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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2018-10-08

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

The main changes are:

1) sk_lookup_[tcp|udp] and sk_release helpers from Joe Stringer which allow
BPF programs to perform lookups for sockets in a network namespace. This would
allow programs to determine early on in processing whether the stack is
expecting to receive the packet, and perform some action (eg drop,
forward somewhere) based on this information.

2) per-cpu cgroup local storage from Roman Gushchin.
Per-cpu cgroup local storage is very similar to simple cgroup storage
except all the data is per-cpu. The main goal of per-cpu variant is to
implement super fast counters (e.g. packet counters), which don't require
neither lookups, neither atomic operations in a fast path.
The example of these hybrid counters is in selftests/bpf/netcnt_prog.c

3) allow HW offload of programs with BPF-to-BPF function calls from Quentin Monnet

4) support more than 64-byte key/value in HW offloaded BPF maps from Jakub Kicinski

5) rename of libbpf interfaces from Andrey Ignatov.
libbpf is maturing as a library and should follow good practices in
library design and implementation to play well with other libraries.
This patch set brings consistent naming convention to global symbols.

6) relicense libbpf as LGPL-2.1 OR BSD-2-Clause from Alexei Starovoitov
to let Apache2 projects use libbpf

7) various AF_XDP fixes from Björn and Magnus
====================

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

29 files changed, 2059 insertions, 309 deletions

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e22fbe8b975f..6003e9598973 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -72,13 +72,15 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
 	[BPF_MAP_TYPE_CGROUP_STORAGE]	= "cgroup_storage",
 	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
+	[BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE]	= "percpu_cgroup_storage",
 };
 
 static bool map_is_per_cpu(__u32 type)
 {
 	return type == BPF_MAP_TYPE_PERCPU_HASH ||
 	       type == BPF_MAP_TYPE_PERCPU_ARRAY ||
-	       type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+	       type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+	       type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE;
 }
 
 static bool map_is_map_of_maps(__u32 type)
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index ed205ee57655..d441bb7035ca 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -69,7 +69,9 @@ static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	snprintf(netinfo->devices[netinfo->used_len].devname,
 		 sizeof(netinfo->devices[netinfo->used_len].devname),
 		 "%s",
-		 tb[IFLA_IFNAME] ? nla_getattr_str(tb[IFLA_IFNAME]) : "");
+		 tb[IFLA_IFNAME]
+			 ? libbpf_nla_getattr_str(tb[IFLA_IFNAME])
+			 : "");
 	netinfo->used_len++;
 
 	return do_xdp_dump(ifinfo, tb);
@@ -83,7 +85,7 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	if (tcinfo->is_qdisc) {
 		/* skip clsact qdisc */
 		if (tb[TCA_KIND] &&
-		    strcmp(nla_data(tb[TCA_KIND]), "clsact") == 0)
+		    strcmp(libbpf_nla_data(tb[TCA_KIND]), "clsact") == 0)
 			return 0;
 		if (info->tcm_handle == 0)
 			return 0;
@@ -101,7 +103,9 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
 		 sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
 		 "%s",
-		 tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
+		 tb[TCA_KIND]
+			 ? libbpf_nla_getattr_str(tb[TCA_KIND])
+			 : "unknown");
 	tcinfo->used_len++;
 
 	return 0;
@@ -127,14 +131,14 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	tcinfo.array_len = 0;
 
 	tcinfo.is_qdisc = false;
-	ret = nl_get_class(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
-			   &tcinfo);
+	ret = libbpf_nl_get_class(sock, nl_pid, dev->ifindex,
+				  dump_class_qdisc_nlmsg, &tcinfo);
 	if (ret)
 		goto out;
 
 	tcinfo.is_qdisc = true;
-	ret = nl_get_qdisc(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
-			   &tcinfo);
+	ret = libbpf_nl_get_qdisc(sock, nl_pid, dev->ifindex,
+				  dump_class_qdisc_nlmsg, &tcinfo);
 	if (ret)
 		goto out;
 
@@ -142,10 +146,9 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	filter_info.ifindex = dev->ifindex;
 	for (i = 0; i < tcinfo.used_len; i++) {
 		filter_info.kind = tcinfo.handle_array[i].kind;
-		ret = nl_get_filter(sock, nl_pid, dev->ifindex,
-				    tcinfo.handle_array[i].handle,
-				    dump_filter_nlmsg,
-				    &filter_info);
+		ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex,
+					   tcinfo.handle_array[i].handle,
+					   dump_filter_nlmsg, &filter_info);
 		if (ret)
 			goto out;
 	}
@@ -153,22 +156,22 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	/* root, ingress and egress handle */
 	handle = TC_H_ROOT;
 	filter_info.kind = "root";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
 	filter_info.kind = "clsact/ingress";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
 	filter_info.kind = "clsact/egress";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
@@ -196,7 +199,7 @@ static int do_show(int argc, char **argv)
 		usage();
 	}
 
-	sock = bpf_netlink_open(&nl_pid);
+	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0) {
 		fprintf(stderr, "failed to open netlink sock\n");
 		return -1;
@@ -211,7 +214,7 @@ static int do_show(int argc, char **argv)
 		jsonw_start_array(json_wtr);
 	NET_START_OBJECT;
 	NET_START_ARRAY("xdp", "%s:\n");
-	ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
+	ret = libbpf_nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
 	NET_END_ARRAY("\n");
 
 	if (!ret) {
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index 6f5e9cc6836c..4e9f4531269f 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -21,7 +21,7 @@ static void xdp_dump_prog_id(struct nlattr **tb, int attr,
 	if (new_json_object)
 		NET_START_OBJECT
 	NET_DUMP_STR("mode", " %s", mode);
-	NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[attr]))
+	NET_DUMP_UINT("id", " id %u", libbpf_nla_getattr_u32(tb[attr]))
 	if (new_json_object)
 		NET_END_OBJECT
 }
@@ -32,13 +32,13 @@ static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
 	struct nlattr *tb[IFLA_XDP_MAX + 1];
 	unsigned char mode;
 
-	if (nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
 		return -1;
 
 	if (!tb[IFLA_XDP_ATTACHED])
 		return 0;
 
-	mode = nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
+	mode = libbpf_nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
 	if (mode == XDP_ATTACHED_NONE)
 		return 0;
 
@@ -75,14 +75,14 @@ int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
 		return 0;
 
 	return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index,
-			       nla_getattr_str(tb[IFLA_IFNAME]));
+			       libbpf_nla_getattr_str(tb[IFLA_IFNAME]));
 }
 
 static int do_bpf_dump_one_act(struct nlattr *attr)
 {
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
 
-	if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (!tb[TCA_ACT_BPF_PARMS])
@@ -91,10 +91,10 @@ static int do_bpf_dump_one_act(struct nlattr *attr)
 	NET_START_OBJECT_NESTED2;
 	if (tb[TCA_ACT_BPF_NAME])
 		NET_DUMP_STR("name", "%s",
-			     nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+			     libbpf_nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
 	if (tb[TCA_ACT_BPF_ID])
 		NET_DUMP_UINT("id", " id %u",
-			      nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
+			      libbpf_nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
 	NET_END_OBJECT_NESTED;
 	return 0;
 }
@@ -106,10 +106,11 @@ static int do_dump_one_act(struct nlattr *attr)
 	if (!attr)
 		return 0;
 
-	if (nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
-	if (tb[TCA_ACT_KIND] && strcmp(nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
+	if (tb[TCA_ACT_KIND] &&
+	    strcmp(libbpf_nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
 		return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]);
 
 	return 0;
@@ -120,7 +121,7 @@ static int do_bpf_act_dump(struct nlattr *attr)
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	int act, ret;
 
-	if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	NET_START_ARRAY("act", " %s [");
@@ -139,13 +140,15 @@ static int do_bpf_filter_dump(struct nlattr *attr)
 	struct nlattr *tb[TCA_BPF_MAX + 1];
 	int ret;
 
-	if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (tb[TCA_BPF_NAME])
-		NET_DUMP_STR("name", " %s", nla_getattr_str(tb[TCA_BPF_NAME]));
+		NET_DUMP_STR("name", " %s",
+			     libbpf_nla_getattr_str(tb[TCA_BPF_NAME]));
 	if (tb[TCA_BPF_ID])
-		NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[TCA_BPF_ID]));
+		NET_DUMP_UINT("id", " id %u",
+			      libbpf_nla_getattr_u32(tb[TCA_BPF_ID]));
 	if (tb[TCA_BPF_ACT]) {
 		ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
 		if (ret)
@@ -160,7 +163,8 @@ int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind,
 {
 	int ret = 0;
 
-	if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
+	if (tb[TCA_OPTIONS] &&
+	    strcmp(libbpf_nla_data(tb[TCA_KIND]), "bpf") == 0) {
 		NET_START_OBJECT;
 		if (devname[0] != '\0')
 			NET_DUMP_STR("devname", "%s", devname);
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index 0788cfbbed0e..e3516b586a34 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -16,7 +16,7 @@
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_object(json_wtr);		\
 	} else {					\
-		fprintf(stderr, "%s {", name);		\
+		fprintf(stdout, "%s {", name);		\
 	}						\
 }
 
@@ -25,7 +25,7 @@
 	if (json_output)				\
 		jsonw_start_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "{");			\
+		fprintf(stdout, "{");			\
 }
 
