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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-10-14

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

12 days of development and
85 files changed, 1889 insertions(+), 1020 deletions(-)

The main changes are:

1) auto-generation of bpf_helper_defs.h, from Andrii.

2) split of bpf_helpers.h into bpf_{helpers, helper_defs, endian, tracing}.h
   and move into libbpf, from Andrii.

3) Track contents of read-only maps as scalars in the verifier, from Andrii.

4) small x86 JIT optimization, from Daniel.

5) cross compilation support, from Ivan.

6) bpf flow_dissector enhancements, from Jakub and Stanislav.
====================

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

85 files changed, 1889 insertions, 1020 deletions

diff --git a/Documentation/bpf/prog_flow_dissector.rst b/Documentation/bpf/prog_flow_dissector.rst
index a78bf036cadd..4d86780ab0f1 100644
--- a/Documentation/bpf/prog_flow_dissector.rst
+++ b/Documentation/bpf/prog_flow_dissector.rst
@@ -142,3 +142,6 @@ BPF flow dissector doesn't support exporting all the metadata that in-kernel
 C-based implementation can export. Notable example is single VLAN (802.1Q)
 and double VLAN (802.1AD) tags. Please refer to the ``struct bpf_flow_keys``
 for a set of information that's currently can be exported from the BPF context.
+
+When BPF flow dissector is attached to the root network namespace (machine-wide
+policy), users can't override it in their child network namespaces.
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 991549a1c5f3..3ad2ba1ad855 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -909,6 +909,16 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP32 | BPF_JSLT | BPF_K:
 		case BPF_JMP32 | BPF_JSGE | BPF_K:
 		case BPF_JMP32 | BPF_JSLE | BPF_K:
+			/* test dst_reg, dst_reg to save one extra byte */
+			if (imm32 == 0) {
+				if (BPF_CLASS(insn->code) == BPF_JMP)
+					EMIT1(add_2mod(0x48, dst_reg, dst_reg));
+				else if (is_ereg(dst_reg))
+					EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+				EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
+				goto emit_cond_jmp;
+			}
+
 			/* cmp dst_reg, imm8/32 */
 			if (BPF_CLASS(insn->code) == BPF_JMP)
 				EMIT1(add_1mod(0x48, dst_reg));
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5b9d22338606..282e28bf41ec 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -363,7 +363,7 @@ struct bpf_prog_stats {
 	u64 cnt;
 	u64 nsecs;
 	struct u64_stats_sync syncp;
-};
+} __aligned(2 * sizeof(u64));
 
 struct bpf_prog_aux {
 	atomic_t refcnt;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 77c6be96d676..a65c3b0c6935 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -794,7 +794,7 @@ union bpf_attr {
  * 		A 64-bit integer containing the current GID and UID, and
  * 		created as such: *current_gid* **<< 32 \|** *current_uid*.
  *
- * int bpf_get_current_comm(char *buf, u32 size_of_buf)
+ * int bpf_get_current_comm(void *buf, u32 size_of_buf)
  * 	Description
  * 		Copy the **comm** attribute of the current task into *buf* of
  * 		*size_of_buf*. The **comm** attribute contains the name of
@@ -1023,7 +1023,7 @@ union bpf_attr {
  * 		The realm of the route for the packet associated to *skb*, or 0
  * 		if none was found.
  *
- * int bpf_perf_event_output(struct pt_regs *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
  * 	Description
  * 		Write raw *data* blob into a special BPF perf event held by
  * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -1068,7 +1068,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len)
+ * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len)
  * 	Description
  * 		This helper was provided as an easy way to load data from a
  * 		packet. It can be used to load *len* bytes from *offset* from
@@ -1085,7 +1085,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_get_stackid(struct pt_regs *ctx, struct bpf_map *map, u64 flags)
+ * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags)
  * 	Description
  * 		Walk a user or a kernel stack and return its id. To achieve
  * 		this, the helper needs *ctx*, which is a pointer to the context
@@ -1154,7 +1154,7 @@ union bpf_attr {
  * 		The checksum result, or a negative error code in case of
  * 		failure.
  *
- * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
  * 	Description
  * 		Retrieve tunnel options metadata for the packet associated to
  * 		*skb*, and store the raw tunnel option data to the buffer *opt*
@@ -1172,7 +1172,7 @@ union bpf_attr {
  * 	Return
  * 		The size of the option data retrieved.
  *
- * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
  * 	Description
  * 		Set tunnel options metadata for the packet associated to *skb*
  * 		to the option data contained in the raw buffer *opt* of *size*.
@@ -1511,7 +1511,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **setsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1595,7 +1595,7 @@ union bpf_attr {
  * 	Return
  * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
  *
- * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
  * 		Redirect the packet to the socket referenced by *map* (of type
  * 		**BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
@@ -1715,7 +1715,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **getsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1947,7 +1947,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags)
+ * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags)
  * 	Description
  * 		Return a user or a kernel stack in bpf program provided buffer.
  * 		To achieve this, the helper needs *ctx*, which is a pointer
@@ -1980,7 +1980,7 @@ union bpf_attr {
  * 		A non-negative value equal to or less than *size* on success,
  * 		or a negative error in case of failure.
  *
- * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
  * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
  * 		it provides an easy way to load *len* bytes from *offset*
@@ -2033,7 +2033,7 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
- * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
  *		The *skops* is used as a new value for the entry associated to
@@ -2392,7 +2392,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
  *	Description
  *		For socket policies, insert *len* bytes into *msg* at offset
  *		*start*.
@@ -2408,9 +2408,9 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
- * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
+ * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
  *	Description
- *		Will remove *pop* bytes from a *msg* starting at byte *start*.
+ *		Will remove *len* bytes from a *msg* starting at byte *start*.
  *		This may result in **ENOMEM** errors under certain situations if
  *		an allocation and copy are required due to a full ring buffer.
  *		However, the helper will try to avoid doing the allocation
@@ -2505,7 +2505,7 @@ union bpf_attr {
  *		A **struct bpf_tcp_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
- * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
+ * int bpf_skb_ecn_set_ce(struct sk_buff *skb)
  *	Description
  *		Set ECN (Explicit Congestion Notification) field of IP header
  *		to **CE** (Congestion Encountered) if current value is **ECT**
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ffc3e53f5300..d3446f018b9a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2739,6 +2739,41 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 	reg->smax_value = reg->umax_value;
 }
 
+static bool bpf_map_is_rdonly(const struct bpf_map *map)
+{
+	return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+}
+
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+{
+	void *ptr;
+	u64 addr;
+	int err;
+
+	err = map->ops->map_direct_value_addr(map, &addr, off);
+	if (err)
+		return err;
+	ptr = (void *)(long)addr + off;
+
+	switch (size) {
+	case sizeof(u8):
+		*val = (u64)*(u8 *)ptr;
+		break;
+	case sizeof(u16):
+		*val = (u64)*(u16 *)ptr;
+		break;
+	case sizeof(u32):
+		*val = (u64)*(u32 *)ptr;
+		break;
+	case sizeof(u64):
+		*val = *(u64 *)ptr;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -2776,9 +2811,27 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err)
 			return err;
 		err = check_map_access(env, regno, off, size, false);
-		if (!err && t == BPF_READ && value_regno >= 0)
-			mark_reg_unknown(env, regs, value_regno);
+		if (!err && t == BPF_READ && value_regno >= 0) {
+			struct bpf_map *map = reg->map_ptr;
+
+			/* if map is read-only, track its contents as scalars */
+			if (tnum_is_const(reg->var_off) &&
+			    bpf_map_is_rdonly(map) &&
+			    map->ops->map_direct_value_addr) {
+				int map_off = off + reg->var_off.value;
+				u64 val = 0;
 
+				err = bpf_map_direct_read(map, map_off, size,
+							  &val);
+				if (err)
+					return err;
+
+				regs[value_regno].type = SCALAR_VALUE;
+				__mark_reg_known(&regs[value_regno], val);
+			} else {
+				mark_reg_unknown(env, regs, value_regno);
+			}
+		}
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 7c09d87d3269..dbf502c18656 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -114,19 +114,50 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 {
 	struct bpf_prog *attached;
 	struct net *net;
+	int ret = 0;
 
 	net = current->nsproxy->net_ns;
 	mutex_lock(&flow_dissector_mutex);
+
+	if (net == &init_net) {
+		/* BPF flow dissector in the root namespace overrides
+		 * any per-net-namespace one. When attaching to root,
+		 * make sure we don't have any BPF program attached
+		 * to the non-root namespaces.
+		 */
+		struct net *ns;
+
+		for_each_net(ns) {
+			if (ns == &init_net)
+				continue;
+			if (rcu_access_pointer(ns->flow_dissector_prog)) {
+				ret = -EEXIST;
+				goto out;
+			}
+		}
+	} else {
+		/* Make sure root flow dissector is not attached
+		 * when attaching to the non-root namespace.
+		 */
+		if (rcu_access_pointer(init_net.flow_dissector_prog)) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+
 	attached = rcu_dereference_protected(net->flow_dissector_prog,
 					     lockdep_is_held(&flow_dissector_mutex));
-	if (attached) {
-		/* Only one BPF program can be attached at a time */
-		mutex_unlock(&flow_dissector_mutex);
-		return -EEXIST;
+	if (attached == prog) {
+		/* The same program cannot be attached twice */
+		ret = -EINVAL;
+		goto out;
 	}
 	rcu_assign_pointer(net->flow_dissector_prog, prog);
+	if (attached)
+		bpf_prog_put(attached);
+out:
 	mutex_unlock(&flow_dissector_mutex);
-	return 0;
+	return ret;
 }
 
 int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
@@ -910,7 +941,10 @@ bool __skb_flow_dissect(const struct net *net,
 	WARN_ON_ONCE(!net);
 	if (net) {
 		rcu_read_lock();
-		attached = rcu_dereference(net->flow_dissector_prog);
+		attached = rcu_dereference(init_net.flow_dissector_prog);
+
+		if (!attached)
+			attached = rcu_dereference(net->flow_dissector_prog);
 
 		if (attached) {
 			struct bpf_flow_keys flow_keys;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index d7bf62ffbb5e..20781ad5f9c3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -386,7 +386,7 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
 
 /* XDP RX runs under NAPI protection, and in different delivery error
  * scenarios (e.g. queue full), it is possible to return the xdp_frame
- * while still leveraging this protection.  The @napi_direct boolian
+ * while still leveraging this protection.  The @napi_direct boolean
  * is used for those calls sites.  Thus, allowing for faster recycling
  * of xdp_frames/pages in those cases.
  */
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 1d9be26b4edd..4df11ddb9c75 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -4,55 +4,53 @@ BPF_SAMPLES_PATH ?= $(abspath $(srctree)/$(src))
 TOOLS_PATH := $(BPF_SAMPLES_PATH)/../../tools
 
 # List of programs to build
-hostprogs-y := test_lru_dist
-hostprogs-y += sock_example
-hostprogs-y += fds_example
-hostprogs-y += sockex1
-hostprogs-y += sockex2
-hostprogs-y += sockex3
-hostprogs-y += tracex1
-hostprogs-y += tracex2
-hostprogs-y += tracex3
-hostprogs-y += tracex4
-hostprogs-y += tracex5
-hostprogs-y += tracex6
-hostprogs-y += tracex7
-hostprogs-y += test_probe_write_user
-hostprogs-y += trace_output
-hostprogs-y += lathist
-hostprogs-y += offwaketime
-hostprogs-y += spintest
-hostprogs-y += map_perf_test
-hostprogs-y += test_overhead
-hostprogs-y += test_cgrp2_array_pin
-hostprogs-y += test_cgrp2_attach
-hostprogs-y += test_cgrp2_sock
-hostprogs-y += test_cgrp2_sock2
-hostprogs-y += xdp1
-hostprogs-y += xdp2
-hostprogs-y += xdp_router_ipv4
-hostprogs-y += test_current_task_under_cgroup
-hostprogs-y += trace_event
-hostprogs-y += sampleip
-hostprogs-y += tc_l2_redirect
-hostprogs-y += lwt_len_hist
-hostprogs-y += xdp_tx_iptunnel
-hostprogs-y += test_map_in_map
-hostprogs-y += per_socket_stats_example
-hostprogs-y += xdp_redirect
-hostprogs-y += xdp_redirect_map
-hostprogs-y += xdp_redirect_cpu
-hostprogs-y += xdp_monitor
-hostprogs-y += xdp_rxq_info
-hostprogs-y += syscall_tp
-hostprogs-y += cpustat
-hostprogs-y += xdp_adjust_tail
-hostprogs-y += xdpsock
-hostprogs-y += xdp_fwd
-hostprogs-y += task_fd_query
-hostprogs-y += xdp_sample_pkts
-hostprogs-y += ibumad
-hostprogs-y += hbm
+tprogs-y := test_lru_dist
+tprogs-y += sock_example
+tprogs-y += fds_example
+tprogs-y += sockex1
+tprogs-y += sockex2
+tprogs-y += sockex3
+tprogs-y += tracex1
+tprogs-y += tracex2
+tprogs-y += tracex3
+tprogs-y += tracex4
+tprogs-y += tracex5
+tprogs-y += tracex6
+tprogs-y += tracex7
+tprogs-y += test_probe_write_user
+tprogs-y += trace_output
+tprogs-y += lathist
+tprogs-y += offwaketime
+tprogs-y += spintest
+tprogs-y += map_perf_test
+tprogs-y += test_overhead
+tprogs-y += test_cgrp2_array_pin
+tprogs-y += test_cgrp2_attach
+tprogs-y += test_cgrp2_sock
+tprogs-y += test_cgrp2_sock2
+tprogs-y += xdp1
+tprogs-y += xdp2
+tprogs-y += xdp_router_ipv4
+tprogs-y += test_current_task_under_cgroup
+tprogs-y += trace_event
+tprogs-y += sampleip
+tprogs-y += tc_l2_redirect
+tprogs-y += lwt_len_hist
+tprogs-y += xdp_tx_iptunnel
+tprogs-y += test_map_in_map
+tprogs-y += xdp_redirect_map
+tprogs-y += xdp_redirect_cpu
+tprogs-y += xdp_monitor
+tprogs-y += xdp_rxq_info
+tprogs-y += syscall_tp
+tprogs-y += cpustat
+tprogs-y += xdp_adjust_tail
+tprogs-y += xdpsock
+tprogs-y += xdp_fwd
+tprogs-y += task_fd_query
+tprogs-y += xdp_sample_pkts
+tprogs-y += ibumad
+tprogs-y += hbm
 
 # Libbpf dependencies
 LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
@@ -111,7 +109,7 @@ ibumad-objs := bpf_load.o ibumad_user.o $(TRACE_HELPERS)
 hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS)
 
 # Tell kbuild to always build the programs
-always := $(hostprogs-y)
+always := $(tprogs-y)
 always += sockex1_kern.o
 always += sockex2_kern.o
 always += sockex3_kern.o
@@ -145,7 +143,6 @@ always += sampleip_kern.o
 always += lwt_len_hist_kern.o
 always += xdp_tx_iptunnel_kern.o
 always += test_map_in_map_kern.o
-always += cookie_uid_helper_example.o
 always += tcp_synrto_kern.o
 always += tcp_rwnd_kern.o
 always += tcp_bufs_kern.o
@@ -171,20 +168,38 @@ always += ibumad_kern.o
 always += hbm_out_kern.o
 always += hbm_edt_kern.o
 
-KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include
-KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/
-KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
-KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
-KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf
+ifeq ($(ARCH), arm)
+# Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux
+# headers when arm instruction set identification is requested.
+ARM_ARCH_SELECTOR := $(filter -D__LINUX_ARM_ARCH__%, $(KBUILD_CFLAGS))
+BPF_EXTRA_CFLAGS := $(ARM_ARCH_SELECTOR)
+TPROGS_CFLAGS += $(ARM_ARCH_SELECTOR)
+endif
+
+TPROGS_CFLAGS += -Wall -O2
+TPROGS_CFLAGS += -Wmissing-prototypes
+TPROGS_CFLAGS += -Wstrict-prototypes
+
+TPROGS_CFLAGS += -I$(objtree)/usr/include
+TPROGS_CFLAGS += -I$(srctree)/tools/lib/bpf/
+TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+TPROGS_CFLAGS += -I$(srctree)/tools/lib/
+TPROGS_CFLAGS += -I$(srctree)/tools/include
+TPROGS_CFLAGS += -I$(srctree)/tools/perf
 
-HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
+ifdef SYSROOT
+TPROGS_CFLAGS += --sysroot=$(SYSROOT)
+TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib
+endif
+
+TPROGCFLAGS_bpf_load.o += -Wno-unused-variable
 
-KBUILD_HOSTLDLIBS		+= $(LIBBPF) -lelf
-HOSTLDLIBS_tracex4		+= -lrt
-HOSTLDLIBS_trace_output	+= -lrt
-HOSTLDLIBS_map_perf_test	+= -lrt
-HOSTLDLIBS_test_overhead	+= -lrt
-HOSTLDLIBS_xdpsock		+= -pthread
+TPROGS_LDLIBS			+= $(LIBBPF) -lelf
+TPROGLDLIBS_tracex4		+= -lrt
+TPROGLDLIBS_trace_output	+= -lrt
+TPROGLDLIBS_map_perf_test	+= -lrt
+TPROGLDLIBS_test_overhead	+= -lrt
+TPROGLDLIBS_xdpsock		+= -pthread
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
@@ -195,15 +210,14 @@ BTF_PAHOLE ?= pahole
 
 # Detect that we're cross compiling and use the cross compiler
 ifdef CROSS_COMPILE
-HOSTCC = $(CROSS_COMPILE)gcc
-CLANG_ARCH_ARGS = -target $(ARCH)
+CLANG_ARCH_ARGS = --target=$(notdir $(CROSS_COMPILE:%-=%))
 endif
 
 # Don't evaluate probes and warnings if we need to run make recursively
 ifneq ($(src),)
-HDR_PROBE := $(shell echo "\#include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \
-	$(HOSTCC) $(KBUILD_HOSTCFLAGS) -x c - -o /dev/null 2>/dev/null && \
-	echo okay)
+HDR_PROBE := $(shell printf "\#include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \
+	$(CC) $(TPROGS_CFLAGS) $(TPROGS_LDFLAGS) -x c - \
+	-o /dev/null 2>/dev/null && echo okay)
 
 ifeq ($(HDR_PROBE),)
 $(warning WARNING: Detected possible issues with include path.)
@@ -219,10 +233,10 @@ BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
 			  /bin/rm -f ./llvm_btf_verify.o)
 
 ifneq ($(BTF_LLVM_PROBE),)
-	EXTRA_CFLAGS += -g
+	BPF_EXTRA_CFLAGS += -g
 else
 ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),)
-	EXTRA_CFLAGS += -g
+	BPF_EXTRA_CFLAGS += -g
 	LLC_FLAGS += -mattr=dwarfris
 	DWARF2BTF = y
 endif
@@ -239,7 +253,8 @@ clean:
 
 $(LIBBPF): FORCE
 # Fix up variables inherited from Kbuild that tools/ build system won't like
-	$(MAKE) -C $(dir $@) RM='rm -rf' LDFLAGS= srctree=$(BPF_SAMPLES_PATH)/../../ O=
+	$(MAKE) -C $(dir $@) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \
+		LDFLAGS=$(TPROGS_LDFLAGS) srctree=$(BPF_SAMPLES_PATH)/../../ O=
 
