Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2018-01-26

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) A number of extensions to tcp-bpf, from Lawrence.
    - direct R or R/W access to many tcp_sock fields via bpf_sock_ops
    - passing up to 3 arguments to bpf_sock_ops functions
    - tcp_sock field bpf_sock_ops_cb_flags for controlling callbacks
    - optionally calling bpf_sock_ops program when RTO fires
    - optionally calling bpf_sock_ops program when packet is retransmitted
    - optionally calling bpf_sock_ops program when TCP state changes
    - access to tclass and sk_txhash
    - new selftest

2) div/mod exception handling, from Daniel.
    One of the ugly leftovers from the early eBPF days is that div/mod
    operations based on registers have a hard-coded src_reg == 0 test
    in the interpreter as well as in JIT code generators that would
    return from the BPF program with exit code 0. This was basically
    adopted from cBPF interpreter for historical reasons.
    There are multiple reasons why this is very suboptimal and prone
    to bugs. To name one: the return code mapping for such abnormal
    program exit of 0 does not always match with a suitable program
    type's exit code mapping. For example, '0' in tc means action 'ok'
    where the packet gets passed further up the stack, which is just
    undesirable for such cases (e.g. when implementing policy) and
    also does not match with other program types.
    After considering _four_ different ways to address the problem,
    we adapt the same behavior as on some major archs like ARMv8:
    X div 0 results in 0, and X mod 0 results in X. aarch64 and
    aarch32 ISA do not generate any traps or otherwise aborts
    of program execution for unsigned divides.
    Given the options, it seems the most suitable from
    all of them, also since major archs have similar schemes in
    place. Given this is all in the realm of undefined behavior,
    we still have the option to adapt if deemed necessary.

3) sockmap sample refactoring, from John.

4) lpm map get_next_key fixes, from Yonghong.

5) test cleanups, from Alexei and Prashant.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

13 files changed, 950 insertions, 38 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index af1f49ad8b88..db6bdc375126 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -17,7 +17,7 @@
 #define BPF_ALU64	0x07	/* alu mode in double word width */
 
 /* ld/ldx fields */
-#define BPF_DW		0x18	/* double word */
+#define BPF_DW		0x18	/* double word (64-bit) */
 #define BPF_XADD	0xc0	/* exclusive add */
 
 /* alu/jmp fields */
@@ -642,6 +642,14 @@ union bpf_attr {
  *     @optlen: length of optval in bytes
  *     Return: 0 or negative error
  *
+ * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags)
+ *     Set callback flags for sock_ops
+ *     @bpf_sock_ops: pointer to bpf_sock_ops_kern struct
+ *     @flags: flags value
+ *     Return: 0 for no error
+ *             -EINVAL if there is no full tcp socket
+ *             bits in flags that are not supported by current kernel
+ *
  * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
  *     Grow or shrink room in sk_buff.
  *     @skb: pointer to skb
@@ -748,7 +756,8 @@ union bpf_attr {
 	FN(perf_event_read_value),	\
 	FN(perf_prog_read_value),	\
 	FN(getsockopt),			\
-	FN(override_return),
+	FN(override_return),		\
+	FN(sock_ops_cb_flags_set),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -952,8 +961,9 @@ struct bpf_map_info {
 struct bpf_sock_ops {
 	__u32 op;
 	union {
-		__u32 reply;
-		__u32 replylong[4];
+		__u32 args[4];		/* Optionally passed to bpf program */
+		__u32 reply;		/* Returned by bpf program	    */
+		__u32 replylong[4];	/* Optionally returned by bpf prog  */
 	};
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
@@ -968,8 +978,39 @@ struct bpf_sock_ops {
 				 */
 	__u32 snd_cwnd;
 	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
+	__u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
+	__u32 state;
+	__u32 rtt_min;
+	__u32 snd_ssthresh;
+	__u32 rcv_nxt;
+	__u32 snd_nxt;
+	__u32 snd_una;
+	__u32 mss_cache;
+	__u32 ecn_flags;
+	__u32 rate_delivered;
+	__u32 rate_interval_us;
+	__u32 packets_out;
+	__u32 retrans_out;
+	__u32 total_retrans;
+	__u32 segs_in;
+	__u32 data_segs_in;
+	__u32 segs_out;
+	__u32 data_segs_out;
+	__u32 lost_out;
+	__u32 sacked_out;
+	__u32 sk_txhash;
+	__u64 bytes_received;
+	__u64 bytes_acked;
 };
 