 #define NET_END_OBJECT_NESTED				\
@@ -33,7 +33,7 @@
 	if (json_output)				\
 		jsonw_end_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "}");			\
+		fprintf(stdout, "}");			\
 }
 
 #define NET_END_OBJECT					\
@@ -47,7 +47,7 @@
 	if (json_output)				\
 		jsonw_end_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "\n");			\
+		fprintf(stdout, "\n");			\
 }
 
 #define NET_START_ARRAY(name, fmt_str)			\
@@ -56,7 +56,7 @@
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_array(json_wtr);		\
 	} else {					\
-		fprintf(stderr, fmt_str, name);		\
+		fprintf(stdout, fmt_str, name);		\
 	}						\
 }
 
@@ -65,7 +65,7 @@
 	if (json_output)				\
 		jsonw_end_array(json_wtr);		\
 	else						\
-		fprintf(stderr, "%s", endstr);		\
+		fprintf(stdout, "%s", endstr);		\
 }
 
 #define NET_DUMP_UINT(name, fmt_str, val)		\
@@ -73,7 +73,7 @@
 	if (json_output)				\
 		jsonw_uint_field(json_wtr, name, val);	\
 	else						\
-		fprintf(stderr, fmt_str, val);		\
+		fprintf(stdout, fmt_str, val);		\
 }
 
 #define NET_DUMP_STR(name, fmt_str, str)		\
@@ -81,7 +81,7 @@
 	if (json_output)				\
 		jsonw_string_field(json_wtr, name, str);\
 	else						\
-		fprintf(stderr, fmt_str, str);		\
+		fprintf(stdout, fmt_str, str);		\
 }
 
 #define NET_DUMP_STR_ONLY(str)				\
@@ -89,7 +89,7 @@
 	if (json_output)				\
 		jsonw_string(json_wtr, str);		\
 	else						\
-		fprintf(stderr, "%s ", str);		\
+		fprintf(stdout, "%s ", str);		\
 }
 
 #endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index aa5ccd2385ed..f9187b41dff6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -127,6 +127,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_SOCKHASH,
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
 };
 
 enum bpf_prog_type {
@@ -2143,6 +2144,77 @@ union bpf_attr {
  *		request in the skb.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for UDP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * int bpf_sk_release(struct bpf_sock *sk)
+ *	Description
+ *		Release the reference held by *sock*. *sock* must be a non-NULL
+ *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2228,7 +2300,10 @@ union bpf_attr {
 	FN(get_current_cgroup_id),	\
 	FN(get_local_storage),		\
 	FN(sk_select_reuseport),	\
-	FN(skb_ancestor_cgroup_id),
+	FN(skb_ancestor_cgroup_id),	\
+	FN(sk_lookup_tcp),		\
+	FN(sk_lookup_udp),		\
+	FN(sk_release),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2398,6 +2473,23 @@ struct bpf_sock {
 				 */
 };
 
+struct bpf_sock_tuple {
+	union {
+		struct {
+			__be32 saddr;
+			__be32 daddr;
+			__be16 sport;
+			__be16 dport;
+		} ipv4;
+		struct {
+			__be32 saddr[4];
+			__be32 daddr[4];
+			__be16 sport;
+			__be16 dport;
+		} ipv6;
+	};
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index d49902e818b5..6ad27257fd67 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 # Most of this file is copied from tools/lib/traceevent/Makefile
 
 BPF_VERSION = 0
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3878a26a2071..d70a255cb05e 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * common eBPF ELF operations.
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 6f38164b2618..87520a87a75f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * common eBPF ELF operations.
@@ -20,8 +20,8 @@
  * You should have received a copy of the GNU Lesser General Public
  * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
-#ifndef __BPF_BPF_H
-#define __BPF_BPF_H
+#ifndef __LIBBPF_BPF_H
+#define __LIBBPF_BPF_H
 
 #include <linux/bpf.h>
 #include <stdbool.h>
@@ -111,4 +111,4 @@ int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
 int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
 		      __u64 *probe_addr);
-#endif
+#endif /* __LIBBPF_BPF_H */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index cf94b0770522..449591aa9900 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4897e0724d4e..6db5462bb2ef 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,8 +1,8 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (c) 2018 Facebook */
 
-#ifndef __BPF_BTF_H
-#define __BPF_BTF_H
+#ifndef __LIBBPF_BTF_H
+#define __LIBBPF_BTF_H
 
 #include <linux/types.h>
 
@@ -23,4 +23,4 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
 const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 
-#endif
+#endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4f8d43ae20d2..ceb918c14d80 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * Common eBPF ELF object loading operations.
@@ -7,19 +7,6 @@
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
  * Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #define _GNU_SOURCE
@@ -228,7 +215,7 @@ struct bpf_object {
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
 
-static void bpf_program__unload(struct bpf_program *prog)
+void bpf_program__unload(struct bpf_program *prog)
 {
 	int i;
 
@@ -470,7 +457,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		obj->efile.fd = open(obj->path, O_RDONLY);
 		if (obj->efile.fd < 0) {
 			char errmsg[STRERR_BUFSIZE];
-			char *cp = str_error(errno, errmsg, sizeof(errmsg));
+			char *cp = libbpf_strerror_r(errno, errmsg,
+						     sizeof(errmsg));
 
 			pr_warning("failed to open %s: %s\n", obj->path, cp);
 			return -errno;
@@ -811,7 +799,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 						      data->d_size, name, idx);
 			if (err) {
 				char errmsg[STRERR_BUFSIZE];
-				char *cp = str_error(-err, errmsg, sizeof(errmsg));
+				char *cp = libbpf_strerror_r(-err, errmsg,
+							     sizeof(errmsg));
 
 				pr_warning("failed to alloc program %s (%s): %s",
 					   name, obj->path, cp);
@@ -1140,7 +1129,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 
 		*pfd = bpf_create_map_xattr(&create_attr);
 		if (*pfd < 0 && create_attr.btf_key_type_id) {
-			cp = str_error(errno, errmsg, sizeof(errmsg));
+			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
 				   map->name, cp, errno);
 			create_attr.btf_fd = 0;
@@ -1155,7 +1144,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			size_t j;
 
 			err = *pfd;
-			cp = str_error(errno, errmsg, sizeof(errmsg));
+			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("failed to create map (name: '%s'): %s\n",
 				   map->name, cp);
 			for (j = 0; j < i; j++)
@@ -1339,7 +1328,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	}
 
 	ret = -LIBBPF_ERRNO__LOAD;
-	cp = str_error(errno, errmsg, sizeof(errmsg));
+	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 	pr_warning("load bpf program failed: %s\n", cp);
 
 	if (log_buf && log_buf[0] != '\0') {
@@ -1375,9 +1364,9 @@ out:
 	return ret;
 }
 
-static int
+int
 bpf_program__load(struct bpf_program *prog,
-		  char *license, u32 kern_version)
+		  char *license, __u32 kern_version)
 {
 	int err = 0, fd, i;
 
@@ -1655,7 +1644,7 @@ static int check_path(const char *path)
 
 	dir = dirname(dname);
 	if (statfs(dir, &st_fs)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to statfs %s: %s\n", dir, cp);
 		err = -errno;
 	}
@@ -1691,7 +1680,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	}
 
 	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to pin program: %s\n", cp);
 		return -errno;
 	}
@@ -1709,7 +1698,7 @@ static int make_dir(const char *path)
 		err = -errno;
 
 	if (err) {
-		cp = str_error(-err, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
 		pr_warning("failed to mkdir %s: %s\n", path, cp);
 	}
 	return err;
@@ -1771,7 +1760,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 	}
 
 	if (bpf_obj_pin(map->fd, path)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to pin map: %s\n", cp);
 		return -errno;
 	}
@@ -2085,58 +2074,90 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_FULL(string, ptype, atype) \
-	{ string, sizeof(string) - 1, ptype, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, atype) \
+	{ string, sizeof(string) - 1, ptype, eatype, atype }
+
+/* Programs that can NOT be attached. */
+#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, -EINVAL)
 
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0)
+/* Programs that can be attached. */
+#define BPF_APROG_SEC(string, ptype, atype) \
+	BPF_PROG_SEC_IMPL(string, ptype, 0, atype)
 
-#define BPF_S_PROG_SEC(string, ptype) \
-	BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK, ptype)
+/* Programs that must specify expected attach type at load time. */
+#define BPF_EAPROG_SEC(string, ptype, eatype) \
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype)
 