 $(obj)/syscall_nrs.h:	$(obj)/syscall_nrs.s FORCE
 	$(call filechk,offsets,__SYSCALL_NRS_H__)
@@ -276,13 +291,16 @@ $(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
 $(obj)/hbm.o: $(src)/hbm.h
 $(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
 
+-include $(BPF_SAMPLES_PATH)/Makefile.target
+
 # asm/sysreg.h - inline assembly used by it is incompatible with llvm.
 # But, there is no easy way to fix it, so just exclude it since it is
 # useless for BPF samples.
 $(obj)/%.o: $(src)/%.c
 	@echo "  CLANG-bpf " $@
-	$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
-		-I$(srctree)/tools/testing/selftests/bpf/ \
+	$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
+		-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
+		-I$(srctree)/tools/lib/bpf/ \
 		-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
 		-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
diff --git a/samples/bpf/Makefile.target b/samples/bpf/Makefile.target
new file mode 100644
index 000000000000..7621f55e2947
--- /dev/null
+++ b/samples/bpf/Makefile.target
@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: GPL-2.0
+# ==========================================================================
+# Building binaries on the host system
+# Binaries are not used during the compilation of the kernel, and intended
+# to be build for target board, target board can be host of course. Added to
+# build binaries to run not on host system.
+#
+# Sample syntax
+# tprogs-y := xsk_example
+# Will compile xsk_example.c and create an executable named xsk_example
+#
+# tprogs-y    := xdpsock
+# xdpsock-objs := xdpsock_1.o xdpsock_2.o
+# Will compile xdpsock_1.c and xdpsock_2.c, and then link the executable
+# xdpsock, based on xdpsock_1.o and xdpsock_2.o
+#
+# Derived from scripts/Makefile.host
+#
+__tprogs := $(sort $(tprogs-y))
+
+# C code
+# Executables compiled from a single .c file
+tprog-csingle	:= $(foreach m,$(__tprogs), \
+			$(if $($(m)-objs),,$(m)))
+
+# C executables linked based on several .o files
+tprog-cmulti	:= $(foreach m,$(__tprogs),\
+			$(if $($(m)-objs),$(m)))
+
+# Object (.o) files compiled from .c files
+tprog-cobjs	:= $(sort $(foreach m,$(__tprogs),$($(m)-objs)))
+
+tprog-csingle	:= $(addprefix $(obj)/,$(tprog-csingle))
+tprog-cmulti	:= $(addprefix $(obj)/,$(tprog-cmulti))
+tprog-cobjs	:= $(addprefix $(obj)/,$(tprog-cobjs))
+
+#####
+# Handle options to gcc. Support building with separate output directory
+
+_tprogc_flags   = $(TPROGS_CFLAGS) \
+                 $(TPROGCFLAGS_$(basetarget).o)
+
+# $(objtree)/$(obj) for including generated headers from checkin source files
+ifeq ($(KBUILD_EXTMOD),)
+ifdef building_out_of_srctree
+_tprogc_flags   += -I $(objtree)/$(obj)
+endif
+endif
+
+tprogc_flags    = -Wp,-MD,$(depfile) $(_tprogc_flags)
+
+# Create executable from a single .c file
+# tprog-csingle -> Executable
+quiet_cmd_tprog-csingle 	= CC  $@
+      cmd_tprog-csingle	= $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ $< \
+		$(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F))
+$(tprog-csingle): $(obj)/%: $(src)/%.c FORCE
+	$(call if_changed_dep,tprog-csingle)
+
+# Link an executable based on list of .o files, all plain c
+# tprog-cmulti -> executable
+quiet_cmd_tprog-cmulti	= LD  $@
+      cmd_tprog-cmulti	= $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ \
+			  $(addprefix $(obj)/,$($(@F)-objs)) \
+			  $(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F))
+$(tprog-cmulti): $(tprog-cobjs) FORCE
+	$(call if_changed,tprog-cmulti)
+$(call multi_depend, $(tprog-cmulti), , -objs)
+
+# Create .o file from a single .c file
+# tprog-cobjs -> .o
+quiet_cmd_tprog-cobjs	= CC  $@
+      cmd_tprog-cobjs	= $(CC) $(tprogc_flags) -c -o $@ $<
+$(tprog-cobjs): $(obj)/%.o: $(src)/%.c FORCE
+	$(call if_changed_dep,tprog-cobjs)
diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index 5f27e4faca50..cc1f00a1ee06 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -14,6 +14,20 @@ Compiling requires having installed:
 Note that LLVM's tool 'llc' must support target 'bpf', list version
 and supported targets with command: ``llc --version``
 
+Clean and configuration
+-----------------------
+
+It can be needed to clean tools, samples or kernel before trying new arch or
+after some changes (on demand)::
+
+ make -C tools clean
+ make -C samples/bpf clean
+ make clean
+
+Configure kernel, defconfig for instance::
+
+ make defconfig
+
 Kernel headers
 --------------
 
@@ -68,9 +82,26 @@ It is also possible to point make to the newly compiled 'llc' or
 Cross compiling samples
 -----------------------
 In order to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH
-environment variables before calling make. This will direct make to build
-samples for the cross target.
+environment variables before calling make. But do this before clean,
+cofiguration and header install steps described above. This will direct make to
+build samples for the cross target::
+
+ export ARCH=arm64
+ export CROSS_COMPILE="aarch64-linux-gnu-"
+
+Headers can be also installed on RFS of target board if need to keep them in
+sync (not necessarily and it creates a local "usr/include" directory also)::
+
+ make INSTALL_HDR_PATH=~/some_sysroot/usr headers_install
+
+Pointing LLC and CLANG is not necessarily if it's installed on HOST and have
+in its targets appropriate arm64 arch (usually it has several arches).
+Build samples::
+
+ make samples/bpf/
+
+Or build samples with SYSROOT if some header or library is absent in toolchain,
+say libelf, providing address to file system containing headers and libs,
+can be RFS of target board::
 
-export ARCH=arm64
-export CROSS_COMPILE="aarch64-linux-gnu-"
-make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
+ make samples/bpf/ SYSROOT=~/some_sysroot
diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h
index aa207a2eebbd..4edaf47876ca 100644
--- a/samples/bpf/hbm_kern.h
+++ b/samples/bpf/hbm_kern.h
@@ -59,21 +59,18 @@
 #define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20)
 #define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate))
 
-struct bpf_map_def SEC("maps") queue_state = {
-	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
-	.key_size = sizeof(struct bpf_cgroup_storage_key),
-	.value_size = sizeof(struct hbm_vqueue),
-};
-BPF_ANNOTATE_KV_PAIR(queue_state, struct bpf_cgroup_storage_key,
-		     struct hbm_vqueue);
-
-struct bpf_map_def SEC("maps") queue_stats = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(struct hbm_queue_stats),
-	.max_entries = 1,
-};
-BPF_ANNOTATE_KV_PAIR(queue_stats, int, struct hbm_queue_stats);
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct hbm_vqueue);
+} queue_state SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, u32);
+	__type(value, struct hvm_queue_stats);
+} queue_stats SEC(".maps");
 
 struct hbm_pkt_info {
 	int	cwnd;
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 2b2ffb97018b..5c11aefbc489 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -9,25 +9,27 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
+#include "bpf_tracing.h"
 
 #define MAX_ENTRIES 1000
 #define MAX_NR_CPUS 1024
 
-struct bpf_map_def SEC("maps") hash_map = {
+struct bpf_map_def_legacy SEC("maps") hash_map = {
 	.type = BPF_MAP_TYPE_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
 	.max_entries = MAX_ENTRIES,
 };
 
-struct bpf_map_def SEC("maps") lru_hash_map = {
+struct bpf_map_def_legacy SEC("maps") lru_hash_map = {
 	.type = BPF_MAP_TYPE_LRU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
 	.max_entries = 10000,
 };
 
-struct bpf_map_def SEC("maps") nocommon_lru_hash_map = {
+struct bpf_map_def_legacy SEC("maps") nocommon_lru_hash_map = {
 	.type = BPF_MAP_TYPE_LRU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
@@ -35,7 +37,7 @@ struct bpf_map_def SEC("maps") nocommon_lru_hash_map = {
 	.map_flags = BPF_F_NO_COMMON_LRU,
 };
 
-struct bpf_map_def SEC("maps") inner_lru_hash_map = {
+struct bpf_map_def_legacy SEC("maps") inner_lru_hash_map = {
 	.type = BPF_MAP_TYPE_LRU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
@@ -44,20 +46,20 @@ struct bpf_map_def SEC("maps") inner_lru_hash_map = {
 	.numa_node = 0,
 };
 
-struct bpf_map_def SEC("maps") array_of_lru_hashs = {
+struct bpf_map_def_legacy SEC("maps") array_of_lru_hashs = {
 	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
 	.key_size = sizeof(u32),
 	.max_entries = MAX_NR_CPUS,
 };
 
-struct bpf_map_def SEC("maps") percpu_hash_map = {
+struct bpf_map_def_legacy SEC("maps") percpu_hash_map = {
 	.type = BPF_MAP_TYPE_PERCPU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
 	.max_entries = MAX_ENTRIES,
 };
 
-struct bpf_map_def SEC("maps") hash_map_alloc = {
+struct bpf_map_def_legacy SEC("maps") hash_map_alloc = {
 	.type = BPF_MAP_TYPE_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
@@ -65,7 +67,7 @@ struct bpf_map_def SEC("maps") hash_map_alloc = {
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
-struct bpf_map_def SEC("maps") percpu_hash_map_alloc = {
+struct bpf_map_def_legacy SEC("maps") percpu_hash_map_alloc = {
 	.type = BPF_MAP_TYPE_PERCPU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
@@ -73,7 +75,7 @@ struct bpf_map_def SEC("maps") percpu_hash_map_alloc = {
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
-struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
+struct bpf_map_def_legacy SEC("maps") lpm_trie_map_alloc = {
 	.type = BPF_MAP_TYPE_LPM_TRIE,
 	.key_size = 8,
 	.value_size = sizeof(long),
@@ -81,14 +83,14 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
-struct bpf_map_def SEC("maps") array_map = {
+struct bpf_map_def_legacy SEC("maps") array_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
 	.max_entries = MAX_ENTRIES,
 };
 
-struct bpf_map_def SEC("maps") lru_hash_lookup_map = {
+struct bpf_map_def_legacy SEC("maps") lru_hash_lookup_map = {
 	.type = BPF_MAP_TYPE_LRU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c
index e7d9a0a3d45b..9cb5207a692f 100644
--- a/samples/bpf/offwaketime_kern.c
+++ b/samples/bpf/offwaketime_kern.c
@@ -6,6 +6,7 @@
  */
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 #include <uapi/linux/ptrace.h>
 #include <uapi/linux/perf_event.h>
 #include <linux/version.h>
diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c
index 6db6b21fdc6d..ef5892377beb 100644
--- a/samples/bpf/parse_ldabs.c
+++ b/samples/bpf/parse_ldabs.c
@@ -12,6 +12,7 @@
 #include <linux/udp.h>
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
 
 #define DEFAULT_PKTGEN_UDP_PORT	9
 #define IP_MF			0x2000
diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c
index ceabf31079cf..4a190893894f 100644
--- a/samples/bpf/sampleip_kern.c
+++ b/samples/bpf/sampleip_kern.c
@@ -9,6 +9,7 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/bpf_perf_event.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 #define MAX_IPS		8192
 
diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c
index ed18e9a4909c..f96943f443ab 100644
--- a/samples/bpf/sockex1_kern.c
+++ b/samples/bpf/sockex1_kern.c
@@ -3,6 +3,7 @@
 #include <uapi/linux/if_packet.h>
 #include <uapi/linux/ip.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
index f2f9dbc021b0..5566fa7d92fa 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -1,5 +1,6 @@
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
 #include <uapi/linux/in.h>
 #include <uapi/linux/if.h>
 #include <uapi/linux/if_ether.h>
diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c
index c527b57d3ec8..151dd842ecc0 100644
--- a/samples/bpf/sockex3_kern.c
+++ b/samples/bpf/sockex3_kern.c
@@ -6,6 +6,7 @@
  */
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
 #include <uapi/linux/in.h>
 #include <uapi/linux/if.h>
 #include <uapi/linux/if_ether.h>
diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c
index ce0167d09cdc..6e9478aa2938 100644
--- a/samples/bpf/spintest_kern.c
+++ b/samples/bpf/spintest_kern.c
@@ -10,6 +10,7 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/perf_event.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
index 274c884c87fe..ff43341bdfce 100644
--- a/samples/bpf/tcbpf1_kern.c
+++ b/samples/bpf/tcbpf1_kern.c
@@ -8,6 +8,7 @@
 #include <uapi/linux/filter.h>
 #include <uapi/linux/pkt_cls.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
 
 /* compiler workaround */
 #define _htonl __builtin_bswap32
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
index 42c44d091dd1..4f80cbe74c72 100644
--- a/samples/bpf/test_map_in_map_kern.c
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -11,11 +11,13 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/in6.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
+#include "bpf_tracing.h"
 
 #define MAX_NR_PORTS 65536
 
 /* map #0 */
-struct bpf_map_def SEC("maps") port_a = {
+struct bpf_map_def_legacy SEC("maps") port_a = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(int),
@@ -23,7 +25,7 @@ struct bpf_map_def SEC("maps") port_a = {
 };
 
 /* map #1 */
-struct bpf_map_def SEC("maps") port_h = {
+struct bpf_map_def_legacy SEC("maps") port_h = {
 	.type = BPF_MAP_TYPE_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(int),
@@ -31,7 +33,7 @@ struct bpf_map_def SEC("maps") port_h = {
 };
 
 /* map #2 */
-struct bpf_map_def SEC("maps") reg_result_h = {
+struct bpf_map_def_legacy SEC("maps") reg_result_h = {
 	.type = BPF_MAP_TYPE_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(int),
@@ -39,7 +41,7 @@ struct bpf_map_def SEC("maps") reg_result_h = {
 };
 
 /* map #3 */
-struct bpf_map_def SEC("maps") inline_result_h = {
+struct bpf_map_def_legacy SEC("maps") inline_result_h = {
 	.type = BPF_MAP_TYPE_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(int),
@@ -47,7 +49,7 @@ struct bpf_map_def SEC("maps") inline_result_h = {
 };
 
 /* map #4 */ /* Test case #0 */
-struct bpf_map_def SEC("maps") a_of_port_a = {
+struct bpf_map_def_legacy SEC("maps") a_of_port_a = {
 	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
 	.key_size = sizeof(u32),
 	.inner_map_idx = 0, /* map_fd[0] is port_a */
@@ -55,7 +57,7 @@ struct bpf_map_def SEC("maps") a_of_port_a = {
 };
 
 /* map #5 */ /* Test case #1 */
-struct bpf_map_def SEC("maps") h_of_port_a = {
+struct bpf_map_def_legacy SEC("maps") h_of_port_a = {
 	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
 	.key_size = sizeof(u32),
 	.inner_map_idx = 0, /* map_fd[0] is port_a */
@@ -63,7 +65,7 @@ struct bpf_map_def SEC("maps") h_of_port_a = {
 };
 
 /* map #6 */ /* Test case #2 */
-struct bpf_map_def SEC("maps") h_of_port_h = {
+struct bpf_map_def_legacy SEC("maps") h_of_port_h = {
 	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
 	.key_size = sizeof(u32),
 	.inner_map_idx = 1, /* map_fd[1] is port_h */
diff --git a/samples/bpf/test_overhead_kprobe_kern.c b/samples/bpf/test_overhead_kprobe_kern.c
index 468a66a92ef9..8d2518e68db9 100644
--- a/samples/bpf/test_overhead_kprobe_kern.c
+++ b/samples/bpf/test_overhead_kprobe_kern.c
@@ -8,6 +8,7 @@
 #include <linux/ptrace.h>
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 #define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
 
diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c
index 3a677c807044..a543358218e6 100644
--- a/samples/bpf/test_probe_write_user_kern.c
+++ b/samples/bpf/test_probe_write_user_kern.c
@@ -9,6 +9,7 @@
 #include <uapi/linux/bpf.h>
 #include <linux/version.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 struct bpf_map_def SEC("maps") dnat_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c
index 7068fbdde951..8dc18d233a27 100644
--- a/samples/bpf/trace_event_kern.c
+++ b/samples/bpf/trace_event_kern.c
@@ -10,6 +10,7 @@
 #include <uapi/linux/bpf_perf_event.h>
 #include <uapi/linux/perf_event.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 struct key_t {
 	char comm[TASK_COMM_LEN];
diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c
index 107da148820f..1a15f6605129 100644
--- a/samples/bpf/tracex1_kern.c
+++ b/samples/bpf/tracex1_kern.c
@@ -9,6 +9,7 @@
 #include <uapi/linux/bpf.h>
 #include <linux/version.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 #define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
 
diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c
index 5e11c20ce5ec..d70b3ea79ea7 100644
--- a/samples/bpf/tracex2_kern.c
+++ b/samples/bpf/tracex2_kern.c
@@ -9,6 +9,7 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c
index ea1d4c19c132..9af546bebfa9 100644
--- a/samples/bpf/tracex3_kern.c
+++ b/samples/bpf/tracex3_kern.c
@@ -9,6 +9,7 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 struct bpf_map_def SEC("maps") my_map = {
 	.type = BPF_MAP_TYPE_HASH,
diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c
index 6dd8e384de96..2a02cbe9d9a1 100644
--- a/samples/bpf/tracex4_kern.c
+++ b/samples/bpf/tracex4_kern.c
@@ -8,6 +8,7 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 struct pair {
 	u64 val;
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index 35cb0eed3be5..b3557b21a8fe 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -11,6 +11,7 @@
 #include <uapi/linux/unistd.h>
 #include "syscall_nrs.h"
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 #define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
 
diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c
index 411fdb21f8bc..c616508befb9 100644
--- a/samples/bpf/xdp_adjust_tail_kern.c
+++ b/samples/bpf/xdp_adjust_tail_kern.c
@@ -25,6 +25,9 @@
 #define ICMP_TOOBIG_SIZE 98
 #define ICMP_TOOBIG_PAYLOAD_SIZE 92
 
+/* volatile to prevent compiler optimizations */
+static volatile __u32 max_pcktsz = MAX_PCKT_SIZE;
+
 struct bpf_map_def SEC("maps") icmpcnt = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
@@ -92,7 +95,7 @@ static __always_inline int send_icmp4_too_big(struct xdp_md *xdp)
 	orig_iph = data + off;
 	icmp_hdr->type = ICMP_DEST_UNREACH;
 	icmp_hdr->code = ICMP_FRAG_NEEDED;
-	icmp_hdr->un.frag.mtu = htons(MAX_PCKT_SIZE-sizeof(struct ethhdr));
+	icmp_hdr->un.frag.mtu = htons(max_pcktsz - sizeof(struct ethhdr));
 	icmp_hdr->checksum = 0;
 	ipv4_csum(icmp_hdr, ICMP_TOOBIG_PAYLOAD_SIZE, &csum);
 	icmp_hdr->checksum = csum;
@@ -121,7 +124,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp)
 	int pckt_size = data_end - data;
 	int offset;
 
