Merge remote-tracking branch 'net-next/master' into mac80211-next

Merge net-next to resolve a conflict and to get the mac80211
rhashtable fixes so further patches can be applied on top.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>

134 files changed, 6051 insertions, 628 deletions

diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index d43fce568ef7..9bb9ace54ba8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -17,8 +17,8 @@ SYNOPSIS
 	*COMMANDS* :=
 	{ **show** | **list** | **tree** | **attach** | **detach** | **help** }
 
-MAP COMMANDS
-=============
+CGROUP COMMANDS
+===============
 
 |	**bpftool** **cgroup { show | list }** *CGROUP*
 |	**bpftool** **cgroup tree** [*CGROUP_ROOT*]
diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
index 8d489a26e3c9..82de03dd8f52 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
@@ -16,8 +16,8 @@ SYNOPSIS
 
 	*COMMANDS* := { **probe** | **help** }
 
-MAP COMMANDS
-=============
+FEATURE COMMANDS
+================
 
 |	**bpftool** **feature probe** [*COMPONENT*] [**macros** [**prefix** *PREFIX*]]
 |	**bpftool** **feature help**
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 13b56102f528..7e59495cb028 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -18,7 +18,7 @@ SYNOPSIS
 	{ **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load**
 	| **loadall** | **help** }
 
-MAP COMMANDS
+PROG COMMANDS
 =============
 
 |	**bpftool** **prog { show | list }** [*PROG*]
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 27153bb816ac..4f2188845dd8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -16,7 +16,7 @@ SYNOPSIS
 
 	**bpftool** **version**
 
-	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** }
+	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** }
 
 	*OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
 	| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
@@ -34,6 +34,8 @@ SYNOPSIS
 
 	*NET-COMMANDS* := { **show** | **list** | **help** }
 
+	*FEATURE-COMMANDS* := { **probe** | **help** }
+
 DESCRIPTION
 ===========
 	*bpftool* allows for inspection and simple modification of BPF objects
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 897483457bf0..f7261fad45c1 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -297,10 +297,8 @@ char *get_fdinfo(int fd, const char *key)
 	snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd);
 
 	fdi = fopen(path, "r");
-	if (!fdi) {
-		p_err("can't open fdinfo: %s", strerror(errno));
+	if (!fdi)
 		return NULL;
-	}
 
 	while ((n = getline(&line, &line_n, fdi)) > 0) {
 		char *value;
@@ -313,7 +311,6 @@ char *get_fdinfo(int fd, const char *key)
 
 		value = strchr(line, '\t');
 		if (!value || !value[1]) {
-			p_err("malformed fdinfo!?");
 			free(line);
 			return NULL;
 		}
@@ -326,7 +323,6 @@ char *get_fdinfo(int fd, const char *key)
 		return line;
 	}
 
-	p_err("key '%s' not found in fdinfo", key);
 	free(line);
 	fclose(fdi);
 	return NULL;
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 2160a8ef17e5..e0c650d91784 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -358,6 +358,20 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val,
 	return argv + i;
 }
 
+/* on per cpu maps we must copy the provided value on all value instances */
+static void fill_per_cpu_value(struct bpf_map_info *info, void *value)
+{
+	unsigned int i, n, step;
+
+	if (!map_is_per_cpu(info->type))
+		return;
+
+	n = get_possible_cpus();
+	step = round_up(info->value_size, 8);
+	for (i = 1; i < n; i++)
+		memcpy(value + i * step, value, info->value_size);
+}
+
 static int parse_elem(char **argv, struct bpf_map_info *info,
 		      void *key, void *value, __u32 key_size, __u32 value_size,
 		      __u32 *flags, __u32 **value_fd)
@@ -440,6 +454,8 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
 			argv = parse_bytes(argv, "value", value, value_size);
 			if (!argv)
 				return -1;
+
+			fill_per_cpu_value(info, value);
 		}
 
 		return parse_elem(argv, info, key, NULL, key_size, value_size,
@@ -511,10 +527,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 				jsonw_uint_field(json_wtr, "owner_prog_type",
 						 prog_type);
 		}
-		if (atoi(owner_jited))
-			jsonw_bool_field(json_wtr, "owner_jited", true);
-		else
-			jsonw_bool_field(json_wtr, "owner_jited", false);
+		if (owner_jited)
+			jsonw_bool_field(json_wtr, "owner_jited",
+					 !!atoi(owner_jited));
 
 		free(owner_prog_type);
 		free(owner_jited);
@@ -567,7 +582,8 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 		char *owner_prog_type = get_fdinfo(fd, "owner_prog_type");
 		char *owner_jited = get_fdinfo(fd, "owner_jited");
 
-		printf("\n\t");
+		if (owner_prog_type || owner_jited)
+			printf("\n\t");
 		if (owner_prog_type) {
 			unsigned int prog_type = atoi(owner_prog_type);
 
@@ -577,10 +593,9 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 			else
 				printf("owner_prog_type %d  ", prog_type);
 		}
-		if (atoi(owner_jited))
-			printf("owner jited");
-		else
-			printf("owner not jited");
+		if (owner_jited)
+			printf("owner%s jited",
+			       atoi(owner_jited) ? "" : " not");
 
 		free(owner_prog_type);
 		free(owner_jited);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 0640e9bc0ada..33ed0806ccc0 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -78,13 +78,14 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 
 static int prog_fd_by_tag(unsigned char *tag)
 {
-	struct bpf_prog_info info = {};
-	__u32 len = sizeof(info);
 	unsigned int id = 0;
 	int err;
 	int fd;
 
 	while (true) {
+		struct bpf_prog_info info = {};
+		__u32 len = sizeof(info);
+
 		err = bpf_prog_get_next_id(id, &id);
 		if (err) {
 			p_err("%s", strerror(errno));
diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c
index 3040830d7797..84545666a09c 100644
--- a/tools/iio/iio_generic_buffer.c
+++ b/tools/iio/iio_generic_buffer.c
@@ -330,7 +330,7 @@ static const struct option longopts[] = {
 
 int main(int argc, char **argv)
 {
-	unsigned long long num_loops = 2;
+	long long num_loops = 2;
 	unsigned long timedelay = 1000000;
 	unsigned long buf_len = 128;
 
diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h
index fd92ce8388fc..57aaeaf8e192 100644
--- a/tools/include/uapi/asm/bitsperlong.h
+++ b/tools/include/uapi/asm/bitsperlong.h
@@ -15,6 +15,8 @@
 #include "../../arch/ia64/include/uapi/asm/bitsperlong.h"
 #elif defined(__riscv)
 #include "../../arch/riscv/include/uapi/asm/bitsperlong.h"
+#elif defined(__alpha__)
+#include "../../arch/alpha/include/uapi/asm/bitsperlong.h"
 #else
 #include <asm-generic/bitsperlong.h>
 #endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1777fa0c61e4..bcdd2474eee7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2016,6 +2016,19 @@ union bpf_attr {
  *			Only works if *skb* contains an IPv6 packet. Insert a
  *			Segment Routing Header (**struct ipv6_sr_hdr**) inside
  *			the IPv6 header.
+ *		**BPF_LWT_ENCAP_IP**
+ *			IP encapsulation (GRE/GUE/IPIP/etc). The outer header
+ *			must be IPv4 or IPv6, followed by zero or more
+ *			additional headers, up to LWT_BPF_MAX_HEADROOM total
+ *			bytes in all prepended headers. Please note that
+ *			if skb_is_gso(skb) is true, no more than two headers
+ *			can be prepended, and the inner header, if present,
+ *			should be either GRE or UDP/GUE.
+ *
+ *		BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of
+ *		type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called
+ *		by bpf programs of types BPF_PROG_TYPE_LWT_IN and
+ *		BPF_PROG_TYPE_LWT_XMIT.
  *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -2329,6 +2342,23 @@ union bpf_attr {
  *		"**y**".
  *	Return
  *		0
+ *
+ * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_sock** pointer such
+ *		that all the fields in bpf_sock can be accessed.
+ *	Return
+ *		A **struct bpf_sock** pointer on success, or NULL in
+ *		case of failure.
+ *
+ * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_tcp_sock** pointer from a
+ *		**struct bpf_sock** pointer.
+ *
+ *	Return
+ *		A **struct bpf_tcp_sock** pointer on success, or NULL in
+ *		case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2425,7 +2455,9 @@ union bpf_attr {
 	FN(msg_pop_data),		\
 	FN(rc_pointer_rel),		\
 	FN(spin_lock),			\
-	FN(spin_unlock),
+	FN(spin_unlock),		\
+	FN(sk_fullsock),		\
+	FN(tcp_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2498,7 +2530,8 @@ enum bpf_hdr_start_off {
 /* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
 enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6,
-	BPF_LWT_ENCAP_SEG6_INLINE
+	BPF_LWT_ENCAP_SEG6_INLINE,
+	BPF_LWT_ENCAP_IP,
 };
 
 #define __bpf_md_ptr(type, name)	\
@@ -2545,6 +2578,7 @@ struct __sk_buff {
 	__u64 tstamp;
 	__u32 wire_len;
 	__u32 gso_segs;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 struct bpf_tunnel_key {
@@ -2586,7 +2620,15 @@ enum bpf_ret_code {
 	BPF_DROP = 2,
 	/* 3-6 reserved */
 	BPF_REDIRECT = 7,
-	/* >127 are reserved for prog type specific return codes */
+	/* >127 are reserved for prog type specific return codes.
+	 *
+	 * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
+	 *    BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
+	 *    changed and should be routed based on its new L3 header.
+	 *    (This is an L3 redirect, as opposed to L2 redirect
+	 *    represented by BPF_REDIRECT above).
+	 */
+	BPF_LWT_REROUTE = 128,
 };
 
 struct bpf_sock {
@@ -2596,14 +2638,52 @@ struct bpf_sock {
 	__u32 protocol;
 	__u32 mark;
 	__u32 priority;
-	__u32 src_ip4;		/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	/* IP address also allows 1 and 2 bytes access */
+	__u32 src_ip4;
+	__u32 src_ip6[4];
+	__u32 src_port;		/* host byte order */
+	__u32 dst_port;		/* network byte order */
+	__u32 dst_ip4;
+	__u32 dst_ip6[4];
+	__u32 state;
+};
+
+struct bpf_tcp_sock {
+	__u32 snd_cwnd;		/* Sending congestion window		*/
+	__u32 srtt_us;		/* smoothed round trip time << 3 in usecs */
+	__u32 rtt_min;
+	__u32 snd_ssthresh;	/* Slow start size threshold		*/
+	__u32 rcv_nxt;		/* What we want to receive next		*/
+	__u32 snd_nxt;		/* Next sequence we send		*/
+	__u32 snd_una;		/* First byte we want an ack for	*/
+	__u32 mss_cache;	/* Cached effective mss, not including SACKS */
+	__u32 ecn_flags;	/* ECN status bits.			*/
+	__u32 rate_delivered;	/* saved rate sample: packets delivered */
+	__u32 rate_interval_us;	/* saved rate sample: time elapsed */
+	__u32 packets_out;	/* Packets which are "in flight"	*/
+	__u32 retrans_out;	/* Retransmitted packets out		*/
+	__u32 total_retrans;	/* Total retransmits for entire connection */
+	__u32 segs_in;		/* RFC4898 tcpEStatsPerfSegsIn
+				 * total number of segments in.
 				 */
-	__u32 src_ip6[4];	/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	__u32 data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
+				 * total number of data segments in.
+				 */
+	__u32 segs_out;		/* RFC4898 tcpEStatsPerfSegsOut
+				 * The total number of segments sent.
+				 */
+	__u32 data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
+				 * total number of data segments sent.
+				 */
+	__u32 lost_out;		/* Lost packets			*/
+	__u32 sacked_out;	/* SACK'd packets			*/
+	__u64 bytes_received;	/* RFC4898 tcpEStatsAppHCThruOctetsReceived
+				 * sum(delta(rcv_nxt)), or how many bytes
+				 * were acked.
 				 */
-	__u32 src_port;		/* Allows 4-byte read.
-				 * Stored in host byte order
+	__u64 bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
+				 * sum(delta(snd_una)), or how many bytes
+				 * were acked.
 				 */
 };
 
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index d6533828123a..5b225ff63b48 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -925,6 +925,7 @@ enum {
 enum {
 	LINK_XSTATS_TYPE_UNSPEC,
 	LINK_XSTATS_TYPE_BRIDGE,
+	LINK_XSTATS_TYPE_BOND,
 	__LINK_XSTATS_TYPE_MAX
 };
 #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index f6052e70bf40..a55cb8b10165 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -268,7 +268,7 @@ struct sockaddr_in {
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
 #define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_BADCLASS(a)		(((long int) (a) ) == (long int)0xffffffff)
 #define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
 
 #define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
index 6e89a5df49a4..653c4f94f76e 100644
--- a/tools/include/uapi/linux/tc_act/tc_bpf.h
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -13,8 +13,6 @@
 
 #include <linux/pkt_cls.h>
 
-#define TCA_ACT_BPF 13
-
 struct tc_act_bpf {
 	tc_gen;
 };
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3defad77dc7a..9cd015574e83 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -22,6 +22,7 @@
  */
 
 #include <stdlib.h>
+#include <string.h>
 #include <memory.h>
 #include <unistd.h>
 #include <asm/unistd.h>
@@ -214,23 +215,35 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 {
 	void *finfo = NULL, *linfo = NULL;
 	union bpf_attr attr;
+	__u32 log_level;
 	__u32 name_len;
 	int fd;
 
-	if (!load_attr)
+	if (!load_attr || !log_buf != !log_buf_sz)
+		return -EINVAL;
+
+	log_level = load_attr->log_level;
+	if (log_level > 2 || (log_level && !log_buf))
 		return -EINVAL;
 
 	name_len = load_attr->name ? strlen(load_attr->name) : 0;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
 	attr.insn_cnt = (__u32)load_attr->insns_cnt;
 	attr.insns = ptr_to_u64(load_attr->insns);
 	attr.license = ptr_to_u64(load_attr->license);
-	attr.log_buf = ptr_to_u64(NULL);
-	attr.log_size = 0;
-	attr.log_level = 0;
+
+	attr.log_level = log_level;
+	if (log_level) {
+		attr.log_buf = ptr_to_u64(log_buf);
+		attr.log_size = log_buf_sz;
+	} else {
+		attr.log_buf = ptr_to_u64(NULL);
+		attr.log_size = 0;
+	}
+
 	attr.kern_version = load_attr->kern_version;
 	attr.prog_ifindex = load_attr->prog_ifindex;
 	attr.prog_btf_fd = load_attr->prog_btf_fd;
@@ -286,7 +299,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 			goto done;
 	}
 
-	if (!log_buf || !log_buf_sz)
+	if (log_level || !log_buf)
 		goto done;
 
 	/* Try again with log */
@@ -327,7 +340,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = type;
 	attr.insn_cnt = (__u32)insns_cnt;
 	attr.insns = ptr_to_u64(insns);
@@ -347,7 +360,7 @@ int bpf_map_update_elem(int fd, const void *key, const void *value,
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -360,7 +373,7 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -372,7 +385,7 @@ int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -385,7 +398,7 @@ int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -397,7 +410,7 @@ int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 
@@ -408,7 +421,7 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.next_key = ptr_to_u64(next_key);
@@ -420,7 +433,7 @@ int bpf_obj_pin(int fd, const char *pathname)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.bpf_fd = fd;
 
@@ -431,7 +444,7 @@ int bpf_obj_get(const char *pathname)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 
 	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
@@ -442,7 +455,7 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	   = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type   = type;
@@ -455,7 +468,7 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_type = type;
 
@@ -466,7 +479,7 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type = type;
@@ -480,7 +493,7 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 	union bpf_attr attr;
 	int ret;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.query.target_fd	= target_fd;
 	attr.query.attach_type	= type;
 	attr.query.query_flags	= query_flags;
@@ -501,7 +514,7 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 	union bpf_attr attr;
 	int ret;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = prog_fd;
 	attr.test.data_in = ptr_to_u64(data);
 	attr.test.data_out = ptr_to_u64(data_out);
@@ -526,7 +539,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	if (!test_attr->data_out && test_attr->data_size_out > 0)
 		return -EINVAL;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = test_attr->prog_fd;
 	attr.test.data_in = ptr_to_u64(test_attr->data_in);
 	attr.test.data_out = ptr_to_u64(test_attr->data_out);
@@ -546,7 +559,7 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
 	union bpf_attr attr;
 	int err;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.start_id = start_id;
 
 	err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr));
@@ -561,7 +574,7 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
 	union bpf_attr attr;
 	int err;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.start_id = start_id;
 
 	err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr));
@@ -575,7 +588,7 @@ int bpf_prog_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.prog_id = id;
 
 	return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -585,7 +598,7 @@ int bpf_map_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_id = id;
 
 	return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -595,7 +608,7 @@ int bpf_btf_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.btf_id = id;
 
 	return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -606,7 +619,7 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
 	union bpf_attr attr;
 	int err;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.info.bpf_fd = prog_fd;
 	attr.info.info_len = *info_len;
 	attr.info.info = ptr_to_u64(info);
@@ -622,7 +635,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index ed09eed2dc3b..6ffdd79bea89 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -85,6 +85,7 @@ struct bpf_load_program_attr {
 	__u32 line_info_rec_size;
 	const void *line_info;
 	__u32 line_info_cnt;
+	__u32 log_level;
 };
 
 /* Flags to direct loading requirements */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d682d3b8f7b9..68b50e9bbde1 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
@@ -9,12 +10,14 @@
 #include <linux/btf.h>
 #include "btf.h"
 #include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_util.h"
 
-#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); }
 #define max(a, b) ((a) > (b) ? (a) : (b))
 #define min(a, b) ((a) < (b) ? (a) : (b))
 
-#define BTF_MAX_NR_TYPES 65535
+#define BTF_MAX_NR_TYPES 0x7fffffff
+#define BTF_MAX_STR_OFFSET 0x7fffffff
 
 #define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
 		((k) == BTF_KIND_VOLATILE) || \
@@ -39,9 +42,8 @@ struct btf {
 
 struct btf_ext_info {
 	/*
-	 * info points to a deep copy of the individual info section
-	 * (e.g. func_info and line_info) from the .BTF.ext.
-	 * It does not include the __u32 rec_size.
+	 * info points to the individual info section (e.g. func_info and
+	 * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
 	 */
 	void *info;
 	__u32 rec_size;
@@ -49,8 +51,13 @@ struct btf_ext_info {
 };
 
 struct btf_ext {
+	union {
+		struct btf_ext_header *hdr;
+		void *data;
+	};
 	struct btf_ext_info func_info;
 	struct btf_ext_info line_info;
+	__u32 data_size;
 };
 
 struct btf_ext_info_sec {
@@ -107,54 +114,54 @@ static int btf_add_type(struct btf *btf, struct btf_type *t)
 	return 0;
 }
 
-static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
+static int btf_parse_hdr(struct btf *btf)
 {
 	const struct btf_header *hdr = btf->hdr;
 	__u32 meta_left;
 
 	if (btf->data_size < sizeof(struct btf_header)) {
-		elog("BTF header not found\n");
+		pr_debug("BTF header not found\n");
 		return -EINVAL;
 	}
 
 	if (hdr->magic != BTF_MAGIC) {
-		elog("Invalid BTF magic:%x\n", hdr->magic);
+		pr_debug("Invalid BTF magic:%x\n", hdr->magic);
 		return -EINVAL;
 	}
 
 	if (hdr->version != BTF_VERSION) {
-		elog("Unsupported BTF version:%u\n", hdr->version);
+		pr_debug("Unsupported BTF version:%u\n", hdr->version);
 		return -ENOTSUP;
 	}
 
 	if (hdr->flags) {
-		elog("Unsupported BTF flags:%x\n", hdr->flags);
+		pr_debug("Unsupported BTF flags:%x\n", hdr->flags);
 		return -ENOTSUP;
 	}
 
 	meta_left = btf->data_size - sizeof(*hdr);
 	if (!meta_left) {
-		elog("BTF has no data\n");
+		pr_debug("BTF has no data\n");
 		return -EINVAL;
 	}
 
 	if (meta_left < hdr->type_off) {
-		elog("Invalid BTF type section offset:%u\n", hdr->type_off);
+		pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off);
 		return -EINVAL;
 	}
 
 	if (meta_left < hdr->str_off) {
-		elog("Invalid BTF string section offset:%u\n", hdr->str_off);
+		pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off);
 		return -EINVAL;
 	}
 
 	if (hdr->type_off >= hdr->str_off) {
-		elog("BTF type section offset >= string section offset. No type?\n");
+		pr_debug("BTF type section offset >= string section offset. No type?\n");
 		return -EINVAL;
 	}
 
 	if (hdr->type_off & 0x02) {
-		elog("BTF type section is not aligned to 4 bytes\n");
+		pr_debug("BTF type section is not aligned to 4 bytes\n");
 		return -EINVAL;
 	}
 
@@ -163,15 +170,15 @@ static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
 	return 0;
 }
 
-static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log)
+static int btf_parse_str_sec(struct btf *btf)
 {
 	const struct btf_header *hdr = btf->hdr;
 	const char *start = btf->nohdr_data + hdr->str_off;
 	const char *end = start + btf->hdr->str_len;
 
-	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
+	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET ||
 	    start[0] || end[-1]) {
-		elog("Invalid BTF string section\n");
+		pr_debug("Invalid BTF string section\n");
 		return -EINVAL;
 	}
 
@@ -180,7 +187,38 @@ static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log)
 	return 0;
 }
 
-static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
+static int btf_type_size(struct btf_type *t)
+{
+	int base_size = sizeof(struct btf_type);
+	__u16 vlen = BTF_INFO_VLEN(t->info);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_FWD:
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_FUNC:
+		return base_size;
+	case BTF_KIND_INT:
+		return base_size + sizeof(__u32);
+	case BTF_KIND_ENUM:
+		return base_size + vlen * sizeof(struct btf_enum);
+	case BTF_KIND_ARRAY:
+		return base_size + sizeof(struct btf_array);
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		return base_size + vlen * sizeof(struct btf_member);
+	case BTF_KIND_FUNC_PROTO:
+		return base_size + vlen * sizeof(struct btf_param);
+	default:
+		pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info));
+		return -EINVAL;
+	}
+}
+
+static int btf_parse_type_sec(struct btf *btf)
 {
 	struct btf_header *hdr = btf->hdr;
 	void *nohdr_data = btf->nohdr_data;
@@ -189,41 +227,13 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 
 	while (next_type < end_type) {
 		struct btf_type *t = next_type;
-		__u16 vlen = BTF_INFO_VLEN(t->info);
+		int type_size;
 		int err;
 
-		next_type += sizeof(*t);
-		switch (BTF_INFO_KIND(t->info)) {
-		case BTF_KIND_INT:
-			next_type += sizeof(int);
-			break;
-		case BTF_KIND_ARRAY:
-			next_type += sizeof(struct btf_array);
-			break;
-		case BTF_KIND_STRUCT:
-		case BTF_KIND_UNION:
-			next_type += vlen * sizeof(struct btf_member);
-			break;
-		case BTF_KIND_ENUM:
-			next_type += vlen * sizeof(struct btf_enum);
-			break;
-		case BTF_KIND_FUNC_PROTO:
-			next_type += vlen * sizeof(struct btf_param);
-			break;
-		case BTF_KIND_FUNC:
-		case BTF_KIND_TYPEDEF:
-		case BTF_KIND_PTR:
-		case BTF_KIND_FWD:
-		case BTF_KIND_VOLATILE:
-		case BTF_KIND_CONST:
-		case BTF_KIND_RESTRICT:
-			break;
-		default:
-			elog("Unsupported BTF_KIND:%u\n",
-			     BTF_INFO_KIND(t->info));
-			return -EINVAL;
-		}
-
+		type_size = btf_type_size(t);
+		if (type_size < 0)
+			return type_size;
+		next_type += type_size;
 		err = btf_add_type(btf, t);
 		if (err)
 			return err;
@@ -232,6 +242,11 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 	return 0;
 }
 
+__u32 btf__get_nr_types(const struct btf *btf)
+{
+	return btf->nr_types;
+}
+
 const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id > btf->nr_types)
@@ -250,21 +265,6 @@ static bool btf_type_is_void_or_null(const struct btf_type *t)
 	return !t || btf_type_is_void(t);
 }
 
-static __s64 btf_type_size(const struct btf_type *t)
-{
-	switch (BTF_INFO_KIND(t->info)) {
-	case BTF_KIND_INT:
-	case BTF_KIND_STRUCT:
-	case BTF_KIND_UNION:
-	case BTF_KIND_ENUM:
-		return t->size;
-	case BTF_KIND_PTR:
-		return sizeof(void *);
-	default:
-		return -EINVAL;
-	}
-}
-
 #define MAX_RESOLVE_DEPTH 32
 
 __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
@@ -278,11 +278,16 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 	t = btf__type_by_id(btf, type_id);
 	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
 	     i++) {
-		size = btf_type_size(t);
-		if (size >= 0)
-			break;
-
 		switch (BTF_INFO_KIND(t->info)) {
+		case BTF_KIND_INT:
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+		case BTF_KIND_ENUM:
+			size = t->size;
+			goto done;
+		case BTF_KIND_PTR:
+			size = sizeof(void *);
+			goto done;
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_VOLATILE:
 		case BTF_KIND_CONST:
@@ -306,6 +311,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 	if (size < 0)
 		return -EINVAL;
 
+done:
 	if (nelems && size > UINT32_MAX / nelems)
 		return -E2BIG;
 
@@ -363,10 +369,8 @@ void btf__free(struct btf *btf)
 	free(btf);
 }
 
-struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
+struct btf *btf__new(__u8 *data, __u32 size)
 {
-	__u32 log_buf_size = 0;
-	char *log_buf = NULL;
 	struct btf *btf;
 	int err;
 
@@ -376,16 +380,6 @@ struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 
 	btf->fd = -1;
 
-	if (err_log) {
-		log_buf = malloc(BPF_LOG_BUF_SIZE);
-		if (!log_buf) {
-			err = -ENOMEM;
-			goto done;
-		}
-		*log_buf = 0;
-		log_buf_size = BPF_LOG_BUF_SIZE;
-	}
-
 	btf->data = malloc(size);
 	if (!btf->data) {
 		err = -ENOMEM;
@@ -395,30 +389,17 @@ struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 	memcpy(btf->data, data, size);
 	btf->data_size = size;
 
-	btf->fd = bpf_load_btf(btf->data, btf->data_size,
-			       log_buf, log_buf_size, false);
-
-	if (btf->fd == -1) {
-		err = -errno;
-		elog("Error loading BTF: %s(%d)\n", strerror(errno), errno);
-		if (log_buf && *log_buf)
-			elog("%s\n", log_buf);
-		goto done;
-	}
-
-	err = btf_parse_hdr(btf, err_log);
+	err = btf_parse_hdr(btf);
 	if (err)
 		goto done;
 
-	err = btf_parse_str_sec(btf, err_log);
+	err = btf_parse_str_sec(btf);
 	if (err)
 		goto done;
 
-	err = btf_parse_type_sec(btf, err_log);
+	err = btf_parse_type_sec(btf);
 
 done:
-	free(log_buf);
-
 	if (err) {
 		btf__free(btf);
 		return ERR_PTR(err);
@@ -427,11 +408,47 @@ done:
 	return btf;
 }
 
+int btf__load(struct btf *btf)
+{
+	__u32 log_buf_size = BPF_LOG_BUF_SIZE;
+	char *log_buf = NULL;
+	int err = 0;
+
+	if (btf->fd >= 0)
+		return -EEXIST;
+
+	log_buf = malloc(log_buf_size);
+	if (!log_buf)
+		return -ENOMEM;
+
+	*log_buf = 0;
+
+	btf->fd = bpf_load_btf(btf->data, btf->data_size,
+			       log_buf, log_buf_size, false);
+	if (btf->fd < 0) {
+		err = -errno;
+		pr_warning("Error loading BTF: %s(%d)\n", strerror(errno), errno);
+		if (*log_buf)
+			pr_warning("%s\n", log_buf);
+		goto done;
+	}
+
+done:
+	free(log_buf);
+	return err;
+}
+
 int btf__fd(const struct btf *btf)
 {
 	return btf->fd;
 }
 
+const void *btf__get_raw_data(const struct btf *btf, __u32 *size)
+{
+	*size = btf->data_size;
+	return btf->data;
+}
+
 const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->hdr->str_len)
@@ -467,7 +484,7 @@ int btf__get_from_id(__u32 id, struct btf **btf)
 		goto exit_free;
 	}
 
-	bzero(ptr, last_size);
+	memset(ptr, 0, last_size);
 	btf_info.btf = ptr_to_u64(ptr);
 	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
 
@@ -481,7 +498,7 @@ int btf__get_from_id(__u32 id, struct btf **btf)
 			goto exit_free;
 		}
 		ptr = temp_ptr;
-		bzero(ptr, last_size);
+		memset(ptr, 0, last_size);
 		btf_info.btf = ptr_to_u64(ptr);
 		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
 	}
@@ -491,7 +508,7 @@ int btf__get_from_id(__u32 id, struct btf **btf)
 		goto exit_free;
 	}
 
-	*btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size, NULL);
+	*btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size);
 	if (IS_ERR(*btf)) {
 		err = PTR_ERR(*btf);
 		*btf = NULL;
@@ -504,7 +521,79 @@ exit_free:
 	return err;
 }
 
-struct btf_ext_sec_copy_param {
+int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
+			 __u32 expected_key_size, __u32 expected_value_size,
+			 __u32 *key_type_id, __u32 *value_type_id)
+{
+	const struct btf_type *container_type;
+	const struct btf_member *key, *value;
+	const size_t max_name = 256;
+	char container_name[max_name];
+	__s64 key_size, value_size;
+	__s32 container_id;
+
+	if (snprintf(container_name, max_name, "____btf_map_%s", map_name) ==
+	    max_name) {
+		pr_warning("map:%s length of '____btf_map_%s' is too long\n",
+			   map_name, map_name);
+		return -EINVAL;
+	}
+
+	container_id = btf__find_by_name(btf, container_name);
+	if (container_id < 0) {
+		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
+			 map_name, container_name);
+		return container_id;
+	}
+
+	container_type = btf__type_by_id(btf, container_id);
+	if (!container_type) {
+		pr_warning("map:%s cannot find BTF type for container_id:%u\n",
+			   map_name, container_id);
+		return -EINVAL;
+	}
+
+	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
+	    BTF_INFO_VLEN(container_type->info) < 2) {
+		pr_warning("map:%s container_name:%s is an invalid container struct\n",
+			   map_name, container_name);
+		return -EINVAL;
+	}
+
+	key = (struct btf_member *)(container_type + 1);
+	value = key + 1;
+
+	key_size = btf__resolve_size(btf, key->type);
+	if (key_size < 0) {
+		pr_warning("map:%s invalid BTF key_type_size\n", map_name);
+		return key_size;
+	}
+
+	if (expected_key_size != key_size) {
+		pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
+			   map_name, (__u32)key_size, expected_key_size);
+		return -EINVAL;
+	}
+
+	value_size = btf__resolve_size(btf, value->type);
+	if (value_size < 0) {
+		pr_warning("map:%s invalid BTF value_type_size\n", map_name);
+		return value_size;
+	}
+
+	if (expected_value_size != value_size) {
+		pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
+			   map_name, (__u32)value_size, expected_value_size);
+		return -EINVAL;
+	}
+
+	*key_type_id = key->type;
+	*value_type_id = value->type;
+
+	return 0;
+}
+
+struct btf_ext_sec_setup_param {
 	__u32 off;
 	__u32 len;
 	__u32 min_rec_size;
@@ -512,41 +601,33 @@ struct btf_ext_sec_copy_param {
 	const char *desc;
 };
 