-#define BPF_SA_PROG_SEC(string, ptype) \
-	BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype)
+/* Programs that can be attached but attach type can't be identified by section
+ * name. Kept for backward compatibility.
+ */
+#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype)
 
 static const struct {
 	const char *sec;
 	size_t len;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
+	enum bpf_attach_type attach_type;
 } section_names[] = {
-	BPF_PROG_SEC("socket",		BPF_PROG_TYPE_SOCKET_FILTER),
-	BPF_PROG_SEC("kprobe/",		BPF_PROG_TYPE_KPROBE),
-	BPF_PROG_SEC("kretprobe/",	BPF_PROG_TYPE_KPROBE),
-	BPF_PROG_SEC("classifier",	BPF_PROG_TYPE_SCHED_CLS),
-	BPF_PROG_SEC("action",		BPF_PROG_TYPE_SCHED_ACT),
-	BPF_PROG_SEC("tracepoint/",	BPF_PROG_TYPE_TRACEPOINT),
-	BPF_PROG_SEC("raw_tracepoint/",	BPF_PROG_TYPE_RAW_TRACEPOINT),
-	BPF_PROG_SEC("xdp",		BPF_PROG_TYPE_XDP),
-	BPF_PROG_SEC("perf_event",	BPF_PROG_TYPE_PERF_EVENT),
-	BPF_PROG_SEC("cgroup/skb",	BPF_PROG_TYPE_CGROUP_SKB),
-	BPF_PROG_SEC("cgroup/sock",	BPF_PROG_TYPE_CGROUP_SOCK),
-	BPF_PROG_SEC("cgroup/dev",	BPF_PROG_TYPE_CGROUP_DEVICE),
-	BPF_PROG_SEC("lwt_in",		BPF_PROG_TYPE_LWT_IN),
-	BPF_PROG_SEC("lwt_out",		BPF_PROG_TYPE_LWT_OUT),
-	BPF_PROG_SEC("lwt_xmit",	BPF_PROG_TYPE_LWT_XMIT),
-	BPF_PROG_SEC("lwt_seg6local",	BPF_PROG_TYPE_LWT_SEG6LOCAL),
-	BPF_PROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS),
-	BPF_PROG_SEC("sk_skb",		BPF_PROG_TYPE_SK_SKB),
-	BPF_PROG_SEC("sk_msg",		BPF_PROG_TYPE_SK_MSG),
-	BPF_PROG_SEC("lirc_mode2",	BPF_PROG_TYPE_LIRC_MODE2),
-	BPF_PROG_SEC("flow_dissector",	BPF_PROG_TYPE_FLOW_DISSECTOR),
-	BPF_SA_PROG_SEC("cgroup/bind4",	BPF_CGROUP_INET4_BIND),
-	BPF_SA_PROG_SEC("cgroup/bind6",	BPF_CGROUP_INET6_BIND),
-	BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
-	BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT),
-	BPF_SA_PROG_SEC("cgroup/sendmsg4", BPF_CGROUP_UDP4_SENDMSG),
-	BPF_SA_PROG_SEC("cgroup/sendmsg6", BPF_CGROUP_UDP6_SENDMSG),
-	BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND),
-	BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND),
+	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
+	BPF_PROG_SEC("kprobe/",			BPF_PROG_TYPE_KPROBE),
+	BPF_PROG_SEC("kretprobe/",		BPF_PROG_TYPE_KPROBE),
+	BPF_PROG_SEC("classifier",		BPF_PROG_TYPE_SCHED_CLS),
+	BPF_PROG_SEC("action",			BPF_PROG_TYPE_SCHED_ACT),
+	BPF_PROG_SEC("tracepoint/",		BPF_PROG_TYPE_TRACEPOINT),
+	BPF_PROG_SEC("raw_tracepoint/",		BPF_PROG_TYPE_RAW_TRACEPOINT),
+	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
+	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
+	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
+	BPF_PROG_SEC("lwt_out",			BPF_PROG_TYPE_LWT_OUT),
+	BPF_PROG_SEC("lwt_xmit",		BPF_PROG_TYPE_LWT_XMIT),
+	BPF_PROG_SEC("lwt_seg6local",		BPF_PROG_TYPE_LWT_SEG6LOCAL),
+	BPF_APROG_SEC("cgroup_skb/ingress",	BPF_PROG_TYPE_CGROUP_SKB,
+						BPF_CGROUP_INET_INGRESS),
+	BPF_APROG_SEC("cgroup_skb/egress",	BPF_PROG_TYPE_CGROUP_SKB,
+						BPF_CGROUP_INET_EGRESS),
+	BPF_APROG_COMPAT("cgroup/skb",		BPF_PROG_TYPE_CGROUP_SKB),
+	BPF_APROG_SEC("cgroup/sock",		BPF_PROG_TYPE_CGROUP_SOCK,
+						BPF_CGROUP_INET_SOCK_CREATE),
+	BPF_EAPROG_SEC("cgroup/post_bind4",	BPF_PROG_TYPE_CGROUP_SOCK,
+						BPF_CGROUP_INET4_POST_BIND),
+	BPF_EAPROG_SEC("cgroup/post_bind6",	BPF_PROG_TYPE_CGROUP_SOCK,
+						BPF_CGROUP_INET6_POST_BIND),
+	BPF_APROG_SEC("cgroup/dev",		BPF_PROG_TYPE_CGROUP_DEVICE,
+						BPF_CGROUP_DEVICE),
+	BPF_APROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS,
+						BPF_CGROUP_SOCK_OPS),
+	BPF_APROG_SEC("sk_skb/stream_parser",	BPF_PROG_TYPE_SK_SKB,
+						BPF_SK_SKB_STREAM_PARSER),
+	BPF_APROG_SEC("sk_skb/stream_verdict",	BPF_PROG_TYPE_SK_SKB,
+						BPF_SK_SKB_STREAM_VERDICT),
+	BPF_APROG_COMPAT("sk_skb",		BPF_PROG_TYPE_SK_SKB),
+	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
+						BPF_SK_MSG_VERDICT),
+	BPF_APROG_SEC("lirc_mode2",		BPF_PROG_TYPE_LIRC_MODE2,
+						BPF_LIRC_MODE2),
+	BPF_APROG_SEC("flow_dissector",		BPF_PROG_TYPE_FLOW_DISSECTOR,
+						BPF_FLOW_DISSECTOR),
+	BPF_EAPROG_SEC("cgroup/bind4",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET4_BIND),
+	BPF_EAPROG_SEC("cgroup/bind6",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET6_BIND),
+	BPF_EAPROG_SEC("cgroup/connect4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET4_CONNECT),
+	BPF_EAPROG_SEC("cgroup/connect6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET6_CONNECT),
+	BPF_EAPROG_SEC("cgroup/sendmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_UDP4_SENDMSG),
+	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_UDP6_SENDMSG),
 };
 
+#undef BPF_PROG_SEC_IMPL
 #undef BPF_PROG_SEC
-#undef BPF_PROG_SEC_FULL
-#undef BPF_S_PROG_SEC
-#undef BPF_SA_PROG_SEC
+#undef BPF_APROG_SEC
+#undef BPF_EAPROG_SEC
+#undef BPF_APROG_COMPAT
 
 int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 			     enum bpf_attach_type *expected_attach_type)
@@ -2156,6 +2177,25 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 	return -EINVAL;
 }
 
+int libbpf_attach_type_by_name(const char *name,
+			       enum bpf_attach_type *attach_type)
+{
+	int i;
+
+	if (!name)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+		if (strncmp(name, section_names[i].sec, section_names[i].len))
+			continue;
+		if (section_names[i].attach_type == -EINVAL)
+			return -EINVAL;
+		*attach_type = section_names[i].attach_type;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static int
 bpf_program__identify_section(struct bpf_program *prog,
 			      enum bpf_prog_type *prog_type,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e3b00e23e181..8af8d3663991 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * Common eBPF ELF object loading operations.
@@ -6,22 +6,9 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
-#ifndef __BPF_LIBBPF_H
-#define __BPF_LIBBPF_H
+#ifndef __LIBBPF_LIBBPF_H
+#define __LIBBPF_LIBBPF_H
 
 #include <stdio.h>
 #include <stdint.h>
@@ -104,6 +91,8 @@ void *bpf_object__priv(struct bpf_object *prog);
 
 int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 			     enum bpf_attach_type *expected_attach_type);
+int libbpf_attach_type_by_name(const char *name,
+			       enum bpf_attach_type *attach_type);
 
 /* Accessors of bpf_program */
 struct bpf_program;
@@ -126,10 +115,13 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
 
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
+int bpf_program__load(struct bpf_program *prog, char *license,
+		      __u32 kern_version);
 int bpf_program__fd(struct bpf_program *prog);
 int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 			      int instance);
 int bpf_program__pin(struct bpf_program *prog, const char *path);
+void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_insn;
 
@@ -299,18 +291,15 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size,
 			       void **buf, size_t *buf_len,
 			       bpf_perf_event_print_t fn, void *priv);
 
-struct nlmsghdr;
 struct nlattr;
-typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
-typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
-			      void *cookie);
-int bpf_netlink_open(unsigned int *nl_pid);
-int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
-		void *cookie);
-int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_class_nlmsg, void *cookie);
-int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
-int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
-		  dump_nlmsg_t dump_filter_nlmsg, void *cookie);
-#endif
+typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+int libbpf_netlink_open(unsigned int *nl_pid);
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie);
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie);
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
+#endif /* __LIBBPF_LIBBPF_H */
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 2464ade3b326..d83b17f8435c 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -1,23 +1,10 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
  * Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #include <stdio.h>
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index fde1d7bf8199..0ce67aea8f3b 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
@@ -18,7 +18,10 @@
 #define SOL_NETLINK 270
 #endif
 
-int bpf_netlink_open(__u32 *nl_pid)
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
+			      void *cookie);
+
+int libbpf_netlink_open(__u32 *nl_pid)
 {
 	struct sockaddr_nl sa;
 	socklen_t addrlen;
@@ -62,7 +65,7 @@ cleanup:
 }
 
 static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
-			    __dump_nlmsg_t _fn, dump_nlmsg_t fn,
+			    __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
 			    void *cookie)
 {
 	bool multipart = true;
@@ -100,7 +103,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 				if (!err->error)
 					continue;
 				ret = err->error;
-				nla_dump_errormsg(nh);
+				libbpf_nla_dump_errormsg(nh);
 				goto done;
 			case NLMSG_DONE:
 				return 0;
@@ -130,7 +133,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	} req;
 	__u32 nl_pid;
 