-	if (pckt_size > MAX_PCKT_SIZE) {
+	if (pckt_size > max(max_pcktsz, ICMP_TOOBIG_SIZE)) {
 		offset = pckt_size - ICMP_TOOBIG_SIZE;
 		if (bpf_xdp_adjust_tail(xdp, 0 - offset))
 			return XDP_PASS;
diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c
index a3596b617c4c..d86e9ad0356b 100644
--- a/samples/bpf/xdp_adjust_tail_user.c
+++ b/samples/bpf/xdp_adjust_tail_user.c
@@ -23,6 +23,7 @@
 #include "libbpf.h"
 
 #define STATS_INTERVAL_S 2U
+#define MAX_PCKT_SIZE 600
 
 static int ifindex = -1;
 static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
@@ -72,6 +73,7 @@ static void usage(const char *cmd)
 	printf("Usage: %s [...]\n", cmd);
 	printf("    -i <ifname|ifindex> Interface\n");
 	printf("    -T <stop-after-X-seconds> Default: 0 (forever)\n");
+	printf("    -P <MAX_PCKT_SIZE> Default: %u\n", MAX_PCKT_SIZE);
 	printf("    -S use skb-mode\n");
 	printf("    -N enforce native mode\n");
 	printf("    -F force loading prog\n");
@@ -85,13 +87,14 @@ int main(int argc, char **argv)
 		.prog_type	= BPF_PROG_TYPE_XDP,
 	};
 	unsigned char opt_flags[256] = {};
-	const char *optstr = "i:T:SNFh";
+	const char *optstr = "i:T:P:SNFh";
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
 	unsigned int kill_after_s = 0;
 	int i, prog_fd, map_fd, opt;
 	struct bpf_object *obj;
-	struct bpf_map *map;
+	__u32 max_pckt_size = 0;
+	__u32 key = 0;
 	char filename[256];
 	int err;
 
@@ -110,6 +113,9 @@ int main(int argc, char **argv)
 		case 'T':
 			kill_after_s = atoi(optarg);
 			break;
+		case 'P':
+			max_pckt_size = atoi(optarg);
+			break;
 		case 'S':
 			xdp_flags |= XDP_FLAGS_SKB_MODE;
 			break;
@@ -150,15 +156,20 @@ int main(int argc, char **argv)
 	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
 		return 1;
 
-	map = bpf_map__next(NULL, obj);
-	if (!map) {
-		printf("finding a map in obj file failed\n");
-		return 1;
+	/* static global var 'max_pcktsz' is accessible from .data section */
+	if (max_pckt_size) {
+		map_fd = bpf_object__find_map_fd_by_name(obj, "xdp_adju.data");
+		if (map_fd < 0) {
+			printf("finding a max_pcktsz map in obj file failed\n");
+			return 1;
+		}
+		bpf_map_update_elem(map_fd, &key, &max_pckt_size, BPF_ANY);
 	}
-	map_fd = bpf_map__fd(map);
 
-	if (!prog_fd) {
-		printf("load_bpf_file: %s\n", strerror(errno));
+	/* fetch icmpcnt map */
+	map_fd = bpf_object__find_map_fd_by_name(obj, "icmpcnt");
+	if (map_fd < 0) {
+		printf("finding a icmpcnt map in obj file failed\n");
 		return 1;
 	}
 
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index df011ac33402..405c4e091f8b 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -378,7 +378,7 @@ static void usage(const char *prog)
 		"  -q, --queue=n	Use queue n (default 0)\n"
 		"  -p, --poll		Use poll syscall\n"
 		"  -S, --xdp-skb=n	Use XDP skb-mod\n"
-		"  -N, --xdp-native=n	Enfore XDP native mode\n"
+		"  -N, --xdp-native=n	Enforce XDP native mode\n"
 		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
 		"  -z, --zero-copy      Force zero-copy mode.\n"
 		"  -c, --copy           Force copy mode.\n"
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 894cc58c1a03..7df9ce598ff9 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -391,6 +391,154 @@ SEE ALSO
 
         print('')
 
+class PrinterHelpers(Printer):
+    """
+    A printer for dumping collected information about helpers as C header to
+    be included from BPF program.
+    @helpers: array of Helper objects to print to standard output
+    """
+
+    type_fwds = [
+            'struct bpf_fib_lookup',
+            'struct bpf_perf_event_data',
+            'struct bpf_perf_event_value',
+            'struct bpf_sock',
+            'struct bpf_sock_addr',
+            'struct bpf_sock_ops',
+            'struct bpf_sock_tuple',
+            'struct bpf_spin_lock',
+            'struct bpf_sysctl',
+            'struct bpf_tcp_sock',
+            'struct bpf_tunnel_key',
+            'struct bpf_xfrm_state',
+            'struct pt_regs',
+            'struct sk_reuseport_md',
+            'struct sockaddr',
+            'struct tcphdr',
+
+            'struct __sk_buff',
+            'struct sk_msg_md',
+            'struct xdp_md',
+    ]
+    known_types = {
+            '...',
+            'void',
+            'const void',
+            'char',
+            'const char',
+            'int',
+            'long',
+            'unsigned long',
+
+            '__be16',
+            '__be32',
+            '__wsum',
+
+            'struct bpf_fib_lookup',
+            'struct bpf_perf_event_data',
+            'struct bpf_perf_event_value',
+            'struct bpf_sock',
+            'struct bpf_sock_addr',
+            'struct bpf_sock_ops',
+            'struct bpf_sock_tuple',
+            'struct bpf_spin_lock',
+            'struct bpf_sysctl',
+            'struct bpf_tcp_sock',
+            'struct bpf_tunnel_key',
+            'struct bpf_xfrm_state',
+            'struct pt_regs',
+            'struct sk_reuseport_md',
+            'struct sockaddr',
+            'struct tcphdr',
+    }
+    mapped_types = {
+            'u8': '__u8',
+            'u16': '__u16',
+            'u32': '__u32',
+            'u64': '__u64',
+            's8': '__s8',
+            's16': '__s16',
+            's32': '__s32',
+            's64': '__s64',
+            'size_t': 'unsigned long',
+            'struct bpf_map': 'void',
+            'struct sk_buff': 'struct __sk_buff',
+            'const struct sk_buff': 'const struct __sk_buff',
+            'struct sk_msg_buff': 'struct sk_msg_md',
+            'struct xdp_buff': 'struct xdp_md',
+    }
+
+    def print_header(self):
+        header = '''\
+/* This is auto-generated file. See bpf_helpers_doc.py for details. */
+
+/* Forward declarations of BPF structs */'''
+
+        print(header)
+        for fwd in self.type_fwds:
+            print('%s;' % fwd)
+        print('')
+
+    def print_footer(self):
+        footer = ''
+        print(footer)
+
+    def map_type(self, t):
+        if t in self.known_types:
+            return t
+        if t in self.mapped_types:
+            return self.mapped_types[t]
+        print("")
+        print("Unrecognized type '%s', please add it to known types!" % t)
+        sys.exit(1)
+
+    seen_helpers = set()
+
+    def print_one(self, helper):
+        proto = helper.proto_break_down()
+
+        if proto['name'] in self.seen_helpers:
+            return
+        self.seen_helpers.add(proto['name'])
+
+        print('/*')
+        print(" * %s" % proto['name'])
+        print(" *")
+        if (helper.desc):
+            # Do not strip all newline characters: formatted code at the end of
+            # a section must be followed by a blank line.
+            for line in re.sub('\n$', '', helper.desc, count=1).split('\n'):
+                print(' *{}{}'.format(' \t' if line else '', line))
+
+        if (helper.ret):
+            print(' *')
+            print(' * Returns')
+            for line in helper.ret.rstrip().split('\n'):
+                print(' *{}{}'.format(' \t' if line else '', line))
+
+        print(' */')
+        print('static %s %s(*%s)(' % (self.map_type(proto['ret_type']),
+                                      proto['ret_star'], proto['name']), end='')
+        comma = ''
+        for i, a in enumerate(proto['args']):
+            t = a['type']
+            n = a['name']
+            if proto['name'] == 'bpf_get_socket_cookie' and i == 0:
+                    t = 'void'
+                    n = 'ctx'
+            one_arg = '{}{}'.format(comma, self.map_type(t))
+            if n:
+                if a['star']:
+                    one_arg += ' {}'.format(a['star'])
+                else:
+                    one_arg += ' '
+                one_arg += '{}'.format(n)
+            comma = ', '
+            print(one_arg, end='')
+
+        print(') = (void *) %d;' % len(self.seen_helpers))
+        print('')
+
 ###############################################################################
 
 # If script is launched from scripts/ from kernel tree and can access
@@ -405,6 +553,8 @@ Parse eBPF header file and generate documentation for eBPF helper functions.
 The RST-formatted output produced can be turned into a manual page with the
 rst2man utility.
 """)
+argParser.add_argument('--header', action='store_true',
+                       help='generate C header file')
 if (os.path.isfile(bpfh)):
     argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h',
                            default=bpfh)
@@ -417,5 +567,8 @@ headerParser = HeaderParser(args.filename)
 headerParser.run()
 
 # Print formatted output to standard output.
-printer = PrinterRST(headerParser.helpers)
+if args.header:
+    printer = PrinterHelpers(headerParser.helpers)
+else:
+    printer = PrinterRST(headerParser.helpers)
 printer.print_all()
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 93d008687020..4764581ff9ea 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -27,7 +27,7 @@ bool json_output;
 bool show_pinned;
 bool block_mount;
 bool verifier_logs;
-int bpf_flags;
+bool relaxed_maps;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
 
@@ -396,7 +396,7 @@ int main(int argc, char **argv)
 			show_pinned = true;
 			break;
 		case 'm':
-			bpf_flags = MAPS_RELAX_COMPAT;
+			relaxed_maps = true;
 			break;
 		case 'n':
 			block_mount = true;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index af9ad56c303a..2899095f8254 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -94,7 +94,7 @@ extern bool json_output;
 extern bool show_pinned;
 extern bool block_mount;
 extern bool verifier_logs;
-extern int bpf_flags;
+extern bool relaxed_maps;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 43fdbbfe41bb..27da96a797ab 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1092,9 +1092,7 @@ free_data_in:
 static int load_with_options(int argc, char **argv, bool first_prog_only)
 {
 	struct bpf_object_load_attr load_attr = { 0 };
-	struct bpf_object_open_attr open_attr = {
-		.prog_type = BPF_PROG_TYPE_UNSPEC,
-	};
+	enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC;
 	enum bpf_attach_type expected_attach_type;
 	struct map_replace *map_replace = NULL;
 	struct bpf_program *prog = NULL, *pos;
@@ -1105,11 +1103,16 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 	const char *pinfile;
 	unsigned int i, j;
 	__u32 ifindex = 0;
+	const char *file;
 	int idx, err;
 
+	LIBBPF_OPTS(bpf_object_open_opts, open_opts,
+		.relaxed_maps = relaxed_maps,
+	);
+
 	if (!REQ_ARGS(2))
 		return -1;
-	open_attr.file = GET_ARG();
+	file = GET_ARG();
 	pinfile = GET_ARG();
 
 	while (argc) {
@@ -1118,7 +1121,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 
 			NEXT_ARG();
 
-			if (open_attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
+			if (common_prog_type != BPF_PROG_TYPE_UNSPEC) {
 				p_err("program type already specified");
 				goto err_free_reuse_maps;
 			}
@@ -1135,8 +1138,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 			strcat(type, *argv);
 			strcat(type, "/");
 
-			err = libbpf_prog_type_by_name(type,
-						       &open_attr.prog_type,
+			err = libbpf_prog_type_by_name(type, &common_prog_type,
 						       &expected_attach_type);
 			free(type);
 			if (err < 0)
@@ -1224,16 +1226,16 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 
 	set_max_rlimit();
 
-	obj = __bpf_object__open_xattr(&open_attr, bpf_flags);
+	obj = bpf_object__open_file(file, &open_opts);
 	if (IS_ERR_OR_NULL(obj)) {
 		p_err("failed to open object file");
 		goto err_free_reuse_maps;
 	}
 
 	bpf_object__for_each_program(pos, obj) {
-		enum bpf_prog_type prog_type = open_attr.prog_type;
+		enum bpf_prog_type prog_type = common_prog_type;
 
-		if (open_attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
 			const char *sec_name = bpf_program__title(pos, false);
 
 			err = libbpf_prog_type_by_name(sec_name, &prog_type,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 77c6be96d676..a65c3b0c6935 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -794,7 +794,7 @@ union bpf_attr {
  * 		A 64-bit integer containing the current GID and UID, and
  * 		created as such: *current_gid* **<< 32 \|** *current_uid*.
  *
- * int bpf_get_current_comm(char *buf, u32 size_of_buf)
+ * int bpf_get_current_comm(void *buf, u32 size_of_buf)
  * 	Description
  * 		Copy the **comm** attribute of the current task into *buf* of
  * 		*size_of_buf*. The **comm** attribute contains the name of
@@ -1023,7 +1023,7 @@ union bpf_attr {
  * 		The realm of the route for the packet associated to *skb*, or 0
  * 		if none was found.
  *
- * int bpf_perf_event_output(struct pt_regs *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
  * 	Description
  * 		Write raw *data* blob into a special BPF perf event held by
  * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -1068,7 +1068,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len)
+ * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len)
  * 	Description
  * 		This helper was provided as an easy way to load data from a
  * 		packet. It can be used to load *len* bytes from *offset* from
@@ -1085,7 +1085,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_get_stackid(struct pt_regs *ctx, struct bpf_map *map, u64 flags)
+ * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags)
  * 	Description
  * 		Walk a user or a kernel stack and return its id. To achieve
  * 		this, the helper needs *ctx*, which is a pointer to the context
@@ -1154,7 +1154,7 @@ union bpf_attr {
  * 		The checksum result, or a negative error code in case of
  * 		failure.
  *
- * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
  * 	Description
  * 		Retrieve tunnel options metadata for the packet associated to
  * 		*skb*, and store the raw tunnel option data to the buffer *opt*
@@ -1172,7 +1172,7 @@ union bpf_attr {
  * 	Return
  * 		The size of the option data retrieved.
  *
- * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size)
+ * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
  * 	Description
  * 		Set tunnel options metadata for the packet associated to *skb*
  * 		to the option data contained in the raw buffer *opt* of *size*.
@@ -1511,7 +1511,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **setsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1595,7 +1595,7 @@ union bpf_attr {
  * 	Return
  * 		**XDP_REDIRECT** on success, or **XDP_ABORTED** on error.
  *
- * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
  * 		Redirect the packet to the socket referenced by *map* (of type
  * 		**BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
@@ -1715,7 +1715,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen)
+ * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **getsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1947,7 +1947,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags)
+ * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags)
  * 	Description
  * 		Return a user or a kernel stack in bpf program provided buffer.
  * 		To achieve this, the helper needs *ctx*, which is a pointer
@@ -1980,7 +1980,7 @@ union bpf_attr {
  * 		A non-negative value equal to or less than *size* on success,
  * 		or a negative error in case of failure.
  *
- * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
  * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
  * 		it provides an easy way to load *len* bytes from *offset*
@@ -2033,7 +2033,7 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
- * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
+ * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
  *		The *skops* is used as a new value for the entry associated to
@@ -2392,7 +2392,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
  *	Description
  *		For socket policies, insert *len* bytes into *msg* at offset
  *		*start*.
@@ -2408,9 +2408,9 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
- * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
+ * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
  *	Description
- *		Will remove *pop* bytes from a *msg* starting at byte *start*.
+ *		Will remove *len* bytes from a *msg* starting at byte *start*.
  *		This may result in **ENOMEM** errors under certain situations if
  *		an allocation and copy are required due to a full ring buffer.
  *		However, the helper will try to avoid doing the allocation
@@ -2505,7 +2505,7 @@ union bpf_attr {
  *		A **struct bpf_tcp_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
- * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
+ * int bpf_skb_ecn_set_ce(struct sk_buff *skb)
  *	Description
  *		Set ECN (Explicit Congestion Notification) field of IP header
  *		to **CE** (Congestion Encountered) if current value is **ECT**
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index d9e9dec04605..35bf013e368c 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -3,3 +3,7 @@ libbpf.pc
 FEATURE-DUMP.libbpf
 test_libbpf
 libbpf.so.*
+TAGS
+tags
+cscope.*
+/bpf_helper_defs.h
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index c6f94cffe06e..75b538577c17 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -52,7 +52,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx
+FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
@@ -133,6 +133,8 @@ LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
 PC_FILE		:= $(addprefix $(OUTPUT),$(PC_FILE))
 
+TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags)
+
 GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
 			   cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \
@@ -140,22 +142,14 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
 VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
-CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
-
-CXX_TEST_TARGET = $(OUTPUT)test_libbpf
-
-ifeq ($(feature-cxx), 1)
-	CMD_TARGETS += $(CXX_TEST_TARGET)
-endif
-
-TARGETS = $(CMD_TARGETS)
+CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) $(OUTPUT)test_libbpf
 
 all: fixdep
 	$(Q)$(MAKE) all_cmd
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN): force elfdep bpfdep
+$(BPF_IN): force elfdep bpfdep bpf_helper_defs.h
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -173,19 +167,24 @@ $(BPF_IN): force elfdep bpfdep
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
+bpf_helper_defs.h: $(srctree)/include/uapi/linux/bpf.h
+	$(Q)$(srctree)/scripts/bpf_helpers_doc.py --header 		\
+		--file $(srctree)/include/uapi/linux/bpf.h > bpf_helper_defs.h
+
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
-	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
-				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
+	$(QUIET_LINK)$(CC) $(LDFLAGS) \
+		--shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
+		-Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
 	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
 
 $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
-$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
-	$(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@
+$(OUTPUT)test_libbpf: test_libbpf.c $(OUTPUT)libbpf.a
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(INCLUDES) $^ -lelf -o $@
 
 $(OUTPUT)libbpf.pc:
 	$(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
@@ -234,13 +233,18 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
-install_headers:
+install_headers: bpf_helper_defs.h
 	$(call QUIET_INSTALL, headers) \
 		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
 		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
 		$(call do_install,btf.h,$(prefix)/include/bpf,644); \
 		$(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \
-		$(call do_install,xsk.h,$(prefix)/include/bpf,644);
+		$(call do_install,xsk.h,$(prefix)/include/bpf,644); \
+		$(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \
+		$(call do_install,bpf_helper_defs.h,$(prefix)/include/bpf,644); \
+		$(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \
+		$(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \
+		$(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644);
 
 install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
@@ -255,14 +259,14 @@ config-clean:
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
+	$(call QUIET_CLEAN, libbpf) $(RM) $(CMD_TARGETS) \
 		*.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
-		*.pc LIBBPF-CFLAGS
+		*.pc LIBBPF-CFLAGS bpf_helper_defs.h
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
 
-PHONY += force elfdep bpfdep
+PHONY += force elfdep bpfdep cscope tags
 force:
 
 elfdep:
@@ -271,6 +275,14 @@ elfdep:
 bpfdep:
 	@if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi
 