-static int btf_ext_copy_info(struct btf_ext *btf_ext,
-			     __u8 *data, __u32 data_size,
-			     struct btf_ext_sec_copy_param *ext_sec,
-			     btf_print_fn_t err_log)
+static int btf_ext_setup_info(struct btf_ext *btf_ext,
+			      struct btf_ext_sec_setup_param *ext_sec)
 {
-	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
 	const struct btf_ext_info_sec *sinfo;
 	struct btf_ext_info *ext_info;
 	__u32 info_left, record_size;
 	/* The start of the info sec (including the __u32 record_size). */
-	const void *info;
-
-	/* data and data_size do not include btf_ext_header from now on */
-	data = data + hdr->hdr_len;
-	data_size -= hdr->hdr_len;
+	void *info;
 
 	if (ext_sec->off & 0x03) {
-		elog(".BTF.ext %s section is not aligned to 4 bytes\n",
+		pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n",
 		     ext_sec->desc);
 		return -EINVAL;
 	}
 
-	if (data_size < ext_sec->off ||
-	    ext_sec->len > data_size - ext_sec->off) {
-		elog("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n",
-		     ext_sec->desc, ext_sec->off, ext_sec->len);
+	info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off;
+	info_left = ext_sec->len;
+
+	if (btf_ext->data + btf_ext->data_size < info + ext_sec->len) {
+		pr_debug("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n",
+			 ext_sec->desc, ext_sec->off, ext_sec->len);
 		return -EINVAL;
 	}
 
-	info = data + ext_sec->off;
-	info_left = ext_sec->len;
-
 	/* At least a record size */
 	if (info_left < sizeof(__u32)) {
-		elog(".BTF.ext %s record size not found\n", ext_sec->desc);
+		pr_debug(".BTF.ext %s record size not found\n", ext_sec->desc);
 		return -EINVAL;
 	}
 
@@ -554,8 +635,8 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext,
 	record_size = *(__u32 *)info;
 	if (record_size < ext_sec->min_rec_size ||
 	    record_size & 0x03) {
-		elog("%s section in .BTF.ext has invalid record size %u\n",
-		     ext_sec->desc, record_size);
+		pr_debug("%s section in .BTF.ext has invalid record size %u\n",
+			 ext_sec->desc, record_size);
 		return -EINVAL;
 	}
 
@@ -564,7 +645,7 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext,
 
 	/* If no records, return failure now so .BTF.ext won't be used. */
 	if (!info_left) {
-		elog("%s section in .BTF.ext has no records", ext_sec->desc);
+		pr_debug("%s section in .BTF.ext has no records", ext_sec->desc);
 		return -EINVAL;
 	}
 
@@ -574,14 +655,14 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext,
 		__u32 num_records;
 
 		if (info_left < sec_hdrlen) {
-			elog("%s section header is not found in .BTF.ext\n",
+			pr_debug("%s section header is not found in .BTF.ext\n",
 			     ext_sec->desc);
 			return -EINVAL;
 		}
 
 		num_records = sinfo->num_info;
 		if (num_records == 0) {
-			elog("%s section has incorrect num_records in .BTF.ext\n",
+			pr_debug("%s section has incorrect num_records in .BTF.ext\n",
 			     ext_sec->desc);
 			return -EINVAL;
 		}
@@ -589,7 +670,7 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext,
 		total_record_size = sec_hdrlen +
 				    (__u64)num_records * record_size;
 		if (info_left < total_record_size) {
-			elog("%s section has incorrect num_records in .BTF.ext\n",
+			pr_debug("%s section has incorrect num_records in .BTF.ext\n",
 			     ext_sec->desc);
 			return -EINVAL;
 		}
@@ -601,74 +682,64 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext,
 	ext_info = ext_sec->ext_info;
 	ext_info->len = ext_sec->len - sizeof(__u32);
 	ext_info->rec_size = record_size;
-	ext_info->info = malloc(ext_info->len);
-	if (!ext_info->info)
-		return -ENOMEM;
-	memcpy(ext_info->info, info + sizeof(__u32), ext_info->len);
+	ext_info->info = info + sizeof(__u32);
 
 	return 0;
 }
 
-static int btf_ext_copy_func_info(struct btf_ext *btf_ext,
-				  __u8 *data, __u32 data_size,
-				  btf_print_fn_t err_log)
+static int btf_ext_setup_func_info(struct btf_ext *btf_ext)
 {
-	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
-	struct btf_ext_sec_copy_param param = {
-		.off = hdr->func_info_off,
-		.len = hdr->func_info_len,
+	struct btf_ext_sec_setup_param param = {
+		.off = btf_ext->hdr->func_info_off,
+		.len = btf_ext->hdr->func_info_len,
 		.min_rec_size = sizeof(struct bpf_func_info_min),
 		.ext_info = &btf_ext->func_info,
 		.desc = "func_info"
 	};
 
-	return btf_ext_copy_info(btf_ext, data, data_size, &param, err_log);
+	return btf_ext_setup_info(btf_ext, &param);
 }
 
-static int btf_ext_copy_line_info(struct btf_ext *btf_ext,
-				  __u8 *data, __u32 data_size,
-				  btf_print_fn_t err_log)
+static int btf_ext_setup_line_info(struct btf_ext *btf_ext)
 {
-	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
-	struct btf_ext_sec_copy_param param = {
-		.off = hdr->line_info_off,
-		.len = hdr->line_info_len,
+	struct btf_ext_sec_setup_param param = {
+		.off = btf_ext->hdr->line_info_off,
+		.len = btf_ext->hdr->line_info_len,
 		.min_rec_size = sizeof(struct bpf_line_info_min),
 		.ext_info = &btf_ext->line_info,
 		.desc = "line_info",
 	};
 
-	return btf_ext_copy_info(btf_ext, data, data_size, &param, err_log);
+	return btf_ext_setup_info(btf_ext, &param);
 }
 
-static int btf_ext_parse_hdr(__u8 *data, __u32 data_size,
-			     btf_print_fn_t err_log)
+static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
 {
 	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
 
 	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
 	    data_size < hdr->hdr_len) {
-		elog("BTF.ext header not found");
+		pr_debug("BTF.ext header not found");
 		return -EINVAL;
 	}
 
 	if (hdr->magic != BTF_MAGIC) {
-		elog("Invalid BTF.ext magic:%x\n", hdr->magic);
+		pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic);
 		return -EINVAL;
 	}
 
 	if (hdr->version != BTF_VERSION) {
-		elog("Unsupported BTF.ext version:%u\n", hdr->version);
+		pr_debug("Unsupported BTF.ext version:%u\n", hdr->version);
 		return -ENOTSUP;
 	}
 
 	if (hdr->flags) {
-		elog("Unsupported BTF.ext flags:%x\n", hdr->flags);
+		pr_debug("Unsupported BTF.ext flags:%x\n", hdr->flags);
 		return -ENOTSUP;
 	}
 
 	if (data_size == hdr->hdr_len) {
-		elog("BTF.ext has no data\n");
+		pr_debug("BTF.ext has no data\n");
 		return -EINVAL;
 	}
 
@@ -679,18 +750,16 @@ void btf_ext__free(struct btf_ext *btf_ext)
 {
 	if (!btf_ext)
 		return;
-
-	free(btf_ext->func_info.info);
-	free(btf_ext->line_info.info);
+	free(btf_ext->data);
 	free(btf_ext);
 }
 
-struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 {
 	struct btf_ext *btf_ext;
 	int err;
 
-	err = btf_ext_parse_hdr(data, size, err_log);
+	err = btf_ext_parse_hdr(data, size);
 	if (err)
 		return ERR_PTR(err);
 
@@ -698,13 +767,23 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 	if (!btf_ext)
 		return ERR_PTR(-ENOMEM);
 
-	err = btf_ext_copy_func_info(btf_ext, data, size, err_log);
-	if (err) {
-		btf_ext__free(btf_ext);
-		return ERR_PTR(err);
+	btf_ext->data_size = size;
+	btf_ext->data = malloc(size);
+	if (!btf_ext->data) {
+		err = -ENOMEM;
+		goto done;
 	}
+	memcpy(btf_ext->data, data, size);
 
-	err = btf_ext_copy_line_info(btf_ext, data, size, err_log);
+	err = btf_ext_setup_func_info(btf_ext);
+	if (err)
+		goto done;
+
+	err = btf_ext_setup_line_info(btf_ext);
+	if (err)
+		goto done;
+
+done:
 	if (err) {
 		btf_ext__free(btf_ext);
 		return ERR_PTR(err);
@@ -713,6 +792,12 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
 	return btf_ext;
 }
 
+const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size)
+{
+	*size = btf_ext->data_size;
+	return btf_ext->data;
+}
+
 static int btf_ext_reloc_info(const struct btf *btf,
 			      const struct btf_ext_info *ext_info,
 			      const char *sec_name, __u32 insns_cnt,
@@ -761,7 +846,8 @@ static int btf_ext_reloc_info(const struct btf *btf,
 	return -ENOENT;
 }
 
-int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ext,
+int btf_ext__reloc_func_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
 			     const char *sec_name, __u32 insns_cnt,
 			     void **func_info, __u32 *cnt)
 {
@@ -769,7 +855,8 @@ int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ex
 				  insns_cnt, func_info, cnt);
 }
 