-	sock = bpf_netlink_open(&nl_pid);
+	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
 		return sock;
 
@@ -178,8 +181,8 @@ cleanup:
 	return ret;
 }
 
-static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
-			     void *cookie)
+static int __dump_link_nlmsg(struct nlmsghdr *nlh,
+			     libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
 	struct nlattr *tb[IFLA_MAX + 1], *attr;
 	struct ifinfomsg *ifi = NLMSG_DATA(nlh);
@@ -187,14 +190,14 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
 	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
-	if (nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_link_nlmsg(cookie, ifi, tb);
 }
 
-int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
-		void *cookie)
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -216,7 +219,8 @@ int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
 }
 
 static int __dump_class_nlmsg(struct nlmsghdr *nlh,
-			      dump_nlmsg_t dump_class_nlmsg, void *cookie)
+			      libbpf_dump_nlmsg_t dump_class_nlmsg,
+			      void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -224,14 +228,14 @@ static int __dump_class_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_class_nlmsg(cookie, t, tb);
 }
 
-int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_class_nlmsg, void *cookie)
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -254,7 +258,8 @@ int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
 }
 
 static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
-			      dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+			      libbpf_dump_nlmsg_t dump_qdisc_nlmsg,
+			      void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -262,14 +267,14 @@ static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_qdisc_nlmsg(cookie, t, tb);
 }
 
-int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -292,7 +297,8 @@ int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 }
 
 static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
-			       dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+			       libbpf_dump_nlmsg_t dump_filter_nlmsg,
+			       void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -300,14 +306,14 @@ static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_filter_nlmsg(cookie, t, tb);
 }
 
-int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
-		  dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 49f514119bdb..1e69c0c8d413 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -1,13 +1,8 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * NETLINK      Netlink attributes
  *
- *	This library is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU Lesser General Public
- *	License as published by the Free Software Foundation version 2.1
- *	of the License.
- *
  * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
  */
 
@@ -17,13 +12,13 @@
 #include <string.h>
 #include <stdio.h>
 
-static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
-	[NLA_U8]	= sizeof(uint8_t),
-	[NLA_U16]	= sizeof(uint16_t),
-	[NLA_U32]	= sizeof(uint32_t),
-	[NLA_U64]	= sizeof(uint64_t),
-	[NLA_STRING]	= 1,
-	[NLA_FLAG]	= 0,
+static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
+	[LIBBPF_NLA_U8]		= sizeof(uint8_t),
+	[LIBBPF_NLA_U16]	= sizeof(uint16_t),
+	[LIBBPF_NLA_U32]	= sizeof(uint32_t),
+	[LIBBPF_NLA_U64]	= sizeof(uint64_t),
+	[LIBBPF_NLA_STRING]	= 1,
+	[LIBBPF_NLA_FLAG]	= 0,
 };
 
 static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
@@ -47,9 +42,9 @@ static int nla_type(const struct nlattr *nla)
 }
 
 static int validate_nla(struct nlattr *nla, int maxtype,
-			struct nla_policy *policy)
+			struct libbpf_nla_policy *policy)
 {
-	struct nla_policy *pt;
+	struct libbpf_nla_policy *pt;
 	unsigned int minlen = 0;
 	int type = nla_type(nla);
 
@@ -58,23 +53,24 @@ static int validate_nla(struct nlattr *nla, int maxtype,
 
 	pt = &policy[type];
 
-	if (pt->type > NLA_TYPE_MAX)
+	if (pt->type > LIBBPF_NLA_TYPE_MAX)
 		return 0;
 
 	if (pt->minlen)
 		minlen = pt->minlen;
-	else if (pt->type != NLA_UNSPEC)
+	else if (pt->type != LIBBPF_NLA_UNSPEC)
 		minlen = nla_attr_minlen[pt->type];
 
-	if (nla_len(nla) < minlen)
+	if (libbpf_nla_len(nla) < minlen)
 		return -1;
 
-	if (pt->maxlen && nla_len(nla) > pt->maxlen)
+	if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen)
 		return -1;
 
-	if (pt->type == NLA_STRING) {
-		char *data = nla_data(nla);
-		if (data[nla_len(nla) - 1] != '\0')
+	if (pt->type == LIBBPF_NLA_STRING) {
+		char *data = libbpf_nla_data(nla);
+
+		if (data[libbpf_nla_len(nla) - 1] != '\0')
 			return -1;
 	}
 
@@ -104,15 +100,15 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh)
  * @see nla_validate
  * @return 0 on success or a negative error code.
  */
-int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-	      struct nla_policy *policy)
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+		     int len, struct libbpf_nla_policy *policy)
 {
 	struct nlattr *nla;
 	int rem, err;
 
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 
-	nla_for_each_attr(nla, head, len, rem) {
+	libbpf_nla_for_each_attr(nla, head, len, rem) {
 		int type = nla_type(nla);
 
 		if (type > maxtype)
@@ -144,23 +140,25 @@ errout:
  * @arg policy          Attribute validation policy.
  *
  * Feeds the stream of attributes nested into the specified attribute
- * to nla_parse().
+ * to libbpf_nla_parse().
  *
- * @see nla_parse
+ * @see libbpf_nla_parse
  * @return 0 on success or a negative error code.
  */
-int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
-		     struct nla_policy *policy)
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+			    struct nlattr *nla,
+			    struct libbpf_nla_policy *policy)
 {
-	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy);
+	return libbpf_nla_parse(tb, maxtype, libbpf_nla_data(nla),
+				libbpf_nla_len(nla), policy);
 }
 
 /* dump netlink extended ack error message */
-int nla_dump_errormsg(struct nlmsghdr *nlh)
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
 {
-	struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
-		[NLMSGERR_ATTR_MSG]	= { .type = NLA_STRING },
-		[NLMSGERR_ATTR_OFFS]	= { .type = NLA_U32 },
+	struct libbpf_nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
+		[NLMSGERR_ATTR_MSG]	= { .type = LIBBPF_NLA_STRING },
+		[NLMSGERR_ATTR_OFFS]	= { .type = LIBBPF_NLA_U32 },
 	};
 	struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr;
 	struct nlmsgerr *err;
@@ -181,14 +179,15 @@ int nla_dump_errormsg(struct nlmsghdr *nlh)
 	attr = (struct nlattr *) ((void *) err + hlen);
 	alen = nlh->nlmsg_len - hlen;
 
-	if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) {
+	if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
+			     extack_policy) != 0) {
 		fprintf(stderr,
 			"Failed to parse extended error attributes\n");
 		return 0;
 	}
 
 	if (tb[NLMSGERR_ATTR_MSG])
-		errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]);
+		errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]);
 
 	fprintf(stderr, "Kernel error message: %s\n", errmsg);
 
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index a6e2396bce7c..6cc3ac91690f 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -1,18 +1,13 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * NETLINK      Netlink attributes
  *
- *	This library is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU Lesser General Public
- *	License as published by the Free Software Foundation version 2.1
- *	of the License.
- *
  * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
  */
 
-#ifndef __NLATTR_H
-#define __NLATTR_H
+#ifndef __LIBBPF_NLATTR_H
+#define __LIBBPF_NLATTR_H
 
 #include <stdint.h>
 #include <linux/netlink.h>
@@ -23,19 +18,19 @@
  * Standard attribute types to specify validation policy
  */
 enum {
-	NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
-	NLA_U8,		/**< 8 bit integer */
-	NLA_U16,	/**< 16 bit integer */
-	NLA_U32,	/**< 32 bit integer */
-	NLA_U64,	/**< 64 bit integer */
-	NLA_STRING,	/**< NUL terminated character string */
-	NLA_FLAG,	/**< Flag */
-	NLA_MSECS,	/**< Micro seconds (64bit) */
-	NLA_NESTED,	/**< Nested attributes */
-	__NLA_TYPE_MAX,
+	LIBBPF_NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
+	LIBBPF_NLA_U8,		/**< 8 bit integer */
+	LIBBPF_NLA_U16,		/**< 16 bit integer */
+	LIBBPF_NLA_U32,		/**< 32 bit integer */
+	LIBBPF_NLA_U64,		/**< 64 bit integer */
+	LIBBPF_NLA_STRING,	/**< NUL terminated character string */
+	LIBBPF_NLA_FLAG,	/**< Flag */
+	LIBBPF_NLA_MSECS,	/**< Micro seconds (64bit) */
+	LIBBPF_NLA_NESTED,	/**< Nested attributes */
+	__LIBBPF_NLA_TYPE_MAX,
 };
 
-#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+#define LIBBPF_NLA_TYPE_MAX (__LIBBPF_NLA_TYPE_MAX - 1)
 
 /**
  * @ingroup attr
@@ -43,8 +38,8 @@ enum {
  *
  * See section @core_doc{core_attr_parse,Attribute Parsing} for more details.
  */
-struct nla_policy {
-	/** Type of attribute or NLA_UNSPEC */
+struct libbpf_nla_policy {
+	/** Type of attribute or LIBBPF_NLA_UNSPEC */
 	uint16_t	type;
 
 	/** Minimal length of payload required */
@@ -62,49 +57,50 @@ struct nla_policy {
  * @arg len	length of attribute stream
  * @arg rem	initialized to len, holds bytes currently remaining in stream
  */
-#define nla_for_each_attr(pos, head, len, rem) \
+#define libbpf_nla_for_each_attr(pos, head, len, rem) \
 	for (pos = head, rem = len; \
 	     nla_ok(pos, rem); \
 	     pos = nla_next(pos, &(rem)))
 