+cscope:
+	ls *.c *.h > cscope.files
+	cscope -b -q -I $(srctree)/include -f cscope.out
+
+tags:
+	rm -f TAGS tags
+	ls *.c *.h | xargs $(TAGS_PROG) -a
+
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
new file mode 100644
index 000000000000..4daf04c25493
--- /dev/null
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -0,0 +1,167 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_CORE_READ_H__
+#define __BPF_CORE_READ_H__
+
+/*
+ * bpf_core_read() abstracts away bpf_probe_read() call and captures offset
+ * relocation for source address using __builtin_preserve_access_index()
+ * built-in, provided by Clang.
+ *
+ * __builtin_preserve_access_index() takes as an argument an expression of
+ * taking an address of a field within struct/union. It makes compiler emit
+ * a relocation, which records BTF type ID describing root struct/union and an
+ * accessor string which describes exact embedded field that was used to take
+ * an address. See detailed description of this relocation format and
+ * semantics in comments to struct bpf_offset_reloc in libbpf_internal.h.
+ *
+ * This relocation allows libbpf to adjust BPF instruction to use correct
+ * actual field offset, based on target kernel BTF type that matches original
+ * (local) BTF, used to record relocation.
+ */
+#define bpf_core_read(dst, sz, src)					    \
+	bpf_probe_read(dst, sz,						    \
+		       (const void *)__builtin_preserve_access_index(src))
+
+/*
+ * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str()
+ * additionally emitting BPF CO-RE field relocation for specified source
+ * argument.
+ */
+#define bpf_core_read_str(dst, sz, src)					    \
+	bpf_probe_read_str(dst, sz,					    \
+			   (const void *)__builtin_preserve_access_index(src))
+
+#define ___concat(a, b) a ## b
+#define ___apply(fn, n) ___concat(fn, n)
+#define ___nth(_1, _2, _3, _4, _5, _6, _7, _8, _9, _10, __11, N, ...) N
+
+/*
+ * return number of provided arguments; used for switch-based variadic macro
+ * definitions (see ___last, ___arrow, etc below)
+ */
+#define ___narg(...) ___nth(_, ##__VA_ARGS__, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+/*
+ * return 0 if no arguments are passed, N - otherwise; used for
+ * recursively-defined macros to specify termination (0) case, and generic
+ * (N) case (e.g., ___read_ptrs, ___core_read)
+ */
+#define ___empty(...) ___nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+
+#define ___last1(x) x
+#define ___last2(a, x) x
+#define ___last3(a, b, x) x
+#define ___last4(a, b, c, x) x
+#define ___last5(a, b, c, d, x) x
+#define ___last6(a, b, c, d, e, x) x
+#define ___last7(a, b, c, d, e, f, x) x
+#define ___last8(a, b, c, d, e, f, g, x) x
+#define ___last9(a, b, c, d, e, f, g, h, x) x
+#define ___last10(a, b, c, d, e, f, g, h, i, x) x
+#define ___last(...) ___apply(___last, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___nolast2(a, _) a
+#define ___nolast3(a, b, _) a, b
+#define ___nolast4(a, b, c, _) a, b, c
+#define ___nolast5(a, b, c, d, _) a, b, c, d
+#define ___nolast6(a, b, c, d, e, _) a, b, c, d, e
+#define ___nolast7(a, b, c, d, e, f, _) a, b, c, d, e, f
+#define ___nolast8(a, b, c, d, e, f, g, _) a, b, c, d, e, f, g
+#define ___nolast9(a, b, c, d, e, f, g, h, _) a, b, c, d, e, f, g, h
+#define ___nolast10(a, b, c, d, e, f, g, h, i, _) a, b, c, d, e, f, g, h, i
+#define ___nolast(...) ___apply(___nolast, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___arrow1(a) a
+#define ___arrow2(a, b) a->b
+#define ___arrow3(a, b, c) a->b->c
+#define ___arrow4(a, b, c, d) a->b->c->d
+#define ___arrow5(a, b, c, d, e) a->b->c->d->e
+#define ___arrow6(a, b, c, d, e, f) a->b->c->d->e->f
+#define ___arrow7(a, b, c, d, e, f, g) a->b->c->d->e->f->g
+#define ___arrow8(a, b, c, d, e, f, g, h) a->b->c->d->e->f->g->h
+#define ___arrow9(a, b, c, d, e, f, g, h, i) a->b->c->d->e->f->g->h->i
+#define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j
+#define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___type(...) typeof(___arrow(__VA_ARGS__))
+
+#define ___read(read_fn, dst, src_type, src, accessor)			    \
+	read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor)
+
+/* "recursively" read a sequence of inner pointers using local __t var */
+#define ___rd_first(src, a) ___read(bpf_core_read, &__t, ___type(src), src, a);
+#define ___rd_last(...)							    \
+	___read(bpf_core_read, &__t,					    \
+		___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__));
+#define ___rd_p1(...) const void *__t; ___rd_first(__VA_ARGS__)
+#define ___rd_p2(...) ___rd_p1(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p3(...) ___rd_p2(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p4(...) ___rd_p3(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p5(...) ___rd_p4(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p6(...) ___rd_p5(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p7(...) ___rd_p6(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p8(...) ___rd_p7(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p9(...) ___rd_p8(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___read_ptrs(src, ...)						    \
+	___apply(___rd_p, ___narg(__VA_ARGS__))(src, __VA_ARGS__)
+
+#define ___core_read0(fn, dst, src, a)					    \
+	___read(fn, dst, ___type(src), src, a);
+#define ___core_readN(fn, dst, src, ...)				    \
+	___read_ptrs(src, ___nolast(__VA_ARGS__))			    \
+	___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t,	    \
+		___last(__VA_ARGS__));
+#define ___core_read(fn, dst, src, a, ...)				    \
+	___apply(___core_read, ___empty(__VA_ARGS__))(fn, dst,		    \
+						      src, a, ##__VA_ARGS__)
+
+/*
+ * BPF_CORE_READ_INTO() is a more performance-conscious variant of
+ * BPF_CORE_READ(), in which final field is read into user-provided storage.
+ * See BPF_CORE_READ() below for more details on general usage.
+ */
+#define BPF_CORE_READ_INTO(dst, src, a, ...)				    \
+	({								    \
+		___core_read(bpf_core_read, dst, src, a, ##__VA_ARGS__)	    \
+	})
+
+/*
+ * BPF_CORE_READ_STR_INTO() does same "pointer chasing" as
+ * BPF_CORE_READ() for intermediate pointers, but then executes (and returns
+ * corresponding error code) bpf_core_read_str() for final string read.
+ */
+#define BPF_CORE_READ_STR_INTO(dst, src, a, ...)			    \
+	({								    \
+		___core_read(bpf_core_read_str, dst, src, a, ##__VA_ARGS__) \
+	})
+
+/*
+ * BPF_CORE_READ() is used to simplify BPF CO-RE relocatable read, especially
+ * when there are few pointer chasing steps.
+ * E.g., what in non-BPF world (or in BPF w/ BCC) would be something like:
+ *	int x = s->a.b.c->d.e->f->g;
+ * can be succinctly achieved using BPF_CORE_READ as:
+ *	int x = BPF_CORE_READ(s, a.b.c, d.e, f, g);
+ *
+ * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF
+ * CO-RE relocatable bpf_probe_read() wrapper) calls, logically equivalent to:
+ * 1. const void *__t = s->a.b.c;
+ * 2. __t = __t->d.e;
+ * 3. __t = __t->f;
+ * 4. return __t->g;
+ *
+ * Equivalence is logical, because there is a heavy type casting/preservation
+ * involved, as well as all the reads are happening through bpf_probe_read()
+ * calls using __builtin_preserve_access_index() to emit CO-RE relocations.
+ *
+ * N.B. Only up to 9 "field accessors" are supported, which should be more
+ * than enough for any practical purpose.
+ */
+#define BPF_CORE_READ(src, a, ...)					    \
+	({								    \
+		___type(src, a, ##__VA_ARGS__) __r;			    \
+		BPF_CORE_READ_INTO(&__r, src, a, ##__VA_ARGS__);	    \
+		__r;							    \
+	})
+
+#endif
+
diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/lib/bpf/bpf_endian.h
index fbe28008450f..fbe28008450f 100644
--- a/tools/testing/selftests/bpf/bpf_endian.h
+++ b/tools/lib/bpf/bpf_endian.h
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
new file mode 100644
index 000000000000..2203595f38c3
--- /dev/null
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_HELPERS__
+#define __BPF_HELPERS__
+
+#include "bpf_helper_defs.h"
+
+#define __uint(name, val) int (*name)[val]
+#define __type(name, val) typeof(val) *name
+
+/* Helper macro to print out debug messages */
+#define bpf_printk(fmt, ...)				\
+({							\
+	char ____fmt[] = fmt;				\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			 ##__VA_ARGS__);		\
+})
+
+/*
+ * Helper macro to place programs, maps, license in
+ * different sections in elf_bpf file. Section names
+ * are interpreted by elf_bpf loader
+ */
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+#ifndef __always_inline
+#define __always_inline __attribute__((always_inline))
+#endif
+
+/*
+ * Helper structure used by eBPF C program
+ * to describe BPF map attributes to libbpf loader
+ */
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+};
+
+#endif
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
new file mode 100644
index 000000000000..b0dafe8b4ebc
--- /dev/null
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_TRACING_H__
+#define __BPF_TRACING_H__
+
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+	#define bpf_target_x86
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_s390)
+	#define bpf_target_s390
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm)
+	#define bpf_target_arm
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+	#define bpf_target_arm64
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_mips)
+	#define bpf_target_mips
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+	#define bpf_target_powerpc
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+	#define bpf_target_sparc
+	#define bpf_target_defined
+#else
+	#undef bpf_target_defined
+#endif
+
+/* Fall back to what the compiler says */
+#ifndef bpf_target_defined
+#if defined(__x86_64__)
+	#define bpf_target_x86
+#elif defined(__s390__)
+	#define bpf_target_s390
+#elif defined(__arm__)
+	#define bpf_target_arm
+#elif defined(__aarch64__)
+	#define bpf_target_arm64
+#elif defined(__mips__)
+	#define bpf_target_mips
+#elif defined(__powerpc__)
+	#define bpf_target_powerpc
+#elif defined(__sparc__)
+	#define bpf_target_sparc
+#endif
+#endif
+
+#if defined(bpf_target_x86)
+
+#ifdef __KERNEL__
+#define PT_REGS_PARM1(x) ((x)->di)
+#define PT_REGS_PARM2(x) ((x)->si)
+#define PT_REGS_PARM3(x) ((x)->dx)
+#define PT_REGS_PARM4(x) ((x)->cx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->sp)
+#define PT_REGS_FP(x) ((x)->bp)
+#define PT_REGS_RC(x) ((x)->ax)
+#define PT_REGS_SP(x) ((x)->sp)
+#define PT_REGS_IP(x) ((x)->ip)
+#else
+#ifdef __i386__
+/* i386 kernel is built with -mregparm=3 */
+#define PT_REGS_PARM1(x) ((x)->eax)
+#define PT_REGS_PARM2(x) ((x)->edx)
+#define PT_REGS_PARM3(x) ((x)->ecx)
+#define PT_REGS_PARM4(x) 0
+#define PT_REGS_PARM5(x) 0
+#define PT_REGS_RET(x) ((x)->esp)
+#define PT_REGS_FP(x) ((x)->ebp)
+#define PT_REGS_RC(x) ((x)->eax)
+#define PT_REGS_SP(x) ((x)->esp)
+#define PT_REGS_IP(x) ((x)->eip)
+#else
+#define PT_REGS_PARM1(x) ((x)->rdi)
+#define PT_REGS_PARM2(x) ((x)->rsi)
+#define PT_REGS_PARM3(x) ((x)->rdx)
+#define PT_REGS_PARM4(x) ((x)->rcx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->rsp)
+#define PT_REGS_FP(x) ((x)->rbp)
+#define PT_REGS_RC(x) ((x)->rax)
+#define PT_REGS_SP(x) ((x)->rsp)
+#define PT_REGS_IP(x) ((x)->rip)
+#endif
+#endif
+
+#elif defined(bpf_target_s390)
+
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_S390 const volatile user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
+#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
+#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
+#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
+#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
+#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
+#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
+
+#elif defined(bpf_target_arm)
+
+#define PT_REGS_PARM1(x) ((x)->uregs[0])
+#define PT_REGS_PARM2(x) ((x)->uregs[1])
+#define PT_REGS_PARM3(x) ((x)->uregs[2])
+#define PT_REGS_PARM4(x) ((x)->uregs[3])
+#define PT_REGS_PARM5(x) ((x)->uregs[4])
+#define PT_REGS_RET(x) ((x)->uregs[14])
+#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_RC(x) ((x)->uregs[0])
+#define PT_REGS_SP(x) ((x)->uregs[13])
+#define PT_REGS_IP(x) ((x)->uregs[12])
+
+#elif defined(bpf_target_arm64)
+
+/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_ARM64 const volatile struct user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
+#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
+#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
+#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
+#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
+#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
+#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
+
+#elif defined(bpf_target_mips)
+
+#define PT_REGS_PARM1(x) ((x)->regs[4])
+#define PT_REGS_PARM2(x) ((x)->regs[5])
+#define PT_REGS_PARM3(x) ((x)->regs[6])
+#define PT_REGS_PARM4(x) ((x)->regs[7])
+#define PT_REGS_PARM5(x) ((x)->regs[8])
+#define PT_REGS_RET(x) ((x)->regs[31])
+#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_RC(x) ((x)->regs[1])
+#define PT_REGS_SP(x) ((x)->regs[29])
+#define PT_REGS_IP(x) ((x)->cp0_epc)
+
+#elif defined(bpf_target_powerpc)
+
+#define PT_REGS_PARM1(x) ((x)->gpr[3])
+#define PT_REGS_PARM2(x) ((x)->gpr[4])
+#define PT_REGS_PARM3(x) ((x)->gpr[5])
+#define PT_REGS_PARM4(x) ((x)->gpr[6])
+#define PT_REGS_PARM5(x) ((x)->gpr[7])
+#define PT_REGS_RC(x) ((x)->gpr[3])
+#define PT_REGS_SP(x) ((x)->sp)
+#define PT_REGS_IP(x) ((x)->nip)
+
+#elif defined(bpf_target_sparc)
+
+#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
+#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
+#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
+#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
+#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
+#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+
+/* Should this also be a bpf_target check for the sparc case? */
+#if defined(__arch64__)
+#define PT_REGS_IP(x) ((x)->tpc)
+#else
+#define PT_REGS_IP(x) ((x)->pc)
+#endif
+
+#endif
+
+#if defined(bpf_target_powerpc)
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+#elif defined(bpf_target_sparc)
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+#else
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
+	({ bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
+#define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
+	({ bpf_probe_read(&(ip), sizeof(ip),				    \
+			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+#endif
+
+#endif
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index ede55fec3618..139812b46c7b 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -876,7 +876,6 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 	__u16 vlen = btf_vlen(t);
 
 	packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0;
-	align = packed ? 1 : btf_align_of(d->btf, id);
 
 	btf_dump_printf(d, "%s%s%s {",
 			is_struct ? "struct" : "union",
@@ -906,6 +905,13 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 		btf_dump_printf(d, ";");
 	}
 
+	/* pad at the end, if necessary */
+	if (is_struct) {
+		align = packed ? 1 : btf_align_of(d->btf, id);
+		btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align,
+					  lvl + 1);
+	}
+
 	if (vlen)
 		btf_dump_printf(d, "\n");
 	btf_dump_printf(d, "%s}", pfx(lvl));
@@ -969,6 +975,17 @@ static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id,
 {
 	const char *name = btf_dump_ident_name(d, id);
 
+	/*
+	 * Old GCC versions are emitting invalid typedef for __gnuc_va_list
+	 * pointing to VOID. This generates warnings from btf_dump() and
+	 * results in uncompilable header file, so we are fixing it up here
+	 * with valid typedef into __builtin_va_list.
+	 */
+	if (t->type == 0 && strcmp(name, "__gnuc_va_list") == 0) {
+		btf_dump_printf(d, "typedef __builtin_va_list __gnuc_va_list");
+		return;
+	}
+
 	btf_dump_printf(d, "typedef ");
 	btf_dump_emit_type_decl(d, t->type, name, lvl);
 }
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e0276520171b..a02cdedc4e3f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -33,6 +33,7 @@
 #include <linux/limits.h>
 #include <linux/perf_event.h>
 #include <linux/ring_buffer.h>
+#include <linux/version.h>
 #include <sys/epoll.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
@@ -255,7 +256,7 @@ struct bpf_object {
 	 */
 	struct {
 		int fd;
-		void *obj_buf;
+		const void *obj_buf;
 		size_t obj_buf_sz;
 		Elf *elf;
 		GElf_Ehdr ehdr;
@@ -491,9 +492,21 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 	return 0;
 }
 
+static __u32 get_kernel_version(void)
+{
+	__u32 major, minor, patch;
+	struct utsname info;
+
+	uname(&info);
+	if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
+		return 0;
+	return KERNEL_VERSION(major, minor, patch);
+}
+
 static struct bpf_object *bpf_object__new(const char *path,
-					  void *obj_buf,
-					  size_t obj_buf_sz)
+					  const void *obj_buf,
+					  size_t obj_buf_sz,
+					  const char *obj_name)
 {
 	struct bpf_object *obj;
 	char *end;
@@ -505,11 +518,17 @@ static struct bpf_object *bpf_object__new(const char *path,
 	}
 
 	strcpy(obj->path, path);
-	/* Using basename() GNU version which doesn't modify arg. */
-	strncpy(obj->name, basename((void *)path), sizeof(obj->name) - 1);
-	end = strchr(obj->name, '.');
-	if (end)
-		*end = 0;
+	if (obj_name) {
+		strncpy(obj->name, obj_name, sizeof(obj->name) - 1);
+		obj->name[sizeof(obj->name) - 1] = 0;
+	} else {
+		/* Using basename() GNU version which doesn't modify arg. */
+		strncpy(obj->name, basename((void *)path),
+			sizeof(obj->name) - 1);
+		end = strchr(obj->name, '.');
+		if (end)
+			*end = 0;
+	}
 
 	obj->efile.fd = -1;
 	/*
@@ -526,6 +545,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.rodata_shndx = -1;
 	obj->efile.bss_shndx = -1;
 
+	obj->kern_version = get_kernel_version();
 	obj->loaded = false;
 
 	INIT_LIST_HEAD(&obj->list);
@@ -569,7 +589,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		 * obj_buf should have been validated by
 		 * bpf_object__open_buffer().
 		 */
-		obj->efile.elf = elf_memory(obj->efile.obj_buf,
+		obj->efile.elf = elf_memory((char *)obj->efile.obj_buf,
 					    obj->efile.obj_buf_sz);
 	} else {
 		obj->efile.fd = open(obj->path, O_RDONLY);
@@ -636,21 +656,6 @@ bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
 	return 0;
 }
 
-static int
-bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size)
-{
-	__u32 kver;
-
-	if (size != sizeof(kver)) {
-		pr_warning("invalid kver section in %s\n", obj->path);
-		return -LIBBPF_ERRNO__FORMAT;
-	}
-	memcpy(&kver, data, sizeof(kver));
-	obj->kern_version = kver;
-	pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version);
-	return 0;
-}
-
 static int compare_bpf_map(const void *_a, const void *_b)
 {
 	const struct bpf_map *a = _a;
@@ -1568,11 +1573,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 			if (err)
 				return err;
 		} else if (strcmp(name, "version") == 0) {
-			err = bpf_object__init_kversion(obj,
-							data->d_buf,
-							data->d_size);
-			if (err)
-				return err;
+			/* skip, we don't need it anymore */
 		} else if (strcmp(name, "maps") == 0) {
 			obj->efile.maps_shndx = idx;
 		} else if (strcmp(name, MAPS_ELF_SEC) == 0) {
@@ -3551,54 +3552,9 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 	return 0;
 }
 