-int btf_ext__reloc_line_info(const struct btf *btf, const struct btf_ext *btf_ext,
+int btf_ext__reloc_line_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
 			     const char *sec_name, __u32 insns_cnt,
 			     void **line_info, __u32 *cnt)
 {
@@ -786,3 +873,1744 @@ __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext)
 {
 	return btf_ext->line_info.rec_size;
 }
+
+struct btf_dedup;
+
+static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
+				       const struct btf_dedup_opts *opts);
+static void btf_dedup_free(struct btf_dedup *d);
+static int btf_dedup_strings(struct btf_dedup *d);
+static int btf_dedup_prim_types(struct btf_dedup *d);
+static int btf_dedup_struct_types(struct btf_dedup *d);
+static int btf_dedup_ref_types(struct btf_dedup *d);
+static int btf_dedup_compact_types(struct btf_dedup *d);
+static int btf_dedup_remap_types(struct btf_dedup *d);
+
+/*
+ * Deduplicate BTF types and strings.
+ *
+ * BTF dedup algorithm takes as an input `struct btf` representing `.BTF` ELF
+ * section with all BTF type descriptors and string data. It overwrites that
+ * memory in-place with deduplicated types and strings without any loss of
+ * information. If optional `struct btf_ext` representing '.BTF.ext' ELF section
+ * is provided, all the strings referenced from .BTF.ext section are honored
+ * and updated to point to the right offsets after deduplication.
+ *
+ * If function returns with error, type/string data might be garbled and should
+ * be discarded.
+ *
+ * More verbose and detailed description of both problem btf_dedup is solving,
+ * as well as solution could be found at:
+ * https://facebookmicrosites.github.io/bpf/blog/2018/11/14/btf-enhancement.html
+ *
+ * Problem description and justification
+ * =====================================
+ *
+ * BTF type information is typically emitted either as a result of conversion
+ * from DWARF to BTF or directly by compiler. In both cases, each compilation
+ * unit contains information about a subset of all the types that are used
+ * in an application. These subsets are frequently overlapping and contain a lot
+ * of duplicated information when later concatenated together into a single
+ * binary. This algorithm ensures that each unique type is represented by single
+ * BTF type descriptor, greatly reducing resulting size of BTF data.
+ *
+ * Compilation unit isolation and subsequent duplication of data is not the only
+ * problem. The same type hierarchy (e.g., struct and all the type that struct
+ * references) in different compilation units can be represented in BTF to
+ * various degrees of completeness (or, rather, incompleteness) due to
+ * struct/union forward declarations.
+ *
+ * Let's take a look at an example, that we'll use to better understand the
+ * problem (and solution). Suppose we have two compilation units, each using
+ * same `struct S`, but each of them having incomplete type information about
+ * struct's fields:
+ *
+ * // CU #1:
+ * struct S;
+ * struct A {
+ *	int a;
+ *	struct A* self;
+ *	struct S* parent;
+ * };
+ * struct B;
+ * struct S {
+ *	struct A* a_ptr;
+ *	struct B* b_ptr;
+ * };
+ *
+ * // CU #2:
+ * struct S;
+ * struct A;
+ * struct B {
+ *	int b;
+ *	struct B* self;
+ *	struct S* parent;
+ * };
+ * struct S {
+ *	struct A* a_ptr;
+ *	struct B* b_ptr;
+ * };
+ *
+ * In case of CU #1, BTF data will know only that `struct B` exist (but no
+ * more), but will know the complete type information about `struct A`. While
+ * for CU #2, it will know full type information about `struct B`, but will
+ * only know about forward declaration of `struct A` (in BTF terms, it will
+ * have `BTF_KIND_FWD` type descriptor with name `B`).
+ *
+ * This compilation unit isolation means that it's possible that there is no
+ * single CU with complete type information describing structs `S`, `A`, and
+ * `B`. Also, we might get tons of duplicated and redundant type information.
+ *
+ * Additional complication we need to keep in mind comes from the fact that
+ * types, in general, can form graphs containing cycles, not just DAGs.
+ *
+ * While algorithm does deduplication, it also merges and resolves type
+ * information (unless disabled throught `struct btf_opts`), whenever possible.
+ * E.g., in the example above with two compilation units having partial type
+ * information for structs `A` and `B`, the output of algorithm will emit
+ * a single copy of each BTF type that describes structs `A`, `B`, and `S`
+ * (as well as type information for `int` and pointers), as if they were defined
+ * in a single compilation unit as:
+ *
+ * struct A {
+ *	int a;
+ *	struct A* self;
+ *	struct S* parent;
+ * };
+ * struct B {
+ *	int b;
+ *	struct B* self;
+ *	struct S* parent;
+ * };
+ * struct S {
+ *	struct A* a_ptr;
+ *	struct B* b_ptr;
+ * };
+ *
+ * Algorithm summary
+ * =================
+ *
+ * Algorithm completes its work in 6 separate passes:
+ *
+ * 1. Strings deduplication.
+ * 2. Primitive types deduplication (int, enum, fwd).
+ * 3. Struct/union types deduplication.
+ * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func
+ *    protos, and const/volatile/restrict modifiers).
+ * 5. Types compaction.
+ * 6. Types remapping.
+ *
+ * Algorithm determines canonical type descriptor, which is a single
+ * representative type for each truly unique type. This canonical type is the
+ * one that will go into final deduplicated BTF type information. For
+ * struct/unions, it is also the type that algorithm will merge additional type
+ * information into (while resolving FWDs), as it discovers it from data in
+ * other CUs. Each input BTF type eventually gets either mapped to itself, if
+ * that type is canonical, or to some other type, if that type is equivalent
+ * and was chosen as canonical representative. This mapping is stored in
+ * `btf_dedup->map` array. This map is also used to record STRUCT/UNION that
+ * FWD type got resolved to.
+ *
+ * To facilitate fast discovery of canonical types, we also maintain canonical
+ * index (`btf_dedup->dedup_table`), which maps type descriptor's signature hash
+ * (i.e., hashed kind, name, size, fields, etc) into a list of canonical types
+ * that match that signature. With sufficiently good choice of type signature
+ * hashing function, we can limit number of canonical types for each unique type
+ * signature to a very small number, allowing to find canonical type for any
+ * duplicated type very quickly.
+ *
+ * Struct/union deduplication is the most critical part and algorithm for
+ * deduplicating structs/unions is described in greater details in comments for
+ * `btf_dedup_is_equiv` function.
+ */
+int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
+	       const struct btf_dedup_opts *opts)
+{
+	struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts);
+	int err;
+
+	if (IS_ERR(d)) {
+		pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
+		return -EINVAL;
+	}
+
+	err = btf_dedup_strings(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_strings failed:%d\n", err);
+		goto done;
+	}
+	err = btf_dedup_prim_types(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_prim_types failed:%d\n", err);
+		goto done;
+	}
+	err = btf_dedup_struct_types(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_struct_types failed:%d\n", err);
+		goto done;
+	}
+	err = btf_dedup_ref_types(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_ref_types failed:%d\n", err);
+		goto done;
+	}
+	err = btf_dedup_compact_types(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_compact_types failed:%d\n", err);
+		goto done;
+	}
+	err = btf_dedup_remap_types(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_remap_types failed:%d\n", err);
+		goto done;
+	}
+
+done:
+	btf_dedup_free(d);
+	return err;
+}
+
+#define BTF_DEDUP_TABLE_SIZE_LOG 14
+#define BTF_DEDUP_TABLE_MOD ((1 << BTF_DEDUP_TABLE_SIZE_LOG) - 1)
+#define BTF_UNPROCESSED_ID ((__u32)-1)
+#define BTF_IN_PROGRESS_ID ((__u32)-2)
+
+struct btf_dedup_node {
+	struct btf_dedup_node *next;
+	__u32 type_id;
+};
+
+struct btf_dedup {
+	/* .BTF section to be deduped in-place */
+	struct btf *btf;
+	/*
+	 * Optional .BTF.ext section. When provided, any strings referenced
+	 * from it will be taken into account when deduping strings
+	 */
+	struct btf_ext *btf_ext;
+	/*
+	 * This is a map from any type's signature hash to a list of possible
+	 * canonical representative type candidates. Hash collisions are
+	 * ignored, so even types of various kinds can share same list of
+	 * candidates, which is fine because we rely on subsequent
+	 * btf_xxx_equal() checks to authoritatively verify type equality.
+	 */
+	struct btf_dedup_node **dedup_table;
+	/* Canonical types map */
+	__u32 *map;
+	/* Hypothetical mapping, used during type graph equivalence checks */
+	__u32 *hypot_map;
+	__u32 *hypot_list;
+	size_t hypot_cnt;
+	size_t hypot_cap;
+	/* Various option modifying behavior of algorithm */
+	struct btf_dedup_opts opts;
+};
+
+struct btf_str_ptr {
+	const char *str;
+	__u32 new_off;
+	bool used;
+};
+
+struct btf_str_ptrs {
+	struct btf_str_ptr *ptrs;
+	const char *data;
+	__u32 cnt;
+	__u32 cap;
+};
+
+static inline __u32 hash_combine(__u32 h, __u32 value)
+{
+/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
+#define GOLDEN_RATIO_PRIME 0x9e370001UL
+	return h * 37 + value * GOLDEN_RATIO_PRIME;
+#undef GOLDEN_RATIO_PRIME
+}
+
+#define for_each_hash_node(table, hash, node) \
+	for (node = table[hash & BTF_DEDUP_TABLE_MOD]; node; node = node->next)
+
+static int btf_dedup_table_add(struct btf_dedup *d, __u32 hash, __u32 type_id)
+{
+	struct btf_dedup_node *node = malloc(sizeof(struct btf_dedup_node));
+
+	if (!node)
+		return -ENOMEM;
+	node->type_id = type_id;
+	node->next = d->dedup_table[hash & BTF_DEDUP_TABLE_MOD];
+	d->dedup_table[hash & BTF_DEDUP_TABLE_MOD] = node;
+	return 0;
+}
+
+static int btf_dedup_hypot_map_add(struct btf_dedup *d,
+				   __u32 from_id, __u32 to_id)
+{
+	if (d->hypot_cnt == d->hypot_cap) {
+		__u32 *new_list;
+
+		d->hypot_cap += max(16, d->hypot_cap / 2);
+		new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap);
+		if (!new_list)
+			return -ENOMEM;
+		d->hypot_list = new_list;
+	}
+	d->hypot_list[d->hypot_cnt++] = from_id;
+	d->hypot_map[from_id] = to_id;
+	return 0;
+}
+
+static void btf_dedup_clear_hypot_map(struct btf_dedup *d)
+{
+	int i;
+
+	for (i = 0; i < d->hypot_cnt; i++)
+		d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID;
+	d->hypot_cnt = 0;
+}
+
+static void btf_dedup_table_free(struct btf_dedup *d)
+{
+	struct btf_dedup_node *head, *tmp;
+	int i;
+
+	if (!d->dedup_table)
+		return;
+
+	for (i = 0; i < (1 << BTF_DEDUP_TABLE_SIZE_LOG); i++) {
+		while (d->dedup_table[i]) {
+			tmp = d->dedup_table[i];
+			d->dedup_table[i] = tmp->next;
+			free(tmp);
+		}
+
+		head = d->dedup_table[i];
+		while (head) {
+			tmp = head;
+			head = head->next;
+			free(tmp);
+		}
+	}
+
+	free(d->dedup_table);
+	d->dedup_table = NULL;
+}
+
+static void btf_dedup_free(struct btf_dedup *d)
+{
+	btf_dedup_table_free(d);
+
+	free(d->map);
+	d->map = NULL;
+
+	free(d->hypot_map);
+	d->hypot_map = NULL;
+
+	free(d->hypot_list);
+	d->hypot_list = NULL;
+
+	free(d);
+}
+
+static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
+				       const struct btf_dedup_opts *opts)
+{
+	struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup));
+	int i, err = 0;
+
+	if (!d)
+		return ERR_PTR(-ENOMEM);
+
+	d->btf = btf;
+	d->btf_ext = btf_ext;
+
+	d->dedup_table = calloc(1 << BTF_DEDUP_TABLE_SIZE_LOG,
+				sizeof(struct btf_dedup_node *));
+	if (!d->dedup_table) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	d->map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+	if (!d->map) {
+		err = -ENOMEM;
+		goto done;
+	}
+	/* special BTF "void" type is made canonical immediately */
+	d->map[0] = 0;
+	for (i = 1; i <= btf->nr_types; i++)
+		d->map[i] = BTF_UNPROCESSED_ID;
+
+	d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types));
+	if (!d->hypot_map) {
+		err = -ENOMEM;
+		goto done;
+	}
+	for (i = 0; i <= btf->nr_types; i++)
+		d->hypot_map[i] = BTF_UNPROCESSED_ID;
+
+	d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds;
+
+done:
+	if (err) {
+		btf_dedup_free(d);
+		return ERR_PTR(err);
+	}
+
+	return d;
+}
+
+typedef int (*str_off_fn_t)(__u32 *str_off_ptr, void *ctx);
+
+/*
+ * Iterate over all possible places in .BTF and .BTF.ext that can reference
+ * string and pass pointer to it to a provided callback `fn`.
+ */
+static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
+{
+	void *line_data_cur, *line_data_end;
+	int i, j, r, rec_size;
+	struct btf_type *t;
+
+	for (i = 1; i <= d->btf->nr_types; i++) {
+		t = d->btf->types[i];
+		r = fn(&t->name_off, ctx);
+		if (r)
+			return r;
+
+		switch (BTF_INFO_KIND(t->info)) {
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION: {
+			struct btf_member *m = (struct btf_member *)(t + 1);
+			__u16 vlen = BTF_INFO_VLEN(t->info);
+
+			for (j = 0; j < vlen; j++) {
+				r = fn(&m->name_off, ctx);
+				if (r)
+					return r;
+				m++;
+			}
+			break;
+		}
+		case BTF_KIND_ENUM: {
+			struct btf_enum *m = (struct btf_enum *)(t + 1);
+			__u16 vlen = BTF_INFO_VLEN(t->info);
+
+			for (j = 0; j < vlen; j++) {
+				r = fn(&m->name_off, ctx);
+				if (r)
+					return r;
+				m++;
+			}
+			break;
+		}
+		case BTF_KIND_FUNC_PROTO: {
+			struct btf_param *m = (struct btf_param *)(t + 1);
+			__u16 vlen = BTF_INFO_VLEN(t->info);
+
+			for (j = 0; j < vlen; j++) {
+				r = fn(&m->name_off, ctx);
+				if (r)
+					return r;
+				m++;
+			}
+			break;
+		}
+		default:
+			break;
+		}
+	}
+
+	if (!d->btf_ext)
+		return 0;
+
+	line_data_cur = d->btf_ext->line_info.info;
+	line_data_end = d->btf_ext->line_info.info + d->btf_ext->line_info.len;
+	rec_size = d->btf_ext->line_info.rec_size;
+
+	while (line_data_cur < line_data_end) {
+		struct btf_ext_info_sec *sec = line_data_cur;
+		struct bpf_line_info_min *line_info;
+		__u32 num_info = sec->num_info;
+
+		r = fn(&sec->sec_name_off, ctx);
+		if (r)
+			return r;
+
+		line_data_cur += sizeof(struct btf_ext_info_sec);
+		for (i = 0; i < num_info; i++) {
+			line_info = line_data_cur;
+			r = fn(&line_info->file_name_off, ctx);
+			if (r)
+				return r;
+			r = fn(&line_info->line_off, ctx);
+			if (r)
+				return r;
+			line_data_cur += rec_size;
+		}
+	}
+
+	return 0;
+}
+
+static int str_sort_by_content(const void *a1, const void *a2)
+{
+	const struct btf_str_ptr *p1 = a1;
+	const struct btf_str_ptr *p2 = a2;
+
+	return strcmp(p1->str, p2->str);
+}
+
+static int str_sort_by_offset(const void *a1, const void *a2)
+{
+	const struct btf_str_ptr *p1 = a1;
+	const struct btf_str_ptr *p2 = a2;
+
+	if (p1->str != p2->str)
+		return p1->str < p2->str ? -1 : 1;
+	return 0;
+}
+
+static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem)
+{
+	const struct btf_str_ptr *p = pelem;
+
+	if (str_ptr != p->str)
+		return (const char *)str_ptr < p->str ? -1 : 1;
+	return 0;
+}
+
+static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx)
+{
+	struct btf_str_ptrs *strs;
+	struct btf_str_ptr *s;
+
+	if (*str_off_ptr == 0)
+		return 0;
+
+	strs = ctx;
+	s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
+		    sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
+	if (!s)
+		return -EINVAL;
+	s->used = true;
+	return 0;
+}
+
+static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
+{
+	struct btf_str_ptrs *strs;
+	struct btf_str_ptr *s;
+
+	if (*str_off_ptr == 0)
+		return 0;
+
+	strs = ctx;
+	s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt,
+		    sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp);
+	if (!s)
+		return -EINVAL;
+	*str_off_ptr = s->new_off;
+	return 0;
+}
+
+/*
+ * Dedup string and filter out those that are not referenced from either .BTF
+ * or .BTF.ext (if provided) sections.
+ *
+ * This is done by building index of all strings in BTF's string section,
+ * then iterating over all entities that can reference strings (e.g., type
+ * names, struct field names, .BTF.ext line info, etc) and marking corresponding
+ * strings as used. After that all used strings are deduped and compacted into
+ * sequential blob of memory and new offsets are calculated. Then all the string
+ * references are iterated again and rewritten using new offsets.
+ */
+static int btf_dedup_strings(struct btf_dedup *d)
+{
+	const struct btf_header *hdr = d->btf->hdr;
+	char *start = (char *)d->btf->nohdr_data + hdr->str_off;
+	char *end = start + d->btf->hdr->str_len;
+	char *p = start, *tmp_strs = NULL;
+	struct btf_str_ptrs strs = {
+		.cnt = 0,
+		.cap = 0,
+		.ptrs = NULL,
+		.data = start,
+	};
+	int i, j, err = 0, grp_idx;
+	bool grp_used;
+
+	/* build index of all strings */
+	while (p < end) {
+		if (strs.cnt + 1 > strs.cap) {
+			struct btf_str_ptr *new_ptrs;
+
+			strs.cap += max(strs.cnt / 2, 16);
+			new_ptrs = realloc(strs.ptrs,
+					   sizeof(strs.ptrs[0]) * strs.cap);
+			if (!new_ptrs) {
+				err = -ENOMEM;
+				goto done;
+			}
+			strs.ptrs = new_ptrs;
+		}
+
+		strs.ptrs[strs.cnt].str = p;
+		strs.ptrs[strs.cnt].used = false;
+
+		p += strlen(p) + 1;
+		strs.cnt++;
+	}
+
+	/* temporary storage for deduplicated strings */
+	tmp_strs = malloc(d->btf->hdr->str_len);
+	if (!tmp_strs) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	/* mark all used strings */
+	strs.ptrs[0].used = true;
+	err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs);
+	if (err)
+		goto done;
+
+	/* sort strings by context, so that we can identify duplicates */
+	qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content);
+
+	/*
+	 * iterate groups of equal strings and if any instance in a group was
+	 * referenced, emit single instance and remember new offset
+	 */
+	p = tmp_strs;
+	grp_idx = 0;
+	grp_used = strs.ptrs[0].used;
+	/* iterate past end to avoid code duplication after loop */
+	for (i = 1; i <= strs.cnt; i++) {
+		/*
+		 * when i == strs.cnt, we want to skip string comparison and go
+		 * straight to handling last group of strings (otherwise we'd
+		 * need to handle last group after the loop w/ duplicated code)
+		 */
+		if (i < strs.cnt &&
+		    !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) {
+			grp_used = grp_used || strs.ptrs[i].used;
+			continue;
+		}
+
+		/*
+		 * this check would have been required after the loop to handle
+		 * last group of strings, but due to <= condition in a loop
+		 * we avoid that duplication
+		 */
+		if (grp_used) {
+			int new_off = p - tmp_strs;
+			__u32 len = strlen(strs.ptrs[grp_idx].str);
+
+			memmove(p, strs.ptrs[grp_idx].str, len + 1);
+			for (j = grp_idx; j < i; j++)
+				strs.ptrs[j].new_off = new_off;
+			p += len + 1;
+		}
+
+		if (i < strs.cnt) {
+			grp_idx = i;
+			grp_used = strs.ptrs[i].used;
+		}
+	}
+
+	/* replace original strings with deduped ones */
+	d->btf->hdr->str_len = p - tmp_strs;
+	memmove(start, tmp_strs, d->btf->hdr->str_len);
+	end = start + d->btf->hdr->str_len;
+
+	/* restore original order for further binary search lookups */
+	qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset);
+
+	/* remap string offsets */
+	err = btf_for_each_str_off(d, btf_str_remap_offset, &strs);
+	if (err)
+		goto done;
+
+	d->btf->hdr->str_len = end - start;
+
+done:
+	free(tmp_strs);
+	free(strs.ptrs);
+	return err;
+}
+
+static __u32 btf_hash_common(struct btf_type *t)
+{
+	__u32 h;
+
+	h = hash_combine(0, t->name_off);
+	h = hash_combine(h, t->info);
+	h = hash_combine(h, t->size);
+	return h;
+}
+
+static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
+{
+	return t1->name_off == t2->name_off &&
+	       t1->info == t2->info &&
+	       t1->size == t2->size;
+}
+
+/* Calculate type signature hash of INT. */
+static __u32 btf_hash_int(struct btf_type *t)
+{
+	__u32 info = *(__u32 *)(t + 1);
+	__u32 h;
+
+	h = btf_hash_common(t);
+	h = hash_combine(h, info);
+	return h;
+}
+
+/* Check structural equality of two INTs. */
+static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
+{
+	__u32 info1, info2;
+
+	if (!btf_equal_common(t1, t2))
+		return false;
+	info1 = *(__u32 *)(t1 + 1);
+	info2 = *(__u32 *)(t2 + 1);
+	return info1 == info2;
+}
+
+/* Calculate type signature hash of ENUM. */
+static __u32 btf_hash_enum(struct btf_type *t)
+{
+	struct btf_enum *member = (struct btf_enum *)(t + 1);
+	__u32 vlen = BTF_INFO_VLEN(t->info);
+	__u32 h = btf_hash_common(t);
+	int i;
+
+	for (i = 0; i < vlen; i++) {
+		h = hash_combine(h, member->name_off);
+		h = hash_combine(h, member->val);
+		member++;
+	}
+	return h;
+}
+
+/* Check structural equality of two ENUMs. */
+static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+{
+	struct btf_enum *m1, *m2;
+	__u16 vlen;
+	int i;
+
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	vlen = BTF_INFO_VLEN(t1->info);
+	m1 = (struct btf_enum *)(t1 + 1);
+	m2 = (struct btf_enum *)(t2 + 1);
+	for (i = 0; i < vlen; i++) {
+		if (m1->name_off != m2->name_off || m1->val != m2->val)
+			return false;
+		m1++;
+		m2++;
+	}
+	return true;
+}
+
+/*
+ * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs,
+ * as referenced type IDs equivalence is established separately during type
+ * graph equivalence check algorithm.
+ */
+static __u32 btf_hash_struct(struct btf_type *t)
+{
+	struct btf_member *member = (struct btf_member *)(t + 1);
+	__u32 vlen = BTF_INFO_VLEN(t->info);
+	__u32 h = btf_hash_common(t);
+	int i;
+
+	for (i = 0; i < vlen; i++) {
+		h = hash_combine(h, member->name_off);
+		h = hash_combine(h, member->offset);
+		/* no hashing of referenced type ID, it can be unresolved yet */
+		member++;
+	}
+	return h;
+}
+
+/*
+ * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type
+ * IDs. This check is performed during type graph equivalence check and
+ * referenced types equivalence is checked separately.
+ */
+static bool btf_equal_struct(struct btf_type *t1, struct btf_type *t2)
+{
+	struct btf_member *m1, *m2;
+	__u16 vlen;
+	int i;
+
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	vlen = BTF_INFO_VLEN(t1->info);
+	m1 = (struct btf_member *)(t1 + 1);
+	m2 = (struct btf_member *)(t2 + 1);
+	for (i = 0; i < vlen; i++) {
+		if (m1->name_off != m2->name_off || m1->offset != m2->offset)
+			return false;
+		m1++;
+		m2++;
+	}
+	return true;
+}
+
+/*
+ * Calculate type signature hash of ARRAY, including referenced type IDs,
+ * under assumption that they were already resolved to canonical type IDs and
+ * are not going to change.
+ */
+static __u32 btf_hash_array(struct btf_type *t)
+{
+	struct btf_array *info = (struct btf_array *)(t + 1);
+	__u32 h = btf_hash_common(t);
+
+	h = hash_combine(h, info->type);
+	h = hash_combine(h, info->index_type);
+	h = hash_combine(h, info->nelems);
+	return h;
+}
+
+/*
+ * Check exact equality of two ARRAYs, taking into account referenced
+ * type IDs, under assumption that they were already resolved to canonical
+ * type IDs and are not going to change.
+ * This function is called during reference types deduplication to compare
+ * ARRAY to potential canonical representative.
+ */
+static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2)
+{
+	struct btf_array *info1, *info2;
+
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	info1 = (struct btf_array *)(t1 + 1);
+	info2 = (struct btf_array *)(t2 + 1);
+	return info1->type == info2->type &&
+	       info1->index_type == info2->index_type &&
+	       info1->nelems == info2->nelems;
+}
+
+/*
+ * Check structural compatibility of two ARRAYs, ignoring referenced type
+ * IDs. This check is performed during type graph equivalence check and
+ * referenced types equivalence is checked separately.
+ */
+static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2)
+{
+	struct btf_array *info1, *info2;
+
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	info1 = (struct btf_array *)(t1 + 1);
+	info2 = (struct btf_array *)(t2 + 1);
+	return info1->nelems == info2->nelems;
+}
+
+/*
+ * Calculate type signature hash of FUNC_PROTO, including referenced type IDs,
+ * under assumption that they were already resolved to canonical type IDs and
+ * are not going to change.
+ */
+static inline __u32 btf_hash_fnproto(struct btf_type *t)
+{
+	struct btf_param *member = (struct btf_param *)(t + 1);
+	__u16 vlen = BTF_INFO_VLEN(t->info);
+	__u32 h = btf_hash_common(t);
+	int i;
+
+	for (i = 0; i < vlen; i++) {
+		h = hash_combine(h, member->name_off);
+		h = hash_combine(h, member->type);
+		member++;
+	}
+	return h;
+}
+
+/*
+ * Check exact equality of two FUNC_PROTOs, taking into account referenced
+ * type IDs, under assumption that they were already resolved to canonical
+ * type IDs and are not going to change.
+ * This function is called during reference types deduplication to compare
+ * FUNC_PROTO to potential canonical representative.
+ */
+static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2)
+{
+	struct btf_param *m1, *m2;
+	__u16 vlen;
+	int i;
+
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	vlen = BTF_INFO_VLEN(t1->info);
+	m1 = (struct btf_param *)(t1 + 1);
+	m2 = (struct btf_param *)(t2 + 1);
+	for (i = 0; i < vlen; i++) {
+		if (m1->name_off != m2->name_off || m1->type != m2->type)
+			return false;
+		m1++;
+		m2++;
+	}
+	return true;
+}
+
+/*
+ * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type
+ * IDs. This check is performed during type graph equivalence check and
+ * referenced types equivalence is checked separately.
+ */
+static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
+{
+	struct btf_param *m1, *m2;
+	__u16 vlen;
+	int i;
+
+	/* skip return type ID */
+	if (t1->name_off != t2->name_off || t1->info != t2->info)
+		return false;
+
+	vlen = BTF_INFO_VLEN(t1->info);
+	m1 = (struct btf_param *)(t1 + 1);
+	m2 = (struct btf_param *)(t2 + 1);
+	for (i = 0; i < vlen; i++) {
+		if (m1->name_off != m2->name_off)
+			return false;
+		m1++;
+		m2++;
+	}
+	return true;
+}
+
+/*
+ * Deduplicate primitive types, that can't reference other types, by calculating
+ * their type signature hash and comparing them with any possible canonical
+ * candidate. If no canonical candidate matches, type itself is marked as
+ * canonical and is added into `btf_dedup->dedup_table` as another candidate.
+ */
+static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
+{
+	struct btf_type *t = d->btf->types[type_id];
+	struct btf_type *cand;
+	struct btf_dedup_node *cand_node;
+	/* if we don't find equivalent type, then we are canonical */
+	__u32 new_id = type_id;
+	__u32 h;
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_ARRAY:
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+	case BTF_KIND_FUNC:
+	case BTF_KIND_FUNC_PROTO:
+		return 0;
+
+	case BTF_KIND_INT:
+		h = btf_hash_int(t);
+		for_each_hash_node(d->dedup_table, h, cand_node) {
+			cand = d->btf->types[cand_node->type_id];
+			if (btf_equal_int(t, cand)) {
+				new_id = cand_node->type_id;
+				break;
+			}
+		}
+		break;
+
+	case BTF_KIND_ENUM:
+		h = btf_hash_enum(t);
+		for_each_hash_node(d->dedup_table, h, cand_node) {
+			cand = d->btf->types[cand_node->type_id];
+			if (btf_equal_enum(t, cand)) {
+				new_id = cand_node->type_id;
+				break;
+			}
+		}
+		break;
+
+	case BTF_KIND_FWD:
+		h = btf_hash_common(t);
+		for_each_hash_node(d->dedup_table, h, cand_node) {
+			cand = d->btf->types[cand_node->type_id];
+			if (btf_equal_common(t, cand)) {
+				new_id = cand_node->type_id;
+				break;
+			}
+		}
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	d->map[type_id] = new_id;
+	if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int btf_dedup_prim_types(struct btf_dedup *d)
+{
+	int i, err;
+
+	for (i = 1; i <= d->btf->nr_types; i++) {
+		err = btf_dedup_prim_type(d, i);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+/*
+ * Check whether type is already mapped into canonical one (could be to itself).
+ */
+static inline bool is_type_mapped(struct btf_dedup *d, uint32_t type_id)
+{
+	return d->map[type_id] <= BTF_MAX_NR_TYPES;
+}
+
+/*
+ * Resolve type ID into its canonical type ID, if any; otherwise return original
+ * type ID. If type is FWD and is resolved into STRUCT/UNION already, follow
+ * STRUCT/UNION link and resolve it into canonical type ID as well.
+ */
+static inline __u32 resolve_type_id(struct btf_dedup *d, __u32 type_id)
+{
+	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
+		type_id = d->map[type_id];
+	return type_id;
+}
+
+/*
+ * Resolve FWD to underlying STRUCT/UNION, if any; otherwise return original
+ * type ID.
+ */
+static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
+{
+	__u32 orig_type_id = type_id;
+
+	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
+		return type_id;
+
+	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
+		type_id = d->map[type_id];
+
+	if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD)
+		return type_id;
+
+	return orig_type_id;
+}
+
+
+static inline __u16 btf_fwd_kind(struct btf_type *t)
+{
+	return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT;
+}
+
+/*
+ * Check equivalence of BTF type graph formed by candidate struct/union (we'll
+ * call it "candidate graph" in this description for brevity) to a type graph
+ * formed by (potential) canonical struct/union ("canonical graph" for brevity
+ * here, though keep in mind that not all types in canonical graph are
+ * necessarily canonical representatives themselves, some of them might be
+ * duplicates or its uniqueness might not have been established yet).
+ * Returns:
+ *  - >0, if type graphs are equivalent;
+ *  -  0, if not equivalent;
+ *  - <0, on error.
+ *
+ * Algorithm performs side-by-side DFS traversal of both type graphs and checks
+ * equivalence of BTF types at each step. If at any point BTF types in candidate
+ * and canonical graphs are not compatible structurally, whole graphs are
+ * incompatible. If types are structurally equivalent (i.e., all information
+ * except referenced type IDs is exactly the same), a mapping from `canon_id` to
+ * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`).
+ * If a type references other types, then those referenced types are checked
+ * for equivalence recursively.
+ *
+ * During DFS traversal, if we find that for current `canon_id` type we
+ * already have some mapping in hypothetical map, we check for two possible
+ * situations:
+ *   - `canon_id` is mapped to exactly the same type as `cand_id`. This will
+ *     happen when type graphs have cycles. In this case we assume those two
+ *     types are equivalent.
+ *   - `canon_id` is mapped to different type. This is contradiction in our
+ *     hypothetical mapping, because same graph in canonical graph corresponds
+ *     to two different types in candidate graph, which for equivalent type
+ *     graphs shouldn't happen. This condition terminates equivalence check
+ *     with negative result.
+ *
+ * If type graphs traversal exhausts types to check and find no contradiction,
+ * then type graphs are equivalent.
+ *
+ * When checking types for equivalence, there is one special case: FWD types.
+ * If FWD type resolution is allowed and one of the types (either from canonical
+ * or candidate graph) is FWD and other is STRUCT/UNION (depending on FWD's kind
+ * flag) and their names match, hypothetical mapping is updated to point from
+ * FWD to STRUCT/UNION. If graphs will be determined as equivalent successfully,
+ * this mapping will be used to record FWD -> STRUCT/UNION mapping permanently.
+ *
+ * Technically, this could lead to incorrect FWD to STRUCT/UNION resolution,
+ * if there are two exactly named (or anonymous) structs/unions that are
+ * compatible structurally, one of which has FWD field, while other is concrete
+ * STRUCT/UNION, but according to C sources they are different structs/unions
+ * that are referencing different types with the same name. This is extremely
+ * unlikely to happen, but btf_dedup API allows to disable FWD resolution if
+ * this logic is causing problems.
+ *
+ * Doing FWD resolution means that both candidate and/or canonical graphs can
+ * consists of portions of the graph that come from multiple compilation units.
+ * This is due to the fact that types within single compilation unit are always
+ * deduplicated and FWDs are already resolved, if referenced struct/union
+ * definiton is available. So, if we had unresolved FWD and found corresponding
+ * STRUCT/UNION, they will be from different compilation units. This
+ * consequently means that when we "link" FWD to corresponding STRUCT/UNION,
+ * type graph will likely have at least two different BTF types that describe
+ * same type (e.g., most probably there will be two different BTF types for the
+ * same 'int' primitive type) and could even have "overlapping" parts of type
+ * graph that describe same subset of types.
+ *
+ * This in turn means that our assumption that each type in canonical graph
+ * must correspond to exactly one type in candidate graph might not hold
+ * anymore and will make it harder to detect contradictions using hypothetical
+ * map. To handle this problem, we allow to follow FWD -> STRUCT/UNION
+ * resolution only in canonical graph. FWDs in candidate graphs are never
+ * resolved. To see why it's OK, let's check all possible situations w.r.t. FWDs
+ * that can occur:
+ *   - Both types in canonical and candidate graphs are FWDs. If they are
+ *     structurally equivalent, then they can either be both resolved to the
+ *     same STRUCT/UNION or not resolved at all. In both cases they are
+ *     equivalent and there is no need to resolve FWD on candidate side.
+ *   - Both types in canonical and candidate graphs are concrete STRUCT/UNION,
+ *     so nothing to resolve as well, algorithm will check equivalence anyway.
+ *   - Type in canonical graph is FWD, while type in candidate is concrete
+ *     STRUCT/UNION. In this case candidate graph comes from single compilation
+ *     unit, so there is exactly one BTF type for each unique C type. After
+ *     resolving FWD into STRUCT/UNION, there might be more than one BTF type
+ *     in canonical graph mapping to single BTF type in candidate graph, but
+ *     because hypothetical mapping maps from canonical to candidate types, it's
+ *     alright, and we still maintain the property of having single `canon_id`
+ *     mapping to single `cand_id` (there could be two different `canon_id`
+ *     mapped to the same `cand_id`, but it's not contradictory).
+ *   - Type in canonical graph is concrete STRUCT/UNION, while type in candidate
+ *     graph is FWD. In this case we are just going to check compatibility of
+ *     STRUCT/UNION and corresponding FWD, and if they are compatible, we'll
+ *     assume that whatever STRUCT/UNION FWD resolves to must be equivalent to
+ *     a concrete STRUCT/UNION from canonical graph. If the rest of type graphs
+ *     turn out equivalent, we'll re-resolve FWD to concrete STRUCT/UNION from
+ *     canonical graph.
+ */
+static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
+			      __u32 canon_id)
+{
+	struct btf_type *cand_type;
+	struct btf_type *canon_type;
+	__u32 hypot_type_id;
+	__u16 cand_kind;
+	__u16 canon_kind;
+	int i, eq;
+
+	/* if both resolve to the same canonical, they must be equivalent */
+	if (resolve_type_id(d, cand_id) == resolve_type_id(d, canon_id))
+		return 1;
+
+	canon_id = resolve_fwd_id(d, canon_id);
+
+	hypot_type_id = d->hypot_map[canon_id];
+	if (hypot_type_id <= BTF_MAX_NR_TYPES)
+		return hypot_type_id == cand_id;
+
+	if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
+		return -ENOMEM;
+
+	cand_type = d->btf->types[cand_id];
+	canon_type = d->btf->types[canon_id];
+	cand_kind = BTF_INFO_KIND(cand_type->info);
+	canon_kind = BTF_INFO_KIND(canon_type->info);
+
+	if (cand_type->name_off != canon_type->name_off)
+		return 0;
+
+	/* FWD <--> STRUCT/UNION equivalence check, if enabled */
+	if (!d->opts.dont_resolve_fwds
+	    && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD)
+	    && cand_kind != canon_kind) {
+		__u16 real_kind;
+		__u16 fwd_kind;
+
+		if (cand_kind == BTF_KIND_FWD) {
+			real_kind = canon_kind;
+			fwd_kind = btf_fwd_kind(cand_type);
+		} else {
+			real_kind = cand_kind;
+			fwd_kind = btf_fwd_kind(canon_type);
+		}
+		return fwd_kind == real_kind;
+	}
+
+	if (cand_type->info != canon_type->info)
+		return 0;
+
+	switch (cand_kind) {
+	case BTF_KIND_INT:
+		return btf_equal_int(cand_type, canon_type);
+
+	case BTF_KIND_ENUM:
+		return btf_equal_enum(cand_type, canon_type);
+
+	case BTF_KIND_FWD:
+		return btf_equal_common(cand_type, canon_type);
+
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_FUNC:
+		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
+
+	case BTF_KIND_ARRAY: {
+		struct btf_array *cand_arr, *canon_arr;
+
+		if (!btf_compat_array(cand_type, canon_type))
+			return 0;
+		cand_arr = (struct btf_array *)(cand_type + 1);
+		canon_arr = (struct btf_array *)(canon_type + 1);
+		eq = btf_dedup_is_equiv(d,
+			cand_arr->index_type, canon_arr->index_type);
+		if (eq <= 0)
+			return eq;
+		return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type);
+	}
+
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION: {
+		struct btf_member *cand_m, *canon_m;
+		__u16 vlen;
+
+		if (!btf_equal_struct(cand_type, canon_type))
+			return 0;
+		vlen = BTF_INFO_VLEN(cand_type->info);
+		cand_m = (struct btf_member *)(cand_type + 1);
+		canon_m = (struct btf_member *)(canon_type + 1);
+		for (i = 0; i < vlen; i++) {
+			eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type);
+			if (eq <= 0)
+				return eq;
+			cand_m++;
+			canon_m++;
+		}
+
+		return 1;
+	}
+
+	case BTF_KIND_FUNC_PROTO: {
+		struct btf_param *cand_p, *canon_p;
+		__u16 vlen;
+
+		if (!btf_compat_fnproto(cand_type, canon_type))
+			return 0;
+		eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
+		if (eq <= 0)
+			return eq;
+		vlen = BTF_INFO_VLEN(cand_type->info);
+		cand_p = (struct btf_param *)(cand_type + 1);
+		canon_p = (struct btf_param *)(canon_type + 1);
+		for (i = 0; i < vlen; i++) {
+			eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type);
+			if (eq <= 0)
+				return eq;
+			cand_p++;
+			canon_p++;
+		}
+		return 1;
+	}
+
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Use hypothetical mapping, produced by successful type graph equivalence
+ * check, to augment existing struct/union canonical mapping, where possible.
+ *
+ * If BTF_KIND_FWD resolution is allowed, this mapping is also used to record
+ * FWD -> STRUCT/UNION correspondence as well. FWD resolution is bidirectional:
+ * it doesn't matter if FWD type was part of canonical graph or candidate one,
+ * we are recording the mapping anyway. As opposed to carefulness required
+ * for struct/union correspondence mapping (described below), for FWD resolution
+ * it's not important, as by the time that FWD type (reference type) will be
+ * deduplicated all structs/unions will be deduped already anyway.
+ *
+ * Recording STRUCT/UNION mapping is purely a performance optimization and is
+ * not required for correctness. It needs to be done carefully to ensure that
+ * struct/union from candidate's type graph is not mapped into corresponding
+ * struct/union from canonical type graph that itself hasn't been resolved into
+ * canonical representative. The only guarantee we have is that canonical
+ * struct/union was determined as canonical and that won't change. But any
+ * types referenced through that struct/union fields could have been not yet
+ * resolved, so in case like that it's too early to establish any kind of
+ * correspondence between structs/unions.
+ *
+ * No canonical correspondence is derived for primitive types (they are already
+ * deduplicated completely already anyway) or reference types (they rely on
+ * stability of struct/union canonical relationship for equivalence checks).
+ */
+static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
+{
+	__u32 cand_type_id, targ_type_id;
+	__u16 t_kind, c_kind;
+	__u32 t_id, c_id;
+	int i;
+
+	for (i = 0; i < d->hypot_cnt; i++) {
+		cand_type_id = d->hypot_list[i];
+		targ_type_id = d->hypot_map[cand_type_id];
+		t_id = resolve_type_id(d, targ_type_id);
+		c_id = resolve_type_id(d, cand_type_id);
+		t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info);
+		c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info);
+		/*
+		 * Resolve FWD into STRUCT/UNION.
+		 * It's ok to resolve FWD into STRUCT/UNION that's not yet
+		 * mapped to canonical representative (as opposed to
+		 * STRUCT/UNION <--> STRUCT/UNION mapping logic below), because
+		 * eventually that struct is going to be mapped and all resolved
+		 * FWDs will automatically resolve to correct canonical
+		 * representative. This will happen before ref type deduping,
+		 * which critically depends on stability of these mapping. This
+		 * stability is not a requirement for STRUCT/UNION equivalence
+		 * checks, though.
+		 */
+		if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD)
+			d->map[c_id] = t_id;
+		else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD)
+			d->map[t_id] = c_id;
+
+		if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) &&
+		    c_kind != BTF_KIND_FWD &&
+		    is_type_mapped(d, c_id) &&
+		    !is_type_mapped(d, t_id)) {
+			/*
+			 * as a perf optimization, we can map struct/union
+			 * that's part of type graph we just verified for
+			 * equivalence. We can do that for struct/union that has
+			 * canonical representative only, though.
+			 */
+			d->map[t_id] = c_id;
+		}
+	}
+}
+
+/*
+ * Deduplicate struct/union types.
+ *
+ * For each struct/union type its type signature hash is calculated, taking
+ * into account type's name, size, number, order and names of fields, but
+ * ignoring type ID's referenced from fields, because they might not be deduped
+ * completely until after reference types deduplication phase. This type hash
+ * is used to iterate over all potential canonical types, sharing same hash.
+ * For each canonical candidate we check whether type graphs that they form
+ * (through referenced types in fields and so on) are equivalent using algorithm
+ * implemented in `btf_dedup_is_equiv`. If such equivalence is found and
+ * BTF_KIND_FWD resolution is allowed, then hypothetical mapping
+ * (btf_dedup->hypot_map) produced by aforementioned type graph equivalence
+ * algorithm is used to record FWD -> STRUCT/UNION mapping. It's also used to
+ * potentially map other structs/unions to their canonical representatives,
+ * if such relationship hasn't yet been established. This speeds up algorithm
+ * by eliminating some of the duplicate work.
+ *
+ * If no matching canonical representative was found, struct/union is marked
+ * as canonical for itself and is added into btf_dedup->dedup_table hash map
+ * for further look ups.
+ */
+static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
+{
+	struct btf_dedup_node *cand_node;
+	struct btf_type *t;
+	/* if we don't find equivalent type, then we are canonical */
+	__u32 new_id = type_id;
+	__u16 kind;
+	__u32 h;
+
+	/* already deduped or is in process of deduping (loop detected) */
+	if (d->map[type_id] <= BTF_MAX_NR_TYPES)
+		return 0;
+
+	t = d->btf->types[type_id];
+	kind = BTF_INFO_KIND(t->info);
+
+	if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
+		return 0;
+
+	h = btf_hash_struct(t);
+	for_each_hash_node(d->dedup_table, h, cand_node) {
+		int eq;
+
+		btf_dedup_clear_hypot_map(d);
+		eq = btf_dedup_is_equiv(d, type_id, cand_node->type_id);
+		if (eq < 0)
+			return eq;
+		if (!eq)
+			continue;
+		new_id = cand_node->type_id;
+		btf_dedup_merge_hypot_map(d);
+		break;
+	}
+
+	d->map[type_id] = new_id;
+	if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int btf_dedup_struct_types(struct btf_dedup *d)
+{
+	int i, err;
+
+	for (i = 1; i <= d->btf->nr_types; i++) {
+		err = btf_dedup_struct_type(d, i);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+/*
+ * Deduplicate reference type.
+ *
+ * Once all primitive and struct/union types got deduplicated, we can easily
+ * deduplicate all other (reference) BTF types. This is done in two steps:
+ *
+ * 1. Resolve all referenced type IDs into their canonical type IDs. This
+ * resolution can be done either immediately for primitive or struct/union types
+ * (because they were deduped in previous two phases) or recursively for
+ * reference types. Recursion will always terminate at either primitive or
+ * struct/union type, at which point we can "unwind" chain of reference types
+ * one by one. There is no danger of encountering cycles because in C type
+ * system the only way to form type cycle is through struct/union, so any chain
+ * of reference types, even those taking part in a type cycle, will inevitably
+ * reach struct/union at some point.
+ *
+ * 2. Once all referenced type IDs are resolved into canonical ones, BTF type
+ * becomes "stable", in the sense that no further deduplication will cause
+ * any changes to it. With that, it's now possible to calculate type's signature
+ * hash (this time taking into account referenced type IDs) and loop over all
+ * potential canonical representatives. If no match was found, current type
+ * will become canonical representative of itself and will be added into
+ * btf_dedup->dedup_table as another possible canonical representative.
+ */
+static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
+{
+	struct btf_dedup_node *cand_node;
+	struct btf_type *t, *cand;
+	/* if we don't find equivalent type, then we are representative type */
+	__u32 new_id = type_id;
+	__u32 h, ref_type_id;
+
+	if (d->map[type_id] == BTF_IN_PROGRESS_ID)
+		return -ELOOP;
+	if (d->map[type_id] <= BTF_MAX_NR_TYPES)
+		return resolve_type_id(d, type_id);
+
+	t = d->btf->types[type_id];
+	d->map[type_id] = BTF_IN_PROGRESS_ID;
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_FUNC:
+		ref_type_id = btf_dedup_ref_type(d, t->type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		t->type = ref_type_id;
+
+		h = btf_hash_common(t);
+		for_each_hash_node(d->dedup_table, h, cand_node) {
+			cand = d->btf->types[cand_node->type_id];
+			if (btf_equal_common(t, cand)) {
+				new_id = cand_node->type_id;
+				break;
+			}
+		}
+		break;
+
+	case BTF_KIND_ARRAY: {
+		struct btf_array *info = (struct btf_array *)(t + 1);
+
+		ref_type_id = btf_dedup_ref_type(d, info->type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		info->type = ref_type_id;
+
+		ref_type_id = btf_dedup_ref_type(d, info->index_type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		info->index_type = ref_type_id;
+
+		h = btf_hash_array(t);
+		for_each_hash_node(d->dedup_table, h, cand_node) {
+			cand = d->btf->types[cand_node->type_id];
+			if (btf_equal_array(t, cand)) {
+				new_id = cand_node->type_id;
+				break;
+			}
+		}
+		break;
+	}
+
+	case BTF_KIND_FUNC_PROTO: {
+		struct btf_param *param;
+		__u16 vlen;
+		int i;
+
+		ref_type_id = btf_dedup_ref_type(d, t->type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		t->type = ref_type_id;
+
+		vlen = BTF_INFO_VLEN(t->info);
+		param = (struct btf_param *)(t + 1);
+		for (i = 0; i < vlen; i++) {
+			ref_type_id = btf_dedup_ref_type(d, param->type);
+			if (ref_type_id < 0)
+				return ref_type_id;
+			param->type = ref_type_id;
+			param++;
+		}
+
+		h = btf_hash_fnproto(t);
+		for_each_hash_node(d->dedup_table, h, cand_node) {
+			cand = d->btf->types[cand_node->type_id];
+			if (btf_equal_fnproto(t, cand)) {
+				new_id = cand_node->type_id;
+				break;
+			}
+		}
+		break;
+	}
+
+	default:
+		return -EINVAL;
+	}
+
+	d->map[type_id] = new_id;
+	if (type_id == new_id && btf_dedup_table_add(d, h, type_id))
+		return -ENOMEM;
+
+	return new_id;
+}
+
+static int btf_dedup_ref_types(struct btf_dedup *d)
+{
+	int i, err;
+
+	for (i = 1; i <= d->btf->nr_types; i++) {
+		err = btf_dedup_ref_type(d, i);
+		if (err < 0)
+			return err;
+	}
+	btf_dedup_table_free(d);
+	return 0;
+}
+
+/*
+ * Compact types.
+ *
+ * After we established for each type its corresponding canonical representative
+ * type, we now can eliminate types that are not canonical and leave only
+ * canonical ones layed out sequentially in memory by copying them over
+ * duplicates. During compaction btf_dedup->hypot_map array is reused to store
+ * a map from original type ID to a new compacted type ID, which will be used
+ * during next phase to "fix up" type IDs, referenced from struct/union and
+ * reference types.
+ */
+static int btf_dedup_compact_types(struct btf_dedup *d)
+{
+	struct btf_type **new_types;
+	__u32 next_type_id = 1;
+	char *types_start, *p;
+	int i, len;
+
+	/* we are going to reuse hypot_map to store compaction remapping */
+	d->hypot_map[0] = 0;
+	for (i = 1; i <= d->btf->nr_types; i++)
+		d->hypot_map[i] = BTF_UNPROCESSED_ID;
+
+	types_start = d->btf->nohdr_data + d->btf->hdr->type_off;
+	p = types_start;
+
+	for (i = 1; i <= d->btf->nr_types; i++) {
+		if (d->map[i] != i)
+			continue;
+
+		len = btf_type_size(d->btf->types[i]);
+		if (len < 0)
+			return len;
+
+		memmove(p, d->btf->types[i], len);
+		d->hypot_map[i] = next_type_id;
+		d->btf->types[next_type_id] = (struct btf_type *)p;
+		p += len;
+		next_type_id++;
+	}
+
+	/* shrink struct btf's internal types index and update btf_header */
+	d->btf->nr_types = next_type_id - 1;
+	d->btf->types_size = d->btf->nr_types;
+	d->btf->hdr->type_len = p - types_start;
+	new_types = realloc(d->btf->types,
+			    (1 + d->btf->nr_types) * sizeof(struct btf_type *));
+	if (!new_types)
+		return -ENOMEM;
+	d->btf->types = new_types;
+
+	/* make sure string section follows type information without gaps */
+	d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data;
+	memmove(p, d->btf->strings, d->btf->hdr->str_len);
+	d->btf->strings = p;
+	p += d->btf->hdr->str_len;
+
+	d->btf->data_size = p - (char *)d->btf->data;
+	return 0;
+}
+
+/*
+ * Figure out final (deduplicated and compacted) type ID for provided original
+ * `type_id` by first resolving it into corresponding canonical type ID and
+ * then mapping it to a deduplicated type ID, stored in btf_dedup->hypot_map,
+ * which is populated during compaction phase.
+ */
+static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id)
+{
+	__u32 resolved_type_id, new_type_id;
+
+	resolved_type_id = resolve_type_id(d, type_id);
+	new_type_id = d->hypot_map[resolved_type_id];
+	if (new_type_id > BTF_MAX_NR_TYPES)
+		return -EINVAL;
+	return new_type_id;
+}
+
+/*
+ * Remap referenced type IDs into deduped type IDs.
+ *
+ * After BTF types are deduplicated and compacted, their final type IDs may
+ * differ from original ones. The map from original to a corresponding
+ * deduped type ID is stored in btf_dedup->hypot_map and is populated during
+ * compaction phase. During remapping phase we are rewriting all type IDs
+ * referenced from any BTF type (e.g., struct fields, func proto args, etc) to
+ * their final deduped type IDs.
+ */
+static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
+{
+	struct btf_type *t = d->btf->types[type_id];
+	int i, r;
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_INT:
+	case BTF_KIND_ENUM:
+		break;
+
+	case BTF_KIND_FWD:
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_FUNC:
+		r = btf_dedup_remap_type_id(d, t->type);
+		if (r < 0)
+			return r;
+		t->type = r;
+		break;
+
+	case BTF_KIND_ARRAY: {
+		struct btf_array *arr_info = (struct btf_array *)(t + 1);
+
+		r = btf_dedup_remap_type_id(d, arr_info->type);
+		if (r < 0)
+			return r;
+		arr_info->type = r;
+		r = btf_dedup_remap_type_id(d, arr_info->index_type);
+		if (r < 0)
+			return r;
+		arr_info->index_type = r;
+		break;
+	}
+
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION: {
+		struct btf_member *member = (struct btf_member *)(t + 1);
+		__u16 vlen = BTF_INFO_VLEN(t->info);
+
+		for (i = 0; i < vlen; i++) {
+			r = btf_dedup_remap_type_id(d, member->type);
+			if (r < 0)
+				return r;
+			member->type = r;
+			member++;
+		}
+		break;
+	}
+
+	case BTF_KIND_FUNC_PROTO: {
+		struct btf_param *param = (struct btf_param *)(t + 1);
+		__u16 vlen = BTF_INFO_VLEN(t->info);
+
+		r = btf_dedup_remap_type_id(d, t->type);
+		if (r < 0)
+			return r;
+		t->type = r;
+
+		for (i = 0; i < vlen; i++) {
+			r = btf_dedup_remap_type_id(d, param->type);
+			if (r < 0)
+				return r;
+			param->type = r;
+			param++;
+		}
+		break;
+	}
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_dedup_remap_types(struct btf_dedup *d)
+{
+	int i, r;
+
+	for (i = 1; i <= d->btf->nr_types; i++) {
+		r = btf_dedup_remap_type(d, i);
+		if (r < 0)
+			return r;
+	}
+	return 0;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index b0610dcdae6b..94bbc249b0f1 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -55,33 +55,46 @@ struct btf_ext_header {
 	__u32	line_info_len;
 };
 