 /**
- * nla_data - head of payload
+ * libbpf_nla_data - head of payload
  * @nla: netlink attribute
  */
-static inline void *nla_data(const struct nlattr *nla)
+static inline void *libbpf_nla_data(const struct nlattr *nla)
 {
 	return (char *) nla + NLA_HDRLEN;
 }
 
-static inline uint8_t nla_getattr_u8(const struct nlattr *nla)
+static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
 {
-	return *(uint8_t *)nla_data(nla);
+	return *(uint8_t *)libbpf_nla_data(nla);
 }
 
-static inline uint32_t nla_getattr_u32(const struct nlattr *nla)
+static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla)
 {
-	return *(uint32_t *)nla_data(nla);
+	return *(uint32_t *)libbpf_nla_data(nla);
 }
 
-static inline const char *nla_getattr_str(const struct nlattr *nla)
+static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla)
 {
-	return (const char *)nla_data(nla);
+	return (const char *)libbpf_nla_data(nla);
 }
 
 /**
- * nla_len - length of payload
+ * libbpf_nla_len - length of payload
  * @nla: netlink attribute
  */
-static inline int nla_len(const struct nlattr *nla)
+static inline int libbpf_nla_len(const struct nlattr *nla)
 {
 	return nla->nla_len - NLA_HDRLEN;
 }
 
-int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-	      struct nla_policy *policy);
-int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
-		     struct nla_policy *policy);
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+		     int len, struct libbpf_nla_policy *policy);
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+			    struct nlattr *nla,
+			    struct libbpf_nla_policy *policy);
 
-int nla_dump_errormsg(struct nlmsghdr *nlh);
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
 
-#endif /* __NLATTR_H */
+#endif /* __LIBBPF_NLATTR_H */
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index b8798114a357..00e48ac5b806 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 #undef _GNU_SOURCE
 #include <string.h>
 #include <stdio.h>
@@ -9,7 +9,7 @@
  * libc, while checking strerror_r() return to avoid having to check this in
  * all places calling it.
  */
-char *str_error(int err, char *dst, int len)
+char *libbpf_strerror_r(int err, char *dst, int len)
 {
 	int ret = strerror_r(err, dst, len);
 	if (ret)
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index 355b1db571d1..a139334d57b6 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: LGPL-2.1
-#ifndef BPF_STR_ERROR
-#define BPF_STR_ERROR
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __LIBBPF_STR_ERROR_H
+#define __LIBBPF_STR_ERROR_H
 
-char *str_error(int err, char *dst, int len);
-#endif // BPF_STR_ERROR
+char *libbpf_strerror_r(int err, char *dst, int len);
+#endif /* __LIBBPF_STR_ERROR_H */
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index fd3851d5c079..1381ab81099c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,8 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 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_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
-	test_socket_cookie test_cgroup_storage test_select_reuseport
+	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
+	test_netcnt
 
 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     \
@@ -35,7 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o bpf_flow.o
+	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -72,6 +73,7 @@ $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
+$(OUTPUT)/test_netcnt: cgroup_helpers.c
 
 .PHONY: force
 
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index e4be7730222d..1d407b3494f9 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -143,6 +143,18 @@ static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
 	(void *) BPF_FUNC_skb_cgroup_id;
 static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
 	(void *) BPF_FUNC_skb_ancestor_cgroup_id;
+static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx,
+					     struct bpf_sock_tuple *tuple,
+					     int size, unsigned int netns_id,
+					     unsigned long long flags) =
+	(void *) BPF_FUNC_sk_lookup_tcp;
+static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
+					     struct bpf_sock_tuple *tuple,
+					     int size, unsigned int netns_id,
+					     unsigned long long flags) =
+	(void *) BPF_FUNC_sk_lookup_udp;
+static int (*bpf_sk_release)(struct bpf_sock *sk) =
+	(void *) BPF_FUNC_sk_release;
 
 /* 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/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h
new file mode 100644
index 000000000000..81084c1c2c23
--- /dev/null
+++ b/tools/testing/selftests/bpf/netcnt_common.h
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __NETCNT_COMMON_H
+#define __NETCNT_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_PERCPU_PACKETS 32
+
+struct percpu_net_cnt {
+	__u64 packets;
+	__u64 bytes;
+
+	__u64 prev_ts;
+
+	__u64 prev_packets;
+	__u64 prev_bytes;
+};
+
+struct net_cnt {
+	__u64 packets;
+	__u64 bytes;
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/netcnt_prog.c
new file mode 100644
index 000000000000..1198abca1360
--- /dev/null
+++ b/tools/testing/selftests/bpf/netcnt_prog.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/version.h>
+
+#include "bpf_helpers.h"
+#include "netcnt_common.h"
+
+#define MAX_BPS	(3 * 1024 * 1024)
+
+#define REFRESH_TIME_NS	100000000
+#define NS_PER_SEC	1000000000
+
+struct bpf_map_def SEC("maps") percpu_netcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct percpu_net_cnt),
+};
+
+struct bpf_map_def SEC("maps") netcnt = {
+	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct net_cnt),
+};
+
+SEC("cgroup/skb")
+int bpf_nextcnt(struct __sk_buff *skb)
+{
+	struct percpu_net_cnt *percpu_cnt;
+	char fmt[] = "%d %llu %llu\n";
+	struct net_cnt *cnt;
+	__u64 ts, dt;
+	int ret;
+
+	cnt = bpf_get_local_storage(&netcnt, 0);
+	percpu_cnt = bpf_get_local_storage(&percpu_netcnt, 0);
+
+	percpu_cnt->packets++;
+	percpu_cnt->bytes += skb->len;
+
+	if (percpu_cnt->packets > MAX_PERCPU_PACKETS) {
+		__sync_fetch_and_add(&cnt->packets,
+				     percpu_cnt->packets);
+		percpu_cnt->packets = 0;
+
+		__sync_fetch_and_add(&cnt->bytes,
+				     percpu_cnt->bytes);
+		percpu_cnt->bytes = 0;
+	}
+
+	ts = bpf_ktime_get_ns();
+	dt = ts - percpu_cnt->prev_ts;
+
+	dt *= MAX_BPS;
+	dt /= NS_PER_SEC;
+
+	if (cnt->bytes + percpu_cnt->bytes - percpu_cnt->prev_bytes < dt)
+		ret = 1;
+	else
+		ret = 0;
+
+	if (dt > REFRESH_TIME_NS) {
+		percpu_cnt->prev_ts = ts;
+		percpu_cnt->prev_packets = cnt->packets;
+		percpu_cnt->prev_bytes = cnt->bytes;
+	}
+
+	return !!ret;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
index 4e196e3bfecf..f44834155f25 100644
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -4,6 +4,7 @@
 #include <linux/filter.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <sys/sysinfo.h>
 
 #include "bpf_rlimit.h"
 #include "cgroup_helpers.h"
@@ -15,6 +16,14 @@ char bpf_log_buf[BPF_LOG_BUF_SIZE];
 int main(int argc, char **argv)
 {
 	struct bpf_insn prog[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, 0), /* percpu map fd */
+		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_local_storage),
+		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
+		BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+
 		BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
 		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
 		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
@@ -28,9 +37,18 @@ int main(int argc, char **argv)
 	};
 	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 	int error = EXIT_FAILURE;
-	int map_fd, prog_fd, cgroup_fd;
+	int map_fd, percpu_map_fd, prog_fd, cgroup_fd;
 	struct bpf_cgroup_storage_key key;
 	unsigned long long value;
+	unsigned long long *percpu_value;
+	int cpu, nproc;
+
+	nproc = get_nprocs_conf();
+	percpu_value = malloc(sizeof(*percpu_value) * nproc);
+	if (!percpu_value) {
+		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
+		goto err;
+	}
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
 				sizeof(value), 0, 0);
@@ -39,7 +57,15 @@ int main(int argc, char **argv)
 		goto out;
 	}
 
-	prog[0].imm = map_fd;
+	percpu_map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+				       sizeof(key), sizeof(value), 0, 0);
+	if (percpu_map_fd < 0) {
+		printf("Failed to create map: %s\n", strerror(errno));
+		goto out;
+	}
+
+	prog[0].imm = percpu_map_fd;
+	prog[7].imm = map_fd;
 	prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
 				   prog, insns_cnt, "GPL", 0,
 				   bpf_log_buf, BPF_LOG_BUF_SIZE);
@@ -77,7 +103,15 @@ int main(int argc, char **argv)
 	}
 
 	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup cgroup storage\n");
+		printf("Failed to lookup cgroup storage 0\n");
+		goto err;
+	}
+
+	for (cpu = 0; cpu < nproc; cpu++)
+		percpu_value[cpu] = 1000;
+
+	if (bpf_map_update_elem(percpu_map_fd, &key, percpu_value, 0)) {
+		printf("Failed to update the data in the cgroup storage\n");
 		goto err;
 	}
 