-static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
-{
-	switch (type) {
-	case BPF_PROG_TYPE_SOCKET_FILTER:
-	case BPF_PROG_TYPE_SCHED_CLS:
-	case BPF_PROG_TYPE_SCHED_ACT:
-	case BPF_PROG_TYPE_XDP:
-	case BPF_PROG_TYPE_CGROUP_SKB:
-	case BPF_PROG_TYPE_CGROUP_SOCK:
-	case BPF_PROG_TYPE_LWT_IN:
-	case BPF_PROG_TYPE_LWT_OUT:
-	case BPF_PROG_TYPE_LWT_XMIT:
-	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
-	case BPF_PROG_TYPE_SOCK_OPS:
-	case BPF_PROG_TYPE_SK_SKB:
-	case BPF_PROG_TYPE_CGROUP_DEVICE:
-	case BPF_PROG_TYPE_SK_MSG:
-	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
-	case BPF_PROG_TYPE_LIRC_MODE2:
-	case BPF_PROG_TYPE_SK_REUSEPORT:
-	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-	case BPF_PROG_TYPE_UNSPEC:
-	case BPF_PROG_TYPE_TRACEPOINT:
-	case BPF_PROG_TYPE_RAW_TRACEPOINT:
-	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
-	case BPF_PROG_TYPE_PERF_EVENT:
-	case BPF_PROG_TYPE_CGROUP_SYSCTL:
-	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
-		return false;
-	case BPF_PROG_TYPE_KPROBE:
-	default:
-		return true;
-	}
-}
-
-static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
-{
-	if (needs_kver && obj->kern_version == 0) {
-		pr_warning("%s doesn't provide kernel version\n",
-			   obj->path);
-		return -LIBBPF_ERRNO__KVERSION;
-	}
-	return 0;
-}
-
 static struct bpf_object *
-__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
-		   bool needs_kver, int flags)
+__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
+		   const char *obj_name, int flags)
 {
 	struct bpf_object *obj;
 	int err;
@@ -3608,7 +3564,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
 		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
 	}
 
-	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
+	obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name);
 	if (IS_ERR(obj))
 		return obj;
 
@@ -3617,7 +3573,6 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
 	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
 	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
 	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
-	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
 
 	bpf_object__elf_finish(obj);
 	return obj;
@@ -3626,8 +3581,8 @@ out:
 	return ERR_PTR(err);
 }
 
-struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
-					    int flags)
+static struct bpf_object *
+__bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags)
 {
 	/* param validation */
 	if (!attr->file)
@@ -3635,9 +3590,7 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
 
 	pr_debug("loading %s\n", attr->file);
 
-	return __bpf_object__open(attr->file, NULL, 0,
-				  bpf_prog_type__needs_kver(attr->prog_type),
-				  flags);
+	return __bpf_object__open(attr->file, NULL, 0, NULL, flags);
 }
 
 struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
@@ -3655,25 +3608,67 @@ struct bpf_object *bpf_object__open(const char *path)
 	return bpf_object__open_xattr(&attr);
 }
 
-struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-					   size_t obj_buf_sz,
-					   const char *name)
+struct bpf_object *
+bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts)
+{
+	const char *obj_name;
+	bool relaxed_maps;
+
+	if (!OPTS_VALID(opts, bpf_object_open_opts))
+		return ERR_PTR(-EINVAL);
+	if (!path)
+		return ERR_PTR(-EINVAL);
+
+	pr_debug("loading %s\n", path);
+
+	obj_name = OPTS_GET(opts, object_name, path);
+	relaxed_maps = OPTS_GET(opts, relaxed_maps, false);
+	return __bpf_object__open(path, NULL, 0, obj_name,
+				  relaxed_maps ? MAPS_RELAX_COMPAT : 0);
+}
+
+struct bpf_object *
+bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
+		     struct bpf_object_open_opts *opts)
 {
 	char tmp_name[64];
+	const char *obj_name;
+	bool relaxed_maps;
 
-	/* param validation */
-	if (!obj_buf || obj_buf_sz <= 0)
-		return NULL;
+	if (!OPTS_VALID(opts, bpf_object_open_opts))
+		return ERR_PTR(-EINVAL);
+	if (!obj_buf || obj_buf_sz == 0)
+		return ERR_PTR(-EINVAL);
 
-	if (!name) {
+	obj_name = OPTS_GET(opts, object_name, NULL);
+	if (!obj_name) {
 		snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
 			 (unsigned long)obj_buf,
 			 (unsigned long)obj_buf_sz);
-		name = tmp_name;
+		obj_name = tmp_name;
 	}
-	pr_debug("loading object '%s' from buffer\n", name);
+	pr_debug("loading object '%s' from buffer\n", obj_name);
+
+	relaxed_maps = OPTS_GET(opts, relaxed_maps, false);
+	return __bpf_object__open(obj_name, obj_buf, obj_buf_sz, obj_name,
+				  relaxed_maps ? MAPS_RELAX_COMPAT : 0);
+}
+
+struct bpf_object *
+bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
+			const char *name)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts,
+		.object_name = name,
+		/* wrong default, but backwards-compatible */
+		.relaxed_maps = true,
+	);
+
+	/* returning NULL is wrong, but backwards-compatible */
+	if (!obj_buf || obj_buf_sz == 0)
+		return NULL;
 
-	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
+	return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
 }
 
 int bpf_object__unload(struct bpf_object *obj)
@@ -4236,7 +4231,7 @@ bpf_object__next(struct bpf_object *prev)
 
 const char *bpf_object__name(const struct bpf_object *obj)
 {
-	return obj ? obj->path : ERR_PTR(-EINVAL);
+	return obj ? obj->name : ERR_PTR(-EINVAL);
 }
 
 unsigned int bpf_object__kversion(const struct bpf_object *obj)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e8f70977d137..667e6853e51f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -67,14 +67,52 @@ struct bpf_object_open_attr {
 	enum bpf_prog_type prog_type;
 };
 
+/* Helper macro to declare and initialize libbpf options struct
+ *
+ * This dance with uninitialized declaration, followed by memset to zero,
+ * followed by assignment using compound literal syntax is done to preserve
+ * ability to use a nice struct field initialization syntax and **hopefully**
+ * have all the padding bytes initialized to zero. It's not guaranteed though,
+ * when copying literal, that compiler won't copy garbage in literal's padding
+ * bytes, but that's the best way I've found and it seems to work in practice.
+ */
+#define LIBBPF_OPTS(TYPE, NAME, ...)					    \
+	struct TYPE NAME;						    \
+	memset(&NAME, 0, sizeof(struct TYPE));				    \
+	NAME = (struct TYPE) {						    \
+		.sz = sizeof(struct TYPE),				    \
+		__VA_ARGS__						    \
+	}
+
+struct bpf_object_open_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+	/* object name override, if provided:
+	 * - for object open from file, this will override setting object
+	 *   name from file path's base name;
+	 * - for object open from memory buffer, this will specify an object
+	 *   name and will override default "<addr>-<buf-size>" name;
+	 */
+	const char *object_name;
+	/* parse map definitions non-strictly, allowing extra attributes/data */
+	bool relaxed_maps;
+};
+#define bpf_object_open_opts__last_field relaxed_maps
+
 LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
 LIBBPF_API struct bpf_object *
+bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts);
+LIBBPF_API struct bpf_object *
+bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
+		     struct bpf_object_open_opts *opts);
+
+/* deprecated bpf_object__open variants */
+LIBBPF_API struct bpf_object *
+bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
+			const char *name);
+LIBBPF_API struct bpf_object *
 bpf_object__open_xattr(struct bpf_object_open_attr *attr);
-struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
-					    int flags);
-LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-						      size_t obj_buf_sz,
-						      const char *name);
+
 int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 			     __u32 *size);
 int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index d04c7cb623ed..4d241fd92dd4 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -190,3 +190,9 @@ LIBBPF_0.0.5 {
 	global:
 		bpf_btf_get_next_id;
 } LIBBPF_0.0.4;
+
+LIBBPF_0.0.6 {
+	global:
+		bpf_object__open_file;
+		bpf_object__open_mem;
+} LIBBPF_0.0.5;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 2e83a34f8c79..f51444fc7eb7 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -47,6 +47,38 @@ do {				\
 #define pr_info(fmt, ...)	__pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
 #define pr_debug(fmt, ...)	__pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
 
+static inline bool libbpf_validate_opts(const char *opts,
+					size_t opts_sz, size_t user_sz,
+					const char *type_name)
+{
+	if (user_sz < sizeof(size_t)) {
+		pr_warning("%s size (%zu) is too small\n", type_name, user_sz);
+		return false;
+	}
+	if (user_sz > opts_sz) {
+		size_t i;
+
+		for (i = opts_sz; i < user_sz; i++) {
+			if (opts[i]) {
+				pr_warning("%s has non-zero extra bytes",
+					   type_name);
+				return false;
+			}
+		}
+	}
+	return true;
+}
+
+#define OPTS_VALID(opts, type)						      \
+	(!(opts) || libbpf_validate_opts((const char *)opts,		      \
+					 offsetofend(struct type,	      \
+						     type##__last_field),     \
+					 (opts)->sz, #type))
+#define OPTS_HAS(opts, field) \
+	((opts) && opts->sz >= offsetofend(typeof(*(opts)), field))
+#define OPTS_GET(opts, field, fallback_value) \
+	(OPTS_HAS(opts, field) ? (opts)->field : fallback_value)
+
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
 
diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.c
index fc134873bb6d..f0eb2727b766 100644
--- a/tools/lib/bpf/test_libbpf.cpp
+++ b/tools/lib/bpf/test_libbpf.c
@@ -7,12 +7,14 @@
 
 int main(int argc, char *argv[])
 {
-    /* libbpf.h */
-    libbpf_set_print(NULL);
+	/* libbpf.h */
+	libbpf_set_print(NULL);
 
-    /* bpf.h */
-    bpf_prog_get_fd_by_id(0);
+	/* bpf.h */
+	bpf_prog_get_fd_by_id(0);
 
-    /* btf.h */
-    btf__new(NULL, 0);
+	/* btf.h */
+	btf__new(NULL, 0);
+
+	return 0;
 }
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 24fa313524fb..b0f532544c91 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -163,6 +163,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	umem->umem_area = umem_area;
 	xsk_set_umem_config(&umem->config, usr_config);
 
+	memset(&mr, 0, sizeof(mr));
 	mr.addr = (uintptr_t)umem_area;
 	mr.len = size;
 	mr.chunk_size = umem->config.frame_size;
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6889c19a628c..00d05c5e2d57 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -15,8 +15,6 @@ endif
 CLANG		?= clang
 LLC		?= llc
 LLVM_OBJCOPY	?= llvm-objcopy
-LLVM_READELF	?= llvm-readelf
-BTF_PAHOLE	?= pahole
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 CFLAGS += -g -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include \
 	  -Dbpf_prog_load=bpf_prog_test_load \
@@ -29,7 +27,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage test_select_reuseport test_section_names \
 	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
-	test_btf_dump test_cgroup_attach xdping
+	test_cgroup_attach xdping
 
 BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
 TEST_GEN_FILES = $(BPF_OBJ_FILES)
@@ -126,16 +124,6 @@ force:
 $(BPFOBJ): force
 	$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
 
-PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
-
-# Let newer LLVM versions transparently probe the kernel for availability
-# of full BPF instruction set.
-ifeq ($(PROBE),)
-  CPU ?= probe
-else
-  CPU ?= generic
-endif
-
 # Get Clang's default includes on this system, as opposed to those seen by
 # '-target bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
@@ -147,8 +135,9 @@ $(shell $(1) -v -E - </dev/null 2>&1 \
 	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
 endef
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
-BPF_CFLAGS = -I. -I./include/uapi -I../../../include/uapi \
-	     -I$(OUTPUT)/../usr/include -D__TARGET_ARCH_$(SRCARCH)
+BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) 				\
+	     -I. -I./include/uapi -I../../../include/uapi 		\
+	     -I$(BPFDIR) -I$(OUTPUT)/../usr/include
 
 CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 	       -Wno-compare-distinct-pointer-types
@@ -162,28 +151,6 @@ $(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
 $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
 $(OUTPUT)/test_progs.o: flow_dissector_load.h
 
-BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
-BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
-BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
-BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
-			  $(CLANG) -target bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
-			  $(LLVM_READELF) -S ./llvm_btf_verify.o | grep BTF; \
-			  /bin/rm -f ./llvm_btf_verify.o)
-
-ifneq ($(BTF_LLVM_PROBE),)
-	BPF_CFLAGS += -g
-else
-ifneq ($(BTF_LLC_PROBE),)
-ifneq ($(BTF_PAHOLE_PROBE),)
-ifneq ($(BTF_OBJCOPY_PROBE),)
-	BPF_CFLAGS += -g
-	LLC_FLAGS += -mattr=dwarfris
-	DWARF2BTF = y
-endif
-endif
-endif
-endif
-
 TEST_PROGS_CFLAGS := -I. -I$(OUTPUT)
 TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
 TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier
@@ -212,11 +179,8 @@ $(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR)/test_progs_32 \
 					| $(ALU32_BUILD_DIR)
 	($(CLANG) $(BPF_CFLAGS) $(CLANG_CFLAGS) -O2 -target bpf -emit-llvm \
 		-c $< -o - || echo "clang failed") | \
-	$(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \
+	$(LLC) -march=bpf -mcpu=probe -mattr=+alu32 $(LLC_FLAGS) \
 		-filetype=obj -o $@
-ifeq ($(DWARF2BTF),y)
-	$(BTF_PAHOLE) -J $@
-endif
 endif
 
 ifneq ($(BPF_GCC),)
@@ -251,18 +215,13 @@ endif
 $(OUTPUT)/test_xdp.o: progs/test_xdp.c
 	($(CLANG) $(BPF_CFLAGS) $(CLANG_CFLAGS) -O2 -emit-llvm -c $< -o - || \
 		echo "clang failed") | \
-	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
-ifeq ($(DWARF2BTF),y)
-	$(BTF_PAHOLE) -J $@
-endif
+	$(LLC) -march=bpf -mcpu=probe $(LLC_FLAGS) -filetype=obj -o $@
 
-$(OUTPUT)/%.o: progs/%.c
+# libbpf has to be built before BPF programs due to bpf_helper_defs.h
+$(OUTPUT)/%.o: progs/%.c | $(BPFOBJ)
 	($(CLANG) $(BPF_CFLAGS) $(CLANG_CFLAGS) -O2 -target bpf -emit-llvm \
 		-c $< -o - || echo "clang failed") | \
-	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
-ifeq ($(DWARF2BTF),y)
-	$(BTF_PAHOLE) -J $@
-endif
+	$(LLC) -march=bpf -mcpu=probe $(LLC_FLAGS) -filetype=obj -o $@
 