-typedef int (*btf_print_fn_t)(const char *, ...)
-	__attribute__((format(printf, 1, 2)));
-
 LIBBPF_API void btf__free(struct btf *btf);
-LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
+LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
 LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__fd(const struct btf *btf);
+LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
+LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
+				    __u32 expected_key_size,
+				    __u32 expected_value_size,
+				    __u32 *key_type_id, __u32 *value_type_id);
+
+LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size);
+LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext);
+LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext* btf_ext,
+					     __u32 *size);
+LIBBPF_API int btf_ext__reloc_func_info(const struct btf *btf,
+					const struct btf_ext *btf_ext,
+					const char *sec_name, __u32 insns_cnt,
+					void **func_info, __u32 *cnt);
+LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf,
+					const struct btf_ext *btf_ext,
+					const char *sec_name, __u32 insns_cnt,
+					void **line_info, __u32 *cnt);
+LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
+
+struct btf_dedup_opts {
+	bool dont_resolve_fwds;
+};
 
-struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
-void btf_ext__free(struct btf_ext *btf_ext);
-int btf_ext__reloc_func_info(const struct btf *btf,
-			     const struct btf_ext *btf_ext,
-			     const char *sec_name, __u32 insns_cnt,
-			     void **func_info, __u32 *func_info_len);
-int btf_ext__reloc_line_info(const struct btf *btf,
-			     const struct btf_ext *btf_ext,
-			     const char *sec_name, __u32 insns_cnt,
-			     void **line_info, __u32 *cnt);
-__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
-__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
+			  const struct btf_dedup_opts *opts);
 
 #ifdef __cplusplus
 } /* extern "C" */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 03bc01ca2577..b38dcbe7460a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -42,6 +42,7 @@
 #include "bpf.h"
 #include "btf.h"
 #include "str_error.h"
+#include "libbpf_util.h"
 
 #ifndef EM_BPF
 #define EM_BPF 247
@@ -53,39 +54,33 @@
 
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
-__printf(1, 2)
-static int __base_pr(const char *format, ...)
+static int __base_pr(enum libbpf_print_level level, const char *format,
+		     va_list args)
 {
-	va_list args;
-	int err;
+	if (level == LIBBPF_DEBUG)
+		return 0;
 
-	va_start(args, format);
-	err = vfprintf(stderr, format, args);
-	va_end(args);
-	return err;
+	return vfprintf(stderr, format, args);
 }
 
-static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr;
-static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr;
-static __printf(1, 2) libbpf_print_fn_t __pr_debug;
+static libbpf_print_fn_t __libbpf_pr = __base_pr;
 
-#define __pr(func, fmt, ...)	\
-do {				\
-	if ((func))		\
-		(func)("libbpf: " fmt, ##__VA_ARGS__); \
-} while (0)
-
-#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
-#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
-#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)
+void libbpf_set_print(libbpf_print_fn_t fn)
+{
+	__libbpf_pr = fn;
+}
 
-void libbpf_set_print(libbpf_print_fn_t warn,
-		      libbpf_print_fn_t info,
-		      libbpf_print_fn_t debug)
+__printf(2, 3)
+void libbpf_print(enum libbpf_print_level level, const char *format, ...)
 {
-	__pr_warning = warn;
-	__pr_info = info;
-	__pr_debug = debug;
+	va_list args;
+
+	if (!__libbpf_pr)
+		return;
+
+	va_start(args, format);
+	__libbpf_pr(level, format, args);
+	va_end(args);
 }
 
 #define STRERR_BUFSIZE  128
@@ -312,7 +307,7 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 		return -EINVAL;
 	}
 
-	bzero(prog, sizeof(*prog));
+	memset(prog, 0, sizeof(*prog));
 
 	prog->section_name = strdup(section_name);
 	if (!prog->section_name) {
@@ -839,9 +834,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 		else if (strcmp(name, "maps") == 0)
 			obj->efile.maps_shndx = idx;
 		else if (strcmp(name, BTF_ELF_SEC) == 0) {
-			obj->btf = btf__new(data->d_buf, data->d_size,
-					    __pr_debug);
-			if (IS_ERR(obj->btf)) {
+			obj->btf = btf__new(data->d_buf, data->d_size);
+			if (IS_ERR(obj->btf) || btf__load(obj->btf)) {
 				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
 					   BTF_ELF_SEC, PTR_ERR(obj->btf));
 				obj->btf = NULL;
@@ -915,8 +909,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 				 BTF_EXT_ELF_SEC, BTF_ELF_SEC);
 		} else {
 			obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
-						    btf_ext_data->d_size,
-						    __pr_debug);
+						    btf_ext_data->d_size);
 			if (IS_ERR(obj->btf_ext)) {
 				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
 					   BTF_EXT_ELF_SEC,
@@ -1057,72 +1050,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 
 static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
 {
-	const struct btf_type *container_type;
-	const struct btf_member *key, *value;
 	struct bpf_map_def *def = &map->def;
-	const size_t max_name = 256;
-	char container_name[max_name];
-	__s64 key_size, value_size;
-	__s32 container_id;
-
-	if (snprintf(container_name, max_name, "____btf_map_%s", map->name) ==
-	    max_name) {
-		pr_warning("map:%s length of '____btf_map_%s' is too long\n",
-			   map->name, map->name);
-		return -EINVAL;
-	}
-
-	container_id = btf__find_by_name(btf, container_name);
-	if (container_id < 0) {
-		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
-			 map->name, container_name);
-		return container_id;
-	}
-
-	container_type = btf__type_by_id(btf, container_id);
-	if (!container_type) {
-		pr_warning("map:%s cannot find BTF type for container_id:%u\n",
-			   map->name, container_id);
-		return -EINVAL;
-	}
-
-	if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT ||
-	    BTF_INFO_VLEN(container_type->info) < 2) {
-		pr_warning("map:%s container_name:%s is an invalid container struct\n",
-			   map->name, container_name);
-		return -EINVAL;
-	}
-
-	key = (struct btf_member *)(container_type + 1);
-	value = key + 1;
-
-	key_size = btf__resolve_size(btf, key->type);
-	if (key_size < 0) {
-		pr_warning("map:%s invalid BTF key_type_size\n",
-			   map->name);
-		return key_size;
-	}
-
-	if (def->key_size != key_size) {
-		pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
-			   map->name, (__u32)key_size, def->key_size);
-		return -EINVAL;
-	}
-
-	value_size = btf__resolve_size(btf, value->type);
-	if (value_size < 0) {
-		pr_warning("map:%s invalid BTF value_type_size\n", map->name);
-		return value_size;
-	}
+	__u32 key_type_id, value_type_id;
+	int ret;
 
-	if (def->value_size != value_size) {
-		pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
-			   map->name, (__u32)value_size, def->value_size);
-		return -EINVAL;
-	}
+	ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
+				   def->value_size, &key_type_id,
+				   &value_type_id);
+	if (ret)
+		return ret;
 
-	map->btf_key_type_id = key->type;
-	map->btf_value_type_id = value->type;
+	map->btf_key_type_id = key_type_id;
+	map->btf_value_type_id = value_type_id;
 
 	return 0;
 }
@@ -1174,6 +1113,20 @@ err_free_new_name:
 	return -errno;
 }
 
+int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
+{
+	if (!map || !max_entries)
+		return -EINVAL;
+
+	/* If map already created, its attributes can't be changed. */
+	if (map->fd >= 0)
+		return -EBUSY;
+
+	map->def.max_entries = max_entries;
+
+	return 0;
+}
+
 static int
 bpf_object__probe_name(struct bpf_object *obj)
 {
@@ -1637,7 +1590,7 @@ bpf_program__load(struct bpf_program *prog,
 		struct bpf_prog_prep_result result;
 		bpf_program_prep_t preprocessor = prog->preprocessor;
 
-		bzero(&result, sizeof(result));
+		memset(&result, 0, sizeof(result));
 		err = preprocessor(prog, i, prog->insns,
 				   prog->insns_cnt, &result);
 		if (err) {
@@ -2378,6 +2331,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj)
 	return obj ? obj->kern_version : 0;
 }
 
+struct btf *bpf_object__btf(struct bpf_object *obj)
+{
+	return obj ? obj->btf : NULL;
+}
+
 int bpf_object__btf_fd(const struct bpf_object *obj)
 {
 	return obj->btf ? btf__fd(obj->btf) : -1;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 43c77e98df6f..6c0168f8bba5 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -47,17 +47,16 @@ enum libbpf_errno {
 
 LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size);
 
-/*
- * __printf is defined in include/linux/compiler-gcc.h. However,
- * it would be better if libbpf.h didn't depend on Linux header files.
- * So instead of __printf, here we use gcc attribute directly.
- */
-typedef int (*libbpf_print_fn_t)(const char *, ...)
-	__attribute__((format(printf, 1, 2)));
+enum libbpf_print_level {
+        LIBBPF_WARN,
+        LIBBPF_INFO,
+        LIBBPF_DEBUG,
+};
 
-LIBBPF_API void libbpf_set_print(libbpf_print_fn_t warn,
-				 libbpf_print_fn_t info,
-				 libbpf_print_fn_t debug);
+typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level,
+				 const char *, va_list ap);
+
+LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn);
 
 /* Hide internal to user */
 struct bpf_object;
@@ -90,6 +89,9 @@ LIBBPF_API int bpf_object__load(struct bpf_object *obj);
 LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
 LIBBPF_API const char *bpf_object__name(struct bpf_object *obj);
 LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj);
+
+struct btf;
+LIBBPF_API struct btf *bpf_object__btf(struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
 
 LIBBPF_API struct bpf_program *
@@ -295,6 +297,7 @@ LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
 				 bpf_map_clear_priv_t clear_priv);
 LIBBPF_API void *bpf_map__priv(struct bpf_map *map);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
+LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
 LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
 LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 62c680fb13d1..99dfa710c818 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -130,7 +130,21 @@ LIBBPF_0.0.2 {
 		bpf_probe_helper;
 		bpf_probe_map_type;
 		bpf_probe_prog_type;
+		bpf_map__resize;
 		bpf_map_lookup_elem_flags;
+		bpf_object__btf;
 		bpf_object__find_map_fd_by_name;
 		bpf_get_link_xdp_id;
+		btf__dedup;
+		btf__get_map_kv_tids;
+		btf__get_nr_types;
+		btf__get_raw_data;
+		btf__load;
+		btf_ext__free;
+		btf_ext__func_info_rec_size;
+		btf_ext__get_raw_data;
+		btf_ext__line_info_rec_size;
+		btf_ext__new;
+		btf_ext__reloc_func_info;
+		btf_ext__reloc_line_info;
 } LIBBPF_0.0.1;
diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h
new file mode 100644
index 000000000000..81ecda0cb9c9
--- /dev/null
+++ b/tools/lib/bpf/libbpf_util.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2019 Facebook */
+
+#ifndef __LIBBPF_LIBBPF_UTIL_H
+#define __LIBBPF_LIBBPF_UTIL_H
+
+#include <stdbool.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+extern void libbpf_print(enum libbpf_print_level level,
+			 const char *format, ...)
+	__attribute__((format(printf, 2, 3)));
+
+#define __pr(level, fmt, ...)	\
+do {				\
+	libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__);	\
+} while (0)
+
+#define pr_warning(fmt, ...)	__pr(LIBBPF_WARN, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...)	__pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...)	__pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif
diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.cpp
index abf3fc25c9fa..fc134873bb6d 100644
--- a/tools/lib/bpf/test_libbpf.cpp
+++ b/tools/lib/bpf/test_libbpf.cpp
@@ -8,11 +8,11 @@
 int main(int argc, char *argv[])
 {
     /* libbpf.h */
-    libbpf_set_print(NULL, NULL, NULL);
+    libbpf_set_print(NULL);
 
     /* bpf.h */
     bpf_prog_get_fd_by_id(0);
 
     /* btf.h */
-    btf__new(NULL, 0, NULL);
+    btf__new(NULL, 0);
 }
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 095aebdc5bb7..e6150f21267d 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -19,8 +19,11 @@ C2C stands for Cache To Cache.
 The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows
 you to track down the cacheline contentions.
 
-The tool is based on x86's load latency and precise store facility events
-provided by Intel CPUs. These events provide:
+On x86, the tool is based on load latency and precise store facility events
+provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling
+with thresholding feature.
+
+These events provide:
   - memory address of the access
   - type of the access (load and store details)
   - latency (in cycles) of the load access
@@ -46,7 +49,7 @@ RECORD OPTIONS
 
 -l::
 --ldlat::
-	Configure mem-loads latency.
+	Configure mem-loads latency. (x86 only)
 
 -k::
 --all-kernel::
@@ -119,11 +122,16 @@ Following perf record options are configured by default:
   -W,-d,--phys-data,--sample-cpu
 
 Unless specified otherwise with '-e' option, following events are monitored by
-default:
+default on x86:
 
   cpu/mem-loads,ldlat=30/P
   cpu/mem-stores/P
 
+and following on PowerPC:
+
+  cpu/mem-loads/
+  cpu/mem-stores/
+
 User can pass any 'perf record' option behind '--' mark, like (to enable
 callchains and system wide monitoring):
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index f8d2167cf3e7..199ea0f0a6c0 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -82,7 +82,7 @@ RECORD OPTIONS
 	Be more verbose (show counter open errors, etc)
 
 --ldlat <n>::
-	Specify desired latency for loads event.
+	Specify desired latency for loads event. (x86 only)
 
 In addition, for report all perf report options are valid, and for record
 all perf record options.
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 2e6595310420..ba98bd006488 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c
new file mode 100644
index 000000000000..d08311f04e95
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/mem-events.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "mem-events.h"
+
+/* PowerPC does not support 'ldlat' parameter. */
+char *perf_mem_events__name(int i)
+{
+	if (i == PERF_MEM_EVENTS__LOAD)
+		return (char *) "cpu/mem-loads/";
+
+	return (char *) "cpu/mem-stores/";
+}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index d079f36d342d..ac221f137ed2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1681,13 +1681,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 		.force_header = false,
 	};
 	struct perf_evsel *ev2;
-	static bool init;
 	u64 val;
 
-	if (!init) {
-		perf_stat__init_shadow_stats();
-		init = true;
-	}
 	if (!evsel->stats)
 		perf_evlist__alloc_stats(script->session->evlist, false);
 	if (evsel_script(evsel->leader)->gnum++ == 0)
@@ -1794,7 +1789,7 @@ static void process_event(struct perf_script *script,
 		return;
 	}
 
-	if (PRINT_FIELD(TRACE)) {
+	if (PRINT_FIELD(TRACE) && sample->raw_data) {
 		event_format__fprintf(evsel->tp_format, sample->cpu,
 				      sample->raw_data, sample->raw_size, fp);
 	}
@@ -2359,6 +2354,8 @@ static int __cmd_script(struct perf_script *script)
 
 	signal(SIGINT, sig_handler);
 
+	perf_stat__init_shadow_stats();
+
 	/* override event processing functions */
 	if (script->show_task_events) {
 		script->tool.comm = process_comm_event;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ed4583128b9c..b36061cd1ab8 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
 
 static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
+	bool found = false;
+	struct perf_evsel *evsel, *tmp;
+	struct parse_events_error err = { .idx = 0, };
+	int ret = parse_events(evlist, "probe:vfs_getname*", &err);
 
-	if (IS_ERR(evsel))
+	if (ret)
 		return false;
 
-	if (perf_evsel__field(evsel, "pathname") == NULL) {
+	evlist__for_each_entry_safe(evlist, evsel, tmp) {
+		if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
+			continue;
+
+		if (perf_evsel__field(evsel, "pathname")) {
+			evsel->handler = trace__vfs_getname;
+			found = true;
+			continue;
+		}
+
+		list_del_init(&evsel->node);
+		evsel->evlist = NULL;
 		perf_evsel__delete(evsel);
-		return false;
 	}
 
-	evsel->handler = trace__vfs_getname;
-	perf_evlist__add(evlist, evsel);
-	return true;
+	return found;
 }
 
 static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index 44090a9a19f3..e952127e4fb0 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -1,6 +1,8 @@
 #! /usr/bin/python
 # SPDX-License-Identifier: GPL-2.0
 
+from __future__ import print_function
+
 import os
 import sys
 import glob
@@ -8,7 +10,11 @@ import optparse
 import tempfile
 import logging
 import shutil
-import ConfigParser
+
+try:
+    import configparser
+except ImportError:
+    import ConfigParser as configparser
 
 def data_equal(a, b):
     # Allow multiple values in assignment separated by '|'
@@ -100,20 +106,20 @@ class Event(dict):
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s" % (t, self[t], other[t]));
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 return False
             if not data_equal(self[t], other[t]):
                 return False
         return True
 
     def optional(self):
-        if self.has_key('optional') and self['optional'] == '1':
+        if 'optional' in self and self['optional'] == '1':
             return True
         return False
 
     def diff(self, other):
         for t in Event.terms:
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 continue
             if not data_equal(self[t], other[t]):
                 log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
@@ -134,7 +140,7 @@ class Event(dict):
 #   - expected values assignments
 class Test(object):
     def __init__(self, path, options):
-        parser = ConfigParser.SafeConfigParser()
+        parser = configparser.SafeConfigParser()
         parser.read(path)
 
         log.warning("running '%s'" % path)
@@ -193,7 +199,7 @@ class Test(object):
         return True
 
     def load_events(self, path, events):
-        parser_event = ConfigParser.SafeConfigParser()
+        parser_event = configparser.SafeConfigParser()
         parser_event.read(path)
 
         # The event record section header contains 'event' word,
@@ -207,7 +213,7 @@ class Test(object):
             # Read parent event if there's any
             if (':' in section):
                 base = section[section.index(':') + 1:]
-                parser_base = ConfigParser.SafeConfigParser()
+                parser_base = configparser.SafeConfigParser()
                 parser_base.read(self.test_dir + '/' + base)
                 base_items = parser_base.items('event')
 
@@ -322,9 +328,9 @@ def run_tests(options):
     for f in glob.glob(options.test_dir + '/' + options.test):
         try:
             Test(f, options).run()
-        except Unsup, obj:
+        except Unsup as obj:
             log.warning("unsupp  %s" % obj.getMsg())
-        except Notest, obj:
+        except Notest as obj:
             log.warning("skipped %s" % obj.getMsg())
 
 def setup_log(verbose):
@@ -363,7 +369,7 @@ def main():
     parser.add_option("-p", "--perf",
                       action="store", type="string", dest="perf")
     parser.add_option("-v", "--verbose",
-                      action="count", dest="verbose")
+                      default=0, action="count", dest="verbose")
 
     options, args = parser.parse_args()
     if args:
@@ -373,7 +379,7 @@ def main():
     setup_log(options.verbose)
 
     if not options.test_dir:
-        print 'FAILED no -d option specified'
+        print('FAILED no -d option specified')
         sys.exit(-1)
 
     if not options.test:
@@ -382,8 +388,8 @@ def main():
     try:
         run_tests(options)
 
-    except Fail, obj:
-        print "FAILED %s" % obj.getMsg();
+    except Fail as obj:
+        print("FAILED %s" % obj.getMsg())
         sys.exit(-1)
 
     sys.exit(0)
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 5f8501c68da4..5cbba70bcdd0 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 		return -1;
 	}
 
-	is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
+	is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED);
 	if (should_be_signed && !is_signed) {
 		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
 			 evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 1d00e5ec7906..82e16bf84466 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -224,20 +224,24 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 	return ret;
 }
 
-static int disasm__cmp(struct annotation_line *a, struct annotation_line *b)
+static double disasm__cmp(struct annotation_line *a, struct annotation_line *b,
+						  int percent_type)
 {
 	int i;
 
 	for (i = 0; i < a->data_nr; i++) {
-		if (a->data[i].percent == b->data[i].percent)
+		if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type])
 			continue;
-		return a->data[i].percent < b->data[i].percent;
+		return a->data[i].percent[percent_type] -
+			   b->data[i].percent[percent_type];
 	}
 	return 0;
 }
 
-static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al)
+static void disasm_rb_tree__insert(struct annotate_browser *browser,
+				struct annotation_line *al)
 {
+	struct rb_root *root = &browser->entries;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct annotation_line *l;
@@ -246,7 +250,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line
 		parent = *p;
 		l = rb_entry(parent, struct annotation_line, rb_node);
 
-		if (disasm__cmp(al, l))
+		if (disasm__cmp(al, l, browser->opts->percent_type) < 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -329,7 +333,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 			RB_CLEAR_NODE(&pos->al.rb_node);
 			continue;
 		}
-		disasm_rb_tree__insert(&browser->entries, &pos->al);
+		disasm_rb_tree__insert(browser, &pos->al);
 	}
 	pthread_mutex_unlock(&notes->lock);
 
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 2f3eb6d293ee..037d8ff6a634 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -24,22 +24,12 @@
 #include "llvm-utils.h"
 #include "c++/clang-c.h"
 
-#define DEFINE_PRINT_FN(name, level) \
-static int libbpf_##name(const char *fmt, ...)	\
-{						\
-	va_list args;				\
-	int ret;				\
-						\
-	va_start(args, fmt);			\
-	ret = veprintf(level, verbose, pr_fmt(fmt), args);\
-	va_end(args);				\
-	return ret;				\
+static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)),
+			      const char *fmt, va_list args)
+{
+	return veprintf(1, verbose, pr_fmt(fmt), args);
 }
 
-DEFINE_PRINT_FN(warning, 1)
-DEFINE_PRINT_FN(info, 1)
-DEFINE_PRINT_FN(debug, 1)
-
 struct bpf_prog_priv {
 	bool is_tp;
 	char *sys_name;
@@ -59,9 +49,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
 	struct bpf_object *obj;
 
 	if (!libbpf_initialized) {
-		libbpf_set_print(libbpf_warning,
-				 libbpf_info,
-				 libbpf_debug);
+		libbpf_set_print(libbpf_perf_print);
 		libbpf_initialized = true;
 	}
 
@@ -79,9 +67,7 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 	struct bpf_object *obj;
 
 	if (!libbpf_initialized) {
-		libbpf_set_print(libbpf_warning,
-				 libbpf_info,
-				 libbpf_debug);
+		libbpf_set_print(libbpf_perf_print);
 		libbpf_initialized = true;
 	}
 
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 89512504551b..39c0004f2886 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module)
 	}
 	PM.run(*Module);
 
-	return std::move(Buffer);
+	return Buffer;
 }
 
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 1ccbd3342069..383674f448fc 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
 	if (!cpu_list)
 		return cpu_map__read_all_cpu_map();
 
-	if (!isdigit(*cpu_list))
+	/*
+	 * must handle the case of empty cpumap to cover
+	 * TOPOLOGY header for NUMA nodes with no CPU
+	 * ( e.g., because of CPU hotplug)
+	 */
+	if (!isdigit(*cpu_list) && *cpu_list != '\0')
 		goto out;
 
 	while (isdigit(*cpu_list)) {
@@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else
+	else if (*cpu_list != '\0')
 		cpus = cpu_map__default_new();
+	else
+		cpus = cpu_map__dummy_new();
 invalid:
 	free(tmp_cpus);
 out:
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 93f74d8d3cdd..42c3e5a229d2 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
-char *perf_mem_events__name(int i)
+char * __weak perf_mem_events__name(int i)
 {
 	if (i == PERF_MEM_EVENTS__LOAD) {
 		if (!mem_loads_name__init) {
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 897589507d97..ea523d3b248f 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -391,8 +391,10 @@ void ordered_events__free(struct ordered_events *oe)
 	 * Current buffer might not have all the events allocated
 	 * yet, we need to free only allocated ones ...
 	 */
-	list_del(&oe->buffer->list);
-	ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+	if (oe->buffer) {
+		list_del(&oe->buffer->list);
+		ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+	}
 
 	/* ... and continue with the rest */
 	list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 63f758c655d5..64d1f36dee99 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -17,6 +17,8 @@ if cc == "clang":
             vars[var] = sub("-mcet", "", vars[var])
         if not clang_has_option("-fcf-protection"):
             vars[var] = sub("-fcf-protection", "", vars[var])
+        if not clang_has_option("-fstack-clash-protection"):
+            vars[var] = sub("-fstack-clash-protection", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 66a84d5846c8..dca7dfae69ad 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -19,6 +19,20 @@
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+#ifndef ELF32_ST_VISIBILITY
+#define ELF32_ST_VISIBILITY(o)	((o) & 0x03)
+#endif
+
+/* For ELF64 the definitions are the same.  */
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o)	ELF32_ST_VISIBILITY (o)
+#endif
+
+/* How to extract information held in the st_other field.  */
+#ifndef GELF_ST_VISIBILITY
+#define GELF_ST_VISIBILITY(val)	ELF64_ST_VISIBILITY (val)
+#endif
+
 typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
@@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 	return GELF_ST_TYPE(sym->st_info);
 }
 
+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+	return GELF_ST_VISIBILITY(sym->st_other);
+}
+
 #ifndef STT_GNU_IFUNC
 #define STT_GNU_IFUNC 10
 #endif
@@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
 	return elf_sym__type(sym) == STT_NOTYPE &&
 		sym->st_name != 0 &&
 		sym->st_shndx != SHN_UNDEF &&
-		sym->st_shndx != SHN_ABS;
+		sym->st_shndx != SHN_ABS &&
+		elf_sym__visibility(sym) != STV_HIDDEN &&
+		elf_sym__visibility(sym) != STV_INTERNAL;
 }
 
 static bool elf_sym__filter(GElf_Sym *sym)
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 1a2bd15c5b6e..400ee81a3043 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -10,6 +10,7 @@ TARGETS += drivers/dma-buf
 TARGETS += efivarfs
 TARGETS += exec
 TARGETS += filesystems
+TARGETS += filesystems/binderfs
 TARGETS += firmware
 TARGETS += ftrace
 TARGETS += futex
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index dd093bd91aa9..e47168d1257d 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -29,3 +29,4 @@ test_netcnt
 test_section_names
 test_tcpnotify_user
 test_libbpf
+alu32
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 383d2ff13fc7..ccffaa0a0787 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,42 +23,19 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	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_section_names \
-	test_netcnt test_tcpnotify_user
-
-BPF_OBJ_FILES = \
-	test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
-	sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o \
-	test_tcpnotify_kern.o sample_map_ret0.o test_tcpbpf_kern.o \
-	sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o \
-	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o \
-	test_tunnel_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 netcnt_prog.o test_xdp_vlan.o \
-	xdp_dummy.o test_map_in_map.o test_spin_lock.o test_map_lock.o
-
-# Objects are built with default compilation flags and with sub-register
-# code-gen enabled.
-BPF_OBJ_FILES_DUAL_COMPILE = \
-	test_pkt_access.o test_pkt_access.o test_xdp.o test_adjust_tail.o \
-	test_l4lb.o test_l4lb_noinline.o test_xdp_noinline.o test_tcp_estats.o \
-	test_obj_id.o test_pkt_md_access.o test_tracepoint.o \
-	test_stacktrace_map.o test_stacktrace_map.o test_stacktrace_build_id.o \
-	test_stacktrace_build_id.o test_get_stack_rawtp.o \
-	test_get_stack_rawtp.o test_tracepoint.o test_sk_lookup_kern.o \
-	test_queue_map.o test_stack_map.o
-
-TEST_GEN_FILES = $(BPF_OBJ_FILES) $(BPF_OBJ_FILES_DUAL_COMPILE)
-
-# Also test sub-register code-gen if LLVM + kernel both has eBPF v3 processor
-# support which is the first version to contain both ALU32 and JMP32
-# instructions.
+	test_netcnt test_tcpnotify_user test_sock_fields
+
+BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
+TEST_GEN_FILES = $(BPF_OBJ_FILES)
+
+# Also test sub-register code-gen if LLVM has eBPF v3 processor support which
+# contains both ALU32 and JMP32 instructions.
 SUBREG_CODEGEN := $(shell echo "int cal(int a) { return a > 0; }" | \
 			$(CLANG) -target bpf -O2 -emit-llvm -S -x c - -o - | \
-			$(LLC) -mattr=+alu32 -mcpu=probe 2>&1 | \
+			$(LLC) -mattr=+alu32 -mcpu=v3 2>&1 | \
 			grep 'if w')
 ifneq ($(SUBREG_CODEGEN),)
-TEST_GEN_FILES += $(patsubst %.o,alu32/%.o, $(BPF_OBJ_FILES_DUAL_COMPILE))
+TEST_GEN_FILES += $(patsubst %.o,alu32/%.o, $(BPF_OBJ_FILES))
 endif
 
 # Order correspond to 'make run_tests' order
@@ -73,7 +50,8 @@ TEST_PROGS := test_kmod.sh \
 	test_lirc_mode2.sh \
 	test_skb_cgroup_id.sh \
 	test_flow_dissector.sh \
-	test_xdp_vlan.sh
+	test_xdp_vlan.sh \
+	test_lwt_ip_encap.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
@@ -111,6 +89,7 @@ $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
 $(OUTPUT)/test_netcnt: cgroup_helpers.c
+$(OUTPUT)/test_sock_fields: cgroup_helpers.c
 
 .PHONY: force
 
@@ -188,7 +167,8 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(ALU32_BUILD_DIR) \
 	$(CC) $(CFLAGS) -o $(ALU32_BUILD_DIR)/test_progs_32 $< \
 		trace_helpers.c $(OUTPUT)/libbpf.a $(LDLIBS)
 
-$(ALU32_BUILD_DIR)/%.o: %.c $(ALU32_BUILD_DIR) $(ALU32_BUILD_DIR)/test_progs_32
+$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \
+					$(ALU32_BUILD_DIR)/test_progs_32
 	$(CLANG) $(CLANG_FLAGS) \
 		 -O2 -target bpf -emit-llvm -c $< -o - |      \
 	$(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \
@@ -200,7 +180,7 @@ endif
 
 # Have one program compiled without "-target bpf" to test whether libbpf loads
 # it successfully
-$(OUTPUT)/test_xdp.o: test_xdp.c
+$(OUTPUT)/test_xdp.o: progs/test_xdp.c
 	$(CLANG) $(CLANG_FLAGS) \
 		-O2 -emit-llvm -c $< -o - | \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
@@ -208,7 +188,7 @@ ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
 endif
 
-$(OUTPUT)/%.o: %.c
+$(OUTPUT)/%.o: progs/%.c
 	$(CLANG) $(CLANG_FLAGS) \
 		 -O2 -target bpf -emit-llvm -c $< -o - |      \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 6a0ce0f055c5..d9999f1ed1d2 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -176,6 +176,10 @@ static void (*bpf_spin_lock)(struct bpf_spin_lock *lock) =
 	(void *) BPF_FUNC_spin_lock;
 static void (*bpf_spin_unlock)(struct bpf_spin_lock *lock) =
 	(void *) BPF_FUNC_spin_unlock;
+static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) =
+	(void *) BPF_FUNC_sk_fullsock;
+static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) =
+	(void *) BPF_FUNC_tcp_sock;
 