@@ -120,11 +154,31 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
+	/* Check the final value of the counter in the percpu local storage */
+
+	for (cpu = 0; cpu < nproc; cpu++)
+		percpu_value[cpu] = 0;
+
+	if (bpf_map_lookup_elem(percpu_map_fd, &key, percpu_value)) {
+		printf("Failed to lookup the per-cpu cgroup storage\n");
+		goto err;
+	}
+
+	value = 0;
+	for (cpu = 0; cpu < nproc; cpu++)
+		value += percpu_value[cpu];
+
+	if (value != nproc * 1000 + 6) {
+		printf("Unexpected data in the per-cpu cgroup storage\n");
+		goto err;
+	}
+
 	error = 0;
 	printf("test_cgroup_storage:PASS\n");
 
 err:
 	cleanup_cgroup_environment();
+	free(percpu_value);
 
 out:
 	return error;
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
new file mode 100644
index 000000000000..7887df693399
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <sys/sysinfo.h>
+#include <sys/time.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
+#include "netcnt_common.h"
+
+#define BPF_PROG "./netcnt_prog.o"
+#define TEST_CGROUP "/test-network-counters/"
+
+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);
+}
+
+int main(int argc, char **argv)
+{
+	struct percpu_net_cnt *percpu_netcnt;
+	struct bpf_cgroup_storage_key key;
+	int map_fd, percpu_map_fd;
+	int error = EXIT_FAILURE;
+	struct net_cnt netcnt;
+	struct bpf_object *obj;
+	int prog_fd, cgroup_fd;
+	unsigned long packets;
+	unsigned long bytes;
+	int cpu, nproc;
+	__u32 prog_cnt;
+
+	nproc = get_nprocs_conf();
+	percpu_netcnt = malloc(sizeof(*percpu_netcnt) * nproc);
+	if (!percpu_netcnt) {
+		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
+		goto err;
+	}
+
+	if (bpf_prog_load(BPF_PROG, BPF_PROG_TYPE_CGROUP_SKB,
+			  &obj, &prog_fd)) {
+		printf("Failed to load bpf program\n");
+		goto out;
+	}
+
+	if (setup_cgroup_environment()) {
+		printf("Failed to load bpf program\n");
+		goto err;
+	}
+
+	/* Create a cgroup, get fd, and join it */
+	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+	if (!cgroup_fd) {
+		printf("Failed to create test cgroup\n");
+		goto err;
+	}
+
+	if (join_cgroup(TEST_CGROUP)) {
+		printf("Failed to join cgroup\n");
+		goto err;
+	}
+
+	/* Attach bpf program */
+	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
+		printf("Failed to attach bpf program");
+		goto err;
+	}
+
+	assert(system("ping localhost -6 -c 10000 -f -q > /dev/null") == 0);
+
+	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
+			   &prog_cnt)) {
+		printf("Failed to query attached programs");
+		goto err;
+	}
+
+	map_fd = bpf_find_map(__func__, obj, "netcnt");
+	if (map_fd < 0) {
+		printf("Failed to find bpf map with net counters");
+		goto err;
+	}
+
+	percpu_map_fd = bpf_find_map(__func__, obj, "percpu_netcnt");
+	if (percpu_map_fd < 0) {
+		printf("Failed to find bpf map with percpu net counters");
+		goto err;
+	}
+
+	if (bpf_map_get_next_key(map_fd, NULL, &key)) {
+		printf("Failed to get key in cgroup storage\n");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(map_fd, &key, &netcnt)) {
+		printf("Failed to lookup cgroup storage\n");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(percpu_map_fd, &key, &percpu_netcnt[0])) {
+		printf("Failed to lookup percpu cgroup storage\n");
+		goto err;
+	}
+
+	/* Some packets can be still in per-cpu cache, but not more than
+	 * MAX_PERCPU_PACKETS.
+	 */
+	packets = netcnt.packets;
+	bytes = netcnt.bytes;
+	for (cpu = 0; cpu < nproc; cpu++) {
+		if (percpu_netcnt[cpu].packets > MAX_PERCPU_PACKETS) {
+			printf("Unexpected percpu value: %llu\n",
+			       percpu_netcnt[cpu].packets);
+			goto err;
+		}
+
+		packets += percpu_netcnt[cpu].packets;
+		bytes += percpu_netcnt[cpu].bytes;
+	}
+
+	/* No packets should be lost */
+	if (packets != 10000) {
+		printf("Unexpected packet count: %lu\n", packets);
+		goto err;
+	}
+
+	/* Let's check that bytes counter matches the number of packets
+	 * multiplied by the size of ipv6 ICMP packet.
+	 */
+	if (bytes != packets * 104) {
+		printf("Unexpected bytes count: %lu\n", bytes);
+		goto err;
+	}
+
+	error = 0;
+	printf("test_netcnt:PASS\n");
+
+err:
+	cleanup_cgroup_environment();
+	free(percpu_netcnt);
+
+out:
+	return error;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 63a671803ed6..e8becca9c521 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1698,6 +1698,43 @@ static void test_task_fd_query_tp(void)
 				   "sys_enter_read");
 }
 
+static void test_reference_tracking()
+{
+	const char *file = "./test_sk_lookup_kern.o";
+	struct bpf_object *obj;
+	struct bpf_program *prog;
+	__u32 duration;
+	int err = 0;
+
+	obj = bpf_object__open(file);
+	if (IS_ERR(obj)) {
+		error_cnt++;
+		return;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		const char *title;
+
+		/* Ignore .text sections */
+		title = bpf_program__title(prog, false);
+		if (strstr(title, ".text") != NULL)
+			continue;
+
+		bpf_program__set_type(prog, BPF_PROG_TYPE_SCHED_CLS);
+
+		/* Expect verifier failure if test name has 'fail' */
+		if (strstr(title, "fail") != NULL) {
+			libbpf_set_print(NULL, NULL, NULL);
+			err = !bpf_program__load(prog, "GPL", 0);
+			libbpf_set_print(printf, printf, NULL);
+		} else {
+			err = bpf_program__load(prog, "GPL", 0);
+		}
+		CHECK(err, title, "\n");
+	}
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
 	jit_enabled = is_jit_enabled();
@@ -1719,6 +1756,7 @@ int main(void)
 	test_get_stack_raw_tp();
 	test_task_fd_query_rawtp();
 	test_task_fd_query_tp();
+	test_reference_tracking();
 