 PROG_TESTS_DIR = $(OUTPUT)/prog_tests
 $(PROG_TESTS_DIR):
@@ -271,7 +230,7 @@ PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h
 PROG_TESTS_FILES := $(wildcard prog_tests/*.c)
 test_progs.c: $(PROG_TESTS_H)
 $(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
-$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_FILES) | $(PROG_TESTS_H)
+$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_FILES) | $(OUTPUT)/test_attach_probe.o $(PROG_TESTS_H)
 $(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR)
 	$(shell ( cd prog_tests/; \
 		  echo '/* Generated header, do not edit */'; \
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
deleted file mode 100644
index 54a50699bbfd..000000000000
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ /dev/null
@@ -1,535 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-#ifndef __BPF_HELPERS__
-#define __BPF_HELPERS__
-
-#define __uint(name, val) int (*name)[val]
-#define __type(name, val) val *name
-
-/* helper macro to print out debug messages */
-#define bpf_printk(fmt, ...)				\
-({							\
-	char ____fmt[] = fmt;				\
-	bpf_trace_printk(____fmt, sizeof(____fmt),	\
-			 ##__VA_ARGS__);		\
-})
-
-#ifdef __clang__
-
-/* helper macro to place programs, maps, license in
- * different sections in elf_bpf file. Section names
- * are interpreted by elf_bpf loader
- */
-#define SEC(NAME) __attribute__((section(NAME), used))
-
-/* helper functions called from eBPF programs written in C */
-static void *(*bpf_map_lookup_elem)(void *map, const void *key) =
-	(void *) BPF_FUNC_map_lookup_elem;
-static int (*bpf_map_update_elem)(void *map, const void *key, const void *value,
-				  unsigned long long flags) =
-	(void *) BPF_FUNC_map_update_elem;
-static int (*bpf_map_delete_elem)(void *map, const void *key) =
-	(void *) BPF_FUNC_map_delete_elem;
-static int (*bpf_map_push_elem)(void *map, const void *value,
-				unsigned long long flags) =
-	(void *) BPF_FUNC_map_push_elem;
-static int (*bpf_map_pop_elem)(void *map, void *value) =
-	(void *) BPF_FUNC_map_pop_elem;
-static int (*bpf_map_peek_elem)(void *map, void *value) =
-	(void *) BPF_FUNC_map_peek_elem;
-static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
-	(void *) BPF_FUNC_probe_read;
-static unsigned long long (*bpf_ktime_get_ns)(void) =
-	(void *) BPF_FUNC_ktime_get_ns;
-static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
-	(void *) BPF_FUNC_trace_printk;
-static void (*bpf_tail_call)(void *ctx, void *map, int index) =
-	(void *) BPF_FUNC_tail_call;
-static unsigned long long (*bpf_get_smp_processor_id)(void) =
-	(void *) BPF_FUNC_get_smp_processor_id;
-static unsigned long long (*bpf_get_current_pid_tgid)(void) =
-	(void *) BPF_FUNC_get_current_pid_tgid;
-static unsigned long long (*bpf_get_current_uid_gid)(void) =
-	(void *) BPF_FUNC_get_current_uid_gid;
-static int (*bpf_get_current_comm)(void *buf, int buf_size) =
-	(void *) BPF_FUNC_get_current_comm;
-static unsigned long long (*bpf_perf_event_read)(void *map,
-						 unsigned long long flags) =
-	(void *) BPF_FUNC_perf_event_read;
-static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) =
-	(void *) BPF_FUNC_clone_redirect;
-static int (*bpf_redirect)(int ifindex, int flags) =
-	(void *) BPF_FUNC_redirect;
-static int (*bpf_redirect_map)(void *map, int key, int flags) =
-	(void *) BPF_FUNC_redirect_map;
-static int (*bpf_perf_event_output)(void *ctx, void *map,
-				    unsigned long long flags, void *data,
-				    int size) =
-	(void *) BPF_FUNC_perf_event_output;
-static int (*bpf_get_stackid)(void *ctx, void *map, int flags) =
-	(void *) BPF_FUNC_get_stackid;
-static int (*bpf_probe_write_user)(void *dst, const void *src, int size) =
-	(void *) BPF_FUNC_probe_write_user;
-static int (*bpf_current_task_under_cgroup)(void *map, int index) =
-	(void *) BPF_FUNC_current_task_under_cgroup;
-static int (*bpf_skb_get_tunnel_key)(void *ctx, void *key, int size, int flags) =
-	(void *) BPF_FUNC_skb_get_tunnel_key;
-static int (*bpf_skb_set_tunnel_key)(void *ctx, void *key, int size, int flags) =
-	(void *) BPF_FUNC_skb_set_tunnel_key;
-static int (*bpf_skb_get_tunnel_opt)(void *ctx, void *md, int size) =
-	(void *) BPF_FUNC_skb_get_tunnel_opt;
-static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
-	(void *) BPF_FUNC_skb_set_tunnel_opt;
-static unsigned long long (*bpf_get_prandom_u32)(void) =
-	(void *) BPF_FUNC_get_prandom_u32;
-static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
-	(void *) BPF_FUNC_xdp_adjust_head;
-static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) =
-	(void *) BPF_FUNC_xdp_adjust_meta;
-static int (*bpf_get_socket_cookie)(void *ctx) =
-	(void *) BPF_FUNC_get_socket_cookie;
-static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
-			     int optlen) =
-	(void *) BPF_FUNC_setsockopt;
-static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval,
-			     int optlen) =
-	(void *) BPF_FUNC_getsockopt;
-static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) =
-	(void *) BPF_FUNC_sock_ops_cb_flags_set;
-static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
-	(void *) BPF_FUNC_sk_redirect_map;
-static int (*bpf_sk_redirect_hash)(void *ctx, void *map, void *key, int flags) =
-	(void *) BPF_FUNC_sk_redirect_hash;
-static int (*bpf_sock_map_update)(void *map, void *key, void *value,
-				  unsigned long long flags) =
-	(void *) BPF_FUNC_sock_map_update;
-static int (*bpf_sock_hash_update)(void *map, void *key, void *value,
-				   unsigned long long flags) =
-	(void *) BPF_FUNC_sock_hash_update;
-static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
-					void *buf, unsigned int buf_size) =
-	(void *) BPF_FUNC_perf_event_read_value;
-static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
-				       unsigned int buf_size) =
-	(void *) BPF_FUNC_perf_prog_read_value;
-static int (*bpf_override_return)(void *ctx, unsigned long rc) =
-	(void *) BPF_FUNC_override_return;
-static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) =
-	(void *) BPF_FUNC_msg_redirect_map;
-static int (*bpf_msg_redirect_hash)(void *ctx,
-				    void *map, void *key, int flags) =
-	(void *) BPF_FUNC_msg_redirect_hash;
-static int (*bpf_msg_apply_bytes)(void *ctx, int len) =
-	(void *) BPF_FUNC_msg_apply_bytes;
-static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
-	(void *) BPF_FUNC_msg_cork_bytes;
-static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
-	(void *) BPF_FUNC_msg_pull_data;
-static int (*bpf_msg_push_data)(void *ctx, int start, int end, int flags) =
-	(void *) BPF_FUNC_msg_push_data;
-static int (*bpf_msg_pop_data)(void *ctx, int start, int cut, int flags) =
-	(void *) BPF_FUNC_msg_pop_data;
-static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
-	(void *) BPF_FUNC_bind;
-static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
-	(void *) BPF_FUNC_xdp_adjust_tail;
-static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
-				     int size, int flags) =
-	(void *) BPF_FUNC_skb_get_xfrm_state;
-static int (*bpf_sk_select_reuseport)(void *ctx, void *map, void *key, __u32 flags) =
-	(void *) BPF_FUNC_sk_select_reuseport;
-static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) =
-	(void *) BPF_FUNC_get_stack;
-static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
-			     int plen, __u32 flags) =
-	(void *) BPF_FUNC_fib_lookup;
-static int (*bpf_lwt_push_encap)(void *ctx, unsigned int type, void *hdr,
-				 unsigned int len) =
-	(void *) BPF_FUNC_lwt_push_encap;
-static int (*bpf_lwt_seg6_store_bytes)(void *ctx, unsigned int offset,
-				       void *from, unsigned int len) =
-	(void *) BPF_FUNC_lwt_seg6_store_bytes;
-static int (*bpf_lwt_seg6_action)(void *ctx, unsigned int action, void *param,
-				  unsigned int param_len) =
-	(void *) BPF_FUNC_lwt_seg6_action;
-static int (*bpf_lwt_seg6_adjust_srh)(void *ctx, unsigned int offset,
-				      unsigned int len) =
-	(void *) BPF_FUNC_lwt_seg6_adjust_srh;
-static int (*bpf_rc_repeat)(void *ctx) =
-	(void *) BPF_FUNC_rc_repeat;
-static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol,
-			     unsigned long long scancode, unsigned int toggle) =
-	(void *) BPF_FUNC_rc_keydown;
-static unsigned long long (*bpf_get_current_cgroup_id)(void) =
-	(void *) BPF_FUNC_get_current_cgroup_id;
-static void *(*bpf_get_local_storage)(void *map, unsigned long long flags) =
-	(void *) BPF_FUNC_get_local_storage;
-static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
-	(void *) BPF_FUNC_skb_cgroup_id;
-static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
-	(void *) BPF_FUNC_skb_ancestor_cgroup_id;
-static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx,
-					     struct bpf_sock_tuple *tuple,
-					     int size, unsigned long long netns_id,
-					     unsigned long long flags) =
-	(void *) BPF_FUNC_sk_lookup_tcp;
-static struct bpf_sock *(*bpf_skc_lookup_tcp)(void *ctx,
-					     struct bpf_sock_tuple *tuple,
-					     int size, unsigned long long netns_id,
-					     unsigned long long flags) =
-	(void *) BPF_FUNC_skc_lookup_tcp;
-static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
-					     struct bpf_sock_tuple *tuple,
-					     int size, unsigned long long netns_id,
-					     unsigned long long flags) =
-	(void *) BPF_FUNC_sk_lookup_udp;
-static int (*bpf_sk_release)(struct bpf_sock *sk) =
-	(void *) BPF_FUNC_sk_release;
-static int (*bpf_skb_vlan_push)(void *ctx, __be16 vlan_proto, __u16 vlan_tci) =
-	(void *) BPF_FUNC_skb_vlan_push;
-static int (*bpf_skb_vlan_pop)(void *ctx) =
-	(void *) BPF_FUNC_skb_vlan_pop;
-static int (*bpf_rc_pointer_rel)(void *ctx, int rel_x, int rel_y) =
-	(void *) BPF_FUNC_rc_pointer_rel;
-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;
-static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) =
-	(void *) BPF_FUNC_get_listener_sock;
-static int (*bpf_skb_ecn_set_ce)(void *ctx) =
-	(void *) BPF_FUNC_skb_ecn_set_ce;
-static int (*bpf_tcp_check_syncookie)(struct bpf_sock *sk,
-	    void *ip, int ip_len, void *tcp, int tcp_len) =
-	(void *) BPF_FUNC_tcp_check_syncookie;
-static int (*bpf_sysctl_get_name)(void *ctx, char *buf,
-				  unsigned long long buf_len,
-				  unsigned long long flags) =
-	(void *) BPF_FUNC_sysctl_get_name;
-static int (*bpf_sysctl_get_current_value)(void *ctx, char *buf,
-					   unsigned long long buf_len) =
-	(void *) BPF_FUNC_sysctl_get_current_value;
-static int (*bpf_sysctl_get_new_value)(void *ctx, char *buf,
-				       unsigned long long buf_len) =
-	(void *) BPF_FUNC_sysctl_get_new_value;
-static int (*bpf_sysctl_set_new_value)(void *ctx, const char *buf,
-				       unsigned long long buf_len) =
-	(void *) BPF_FUNC_sysctl_set_new_value;
-static int (*bpf_strtol)(const char *buf, unsigned long long buf_len,
-			 unsigned long long flags, long *res) =
-	(void *) BPF_FUNC_strtol;
-static int (*bpf_strtoul)(const char *buf, unsigned long long buf_len,
-			  unsigned long long flags, unsigned long *res) =
-	(void *) BPF_FUNC_strtoul;
-static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk,
-				   void *value, __u64 flags) =
-	(void *) BPF_FUNC_sk_storage_get;
-static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) =
-	(void *)BPF_FUNC_sk_storage_delete;
-static int (*bpf_send_signal)(unsigned sig) = (void *)BPF_FUNC_send_signal;
-static long long (*bpf_tcp_gen_syncookie)(struct bpf_sock *sk, void *ip,
-					  int ip_len, void *tcp, int tcp_len) =
-	(void *) BPF_FUNC_tcp_gen_syncookie;
-
-/* llvm builtin functions that eBPF C program may use to
- * emit BPF_LD_ABS and BPF_LD_IND instructions
- */
-struct sk_buff;
-unsigned long long load_byte(void *skb,
-			     unsigned long long off) asm("llvm.bpf.load.byte");
-unsigned long long load_half(void *skb,
-			     unsigned long long off) asm("llvm.bpf.load.half");
-unsigned long long load_word(void *skb,
-			     unsigned long long off) asm("llvm.bpf.load.word");
-
-/* a helper structure used by eBPF C program
- * to describe map attributes to elf_bpf loader
- */
-struct bpf_map_def {
-	unsigned int type;
-	unsigned int key_size;
-	unsigned int value_size;
-	unsigned int max_entries;
-	unsigned int map_flags;
-	unsigned int inner_map_idx;
-	unsigned int numa_node;
-};
-
-#else
-
-#include <bpf-helpers.h>
-
-#endif
-
-#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val)		\
-	struct ____btf_map_##name {				\
-		type_key key;					\
-		type_val value;					\
-	};							\
-	struct ____btf_map_##name				\
-	__attribute__ ((section(".maps." #name), used))		\
-		____btf_map_##name = { }
-
-static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
-	(void *) BPF_FUNC_skb_load_bytes;
-static int (*bpf_skb_load_bytes_relative)(void *ctx, int off, void *to, int len, __u32 start_header) =
-	(void *) BPF_FUNC_skb_load_bytes_relative;
-static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
-	(void *) BPF_FUNC_skb_store_bytes;
-static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
-	(void *) BPF_FUNC_l3_csum_replace;
-static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
-	(void *) BPF_FUNC_l4_csum_replace;
-static int (*bpf_csum_diff)(void *from, int from_size, void *to, int to_size, int seed) =
-	(void *) BPF_FUNC_csum_diff;
-static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
-	(void *) BPF_FUNC_skb_under_cgroup;
-static int (*bpf_skb_change_head)(void *, int len, int flags) =
-	(void *) BPF_FUNC_skb_change_head;
-static int (*bpf_skb_pull_data)(void *, int len) =
-	(void *) BPF_FUNC_skb_pull_data;
-static unsigned int (*bpf_get_cgroup_classid)(void *ctx) =
-	(void *) BPF_FUNC_get_cgroup_classid;
-static unsigned int (*bpf_get_route_realm)(void *ctx) =
-	(void *) BPF_FUNC_get_route_realm;
-static int (*bpf_skb_change_proto)(void *ctx, __be16 proto, __u64 flags) =
-	(void *) BPF_FUNC_skb_change_proto;
-static int (*bpf_skb_change_type)(void *ctx, __u32 type) =
-	(void *) BPF_FUNC_skb_change_type;
-static unsigned int (*bpf_get_hash_recalc)(void *ctx) =
-	(void *) BPF_FUNC_get_hash_recalc;
-static unsigned long long (*bpf_get_current_task)(void) =
-	(void *) BPF_FUNC_get_current_task;
-static int (*bpf_skb_change_tail)(void *ctx, __u32 len, __u64 flags) =
-	(void *) BPF_FUNC_skb_change_tail;
-static long long (*bpf_csum_update)(void *ctx, __u32 csum) =
-	(void *) BPF_FUNC_csum_update;
-static void (*bpf_set_hash_invalid)(void *ctx) =
-	(void *) BPF_FUNC_set_hash_invalid;
-static int (*bpf_get_numa_node_id)(void) =
-	(void *) BPF_FUNC_get_numa_node_id;
-static int (*bpf_probe_read_str)(void *ctx, __u32 size,
-				 const void *unsafe_ptr) =
-	(void *) BPF_FUNC_probe_read_str;
-static unsigned int (*bpf_get_socket_uid)(void *ctx) =
-	(void *) BPF_FUNC_get_socket_uid;
-static unsigned int (*bpf_set_hash)(void *ctx, __u32 hash) =
-	(void *) BPF_FUNC_set_hash;
-static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
-				  unsigned long long flags) =
-	(void *) BPF_FUNC_skb_adjust_room;
-
-/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
-#if defined(__TARGET_ARCH_x86)
-	#define bpf_target_x86
-	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_s390)
-	#define bpf_target_s390
-	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_arm)
-	#define bpf_target_arm
-	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_arm64)
-	#define bpf_target_arm64
-	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_mips)
-	#define bpf_target_mips
-	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_powerpc)
-	#define bpf_target_powerpc
-	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_sparc)
-	#define bpf_target_sparc
-	#define bpf_target_defined
-#else
-	#undef bpf_target_defined
-#endif
-
-/* Fall back to what the compiler says */
-#ifndef bpf_target_defined
-#if defined(__x86_64__)
-	#define bpf_target_x86
-#elif defined(__s390__)
-	#define bpf_target_s390
-#elif defined(__arm__)
-	#define bpf_target_arm
-#elif defined(__aarch64__)
-	#define bpf_target_arm64
-#elif defined(__mips__)
-	#define bpf_target_mips
-#elif defined(__powerpc__)
-	#define bpf_target_powerpc
-#elif defined(__sparc__)
-	#define bpf_target_sparc
-#endif
-#endif
-
-#if defined(bpf_target_x86)
-
-#ifdef __KERNEL__
-#define PT_REGS_PARM1(x) ((x)->di)
-#define PT_REGS_PARM2(x) ((x)->si)
-#define PT_REGS_PARM3(x) ((x)->dx)
-#define PT_REGS_PARM4(x) ((x)->cx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->sp)
-#define PT_REGS_FP(x) ((x)->bp)
-#define PT_REGS_RC(x) ((x)->ax)
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->ip)
-#else
-#ifdef __i386__
-/* i386 kernel is built with -mregparm=3 */
-#define PT_REGS_PARM1(x) ((x)->eax)
-#define PT_REGS_PARM2(x) ((x)->edx)
-#define PT_REGS_PARM3(x) ((x)->ecx)
-#define PT_REGS_PARM4(x) 0
-#define PT_REGS_PARM5(x) 0
-#define PT_REGS_RET(x) ((x)->esp)
-#define PT_REGS_FP(x) ((x)->ebp)
-#define PT_REGS_RC(x) ((x)->eax)
-#define PT_REGS_SP(x) ((x)->esp)
-#define PT_REGS_IP(x) ((x)->eip)
-#else
-#define PT_REGS_PARM1(x) ((x)->rdi)
-#define PT_REGS_PARM2(x) ((x)->rsi)
-#define PT_REGS_PARM3(x) ((x)->rdx)
-#define PT_REGS_PARM4(x) ((x)->rcx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->rsp)
-#define PT_REGS_FP(x) ((x)->rbp)
-#define PT_REGS_RC(x) ((x)->rax)
-#define PT_REGS_SP(x) ((x)->rsp)
-#define PT_REGS_IP(x) ((x)->rip)
-#endif
-#endif
-
-#elif defined(bpf_target_s390)
-
-/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_S390 const volatile user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
-#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
-#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
-#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
-#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
-#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
-#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
-
-#elif defined(bpf_target_arm)
-
-#define PT_REGS_PARM1(x) ((x)->uregs[0])
-#define PT_REGS_PARM2(x) ((x)->uregs[1])
-#define PT_REGS_PARM3(x) ((x)->uregs[2])
-#define PT_REGS_PARM4(x) ((x)->uregs[3])
-#define PT_REGS_PARM5(x) ((x)->uregs[4])
-#define PT_REGS_RET(x) ((x)->uregs[14])
-#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->uregs[0])
-#define PT_REGS_SP(x) ((x)->uregs[13])
-#define PT_REGS_IP(x) ((x)->uregs[12])
-
-#elif defined(bpf_target_arm64)
-
-/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_ARM64 const volatile struct user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
-#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
-#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
-#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
-#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
-#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
-
-#elif defined(bpf_target_mips)
-
-#define PT_REGS_PARM1(x) ((x)->regs[4])
-#define PT_REGS_PARM2(x) ((x)->regs[5])
-#define PT_REGS_PARM3(x) ((x)->regs[6])
-#define PT_REGS_PARM4(x) ((x)->regs[7])
-#define PT_REGS_PARM5(x) ((x)->regs[8])
-#define PT_REGS_RET(x) ((x)->regs[31])
-#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[1])
-#define PT_REGS_SP(x) ((x)->regs[29])
-#define PT_REGS_IP(x) ((x)->cp0_epc)
-
-#elif defined(bpf_target_powerpc)
-
-#define PT_REGS_PARM1(x) ((x)->gpr[3])
-#define PT_REGS_PARM2(x) ((x)->gpr[4])
-#define PT_REGS_PARM3(x) ((x)->gpr[5])
-#define PT_REGS_PARM4(x) ((x)->gpr[6])
-#define PT_REGS_PARM5(x) ((x)->gpr[7])
-#define PT_REGS_RC(x) ((x)->gpr[3])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->nip)
-
-#elif defined(bpf_target_sparc)
-
-#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
-#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
-#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
-#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
-#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
-#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
-
-/* Should this also be a bpf_target check for the sparc case? */
-#if defined(__arch64__)
-#define PT_REGS_IP(x) ((x)->tpc)
-#else
-#define PT_REGS_IP(x) ((x)->pc)
-#endif
-
-#endif
-
-#if defined(bpf_target_powerpc)
-#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
-#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif defined(bpf_target_sparc)
-#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
-#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#else
-#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({				\
-		bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
-#define BPF_KRETPROBE_READ_RET_IP(ip, ctx)	({				\
-		bpf_probe_read(&(ip), sizeof(ip),				\
-				(void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
-#endif
-
-/*
- * BPF_CORE_READ abstracts away bpf_probe_read() call and captures offset
- * relocation for source address using __builtin_preserve_access_index()
- * built-in, provided by Clang.
- *
- * __builtin_preserve_access_index() takes as an argument an expression of
- * taking an address of a field within struct/union. It makes compiler emit
- * a relocation, which records BTF type ID describing root struct/union and an
- * accessor string which describes exact embedded field that was used to take
- * an address. See detailed description of this relocation format and
- * semantics in comments to struct bpf_offset_reloc in libbpf_internal.h.
- *
- * This relocation allows libbpf to adjust BPF instruction to use correct
- * actual field offset, based on target kernel BTF type that matches original
- * (local) BTF, used to record relocation.
- */
-#define BPF_CORE_READ(dst, src)						\
-	bpf_probe_read((dst), sizeof(*(src)),				\
-		       __builtin_preserve_access_index(src))
-
-#endif
diff --git a/tools/testing/selftests/bpf/bpf_legacy.h b/tools/testing/selftests/bpf/bpf_legacy.h
new file mode 100644
index 000000000000..6f8988738bc1
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_legacy.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_LEGACY__
+#define __BPF_LEGACY__
+
+/*
+ * legacy bpf_map_def with extra fields supported only by bpf_load(), do not
+ * use outside of samples/bpf
+ */
+struct bpf_map_def_legacy {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+	unsigned int inner_map_idx;
+	unsigned int numa_node;
+};
+
+#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val)		\
+	struct ____btf_map_##name {				\
+		type_key key;					\
+		type_val value;					\
+	};							\
+	struct ____btf_map_##name				\
+	__attribute__ ((section(".maps." #name), used))		\
+		____btf_map_##name = { }
+
+/* llvm builtin functions that eBPF C program may use to
+ * emit BPF_LD_ABS and BPF_LD_IND instructions
+ */
+unsigned long long load_byte(void *skb,
+			     unsigned long long off) asm("llvm.bpf.load.byte");
+unsigned long long load_half(void *skb,
+			     unsigned long long off) asm("llvm.bpf.load.half");
+unsigned long long load_word(void *skb,
+			     unsigned long long off) asm("llvm.bpf.load.word");
+
+#endif
+
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index e95c33e333a4..0fb910df5387 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -41,7 +41,7 @@
  *
  * If successful, 0 is returned.
  */
-int enable_all_controllers(char *cgroup_path)
+static int enable_all_controllers(char *cgroup_path)
 {
 	char path[PATH_MAX + 1];
 	char buf[PATH_MAX];
@@ -98,7 +98,7 @@ int enable_all_controllers(char *cgroup_path)
  */
 int setup_cgroup_environment(void)
 {
-	char cgroup_workdir[PATH_MAX + 1];
+	char cgroup_workdir[PATH_MAX - 24];
 
 	format_cgroup_path(cgroup_workdir, "");
 