 /* 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/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 315a44fa32af..a29206ebbd13 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -13,7 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void)
 	unsigned int start, end, possible_cpus = 0;
 	char buff[128];
 	FILE *fp;
-	int n;
+	int len, n, i, j = 0;
 
 	fp = fopen(fcpu, "r");
 	if (!fp) {
@@ -21,17 +21,27 @@ static inline unsigned int bpf_num_possible_cpus(void)
 		exit(1);
 	}
 
-	while (fgets(buff, sizeof(buff), fp)) {
-		n = sscanf(buff, "%u-%u", &start, &end);
-		if (n == 0) {
-			printf("Failed to retrieve # possible CPUs!\n");
-			exit(1);
-		} else if (n == 1) {
-			end = start;
+	if (!fgets(buff, sizeof(buff), fp)) {
+		printf("Failed to read %s!\n", fcpu);
+		exit(1);
+	}
+
+	len = strlen(buff);
+	for (i = 0; i <= len; i++) {
+		if (buff[i] == ',' || buff[i] == '\0') {
+			buff[i] = '\0';
+			n = sscanf(&buff[j], "%u-%u", &start, &end);
+			if (n <= 0) {
+				printf("Failed to retrieve # possible CPUs!\n");
+				exit(1);
+			} else if (n == 1) {
+				end = start;
+			}
+			possible_cpus += end - start + 1;
+			j = i + 1;
 		}
-		possible_cpus = start == 0 ? end + 1 : 0;
-		break;
 	}
+
 	fclose(fp);
 
 	return possible_cpus;
@@ -48,4 +58,13 @@ static inline unsigned int bpf_num_possible_cpus(void)
 # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #endif
 
+#ifndef sizeof_field
+#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
+#endif
+
+#ifndef offsetofend
+#define offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER)	+ sizeof_field(TYPE, MEMBER))
+#endif
+
 #endif /* __BPF_UTIL__ */
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 284660f5aa95..284660f5aa95 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
diff --git a/tools/testing/selftests/bpf/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index 1fd244d35ba9..1fd244d35ba9 100644
--- a/tools/testing/selftests/bpf/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
diff --git a/tools/testing/selftests/bpf/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c
index 26397ab7b3c7..26397ab7b3c7 100644
--- a/tools/testing/selftests/bpf/connect6_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect6_prog.c
diff --git a/tools/testing/selftests/bpf/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c
index ce41a3475f27..ce41a3475f27 100644
--- a/tools/testing/selftests/bpf/dev_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c
diff --git a/tools/testing/selftests/bpf/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
index 014dba10b8a5..014dba10b8a5 100644
--- a/tools/testing/selftests/bpf/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c
index 9f741e69cebe..9f741e69cebe 100644
--- a/tools/testing/selftests/bpf/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
diff --git a/tools/testing/selftests/bpf/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
index 0756303676ac..0756303676ac 100644
--- a/tools/testing/selftests/bpf/sample_map_ret0.c
+++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c
diff --git a/tools/testing/selftests/bpf/sample_ret0.c b/tools/testing/selftests/bpf/progs/sample_ret0.c
index fec99750d6ea..fec99750d6ea 100644
--- a/tools/testing/selftests/bpf/sample_ret0.c
+++ b/tools/testing/selftests/bpf/progs/sample_ret0.c
diff --git a/tools/testing/selftests/bpf/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
index a91536b1c47e..a91536b1c47e 100644
--- a/tools/testing/selftests/bpf/sendmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
index 5aeaa284fc47..5aeaa284fc47 100644
--- a/tools/testing/selftests/bpf/sendmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
diff --git a/tools/testing/selftests/bpf/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
index 9ff8ac4b0bf6..9ff8ac4b0bf6 100644
--- a/tools/testing/selftests/bpf/socket_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c
diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
index 0f92858f6226..0f92858f6226 100644
--- a/tools/testing/selftests/bpf/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
diff --git a/tools/testing/selftests/bpf/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
index 12a7b5c82ed6..12a7b5c82ed6 100644
--- a/tools/testing/selftests/bpf/sockmap_tcp_msg_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index 2ce7634a4012..2ce7634a4012 100644
--- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
diff --git a/tools/testing/selftests/bpf/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_adjust_tail.c
index 4cd5e860c903..4cd5e860c903 100644
--- a/tools/testing/selftests/bpf/test_adjust_tail.c
+++ b/tools/testing/selftests/bpf/progs/test_adjust_tail.c
diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index e5c79fe0ffdb..e5c79fe0ffdb 100644
--- a/tools/testing/selftests/bpf/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
index 434188c37774..434188c37774 100644
--- a/tools/testing/selftests/bpf/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
diff --git a/tools/testing/selftests/bpf/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index f6d9f238e00a..f6d9f238e00a 100644
--- a/tools/testing/selftests/bpf/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
diff --git a/tools/testing/selftests/bpf/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c
index 1e10c9590991..1e10c9590991 100644
--- a/tools/testing/selftests/bpf/test_l4lb.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb.c
diff --git a/tools/testing/selftests/bpf/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
index ba44a14e6dc4..ba44a14e6dc4 100644
--- a/tools/testing/selftests/bpf/test_l4lb_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
index 4147130cc3b7..4147130cc3b7 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
new file mode 100644
index 000000000000..c957d6dfe6d7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+struct grehdr {
+	__be16 flags;
+	__be16 protocol;
+};
+
+SEC("encap_gre")
+int bpf_lwt_encap_gre(struct __sk_buff *skb)
+{
+	struct encap_hdr {
+		struct iphdr iph;
+		struct grehdr greh;
+	} hdr;
+	int err;
+
+	memset(&hdr, 0, sizeof(struct encap_hdr));
+
+	hdr.iph.ihl = 5;
+	hdr.iph.version = 4;
+	hdr.iph.ttl = 0x40;
+	hdr.iph.protocol = 47;  /* IPPROTO_GRE */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	hdr.iph.saddr = 0x640110ac;  /* 172.16.1.100 */
+	hdr.iph.daddr = 0x641010ac;  /* 172.16.16.100 */
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	hdr.iph.saddr = 0xac100164;  /* 172.16.1.100 */
+	hdr.iph.daddr = 0xac101064;  /* 172.16.16.100 */
+#else
+#error "Fix your compiler's __BYTE_ORDER__?!"
+#endif
+	hdr.iph.tot_len = bpf_htons(skb->len + sizeof(struct encap_hdr));
+
+	hdr.greh.protocol = skb->protocol;
+
+	err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr,
+				 sizeof(struct encap_hdr));
+	if (err)
+		return BPF_DROP;
+
+	return BPF_LWT_REROUTE;
+}
+
+SEC("encap_gre6")
+int bpf_lwt_encap_gre6(struct __sk_buff *skb)
+{
+	struct encap_hdr {
+		struct ipv6hdr ip6hdr;
+		struct grehdr greh;
+	} hdr;
+	int err;
+
+	memset(&hdr, 0, sizeof(struct encap_hdr));
+
+	hdr.ip6hdr.version = 6;
+	hdr.ip6hdr.payload_len = bpf_htons(skb->len + sizeof(struct grehdr));
+	hdr.ip6hdr.nexthdr = 47;  /* IPPROTO_GRE */
+	hdr.ip6hdr.hop_limit = 0x40;
+	/* fb01::1 */
+	hdr.ip6hdr.saddr.s6_addr[0] = 0xfb;
+	hdr.ip6hdr.saddr.s6_addr[1] = 1;
+	hdr.ip6hdr.saddr.s6_addr[15] = 1;
+	/* fb10::1 */
+	hdr.ip6hdr.daddr.s6_addr[0] = 0xfb;
+	hdr.ip6hdr.daddr.s6_addr[1] = 0x10;
+	hdr.ip6hdr.daddr.s6_addr[15] = 1;
+
+	hdr.greh.protocol = skb->protocol;
+
+	err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr,
+				 sizeof(struct encap_hdr));
+	if (err)
+		return BPF_DROP;
+
+	return BPF_LWT_REROUTE;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 0575751bc1bc..0575751bc1bc 100644
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
diff --git a/tools/testing/selftests/bpf/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index ce923e67e08e..ce923e67e08e 100644
--- a/tools/testing/selftests/bpf/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
diff --git a/tools/testing/selftests/bpf/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c
index af8cc68ed2f9..af8cc68ed2f9 100644
--- a/tools/testing/selftests/bpf/test_map_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_map_lock.c
diff --git a/tools/testing/selftests/bpf/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c
index 880d2963b472..880d2963b472 100644
--- a/tools/testing/selftests/bpf/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c
index 6e11ba11709e..6e11ba11709e 100644
--- a/tools/testing/selftests/bpf/test_pkt_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c
diff --git a/tools/testing/selftests/bpf/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
index 7956302ecdf2..7956302ecdf2 100644
--- a/tools/testing/selftests/bpf/test_pkt_md_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
diff --git a/tools/testing/selftests/bpf/test_queue_map.c b/tools/testing/selftests/bpf/progs/test_queue_map.c
index 87db1f9da33d..87db1f9da33d 100644
--- a/tools/testing/selftests/bpf/test_queue_map.c
+++ b/tools/testing/selftests/bpf/progs/test_queue_map.c
diff --git a/tools/testing/selftests/bpf/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 5b54ec637ada..5b54ec637ada 100644
--- a/tools/testing/selftests/bpf/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
diff --git a/tools/testing/selftests/bpf/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index e21cd736c196..e21cd736c196 100644
--- a/tools/testing/selftests/bpf/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
index 68cf9829f5a7..68cf9829f5a7 100644
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
new file mode 100644
index 000000000000..de1a43e8f610
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/bpf.h>
+#include <netinet/in.h>
+#include <stdbool.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+enum bpf_array_idx {
+	SRV_IDX,
+	CLI_IDX,
+	__NR_BPF_ARRAY_IDX,
+};
+
+struct bpf_map_def SEC("maps") addr_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct sockaddr_in6),
+	.max_entries = __NR_BPF_ARRAY_IDX,
+};
+
+struct bpf_map_def SEC("maps") sock_result_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct bpf_sock),
+	.max_entries = __NR_BPF_ARRAY_IDX,
+};
+
+struct bpf_map_def SEC("maps") tcp_sock_result_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct bpf_tcp_sock),
+	.max_entries = __NR_BPF_ARRAY_IDX,
+};
+
+struct bpf_map_def SEC("maps") linum_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+};
+
+static bool is_loopback6(__u32 *a6)
+{
+	return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1);
+}
+
+static void skcpy(struct bpf_sock *dst,
+		  const struct bpf_sock *src)
+{
+	dst->bound_dev_if = src->bound_dev_if;
+	dst->family = src->family;
+	dst->type = src->type;
+	dst->protocol = src->protocol;
+	dst->mark = src->mark;
+	dst->priority = src->priority;
+	dst->src_ip4 = src->src_ip4;
+	dst->src_ip6[0] = src->src_ip6[0];
+	dst->src_ip6[1] = src->src_ip6[1];
+	dst->src_ip6[2] = src->src_ip6[2];
+	dst->src_ip6[3] = src->src_ip6[3];
+	dst->src_port = src->src_port;
+	dst->dst_ip4 = src->dst_ip4;
+	dst->dst_ip6[0] = src->dst_ip6[0];
+	dst->dst_ip6[1] = src->dst_ip6[1];
+	dst->dst_ip6[2] = src->dst_ip6[2];
+	dst->dst_ip6[3] = src->dst_ip6[3];
+	dst->dst_port = src->dst_port;
+	dst->state = src->state;
+}
+
+static void tpcpy(struct bpf_tcp_sock *dst,
+		  const struct bpf_tcp_sock *src)
+{
+	dst->snd_cwnd = src->snd_cwnd;
+	dst->srtt_us = src->srtt_us;
+	dst->rtt_min = src->rtt_min;
+	dst->snd_ssthresh = src->snd_ssthresh;
+	dst->rcv_nxt = src->rcv_nxt;
+	dst->snd_nxt = src->snd_nxt;
+	dst->snd_una = src->snd_una;
+	dst->mss_cache = src->mss_cache;
+	dst->ecn_flags = src->ecn_flags;
+	dst->rate_delivered = src->rate_delivered;
+	dst->rate_interval_us = src->rate_interval_us;
+	dst->packets_out = src->packets_out;
+	dst->retrans_out = src->retrans_out;
+	dst->total_retrans = src->total_retrans;
+	dst->segs_in = src->segs_in;
+	dst->data_segs_in = src->data_segs_in;
+	dst->segs_out = src->segs_out;
+	dst->data_segs_out = src->data_segs_out;
+	dst->lost_out = src->lost_out;
+	dst->sacked_out = src->sacked_out;
+	dst->bytes_received = src->bytes_received;
+	dst->bytes_acked = src->bytes_acked;
+}
+
+#define RETURN {						\
+	linum = __LINE__;					\
+	bpf_map_update_elem(&linum_map, &idx0, &linum, 0);	\
+	return 1;						\
+}
+
+SEC("cgroup_skb/egress")
+int read_sock_fields(struct __sk_buff *skb)
+{
+	__u32 srv_idx = SRV_IDX, cli_idx = CLI_IDX, idx;
+	struct sockaddr_in6 *srv_sa6, *cli_sa6;
+	struct bpf_tcp_sock *tp, *tp_ret;
+	struct bpf_sock *sk, *sk_ret;
+	__u32 linum, idx0 = 0;
+
+	sk = skb->sk;
+	if (!sk || sk->state == 10)
+		RETURN;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk || sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP ||
+	    !is_loopback6(sk->src_ip6))
+		RETURN;
+
+	tp = bpf_tcp_sock(sk);
+	if (!tp)
+		RETURN;
+
+	srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx);
+	cli_sa6 = bpf_map_lookup_elem(&addr_map, &cli_idx);
+	if (!srv_sa6 || !cli_sa6)
+		RETURN;
+
+	if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port))
+		idx = srv_idx;
+	else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port))
+		idx = cli_idx;
+	else
+		RETURN;
+
+	sk_ret = bpf_map_lookup_elem(&sock_result_map, &idx);
+	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &idx);
+	if (!sk_ret || !tp_ret)
+		RETURN;
+
+	skcpy(sk_ret, sk);
+	tpcpy(tp_ret, tp);
+
+	RETURN;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_sockhash_kern.c b/tools/testing/selftests/bpf/progs/test_sockhash_kern.c
index e6755916442a..e6755916442a 100644
--- a/tools/testing/selftests/bpf/test_sockhash_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sockhash_kern.c
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.c b/tools/testing/selftests/bpf/progs/test_sockmap_kern.c
index 677b2ed1cc1e..677b2ed1cc1e 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.c
diff --git a/tools/testing/selftests/bpf/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c
index 40f904312090..40f904312090 100644
--- a/tools/testing/selftests/bpf/test_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c
diff --git a/tools/testing/selftests/bpf/test_stack_map.c b/tools/testing/selftests/bpf/progs/test_stack_map.c
index 31c3880e6da0..31c3880e6da0 100644
--- a/tools/testing/selftests/bpf/test_stack_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stack_map.c
diff --git a/tools/testing/selftests/bpf/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index d86c281e957f..d86c281e957f 100644
--- a/tools/testing/selftests/bpf/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
diff --git a/tools/testing/selftests/bpf/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index af111af7ca1a..af111af7ca1a 100644
--- a/tools/testing/selftests/bpf/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
diff --git a/tools/testing/selftests/bpf/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
index bee3bbecc0c4..bee3bbecc0c4 100644
--- a/tools/testing/selftests/bpf/test_tcp_estats.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 74f73b33a7b0..74f73b33a7b0 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index edbca203ce2d..edbca203ce2d 100644
--- a/tools/testing/selftests/bpf/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
diff --git a/tools/testing/selftests/bpf/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index 04bf084517e0..04bf084517e0 100644
--- a/tools/testing/selftests/bpf/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
diff --git a/tools/testing/selftests/bpf/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 504df69c83df..504df69c83df 100644
--- a/tools/testing/selftests/bpf/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
diff --git a/tools/testing/selftests/bpf/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index 5e7df8bb5b5d..5e7df8bb5b5d 100644
--- a/tools/testing/selftests/bpf/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
index 8d0182650653..8d0182650653 100644
--- a/tools/testing/selftests/bpf/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
diff --git a/tools/testing/selftests/bpf/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index 5e4aac74f9d0..5e4aac74f9d0 100644
--- a/tools/testing/selftests/bpf/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
index ef9e704be140..ef9e704be140 100644
--- a/tools/testing/selftests/bpf/test_xdp_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
index 365a7d2d9f5c..365a7d2d9f5c 100644
--- a/tools/testing/selftests/bpf/test_xdp_vlan.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
diff --git a/tools/testing/selftests/bpf/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c
index 43b0ef1001ed..43b0ef1001ed 100644
--- a/tools/testing/selftests/bpf/xdp_dummy.c
+++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
index 7f8200a8702b..a53ed58528d6 100755
--- a/tools/testing/selftests/bpf/tcp_client.py
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -30,12 +30,11 @@ def send(sock, s):
 
 
 serverPort = int(sys.argv[1])
-HostName = socket.gethostname()
 
 # create active socket
 sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
 try:
-    sock.connect((HostName, serverPort))
+    sock.connect(('localhost', serverPort))
 except socket.error as e:
     sys.exit(1)
 
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
index b39903fca4c8..0ca60d193bed 100755
--- a/tools/testing/selftests/bpf/tcp_server.py
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -35,13 +35,10 @@ MAX_PORTS = 2
 serverPort = SERVER_PORT
 serverSocket = None
 
-HostName = socket.gethostname()
-
 # create passive socket
 serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
-host = socket.gethostname()
 
-try: serverSocket.bind((host, 0))
+try: serverSocket.bind(('localhost', 0))
 except socket.error as msg:
     print('bind fails: ' + str(msg))
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 179f1d8ec5bf..02d314383a9c 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -52,18 +52,10 @@ static int count_result(int err)
 	return err;
 }
 
-#define __printf(a, b)	__attribute__((format(printf, a, b)))
-
-__printf(1, 2)
-static int __base_pr(const char *format, ...)
+static int __base_pr(enum libbpf_print_level level __attribute__((unused)),
+		     const char *format, va_list args)
 {
-	va_list args;
-	int err;
-
-	va_start(args, format);
-	err = vfprintf(stderr, format, args);
-	va_end(args);
-	return err;
+	return vfprintf(stderr, format, args);
 }
 
 #define BTF_INFO_ENC(kind, kind_flag, vlen)			\
@@ -78,12 +70,21 @@ static int __base_pr(const char *format, ...)
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz),	\
 	BTF_INT_ENC(encoding, bits_offset, bits)
 
+#define BTF_FWD_ENC(name, kind_flag) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0)
+
 #define BTF_ARRAY_ENC(type, index_type, nr_elems)	\
 	(type), (index_type), (nr_elems)
 #define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \
 	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \
 	BTF_ARRAY_ENC(type, index_type, nr_elems)
 
+#define BTF_STRUCT_ENC(name, nr_elems, sz)	\
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz)
+
+#define BTF_UNION_ENC(name, nr_elems, sz)	\
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz)
+
 #define BTF_MEMBER_ENC(name, type, bits_offset)	\
 	(name), (type), (bits_offset)
 #define BTF_ENUM_ENC(name, val) (name), (val)
@@ -99,6 +100,12 @@ static int __base_pr(const char *format, ...)
 #define BTF_CONST_ENC(type) \
 	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type)
 
+#define BTF_VOLATILE_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type)
+
+#define BTF_RESTRICT_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type)
+
 #define BTF_FUNC_PROTO_ENC(ret_type, nargs) \
 	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type)
 
@@ -111,6 +118,10 @@ static int __base_pr(const char *format, ...)
 #define BTF_END_RAW 0xdeadbeef
 #define NAME_TBD 0xdeadb33f
 
+#define NAME_NTH(N) (0xffff0000 | N)
+#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xffff0000)
+#define GET_NAME_NTH_IDX(X) (X & 0x0000ffff)
+
 #define MAX_NR_RAW_U32 1024
 #define BTF_LOG_BUF_SIZE 65535
 
@@ -119,12 +130,14 @@ static struct args {
 	unsigned int file_test_num;
 	unsigned int get_info_test_num;
 	unsigned int info_raw_test_num;
+	unsigned int dedup_test_num;
 	bool raw_test;
 	bool file_test;
 	bool get_info_test;
 	bool pprint_test;
 	bool always_log;
 	bool info_raw_test;
+	bool dedup_test;
 } args;
 
 static char btf_log_buf[BTF_LOG_BUF_SIZE];
@@ -1889,13 +1902,12 @@ static struct btf_raw_test raw_tests[] = {
 },
 
 {
-	.descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)",
+	.descr = "func proto (TYPEDEF=>FUNC_PROTO)",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),		/* [2] */
-		BTF_CONST_ENC(4),				/* [3] */
-		BTF_TYPEDEF_ENC(NAME_TBD, 5),			/* [4] */
-		BTF_FUNC_PROTO_ENC(0, 2),			/* [5] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),			/* [3] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [4] */
 			BTF_FUNC_PROTO_ARG_ENC(0, 1),
 			BTF_FUNC_PROTO_ARG_ENC(0, 2),
 		BTF_END_RAW,
@@ -1909,8 +1921,6 @@ static struct btf_raw_test raw_tests[] = {
 	.key_type_id = 1,
 	.value_type_id = 1,
 	.max_entries = 4,
-	.btf_load_err = true,
-	.err_str = "Invalid type_id",
 },
 
 {
@@ -1965,7 +1975,7 @@ static struct btf_raw_test raw_tests[] = {
 		/* void (*)(int a, unsigned int <bad_name_off>) */
 		BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
-			BTF_FUNC_PROTO_ARG_ENC(0xffffffff, 2),
+			BTF_FUNC_PROTO_ARG_ENC(0x0fffffff, 2),
 		BTF_END_RAW,
 	},
 	.str_sec = "\0a",
@@ -2835,11 +2845,13 @@ static void *btf_raw_create(const struct btf_header *hdr,
 			    const char **ret_next_str)
 {
 	const char *next_str = str, *end_str = str + str_sec_size;
+	const char **strs_idx = NULL, **tmp_strs_idx;
+	int strs_cap = 0, strs_cnt = 0, next_str_idx = 0;
 	unsigned int size_needed, offset;
 	struct btf_header *ret_hdr;
-	int i, type_sec_size;
+	int i, type_sec_size, err = 0;
 	uint32_t *ret_types;
-	void *raw_btf;
+	void *raw_btf = NULL;
 
 	type_sec_size = get_raw_sec_size(raw_types);
 	if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types"))
@@ -2854,17 +2866,44 @@ static void *btf_raw_create(const struct btf_header *hdr,
 	memcpy(raw_btf, hdr, sizeof(*hdr));
 	offset = sizeof(*hdr);
 
+	/* Index strings */
+	while ((next_str = get_next_str(next_str, end_str))) {
+		if (strs_cnt == strs_cap) {
+			strs_cap += max(16, strs_cap / 2);
+			tmp_strs_idx = realloc(strs_idx,
+					       sizeof(*strs_idx) * strs_cap);
+			if (CHECK(!tmp_strs_idx,
+				  "Cannot allocate memory for strs_idx")) {
+				err = -1;
+				goto done;
+			}
+			strs_idx = tmp_strs_idx;
+		}
+		strs_idx[strs_cnt++] = next_str;
+		next_str += strlen(next_str);
+	}
+
 	/* Copy type section */
 	ret_types = raw_btf + offset;
 	for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) {
 		if (raw_types[i] == NAME_TBD) {
-			next_str = get_next_str(next_str, end_str);
-			if (CHECK(!next_str, "Error in getting next_str")) {
-				free(raw_btf);
-				return NULL;
+			if (CHECK(next_str_idx == strs_cnt,
+				  "Error in getting next_str #%d",
+				  next_str_idx)) {
+				err = -1;
+				goto done;
 			}
-			ret_types[i] = next_str - str;
-			next_str += strlen(next_str);
+			ret_types[i] = strs_idx[next_str_idx++] - str;
+		} else if (IS_NAME_NTH(raw_types[i])) {
+			int idx = GET_NAME_NTH_IDX(raw_types[i]);
+
+			if (CHECK(idx <= 0 || idx > strs_cnt,
+				  "Error getting string #%d, strs_cnt:%d",
+				  idx, strs_cnt)) {
+				err = -1;
+				goto done;
+			}
+			ret_types[i] = strs_idx[idx-1] - str;
 		} else {
 			ret_types[i] = raw_types[i];
 		}
@@ -2881,8 +2920,17 @@ static void *btf_raw_create(const struct btf_header *hdr,
 
 	*btf_size = size_needed;
 	if (ret_next_str)
-		*ret_next_str = next_str;
+		*ret_next_str =
+			next_str_idx < strs_cnt ? strs_idx[next_str_idx] : NULL;
 
+done:
+	if (err) {
+		if (raw_btf)
+			free(raw_btf);
+		if (strs_idx)
+			free(strs_idx);
+		return NULL;
+	}
 	return raw_btf;
 }
 