 	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_section_names.c b/tools/testing/selftests/bpf/test_section_names.c
new file mode 100644
index 000000000000..7c4f41572b1c
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_section_names.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <err.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_util.h"
+
+struct sec_name_test {
+	const char sec_name[32];
+	struct {
+		int rc;
+		enum bpf_prog_type prog_type;
+		enum bpf_attach_type expected_attach_type;
+	} expected_load;
+	struct {
+		int rc;
+		enum bpf_attach_type attach_type;
+	} expected_attach;
+};
+
+static struct sec_name_test tests[] = {
+	{"InvAliD", {-EINVAL, 0, 0}, {-EINVAL, 0} },
+	{"cgroup", {-EINVAL, 0, 0}, {-EINVAL, 0} },
+	{"socket", {0, BPF_PROG_TYPE_SOCKET_FILTER, 0}, {-EINVAL, 0} },
+	{"kprobe/", {0, BPF_PROG_TYPE_KPROBE, 0}, {-EINVAL, 0} },
+	{"kretprobe/", {0, BPF_PROG_TYPE_KPROBE, 0}, {-EINVAL, 0} },
+	{"classifier", {0, BPF_PROG_TYPE_SCHED_CLS, 0}, {-EINVAL, 0} },
+	{"action", {0, BPF_PROG_TYPE_SCHED_ACT, 0}, {-EINVAL, 0} },
+	{"tracepoint/", {0, BPF_PROG_TYPE_TRACEPOINT, 0}, {-EINVAL, 0} },
+	{
+		"raw_tracepoint/",
+		{0, BPF_PROG_TYPE_RAW_TRACEPOINT, 0},
+		{-EINVAL, 0},
+	},
+	{"xdp", {0, BPF_PROG_TYPE_XDP, 0}, {-EINVAL, 0} },
+	{"perf_event", {0, BPF_PROG_TYPE_PERF_EVENT, 0}, {-EINVAL, 0} },
+	{"lwt_in", {0, BPF_PROG_TYPE_LWT_IN, 0}, {-EINVAL, 0} },
+	{"lwt_out", {0, BPF_PROG_TYPE_LWT_OUT, 0}, {-EINVAL, 0} },
+	{"lwt_xmit", {0, BPF_PROG_TYPE_LWT_XMIT, 0}, {-EINVAL, 0} },
+	{"lwt_seg6local", {0, BPF_PROG_TYPE_LWT_SEG6LOCAL, 0}, {-EINVAL, 0} },
+	{
+		"cgroup_skb/ingress",
+		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_CGROUP_INET_INGRESS},
+	},
+	{
+		"cgroup_skb/egress",
+		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_CGROUP_INET_EGRESS},
+	},
+	{"cgroup/skb", {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, {-EINVAL, 0} },
+	{
+		"cgroup/sock",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, 0},
+		{0, BPF_CGROUP_INET_SOCK_CREATE},
+	},
+	{
+		"cgroup/post_bind4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND},
+		{0, BPF_CGROUP_INET4_POST_BIND},
+	},
+	{
+		"cgroup/post_bind6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND},
+		{0, BPF_CGROUP_INET6_POST_BIND},
+	},
+	{
+		"cgroup/dev",
+		{0, BPF_PROG_TYPE_CGROUP_DEVICE, 0},
+		{0, BPF_CGROUP_DEVICE},
+	},
+	{"sockops", {0, BPF_PROG_TYPE_SOCK_OPS, 0}, {0, BPF_CGROUP_SOCK_OPS} },
+	{
+		"sk_skb/stream_parser",
+		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_SK_SKB_STREAM_PARSER},
+	},
+	{
+		"sk_skb/stream_verdict",
+		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_SK_SKB_STREAM_VERDICT},
+	},
+	{"sk_skb", {0, BPF_PROG_TYPE_SK_SKB, 0}, {-EINVAL, 0} },
+	{"sk_msg", {0, BPF_PROG_TYPE_SK_MSG, 0}, {0, BPF_SK_MSG_VERDICT} },
+	{"lirc_mode2", {0, BPF_PROG_TYPE_LIRC_MODE2, 0}, {0, BPF_LIRC_MODE2} },
+	{
+		"flow_dissector",
+		{0, BPF_PROG_TYPE_FLOW_DISSECTOR, 0},
+		{0, BPF_FLOW_DISSECTOR},
+	},
+	{
+		"cgroup/bind4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND},
+		{0, BPF_CGROUP_INET4_BIND},
+	},
+	{
+		"cgroup/bind6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND},
+		{0, BPF_CGROUP_INET6_BIND},
+	},
+	{
+		"cgroup/connect4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT},
+		{0, BPF_CGROUP_INET4_CONNECT},
+	},
+	{
+		"cgroup/connect6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT},
+		{0, BPF_CGROUP_INET6_CONNECT},
+	},
+	{
+		"cgroup/sendmsg4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG},
+		{0, BPF_CGROUP_UDP4_SENDMSG},
+	},
+	{
+		"cgroup/sendmsg6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG},
+		{0, BPF_CGROUP_UDP6_SENDMSG},
+	},
+};
+
+static int test_prog_type_by_name(const struct sec_name_test *test)
+{
+	enum bpf_attach_type expected_attach_type;
+	enum bpf_prog_type prog_type;
+	int rc;
+
+	rc = libbpf_prog_type_by_name(test->sec_name, &prog_type,
+				      &expected_attach_type);
+
+	if (rc != test->expected_load.rc) {
+		warnx("prog: unexpected rc=%d for %s", rc, test->sec_name);
+		return -1;
+	}
+
+	if (rc)
+		return 0;
+
+	if (prog_type != test->expected_load.prog_type) {
+		warnx("prog: unexpected prog_type=%d for %s", prog_type,
+		      test->sec_name);
+		return -1;
+	}
+
+	if (expected_attach_type != test->expected_load.expected_attach_type) {
+		warnx("prog: unexpected expected_attach_type=%d for %s",
+		      expected_attach_type, test->sec_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int test_attach_type_by_name(const struct sec_name_test *test)
+{
+	enum bpf_attach_type attach_type;
+	int rc;
+
+	rc = libbpf_attach_type_by_name(test->sec_name, &attach_type);
+
+	if (rc != test->expected_attach.rc) {
+		warnx("attach: unexpected rc=%d for %s", rc, test->sec_name);
+		return -1;
+	}
+
+	if (rc)
+		return 0;
+
+	if (attach_type != test->expected_attach.attach_type) {
+		warnx("attach: unexpected attach_type=%d for %s", attach_type,
+		      test->sec_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int run_test_case(const struct sec_name_test *test)
+{
+	if (test_prog_type_by_name(test))
+		return -1;
+	if (test_attach_type_by_name(test))
+		return -1;
+	return 0;
+}
+
+static int run_tests(void)
+{
+	int passes = 0;
+	int fails = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+		if (run_test_case(&tests[i]))
+			++fails;
+		else
+			++passes;
+	}
+	printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
+	return fails ? -1 : 0;
+}
+
+int main(int argc, char **argv)
+{
+	return run_tests();
+}
diff --git a/tools/testing/selftests/bpf/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/test_sk_lookup_kern.c
new file mode 100644
index 000000000000..b745bdc08c2b
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sk_lookup_kern.c
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/tcp.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */
+static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off,
+					void *data_end, __u16 eth_proto,
+					bool *ipv4)
+{
+	struct bpf_sock_tuple *result;
+	__u8 proto = 0;
+	__u64 ihl_len;
+
+	if (eth_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(data + nh_off);
+
+		if (iph + 1 > data_end)
+			return NULL;
+		ihl_len = iph->ihl * 4;
+		proto = iph->protocol;
+		*ipv4 = true;
+		result = (struct bpf_sock_tuple *)&iph->saddr;
+	} else if (eth_proto == bpf_htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + nh_off);
+
+		if (ip6h + 1 > data_end)
+			return NULL;
+		ihl_len = sizeof(*ip6h);
+		proto = ip6h->nexthdr;
+		*ipv4 = true;
+		result = (struct bpf_sock_tuple *)&ip6h->saddr;
+	}
+
+	if (data + nh_off + ihl_len > data_end || proto != IPPROTO_TCP)
+		return NULL;
+
+	return result;
+}
+
+SEC("sk_lookup_success")
+int bpf_sk_lookup_test0(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	struct bpf_sock_tuple *tuple;
+	struct bpf_sock *sk;
+	size_t tuple_len;
+	bool ipv4;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	tuple = get_tuple(data, sizeof(*eth), data_end, eth->h_proto, &ipv4);
+	if (!tuple || tuple + sizeof *tuple > data_end)
+		return TC_ACT_SHOT;
+
+	tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
+	sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, 0, 0);
+	if (sk)
+		bpf_sk_release(sk);
+	return sk ? TC_ACT_OK : TC_ACT_UNSPEC;
+}
+
+SEC("sk_lookup_success_simple")
+int bpf_sk_lookup_test1(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk)
+		bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_use_after_free")
+int bpf_sk_lookup_uaf(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family = 0;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk) {
+		bpf_sk_release(sk);
+		family = sk->family;
+	}
+	return family;
+}
+
+SEC("fail_modify_sk_pointer")
+int bpf_sk_lookup_modptr(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk) {
+		sk += 1;
+		bpf_sk_release(sk);
+	}
+	return 0;
+}
+
+SEC("fail_modify_sk_or_null_pointer")
+int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk += 1;
+	if (sk)
+		bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_no_release")
+int bpf_sk_lookup_test2(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	return 0;
+}
+
+SEC("fail_release_twice")
+int bpf_sk_lookup_test3(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_release(sk);
+	bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_release_unchecked")
+int bpf_sk_lookup_test4(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_release(sk);
+	return 0;
+}
+
+void lookup_no_release(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+}
+
+SEC("fail_no_release_subcall")
+int bpf_sk_lookup_test5(struct __sk_buff *skb)
+{
+	lookup_no_release(skb);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c
index 68e108e4687a..b6c2c605d8c0 100644
--- a/tools/testing/selftests/bpf/test_socket_cookie.c
+++ b/tools/testing/selftests/bpf/test_socket_cookie.c
@@ -158,11 +158,7 @@ static int run_test(int cgfd)
 	bpf_object__for_each_program(prog, pobj) {
 		prog_name = bpf_program__title(prog, /*needs_copy*/ false);
 
-		if (strcmp(prog_name, "cgroup/connect6") == 0) {
-			attach_type = BPF_CGROUP_INET6_CONNECT;
-		} else if (strcmp(prog_name, "sockops") == 0) {
-			attach_type = BPF_CGROUP_SOCK_OPS;
-		} else {
+		if (libbpf_attach_type_by_name(prog_name, &attach_type)) {
 			log_err("Unexpected prog: %s", prog_name);
 			goto err;
 		}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 67c412d19c09..bc9cd8537467 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2014 PLUMgrid, http://plumgrid.com
  * Copyright (c) 2017 Facebook
+ * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -68,6 +69,7 @@ struct bpf_test {
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
 	int fixup_cgroup_storage[MAX_FIXUPS];
+	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval;
@@ -177,6 +179,24 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	self->retval = (uint32_t)res;
 }
 