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 5ecc267d98b0..4f50d32c4abb 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -1,6 +1,24 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
+#define EMBED_FILE(NAME, PATH)						    \
+asm (									    \
+"      .pushsection \".rodata\", \"a\", @progbits              \n"	    \
+"      .global "#NAME"_data                                    \n"	    \
+#NAME"_data:                                                   \n"	    \
+"      .incbin \"" PATH "\"                                    \n"	    \
+#NAME"_data_end:                                               \n"	    \
+"      .global "#NAME"_size                                    \n"	    \
+"      .type "#NAME"_size, @object                             \n"	    \
+"      .size "#NAME"_size, 4                                   \n"	    \
+"      .align 4,                                               \n"	    \
+#NAME"_size:                                                   \n"	    \
+"      .int "#NAME"_data_end - "#NAME"_data                    \n"	    \
+"      .popsection                                             \n"	    \
+);									    \
+extern char NAME##_data[];						    \
+extern int NAME##_size;
+
 ssize_t get_base_addr() {
 	size_t start;
 	char buf[256];
@@ -21,6 +39,8 @@ ssize_t get_base_addr() {
 	return -EINVAL;
 }
 
+EMBED_FILE(probe, "test_attach_probe.o");
+
 void test_attach_probe(void)
 {
 	const char *kprobe_name = "kprobe/sys_nanosleep";
@@ -29,11 +49,15 @@ void test_attach_probe(void)
 	const char *uretprobe_name = "uretprobe/trigger_func";
 	const int kprobe_idx = 0, kretprobe_idx = 1;
 	const int uprobe_idx = 2, uretprobe_idx = 3;
-	const char *file = "./test_attach_probe.o";
+	const char *obj_name = "attach_probe";
+	LIBBPF_OPTS(bpf_object_open_opts, open_opts,
+		.object_name = obj_name,
+		.relaxed_maps = true,
+	);
 	struct bpf_program *kprobe_prog, *kretprobe_prog;
 	struct bpf_program *uprobe_prog, *uretprobe_prog;
 	struct bpf_object *obj;
-	int err, prog_fd, duration = 0, res;
+	int err, duration = 0, res;
 	struct bpf_link *kprobe_link = NULL;
 	struct bpf_link *kretprobe_link = NULL;
 	struct bpf_link *uprobe_link = NULL;
@@ -48,11 +72,16 @@ void test_attach_probe(void)
 		return;
 	uprobe_offset = (size_t)&get_base_addr - base_addr;
 
-	/* load programs */
-	err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
-	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+	/* open object */
+	obj = bpf_object__open_mem(probe_data, probe_size, &open_opts);
+	if (CHECK(IS_ERR(obj), "obj_open_mem", "err %ld\n", PTR_ERR(obj)))
 		return;
 
+	if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name",
+		  "wrong obj name '%s', expected '%s'\n",
+		  bpf_object__name(obj), obj_name))
+		goto cleanup;
+
 	kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
 	if (CHECK(!kprobe_prog, "find_probe",
 		  "prog '%s' not found\n", kprobe_name))
@@ -70,6 +99,16 @@ void test_attach_probe(void)
 		  "prog '%s' not found\n", uretprobe_name))
 		goto cleanup;
 
+	bpf_program__set_kprobe(kprobe_prog);
+	bpf_program__set_kprobe(kretprobe_prog);
+	bpf_program__set_kprobe(uprobe_prog);
+	bpf_program__set_kprobe(uretprobe_prog);
+
+	/* create maps && load programs */
+	err = bpf_object__load(obj);
+	if (CHECK(err, "obj_load", "err %d\n", err))
+		goto cleanup;
+
 	/* load maps */
 	results_map_fd = bpf_find_map(__func__, obj, "results_map");
 	if (CHECK(results_map_fd < 0, "find_results_map",
diff --git a/tools/testing/selftests/bpf/test_btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 6e75dd3cb14f..7390d3061065 100644
--- a/tools/testing/selftests/bpf/test_btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -1,36 +1,26 @@
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <errno.h>
-#include <linux/err.h>
-#include <btf.h>
-
-#define CHECK(condition, format...) ({					\
-	int __ret = !!(condition);					\
-	if (__ret) {							\
-		fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__);	\
-		fprintf(stderr, format);				\
-	}								\
-	__ret;								\
-})
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static int duration = 0;
 
 void btf_dump_printf(void *ctx, const char *fmt, va_list args)
 {
 	vfprintf(ctx, fmt, args);
 }
 
-struct btf_dump_test_case {
+static struct btf_dump_test_case {
 	const char *name;
+	const char *file;
 	struct btf_dump_opts opts;
 } btf_dump_test_cases[] = {
-	{.name = "btf_dump_test_case_syntax", .opts = {}},
-	{.name = "btf_dump_test_case_ordering", .opts = {}},
-	{.name = "btf_dump_test_case_padding", .opts = {}},
-	{.name = "btf_dump_test_case_packing", .opts = {}},
-	{.name = "btf_dump_test_case_bitfields", .opts = {}},
-	{.name = "btf_dump_test_case_multidim", .opts = {}},
-	{.name = "btf_dump_test_case_namespacing", .opts = {}},
+	{"btf_dump: syntax", "btf_dump_test_case_syntax", {}},
+	{"btf_dump: ordering", "btf_dump_test_case_ordering", {}},
+	{"btf_dump: padding", "btf_dump_test_case_padding", {}},
+	{"btf_dump: packing", "btf_dump_test_case_packing", {}},
+	{"btf_dump: bitfields", "btf_dump_test_case_bitfields", {}},
+	{"btf_dump: multidim", "btf_dump_test_case_multidim", {}},
+	{"btf_dump: namespacing", "btf_dump_test_case_namespacing", {}},
 };
 
 static int btf_dump_all_types(const struct btf *btf,
@@ -55,55 +45,51 @@ done:
 	return err;
 }
 
-int test_btf_dump_case(int n, struct btf_dump_test_case *test_case)
+static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
 {
 	char test_file[256], out_file[256], diff_cmd[1024];
 	struct btf *btf = NULL;
 	int err = 0, fd = -1;
 	FILE *f = NULL;
 
-	fprintf(stderr, "Test case #%d (%s): ", n, test_case->name);
-
-	snprintf(test_file, sizeof(test_file), "%s.o", test_case->name);
+	snprintf(test_file, sizeof(test_file), "%s.o", t->file);
 
 	btf = btf__parse_elf(test_file, NULL);
-	if (CHECK(IS_ERR(btf),
+	if (CHECK(IS_ERR(btf), "btf_parse_elf",
 	    "failed to load test BTF: %ld\n", PTR_ERR(btf))) {
 		err = -PTR_ERR(btf);
 		btf = NULL;
 		goto done;
 	}
 
-	snprintf(out_file, sizeof(out_file),
-		 "/tmp/%s.output.XXXXXX", test_case->name);
+	snprintf(out_file, sizeof(out_file), "/tmp/%s.output.XXXXXX", t->file);
 	fd = mkstemp(out_file);
-	if (CHECK(fd < 0, "failed to create temp output file: %d\n", fd)) {
+	if (CHECK(fd < 0, "create_tmp", "failed to create file: %d\n", fd)) {
 		err = fd;
 		goto done;
 	}
 	f = fdopen(fd, "w");
-	if (CHECK(f == NULL, "failed to open temp output file: %s(%d)\n",
+	if (CHECK(f == NULL, "open_tmp",  "failed to open file: %s(%d)\n",
 		  strerror(errno), errno)) {
 		close(fd);
 		goto done;
 	}
 
-	test_case->opts.ctx = f;
-	err = btf_dump_all_types(btf, &test_case->opts);
+	t->opts.ctx = f;
+	err = btf_dump_all_types(btf, &t->opts);
 	fclose(f);
 	close(fd);
-	if (CHECK(err, "failure during C dumping: %d\n", err)) {
+	if (CHECK(err, "btf_dump", "failure during C dumping: %d\n", err)) {
 		goto done;
 	}
 
-	snprintf(test_file, sizeof(test_file), "progs/%s.c", test_case->name);
+	snprintf(test_file, sizeof(test_file), "progs/%s.c", t->file);
 	if (access(test_file, R_OK) == -1)
 		/*
 		 * When the test is run with O=, kselftest copies TEST_FILES
 		 * without preserving the directory structure.
 		 */
-		snprintf(test_file, sizeof(test_file), "%s.c",
-			test_case->name);
+		snprintf(test_file, sizeof(test_file), "%s.c", t->file);
 	/*
 	 * Diff test output and expected test output, contained between
 	 * START-EXPECTED-OUTPUT and END-EXPECTED-OUTPUT lines in test case.
@@ -118,33 +104,27 @@ int test_btf_dump_case(int n, struct btf_dump_test_case *test_case)
 		 "out {sub(/^[ \\t]*\\*/, \"\"); print}' '%s' | diff -u - '%s'",
 		 test_file, out_file);
 	err = system(diff_cmd);
-	if (CHECK(err,
+	if (CHECK(err, "diff",
 		  "differing test output, output=%s, err=%d, diff cmd:\n%s\n",
 		  out_file, err, diff_cmd))
 		goto done;
 
 	remove(out_file);
-	fprintf(stderr, "OK\n");
 
 done:
 	btf__free(btf);
 	return err;
 }
 
-int main() {
-	int test_case_cnt, i, err, failed = 0;
-
-	test_case_cnt = sizeof(btf_dump_test_cases) /
-			sizeof(btf_dump_test_cases[0]);
+void test_btf_dump() {
+	int i;
 
-	for (i = 0; i < test_case_cnt; i++) {
-		err = test_btf_dump_case(i, &btf_dump_test_cases[i]);
-		if (err)
-			failed++;
-	}
+	for (i = 0; i < ARRAY_SIZE(btf_dump_test_cases); i++) {
+		struct btf_dump_test_case *t = &btf_dump_test_cases[i];
 
-	fprintf(stderr, "%d tests succeeded, %d tests failed.\n",
-		test_case_cnt - failed, failed);
+		if (!test__start_subtest(t->name))
+			continue;
 
-	return failed;
+		 test_btf_dump_case(i, &btf_dump_test_cases[i]);
+	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index f3863f976a48..21a0dff66241 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -193,8 +193,12 @@ static struct core_reloc_test_case test_cases[] = {
 		.btf_src_file = NULL, /* load from /lib/modules/$(uname -r) */
 		.input = "",
 		.input_len = 0,
-		.output = "\1", /* true */
-		.output_len = 1,
+		.output = STRUCT_TO_CHAR_PTR(core_reloc_kernel_output) {
+			.valid = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, },
+			.comm = "test_progs\0\0\0\0\0",
+			.comm_len = 11,
+		},
+		.output_len = sizeof(struct core_reloc_kernel_output),
 	},
 
 	/* validate BPF program can use multiple flavors to match against
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
new file mode 100644
index 000000000000..777faffc4639
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that the flow_dissector program can be updated with a single
+ * syscall by attaching a new program that replaces the existing one.
+ *
+ * Corner case - the same program cannot be attached twice.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <unistd.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+
+#include "test_progs.h"
+
+static bool is_attached(int netns)
+{
+	__u32 cnt;
+	int err;
+
+	err = bpf_prog_query(netns, BPF_FLOW_DISSECTOR, 0, NULL, NULL, &cnt);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_query");
+		return true; /* fail-safe */
+	}
+
+	return cnt > 0;
+}
+
+static int load_prog(void)
+{
+	struct bpf_insn prog[] = {
+		BPF_MOV64_IMM(BPF_REG_0, BPF_OK),
+		BPF_EXIT_INSN(),
+	};
+	int fd;
+
+	fd = bpf_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog,
+			      ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
+	if (CHECK_FAIL(fd < 0))
+		perror("bpf_load_program");
+
+	return fd;
+}
+
+static void do_flow_dissector_reattach(void)
+{
+	int prog_fd[2] = { -1, -1 };
+	int err;
+
+	prog_fd[0] = load_prog();
+	if (prog_fd[0] < 0)
+		return;
+
+	prog_fd[1] = load_prog();
+	if (prog_fd[1] < 0)
+		goto out_close;
+
+	err = bpf_prog_attach(prog_fd[0], 0, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach-0");
+		goto out_close;
+	}
+
+	/* Expect success when attaching a different program */
+	err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach-1");
+		goto out_detach;
+	}
+
+	/* Expect failure when attaching the same program twice */
+	err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK_FAIL(!err || errno != EINVAL))
+		perror("bpf_prog_attach-2");
+
+out_detach:
+	err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+	if (CHECK_FAIL(err))
+		perror("bpf_prog_detach");
+
+out_close:
+	close(prog_fd[1]);
+	close(prog_fd[0]);
+}
+
+void test_flow_dissector_reattach(void)
+{
+	int init_net, err;
+
+	init_net = open("/proc/1/ns/net", O_RDONLY);
+	if (CHECK_FAIL(init_net < 0)) {
+		perror("open(/proc/1/ns/net)");
+		return;
+	}
+
+	err = setns(init_net, CLONE_NEWNET);
+	if (CHECK_FAIL(err)) {
+		perror("setns(/proc/1/ns/net)");
+		goto out_close;
+	}
+
+	if (is_attached(init_net)) {
+		test__skip();
+		printf("Can't test with flow dissector attached to init_net\n");
+		return;
+	}
+
+	/* First run tests in root network namespace */
+	do_flow_dissector_reattach();
+
+	/* Then repeat tests in a non-root namespace */
+	err = unshare(CLONE_NEWNET);
+	if (CHECK_FAIL(err)) {
+		perror("unshare(CLONE_NEWNET)");
+		goto out_close;
+	}
+	do_flow_dissector_reattach();
+
+out_close:
+	close(init_net);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
new file mode 100644
index 000000000000..9bf9de0aaeea
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+struct bss {
+	unsigned did_run;
+	unsigned iters;
+	unsigned sum;
+};
+
+struct rdonly_map_subtest {
+	const char *subtest_name;
+	const char *prog_name;
+	unsigned exp_iters;
+	unsigned exp_sum;
+};
+
+void test_rdonly_maps(void)
+{
+	const char *prog_name_skip_loop = "raw_tracepoint/sys_enter:skip_loop";
+	const char *prog_name_part_loop = "raw_tracepoint/sys_enter:part_loop";
+	const char *prog_name_full_loop = "raw_tracepoint/sys_enter:full_loop";
+	const char *file = "test_rdonly_maps.o";
+	struct rdonly_map_subtest subtests[] = {
+		{ "skip loop", prog_name_skip_loop, 0, 0 },
+		{ "part loop", prog_name_part_loop, 3, 2 + 3 + 4 },
+		{ "full loop", prog_name_full_loop, 4, 2 + 3 + 4 + 5 },
+	};
+	int i, err, zero = 0, duration = 0;
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct bpf_map *bss_map;
+	struct bpf_object *obj;
+	struct bss bss;
+
+	obj = bpf_object__open_file(file, NULL);
+	if (CHECK(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj)))
+		return;
+
+	bpf_object__for_each_program(prog, obj) {
+		bpf_program__set_raw_tracepoint(prog);
+	}
+
+	err = bpf_object__load(obj);
+	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
+		goto cleanup;
+
+	bss_map = bpf_object__find_map_by_name(obj, "test_rdo.bss");
+	if (CHECK(!bss_map, "find_bss_map", "failed\n"))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(subtests); i++) {
+		const struct rdonly_map_subtest *t = &subtests[i];
+
+		if (!test__start_subtest(t->subtest_name))
+			continue;
+
+		prog = bpf_object__find_program_by_title(obj, t->prog_name);
+		if (CHECK(!prog, "find_prog", "prog '%s' not found\n",
+			  t->prog_name))
+			goto cleanup;
+
+		memset(&bss, 0, sizeof(bss));
+		err = bpf_map_update_elem(bpf_map__fd(bss_map), &zero, &bss, 0);
+		if (CHECK(err, "set_bss", "failed to set bss data: %d\n", err))
+			goto cleanup;
+
+		link = bpf_program__attach_raw_tracepoint(prog, "sys_enter");
+		if (CHECK(IS_ERR(link), "attach_prog", "prog '%s', err %ld\n",
+			  t->prog_name, PTR_ERR(link))) {
+			link = NULL;
+			goto cleanup;
+		}
+
+		/* trigger probe */
+		usleep(1);
+
+		bpf_link__destroy(link);
+		link = NULL;
+
+		err = bpf_map_lookup_elem(bpf_map__fd(bss_map), &zero, &bss);
+		if (CHECK(err, "get_bss", "failed to get bss data: %d\n", err))
+			goto cleanup;
+		if (CHECK(bss.did_run == 0, "check_run",
+			  "prog '%s' didn't run?\n", t->prog_name))
+			goto cleanup;
+		if (CHECK(bss.iters != t->exp_iters, "check_iters",
+			  "prog '%s' iters: %d, expected: %d\n",
+			  t->prog_name, bss.iters, t->exp_iters))
+			goto cleanup;
+		if (CHECK(bss.sum != t->exp_sum, "check_sum",
+			  "prog '%s' sum: %d, expected: %d\n",
+			  t->prog_name, bss.sum, t->exp_sum))
+			goto cleanup;
+	}
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
index 5c78e2b5a917..86cee820d4d3 100644
--- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
+++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
@@ -3,16 +3,26 @@
 
 void test_reference_tracking(void)
 {
-	const char *file = "./test_sk_lookup_kern.o";
+	const char *file = "test_sk_lookup_kern.o";
+	const char *obj_name = "ref_track";
+	LIBBPF_OPTS(bpf_object_open_opts, open_opts,
+		.object_name = obj_name,
+		.relaxed_maps = true,
+	);
 	struct bpf_object *obj;
 	struct bpf_program *prog;
 	__u32 duration = 0;
 	int err = 0;
 
-	obj = bpf_object__open(file);
+	obj = bpf_object__open_file(file, &open_opts);
 	if (CHECK_FAIL(IS_ERR(obj)))
 		return;
 
+	if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name",
+		  "wrong obj name '%s', expected '%s'\n",
+		  bpf_object__name(obj), obj_name))
+		goto cleanup;
+
 	bpf_object__for_each_program(prog, obj) {
 		const char *title;
 
@@ -35,5 +45,7 @@ void test_reference_tracking(void)
 		}
 		CHECK(err, title, "\n");
 	}
+
+cleanup:
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
index 3a62119c7498..35c512818a56 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
@@ -62,6 +62,10 @@ struct padded_a_lot {
  *	long: 64;
  *	long: 64;
  *	int b;
+ *	long: 32;
+ *	long: 64;
+ *	long: 64;
+ *	long: 64;
  *};
  *
  */
@@ -95,7 +99,6 @@ struct zone_padding {
 struct zone {
 	int a;
 	short b;
-	short: 16;
 	struct zone_padding __pad__;
 };
 