@@ -5551,20 +5599,463 @@ static int test_info_raw(void)
 	return err;
 }
 
+struct btf_raw_data {
+	__u32 raw_types[MAX_NR_RAW_U32];
+	const char *str_sec;
+	__u32 str_sec_size;
+};
+
+struct btf_dedup_test {
+	const char *descr;
+	struct btf_raw_data input;
+	struct btf_raw_data expect;
+	struct btf_dedup_opts opts;
+};
+
+const struct btf_dedup_test dedup_tests[] = {
+
+{
+	.descr = "dedup: unused strings filtering",
+	.input = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_TYPE_INT_ENC(NAME_NTH(5), BTF_INT_SIGNED, 0, 64, 8),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0unused\0int\0foo\0bar\0long"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 64, 8),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0int\0long"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
+{
+	.descr = "dedup: strings deduplication",
+	.input = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 64, 8),
+			BTF_TYPE_INT_ENC(NAME_NTH(3), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_TYPE_INT_ENC(NAME_NTH(4), BTF_INT_SIGNED, 0, 64, 8),
+			BTF_TYPE_INT_ENC(NAME_NTH(5), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0int\0long int\0int\0long int\0int"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 64, 8),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0int\0long int"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
+{
+	.descr = "dedup: struct example #1",
+	/*
+	 * struct s {
+	 *	struct s *next;
+	 *	const int *a;
+	 *	int b[16];
+	 *	int c;
+	 * }
+	 */
+	.input = {
+		.raw_types = {
+			/* int */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			/* int[16] */
+			BTF_TYPE_ARRAY_ENC(1, 1, 16),					/* [2] */
+			/* struct s { */
+			BTF_STRUCT_ENC(NAME_NTH(2), 4, 84),				/* [3] */
+				BTF_MEMBER_ENC(NAME_NTH(3), 4, 0),	/* struct s *next;	*/
+				BTF_MEMBER_ENC(NAME_NTH(4), 5, 64),	/* const int *a;	*/
+				BTF_MEMBER_ENC(NAME_NTH(5), 2, 128),	/* int b[16];		*/
+				BTF_MEMBER_ENC(NAME_NTH(6), 1, 640),	/* int c;		*/
+			/* ptr -> [3] struct s */
+			BTF_PTR_ENC(3),							/* [4] */
+			/* ptr -> [6] const int */
+			BTF_PTR_ENC(6),							/* [5] */
+			/* const -> [1] int */
+			BTF_CONST_ENC(1),						/* [6] */
+
+			/* full copy of the above */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),	/* [7] */
+			BTF_TYPE_ARRAY_ENC(7, 7, 16),					/* [8] */
+			BTF_STRUCT_ENC(NAME_NTH(2), 4, 84),				/* [9] */
+				BTF_MEMBER_ENC(NAME_NTH(3), 10, 0),
+				BTF_MEMBER_ENC(NAME_NTH(4), 11, 64),
+				BTF_MEMBER_ENC(NAME_NTH(5), 8, 128),
+				BTF_MEMBER_ENC(NAME_NTH(6), 7, 640),
+			BTF_PTR_ENC(9),							/* [10] */
+			BTF_PTR_ENC(12),						/* [11] */
+			BTF_CONST_ENC(7),						/* [12] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0"),
+	},
+	.expect = {
+		.raw_types = {
+			/* int */
+			BTF_TYPE_INT_ENC(NAME_NTH(4), BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			/* int[16] */
+			BTF_TYPE_ARRAY_ENC(1, 1, 16),					/* [2] */
+			/* struct s { */
+			BTF_STRUCT_ENC(NAME_NTH(6), 4, 84),				/* [3] */
+				BTF_MEMBER_ENC(NAME_NTH(5), 4, 0),	/* struct s *next;	*/
+				BTF_MEMBER_ENC(NAME_NTH(1), 5, 64),	/* const int *a;	*/
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 128),	/* int b[16];		*/
+				BTF_MEMBER_ENC(NAME_NTH(3), 1, 640),	/* int c;		*/
+			/* ptr -> [3] struct s */
+			BTF_PTR_ENC(3),							/* [4] */
+			/* ptr -> [6] const int */
+			BTF_PTR_ENC(6),							/* [5] */
+			/* const -> [1] int */
+			BTF_CONST_ENC(1),						/* [6] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0a\0b\0c\0int\0next\0s"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
+{
+	.descr = "dedup: all possible kinds (no duplicates)",
+	.input = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 8),		/* [1] int */
+			BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), 4),	/* [2] enum */
+				BTF_ENUM_ENC(NAME_TBD, 0),
+				BTF_ENUM_ENC(NAME_TBD, 1),
+			BTF_FWD_ENC(NAME_TBD, 1 /* union kind_flag */),			/* [3] fwd */
+			BTF_TYPE_ARRAY_ENC(2, 1, 7),					/* [4] array */
+			BTF_STRUCT_ENC(NAME_TBD, 1, 4),					/* [5] struct */
+				BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+			BTF_UNION_ENC(NAME_TBD, 1, 4),					/* [6] union */
+				BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+			BTF_TYPEDEF_ENC(NAME_TBD, 1),					/* [7] typedef */
+			BTF_PTR_ENC(0),							/* [8] ptr */
+			BTF_CONST_ENC(8),						/* [9] const */
+			BTF_VOLATILE_ENC(8),						/* [10] volatile */
+			BTF_RESTRICT_ENC(8),						/* [11] restrict */
+			BTF_FUNC_PROTO_ENC(1, 2),					/* [12] func_proto */
+				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
+			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 8),		/* [1] int */
+			BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), 4),	/* [2] enum */
+				BTF_ENUM_ENC(NAME_TBD, 0),
+				BTF_ENUM_ENC(NAME_TBD, 1),
+			BTF_FWD_ENC(NAME_TBD, 1 /* union kind_flag */),			/* [3] fwd */
+			BTF_TYPE_ARRAY_ENC(2, 1, 7),					/* [4] array */
+			BTF_STRUCT_ENC(NAME_TBD, 1, 4),					/* [5] struct */
+				BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+			BTF_UNION_ENC(NAME_TBD, 1, 4),					/* [6] union */
+				BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+			BTF_TYPEDEF_ENC(NAME_TBD, 1),					/* [7] typedef */
+			BTF_PTR_ENC(0),							/* [8] ptr */
+			BTF_CONST_ENC(8),						/* [9] const */
+			BTF_VOLATILE_ENC(8),						/* [10] volatile */
+			BTF_RESTRICT_ENC(8),						/* [11] restrict */
+			BTF_FUNC_PROTO_ENC(1, 2),					/* [12] func_proto */
+				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
+			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
+{
+	.descr = "dedup: no int duplicates",
+	.input = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 8),
+			/* different name */
+			BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 32, 8),
+			/* different encoding */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_CHAR, 0, 32, 8),
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_BOOL, 0, 32, 8),
+			/* different bit offset */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 8, 32, 8),
+			/* different bit size */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 27, 8),
+			/* different byte size */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0int\0some other int"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 8),
+			/* different name */
+			BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 32, 8),
+			/* different encoding */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_CHAR, 0, 32, 8),
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_BOOL, 0, 32, 8),
+			/* different bit offset */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 8, 32, 8),
+			/* different bit size */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 27, 8),
+			/* different byte size */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0int\0some other int"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
+
+};
+
+static int btf_type_size(const struct btf_type *t)
+{
+	int base_size = sizeof(struct btf_type);
+	__u16 vlen = BTF_INFO_VLEN(t->info);
+	__u16 kind = BTF_INFO_KIND(t->info);
+
+	switch (kind) {
+	case BTF_KIND_FWD:
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_FUNC:
+		return base_size;
+	case BTF_KIND_INT:
+		return base_size + sizeof(__u32);
+	case BTF_KIND_ENUM:
+		return base_size + vlen * sizeof(struct btf_enum);
+	case BTF_KIND_ARRAY:
+		return base_size + sizeof(struct btf_array);
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		return base_size + vlen * sizeof(struct btf_member);
+	case BTF_KIND_FUNC_PROTO:
+		return base_size + vlen * sizeof(struct btf_param);
+	default:
+		fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind);
+		return -EINVAL;
+	}
+}
+
+static void dump_btf_strings(const char *strs, __u32 len)
+{
+	const char *cur = strs;
+	int i = 0;
+
+	while (cur < strs + len) {
+		fprintf(stderr, "string #%d: '%s'\n", i, cur);
+		cur += strlen(cur) + 1;
+		i++;
+	}
+}
+
+static int do_test_dedup(unsigned int test_num)
+{
+	const struct btf_dedup_test *test = &dedup_tests[test_num - 1];
+	__u32 test_nr_types, expect_nr_types, test_btf_size, expect_btf_size;
+	const struct btf_header *test_hdr, *expect_hdr;
+	struct btf *test_btf = NULL, *expect_btf = NULL;
+	const void *test_btf_data, *expect_btf_data;
+	const char *ret_test_next_str, *ret_expect_next_str;
+	const char *test_strs, *expect_strs;
+	const char *test_str_cur, *test_str_end;
+	const char *expect_str_cur, *expect_str_end;
+	unsigned int raw_btf_size;
+	void *raw_btf;
+	int err = 0, i;
+
+	fprintf(stderr, "BTF dedup test[%u] (%s):", test_num, test->descr);
+
+	raw_btf = btf_raw_create(&hdr_tmpl, test->input.raw_types,
+				 test->input.str_sec, test->input.str_sec_size,
+				 &raw_btf_size, &ret_test_next_str);
+	if (!raw_btf)
+		return -1;
+	test_btf = btf__new((__u8 *)raw_btf, raw_btf_size);
+	free(raw_btf);
+	if (CHECK(IS_ERR(test_btf), "invalid test_btf errno:%ld",
+		  PTR_ERR(test_btf))) {
+		err = -1;
+		goto done;
+	}
+
+	raw_btf = btf_raw_create(&hdr_tmpl, test->expect.raw_types,
+				 test->expect.str_sec,
+				 test->expect.str_sec_size,
+				 &raw_btf_size, &ret_expect_next_str);
+	if (!raw_btf)
+		return -1;
+	expect_btf = btf__new((__u8 *)raw_btf, raw_btf_size);
+	free(raw_btf);
+	if (CHECK(IS_ERR(expect_btf), "invalid expect_btf errno:%ld",
+		  PTR_ERR(expect_btf))) {
+		err = -1;
+		goto done;
+	}
+
+	err = btf__dedup(test_btf, NULL, &test->opts);
+	if (CHECK(err, "btf_dedup failed errno:%d", err)) {
+		err = -1;
+		goto done;
+	}
+
+	test_btf_data = btf__get_raw_data(test_btf, &test_btf_size);
+	expect_btf_data = btf__get_raw_data(expect_btf, &expect_btf_size);
+	if (CHECK(test_btf_size != expect_btf_size,
+		  "test_btf_size:%u != expect_btf_size:%u",
+		  test_btf_size, expect_btf_size)) {
+		err = -1;
+		goto done;
+	}
+
+	test_hdr = test_btf_data;
+	test_strs = test_btf_data + test_hdr->str_off;
+	expect_hdr = expect_btf_data;
+	expect_strs = expect_btf_data + expect_hdr->str_off;
+	if (CHECK(test_hdr->str_len != expect_hdr->str_len,
+		  "test_hdr->str_len:%u != expect_hdr->str_len:%u",
+		  test_hdr->str_len, expect_hdr->str_len)) {
+		fprintf(stderr, "\ntest strings:\n");
+		dump_btf_strings(test_strs, test_hdr->str_len);
+		fprintf(stderr, "\nexpected strings:\n");
+		dump_btf_strings(expect_strs, expect_hdr->str_len);
+		err = -1;
+		goto done;
+	}
+
+	test_str_cur = test_strs;
+	test_str_end = test_strs + test_hdr->str_len;
+	expect_str_cur = expect_strs;
+	expect_str_end = expect_strs + expect_hdr->str_len;
+	while (test_str_cur < test_str_end && expect_str_cur < expect_str_end) {
+		size_t test_len, expect_len;
+
+		test_len = strlen(test_str_cur);
+		expect_len = strlen(expect_str_cur);
+		if (CHECK(test_len != expect_len,
+			  "test_len:%zu != expect_len:%zu "
+			  "(test_str:%s, expect_str:%s)",
+			  test_len, expect_len, test_str_cur, expect_str_cur)) {
+			err = -1;
+			goto done;
+		}
+		if (CHECK(strcmp(test_str_cur, expect_str_cur),
+			  "test_str:%s != expect_str:%s",
+			  test_str_cur, expect_str_cur)) {
+			err = -1;
+			goto done;
+		}
+		test_str_cur += test_len + 1;
+		expect_str_cur += expect_len + 1;
+	}
+	if (CHECK(test_str_cur != test_str_end,
+		  "test_str_cur:%p != test_str_end:%p",
+		  test_str_cur, test_str_end)) {
+		err = -1;
+		goto done;
+	}
+
+	test_nr_types = btf__get_nr_types(test_btf);
+	expect_nr_types = btf__get_nr_types(expect_btf);
+	if (CHECK(test_nr_types != expect_nr_types,
+		  "test_nr_types:%u != expect_nr_types:%u",
+		  test_nr_types, expect_nr_types)) {
+		err = -1;
+		goto done;
+	}
+
+	for (i = 1; i <= test_nr_types; i++) {
+		const struct btf_type *test_type, *expect_type;
+		int test_size, expect_size;
+
+		test_type = btf__type_by_id(test_btf, i);
+		expect_type = btf__type_by_id(expect_btf, i);
+		test_size = btf_type_size(test_type);
+		expect_size = btf_type_size(expect_type);
+
+		if (CHECK(test_size != expect_size,
+			  "type #%d: test_size:%d != expect_size:%u",
+			  i, test_size, expect_size)) {
+			err = -1;
+			goto done;
+		}
+		if (CHECK(memcmp((void *)test_type,
+				 (void *)expect_type,
+				 test_size),
+			  "type #%d: contents differ", i)) {
+			err = -1;
+			goto done;
+		}
+	}
+
+done:
+	if (!err)
+		fprintf(stderr, "OK");
+	if (!IS_ERR(test_btf))
+		btf__free(test_btf);
+	if (!IS_ERR(expect_btf))
+		btf__free(expect_btf);
+
+	return err;
+}
+
+static int test_dedup(void)
+{
+	unsigned int i;
+	int err = 0;
+
+	if (args.dedup_test_num)
+		return count_result(do_test_dedup(args.dedup_test_num));
+
+	for (i = 1; i <= ARRAY_SIZE(dedup_tests); i++)
+		err |= count_result(do_test_dedup(i));
+
+	return err;
+}
+
 static void usage(const char *cmd)
 {
 	fprintf(stderr, "Usage: %s [-l] [[-r btf_raw_test_num (1 - %zu)] |\n"
 			"\t[-g btf_get_info_test_num (1 - %zu)] |\n"
 			"\t[-f btf_file_test_num (1 - %zu)] |\n"
 			"\t[-k btf_prog_info_raw_test_num (1 - %zu)] |\n"
-			"\t[-p (pretty print test)]]\n",
+			"\t[-p (pretty print test)] |\n"
+			"\t[-d btf_dedup_test_num (1 - %zu)]]\n",
 		cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
-		ARRAY_SIZE(file_tests), ARRAY_SIZE(info_raw_tests));
+		ARRAY_SIZE(file_tests), ARRAY_SIZE(info_raw_tests),
+		ARRAY_SIZE(dedup_tests));
 }
 
 static int parse_args(int argc, char **argv)
 {
-	const char *optstr = "lpk:f:r:g:";
+	const char *optstr = "hlpk:f:r:g:d:";
 	int opt;
 
 	while ((opt = getopt(argc, argv, optstr)) != -1) {
@@ -5591,12 +6082,16 @@ static int parse_args(int argc, char **argv)
 			args.info_raw_test_num = atoi(optarg);
 			args.info_raw_test = true;
 			break;
+		case 'd':
+			args.dedup_test_num = atoi(optarg);
+			args.dedup_test = true;
+			break;
 		case 'h':
 			usage(argv[0]);
 			exit(0);
 		default:
-				usage(argv[0]);
-				return -1;
+			usage(argv[0]);
+			return -1;
 		}
 	}
 
@@ -5632,6 +6127,14 @@ static int parse_args(int argc, char **argv)
 		return -1;
 	}
 
+	if (args.dedup_test_num &&
+	    (args.dedup_test_num < 1 ||
+	     args.dedup_test_num > ARRAY_SIZE(dedup_tests))) {
+		fprintf(stderr, "BTF dedup test number must be [1 - %zu]\n",
+			ARRAY_SIZE(dedup_tests));
+		return -1;
+	}
+
 	return 0;
 }
 
@@ -5650,7 +6153,7 @@ int main(int argc, char **argv)
 		return err;
 
 	if (args.always_log)
-		libbpf_set_print(__base_pr, __base_pr, __base_pr);
+		libbpf_set_print(__base_pr);
 
 	if (args.raw_test)
 		err |= test_raw();
@@ -5667,14 +6170,18 @@ int main(int argc, char **argv)
 	if (args.info_raw_test)
 		err |= test_info_raw();
 
+	if (args.dedup_test)
+		err |= test_dedup();
+
 	if (args.raw_test || args.get_info_test || args.file_test ||
-	    args.pprint_test || args.info_raw_test)
+	    args.pprint_test || args.info_raw_test || args.dedup_test)
 		goto done;
 
 	err |= test_raw();
 	err |= test_get_info();
 	err |= test_file();
 	err |= test_info_raw();
+	err |= test_dedup();
 
 done:
 	print_summary();
diff --git a/tools/testing/selftests/bpf/test_libbpf_open.c b/tools/testing/selftests/bpf/test_libbpf_open.c
index 8fcd1c076add..1909ecf4d999 100644
--- a/tools/testing/selftests/bpf/test_libbpf_open.c
+++ b/tools/testing/selftests/bpf/test_libbpf_open.c
@@ -34,23 +34,16 @@ static void usage(char *argv[])
 	printf("\n");
 }
 
-#define DEFINE_PRINT_FN(name, enabled) \
-static int libbpf_##name(const char *fmt, ...)  	\
-{							\
-        va_list args;					\
-        int ret;					\
-							\
-        va_start(args, fmt);				\
-	if (enabled) {					\
-		fprintf(stderr, "[" #name "] ");	\
-		ret = vfprintf(stderr, fmt, args);	\
-	}						\
-        va_end(args);					\
-        return ret;					\
+static bool debug = 0;
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *fmt, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !debug)
+		return 0;
+
+	fprintf(stderr, "[%d] ", level);
+	return vfprintf(stderr, fmt, args);
 }
-DEFINE_PRINT_FN(warning, 1)
-DEFINE_PRINT_FN(info, 1)
-DEFINE_PRINT_FN(debug, 1)
 
 #define EXIT_FAIL_LIBBPF EXIT_FAILURE
 #define EXIT_FAIL_OPTION 2
@@ -120,15 +113,14 @@ int main(int argc, char **argv)
 	int longindex = 0;
 	int opt;
 
-	libbpf_set_print(libbpf_warning, libbpf_info, NULL);
+	libbpf_set_print(libbpf_debug_print);
 
 	/* Parse commands line args */
 	while ((opt = getopt_long(argc, argv, "hDq",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 'D':
-			libbpf_set_print(libbpf_warning, libbpf_info,
-					 libbpf_debug);
+			debug = 1;
 			break;
 		case 'q': /* Use in scripting mode */
 			verbose = 0;
diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
new file mode 100755
index 000000000000..612632c1425f
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
@@ -0,0 +1,376 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Setup/topology:
+#
+#    NS1             NS2             NS3
+#   veth1 <---> veth2   veth3 <---> veth4 (the top route)
+#   veth5 <---> veth6   veth7 <---> veth8 (the bottom route)
+#
+#   each vethN gets IPv[4|6]_N address
+#
+#   IPv*_SRC = IPv*_1
+#   IPv*_DST = IPv*_4
+#
+#   all tests test pings from IPv*_SRC to IPv*_DST
+#
+#   by default, routes are configured to allow packets to go
+#   IP*_1 <=> IP*_2 <=> IP*_3 <=> IP*_4 (the top route)
+#
+#   a GRE device is installed in NS3 with IPv*_GRE, and
+#   NS1/NS2 are configured to route packets to IPv*_GRE via IP*_8
+#   (the bottom route)
+#
+# Tests:
+#
+#   1. routes NS2->IPv*_DST are brought down, so the only way a ping
+#      from IP*_SRC to IP*_DST can work is via IPv*_GRE
+#
+#   2a. in an egress test, a bpf LWT_XMIT program is installed on veth1
+#       that encaps the packets with an IP/GRE header to route to IPv*_GRE
+#
+#       ping: SRC->[encap at veth1:egress]->GRE:decap->DST
+#       ping replies go DST->SRC directly
+#
+#   2b. in an ingress test, a bpf LWT_IN program is installed on veth2
+#       that encaps the packets with an IP/GRE header to route to IPv*_GRE
+#
+#       ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
+#       ping replies go DST->SRC directly
+
+if [[ $EUID -ne 0 ]]; then
+	echo "This script must be run as root"
+	echo "FAIL"
+	exit 1
+fi
+
+readonly NS1="ns1-$(mktemp -u XXXXXX)"
+readonly NS2="ns2-$(mktemp -u XXXXXX)"
+readonly NS3="ns3-$(mktemp -u XXXXXX)"
+
+readonly IPv4_1="172.16.1.100"
+readonly IPv4_2="172.16.2.100"
+readonly IPv4_3="172.16.3.100"
+readonly IPv4_4="172.16.4.100"
+readonly IPv4_5="172.16.5.100"
+readonly IPv4_6="172.16.6.100"
+readonly IPv4_7="172.16.7.100"
+readonly IPv4_8="172.16.8.100"
+readonly IPv4_GRE="172.16.16.100"
+
+readonly IPv4_SRC=$IPv4_1
+readonly IPv4_DST=$IPv4_4
+
+readonly IPv6_1="fb01::1"
+readonly IPv6_2="fb02::1"
+readonly IPv6_3="fb03::1"
+readonly IPv6_4="fb04::1"
+readonly IPv6_5="fb05::1"
+readonly IPv6_6="fb06::1"
+readonly IPv6_7="fb07::1"
+readonly IPv6_8="fb08::1"
+readonly IPv6_GRE="fb10::1"
+
+readonly IPv6_SRC=$IPv6_1
+readonly IPv6_DST=$IPv6_4
+
+TEST_STATUS=0
+TESTS_SUCCEEDED=0
+TESTS_FAILED=0
+
+process_test_results()
+{
+	if [[ "${TEST_STATUS}" -eq 0 ]] ; then
+		echo "PASS"
+		TESTS_SUCCEEDED=$((TESTS_SUCCEEDED+1))
+	else
+		echo "FAIL"
+		TESTS_FAILED=$((TESTS_FAILED+1))
+	fi
+}
+
+print_test_summary_and_exit()
+{
+	echo "passed tests: ${TESTS_SUCCEEDED}"
+	echo "failed tests: ${TESTS_FAILED}"
+	if [ "${TESTS_FAILED}" -eq "0" ] ; then
+		exit 0
+	else
+		exit 1
+	fi
+}
+
+setup()
+{
+	set -e  # exit on error
+	TEST_STATUS=0
+
+	# create devices and namespaces
+	ip netns add "${NS1}"
+	ip netns add "${NS2}"
+	ip netns add "${NS3}"
+
+	ip link add veth1 type veth peer name veth2
+	ip link add veth3 type veth peer name veth4
+	ip link add veth5 type veth peer name veth6
+	ip link add veth7 type veth peer name veth8
+
+	ip netns exec ${NS2} sysctl -wq net.ipv4.ip_forward=1
+	ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.forwarding=1
+
+	ip link set veth1 netns ${NS1}
+	ip link set veth2 netns ${NS2}
+	ip link set veth3 netns ${NS2}
+	ip link set veth4 netns ${NS3}
+	ip link set veth5 netns ${NS1}
+	ip link set veth6 netns ${NS2}
+	ip link set veth7 netns ${NS2}
+	ip link set veth8 netns ${NS3}
+
+	# configure addesses: the top route (1-2-3-4)
+	ip -netns ${NS1}    addr add ${IPv4_1}/24  dev veth1
+	ip -netns ${NS2}    addr add ${IPv4_2}/24  dev veth2
+	ip -netns ${NS2}    addr add ${IPv4_3}/24  dev veth3
+	ip -netns ${NS3}    addr add ${IPv4_4}/24  dev veth4
+	ip -netns ${NS1} -6 addr add ${IPv6_1}/128 nodad dev veth1
+	ip -netns ${NS2} -6 addr add ${IPv6_2}/128 nodad dev veth2
+	ip -netns ${NS2} -6 addr add ${IPv6_3}/128 nodad dev veth3
+	ip -netns ${NS3} -6 addr add ${IPv6_4}/128 nodad dev veth4
+
+	# configure addresses: the bottom route (5-6-7-8)
+	ip -netns ${NS1}    addr add ${IPv4_5}/24  dev veth5
+	ip -netns ${NS2}    addr add ${IPv4_6}/24  dev veth6
+	ip -netns ${NS2}    addr add ${IPv4_7}/24  dev veth7
+	ip -netns ${NS3}    addr add ${IPv4_8}/24  dev veth8
+	ip -netns ${NS1} -6 addr add ${IPv6_5}/128 nodad dev veth5
+	ip -netns ${NS2} -6 addr add ${IPv6_6}/128 nodad dev veth6
+	ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7
+	ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8
+
+
+	ip -netns ${NS1} link set dev veth1 up
+	ip -netns ${NS2} link set dev veth2 up
+	ip -netns ${NS2} link set dev veth3 up
+	ip -netns ${NS3} link set dev veth4 up
+	ip -netns ${NS1} link set dev veth5 up
+	ip -netns ${NS2} link set dev veth6 up
+	ip -netns ${NS2} link set dev veth7 up
+	ip -netns ${NS3} link set dev veth8 up
+
+	# configure routes: IP*_SRC -> veth1/IP*_2 (= top route) default;
+	# the bottom route to specific bottom addresses
+
+	# NS1
+	# top route
+	ip -netns ${NS1}    route add ${IPv4_2}/32  dev veth1
+	ip -netns ${NS1}    route add default dev veth1 via ${IPv4_2}  # go top by default
+	ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1
+	ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2}  # go top by default
+	# bottom route
+	ip -netns ${NS1}    route add ${IPv4_6}/32  dev veth5
+	ip -netns ${NS1}    route add ${IPv4_7}/32  dev veth5 via ${IPv4_6}
+	ip -netns ${NS1}    route add ${IPv4_8}/32  dev veth5 via ${IPv4_6}
+	ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5
+	ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6}
+	ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6}
+
+	# NS2
+	# top route
+	ip -netns ${NS2}    route add ${IPv4_1}/32  dev veth2
+	ip -netns ${NS2}    route add ${IPv4_4}/32  dev veth3
+	ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2
+	ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3
+	# bottom route
+	ip -netns ${NS2}    route add ${IPv4_5}/32  dev veth6
+	ip -netns ${NS2}    route add ${IPv4_8}/32  dev veth7
+	ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6
+	ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7
+
+	# NS3
+	# top route
+	ip -netns ${NS3}    route add ${IPv4_3}/32  dev veth4
+	ip -netns ${NS3}    route add ${IPv4_1}/32  dev veth4 via ${IPv4_3}
+	ip -netns ${NS3}    route add ${IPv4_2}/32  dev veth4 via ${IPv4_3}
+	ip -netns ${NS3} -6 route add ${IPv6_3}/128 dev veth4
+	ip -netns ${NS3} -6 route add ${IPv6_1}/128 dev veth4 via ${IPv6_3}
+	ip -netns ${NS3} -6 route add ${IPv6_2}/128 dev veth4 via ${IPv6_3}
+	# bottom route
+	ip -netns ${NS3}    route add ${IPv4_7}/32  dev veth8
+	ip -netns ${NS3}    route add ${IPv4_5}/32  dev veth8 via ${IPv4_7}
+	ip -netns ${NS3}    route add ${IPv4_6}/32  dev veth8 via ${IPv4_7}
+	ip -netns ${NS3} -6 route add ${IPv6_7}/128 dev veth8
+	ip -netns ${NS3} -6 route add ${IPv6_5}/128 dev veth8 via ${IPv6_7}
+	ip -netns ${NS3} -6 route add ${IPv6_6}/128 dev veth8 via ${IPv6_7}
+
+	# configure IPv4 GRE device in NS3, and a route to it via the "bottom" route
+	ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255
+	ip -netns ${NS3} link set gre_dev up
+	ip -netns ${NS3} addr add ${IPv4_GRE} nodad dev gre_dev
+	ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6}
+	ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8}
+
+
+	# configure IPv6 GRE device in NS3, and a route to it via the "bottom" route
+	ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255
+	ip -netns ${NS3} link set gre6_dev up
+	ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev
+	ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6}
+	ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8}
+
+	# rp_filter gets confused by what these tests are doing, so disable it
+	ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
+
+	sleep 1  # reduce flakiness
+	set +e
+}
+
+cleanup()
+{
+	ip netns del ${NS1} 2> /dev/null
+	ip netns del ${NS2} 2> /dev/null
+	ip netns del ${NS3} 2> /dev/null
+}
+
+trap cleanup EXIT
+
+remove_routes_to_gredev()
+{
+	ip -netns ${NS1} route del ${IPv4_GRE} dev veth5
+	ip -netns ${NS2} route del ${IPv4_GRE} dev veth7
+	ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5
+	ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7
+}
+
+add_unreachable_routes_to_gredev()
+{
+	ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32
+	ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32
+	ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128
+	ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128
+}
+
+test_ping()
+{
+	local readonly PROTO=$1
+	local readonly EXPECTED=$2
+	local RET=0
+
+	if [ "${PROTO}" == "IPv4" ] ; then
+		ip netns exec ${NS1} ping  -c 1 -W 1 -I ${IPv4_SRC} ${IPv4_DST} 2>&1 > /dev/null
+		RET=$?
+	elif [ "${PROTO}" == "IPv6" ] ; then
+		ip netns exec ${NS1} ping6 -c 1 -W 6 -I ${IPv6_SRC} ${IPv6_DST} 2>&1 > /dev/null
+		RET=$?
+	else
+		echo "    test_ping: unknown PROTO: ${PROTO}"
+		TEST_STATUS=1
+	fi
+
+	if [ "0" != "${RET}" ]; then
+		RET=1
+	fi
+
+	if [ "${EXPECTED}" != "${RET}" ] ; then
+		echo "    test_ping failed: expected: ${EXPECTED}; got ${RET}"
+		TEST_STATUS=1
+	fi
+}
+
+test_egress()
+{
+	local readonly ENCAP=$1
+	echo "starting egress ${ENCAP} encap test"
+	setup
+
+	# by default, pings work
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	# remove NS2->DST routes, ping fails
+	ip -netns ${NS2}    route del ${IPv4_DST}/32  dev veth3
+	ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	# install replacement routes (LWT/eBPF), pings succeed
+	if [ "${ENCAP}" == "IPv4" ] ; then
+		ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1
+		ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1
+	elif [ "${ENCAP}" == "IPv6" ] ; then
+		ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1
+		ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1
+	else
+		echo "    unknown encap ${ENCAP}"
+		TEST_STATUS=1
+	fi
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	# a negative test: remove routes to GRE devices: ping fails
+	remove_routes_to_gredev
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	# another negative test
+	add_unreachable_routes_to_gredev
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	cleanup
+	process_test_results
+}
+
+test_ingress()
+{
+	local readonly ENCAP=$1
+	echo "starting ingress ${ENCAP} encap test"
+	setup
+
+	# need to wait a bit for IPv6 to autoconf, otherwise
+	# ping6 sometimes fails with "unable to bind to address"
+
+	# by default, pings work
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	# remove NS2->DST routes, pings fail
+	ip -netns ${NS2}    route del ${IPv4_DST}/32  dev veth3
+	ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	# install replacement routes (LWT/eBPF), pings succeed
+	if [ "${ENCAP}" == "IPv4" ] ; then
+		ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2
+		ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2
+	elif [ "${ENCAP}" == "IPv6" ] ; then
+		ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2
+		ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2
+	else
+		echo "FAIL: unknown encap ${ENCAP}"
+	fi
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	# a negative test: remove routes to GRE devices: ping fails
+	remove_routes_to_gredev
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	# another negative test
+	add_unreachable_routes_to_gredev
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	cleanup
+	process_test_results
+}
+
+test_egress IPv4
+test_egress IPv6
+test_ingress IPv4
+test_ingress IPv6
+
+print_test_summary_and_exit
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index e7798dd97f4b..3c627771f965 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -45,7 +45,7 @@ static int map_flags;
 	}								\
 })
 
-static void test_hashmap(int task, void *data)
+static void test_hashmap(unsigned int task, void *data)
 {
 	long long key, next_key, first_key, value;
 	int fd;
@@ -135,7 +135,7 @@ static void test_hashmap(int task, void *data)
 	close(fd);
 }
 
-static void test_hashmap_sizes(int task, void *data)
+static void test_hashmap_sizes(unsigned int task, void *data)
 {
 	int fd, i, j;
 
@@ -155,7 +155,7 @@ static void test_hashmap_sizes(int task, void *data)
 		}
 }
 
-static void test_hashmap_percpu(int task, void *data)
+static void test_hashmap_percpu(unsigned int task, void *data)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	BPF_DECLARE_PERCPU(long, value);
@@ -282,7 +282,7 @@ static int helper_fill_hashmap(int max_entries)
 	return fd;
 }
 
-static void test_hashmap_walk(int task, void *data)
+static void test_hashmap_walk(unsigned int task, void *data)
 {
 	int fd, i, max_entries = 1000;
 	long long key, value, next_key;
@@ -353,7 +353,7 @@ static void test_hashmap_zero_seed(void)
 	close(second);
 }
 
-static void test_arraymap(int task, void *data)
+static void test_arraymap(unsigned int task, void *data)
 {
 	int key, next_key, fd;
 	long long value;
@@ -408,7 +408,7 @@ static void test_arraymap(int task, void *data)
 	close(fd);
 }
 
-static void test_arraymap_percpu(int task, void *data)
+static void test_arraymap_percpu(unsigned int task, void *data)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	BPF_DECLARE_PERCPU(long, values);
@@ -504,7 +504,7 @@ static void test_arraymap_percpu_many_keys(void)
 	close(fd);
 }
 
-static void test_devmap(int task, void *data)
+static void test_devmap(unsigned int task, void *data)
 {
 	int fd;
 	__u32 key, value;
@@ -519,7 +519,7 @@ static void test_devmap(int task, void *data)
 	close(fd);
 }
 
-static void test_queuemap(int task, void *data)
+static void test_queuemap(unsigned int task, void *data)
 {
 	const int MAP_SIZE = 32;
 	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
@@ -577,7 +577,7 @@ static void test_queuemap(int task, void *data)
 	close(fd);
 }
 
-static void test_stackmap(int task, void *data)
+static void test_stackmap(unsigned int task, void *data)
 {
 	const int MAP_SIZE = 32;
 	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
@@ -642,7 +642,7 @@ static void test_stackmap(int task, void *data)
 #define SOCKMAP_PARSE_PROG "./sockmap_parse_prog.o"
 #define SOCKMAP_VERDICT_PROG "./sockmap_verdict_prog.o"
 #define SOCKMAP_TCP_MSG_PROG "./sockmap_tcp_msg_prog.o"
-static void test_sockmap(int tasks, void *data)
+static void test_sockmap(unsigned int tasks, void *data)
 {
 	struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_msg, *bpf_map_break;
 	int map_fd_msg = 0, map_fd_rx = 0, map_fd_tx = 0, map_fd_break;
@@ -1268,10 +1268,11 @@ static void test_map_large(void)
 }
 
 #define run_parallel(N, FN, DATA) \
-	printf("Fork %d tasks to '" #FN "'\n", N); \
+	printf("Fork %u tasks to '" #FN "'\n", N); \
 	__run_parallel(N, FN, DATA)
 
-static void __run_parallel(int tasks, void (*fn)(int task, void *data),
+static void __run_parallel(unsigned int tasks,
+			   void (*fn)(unsigned int task, void *data),
 			   void *data)
 {
 	pid_t pid[tasks];
@@ -1312,7 +1313,7 @@ static void test_map_stress(void)
 #define DO_UPDATE 1
 #define DO_DELETE 0
 
-static void test_update_delete(int fn, void *data)
+static void test_update_delete(unsigned int fn, void *data)
 {
 	int do_update = ((int *)data)[1];
 	int fd = ((int *)data)[0];
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index d59642e70f56..84bea3985d64 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -23,6 +23,7 @@ import string
 import struct
 import subprocess
 import time
+import traceback
 
 logfile = None
 log_level = 1
@@ -78,7 +79,9 @@ def fail(cond, msg):
     if not cond:
         return
     print("FAIL: " + msg)
-    log("FAIL: " + msg, "", level=1)
+    tb = "".join(traceback.extract_stack().format())
+    print(tb)
+    log("FAIL: " + msg, tb, level=1)
     os.sys.exit(1)
 
 def start_test(msg):
@@ -589,6 +592,15 @@ def check_verifier_log(output, reference):
             return
     fail(True, "Missing or incorrect message from netdevsim in verifier log")
 
+def check_multi_basic(two_xdps):
+    fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs")
+    fail("prog" in two_xdps, "Base program reported in multi program mode")
+    fail(len(two_xdps["attached"]) != 2,
+         "Wrong attached program count with two programs")
+    fail(two_xdps["attached"][0]["prog"]["id"] ==
+         two_xdps["attached"][1]["prog"]["id"],
+         "Offloaded and other programs have the same id")
+
 def test_spurios_extack(sim, obj, skip_hw, needle):
     res = sim.cls_bpf_add_filter(obj, prio=1, handle=1, skip_hw=skip_hw,
                                  include_stderr=True)
@@ -600,6 +612,67 @@ def test_spurios_extack(sim, obj, skip_hw, needle):
                             include_stderr=True)
     check_no_extack(res, needle)
 
