos;
+	*real = bpf_map_lookup_elem(&reals, &key);
+}
+
+/* don't believe your eyes!
+ * below function has 6 arguments whereas bpf and llvm allow maximum of 5
+ * but since it's _static_ llvm can optimize one argument away
+ */
+__attribute__ ((noinline))
+static int process_l3_headers_v6(struct packet_description *pckt,
+				 __u8 *protocol, __u64 off,
+				 __u16 *pkt_bytes, void *data,
+				 void *data_end)
+{
+	struct ipv6hdr *ip6h;
+	__u64 iph_len;
+	int action;
+
+	ip6h = data + off;
+	if (ip6h + 1 > data_end)
+		return XDP_DROP;
+	iph_len = sizeof(struct ipv6hdr);
+	*protocol = ip6h->nexthdr;
+	pckt->flow.proto = *protocol;
+	*pkt_bytes = __builtin_bswap16(ip6h->payload_len);
+	off += iph_len;
+	if (*protocol == 45) {
+		return XDP_DROP;
+	} else if (*protocol == 59) {
+		action = parse_icmpv6(data, data_end, off, pckt);
+		if (action >= 0)
+			return action;
+	} else {
+		memcpy(pckt->flow.srcv6, ip6h->saddr.in6_u.u6_addr32, 16);
+		memcpy(pckt->flow.dstv6, ip6h->daddr.in6_u.u6_addr32, 16);
+	}
+	return -1;
+}
+
+__attribute__ ((noinline))
+static int process_l3_headers_v4(struct packet_description *pckt,
+				 __u8 *protocol, __u64 off,
+				 __u16 *pkt_bytes, void *data,
+				 void *data_end)
+{
+	struct iphdr *iph;
+	__u64 iph_len;
+	int action;
+
+	iph = data + off;
+	if (iph + 1 > data_end)
+		return XDP_DROP;
+	if (iph->ihl != 5)
+		return XDP_DROP;
+	*protocol = iph->protocol;
+	pckt->flow.proto = *protocol;
+	*pkt_bytes = __builtin_bswap16(iph->tot_len);
+	off += 20;
+	if (iph->frag_off & 65343)
+		return XDP_DROP;
+	if (*protocol == IPPROTO_ICMP) {
+		action = parse_icmp(data, data_end, off, pckt);
+		if (action >= 0)
+			return action;
+	} else {
+		pckt->flow.src = iph->saddr;
+		pckt->flow.dst = iph->daddr;
+	}
+	return -1;
+}
+
+__attribute__ ((noinline))
+static int process_packet(void *data, __u64 off, void *data_end,
+			  bool is_ipv6, struct xdp_md *xdp)
+{
+
+	struct real_definition *dst = NULL;
+	struct packet_description pckt = { };
+	struct vip_definition vip = { };
+	struct lb_stats *data_stats;
+	struct eth_hdr *eth = data;
+	void *lru_map = &lru_cache;
+	struct vip_meta *vip_info;
+	__u32 lru_stats_key = 513;
+	__u32 mac_addr_pos = 0;
+	__u32 stats_key = 512;
+	struct ctl_value *cval;
+	__u16 pkt_bytes;
+	__u64 iph_len;
+	__u8 protocol;
+	__u32 vip_num;
+	int action;
+
+	if (is_ipv6)
+		action = process_l3_headers_v6(&pckt, &protocol, off,
+					       &pkt_bytes, data, data_end);
+	else
+		action = process_l3_headers_v4(&pckt, &protocol, off,
+					       &pkt_bytes, data, data_end);
+	if (action >= 0)
+		return action;
+	protocol = pckt.flow.proto;
+	if (protocol == IPPROTO_TCP) {
+		if (!parse_tcp(data, data_end, is_ipv6, &pckt))
+			return XDP_DROP;
+	} else if (protocol == IPPROTO_UDP) {
+		if (!parse_udp(data, data_end, is_ipv6, &pckt))
+			return XDP_DROP;
+	} else {
+		return XDP_TX;
+	}
+
+	if (is_ipv6)
+		memcpy(vip.vipv6, pckt.flow.dstv6, 16);
+	else
+		vip.vip = pckt.flow.dst;
+	vip.port = pckt.flow.port16[1];
+	vip.proto = pckt.flow.proto;
+	vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+	if (!vip_info) {
+		vip.port = 0;
+		vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+		if (!vip_info)
+			return XDP_PASS;
+		if (!(vip_info->flags & (1 << 4)))
+			pckt.flow.port16[1] = 0;
+	}
+	if (data_end - data > 1400)
+		return XDP_DROP;
+	data_stats = bpf_map_lookup_elem(&stats, &stats_key);
+	if (!data_stats)
+		return XDP_DROP;
+	data_stats->v1 += 1;
+	if (!dst) {
+		if (vip_info->flags & (1 << 0))
+			pckt.flow.port16[0] = 0;
+		if (!(pckt.flags & (1 << 1)) && !(vip_info->flags & (1 << 1)))
+			connection_table_lookup(&dst, &pckt, lru_map);
+		if (dst)
+			goto out;
+		if (pckt.flow.proto == IPPROTO_TCP) {
+			struct lb_stats *lru_stats =
+			    bpf_map_lookup_elem(&stats, &lru_stats_key);
+
+			if (!lru_stats)
+				return XDP_DROP;
+			if (pckt.flags & (1 << 1))
+				lru_stats->v1 += 1;
+			else
+				lru_stats->v2 += 1;
+		}
+		if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6, lru_map))
+			return XDP_DROP;
+		data_stats->v2 += 1;
+	}
+out:
+	cval = bpf_map_lookup_elem(&ctl_array, &mac_addr_pos);
+	if (!cval)
+		return XDP_DROP;
+	if (dst->flags & (1 << 0)) {
+		if (!encap_v6(xdp, cval, &pckt, dst, pkt_bytes))
+			return XDP_DROP;
+	} else {
+		if (!encap_v4(xdp, cval, &pckt, dst, pkt_bytes))
+			return XDP_DROP;
+	}
+	vip_num = vip_info->vip_num;
+	data_stats = bpf_map_lookup_elem(&stats, &vip_num);
+	if (!data_stats)
+		return XDP_DROP;
+	data_stats->v1 += 1;
+	data_stats->v2 += pkt_bytes;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+	if (data + 4 > data_end)
+		return XDP_DROP;
+	*(u32 *)data = dst->dst;
+	return XDP_DROP;
+}
+
+__attribute__ ((section("xdp-test"), used))
+int balancer_ingress(struct xdp_md *ctx)
+{
+	void *data = (void *)(long)ctx->data;
+	void *data_end = (void *)(long)ctx->data_end;
+	struct eth_hdr *eth = data;
+	__u32 eth_proto;
+	__u32 nh_off;
+
+	nh_off = sizeof(struct eth_hdr);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+	eth_proto = eth->eth_proto;
+	if (eth_proto == 8)
+		return process_packet(data, nh_off, data_end, 0, ctx);
+	else if (eth_proto == 56710)
+		return process_packet(data, nh_off, data_end, 1, ctx);
+	else
+		return XDP_DROP;
+}
+
+char _license[] __attribute__ ((section("license"), used)) = "GPL";
+int _version __attribute__ ((section("version"), used)) = 1;