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index f686a8138d90..9a6bdeb4894c 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -1,5 +1,14 @@
 #include <stdint.h>
 #include <stdbool.h>
+/*
+ * KERNEL
+ */
+
+struct core_reloc_kernel_output {
+	int valid[10];
+	char comm[16];
+	int comm_len;
+};
 
 /*
  * FLAVORS
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index 7cdb7f878310..40ac722a9da5 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -7,6 +7,7 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index 9b2f808a2863..bb80f29aa7f7 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -7,6 +7,7 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index d727657d51e2..2b9165a7afe1 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -7,6 +7,7 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_tracing.h"
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index 9a3d1c79e6fe..1bafbb944e37 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -14,13 +14,12 @@ struct sockopt_sk {
 	__u8 val;
 };
 
-struct bpf_map_def SEC("maps") socket_storage_map = {
-	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct sockopt_sk),
-	.map_flags = BPF_F_NO_PREALLOC,
-};
-BPF_ANNOTATE_KV_PAIR(socket_storage_map, int, struct sockopt_sk);
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct sockopt_sk);
+} socket_storage_map SEC(".maps");
 
 SEC("cgroup/getsockopt")
 int _getsockopt(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c
index 233bdcb1659e..2cf813a06b83 100644
--- a/tools/testing/selftests/bpf/progs/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c
@@ -13,13 +13,12 @@ struct tcp_rtt_storage {
 	__u32 icsk_retransmits;
 };
 
-struct bpf_map_def SEC("maps") socket_storage_map = {
-	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.key_size = sizeof(int),
-	.value_size = sizeof(struct tcp_rtt_storage),
-	.map_flags = BPF_F_NO_PREALLOC,
-};
-BPF_ANNOTATE_KV_PAIR(socket_storage_map, int, struct tcp_rtt_storage);
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct tcp_rtt_storage);
+} socket_storage_map SEC(".maps");
 
 SEC("sockops")
 int _sockops(struct bpf_sock_ops *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index 63a8dfef893b..534621e38906 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -49,4 +49,3 @@ int handle_uprobe_return(struct pt_regs *ctx)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index e5c79fe0ffdb..763c51447c19 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2018 Facebook */
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index 5ee3622ddebb..96f9e8451029 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2018 Facebook */
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
+#include "bpf_legacy.h"
 
 int _version SEC("version") = 1;
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
index bf67f0fdf743..96b1f5f3b07a 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -31,6 +32,8 @@ struct core_reloc_arrays {
 	struct core_reloc_arrays_substruct d[1][2];
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_arrays(void *ctx)
 {
@@ -38,16 +41,16 @@ int test_core_arrays(void *ctx)
 	struct core_reloc_arrays_output *out = (void *)&data.out;
 
 	/* in->a[2] */
-	if (BPF_CORE_READ(&out->a2, &in->a[2]))
+	if (CORE_READ(&out->a2, &in->a[2]))
 		return 1;
 	/* in->b[1][2][3] */
-	if (BPF_CORE_READ(&out->b123, &in->b[1][2][3]))
+	if (CORE_READ(&out->b123, &in->b[1][2][3]))
 		return 1;
 	/* in->c[1].c */
-	if (BPF_CORE_READ(&out->c1c, &in->c[1].c))
+	if (CORE_READ(&out->c1c, &in->c[1].c))
 		return 1;
 	/* in->d[0][0].d */
-	if (BPF_CORE_READ(&out->d00d, &in->d[0][0].d))
+	if (CORE_READ(&out->d00d, &in->d[0][0].d))
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
index 9fda73e87972..71fd7cebc9d7 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -39,6 +40,8 @@ struct core_reloc_flavors___weird {
 	};
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_flavors(void *ctx)
 {
@@ -48,13 +51,13 @@ int test_core_flavors(void *ctx)
 	struct core_reloc_flavors *out = (void *)&data.out;
 
 	/* read a using weird layout */
-	if (BPF_CORE_READ(&out->a, &in_weird->a))
+	if (CORE_READ(&out->a, &in_weird->a))
 		return 1;
 	/* read b using reversed layout */
-	if (BPF_CORE_READ(&out->b, &in_rev->b))
+	if (CORE_READ(&out->b, &in_rev->b))
 		return 1;
 	/* read c using original layout */
-	if (BPF_CORE_READ(&out->c, &in_orig->c))
+	if (CORE_READ(&out->c, &in_orig->c))
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
index d99233c8008a..ad5c3f59c9c6 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -23,20 +24,22 @@ struct core_reloc_ints {
 	int64_t		s64_field;
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_ints(void *ctx)
 {
 	struct core_reloc_ints *in = (void *)&data.in;
 	struct core_reloc_ints *out = (void *)&data.out;
 
-	if (BPF_CORE_READ(&out->u8_field, &in->u8_field) ||
-	    BPF_CORE_READ(&out->s8_field, &in->s8_field) ||
-	    BPF_CORE_READ(&out->u16_field, &in->u16_field) ||
-	    BPF_CORE_READ(&out->s16_field, &in->s16_field) ||
-	    BPF_CORE_READ(&out->u32_field, &in->u32_field) ||
-	    BPF_CORE_READ(&out->s32_field, &in->s32_field) ||
-	    BPF_CORE_READ(&out->u64_field, &in->u64_field) ||
-	    BPF_CORE_READ(&out->s64_field, &in->s64_field))
+	if (CORE_READ(&out->u8_field, &in->u8_field) ||
+	    CORE_READ(&out->s8_field, &in->s8_field) ||
+	    CORE_READ(&out->u16_field, &in->u16_field) ||
+	    CORE_READ(&out->s16_field, &in->s16_field) ||
+	    CORE_READ(&out->u32_field, &in->u32_field) ||
+	    CORE_READ(&out->s32_field, &in->s32_field) ||
+	    CORE_READ(&out->u64_field, &in->u64_field) ||
+	    CORE_READ(&out->s64_field, &in->s64_field))
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
index 37e02aa3f0c8..50f609618b65 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -12,24 +13,78 @@ static volatile struct data {
 	char out[256];
 } data;
 
+struct core_reloc_kernel_output {
+	int valid[10];
+	char comm[16];
+	int comm_len;
+};
+
 struct task_struct {
 	int pid;
 	int tgid;
+	char comm[16];
+	struct task_struct *group_leader;
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_kernel(void *ctx)
 {
 	struct task_struct *task = (void *)bpf_get_current_task();
+	struct core_reloc_kernel_output *out = (void *)&data.out;
 	uint64_t pid_tgid = bpf_get_current_pid_tgid();
+	uint32_t real_tgid = (uint32_t)pid_tgid;
 	int pid, tgid;
 
-	if (BPF_CORE_READ(&pid, &task->pid) ||
-	    BPF_CORE_READ(&tgid, &task->tgid))
+	if (CORE_READ(&pid, &task->pid) ||
+	    CORE_READ(&tgid, &task->tgid))
 		return 1;
 
 	/* validate pid + tgid matches */
-	data.out[0] = (((uint64_t)pid << 32) | tgid) == pid_tgid;
+	out->valid[0] = (((uint64_t)pid << 32) | tgid) == pid_tgid;
+
+	/* test variadic BPF_CORE_READ macros */
+	out->valid[1] = BPF_CORE_READ(task,
+				      tgid) == real_tgid;
+	out->valid[2] = BPF_CORE_READ(task,
+				      group_leader,
+				      tgid) == real_tgid;
+	out->valid[3] = BPF_CORE_READ(task,
+				      group_leader, group_leader,
+				      tgid) == real_tgid;
+	out->valid[4] = BPF_CORE_READ(task,
+				      group_leader, group_leader, group_leader,
+				      tgid) == real_tgid;
+	out->valid[5] = BPF_CORE_READ(task,
+				      group_leader, group_leader, group_leader,
+				      group_leader,
+				      tgid) == real_tgid;
+	out->valid[6] = BPF_CORE_READ(task,
+				      group_leader, group_leader, group_leader,
+				      group_leader, group_leader,
+				      tgid) == real_tgid;
+	out->valid[7] = BPF_CORE_READ(task,
+				      group_leader, group_leader, group_leader,
+				      group_leader, group_leader, group_leader,
+				      tgid) == real_tgid;
+	out->valid[8] = BPF_CORE_READ(task,
+				      group_leader, group_leader, group_leader,
+				      group_leader, group_leader, group_leader,
+				      group_leader,
+				      tgid) == real_tgid;
+	out->valid[9] = BPF_CORE_READ(task,
+				      group_leader, group_leader, group_leader,
+				      group_leader, group_leader, group_leader,
+				      group_leader, group_leader,
+				      tgid) == real_tgid;
+
+	/* test BPF_CORE_READ_STR_INTO() returns correct code and contents */
+	out->comm_len = BPF_CORE_READ_STR_INTO(
+		&out->comm, task,
+		group_leader, group_leader, group_leader, group_leader,
+		group_leader, group_leader, group_leader, group_leader,
+		comm);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
index c59984bd3e23..1a36b0856653 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -32,6 +33,8 @@ struct core_reloc_misc_extensible {
 	int b;
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_misc(void *ctx)
 {
@@ -41,15 +44,15 @@ int test_core_misc(void *ctx)
 	struct core_reloc_misc_output *out = (void *)&data.out;
 
 	/* record two different relocations with the same accessor string */
-	if (BPF_CORE_READ(&out->a, &in_a->a1) ||	/* accessor: 0:0 */
-	    BPF_CORE_READ(&out->b, &in_b->b1))		/* accessor: 0:0 */
+	if (CORE_READ(&out->a, &in_a->a1) ||		/* accessor: 0:0 */
+	    CORE_READ(&out->b, &in_b->b1))		/* accessor: 0:0 */
 		return 1;
 
 	/* Validate relocations capture array-only accesses for structs with
 	 * fixed header, but with potentially extendable tail. This will read
 	 * first 4 bytes of 2nd element of in_ext array of potentially
 	 * variably sized struct core_reloc_misc_extensible. */ 
-	if (BPF_CORE_READ(&out->c, &in_ext[2]))		/* accessor: 2 */
+	if (CORE_READ(&out->c, &in_ext[2]))		/* accessor: 2 */
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
index f98b942c062b..3199fafede2c 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -41,20 +42,22 @@ struct core_reloc_mods {
 	core_reloc_mods_substruct_t h;
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_mods(void *ctx)
 {
 	struct core_reloc_mods *in = (void *)&data.in;
 	struct core_reloc_mods_output *out = (void *)&data.out;
 
-	if (BPF_CORE_READ(&out->a, &in->a) ||
-	    BPF_CORE_READ(&out->b, &in->b) ||
-	    BPF_CORE_READ(&out->c, &in->c) ||
-	    BPF_CORE_READ(&out->d, &in->d) ||
-	    BPF_CORE_READ(&out->e, &in->e[2]) ||
-	    BPF_CORE_READ(&out->f, &in->f[1]) ||
-	    BPF_CORE_READ(&out->g, &in->g.x) ||
-	    BPF_CORE_READ(&out->h, &in->h.y))
+	if (CORE_READ(&out->a, &in->a) ||
+	    CORE_READ(&out->b, &in->b) ||
+	    CORE_READ(&out->c, &in->c) ||
+	    CORE_READ(&out->d, &in->d) ||
+	    CORE_READ(&out->e, &in->e[2]) ||
+	    CORE_READ(&out->f, &in->f[1]) ||
+	    CORE_READ(&out->g, &in->g.x) ||
+	    CORE_READ(&out->h, &in->h.y))
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
index 3ca30cec2b39..98238cb64fbd 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -30,15 +31,17 @@ struct core_reloc_nesting {
 	} b;
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_nesting(void *ctx)
 {
 	struct core_reloc_nesting *in = (void *)&data.in;
 	struct core_reloc_nesting *out = (void *)&data.out;
 
-	if (BPF_CORE_READ(&out->a.a.a, &in->a.a.a))
+	if (CORE_READ(&out->a.a.a, &in->a.a.a))
 		return 1;
-	if (BPF_CORE_READ(&out->b.b.b, &in->b.b.b))
+	if (CORE_READ(&out->b.b.b, &in->b.b.b))
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
index add52f23ab35..4f3ecb9127bb 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -25,17 +26,19 @@ struct core_reloc_primitives {
 	int (*f)(const char *);
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_primitives(void *ctx)
 {
 	struct core_reloc_primitives *in = (void *)&data.in;
 	struct core_reloc_primitives *out = (void *)&data.out;
 
-	if (BPF_CORE_READ(&out->a, &in->a) ||
-	    BPF_CORE_READ(&out->b, &in->b) ||
-	    BPF_CORE_READ(&out->c, &in->c) ||
-	    BPF_CORE_READ(&out->d, &in->d) ||
-	    BPF_CORE_READ(&out->f, &in->f))
+	if (CORE_READ(&out->a, &in->a) ||
+	    CORE_READ(&out->b, &in->b) ||
+	    CORE_READ(&out->c, &in->c) ||
+	    CORE_READ(&out->d, &in->d) ||
+	    CORE_READ(&out->f, &in->f))
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
index 526b7ddc7ea1..27f602f00419 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <stdint.h>
 #include "bpf_helpers.h"
+#include "bpf_core_read.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -16,13 +17,15 @@ struct core_reloc_ptr_as_arr {
 	int a;
 };
 
+#define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+
 SEC("raw_tracepoint/sys_enter")
 int test_core_ptr_as_arr(void *ctx)
 {
 	struct core_reloc_ptr_as_arr *in = (void *)&data.in;
 	struct core_reloc_ptr_as_arr *out = (void *)&data.out;
 
-	if (BPF_CORE_READ(&out->a, &in[2].a))
+	if (CORE_READ(&out->a, &in[2].a))
 		return 1;
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index f8ffa3f3d44b..6a4a8f57f174 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -47,12 +47,11 @@ struct {
  * issue and avoid complicated C programming massaging.
  * This is an acceptable workaround since there is one entry here.
  */
-typedef __u64 raw_stack_trace_t[2 * MAX_STACK_RAWTP];
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 1);
 	__type(key, __u32);
-	__type(value, raw_stack_trace_t);
+	__type(value, __u64[2 * MAX_STACK_RAWTP]);
 } rawdata_map SEC(".maps");
 
 SEC("raw_tracepoint/sys_enter")
@@ -100,4 +99,3 @@ int bpf_prog1(void *ctx)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index 876c27deb65a..07c09ca5546a 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -22,4 +22,3 @@ int handle_sys_nanosleep_entry(struct pt_regs *ctx)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
new file mode 100644
index 000000000000..52d94e8b214d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+static volatile const struct {
+	unsigned a[4];
+	/*
+	 * if the struct's size is multiple of 16, compiler will put it into
+	 * .rodata.cst16 section, which is not recognized by libbpf; work
+	 * around this by ensuring we don't have 16-aligned struct
+	 */
+	char _y;
+} rdonly_values = { .a = {2, 3, 4, 5} };
+
+static volatile struct {
+	unsigned did_run;
+	unsigned iters;
+	unsigned sum;
+} res;
+
+SEC("raw_tracepoint/sys_enter:skip_loop")
+int skip_loop(struct pt_regs *ctx)
+{
+	/* prevent compiler to optimize everything out */
+	unsigned * volatile p = (void *)&rdonly_values.a;
+	unsigned iters = 0, sum = 0;
+
+	/* we should never enter this loop */
+	while (*p & 1) {
+		iters++;
+		sum += *p;
+		p++;
+	}
+	res.did_run = 1;
+	res.iters = iters;
+	res.sum = sum;
+	return 0;
+}
+
+SEC("raw_tracepoint/sys_enter:part_loop")
+int part_loop(struct pt_regs *ctx)
+{
+	/* prevent compiler to optimize everything out */
+	unsigned * volatile p = (void *)&rdonly_values.a;
+	unsigned iters = 0, sum = 0;
+
+	/* validate verifier can derive loop termination */
+	while (*p < 5) {
+		iters++;
+		sum += *p;
+		p++;
+	}
+	res.did_run = 1;
+	res.iters = iters;
+	res.sum = sum;
+	return 0;
+}
+
+SEC("raw_tracepoint/sys_enter:full_loop")
+int full_loop(struct pt_regs *ctx)
+{
+	/* prevent compiler to optimize everything out */
+	unsigned * volatile p = (void *)&rdonly_values.a;
+	int i = sizeof(rdonly_values.a) / sizeof(rdonly_values.a[0]);
+	unsigned iters = 0, sum = 0;
+
+	/* validate verifier can allow full loop as well */
+	while (i > 0 ) {
+		iters++;
+		sum += *p;
+		p++;
+		i--;
+	}
+	res.did_run = 1;
+	res.iters = iters;
+	res.sum = sum;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index fa0be3e10a10..3b7e1dca8829 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -74,4 +74,3 @@ int oncpu(struct sched_switch_args *ctx)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
index d23d4da66b83..2c3a25d64faf 100755
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -18,19 +18,55 @@ fi
 # this is the case and run it with in_netns.sh if it is being run in the root
 # namespace.
 if [[ -z $(ip netns identify $$) ]]; then
+	err=0
+	if bpftool="$(which bpftool)"; then
+		echo "Testing global flow dissector..."
+
+		$bpftool prog loadall ./bpf_flow.o /sys/fs/bpf/flow \
+			type flow_dissector
+
+		if ! unshare --net $bpftool prog attach pinned \
+			/sys/fs/bpf/flow/flow_dissector flow_dissector; then
+			echo "Unexpected unsuccessful attach in namespace" >&2
+			err=1
+		fi
+
+		$bpftool prog attach pinned /sys/fs/bpf/flow/flow_dissector \
+			flow_dissector
+
+		if unshare --net $bpftool prog attach pinned \
+			/sys/fs/bpf/flow/flow_dissector flow_dissector; then
+			echo "Unexpected successful attach in namespace" >&2
+			err=1
+		fi
+
+		if ! $bpftool prog detach pinned \
+			/sys/fs/bpf/flow/flow_dissector flow_dissector; then
+			echo "Failed to detach flow dissector" >&2
+			err=1
+		fi
+
+		rm -rf /sys/fs/bpf/flow
+	else
+		echo "Skipping root flow dissector test, bpftool not found" >&2
+	fi
+
+	# Run the rest of the tests in a net namespace.
 	../net/in_netns.sh "$0" "$@"
-	exit $?
-fi
+	err=$(( $err + $? ))
 
-# Determine selftest success via shell exit code
-exit_handler()
-{
-	if (( $? == 0 )); then
+	if (( $err == 0 )); then
 		echo "selftests: $TESTNAME [PASS]";
 	else
 		echo "selftests: $TESTNAME [FAILED]";
 	fi
 
+	exit $err
+fi
+
+# Determine selftest success via shell exit code
+exit_handler()
+{
 	set +e
 
 	# Cleanup
diff --git a/tools/testing/selftests/bpf/verifier/loops1.c b/tools/testing/selftests/bpf/verifier/loops1.c
index 1fc4e61e9f9f..1af37187dc12 100644
--- a/tools/testing/selftests/bpf/verifier/loops1.c
+++ b/tools/testing/selftests/bpf/verifier/loops1.c
@@ -187,3 +187,20 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.retval = 55,
 },
+{
+	"taken loop with back jump to 1st insn, 2",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_1, 10),
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+	BPF_JMP32_IMM(BPF_JNE, BPF_REG_1, 0, -3),
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.retval = 55,
+},