+def test_multi_prog(sim, obj, modename, modeid):
+    start_test("Test multi-attachment XDP - %s + offload..." %
+               (modename or "default", ))
+    sim.set_xdp(obj, "offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+    fail("prog" not in xdp, "Base program not reported in single program mode")
+    fail(len(xdp["attached"]) != 1,
+         "Wrong attached program count with one program")
+
+    sim.set_xdp(obj, modename)
+    two_xdps = sim.ip_link_show(xdp=True)["xdp"]
+
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after other activated")
+    check_multi_basic(two_xdps)
+
+    offloaded2 = sim.dfs_read("bpf_offloaded_id")
+    fail(offloaded != offloaded2,
+         "Offload ID changed after loading other program")
+
+    start_test("Test multi-attachment XDP - replace...")
+    ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True)
+    fail(ret == 0, "Replaced one of programs without -force")
+    check_extack(err, "XDP program already attached.", args)
+
+    if modename == "" or modename == "drv":
+        othermode = "" if modename == "drv" else "drv"
+        start_test("Test multi-attachment XDP - detach...")
+        ret, _, err = sim.unset_xdp(othermode, force=True,
+                                    fail=False, include_stderr=True)
+        fail(ret == 0, "Removed program with a bad mode")
+        check_extack(err, "program loaded with different flags.", args)
+
+    sim.unset_xdp("offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+
+    fail(xdp["mode"] != modeid, "Bad mode reported after multiple programs")
+    fail("prog" not in xdp,
+         "Base program not reported after multi program mode")
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after other activated")
+    fail(len(xdp["attached"]) != 1,
+         "Wrong attached program count with remaining programs")
+    fail(offloaded != "0", "Offload ID reported with only other program left")
+
+    start_test("Test multi-attachment XDP - reattach...")
+    sim.set_xdp(obj, "offload")
+    two_xdps = sim.ip_link_show(xdp=True)["xdp"]
+
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Other program not reported after offload activated")
+    check_multi_basic(two_xdps)
+
+    start_test("Test multi-attachment XDP - device remove...")
+    sim.remove()
+
+    sim = NetdevSim()
+    sim.set_ethtool_tc_offloads(True)
+    return sim
 
 # Parse command line
 parser = argparse.ArgumentParser()
@@ -842,7 +915,9 @@ try:
     ret, _, err = sim.set_xdp(obj, "generic", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
-    fail(err.count("File exists") != 1, "Replaced driver XDP with generic")
+    check_extack(err,
+                 "native and generic XDP can't be active at the same time.",
+                 args)
     ret, _, err = sim.set_xdp(obj, "", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
@@ -931,59 +1006,9 @@ try:
     rm(pin_file)
     bpftool_prog_list_wait(expected=0)
 
-    start_test("Test multi-attachment XDP - attach...")
-    sim.set_xdp(obj, "offload")
-    xdp = sim.ip_link_show(xdp=True)["xdp"]
-    offloaded = sim.dfs_read("bpf_offloaded_id")
-    fail("prog" not in xdp, "Base program not reported in single program mode")
-    fail(len(ipl["xdp"]["attached"]) != 1,
-         "Wrong attached program count with one program")
-
-    sim.set_xdp(obj, "")
-    two_xdps = sim.ip_link_show(xdp=True)["xdp"]
-    offloaded2 = sim.dfs_read("bpf_offloaded_id")
-
-    fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs")
-    fail("prog" in two_xdps, "Base program reported in multi program mode")
-    fail(xdp["attached"][0] not in two_xdps["attached"],
-         "Offload program not reported after driver activated")
-    fail(len(two_xdps["attached"]) != 2,
-         "Wrong attached program count with two programs")
-    fail(two_xdps["attached"][0]["prog"]["id"] ==
-         two_xdps["attached"][1]["prog"]["id"],
-         "offloaded and drv programs have the same id")
-    fail(offloaded != offloaded2,
-         "offload ID changed after loading driver program")
-
-    start_test("Test multi-attachment XDP - replace...")
-    ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True)
-    fail(err.count("busy") != 1, "Replaced one of programs without -force")
-
-    start_test("Test multi-attachment XDP - detach...")
-    ret, _, err = sim.unset_xdp("drv", force=True,
-                                fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode")
-    check_extack(err, "program loaded with different flags.", args)
-
-    sim.unset_xdp("offload")
-    xdp = sim.ip_link_show(xdp=True)["xdp"]
-    offloaded = sim.dfs_read("bpf_offloaded_id")
-
-    fail(xdp["mode"] != 1, "Bad mode reported after multiple programs")
-    fail("prog" not in xdp,
-         "Base program not reported after multi program mode")
-    fail(xdp["attached"][0] not in two_xdps["attached"],
-         "Offload program not reported after driver activated")
-    fail(len(ipl["xdp"]["attached"]) != 1,
-         "Wrong attached program count with remaining programs")
-    fail(offloaded != "0", "offload ID reported with only driver program left")
-
-    start_test("Test multi-attachment XDP - device remove...")
-    sim.set_xdp(obj, "offload")
-    sim.remove()
-
-    sim = NetdevSim()
-    sim.set_ethtool_tc_offloads(True)
+    sim = test_multi_prog(sim, obj, "", 1)
+    sim = test_multi_prog(sim, obj, "drv", 1)
+    sim = test_multi_prog(sim, obj, "generic", 2)
 
     start_test("Test mixing of TC and XDP...")
     sim.tc_add_ingress()
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index a08d026ac396..c52bd90fbb34 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <assert.h>
 #include <stdlib.h>
+#include <stdarg.h>
 #include <time.h>
 
 #include <linux/types.h>
@@ -1783,6 +1784,15 @@ static void test_task_fd_query_tp(void)
 				   "sys_enter_read");
 }
 
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG)
+		return 0;
+
+	return vfprintf(stderr, format, args);
+}
+
 static void test_reference_tracking()
 {
 	const char *file = "./test_sk_lookup_kern.o";
@@ -1809,9 +1819,9 @@ static void test_reference_tracking()
 
 		/* Expect verifier failure if test name has 'fail' */
 		if (strstr(title, "fail") != NULL) {
-			libbpf_set_print(NULL, NULL, NULL);
+			libbpf_set_print(NULL);
 			err = !bpf_program__load(prog, "GPL", 0);
-			libbpf_set_print(printf, printf, NULL);
+			libbpf_set_print(libbpf_debug_print);
 		} else {
 			err = bpf_program__load(prog, "GPL", 0);
 		}
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index 561ffb6d6433..fb679ac3d4b0 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -20,6 +20,7 @@
 #define MAX_INSNS	512
 
 char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static bool verbose = false;
 
 struct sock_test {
 	const char *descr;
@@ -325,6 +326,7 @@ static int load_sock_prog(const struct bpf_insn *prog,
 			  enum bpf_attach_type attach_type)
 {
 	struct bpf_load_program_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(struct bpf_load_program_attr));
 	attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
@@ -332,8 +334,13 @@ static int load_sock_prog(const struct bpf_insn *prog,
 	attr.insns = prog;
 	attr.insns_cnt = probe_prog_length(attr.insns);
 	attr.license = "GPL";
+	attr.log_level = 2;
 
-	return bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE);
+	ret = bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE);
+	if (verbose && ret < 0)
+		fprintf(stderr, "%s\n", bpf_log_buf);
+
+	return ret;
 }
 
 static int attach_sock_prog(int cgfd, int progfd,
diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c
new file mode 100644
index 000000000000..9bb58369b481
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sock_fields.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <sys/socket.h>
+#include <sys/epoll.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "cgroup_helpers.h"
+
+enum bpf_array_idx {
+	SRV_IDX,
+	CLI_IDX,
+	__NR_BPF_ARRAY_IDX,
+};
+
+#define CHECK(condition, tag, format...) ({				\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);	\
+		printf(format);						\
+		printf("\n");						\
+		exit(-1);						\
+	}								\
+})
+
+#define TEST_CGROUP "/test-bpf-sock-fields"
+#define DATA "Hello BPF!"
+#define DATA_LEN sizeof(DATA)
+
+static struct sockaddr_in6 srv_sa6, cli_sa6;
+static int linum_map_fd;
+static int addr_map_fd;
+static int tp_map_fd;
+static int sk_map_fd;
+static __u32 srv_idx = SRV_IDX;
+static __u32 cli_idx = CLI_IDX;
+
+static void init_loopback6(struct sockaddr_in6 *sa6)
+{
+	memset(sa6, 0, sizeof(*sa6));
+	sa6->sin6_family = AF_INET6;
+	sa6->sin6_addr = in6addr_loopback;
+}
+
+static void print_sk(const struct bpf_sock *sk)
+{
+	char src_ip4[24], dst_ip4[24];
+	char src_ip6[64], dst_ip6[64];
+
+	inet_ntop(AF_INET, &sk->src_ip4, src_ip4, sizeof(src_ip4));
+	inet_ntop(AF_INET6, &sk->src_ip6, src_ip6, sizeof(src_ip6));
+	inet_ntop(AF_INET, &sk->dst_ip4, dst_ip4, sizeof(dst_ip4));
+	inet_ntop(AF_INET6, &sk->dst_ip6, dst_ip6, sizeof(dst_ip6));
+
+	printf("state:%u bound_dev_if:%u family:%u type:%u protocol:%u mark:%u priority:%u "
+	       "src_ip4:%x(%s) src_ip6:%x:%x:%x:%x(%s) src_port:%u "
+	       "dst_ip4:%x(%s) dst_ip6:%x:%x:%x:%x(%s) dst_port:%u\n",
+	       sk->state, sk->bound_dev_if, sk->family, sk->type, sk->protocol,
+	       sk->mark, sk->priority,
+	       sk->src_ip4, src_ip4,
+	       sk->src_ip6[0], sk->src_ip6[1], sk->src_ip6[2], sk->src_ip6[3],
+	       src_ip6, sk->src_port,
+	       sk->dst_ip4, dst_ip4,
+	       sk->dst_ip6[0], sk->dst_ip6[1], sk->dst_ip6[2], sk->dst_ip6[3],
+	       dst_ip6, ntohs(sk->dst_port));
+}
+
+static void print_tp(const struct bpf_tcp_sock *tp)
+{
+	printf("snd_cwnd:%u srtt_us:%u rtt_min:%u snd_ssthresh:%u rcv_nxt:%u "
+	       "snd_nxt:%u snd:una:%u mss_cache:%u ecn_flags:%u "
+	       "rate_delivered:%u rate_interval_us:%u packets_out:%u "
+	       "retrans_out:%u total_retrans:%u segs_in:%u data_segs_in:%u "
+	       "segs_out:%u data_segs_out:%u lost_out:%u sacked_out:%u "
+	       "bytes_received:%llu bytes_acked:%llu\n",
+	       tp->snd_cwnd, tp->srtt_us, tp->rtt_min, tp->snd_ssthresh,
+	       tp->rcv_nxt, tp->snd_nxt, tp->snd_una, tp->mss_cache,
+	       tp->ecn_flags, tp->rate_delivered, tp->rate_interval_us,
+	       tp->packets_out, tp->retrans_out, tp->total_retrans,
+	       tp->segs_in, tp->data_segs_in, tp->segs_out,
+	       tp->data_segs_out, tp->lost_out, tp->sacked_out,
+	       tp->bytes_received, tp->bytes_acked);
+}
+
+static void check_result(void)
+{
+	struct bpf_tcp_sock srv_tp, cli_tp;
+	struct bpf_sock srv_sk, cli_sk;
+	__u32 linum, idx0 = 0;
+	int err;
+
+	err = bpf_map_lookup_elem(linum_map_fd, &idx0, &linum);
+	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
+	      "err:%d errno:%d", err, errno);
+
+	err = bpf_map_lookup_elem(sk_map_fd, &srv_idx, &srv_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &srv_idx)",
+	      "err:%d errno:%d", err, errno);
+	err = bpf_map_lookup_elem(tp_map_fd, &srv_idx, &srv_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &srv_idx)",
+	      "err:%d errno:%d", err, errno);
+
+	err = bpf_map_lookup_elem(sk_map_fd, &cli_idx, &cli_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &cli_idx)",
+	      "err:%d errno:%d", err, errno);
+	err = bpf_map_lookup_elem(tp_map_fd, &cli_idx, &cli_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &cli_idx)",
+	      "err:%d errno:%d", err, errno);
+
+	printf("srv_sk: ");
+	print_sk(&srv_sk);
+	printf("\n");
+
+	printf("cli_sk: ");
+	print_sk(&cli_sk);
+	printf("\n");
+
+	printf("srv_tp: ");
+	print_tp(&srv_tp);
+	printf("\n");
+
+	printf("cli_tp: ");
+	print_tp(&cli_tp);
+	printf("\n");
+
+	CHECK(srv_sk.state == 10 ||
+	      !srv_sk.state ||
+	      srv_sk.family != AF_INET6 ||
+	      srv_sk.protocol != IPPROTO_TCP ||
+	      memcmp(srv_sk.src_ip6, &in6addr_loopback,
+		     sizeof(srv_sk.src_ip6)) ||
+	      memcmp(srv_sk.dst_ip6, &in6addr_loopback,
+		     sizeof(srv_sk.dst_ip6)) ||
+	      srv_sk.src_port != ntohs(srv_sa6.sin6_port) ||
+	      srv_sk.dst_port != cli_sa6.sin6_port,
+	      "Unexpected srv_sk", "Check srv_sk output. linum:%u", linum);
+
+	CHECK(cli_sk.state == 10 ||
+	      !cli_sk.state ||
+	      cli_sk.family != AF_INET6 ||
+	      cli_sk.protocol != IPPROTO_TCP ||
+	      memcmp(cli_sk.src_ip6, &in6addr_loopback,
+		     sizeof(cli_sk.src_ip6)) ||
+	      memcmp(cli_sk.dst_ip6, &in6addr_loopback,
+		     sizeof(cli_sk.dst_ip6)) ||
+	      cli_sk.src_port != ntohs(cli_sa6.sin6_port) ||
+	      cli_sk.dst_port != srv_sa6.sin6_port,
+	      "Unexpected cli_sk", "Check cli_sk output. linum:%u", linum);
+
+	CHECK(srv_tp.data_segs_out != 1 ||
+	      srv_tp.data_segs_in ||
+	      srv_tp.snd_cwnd != 10 ||
+	      srv_tp.total_retrans ||
+	      srv_tp.bytes_acked != DATA_LEN,
+	      "Unexpected srv_tp", "Check srv_tp output. linum:%u", linum);
+
+	CHECK(cli_tp.data_segs_out ||
+	      cli_tp.data_segs_in != 1 ||
+	      cli_tp.snd_cwnd != 10 ||
+	      cli_tp.total_retrans ||
+	      cli_tp.bytes_received != DATA_LEN,
+	      "Unexpected cli_tp", "Check cli_tp output. linum:%u", linum);
+}
+
+static void test(void)
+{
+	int listen_fd, cli_fd, accept_fd, epfd, err;
+	struct epoll_event ev;
+	socklen_t addrlen;
+
+	addrlen = sizeof(struct sockaddr_in6);
+	ev.events = EPOLLIN;
+
+	epfd = epoll_create(1);
+	CHECK(epfd == -1, "epoll_create()", "epfd:%d errno:%d", epfd, errno);
+
+	/* Prepare listen_fd */
+	listen_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
+	CHECK(listen_fd == -1, "socket()", "listen_fd:%d errno:%d",
+	      listen_fd, errno);
+
+	init_loopback6(&srv_sa6);
+	err = bind(listen_fd, (struct sockaddr *)&srv_sa6, sizeof(srv_sa6));
+	CHECK(err, "bind(listen_fd)", "err:%d errno:%d", err, errno);
+
+	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
+	CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d", err, errno);
+
+	err = listen(listen_fd, 1);
+	CHECK(err, "listen(listen_fd)", "err:%d errno:%d", err, errno);
+
+	/* Prepare cli_fd */
+	cli_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
+	CHECK(cli_fd == -1, "socket()", "cli_fd:%d errno:%d", cli_fd, errno);
+
+	init_loopback6(&cli_sa6);
+	err = bind(cli_fd, (struct sockaddr *)&cli_sa6, sizeof(cli_sa6));
+	CHECK(err, "bind(cli_fd)", "err:%d errno:%d", err, errno);
+
+	err = getsockname(cli_fd, (struct sockaddr *)&cli_sa6, &addrlen);
+	CHECK(err, "getsockname(cli_fd)", "err:%d errno:%d",
+	      err, errno);
+
+	/* Update addr_map with srv_sa6 and cli_sa6 */
+	err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0);
+	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
+
+	err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0);
+	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
+
+	/* Connect from cli_sa6 to srv_sa6 */
+	err = connect(cli_fd, (struct sockaddr *)&srv_sa6, addrlen);
+	printf("srv_sa6.sin6_port:%u cli_sa6.sin6_port:%u\n\n",
+	       ntohs(srv_sa6.sin6_port), ntohs(cli_sa6.sin6_port));
+	CHECK(err && errno != EINPROGRESS,
+	      "connect(cli_fd)", "err:%d errno:%d", err, errno);
+
+	ev.data.fd = listen_fd;
+	err = epoll_ctl(epfd, EPOLL_CTL_ADD, listen_fd, &ev);
+	CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, listen_fd)", "err:%d errno:%d",
+	      err, errno);
+
+	/* Accept the connection */
+	/* Have some timeout in accept(listen_fd). Just in case. */
+	err = epoll_wait(epfd, &ev, 1, 1000);
+	CHECK(err != 1 || ev.data.fd != listen_fd,
+	      "epoll_wait(listen_fd)",
+	      "err:%d errno:%d ev.data.fd:%d listen_fd:%d",
+	      err, errno, ev.data.fd, listen_fd);
+
+	accept_fd = accept(listen_fd, NULL, NULL);
+	CHECK(accept_fd == -1, "accept(listen_fd)", "accept_fd:%d errno:%d",
+	      accept_fd, errno);
+	close(listen_fd);
+
+	/* Send some data from accept_fd to cli_fd */
+	err = send(accept_fd, DATA, DATA_LEN, 0);
+	CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d",
+	      err, errno);
+
+	/* Have some timeout in recv(cli_fd). Just in case. */
+	ev.data.fd = cli_fd;
+	err = epoll_ctl(epfd, EPOLL_CTL_ADD, cli_fd, &ev);
+	CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, cli_fd)", "err:%d errno:%d",
+	      err, errno);
+
+	err = epoll_wait(epfd, &ev, 1, 1000);
+	CHECK(err != 1 || ev.data.fd != cli_fd,
+	      "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d",
+	      err, errno, ev.data.fd, cli_fd);
+
+	err = recv(cli_fd, NULL, 0, MSG_TRUNC);
+	CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno);
+
+	close(epfd);
+	close(accept_fd);
+	close(cli_fd);
+
+	check_result();
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_prog_load_attr attr = {
+		.file = "test_sock_fields_kern.o",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+		.expected_attach_type = BPF_CGROUP_INET_EGRESS,
+	};
+	int cgroup_fd, prog_fd, err;
+	struct bpf_object *obj;
+	struct bpf_map *map;
+
+	err = setup_cgroup_environment();
+	CHECK(err, "setup_cgroup_environment()", "err:%d errno:%d",
+	      err, errno);
+
+	atexit(cleanup_cgroup_environment);
+
+	/* Create a cgroup, get fd, and join it */
+	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+	CHECK(cgroup_fd == -1, "create_and_get_cgroup()",
+	      "cgroup_fd:%d errno:%d", cgroup_fd, errno);
+
+	err = join_cgroup(TEST_CGROUP);
+	CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno);
+
+	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	CHECK(err, "bpf_prog_load_xattr()", "err:%d", err);
+
+	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
+	CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)",
+	      "err:%d errno%d", err, errno);
+	close(cgroup_fd);
+
+	map = bpf_object__find_map_by_name(obj, "addr_map");
+	CHECK(!map, "cannot find addr_map", "(null)");
+	addr_map_fd = bpf_map__fd(map);
+
+	map = bpf_object__find_map_by_name(obj, "sock_result_map");
+	CHECK(!map, "cannot find sock_result_map", "(null)");
+	sk_map_fd = bpf_map__fd(map);
+
+	map = bpf_object__find_map_by_name(obj, "tcp_sock_result_map");
+	CHECK(!map, "cannot find tcp_sock_result_map", "(null)");
+	tp_map_fd = bpf_map__fd(map);
+
+	map = bpf_object__find_map_by_name(obj, "linum_map");
+	CHECK(!map, "cannot find linum_map", "(null)");
+	linum_map_fd = bpf_map__fd(map);
+
+	test();
+
+	bpf_object__close(obj);
+	cleanup_cgroup_environment();
+
+	printf("PASS\n");
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c b/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c
index b0195770da6a..c6c69220a569 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c
@@ -100,6 +100,7 @@
 	.errstr = "invalid bpf_context access",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_SK_MSG,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"invalid read past end of SK_MSG",
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 881f1c7f57a1..c660deb582f1 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -687,6 +687,7 @@
 	},
 	.errstr = "invalid bpf_context access",
 	.result = REJECT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"check skb->hash half load not permitted, unaligned 3",
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index ceb39ffa0e88..f0961c58581e 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -27,6 +27,7 @@
 		  .data64 = { 1ULL << 63 | 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset32: BPF_X",
@@ -58,6 +59,7 @@
 		  .data64 = { 1ULL << 63 | 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset32: min/max deduction",
@@ -93,6 +95,7 @@
 		  .data64 = { -1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jeq32: BPF_X",
@@ -119,6 +122,7 @@
 		  .data64 = { 1ULL << 63 | 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jeq32: min/max deduction",
@@ -154,6 +158,7 @@
 		  .data64 = { -1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jne32: BPF_X",
@@ -180,6 +185,7 @@
 		  .data64 = { 1ULL << 63 | 2, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jne32: min/max deduction",
@@ -218,6 +224,7 @@
 		  .data64 = { 0, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jge32: BPF_X",
@@ -244,6 +251,7 @@
 		  .data64 = { (UINT_MAX - 1) | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jge32: min/max deduction",
@@ -284,6 +292,7 @@
 		  .data64 = { 0, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: BPF_X",
@@ -310,6 +319,7 @@
 		  .data64 = { (UINT_MAX - 1) | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: min/max deduction",
@@ -350,6 +360,7 @@
 		  .data64 = { INT_MAX, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jle32: BPF_X",
@@ -376,6 +387,7 @@
 		  .data64 = { UINT_MAX, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jle32: min/max deduction",
@@ -416,6 +428,7 @@
 		  .data64 = { INT_MAX - 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jlt32: BPF_X",
@@ -442,6 +455,7 @@
 		  .data64 = { (INT_MAX - 1) | 3ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jlt32: min/max deduction",
@@ -482,6 +496,7 @@
 		  .data64 = { -2, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsge32: BPF_X",
@@ -508,6 +523,7 @@
 		  .data64 = { -2, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsge32: min/max deduction",
@@ -548,6 +564,7 @@
 		  .data64 = { 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsgt32: BPF_X",
@@ -574,6 +591,7 @@
 		  .data64 = { 0x7fffffff, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsgt32: min/max deduction",
@@ -614,6 +632,7 @@
 		  .data64 = { 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsle32: BPF_X",
@@ -640,6 +659,7 @@
 		  .data64 = { 0x7fffffff | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsle32: min/max deduction",
@@ -680,6 +700,7 @@
 		  .data64 = { 1, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jslt32: BPF_X",
@@ -706,6 +727,7 @@
 		  .data64 = { 0x7fffffff | 2ULL << 32, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jslt32: min/max deduction",
diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c
index 7e14037acfaf..8dcd4e0383d5 100644
--- a/tools/testing/selftests/bpf/verifier/jset.c
+++ b/tools/testing/selftests/bpf/verifier/jset.c
@@ -53,6 +53,7 @@
 		  .data64 = { ~0ULL, }
 		},
 	},
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset: sign-extend",
@@ -70,6 +71,7 @@
 	.result = ACCEPT,
 	.retval = 2,
 	.data = { 1, 0, 0, 0, 0, 0, 0, 1, },
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jset: known const compare",
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index dc2cc823df2b..3ed3593bd8b6 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -547,7 +547,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "cannot write into socket",
+	.errstr = "cannot write into sock",
 	.result = REJECT,
 },
 {
@@ -562,7 +562,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "invalid bpf_sock access off=0 size=8",
+	.errstr = "invalid sock access off=0 size=8",
 	.result = REJECT,
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
new file mode 100644
index 000000000000..0ddfdf76aba5
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -0,0 +1,384 @@
+{
+	"skb->sk: no NULL check",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid mem access 'sock_common_or_null'",
+},
+{
+	"skb->sk: sk->family [non fullsock field]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sock, family)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"skb->sk: sk->type [fullsock field]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sock, type)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid sock_common access",
+},
+{
+	"bpf_sk_fullsock(skb->sk): no !skb->sk check",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "type=sock_common_or_null expected=sock_common",
+},
+{
+	"sk_fullsock(skb->sk): no NULL check on ret",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid mem access 'sock_or_null'",
+},
+{
+	"sk_fullsock(skb->sk): sk->type [fullsock field]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->family [non fullsock field]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, family)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->state [narrow load]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, state)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [narrow load]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid sock access",
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_ip6 [load 2nd byte]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_ip6[0]) + 1),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->type [narrow load]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->protocol [narrow load]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, protocol)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): beyond last field",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, state)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid sock access",
+},
+{
+	"bpf_tcp_sock(skb->sk): no !skb->sk check",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "type=sock_common_or_null expected=sock_common",
+},
+{
+	"bpf_tcp_sock(skb->sk): no NULL check on ret",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid mem access 'tcp_sock_or_null'",
+},
+{
+	"bpf_tcp_sock(skb->sk): tp->snd_cwnd",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"bpf_tcp_sock(skb->sk): tp->bytes_acked",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, bytes_acked)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"bpf_tcp_sock(skb->sk): beyond last field",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_tcp_sock, bytes_acked)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid tcp_sock access",
+},
+{
+	"bpf_tcp_sock(bpf_sk_fullsock(skb->sk)): tp->snd_cwnd",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"bpf_sk_release(skb->sk)",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, 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(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "type=sock_common expected=sock",
+},
+{
+	"bpf_sk_release(bpf_sk_fullsock(skb->sk))",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "reference has not been acquired before",
+},
+{
+	"bpf_sk_release(bpf_tcp_sock(skb->sk))",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "type=tcp_sock expected=sock",
+},
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index d58db72fdfe8..45d43bf82f26 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -46,6 +46,7 @@
 	.errstr_unpriv = "attempt to corrupt spilled",
 	.errstr = "R0 invalid mem access 'inv",
 	.result = REJECT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"check corrupted spill/fill, LSB",
diff --git a/tools/testing/selftests/bpf/verifier/spin_lock.c b/tools/testing/selftests/bpf/verifier/spin_lock.c
index d829eef372a4..781621facae4 100644
--- a/tools/testing/selftests/bpf/verifier/spin_lock.c
+++ b/tools/testing/selftests/bpf/verifier/spin_lock.c
@@ -83,6 +83,7 @@
 	.result_unpriv = REJECT,
 	.errstr_unpriv = "",
 	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"spin_lock: test4 direct ld/st",
@@ -112,6 +113,7 @@
 	.result_unpriv = REJECT,
 	.errstr_unpriv = "",
 	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"spin_lock: test5 call within a locked region",
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index 3e046695fad7..dbaf5be947b2 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -365,7 +365,7 @@
 	},
 	.result = REJECT,
 	//.errstr = "same insn cannot be used with different pointers",
-	.errstr = "cannot write into socket",
+	.errstr = "cannot write into sock",
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index 9ab5ace83e02..4b721a77bebb 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -512,6 +512,7 @@
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
 	.retval = 0xabcdef12,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: unknown scalar += value_ptr, 3",
@@ -537,6 +538,7 @@
 	.result_unpriv = REJECT,
 	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
 	.retval = 0xabcdef12,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: unknown scalar += value_ptr, 4",
@@ -559,6 +561,7 @@
 	.result = REJECT,
 	.errstr = "R1 max value is outside of the array range",
 	.errstr_unpriv = "R1 pointer arithmetic of map value goes out of range",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: value_ptr += unknown scalar, 1",
@@ -598,6 +601,7 @@
 	.fixup_map_array_48b = { 3 },
 	.result = ACCEPT,
 	.retval = 0xabcdef12,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map access: value_ptr += unknown scalar, 3",
diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
index bab13dd025a6..0d26b5e3f966 100755
--- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
+++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
@@ -37,6 +37,10 @@ prerequisite()
 		exit $ksft_skip
 	fi
 
+	present_cpus=`cat $SYSFS/devices/system/cpu/present`
+	present_max=${present_cpus##*-}
+	echo "present_cpus = $present_cpus present_max = $present_max"
+
 	echo -e "\t Cpus in online state: $online_cpus"
 
 	offline_cpus=`cat $SYSFS/devices/system/cpu/offline`
@@ -151,6 +155,8 @@ online_cpus=0
 online_max=0
 offline_cpus=0
 offline_max=0
+present_cpus=0
+present_max=0
 
 while getopts e:ahp: opt; do
 	case $opt in
@@ -190,9 +196,10 @@ if [ $allcpus -eq 0 ]; then
 	online_cpu_expect_success $online_max
 
 	if [[ $offline_cpus -gt 0 ]]; then
-		echo -e "\t offline to online to offline: cpu $offline_max"
-		online_cpu_expect_success $offline_max
-		offline_cpu_expect_success $offline_max
+		echo -e "\t offline to online to offline: cpu $present_max"
+		online_cpu_expect_success $present_max
+		offline_cpu_expect_success $present_max
+		online_cpu $present_max
 	fi
 	exit 0
 else
diff --git a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh
new file mode 100755
index 000000000000..5ba5bef44d5b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh
@@ -0,0 +1,200 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that blackhole routes are marked as offloaded and that packets hitting
+# them are dropped by the ASIC and not by the kernel.
+#
+# +---------------------------------+
+# | H1 (vrf)                        |
+# |    + $h1                        |
+# |    | 192.0.2.1/24               |
+# |    | 2001:db8:1::1/64           |
+# |    |                            |
+# |    |  default via 192.0.2.2     |
+# |    |  default via 2001:db8:1::2 |
+# +----|----------------------------+
+#      |
+# +----|----------------------------------------------------------------------+
+# | SW |                                                                      |
+# |    + $rp1                                                                 |
+# |        192.0.2.2/24                                                       |
+# |        2001:db8:1::2/64                                                   |
+# |                                                                           |
+# |        2001:db8:2::2/64                                                   |
+# |        198.51.100.2/24                                                    |
+# |    + $rp2                                                                 |
+# |    |                                                                      |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|----------------------------+
+# |    |  default via 198.51.100.2  |
+# |    |  default via 2001:db8:2::2 |
+# |    |                            |
+# |    | 2001:db8:2::1/64           |
+# |    | 198.51.100.1/24            |
+# |    + $h2                        |
+# | H2 (vrf)                        |
+# +---------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	blackhole_ipv4
+	blackhole_ipv6
+"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+
+	ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add default vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del default vrf v$h1 nexthop via 2001:db8:1::2
+	ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
+
+	simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 198.51.100.1/24 2001:db8:2::1/64
+
+	ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
+	ip -6 route add default vrf v$h2 nexthop via 2001:db8:2::2
+}
+
+h2_destroy()
+{
+	ip -6 route del default vrf v$h2 nexthop via 2001:db8:2::2
+	ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
+
+	simple_if_fini $h2 198.51.100.1/24 2001:db8:2::1/64
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+
+	tc qdisc add dev $rp1 clsact
+
+	__addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
+	__addr_add_del $rp2 add 198.51.100.2/24 2001:db8:2::2/64
+}
+
+router_destroy()
+{
+	__addr_add_del $rp2 del 198.51.100.2/24 2001:db8:2::2/64
+	__addr_add_del $rp1 del 192.0.2.2/24 2001:db8:1::2/64
+
+	tc qdisc del dev $rp1 clsact
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+ping_ipv4()
+{
+	ping_test $h1 198.51.100.1 ": h1->h2"
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::1 ": h1->h2"
+}
+
+blackhole_ipv4()
+{
+	# Transmit packets from H1 to H2 and make sure they are dropped by the
+	# ASIC and not by the kernel
+	RET=0
+
+	ip -4 route add blackhole 198.51.100.0/30
+	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
+		skip_hw dst_ip 198.51.100.1 src_ip 192.0.2.1 ip_proto icmp \
+		action pass
+
+	ip -4 route show 198.51.100.0/30 | grep -q offload
+	check_err $? "route not marked as offloaded when should"
+
+	ping_do $h1 198.51.100.1
+	check_fail $? "ping passed when should not"
+
+	tc_check_packets "dev $rp1 ingress" 101 0
+	check_err $? "packets trapped and not dropped by ASIC"
+
+	log_test "IPv4 blackhole route"
+
+	tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower
+	ip -4 route del blackhole 198.51.100.0/30
+}
+
+blackhole_ipv6()
+{
+	RET=0
+
+	ip -6 route add blackhole 2001:db8:2::/120
+	tc filter add dev $rp1 ingress protocol ipv6 pref 1 handle 101 flower \
+		skip_hw dst_ip 2001:db8:2::1 src_ip 2001:db8:1::1 \
+		ip_proto icmpv6 action pass
+
+	ip -6 route show 2001:db8:2::/120 | grep -q offload
+	check_err $? "route not marked as offloaded when should"
+
+	ping6_do $h1 2001:db8:2::1
+	check_fail $? "ping passed when should not"
+
+	tc_check_packets "dev $rp1 ingress" 101 0
+	check_err $? "packets trapped and not dropped by ASIC"
+
+	log_test "IPv6 blackhole route"
+
+	tc filter del dev $rp1 ingress protocol ipv6 pref 1 handle 101 flower
+	ip -6 route del blackhole 2001:db8:2::/120
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+	forwarding_enable
+
+	h1_create
+	h2_create
+	router_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	router_destroy
+	h2_destroy
+	h1_destroy
+
+	forwarding_restore
+	vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index f1922bf597b0..4d5b880b1d96 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -9,11 +9,11 @@ lib_dir=$(dirname $0)/../../../../net/forwarding
 