+/* Definitions for bpf_sock_ops_cb_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x7		/* Mask of all currently
+							 * supported cb flags
+							 */
+
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
@@ -1003,6 +1044,43 @@ enum {
 					 * a congestion threshold. RTTs above
 					 * this indicate congestion
 					 */
+	BPF_SOCK_OPS_RTO_CB,		/* Called when an RTO has triggered.
+					 * Arg1: value of icsk_retransmits
+					 * Arg2: value of icsk_rto
+					 * Arg3: whether RTO has expired
+					 */
+	BPF_SOCK_OPS_RETRANS_CB,	/* Called when skb is retransmitted.
+					 * Arg1: sequence number of 1st byte
+					 * Arg2: # segments
+					 * Arg3: return value of
+					 *       tcp_transmit_skb (0 => success)
+					 */
+	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
+					 * Arg1: old_state
+					 * Arg2: new_state
+					 */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+	BPF_TCP_ESTABLISHED = 1,
+	BPF_TCP_SYN_SENT,
+	BPF_TCP_SYN_RECV,
+	BPF_TCP_FIN_WAIT1,
+	BPF_TCP_FIN_WAIT2,
+	BPF_TCP_TIME_WAIT,
+	BPF_TCP_CLOSE,
+	BPF_TCP_CLOSE_WAIT,
+	BPF_TCP_LAST_ACK,
+	BPF_TCP_LISTEN,
+	BPF_TCP_CLOSING,	/* Now a valid state */
+	BPF_TCP_NEW_SYN_RECV,
+
+	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 3a44b655d852..bf05bc5e36e5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -11,16 +11,16 @@ 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 sample_ret0.o test_tracepoint.o \
 	test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
-	sample_map_ret0.o
+	sample_map_ret0.o test_tcpbpf_kern.o
 
 TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
 	test_offload.py
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 33cb00e46c49..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,
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 e19b410125eb..ff8bd7e3e50c 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -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_w=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))"},
 		}
 	},
 	{
diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c
index c1535b34f14f..3489cc283433 100644
--- a/tools/testing/selftests/bpf/test_dev_cgroup.c
+++ b/tools/testing/selftests/bpf/test_dev_cgroup.c
@@ -21,7 +21,7 @@
 
 #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)
 {
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index 081510853c6d..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>
@@ -641,6 +642,98 @@ static void test_lpm_get_next_key(void)
 	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 };
@@ -667,6 +760,8 @@ int main(void)
 
 	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_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_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index fb82d29ee863..697bd83de295 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -21,6 +21,7 @@
 #include <stddef.h>
 #include <stdbool.h>
 #include <sched.h>
+#include <limits.h>
 
 #include <sys/capability.h>
 #include <sys/resource.h>
@@ -111,7 +112,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"DIV32 by 0, zero check 2",
@@ -123,7 +124,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"DIV64 by 0, zero check",
@@ -135,7 +136,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"MOD32 by 0, zero check 1",
@@ -147,7 +148,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"MOD32 by 0, zero check 2",
@@ -159,7 +160,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
-		.retval = 0,
+		.retval = 42,
 	},
 	{
 		"MOD64 by 0, zero check",
@@ -171,13 +172,245 @@ static struct bpf_test tests[] = {
 			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 = "last insn is not an exit or jmp",
+		.errstr = "unknown opcode 00",
 		.result = REJECT,
 	},
 	{
@@ -374,7 +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",
@@ -385,7 +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",
@@ -501,7 +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,
 	},
 	{
@@ -691,7 +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,
 	},
 	{
@@ -709,7 +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,
 	},
 	{
@@ -718,7 +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,
 	},
 	{
@@ -7543,7 +7776,7 @@ static struct bpf_test tests[] = {
 			},
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_END uses reserved fields",
+		.errstr = "unknown opcode d7",
 		.result = REJECT,
 	},
 	{
@@ -8766,6 +8999,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.retval = 1,
 	},
 	{
 		"check deducing bounds from const, 3",
@@ -8963,6 +9197,90 @@ static struct bpf_test tests[] = {
 		.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),