+/* BPF_SK_LOOKUP contains 13 instructions, if you need to fix up maps */
+#define BPF_SK_LOOKUP							\
+	/* struct bpf_sock_tuple tuple = {} */				\
+	BPF_MOV64_IMM(BPF_REG_2, 0),					\
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8),			\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -16),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -24),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -32),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -40),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -48),		\
+	/* sk = sk_lookup_tcp(ctx, &tuple, sizeof tuple, 0, 0) */	\
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),				\
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -48),				\
+	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),	\
+	BPF_MOV64_IMM(BPF_REG_4, 0),					\
+	BPF_MOV64_IMM(BPF_REG_5, 0),					\
+	BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp)
+
 static struct bpf_test tests[] = {
 	{
 		"add+sub+mul",
@@ -2707,6 +2727,137 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
+		"unpriv: spill/fill of different pointers stx - ctx and sock",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb == NULL) *target = sock; */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* else *target = skb; */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* struct __sk_buff *skb = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* skb->mark = 42; */
+			BPF_MOV64_IMM(BPF_REG_3, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct __sk_buff, mark)),
+			/* if (sk) bpf_sk_release(sk) */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "type=ctx expected=sock",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - leak sock",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb == NULL) *target = sock; */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* else *target = skb; */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* struct __sk_buff *skb = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* skb->mark = 42; */
+			BPF_MOV64_IMM(BPF_REG_3, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		//.errstr = "same insn cannot be used with different pointers",
+		.errstr = "Unreleased reference",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - sock and ctx (read)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb) *target = skb */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* else *target = sock */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* struct bpf_sock *sk = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* if (sk) u32 foo = sk->mark; bpf_sk_release(sk); */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2),
+				BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+					    offsetof(struct bpf_sock, mark)),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "same insn cannot be used with different pointers",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - sock and ctx (write)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb) *target = skb */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* else *target = sock */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* struct bpf_sock *sk = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* if (sk) sk->mark = 42; bpf_sk_release(sk); */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
+				BPF_MOV64_IMM(BPF_REG_3, 42),
+				BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+					    offsetof(struct bpf_sock, mark)),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		//.errstr = "same insn cannot be used with different pointers",
+		.errstr = "cannot write into socket",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
 		"unpriv: spill/fill of different pointers ldx",
 		.insns = {
 			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
@@ -3275,7 +3426,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_ST stores into R1 context is not allowed",
+		.errstr = "BPF_ST stores into R1 inv is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -3287,7 +3438,7 @@ static struct bpf_test tests[] = {
 				     BPF_REG_0, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -3637,7 +3788,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4676,7 +4827,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
-		"invalid per-cgroup storage access 3",
+		"invalid cgroup storage access 3",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_2, 0),
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
@@ -4744,6 +4895,121 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
+		"valid per-cpu cgroup storage access",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 1 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "fd 1 is not pointing to valid bpf_map",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=256 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 4",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 5",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 7),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 6",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
 		"multiple registers share map_lookup_elem result",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_1, 10),
@@ -4780,7 +5046,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -4801,7 +5067,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -4822,7 +5088,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -5150,7 +5416,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 	},
 	{
 		"leak pointer into ctx 2",
@@ -5165,7 +5431,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R10 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 	},
 	{
 		"leak pointer into ctx 3",
@@ -7137,7 +7403,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map_in_map = { 3 },
-		.errstr = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited",
+		.errstr = "R1 pointer arithmetic on map_ptr prohibited",
 		.result = REJECT,
 	},
 	{
@@ -8811,7 +9077,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -8830,7 +9096,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -12114,7 +12380,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R2 packet",
+		.errstr = "BPF_XADD stores into R2 ctx",
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
@@ -12442,6 +12708,214 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
+		"reference tracking: leak potential reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak potential reference on stack",
+		.insns = {
+			BPF_SK_LOOKUP,
+			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_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak potential reference on stack 2",
+		.insns = {
+			BPF_SK_LOOKUP,
+			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_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: zero potential reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: copy and zero potential references",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_7, 0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference without check",
+		.insns = {
+			BPF_SK_LOOKUP,
+			/* reference in r0 may be NULL */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=sock_or_null expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference 2",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference twice",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference twice inside branch",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), /* goto end */
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: alloc, check, free in one subbranch",
+		.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, 16),
+			/* if (offsetof(skb, mark) > data_len) exit; */
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_SK_LOOKUP,
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 1), /* mark == 0? */
+			/* Leak reference in R0 */
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: alloc, check, free in both subbranches",
+		.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, 16),
+			/* if (offsetof(skb, mark) > data_len) exit; */
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_SK_LOOKUP,
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4), /* mark == 0? */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking in call: free reference in subprog",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
+			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_2, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
 		"pass modified ctx pointer to helper, 1",
 		.insns = {
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
@@ -12511,6 +12985,407 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"reference tracking in call: free reference in subprog and outside",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: alloc & leak reference in subprog",
+		.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),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_4),
+			BPF_SK_LOOKUP,
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: alloc in subprog, release outside",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(), /* return sk */
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = POINTER_VALUE,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking in call: sk_ptr leak 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, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: sk_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, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			/* now the sk_ptr is verified, free the reference */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_4, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: allow LD_ABS",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: forbid LD_ABS while holding reference",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: allow LD_IND",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_7, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"reference tracking: forbid LD_IND while holding reference",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_7, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_4),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: check reference or tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 17 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference then tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 18 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: leak possible reference over tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			/* Look up socket and store in REG_6 */
+			BPF_SK_LOOKUP,
+			/* bpf_tail_call() */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 16 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "tail_call would lead to reference leak",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak checked reference over tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			/* Look up socket and store in REG_6 */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			/* if (!sk) goto end */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 17 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "tail_call would lead to reference leak",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: mangle and release sock_or_null",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R1 pointer arithmetic on sock_or_null prohibited",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: mangle and release sock",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R1 pointer arithmetic on sock prohibited",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: access member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: write to member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LD_IMM64(BPF_REG_2, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_2,
+				    offsetof(struct bpf_sock, mark)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LD_IMM64(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "cannot write into socket",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: invalid 64-bit access of member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "invalid bpf_sock access off=0 size=8",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: access after release",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: direct access for lookup",
+		.insns = {
+			/* Check that the packet is at least 64B long */
+			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, 64),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 9),
+			/* sk = sk_lookup_tcp(ctx, skb->data, ...) */
+			BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -12536,18 +13411,18 @@ static int create_map(uint32_t type, uint32_t size_key,
 	return fd;
 }
 
-static int create_prog_dummy1(void)
+static int create_prog_dummy1(enum bpf_map_type prog_type)
 {
 	struct bpf_insn prog[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 42),
 		BPF_EXIT_INSN(),
 	};
 
-	return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+	return bpf_load_program(prog_type, prog,
 				ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
 }
 
-static int create_prog_dummy2(int mfd, int idx)
+static int create_prog_dummy2(enum bpf_map_type prog_type, int mfd, int idx)
 {
 	struct bpf_insn prog[] = {
 		BPF_MOV64_IMM(BPF_REG_3, idx),
@@ -12558,11 +13433,12 @@ static int create_prog_dummy2(int mfd, int idx)
 		BPF_EXIT_INSN(),
 	};
 
-	return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+	return bpf_load_program(prog_type, prog,
 				ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
 }
 
-static int create_prog_array(uint32_t max_elem, int p1key)
+static int create_prog_array(enum bpf_map_type prog_type, uint32_t max_elem,
+			     int p1key)
 {
 	int p2key = 1;
 	int mfd, p1fd, p2fd;
@@ -12574,8 +13450,8 @@ static int create_prog_array(uint32_t max_elem, int p1key)
 		return -1;
 	}
 
-	p1fd = create_prog_dummy1();
-	p2fd = create_prog_dummy2(mfd, p2key);
+	p1fd = create_prog_dummy1(prog_type);
+	p2fd = create_prog_dummy2(prog_type, mfd, p2key);
 	if (p1fd < 0 || p2fd < 0)
 		goto out;
 	if (bpf_map_update_elem(mfd, &p1key, &p1fd, BPF_ANY) < 0)
@@ -12615,23 +13491,25 @@ static int create_map_in_map(void)
 	return outer_map_fd;
 }
 
-static int create_cgroup_storage(void)
+static int create_cgroup_storage(bool percpu)
 {
+	enum bpf_map_type type = percpu ? BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE :
+		BPF_MAP_TYPE_CGROUP_STORAGE;
 	int fd;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
-			    sizeof(struct bpf_cgroup_storage_key),
+	fd = bpf_create_map(type, sizeof(struct bpf_cgroup_storage_key),
 			    TEST_DATA_LEN, 0, 0);
 	if (fd < 0)
-		printf("Failed to create array '%s'!\n", strerror(errno));
+		printf("Failed to create cgroup storage '%s'!\n",
+		       strerror(errno));
 
 	return fd;
 }
 
 static char bpf_vlog[UINT_MAX >> 8];
 
-static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
-			  int *map_fds)
+static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
+			  struct bpf_insn *prog, int *map_fds)
 {
 	int *fixup_map1 = test->fixup_map1;
 	int *fixup_map2 = test->fixup_map2;
@@ -12641,6 +13519,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
 	int *fixup_cgroup_storage = test->fixup_cgroup_storage;
+	int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
 
 	if (test->fill_helper)
 		test->fill_helper(test);
@@ -12686,7 +13565,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_prog1) {
-		map_fds[4] = create_prog_array(4, 0);
+		map_fds[4] = create_prog_array(prog_type, 4, 0);
 		do {
 			prog[*fixup_prog1].imm = map_fds[4];
 			fixup_prog1++;
@@ -12694,7 +13573,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_prog2) {
-		map_fds[5] = create_prog_array(8, 7);
+		map_fds[5] = create_prog_array(prog_type, 8, 7);
 		do {
 			prog[*fixup_prog2].imm = map_fds[5];
 			fixup_prog2++;
@@ -12710,12 +13589,20 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_cgroup_storage) {
-		map_fds[7] = create_cgroup_storage();
+		map_fds[7] = create_cgroup_storage(false);
 		do {
 			prog[*fixup_cgroup_storage].imm = map_fds[7];
 			fixup_cgroup_storage++;
 		} while (*fixup_cgroup_storage);
 	}
+
+	if (*fixup_percpu_cgroup_storage) {
+		map_fds[8] = create_cgroup_storage(true);
+		do {
+			prog[*fixup_percpu_cgroup_storage].imm = map_fds[8];
+			fixup_percpu_cgroup_storage++;
+		} while (*fixup_percpu_cgroup_storage);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
@@ -12732,11 +13619,13 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		map_fds[i] = -1;
 
-	do_test_fixup(test, prog, map_fds);
+	if (!prog_type)
+		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	do_test_fixup(test, prog_type, prog, map_fds);
 	prog_len = probe_filter_length(prog);
 
-	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
-				     prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+	fd_prog = bpf_verify_program(prog_type, prog, prog_len,
+				     test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
 				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
 
 	expected_ret = unpriv && test->result_unpriv != UNDEF ?