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
-	delta_two_masks_one_key_test bloom_simple_test \
-	bloom_complex_test bloom_delta_test"
+	delta_two_masks_one_key_test delta_simple_rehash_test \
+	bloom_simple_test bloom_complex_test bloom_delta_test"
 NUM_NETIFS=2
 source $lib_dir/tc_common.sh
-source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
 
 tcflags="skip_hw"
 
@@ -494,6 +494,77 @@ delta_two_masks_one_key_test()
 	log_test "delta two masks one key test ($tcflags)"
 }
 
+delta_simple_rehash_test()
+{
+	RET=0
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	devlink dev param set $DEVLINK_DEV \
+		name acl_region_rehash_interval cmode runtime value 0
+	check_err $? "Failed to set ACL region rehash interval"
+
+	tp_record_all mlxsw:mlxsw_sp_acl_tcam_vregion_rehash 7
+	tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_rehash
+	check_fail $? "Rehash trace was hit even when rehash should be disabled"
+
+	devlink dev param set $DEVLINK_DEV \
+		name acl_region_rehash_interval cmode runtime value 3000
+	check_err $? "Failed to set ACL region rehash interval"
+
+	sleep 1
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.1.0/25 action drop
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+		$tcflags dst_ip 192.0.3.0/24 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_fail $? "Matched a wrong filter"
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_fail $? "Matched a wrong filter"
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Did not match on correct filter"
+
+	tp_record_all mlxsw:* 3
+	tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_rehash
+	check_err $? "Rehash trace was not hit"
+	tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_migrate
+	check_err $? "Migrate trace was not hit"
+	tp_record_all mlxsw:* 3
+	tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_rehash
+	check_err $? "Rehash trace was not hit"
+	tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_migrate
+	check_fail $? "Migrate trace was hit when no migration should happen"
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_fail $? "Matched a wrong filter after rehash"
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_fail $? "Matched a wrong filter after rehash"
+
+	tc_check_packets "dev $h2 ingress" 102 2
+	check_err $? "Did not match on correct filter after rehash"
+
+	tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+	log_test "delta simple rehash test ($tcflags)"
+}
+
 bloom_simple_test()
 {
 	# Bloom filter requires that the eRP table is used. This test
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index a0a80e1a69e8..e7ffc79561b7 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -2,7 +2,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
 NUM_NETIFS=6
-source ../../../../net/forwarding/lib.sh
 source ../../../../net/forwarding/tc_common.sh
 source devlink_lib_spectrum.sh
 
diff --git a/tools/testing/selftests/filesystems/binderfs/.gitignore b/tools/testing/selftests/filesystems/binderfs/.gitignore
new file mode 100644
index 000000000000..8a5d9bf63dd4
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/.gitignore
@@ -0,0 +1 @@
+binderfs_test
diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile
new file mode 100644
index 000000000000..58cb659b56b4
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += -I../../../../../usr/include/
+TEST_GEN_PROGS := binderfs_test
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
new file mode 100644
index 000000000000..8c2ed962e1c7
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <linux/android/binder.h>
+#include <linux/android/binderfs.h>
+#include "../../kselftest.h"
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+	ssize_t ret;
+again:
+	ret = write(fd, buf, count);
+	if (ret < 0 && errno == EINTR)
+		goto again;
+
+	return ret;
+}
+
+static void write_to_file(const char *filename, const void *buf, size_t count,
+			  int allowed_errno)
+{
+	int fd, saved_errno;
+	ssize_t ret;
+
+	fd = open(filename, O_WRONLY | O_CLOEXEC);
+	if (fd < 0)
+		ksft_exit_fail_msg("%s - Failed to open file %s\n",
+				   strerror(errno), filename);
+
+	ret = write_nointr(fd, buf, count);
+	if (ret < 0) {
+		if (allowed_errno && (errno == allowed_errno)) {
+			close(fd);
+			return;
+		}
+
+		goto on_error;
+	}
+
+	if ((size_t)ret != count)
+		goto on_error;
+
+	close(fd);
+	return;
+
+on_error:
+	saved_errno = errno;
+	close(fd);
+	errno = saved_errno;
+
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to write to file %s\n",
+				   strerror(errno), filename);
+
+	ksft_exit_fail_msg("Failed to write to file %s\n", filename);
+}
+
+static void change_to_userns(void)
+{
+	int ret;
+	uid_t uid;
+	gid_t gid;
+	/* {g,u}id_map files only allow a max of 4096 bytes written to them */
+	char idmap[4096];
+
+	uid = getuid();
+	gid = getgid();
+
+	ret = unshare(CLONE_NEWUSER);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to unshare user namespace\n",
+				   strerror(errno));
+
+	write_to_file("/proc/self/setgroups", "deny", strlen("deny"), ENOENT);
+
+	ret = snprintf(idmap, sizeof(idmap), "0 %d 1", uid);
+	if (ret < 0 || (size_t)ret >= sizeof(idmap))
+		ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n",
+				   strerror(errno));
+
+	write_to_file("/proc/self/uid_map", idmap, strlen(idmap), 0);
+
+	ret = snprintf(idmap, sizeof(idmap), "0 %d 1", gid);
+	if (ret < 0 || (size_t)ret >= sizeof(idmap))
+		ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n",
+				   strerror(errno));
+
+	write_to_file("/proc/self/gid_map", idmap, strlen(idmap), 0);
+
+	ret = setgid(0);
+	if (ret)
+		ksft_exit_fail_msg("%s - Failed to setgid(0)\n",
+				   strerror(errno));
+
+	ret = setuid(0);
+	if (ret)
+		ksft_exit_fail_msg("%s - Failed to setgid(0)\n",
+				   strerror(errno));
+}
+
+static void change_to_mountns(void)
+{
+	int ret;
+
+	ret = unshare(CLONE_NEWNS);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n",
+				   strerror(errno));
+
+	ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to mount / as private\n",
+				   strerror(errno));
+}
+
+static void rmdir_protect_errno(const char *dir)
+{
+	int saved_errno = errno;
+	(void)rmdir(dir);
+	errno = saved_errno;
+}
+
+static void __do_binderfs_test(void)
+{
+	int fd, ret, saved_errno;
+	size_t len;
+	ssize_t wret;
+	bool keep = false;
+	struct binderfs_device device = { 0 };
+	struct binder_version version = { 0 };
+
+	change_to_mountns();
+
+	ret = mkdir("/dev/binderfs", 0755);
+	if (ret < 0) {
+		if (errno != EEXIST)
+			ksft_exit_fail_msg(
+				"%s - Failed to create binderfs mountpoint\n",
+				strerror(errno));
+
+		keep = true;
+	}
+
+	ret = mount(NULL, "/dev/binderfs", "binder", 0, 0);
+	if (ret < 0) {
+		if (errno != ENODEV)
+			ksft_exit_fail_msg("%s - Failed to mount binderfs\n",
+					   strerror(errno));
+
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_skip(
+			"The Android binderfs filesystem is not available\n");
+	}
+
+	/* binderfs mount test passed */
+	ksft_inc_pass_cnt();
+
+	memcpy(device.name, "my-binder", strlen("my-binder"));
+
+	fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC);
+	if (fd < 0)
+		ksft_exit_fail_msg(
+			"%s - Failed to open binder-control device\n",
+			strerror(errno));
+
+	ret = ioctl(fd, BINDER_CTL_ADD, &device);
+	saved_errno = errno;
+	close(fd);
+	errno = saved_errno;
+	if (ret < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg(
+			"%s - Failed to allocate new binder device\n",
+			strerror(errno));
+	}
+
+	ksft_print_msg(
+		"Allocated new binder device with major %d, minor %d, and name %s\n",
+		device.major, device.minor, device.name);
+
+	/* binder device allocation test passed */
+	ksft_inc_pass_cnt();
+
+	fd = open("/dev/binderfs/my-binder", O_CLOEXEC | O_RDONLY);
+	if (fd < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg("%s - Failed to open my-binder device\n",
+				   strerror(errno));
+	}
+
+	ret = ioctl(fd, BINDER_VERSION, &version);
+	saved_errno = errno;
+	close(fd);
+	errno = saved_errno;
+	if (ret < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg(
+			"%s - Failed to open perform BINDER_VERSION request\n",
+			strerror(errno));
+	}
+
+	ksft_print_msg("Detected binder version: %d\n",
+		       version.protocol_version);
+
+	/* binder transaction with binderfs binder device passed */
+	ksft_inc_pass_cnt();
+
+	ret = unlink("/dev/binderfs/my-binder");
+	if (ret < 0) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg("%s - Failed to delete binder device\n",
+				   strerror(errno));
+	}
+
+	/* binder device removal passed */
+	ksft_inc_pass_cnt();
+
+	ret = unlink("/dev/binderfs/binder-control");
+	if (!ret) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg("Managed to delete binder-control device\n");
+	} else if (errno != EPERM) {
+		keep ? : rmdir_protect_errno("/dev/binderfs");
+		ksft_exit_fail_msg(
+			"%s - Failed to delete binder-control device but exited with unexpected error code\n",
+			strerror(errno));
+	}
+
+	/* binder-control device removal failed as expected */
+	ksft_inc_xfail_cnt();
+
+on_error:
+	ret = umount2("/dev/binderfs", MNT_DETACH);
+	keep ?: rmdir_protect_errno("/dev/binderfs");
+	if (ret < 0)
+		ksft_exit_fail_msg("%s - Failed to unmount binderfs\n",
+				   strerror(errno));
+
+	/* binderfs unmount test passed */
+	ksft_inc_pass_cnt();
+}
+
+static void binderfs_test_privileged()
+{
+	if (geteuid() != 0)
+		ksft_print_msg(
+			"Tests are not run as root. Skipping privileged tests\n");
+	else
+		__do_binderfs_test();
+}
+
+static void binderfs_test_unprivileged()
+{
+	change_to_userns();
+	__do_binderfs_test();
+}
+
+int main(int argc, char *argv[])
+{
+	binderfs_test_privileged();
+	binderfs_test_unprivileged();
+	ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/filesystems/binderfs/config b/tools/testing/selftests/filesystems/binderfs/config
new file mode 100644
index 000000000000..02dd6cc9cf99
--- /dev/null
+++ b/tools/testing/selftests/filesystems/binderfs/config
@@ -0,0 +1,3 @@
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDERFS=y
+CONFIG_ANDROID_BINDER_IPC=y
diff --git a/tools/testing/selftests/ir/Makefile b/tools/testing/selftests/ir/Makefile
index f4ba8eb84b95..ad06489c22a5 100644
--- a/tools/testing/selftests/ir/Makefile
+++ b/tools/testing/selftests/ir/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := ir_loopback.sh
 TEST_GEN_PROGS_EXTENDED := ir_loopback
+APIDIR := ../../../include/uapi
+CFLAGS += -Wall -O2 -I$(APIDIR)
 
 include ../lib.mk
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index f8f3e90700c0..1e6d14d2825c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -21,6 +21,6 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
-$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
+$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
 $(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index 5cd2aed97958..da96eff72a8e 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -10,3 +10,5 @@ CONFIG_NET_CLS_FLOWER=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_VETH=m
+CONFIG_NAMESPACES=y
+CONFIG_NET_NS=y
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 4ac50ccb3272..47ddfc154036 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -753,6 +753,20 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
 
 	vec.iov_base = buf;
+	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len);
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	EXPECT_NE(cmsg, NULL);
+	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
+	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
+	record_type = *((unsigned char *)CMSG_DATA(cmsg));
+	EXPECT_EQ(record_type, 100);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+
+	/* Recv the message again without MSG_PEEK */
+	record_type = 0;
+	memset(buf, 0, sizeof(buf));
+
 	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len);
 	cmsg = CMSG_FIRSTHDR(&msg);
 	EXPECT_NE(cmsg, NULL);
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 47ed6cef93fb..c9ff2b47bd1c 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for netfilter selftests
 
-TEST_PROGS := nft_trans_stress.sh
+TEST_PROGS := nft_trans_stress.sh nft_nat.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
index 1017313e41a8..59caa8f71cd8 100644
--- a/tools/testing/selftests/netfilter/config
+++ b/tools/testing/selftests/netfilter/config
@@ -1,2 +1,2 @@
 CONFIG_NET_NS=y
-NF_TABLES_INET=y
+CONFIG_NF_TABLES_INET=y
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
new file mode 100755
index 000000000000..8ec76681605c
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -0,0 +1,762 @@
+#!/bin/bash
+#
+# This test is for basic NAT functionality: snat, dnat, redirect, masquerade.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+ip netns add ns0
+ip netns add ns1
+ip netns add ns2
+
+ip link add veth0 netns ns0 type veth peer name eth0 netns ns1
+ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
+
+ip -net ns0 link set lo up
+ip -net ns0 link set veth0 up
+ip -net ns0 addr add 10.0.1.1/24 dev veth0
+ip -net ns0 addr add dead:1::1/64 dev veth0
+
+ip -net ns0 link set veth1 up
+ip -net ns0 addr add 10.0.2.1/24 dev veth1
+ip -net ns0 addr add dead:2::1/64 dev veth1
+
+for i in 1 2; do
+  ip -net ns$i link set lo up
+  ip -net ns$i link set eth0 up
+  ip -net ns$i addr add 10.0.$i.99/24 dev eth0
+  ip -net ns$i route add default via 10.0.$i.1
+  ip -net ns$i addr add dead:$i::99/64 dev eth0
+  ip -net ns$i route add default via dead:$i::1
+done
+
+bad_counter()
+{
+	local ns=$1
+	local counter=$2
+	local expect=$3
+
+	echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2
+	ip netns exec $ns nft list counter inet filter $counter 1>&2
+}
+
+check_counters()
+{
+	ns=$1
+	local lret=0
+
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0in "packets 1 bytes 84"
+		lret=1
+	fi
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0out "packets 1 bytes 84"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 104"
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0in6 "$expect"
+		lret=1
+	fi
+	cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter $ns ns0out6 "$expect"
+		lret=1
+	fi
+
+	return $lret
+}
+
+check_ns0_counters()
+{
+	local ns=$1
+	local lret=0
+
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0in "packets 0 bytes 0"
+		lret=1
+	fi
+
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0in6 "packets 0 bytes 0"
+		lret=1
+	fi
+
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0out "packets 0 bytes 0"
+		lret=1
+	fi
+	cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0")
+	if [ $? -ne 0 ]; then
+		bad_counter ns0 ns0out6 "packets 0 bytes 0"
+		lret=1
+	fi
+
+	for dir in "in" "out" ; do
+		expect="packets 1 bytes 84"
+		cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 $ns$dir "$expect"
+			lret=1
+		fi
+
+		expect="packets 1 bytes 104"
+		cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 $ns$dir6 "$expect"
+			lret=1
+		fi
+	done
+
+	return $lret
+}
+
+reset_counters()
+{
+	for i in 0 1 2;do
+		ip netns exec ns$i nft reset counters inet > /dev/null
+	done
+}
+
+test_local_dnat6()
+{
+	local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+	chain output {
+		type nat hook output priority 0; policy accept;
+		ip6 daddr dead:1::99 dnat to dead:2::99
+	}
+}
+EOF
+	if [ $? -ne 0 ]; then
+		echo "SKIP: Could not add add ip6 dnat hook"
+		return $ksft_skip
+	fi
+
+	# ping netns1, expect rewrite to netns2
+	ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null
+	if [ $? -ne 0 ]; then
+		lret=1
+		echo "ERROR: ping6 failed"
+		return $lret
+	fi
+
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 0 count in ns1
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 1 packet in ns2
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2"
+	ip netns exec ns0 nft flush chain ip6 nat output
+
+	return $lret
+}
+
+test_local_dnat()
+{
+	local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+	chain output {
+		type nat hook output priority 0; policy accept;
+		ip daddr 10.0.1.99 dnat to 10.0.2.99
+	}
+}
+EOF
+	# ping netns1, expect rewrite to netns2
+	ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+	if [ $? -ne 0 ]; then
+		lret=1
+		echo "ERROR: ping failed"
+		return $lret
+	fi
+
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 0 count in ns1
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 1 packet in ns2
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2"
+
+	ip netns exec ns0 nft flush chain ip nat output
+
+	reset_counters
+	ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+	if [ $? -ne 0 ]; then
+		lret=1
+		echo "ERROR: ping failed"
+		return $lret
+	fi
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 1 count in ns1
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns0 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# expect 0 packet in ns2
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns2$dir "$expect"
+			lret=1
+		fi
+	done
+
+	test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush"
+
+	return $lret
+}
+
+
+test_masquerade6()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 via ipv6"
+		return 1
+		lret=1
+	fi
+
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+	chain postrouting {
+		type nat hook postrouting priority 0; policy accept;
+		meta oif veth0 masquerade
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading"
+		lret=1
+	fi
+
+	# ns1 should have seen packets from ns0, due to masquerade
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns1 should not have seen packets from ns2, due to masquerade
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft flush chain ip6 nat postrouting
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not flush ip6 nat postrouting" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2"
+
+	return $lret
+}
+
+test_masquerade()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: canot ping ns1 from ns2"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0; policy accept;
+		meta oif veth0 masquerade
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading"
+		lret=1
+	fi
+
+	# ns1 should have seen packets from ns0, due to masquerade
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns1 should not have seen packets from ns2, due to masquerade
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft flush chain ip nat postrouting
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not flush nat postrouting" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IP masquerade for ns2"
+
+	return $lret
+}
+
+test_redirect6()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannnot ping ns1 from ns2 via ipv6"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+	chain prerouting {
+		type nat hook prerouting priority 0; policy accept;
+		meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect"
+		lret=1
+	fi
+
+	# ns1 should have seen no packets from ns2, due to redirection
+	expect="packets 0 bytes 0"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns0 should have seen packets from ns2, due to masquerade
+	expect="packets 1 bytes 104"
+	for dir in "in6" "out6" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft delete table ip6 nat
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not delete ip6 nat table" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2"
+
+	return $lret
+}
+
+test_redirect()
+{
+	local lret=0
+
+	ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2"
+		lret=1
+	fi
+
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns2$dir "$expect"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns2 ns1$dir "$expect"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+	chain prerouting {
+		type nat hook prerouting priority 0; policy accept;
+		meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect
+	}
+}
+EOF
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ip redirect"
+		lret=1
+	fi
+
+	# ns1 should have seen no packets from ns2, due to redirection
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+
+		cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	# ns0 should have seen packets from ns2, due to masquerade
+	expect="packets 1 bytes 84"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter ns1 ns0$dir "$expect"
+			lret=1
+		fi
+	done
+
+	ip netns exec ns0 nft delete table ip nat
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not delete nat table" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IP redirection for ns2"
+
+	return $lret
+}
+
+
+# ip netns exec ns0 ping -c 1 -q 10.0.$i.99
+for i in 0 1 2; do
+ip netns exec ns$i nft -f - <<EOF
+table inet filter {
+	counter ns0in {}
+	counter ns1in {}
+	counter ns2in {}
+
+	counter ns0out {}
+	counter ns1out {}
+	counter ns2out {}
+
+	counter ns0in6 {}
+	counter ns1in6 {}
+	counter ns2in6 {}
+
+	counter ns0out6 {}
+	counter ns1out6 {}
+	counter ns2out6 {}
+
+	map nsincounter {
+		type ipv4_addr : counter
+		elements = { 10.0.1.1 : "ns0in",
+			     10.0.2.1 : "ns0in",
+			     10.0.1.99 : "ns1in",
+			     10.0.2.99 : "ns2in" }
+	}
+
+	map nsincounter6 {
+		type ipv6_addr : counter
+		elements = { dead:1::1 : "ns0in6",
+			     dead:2::1 : "ns0in6",
+			     dead:1::99 : "ns1in6",
+			     dead:2::99 : "ns2in6" }
+	}
+
+	map nsoutcounter {
+		type ipv4_addr : counter
+		elements = { 10.0.1.1 : "ns0out",
+			     10.0.2.1 : "ns0out",
+			     10.0.1.99: "ns1out",
+			     10.0.2.99: "ns2out" }
+	}
+
+	map nsoutcounter6 {
+		type ipv6_addr : counter
+		elements = { dead:1::1 : "ns0out6",
+			     dead:2::1 : "ns0out6",
+			     dead:1::99 : "ns1out6",
+			     dead:2::99 : "ns2out6" }
+	}
+
+	chain input {
+		type filter hook input priority 0; policy accept;
+		counter name ip saddr map @nsincounter
+		icmpv6 type { "echo-request", "echo-reply" } counter name ip6 saddr map @nsincounter6
+	}
+	chain output {
+		type filter hook output priority 0; policy accept;
+		counter name ip daddr map @nsoutcounter
+		icmpv6 type { "echo-request", "echo-reply" } counter name ip6 daddr map @nsoutcounter6
+	}
+}
+EOF
+done
+
+sleep 3
+# test basic connectivity
+for i in 1 2; do
+  ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null
+  if [ $? -ne 0 ];then
+  	echo "ERROR: Could not reach other namespace(s)" 1>&2
+	ret=1
+  fi
+
+  ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null
+  if [ $? -ne 0 ];then
+	echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2
+	ret=1
+  fi
+  check_counters ns$i
+  if [ $? -ne 0 ]; then
+	ret=1
+  fi
+
+  check_ns0_counters ns$i
+  if [ $? -ne 0 ]; then
+	ret=1
+  fi
+  reset_counters
+done
+
+if [ $ret -eq 0 ];then
+	echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2"
+fi
+
+reset_counters
+test_local_dnat
+test_local_dnat6
+
+reset_counters
+test_masquerade
+test_masquerade6
+
+reset_counters
+test_redirect
+test_redirect6
+
+for i in 0 1 2; do ip netns del ns$i;done
+
+exit $ret
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
index 9050eeea5f5f..1de8bd8ccf5d 100644
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -9,6 +9,3 @@ all: $(TEST_PROGS)
 top_srcdir = ../../../../..
 KSFT_KHDR_INSTALL := 1
 include ../../lib.mk
-
-clean:
-	rm -fr $(TEST_GEN_FILES)
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 82121a81681f..29bac5ef9a93 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -10,4 +10,5 @@
 /proc-uptime-002
 /read
 /self
+/setns-dcache
 /thread-self
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index 1c12c34cf85d..434d033ee067 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001
 TEST_GEN_PROGS += proc-uptime-002
 TEST_GEN_PROGS += read
 TEST_GEN_PROGS += self
+TEST_GEN_PROGS += setns-dcache
 TEST_GEN_PROGS += thread-self
 
 include ../lib.mk
diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c
new file mode 100644
index 000000000000..60ab197a73fc
--- /dev/null
+++ b/tools/testing/selftests/proc/setns-dcache.c
@@ -0,0 +1,129 @@
+/*
+ * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/*
+ * Test that setns(CLONE_NEWNET) points to new /proc/net content even
+ * if old one is in dcache.
+ *
+ * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+
+static pid_t pid = -1;
+
+static void f(void)
+{
+	if (pid > 0) {
+		kill(pid, SIGTERM);
+	}
+}
+
+int main(void)
+{
+	int fd[2];
+	char _ = 0;
+	int nsfd;
+
+	atexit(f);
+
+	/* Check for priviledges and syscall availability straight away. */
+	if (unshare(CLONE_NEWNET) == -1) {
+		if (errno == ENOSYS || errno == EPERM) {
+			return 4;
+		}
+		return 1;
+	}
+	/* Distinguisher between two otherwise empty net namespaces. */
+	if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) {
+		return 1;
+	}
+
+	if (pipe(fd) == -1) {
+		return 1;
+	}
+
+	pid = fork();
+	if (pid == -1) {
+		return 1;
+	}
+
+	if (pid == 0) {
+		if (unshare(CLONE_NEWNET) == -1) {
+			return 1;
+		}
+
+		if (write(fd[1], &_, 1) != 1) {
+			return 1;
+		}
+
+		pause();
+
+		return 0;
+	}
+
+	if (read(fd[0], &_, 1) != 1) {
+		return 1;
+	}
+
+	{
+		char buf[64];
+		snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid);
+		nsfd = open(buf, O_RDONLY);
+		if (nsfd == -1) {
+			return 1;
+		}
+	}
+
+	/* Reliably pin dentry into dcache. */
+	(void)open("/proc/net/unix", O_RDONLY);
+
+	if (setns(nsfd, CLONE_NEWNET) == -1) {
+		return 1;
+	}
+
+	kill(pid, SIGTERM);
+	pid = 0;
+
+	{
+		char buf[4096];
+		ssize_t rv;
+		int fd;
+
+		fd = open("/proc/net/unix", O_RDONLY);
+		if (fd == -1) {
+			return 1;
+		}
+
+#define S "Num       RefCount Protocol Flags    Type St Inode Path\n"
+		rv = read(fd, buf, sizeof(buf));
+
+		assert(rv == strlen(S));
+		assert(memcmp(buf, S, strlen(S)) == 0);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 496a9a8c773a..7e632b465ab4 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1608,7 +1608,16 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 #ifdef SYSCALL_NUM_RET_SHARE_REG
 # define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(-1, action)
 #else
-# define EXPECT_SYSCALL_RETURN(val, action)	EXPECT_EQ(val, action)
+# define EXPECT_SYSCALL_RETURN(val, action)		\
+	do {						\
+		errno = 0;				\
+		if (val < 0) {				\
+			EXPECT_EQ(-1, action);		\
+			EXPECT_EQ(-(val), errno);	\
+		} else {				\
+			EXPECT_EQ(val, action);		\
+		}					\
+	} while (0)
 #endif
 
 /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
@@ -1647,7 +1656,7 @@ int get_syscall(struct __test_metadata *_metadata, pid_t tracee)
 
 /* Architecture-specific syscall changing routine. */
 void change_syscall(struct __test_metadata *_metadata,
-		    pid_t tracee, int syscall)
+		    pid_t tracee, int syscall, int result)
 {
 	int ret;
 	ARCH_REGS regs;
@@ -1706,7 +1715,7 @@ void change_syscall(struct __test_metadata *_metadata,
 #ifdef SYSCALL_NUM_RET_SHARE_REG
 		TH_LOG("Can't modify syscall return on this architecture");
 #else
-		regs.SYSCALL_RET = EPERM;
+		regs.SYSCALL_RET = result;
 #endif
 
 #ifdef HAVE_GETREGS
@@ -1734,14 +1743,19 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee,
 	case 0x1002:
 		/* change getpid to getppid. */
 		EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee));
-		change_syscall(_metadata, tracee, __NR_getppid);
+		change_syscall(_metadata, tracee, __NR_getppid, 0);
 		break;
 	case 0x1003:
-		/* skip gettid. */
+		/* skip gettid with valid return code. */
 		EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee));
-		change_syscall(_metadata, tracee, -1);
+		change_syscall(_metadata, tracee, -1, 45000);
 		break;
 	case 0x1004:
+		/* skip openat with error. */
+		EXPECT_EQ(__NR_openat, get_syscall(_metadata, tracee));
+		change_syscall(_metadata, tracee, -1, -ESRCH);
+		break;
+	case 0x1005:
 		/* do nothing (allow getppid) */
 		EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee));
 		break;
@@ -1774,9 +1788,11 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee,
 	nr = get_syscall(_metadata, tracee);
 
 	if (nr == __NR_getpid)
-		change_syscall(_metadata, tracee, __NR_getppid);
+		change_syscall(_metadata, tracee, __NR_getppid, 0);
+	if (nr == __NR_gettid)
+		change_syscall(_metadata, tracee, -1, 45000);
 	if (nr == __NR_openat)
-		change_syscall(_metadata, tracee, -1);
+		change_syscall(_metadata, tracee, -1, -ESRCH);
 }
 
 FIXTURE_DATA(TRACE_syscall) {
@@ -1793,8 +1809,10 @@ FIXTURE_SETUP(TRACE_syscall)
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1002),
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_gettid, 0, 1),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1003),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_openat, 0, 1),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1004),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005),
 		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
 	};
 
@@ -1842,15 +1860,26 @@ TEST_F(TRACE_syscall, ptrace_syscall_redirected)
 	EXPECT_NE(self->mypid, syscall(__NR_getpid));
 }
 
-TEST_F(TRACE_syscall, ptrace_syscall_dropped)
+TEST_F(TRACE_syscall, ptrace_syscall_errno)
+{
+	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+	teardown_trace_fixture(_metadata, self->tracer);
+	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+					   true);
+
+	/* Tracer should skip the open syscall, resulting in ESRCH. */
+	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
+}
+
+TEST_F(TRACE_syscall, ptrace_syscall_faked)
 {
 	/* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
 	teardown_trace_fixture(_metadata, self->tracer);
 	self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
 					   true);
 
-	/* Tracer should skip the open syscall, resulting in EPERM. */
-	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_openat));
+	/* Tracer should skip the gettid syscall, resulting fake pid. */
+	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
 }
 
 TEST_F(TRACE_syscall, syscall_allowed)
@@ -1883,7 +1912,21 @@ TEST_F(TRACE_syscall, syscall_redirected)
 	EXPECT_NE(self->mypid, syscall(__NR_getpid));
 }
 
-TEST_F(TRACE_syscall, syscall_dropped)
+TEST_F(TRACE_syscall, syscall_errno)
+{
+	long ret;
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
+	ASSERT_EQ(0, ret);
+
+	/* openat has been skipped and an errno return. */
+	EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat));
+}
+
+TEST_F(TRACE_syscall, syscall_faked)
 {
 	long ret;
 
@@ -1894,8 +1937,7 @@ TEST_F(TRACE_syscall, syscall_dropped)
 	ASSERT_EQ(0, ret);
 
 	/* gettid has been skipped and an altered return value stored. */
-	EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid));
-	EXPECT_NE(self->mytid, syscall(__NR_gettid));
+	EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid));
 }
 
 TEST_F(TRACE_syscall, skip_after_RET_TRACE)
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index c02683cfb6c9..7656c7ce79d9 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -O3 -Wl,-no-as-needed -Wall
-LDFLAGS += -lrt -lpthread -lm
+LDLIBS += -lrt -lpthread -lm
 
 # these are all "safe" tests that don't modify
 # system time or require escalated privileges